diff --git a/Documentation/ABI/stable/sysfs-driver-mlxreg-io b/Documentation/ABI/stable/sysfs-driver-mlxreg-io index 8ca498447aeb..05601a90a9b6 100644 --- a/Documentation/ABI/stable/sysfs-driver-mlxreg-io +++ b/Documentation/ABI/stable/sysfs-driver-mlxreg-io @@ -29,13 +29,13 @@ Description: This file shows the system fans direction: The files are read only. -What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/jtag_enable +What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/cpld3_version Date: November 2018 KernelVersion: 5.0 Contact: Vadim Pasternak Description: These files show with which CPLD versions have been burned - on LED board. + on LED or Gearbox board. The files are read only. @@ -121,6 +121,15 @@ Description: These files show the system reset cause, as following: ComEx The files are read only. +What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/cpld4_version +Date: November 2018 +KernelVersion: 5.0 +Contact: Vadim Pasternak +Description: These files show with which CPLD versions have been burned + on LED board. + + The files are read only. + Date: June 2019 KernelVersion: 5.3 Contact: Vadim Pasternak diff --git a/Documentation/ABI/testing/sysfs-bus-mei b/Documentation/ABI/testing/sysfs-bus-mei index 6bd45346ac7e..3f8701e8fa24 100644 --- a/Documentation/ABI/testing/sysfs-bus-mei +++ b/Documentation/ABI/testing/sysfs-bus-mei @@ -4,7 +4,7 @@ KernelVersion: 3.10 Contact: Samuel Ortiz linux-mei@linux.intel.com Description: Stores the same MODALIAS value emitted by uevent - Format: mei::: + Format: mei::: What: /sys/bus/mei/devices/.../name Date: May 2015 diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 5361ebec3361..5cdd45c11a3c 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1446,9 +1446,11 @@ IO The "io" controller regulates the distribution of IO resources. This controller implements both weight based and absolute bandwidth or IOPS -limit distribution; however, weight based distribution is available -only if cfq-iosched is in use and neither scheme is available for -blk-mq devices. +limit distribution. Weight based distribution is implemented by +either iocost controller or bfq IO scheduler. When bfq is selected as +the IO scheduler for any block device, iocost is disabled and bfq's +implementation overrides for all devices. If bfq is built as a kernel +module, unloading it re-enables iocost. IO Interface Files diff --git a/Documentation/admin-guide/device-mapper/index.rst b/Documentation/admin-guide/device-mapper/index.rst index c77c58b8f67b..d8dec8911eb3 100644 --- a/Documentation/admin-guide/device-mapper/index.rst +++ b/Documentation/admin-guide/device-mapper/index.rst @@ -8,6 +8,7 @@ Device Mapper cache-policies cache delay + dm-clone dm-crypt dm-flakey dm-init diff --git a/Documentation/admin-guide/hw-vuln/mds.rst b/Documentation/admin-guide/hw-vuln/mds.rst index e3a796c0d3a2..2d19c9f4c1fe 100644 --- a/Documentation/admin-guide/hw-vuln/mds.rst +++ b/Documentation/admin-guide/hw-vuln/mds.rst @@ -265,8 +265,11 @@ time with the option "mds=". The valid arguments for this option are: ============ ============================================================= -Not specifying this option is equivalent to "mds=full". - +Not specifying this option is equivalent to "mds=full". For processors +that are affected by both TAA (TSX Asynchronous Abort) and MDS, +specifying just "mds=off" without an accompanying "tsx_async_abort=off" +will have no effect as the same mitigation is used for both +vulnerabilities. Mitigation selection guide -------------------------- diff --git a/Documentation/admin-guide/hw-vuln/tsx_async_abort.rst b/Documentation/admin-guide/hw-vuln/tsx_async_abort.rst index fddbd7579c53..af6865b822d2 100644 --- a/Documentation/admin-guide/hw-vuln/tsx_async_abort.rst +++ b/Documentation/admin-guide/hw-vuln/tsx_async_abort.rst @@ -174,7 +174,10 @@ the option "tsx_async_abort=". The valid arguments for this option are: CPU is not vulnerable to cross-thread TAA attacks. ============ ============================================================= -Not specifying this option is equivalent to "tsx_async_abort=full". +Not specifying this option is equivalent to "tsx_async_abort=full". For +processors that are affected by both TAA and MDS, specifying just +"tsx_async_abort=off" without an accompanying "mds=off" will have no +effect as the same mitigation is used for both vulnerabilities. The kernel command line also allows to control the TSX feature using the parameter "tsx=" on CPUs which support TSX control. MSR_IA32_TSX_CTRL is used diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 8dee8f68fe15..5594c8bf1dcd 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -113,7 +113,7 @@ the GPE dispatcher. This facility can be used to prevent such uncontrolled GPE floodings. - Format: + Format: acpi_no_auto_serialize [HW,ACPI] Disable auto-serialization of AML methods @@ -2473,6 +2473,12 @@ SMT on vulnerable CPUs off - Unconditionally disable MDS mitigation + On TAA-affected machines, mds=off can be prevented by + an active TAA mitigation as both vulnerabilities are + mitigated with the same mechanism so in order to disable + this mitigation, you need to specify tsx_async_abort=off + too. + Not specifying this option is equivalent to mds=full. @@ -4931,6 +4937,11 @@ vulnerable to cross-thread TAA attacks. off - Unconditionally disable TAA mitigation + On MDS-affected machines, tsx_async_abort=off can be + prevented by an active MDS mitigation as both vulnerabilities + are mitigated with the same mechanism so in order to disable + this mitigation, you need to specify mds=off too. + Not specifying this option is equivalent to tsx_async_abort=full. On CPUs which are MDS affected and deploy MDS mitigation, TAA mitigation is not @@ -5090,13 +5101,13 @@ Flags is a set of characters, each corresponding to a common usb-storage quirk flag as follows: a = SANE_SENSE (collect more than 18 bytes - of sense data); + of sense data, not on uas); b = BAD_SENSE (don't collect more than 18 - bytes of sense data); + bytes of sense data, not on uas); c = FIX_CAPACITY (decrease the reported device capacity by one sector); d = NO_READ_DISC_INFO (don't use - READ_DISC_INFO command); + READ_DISC_INFO command, not on uas); e = NO_READ_CAPACITY_16 (don't use READ_CAPACITY_16 command); f = NO_REPORT_OPCODES (don't use report opcodes @@ -5111,17 +5122,18 @@ j = NO_REPORT_LUNS (don't use report luns command, uas only); l = NOT_LOCKABLE (don't try to lock and - unlock ejectable media); + unlock ejectable media, not on uas); m = MAX_SECTORS_64 (don't transfer more - than 64 sectors = 32 KB at a time); + than 64 sectors = 32 KB at a time, + not on uas); n = INITIAL_READ10 (force a retry of the - initial READ(10) command); + initial READ(10) command, not on uas); o = CAPACITY_OK (accept the capacity - reported by the device); + reported by the device, not on uas); p = WRITE_CACHE (the device cache is ON - by default); + by default, not on uas); r = IGNORE_RESIDUE (the device reports - bogus residue values); + bogus residue values, not on uas); s = SINGLE_LUN (the device has only one Logical Unit); t = NO_ATA_1X (don't allow ATA(12) and ATA(16) @@ -5130,7 +5142,8 @@ w = NO_WP_DETECT (don't test whether the medium is write-protected). y = ALWAYS_SYNC (issue a SYNCHRONIZE_CACHE - even if the device claims no cache) + even if the device claims no cache, + not on uas) Example: quirks=0419:aaf5:rl,0421:0433:rc user_debug= [KNL,ARM] diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst index 032c7cd3cede..97ea247cc43a 100644 --- a/Documentation/admin-guide/sysctl/kernel.rst +++ b/Documentation/admin-guide/sysctl/kernel.rst @@ -105,6 +105,7 @@ show up in /proc/sys/kernel: - unknown_nmi_panic - watchdog - watchdog_thresh +- yield_type - version @@ -1175,3 +1176,13 @@ is 10 seconds. The softlockup threshold is (2 * watchdog_thresh). Setting this tunable to zero will disable lockup detection altogether. + +yield_type: +=========== + +BMQ CPU scheduler only. This determines what type of yield calls to +sched_yield will perform. + + 0 - No yield. + 1 - Deboost and requeue task. (default) + 2 - Set run queue skip task. diff --git a/Documentation/block/bfq-iosched.rst b/Documentation/block/bfq-iosched.rst index 0d237d402860..8ecd37903391 100644 --- a/Documentation/block/bfq-iosched.rst +++ b/Documentation/block/bfq-iosched.rst @@ -536,12 +536,14 @@ process. To get proportional sharing of bandwidth with BFQ for a given device, BFQ must of course be the active scheduler for that device. -Within each group directory, the names of the files associated with -BFQ-specific cgroup parameters and stats begin with the "bfq." -prefix. So, with cgroups-v1 or cgroups-v2, the full prefix for -BFQ-specific files is "blkio.bfq." or "io.bfq." For example, the group -parameter to set the weight of a group with BFQ is blkio.bfq.weight -or io.bfq.weight. +The interface of the proportional-share policy implemented by BFQ +consists of a series of cgroup parameters. For legacy issues, each +parameter can be read or written, equivalently, through one of two +files: the first file has the same name as the parameter to +read/write, while the second file has that same name prepended by the +prefix "bfq.". For example, the two files by which to set/show the +weight of a group are blkio.weight and blkio.bfq.weight with +cgroups-v1, or io.weight and io.bfq.weight with cgroups-v2. As for cgroups-v1 (blkio controller), the exact set of stat files created, and kept up-to-date by bfq, depends on whether @@ -550,14 +552,15 @@ the stat files documented in Documentation/admin-guide/cgroup-v1/blkio-controller.rst. If, instead, CONFIG_BFQ_CGROUP_DEBUG is not set, then bfq creates only the files:: - blkio.bfq.io_service_bytes - blkio.bfq.io_service_bytes_recursive - blkio.bfq.io_serviced - blkio.bfq.io_serviced_recursive + blkio.io_service_bytes + blkio.io_service_bytes_recursive + blkio.io_serviced + blkio.io_serviced_recursive -The value of CONFIG_BFQ_CGROUP_DEBUG greatly influences the maximum -throughput sustainable with bfq, because updating the blkio.bfq.* -stats is rather costly, especially for some of the stats enabled by +(plus their counterparts with also the bfq prefix). The value of +CONFIG_BFQ_CGROUP_DEBUG greatly influences the maximum throughput +sustainable with BFQ, because updating the blkio.* stats is rather +costly, especially for some of the stats enabled by CONFIG_BFQ_CGROUP_DEBUG. Parameters to set @@ -565,11 +568,12 @@ Parameters to set For each group, there is only the following parameter to set. -weight (namely blkio.bfq.weight or io.bfq-weight): the weight of the -group inside its parent. Available values: 1..10000 (default 100). The -linear mapping between ioprio and weights, described at the beginning -of the tunable section, is still valid, but all weights higher than -IOPRIO_BE_NR*10 are mapped to ioprio 0. +weight (namely blkio.weight/blkio.bfq.weight or +io.weight/io.bfq.weight): the weight of the group inside its +parent. Available values: 1..10000 (default 100). The linear mapping +between ioprio and weights, described at the beginning of the tunable +section, is still valid, but all weights higher than IOPRIO_BE_NR*10 +are mapped to ioprio 0. Recall that, if low-latency is set, then BFQ automatically raises the weight of the queues associated with interactive and soft real-time diff --git a/Documentation/devicetree/bindings/Makefile b/Documentation/devicetree/bindings/Makefile index 5138a2f6232a..646cb3525373 100644 --- a/Documentation/devicetree/bindings/Makefile +++ b/Documentation/devicetree/bindings/Makefile @@ -12,7 +12,6 @@ $(obj)/%.example.dts: $(src)/%.yaml FORCE $(call if_changed,chk_binding) DT_TMP_SCHEMA := processed-schema.yaml -extra-y += $(DT_TMP_SCHEMA) quiet_cmd_mk_schema = SCHEMA $@ cmd_mk_schema = $(DT_MK_SCHEMA) $(DT_MK_SCHEMA_FLAGS) -o $@ $(real-prereqs) @@ -26,8 +25,12 @@ DT_DOCS = $(shell \ DT_SCHEMA_FILES ?= $(addprefix $(src)/,$(DT_DOCS)) +ifeq ($(CHECK_DTBS),) extra-y += $(patsubst $(src)/%.yaml,%.example.dts, $(DT_SCHEMA_FILES)) extra-y += $(patsubst $(src)/%.yaml,%.example.dt.yaml, $(DT_SCHEMA_FILES)) +endif $(obj)/$(DT_TMP_SCHEMA): $(DT_SCHEMA_FILES) FORCE $(call if_changed,mk_schema) + +extra-y += $(DT_TMP_SCHEMA) diff --git a/Documentation/devicetree/bindings/clock/renesas,rcar-usb2-clock-sel.txt b/Documentation/devicetree/bindings/clock/renesas,rcar-usb2-clock-sel.txt index e96e085271c1..83f6c6a7c41c 100644 --- a/Documentation/devicetree/bindings/clock/renesas,rcar-usb2-clock-sel.txt +++ b/Documentation/devicetree/bindings/clock/renesas,rcar-usb2-clock-sel.txt @@ -46,7 +46,7 @@ Required properties: Example (R-Car H3): usb2_clksel: clock-controller@e6590630 { - compatible = "renesas,r8a77950-rcar-usb2-clock-sel", + compatible = "renesas,r8a7795-rcar-usb2-clock-sel", "renesas,rcar-gen3-usb2-clock-sel"; reg = <0 0xe6590630 0 0x02>; clocks = <&cpg CPG_MOD 703>, <&usb_extal>, <&usb_xtal>; diff --git a/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.txt b/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.txt index ae661e65354e..f9499b20d840 100644 --- a/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.txt +++ b/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.txt @@ -81,6 +81,12 @@ Optional properties: Definition: Name of external front end module used. Some valid FEM names for example: "microsemi-lx5586", "sky85703-11" and "sky85803" etc. +- qcom,snoc-host-cap-8bit-quirk: + Usage: Optional + Value type: + Definition: Quirk specifying that the firmware expects the 8bit version + of the host capability QMI request + Example (to supply PCI based wifi block details): diff --git a/Documentation/devicetree/bindings/reset/brcm,brcmstb-reset.txt b/Documentation/devicetree/bindings/reset/brcm,brcmstb-reset.txt index 6e5341b4f891..ee59409640f2 100644 --- a/Documentation/devicetree/bindings/reset/brcm,brcmstb-reset.txt +++ b/Documentation/devicetree/bindings/reset/brcm,brcmstb-reset.txt @@ -22,6 +22,6 @@ Example: }; ðernet_switch { - resets = <&reset>; + resets = <&reset 26>; reset-names = "switch"; }; diff --git a/Documentation/devicetree/bindings/sound/mt8183-mt6358-ts3a227-max98357.txt b/Documentation/devicetree/bindings/sound/mt8183-mt6358-ts3a227-max98357.txt index d6d5207fa996..17ff3892f439 100644 --- a/Documentation/devicetree/bindings/sound/mt8183-mt6358-ts3a227-max98357.txt +++ b/Documentation/devicetree/bindings/sound/mt8183-mt6358-ts3a227-max98357.txt @@ -2,9 +2,11 @@ MT8183 with MT6358, TS3A227 and MAX98357 CODECS Required properties: - compatible : "mediatek,mt8183_mt6358_ts3a227_max98357" -- mediatek,headset-codec: the phandles of ts3a227 codecs - mediatek,platform: the phandle of MT8183 ASoC platform +Optional properties: +- mediatek,headset-codec: the phandles of ts3a227 codecs + Example: sound { diff --git a/Documentation/devicetree/writing-schema.rst b/Documentation/devicetree/writing-schema.rst index f4a638072262..83e04e5c342d 100644 --- a/Documentation/devicetree/writing-schema.rst +++ b/Documentation/devicetree/writing-schema.rst @@ -130,11 +130,13 @@ binding schema. All of the DT binding documents can be validated using the make dt_binding_check -In order to perform validation of DT source files, use the `dtbs_check` target:: +In order to perform validation of DT source files, use the ``dtbs_check`` target:: make dtbs_check -This will first run the `dt_binding_check` which generates the processed schema. +Note that ``dtbs_check`` will skip any binding schema files with errors. It is +necessary to use ``dt_binding_check`` to get all the validation errors in the +binding schema files. It is also possible to run checks with a single schema file by setting the ``DT_SCHEMA_FILES`` variable to a specific schema file. diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index 99ca040e3f90..d6bf97ee44bd 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -46,6 +46,7 @@ Table of Contents 3.10 /proc//timerslack_ns - Task timerslack value 3.11 /proc//patch_state - Livepatch patch operation state 3.12 /proc//arch_status - Task architecture specific information + 3.13 /proc//ksm - Remote KSM 4 Configuring procfs 4.1 Mount options @@ -2010,6 +2011,19 @@ x86 specific entries: the task is unlikely an AVX512 user, but depends on the workload and the scheduling scenario, it also could be a false negative mentioned above. +3.13 /proc//ksm - Remote KSM +-------------------------------------------- +This write-only file allows marking memory of another task for merging +and unmerging via KSM. + +The following actions are available: + + * mark task's memory as mergeable: + # echo merge > /proc//ksm + + * unmerging all the task's memory: + # echo unmerge > /proc//ksm + ------------------------------------------------------------------------------ Configuring procfs ------------------------------------------------------------------------------ diff --git a/Documentation/networking/j1939.rst b/Documentation/networking/j1939.rst index dc60b13fcd09..f5be243d250a 100644 --- a/Documentation/networking/j1939.rst +++ b/Documentation/networking/j1939.rst @@ -339,7 +339,7 @@ To claim an address following code example can be used: .pgn = J1939_PGN_ADDRESS_CLAIMED, .pgn_mask = J1939_PGN_PDU1_MAX, }, { - .pgn = J1939_PGN_ADDRESS_REQUEST, + .pgn = J1939_PGN_REQUEST, .pgn_mask = J1939_PGN_PDU1_MAX, }, { .pgn = J1939_PGN_ADDRESS_COMMANDED, diff --git a/Documentation/scheduler/sched-BMQ.txt b/Documentation/scheduler/sched-BMQ.txt new file mode 100644 index 000000000000..05c84eec0f31 --- /dev/null +++ b/Documentation/scheduler/sched-BMQ.txt @@ -0,0 +1,110 @@ + BitMap queue CPU Scheduler + -------------------------- + +CONTENT +======== + + Background + Design + Overview + Task policy + Priority management + BitMap Queue + CPU Assignment and Migration + + +Background +========== + +BitMap Queue CPU scheduler, referred to as BMQ from here on, is an evolution +of previous Priority and Deadline based Skiplist multiple queue scheduler(PDS), +and inspired by Zircon scheduler. The goal of it is to keep the scheduler code +simple, while efficiency and scalable for interactive tasks, such as desktop, +movie playback and gaming etc. + +Design +====== + +Overview +-------- + +BMQ use per CPU run queue design, each CPU(logical) has it's own run queue, +each CPU is responsible for scheduling the tasks that are putting into it's +run queue. + +The run queue is a set of priority queues. Note that these queues are fifo +queue for non-rt tasks or priority queue for rt tasks in data structure. See +BitMap Queue below for details. BMQ is optimized for non-rt tasks in the fact +that most applications are non-rt tasks. No matter the queue is fifo or +priority, In each queue is an ordered list of runnable tasks awaiting execution +and the data structures are the same. When it is time for a new task to run, +the scheduler simply looks the lowest numbered queueue that contains a task, +and runs the first task from the head of that queue. And per CPU idle task is +also in the run queue, so the scheduler can always find a task to run on from +its run queue. + +Each task will assigned the same timeslice(default 4ms) when it is picked to +start running. Task will be reinserted at the end of the appropriate priority +queue when it uses its whole timeslice. When the scheduler selects a new task +from the priority queue it sets the CPU's preemption timer for the remainder of +the previous timeslice. When that timer fires the scheduler will stop execution +on that task, select another task and start over again. + +If a task blocks waiting for a shared resource then it's taken out of its +priority queue and is placed in a wait queue for the shared resource. When it +is unblocked it will be reinserted in the appropriate priority queue of an +eligible CPU. + +Task policy +----------- + +BMQ supports DEADLINE, FIFO, RR, NORMAL, BATCH and IDLE task policy like the +mainline CFS scheduler. But BMQ is heavy optimized for non-rt task, that's +NORMAL/BATCH/IDLE policy tasks. Below is the implementation detail of each +policy. + +DEADLINE + It is squashed as priority 0 FIFO task. + +FIFO/RR + All RT tasks share one single priority queue in BMQ run queue designed. The +complexity of insert operation is O(n). BMQ is not designed for system runs +with major rt policy tasks. + +NORMAL/BATCH/IDLE + BATCH and IDLE tasks are treated as the same policy. They compete CPU with +NORMAL policy tasks, but they just don't boost. To control the priority of +NORMAL/BATCH/IDLE tasks, simply use nice level. + +ISO + ISO policy is not supported in BMQ. Please use nice level -20 NORMAL policy +task instead. + +Priority management +------------------- + +RT tasks have priority from 0-99. For non-rt tasks, there are three different +factors used to determine the effective priority of a task. The effective +priority being what is used to determine which queue it will be in. + +The first factor is simply the task’s static priority. Which is assigned from +task's nice level, within [-20, 19] in userland's point of view and [0, 39] +internally. + +The second factor is the priority boost. This is a value bounded between +[-MAX_PRIORITY_ADJ, MAX_PRIORITY_ADJ] used to offset the base priority, it is +modified by the following cases: + +*When a thread has used up its entire timeslice, always deboost its boost by +increasing by one. +*When a thread gives up cpu control(voluntary or non-voluntary) to reschedule, +and its switch-in time(time after last switch and run) below the thredhold +based on its priority boost, will boost its boost by decreasing by one buti is +capped at 0 (won’t go negative). + +The intent in this system is to ensure that interactive threads are serviced +quickly. These are usually the threads that interact directly with the user +and cause user-perceivable latency. These threads usually do little work and +spend most of their time blocked awaiting another user event. So they get the +priority boost from unblocking while background threads that do most of the +processing receive the priority penalty for using their entire timeslice. diff --git a/Documentation/scsi/smartpqi.txt b/Documentation/scsi/smartpqi.txt index 201f80c7c050..df129f55ace5 100644 --- a/Documentation/scsi/smartpqi.txt +++ b/Documentation/scsi/smartpqi.txt @@ -29,7 +29,7 @@ smartpqi specific entries in /sys smartpqi host attributes: ------------------------- /sys/class/scsi_host/host*/rescan - /sys/class/scsi_host/host*/version + /sys/class/scsi_host/host*/driver_version The host rescan attribute is a write only attribute. Writing to this attribute will trigger the driver to scan for new, changed, or removed diff --git a/MAINTAINERS b/MAINTAINERS index 9d3a5c54a41d..4f7ac27d8651 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6973,6 +6973,7 @@ L: linux-acpi@vger.kernel.org S: Maintained F: Documentation/firmware-guide/acpi/gpio-properties.rst F: drivers/gpio/gpiolib-acpi.c +F: drivers/gpio/gpiolib-acpi.h GPIO IR Transmitter M: Sean Young diff --git a/Makefile b/Makefile index d4d36c61940b..65726e7d68cb 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 4 SUBLEVEL = 0 -EXTRAVERSION = +EXTRAVERSION = -pf6 NAME = Kleptomaniac Octopus # *DOCUMENTATION* diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 8a50efb559f3..39002d769d95 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -73,6 +73,7 @@ config ARM select HAVE_ARM_SMCCC if CPU_V7 select HAVE_EBPF_JIT if !CPU_ENDIAN_BE32 select HAVE_CONTEXT_TRACKING + select HAVE_COPY_THREAD_TLS select HAVE_C_RECORDMCOUNT select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS if MMU diff --git a/arch/arm/boot/compressed/libfdt_env.h b/arch/arm/boot/compressed/libfdt_env.h index b36c0289a308..6a0f1f524466 100644 --- a/arch/arm/boot/compressed/libfdt_env.h +++ b/arch/arm/boot/compressed/libfdt_env.h @@ -2,11 +2,13 @@ #ifndef _ARM_LIBFDT_ENV_H #define _ARM_LIBFDT_ENV_H +#include #include #include #include -#define INT_MAX ((int)(~0U>>1)) +#define INT32_MAX S32_MAX +#define UINT32_MAX U32_MAX typedef __be16 fdt16_t; typedef __be32 fdt32_t; diff --git a/arch/arm/boot/dts/am335x-sancloud-bbe.dts b/arch/arm/boot/dts/am335x-sancloud-bbe.dts index 8678e6e35493..e5fdb7abb0d5 100644 --- a/arch/arm/boot/dts/am335x-sancloud-bbe.dts +++ b/arch/arm/boot/dts/am335x-sancloud-bbe.dts @@ -108,7 +108,7 @@ &cpsw_emac0 { phy-handle = <ðphy0>; - phy-mode = "rgmii-txid"; + phy-mode = "rgmii-id"; }; &i2c0 { diff --git a/arch/arm/boot/dts/am437x-gp-evm.dts b/arch/arm/boot/dts/am437x-gp-evm.dts index cae4500194fe..811c8cae315b 100644 --- a/arch/arm/boot/dts/am437x-gp-evm.dts +++ b/arch/arm/boot/dts/am437x-gp-evm.dts @@ -86,7 +86,7 @@ }; lcd0: display { - compatible = "osddisplays,osd057T0559-34ts", "panel-dpi"; + compatible = "osddisplays,osd070t1718-19ts", "panel-dpi"; label = "lcd"; backlight = <&lcd_bl>; diff --git a/arch/arm/boot/dts/am43x-epos-evm.dts b/arch/arm/boot/dts/am43x-epos-evm.dts index 95314121d111..078cb473fa7d 100644 --- a/arch/arm/boot/dts/am43x-epos-evm.dts +++ b/arch/arm/boot/dts/am43x-epos-evm.dts @@ -42,7 +42,7 @@ }; lcd0: display { - compatible = "osddisplays,osd057T0559-34ts", "panel-dpi"; + compatible = "osddisplays,osd070t1718-19ts", "panel-dpi"; label = "lcd"; backlight = <&lcd_bl>; diff --git a/arch/arm/boot/dts/bcm-cygnus.dtsi b/arch/arm/boot/dts/bcm-cygnus.dtsi index 2dac3efc7640..1bc45cfd5453 100644 --- a/arch/arm/boot/dts/bcm-cygnus.dtsi +++ b/arch/arm/boot/dts/bcm-cygnus.dtsi @@ -174,8 +174,8 @@ mdio: mdio@18002000 { compatible = "brcm,iproc-mdio"; reg = <0x18002000 0x8>; - #size-cells = <1>; - #address-cells = <0>; + #size-cells = <0>; + #address-cells = <1>; status = "disabled"; gphy0: ethernet-phy@0 { diff --git a/arch/arm/boot/dts/bcm283x.dtsi b/arch/arm/boot/dts/bcm283x.dtsi index 2d191fcbc2cc..90125ce19a1b 100644 --- a/arch/arm/boot/dts/bcm283x.dtsi +++ b/arch/arm/boot/dts/bcm283x.dtsi @@ -40,7 +40,7 @@ trips { cpu-crit { - temperature = <80000>; + temperature = <90000>; hysteresis = <0>; type = "critical"; }; diff --git a/arch/arm/boot/dts/bcm5301x.dtsi b/arch/arm/boot/dts/bcm5301x.dtsi index 372dc1eb88a0..2d9b4dd05830 100644 --- a/arch/arm/boot/dts/bcm5301x.dtsi +++ b/arch/arm/boot/dts/bcm5301x.dtsi @@ -353,8 +353,8 @@ mdio: mdio@18003000 { compatible = "brcm,iproc-mdio"; reg = <0x18003000 0x8>; - #size-cells = <1>; - #address-cells = <0>; + #size-cells = <0>; + #address-cells = <1>; }; mdio-bus-mux@18003000 { diff --git a/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi b/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi index c2a9dd57e56a..aa86341adaaa 100644 --- a/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi +++ b/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi @@ -215,7 +215,7 @@ flash0: n25q256a@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "micron,n25q256a"; + compatible = "micron,n25q256a", "jedec,spi-nor"; spi-max-frequency = <29000000>; spi-rx-bus-width = <4>; spi-tx-bus-width = <4>; diff --git a/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi b/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi index d1eae47b83f6..82f7ae030600 100644 --- a/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi +++ b/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi @@ -160,12 +160,12 @@ regulator-enable-ramp-delay = <1000>; }; - /* Used by DSS */ + /* Used by DSS and is the "zerov_regulator" trigger for SoC off mode */ vcsi: VCSI { regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; regulator-enable-ramp-delay = <1000>; - regulator-boot-on; + regulator-always-on; }; vdac: VDAC { diff --git a/arch/arm/boot/dts/omap3-pandora-common.dtsi b/arch/arm/boot/dts/omap3-pandora-common.dtsi index ec5891718ae6..150d5be42d27 100644 --- a/arch/arm/boot/dts/omap3-pandora-common.dtsi +++ b/arch/arm/boot/dts/omap3-pandora-common.dtsi @@ -226,6 +226,17 @@ gpio = <&gpio6 4 GPIO_ACTIVE_HIGH>; /* GPIO_164 */ }; + /* wl1251 wifi+bt module */ + wlan_en: fixed-regulator-wg7210_en { + compatible = "regulator-fixed"; + regulator-name = "vwlan"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + startup-delay-us = <50000>; + enable-active-high; + gpio = <&gpio1 23 GPIO_ACTIVE_HIGH>; + }; + /* wg7210 (wifi+bt module) 32k clock buffer */ wg7210_32k: fixed-regulator-wg7210_32k { compatible = "regulator-fixed"; @@ -522,9 +533,30 @@ /*wp-gpios = <&gpio4 31 GPIO_ACTIVE_HIGH>;*/ /* GPIO_127 */ }; -/* mmc3 is probed using pdata-quirks to pass wl1251 card data */ &mmc3 { - status = "disabled"; + vmmc-supply = <&wlan_en>; + + bus-width = <4>; + non-removable; + ti,non-removable; + cap-power-off-card; + + pinctrl-names = "default"; + pinctrl-0 = <&mmc3_pins>; + + #address-cells = <1>; + #size-cells = <0>; + + wlan: wifi@1 { + compatible = "ti,wl1251"; + + reg = <1>; + + interrupt-parent = <&gpio1>; + interrupts = <21 IRQ_TYPE_LEVEL_HIGH>; /* GPIO_21 */ + + ti,wl1251-has-eeprom; + }; }; /* bluetooth*/ diff --git a/arch/arm/boot/dts/omap3-tao3530.dtsi b/arch/arm/boot/dts/omap3-tao3530.dtsi index a7a04d78deeb..f24e2326cfa7 100644 --- a/arch/arm/boot/dts/omap3-tao3530.dtsi +++ b/arch/arm/boot/dts/omap3-tao3530.dtsi @@ -222,7 +222,7 @@ pinctrl-0 = <&mmc1_pins>; vmmc-supply = <&vmmc1>; vqmmc-supply = <&vsim>; - cd-gpios = <&twl_gpio 0 GPIO_ACTIVE_HIGH>; + cd-gpios = <&twl_gpio 0 GPIO_ACTIVE_LOW>; bus-width = <8>; }; diff --git a/arch/arm/boot/dts/s3c6410-mini6410.dts b/arch/arm/boot/dts/s3c6410-mini6410.dts index 0e159c884f97..1aeac33b0d34 100644 --- a/arch/arm/boot/dts/s3c6410-mini6410.dts +++ b/arch/arm/boot/dts/s3c6410-mini6410.dts @@ -165,6 +165,10 @@ }; }; +&clocks { + clocks = <&fin_pll>; +}; + &sdhci0 { pinctrl-names = "default"; pinctrl-0 = <&sd0_clk>, <&sd0_cmd>, <&sd0_cd>, <&sd0_bus4>; diff --git a/arch/arm/boot/dts/s3c6410-smdk6410.dts b/arch/arm/boot/dts/s3c6410-smdk6410.dts index a9a5689dc462..3bf6c450a26e 100644 --- a/arch/arm/boot/dts/s3c6410-smdk6410.dts +++ b/arch/arm/boot/dts/s3c6410-smdk6410.dts @@ -69,6 +69,10 @@ }; }; +&clocks { + clocks = <&fin_pll>; +}; + &sdhci0 { pinctrl-names = "default"; pinctrl-0 = <&sd0_clk>, <&sd0_cmd>, <&sd0_cd>, <&sd0_bus4>; diff --git a/arch/arm/configs/exynos_defconfig b/arch/arm/configs/exynos_defconfig index 08db1c83eb2d..736ed7a7bcf8 100644 --- a/arch/arm/configs/exynos_defconfig +++ b/arch/arm/configs/exynos_defconfig @@ -348,6 +348,7 @@ CONFIG_PRINTK_TIME=y CONFIG_DYNAMIC_DEBUG=y CONFIG_DEBUG_INFO=y CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_FS=y CONFIG_DEBUG_KERNEL=y CONFIG_SOFTLOCKUP_DETECTOR=y # CONFIG_DETECT_HUNG_TASK is not set diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig index 0f7381ee0c37..dabb80453249 100644 --- a/arch/arm/configs/imx_v6_v7_defconfig +++ b/arch/arm/configs/imx_v6_v7_defconfig @@ -460,6 +460,7 @@ CONFIG_FONT_8x8=y CONFIG_FONT_8x16=y CONFIG_PRINTK_TIME=y CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_FS=y # CONFIG_SCHED_DEBUG is not set CONFIG_PROVE_LOCKING=y # CONFIG_DEBUG_BUGVERBOSE is not set diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig index 40d7f1a4fc45..4ec69fb8a698 100644 --- a/arch/arm/configs/omap2plus_defconfig +++ b/arch/arm/configs/omap2plus_defconfig @@ -552,5 +552,6 @@ CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_SPLIT=y CONFIG_DEBUG_INFO_DWARF4=y CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_FS=y CONFIG_SCHEDSTATS=y # CONFIG_DEBUG_BUGVERBOSE is not set diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 9485acc520a4..e7fac125ea0d 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -224,8 +224,8 @@ void release_thread(struct task_struct *dead_task) asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); int -copy_thread(unsigned long clone_flags, unsigned long stack_start, - unsigned long stk_sz, struct task_struct *p) +copy_thread_tls(unsigned long clone_flags, unsigned long stack_start, + unsigned long stk_sz, struct task_struct *p, unsigned long tls) { struct thread_info *thread = task_thread_info(p); struct pt_regs *childregs = task_pt_regs(p); @@ -259,7 +259,7 @@ copy_thread(unsigned long clone_flags, unsigned long stack_start, clear_ptrace_hw_breakpoint(p); if (clone_flags & CLONE_SETTLS) - thread->tp_value[0] = childregs->ARM_r3; + thread->tp_value[0] = tls; thread->tp_value[1] = get_tpuser(); thread_notify(THREAD_NOTIFY_COPY, thread); diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 4b0bab2607e4..46e1be9e57a8 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -240,6 +240,10 @@ int __cpu_disable(void) if (ret) return ret; +#ifdef CONFIG_GENERIC_ARCH_TOPOLOGY + remove_cpu_topology(cpu); +#endif + /* * Take this CPU offline. Once we clear this, we can't return, * and we must not schedule until we're ready to give up the cpu. diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c index 5b9faba03afb..8d2e61d9e7a6 100644 --- a/arch/arm/kernel/topology.c +++ b/arch/arm/kernel/topology.c @@ -196,9 +196,8 @@ void store_cpu_topology(unsigned int cpuid) struct cpu_topology *cpuid_topo = &cpu_topology[cpuid]; unsigned int mpidr; - /* If the cpu topology has been already set, just return */ - if (cpuid_topo->core_id != -1) - return; + if (cpuid_topo->package_id != -1) + goto topology_populated; mpidr = read_cpuid_mpidr(); @@ -231,14 +230,15 @@ void store_cpu_topology(unsigned int cpuid) cpuid_topo->package_id = -1; } - update_siblings_masks(cpuid); - update_cpu_capacity(cpuid); pr_info("CPU%u: thread %d, cpu %d, socket %d, mpidr %x\n", cpuid, cpu_topology[cpuid].thread_id, cpu_topology[cpuid].core_id, cpu_topology[cpuid].package_id, mpidr); + +topology_populated: + update_siblings_masks(cpuid); } static inline int cpu_corepower_flags(void) diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c index 2efd18e8824c..1b7cf81ff035 100644 --- a/arch/arm/mach-omap2/pdata-quirks.c +++ b/arch/arm/mach-omap2/pdata-quirks.c @@ -7,7 +7,6 @@ #include #include #include -#include #include #include #include @@ -311,118 +310,15 @@ static void __init omap3_logicpd_torpedo_init(void) } /* omap3pandora legacy devices */ -#define PANDORA_WIFI_IRQ_GPIO 21 -#define PANDORA_WIFI_NRESET_GPIO 23 static struct platform_device pandora_backlight = { .name = "pandora-backlight", .id = -1, }; -static struct regulator_consumer_supply pandora_vmmc3_supply[] = { - REGULATOR_SUPPLY("vmmc", "omap_hsmmc.2"), -}; - -static struct regulator_init_data pandora_vmmc3 = { - .constraints = { - .valid_ops_mask = REGULATOR_CHANGE_STATUS, - }, - .num_consumer_supplies = ARRAY_SIZE(pandora_vmmc3_supply), - .consumer_supplies = pandora_vmmc3_supply, -}; - -static struct fixed_voltage_config pandora_vwlan = { - .supply_name = "vwlan", - .microvolts = 1800000, /* 1.8V */ - .startup_delay = 50000, /* 50ms */ - .init_data = &pandora_vmmc3, -}; - -static struct platform_device pandora_vwlan_device = { - .name = "reg-fixed-voltage", - .id = 1, - .dev = { - .platform_data = &pandora_vwlan, - }, -}; - -static struct gpiod_lookup_table pandora_vwlan_gpiod_table = { - .dev_id = "reg-fixed-voltage.1", - .table = { - /* - * As this is a low GPIO number it should be at the first - * GPIO bank. - */ - GPIO_LOOKUP("gpio-0-31", PANDORA_WIFI_NRESET_GPIO, - NULL, GPIO_ACTIVE_HIGH), - { }, - }, -}; - -static void pandora_wl1251_init_card(struct mmc_card *card) -{ - /* - * We have TI wl1251 attached to MMC3. Pass this information to - * SDIO core because it can't be probed by normal methods. - */ - if (card->type == MMC_TYPE_SDIO || card->type == MMC_TYPE_SD_COMBO) { - card->quirks |= MMC_QUIRK_NONSTD_SDIO; - card->cccr.wide_bus = 1; - card->cis.vendor = 0x104c; - card->cis.device = 0x9066; - card->cis.blksize = 512; - card->cis.max_dtr = 24000000; - card->ocr = 0x80; - } -} - -static struct omap2_hsmmc_info pandora_mmc3[] = { - { - .mmc = 3, - .caps = MMC_CAP_4_BIT_DATA | MMC_CAP_POWER_OFF_CARD, - .init_card = pandora_wl1251_init_card, - }, - {} /* Terminator */ -}; - -static void __init pandora_wl1251_init(void) -{ - struct wl1251_platform_data pandora_wl1251_pdata; - int ret; - - memset(&pandora_wl1251_pdata, 0, sizeof(pandora_wl1251_pdata)); - - pandora_wl1251_pdata.power_gpio = -1; - - ret = gpio_request_one(PANDORA_WIFI_IRQ_GPIO, GPIOF_IN, "wl1251 irq"); - if (ret < 0) - goto fail; - - pandora_wl1251_pdata.irq = gpio_to_irq(PANDORA_WIFI_IRQ_GPIO); - if (pandora_wl1251_pdata.irq < 0) - goto fail_irq; - - pandora_wl1251_pdata.use_eeprom = true; - ret = wl1251_set_platform_data(&pandora_wl1251_pdata); - if (ret < 0) - goto fail_irq; - - return; - -fail_irq: - gpio_free(PANDORA_WIFI_IRQ_GPIO); -fail: - pr_err("wl1251 board initialisation failed\n"); -} - static void __init omap3_pandora_legacy_init(void) { platform_device_register(&pandora_backlight); - gpiod_add_lookup_table(&pandora_vwlan_gpiod_table); - platform_device_register(&pandora_vwlan_device); - omap_hsmmc_init(pandora_mmc3); - omap_hsmmc_late_init(pandora_mmc3); - pandora_wl1251_init(); } #endif /* CONFIG_ARCH_OMAP3 */ diff --git a/arch/arm/mach-tegra/reset-handler.S b/arch/arm/mach-tegra/reset-handler.S index 67b763fea005..e3f34815c9da 100644 --- a/arch/arm/mach-tegra/reset-handler.S +++ b/arch/arm/mach-tegra/reset-handler.S @@ -44,16 +44,16 @@ ENTRY(tegra_resume) cmp r6, #TEGRA20 beq 1f @ Yes /* Clear the flow controller flags for this CPU. */ - cpu_to_csr_reg r1, r0 + cpu_to_csr_reg r3, r0 mov32 r2, TEGRA_FLOW_CTRL_BASE - ldr r1, [r2, r1] + ldr r1, [r2, r3] /* Clear event & intr flag */ orr r1, r1, \ #FLOW_CTRL_CSR_INTR_FLAG | FLOW_CTRL_CSR_EVENT_FLAG movw r0, #0x3FFD @ enable, cluster_switch, immed, bitmaps @ & ext flags for CPU power mgnt bic r1, r1, r0 - str r1, [r2] + str r1, [r2, r3] 1: mov32 r9, 0xc09 diff --git a/arch/arm/mach-vexpress/spc.c b/arch/arm/mach-vexpress/spc.c index 354e0e7025ae..1da11bdb1dfb 100644 --- a/arch/arm/mach-vexpress/spc.c +++ b/arch/arm/mach-vexpress/spc.c @@ -551,8 +551,9 @@ static struct clk *ve_spc_clk_register(struct device *cpu_dev) static int __init ve_spc_clk_init(void) { - int cpu; + int cpu, cluster; struct clk *clk; + bool init_opp_table[MAX_CLUSTERS] = { false }; if (!info) return 0; /* Continue only if SPC is initialised */ @@ -578,8 +579,17 @@ static int __init ve_spc_clk_init(void) continue; } + cluster = topology_physical_package_id(cpu_dev->id); + if (init_opp_table[cluster]) + continue; + if (ve_init_opp_table(cpu_dev)) pr_warn("failed to initialise cpu%d opp table\n", cpu); + else if (dev_pm_opp_set_sharing_cpus(cpu_dev, + topology_core_cpumask(cpu_dev->id))) + pr_warn("failed to mark OPPs shared for cpu%d\n", cpu); + else + init_opp_table[cluster] = true; } platform_device_register_simple("vexpress-spc-cpufreq", -1, NULL, 0); diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c index db9247898300..287ef898a55e 100644 --- a/arch/arm/mm/dma-mapping-nommu.c +++ b/arch/arm/mm/dma-mapping-nommu.c @@ -35,7 +35,7 @@ static void *arm_nommu_dma_alloc(struct device *dev, size_t size, unsigned long attrs) { - void *ret = dma_alloc_from_global_coherent(size, dma_handle); + void *ret = dma_alloc_from_global_coherent(dev, size, dma_handle); /* * dma_alloc_from_global_coherent() may fail because: diff --git a/arch/arm/mm/proc-v7-bugs.c b/arch/arm/mm/proc-v7-bugs.c index 9a07916af8dd..a6554fdb56c5 100644 --- a/arch/arm/mm/proc-v7-bugs.c +++ b/arch/arm/mm/proc-v7-bugs.c @@ -65,6 +65,9 @@ static void cpu_v7_spectre_init(void) break; #ifdef CONFIG_ARM_PSCI + case ARM_CPU_PART_BRAHMA_B53: + /* Requires no workaround */ + break; default: /* Other ARM CPUs require no workaround */ if (read_cpuid_implementor() == ARM_CPU_IMP_ARM) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 3f047afb982c..6ccd2ed30963 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -139,6 +139,7 @@ config ARM64 select HAVE_CMPXCHG_DOUBLE select HAVE_CMPXCHG_LOCAL select HAVE_CONTEXT_TRACKING + select HAVE_COPY_THREAD_TLS select HAVE_DEBUG_BUGVERBOSE select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts index 6039adda12ee..b0b12e389835 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts @@ -296,7 +296,7 @@ }; &usb0_phy { - status = "okay"; + status = "disabled"; phy-supply = <&usb_otg_pwr>; }; @@ -306,7 +306,7 @@ }; &usb0 { - status = "okay"; + status = "disabled"; }; &usb1 { diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-khadas-vim.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-khadas-vim.dts index 2a5cd303123d..8d6f316a5c7b 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-khadas-vim.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-khadas-vim.dts @@ -192,6 +192,9 @@ bluetooth { compatible = "brcm,bcm43438-bt"; shutdown-gpios = <&gpio GPIOX_17 GPIO_ACTIVE_HIGH>; + max-speed = <2000000>; + clocks = <&wifi32k>; + clock-names = "lpo"; }; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts index f25ddd18a607..4d67eb715b91 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts @@ -409,6 +409,9 @@ bluetooth { compatible = "brcm,bcm43438-bt"; shutdown-gpios = <&gpio GPIOX_17 GPIO_ACTIVE_HIGH>; + max-speed = <2000000>; + clocks = <&wifi32k>; + clock-names = "lpo"; }; }; diff --git a/arch/arm64/boot/dts/exynos/exynos5433.dtsi b/arch/arm64/boot/dts/exynos/exynos5433.dtsi index a76f620f7f35..a5f8752f607b 100644 --- a/arch/arm64/boot/dts/exynos/exynos5433.dtsi +++ b/arch/arm64/boot/dts/exynos/exynos5433.dtsi @@ -18,8 +18,8 @@ / { compatible = "samsung,exynos5433"; - #address-cells = <1>; - #size-cells = <1>; + #address-cells = <2>; + #size-cells = <2>; interrupt-parent = <&gic>; @@ -311,7 +311,7 @@ compatible = "simple-bus"; #address-cells = <1>; #size-cells = <1>; - ranges; + ranges = <0x0 0x0 0x0 0x18000000>; chipid@10000000 { compatible = "samsung,exynos4210-chipid"; diff --git a/arch/arm64/boot/dts/exynos/exynos7.dtsi b/arch/arm64/boot/dts/exynos/exynos7.dtsi index bcb9d8cee267..0821489a874d 100644 --- a/arch/arm64/boot/dts/exynos/exynos7.dtsi +++ b/arch/arm64/boot/dts/exynos/exynos7.dtsi @@ -12,8 +12,8 @@ / { compatible = "samsung,exynos7"; interrupt-parent = <&gic>; - #address-cells = <1>; - #size-cells = <1>; + #address-cells = <2>; + #size-cells = <2>; aliases { pinctrl0 = &pinctrl_alive; @@ -98,7 +98,7 @@ compatible = "simple-bus"; #address-cells = <1>; #size-cells = <1>; - ranges; + ranges = <0 0 0 0x18000000>; chipid@10000000 { compatible = "samsung,exynos4210-chipid"; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi index 72b9a75976a1..bb960fe2bb64 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi @@ -102,7 +102,7 @@ reboot { compatible ="syscon-reboot"; - regmap = <&dcfg>; + regmap = <&rst>; offset = <0xb0>; mask = <0x02>; }; @@ -161,6 +161,12 @@ big-endian; }; + rst: syscon@1e60000 { + compatible = "syscon"; + reg = <0x0 0x1e60000 0x0 0x10000>; + little-endian; + }; + scfg: syscon@1fc0000 { compatible = "fsl,ls1028a-scfg", "syscon"; reg = <0x0 0x1fc0000 0x0 0x10000>; @@ -567,7 +573,7 @@ 0x00010004 0x0000003d 0x00010005 0x00000045 0x00010006 0x0000004d - 0x00010007 0x00000045 + 0x00010007 0x00000055 0x00010008 0x0000005e 0x00010009 0x00000066 0x0001000a 0x0000006e diff --git a/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi b/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi index 4c38426a6969..02909a48dfcd 100644 --- a/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi @@ -309,9 +309,8 @@ regulator-name = "VDD_12V"; regulator-min-microvolt = <1200000>; regulator-max-microvolt = <1200000>; - gpio = <&gpio TEGRA194_MAIN_GPIO(A, 1) GPIO_ACTIVE_LOW>; + gpio = <&gpio TEGRA194_MAIN_GPIO(A, 1) GPIO_ACTIVE_HIGH>; regulator-boot-on; - enable-active-low; }; }; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi b/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi index a7dc319214a4..b0095072bc28 100644 --- a/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi @@ -1612,7 +1612,7 @@ regulator-name = "VDD_HDMI_5V0"; regulator-min-microvolt = <5000000>; regulator-max-microvolt = <5000000>; - gpio = <&exp1 12 GPIO_ACTIVE_LOW>; + gpio = <&exp1 12 GPIO_ACTIVE_HIGH>; enable-active-high; vin-supply = <&vdd_5v0_sys>; }; diff --git a/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi b/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi index 04ad2fb22b9a..dba3488492f1 100644 --- a/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi +++ b/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi @@ -623,6 +623,8 @@ l21 { regulator-min-microvolt = <2950000>; regulator-max-microvolt = <2950000>; + regulator-allow-set-load; + regulator-system-load = <200000>; }; l22 { regulator-min-microvolt = <3300000>; diff --git a/arch/arm64/boot/dts/qcom/msm8998-clamshell.dtsi b/arch/arm64/boot/dts/qcom/msm8998-clamshell.dtsi index 9682d4dd7496..1bae90705746 100644 --- a/arch/arm64/boot/dts/qcom/msm8998-clamshell.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8998-clamshell.dtsi @@ -23,6 +23,43 @@ }; }; +/* + * The laptop FW does not appear to support the retention state as it is + * not advertised as enabled in ACPI, and enabling it in DT can cause boot + * hangs. + */ +&CPU0 { + cpu-idle-states = <&LITTLE_CPU_SLEEP_1>; +}; + +&CPU1 { + cpu-idle-states = <&LITTLE_CPU_SLEEP_1>; +}; + +&CPU2 { + cpu-idle-states = <&LITTLE_CPU_SLEEP_1>; +}; + +&CPU3 { + cpu-idle-states = <&LITTLE_CPU_SLEEP_1>; +}; + +&CPU4 { + cpu-idle-states = <&BIG_CPU_SLEEP_1>; +}; + +&CPU5 { + cpu-idle-states = <&BIG_CPU_SLEEP_1>; +}; + +&CPU6 { + cpu-idle-states = <&BIG_CPU_SLEEP_1>; +}; + +&CPU7 { + cpu-idle-states = <&BIG_CPU_SLEEP_1>; +}; + &qusb2phy { status = "okay"; diff --git a/arch/arm64/crypto/aes-neonbs-glue.c b/arch/arm64/crypto/aes-neonbs-glue.c index ea873b8904c4..e3e27349a9fe 100644 --- a/arch/arm64/crypto/aes-neonbs-glue.c +++ b/arch/arm64/crypto/aes-neonbs-glue.c @@ -384,7 +384,7 @@ static int __xts_crypt(struct skcipher_request *req, bool encrypt, goto xts_tail; kernel_neon_end(); - skcipher_walk_done(&walk, nbytes); + err = skcipher_walk_done(&walk, nbytes); } if (err || likely(!tail)) diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index 8dc6c5cdabe6..baf52baaa2a5 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -85,13 +85,12 @@ #define PAGE_SHARED_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_WRITE) #define PAGE_READONLY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN) #define PAGE_READONLY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN) -#define PAGE_EXECONLY __pgprot(_PAGE_DEFAULT | PTE_RDONLY | PTE_NG | PTE_PXN) #define __P000 PAGE_NONE #define __P001 PAGE_READONLY #define __P010 PAGE_READONLY #define __P011 PAGE_READONLY -#define __P100 PAGE_EXECONLY +#define __P100 PAGE_READONLY_EXEC #define __P101 PAGE_READONLY_EXEC #define __P110 PAGE_READONLY_EXEC #define __P111 PAGE_READONLY_EXEC @@ -100,7 +99,7 @@ #define __S001 PAGE_READONLY #define __S010 PAGE_SHARED #define __S011 PAGE_SHARED -#define __S100 PAGE_EXECONLY +#define __S100 PAGE_READONLY_EXEC #define __S101 PAGE_READONLY_EXEC #define __S110 PAGE_SHARED_EXEC #define __S111 PAGE_SHARED_EXEC diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 565aa45ef134..13ebe2bad79f 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -96,12 +96,8 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; #define pte_dirty(pte) (pte_sw_dirty(pte) || pte_hw_dirty(pte)) #define pte_valid(pte) (!!(pte_val(pte) & PTE_VALID)) -/* - * Execute-only user mappings do not have the PTE_USER bit set. All valid - * kernel mappings have the PTE_UXN bit set. - */ #define pte_valid_not_user(pte) \ - ((pte_val(pte) & (PTE_VALID | PTE_USER | PTE_UXN)) == (PTE_VALID | PTE_UXN)) + ((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID) #define pte_valid_young(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_AF)) == (PTE_VALID | PTE_AF)) #define pte_valid_user(pte) \ @@ -117,8 +113,8 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; /* * p??_access_permitted() is true for valid user mappings (subject to the - * write permission check) other than user execute-only which do not have the - * PTE_USER bit set. PROT_NONE mappings do not have the PTE_VALID bit set. + * write permission check). PROT_NONE mappings do not have the PTE_VALID bit + * set. */ #define pte_access_permitted(pte, write) \ (pte_valid_user(pte) && (!(write) || pte_write(pte))) diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 127712b0b970..32fc8061aa76 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -62,8 +62,13 @@ static inline unsigned long __range_ok(const void __user *addr, unsigned long si { unsigned long ret, limit = current_thread_info()->addr_limit; + /* + * Asynchronous I/O running in a kernel thread does not have the + * TIF_TAGGED_ADDR flag of the process owning the mm, so always untag + * the user address before checking. + */ if (IS_ENABLED(CONFIG_ARM64_TAGGED_ADDR_ABI) && - test_thread_flag(TIF_TAGGED_ADDR)) + (current->flags & PF_KTHREAD || test_thread_flag(TIF_TAGGED_ADDR))) addr = untagged_addr(addr); __chk_user_ptr(addr); diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 2629a68b8724..5af82587909e 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -42,7 +42,6 @@ #endif #define __ARCH_WANT_SYS_CLONE -#define __ARCH_WANT_SYS_CLONE3 #ifndef __COMPAT_SYSCALL_NR #include diff --git a/arch/arm64/include/uapi/asm/unistd.h b/arch/arm64/include/uapi/asm/unistd.h index 4703d218663a..f83a70e07df8 100644 --- a/arch/arm64/include/uapi/asm/unistd.h +++ b/arch/arm64/include/uapi/asm/unistd.h @@ -19,5 +19,6 @@ #define __ARCH_WANT_NEW_STAT #define __ARCH_WANT_SET_GET_RLIMIT #define __ARCH_WANT_TIME32_SYSCALLS +#define __ARCH_WANT_SYS_CLONE3 #include diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 93f34b4eca25..96f576e9ea46 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -575,6 +575,7 @@ static const struct midr_range spectre_v2_safe_list[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A53), MIDR_ALL_VERSIONS(MIDR_CORTEX_A55), MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53), + MIDR_ALL_VERSIONS(MIDR_HISI_TSV110), { /* sentinel */ } }; diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 71f788cd2b18..d54586d5b031 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -360,8 +360,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) asmlinkage void ret_from_fork(void) asm("ret_from_fork"); -int copy_thread(unsigned long clone_flags, unsigned long stack_start, - unsigned long stk_sz, struct task_struct *p) +int copy_thread_tls(unsigned long clone_flags, unsigned long stack_start, + unsigned long stk_sz, struct task_struct *p, unsigned long tls) { struct pt_regs *childregs = task_pt_regs(p); @@ -394,11 +394,11 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, } /* - * If a TLS pointer was passed to clone (4th argument), use it - * for the new thread. + * If a TLS pointer was passed to clone, use it for the new + * thread. */ if (clone_flags & CLONE_SETTLS) - p->thread.uw.tp_value = childregs->regs[3]; + p->thread.uw.tp_value = tls; } else { memset(childregs, 0, sizeof(struct pt_regs)); childregs->pstate = PSR_MODE_EL1h; diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c index c9f72b2665f1..43ae4e0c968f 100644 --- a/arch/arm64/kernel/psci.c +++ b/arch/arm64/kernel/psci.c @@ -81,7 +81,8 @@ static void cpu_psci_cpu_die(unsigned int cpu) static int cpu_psci_cpu_kill(unsigned int cpu) { - int err, i; + int err; + unsigned long start, end; if (!psci_ops.affinity_info) return 0; @@ -91,16 +92,18 @@ static int cpu_psci_cpu_kill(unsigned int cpu) * while it is dying. So, try again a few times. */ - for (i = 0; i < 10; i++) { + start = jiffies; + end = start + msecs_to_jiffies(100); + do { err = psci_ops.affinity_info(cpu_logical_map(cpu), 0); if (err == PSCI_0_2_AFFINITY_LEVEL_OFF) { - pr_info("CPU%d killed.\n", cpu); + pr_info("CPU%d killed (polled %d ms)\n", cpu, + jiffies_to_msecs(jiffies - start)); return 0; } - msleep(10); - pr_info("Retrying again to check for CPU kill\n"); - } + usleep_range(100, 1000); + } while (time_before(jiffies, end)); pr_warn("CPU%d may not have shut down cleanly (AFFINITY_INFO reports %d)\n", cpu, err); diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 46822afc57e0..01a515e0171e 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -2360,8 +2360,11 @@ static const struct sys_reg_desc *index_to_sys_reg_desc(struct kvm_vcpu *vcpu, if ((id & KVM_REG_ARM_COPROC_MASK) != KVM_REG_ARM64_SYSREG) return NULL; + if (!index_to_params(id, ¶ms)) + return NULL; + table = get_target_table(vcpu->arch.target, true, &num); - r = find_reg_by_id(id, ¶ms, table, num); + r = find_reg(¶ms, table, num); if (!r) r = find_reg(¶ms, sys_reg_descs, ARRAY_SIZE(sys_reg_descs)); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 9fc6db0bcbad..d26e6cd28953 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -454,7 +454,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, const struct fault_info *inf; struct mm_struct *mm = current->mm; vm_fault_t fault, major = 0; - unsigned long vm_flags = VM_READ | VM_WRITE; + unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC; unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; if (kprobe_page_fault(regs, esr)) diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 60c929f3683b..d10247fab0fd 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1069,7 +1069,6 @@ void arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct zone *zone; /* * FIXME: Cleanup page tables (also in arch_add_memory() in case @@ -1078,7 +1077,6 @@ void arch_remove_memory(int nid, u64 start, u64 size, * unplug. ARCH_ENABLE_MEMORY_HOTREMOVE must not be * unlocked yet. */ - zone = page_zone(pfn_to_page(start_pfn)); - __remove_pages(zone, start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); } #endif diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h index 12cd9231c4b8..0231d69c8bf2 100644 --- a/arch/hexagon/include/asm/atomic.h +++ b/arch/hexagon/include/asm/atomic.h @@ -91,7 +91,7 @@ static inline void atomic_##op(int i, atomic_t *v) \ "1: %0 = memw_locked(%1);\n" \ " %0 = "#op "(%0,%2);\n" \ " memw_locked(%1,P3)=%0;\n" \ - " if !P3 jump 1b;\n" \ + " if (!P3) jump 1b;\n" \ : "=&r" (output) \ : "r" (&v->counter), "r" (i) \ : "memory", "p3" \ @@ -107,7 +107,7 @@ static inline int atomic_##op##_return(int i, atomic_t *v) \ "1: %0 = memw_locked(%1);\n" \ " %0 = "#op "(%0,%2);\n" \ " memw_locked(%1,P3)=%0;\n" \ - " if !P3 jump 1b;\n" \ + " if (!P3) jump 1b;\n" \ : "=&r" (output) \ : "r" (&v->counter), "r" (i) \ : "memory", "p3" \ @@ -124,7 +124,7 @@ static inline int atomic_fetch_##op(int i, atomic_t *v) \ "1: %0 = memw_locked(%2);\n" \ " %1 = "#op "(%0,%3);\n" \ " memw_locked(%2,P3)=%1;\n" \ - " if !P3 jump 1b;\n" \ + " if (!P3) jump 1b;\n" \ : "=&r" (output), "=&r" (val) \ : "r" (&v->counter), "r" (i) \ : "memory", "p3" \ @@ -173,7 +173,7 @@ static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) " }" " memw_locked(%2, p3) = %1;" " {" - " if !p3 jump 1b;" + " if (!p3) jump 1b;" " }" "2:" : "=&r" (__oldval), "=&r" (tmp) diff --git a/arch/hexagon/include/asm/bitops.h b/arch/hexagon/include/asm/bitops.h index 47384b094b94..71429f756af0 100644 --- a/arch/hexagon/include/asm/bitops.h +++ b/arch/hexagon/include/asm/bitops.h @@ -38,7 +38,7 @@ static inline int test_and_clear_bit(int nr, volatile void *addr) "1: R12 = memw_locked(R10);\n" " { P0 = tstbit(R12,R11); R12 = clrbit(R12,R11); }\n" " memw_locked(R10,P1) = R12;\n" - " {if !P1 jump 1b; %0 = mux(P0,#1,#0);}\n" + " {if (!P1) jump 1b; %0 = mux(P0,#1,#0);}\n" : "=&r" (oldval) : "r" (addr), "r" (nr) : "r10", "r11", "r12", "p0", "p1", "memory" @@ -62,7 +62,7 @@ static inline int test_and_set_bit(int nr, volatile void *addr) "1: R12 = memw_locked(R10);\n" " { P0 = tstbit(R12,R11); R12 = setbit(R12,R11); }\n" " memw_locked(R10,P1) = R12;\n" - " {if !P1 jump 1b; %0 = mux(P0,#1,#0);}\n" + " {if (!P1) jump 1b; %0 = mux(P0,#1,#0);}\n" : "=&r" (oldval) : "r" (addr), "r" (nr) : "r10", "r11", "r12", "p0", "p1", "memory" @@ -88,7 +88,7 @@ static inline int test_and_change_bit(int nr, volatile void *addr) "1: R12 = memw_locked(R10);\n" " { P0 = tstbit(R12,R11); R12 = togglebit(R12,R11); }\n" " memw_locked(R10,P1) = R12;\n" - " {if !P1 jump 1b; %0 = mux(P0,#1,#0);}\n" + " {if (!P1) jump 1b; %0 = mux(P0,#1,#0);}\n" : "=&r" (oldval) : "r" (addr), "r" (nr) : "r10", "r11", "r12", "p0", "p1", "memory" @@ -223,7 +223,7 @@ static inline int ffs(int x) int r; asm("{ P0 = cmp.eq(%1,#0); %0 = ct0(%1);}\n" - "{ if P0 %0 = #0; if !P0 %0 = add(%0,#1);}\n" + "{ if (P0) %0 = #0; if (!P0) %0 = add(%0,#1);}\n" : "=&r" (r) : "r" (x) : "p0"); diff --git a/arch/hexagon/include/asm/cmpxchg.h b/arch/hexagon/include/asm/cmpxchg.h index 6091322c3af9..92b8a02e588a 100644 --- a/arch/hexagon/include/asm/cmpxchg.h +++ b/arch/hexagon/include/asm/cmpxchg.h @@ -30,7 +30,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, __asm__ __volatile__ ( "1: %0 = memw_locked(%1);\n" /* load into retval */ " memw_locked(%1,P0) = %2;\n" /* store into memory */ - " if !P0 jump 1b;\n" + " if (!P0) jump 1b;\n" : "=&r" (retval) : "r" (ptr), "r" (x) : "memory", "p0" diff --git a/arch/hexagon/include/asm/futex.h b/arch/hexagon/include/asm/futex.h index cb635216a732..0191f7c7193e 100644 --- a/arch/hexagon/include/asm/futex.h +++ b/arch/hexagon/include/asm/futex.h @@ -16,7 +16,7 @@ /* For example: %1 = %4 */ \ insn \ "2: memw_locked(%3,p2) = %1;\n" \ - " if !p2 jump 1b;\n" \ + " if (!p2) jump 1b;\n" \ " %1 = #0;\n" \ "3:\n" \ ".section .fixup,\"ax\"\n" \ @@ -84,10 +84,10 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, "1: %1 = memw_locked(%3)\n" " {\n" " p2 = cmp.eq(%1,%4)\n" - " if !p2.new jump:NT 3f\n" + " if (!p2.new) jump:NT 3f\n" " }\n" "2: memw_locked(%3,p2) = %5\n" - " if !p2 jump 1b\n" + " if (!p2) jump 1b\n" "3:\n" ".section .fixup,\"ax\"\n" "4: %0 = #%6\n" diff --git a/arch/hexagon/include/asm/spinlock.h b/arch/hexagon/include/asm/spinlock.h index bfe07d842ff3..ef103b73bec8 100644 --- a/arch/hexagon/include/asm/spinlock.h +++ b/arch/hexagon/include/asm/spinlock.h @@ -30,9 +30,9 @@ static inline void arch_read_lock(arch_rwlock_t *lock) __asm__ __volatile__( "1: R6 = memw_locked(%0);\n" " { P3 = cmp.ge(R6,#0); R6 = add(R6,#1);}\n" - " { if !P3 jump 1b; }\n" + " { if (!P3) jump 1b; }\n" " memw_locked(%0,P3) = R6;\n" - " { if !P3 jump 1b; }\n" + " { if (!P3) jump 1b; }\n" : : "r" (&lock->lock) : "memory", "r6", "p3" @@ -46,7 +46,7 @@ static inline void arch_read_unlock(arch_rwlock_t *lock) "1: R6 = memw_locked(%0);\n" " R6 = add(R6,#-1);\n" " memw_locked(%0,P3) = R6\n" - " if !P3 jump 1b;\n" + " if (!P3) jump 1b;\n" : : "r" (&lock->lock) : "memory", "r6", "p3" @@ -61,7 +61,7 @@ static inline int arch_read_trylock(arch_rwlock_t *lock) __asm__ __volatile__( " R6 = memw_locked(%1);\n" " { %0 = #0; P3 = cmp.ge(R6,#0); R6 = add(R6,#1);}\n" - " { if !P3 jump 1f; }\n" + " { if (!P3) jump 1f; }\n" " memw_locked(%1,P3) = R6;\n" " { %0 = P3 }\n" "1:\n" @@ -78,9 +78,9 @@ static inline void arch_write_lock(arch_rwlock_t *lock) __asm__ __volatile__( "1: R6 = memw_locked(%0)\n" " { P3 = cmp.eq(R6,#0); R6 = #-1;}\n" - " { if !P3 jump 1b; }\n" + " { if (!P3) jump 1b; }\n" " memw_locked(%0,P3) = R6;\n" - " { if !P3 jump 1b; }\n" + " { if (!P3) jump 1b; }\n" : : "r" (&lock->lock) : "memory", "r6", "p3" @@ -94,7 +94,7 @@ static inline int arch_write_trylock(arch_rwlock_t *lock) __asm__ __volatile__( " R6 = memw_locked(%1)\n" " { %0 = #0; P3 = cmp.eq(R6,#0); R6 = #-1;}\n" - " { if !P3 jump 1f; }\n" + " { if (!P3) jump 1f; }\n" " memw_locked(%1,P3) = R6;\n" " %0 = P3;\n" "1:\n" @@ -117,9 +117,9 @@ static inline void arch_spin_lock(arch_spinlock_t *lock) __asm__ __volatile__( "1: R6 = memw_locked(%0);\n" " P3 = cmp.eq(R6,#0);\n" - " { if !P3 jump 1b; R6 = #1; }\n" + " { if (!P3) jump 1b; R6 = #1; }\n" " memw_locked(%0,P3) = R6;\n" - " { if !P3 jump 1b; }\n" + " { if (!P3) jump 1b; }\n" : : "r" (&lock->lock) : "memory", "r6", "p3" @@ -139,7 +139,7 @@ static inline unsigned int arch_spin_trylock(arch_spinlock_t *lock) __asm__ __volatile__( " R6 = memw_locked(%1);\n" " P3 = cmp.eq(R6,#0);\n" - " { if !P3 jump 1f; R6 = #1; %0 = #0; }\n" + " { if (!P3) jump 1f; R6 = #1; %0 = #0; }\n" " memw_locked(%1,P3) = R6;\n" " %0 = P3;\n" "1:\n" diff --git a/arch/hexagon/kernel/stacktrace.c b/arch/hexagon/kernel/stacktrace.c index 35f29423fda8..5ed02f699479 100644 --- a/arch/hexagon/kernel/stacktrace.c +++ b/arch/hexagon/kernel/stacktrace.c @@ -11,8 +11,6 @@ #include #include -register unsigned long current_frame_pointer asm("r30"); - struct stackframe { unsigned long fp; unsigned long rets; @@ -30,7 +28,7 @@ void save_stack_trace(struct stack_trace *trace) low = (unsigned long)task_stack_page(current); high = low + THREAD_SIZE; - fp = current_frame_pointer; + fp = (unsigned long)__builtin_frame_address(0); while (fp >= low && fp <= (high - sizeof(*frame))) { frame = (struct stackframe *)fp; diff --git a/arch/hexagon/kernel/vm_entry.S b/arch/hexagon/kernel/vm_entry.S index 12242c27e2df..4023fdbea490 100644 --- a/arch/hexagon/kernel/vm_entry.S +++ b/arch/hexagon/kernel/vm_entry.S @@ -369,7 +369,7 @@ ret_from_fork: R26.L = #LO(do_work_pending); R0 = #VM_INT_DISABLE; } - if P0 jump check_work_pending + if (P0) jump check_work_pending { R0 = R25; callr R24 diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index bf9df2625bc8..a6dd80a2c939 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -689,9 +689,7 @@ void arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct zone *zone; - zone = page_zone(pfn_to_page(start_pfn)); - __remove_pages(zone, start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); } #endif diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index a0bd9bdb5f83..e5c2d47608fe 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -46,7 +46,7 @@ config MIPS select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE if CPU_SUPPORTS_HUGEPAGES select HAVE_ASM_MODVERSIONS - select HAVE_EBPF_JIT if (!CPU_MICROMIPS) + select HAVE_EBPF_JIT if 64BIT && !CPU_MICROMIPS && TARGET_ISA_REV >= 2 select HAVE_CONTEXT_TRACKING select HAVE_COPY_THREAD_TLS select HAVE_C_RECORDMCOUNT diff --git a/arch/mips/boot/compressed/Makefile b/arch/mips/boot/compressed/Makefile index 172801ed35b8..d859f079b771 100644 --- a/arch/mips/boot/compressed/Makefile +++ b/arch/mips/boot/compressed/Makefile @@ -29,6 +29,9 @@ KBUILD_AFLAGS := $(KBUILD_AFLAGS) -D__ASSEMBLY__ \ -DBOOT_HEAP_SIZE=$(BOOT_HEAP_SIZE) \ -DKERNEL_ENTRY=$(VMLINUX_ENTRY_ADDRESS) +# Prevents link failures: __sanitizer_cov_trace_pc() is not linked in. +KCOV_INSTRUMENT := n + # decompressor objects (linked with vmlinuz) vmlinuzobjs-y := $(obj)/head.o $(obj)/decompress.o $(obj)/string.o diff --git a/arch/mips/include/asm/pgtable-64.h b/arch/mips/include/asm/pgtable-64.h index 93a9dce31f25..813dfe5f45a5 100644 --- a/arch/mips/include/asm/pgtable-64.h +++ b/arch/mips/include/asm/pgtable-64.h @@ -18,10 +18,12 @@ #include #define __ARCH_USE_5LEVEL_HACK -#if defined(CONFIG_PAGE_SIZE_64KB) && !defined(CONFIG_MIPS_VA_BITS_48) +#if CONFIG_PGTABLE_LEVELS == 2 #include -#elif !(defined(CONFIG_PAGE_SIZE_4KB) && defined(CONFIG_MIPS_VA_BITS_48)) +#elif CONFIG_PGTABLE_LEVELS == 3 #include +#else +#include #endif /* @@ -216,6 +218,9 @@ static inline unsigned long pgd_page_vaddr(pgd_t pgd) return pgd_val(pgd); } +#define pgd_phys(pgd) virt_to_phys((void *)pgd_val(pgd)) +#define pgd_page(pgd) (pfn_to_page(pgd_phys(pgd) >> PAGE_SHIFT)) + static inline pud_t *pud_offset(pgd_t *pgd, unsigned long address) { return (pud_t *)pgd_page_vaddr(*pgd) + pud_index(address); diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h index 4993db40482c..ee26f9a4575d 100644 --- a/arch/mips/include/asm/thread_info.h +++ b/arch/mips/include/asm/thread_info.h @@ -49,8 +49,26 @@ struct thread_info { .addr_limit = KERNEL_DS, \ } -/* How to get the thread information struct from C. */ +/* + * A pointer to the struct thread_info for the currently executing thread is + * held in register $28/$gp. + * + * We declare __current_thread_info as a global register variable rather than a + * local register variable within current_thread_info() because clang doesn't + * support explicit local register variables. + * + * When building the VDSO we take care not to declare the global register + * variable because this causes GCC to not preserve the value of $28/$gp in + * functions that change its value (which is common in the PIC VDSO when + * accessing the GOT). Since the VDSO shouldn't be accessing + * __current_thread_info anyway we declare it extern in order to cause a link + * failure if it's referenced. + */ +#ifdef __VDSO__ +extern struct thread_info *__current_thread_info; +#else register struct thread_info *__current_thread_info __asm__("$28"); +#endif static inline struct thread_info *current_thread_info(void) { diff --git a/arch/mips/include/asm/vdso/gettimeofday.h b/arch/mips/include/asm/vdso/gettimeofday.h index b08825531e9f..0ae9b4cbc153 100644 --- a/arch/mips/include/asm/vdso/gettimeofday.h +++ b/arch/mips/include/asm/vdso/gettimeofday.h @@ -26,8 +26,6 @@ #define __VDSO_USE_SYSCALL ULLONG_MAX -#ifdef CONFIG_MIPS_CLOCK_VSYSCALL - static __always_inline long gettimeofday_fallback( struct __kernel_old_timeval *_tv, struct timezone *_tz) @@ -48,17 +46,6 @@ static __always_inline long gettimeofday_fallback( return error ? -ret : ret; } -#else - -static __always_inline long gettimeofday_fallback( - struct __kernel_old_timeval *_tv, - struct timezone *_tz) -{ - return -1; -} - -#endif - static __always_inline long clock_gettime_fallback( clockid_t _clkid, struct __kernel_timespec *_ts) diff --git a/arch/mips/kernel/cacheinfo.c b/arch/mips/kernel/cacheinfo.c index f777e44653d5..47312c529410 100644 --- a/arch/mips/kernel/cacheinfo.c +++ b/arch/mips/kernel/cacheinfo.c @@ -50,6 +50,25 @@ static int __init_cache_level(unsigned int cpu) return 0; } +static void fill_cpumask_siblings(int cpu, cpumask_t *cpu_map) +{ + int cpu1; + + for_each_possible_cpu(cpu1) + if (cpus_are_siblings(cpu, cpu1)) + cpumask_set_cpu(cpu1, cpu_map); +} + +static void fill_cpumask_cluster(int cpu, cpumask_t *cpu_map) +{ + int cpu1; + int cluster = cpu_cluster(&cpu_data[cpu]); + + for_each_possible_cpu(cpu1) + if (cpu_cluster(&cpu_data[cpu1]) == cluster) + cpumask_set_cpu(cpu1, cpu_map); +} + static int __populate_cache_leaves(unsigned int cpu) { struct cpuinfo_mips *c = ¤t_cpu_data; @@ -57,14 +76,20 @@ static int __populate_cache_leaves(unsigned int cpu) struct cacheinfo *this_leaf = this_cpu_ci->info_list; if (c->icache.waysize) { + /* L1 caches are per core */ + fill_cpumask_siblings(cpu, &this_leaf->shared_cpu_map); populate_cache(dcache, this_leaf, 1, CACHE_TYPE_DATA); + fill_cpumask_siblings(cpu, &this_leaf->shared_cpu_map); populate_cache(icache, this_leaf, 1, CACHE_TYPE_INST); } else { populate_cache(dcache, this_leaf, 1, CACHE_TYPE_UNIFIED); } - if (c->scache.waysize) + if (c->scache.waysize) { + /* L2 cache is per cluster */ + fill_cpumask_cluster(cpu, &this_leaf->shared_cpu_map); populate_cache(scache, this_leaf, 2, CACHE_TYPE_UNIFIED); + } if (c->tcache.waysize) populate_cache(tcache, this_leaf, 3, CACHE_TYPE_UNIFIED); diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c index 46b76751f3a5..561154cbcc40 100644 --- a/arch/mips/net/ebpf_jit.c +++ b/arch/mips/net/ebpf_jit.c @@ -604,6 +604,7 @@ static void emit_const_to_reg(struct jit_ctx *ctx, int dst, u64 value) static int emit_bpf_tail_call(struct jit_ctx *ctx, int this_idx) { int off, b_off; + int tcc_reg; ctx->flags |= EBPF_SEEN_TC; /* @@ -616,14 +617,14 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx, int this_idx) b_off = b_imm(this_idx + 1, ctx); emit_instr(ctx, bne, MIPS_R_AT, MIPS_R_ZERO, b_off); /* - * if (--TCC < 0) + * if (TCC-- < 0) * goto out; */ /* Delay slot */ - emit_instr(ctx, daddiu, MIPS_R_T5, - (ctx->flags & EBPF_TCC_IN_V1) ? MIPS_R_V1 : MIPS_R_S4, -1); + tcc_reg = (ctx->flags & EBPF_TCC_IN_V1) ? MIPS_R_V1 : MIPS_R_S4; + emit_instr(ctx, daddiu, MIPS_R_T5, tcc_reg, -1); b_off = b_imm(this_idx + 1, ctx); - emit_instr(ctx, bltz, MIPS_R_T5, b_off); + emit_instr(ctx, bltz, tcc_reg, b_off); /* * prog = array->ptrs[index]; * if (prog == NULL) @@ -1803,7 +1804,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) unsigned int image_size; u8 *image_ptr; - if (!prog->jit_requested || MIPS_ISA_REV < 2) + if (!prog->jit_requested) return prog; tmp = bpf_jit_blind_constants(prog); diff --git a/arch/mips/pci/pci-xtalk-bridge.c b/arch/mips/pci/pci-xtalk-bridge.c index 7b4d40354ee7..30017d5945bc 100644 --- a/arch/mips/pci/pci-xtalk-bridge.c +++ b/arch/mips/pci/pci-xtalk-bridge.c @@ -279,16 +279,15 @@ static int bridge_set_affinity(struct irq_data *d, const struct cpumask *mask, struct bridge_irq_chip_data *data = d->chip_data; int bit = d->parent_data->hwirq; int pin = d->hwirq; - nasid_t nasid; int ret, cpu; ret = irq_chip_set_affinity_parent(d, mask, force); if (ret >= 0) { cpu = cpumask_first_and(mask, cpu_online_mask); - nasid = COMPACT_TO_NASID_NODEID(cpu_to_node(cpu)); + data->nnasid = COMPACT_TO_NASID_NODEID(cpu_to_node(cpu)); bridge_write(data->bc, b_int_addr[pin].addr, (((data->bc->intr_addr >> 30) & 0x30000) | - bit | (nasid << 8))); + bit | (data->nasid << 8))); bridge_read(data->bc, b_wid_tflush); } return ret; diff --git a/arch/mips/ralink/Kconfig b/arch/mips/ralink/Kconfig index 1434fa60f3db..94e9ce994494 100644 --- a/arch/mips/ralink/Kconfig +++ b/arch/mips/ralink/Kconfig @@ -51,6 +51,7 @@ choice select MIPS_GIC select COMMON_CLK select CLKSRC_MIPS_GIC + select HAVE_PCI if PCI_MT7621 endchoice choice diff --git a/arch/mips/sgi-ip27/ip27-irq.c b/arch/mips/sgi-ip27/ip27-irq.c index 37be04975831..79a2f6bd2b5a 100644 --- a/arch/mips/sgi-ip27/ip27-irq.c +++ b/arch/mips/sgi-ip27/ip27-irq.c @@ -73,6 +73,9 @@ static void setup_hub_mask(struct hub_irq_data *hd, const struct cpumask *mask) int cpu; cpu = cpumask_first_and(mask, cpu_online_mask); + if (cpu >= nr_cpu_ids) + cpu = cpumask_any(cpu_online_mask); + nasid = COMPACT_TO_NASID_NODEID(cpu_to_node(cpu)); hd->cpu = cpu; if (!cputoslice(cpu)) { @@ -139,6 +142,7 @@ static int hub_domain_alloc(struct irq_domain *domain, unsigned int virq, /* use CPU connected to nearest hub */ hub = hub_data(NASID_TO_COMPACT_NODEID(info->nasid)); setup_hub_mask(hd, &hub->h_cpus); + info->nasid = cpu_to_node(hd->cpu); /* Make sure it's not already pending when we connect it. */ REMOTE_HUB_CLR_INTR(info->nasid, swlevel); diff --git a/arch/mips/vdso/vgettimeofday.c b/arch/mips/vdso/vgettimeofday.c index 6ebdc37c89fc..6b83b6376a4b 100644 --- a/arch/mips/vdso/vgettimeofday.c +++ b/arch/mips/vdso/vgettimeofday.c @@ -17,12 +17,22 @@ int __vdso_clock_gettime(clockid_t clock, return __cvdso_clock_gettime32(clock, ts); } +#ifdef CONFIG_MIPS_CLOCK_VSYSCALL + +/* + * This is behind the ifdef so that we don't provide the symbol when there's no + * possibility of there being a usable clocksource, because there's nothing we + * can do without it. When libc fails the symbol lookup it should fall back on + * the standard syscall path. + */ int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz) { return __cvdso_gettimeofday(tv, tz); } +#endif /* CONFIG_MIPS_CLOCK_VSYSCALL */ + int __vdso_clock_getres(clockid_t clock_id, struct old_timespec32 *res) { @@ -43,12 +53,22 @@ int __vdso_clock_gettime(clockid_t clock, return __cvdso_clock_gettime(clock, ts); } +#ifdef CONFIG_MIPS_CLOCK_VSYSCALL + +/* + * This is behind the ifdef so that we don't provide the symbol when there's no + * possibility of there being a usable clocksource, because there's nothing we + * can do without it. When libc fails the symbol lookup it should fall back on + * the standard syscall path. + */ int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz) { return __cvdso_gettimeofday(tv, tz); } +#endif /* CONFIG_MIPS_CLOCK_VSYSCALL */ + int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res) { diff --git a/arch/nds32/include/asm/cacheflush.h b/arch/nds32/include/asm/cacheflush.h index d9ac7e6408ef..caddded56e77 100644 --- a/arch/nds32/include/asm/cacheflush.h +++ b/arch/nds32/include/asm/cacheflush.h @@ -9,7 +9,11 @@ #define PG_dcache_dirty PG_arch_1 void flush_icache_range(unsigned long start, unsigned long end); +#define flush_icache_range flush_icache_range + void flush_icache_page(struct vm_area_struct *vma, struct page *page); +#define flush_icache_page flush_icache_page + #ifdef CONFIG_CPU_CACHE_ALIASING void flush_cache_mm(struct mm_struct *mm); void flush_cache_dup_mm(struct mm_struct *mm); @@ -40,12 +44,11 @@ void invalidate_kernel_vmap_range(void *addr, int size); #define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&(mapping)->i_pages) #else -#include -#undef flush_icache_range -#undef flush_icache_page -#undef flush_icache_user_range void flush_icache_user_range(struct vm_area_struct *vma, struct page *page, unsigned long addr, int len); +#define flush_icache_user_range flush_icache_user_range + +#include #endif #endif /* __NDS32_CACHEFLUSH_H__ */ diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index b16237c95ea3..0c29d6cb2c8d 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -62,6 +62,7 @@ config PARISC select HAVE_FTRACE_MCOUNT_RECORD if HAVE_DYNAMIC_FTRACE select HAVE_KPROBES_ON_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_REGS + select HAVE_COPY_THREAD_TLS help The PA-RISC microprocessor is designed by Hewlett-Packard and used diff --git a/arch/parisc/include/asm/cmpxchg.h b/arch/parisc/include/asm/cmpxchg.h index f627c37dad9c..ab5c215cf46c 100644 --- a/arch/parisc/include/asm/cmpxchg.h +++ b/arch/parisc/include/asm/cmpxchg.h @@ -44,8 +44,14 @@ __xchg(unsigned long x, __volatile__ void *ptr, int size) ** if (((unsigned long)p & 0xf) == 0) ** return __ldcw(p); */ -#define xchg(ptr, x) \ - ((__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr), sizeof(*(ptr)))) +#define xchg(ptr, x) \ +({ \ + __typeof__(*(ptr)) __ret; \ + __typeof__(*(ptr)) _x_ = (x); \ + __ret = (__typeof__(*(ptr))) \ + __xchg((unsigned long)_x_, (ptr), sizeof(*(ptr))); \ + __ret; \ +}) /* bug catcher for when unsupported size is used - won't link */ extern void __cmpxchg_called_with_bad_pointer(void); diff --git a/arch/parisc/include/asm/kexec.h b/arch/parisc/include/asm/kexec.h index a99ea747d7ed..87e174006995 100644 --- a/arch/parisc/include/asm/kexec.h +++ b/arch/parisc/include/asm/kexec.h @@ -2,8 +2,6 @@ #ifndef _ASM_PARISC_KEXEC_H #define _ASM_PARISC_KEXEC_H -#ifdef CONFIG_KEXEC - /* Maximum physical address we can use pages from */ #define KEXEC_SOURCE_MEMORY_LIMIT (-1UL) /* Maximum address we can reach in physical address mode */ @@ -32,6 +30,4 @@ static inline void crash_setup_regs(struct pt_regs *newregs, #endif /* __ASSEMBLY__ */ -#endif /* CONFIG_KEXEC */ - #endif /* _ASM_PARISC_KEXEC_H */ diff --git a/arch/parisc/kernel/Makefile b/arch/parisc/kernel/Makefile index 2663c8f8be11..068d90950d93 100644 --- a/arch/parisc/kernel/Makefile +++ b/arch/parisc/kernel/Makefile @@ -37,5 +37,5 @@ obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o obj-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_KPROBES) += kprobes.o -obj-$(CONFIG_KEXEC) += kexec.o relocate_kernel.o +obj-$(CONFIG_KEXEC_CORE) += kexec.o relocate_kernel.o obj-$(CONFIG_KEXEC_FILE) += kexec_file.o diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c index 3b330e58a4f0..a6c9f49c6612 100644 --- a/arch/parisc/kernel/drivers.c +++ b/arch/parisc/kernel/drivers.c @@ -810,7 +810,7 @@ EXPORT_SYMBOL(device_to_hwpath); static void walk_native_bus(unsigned long io_io_low, unsigned long io_io_high, struct device *parent); -static void walk_lower_bus(struct parisc_device *dev) +static void __init walk_lower_bus(struct parisc_device *dev) { unsigned long io_io_low, io_io_high; diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index ecc5c2771208..230a6422b99f 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -208,8 +208,8 @@ arch_initcall(parisc_idle_init); * Copy architecture-specific thread state */ int -copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long kthread_arg, struct task_struct *p) +copy_thread_tls(unsigned long clone_flags, unsigned long usp, + unsigned long kthread_arg, struct task_struct *p, unsigned long tls) { struct pt_regs *cregs = &(p->thread.regs); void *stack = task_stack_page(p); @@ -254,9 +254,9 @@ copy_thread(unsigned long clone_flags, unsigned long usp, cregs->ksp = (unsigned long)stack + THREAD_SZ_ALGN + FRAME_SIZE; cregs->kpc = (unsigned long) &child_return; - /* Setup thread TLS area from the 4th parameter in clone */ + /* Setup thread TLS area */ if (clone_flags & CLONE_SETTLS) - cregs->cr27 = cregs->gr[23]; + cregs->cr27 = tls; } return 0; diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 83522c9fc7b6..37ac731a556b 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -91,11 +91,13 @@ MULTIPLEWORD := -mmultiple endif ifdef CONFIG_PPC64 +ifndef CONFIG_CC_IS_CLANG cflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mabi=elfv1) cflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mcall-aixdesc) aflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mabi=elfv1) aflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mabi=elfv2 endif +endif ifndef CONFIG_CC_IS_CLANG cflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mno-strict-align @@ -141,6 +143,7 @@ endif endif CFLAGS-$(CONFIG_PPC64) := $(call cc-option,-mtraceback=no) +ifndef CONFIG_CC_IS_CLANG ifdef CONFIG_CPU_LITTLE_ENDIAN CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv2,$(call cc-option,-mcall-aixdesc)) AFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv2) @@ -149,6 +152,7 @@ CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv1) CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mcall-aixdesc) AFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv1) endif +endif CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mcmodel=medium,$(call cc-option,-mminimal-toc)) CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mno-pointers-to-nested-functions) diff --git a/arch/powerpc/boot/libfdt_env.h b/arch/powerpc/boot/libfdt_env.h index 2abc8e83b95e..9757d4f6331e 100644 --- a/arch/powerpc/boot/libfdt_env.h +++ b/arch/powerpc/boot/libfdt_env.h @@ -6,6 +6,8 @@ #include #define INT_MAX ((int)(~0U>>1)) +#define UINT32_MAX ((u32)~0U) +#define INT32_MAX ((s32)(UINT32_MAX >> 1)) #include "of.h" diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h index 8561498e653c..d84d1417ddb6 100644 --- a/arch/powerpc/include/asm/asm-prototypes.h +++ b/arch/powerpc/include/asm/asm-prototypes.h @@ -152,9 +152,12 @@ void _kvmppc_save_tm_pr(struct kvm_vcpu *vcpu, u64 guest_msr); /* Patch sites */ extern s32 patch__call_flush_count_cache; extern s32 patch__flush_count_cache_return; +extern s32 patch__flush_link_stack_return; +extern s32 patch__call_kvm_flush_link_stack; extern s32 patch__memset_nocache, patch__memcpy_nocache; extern long flush_count_cache; +extern long kvm_flush_link_stack; #ifdef CONFIG_PPC_TRANSACTIONAL_MEM void kvmppc_save_tm_hv(struct kvm_vcpu *vcpu, u64 msr, bool preserve_nv); diff --git a/arch/powerpc/include/asm/fixmap.h b/arch/powerpc/include/asm/fixmap.h index 0cfc365d814b..722289a1d000 100644 --- a/arch/powerpc/include/asm/fixmap.h +++ b/arch/powerpc/include/asm/fixmap.h @@ -77,7 +77,12 @@ enum fixed_addresses { static inline void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags) { - map_kernel_page(fix_to_virt(idx), phys, flags); + if (__builtin_constant_p(idx)) + BUILD_BUG_ON(idx >= __end_of_fixed_addresses); + else if (WARN_ON(idx >= __end_of_fixed_addresses)) + return; + + map_kernel_page(__fix_to_virt(idx), phys, flags); } #endif /* !__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h index 5a9b6eb651b6..d19871763ed4 100644 --- a/arch/powerpc/include/asm/sections.h +++ b/arch/powerpc/include/asm/sections.h @@ -5,8 +5,22 @@ #include #include + +#define arch_is_kernel_initmem_freed arch_is_kernel_initmem_freed + #include +extern bool init_mem_is_free; + +static inline int arch_is_kernel_initmem_freed(unsigned long addr) +{ + if (!init_mem_is_free) + return 0; + + return addr >= (unsigned long)__init_begin && + addr < (unsigned long)__init_end; +} + extern char __head_end[]; #ifdef __powerpc64__ diff --git a/arch/powerpc/include/asm/security_features.h b/arch/powerpc/include/asm/security_features.h index 759597bf0fd8..ccf44c135389 100644 --- a/arch/powerpc/include/asm/security_features.h +++ b/arch/powerpc/include/asm/security_features.h @@ -81,6 +81,9 @@ static inline bool security_ftr_enabled(unsigned long feature) // Software required to flush count cache on context switch #define SEC_FTR_FLUSH_COUNT_CACHE 0x0000000000000400ull +// Software required to flush link stack on context switch +#define SEC_FTR_FLUSH_LINK_STACK 0x0000000000001000ull + // Features enabled by default #define SEC_FTR_DEFAULT \ diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h index e9a960e28f3c..d6102e34eb21 100644 --- a/arch/powerpc/include/asm/spinlock.h +++ b/arch/powerpc/include/asm/spinlock.h @@ -15,6 +15,7 @@ * * (the type definitions are in asm/spinlock_types.h) */ +#include #include #ifdef CONFIG_PPC64 #include @@ -36,10 +37,12 @@ #endif #ifdef CONFIG_PPC_PSERIES +DECLARE_STATIC_KEY_FALSE(shared_processor); + #define vcpu_is_preempted vcpu_is_preempted static inline bool vcpu_is_preempted(int cpu) { - if (!firmware_has_feature(FW_FEATURE_SPLPAR)) + if (!static_branch_unlikely(&shared_processor)) return false; return !!(be32_to_cpu(lppaca_of(cpu).yield_count) & 1); } diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 15002b51ff18..c92fe7fe9692 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -401,7 +401,7 @@ copy_to_user_mcsafe(void __user *to, const void *from, unsigned long n) return n; } -extern unsigned long __clear_user(void __user *addr, unsigned long size); +unsigned long __arch_clear_user(void __user *addr, unsigned long size); static inline unsigned long clear_user(void __user *addr, unsigned long size) { @@ -409,12 +409,17 @@ static inline unsigned long clear_user(void __user *addr, unsigned long size) might_fault(); if (likely(access_ok(addr, size))) { allow_write_to_user(addr, size); - ret = __clear_user(addr, size); + ret = __arch_clear_user(addr, size); prevent_write_to_user(addr, size); } return ret; } +static inline unsigned long __clear_user(void __user *addr, unsigned long size) +{ + return clear_user(addr, size); +} + extern long strncpy_from_user(char *dst, const char __user *src, long count); extern __must_check long strnlen_user(const char __user *str, long n); diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h index c61d59ed3b45..2ccb938d8544 100644 --- a/arch/powerpc/include/asm/vdso_datapage.h +++ b/arch/powerpc/include/asm/vdso_datapage.h @@ -82,6 +82,7 @@ struct vdso_data { __s32 wtom_clock_nsec; /* Wall to monotonic clock nsec */ __s64 wtom_clock_sec; /* Wall to monotonic clock sec */ struct timespec stamp_xtime; /* xtime as at tb_orig_stamp */ + __u32 hrtimer_res; /* hrtimer resolution */ __u32 syscall_map_64[SYSCALL_MAP_SIZE]; /* map of syscalls */ __u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */ }; @@ -103,6 +104,7 @@ struct vdso_data { __s32 wtom_clock_nsec; struct timespec stamp_xtime; /* xtime as at tb_orig_stamp */ __u32 stamp_sec_fraction; /* fractional seconds of stamp_xtime */ + __u32 hrtimer_res; /* hrtimer resolution */ __u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */ __u32 dcache_block_size; /* L1 d-cache block size */ __u32 icache_block_size; /* L1 i-cache block size */ diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index a7ca8fe62368..3c02445cf086 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -5,8 +5,8 @@ CFLAGS_ptrace.o += -DUTS_MACHINE='"$(UTS_MACHINE)"' -# Disable clang warning for using setjmp without setjmp.h header -CFLAGS_crash.o += $(call cc-disable-warning, builtin-requires-header) +# Avoid clang warnings around longjmp/setjmp declarations +CFLAGS_crash.o += -ffreestanding ifdef CONFIG_PPC64 CFLAGS_prom_init.o += $(NO_MINIMAL_TOC) diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 484f54dab247..5c0a1e17219b 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -387,6 +387,7 @@ int main(void) OFFSET(WTOM_CLOCK_NSEC, vdso_data, wtom_clock_nsec); OFFSET(STAMP_XTIME, vdso_data, stamp_xtime); OFFSET(STAMP_SEC_FRAC, vdso_data, stamp_sec_fraction); + OFFSET(CLOCK_HRTIMER_RES, vdso_data, hrtimer_res); OFFSET(CFG_ICACHE_BLOCKSZ, vdso_data, icache_block_size); OFFSET(CFG_DCACHE_BLOCKSZ, vdso_data, dcache_block_size); OFFSET(CFG_ICACHE_LOGBLOCKSZ, vdso_data, icache_log_block_size); @@ -417,7 +418,6 @@ int main(void) DEFINE(CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE); DEFINE(CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE); DEFINE(NSEC_PER_SEC, NSEC_PER_SEC); - DEFINE(CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC); #ifdef CONFIG_BUG DEFINE(BUG_ENTRY_SIZE, sizeof(struct bug_entry)); diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index d9279d0ee9f5..c031be8d41ff 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -897,12 +897,12 @@ void eeh_handle_normal_event(struct eeh_pe *pe) /* Log the event */ if (pe->type & EEH_PE_PHB) { - pr_err("EEH: PHB#%x failure detected, location: %s\n", + pr_err("EEH: Recovering PHB#%x, location: %s\n", pe->phb->global_number, eeh_pe_loc_get(pe)); } else { struct eeh_pe *phb_pe = eeh_phb_pe_get(pe->phb); - pr_err("EEH: Frozen PHB#%x-PE#%x detected\n", + pr_err("EEH: Recovering PHB#%x-PE#%x\n", pe->phb->global_number, pe->addr); pr_err("EEH: PE location: %s, PHB location: %s\n", eeh_pe_loc_get(pe), eeh_pe_loc_get(phb_pe)); diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 6467bdab8d40..3fd3ef352e3f 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -537,6 +537,7 @@ flush_count_cache: /* Save LR into r9 */ mflr r9 + // Flush the link stack .rept 64 bl .+4 .endr @@ -546,6 +547,11 @@ flush_count_cache: .balign 32 /* Restore LR */ 1: mtlr r9 + + // If we're just flushing the link stack, return here +3: nop + patch_site 3b patch__flush_link_stack_return + li r9,0x7fff mtctr r9 diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 5645bc9cbc09..add67498c126 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -619,8 +619,6 @@ void __do_irq(struct pt_regs *regs) trace_irq_entry(regs); - check_stack_overflow(); - /* * Query the platform PIC for the interrupt & ack it. * @@ -652,6 +650,8 @@ void do_IRQ(struct pt_regs *regs) irqsp = hardirq_ctx[raw_smp_processor_id()]; sirqsp = softirq_ctx[raw_smp_processor_id()]; + check_stack_overflow(); + /* Already there ? */ if (unlikely(cursp == irqsp || cursp == sirqsp)) { __do_irq(regs); diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index b55a7b4cb543..9bc0aa9aeb65 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -82,7 +82,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) subf r8,r6,r4 /* compute length */ add r8,r8,r5 /* ensure we get enough */ lwz r9,DCACHEL1LOGBLOCKSIZE(r10) /* Get log-2 of cache block size */ - srw. r8,r8,r9 /* compute line count */ + srd. r8,r8,r9 /* compute line count */ beqlr /* nothing to do? */ mtctr r8 1: dcbst 0,r6 @@ -98,7 +98,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) subf r8,r6,r4 /* compute length */ add r8,r8,r5 lwz r9,ICACHEL1LOGBLOCKSIZE(r10) /* Get log-2 of Icache block size */ - srw. r8,r8,r9 /* compute line count */ + srd. r8,r8,r9 /* compute line count */ beqlr /* nothing to do? */ mtctr r8 2: icbi 0,r6 diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c index 7cfcb294b11c..d341b464f23c 100644 --- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -24,6 +24,7 @@ enum count_cache_flush_type { COUNT_CACHE_FLUSH_HW = 0x4, }; static enum count_cache_flush_type count_cache_flush_type = COUNT_CACHE_FLUSH_NONE; +static bool link_stack_flush_enabled; bool barrier_nospec_enabled; static bool no_nospec; @@ -141,32 +142,33 @@ ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, cha thread_priv = security_ftr_enabled(SEC_FTR_L1D_THREAD_PRIV); - if (rfi_flush || thread_priv) { + if (rfi_flush) { struct seq_buf s; seq_buf_init(&s, buf, PAGE_SIZE - 1); - seq_buf_printf(&s, "Mitigation: "); - - if (rfi_flush) - seq_buf_printf(&s, "RFI Flush"); - - if (rfi_flush && thread_priv) - seq_buf_printf(&s, ", "); - + seq_buf_printf(&s, "Mitigation: RFI Flush"); if (thread_priv) - seq_buf_printf(&s, "L1D private per thread"); + seq_buf_printf(&s, ", L1D private per thread"); seq_buf_printf(&s, "\n"); return s.len; } + if (thread_priv) + return sprintf(buf, "Vulnerable: L1D private per thread\n"); + if (!security_ftr_enabled(SEC_FTR_L1D_FLUSH_HV) && !security_ftr_enabled(SEC_FTR_L1D_FLUSH_PR)) return sprintf(buf, "Not affected\n"); return sprintf(buf, "Vulnerable\n"); } + +ssize_t cpu_show_l1tf(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_meltdown(dev, attr, buf); +} #endif ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf) @@ -212,11 +214,19 @@ ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, c if (ccd) seq_buf_printf(&s, "Indirect branch cache disabled"); + + if (link_stack_flush_enabled) + seq_buf_printf(&s, ", Software link stack flush"); + } else if (count_cache_flush_type != COUNT_CACHE_FLUSH_NONE) { seq_buf_printf(&s, "Mitigation: Software count cache flush"); if (count_cache_flush_type == COUNT_CACHE_FLUSH_HW) seq_buf_printf(&s, " (hardware accelerated)"); + + if (link_stack_flush_enabled) + seq_buf_printf(&s, ", Software link stack flush"); + } else if (btb_flush_enabled) { seq_buf_printf(&s, "Mitigation: Branch predictor state flush"); } else { @@ -377,18 +387,49 @@ static __init int stf_barrier_debugfs_init(void) device_initcall(stf_barrier_debugfs_init); #endif /* CONFIG_DEBUG_FS */ +static void no_count_cache_flush(void) +{ + count_cache_flush_type = COUNT_CACHE_FLUSH_NONE; + pr_info("count-cache-flush: software flush disabled.\n"); +} + static void toggle_count_cache_flush(bool enable) { - if (!enable || !security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE)) { + if (!security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE) && + !security_ftr_enabled(SEC_FTR_FLUSH_LINK_STACK)) + enable = false; + + if (!enable) { patch_instruction_site(&patch__call_flush_count_cache, PPC_INST_NOP); - count_cache_flush_type = COUNT_CACHE_FLUSH_NONE; - pr_info("count-cache-flush: software flush disabled.\n"); +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + patch_instruction_site(&patch__call_kvm_flush_link_stack, PPC_INST_NOP); +#endif + pr_info("link-stack-flush: software flush disabled.\n"); + link_stack_flush_enabled = false; + no_count_cache_flush(); return; } + // This enables the branch from _switch to flush_count_cache patch_branch_site(&patch__call_flush_count_cache, (u64)&flush_count_cache, BRANCH_SET_LINK); +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + // This enables the branch from guest_exit_cont to kvm_flush_link_stack + patch_branch_site(&patch__call_kvm_flush_link_stack, + (u64)&kvm_flush_link_stack, BRANCH_SET_LINK); +#endif + + pr_info("link-stack-flush: software flush enabled.\n"); + link_stack_flush_enabled = true; + + // If we just need to flush the link stack, patch an early return + if (!security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE)) { + patch_instruction_site(&patch__flush_link_stack_return, PPC_INST_BLR); + no_count_cache_flush(); + return; + } + if (!security_ftr_enabled(SEC_FTR_BCCTR_FLUSH_ASSIST)) { count_cache_flush_type = COUNT_CACHE_FLUSH_SW; pr_info("count-cache-flush: full software flush sequence enabled.\n"); @@ -407,11 +448,20 @@ void setup_count_cache_flush(void) if (no_spectrev2 || cpu_mitigations_off()) { if (security_ftr_enabled(SEC_FTR_BCCTRL_SERIALISED) || security_ftr_enabled(SEC_FTR_COUNT_CACHE_DISABLED)) - pr_warn("Spectre v2 mitigations not under software control, can't disable\n"); + pr_warn("Spectre v2 mitigations not fully under software control, can't disable\n"); enable = false; } + /* + * There's no firmware feature flag/hypervisor bit to tell us we need to + * flush the link stack on context switch. So we set it here if we see + * either of the Spectre v2 mitigations that aim to protect userspace. + */ + if (security_ftr_enabled(SEC_FTR_COUNT_CACHE_DISABLED) || + security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE)) + security_ftr_set(SEC_FTR_FLUSH_LINK_STACK); + toggle_count_cache_flush(enable); } diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 694522308cd5..11301a1187f3 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -232,7 +232,7 @@ static u64 scan_dispatch_log(u64 stop_tb) * Accumulate stolen time by scanning the dispatch trace log. * Called on entry from user mode. */ -void accumulate_stolen_time(void) +void notrace accumulate_stolen_time(void) { u64 sst, ust; unsigned long save_irq_soft_mask = irq_soft_mask_return(); @@ -959,6 +959,7 @@ void update_vsyscall(struct timekeeper *tk) vdso_data->wtom_clock_nsec = tk->wall_to_monotonic.tv_nsec; vdso_data->stamp_xtime = xt; vdso_data->stamp_sec_fraction = frac_sec; + vdso_data->hrtimer_res = hrtimer_resolution; smp_wmb(); ++(vdso_data->tb_update_count); } diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 82f43535e686..014ff0701f24 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -250,15 +250,22 @@ static void oops_end(unsigned long flags, struct pt_regs *regs, } NOKPROBE_SYMBOL(oops_end); +static char *get_mmu_str(void) +{ + if (early_radix_enabled()) + return " MMU=Radix"; + if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE)) + return " MMU=Hash"; + return ""; +} + static int __die(const char *str, struct pt_regs *regs, long err) { printk("Oops: %s, sig: %ld [#%d]\n", str, err, ++die_counter); - printk("%s PAGE_SIZE=%luK%s%s%s%s%s%s%s %s\n", + printk("%s PAGE_SIZE=%luK%s%s%s%s%s%s %s\n", IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN) ? "LE" : "BE", - PAGE_SIZE / 1024, - early_radix_enabled() ? " MMU=Radix" : "", - early_mmu_has_feature(MMU_FTR_HPTE_TABLE) ? " MMU=Hash" : "", + PAGE_SIZE / 1024, get_mmu_str(), IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "", IS_ENABLED(CONFIG_SMP) ? " SMP" : "", IS_ENABLED(CONFIG_SMP) ? (" NR_CPUS=" __stringify(NR_CPUS)) : "", diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S index becd9f8767ed..a967e795b96d 100644 --- a/arch/powerpc/kernel/vdso32/gettimeofday.S +++ b/arch/powerpc/kernel/vdso32/gettimeofday.S @@ -156,12 +156,15 @@ V_FUNCTION_BEGIN(__kernel_clock_getres) cror cr0*4+eq,cr0*4+eq,cr1*4+eq bne cr0,99f + mflr r12 + .cfi_register lr,r12 + bl __get_datapage@local /* get data page */ + lwz r5, CLOCK_HRTIMER_RES(r3) + mtlr r12 li r3,0 cmpli cr0,r4,0 crclr cr0*4+so beqlr - lis r5,CLOCK_REALTIME_RES@h - ori r5,r5,CLOCK_REALTIME_RES@l stw r3,TSPC32_TV_SEC(r4) stw r5,TSPC32_TV_NSEC(r4) blr diff --git a/arch/powerpc/kernel/vdso64/cacheflush.S b/arch/powerpc/kernel/vdso64/cacheflush.S index 3f92561a64c4..526f5ba2593e 100644 --- a/arch/powerpc/kernel/vdso64/cacheflush.S +++ b/arch/powerpc/kernel/vdso64/cacheflush.S @@ -35,7 +35,7 @@ V_FUNCTION_BEGIN(__kernel_sync_dicache) subf r8,r6,r4 /* compute length */ add r8,r8,r5 /* ensure we get enough */ lwz r9,CFG_DCACHE_LOGBLOCKSZ(r10) - srw. r8,r8,r9 /* compute line count */ + srd. r8,r8,r9 /* compute line count */ crclr cr0*4+so beqlr /* nothing to do? */ mtctr r8 @@ -52,7 +52,7 @@ V_FUNCTION_BEGIN(__kernel_sync_dicache) subf r8,r6,r4 /* compute length */ add r8,r8,r5 lwz r9,CFG_ICACHE_LOGBLOCKSZ(r10) - srw. r8,r8,r9 /* compute line count */ + srd. r8,r8,r9 /* compute line count */ crclr cr0*4+so beqlr /* nothing to do? */ mtctr r8 diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S index 07bfe33fe874..81757f06bbd7 100644 --- a/arch/powerpc/kernel/vdso64/gettimeofday.S +++ b/arch/powerpc/kernel/vdso64/gettimeofday.S @@ -186,12 +186,15 @@ V_FUNCTION_BEGIN(__kernel_clock_getres) cror cr0*4+eq,cr0*4+eq,cr1*4+eq bne cr0,99f + mflr r12 + .cfi_register lr,r12 + bl V_LOCAL_FUNC(__get_datapage) + lwz r5, CLOCK_HRTIMER_RES(r3) + mtlr r12 li r3,0 cmpldi cr0,r4,0 crclr cr0*4+so beqlr - lis r5,CLOCK_REALTIME_RES@h - ori r5,r5,CLOCK_REALTIME_RES@l std r3,TSPC64_TV_SEC(r4) std r5,TSPC64_TV_NSEC(r4) blr diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index faebcbb8c4db..c6fbbd29bd87 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -11,6 +11,7 @@ */ #include +#include #include #include #include @@ -1116,7 +1117,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) ld r7, VCPU_GPR(R7)(r4) bne ret_to_ultra - lwz r0, VCPU_CR(r4) + ld r0, VCPU_CR(r4) mtcr r0 ld r0, VCPU_GPR(R0)(r4) @@ -1136,7 +1137,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) * R3 = UV_RETURN */ ret_to_ultra: - lwz r0, VCPU_CR(r4) + ld r0, VCPU_CR(r4) mtcr r0 ld r0, VCPU_GPR(R3)(r4) @@ -1487,6 +1488,13 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */ 1: #endif /* CONFIG_KVM_XICS */ + /* + * Possibly flush the link stack here, before we do a blr in + * guest_exit_short_path. + */ +1: nop + patch_site 1b patch__call_kvm_flush_link_stack + /* If we came in through the P9 short path, go back out to C now */ lwz r0, STACK_SLOT_SHORT_PATH(r1) cmpwi r0, 0 @@ -1963,6 +1971,28 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) mtlr r0 blr +.balign 32 +.global kvm_flush_link_stack +kvm_flush_link_stack: + /* Save LR into r0 */ + mflr r0 + + /* Flush the link stack. On Power8 it's up to 32 entries in size. */ + .rept 32 + bl .+4 + .endr + + /* And on Power9 it's up to 64. */ +BEGIN_FTR_SECTION + .rept 32 + bl .+4 + .endr +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) + + /* Restore LR */ + mtlr r0 + blr + kvmppc_guest_external: /* External interrupt, first check for host_ipi. If this is * set, we know the host wants us out so let's do it now diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index a3f9c665bb5b..baa740815b3c 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -2005,6 +2005,10 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type) pr_devel("Creating xive for partition\n"); + /* Already there ? */ + if (kvm->arch.xive) + return -EEXIST; + xive = kvmppc_xive_get_device(kvm, type); if (!xive) return -ENOMEM; @@ -2014,12 +2018,6 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type) xive->kvm = kvm; mutex_init(&xive->lock); - /* Already there ? */ - if (kvm->arch.xive) - ret = -EEXIST; - else - kvm->arch.xive = xive; - /* We use the default queue size set by the host */ xive->q_order = xive_native_default_eq_shift(); if (xive->q_order < PAGE_SHIFT) @@ -2039,6 +2037,7 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type) if (ret) return ret; + kvm->arch.xive = xive; return 0; } diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index 78b906ffa0d2..5a3373e06e60 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -50,6 +50,24 @@ static void kvmppc_xive_native_cleanup_queue(struct kvm_vcpu *vcpu, int prio) } } +static int kvmppc_xive_native_configure_queue(u32 vp_id, struct xive_q *q, + u8 prio, __be32 *qpage, + u32 order, bool can_escalate) +{ + int rc; + __be32 *qpage_prev = q->qpage; + + rc = xive_native_configure_queue(vp_id, q, prio, qpage, order, + can_escalate); + if (rc) + return rc; + + if (qpage_prev) + put_page(virt_to_page(qpage_prev)); + + return rc; +} + void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu) { struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu; @@ -582,19 +600,14 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive, q->guest_qaddr = 0; q->guest_qshift = 0; - rc = xive_native_configure_queue(xc->vp_id, q, priority, - NULL, 0, true); + rc = kvmppc_xive_native_configure_queue(xc->vp_id, q, priority, + NULL, 0, true); if (rc) { pr_err("Failed to reset queue %d for VCPU %d: %d\n", priority, xc->server_num, rc); return rc; } - if (q->qpage) { - put_page(virt_to_page(q->qpage)); - q->qpage = NULL; - } - return 0; } @@ -624,12 +637,6 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive, srcu_idx = srcu_read_lock(&kvm->srcu); gfn = gpa_to_gfn(kvm_eq.qaddr); - page = gfn_to_page(kvm, gfn); - if (is_error_page(page)) { - srcu_read_unlock(&kvm->srcu, srcu_idx); - pr_err("Couldn't get queue page %llx!\n", kvm_eq.qaddr); - return -EINVAL; - } page_size = kvm_host_page_size(kvm, gfn); if (1ull << kvm_eq.qshift > page_size) { @@ -638,6 +645,13 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive, return -EINVAL; } + page = gfn_to_page(kvm, gfn); + if (is_error_page(page)) { + srcu_read_unlock(&kvm->srcu, srcu_idx); + pr_err("Couldn't get queue page %llx!\n", kvm_eq.qaddr); + return -EINVAL; + } + qaddr = page_to_virt(page) + (kvm_eq.qaddr & ~PAGE_MASK); srcu_read_unlock(&kvm->srcu, srcu_idx); @@ -653,8 +667,8 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive, * OPAL level because the use of END ESBs is not supported by * Linux. */ - rc = xive_native_configure_queue(xc->vp_id, q, priority, - (__be32 *) qaddr, kvm_eq.qshift, true); + rc = kvmppc_xive_native_configure_queue(xc->vp_id, q, priority, + (__be32 *) qaddr, kvm_eq.qshift, true); if (rc) { pr_err("Failed to configure queue %d for VCPU %d: %d\n", priority, xc->server_num, rc); @@ -1081,7 +1095,6 @@ static int kvmppc_xive_native_create(struct kvm_device *dev, u32 type) dev->private = xive; xive->dev = dev; xive->kvm = kvm; - kvm->arch.xive = xive; mutex_init(&xive->mapping_lock); mutex_init(&xive->lock); @@ -1102,6 +1115,7 @@ static int kvmppc_xive_native_create(struct kvm_device *dev, u32 type) if (ret) return ret; + kvm->arch.xive = xive; return 0; } diff --git a/arch/powerpc/lib/string_32.S b/arch/powerpc/lib/string_32.S index f69a6aab7bfb..1ddb26394e8a 100644 --- a/arch/powerpc/lib/string_32.S +++ b/arch/powerpc/lib/string_32.S @@ -17,7 +17,7 @@ CACHELINE_BYTES = L1_CACHE_BYTES LG_CACHELINE_BYTES = L1_CACHE_SHIFT CACHELINE_MASK = (L1_CACHE_BYTES-1) -_GLOBAL(__clear_user) +_GLOBAL(__arch_clear_user) /* * Use dcbz on the complete cache lines in the destination * to set them to zero. This requires that the destination @@ -87,4 +87,4 @@ _GLOBAL(__clear_user) EX_TABLE(8b, 91b) EX_TABLE(9b, 91b) -EXPORT_SYMBOL(__clear_user) +EXPORT_SYMBOL(__arch_clear_user) diff --git a/arch/powerpc/lib/string_64.S b/arch/powerpc/lib/string_64.S index 507b18b1660e..169872bc0892 100644 --- a/arch/powerpc/lib/string_64.S +++ b/arch/powerpc/lib/string_64.S @@ -17,7 +17,7 @@ PPC64_CACHES: .section ".text" /** - * __clear_user: - Zero a block of memory in user space, with less checking. + * __arch_clear_user: - Zero a block of memory in user space, with less checking. * @to: Destination address, in user space. * @n: Number of bytes to zero. * @@ -58,7 +58,7 @@ err3; stb r0,0(r3) mr r3,r4 blr -_GLOBAL_TOC(__clear_user) +_GLOBAL_TOC(__arch_clear_user) cmpdi r4,32 neg r6,r3 li r0,0 @@ -181,4 +181,4 @@ err1; dcbz 0,r3 cmpdi r4,32 blt .Lshort_clear b .Lmedium_clear -EXPORT_SYMBOL(__clear_user) +EXPORT_SYMBOL(__arch_clear_user) diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index 6c123760164e..83c51a7d7eee 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -294,10 +294,18 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend, ret = mmu_hash_ops.hpte_insert(hpteg, vpn, paddr, tprot, HPTE_V_BOLTED, psize, psize, ssize); - + if (ret == -1) { + /* Try to remove a non bolted entry */ + ret = mmu_hash_ops.hpte_remove(hpteg); + if (ret != -1) + ret = mmu_hash_ops.hpte_insert(hpteg, vpn, paddr, tprot, + HPTE_V_BOLTED, psize, psize, + ssize); + } if (ret < 0) break; + cond_resched(); #ifdef CONFIG_DEBUG_PAGEALLOC if (debug_pagealloc_enabled() && (paddr >> PAGE_SHIFT) < linear_map_hash_count) diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index be941d382c8d..9f5b32163bda 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -104,6 +104,27 @@ int __weak remove_section_mapping(unsigned long start, unsigned long end) return -ENODEV; } +#define FLUSH_CHUNK_SIZE SZ_1G +/** + * flush_dcache_range_chunked(): Write any modified data cache blocks out to + * memory and invalidate them, in chunks of up to FLUSH_CHUNK_SIZE + * Does not invalidate the corresponding instruction cache blocks. + * + * @start: the start address + * @stop: the stop address (exclusive) + * @chunk: the max size of the chunks + */ +static void flush_dcache_range_chunked(unsigned long start, unsigned long stop, + unsigned long chunk) +{ + unsigned long i; + + for (i = start; i < stop; i += chunk) { + flush_dcache_range(i, min(stop, i + chunk)); + cond_resched(); + } +} + int __ref arch_add_memory(int nid, u64 start, u64 size, struct mhp_restrictions *restrictions) { @@ -120,7 +141,8 @@ int __ref arch_add_memory(int nid, u64 start, u64 size, start, start + size, rc); return -EFAULT; } - flush_dcache_range(start, start + size); + + flush_dcache_range_chunked(start, start + size, FLUSH_CHUNK_SIZE); return __add_pages(nid, start_pfn, nr_pages, restrictions); } @@ -130,14 +152,14 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct page *page = pfn_to_page(start_pfn) + vmem_altmap_offset(altmap); int ret; - __remove_pages(page_zone(page), start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); /* Remove htab bolted mappings for this section of memory */ start = (unsigned long)__va(start); - flush_dcache_range(start, start + size); + flush_dcache_range_chunked(start, start + size, FLUSH_CHUNK_SIZE); + ret = remove_section_mapping(start, start + size); WARN_ON_ONCE(ret); @@ -260,6 +282,14 @@ void __init mem_init(void) BUILD_BUG_ON(MMU_PAGE_COUNT > 16); #ifdef CONFIG_SWIOTLB + /* + * Some platforms (e.g. 85xx) limit DMA-able memory way below + * 4G. We force memblock to bottom-up mode to ensure that the + * memory allocated in swiotlb_init() is DMA-able. + * As it's the last memblock allocation, no need to reset it + * back to to-down. + */ + memblock_set_bottom_up(true); swiotlb_init(0); #endif diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c index 42bbcd47cc85..dffe1a45b6ed 100644 --- a/arch/powerpc/mm/slice.c +++ b/arch/powerpc/mm/slice.c @@ -50,7 +50,7 @@ static void slice_print_mask(const char *label, const struct slice_mask *mask) { #endif -static inline bool slice_addr_is_low(unsigned long addr) +static inline notrace bool slice_addr_is_low(unsigned long addr) { u64 tmp = (u64)addr; @@ -659,7 +659,7 @@ unsigned long arch_get_unmapped_area_topdown(struct file *filp, mm_ctx_user_psize(¤t->mm->context), 1); } -unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr) +unsigned int notrace get_slice_psize(struct mm_struct *mm, unsigned long addr) { unsigned char *psizes; int index, mask_index; diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c index f18d5067cd0f..fe489fc01c73 100644 --- a/arch/powerpc/platforms/cell/spufs/sched.c +++ b/arch/powerpc/platforms/cell/spufs/sched.c @@ -51,11 +51,6 @@ static struct task_struct *spusched_task; static struct timer_list spusched_timer; static struct timer_list spuloadavg_timer; -/* - * Priority of a normal, non-rt, non-niced'd process (aka nice level 0). - */ -#define NORMAL_PRIO 120 - /* * Frequency of the spu scheduler tick. By default we do one SPU scheduler * tick for every 10 CPU scheduler ticks. diff --git a/arch/powerpc/platforms/powernv/opal-imc.c b/arch/powerpc/platforms/powernv/opal-imc.c index e04b20625cb9..7ccc5c85c74e 100644 --- a/arch/powerpc/platforms/powernv/opal-imc.c +++ b/arch/powerpc/platforms/powernv/opal-imc.c @@ -285,7 +285,14 @@ static int opal_imc_counters_probe(struct platform_device *pdev) domain = IMC_DOMAIN_THREAD; break; case IMC_TYPE_TRACE: - domain = IMC_DOMAIN_TRACE; + /* + * FIXME. Using trace_imc events to monitor application + * or KVM thread performance can cause a checkstop + * (system crash). + * Disable it for now. + */ + pr_info_once("IMC: disabling trace_imc PMU\n"); + domain = -1; break; default: pr_warn("IMC Unknown Device type \n"); diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 2825d004dece..c0bea75ac27b 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -945,6 +945,23 @@ void __init pnv_pci_init(void) if (!firmware_has_feature(FW_FEATURE_OPAL)) return; +#ifdef CONFIG_PCIEPORTBUS + /* + * On PowerNV PCIe devices are (currently) managed in cooperation + * with firmware. This isn't *strictly* required, but there's enough + * assumptions baked into both firmware and the platform code that + * it's unwise to allow the portbus services to be used. + * + * We need to fix this eventually, but for now set this flag to disable + * the portbus driver. The AER service isn't required since that AER + * events are handled via EEH. The pciehp hotplug driver can't work + * without kernel changes (and portbus binding breaks pnv_php). The + * other services also require some thinking about how we're going + * to integrate them. + */ + pcie_ports_disabled = true; +#endif + /* Look for IODA IO-Hubs. */ for_each_compatible_node(np, NULL, "ibm,ioda-hub") { pnv_pci_init_ioda_hub(np); diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c index b33251d75927..572651a5c87b 100644 --- a/arch/powerpc/platforms/pseries/cmm.c +++ b/arch/powerpc/platforms/pseries/cmm.c @@ -411,6 +411,10 @@ static struct bus_type cmm_subsys = { .dev_name = "cmm", }; +static void cmm_release_device(struct device *dev) +{ +} + /** * cmm_sysfs_register - Register with sysfs * @@ -426,6 +430,7 @@ static int cmm_sysfs_register(struct device *dev) dev->id = 0; dev->bus = &cmm_subsys; + dev->release = cmm_release_device; if ((rc = device_register(dev))) goto subsys_unregister; diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 61883291defc..ee07d0718bf1 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -152,7 +152,7 @@ static int papr_scm_meta_get(struct papr_scm_priv *p, int len, read; int64_t ret; - if ((hdr->in_offset + hdr->in_length) >= p->metadata_size) + if ((hdr->in_offset + hdr->in_length) > p->metadata_size) return -EINVAL; for (len = hdr->in_length; len; len -= read) { @@ -206,7 +206,7 @@ static int papr_scm_meta_set(struct papr_scm_priv *p, __be64 data_be; int64_t ret; - if ((hdr->in_offset + hdr->in_length) >= p->metadata_size) + if ((hdr->in_offset + hdr->in_length) > p->metadata_size) return -EINVAL; for (len = hdr->in_length; len; len -= wrote) { diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 0a40201f315f..0c8421dd01ab 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -74,6 +74,9 @@ #include "pseries.h" #include "../../../../drivers/pci/pci.h" +DEFINE_STATIC_KEY_FALSE(shared_processor); +EXPORT_SYMBOL_GPL(shared_processor); + int CMO_PrPSP = -1; int CMO_SecPSP = -1; unsigned long CMO_PageSize = (ASM_CONST(1) << IOMMU_PAGE_SHIFT_4K); @@ -758,6 +761,10 @@ static void __init pSeries_setup_arch(void) if (firmware_has_feature(FW_FEATURE_LPAR)) { vpa_init(boot_cpuid); + + if (lppaca_shared_proc(get_lppaca())) + static_branch_enable(&shared_processor); + ppc_md.power_save = pseries_lpar_idle; ppc_md.enable_pmcs = pseries_lpar_enable_pmcs; #ifdef CONFIG_PCI_IOV diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index df832b09e3e9..f5fadbd2533a 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -1035,6 +1035,15 @@ static int xive_irq_alloc_data(unsigned int virq, irq_hw_number_t hw) xd->target = XIVE_INVALID_TARGET; irq_set_handler_data(virq, xd); + /* + * Turn OFF by default the interrupt being mapped. A side + * effect of this check is the mapping the ESB page of the + * interrupt in the Linux address space. This prevents page + * fault issues in the crash handler which masks all + * interrupts. + */ + xive_esb_read(xd, XIVE_ESB_SET_PQ_01); + return 0; } diff --git a/arch/powerpc/sysdev/xive/spapr.c b/arch/powerpc/sysdev/xive/spapr.c index 33c10749edec..55dc61cb4867 100644 --- a/arch/powerpc/sysdev/xive/spapr.c +++ b/arch/powerpc/sysdev/xive/spapr.c @@ -392,20 +392,28 @@ static int xive_spapr_populate_irq_data(u32 hw_irq, struct xive_irq_data *data) data->esb_shift = esb_shift; data->trig_page = trig_page; + data->hw_irq = hw_irq; + /* * No chip-id for the sPAPR backend. This has an impact how we * pick a target. See xive_pick_irq_target(). */ data->src_chip = XIVE_INVALID_CHIP_ID; + /* + * When the H_INT_ESB flag is set, the H_INT_ESB hcall should + * be used for interrupt management. Skip the remapping of the + * ESB pages which are not available. + */ + if (data->flags & XIVE_IRQ_FLAG_H_INT_ESB) + return 0; + data->eoi_mmio = ioremap(data->eoi_page, 1u << data->esb_shift); if (!data->eoi_mmio) { pr_err("Failed to map EOI page for irq 0x%x\n", hw_irq); return -ENOMEM; } - data->hw_irq = hw_irq; - /* Full function page supports trigger */ if (flags & XIVE_SRC_TRIGGER) { data->trig_mmio = data->eoi_mmio; diff --git a/arch/powerpc/tools/relocs_check.sh b/arch/powerpc/tools/relocs_check.sh index 2b4e959caa36..7b9fe0a567cf 100755 --- a/arch/powerpc/tools/relocs_check.sh +++ b/arch/powerpc/tools/relocs_check.sh @@ -20,7 +20,7 @@ objdump="$1" vmlinux="$2" bad_relocs=$( -"$objdump" -R "$vmlinux" | +$objdump -R "$vmlinux" | # Only look at relocation lines. grep -E '\:' | awk '{print $1}' ) BRANCHES=$( -"$objdump" -R "$vmlinux" -D --start-address=0xc000000000000000 \ +$objdump -R "$vmlinux" -D --start-address=0xc000000000000000 \ --stop-address=${end_intr} | grep -e "^c[0-9a-f]*:[[:space:]]*\([0-9a-f][0-9a-f][[:space:]]\)\{4\}[[:space:]]*b" | grep -v '\<__start_initialization_multiplatform>' | diff --git a/arch/powerpc/xmon/Makefile b/arch/powerpc/xmon/Makefile index f142570ad860..c3842dbeb1b7 100644 --- a/arch/powerpc/xmon/Makefile +++ b/arch/powerpc/xmon/Makefile @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for xmon -# Disable clang warning for using setjmp without setjmp.h header -subdir-ccflags-y := $(call cc-disable-warning, builtin-requires-header) +# Avoid clang warnings around longjmp/setjmp declarations +subdir-ccflags-y := -ffreestanding GCOV_PROFILE := n KCOV_INSTRUMENT := n diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 8eebbc8860bb..ade9699aa0dd 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -61,6 +61,7 @@ config RISCV select SPARSEMEM_STATIC if 32BIT select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU select HAVE_ARCH_MMAP_RND_BITS + select HAVE_COPY_THREAD_TLS config ARCH_MMAP_RND_BITS_MIN default 18 if 64BIT diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index b94d8db5ddcc..c40fdcdeb950 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -142,7 +142,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, */ old = *parent; - if (function_graph_enter(old, self_addr, frame_pointer, parent)) + if (!function_graph_enter(old, self_addr, frame_pointer, parent)) *parent = return_hooker; } diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index 85e3c39bb60b..330b34706aa0 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -99,8 +99,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) return 0; } -int copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long arg, struct task_struct *p) +int copy_thread_tls(unsigned long clone_flags, unsigned long usp, + unsigned long arg, struct task_struct *p, unsigned long tls) { struct pt_regs *childregs = task_pt_regs(p); @@ -120,7 +120,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, if (usp) /* User fork */ childregs->sp = usp; if (clone_flags & CLONE_SETTLS) - childregs->tp = childregs->a5; + childregs->tp = tls; childregs->a0 = 0; /* Return value of fork() */ p->thread.ra = (unsigned long)ret_from_fork; } diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c index 3f15938dec89..c54bd3c79955 100644 --- a/arch/riscv/mm/cacheflush.c +++ b/arch/riscv/mm/cacheflush.c @@ -14,6 +14,7 @@ void flush_icache_all(void) { sbi_remote_fence_i(NULL); } +EXPORT_SYMBOL(flush_icache_all); /* * Performs an icache flush for the given MM context. RISC-V has no direct diff --git a/arch/riscv/net/bpf_jit_comp.c b/arch/riscv/net/bpf_jit_comp.c index 5451ef3845f2..7fbf56aab661 100644 --- a/arch/riscv/net/bpf_jit_comp.c +++ b/arch/riscv/net/bpf_jit_comp.c @@ -631,14 +631,14 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx) return -1; emit(rv_bgeu(RV_REG_A2, RV_REG_T1, off >> 1), ctx); - /* if (--TCC < 0) + /* if (TCC-- < 0) * goto out; */ emit(rv_addi(RV_REG_T1, tcc, -1), ctx); off = (tc_ninsn - (ctx->ninsns - start_insn)) << 2; if (is_13b_check(off, insn)) return -1; - emit(rv_blt(RV_REG_T1, RV_REG_ZERO, off >> 1), ctx); + emit(rv_blt(tcc, RV_REG_ZERO, off >> 1), ctx); /* prog = array->ptrs[index]; * if (!prog) diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index 5367950510f6..fa0150285d38 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -170,6 +170,11 @@ void startup_kernel(void) handle_relocs(__kaslr_offset); if (__kaslr_offset) { + /* + * Save KASLR offset for early dumps, before vmcore_info is set. + * Mark as uneven to distinguish from real vmcore_info pointer. + */ + S390_lowcore.vmcore_info = __kaslr_offset | 0x1UL; /* Clear non-relocated kernel */ if (IS_ENABLED(CONFIG_KERNEL_UNCOMPRESSED)) memset(img, 0, vmlinux.image_size); diff --git a/arch/s390/crypto/sha_common.c b/arch/s390/crypto/sha_common.c index d39e0f079217..686fe7aa192f 100644 --- a/arch/s390/crypto/sha_common.c +++ b/arch/s390/crypto/sha_common.c @@ -74,14 +74,17 @@ int s390_sha_final(struct shash_desc *desc, u8 *out) struct s390_sha_ctx *ctx = shash_desc_ctx(desc); unsigned int bsize = crypto_shash_blocksize(desc->tfm); u64 bits; - unsigned int n, mbl_offset; + unsigned int n; + int mbl_offset; n = ctx->count % bsize; bits = ctx->count * 8; - mbl_offset = s390_crypto_shash_parmsize(ctx->func) / sizeof(u32); + mbl_offset = s390_crypto_shash_parmsize(ctx->func); if (mbl_offset < 0) return -EINVAL; + mbl_offset = mbl_offset / sizeof(u32); + /* set total msg bit length (mbl) in CPACF parmblock */ switch (ctx->func) { case CPACF_KLMD_SHA_1: diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index bccb8f4a63e2..77606c4acd58 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -56,7 +56,12 @@ static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long address) crst_table_init(table, _REGION2_ENTRY_EMPTY); return (p4d_t *) table; } -#define p4d_free(mm, p4d) crst_table_free(mm, (unsigned long *) p4d) + +static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d) +{ + if (!mm_p4d_folded(mm)) + crst_table_free(mm, (unsigned long *) p4d); +} static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) { @@ -65,7 +70,12 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) crst_table_init(table, _REGION3_ENTRY_EMPTY); return (pud_t *) table; } -#define pud_free(mm, pud) crst_table_free(mm, (unsigned long *) pud) + +static inline void pud_free(struct mm_struct *mm, pud_t *pud) +{ + if (!mm_pud_folded(mm)) + crst_table_free(mm, (unsigned long *) pud); +} static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr) { @@ -83,6 +93,8 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr) static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) { + if (mm_pmd_folded(mm)) + return; pgtable_pmd_page_dtor(virt_to_page(pmd)); crst_table_free(mm, (unsigned long *) pmd); } diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 5ff98d76a66c..a9e46b83c536 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1173,8 +1173,6 @@ void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr); static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t entry) { - if (!MACHINE_HAS_NX) - pte_val(entry) &= ~_PAGE_NOEXEC; if (pte_present(entry)) pte_val(entry) &= ~_PAGE_UNUSED; if (mm_has_pgste(mm)) @@ -1191,6 +1189,8 @@ static inline pte_t mk_pte_phys(unsigned long physpage, pgprot_t pgprot) { pte_t __pte; pte_val(__pte) = physpage + pgprot_val(pgprot); + if (!MACHINE_HAS_NX) + pte_val(__pte) &= ~_PAGE_NOEXEC; return pte_mkyoung(__pte); } diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h index 64539c221672..2dc9eb4e1acc 100644 --- a/arch/s390/include/asm/timex.h +++ b/arch/s390/include/asm/timex.h @@ -10,8 +10,9 @@ #ifndef _ASM_S390_TIMEX_H #define _ASM_S390_TIMEX_H -#include +#include #include +#include /* The value of the TOD clock for 1.1.1970. */ #define TOD_UNIX_EPOCH 0x7d91048bca000000ULL @@ -186,15 +187,18 @@ extern unsigned char tod_clock_base[16] __aligned(8); /** * get_clock_monotonic - returns current time in clock rate units * - * The caller must ensure that preemption is disabled. * The clock and tod_clock_base get changed via stop_machine. - * Therefore preemption must be disabled when calling this - * function, otherwise the returned value is not guaranteed to - * be monotonic. + * Therefore preemption must be disabled, otherwise the returned + * value is not guaranteed to be monotonic. */ static inline unsigned long long get_tod_clock_monotonic(void) { - return get_tod_clock() - *(unsigned long long *) &tod_clock_base[1]; + unsigned long long tod; + + preempt_disable_notrace(); + tod = get_tod_clock() - *(unsigned long long *) &tod_clock_base[1]; + preempt_enable_notrace(); + return tod; } /** diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c index 7abe6ae261b4..f304802ecf7b 100644 --- a/arch/s390/kernel/dis.c +++ b/arch/s390/kernel/dis.c @@ -461,10 +461,11 @@ static int print_insn(char *buffer, unsigned char *code, unsigned long addr) ptr += sprintf(ptr, "%%c%i", value); else if (operand->flags & OPERAND_VR) ptr += sprintf(ptr, "%%v%i", value); - else if (operand->flags & OPERAND_PCREL) - ptr += sprintf(ptr, "%lx", (signed int) value - + addr); - else if (operand->flags & OPERAND_SIGNED) + else if (operand->flags & OPERAND_PCREL) { + void *pcrel = (void *)((int)value + addr); + + ptr += sprintf(ptr, "%px", pcrel); + } else if (operand->flags & OPERAND_SIGNED) ptr += sprintf(ptr, "%i", value); else ptr += sprintf(ptr, "%u", value); @@ -536,7 +537,7 @@ void show_code(struct pt_regs *regs) else *ptr++ = ' '; addr = regs->psw.addr + start - 32; - ptr += sprintf(ptr, "%016lx: ", addr); + ptr += sprintf(ptr, "%px: ", (void *)addr); if (start + opsize >= end) break; for (i = 0; i < opsize; i++) @@ -564,7 +565,7 @@ void print_fn_code(unsigned char *code, unsigned long len) opsize = insn_length(*code); if (opsize > len) break; - ptr += sprintf(ptr, "%p: ", code); + ptr += sprintf(ptr, "%px: ", code); for (i = 0; i < opsize; i++) ptr += sprintf(ptr, "%02x", code[i]); *ptr++ = '\t'; diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index 444a19125a81..cb8b1cc285c9 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -164,7 +164,9 @@ static bool kdump_csum_valid(struct kimage *image) #ifdef CONFIG_CRASH_DUMP int rc; + preempt_disable(); rc = CALL_ON_STACK(do_start_kdump, S390_lowcore.nodat_stack, 1, image); + preempt_enable(); return rc == 0; #else return false; @@ -254,10 +256,10 @@ void arch_crash_save_vmcoreinfo(void) VMCOREINFO_SYMBOL(lowcore_ptr); VMCOREINFO_SYMBOL(high_memory); VMCOREINFO_LENGTH(lowcore_ptr, NR_CPUS); - mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note()); vmcoreinfo_append_str("SDMA=%lx\n", __sdma); vmcoreinfo_append_str("EDMA=%lx\n", __edma); vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); + mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note()); } void machine_shutdown(void) diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index 48d48b6187c0..0eb1d1cc53a8 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -199,7 +199,7 @@ static const int cpumf_generic_events_user[] = { [PERF_COUNT_HW_BUS_CYCLES] = -1, }; -static int __hw_perf_event_init(struct perf_event *event) +static int __hw_perf_event_init(struct perf_event *event, unsigned int type) { struct perf_event_attr *attr = &event->attr; struct hw_perf_event *hwc = &event->hw; @@ -207,7 +207,7 @@ static int __hw_perf_event_init(struct perf_event *event) int err = 0; u64 ev; - switch (attr->type) { + switch (type) { case PERF_TYPE_RAW: /* Raw events are used to access counters directly, * hence do not permit excludes */ @@ -294,17 +294,16 @@ static int __hw_perf_event_init(struct perf_event *event) static int cpumf_pmu_event_init(struct perf_event *event) { + unsigned int type = event->attr.type; int err; - switch (event->attr.type) { - case PERF_TYPE_HARDWARE: - case PERF_TYPE_HW_CACHE: - case PERF_TYPE_RAW: - err = __hw_perf_event_init(event); - break; - default: + if (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_RAW) + err = __hw_perf_event_init(event, type); + else if (event->pmu->type == type) + /* Registered as unknown PMU */ + err = __hw_perf_event_init(event, PERF_TYPE_RAW); + else return -ENOENT; - } if (unlikely(err) && event->destroy) event->destroy(event); @@ -553,7 +552,7 @@ static int __init cpumf_pmu_init(void) return -ENODEV; cpumf_pmu.attr_groups = cpumf_cf_event_group(); - rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", PERF_TYPE_RAW); + rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", -1); if (rc) pr_err("Registering the cpum_cf PMU failed with rc=%i\n", rc); return rc; diff --git a/arch/s390/kernel/perf_cpum_cf_diag.c b/arch/s390/kernel/perf_cpum_cf_diag.c index 2654e348801a..e949ab832ed7 100644 --- a/arch/s390/kernel/perf_cpum_cf_diag.c +++ b/arch/s390/kernel/perf_cpum_cf_diag.c @@ -243,13 +243,13 @@ static int cf_diag_event_init(struct perf_event *event) int err = -ENOENT; debug_sprintf_event(cf_diag_dbg, 5, - "%s event %p cpu %d config %#llx " + "%s event %p cpu %d config %#llx type:%u " "sample_type %#llx cf_diag_events %d\n", __func__, - event, event->cpu, attr->config, attr->sample_type, - atomic_read(&cf_diag_events)); + event, event->cpu, attr->config, event->pmu->type, + attr->sample_type, atomic_read(&cf_diag_events)); if (event->attr.config != PERF_EVENT_CPUM_CF_DIAG || - event->attr.type != PERF_TYPE_RAW) + event->attr.type != event->pmu->type) goto out; /* Raw events are used to access counters directly, @@ -693,7 +693,7 @@ static int __init cf_diag_init(void) } debug_register_view(cf_diag_dbg, &debug_sprintf_view); - rc = perf_pmu_register(&cf_diag, "cpum_cf_diag", PERF_TYPE_RAW); + rc = perf_pmu_register(&cf_diag, "cpum_cf_diag", -1); if (rc) { debug_unregister_view(cf_diag_dbg, &debug_sprintf_view); debug_unregister(cf_diag_dbg); diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 3d8b12a9a6ff..fdb8083e7870 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -193,7 +193,7 @@ static int realloc_sampling_buffer(struct sf_buffer *sfb, unsigned long num_sdb, gfp_t gfp_flags) { int i, rc; - unsigned long *new, *tail; + unsigned long *new, *tail, *tail_prev = NULL; if (!sfb->sdbt || !sfb->tail) return -EINVAL; @@ -232,6 +232,7 @@ static int realloc_sampling_buffer(struct sf_buffer *sfb, sfb->num_sdbt++; /* Link current page to tail of chain */ *tail = (unsigned long)(void *) new + 1; + tail_prev = tail; tail = new; } @@ -241,10 +242,22 @@ static int realloc_sampling_buffer(struct sf_buffer *sfb, * issue, a new realloc call (if required) might succeed. */ rc = alloc_sample_data_block(tail, gfp_flags); - if (rc) + if (rc) { + /* Undo last SDBT. An SDBT with no SDB at its first + * entry but with an SDBT entry instead can not be + * handled by the interrupt handler code. + * Avoid this situation. + */ + if (tail_prev) { + sfb->num_sdbt--; + free_page((unsigned long) new); + tail = tail_prev; + } break; + } sfb->num_sdb++; tail++; + tail_prev = new = NULL; /* Allocated at least one SBD */ } /* Link sampling buffer to its origin */ @@ -1300,18 +1313,28 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all) */ if (flush_all && done) break; - - /* If an event overflow happened, discard samples by - * processing any remaining sample-data-blocks. - */ - if (event_overflow) - flush_all = 1; } /* Account sample overflows in the event hardware structure */ if (sampl_overflow) OVERFLOW_REG(hwc) = DIV_ROUND_UP(OVERFLOW_REG(hwc) + sampl_overflow, 1 + num_sdb); + + /* Perf_event_overflow() and perf_event_account_interrupt() limit + * the interrupt rate to an upper limit. Roughly 1000 samples per + * task tick. + * Hitting this limit results in a large number + * of throttled REF_REPORT_THROTTLE entries and the samples + * are dropped. + * Slightly increase the interval to avoid hitting this limit. + */ + if (event_overflow) { + SAMPL_RATE(hwc) += DIV_ROUND_UP(SAMPL_RATE(hwc), 10); + debug_sprintf_event(sfdbg, 1, "%s: rate adjustment %ld\n", + __func__, + DIV_ROUND_UP(SAMPL_RATE(hwc), 10)); + } + if (sampl_overflow || event_overflow) debug_sprintf_event(sfdbg, 4, "hw_perf_event_update: " "overflow stats: sample=%llu event=%llu\n", diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c index fcb6c2e92b07..1e75cc983546 100644 --- a/arch/s390/kernel/perf_event.c +++ b/arch/s390/kernel/perf_event.c @@ -224,9 +224,13 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { struct unwind_state state; + unsigned long addr; - unwind_for_each_frame(&state, current, regs, 0) - perf_callchain_store(entry, state.ip); + unwind_for_each_frame(&state, current, regs, 0) { + addr = unwind_get_return_address(&state); + if (!addr || perf_callchain_store(entry, addr)) + return; + } } /* Perf definitions for PMU event attributes in sysfs */ diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 44974654cbd0..06dddd7c4290 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -262,10 +262,13 @@ static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu) lc->spinlock_index = 0; lc->percpu_offset = __per_cpu_offset[cpu]; lc->kernel_asce = S390_lowcore.kernel_asce; + lc->user_asce = S390_lowcore.kernel_asce; lc->machine_flags = S390_lowcore.machine_flags; lc->user_timer = lc->system_timer = lc->steal_timer = lc->avg_steal_timer = 0; __ctl_store(lc->cregs_save_area, 0, 15); + lc->cregs_save_area[1] = lc->kernel_asce; + lc->cregs_save_area[7] = lc->vdso_asce; save_access_regs((unsigned int *) lc->access_regs_save_area); memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list, sizeof(lc->stfle_fac_list)); @@ -724,39 +727,67 @@ static void __ref smp_get_core_info(struct sclp_core_info *info, int early) static int smp_add_present_cpu(int cpu); -static int __smp_rescan_cpus(struct sclp_core_info *info, int sysfs_add) +static int smp_add_core(struct sclp_core_entry *core, cpumask_t *avail, + bool configured, bool early) { struct pcpu *pcpu; - cpumask_t avail; - int cpu, nr, i, j; + int cpu, nr, i; u16 address; nr = 0; - cpumask_xor(&avail, cpu_possible_mask, cpu_present_mask); - cpu = cpumask_first(&avail); - for (i = 0; (i < info->combined) && (cpu < nr_cpu_ids); i++) { - if (sclp.has_core_type && info->core[i].type != boot_core_type) + if (sclp.has_core_type && core->type != boot_core_type) + return nr; + cpu = cpumask_first(avail); + address = core->core_id << smp_cpu_mt_shift; + for (i = 0; (i <= smp_cpu_mtid) && (cpu < nr_cpu_ids); i++) { + if (pcpu_find_address(cpu_present_mask, address + i)) continue; - address = info->core[i].core_id << smp_cpu_mt_shift; - for (j = 0; j <= smp_cpu_mtid; j++) { - if (pcpu_find_address(cpu_present_mask, address + j)) - continue; - pcpu = pcpu_devices + cpu; - pcpu->address = address + j; - pcpu->state = - (cpu >= info->configured*(smp_cpu_mtid + 1)) ? - CPU_STATE_STANDBY : CPU_STATE_CONFIGURED; - smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN); - set_cpu_present(cpu, true); - if (sysfs_add && smp_add_present_cpu(cpu) != 0) - set_cpu_present(cpu, false); - else - nr++; - cpu = cpumask_next(cpu, &avail); - if (cpu >= nr_cpu_ids) + pcpu = pcpu_devices + cpu; + pcpu->address = address + i; + if (configured) + pcpu->state = CPU_STATE_CONFIGURED; + else + pcpu->state = CPU_STATE_STANDBY; + smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN); + set_cpu_present(cpu, true); + if (!early && smp_add_present_cpu(cpu) != 0) + set_cpu_present(cpu, false); + else + nr++; + cpumask_clear_cpu(cpu, avail); + cpu = cpumask_next(cpu, avail); + } + return nr; +} + +static int __smp_rescan_cpus(struct sclp_core_info *info, bool early) +{ + struct sclp_core_entry *core; + cpumask_t avail; + bool configured; + u16 core_id; + int nr, i; + + nr = 0; + cpumask_xor(&avail, cpu_possible_mask, cpu_present_mask); + /* + * Add IPL core first (which got logical CPU number 0) to make sure + * that all SMT threads get subsequent logical CPU numbers. + */ + if (early) { + core_id = pcpu_devices[0].address >> smp_cpu_mt_shift; + for (i = 0; i < info->configured; i++) { + core = &info->core[i]; + if (core->core_id == core_id) { + nr += smp_add_core(core, &avail, true, early); break; + } } } + for (i = 0; i < info->combined; i++) { + configured = i < info->configured; + nr += smp_add_core(&info->core[i], &avail, configured, early); + } return nr; } @@ -805,7 +836,7 @@ void __init smp_detect_cpus(void) /* Add CPUs present at boot */ get_online_cpus(); - __smp_rescan_cpus(info, 0); + __smp_rescan_cpus(info, true); put_online_cpus(); memblock_free_early((unsigned long)info, sizeof(*info)); } @@ -816,6 +847,8 @@ static void smp_init_secondary(void) S390_lowcore.last_update_clock = get_tod_clock(); restore_access_regs(S390_lowcore.access_regs_save_area); + set_cpu_flag(CIF_ASCE_PRIMARY); + set_cpu_flag(CIF_ASCE_SECONDARY); cpu_init(); preempt_disable(); init_cpu_timer(); @@ -1148,7 +1181,7 @@ int __ref smp_rescan_cpus(void) smp_get_core_info(info, 0); get_online_cpus(); mutex_lock(&smp_cpu_state_mutex); - nr = __smp_rescan_cpus(info, 1); + nr = __smp_rescan_cpus(info, false); mutex_unlock(&smp_cpu_state_mutex); put_online_cpus(); kfree(info); diff --git a/arch/s390/kernel/unwind_bc.c b/arch/s390/kernel/unwind_bc.c index a8204f952315..6e609b13c0ce 100644 --- a/arch/s390/kernel/unwind_bc.c +++ b/arch/s390/kernel/unwind_bc.c @@ -60,6 +60,11 @@ bool unwind_next_frame(struct unwind_state *state) ip = READ_ONCE_NOCHECK(sf->gprs[8]); reliable = false; regs = NULL; + if (!__kernel_text_address(ip)) { + /* skip bogus %r14 */ + state->regs = NULL; + return unwind_next_frame(state); + } } else { sf = (struct stack_frame *) state->sp; sp = READ_ONCE_NOCHECK(sf->back_chain); diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index a124f19f7b3c..c1d96e588152 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -291,10 +291,8 @@ void arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct zone *zone; - zone = page_zone(pfn_to_page(start_pfn)); - __remove_pages(zone, start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); vmem_remove_mapping(start, size); } #endif /* CONFIG_MEMORY_HOTPLUG */ diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c index 1864a8bb9622..de7ca4b6718f 100644 --- a/arch/s390/mm/maccess.c +++ b/arch/s390/mm/maccess.c @@ -70,7 +70,7 @@ void notrace s390_kernel_write(void *dst, const void *src, size_t size) spin_unlock_irqrestore(&s390_kernel_write_lock, flags); } -static int __memcpy_real(void *dest, void *src, size_t count) +static int __no_sanitize_address __memcpy_real(void *dest, void *src, size_t count) { register unsigned long _dest asm("2") = (unsigned long) dest; register unsigned long _len1 asm("3") = (unsigned long) count; @@ -91,19 +91,23 @@ static int __memcpy_real(void *dest, void *src, size_t count) return rc; } -static unsigned long _memcpy_real(unsigned long dest, unsigned long src, - unsigned long count) +static unsigned long __no_sanitize_address _memcpy_real(unsigned long dest, + unsigned long src, + unsigned long count) { int irqs_disabled, rc; unsigned long flags; if (!count) return 0; - flags = __arch_local_irq_stnsm(0xf8UL); + flags = arch_local_irq_save(); irqs_disabled = arch_irqs_disabled_flags(flags); if (!irqs_disabled) trace_hardirqs_off(); + __arch_local_irq_stnsm(0xf8); // disable DAT rc = __memcpy_real((void *) dest, (void *) src, (size_t) count); + if (flags & PSW_MASK_DAT) + __arch_local_irq_stosm(0x04); // enable DAT if (!irqs_disabled) trace_hardirqs_on(); __arch_local_irq_ssm(flags); @@ -115,9 +119,15 @@ static unsigned long _memcpy_real(unsigned long dest, unsigned long src, */ int memcpy_real(void *dest, void *src, size_t count) { - if (S390_lowcore.nodat_stack != 0) - return CALL_ON_STACK(_memcpy_real, S390_lowcore.nodat_stack, - 3, dest, src, count); + int rc; + + if (S390_lowcore.nodat_stack != 0) { + preempt_disable(); + rc = CALL_ON_STACK(_memcpy_real, S390_lowcore.nodat_stack, 3, + dest, src, count); + preempt_enable(); + return rc; + } /* * This is a really early memcpy_real call, the stacks are * not set up yet. Just call _memcpy_real on the early boot diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index ce88211b9c6c..c8c16b5eed6b 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include #include @@ -1369,7 +1370,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) } memset(&jit, 0, sizeof(jit)); - jit.addrs = kcalloc(fp->len + 1, sizeof(*jit.addrs), GFP_KERNEL); + jit.addrs = kvcalloc(fp->len + 1, sizeof(*jit.addrs), GFP_KERNEL); if (jit.addrs == NULL) { fp = orig_fp; goto out; @@ -1422,7 +1423,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) if (!fp->is_func || extra_pass) { bpf_prog_fill_jited_linfo(fp, jit.addrs + 1); free_addrs: - kfree(jit.addrs); + kvfree(jit.addrs); kfree(jit_data); fp->aux->jit_data = NULL; } diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile index bc0d7a0d0394..9de56065f28c 100644 --- a/arch/s390/purgatory/Makefile +++ b/arch/s390/purgatory/Makefile @@ -15,8 +15,10 @@ CFLAGS_sha256.o := -D__DISABLE_EXPORTS $(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S FORCE $(call if_changed_rule,as_o_S) -$(obj)/string.o: $(srctree)/arch/s390/lib/string.c FORCE - $(call if_changed_rule,cc_o_c) +KCOV_INSTRUMENT := n +GCOV_PROFILE := n +UBSAN_SANITIZE := n +KASAN_SANITIZE := n KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes KBUILD_CFLAGS += -Wno-pointer-sign -Wno-sign-compare diff --git a/arch/s390/purgatory/string.c b/arch/s390/purgatory/string.c new file mode 100644 index 000000000000..c98c22a72db7 --- /dev/null +++ b/arch/s390/purgatory/string.c @@ -0,0 +1,3 @@ +// SPDX-License-Identifier: GPL-2.0 +#define __HAVE_ARCH_MEMCMP /* arch function */ +#include "../lib/string.c" diff --git a/arch/sh/include/cpu-sh4/cpu/sh7734.h b/arch/sh/include/cpu-sh4/cpu/sh7734.h index 96f0246ad2f2..82b63208135a 100644 --- a/arch/sh/include/cpu-sh4/cpu/sh7734.h +++ b/arch/sh/include/cpu-sh4/cpu/sh7734.h @@ -134,7 +134,7 @@ enum { GPIO_FN_EX_WAIT1, GPIO_FN_SD1_DAT0_A, GPIO_FN_DREQ2, GPIO_FN_CAN1_TX_C, GPIO_FN_ET0_LINK_C, GPIO_FN_ET0_ETXD5_A, GPIO_FN_EX_WAIT0, GPIO_FN_TCLK1_B, - GPIO_FN_RD_WR, GPIO_FN_TCLK0, + GPIO_FN_RD_WR, GPIO_FN_TCLK0, GPIO_FN_CAN_CLK_B, GPIO_FN_ET0_ETXD4, GPIO_FN_EX_CS5, GPIO_FN_SD1_CMD_A, GPIO_FN_ATADIR, GPIO_FN_QSSL_B, GPIO_FN_ET0_ETXD3_A, GPIO_FN_EX_CS4, GPIO_FN_SD1_WP_A, GPIO_FN_ATAWR, GPIO_FN_QMI_QIO1_B, diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index dfdbaa50946e..d1b1ff2be17a 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -434,9 +434,7 @@ void arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = PFN_DOWN(start); unsigned long nr_pages = size >> PAGE_SHIFT; - struct zone *zone; - zone = page_zone(pfn_to_page(start_pfn)); - __remove_pages(zone, start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); } #endif /* CONFIG_MEMORY_HOTPLUG */ diff --git a/arch/sparc/include/asm/io_64.h b/arch/sparc/include/asm/io_64.h index 688911051b44..f4afa301954a 100644 --- a/arch/sparc/include/asm/io_64.h +++ b/arch/sparc/include/asm/io_64.h @@ -407,6 +407,7 @@ static inline void __iomem *ioremap(unsigned long offset, unsigned long size) } #define ioremap_nocache(X,Y) ioremap((X),(Y)) +#define ioremap_uc(X,Y) ioremap((X),(Y)) #define ioremap_wc(X,Y) ioremap((X),(Y)) #define ioremap_wt(X,Y) ioremap((X),(Y)) diff --git a/arch/um/Kconfig b/arch/um/Kconfig index fec6b4ca2b6e..c56d3526a3bd 100644 --- a/arch/um/Kconfig +++ b/arch/um/Kconfig @@ -14,6 +14,7 @@ config UML select HAVE_FUTEX_CMPXCHG if FUTEX select HAVE_DEBUG_KMEMLEAK select HAVE_DEBUG_BUGVERBOSE + select HAVE_COPY_THREAD_TLS select GENERIC_IRQ_SHOW select GENERIC_CPU_DEVICES select GENERIC_CLOCKEVENTS diff --git a/arch/um/drivers/virtio_uml.c b/arch/um/drivers/virtio_uml.c index fc8c52cff5aa..c5643a59a8c7 100644 --- a/arch/um/drivers/virtio_uml.c +++ b/arch/um/drivers/virtio_uml.c @@ -83,7 +83,7 @@ static int full_sendmsg_fds(int fd, const void *buf, unsigned int len, return 0; } -static int full_read(int fd, void *buf, int len) +static int full_read(int fd, void *buf, int len, bool abortable) { int rc; @@ -93,7 +93,7 @@ static int full_read(int fd, void *buf, int len) buf += rc; len -= rc; } - } while (len && (rc > 0 || rc == -EINTR)); + } while (len && (rc > 0 || rc == -EINTR || (!abortable && rc == -EAGAIN))); if (rc < 0) return rc; @@ -104,7 +104,7 @@ static int full_read(int fd, void *buf, int len) static int vhost_user_recv_header(int fd, struct vhost_user_msg *msg) { - return full_read(fd, msg, sizeof(msg->header)); + return full_read(fd, msg, sizeof(msg->header), true); } static int vhost_user_recv(int fd, struct vhost_user_msg *msg, @@ -118,7 +118,7 @@ static int vhost_user_recv(int fd, struct vhost_user_msg *msg, size = msg->header.size; if (size > max_payload_size) return -EPROTO; - return full_read(fd, &msg->payload, size); + return full_read(fd, &msg->payload, size, false); } static int vhost_user_recv_resp(struct virtio_uml_device *vu_dev, diff --git a/arch/um/include/asm/ptrace-generic.h b/arch/um/include/asm/ptrace-generic.h index 81c647ef9c6c..adf91ef553ae 100644 --- a/arch/um/include/asm/ptrace-generic.h +++ b/arch/um/include/asm/ptrace-generic.h @@ -36,7 +36,7 @@ extern long subarch_ptrace(struct task_struct *child, long request, extern unsigned long getreg(struct task_struct *child, int regno); extern int putreg(struct task_struct *child, int regno, unsigned long value); -extern int arch_copy_tls(struct task_struct *new); +extern int arch_set_tls(struct task_struct *new, unsigned long tls); extern void clear_flushed_tls(struct task_struct *task); extern int syscall_trace_enter(struct pt_regs *regs); extern void syscall_trace_leave(struct pt_regs *regs); diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index 263a8f069133..17045e7211bf 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -153,8 +153,8 @@ void fork_handler(void) userspace(¤t->thread.regs.regs, current_thread_info()->aux_fp_regs); } -int copy_thread(unsigned long clone_flags, unsigned long sp, - unsigned long arg, struct task_struct * p) +int copy_thread_tls(unsigned long clone_flags, unsigned long sp, + unsigned long arg, struct task_struct * p, unsigned long tls) { void (*handler)(void); int kthread = current->flags & PF_KTHREAD; @@ -188,7 +188,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, * Set a new TLS for the child thread? */ if (clone_flags & CLONE_SETTLS) - ret = arch_copy_tls(p); + ret = arch_set_tls(p, tls); } return ret; diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 8e29c991ba3e..4c16c7c509d4 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -116,6 +116,7 @@ config MPENTIUMM config MPENTIUM4 bool "Pentium-4/Celeron(P4-based)/Pentium-4 M/older Xeon" depends on X86_32 + select X86_P6_NOP ---help--- Select this for Intel Pentium 4 chips. This includes the Pentium 4, Pentium D, P4-based Celeron and Xeon, and @@ -148,9 +149,8 @@ config MPENTIUM4 -Paxville -Dempsey - config MK6 - bool "K6/K6-II/K6-III" + bool "AMD K6/K6-II/K6-III" depends on X86_32 ---help--- Select this for an AMD K6-family processor. Enables use of @@ -158,7 +158,7 @@ config MK6 flags to GCC. config MK7 - bool "Athlon/Duron/K7" + bool "AMD Athlon/Duron/K7" depends on X86_32 ---help--- Select this for an AMD Athlon K7-family processor. Enables use of @@ -166,12 +166,90 @@ config MK7 flags to GCC. config MK8 - bool "Opteron/Athlon64/Hammer/K8" + bool "AMD Opteron/Athlon64/Hammer/K8" ---help--- Select this for an AMD Opteron or Athlon64 Hammer-family processor. Enables use of some extended instructions, and passes appropriate optimization flags to GCC. +config MK8SSE3 + bool "AMD Opteron/Athlon64/Hammer/K8 with SSE3" + ---help--- + Select this for improved AMD Opteron or Athlon64 Hammer-family processors. + Enables use of some extended instructions, and passes appropriate + optimization flags to GCC. + +config MK10 + bool "AMD 61xx/7x50/PhenomX3/X4/II/K10" + ---help--- + Select this for an AMD 61xx Eight-Core Magny-Cours, Athlon X2 7x50, + Phenom X3/X4/II, Athlon II X2/X3/X4, or Turion II-family processor. + Enables use of some extended instructions, and passes appropriate + optimization flags to GCC. + +config MBARCELONA + bool "AMD Barcelona" + ---help--- + Select this for AMD Family 10h Barcelona processors. + + Enables -march=barcelona + +config MBOBCAT + bool "AMD Bobcat" + ---help--- + Select this for AMD Family 14h Bobcat processors. + + Enables -march=btver1 + +config MJAGUAR + bool "AMD Jaguar" + ---help--- + Select this for AMD Family 16h Jaguar processors. + + Enables -march=btver2 + +config MBULLDOZER + bool "AMD Bulldozer" + ---help--- + Select this for AMD Family 15h Bulldozer processors. + + Enables -march=bdver1 + +config MPILEDRIVER + bool "AMD Piledriver" + ---help--- + Select this for AMD Family 15h Piledriver processors. + + Enables -march=bdver2 + +config MSTEAMROLLER + bool "AMD Steamroller" + ---help--- + Select this for AMD Family 15h Steamroller processors. + + Enables -march=bdver3 + +config MEXCAVATOR + bool "AMD Excavator" + ---help--- + Select this for AMD Family 15h Excavator processors. + + Enables -march=bdver4 + +config MZEN + bool "AMD Zen" + ---help--- + Select this for AMD Family 17h Zen processors. + + Enables -march=znver1 + +config MZEN2 + bool "AMD Zen 2" + ---help--- + Select this for AMD Family 17h Zen 2 processors. + + Enables -march=znver2 + config MCRUSOE bool "Crusoe" depends on X86_32 @@ -253,6 +331,7 @@ config MVIAC7 config MPSC bool "Intel P4 / older Netburst based Xeon" + select X86_P6_NOP depends on X86_64 ---help--- Optimize for Intel Pentium 4, Pentium D and older Nocona/Dempsey @@ -262,8 +341,19 @@ config MPSC using the cpu family field in /proc/cpuinfo. Family 15 is an older Xeon, Family 6 a newer one. +config MATOM + bool "Intel Atom" + select X86_P6_NOP + ---help--- + + Select this for the Intel Atom platform. Intel Atom CPUs have an + in-order pipelining architecture and thus can benefit from + accordingly optimized code. Use a recent GCC with specific Atom + support in order to fully benefit from selecting this option. + config MCORE2 - bool "Core 2/newer Xeon" + bool "Intel Core 2" + select X86_P6_NOP ---help--- Select this for Intel Core 2 and newer Core 2 Xeons (Xeon 51xx and @@ -271,14 +361,133 @@ config MCORE2 family in /proc/cpuinfo. Newer ones have 6 and older ones 15 (not a typo) -config MATOM - bool "Intel Atom" + Enables -march=core2 + +config MNEHALEM + bool "Intel Nehalem" + select X86_P6_NOP ---help--- - Select this for the Intel Atom platform. Intel Atom CPUs have an - in-order pipelining architecture and thus can benefit from - accordingly optimized code. Use a recent GCC with specific Atom - support in order to fully benefit from selecting this option. + Select this for 1st Gen Core processors in the Nehalem family. + + Enables -march=nehalem + +config MWESTMERE + bool "Intel Westmere" + select X86_P6_NOP + ---help--- + + Select this for the Intel Westmere formerly Nehalem-C family. + + Enables -march=westmere + +config MSILVERMONT + bool "Intel Silvermont" + select X86_P6_NOP + ---help--- + + Select this for the Intel Silvermont platform. + + Enables -march=silvermont + +config MGOLDMONT + bool "Intel Goldmont" + select X86_P6_NOP + ---help--- + + Select this for the Intel Goldmont platform including Apollo Lake and Denverton. + + Enables -march=goldmont + +config MGOLDMONTPLUS + bool "Intel Goldmont Plus" + select X86_P6_NOP + ---help--- + + Select this for the Intel Goldmont Plus platform including Gemini Lake. + + Enables -march=goldmont-plus + +config MSANDYBRIDGE + bool "Intel Sandy Bridge" + select X86_P6_NOP + ---help--- + + Select this for 2nd Gen Core processors in the Sandy Bridge family. + + Enables -march=sandybridge + +config MIVYBRIDGE + bool "Intel Ivy Bridge" + select X86_P6_NOP + ---help--- + + Select this for 3rd Gen Core processors in the Ivy Bridge family. + + Enables -march=ivybridge + +config MHASWELL + bool "Intel Haswell" + select X86_P6_NOP + ---help--- + + Select this for 4th Gen Core processors in the Haswell family. + + Enables -march=haswell + +config MBROADWELL + bool "Intel Broadwell" + select X86_P6_NOP + ---help--- + + Select this for 5th Gen Core processors in the Broadwell family. + + Enables -march=broadwell + +config MSKYLAKE + bool "Intel Skylake" + select X86_P6_NOP + ---help--- + + Select this for 6th Gen Core processors in the Skylake family. + + Enables -march=skylake + +config MSKYLAKEX + bool "Intel Skylake X" + select X86_P6_NOP + ---help--- + + Select this for 6th Gen Core processors in the Skylake X family. + + Enables -march=skylake-avx512 + +config MCANNONLAKE + bool "Intel Cannon Lake" + select X86_P6_NOP + ---help--- + + Select this for 8th Gen Core processors + + Enables -march=cannonlake + +config MICELAKE + bool "Intel Ice Lake" + select X86_P6_NOP + ---help--- + + Select this for 10th Gen Core processors in the Ice Lake family. + + Enables -march=icelake-client + +config MCASCADELAKE + bool "Intel Cascade Lake" + select X86_P6_NOP + ---help--- + + Select this for Xeon processors in the Cascade Lake family. + + Enables -march=cascadelake config GENERIC_CPU bool "Generic-x86-64" @@ -287,6 +496,19 @@ config GENERIC_CPU Generic x86-64 CPU. Run equally well on all x86-64 CPUs. +config MNATIVE + bool "Native optimizations autodetected by GCC" + ---help--- + + GCC 4.2 and above support -march=native, which automatically detects + the optimum settings to use based on your processor. -march=native + also detects and applies additional settings beyond -march specific + to your CPU, (eg. -msse4). Unless you have a specific reason not to + (e.g. distcc cross-compiling), you should probably be using + -march=native rather than anything listed below. + + Enables -march=native + endchoice config X86_GENERIC @@ -311,7 +533,7 @@ config X86_INTERNODE_CACHE_SHIFT config X86_L1_CACHE_SHIFT int default "7" if MPENTIUM4 || MPSC - default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU + default "6" if MK7 || MK8 || MK8SSE3 || MK10 || MBARCELONA || MBOBCAT || MBULLDOZER || MPILEDRIVER || MSTEAMROLLER || MEXCAVATOR || MZEN || MZEN2 || MJAGUAR || MPENTIUMM || MCORE2 || MNEHALEM || MWESTMERE || MSILVERMONT || MGOLDMONT || MGOLDMONTPLUS || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MSKYLAKEX || MCANNONLAKE || MICELAKE || MCASCADELAKE || MNATIVE || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU default "4" if MELAN || M486 || MGEODEGX1 default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX @@ -329,35 +551,36 @@ config X86_ALIGNMENT_16 config X86_INTEL_USERCOPY def_bool y - depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M586MMX || X86_GENERIC || MK8 || MK7 || MEFFICEON || MCORE2 + depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M586MMX || X86_GENERIC || MK8 || MK8SSE3 || MK7 || MEFFICEON || MCORE2 || MK10 || MBARCELONA || MNEHALEM || MWESTMERE || MSILVERMONT || MGOLDMONT || MGOLDMONTPLUS || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MSKYLAKEX || MCANNONLAKE || MICELAKE || MCASCADELAKE || MNATIVE config X86_USE_PPRO_CHECKSUM def_bool y - depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MVIAC7 || MEFFICEON || MGEODE_LX || MCORE2 || MATOM + depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MK10 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MK8SSE3 || MVIAC3_2 || MVIAC7 || MEFFICEON || MGEODE_LX || MCORE2 || MNEHALEM || MWESTMERE || MSILVERMONT || MGOLDMONT || MGOLDMONTPLUS || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MSKYLAKEX || MCANNONLAKE || MICELAKE || MCASCADELAKE || MATOM || MNATIVE config X86_USE_3DNOW def_bool y depends on (MCYRIXIII || MK7 || MGEODE_LX) && !UML -# -# P6_NOPs are a relatively minor optimization that require a family >= -# 6 processor, except that it is broken on certain VIA chips. -# Furthermore, AMD chips prefer a totally different sequence of NOPs -# (which work on all CPUs). In addition, it looks like Virtual PC -# does not understand them. -# -# As a result, disallow these if we're not compiling for X86_64 (these -# NOPs do work on all x86-64 capable chips); the list of processors in -# the right-hand clause are the cores that benefit from this optimization. -# config X86_P6_NOP - def_bool y - depends on X86_64 - depends on (MCORE2 || MPENTIUM4 || MPSC) + default n + bool "Support for P6_NOPs on Intel chips" + depends on (MCORE2 || MPENTIUM4 || MPSC || MATOM || MNEHALEM || MWESTMERE || MSILVERMONT || MGOLDMONT || MGOLDMONTPLUS || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MSKYLAKEX || MCANNONLAKE || MICELAKE || MCASCADELAKE || MNATIVE) + ---help--- + P6_NOPs are a relatively minor optimization that require a family >= + 6 processor, except that it is broken on certain VIA chips. + Furthermore, AMD chips prefer a totally different sequence of NOPs + (which work on all CPUs). In addition, it looks like Virtual PC + does not understand them. + + As a result, disallow these if we're not compiling for X86_64 (these + NOPs do work on all x86-64 capable chips); the list of processors in + the right-hand clause are the cores that benefit from this optimization. + + Say Y if you have Intel CPU newer than Pentium Pro, N otherwise. config X86_TSC def_bool y - depends on (MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2 || MATOM) || X86_64 + depends on (MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MK8SSE3 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2 || MNEHALEM || MWESTMERE || MSILVERMONT || MGOLDMONT || MGOLDMONTPLUS || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MSKYLAKEX || MCANNONLAKE || MICELAKE || MCASCADELAKE || MNATIVE || MATOM) || X86_64 config X86_CMPXCHG64 def_bool y @@ -367,7 +590,7 @@ config X86_CMPXCHG64 # generates cmov. config X86_CMOV def_bool y - depends on (MK8 || MK7 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64 || MATOM || MGEODE_LX) + depends on (MK8 || MK8SSE3 || MK10 || MBARCELONA || MBOBCAT || MBULLDOZER || MPILEDRIVER || MSTEAMROLLER || MEXCAVATOR || MZEN || MZEN2 || MJAGUAR || MK7 || MCORE2 || MNEHALEM || MWESTMERE || MSILVERMONT || MGOLDMONT || MGOLDMONTPLUS || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MSKYLAKEX || MCANNONLAKE || MICELAKE || MCASCADELAKE || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64 || MNATIVE || MATOM || MGEODE_LX) config X86_MINIMUM_CPU_FAMILY int diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 94df0868804b..dcbed7e3a070 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -119,13 +119,53 @@ else KBUILD_CFLAGS += $(call cc-option,-mskip-rax-setup) # FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu) + cflags-$(CONFIG_MNATIVE) += $(call cc-option,-march=native) cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8) + cflags-$(CONFIG_MK8SSE3) += $(call cc-option,-march=k8-sse3,-mtune=k8) + cflags-$(CONFIG_MK10) += $(call cc-option,-march=amdfam10) + cflags-$(CONFIG_MBARCELONA) += $(call cc-option,-march=barcelona) + cflags-$(CONFIG_MBOBCAT) += $(call cc-option,-march=btver1) + cflags-$(CONFIG_MJAGUAR) += $(call cc-option,-march=btver2) + cflags-$(CONFIG_MBULLDOZER) += $(call cc-option,-march=bdver1) + cflags-$(CONFIG_MPILEDRIVER) += $(call cc-option,-march=bdver2) + cflags-$(CONFIG_MSTEAMROLLER) += $(call cc-option,-march=bdver3) + cflags-$(CONFIG_MEXCAVATOR) += $(call cc-option,-march=bdver4) + cflags-$(CONFIG_MZEN) += $(call cc-option,-march=znver1) + cflags-$(CONFIG_MZEN2) += $(call cc-option,-march=znver2) cflags-$(CONFIG_MPSC) += $(call cc-option,-march=nocona) cflags-$(CONFIG_MCORE2) += \ - $(call cc-option,-march=core2,$(call cc-option,-mtune=generic)) - cflags-$(CONFIG_MATOM) += $(call cc-option,-march=atom) \ - $(call cc-option,-mtune=atom,$(call cc-option,-mtune=generic)) + $(call cc-option,-march=core2,$(call cc-option,-mtune=core2)) + cflags-$(CONFIG_MNEHALEM) += \ + $(call cc-option,-march=nehalem,$(call cc-option,-mtune=nehalem)) + cflags-$(CONFIG_MWESTMERE) += \ + $(call cc-option,-march=westmere,$(call cc-option,-mtune=westmere)) + cflags-$(CONFIG_MSILVERMONT) += \ + $(call cc-option,-march=silvermont,$(call cc-option,-mtune=silvermont)) + cflags-$(CONFIG_MGOLDMONT) += \ + $(call cc-option,-march=goldmont,$(call cc-option,-mtune=goldmont)) + cflags-$(CONFIG_MGOLDMONTPLUS) += \ + $(call cc-option,-march=goldmont-plus,$(call cc-option,-mtune=goldmont-plus)) + cflags-$(CONFIG_MSANDYBRIDGE) += \ + $(call cc-option,-march=sandybridge,$(call cc-option,-mtune=sandybridge)) + cflags-$(CONFIG_MIVYBRIDGE) += \ + $(call cc-option,-march=ivybridge,$(call cc-option,-mtune=ivybridge)) + cflags-$(CONFIG_MHASWELL) += \ + $(call cc-option,-march=haswell,$(call cc-option,-mtune=haswell)) + cflags-$(CONFIG_MBROADWELL) += \ + $(call cc-option,-march=broadwell,$(call cc-option,-mtune=broadwell)) + cflags-$(CONFIG_MSKYLAKE) += \ + $(call cc-option,-march=skylake,$(call cc-option,-mtune=skylake)) + cflags-$(CONFIG_MSKYLAKEX) += \ + $(call cc-option,-march=skylake-avx512,$(call cc-option,-mtune=skylake-avx512)) + cflags-$(CONFIG_MCANNONLAKE) += \ + $(call cc-option,-march=cannonlake,$(call cc-option,-mtune=cannonlake)) + cflags-$(CONFIG_MICELAKE) += \ + $(call cc-option,-march=icelake-client,$(call cc-option,-mtune=icelake-client)) + cflags-$(CONFIG_MCASCADELAKE) += \ + $(call cc-option,-march=cascadelake,$(call cc-option,-mtune=cascadelake)) + cflags-$(CONFIG_MATOM) += $(call cc-option,-march=bonnell) \ + $(call cc-option,-mtune=bonnell,$(call cc-option,-mtune=generic)) cflags-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=generic) KBUILD_CFLAGS += $(cflags-y) diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu index 1f5faf8606b4..058d1b96eb67 100644 --- a/arch/x86/Makefile_32.cpu +++ b/arch/x86/Makefile_32.cpu @@ -23,7 +23,19 @@ cflags-$(CONFIG_MK6) += -march=k6 # Please note, that patches that add -march=athlon-xp and friends are pointless. # They make zero difference whatsosever to performance at this time. cflags-$(CONFIG_MK7) += -march=athlon +cflags-$(CONFIG_MNATIVE) += $(call cc-option,-march=native) cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8,-march=athlon) +cflags-$(CONFIG_MK8SSE3) += $(call cc-option,-march=k8-sse3,-march=athlon) +cflags-$(CONFIG_MK10) += $(call cc-option,-march=amdfam10,-march=athlon) +cflags-$(CONFIG_MBARCELONA) += $(call cc-option,-march=barcelona,-march=athlon) +cflags-$(CONFIG_MBOBCAT) += $(call cc-option,-march=btver1,-march=athlon) +cflags-$(CONFIG_MJAGUAR) += $(call cc-option,-march=btver2,-march=athlon) +cflags-$(CONFIG_MBULLDOZER) += $(call cc-option,-march=bdver1,-march=athlon) +cflags-$(CONFIG_MPILEDRIVER) += $(call cc-option,-march=bdver2,-march=athlon) +cflags-$(CONFIG_MSTEAMROLLER) += $(call cc-option,-march=bdver3,-march=athlon) +cflags-$(CONFIG_MEXCAVATOR) += $(call cc-option,-march=bdver4,-march=athlon) +cflags-$(CONFIG_MZEN) += $(call cc-option,-march=znver1,-march=athlon) +cflags-$(CONFIG_MZEN2) += $(call cc-option,-march=znver2,-march=athlon) cflags-$(CONFIG_MCRUSOE) += -march=i686 -falign-functions=0 -falign-jumps=0 -falign-loops=0 cflags-$(CONFIG_MEFFICEON) += -march=i686 $(call tune,pentium3) -falign-functions=0 -falign-jumps=0 -falign-loops=0 cflags-$(CONFIG_MWINCHIPC6) += $(call cc-option,-march=winchip-c6,-march=i586) @@ -32,8 +44,22 @@ cflags-$(CONFIG_MCYRIXIII) += $(call cc-option,-march=c3,-march=i486) -falign-fu cflags-$(CONFIG_MVIAC3_2) += $(call cc-option,-march=c3-2,-march=i686) cflags-$(CONFIG_MVIAC7) += -march=i686 cflags-$(CONFIG_MCORE2) += -march=i686 $(call tune,core2) -cflags-$(CONFIG_MATOM) += $(call cc-option,-march=atom,$(call cc-option,-march=core2,-march=i686)) \ - $(call cc-option,-mtune=atom,$(call cc-option,-mtune=generic)) +cflags-$(CONFIG_MNEHALEM) += -march=i686 $(call tune,nehalem) +cflags-$(CONFIG_MWESTMERE) += -march=i686 $(call tune,westmere) +cflags-$(CONFIG_MSILVERMONT) += -march=i686 $(call tune,silvermont) +cflags-$(CONFIG_MGOLDMONT) += -march=i686 $(call tune,goldmont) +cflags-$(CONFIG_MGOLDMONTPLUS) += -march=i686 $(call tune,goldmont-plus) +cflags-$(CONFIG_MSANDYBRIDGE) += -march=i686 $(call tune,sandybridge) +cflags-$(CONFIG_MIVYBRIDGE) += -march=i686 $(call tune,ivybridge) +cflags-$(CONFIG_MHASWELL) += -march=i686 $(call tune,haswell) +cflags-$(CONFIG_MBROADWELL) += -march=i686 $(call tune,broadwell) +cflags-$(CONFIG_MSKYLAKE) += -march=i686 $(call tune,skylake) +cflags-$(CONFIG_MSKYLAKEX) += -march=i686 $(call tune,skylake-avx512) +cflags-$(CONFIG_MCANNONLAKE) += -march=i686 $(call tune,cannonlake) +cflags-$(CONFIG_MICELAKE) += -march=i686 $(call tune,icelake-client) +cflags-$(CONFIG_MCASCADELAKE) += -march=i686 $(call tune,cascadelake) +cflags-$(CONFIG_MATOM) += $(call cc-option,-march=bonnell,$(call cc-option,-march=core2,-march=i686)) \ + $(call cc-option,-mtune=bonnell,$(call cc-option,-mtune=generic)) # AMD Elan support cflags-$(CONFIG_MELAN) += -march=i486 diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index f83ca5aa8b77..f07baf0388bc 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -172,7 +172,7 @@ ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI .if \no_user_check == 0 /* coming from usermode? */ - testl $SEGMENT_RPL_MASK, PT_CS(%esp) + testl $USER_SEGMENT_RPL_MASK, PT_CS(%esp) jz .Lend_\@ .endif /* On user-cr3? */ @@ -205,64 +205,76 @@ #define CS_FROM_ENTRY_STACK (1 << 31) #define CS_FROM_USER_CR3 (1 << 30) #define CS_FROM_KERNEL (1 << 29) +#define CS_FROM_ESPFIX (1 << 28) .macro FIXUP_FRAME /* * The high bits of the CS dword (__csh) are used for CS_FROM_*. * Clear them in case hardware didn't do this for us. */ - andl $0x0000ffff, 3*4(%esp) + andl $0x0000ffff, 4*4(%esp) #ifdef CONFIG_VM86 - testl $X86_EFLAGS_VM, 4*4(%esp) + testl $X86_EFLAGS_VM, 5*4(%esp) jnz .Lfrom_usermode_no_fixup_\@ #endif - testl $SEGMENT_RPL_MASK, 3*4(%esp) + testl $USER_SEGMENT_RPL_MASK, 4*4(%esp) jnz .Lfrom_usermode_no_fixup_\@ - orl $CS_FROM_KERNEL, 3*4(%esp) + orl $CS_FROM_KERNEL, 4*4(%esp) /* * When we're here from kernel mode; the (exception) stack looks like: * - * 5*4(%esp) - - * 4*4(%esp) - flags - * 3*4(%esp) - cs - * 2*4(%esp) - ip - * 1*4(%esp) - orig_eax - * 0*4(%esp) - gs / function + * 6*4(%esp) - + * 5*4(%esp) - flags + * 4*4(%esp) - cs + * 3*4(%esp) - ip + * 2*4(%esp) - orig_eax + * 1*4(%esp) - gs / function + * 0*4(%esp) - fs * * Lets build a 5 entry IRET frame after that, such that struct pt_regs * is complete and in particular regs->sp is correct. This gives us - * the original 5 enties as gap: + * the original 6 enties as gap: * - * 12*4(%esp) - - * 11*4(%esp) - gap / flags - * 10*4(%esp) - gap / cs - * 9*4(%esp) - gap / ip - * 8*4(%esp) - gap / orig_eax - * 7*4(%esp) - gap / gs / function - * 6*4(%esp) - ss - * 5*4(%esp) - sp - * 4*4(%esp) - flags - * 3*4(%esp) - cs - * 2*4(%esp) - ip - * 1*4(%esp) - orig_eax - * 0*4(%esp) - gs / function + * 14*4(%esp) - + * 13*4(%esp) - gap / flags + * 12*4(%esp) - gap / cs + * 11*4(%esp) - gap / ip + * 10*4(%esp) - gap / orig_eax + * 9*4(%esp) - gap / gs / function + * 8*4(%esp) - gap / fs + * 7*4(%esp) - ss + * 6*4(%esp) - sp + * 5*4(%esp) - flags + * 4*4(%esp) - cs + * 3*4(%esp) - ip + * 2*4(%esp) - orig_eax + * 1*4(%esp) - gs / function + * 0*4(%esp) - fs */ pushl %ss # ss pushl %esp # sp (points at ss) - addl $6*4, (%esp) # point sp back at the previous context - pushl 6*4(%esp) # flags - pushl 6*4(%esp) # cs - pushl 6*4(%esp) # ip - pushl 6*4(%esp) # orig_eax - pushl 6*4(%esp) # gs / function + addl $7*4, (%esp) # point sp back at the previous context + pushl 7*4(%esp) # flags + pushl 7*4(%esp) # cs + pushl 7*4(%esp) # ip + pushl 7*4(%esp) # orig_eax + pushl 7*4(%esp) # gs / function + pushl 7*4(%esp) # fs .Lfrom_usermode_no_fixup_\@: .endm .macro IRET_FRAME + /* + * We're called with %ds, %es, %fs, and %gs from the interrupted + * frame, so we shouldn't use them. Also, we may be in ESPFIX + * mode and therefore have a nonzero SS base and an offset ESP, + * so any attempt to access the stack needs to use SS. (except for + * accesses through %esp, which automatically use SS.) + */ testl $CS_FROM_KERNEL, 1*4(%esp) jz .Lfinished_frame_\@ @@ -276,31 +288,40 @@ movl 5*4(%esp), %eax # (modified) regs->sp movl 4*4(%esp), %ecx # flags - movl %ecx, -4(%eax) + movl %ecx, %ss:-1*4(%eax) movl 3*4(%esp), %ecx # cs andl $0x0000ffff, %ecx - movl %ecx, -8(%eax) + movl %ecx, %ss:-2*4(%eax) movl 2*4(%esp), %ecx # ip - movl %ecx, -12(%eax) + movl %ecx, %ss:-3*4(%eax) movl 1*4(%esp), %ecx # eax - movl %ecx, -16(%eax) + movl %ecx, %ss:-4*4(%eax) popl %ecx - lea -16(%eax), %esp + lea -4*4(%eax), %esp popl %eax .Lfinished_frame_\@: .endm -.macro SAVE_ALL pt_regs_ax=%eax switch_stacks=0 skip_gs=0 +.macro SAVE_ALL pt_regs_ax=%eax switch_stacks=0 skip_gs=0 unwind_espfix=0 cld .if \skip_gs == 0 PUSH_GS .endif - FIXUP_FRAME pushl %fs + + pushl %eax + movl $(__KERNEL_PERCPU), %eax + movl %eax, %fs +.if \unwind_espfix > 0 + UNWIND_ESPFIX_STACK +.endif + popl %eax + + FIXUP_FRAME pushl %es pushl %ds pushl \pt_regs_ax @@ -313,8 +334,6 @@ movl $(__USER_DS), %edx movl %edx, %ds movl %edx, %es - movl $(__KERNEL_PERCPU), %edx - movl %edx, %fs .if \skip_gs == 0 SET_KERNEL_GS %edx .endif @@ -324,8 +343,8 @@ .endif .endm -.macro SAVE_ALL_NMI cr3_reg:req - SAVE_ALL +.macro SAVE_ALL_NMI cr3_reg:req unwind_espfix=0 + SAVE_ALL unwind_espfix=\unwind_espfix BUG_IF_WRONG_CR3 @@ -357,6 +376,7 @@ 2: popl %es 3: popl %fs POP_GS \pop + IRET_FRAME .pushsection .fixup, "ax" 4: movl $0, (%esp) jmp 1b @@ -395,7 +415,8 @@ .macro CHECK_AND_APPLY_ESPFIX #ifdef CONFIG_X86_ESPFIX32 -#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8) +#define GDT_ESPFIX_OFFSET (GDT_ENTRY_ESPFIX_SS * 8) +#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + GDT_ESPFIX_OFFSET ALTERNATIVE "jmp .Lend_\@", "", X86_BUG_ESPFIX @@ -1075,7 +1096,6 @@ restore_all: /* Restore user state */ RESTORE_REGS pop=4 # skip orig_eax/error_code .Lirq_return: - IRET_FRAME /* * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization * when returning from IPI handler and when returning from @@ -1128,30 +1148,43 @@ ENDPROC(entry_INT80_32) * We can't call C functions using the ESPFIX stack. This code reads * the high word of the segment base from the GDT and swiches to the * normal stack and adjusts ESP with the matching offset. + * + * We might be on user CR3 here, so percpu data is not mapped and we can't + * access the GDT through the percpu segment. Instead, use SGDT to find + * the cpu_entry_area alias of the GDT. */ #ifdef CONFIG_X86_ESPFIX32 /* fixup the stack */ - mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */ - mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */ + pushl %ecx + subl $2*4, %esp + sgdt (%esp) + movl 2(%esp), %ecx /* GDT address */ + /* + * Careful: ECX is a linear pointer, so we need to force base + * zero. %cs is the only known-linear segment we have right now. + */ + mov %cs:GDT_ESPFIX_OFFSET + 4(%ecx), %al /* bits 16..23 */ + mov %cs:GDT_ESPFIX_OFFSET + 7(%ecx), %ah /* bits 24..31 */ shl $16, %eax + addl $2*4, %esp + popl %ecx addl %esp, %eax /* the adjusted stack pointer */ pushl $__KERNEL_DS pushl %eax lss (%esp), %esp /* switch to the normal stack segment */ #endif .endm + .macro UNWIND_ESPFIX_STACK + /* It's safe to clobber %eax, all other regs need to be preserved */ #ifdef CONFIG_X86_ESPFIX32 movl %ss, %eax /* see if on espfix stack */ cmpw $__ESPFIX_SS, %ax - jne 27f - movl $__KERNEL_DS, %eax - movl %eax, %ds - movl %eax, %es + jne .Lno_fixup_\@ /* switch to normal stack */ FIXUP_ESPFIX_STACK -27: +.Lno_fixup_\@: #endif .endm @@ -1341,11 +1374,6 @@ END(spurious_interrupt_bug) #ifdef CONFIG_XEN_PV ENTRY(xen_hypervisor_callback) - pushl $-1 /* orig_ax = -1 => not a system call */ - SAVE_ALL - ENCODE_FRAME_POINTER - TRACE_IRQS_OFF - /* * Check to see if we got the event in the critical * region in xen_iret_direct, after we've reenabled @@ -1353,16 +1381,17 @@ ENTRY(xen_hypervisor_callback) * iret instruction's behaviour where it delivers a * pending interrupt when enabling interrupts: */ - movl PT_EIP(%esp), %eax - cmpl $xen_iret_start_crit, %eax + cmpl $xen_iret_start_crit, (%esp) jb 1f - cmpl $xen_iret_end_crit, %eax + cmpl $xen_iret_end_crit, (%esp) jae 1f - - jmp xen_iret_crit_fixup - -ENTRY(xen_do_upcall) -1: mov %esp, %eax + call xen_iret_crit_fixup +1: + pushl $-1 /* orig_ax = -1 => not a system call */ + SAVE_ALL + ENCODE_FRAME_POINTER + TRACE_IRQS_OFF + mov %esp, %eax call xen_evtchn_do_upcall #ifndef CONFIG_PREEMPTION call xen_maybe_preempt_hcall @@ -1449,10 +1478,9 @@ END(page_fault) common_exception_read_cr2: /* the function address is in %gs's slot on the stack */ - SAVE_ALL switch_stacks=1 skip_gs=1 + SAVE_ALL switch_stacks=1 skip_gs=1 unwind_espfix=1 ENCODE_FRAME_POINTER - UNWIND_ESPFIX_STACK /* fixup %gs */ GS_TO_REG %ecx @@ -1474,9 +1502,8 @@ END(common_exception_read_cr2) common_exception: /* the function address is in %gs's slot on the stack */ - SAVE_ALL switch_stacks=1 skip_gs=1 + SAVE_ALL switch_stacks=1 skip_gs=1 unwind_espfix=1 ENCODE_FRAME_POINTER - UNWIND_ESPFIX_STACK /* fixup %gs */ GS_TO_REG %ecx @@ -1515,6 +1542,10 @@ ENTRY(nmi) ASM_CLAC #ifdef CONFIG_X86_ESPFIX32 + /* + * ESPFIX_SS is only ever set on the return to user path + * after we've switched to the entry stack. + */ pushl %eax movl %ss, %eax cmpw $__ESPFIX_SS, %ax @@ -1550,6 +1581,11 @@ ENTRY(nmi) movl %ebx, %esp .Lnmi_return: +#ifdef CONFIG_X86_ESPFIX32 + testl $CS_FROM_ESPFIX, PT_CS(%esp) + jnz .Lnmi_from_espfix +#endif + CHECK_AND_APPLY_ESPFIX RESTORE_ALL_NMI cr3_reg=%edi pop=4 jmp .Lirq_return @@ -1557,23 +1593,42 @@ ENTRY(nmi) #ifdef CONFIG_X86_ESPFIX32 .Lnmi_espfix_stack: /* - * create the pointer to lss back + * Create the pointer to LSS back */ pushl %ss pushl %esp addl $4, (%esp) - /* copy the iret frame of 12 bytes */ - .rept 3 - pushl 16(%esp) - .endr - pushl %eax - SAVE_ALL_NMI cr3_reg=%edi + + /* Copy the (short) IRET frame */ + pushl 4*4(%esp) # flags + pushl 4*4(%esp) # cs + pushl 4*4(%esp) # ip + + pushl %eax # orig_ax + + SAVE_ALL_NMI cr3_reg=%edi unwind_espfix=1 ENCODE_FRAME_POINTER - FIXUP_ESPFIX_STACK # %eax == %esp + + /* clear CS_FROM_KERNEL, set CS_FROM_ESPFIX */ + xorl $(CS_FROM_ESPFIX | CS_FROM_KERNEL), PT_CS(%esp) + xorl %edx, %edx # zero error code - call do_nmi + movl %esp, %eax # pt_regs pointer + jmp .Lnmi_from_sysenter_stack + +.Lnmi_from_espfix: RESTORE_ALL_NMI cr3_reg=%edi - lss 12+4(%esp), %esp # back to espfix stack + /* + * Because we cleared CS_FROM_KERNEL, IRET_FRAME 'forgot' to + * fix up the gap and long frame: + * + * 3 - original frame (exception) + * 2 - ESPFIX block (above) + * 6 - gap (FIXUP_FRAME) + * 5 - long frame (FIXUP_FRAME) + * 1 - orig_ax + */ + lss (1+5+6)*4(%esp), %esp # back to espfix stack jmp .Lirq_return #endif END(nmi) diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c index aa3336a7cb15..7d17b3addbbb 100644 --- a/arch/x86/entry/syscall_32.c +++ b/arch/x86/entry/syscall_32.c @@ -10,13 +10,11 @@ #ifdef CONFIG_IA32_EMULATION /* On X86_64, we use struct pt_regs * to pass parameters to syscalls */ #define __SYSCALL_I386(nr, sym, qual) extern asmlinkage long sym(const struct pt_regs *); - -/* this is a lie, but it does not hurt as sys_ni_syscall just returns -EINVAL */ -extern asmlinkage long sys_ni_syscall(const struct pt_regs *); - +#define __sys_ni_syscall __ia32_sys_ni_syscall #else /* CONFIG_IA32_EMULATION */ #define __SYSCALL_I386(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); +#define __sys_ni_syscall sys_ni_syscall #endif /* CONFIG_IA32_EMULATION */ #include @@ -29,6 +27,6 @@ __visible const sys_call_ptr_t ia32_sys_call_table[__NR_syscall_compat_max+1] = * Smells like a compiler bug -- it doesn't work * when the & below is removed. */ - [0 ... __NR_syscall_compat_max] = &sys_ni_syscall, + [0 ... __NR_syscall_compat_max] = &__sys_ni_syscall, #include }; diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c index b1bf31713374..adf619a856e8 100644 --- a/arch/x86/entry/syscall_64.c +++ b/arch/x86/entry/syscall_64.c @@ -4,11 +4,17 @@ #include #include #include +#include #include #include -/* this is a lie, but it does not hurt as sys_ni_syscall just returns -EINVAL */ -extern asmlinkage long sys_ni_syscall(const struct pt_regs *); +extern asmlinkage long sys_ni_syscall(void); + +SYSCALL_DEFINE0(ni_syscall) +{ + return sys_ni_syscall(); +} + #define __SYSCALL_64(nr, sym, qual) extern asmlinkage long sym(const struct pt_regs *); #define __SYSCALL_X32(nr, sym, qual) __SYSCALL_64(nr, sym, qual) #include @@ -23,7 +29,7 @@ asmlinkage const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = { * Smells like a compiler bug -- it doesn't work * when the & below is removed. */ - [0 ... __NR_syscall_max] = &sys_ni_syscall, + [0 ... __NR_syscall_max] = &__x64_sys_ni_syscall, #include }; @@ -40,7 +46,7 @@ asmlinkage const sys_call_ptr_t x32_sys_call_table[__NR_syscall_x32_max+1] = { * Smells like a compiler bug -- it doesn't work * when the & below is removed. */ - [0 ... __NR_syscall_x32_max] = &sys_ni_syscall, + [0 ... __NR_syscall_x32_max] = &__x64_sys_ni_syscall, #include }; diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 3fe02546aed3..15908eb9b17e 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -124,13 +124,13 @@ 110 i386 iopl sys_iopl __ia32_sys_iopl 111 i386 vhangup sys_vhangup __ia32_sys_vhangup 112 i386 idle -113 i386 vm86old sys_vm86old sys_ni_syscall +113 i386 vm86old sys_vm86old __ia32_sys_ni_syscall 114 i386 wait4 sys_wait4 __ia32_compat_sys_wait4 115 i386 swapoff sys_swapoff __ia32_sys_swapoff 116 i386 sysinfo sys_sysinfo __ia32_compat_sys_sysinfo 117 i386 ipc sys_ipc __ia32_compat_sys_ipc 118 i386 fsync sys_fsync __ia32_sys_fsync -119 i386 sigreturn sys_sigreturn sys32_sigreturn +119 i386 sigreturn sys_sigreturn __ia32_compat_sys_sigreturn 120 i386 clone sys_clone __ia32_compat_sys_x86_clone 121 i386 setdomainname sys_setdomainname __ia32_sys_setdomainname 122 i386 uname sys_newuname __ia32_sys_newuname @@ -177,14 +177,14 @@ 163 i386 mremap sys_mremap __ia32_sys_mremap 164 i386 setresuid sys_setresuid16 __ia32_sys_setresuid16 165 i386 getresuid sys_getresuid16 __ia32_sys_getresuid16 -166 i386 vm86 sys_vm86 sys_ni_syscall +166 i386 vm86 sys_vm86 __ia32_sys_ni_syscall 167 i386 query_module 168 i386 poll sys_poll __ia32_sys_poll 169 i386 nfsservctl 170 i386 setresgid sys_setresgid16 __ia32_sys_setresgid16 171 i386 getresgid sys_getresgid16 __ia32_sys_getresgid16 172 i386 prctl sys_prctl __ia32_sys_prctl -173 i386 rt_sigreturn sys_rt_sigreturn sys32_rt_sigreturn +173 i386 rt_sigreturn sys_rt_sigreturn __ia32_compat_sys_rt_sigreturn 174 i386 rt_sigaction sys_rt_sigaction __ia32_compat_sys_rt_sigaction 175 i386 rt_sigprocmask sys_rt_sigprocmask __ia32_compat_sys_rt_sigprocmask 176 i386 rt_sigpending sys_rt_sigpending __ia32_compat_sys_rt_sigpending diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 7b21455d7504..e622158f5659 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -375,7 +375,7 @@ int x86_add_exclusive(unsigned int what) * LBR and BTS are still mutually exclusive. */ if (x86_pmu.lbr_pt_coexist && what == x86_lbr_exclusive_pt) - return 0; + goto out; if (!atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what])) { mutex_lock(&pmc_reserve_mutex); @@ -387,6 +387,7 @@ int x86_add_exclusive(unsigned int what) mutex_unlock(&pmc_reserve_mutex); } +out: atomic_inc(&active_events); return 0; @@ -397,11 +398,15 @@ int x86_add_exclusive(unsigned int what) void x86_del_exclusive(unsigned int what) { + atomic_dec(&active_events); + + /* + * See the comment in x86_add_exclusive(). + */ if (x86_pmu.lbr_pt_coexist && what == x86_lbr_exclusive_pt) return; atomic_dec(&x86_pmu.lbr_exclusive[what]); - atomic_dec(&active_events); } int x86_setup_perfctr(struct perf_event *event) @@ -1641,9 +1646,12 @@ static struct attribute_group x86_pmu_format_group __ro_after_init = { ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, char *page) { - struct perf_pmu_events_attr *pmu_attr = \ + struct perf_pmu_events_attr *pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr); - u64 config = x86_pmu.event_map(pmu_attr->id); + u64 config = 0; + + if (pmu_attr->id < x86_pmu.max_events) + config = x86_pmu.event_map(pmu_attr->id); /* string trumps id */ if (pmu_attr->event_str) @@ -1712,6 +1720,9 @@ is_visible(struct kobject *kobj, struct attribute *attr, int idx) { struct perf_pmu_events_attr *pmu_attr; + if (idx >= x86_pmu.max_events) + return 0; + pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr.attr); /* str trumps id */ return pmu_attr->event_str || x86_pmu.event_map(idx) ? attr->mode : 0; diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c index 5ee3fed881d3..741540d849f3 100644 --- a/arch/x86/events/intel/bts.c +++ b/arch/x86/events/intel/bts.c @@ -63,9 +63,17 @@ struct bts_buffer { static struct pmu bts_pmu; +static int buf_nr_pages(struct page *page) +{ + if (!PagePrivate(page)) + return 1; + + return 1 << page_private(page); +} + static size_t buf_size(struct page *page) { - return 1 << (PAGE_SHIFT + page_private(page)); + return buf_nr_pages(page) * PAGE_SIZE; } static void * @@ -83,9 +91,7 @@ bts_buffer_setup_aux(struct perf_event *event, void **pages, /* count all the high order buffers */ for (pg = 0, nbuf = 0; pg < nr_pages;) { page = virt_to_page(pages[pg]); - if (WARN_ON_ONCE(!PagePrivate(page) && nr_pages > 1)) - return NULL; - pg += 1 << page_private(page); + pg += buf_nr_pages(page); nbuf++; } @@ -109,7 +115,7 @@ bts_buffer_setup_aux(struct perf_event *event, void **pages, unsigned int __nr_pages; page = virt_to_page(pages[pg]); - __nr_pages = PagePrivate(page) ? 1 << page_private(page) : 1; + __nr_pages = buf_nr_pages(page); buf->buf[nbuf].page = page; buf->buf[nbuf].offset = offset; buf->buf[nbuf].displacement = (pad ? BTS_RECORD_SIZE - pad : 0); diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index 1cee10091b9f..30416d7f19d4 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include @@ -118,7 +119,7 @@ static int ia32_restore_sigcontext(struct pt_regs *regs, return err; } -asmlinkage long sys32_sigreturn(void) +COMPAT_SYSCALL_DEFINE0(sigreturn) { struct pt_regs *regs = current_pt_regs(); struct sigframe_ia32 __user *frame = (struct sigframe_ia32 __user *)(regs->sp-8); @@ -144,7 +145,7 @@ asmlinkage long sys32_sigreturn(void) return 0; } -asmlinkage long sys32_rt_sigreturn(void) +COMPAT_SYSCALL_DEFINE0(rt_sigreturn) { struct pt_regs *regs = current_pt_regs(); struct rt_sigframe_ia32 __user *frame; diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h index 8348f7d69fd5..ea866c7bf31d 100644 --- a/arch/x86/include/asm/cpu_entry_area.h +++ b/arch/x86/include/asm/cpu_entry_area.h @@ -78,8 +78,12 @@ struct cpu_entry_area { /* * The GDT is just below entry_stack and thus serves (on x86_64) as - * a a read-only guard page. + * a read-only guard page. On 32-bit the GDT must be writeable, so + * it needs an extra guard page. */ +#ifdef CONFIG_X86_32 + char guard_entry_stack[PAGE_SIZE]; +#endif struct entry_stack_page entry_stack_page; /* @@ -94,7 +98,6 @@ struct cpu_entry_area { */ struct cea_exception_stacks estacks; #endif -#ifdef CONFIG_CPU_SUP_INTEL /* * Per CPU debug store for Intel performance monitoring. Wastes a * full page at the moment. @@ -105,11 +108,13 @@ struct cpu_entry_area { * Reserve enough fixmap PTEs. */ struct debug_store_buffers cpu_debug_buffers; -#endif }; -#define CPU_ENTRY_AREA_SIZE (sizeof(struct cpu_entry_area)) -#define CPU_ENTRY_AREA_TOT_SIZE (CPU_ENTRY_AREA_SIZE * NR_CPUS) +#define CPU_ENTRY_AREA_SIZE (sizeof(struct cpu_entry_area)) +#define CPU_ENTRY_AREA_ARRAY_SIZE (CPU_ENTRY_AREA_SIZE * NR_CPUS) + +/* Total size includes the readonly IDT mapping page as well: */ +#define CPU_ENTRY_AREA_TOTAL_SIZE (CPU_ENTRY_AREA_ARRAY_SIZE + PAGE_SIZE) DECLARE_PER_CPU(struct cpu_entry_area *, cpu_entry_area); DECLARE_PER_CPU(struct cea_exception_stacks *, cea_exception_stacks); @@ -117,13 +122,14 @@ DECLARE_PER_CPU(struct cea_exception_stacks *, cea_exception_stacks); extern void setup_cpu_entry_areas(void); extern void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags); +/* Single page reserved for the readonly IDT mapping: */ #define CPU_ENTRY_AREA_RO_IDT CPU_ENTRY_AREA_BASE #define CPU_ENTRY_AREA_PER_CPU (CPU_ENTRY_AREA_RO_IDT + PAGE_SIZE) #define CPU_ENTRY_AREA_RO_IDT_VADDR ((void *)CPU_ENTRY_AREA_RO_IDT) #define CPU_ENTRY_AREA_MAP_SIZE \ - (CPU_ENTRY_AREA_PER_CPU + CPU_ENTRY_AREA_TOT_SIZE - CPU_ENTRY_AREA_BASE) + (CPU_ENTRY_AREA_PER_CPU + CPU_ENTRY_AREA_ARRAY_SIZE - CPU_ENTRY_AREA_BASE) extern struct cpu_entry_area *get_cpu_entry_area(int cpu); diff --git a/arch/x86/include/asm/crash.h b/arch/x86/include/asm/crash.h index 0acf5ee45a21..ef5638f641f2 100644 --- a/arch/x86/include/asm/crash.h +++ b/arch/x86/include/asm/crash.h @@ -2,6 +2,8 @@ #ifndef _ASM_X86_CRASH_H #define _ASM_X86_CRASH_H +struct kimage; + int crash_load_segments(struct kimage *image); int crash_copy_backup_region(struct kimage *image); int crash_setup_memmap_entries(struct kimage *image, diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 0c47aa82e2e2..28183ee3cc42 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -156,7 +156,7 @@ extern pte_t *kmap_pte; extern pte_t *pkmap_page_table; void __native_set_fixmap(enum fixed_addresses idx, pte_t pte); -void native_set_fixmap(enum fixed_addresses idx, +void native_set_fixmap(unsigned /* enum fixed_addresses */ idx, phys_addr_t phys, pgprot_t flags); #ifndef CONFIG_PARAVIRT_XXL diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 4c95c365058a..44c48e34d799 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -509,7 +509,7 @@ static inline void __fpu_invalidate_fpregs_state(struct fpu *fpu) static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu) { - return fpu == this_cpu_read_stable(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu; + return fpu == this_cpu_read(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu; } /* diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h index 7948a17febb4..50b5e6ee4934 100644 --- a/arch/x86/include/asm/module.h +++ b/arch/x86/include/asm/module.h @@ -25,6 +25,36 @@ struct mod_arch_specific { #define MODULE_PROC_FAMILY "586MMX " #elif defined CONFIG_MCORE2 #define MODULE_PROC_FAMILY "CORE2 " +#elif defined CONFIG_MNATIVE +#define MODULE_PROC_FAMILY "NATIVE " +#elif defined CONFIG_MNEHALEM +#define MODULE_PROC_FAMILY "NEHALEM " +#elif defined CONFIG_MWESTMERE +#define MODULE_PROC_FAMILY "WESTMERE " +#elif defined CONFIG_MSILVERMONT +#define MODULE_PROC_FAMILY "SILVERMONT " +#elif defined CONFIG_MGOLDMONT +#define MODULE_PROC_FAMILY "GOLDMONT " +#elif defined CONFIG_MGOLDMONTPLUS +#define MODULE_PROC_FAMILY "GOLDMONTPLUS " +#elif defined CONFIG_MSANDYBRIDGE +#define MODULE_PROC_FAMILY "SANDYBRIDGE " +#elif defined CONFIG_MIVYBRIDGE +#define MODULE_PROC_FAMILY "IVYBRIDGE " +#elif defined CONFIG_MHASWELL +#define MODULE_PROC_FAMILY "HASWELL " +#elif defined CONFIG_MBROADWELL +#define MODULE_PROC_FAMILY "BROADWELL " +#elif defined CONFIG_MSKYLAKE +#define MODULE_PROC_FAMILY "SKYLAKE " +#elif defined CONFIG_MSKYLAKEX +#define MODULE_PROC_FAMILY "SKYLAKEX " +#elif defined CONFIG_MCANNONLAKE +#define MODULE_PROC_FAMILY "CANNONLAKE " +#elif defined CONFIG_MICELAKE +#define MODULE_PROC_FAMILY "ICELAKE " +#elif defined CONFIG_MCASCADELAKE +#define MODULE_PROC_FAMILY "CASCADELAKE " #elif defined CONFIG_MATOM #define MODULE_PROC_FAMILY "ATOM " #elif defined CONFIG_M686 @@ -43,6 +73,28 @@ struct mod_arch_specific { #define MODULE_PROC_FAMILY "K7 " #elif defined CONFIG_MK8 #define MODULE_PROC_FAMILY "K8 " +#elif defined CONFIG_MK8SSE3 +#define MODULE_PROC_FAMILY "K8SSE3 " +#elif defined CONFIG_MK10 +#define MODULE_PROC_FAMILY "K10 " +#elif defined CONFIG_MBARCELONA +#define MODULE_PROC_FAMILY "BARCELONA " +#elif defined CONFIG_MBOBCAT +#define MODULE_PROC_FAMILY "BOBCAT " +#elif defined CONFIG_MBULLDOZER +#define MODULE_PROC_FAMILY "BULLDOZER " +#elif defined CONFIG_MPILEDRIVER +#define MODULE_PROC_FAMILY "PILEDRIVER " +#elif defined CONFIG_MSTEAMROLLER +#define MODULE_PROC_FAMILY "STEAMROLLER " +#elif defined CONFIG_MJAGUAR +#define MODULE_PROC_FAMILY "JAGUAR " +#elif defined CONFIG_MEXCAVATOR +#define MODULE_PROC_FAMILY "EXCAVATOR " +#elif defined CONFIG_MZEN +#define MODULE_PROC_FAMILY "ZEN " +#elif defined CONFIG_MZEN2 +#define MODULE_PROC_FAMILY "ZEN2 " #elif defined CONFIG_MELAN #define MODULE_PROC_FAMILY "ELAN " #elif defined CONFIG_MCRUSOE diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h index b0bc0fff5f1f..1636eb8e5a5b 100644 --- a/arch/x86/include/asm/pgtable_32_types.h +++ b/arch/x86/include/asm/pgtable_32_types.h @@ -44,11 +44,11 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */ * Define this here and validate with BUILD_BUG_ON() in pgtable_32.c * to avoid include recursion hell */ -#define CPU_ENTRY_AREA_PAGES (NR_CPUS * 40) +#define CPU_ENTRY_AREA_PAGES (NR_CPUS * 39) -#define CPU_ENTRY_AREA_BASE \ - ((FIXADDR_TOT_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1)) \ - & PMD_MASK) +/* The +1 is for the readonly IDT page: */ +#define CPU_ENTRY_AREA_BASE \ + ((FIXADDR_TOT_START - PAGE_SIZE*(CPU_ENTRY_AREA_PAGES+1)) & PMD_MASK) #define LDT_BASE_ADDR \ ((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK) diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index ac3892920419..6669164abadc 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -31,6 +31,18 @@ */ #define SEGMENT_RPL_MASK 0x3 +/* + * When running on Xen PV, the actual privilege level of the kernel is 1, + * not 0. Testing the Requested Privilege Level in a segment selector to + * determine whether the context is user mode or kernel mode with + * SEGMENT_RPL_MASK is wrong because the PV kernel's privilege level + * matches the 0x3 mask. + * + * Testing with USER_SEGMENT_RPL_MASK is valid for both native and Xen PV + * kernels because privilege level 2 is never used. + */ +#define USER_SEGMENT_RPL_MASK 0x2 + /* User mode is privilege level 3: */ #define USER_RPL 0x3 diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h index e046a405743d..e2389ce9bf58 100644 --- a/arch/x86/include/asm/syscall_wrapper.h +++ b/arch/x86/include/asm/syscall_wrapper.h @@ -6,6 +6,8 @@ #ifndef _ASM_X86_SYSCALL_WRAPPER_H #define _ASM_X86_SYSCALL_WRAPPER_H +struct pt_regs; + /* Mapping of registers to parameters for syscalls on x86-64 and x32 */ #define SC_X86_64_REGS_TO_ARGS(x, ...) \ __MAP(x,__SC_ARGS \ @@ -28,13 +30,21 @@ * kernel/sys_ni.c and SYS_NI in kernel/time/posix-stubs.c to cover this * case as well. */ +#define __IA32_COMPAT_SYS_STUB0(x, name) \ + asmlinkage long __ia32_compat_sys_##name(const struct pt_regs *regs);\ + ALLOW_ERROR_INJECTION(__ia32_compat_sys_##name, ERRNO); \ + asmlinkage long __ia32_compat_sys_##name(const struct pt_regs *regs)\ + { \ + return __se_compat_sys_##name(); \ + } + #define __IA32_COMPAT_SYS_STUBx(x, name, ...) \ asmlinkage long __ia32_compat_sys##name(const struct pt_regs *regs);\ ALLOW_ERROR_INJECTION(__ia32_compat_sys##name, ERRNO); \ asmlinkage long __ia32_compat_sys##name(const struct pt_regs *regs)\ { \ return __se_compat_sys##name(SC_IA32_REGS_TO_ARGS(x,__VA_ARGS__));\ - } \ + } #define __IA32_SYS_STUBx(x, name, ...) \ asmlinkage long __ia32_sys##name(const struct pt_regs *regs); \ @@ -48,16 +58,23 @@ * To keep the naming coherent, re-define SYSCALL_DEFINE0 to create an alias * named __ia32_sys_*() */ -#define SYSCALL_DEFINE0(sname) \ - SYSCALL_METADATA(_##sname, 0); \ - asmlinkage long __x64_sys_##sname(void); \ - ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO); \ - SYSCALL_ALIAS(__ia32_sys_##sname, __x64_sys_##sname); \ - asmlinkage long __x64_sys_##sname(void) -#define COND_SYSCALL(name) \ - cond_syscall(__x64_sys_##name); \ - cond_syscall(__ia32_sys_##name) +#define SYSCALL_DEFINE0(sname) \ + SYSCALL_METADATA(_##sname, 0); \ + asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused);\ + ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO); \ + SYSCALL_ALIAS(__ia32_sys_##sname, __x64_sys_##sname); \ + asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused) + +#define COND_SYSCALL(name) \ + asmlinkage __weak long __x64_sys_##name(const struct pt_regs *__unused) \ + { \ + return sys_ni_syscall(); \ + } \ + asmlinkage __weak long __ia32_sys_##name(const struct pt_regs *__unused)\ + { \ + return sys_ni_syscall(); \ + } #define SYS_NI(name) \ SYSCALL_ALIAS(__x64_sys_##name, sys_ni_posix_timers); \ @@ -75,15 +92,24 @@ * of the x86-64-style parameter ordering of x32 syscalls. The syscalls common * with x86_64 obviously do not need such care. */ +#define __X32_COMPAT_SYS_STUB0(x, name, ...) \ + asmlinkage long __x32_compat_sys_##name(const struct pt_regs *regs);\ + ALLOW_ERROR_INJECTION(__x32_compat_sys_##name, ERRNO); \ + asmlinkage long __x32_compat_sys_##name(const struct pt_regs *regs)\ + { \ + return __se_compat_sys_##name();\ + } + #define __X32_COMPAT_SYS_STUBx(x, name, ...) \ asmlinkage long __x32_compat_sys##name(const struct pt_regs *regs);\ ALLOW_ERROR_INJECTION(__x32_compat_sys##name, ERRNO); \ asmlinkage long __x32_compat_sys##name(const struct pt_regs *regs)\ { \ return __se_compat_sys##name(SC_X86_64_REGS_TO_ARGS(x,__VA_ARGS__));\ - } \ + } #else /* CONFIG_X86_X32 */ +#define __X32_COMPAT_SYS_STUB0(x, name) #define __X32_COMPAT_SYS_STUBx(x, name, ...) #endif /* CONFIG_X86_X32 */ @@ -94,6 +120,17 @@ * mapping of registers to parameters, we need to generate stubs for each * of them. */ +#define COMPAT_SYSCALL_DEFINE0(name) \ + static long __se_compat_sys_##name(void); \ + static inline long __do_compat_sys_##name(void); \ + __IA32_COMPAT_SYS_STUB0(x, name) \ + __X32_COMPAT_SYS_STUB0(x, name) \ + static long __se_compat_sys_##name(void) \ + { \ + return __do_compat_sys_##name(); \ + } \ + static inline long __do_compat_sys_##name(void) + #define COMPAT_SYSCALL_DEFINEx(x, name, ...) \ static long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ @@ -181,15 +218,19 @@ * macros to work correctly. */ #ifndef SYSCALL_DEFINE0 -#define SYSCALL_DEFINE0(sname) \ - SYSCALL_METADATA(_##sname, 0); \ - asmlinkage long __x64_sys_##sname(void); \ - ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO); \ - asmlinkage long __x64_sys_##sname(void) +#define SYSCALL_DEFINE0(sname) \ + SYSCALL_METADATA(_##sname, 0); \ + asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused);\ + ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO); \ + asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused) #endif #ifndef COND_SYSCALL -#define COND_SYSCALL(name) cond_syscall(__x64_sys_##name) +#define COND_SYSCALL(name) \ + asmlinkage __weak long __x64_sys_##name(const struct pt_regs *__unused) \ + { \ + return sys_ni_syscall(); \ + } #endif #ifndef SYS_NI @@ -201,7 +242,6 @@ * For VSYSCALLS, we need to declare these three syscalls with the new * pt_regs-based calling convention for in-kernel use. */ -struct pt_regs; asmlinkage long __x64_sys_getcpu(const struct pt_regs *regs); asmlinkage long __x64_sys_gettimeofday(const struct pt_regs *regs); asmlinkage long __x64_sys_time(const struct pt_regs *regs); diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index d6af97fd170a..f0262cb5657a 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1727,9 +1727,10 @@ static bool io_apic_level_ack_pending(struct mp_chip_data *data) static inline bool ioapic_irqd_mask(struct irq_data *data) { - /* If we are moving the irq we need to mask it */ + /* If we are moving the IRQ we need to mask it */ if (unlikely(irqd_is_setaffinity_pending(data))) { - mask_ioapic_irq(data); + if (!irqd_irq_masked(data)) + mask_ioapic_irq(data); return true; } return false; @@ -1766,7 +1767,9 @@ static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked) */ if (!io_apic_level_ack_pending(data->chip_data)) irq_move_masked_irq(data); - unmask_ioapic_irq(data); + /* If the IRQ is masked in the core, leave it: */ + if (!irqd_irq_masked(data)) + unmask_ioapic_irq(data); } } #else diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 4c7b0fa15a19..8bf64899f56a 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -39,6 +39,7 @@ static void __init spectre_v2_select_mitigation(void); static void __init ssb_select_mitigation(void); static void __init l1tf_select_mitigation(void); static void __init mds_select_mitigation(void); +static void __init mds_print_mitigation(void); static void __init taa_select_mitigation(void); /* The base value of the SPEC_CTRL MSR that always has to be preserved. */ @@ -108,6 +109,12 @@ void __init check_bugs(void) mds_select_mitigation(); taa_select_mitigation(); + /* + * As MDS and TAA mitigations are inter-related, print MDS + * mitigation until after TAA mitigation selection is done. + */ + mds_print_mitigation(); + arch_smt_update(); #ifdef CONFIG_X86_32 @@ -245,6 +252,12 @@ static void __init mds_select_mitigation(void) (mds_nosmt || cpu_mitigations_auto_nosmt())) cpu_smt_disable(false); } +} + +static void __init mds_print_mitigation(void) +{ + if (!boot_cpu_has_bug(X86_BUG_MDS) || cpu_mitigations_off()) + return; pr_info("%s\n", mds_strings[mds_mitigation]); } @@ -304,8 +317,12 @@ static void __init taa_select_mitigation(void) return; } - /* TAA mitigation is turned off on the cmdline (tsx_async_abort=off) */ - if (taa_mitigation == TAA_MITIGATION_OFF) + /* + * TAA mitigation via VERW is turned off if both + * tsx_async_abort=off and mds=off are specified. + */ + if (taa_mitigation == TAA_MITIGATION_OFF && + mds_mitigation == MDS_MITIGATION_OFF) goto out; if (boot_cpu_has(X86_FEATURE_MD_CLEAR)) @@ -339,6 +356,15 @@ static void __init taa_select_mitigation(void) if (taa_nosmt || cpu_mitigations_auto_nosmt()) cpu_smt_disable(false); + /* + * Update MDS mitigation, if necessary, as the mds_user_clear is + * now enabled for TAA mitigation. + */ + if (mds_mitigation == MDS_MITIGATION_OFF && + boot_cpu_has_bug(X86_BUG_MDS)) { + mds_mitigation = MDS_MITIGATION_FULL; + mds_select_mitigation(); + } out: pr_info("%s\n", taa_strings[taa_mitigation]); } diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 6ea7fdc82f3c..259f3f4e2e5f 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -266,10 +266,10 @@ static void smca_configure(unsigned int bank, unsigned int cpu) smca_set_misc_banks_map(bank, cpu); /* Return early if this bank was already initialized. */ - if (smca_banks[bank].hwid) + if (smca_banks[bank].hwid && smca_banks[bank].hwid->hwid_mcatype != 0) return; - if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_IPID(bank), &low, &high)) { + if (rdmsr_safe(MSR_AMD64_SMCA_MCx_IPID(bank), &low, &high)) { pr_warn("Failed to read MCA_IPID for bank %d\n", bank); return; } diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 743370ee4983..aecb15ba66cd 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -814,8 +814,8 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, if (quirk_no_way_out) quirk_no_way_out(i, m, regs); + m->bank = i; if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) { - m->bank = i; mce_read_aux(m, i); *msg = tmp; return 1; diff --git a/arch/x86/kernel/cpu/mce/therm_throt.c b/arch/x86/kernel/cpu/mce/therm_throt.c index 6e2becf547c5..bc441d68d060 100644 --- a/arch/x86/kernel/cpu/mce/therm_throt.c +++ b/arch/x86/kernel/cpu/mce/therm_throt.c @@ -188,7 +188,7 @@ static void therm_throt_process(bool new_event, int event, int level) /* if we just entered the thermal event */ if (new_event) { if (event == THERMAL_THROTTLING_EVENT) - pr_crit("CPU%d: %s temperature above threshold, cpu clock throttled (total events = %lu)\n", + pr_warn("CPU%d: %s temperature above threshold, cpu clock throttled (total events = %lu)\n", this_cpu, level == CORE_LEVEL ? "Core" : "Package", state->count); diff --git a/arch/x86/kernel/doublefault.c b/arch/x86/kernel/doublefault.c index 0b8cedb20d6d..d5c9b13bafdf 100644 --- a/arch/x86/kernel/doublefault.c +++ b/arch/x86/kernel/doublefault.c @@ -65,6 +65,9 @@ struct x86_hw_tss doublefault_tss __cacheline_aligned = { .ss = __KERNEL_DS, .ds = __USER_DS, .fs = __KERNEL_PERCPU, +#ifndef CONFIG_X86_32_LAZY_GS + .gs = __KERNEL_STACK_CANARY, +#endif .__cr3 = __pa_nodebug(swapper_pg_dir), }; diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 4cba91ec8049..2f9ec14be3b1 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -710,8 +710,12 @@ 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_INTEL, 0x3e20, + PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, { PCI_VENDOR_ID_INTEL, 0x3ec4, PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, + { PCI_VENDOR_ID_INTEL, 0x8a12, + 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}, {} diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 30f9cb2c0b55..2e6a0676c1f4 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -571,6 +571,16 @@ ENTRY(initial_page_table) # error "Kernel PMDs should be 1, 2 or 3" # endif .align PAGE_SIZE /* needs to be page-sized too */ + +#ifdef CONFIG_PAGE_TABLE_ISOLATION + /* + * PTI needs another page so sync_initial_pagetable() works correctly + * and does not scribble over the data which is placed behind the + * actual initial_page_table. See clone_pgd_range(). + */ + .fill 1024, 4, 0 +#endif + #endif .data diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index f68c0c753c38..b1d5a8c94a57 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -402,7 +402,8 @@ static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry, int index) entry->edx |= F(SPEC_CTRL); if (boot_cpu_has(X86_FEATURE_STIBP)) entry->edx |= F(INTEL_STIBP); - if (boot_cpu_has(X86_FEATURE_SSBD)) + if (boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || + boot_cpu_has(X86_FEATURE_AMD_SSBD)) entry->edx |= F(SPEC_CTRL_SSBD); /* * We emulate ARCH_CAPABILITIES in software even @@ -504,7 +505,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, r = -E2BIG; - if (*nent >= maxnent) + if (WARN_ON(*nent >= maxnent)) goto out; do_host_cpuid(entry, function, 0); @@ -759,7 +760,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, entry->ebx |= F(AMD_IBRS); if (boot_cpu_has(X86_FEATURE_STIBP)) entry->ebx |= F(AMD_STIBP); - if (boot_cpu_has(X86_FEATURE_SSBD)) + if (boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || + boot_cpu_has(X86_FEATURE_AMD_SSBD)) entry->ebx |= F(AMD_SSBD); if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) entry->ebx |= F(AMD_SSB_NO); @@ -810,6 +812,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, static int do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 func, int *nent, int maxnent, unsigned int type) { + if (*nent >= maxnent) + return -E2BIG; + if (type == KVM_GET_EMULATED_CPUID) return __do_cpuid_func_emulated(entry, func, nent, maxnent); diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 0e7c9301fe86..d0523741fb03 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2418,6 +2418,16 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, entry_failure_code)) return -EINVAL; + /* + * Immediately write vmcs02.GUEST_CR3. It will be propagated to vmcs12 + * on nested VM-Exit, which can occur without actually running L2 and + * thus without hitting vmx_set_cr3(), e.g. if L1 is entering L2 with + * vmcs12.GUEST_ACTIVITYSTATE=HLT, in which case KVM will intercept the + * transition to HLT instead of running L2. + */ + if (enable_ept) + vmcs_writel(GUEST_CR3, vmcs12->guest_cr3); + /* Late preparation of GUEST_PDPTRs now that EFER and CRs are set. */ if (load_guest_pdptrs_vmcs12 && nested_cpu_has_ept(vmcs12) && is_pae_paging(vcpu)) { diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 04a8212704c1..f09a213fd5cb 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -2995,6 +2995,7 @@ u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa) void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) { struct kvm *kvm = vcpu->kvm; + bool update_guest_cr3 = true; unsigned long guest_cr3; u64 eptp; @@ -3011,15 +3012,18 @@ void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock); } - if (enable_unrestricted_guest || is_paging(vcpu) || - is_guest_mode(vcpu)) + /* Loading vmcs02.GUEST_CR3 is handled by nested VM-Enter. */ + if (is_guest_mode(vcpu)) + update_guest_cr3 = false; + else if (enable_unrestricted_guest || is_paging(vcpu)) guest_cr3 = kvm_read_cr3(vcpu); else guest_cr3 = to_kvm_vmx(kvm)->ept_identity_map_addr; ept_load_pdptrs(vcpu); } - vmcs_writel(GUEST_CR3, guest_cr3); + if (update_guest_cr3) + vmcs_writel(GUEST_CR3, guest_cr3); } int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 5d530521f11d..8d82ec0482fc 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -300,13 +300,14 @@ int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask) struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu); int err; - if (((value ^ smsr->values[slot].curr) & mask) == 0) + value = (value & mask) | (smsr->values[slot].host & ~mask); + if (value == smsr->values[slot].curr) return 0; - smsr->values[slot].curr = value; err = wrmsrl_safe(shared_msrs_global.msrs[slot], value); if (err) return 1; + smsr->values[slot].curr = value; if (!smsr->registered) { smsr->urn.on_user_return = kvm_on_user_return; user_return_notifier_register(&smsr->urn); @@ -1327,10 +1328,15 @@ static u64 kvm_get_arch_capabilities(void) * If TSX is disabled on the system, guests are also mitigated against * TAA and clear CPU buffer mitigation is not required for guests. */ - if (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM) && - (data & ARCH_CAP_TSX_CTRL_MSR)) + if (!boot_cpu_has(X86_FEATURE_RTM)) + data &= ~ARCH_CAP_TAA_NO; + else if (!boot_cpu_has_bug(X86_BUG_TAA)) + data |= ARCH_CAP_TAA_NO; + else if (data & ARCH_CAP_TSX_CTRL_MSR) data &= ~ARCH_CAP_MDS_NO; + /* KVM does not emulate MSR_IA32_TSX_CTRL. */ + data &= ~ARCH_CAP_TSX_CTRL_MSR; return data; } @@ -4421,6 +4427,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, case KVM_SET_NESTED_STATE: { struct kvm_nested_state __user *user_kvm_nested_state = argp; struct kvm_nested_state kvm_state; + int idx; r = -EINVAL; if (!kvm_x86_ops->set_nested_state) @@ -4444,7 +4451,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, && !(kvm_state.flags & KVM_STATE_NESTED_GUEST_MODE)) break; + idx = srcu_read_lock(&vcpu->kvm->srcu); r = kvm_x86_ops->set_nested_state(vcpu, user_kvm_nested_state, &kvm_state); + srcu_read_unlock(&vcpu->kvm->srcu, idx); break; } case KVM_GET_SUPPORTED_HV_CPUID: { diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt index e0b85930dd77..0a0e9112f284 100644 --- a/arch/x86/lib/x86-opcode-map.txt +++ b/arch/x86/lib/x86-opcode-map.txt @@ -333,7 +333,7 @@ AVXcode: 1 06: CLTS 07: SYSRET (o64) 08: INVD -09: WBINVD +09: WBINVD | WBNOINVD (F3) 0a: 0b: UD2 (1B) 0c: @@ -364,7 +364,7 @@ AVXcode: 1 # a ModR/M byte. 1a: BNDCL Gv,Ev (F3) | BNDCU Gv,Ev (F2) | BNDMOV Gv,Ev (66) | BNDLDX Gv,Ev 1b: BNDCN Gv,Ev (F2) | BNDMOV Ev,Gv (66) | BNDMK Gv,Ev (F3) | BNDSTX Ev,Gv -1c: +1c: Grp20 (1A),(1C) 1d: 1e: 1f: NOP Ev @@ -792,6 +792,8 @@ f3: Grp17 (1A) f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v) f6: ADCX Gy,Ey (66) | ADOX Gy,Ey (F3) | MULX By,Gy,rDX,Ey (F2),(v) f7: BEXTR Gy,Ey,By (v) | SHLX Gy,Ey,By (66),(v) | SARX Gy,Ey,By (F3),(v) | SHRX Gy,Ey,By (F2),(v) +f8: MOVDIR64B Gv,Mdqq (66) | ENQCMD Gv,Mdqq (F2) | ENQCMDS Gv,Mdqq (F3) +f9: MOVDIRI My,Gy EndTable Table: 3-byte opcode 2 (0x0f 0x3a) @@ -943,9 +945,9 @@ GrpTable: Grp6 EndTable GrpTable: Grp7 -0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) -1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) -2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) +0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B) +1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) | ENCLS (111),(11B) +2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) | ENCLU (111),(11B) 3: LIDT Ms 4: SMSW Mw/Rv 5: rdpkru (110),(11B) | wrpkru (111),(11B) @@ -1020,7 +1022,7 @@ GrpTable: Grp15 3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B) 4: XSAVE | ptwrite Ey (F3),(11B) 5: XRSTOR | lfence (11B) -6: XSAVEOPT | clwb (66) | mfence (11B) +6: XSAVEOPT | clwb (66) | mfence (11B) | TPAUSE Rd (66),(11B) | UMONITOR Rv (F3),(11B) | UMWAIT Rd (F2),(11B) 7: clflush | clflushopt (66) | sfence (11B) EndTable @@ -1051,6 +1053,10 @@ GrpTable: Grp19 6: vscatterpf1qps/d Wx (66),(ev) EndTable +GrpTable: Grp20 +0: cldemote Mb +EndTable + # AMD's Prefetch Group GrpTable: GrpP 0: PREFETCH diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h index f98a0c956764..9b41391867dc 100644 --- a/arch/x86/math-emu/fpu_system.h +++ b/arch/x86/math-emu/fpu_system.h @@ -107,6 +107,8 @@ static inline bool seg_writable(struct desc_struct *d) #define FPU_access_ok(y,z) if ( !access_ok(y,z) ) \ math_abort(FPU_info,SIGSEGV) #define FPU_abort math_abort(FPU_info, SIGSEGV) +#define FPU_copy_from_user(to, from, n) \ + do { if (copy_from_user(to, from, n)) FPU_abort; } while (0) #undef FPU_IGNORE_CODE_SEGV #ifdef FPU_IGNORE_CODE_SEGV @@ -122,7 +124,7 @@ static inline bool seg_writable(struct desc_struct *d) #define FPU_code_access_ok(z) FPU_access_ok((void __user *)FPU_EIP,z) #endif -#define FPU_get_user(x,y) get_user((x),(y)) -#define FPU_put_user(x,y) put_user((x),(y)) +#define FPU_get_user(x,y) do { if (get_user((x),(y))) FPU_abort; } while (0) +#define FPU_put_user(x,y) do { if (put_user((x),(y))) FPU_abort; } while (0) #endif diff --git a/arch/x86/math-emu/reg_ld_str.c b/arch/x86/math-emu/reg_ld_str.c index f3779743d15e..fe6246ff9887 100644 --- a/arch/x86/math-emu/reg_ld_str.c +++ b/arch/x86/math-emu/reg_ld_str.c @@ -85,7 +85,7 @@ int FPU_load_extended(long double __user *s, int stnr) RE_ENTRANT_CHECK_OFF; FPU_access_ok(s, 10); - __copy_from_user(sti_ptr, s, 10); + FPU_copy_from_user(sti_ptr, s, 10); RE_ENTRANT_CHECK_ON; return FPU_tagof(sti_ptr); @@ -1126,9 +1126,9 @@ void frstor(fpu_addr_modes addr_modes, u_char __user *data_address) /* Copy all registers in stack order. */ RE_ENTRANT_CHECK_OFF; FPU_access_ok(s, 80); - __copy_from_user(register_base + offset, s, other); + FPU_copy_from_user(register_base + offset, s, other); if (offset) - __copy_from_user(register_base, s + other, offset); + FPU_copy_from_user(register_base, s + other, offset); RE_ENTRANT_CHECK_ON; for (i = 0; i < 8; i++) { diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c index 752ad11d6868..d9643647a9ce 100644 --- a/arch/x86/mm/cpu_entry_area.c +++ b/arch/x86/mm/cpu_entry_area.c @@ -178,7 +178,9 @@ static __init void setup_cpu_entry_area_ptes(void) #ifdef CONFIG_X86_32 unsigned long start, end; - BUILD_BUG_ON(CPU_ENTRY_AREA_PAGES * PAGE_SIZE < CPU_ENTRY_AREA_MAP_SIZE); + /* The +1 is for the readonly IDT: */ + BUILD_BUG_ON((CPU_ENTRY_AREA_PAGES+1)*PAGE_SIZE != CPU_ENTRY_AREA_MAP_SIZE); + BUILD_BUG_ON(CPU_ENTRY_AREA_TOTAL_SIZE != CPU_ENTRY_AREA_MAP_SIZE); BUG_ON(CPU_ENTRY_AREA_BASE & ~PMD_MASK); start = CPU_ENTRY_AREA_BASE; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 9ceacd1156db..304d31d8cbbc 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -197,7 +197,7 @@ void vmalloc_sync_all(void) return; for (address = VMALLOC_START & PMD_MASK; - address >= TASK_SIZE_MAX && address < FIXADDR_TOP; + address >= TASK_SIZE_MAX && address < VMALLOC_END; address += PMD_SIZE) { struct page *page; diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 930edeb41ec3..0a74407ef92e 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -865,10 +865,8 @@ void arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct zone *zone; - zone = page_zone(pfn_to_page(start_pfn)); - __remove_pages(zone, start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); } #endif diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index a6b5c653727b..b8541d77452c 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1212,10 +1212,8 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct page *page = pfn_to_page(start_pfn) + vmem_altmap_offset(altmap); - struct zone *zone = page_zone(page); - __remove_pages(zone, start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); kernel_physical_mapping_remove(start, start + size); } #endif /* CONFIG_MEMORY_HOTPLUG */ diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 3e4b9035bb9a..7bd2c3a52297 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -643,8 +643,8 @@ void __native_set_fixmap(enum fixed_addresses idx, pte_t pte) fixmaps_set++; } -void native_set_fixmap(enum fixed_addresses idx, phys_addr_t phys, - pgprot_t flags) +void native_set_fixmap(unsigned /* enum fixed_addresses */ idx, + phys_addr_t phys, pgprot_t flags) { /* Sanitize 'prot' against any unsupported bits: */ pgprot_val(flags) &= __default_kernel_pte_mask; diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 527e69b12002..e723559c386a 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -588,6 +588,17 @@ static void pci_fixup_amd_ehci_pme(struct pci_dev *dev) } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x7808, pci_fixup_amd_ehci_pme); +/* + * Device [1022:7914] + * When in D0, PME# doesn't get asserted when plugging USB 2.0 device. + */ +static void pci_fixup_amd_fch_xhci_pme(struct pci_dev *dev) +{ + dev_info(&dev->dev, "PME# does not work under D0, disabling it\n"); + dev->pme_support &= ~(PCI_PM_CAP_PME_D0 >> PCI_PM_CAP_PME_SHIFT); +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x7914, pci_fixup_amd_fch_xhci_pme); + /* * Apple MacBook Pro: Avoid [mem 0x7fa00000-0x7fbfffff] * diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 3b9fd679cea9..aefe845dff59 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -260,10 +260,6 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size) return; } - /* No need to reserve regions that will never be freed. */ - if (md.attribute & EFI_MEMORY_RUNTIME) - return; - size += addr % EFI_PAGE_SIZE; size = round_up(size, EFI_PAGE_SIZE); addr = round_down(addr, EFI_PAGE_SIZE); @@ -293,6 +289,8 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size) early_memunmap(new, new_size); efi_memmap_install(new_phys, num_entries); + e820__range_update(addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED); + e820__update_table(e820_table); } /* diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk index b02a36b2c14f..a42015b305f4 100644 --- a/arch/x86/tools/gen-insn-attr-x86.awk +++ b/arch/x86/tools/gen-insn-attr-x86.awk @@ -69,7 +69,7 @@ BEGIN { lprefix1_expr = "\\((66|!F3)\\)" lprefix2_expr = "\\(F3\\)" - lprefix3_expr = "\\((F2|!F3|66\\&F2)\\)" + lprefix3_expr = "\\((F2|!F3|66&F2)\\)" lprefix_expr = "\\((66|F2|F3)\\)" max_lprefix = 4 @@ -257,7 +257,7 @@ function convert_operands(count,opnd, i,j,imm,mod) return add_flags(imm, mod) } -/^[0-9a-f]+\:/ { +/^[0-9a-f]+:/ { if (NR == 1) next # get index diff --git a/arch/x86/um/tls_32.c b/arch/x86/um/tls_32.c index 5bd949da7a4a..ac8eee093f9c 100644 --- a/arch/x86/um/tls_32.c +++ b/arch/x86/um/tls_32.c @@ -215,14 +215,12 @@ static int set_tls_entry(struct task_struct* task, struct user_desc *info, return 0; } -int arch_copy_tls(struct task_struct *new) +int arch_set_tls(struct task_struct *new, unsigned long tls) { struct user_desc info; int idx, ret = -EFAULT; - if (copy_from_user(&info, - (void __user *) UPT_SI(&new->thread.regs.regs), - sizeof(info))) + if (copy_from_user(&info, (void __user *) tls, sizeof(info))) goto out; ret = -EINVAL; diff --git a/arch/x86/um/tls_64.c b/arch/x86/um/tls_64.c index 3a621e0d3925..ebd3855d9b13 100644 --- a/arch/x86/um/tls_64.c +++ b/arch/x86/um/tls_64.c @@ -6,14 +6,13 @@ void clear_flushed_tls(struct task_struct *task) { } -int arch_copy_tls(struct task_struct *t) +int arch_set_tls(struct task_struct *t, unsigned long tls) { /* * If CLONE_SETTLS is set, we need to save the thread id - * (which is argument 5, child_tid, of clone) so it can be set - * during context switches. + * so it can be set during context switches. */ - t->thread.arch.fs = t->thread.regs.regs.gp[R8 / sizeof(long)]; + t->thread.arch.fs = tls; return 0; } diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S index c15db060a242..cd177772fe4d 100644 --- a/arch/x86/xen/xen-asm_32.S +++ b/arch/x86/xen/xen-asm_32.S @@ -126,10 +126,9 @@ hyper_iret: .globl xen_iret_start_crit, xen_iret_end_crit /* - * This is called by xen_hypervisor_callback in entry.S when it sees + * This is called by xen_hypervisor_callback in entry_32.S when it sees * that the EIP at the time of interrupt was between - * xen_iret_start_crit and xen_iret_end_crit. We're passed the EIP in - * %eax so we can do a more refined determination of what to do. + * xen_iret_start_crit and xen_iret_end_crit. * * The stack format at this point is: * ---------------- @@ -138,70 +137,46 @@ hyper_iret: * eflags } outer exception info * cs } * eip } - * ---------------- <- edi (copy dest) - * eax : outer eax if it hasn't been restored * ---------------- - * eflags } nested exception info - * cs } (no ss/esp because we're nested - * eip } from the same ring) - * orig_eax }<- esi (copy src) - * - - - - - - - - - * fs } - * es } - * ds } SAVE_ALL state - * eax } - * : : - * ebx }<- esp + * eax : outer eax if it hasn't been restored * ---------------- + * eflags } + * cs } nested exception info + * eip } + * return address : (into xen_hypervisor_callback) * - * In order to deliver the nested exception properly, we need to shift - * everything from the return addr up to the error code so it sits - * just under the outer exception info. This means that when we - * handle the exception, we do it in the context of the outer - * exception rather than starting a new one. + * In order to deliver the nested exception properly, we need to discard the + * nested exception frame such that when we handle the exception, we do it + * in the context of the outer exception rather than starting a new one. * - * The only caveat is that if the outer eax hasn't been restored yet - * (ie, it's still on stack), we need to insert its value into the - * SAVE_ALL state before going on, since it's usermode state which we - * eventually need to restore. + * The only caveat is that if the outer eax hasn't been restored yet (i.e. + * it's still on stack), we need to restore its value here. */ ENTRY(xen_iret_crit_fixup) /* * Paranoia: Make sure we're really coming from kernel space. * One could imagine a case where userspace jumps into the * critical range address, but just before the CPU delivers a - * GP, it decides to deliver an interrupt instead. Unlikely? - * Definitely. Easy to avoid? Yes. The Intel documents - * explicitly say that the reported EIP for a bad jump is the - * jump instruction itself, not the destination, but some - * virtual environments get this wrong. + * PF, it decides to deliver an interrupt instead. Unlikely? + * Definitely. Easy to avoid? Yes. */ - movl PT_CS(%esp), %ecx - andl $SEGMENT_RPL_MASK, %ecx - cmpl $USER_RPL, %ecx - je 2f - - lea PT_ORIG_EAX(%esp), %esi - lea PT_EFLAGS(%esp), %edi + testb $2, 2*4(%esp) /* nested CS */ + jnz 2f /* * If eip is before iret_restore_end then stack * hasn't been restored yet. */ - cmp $iret_restore_end, %eax + cmpl $iret_restore_end, 1*4(%esp) jae 1f - movl 0+4(%edi), %eax /* copy EAX (just above top of frame) */ - movl %eax, PT_EAX(%esp) + movl 4*4(%esp), %eax /* load outer EAX */ + ret $4*4 /* discard nested EIP, CS, and EFLAGS as + * well as the just restored EAX */ - lea ESP_OFFSET(%edi), %edi /* move dest up over saved regs */ - - /* set up the copy */ -1: std - mov $PT_EIP / 4, %ecx /* saved regs up to orig_eax */ - rep movsl - cld - - lea 4(%edi), %esp /* point esp to new frame */ -2: jmp xen_do_upcall +1: + ret $3*4 /* discard nested EIP, CS, and EFLAGS */ +2: + ret +END(xen_iret_crit_fixup) diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index a8e7beb6b7b5..8352037322df 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -22,6 +22,7 @@ config XTENSA select HAVE_ARCH_JUMP_LABEL select HAVE_ARCH_KASAN if MMU select HAVE_ARCH_TRACEHOOK + select HAVE_COPY_THREAD_TLS select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS select HAVE_EXIT_THREAD diff --git a/arch/xtensa/include/asm/syscall.h b/arch/xtensa/include/asm/syscall.h index 359ab40e935a..c90fb944f9d8 100644 --- a/arch/xtensa/include/asm/syscall.h +++ b/arch/xtensa/include/asm/syscall.h @@ -51,7 +51,7 @@ static inline void syscall_set_return_value(struct task_struct *task, struct pt_regs *regs, int error, long val) { - regs->areg[0] = (long) error ? error : val; + regs->areg[2] = (long) error ? error : val; } #define SYSCALL_MAX_ARGS 6 diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c index db278a9e80c7..7cbf8bd6d922 100644 --- a/arch/xtensa/kernel/process.c +++ b/arch/xtensa/kernel/process.c @@ -202,8 +202,9 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) * involved. Much simpler to just not copy those live frames across. */ -int copy_thread(unsigned long clone_flags, unsigned long usp_thread_fn, - unsigned long thread_fn_arg, struct task_struct *p) +int copy_thread_tls(unsigned long clone_flags, unsigned long usp_thread_fn, + unsigned long thread_fn_arg, struct task_struct *p, + unsigned long tls) { struct pt_regs *childregs = task_pt_regs(p); @@ -264,9 +265,8 @@ int copy_thread(unsigned long clone_flags, unsigned long usp_thread_fn, ®s->areg[XCHAL_NUM_AREGS - len/4], len); } - /* The thread pointer is passed in the '4th argument' (= a5) */ if (clone_flags & CLONE_SETTLS) - childregs->threadptr = childregs->areg[5]; + childregs->threadptr = tls; } else { p->thread.ra = MAKE_RA_FOR_CALL( (unsigned long)ret_from_kernel_thread, 1); diff --git a/arch/xtensa/mm/kasan_init.c b/arch/xtensa/mm/kasan_init.c index af7152560bc3..b771459778fe 100644 --- a/arch/xtensa/mm/kasan_init.c +++ b/arch/xtensa/mm/kasan_init.c @@ -56,7 +56,9 @@ static void __init populate(void *start, void *end) for (k = 0; k < PTRS_PER_PTE; ++k, ++j) { phys_addr_t phys = - memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE); + memblock_phys_alloc_range(PAGE_SIZE, PAGE_SIZE, + 0, + MEMBLOCK_ALLOC_ANYWHERE); if (!phys) panic("Failed to allocate page table page\n"); diff --git a/arch/xtensa/mm/tlb.c b/arch/xtensa/mm/tlb.c index 59153d0aa890..b43f03620843 100644 --- a/arch/xtensa/mm/tlb.c +++ b/arch/xtensa/mm/tlb.c @@ -216,6 +216,8 @@ static int check_tlb_entry(unsigned w, unsigned e, bool dtlb) unsigned tlbidx = w | (e << PAGE_SHIFT); unsigned r0 = dtlb ? read_dtlb_virtual(tlbidx) : read_itlb_virtual(tlbidx); + unsigned r1 = dtlb ? + read_dtlb_translation(tlbidx) : read_itlb_translation(tlbidx); unsigned vpn = (r0 & PAGE_MASK) | (e << PAGE_SHIFT); unsigned pte = get_pte_for_vaddr(vpn); unsigned mm_asid = (get_rasid_register() >> 8) & ASID_MASK; @@ -231,8 +233,6 @@ static int check_tlb_entry(unsigned w, unsigned e, bool dtlb) } if (tlb_asid == mm_asid) { - unsigned r1 = dtlb ? read_dtlb_translation(tlbidx) : - read_itlb_translation(tlbidx); if ((pte ^ r1) & PAGE_MASK) { pr_err("%cTLB: way: %u, entry: %u, mapping: %08x->%08x, PTE: %08x\n", dtlb ? 'D' : 'I', w, e, r0, r1, pte); diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index 86a607cf19a1..d3b59b731992 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -1194,7 +1194,9 @@ struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node) } struct blkcg_policy blkcg_policy_bfq = { +#ifndef CONFIG_BLK_CGROUP_IOCOST .dfl_cftypes = bfq_blkg_files, +#endif .legacy_cftypes = bfq_blkcg_legacy_files, .cpd_alloc_fn = bfq_cpd_alloc, @@ -1209,139 +1211,143 @@ struct blkcg_policy blkcg_policy_bfq = { .pd_reset_stats_fn = bfq_pd_reset_stats, }; -struct cftype bfq_blkcg_legacy_files[] = { - { - .name = "bfq.weight", - .flags = CFTYPE_NOT_ON_ROOT, - .seq_show = bfq_io_show_weight_legacy, - .write_u64 = bfq_io_set_weight_legacy, - }, - { - .name = "bfq.weight_device", - .flags = CFTYPE_NOT_ON_ROOT, - .seq_show = bfq_io_show_weight, - .write = bfq_io_set_weight, - }, - - /* statistics, covers only the tasks in the bfqg */ - { - .name = "bfq.io_service_bytes", - .private = (unsigned long)&blkcg_policy_bfq, - .seq_show = blkg_print_stat_bytes, - }, - { - .name = "bfq.io_serviced", - .private = (unsigned long)&blkcg_policy_bfq, - .seq_show = blkg_print_stat_ios, - }, -#ifdef CONFIG_BFQ_CGROUP_DEBUG - { - .name = "bfq.time", - .private = offsetof(struct bfq_group, stats.time), - .seq_show = bfqg_print_stat, - }, - { - .name = "bfq.sectors", - .seq_show = bfqg_print_stat_sectors, - }, - { - .name = "bfq.io_service_time", - .private = offsetof(struct bfq_group, stats.service_time), - .seq_show = bfqg_print_rwstat, - }, - { - .name = "bfq.io_wait_time", - .private = offsetof(struct bfq_group, stats.wait_time), - .seq_show = bfqg_print_rwstat, - }, - { - .name = "bfq.io_merged", - .private = offsetof(struct bfq_group, stats.merged), - .seq_show = bfqg_print_rwstat, - }, - { - .name = "bfq.io_queued", - .private = offsetof(struct bfq_group, stats.queued), - .seq_show = bfqg_print_rwstat, - }, -#endif /* CONFIG_BFQ_CGROUP_DEBUG */ +#define bfq_make_blkcg_legacy_files(prefix) \ + { \ + .name = #prefix "weight", \ + .flags = CFTYPE_NOT_ON_ROOT, \ + .seq_show = bfq_io_show_weight, \ + .write_u64 = bfq_io_set_weight_legacy, \ + }, \ + \ + /* statistics, covers only the tasks in the bfqg */ \ + { \ + .name = #prefix "io_service_bytes", \ + .private = (unsigned long)&blkcg_policy_bfq, \ + .seq_show = blkg_print_stat_bytes, \ + }, \ + { \ + .name = #prefix "io_serviced", \ + .private = (unsigned long)&blkcg_policy_bfq, \ + .seq_show = blkg_print_stat_ios, \ + }, \ + \ + /* the same statistics which cover the bfqg and its descendants */ \ + { \ + .name = #prefix "io_service_bytes_recursive", \ + .private = (unsigned long)&blkcg_policy_bfq, \ + .seq_show = blkg_print_stat_bytes_recursive, \ + }, \ + { \ + .name = #prefix "io_serviced_recursive", \ + .private = (unsigned long)&blkcg_policy_bfq, \ + .seq_show = blkg_print_stat_ios_recursive, \ + } - /* the same statistics which cover the bfqg and its descendants */ - { - .name = "bfq.io_service_bytes_recursive", - .private = (unsigned long)&blkcg_policy_bfq, - .seq_show = blkg_print_stat_bytes_recursive, - }, - { - .name = "bfq.io_serviced_recursive", - .private = (unsigned long)&blkcg_policy_bfq, - .seq_show = blkg_print_stat_ios_recursive, - }, +#define bfq_make_blkcg_legacy_debug_files(prefix) \ + { \ + .name = #prefix "time", \ + .private = offsetof(struct bfq_group, stats.time), \ + .seq_show = bfqg_print_stat, \ + }, \ + { \ + .name = #prefix "sectors", \ + .seq_show = bfqg_print_stat_sectors, \ + }, \ + { \ + .name = #prefix "io_service_time", \ + .private = offsetof(struct bfq_group, stats.service_time), \ + .seq_show = bfqg_print_rwstat, \ + }, \ + { \ + .name = #prefix "io_wait_time", \ + .private = offsetof(struct bfq_group, stats.wait_time), \ + .seq_show = bfqg_print_rwstat, \ + }, \ + { \ + .name = #prefix "io_merged", \ + .private = offsetof(struct bfq_group, stats.merged), \ + .seq_show = bfqg_print_rwstat, \ + }, \ + { \ + .name = #prefix "io_queued", \ + .private = offsetof(struct bfq_group, stats.queued), \ + .seq_show = bfqg_print_rwstat, \ + }, \ + { \ + .name = #prefix "time_recursive", \ + .private = offsetof(struct bfq_group, stats.time), \ + .seq_show = bfqg_print_stat_recursive, \ + }, \ + { \ + .name = #prefix "sectors_recursive", \ + .seq_show = bfqg_print_stat_sectors_recursive, \ + }, \ + { \ + .name = #prefix "io_service_time_recursive", \ + .private = offsetof(struct bfq_group, stats.service_time), \ + .seq_show = bfqg_print_rwstat_recursive, \ + }, \ + { \ + .name = #prefix "io_wait_time_recursive", \ + .private = offsetof(struct bfq_group, stats.wait_time), \ + .seq_show = bfqg_print_rwstat_recursive, \ + }, \ + { \ + .name = #prefix "io_merged_recursive", \ + .private = offsetof(struct bfq_group, stats.merged), \ + .seq_show = bfqg_print_rwstat_recursive, \ + }, \ + { \ + .name = #prefix "io_queued_recursive", \ + .private = offsetof(struct bfq_group, stats.queued), \ + .seq_show = bfqg_print_rwstat_recursive, \ + }, \ + { \ + .name = #prefix "avg_queue_size", \ + .seq_show = bfqg_print_avg_queue_size, \ + }, \ + { \ + .name = #prefix "group_wait_time", \ + .private = offsetof(struct bfq_group, stats.group_wait_time), \ + .seq_show = bfqg_print_stat, \ + }, \ + { \ + .name = #prefix "idle_time", \ + .private = offsetof(struct bfq_group, stats.idle_time), \ + .seq_show = bfqg_print_stat, \ + }, \ + { \ + .name = #prefix "empty_time", \ + .private = offsetof(struct bfq_group, stats.empty_time), \ + .seq_show = bfqg_print_stat, \ + }, \ + { \ + .name = #prefix "dequeue", \ + .private = offsetof(struct bfq_group, stats.dequeue), \ + .seq_show = bfqg_print_stat, \ + } + +struct cftype bfq_blkcg_legacy_files[] = { + bfq_make_blkcg_legacy_files(bfq.), + bfq_make_blkcg_legacy_files(), #ifdef CONFIG_BFQ_CGROUP_DEBUG - { - .name = "bfq.time_recursive", - .private = offsetof(struct bfq_group, stats.time), - .seq_show = bfqg_print_stat_recursive, - }, - { - .name = "bfq.sectors_recursive", - .seq_show = bfqg_print_stat_sectors_recursive, - }, - { - .name = "bfq.io_service_time_recursive", - .private = offsetof(struct bfq_group, stats.service_time), - .seq_show = bfqg_print_rwstat_recursive, - }, - { - .name = "bfq.io_wait_time_recursive", - .private = offsetof(struct bfq_group, stats.wait_time), - .seq_show = bfqg_print_rwstat_recursive, - }, - { - .name = "bfq.io_merged_recursive", - .private = offsetof(struct bfq_group, stats.merged), - .seq_show = bfqg_print_rwstat_recursive, - }, - { - .name = "bfq.io_queued_recursive", - .private = offsetof(struct bfq_group, stats.queued), - .seq_show = bfqg_print_rwstat_recursive, - }, - { - .name = "bfq.avg_queue_size", - .seq_show = bfqg_print_avg_queue_size, - }, - { - .name = "bfq.group_wait_time", - .private = offsetof(struct bfq_group, stats.group_wait_time), - .seq_show = bfqg_print_stat, - }, - { - .name = "bfq.idle_time", - .private = offsetof(struct bfq_group, stats.idle_time), - .seq_show = bfqg_print_stat, - }, - { - .name = "bfq.empty_time", - .private = offsetof(struct bfq_group, stats.empty_time), - .seq_show = bfqg_print_stat, - }, - { - .name = "bfq.dequeue", - .private = offsetof(struct bfq_group, stats.dequeue), - .seq_show = bfqg_print_stat, - }, -#endif /* CONFIG_BFQ_CGROUP_DEBUG */ + bfq_make_blkcg_legacy_debug_files(bfq.), + bfq_make_blkcg_legacy_debug_files(), +#endif { } /* terminate */ }; +#define bfq_make_blkg_files(prefix) \ + { \ + .name = #prefix "weight", \ + .flags = CFTYPE_NOT_ON_ROOT, \ + .seq_show = bfq_io_show_weight, \ + .write = bfq_io_set_weight, \ + } + struct cftype bfq_blkg_files[] = { - { - .name = "bfq.weight", - .flags = CFTYPE_NOT_ON_ROOT, - .seq_show = bfq_io_show_weight, - .write = bfq_io_set_weight, - }, + bfq_make_blkg_files(bfq.), + bfq_make_blkg_files(), {} /* terminate */ }; diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 0c6214497fcc..f42296175434 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -6402,6 +6402,36 @@ static void bfq_init_root_group(struct bfq_group *root_group, root_group->sched_data.bfq_class_idle_last_service = jiffies; } +#if defined(CONFIG_BFQ_GROUP_IOSCHED) && defined(CONFIG_BLK_CGROUP_IOCOST) +static bool bfq_enabled = false; + +static void bfq_enable(void) +{ + static DEFINE_MUTEX(bfq_enable_mutex); + + mutex_lock(&bfq_enable_mutex); + if (!bfq_enabled) { + pr_info("bfq-iosched: Overriding iocost\n"); + blkcg_policy_unregister(&blkcg_policy_iocost); + cgroup_add_dfl_cftypes(&io_cgrp_subsys, bfq_blkg_files); + bfq_enabled = true; + } + mutex_unlock(&bfq_enable_mutex); +} + +static void __exit bfq_disable(void) +{ + if (bfq_enabled) { + pr_info("bfq-iosched: Restoring iocost\n"); + cgroup_rm_cftypes(bfq_blkg_files); + blkcg_policy_register(&blkcg_policy_iocost); + } +} +#else +static void bfq_enable(void) {} +static void __exit bfq_disable(void) {} +#endif + static int bfq_init_queue(struct request_queue *q, struct elevator_type *e) { struct bfq_data *bfqd; @@ -6526,6 +6556,7 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e) bfq_init_entity(&bfqd->oom_bfqq.entity, bfqd->root_group); wbt_disable_default(q); + bfq_enable(); return 0; out_free: @@ -6843,6 +6874,7 @@ static void __exit bfq_exit(void) blkcg_policy_unregister(&blkcg_policy_bfq); #endif bfq_slab_kill(); + bfq_disable(); } module_init(bfq_init); diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h index 5d1a519640f6..b320fe9f7676 100644 --- a/block/bfq-iosched.h +++ b/block/bfq-iosched.h @@ -1062,6 +1062,8 @@ struct bfq_group *bfqq_group(struct bfq_queue *bfqq); #define bfq_log_bfqq(bfqd, bfqq, fmt, args...) do { \ char pid_str[MAX_PID_STR_LENGTH]; \ + if (likely(!blk_trace_note_message_enabled((bfqd)->queue))) \ + break; \ bfq_pid_to_str((bfqq)->pid, pid_str, MAX_PID_STR_LENGTH); \ blk_add_cgroup_trace_msg((bfqd)->queue, \ bfqg_to_blkg(bfqq_group(bfqq))->blkcg, \ @@ -1078,6 +1080,8 @@ struct bfq_group *bfqq_group(struct bfq_queue *bfqq); #define bfq_log_bfqq(bfqd, bfqq, fmt, args...) do { \ char pid_str[MAX_PID_STR_LENGTH]; \ + if (likely(!blk_trace_note_message_enabled((bfqd)->queue))) \ + break; \ bfq_pid_to_str((bfqq)->pid, pid_str, MAX_PID_STR_LENGTH); \ blk_add_trace_msg((bfqd)->queue, "bfq%s%c " fmt, pid_str, \ bfq_bfqq_sync((bfqq)) ? 'S' : 'A', \ diff --git a/block/bio.c b/block/bio.c index b1170ec18464..906da3581a3e 100644 --- a/block/bio.c +++ b/block/bio.c @@ -535,6 +535,55 @@ void zero_fill_bio_iter(struct bio *bio, struct bvec_iter start) } EXPORT_SYMBOL(zero_fill_bio_iter); +/** + * bio_truncate - truncate the bio to small size of @new_size + * @bio: the bio to be truncated + * @new_size: new size for truncating the bio + * + * Description: + * Truncate the bio to new size of @new_size. If bio_op(bio) is + * REQ_OP_READ, zero the truncated part. This function should only + * be used for handling corner cases, such as bio eod. + */ +void bio_truncate(struct bio *bio, unsigned new_size) +{ + struct bio_vec bv; + struct bvec_iter iter; + unsigned int done = 0; + bool truncated = false; + + if (new_size >= bio->bi_iter.bi_size) + return; + + if (bio_op(bio) != REQ_OP_READ) + goto exit; + + bio_for_each_segment(bv, bio, iter) { + if (done + bv.bv_len > new_size) { + unsigned offset; + + if (!truncated) + offset = new_size - done; + else + offset = 0; + zero_user(bv.bv_page, offset, bv.bv_len - offset); + truncated = true; + } + done += bv.bv_len; + } + + exit: + /* + * Don't touch bvec table here and make it really immutable, since + * fs bio user has to retrieve all pages via bio_for_each_segment_all + * in its .end_bio() callback. + * + * It is enough to truncate bio by updating .bi_size since we can make + * correct bvec with the updated .bi_size for drivers. + */ + bio->bi_iter.bi_size = new_size; +} + /** * bio_put - release a reference to a bio * @bio: bio to release reference to @@ -751,10 +800,12 @@ bool __bio_try_merge_page(struct bio *bio, struct page *page, if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED))) return false; - if (bio->bi_vcnt > 0 && !bio_full(bio, len)) { + if (bio->bi_vcnt > 0) { struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1]; if (page_is_mergeable(bv, page, len, off, same_page)) { + if (bio->bi_iter.bi_size > UINT_MAX - len) + return false; bv->bv_len += len; bio->bi_iter.bi_size += len; return true; diff --git a/block/blk-core.c b/block/blk-core.c index d5e668ec751b..1075aaff606d 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -886,11 +886,14 @@ generic_make_request_checks(struct bio *bio) } /* - * For a REQ_NOWAIT based request, return -EOPNOTSUPP - * if queue is not a request based queue. + * Non-mq queues do not honor REQ_NOWAIT, so complete a bio + * with BLK_STS_AGAIN status in order to catch -EAGAIN and + * to give a chance to the caller to repeat request gracefully. */ - if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_mq(q)) - goto not_supported; + if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_mq(q)) { + status = BLK_STS_AGAIN; + goto end_io; + } if (should_fail_bio(bio)) goto end_io; diff --git a/block/blk-flush.c b/block/blk-flush.c index 1eec9cbe5a0a..b1f0a1ac505c 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -69,6 +69,7 @@ #include #include #include +#include #include "blk.h" #include "blk-mq.h" @@ -492,6 +493,9 @@ struct blk_flush_queue *blk_alloc_flush_queue(struct request_queue *q, INIT_LIST_HEAD(&fq->flush_queue[1]); INIT_LIST_HEAD(&fq->flush_data_in_flight); + lockdep_register_key(&fq->key); + lockdep_set_class(&fq->mq_flush_lock, &fq->key); + return fq; fail_rq: @@ -506,6 +510,7 @@ void blk_free_flush_queue(struct blk_flush_queue *fq) if (!fq) return; + lockdep_unregister_key(&fq->key); kfree(fq->flush_rq); kfree(fq); } diff --git a/block/blk-iocost.c b/block/blk-iocost.c index e01267f99183..09b84e65d42f 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -605,8 +605,6 @@ static u32 vrate_adj_pct[] = 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 4, 4, 4, 4, 4, 4, 4, 8, 8, 8, 8, 8, 8, 8, 8, 16 }; -static struct blkcg_policy blkcg_policy_iocost; - /* accessors and helpers */ static struct ioc *rqos_to_ioc(struct rq_qos *rqos) { @@ -1212,7 +1210,7 @@ static enum hrtimer_restart iocg_waitq_timer_fn(struct hrtimer *timer) return HRTIMER_NORESTART; } -static void iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now, u64 cost) +static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now, u64 cost) { struct ioc *ioc = iocg->ioc; struct blkcg_gq *blkg = iocg_to_blkg(iocg); @@ -1229,11 +1227,11 @@ static void iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now, u64 cost) /* clear or maintain depending on the overage */ if (time_before_eq64(vtime, now->vnow)) { blkcg_clear_delay(blkg); - return; + return false; } if (!atomic_read(&blkg->use_delay) && time_before_eq64(vtime, now->vnow + vmargin)) - return; + return false; /* use delay */ if (cost) { @@ -1250,10 +1248,11 @@ static void iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now, u64 cost) oexpires = ktime_to_ns(hrtimer_get_softexpires(&iocg->delay_timer)); if (hrtimer_is_queued(&iocg->delay_timer) && abs(oexpires - expires) <= margin_ns / 4) - return; + return true; hrtimer_start_range_ns(&iocg->delay_timer, ns_to_ktime(expires), margin_ns / 4, HRTIMER_MODE_ABS); + return true; } static enum hrtimer_restart iocg_delay_timer_fn(struct hrtimer *timer) @@ -1739,7 +1738,9 @@ static void ioc_rqos_throttle(struct rq_qos *rqos, struct bio *bio) */ if (bio_issue_as_root_blkg(bio) || fatal_signal_pending(current)) { atomic64_add(abs_cost, &iocg->abs_vdebt); - iocg_kick_delay(iocg, &now, cost); + if (iocg_kick_delay(iocg, &now, cost)) + blkcg_schedule_throttle(rqos->q, + (bio->bi_opf & REQ_SWAP) == REQ_SWAP); return; } @@ -2446,7 +2447,7 @@ static struct cftype ioc_files[] = { {} }; -static struct blkcg_policy blkcg_policy_iocost = { +struct blkcg_policy blkcg_policy_iocost = { .dfl_cftypes = ioc_files, .cpd_alloc_fn = ioc_cpd_alloc, .cpd_free_fn = ioc_cpd_free, @@ -2454,6 +2455,7 @@ static struct blkcg_policy blkcg_policy_iocost = { .pd_init_fn = ioc_pd_init, .pd_free_fn = ioc_pd_free, }; +EXPORT_SYMBOL_GPL(blkcg_policy_iocost); static int __init ioc_init(void) { diff --git a/block/blk-map.c b/block/blk-map.c index 3a62e471d81b..b0790268ed9d 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -151,7 +151,7 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq, return 0; unmap_rq: - __blk_rq_unmap_user(bio); + blk_rq_unmap_user(bio); fail: rq->bio = NULL; return ret; diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c index a0d3ce30fa08..a09ab0c3d074 100644 --- a/block/blk-mq-sysfs.c +++ b/block/blk-mq-sysfs.c @@ -166,20 +166,25 @@ static ssize_t blk_mq_hw_sysfs_nr_reserved_tags_show(struct blk_mq_hw_ctx *hctx, static ssize_t blk_mq_hw_sysfs_cpus_show(struct blk_mq_hw_ctx *hctx, char *page) { + const size_t size = PAGE_SIZE - 1; unsigned int i, first = 1; - ssize_t ret = 0; + int ret = 0, pos = 0; for_each_cpu(i, hctx->cpumask) { if (first) - ret += sprintf(ret + page, "%u", i); + ret = snprintf(pos + page, size - pos, "%u", i); else - ret += sprintf(ret + page, ", %u", i); + ret = snprintf(pos + page, size - pos, ", %u", i); + + if (ret >= size - pos) + break; first = 0; + pos += ret; } - ret += sprintf(ret + page, "\n"); - return ret; + ret = snprintf(pos + page, size + 1 - pos, "\n"); + return pos + ret; } static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_nr_tags = { diff --git a/block/blk.h b/block/blk.h index 47fba9362e60..ffea1691470e 100644 --- a/block/blk.h +++ b/block/blk.h @@ -30,6 +30,7 @@ struct blk_flush_queue { * at the same time */ struct request *orig_rq; + struct lock_class_key key; spinlock_t mq_flush_lock; }; diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c index 6ca015f92766..7f053468b50d 100644 --- a/block/compat_ioctl.c +++ b/block/compat_ioctl.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include @@ -354,6 +355,10 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) * but we call blkdev_ioctl, which gets the lock for us */ case BLKRRPART: + case BLKREPORTZONE: + case BLKRESETZONE: + case BLKGETZONESZ: + case BLKGETNRZONES: return blkdev_ioctl(bdev, mode, cmd, (unsigned long)compat_ptr(arg)); case BLKBSZSET_32: @@ -401,6 +406,14 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) case BLKTRACETEARDOWN: /* compatible */ ret = blk_trace_ioctl(bdev, cmd, compat_ptr(arg)); return ret; + case IOC_PR_REGISTER: + case IOC_PR_RESERVE: + case IOC_PR_RELEASE: + case IOC_PR_PREEMPT: + case IOC_PR_PREEMPT_ABORT: + case IOC_PR_CLEAR: + return blkdev_ioctl(bdev, mode, cmd, + (unsigned long)compat_ptr(arg)); default: if (disk->fops->compat_ioctl) ret = disk->fops->compat_ioctl(bdev, mode, cmd, arg); diff --git a/crypto/Kconfig b/crypto/Kconfig index 9e524044d312..29472fb795f3 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -309,6 +309,7 @@ config CRYPTO_AEGIS128 config CRYPTO_AEGIS128_SIMD bool "Support SIMD acceleration for AEGIS-128" depends on CRYPTO_AEGIS128 && ((ARM || ARM64) && KERNEL_MODE_NEON) + depends on !ARM || CC_IS_CLANG || GCC_VERSION >= 40800 default y config CRYPTO_AEGIS128_AESNI_SSE2 diff --git a/crypto/Makefile b/crypto/Makefile index fcb1ee679782..aa740c8492b9 100644 --- a/crypto/Makefile +++ b/crypto/Makefile @@ -93,7 +93,7 @@ obj-$(CONFIG_CRYPTO_AEGIS128) += aegis128.o aegis128-y := aegis128-core.o ifeq ($(ARCH),arm) -CFLAGS_aegis128-neon-inner.o += -ffreestanding -march=armv7-a -mfloat-abi=softfp +CFLAGS_aegis128-neon-inner.o += -ffreestanding -march=armv8-a -mfloat-abi=softfp CFLAGS_aegis128-neon-inner.o += -mfpu=crypto-neon-fp-armv8 aegis128-$(CONFIG_CRYPTO_AEGIS128_SIMD) += aegis128-neon.o aegis128-neon-inner.o endif diff --git a/crypto/af_alg.c b/crypto/af_alg.c index 879cf23f7489..0dceaabc6321 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -1043,7 +1043,7 @@ void af_alg_async_cb(struct crypto_async_request *_req, int err) af_alg_free_resources(areq); sock_put(sk); - iocb->ki_complete(iocb, err ? err : resultlen, 0); + iocb->ki_complete(iocb, err ? err : (int)resultlen, 0); } EXPORT_SYMBOL_GPL(af_alg_async_cb); diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index c1601edd70e3..e2c8ab408bed 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -56,7 +56,7 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg, struct alg_sock *pask = alg_sk(psk); struct af_alg_ctx *ctx = ask->private; struct crypto_skcipher *tfm = pask->private; - unsigned int bs = crypto_skcipher_blocksize(tfm); + unsigned int bs = crypto_skcipher_chunksize(tfm); struct af_alg_async_req *areq; int err = 0; size_t len = 0; diff --git a/crypto/asymmetric_keys/asym_tpm.c b/crypto/asymmetric_keys/asym_tpm.c index 76d2ce3a1b5b..5154e280ada2 100644 --- a/crypto/asymmetric_keys/asym_tpm.c +++ b/crypto/asymmetric_keys/asym_tpm.c @@ -486,6 +486,7 @@ static int tpm_key_encrypt(struct tpm_key *tk, if (ret < 0) goto error_free_tfm; + ret = -ENOMEM; req = akcipher_request_alloc(tfm, GFP_KERNEL); if (!req) goto error_free_tfm; diff --git a/crypto/asymmetric_keys/public_key.c b/crypto/asymmetric_keys/public_key.c index 364b9df9d631..d7f43d4ea925 100644 --- a/crypto/asymmetric_keys/public_key.c +++ b/crypto/asymmetric_keys/public_key.c @@ -184,6 +184,7 @@ static int software_key_eds_op(struct kernel_pkey_params *params, if (IS_ERR(tfm)) return PTR_ERR(tfm); + ret = -ENOMEM; req = akcipher_request_alloc(tfm, GFP_KERNEL); if (!req) goto error_free_tfm; diff --git a/crypto/crypto_user_base.c b/crypto/crypto_user_base.c index 910e0b46012e..b785c476de67 100644 --- a/crypto/crypto_user_base.c +++ b/crypto/crypto_user_base.c @@ -213,8 +213,10 @@ static int crypto_report(struct sk_buff *in_skb, struct nlmsghdr *in_nlh, drop_alg: crypto_mod_put(alg); - if (err) + if (err) { + kfree_skb(skb); return err; + } return nlmsg_unicast(net->crypto_nlsk, skb, NETLINK_CB(in_skb).portid); } diff --git a/crypto/crypto_user_stat.c b/crypto/crypto_user_stat.c index 8bad88413de1..1be95432fa23 100644 --- a/crypto/crypto_user_stat.c +++ b/crypto/crypto_user_stat.c @@ -328,8 +328,10 @@ int crypto_reportstat(struct sk_buff *in_skb, struct nlmsghdr *in_nlh, drop_alg: crypto_mod_put(alg); - if (err) + if (err) { + kfree_skb(skb); return err; + } return nlmsg_unicast(net->crypto_nlsk, skb, NETLINK_CB(in_skb).portid); } diff --git a/crypto/ecc.c b/crypto/ecc.c index dfe114bc0c4a..8ee787723c5c 100644 --- a/crypto/ecc.c +++ b/crypto/ecc.c @@ -1284,10 +1284,11 @@ EXPORT_SYMBOL(ecc_point_mult_shamir); static inline void ecc_swap_digits(const u64 *in, u64 *out, unsigned int ndigits) { + const __be64 *src = (__force __be64 *)in; int i; for (i = 0; i < ndigits; i++) - out[i] = __swab64(in[ndigits - 1 - i]); + out[i] = be64_to_cpu(src[ndigits - 1 - i]); } static int __ecc_is_key_valid(const struct ecc_curve *curve, diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c index 60bbc5090abe..751ed38f2a10 100644 --- a/drivers/acpi/acpi_lpss.c +++ b/drivers/acpi/acpi_lpss.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -463,6 +464,18 @@ struct lpss_device_links { const char *consumer_hid; const char *consumer_uid; u32 flags; + const struct dmi_system_id *dep_missing_ids; +}; + +/* Please keep this list sorted alphabetically by vendor and model */ +static const struct dmi_system_id i2c1_dep_missing_dmi_ids[] = { + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "T200TA"), + }, + }, + {} }; /* @@ -473,9 +486,17 @@ struct lpss_device_links { * the supplier is not enumerated until after the consumer is probed. */ static const struct lpss_device_links lpss_device_links[] = { + /* CHT External sdcard slot controller depends on PMIC I2C ctrl */ {"808622C1", "7", "80860F14", "3", DL_FLAG_PM_RUNTIME}, + /* CHT iGPU depends on PMIC I2C controller */ {"808622C1", "7", "LNXVIDEO", NULL, DL_FLAG_PM_RUNTIME}, + /* BYT iGPU depends on the Embedded Controller I2C controller (UID 1) */ + {"80860F41", "1", "LNXVIDEO", NULL, DL_FLAG_PM_RUNTIME, + i2c1_dep_missing_dmi_ids}, + /* BYT CR iGPU depends on PMIC I2C controller (UID 5 on CR) */ {"80860F41", "5", "LNXVIDEO", NULL, DL_FLAG_PM_RUNTIME}, + /* BYT iGPU depends on PMIC I2C controller (UID 7 on non CR) */ + {"80860F41", "7", "LNXVIDEO", NULL, DL_FLAG_PM_RUNTIME}, }; static bool hid_uid_match(struct acpi_device *adev, @@ -570,7 +591,8 @@ static void acpi_lpss_link_consumer(struct device *dev1, if (!dev2) return; - if (acpi_lpss_dep(ACPI_COMPANION(dev2), ACPI_HANDLE(dev1))) + if ((link->dep_missing_ids && dmi_check_system(link->dep_missing_ids)) + || acpi_lpss_dep(ACPI_COMPANION(dev2), ACPI_HANDLE(dev1))) device_link_add(dev2, dev1, link->flags); put_device(dev2); @@ -585,7 +607,8 @@ static void acpi_lpss_link_supplier(struct device *dev1, if (!dev2) return; - if (acpi_lpss_dep(ACPI_COMPANION(dev1), ACPI_HANDLE(dev2))) + if ((link->dep_missing_ids && dmi_check_system(link->dep_missing_ids)) + || acpi_lpss_dep(ACPI_COMPANION(dev1), ACPI_HANDLE(dev2))) device_link_add(dev1, dev2, link->flags); put_device(dev2); diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index 48bc96d45bab..54002670cb7a 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -153,7 +153,7 @@ int acpi_bus_get_private_data(acpi_handle handle, void **data) { acpi_status status; - if (!*data) + if (!data) return -EINVAL; status = acpi_get_data(handle, acpi_bus_private_data_handler, data); diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c index 4a2cde2c536a..ce93a355bd1c 100644 --- a/drivers/acpi/button.c +++ b/drivers/acpi/button.c @@ -78,6 +78,17 @@ static const struct dmi_system_id lid_blacklst[] = { DMI_MATCH(DMI_BIOS_VERSION, "BYT70A.YNCHENG.WIN.007"), }, }, + { + /* + * Medion Akoya E2215T, notification of the LID device only + * happens on close, not on open and _LID always returns closed. + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "MEDION"), + DMI_MATCH(DMI_PRODUCT_NAME, "E2215T MD60198"), + }, + .driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_OPEN, + }, {} }; diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c index 08bb9f2f2d23..5e4a8860a9c0 100644 --- a/drivers/acpi/device_pm.c +++ b/drivers/acpi/device_pm.c @@ -1314,9 +1314,19 @@ static void acpi_dev_pm_detach(struct device *dev, bool power_off) */ int acpi_dev_pm_attach(struct device *dev, bool power_on) { + /* + * Skip devices whose ACPI companions match the device IDs below, + * because they require special power management handling incompatible + * with the generic ACPI PM domain. + */ + static const struct acpi_device_id special_pm_ids[] = { + {"PNP0C0B", }, /* Generic ACPI fan */ + {"INT3404", }, /* Fan */ + {} + }; struct acpi_device *adev = ACPI_COMPANION(dev); - if (!adev) + if (!adev || !acpi_match_device_ids(adev, special_pm_ids)) return 0; /* diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index da1e5c5ce150..bd75caff8322 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -525,26 +525,10 @@ static void acpi_ec_enable_event(struct acpi_ec *ec) } #ifdef CONFIG_PM_SLEEP -static bool acpi_ec_query_flushed(struct acpi_ec *ec) +static void __acpi_ec_flush_work(void) { - bool flushed; - unsigned long flags; - - spin_lock_irqsave(&ec->lock, flags); - flushed = !ec->nr_pending_queries; - spin_unlock_irqrestore(&ec->lock, flags); - return flushed; -} - -static void __acpi_ec_flush_event(struct acpi_ec *ec) -{ - /* - * When ec_freeze_events is true, we need to flush events in - * the proper position before entering the noirq stage. - */ - wait_event(ec->wait, acpi_ec_query_flushed(ec)); - if (ec_query_wq) - flush_workqueue(ec_query_wq); + flush_scheduled_work(); /* flush ec->work */ + flush_workqueue(ec_query_wq); /* flush queries */ } static void acpi_ec_disable_event(struct acpi_ec *ec) @@ -554,15 +538,21 @@ static void acpi_ec_disable_event(struct acpi_ec *ec) spin_lock_irqsave(&ec->lock, flags); __acpi_ec_disable_event(ec); spin_unlock_irqrestore(&ec->lock, flags); - __acpi_ec_flush_event(ec); + + /* + * When ec_freeze_events is true, we need to flush events in + * the proper position before entering the noirq stage. + */ + __acpi_ec_flush_work(); } void acpi_ec_flush_work(void) { - if (first_ec) - __acpi_ec_flush_event(first_ec); + /* Without ec_query_wq there is nothing to flush. */ + if (!ec_query_wq) + return; - flush_scheduled_work(); + __acpi_ec_flush_work(); } #endif /* CONFIG_PM_SLEEP */ diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c index a2e844a8e9ed..41168c027a5a 100644 --- a/drivers/acpi/osl.c +++ b/drivers/acpi/osl.c @@ -374,19 +374,21 @@ void *__ref acpi_os_map_memory(acpi_physical_address phys, acpi_size size) } EXPORT_SYMBOL_GPL(acpi_os_map_memory); -static void acpi_os_drop_map_ref(struct acpi_ioremap *map) +/* Must be called with mutex_lock(&acpi_ioremap_lock) */ +static unsigned long acpi_os_drop_map_ref(struct acpi_ioremap *map) { - if (!--map->refcount) + unsigned long refcount = --map->refcount; + + if (!refcount) list_del_rcu(&map->list); + return refcount; } static void acpi_os_map_cleanup(struct acpi_ioremap *map) { - if (!map->refcount) { - synchronize_rcu_expedited(); - acpi_unmap(map->phys, map->virt); - kfree(map); - } + synchronize_rcu_expedited(); + acpi_unmap(map->phys, map->virt); + kfree(map); } /** @@ -406,6 +408,7 @@ static void acpi_os_map_cleanup(struct acpi_ioremap *map) void __ref acpi_os_unmap_iomem(void __iomem *virt, acpi_size size) { struct acpi_ioremap *map; + unsigned long refcount; if (!acpi_permanent_mmap) { __acpi_unmap_table(virt, size); @@ -419,10 +422,11 @@ void __ref acpi_os_unmap_iomem(void __iomem *virt, acpi_size size) WARN(true, PREFIX "%s: bad address %p\n", __func__, virt); return; } - acpi_os_drop_map_ref(map); + refcount = acpi_os_drop_map_ref(map); mutex_unlock(&acpi_ioremap_lock); - acpi_os_map_cleanup(map); + if (!refcount) + acpi_os_map_cleanup(map); } EXPORT_SYMBOL_GPL(acpi_os_unmap_iomem); @@ -457,6 +461,7 @@ void acpi_os_unmap_generic_address(struct acpi_generic_address *gas) { u64 addr; struct acpi_ioremap *map; + unsigned long refcount; if (gas->space_id != ACPI_ADR_SPACE_SYSTEM_MEMORY) return; @@ -472,10 +477,11 @@ void acpi_os_unmap_generic_address(struct acpi_generic_address *gas) mutex_unlock(&acpi_ioremap_lock); return; } - acpi_os_drop_map_ref(map); + refcount = acpi_os_drop_map_ref(map); mutex_unlock(&acpi_ioremap_lock); - acpi_os_map_cleanup(map); + if (!refcount) + acpi_os_map_cleanup(map); } EXPORT_SYMBOL(acpi_os_unmap_generic_address); diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 2af937a8b1c5..6747a279621b 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -977,6 +977,16 @@ static int acpi_s2idle_prepare_late(void) return 0; } +static void acpi_s2idle_sync(void) +{ + /* + * The EC driver uses the system workqueue and an additional special + * one, so those need to be flushed too. + */ + acpi_ec_flush_work(); + acpi_os_wait_events_complete(); /* synchronize Notify handling */ +} + static void acpi_s2idle_wake(void) { /* @@ -1001,13 +1011,8 @@ static void acpi_s2idle_wake(void) * should be missed by canceling the wakeup here. */ pm_system_cancel_wakeup(); - /* - * The EC driver uses the system workqueue and an additional - * special one, so those need to be flushed too. - */ - acpi_os_wait_events_complete(); /* synchronize EC GPE processing */ - acpi_ec_flush_work(); - acpi_os_wait_events_complete(); /* synchronize Notify handling */ + + acpi_s2idle_sync(); rearm_wake_irq(acpi_sci_irq); } @@ -1024,6 +1029,13 @@ static void acpi_s2idle_restore_early(void) static void acpi_s2idle_restore(void) { + /* + * Drain pending events before restoring the working-state configuration + * of GPEs. + */ + acpi_os_wait_events_complete(); /* synchronize GPE processing */ + acpi_s2idle_sync(); + s2idle_wakeup = false; acpi_enable_all_runtime_gpes(); diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c index 75948a3f1a20..c60d2c6d31d6 100644 --- a/drivers/acpi/sysfs.c +++ b/drivers/acpi/sysfs.c @@ -819,14 +819,14 @@ static ssize_t counter_set(struct kobject *kobj, * interface: * echo unmask > /sys/firmware/acpi/interrupts/gpe00 */ -#define ACPI_MASKABLE_GPE_MAX 0xFF +#define ACPI_MASKABLE_GPE_MAX 0x100 static DECLARE_BITMAP(acpi_masked_gpes_map, ACPI_MASKABLE_GPE_MAX) __initdata; static int __init acpi_gpe_set_masked_gpes(char *val) { u8 gpe; - if (kstrtou8(val, 0, &gpe) || gpe > ACPI_MASKABLE_GPE_MAX) + if (kstrtou8(val, 0, &gpe)) return -EINVAL; set_bit(gpe, acpi_masked_gpes_map); @@ -838,7 +838,7 @@ void __init acpi_gpe_apply_masked_gpes(void) { acpi_handle handle; acpi_status status; - u8 gpe; + u16 gpe; for_each_set_bit(gpe, acpi_masked_gpes_map, ACPI_MASKABLE_GPE_MAX) { status = acpi_get_gpe_device(gpe, &handle); diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 265d9dd46a5e..976a69420c16 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -3314,7 +3314,7 @@ static void binder_transaction(struct binder_proc *proc, binder_size_t parent_offset; struct binder_fd_array_object *fda = to_binder_fd_array_object(hdr); - size_t num_valid = (buffer_offset - off_start_offset) * + size_t num_valid = (buffer_offset - off_start_offset) / sizeof(binder_size_t); struct binder_buffer_object *parent = binder_validate_ptr(target_proc, t->buffer, @@ -3388,7 +3388,7 @@ static void binder_transaction(struct binder_proc *proc, t->buffer->user_data + sg_buf_offset; sg_buf_offset += ALIGN(bp->length, sizeof(u64)); - num_valid = (buffer_offset - off_start_offset) * + num_valid = (buffer_offset - off_start_offset) / sizeof(binder_size_t); ret = binder_fixup_parent(t, thread, bp, off_start_offset, diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index eb76a823fbb2..7067d5542a82 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -277,8 +277,7 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate, return 0; free_range: - for (page_addr = end - PAGE_SIZE; page_addr >= start; - page_addr -= PAGE_SIZE) { + for (page_addr = end - PAGE_SIZE; 1; page_addr -= PAGE_SIZE) { bool ret; size_t index; @@ -291,6 +290,8 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate, WARN_ON(!ret); trace_binder_free_lru_end(alloc, index); + if (page_addr == start) + break; continue; err_vm_insert_page_failed: @@ -298,7 +299,8 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate, page->page_ptr = NULL; err_alloc_page_failed: err_page_ptr_cleared: - ; + if (page_addr == start) + break; } err_no_vma: if (mm) { @@ -681,17 +683,17 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc, struct binder_buffer *buffer; mutex_lock(&binder_alloc_mmap_lock); - if (alloc->buffer) { + if (alloc->buffer_size) { ret = -EBUSY; failure_string = "already mapped"; goto err_already_mapped; } + alloc->buffer_size = min_t(unsigned long, vma->vm_end - vma->vm_start, + SZ_4M); + mutex_unlock(&binder_alloc_mmap_lock); alloc->buffer = (void __user *)vma->vm_start; - mutex_unlock(&binder_alloc_mmap_lock); - alloc->buffer_size = min_t(unsigned long, vma->vm_end - vma->vm_start, - SZ_4M); alloc->pages = kcalloc(alloc->buffer_size / PAGE_SIZE, sizeof(alloc->pages[0]), GFP_KERNEL); @@ -722,8 +724,9 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc, kfree(alloc->pages); alloc->pages = NULL; err_alloc_pages_failed: - mutex_lock(&binder_alloc_mmap_lock); alloc->buffer = NULL; + mutex_lock(&binder_alloc_mmap_lock); + alloc->buffer_size = 0; err_already_mapped: mutex_unlock(&binder_alloc_mmap_lock); binder_alloc_debug(BINDER_DEBUG_USER_ERROR, @@ -841,14 +844,20 @@ void binder_alloc_print_pages(struct seq_file *m, int free = 0; mutex_lock(&alloc->mutex); - for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) { - page = &alloc->pages[i]; - if (!page->page_ptr) - free++; - else if (list_empty(&page->lru)) - active++; - else - lru++; + /* + * Make sure the binder_alloc is fully initialized, otherwise we might + * read inconsistent state. + */ + if (binder_alloc_get_vma(alloc) != NULL) { + for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) { + page = &alloc->pages[i]; + if (!page->page_ptr) + free++; + else if (list_empty(&page->lru)) + active++; + else + lru++; + } } mutex_unlock(&alloc->mutex); seq_printf(m, " pages: %d:%d:%d\n", active, lru, free); diff --git a/drivers/ata/ahci_brcm.c b/drivers/ata/ahci_brcm.c index f41744b9b38a..66a570d0da83 100644 --- a/drivers/ata/ahci_brcm.c +++ b/drivers/ata/ahci_brcm.c @@ -76,8 +76,7 @@ enum brcm_ahci_version { }; enum brcm_ahci_quirks { - BRCM_AHCI_QUIRK_NO_NCQ = BIT(0), - BRCM_AHCI_QUIRK_SKIP_PHY_ENABLE = BIT(1), + BRCM_AHCI_QUIRK_SKIP_PHY_ENABLE = BIT(0), }; struct brcm_ahci_priv { @@ -213,19 +212,12 @@ static void brcm_sata_phys_disable(struct brcm_ahci_priv *priv) brcm_sata_phy_disable(priv, i); } -static u32 brcm_ahci_get_portmask(struct platform_device *pdev, +static u32 brcm_ahci_get_portmask(struct ahci_host_priv *hpriv, struct brcm_ahci_priv *priv) { - void __iomem *ahci; - struct resource *res; u32 impl; - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "ahci"); - ahci = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(ahci)) - return 0; - - impl = readl(ahci + HOST_PORTS_IMPL); + impl = readl(hpriv->mmio + HOST_PORTS_IMPL); if (fls(impl) > SATA_TOP_MAX_PHYS) dev_warn(priv->dev, "warning: more ports than PHYs (%#x)\n", @@ -233,9 +225,6 @@ static u32 brcm_ahci_get_portmask(struct platform_device *pdev, else if (!impl) dev_info(priv->dev, "no ports found\n"); - devm_iounmap(&pdev->dev, ahci); - devm_release_mem_region(&pdev->dev, res->start, resource_size(res)); - return impl; } @@ -285,6 +274,13 @@ static unsigned int brcm_ahci_read_id(struct ata_device *dev, /* Perform the SATA PHY reset sequence */ brcm_sata_phy_disable(priv, ap->port_no); + /* Reset the SATA clock */ + ahci_platform_disable_clks(hpriv); + msleep(10); + + ahci_platform_enable_clks(hpriv); + msleep(10); + /* Bring the PHY back on */ brcm_sata_phy_enable(priv, ap->port_no); @@ -347,11 +343,10 @@ static int brcm_ahci_suspend(struct device *dev) struct ata_host *host = dev_get_drvdata(dev); struct ahci_host_priv *hpriv = host->private_data; struct brcm_ahci_priv *priv = hpriv->plat_data; - int ret; - ret = ahci_platform_suspend(dev); brcm_sata_phys_disable(priv); - return ret; + + return ahci_platform_suspend(dev); } static int brcm_ahci_resume(struct device *dev) @@ -359,11 +354,44 @@ static int brcm_ahci_resume(struct device *dev) struct ata_host *host = dev_get_drvdata(dev); struct ahci_host_priv *hpriv = host->private_data; struct brcm_ahci_priv *priv = hpriv->plat_data; + int ret; + + /* Make sure clocks are turned on before re-configuration */ + ret = ahci_platform_enable_clks(hpriv); + if (ret) + return ret; brcm_sata_init(priv); brcm_sata_phys_enable(priv); brcm_sata_alpm_init(hpriv); - return ahci_platform_resume(dev); + + /* Since we had to enable clocks earlier on, we cannot use + * ahci_platform_resume() as-is since a second call to + * ahci_platform_enable_resources() would bump up the resources + * (regulators, clocks, PHYs) count artificially so we copy the part + * after ahci_platform_enable_resources(). + */ + ret = ahci_platform_enable_phys(hpriv); + if (ret) + goto out_disable_phys; + + ret = ahci_platform_resume_host(dev); + if (ret) + goto out_disable_platform_phys; + + /* We resumed so update PM runtime state */ + pm_runtime_disable(dev); + pm_runtime_set_active(dev); + pm_runtime_enable(dev); + + return 0; + +out_disable_platform_phys: + ahci_platform_disable_phys(hpriv); +out_disable_phys: + brcm_sata_phys_disable(priv); + ahci_platform_disable_clks(hpriv); + return ret; } #endif @@ -410,44 +438,71 @@ static int brcm_ahci_probe(struct platform_device *pdev) if (!IS_ERR_OR_NULL(priv->rcdev)) reset_control_deassert(priv->rcdev); - if ((priv->version == BRCM_SATA_BCM7425) || - (priv->version == BRCM_SATA_NSP)) { - priv->quirks |= BRCM_AHCI_QUIRK_NO_NCQ; + hpriv = ahci_platform_get_resources(pdev, 0); + if (IS_ERR(hpriv)) { + ret = PTR_ERR(hpriv); + goto out_reset; + } + + hpriv->plat_data = priv; + hpriv->flags = AHCI_HFLAG_WAKE_BEFORE_STOP | AHCI_HFLAG_NO_WRITE_TO_RO; + + switch (priv->version) { + case BRCM_SATA_BCM7425: + hpriv->flags |= AHCI_HFLAG_DELAY_ENGINE; + /* fall through */ + case BRCM_SATA_NSP: + hpriv->flags |= AHCI_HFLAG_NO_NCQ; priv->quirks |= BRCM_AHCI_QUIRK_SKIP_PHY_ENABLE; + break; + default: + break; } + ret = ahci_platform_enable_clks(hpriv); + if (ret) + goto out_reset; + + /* Must be first so as to configure endianness including that + * of the standard AHCI register space. + */ brcm_sata_init(priv); - priv->port_mask = brcm_ahci_get_portmask(pdev, priv); - if (!priv->port_mask) - return -ENODEV; + /* Initializes priv->port_mask which is used below */ + priv->port_mask = brcm_ahci_get_portmask(hpriv, priv); + if (!priv->port_mask) { + ret = -ENODEV; + goto out_disable_clks; + } + /* Must be done before ahci_platform_enable_phys() */ brcm_sata_phys_enable(priv); - hpriv = ahci_platform_get_resources(pdev, 0); - if (IS_ERR(hpriv)) - return PTR_ERR(hpriv); - hpriv->plat_data = priv; - hpriv->flags = AHCI_HFLAG_WAKE_BEFORE_STOP; - brcm_sata_alpm_init(hpriv); - ret = ahci_platform_enable_resources(hpriv); + ret = ahci_platform_enable_phys(hpriv); if (ret) - return ret; - - if (priv->quirks & BRCM_AHCI_QUIRK_NO_NCQ) - hpriv->flags |= AHCI_HFLAG_NO_NCQ; - hpriv->flags |= AHCI_HFLAG_NO_WRITE_TO_RO; + goto out_disable_phys; ret = ahci_platform_init_host(pdev, hpriv, &ahci_brcm_port_info, &ahci_platform_sht); if (ret) - return ret; + goto out_disable_platform_phys; dev_info(dev, "Broadcom AHCI SATA3 registered\n"); return 0; + +out_disable_platform_phys: + ahci_platform_disable_phys(hpriv); +out_disable_phys: + brcm_sata_phys_disable(priv); +out_disable_clks: + ahci_platform_disable_clks(hpriv); +out_reset: + if (!IS_ERR_OR_NULL(priv->rcdev)) + reset_control_assert(priv->rcdev); + return ret; } static int brcm_ahci_remove(struct platform_device *pdev) @@ -457,12 +512,12 @@ static int brcm_ahci_remove(struct platform_device *pdev) struct brcm_ahci_priv *priv = hpriv->plat_data; int ret; + brcm_sata_phys_disable(priv); + ret = ata_platform_remove_one(pdev); if (ret) return ret; - brcm_sata_phys_disable(priv); - return 0; } diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c index 8befce036af8..129556fcf6be 100644 --- a/drivers/ata/libahci_platform.c +++ b/drivers/ata/libahci_platform.c @@ -43,7 +43,7 @@ EXPORT_SYMBOL_GPL(ahci_platform_ops); * RETURNS: * 0 on success otherwise a negative error code */ -static int ahci_platform_enable_phys(struct ahci_host_priv *hpriv) +int ahci_platform_enable_phys(struct ahci_host_priv *hpriv) { int rc, i; @@ -74,6 +74,7 @@ static int ahci_platform_enable_phys(struct ahci_host_priv *hpriv) } return rc; } +EXPORT_SYMBOL_GPL(ahci_platform_enable_phys); /** * ahci_platform_disable_phys - Disable PHYs @@ -81,7 +82,7 @@ static int ahci_platform_enable_phys(struct ahci_host_priv *hpriv) * * This function disables all PHYs found in hpriv->phys. */ -static void ahci_platform_disable_phys(struct ahci_host_priv *hpriv) +void ahci_platform_disable_phys(struct ahci_host_priv *hpriv) { int i; @@ -90,6 +91,7 @@ static void ahci_platform_disable_phys(struct ahci_host_priv *hpriv) phy_exit(hpriv->phys[i]); } } +EXPORT_SYMBOL_GPL(ahci_platform_disable_phys); /** * ahci_platform_enable_clks - Enable platform clocks diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 28c492be0a57..84b183a6424e 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -5325,6 +5325,30 @@ void ata_qc_complete(struct ata_queued_cmd *qc) } } +/** + * ata_qc_get_active - get bitmask of active qcs + * @ap: port in question + * + * LOCKING: + * spin_lock_irqsave(host lock) + * + * RETURNS: + * Bitmask of active qcs + */ +u64 ata_qc_get_active(struct ata_port *ap) +{ + u64 qc_active = ap->qc_active; + + /* ATA_TAG_INTERNAL is sent to hw as tag 0 */ + if (qc_active & (1ULL << ATA_TAG_INTERNAL)) { + qc_active |= (1 << 0); + qc_active &= ~(1ULL << ATA_TAG_INTERNAL); + } + + return qc_active; +} +EXPORT_SYMBOL_GPL(ata_qc_get_active); + /** * ata_qc_complete_multiple - Complete multiple qcs successfully * @ap: port in question @@ -6708,6 +6732,9 @@ void ata_host_detach(struct ata_host *host) { int i; + /* Ensure ata_port probe has completed */ + async_synchronize_full(); + for (i = 0; i < host->n_ports; i++) ata_port_detach(host->ports[i]); diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c index 8e9cb198fcd1..ca6c706e9c25 100644 --- a/drivers/ata/sata_fsl.c +++ b/drivers/ata/sata_fsl.c @@ -1278,7 +1278,7 @@ static void sata_fsl_host_intr(struct ata_port *ap) i, ioread32(hcr_base + CC), ioread32(hcr_base + CA)); } - ata_qc_complete_multiple(ap, ap->qc_active ^ done_mask); + ata_qc_complete_multiple(ap, ata_qc_get_active(ap) ^ done_mask); return; } else if ((ap->qc_active & (1ULL << ATA_TAG_INTERNAL))) { diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index ad385a113391..bde695a32097 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -2827,7 +2827,7 @@ static void mv_process_crpb_entries(struct ata_port *ap, struct mv_port_priv *pp } if (work_done) { - ata_qc_complete_multiple(ap, ap->qc_active ^ done_mask); + ata_qc_complete_multiple(ap, ata_qc_get_active(ap) ^ done_mask); /* Update the software queue position index in hardware */ writelfl((pp->crpb_dma & EDMA_RSP_Q_BASE_LO_MASK) | diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c index 56946012d113..7510303111fa 100644 --- a/drivers/ata/sata_nv.c +++ b/drivers/ata/sata_nv.c @@ -984,7 +984,7 @@ static irqreturn_t nv_adma_interrupt(int irq, void *dev_instance) check_commands = 0; check_commands &= ~(1 << pos); } - ata_qc_complete_multiple(ap, ap->qc_active ^ done_mask); + ata_qc_complete_multiple(ap, ata_qc_get_active(ap) ^ done_mask); } } diff --git a/drivers/base/firmware_loader/builtin/Makefile b/drivers/base/firmware_loader/builtin/Makefile index 37e5ae387400..4a66888e7253 100644 --- a/drivers/base/firmware_loader/builtin/Makefile +++ b/drivers/base/firmware_loader/builtin/Makefile @@ -8,7 +8,8 @@ fwdir := $(addprefix $(srctree)/,$(filter-out /%,$(fwdir)))$(filter /%,$(fwdir)) obj-y := $(addsuffix .gen.o, $(subst $(quote),,$(CONFIG_EXTRA_FIRMWARE))) FWNAME = $(patsubst $(obj)/%.gen.S,%,$@) -FWSTR = $(subst /,_,$(subst .,_,$(subst -,_,$(FWNAME)))) +comma := , +FWSTR = $(subst $(comma),_,$(subst /,_,$(subst .,_,$(subst -,_,$(FWNAME))))) ASM_WORD = $(if $(CONFIG_64BIT),.quad,.long) ASM_ALIGN = $(if $(CONFIG_64BIT),3,2) PROGBITS = $(if $(CONFIG_ARM),%,@)progbits diff --git a/drivers/base/platform.c b/drivers/base/platform.c index b230beb6ccb4..3c0cd20925b7 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -1278,6 +1278,11 @@ struct bus_type platform_bus_type = { }; EXPORT_SYMBOL_GPL(platform_bus_type); +static inline int __platform_match(struct device *dev, const void *drv) +{ + return platform_match(dev, (struct device_driver *)drv); +} + /** * platform_find_device_by_driver - Find a platform device with a given * driver. @@ -1288,7 +1293,7 @@ struct device *platform_find_device_by_driver(struct device *start, const struct device_driver *drv) { return bus_find_device(&platform_bus_type, start, drv, - (void *)platform_match); + __platform_match); } EXPORT_SYMBOL_GPL(platform_find_device_by_driver); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index f6f77eaa7217..ef6e251857c8 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -417,18 +417,20 @@ static int lo_read_transfer(struct loop_device *lo, struct request *rq, return ret; } -static int lo_discard(struct loop_device *lo, struct request *rq, loff_t pos) +static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos, + int mode) { /* - * We use punch hole to reclaim the free space used by the - * image a.k.a. discard. However we do not support discard if - * encryption is enabled, because it may give an attacker - * useful information. + * We use fallocate to manipulate the space mappings used by the image + * a.k.a. discard/zerorange. However we do not support this if + * encryption is enabled, because it may give an attacker useful + * information. */ struct file *file = lo->lo_backing_file; - int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE; int ret; + mode |= FALLOC_FL_KEEP_SIZE; + if ((!file->f_op->fallocate) || lo->lo_encrypt_key_size) { ret = -EOPNOTSUPP; goto out; @@ -596,9 +598,17 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq) switch (req_op(rq)) { case REQ_OP_FLUSH: return lo_req_flush(lo, rq); - case REQ_OP_DISCARD: case REQ_OP_WRITE_ZEROES: - return lo_discard(lo, rq, pos); + /* + * If the caller doesn't want deallocation, call zeroout to + * write zeroes the range. Otherwise, punch them out. + */ + return lo_fallocate(lo, rq, pos, + (rq->cmd_flags & REQ_NOUNMAP) ? + FALLOC_FL_ZERO_RANGE : + FALLOC_FL_PUNCH_HOLE); + case REQ_OP_DISCARD: + return lo_fallocate(lo, rq, pos, FALLOC_FL_PUNCH_HOLE); case REQ_OP_WRITE: if (lo->transfer) return lo_write_transfer(lo, rq, pos); diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 19e75999bb15..b4607dd96185 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1032,14 +1032,15 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg, sockfd_put(sock); return -ENOMEM; } + + config->socks = socks; + nsock = kzalloc(sizeof(struct nbd_sock), GFP_KERNEL); if (!nsock) { sockfd_put(sock); return -ENOMEM; } - config->socks = socks; - nsock->fallback_index = -1; nsock->dead = false; mutex_init(&nsock->tx_lock); @@ -1295,10 +1296,10 @@ static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *b mutex_unlock(&nbd->config_lock); ret = wait_event_interruptible(config->recv_wq, atomic_read(&config->recv_threads) == 0); - if (ret) { + if (ret) sock_shutdown(nbd); - flush_workqueue(nbd->recv_workq); - } + flush_workqueue(nbd->recv_workq); + mutex_lock(&nbd->config_lock); nbd_bdev_reset(bdev); /* user requested, ignore socket errors */ diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index fd1e19f1a49f..3666afa639d1 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -936,6 +936,8 @@ static int xen_blkbk_map(struct xen_blkif_ring *ring, out_of_memory: pr_alert("%s: out of memory\n", __func__); put_free_pages(ring, pages_to_gnt, segs_to_map); + for (i = last_map; i < num; i++) + pages[i]->handle = BLKBACK_INVALID_HANDLE; return -ENOMEM; } diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index b90dbcd99c03..c4cd68116e7f 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -171,6 +171,15 @@ static struct xen_blkif *xen_blkif_alloc(domid_t domid) blkif->domid = domid; atomic_set(&blkif->refcnt, 1); init_completion(&blkif->drain_complete); + + /* + * Because freeing back to the cache may be deferred, it is not + * safe to unload the module (and hence destroy the cache) until + * this has completed. To prevent premature unloading, take an + * extra module reference here and release only when the object + * has been freed back to the cache. + */ + __module_get(THIS_MODULE); INIT_WORK(&blkif->free_work, xen_blkif_deferred_free); return blkif; @@ -320,6 +329,7 @@ static void xen_blkif_free(struct xen_blkif *blkif) /* Make sure everything is drained before shutting down */ kmem_cache_free(xen_blkif_cachep, blkif); + module_put(THIS_MODULE); } int __init xen_blkif_interface_init(void) diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index a9c35ebb30f8..04cf767d0708 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -1200,7 +1200,7 @@ static int btusb_open(struct hci_dev *hdev) if (data->setup_on_usb) { err = data->setup_on_usb(hdev); if (err < 0) - return err; + goto setup_fail; } data->intf->needs_remote_wakeup = 1; @@ -1239,6 +1239,7 @@ static int btusb_open(struct hci_dev *hdev) failed: clear_bit(BTUSB_INTR_RUNNING, &data->flags); +setup_fail: usb_autopm_put_interface(data->intf); return err; } @@ -3807,8 +3808,8 @@ static int btusb_probe(struct usb_interface *intf, btusb_check_needs_reset_resume(intf); } -#ifdef CONFIG_BT_HCIBTUSB_RTL - if (id->driver_info & BTUSB_REALTEK) { + if (IS_ENABLED(CONFIG_BT_HCIBTUSB_RTL) && + (id->driver_info & BTUSB_REALTEK)) { hdev->setup = btrtl_setup_realtek; hdev->shutdown = btrtl_shutdown_realtek; hdev->cmd_timeout = btusb_rtl_cmd_timeout; @@ -3819,7 +3820,6 @@ static int btusb_probe(struct usb_interface *intf, */ set_bit(BTUSB_WAKEUP_DISABLE, &data->flags); } -#endif if (id->driver_info & BTUSB_AMP) { /* AMP controllers do not support SCO packets */ diff --git a/drivers/bluetooth/hci_bcsp.c b/drivers/bluetooth/hci_bcsp.c index fe2e307009f4..cf4a56095817 100644 --- a/drivers/bluetooth/hci_bcsp.c +++ b/drivers/bluetooth/hci_bcsp.c @@ -591,6 +591,7 @@ static int bcsp_recv(struct hci_uart *hu, const void *data, int count) if (*ptr == 0xc0) { BT_ERR("Short BCSP packet"); kfree_skb(bcsp->rx_skb); + bcsp->rx_skb = NULL; bcsp->rx_state = BCSP_W4_PKT_START; bcsp->rx_count = 0; } else @@ -606,6 +607,7 @@ static int bcsp_recv(struct hci_uart *hu, const void *data, int count) bcsp->rx_skb->data[2])) != bcsp->rx_skb->data[3]) { BT_ERR("Error in BCSP hdr checksum"); kfree_skb(bcsp->rx_skb); + bcsp->rx_skb = NULL; bcsp->rx_state = BCSP_W4_PKT_DELIMITER; bcsp->rx_count = 0; continue; @@ -630,6 +632,7 @@ static int bcsp_recv(struct hci_uart *hu, const void *data, int count) bscp_get_crc(bcsp)); kfree_skb(bcsp->rx_skb); + bcsp->rx_skb = NULL; bcsp->rx_state = BCSP_W4_PKT_DELIMITER; bcsp->rx_count = 0; continue; diff --git a/drivers/bluetooth/hci_ll.c b/drivers/bluetooth/hci_ll.c index 285706618f8a..d9a4c6c691e0 100644 --- a/drivers/bluetooth/hci_ll.c +++ b/drivers/bluetooth/hci_ll.c @@ -621,13 +621,6 @@ static int ll_setup(struct hci_uart *hu) serdev_device_set_flow_control(serdev, true); - if (hu->oper_speed) - speed = hu->oper_speed; - else if (hu->proto->oper_speed) - speed = hu->proto->oper_speed; - else - speed = 0; - do { /* Reset the Bluetooth device */ gpiod_set_value_cansleep(lldev->enable_gpio, 0); @@ -639,20 +632,6 @@ static int ll_setup(struct hci_uart *hu) return err; } - if (speed) { - __le32 speed_le = cpu_to_le32(speed); - struct sk_buff *skb; - - skb = __hci_cmd_sync(hu->hdev, - HCI_VS_UPDATE_UART_HCI_BAUDRATE, - sizeof(speed_le), &speed_le, - HCI_INIT_TIMEOUT); - if (!IS_ERR(skb)) { - kfree_skb(skb); - serdev_device_set_baudrate(serdev, speed); - } - } - err = download_firmware(lldev); if (!err) break; @@ -677,7 +656,25 @@ static int ll_setup(struct hci_uart *hu) } /* Operational speed if any */ + if (hu->oper_speed) + speed = hu->oper_speed; + else if (hu->proto->oper_speed) + speed = hu->proto->oper_speed; + else + speed = 0; + + if (speed) { + __le32 speed_le = cpu_to_le32(speed); + struct sk_buff *skb; + skb = __hci_cmd_sync(hu->hdev, HCI_VS_UPDATE_UART_HCI_BAUDRATE, + sizeof(speed_le), &speed_le, + HCI_INIT_TIMEOUT); + if (!IS_ERR(skb)) { + kfree_skb(skb); + serdev_device_set_baudrate(serdev, speed); + } + } return 0; } diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index 2b6670daf7fc..34bd9bf4e68a 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -1594,6 +1594,10 @@ static int sysc_reset(struct sysc *ddata) sysc_val |= sysc_mask; sysc_write(ddata, sysc_offset, sysc_val); + if (ddata->cfg.srst_udelay) + usleep_range(ddata->cfg.srst_udelay, + ddata->cfg.srst_udelay * 2); + if (ddata->clk_enable_quirk) ddata->clk_enable_quirk(ddata); diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index ac42ae4651ce..eebdcbef0578 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -996,6 +996,12 @@ static void cdrom_count_tracks(struct cdrom_device_info *cdi, tracktype *tracks) tracks->xa = 0; tracks->error = 0; cd_dbg(CD_COUNT_TRACKS, "entering cdrom_count_tracks\n"); + + if (!CDROM_CAN(CDC_PLAY_AUDIO)) { + tracks->error = CDS_NO_INFO; + return; + } + /* Grab the TOC header so we can see how many tracks there are */ ret = cdi->ops->audio_ioctl(cdi, CDROMREADTOCHDR, &header); if (ret) { @@ -1162,7 +1168,8 @@ int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev, ret = open_for_data(cdi); if (ret) goto err; - cdrom_mmc3_profile(cdi); + if (CDROM_CAN(CDC_GENERIC_PACKET)) + cdrom_mmc3_profile(cdi); if (mode & FMODE_WRITE) { ret = -EROFS; if (cdrom_open_write(cdi)) @@ -2882,6 +2889,9 @@ int cdrom_get_last_written(struct cdrom_device_info *cdi, long *last_written) it doesn't give enough information or fails. then we return the toc contents. */ use_toc: + if (!CDROM_CAN(CDC_PLAY_AUDIO)) + return -ENOSYS; + toc.cdte_format = CDROM_MSF; toc.cdte_track = CDROM_LEADOUT; if ((ret = cdi->ops->audio_ioctl(cdi, CDROMREADTOCENTRY, &toc))) diff --git a/drivers/char/hw_random/omap-rng.c b/drivers/char/hw_random/omap-rng.c index b27f39688b5e..e329f82c0467 100644 --- a/drivers/char/hw_random/omap-rng.c +++ b/drivers/char/hw_random/omap-rng.c @@ -66,6 +66,13 @@ #define OMAP4_RNG_OUTPUT_SIZE 0x8 #define EIP76_RNG_OUTPUT_SIZE 0x10 +/* + * EIP76 RNG takes approx. 700us to produce 16 bytes of output data + * as per testing results. And to account for the lack of udelay()'s + * reliability, we keep the timeout as 1000us. + */ +#define RNG_DATA_FILL_TIMEOUT 100 + enum { RNG_OUTPUT_0_REG = 0, RNG_OUTPUT_1_REG, @@ -176,7 +183,7 @@ static int omap_rng_do_read(struct hwrng *rng, void *data, size_t max, if (max < priv->pdata->data_size) return 0; - for (i = 0; i < 20; i++) { + for (i = 0; i < RNG_DATA_FILL_TIMEOUT; i++) { present = priv->pdata->data_present(priv); if (present || !wait) break; diff --git a/drivers/char/hw_random/omap3-rom-rng.c b/drivers/char/hw_random/omap3-rom-rng.c index 38b719017186..648e39ce6bd9 100644 --- a/drivers/char/hw_random/omap3-rom-rng.c +++ b/drivers/char/hw_random/omap3-rom-rng.c @@ -121,7 +121,8 @@ static int omap3_rom_rng_remove(struct platform_device *pdev) { cancel_delayed_work_sync(&idle_work); hwrng_unregister(&omap3_rom_rng_ops); - clk_disable_unprepare(rng_clk); + if (!rng_idle) + clk_disable_unprepare(rng_clk); return 0; } diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index 2aab80e19ae0..3c8a559506e8 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -448,6 +448,8 @@ enum ipmi_stat_indexes { #define IPMI_IPMB_NUM_SEQ 64 struct ipmi_smi { + struct module *owner; + /* What interface number are we? */ int intf_num; @@ -1220,6 +1222,11 @@ int ipmi_create_user(unsigned int if_num, if (rv) goto out_kfree; + if (!try_module_get(intf->owner)) { + rv = -ENODEV; + goto out_kfree; + } + /* Note that each existing user holds a refcount to the interface. */ kref_get(&intf->refcount); @@ -1349,6 +1356,7 @@ static void _ipmi_destroy_user(struct ipmi_user *user) } kref_put(&intf->refcount, intf_free); + module_put(intf->owner); } int ipmi_destroy_user(struct ipmi_user *user) @@ -2459,7 +2467,7 @@ static int __get_device_id(struct ipmi_smi *intf, struct bmc_device *bmc) * been recently fetched, this will just use the cached data. Otherwise * it will run a new fetch. * - * Except for the first time this is called (in ipmi_register_smi()), + * Except for the first time this is called (in ipmi_add_smi()), * this will always return good data; */ static int __bmc_get_device_id(struct ipmi_smi *intf, struct bmc_device *bmc, @@ -3377,10 +3385,11 @@ static void redo_bmc_reg(struct work_struct *work) kref_put(&intf->refcount, intf_free); } -int ipmi_register_smi(const struct ipmi_smi_handlers *handlers, - void *send_info, - struct device *si_dev, - unsigned char slave_addr) +int ipmi_add_smi(struct module *owner, + const struct ipmi_smi_handlers *handlers, + void *send_info, + struct device *si_dev, + unsigned char slave_addr) { int i, j; int rv; @@ -3406,7 +3415,7 @@ int ipmi_register_smi(const struct ipmi_smi_handlers *handlers, return rv; } - + intf->owner = owner; intf->bmc = &intf->tmp_bmc; INIT_LIST_HEAD(&intf->bmc->intfs); mutex_init(&intf->bmc->dyn_mutex); @@ -3514,7 +3523,7 @@ int ipmi_register_smi(const struct ipmi_smi_handlers *handlers, return rv; } -EXPORT_SYMBOL(ipmi_register_smi); +EXPORT_SYMBOL(ipmi_add_smi); static void deliver_smi_err_response(struct ipmi_smi *intf, struct ipmi_smi_msg *msg, diff --git a/drivers/char/lp.c b/drivers/char/lp.c index 7c9269e3477a..bd95aba1f9fe 100644 --- a/drivers/char/lp.c +++ b/drivers/char/lp.c @@ -713,6 +713,10 @@ static int lp_set_timeout64(unsigned int minor, void __user *arg) if (copy_from_user(karg, arg, sizeof(karg))) return -EFAULT; + /* sparc64 suseconds_t is 32-bit only */ + if (IS_ENABLED(CONFIG_SPARC64) && !in_compat_syscall()) + karg[1] >>= 32; + return lp_set_timeout(minor, karg[0], karg[1]); } diff --git a/drivers/char/ppdev.c b/drivers/char/ppdev.c index c86f18aa8985..34bb88fe0b0a 100644 --- a/drivers/char/ppdev.c +++ b/drivers/char/ppdev.c @@ -619,20 +619,27 @@ static int pp_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg) if (copy_from_user(time32, argp, sizeof(time32))) return -EFAULT; + if ((time32[0] < 0) || (time32[1] < 0)) + return -EINVAL; + return pp_set_timeout(pp->pdev, time32[0], time32[1]); case PPSETTIME64: if (copy_from_user(time64, argp, sizeof(time64))) return -EFAULT; + if ((time64[0] < 0) || (time64[1] < 0)) + return -EINVAL; + + if (IS_ENABLED(CONFIG_SPARC64) && !in_compat_syscall()) + time64[1] >>= 32; + return pp_set_timeout(pp->pdev, time64[0], time64[1]); case PPGETTIME32: jiffies_to_timespec64(pp->pdev->timeout, &ts); time32[0] = ts.tv_sec; time32[1] = ts.tv_nsec / NSEC_PER_USEC; - if ((time32[0] < 0) || (time32[1] < 0)) - return -EINVAL; if (copy_to_user(argp, time32, sizeof(time32))) return -EFAULT; @@ -643,8 +650,9 @@ static int pp_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg) jiffies_to_timespec64(pp->pdev->timeout, &ts); time64[0] = ts.tv_sec; time64[1] = ts.tv_nsec / NSEC_PER_USEC; - if ((time64[0] < 0) || (time64[1] < 0)) - return -EINVAL; + + if (IS_ENABLED(CONFIG_SPARC64) && !in_compat_syscall()) + time64[1] <<= 32; if (copy_to_user(argp, time64, sizeof(time64))) return -EFAULT; diff --git a/drivers/char/tpm/tpm-dev-common.c b/drivers/char/tpm/tpm-dev-common.c index 2ec47a69a2a6..87f449340202 100644 --- a/drivers/char/tpm/tpm-dev-common.c +++ b/drivers/char/tpm/tpm-dev-common.c @@ -61,6 +61,12 @@ static void tpm_dev_async_work(struct work_struct *work) mutex_lock(&priv->buffer_mutex); priv->command_enqueued = false; + ret = tpm_try_get_ops(priv->chip); + if (ret) { + priv->response_length = ret; + goto out; + } + ret = tpm_dev_transmit(priv->chip, priv->space, priv->data_buffer, sizeof(priv->data_buffer)); tpm_put_ops(priv->chip); @@ -68,6 +74,7 @@ static void tpm_dev_async_work(struct work_struct *work) priv->response_length = ret; mod_timer(&priv->user_read_timer, jiffies + (120 * HZ)); } +out: mutex_unlock(&priv->buffer_mutex); wake_up_interruptible(&priv->async_wait); } @@ -123,7 +130,7 @@ ssize_t tpm_common_read(struct file *file, char __user *buf, priv->response_read = true; ret_size = min_t(ssize_t, size, priv->response_length); - if (!ret_size) { + if (ret_size <= 0) { priv->response_length = 0; goto out; } @@ -204,6 +211,7 @@ ssize_t tpm_common_write(struct file *file, const char __user *buf, if (file->f_flags & O_NONBLOCK) { priv->command_enqueued = true; queue_work(tpm_dev_wq, &priv->async_work); + tpm_put_ops(priv->chip); mutex_unlock(&priv->buffer_mutex); return size; } diff --git a/drivers/char/tpm/tpm-dev.h b/drivers/char/tpm/tpm-dev.h index 1089fc0bb290..f3742bcc73e3 100644 --- a/drivers/char/tpm/tpm-dev.h +++ b/drivers/char/tpm/tpm-dev.h @@ -14,7 +14,7 @@ struct file_priv { struct work_struct timeout_work; struct work_struct async_work; wait_queue_head_t async_wait; - size_t response_length; + ssize_t response_length; bool response_read; bool command_enqueued; diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index ba9acae83bff..5817dfe5c5d2 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -939,6 +939,10 @@ static int tpm2_get_cc_attrs_tbl(struct tpm_chip *chip) chip->cc_attrs_tbl = devm_kcalloc(&chip->dev, 4, nr_commands, GFP_KERNEL); + if (!chip->cc_attrs_tbl) { + rc = -ENOMEM; + goto out; + } rc = tpm_buf_init(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_GET_CAPABILITY); if (rc) diff --git a/drivers/char/tpm/tpm_ftpm_tee.c b/drivers/char/tpm/tpm_ftpm_tee.c index 6640a14dbe48..22bf553ccf9d 100644 --- a/drivers/char/tpm/tpm_ftpm_tee.c +++ b/drivers/char/tpm/tpm_ftpm_tee.c @@ -32,7 +32,7 @@ static const uuid_t ftpm_ta_uuid = 0x82, 0xCB, 0x34, 0x3F, 0xB7, 0xF3, 0x78, 0x96); /** - * ftpm_tee_tpm_op_recv - retrieve fTPM response. + * ftpm_tee_tpm_op_recv() - retrieve fTPM response. * @chip: the tpm_chip description as specified in driver/char/tpm/tpm.h. * @buf: the buffer to store data. * @count: the number of bytes to read. @@ -61,7 +61,7 @@ static int ftpm_tee_tpm_op_recv(struct tpm_chip *chip, u8 *buf, size_t count) } /** - * ftpm_tee_tpm_op_send - send TPM commands through the TEE shared memory. + * ftpm_tee_tpm_op_send() - send TPM commands through the TEE shared memory. * @chip: the tpm_chip description as specified in driver/char/tpm/tpm.h * @buf: the buffer to send. * @len: the number of bytes to send. @@ -208,7 +208,7 @@ static int ftpm_tee_match(struct tee_ioctl_version_data *ver, const void *data) } /** - * ftpm_tee_probe - initialize the fTPM + * ftpm_tee_probe() - initialize the fTPM * @pdev: the platform_device description. * * Return: @@ -298,7 +298,7 @@ static int ftpm_tee_probe(struct platform_device *pdev) } /** - * ftpm_tee_remove - remove the TPM device + * ftpm_tee_remove() - remove the TPM device * @pdev: the platform_device description. * * Return: @@ -328,6 +328,19 @@ static int ftpm_tee_remove(struct platform_device *pdev) return 0; } +/** + * ftpm_tee_shutdown() - shutdown the TPM device + * @pdev: the platform_device description. + */ +static void ftpm_tee_shutdown(struct platform_device *pdev) +{ + struct ftpm_tee_private *pvt_data = dev_get_drvdata(&pdev->dev); + + tee_shm_free(pvt_data->shm); + tee_client_close_session(pvt_data->ctx, pvt_data->session); + tee_client_close_context(pvt_data->ctx); +} + static const struct of_device_id of_ftpm_tee_ids[] = { { .compatible = "microsoft,ftpm" }, { } @@ -341,6 +354,7 @@ static struct platform_driver ftpm_tee_driver = { }, .probe = ftpm_tee_probe, .remove = ftpm_tee_remove, + .shutdown = ftpm_tee_shutdown, }; module_platform_driver(ftpm_tee_driver); diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c index e4fdde93ed4c..e7df342a317d 100644 --- a/drivers/char/tpm/tpm_tis.c +++ b/drivers/char/tpm/tpm_tis.c @@ -286,7 +286,7 @@ static int tpm_tis_plat_probe(struct platform_device *pdev) } tpm_info.res = *res; - tpm_info.irq = platform_get_irq(pdev, 0); + tpm_info.irq = platform_get_irq_optional(pdev, 0); if (tpm_info.irq <= 0) { if (pdev != force_pdev) tpm_info.irq = -1; diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index 270f43acbb77..c3181ea9f271 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -980,8 +980,6 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq, goto out_err; } - tpm_chip_start(chip); - chip->flags |= TPM_CHIP_FLAG_IRQ; if (irq) { tpm_tis_probe_irq_single(chip, intmask, IRQF_SHARED, irq); @@ -991,7 +989,6 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq, } else { tpm_tis_probe_irq(chip, intmask); } - tpm_chip_stop(chip); } rc = tpm_chip_register(chip); diff --git a/drivers/clk/at91/at91sam9260.c b/drivers/clk/at91/at91sam9260.c index 0aabe49aed09..a9d4234758d7 100644 --- a/drivers/clk/at91/at91sam9260.c +++ b/drivers/clk/at91/at91sam9260.c @@ -348,7 +348,7 @@ static void __init at91sam926x_pmc_setup(struct device_node *np, return; mainxtal_name = of_clk_get_parent_name(np, i); - regmap = syscon_node_to_regmap(np); + regmap = device_node_to_regmap(np); if (IS_ERR(regmap)) return; diff --git a/drivers/clk/at91/at91sam9rl.c b/drivers/clk/at91/at91sam9rl.c index 0ac34cdaa106..77fe83a73bf4 100644 --- a/drivers/clk/at91/at91sam9rl.c +++ b/drivers/clk/at91/at91sam9rl.c @@ -83,7 +83,7 @@ static void __init at91sam9rl_pmc_setup(struct device_node *np) return; mainxtal_name = of_clk_get_parent_name(np, i); - regmap = syscon_node_to_regmap(np); + regmap = device_node_to_regmap(np); if (IS_ERR(regmap)) return; diff --git a/drivers/clk/at91/at91sam9x5.c b/drivers/clk/at91/at91sam9x5.c index 0855f3a80cc7..086cf0b4955c 100644 --- a/drivers/clk/at91/at91sam9x5.c +++ b/drivers/clk/at91/at91sam9x5.c @@ -146,7 +146,7 @@ static void __init at91sam9x5_pmc_setup(struct device_node *np, return; mainxtal_name = of_clk_get_parent_name(np, i); - regmap = syscon_node_to_regmap(np); + regmap = device_node_to_regmap(np); if (IS_ERR(regmap)) return; diff --git a/drivers/clk/at91/pmc.c b/drivers/clk/at91/pmc.c index 0b03cfae3a9d..b71515acdec1 100644 --- a/drivers/clk/at91/pmc.c +++ b/drivers/clk/at91/pmc.c @@ -275,7 +275,7 @@ static int __init pmc_register_ops(void) np = of_find_matching_node(NULL, sama5d2_pmc_dt_ids); - pmcreg = syscon_node_to_regmap(np); + pmcreg = device_node_to_regmap(np); if (IS_ERR(pmcreg)) return PTR_ERR(pmcreg); diff --git a/drivers/clk/at91/sama5d2.c b/drivers/clk/at91/sama5d2.c index 0de1108737db..ff7e3f727082 100644 --- a/drivers/clk/at91/sama5d2.c +++ b/drivers/clk/at91/sama5d2.c @@ -162,7 +162,7 @@ static void __init sama5d2_pmc_setup(struct device_node *np) return; mainxtal_name = of_clk_get_parent_name(np, i); - regmap = syscon_node_to_regmap(np); + regmap = device_node_to_regmap(np); if (IS_ERR(regmap)) return; diff --git a/drivers/clk/at91/sama5d4.c b/drivers/clk/at91/sama5d4.c index 25b156d4e645..a6dee4a3b6e4 100644 --- a/drivers/clk/at91/sama5d4.c +++ b/drivers/clk/at91/sama5d4.c @@ -136,7 +136,7 @@ static void __init sama5d4_pmc_setup(struct device_node *np) return; mainxtal_name = of_clk_get_parent_name(np, i); - regmap = syscon_node_to_regmap(np); + regmap = device_node_to_regmap(np); if (IS_ERR(regmap)) return; diff --git a/drivers/clk/clk-gpio.c b/drivers/clk/clk-gpio.c index 9d930edd6516..13304cf5f2a8 100644 --- a/drivers/clk/clk-gpio.c +++ b/drivers/clk/clk-gpio.c @@ -280,7 +280,7 @@ static int gpio_clk_driver_probe(struct platform_device *pdev) else clk = clk_register_gpio_gate(&pdev->dev, node->name, parent_names ? parent_names[0] : NULL, gpiod, - 0); + CLK_SET_RATE_PARENT); if (IS_ERR(clk)) return PTR_ERR(clk); diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 1c677d7f7f53..4fc294c2f9e8 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -3231,6 +3231,34 @@ static inline void clk_debug_unregister(struct clk_core *core) } #endif +static void clk_core_reparent_orphans_nolock(void) +{ + struct clk_core *orphan; + struct hlist_node *tmp2; + + /* + * walk the list of orphan clocks and reparent any that newly finds a + * parent. + */ + hlist_for_each_entry_safe(orphan, tmp2, &clk_orphan_list, child_node) { + struct clk_core *parent = __clk_init_parent(orphan); + + /* + * We need to use __clk_set_parent_before() and _after() to + * to properly migrate any prepare/enable count of the orphan + * clock. This is important for CLK_IS_CRITICAL clocks, which + * are enabled during init but might not have a parent yet. + */ + if (parent) { + /* update the clk tree topology */ + __clk_set_parent_before(orphan, parent); + __clk_set_parent_after(orphan, parent, NULL); + __clk_recalc_accuracies(orphan); + __clk_recalc_rates(orphan, 0); + } + } +} + /** * __clk_core_init - initialize the data structures in a struct clk_core * @core: clk_core being initialized @@ -3241,8 +3269,6 @@ static inline void clk_debug_unregister(struct clk_core *core) static int __clk_core_init(struct clk_core *core) { int ret; - struct clk_core *orphan; - struct hlist_node *tmp2; unsigned long rate; if (!core) @@ -3389,27 +3415,8 @@ static int __clk_core_init(struct clk_core *core) clk_enable_unlock(flags); } - /* - * walk the list of orphan clocks and reparent any that newly finds a - * parent. - */ - hlist_for_each_entry_safe(orphan, tmp2, &clk_orphan_list, child_node) { - struct clk_core *parent = __clk_init_parent(orphan); + clk_core_reparent_orphans_nolock(); - /* - * We need to use __clk_set_parent_before() and _after() to - * to properly migrate any prepare/enable count of the orphan - * clock. This is important for CLK_IS_CRITICAL clocks, which - * are enabled during init but might not have a parent yet. - */ - if (parent) { - /* update the clk tree topology */ - __clk_set_parent_before(orphan, parent); - __clk_set_parent_after(orphan, parent, NULL); - __clk_recalc_accuracies(orphan); - __clk_recalc_rates(orphan, 0); - } - } kref_init(&core->ref); out: @@ -3879,6 +3886,7 @@ void clk_unregister(struct clk *clk) __func__, clk->core->name); kref_put(&clk->core->ref, __clk_release); + free_clk(clk); unlock: clk_prepare_unlock(); } @@ -4160,6 +4168,13 @@ int clk_notifier_unregister(struct clk *clk, struct notifier_block *nb) EXPORT_SYMBOL_GPL(clk_notifier_unregister); #ifdef CONFIG_OF +static void clk_core_reparent_orphans(void) +{ + clk_prepare_lock(); + clk_core_reparent_orphans_nolock(); + clk_prepare_unlock(); +} + /** * struct of_clk_provider - Clock provider registration structure * @link: Entry in global list of clock providers @@ -4255,6 +4270,8 @@ int of_clk_add_provider(struct device_node *np, mutex_unlock(&of_clk_mutex); pr_debug("Added clock from %pOF\n", np); + clk_core_reparent_orphans(); + ret = of_clk_set_defaults(np, true); if (ret < 0) of_clk_del_provider(np); @@ -4290,6 +4307,8 @@ int of_clk_add_hw_provider(struct device_node *np, mutex_unlock(&of_clk_mutex); pr_debug("Added clk_hw provider from %pOF\n", np); + clk_core_reparent_orphans(); + ret = of_clk_set_defaults(np, true); if (ret < 0) of_clk_del_provider(np); diff --git a/drivers/clk/imx/clk-composite-8m.c b/drivers/clk/imx/clk-composite-8m.c index 388bdb94f841..d3486ee79ab5 100644 --- a/drivers/clk/imx/clk-composite-8m.c +++ b/drivers/clk/imx/clk-composite-8m.c @@ -142,6 +142,7 @@ struct clk *imx8m_clk_composite_flags(const char *name, mux->reg = reg; mux->shift = PCG_PCS_SHIFT; mux->mask = PCG_PCS_MASK; + mux->lock = &imx_ccm_lock; div = kzalloc(sizeof(*div), GFP_KERNEL); if (!div) @@ -161,6 +162,7 @@ struct clk *imx8m_clk_composite_flags(const char *name, gate_hw = &gate->hw; gate->reg = reg; gate->bit_idx = PCG_CGC_SHIFT; + gate->lock = &imx_ccm_lock; hw = clk_hw_register_composite(NULL, name, parent_names, num_parents, mux_hw, &clk_mux_ops, div_hw, diff --git a/drivers/clk/imx/clk-imx7ulp.c b/drivers/clk/imx/clk-imx7ulp.c index 2022d9bead91..a0f650150367 100644 --- a/drivers/clk/imx/clk-imx7ulp.c +++ b/drivers/clk/imx/clk-imx7ulp.c @@ -40,6 +40,7 @@ static const struct clk_div_table ulp_div_table[] = { { .val = 5, .div = 16, }, { .val = 6, .div = 32, }, { .val = 7, .div = 64, }, + { /* sentinel */ }, }; static const int pcc2_uart_clk_ids[] __initconst = { diff --git a/drivers/clk/imx/clk-pll14xx.c b/drivers/clk/imx/clk-pll14xx.c index 7a815ec76aa5..047f1d8fe323 100644 --- a/drivers/clk/imx/clk-pll14xx.c +++ b/drivers/clk/imx/clk-pll14xx.c @@ -112,48 +112,22 @@ static unsigned long clk_pll1443x_recalc_rate(struct clk_hw *hw, return fvco; } -static inline bool clk_pll1416x_mp_change(const struct imx_pll14xx_rate_table *rate, +static inline bool clk_pll14xx_mp_change(const struct imx_pll14xx_rate_table *rate, u32 pll_div) { u32 old_mdiv, old_pdiv; - old_mdiv = (pll_div >> MDIV_SHIFT) & MDIV_MASK; - old_pdiv = (pll_div >> PDIV_SHIFT) & PDIV_MASK; + old_mdiv = (pll_div & MDIV_MASK) >> MDIV_SHIFT; + old_pdiv = (pll_div & PDIV_MASK) >> PDIV_SHIFT; return rate->mdiv != old_mdiv || rate->pdiv != old_pdiv; } -static inline bool clk_pll1443x_mpk_change(const struct imx_pll14xx_rate_table *rate, - u32 pll_div_ctl0, u32 pll_div_ctl1) -{ - u32 old_mdiv, old_pdiv, old_kdiv; - - old_mdiv = (pll_div_ctl0 >> MDIV_SHIFT) & MDIV_MASK; - old_pdiv = (pll_div_ctl0 >> PDIV_SHIFT) & PDIV_MASK; - old_kdiv = (pll_div_ctl1 >> KDIV_SHIFT) & KDIV_MASK; - - return rate->mdiv != old_mdiv || rate->pdiv != old_pdiv || - rate->kdiv != old_kdiv; -} - -static inline bool clk_pll1443x_mp_change(const struct imx_pll14xx_rate_table *rate, - u32 pll_div_ctl0, u32 pll_div_ctl1) -{ - u32 old_mdiv, old_pdiv, old_kdiv; - - old_mdiv = (pll_div_ctl0 >> MDIV_SHIFT) & MDIV_MASK; - old_pdiv = (pll_div_ctl0 >> PDIV_SHIFT) & PDIV_MASK; - old_kdiv = (pll_div_ctl1 >> KDIV_SHIFT) & KDIV_MASK; - - return rate->mdiv != old_mdiv || rate->pdiv != old_pdiv || - rate->kdiv != old_kdiv; -} - static int clk_pll14xx_wait_lock(struct clk_pll14xx *pll) { u32 val; - return readl_poll_timeout(pll->base, val, val & LOCK_TIMEOUT_US, 0, + return readl_poll_timeout(pll->base, val, val & LOCK_STATUS, 0, LOCK_TIMEOUT_US); } @@ -174,7 +148,7 @@ static int clk_pll1416x_set_rate(struct clk_hw *hw, unsigned long drate, tmp = readl_relaxed(pll->base + 4); - if (!clk_pll1416x_mp_change(rate, tmp)) { + if (!clk_pll14xx_mp_change(rate, tmp)) { tmp &= ~(SDIV_MASK) << SDIV_SHIFT; tmp |= rate->sdiv << SDIV_SHIFT; writel_relaxed(tmp, pll->base + 4); @@ -239,13 +213,15 @@ static int clk_pll1443x_set_rate(struct clk_hw *hw, unsigned long drate, } tmp = readl_relaxed(pll->base + 4); - div_val = readl_relaxed(pll->base + 8); - if (!clk_pll1443x_mpk_change(rate, tmp, div_val)) { + if (!clk_pll14xx_mp_change(rate, tmp)) { tmp &= ~(SDIV_MASK) << SDIV_SHIFT; tmp |= rate->sdiv << SDIV_SHIFT; writel_relaxed(tmp, pll->base + 4); + tmp = rate->kdiv << KDIV_SHIFT; + writel_relaxed(tmp, pll->base + 8); + return 0; } diff --git a/drivers/clk/meson/axg-audio.c b/drivers/clk/meson/axg-audio.c index 18b23cdf679c..aa2522624fd3 100644 --- a/drivers/clk/meson/axg-audio.c +++ b/drivers/clk/meson/axg-audio.c @@ -1001,7 +1001,7 @@ static const struct regmap_config axg_audio_regmap_cfg = { .reg_bits = 32, .val_bits = 32, .reg_stride = 4, - .max_register = AUDIO_CLK_PDMIN_CTRL1, + .max_register = AUDIO_CLK_SPDIFOUT_B_CTRL, }; struct audioclk_data { diff --git a/drivers/clk/pxa/clk-pxa27x.c b/drivers/clk/pxa/clk-pxa27x.c index 287fdeae7c7c..7b123105b5de 100644 --- a/drivers/clk/pxa/clk-pxa27x.c +++ b/drivers/clk/pxa/clk-pxa27x.c @@ -459,6 +459,7 @@ struct dummy_clk { }; static struct dummy_clk dummy_clks[] __initdata = { DUMMY_CLK(NULL, "pxa27x-gpio", "osc_32_768khz"), + DUMMY_CLK(NULL, "pxa-rtc", "osc_32_768khz"), DUMMY_CLK(NULL, "sa1100-rtc", "osc_32_768khz"), DUMMY_CLK("UARTCLK", "pxa2xx-ir", "STUART"), }; diff --git a/drivers/clk/qcom/clk-rcg2.c b/drivers/clk/qcom/clk-rcg2.c index b98b81ef43a1..5a89ed88cc27 100644 --- a/drivers/clk/qcom/clk-rcg2.c +++ b/drivers/clk/qcom/clk-rcg2.c @@ -220,6 +220,8 @@ static int _freq_tbl_determine_rate(struct clk_hw *hw, const struct freq_tbl *f, if (clk_flags & CLK_SET_RATE_PARENT) { rate = f->freq; if (f->pre_div) { + if (!rate) + rate = req->rate; rate /= 2; rate *= f->pre_div + 1; } diff --git a/drivers/clk/qcom/clk-smd-rpm.c b/drivers/clk/qcom/clk-smd-rpm.c index fef5e8157061..930fa4a4c52a 100644 --- a/drivers/clk/qcom/clk-smd-rpm.c +++ b/drivers/clk/qcom/clk-smd-rpm.c @@ -648,6 +648,7 @@ static const struct rpm_smd_clk_desc rpm_clk_qcs404 = { }; /* msm8998 */ +DEFINE_CLK_SMD_RPM(msm8998, pcnoc_clk, pcnoc_a_clk, QCOM_SMD_RPM_BUS_CLK, 0); DEFINE_CLK_SMD_RPM(msm8998, snoc_clk, snoc_a_clk, QCOM_SMD_RPM_BUS_CLK, 1); DEFINE_CLK_SMD_RPM(msm8998, cnoc_clk, cnoc_a_clk, QCOM_SMD_RPM_BUS_CLK, 2); DEFINE_CLK_SMD_RPM(msm8998, ce1_clk, ce1_a_clk, QCOM_SMD_RPM_CE_CLK, 0); @@ -670,6 +671,8 @@ DEFINE_CLK_SMD_RPM_XO_BUFFER_PINCTRL(msm8998, rf_clk2_pin, rf_clk2_a_pin, 5); DEFINE_CLK_SMD_RPM_XO_BUFFER(msm8998, rf_clk3, rf_clk3_a, 6); DEFINE_CLK_SMD_RPM_XO_BUFFER_PINCTRL(msm8998, rf_clk3_pin, rf_clk3_a_pin, 6); static struct clk_smd_rpm *msm8998_clks[] = { + [RPM_SMD_PCNOC_CLK] = &msm8998_pcnoc_clk, + [RPM_SMD_PCNOC_A_CLK] = &msm8998_pcnoc_a_clk, [RPM_SMD_SNOC_CLK] = &msm8998_snoc_clk, [RPM_SMD_SNOC_A_CLK] = &msm8998_snoc_a_clk, [RPM_SMD_CNOC_CLK] = &msm8998_cnoc_clk, diff --git a/drivers/clk/qcom/common.c b/drivers/clk/qcom/common.c index 28ddc747d703..bdeacebbf0e4 100644 --- a/drivers/clk/qcom/common.c +++ b/drivers/clk/qcom/common.c @@ -29,6 +29,9 @@ struct freq_tbl *qcom_find_freq(const struct freq_tbl *f, unsigned long rate) if (!f) return NULL; + if (!f->freq) + return f; + for (; f->freq; f++) if (rate <= f->freq) return f; diff --git a/drivers/clk/samsung/clk-exynos5420.c b/drivers/clk/samsung/clk-exynos5420.c index 31466cd1842f..3b7601647d7b 100644 --- a/drivers/clk/samsung/clk-exynos5420.c +++ b/drivers/clk/samsung/clk-exynos5420.c @@ -165,6 +165,8 @@ static const unsigned long exynos5x_clk_regs[] __initconst = { GATE_BUS_CPU, GATE_SCLK_CPU, CLKOUT_CMU_CPU, + APLL_CON0, + KPLL_CON0, CPLL_CON0, DPLL_CON0, EPLL_CON0, diff --git a/drivers/clocksource/asm9260_timer.c b/drivers/clocksource/asm9260_timer.c index 9f09a59161e7..5b39d3701fa3 100644 --- a/drivers/clocksource/asm9260_timer.c +++ b/drivers/clocksource/asm9260_timer.c @@ -194,6 +194,10 @@ static int __init asm9260_timer_init(struct device_node *np) } clk = of_clk_get(np, 0); + if (IS_ERR(clk)) { + pr_err("Failed to get clk!\n"); + return PTR_ERR(clk); + } ret = clk_prepare_enable(clk); if (ret) { diff --git a/drivers/clocksource/timer-of.c b/drivers/clocksource/timer-of.c index 11ff701ff4bb..a3c73e972fce 100644 --- a/drivers/clocksource/timer-of.c +++ b/drivers/clocksource/timer-of.c @@ -192,7 +192,7 @@ int __init timer_of_init(struct device_node *np, struct timer_of *to) } if (!to->clkevt.name) - to->clkevt.name = np->name; + to->clkevt.name = np->full_name; to->np = np; diff --git a/drivers/clocksource/timer-riscv.c b/drivers/clocksource/timer-riscv.c index 470c7ef02ea4..4b04ffbe5e7e 100644 --- a/drivers/clocksource/timer-riscv.c +++ b/drivers/clocksource/timer-riscv.c @@ -41,7 +41,7 @@ static unsigned long long riscv_clocksource_rdtime(struct clocksource *cs) return get_cycles64(); } -static u64 riscv_sched_clock(void) +static u64 notrace riscv_sched_clock(void) { return get_cycles64(); } diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 48a224a6b178..a7db4f22a077 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -933,6 +933,9 @@ static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf) struct freq_attr *fattr = to_attr(attr); ssize_t ret; + if (!fattr->show) + return -EIO; + down_read(&policy->rwsem); ret = fattr->show(policy, buf); up_read(&policy->rwsem); @@ -947,6 +950,9 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr, struct freq_attr *fattr = to_attr(attr); ssize_t ret = -EINVAL; + if (!fattr->store) + return -EIO; + /* * cpus_read_trylock() is used here to work around a circular lock * dependency problem with respect to the cpufreq_register_driver(). @@ -2628,6 +2634,13 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) if (cpufreq_disabled()) return -ENODEV; + /* + * The cpufreq core depends heavily on the availability of device + * structure, make sure they are available before proceeding further. + */ + if (!get_cpu_device(0)) + return -EPROBE_DEFER; + if (!driver_data || !driver_data->verify || !driver_data->init || !(driver_data->setpolicy || driver_data->target_index || driver_data->target) || diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c index b66e81c06a57..a294f8f5fd75 100644 --- a/drivers/cpufreq/cpufreq_conservative.c +++ b/drivers/cpufreq/cpufreq_conservative.c @@ -28,8 +28,8 @@ struct cs_dbs_tuners { }; /* Conservative governor macros */ -#define DEF_FREQUENCY_UP_THRESHOLD (80) -#define DEF_FREQUENCY_DOWN_THRESHOLD (20) +#define DEF_FREQUENCY_UP_THRESHOLD (63) +#define DEF_FREQUENCY_DOWN_THRESHOLD (26) #define DEF_FREQUENCY_STEP (5) #define DEF_SAMPLING_DOWN_FACTOR (1) #define MAX_SAMPLING_DOWN_FACTOR (10) diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c index dced033875bf..d2cd03766b09 100644 --- a/drivers/cpufreq/cpufreq_ondemand.c +++ b/drivers/cpufreq/cpufreq_ondemand.c @@ -18,7 +18,7 @@ #include "cpufreq_ondemand.h" /* On-demand governor macros */ -#define DEF_FREQUENCY_UP_THRESHOLD (80) +#define DEF_FREQUENCY_UP_THRESHOLD (63) #define DEF_SAMPLING_DOWN_FACTOR (1) #define MAX_SAMPLING_DOWN_FACTOR (100000) #define MICRO_FREQUENCY_UP_THRESHOLD (95) @@ -127,7 +127,7 @@ static void dbs_freq_increase(struct cpufreq_policy *policy, unsigned int freq) } /* - * Every sampling_rate, we check, if current idle time is less than 20% + * Every sampling_rate, we check, if current idle time is less than 37% * (default), then we try to increase frequency. Else, we adjust the frequency * proportional to load. */ diff --git a/drivers/cpufreq/imx-cpufreq-dt.c b/drivers/cpufreq/imx-cpufreq-dt.c index 35db14cf3102..85a6efd6b68f 100644 --- a/drivers/cpufreq/imx-cpufreq-dt.c +++ b/drivers/cpufreq/imx-cpufreq-dt.c @@ -44,19 +44,19 @@ static int imx_cpufreq_dt_probe(struct platform_device *pdev) mkt_segment = (cell_value & OCOTP_CFG3_MKT_SEGMENT_MASK) >> OCOTP_CFG3_MKT_SEGMENT_SHIFT; /* - * Early samples without fuses written report "0 0" which means - * consumer segment and minimum speed grading. - * - * According to datasheet minimum speed grading is not supported for - * consumer parts so clamp to 1 to avoid warning for "no OPPs" + * Early samples without fuses written report "0 0" which may NOT + * match any OPP defined in DT. So clamp to minimum OPP defined in + * DT to avoid warning for "no OPPs". * * Applies to i.MX8M series SoCs. */ - if (mkt_segment == 0 && speed_grade == 0 && ( - of_machine_is_compatible("fsl,imx8mm") || - of_machine_is_compatible("fsl,imx8mn") || - of_machine_is_compatible("fsl,imx8mq"))) - speed_grade = 1; + if (mkt_segment == 0 && speed_grade == 0) { + if (of_machine_is_compatible("fsl,imx8mm") || + of_machine_is_compatible("fsl,imx8mq")) + speed_grade = 1; + if (of_machine_is_compatible("fsl,imx8mn")) + speed_grade = 0xb; + } supported_hw[0] = BIT(speed_grade); supported_hw[1] = BIT(mkt_segment); diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c index 6061850e59c9..56f4bc0d209e 100644 --- a/drivers/cpufreq/powernv-cpufreq.c +++ b/drivers/cpufreq/powernv-cpufreq.c @@ -1041,9 +1041,14 @@ static struct cpufreq_driver powernv_cpufreq_driver = { static int init_chip_info(void) { - unsigned int chip[256]; + unsigned int *chip; unsigned int cpu, i; unsigned int prev_chip_id = UINT_MAX; + int ret = 0; + + chip = kcalloc(num_possible_cpus(), sizeof(*chip), GFP_KERNEL); + if (!chip) + return -ENOMEM; for_each_possible_cpu(cpu) { unsigned int id = cpu_to_chip_id(cpu); @@ -1055,8 +1060,10 @@ static int init_chip_info(void) } chips = kcalloc(nr_chips, sizeof(struct chip), GFP_KERNEL); - if (!chips) - return -ENOMEM; + if (!chips) { + ret = -ENOMEM; + goto free_and_return; + } for (i = 0; i < nr_chips; i++) { chips[i].id = chip[i]; @@ -1066,7 +1073,9 @@ static int init_chip_info(void) per_cpu(chip_info, cpu) = &chips[i]; } - return 0; +free_and_return: + kfree(chip); + return ret; } static inline void clean_chip_info(void) diff --git a/drivers/cpufreq/sun50i-cpufreq-nvmem.c b/drivers/cpufreq/sun50i-cpufreq-nvmem.c index eca32e443716..9907a165135b 100644 --- a/drivers/cpufreq/sun50i-cpufreq-nvmem.c +++ b/drivers/cpufreq/sun50i-cpufreq-nvmem.c @@ -25,7 +25,7 @@ static struct platform_device *cpufreq_dt_pdev, *sun50i_cpufreq_pdev; /** - * sun50i_cpufreq_get_efuse() - Parse and return efuse value present on SoC + * sun50i_cpufreq_get_efuse() - Determine speed grade from efuse value * @versions: Set to the value parsed from efuse * * Returns 0 if success. @@ -69,21 +69,16 @@ static int sun50i_cpufreq_get_efuse(u32 *versions) return PTR_ERR(speedbin); efuse_value = (*speedbin >> NVMEM_SHIFT) & NVMEM_MASK; - switch (efuse_value) { - case 0b0001: - *versions = 1; - break; - case 0b0011: - *versions = 2; - break; - default: - /* - * For other situations, we treat it as bin0. - * This vf table can be run for any good cpu. - */ + + /* + * We treat unexpected efuse values as if the SoC was from + * the slowest bin. Expected efuse values are 1-3, slowest + * to fastest. + */ + if (efuse_value >= 1 && efuse_value <= 3) + *versions = efuse_value - 1; + else *versions = 0; - break; - } kfree(speedbin); return 0; diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 0895b988fa92..29d2d7a21bd7 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -384,6 +384,7 @@ u64 cpuidle_poll_time(struct cpuidle_driver *drv, continue; limit_ns = (u64)drv->states[i].target_residency * NSEC_PER_USEC; + break; } dev->poll_limit_ns = limit_ns; diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c index 80c1a830d991..9db154224999 100644 --- a/drivers/cpuidle/driver.c +++ b/drivers/cpuidle/driver.c @@ -62,24 +62,23 @@ static inline void __cpuidle_unset_driver(struct cpuidle_driver *drv) * __cpuidle_set_driver - set per CPU driver variables for the given driver. * @drv: a valid pointer to a struct cpuidle_driver * - * For each CPU in the driver's cpumask, unset the registered driver per CPU - * to @drv. - * - * Returns 0 on success, -EBUSY if the CPUs have driver(s) already. + * Returns 0 on success, -EBUSY if any CPU in the cpumask have a driver + * different from drv already. */ static inline int __cpuidle_set_driver(struct cpuidle_driver *drv) { int cpu; for_each_cpu(cpu, drv->cpumask) { + struct cpuidle_driver *old_drv; - if (__cpuidle_get_cpu_driver(cpu)) { - __cpuidle_unset_driver(drv); + old_drv = __cpuidle_get_cpu_driver(cpu); + if (old_drv && old_drv != drv) return -EBUSY; - } + } + for_each_cpu(cpu, drv->cpumask) per_cpu(cpuidle_drivers, cpu) = drv; - } return 0; } diff --git a/drivers/cpuidle/governors/teo.c b/drivers/cpuidle/governors/teo.c index b5a0e498f798..b9b9156618e6 100644 --- a/drivers/cpuidle/governors/teo.c +++ b/drivers/cpuidle/governors/teo.c @@ -233,7 +233,7 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, { struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu); int latency_req = cpuidle_governor_latency_req(dev->cpu); - unsigned int duration_us, count; + unsigned int duration_us, hits, misses, early_hits; int max_early_idx, constraint_idx, idx, i; ktime_t delta_tick; @@ -247,7 +247,9 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, cpu_data->sleep_length_ns = tick_nohz_get_sleep_length(&delta_tick); duration_us = ktime_to_us(cpu_data->sleep_length_ns); - count = 0; + hits = 0; + misses = 0; + early_hits = 0; max_early_idx = -1; constraint_idx = drv->state_count; idx = -1; @@ -258,23 +260,61 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, if (s->disabled || su->disable) { /* - * If the "early hits" metric of a disabled state is - * greater than the current maximum, it should be taken - * into account, because it would be a mistake to select - * a deeper state with lower "early hits" metric. The - * index cannot be changed to point to it, however, so - * just increase the max count alone and let the index - * still point to a shallower idle state. + * Ignore disabled states with target residencies beyond + * the anticipated idle duration. */ - if (max_early_idx >= 0 && - count < cpu_data->states[i].early_hits) - count = cpu_data->states[i].early_hits; + if (s->target_residency > duration_us) + continue; + + /* + * This state is disabled, so the range of idle duration + * values corresponding to it is covered by the current + * candidate state, but still the "hits" and "misses" + * metrics of the disabled state need to be used to + * decide whether or not the state covering the range in + * question is good enough. + */ + hits = cpu_data->states[i].hits; + misses = cpu_data->states[i].misses; + + if (early_hits >= cpu_data->states[i].early_hits || + idx < 0) + continue; + + /* + * If the current candidate state has been the one with + * the maximum "early hits" metric so far, the "early + * hits" metric of the disabled state replaces the + * current "early hits" count to avoid selecting a + * deeper state with lower "early hits" metric. + */ + if (max_early_idx == idx) { + early_hits = cpu_data->states[i].early_hits; + continue; + } + + /* + * The current candidate state is closer to the disabled + * one than the current maximum "early hits" state, so + * replace the latter with it, but in case the maximum + * "early hits" state index has not been set so far, + * check if the current candidate state is not too + * shallow for that role. + */ + if (!(tick_nohz_tick_stopped() && + drv->states[idx].target_residency < TICK_USEC)) { + early_hits = cpu_data->states[i].early_hits; + max_early_idx = idx; + } continue; } - if (idx < 0) + if (idx < 0) { idx = i; /* first enabled state */ + hits = cpu_data->states[i].hits; + misses = cpu_data->states[i].misses; + } if (s->target_residency > duration_us) break; @@ -283,11 +323,13 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, constraint_idx = i; idx = i; + hits = cpu_data->states[i].hits; + misses = cpu_data->states[i].misses; - if (count < cpu_data->states[i].early_hits && + if (early_hits < cpu_data->states[i].early_hits && !(tick_nohz_tick_stopped() && drv->states[i].target_residency < TICK_USEC)) { - count = cpu_data->states[i].early_hits; + early_hits = cpu_data->states[i].early_hits; max_early_idx = i; } } @@ -300,8 +342,7 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, * "early hits" metric, but if that cannot be determined, just use the * state selected so far. */ - if (cpu_data->states[idx].hits <= cpu_data->states[idx].misses && - max_early_idx >= 0) { + if (hits <= misses && max_early_idx >= 0) { idx = max_early_idx; duration_us = drv->states[idx].target_residency; } @@ -316,10 +357,9 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, if (idx < 0) { idx = 0; /* No states enabled. Must use 0. */ } else if (idx > 0) { + unsigned int count = 0; u64 sum = 0; - count = 0; - /* * Count and sum the most recent idle duration values less than * the current expected idle duration value. diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig index 1fb622f2a87d..8eabf7b20101 100644 --- a/drivers/crypto/Kconfig +++ b/drivers/crypto/Kconfig @@ -287,6 +287,7 @@ config CRYPTO_DEV_TALITOS select CRYPTO_AUTHENC select CRYPTO_BLKCIPHER select CRYPTO_HASH + select CRYPTO_LIB_DES select HW_RANDOM depends on FSL_SOC help diff --git a/drivers/crypto/amcc/crypto4xx_core.c b/drivers/crypto/amcc/crypto4xx_core.c index de5e9352e920..7d6b695c4ab3 100644 --- a/drivers/crypto/amcc/crypto4xx_core.c +++ b/drivers/crypto/amcc/crypto4xx_core.c @@ -365,12 +365,8 @@ static u32 crypto4xx_build_sdr(struct crypto4xx_device *dev) dma_alloc_coherent(dev->core_dev->device, PPC4XX_SD_BUFFER_SIZE * PPC4XX_NUM_SD, &dev->scatter_buffer_pa, GFP_ATOMIC); - if (!dev->scatter_buffer_va) { - dma_free_coherent(dev->core_dev->device, - sizeof(struct ce_sd) * PPC4XX_NUM_SD, - dev->sdr, dev->sdr_pa); + if (!dev->scatter_buffer_va) return -ENOMEM; - } for (i = 0; i < PPC4XX_NUM_SD; i++) { dev->sdr[i].ptr = dev->scatter_buffer_pa + diff --git a/drivers/crypto/atmel-aes.c b/drivers/crypto/atmel-aes.c index 026f193556f9..db99cee1991c 100644 --- a/drivers/crypto/atmel-aes.c +++ b/drivers/crypto/atmel-aes.c @@ -145,7 +145,7 @@ struct atmel_aes_xts_ctx { u32 key2[AES_KEYSIZE_256 / sizeof(u32)]; }; -#ifdef CONFIG_CRYPTO_DEV_ATMEL_AUTHENC +#if IS_ENABLED(CONFIG_CRYPTO_DEV_ATMEL_AUTHENC) struct atmel_aes_authenc_ctx { struct atmel_aes_base_ctx base; struct atmel_sha_authenc_ctx *auth; @@ -157,7 +157,7 @@ struct atmel_aes_reqctx { u32 lastc[AES_BLOCK_SIZE / sizeof(u32)]; }; -#ifdef CONFIG_CRYPTO_DEV_ATMEL_AUTHENC +#if IS_ENABLED(CONFIG_CRYPTO_DEV_ATMEL_AUTHENC) struct atmel_aes_authenc_reqctx { struct atmel_aes_reqctx base; @@ -486,13 +486,36 @@ static inline bool atmel_aes_is_encrypt(const struct atmel_aes_dev *dd) return (dd->flags & AES_FLAGS_ENCRYPT); } -#ifdef CONFIG_CRYPTO_DEV_ATMEL_AUTHENC +#if IS_ENABLED(CONFIG_CRYPTO_DEV_ATMEL_AUTHENC) static void atmel_aes_authenc_complete(struct atmel_aes_dev *dd, int err); #endif +static void atmel_aes_set_iv_as_last_ciphertext_block(struct atmel_aes_dev *dd) +{ + struct ablkcipher_request *req = ablkcipher_request_cast(dd->areq); + struct atmel_aes_reqctx *rctx = ablkcipher_request_ctx(req); + struct crypto_ablkcipher *ablkcipher = crypto_ablkcipher_reqtfm(req); + unsigned int ivsize = crypto_ablkcipher_ivsize(ablkcipher); + + if (req->nbytes < ivsize) + return; + + if (rctx->mode & AES_FLAGS_ENCRYPT) { + scatterwalk_map_and_copy(req->info, req->dst, + req->nbytes - ivsize, ivsize, 0); + } else { + if (req->src == req->dst) + memcpy(req->info, rctx->lastc, ivsize); + else + scatterwalk_map_and_copy(req->info, req->src, + req->nbytes - ivsize, + ivsize, 0); + } +} + static inline int atmel_aes_complete(struct atmel_aes_dev *dd, int err) { -#ifdef CONFIG_CRYPTO_DEV_ATMEL_AUTHENC +#if IS_ENABLED(CONFIG_CRYPTO_DEV_ATMEL_AUTHENC) if (dd->ctx->is_aead) atmel_aes_authenc_complete(dd, err); #endif @@ -500,26 +523,8 @@ static inline int atmel_aes_complete(struct atmel_aes_dev *dd, int err) clk_disable(dd->iclk); dd->flags &= ~AES_FLAGS_BUSY; - if (!dd->ctx->is_aead) { - struct ablkcipher_request *req = - ablkcipher_request_cast(dd->areq); - struct atmel_aes_reqctx *rctx = ablkcipher_request_ctx(req); - struct crypto_ablkcipher *ablkcipher = - crypto_ablkcipher_reqtfm(req); - int ivsize = crypto_ablkcipher_ivsize(ablkcipher); - - if (rctx->mode & AES_FLAGS_ENCRYPT) { - scatterwalk_map_and_copy(req->info, req->dst, - req->nbytes - ivsize, ivsize, 0); - } else { - if (req->src == req->dst) { - memcpy(req->info, rctx->lastc, ivsize); - } else { - scatterwalk_map_and_copy(req->info, req->src, - req->nbytes - ivsize, ivsize, 0); - } - } - } + if (!dd->ctx->is_aead) + atmel_aes_set_iv_as_last_ciphertext_block(dd); if (dd->is_async) dd->areq->complete(dd->areq, err); @@ -1125,10 +1130,12 @@ static int atmel_aes_crypt(struct ablkcipher_request *req, unsigned long mode) rctx->mode = mode; if (!(mode & AES_FLAGS_ENCRYPT) && (req->src == req->dst)) { - int ivsize = crypto_ablkcipher_ivsize(ablkcipher); + unsigned int ivsize = crypto_ablkcipher_ivsize(ablkcipher); - scatterwalk_map_and_copy(rctx->lastc, req->src, - (req->nbytes - ivsize), ivsize, 0); + if (req->nbytes >= ivsize) + scatterwalk_map_and_copy(rctx->lastc, req->src, + req->nbytes - ivsize, + ivsize, 0); } return atmel_aes_handle_queue(dd, &req->base); @@ -1973,7 +1980,7 @@ static struct crypto_alg aes_xts_alg = { } }; -#ifdef CONFIG_CRYPTO_DEV_ATMEL_AUTHENC +#if IS_ENABLED(CONFIG_CRYPTO_DEV_ATMEL_AUTHENC) /* authenc aead functions */ static int atmel_aes_authenc_start(struct atmel_aes_dev *dd); @@ -2460,7 +2467,7 @@ static void atmel_aes_unregister_algs(struct atmel_aes_dev *dd) { int i; -#ifdef CONFIG_CRYPTO_DEV_ATMEL_AUTHENC +#if IS_ENABLED(CONFIG_CRYPTO_DEV_ATMEL_AUTHENC) if (dd->caps.has_authenc) for (i = 0; i < ARRAY_SIZE(aes_authenc_algs); i++) crypto_unregister_aead(&aes_authenc_algs[i]); @@ -2507,7 +2514,7 @@ static int atmel_aes_register_algs(struct atmel_aes_dev *dd) goto err_aes_xts_alg; } -#ifdef CONFIG_CRYPTO_DEV_ATMEL_AUTHENC +#if IS_ENABLED(CONFIG_CRYPTO_DEV_ATMEL_AUTHENC) if (dd->caps.has_authenc) { for (i = 0; i < ARRAY_SIZE(aes_authenc_algs); i++) { err = crypto_register_aead(&aes_authenc_algs[i]); @@ -2519,7 +2526,7 @@ static int atmel_aes_register_algs(struct atmel_aes_dev *dd) return 0; -#ifdef CONFIG_CRYPTO_DEV_ATMEL_AUTHENC +#if IS_ENABLED(CONFIG_CRYPTO_DEV_ATMEL_AUTHENC) /* i = ARRAY_SIZE(aes_authenc_algs); */ err_aes_authenc_alg: for (j = 0; j < i; j++) @@ -2709,7 +2716,7 @@ static int atmel_aes_probe(struct platform_device *pdev) atmel_aes_get_cap(aes_dd); -#ifdef CONFIG_CRYPTO_DEV_ATMEL_AUTHENC +#if IS_ENABLED(CONFIG_CRYPTO_DEV_ATMEL_AUTHENC) if (aes_dd->caps.has_authenc && !atmel_sha_authenc_is_ready()) { err = -EPROBE_DEFER; goto iclk_unprepare; diff --git a/drivers/crypto/atmel-authenc.h b/drivers/crypto/atmel-authenc.h index cbd37a2edada..d6de810df44f 100644 --- a/drivers/crypto/atmel-authenc.h +++ b/drivers/crypto/atmel-authenc.h @@ -12,7 +12,7 @@ #ifndef __ATMEL_AUTHENC_H__ #define __ATMEL_AUTHENC_H__ -#ifdef CONFIG_CRYPTO_DEV_ATMEL_AUTHENC +#if IS_ENABLED(CONFIG_CRYPTO_DEV_ATMEL_AUTHENC) #include #include diff --git a/drivers/crypto/atmel-sha.c b/drivers/crypto/atmel-sha.c index 84cb8748a795..d32626458e67 100644 --- a/drivers/crypto/atmel-sha.c +++ b/drivers/crypto/atmel-sha.c @@ -2212,7 +2212,7 @@ static struct ahash_alg sha_hmac_algs[] = { }, }; -#ifdef CONFIG_CRYPTO_DEV_ATMEL_AUTHENC +#if IS_ENABLED(CONFIG_CRYPTO_DEV_ATMEL_AUTHENC) /* authenc functions */ static int atmel_sha_authenc_init2(struct atmel_sha_dev *dd); diff --git a/drivers/crypto/cavium/nitrox/nitrox_main.c b/drivers/crypto/cavium/nitrox/nitrox_main.c index bc924980e10c..c4632d84c9a1 100644 --- a/drivers/crypto/cavium/nitrox/nitrox_main.c +++ b/drivers/crypto/cavium/nitrox/nitrox_main.c @@ -103,8 +103,7 @@ static void write_to_ucd_unit(struct nitrox_device *ndev, u32 ucode_size, offset = UCD_UCODE_LOAD_BLOCK_NUM; nitrox_write_csr(ndev, offset, block_num); - code_size = ucode_size; - code_size = roundup(code_size, 8); + code_size = roundup(ucode_size, 16); while (code_size) { data = ucode_data[i]; /* write 8 bytes at a time */ @@ -220,11 +219,11 @@ static int nitrox_load_fw(struct nitrox_device *ndev) /* write block number and firmware length * bit:<2:0> block number - * bit:3 is set SE uses 32KB microcode - * bit:3 is clear SE uses 64KB microcode + * bit:3 is set AE uses 32KB microcode + * bit:3 is clear AE uses 64KB microcode */ core_2_eid_val.value = 0ULL; - core_2_eid_val.ucode_blk = 0; + core_2_eid_val.ucode_blk = 2; if (ucode_size <= CNN55XX_UCD_BLOCK_SIZE) core_2_eid_val.ucode_len = 1; else diff --git a/drivers/crypto/ccp/ccp-dmaengine.c b/drivers/crypto/ccp/ccp-dmaengine.c index a54f9367a580..0770a83bf1a5 100644 --- a/drivers/crypto/ccp/ccp-dmaengine.c +++ b/drivers/crypto/ccp/ccp-dmaengine.c @@ -342,6 +342,7 @@ static struct ccp_dma_desc *ccp_alloc_dma_desc(struct ccp_dma_chan *chan, desc->tx_desc.flags = flags; desc->tx_desc.tx_submit = ccp_tx_submit; desc->ccp = chan->ccp; + INIT_LIST_HEAD(&desc->entry); INIT_LIST_HEAD(&desc->pending); INIT_LIST_HEAD(&desc->active); desc->status = DMA_IN_PROGRESS; diff --git a/drivers/crypto/geode-aes.c b/drivers/crypto/geode-aes.c index d81a1297cb9e..73a899e6f837 100644 --- a/drivers/crypto/geode-aes.c +++ b/drivers/crypto/geode-aes.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include @@ -23,12 +24,12 @@ static spinlock_t lock; /* Write a 128 bit field (either a writable key or IV) */ static inline void -_writefield(u32 offset, void *value) +_writefield(u32 offset, const void *value) { int i; for (i = 0; i < 4; i++) - iowrite32(((u32 *) value)[i], _iobase + offset + (i * 4)); + iowrite32(((const u32 *) value)[i], _iobase + offset + (i * 4)); } /* Read a 128 bit field (either a writable key or IV) */ @@ -42,12 +43,12 @@ _readfield(u32 offset, void *value) } static int -do_crypt(void *src, void *dst, int len, u32 flags) +do_crypt(const void *src, void *dst, u32 len, u32 flags) { u32 status; u32 counter = AES_OP_TIMEOUT; - iowrite32(virt_to_phys(src), _iobase + AES_SOURCEA_REG); + iowrite32(virt_to_phys((void *)src), _iobase + AES_SOURCEA_REG); iowrite32(virt_to_phys(dst), _iobase + AES_DSTA_REG); iowrite32(len, _iobase + AES_LENA_REG); @@ -64,16 +65,14 @@ do_crypt(void *src, void *dst, int len, u32 flags) return counter ? 0 : 1; } -static unsigned int -geode_aes_crypt(struct geode_aes_op *op) +static void +geode_aes_crypt(const struct geode_aes_tfm_ctx *tctx, const void *src, + void *dst, u32 len, u8 *iv, int mode, int dir) { u32 flags = 0; unsigned long iflags; int ret; - if (op->len == 0) - return 0; - /* If the source and destination is the same, then * we need to turn on the coherent flags, otherwise * we don't need to worry @@ -81,32 +80,28 @@ geode_aes_crypt(struct geode_aes_op *op) flags |= (AES_CTRL_DCA | AES_CTRL_SCA); - if (op->dir == AES_DIR_ENCRYPT) + if (dir == AES_DIR_ENCRYPT) flags |= AES_CTRL_ENCRYPT; /* Start the critical section */ spin_lock_irqsave(&lock, iflags); - if (op->mode == AES_MODE_CBC) { + if (mode == AES_MODE_CBC) { flags |= AES_CTRL_CBC; - _writefield(AES_WRITEIV0_REG, op->iv); + _writefield(AES_WRITEIV0_REG, iv); } - if (!(op->flags & AES_FLAGS_HIDDENKEY)) { - flags |= AES_CTRL_WRKEY; - _writefield(AES_WRITEKEY0_REG, op->key); - } + flags |= AES_CTRL_WRKEY; + _writefield(AES_WRITEKEY0_REG, tctx->key); - ret = do_crypt(op->src, op->dst, op->len, flags); + ret = do_crypt(src, dst, len, flags); BUG_ON(ret); - if (op->mode == AES_MODE_CBC) - _readfield(AES_WRITEIV0_REG, op->iv); + if (mode == AES_MODE_CBC) + _readfield(AES_WRITEIV0_REG, iv); spin_unlock_irqrestore(&lock, iflags); - - return op->len; } /* CRYPTO-API Functions */ @@ -114,13 +109,13 @@ geode_aes_crypt(struct geode_aes_op *op) static int geode_setkey_cip(struct crypto_tfm *tfm, const u8 *key, unsigned int len) { - struct geode_aes_op *op = crypto_tfm_ctx(tfm); + struct geode_aes_tfm_ctx *tctx = crypto_tfm_ctx(tfm); unsigned int ret; - op->keylen = len; + tctx->keylen = len; if (len == AES_KEYSIZE_128) { - memcpy(op->key, key, len); + memcpy(tctx->key, key, len); return 0; } @@ -133,135 +128,93 @@ static int geode_setkey_cip(struct crypto_tfm *tfm, const u8 *key, /* * The requested key size is not supported by HW, do a fallback */ - op->fallback.cip->base.crt_flags &= ~CRYPTO_TFM_REQ_MASK; - op->fallback.cip->base.crt_flags |= (tfm->crt_flags & CRYPTO_TFM_REQ_MASK); + tctx->fallback.cip->base.crt_flags &= ~CRYPTO_TFM_REQ_MASK; + tctx->fallback.cip->base.crt_flags |= + (tfm->crt_flags & CRYPTO_TFM_REQ_MASK); - ret = crypto_cipher_setkey(op->fallback.cip, key, len); + ret = crypto_cipher_setkey(tctx->fallback.cip, key, len); if (ret) { tfm->crt_flags &= ~CRYPTO_TFM_RES_MASK; - tfm->crt_flags |= (op->fallback.cip->base.crt_flags & CRYPTO_TFM_RES_MASK); + tfm->crt_flags |= (tctx->fallback.cip->base.crt_flags & + CRYPTO_TFM_RES_MASK); } return ret; } -static int geode_setkey_blk(struct crypto_tfm *tfm, const u8 *key, - unsigned int len) +static int geode_setkey_skcipher(struct crypto_skcipher *tfm, const u8 *key, + unsigned int len) { - struct geode_aes_op *op = crypto_tfm_ctx(tfm); + struct geode_aes_tfm_ctx *tctx = crypto_skcipher_ctx(tfm); unsigned int ret; - op->keylen = len; + tctx->keylen = len; if (len == AES_KEYSIZE_128) { - memcpy(op->key, key, len); + memcpy(tctx->key, key, len); return 0; } if (len != AES_KEYSIZE_192 && len != AES_KEYSIZE_256) { /* not supported at all */ - tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN; + crypto_skcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN); return -EINVAL; } /* * The requested key size is not supported by HW, do a fallback */ - op->fallback.blk->base.crt_flags &= ~CRYPTO_TFM_REQ_MASK; - op->fallback.blk->base.crt_flags |= (tfm->crt_flags & CRYPTO_TFM_REQ_MASK); - - ret = crypto_blkcipher_setkey(op->fallback.blk, key, len); - if (ret) { - tfm->crt_flags &= ~CRYPTO_TFM_RES_MASK; - tfm->crt_flags |= (op->fallback.blk->base.crt_flags & CRYPTO_TFM_RES_MASK); - } - return ret; -} - -static int fallback_blk_dec(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) -{ - unsigned int ret; - struct crypto_blkcipher *tfm; - struct geode_aes_op *op = crypto_blkcipher_ctx(desc->tfm); - - tfm = desc->tfm; - desc->tfm = op->fallback.blk; - - ret = crypto_blkcipher_decrypt_iv(desc, dst, src, nbytes); - - desc->tfm = tfm; - return ret; -} -static int fallback_blk_enc(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) -{ - unsigned int ret; - struct crypto_blkcipher *tfm; - struct geode_aes_op *op = crypto_blkcipher_ctx(desc->tfm); - - tfm = desc->tfm; - desc->tfm = op->fallback.blk; - - ret = crypto_blkcipher_encrypt_iv(desc, dst, src, nbytes); - - desc->tfm = tfm; + crypto_skcipher_clear_flags(tctx->fallback.skcipher, + CRYPTO_TFM_REQ_MASK); + crypto_skcipher_set_flags(tctx->fallback.skcipher, + crypto_skcipher_get_flags(tfm) & + CRYPTO_TFM_REQ_MASK); + ret = crypto_skcipher_setkey(tctx->fallback.skcipher, key, len); + crypto_skcipher_set_flags(tfm, + crypto_skcipher_get_flags(tctx->fallback.skcipher) & + CRYPTO_TFM_RES_MASK); return ret; } static void geode_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) { - struct geode_aes_op *op = crypto_tfm_ctx(tfm); + const struct geode_aes_tfm_ctx *tctx = crypto_tfm_ctx(tfm); - if (unlikely(op->keylen != AES_KEYSIZE_128)) { - crypto_cipher_encrypt_one(op->fallback.cip, out, in); + if (unlikely(tctx->keylen != AES_KEYSIZE_128)) { + crypto_cipher_encrypt_one(tctx->fallback.cip, out, in); return; } - op->src = (void *) in; - op->dst = (void *) out; - op->mode = AES_MODE_ECB; - op->flags = 0; - op->len = AES_BLOCK_SIZE; - op->dir = AES_DIR_ENCRYPT; - - geode_aes_crypt(op); + geode_aes_crypt(tctx, in, out, AES_BLOCK_SIZE, NULL, + AES_MODE_ECB, AES_DIR_ENCRYPT); } static void geode_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) { - struct geode_aes_op *op = crypto_tfm_ctx(tfm); + const struct geode_aes_tfm_ctx *tctx = crypto_tfm_ctx(tfm); - if (unlikely(op->keylen != AES_KEYSIZE_128)) { - crypto_cipher_decrypt_one(op->fallback.cip, out, in); + if (unlikely(tctx->keylen != AES_KEYSIZE_128)) { + crypto_cipher_decrypt_one(tctx->fallback.cip, out, in); return; } - op->src = (void *) in; - op->dst = (void *) out; - op->mode = AES_MODE_ECB; - op->flags = 0; - op->len = AES_BLOCK_SIZE; - op->dir = AES_DIR_DECRYPT; - - geode_aes_crypt(op); + geode_aes_crypt(tctx, in, out, AES_BLOCK_SIZE, NULL, + AES_MODE_ECB, AES_DIR_DECRYPT); } static int fallback_init_cip(struct crypto_tfm *tfm) { const char *name = crypto_tfm_alg_name(tfm); - struct geode_aes_op *op = crypto_tfm_ctx(tfm); + struct geode_aes_tfm_ctx *tctx = crypto_tfm_ctx(tfm); - op->fallback.cip = crypto_alloc_cipher(name, 0, - CRYPTO_ALG_NEED_FALLBACK); + tctx->fallback.cip = crypto_alloc_cipher(name, 0, + CRYPTO_ALG_NEED_FALLBACK); - if (IS_ERR(op->fallback.cip)) { + if (IS_ERR(tctx->fallback.cip)) { printk(KERN_ERR "Error allocating fallback algo %s\n", name); - return PTR_ERR(op->fallback.cip); + return PTR_ERR(tctx->fallback.cip); } return 0; @@ -269,10 +222,9 @@ static int fallback_init_cip(struct crypto_tfm *tfm) static void fallback_exit_cip(struct crypto_tfm *tfm) { - struct geode_aes_op *op = crypto_tfm_ctx(tfm); + struct geode_aes_tfm_ctx *tctx = crypto_tfm_ctx(tfm); - crypto_free_cipher(op->fallback.cip); - op->fallback.cip = NULL; + crypto_free_cipher(tctx->fallback.cip); } static struct crypto_alg geode_alg = { @@ -285,7 +237,7 @@ static struct crypto_alg geode_alg = { .cra_init = fallback_init_cip, .cra_exit = fallback_exit_cip, .cra_blocksize = AES_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct geode_aes_op), + .cra_ctxsize = sizeof(struct geode_aes_tfm_ctx), .cra_module = THIS_MODULE, .cra_u = { .cipher = { @@ -298,209 +250,126 @@ static struct crypto_alg geode_alg = { } }; -static int -geode_cbc_decrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) +static int geode_init_skcipher(struct crypto_skcipher *tfm) { - struct geode_aes_op *op = crypto_blkcipher_ctx(desc->tfm); - struct blkcipher_walk walk; - int err, ret; - - if (unlikely(op->keylen != AES_KEYSIZE_128)) - return fallback_blk_dec(desc, dst, src, nbytes); - - blkcipher_walk_init(&walk, dst, src, nbytes); - err = blkcipher_walk_virt(desc, &walk); - op->iv = walk.iv; - - while ((nbytes = walk.nbytes)) { - op->src = walk.src.virt.addr, - op->dst = walk.dst.virt.addr; - op->mode = AES_MODE_CBC; - op->len = nbytes - (nbytes % AES_BLOCK_SIZE); - op->dir = AES_DIR_DECRYPT; + const char *name = crypto_tfm_alg_name(&tfm->base); + struct geode_aes_tfm_ctx *tctx = crypto_skcipher_ctx(tfm); - ret = geode_aes_crypt(op); - - nbytes -= ret; - err = blkcipher_walk_done(desc, &walk, nbytes); + tctx->fallback.skcipher = + crypto_alloc_skcipher(name, 0, CRYPTO_ALG_NEED_FALLBACK | + CRYPTO_ALG_ASYNC); + if (IS_ERR(tctx->fallback.skcipher)) { + printk(KERN_ERR "Error allocating fallback algo %s\n", name); + return PTR_ERR(tctx->fallback.skcipher); } - return err; + crypto_skcipher_set_reqsize(tfm, sizeof(struct skcipher_request) + + crypto_skcipher_reqsize(tctx->fallback.skcipher)); + return 0; } -static int -geode_cbc_encrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) +static void geode_exit_skcipher(struct crypto_skcipher *tfm) { - struct geode_aes_op *op = crypto_blkcipher_ctx(desc->tfm); - struct blkcipher_walk walk; - int err, ret; - - if (unlikely(op->keylen != AES_KEYSIZE_128)) - return fallback_blk_enc(desc, dst, src, nbytes); - - blkcipher_walk_init(&walk, dst, src, nbytes); - err = blkcipher_walk_virt(desc, &walk); - op->iv = walk.iv; - - while ((nbytes = walk.nbytes)) { - op->src = walk.src.virt.addr, - op->dst = walk.dst.virt.addr; - op->mode = AES_MODE_CBC; - op->len = nbytes - (nbytes % AES_BLOCK_SIZE); - op->dir = AES_DIR_ENCRYPT; - - ret = geode_aes_crypt(op); - nbytes -= ret; - err = blkcipher_walk_done(desc, &walk, nbytes); - } + struct geode_aes_tfm_ctx *tctx = crypto_skcipher_ctx(tfm); - return err; + crypto_free_skcipher(tctx->fallback.skcipher); } -static int fallback_init_blk(struct crypto_tfm *tfm) +static int geode_skcipher_crypt(struct skcipher_request *req, int mode, int dir) { - const char *name = crypto_tfm_alg_name(tfm); - struct geode_aes_op *op = crypto_tfm_ctx(tfm); + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + const struct geode_aes_tfm_ctx *tctx = crypto_skcipher_ctx(tfm); + struct skcipher_walk walk; + unsigned int nbytes; + int err; + + if (unlikely(tctx->keylen != AES_KEYSIZE_128)) { + struct skcipher_request *subreq = skcipher_request_ctx(req); + + *subreq = *req; + skcipher_request_set_tfm(subreq, tctx->fallback.skcipher); + if (dir == AES_DIR_DECRYPT) + return crypto_skcipher_decrypt(subreq); + else + return crypto_skcipher_encrypt(subreq); + } - op->fallback.blk = crypto_alloc_blkcipher(name, 0, - CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK); + err = skcipher_walk_virt(&walk, req, false); - if (IS_ERR(op->fallback.blk)) { - printk(KERN_ERR "Error allocating fallback algo %s\n", name); - return PTR_ERR(op->fallback.blk); + while ((nbytes = walk.nbytes) != 0) { + geode_aes_crypt(tctx, walk.src.virt.addr, walk.dst.virt.addr, + round_down(nbytes, AES_BLOCK_SIZE), + walk.iv, mode, dir); + err = skcipher_walk_done(&walk, nbytes % AES_BLOCK_SIZE); } - return 0; + return err; } -static void fallback_exit_blk(struct crypto_tfm *tfm) +static int geode_cbc_encrypt(struct skcipher_request *req) { - struct geode_aes_op *op = crypto_tfm_ctx(tfm); - - crypto_free_blkcipher(op->fallback.blk); - op->fallback.blk = NULL; + return geode_skcipher_crypt(req, AES_MODE_CBC, AES_DIR_ENCRYPT); } -static struct crypto_alg geode_cbc_alg = { - .cra_name = "cbc(aes)", - .cra_driver_name = "cbc-aes-geode", - .cra_priority = 400, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | - CRYPTO_ALG_KERN_DRIVER_ONLY | - CRYPTO_ALG_NEED_FALLBACK, - .cra_init = fallback_init_blk, - .cra_exit = fallback_exit_blk, - .cra_blocksize = AES_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct geode_aes_op), - .cra_alignmask = 15, - .cra_type = &crypto_blkcipher_type, - .cra_module = THIS_MODULE, - .cra_u = { - .blkcipher = { - .min_keysize = AES_MIN_KEY_SIZE, - .max_keysize = AES_MAX_KEY_SIZE, - .setkey = geode_setkey_blk, - .encrypt = geode_cbc_encrypt, - .decrypt = geode_cbc_decrypt, - .ivsize = AES_BLOCK_SIZE, - } - } -}; - -static int -geode_ecb_decrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) +static int geode_cbc_decrypt(struct skcipher_request *req) { - struct geode_aes_op *op = crypto_blkcipher_ctx(desc->tfm); - struct blkcipher_walk walk; - int err, ret; - - if (unlikely(op->keylen != AES_KEYSIZE_128)) - return fallback_blk_dec(desc, dst, src, nbytes); - - blkcipher_walk_init(&walk, dst, src, nbytes); - err = blkcipher_walk_virt(desc, &walk); - - while ((nbytes = walk.nbytes)) { - op->src = walk.src.virt.addr, - op->dst = walk.dst.virt.addr; - op->mode = AES_MODE_ECB; - op->len = nbytes - (nbytes % AES_BLOCK_SIZE); - op->dir = AES_DIR_DECRYPT; - - ret = geode_aes_crypt(op); - nbytes -= ret; - err = blkcipher_walk_done(desc, &walk, nbytes); - } - - return err; + return geode_skcipher_crypt(req, AES_MODE_CBC, AES_DIR_DECRYPT); } -static int -geode_ecb_encrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes) +static int geode_ecb_encrypt(struct skcipher_request *req) { - struct geode_aes_op *op = crypto_blkcipher_ctx(desc->tfm); - struct blkcipher_walk walk; - int err, ret; - - if (unlikely(op->keylen != AES_KEYSIZE_128)) - return fallback_blk_enc(desc, dst, src, nbytes); - - blkcipher_walk_init(&walk, dst, src, nbytes); - err = blkcipher_walk_virt(desc, &walk); - - while ((nbytes = walk.nbytes)) { - op->src = walk.src.virt.addr, - op->dst = walk.dst.virt.addr; - op->mode = AES_MODE_ECB; - op->len = nbytes - (nbytes % AES_BLOCK_SIZE); - op->dir = AES_DIR_ENCRYPT; - - ret = geode_aes_crypt(op); - nbytes -= ret; - ret = blkcipher_walk_done(desc, &walk, nbytes); - } + return geode_skcipher_crypt(req, AES_MODE_ECB, AES_DIR_ENCRYPT); +} - return err; +static int geode_ecb_decrypt(struct skcipher_request *req) +{ + return geode_skcipher_crypt(req, AES_MODE_ECB, AES_DIR_DECRYPT); } -static struct crypto_alg geode_ecb_alg = { - .cra_name = "ecb(aes)", - .cra_driver_name = "ecb-aes-geode", - .cra_priority = 400, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | - CRYPTO_ALG_KERN_DRIVER_ONLY | - CRYPTO_ALG_NEED_FALLBACK, - .cra_init = fallback_init_blk, - .cra_exit = fallback_exit_blk, - .cra_blocksize = AES_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct geode_aes_op), - .cra_alignmask = 15, - .cra_type = &crypto_blkcipher_type, - .cra_module = THIS_MODULE, - .cra_u = { - .blkcipher = { - .min_keysize = AES_MIN_KEY_SIZE, - .max_keysize = AES_MAX_KEY_SIZE, - .setkey = geode_setkey_blk, - .encrypt = geode_ecb_encrypt, - .decrypt = geode_ecb_decrypt, - } - } +static struct skcipher_alg geode_skcipher_algs[] = { + { + .base.cra_name = "cbc(aes)", + .base.cra_driver_name = "cbc-aes-geode", + .base.cra_priority = 400, + .base.cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY | + CRYPTO_ALG_NEED_FALLBACK, + .base.cra_blocksize = AES_BLOCK_SIZE, + .base.cra_ctxsize = sizeof(struct geode_aes_tfm_ctx), + .base.cra_alignmask = 15, + .base.cra_module = THIS_MODULE, + .init = geode_init_skcipher, + .exit = geode_exit_skcipher, + .setkey = geode_setkey_skcipher, + .encrypt = geode_cbc_encrypt, + .decrypt = geode_cbc_decrypt, + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + }, { + .base.cra_name = "ecb(aes)", + .base.cra_driver_name = "ecb-aes-geode", + .base.cra_priority = 400, + .base.cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY | + CRYPTO_ALG_NEED_FALLBACK, + .base.cra_blocksize = AES_BLOCK_SIZE, + .base.cra_ctxsize = sizeof(struct geode_aes_tfm_ctx), + .base.cra_alignmask = 15, + .base.cra_module = THIS_MODULE, + .init = geode_init_skcipher, + .exit = geode_exit_skcipher, + .setkey = geode_setkey_skcipher, + .encrypt = geode_ecb_encrypt, + .decrypt = geode_ecb_decrypt, + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + }, }; static void geode_aes_remove(struct pci_dev *dev) { crypto_unregister_alg(&geode_alg); - crypto_unregister_alg(&geode_ecb_alg); - crypto_unregister_alg(&geode_cbc_alg); + crypto_unregister_skciphers(geode_skcipher_algs, + ARRAY_SIZE(geode_skcipher_algs)); pci_iounmap(dev, _iobase); _iobase = NULL; @@ -538,20 +407,14 @@ static int geode_aes_probe(struct pci_dev *dev, const struct pci_device_id *id) if (ret) goto eiomap; - ret = crypto_register_alg(&geode_ecb_alg); + ret = crypto_register_skciphers(geode_skcipher_algs, + ARRAY_SIZE(geode_skcipher_algs)); if (ret) goto ealg; - ret = crypto_register_alg(&geode_cbc_alg); - if (ret) - goto eecb; - dev_notice(&dev->dev, "GEODE AES engine enabled.\n"); return 0; - eecb: - crypto_unregister_alg(&geode_ecb_alg); - ealg: crypto_unregister_alg(&geode_alg); diff --git a/drivers/crypto/geode-aes.h b/drivers/crypto/geode-aes.h index 5c6e131a8f9d..6d0a0cdc7647 100644 --- a/drivers/crypto/geode-aes.h +++ b/drivers/crypto/geode-aes.h @@ -46,21 +46,10 @@ #define AES_OP_TIMEOUT 0x50000 -struct geode_aes_op { - - void *src; - void *dst; - - u32 mode; - u32 dir; - u32 flags; - int len; - +struct geode_aes_tfm_ctx { u8 key[AES_KEYSIZE_128]; - u8 *iv; - union { - struct crypto_blkcipher *blk; + struct crypto_skcipher *skcipher; struct crypto_cipher *cip; } fallback; u32 keylen; diff --git a/drivers/crypto/hisilicon/Kconfig b/drivers/crypto/hisilicon/Kconfig index ebaf91e0146d..504daff7687d 100644 --- a/drivers/crypto/hisilicon/Kconfig +++ b/drivers/crypto/hisilicon/Kconfig @@ -17,6 +17,7 @@ config CRYPTO_DEV_HISI_SEC config CRYPTO_DEV_HISI_QM tristate depends on ARM64 && PCI && PCI_MSI + select NEED_SG_DMA_LENGTH help HiSilicon accelerator engines use a common queue management interface. Specific engine driver may use this module. diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c index 4ab1bde8dd9b..991a4425f006 100644 --- a/drivers/crypto/inside-secure/safexcel.c +++ b/drivers/crypto/inside-secure/safexcel.c @@ -221,9 +221,9 @@ static void eip197_trc_cache_init(struct safexcel_crypto_priv *priv) /* Step #3: Determine log2 of hash table size */ cs_ht_sz = __fls(asize - cs_rc_max) - 2; /* Step #4: determine current size of hash table in dwords */ - cs_ht_wc = 16<> 4)); + cs_rc_max = min_t(uint, cs_rc_abs_max, asize - (cs_ht_wc >> 2)); /* Clear the cache RAMs */ eip197_trc_cache_clear(priv, cs_rc_max, cs_ht_wc); @@ -1120,6 +1120,8 @@ static int safexcel_request_ring_irq(void *pdev, int irqid, irq_name, irq); return irq; } + } else { + return -ENXIO; } ret = devm_request_threaded_irq(dev, irq, handler, diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c b/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c index 6536fd4bee65..7e5e092a23b3 100644 --- a/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c +++ b/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c @@ -72,7 +72,8 @@ static int noinline_for_stack sun4i_ss_opti_poll(struct skcipher_request *areq) oi = 0; oo = 0; do { - todo = min3(rx_cnt, ileft, (mi.length - oi) / 4); + todo = min(rx_cnt, ileft); + todo = min_t(size_t, todo, (mi.length - oi) / 4); if (todo) { ileft -= todo; writesl(ss->base + SS_RXFIFO, mi.addr + oi, todo); @@ -87,7 +88,8 @@ static int noinline_for_stack sun4i_ss_opti_poll(struct skcipher_request *areq) rx_cnt = SS_RXFIFO_SPACES(spaces); tx_cnt = SS_TXFIFO_SPACES(spaces); - todo = min3(tx_cnt, oleft, (mo.length - oo) / 4); + todo = min(tx_cnt, oleft); + todo = min_t(size_t, todo, (mo.length - oo) / 4); if (todo) { oleft -= todo; readsl(ss->base + SS_TXFIFO, mo.addr + oo, todo); @@ -239,7 +241,8 @@ static int sun4i_ss_cipher_poll(struct skcipher_request *areq) * todo is the number of consecutive 4byte word that we * can read from current SG */ - todo = min3(rx_cnt, ileft / 4, (mi.length - oi) / 4); + todo = min(rx_cnt, ileft / 4); + todo = min_t(size_t, todo, (mi.length - oi) / 4); if (todo && !ob) { writesl(ss->base + SS_RXFIFO, mi.addr + oi, todo); @@ -253,8 +256,8 @@ static int sun4i_ss_cipher_poll(struct skcipher_request *areq) * we need to be able to write all buf in one * pass, so it is why we min() with rx_cnt */ - todo = min3(rx_cnt * 4 - ob, ileft, - mi.length - oi); + todo = min(rx_cnt * 4 - ob, ileft); + todo = min_t(size_t, todo, mi.length - oi); memcpy(buf + ob, mi.addr + oi, todo); ileft -= todo; oi += todo; @@ -274,7 +277,8 @@ static int sun4i_ss_cipher_poll(struct skcipher_request *areq) spaces = readl(ss->base + SS_FCSR); rx_cnt = SS_RXFIFO_SPACES(spaces); tx_cnt = SS_TXFIFO_SPACES(spaces); - dev_dbg(ss->dev, "%x %u/%u %u/%u cnt=%u %u/%u %u/%u cnt=%u %u\n", + dev_dbg(ss->dev, + "%x %u/%zu %u/%u cnt=%u %u/%zu %u/%u cnt=%u %u\n", mode, oi, mi.length, ileft, areq->cryptlen, rx_cnt, oo, mo.length, oleft, areq->cryptlen, tx_cnt, ob); @@ -282,7 +286,8 @@ static int sun4i_ss_cipher_poll(struct skcipher_request *areq) if (!tx_cnt) continue; /* todo in 4bytes word */ - todo = min3(tx_cnt, oleft / 4, (mo.length - oo) / 4); + todo = min(tx_cnt, oleft / 4); + todo = min_t(size_t, todo, (mo.length - oo) / 4); if (todo) { readsl(ss->base + SS_TXFIFO, mo.addr + oo, todo); oleft -= todo * 4; @@ -308,7 +313,8 @@ static int sun4i_ss_cipher_poll(struct skcipher_request *areq) * no more than remaining buffer * no need to test against oleft */ - todo = min(mo.length - oo, obl - obo); + todo = min_t(size_t, + mo.length - oo, obl - obo); memcpy(mo.addr + oo, bufo + obo, todo); oleft -= todo; obo += todo; diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-hash.c b/drivers/crypto/sunxi-ss/sun4i-ss-hash.c index fcffba5ef927..1369c5fa3087 100644 --- a/drivers/crypto/sunxi-ss/sun4i-ss-hash.c +++ b/drivers/crypto/sunxi-ss/sun4i-ss-hash.c @@ -272,8 +272,8 @@ static int sun4i_hash(struct ahash_request *areq) */ while (op->len < 64 && i < end) { /* how many bytes we can read from current SG */ - in_r = min3(mi.length - in_i, end - i, - 64 - op->len); + in_r = min(end - i, 64 - op->len); + in_r = min_t(size_t, mi.length - in_i, in_r); memcpy(op->buf + op->len, mi.addr + in_i, in_r); op->len += in_r; i += in_r; @@ -293,8 +293,8 @@ static int sun4i_hash(struct ahash_request *areq) } if (mi.length - in_i > 3 && i < end) { /* how many bytes we can read from current SG */ - in_r = min3(mi.length - in_i, areq->nbytes - i, - ((mi.length - in_i) / 4) * 4); + in_r = min_t(size_t, mi.length - in_i, areq->nbytes - i); + in_r = min_t(size_t, ((mi.length - in_i) / 4) * 4, in_r); /* how many bytes we can write in the device*/ todo = min3((u32)(end - i) / 4, rx_cnt, (u32)in_r / 4); writesl(ss->base + SS_RXFIFO, mi.addr + in_i, todo); @@ -320,8 +320,8 @@ static int sun4i_hash(struct ahash_request *areq) if ((areq->nbytes - i) < 64) { while (i < areq->nbytes && in_i < mi.length && op->len < 64) { /* how many bytes we can read from current SG */ - in_r = min3(mi.length - in_i, areq->nbytes - i, - 64 - op->len); + in_r = min(areq->nbytes - i, 64 - op->len); + in_r = min_t(size_t, mi.length - in_i, in_r); memcpy(op->buf + op->len, mi.addr + in_i, in_r); op->len += in_r; i += in_r; diff --git a/drivers/crypto/virtio/virtio_crypto_algs.c b/drivers/crypto/virtio/virtio_crypto_algs.c index 42d19205166b..82b316b2f537 100644 --- a/drivers/crypto/virtio/virtio_crypto_algs.c +++ b/drivers/crypto/virtio/virtio_crypto_algs.c @@ -105,8 +105,6 @@ virtio_crypto_alg_validate_key(int key_len, uint32_t *alg) *alg = VIRTIO_CRYPTO_CIPHER_AES_CBC; break; default: - pr_err("virtio_crypto: Unsupported key length: %d\n", - key_len); return -EINVAL; } return 0; @@ -437,6 +435,11 @@ __virtio_crypto_ablkcipher_do_req(struct virtio_crypto_sym_request *vc_sym_req, goto free; } memcpy(iv, req->info, ivsize); + if (!vc_sym_req->encrypt) + scatterwalk_map_and_copy(req->info, req->src, + req->nbytes - AES_BLOCK_SIZE, + AES_BLOCK_SIZE, 0); + sg_init_one(&iv_sg, iv, ivsize); sgs[num_out++] = &iv_sg; vc_sym_req->iv = iv; @@ -484,6 +487,11 @@ static int virtio_crypto_ablkcipher_encrypt(struct ablkcipher_request *req) /* Use the first data virtqueue as default */ struct data_queue *data_vq = &vcrypto->data_vq[0]; + if (!req->nbytes) + return 0; + if (req->nbytes % AES_BLOCK_SIZE) + return -EINVAL; + vc_req->dataq = data_vq; vc_req->alg_cb = virtio_crypto_dataq_sym_callback; vc_sym_req->ablkcipher_ctx = ctx; @@ -504,6 +512,11 @@ static int virtio_crypto_ablkcipher_decrypt(struct ablkcipher_request *req) /* Use the first data virtqueue as default */ struct data_queue *data_vq = &vcrypto->data_vq[0]; + if (!req->nbytes) + return 0; + if (req->nbytes % AES_BLOCK_SIZE) + return -EINVAL; + vc_req->dataq = data_vq; vc_req->alg_cb = virtio_crypto_dataq_sym_callback; vc_sym_req->ablkcipher_ctx = ctx; @@ -563,6 +576,10 @@ static void virtio_crypto_ablkcipher_finalize_req( struct ablkcipher_request *req, int err) { + if (vc_sym_req->encrypt) + scatterwalk_map_and_copy(req->info, req->dst, + req->nbytes - AES_BLOCK_SIZE, + AES_BLOCK_SIZE, 0); crypto_finalize_ablkcipher_request(vc_sym_req->base.dataq->engine, req, err); kzfree(vc_sym_req->iv); diff --git a/drivers/crypto/vmx/Makefile b/drivers/crypto/vmx/Makefile index cab32cfec9c4..709670d2b553 100644 --- a/drivers/crypto/vmx/Makefile +++ b/drivers/crypto/vmx/Makefile @@ -3,13 +3,13 @@ obj-$(CONFIG_CRYPTO_DEV_VMX_ENCRYPT) += vmx-crypto.o vmx-crypto-objs := vmx.o aesp8-ppc.o ghashp8-ppc.o aes.o aes_cbc.o aes_ctr.o aes_xts.o ghash.o ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y) -TARGET := linux-ppc64le +override flavour := linux-ppc64le else -TARGET := linux-ppc64 +override flavour := linux-ppc64 endif quiet_cmd_perl = PERL $@ - cmd_perl = $(PERL) $(<) $(TARGET) > $(@) + cmd_perl = $(PERL) $(<) $(flavour) > $(@) targets += aesp8-ppc.S ghashp8-ppc.S diff --git a/drivers/devfreq/Kconfig b/drivers/devfreq/Kconfig index defe1d438710..af4a3ccb96b3 100644 --- a/drivers/devfreq/Kconfig +++ b/drivers/devfreq/Kconfig @@ -99,6 +99,7 @@ config ARM_TEGRA_DEVFREQ ARCH_TEGRA_210_SOC || \ COMPILE_TEST select PM_OPP + depends on COMMON_CLK help This adds the DEVFREQ driver for the Tegra family of SoCs. It reads ACTMON counters of memory controllers and adjusts the diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index 446490c9d635..c64d20fdc187 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -160,6 +160,7 @@ int devfreq_update_status(struct devfreq *devfreq, unsigned long freq) int lev, prev_lev, ret = 0; unsigned long cur_time; + lockdep_assert_held(&devfreq->lock); cur_time = jiffies; /* Immediately exit if previous_freq is not initialized yet. */ @@ -550,26 +551,30 @@ static int devfreq_notifier_call(struct notifier_block *nb, unsigned long type, void *devp) { struct devfreq *devfreq = container_of(nb, struct devfreq, nb); - int ret; + int err = -EINVAL; mutex_lock(&devfreq->lock); devfreq->scaling_min_freq = find_available_min_freq(devfreq); - if (!devfreq->scaling_min_freq) { - mutex_unlock(&devfreq->lock); - return -EINVAL; - } + if (!devfreq->scaling_min_freq) + goto out; devfreq->scaling_max_freq = find_available_max_freq(devfreq); if (!devfreq->scaling_max_freq) { - mutex_unlock(&devfreq->lock); - return -EINVAL; + devfreq->scaling_max_freq = ULONG_MAX; + goto out; } - ret = update_devfreq(devfreq); + err = update_devfreq(devfreq); + +out: mutex_unlock(&devfreq->lock); + if (err) + dev_err(devfreq->dev.parent, + "failed to update frequency from OPP notifier (%d)\n", + err); - return ret; + return NOTIFY_OK; } /** @@ -583,11 +588,6 @@ static void devfreq_dev_release(struct device *dev) struct devfreq *devfreq = to_devfreq(dev); mutex_lock(&devfreq_list_lock); - if (IS_ERR(find_device_devfreq(devfreq->dev.parent))) { - mutex_unlock(&devfreq_list_lock); - dev_warn(&devfreq->dev, "releasing devfreq which doesn't exist\n"); - return; - } list_del(&devfreq->node); mutex_unlock(&devfreq_list_lock); @@ -642,6 +642,7 @@ struct devfreq *devfreq_add_device(struct device *dev, devfreq->dev.parent = dev; devfreq->dev.class = devfreq_class; devfreq->dev.release = devfreq_dev_release; + INIT_LIST_HEAD(&devfreq->node); devfreq->profile = profile; strncpy(devfreq->governor_name, governor_name, DEVFREQ_NAME_LEN); devfreq->previous_freq = profile->initial_freq; @@ -1195,7 +1196,7 @@ static ssize_t available_governors_show(struct device *d, * The devfreq with immutable governor (e.g., passive) shows * only own governor. */ - if (df->governor->immutable) { + if (df->governor && df->governor->immutable) { count = scnprintf(&buf[count], DEVFREQ_NAME_LEN, "%s ", df->governor_name); /* @@ -1397,12 +1398,17 @@ static ssize_t trans_stat_show(struct device *dev, int i, j; unsigned int max_state = devfreq->profile->max_state; - if (!devfreq->stop_polling && - devfreq_update_status(devfreq, devfreq->previous_freq)) - return 0; if (max_state == 0) return sprintf(buf, "Not Supported.\n"); + mutex_lock(&devfreq->lock); + if (!devfreq->stop_polling && + devfreq_update_status(devfreq, devfreq->previous_freq)) { + mutex_unlock(&devfreq->lock); + return 0; + } + mutex_unlock(&devfreq->lock); + len = sprintf(buf, " From : To\n"); len += sprintf(buf + len, " :"); for (i = 0; i < max_state; i++) diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c index 25c5c071645b..91185db9a952 100644 --- a/drivers/dma-buf/sync_file.c +++ b/drivers/dma-buf/sync_file.c @@ -221,7 +221,7 @@ static struct sync_file *sync_file_merge(const char *name, struct sync_file *a, a_fences = get_fences(a, &a_num_fences); b_fences = get_fences(b, &b_num_fences); if (a_num_fences > INT_MAX - b_num_fences) - return NULL; + goto err; num_fences = a_num_fences + b_num_fences; diff --git a/drivers/dma/dma-jz4780.c b/drivers/dma/dma-jz4780.c index cafb1cc065bb..bf95f1d551c5 100644 --- a/drivers/dma/dma-jz4780.c +++ b/drivers/dma/dma-jz4780.c @@ -1004,7 +1004,8 @@ static const struct jz4780_dma_soc_data jz4740_dma_soc_data = { static const struct jz4780_dma_soc_data jz4725b_dma_soc_data = { .nb_channels = 6, .transfer_ord_max = 5, - .flags = JZ_SOC_DATA_PER_CHAN_PM | JZ_SOC_DATA_NO_DCKES_DCKEC, + .flags = JZ_SOC_DATA_PER_CHAN_PM | JZ_SOC_DATA_NO_DCKES_DCKEC | + JZ_SOC_DATA_BREAK_LINKS, }; static const struct jz4780_dma_soc_data jz4770_dma_soc_data = { diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c index c90c798e5ec3..0585d749d935 100644 --- a/drivers/dma/dw/platform.c +++ b/drivers/dma/dw/platform.c @@ -66,7 +66,7 @@ static int dw_probe(struct platform_device *pdev) data->chip = chip; - chip->clk = devm_clk_get(chip->dev, "hclk"); + chip->clk = devm_clk_get_optional(chip->dev, "hclk"); if (IS_ERR(chip->clk)) return PTR_ERR(chip->clk); err = clk_prepare_enable(chip->clk); diff --git a/drivers/dma/fsl-qdma.c b/drivers/dma/fsl-qdma.c index 06664fbd2d91..89792083d62c 100644 --- a/drivers/dma/fsl-qdma.c +++ b/drivers/dma/fsl-qdma.c @@ -1155,6 +1155,9 @@ static int fsl_qdma_probe(struct platform_device *pdev) return ret; fsl_qdma->irq_base = platform_get_irq_byname(pdev, "qdma-queue0"); + if (fsl_qdma->irq_base < 0) + return fsl_qdma->irq_base; + fsl_qdma->feature = of_property_read_bool(np, "big-endian"); INIT_LIST_HEAD(&fsl_qdma->dma_dev.channels); diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c index 1a422a8b43cf..18c011e57592 100644 --- a/drivers/dma/ioat/dma.c +++ b/drivers/dma/ioat/dma.c @@ -377,10 +377,11 @@ ioat_alloc_ring(struct dma_chan *c, int order, gfp_t flags) descs->virt = dma_alloc_coherent(to_dev(ioat_chan), SZ_2M, &descs->hw, flags); - if (!descs->virt && (i > 0)) { + if (!descs->virt) { int idx; for (idx = 0; idx < i; idx++) { + descs = &ioat_chan->descs[idx]; dma_free_coherent(to_dev(ioat_chan), SZ_2M, descs->virt, descs->hw); descs->virt = NULL; diff --git a/drivers/dma/k3dma.c b/drivers/dma/k3dma.c index 4b36c8810517..d05471653224 100644 --- a/drivers/dma/k3dma.c +++ b/drivers/dma/k3dma.c @@ -229,9 +229,11 @@ static irqreturn_t k3_dma_int_handler(int irq, void *dev_id) c = p->vchan; if (c && (tc1 & BIT(i))) { spin_lock_irqsave(&c->vc.lock, flags); - vchan_cookie_complete(&p->ds_run->vd); - p->ds_done = p->ds_run; - p->ds_run = NULL; + if (p->ds_run != NULL) { + vchan_cookie_complete(&p->ds_run->vd); + p->ds_done = p->ds_run; + p->ds_run = NULL; + } spin_unlock_irqrestore(&c->vc.lock, flags); } if (c && (tc2 & BIT(i))) { @@ -271,6 +273,10 @@ static int k3_dma_start_txd(struct k3_dma_chan *c) if (BIT(c->phy->idx) & k3_dma_get_chan_stat(d)) return -EAGAIN; + /* Avoid losing track of ds_run if a transaction is in flight */ + if (c->phy->ds_run) + return -EAGAIN; + if (vd) { struct k3_dma_desc_sw *ds = container_of(vd, struct k3_dma_desc_sw, vd); diff --git a/drivers/dma/virt-dma.c b/drivers/dma/virt-dma.c index ec4adf4260a0..256fc662c500 100644 --- a/drivers/dma/virt-dma.c +++ b/drivers/dma/virt-dma.c @@ -104,9 +104,8 @@ static void vchan_complete(unsigned long arg) dmaengine_desc_get_callback(&vd->tx, &cb); list_del(&vd->node); - vchan_vdesc_fini(vd); - dmaengine_desc_callback_invoke(&cb, &vd->tx_result); + vchan_vdesc_fini(vd); } } diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c index 5d56f1e4d332..43acba2a1c0e 100644 --- a/drivers/dma/xilinx/xilinx_dma.c +++ b/drivers/dma/xilinx/xilinx_dma.c @@ -1433,6 +1433,7 @@ static int xilinx_dma_reset(struct xilinx_dma_chan *chan) chan->err = false; chan->idle = true; + chan->desc_pendingcount = 0; chan->desc_submitcount = 0; return err; diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c index fbda4b876afd..0be3d1b17f03 100644 --- a/drivers/edac/altera_edac.c +++ b/drivers/edac/altera_edac.c @@ -560,6 +560,7 @@ static const struct regmap_config s10_sdram_regmap_cfg = { .reg_write = s10_protected_reg_write, .use_single_read = true, .use_single_write = true, + .fast_io = true, }; /************** ***********/ diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index c1d4536ae466..cc5e56d752c8 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -2936,6 +2936,7 @@ static int init_csrows_df(struct mem_ctl_info *mci) dimm->mtype = pvt->dram_type; dimm->edac_mode = edac_mode; dimm->dtype = dev_type; + dimm->grain = 64; } } @@ -3012,6 +3013,7 @@ static int init_csrows(struct mem_ctl_info *mci) dimm = csrow->channels[j]->dimm; dimm->mtype = pvt->dram_type; dimm->edac_mode = edac_mode; + dimm->grain = 64; } } diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c index 0bb62857ffb2..523dd56a798c 100644 --- a/drivers/edac/ghes_edac.c +++ b/drivers/edac/ghes_edac.c @@ -26,9 +26,18 @@ struct ghes_edac_pvt { char msg[80]; }; -static atomic_t ghes_init = ATOMIC_INIT(0); +static refcount_t ghes_refcount = REFCOUNT_INIT(0); + +/* + * Access to ghes_pvt must be protected by ghes_lock. The spinlock + * also provides the necessary (implicit) memory barrier for the SMP + * case to make the pointer visible on another CPU. + */ static struct ghes_edac_pvt *ghes_pvt; +/* GHES registration mutex */ +static DEFINE_MUTEX(ghes_reg_mutex); + /* * Sync with other, potentially concurrent callers of * ghes_edac_report_mem_error(). We don't know what the @@ -79,9 +88,8 @@ static void ghes_edac_count_dimms(const struct dmi_header *dh, void *arg) (*num_dimm)++; } -static int get_dimm_smbios_index(u16 handle) +static int get_dimm_smbios_index(struct mem_ctl_info *mci, u16 handle) { - struct mem_ctl_info *mci = ghes_pvt->mci; int i; for (i = 0; i < mci->tot_dimms; i++) { @@ -198,14 +206,11 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err) enum hw_event_mc_err_type type; struct edac_raw_error_desc *e; struct mem_ctl_info *mci; - struct ghes_edac_pvt *pvt = ghes_pvt; + struct ghes_edac_pvt *pvt; unsigned long flags; char *p; u8 grain_bits; - if (!pvt) - return; - /* * We can do the locking below because GHES defers error processing * from NMI to IRQ context. Whenever that changes, we'd at least @@ -216,12 +221,17 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err) spin_lock_irqsave(&ghes_lock, flags); + pvt = ghes_pvt; + if (!pvt) + goto unlock; + mci = pvt->mci; e = &mci->error_desc; /* Cleans the error report buffer */ memset(e, 0, sizeof (*e)); e->error_count = 1; + e->grain = 1; strcpy(e->label, "unknown label"); e->msg = pvt->msg; e->other_detail = pvt->other_detail; @@ -317,7 +327,7 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err) /* Error grain */ if (mem_err->validation_bits & CPER_MEM_VALID_PA_MASK) - e->grain = ~(mem_err->physical_addr_mask & ~PAGE_MASK); + e->grain = ~mem_err->physical_addr_mask + 1; /* Memory error location, mapped on e->location */ p = e->location; @@ -348,7 +358,7 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err) p += sprintf(p, "DIMM DMI handle: 0x%.4x ", mem_err->mem_dev_handle); - index = get_dimm_smbios_index(mem_err->mem_dev_handle); + index = get_dimm_smbios_index(mci, mem_err->mem_dev_handle); if (index >= 0) { e->top_layer = index; e->enable_per_layer_report = true; @@ -433,8 +443,13 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err) if (p > pvt->other_detail) *(p - 1) = '\0'; + /* Sanity-check driver-supplied grain value. */ + if (WARN_ON_ONCE(!e->grain)) + e->grain = 1; + + grain_bits = fls_long(e->grain - 1); + /* Generate the trace event */ - grain_bits = fls_long(e->grain); snprintf(pvt->detail_location, sizeof(pvt->detail_location), "APEI location: %s %s", e->location, e->other_detail); trace_mc_event(type, e->msg, e->label, e->error_count, @@ -443,6 +458,8 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err) grain_bits, e->syndrome, pvt->detail_location); edac_raw_mc_handle_error(type, mci, e); + +unlock: spin_unlock_irqrestore(&ghes_lock, flags); } @@ -457,10 +474,12 @@ static struct acpi_platform_list plat_list[] = { int ghes_edac_register(struct ghes *ghes, struct device *dev) { bool fake = false; - int rc, num_dimm = 0; + int rc = 0, num_dimm = 0; struct mem_ctl_info *mci; + struct ghes_edac_pvt *pvt; struct edac_mc_layer layers[1]; struct ghes_edac_dimm_fill dimm_fill; + unsigned long flags; int idx = -1; if (IS_ENABLED(CONFIG_X86)) { @@ -472,11 +491,14 @@ int ghes_edac_register(struct ghes *ghes, struct device *dev) idx = 0; } + /* finish another registration/unregistration instance first */ + mutex_lock(&ghes_reg_mutex); + /* * We have only one logical memory controller to which all DIMMs belong. */ - if (atomic_inc_return(&ghes_init) > 1) - return 0; + if (refcount_inc_not_zero(&ghes_refcount)) + goto unlock; /* Get the number of DIMMs */ dmi_walk(ghes_edac_count_dimms, &num_dimm); @@ -494,12 +516,13 @@ int ghes_edac_register(struct ghes *ghes, struct device *dev) mci = edac_mc_alloc(0, ARRAY_SIZE(layers), layers, sizeof(struct ghes_edac_pvt)); if (!mci) { pr_info("Can't allocate memory for EDAC data\n"); - return -ENOMEM; + rc = -ENOMEM; + goto unlock; } - ghes_pvt = mci->pvt_info; - ghes_pvt->ghes = ghes; - ghes_pvt->mci = mci; + pvt = mci->pvt_info; + pvt->ghes = ghes; + pvt->mci = mci; mci->pdev = dev; mci->mtype_cap = MEM_FLAG_EMPTY; @@ -541,23 +564,48 @@ int ghes_edac_register(struct ghes *ghes, struct device *dev) if (rc < 0) { pr_info("Can't register at EDAC core\n"); edac_mc_free(mci); - return -ENODEV; + rc = -ENODEV; + goto unlock; } - return 0; + + spin_lock_irqsave(&ghes_lock, flags); + ghes_pvt = pvt; + spin_unlock_irqrestore(&ghes_lock, flags); + + /* only set on success */ + refcount_set(&ghes_refcount, 1); + +unlock: + mutex_unlock(&ghes_reg_mutex); + + return rc; } void ghes_edac_unregister(struct ghes *ghes) { struct mem_ctl_info *mci; + unsigned long flags; - if (!ghes_pvt) - return; + mutex_lock(&ghes_reg_mutex); - if (atomic_dec_return(&ghes_init)) - return; + if (!refcount_dec_and_test(&ghes_refcount)) + goto unlock; - mci = ghes_pvt->mci; + /* + * Wait for the irq handler being finished. + */ + spin_lock_irqsave(&ghes_lock, flags); + mci = ghes_pvt ? ghes_pvt->mci : NULL; ghes_pvt = NULL; - edac_mc_del_mc(mci->pdev); - edac_mc_free(mci); + spin_unlock_irqrestore(&ghes_lock, flags); + + if (!mci) + goto unlock; + + mci = edac_mc_del_mc(mci->pdev); + if (mci) + edac_mc_free(mci); + +unlock: + mutex_unlock(&ghes_reg_mutex); } diff --git a/drivers/extcon/extcon-sm5502.c b/drivers/extcon/extcon-sm5502.c index dc43847ad2b0..b3d93baf4fc5 100644 --- a/drivers/extcon/extcon-sm5502.c +++ b/drivers/extcon/extcon-sm5502.c @@ -65,6 +65,10 @@ struct sm5502_muic_info { /* Default value of SM5502 register to bring up MUIC device. */ static struct reg_data sm5502_reg_data[] = { { + .reg = SM5502_REG_RESET, + .val = SM5502_REG_RESET_MASK, + .invert = true, + }, { .reg = SM5502_REG_CONTROL, .val = SM5502_REG_CONTROL_MASK_INT_MASK, .invert = false, diff --git a/drivers/extcon/extcon-sm5502.h b/drivers/extcon/extcon-sm5502.h index 9dbb634d213b..ce1f1ec310c4 100644 --- a/drivers/extcon/extcon-sm5502.h +++ b/drivers/extcon/extcon-sm5502.h @@ -237,6 +237,8 @@ enum sm5502_reg { #define DM_DP_SWITCH_UART ((DM_DP_CON_SWITCH_UART <hh_data + HH_DATA_OFF(sizeof(*h))); h->h_proto = type; memcpy(h->h_dest, neigh->ha, net->addr_len); - hh->hh_len = FWNET_HLEN; + + /* Pairs with the READ_ONCE() in neigh_resolve_output(), + * neigh_hh_output() and neigh_update_hhs(). + */ + smp_store_release(&hh->hh_len, FWNET_HLEN); return 0; } diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c index 92f843eaf1e0..7a30952b463d 100644 --- a/drivers/firmware/arm_scmi/bus.c +++ b/drivers/firmware/arm_scmi/bus.c @@ -135,8 +135,10 @@ scmi_device_create(struct device_node *np, struct device *parent, int protocol) return NULL; id = ida_simple_get(&scmi_bus_id, 1, 0, GFP_KERNEL); - if (id < 0) - goto free_mem; + if (id < 0) { + kfree(scmi_dev); + return NULL; + } scmi_dev->id = id; scmi_dev->protocol_id = protocol; @@ -154,8 +156,6 @@ scmi_device_create(struct device_node *np, struct device *parent, int protocol) put_dev: put_device(&scmi_dev->dev); ida_simple_remove(&scmi_bus_id, id); -free_mem: - kfree(scmi_dev); return NULL; } diff --git a/drivers/firmware/efi/earlycon.c b/drivers/firmware/efi/earlycon.c index c9a0efca17b0..d4077db6dc97 100644 --- a/drivers/firmware/efi/earlycon.c +++ b/drivers/firmware/efi/earlycon.c @@ -13,18 +13,57 @@ #include +static const struct console *earlycon_console __initdata; static const struct font_desc *font; static u32 efi_x, efi_y; static u64 fb_base; static pgprot_t fb_prot; +static void *efi_fb; + +/* + * EFI earlycon needs to use early_memremap() to map the framebuffer. + * But early_memremap() is not usable for 'earlycon=efifb keep_bootcon', + * memremap() should be used instead. memremap() will be available after + * paging_init() which is earlier than initcall callbacks. Thus adding this + * early initcall function early_efi_map_fb() to map the whole EFI framebuffer. + */ +static int __init efi_earlycon_remap_fb(void) +{ + /* bail if there is no bootconsole or it has been disabled already */ + if (!earlycon_console || !(earlycon_console->flags & CON_ENABLED)) + return 0; + + if (pgprot_val(fb_prot) == pgprot_val(PAGE_KERNEL)) + efi_fb = memremap(fb_base, screen_info.lfb_size, MEMREMAP_WB); + else + efi_fb = memremap(fb_base, screen_info.lfb_size, MEMREMAP_WC); + + return efi_fb ? 0 : -ENOMEM; +} +early_initcall(efi_earlycon_remap_fb); + +static int __init efi_earlycon_unmap_fb(void) +{ + /* unmap the bootconsole fb unless keep_bootcon has left it enabled */ + if (efi_fb && !(earlycon_console->flags & CON_ENABLED)) + memunmap(efi_fb); + return 0; +} +late_initcall(efi_earlycon_unmap_fb); static __ref void *efi_earlycon_map(unsigned long start, unsigned long len) { + if (efi_fb) + return efi_fb + start; + return early_memremap_prot(fb_base + start, len, pgprot_val(fb_prot)); } static __ref void efi_earlycon_unmap(void *addr, unsigned long len) { + if (efi_fb) + return; + early_memunmap(addr, len); } @@ -201,6 +240,7 @@ static int __init efi_earlycon_setup(struct earlycon_device *device, efi_earlycon_scroll_up(); device->con->write = efi_earlycon_write; + earlycon_console = device->con; return 0; } EARLYCON_DECLARE(efifb, efi_earlycon_setup); diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index e98bbf8e56d9..34d41f67b54d 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -970,6 +970,24 @@ static int __init efi_memreserve_map_root(void) return 0; } +static int efi_mem_reserve_iomem(phys_addr_t addr, u64 size) +{ + struct resource *res, *parent; + + res = kzalloc(sizeof(struct resource), GFP_ATOMIC); + if (!res) + return -ENOMEM; + + res->name = "reserved"; + res->flags = IORESOURCE_MEM; + res->start = addr; + res->end = addr + size - 1; + + /* we expect a conflict with a 'System RAM' region */ + parent = request_resource_conflict(&iomem_resource, res); + return parent ? request_resource(parent, res) : 0; +} + int __ref efi_mem_reserve_persistent(phys_addr_t addr, u64 size) { struct linux_efi_memreserve *rsv; @@ -994,7 +1012,7 @@ int __ref efi_mem_reserve_persistent(phys_addr_t addr, u64 size) rsv->entry[index].size = size; memunmap(rsv); - return 0; + return efi_mem_reserve_iomem(addr, size); } memunmap(rsv); } @@ -1004,6 +1022,12 @@ int __ref efi_mem_reserve_persistent(phys_addr_t addr, u64 size) if (!rsv) return -ENOMEM; + rc = efi_mem_reserve_iomem(__pa(rsv), SZ_4K); + if (rc) { + free_page((unsigned long)rsv); + return rc; + } + /* * The memremap() call above assumes that a linux_efi_memreserve entry * never crosses a page boundary, so let's ensure that this remains true @@ -1020,7 +1044,7 @@ int __ref efi_mem_reserve_persistent(phys_addr_t addr, u64 size) efi_memreserve_root->next = __pa(rsv); spin_unlock(&efi_mem_reserve_persistent_lock); - return 0; + return efi_mem_reserve_iomem(addr, size); } static int __init efi_memreserve_root_init(void) diff --git a/drivers/firmware/efi/libstub/gop.c b/drivers/firmware/efi/libstub/gop.c index 0101ca4c13b1..b7bf1e993b8b 100644 --- a/drivers/firmware/efi/libstub/gop.c +++ b/drivers/firmware/efi/libstub/gop.c @@ -83,30 +83,6 @@ setup_pixel_info(struct screen_info *si, u32 pixels_per_scan_line, } } -static efi_status_t -__gop_query32(efi_system_table_t *sys_table_arg, - struct efi_graphics_output_protocol_32 *gop32, - struct efi_graphics_output_mode_info **info, - unsigned long *size, u64 *fb_base) -{ - struct efi_graphics_output_protocol_mode_32 *mode; - efi_graphics_output_protocol_query_mode query_mode; - efi_status_t status; - unsigned long m; - - m = gop32->mode; - mode = (struct efi_graphics_output_protocol_mode_32 *)m; - query_mode = (void *)(unsigned long)gop32->query_mode; - - status = __efi_call_early(query_mode, (void *)gop32, mode->mode, size, - info); - if (status != EFI_SUCCESS) - return status; - - *fb_base = mode->frame_buffer_base; - return status; -} - static efi_status_t setup_gop32(efi_system_table_t *sys_table_arg, struct screen_info *si, efi_guid_t *proto, unsigned long size, void **gop_handle) @@ -119,7 +95,7 @@ setup_gop32(efi_system_table_t *sys_table_arg, struct screen_info *si, u64 fb_base; struct efi_pixel_bitmask pixel_info; int pixel_format; - efi_status_t status = EFI_NOT_FOUND; + efi_status_t status; u32 *handles = (u32 *)(unsigned long)gop_handle; int i; @@ -128,6 +104,7 @@ setup_gop32(efi_system_table_t *sys_table_arg, struct screen_info *si, nr_gops = size / sizeof(u32); for (i = 0; i < nr_gops; i++) { + struct efi_graphics_output_protocol_mode_32 *mode; struct efi_graphics_output_mode_info *info = NULL; efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID; bool conout_found = false; @@ -145,9 +122,11 @@ setup_gop32(efi_system_table_t *sys_table_arg, struct screen_info *si, if (status == EFI_SUCCESS) conout_found = true; - status = __gop_query32(sys_table_arg, gop32, &info, &size, - ¤t_fb_base); - if (status == EFI_SUCCESS && (!first_gop || conout_found) && + mode = (void *)(unsigned long)gop32->mode; + info = (void *)(unsigned long)mode->info; + current_fb_base = mode->frame_buffer_base; + + if ((!first_gop || conout_found) && info->pixel_format != PIXEL_BLT_ONLY) { /* * Systems that use the UEFI Console Splitter may @@ -175,7 +154,7 @@ setup_gop32(efi_system_table_t *sys_table_arg, struct screen_info *si, /* Did we find any GOPs? */ if (!first_gop) - goto out; + return EFI_NOT_FOUND; /* EFI framebuffer */ si->orig_video_isVGA = VIDEO_TYPE_EFI; @@ -197,32 +176,8 @@ setup_gop32(efi_system_table_t *sys_table_arg, struct screen_info *si, si->lfb_size = si->lfb_linelength * si->lfb_height; si->capabilities |= VIDEO_CAPABILITY_SKIP_QUIRKS; -out: - return status; -} - -static efi_status_t -__gop_query64(efi_system_table_t *sys_table_arg, - struct efi_graphics_output_protocol_64 *gop64, - struct efi_graphics_output_mode_info **info, - unsigned long *size, u64 *fb_base) -{ - struct efi_graphics_output_protocol_mode_64 *mode; - efi_graphics_output_protocol_query_mode query_mode; - efi_status_t status; - unsigned long m; - - m = gop64->mode; - mode = (struct efi_graphics_output_protocol_mode_64 *)m; - query_mode = (void *)(unsigned long)gop64->query_mode; - - status = __efi_call_early(query_mode, (void *)gop64, mode->mode, size, - info); - if (status != EFI_SUCCESS) - return status; - *fb_base = mode->frame_buffer_base; - return status; + return EFI_SUCCESS; } static efi_status_t @@ -237,7 +192,7 @@ setup_gop64(efi_system_table_t *sys_table_arg, struct screen_info *si, u64 fb_base; struct efi_pixel_bitmask pixel_info; int pixel_format; - efi_status_t status = EFI_NOT_FOUND; + efi_status_t status; u64 *handles = (u64 *)(unsigned long)gop_handle; int i; @@ -246,6 +201,7 @@ setup_gop64(efi_system_table_t *sys_table_arg, struct screen_info *si, nr_gops = size / sizeof(u64); for (i = 0; i < nr_gops; i++) { + struct efi_graphics_output_protocol_mode_64 *mode; struct efi_graphics_output_mode_info *info = NULL; efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID; bool conout_found = false; @@ -263,9 +219,11 @@ setup_gop64(efi_system_table_t *sys_table_arg, struct screen_info *si, if (status == EFI_SUCCESS) conout_found = true; - status = __gop_query64(sys_table_arg, gop64, &info, &size, - ¤t_fb_base); - if (status == EFI_SUCCESS && (!first_gop || conout_found) && + mode = (void *)(unsigned long)gop64->mode; + info = (void *)(unsigned long)mode->info; + current_fb_base = mode->frame_buffer_base; + + if ((!first_gop || conout_found) && info->pixel_format != PIXEL_BLT_ONLY) { /* * Systems that use the UEFI Console Splitter may @@ -293,7 +251,7 @@ setup_gop64(efi_system_table_t *sys_table_arg, struct screen_info *si, /* Did we find any GOPs? */ if (!first_gop) - goto out; + return EFI_NOT_FOUND; /* EFI framebuffer */ si->orig_video_isVGA = VIDEO_TYPE_EFI; @@ -315,8 +273,8 @@ setup_gop64(efi_system_table_t *sys_table_arg, struct screen_info *si, si->lfb_size = si->lfb_linelength * si->lfb_height; si->capabilities |= VIDEO_CAPABILITY_SKIP_QUIRKS; -out: - return status; + + return EFI_SUCCESS; } /* diff --git a/drivers/firmware/efi/rci2-table.c b/drivers/firmware/efi/rci2-table.c index 76b0c354a027..de1a9a1f9f14 100644 --- a/drivers/firmware/efi/rci2-table.c +++ b/drivers/firmware/efi/rci2-table.c @@ -81,6 +81,9 @@ static int __init efi_rci2_sysfs_init(void) struct kobject *tables_kobj; int ret = -ENOMEM; + if (rci2_table_phys == EFI_INVALID_TABLE_ADDR) + return 0; + rci2_base = memremap(rci2_table_phys, sizeof(struct rci2_table_global_hdr), MEMREMAP_WB); diff --git a/drivers/firmware/qcom_scm-64.c b/drivers/firmware/qcom_scm-64.c index 91d5ad7cf58b..25e0f60c759a 100644 --- a/drivers/firmware/qcom_scm-64.c +++ b/drivers/firmware/qcom_scm-64.c @@ -150,7 +150,7 @@ static int qcom_scm_call(struct device *dev, u32 svc_id, u32 cmd_id, kfree(args_virt); } - if (res->a0 < 0) + if ((long)res->a0 < 0) return qcom_scm_remap_error(res->a0); return 0; diff --git a/drivers/fsi/fsi-core.c b/drivers/fsi/fsi-core.c index 1f76740f33b6..9282239b4d95 100644 --- a/drivers/fsi/fsi-core.c +++ b/drivers/fsi/fsi-core.c @@ -544,6 +544,31 @@ static int fsi_slave_scan(struct fsi_slave *slave) return 0; } +static unsigned long aligned_access_size(size_t offset, size_t count) +{ + unsigned long offset_unit, count_unit; + + /* Criteria: + * + * 1. Access size must be less than or equal to the maximum access + * width or the highest power-of-two factor of offset + * 2. Access size must be less than or equal to the amount specified by + * count + * + * The access width is optimal if we can calculate 1 to be strictly + * equal while still satisfying 2. + */ + + /* Find 1 by the bottom bit of offset (with a 4 byte access cap) */ + offset_unit = BIT(__builtin_ctzl(offset | 4)); + + /* Find 2 by the top bit of count */ + count_unit = BIT(8 * sizeof(unsigned long) - 1 - __builtin_clzl(count)); + + /* Constrain the maximum access width to the minimum of both criteria */ + return BIT(__builtin_ctzl(offset_unit | count_unit)); +} + static ssize_t fsi_slave_sysfs_raw_read(struct file *file, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) @@ -559,8 +584,7 @@ static ssize_t fsi_slave_sysfs_raw_read(struct file *file, return -EINVAL; for (total_len = 0; total_len < count; total_len += read_len) { - read_len = min_t(size_t, count, 4); - read_len -= off & 0x3; + read_len = aligned_access_size(off, count - total_len); rc = fsi_slave_read(slave, off, buf + total_len, read_len); if (rc) @@ -587,8 +611,7 @@ static ssize_t fsi_slave_sysfs_raw_write(struct file *file, return -EINVAL; for (total_len = 0; total_len < count; total_len += write_len) { - write_len = min_t(size_t, count, 4); - write_len -= off & 0x3; + write_len = aligned_access_size(off, count - total_len); rc = fsi_slave_write(slave, off, buf + total_len, write_len); if (rc) diff --git a/drivers/gpio/gpio-lynxpoint.c b/drivers/gpio/gpio-lynxpoint.c index e9e47c0d5be7..490ce7bae25e 100644 --- a/drivers/gpio/gpio-lynxpoint.c +++ b/drivers/gpio/gpio-lynxpoint.c @@ -164,6 +164,12 @@ static int lp_irq_type(struct irq_data *d, unsigned type) value |= TRIG_SEL_BIT | INT_INV_BIT; outl(value, reg); + + if (type & IRQ_TYPE_EDGE_BOTH) + irq_set_handler_locked(d, handle_edge_irq); + else if (type & IRQ_TYPE_LEVEL_MASK) + irq_set_handler_locked(d, handle_level_irq); + spin_unlock_irqrestore(&lg->lock, flags); return 0; diff --git a/drivers/gpio/gpio-mpc8xxx.c b/drivers/gpio/gpio-mpc8xxx.c index 16a47de29c94..d72a3a5507b0 100644 --- a/drivers/gpio/gpio-mpc8xxx.c +++ b/drivers/gpio/gpio-mpc8xxx.c @@ -346,6 +346,7 @@ static int mpc8xxx_probe(struct platform_device *pdev) return -ENOMEM; gc = &mpc8xxx_gc->gc; + gc->parent = &pdev->dev; if (of_property_read_bool(np, "little-endian")) { ret = bgpio_init(gc, &pdev->dev, 4, @@ -377,7 +378,8 @@ static int mpc8xxx_probe(struct platform_device *pdev) * It's assumed that only a single type of gpio controller is available * on the current machine, so overwriting global data is fine. */ - mpc8xxx_irq_chip.irq_set_type = devtype->irq_set_type; + if (devtype->irq_set_type) + mpc8xxx_irq_chip.irq_set_type = devtype->irq_set_type; if (devtype->gpio_dir_out) gc->direction_output = devtype->gpio_dir_out; @@ -386,6 +388,9 @@ static int mpc8xxx_probe(struct platform_device *pdev) gc->to_irq = mpc8xxx_gpio_to_irq; + if (of_device_is_compatible(np, "fsl,qoriq-gpio")) + gc->write_reg(mpc8xxx_gc->regs + GPIO_IBE, 0xffffffff); + ret = gpiochip_add_data(gc, mpc8xxx_gc); if (ret) { pr_err("%pOF: GPIO chip registration failed with status %d\n", diff --git a/drivers/gpio/gpio-mxc.c b/drivers/gpio/gpio-mxc.c index 7907a8755866..c77d474185f3 100644 --- a/drivers/gpio/gpio-mxc.c +++ b/drivers/gpio/gpio-mxc.c @@ -411,6 +411,7 @@ static int mxc_gpio_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; struct mxc_gpio_port *port; + int irq_count; int irq_base; int err; @@ -426,9 +427,15 @@ static int mxc_gpio_probe(struct platform_device *pdev) if (IS_ERR(port->base)) return PTR_ERR(port->base); - port->irq_high = platform_get_irq(pdev, 1); - if (port->irq_high < 0) - port->irq_high = 0; + irq_count = platform_irq_count(pdev); + if (irq_count < 0) + return irq_count; + + if (irq_count > 1) { + port->irq_high = platform_get_irq(pdev, 1); + if (port->irq_high < 0) + port->irq_high = 0; + } port->irq = platform_get_irq(pdev, 0); if (port->irq < 0) diff --git a/drivers/gpio/gpio-xtensa.c b/drivers/gpio/gpio-xtensa.c index 43d3fa5f511a..0fb2211f9573 100644 --- a/drivers/gpio/gpio-xtensa.c +++ b/drivers/gpio/gpio-xtensa.c @@ -44,15 +44,14 @@ static inline unsigned long enable_cp(unsigned long *cpenable) unsigned long flags; local_irq_save(flags); - RSR_CPENABLE(*cpenable); - WSR_CPENABLE(*cpenable | BIT(XCHAL_CP_ID_XTIOP)); - + *cpenable = xtensa_get_sr(cpenable); + xtensa_set_sr(*cpenable | BIT(XCHAL_CP_ID_XTIOP), cpenable); return flags; } static inline void disable_cp(unsigned long flags, unsigned long cpenable) { - WSR_CPENABLE(cpenable); + xtensa_set_sr(cpenable, cpenable); local_irq_restore(flags); } diff --git a/drivers/gpio/gpio-zynq.c b/drivers/gpio/gpio-zynq.c index cd475ff4bcad..7835aad6d162 100644 --- a/drivers/gpio/gpio-zynq.c +++ b/drivers/gpio/gpio-zynq.c @@ -681,6 +681,8 @@ static void zynq_gpio_restore_context(struct zynq_gpio *gpio) unsigned int bank_num; for (bank_num = 0; bank_num < gpio->p_data->max_bank; bank_num++) { + writel_relaxed(ZYNQ_GPIO_IXR_DISABLE_ALL, gpio->base_addr + + ZYNQ_GPIO_INTDIS_OFFSET(bank_num)); writel_relaxed(gpio->context.datalsw[bank_num], gpio->base_addr + ZYNQ_GPIO_DATA_LSW_OFFSET(bank_num)); @@ -690,9 +692,6 @@ static void zynq_gpio_restore_context(struct zynq_gpio *gpio) writel_relaxed(gpio->context.dirm[bank_num], gpio->base_addr + ZYNQ_GPIO_DIRM_OFFSET(bank_num)); - writel_relaxed(gpio->context.int_en[bank_num], - gpio->base_addr + - ZYNQ_GPIO_INTEN_OFFSET(bank_num)); writel_relaxed(gpio->context.int_type[bank_num], gpio->base_addr + ZYNQ_GPIO_INTTYPE_OFFSET(bank_num)); @@ -702,6 +701,9 @@ static void zynq_gpio_restore_context(struct zynq_gpio *gpio) writel_relaxed(gpio->context.int_any[bank_num], gpio->base_addr + ZYNQ_GPIO_INTANY_OFFSET(bank_num)); + writel_relaxed(~(gpio->context.int_en[bank_num]), + gpio->base_addr + + ZYNQ_GPIO_INTEN_OFFSET(bank_num)); } } diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index 59ccfd24627d..1f98e988c0d3 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -21,11 +21,19 @@ #include "gpiolib.h" #include "gpiolib-acpi.h" +#define QUIRK_NO_EDGE_EVENTS_ON_BOOT 0x01l +#define QUIRK_NO_WAKEUP 0x02l + static int run_edge_events_on_boot = -1; module_param(run_edge_events_on_boot, int, 0444); MODULE_PARM_DESC(run_edge_events_on_boot, "Run edge _AEI event-handlers at boot: 0=no, 1=yes, -1=auto"); +static int honor_wakeup = -1; +module_param(honor_wakeup, int, 0444); +MODULE_PARM_DESC(honor_wakeup, + "Honor the ACPI wake-capable flag: 0=no, 1=yes, -1=auto"); + /** * struct acpi_gpio_event - ACPI GPIO event handler data * @@ -274,7 +282,7 @@ static acpi_status acpi_gpiochip_alloc_event(struct acpi_resource *ares, event->handle = evt_handle; event->handler = handler; event->irq = irq; - event->irq_is_wake = agpio->wake_capable == ACPI_WAKE_CAPABLE; + event->irq_is_wake = honor_wakeup && agpio->wake_capable == ACPI_WAKE_CAPABLE; event->pin = pin; event->desc = desc; @@ -1302,7 +1310,7 @@ static int acpi_gpio_handle_deferred_request_irqs(void) /* We must use _sync so that this runs after the first deferred_probe run */ late_initcall_sync(acpi_gpio_handle_deferred_request_irqs); -static const struct dmi_system_id run_edge_events_on_boot_blacklist[] = { +static const struct dmi_system_id gpiolib_acpi_quirks[] = { { /* * The Minix Neo Z83-4 has a micro-USB-B id-pin handler for @@ -1312,7 +1320,8 @@ static const struct dmi_system_id run_edge_events_on_boot_blacklist[] = { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "MINIX"), DMI_MATCH(DMI_PRODUCT_NAME, "Z83-4"), - } + }, + .driver_data = (void *)QUIRK_NO_EDGE_EVENTS_ON_BOOT, }, { /* @@ -1324,20 +1333,52 @@ static const struct dmi_system_id run_edge_events_on_boot_blacklist[] = { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Wortmann_AG"), DMI_MATCH(DMI_PRODUCT_NAME, "TERRA_PAD_1061"), - } + }, + .driver_data = (void *)QUIRK_NO_EDGE_EVENTS_ON_BOOT, + }, + { + /* + * Various HP X2 10 Cherry Trail models use an external + * embedded-controller connected via I2C + an ACPI GPIO + * event handler. The embedded controller generates various + * spurious wakeup events when suspended. So disable wakeup + * for its handler (it uses the only ACPI GPIO event handler). + * This breaks wakeup when opening the lid, the user needs + * to press the power-button to wakeup the system. The + * alternative is suspend simply not working, which is worse. + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "HP"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP x2 Detachable 10-p0XX"), + }, + .driver_data = (void *)QUIRK_NO_WAKEUP, }, {} /* Terminating entry */ }; static int acpi_gpio_setup_params(void) { + const struct dmi_system_id *id; + long quirks = 0; + + id = dmi_first_match(gpiolib_acpi_quirks); + if (id) + quirks = (long)id->driver_data; + if (run_edge_events_on_boot < 0) { - if (dmi_check_system(run_edge_events_on_boot_blacklist)) + if (quirks & QUIRK_NO_EDGE_EVENTS_ON_BOOT) run_edge_events_on_boot = 0; else run_edge_events_on_boot = 1; } + if (honor_wakeup < 0) { + if (quirks & QUIRK_NO_WAKEUP) + honor_wakeup = 0; + else + honor_wakeup = 1; + } + return 0; } diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c index 80ea49f570f4..43ffec3a6fbb 100644 --- a/drivers/gpio/gpiolib-of.c +++ b/drivers/gpio/gpiolib-of.c @@ -23,6 +23,29 @@ #include "gpiolib.h" #include "gpiolib-of.h" +/** + * of_gpio_spi_cs_get_count() - special GPIO counting for SPI + * Some elder GPIO controllers need special quirks. Currently we handle + * the Freescale GPIO controller with bindings that doesn't use the + * established "cs-gpios" for chip selects but instead rely on + * "gpios" for the chip select lines. If we detect this, we redirect + * the counting of "cs-gpios" to count "gpios" transparent to the + * driver. + */ +int of_gpio_spi_cs_get_count(struct device *dev, const char *con_id) +{ + struct device_node *np = dev->of_node; + + if (!IS_ENABLED(CONFIG_SPI_MASTER)) + return 0; + if (!con_id || strcmp(con_id, "cs")) + return 0; + if (!of_device_is_compatible(np, "fsl,spi") && + !of_device_is_compatible(np, "aeroflexgaisler,spictrl")) + return 0; + return of_gpio_named_count(np, "gpios"); +} + /* * This is used by external users of of_gpio_count() from * @@ -35,6 +58,10 @@ int of_gpio_get_count(struct device *dev, const char *con_id) char propname[32]; unsigned int i; + ret = of_gpio_spi_cs_get_count(dev, con_id); + if (ret > 0) + return ret; + for (i = 0; i < ARRAY_SIZE(gpio_suffixes); i++) { if (con_id) snprintf(propname, sizeof(propname), "%s-%s", diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 104ed299d5ea..3d9524a2abc4 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -220,6 +220,14 @@ int gpiod_get_direction(struct gpio_desc *desc) chip = gpiod_to_chip(desc); offset = gpio_chip_hwgpio(desc); + /* + * Open drain emulation using input mode may incorrectly report + * input here, fix that up. + */ + if (test_bit(FLAG_OPEN_DRAIN, &desc->flags) && + test_bit(FLAG_IS_OUT, &desc->flags)) + return 0; + if (!chip->get_direction) return -ENOTSUPP; @@ -4320,8 +4328,9 @@ static struct gpio_desc *gpiod_find(struct device *dev, const char *con_id, if (chip->ngpio <= p->chip_hwnum) { dev_err(dev, - "requested GPIO %d is out of range [0..%d] for chip %s\n", - idx, chip->ngpio, chip->label); + "requested GPIO %u (%u) is out of range [0..%u] for chip %s\n", + idx, p->chip_hwnum, chip->ngpio - 1, + chip->label); return ERR_PTR(-EINVAL); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index bd37df5dd6d0..d1e278e999ee 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -813,6 +813,7 @@ struct amdgpu_device { uint8_t *bios; uint32_t bios_size; struct amdgpu_bo *stolen_vga_memory; + struct amdgpu_bo *discovery_memory; uint32_t bios_scratch_reg_offset; uint32_t bios_scratch[AMDGPU_BIOS_NUM_SCRATCH]; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c index 5652cc72ed3a..81842ba8cd75 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c @@ -859,6 +859,9 @@ static int amdgpu_debugfs_test_ib(struct seq_file *m, void *data) struct amdgpu_device *adev = dev->dev_private; int r = 0, i; + /* Avoid accidently unparking the sched thread during GPU reset */ + mutex_lock(&adev->lock_reset); + /* hold on the scheduler */ for (i = 0; i < AMDGPU_MAX_RINGS; i++) { struct amdgpu_ring *ring = adev->rings[i]; @@ -884,6 +887,8 @@ static int amdgpu_debugfs_test_ib(struct seq_file *m, void *data) kthread_unpark(ring->sched.thread); } + mutex_unlock(&adev->lock_reset); + return 0; } @@ -1036,6 +1041,9 @@ static int amdgpu_debugfs_ib_preempt(void *data, u64 val) if (!fences) return -ENOMEM; + /* Avoid accidently unparking the sched thread during GPU reset */ + mutex_lock(&adev->lock_reset); + /* stop the scheduler */ kthread_park(ring->sched.thread); @@ -1075,6 +1083,8 @@ static int amdgpu_debugfs_ib_preempt(void *data, u64 val) /* restart the scheduler */ kthread_unpark(ring->sched.thread); + mutex_unlock(&adev->lock_reset); + ttm_bo_unlock_delayed_workqueue(&adev->mman.bdev, resched); if (fences) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index 1481899f86c1..71198c5318e1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -136,7 +136,7 @@ static int amdgpu_discovery_read_binary(struct amdgpu_device *adev, uint8_t *bin { uint32_t *p = (uint32_t *)binary; uint64_t vram_size = (uint64_t)RREG32(mmRCC_CONFIG_MEMSIZE) << 20; - uint64_t pos = vram_size - BINARY_MAX_SIZE; + uint64_t pos = vram_size - DISCOVERY_TMR_SIZE; unsigned long flags; while (pos < vram_size) { @@ -179,7 +179,7 @@ int amdgpu_discovery_init(struct amdgpu_device *adev) uint16_t checksum; int r; - adev->discovery = kzalloc(BINARY_MAX_SIZE, GFP_KERNEL); + adev->discovery = kzalloc(DISCOVERY_TMR_SIZE, GFP_KERNEL); if (!adev->discovery) return -ENOMEM; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h index 85b8c4d4d576..5a6693d7d269 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h @@ -24,6 +24,8 @@ #ifndef __AMDGPU_DISCOVERY__ #define __AMDGPU_DISCOVERY__ +#define DISCOVERY_TMR_SIZE (64 << 10) + int amdgpu_discovery_init(struct amdgpu_device *adev); void amdgpu_discovery_fini(struct amdgpu_device *adev); int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index b19157b19fa0..33a1099e2f33 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -145,7 +145,7 @@ int amdgpu_async_gfx_ring = 1; int amdgpu_mcbp = 0; int amdgpu_discovery = -1; int amdgpu_mes = 0; -int amdgpu_noretry = 1; +int amdgpu_noretry; struct amdgpu_mgpu_info mgpu_info = { .mutex = __MUTEX_INITIALIZER(mgpu_info.mutex), @@ -613,7 +613,7 @@ MODULE_PARM_DESC(mes, module_param_named(mes, amdgpu_mes, int, 0444); MODULE_PARM_DESC(noretry, - "Disable retry faults (0 = retry enabled, 1 = retry disabled (default))"); + "Disable retry faults (0 = retry enabled (default), 1 = retry disabled)"); module_param_named(noretry, amdgpu_noretry, int, 0644); #ifdef CONFIG_HSA_AMD diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h index b6e1d98ef01e..aef6c396bd58 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h @@ -77,6 +77,7 @@ struct amdgpu_gmc_fault { struct amdgpu_vmhub { uint32_t ctx0_ptb_addr_lo32; uint32_t ctx0_ptb_addr_hi32; + uint32_t vm_inv_eng0_sem; uint32_t vm_inv_eng0_req; uint32_t vm_inv_eng0_ack; uint32_t vm_context0_cntl; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 7289e1b4fb60..28361a9c5add 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -342,6 +342,67 @@ int amdgpu_bo_create_kernel(struct amdgpu_device *adev, return 0; } +/** + * amdgpu_bo_create_kernel_at - create BO for kernel use at specific location + * + * @adev: amdgpu device object + * @offset: offset of the BO + * @size: size of the BO + * @domain: where to place it + * @bo_ptr: used to initialize BOs in structures + * @cpu_addr: optional CPU address mapping + * + * Creates a kernel BO at a specific offset in the address space of the domain. + * + * Returns: + * 0 on success, negative error code otherwise. + */ +int amdgpu_bo_create_kernel_at(struct amdgpu_device *adev, + uint64_t offset, uint64_t size, uint32_t domain, + struct amdgpu_bo **bo_ptr, void **cpu_addr) +{ + struct ttm_operation_ctx ctx = { false, false }; + unsigned int i; + int r; + + offset &= PAGE_MASK; + size = ALIGN(size, PAGE_SIZE); + + r = amdgpu_bo_create_reserved(adev, size, PAGE_SIZE, domain, bo_ptr, + NULL, NULL); + if (r) + return r; + + /* + * Remove the original mem node and create a new one at the request + * position. + */ + for (i = 0; i < (*bo_ptr)->placement.num_placement; ++i) { + (*bo_ptr)->placements[i].fpfn = offset >> PAGE_SHIFT; + (*bo_ptr)->placements[i].lpfn = (offset + size) >> PAGE_SHIFT; + } + + ttm_bo_mem_put(&(*bo_ptr)->tbo, &(*bo_ptr)->tbo.mem); + r = ttm_bo_mem_space(&(*bo_ptr)->tbo, &(*bo_ptr)->placement, + &(*bo_ptr)->tbo.mem, &ctx); + if (r) + goto error; + + if (cpu_addr) { + r = amdgpu_bo_kmap(*bo_ptr, cpu_addr); + if (r) + goto error; + } + + amdgpu_bo_unreserve(*bo_ptr); + return 0; + +error: + amdgpu_bo_unreserve(*bo_ptr); + amdgpu_bo_unref(bo_ptr); + return r; +} + /** * amdgpu_bo_free_kernel - free BO for kernel use * diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h index 658f4c9779b7..4fcea23ee516 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h @@ -237,6 +237,9 @@ int amdgpu_bo_create_kernel(struct amdgpu_device *adev, unsigned long size, int align, u32 domain, struct amdgpu_bo **bo_ptr, u64 *gpu_addr, void **cpu_addr); +int amdgpu_bo_create_kernel_at(struct amdgpu_device *adev, + uint64_t offset, uint64_t size, uint32_t domain, + struct amdgpu_bo **bo_ptr, void **cpu_addr); void amdgpu_bo_free_kernel(struct amdgpu_bo **bo, u64 *gpu_addr, void **cpu_addr); int amdgpu_bo_kmap(struct amdgpu_bo *bo, void **ptr); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 016ea274b955..9c5cbc47edf1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -65,12 +65,6 @@ const char *ras_block_string[] = { /* inject address is 52 bits */ #define RAS_UMC_INJECT_ADDR_LIMIT (0x1ULL << 52) -static int amdgpu_ras_reserve_vram(struct amdgpu_device *adev, - uint64_t offset, uint64_t size, - struct amdgpu_bo **bo_ptr); -static int amdgpu_ras_release_vram(struct amdgpu_device *adev, - struct amdgpu_bo **bo_ptr); - static ssize_t amdgpu_ras_debugfs_read(struct file *f, char __user *buf, size_t size, loff_t *pos) { @@ -1214,75 +1208,6 @@ static void amdgpu_ras_do_recovery(struct work_struct *work) atomic_set(&ras->in_recovery, 0); } -static int amdgpu_ras_release_vram(struct amdgpu_device *adev, - struct amdgpu_bo **bo_ptr) -{ - /* no need to free it actually. */ - amdgpu_bo_free_kernel(bo_ptr, NULL, NULL); - return 0; -} - -/* reserve vram with size@offset */ -static int amdgpu_ras_reserve_vram(struct amdgpu_device *adev, - uint64_t offset, uint64_t size, - struct amdgpu_bo **bo_ptr) -{ - struct ttm_operation_ctx ctx = { false, false }; - struct amdgpu_bo_param bp; - int r = 0; - int i; - struct amdgpu_bo *bo; - - if (bo_ptr) - *bo_ptr = NULL; - memset(&bp, 0, sizeof(bp)); - bp.size = size; - bp.byte_align = PAGE_SIZE; - bp.domain = AMDGPU_GEM_DOMAIN_VRAM; - bp.flags = AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS | - AMDGPU_GEM_CREATE_NO_CPU_ACCESS; - bp.type = ttm_bo_type_kernel; - bp.resv = NULL; - - r = amdgpu_bo_create(adev, &bp, &bo); - if (r) - return -EINVAL; - - r = amdgpu_bo_reserve(bo, false); - if (r) - goto error_reserve; - - offset = ALIGN(offset, PAGE_SIZE); - for (i = 0; i < bo->placement.num_placement; ++i) { - bo->placements[i].fpfn = offset >> PAGE_SHIFT; - bo->placements[i].lpfn = (offset + size) >> PAGE_SHIFT; - } - - ttm_bo_mem_put(&bo->tbo, &bo->tbo.mem); - r = ttm_bo_mem_space(&bo->tbo, &bo->placement, &bo->tbo.mem, &ctx); - if (r) - goto error_pin; - - r = amdgpu_bo_pin_restricted(bo, - AMDGPU_GEM_DOMAIN_VRAM, - offset, - offset + size); - if (r) - goto error_pin; - - if (bo_ptr) - *bo_ptr = bo; - - amdgpu_bo_unreserve(bo); - return r; - -error_pin: - amdgpu_bo_unreserve(bo); -error_reserve: - amdgpu_bo_unref(&bo); - return r; -} - /* alloc/realloc bps array */ static int amdgpu_ras_realloc_eh_data_space(struct amdgpu_device *adev, struct ras_err_handler_data *data, int pages) @@ -1345,7 +1270,7 @@ int amdgpu_ras_reserve_bad_pages(struct amdgpu_device *adev) struct amdgpu_ras *con = amdgpu_ras_get_context(adev); struct ras_err_handler_data *data; uint64_t bp; - struct amdgpu_bo *bo; + struct amdgpu_bo *bo = NULL; int i; if (!con || !con->eh_data) @@ -1359,12 +1284,14 @@ int amdgpu_ras_reserve_bad_pages(struct amdgpu_device *adev) for (i = data->last_reserved; i < data->count; i++) { bp = data->bps[i].bp; - if (amdgpu_ras_reserve_vram(adev, bp << PAGE_SHIFT, - PAGE_SIZE, &bo)) + if (amdgpu_bo_create_kernel_at(adev, bp << PAGE_SHIFT, PAGE_SIZE, + AMDGPU_GEM_DOMAIN_VRAM, + &bo, NULL)) DRM_ERROR("RAS ERROR: reserve vram %llx fail\n", bp); data->bps[i].bo = bo; data->last_reserved = i + 1; + bo = NULL; } out: mutex_unlock(&con->recovery_lock); @@ -1390,7 +1317,7 @@ static int amdgpu_ras_release_bad_pages(struct amdgpu_device *adev) for (i = data->last_reserved - 1; i >= 0; i--) { bo = data->bps[i].bo; - amdgpu_ras_release_vram(adev, &bo); + amdgpu_bo_free_kernel(&bo, NULL, NULL); data->bps[i].bo = bo; data->last_reserved = i; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c index b66d29d5ffa2..b158230af8db 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c @@ -138,6 +138,7 @@ static void amdgpu_do_test_moves(struct amdgpu_device *adev) } dma_fence_put(fence); + fence = NULL; r = amdgpu_bo_kmap(vram_obj, &vram_map); if (r) { @@ -183,6 +184,7 @@ static void amdgpu_do_test_moves(struct amdgpu_device *adev) } dma_fence_put(fence); + fence = NULL; r = amdgpu_bo_kmap(gtt_obj[i], >t_map); if (r) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h index 77674a7b9616..91899d28fa72 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h @@ -170,7 +170,7 @@ TRACE_EVENT(amdgpu_cs_ioctl, __field(unsigned int, context) __field(unsigned int, seqno) __field(struct dma_fence *, fence) - __field(char *, ring_name) + __string(ring, to_amdgpu_ring(job->base.sched)->name) __field(u32, num_ibs) ), @@ -179,12 +179,12 @@ TRACE_EVENT(amdgpu_cs_ioctl, __assign_str(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job)) __entry->context = job->base.s_fence->finished.context; __entry->seqno = job->base.s_fence->finished.seqno; - __entry->ring_name = to_amdgpu_ring(job->base.sched)->name; + __assign_str(ring, to_amdgpu_ring(job->base.sched)->name) __entry->num_ibs = job->num_ibs; ), TP_printk("sched_job=%llu, timeline=%s, context=%u, seqno=%u, ring_name=%s, num_ibs=%u", __entry->sched_job_id, __get_str(timeline), __entry->context, - __entry->seqno, __entry->ring_name, __entry->num_ibs) + __entry->seqno, __get_str(ring), __entry->num_ibs) ); TRACE_EVENT(amdgpu_sched_run_job, @@ -195,7 +195,7 @@ TRACE_EVENT(amdgpu_sched_run_job, __string(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job)) __field(unsigned int, context) __field(unsigned int, seqno) - __field(char *, ring_name) + __string(ring, to_amdgpu_ring(job->base.sched)->name) __field(u32, num_ibs) ), @@ -204,12 +204,12 @@ TRACE_EVENT(amdgpu_sched_run_job, __assign_str(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job)) __entry->context = job->base.s_fence->finished.context; __entry->seqno = job->base.s_fence->finished.seqno; - __entry->ring_name = to_amdgpu_ring(job->base.sched)->name; + __assign_str(ring, to_amdgpu_ring(job->base.sched)->name) __entry->num_ibs = job->num_ibs; ), TP_printk("sched_job=%llu, timeline=%s, context=%u, seqno=%u, ring_name=%s, num_ibs=%u", __entry->sched_job_id, __get_str(timeline), __entry->context, - __entry->seqno, __entry->ring_name, __entry->num_ibs) + __entry->seqno, __get_str(ring), __entry->num_ibs) ); @@ -468,7 +468,7 @@ TRACE_EVENT(amdgpu_ib_pipe_sync, TP_PROTO(struct amdgpu_job *sched_job, struct dma_fence *fence), TP_ARGS(sched_job, fence), TP_STRUCT__entry( - __field(const char *,name) + __string(ring, sched_job->base.sched->name); __field(uint64_t, id) __field(struct dma_fence *, fence) __field(uint64_t, ctx) @@ -476,14 +476,14 @@ TRACE_EVENT(amdgpu_ib_pipe_sync, ), TP_fast_assign( - __entry->name = sched_job->base.sched->name; + __assign_str(ring, sched_job->base.sched->name) __entry->id = sched_job->base.id; __entry->fence = fence; __entry->ctx = fence->context; __entry->seqno = fence->seqno; ), TP_printk("job ring=%s, id=%llu, need pipe sync to fence=%p, context=%llu, seq=%u", - __entry->name, __entry->id, + __get_str(ring), __entry->id, __entry->fence, __entry->ctx, __entry->seqno) ); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index dff41d0a85fe..f15ded1ce905 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -35,6 +35,7 @@ #include #include #include +#include #include #include #include @@ -788,7 +789,7 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages) struct hmm_mirror *mirror = bo->mn ? &bo->mn->mirror : NULL; struct ttm_tt *ttm = bo->tbo.ttm; struct amdgpu_ttm_tt *gtt = (void *)ttm; - struct mm_struct *mm = gtt->usertask->mm; + struct mm_struct *mm; unsigned long start = gtt->userptr; struct vm_area_struct *vma; struct hmm_range *range; @@ -796,25 +797,14 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages) uint64_t *pfns; int r = 0; - if (!mm) /* Happens during process shutdown */ - return -ESRCH; - if (unlikely(!mirror)) { DRM_DEBUG_DRIVER("Failed to get hmm_mirror\n"); - r = -EFAULT; - goto out; + return -EFAULT; } - vma = find_vma(mm, start); - if (unlikely(!vma || start < vma->vm_start)) { - r = -EFAULT; - goto out; - } - if (unlikely((gtt->userflags & AMDGPU_GEM_USERPTR_ANONONLY) && - vma->vm_file)) { - r = -EPERM; - goto out; - } + mm = mirror->hmm->mmu_notifier.mm; + if (!mmget_not_zero(mm)) /* Happens during process shutdown */ + return -ESRCH; range = kzalloc(sizeof(*range), GFP_KERNEL); if (unlikely(!range)) { @@ -847,6 +837,17 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages) hmm_range_wait_until_valid(range, HMM_RANGE_DEFAULT_TIMEOUT); down_read(&mm->mmap_sem); + vma = find_vma(mm, start); + if (unlikely(!vma || start < vma->vm_start)) { + r = -EFAULT; + goto out_unlock; + } + if (unlikely((gtt->userflags & AMDGPU_GEM_USERPTR_ANONONLY) && + vma->vm_file)) { + r = -EPERM; + goto out_unlock; + } + r = hmm_range_fault(range, 0); up_read(&mm->mmap_sem); @@ -865,15 +866,19 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages) } gtt->range = range; + mmput(mm); return 0; +out_unlock: + up_read(&mm->mmap_sem); out_free_pfns: hmm_range_unregister(range); kvfree(pfns); out_free_ranges: kfree(range); out: + mmput(mm); return r; } @@ -1634,81 +1639,25 @@ static void amdgpu_ttm_fw_reserve_vram_fini(struct amdgpu_device *adev) */ static int amdgpu_ttm_fw_reserve_vram_init(struct amdgpu_device *adev) { - struct ttm_operation_ctx ctx = { false, false }; - struct amdgpu_bo_param bp; - int r = 0; - int i; - u64 vram_size = adev->gmc.visible_vram_size; - u64 offset = adev->fw_vram_usage.start_offset; - u64 size = adev->fw_vram_usage.size; - struct amdgpu_bo *bo; - - memset(&bp, 0, sizeof(bp)); - bp.size = adev->fw_vram_usage.size; - bp.byte_align = PAGE_SIZE; - bp.domain = AMDGPU_GEM_DOMAIN_VRAM; - bp.flags = AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED | - AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; - bp.type = ttm_bo_type_kernel; - bp.resv = NULL; + uint64_t vram_size = adev->gmc.visible_vram_size; + int r; + adev->fw_vram_usage.va = NULL; adev->fw_vram_usage.reserved_bo = NULL; - if (adev->fw_vram_usage.size > 0 && - adev->fw_vram_usage.size <= vram_size) { - - r = amdgpu_bo_create(adev, &bp, - &adev->fw_vram_usage.reserved_bo); - if (r) - goto error_create; - - r = amdgpu_bo_reserve(adev->fw_vram_usage.reserved_bo, false); - if (r) - goto error_reserve; - - /* remove the original mem node and create a new one at the - * request position - */ - bo = adev->fw_vram_usage.reserved_bo; - offset = ALIGN(offset, PAGE_SIZE); - for (i = 0; i < bo->placement.num_placement; ++i) { - bo->placements[i].fpfn = offset >> PAGE_SHIFT; - bo->placements[i].lpfn = (offset + size) >> PAGE_SHIFT; - } - - ttm_bo_mem_put(&bo->tbo, &bo->tbo.mem); - r = ttm_bo_mem_space(&bo->tbo, &bo->placement, - &bo->tbo.mem, &ctx); - if (r) - goto error_pin; - - r = amdgpu_bo_pin_restricted(adev->fw_vram_usage.reserved_bo, - AMDGPU_GEM_DOMAIN_VRAM, - adev->fw_vram_usage.start_offset, - (adev->fw_vram_usage.start_offset + - adev->fw_vram_usage.size)); - if (r) - goto error_pin; - r = amdgpu_bo_kmap(adev->fw_vram_usage.reserved_bo, - &adev->fw_vram_usage.va); - if (r) - goto error_kmap; - - amdgpu_bo_unreserve(adev->fw_vram_usage.reserved_bo); - } - return r; + if (adev->fw_vram_usage.size == 0 || + adev->fw_vram_usage.size > vram_size) + return 0; -error_kmap: - amdgpu_bo_unpin(adev->fw_vram_usage.reserved_bo); -error_pin: - amdgpu_bo_unreserve(adev->fw_vram_usage.reserved_bo); -error_reserve: - amdgpu_bo_unref(&adev->fw_vram_usage.reserved_bo); -error_create: - adev->fw_vram_usage.va = NULL; - adev->fw_vram_usage.reserved_bo = NULL; + return amdgpu_bo_create_kernel_at(adev, + adev->fw_vram_usage.start_offset, + adev->fw_vram_usage.size, + AMDGPU_GEM_DOMAIN_VRAM, + &adev->fw_vram_usage.reserved_bo, + &adev->fw_vram_usage.va); return r; } + /** * amdgpu_ttm_init - Init the memory management (ttm) as well as various * gtt/vram related fields. @@ -1781,6 +1730,20 @@ int amdgpu_ttm_init(struct amdgpu_device *adev) NULL, &stolen_vga_buf); if (r) return r; + + /* + * reserve one TMR (64K) memory at the top of VRAM which holds + * IP Discovery data and is protected by PSP. + */ + r = amdgpu_bo_create_kernel_at(adev, + adev->gmc.real_vram_size - DISCOVERY_TMR_SIZE, + DISCOVERY_TMR_SIZE, + AMDGPU_GEM_DOMAIN_VRAM, + &adev->discovery_memory, + NULL); + if (r) + return r; + DRM_INFO("amdgpu: %uM of VRAM memory ready\n", (unsigned) (adev->gmc.real_vram_size / (1024 * 1024))); @@ -1845,6 +1808,9 @@ void amdgpu_ttm_late_init(struct amdgpu_device *adev) void *stolen_vga_buf; /* return the VGA stolen memory (if any) back to VRAM */ amdgpu_bo_free_kernel(&adev->stolen_vga_memory, NULL, &stolen_vga_buf); + + /* return the IP Discovery TMR memory back to VRAM */ + amdgpu_bo_free_kernel(&adev->discovery_memory, NULL, NULL); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 5251352f5922..c7514f743409 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1034,10 +1034,8 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, bool need_ id->oa_base != job->oa_base || id->oa_size != job->oa_size); bool vm_flush_needed = job->vm_needs_flush; - bool pasid_mapping_needed = id->pasid != job->pasid || - !id->pasid_mapping || - !dma_fence_is_signaled(id->pasid_mapping); struct dma_fence *fence = NULL; + bool pasid_mapping_needed = false; unsigned patch_offset = 0; int r; @@ -1047,6 +1045,12 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, bool need_ pasid_mapping_needed = true; } + mutex_lock(&id_mgr->lock); + if (id->pasid != job->pasid || !id->pasid_mapping || + !dma_fence_is_signaled(id->pasid_mapping)) + pasid_mapping_needed = true; + mutex_unlock(&id_mgr->lock); + gds_switch_needed &= !!ring->funcs->emit_gds_switch; vm_flush_needed &= !!ring->funcs->emit_vm_flush && job->vm_pd_addr != AMDGPU_BO_INVALID_OFFSET; @@ -1086,9 +1090,11 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, bool need_ } if (pasid_mapping_needed) { + mutex_lock(&id_mgr->lock); id->pasid = job->pasid; dma_fence_put(id->pasid_mapping); id->pasid_mapping = dma_fence_get(fence); + mutex_unlock(&id_mgr->lock); } dma_fence_put(fence); diff --git a/drivers/gpu/drm/amd/amdgpu/df_v3_6.c b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c index 5850c8e34caa..97d11d792351 100644 --- a/drivers/gpu/drm/amd/amdgpu/df_v3_6.c +++ b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c @@ -261,23 +261,29 @@ static void df_v3_6_update_medium_grain_clock_gating(struct amdgpu_device *adev, { u32 tmp; - /* Put DF on broadcast mode */ - adev->df_funcs->enable_broadcast_mode(adev, true); - - if (enable && (adev->cg_flags & AMD_CG_SUPPORT_DF_MGCG)) { - tmp = RREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater); - tmp &= ~DF_PIE_AON0_DfGlobalClkGater__MGCGMode_MASK; - tmp |= DF_V3_6_MGCG_ENABLE_15_CYCLE_DELAY; - WREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater, tmp); - } else { - tmp = RREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater); - tmp &= ~DF_PIE_AON0_DfGlobalClkGater__MGCGMode_MASK; - tmp |= DF_V3_6_MGCG_DISABLE; - WREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater, tmp); - } + if (adev->cg_flags & AMD_CG_SUPPORT_DF_MGCG) { + /* Put DF on broadcast mode */ + adev->df_funcs->enable_broadcast_mode(adev, true); + + if (enable) { + tmp = RREG32_SOC15(DF, 0, + mmDF_PIE_AON0_DfGlobalClkGater); + tmp &= ~DF_PIE_AON0_DfGlobalClkGater__MGCGMode_MASK; + tmp |= DF_V3_6_MGCG_ENABLE_15_CYCLE_DELAY; + WREG32_SOC15(DF, 0, + mmDF_PIE_AON0_DfGlobalClkGater, tmp); + } else { + tmp = RREG32_SOC15(DF, 0, + mmDF_PIE_AON0_DfGlobalClkGater); + tmp &= ~DF_PIE_AON0_DfGlobalClkGater__MGCGMode_MASK; + tmp |= DF_V3_6_MGCG_DISABLE; + WREG32_SOC15(DF, 0, + mmDF_PIE_AON0_DfGlobalClkGater, tmp); + } - /* Exit broadcast mode */ - adev->df_funcs->enable_broadcast_mode(adev, false); + /* Exit broadcast mode */ + adev->df_funcs->enable_broadcast_mode(adev, false); + } } static void df_v3_6_get_clockgating_state(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 53090eae0082..596722e79a26 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -1785,27 +1785,52 @@ static void gfx_v10_0_enable_gui_idle_interrupt(struct amdgpu_device *adev, WREG32_SOC15(GC, 0, mmCP_INT_CNTL_RING0, tmp); } -static void gfx_v10_0_init_csb(struct amdgpu_device *adev) +static int gfx_v10_0_init_csb(struct amdgpu_device *adev) { + int r; + + if (adev->in_gpu_reset) { + r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, false); + if (r) + return r; + + r = amdgpu_bo_kmap(adev->gfx.rlc.clear_state_obj, + (void **)&adev->gfx.rlc.cs_ptr); + if (!r) { + adev->gfx.rlc.funcs->get_csb_buffer(adev, + adev->gfx.rlc.cs_ptr); + amdgpu_bo_kunmap(adev->gfx.rlc.clear_state_obj); + } + + amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj); + if (r) + return r; + } + /* csib */ WREG32_SOC15(GC, 0, mmRLC_CSIB_ADDR_HI, adev->gfx.rlc.clear_state_gpu_addr >> 32); WREG32_SOC15(GC, 0, mmRLC_CSIB_ADDR_LO, adev->gfx.rlc.clear_state_gpu_addr & 0xfffffffc); WREG32_SOC15(GC, 0, mmRLC_CSIB_LENGTH, adev->gfx.rlc.clear_state_size); + + return 0; } -static void gfx_v10_0_init_pg(struct amdgpu_device *adev) +static int gfx_v10_0_init_pg(struct amdgpu_device *adev) { int i; + int r; - gfx_v10_0_init_csb(adev); + r = gfx_v10_0_init_csb(adev); + if (r) + return r; for (i = 0; i < adev->num_vmhubs; i++) amdgpu_gmc_flush_gpu_tlb(adev, 0, i, 0); /* TODO: init power gating */ - return; + return 0; } void gfx_v10_0_rlc_stop(struct amdgpu_device *adev) @@ -1907,7 +1932,10 @@ static int gfx_v10_0_rlc_resume(struct amdgpu_device *adev) r = gfx_v10_0_wait_for_rlc_autoload_complete(adev); if (r) return r; - gfx_v10_0_init_pg(adev); + + r = gfx_v10_0_init_pg(adev); + if (r) + return r; /* enable RLC SRM */ gfx_v10_0_rlc_enable_srm(adev); @@ -1933,7 +1961,10 @@ static int gfx_v10_0_rlc_resume(struct amdgpu_device *adev) return r; } - gfx_v10_0_init_pg(adev); + r = gfx_v10_0_init_pg(adev); + if (r) + return r; + adev->gfx.rlc.funcs->start(adev); if (adev->firmware.load_type == AMDGPU_FW_LOAD_RLC_BACKDOOR_AUTO) { @@ -2400,7 +2431,7 @@ static int gfx_v10_0_wait_for_rlc_autoload_complete(struct amdgpu_device *adev) return 0; } -static void gfx_v10_0_cp_gfx_enable(struct amdgpu_device *adev, bool enable) +static int gfx_v10_0_cp_gfx_enable(struct amdgpu_device *adev, bool enable) { int i; u32 tmp = RREG32_SOC15(GC, 0, mmCP_ME_CNTL); @@ -2413,7 +2444,17 @@ static void gfx_v10_0_cp_gfx_enable(struct amdgpu_device *adev, bool enable) adev->gfx.gfx_ring[i].sched.ready = false; } WREG32_SOC15(GC, 0, mmCP_ME_CNTL, tmp); - udelay(50); + + for (i = 0; i < adev->usec_timeout; i++) { + if (RREG32_SOC15(GC, 0, mmCP_STAT) == 0) + break; + udelay(1); + } + + if (i >= adev->usec_timeout) + DRM_ERROR("failed to %s cp gfx\n", enable ? "unhalt" : "halt"); + + return 0; } static int gfx_v10_0_cp_gfx_load_pfp_microcode(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 87dd55e9d72b..cc88ba76a8d4 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -6184,7 +6184,23 @@ static void gfx_v8_0_ring_emit_fence_gfx(struct amdgpu_ring *ring, u64 addr, bool write64bit = flags & AMDGPU_FENCE_FLAG_64BIT; bool int_sel = flags & AMDGPU_FENCE_FLAG_INT; - /* EVENT_WRITE_EOP - flush caches, send int */ + /* Workaround for cache flush problems. First send a dummy EOP + * event down the pipe with seq one below. + */ + amdgpu_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE_EOP, 4)); + amdgpu_ring_write(ring, (EOP_TCL1_ACTION_EN | + EOP_TC_ACTION_EN | + EOP_TC_WB_ACTION_EN | + EVENT_TYPE(CACHE_FLUSH_AND_INV_TS_EVENT) | + EVENT_INDEX(5))); + amdgpu_ring_write(ring, addr & 0xfffffffc); + amdgpu_ring_write(ring, (upper_32_bits(addr) & 0xffff) | + DATA_SEL(1) | INT_SEL(0)); + amdgpu_ring_write(ring, lower_32_bits(seq - 1)); + amdgpu_ring_write(ring, upper_32_bits(seq - 1)); + + /* Then send the real EOP event down the pipe: + * EVENT_WRITE_EOP - flush caches, send int */ amdgpu_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE_EOP, 4)); amdgpu_ring_write(ring, (EOP_TCL1_ACTION_EN | EOP_TC_ACTION_EN | @@ -6926,7 +6942,7 @@ static const struct amdgpu_ring_funcs gfx_v8_0_ring_funcs_gfx = { 5 + /* COND_EXEC */ 7 + /* PIPELINE_SYNC */ VI_FLUSH_GPU_TLB_NUM_WREG * 5 + 9 + /* VM_FLUSH */ - 8 + /* FENCE for VM_FLUSH */ + 12 + /* FENCE for VM_FLUSH */ 20 + /* GDS switch */ 4 + /* double SWITCH_BUFFER, the first COND_EXEC jump to the place just @@ -6938,7 +6954,7 @@ static const struct amdgpu_ring_funcs gfx_v8_0_ring_funcs_gfx = { 31 + /* DE_META */ 3 + /* CNTX_CTRL */ 5 + /* HDP_INVL */ - 8 + 8 + /* FENCE x2 */ + 12 + 12 + /* FENCE x2 */ 2, /* SWITCH_BUFFER */ .emit_ib_size = 4, /* gfx_v8_0_ring_emit_ib_gfx */ .emit_ib = gfx_v8_0_ring_emit_ib_gfx, diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 97cf0b536873..ab4a0d8545dc 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -1038,17 +1038,10 @@ static void gfx_v9_0_check_if_need_gfxoff(struct amdgpu_device *adev) case CHIP_VEGA20: break; case CHIP_RAVEN: - /* Disable GFXOFF on original raven. There are combinations - * of sbios and platforms that are not stable. - */ - if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8)) - adev->pm.pp_feature &= ~PP_GFXOFF_MASK; - else if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8) - &&((adev->gfx.rlc_fw_version != 106 && - adev->gfx.rlc_fw_version < 531) || - (adev->gfx.rlc_fw_version == 53815) || - (adev->gfx.rlc_feature_version < 1) || - !adev->gfx.rlc.is_rlc_v2_1)) + if (!(adev->rev_id >= 0x8 || + adev->pdev->device == 0x15d8) && + (adev->pm.fw_version < 0x41e2b || /* not raven1 fresh */ + !adev->gfx.rlc.is_rlc_v2_1)) /* without rlc save restore ucodes */ adev->pm.pp_feature &= ~PP_GFXOFF_MASK; if (adev->pm.pp_feature & PP_GFXOFF_MASK) @@ -2930,7 +2923,8 @@ static void gfx_v9_0_init_pg(struct amdgpu_device *adev) * And it's needed by gfxoff feature. */ if (adev->gfx.rlc.is_rlc_v2_1) { - gfx_v9_1_init_rlc_save_restore_list(adev); + if (adev->asic_type == CHIP_VEGA12) + gfx_v9_1_init_rlc_save_restore_list(adev); gfx_v9_0_enable_save_restore_machine(adev); } diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c index 6ce37ce77d14..d6fbdc6c0548 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c @@ -365,6 +365,8 @@ void gfxhub_v1_0_init(struct amdgpu_device *adev) hub->ctx0_ptb_addr_hi32 = SOC15_REG_OFFSET(GC, 0, mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32); + hub->vm_inv_eng0_sem = + SOC15_REG_OFFSET(GC, 0, mmVM_INVALIDATE_ENG0_SEM); hub->vm_inv_eng0_req = SOC15_REG_OFFSET(GC, 0, mmVM_INVALIDATE_ENG0_REQ); hub->vm_inv_eng0_ack = diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c index db10640a3b2f..fbe06c13a09c 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c @@ -350,6 +350,8 @@ void gfxhub_v2_0_init(struct amdgpu_device *adev) hub->ctx0_ptb_addr_hi32 = SOC15_REG_OFFSET(GC, 0, mmGCVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32); + hub->vm_inv_eng0_sem = + SOC15_REG_OFFSET(GC, 0, mmGCVM_INVALIDATE_ENG0_SEM); hub->vm_inv_eng0_req = SOC15_REG_OFFSET(GC, 0, mmGCVM_INVALIDATE_ENG0_REQ); hub->vm_inv_eng0_ack = diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index 5c7d5f73f54f..a7ba4c6cf7a1 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -235,6 +235,29 @@ static void gmc_v10_0_flush_vm_hub(struct amdgpu_device *adev, uint32_t vmid, const unsigned eng = 17; unsigned int i; + spin_lock(&adev->gmc.invalidate_lock); + /* + * It may lose gpuvm invalidate acknowldege state across power-gating + * off cycle, add semaphore acquire before invalidation and semaphore + * release after invalidation to avoid entering power gated state + * to WA the Issue + */ + + /* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */ + if (vmhub == AMDGPU_MMHUB_0 || + vmhub == AMDGPU_MMHUB_1) { + for (i = 0; i < adev->usec_timeout; i++) { + /* a read return value of 1 means semaphore acuqire */ + tmp = RREG32_NO_KIQ(hub->vm_inv_eng0_sem + eng); + if (tmp & 0x1) + break; + udelay(1); + } + + if (i >= adev->usec_timeout) + DRM_ERROR("Timeout waiting for sem acquire in VM flush!\n"); + } + WREG32_NO_KIQ(hub->vm_inv_eng0_req + eng, tmp); /* @@ -254,6 +277,17 @@ static void gmc_v10_0_flush_vm_hub(struct amdgpu_device *adev, uint32_t vmid, udelay(1); } + /* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */ + if (vmhub == AMDGPU_MMHUB_0 || + vmhub == AMDGPU_MMHUB_1) + /* + * add semaphore release after invalidation, + * write with 0 means semaphore release + */ + WREG32_NO_KIQ(hub->vm_inv_eng0_sem + eng, 0); + + spin_unlock(&adev->gmc.invalidate_lock); + if (i < adev->usec_timeout) return; @@ -338,6 +372,20 @@ static uint64_t gmc_v10_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring, uint32_t req = gmc_v10_0_get_invalidate_req(vmid, 0); unsigned eng = ring->vm_inv_eng; + /* + * It may lose gpuvm invalidate acknowldege state across power-gating + * off cycle, add semaphore acquire before invalidation and semaphore + * release after invalidation to avoid entering power gated state + * to WA the Issue + */ + + /* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */ + if (ring->funcs->vmhub == AMDGPU_MMHUB_0 || + ring->funcs->vmhub == AMDGPU_MMHUB_1) + /* a read return value of 1 means semaphore acuqire */ + amdgpu_ring_emit_reg_wait(ring, + hub->vm_inv_eng0_sem + eng, 0x1, 0x1); + amdgpu_ring_emit_wreg(ring, hub->ctx0_ptb_addr_lo32 + (2 * vmid), lower_32_bits(pd_addr)); @@ -348,6 +396,15 @@ static uint64_t gmc_v10_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring, hub->vm_inv_eng0_ack + eng, req, 1 << vmid); + /* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */ + if (ring->funcs->vmhub == AMDGPU_MMHUB_0 || + ring->funcs->vmhub == AMDGPU_MMHUB_1) + /* + * add semaphore release after invalidation, + * write with 0 means semaphore release + */ + amdgpu_ring_emit_wreg(ring, hub->vm_inv_eng0_sem + eng, 0); + return pd_addr; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index f91337030dc0..d7caca042173 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -448,6 +448,24 @@ static uint32_t gmc_v9_0_get_invalidate_req(unsigned int vmid, return req; } +/** + * gmc_v9_0_use_invalidate_semaphore - judge whether to use semaphore + * + * @adev: amdgpu_device pointer + * @vmhub: vmhub type + * + */ +static bool gmc_v9_0_use_invalidate_semaphore(struct amdgpu_device *adev, + uint32_t vmhub) +{ + return ((vmhub == AMDGPU_MMHUB_0 || + vmhub == AMDGPU_MMHUB_1) && + (!amdgpu_sriov_vf(adev)) && + (!(adev->asic_type == CHIP_RAVEN && + adev->rev_id < 0x8 && + adev->pdev->device == 0x15d8))); +} + /* * GART * VMID 0 is the physical GPU addresses as used by the kernel. @@ -467,6 +485,7 @@ static uint32_t gmc_v9_0_get_invalidate_req(unsigned int vmid, static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid, uint32_t vmhub, uint32_t flush_type) { + bool use_semaphore = gmc_v9_0_use_invalidate_semaphore(adev, vmhub); const unsigned eng = 17; u32 j, tmp; struct amdgpu_vmhub *hub; @@ -491,6 +510,28 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid, } spin_lock(&adev->gmc.invalidate_lock); + + /* + * It may lose gpuvm invalidate acknowldege state across power-gating + * off cycle, add semaphore acquire before invalidation and semaphore + * release after invalidation to avoid entering power gated state + * to WA the Issue + */ + + /* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */ + if (use_semaphore) { + for (j = 0; j < adev->usec_timeout; j++) { + /* a read return value of 1 means semaphore acuqire */ + tmp = RREG32_NO_KIQ(hub->vm_inv_eng0_sem + eng); + if (tmp & 0x1) + break; + udelay(1); + } + + if (j >= adev->usec_timeout) + DRM_ERROR("Timeout waiting for sem acquire in VM flush!\n"); + } + WREG32_NO_KIQ(hub->vm_inv_eng0_req + eng, tmp); /* @@ -506,7 +547,17 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid, break; udelay(1); } + + /* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */ + if (use_semaphore) + /* + * add semaphore release after invalidation, + * write with 0 means semaphore release + */ + WREG32_NO_KIQ(hub->vm_inv_eng0_sem + eng, 0); + spin_unlock(&adev->gmc.invalidate_lock); + if (j < adev->usec_timeout) return; @@ -516,11 +567,25 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid, static uint64_t gmc_v9_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring, unsigned vmid, uint64_t pd_addr) { + bool use_semaphore = gmc_v9_0_use_invalidate_semaphore(ring->adev, ring->funcs->vmhub); struct amdgpu_device *adev = ring->adev; struct amdgpu_vmhub *hub = &adev->vmhub[ring->funcs->vmhub]; uint32_t req = gmc_v9_0_get_invalidate_req(vmid, 0); unsigned eng = ring->vm_inv_eng; + /* + * It may lose gpuvm invalidate acknowldege state across power-gating + * off cycle, add semaphore acquire before invalidation and semaphore + * release after invalidation to avoid entering power gated state + * to WA the Issue + */ + + /* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */ + if (use_semaphore) + /* a read return value of 1 means semaphore acuqire */ + amdgpu_ring_emit_reg_wait(ring, + hub->vm_inv_eng0_sem + eng, 0x1, 0x1); + amdgpu_ring_emit_wreg(ring, hub->ctx0_ptb_addr_lo32 + (2 * vmid), lower_32_bits(pd_addr)); @@ -531,6 +596,14 @@ static uint64_t gmc_v9_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring, hub->vm_inv_eng0_ack + eng, req, 1 << vmid); + /* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */ + if (use_semaphore) + /* + * add semaphore release after invalidation, + * write with 0 means semaphore release + */ + amdgpu_ring_emit_wreg(ring, hub->vm_inv_eng0_sem + eng, 0); + return pd_addr; } diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c index 04cd4b6f95d4..641f1258f08d 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c @@ -418,6 +418,8 @@ void mmhub_v1_0_init(struct amdgpu_device *adev) hub->ctx0_ptb_addr_hi32 = SOC15_REG_OFFSET(MMHUB, 0, mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32); + hub->vm_inv_eng0_sem = + SOC15_REG_OFFSET(MMHUB, 0, mmVM_INVALIDATE_ENG0_SEM); hub->vm_inv_eng0_req = SOC15_REG_OFFSET(MMHUB, 0, mmVM_INVALIDATE_ENG0_REQ); hub->vm_inv_eng0_ack = diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c index b39bea6f54e9..096bb883c29d 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c @@ -341,6 +341,8 @@ void mmhub_v2_0_init(struct amdgpu_device *adev) hub->ctx0_ptb_addr_hi32 = SOC15_REG_OFFSET(MMHUB, 0, mmMMVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32); + hub->vm_inv_eng0_sem = + SOC15_REG_OFFSET(MMHUB, 0, mmMMVM_INVALIDATE_ENG0_SEM); hub->vm_inv_eng0_req = SOC15_REG_OFFSET(MMHUB, 0, mmMMVM_INVALIDATE_ENG0_REQ); hub->vm_inv_eng0_ack = diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c index 9ed178fa241c..fb161c83e409 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c @@ -502,6 +502,10 @@ void mmhub_v9_4_init(struct amdgpu_device *adev) SOC15_REG_OFFSET(MMHUB, 0, mmVML2VC0_VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32) + i * MMHUB_INSTANCE_REGISTER_OFFSET; + hub[i]->vm_inv_eng0_sem = + SOC15_REG_OFFSET(MMHUB, 0, + mmVML2VC0_VM_INVALIDATE_ENG0_SEM) + + i * MMHUB_INSTANCE_REGISTER_OFFSET; hub[i]->vm_inv_eng0_req = SOC15_REG_OFFSET(MMHUB, 0, mmVML2VC0_VM_INVALIDATE_ENG0_REQ) + diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c index 10166104b8a3..d483684db95b 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c @@ -398,6 +398,34 @@ static bool psp_v11_0_support_vmr_ring(struct psp_context *psp) return false; } +static int psp_v11_0_ring_stop(struct psp_context *psp, + enum psp_ring_type ring_type) +{ + int ret = 0; + struct amdgpu_device *adev = psp->adev; + + /* Write the ring destroy command*/ + if (psp_v11_0_support_vmr_ring(psp)) + WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_101, + GFX_CTRL_CMD_ID_DESTROY_GPCOM_RING); + else + WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_64, + GFX_CTRL_CMD_ID_DESTROY_RINGS); + + /* there might be handshake issue with hardware which needs delay */ + mdelay(20); + + /* Wait for response flag (bit 31) */ + if (psp_v11_0_support_vmr_ring(psp)) + ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_101), + 0x80000000, 0x80000000, false); + else + ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_64), + 0x80000000, 0x80000000, false); + + return ret; +} + static int psp_v11_0_ring_create(struct psp_context *psp, enum psp_ring_type ring_type) { @@ -407,6 +435,12 @@ static int psp_v11_0_ring_create(struct psp_context *psp, struct amdgpu_device *adev = psp->adev; if (psp_v11_0_support_vmr_ring(psp)) { + ret = psp_v11_0_ring_stop(psp, ring_type); + if (ret) { + DRM_ERROR("psp_v11_0_ring_stop_sriov failed!\n"); + return ret; + } + /* Write low address of the ring to C2PMSG_102 */ psp_ring_reg = lower_32_bits(ring->ring_mem_mc_addr); WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102, psp_ring_reg); @@ -451,33 +485,6 @@ static int psp_v11_0_ring_create(struct psp_context *psp, return ret; } -static int psp_v11_0_ring_stop(struct psp_context *psp, - enum psp_ring_type ring_type) -{ - int ret = 0; - struct amdgpu_device *adev = psp->adev; - - /* Write the ring destroy command*/ - if (psp_v11_0_support_vmr_ring(psp)) - WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_101, - GFX_CTRL_CMD_ID_DESTROY_GPCOM_RING); - else - WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_64, - GFX_CTRL_CMD_ID_DESTROY_RINGS); - - /* there might be handshake issue with hardware which needs delay */ - mdelay(20); - - /* Wait for response flag (bit 31) */ - if (psp_v11_0_support_vmr_ring(psp)) - ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_101), - 0x80000000, 0x80000000, false); - else - ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_64), - 0x80000000, 0x80000000, false); - - return ret; -} static int psp_v11_0_ring_destroy(struct psp_context *psp, enum psp_ring_type ring_type) diff --git a/drivers/gpu/drm/amd/amdgpu/si_ih.c b/drivers/gpu/drm/amd/amdgpu/si_ih.c index 57bb5f9e08b2..88ae27a5a03d 100644 --- a/drivers/gpu/drm/amd/amdgpu/si_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/si_ih.c @@ -64,7 +64,8 @@ static int si_ih_irq_init(struct amdgpu_device *adev) u32 interrupt_cntl, ih_cntl, ih_rb_cntl; si_ih_disable_interrupts(adev); - WREG32(INTERRUPT_CNTL2, adev->irq.ih.gpu_addr >> 8); + /* set dummy read address to dummy page address */ + WREG32(INTERRUPT_CNTL2, adev->dummy_page_addr >> 8); interrupt_cntl = RREG32(INTERRUPT_CNTL); interrupt_cntl &= ~IH_DUMMY_RD_OVERRIDE; interrupt_cntl &= ~IH_REQ_NONSNOOP_EN; diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.h b/drivers/gpu/drm/amd/amdgpu/soc15.h index a3dde0c31f57..a1d4ea69a284 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.h +++ b/drivers/gpu/drm/amd/amdgpu/soc15.h @@ -28,8 +28,8 @@ #include "nbio_v7_0.h" #include "nbio_v7_4.h" -#define SOC15_FLUSH_GPU_TLB_NUM_WREG 4 -#define SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT 1 +#define SOC15_FLUSH_GPU_TLB_NUM_WREG 6 +#define SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT 3 extern const struct amd_ip_funcs soc15_common_ip_funcs; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index d985e31fcc1e..f335f73919d1 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -1676,7 +1676,8 @@ static int allocate_hiq_sdma_mqd(struct device_queue_manager *dqm) struct kfd_dev *dev = dqm->dev; struct kfd_mem_obj *mem_obj = &dqm->hiq_sdma_mqd; uint32_t size = dqm->mqd_mgrs[KFD_MQD_TYPE_SDMA]->mqd_size * - dev->device_info->num_sdma_engines * + (dev->device_info->num_sdma_engines + + dev->device_info->num_xgmi_sdma_engines) * dev->device_info->num_sdma_queues_per_engine + dqm->mqd_mgrs[KFD_MQD_TYPE_HIQ]->mqd_size; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c b/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c index c56ac47cd318..bc47f6a44456 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c @@ -62,6 +62,11 @@ int kfd_interrupt_init(struct kfd_dev *kfd) } kfd->ih_wq = alloc_workqueue("KFD IH", WQ_HIGHPRI, 1); + if (unlikely(!kfd->ih_wq)) { + kfifo_free(&kfd->ih_fifo); + dev_err(kfd_chardev(), "Failed to allocate KFD IH workqueue\n"); + return -ENOMEM; + } spin_lock_init(&kfd->interrupt_lock); INIT_WORK(&kfd->interrupt_work, interrupt_wq); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 4139f129eafb..25b72eb76add 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -697,6 +697,9 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) if (amdgpu_dc_feature_mask & DC_MULTI_MON_PP_MCLK_SWITCH_MASK) init_data.flags.multi_mon_pp_mclk_switch = true; + if (amdgpu_dc_feature_mask & DC_DISABLE_FRACTIONAL_PWM_MASK) + init_data.flags.disable_fractional_pwm = true; + init_data.flags.power_down_display_on_boot = true; #ifdef CONFIG_DRM_AMD_DC_DCN2_0 @@ -940,6 +943,11 @@ static int dm_late_init(void *handle) params.backlight_lut_array_size = 16; params.backlight_lut_array = linear_lut; + /* Min backlight level after ABM reduction, Don't allow below 1% + * 0xFFFF x 0.01 = 0x28F + */ + params.min_abm_backlight = 0x28F; + /* todo will enable for navi10 */ if (adev->asic_type <= CHIP_RAVEN) { ret = dmcu_load_iram(dmcu, params); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c index f4cfa0caeba8..785322cd4c6c 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c @@ -342,7 +342,8 @@ bool dm_pp_get_clock_levels_by_type( if (adev->powerplay.pp_funcs && adev->powerplay.pp_funcs->get_clock_by_type) { if (adev->powerplay.pp_funcs->get_clock_by_type(pp_handle, dc_to_pp_clock_type(clk_type), &pp_clks)) { - /* Error in pplib. Provide default values. */ + /* Error in pplib. Provide default values. */ + get_default_clock_levels(clk_type, dc_clks); return true; } } else if (adev->smu.funcs && adev->smu.funcs->get_clock_by_type) { diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c index 3e8ac303bd52..23ec283eb07b 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c @@ -320,6 +320,8 @@ void dcn2_update_clocks_fpga(struct clk_mgr *clk_mgr, struct dc_state *context, bool safe_to_lower) { + struct clk_mgr_internal *clk_mgr_int = TO_CLK_MGR_INTERNAL(clk_mgr); + struct dc_clocks *new_clocks = &context->bw_ctx.bw.dcn.clk; /* Min fclk = 1.2GHz since all the extra scemi logic seems to run off of it */ int fclk_adj = new_clocks->fclk_khz > 1200000 ? new_clocks->fclk_khz : 1200000; @@ -357,14 +359,18 @@ void dcn2_update_clocks_fpga(struct clk_mgr *clk_mgr, clk_mgr->clks.dispclk_khz = new_clocks->dispclk_khz; } - /* Both fclk and dppclk ref are run on the same scemi clock so we - * need to keep the same value for both + /* Both fclk and ref_dppclk run on the same scemi clock. + * So take the higher value since the DPP DTO is typically programmed + * such that max dppclk is 1:1 with ref_dppclk. */ if (clk_mgr->clks.fclk_khz > clk_mgr->clks.dppclk_khz) clk_mgr->clks.dppclk_khz = clk_mgr->clks.fclk_khz; if (clk_mgr->clks.dppclk_khz > clk_mgr->clks.fclk_khz) clk_mgr->clks.fclk_khz = clk_mgr->clks.dppclk_khz; + // Both fclk and ref_dppclk run on the same scemi clock. + clk_mgr_int->dccg->ref_dppclk = clk_mgr->clks.fclk_khz; + dm_set_dcn_clocks(clk_mgr->ctx, &clk_mgr->clks); } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c index 50984c1811bb..468c6bb0e311 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c @@ -33,7 +33,7 @@ #include "mp/mp_12_0_0_sh_mask.h" #define REG(reg_name) \ - (MP1_BASE.instance[0].segment[mm ## reg_name ## _BASE_IDX] + mm ## reg_name) + (MP0_BASE.instance[0].segment[mm ## reg_name ## _BASE_IDX] + mm ## reg_name) #define FN(reg_name, field) \ FD(reg_name##__##field) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index ca20b150afcc..793aa8e8ec9a 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -373,7 +373,7 @@ bool dc_link_is_dp_sink_present(struct dc_link *link) if (GPIO_RESULT_OK != dal_ddc_open( ddc, GPIO_MODE_INPUT, GPIO_DDC_CONFIG_TYPE_MODE_I2C)) { - dal_gpio_destroy_ddc(&ddc); + dal_ddc_close(ddc); return present; } @@ -2169,8 +2169,10 @@ static void disable_link(struct dc_link *link, enum signal_type signal) dp_set_fec_ready(link, false); } #endif - } else - link->link_enc->funcs->disable_output(link->link_enc, signal); + } else { + if (signal != SIGNAL_TYPE_VIRTUAL) + link->link_enc->funcs->disable_output(link->link_enc, signal); + } if (signal == SIGNAL_TYPE_DISPLAY_PORT_MST) { /* MST disable link only when no stream use the link */ @@ -2217,7 +2219,7 @@ static bool dp_active_dongle_validate_timing( break; } - if (dongle_caps->dongle_type != DISPLAY_DONGLE_DP_HDMI_CONVERTER || + if (dpcd_caps->dongle_type != DISPLAY_DONGLE_DP_HDMI_CONVERTER || dongle_caps->extendedCapValid == false) return true; @@ -2767,6 +2769,15 @@ void core_link_enable_stream( CONTROLLER_DP_TEST_PATTERN_VIDEOMODE, COLOR_DEPTH_UNDEFINED); + /* This second call is needed to reconfigure the DIG + * as a workaround for the incorrect value being applied + * from transmitter control. + */ + if (!dc_is_virtual_signal(pipe_ctx->stream->signal)) + stream->link->link_enc->funcs->setup( + stream->link->link_enc, + pipe_ctx->stream->signal); + #ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT if (pipe_ctx->stream->timing.flags.DSC) { if (dc_is_dp_signal(pipe_ctx->stream->signal) || diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index f5742719b5d9..0ab890c927ec 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -2545,6 +2545,7 @@ static void get_active_converter_info( uint8_t data, struct dc_link *link) { union dp_downstream_port_present ds_port = { .byte = data }; + memset(&link->dpcd_caps.dongle_caps, 0, sizeof(link->dpcd_caps.dongle_caps)); /* decode converter info*/ if (!ds_port.fields.PORT_PRESENT) { @@ -2691,6 +2692,7 @@ static void dp_wa_power_up_0010FA(struct dc_link *link, uint8_t *dpcd_data, * keep receiver powered all the time.*/ case DP_BRANCH_DEVICE_ID_0010FA: case DP_BRANCH_DEVICE_ID_0080E1: + case DP_BRANCH_DEVICE_ID_00E04C: link->wa_flags.dp_keep_receiver_powered = true; break; @@ -3490,7 +3492,14 @@ void dp_set_fec_enable(struct dc_link *link, bool enable) if (link_enc->funcs->fec_set_enable && link->dpcd_caps.fec_cap.bits.FEC_CAPABLE) { if (link->fec_state == dc_link_fec_ready && enable) { - msleep(1); + /* Accord to DP spec, FEC enable sequence can first + * be transmitted anytime after 1000 LL codes have + * been transmitted on the link after link training + * completion. Using 1 lane RBR should have the maximum + * time for transmitting 1000 LL codes which is 6.173 us. + * So use 7 microseconds delay instead. + */ + udelay(7); link_enc->funcs->fec_set_enable(link_enc, true); link->fec_state = dc_link_fec_enabled; } else if (link->fec_state == dc_link_fec_enabled && !enable) { diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c index 79438c4f1e20..a519dbc5ecb6 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c @@ -277,7 +277,8 @@ void dp_retrain_link_dp_test(struct dc_link *link, if (pipes[i].stream != NULL && !pipes[i].top_pipe && !pipes[i].prev_odm_pipe && pipes[i].stream->link != NULL && - pipes[i].stream_res.stream_enc != NULL) { + pipes[i].stream_res.stream_enc != NULL && + pipes[i].stream->link == link) { udelay(100); pipes[i].stream_res.stream_enc->funcs->dp_blank( diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c index bf1d7bb90e0f..bb09243758fe 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c @@ -423,10 +423,10 @@ bool dc_stream_add_writeback(struct dc *dc, if (dwb->funcs->is_enabled(dwb)) { /* writeback pipe already enabled, only need to update */ - dc->hwss.update_writeback(dc, stream_status, wb_info); + dc->hwss.update_writeback(dc, stream_status, wb_info, dc->current_state); } else { /* Enable writeback pipe from scratch*/ - dc->hwss.enable_writeback(dc, stream_status, wb_info); + dc->hwss.enable_writeback(dc, stream_status, wb_info, dc->current_state); } } diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c b/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c index 58bd131d5b48..698b84acc44f 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c @@ -77,6 +77,9 @@ static bool dce_abm_set_pipe(struct abm *abm, uint32_t controller_id) /* notifyDMCUMsg */ REG_UPDATE(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, 1); + REG_WAIT(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, 0, + 1, 80000); + return true; } @@ -401,6 +404,10 @@ static bool dce_abm_init_backlight(struct abm *abm) /* Enable the backlight output */ REG_UPDATE(BL_PWM_CNTL, BL_PWM_EN, 1); + /* Disable fractional pwm if configured */ + REG_UPDATE(BL_PWM_CNTL, BL_PWM_FRACTIONAL_EN, + abm->ctx->dc->config.disable_fractional_pwm ? 0 : 1); + /* Unlock group 2 backlight registers */ REG_UPDATE(BL_PWM_GRP1_REG_LOCK, BL_PWM_GRP1_REG_LOCK, 0); diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index 1212da12c414..937a8ba81160 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1103,6 +1103,25 @@ void dcn20_pipe_control_lock( if (pipe->plane_state != NULL) flip_immediate = pipe->plane_state->flip_immediate; + if (flip_immediate && lock) { + const int TIMEOUT_FOR_FLIP_PENDING = 100000; + int i; + + for (i = 0; i < TIMEOUT_FOR_FLIP_PENDING; ++i) { + if (!pipe->plane_res.hubp->funcs->hubp_is_flip_pending(pipe->plane_res.hubp)) + break; + udelay(1); + } + + if (pipe->bottom_pipe != NULL) { + for (i = 0; i < TIMEOUT_FOR_FLIP_PENDING; ++i) { + if (!pipe->bottom_pipe->plane_res.hubp->funcs->hubp_is_flip_pending(pipe->bottom_pipe->plane_res.hubp)) + break; + udelay(1); + } + } + } + /* In flip immediate and pipe splitting case, we need to use GSL * for synchronization. Only do setup on locking and on flip type change. */ @@ -1337,7 +1356,8 @@ bool dcn20_update_bandwidth( static void dcn20_enable_writeback( struct dc *dc, const struct dc_stream_status *stream_status, - struct dc_writeback_info *wb_info) + struct dc_writeback_info *wb_info, + struct dc_state *context) { struct dwbc *dwb; struct mcif_wb *mcif_wb; @@ -1354,7 +1374,7 @@ static void dcn20_enable_writeback( optc->funcs->set_dwb_source(optc, wb_info->dwb_pipe_inst); /* set MCIF_WB buffer and arbitration configuration */ mcif_wb->funcs->config_mcif_buf(mcif_wb, &wb_info->mcif_buf_params, wb_info->dwb_params.dest_height); - mcif_wb->funcs->config_mcif_arb(mcif_wb, &dc->current_state->bw_ctx.bw.dcn.bw_writeback.mcif_wb_arb[wb_info->dwb_pipe_inst]); + mcif_wb->funcs->config_mcif_arb(mcif_wb, &context->bw_ctx.bw.dcn.bw_writeback.mcif_wb_arb[wb_info->dwb_pipe_inst]); /* Enable MCIF_WB */ mcif_wb->funcs->enable_mcif(mcif_wb); /* Enable DWB */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c index 2137e2be2140..dda90995ba93 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c @@ -287,6 +287,10 @@ void optc2_get_optc_source(struct timing_generator *optc, *num_of_src_opp = 2; else *num_of_src_opp = 1; + + /* Work around VBIOS not updating OPTC_NUM_OF_INPUT_SEGMENT */ + if (*src_opp_id_1 == 0xf) + *num_of_src_opp = 1; } void optc2_set_dwb_source(struct timing_generator *optc, diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index 6b2f2f1a1c9c..3b7769a3e67e 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -1419,13 +1419,20 @@ enum dc_status dcn20_build_mapped_resource(const struct dc *dc, struct dc_state static void acquire_dsc(struct resource_context *res_ctx, const struct resource_pool *pool, - struct display_stream_compressor **dsc) + struct display_stream_compressor **dsc, + int pipe_idx) { int i; ASSERT(*dsc == NULL); *dsc = NULL; + if (pool->res_cap->num_dsc == pool->res_cap->num_opp) { + *dsc = pool->dscs[pipe_idx]; + res_ctx->is_dsc_acquired[pipe_idx] = true; + return; + } + /* Find first free DSC */ for (i = 0; i < pool->res_cap->num_dsc; i++) if (!res_ctx->is_dsc_acquired[i]) { @@ -1468,7 +1475,7 @@ static enum dc_status add_dsc_to_stream_resource(struct dc *dc, if (pipe_ctx->stream != dc_stream) continue; - acquire_dsc(&dc_ctx->res_ctx, pool, &pipe_ctx->stream_res.dsc); + acquire_dsc(&dc_ctx->res_ctx, pool, &pipe_ctx->stream_res.dsc, i); /* The number of DSCs can be less than the number of pipes */ if (!pipe_ctx->stream_res.dsc) { @@ -1669,7 +1676,7 @@ static bool dcn20_split_stream_for_odm( next_odm_pipe->stream_res.opp = pool->opps[next_odm_pipe->pipe_idx]; #ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT if (next_odm_pipe->stream->timing.flags.DSC == 1) { - acquire_dsc(res_ctx, pool, &next_odm_pipe->stream_res.dsc); + acquire_dsc(res_ctx, pool, &next_odm_pipe->stream_res.dsc, next_odm_pipe->pipe_idx); ASSERT(next_odm_pipe->stream_res.dsc); if (next_odm_pipe->stream_res.dsc == NULL) return false; @@ -1765,7 +1772,7 @@ int dcn20_populate_dml_pipes_from_context( pipe_cnt = i; continue; } - if (!resource_are_streams_timing_synchronizable( + if (dc->debug.disable_timing_sync || !resource_are_streams_timing_synchronizable( res_ctx->pipe_ctx[pipe_cnt].stream, res_ctx->pipe_ctx[i].stream)) { synchronized_vblank = false; @@ -2474,6 +2481,7 @@ bool dcn20_fast_validate_bw( &context->res_ctx, dc->res_pool, pipe, hsplit_pipe)) goto validate_fail; + dcn20_build_mapped_resource(dc, context, pipe->stream); } else dcn20_split_stream_for_mpc( &context->res_ctx, dc->res_pool, @@ -3040,7 +3048,7 @@ static void cap_soc_clocks( static void update_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_st *bb, struct pp_smu_nv_clock_table *max_clocks, unsigned int *uclk_states, unsigned int num_states) { - struct _vcs_dpi_voltage_scaling_st calculated_states[MAX_CLOCK_LIMIT_STATES] = {0}; + struct _vcs_dpi_voltage_scaling_st calculated_states[MAX_CLOCK_LIMIT_STATES]; int i; int num_calculated_states = 0; int min_dcfclk = 0; @@ -3048,6 +3056,8 @@ static void update_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_ if (num_states == 0) return; + memset(calculated_states, 0, sizeof(calculated_states)); + if (dc->bb_overrides.min_dcfclk_mhz > 0) min_dcfclk = dc->bb_overrides.min_dcfclk_mhz; else diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c index 5ab9d6240498..e95025b1d14d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c @@ -492,15 +492,23 @@ void enc2_stream_encoder_dp_unblank( DP_VID_N_MUL, n_multiply); } - /* set DIG_START to 0x1 to reset FIFO */ + /* make sure stream is disabled before resetting steer fifo */ + REG_UPDATE(DP_VID_STREAM_CNTL, DP_VID_STREAM_ENABLE, false); + REG_WAIT(DP_VID_STREAM_CNTL, DP_VID_STREAM_STATUS, 0, 10, 5000); + /* set DIG_START to 0x1 to reset FIFO */ REG_UPDATE(DIG_FE_CNTL, DIG_START, 1); + udelay(1); /* write 0 to take the FIFO out of reset */ REG_UPDATE(DIG_FE_CNTL, DIG_START, 0); - /* switch DP encoder to CRTC data */ + /* switch DP encoder to CRTC data, but reset it the fifo first. It may happen + * that it overflows during mode transition, and sometimes doesn't recover. + */ + REG_UPDATE(DP_STEER_FIFO, DP_STEER_FIFO_RESET, 1); + udelay(10); REG_UPDATE(DP_STEER_FIFO, DP_STEER_FIFO_RESET, 0); diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c index d1266741763b..f5f6b4a0f0aa 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c @@ -22,6 +22,7 @@ * Authors: AMD * */ +#include #include "dm_services.h" #include "dcn20/dcn20_hubbub.h" #include "dcn21_hubbub.h" @@ -71,30 +72,39 @@ static uint32_t convert_and_clamp( void dcn21_dchvm_init(struct hubbub *hubbub) { struct dcn20_hubbub *hubbub1 = TO_DCN20_HUBBUB(hubbub); + uint32_t riommu_active; + int i; //Init DCHVM block REG_UPDATE(DCHVM_CTRL0, HOSTVM_INIT_REQ, 1); //Poll until RIOMMU_ACTIVE = 1 - //TODO: Figure out interval us and retry count - REG_WAIT(DCHVM_RIOMMU_STAT0, RIOMMU_ACTIVE, 1, 5, 100); + for (i = 0; i < 100; i++) { + REG_GET(DCHVM_RIOMMU_STAT0, RIOMMU_ACTIVE, &riommu_active); - //Reflect the power status of DCHUBBUB - REG_UPDATE(DCHVM_RIOMMU_CTRL0, HOSTVM_POWERSTATUS, 1); + if (riommu_active) + break; + else + udelay(5); + } + + if (riommu_active) { + //Reflect the power status of DCHUBBUB + REG_UPDATE(DCHVM_RIOMMU_CTRL0, HOSTVM_POWERSTATUS, 1); - //Start rIOMMU prefetching - REG_UPDATE(DCHVM_RIOMMU_CTRL0, HOSTVM_PREFETCH_REQ, 1); + //Start rIOMMU prefetching + REG_UPDATE(DCHVM_RIOMMU_CTRL0, HOSTVM_PREFETCH_REQ, 1); - // Enable dynamic clock gating - REG_UPDATE_4(DCHVM_CLK_CTRL, - HVM_DISPCLK_R_GATE_DIS, 0, - HVM_DISPCLK_G_GATE_DIS, 0, - HVM_DCFCLK_R_GATE_DIS, 0, - HVM_DCFCLK_G_GATE_DIS, 0); + // Enable dynamic clock gating + REG_UPDATE_4(DCHVM_CLK_CTRL, + HVM_DISPCLK_R_GATE_DIS, 0, + HVM_DISPCLK_G_GATE_DIS, 0, + HVM_DCFCLK_R_GATE_DIS, 0, + HVM_DCFCLK_G_GATE_DIS, 0); - //Poll until HOSTVM_PREFETCH_DONE = 1 - //TODO: Figure out interval us and retry count - REG_WAIT(DCHVM_RIOMMU_STAT0, HOSTVM_PREFETCH_DONE, 1, 5, 100); + //Poll until HOSTVM_PREFETCH_DONE = 1 + REG_WAIT(DCHVM_RIOMMU_STAT0, HOSTVM_PREFETCH_DONE, 1, 5, 100); + } } static int hubbub21_init_dchub(struct hubbub *hubbub, diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index de182185fe1f..b0e5e64df212 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -258,7 +258,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_1_soc = { .vmm_page_size_bytes = 4096, .dram_clock_change_latency_us = 23.84, .return_bus_width_bytes = 64, - .dispclk_dppclk_vco_speed_mhz = 3550, + .dispclk_dppclk_vco_speed_mhz = 3600, .xfc_bus_transport_time_us = 4, .xfc_xbuf_latency_tolerance_us = 4, .use_urgent_burst_bw = 1, diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h index 3a938cd414ea..f6cc2d6f576d 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h @@ -321,10 +321,12 @@ struct hw_sequencer_funcs { struct dc_state *context); void (*update_writeback)(struct dc *dc, const struct dc_stream_status *stream_status, - struct dc_writeback_info *wb_info); + struct dc_writeback_info *wb_info, + struct dc_state *context); void (*enable_writeback)(struct dc *dc, const struct dc_stream_status *stream_status, - struct dc_writeback_info *wb_info); + struct dc_writeback_info *wb_info, + struct dc_state *context); void (*disable_writeback)(struct dc *dc, unsigned int dwb_pipe_inst); #endif diff --git a/drivers/gpu/drm/amd/display/include/ddc_service_types.h b/drivers/gpu/drm/amd/display/include/ddc_service_types.h index 18961707db23..9ad49da50a17 100644 --- a/drivers/gpu/drm/amd/display/include/ddc_service_types.h +++ b/drivers/gpu/drm/amd/display/include/ddc_service_types.h @@ -31,6 +31,8 @@ #define DP_BRANCH_DEVICE_ID_0022B9 0x0022B9 #define DP_BRANCH_DEVICE_ID_00001A 0x00001A #define DP_BRANCH_DEVICE_ID_0080E1 0x0080e1 +#define DP_BRANCH_DEVICE_ID_90CC24 0x90CC24 +#define DP_BRANCH_DEVICE_ID_00E04C 0x00E04C enum ddc_result { DDC_RESULT_UNKNOWN = 0, diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c index ec70c9b12e1a..0978c698f0f8 100644 --- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c +++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c @@ -743,6 +743,10 @@ void mod_freesync_build_vrr_params(struct mod_freesync *mod_freesync, nominal_field_rate_in_uhz = mod_freesync_calc_nominal_field_rate(stream); + /* Rounded to the nearest Hz */ + nominal_field_rate_in_uhz = 1000000ULL * + div_u64(nominal_field_rate_in_uhz + 500000, 1000000); + min_refresh_in_uhz = in_config->min_refresh_in_uhz; max_refresh_in_uhz = in_config->max_refresh_in_uhz; @@ -996,14 +1000,13 @@ unsigned long long mod_freesync_calc_nominal_field_rate( const struct dc_stream_state *stream) { unsigned long long nominal_field_rate_in_uhz = 0; + unsigned int total = stream->timing.h_total * stream->timing.v_total; - /* Calculate nominal field rate for stream */ + /* Calculate nominal field rate for stream, rounded up to nearest integer */ nominal_field_rate_in_uhz = stream->timing.pix_clk_100hz / 10; nominal_field_rate_in_uhz *= 1000ULL * 1000ULL * 1000ULL; - nominal_field_rate_in_uhz = div_u64(nominal_field_rate_in_uhz, - stream->timing.h_total); - nominal_field_rate_in_uhz = div_u64(nominal_field_rate_in_uhz, - stream->timing.v_total); + + nominal_field_rate_in_uhz = div_u64(nominal_field_rate_in_uhz, total); return nominal_field_rate_in_uhz; } diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c index 05e2be856037..ba1aafe40512 100644 --- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c +++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c @@ -115,7 +115,7 @@ static const struct abm_parameters * const abm_settings[] = { /* NOTE: iRAM is 256B in size */ struct iram_table_v_2 { /* flags */ - uint16_t flags; /* 0x00 U16 */ + uint16_t min_abm_backlight; /* 0x00 U16 */ /* parameters for ABM2.0 algorithm */ uint8_t min_reduction[NUM_AMBI_LEVEL][NUM_AGGR_LEVEL]; /* 0x02 U0.8 */ @@ -140,10 +140,10 @@ struct iram_table_v_2 { /* For reading PSR State directly from IRAM */ uint8_t psr_state; /* 0xf0 */ - uint8_t dmcu_mcp_interface_version; /* 0xf1 */ - uint8_t dmcu_abm_feature_version; /* 0xf2 */ - uint8_t dmcu_psr_feature_version; /* 0xf3 */ - uint16_t dmcu_version; /* 0xf4 */ + uint8_t dmcu_mcp_interface_version; /* 0xf1 */ + uint8_t dmcu_abm_feature_version; /* 0xf2 */ + uint8_t dmcu_psr_feature_version; /* 0xf3 */ + uint16_t dmcu_version; /* 0xf4 */ uint8_t dmcu_state; /* 0xf6 */ uint16_t blRampReduction; /* 0xf7 */ @@ -164,42 +164,43 @@ struct iram_table_v_2_2 { uint8_t max_reduction[NUM_AMBI_LEVEL][NUM_AGGR_LEVEL]; /* 0x16 U0.8 */ uint8_t bright_pos_gain[NUM_AMBI_LEVEL][NUM_AGGR_LEVEL]; /* 0x2a U2.6 */ uint8_t dark_pos_gain[NUM_AMBI_LEVEL][NUM_AGGR_LEVEL]; /* 0x3e U2.6 */ - uint8_t hybrid_factor[NUM_AGGR_LEVEL]; /* 0x52 U0.8 */ - uint8_t contrast_factor[NUM_AGGR_LEVEL]; /* 0x56 U0.8 */ - uint8_t deviation_gain[NUM_AGGR_LEVEL]; /* 0x5a U0.8 */ - uint8_t iir_curve[NUM_AMBI_LEVEL]; /* 0x5e U0.8 */ - uint8_t min_knee[NUM_AGGR_LEVEL]; /* 0x63 U0.8 */ - uint8_t max_knee[NUM_AGGR_LEVEL]; /* 0x67 U0.8 */ - uint8_t pad[21]; /* 0x6b U0.8 */ + uint8_t hybrid_factor[NUM_AGGR_LEVEL]; /* 0x52 U0.8 */ + uint8_t contrast_factor[NUM_AGGR_LEVEL]; /* 0x56 U0.8 */ + uint8_t deviation_gain[NUM_AGGR_LEVEL]; /* 0x5a U0.8 */ + uint8_t iir_curve[NUM_AMBI_LEVEL]; /* 0x5e U0.8 */ + uint8_t min_knee[NUM_AGGR_LEVEL]; /* 0x63 U0.8 */ + uint8_t max_knee[NUM_AGGR_LEVEL]; /* 0x67 U0.8 */ + uint16_t min_abm_backlight; /* 0x6b U16 */ + uint8_t pad[19]; /* 0x6d U0.8 */ /* parameters for crgb conversion */ - uint16_t crgb_thresh[NUM_POWER_FN_SEGS]; /* 0x80 U3.13 */ - uint16_t crgb_offset[NUM_POWER_FN_SEGS]; /* 0x90 U1.15 */ - uint16_t crgb_slope[NUM_POWER_FN_SEGS]; /* 0xa0 U4.12 */ + uint16_t crgb_thresh[NUM_POWER_FN_SEGS]; /* 0x80 U3.13 */ + uint16_t crgb_offset[NUM_POWER_FN_SEGS]; /* 0x90 U1.15 */ + uint16_t crgb_slope[NUM_POWER_FN_SEGS]; /* 0xa0 U4.12 */ /* parameters for custom curve */ /* thresholds for brightness --> backlight */ - uint16_t backlight_thresholds[NUM_BL_CURVE_SEGS]; /* 0xb0 U16.0 */ + uint16_t backlight_thresholds[NUM_BL_CURVE_SEGS]; /* 0xb0 U16.0 */ /* offsets for brightness --> backlight */ - uint16_t backlight_offsets[NUM_BL_CURVE_SEGS]; /* 0xd0 U16.0 */ + uint16_t backlight_offsets[NUM_BL_CURVE_SEGS]; /* 0xd0 U16.0 */ /* For reading PSR State directly from IRAM */ - uint8_t psr_state; /* 0xf0 */ - uint8_t dmcu_mcp_interface_version; /* 0xf1 */ - uint8_t dmcu_abm_feature_version; /* 0xf2 */ - uint8_t dmcu_psr_feature_version; /* 0xf3 */ - uint16_t dmcu_version; /* 0xf4 */ - uint8_t dmcu_state; /* 0xf6 */ - - uint8_t dummy1; /* 0xf7 */ - uint8_t dummy2; /* 0xf8 */ - uint8_t dummy3; /* 0xf9 */ - uint8_t dummy4; /* 0xfa */ - uint8_t dummy5; /* 0xfb */ - uint8_t dummy6; /* 0xfc */ - uint8_t dummy7; /* 0xfd */ - uint8_t dummy8; /* 0xfe */ - uint8_t dummy9; /* 0xff */ + uint8_t psr_state; /* 0xf0 */ + uint8_t dmcu_mcp_interface_version; /* 0xf1 */ + uint8_t dmcu_abm_feature_version; /* 0xf2 */ + uint8_t dmcu_psr_feature_version; /* 0xf3 */ + uint16_t dmcu_version; /* 0xf4 */ + uint8_t dmcu_state; /* 0xf6 */ + + uint8_t dummy1; /* 0xf7 */ + uint8_t dummy2; /* 0xf8 */ + uint8_t dummy3; /* 0xf9 */ + uint8_t dummy4; /* 0xfa */ + uint8_t dummy5; /* 0xfb */ + uint8_t dummy6; /* 0xfc */ + uint8_t dummy7; /* 0xfd */ + uint8_t dummy8; /* 0xfe */ + uint8_t dummy9; /* 0xff */ }; #pragma pack(pop) @@ -271,7 +272,8 @@ void fill_iram_v_2(struct iram_table_v_2 *ram_table, struct dmcu_iram_parameters { unsigned int set = params.set; - ram_table->flags = 0x0; + ram_table->min_abm_backlight = + cpu_to_be16(params.min_abm_backlight); ram_table->deviation_gain = 0xb3; ram_table->blRampReduction = @@ -445,6 +447,9 @@ void fill_iram_v_2_2(struct iram_table_v_2_2 *ram_table, struct dmcu_iram_parame ram_table->flags = 0x0; + ram_table->min_abm_backlight = + cpu_to_be16(params.min_abm_backlight); + ram_table->deviation_gain[0] = 0xb3; ram_table->deviation_gain[1] = 0xa8; ram_table->deviation_gain[2] = 0x98; @@ -588,6 +593,10 @@ void fill_iram_v_2_3(struct iram_table_v_2_2 *ram_table, struct dmcu_iram_parame unsigned int set = params.set; ram_table->flags = 0x0; + + ram_table->min_abm_backlight = + cpu_to_be16(params.min_abm_backlight); + for (i = 0; i < NUM_AGGR_LEVEL; i++) { ram_table->hybrid_factor[i] = abm_settings[set][i].brightness_gain; ram_table->contrast_factor[i] = abm_settings[set][i].contrast_factor; diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.h b/drivers/gpu/drm/amd/display/modules/power/power_helpers.h index da5df00fedce..e54157026330 100644 --- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.h +++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.h @@ -38,6 +38,7 @@ struct dmcu_iram_parameters { unsigned int backlight_lut_array_size; unsigned int backlight_ramping_reduction; unsigned int backlight_ramping_start; + unsigned int min_abm_backlight; unsigned int set; }; diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h index 8889aaceec60..5450ed762b7a 100644 --- a/drivers/gpu/drm/amd/include/amd_shared.h +++ b/drivers/gpu/drm/amd/include/amd_shared.h @@ -143,6 +143,7 @@ enum PP_FEATURE_MASK { enum DC_FEATURE_MASK { DC_FBC_MASK = 0x1, DC_MULTI_MON_PP_MCLK_SWITCH_MASK = 0x2, + DC_DISABLE_FRACTIONAL_PWM_MASK = 0x4, }; enum amd_dpm_forced_level; diff --git a/drivers/gpu/drm/amd/include/discovery.h b/drivers/gpu/drm/amd/include/discovery.h index 5dcb776548d8..7ec4331e67f2 100644 --- a/drivers/gpu/drm/amd/include/discovery.h +++ b/drivers/gpu/drm/amd/include/discovery.h @@ -25,7 +25,6 @@ #define _DISCOVERY_H_ #define PSP_HEADER_SIZE 256 -#define BINARY_MAX_SIZE (64 << 10) #define BINARY_SIGNATURE 0x28211407 #define DISCOVERY_TABLE_SIGNATURE 0x53445049 diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c index 4acf139ea014..a066e9297777 100644 --- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c @@ -844,6 +844,7 @@ static int smu_sw_init(void *handle) smu->smu_baco.platform_support = false; mutex_init(&smu->sensor_lock); + mutex_init(&smu->metrics_lock); smu->watermarks_bitmap = 0; smu->power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT; @@ -1344,7 +1345,10 @@ static int smu_suspend(void *handle) int ret; struct amdgpu_device *adev = (struct amdgpu_device *)handle; struct smu_context *smu = &adev->smu; - bool baco_feature_is_enabled = smu_feature_is_enabled(smu, SMU_FEATURE_BACO_BIT); + bool baco_feature_is_enabled = false; + + if(!(adev->flags & AMD_IS_APU)) + baco_feature_is_enabled = smu_feature_is_enabled(smu, SMU_FEATURE_BACO_BIT); ret = smu_system_features_control(smu, false); if (ret) diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c index d493a3f8c07a..08a717a34bd6 100644 --- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c @@ -910,18 +910,21 @@ static int arcturus_get_metrics_table(struct smu_context *smu, struct smu_table_context *smu_table= &smu->smu_table; int ret = 0; + mutex_lock(&smu->metrics_lock); if (!smu_table->metrics_time || time_after(jiffies, smu_table->metrics_time + HZ / 1000)) { ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0, (void *)smu_table->metrics_table, false); if (ret) { pr_info("Failed to export SMU metrics table!\n"); + mutex_unlock(&smu->metrics_lock); return ret; } smu_table->metrics_time = jiffies; } memcpy(metrics_table, smu_table->metrics_table, sizeof(SmuMetrics_t)); + mutex_unlock(&smu->metrics_lock); return ret; } @@ -1388,12 +1391,17 @@ static int arcturus_get_power_profile_mode(struct smu_context *smu, "VR", "COMPUTE", "CUSTOM"}; + static const char *title[] = { + "PROFILE_INDEX(NAME)"}; uint32_t i, size = 0; int16_t workload_type = 0; if (!smu->pm_enabled || !buf) return -EINVAL; + size += sprintf(buf + size, "%16s\n", + title[0]); + for (i = 0; i <= PP_SMC_POWER_PROFILE_CUSTOM; i++) { /* * Conv PP_SMC_POWER_PROFILE* to WORKLOAD_PPLIB_*_BIT diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_baco.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_baco.c index df6ff9252401..b068d1c7b44d 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_baco.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_baco.c @@ -29,7 +29,7 @@ #include "vega20_baco.h" #include "vega20_smumgr.h" - +#include "amdgpu_ras.h" static const struct soc15_baco_cmd_entry clean_baco_tbl[] = { @@ -74,6 +74,7 @@ int vega20_baco_get_state(struct pp_hwmgr *hwmgr, enum BACO_STATE *state) int vega20_baco_set_state(struct pp_hwmgr *hwmgr, enum BACO_STATE state) { struct amdgpu_device *adev = (struct amdgpu_device *)(hwmgr->adev); + struct amdgpu_ras *ras = amdgpu_ras_get_context(adev); enum BACO_STATE cur_state; uint32_t data; @@ -84,10 +85,11 @@ int vega20_baco_set_state(struct pp_hwmgr *hwmgr, enum BACO_STATE state) return 0; if (state == BACO_STATE_IN) { - data = RREG32_SOC15(THM, 0, mmTHM_BACO_CNTL); - data |= 0x80000000; - WREG32_SOC15(THM, 0, mmTHM_BACO_CNTL, data); - + if (!ras || !ras->supported) { + data = RREG32_SOC15(THM, 0, mmTHM_BACO_CNTL); + data |= 0x80000000; + WREG32_SOC15(THM, 0, mmTHM_BACO_CNTL, data); + } if(smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_EnterBaco, 0)) return -EINVAL; diff --git a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h index 23171a4d9a31..5ad9a7878f6b 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h @@ -345,6 +345,7 @@ struct smu_context const struct pptable_funcs *ppt_funcs; struct mutex mutex; struct mutex sensor_lock; + struct mutex metrics_lock; uint64_t pool_size; struct smu_table_context smu_table; diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c index 328e258a6895..7d913a06ebac 100644 --- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c @@ -547,17 +547,20 @@ static int navi10_get_metrics_table(struct smu_context *smu, struct smu_table_context *smu_table= &smu->smu_table; int ret = 0; + mutex_lock(&smu->metrics_lock); if (!smu_table->metrics_time || time_after(jiffies, smu_table->metrics_time + msecs_to_jiffies(100))) { ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0, (void *)smu_table->metrics_table, false); if (ret) { pr_info("Failed to export SMU metrics table!\n"); + mutex_unlock(&smu->metrics_lock); return ret; } smu_table->metrics_time = jiffies; } memcpy(metrics_table, smu_table->metrics_table, sizeof(SmuMetrics_t)); + mutex_unlock(&smu->metrics_lock); return ret; } diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c index e62bfba51562..e5283dafc414 100644 --- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c @@ -183,11 +183,13 @@ static int renoir_print_clk_levels(struct smu_context *smu, int i, size = 0, ret = 0; uint32_t cur_value = 0, value = 0, count = 0, min = 0, max = 0; DpmClocks_t *clk_table = smu->smu_table.clocks_table; - SmuMetrics_t metrics = {0}; + SmuMetrics_t metrics; if (!clk_table || clk_type >= SMU_CLK_COUNT) return -EINVAL; + memset(&metrics, 0, sizeof(metrics)); + ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0, (void *)&metrics, false); if (ret) diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c index 92c393f613d3..3c3f719971f7 100644 --- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c @@ -1691,17 +1691,20 @@ static int vega20_get_metrics_table(struct smu_context *smu, struct smu_table_context *smu_table= &smu->smu_table; int ret = 0; + mutex_lock(&smu->metrics_lock); if (!smu_table->metrics_time || time_after(jiffies, smu_table->metrics_time + HZ / 1000)) { ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0, (void *)smu_table->metrics_table, false); if (ret) { pr_info("Failed to export SMU metrics table!\n"); + mutex_unlock(&smu->metrics_lock); return ret; } smu_table->metrics_time = jiffies; } memcpy(metrics_table, smu_table->metrics_table, sizeof(SmuMetrics_t)); + mutex_unlock(&smu->metrics_lock); return ret; } diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_crtc.c b/drivers/gpu/drm/arm/display/komeda/komeda_crtc.c index 624d257da20f..52c42569a111 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_crtc.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_crtc.c @@ -250,6 +250,7 @@ komeda_crtc_atomic_enable(struct drm_crtc *crtc, { komeda_crtc_prepare(to_kcrtc(crtc)); drm_crtc_vblank_on(crtc); + WARN_ON(drm_crtc_vblank_get(crtc)); komeda_crtc_do_flush(crtc, old); } @@ -319,6 +320,7 @@ komeda_crtc_atomic_disable(struct drm_crtc *crtc, } } + drm_crtc_vblank_put(crtc); drm_crtc_vblank_off(crtc); komeda_crtc_unprepare(kcrtc); } diff --git a/drivers/gpu/drm/arm/malidp_mw.c b/drivers/gpu/drm/arm/malidp_mw.c index 875a3a9eabfa..7d0e7b031e44 100644 --- a/drivers/gpu/drm/arm/malidp_mw.c +++ b/drivers/gpu/drm/arm/malidp_mw.c @@ -56,7 +56,7 @@ malidp_mw_connector_mode_valid(struct drm_connector *connector, return MODE_OK; } -const struct drm_connector_helper_funcs malidp_mw_connector_helper_funcs = { +static const struct drm_connector_helper_funcs malidp_mw_connector_helper_funcs = { .get_modes = malidp_mw_connector_get_modes, .mode_valid = malidp_mw_connector_mode_valid, }; diff --git a/drivers/gpu/drm/bridge/analogix-anx78xx.c b/drivers/gpu/drm/bridge/analogix-anx78xx.c index 3c7cc5af735c..56df07cdab68 100644 --- a/drivers/gpu/drm/bridge/analogix-anx78xx.c +++ b/drivers/gpu/drm/bridge/analogix-anx78xx.c @@ -715,7 +715,9 @@ static int anx78xx_init_pdata(struct anx78xx *anx78xx) /* 1.0V digital core power regulator */ pdata->dvdd10 = devm_regulator_get(dev, "dvdd10"); if (IS_ERR(pdata->dvdd10)) { - DRM_ERROR("DVDD10 regulator not found\n"); + if (PTR_ERR(pdata->dvdd10) != -EPROBE_DEFER) + DRM_ERROR("DVDD10 regulator not found\n"); + return PTR_ERR(pdata->dvdd10); } @@ -1332,7 +1334,9 @@ static int anx78xx_i2c_probe(struct i2c_client *client, err = anx78xx_init_pdata(anx78xx); if (err) { - DRM_ERROR("Failed to initialize pdata: %d\n", err); + if (err != -EPROBE_DEFER) + DRM_ERROR("Failed to initialize pdata: %d\n", err); + return err; } diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c index 521d689413c8..1326f2c734bf 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c @@ -36,6 +36,7 @@ #include "dw-hdmi-cec.h" #include "dw-hdmi.h" +#define DDC_CI_ADDR 0x37 #define DDC_SEGMENT_ADDR 0x30 #define HDMI_EDID_LEN 512 @@ -398,6 +399,15 @@ static int dw_hdmi_i2c_xfer(struct i2c_adapter *adap, u8 addr = msgs[0].addr; int i, ret = 0; + if (addr == DDC_CI_ADDR) + /* + * The internal I2C controller does not support the multi-byte + * read and write operations needed for DDC/CI. + * TOFIX: Blacklist the DDC/CI address until we filter out + * unsupported I2C operations. + */ + return -EOPNOTSUPP; + dev_dbg(hdmi->dev, "xfer: num: %d, addr: %#x\n", num, addr); for (i = 0; i < num; i++) { @@ -2023,7 +2033,7 @@ static int dw_hdmi_setup(struct dw_hdmi *hdmi, struct drm_display_mode *mode) /* HDMI Initialization Step E - Configure audio */ hdmi_clk_regenerator_update_pixel_clock(hdmi); - hdmi_enable_audio_clk(hdmi, true); + hdmi_enable_audio_clk(hdmi, hdmi->audio_enable); } /* not for DVI mode */ diff --git a/drivers/gpu/drm/drm_damage_helper.c b/drivers/gpu/drm/drm_damage_helper.c index 8230dac01a89..3a4126dc2520 100644 --- a/drivers/gpu/drm/drm_damage_helper.c +++ b/drivers/gpu/drm/drm_damage_helper.c @@ -212,8 +212,14 @@ int drm_atomic_helper_dirtyfb(struct drm_framebuffer *fb, drm_for_each_plane(plane, fb->dev) { struct drm_plane_state *plane_state; - if (plane->state->fb != fb) + ret = drm_modeset_lock(&plane->mutex, state->acquire_ctx); + if (ret) + goto out; + + if (plane->state->fb != fb) { + drm_modeset_unlock(&plane->mutex); continue; + } plane_state = drm_atomic_get_plane_state(state, plane); if (IS_ERR(plane_state)) { diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 82add736e17d..a48a4c21b1b3 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -339,7 +339,7 @@ static void drm_dp_encode_sideband_req(struct drm_dp_sideband_msg_req_body *req, memcpy(&buf[idx], req->u.i2c_read.transactions[i].bytes, req->u.i2c_read.transactions[i].num_bytes); idx += req->u.i2c_read.transactions[i].num_bytes; - buf[idx] = (req->u.i2c_read.transactions[i].no_stop_bit & 0x1) << 5; + buf[idx] = (req->u.i2c_read.transactions[i].no_stop_bit & 0x1) << 4; buf[idx] |= (req->u.i2c_read.transactions[i].i2c_transaction_delay & 0xf); idx++; } @@ -2465,9 +2465,11 @@ int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr) drm_dp_mst_topology_put_port(port); } - for (i = 0; i < mgr->max_payloads; i++) { - if (mgr->payloads[i].payload_state != DP_PAYLOAD_DELETE_LOCAL) + for (i = 0; i < mgr->max_payloads; /* do nothing */) { + if (mgr->payloads[i].payload_state != DP_PAYLOAD_DELETE_LOCAL) { + i++; continue; + } DRM_DEBUG_KMS("removing payload %d\n", i); for (j = i; j < mgr->max_payloads - 1; j++) { diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 6b0177112e18..3f50b8865db4 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -3722,7 +3722,7 @@ cea_db_offsets(const u8 *cea, int *start, int *end) if (*end < 4 || *end > 127) return -ERANGE; } else { - return -ENOTSUPP; + return -EOPNOTSUPP; } return 0; @@ -4191,7 +4191,7 @@ int drm_edid_to_sad(struct edid *edid, struct cea_sad **sads) if (cea_revision(cea) < 3) { DRM_DEBUG_KMS("SAD: wrong CEA revision\n"); - return -ENOTSUPP; + return -EOPNOTSUPP; } if (cea_db_offsets(cea, &start, &end)) { @@ -4252,7 +4252,7 @@ int drm_edid_to_speaker_allocation(struct edid *edid, u8 **sadb) if (cea_revision(cea) < 3) { DRM_DEBUG_KMS("SAD: wrong CEA revision\n"); - return -ENOTSUPP; + return -EOPNOTSUPP; } if (cea_db_offsets(cea, &start, &end)) { diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index a7ba5b4902d6..8d193a58363d 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -1320,7 +1320,7 @@ int drm_fb_helper_check_var(struct fb_var_screeninfo *var, * Changes struct fb_var_screeninfo are currently not pushed back * to KMS, hence fail if different settings are requested. */ - if (var->bits_per_pixel != fb->format->cpp[0] * 8 || + if (var->bits_per_pixel > fb->format->cpp[0] * 8 || var->xres > fb->width || var->yres > fb->height || var->xres_virtual > fb->width || var->yres_virtual > fb->height) { DRM_DEBUG("fb requested width/height/bpp can't fit in current fb " @@ -1345,6 +1345,11 @@ int drm_fb_helper_check_var(struct fb_var_screeninfo *var, drm_fb_helper_fill_pixel_fmt(var, fb->format->depth); } + /* + * Likewise, bits_per_pixel should be rounded up to a supported value. + */ + var->bits_per_pixel = fb->format->cpp[0] * 8; + /* * drm fbdev emulation doesn't support changing the pixel format at all, * so reject all pixel format changing requests. diff --git a/drivers/gpu/drm/drm_mipi_dbi.c b/drivers/gpu/drm/drm_mipi_dbi.c index 1961f713aaab..f8154316a3b0 100644 --- a/drivers/gpu/drm/drm_mipi_dbi.c +++ b/drivers/gpu/drm/drm_mipi_dbi.c @@ -955,7 +955,7 @@ static int mipi_dbi_typec1_command(struct mipi_dbi *dbi, u8 *cmd, int ret; if (mipi_dbi_command_is_read(dbi, *cmd)) - return -ENOTSUPP; + return -EOPNOTSUPP; MIPI_DBI_DEBUG_COMMAND(*cmd, parameters, num); @@ -1187,8 +1187,7 @@ static ssize_t mipi_dbi_debugfs_command_write(struct file *file, struct mipi_dbi_dev *dbidev = m->private; u8 val, cmd = 0, parameters[64]; char *buf, *pos, *token; - unsigned int i; - int ret, idx; + int i, ret, idx; if (!drm_dev_enter(&dbidev->drm, &idx)) return -ENODEV; diff --git a/drivers/gpu/drm/drm_property.c b/drivers/gpu/drm/drm_property.c index 892ce636ef72..6ee04803c362 100644 --- a/drivers/gpu/drm/drm_property.c +++ b/drivers/gpu/drm/drm_property.c @@ -561,7 +561,7 @@ drm_property_create_blob(struct drm_device *dev, size_t length, struct drm_property_blob *blob; int ret; - if (!length || length > ULONG_MAX - sizeof(struct drm_property_blob)) + if (!length || length > INT_MAX - sizeof(struct drm_property_blob)) return ERR_PTR(-EINVAL); blob = kvzalloc(sizeof(struct drm_property_blob)+length, GFP_KERNEL); diff --git a/drivers/gpu/drm/drm_vblank.c b/drivers/gpu/drm/drm_vblank.c index fd1fbc77871f..552ec82e9bc5 100644 --- a/drivers/gpu/drm/drm_vblank.c +++ b/drivers/gpu/drm/drm_vblank.c @@ -1581,7 +1581,7 @@ int drm_wait_vblank_ioctl(struct drm_device *dev, void *data, unsigned int flags, pipe, high_pipe; if (!dev->irq_enabled) - return -EINVAL; + return -EOPNOTSUPP; if (vblwait->request.type & _DRM_VBLANK_SIGNAL) return -EINVAL; @@ -1838,7 +1838,7 @@ int drm_crtc_get_sequence_ioctl(struct drm_device *dev, void *data, return -EOPNOTSUPP; if (!dev->irq_enabled) - return -EINVAL; + return -EOPNOTSUPP; crtc = drm_crtc_find(dev, file_priv, get_seq->crtc_id); if (!crtc) @@ -1896,7 +1896,7 @@ int drm_crtc_queue_sequence_ioctl(struct drm_device *dev, void *data, return -EOPNOTSUPP; if (!dev->irq_enabled) - return -EINVAL; + return -EOPNOTSUPP; crtc = drm_crtc_find(dev, file_priv, queue_seq->crtc_id); if (!crtc) diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c index 7ae087b0504d..88b6fcaa20be 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c @@ -1313,6 +1313,7 @@ static int gsc_remove(struct platform_device *pdev) { struct device *dev = &pdev->dev; + component_del(dev, &gsc_component_ops); pm_runtime_dont_use_autosuspend(dev); pm_runtime_disable(dev); diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c index bc1565f1822a..09aa73c0f2ad 100644 --- a/drivers/gpu/drm/exynos/exynos_hdmi.c +++ b/drivers/gpu/drm/exynos/exynos_hdmi.c @@ -852,6 +852,10 @@ static enum drm_connector_status hdmi_detect(struct drm_connector *connector, static void hdmi_connector_destroy(struct drm_connector *connector) { + struct hdmi_context *hdata = connector_to_hdmi(connector); + + cec_notifier_conn_unregister(hdata->notifier); + drm_connector_unregister(connector); drm_connector_cleanup(connector); } @@ -935,6 +939,7 @@ static int hdmi_create_connector(struct drm_encoder *encoder) { struct hdmi_context *hdata = encoder_to_hdmi(encoder); struct drm_connector *connector = &hdata->connector; + struct cec_connector_info conn_info; int ret; connector->interlace_allowed = true; @@ -957,6 +962,15 @@ static int hdmi_create_connector(struct drm_encoder *encoder) DRM_DEV_ERROR(hdata->dev, "Failed to attach bridge\n"); } + cec_fill_conn_info_from_drm(&conn_info, connector); + + hdata->notifier = cec_notifier_conn_register(hdata->dev, NULL, + &conn_info); + if (!hdata->notifier) { + ret = -ENOMEM; + DRM_DEV_ERROR(hdata->dev, "Failed to allocate CEC notifier\n"); + } + return ret; } @@ -1528,8 +1542,8 @@ static void hdmi_disable(struct drm_encoder *encoder) */ mutex_unlock(&hdata->mutex); cancel_delayed_work(&hdata->hotplug_work); - cec_notifier_set_phys_addr(hdata->notifier, - CEC_PHYS_ADDR_INVALID); + if (hdata->notifier) + cec_notifier_phys_addr_invalidate(hdata->notifier); return; } @@ -2006,12 +2020,6 @@ static int hdmi_probe(struct platform_device *pdev) } } - hdata->notifier = cec_notifier_get(&pdev->dev); - if (hdata->notifier == NULL) { - ret = -ENOMEM; - goto err_hdmiphy; - } - pm_runtime_enable(dev); audio_infoframe = &hdata->audio.infoframe; @@ -2023,7 +2031,7 @@ static int hdmi_probe(struct platform_device *pdev) ret = hdmi_register_audio_device(hdata); if (ret) - goto err_notifier_put; + goto err_rpm_disable; ret = component_add(&pdev->dev, &hdmi_component_ops); if (ret) @@ -2034,8 +2042,7 @@ static int hdmi_probe(struct platform_device *pdev) err_unregister_audio: platform_device_unregister(hdata->audio.pdev); -err_notifier_put: - cec_notifier_put(hdata->notifier); +err_rpm_disable: pm_runtime_disable(dev); err_hdmiphy: @@ -2054,12 +2061,10 @@ static int hdmi_remove(struct platform_device *pdev) struct hdmi_context *hdata = platform_get_drvdata(pdev); cancel_delayed_work_sync(&hdata->hotplug_work); - cec_notifier_set_phys_addr(hdata->notifier, CEC_PHYS_ADDR_INVALID); component_del(&pdev->dev, &hdmi_component_ops); platform_device_unregister(hdata->audio.pdev); - cec_notifier_put(hdata->notifier); pm_runtime_disable(&pdev->dev); if (!IS_ERR(hdata->reg_hdmi_en)) diff --git a/drivers/gpu/drm/gma500/oaktrail_crtc.c b/drivers/gpu/drm/gma500/oaktrail_crtc.c index 167c10767dd4..900e5499249d 100644 --- a/drivers/gpu/drm/gma500/oaktrail_crtc.c +++ b/drivers/gpu/drm/gma500/oaktrail_crtc.c @@ -129,6 +129,7 @@ static bool mrst_sdvo_find_best_pll(const struct gma_limit_t *limit, s32 freq_error, min_error = 100000; memset(best_clock, 0, sizeof(*best_clock)); + memset(&clock, 0, sizeof(clock)); for (clock.m = limit->m.min; clock.m <= limit->m.max; clock.m++) { for (clock.n = limit->n.min; clock.n <= limit->n.max; @@ -185,6 +186,7 @@ static bool mrst_lvds_find_best_pll(const struct gma_limit_t *limit, int err = target; memset(best_clock, 0, sizeof(*best_clock)); + memset(&clock, 0, sizeof(clock)); for (clock.m = limit->m.min; clock.m <= limit->m.max; clock.m++) { for (clock.p1 = limit->p1.min; clock.p1 <= limit->p1.max; diff --git a/drivers/gpu/drm/i810/i810_dma.c b/drivers/gpu/drm/i810/i810_dma.c index 2a77823b8e9a..e66c38332df4 100644 --- a/drivers/gpu/drm/i810/i810_dma.c +++ b/drivers/gpu/drm/i810/i810_dma.c @@ -728,7 +728,7 @@ static void i810_dma_dispatch_vertex(struct drm_device *dev, if (nbox > I810_NR_SAREA_CLIPRECTS) nbox = I810_NR_SAREA_CLIPRECTS; - if (used > 4 * 1024) + if (used < 0 || used > 4 * 1024) used = 0; if (sarea_priv->dirty) @@ -1048,7 +1048,7 @@ static void i810_dma_dispatch_mc(struct drm_device *dev, struct drm_buf *buf, in if (u != I810_BUF_CLIENT) DRM_DEBUG("MC found buffer that isn't mine!\n"); - if (used > 4 * 1024) + if (used < 0 || used > 4 * 1024) used = 0; sarea_priv->dirty = 0x7f; diff --git a/drivers/gpu/drm/i915/display/intel_audio.c b/drivers/gpu/drm/i915/display/intel_audio.c index ddcccf4408c3..0cf475f3063c 100644 --- a/drivers/gpu/drm/i915/display/intel_audio.c +++ b/drivers/gpu/drm/i915/display/intel_audio.c @@ -850,11 +850,23 @@ static unsigned long i915_audio_component_get_power(struct device *kdev) ret = intel_display_power_get(dev_priv, POWER_DOMAIN_AUDIO); - /* Force CDCLK to 2*BCLK as long as we need audio to be powered. */ - if (dev_priv->audio_power_refcount++ == 0) - if (IS_CANNONLAKE(dev_priv) || IS_GEMINILAKE(dev_priv)) + if (dev_priv->audio_power_refcount++ == 0) { + if (IS_TIGERLAKE(dev_priv) || IS_ICELAKE(dev_priv)) { + I915_WRITE(AUD_FREQ_CNTRL, dev_priv->audio_freq_cntrl); + DRM_DEBUG_KMS("restored AUD_FREQ_CNTRL to 0x%x\n", + dev_priv->audio_freq_cntrl); + } + + /* Force CDCLK to 2*BCLK as long as we need audio powered. */ + if (IS_GEMINILAKE(dev_priv)) glk_force_audio_cdclk(dev_priv, true); + if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) + I915_WRITE(AUD_PIN_BUF_CTL, + (I915_READ(AUD_PIN_BUF_CTL) | + AUD_PIN_BUF_ENABLE)); + } + return ret; } @@ -865,7 +877,7 @@ static void i915_audio_component_put_power(struct device *kdev, /* Stop forcing CDCLK to 2*BCLK if no need for audio to be powered. */ if (--dev_priv->audio_power_refcount == 0) - if (IS_CANNONLAKE(dev_priv) || IS_GEMINILAKE(dev_priv)) + if (IS_GEMINILAKE(dev_priv)) glk_force_audio_cdclk(dev_priv, false); intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO, cookie); @@ -1114,6 +1126,12 @@ static void i915_audio_component_init(struct drm_i915_private *dev_priv) return; } + if (IS_TIGERLAKE(dev_priv) || IS_ICELAKE(dev_priv)) { + dev_priv->audio_freq_cntrl = I915_READ(AUD_FREQ_CNTRL); + DRM_DEBUG_KMS("init value of AUD_FREQ_CNTRL of 0x%x\n", + dev_priv->audio_freq_cntrl); + } + dev_priv->audio_component_registered = true; } diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c index 16ed44bfd734..07a038f21619 100644 --- a/drivers/gpu/drm/i915/display/intel_fbc.c +++ b/drivers/gpu/drm/i915/display/intel_fbc.c @@ -1284,7 +1284,7 @@ static int intel_sanitize_fbc_option(struct drm_i915_private *dev_priv) return 0; /* https://bugs.freedesktop.org/show_bug.cgi?id=108085 */ - if (IS_GEMINILAKE(dev_priv)) + if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) return 0; if (IS_BROADWELL(dev_priv) || INTEL_GEN(dev_priv) >= 9) diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 06a506c29463..4949b5ad860f 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -525,7 +525,8 @@ __unwind_incomplete_requests(struct intel_engine_cs *engine) */ if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &rq->fence.flags)) { - spin_lock(&rq->lock); + spin_lock_nested(&rq->lock, + SINGLE_DEPTH_NESTING); i915_request_cancel_breadcrumb(rq); spin_unlock(&rq->lock); } @@ -2131,6 +2132,14 @@ static u32 *gen9_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch) /* WaFlushCoherentL3CacheLinesAtContextSwitch:skl,bxt,glk */ batch = gen8_emit_flush_coherentl3_wa(engine, batch); + /* WaClearSlmSpaceAtContextSwitch:skl,bxt,kbl,glk,cfl */ + batch = gen8_emit_pipe_control(batch, + PIPE_CONTROL_FLUSH_L3 | + PIPE_CONTROL_GLOBAL_GTT_IVB | + PIPE_CONTROL_CS_STALL | + PIPE_CONTROL_QW_WRITE, + slm_offset(engine)); + batch = emit_lri(batch, lri, ARRAY_SIZE(lri)); /* WaMediaPoolStateCmdInWABB:bxt,glk */ @@ -3715,9 +3724,11 @@ intel_execlists_create_virtual(struct i915_gem_context *ctx, ve->base.i915 = ctx->i915; ve->base.gt = siblings[0]->gt; ve->base.id = -1; + ve->base.class = OTHER_CLASS; ve->base.uabi_class = I915_ENGINE_CLASS_INVALID; ve->base.instance = I915_ENGINE_CLASS_INVALID_VIRTUAL; + ve->base.uabi_instance = I915_ENGINE_CLASS_INVALID_VIRTUAL; /* * The decision on whether to submit a request using semaphores diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c index e753b1e706e2..fc29a3705354 100644 --- a/drivers/gpu/drm/i915/gvt/cmd_parser.c +++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c @@ -1597,9 +1597,9 @@ static int cmd_handler_mi_op_2f(struct parser_exec_state *s) if (!(cmd_val(s, 0) & (1 << 22))) return ret; - /* check if QWORD */ - if (DWORD_FIELD(0, 20, 19) == 1) - valid_len += 8; + /* check inline data */ + if (cmd_val(s, 0) & BIT(18)) + valid_len = CMD_LEN(9); ret = gvt_check_valid_cmd_length(cmd_length(s), valid_len); if (ret) diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 89b6112bd66b..043ce1b47aeb 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1530,6 +1530,7 @@ struct drm_i915_private { */ struct mutex av_mutex; int audio_power_refcount; + u32 audio_freq_cntrl; struct { struct mutex mutex; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index f8ee9aba3955..1dd7b6187780 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -4049,7 +4049,13 @@ enum { #define GWUNIT_CLKGATE_DIS (1 << 16) #define UNSLICE_UNIT_LEVEL_CLKGATE _MMIO(0x9434) -#define VFUNIT_CLKGATE_DIS (1 << 20) +#define VFUNIT_CLKGATE_DIS REG_BIT(20) +#define HSUNIT_CLKGATE_DIS REG_BIT(8) +#define VSUNIT_CLKGATE_DIS REG_BIT(3) + +#define UNSLICE_UNIT_LEVEL_CLKGATE2 _MMIO(0x94e4) +#define VSUNIT_CLKGATE_DIS_TGL REG_BIT(19) +#define PSDUNIT_CLKGATE_DIS REG_BIT(5) #define INF_UNIT_LEVEL_CLKGATE _MMIO(0x9560) #define CGPSF_CLKGATE_DIS (1 << 3) @@ -9104,6 +9110,10 @@ enum { #define HSW_AUD_CHICKENBIT _MMIO(0x65f10) #define SKL_AUD_CODEC_WAKE_SIGNAL (1 << 15) +#define AUD_FREQ_CNTRL _MMIO(0x65900) +#define AUD_PIN_BUF_CTL _MMIO(0x48414) +#define AUD_PIN_BUF_ENABLE REG_BIT(31) + /* * HSW - ICL power wells * diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 2efe1d12d5a9..3ccfc025fde2 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -9194,6 +9194,17 @@ static void icl_init_clock_gating(struct drm_i915_private *dev_priv) /* WaEnable32PlaneMode:icl */ I915_WRITE(GEN9_CSFE_CHICKEN1_RCS, _MASKED_BIT_ENABLE(GEN11_ENABLE_32_PLANE_MODE)); + + /* + * Wa_1408615072:icl,ehl (vsunit) + * Wa_1407596294:icl,ehl (hsunit) + */ + intel_uncore_rmw(&dev_priv->uncore, UNSLICE_UNIT_LEVEL_CLKGATE, + 0, VSUNIT_CLKGATE_DIS | HSUNIT_CLKGATE_DIS); + + /* Wa_1407352427:icl,ehl */ + intel_uncore_rmw(&dev_priv->uncore, UNSLICE_UNIT_LEVEL_CLKGATE2, + 0, PSDUNIT_CLKGATE_DIS); } static void cnp_init_clock_gating(struct drm_i915_private *dev_priv) diff --git a/drivers/gpu/drm/mcde/mcde_drv.c b/drivers/gpu/drm/mcde/mcde_drv.c index 9a09eba53182..5649887d2b90 100644 --- a/drivers/gpu/drm/mcde/mcde_drv.c +++ b/drivers/gpu/drm/mcde/mcde_drv.c @@ -484,7 +484,8 @@ static int mcde_probe(struct platform_device *pdev) } if (!match) { dev_err(dev, "no matching components\n"); - return -ENODEV; + ret = -ENODEV; + goto clk_disable; } if (IS_ERR(match)) { dev_err(dev, "could not create component match\n"); diff --git a/drivers/gpu/drm/mcde/mcde_dsi.c b/drivers/gpu/drm/mcde/mcde_dsi.c index f9c9e32b299c..35bb825d1918 100644 --- a/drivers/gpu/drm/mcde/mcde_dsi.c +++ b/drivers/gpu/drm/mcde/mcde_dsi.c @@ -935,11 +935,13 @@ static int mcde_dsi_bind(struct device *dev, struct device *master, for_each_available_child_of_node(dev->of_node, child) { panel = of_drm_find_panel(child); if (IS_ERR(panel)) { - dev_err(dev, "failed to find panel try bridge (%lu)\n", + dev_err(dev, "failed to find panel try bridge (%ld)\n", PTR_ERR(panel)); + panel = NULL; + bridge = of_drm_find_bridge(child); if (IS_ERR(bridge)) { - dev_err(dev, "failed to find bridge (%lu)\n", + dev_err(dev, "failed to find bridge (%ld)\n", PTR_ERR(bridge)); return PTR_ERR(bridge); } diff --git a/drivers/gpu/drm/meson/meson_vclk.c b/drivers/gpu/drm/meson/meson_vclk.c index ac491a781952..f690793ae2d5 100644 --- a/drivers/gpu/drm/meson/meson_vclk.c +++ b/drivers/gpu/drm/meson/meson_vclk.c @@ -638,13 +638,18 @@ static bool meson_hdmi_pll_validate_params(struct meson_drm *priv, if (frac >= HDMI_FRAC_MAX_GXBB) return false; } else if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXM) || - meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXL) || - meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A)) { + meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXL)) { /* Empiric supported min/max dividers */ if (m < 106 || m > 247) return false; if (frac >= HDMI_FRAC_MAX_GXL) return false; + } else if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A)) { + /* Empiric supported min/max dividers */ + if (m < 106 || m > 247) + return false; + if (frac >= HDMI_FRAC_MAX_G12A) + return false; } return true; diff --git a/drivers/gpu/drm/meson/meson_venc_cvbs.c b/drivers/gpu/drm/meson/meson_venc_cvbs.c index 9ab27aecfcf3..1bd6b6d15ffb 100644 --- a/drivers/gpu/drm/meson/meson_venc_cvbs.c +++ b/drivers/gpu/drm/meson/meson_venc_cvbs.c @@ -64,6 +64,25 @@ struct meson_cvbs_mode meson_cvbs_modes[MESON_CVBS_MODES_COUNT] = { }, }; +static const struct meson_cvbs_mode * +meson_cvbs_get_mode(const struct drm_display_mode *req_mode) +{ + int i; + + for (i = 0; i < MESON_CVBS_MODES_COUNT; ++i) { + struct meson_cvbs_mode *meson_mode = &meson_cvbs_modes[i]; + + if (drm_mode_match(req_mode, &meson_mode->mode, + DRM_MODE_MATCH_TIMINGS | + DRM_MODE_MATCH_CLOCK | + DRM_MODE_MATCH_FLAGS | + DRM_MODE_MATCH_3D_FLAGS)) + return meson_mode; + } + + return NULL; +} + /* Connector */ static void meson_cvbs_connector_destroy(struct drm_connector *connector) @@ -136,14 +155,8 @@ static int meson_venc_cvbs_encoder_atomic_check(struct drm_encoder *encoder, struct drm_crtc_state *crtc_state, struct drm_connector_state *conn_state) { - int i; - - for (i = 0; i < MESON_CVBS_MODES_COUNT; ++i) { - struct meson_cvbs_mode *meson_mode = &meson_cvbs_modes[i]; - - if (drm_mode_equal(&crtc_state->mode, &meson_mode->mode)) - return 0; - } + if (meson_cvbs_get_mode(&crtc_state->mode)) + return 0; return -EINVAL; } @@ -191,24 +204,17 @@ static void meson_venc_cvbs_encoder_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode, struct drm_display_mode *adjusted_mode) { + const struct meson_cvbs_mode *meson_mode = meson_cvbs_get_mode(mode); struct meson_venc_cvbs *meson_venc_cvbs = encoder_to_meson_venc_cvbs(encoder); struct meson_drm *priv = meson_venc_cvbs->priv; - int i; - for (i = 0; i < MESON_CVBS_MODES_COUNT; ++i) { - struct meson_cvbs_mode *meson_mode = &meson_cvbs_modes[i]; + if (meson_mode) { + meson_venci_cvbs_mode_set(priv, meson_mode->enci); - if (drm_mode_equal(mode, &meson_mode->mode)) { - meson_venci_cvbs_mode_set(priv, - meson_mode->enci); - - /* Setup 27MHz vclk2 for ENCI and VDAC */ - meson_vclk_setup(priv, MESON_VCLK_TARGET_CVBS, - MESON_VCLK_CVBS, MESON_VCLK_CVBS, - MESON_VCLK_CVBS, true); - break; - } + /* Setup 27MHz vclk2 for ENCI and VDAC */ + meson_vclk_setup(priv, MESON_VCLK_TARGET_CVBS, MESON_VCLK_CVBS, + MESON_VCLK_CVBS, MESON_VCLK_CVBS, true); } } diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.c b/drivers/gpu/drm/mgag200/mgag200_drv.c index afd9119b6cf1..c96c4393b124 100644 --- a/drivers/gpu/drm/mgag200/mgag200_drv.c +++ b/drivers/gpu/drm/mgag200/mgag200_drv.c @@ -30,7 +30,8 @@ module_param_named(modeset, mgag200_modeset, int, 0400); static struct drm_driver driver; static const struct pci_device_id pciidlist[] = { - { PCI_VENDOR_ID_MATROX, 0x522, PCI_ANY_ID, PCI_ANY_ID, 0, 0, G200_SE_A }, + { PCI_VENDOR_ID_MATROX, 0x522, PCI_ANY_ID, PCI_ANY_ID, 0, 0, + G200_SE_A | MGAG200_FLAG_HW_BUG_NO_STARTADD}, { PCI_VENDOR_ID_MATROX, 0x524, PCI_ANY_ID, PCI_ANY_ID, 0, 0, G200_SE_B }, { PCI_VENDOR_ID_MATROX, 0x530, PCI_ANY_ID, PCI_ANY_ID, 0, 0, G200_EV }, { PCI_VENDOR_ID_MATROX, 0x532, PCI_ANY_ID, PCI_ANY_ID, 0, 0, G200_WB }, @@ -63,6 +64,35 @@ static const struct file_operations mgag200_driver_fops = { DRM_VRAM_MM_FILE_OPERATIONS }; +static bool mgag200_pin_bo_at_0(const struct mga_device *mdev) +{ + return mdev->flags & MGAG200_FLAG_HW_BUG_NO_STARTADD; +} + +int mgag200_driver_dumb_create(struct drm_file *file, + struct drm_device *dev, + struct drm_mode_create_dumb *args) +{ + struct mga_device *mdev = dev->dev_private; + unsigned long pg_align; + + if (WARN_ONCE(!dev->vram_mm, "VRAM MM not initialized")) + return -EINVAL; + + pg_align = 0ul; + + /* + * Aligning scanout buffers to the size of the video ram forces + * placement at offset 0. Works around a bug where HW does not + * respect 'startadd' field. + */ + if (mgag200_pin_bo_at_0(mdev)) + pg_align = PFN_UP(mdev->mc.vram_size); + + return drm_gem_vram_fill_create_dumb(file, dev, &dev->vram_mm->bdev, + pg_align, false, args); +} + static struct drm_driver driver = { .driver_features = DRIVER_GEM | DRIVER_MODESET, .load = mgag200_driver_load, @@ -74,7 +104,9 @@ static struct drm_driver driver = { .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, .patchlevel = DRIVER_PATCHLEVEL, - DRM_GEM_VRAM_DRIVER + .dumb_create = mgag200_driver_dumb_create, + .dumb_map_offset = drm_gem_vram_driver_dumb_mmap_offset, + .gem_prime_mmap = drm_gem_prime_mmap, }; static struct pci_driver mgag200_pci_driver = { diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.h b/drivers/gpu/drm/mgag200/mgag200_drv.h index 1c93f8dc08c7..7cc1a242df5f 100644 --- a/drivers/gpu/drm/mgag200/mgag200_drv.h +++ b/drivers/gpu/drm/mgag200/mgag200_drv.h @@ -159,6 +159,12 @@ enum mga_type { G200_EW3, }; +/* HW does not handle 'startadd' field correct. */ +#define MGAG200_FLAG_HW_BUG_NO_STARTADD (1ul << 8) + +#define MGAG200_TYPE_MASK (0x000000ff) +#define MGAG200_FLAG_MASK (0x00ffff00) + #define IS_G200_SE(mdev) (mdev->type == G200_SE_A || mdev->type == G200_SE_B) struct mga_device { @@ -188,6 +194,18 @@ struct mga_device { u32 unique_rev_id; }; +static inline enum mga_type +mgag200_type_from_driver_data(kernel_ulong_t driver_data) +{ + return (enum mga_type)(driver_data & MGAG200_TYPE_MASK); +} + +static inline unsigned long +mgag200_flags_from_driver_data(kernel_ulong_t driver_data) +{ + return driver_data & MGAG200_FLAG_MASK; +} + /* mgag200_mode.c */ int mgag200_modeset_init(struct mga_device *mdev); void mgag200_modeset_fini(struct mga_device *mdev); diff --git a/drivers/gpu/drm/mgag200/mgag200_main.c b/drivers/gpu/drm/mgag200/mgag200_main.c index a9773334dedf..388212b2d63f 100644 --- a/drivers/gpu/drm/mgag200/mgag200_main.c +++ b/drivers/gpu/drm/mgag200/mgag200_main.c @@ -94,7 +94,8 @@ static int mgag200_device_init(struct drm_device *dev, struct mga_device *mdev = dev->dev_private; int ret, option; - mdev->type = flags; + mdev->flags = mgag200_flags_from_driver_data(flags); + mdev->type = mgag200_type_from_driver_data(flags); /* Hardcode the number of CRTCs to 1 */ mdev->num_crtc = 1; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c index e686331fa089..691c1a277d91 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c @@ -352,26 +352,26 @@ static void a6xx_get_debugbus(struct msm_gpu *gpu, cxdbg = ioremap(res->start, resource_size(res)); if (cxdbg) { - cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_CNTLT, + cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_CNTLT, A6XX_DBGC_CFG_DBGBUS_CNTLT_SEGT(0xf)); - cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_CNTLM, + cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_CNTLM, A6XX_DBGC_CFG_DBGBUS_CNTLM_ENABLE(0xf)); - cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_0, 0); - cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_1, 0); - cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_2, 0); - cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_3, 0); + cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_IVTL_0, 0); + cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_IVTL_1, 0); + cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_IVTL_2, 0); + cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_IVTL_3, 0); - cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_BYTEL_0, + cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_BYTEL_0, 0x76543210); - cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_BYTEL_1, + cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_BYTEL_1, 0xFEDCBA98); - cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_0, 0); - cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_1, 0); - cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_2, 0); - cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_3, 0); + cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_MASKL_0, 0); + cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_MASKL_1, 0); + cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_MASKL_2, 0); + cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_MASKL_3, 0); } a6xx_state->debugbus = state_kcalloc(a6xx_state, diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c index 6be879578140..1c74381a4fc9 100644 --- a/drivers/gpu/drm/msm/msm_debugfs.c +++ b/drivers/gpu/drm/msm/msm_debugfs.c @@ -47,12 +47,8 @@ static int msm_gpu_release(struct inode *inode, struct file *file) struct msm_gpu_show_priv *show_priv = m->private; struct msm_drm_private *priv = show_priv->dev->dev_private; struct msm_gpu *gpu = priv->gpu; - int ret; - - ret = mutex_lock_interruptible(&show_priv->dev->struct_mutex); - if (ret) - return ret; + mutex_lock(&show_priv->dev->struct_mutex); gpu->funcs->gpu_state_put(show_priv->state); mutex_unlock(&show_priv->dev->struct_mutex); diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index a052364a5d74..edd45f434ccd 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -16,6 +16,7 @@ #include #include #include +#include /* * Power Management: diff --git a/drivers/gpu/drm/nouveau/dispnv50/atom.h b/drivers/gpu/drm/nouveau/dispnv50/atom.h index 43df86c38f58..24f7700768da 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/atom.h +++ b/drivers/gpu/drm/nouveau/dispnv50/atom.h @@ -114,6 +114,7 @@ struct nv50_head_atom { u8 nhsync:1; u8 nvsync:1; u8 depth:4; + u8 bpc; } or; /* Currently only used for MST */ diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index b46be8a091e9..d735ea7e2d88 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -326,9 +326,9 @@ nv50_outp_atomic_check_view(struct drm_encoder *encoder, * same size as the native one (e.g. different * refresh rate) */ - if (adjusted_mode->hdisplay == native_mode->hdisplay && - adjusted_mode->vdisplay == native_mode->vdisplay && - adjusted_mode->type & DRM_MODE_TYPE_DRIVER) + if (mode->hdisplay == native_mode->hdisplay && + mode->vdisplay == native_mode->vdisplay && + mode->type & DRM_MODE_TYPE_DRIVER) break; mode = native_mode; asyc->scaler.full = true; @@ -353,10 +353,20 @@ nv50_outp_atomic_check(struct drm_encoder *encoder, struct drm_crtc_state *crtc_state, struct drm_connector_state *conn_state) { - struct nouveau_connector *nv_connector = - nouveau_connector(conn_state->connector); - return nv50_outp_atomic_check_view(encoder, crtc_state, conn_state, - nv_connector->native_mode); + struct drm_connector *connector = conn_state->connector; + struct nouveau_connector *nv_connector = nouveau_connector(connector); + struct nv50_head_atom *asyh = nv50_head_atom(crtc_state); + int ret; + + ret = nv50_outp_atomic_check_view(encoder, crtc_state, conn_state, + nv_connector->native_mode); + if (ret) + return ret; + + if (crtc_state->mode_changed || crtc_state->connectors_changed) + asyh->or.bpc = connector->display_info.bpc; + + return 0; } /****************************************************************************** @@ -770,32 +780,54 @@ nv50_msto_atomic_check(struct drm_encoder *encoder, struct nv50_mstm *mstm = mstc->mstm; struct nv50_head_atom *asyh = nv50_head_atom(crtc_state); int slots; + int ret; + + ret = nv50_outp_atomic_check_view(encoder, crtc_state, conn_state, + mstc->native); + if (ret) + return ret; + + if (!crtc_state->mode_changed && !crtc_state->connectors_changed) + return 0; + + /* + * When restoring duplicated states, we need to make sure that the bw + * remains the same and avoid recalculating it, as the connector's bpc + * may have changed after the state was duplicated + */ + if (!state->duplicated) { + const int clock = crtc_state->adjusted_mode.clock; - if (crtc_state->mode_changed || crtc_state->connectors_changed) { /* - * When restoring duplicated states, we need to make sure that - * the bw remains the same and avoid recalculating it, as the - * connector's bpc may have changed after the state was - * duplicated + * XXX: Since we don't use HDR in userspace quite yet, limit + * the bpc to 8 to save bandwidth on the topology. In the + * future, we'll want to properly fix this by dynamically + * selecting the highest possible bpc that would fit in the + * topology */ - if (!state->duplicated) { - const int bpp = connector->display_info.bpc * 3; - const int clock = crtc_state->adjusted_mode.clock; + asyh->or.bpc = min(connector->display_info.bpc, 8U); + asyh->dp.pbn = drm_dp_calc_pbn_mode(clock, asyh->or.bpc * 3); + } - asyh->dp.pbn = drm_dp_calc_pbn_mode(clock, bpp); - } + slots = drm_dp_atomic_find_vcpi_slots(state, &mstm->mgr, mstc->port, + asyh->dp.pbn); + if (slots < 0) + return slots; - slots = drm_dp_atomic_find_vcpi_slots(state, &mstm->mgr, - mstc->port, - asyh->dp.pbn); - if (slots < 0) - return slots; + asyh->dp.tu = slots; - asyh->dp.tu = slots; - } + return 0; +} - return nv50_outp_atomic_check_view(encoder, crtc_state, conn_state, - mstc->native); +static u8 +nv50_dp_bpc_to_depth(unsigned int bpc) +{ + switch (bpc) { + case 6: return 0x2; + case 8: return 0x5; + case 10: /* fall-through */ + default: return 0x6; + } } static void @@ -808,7 +840,7 @@ nv50_msto_enable(struct drm_encoder *encoder) struct nv50_mstm *mstm = NULL; struct drm_connector *connector; struct drm_connector_list_iter conn_iter; - u8 proto, depth; + u8 proto; bool r; drm_connector_list_iter_begin(encoder->dev, &conn_iter); @@ -837,14 +869,8 @@ nv50_msto_enable(struct drm_encoder *encoder) else proto = 0x9; - switch (mstc->connector.display_info.bpc) { - case 6: depth = 0x2; break; - case 8: depth = 0x5; break; - case 10: - default: depth = 0x6; break; - } - - mstm->outp->update(mstm->outp, head->base.index, armh, proto, depth); + mstm->outp->update(mstm->outp, head->base.index, armh, proto, + nv50_dp_bpc_to_depth(armh->or.bpc)); msto->head = head; msto->mstc = mstc; @@ -1498,20 +1524,14 @@ nv50_sor_enable(struct drm_encoder *encoder) lvds.lvds.script |= 0x0200; } - if (nv_connector->base.display_info.bpc == 8) + if (asyh->or.bpc == 8) lvds.lvds.script |= 0x0200; } nvif_mthd(&disp->disp->object, 0, &lvds, sizeof(lvds)); break; case DCB_OUTPUT_DP: - if (nv_connector->base.display_info.bpc == 6) - depth = 0x2; - else - if (nv_connector->base.display_info.bpc == 8) - depth = 0x5; - else - depth = 0x6; + depth = nv50_dp_bpc_to_depth(asyh->or.bpc); if (nv_encoder->link & 1) proto = 0x8; @@ -1662,7 +1682,7 @@ nv50_pior_enable(struct drm_encoder *encoder) nv50_outp_acquire(nv_encoder); nv_connector = nouveau_encoder_connector_get(nv_encoder); - switch (nv_connector->base.display_info.bpc) { + switch (asyh->or.bpc) { case 10: asyh->or.depth = 0x6; break; case 8: asyh->or.depth = 0x5; break; case 6: asyh->or.depth = 0x2; break; diff --git a/drivers/gpu/drm/nouveau/dispnv50/head.c b/drivers/gpu/drm/nouveau/dispnv50/head.c index 71c23bf1fe25..c9692df2b76c 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/head.c +++ b/drivers/gpu/drm/nouveau/dispnv50/head.c @@ -81,18 +81,17 @@ nv50_head_atomic_check_dither(struct nv50_head_atom *armh, struct nv50_head_atom *asyh, struct nouveau_conn_atom *asyc) { - struct drm_connector *connector = asyc->state.connector; u32 mode = 0x00; if (asyc->dither.mode == DITHERING_MODE_AUTO) { - if (asyh->base.depth > connector->display_info.bpc * 3) + if (asyh->base.depth > asyh->or.bpc * 3) mode = DITHERING_MODE_DYNAMIC2X2; } else { mode = asyc->dither.mode; } if (asyc->dither.depth == DITHERING_DEPTH_AUTO) { - if (connector->display_info.bpc >= 8) + if (asyh->or.bpc >= 8) mode |= DITHERING_DEPTH_8BPC; } else { mode |= asyc->dither.depth; diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c index 94dfa2e5a9ab..eb31c5b6c8e9 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -245,14 +245,22 @@ nouveau_conn_atomic_duplicate_state(struct drm_connector *connector) void nouveau_conn_reset(struct drm_connector *connector) { + struct nouveau_connector *nv_connector = nouveau_connector(connector); struct nouveau_conn_atom *asyc; - if (WARN_ON(!(asyc = kzalloc(sizeof(*asyc), GFP_KERNEL)))) - return; + if (drm_drv_uses_atomic_modeset(connector->dev)) { + if (WARN_ON(!(asyc = kzalloc(sizeof(*asyc), GFP_KERNEL)))) + return; + + if (connector->state) + nouveau_conn_atomic_destroy_state(connector, + connector->state); + + __drm_atomic_helper_connector_reset(connector, &asyc->state); + } else { + asyc = &nv_connector->properties_state; + } - if (connector->state) - nouveau_conn_atomic_destroy_state(connector, connector->state); - __drm_atomic_helper_connector_reset(connector, &asyc->state); asyc->dither.mode = DITHERING_MODE_AUTO; asyc->dither.depth = DITHERING_DEPTH_AUTO; asyc->scaler.mode = DRM_MODE_SCALE_NONE; @@ -276,8 +284,14 @@ void nouveau_conn_attach_properties(struct drm_connector *connector) { struct drm_device *dev = connector->dev; - struct nouveau_conn_atom *armc = nouveau_conn_atom(connector->state); struct nouveau_display *disp = nouveau_display(dev); + struct nouveau_connector *nv_connector = nouveau_connector(connector); + struct nouveau_conn_atom *armc; + + if (drm_drv_uses_atomic_modeset(connector->dev)) + armc = nouveau_conn_atom(connector->state); + else + armc = &nv_connector->properties_state; /* Init DVI-I specific properties. */ if (connector->connector_type == DRM_MODE_CONNECTOR_DVII) @@ -749,9 +763,9 @@ static int nouveau_connector_set_property(struct drm_connector *connector, struct drm_property *property, uint64_t value) { - struct nouveau_conn_atom *asyc = nouveau_conn_atom(connector->state); struct nouveau_connector *nv_connector = nouveau_connector(connector); struct nouveau_encoder *nv_encoder = nv_connector->detected_encoder; + struct nouveau_conn_atom *asyc = &nv_connector->properties_state; struct drm_encoder *encoder = to_drm_encoder(nv_encoder); int ret; @@ -1131,6 +1145,16 @@ nouveau_connector_hotplug(struct nvif_notify *notify) const char *name = connector->name; struct nouveau_encoder *nv_encoder; int ret; + bool plugged = (rep->mask != NVIF_NOTIFY_CONN_V0_UNPLUG); + + if (rep->mask & NVIF_NOTIFY_CONN_V0_IRQ) { + NV_DEBUG(drm, "service %s\n", name); + drm_dp_cec_irq(&nv_connector->aux); + if ((nv_encoder = find_encoder(connector, DCB_OUTPUT_DP))) + nv50_mstm_service(nv_encoder->dp.mstm); + + return NVIF_NOTIFY_KEEP; + } ret = pm_runtime_get(drm->dev->dev); if (ret == 0) { @@ -1151,25 +1175,16 @@ nouveau_connector_hotplug(struct nvif_notify *notify) return NVIF_NOTIFY_DROP; } - if (rep->mask & NVIF_NOTIFY_CONN_V0_IRQ) { - NV_DEBUG(drm, "service %s\n", name); - drm_dp_cec_irq(&nv_connector->aux); - if ((nv_encoder = find_encoder(connector, DCB_OUTPUT_DP))) - nv50_mstm_service(nv_encoder->dp.mstm); - } else { - bool plugged = (rep->mask != NVIF_NOTIFY_CONN_V0_UNPLUG); - + if (!plugged) + drm_dp_cec_unset_edid(&nv_connector->aux); + NV_DEBUG(drm, "%splugged %s\n", plugged ? "" : "un", name); + if ((nv_encoder = find_encoder(connector, DCB_OUTPUT_DP))) { if (!plugged) - drm_dp_cec_unset_edid(&nv_connector->aux); - NV_DEBUG(drm, "%splugged %s\n", plugged ? "" : "un", name); - if ((nv_encoder = find_encoder(connector, DCB_OUTPUT_DP))) { - if (!plugged) - nv50_mstm_remove(nv_encoder->dp.mstm); - } - - drm_helper_hpd_irq_event(connector->dev); + nv50_mstm_remove(nv_encoder->dp.mstm); } + drm_helper_hpd_irq_event(connector->dev); + pm_runtime_mark_last_busy(drm->dev->dev); pm_runtime_put_autosuspend(drm->dev->dev); return NVIF_NOTIFY_KEEP; diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.h b/drivers/gpu/drm/nouveau/nouveau_connector.h index f43a8d63aef8..de84fb4708c7 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.h +++ b/drivers/gpu/drm/nouveau/nouveau_connector.h @@ -29,6 +29,7 @@ #include +#include #include #include #include @@ -44,6 +45,60 @@ struct dcb_output; struct nouveau_backlight; #endif +#define nouveau_conn_atom(p) \ + container_of((p), struct nouveau_conn_atom, state) + +struct nouveau_conn_atom { + struct drm_connector_state state; + + struct { + /* The enum values specifically defined here match nv50/gf119 + * hw values, and the code relies on this. + */ + enum { + DITHERING_MODE_OFF = 0x00, + DITHERING_MODE_ON = 0x01, + DITHERING_MODE_DYNAMIC2X2 = 0x10 | DITHERING_MODE_ON, + DITHERING_MODE_STATIC2X2 = 0x18 | DITHERING_MODE_ON, + DITHERING_MODE_TEMPORAL = 0x20 | DITHERING_MODE_ON, + DITHERING_MODE_AUTO + } mode; + enum { + DITHERING_DEPTH_6BPC = 0x00, + DITHERING_DEPTH_8BPC = 0x02, + DITHERING_DEPTH_AUTO + } depth; + } dither; + + struct { + int mode; /* DRM_MODE_SCALE_* */ + struct { + enum { + UNDERSCAN_OFF, + UNDERSCAN_ON, + UNDERSCAN_AUTO, + } mode; + u32 hborder; + u32 vborder; + } underscan; + bool full; + } scaler; + + struct { + int color_vibrance; + int vibrant_hue; + } procamp; + + union { + struct { + bool dither:1; + bool scaler:1; + bool procamp:1; + }; + u8 mask; + } set; +}; + struct nouveau_connector { struct drm_connector base; enum dcb_connector_type type; @@ -63,6 +118,12 @@ struct nouveau_connector { #ifdef CONFIG_DRM_NOUVEAU_BACKLIGHT struct nouveau_backlight *backlight; #endif + /* + * Our connector property code expects a nouveau_conn_atom struct + * even on pre-nv50 where we do not support atomic. This embedded + * version gets used in the non atomic modeset case. + */ + struct nouveau_conn_atom properties_state; }; static inline struct nouveau_connector *nouveau_connector( @@ -121,61 +182,6 @@ extern int nouveau_ignorelid; extern int nouveau_duallink; extern int nouveau_hdmimhz; -#include -#define nouveau_conn_atom(p) \ - container_of((p), struct nouveau_conn_atom, state) - -struct nouveau_conn_atom { - struct drm_connector_state state; - - struct { - /* The enum values specifically defined here match nv50/gf119 - * hw values, and the code relies on this. - */ - enum { - DITHERING_MODE_OFF = 0x00, - DITHERING_MODE_ON = 0x01, - DITHERING_MODE_DYNAMIC2X2 = 0x10 | DITHERING_MODE_ON, - DITHERING_MODE_STATIC2X2 = 0x18 | DITHERING_MODE_ON, - DITHERING_MODE_TEMPORAL = 0x20 | DITHERING_MODE_ON, - DITHERING_MODE_AUTO - } mode; - enum { - DITHERING_DEPTH_6BPC = 0x00, - DITHERING_DEPTH_8BPC = 0x02, - DITHERING_DEPTH_AUTO - } depth; - } dither; - - struct { - int mode; /* DRM_MODE_SCALE_* */ - struct { - enum { - UNDERSCAN_OFF, - UNDERSCAN_ON, - UNDERSCAN_AUTO, - } mode; - u32 hborder; - u32 vborder; - } underscan; - bool full; - } scaler; - - struct { - int color_vibrance; - int vibrant_hue; - } procamp; - - union { - struct { - bool dither:1; - bool scaler:1; - bool procamp:1; - }; - u8 mask; - } set; -}; - void nouveau_conn_attach_properties(struct drm_connector *); void nouveau_conn_reset(struct drm_connector *); struct drm_connector_state * diff --git a/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c b/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c index b5b14aa059ea..2aa89eaecf6f 100644 --- a/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c +++ b/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c @@ -426,6 +426,7 @@ static int rpi_touchscreen_probe(struct i2c_client *i2c, return PTR_ERR(ts->dsi); } + drm_panel_init(&ts->base); ts->base.dev = dev; ts->base.funcs = &rpi_touchscreen_funcs; diff --git a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c index 5e3e92ea9ea6..3b2612ae931e 100644 --- a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c +++ b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c @@ -381,6 +381,7 @@ static int st7789v_probe(struct spi_device *spi) spi_set_drvdata(spi, ctx); ctx->spi = spi; + drm_panel_init(&ctx->panel); ctx->panel.dev = &spi->dev; ctx->panel.funcs = &st7789v_drm_funcs; diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c index f21bc8a7ee3a..1c67ac434e10 100644 --- a/drivers/gpu/drm/panfrost/panfrost_drv.c +++ b/drivers/gpu/drm/panfrost/panfrost_drv.c @@ -303,14 +303,17 @@ static int panfrost_ioctl_mmap_bo(struct drm_device *dev, void *data, } /* Don't allow mmapping of heap objects as pages are not pinned. */ - if (to_panfrost_bo(gem_obj)->is_heap) - return -EINVAL; + if (to_panfrost_bo(gem_obj)->is_heap) { + ret = -EINVAL; + goto out; + } ret = drm_gem_create_mmap_offset(gem_obj); if (ret == 0) args->offset = drm_vma_node_offset_addr(&gem_obj->vma_node); - drm_gem_object_put_unlocked(gem_obj); +out: + drm_gem_object_put_unlocked(gem_obj); return ret; } @@ -347,20 +350,19 @@ static int panfrost_ioctl_madvise(struct drm_device *dev, void *data, return -ENOENT; } + mutex_lock(&pfdev->shrinker_lock); args->retained = drm_gem_shmem_madvise(gem_obj, args->madv); if (args->retained) { struct panfrost_gem_object *bo = to_panfrost_bo(gem_obj); - mutex_lock(&pfdev->shrinker_lock); - if (args->madv == PANFROST_MADV_DONTNEED) - list_add_tail(&bo->base.madv_list, &pfdev->shrinker_list); + list_add_tail(&bo->base.madv_list, + &pfdev->shrinker_list); else if (args->madv == PANFROST_MADV_WILLNEED) list_del_init(&bo->base.madv_list); - - mutex_unlock(&pfdev->shrinker_lock); } + mutex_unlock(&pfdev->shrinker_lock); drm_gem_object_put_unlocked(gem_obj); return 0; @@ -443,7 +445,7 @@ panfrost_postclose(struct drm_device *dev, struct drm_file *file) { struct panfrost_file_priv *panfrost_priv = file->driver_priv; - panfrost_perfcnt_close(panfrost_priv); + panfrost_perfcnt_close(file); panfrost_job_close(panfrost_priv); panfrost_mmu_pgtable_free(panfrost_priv); diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.c b/drivers/gpu/drm/panfrost/panfrost_gem.c index acb07fe06580..92a95210a899 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gem.c +++ b/drivers/gpu/drm/panfrost/panfrost_gem.c @@ -19,6 +19,16 @@ static void panfrost_gem_free_object(struct drm_gem_object *obj) struct panfrost_gem_object *bo = to_panfrost_bo(obj); struct panfrost_device *pfdev = obj->dev->dev_private; + /* + * Make sure the BO is no longer inserted in the shrinker list before + * taking care of the destruction itself. If we don't do that we have a + * race condition between this function and what's done in + * panfrost_gem_shrinker_scan(). + */ + mutex_lock(&pfdev->shrinker_lock); + list_del_init(&bo->base.madv_list); + mutex_unlock(&pfdev->shrinker_lock); + if (bo->sgts) { int i; int n_sgt = bo->base.base.size / SZ_2M; @@ -33,15 +43,10 @@ static void panfrost_gem_free_object(struct drm_gem_object *obj) kfree(bo->sgts); } - mutex_lock(&pfdev->shrinker_lock); - if (!list_empty(&bo->base.madv_list)) - list_del(&bo->base.madv_list); - mutex_unlock(&pfdev->shrinker_lock); - drm_gem_shmem_free_object(obj); } -static int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv) +int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv) { int ret; size_t size = obj->size; @@ -80,7 +85,7 @@ static int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_p return ret; } -static void panfrost_gem_close(struct drm_gem_object *obj, struct drm_file *file_priv) +void panfrost_gem_close(struct drm_gem_object *obj, struct drm_file *file_priv) { struct panfrost_gem_object *bo = to_panfrost_bo(obj); struct panfrost_file_priv *priv = file_priv->driver_priv; diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.h b/drivers/gpu/drm/panfrost/panfrost_gem.h index 50920819cc16..4b17e7308764 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gem.h +++ b/drivers/gpu/drm/panfrost/panfrost_gem.h @@ -45,6 +45,10 @@ panfrost_gem_create_with_handle(struct drm_file *file_priv, u32 flags, uint32_t *handle); +int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv); +void panfrost_gem_close(struct drm_gem_object *obj, + struct drm_file *file_priv); + void panfrost_gem_shrinker_init(struct drm_device *dev); void panfrost_gem_shrinker_cleanup(struct drm_device *dev); diff --git a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c index 2dba192bf198..2c04e858c50a 100644 --- a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c +++ b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c @@ -67,9 +67,10 @@ static int panfrost_perfcnt_dump_locked(struct panfrost_device *pfdev) } static int panfrost_perfcnt_enable_locked(struct panfrost_device *pfdev, - struct panfrost_file_priv *user, + struct drm_file *file_priv, unsigned int counterset) { + struct panfrost_file_priv *user = file_priv->driver_priv; struct panfrost_perfcnt *perfcnt = pfdev->perfcnt; struct drm_gem_shmem_object *bo; u32 cfg; @@ -91,14 +92,14 @@ static int panfrost_perfcnt_enable_locked(struct panfrost_device *pfdev, perfcnt->bo = to_panfrost_bo(&bo->base); /* Map the perfcnt buf in the address space attached to file_priv. */ - ret = panfrost_mmu_map(perfcnt->bo); + ret = panfrost_gem_open(&perfcnt->bo->base.base, file_priv); if (ret) goto err_put_bo; perfcnt->buf = drm_gem_shmem_vmap(&bo->base); if (IS_ERR(perfcnt->buf)) { ret = PTR_ERR(perfcnt->buf); - goto err_put_bo; + goto err_close_bo; } /* @@ -157,14 +158,17 @@ static int panfrost_perfcnt_enable_locked(struct panfrost_device *pfdev, err_vunmap: drm_gem_shmem_vunmap(&perfcnt->bo->base.base, perfcnt->buf); +err_close_bo: + panfrost_gem_close(&perfcnt->bo->base.base, file_priv); err_put_bo: drm_gem_object_put_unlocked(&bo->base); return ret; } static int panfrost_perfcnt_disable_locked(struct panfrost_device *pfdev, - struct panfrost_file_priv *user) + struct drm_file *file_priv) { + struct panfrost_file_priv *user = file_priv->driver_priv; struct panfrost_perfcnt *perfcnt = pfdev->perfcnt; if (user != perfcnt->user) @@ -180,6 +184,7 @@ static int panfrost_perfcnt_disable_locked(struct panfrost_device *pfdev, perfcnt->user = NULL; drm_gem_shmem_vunmap(&perfcnt->bo->base.base, perfcnt->buf); perfcnt->buf = NULL; + panfrost_gem_close(&perfcnt->bo->base.base, file_priv); drm_gem_object_put_unlocked(&perfcnt->bo->base.base); perfcnt->bo = NULL; pm_runtime_mark_last_busy(pfdev->dev); @@ -191,7 +196,6 @@ static int panfrost_perfcnt_disable_locked(struct panfrost_device *pfdev, int panfrost_ioctl_perfcnt_enable(struct drm_device *dev, void *data, struct drm_file *file_priv) { - struct panfrost_file_priv *pfile = file_priv->driver_priv; struct panfrost_device *pfdev = dev->dev_private; struct panfrost_perfcnt *perfcnt = pfdev->perfcnt; struct drm_panfrost_perfcnt_enable *req = data; @@ -207,10 +211,10 @@ int panfrost_ioctl_perfcnt_enable(struct drm_device *dev, void *data, mutex_lock(&perfcnt->lock); if (req->enable) - ret = panfrost_perfcnt_enable_locked(pfdev, pfile, + ret = panfrost_perfcnt_enable_locked(pfdev, file_priv, req->counterset); else - ret = panfrost_perfcnt_disable_locked(pfdev, pfile); + ret = panfrost_perfcnt_disable_locked(pfdev, file_priv); mutex_unlock(&perfcnt->lock); return ret; @@ -248,15 +252,16 @@ int panfrost_ioctl_perfcnt_dump(struct drm_device *dev, void *data, return ret; } -void panfrost_perfcnt_close(struct panfrost_file_priv *pfile) +void panfrost_perfcnt_close(struct drm_file *file_priv) { + struct panfrost_file_priv *pfile = file_priv->driver_priv; struct panfrost_device *pfdev = pfile->pfdev; struct panfrost_perfcnt *perfcnt = pfdev->perfcnt; pm_runtime_get_sync(pfdev->dev); mutex_lock(&perfcnt->lock); if (perfcnt->user == pfile) - panfrost_perfcnt_disable_locked(pfdev, pfile); + panfrost_perfcnt_disable_locked(pfdev, file_priv); mutex_unlock(&perfcnt->lock); pm_runtime_mark_last_busy(pfdev->dev); pm_runtime_put_autosuspend(pfdev->dev); diff --git a/drivers/gpu/drm/panfrost/panfrost_perfcnt.h b/drivers/gpu/drm/panfrost/panfrost_perfcnt.h index 13b8fdaa1b43..8bbcf5f5fb33 100644 --- a/drivers/gpu/drm/panfrost/panfrost_perfcnt.h +++ b/drivers/gpu/drm/panfrost/panfrost_perfcnt.h @@ -9,7 +9,7 @@ void panfrost_perfcnt_sample_done(struct panfrost_device *pfdev); void panfrost_perfcnt_clean_cache_done(struct panfrost_device *pfdev); int panfrost_perfcnt_init(struct panfrost_device *pfdev); void panfrost_perfcnt_fini(struct panfrost_device *pfdev); -void panfrost_perfcnt_close(struct panfrost_file_priv *pfile); +void panfrost_perfcnt_close(struct drm_file *file_priv); int panfrost_ioctl_perfcnt_enable(struct drm_device *dev, void *data, struct drm_file *file_priv); int panfrost_ioctl_perfcnt_dump(struct drm_device *dev, void *data, diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c index 7089dfc8c2a9..110fb38004b1 100644 --- a/drivers/gpu/drm/radeon/r100.c +++ b/drivers/gpu/drm/radeon/r100.c @@ -1826,8 +1826,8 @@ static int r100_packet0_check(struct radeon_cs_parser *p, track->textures[i].use_pitch = 1; } else { track->textures[i].use_pitch = 0; - track->textures[i].width = 1 << ((idx_value >> RADEON_TXFORMAT_WIDTH_SHIFT) & RADEON_TXFORMAT_WIDTH_MASK); - track->textures[i].height = 1 << ((idx_value >> RADEON_TXFORMAT_HEIGHT_SHIFT) & RADEON_TXFORMAT_HEIGHT_MASK); + track->textures[i].width = 1 << ((idx_value & RADEON_TXFORMAT_WIDTH_MASK) >> RADEON_TXFORMAT_WIDTH_SHIFT); + track->textures[i].height = 1 << ((idx_value & RADEON_TXFORMAT_HEIGHT_MASK) >> RADEON_TXFORMAT_HEIGHT_SHIFT); } if (idx_value & RADEON_TXFORMAT_CUBIC_MAP_ENABLE) track->textures[i].tex_coord_type = 2; diff --git a/drivers/gpu/drm/radeon/r200.c b/drivers/gpu/drm/radeon/r200.c index 840401413c58..f5f2ffea5ab2 100644 --- a/drivers/gpu/drm/radeon/r200.c +++ b/drivers/gpu/drm/radeon/r200.c @@ -476,8 +476,8 @@ int r200_packet0_check(struct radeon_cs_parser *p, track->textures[i].use_pitch = 1; } else { track->textures[i].use_pitch = 0; - track->textures[i].width = 1 << ((idx_value >> RADEON_TXFORMAT_WIDTH_SHIFT) & RADEON_TXFORMAT_WIDTH_MASK); - track->textures[i].height = 1 << ((idx_value >> RADEON_TXFORMAT_HEIGHT_SHIFT) & RADEON_TXFORMAT_HEIGHT_MASK); + track->textures[i].width = 1 << ((idx_value & RADEON_TXFORMAT_WIDTH_MASK) >> RADEON_TXFORMAT_WIDTH_SHIFT); + track->textures[i].height = 1 << ((idx_value & RADEON_TXFORMAT_HEIGHT_MASK) >> RADEON_TXFORMAT_HEIGHT_SHIFT); } if (idx_value & R200_TXFORMAT_LOOKUP_DISABLE) track->textures[i].lookup_disable = true; diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index f39b97ed4ade..2af64459b3d7 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -632,43 +632,41 @@ static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb) } /** - * drm_sched_cleanup_jobs - destroy finished jobs + * drm_sched_get_cleanup_job - fetch the next finished job to be destroyed * * @sched: scheduler instance * - * Remove all finished jobs from the mirror list and destroy them. + * Returns the next finished job from the mirror list (if there is one) + * ready for it to be destroyed. */ -static void drm_sched_cleanup_jobs(struct drm_gpu_scheduler *sched) +static struct drm_sched_job * +drm_sched_get_cleanup_job(struct drm_gpu_scheduler *sched) { + struct drm_sched_job *job; unsigned long flags; /* Don't destroy jobs while the timeout worker is running */ if (sched->timeout != MAX_SCHEDULE_TIMEOUT && !cancel_delayed_work(&sched->work_tdr)) - return; - + return NULL; - while (!list_empty(&sched->ring_mirror_list)) { - struct drm_sched_job *job; + spin_lock_irqsave(&sched->job_list_lock, flags); - job = list_first_entry(&sched->ring_mirror_list, + job = list_first_entry_or_null(&sched->ring_mirror_list, struct drm_sched_job, node); - if (!dma_fence_is_signaled(&job->s_fence->finished)) - break; - spin_lock_irqsave(&sched->job_list_lock, flags); + if (job && dma_fence_is_signaled(&job->s_fence->finished)) { /* remove job from ring_mirror_list */ list_del_init(&job->node); - spin_unlock_irqrestore(&sched->job_list_lock, flags); - - sched->ops->free_job(job); + } else { + job = NULL; + /* queue timeout for next job */ + drm_sched_start_timeout(sched); } - /* queue timeout for next job */ - spin_lock_irqsave(&sched->job_list_lock, flags); - drm_sched_start_timeout(sched); spin_unlock_irqrestore(&sched->job_list_lock, flags); + return job; } /** @@ -708,12 +706,19 @@ static int drm_sched_main(void *param) struct drm_sched_fence *s_fence; struct drm_sched_job *sched_job; struct dma_fence *fence; + struct drm_sched_job *cleanup_job = NULL; wait_event_interruptible(sched->wake_up_worker, - (drm_sched_cleanup_jobs(sched), + (cleanup_job = drm_sched_get_cleanup_job(sched)) || (!drm_sched_blocked(sched) && (entity = drm_sched_select_entity(sched))) || - kthread_should_stop())); + kthread_should_stop()); + + if (cleanup_job) { + sched->ops->free_job(cleanup_job); + /* queue timeout for next job */ + drm_sched_start_timeout(sched); + } if (!entity) continue; diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c index eb8071a4d6d0..9c3bdfd20337 100644 --- a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c +++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c @@ -683,8 +683,6 @@ static void sun4i_hdmi_unbind(struct device *dev, struct device *master, struct sun4i_hdmi *hdmi = dev_get_drvdata(dev); cec_unregister_adapter(hdmi->cec_adap); - drm_connector_cleanup(&hdmi->connector); - drm_encoder_cleanup(&hdmi->encoder); i2c_del_adapter(hdmi->i2c); i2c_put_adapter(hdmi->ddc_i2c); clk_disable_unprepare(hdmi->mod_clk); diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c index b89439ed210d..27c80c9e2b83 100644 --- a/drivers/gpu/drm/sun4i/sun4i_tcon.c +++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c @@ -488,7 +488,7 @@ static void sun4i_tcon0_mode_set_rgb(struct sun4i_tcon *tcon, WARN_ON(!tcon->quirks->has_channel_0); - tcon->dclk_min_div = 1; + tcon->dclk_min_div = tcon->quirks->dclk_min_div; tcon->dclk_max_div = 127; sun4i_tcon0_mode_set_common(tcon, mode); @@ -1425,12 +1425,14 @@ static int sun8i_r40_tcon_tv_set_mux(struct sun4i_tcon *tcon, static const struct sun4i_tcon_quirks sun4i_a10_quirks = { .has_channel_0 = true, .has_channel_1 = true, + .dclk_min_div = 4, .set_mux = sun4i_a10_tcon_set_mux, }; static const struct sun4i_tcon_quirks sun5i_a13_quirks = { .has_channel_0 = true, .has_channel_1 = true, + .dclk_min_div = 4, .set_mux = sun5i_a13_tcon_set_mux, }; @@ -1439,6 +1441,7 @@ static const struct sun4i_tcon_quirks sun6i_a31_quirks = { .has_channel_1 = true, .has_lvds_alt = true, .needs_de_be_mux = true, + .dclk_min_div = 1, .set_mux = sun6i_tcon_set_mux, }; @@ -1446,11 +1449,13 @@ static const struct sun4i_tcon_quirks sun6i_a31s_quirks = { .has_channel_0 = true, .has_channel_1 = true, .needs_de_be_mux = true, + .dclk_min_div = 1, }; static const struct sun4i_tcon_quirks sun7i_a20_quirks = { .has_channel_0 = true, .has_channel_1 = true, + .dclk_min_div = 4, /* Same display pipeline structure as A10 */ .set_mux = sun4i_a10_tcon_set_mux, }; @@ -1458,11 +1463,13 @@ static const struct sun4i_tcon_quirks sun7i_a20_quirks = { static const struct sun4i_tcon_quirks sun8i_a33_quirks = { .has_channel_0 = true, .has_lvds_alt = true, + .dclk_min_div = 1, }; static const struct sun4i_tcon_quirks sun8i_a83t_lcd_quirks = { .supports_lvds = true, .has_channel_0 = true, + .dclk_min_div = 1, }; static const struct sun4i_tcon_quirks sun8i_a83t_tv_quirks = { @@ -1476,11 +1483,13 @@ static const struct sun4i_tcon_quirks sun8i_r40_tv_quirks = { static const struct sun4i_tcon_quirks sun8i_v3s_quirks = { .has_channel_0 = true, + .dclk_min_div = 1, }; static const struct sun4i_tcon_quirks sun9i_a80_tcon_lcd_quirks = { - .has_channel_0 = true, - .needs_edp_reset = true, + .has_channel_0 = true, + .needs_edp_reset = true, + .dclk_min_div = 1, }; static const struct sun4i_tcon_quirks sun9i_a80_tcon_tv_quirks = { diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.h b/drivers/gpu/drm/sun4i/sun4i_tcon.h index f9f1fe80b206..a62ec826ae71 100644 --- a/drivers/gpu/drm/sun4i/sun4i_tcon.h +++ b/drivers/gpu/drm/sun4i/sun4i_tcon.h @@ -224,6 +224,7 @@ struct sun4i_tcon_quirks { bool needs_de_be_mux; /* sun6i needs mux to select backend */ bool needs_edp_reset; /* a80 edp reset needed for tcon0 access */ bool supports_lvds; /* Does the TCON support an LVDS output? */ + u8 dclk_min_div; /* minimum divider for TCON0 DCLK */ /* callback to handle tcon muxing options */ int (*set_mux)(struct sun4i_tcon *, const struct drm_encoder *); diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c index 1636344ba9ec..f83522717488 100644 --- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c +++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c @@ -437,9 +437,9 @@ static void sun6i_dsi_setup_burst(struct sun6i_dsi *dsi, SUN6I_DSI_BURST_LINE_SYNC_POINT(SUN6I_DSI_SYNC_POINT)); val = SUN6I_DSI_TCON_DRQ_ENABLE_MODE; - } else if ((mode->hsync_end - mode->hdisplay) > 20) { + } else if ((mode->hsync_start - mode->hdisplay) > 20) { /* Maaaaaagic */ - u16 drq = (mode->hsync_end - mode->hdisplay) - 20; + u16 drq = (mode->hsync_start - mode->hdisplay) - 20; drq *= mipi_dsi_pixel_format_to_bpp(device->format); drq /= 32; diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index 6fb7d74ff553..bc7cc32140f8 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -201,19 +201,19 @@ static int tegra_drm_load(struct drm_device *drm, unsigned long flags) if (tegra->hub) tegra_display_hub_cleanup(tegra->hub); device: - host1x_device_exit(device); -fbdev: - drm_kms_helper_poll_fini(drm); - tegra_drm_fb_free(drm); -config: - drm_mode_config_cleanup(drm); - if (tegra->domain) { mutex_destroy(&tegra->mm_lock); drm_mm_takedown(&tegra->mm); put_iova_domain(&tegra->carveout.domain); iova_cache_put(); } + + host1x_device_exit(device); +fbdev: + drm_kms_helper_poll_fini(drm); + tegra_drm_fb_free(drm); +config: + drm_mode_config_cleanup(drm); domain: if (tegra->domain) iommu_domain_free(tegra->domain); diff --git a/drivers/gpu/drm/tegra/sor.c b/drivers/gpu/drm/tegra/sor.c index e1669ada0a40..75e65d9536d5 100644 --- a/drivers/gpu/drm/tegra/sor.c +++ b/drivers/gpu/drm/tegra/sor.c @@ -3200,6 +3200,11 @@ static int tegra_sor_parse_dt(struct tegra_sor *sor) * earlier */ sor->pad = TEGRA_IO_PAD_HDMI_DP0 + sor->index; + } else { + if (sor->soc->supports_edp) + sor->index = 0; + else + sor->index = 1; } err = of_property_read_u32_array(np, "nvidia,xbar-cfg", xbar_cfg, 5); diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 98819462f025..f07803699809 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -926,7 +926,8 @@ EXPORT_SYMBOL(ttm_bo_mem_put); */ static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo, struct ttm_mem_type_manager *man, - struct ttm_mem_reg *mem) + struct ttm_mem_reg *mem, + bool no_wait_gpu) { struct dma_fence *fence; int ret; @@ -935,19 +936,22 @@ static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo, fence = dma_fence_get(man->move); spin_unlock(&man->move_lock); - if (fence) { - dma_resv_add_shared_fence(bo->base.resv, fence); + if (!fence) + return 0; - ret = dma_resv_reserve_shared(bo->base.resv, 1); - if (unlikely(ret)) { - dma_fence_put(fence); - return ret; - } + if (no_wait_gpu) + return -EBUSY; + + dma_resv_add_shared_fence(bo->base.resv, fence); - dma_fence_put(bo->moving); - bo->moving = fence; + ret = dma_resv_reserve_shared(bo->base.resv, 1); + if (unlikely(ret)) { + dma_fence_put(fence); + return ret; } + dma_fence_put(bo->moving); + bo->moving = fence; return 0; } @@ -978,7 +982,7 @@ static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo, return ret; } while (1); - return ttm_bo_add_move_fence(bo, man, mem); + return ttm_bo_add_move_fence(bo, man, mem, ctx->no_wait_gpu); } static uint32_t ttm_bo_select_caching(struct ttm_mem_type_manager *man, @@ -1120,14 +1124,18 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo, if (unlikely(ret)) goto error; - if (mem->mm_node) { - ret = ttm_bo_add_move_fence(bo, man, mem); - if (unlikely(ret)) { - (*man->func->put_node)(man, mem); - goto error; - } - return 0; + if (!mem->mm_node) + continue; + + ret = ttm_bo_add_move_fence(bo, man, mem, ctx->no_wait_gpu); + if (unlikely(ret)) { + (*man->func->put_node)(man, mem); + if (ret == -EBUSY) + continue; + + goto error; } + return 0; } for (i = 0; i < placement->num_busy_placement; ++i) { diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index ee7d4e7b0ee3..0853b980bcb3 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -1285,6 +1285,9 @@ static const struct cec_adap_ops vc4_hdmi_cec_adap_ops = { static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data) { +#ifdef CONFIG_DRM_VC4_HDMI_CEC + struct cec_connector_info conn_info; +#endif struct platform_device *pdev = to_platform_device(dev); struct drm_device *drm = dev_get_drvdata(master); struct vc4_dev *vc4 = drm->dev_private; @@ -1403,13 +1406,15 @@ static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data) #ifdef CONFIG_DRM_VC4_HDMI_CEC hdmi->cec_adap = cec_allocate_adapter(&vc4_hdmi_cec_adap_ops, vc4, "vc4", - CEC_CAP_TRANSMIT | - CEC_CAP_LOG_ADDRS | - CEC_CAP_PASSTHROUGH | - CEC_CAP_RC, 1); + CEC_CAP_DEFAULTS | + CEC_CAP_CONNECTOR_INFO, 1); ret = PTR_ERR_OR_ZERO(hdmi->cec_adap); if (ret < 0) goto err_destroy_conn; + + cec_fill_conn_info_from_drm(&conn_info, hdmi->connector); + cec_s_conn_info(hdmi->cec_adap, &conn_info); + HDMI_WRITE(VC4_HDMI_CPU_MASK_SET, 0xffffffff); value = HDMI_READ(VC4_HDMI_CEC_CNTRL_1); value &= ~VC4_HDMI_CEC_DIV_CLK_CNT_MASK; diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c index eaa5c3352c13..22559670faee 100644 --- a/drivers/gpu/host1x/job.c +++ b/drivers/gpu/host1x/job.c @@ -436,7 +436,8 @@ static int validate(struct host1x_firewall *fw, struct host1x_job_gather *g) return err; } -static inline int copy_gathers(struct host1x_job *job, struct device *dev) +static inline int copy_gathers(struct device *host, struct host1x_job *job, + struct device *dev) { struct host1x_firewall fw; size_t size = 0; @@ -459,12 +460,12 @@ static inline int copy_gathers(struct host1x_job *job, struct device *dev) * Try a non-blocking allocation from a higher priority pools first, * as awaiting for the allocation here is a major performance hit. */ - job->gather_copy_mapped = dma_alloc_wc(dev, size, &job->gather_copy, + job->gather_copy_mapped = dma_alloc_wc(host, size, &job->gather_copy, GFP_NOWAIT); /* the higher priority allocation failed, try the generic-blocking */ if (!job->gather_copy_mapped) - job->gather_copy_mapped = dma_alloc_wc(dev, size, + job->gather_copy_mapped = dma_alloc_wc(host, size, &job->gather_copy, GFP_KERNEL); if (!job->gather_copy_mapped) @@ -512,7 +513,7 @@ int host1x_job_pin(struct host1x_job *job, struct device *dev) goto out; if (IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL)) { - err = copy_gathers(job, dev); + err = copy_gathers(host->dev, job, dev); if (err) goto out; } @@ -573,7 +574,7 @@ void host1x_job_unpin(struct host1x_job *job) job->num_unpins = 0; if (job->gather_copy_size) - dma_free_wc(job->channel->dev, job->gather_copy_size, + dma_free_wc(host->dev, job->gather_copy_size, job->gather_copy_mapped, job->gather_copy); } EXPORT_SYMBOL(host1x_job_unpin); diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 63fdbf09b044..851fe54ea59e 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -211,6 +211,18 @@ static unsigned hid_lookup_collection(struct hid_parser *parser, unsigned type) return 0; /* we know nothing about this usage type */ } +/* + * Concatenate usage which defines 16 bits or less with the + * currently defined usage page to form a 32 bit usage + */ + +static void complete_usage(struct hid_parser *parser, unsigned int index) +{ + parser->local.usage[index] &= 0xFFFF; + parser->local.usage[index] |= + (parser->global.usage_page & 0xFFFF) << 16; +} + /* * Add a usage to the temporary parser table. */ @@ -222,6 +234,14 @@ static int hid_add_usage(struct hid_parser *parser, unsigned usage, u8 size) return -1; } parser->local.usage[parser->local.usage_index] = usage; + + /* + * If Usage item only includes usage id, concatenate it with + * currently defined usage page + */ + if (size <= 2) + complete_usage(parser, parser->local.usage_index); + parser->local.usage_size[parser->local.usage_index] = size; parser->local.collection_index[parser->local.usage_index] = parser->collection_stack_ptr ? @@ -268,6 +288,12 @@ static int hid_add_field(struct hid_parser *parser, unsigned report_type, unsign offset = report->size; report->size += parser->global.report_size * parser->global.report_count; + /* Total size check: Allow for possible report index byte */ + if (report->size > (HID_MAX_BUFFER_SIZE - 1) << 3) { + hid_err(parser->device, "report is too long\n"); + return -1; + } + if (!parser->local.usage_index) /* Ignore padding fields */ return 0; @@ -543,13 +569,32 @@ static int hid_parser_local(struct hid_parser *parser, struct hid_item *item) * usage value." */ -static void hid_concatenate_usage_page(struct hid_parser *parser) +static void hid_concatenate_last_usage_page(struct hid_parser *parser) { int i; + unsigned int usage_page; + unsigned int current_page; - for (i = 0; i < parser->local.usage_index; i++) - if (parser->local.usage_size[i] <= 2) - parser->local.usage[i] += parser->global.usage_page << 16; + if (!parser->local.usage_index) + return; + + usage_page = parser->global.usage_page; + + /* + * Concatenate usage page again only if last declared Usage Page + * has not been already used in previous usages concatenation + */ + for (i = parser->local.usage_index - 1; i >= 0; i--) { + if (parser->local.usage_size[i] > 2) + /* Ignore extended usages */ + continue; + + current_page = parser->local.usage[i] >> 16; + if (current_page == usage_page) + break; + + complete_usage(parser, i); + } } /* @@ -561,7 +606,7 @@ static int hid_parser_main(struct hid_parser *parser, struct hid_item *item) __u32 data; int ret; - hid_concatenate_usage_page(parser); + hid_concatenate_last_usage_page(parser); data = item_udata(item); @@ -742,6 +787,10 @@ static void hid_scan_feature_usage(struct hid_parser *parser, u32 usage) if (usage == 0xff0000c5 && parser->global.report_count == 256 && parser->global.report_size == 8) parser->scan_flags |= HID_SCAN_FLAG_MT_WIN_8; + + if (usage == 0xff0000c6 && parser->global.report_count == 1 && + parser->global.report_size == 8) + parser->scan_flags |= HID_SCAN_FLAG_MT_WIN_8; } static void hid_scan_collection(struct hid_parser *parser, unsigned type) @@ -772,7 +821,7 @@ static int hid_scan_main(struct hid_parser *parser, struct hid_item *item) __u32 data; int i; - hid_concatenate_usage_page(parser); + hid_concatenate_last_usage_page(parser); data = item_udata(item); diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 447e8db21174..6273e7178e78 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -573,6 +573,7 @@ #define USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE_094A 0x094a #define USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE_0941 0x0941 #define USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE_0641 0x0641 +#define USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE_1f4a 0x1f4a #define USB_VENDOR_ID_HUION 0x256c #define USB_DEVICE_ID_HUION_TABLET 0x006e @@ -959,6 +960,7 @@ #define I2C_VENDOR_ID_RAYDIUM 0x2386 #define I2C_PRODUCT_ID_RAYDIUM_4B33 0x4b33 +#define I2C_PRODUCT_ID_RAYDIUM_3118 0x3118 #define USB_VENDOR_ID_RAZER 0x1532 #define USB_DEVICE_ID_RAZER_BLADE_14 0x011D diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 63855f275a38..dea9cc65bf80 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -1132,9 +1132,15 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel } mapped: - if (device->driver->input_mapped && device->driver->input_mapped(device, - hidinput, field, usage, &bit, &max) < 0) - goto ignore; + if (device->driver->input_mapped && + device->driver->input_mapped(device, hidinput, field, usage, + &bit, &max) < 0) { + /* + * The driver indicated that no further generic handling + * of the usage is desired. + */ + return; + } set_bit(usage->type, input->evbit); @@ -1215,9 +1221,11 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel set_bit(MSC_SCAN, input->mscbit); } -ignore: return; +ignore: + usage->type = 0; + usage->code = 0; } static void hidinput_handle_scroll(struct hid_usage *usage, diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index 8e91e2f06cb4..cd9193078525 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -1102,6 +1102,9 @@ static int hidpp20_batterylevel_get_battery_capacity(struct hidpp_device *hidpp, ret = hidpp_send_fap_command_sync(hidpp, feature_index, CMD_BATTERY_LEVEL_STATUS_GET_BATTERY_LEVEL_STATUS, NULL, 0, &response); + /* Ignore these intermittent errors */ + if (ret == HIDPP_ERROR_RESOURCE_ERROR) + return -EIO; if (ret > 0) { hid_err(hidpp->hid_dev, "%s: received protocol error 0x%02x\n", __func__, ret); diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index c50bcd967d99..9a35af1e2662 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -94,6 +94,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE_094A), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE_0941), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE_0641), HID_QUIRK_ALWAYS_POLL }, + { HID_USB_DEVICE(USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE_1f4a), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_IDEACOM, USB_DEVICE_ID_IDEACOM_IDC6680), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_INNOMEDIA, USB_DEVICE_ID_INNEX_GENESIS_ATARI), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M610X), HID_QUIRK_MULTI_INPUT }, diff --git a/drivers/hid/hid-rmi.c b/drivers/hid/hid-rmi.c index 7c6abd7e0979..9ce22acdfaca 100644 --- a/drivers/hid/hid-rmi.c +++ b/drivers/hid/hid-rmi.c @@ -744,7 +744,8 @@ static void rmi_remove(struct hid_device *hdev) { struct rmi_data *hdata = hid_get_drvdata(hdev); - if (hdata->device_flags & RMI_DEVICE) { + if ((hdata->device_flags & RMI_DEVICE) + && test_bit(RMI_STARTED, &hdata->flags)) { clear_bit(RMI_STARTED, &hdata->flags); cancel_work_sync(&hdata->reset_work); rmi_unregister_transport_device(&hdata->xport); diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c index bbc6ec1aa5cb..b382c6bf2c5c 100644 --- a/drivers/hid/hidraw.c +++ b/drivers/hid/hidraw.c @@ -249,13 +249,14 @@ static ssize_t hidraw_get_report(struct file *file, char __user *buffer, size_t static __poll_t hidraw_poll(struct file *file, poll_table *wait) { struct hidraw_list *list = file->private_data; + __poll_t mask = EPOLLOUT | EPOLLWRNORM; /* hidraw is always writable */ poll_wait(file, &list->hidraw->wait, wait); if (list->head != list->tail) - return EPOLLIN | EPOLLRDNORM | EPOLLOUT; + mask |= EPOLLIN | EPOLLRDNORM; if (!list->hidraw->exist) - return EPOLLERR | EPOLLHUP; - return 0; + mask |= EPOLLERR | EPOLLHUP; + return mask; } static int hidraw_open(struct inode *inode, struct file *file) diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c index 04c088131e04..ac44bf752ff1 100644 --- a/drivers/hid/i2c-hid/i2c-hid-core.c +++ b/drivers/hid/i2c-hid/i2c-hid-core.c @@ -48,6 +48,7 @@ #define I2C_HID_QUIRK_SET_PWR_WAKEUP_DEV BIT(0) #define I2C_HID_QUIRK_NO_IRQ_AFTER_RESET BIT(1) #define I2C_HID_QUIRK_BOGUS_IRQ BIT(4) +#define I2C_HID_QUIRK_RESET_ON_RESUME BIT(5) /* flags */ #define I2C_HID_STARTED 0 @@ -170,8 +171,12 @@ static const struct i2c_hid_quirks { I2C_HID_QUIRK_SET_PWR_WAKEUP_DEV }, { I2C_VENDOR_ID_HANTICK, I2C_PRODUCT_ID_HANTICK_5288, I2C_HID_QUIRK_NO_IRQ_AFTER_RESET }, + { I2C_VENDOR_ID_RAYDIUM, I2C_PRODUCT_ID_RAYDIUM_3118, + I2C_HID_QUIRK_NO_IRQ_AFTER_RESET }, { USB_VENDOR_ID_ELAN, HID_ANY_ID, I2C_HID_QUIRK_BOGUS_IRQ }, + { USB_VENDOR_ID_ALPS_JP, HID_ANY_ID, + I2C_HID_QUIRK_RESET_ON_RESUME }, { 0, 0 } }; @@ -1212,8 +1217,15 @@ static int i2c_hid_resume(struct device *dev) * solves "incomplete reports" on Raydium devices 2386:3118 and * 2386:4B33 and fixes various SIS touchscreens no longer sending * data after a suspend/resume. + * + * However some ALPS touchpads generate IRQ storm without reset, so + * let's still reset them here. */ - ret = i2c_hid_set_power(client, I2C_HID_PWR_ON); + if (ihid->quirks & I2C_HID_QUIRK_RESET_ON_RESUME) + ret = i2c_hid_hwreset(client); + else + ret = i2c_hid_set_power(client, I2C_HID_PWR_ON); + if (ret) return ret; diff --git a/drivers/hid/uhid.c b/drivers/hid/uhid.c index fa0cc0899827..8fe3efcb8327 100644 --- a/drivers/hid/uhid.c +++ b/drivers/hid/uhid.c @@ -766,13 +766,14 @@ static ssize_t uhid_char_write(struct file *file, const char __user *buffer, static __poll_t uhid_char_poll(struct file *file, poll_table *wait) { struct uhid_device *uhid = file->private_data; + __poll_t mask = EPOLLOUT | EPOLLWRNORM; /* uhid is always writable */ poll_wait(file, &uhid->waitq, wait); if (uhid->head != uhid->tail) - return EPOLLIN | EPOLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; - return 0; + return mask; } static const struct file_operations uhid_fops = { diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c index 1f9bc4483465..c879b214a479 100644 --- a/drivers/hid/usbhid/hiddev.c +++ b/drivers/hid/usbhid/hiddev.c @@ -241,12 +241,51 @@ static int hiddev_release(struct inode * inode, struct file * file) return 0; } +static int __hiddev_open(struct hiddev *hiddev, struct file *file) +{ + struct hiddev_list *list; + int error; + + lockdep_assert_held(&hiddev->existancelock); + + list = vzalloc(sizeof(*list)); + if (!list) + return -ENOMEM; + + mutex_init(&list->thread_lock); + list->hiddev = hiddev; + + if (!hiddev->open++) { + error = hid_hw_power(hiddev->hid, PM_HINT_FULLON); + if (error < 0) + goto err_drop_count; + + error = hid_hw_open(hiddev->hid); + if (error < 0) + goto err_normal_power; + } + + spin_lock_irq(&hiddev->list_lock); + list_add_tail(&list->node, &hiddev->list); + spin_unlock_irq(&hiddev->list_lock); + + file->private_data = list; + + return 0; + +err_normal_power: + hid_hw_power(hiddev->hid, PM_HINT_NORMAL); +err_drop_count: + hiddev->open--; + vfree(list); + return error; +} + /* * open file op */ static int hiddev_open(struct inode *inode, struct file *file) { - struct hiddev_list *list; struct usb_interface *intf; struct hid_device *hid; struct hiddev *hiddev; @@ -255,66 +294,14 @@ static int hiddev_open(struct inode *inode, struct file *file) intf = usbhid_find_interface(iminor(inode)); if (!intf) return -ENODEV; + hid = usb_get_intfdata(intf); hiddev = hid->hiddev; - if (!(list = vzalloc(sizeof(struct hiddev_list)))) - return -ENOMEM; - mutex_init(&list->thread_lock); - list->hiddev = hiddev; - file->private_data = list; - - /* - * no need for locking because the USB major number - * is shared which usbcore guards against disconnect - */ - if (list->hiddev->exist) { - if (!list->hiddev->open++) { - res = hid_hw_open(hiddev->hid); - if (res < 0) - goto bail; - } - } else { - res = -ENODEV; - goto bail; - } - - spin_lock_irq(&list->hiddev->list_lock); - list_add_tail(&list->node, &hiddev->list); - spin_unlock_irq(&list->hiddev->list_lock); - mutex_lock(&hiddev->existancelock); - /* - * recheck exist with existance lock held to - * avoid opening a disconnected device - */ - if (!list->hiddev->exist) { - res = -ENODEV; - goto bail_unlock; - } - if (!list->hiddev->open++) - if (list->hiddev->exist) { - struct hid_device *hid = hiddev->hid; - res = hid_hw_power(hid, PM_HINT_FULLON); - if (res < 0) - goto bail_unlock; - res = hid_hw_open(hid); - if (res < 0) - goto bail_normal_power; - } - mutex_unlock(&hiddev->existancelock); - return 0; -bail_normal_power: - hid_hw_power(hid, PM_HINT_NORMAL); -bail_unlock: + res = hiddev->exist ? __hiddev_open(hiddev, file) : -ENODEV; mutex_unlock(&hiddev->existancelock); - spin_lock_irq(&list->hiddev->list_lock); - list_del(&list->node); - spin_unlock_irq(&list->hiddev->list_lock); -bail: - file->private_data = NULL; - vfree(list); return res; } diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 53a60c81e220..05ead1735c6e 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -2308,7 +2308,7 @@ static void hv_crash_handler(struct pt_regs *regs) vmbus_connection.conn_state = DISCONNECTED; cpu = smp_processor_id(); hv_stimer_cleanup(cpu); - hv_synic_cleanup(cpu); + hv_synic_disable_regs(cpu); hyperv_cleanup(); }; diff --git a/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c b/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c index 219c10eb752c..ee44640edeb5 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c @@ -652,10 +652,13 @@ static ssize_t cyc_threshold_store(struct device *dev, if (kstrtoul(buf, 16, &val)) return -EINVAL; + + /* mask off max threshold before checking min value */ + val &= ETM_CYC_THRESHOLD_MASK; if (val < drvdata->ccitmin) return -EINVAL; - config->ccctlr = val & ETM_CYC_THRESHOLD_MASK; + config->ccctlr = val; return size; } static DEVICE_ATTR_RW(cyc_threshold); @@ -686,14 +689,16 @@ static ssize_t bb_ctrl_store(struct device *dev, return -EINVAL; if (!drvdata->nr_addr_cmp) return -EINVAL; + /* - * Bit[7:0] selects which address range comparator is used for - * branch broadcast control. + * Bit[8] controls include(1) / exclude(0), bits[0-7] select + * individual range comparators. If include then at least 1 + * range must be selected. */ - if (BMVAL(val, 0, 7) > drvdata->nr_addr_cmp) + if ((val & BIT(8)) && (BMVAL(val, 0, 7) == 0)) return -EINVAL; - config->bb_ctrl = val; + config->bb_ctrl = val & GENMASK(8, 0); return size; } static DEVICE_ATTR_RW(bb_ctrl); @@ -1324,8 +1329,8 @@ static ssize_t seq_event_store(struct device *dev, spin_lock(&drvdata->spinlock); idx = config->seq_idx; - /* RST, bits[7:0] */ - config->seq_ctrl[idx] = val & 0xFF; + /* Seq control has two masks B[15:8] F[7:0] */ + config->seq_ctrl[idx] = val & 0xFFFF; spin_unlock(&drvdata->spinlock); return size; } @@ -1580,7 +1585,7 @@ static ssize_t res_ctrl_store(struct device *dev, if (idx % 2 != 0) /* PAIRINV, bit[21] */ val &= ~BIT(21); - config->res_ctrl[idx] = val; + config->res_ctrl[idx] = val & GENMASK(21, 0); spin_unlock(&drvdata->spinlock); return size; } diff --git a/drivers/hwtracing/coresight/coresight-funnel.c b/drivers/hwtracing/coresight/coresight-funnel.c index 05f7896c3a01..b605889b507a 100644 --- a/drivers/hwtracing/coresight/coresight-funnel.c +++ b/drivers/hwtracing/coresight/coresight-funnel.c @@ -38,12 +38,14 @@ DEFINE_CORESIGHT_DEVLIST(funnel_devs, "funnel"); * @atclk: optional clock for the core parts of the funnel. * @csdev: component vitals needed by the framework. * @priority: port selection order. + * @spinlock: serialize enable/disable operations. */ struct funnel_drvdata { void __iomem *base; struct clk *atclk; struct coresight_device *csdev; unsigned long priority; + spinlock_t spinlock; }; static int dynamic_funnel_enable_hw(struct funnel_drvdata *drvdata, int port) @@ -76,11 +78,21 @@ static int funnel_enable(struct coresight_device *csdev, int inport, { int rc = 0; struct funnel_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - - if (drvdata->base) - rc = dynamic_funnel_enable_hw(drvdata, inport); - + unsigned long flags; + bool first_enable = false; + + spin_lock_irqsave(&drvdata->spinlock, flags); + if (atomic_read(&csdev->refcnt[inport]) == 0) { + if (drvdata->base) + rc = dynamic_funnel_enable_hw(drvdata, inport); + if (!rc) + first_enable = true; + } if (!rc) + atomic_inc(&csdev->refcnt[inport]); + spin_unlock_irqrestore(&drvdata->spinlock, flags); + + if (first_enable) dev_dbg(&csdev->dev, "FUNNEL inport %d enabled\n", inport); return rc; } @@ -107,11 +119,19 @@ static void funnel_disable(struct coresight_device *csdev, int inport, int outport) { struct funnel_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + unsigned long flags; + bool last_disable = false; + + spin_lock_irqsave(&drvdata->spinlock, flags); + if (atomic_dec_return(&csdev->refcnt[inport]) == 0) { + if (drvdata->base) + dynamic_funnel_disable_hw(drvdata, inport); + last_disable = true; + } + spin_unlock_irqrestore(&drvdata->spinlock, flags); - if (drvdata->base) - dynamic_funnel_disable_hw(drvdata, inport); - - dev_dbg(&csdev->dev, "FUNNEL inport %d disabled\n", inport); + if (last_disable) + dev_dbg(&csdev->dev, "FUNNEL inport %d disabled\n", inport); } static const struct coresight_ops_link funnel_link_ops = { diff --git a/drivers/hwtracing/coresight/coresight-replicator.c b/drivers/hwtracing/coresight/coresight-replicator.c index b29ba640eb25..43304196a1a6 100644 --- a/drivers/hwtracing/coresight/coresight-replicator.c +++ b/drivers/hwtracing/coresight/coresight-replicator.c @@ -31,11 +31,13 @@ DEFINE_CORESIGHT_DEVLIST(replicator_devs, "replicator"); * whether this one is programmable or not. * @atclk: optional clock for the core parts of the replicator. * @csdev: component vitals needed by the framework + * @spinlock: serialize enable/disable operations. */ struct replicator_drvdata { void __iomem *base; struct clk *atclk; struct coresight_device *csdev; + spinlock_t spinlock; }; static void dynamic_replicator_reset(struct replicator_drvdata *drvdata) @@ -97,10 +99,22 @@ static int replicator_enable(struct coresight_device *csdev, int inport, { int rc = 0; struct replicator_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - - if (drvdata->base) - rc = dynamic_replicator_enable(drvdata, inport, outport); + unsigned long flags; + bool first_enable = false; + + spin_lock_irqsave(&drvdata->spinlock, flags); + if (atomic_read(&csdev->refcnt[outport]) == 0) { + if (drvdata->base) + rc = dynamic_replicator_enable(drvdata, inport, + outport); + if (!rc) + first_enable = true; + } if (!rc) + atomic_inc(&csdev->refcnt[outport]); + spin_unlock_irqrestore(&drvdata->spinlock, flags); + + if (first_enable) dev_dbg(&csdev->dev, "REPLICATOR enabled\n"); return rc; } @@ -137,10 +151,19 @@ static void replicator_disable(struct coresight_device *csdev, int inport, int outport) { struct replicator_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + unsigned long flags; + bool last_disable = false; + + spin_lock_irqsave(&drvdata->spinlock, flags); + if (atomic_dec_return(&csdev->refcnt[outport]) == 0) { + if (drvdata->base) + dynamic_replicator_disable(drvdata, inport, outport); + last_disable = true; + } + spin_unlock_irqrestore(&drvdata->spinlock, flags); - if (drvdata->base) - dynamic_replicator_disable(drvdata, inport, outport); - dev_dbg(&csdev->dev, "REPLICATOR disabled\n"); + if (last_disable) + dev_dbg(&csdev->dev, "REPLICATOR disabled\n"); } static const struct coresight_ops_link replicator_link_ops = { diff --git a/drivers/hwtracing/coresight/coresight-tmc-etf.c b/drivers/hwtracing/coresight/coresight-tmc-etf.c index 807416b75ecc..d0cc3985b72a 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etf.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etf.c @@ -334,9 +334,10 @@ static int tmc_disable_etf_sink(struct coresight_device *csdev) static int tmc_enable_etf_link(struct coresight_device *csdev, int inport, int outport) { - int ret; + int ret = 0; unsigned long flags; struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + bool first_enable = false; spin_lock_irqsave(&drvdata->spinlock, flags); if (drvdata->reading) { @@ -344,12 +345,18 @@ static int tmc_enable_etf_link(struct coresight_device *csdev, return -EBUSY; } - ret = tmc_etf_enable_hw(drvdata); + if (atomic_read(&csdev->refcnt[0]) == 0) { + ret = tmc_etf_enable_hw(drvdata); + if (!ret) { + drvdata->mode = CS_MODE_SYSFS; + first_enable = true; + } + } if (!ret) - drvdata->mode = CS_MODE_SYSFS; + atomic_inc(&csdev->refcnt[0]); spin_unlock_irqrestore(&drvdata->spinlock, flags); - if (!ret) + if (first_enable) dev_dbg(&csdev->dev, "TMC-ETF enabled\n"); return ret; } @@ -359,6 +366,7 @@ static void tmc_disable_etf_link(struct coresight_device *csdev, { unsigned long flags; struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + bool last_disable = false; spin_lock_irqsave(&drvdata->spinlock, flags); if (drvdata->reading) { @@ -366,11 +374,15 @@ static void tmc_disable_etf_link(struct coresight_device *csdev, return; } - tmc_etf_disable_hw(drvdata); - drvdata->mode = CS_MODE_DISABLED; + if (atomic_dec_return(&csdev->refcnt[0]) == 0) { + tmc_etf_disable_hw(drvdata); + drvdata->mode = CS_MODE_DISABLED; + last_disable = true; + } spin_unlock_irqrestore(&drvdata->spinlock, flags); - dev_dbg(&csdev->dev, "TMC-ETF disabled\n"); + if (last_disable) + dev_dbg(&csdev->dev, "TMC-ETF disabled\n"); } static void *tmc_alloc_etf_buffer(struct coresight_device *csdev, diff --git a/drivers/hwtracing/coresight/coresight.c b/drivers/hwtracing/coresight/coresight.c index 6453c67a4d01..0bbce0d29158 100644 --- a/drivers/hwtracing/coresight/coresight.c +++ b/drivers/hwtracing/coresight/coresight.c @@ -253,9 +253,9 @@ static int coresight_enable_link(struct coresight_device *csdev, struct coresight_device *parent, struct coresight_device *child) { - int ret; + int ret = 0; int link_subtype; - int refport, inport, outport; + int inport, outport; if (!parent || !child) return -EINVAL; @@ -264,29 +264,17 @@ static int coresight_enable_link(struct coresight_device *csdev, outport = coresight_find_link_outport(csdev, child); link_subtype = csdev->subtype.link_subtype; - if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG) - refport = inport; - else if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_SPLIT) - refport = outport; - else - refport = 0; - - if (refport < 0) - return refport; + if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG && inport < 0) + return inport; + if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_SPLIT && outport < 0) + return outport; - if (atomic_inc_return(&csdev->refcnt[refport]) == 1) { - if (link_ops(csdev)->enable) { - ret = link_ops(csdev)->enable(csdev, inport, outport); - if (ret) { - atomic_dec(&csdev->refcnt[refport]); - return ret; - } - } - } - - csdev->enable = true; + if (link_ops(csdev)->enable) + ret = link_ops(csdev)->enable(csdev, inport, outport); + if (!ret) + csdev->enable = true; - return 0; + return ret; } static void coresight_disable_link(struct coresight_device *csdev, @@ -295,7 +283,7 @@ static void coresight_disable_link(struct coresight_device *csdev, { int i, nr_conns; int link_subtype; - int refport, inport, outport; + int inport, outport; if (!parent || !child) return; @@ -305,20 +293,15 @@ static void coresight_disable_link(struct coresight_device *csdev, link_subtype = csdev->subtype.link_subtype; if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG) { - refport = inport; nr_conns = csdev->pdata->nr_inport; } else if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_SPLIT) { - refport = outport; nr_conns = csdev->pdata->nr_outport; } else { - refport = 0; nr_conns = 1; } - if (atomic_dec_return(&csdev->refcnt[refport]) == 0) { - if (link_ops(csdev)->disable) - link_ops(csdev)->disable(csdev, inport, outport); - } + if (link_ops(csdev)->disable) + link_ops(csdev)->disable(csdev, inport, outport); for (i = 0; i < nr_conns; i++) if (atomic_read(&csdev->refcnt[i]) != 0) diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c index d5c1821b31c6..ca232ec565e8 100644 --- a/drivers/hwtracing/intel_th/core.c +++ b/drivers/hwtracing/intel_th/core.c @@ -649,10 +649,8 @@ intel_th_subdevice_alloc(struct intel_th *th, } err = intel_th_device_add_resources(thdev, res, subdev->nres); - if (err) { - put_device(&thdev->dev); + if (err) goto fail_put_device; - } if (subdev->type == INTEL_TH_OUTPUT) { if (subdev->mknode) @@ -667,10 +665,8 @@ intel_th_subdevice_alloc(struct intel_th *th, } err = device_add(&thdev->dev); - if (err) { - put_device(&thdev->dev); + if (err) goto fail_free_res; - } /* need switch driver to be loaded to enumerate the rest */ if (subdev->type == INTEL_TH_SWITCH && !req) { @@ -838,9 +834,6 @@ static irqreturn_t intel_th_irq(int irq, void *data) ret |= d->irq(th->thdev[i]); } - if (ret == IRQ_NONE) - pr_warn_ratelimited("nobody cared for irq\n"); - return ret; } @@ -891,6 +884,7 @@ intel_th_alloc(struct device *dev, struct intel_th_drvdata *drvdata, if (th->irq == -1) th->irq = devres[r].start; + th->num_irqs++; break; default: dev_warn(dev, "Unknown resource type %lx\n", @@ -944,6 +938,9 @@ void intel_th_free(struct intel_th *th) th->num_thdevs = 0; + for (i = 0; i < th->num_irqs; i++) + devm_free_irq(th->dev, th->irq + i, th); + pm_runtime_get_sync(th->dev); pm_runtime_forbid(th->dev); diff --git a/drivers/hwtracing/intel_th/intel_th.h b/drivers/hwtracing/intel_th/intel_th.h index 0df480072b6c..6f4f5486fe6d 100644 --- a/drivers/hwtracing/intel_th/intel_th.h +++ b/drivers/hwtracing/intel_th/intel_th.h @@ -261,6 +261,7 @@ enum th_mmio_idx { * @num_thdevs: number of devices in the @thdev array * @num_resources: number of resources in the @resource array * @irq: irq number + * @num_irqs: number of IRQs is use * @id: this Intel TH controller's device ID in the system * @major: device node major for output devices */ @@ -277,6 +278,7 @@ struct intel_th { unsigned int num_thdevs; unsigned int num_resources; int irq; + int num_irqs; int id; int major; diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c index 6d240dfae9d9..8e48c7458aa3 100644 --- a/drivers/hwtracing/intel_th/msu.c +++ b/drivers/hwtracing/intel_th/msu.c @@ -1676,10 +1676,13 @@ static int intel_th_msc_init(struct msc *msc) return 0; } -static void msc_win_switch(struct msc *msc) +static int msc_win_switch(struct msc *msc) { struct msc_window *first; + if (list_empty(&msc->win_list)) + return -EINVAL; + first = list_first_entry(&msc->win_list, struct msc_window, entry); if (msc_is_last_win(msc->cur_win)) @@ -1691,6 +1694,8 @@ static void msc_win_switch(struct msc *msc) msc->base_addr = msc_win_base_dma(msc->cur_win); intel_th_trace_switch(msc->thdev); + + return 0; } /** @@ -2025,16 +2030,15 @@ win_switch_store(struct device *dev, struct device_attribute *attr, if (val != 1) return -EINVAL; + ret = -EINVAL; mutex_lock(&msc->buf_mutex); /* * Window switch can only happen in the "multi" mode. * If a external buffer is engaged, they have the full * control over window switching. */ - if (msc->mode != MSC_MODE_MULTI || msc->mbuf) - ret = -ENOTSUPP; - else - msc_win_switch(msc); + if (msc->mode == MSC_MODE_MULTI && !msc->mbuf) + ret = msc_win_switch(msc); mutex_unlock(&msc->buf_mutex); return ret ? ret : size; diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c index 03ca5b1bef9f..e9d90b53bbc4 100644 --- a/drivers/hwtracing/intel_th/pci.c +++ b/drivers/hwtracing/intel_th/pci.c @@ -204,11 +204,26 @@ static const struct pci_device_id intel_th_pci_id_table[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x06a6), .driver_data = (kernel_ulong_t)&intel_th_2x, }, + { + /* Comet Lake PCH-V */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa3a6), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, { /* Ice Lake NNPI */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x45c5), .driver_data = (kernel_ulong_t)&intel_th_2x, }, + { + /* Ice Lake CPU */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x8a29), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Tiger Lake CPU */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x9a33), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, { /* Tiger Lake PCH */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa0a6), @@ -219,6 +234,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4da6), .driver_data = (kernel_ulong_t)&intel_th_2x, }, + { + /* Elkhart Lake */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4b26), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, { 0 }, }; diff --git a/drivers/hwtracing/stm/policy.c b/drivers/hwtracing/stm/policy.c index 4b9e44b227d8..4f932a419752 100644 --- a/drivers/hwtracing/stm/policy.c +++ b/drivers/hwtracing/stm/policy.c @@ -345,7 +345,11 @@ void stp_policy_unbind(struct stp_policy *policy) stm->policy = NULL; policy->stm = NULL; + /* + * Drop the reference on the protocol driver and lose the link. + */ stm_put_protocol(stm->pdrv); + stm->pdrv = NULL; stm_put_device(stm); } diff --git a/drivers/i2c/busses/i2c-bcm2835.c b/drivers/i2c/busses/i2c-bcm2835.c index e01b2b57e724..5ab901ad615d 100644 --- a/drivers/i2c/busses/i2c-bcm2835.c +++ b/drivers/i2c/busses/i2c-bcm2835.c @@ -58,6 +58,7 @@ struct bcm2835_i2c_dev { struct i2c_adapter adapter; struct completion completion; struct i2c_msg *curr_msg; + struct clk *bus_clk; int num_msgs; u32 msg_err; u8 *msg_buf; @@ -404,7 +405,6 @@ static int bcm2835_i2c_probe(struct platform_device *pdev) struct resource *mem, *irq; int ret; struct i2c_adapter *adap; - struct clk *bus_clk; struct clk *mclk; u32 bus_clk_rate; @@ -427,11 +427,11 @@ static int bcm2835_i2c_probe(struct platform_device *pdev) return PTR_ERR(mclk); } - bus_clk = bcm2835_i2c_register_div(&pdev->dev, mclk, i2c_dev); + i2c_dev->bus_clk = bcm2835_i2c_register_div(&pdev->dev, mclk, i2c_dev); - if (IS_ERR(bus_clk)) { + if (IS_ERR(i2c_dev->bus_clk)) { dev_err(&pdev->dev, "Could not register clock\n"); - return PTR_ERR(bus_clk); + return PTR_ERR(i2c_dev->bus_clk); } ret = of_property_read_u32(pdev->dev.of_node, "clock-frequency", @@ -442,13 +442,13 @@ static int bcm2835_i2c_probe(struct platform_device *pdev) bus_clk_rate = 100000; } - ret = clk_set_rate_exclusive(bus_clk, bus_clk_rate); + ret = clk_set_rate_exclusive(i2c_dev->bus_clk, bus_clk_rate); if (ret < 0) { dev_err(&pdev->dev, "Could not set clock frequency\n"); return ret; } - ret = clk_prepare_enable(bus_clk); + ret = clk_prepare_enable(i2c_dev->bus_clk); if (ret) { dev_err(&pdev->dev, "Couldn't prepare clock"); return ret; @@ -491,10 +491,9 @@ static int bcm2835_i2c_probe(struct platform_device *pdev) static int bcm2835_i2c_remove(struct platform_device *pdev) { struct bcm2835_i2c_dev *i2c_dev = platform_get_drvdata(pdev); - struct clk *bus_clk = devm_clk_get(i2c_dev->dev, "div"); - clk_rate_exclusive_put(bus_clk); - clk_disable_unprepare(bus_clk); + clk_rate_exclusive_put(i2c_dev->bus_clk); + clk_disable_unprepare(i2c_dev->bus_clk); free_irq(i2c_dev->irq, i2c_dev); i2c_del_adapter(&i2c_dev->adapter); diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c index b24e7b937f21..84cfed17ff4f 100644 --- a/drivers/i2c/busses/i2c-stm32f7.c +++ b/drivers/i2c/busses/i2c-stm32f7.c @@ -1985,6 +1985,11 @@ static int stm32f7_i2c_probe(struct platform_device *pdev) pm_runtime_set_suspended(i2c_dev->dev); pm_runtime_dont_use_autosuspend(i2c_dev->dev); + if (i2c_dev->dma) { + stm32_i2c_dma_free(i2c_dev->dma); + i2c_dev->dma = NULL; + } + clk_free: clk_disable_unprepare(i2c_dev->clk); @@ -1995,21 +2000,21 @@ static int stm32f7_i2c_remove(struct platform_device *pdev) { struct stm32f7_i2c_dev *i2c_dev = platform_get_drvdata(pdev); - if (i2c_dev->dma) { - stm32_i2c_dma_free(i2c_dev->dma); - i2c_dev->dma = NULL; - } - i2c_del_adapter(&i2c_dev->adap); pm_runtime_get_sync(i2c_dev->dev); - clk_disable_unprepare(i2c_dev->clk); - pm_runtime_put_noidle(i2c_dev->dev); pm_runtime_disable(i2c_dev->dev); pm_runtime_set_suspended(i2c_dev->dev); pm_runtime_dont_use_autosuspend(i2c_dev->dev); + if (i2c_dev->dma) { + stm32_i2c_dma_free(i2c_dev->dma); + i2c_dev->dma = NULL; + } + + clk_disable_unprepare(i2c_dev->clk); + return 0; } diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 5f6a4985f2bc..810a942eaa8e 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -186,10 +186,11 @@ int i2c_generic_scl_recovery(struct i2c_adapter *adap) * If we can set SDA, we will always create a STOP to ensure additional * pulses will do no harm. This is achieved by letting SDA follow SCL * half a cycle later. Check the 'incomplete_write_byte' fault injector - * for details. + * for details. Note that we must honour tsu:sto, 4us, but lets use 5us + * here for simplicity. */ bri->set_scl(adap, scl); - ndelay(RECOVERY_NDELAY / 2); + ndelay(RECOVERY_NDELAY); if (bri->set_sda) bri->set_sda(adap, scl); ndelay(RECOVERY_NDELAY / 2); @@ -211,7 +212,13 @@ int i2c_generic_scl_recovery(struct i2c_adapter *adap) scl = !scl; bri->set_scl(adap, scl); /* Creating STOP again, see above */ - ndelay(RECOVERY_NDELAY / 2); + if (scl) { + /* Honour minimum tsu:sto */ + ndelay(RECOVERY_NDELAY); + } else { + /* Honour minimum tf and thd:dat */ + ndelay(RECOVERY_NDELAY / 2); + } if (bri->set_sda) bri->set_sda(adap, scl); ndelay(RECOVERY_NDELAY / 2); diff --git a/drivers/iio/accel/st_accel_core.c b/drivers/iio/accel/st_accel_core.c index 2e37f8a6d8cf..be661396095c 100644 --- a/drivers/iio/accel/st_accel_core.c +++ b/drivers/iio/accel/st_accel_core.c @@ -993,6 +993,7 @@ static const struct iio_trigger_ops st_accel_trigger_ops = { #define ST_ACCEL_TRIGGER_OPS NULL #endif +#ifdef CONFIG_ACPI static const struct iio_mount_matrix * get_mount_matrix(const struct iio_dev *indio_dev, const struct iio_chan_spec *chan) @@ -1013,7 +1014,6 @@ static const struct iio_chan_spec_ext_info mount_matrix_ext_info[] = { static int apply_acpi_orientation(struct iio_dev *indio_dev, struct iio_chan_spec *channels) { -#ifdef CONFIG_ACPI struct st_sensor_data *adata = iio_priv(indio_dev); struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL}; struct acpi_device *adev; @@ -1141,10 +1141,14 @@ static int apply_acpi_orientation(struct iio_dev *indio_dev, out: kfree(buffer.pointer); return ret; +} #else /* !CONFIG_ACPI */ +static int apply_acpi_orientation(struct iio_dev *indio_dev, + struct iio_chan_spec *channels) +{ return 0; -#endif } +#endif /* * st_accel_get_settings() - get sensor settings from device name diff --git a/drivers/iio/adc/ad7124.c b/drivers/iio/adc/ad7124.c index edc6f1cc90b2..3f03abf100b5 100644 --- a/drivers/iio/adc/ad7124.c +++ b/drivers/iio/adc/ad7124.c @@ -39,6 +39,8 @@ #define AD7124_STATUS_POR_FLAG_MSK BIT(4) /* AD7124_ADC_CONTROL */ +#define AD7124_ADC_CTRL_REF_EN_MSK BIT(8) +#define AD7124_ADC_CTRL_REF_EN(x) FIELD_PREP(AD7124_ADC_CTRL_REF_EN_MSK, x) #define AD7124_ADC_CTRL_PWR_MSK GENMASK(7, 6) #define AD7124_ADC_CTRL_PWR(x) FIELD_PREP(AD7124_ADC_CTRL_PWR_MSK, x) #define AD7124_ADC_CTRL_MODE_MSK GENMASK(5, 2) @@ -424,7 +426,10 @@ static int ad7124_init_channel_vref(struct ad7124_state *st, break; case AD7124_INT_REF: st->channel_config[channel_number].vref_mv = 2500; - break; + st->adc_control &= ~AD7124_ADC_CTRL_REF_EN_MSK; + st->adc_control |= AD7124_ADC_CTRL_REF_EN(1); + return ad_sd_write_reg(&st->sd, AD7124_ADC_CONTROL, + 2, st->adc_control); default: dev_err(&st->sd.spi->dev, "Invalid reference %d\n", refsel); return -EINVAL; diff --git a/drivers/iio/adc/ad7606.c b/drivers/iio/adc/ad7606.c index f5ba94c03a8d..e4683a68522a 100644 --- a/drivers/iio/adc/ad7606.c +++ b/drivers/iio/adc/ad7606.c @@ -85,7 +85,7 @@ static int ad7606_reg_access(struct iio_dev *indio_dev, static int ad7606_read_samples(struct ad7606_state *st) { - unsigned int num = st->chip_info->num_channels; + unsigned int num = st->chip_info->num_channels - 1; u16 *data = st->data; int ret; diff --git a/drivers/iio/adc/ad7949.c b/drivers/iio/adc/ad7949.c index ac0ffff6c5ae..6b51bfcad0d0 100644 --- a/drivers/iio/adc/ad7949.c +++ b/drivers/iio/adc/ad7949.c @@ -57,29 +57,11 @@ struct ad7949_adc_chip { u32 buffer ____cacheline_aligned; }; -static bool ad7949_spi_cfg_is_read_back(struct ad7949_adc_chip *ad7949_adc) -{ - if (!(ad7949_adc->cfg & AD7949_CFG_READ_BACK)) - return true; - - return false; -} - -static int ad7949_spi_bits_per_word(struct ad7949_adc_chip *ad7949_adc) -{ - int ret = ad7949_adc->resolution; - - if (ad7949_spi_cfg_is_read_back(ad7949_adc)) - ret += AD7949_CFG_REG_SIZE_BITS; - - return ret; -} - static int ad7949_spi_write_cfg(struct ad7949_adc_chip *ad7949_adc, u16 val, u16 mask) { int ret; - int bits_per_word = ad7949_spi_bits_per_word(ad7949_adc); + int bits_per_word = ad7949_adc->resolution; int shift = bits_per_word - AD7949_CFG_REG_SIZE_BITS; struct spi_message msg; struct spi_transfer tx[] = { @@ -107,7 +89,8 @@ static int ad7949_spi_read_channel(struct ad7949_adc_chip *ad7949_adc, int *val, unsigned int channel) { int ret; - int bits_per_word = ad7949_spi_bits_per_word(ad7949_adc); + int i; + int bits_per_word = ad7949_adc->resolution; int mask = GENMASK(ad7949_adc->resolution, 0); struct spi_message msg; struct spi_transfer tx[] = { @@ -118,12 +101,23 @@ static int ad7949_spi_read_channel(struct ad7949_adc_chip *ad7949_adc, int *val, }, }; - ret = ad7949_spi_write_cfg(ad7949_adc, - channel << AD7949_OFFSET_CHANNEL_SEL, - AD7949_MASK_CHANNEL_SEL); - if (ret) - return ret; + /* + * 1: write CFG for sample N and read old data (sample N-2) + * 2: if CFG was not changed since sample N-1 then we'll get good data + * at the next xfer, so we bail out now, otherwise we write something + * and we read garbage (sample N-1 configuration). + */ + for (i = 0; i < 2; i++) { + ret = ad7949_spi_write_cfg(ad7949_adc, + channel << AD7949_OFFSET_CHANNEL_SEL, + AD7949_MASK_CHANNEL_SEL); + if (ret) + return ret; + if (channel == ad7949_adc->current_channel) + break; + } + /* 3: write something and read actual data */ ad7949_adc->buffer = 0; spi_message_init_with_transfers(&msg, tx, 1); ret = spi_sync(ad7949_adc->spi, &msg); @@ -138,10 +132,7 @@ static int ad7949_spi_read_channel(struct ad7949_adc_chip *ad7949_adc, int *val, ad7949_adc->current_channel = channel; - if (ad7949_spi_cfg_is_read_back(ad7949_adc)) - *val = (ad7949_adc->buffer >> AD7949_CFG_REG_SIZE_BITS) & mask; - else - *val = ad7949_adc->buffer & mask; + *val = ad7949_adc->buffer & mask; return 0; } diff --git a/drivers/iio/adc/dln2-adc.c b/drivers/iio/adc/dln2-adc.c index 5fa78c273a25..65c7c9329b1c 100644 --- a/drivers/iio/adc/dln2-adc.c +++ b/drivers/iio/adc/dln2-adc.c @@ -524,6 +524,10 @@ static int dln2_adc_triggered_buffer_postenable(struct iio_dev *indio_dev) u16 conflict; unsigned int trigger_chan; + ret = iio_triggered_buffer_postenable(indio_dev); + if (ret) + return ret; + mutex_lock(&dln2->mutex); /* Enable ADC */ @@ -537,6 +541,7 @@ static int dln2_adc_triggered_buffer_postenable(struct iio_dev *indio_dev) (int)conflict); ret = -EBUSY; } + iio_triggered_buffer_predisable(indio_dev); return ret; } @@ -550,6 +555,7 @@ static int dln2_adc_triggered_buffer_postenable(struct iio_dev *indio_dev) mutex_unlock(&dln2->mutex); if (ret < 0) { dev_dbg(&dln2->pdev->dev, "Problem in %s\n", __func__); + iio_triggered_buffer_predisable(indio_dev); return ret; } } else { @@ -557,12 +563,12 @@ static int dln2_adc_triggered_buffer_postenable(struct iio_dev *indio_dev) mutex_unlock(&dln2->mutex); } - return iio_triggered_buffer_postenable(indio_dev); + return 0; } static int dln2_adc_triggered_buffer_predisable(struct iio_dev *indio_dev) { - int ret; + int ret, ret2; struct dln2_adc *dln2 = iio_priv(indio_dev); mutex_lock(&dln2->mutex); @@ -577,12 +583,14 @@ static int dln2_adc_triggered_buffer_predisable(struct iio_dev *indio_dev) ret = dln2_adc_set_port_enabled(dln2, false, NULL); mutex_unlock(&dln2->mutex); - if (ret < 0) { + if (ret < 0) dev_dbg(&dln2->pdev->dev, "Problem in %s\n", __func__); - return ret; - } - return iio_triggered_buffer_predisable(indio_dev); + ret2 = iio_triggered_buffer_predisable(indio_dev); + if (ret == 0) + ret = ret2; + + return ret; } static const struct iio_buffer_setup_ops dln2_adc_buffer_setup_ops = { diff --git a/drivers/iio/adc/max1027.c b/drivers/iio/adc/max1027.c index 214883458582..e3be8eedd773 100644 --- a/drivers/iio/adc/max1027.c +++ b/drivers/iio/adc/max1027.c @@ -458,6 +458,14 @@ static int max1027_probe(struct spi_device *spi) return ret; } + /* Internal reset */ + st->reg = MAX1027_RST_REG; + ret = spi_write(st->spi, &st->reg, 1); + if (ret < 0) { + dev_err(&indio_dev->dev, "Failed to reset the ADC\n"); + return ret; + } + /* Disable averaging */ st->reg = MAX1027_AVG_REG; ret = spi_write(st->spi, &st->reg, 1); diff --git a/drivers/iio/adc/max9611.c b/drivers/iio/adc/max9611.c index da073d72f649..e480529b3f04 100644 --- a/drivers/iio/adc/max9611.c +++ b/drivers/iio/adc/max9611.c @@ -89,6 +89,12 @@ #define MAX9611_TEMP_SCALE_NUM 1000000 #define MAX9611_TEMP_SCALE_DIV 2083 +/* + * Conversion time is 2 ms (typically) at Ta=25 degreeC + * No maximum value is known, so play it safe. + */ +#define MAX9611_CONV_TIME_US_RANGE 3000, 3300 + struct max9611_dev { struct device *dev; struct i2c_client *i2c_client; @@ -236,11 +242,9 @@ static int max9611_read_single(struct max9611_dev *max9611, return ret; } - /* - * need a delay here to make register configuration - * stabilize. 1 msec at least, from empirical testing. - */ - usleep_range(1000, 2000); + /* need a delay here to make register configuration stabilize. */ + + usleep_range(MAX9611_CONV_TIME_US_RANGE); ret = i2c_smbus_read_word_swapped(max9611->i2c_client, reg_addr); if (ret < 0) { @@ -507,7 +511,7 @@ static int max9611_init(struct max9611_dev *max9611) MAX9611_REG_CTRL2, 0); return ret; } - usleep_range(1000, 2000); + usleep_range(MAX9611_CONV_TIME_US_RANGE); return 0; } diff --git a/drivers/iio/dac/Kconfig b/drivers/iio/dac/Kconfig index cc42219a64f7..979070196da9 100644 --- a/drivers/iio/dac/Kconfig +++ b/drivers/iio/dac/Kconfig @@ -60,8 +60,8 @@ config AD5446 help Say yes here to build support for Analog Devices AD5300, AD5301, AD5310, AD5311, AD5320, AD5321, AD5444, AD5446, AD5450, AD5451, AD5452, AD5453, - AD5512A, AD5541A, AD5542A, AD5543, AD5553, AD5601, AD5602, AD5611, AD5612, - AD5620, AD5621, AD5622, AD5640, AD5641, AD5660, AD5662 DACs + AD5512A, AD5541A, AD5542A, AD5543, AD5553, AD5600, AD5601, AD5602, AD5611, + AD5612, AD5620, AD5621, AD5622, AD5640, AD5641, AD5660, AD5662 DACs as well as Texas Instruments DAC081S101, DAC101S101, DAC121S101. To compile this driver as a module, choose M here: the diff --git a/drivers/iio/dac/ad5446.c b/drivers/iio/dac/ad5446.c index 7df8b4cc295d..61c670f7fc5f 100644 --- a/drivers/iio/dac/ad5446.c +++ b/drivers/iio/dac/ad5446.c @@ -327,6 +327,7 @@ enum ad5446_supported_spi_device_ids { ID_AD5541A, ID_AD5512A, ID_AD5553, + ID_AD5600, ID_AD5601, ID_AD5611, ID_AD5621, @@ -381,6 +382,10 @@ static const struct ad5446_chip_info ad5446_spi_chip_info[] = { .channel = AD5446_CHANNEL(14, 16, 0), .write = ad5446_write, }, + [ID_AD5600] = { + .channel = AD5446_CHANNEL(16, 16, 0), + .write = ad5446_write, + }, [ID_AD5601] = { .channel = AD5446_CHANNEL_POWERDOWN(8, 16, 6), .write = ad5446_write, @@ -448,6 +453,7 @@ static const struct spi_device_id ad5446_spi_ids[] = { {"ad5542a", ID_AD5541A}, /* ad5541a and ad5542a are compatible */ {"ad5543", ID_AD5541A}, /* ad5541a and ad5543 are compatible */ {"ad5553", ID_AD5553}, + {"ad5600", ID_AD5600}, {"ad5601", ID_AD5601}, {"ad5611", ID_AD5611}, {"ad5621", ID_AD5621}, diff --git a/drivers/iio/humidity/hdc100x.c b/drivers/iio/humidity/hdc100x.c index bfe1cdb16846..dcf5a5bdfaa8 100644 --- a/drivers/iio/humidity/hdc100x.c +++ b/drivers/iio/humidity/hdc100x.c @@ -229,7 +229,7 @@ static int hdc100x_read_raw(struct iio_dev *indio_dev, *val2 = 65536; return IIO_VAL_FRACTIONAL; } else { - *val = 100; + *val = 100000; *val2 = 65536; return IIO_VAL_FRACTIONAL; } diff --git a/drivers/iio/imu/adis16480.c b/drivers/iio/imu/adis16480.c index 8743b2f376e2..cf7b59d97802 100644 --- a/drivers/iio/imu/adis16480.c +++ b/drivers/iio/imu/adis16480.c @@ -454,12 +454,14 @@ static int adis16480_get_calibbias(struct iio_dev *indio_dev, case IIO_MAGN: case IIO_PRESSURE: ret = adis_read_reg_16(&st->adis, reg, &val16); - *bias = sign_extend32(val16, 15); + if (ret == 0) + *bias = sign_extend32(val16, 15); break; case IIO_ANGL_VEL: case IIO_ACCEL: ret = adis_read_reg_32(&st->adis, reg, &val32); - *bias = sign_extend32(val32, 31); + if (ret == 0) + *bias = sign_extend32(val32, 31); break; default: ret = -EINVAL; @@ -623,9 +625,13 @@ static int adis16480_read_raw(struct iio_dev *indio_dev, *val2 = (st->chip_info->temp_scale % 1000) * 1000; return IIO_VAL_INT_PLUS_MICRO; case IIO_PRESSURE: - *val = 0; - *val2 = 4000; /* 40ubar = 0.004 kPa */ - return IIO_VAL_INT_PLUS_MICRO; + /* + * max scale is 1310 mbar + * max raw value is 32767 shifted for 32bits + */ + *val = 131; /* 1310mbar = 131 kPa */ + *val2 = 32767 << 16; + return IIO_VAL_FRACTIONAL; default: return -EINVAL; } @@ -786,13 +792,14 @@ static const struct adis16480_chip_info adis16480_chip_info[] = { .channels = adis16485_channels, .num_channels = ARRAY_SIZE(adis16485_channels), /* - * storing the value in rad/degree and the scale in degree - * gives us the result in rad and better precession than - * storing the scale directly in rad. + * Typically we do IIO_RAD_TO_DEGREE in the denominator, which + * is exactly the same as IIO_DEGREE_TO_RAD in numerator, since + * it gives better approximation. However, in this case we + * cannot do it since it would not fit in a 32bit variable. */ - .gyro_max_val = IIO_RAD_TO_DEGREE(22887), - .gyro_max_scale = 300, - .accel_max_val = IIO_M_S_2_TO_G(21973), + .gyro_max_val = 22887 << 16, + .gyro_max_scale = IIO_DEGREE_TO_RAD(300), + .accel_max_val = IIO_M_S_2_TO_G(21973 << 16), .accel_max_scale = 18, .temp_scale = 5650, /* 5.65 milli degree Celsius */ .int_clk = 2460000, @@ -802,9 +809,9 @@ static const struct adis16480_chip_info adis16480_chip_info[] = { [ADIS16480] = { .channels = adis16480_channels, .num_channels = ARRAY_SIZE(adis16480_channels), - .gyro_max_val = IIO_RAD_TO_DEGREE(22500), - .gyro_max_scale = 450, - .accel_max_val = IIO_M_S_2_TO_G(12500), + .gyro_max_val = 22500 << 16, + .gyro_max_scale = IIO_DEGREE_TO_RAD(450), + .accel_max_val = IIO_M_S_2_TO_G(12500 << 16), .accel_max_scale = 10, .temp_scale = 5650, /* 5.65 milli degree Celsius */ .int_clk = 2460000, @@ -814,9 +821,9 @@ static const struct adis16480_chip_info adis16480_chip_info[] = { [ADIS16485] = { .channels = adis16485_channels, .num_channels = ARRAY_SIZE(adis16485_channels), - .gyro_max_val = IIO_RAD_TO_DEGREE(22500), - .gyro_max_scale = 450, - .accel_max_val = IIO_M_S_2_TO_G(20000), + .gyro_max_val = 22500 << 16, + .gyro_max_scale = IIO_DEGREE_TO_RAD(450), + .accel_max_val = IIO_M_S_2_TO_G(20000 << 16), .accel_max_scale = 5, .temp_scale = 5650, /* 5.65 milli degree Celsius */ .int_clk = 2460000, @@ -826,9 +833,9 @@ static const struct adis16480_chip_info adis16480_chip_info[] = { [ADIS16488] = { .channels = adis16480_channels, .num_channels = ARRAY_SIZE(adis16480_channels), - .gyro_max_val = IIO_RAD_TO_DEGREE(22500), - .gyro_max_scale = 450, - .accel_max_val = IIO_M_S_2_TO_G(22500), + .gyro_max_val = 22500 << 16, + .gyro_max_scale = IIO_DEGREE_TO_RAD(450), + .accel_max_val = IIO_M_S_2_TO_G(22500 << 16), .accel_max_scale = 18, .temp_scale = 5650, /* 5.65 milli degree Celsius */ .int_clk = 2460000, @@ -838,9 +845,9 @@ static const struct adis16480_chip_info adis16480_chip_info[] = { [ADIS16495_1] = { .channels = adis16485_channels, .num_channels = ARRAY_SIZE(adis16485_channels), - .gyro_max_val = IIO_RAD_TO_DEGREE(20000), - .gyro_max_scale = 125, - .accel_max_val = IIO_M_S_2_TO_G(32000), + .gyro_max_val = 20000 << 16, + .gyro_max_scale = IIO_DEGREE_TO_RAD(125), + .accel_max_val = IIO_M_S_2_TO_G(32000 << 16), .accel_max_scale = 8, .temp_scale = 12500, /* 12.5 milli degree Celsius */ .int_clk = 4250000, @@ -851,9 +858,9 @@ static const struct adis16480_chip_info adis16480_chip_info[] = { [ADIS16495_2] = { .channels = adis16485_channels, .num_channels = ARRAY_SIZE(adis16485_channels), - .gyro_max_val = IIO_RAD_TO_DEGREE(18000), - .gyro_max_scale = 450, - .accel_max_val = IIO_M_S_2_TO_G(32000), + .gyro_max_val = 18000 << 16, + .gyro_max_scale = IIO_DEGREE_TO_RAD(450), + .accel_max_val = IIO_M_S_2_TO_G(32000 << 16), .accel_max_scale = 8, .temp_scale = 12500, /* 12.5 milli degree Celsius */ .int_clk = 4250000, @@ -864,9 +871,9 @@ static const struct adis16480_chip_info adis16480_chip_info[] = { [ADIS16495_3] = { .channels = adis16485_channels, .num_channels = ARRAY_SIZE(adis16485_channels), - .gyro_max_val = IIO_RAD_TO_DEGREE(20000), - .gyro_max_scale = 2000, - .accel_max_val = IIO_M_S_2_TO_G(32000), + .gyro_max_val = 20000 << 16, + .gyro_max_scale = IIO_DEGREE_TO_RAD(2000), + .accel_max_val = IIO_M_S_2_TO_G(32000 << 16), .accel_max_scale = 8, .temp_scale = 12500, /* 12.5 milli degree Celsius */ .int_clk = 4250000, @@ -877,9 +884,9 @@ static const struct adis16480_chip_info adis16480_chip_info[] = { [ADIS16497_1] = { .channels = adis16485_channels, .num_channels = ARRAY_SIZE(adis16485_channels), - .gyro_max_val = IIO_RAD_TO_DEGREE(20000), - .gyro_max_scale = 125, - .accel_max_val = IIO_M_S_2_TO_G(32000), + .gyro_max_val = 20000 << 16, + .gyro_max_scale = IIO_DEGREE_TO_RAD(125), + .accel_max_val = IIO_M_S_2_TO_G(32000 << 16), .accel_max_scale = 40, .temp_scale = 12500, /* 12.5 milli degree Celsius */ .int_clk = 4250000, @@ -890,9 +897,9 @@ static const struct adis16480_chip_info adis16480_chip_info[] = { [ADIS16497_2] = { .channels = adis16485_channels, .num_channels = ARRAY_SIZE(adis16485_channels), - .gyro_max_val = IIO_RAD_TO_DEGREE(18000), - .gyro_max_scale = 450, - .accel_max_val = IIO_M_S_2_TO_G(32000), + .gyro_max_val = 18000 << 16, + .gyro_max_scale = IIO_DEGREE_TO_RAD(450), + .accel_max_val = IIO_M_S_2_TO_G(32000 << 16), .accel_max_scale = 40, .temp_scale = 12500, /* 12.5 milli degree Celsius */ .int_clk = 4250000, @@ -903,9 +910,9 @@ static const struct adis16480_chip_info adis16480_chip_info[] = { [ADIS16497_3] = { .channels = adis16485_channels, .num_channels = ARRAY_SIZE(adis16485_channels), - .gyro_max_val = IIO_RAD_TO_DEGREE(20000), - .gyro_max_scale = 2000, - .accel_max_val = IIO_M_S_2_TO_G(32000), + .gyro_max_val = 20000 << 16, + .gyro_max_scale = IIO_DEGREE_TO_RAD(2000), + .accel_max_val = IIO_M_S_2_TO_G(32000 << 16), .accel_max_scale = 40, .temp_scale = 12500, /* 12.5 milli degree Celsius */ .int_clk = 4250000, @@ -919,6 +926,7 @@ static const struct iio_info adis16480_info = { .read_raw = &adis16480_read_raw, .write_raw = &adis16480_write_raw, .update_scan_mode = adis_update_scan_mode, + .debugfs_reg_access = adis_debugfs_reg_access, }; static int adis16480_stop_device(struct iio_dev *indio_dev) diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c index 868281b8adb0..2261c6c4ac65 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c @@ -115,6 +115,7 @@ static const struct inv_mpu6050_hw hw_info[] = { .reg = ®_set_6050, .config = &chip_config_6050, .fifo_size = 1024, + .temp = {INV_MPU6050_TEMP_OFFSET, INV_MPU6050_TEMP_SCALE}, }, { .whoami = INV_MPU6500_WHOAMI_VALUE, @@ -122,6 +123,7 @@ static const struct inv_mpu6050_hw hw_info[] = { .reg = ®_set_6500, .config = &chip_config_6050, .fifo_size = 512, + .temp = {INV_MPU6500_TEMP_OFFSET, INV_MPU6500_TEMP_SCALE}, }, { .whoami = INV_MPU6515_WHOAMI_VALUE, @@ -129,6 +131,7 @@ static const struct inv_mpu6050_hw hw_info[] = { .reg = ®_set_6500, .config = &chip_config_6050, .fifo_size = 512, + .temp = {INV_MPU6500_TEMP_OFFSET, INV_MPU6500_TEMP_SCALE}, }, { .whoami = INV_MPU6000_WHOAMI_VALUE, @@ -136,6 +139,7 @@ static const struct inv_mpu6050_hw hw_info[] = { .reg = ®_set_6050, .config = &chip_config_6050, .fifo_size = 1024, + .temp = {INV_MPU6050_TEMP_OFFSET, INV_MPU6050_TEMP_SCALE}, }, { .whoami = INV_MPU9150_WHOAMI_VALUE, @@ -143,6 +147,7 @@ static const struct inv_mpu6050_hw hw_info[] = { .reg = ®_set_6050, .config = &chip_config_6050, .fifo_size = 1024, + .temp = {INV_MPU6050_TEMP_OFFSET, INV_MPU6050_TEMP_SCALE}, }, { .whoami = INV_MPU9250_WHOAMI_VALUE, @@ -150,6 +155,7 @@ static const struct inv_mpu6050_hw hw_info[] = { .reg = ®_set_6500, .config = &chip_config_6050, .fifo_size = 512, + .temp = {INV_MPU6500_TEMP_OFFSET, INV_MPU6500_TEMP_SCALE}, }, { .whoami = INV_MPU9255_WHOAMI_VALUE, @@ -157,6 +163,7 @@ static const struct inv_mpu6050_hw hw_info[] = { .reg = ®_set_6500, .config = &chip_config_6050, .fifo_size = 512, + .temp = {INV_MPU6500_TEMP_OFFSET, INV_MPU6500_TEMP_SCALE}, }, { .whoami = INV_ICM20608_WHOAMI_VALUE, @@ -164,6 +171,7 @@ static const struct inv_mpu6050_hw hw_info[] = { .reg = ®_set_6500, .config = &chip_config_6050, .fifo_size = 512, + .temp = {INV_ICM20608_TEMP_OFFSET, INV_ICM20608_TEMP_SCALE}, }, { .whoami = INV_ICM20602_WHOAMI_VALUE, @@ -171,6 +179,7 @@ static const struct inv_mpu6050_hw hw_info[] = { .reg = ®_set_icm20602, .config = &chip_config_6050, .fifo_size = 1008, + .temp = {INV_ICM20608_TEMP_OFFSET, INV_ICM20608_TEMP_SCALE}, }, }; @@ -471,12 +480,8 @@ inv_mpu6050_read_raw(struct iio_dev *indio_dev, return IIO_VAL_INT_PLUS_MICRO; case IIO_TEMP: - *val = 0; - if (st->chip_type == INV_ICM20602) - *val2 = INV_ICM20602_TEMP_SCALE; - else - *val2 = INV_MPU6050_TEMP_SCALE; - + *val = st->hw->temp.scale / 1000000; + *val2 = st->hw->temp.scale % 1000000; return IIO_VAL_INT_PLUS_MICRO; default: return -EINVAL; @@ -484,11 +489,7 @@ inv_mpu6050_read_raw(struct iio_dev *indio_dev, case IIO_CHAN_INFO_OFFSET: switch (chan->type) { case IIO_TEMP: - if (st->chip_type == INV_ICM20602) - *val = INV_ICM20602_TEMP_OFFSET; - else - *val = INV_MPU6050_TEMP_OFFSET; - + *val = st->hw->temp.offset; return IIO_VAL_INT; default: return -EINVAL; diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h b/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h index 51235677c534..c32bd0c012b5 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h @@ -101,6 +101,7 @@ struct inv_mpu6050_chip_config { * @reg: register map of the chip. * @config: configuration of the chip. * @fifo_size: size of the FIFO in bytes. + * @temp: offset and scale to apply to raw temperature. */ struct inv_mpu6050_hw { u8 whoami; @@ -108,6 +109,10 @@ struct inv_mpu6050_hw { const struct inv_mpu6050_reg_map *reg; const struct inv_mpu6050_chip_config *config; size_t fifo_size; + struct { + int offset; + int scale; + } temp; }; /* @@ -218,16 +223,19 @@ struct inv_mpu6050_state { #define INV_MPU6050_REG_UP_TIME_MIN 5000 #define INV_MPU6050_REG_UP_TIME_MAX 10000 -#define INV_MPU6050_TEMP_OFFSET 12421 -#define INV_MPU6050_TEMP_SCALE 2941 +#define INV_MPU6050_TEMP_OFFSET 12420 +#define INV_MPU6050_TEMP_SCALE 2941176 #define INV_MPU6050_MAX_GYRO_FS_PARAM 3 #define INV_MPU6050_MAX_ACCL_FS_PARAM 3 #define INV_MPU6050_THREE_AXIS 3 #define INV_MPU6050_GYRO_CONFIG_FSR_SHIFT 3 #define INV_MPU6050_ACCL_CONFIG_FSR_SHIFT 3 -#define INV_ICM20602_TEMP_OFFSET 8170 -#define INV_ICM20602_TEMP_SCALE 3060 +#define INV_MPU6500_TEMP_OFFSET 7011 +#define INV_MPU6500_TEMP_SCALE 2995178 + +#define INV_ICM20608_TEMP_OFFSET 8170 +#define INV_ICM20608_TEMP_SCALE 3059976 /* 6 + 6 round up and plus 8 */ #define INV_MPU6050_OUTPUT_DATA_SIZE 24 diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c index fd5ebe1e1594..3e0528793d95 100644 --- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c @@ -152,9 +152,10 @@ static const struct st_lsm6dsx_settings st_lsm6dsx_sensor_settings[] = { .addr = 0x10, .mask = GENMASK(4, 3), }, - .fs_avl[0] = { IIO_DEGREE_TO_RAD(245), 0x0 }, - .fs_avl[1] = { IIO_DEGREE_TO_RAD(500), 0x1 }, - .fs_avl[2] = { IIO_DEGREE_TO_RAD(2000), 0x3 }, + + .fs_avl[0] = { IIO_DEGREE_TO_RAD(8750), 0x0 }, + .fs_avl[1] = { IIO_DEGREE_TO_RAD(17500), 0x1 }, + .fs_avl[2] = { IIO_DEGREE_TO_RAD(70000), 0x3 }, .fs_len = 3, }, }, @@ -985,8 +986,7 @@ int st_lsm6dsx_check_odr(struct st_lsm6dsx_sensor *sensor, u16 odr, u8 *val) return -EINVAL; *val = odr_table->odr_avl[i].val; - - return 0; + return odr_table->odr_avl[i].hz; } static u16 st_lsm6dsx_check_odr_dependency(struct st_lsm6dsx_hw *hw, u16 odr, @@ -1149,8 +1149,10 @@ static int st_lsm6dsx_write_raw(struct iio_dev *iio_dev, case IIO_CHAN_INFO_SAMP_FREQ: { u8 data; - err = st_lsm6dsx_check_odr(sensor, val, &data); - if (!err) + val = st_lsm6dsx_check_odr(sensor, val, &data); + if (val < 0) + err = val; + else sensor->odr = val; break; } diff --git a/drivers/iio/light/bh1750.c b/drivers/iio/light/bh1750.c index 28347df78cff..adb5ab9e3439 100644 --- a/drivers/iio/light/bh1750.c +++ b/drivers/iio/light/bh1750.c @@ -59,9 +59,9 @@ struct bh1750_chip_info { u16 int_time_low_mask; u16 int_time_high_mask; -} +}; -static const bh1750_chip_info_tbl[] = { +static const struct bh1750_chip_info bh1750_chip_info_tbl[] = { [BH1710] = { 140, 1022, 300, 400, 250000000, 2, 0x001F, 0x03E0 }, [BH1721] = { 140, 1020, 300, 400, 250000000, 2, 0x0010, 0x03E0 }, [BH1750] = { 31, 254, 69, 1740, 57500000, 1, 0x001F, 0x00E0 }, diff --git a/drivers/iio/pressure/cros_ec_baro.c b/drivers/iio/pressure/cros_ec_baro.c index 2354302375de..52f53f3123b1 100644 --- a/drivers/iio/pressure/cros_ec_baro.c +++ b/drivers/iio/pressure/cros_ec_baro.c @@ -114,6 +114,7 @@ static int cros_ec_baro_write(struct iio_dev *indio_dev, static const struct iio_info cros_ec_baro_info = { .read_raw = &cros_ec_baro_read, .write_raw = &cros_ec_baro_write, + .read_avail = &cros_ec_sensors_core_read_avail, }; static int cros_ec_baro_probe(struct platform_device *pdev) @@ -149,6 +150,8 @@ static int cros_ec_baro_probe(struct platform_device *pdev) BIT(IIO_CHAN_INFO_SCALE) | BIT(IIO_CHAN_INFO_SAMP_FREQ) | BIT(IIO_CHAN_INFO_FREQUENCY); + channel->info_mask_shared_by_all_available = + BIT(IIO_CHAN_INFO_SAMP_FREQ); channel->scan_type.realbits = CROS_EC_SENSOR_BITS; channel->scan_type.storagebits = CROS_EC_SENSOR_BITS; channel->scan_type.shift = 0; diff --git a/drivers/iio/temperature/max31856.c b/drivers/iio/temperature/max31856.c index f184ba5601d9..73ed550e3fc9 100644 --- a/drivers/iio/temperature/max31856.c +++ b/drivers/iio/temperature/max31856.c @@ -284,6 +284,8 @@ static int max31856_probe(struct spi_device *spi) spi_set_drvdata(spi, indio_dev); indio_dev->info = &max31856_info; + indio_dev->dev.parent = &spi->dev; + indio_dev->dev.of_node = spi->dev.of_node; indio_dev->name = id->name; indio_dev->modes = INDIO_DIRECT_MODE; indio_dev->channels = max31856_channels; diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c index 6d7ec371e7b2..606fa6d86685 100644 --- a/drivers/infiniband/core/addr.c +++ b/drivers/infiniband/core/addr.c @@ -421,16 +421,15 @@ static int addr6_resolve(struct sockaddr *src_sock, (const struct sockaddr_in6 *)dst_sock; struct flowi6 fl6; struct dst_entry *dst; - int ret; memset(&fl6, 0, sizeof fl6); fl6.daddr = dst_in->sin6_addr; fl6.saddr = src_in->sin6_addr; fl6.flowi6_oif = addr->bound_dev_if; - ret = ipv6_stub->ipv6_dst_lookup(addr->net, NULL, &dst, &fl6); - if (ret < 0) - return ret; + dst = ipv6_stub->ipv6_dst_lookup_flow(addr->net, NULL, &fl6, NULL); + if (IS_ERR(dst)) + return PTR_ERR(dst); if (ipv6_addr_any(&src_in->sin6_addr)) src_in->sin6_addr = fl6.saddr; diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index d78f67623f24..50052e9a1731 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -4736,6 +4736,7 @@ static int __init cma_init(void) err: unregister_netdevice_notifier(&cma_nb); ib_sa_unregister_client(&sa_client); + unregister_pernet_subsys(&cma_pernet_operations); err_wq: destroy_workqueue(cma_wq); return ret; diff --git a/drivers/infiniband/core/counters.c b/drivers/infiniband/core/counters.c index 680ad27f497d..46dd50ff7c85 100644 --- a/drivers/infiniband/core/counters.c +++ b/drivers/infiniband/core/counters.c @@ -282,6 +282,9 @@ int rdma_counter_bind_qp_auto(struct ib_qp *qp, u8 port) struct rdma_counter *counter; int ret; + if (!qp->res.valid) + return 0; + if (!rdma_is_port_valid(dev, port)) return -EINVAL; @@ -463,10 +466,15 @@ static struct rdma_counter *rdma_get_counter_by_id(struct ib_device *dev, int rdma_counter_bind_qpn(struct ib_device *dev, u8 port, u32 qp_num, u32 counter_id) { + struct rdma_port_counter *port_counter; struct rdma_counter *counter; struct ib_qp *qp; int ret; + port_counter = &dev->port_data[port].port_counter; + if (port_counter->mode.mode == RDMA_COUNTER_MODE_AUTO) + return -EINVAL; + qp = rdma_counter_get_qp(dev, qp_num); if (!qp) return -ENOENT; @@ -503,6 +511,7 @@ int rdma_counter_bind_qpn(struct ib_device *dev, u8 port, int rdma_counter_bind_qpn_alloc(struct ib_device *dev, u8 port, u32 qp_num, u32 *counter_id) { + struct rdma_port_counter *port_counter; struct rdma_counter *counter; struct ib_qp *qp; int ret; @@ -510,9 +519,13 @@ int rdma_counter_bind_qpn_alloc(struct ib_device *dev, u8 port, if (!rdma_is_port_valid(dev, port)) return -EINVAL; - if (!dev->port_data[port].port_counter.hstats) + port_counter = &dev->port_data[port].port_counter; + if (!port_counter->hstats) return -EOPNOTSUPP; + if (port_counter->mode.mode == RDMA_COUNTER_MODE_AUTO) + return -EINVAL; + qp = rdma_counter_get_qp(dev, qp_num); if (!qp) return -ENOENT; diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 50a92442c4f7..2b5bd7206fc6 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -1199,9 +1199,21 @@ static void setup_dma_device(struct ib_device *device) WARN_ON_ONCE(!parent); device->dma_device = parent; } - /* Setup default max segment size for all IB devices */ - dma_set_max_seg_size(device->dma_device, SZ_2G); + if (!device->dev.dma_parms) { + if (parent) { + /* + * The caller did not provide DMA parameters, so + * 'parent' probably represents a PCI device. The PCI + * core sets the maximum segment size to 64 + * KB. Increase this parameter to 2 GB. + */ + device->dev.dma_parms = parent->dma_parms; + dma_set_max_seg_size(device->dma_device, SZ_2G); + } else { + WARN_ON_ONCE(true); + } + } } /* @@ -2397,8 +2409,12 @@ int ib_modify_port(struct ib_device *device, rc = device->ops.modify_port(device, port_num, port_modify_mask, port_modify); + else if (rdma_protocol_roce(device, port_num) && + ((port_modify->set_port_cap_mask & ~IB_PORT_CM_SUP) == 0 || + (port_modify->clr_port_cap_mask & ~IB_PORT_CM_SUP) == 0)) + rc = 0; else - rc = rdma_protocol_roce(device, port_num) ? 0 : -ENOSYS; + rc = -EOPNOTSUPP; return rc; } EXPORT_SYMBOL(ib_modify_port); diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index b4149dc9e824..ebc3e3d4a6e2 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -3323,8 +3323,10 @@ int bnxt_re_dereg_mr(struct ib_mr *ib_mr, struct ib_udata *udata) int rc; rc = bnxt_qplib_free_mrw(&rdev->qplib_res, &mr->qplib_mr); - if (rc) + if (rc) { dev_err(rdev_to_dev(rdev), "Dereg MR failed: %#x\n", rc); + return rc; + } if (mr->pages) { rc = bnxt_qplib_free_fast_reg_page_list(&rdev->qplib_res, diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index 30a54f8aa42c..27e2df44d043 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -477,6 +477,7 @@ static int bnxt_re_net_stats_ctx_alloc(struct bnxt_re_dev *rdev, bnxt_re_init_hwrm_hdr(rdev, (void *)&req, HWRM_STAT_CTX_ALLOC, -1, -1); req.update_period_ms = cpu_to_le32(1000); req.stats_dma_addr = cpu_to_le64(dma_map); + req.stats_dma_length = cpu_to_le16(sizeof(struct ctx_hw_stats_ext)); req.stat_ctx_flags = STAT_CTX_ALLOC_REQ_STAT_CTX_FLAGS_ROCE; bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp, sizeof(resp), DFLT_HWRM_CMD_TIMEOUT); @@ -1270,10 +1271,10 @@ static void bnxt_re_query_hwrm_intf_version(struct bnxt_re_dev *rdev) return; } rdev->qplib_ctx.hwrm_intf_ver = - (u64)resp.hwrm_intf_major << 48 | - (u64)resp.hwrm_intf_minor << 32 | - (u64)resp.hwrm_intf_build << 16 | - resp.hwrm_intf_patch; + (u64)le16_to_cpu(resp.hwrm_intf_major) << 48 | + (u64)le16_to_cpu(resp.hwrm_intf_minor) << 32 | + (u64)le16_to_cpu(resp.hwrm_intf_build) << 16 | + le16_to_cpu(resp.hwrm_intf_patch); } static void bnxt_re_ib_unreg(struct bnxt_re_dev *rdev) diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index 958c1ff9c515..4d07d22bfa7b 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -2283,13 +2283,13 @@ static int bnxt_qplib_cq_process_req(struct bnxt_qplib_cq *cq, /* Add qp to flush list of the CQ */ bnxt_qplib_add_flush_qp(qp); } else { + /* Before we complete, do WA 9060 */ + if (do_wa9060(qp, cq, cq_cons, sw_sq_cons, + cqe_sq_cons)) { + *lib_qp = qp; + goto out; + } if (swq->flags & SQ_SEND_FLAGS_SIGNAL_COMP) { - /* Before we complete, do WA 9060 */ - if (do_wa9060(qp, cq, cq_cons, sw_sq_cons, - cqe_sq_cons)) { - *lib_qp = qp; - goto out; - } cqe->status = CQ_REQ_STATUS_OK; cqe++; (*budget)--; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.h b/drivers/infiniband/hw/bnxt_re/qplib_res.h index fbda11a7ab1a..aaa76d792185 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_res.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_res.h @@ -186,7 +186,9 @@ struct bnxt_qplib_chip_ctx { u8 chip_metal; }; -#define CHIP_NUM_57500 0x1750 +#define CHIP_NUM_57508 0x1750 +#define CHIP_NUM_57504 0x1751 +#define CHIP_NUM_57502 0x1752 struct bnxt_qplib_res { struct pci_dev *pdev; @@ -203,7 +205,9 @@ struct bnxt_qplib_res { static inline bool bnxt_qplib_is_chip_gen_p5(struct bnxt_qplib_chip_ctx *cctx) { - return (cctx->chip_num == CHIP_NUM_57500); + return (cctx->chip_num == CHIP_NUM_57508 || + cctx->chip_num == CHIP_NUM_57504 || + cctx->chip_num == CHIP_NUM_57502); } static inline u8 bnxt_qplib_get_hwq_type(struct bnxt_qplib_res *res) diff --git a/drivers/infiniband/hw/efa/efa_com.c b/drivers/infiniband/hw/efa/efa_com.c index 3c412bc5b94f..0778f4f7dccd 100644 --- a/drivers/infiniband/hw/efa/efa_com.c +++ b/drivers/infiniband/hw/efa/efa_com.c @@ -317,6 +317,7 @@ static struct efa_comp_ctx *__efa_com_submit_admin_cmd(struct efa_com_admin_queu struct efa_admin_acq_entry *comp, size_t comp_size_in_bytes) { + struct efa_admin_aq_entry *aqe; struct efa_comp_ctx *comp_ctx; u16 queue_size_mask; u16 cmd_id; @@ -350,7 +351,9 @@ static struct efa_comp_ctx *__efa_com_submit_admin_cmd(struct efa_com_admin_queu reinit_completion(&comp_ctx->wait_event); - memcpy(&aq->sq.entries[pi], cmd, cmd_size_in_bytes); + aqe = &aq->sq.entries[pi]; + memset(aqe, 0, sizeof(*aqe)); + memcpy(aqe, cmd, cmd_size_in_bytes); aq->sq.pc++; atomic64_inc(&aq->stats.submitted_cmd); diff --git a/drivers/infiniband/hw/hfi1/iowait.c b/drivers/infiniband/hw/hfi1/iowait.c index adb4a1ba921b..5836fe7b2817 100644 --- a/drivers/infiniband/hw/hfi1/iowait.c +++ b/drivers/infiniband/hw/hfi1/iowait.c @@ -81,7 +81,9 @@ void iowait_init(struct iowait *wait, u32 tx_limit, void iowait_cancel_work(struct iowait *w) { cancel_work_sync(&iowait_get_ib_work(w)->iowork); - cancel_work_sync(&iowait_get_tid_work(w)->iowork); + /* Make sure that the iowork for TID RDMA is used */ + if (iowait_get_tid_work(w)->iowork.func) + cancel_work_sync(&iowait_get_tid_work(w)->iowork); } /** diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c index e53f542b60af..8a2e0d9351e9 100644 --- a/drivers/infiniband/hw/hfi1/tid_rdma.c +++ b/drivers/infiniband/hw/hfi1/tid_rdma.c @@ -4633,6 +4633,15 @@ void hfi1_rc_rcv_tid_rdma_ack(struct hfi1_packet *packet) */ fpsn = full_flow_psn(flow, flow->flow_state.spsn); req->r_ack_psn = psn; + /* + * If resync_psn points to the last flow PSN for a + * segment and the new segment (likely from a new + * request) starts with a new generation number, we + * need to adjust resync_psn accordingly. + */ + if (flow->flow_state.generation != + (resync_psn >> HFI1_KDETH_BTH_SEQ_SHIFT)) + resync_psn = mask_psn(fpsn - 1); flow->resync_npkts += delta_psn(mask_psn(resync_psn + 1), fpsn); /* diff --git a/drivers/infiniband/hw/hns/Kconfig b/drivers/infiniband/hw/hns/Kconfig index d602b698b57e..4921c1e40ccd 100644 --- a/drivers/infiniband/hw/hns/Kconfig +++ b/drivers/infiniband/hw/hns/Kconfig @@ -1,23 +1,34 @@ # SPDX-License-Identifier: GPL-2.0-only config INFINIBAND_HNS - bool "HNS RoCE Driver" + tristate "HNS RoCE Driver" depends on NET_VENDOR_HISILICON depends on ARM64 || (COMPILE_TEST && 64BIT) + depends on (HNS_DSAF && HNS_ENET) || HNS3 ---help--- This is a RoCE/RDMA driver for the Hisilicon RoCE engine. The engine is used in Hisilicon Hip06 and more further ICT SoC based on platform device. + To compile HIP06 or HIP08 driver as module, choose M here. + config INFINIBAND_HNS_HIP06 - tristate "Hisilicon Hip06 Family RoCE support" + bool "Hisilicon Hip06 Family RoCE support" depends on INFINIBAND_HNS && HNS && HNS_DSAF && HNS_ENET + depends on INFINIBAND_HNS=m || (HNS_DSAF=y && HNS_ENET=y) ---help--- RoCE driver support for Hisilicon RoCE engine in Hisilicon Hip06 and Hip07 SoC. These RoCE engines are platform devices. + To compile this driver, choose Y here: if INFINIBAND_HNS is m, this + module will be called hns-roce-hw-v1 + config INFINIBAND_HNS_HIP08 - tristate "Hisilicon Hip08 Family RoCE support" + bool "Hisilicon Hip08 Family RoCE support" depends on INFINIBAND_HNS && PCI && HNS3 + depends on INFINIBAND_HNS=m || HNS3=y ---help--- RoCE driver support for Hisilicon RoCE engine in Hisilicon Hip08 SoC. The RoCE engine is a PCI device. + + To compile this driver, choose Y here: if INFINIBAND_HNS is m, this + module will be called hns-roce-hw-v2. diff --git a/drivers/infiniband/hw/hns/Makefile b/drivers/infiniband/hw/hns/Makefile index 449a2d81319d..e105945b94a1 100644 --- a/drivers/infiniband/hw/hns/Makefile +++ b/drivers/infiniband/hw/hns/Makefile @@ -9,8 +9,12 @@ hns-roce-objs := hns_roce_main.o hns_roce_cmd.o hns_roce_pd.o \ hns_roce_ah.o hns_roce_hem.o hns_roce_mr.o hns_roce_qp.o \ hns_roce_cq.o hns_roce_alloc.o hns_roce_db.o hns_roce_srq.o hns_roce_restrack.o +ifdef CONFIG_INFINIBAND_HNS_HIP06 hns-roce-hw-v1-objs := hns_roce_hw_v1.o $(hns-roce-objs) -obj-$(CONFIG_INFINIBAND_HNS_HIP06) += hns-roce-hw-v1.o +obj-$(CONFIG_INFINIBAND_HNS) += hns-roce-hw-v1.o +endif +ifdef CONFIG_INFINIBAND_HNS_HIP08 hns-roce-hw-v2-objs := hns_roce_hw_v2.o hns_roce_hw_v2_dfx.o $(hns-roce-objs) -obj-$(CONFIG_INFINIBAND_HNS_HIP08) += hns-roce-hw-v2.o +obj-$(CONFIG_INFINIBAND_HNS) += hns-roce-hw-v2.o +endif diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index e82567fcdeb7..79294f278b26 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -389,7 +389,7 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp, roce_set_field(ud_sq_wqe->byte_36, V2_UD_SEND_WQE_BYTE_36_VLAN_M, V2_UD_SEND_WQE_BYTE_36_VLAN_S, - le16_to_cpu(ah->av.vlan)); + ah->av.vlan); roce_set_field(ud_sq_wqe->byte_36, V2_UD_SEND_WQE_BYTE_36_HOPLIMIT_M, V2_UD_SEND_WQE_BYTE_36_HOPLIMIT_S, @@ -4650,16 +4650,14 @@ static int hns_roce_v2_destroy_qp_common(struct hns_roce_dev *hr_dev, { struct hns_roce_cq *send_cq, *recv_cq; struct ib_device *ibdev = &hr_dev->ib_dev; - int ret; + int ret = 0; if (hr_qp->ibqp.qp_type == IB_QPT_RC && hr_qp->state != IB_QPS_RESET) { /* Modify qp to reset before destroying qp */ ret = hns_roce_v2_modify_qp(&hr_qp->ibqp, NULL, 0, hr_qp->state, IB_QPS_RESET); - if (ret) { + if (ret) ibdev_err(ibdev, "modify QP to Reset failed.\n"); - return ret; - } } send_cq = to_hr_cq(hr_qp->ibqp.send_cq); @@ -4715,7 +4713,7 @@ static int hns_roce_v2_destroy_qp_common(struct hns_roce_dev *hr_dev, kfree(hr_qp->rq_inl_buf.wqe_list); } - return 0; + return ret; } static int hns_roce_v2_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) @@ -4725,11 +4723,9 @@ static int hns_roce_v2_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) int ret; ret = hns_roce_v2_destroy_qp_common(hr_dev, hr_qp, udata); - if (ret) { + if (ret) ibdev_err(&hr_dev->ib_dev, "Destroy qp 0x%06lx failed(%d)\n", hr_qp->qpn, ret); - return ret; - } if (hr_qp->ibqp.qp_type == IB_QPT_GSI) kfree(hr_to_hr_sqp(hr_qp)); @@ -6092,11 +6088,11 @@ static void hns_roce_v2_write_srqc(struct hns_roce_dev *hr_dev, roce_set_field(srq_context->byte_44_idxbufpgsz_addr, SRQC_BYTE_44_SRQ_IDX_BA_PG_SZ_M, SRQC_BYTE_44_SRQ_IDX_BA_PG_SZ_S, - hr_dev->caps.idx_ba_pg_sz); + hr_dev->caps.idx_ba_pg_sz + PG_SHIFT_OFFSET); roce_set_field(srq_context->byte_44_idxbufpgsz_addr, SRQC_BYTE_44_SRQ_IDX_BUF_PG_SZ_M, SRQC_BYTE_44_SRQ_IDX_BUF_PG_SZ_S, - hr_dev->caps.idx_buf_pg_sz); + hr_dev->caps.idx_buf_pg_sz + PG_SHIFT_OFFSET); srq_context->idx_nxt_blk_addr = cpu_to_le32(mtts_idx[1] >> PAGE_ADDR_SHIFT); diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h index 43219d2f7de0..76a14db7028d 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h @@ -87,8 +87,8 @@ #define HNS_ROCE_V2_MTT_ENTRY_SZ 64 #define HNS_ROCE_V2_CQE_ENTRY_SIZE 32 #define HNS_ROCE_V2_SCCC_ENTRY_SZ 32 -#define HNS_ROCE_V2_QPC_TIMER_ENTRY_SZ 4096 -#define HNS_ROCE_V2_CQC_TIMER_ENTRY_SZ 4096 +#define HNS_ROCE_V2_QPC_TIMER_ENTRY_SZ PAGE_SIZE +#define HNS_ROCE_V2_CQC_TIMER_ENTRY_SZ PAGE_SIZE #define HNS_ROCE_V2_PAGE_SIZE_SUPPORTED 0xFFFFF000 #define HNS_ROCE_V2_MAX_INNER_MTPT_NUM 2 #define HNS_ROCE_INVALID_LKEY 0x100 diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c index bd78ff90d998..8dd2d666f687 100644 --- a/drivers/infiniband/hw/hns/hns_roce_qp.c +++ b/drivers/infiniband/hw/hns/hns_roce_qp.c @@ -332,9 +332,8 @@ static int check_sq_size_with_integrity(struct hns_roce_dev *hr_dev, u8 max_sq_stride = ilog2(roundup_sq_stride); /* Sanity check SQ size before proceeding */ - if ((u32)(1 << ucmd->log_sq_bb_count) > hr_dev->caps.max_wqes || - ucmd->log_sq_stride > max_sq_stride || - ucmd->log_sq_stride < HNS_ROCE_IB_MIN_SQ_STRIDE) { + if (ucmd->log_sq_stride > max_sq_stride || + ucmd->log_sq_stride < HNS_ROCE_IB_MIN_SQ_STRIDE) { ibdev_err(&hr_dev->ib_dev, "check SQ size error!\n"); return -EINVAL; } @@ -358,13 +357,16 @@ static int hns_roce_set_user_sq_size(struct hns_roce_dev *hr_dev, u32 max_cnt; int ret; + if (check_shl_overflow(1, ucmd->log_sq_bb_count, &hr_qp->sq.wqe_cnt) || + hr_qp->sq.wqe_cnt > hr_dev->caps.max_wqes) + return -EINVAL; + ret = check_sq_size_with_integrity(hr_dev, cap, ucmd); if (ret) { ibdev_err(&hr_dev->ib_dev, "Sanity check sq size failed\n"); return ret; } - hr_qp->sq.wqe_cnt = 1 << ucmd->log_sq_bb_count; hr_qp->sq.wqe_shift = ucmd->log_sq_stride; max_cnt = max(1U, cap->max_send_sge); diff --git a/drivers/infiniband/hw/hns/hns_roce_restrack.c b/drivers/infiniband/hw/hns/hns_roce_restrack.c index 0a31d0a3d657..39c08217e861 100644 --- a/drivers/infiniband/hw/hns/hns_roce_restrack.c +++ b/drivers/infiniband/hw/hns/hns_roce_restrack.c @@ -95,14 +95,18 @@ static int hns_roce_fill_res_cq_entry(struct sk_buff *msg, ret = hr_dev->dfx->query_cqc_info(hr_dev, hr_cq->cqn, (int *)context); if (ret) - goto err; + return -EINVAL; table_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_DRIVER); - if (!table_attr) + if (!table_attr) { + ret = -EMSGSIZE; goto err; + } - if (hns_roce_fill_cq(msg, context)) + if (hns_roce_fill_cq(msg, context)) { + ret = -EMSGSIZE; goto err_cancel_table; + } nla_nest_end(msg, table_attr); kfree(context); @@ -113,7 +117,7 @@ static int hns_roce_fill_res_cq_entry(struct sk_buff *msg, nla_nest_cancel(msg, table_attr); err: kfree(context); - return -EMSGSIZE; + return ret; } int hns_roce_fill_res_entry(struct sk_buff *msg, diff --git a/drivers/infiniband/hw/hns/hns_roce_srq.c b/drivers/infiniband/hw/hns/hns_roce_srq.c index 43ea2c13b212..108667ae6b14 100644 --- a/drivers/infiniband/hw/hns/hns_roce_srq.c +++ b/drivers/infiniband/hw/hns/hns_roce_srq.c @@ -180,8 +180,7 @@ static int create_user_srq(struct hns_roce_srq *srq, struct ib_udata *udata, { struct hns_roce_dev *hr_dev = to_hr_dev(srq->ibsrq.device); struct hns_roce_ib_create_srq ucmd; - u32 page_shift; - u32 npages; + struct hns_roce_buf *buf; int ret; if (ib_copy_from_udata(&ucmd, udata, sizeof(ucmd))) @@ -191,11 +190,13 @@ static int create_user_srq(struct hns_roce_srq *srq, struct ib_udata *udata, if (IS_ERR(srq->umem)) return PTR_ERR(srq->umem); - npages = (ib_umem_page_count(srq->umem) + - (1 << hr_dev->caps.srqwqe_buf_pg_sz) - 1) / - (1 << hr_dev->caps.srqwqe_buf_pg_sz); - page_shift = PAGE_SHIFT + hr_dev->caps.srqwqe_buf_pg_sz; - ret = hns_roce_mtt_init(hr_dev, npages, page_shift, &srq->mtt); + buf = &srq->buf; + buf->npages = (ib_umem_page_count(srq->umem) + + (1 << hr_dev->caps.srqwqe_buf_pg_sz) - 1) / + (1 << hr_dev->caps.srqwqe_buf_pg_sz); + buf->page_shift = PAGE_SHIFT + hr_dev->caps.srqwqe_buf_pg_sz; + ret = hns_roce_mtt_init(hr_dev, buf->npages, buf->page_shift, + &srq->mtt); if (ret) goto err_user_buf; @@ -212,9 +213,12 @@ static int create_user_srq(struct hns_roce_srq *srq, struct ib_udata *udata, goto err_user_srq_mtt; } - ret = hns_roce_mtt_init(hr_dev, ib_umem_page_count(srq->idx_que.umem), - PAGE_SHIFT, &srq->idx_que.mtt); - + buf = &srq->idx_que.idx_buf; + buf->npages = DIV_ROUND_UP(ib_umem_page_count(srq->idx_que.umem), + 1 << hr_dev->caps.idx_buf_pg_sz); + buf->page_shift = PAGE_SHIFT + hr_dev->caps.idx_buf_pg_sz; + ret = hns_roce_mtt_init(hr_dev, buf->npages, buf->page_shift, + &srq->idx_que.mtt); if (ret) { dev_err(hr_dev->dev, "hns_roce_mtt_init error for idx que\n"); goto err_user_idx_mtt; diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 8d2f1e38b891..907d99822bf0 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -3008,16 +3008,17 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr) ibdev->ib_active = false; flush_workqueue(wq); - mlx4_ib_close_sriov(ibdev); - mlx4_ib_mad_cleanup(ibdev); - ib_unregister_device(&ibdev->ib_dev); - mlx4_ib_diag_cleanup(ibdev); if (ibdev->iboe.nb.notifier_call) { if (unregister_netdevice_notifier(&ibdev->iboe.nb)) pr_warn("failure unregistering notifier\n"); ibdev->iboe.nb.notifier_call = NULL; } + mlx4_ib_close_sriov(ibdev); + mlx4_ib_mad_cleanup(ibdev); + ib_unregister_device(&ibdev->ib_dev); + mlx4_ib_diag_cleanup(ibdev); + mlx4_qp_release_range(dev, ibdev->steer_qpn_base, ibdev->steer_qpn_count); kfree(ibdev->ib_uc_qpns_bitmap); diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 831539419c30..e1cfbedefcbc 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -3548,10 +3548,6 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev, } INIT_LIST_HEAD(&handler->list); - if (dst) { - memcpy(&dest_arr[0], dst, sizeof(*dst)); - dest_num++; - } for (spec_index = 0; spec_index < flow_attr->num_of_specs; spec_index++) { err = parse_flow_attr(dev->mdev, spec, @@ -3564,6 +3560,11 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev, ib_flow += ((union ib_flow_spec *)ib_flow)->size; } + if (dst && !(flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DROP)) { + memcpy(&dest_arr[0], dst, sizeof(*dst)); + dest_num++; + } + if (!flow_is_multicast_only(flow_attr)) set_underlay_qp(dev, spec, underlay_qpn); @@ -3604,10 +3605,8 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev, } if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DROP) { - if (!(flow_act.action & MLX5_FLOW_CONTEXT_ACTION_COUNT)) { + if (!dest_num) rule_dst = NULL; - dest_num = 0; - } } else { if (is_egress) flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_ALLOW; diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 7019c12005f4..99d563dba91b 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -428,7 +428,7 @@ struct mlx5_ib_mr *mlx5_mr_cache_alloc(struct mlx5_ib_dev *dev, int entry) if (entry < 0 || entry >= MAX_MR_CACHE_ENTRIES) { mlx5_ib_err(dev, "cache entry %d is out of range\n", entry); - return NULL; + return ERR_PTR(-EINVAL); } ent = &cache->ent[entry]; diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c index dc71b6e16a07..b462eaca1ee3 100644 --- a/drivers/infiniband/hw/qedr/main.c +++ b/drivers/infiniband/hw/qedr/main.c @@ -357,6 +357,7 @@ static int qedr_alloc_resources(struct qedr_dev *dev) return -ENOMEM; spin_lock_init(&dev->sgid_lock); + xa_init_flags(&dev->srqs, XA_FLAGS_LOCK_IRQ); if (IS_IWARP(dev)) { xa_init_flags(&dev->qps, XA_FLAGS_LOCK_IRQ); diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c index 6f3ce86019b7..a7ccca3c4f89 100644 --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -1577,6 +1577,14 @@ static void qedr_cleanup_user(struct qedr_dev *dev, struct qedr_qp *qp) ib_umem_release(qp->urq.umem); qp->urq.umem = NULL; + + if (rdma_protocol_roce(&dev->ibdev, 1)) { + qedr_free_pbl(dev, &qp->usq.pbl_info, qp->usq.pbl_tbl); + qedr_free_pbl(dev, &qp->urq.pbl_info, qp->urq.pbl_tbl); + } else { + kfree(qp->usq.pbl_tbl); + kfree(qp->urq.pbl_tbl); + } } static int qedr_create_user_qp(struct qedr_dev *dev, @@ -2673,8 +2681,8 @@ int qedr_dereg_mr(struct ib_mr *ib_mr, struct ib_udata *udata) dev->ops->rdma_free_tid(dev->rdma_ctx, mr->hw_mr.itid); - if ((mr->type != QEDR_MR_DMA) && (mr->type != QEDR_MR_FRMR)) - qedr_free_pbl(dev, &mr->info.pbl_info, mr->info.pbl_table); + if (mr->type != QEDR_MR_DMA) + free_mr_info(dev, &mr->info); /* it could be user registered memory. */ ib_umem_release(mr->umem); diff --git a/drivers/infiniband/hw/qib/qib_sysfs.c b/drivers/infiniband/hw/qib/qib_sysfs.c index 3926be78036e..568b21eb6ea1 100644 --- a/drivers/infiniband/hw/qib/qib_sysfs.c +++ b/drivers/infiniband/hw/qib/qib_sysfs.c @@ -301,6 +301,9 @@ static ssize_t qib_portattr_show(struct kobject *kobj, struct qib_pportdata *ppd = container_of(kobj, struct qib_pportdata, pport_kobj); + if (!pattr->show) + return -EIO; + return pattr->show(ppd, buf); } @@ -312,6 +315,9 @@ static ssize_t qib_portattr_store(struct kobject *kobj, struct qib_pportdata *ppd = container_of(kobj, struct qib_pportdata, pport_kobj); + if (!pattr->store) + return -EIO; + return pattr->store(ppd, buf, len); } diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c index 5a3474f9351b..312c2fc961c0 100644 --- a/drivers/infiniband/sw/rxe/rxe_net.c +++ b/drivers/infiniband/sw/rxe/rxe_net.c @@ -117,10 +117,12 @@ static struct dst_entry *rxe_find_route6(struct net_device *ndev, memcpy(&fl6.daddr, daddr, sizeof(*daddr)); fl6.flowi6_proto = IPPROTO_UDP; - if (unlikely(ipv6_stub->ipv6_dst_lookup(sock_net(recv_sockets.sk6->sk), - recv_sockets.sk6->sk, &ndst, &fl6))) { + ndst = ipv6_stub->ipv6_dst_lookup_flow(sock_net(recv_sockets.sk6->sk), + recv_sockets.sk6->sk, &fl6, + NULL); + if (unlikely(IS_ERR(ndst))) { pr_err_ratelimited("no route to %pI6\n", daddr); - goto put; + return NULL; } if (unlikely(ndst->error)) { diff --git a/drivers/infiniband/sw/rxe/rxe_recv.c b/drivers/infiniband/sw/rxe/rxe_recv.c index f9a492ed900b..831ad578a7b2 100644 --- a/drivers/infiniband/sw/rxe/rxe_recv.c +++ b/drivers/infiniband/sw/rxe/rxe_recv.c @@ -389,7 +389,7 @@ void rxe_rcv(struct sk_buff *skb) calc_icrc = rxe_icrc_hdr(pkt, skb); calc_icrc = rxe_crc32(rxe, calc_icrc, (u8 *)payload_addr(pkt), - payload_size(pkt)); + payload_size(pkt) + bth_pad(pkt)); calc_icrc = (__force u32)cpu_to_be32(~calc_icrc); if (unlikely(calc_icrc != pack_icrc)) { if (skb->protocol == htons(ETH_P_IPV6)) diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c index c5d9b558fa90..e5031172c019 100644 --- a/drivers/infiniband/sw/rxe/rxe_req.c +++ b/drivers/infiniband/sw/rxe/rxe_req.c @@ -500,6 +500,12 @@ static int fill_packet(struct rxe_qp *qp, struct rxe_send_wqe *wqe, if (err) return err; } + if (bth_pad(pkt)) { + u8 *pad = payload_addr(pkt) + paylen; + + memset(pad, 0, bth_pad(pkt)); + crc = rxe_crc32(rxe, crc, pad, bth_pad(pkt)); + } } p = payload_addr(pkt) + paylen + bth_pad(pkt); diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c index 1cbfbd98eb22..c4a8195bf670 100644 --- a/drivers/infiniband/sw/rxe/rxe_resp.c +++ b/drivers/infiniband/sw/rxe/rxe_resp.c @@ -732,6 +732,13 @@ static enum resp_states read_reply(struct rxe_qp *qp, if (err) pr_err("Failed copying memory\n"); + if (bth_pad(&ack_pkt)) { + struct rxe_dev *rxe = to_rdev(qp->ibqp.device); + u8 *pad = payload_addr(&ack_pkt) + payload; + + memset(pad, 0, bth_pad(&ack_pkt)); + icrc = rxe_crc32(rxe, icrc, pad, bth_pad(&ack_pkt)); + } p = payload_addr(&ack_pkt) + payload + bth_pad(&ack_pkt); *p = ~icrc; diff --git a/drivers/infiniband/sw/siw/siw_cm.c b/drivers/infiniband/sw/siw/siw_cm.c index 8c1931a57f4a..0454561718d9 100644 --- a/drivers/infiniband/sw/siw/siw_cm.c +++ b/drivers/infiniband/sw/siw/siw_cm.c @@ -1867,14 +1867,7 @@ static int siw_listen_address(struct iw_cm_id *id, int backlog, list_add_tail(&cep->listenq, (struct list_head *)id->provider_data); cep->state = SIW_EPSTATE_LISTENING; - if (addr_family == AF_INET) - siw_dbg(id->device, "Listen at laddr %pI4 %u\n", - &(((struct sockaddr_in *)laddr)->sin_addr), - ((struct sockaddr_in *)laddr)->sin_port); - else - siw_dbg(id->device, "Listen at laddr %pI6 %u\n", - &(((struct sockaddr_in6 *)laddr)->sin6_addr), - ((struct sockaddr_in6 *)laddr)->sin6_port); + siw_dbg(id->device, "Listen at laddr %pISp\n", laddr); return 0; diff --git a/drivers/infiniband/sw/siw/siw_main.c b/drivers/infiniband/sw/siw/siw_main.c index 05a92f997f60..fb01407a310f 100644 --- a/drivers/infiniband/sw/siw/siw_main.c +++ b/drivers/infiniband/sw/siw/siw_main.c @@ -248,24 +248,6 @@ static struct ib_qp *siw_get_base_qp(struct ib_device *base_dev, int id) return NULL; } -static void siw_verbs_sq_flush(struct ib_qp *base_qp) -{ - struct siw_qp *qp = to_siw_qp(base_qp); - - down_write(&qp->state_lock); - siw_sq_flush(qp); - up_write(&qp->state_lock); -} - -static void siw_verbs_rq_flush(struct ib_qp *base_qp) -{ - struct siw_qp *qp = to_siw_qp(base_qp); - - down_write(&qp->state_lock); - siw_rq_flush(qp); - up_write(&qp->state_lock); -} - static const struct ib_device_ops siw_device_ops = { .owner = THIS_MODULE, .uverbs_abi_ver = SIW_ABI_VERSION, @@ -284,8 +266,6 @@ static const struct ib_device_ops siw_device_ops = { .destroy_cq = siw_destroy_cq, .destroy_qp = siw_destroy_qp, .destroy_srq = siw_destroy_srq, - .drain_rq = siw_verbs_rq_flush, - .drain_sq = siw_verbs_sq_flush, .get_dma_mr = siw_get_dma_mr, .get_port_immutable = siw_get_port_immutable, .iw_accept = siw_accept, diff --git a/drivers/infiniband/sw/siw/siw_verbs.c b/drivers/infiniband/sw/siw/siw_verbs.c index b18a677832e1..1b1a40db529c 100644 --- a/drivers/infiniband/sw/siw/siw_verbs.c +++ b/drivers/infiniband/sw/siw/siw_verbs.c @@ -685,6 +685,47 @@ static int siw_copy_inline_sgl(const struct ib_send_wr *core_wr, return bytes; } +/* Complete SQ WR's without processing */ +static int siw_sq_flush_wr(struct siw_qp *qp, const struct ib_send_wr *wr, + const struct ib_send_wr **bad_wr) +{ + struct siw_sqe sqe = {}; + int rv = 0; + + while (wr) { + sqe.id = wr->wr_id; + sqe.opcode = wr->opcode; + rv = siw_sqe_complete(qp, &sqe, 0, SIW_WC_WR_FLUSH_ERR); + if (rv) { + if (bad_wr) + *bad_wr = wr; + break; + } + wr = wr->next; + } + return rv; +} + +/* Complete RQ WR's without processing */ +static int siw_rq_flush_wr(struct siw_qp *qp, const struct ib_recv_wr *wr, + const struct ib_recv_wr **bad_wr) +{ + struct siw_rqe rqe = {}; + int rv = 0; + + while (wr) { + rqe.id = wr->wr_id; + rv = siw_rqe_complete(qp, &rqe, 0, 0, SIW_WC_WR_FLUSH_ERR); + if (rv) { + if (bad_wr) + *bad_wr = wr; + break; + } + wr = wr->next; + } + return rv; +} + /* * siw_post_send() * @@ -703,26 +744,54 @@ int siw_post_send(struct ib_qp *base_qp, const struct ib_send_wr *wr, unsigned long flags; int rv = 0; + if (wr && !qp->kernel_verbs) { + siw_dbg_qp(qp, "wr must be empty for user mapped sq\n"); + *bad_wr = wr; + return -EINVAL; + } + /* * Try to acquire QP state lock. Must be non-blocking * to accommodate kernel clients needs. */ if (!down_read_trylock(&qp->state_lock)) { - *bad_wr = wr; - siw_dbg_qp(qp, "QP locked, state %d\n", qp->attrs.state); - return -ENOTCONN; + if (qp->attrs.state == SIW_QP_STATE_ERROR) { + /* + * ERROR state is final, so we can be sure + * this state will not change as long as the QP + * exists. + * + * This handles an ib_drain_sq() call with + * a concurrent request to set the QP state + * to ERROR. + */ + rv = siw_sq_flush_wr(qp, wr, bad_wr); + } else { + siw_dbg_qp(qp, "QP locked, state %d\n", + qp->attrs.state); + *bad_wr = wr; + rv = -ENOTCONN; + } + return rv; } if (unlikely(qp->attrs.state != SIW_QP_STATE_RTS)) { + if (qp->attrs.state == SIW_QP_STATE_ERROR) { + /* + * Immediately flush this WR to CQ, if QP + * is in ERROR state. SQ is guaranteed to + * be empty, so WR complets in-order. + * + * Typically triggered by ib_drain_sq(). + */ + rv = siw_sq_flush_wr(qp, wr, bad_wr); + } else { + siw_dbg_qp(qp, "QP out of state %d\n", + qp->attrs.state); + *bad_wr = wr; + rv = -ENOTCONN; + } up_read(&qp->state_lock); - *bad_wr = wr; - siw_dbg_qp(qp, "QP out of state %d\n", qp->attrs.state); - return -ENOTCONN; - } - if (wr && !qp->kernel_verbs) { - siw_dbg_qp(qp, "wr must be empty for user mapped sq\n"); - up_read(&qp->state_lock); - *bad_wr = wr; - return -EINVAL; + return rv; } spin_lock_irqsave(&qp->sq_lock, flags); @@ -917,24 +986,54 @@ int siw_post_receive(struct ib_qp *base_qp, const struct ib_recv_wr *wr, *bad_wr = wr; return -EOPNOTSUPP; /* what else from errno.h? */ } + if (!qp->kernel_verbs) { + siw_dbg_qp(qp, "no kernel post_recv for user mapped sq\n"); + *bad_wr = wr; + return -EINVAL; + } + /* * Try to acquire QP state lock. Must be non-blocking * to accommodate kernel clients needs. */ if (!down_read_trylock(&qp->state_lock)) { - *bad_wr = wr; - return -ENOTCONN; - } - if (!qp->kernel_verbs) { - siw_dbg_qp(qp, "no kernel post_recv for user mapped sq\n"); - up_read(&qp->state_lock); - *bad_wr = wr; - return -EINVAL; + if (qp->attrs.state == SIW_QP_STATE_ERROR) { + /* + * ERROR state is final, so we can be sure + * this state will not change as long as the QP + * exists. + * + * This handles an ib_drain_rq() call with + * a concurrent request to set the QP state + * to ERROR. + */ + rv = siw_rq_flush_wr(qp, wr, bad_wr); + } else { + siw_dbg_qp(qp, "QP locked, state %d\n", + qp->attrs.state); + *bad_wr = wr; + rv = -ENOTCONN; + } + return rv; } if (qp->attrs.state > SIW_QP_STATE_RTS) { + if (qp->attrs.state == SIW_QP_STATE_ERROR) { + /* + * Immediately flush this WR to CQ, if QP + * is in ERROR state. RQ is guaranteed to + * be empty, so WR complets in-order. + * + * Typically triggered by ib_drain_rq(). + */ + rv = siw_rq_flush_wr(qp, wr, bad_wr); + } else { + siw_dbg_qp(qp, "QP out of state %d\n", + qp->attrs.state); + *bad_wr = wr; + rv = -ENOTCONN; + } up_read(&qp->state_lock); - *bad_wr = wr; - return -EINVAL; + return rv; } /* * Serialize potentially multiple producers. diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c index 2e72fc5af157..c4c015c60446 100644 --- a/drivers/infiniband/ulp/iser/iscsi_iser.c +++ b/drivers/infiniband/ulp/iser/iscsi_iser.c @@ -646,6 +646,7 @@ iscsi_iser_session_create(struct iscsi_endpoint *ep, if (ib_conn->pi_support) { u32 sig_caps = ib_dev->attrs.sig_prot_cap; + shost->sg_prot_tablesize = shost->sg_tablesize; scsi_host_set_prot(shost, iser_dif_prot_caps(sig_caps)); scsi_host_set_guard(shost, SHOST_DIX_GUARD_IP | SHOST_DIX_GUARD_CRC); diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index e25c70a56be6..02b92e3cd9a8 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -1364,9 +1364,11 @@ static int srpt_build_cmd_rsp(struct srpt_rdma_ch *ch, struct srpt_send_ioctx *ioctx, u64 tag, int status) { + struct se_cmd *cmd = &ioctx->cmd; struct srp_rsp *srp_rsp; const u8 *sense_data; int sense_data_len, max_sense_len; + u32 resid = cmd->residual_count; /* * The lowest bit of all SAM-3 status codes is zero (see also @@ -1388,6 +1390,28 @@ static int srpt_build_cmd_rsp(struct srpt_rdma_ch *ch, srp_rsp->tag = tag; srp_rsp->status = status; + if (cmd->se_cmd_flags & SCF_UNDERFLOW_BIT) { + if (cmd->data_direction == DMA_TO_DEVICE) { + /* residual data from an underflow write */ + srp_rsp->flags = SRP_RSP_FLAG_DOUNDER; + srp_rsp->data_out_res_cnt = cpu_to_be32(resid); + } else if (cmd->data_direction == DMA_FROM_DEVICE) { + /* residual data from an underflow read */ + srp_rsp->flags = SRP_RSP_FLAG_DIUNDER; + srp_rsp->data_in_res_cnt = cpu_to_be32(resid); + } + } else if (cmd->se_cmd_flags & SCF_OVERFLOW_BIT) { + if (cmd->data_direction == DMA_TO_DEVICE) { + /* residual data from an overflow write */ + srp_rsp->flags = SRP_RSP_FLAG_DOOVER; + srp_rsp->data_out_res_cnt = cpu_to_be32(resid); + } else if (cmd->data_direction == DMA_FROM_DEVICE) { + /* residual data from an overflow read */ + srp_rsp->flags = SRP_RSP_FLAG_DIOVER; + srp_rsp->data_in_res_cnt = cpu_to_be32(resid); + } + } + if (sense_data_len) { BUILD_BUG_ON(MIN_MAX_RSP_SIZE <= sizeof(*srp_rsp)); max_sense_len = ch->max_ti_iu_len - sizeof(*srp_rsp); diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c index d7dd6fcf2db0..f918fca9ada3 100644 --- a/drivers/input/evdev.c +++ b/drivers/input/evdev.c @@ -224,13 +224,13 @@ static void __pass_event(struct evdev_client *client, */ client->tail = (client->head - 2) & (client->bufsize - 1); - client->buffer[client->tail].input_event_sec = - event->input_event_sec; - client->buffer[client->tail].input_event_usec = - event->input_event_usec; - client->buffer[client->tail].type = EV_SYN; - client->buffer[client->tail].code = SYN_DROPPED; - client->buffer[client->tail].value = 0; + client->buffer[client->tail] = (struct input_event) { + .input_event_sec = event->input_event_sec, + .input_event_usec = event->input_event_usec, + .type = EV_SYN, + .code = SYN_DROPPED, + .value = 0, + }; client->packet_head = client->tail; } diff --git a/drivers/input/input.c b/drivers/input/input.c index 55086279d044..ee6c3234df36 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -878,16 +878,18 @@ static int input_default_setkeycode(struct input_dev *dev, } } - __clear_bit(*old_keycode, dev->keybit); - __set_bit(ke->keycode, dev->keybit); - - for (i = 0; i < dev->keycodemax; i++) { - if (input_fetch_keycode(dev, i) == *old_keycode) { - __set_bit(*old_keycode, dev->keybit); - break; /* Setting the bit twice is useless, so break */ + if (*old_keycode <= KEY_MAX) { + __clear_bit(*old_keycode, dev->keybit); + for (i = 0; i < dev->keycodemax; i++) { + if (input_fetch_keycode(dev, i) == *old_keycode) { + __set_bit(*old_keycode, dev->keybit); + /* Setting the bit twice is useless, so break */ + break; + } } } + __set_bit(ke->keycode, dev->keybit); return 0; } @@ -943,9 +945,13 @@ int input_set_keycode(struct input_dev *dev, * Simulate keyup event if keycode is not present * in the keymap anymore */ - if (test_bit(EV_KEY, dev->evbit) && - !is_event_supported(old_keycode, dev->keybit, KEY_MAX) && - __test_and_clear_bit(old_keycode, dev->key)) { + if (old_keycode > KEY_MAX) { + dev_warn(dev->dev.parent ?: &dev->dev, + "%s: got too big old keycode %#x\n", + __func__, old_keycode); + } else if (test_bit(EV_KEY, dev->evbit) && + !is_event_supported(old_keycode, dev->keybit, KEY_MAX) && + __test_and_clear_bit(old_keycode, dev->key)) { struct input_value vals[] = { { EV_KEY, old_keycode, 0 }, input_value_sync diff --git a/drivers/input/joystick/psxpad-spi.c b/drivers/input/joystick/psxpad-spi.c index 7eee1b0e360f..99a6052500ca 100644 --- a/drivers/input/joystick/psxpad-spi.c +++ b/drivers/input/joystick/psxpad-spi.c @@ -292,7 +292,7 @@ static int psxpad_spi_probe(struct spi_device *spi) if (!pad) return -ENOMEM; - pdev = input_allocate_polled_device(); + pdev = devm_input_allocate_polled_device(&spi->dev); if (!pdev) { dev_err(&spi->dev, "failed to allocate input device\n"); return -ENOMEM; diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c index 84051f20b18a..002654ec7040 100644 --- a/drivers/input/misc/uinput.c +++ b/drivers/input/misc/uinput.c @@ -74,12 +74,16 @@ static int uinput_dev_event(struct input_dev *dev, struct uinput_device *udev = input_get_drvdata(dev); struct timespec64 ts; - udev->buff[udev->head].type = type; - udev->buff[udev->head].code = code; - udev->buff[udev->head].value = value; ktime_get_ts64(&ts); - udev->buff[udev->head].input_event_sec = ts.tv_sec; - udev->buff[udev->head].input_event_usec = ts.tv_nsec / NSEC_PER_USEC; + + udev->buff[udev->head] = (struct input_event) { + .input_event_sec = ts.tv_sec, + .input_event_usec = ts.tv_nsec / NSEC_PER_USEC, + .type = type, + .code = code, + .value = value, + }; + udev->head = (udev->head + 1) % UINPUT_BUFFER_SIZE; wake_up_interruptible(&udev->waitq); diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index 56fae3472114..1ae6f8bba9ae 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -172,6 +172,7 @@ static const char * const smbus_pnp_ids[] = { "LEN0071", /* T480 */ "LEN0072", /* X1 Carbon Gen 5 (2017) - Elan/ALPS trackpoint */ "LEN0073", /* X1 Carbon G5 (Elantech) */ + "LEN0091", /* X1 Carbon 6 */ "LEN0092", /* X1 Carbon 6 */ "LEN0093", /* T480 */ "LEN0096", /* X280 */ diff --git a/drivers/input/rmi4/rmi_f34v7.c b/drivers/input/rmi4/rmi_f34v7.c index a4cabf52740c..74f7c6f214ff 100644 --- a/drivers/input/rmi4/rmi_f34v7.c +++ b/drivers/input/rmi4/rmi_f34v7.c @@ -1189,6 +1189,9 @@ int rmi_f34v7_do_reflash(struct f34_data *f34, const struct firmware *fw) { int ret; + f34->fn->rmi_dev->driver->set_irq_bits(f34->fn->rmi_dev, + f34->fn->irq_mask); + rmi_f34v7_read_queries_bl_version(f34); f34->v7.image = fw->data; diff --git a/drivers/input/rmi4/rmi_smbus.c b/drivers/input/rmi4/rmi_smbus.c index 2407ea43de59..b313c579914f 100644 --- a/drivers/input/rmi4/rmi_smbus.c +++ b/drivers/input/rmi4/rmi_smbus.c @@ -163,7 +163,6 @@ static int rmi_smb_write_block(struct rmi_transport_dev *xport, u16 rmiaddr, /* prepare to write next block of bytes */ cur_len -= SMB_MAX_COUNT; databuff += SMB_MAX_COUNT; - rmiaddr += SMB_MAX_COUNT; } exit: mutex_unlock(&rmi_smb->page_mutex); @@ -215,7 +214,6 @@ static int rmi_smb_read_block(struct rmi_transport_dev *xport, u16 rmiaddr, /* prepare to read next block of bytes */ cur_len -= SMB_MAX_COUNT; databuff += SMB_MAX_COUNT; - rmiaddr += SMB_MAX_COUNT; } retval = 0; diff --git a/drivers/input/touchscreen/atmel_mxt_ts.c b/drivers/input/touchscreen/atmel_mxt_ts.c index 24c4b691b1c9..ae60442efda0 100644 --- a/drivers/input/touchscreen/atmel_mxt_ts.c +++ b/drivers/input/touchscreen/atmel_mxt_ts.c @@ -3156,6 +3156,8 @@ static int __maybe_unused mxt_suspend(struct device *dev) mutex_unlock(&input_dev->mutex); + disable_irq(data->irq); + return 0; } @@ -3168,6 +3170,8 @@ static int __maybe_unused mxt_resume(struct device *dev) if (!input_dev) return 0; + enable_irq(data->irq); + mutex_lock(&input_dev->mutex); if (input_dev->users) diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c index fb43aa708660..0403102e807e 100644 --- a/drivers/input/touchscreen/goodix.c +++ b/drivers/input/touchscreen/goodix.c @@ -128,6 +128,15 @@ static const unsigned long goodix_irq_flags[] = { */ static const struct dmi_system_id rotated_screen[] = { #if defined(CONFIG_DMI) && defined(CONFIG_X86) + { + .ident = "Teclast X89", + .matches = { + /* tPAD is too generic, also match on bios date */ + DMI_MATCH(DMI_BOARD_VENDOR, "TECLAST"), + DMI_MATCH(DMI_BOARD_NAME, "tPAD"), + DMI_MATCH(DMI_BIOS_DATE, "12/19/2014"), + }, + }, { .ident = "WinBook TW100", .matches = { diff --git a/drivers/input/touchscreen/ili210x.c b/drivers/input/touchscreen/ili210x.c index e9006407c9bc..f4ebdab06280 100644 --- a/drivers/input/touchscreen/ili210x.c +++ b/drivers/input/touchscreen/ili210x.c @@ -334,7 +334,12 @@ static int ili210x_i2c_probe(struct i2c_client *client, input_set_abs_params(input, ABS_MT_POSITION_X, 0, 0xffff, 0, 0); input_set_abs_params(input, ABS_MT_POSITION_Y, 0, 0xffff, 0, 0); touchscreen_parse_properties(input, true, &priv->prop); - input_mt_init_slots(input, priv->max_touches, INPUT_MT_DIRECT); + + error = input_mt_init_slots(input, priv->max_touches, INPUT_MT_DIRECT); + if (error) { + dev_err(dev, "Unable to set up slots, err: %d\n", error); + return error; + } error = devm_add_action(dev, ili210x_cancel_work, priv); if (error) diff --git a/drivers/input/touchscreen/st1232.c b/drivers/input/touchscreen/st1232.c index 1139714e72e2..1c5f8875cb79 100644 --- a/drivers/input/touchscreen/st1232.c +++ b/drivers/input/touchscreen/st1232.c @@ -149,6 +149,11 @@ static void st1232_ts_power(struct st1232_ts_data *ts, bool poweron) gpiod_set_value_cansleep(ts->reset_gpio, !poweron); } +static void st1232_ts_power_off(void *data) +{ + st1232_ts_power(data, false); +} + static const struct st_chip_info st1232_chip_info = { .have_z = true, .max_x = 0x31f, /* 800 - 1 */ @@ -229,6 +234,13 @@ static int st1232_ts_probe(struct i2c_client *client, st1232_ts_power(ts, true); + error = devm_add_action_or_reset(&client->dev, st1232_ts_power_off, ts); + if (error) { + dev_err(&client->dev, + "Failed to install power off action: %d\n", error); + return error; + } + input_dev->name = "st1232-touchscreen"; input_dev->id.bustype = BUS_I2C; input_dev->dev.parent = &client->dev; @@ -271,15 +283,6 @@ static int st1232_ts_probe(struct i2c_client *client, return 0; } -static int st1232_ts_remove(struct i2c_client *client) -{ - struct st1232_ts_data *ts = i2c_get_clientdata(client); - - st1232_ts_power(ts, false); - - return 0; -} - static int __maybe_unused st1232_ts_suspend(struct device *dev) { struct i2c_client *client = to_i2c_client(dev); @@ -329,7 +332,6 @@ MODULE_DEVICE_TABLE(of, st1232_ts_dt_ids); static struct i2c_driver st1232_ts_driver = { .probe = st1232_ts_probe, - .remove = st1232_ts_remove, .id_table = st1232_ts_id, .driver = { .name = ST1232_TS_NAME, diff --git a/drivers/interconnect/qcom/qcs404.c b/drivers/interconnect/qcom/qcs404.c index b4966d8f3348..8e0735a87040 100644 --- a/drivers/interconnect/qcom/qcs404.c +++ b/drivers/interconnect/qcom/qcs404.c @@ -414,7 +414,7 @@ static int qnoc_probe(struct platform_device *pdev) struct icc_provider *provider; struct qcom_icc_node **qnodes; struct qcom_icc_provider *qp; - struct icc_node *node; + struct icc_node *node, *tmp; size_t num_nodes, i; int ret; @@ -494,7 +494,7 @@ static int qnoc_probe(struct platform_device *pdev) return 0; err: - list_for_each_entry(node, &provider->nodes, node_list) { + list_for_each_entry_safe(node, tmp, &provider->nodes, node_list) { icc_node_del(node); icc_node_destroy(node->id); } @@ -508,9 +508,9 @@ static int qnoc_remove(struct platform_device *pdev) { struct qcom_icc_provider *qp = platform_get_drvdata(pdev); struct icc_provider *provider = &qp->provider; - struct icc_node *n; + struct icc_node *n, *tmp; - list_for_each_entry(n, &provider->nodes, node_list) { + list_for_each_entry_safe(n, tmp, &provider->nodes, node_list) { icc_node_del(n); icc_node_destroy(n->id); } diff --git a/drivers/interconnect/qcom/sdm845.c b/drivers/interconnect/qcom/sdm845.c index 502a6c22b41e..387267ee9648 100644 --- a/drivers/interconnect/qcom/sdm845.c +++ b/drivers/interconnect/qcom/sdm845.c @@ -868,9 +868,9 @@ static int qnoc_remove(struct platform_device *pdev) { struct qcom_icc_provider *qp = platform_get_drvdata(pdev); struct icc_provider *provider = &qp->provider; - struct icc_node *n; + struct icc_node *n, *tmp; - list_for_each_entry(n, &provider->nodes, node_list) { + list_for_each_entry_safe(n, tmp, &provider->nodes, node_list) { icc_node_del(n); icc_node_destroy(n->id); } diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 8da93e730d6f..ed90361b84dc 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -3611,19 +3611,19 @@ static int arm_smmu_device_probe(struct platform_device *pdev) /* Interrupt lines */ - irq = platform_get_irq_byname(pdev, "combined"); + irq = platform_get_irq_byname_optional(pdev, "combined"); if (irq > 0) smmu->combined_irq = irq; else { - irq = platform_get_irq_byname(pdev, "eventq"); + irq = platform_get_irq_byname_optional(pdev, "eventq"); if (irq > 0) smmu->evtq.q.irq = irq; - irq = platform_get_irq_byname(pdev, "priq"); + irq = platform_get_irq_byname_optional(pdev, "priq"); if (irq > 0) smmu->priq.q.irq = irq; - irq = platform_get_irq_byname(pdev, "gerror"); + irq = platform_get_irq_byname_optional(pdev, "gerror"); if (irq > 0) smmu->gerr_irq = irq; } diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index f321279baf9e..51456e7f264f 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -43,7 +44,6 @@ struct iommu_dma_cookie { dma_addr_t msi_iova; }; struct list_head msi_page_list; - spinlock_t msi_lock; /* Domain for flush queue callback; NULL if flush queue not in use */ struct iommu_domain *fq_domain; @@ -62,7 +62,6 @@ static struct iommu_dma_cookie *cookie_alloc(enum iommu_dma_cookie_type type) cookie = kzalloc(sizeof(*cookie), GFP_KERNEL); if (cookie) { - spin_lock_init(&cookie->msi_lock); INIT_LIST_HEAD(&cookie->msi_page_list); cookie->type = type; } @@ -1150,7 +1149,7 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev, if (msi_page->phys == msi_addr) return msi_page; - msi_page = kzalloc(sizeof(*msi_page), GFP_ATOMIC); + msi_page = kzalloc(sizeof(*msi_page), GFP_KERNEL); if (!msi_page) return NULL; @@ -1180,7 +1179,7 @@ int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr) struct iommu_domain *domain = iommu_get_domain_for_dev(dev); struct iommu_dma_cookie *cookie; struct iommu_dma_msi_page *msi_page; - unsigned long flags; + static DEFINE_MUTEX(msi_prepare_lock); /* see below */ if (!domain || !domain->iova_cookie) { desc->iommu_cookie = NULL; @@ -1190,13 +1189,13 @@ int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr) cookie = domain->iova_cookie; /* - * We disable IRQs to rule out a possible inversion against - * irq_desc_lock if, say, someone tries to retarget the affinity - * of an MSI from within an IPI handler. + * In fact the whole prepare operation should already be serialised by + * irq_domain_mutex further up the callchain, but that's pretty subtle + * on its own, so consider this locking as failsafe documentation... */ - spin_lock_irqsave(&cookie->msi_lock, flags); + mutex_lock(&msi_prepare_lock); msi_page = iommu_dma_get_msi_page(dev, msi_addr, domain); - spin_unlock_irqrestore(&cookie->msi_lock, flags); + mutex_unlock(&msi_prepare_lock); msi_desc_set_iommu_cookie(desc, msi_page); diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 6db6d969e31c..e84c5dfe146f 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -5447,9 +5447,6 @@ static int intel_iommu_map(struct iommu_domain *domain, int prot = 0; int ret; - if (dmar_domain->flags & DOMAIN_FLAG_LOSE_CHILDREN) - return -EINVAL; - if (iommu_prot & IOMMU_READ) prot |= DMA_PTE_READ; if (iommu_prot & IOMMU_WRITE) @@ -5492,8 +5489,6 @@ static size_t intel_iommu_unmap(struct iommu_domain *domain, /* Cope with horrid API which requires us to unmap more than the size argument if it happens to be a large-page mapping. */ BUG_ON(!pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level)); - if (dmar_domain->flags & DOMAIN_FLAG_LOSE_CHILDREN) - return 0; if (size < VTD_PAGE_SIZE << level_to_offset_bits(level)) size = VTD_PAGE_SIZE << level_to_offset_bits(level); @@ -5525,9 +5520,6 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain, int level = 0; u64 phys = 0; - if (dmar_domain->flags & DOMAIN_FLAG_LOSE_CHILDREN) - return 0; - pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level); if (pte) phys = dma_pte_addr(pte); @@ -5601,8 +5593,10 @@ static int intel_iommu_add_device(struct device *dev) group = iommu_group_get_for_dev(dev); - if (IS_ERR(group)) - return PTR_ERR(group); + if (IS_ERR(group)) { + ret = PTR_ERR(group); + goto unlink; + } iommu_group_put(group); @@ -5628,7 +5622,8 @@ static int intel_iommu_add_device(struct device *dev) if (!get_private_domain_for_dev(dev)) { dev_warn(dev, "Failed to get a private domain.\n"); - return -ENOMEM; + ret = -ENOMEM; + goto unlink; } dev_info(dev, @@ -5643,6 +5638,10 @@ static int intel_iommu_add_device(struct device *dev) } return 0; + +unlink: + iommu_device_unlink(&iommu->iommu, dev); + return ret; } static void intel_iommu_remove_device(struct device *dev) @@ -5705,8 +5704,8 @@ static void intel_iommu_get_resv_regions(struct device *device, struct pci_dev *pdev = to_pci_dev(device); if ((pdev->class >> 8) == PCI_CLASS_BRIDGE_ISA) { - reg = iommu_alloc_resv_region(0, 1UL << 24, 0, - IOMMU_RESV_DIRECT); + reg = iommu_alloc_resv_region(0, 1UL << 24, prot, + IOMMU_RESV_DIRECT_RELAXABLE); if (reg) list_add_tail(®->list, head); } @@ -5794,6 +5793,13 @@ static void intel_iommu_apply_resv_region(struct device *dev, WARN_ON_ONCE(!reserve_iova(&dmar_domain->iovad, start, end)); } +static struct iommu_group *intel_iommu_device_group(struct device *dev) +{ + if (dev_is_pci(dev)) + return pci_device_group(dev); + return generic_device_group(dev); +} + #ifdef CONFIG_INTEL_IOMMU_SVM struct intel_iommu *intel_svm_device_to_iommu(struct device *dev) { @@ -5966,7 +5972,7 @@ const struct iommu_ops intel_iommu_ops = { .get_resv_regions = intel_iommu_get_resv_regions, .put_resv_regions = intel_iommu_put_resv_regions, .apply_resv_region = intel_iommu_apply_resv_region, - .device_group = pci_device_group, + .device_group = intel_iommu_device_group, .dev_has_feat = intel_iommu_dev_has_feat, .dev_feat_enabled = intel_iommu_dev_feat_enabled, .dev_enable_feat = intel_iommu_dev_enable_feat, diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c index 9b159132405d..dca88f9fdf29 100644 --- a/drivers/iommu/intel-svm.c +++ b/drivers/iommu/intel-svm.c @@ -104,11 +104,7 @@ static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_d { struct qi_desc desc; - /* - * Do PASID granu IOTLB invalidation if page selective capability is - * not available. - */ - if (pages == -1 || !cap_pgsel_inv(svm->iommu->cap)) { + if (pages == -1) { desc.qw0 = QI_EIOTLB_PASID(svm->pasid) | QI_EIOTLB_DID(sdev->did) | QI_EIOTLB_GRAN(QI_GRAN_NONG_PASID) | diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index d658c7c6a2ab..cd3c0ea56657 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -312,8 +312,8 @@ int iommu_insert_resv_region(struct iommu_resv_region *new, list_for_each_entry_safe(iter, tmp, regions, list) { phys_addr_t top_end, iter_end = iter->start + iter->length - 1; - /* no merge needed on elements of different types than @nr */ - if (iter->type != nr->type) { + /* no merge needed on elements of different types than @new */ + if (iter->type != new->type) { list_move_tail(&iter->list, &stack); continue; } @@ -751,6 +751,7 @@ int iommu_group_add_device(struct iommu_group *group, struct device *dev) mutex_unlock(&group->mutex); dev->iommu_group = NULL; kobject_put(group->devices_kobj); + sysfs_remove_link(group->devices_kobj, device->name); err_free_name: kfree(device->name); err_remove_link: @@ -2221,13 +2222,13 @@ request_default_domain_for_dev(struct device *dev, unsigned long type) goto out; } - iommu_group_create_direct_mappings(group, dev); - /* Make the domain the default for this group */ if (group->default_domain) iommu_domain_free(group->default_domain); group->default_domain = domain; + iommu_group_create_direct_mappings(group, dev); + dev_info(dev, "Using iommu %s mapping\n", type == IOMMU_DOMAIN_DMA ? "dma" : "direct"); diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c index 41c605b0058f..c7a914b9bbbc 100644 --- a/drivers/iommu/iova.c +++ b/drivers/iommu/iova.c @@ -233,7 +233,7 @@ static DEFINE_MUTEX(iova_cache_mutex); struct iova *alloc_iova_mem(void) { - return kmem_cache_alloc(iova_cache, GFP_ATOMIC); + return kmem_cache_zalloc(iova_cache, GFP_ATOMIC); } EXPORT_SYMBOL(alloc_iova_mem); diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 67a483c1a935..c2f6c78fee44 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -219,22 +219,37 @@ static void mtk_iommu_tlb_sync(void *cookie) static void mtk_iommu_tlb_flush_walk(unsigned long iova, size_t size, size_t granule, void *cookie) { + struct mtk_iommu_data *data = cookie; + unsigned long flags; + + spin_lock_irqsave(&data->tlb_lock, flags); mtk_iommu_tlb_add_flush_nosync(iova, size, granule, false, cookie); mtk_iommu_tlb_sync(cookie); + spin_unlock_irqrestore(&data->tlb_lock, flags); } static void mtk_iommu_tlb_flush_leaf(unsigned long iova, size_t size, size_t granule, void *cookie) { + struct mtk_iommu_data *data = cookie; + unsigned long flags; + + spin_lock_irqsave(&data->tlb_lock, flags); mtk_iommu_tlb_add_flush_nosync(iova, size, granule, true, cookie); mtk_iommu_tlb_sync(cookie); + spin_unlock_irqrestore(&data->tlb_lock, flags); } static void mtk_iommu_tlb_flush_page_nosync(struct iommu_iotlb_gather *gather, unsigned long iova, size_t granule, void *cookie) { + struct mtk_iommu_data *data = cookie; + unsigned long flags; + + spin_lock_irqsave(&data->tlb_lock, flags); mtk_iommu_tlb_add_flush_nosync(iova, granule, granule, true, cookie); + spin_unlock_irqrestore(&data->tlb_lock, flags); } static const struct iommu_flush_ops mtk_iommu_flush_ops = { @@ -447,13 +462,18 @@ static size_t mtk_iommu_unmap(struct iommu_domain *domain, static void mtk_iommu_flush_iotlb_all(struct iommu_domain *domain) { - mtk_iommu_tlb_sync(mtk_iommu_get_m4u_data()); + mtk_iommu_tlb_flush_all(mtk_iommu_get_m4u_data()); } static void mtk_iommu_iotlb_sync(struct iommu_domain *domain, struct iommu_iotlb_gather *gather) { - mtk_iommu_tlb_sync(mtk_iommu_get_m4u_data()); + struct mtk_iommu_data *data = mtk_iommu_get_m4u_data(); + unsigned long flags; + + spin_lock_irqsave(&data->tlb_lock, flags); + mtk_iommu_tlb_sync(data); + spin_unlock_irqrestore(&data->tlb_lock, flags); } static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain, @@ -733,6 +753,7 @@ static int mtk_iommu_probe(struct platform_device *pdev) if (ret) return ret; + spin_lock_init(&data->tlb_lock); list_add_tail(&data->list, &m4ulist); if (!iommu_present(&platform_bus_type)) diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h index fc0f16eabacd..8cae22de7663 100644 --- a/drivers/iommu/mtk_iommu.h +++ b/drivers/iommu/mtk_iommu.h @@ -58,6 +58,7 @@ struct mtk_iommu_data { struct iommu_group *m4u_group; bool enable_4GB; bool tlb_flush_active; + spinlock_t tlb_lock; /* lock for tlb range flush */ struct iommu_device iommu; const struct mtk_iommu_plat_data *plat_data; diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c index 4dcbf68dfda4..0df091934361 100644 --- a/drivers/iommu/rockchip-iommu.c +++ b/drivers/iommu/rockchip-iommu.c @@ -980,13 +980,13 @@ static struct iommu_domain *rk_iommu_domain_alloc(unsigned type) if (!dma_dev) return NULL; - rk_domain = devm_kzalloc(dma_dev, sizeof(*rk_domain), GFP_KERNEL); + rk_domain = kzalloc(sizeof(*rk_domain), GFP_KERNEL); if (!rk_domain) return NULL; if (type == IOMMU_DOMAIN_DMA && iommu_get_dma_cookie(&rk_domain->domain)) - return NULL; + goto err_free_domain; /* * rk32xx iommus use a 2 level pagetable. @@ -1021,6 +1021,8 @@ static struct iommu_domain *rk_iommu_domain_alloc(unsigned type) err_put_cookie: if (type == IOMMU_DOMAIN_DMA) iommu_put_dma_cookie(&rk_domain->domain); +err_free_domain: + kfree(rk_domain); return NULL; } @@ -1049,6 +1051,7 @@ static void rk_iommu_domain_free(struct iommu_domain *domain) if (domain->type == IOMMU_DOMAIN_DMA) iommu_put_dma_cookie(&rk_domain->domain); + kfree(rk_domain); } static int rk_iommu_add_device(struct device *dev) diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index 7293fc3f796d..dd486233e282 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -159,9 +159,9 @@ static bool smmu_dma_addr_valid(struct tegra_smmu *smmu, dma_addr_t addr) return (addr & smmu->pfn_mask) == addr; } -static dma_addr_t smmu_pde_to_dma(u32 pde) +static dma_addr_t smmu_pde_to_dma(struct tegra_smmu *smmu, u32 pde) { - return pde << 12; + return (dma_addr_t)(pde & smmu->pfn_mask) << 12; } static void smmu_flush_ptc_all(struct tegra_smmu *smmu) @@ -549,6 +549,7 @@ static u32 *tegra_smmu_pte_lookup(struct tegra_smmu_as *as, unsigned long iova, dma_addr_t *dmap) { unsigned int pd_index = iova_pd_index(iova); + struct tegra_smmu *smmu = as->smmu; struct page *pt_page; u32 *pd; @@ -557,7 +558,7 @@ static u32 *tegra_smmu_pte_lookup(struct tegra_smmu_as *as, unsigned long iova, return NULL; pd = page_address(as->pd); - *dmap = smmu_pde_to_dma(pd[pd_index]); + *dmap = smmu_pde_to_dma(smmu, pd[pd_index]); return tegra_smmu_pte_offset(pt_page, iova); } @@ -599,7 +600,7 @@ static u32 *as_get_pte(struct tegra_smmu_as *as, dma_addr_t iova, } else { u32 *pd = page_address(as->pd); - *dmap = smmu_pde_to_dma(pd[pde]); + *dmap = smmu_pde_to_dma(smmu, pd[pde]); } return tegra_smmu_pte_offset(as->pts[pde], iova); @@ -624,7 +625,7 @@ static void tegra_smmu_pte_put_use(struct tegra_smmu_as *as, unsigned long iova) if (--as->count[pde] == 0) { struct tegra_smmu *smmu = as->smmu; u32 *pd = page_address(as->pd); - dma_addr_t pte_dma = smmu_pde_to_dma(pd[pde]); + dma_addr_t pte_dma = smmu_pde_to_dma(smmu, pd[pde]); tegra_smmu_set_pde(as, iova, 0); diff --git a/drivers/irqchip/irq-bcm7038-l1.c b/drivers/irqchip/irq-bcm7038-l1.c index fc75c61233aa..58bec2126966 100644 --- a/drivers/irqchip/irq-bcm7038-l1.c +++ b/drivers/irqchip/irq-bcm7038-l1.c @@ -281,6 +281,10 @@ static int __init bcm7038_l1_init_one(struct device_node *dn, pr_err("failed to map parent interrupt %d\n", parent_irq); return -EINVAL; } + + if (of_property_read_bool(dn, "brcm,irq-can-wake")) + enable_irq_wake(parent_irq); + irq_set_chained_handler_and_data(parent_irq, bcm7038_l1_irq_handle, intc); diff --git a/drivers/irqchip/irq-ingenic.c b/drivers/irqchip/irq-ingenic.c index f126255b3260..dda512dfe2c1 100644 --- a/drivers/irqchip/irq-ingenic.c +++ b/drivers/irqchip/irq-ingenic.c @@ -108,6 +108,14 @@ static int __init ingenic_intc_of_init(struct device_node *node, goto out_unmap_irq; } + domain = irq_domain_add_legacy(node, num_chips * 32, + JZ4740_IRQ_BASE, 0, + &irq_domain_simple_ops, NULL); + if (!domain) { + err = -ENOMEM; + goto out_unmap_base; + } + for (i = 0; i < num_chips; i++) { /* Mask all irqs */ writel(0xffffffff, intc->base + (i * CHIP_SIZE) + @@ -134,14 +142,11 @@ static int __init ingenic_intc_of_init(struct device_node *node, IRQ_NOPROBE | IRQ_LEVEL); } - domain = irq_domain_add_legacy(node, num_chips * 32, JZ4740_IRQ_BASE, 0, - &irq_domain_simple_ops, NULL); - if (!domain) - pr_warn("unable to register IRQ domain\n"); - setup_irq(parent_irq, &intc_cascade_action); return 0; +out_unmap_base: + iounmap(intc->base); out_unmap_irq: irq_dispose_mapping(parent_irq); out_free: diff --git a/drivers/leds/leds-an30259a.c b/drivers/leds/leds-an30259a.c index 250dc9d6f635..82350a28a564 100644 --- a/drivers/leds/leds-an30259a.c +++ b/drivers/leds/leds-an30259a.c @@ -305,6 +305,13 @@ static int an30259a_probe(struct i2c_client *client) chip->regmap = devm_regmap_init_i2c(client, &an30259a_regmap_config); + if (IS_ERR(chip->regmap)) { + err = PTR_ERR(chip->regmap); + dev_err(&client->dev, "Failed to allocate register map: %d\n", + err); + goto exit; + } + for (i = 0; i < chip->num_leds; i++) { struct led_init_data init_data = {}; diff --git a/drivers/leds/leds-lm3692x.c b/drivers/leds/leds-lm3692x.c index 3d381f2f73d0..1ac9a44570ee 100644 --- a/drivers/leds/leds-lm3692x.c +++ b/drivers/leds/leds-lm3692x.c @@ -334,9 +334,18 @@ static int lm3692x_probe_dt(struct lm3692x_led *led) return ret; } - led->regulator = devm_regulator_get(&led->client->dev, "vled"); - if (IS_ERR(led->regulator)) + led->regulator = devm_regulator_get_optional(&led->client->dev, "vled"); + if (IS_ERR(led->regulator)) { + ret = PTR_ERR(led->regulator); + if (ret != -ENODEV) { + if (ret != -EPROBE_DEFER) + dev_err(&led->client->dev, + "Failed to get vled regulator: %d\n", + ret); + return ret; + } led->regulator = NULL; + } child = device_get_next_child_node(&led->client->dev, child); if (!child) { diff --git a/drivers/leds/trigger/ledtrig-netdev.c b/drivers/leds/trigger/ledtrig-netdev.c index 136f86a1627d..d5e774d83021 100644 --- a/drivers/leds/trigger/ledtrig-netdev.c +++ b/drivers/leds/trigger/ledtrig-netdev.c @@ -302,10 +302,12 @@ static int netdev_trig_notify(struct notifier_block *nb, container_of(nb, struct led_netdev_data, notifier); if (evt != NETDEV_UP && evt != NETDEV_DOWN && evt != NETDEV_CHANGE - && evt != NETDEV_REGISTER && evt != NETDEV_UNREGISTER) + && evt != NETDEV_REGISTER && evt != NETDEV_UNREGISTER + && evt != NETDEV_CHANGENAME) return NOTIFY_DONE; if (!(dev == trigger_data->net_dev || + (evt == NETDEV_CHANGENAME && !strcmp(dev->name, trigger_data->device_name)) || (evt == NETDEV_REGISTER && !strcmp(dev->name, trigger_data->device_name)))) return NOTIFY_DONE; @@ -315,6 +317,7 @@ static int netdev_trig_notify(struct notifier_block *nb, clear_bit(NETDEV_LED_MODE_LINKUP, &trigger_data->mode); switch (evt) { + case NETDEV_CHANGENAME: case NETDEV_REGISTER: if (trigger_data->net_dev) dev_put(trigger_data->net_dev); diff --git a/drivers/mailbox/imx-mailbox.c b/drivers/mailbox/imx-mailbox.c index 9f74dee1a58c..afe625e88a5c 100644 --- a/drivers/mailbox/imx-mailbox.c +++ b/drivers/mailbox/imx-mailbox.c @@ -214,11 +214,24 @@ static void imx_mu_shutdown(struct mbox_chan *chan) struct imx_mu_priv *priv = to_imx_mu_priv(chan->mbox); struct imx_mu_con_priv *cp = chan->con_priv; - if (cp->type == IMX_MU_TYPE_TXDB) + if (cp->type == IMX_MU_TYPE_TXDB) { tasklet_kill(&cp->txdb_tasklet); + return; + } - imx_mu_xcr_rmw(priv, 0, IMX_MU_xCR_TIEn(cp->idx) | - IMX_MU_xCR_RIEn(cp->idx) | IMX_MU_xCR_GIEn(cp->idx)); + switch (cp->type) { + case IMX_MU_TYPE_TX: + imx_mu_xcr_rmw(priv, 0, IMX_MU_xCR_TIEn(cp->idx)); + break; + case IMX_MU_TYPE_RX: + imx_mu_xcr_rmw(priv, 0, IMX_MU_xCR_RIEn(cp->idx)); + break; + case IMX_MU_TYPE_RXDB: + imx_mu_xcr_rmw(priv, 0, IMX_MU_xCR_GIEn(cp->idx)); + break; + default: + break; + } free_irq(priv->irq, chan); } diff --git a/drivers/mailbox/tegra-hsp.c b/drivers/mailbox/tegra-hsp.c index 4c5ba35d48d4..834b35dc3b13 100644 --- a/drivers/mailbox/tegra-hsp.c +++ b/drivers/mailbox/tegra-hsp.c @@ -657,7 +657,7 @@ static int tegra_hsp_probe(struct platform_device *pdev) hsp->num_db = (value >> HSP_nDB_SHIFT) & HSP_nINT_MASK; hsp->num_si = (value >> HSP_nSI_SHIFT) & HSP_nINT_MASK; - err = platform_get_irq_byname(pdev, "doorbell"); + err = platform_get_irq_byname_optional(pdev, "doorbell"); if (err >= 0) hsp->doorbell_irq = err; @@ -677,7 +677,7 @@ static int tegra_hsp_probe(struct platform_device *pdev) if (!name) return -ENOMEM; - err = platform_get_irq_byname(pdev, name); + err = platform_get_irq_byname_optional(pdev, name); if (err >= 0) { hsp->shared_irqs[i] = err; count++; diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c index 6f776823b9ba..a1df0d95151c 100644 --- a/drivers/md/bcache/alloc.c +++ b/drivers/md/bcache/alloc.c @@ -377,7 +377,10 @@ static int bch_allocator_thread(void *arg) if (!fifo_full(&ca->free_inc)) goto retry_invalidate; - bch_prio_write(ca); + if (bch_prio_write(ca, false) < 0) { + ca->invalidate_needs_gc = 1; + wake_up_gc(ca->set); + } } } out: diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 013e35a9e317..deb924e1d790 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -977,7 +977,7 @@ bool bch_cached_dev_error(struct cached_dev *dc); __printf(2, 3) bool bch_cache_set_error(struct cache_set *c, const char *fmt, ...); -void bch_prio_write(struct cache *ca); +int bch_prio_write(struct cache *ca, bool wait); void bch_write_bdev_super(struct cached_dev *dc, struct closure *parent); extern struct workqueue_struct *bcache_wq; diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index ba434d9ac720..46a8b5a91c38 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -723,6 +723,8 @@ static unsigned long bch_mca_scan(struct shrinker *shrink, * IO can always make forward progress: */ nr /= c->btree_pages; + if (nr == 0) + nr = 1; nr = min_t(unsigned long, nr, mca_can_free(c)); i = 0; diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 20ed838e9413..64999c7a8033 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -529,12 +529,29 @@ static void prio_io(struct cache *ca, uint64_t bucket, int op, closure_sync(cl); } -void bch_prio_write(struct cache *ca) +int bch_prio_write(struct cache *ca, bool wait) { int i; struct bucket *b; struct closure cl; + pr_debug("free_prio=%zu, free_none=%zu, free_inc=%zu", + fifo_used(&ca->free[RESERVE_PRIO]), + fifo_used(&ca->free[RESERVE_NONE]), + fifo_used(&ca->free_inc)); + + /* + * Pre-check if there are enough free buckets. In the non-blocking + * scenario it's better to fail early rather than starting to allocate + * buckets and do a cleanup later in case of failure. + */ + if (!wait) { + size_t avail = fifo_used(&ca->free[RESERVE_PRIO]) + + fifo_used(&ca->free[RESERVE_NONE]); + if (prio_buckets(ca) > avail) + return -ENOMEM; + } + closure_init_stack(&cl); lockdep_assert_held(&ca->set->bucket_lock); @@ -544,9 +561,6 @@ void bch_prio_write(struct cache *ca) atomic_long_add(ca->sb.bucket_size * prio_buckets(ca), &ca->meta_sectors_written); - //pr_debug("free %zu, free_inc %zu, unused %zu", fifo_used(&ca->free), - // fifo_used(&ca->free_inc), fifo_used(&ca->unused)); - for (i = prio_buckets(ca) - 1; i >= 0; --i) { long bucket; struct prio_set *p = ca->disk_buckets; @@ -564,7 +578,7 @@ void bch_prio_write(struct cache *ca) p->magic = pset_magic(&ca->sb); p->csum = bch_crc64(&p->magic, bucket_bytes(ca) - 8); - bucket = bch_bucket_alloc(ca, RESERVE_PRIO, true); + bucket = bch_bucket_alloc(ca, RESERVE_PRIO, wait); BUG_ON(bucket == -1); mutex_unlock(&ca->set->bucket_lock); @@ -593,6 +607,7 @@ void bch_prio_write(struct cache *ca) ca->prio_last_buckets[i] = ca->prio_buckets[i]; } + return 0; } static void prio_read(struct cache *ca, uint64_t bucket) @@ -761,20 +776,28 @@ static inline int idx_to_first_minor(int idx) static void bcache_device_free(struct bcache_device *d) { + struct gendisk *disk = d->disk; + lockdep_assert_held(&bch_register_lock); - pr_info("%s stopped", d->disk->disk_name); + if (disk) + pr_info("%s stopped", disk->disk_name); + else + pr_err("bcache device (NULL gendisk) stopped"); if (d->c) bcache_device_detach(d); - if (d->disk && d->disk->flags & GENHD_FL_UP) - del_gendisk(d->disk); - if (d->disk && d->disk->queue) - blk_cleanup_queue(d->disk->queue); - if (d->disk) { + + if (disk) { + if (disk->flags & GENHD_FL_UP) + del_gendisk(disk); + + if (disk->queue) + blk_cleanup_queue(disk->queue); + ida_simple_remove(&bcache_device_idx, - first_minor_to_idx(d->disk->first_minor)); - put_disk(d->disk); + first_minor_to_idx(disk->first_minor)); + put_disk(disk); } bioset_exit(&d->bio_split); @@ -1954,7 +1977,7 @@ static int run_cache_set(struct cache_set *c) mutex_lock(&c->bucket_lock); for_each_cache(ca, c, i) - bch_prio_write(ca); + bch_prio_write(ca, true); mutex_unlock(&c->bucket_lock); err = "cannot allocate new UUID bucket"; diff --git a/drivers/md/dm-clone-metadata.c b/drivers/md/dm-clone-metadata.c index 6bc8c1d1c351..54e4fdd607e1 100644 --- a/drivers/md/dm-clone-metadata.c +++ b/drivers/md/dm-clone-metadata.c @@ -67,23 +67,34 @@ struct superblock_disk { * To save constantly doing look ups on disk we keep an in core copy of the * on-disk bitmap, the region_map. * - * To further reduce metadata I/O overhead we use a second bitmap, the dmap - * (dirty bitmap), which tracks the dirty words, i.e. longs, of the region_map. + * In order to track which regions are hydrated during a metadata transaction, + * we use a second set of bitmaps, the dmap (dirty bitmap), which includes two + * bitmaps, namely dirty_regions and dirty_words. The dirty_regions bitmap + * tracks the regions that got hydrated during the current metadata + * transaction. The dirty_words bitmap tracks the dirty words, i.e. longs, of + * the dirty_regions bitmap. + * + * This allows us to precisely track the regions that were hydrated during the + * current metadata transaction and update the metadata accordingly, when we + * commit the current transaction. This is important because dm-clone should + * only commit the metadata of regions that were properly flushed to the + * destination device beforehand. Otherwise, in case of a crash, we could end + * up with a corrupted dm-clone device. * * When a region finishes hydrating dm-clone calls * dm_clone_set_region_hydrated(), or for discard requests * dm_clone_cond_set_range(), which sets the corresponding bits in region_map * and dmap. * - * During a metadata commit we scan the dmap for dirty region_map words (longs) - * and update accordingly the on-disk metadata. Thus, we don't have to flush to - * disk the whole region_map. We can just flush the dirty region_map words. + * During a metadata commit we scan dmap->dirty_words and dmap->dirty_regions + * and update the on-disk metadata accordingly. Thus, we don't have to flush to + * disk the whole region_map. We can just flush the dirty region_map bits. * - * We use a dirty bitmap, which is smaller than the original region_map, to - * reduce the amount of memory accesses during a metadata commit. As dm-bitset - * accesses the on-disk bitmap in 64-bit word granularity, there is no - * significant benefit in tracking the dirty region_map bits with a smaller - * granularity. + * We use the helper dmap->dirty_words bitmap, which is smaller than the + * original region_map, to reduce the amount of memory accesses during a + * metadata commit. Moreover, as dm-bitset also accesses the on-disk bitmap in + * 64-bit word granularity, the dirty_words bitmap helps us avoid useless disk + * accesses. * * We could update directly the on-disk bitmap, when dm-clone calls either * dm_clone_set_region_hydrated() or dm_clone_cond_set_range(), buts this @@ -92,12 +103,13 @@ struct superblock_disk { * e.g., in a hooked overwrite bio's completion routine, and further reduce the * I/O completion latency. * - * We maintain two dirty bitmaps. During a metadata commit we atomically swap - * the currently used dmap with the unused one. This allows the metadata update - * functions to run concurrently with an ongoing commit. + * We maintain two dirty bitmap sets. During a metadata commit we atomically + * swap the currently used dmap with the unused one. This allows the metadata + * update functions to run concurrently with an ongoing commit. */ struct dirty_map { unsigned long *dirty_words; + unsigned long *dirty_regions; unsigned int changed; }; @@ -115,6 +127,9 @@ struct dm_clone_metadata { struct dirty_map dmap[2]; struct dirty_map *current_dmap; + /* Protected by lock */ + struct dirty_map *committing_dmap; + /* * In core copy of the on-disk bitmap to save constantly doing look ups * on disk. @@ -461,34 +476,53 @@ static size_t bitmap_size(unsigned long nr_bits) return BITS_TO_LONGS(nr_bits) * sizeof(long); } -static int dirty_map_init(struct dm_clone_metadata *cmd) +static int __dirty_map_init(struct dirty_map *dmap, unsigned long nr_words, + unsigned long nr_regions) { - cmd->dmap[0].changed = 0; - cmd->dmap[0].dirty_words = kvzalloc(bitmap_size(cmd->nr_words), GFP_KERNEL); + dmap->changed = 0; - if (!cmd->dmap[0].dirty_words) { - DMERR("Failed to allocate dirty bitmap"); + dmap->dirty_words = kvzalloc(bitmap_size(nr_words), GFP_KERNEL); + if (!dmap->dirty_words) + return -ENOMEM; + + dmap->dirty_regions = kvzalloc(bitmap_size(nr_regions), GFP_KERNEL); + if (!dmap->dirty_regions) { + kvfree(dmap->dirty_words); return -ENOMEM; } - cmd->dmap[1].changed = 0; - cmd->dmap[1].dirty_words = kvzalloc(bitmap_size(cmd->nr_words), GFP_KERNEL); + return 0; +} + +static void __dirty_map_exit(struct dirty_map *dmap) +{ + kvfree(dmap->dirty_words); + kvfree(dmap->dirty_regions); +} + +static int dirty_map_init(struct dm_clone_metadata *cmd) +{ + if (__dirty_map_init(&cmd->dmap[0], cmd->nr_words, cmd->nr_regions)) { + DMERR("Failed to allocate dirty bitmap"); + return -ENOMEM; + } - if (!cmd->dmap[1].dirty_words) { + if (__dirty_map_init(&cmd->dmap[1], cmd->nr_words, cmd->nr_regions)) { DMERR("Failed to allocate dirty bitmap"); - kvfree(cmd->dmap[0].dirty_words); + __dirty_map_exit(&cmd->dmap[0]); return -ENOMEM; } cmd->current_dmap = &cmd->dmap[0]; + cmd->committing_dmap = NULL; return 0; } static void dirty_map_exit(struct dm_clone_metadata *cmd) { - kvfree(cmd->dmap[0].dirty_words); - kvfree(cmd->dmap[1].dirty_words); + __dirty_map_exit(&cmd->dmap[0]); + __dirty_map_exit(&cmd->dmap[1]); } static int __load_bitset_in_core(struct dm_clone_metadata *cmd) @@ -633,21 +667,23 @@ unsigned long dm_clone_find_next_unhydrated_region(struct dm_clone_metadata *cmd return find_next_zero_bit(cmd->region_map, cmd->nr_regions, start); } -static int __update_metadata_word(struct dm_clone_metadata *cmd, unsigned long word) +static int __update_metadata_word(struct dm_clone_metadata *cmd, + unsigned long *dirty_regions, + unsigned long word) { int r; unsigned long index = word * BITS_PER_LONG; unsigned long max_index = min(cmd->nr_regions, (word + 1) * BITS_PER_LONG); while (index < max_index) { - if (test_bit(index, cmd->region_map)) { + if (test_bit(index, dirty_regions)) { r = dm_bitset_set_bit(&cmd->bitset_info, cmd->bitset_root, index, &cmd->bitset_root); - if (r) { DMERR("dm_bitset_set_bit failed"); return r; } + __clear_bit(index, dirty_regions); } index++; } @@ -721,7 +757,7 @@ static int __flush_dmap(struct dm_clone_metadata *cmd, struct dirty_map *dmap) if (word == cmd->nr_words) break; - r = __update_metadata_word(cmd, word); + r = __update_metadata_word(cmd, dmap->dirty_regions, word); if (r) return r; @@ -743,16 +779,18 @@ static int __flush_dmap(struct dm_clone_metadata *cmd, struct dirty_map *dmap) return 0; } -int dm_clone_metadata_commit(struct dm_clone_metadata *cmd) +int dm_clone_metadata_pre_commit(struct dm_clone_metadata *cmd) { - int r = -EPERM; + int r = 0; unsigned long flags; struct dirty_map *dmap, *next_dmap; down_write(&cmd->lock); - if (cmd->fail_io || dm_bm_is_read_only(cmd->bm)) + if (cmd->fail_io || dm_bm_is_read_only(cmd->bm)) { + r = -EPERM; goto out; + } /* Get current dirty bitmap */ dmap = cmd->current_dmap; @@ -764,7 +802,7 @@ int dm_clone_metadata_commit(struct dm_clone_metadata *cmd) * The last commit failed, so we don't have a clean dirty-bitmap to * use. */ - if (WARN_ON(next_dmap->changed)) { + if (WARN_ON(next_dmap->changed || cmd->committing_dmap)) { r = -EINVAL; goto out; } @@ -774,11 +812,33 @@ int dm_clone_metadata_commit(struct dm_clone_metadata *cmd) cmd->current_dmap = next_dmap; spin_unlock_irqrestore(&cmd->bitmap_lock, flags); - /* - * No one is accessing the old dirty bitmap anymore, so we can flush - * it. - */ - r = __flush_dmap(cmd, dmap); + /* Set old dirty bitmap as currently committing */ + cmd->committing_dmap = dmap; +out: + up_write(&cmd->lock); + + return r; +} + +int dm_clone_metadata_commit(struct dm_clone_metadata *cmd) +{ + int r = -EPERM; + + down_write(&cmd->lock); + + if (cmd->fail_io || dm_bm_is_read_only(cmd->bm)) + goto out; + + if (WARN_ON(!cmd->committing_dmap)) { + r = -EINVAL; + goto out; + } + + r = __flush_dmap(cmd, cmd->committing_dmap); + if (!r) { + /* Clear committing dmap */ + cmd->committing_dmap = NULL; + } out: up_write(&cmd->lock); @@ -803,6 +863,7 @@ int dm_clone_set_region_hydrated(struct dm_clone_metadata *cmd, unsigned long re dmap = cmd->current_dmap; __set_bit(word, dmap->dirty_words); + __set_bit(region_nr, dmap->dirty_regions); __set_bit(region_nr, cmd->region_map); dmap->changed = 1; @@ -831,6 +892,7 @@ int dm_clone_cond_set_range(struct dm_clone_metadata *cmd, unsigned long start, if (!test_bit(region_nr, cmd->region_map)) { word = region_nr / BITS_PER_LONG; __set_bit(word, dmap->dirty_words); + __set_bit(region_nr, dmap->dirty_regions); __set_bit(region_nr, cmd->region_map); dmap->changed = 1; } diff --git a/drivers/md/dm-clone-metadata.h b/drivers/md/dm-clone-metadata.h index 434bff08508b..c7848c49aef8 100644 --- a/drivers/md/dm-clone-metadata.h +++ b/drivers/md/dm-clone-metadata.h @@ -73,7 +73,23 @@ void dm_clone_metadata_close(struct dm_clone_metadata *cmd); /* * Commit dm-clone metadata to disk. + * + * We use a two phase commit: + * + * 1. dm_clone_metadata_pre_commit(): Prepare the current transaction for + * committing. After this is called, all subsequent metadata updates, done + * through either dm_clone_set_region_hydrated() or + * dm_clone_cond_set_range(), will be part of the **next** transaction. + * + * 2. dm_clone_metadata_commit(): Actually commit the current transaction to + * disk and start a new transaction. + * + * This allows dm-clone to flush the destination device after step (1) to + * ensure that all freshly hydrated regions, for which we are updating the + * metadata, are properly written to non-volatile storage and won't be lost in + * case of a crash. */ +int dm_clone_metadata_pre_commit(struct dm_clone_metadata *cmd); int dm_clone_metadata_commit(struct dm_clone_metadata *cmd); /* @@ -110,6 +126,7 @@ int dm_clone_metadata_abort(struct dm_clone_metadata *cmd); * Switches metadata to a read only mode. Once read-only mode has been entered * the following functions will return -EPERM: * + * dm_clone_metadata_pre_commit() * dm_clone_metadata_commit() * dm_clone_set_region_hydrated() * dm_clone_cond_set_range() diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c index 4ca8f1977222..e6e5d24a79f5 100644 --- a/drivers/md/dm-clone-target.c +++ b/drivers/md/dm-clone-target.c @@ -86,6 +86,12 @@ struct clone { struct dm_clone_metadata *cmd; + /* + * bio used to flush the destination device, before committing the + * metadata. + */ + struct bio flush_bio; + /* Region hydration hash table */ struct hash_table_bucket *ht; @@ -1106,10 +1112,13 @@ static bool need_commit_due_to_time(struct clone *clone) /* * A non-zero return indicates read-only or fail mode. */ -static int commit_metadata(struct clone *clone) +static int commit_metadata(struct clone *clone, bool *dest_dev_flushed) { int r = 0; + if (dest_dev_flushed) + *dest_dev_flushed = false; + mutex_lock(&clone->commit_lock); if (!dm_clone_changed_this_transaction(clone->cmd)) @@ -1120,8 +1129,26 @@ static int commit_metadata(struct clone *clone) goto out; } - r = dm_clone_metadata_commit(clone->cmd); + r = dm_clone_metadata_pre_commit(clone->cmd); + if (unlikely(r)) { + __metadata_operation_failed(clone, "dm_clone_metadata_pre_commit", r); + goto out; + } + bio_reset(&clone->flush_bio); + bio_set_dev(&clone->flush_bio, clone->dest_dev->bdev); + clone->flush_bio.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH; + + r = submit_bio_wait(&clone->flush_bio); + if (unlikely(r)) { + __metadata_operation_failed(clone, "flush destination device", r); + goto out; + } + + if (dest_dev_flushed) + *dest_dev_flushed = true; + + r = dm_clone_metadata_commit(clone->cmd); if (unlikely(r)) { __metadata_operation_failed(clone, "dm_clone_metadata_commit", r); goto out; @@ -1194,6 +1221,7 @@ static void process_deferred_flush_bios(struct clone *clone) { struct bio *bio; unsigned long flags; + bool dest_dev_flushed; struct bio_list bios = BIO_EMPTY_LIST; struct bio_list bio_completions = BIO_EMPTY_LIST; @@ -1213,7 +1241,7 @@ static void process_deferred_flush_bios(struct clone *clone) !(dm_clone_changed_this_transaction(clone->cmd) && need_commit_due_to_time(clone))) return; - if (commit_metadata(clone)) { + if (commit_metadata(clone, &dest_dev_flushed)) { bio_list_merge(&bios, &bio_completions); while ((bio = bio_list_pop(&bios))) @@ -1227,8 +1255,17 @@ static void process_deferred_flush_bios(struct clone *clone) while ((bio = bio_list_pop(&bio_completions))) bio_endio(bio); - while ((bio = bio_list_pop(&bios))) - generic_make_request(bio); + while ((bio = bio_list_pop(&bios))) { + if ((bio->bi_opf & REQ_PREFLUSH) && dest_dev_flushed) { + /* We just flushed the destination device as part of + * the metadata commit, so there is no reason to send + * another flush. + */ + bio_endio(bio); + } else { + generic_make_request(bio); + } + } } static void do_worker(struct work_struct *work) @@ -1400,7 +1437,7 @@ static void clone_status(struct dm_target *ti, status_type_t type, /* Commit to ensure statistics aren't out-of-date */ if (!(status_flags & DM_STATUS_NOFLUSH_FLAG) && !dm_suspended(ti)) - (void) commit_metadata(clone); + (void) commit_metadata(clone, NULL); r = dm_clone_get_free_metadata_block_count(clone->cmd, &nr_free_metadata_blocks); @@ -1834,6 +1871,7 @@ static int clone_ctr(struct dm_target *ti, unsigned int argc, char **argv) bio_list_init(&clone->deferred_flush_completions); clone->hydration_offset = 0; atomic_set(&clone->hydrations_in_flight, 0); + bio_init(&clone->flush_bio, NULL, 0); clone->wq = alloc_workqueue("dm-" DM_MSG_PREFIX, WQ_MEM_RECLAIM, 0); if (!clone->wq) { @@ -1907,6 +1945,7 @@ static void clone_dtr(struct dm_target *ti) struct clone *clone = ti->private; mutex_destroy(&clone->commit_lock); + bio_uninit(&clone->flush_bio); for (i = 0; i < clone->nr_ctr_args; i++) kfree(clone->ctr_args[i]); @@ -1961,7 +2000,7 @@ static void clone_postsuspend(struct dm_target *ti) wait_event(clone->hydration_stopped, !atomic_read(&clone->hydrations_in_flight)); flush_workqueue(clone->wq); - (void) commit_metadata(clone); + (void) commit_metadata(clone, NULL); } static void clone_resume(struct dm_target *ti) diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index f87f6495652f..eb9782fc93fe 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -2700,21 +2700,18 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) } ret = -ENOMEM; - cc->io_queue = alloc_workqueue("kcryptd_io/%s", - WQ_HIGHPRI | WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, - 1, devname); + cc->io_queue = alloc_workqueue("kcryptd_io/%s", WQ_MEM_RECLAIM, 1, devname); if (!cc->io_queue) { ti->error = "Couldn't create kcryptd io queue"; goto bad; } if (test_bit(DM_CRYPT_SAME_CPU, &cc->flags)) - cc->crypt_queue = alloc_workqueue("kcryptd/%s", - WQ_HIGHPRI | WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, + cc->crypt_queue = alloc_workqueue("kcryptd/%s", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, 1, devname); else cc->crypt_queue = alloc_workqueue("kcryptd/%s", - WQ_HIGHPRI | WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | WQ_UNBOUND, + WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | WQ_UNBOUND, num_online_cpus(), devname); if (!cc->crypt_queue) { ti->error = "Couldn't create kcryptd queue"; diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index dbcc1e41cd57..e0c32793c248 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -599,45 +599,10 @@ static struct pgpath *__map_bio(struct multipath *m, struct bio *bio) return pgpath; } -static struct pgpath *__map_bio_fast(struct multipath *m, struct bio *bio) -{ - struct pgpath *pgpath; - unsigned long flags; - - /* Do we need to select a new pgpath? */ - /* - * FIXME: currently only switching path if no path (due to failure, etc) - * - which negates the point of using a path selector - */ - pgpath = READ_ONCE(m->current_pgpath); - if (!pgpath) - pgpath = choose_pgpath(m, bio->bi_iter.bi_size); - - if (!pgpath) { - if (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) { - /* Queue for the daemon to resubmit */ - spin_lock_irqsave(&m->lock, flags); - bio_list_add(&m->queued_bios, bio); - spin_unlock_irqrestore(&m->lock, flags); - queue_work(kmultipathd, &m->process_queued_bios); - - return ERR_PTR(-EAGAIN); - } - return NULL; - } - - return pgpath; -} - static int __multipath_map_bio(struct multipath *m, struct bio *bio, struct dm_mpath_io *mpio) { - struct pgpath *pgpath; - - if (!m->hw_handler_name) - pgpath = __map_bio_fast(m, bio); - else - pgpath = __map_bio(m, bio); + struct pgpath *pgpath = __map_bio(m, bio); if (IS_ERR(pgpath)) return DM_MAPIO_SUBMITTED; diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index 4c68a7b93d5e..b88d6d701f5b 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -188,6 +188,15 @@ struct dm_pool_metadata { unsigned long flags; sector_t data_block_size; + /* + * Pre-commit callback. + * + * This allows the thin provisioning target to run a callback before + * the metadata are committed. + */ + dm_pool_pre_commit_fn pre_commit_fn; + void *pre_commit_context; + /* * We reserve a section of the metadata for commit overhead. * All reported space does *not* include this. @@ -826,6 +835,14 @@ static int __commit_transaction(struct dm_pool_metadata *pmd) if (unlikely(!pmd->in_service)) return 0; + if (pmd->pre_commit_fn) { + r = pmd->pre_commit_fn(pmd->pre_commit_context); + if (r < 0) { + DMERR("pre-commit callback failed"); + return r; + } + } + r = __write_changed_details(pmd); if (r < 0) return r; @@ -892,6 +909,8 @@ struct dm_pool_metadata *dm_pool_metadata_open(struct block_device *bdev, pmd->in_service = false; pmd->bdev = bdev; pmd->data_block_size = data_block_size; + pmd->pre_commit_fn = NULL; + pmd->pre_commit_context = NULL; r = __create_persistent_data_objects(pmd, format_device); if (r) { @@ -2044,6 +2063,16 @@ int dm_pool_register_metadata_threshold(struct dm_pool_metadata *pmd, return r; } +void dm_pool_register_pre_commit_callback(struct dm_pool_metadata *pmd, + dm_pool_pre_commit_fn fn, + void *context) +{ + pmd_write_lock_in_core(pmd); + pmd->pre_commit_fn = fn; + pmd->pre_commit_context = context; + pmd_write_unlock(pmd); +} + int dm_pool_metadata_set_needs_check(struct dm_pool_metadata *pmd) { int r = -EINVAL; diff --git a/drivers/md/dm-thin-metadata.h b/drivers/md/dm-thin-metadata.h index f6be0d733c20..7ef56bd2a7e3 100644 --- a/drivers/md/dm-thin-metadata.h +++ b/drivers/md/dm-thin-metadata.h @@ -230,6 +230,13 @@ bool dm_pool_metadata_needs_check(struct dm_pool_metadata *pmd); */ void dm_pool_issue_prefetches(struct dm_pool_metadata *pmd); +/* Pre-commit callback */ +typedef int (*dm_pool_pre_commit_fn)(void *context); + +void dm_pool_register_pre_commit_callback(struct dm_pool_metadata *pmd, + dm_pool_pre_commit_fn fn, + void *context); + /*----------------------------------------------------------------*/ #endif diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index fcd887703f95..1696bfd23ad1 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -328,6 +328,7 @@ struct pool_c { dm_block_t low_water_blocks; struct pool_features requested_pf; /* Features requested during table load */ struct pool_features adjusted_pf; /* Features used after adjusting for constituent devices */ + struct bio flush_bio; }; /* @@ -2392,8 +2393,16 @@ static void process_deferred_bios(struct pool *pool) while ((bio = bio_list_pop(&bio_completions))) bio_endio(bio); - while ((bio = bio_list_pop(&bios))) - generic_make_request(bio); + while ((bio = bio_list_pop(&bios))) { + /* + * The data device was flushed as part of metadata commit, + * so complete redundant flushes immediately. + */ + if (bio->bi_opf & REQ_PREFLUSH) + bio_endio(bio); + else + generic_make_request(bio); + } } static void do_worker(struct work_struct *ws) @@ -3127,6 +3136,7 @@ static void pool_dtr(struct dm_target *ti) __pool_dec(pt->pool); dm_put_device(ti, pt->metadata_dev); dm_put_device(ti, pt->data_dev); + bio_uninit(&pt->flush_bio); kfree(pt); mutex_unlock(&dm_thin_pool_table.mutex); @@ -3192,6 +3202,29 @@ static void metadata_low_callback(void *context) dm_table_event(pool->ti->table); } +/* + * We need to flush the data device **before** committing the metadata. + * + * This ensures that the data blocks of any newly inserted mappings are + * properly written to non-volatile storage and won't be lost in case of a + * crash. + * + * Failure to do so can result in data corruption in the case of internal or + * external snapshots and in the case of newly provisioned blocks, when block + * zeroing is enabled. + */ +static int metadata_pre_commit_callback(void *context) +{ + struct pool_c *pt = context; + struct bio *flush_bio = &pt->flush_bio; + + bio_reset(flush_bio); + bio_set_dev(flush_bio, pt->data_dev->bdev); + flush_bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH; + + return submit_bio_wait(flush_bio); +} + static sector_t get_dev_size(struct block_device *bdev) { return i_size_read(bdev->bd_inode) >> SECTOR_SHIFT; @@ -3360,6 +3393,7 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv) pt->data_dev = data_dev; pt->low_water_blocks = low_water_blocks; pt->adjusted_pf = pt->requested_pf = pf; + bio_init(&pt->flush_bio, NULL, 0); ti->num_flush_bios = 1; /* @@ -3386,6 +3420,10 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv) if (r) goto out_flags_changed; + dm_pool_register_pre_commit_callback(pt->pool->pmd, + metadata_pre_commit_callback, + pt); + pt->callbacks.congested_fn = pool_is_congested; dm_table_add_target_callbacks(ti->table, &pt->callbacks); diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index d06b8aa41e26..43d1af1d8173 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -1218,7 +1218,8 @@ static int writecache_map(struct dm_target *ti, struct bio *bio) } } while (bio->bi_iter.bi_size); - if (unlikely(wc->uncommitted_blocks >= wc->autocommit_blocks)) + if (unlikely(bio->bi_opf & REQ_FUA || + wc->uncommitted_blocks >= wc->autocommit_blocks)) writecache_flush(wc); else writecache_schedule_autocommit(wc); diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c index 595a73110e17..ac1179ca80d9 100644 --- a/drivers/md/dm-zoned-metadata.c +++ b/drivers/md/dm-zoned-metadata.c @@ -554,6 +554,7 @@ static struct dmz_mblock *dmz_get_mblock(struct dmz_metadata *zmd, TASK_UNINTERRUPTIBLE); if (test_bit(DMZ_META_ERROR, &mblk->state)) { dmz_release_mblock(zmd, mblk); + dmz_check_bdev(zmd->dev); return ERR_PTR(-EIO); } @@ -625,6 +626,8 @@ static int dmz_rdwr_block(struct dmz_metadata *zmd, int op, sector_t block, ret = submit_bio_wait(bio); bio_put(bio); + if (ret) + dmz_check_bdev(zmd->dev); return ret; } @@ -691,6 +694,7 @@ static int dmz_write_dirty_mblocks(struct dmz_metadata *zmd, TASK_UNINTERRUPTIBLE); if (test_bit(DMZ_META_ERROR, &mblk->state)) { clear_bit(DMZ_META_ERROR, &mblk->state); + dmz_check_bdev(zmd->dev); ret = -EIO; } nr_mblks_submitted--; @@ -768,7 +772,7 @@ int dmz_flush_metadata(struct dmz_metadata *zmd) /* If there are no dirty metadata blocks, just flush the device cache */ if (list_empty(&write_list)) { ret = blkdev_issue_flush(zmd->dev->bdev, GFP_NOIO, NULL); - goto out; + goto err; } /* @@ -778,7 +782,7 @@ int dmz_flush_metadata(struct dmz_metadata *zmd) */ ret = dmz_log_dirty_mblocks(zmd, &write_list); if (ret) - goto out; + goto err; /* * The log is on disk. It is now safe to update in place @@ -786,11 +790,11 @@ int dmz_flush_metadata(struct dmz_metadata *zmd) */ ret = dmz_write_dirty_mblocks(zmd, &write_list, zmd->mblk_primary); if (ret) - goto out; + goto err; ret = dmz_write_sb(zmd, zmd->mblk_primary); if (ret) - goto out; + goto err; while (!list_empty(&write_list)) { mblk = list_first_entry(&write_list, struct dmz_mblock, link); @@ -805,16 +809,20 @@ int dmz_flush_metadata(struct dmz_metadata *zmd) zmd->sb_gen++; out: - if (ret && !list_empty(&write_list)) { - spin_lock(&zmd->mblk_lock); - list_splice(&write_list, &zmd->mblk_dirty_list); - spin_unlock(&zmd->mblk_lock); - } - dmz_unlock_flush(zmd); up_write(&zmd->mblk_sem); return ret; + +err: + if (!list_empty(&write_list)) { + spin_lock(&zmd->mblk_lock); + list_splice(&write_list, &zmd->mblk_dirty_list); + spin_unlock(&zmd->mblk_lock); + } + if (!dmz_check_bdev(zmd->dev)) + ret = -EIO; + goto out; } /* @@ -1244,6 +1252,7 @@ static int dmz_update_zone(struct dmz_metadata *zmd, struct dm_zone *zone) if (ret) { dmz_dev_err(zmd->dev, "Get zone %u report failed", dmz_id(zmd, zone)); + dmz_check_bdev(zmd->dev); return ret; } diff --git a/drivers/md/dm-zoned-reclaim.c b/drivers/md/dm-zoned-reclaim.c index d240d7ca8a8a..e7ace908a9b7 100644 --- a/drivers/md/dm-zoned-reclaim.c +++ b/drivers/md/dm-zoned-reclaim.c @@ -82,6 +82,7 @@ static int dmz_reclaim_align_wp(struct dmz_reclaim *zrc, struct dm_zone *zone, "Align zone %u wp %llu to %llu (wp+%u) blocks failed %d", dmz_id(zmd, zone), (unsigned long long)wp_block, (unsigned long long)block, nr_blocks, ret); + dmz_check_bdev(zrc->dev); return ret; } @@ -489,12 +490,7 @@ static void dmz_reclaim_work(struct work_struct *work) ret = dmz_do_reclaim(zrc); if (ret) { dmz_dev_debug(zrc->dev, "Reclaim error %d\n", ret); - if (ret == -EIO) - /* - * LLD might be performing some error handling sequence - * at the underlying device. To not interfere, do not - * attempt to schedule the next reclaim run immediately. - */ + if (!dmz_check_bdev(zrc->dev)) return; } diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index d3bcc4197f5d..4574e0dedbd6 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -80,6 +80,8 @@ static inline void dmz_bio_endio(struct bio *bio, blk_status_t status) if (status != BLK_STS_OK && bio->bi_status == BLK_STS_OK) bio->bi_status = status; + if (bio->bi_status != BLK_STS_OK) + bioctx->target->dev->flags |= DMZ_CHECK_BDEV; if (refcount_dec_and_test(&bioctx->ref)) { struct dm_zone *zone = bioctx->zone; @@ -565,31 +567,51 @@ static int dmz_queue_chunk_work(struct dmz_target *dmz, struct bio *bio) } /* - * Check the backing device availability. If it's on the way out, + * Check if the backing device is being removed. If it's on the way out, * start failing I/O. Reclaim and metadata components also call this * function to cleanly abort operation in the event of such failure. */ bool dmz_bdev_is_dying(struct dmz_dev *dmz_dev) { - struct gendisk *disk; + if (dmz_dev->flags & DMZ_BDEV_DYING) + return true; - if (!(dmz_dev->flags & DMZ_BDEV_DYING)) { - disk = dmz_dev->bdev->bd_disk; - if (blk_queue_dying(bdev_get_queue(dmz_dev->bdev))) { - dmz_dev_warn(dmz_dev, "Backing device queue dying"); - dmz_dev->flags |= DMZ_BDEV_DYING; - } else if (disk->fops->check_events) { - if (disk->fops->check_events(disk, 0) & - DISK_EVENT_MEDIA_CHANGE) { - dmz_dev_warn(dmz_dev, "Backing device offline"); - dmz_dev->flags |= DMZ_BDEV_DYING; - } - } + if (dmz_dev->flags & DMZ_CHECK_BDEV) + return !dmz_check_bdev(dmz_dev); + + if (blk_queue_dying(bdev_get_queue(dmz_dev->bdev))) { + dmz_dev_warn(dmz_dev, "Backing device queue dying"); + dmz_dev->flags |= DMZ_BDEV_DYING; } return dmz_dev->flags & DMZ_BDEV_DYING; } +/* + * Check the backing device availability. This detects such events as + * backing device going offline due to errors, media removals, etc. + * This check is less efficient than dmz_bdev_is_dying() and should + * only be performed as a part of error handling. + */ +bool dmz_check_bdev(struct dmz_dev *dmz_dev) +{ + struct gendisk *disk; + + dmz_dev->flags &= ~DMZ_CHECK_BDEV; + + if (dmz_bdev_is_dying(dmz_dev)) + return false; + + disk = dmz_dev->bdev->bd_disk; + if (disk->fops->check_events && + disk->fops->check_events(disk, 0) & DISK_EVENT_MEDIA_CHANGE) { + dmz_dev_warn(dmz_dev, "Backing device offline"); + dmz_dev->flags |= DMZ_BDEV_DYING; + } + + return !(dmz_dev->flags & DMZ_BDEV_DYING); +} + /* * Process a new BIO. */ @@ -902,8 +924,8 @@ static int dmz_prepare_ioctl(struct dm_target *ti, struct block_device **bdev) { struct dmz_target *dmz = ti->private; - if (dmz_bdev_is_dying(dmz->dev)) - return -ENODEV; + if (!dmz_check_bdev(dmz->dev)) + return -EIO; *bdev = dmz->dev->bdev; diff --git a/drivers/md/dm-zoned.h b/drivers/md/dm-zoned.h index d8e70b0ade35..5b5e493d479c 100644 --- a/drivers/md/dm-zoned.h +++ b/drivers/md/dm-zoned.h @@ -72,6 +72,7 @@ struct dmz_dev { /* Device flags. */ #define DMZ_BDEV_DYING (1 << 0) +#define DMZ_CHECK_BDEV (2 << 0) /* * Zone descriptor. @@ -255,5 +256,6 @@ void dmz_schedule_reclaim(struct dmz_reclaim *zrc); * Functions defined in dm-zoned-target.c */ bool dmz_bdev_is_dying(struct dmz_dev *dmz_dev); +bool dmz_check_bdev(struct dmz_dev *dmz_dev); #endif /* DM_ZONED_H */ diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index b092c7b5282f..3ad18246fcb3 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -2139,6 +2139,7 @@ int md_bitmap_resize(struct bitmap *bitmap, sector_t blocks, memcpy(page_address(store.sb_page), page_address(bitmap->storage.sb_page), sizeof(bitmap_super_t)); + spin_lock_irq(&bitmap->counts.lock); md_bitmap_file_unmap(&bitmap->storage); bitmap->storage = store; @@ -2154,7 +2155,6 @@ int md_bitmap_resize(struct bitmap *bitmap, sector_t blocks, blocks = min(old_counts.chunks << old_counts.chunkshift, chunks << chunkshift); - spin_lock_irq(&bitmap->counts.lock); /* For cluster raid, need to pre-allocate bitmap */ if (mddev_is_clustered(bitmap->mddev)) { unsigned long page; diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c index c766c559d36d..26c75c0199fa 100644 --- a/drivers/md/md-linear.c +++ b/drivers/md/md-linear.c @@ -244,10 +244,9 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio) sector_t start_sector, end_sector, data_offset; sector_t bio_sector = bio->bi_iter.bi_sector; - if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { - md_flush_request(mddev, bio); + if (unlikely(bio->bi_opf & REQ_PREFLUSH) + && md_flush_request(mddev, bio)) return true; - } tmp_dev = which_dev(mddev, bio_sector); start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors; diff --git a/drivers/md/md-multipath.c b/drivers/md/md-multipath.c index 6780938d2991..152f9e65a226 100644 --- a/drivers/md/md-multipath.c +++ b/drivers/md/md-multipath.c @@ -104,10 +104,9 @@ static bool multipath_make_request(struct mddev *mddev, struct bio * bio) struct multipath_bh * mp_bh; struct multipath_info *multipath; - if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { - md_flush_request(mddev, bio); + if (unlikely(bio->bi_opf & REQ_PREFLUSH) + && md_flush_request(mddev, bio)) return true; - } mp_bh = mempool_alloc(&conf->pool, GFP_NOIO); diff --git a/drivers/md/md.c b/drivers/md/md.c index 1be7abeb24fd..4e7c9f398bc6 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -550,7 +550,13 @@ static void md_submit_flush_data(struct work_struct *ws) } } -void md_flush_request(struct mddev *mddev, struct bio *bio) +/* + * Manages consolidation of flushes and submitting any flushes needed for + * a bio with REQ_PREFLUSH. Returns true if the bio is finished or is + * being finished in another context. Returns false if the flushing is + * complete but still needs the I/O portion of the bio to be processed. + */ +bool md_flush_request(struct mddev *mddev, struct bio *bio) { ktime_t start = ktime_get_boottime(); spin_lock_irq(&mddev->lock); @@ -575,9 +581,10 @@ void md_flush_request(struct mddev *mddev, struct bio *bio) bio_endio(bio); else { bio->bi_opf &= ~REQ_PREFLUSH; - mddev->pers->make_request(mddev, bio); + return false; } } + return true; } EXPORT_SYMBOL(md_flush_request); @@ -1098,6 +1105,7 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE]; mdp_super_t *sb; int ret; + bool spare_disk = true; /* * Calculate the position of the superblock (512byte sectors), @@ -1148,8 +1156,19 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor else rdev->desc_nr = sb->this_disk.number; + /* not spare disk, or LEVEL_MULTIPATH */ + if (sb->level == LEVEL_MULTIPATH || + (rdev->desc_nr >= 0 && + rdev->desc_nr < MD_SB_DISKS && + sb->disks[rdev->desc_nr].state & + ((1<sb_page); @@ -1165,7 +1184,8 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor } ev1 = md_event(sb); ev2 = md_event(refsb); - if (ev1 > ev2) + + if (!spare_disk && ev1 > ev2) ret = 1; else ret = 0; @@ -1525,6 +1545,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_ sector_t sectors; char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE]; int bmask; + bool spare_disk = true; /* * Calculate the position of the superblock in 512byte sectors. @@ -1658,8 +1679,19 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_ sb->level != 0) return -EINVAL; + /* not spare disk, or LEVEL_MULTIPATH */ + if (sb->level == cpu_to_le32(LEVEL_MULTIPATH) || + (rdev->desc_nr >= 0 && + rdev->desc_nr < le32_to_cpu(sb->max_dev) && + (le16_to_cpu(sb->dev_roles[rdev->desc_nr]) < MD_DISK_ROLE_MAX || + le16_to_cpu(sb->dev_roles[rdev->desc_nr]) == MD_DISK_ROLE_JOURNAL))) + spare_disk = false; + if (!refdev) { - ret = 1; + if (!spare_disk) + ret = 1; + else + ret = 0; } else { __u64 ev1, ev2; struct mdp_superblock_1 *refsb = page_address(refdev->sb_page); @@ -1676,7 +1708,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_ ev1 = le64_to_cpu(sb->events); ev2 = le64_to_cpu(refsb->events); - if (ev1 > ev2) + if (!spare_disk && ev1 > ev2) ret = 1; else ret = 0; @@ -3597,7 +3629,7 @@ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int supe * Check a full RAID array for plausibility */ -static void analyze_sbs(struct mddev *mddev) +static int analyze_sbs(struct mddev *mddev) { int i; struct md_rdev *rdev, *freshest, *tmp; @@ -3618,6 +3650,12 @@ static void analyze_sbs(struct mddev *mddev) md_kick_rdev_from_array(rdev); } + /* Cannot find a valid fresh disk */ + if (!freshest) { + pr_warn("md: cannot find a valid disk\n"); + return -EINVAL; + } + super_types[mddev->major_version]. validate_super(mddev, freshest); @@ -3652,6 +3690,8 @@ static void analyze_sbs(struct mddev *mddev) clear_bit(In_sync, &rdev->flags); } } + + return 0; } /* Read a fixed-point number. @@ -5570,7 +5610,9 @@ int md_run(struct mddev *mddev) if (!mddev->raid_disks) { if (!mddev->persistent) return -EINVAL; - analyze_sbs(mddev); + err = analyze_sbs(mddev); + if (err) + return -EINVAL; } if (mddev->level != LEVEL_NONE) diff --git a/drivers/md/md.h b/drivers/md/md.h index c5e3ff398b59..5f86f8adb0a4 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -550,7 +550,7 @@ struct md_personality int level; struct list_head list; struct module *owner; - bool (*make_request)(struct mddev *mddev, struct bio *bio); + bool __must_check (*make_request)(struct mddev *mddev, struct bio *bio); /* * start up works that do NOT require md_thread. tasks that * requires md_thread should go into start() @@ -703,7 +703,7 @@ extern void md_error(struct mddev *mddev, struct md_rdev *rdev); extern void md_finish_reshape(struct mddev *mddev); extern int mddev_congested(struct mddev *mddev, int bits); -extern void md_flush_request(struct mddev *mddev, struct bio *bio); +extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio); extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev, sector_t sector, int size, struct page *page); extern int md_super_wait(struct mddev *mddev); diff --git a/drivers/md/persistent-data/dm-btree-remove.c b/drivers/md/persistent-data/dm-btree-remove.c index 21ea537bd55e..eff04fa23dfa 100644 --- a/drivers/md/persistent-data/dm-btree-remove.c +++ b/drivers/md/persistent-data/dm-btree-remove.c @@ -203,7 +203,13 @@ static void __rebalance2(struct dm_btree_info *info, struct btree_node *parent, struct btree_node *right = r->n; uint32_t nr_left = le32_to_cpu(left->header.nr_entries); uint32_t nr_right = le32_to_cpu(right->header.nr_entries); - unsigned threshold = 2 * merge_threshold(left) + 1; + /* + * Ensure the number of entries in each child will be greater + * than or equal to (max_entries / 3 + 1), so no matter which + * child is used for removal, the number will still be not + * less than (max_entries / 3). + */ + unsigned int threshold = 2 * (merge_threshold(left) + 1); if (nr_left + nr_right < threshold) { /* diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 1e772287b1c8..b7c20979bd19 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -575,10 +575,9 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio) unsigned chunk_sects; unsigned sectors; - if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { - md_flush_request(mddev, bio); + if (unlikely(bio->bi_opf & REQ_PREFLUSH) + && md_flush_request(mddev, bio)) return true; - } if (unlikely((bio_op(bio) == REQ_OP_DISCARD))) { raid0_handle_discard(mddev, bio); @@ -615,7 +614,7 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio) tmp_dev = map_sector(mddev, zone, sector, §or); break; default: - WARN("md/raid0:%s: Invalid layout\n", mdname(mddev)); + WARN(1, "md/raid0:%s: Invalid layout\n", mdname(mddev)); bio_io_error(bio); return true; } diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 0466ee2453b4..c7137f50bd1d 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1567,10 +1567,9 @@ static bool raid1_make_request(struct mddev *mddev, struct bio *bio) { sector_t sectors; - if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { - md_flush_request(mddev, bio); + if (unlikely(bio->bi_opf & REQ_PREFLUSH) + && md_flush_request(mddev, bio)) return true; - } /* * There is a limit to the maximum size, but @@ -2782,7 +2781,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr, write_targets++; } } - if (bio->bi_end_io) { + if (rdev && bio->bi_end_io) { atomic_inc(&rdev->nr_pending); bio->bi_iter.bi_sector = sector_nr + rdev->data_offset; bio_set_dev(bio, rdev->bdev); diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 299c7b1c9718..ec136e44aef7 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -191,7 +191,7 @@ static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data) out_free_pages: while (--j >= 0) - resync_free_pages(&rps[j * 2]); + resync_free_pages(&rps[j]); j = 0; out_free_bio: @@ -1525,10 +1525,9 @@ static bool raid10_make_request(struct mddev *mddev, struct bio *bio) int chunk_sects = chunk_mask + 1; int sectors = bio_sectors(bio); - if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { - md_flush_request(mddev, bio); + if (unlikely(bio->bi_opf & REQ_PREFLUSH) + && md_flush_request(mddev, bio)) return true; - } if (!md_write_start(mddev, bio)) return false; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 223e97ab27e6..36cd7c2fbf40 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -5592,8 +5592,8 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi) if (ret == 0) return true; if (ret == -ENODEV) { - md_flush_request(mddev, bi); - return true; + if (md_flush_request(mddev, bi)) + return true; } /* ret == -EAGAIN, fallback */ /* @@ -5726,7 +5726,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi) do_flush = false; } - if (!sh->batch_head) + if (!sh->batch_head || sh == sh->batch_head) set_bit(STRIPE_HANDLE, &sh->state); clear_bit(STRIPE_DELAYED, &sh->state); if ((!sh->batch_head || sh == sh->batch_head) && diff --git a/drivers/media/cec/cec-adap.c b/drivers/media/cec/cec-adap.c index 5ef7daeb8cbd..b14c09cd9593 100644 --- a/drivers/media/cec/cec-adap.c +++ b/drivers/media/cec/cec-adap.c @@ -378,7 +378,8 @@ static void cec_data_cancel(struct cec_data *data, u8 tx_status) } else { list_del_init(&data->list); if (!(data->msg.tx_status & CEC_TX_STATUS_OK)) - data->adap->transmit_queue_sz--; + if (!WARN_ON(!data->adap->transmit_queue_sz)) + data->adap->transmit_queue_sz--; } if (data->msg.tx_status & CEC_TX_STATUS_OK) { @@ -430,6 +431,14 @@ static void cec_flush(struct cec_adapter *adap) * need to do anything special in that case. */ } + /* + * If something went wrong and this counter isn't what it should + * be, then this will reset it back to 0. Warn if it is not 0, + * since it indicates a bug, either in this framework or in a + * CEC driver. + */ + if (WARN_ON(adap->transmit_queue_sz)) + adap->transmit_queue_sz = 0; } /* @@ -454,7 +463,7 @@ int cec_thread_func(void *_adap) bool timeout = false; u8 attempts; - if (adap->transmitting) { + if (adap->transmit_in_progress) { int err; /* @@ -489,7 +498,7 @@ int cec_thread_func(void *_adap) goto unlock; } - if (adap->transmitting && timeout) { + if (adap->transmit_in_progress && timeout) { /* * If we timeout, then log that. Normally this does * not happen and it is an indication of a faulty CEC @@ -498,14 +507,18 @@ int cec_thread_func(void *_adap) * so much traffic on the bus that the adapter was * unable to transmit for CEC_XFER_TIMEOUT_MS (2.1s). */ - pr_warn("cec-%s: message %*ph timed out\n", adap->name, - adap->transmitting->msg.len, - adap->transmitting->msg.msg); + if (adap->transmitting) { + pr_warn("cec-%s: message %*ph timed out\n", adap->name, + adap->transmitting->msg.len, + adap->transmitting->msg.msg); + /* Just give up on this. */ + cec_data_cancel(adap->transmitting, + CEC_TX_STATUS_TIMEOUT); + } else { + pr_warn("cec-%s: transmit timed out\n", adap->name); + } adap->transmit_in_progress = false; adap->tx_timeouts++; - /* Just give up on this. */ - cec_data_cancel(adap->transmitting, - CEC_TX_STATUS_TIMEOUT); goto unlock; } @@ -520,7 +533,8 @@ int cec_thread_func(void *_adap) data = list_first_entry(&adap->transmit_queue, struct cec_data, list); list_del_init(&data->list); - adap->transmit_queue_sz--; + if (!WARN_ON(!data->adap->transmit_queue_sz)) + adap->transmit_queue_sz--; /* Make this the current transmitting message */ adap->transmitting = data; @@ -1083,11 +1097,11 @@ void cec_received_msg_ts(struct cec_adapter *adap, valid_la = false; else if (!cec_msg_is_broadcast(msg) && !(dir_fl & DIRECTED)) valid_la = false; - else if (cec_msg_is_broadcast(msg) && !(dir_fl & BCAST1_4)) + else if (cec_msg_is_broadcast(msg) && !(dir_fl & BCAST)) valid_la = false; else if (cec_msg_is_broadcast(msg) && - adap->log_addrs.cec_version >= CEC_OP_CEC_VERSION_2_0 && - !(dir_fl & BCAST2_0)) + adap->log_addrs.cec_version < CEC_OP_CEC_VERSION_2_0 && + !(dir_fl & BCAST1_4)) valid_la = false; } if (valid_la && min_len) { diff --git a/drivers/media/i2c/Kconfig b/drivers/media/i2c/Kconfig index 7eee1812bba3..fcffcc31d168 100644 --- a/drivers/media/i2c/Kconfig +++ b/drivers/media/i2c/Kconfig @@ -1113,6 +1113,7 @@ comment "SDR tuner chips" config SDR_MAX2175 tristate "Maxim 2175 RF to Bits tuner" depends on VIDEO_V4L2 && MEDIA_SDR_SUPPORT && I2C + select REGMAP_I2C help Support for Maxim 2175 tuner. It is an advanced analog/digital radio receiver with RF-to-Bits front-end designed for SDR solutions. diff --git a/drivers/media/i2c/ad5820.c b/drivers/media/i2c/ad5820.c index 925c171e7797..7a49651f4d1f 100644 --- a/drivers/media/i2c/ad5820.c +++ b/drivers/media/i2c/ad5820.c @@ -309,6 +309,7 @@ static int ad5820_probe(struct i2c_client *client, v4l2_i2c_subdev_init(&coil->subdev, client, &ad5820_ops); coil->subdev.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE; coil->subdev.internal_ops = &ad5820_internal_ops; + coil->subdev.entity.function = MEDIA_ENT_F_LENS; strscpy(coil->subdev.name, "ad5820 focus", sizeof(coil->subdev.name)); ret = media_entity_pads_init(&coil->subdev.entity, 0, NULL); diff --git a/drivers/media/i2c/ov2659.c b/drivers/media/i2c/ov2659.c index f4ded0669ff9..e1ff38009cf0 100644 --- a/drivers/media/i2c/ov2659.c +++ b/drivers/media/i2c/ov2659.c @@ -419,10 +419,14 @@ static struct sensor_register ov2659_720p[] = { { REG_TIMING_YINC, 0x11 }, { REG_TIMING_VERT_FORMAT, 0x80 }, { REG_TIMING_HORIZ_FORMAT, 0x00 }, + { 0x370a, 0x12 }, { 0x3a03, 0xe8 }, { 0x3a09, 0x6f }, { 0x3a0b, 0x5d }, { 0x3a15, 0x9a }, + { REG_VFIFO_READ_START_H, 0x00 }, + { REG_VFIFO_READ_START_L, 0x80 }, + { REG_ISP_CTRL02, 0x00 }, { REG_NULL, 0x00 }, }; @@ -1201,11 +1205,15 @@ static int ov2659_s_stream(struct v4l2_subdev *sd, int on) goto unlock; } - ov2659_set_pixel_clock(ov2659); - ov2659_set_frame_size(ov2659); - ov2659_set_format(ov2659); - ov2659_set_streaming(ov2659, 1); - ov2659->streaming = on; + ret = ov2659_set_pixel_clock(ov2659); + if (!ret) + ret = ov2659_set_frame_size(ov2659); + if (!ret) + ret = ov2659_set_format(ov2659); + if (!ret) { + ov2659_set_streaming(ov2659, 1); + ov2659->streaming = on; + } unlock: mutex_unlock(&ov2659->lock); diff --git a/drivers/media/i2c/ov5640.c b/drivers/media/i2c/ov5640.c index 500d9bbff10b..18dd2d717088 100644 --- a/drivers/media/i2c/ov5640.c +++ b/drivers/media/i2c/ov5640.c @@ -1611,6 +1611,11 @@ ov5640_find_mode(struct ov5640_dev *sensor, enum ov5640_frame_rate fr, !(mode->hact == 640 && mode->vact == 480)) return NULL; + /* 2592x1944 only works at 15fps max */ + if ((mode->hact == 2592 && mode->vact == 1944) && + fr > OV5640_15_FPS) + return NULL; + return mode; } diff --git a/drivers/media/i2c/ov6650.c b/drivers/media/i2c/ov6650.c index 5b9af5e5b7f1..af482620f94a 100644 --- a/drivers/media/i2c/ov6650.c +++ b/drivers/media/i2c/ov6650.c @@ -130,6 +130,7 @@ #define CLKRC_24MHz 0xc0 #define CLKRC_DIV_MASK 0x3f #define GET_CLKRC_DIV(x) (((x) & CLKRC_DIV_MASK) + 1) +#define DEF_CLKRC 0x00 #define COMA_RESET BIT(7) #define COMA_QCIF BIT(5) @@ -200,7 +201,6 @@ struct ov6650 { unsigned long pclk_max; /* from resolution and format */ struct v4l2_fract tpf; /* as requested with s_frame_interval */ u32 code; - enum v4l2_colorspace colorspace; }; @@ -213,6 +213,17 @@ static u32 ov6650_codes[] = { MEDIA_BUS_FMT_Y8_1X8, }; +static const struct v4l2_mbus_framefmt ov6650_def_fmt = { + .width = W_CIF, + .height = H_CIF, + .code = MEDIA_BUS_FMT_SBGGR8_1X8, + .colorspace = V4L2_COLORSPACE_SRGB, + .field = V4L2_FIELD_NONE, + .ycbcr_enc = V4L2_YCBCR_ENC_DEFAULT, + .quantization = V4L2_QUANTIZATION_DEFAULT, + .xfer_func = V4L2_XFER_FUNC_DEFAULT, +}; + /* read a register */ static int ov6650_reg_read(struct i2c_client *client, u8 reg, u8 *val) { @@ -465,38 +476,39 @@ static int ov6650_set_selection(struct v4l2_subdev *sd, { struct i2c_client *client = v4l2_get_subdevdata(sd); struct ov6650 *priv = to_ov6650(client); - struct v4l2_rect rect = sel->r; int ret; if (sel->which != V4L2_SUBDEV_FORMAT_ACTIVE || sel->target != V4L2_SEL_TGT_CROP) return -EINVAL; - v4l_bound_align_image(&rect.width, 2, W_CIF, 1, - &rect.height, 2, H_CIF, 1, 0); - v4l_bound_align_image(&rect.left, DEF_HSTRT << 1, - (DEF_HSTRT << 1) + W_CIF - (__s32)rect.width, 1, - &rect.top, DEF_VSTRT << 1, - (DEF_VSTRT << 1) + H_CIF - (__s32)rect.height, 1, - 0); + v4l_bound_align_image(&sel->r.width, 2, W_CIF, 1, + &sel->r.height, 2, H_CIF, 1, 0); + v4l_bound_align_image(&sel->r.left, DEF_HSTRT << 1, + (DEF_HSTRT << 1) + W_CIF - (__s32)sel->r.width, 1, + &sel->r.top, DEF_VSTRT << 1, + (DEF_VSTRT << 1) + H_CIF - (__s32)sel->r.height, + 1, 0); - ret = ov6650_reg_write(client, REG_HSTRT, rect.left >> 1); + ret = ov6650_reg_write(client, REG_HSTRT, sel->r.left >> 1); if (!ret) { - priv->rect.left = rect.left; + priv->rect.width += priv->rect.left - sel->r.left; + priv->rect.left = sel->r.left; ret = ov6650_reg_write(client, REG_HSTOP, - (rect.left + rect.width) >> 1); + (sel->r.left + sel->r.width) >> 1); } if (!ret) { - priv->rect.width = rect.width; - ret = ov6650_reg_write(client, REG_VSTRT, rect.top >> 1); + priv->rect.width = sel->r.width; + ret = ov6650_reg_write(client, REG_VSTRT, sel->r.top >> 1); } if (!ret) { - priv->rect.top = rect.top; + priv->rect.height += priv->rect.top - sel->r.top; + priv->rect.top = sel->r.top; ret = ov6650_reg_write(client, REG_VSTOP, - (rect.top + rect.height) >> 1); + (sel->r.top + sel->r.height) >> 1); } if (!ret) - priv->rect.height = rect.height; + priv->rect.height = sel->r.height; return ret; } @@ -512,12 +524,20 @@ static int ov6650_get_fmt(struct v4l2_subdev *sd, if (format->pad) return -EINVAL; - mf->width = priv->rect.width >> priv->half_scale; - mf->height = priv->rect.height >> priv->half_scale; - mf->code = priv->code; - mf->colorspace = priv->colorspace; - mf->field = V4L2_FIELD_NONE; + /* initialize response with default media bus frame format */ + *mf = ov6650_def_fmt; + + /* update media bus format code and frame size */ + if (format->which == V4L2_SUBDEV_FORMAT_TRY) { + mf->width = cfg->try_fmt.width; + mf->height = cfg->try_fmt.height; + mf->code = cfg->try_fmt.code; + } else { + mf->width = priv->rect.width >> priv->half_scale; + mf->height = priv->rect.height >> priv->half_scale; + mf->code = priv->code; + } return 0; } @@ -610,7 +630,6 @@ static int ov6650_s_fmt(struct v4l2_subdev *sd, struct v4l2_mbus_framefmt *mf) dev_err(&client->dev, "Pixel format not handled: 0x%x\n", code); return -EINVAL; } - priv->code = code; if (code == MEDIA_BUS_FMT_Y8_1X8 || code == MEDIA_BUS_FMT_SBGGR8_1X8) { @@ -623,11 +642,6 @@ static int ov6650_s_fmt(struct v4l2_subdev *sd, struct v4l2_mbus_framefmt *mf) priv->pclk_max = 8000000; } - if (code == MEDIA_BUS_FMT_SBGGR8_1X8) - priv->colorspace = V4L2_COLORSPACE_SRGB; - else if (code != 0) - priv->colorspace = V4L2_COLORSPACE_JPEG; - if (half_scale) { dev_dbg(&client->dev, "max resolution: QCIF\n"); coma_set |= COMA_QCIF; @@ -636,7 +650,6 @@ static int ov6650_s_fmt(struct v4l2_subdev *sd, struct v4l2_mbus_framefmt *mf) dev_dbg(&client->dev, "max resolution: CIF\n"); coma_mask |= COMA_QCIF; } - priv->half_scale = half_scale; clkrc = CLKRC_12MHz; mclk = 12000000; @@ -654,14 +667,14 @@ static int ov6650_s_fmt(struct v4l2_subdev *sd, struct v4l2_mbus_framefmt *mf) ret = ov6650_reg_rmw(client, REG_COMA, coma_set, coma_mask); if (!ret) ret = ov6650_reg_write(client, REG_CLKRC, clkrc); - if (!ret) - ret = ov6650_reg_rmw(client, REG_COML, coml_set, coml_mask); - if (!ret) { - mf->colorspace = priv->colorspace; - mf->width = priv->rect.width >> half_scale; - mf->height = priv->rect.height >> half_scale; + priv->half_scale = half_scale; + + ret = ov6650_reg_rmw(client, REG_COML, coml_set, coml_mask); } + if (!ret) + priv->code = code; + return ret; } @@ -680,8 +693,6 @@ static int ov6650_set_fmt(struct v4l2_subdev *sd, v4l_bound_align_image(&mf->width, 2, W_CIF, 1, &mf->height, 2, H_CIF, 1, 0); - mf->field = V4L2_FIELD_NONE; - switch (mf->code) { case MEDIA_BUS_FMT_Y10_1X10: mf->code = MEDIA_BUS_FMT_Y8_1X8; @@ -691,20 +702,39 @@ static int ov6650_set_fmt(struct v4l2_subdev *sd, case MEDIA_BUS_FMT_YUYV8_2X8: case MEDIA_BUS_FMT_VYUY8_2X8: case MEDIA_BUS_FMT_UYVY8_2X8: - mf->colorspace = V4L2_COLORSPACE_JPEG; break; default: mf->code = MEDIA_BUS_FMT_SBGGR8_1X8; /* fall through */ case MEDIA_BUS_FMT_SBGGR8_1X8: - mf->colorspace = V4L2_COLORSPACE_SRGB; break; } - if (format->which == V4L2_SUBDEV_FORMAT_ACTIVE) - return ov6650_s_fmt(sd, mf); - cfg->try_fmt = *mf; + if (format->which == V4L2_SUBDEV_FORMAT_TRY) { + /* store media bus format code and frame size in pad config */ + cfg->try_fmt.width = mf->width; + cfg->try_fmt.height = mf->height; + cfg->try_fmt.code = mf->code; + + /* return default mbus frame format updated with pad config */ + *mf = ov6650_def_fmt; + mf->width = cfg->try_fmt.width; + mf->height = cfg->try_fmt.height; + mf->code = cfg->try_fmt.code; + + } else { + /* apply new media bus format code and frame size */ + int ret = ov6650_s_fmt(sd, mf); + if (ret) + return ret; + + /* return default format updated with active size and code */ + *mf = ov6650_def_fmt; + mf->width = priv->rect.width >> priv->half_scale; + mf->height = priv->rect.height >> priv->half_scale; + mf->code = priv->code; + } return 0; } @@ -754,19 +784,17 @@ static int ov6650_s_frame_interval(struct v4l2_subdev *sd, else if (div > GET_CLKRC_DIV(CLKRC_DIV_MASK)) div = GET_CLKRC_DIV(CLKRC_DIV_MASK); - /* - * Keep result to be used as tpf limit - * for subsequent clock divider calculations - */ - priv->tpf.numerator = div; - priv->tpf.denominator = FRAME_RATE_MAX; + tpf->numerator = div; + tpf->denominator = FRAME_RATE_MAX; - clkrc = to_clkrc(&priv->tpf, priv->pclk_limit, priv->pclk_max); + clkrc = to_clkrc(tpf, priv->pclk_limit, priv->pclk_max); ret = ov6650_reg_rmw(client, REG_CLKRC, clkrc, CLKRC_DIV_MASK); if (!ret) { - tpf->numerator = GET_CLKRC_DIV(clkrc); - tpf->denominator = FRAME_RATE_MAX; + priv->tpf.numerator = GET_CLKRC_DIV(clkrc); + priv->tpf.denominator = FRAME_RATE_MAX; + + *tpf = priv->tpf; } return ret; @@ -849,6 +877,11 @@ static int ov6650_video_probe(struct v4l2_subdev *sd) ret = ov6650_reset(client); if (!ret) ret = ov6650_prog_dflt(client); + if (!ret) { + struct v4l2_mbus_framefmt mf = ov6650_def_fmt; + + ret = ov6650_s_fmt(sd, &mf); + } if (!ret) ret = v4l2_ctrl_handler_setup(&priv->hdl); @@ -989,8 +1022,10 @@ static int ov6650_probe(struct i2c_client *client, V4L2_CID_GAMMA, 0, 0xff, 1, 0x12); priv->subdev.ctrl_handler = &priv->hdl; - if (priv->hdl.error) - return priv->hdl.error; + if (priv->hdl.error) { + ret = priv->hdl.error; + goto ectlhdlfree; + } v4l2_ctrl_auto_cluster(2, &priv->autogain, 0, true); v4l2_ctrl_auto_cluster(3, &priv->autowb, 0, true); @@ -1001,15 +1036,18 @@ static int ov6650_probe(struct i2c_client *client, priv->rect.top = DEF_VSTRT << 1; priv->rect.width = W_CIF; priv->rect.height = H_CIF; - priv->half_scale = false; - priv->code = MEDIA_BUS_FMT_YUYV8_2X8; - priv->colorspace = V4L2_COLORSPACE_JPEG; + + /* Hardware default frame interval */ + priv->tpf.numerator = GET_CLKRC_DIV(DEF_CLKRC); + priv->tpf.denominator = FRAME_RATE_MAX; priv->subdev.internal_ops = &ov6650_internal_ops; ret = v4l2_async_register_subdev(&priv->subdev); - if (ret) - v4l2_ctrl_handler_free(&priv->hdl); + if (!ret) + return 0; +ectlhdlfree: + v4l2_ctrl_handler_free(&priv->hdl); return ret; } diff --git a/drivers/media/i2c/smiapp/smiapp-core.c b/drivers/media/i2c/smiapp/smiapp-core.c index 9adf8e034e7d..42805dfbffeb 100644 --- a/drivers/media/i2c/smiapp/smiapp-core.c +++ b/drivers/media/i2c/smiapp/smiapp-core.c @@ -3101,19 +3101,23 @@ static int smiapp_probe(struct i2c_client *client) if (rval < 0) goto out_media_entity_cleanup; - rval = v4l2_async_register_subdev_sensor_common(&sensor->src->sd); - if (rval < 0) - goto out_media_entity_cleanup; - pm_runtime_set_active(&client->dev); pm_runtime_get_noresume(&client->dev); pm_runtime_enable(&client->dev); + + rval = v4l2_async_register_subdev_sensor_common(&sensor->src->sd); + if (rval < 0) + goto out_disable_runtime_pm; + pm_runtime_set_autosuspend_delay(&client->dev, 1000); pm_runtime_use_autosuspend(&client->dev); pm_runtime_put_autosuspend(&client->dev); return 0; +out_disable_runtime_pm: + pm_runtime_disable(&client->dev); + out_media_entity_cleanup: media_entity_cleanup(&sensor->src->sd.entity); diff --git a/drivers/media/i2c/st-mipid02.c b/drivers/media/i2c/st-mipid02.c index 81285b8d5cfb..003ba22334cd 100644 --- a/drivers/media/i2c/st-mipid02.c +++ b/drivers/media/i2c/st-mipid02.c @@ -971,6 +971,11 @@ static int mipid02_probe(struct i2c_client *client) bridge->reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH); + if (IS_ERR(bridge->reset_gpio)) { + dev_err(dev, "failed to get reset GPIO\n"); + return PTR_ERR(bridge->reset_gpio); + } + ret = mipid02_get_regulators(bridge); if (ret) { dev_err(dev, "failed to get regulators %d", ret); diff --git a/drivers/media/pci/cx88/cx88-video.c b/drivers/media/pci/cx88/cx88-video.c index dcc0f02aeb70..b8abcd550604 100644 --- a/drivers/media/pci/cx88/cx88-video.c +++ b/drivers/media/pci/cx88/cx88-video.c @@ -1277,7 +1277,7 @@ static int cx8800_initdev(struct pci_dev *pci_dev, core = cx88_core_get(dev->pci); if (!core) { err = -EINVAL; - goto fail_free; + goto fail_disable; } dev->core = core; @@ -1323,7 +1323,7 @@ static int cx8800_initdev(struct pci_dev *pci_dev, cc->step, cc->default_value); if (!vc) { err = core->audio_hdl.error; - goto fail_core; + goto fail_irq; } vc->priv = (void *)cc; } @@ -1337,7 +1337,7 @@ static int cx8800_initdev(struct pci_dev *pci_dev, cc->step, cc->default_value); if (!vc) { err = core->video_hdl.error; - goto fail_core; + goto fail_irq; } vc->priv = (void *)cc; if (vc->id == V4L2_CID_CHROMA_AGC) @@ -1509,11 +1509,14 @@ static int cx8800_initdev(struct pci_dev *pci_dev, fail_unreg: cx8800_unregister_video(dev); - free_irq(pci_dev->irq, dev); mutex_unlock(&core->lock); +fail_irq: + free_irq(pci_dev->irq, dev); fail_core: core->v4ldev = NULL; cx88_core_put(core, dev->pci); +fail_disable: + pci_disable_device(pci_dev); fail_free: kfree(dev); return err; diff --git a/drivers/media/platform/am437x/am437x-vpfe.c b/drivers/media/platform/am437x/am437x-vpfe.c index 2b42ba1f5949..e13dbf27a9c2 100644 --- a/drivers/media/platform/am437x/am437x-vpfe.c +++ b/drivers/media/platform/am437x/am437x-vpfe.c @@ -1830,6 +1830,10 @@ static int vpfe_s_std(struct file *file, void *priv, v4l2_std_id std_id) if (!(sdinfo->inputs[0].capabilities & V4L2_IN_CAP_STD)) return -ENODATA; + /* if trying to set the same std then nothing to do */ + if (vpfe_standards[vpfe->std_index].std_id == std_id) + return 0; + /* If streaming is started, return error */ if (vb2_is_busy(&vpfe->buffer_queue)) { vpfe_err(vpfe, "%s device busy\n", __func__); diff --git a/drivers/media/platform/aspeed-video.c b/drivers/media/platform/aspeed-video.c index eb12f3793062..4eaaf39b9223 100644 --- a/drivers/media/platform/aspeed-video.c +++ b/drivers/media/platform/aspeed-video.c @@ -606,6 +606,16 @@ static irqreturn_t aspeed_video_irq(int irq, void *arg) aspeed_video_start_frame(video); } + /* + * CAPTURE_COMPLETE and FRAME_COMPLETE interrupts come even when these + * are disabled in the VE_INTERRUPT_CTRL register so clear them to + * prevent unnecessary interrupt calls. + */ + if (sts & VE_INTERRUPT_CAPTURE_COMPLETE) + sts &= ~VE_INTERRUPT_CAPTURE_COMPLETE; + if (sts & VE_INTERRUPT_FRAME_COMPLETE) + sts &= ~VE_INTERRUPT_FRAME_COMPLETE; + return sts ? IRQ_NONE : IRQ_HANDLED; } @@ -741,6 +751,8 @@ static void aspeed_video_get_resolution(struct aspeed_video *video) } set_bit(VIDEO_RES_DETECT, &video->flags); + aspeed_video_update(video, VE_CTRL, + VE_CTRL_VSYNC_POL | VE_CTRL_HSYNC_POL, 0); aspeed_video_enable_mode_detect(video); rc = wait_event_interruptible_timeout(video->wait, @@ -1646,7 +1658,8 @@ static int aspeed_video_probe(struct platform_device *pdev) { int rc; struct resource *res; - struct aspeed_video *video = kzalloc(sizeof(*video), GFP_KERNEL); + struct aspeed_video *video = + devm_kzalloc(&pdev->dev, sizeof(*video), GFP_KERNEL); if (!video) return -ENOMEM; diff --git a/drivers/media/platform/cadence/cdns-csi2rx.c b/drivers/media/platform/cadence/cdns-csi2rx.c index 31ace114eda1..be9ec59774d6 100644 --- a/drivers/media/platform/cadence/cdns-csi2rx.c +++ b/drivers/media/platform/cadence/cdns-csi2rx.c @@ -129,7 +129,7 @@ static int csi2rx_start(struct csi2rx_priv *csi2rx) */ for (i = csi2rx->num_lanes; i < csi2rx->max_lanes; i++) { unsigned int idx = find_first_zero_bit(&lanes_used, - sizeof(lanes_used)); + csi2rx->max_lanes); set_bit(idx, &lanes_used); reg |= CSI2RX_STATIC_CFG_DLANE_MAP(i, i + 1); } diff --git a/drivers/media/platform/coda/coda-common.c b/drivers/media/platform/coda/coda-common.c index 73222c0615c0..834f11fe9dc2 100644 --- a/drivers/media/platform/coda/coda-common.c +++ b/drivers/media/platform/coda/coda-common.c @@ -1084,16 +1084,16 @@ static int coda_decoder_cmd(struct file *file, void *fh, switch (dc->cmd) { case V4L2_DEC_CMD_START: - mutex_lock(&ctx->bitstream_mutex); mutex_lock(&dev->coda_mutex); + mutex_lock(&ctx->bitstream_mutex); coda_bitstream_flush(ctx); - mutex_unlock(&dev->coda_mutex); dst_vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE); vb2_clear_last_buffer_dequeued(dst_vq); ctx->bit_stream_param &= ~CODA_BIT_STREAM_END_FLAG; coda_fill_bitstream(ctx, NULL); mutex_unlock(&ctx->bitstream_mutex); + mutex_unlock(&dev->coda_mutex); break; case V4L2_DEC_CMD_STOP: stream_end = false; diff --git a/drivers/media/platform/exynos4-is/fimc-isp-video.c b/drivers/media/platform/exynos4-is/fimc-isp-video.c index 378cc302e1f8..d2cbcdca0463 100644 --- a/drivers/media/platform/exynos4-is/fimc-isp-video.c +++ b/drivers/media/platform/exynos4-is/fimc-isp-video.c @@ -313,7 +313,7 @@ static int isp_video_release(struct file *file) ivc->streaming = 0; } - vb2_fop_release(file); + _vb2_fop_release(file, NULL); if (v4l2_fh_is_singular_file(file)) { fimc_pipeline_call(&ivc->ve, close); diff --git a/drivers/media/platform/exynos4-is/media-dev.c b/drivers/media/platform/exynos4-is/media-dev.c index a838189d4490..9aaf3b8060d5 100644 --- a/drivers/media/platform/exynos4-is/media-dev.c +++ b/drivers/media/platform/exynos4-is/media-dev.c @@ -1457,12 +1457,12 @@ static int fimc_md_probe(struct platform_device *pdev) ret = v4l2_device_register(dev, &fmd->v4l2_dev); if (ret < 0) { v4l2_err(v4l2_dev, "Failed to register v4l2_device: %d\n", ret); - return ret; + goto err_md; } ret = fimc_md_get_clocks(fmd); if (ret) - goto err_md; + goto err_v4l2dev; ret = fimc_md_get_pinctrl(fmd); if (ret < 0) { @@ -1519,9 +1519,10 @@ static int fimc_md_probe(struct platform_device *pdev) fimc_md_unregister_entities(fmd); err_clk: fimc_md_put_clocks(fmd); +err_v4l2dev: + v4l2_device_unregister(&fmd->v4l2_dev); err_md: media_device_cleanup(&fmd->media_dev); - v4l2_device_unregister(&fmd->v4l2_dev); return ret; } diff --git a/drivers/media/platform/meson/ao-cec-g12a.c b/drivers/media/platform/meson/ao-cec-g12a.c index 3b39e875292e..3d8fe854feb0 100644 --- a/drivers/media/platform/meson/ao-cec-g12a.c +++ b/drivers/media/platform/meson/ao-cec-g12a.c @@ -662,34 +662,27 @@ static int meson_ao_cec_g12a_probe(struct platform_device *pdev) if (IS_ERR(ao_cec->adap)) return PTR_ERR(ao_cec->adap); - ao_cec->notify = cec_notifier_cec_adap_register(hdmi_dev, NULL, - ao_cec->adap); - if (!ao_cec->notify) { - ret = -ENOMEM; - goto out_probe_adapter; - } - ao_cec->adap->owner = THIS_MODULE; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); base = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(base)) { ret = PTR_ERR(base); - goto out_probe_notify; + goto out_probe_adapter; } ao_cec->regmap = devm_regmap_init_mmio(&pdev->dev, base, &meson_ao_cec_g12a_regmap_conf); if (IS_ERR(ao_cec->regmap)) { ret = PTR_ERR(ao_cec->regmap); - goto out_probe_notify; + goto out_probe_adapter; } ao_cec->regmap_cec = devm_regmap_init(&pdev->dev, NULL, ao_cec, &meson_ao_cec_g12a_cec_regmap_conf); if (IS_ERR(ao_cec->regmap_cec)) { ret = PTR_ERR(ao_cec->regmap_cec); - goto out_probe_notify; + goto out_probe_adapter; } irq = platform_get_irq(pdev, 0); @@ -699,45 +692,52 @@ static int meson_ao_cec_g12a_probe(struct platform_device *pdev) 0, NULL, ao_cec); if (ret) { dev_err(&pdev->dev, "irq request failed\n"); - goto out_probe_notify; + goto out_probe_adapter; } ao_cec->oscin = devm_clk_get(&pdev->dev, "oscin"); if (IS_ERR(ao_cec->oscin)) { dev_err(&pdev->dev, "oscin clock request failed\n"); ret = PTR_ERR(ao_cec->oscin); - goto out_probe_notify; + goto out_probe_adapter; } ret = meson_ao_cec_g12a_setup_clk(ao_cec); if (ret) - goto out_probe_notify; + goto out_probe_adapter; ret = clk_prepare_enable(ao_cec->core); if (ret) { dev_err(&pdev->dev, "core clock enable failed\n"); - goto out_probe_notify; + goto out_probe_adapter; } device_reset_optional(&pdev->dev); platform_set_drvdata(pdev, ao_cec); + ao_cec->notify = cec_notifier_cec_adap_register(hdmi_dev, NULL, + ao_cec->adap); + if (!ao_cec->notify) { + ret = -ENOMEM; + goto out_probe_core_clk; + } + ret = cec_register_adapter(ao_cec->adap, &pdev->dev); if (ret < 0) - goto out_probe_core_clk; + goto out_probe_notify; /* Setup Hardware */ regmap_write(ao_cec->regmap, CECB_GEN_CNTL_REG, CECB_GEN_CNTL_RESET); return 0; -out_probe_core_clk: - clk_disable_unprepare(ao_cec->core); - out_probe_notify: cec_notifier_cec_adap_unregister(ao_cec->notify); +out_probe_core_clk: + clk_disable_unprepare(ao_cec->core); + out_probe_adapter: cec_delete_adapter(ao_cec->adap); diff --git a/drivers/media/platform/meson/ao-cec.c b/drivers/media/platform/meson/ao-cec.c index 64ed549bf012..03600e8b3ef0 100644 --- a/drivers/media/platform/meson/ao-cec.c +++ b/drivers/media/platform/meson/ao-cec.c @@ -624,20 +624,13 @@ static int meson_ao_cec_probe(struct platform_device *pdev) if (IS_ERR(ao_cec->adap)) return PTR_ERR(ao_cec->adap); - ao_cec->notify = cec_notifier_cec_adap_register(hdmi_dev, NULL, - ao_cec->adap); - if (!ao_cec->notify) { - ret = -ENOMEM; - goto out_probe_adapter; - } - ao_cec->adap->owner = THIS_MODULE; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); ao_cec->base = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(ao_cec->base)) { ret = PTR_ERR(ao_cec->base); - goto out_probe_notify; + goto out_probe_adapter; } irq = platform_get_irq(pdev, 0); @@ -647,20 +640,20 @@ static int meson_ao_cec_probe(struct platform_device *pdev) 0, NULL, ao_cec); if (ret) { dev_err(&pdev->dev, "irq request failed\n"); - goto out_probe_notify; + goto out_probe_adapter; } ao_cec->core = devm_clk_get(&pdev->dev, "core"); if (IS_ERR(ao_cec->core)) { dev_err(&pdev->dev, "core clock request failed\n"); ret = PTR_ERR(ao_cec->core); - goto out_probe_notify; + goto out_probe_adapter; } ret = clk_prepare_enable(ao_cec->core); if (ret) { dev_err(&pdev->dev, "core clock enable failed\n"); - goto out_probe_notify; + goto out_probe_adapter; } ret = clk_set_rate(ao_cec->core, CEC_CLK_RATE); @@ -674,9 +667,16 @@ static int meson_ao_cec_probe(struct platform_device *pdev) ao_cec->pdev = pdev; platform_set_drvdata(pdev, ao_cec); + ao_cec->notify = cec_notifier_cec_adap_register(hdmi_dev, NULL, + ao_cec->adap); + if (!ao_cec->notify) { + ret = -ENOMEM; + goto out_probe_clk; + } + ret = cec_register_adapter(ao_cec->adap, &pdev->dev); if (ret < 0) - goto out_probe_clk; + goto out_probe_notify; /* Setup Hardware */ writel_relaxed(CEC_GEN_CNTL_RESET, @@ -684,12 +684,12 @@ static int meson_ao_cec_probe(struct platform_device *pdev) return 0; -out_probe_clk: - clk_disable_unprepare(ao_cec->core); - out_probe_notify: cec_notifier_cec_adap_unregister(ao_cec->notify); +out_probe_clk: + clk_disable_unprepare(ao_cec->core); + out_probe_adapter: cec_delete_adapter(ao_cec->adap); diff --git a/drivers/media/platform/qcom/venus/core.c b/drivers/media/platform/qcom/venus/core.c index e6eff512a8a1..84e982f259a0 100644 --- a/drivers/media/platform/qcom/venus/core.c +++ b/drivers/media/platform/qcom/venus/core.c @@ -427,10 +427,11 @@ static const struct venus_resources msm8916_res = { }; static const struct freq_tbl msm8996_freq_table[] = { - { 1944000, 490000000 }, /* 4k UHD @ 60 */ - { 972000, 320000000 }, /* 4k UHD @ 30 */ - { 489600, 150000000 }, /* 1080p @ 60 */ - { 244800, 75000000 }, /* 1080p @ 30 */ + { 1944000, 520000000 }, /* 4k UHD @ 60 (decode only) */ + { 972000, 520000000 }, /* 4k UHD @ 30 */ + { 489600, 346666667 }, /* 1080p @ 60 */ + { 244800, 150000000 }, /* 1080p @ 30 */ + { 108000, 75000000 }, /* 720p @ 30 */ }; static const struct reg_val msm8996_reg_preset[] = { diff --git a/drivers/media/platform/qcom/venus/hfi_venus.c b/drivers/media/platform/qcom/venus/hfi_venus.c index 7129a2aea09a..0d8855014ab3 100644 --- a/drivers/media/platform/qcom/venus/hfi_venus.c +++ b/drivers/media/platform/qcom/venus/hfi_venus.c @@ -1472,6 +1472,7 @@ static int venus_suspend_3xx(struct venus_core *core) { struct venus_hfi_device *hdev = to_hfi_priv(core); struct device *dev = core->dev; + u32 ctrl_status; bool val; int ret; @@ -1487,6 +1488,10 @@ static int venus_suspend_3xx(struct venus_core *core) return -EINVAL; } + ctrl_status = venus_readl(hdev, CPU_CS_SCIACMDARG0); + if (ctrl_status & CPU_CS_SCIACMDARG0_PC_READY) + goto power_off; + /* * Power collapse sequence for Venus 3xx and 4xx versions: * 1. Check for ARM9 and video core to be idle by checking WFI bit @@ -1511,6 +1516,7 @@ static int venus_suspend_3xx(struct venus_core *core) if (ret) return ret; +power_off: mutex_lock(&hdev->lock); ret = venus_power_off(hdev); diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c index 7f4660555ddb..59ae7a1e63bc 100644 --- a/drivers/media/platform/qcom/venus/vdec.c +++ b/drivers/media/platform/qcom/venus/vdec.c @@ -1412,9 +1412,6 @@ static const struct v4l2_file_operations vdec_fops = { .unlocked_ioctl = video_ioctl2, .poll = v4l2_m2m_fop_poll, .mmap = v4l2_m2m_fop_mmap, -#ifdef CONFIG_COMPAT - .compat_ioctl32 = v4l2_compat_ioctl32, -#endif }; static int vdec_probe(struct platform_device *pdev) diff --git a/drivers/media/platform/qcom/venus/venc.c b/drivers/media/platform/qcom/venus/venc.c index 1b7fb2d5887c..30028ceb548b 100644 --- a/drivers/media/platform/qcom/venus/venc.c +++ b/drivers/media/platform/qcom/venus/venc.c @@ -1235,9 +1235,6 @@ static const struct v4l2_file_operations venc_fops = { .unlocked_ioctl = video_ioctl2, .poll = v4l2_m2m_fop_poll, .mmap = v4l2_m2m_fop_mmap, -#ifdef CONFIG_COMPAT - .compat_ioctl32 = v4l2_compat_ioctl32, -#endif }; static int venc_probe(struct platform_device *pdev) diff --git a/drivers/media/platform/rcar-vin/rcar-v4l2.c b/drivers/media/platform/rcar-vin/rcar-v4l2.c index cbc1c07f0a96..ec2796413e26 100644 --- a/drivers/media/platform/rcar-vin/rcar-v4l2.c +++ b/drivers/media/platform/rcar-vin/rcar-v4l2.c @@ -208,6 +208,7 @@ static int rvin_try_format(struct rvin_dev *vin, u32 which, ret = v4l2_subdev_call(sd, pad, set_fmt, pad_cfg, &format); if (ret < 0 && ret != -ENOIOCTLCMD) goto done; + ret = 0; v4l2_fill_pix_format(pix, &format.format); @@ -242,7 +243,7 @@ static int rvin_try_format(struct rvin_dev *vin, u32 which, done: v4l2_subdev_free_pad_config(pad_cfg); - return 0; + return ret; } static int rvin_querycap(struct file *file, void *priv, diff --git a/drivers/media/platform/rcar_drif.c b/drivers/media/platform/rcar_drif.c index 608e5217ccd5..0f267a237b42 100644 --- a/drivers/media/platform/rcar_drif.c +++ b/drivers/media/platform/rcar_drif.c @@ -912,6 +912,7 @@ static int rcar_drif_g_fmt_sdr_cap(struct file *file, void *priv, { struct rcar_drif_sdr *sdr = video_drvdata(file); + memset(f->fmt.sdr.reserved, 0, sizeof(f->fmt.sdr.reserved)); f->fmt.sdr.pixelformat = sdr->fmt->pixelformat; f->fmt.sdr.buffersize = sdr->fmt->buffersize; diff --git a/drivers/media/platform/seco-cec/seco-cec.c b/drivers/media/platform/seco-cec/seco-cec.c index 9cd60fe1867c..a86b6e8f9196 100644 --- a/drivers/media/platform/seco-cec/seco-cec.c +++ b/drivers/media/platform/seco-cec/seco-cec.c @@ -675,6 +675,7 @@ static int secocec_probe(struct platform_device *pdev) err_delete_adapter: cec_delete_adapter(secocec->cec_adap); err: + release_region(BRA_SMB_BASE_ADDR, 7); dev_err(dev, "%s device probe failed\n", dev_name(dev)); return ret; diff --git a/drivers/media/platform/sti/bdisp/bdisp-v4l2.c b/drivers/media/platform/sti/bdisp/bdisp-v4l2.c index e90f1ba30574..675b5f2b4c2e 100644 --- a/drivers/media/platform/sti/bdisp/bdisp-v4l2.c +++ b/drivers/media/platform/sti/bdisp/bdisp-v4l2.c @@ -651,8 +651,7 @@ static int bdisp_release(struct file *file) dev_dbg(bdisp->dev, "%s\n", __func__); - if (mutex_lock_interruptible(&bdisp->lock)) - return -ERESTARTSYS; + mutex_lock(&bdisp->lock); v4l2_m2m_ctx_release(ctx->fh.m2m_ctx); diff --git a/drivers/media/platform/ti-vpe/vpdma.h b/drivers/media/platform/ti-vpe/vpdma.h index 28bc94129348..9bacfd603250 100644 --- a/drivers/media/platform/ti-vpe/vpdma.h +++ b/drivers/media/platform/ti-vpe/vpdma.h @@ -57,6 +57,7 @@ struct vpdma_data_format { * line stride of source and dest * buffers should be 16 byte aligned */ +#define VPDMA_MAX_STRIDE 65520 /* Max line stride 16 byte aligned */ #define VPDMA_DTD_DESC_SIZE 32 /* 8 words */ #define VPDMA_CFD_CTD_DESC_SIZE 16 /* 4 words */ diff --git a/drivers/media/platform/ti-vpe/vpe.c b/drivers/media/platform/ti-vpe/vpe.c index 60b575bb44c4..8b14ba4a3d9e 100644 --- a/drivers/media/platform/ti-vpe/vpe.c +++ b/drivers/media/platform/ti-vpe/vpe.c @@ -338,20 +338,25 @@ enum { }; /* find our format description corresponding to the passed v4l2_format */ -static struct vpe_fmt *find_format(struct v4l2_format *f) +static struct vpe_fmt *__find_format(u32 fourcc) { struct vpe_fmt *fmt; unsigned int k; for (k = 0; k < ARRAY_SIZE(vpe_formats); k++) { fmt = &vpe_formats[k]; - if (fmt->fourcc == f->fmt.pix.pixelformat) + if (fmt->fourcc == fourcc) return fmt; } return NULL; } +static struct vpe_fmt *find_format(struct v4l2_format *f) +{ + return __find_format(f->fmt.pix.pixelformat); +} + /* * there is one vpe_dev structure in the driver, it is shared by * all instances. @@ -1013,11 +1018,14 @@ static void add_out_dtd(struct vpe_ctx *ctx, int port) dma_addr_t dma_addr; u32 flags = 0; u32 offset = 0; + u32 stride; if (port == VPE_PORT_MV_OUT) { vpdma_fmt = &vpdma_misc_fmts[VPDMA_DATA_FMT_MV]; dma_addr = ctx->mv_buf_dma[mv_buf_selector]; q_data = &ctx->q_data[Q_DATA_SRC]; + stride = ALIGN((q_data->width * vpdma_fmt->depth) >> 3, + VPDMA_STRIDE_ALIGN); } else { /* to incorporate interleaved formats */ int plane = fmt->coplanar ? p_data->vb_part : 0; @@ -1044,6 +1052,7 @@ static void add_out_dtd(struct vpe_ctx *ctx, int port) } /* Apply the offset */ dma_addr += offset; + stride = q_data->bytesperline[VPE_LUMA]; } if (q_data->flags & Q_DATA_FRAME_1D) @@ -1055,7 +1064,7 @@ static void add_out_dtd(struct vpe_ctx *ctx, int port) MAX_W, MAX_H); vpdma_add_out_dtd(&ctx->desc_list, q_data->width, - q_data->bytesperline[VPE_LUMA], &q_data->c_rect, + stride, &q_data->c_rect, vpdma_fmt, dma_addr, MAX_OUT_WIDTH_REG1, MAX_OUT_HEIGHT_REG1, p_data->channel, flags); } @@ -1074,10 +1083,13 @@ static void add_in_dtd(struct vpe_ctx *ctx, int port) dma_addr_t dma_addr; u32 flags = 0; u32 offset = 0; + u32 stride; if (port == VPE_PORT_MV_IN) { vpdma_fmt = &vpdma_misc_fmts[VPDMA_DATA_FMT_MV]; dma_addr = ctx->mv_buf_dma[mv_buf_selector]; + stride = ALIGN((q_data->width * vpdma_fmt->depth) >> 3, + VPDMA_STRIDE_ALIGN); } else { /* to incorporate interleaved formats */ int plane = fmt->coplanar ? p_data->vb_part : 0; @@ -1104,6 +1116,7 @@ static void add_in_dtd(struct vpe_ctx *ctx, int port) } /* Apply the offset */ dma_addr += offset; + stride = q_data->bytesperline[VPE_LUMA]; if (q_data->flags & Q_DATA_INTERLACED_SEQ_TB) { /* @@ -1139,10 +1152,10 @@ static void add_in_dtd(struct vpe_ctx *ctx, int port) if (p_data->vb_part && fmt->fourcc == V4L2_PIX_FMT_NV12) frame_height /= 2; - vpdma_add_in_dtd(&ctx->desc_list, q_data->width, - q_data->bytesperline[VPE_LUMA], &q_data->c_rect, - vpdma_fmt, dma_addr, p_data->channel, field, flags, frame_width, - frame_height, 0, 0); + vpdma_add_in_dtd(&ctx->desc_list, q_data->width, stride, + &q_data->c_rect, vpdma_fmt, dma_addr, + p_data->channel, field, flags, frame_width, + frame_height, 0, 0); } /* @@ -1391,9 +1404,6 @@ static irqreturn_t vpe_irq(int irq_vpe, void *data) /* the previous dst mv buffer becomes the next src mv buffer */ ctx->src_mv_buf_selector = !ctx->src_mv_buf_selector; - if (ctx->aborting) - goto finished; - s_vb = ctx->src_vbs[0]; d_vb = ctx->dst_vb; @@ -1404,6 +1414,7 @@ static irqreturn_t vpe_irq(int irq_vpe, void *data) d_vb->timecode = s_vb->timecode; d_vb->sequence = ctx->sequence; + s_vb->sequence = ctx->sequence; d_q_data = &ctx->q_data[Q_DATA_DST]; if (d_q_data->flags & Q_IS_INTERLACED) { @@ -1457,6 +1468,9 @@ static irqreturn_t vpe_irq(int irq_vpe, void *data) ctx->src_vbs[0] = NULL; ctx->dst_vb = NULL; + if (ctx->aborting) + goto finished; + ctx->bufs_completed++; if (ctx->bufs_completed < ctx->bufs_per_job && job_ready(ctx)) { device_run(ctx); @@ -1566,9 +1580,9 @@ static int __vpe_try_fmt(struct vpe_ctx *ctx, struct v4l2_format *f, unsigned int stride = 0; if (!fmt || !(fmt->types & type)) { - vpe_err(ctx->dev, "Fourcc format (0x%08x) invalid.\n", + vpe_dbg(ctx->dev, "Fourcc format (0x%08x) invalid.\n", pix->pixelformat); - return -EINVAL; + fmt = __find_format(V4L2_PIX_FMT_YUYV); } if (pix->field != V4L2_FIELD_NONE && pix->field != V4L2_FIELD_ALTERNATE @@ -1615,7 +1629,7 @@ static int __vpe_try_fmt(struct vpe_ctx *ctx, struct v4l2_format *f, &pix->height, MIN_H, MAX_H, H_ALIGN, S_ALIGN); - if (!pix->num_planes) + if (!pix->num_planes || pix->num_planes > 2) pix->num_planes = fmt->coplanar ? 2 : 1; else if (pix->num_planes > 1 && !fmt->coplanar) pix->num_planes = 1; @@ -1654,6 +1668,10 @@ static int __vpe_try_fmt(struct vpe_ctx *ctx, struct v4l2_format *f, if (stride > plane_fmt->bytesperline) plane_fmt->bytesperline = stride; + plane_fmt->bytesperline = clamp_t(u32, plane_fmt->bytesperline, + stride, + VPDMA_MAX_STRIDE); + plane_fmt->bytesperline = ALIGN(plane_fmt->bytesperline, VPDMA_STRIDE_ALIGN); @@ -2274,7 +2292,7 @@ static int vpe_open(struct file *file) v4l2_ctrl_handler_setup(hdl); s_q_data = &ctx->q_data[Q_DATA_SRC]; - s_q_data->fmt = &vpe_formats[2]; + s_q_data->fmt = __find_format(V4L2_PIX_FMT_YUYV); s_q_data->width = 1920; s_q_data->height = 1080; s_q_data->nplanes = 1; @@ -2352,6 +2370,12 @@ static int vpe_release(struct file *file) mutex_lock(&dev->dev_mutex); free_mv_buffers(ctx); + + vpdma_unmap_desc_buf(dev->vpdma, &ctx->desc_list.buf); + vpdma_unmap_desc_buf(dev->vpdma, &ctx->mmr_adb); + vpdma_unmap_desc_buf(dev->vpdma, &ctx->sc_coeff_h); + vpdma_unmap_desc_buf(dev->vpdma, &ctx->sc_coeff_v); + vpdma_free_desc_list(&ctx->desc_list); vpdma_free_desc_buf(&ctx->mmr_adb); diff --git a/drivers/media/platform/vicodec/vicodec-core.c b/drivers/media/platform/vicodec/vicodec-core.c index 0ee143ae0f6b..82350097503e 100644 --- a/drivers/media/platform/vicodec/vicodec-core.c +++ b/drivers/media/platform/vicodec/vicodec-core.c @@ -2139,6 +2139,9 @@ static void vicodec_v4l2_dev_release(struct v4l2_device *v4l2_dev) v4l2_m2m_release(dev->stateful_enc.m2m_dev); v4l2_m2m_release(dev->stateful_dec.m2m_dev); v4l2_m2m_release(dev->stateless_dec.m2m_dev); +#ifdef CONFIG_MEDIA_CONTROLLER + media_device_cleanup(&dev->mdev); +#endif kfree(dev); } @@ -2250,7 +2253,6 @@ static int vicodec_remove(struct platform_device *pdev) v4l2_m2m_unregister_media_controller(dev->stateful_enc.m2m_dev); v4l2_m2m_unregister_media_controller(dev->stateful_dec.m2m_dev); v4l2_m2m_unregister_media_controller(dev->stateless_dec.m2m_dev); - media_device_cleanup(&dev->mdev); #endif video_unregister_device(&dev->stateful_enc.vfd); diff --git a/drivers/media/platform/vim2m.c b/drivers/media/platform/vim2m.c index acd3bd48c7e2..8d6b09623d88 100644 --- a/drivers/media/platform/vim2m.c +++ b/drivers/media/platform/vim2m.c @@ -1073,6 +1073,9 @@ static int vim2m_start_streaming(struct vb2_queue *q, unsigned int count) if (!q_data) return -EINVAL; + if (V4L2_TYPE_IS_OUTPUT(q->type)) + ctx->aborting = 0; + q_data->sequence = 0; return 0; } @@ -1272,6 +1275,9 @@ static void vim2m_device_release(struct video_device *vdev) v4l2_device_unregister(&dev->v4l2_dev); v4l2_m2m_release(dev->m2m_dev); +#ifdef CONFIG_MEDIA_CONTROLLER + media_device_cleanup(&dev->mdev); +#endif kfree(dev); } @@ -1343,6 +1349,7 @@ static int vim2m_probe(struct platform_device *pdev) if (IS_ERR(dev->m2m_dev)) { v4l2_err(&dev->v4l2_dev, "Failed to init mem2mem device\n"); ret = PTR_ERR(dev->m2m_dev); + dev->m2m_dev = NULL; goto error_dev; } @@ -1395,7 +1402,6 @@ static int vim2m_remove(struct platform_device *pdev) #ifdef CONFIG_MEDIA_CONTROLLER media_device_unregister(&dev->mdev); v4l2_m2m_unregister_media_controller(dev->m2m_dev); - media_device_cleanup(&dev->mdev); #endif video_unregister_device(&dev->vfd); diff --git a/drivers/media/platform/vimc/vimc-common.c b/drivers/media/platform/vimc/vimc-common.c index 7e1ae0b12f1e..a3120f4f7a90 100644 --- a/drivers/media/platform/vimc/vimc-common.c +++ b/drivers/media/platform/vimc/vimc-common.c @@ -375,7 +375,7 @@ int vimc_ent_sd_register(struct vimc_ent_device *ved, { int ret; - /* Allocate the pads */ + /* Allocate the pads. Should be released from the sd_int_op release */ ved->pads = vimc_pads_init(num_pads, pads_flag); if (IS_ERR(ved->pads)) return PTR_ERR(ved->pads); @@ -424,7 +424,6 @@ EXPORT_SYMBOL_GPL(vimc_ent_sd_register); void vimc_ent_sd_unregister(struct vimc_ent_device *ved, struct v4l2_subdev *sd) { media_entity_cleanup(ved->ent); - vimc_pads_cleanup(ved->pads); v4l2_device_unregister_subdev(sd); } EXPORT_SYMBOL_GPL(vimc_ent_sd_unregister); diff --git a/drivers/media/platform/vimc/vimc-debayer.c b/drivers/media/platform/vimc/vimc-debayer.c index b72b8385067b..baafd9d7fb2c 100644 --- a/drivers/media/platform/vimc/vimc-debayer.c +++ b/drivers/media/platform/vimc/vimc-debayer.c @@ -484,6 +484,7 @@ static void vimc_deb_release(struct v4l2_subdev *sd) struct vimc_deb_device *vdeb = container_of(sd, struct vimc_deb_device, sd); + vimc_pads_cleanup(vdeb->ved.pads); kfree(vdeb); } diff --git a/drivers/media/platform/vimc/vimc-scaler.c b/drivers/media/platform/vimc/vimc-scaler.c index 49ab8d9dd9c9..c0d9f43d5777 100644 --- a/drivers/media/platform/vimc/vimc-scaler.c +++ b/drivers/media/platform/vimc/vimc-scaler.c @@ -343,6 +343,7 @@ static void vimc_sca_release(struct v4l2_subdev *sd) struct vimc_sca_device *vsca = container_of(sd, struct vimc_sca_device, sd); + vimc_pads_cleanup(vsca->ved.pads); kfree(vsca); } diff --git a/drivers/media/platform/vimc/vimc-sensor.c b/drivers/media/platform/vimc/vimc-sensor.c index 6c53b9fc1617..420573e5f6d6 100644 --- a/drivers/media/platform/vimc/vimc-sensor.c +++ b/drivers/media/platform/vimc/vimc-sensor.c @@ -25,7 +25,6 @@ struct vimc_sen_device { struct v4l2_subdev sd; struct device *dev; struct tpg_data tpg; - struct task_struct *kthread_sen; u8 *frame; /* The active format */ struct v4l2_mbus_framefmt mbus_format; @@ -208,10 +207,6 @@ static int vimc_sen_s_stream(struct v4l2_subdev *sd, int enable) const struct vimc_pix_map *vpix; unsigned int frame_size; - if (vsen->kthread_sen) - /* tpg is already executing */ - return 0; - /* Calculate the frame size */ vpix = vimc_pix_map_by_code(vsen->mbus_format.code); frame_size = vsen->mbus_format.width * vpix->bpp * @@ -297,6 +292,7 @@ static void vimc_sen_release(struct v4l2_subdev *sd) v4l2_ctrl_handler_free(&vsen->hdl); tpg_free(&vsen->tpg); + vimc_pads_cleanup(vsen->ved.pads); kfree(vsen); } diff --git a/drivers/media/platform/vivid/vivid-core.c b/drivers/media/platform/vivid/vivid-core.c index 53315c8dd2bb..f6a5cdbd74e7 100644 --- a/drivers/media/platform/vivid/vivid-core.c +++ b/drivers/media/platform/vivid/vivid-core.c @@ -616,6 +616,9 @@ static void vivid_dev_release(struct v4l2_device *v4l2_dev) vivid_free_controls(dev); v4l2_device_unregister(&dev->v4l2_dev); +#ifdef CONFIG_MEDIA_CONTROLLER + media_device_cleanup(&dev->mdev); +#endif vfree(dev->scaled_line); vfree(dev->blended_line); vfree(dev->edid); @@ -1580,7 +1583,6 @@ static int vivid_remove(struct platform_device *pdev) #ifdef CONFIG_MEDIA_CONTROLLER media_device_unregister(&dev->mdev); - media_device_cleanup(&dev->mdev); #endif if (dev->has_vid_cap) { diff --git a/drivers/media/platform/vivid/vivid-kthread-cap.c b/drivers/media/platform/vivid/vivid-kthread-cap.c index 003319d7816d..31f78d6a05a4 100644 --- a/drivers/media/platform/vivid/vivid-kthread-cap.c +++ b/drivers/media/platform/vivid/vivid-kthread-cap.c @@ -796,7 +796,11 @@ static int vivid_thread_vid_cap(void *data) if (kthread_should_stop()) break; - mutex_lock(&dev->mutex); + if (!mutex_trylock(&dev->mutex)) { + schedule_timeout_uninterruptible(1); + continue; + } + cur_jiffies = jiffies; if (dev->cap_seq_resync) { dev->jiffies_vid_cap = cur_jiffies; @@ -956,8 +960,6 @@ void vivid_stop_generating_vid_cap(struct vivid_dev *dev, bool *pstreaming) /* shutdown control thread */ vivid_grab_controls(dev, false); - mutex_unlock(&dev->mutex); kthread_stop(dev->kthread_vid_cap); dev->kthread_vid_cap = NULL; - mutex_lock(&dev->mutex); } diff --git a/drivers/media/platform/vivid/vivid-kthread-out.c b/drivers/media/platform/vivid/vivid-kthread-out.c index ce5bcda2348c..1e165a6a2207 100644 --- a/drivers/media/platform/vivid/vivid-kthread-out.c +++ b/drivers/media/platform/vivid/vivid-kthread-out.c @@ -143,7 +143,11 @@ static int vivid_thread_vid_out(void *data) if (kthread_should_stop()) break; - mutex_lock(&dev->mutex); + if (!mutex_trylock(&dev->mutex)) { + schedule_timeout_uninterruptible(1); + continue; + } + cur_jiffies = jiffies; if (dev->out_seq_resync) { dev->jiffies_vid_out = cur_jiffies; @@ -301,8 +305,6 @@ void vivid_stop_generating_vid_out(struct vivid_dev *dev, bool *pstreaming) /* shutdown control thread */ vivid_grab_controls(dev, false); - mutex_unlock(&dev->mutex); kthread_stop(dev->kthread_vid_out); dev->kthread_vid_out = NULL; - mutex_lock(&dev->mutex); } diff --git a/drivers/media/platform/vivid/vivid-sdr-cap.c b/drivers/media/platform/vivid/vivid-sdr-cap.c index 9acc709b0740..2b7522e16efc 100644 --- a/drivers/media/platform/vivid/vivid-sdr-cap.c +++ b/drivers/media/platform/vivid/vivid-sdr-cap.c @@ -141,7 +141,11 @@ static int vivid_thread_sdr_cap(void *data) if (kthread_should_stop()) break; - mutex_lock(&dev->mutex); + if (!mutex_trylock(&dev->mutex)) { + schedule_timeout_uninterruptible(1); + continue; + } + cur_jiffies = jiffies; if (dev->sdr_cap_seq_resync) { dev->jiffies_sdr_cap = cur_jiffies; @@ -303,10 +307,8 @@ static void sdr_cap_stop_streaming(struct vb2_queue *vq) } /* shutdown control thread */ - mutex_unlock(&dev->mutex); kthread_stop(dev->kthread_sdr_cap); dev->kthread_sdr_cap = NULL; - mutex_lock(&dev->mutex); } static void sdr_cap_buf_request_complete(struct vb2_buffer *vb) diff --git a/drivers/media/platform/vivid/vivid-vid-cap.c b/drivers/media/platform/vivid/vivid-vid-cap.c index 8cbaa0c998ed..2d030732feac 100644 --- a/drivers/media/platform/vivid/vivid-vid-cap.c +++ b/drivers/media/platform/vivid/vivid-vid-cap.c @@ -223,9 +223,6 @@ static int vid_cap_start_streaming(struct vb2_queue *vq, unsigned count) if (vb2_is_streaming(&dev->vb_vid_out_q)) dev->can_loop_video = vivid_vid_can_loop(dev); - if (dev->kthread_vid_cap) - return 0; - dev->vid_cap_seq_count = 0; dprintk(dev, 1, "%s\n", __func__); for (i = 0; i < VIDEO_MAX_FRAME; i++) diff --git a/drivers/media/platform/vivid/vivid-vid-out.c b/drivers/media/platform/vivid/vivid-vid-out.c index 148b663a6075..a0364ac497f9 100644 --- a/drivers/media/platform/vivid/vivid-vid-out.c +++ b/drivers/media/platform/vivid/vivid-vid-out.c @@ -161,9 +161,6 @@ static int vid_out_start_streaming(struct vb2_queue *vq, unsigned count) if (vb2_is_streaming(&dev->vb_vid_cap_q)) dev->can_loop_video = vivid_vid_can_loop(dev); - if (dev->kthread_vid_out) - return 0; - dev->vid_out_seq_count = 0; dprintk(dev, 1, "%s\n", __func__); if (dev->start_streaming_error) { diff --git a/drivers/media/radio/radio-wl1273.c b/drivers/media/radio/radio-wl1273.c index 104ac41c6f96..112376873167 100644 --- a/drivers/media/radio/radio-wl1273.c +++ b/drivers/media/radio/radio-wl1273.c @@ -1148,8 +1148,7 @@ static int wl1273_fm_fops_release(struct file *file) if (radio->rds_users > 0) { radio->rds_users--; if (radio->rds_users == 0) { - if (mutex_lock_interruptible(&core->lock)) - return -EINTR; + mutex_lock(&core->lock); radio->irq_flags &= ~WL1273_RDS_EVENT; diff --git a/drivers/media/radio/si470x/radio-si470x-i2c.c b/drivers/media/radio/si470x/radio-si470x-i2c.c index 7541698a0be1..f491420d7b53 100644 --- a/drivers/media/radio/si470x/radio-si470x-i2c.c +++ b/drivers/media/radio/si470x/radio-si470x-i2c.c @@ -482,6 +482,8 @@ static int si470x_i2c_remove(struct i2c_client *client) if (radio->gpio_reset) gpiod_set_value(radio->gpio_reset, 0); + v4l2_ctrl_handler_free(&radio->hdl); + v4l2_device_unregister(&radio->v4l2_dev); return 0; } diff --git a/drivers/media/rc/imon.c b/drivers/media/rc/imon.c index 37a850421fbb..c683a244b9fa 100644 --- a/drivers/media/rc/imon.c +++ b/drivers/media/rc/imon.c @@ -1598,8 +1598,7 @@ static void imon_incoming_packet(struct imon_context *ictx, spin_unlock_irqrestore(&ictx->kc_lock, flags); /* send touchscreen events through input subsystem if touchpad data */ - if (ictx->display_type == IMON_DISPLAY_TYPE_VGA && len == 8 && - buf[7] == 0x86) { + if (ictx->touch && len == 8 && buf[7] == 0x86) { imon_touch_event(ictx, buf); return; diff --git a/drivers/media/rc/mceusb.c b/drivers/media/rc/mceusb.c index 3fc9829a9233..f9616158bcf4 100644 --- a/drivers/media/rc/mceusb.c +++ b/drivers/media/rc/mceusb.c @@ -564,7 +564,7 @@ static int mceusb_cmd_datasize(u8 cmd, u8 subcmd) datasize = 4; break; case MCE_CMD_G_REVISION: - datasize = 2; + datasize = 4; break; case MCE_RSP_EQWAKESUPPORT: case MCE_RSP_GETWAKESOURCE: @@ -600,14 +600,9 @@ static void mceusb_dev_printdata(struct mceusb_dev *ir, u8 *buf, int buf_len, char *inout; u8 cmd, subcmd, *data; struct device *dev = ir->dev; - int start, skip = 0; u32 carrier, period; - /* skip meaningless 0xb1 0x60 header bytes on orig receiver */ - if (ir->flags.microsoft_gen1 && !out && !offset) - skip = 2; - - if (len <= skip) + if (offset < 0 || offset >= buf_len) return; dev_dbg(dev, "%cx data[%d]: %*ph (len=%d sz=%d)", @@ -616,11 +611,32 @@ static void mceusb_dev_printdata(struct mceusb_dev *ir, u8 *buf, int buf_len, inout = out ? "Request" : "Got"; - start = offset + skip; - cmd = buf[start] & 0xff; - subcmd = buf[start + 1] & 0xff; - data = buf + start + 2; + cmd = buf[offset]; + subcmd = (offset + 1 < buf_len) ? buf[offset + 1] : 0; + data = &buf[offset] + 2; + + /* Trace meaningless 0xb1 0x60 header bytes on original receiver */ + if (ir->flags.microsoft_gen1 && !out && !offset) { + dev_dbg(dev, "MCE gen 1 header"); + return; + } + + /* Trace IR data header or trailer */ + if (cmd != MCE_CMD_PORT_IR && + (cmd & MCE_PORT_MASK) == MCE_COMMAND_IRDATA) { + if (cmd == MCE_IRDATA_TRAILER) + dev_dbg(dev, "End of raw IR data"); + else + dev_dbg(dev, "Raw IR data, %d pulse/space samples", + cmd & MCE_PACKET_LENGTH_MASK); + return; + } + + /* Unexpected end of buffer? */ + if (offset + len > buf_len) + return; + /* Decode MCE command/response */ switch (cmd) { case MCE_CMD_NULL: if (subcmd == MCE_CMD_NULL) @@ -644,7 +660,7 @@ static void mceusb_dev_printdata(struct mceusb_dev *ir, u8 *buf, int buf_len, dev_dbg(dev, "Get hw/sw rev?"); else dev_dbg(dev, "hw/sw rev %*ph", - 4, &buf[start + 2]); + 4, &buf[offset + 2]); break; case MCE_CMD_RESUME: dev_dbg(dev, "Device resume requested"); @@ -746,13 +762,6 @@ static void mceusb_dev_printdata(struct mceusb_dev *ir, u8 *buf, int buf_len, default: break; } - - if (cmd == MCE_IRDATA_TRAILER) - dev_dbg(dev, "End of raw IR data"); - else if ((cmd != MCE_CMD_PORT_IR) && - ((cmd & MCE_PORT_MASK) == MCE_COMMAND_IRDATA)) - dev_dbg(dev, "Raw IR data, %d pulse/space samples", - cmd & MCE_PACKET_LENGTH_MASK); #endif } @@ -1136,32 +1145,62 @@ static int mceusb_set_rx_carrier_report(struct rc_dev *dev, int enable) } /* + * Handle PORT_SYS/IR command response received from the MCE device. + * + * Assumes single response with all its data (not truncated) + * in buf_in[]. The response itself determines its total length + * (mceusb_cmd_datasize() + 2) and hence the minimum size of buf_in[]. + * * We don't do anything but print debug spew for many of the command bits * we receive from the hardware, but some of them are useful information * we want to store so that we can use them. */ -static void mceusb_handle_command(struct mceusb_dev *ir, int index) +static void mceusb_handle_command(struct mceusb_dev *ir, u8 *buf_in) { + u8 cmd = buf_in[0]; + u8 subcmd = buf_in[1]; + u8 *hi = &buf_in[2]; /* read only when required */ + u8 *lo = &buf_in[3]; /* read only when required */ struct ir_raw_event rawir = {}; - u8 hi = ir->buf_in[index + 1] & 0xff; - u8 lo = ir->buf_in[index + 2] & 0xff; u32 carrier_cycles; u32 cycles_fix; - switch (ir->buf_in[index]) { - /* the one and only 5-byte return value command */ - case MCE_RSP_GETPORTSTATUS: - if ((ir->buf_in[index + 4] & 0xff) == 0x00) - ir->txports_cabled |= 1 << hi; - break; + if (cmd == MCE_CMD_PORT_SYS) { + switch (subcmd) { + /* the one and only 5-byte return value command */ + case MCE_RSP_GETPORTSTATUS: + if (buf_in[5] == 0) + ir->txports_cabled |= 1 << *hi; + break; + + /* 1-byte return value commands */ + case MCE_RSP_EQEMVER: + ir->emver = *hi; + break; + + /* No return value commands */ + case MCE_RSP_CMD_ILLEGAL: + ir->need_reset = true; + break; + + default: + break; + } + + return; + } + if (cmd != MCE_CMD_PORT_IR) + return; + + switch (subcmd) { /* 2-byte return value commands */ case MCE_RSP_EQIRTIMEOUT: - ir->rc->timeout = US_TO_NS((hi << 8 | lo) * MCE_TIME_UNIT); + ir->rc->timeout = US_TO_NS((*hi << 8 | *lo) * MCE_TIME_UNIT); break; case MCE_RSP_EQIRNUMPORTS: - ir->num_txports = hi; - ir->num_rxports = lo; + ir->num_txports = *hi; + ir->num_rxports = *lo; break; case MCE_RSP_EQIRRXCFCNT: /* @@ -1174,7 +1213,7 @@ static void mceusb_handle_command(struct mceusb_dev *ir, int index) */ if (ir->carrier_report_enabled && ir->learning_active && ir->pulse_tunit > 0) { - carrier_cycles = (hi << 8 | lo); + carrier_cycles = (*hi << 8 | *lo); /* * Adjust carrier cycle count by adding * 1 missed count per pulse "on" @@ -1192,24 +1231,24 @@ static void mceusb_handle_command(struct mceusb_dev *ir, int index) break; /* 1-byte return value commands */ - case MCE_RSP_EQEMVER: - ir->emver = hi; - break; case MCE_RSP_EQIRTXPORTS: - ir->tx_mask = hi; + ir->tx_mask = *hi; break; case MCE_RSP_EQIRRXPORTEN: - ir->learning_active = ((hi & 0x02) == 0x02); - if (ir->rxports_active != hi) { + ir->learning_active = ((*hi & 0x02) == 0x02); + if (ir->rxports_active != *hi) { dev_info(ir->dev, "%s-range (0x%x) receiver active", - ir->learning_active ? "short" : "long", hi); - ir->rxports_active = hi; + ir->learning_active ? "short" : "long", *hi); + ir->rxports_active = *hi; } break; + + /* No return value commands */ case MCE_RSP_CMD_ILLEGAL: case MCE_RSP_TX_TIMEOUT: ir->need_reset = true; break; + default: break; } @@ -1235,7 +1274,8 @@ static void mceusb_process_ir_data(struct mceusb_dev *ir, int buf_len) ir->rem = mceusb_cmd_datasize(ir->cmd, ir->buf_in[i]); mceusb_dev_printdata(ir, ir->buf_in, buf_len, i - 1, ir->rem + 2, false); - mceusb_handle_command(ir, i); + if (i + ir->rem < buf_len) + mceusb_handle_command(ir, &ir->buf_in[i - 1]); ir->parser_state = CMD_DATA; break; case PARSE_IRDATA: @@ -1264,15 +1304,22 @@ static void mceusb_process_ir_data(struct mceusb_dev *ir, int buf_len) ir->rem--; break; case CMD_HEADER: - /* decode mce packets of the form (84),AA,BB,CC,DD */ - /* IR data packets can span USB messages - rem */ ir->cmd = ir->buf_in[i]; if ((ir->cmd == MCE_CMD_PORT_IR) || ((ir->cmd & MCE_PORT_MASK) != MCE_COMMAND_IRDATA)) { + /* + * got PORT_SYS, PORT_IR, or unknown + * command response prefix + */ ir->parser_state = SUBCMD; continue; } + /* + * got IR data prefix (0x80 + num_bytes) + * decode MCE packets of the form {0x83, AA, BB, CC} + * IR data packets can span USB messages + */ ir->rem = (ir->cmd & MCE_PACKET_LENGTH_MASK); mceusb_dev_printdata(ir, ir->buf_in, buf_len, i, ir->rem + 1, false); @@ -1296,6 +1343,14 @@ static void mceusb_process_ir_data(struct mceusb_dev *ir, int buf_len) if (ir->parser_state != CMD_HEADER && !ir->rem) ir->parser_state = CMD_HEADER; } + + /* + * Accept IR data spanning multiple rx buffers. + * Reject MCE command response spanning multiple rx buffers. + */ + if (ir->parser_state != PARSE_IRDATA || !ir->rem) + ir->parser_state = CMD_HEADER; + if (event) { dev_dbg(ir->dev, "processed IR data"); ir_raw_event_handle(ir->rc); diff --git a/drivers/media/rc/rc-main.c b/drivers/media/rc/rc-main.c index 13da4c5c7d17..7741151606ef 100644 --- a/drivers/media/rc/rc-main.c +++ b/drivers/media/rc/rc-main.c @@ -1773,6 +1773,7 @@ static int rc_prepare_rx_device(struct rc_dev *dev) set_bit(MSC_SCAN, dev->input_dev->mscbit); /* Pointer/mouse events */ + set_bit(INPUT_PROP_POINTING_STICK, dev->input_dev->propbit); set_bit(EV_REL, dev->input_dev->evbit); set_bit(REL_X, dev->input_dev->relbit); set_bit(REL_Y, dev->input_dev->relbit); diff --git a/drivers/media/usb/b2c2/flexcop-usb.c b/drivers/media/usb/b2c2/flexcop-usb.c index 1826ff825c2e..039963a7765b 100644 --- a/drivers/media/usb/b2c2/flexcop-usb.c +++ b/drivers/media/usb/b2c2/flexcop-usb.c @@ -295,7 +295,7 @@ static int flexcop_usb_i2c_req(struct flexcop_i2c_adapter *i2c, mutex_unlock(&fc_usb->data_mutex); - return 0; + return ret; } /* actual bus specific access functions, @@ -504,7 +504,13 @@ static int flexcop_usb_transfer_init(struct flexcop_usb *fc_usb) static int flexcop_usb_init(struct flexcop_usb *fc_usb) { /* use the alternate setting with the larges buffer */ - usb_set_interface(fc_usb->udev,0,1); + int ret = usb_set_interface(fc_usb->udev, 0, 1); + + if (ret) { + err("set interface failed."); + return ret; + } + switch (fc_usb->udev->speed) { case USB_SPEED_LOW: err("cannot handle USB speed because it is too slow."); @@ -538,6 +544,9 @@ static int flexcop_usb_probe(struct usb_interface *intf, struct flexcop_device *fc = NULL; int ret; + if (intf->cur_altsetting->desc.bNumEndpoints < 1) + return -ENODEV; + if ((fc = flexcop_device_kmalloc(sizeof(struct flexcop_usb))) == NULL) { err("out of memory\n"); return -ENOMEM; diff --git a/drivers/media/usb/dvb-usb/af9005.c b/drivers/media/usb/dvb-usb/af9005.c index 02697d86e8c1..ac93e88d7038 100644 --- a/drivers/media/usb/dvb-usb/af9005.c +++ b/drivers/media/usb/dvb-usb/af9005.c @@ -976,8 +976,9 @@ static int af9005_identify_state(struct usb_device *udev, else if (reply == 0x02) *cold = 0; else - return -EIO; - deb_info("Identify state cold = %d\n", *cold); + ret = -EIO; + if (!ret) + deb_info("Identify state cold = %d\n", *cold); err: kfree(buf); diff --git a/drivers/media/usb/dvb-usb/cxusb.c b/drivers/media/usb/dvb-usb/cxusb.c index f02fa0a67aa4..fac19ec46089 100644 --- a/drivers/media/usb/dvb-usb/cxusb.c +++ b/drivers/media/usb/dvb-usb/cxusb.c @@ -521,7 +521,8 @@ static int cxusb_rc_query(struct dvb_usb_device *d) { u8 ircode[4]; - cxusb_ctrl_msg(d, CMD_GET_IR_CODE, NULL, 0, ircode, 4); + if (cxusb_ctrl_msg(d, CMD_GET_IR_CODE, NULL, 0, ircode, 4) < 0) + return 0; if (ircode[2] || ircode[3]) rc_keydown(d->rc_dev, RC_PROTO_NEC, diff --git a/drivers/media/usb/pulse8-cec/pulse8-cec.c b/drivers/media/usb/pulse8-cec/pulse8-cec.c index ac88ade94cda..59609556d969 100644 --- a/drivers/media/usb/pulse8-cec/pulse8-cec.c +++ b/drivers/media/usb/pulse8-cec/pulse8-cec.c @@ -116,6 +116,7 @@ struct pulse8 { unsigned int vers; struct completion cmd_done; struct work_struct work; + u8 work_result; struct delayed_work ping_eeprom_work; struct cec_msg rx_msg; u8 data[DATA_SIZE]; @@ -137,8 +138,10 @@ static void pulse8_irq_work_handler(struct work_struct *work) { struct pulse8 *pulse8 = container_of(work, struct pulse8, work); + u8 result = pulse8->work_result; - switch (pulse8->data[0] & 0x3f) { + pulse8->work_result = 0; + switch (result & 0x3f) { case MSGCODE_FRAME_DATA: cec_received_msg(pulse8->adap, &pulse8->rx_msg); break; @@ -172,12 +175,12 @@ static irqreturn_t pulse8_interrupt(struct serio *serio, unsigned char data, pulse8->escape = false; } else if (data == MSGEND) { struct cec_msg *msg = &pulse8->rx_msg; + u8 msgcode = pulse8->buf[0]; if (debug) dev_info(pulse8->dev, "received: %*ph\n", pulse8->idx, pulse8->buf); - pulse8->data[0] = pulse8->buf[0]; - switch (pulse8->buf[0] & 0x3f) { + switch (msgcode & 0x3f) { case MSGCODE_FRAME_START: msg->len = 1; msg->msg[0] = pulse8->buf[1]; @@ -186,14 +189,20 @@ static irqreturn_t pulse8_interrupt(struct serio *serio, unsigned char data, if (msg->len == CEC_MAX_MSG_SIZE) break; msg->msg[msg->len++] = pulse8->buf[1]; - if (pulse8->buf[0] & MSGCODE_FRAME_EOM) + if (msgcode & MSGCODE_FRAME_EOM) { + WARN_ON(pulse8->work_result); + pulse8->work_result = msgcode; schedule_work(&pulse8->work); + break; + } break; case MSGCODE_TRANSMIT_SUCCEEDED: case MSGCODE_TRANSMIT_FAILED_LINE: case MSGCODE_TRANSMIT_FAILED_ACK: case MSGCODE_TRANSMIT_FAILED_TIMEOUT_DATA: case MSGCODE_TRANSMIT_FAILED_TIMEOUT_LINE: + WARN_ON(pulse8->work_result); + pulse8->work_result = msgcode; schedule_work(&pulse8->work); break; case MSGCODE_HIGH_ERROR: diff --git a/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c b/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c index a34717eba409..eaa08c7999d4 100644 --- a/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c +++ b/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c @@ -898,8 +898,12 @@ static void pvr2_v4l2_internal_check(struct pvr2_channel *chp) pvr2_v4l2_dev_disassociate_parent(vp->dev_video); pvr2_v4l2_dev_disassociate_parent(vp->dev_radio); if (!list_empty(&vp->dev_video->devbase.fh_list) || - !list_empty(&vp->dev_radio->devbase.fh_list)) + (vp->dev_radio && + !list_empty(&vp->dev_radio->devbase.fh_list))) { + pvr2_trace(PVR2_TRACE_STRUCT, + "pvr2_v4l2 internal_check exit-empty id=%p", vp); return; + } pvr2_v4l2_destroy_no_lock(vp); } @@ -935,7 +939,8 @@ static int pvr2_v4l2_release(struct file *file) kfree(fhp); if (vp->channel.mc_head->disconnect_flag && list_empty(&vp->dev_video->devbase.fh_list) && - list_empty(&vp->dev_radio->devbase.fh_list)) { + (!vp->dev_radio || + list_empty(&vp->dev_radio->devbase.fh_list))) { pvr2_v4l2_destroy_no_lock(vp); } return 0; diff --git a/drivers/media/usb/usbvision/usbvision-video.c b/drivers/media/usb/usbvision/usbvision-video.c index cdc66adda755..93d36aab824f 100644 --- a/drivers/media/usb/usbvision/usbvision-video.c +++ b/drivers/media/usb/usbvision/usbvision-video.c @@ -314,6 +314,10 @@ static int usbvision_v4l2_open(struct file *file) if (mutex_lock_interruptible(&usbvision->v4l2_lock)) return -ERESTARTSYS; + if (usbvision->remove_pending) { + err_code = -ENODEV; + goto unlock; + } if (usbvision->user) { err_code = -EBUSY; } else { @@ -377,6 +381,7 @@ static int usbvision_v4l2_open(struct file *file) static int usbvision_v4l2_close(struct file *file) { struct usb_usbvision *usbvision = video_drvdata(file); + int r; PDEBUG(DBG_IO, "close"); @@ -391,9 +396,10 @@ static int usbvision_v4l2_close(struct file *file) usbvision_scratch_free(usbvision); usbvision->user--; + r = usbvision->remove_pending; mutex_unlock(&usbvision->v4l2_lock); - if (usbvision->remove_pending) { + if (r) { printk(KERN_INFO "%s: Final disconnect\n", __func__); usbvision_release(usbvision); return 0; @@ -453,6 +459,9 @@ static int vidioc_querycap(struct file *file, void *priv, { struct usb_usbvision *usbvision = video_drvdata(file); + if (!usbvision->dev) + return -ENODEV; + strscpy(vc->driver, "USBVision", sizeof(vc->driver)); strscpy(vc->card, usbvision_device_data[usbvision->dev_model].model_string, @@ -1061,6 +1070,11 @@ static int usbvision_radio_open(struct file *file) if (mutex_lock_interruptible(&usbvision->v4l2_lock)) return -ERESTARTSYS; + + if (usbvision->remove_pending) { + err_code = -ENODEV; + goto out; + } err_code = v4l2_fh_open(file); if (err_code) goto out; @@ -1093,21 +1107,24 @@ static int usbvision_radio_open(struct file *file) static int usbvision_radio_close(struct file *file) { struct usb_usbvision *usbvision = video_drvdata(file); + int r; PDEBUG(DBG_IO, ""); mutex_lock(&usbvision->v4l2_lock); /* Set packet size to 0 */ usbvision->iface_alt = 0; - usb_set_interface(usbvision->dev, usbvision->iface, - usbvision->iface_alt); + if (usbvision->dev) + usb_set_interface(usbvision->dev, usbvision->iface, + usbvision->iface_alt); usbvision_audio_off(usbvision); usbvision->radio = 0; usbvision->user--; + r = usbvision->remove_pending; mutex_unlock(&usbvision->v4l2_lock); - if (usbvision->remove_pending) { + if (r) { printk(KERN_INFO "%s: Final disconnect\n", __func__); v4l2_fh_release(file); usbvision_release(usbvision); @@ -1539,6 +1556,7 @@ static int usbvision_probe(struct usb_interface *intf, static void usbvision_disconnect(struct usb_interface *intf) { struct usb_usbvision *usbvision = to_usbvision(usb_get_intfdata(intf)); + int u; PDEBUG(DBG_PROBE, ""); @@ -1555,13 +1573,14 @@ static void usbvision_disconnect(struct usb_interface *intf) v4l2_device_disconnect(&usbvision->v4l2_dev); usbvision_i2c_unregister(usbvision); usbvision->remove_pending = 1; /* Now all ISO data will be ignored */ + u = usbvision->user; usb_put_dev(usbvision->dev); usbvision->dev = NULL; /* USB device is no more */ mutex_unlock(&usbvision->v4l2_lock); - if (usbvision->user) { + if (u) { printk(KERN_INFO "%s: In use, disconnect pending\n", __func__); wake_up_interruptible(&usbvision->wait_frame); diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c index 66ee168ddc7e..428235ca2635 100644 --- a/drivers/media/usb/uvc/uvc_driver.c +++ b/drivers/media/usb/uvc/uvc_driver.c @@ -2151,6 +2151,20 @@ static int uvc_probe(struct usb_interface *intf, sizeof(dev->name) - len); } + /* Initialize the media device. */ +#ifdef CONFIG_MEDIA_CONTROLLER + dev->mdev.dev = &intf->dev; + strscpy(dev->mdev.model, dev->name, sizeof(dev->mdev.model)); + if (udev->serial) + strscpy(dev->mdev.serial, udev->serial, + sizeof(dev->mdev.serial)); + usb_make_path(udev, dev->mdev.bus_info, sizeof(dev->mdev.bus_info)); + dev->mdev.hw_revision = le16_to_cpu(udev->descriptor.bcdDevice); + media_device_init(&dev->mdev); + + dev->vdev.mdev = &dev->mdev; +#endif + /* Parse the Video Class control descriptor. */ if (uvc_parse_control(dev) < 0) { uvc_trace(UVC_TRACE_PROBE, "Unable to parse UVC " @@ -2171,19 +2185,7 @@ static int uvc_probe(struct usb_interface *intf, "linux-uvc-devel mailing list.\n"); } - /* Initialize the media device and register the V4L2 device. */ -#ifdef CONFIG_MEDIA_CONTROLLER - dev->mdev.dev = &intf->dev; - strscpy(dev->mdev.model, dev->name, sizeof(dev->mdev.model)); - if (udev->serial) - strscpy(dev->mdev.serial, udev->serial, - sizeof(dev->mdev.serial)); - usb_make_path(udev, dev->mdev.bus_info, sizeof(dev->mdev.bus_info)); - dev->mdev.hw_revision = le16_to_cpu(udev->descriptor.bcdDevice); - media_device_init(&dev->mdev); - - dev->vdev.mdev = &dev->mdev; -#endif + /* Register the V4L2 device. */ if (v4l2_device_register(&intf->dev, &dev->vdev) < 0) goto error; diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c index 1d8f38824631..cd84dbbf6a89 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls.c +++ b/drivers/media/v4l2-core/v4l2-ctrls.c @@ -3144,6 +3144,7 @@ static void v4l2_ctrl_request_queue(struct media_request_object *obj) struct v4l2_ctrl_handler *prev_hdl = NULL; struct v4l2_ctrl_ref *ref_ctrl, *ref_ctrl_prev = NULL; + mutex_lock(main_hdl->lock); if (list_empty(&main_hdl->requests_queued)) goto queue; @@ -3175,18 +3176,22 @@ static void v4l2_ctrl_request_queue(struct media_request_object *obj) queue: list_add_tail(&hdl->requests_queued, &main_hdl->requests_queued); hdl->request_is_queued = true; + mutex_unlock(main_hdl->lock); } static void v4l2_ctrl_request_unbind(struct media_request_object *obj) { struct v4l2_ctrl_handler *hdl = container_of(obj, struct v4l2_ctrl_handler, req_obj); + struct v4l2_ctrl_handler *main_hdl = obj->priv; list_del_init(&hdl->requests); + mutex_lock(main_hdl->lock); if (hdl->request_is_queued) { list_del_init(&hdl->requests_queued); hdl->request_is_queued = false; } + mutex_unlock(main_hdl->lock); } static void v4l2_ctrl_request_release(struct media_request_object *obj) @@ -4128,9 +4133,11 @@ void v4l2_ctrl_request_complete(struct media_request *req, v4l2_ctrl_unlock(ctrl); } + mutex_lock(main_hdl->lock); WARN_ON(!hdl->request_is_queued); list_del_init(&hdl->requests_queued); hdl->request_is_queued = false; + mutex_unlock(main_hdl->lock); media_request_object_complete(obj); media_request_object_put(obj); } diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 51b912743f0f..21bb96ce4cd6 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1466,10 +1466,26 @@ static int v4l_enum_fmt(const struct v4l2_ioctl_ops *ops, return ret; } +static void v4l_pix_format_touch(struct v4l2_pix_format *p) +{ + /* + * The v4l2_pix_format structure contains fields that make no sense for + * touch. Set them to default values in this case. + */ + + p->field = V4L2_FIELD_NONE; + p->colorspace = V4L2_COLORSPACE_RAW; + p->flags = 0; + p->ycbcr_enc = 0; + p->quantization = 0; + p->xfer_func = 0; +} + static int v4l_g_fmt(const struct v4l2_ioctl_ops *ops, struct file *file, void *fh, void *arg) { struct v4l2_format *p = arg; + struct video_device *vfd = video_devdata(file); int ret = check_fmt(file, p->type); if (ret) @@ -1507,6 +1523,8 @@ static int v4l_g_fmt(const struct v4l2_ioctl_ops *ops, ret = ops->vidioc_g_fmt_vid_cap(file, fh, arg); /* just in case the driver zeroed it again */ p->fmt.pix.priv = V4L2_PIX_FMT_PRIV_MAGIC; + if (vfd->vfl_type == VFL_TYPE_TOUCH) + v4l_pix_format_touch(&p->fmt.pix); return ret; case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE: return ops->vidioc_g_fmt_vid_cap_mplane(file, fh, arg); @@ -1544,21 +1562,6 @@ static int v4l_g_fmt(const struct v4l2_ioctl_ops *ops, return -EINVAL; } -static void v4l_pix_format_touch(struct v4l2_pix_format *p) -{ - /* - * The v4l2_pix_format structure contains fields that make no sense for - * touch. Set them to default values in this case. - */ - - p->field = V4L2_FIELD_NONE; - p->colorspace = V4L2_COLORSPACE_RAW; - p->flags = 0; - p->ycbcr_enc = 0; - p->quantization = 0; - p->xfer_func = 0; -} - static int v4l_s_fmt(const struct v4l2_ioctl_ops *ops, struct file *file, void *fh, void *arg) { diff --git a/drivers/memory/mtk-smi.c b/drivers/memory/mtk-smi.c index 439d7d886873..a113e811faab 100644 --- a/drivers/memory/mtk-smi.c +++ b/drivers/memory/mtk-smi.c @@ -366,6 +366,8 @@ static int __maybe_unused mtk_smi_larb_suspend(struct device *dev) static const struct dev_pm_ops smi_larb_pm_ops = { SET_RUNTIME_PM_OPS(mtk_smi_larb_suspend, mtk_smi_larb_resume, NULL) + SET_LATE_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, + pm_runtime_force_resume) }; static struct platform_driver mtk_smi_larb_driver = { @@ -507,6 +509,8 @@ static int __maybe_unused mtk_smi_common_suspend(struct device *dev) static const struct dev_pm_ops smi_common_pm_ops = { SET_RUNTIME_PM_OPS(mtk_smi_common_suspend, mtk_smi_common_resume, NULL) + SET_LATE_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, + pm_runtime_force_resume) }; static struct platform_driver mtk_smi_common_driver = { diff --git a/drivers/mfd/intel-lpss.c b/drivers/mfd/intel-lpss.c index bfe4ff337581..b0f0781a6b9c 100644 --- a/drivers/mfd/intel-lpss.c +++ b/drivers/mfd/intel-lpss.c @@ -384,7 +384,7 @@ int intel_lpss_probe(struct device *dev, if (!lpss) return -ENOMEM; - lpss->priv = devm_ioremap(dev, info->mem->start + LPSS_PRIV_OFFSET, + lpss->priv = devm_ioremap_uc(dev, info->mem->start + LPSS_PRIV_OFFSET, LPSS_PRIV_SIZE); if (!lpss->priv) return -ENOMEM; diff --git a/drivers/misc/enclosure.c b/drivers/misc/enclosure.c index 6d27ccfe0680..3c2d405bc79b 100644 --- a/drivers/misc/enclosure.c +++ b/drivers/misc/enclosure.c @@ -406,10 +406,9 @@ int enclosure_remove_device(struct enclosure_device *edev, struct device *dev) cdev = &edev->component[i]; if (cdev->dev == dev) { enclosure_remove_links(cdev); - device_del(&cdev->cdev); put_device(dev); cdev->dev = NULL; - return device_add(&cdev->cdev); + return 0; } } return -ENODEV; diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index 1b1a794d639d..842f2210dc7e 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -1430,8 +1430,8 @@ static int fastrpc_rpmsg_probe(struct rpmsg_device *rpdev) return -ENOMEM; data->miscdev.minor = MISC_DYNAMIC_MINOR; - data->miscdev.name = kasprintf(GFP_KERNEL, "fastrpc-%s", - domains[domain_id]); + data->miscdev.name = devm_kasprintf(rdev, GFP_KERNEL, "fastrpc-%s", + domains[domain_id]); data->miscdev.fops = &fastrpc_fops; err = misc_register(&data->miscdev); if (err) diff --git a/drivers/misc/habanalabs/command_submission.c b/drivers/misc/habanalabs/command_submission.c index a9ac045dcfde..447f307ef4d6 100644 --- a/drivers/misc/habanalabs/command_submission.c +++ b/drivers/misc/habanalabs/command_submission.c @@ -777,8 +777,9 @@ int hl_cs_wait_ioctl(struct hl_fpriv *hpriv, void *data) memset(args, 0, sizeof(*args)); if (rc < 0) { - dev_err(hdev->dev, "Error %ld on waiting for CS handle %llu\n", - rc, seq); + dev_err_ratelimited(hdev->dev, + "Error %ld on waiting for CS handle %llu\n", + rc, seq); if (rc == -ERESTARTSYS) { args->out.status = HL_WAIT_CS_STATUS_INTERRUPTED; rc = -EINTR; diff --git a/drivers/misc/habanalabs/context.c b/drivers/misc/habanalabs/context.c index 17db7b3dfb4c..2df6fb87e7ff 100644 --- a/drivers/misc/habanalabs/context.c +++ b/drivers/misc/habanalabs/context.c @@ -176,7 +176,7 @@ struct dma_fence *hl_ctx_get_fence(struct hl_ctx *ctx, u64 seq) spin_lock(&ctx->cs_lock); if (seq >= ctx->cs_sequence) { - dev_notice(hdev->dev, + dev_notice_ratelimited(hdev->dev, "Can't wait on seq %llu because current CS is at seq %llu\n", seq, ctx->cs_sequence); spin_unlock(&ctx->cs_lock); diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 6fba14b81f90..fe3574a83b7c 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -2171,7 +2171,7 @@ static int goya_push_linux_to_device(struct hl_device *hdev) static int goya_pldm_init_cpu(struct hl_device *hdev) { - u32 val, unit_rst_val; + u32 unit_rst_val; int rc; /* Must initialize SRAM scrambler before pushing u-boot to SRAM */ @@ -2179,14 +2179,14 @@ static int goya_pldm_init_cpu(struct hl_device *hdev) /* Put ARM cores into reset */ WREG32(mmCPU_CA53_CFG_ARM_RST_CONTROL, CPU_RESET_ASSERT); - val = RREG32(mmCPU_CA53_CFG_ARM_RST_CONTROL); + RREG32(mmCPU_CA53_CFG_ARM_RST_CONTROL); /* Reset the CA53 MACRO */ unit_rst_val = RREG32(mmPSOC_GLOBAL_CONF_UNIT_RST_N); WREG32(mmPSOC_GLOBAL_CONF_UNIT_RST_N, CA53_RESET); - val = RREG32(mmPSOC_GLOBAL_CONF_UNIT_RST_N); + RREG32(mmPSOC_GLOBAL_CONF_UNIT_RST_N); WREG32(mmPSOC_GLOBAL_CONF_UNIT_RST_N, unit_rst_val); - val = RREG32(mmPSOC_GLOBAL_CONF_UNIT_RST_N); + RREG32(mmPSOC_GLOBAL_CONF_UNIT_RST_N); rc = goya_push_uboot_to_device(hdev); if (rc) @@ -2207,7 +2207,7 @@ static int goya_pldm_init_cpu(struct hl_device *hdev) /* Release ARM core 0 from reset */ WREG32(mmCPU_CA53_CFG_ARM_RST_CONTROL, CPU_RESET_CORE0_DEASSERT); - val = RREG32(mmCPU_CA53_CFG_ARM_RST_CONTROL); + RREG32(mmCPU_CA53_CFG_ARM_RST_CONTROL); return 0; } @@ -2475,13 +2475,12 @@ int goya_mmu_init(struct hl_device *hdev) static int goya_hw_init(struct hl_device *hdev) { struct asic_fixed_properties *prop = &hdev->asic_prop; - u32 val; int rc; dev_info(hdev->dev, "Starting initialization of H/W\n"); /* Perform read from the device to make sure device is up */ - val = RREG32(mmPCIE_DBI_DEVICE_ID_VENDOR_ID_REG); + RREG32(mmPCIE_DBI_DEVICE_ID_VENDOR_ID_REG); /* * Let's mark in the H/W that we have reached this point. We check @@ -2533,7 +2532,7 @@ static int goya_hw_init(struct hl_device *hdev) goto disable_queues; /* Perform read from the device to flush all MSI-X configuration */ - val = RREG32(mmPCIE_DBI_DEVICE_ID_VENDOR_ID_REG); + RREG32(mmPCIE_DBI_DEVICE_ID_VENDOR_ID_REG); return 0; diff --git a/drivers/misc/habanalabs/memory.c b/drivers/misc/habanalabs/memory.c index 365fb0cb8dff..22566b75ca50 100644 --- a/drivers/misc/habanalabs/memory.c +++ b/drivers/misc/habanalabs/memory.c @@ -965,17 +965,19 @@ static int map_device_va(struct hl_ctx *ctx, struct hl_mem_in *args, * * @ctx : current context * @vaddr : device virtual address to unmap + * @ctx_free : true if in context free flow, false otherwise. * * This function does the following: * - Unmap the physical pages related to the given virtual address * - return the device virtual block to the virtual block list */ -static int unmap_device_va(struct hl_ctx *ctx, u64 vaddr) +static int unmap_device_va(struct hl_ctx *ctx, u64 vaddr, bool ctx_free) { struct hl_device *hdev = ctx->hdev; struct hl_vm_phys_pg_pack *phys_pg_pack = NULL; struct hl_vm_hash_node *hnode = NULL; struct hl_userptr *userptr = NULL; + struct hl_va_range *va_range; enum vm_type_t *vm_type; u64 next_vaddr, i; u32 page_size; @@ -1003,6 +1005,7 @@ static int unmap_device_va(struct hl_ctx *ctx, u64 vaddr) if (*vm_type == VM_TYPE_USERPTR) { is_userptr = true; + va_range = &ctx->host_va_range; userptr = hnode->ptr; rc = init_phys_pg_pack_from_userptr(ctx, userptr, &phys_pg_pack); @@ -1014,6 +1017,7 @@ static int unmap_device_va(struct hl_ctx *ctx, u64 vaddr) } } else if (*vm_type == VM_TYPE_PHYS_PACK) { is_userptr = false; + va_range = &ctx->dram_va_range; phys_pg_pack = hnode->ptr; } else { dev_warn(hdev->dev, @@ -1052,12 +1056,18 @@ static int unmap_device_va(struct hl_ctx *ctx, u64 vaddr) mutex_unlock(&ctx->mmu_lock); - if (add_va_block(hdev, - is_userptr ? &ctx->host_va_range : &ctx->dram_va_range, - vaddr, - vaddr + phys_pg_pack->total_size - 1)) - dev_warn(hdev->dev, "add va block failed for vaddr: 0x%llx\n", - vaddr); + /* + * No point in maintaining the free VA block list if the context is + * closing as the list will be freed anyway + */ + if (!ctx_free) { + rc = add_va_block(hdev, va_range, vaddr, + vaddr + phys_pg_pack->total_size - 1); + if (rc) + dev_warn(hdev->dev, + "add va block failed for vaddr: 0x%llx\n", + vaddr); + } atomic_dec(&phys_pg_pack->mapping_cnt); kfree(hnode); @@ -1189,8 +1199,8 @@ int hl_mem_ioctl(struct hl_fpriv *hpriv, void *data) break; case HL_MEM_OP_UNMAP: - rc = unmap_device_va(ctx, - args->in.unmap.device_virt_addr); + rc = unmap_device_va(ctx, args->in.unmap.device_virt_addr, + false); break; default: @@ -1620,7 +1630,7 @@ void hl_vm_ctx_fini(struct hl_ctx *ctx) dev_dbg(hdev->dev, "hl_mem_hash_node of vaddr 0x%llx of asid %d is still alive\n", hnode->vaddr, ctx->asid); - unmap_device_va(ctx, hnode->vaddr); + unmap_device_va(ctx, hnode->vaddr, true); } spin_lock(&vm->idr_lock); diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c index 985bd4fd3328..53bb394ccba6 100644 --- a/drivers/misc/mei/bus.c +++ b/drivers/misc/mei/bus.c @@ -873,15 +873,16 @@ static const struct device_type mei_cl_device_type = { /** * mei_cl_bus_set_name - set device name for me client device + * - + * Example: 0000:00:16.0-55213584-9a29-4916-badf-0fb7ed682aeb * * @cldev: me client device */ static inline void mei_cl_bus_set_name(struct mei_cl_device *cldev) { - dev_set_name(&cldev->dev, "mei:%s:%pUl:%02X", - cldev->name, - mei_me_cl_uuid(cldev->me_cl), - mei_me_cl_ver(cldev->me_cl)); + dev_set_name(&cldev->dev, "%s-%pUl", + dev_name(cldev->bus->dev), + mei_me_cl_uuid(cldev->me_cl)); } /** diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h index c09f8bb49495..b359f06f05e7 100644 --- a/drivers/misc/mei/hw-me-regs.h +++ b/drivers/misc/mei/hw-me-regs.h @@ -81,6 +81,7 @@ #define MEI_DEV_ID_CMP_LP 0x02e0 /* Comet Point LP */ #define MEI_DEV_ID_CMP_LP_3 0x02e4 /* Comet Point LP 3 (iTouch) */ +#define MEI_DEV_ID_CMP_V 0xA3BA /* Comet Point Lake V */ #define MEI_DEV_ID_ICP_LP 0x34E0 /* Ice Lake Point LP */ diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index 3dca63eddaa0..ce43415a536c 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -98,6 +98,7 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_CMP_LP, MEI_ME_PCH12_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_CMP_LP_3, MEI_ME_PCH8_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_CMP_V, MEI_ME_PCH12_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_ICP_LP, MEI_ME_PCH12_CFG)}, diff --git a/drivers/misc/ocxl/context.c b/drivers/misc/ocxl/context.c index 994563a078eb..de8a66b9d76b 100644 --- a/drivers/misc/ocxl/context.c +++ b/drivers/misc/ocxl/context.c @@ -10,18 +10,17 @@ int ocxl_context_alloc(struct ocxl_context **context, struct ocxl_afu *afu, int pasid; struct ocxl_context *ctx; - *context = kzalloc(sizeof(struct ocxl_context), GFP_KERNEL); - if (!*context) + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) return -ENOMEM; - ctx = *context; - ctx->afu = afu; mutex_lock(&afu->contexts_lock); pasid = idr_alloc(&afu->contexts_idr, ctx, afu->pasid_base, afu->pasid_base + afu->pasid_max, GFP_KERNEL); if (pasid < 0) { mutex_unlock(&afu->contexts_lock); + kfree(ctx); return pasid; } afu->pasid_count++; @@ -43,6 +42,7 @@ int ocxl_context_alloc(struct ocxl_context **context, struct ocxl_afu *afu, * duration of the life of the context */ ocxl_afu_get(afu); + *context = ctx; return 0; } EXPORT_SYMBOL_GPL(ocxl_context_alloc); diff --git a/drivers/misc/ocxl/file.c b/drivers/misc/ocxl/file.c index 2870c25da166..4d1b44de1492 100644 --- a/drivers/misc/ocxl/file.c +++ b/drivers/misc/ocxl/file.c @@ -18,18 +18,15 @@ static struct class *ocxl_class; static struct mutex minors_idr_lock; static struct idr minors_idr; -static struct ocxl_file_info *find_file_info(dev_t devno) +static struct ocxl_file_info *find_and_get_file_info(dev_t devno) { struct ocxl_file_info *info; - /* - * We don't declare an RCU critical section here, as our AFU - * is protected by a reference counter on the device. By the time the - * info reference is removed from the idr, the ref count of - * the device is already at 0, so no user API will access that AFU and - * this function can't return it. - */ + mutex_lock(&minors_idr_lock); info = idr_find(&minors_idr, MINOR(devno)); + if (info) + get_device(&info->dev); + mutex_unlock(&minors_idr_lock); return info; } @@ -58,14 +55,16 @@ static int afu_open(struct inode *inode, struct file *file) pr_debug("%s for device %x\n", __func__, inode->i_rdev); - info = find_file_info(inode->i_rdev); + info = find_and_get_file_info(inode->i_rdev); if (!info) return -ENODEV; rc = ocxl_context_alloc(&ctx, info->afu, inode->i_mapping); - if (rc) + if (rc) { + put_device(&info->dev); return rc; - + } + put_device(&info->dev); file->private_data = ctx; return 0; } @@ -487,7 +486,6 @@ static void info_release(struct device *dev) { struct ocxl_file_info *info = container_of(dev, struct ocxl_file_info, dev); - free_minor(info); ocxl_afu_put(info->afu); kfree(info); } @@ -577,6 +575,7 @@ void ocxl_file_unregister_afu(struct ocxl_afu *afu) ocxl_file_make_invisible(info); ocxl_sysfs_unregister_afu(info); + free_minor(info); device_unregister(&info->dev); } diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 2c71a434c915..95b41c0891d0 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -408,38 +408,6 @@ static int mmc_blk_ioctl_copy_to_user(struct mmc_ioc_cmd __user *ic_ptr, return 0; } -static int ioctl_rpmb_card_status_poll(struct mmc_card *card, u32 *status, - u32 retries_max) -{ - int err; - u32 retry_count = 0; - - if (!status || !retries_max) - return -EINVAL; - - do { - err = __mmc_send_status(card, status, 5); - if (err) - break; - - if (!R1_STATUS(*status) && - (R1_CURRENT_STATE(*status) != R1_STATE_PRG)) - break; /* RPMB programming operation complete */ - - /* - * Rechedule to give the MMC device a chance to continue - * processing the previous command without being polled too - * frequently. - */ - usleep_range(1000, 5000); - } while (++retry_count < retries_max); - - if (retry_count == retries_max) - err = -EPERM; - - return err; -} - static int ioctl_do_sanitize(struct mmc_card *card) { int err; @@ -468,6 +436,58 @@ static int ioctl_do_sanitize(struct mmc_card *card) return err; } +static inline bool mmc_blk_in_tran_state(u32 status) +{ + /* + * Some cards mishandle the status bits, so make sure to check both the + * busy indication and the card state. + */ + return status & R1_READY_FOR_DATA && + (R1_CURRENT_STATE(status) == R1_STATE_TRAN); +} + +static int card_busy_detect(struct mmc_card *card, unsigned int timeout_ms, + u32 *resp_errs) +{ + unsigned long timeout = jiffies + msecs_to_jiffies(timeout_ms); + int err = 0; + u32 status; + + do { + bool done = time_after(jiffies, timeout); + + err = __mmc_send_status(card, &status, 5); + if (err) { + dev_err(mmc_dev(card->host), + "error %d requesting status\n", err); + return err; + } + + /* Accumulate any response error bits seen */ + if (resp_errs) + *resp_errs |= status; + + /* + * Timeout if the device never becomes ready for data and never + * leaves the program state. + */ + if (done) { + dev_err(mmc_dev(card->host), + "Card stuck in wrong state! %s status: %#x\n", + __func__, status); + return -ETIMEDOUT; + } + + /* + * Some cards mishandle the status bits, + * so make sure to check both the busy + * indication and the card state. + */ + } while (!mmc_blk_in_tran_state(status)); + + return err; +} + static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, struct mmc_blk_ioc_data *idata) { @@ -477,7 +497,6 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, struct scatterlist sg; int err; unsigned int target_part; - u32 status = 0; if (!card || !md || !idata) return -EINVAL; @@ -611,16 +630,12 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, memcpy(&(idata->ic.response), cmd.resp, sizeof(cmd.resp)); - if (idata->rpmb) { + if (idata->rpmb || (cmd.flags & MMC_RSP_R1B)) { /* - * Ensure RPMB command has completed by polling CMD13 + * Ensure RPMB/R1B command has completed by polling CMD13 * "Send Status". */ - err = ioctl_rpmb_card_status_poll(card, &status, 5); - if (err) - dev_err(mmc_dev(card->host), - "%s: Card Status=0x%08X, error %d\n", - __func__, status, err); + err = card_busy_detect(card, MMC_BLK_TIMEOUT_MS, NULL); } return err; @@ -970,58 +985,6 @@ static unsigned int mmc_blk_data_timeout_ms(struct mmc_host *host, return ms; } -static inline bool mmc_blk_in_tran_state(u32 status) -{ - /* - * Some cards mishandle the status bits, so make sure to check both the - * busy indication and the card state. - */ - return status & R1_READY_FOR_DATA && - (R1_CURRENT_STATE(status) == R1_STATE_TRAN); -} - -static int card_busy_detect(struct mmc_card *card, unsigned int timeout_ms, - struct request *req, u32 *resp_errs) -{ - unsigned long timeout = jiffies + msecs_to_jiffies(timeout_ms); - int err = 0; - u32 status; - - do { - bool done = time_after(jiffies, timeout); - - err = __mmc_send_status(card, &status, 5); - if (err) { - pr_err("%s: error %d requesting status\n", - req->rq_disk->disk_name, err); - return err; - } - - /* Accumulate any response error bits seen */ - if (resp_errs) - *resp_errs |= status; - - /* - * Timeout if the device never becomes ready for data and never - * leaves the program state. - */ - if (done) { - pr_err("%s: Card stuck in wrong state! %s %s status: %#x\n", - mmc_hostname(card->host), - req->rq_disk->disk_name, __func__, status); - return -ETIMEDOUT; - } - - /* - * Some cards mishandle the status bits, - * so make sure to check both the busy - * indication and the card state. - */ - } while (!mmc_blk_in_tran_state(status)); - - return err; -} - static int mmc_blk_reset(struct mmc_blk_data *md, struct mmc_host *host, int type) { @@ -1671,7 +1634,7 @@ static int mmc_blk_fix_state(struct mmc_card *card, struct request *req) mmc_blk_send_stop(card, timeout); - err = card_busy_detect(card, timeout, req, NULL); + err = card_busy_detect(card, timeout, NULL); mmc_retune_release(card->host); @@ -1895,7 +1858,7 @@ static int mmc_blk_card_busy(struct mmc_card *card, struct request *req) if (mmc_host_is_spi(card->host) || rq_data_dir(req) == READ) return 0; - err = card_busy_detect(card, MMC_BLK_TIMEOUT_MS, req, &status); + err = card_busy_detect(card, MMC_BLK_TIMEOUT_MS, &status); /* * Do not assume data transferred correctly if there are any error bits diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index 221127324709..abf8f5eb0a1c 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -1469,8 +1469,7 @@ void mmc_detach_bus(struct mmc_host *host) mmc_bus_put(host); } -static void _mmc_detect_change(struct mmc_host *host, unsigned long delay, - bool cd_irq) +void _mmc_detect_change(struct mmc_host *host, unsigned long delay, bool cd_irq) { /* * If the device is configured as wakeup, we prevent a new sleep for @@ -2129,7 +2128,7 @@ int mmc_hw_reset(struct mmc_host *host) ret = host->bus_ops->hw_reset(host); mmc_bus_put(host); - if (ret) + if (ret < 0) pr_warn("%s: tried to HW reset card, got error %d\n", mmc_hostname(host), ret); @@ -2297,11 +2296,8 @@ void mmc_rescan(struct work_struct *work) mmc_bus_get(host); - /* - * if there is a _removable_ card registered, check whether it is - * still present - */ - if (host->bus_ops && !host->bus_dead && mmc_card_is_removable(host)) + /* Verify a registered card to be functional, else remove it. */ + if (host->bus_ops && !host->bus_dead) host->bus_ops->detect(host); host->detect_change = 0; diff --git a/drivers/mmc/core/core.h b/drivers/mmc/core/core.h index 328c78dbee66..575ac0257af2 100644 --- a/drivers/mmc/core/core.h +++ b/drivers/mmc/core/core.h @@ -70,6 +70,8 @@ void mmc_rescan(struct work_struct *work); void mmc_start_host(struct mmc_host *host); void mmc_stop_host(struct mmc_host *host); +void _mmc_detect_change(struct mmc_host *host, unsigned long delay, + bool cd_irq); int _mmc_detect_card_removed(struct mmc_host *host); int mmc_detect_card_removed(struct mmc_host *host); diff --git a/drivers/mmc/core/sdio.c b/drivers/mmc/core/sdio.c index 26cabd53ddc5..ebb387aa5158 100644 --- a/drivers/mmc/core/sdio.c +++ b/drivers/mmc/core/sdio.c @@ -1048,9 +1048,35 @@ static int mmc_sdio_runtime_resume(struct mmc_host *host) return ret; } +/* + * SDIO HW reset + * + * Returns 0 if the HW reset was executed synchronously, returns 1 if the HW + * reset was asynchronously scheduled, else a negative error code. + */ static int mmc_sdio_hw_reset(struct mmc_host *host) { - mmc_power_cycle(host, host->card->ocr); + struct mmc_card *card = host->card; + + /* + * In case the card is shared among multiple func drivers, reset the + * card through a rescan work. In this way it will be removed and + * re-detected, thus all func drivers becomes informed about it. + */ + if (atomic_read(&card->sdio_funcs_probed) > 1) { + if (mmc_card_removed(card)) + return 1; + host->rescan_entered = 0; + mmc_card_set_removed(card); + _mmc_detect_change(host, 0, false); + return 1; + } + + /* + * A single func driver has been probed, then let's skip the heavy + * hotplug dance above and execute the reset immediately. + */ + mmc_power_cycle(host, card->ocr); return mmc_sdio_reinit_card(host); } diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c index 2963e6542958..3cc928282af7 100644 --- a/drivers/mmc/core/sdio_bus.c +++ b/drivers/mmc/core/sdio_bus.c @@ -138,6 +138,8 @@ static int sdio_bus_probe(struct device *dev) if (ret) return ret; + atomic_inc(&func->card->sdio_funcs_probed); + /* Unbound SDIO functions are always suspended. * During probe, the function is set active and the usage count * is incremented. If the driver supports runtime PM, @@ -153,7 +155,10 @@ static int sdio_bus_probe(struct device *dev) /* Set the default block size so the driver is sure it's something * sensible. */ sdio_claim_host(func); - ret = sdio_set_block_size(func, 0); + if (mmc_card_removed(func->card)) + ret = -ENOMEDIUM; + else + ret = sdio_set_block_size(func, 0); sdio_release_host(func); if (ret) goto disable_runtimepm; @@ -165,6 +170,7 @@ static int sdio_bus_probe(struct device *dev) return 0; disable_runtimepm: + atomic_dec(&func->card->sdio_funcs_probed); if (func->card->host->caps & MMC_CAP_POWER_OFF_CARD) pm_runtime_put_noidle(dev); dev_pm_domain_detach(dev, false); @@ -181,6 +187,7 @@ static int sdio_bus_remove(struct device *dev) pm_runtime_get_sync(dev); drv->remove(func); + atomic_dec(&func->card->sdio_funcs_probed); if (func->irq_handler) { pr_warn("WARNING: driver %s did not remove its interrupt handler!\n", diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c index 189e42674d85..010fe29a4888 100644 --- a/drivers/mmc/host/mtk-sd.c +++ b/drivers/mmc/host/mtk-sd.c @@ -228,6 +228,7 @@ #define MSDC_PATCH_BIT_SPCPUSH (0x1 << 29) /* RW */ #define MSDC_PATCH_BIT_DECRCTMO (0x1 << 30) /* RW */ +#define MSDC_PATCH_BIT1_CMDTA (0x7 << 3) /* RW */ #define MSDC_PATCH_BIT1_STOP_DLY (0xf << 8) /* RW */ #define MSDC_PATCH_BIT2_CFGRESP (0x1 << 15) /* RW */ @@ -1881,6 +1882,7 @@ static int hs400_tune_response(struct mmc_host *mmc, u32 opcode) /* select EMMC50 PAD CMD tune */ sdr_set_bits(host->base + PAD_CMD_TUNE, BIT(0)); + sdr_set_field(host->base + MSDC_PATCH_BIT1, MSDC_PATCH_BIT1_CMDTA, 2); if (mmc->ios.timing == MMC_TIMING_MMC_HS200 || mmc->ios.timing == MMC_TIMING_UHS_SDR104) diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c index 952fa4063ff8..d0df054b0b47 100644 --- a/drivers/mmc/host/omap_hsmmc.c +++ b/drivers/mmc/host/omap_hsmmc.c @@ -1512,6 +1512,36 @@ static void omap_hsmmc_init_card(struct mmc_host *mmc, struct mmc_card *card) if (mmc_pdata(host)->init_card) mmc_pdata(host)->init_card(card); + else if (card->type == MMC_TYPE_SDIO || + card->type == MMC_TYPE_SD_COMBO) { + struct device_node *np = mmc_dev(mmc)->of_node; + + /* + * REVISIT: should be moved to sdio core and made more + * general e.g. by expanding the DT bindings of child nodes + * to provide a mechanism to provide this information: + * Documentation/devicetree/bindings/mmc/mmc-card.txt + */ + + np = of_get_compatible_child(np, "ti,wl1251"); + if (np) { + /* + * We have TI wl1251 attached to MMC3. Pass this + * information to the SDIO core because it can't be + * probed by normal methods. + */ + + dev_info(host->dev, "found wl1251\n"); + card->quirks |= MMC_QUIRK_NONSTD_SDIO; + card->cccr.wide_bus = 1; + card->cis.vendor = 0x104c; + card->cis.device = 0x9066; + card->cis.blksize = 512; + card->cis.max_dtr = 24000000; + card->ocr = 0x80; + of_node_put(np); + } + } } static void omap_hsmmc_enable_sdio_irq(struct mmc_host *mmc, int enable) diff --git a/drivers/mmc/host/sdhci-esdhc.h b/drivers/mmc/host/sdhci-esdhc.h index 57b582bf73d9..9289bb4d633e 100644 --- a/drivers/mmc/host/sdhci-esdhc.h +++ b/drivers/mmc/host/sdhci-esdhc.h @@ -51,6 +51,11 @@ #define ESDHC_CLOCK_HCKEN 0x00000002 #define ESDHC_CLOCK_IPGEN 0x00000001 +/* System Control 2 Register */ +#define ESDHC_SYSTEM_CONTROL_2 0x3c +#define ESDHC_SMPCLKSEL 0x00800000 +#define ESDHC_EXTN 0x00400000 + /* Host Controller Capabilities Register 2 */ #define ESDHC_CAPABILITIES_1 0x114 @@ -59,7 +64,16 @@ #define ESDHC_HS400_WNDW_ADJUST 0x00000040 #define ESDHC_HS400_MODE 0x00000010 #define ESDHC_TB_EN 0x00000004 +#define ESDHC_TB_MODE_MASK 0x00000003 +#define ESDHC_TB_MODE_SW 0x00000003 +#define ESDHC_TB_MODE_3 0x00000002 + +#define ESDHC_TBSTAT 0x124 + #define ESDHC_TBPTR 0x128 +#define ESDHC_WNDW_STRT_PTR_SHIFT 8 +#define ESDHC_WNDW_STRT_PTR_MASK (0x7f << 8) +#define ESDHC_WNDW_END_PTR_MASK 0x7f /* SD Clock Control Register */ #define ESDHC_SDCLKCTL 0x144 diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c index b75c82d8d6c1..3d0bb5e2e09b 100644 --- a/drivers/mmc/host/sdhci-msm.c +++ b/drivers/mmc/host/sdhci-msm.c @@ -99,7 +99,7 @@ #define CORE_PWRSAVE_DLL BIT(3) -#define DDR_CONFIG_POR_VAL 0x80040853 +#define DDR_CONFIG_POR_VAL 0x80040873 #define INVALID_TUNING_PHASE -1 @@ -148,8 +148,9 @@ struct sdhci_msm_offset { u32 core_ddr_200_cfg; u32 core_vendor_spec3; u32 core_dll_config_2; + u32 core_dll_config_3; + u32 core_ddr_config_old; /* Applicable to sdcc minor ver < 0x49 */ u32 core_ddr_config; - u32 core_ddr_config_2; }; static const struct sdhci_msm_offset sdhci_msm_v5_offset = { @@ -177,8 +178,8 @@ static const struct sdhci_msm_offset sdhci_msm_v5_offset = { .core_ddr_200_cfg = 0x224, .core_vendor_spec3 = 0x250, .core_dll_config_2 = 0x254, - .core_ddr_config = 0x258, - .core_ddr_config_2 = 0x25c, + .core_dll_config_3 = 0x258, + .core_ddr_config = 0x25c, }; static const struct sdhci_msm_offset sdhci_msm_mci_offset = { @@ -207,8 +208,8 @@ static const struct sdhci_msm_offset sdhci_msm_mci_offset = { .core_ddr_200_cfg = 0x184, .core_vendor_spec3 = 0x1b0, .core_dll_config_2 = 0x1b4, - .core_ddr_config = 0x1b8, - .core_ddr_config_2 = 0x1bc, + .core_ddr_config_old = 0x1b8, + .core_ddr_config = 0x1bc, }; struct sdhci_msm_variant_ops { @@ -253,6 +254,7 @@ struct sdhci_msm_host { const struct sdhci_msm_offset *offset; bool use_cdr; u32 transfer_mode; + bool updated_ddr_cfg; }; static const struct sdhci_msm_offset *sdhci_priv_msm_offset(struct sdhci_host *host) @@ -924,8 +926,10 @@ static int sdhci_msm_cdclp533_calibration(struct sdhci_host *host) static int sdhci_msm_cm_dll_sdc4_calibration(struct sdhci_host *host) { struct mmc_host *mmc = host->mmc; - u32 dll_status, config; + u32 dll_status, config, ddr_cfg_offset; int ret; + struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); + struct sdhci_msm_host *msm_host = sdhci_pltfm_priv(pltfm_host); const struct sdhci_msm_offset *msm_offset = sdhci_priv_msm_offset(host); @@ -938,8 +942,11 @@ static int sdhci_msm_cm_dll_sdc4_calibration(struct sdhci_host *host) * bootloaders. In the future, if this changes, then the desired * values will need to be programmed appropriately. */ - writel_relaxed(DDR_CONFIG_POR_VAL, host->ioaddr + - msm_offset->core_ddr_config); + if (msm_host->updated_ddr_cfg) + ddr_cfg_offset = msm_offset->core_ddr_config; + else + ddr_cfg_offset = msm_offset->core_ddr_config_old; + writel_relaxed(DDR_CONFIG_POR_VAL, host->ioaddr + ddr_cfg_offset); if (mmc->ios.enhanced_strobe) { config = readl_relaxed(host->ioaddr + @@ -1899,6 +1906,9 @@ static int sdhci_msm_probe(struct platform_device *pdev) msm_offset->core_vendor_spec_capabilities0); } + if (core_major == 1 && core_minor >= 0x49) + msm_host->updated_ddr_cfg = true; + /* * Power on reset state may trigger power irq if previous status of * PWRCTL was either BUS_ON or IO_HIGH_V. So before enabling pwr irq diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c index 1d1953dfc54b..fcfb50f84c8b 100644 --- a/drivers/mmc/host/sdhci-of-esdhc.c +++ b/drivers/mmc/host/sdhci-of-esdhc.c @@ -77,8 +77,11 @@ struct sdhci_esdhc { bool quirk_incorrect_hostver; bool quirk_limited_clk_division; bool quirk_unreliable_pulse_detection; - bool quirk_fixup_tuning; + bool quirk_tuning_erratum_type1; + bool quirk_tuning_erratum_type2; bool quirk_ignore_data_inhibit; + bool quirk_delay_before_data_reset; + bool in_sw_tuning; unsigned int peripheral_clock; const struct esdhc_clk_fixup *clk_fixup; u32 div_ratio; @@ -408,6 +411,8 @@ static void esdhc_le_writel(struct sdhci_host *host, u32 val, int reg) static void esdhc_be_writew(struct sdhci_host *host, u16 val, int reg) { + struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); + struct sdhci_esdhc *esdhc = sdhci_pltfm_priv(pltfm_host); int base = reg & ~0x3; u32 value; u32 ret; @@ -416,10 +421,24 @@ static void esdhc_be_writew(struct sdhci_host *host, u16 val, int reg) ret = esdhc_writew_fixup(host, reg, val, value); if (reg != SDHCI_TRANSFER_MODE) iowrite32be(ret, host->ioaddr + base); + + /* Starting SW tuning requires ESDHC_SMPCLKSEL to be set + * 1us later after ESDHC_EXTN is set. + */ + if (base == ESDHC_SYSTEM_CONTROL_2) { + if (!(value & ESDHC_EXTN) && (ret & ESDHC_EXTN) && + esdhc->in_sw_tuning) { + udelay(1); + ret |= ESDHC_SMPCLKSEL; + iowrite32be(ret, host->ioaddr + base); + } + } } static void esdhc_le_writew(struct sdhci_host *host, u16 val, int reg) { + struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); + struct sdhci_esdhc *esdhc = sdhci_pltfm_priv(pltfm_host); int base = reg & ~0x3; u32 value; u32 ret; @@ -428,6 +447,18 @@ static void esdhc_le_writew(struct sdhci_host *host, u16 val, int reg) ret = esdhc_writew_fixup(host, reg, val, value); if (reg != SDHCI_TRANSFER_MODE) iowrite32(ret, host->ioaddr + base); + + /* Starting SW tuning requires ESDHC_SMPCLKSEL to be set + * 1us later after ESDHC_EXTN is set. + */ + if (base == ESDHC_SYSTEM_CONTROL_2) { + if (!(value & ESDHC_EXTN) && (ret & ESDHC_EXTN) && + esdhc->in_sw_tuning) { + udelay(1); + ret |= ESDHC_SMPCLKSEL; + iowrite32(ret, host->ioaddr + base); + } + } } static void esdhc_be_writeb(struct sdhci_host *host, u8 val, int reg) @@ -705,14 +736,16 @@ static void esdhc_reset(struct sdhci_host *host, u8 mask) struct sdhci_esdhc *esdhc = sdhci_pltfm_priv(pltfm_host); u32 val; + if (esdhc->quirk_delay_before_data_reset && + (mask & SDHCI_RESET_DATA) && + (host->flags & SDHCI_REQ_USE_DMA)) + mdelay(5); + sdhci_reset(host, mask); sdhci_writel(host, host->ier, SDHCI_INT_ENABLE); sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE); - if (of_find_compatible_node(NULL, NULL, "fsl,p2020-esdhc")) - mdelay(5); - if (mask & SDHCI_RESET_ALL) { val = sdhci_readl(host, ESDHC_TBCTL); val &= ~ESDHC_TB_EN; @@ -796,16 +829,21 @@ static int esdhc_signal_voltage_switch(struct mmc_host *mmc, } } -static struct soc_device_attribute soc_fixup_tuning[] = { +static struct soc_device_attribute soc_tuning_erratum_type1[] = { + { .family = "QorIQ T1023", .revision = "1.0", }, { .family = "QorIQ T1040", .revision = "1.0", }, { .family = "QorIQ T2080", .revision = "1.0", }, - { .family = "QorIQ T1023", .revision = "1.0", }, { .family = "QorIQ LS1021A", .revision = "1.0", }, - { .family = "QorIQ LS1080A", .revision = "1.0", }, - { .family = "QorIQ LS2080A", .revision = "1.0", }, + { }, +}; + +static struct soc_device_attribute soc_tuning_erratum_type2[] = { { .family = "QorIQ LS1012A", .revision = "1.0", }, { .family = "QorIQ LS1043A", .revision = "1.*", }, { .family = "QorIQ LS1046A", .revision = "1.0", }, + { .family = "QorIQ LS1080A", .revision = "1.0", }, + { .family = "QorIQ LS2080A", .revision = "1.0", }, + { .family = "QorIQ LA1575A", .revision = "1.0", }, { }, }; @@ -829,15 +867,97 @@ static void esdhc_tuning_block_enable(struct sdhci_host *host, bool enable) esdhc_clock_enable(host, true); } +static void esdhc_prepare_sw_tuning(struct sdhci_host *host, u8 *window_start, + u8 *window_end) +{ + struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); + struct sdhci_esdhc *esdhc = sdhci_pltfm_priv(pltfm_host); + u8 tbstat_15_8, tbstat_7_0; + u32 val; + + if (esdhc->quirk_tuning_erratum_type1) { + *window_start = 5 * esdhc->div_ratio; + *window_end = 3 * esdhc->div_ratio; + return; + } + + /* Write TBCTL[11:8]=4'h8 */ + val = sdhci_readl(host, ESDHC_TBCTL); + val &= ~(0xf << 8); + val |= 8 << 8; + sdhci_writel(host, val, ESDHC_TBCTL); + + mdelay(1); + + /* Read TBCTL[31:0] register and rewrite again */ + val = sdhci_readl(host, ESDHC_TBCTL); + sdhci_writel(host, val, ESDHC_TBCTL); + + mdelay(1); + + /* Read the TBSTAT[31:0] register twice */ + val = sdhci_readl(host, ESDHC_TBSTAT); + val = sdhci_readl(host, ESDHC_TBSTAT); + + /* Reset data lines by setting ESDHCCTL[RSTD] */ + sdhci_reset(host, SDHCI_RESET_DATA); + /* Write 32'hFFFF_FFFF to IRQSTAT register */ + sdhci_writel(host, 0xFFFFFFFF, SDHCI_INT_STATUS); + + /* If TBSTAT[15:8]-TBSTAT[7:0] > 4 * div_ratio + * or TBSTAT[7:0]-TBSTAT[15:8] > 4 * div_ratio, + * then program TBPTR[TB_WNDW_END_PTR] = 4 * div_ratio + * and program TBPTR[TB_WNDW_START_PTR] = 8 * div_ratio. + */ + tbstat_7_0 = val & 0xff; + tbstat_15_8 = (val >> 8) & 0xff; + + if (abs(tbstat_15_8 - tbstat_7_0) > (4 * esdhc->div_ratio)) { + *window_start = 8 * esdhc->div_ratio; + *window_end = 4 * esdhc->div_ratio; + } else { + *window_start = 5 * esdhc->div_ratio; + *window_end = 3 * esdhc->div_ratio; + } +} + +static int esdhc_execute_sw_tuning(struct mmc_host *mmc, u32 opcode, + u8 window_start, u8 window_end) +{ + struct sdhci_host *host = mmc_priv(mmc); + struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); + struct sdhci_esdhc *esdhc = sdhci_pltfm_priv(pltfm_host); + u32 val; + int ret; + + /* Program TBPTR[TB_WNDW_END_PTR] and TBPTR[TB_WNDW_START_PTR] */ + val = ((u32)window_start << ESDHC_WNDW_STRT_PTR_SHIFT) & + ESDHC_WNDW_STRT_PTR_MASK; + val |= window_end & ESDHC_WNDW_END_PTR_MASK; + sdhci_writel(host, val, ESDHC_TBPTR); + + /* Program the software tuning mode by setting TBCTL[TB_MODE]=2'h3 */ + val = sdhci_readl(host, ESDHC_TBCTL); + val &= ~ESDHC_TB_MODE_MASK; + val |= ESDHC_TB_MODE_SW; + sdhci_writel(host, val, ESDHC_TBCTL); + + esdhc->in_sw_tuning = true; + ret = sdhci_execute_tuning(mmc, opcode); + esdhc->in_sw_tuning = false; + return ret; +} + static int esdhc_execute_tuning(struct mmc_host *mmc, u32 opcode) { struct sdhci_host *host = mmc_priv(mmc); struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); struct sdhci_esdhc *esdhc = sdhci_pltfm_priv(pltfm_host); + u8 window_start, window_end; + int ret, retries = 1; bool hs400_tuning; unsigned int clk; u32 val; - int ret; /* For tuning mode, the sd clock divisor value * must be larger than 3 according to reference manual. @@ -846,39 +966,73 @@ static int esdhc_execute_tuning(struct mmc_host *mmc, u32 opcode) if (host->clock > clk) esdhc_of_set_clock(host, clk); - if (esdhc->quirk_limited_clk_division && - host->flags & SDHCI_HS400_TUNING) - esdhc_of_set_clock(host, host->clock); - esdhc_tuning_block_enable(host, true); hs400_tuning = host->flags & SDHCI_HS400_TUNING; - ret = sdhci_execute_tuning(mmc, opcode); - if (hs400_tuning) { - val = sdhci_readl(host, ESDHC_SDTIMNGCTL); - val |= ESDHC_FLW_CTL_BG; - sdhci_writel(host, val, ESDHC_SDTIMNGCTL); - } + do { + if (esdhc->quirk_limited_clk_division && + hs400_tuning) + esdhc_of_set_clock(host, host->clock); - if (host->tuning_err == -EAGAIN && esdhc->quirk_fixup_tuning) { + /* Do HW tuning */ + val = sdhci_readl(host, ESDHC_TBCTL); + val &= ~ESDHC_TB_MODE_MASK; + val |= ESDHC_TB_MODE_3; + sdhci_writel(host, val, ESDHC_TBCTL); - /* program TBPTR[TB_WNDW_END_PTR] = 3*DIV_RATIO and - * program TBPTR[TB_WNDW_START_PTR] = 5*DIV_RATIO - */ - val = sdhci_readl(host, ESDHC_TBPTR); - val = (val & ~((0x7f << 8) | 0x7f)) | - (3 * esdhc->div_ratio) | ((5 * esdhc->div_ratio) << 8); - sdhci_writel(host, val, ESDHC_TBPTR); + ret = sdhci_execute_tuning(mmc, opcode); + if (ret) + break; - /* program the software tuning mode by setting - * TBCTL[TB_MODE]=2'h3 + /* If HW tuning fails and triggers erratum, + * try workaround. */ - val = sdhci_readl(host, ESDHC_TBCTL); - val |= 0x3; - sdhci_writel(host, val, ESDHC_TBCTL); - sdhci_execute_tuning(mmc, opcode); + ret = host->tuning_err; + if (ret == -EAGAIN && + (esdhc->quirk_tuning_erratum_type1 || + esdhc->quirk_tuning_erratum_type2)) { + /* Recover HS400 tuning flag */ + if (hs400_tuning) + host->flags |= SDHCI_HS400_TUNING; + pr_info("%s: Hold on to use fixed sampling clock. Try SW tuning!\n", + mmc_hostname(mmc)); + /* Do SW tuning */ + esdhc_prepare_sw_tuning(host, &window_start, + &window_end); + ret = esdhc_execute_sw_tuning(mmc, opcode, + window_start, + window_end); + if (ret) + break; + + /* Retry both HW/SW tuning with reduced clock. */ + ret = host->tuning_err; + if (ret == -EAGAIN && retries) { + /* Recover HS400 tuning flag */ + if (hs400_tuning) + host->flags |= SDHCI_HS400_TUNING; + + clk = host->max_clk / (esdhc->div_ratio + 1); + esdhc_of_set_clock(host, clk); + pr_info("%s: Hold on to use fixed sampling clock. Try tuning with reduced clock!\n", + mmc_hostname(mmc)); + } else { + break; + } + } else { + break; + } + } while (retries--); + + if (ret) { + esdhc_tuning_block_enable(host, false); + } else if (hs400_tuning) { + val = sdhci_readl(host, ESDHC_SDTIMNGCTL); + val |= ESDHC_FLW_CTL_BG; + sdhci_writel(host, val, ESDHC_SDTIMNGCTL); } + return ret; } @@ -1049,6 +1203,10 @@ static void esdhc_init(struct platform_device *pdev, struct sdhci_host *host) if (match) esdhc->clk_fixup = match->data; np = pdev->dev.of_node; + + if (of_device_is_compatible(np, "fsl,p2020-esdhc")) + esdhc->quirk_delay_before_data_reset = true; + clk = of_clk_get(np, 0); if (!IS_ERR(clk)) { /* @@ -1114,10 +1272,15 @@ static int sdhci_esdhc_probe(struct platform_device *pdev) pltfm_host = sdhci_priv(host); esdhc = sdhci_pltfm_priv(pltfm_host); - if (soc_device_match(soc_fixup_tuning)) - esdhc->quirk_fixup_tuning = true; + if (soc_device_match(soc_tuning_erratum_type1)) + esdhc->quirk_tuning_erratum_type1 = true; else - esdhc->quirk_fixup_tuning = false; + esdhc->quirk_tuning_erratum_type1 = false; + + if (soc_device_match(soc_tuning_erratum_type2)) + esdhc->quirk_tuning_erratum_type2 = true; + else + esdhc->quirk_tuning_erratum_type2 = false; if (esdhc->vendor_ver == VENDOR_V_22) host->quirks2 |= SDHCI_QUIRK2_HOST_NO_CMD23; @@ -1126,8 +1289,8 @@ static int sdhci_esdhc_probe(struct platform_device *pdev) host->quirks &= ~SDHCI_QUIRK_NO_BUSY_IRQ; if (of_find_compatible_node(NULL, NULL, "fsl,p2020-esdhc")) { - host->quirks2 |= SDHCI_QUIRK_RESET_AFTER_REQUEST; - host->quirks2 |= SDHCI_QUIRK_BROKEN_TIMEOUT_VAL; + host->quirks |= SDHCI_QUIRK_RESET_AFTER_REQUEST; + host->quirks |= SDHCI_QUIRK_BROKEN_TIMEOUT_VAL; } if (of_device_is_compatible(np, "fsl,p5040-esdhc") || diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c index eaffa85bc728..642a9667db4d 100644 --- a/drivers/mmc/host/sdhci-pci-core.c +++ b/drivers/mmc/host/sdhci-pci-core.c @@ -26,6 +26,7 @@ #include #include #include +#include #ifdef CONFIG_X86 #include @@ -782,11 +783,18 @@ static int byt_emmc_probe_slot(struct sdhci_pci_slot *slot) return 0; } +static bool glk_broken_cqhci(struct sdhci_pci_slot *slot) +{ + return slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_GLK_EMMC && + dmi_match(DMI_BIOS_VENDOR, "LENOVO"); +} + static int glk_emmc_probe_slot(struct sdhci_pci_slot *slot) { int ret = byt_emmc_probe_slot(slot); - slot->host->mmc->caps2 |= MMC_CAP2_CQE; + if (!glk_broken_cqhci(slot)) + slot->host->mmc->caps2 |= MMC_CAP2_CQE; if (slot->chip->pdev->device != PCI_DEVICE_ID_INTEL_GLK_EMMC) { slot->host->mmc->caps2 |= MMC_CAP2_HS400_ES, diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index b056400e34b1..5f9df2dbde06 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -1871,9 +1871,7 @@ void sdhci_set_uhs_signaling(struct sdhci_host *host, unsigned timing) ctrl_2 |= SDHCI_CTRL_UHS_SDR104; else if (timing == MMC_TIMING_UHS_SDR12) ctrl_2 |= SDHCI_CTRL_UHS_SDR12; - else if (timing == MMC_TIMING_SD_HS || - timing == MMC_TIMING_MMC_HS || - timing == MMC_TIMING_UHS_SDR25) + else if (timing == MMC_TIMING_UHS_SDR25) ctrl_2 |= SDHCI_CTRL_UHS_SDR25; else if (timing == MMC_TIMING_UHS_SDR50) ctrl_2 |= SDHCI_CTRL_UHS_SDR50; @@ -2408,8 +2406,8 @@ static int __sdhci_execute_tuning(struct sdhci_host *host, u32 opcode) sdhci_send_tuning(host, opcode); if (!host->tuning_done) { - pr_info("%s: Tuning timeout, falling back to fixed sampling clock\n", - mmc_hostname(host->mmc)); + pr_debug("%s: Tuning timeout, falling back to fixed sampling clock\n", + mmc_hostname(host->mmc)); sdhci_abort_tuning(host, opcode); return -ETIMEDOUT; } @@ -3758,6 +3756,9 @@ int sdhci_setup_host(struct sdhci_host *host) mmc_hostname(mmc), host->version); } + if (host->quirks & SDHCI_QUIRK_BROKEN_CQE) + mmc->caps2 &= ~MMC_CAP2_CQE; + if (host->quirks & SDHCI_QUIRK_FORCE_DMA) host->flags |= SDHCI_USE_SDMA; else if (!(host->caps & SDHCI_CAN_DO_SDMA)) diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h index 0ed3e0eaef5f..fe83ece6965b 100644 --- a/drivers/mmc/host/sdhci.h +++ b/drivers/mmc/host/sdhci.h @@ -409,6 +409,8 @@ struct sdhci_host { #define SDHCI_QUIRK_BROKEN_CARD_DETECTION (1<<15) /* Controller reports inverted write-protect state */ #define SDHCI_QUIRK_INVERTED_WRITE_PROTECT (1<<16) +/* Controller has unusable command queue engine */ +#define SDHCI_QUIRK_BROKEN_CQE (1<<17) /* Controller does not like fast PIO transfers */ #define SDHCI_QUIRK_PIO_NEEDS_DELAY (1<<18) /* Controller does not have a LED */ diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c index 9b6e1001e77c..dec5a99f52cf 100644 --- a/drivers/mmc/host/tmio_mmc_core.c +++ b/drivers/mmc/host/tmio_mmc_core.c @@ -1184,7 +1184,7 @@ int tmio_mmc_host_probe(struct tmio_mmc_host *_host) if (ret == -EPROBE_DEFER) return ret; - mmc->caps |= MMC_CAP_4_BIT_DATA | pdata->capabilities; + mmc->caps |= MMC_CAP_ERASE | MMC_CAP_4_BIT_DATA | pdata->capabilities; mmc->caps2 |= pdata->capabilities2; mmc->max_segs = pdata->max_segs ? : 32; mmc->max_blk_size = TMIO_MAX_BLK_SIZE; diff --git a/drivers/mtd/devices/spear_smi.c b/drivers/mtd/devices/spear_smi.c index 986f81d2f93e..47ad0766affa 100644 --- a/drivers/mtd/devices/spear_smi.c +++ b/drivers/mtd/devices/spear_smi.c @@ -592,6 +592,26 @@ static int spear_mtd_read(struct mtd_info *mtd, loff_t from, size_t len, return 0; } +/* + * The purpose of this function is to ensure a memcpy_toio() with byte writes + * only. Its structure is inspired from the ARM implementation of _memcpy_toio() + * which also does single byte writes but cannot be used here as this is just an + * implementation detail and not part of the API. Not mentioning the comment + * stating that _memcpy_toio() should be optimized. + */ +static void spear_smi_memcpy_toio_b(volatile void __iomem *dest, + const void *src, size_t len) +{ + const unsigned char *from = src; + + while (len) { + len--; + writeb(*from, dest); + from++; + dest++; + } +} + static inline int spear_smi_cpy_toio(struct spear_smi *dev, u32 bank, void __iomem *dest, const void *src, size_t len) { @@ -614,7 +634,23 @@ static inline int spear_smi_cpy_toio(struct spear_smi *dev, u32 bank, ctrlreg1 = readl(dev->io_base + SMI_CR1); writel((ctrlreg1 | WB_MODE) & ~SW_MODE, dev->io_base + SMI_CR1); - memcpy_toio(dest, src, len); + /* + * In Write Burst mode (WB_MODE), the specs states that writes must be: + * - incremental + * - of the same size + * The ARM implementation of memcpy_toio() will optimize the number of + * I/O by using as much 4-byte writes as possible, surrounded by + * 2-byte/1-byte access if: + * - the destination is not 4-byte aligned + * - the length is not a multiple of 4-byte. + * Avoid this alternance of write access size by using our own 'byte + * access' helper if at least one of the two conditions above is true. + */ + if (IS_ALIGNED(len, sizeof(u32)) && + IS_ALIGNED((uintptr_t)dest, sizeof(u32))) + memcpy_toio(dest, src, len); + else + spear_smi_memcpy_toio_b(dest, src, len); writel(ctrlreg1, dev->io_base + SMI_CR1); diff --git a/drivers/mtd/nand/onenand/omap2.c b/drivers/mtd/nand/onenand/omap2.c index edf94ee54ec7..71a632b815aa 100644 --- a/drivers/mtd/nand/onenand/omap2.c +++ b/drivers/mtd/nand/onenand/omap2.c @@ -328,7 +328,8 @@ static inline int omap2_onenand_dma_transfer(struct omap2_onenand *c, struct dma_async_tx_descriptor *tx; dma_cookie_t cookie; - tx = dmaengine_prep_dma_memcpy(c->dma_chan, dst, src, count, 0); + tx = dmaengine_prep_dma_memcpy(c->dma_chan, dst, src, count, + DMA_CTRL_ACK | DMA_PREP_INTERRUPT); if (!tx) { dev_err(&c->pdev->dev, "Failed to prepare DMA memcpy\n"); return -EIO; diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index 5c2c30a7dffa..f64e3b6605c6 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -292,12 +292,16 @@ int nand_bbm_get_next_page(struct nand_chip *chip, int page) struct mtd_info *mtd = nand_to_mtd(chip); int last_page = ((mtd->erasesize - mtd->writesize) >> chip->page_shift) & chip->pagemask; + unsigned int bbm_flags = NAND_BBM_FIRSTPAGE | NAND_BBM_SECONDPAGE + | NAND_BBM_LASTPAGE; + if (page == 0 && !(chip->options & bbm_flags)) + return 0; if (page == 0 && chip->options & NAND_BBM_FIRSTPAGE) return 0; - else if (page <= 1 && chip->options & NAND_BBM_SECONDPAGE) + if (page <= 1 && chip->options & NAND_BBM_SECONDPAGE) return 1; - else if (page <= last_page && chip->options & NAND_BBM_LASTPAGE) + if (page <= last_page && chip->options & NAND_BBM_LASTPAGE) return last_page; return -EINVAL; diff --git a/drivers/mtd/nand/raw/nand_micron.c b/drivers/mtd/nand/raw/nand_micron.c index 8ca9fad6e6ad..56654030ec7f 100644 --- a/drivers/mtd/nand/raw/nand_micron.c +++ b/drivers/mtd/nand/raw/nand_micron.c @@ -446,8 +446,10 @@ static int micron_nand_init(struct nand_chip *chip) if (ret) goto err_free_manuf_data; + chip->options |= NAND_BBM_FIRSTPAGE; + if (mtd->writesize == 2048) - chip->options |= NAND_BBM_FIRSTPAGE | NAND_BBM_SECONDPAGE; + chip->options |= NAND_BBM_SECONDPAGE; ondie = micron_supports_on_die_ecc(chip); diff --git a/drivers/mtd/nand/raw/stm32_fmc2_nand.c b/drivers/mtd/nand/raw/stm32_fmc2_nand.c index 8cc852dc7d54..5c06e0b4d4ef 100644 --- a/drivers/mtd/nand/raw/stm32_fmc2_nand.c +++ b/drivers/mtd/nand/raw/stm32_fmc2_nand.c @@ -37,6 +37,7 @@ /* Max ECC buffer length */ #define FMC2_MAX_ECC_BUF_LEN (FMC2_BCHDSRS_LEN * FMC2_MAX_SG) +#define FMC2_TIMEOUT_US 1000 #define FMC2_TIMEOUT_MS 1000 /* Timings */ @@ -53,6 +54,8 @@ #define FMC2_PMEM 0x88 #define FMC2_PATT 0x8c #define FMC2_HECCR 0x94 +#define FMC2_ISR 0x184 +#define FMC2_ICR 0x188 #define FMC2_CSQCR 0x200 #define FMC2_CSQCFGR1 0x204 #define FMC2_CSQCFGR2 0x208 @@ -118,6 +121,12 @@ #define FMC2_PATT_ATTHIZ(x) (((x) & 0xff) << 24) #define FMC2_PATT_DEFAULT 0x0a0a0a0a +/* Register: FMC2_ISR */ +#define FMC2_ISR_IHLF BIT(1) + +/* Register: FMC2_ICR */ +#define FMC2_ICR_CIHLF BIT(1) + /* Register: FMC2_CSQCR */ #define FMC2_CSQCR_CSQSTART BIT(0) @@ -1322,6 +1331,31 @@ static void stm32_fmc2_write_data(struct nand_chip *chip, const void *buf, stm32_fmc2_set_buswidth_16(fmc2, true); } +static int stm32_fmc2_waitrdy(struct nand_chip *chip, unsigned long timeout_ms) +{ + struct stm32_fmc2_nfc *fmc2 = to_stm32_nfc(chip->controller); + const struct nand_sdr_timings *timings; + u32 isr, sr; + + /* Check if there is no pending requests to the NAND flash */ + if (readl_relaxed_poll_timeout_atomic(fmc2->io_base + FMC2_SR, sr, + sr & FMC2_SR_NWRF, 1, + FMC2_TIMEOUT_US)) + dev_warn(fmc2->dev, "Waitrdy timeout\n"); + + /* Wait tWB before R/B# signal is low */ + timings = nand_get_sdr_timings(&chip->data_interface); + ndelay(PSEC_TO_NSEC(timings->tWB_max)); + + /* R/B# signal is low, clear high level flag */ + writel_relaxed(FMC2_ICR_CIHLF, fmc2->io_base + FMC2_ICR); + + /* Wait R/B# signal is high */ + return readl_relaxed_poll_timeout_atomic(fmc2->io_base + FMC2_ISR, + isr, isr & FMC2_ISR_IHLF, + 5, 1000 * timeout_ms); +} + static int stm32_fmc2_exec_op(struct nand_chip *chip, const struct nand_operation *op, bool check_only) @@ -1366,8 +1400,8 @@ static int stm32_fmc2_exec_op(struct nand_chip *chip, break; case NAND_OP_WAITRDY_INSTR: - ret = nand_soft_waitrdy(chip, - instr->ctx.waitrdy.timeout_ms); + ret = stm32_fmc2_waitrdy(chip, + instr->ctx.waitrdy.timeout_ms); break; } } diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index 7acf4a93b592..1548e0f7f5f4 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -2544,7 +2544,7 @@ static int spi_nor_read(struct mtd_info *mtd, loff_t from, size_t len, size_t *retlen, u_char *buf) { struct spi_nor *nor = mtd_to_spi_nor(mtd); - int ret; + ssize_t ret; dev_dbg(nor->dev, "from 0x%08x, len %zd\n", (u32)from, len); @@ -2865,7 +2865,7 @@ static int spi_nor_hwcaps_pp2cmd(u32 hwcaps) */ static int spi_nor_read_raw(struct spi_nor *nor, u32 addr, size_t len, u8 *buf) { - int ret; + ssize_t ret; while (len) { ret = spi_nor_read_data(nor, addr, len, buf); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 62f65573eb04..7dcd709f4ac3 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2225,9 +2225,6 @@ static void bond_miimon_commit(struct bonding *bond) } else if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { /* make it immediately active */ bond_set_active_slave(slave); - } else if (slave != primary) { - /* prevent it from being the active one */ - bond_set_backup_slave(slave); } slave_info(bond->dev, slave->dev, "link status definitely up, %u Mbps %s duplex\n", @@ -3612,32 +3609,35 @@ static int bond_neigh_init(struct neighbour *n) const struct net_device_ops *slave_ops; struct neigh_parms parms; struct slave *slave; - int ret; + int ret = 0; - slave = bond_first_slave(bond); + rcu_read_lock(); + slave = bond_first_slave_rcu(bond); if (!slave) - return 0; + goto out; slave_ops = slave->dev->netdev_ops; if (!slave_ops->ndo_neigh_setup) - return 0; - - parms.neigh_setup = NULL; - parms.neigh_cleanup = NULL; - ret = slave_ops->ndo_neigh_setup(slave->dev, &parms); - if (ret) - return ret; + goto out; - /* Assign slave's neigh_cleanup to neighbour in case cleanup is called - * after the last slave has been detached. Assumes that all slaves - * utilize the same neigh_cleanup (true at this writing as only user - * is ipoib). + /* TODO: find another way [1] to implement this. + * Passing a zeroed structure is fragile, + * but at least we do not pass garbage. + * + * [1] One way would be that ndo_neigh_setup() never touch + * struct neigh_parms, but propagate the new neigh_setup() + * back to ___neigh_create() / neigh_parms_alloc() */ - n->parms->neigh_cleanup = parms.neigh_cleanup; + memset(&parms, 0, sizeof(parms)); + ret = slave_ops->ndo_neigh_setup(slave->dev, &parms); - if (!parms.neigh_setup) - return 0; + if (ret) + goto out; - return parms.neigh_setup(n); + if (parms.neigh_setup) + ret = parms.neigh_setup(n); +out: + rcu_read_unlock(); + return ret; } /* The bonding ndo_neigh_setup is called at init time beofre any diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index 57f9a2f51085..e5c207ad3c77 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -389,6 +389,34 @@ static struct flexcan_mb __iomem *flexcan_get_mb(const struct flexcan_priv *priv (&priv->regs->mb[bank][priv->mb_size * mb_index]); } +static int flexcan_low_power_enter_ack(struct flexcan_priv *priv) +{ + struct flexcan_regs __iomem *regs = priv->regs; + unsigned int timeout = FLEXCAN_TIMEOUT_US / 10; + + while (timeout-- && !(priv->read(®s->mcr) & FLEXCAN_MCR_LPM_ACK)) + udelay(10); + + if (!(priv->read(®s->mcr) & FLEXCAN_MCR_LPM_ACK)) + return -ETIMEDOUT; + + return 0; +} + +static int flexcan_low_power_exit_ack(struct flexcan_priv *priv) +{ + struct flexcan_regs __iomem *regs = priv->regs; + unsigned int timeout = FLEXCAN_TIMEOUT_US / 10; + + while (timeout-- && (priv->read(®s->mcr) & FLEXCAN_MCR_LPM_ACK)) + udelay(10); + + if (priv->read(®s->mcr) & FLEXCAN_MCR_LPM_ACK) + return -ETIMEDOUT; + + return 0; +} + static void flexcan_enable_wakeup_irq(struct flexcan_priv *priv, bool enable) { struct flexcan_regs __iomem *regs = priv->regs; @@ -407,7 +435,6 @@ static void flexcan_enable_wakeup_irq(struct flexcan_priv *priv, bool enable) static inline int flexcan_enter_stop_mode(struct flexcan_priv *priv) { struct flexcan_regs __iomem *regs = priv->regs; - unsigned int ackval; u32 reg_mcr; reg_mcr = priv->read(®s->mcr); @@ -418,36 +445,24 @@ static inline int flexcan_enter_stop_mode(struct flexcan_priv *priv) regmap_update_bits(priv->stm.gpr, priv->stm.req_gpr, 1 << priv->stm.req_bit, 1 << priv->stm.req_bit); - /* get stop acknowledgment */ - if (regmap_read_poll_timeout(priv->stm.gpr, priv->stm.ack_gpr, - ackval, ackval & (1 << priv->stm.ack_bit), - 0, FLEXCAN_TIMEOUT_US)) - return -ETIMEDOUT; - - return 0; + return flexcan_low_power_enter_ack(priv); } static inline int flexcan_exit_stop_mode(struct flexcan_priv *priv) { struct flexcan_regs __iomem *regs = priv->regs; - unsigned int ackval; u32 reg_mcr; /* remove stop request */ regmap_update_bits(priv->stm.gpr, priv->stm.req_gpr, 1 << priv->stm.req_bit, 0); - /* get stop acknowledgment */ - if (regmap_read_poll_timeout(priv->stm.gpr, priv->stm.ack_gpr, - ackval, !(ackval & (1 << priv->stm.ack_bit)), - 0, FLEXCAN_TIMEOUT_US)) - return -ETIMEDOUT; reg_mcr = priv->read(®s->mcr); reg_mcr &= ~FLEXCAN_MCR_SLF_WAK; priv->write(reg_mcr, ®s->mcr); - return 0; + return flexcan_low_power_exit_ack(priv); } static inline void flexcan_error_irq_enable(const struct flexcan_priv *priv) @@ -506,39 +521,25 @@ static inline int flexcan_transceiver_disable(const struct flexcan_priv *priv) static int flexcan_chip_enable(struct flexcan_priv *priv) { struct flexcan_regs __iomem *regs = priv->regs; - unsigned int timeout = FLEXCAN_TIMEOUT_US / 10; u32 reg; reg = priv->read(®s->mcr); reg &= ~FLEXCAN_MCR_MDIS; priv->write(reg, ®s->mcr); - while (timeout-- && (priv->read(®s->mcr) & FLEXCAN_MCR_LPM_ACK)) - udelay(10); - - if (priv->read(®s->mcr) & FLEXCAN_MCR_LPM_ACK) - return -ETIMEDOUT; - - return 0; + return flexcan_low_power_exit_ack(priv); } static int flexcan_chip_disable(struct flexcan_priv *priv) { struct flexcan_regs __iomem *regs = priv->regs; - unsigned int timeout = FLEXCAN_TIMEOUT_US / 10; u32 reg; reg = priv->read(®s->mcr); reg |= FLEXCAN_MCR_MDIS; priv->write(reg, ®s->mcr); - while (timeout-- && !(priv->read(®s->mcr) & FLEXCAN_MCR_LPM_ACK)) - udelay(10); - - if (!(priv->read(®s->mcr) & FLEXCAN_MCR_LPM_ACK)) - return -ETIMEDOUT; - - return 0; + return flexcan_low_power_enter_ack(priv); } static int flexcan_chip_freeze(struct flexcan_priv *priv) @@ -1703,6 +1704,9 @@ static int __maybe_unused flexcan_resume(struct device *device) netif_start_queue(dev); if (device_may_wakeup(device)) { disable_irq_wake(dev->irq); + err = flexcan_exit_stop_mode(priv); + if (err) + return err; } else { err = pm_runtime_force_resume(device); if (err) @@ -1748,14 +1752,9 @@ static int __maybe_unused flexcan_noirq_resume(struct device *device) { struct net_device *dev = dev_get_drvdata(device); struct flexcan_priv *priv = netdev_priv(dev); - int err; - if (netif_running(dev) && device_may_wakeup(device)) { + if (netif_running(dev) && device_may_wakeup(device)) flexcan_enable_wakeup_irq(priv, false); - err = flexcan_exit_stop_mode(priv); - if (err) - return err; - } return 0; } diff --git a/drivers/net/can/m_can/tcan4x5x.c b/drivers/net/can/m_can/tcan4x5x.c index 3db619209fe1..d797912e665a 100644 --- a/drivers/net/can/m_can/tcan4x5x.c +++ b/drivers/net/can/m_can/tcan4x5x.c @@ -354,6 +354,8 @@ static int tcan4x5x_parse_config(struct m_can_classdev *cdev) if (IS_ERR(tcan4x5x->reset_gpio)) tcan4x5x->reset_gpio = NULL; + usleep_range(700, 1000); + tcan4x5x->device_state_gpio = devm_gpiod_get_optional(cdev->dev, "device-state", GPIOD_IN); @@ -443,6 +445,10 @@ static int tcan4x5x_can_probe(struct spi_device *spi) tcan4x5x_power_enable(priv->power, 1); + ret = tcan4x5x_init(mcan_class); + if (ret) + goto out_power; + ret = m_can_class_register(mcan_class); if (ret) goto out_power; diff --git a/drivers/net/can/mscan/mscan.c b/drivers/net/can/mscan/mscan.c index 8caf7af0dee2..99101d7027a8 100644 --- a/drivers/net/can/mscan/mscan.c +++ b/drivers/net/can/mscan/mscan.c @@ -381,13 +381,12 @@ static int mscan_rx_poll(struct napi_struct *napi, int quota) struct net_device *dev = napi->dev; struct mscan_regs __iomem *regs = priv->reg_base; struct net_device_stats *stats = &dev->stats; - int npackets = 0; - int ret = 1; + int work_done = 0; struct sk_buff *skb; struct can_frame *frame; u8 canrflg; - while (npackets < quota) { + while (work_done < quota) { canrflg = in_8(®s->canrflg); if (!(canrflg & (MSCAN_RXF | MSCAN_ERR_IF))) break; @@ -408,18 +407,18 @@ static int mscan_rx_poll(struct napi_struct *napi, int quota) stats->rx_packets++; stats->rx_bytes += frame->can_dlc; - npackets++; + work_done++; netif_receive_skb(skb); } - if (!(in_8(®s->canrflg) & (MSCAN_RXF | MSCAN_ERR_IF))) { - napi_complete(&priv->napi); - clear_bit(F_RX_PROGRESS, &priv->flags); - if (priv->can.state < CAN_STATE_BUS_OFF) - out_8(®s->canrier, priv->shadow_canrier); - ret = 0; + if (work_done < quota) { + if (likely(napi_complete_done(&priv->napi, work_done))) { + clear_bit(F_RX_PROGRESS, &priv->flags); + if (priv->can.state < CAN_STATE_BUS_OFF) + out_8(®s->canrier, priv->shadow_canrier); + } } - return ret; + return work_done; } static irqreturn_t mscan_isr(int irq, void *dev_id) diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c index 0a9f42e5fedf..2e57122f02fb 100644 --- a/drivers/net/can/slcan.c +++ b/drivers/net/can/slcan.c @@ -617,6 +617,7 @@ static int slcan_open(struct tty_struct *tty) sl->tty = NULL; tty->disc_data = NULL; clear_bit(SLF_INUSE, &sl->flags); + slc_free_netdev(sl->dev); free_netdev(sl->dev); err_exit: diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index 2f74f6704c12..a4b4b742c80c 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -918,7 +918,7 @@ static int gs_usb_probe(struct usb_interface *intf, GS_USB_BREQ_HOST_FORMAT, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_INTERFACE, 1, - intf->altsetting[0].desc.bInterfaceNumber, + intf->cur_altsetting->desc.bInterfaceNumber, hconf, sizeof(*hconf), 1000); @@ -941,7 +941,7 @@ static int gs_usb_probe(struct usb_interface *intf, GS_USB_BREQ_DEVICE_CONFIG, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_INTERFACE, 1, - intf->altsetting[0].desc.bInterfaceNumber, + intf->cur_altsetting->desc.bInterfaceNumber, dconf, sizeof(*dconf), 1000); diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c index 5fc0be564274..7ab87a758754 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c @@ -1590,7 +1590,7 @@ static int kvaser_usb_hydra_setup_endpoints(struct kvaser_usb *dev) struct usb_endpoint_descriptor *ep; int i; - iface_desc = &dev->intf->altsetting[0]; + iface_desc = dev->intf->cur_altsetting; for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) { ep = &iface_desc->endpoint[i].desc; diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c index 07d2f3aa2c02..1b9957f12459 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c @@ -608,7 +608,7 @@ static int kvaser_usb_leaf_simple_cmd_async(struct kvaser_usb_net_priv *priv, struct kvaser_cmd *cmd; int err; - cmd = kmalloc(sizeof(*cmd), GFP_ATOMIC); + cmd = kzalloc(sizeof(*cmd), GFP_ATOMIC); if (!cmd) return -ENOMEM; @@ -1140,7 +1140,7 @@ static int kvaser_usb_leaf_set_opt_mode(const struct kvaser_usb_net_priv *priv) struct kvaser_cmd *cmd; int rc; - cmd = kmalloc(sizeof(*cmd), GFP_KERNEL); + cmd = kzalloc(sizeof(*cmd), GFP_KERNEL); if (!cmd) return -ENOMEM; @@ -1206,7 +1206,7 @@ static int kvaser_usb_leaf_flush_queue(struct kvaser_usb_net_priv *priv) struct kvaser_cmd *cmd; int rc; - cmd = kmalloc(sizeof(*cmd), GFP_KERNEL); + cmd = kzalloc(sizeof(*cmd), GFP_KERNEL); if (!cmd) return -ENOMEM; @@ -1310,7 +1310,7 @@ static int kvaser_usb_leaf_setup_endpoints(struct kvaser_usb *dev) struct usb_endpoint_descriptor *endpoint; int i; - iface_desc = &dev->intf->altsetting[0]; + iface_desc = dev->intf->cur_altsetting; for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) { endpoint = &iface_desc->endpoint[i].desc; diff --git a/drivers/net/can/usb/ucan.c b/drivers/net/can/usb/ucan.c index 04aac3bb54ef..81e942f713e6 100644 --- a/drivers/net/can/usb/ucan.c +++ b/drivers/net/can/usb/ucan.c @@ -792,7 +792,7 @@ static void ucan_read_bulk_callback(struct urb *urb) up); usb_anchor_urb(urb, &up->rx_urbs); - ret = usb_submit_urb(urb, GFP_KERNEL); + ret = usb_submit_urb(urb, GFP_ATOMIC); if (ret < 0) { netdev_err(up->netdev, diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c index 7c482b2d78d2..2be846ee627d 100644 --- a/drivers/net/can/xilinx_can.c +++ b/drivers/net/can/xilinx_can.c @@ -60,6 +60,8 @@ enum xcan_reg { XCAN_TXMSG_BASE_OFFSET = 0x0100, /* TX Message Space */ XCAN_RXMSG_BASE_OFFSET = 0x1100, /* RX Message Space */ XCAN_RXMSG_2_BASE_OFFSET = 0x2100, /* RX Message Space */ + XCAN_AFR_2_MASK_OFFSET = 0x0A00, /* Acceptance Filter MASK */ + XCAN_AFR_2_ID_OFFSET = 0x0A04, /* Acceptance Filter ID */ }; #define XCAN_FRAME_ID_OFFSET(frame_base) ((frame_base) + 0x00) @@ -1803,6 +1805,11 @@ static int xcan_probe(struct platform_device *pdev) pm_runtime_put(&pdev->dev); + if (priv->devtype.flags & XCAN_FLAG_CANFD_2) { + priv->write_reg(priv, XCAN_AFR_2_ID_OFFSET, 0x00000000); + priv->write_reg(priv, XCAN_AFR_2_MASK_OFFSET, 0x00000000); + } + netdev_dbg(ndev, "reg_base=0x%p irq=%d clock=%d, tx buffers: actual %d, using %d\n", priv->reg_base, ndev->irq, priv->can.clock.freq, hw_tx_max, priv->tx_max); diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig index f6232ce8481f..685e12b05a7c 100644 --- a/drivers/net/dsa/Kconfig +++ b/drivers/net/dsa/Kconfig @@ -77,6 +77,7 @@ config NET_DSA_REALTEK_SMI config NET_DSA_SMSC_LAN9303 tristate select NET_DSA_TAG_LAN9303 + select REGMAP ---help--- This enables support for the SMSC/Microchip LAN9303 3 port ethernet switch chips. diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index cc3536315eff..a7132c1593c3 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -347,7 +347,7 @@ static void b53_set_forwarding(struct b53_device *dev, int enable) * frames should be flooded or not. */ b53_read8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, &mgmt); - mgmt |= B53_UC_FWD_EN | B53_MC_FWD_EN; + mgmt |= B53_UC_FWD_EN | B53_MC_FWD_EN | B53_IPMC_FWD_EN; b53_write8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, mgmt); } @@ -526,6 +526,8 @@ int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy) cpu_port = ds->ports[port].cpu_dp->index; + b53_br_egress_floods(ds, port, true, true); + if (dev->ops->irq_enable) ret = dev->ops->irq_enable(dev, port); if (ret) @@ -641,6 +643,8 @@ static void b53_enable_cpu_port(struct b53_device *dev, int port) b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), port_ctrl); b53_brcm_hdr_setup(dev->ds, port); + + b53_br_egress_floods(dev->ds, port, true, true); } static void b53_enable_mib(struct b53_device *dev) @@ -1766,19 +1770,26 @@ int b53_br_egress_floods(struct dsa_switch *ds, int port, struct b53_device *dev = ds->priv; u16 uc, mc; - b53_read16(dev, B53_CTRL_PAGE, B53_UC_FWD_EN, &uc); + b53_read16(dev, B53_CTRL_PAGE, B53_UC_FLOOD_MASK, &uc); if (unicast) uc |= BIT(port); else uc &= ~BIT(port); - b53_write16(dev, B53_CTRL_PAGE, B53_UC_FWD_EN, uc); + b53_write16(dev, B53_CTRL_PAGE, B53_UC_FLOOD_MASK, uc); + + b53_read16(dev, B53_CTRL_PAGE, B53_MC_FLOOD_MASK, &mc); + if (multicast) + mc |= BIT(port); + else + mc &= ~BIT(port); + b53_write16(dev, B53_CTRL_PAGE, B53_MC_FLOOD_MASK, mc); - b53_read16(dev, B53_CTRL_PAGE, B53_MC_FWD_EN, &mc); + b53_read16(dev, B53_CTRL_PAGE, B53_IPMC_FLOOD_MASK, &mc); if (multicast) mc |= BIT(port); else mc &= ~BIT(port); - b53_write16(dev, B53_CTRL_PAGE, B53_MC_FWD_EN, mc); + b53_write16(dev, B53_CTRL_PAGE, B53_IPMC_FLOOD_MASK, mc); return 0; diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c index d264776a95a3..471837cf0b21 100644 --- a/drivers/net/dsa/bcm_sf2_cfp.c +++ b/drivers/net/dsa/bcm_sf2_cfp.c @@ -358,7 +358,7 @@ static int bcm_sf2_cfp_ipv4_rule_set(struct bcm_sf2_priv *priv, int port, return -EINVAL; } - ip_frag = be32_to_cpu(fs->m_ext.data[0]); + ip_frag = !!(be32_to_cpu(fs->h_ext.data[0]) & 1); /* Locate the first rule available */ if (fs->location == RX_CLS_LOC_ANY) @@ -569,7 +569,7 @@ static int bcm_sf2_cfp_rule_cmp(struct bcm_sf2_priv *priv, int port, if (rule->fs.flow_type != fs->flow_type || rule->fs.ring_cookie != fs->ring_cookie || - rule->fs.m_ext.data[0] != fs->m_ext.data[0]) + rule->fs.h_ext.data[0] != fs->h_ext.data[0]) continue; switch (fs->flow_type & ~FLOW_EXT) { @@ -621,7 +621,7 @@ static int bcm_sf2_cfp_ipv6_rule_set(struct bcm_sf2_priv *priv, int port, return -EINVAL; } - ip_frag = be32_to_cpu(fs->m_ext.data[0]); + ip_frag = !!(be32_to_cpu(fs->h_ext.data[0]) & 1); layout = &udf_tcpip6_layout; slice_num = bcm_sf2_get_slice_number(layout, 0); diff --git a/drivers/net/dsa/mv88e6xxx/global1.c b/drivers/net/dsa/mv88e6xxx/global1.c index 25ec4c0ac589..8a903624fdd7 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.c +++ b/drivers/net/dsa/mv88e6xxx/global1.c @@ -332,6 +332,11 @@ int mv88e6390_g1_set_cpu_port(struct mv88e6xxx_chip *chip, int port) { u16 ptr = MV88E6390_G1_MONITOR_MGMT_CTL_PTR_CPU_DEST; + /* Use the default high priority for management frames sent to + * the CPU. + */ + port |= MV88E6390_G1_MONITOR_MGMT_CTL_PTR_CPU_DEST_MGMTPRI; + return mv88e6390_g1_monitor_write(chip, ptr, port); } diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h index 0870fcc8bfc8..0ae96a1e919b 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.h +++ b/drivers/net/dsa/mv88e6xxx/global1.h @@ -210,6 +210,7 @@ #define MV88E6390_G1_MONITOR_MGMT_CTL_PTR_INGRESS_DEST 0x2000 #define MV88E6390_G1_MONITOR_MGMT_CTL_PTR_EGRESS_DEST 0x2100 #define MV88E6390_G1_MONITOR_MGMT_CTL_PTR_CPU_DEST 0x3000 +#define MV88E6390_G1_MONITOR_MGMT_CTL_PTR_CPU_DEST_MGMTPRI 0x00e0 #define MV88E6390_G1_MONITOR_MGMT_CTL_DATA_MASK 0x00ff /* Offset 0x1C: Global Control 2 */ diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c index 15ef81654b67..330c41e87171 100644 --- a/drivers/net/dsa/mv88e6xxx/port.c +++ b/drivers/net/dsa/mv88e6xxx/port.c @@ -393,7 +393,7 @@ phy_interface_t mv88e6390x_port_max_speed_mode(int port) } static int mv88e6xxx_port_set_cmode(struct mv88e6xxx_chip *chip, int port, - phy_interface_t mode) + phy_interface_t mode, bool force) { u8 lane; u16 cmode; @@ -427,8 +427,8 @@ static int mv88e6xxx_port_set_cmode(struct mv88e6xxx_chip *chip, int port, cmode = 0; } - /* cmode doesn't change, nothing to do for us */ - if (cmode == chip->ports[port].cmode) + /* cmode doesn't change, nothing to do for us unless forced */ + if (cmode == chip->ports[port].cmode && !force) return 0; lane = mv88e6xxx_serdes_get_lane(chip, port); @@ -484,7 +484,7 @@ int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port, if (port != 9 && port != 10) return -EOPNOTSUPP; - return mv88e6xxx_port_set_cmode(chip, port, mode); + return mv88e6xxx_port_set_cmode(chip, port, mode, false); } int mv88e6390_port_set_cmode(struct mv88e6xxx_chip *chip, int port, @@ -504,7 +504,7 @@ int mv88e6390_port_set_cmode(struct mv88e6xxx_chip *chip, int port, break; } - return mv88e6xxx_port_set_cmode(chip, port, mode); + return mv88e6xxx_port_set_cmode(chip, port, mode, false); } static int mv88e6341_port_set_cmode_writable(struct mv88e6xxx_chip *chip, @@ -555,7 +555,7 @@ int mv88e6341_port_set_cmode(struct mv88e6xxx_chip *chip, int port, if (err) return err; - return mv88e6xxx_port_set_cmode(chip, port, mode); + return mv88e6xxx_port_set_cmode(chip, port, mode, true); } int mv88e6185_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode) diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 7687ddcae159..7763221286d4 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -594,15 +594,15 @@ static int sja1105_parse_rgmii_delays(struct sja1105_private *priv, int i; for (i = 0; i < SJA1105_NUM_PORTS; i++) { - if (ports->role == XMII_MAC) + if (ports[i].role == XMII_MAC) continue; - if (ports->phy_mode == PHY_INTERFACE_MODE_RGMII_RXID || - ports->phy_mode == PHY_INTERFACE_MODE_RGMII_ID) + if (ports[i].phy_mode == PHY_INTERFACE_MODE_RGMII_RXID || + ports[i].phy_mode == PHY_INTERFACE_MODE_RGMII_ID) priv->rgmii_rx_delay[i] = true; - if (ports->phy_mode == PHY_INTERFACE_MODE_RGMII_TXID || - ports->phy_mode == PHY_INTERFACE_MODE_RGMII_ID) + if (ports[i].phy_mode == PHY_INTERFACE_MODE_RGMII_TXID || + ports[i].phy_mode == PHY_INTERFACE_MODE_RGMII_ID) priv->rgmii_tx_delay[i] = true; if ((priv->rgmii_rx_delay[i] || priv->rgmii_tx_delay[i]) && @@ -1389,6 +1389,8 @@ int sja1105_static_config_reload(struct sja1105_private *priv) int speed_mbps[SJA1105_NUM_PORTS]; int rc, i; + mutex_lock(&priv->mgmt_lock); + mac = priv->static_config.tables[BLK_IDX_MAC_CONFIG].entries; /* Back up the dynamic link speed changed by sja1105_adjust_port_config @@ -1420,6 +1422,8 @@ int sja1105_static_config_reload(struct sja1105_private *priv) goto out; } out: + mutex_unlock(&priv->mgmt_lock); + return rc; } @@ -1556,8 +1560,8 @@ static int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled) if (enabled) { /* Enable VLAN filtering. */ - tpid = ETH_P_8021AD; - tpid2 = ETH_P_8021Q; + tpid = ETH_P_8021Q; + tpid2 = ETH_P_8021AD; } else { /* Disable VLAN filtering. */ tpid = ETH_P_SJA1105; @@ -1566,9 +1570,9 @@ static int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled) table = &priv->static_config.tables[BLK_IDX_GENERAL_PARAMS]; general_params = table->entries; - /* EtherType used to identify outer tagged (S-tag) VLAN traffic */ - general_params->tpid = tpid; /* EtherType used to identify inner tagged (C-tag) VLAN traffic */ + general_params->tpid = tpid; + /* EtherType used to identify outer tagged (S-tag) VLAN traffic */ general_params->tpid2 = tpid2; /* When VLAN filtering is on, we need to at least be able to * decode management traffic through the "backup plan". diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.c b/drivers/net/dsa/sja1105/sja1105_static_config.c index 0d03e13e9909..63d2311817c4 100644 --- a/drivers/net/dsa/sja1105/sja1105_static_config.c +++ b/drivers/net/dsa/sja1105/sja1105_static_config.c @@ -142,6 +142,9 @@ static size_t sja1105et_general_params_entry_packing(void *buf, void *entry_ptr, return size; } +/* TPID and TPID2 are intentionally reversed so that semantic + * compatibility with E/T is kept. + */ static size_t sja1105pqrs_general_params_entry_packing(void *buf, void *entry_ptr, enum packing_op op) @@ -166,9 +169,9 @@ sja1105pqrs_general_params_entry_packing(void *buf, void *entry_ptr, sja1105_packing(buf, &entry->mirr_port, 141, 139, size, op); sja1105_packing(buf, &entry->vlmarker, 138, 107, size, op); sja1105_packing(buf, &entry->vlmask, 106, 75, size, op); - sja1105_packing(buf, &entry->tpid, 74, 59, size, op); + sja1105_packing(buf, &entry->tpid2, 74, 59, size, op); sja1105_packing(buf, &entry->ignore2stf, 58, 58, size, op); - sja1105_packing(buf, &entry->tpid2, 57, 42, size, op); + sja1105_packing(buf, &entry->tpid, 57, 42, size, op); sja1105_packing(buf, &entry->queue_ts, 41, 41, size, op); sja1105_packing(buf, &entry->egrmirrvid, 40, 29, size, op); sja1105_packing(buf, &entry->egrmirrpcp, 28, 26, size, op); diff --git a/drivers/net/ethernet/amazon/ena/ena_com.h b/drivers/net/ethernet/amazon/ena/ena_com.h index 7c941eba0bc9..0ce37d54ed10 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.h +++ b/drivers/net/ethernet/amazon/ena/ena_com.h @@ -72,7 +72,7 @@ /*****************************************************************************/ /* ENA adaptive interrupt moderation settings */ -#define ENA_INTR_INITIAL_TX_INTERVAL_USECS 196 +#define ENA_INTR_INITIAL_TX_INTERVAL_USECS 64 #define ENA_INTR_INITIAL_RX_INTERVAL_USECS 0 #define ENA_DEFAULT_INTR_DELAY_RESOLUTION 1 diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c index 16553d92fad2..8c1c73b0ced7 100644 --- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c +++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c @@ -315,10 +315,9 @@ static int ena_get_coalesce(struct net_device *net_dev, ena_com_get_nonadaptive_moderation_interval_tx(ena_dev) * ena_dev->intr_delay_resolution; - if (!ena_com_get_adaptive_moderation_enabled(ena_dev)) - coalesce->rx_coalesce_usecs = - ena_com_get_nonadaptive_moderation_interval_rx(ena_dev) - * ena_dev->intr_delay_resolution; + coalesce->rx_coalesce_usecs = + ena_com_get_nonadaptive_moderation_interval_rx(ena_dev) + * ena_dev->intr_delay_resolution; coalesce->use_adaptive_rx_coalesce = ena_com_get_adaptive_moderation_enabled(ena_dev); @@ -367,12 +366,6 @@ static int ena_set_coalesce(struct net_device *net_dev, ena_update_tx_rings_intr_moderation(adapter); - if (coalesce->use_adaptive_rx_coalesce) { - if (!ena_com_get_adaptive_moderation_enabled(ena_dev)) - ena_com_enable_adaptive_moderation(ena_dev); - return 0; - } - rc = ena_com_update_nonadaptive_moderation_interval_rx(ena_dev, coalesce->rx_coalesce_usecs); if (rc) @@ -380,10 +373,13 @@ static int ena_set_coalesce(struct net_device *net_dev, ena_update_rx_rings_intr_moderation(adapter); - if (!coalesce->use_adaptive_rx_coalesce) { - if (ena_com_get_adaptive_moderation_enabled(ena_dev)) - ena_com_disable_adaptive_moderation(ena_dev); - } + if (coalesce->use_adaptive_rx_coalesce && + !ena_com_get_adaptive_moderation_enabled(ena_dev)) + ena_com_enable_adaptive_moderation(ena_dev); + + if (!coalesce->use_adaptive_rx_coalesce && + ena_com_get_adaptive_moderation_enabled(ena_dev)) + ena_com_disable_adaptive_moderation(ena_dev); return 0; } diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index c487d2a7d6dd..b4a145220aba 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -1238,8 +1238,8 @@ static int ena_io_poll(struct napi_struct *napi, int budget) struct ena_napi *ena_napi = container_of(napi, struct ena_napi, napi); struct ena_ring *tx_ring, *rx_ring; - u32 tx_work_done; - u32 rx_work_done; + int tx_work_done; + int rx_work_done = 0; int tx_budget; int napi_comp_call = 0; int ret; @@ -1256,7 +1256,11 @@ static int ena_io_poll(struct napi_struct *napi, int budget) } tx_work_done = ena_clean_tx_irq(tx_ring, tx_budget); - rx_work_done = ena_clean_rx_irq(rx_ring, napi, budget); + /* On netpoll the budget is zero and the handler should only clean the + * tx completions. + */ + if (likely(budget)) + rx_work_done = ena_clean_rx_irq(rx_ring, napi, budget); /* If the device is about to reset or down, avoid unmask * the interrupt and return 0 so NAPI won't reschedule diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h index 8b08cb18e363..3f63ffd7561b 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h @@ -1109,7 +1109,7 @@ static inline u8 bnx2x_get_path_func_num(struct bnx2x *bp) for (i = 0; i < E1H_FUNC_MAX / 2; i++) { u32 func_config = MF_CFG_RD(bp, - func_mf_config[BP_PORT(bp) + 2 * i]. + func_mf_config[BP_PATH(bp) + 2 * i]. config); func_num += ((func_config & FUNC_MF_CFG_FUNC_HIDE) ? 0 : 1); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 192ff8d5da32..cff64e43bdd8 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -9976,10 +9976,18 @@ static void bnx2x_recovery_failed(struct bnx2x *bp) */ static void bnx2x_parity_recover(struct bnx2x *bp) { - bool global = false; u32 error_recovered, error_unrecovered; - bool is_parity; + bool is_parity, global = false; +#ifdef CONFIG_BNX2X_SRIOV + int vf_idx; + + for (vf_idx = 0; vf_idx < bp->requested_nr_virtfn; vf_idx++) { + struct bnx2x_virtf *vf = BP_VF(bp, vf_idx); + if (vf) + vf->state = VF_LOST; + } +#endif DP(NETIF_MSG_HW, "Handling parity\n"); while (1) { switch (bp->recovery_state) { diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index 0edbb0a76847..5097a44686b3 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -2397,15 +2397,21 @@ static int bnx2x_set_pf_tx_switching(struct bnx2x *bp, bool enable) /* send the ramrod on all the queues of the PF */ for_each_eth_queue(bp, i) { struct bnx2x_fastpath *fp = &bp->fp[i]; + int tx_idx; /* Set the appropriate Queue object */ q_params.q_obj = &bnx2x_sp_obj(bp, fp).q_obj; - /* Update the Queue state */ - rc = bnx2x_queue_state_change(bp, &q_params); - if (rc) { - BNX2X_ERR("Failed to configure Tx switching\n"); - return rc; + for (tx_idx = FIRST_TX_COS_INDEX; + tx_idx < fp->max_cos; tx_idx++) { + q_params.params.update.cid_index = tx_idx; + + /* Update the Queue state */ + rc = bnx2x_queue_state_change(bp, &q_params); + if (rc) { + BNX2X_ERR("Failed to configure Tx switching\n"); + return rc; + } } } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h index b6ebd92ec565..3a716c015415 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h @@ -139,6 +139,7 @@ struct bnx2x_virtf { #define VF_ACQUIRED 1 /* VF acquired, but not initialized */ #define VF_ENABLED 2 /* VF Enabled */ #define VF_RESET 3 /* VF FLR'd, pending cleanup */ +#define VF_LOST 4 /* Recovery while VFs are loaded */ bool flr_clnup_stage; /* true during flr cleanup */ bool malicious; /* true if FW indicated so, until FLR */ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c index 0752b7fa4d9c..ea0e9394f898 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c @@ -2107,6 +2107,18 @@ static void bnx2x_vf_mbx_request(struct bnx2x *bp, struct bnx2x_virtf *vf, { int i; + if (vf->state == VF_LOST) { + /* Just ack the FW and return if VFs are lost + * in case of parity error. VFs are supposed to be timedout + * on waiting for PF response. + */ + DP(BNX2X_MSG_IOV, + "VF 0x%x lost, not handling the request\n", vf->abs_vfid); + + storm_memset_vf_mbx_ack(bp, vf->abs_vfid); + return; + } + /* check if tlv type is known */ if (bnx2x_tlv_supported(mbx->first_tlv.tl.type)) { /* Lock the per vf op mutex and note the locker's identity. diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 04ec909e06df..5c75b061243f 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1767,8 +1767,12 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, rc = -EIO; if (rx_err & RX_CMPL_ERRORS_BUFFER_ERROR_MASK) { - netdev_warn(bp->dev, "RX buffer error %x\n", rx_err); - bnxt_sched_reset(bp, rxr); + bnapi->cp_ring.rx_buf_errors++; + if (!(bp->flags & BNXT_FLAG_CHIP_P5)) { + netdev_warn(bp->dev, "RX buffer error %x\n", + rx_err); + bnxt_sched_reset(bp, rxr); + } } goto next_rx_no_len; } @@ -1991,6 +1995,9 @@ static int bnxt_async_event_process(struct bnxt *bp, case ASYNC_EVENT_CMPL_EVENT_ID_RESET_NOTIFY: { u32 data1 = le32_to_cpu(cmpl->event_data1); + if (!bp->fw_health) + goto async_event_process_exit; + bp->fw_reset_timestamp = jiffies; bp->fw_reset_min_dsecs = cmpl->timestamp_lo; if (!bp->fw_reset_min_dsecs) @@ -4434,8 +4441,9 @@ static int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp) FUNC_DRV_RGTR_REQ_ENABLES_VER); req.os_type = cpu_to_le16(FUNC_DRV_RGTR_REQ_OS_TYPE_LINUX); - flags = FUNC_DRV_RGTR_REQ_FLAGS_16BIT_VER_MODE | - FUNC_DRV_RGTR_REQ_FLAGS_HOT_RESET_SUPPORT; + flags = FUNC_DRV_RGTR_REQ_FLAGS_16BIT_VER_MODE; + if (bp->fw_cap & BNXT_FW_CAP_HOT_RESET) + flags |= FUNC_DRV_RGTR_REQ_FLAGS_HOT_RESET_SUPPORT; if (bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY) flags |= FUNC_DRV_RGTR_REQ_FLAGS_ERROR_RECOVERY_SUPPORT; req.flags = cpu_to_le32(flags); @@ -6170,7 +6178,7 @@ static void bnxt_hwrm_set_coal_params(struct bnxt *bp, tmr = bnxt_usec_to_coal_tmr(bp, hw_coal->coal_ticks_irq); val = clamp_t(u16, tmr, 1, coal_cap->cmpl_aggr_dma_tmr_during_int_max); - req->cmpl_aggr_dma_tmr_during_int = cpu_to_le16(tmr); + req->cmpl_aggr_dma_tmr_during_int = cpu_to_le16(val); req->enables |= cpu_to_le16(BNXT_COAL_CMPL_AGGR_TMR_DURING_INT_ENABLE); } @@ -7092,14 +7100,6 @@ static int bnxt_hwrm_error_recovery_qcfg(struct bnxt *bp) rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (rc) goto err_recovery_out; - if (!fw_health) { - fw_health = kzalloc(sizeof(*fw_health), GFP_KERNEL); - bp->fw_health = fw_health; - if (!fw_health) { - rc = -ENOMEM; - goto err_recovery_out; - } - } fw_health->flags = le32_to_cpu(resp->flags); if ((fw_health->flags & ERROR_RECOVERY_QCFG_RESP_FLAGS_CO_CPU) && !(bp->fw_cap & BNXT_FW_CAP_KONG_MB_CHNL)) { @@ -8762,6 +8762,9 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up) } if (resc_reinit || fw_reset) { if (fw_reset) { + bnxt_free_ctx_mem(bp); + kfree(bp->ctx); + bp->ctx = NULL; rc = bnxt_fw_init_one(bp); if (rc) { set_bit(BNXT_STATE_ABORT_ERR, &bp->state); @@ -9950,8 +9953,7 @@ static void bnxt_fw_health_check(struct bnxt *bp) struct bnxt_fw_health *fw_health = bp->fw_health; u32 val; - if (!fw_health || !fw_health->enabled || - test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) + if (!fw_health->enabled || test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) return; if (fw_health->tmr_counter) { @@ -10412,6 +10414,23 @@ static void bnxt_init_dflt_coal(struct bnxt *bp) bp->stats_coal_ticks = BNXT_DEF_STATS_COAL_TICKS; } +static void bnxt_alloc_fw_health(struct bnxt *bp) +{ + if (bp->fw_health) + return; + + if (!(bp->fw_cap & BNXT_FW_CAP_HOT_RESET) && + !(bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY)) + return; + + bp->fw_health = kzalloc(sizeof(*bp->fw_health), GFP_KERNEL); + if (!bp->fw_health) { + netdev_warn(bp->dev, "Failed to allocate fw_health\n"); + bp->fw_cap &= ~BNXT_FW_CAP_HOT_RESET; + bp->fw_cap &= ~BNXT_FW_CAP_ERROR_RECOVERY; + } +} + static int bnxt_fw_init_one_p1(struct bnxt *bp) { int rc; @@ -10458,6 +10477,7 @@ static int bnxt_fw_init_one_p2(struct bnxt *bp) netdev_warn(bp->dev, "hwrm query adv flow mgnt failure rc: %d\n", rc); + bnxt_alloc_fw_health(bp); rc = bnxt_hwrm_error_recovery_qcfg(bp); if (rc) netdev_warn(bp->dev, "hwrm query error recovery failure rc: %d\n", @@ -10543,6 +10563,12 @@ static int bnxt_fw_init_one(struct bnxt *bp) rc = bnxt_approve_mac(bp, bp->dev->dev_addr, false); if (rc) return rc; + + /* In case fw capabilities have changed, destroy the unneeded + * reporters and create newly capable ones. + */ + bnxt_dl_fw_reporters_destroy(bp, false); + bnxt_dl_fw_reporters_create(bp); bnxt_fw_init_one_p3(bp); return 0; } @@ -10676,8 +10702,7 @@ static void bnxt_fw_reset_task(struct work_struct *work) bnxt_queue_fw_reset_work(bp, bp->fw_reset_min_dsecs * HZ / 10); return; case BNXT_FW_RESET_STATE_ENABLE_DEV: - if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state) && - bp->fw_health) { + if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state)) { u32 val; val = bnxt_fw_health_readl(bp, @@ -11318,11 +11343,11 @@ static void bnxt_remove_one(struct pci_dev *pdev) struct net_device *dev = pci_get_drvdata(pdev); struct bnxt *bp = netdev_priv(dev); - if (BNXT_PF(bp)) { + if (BNXT_PF(bp)) bnxt_sriov_disable(bp); - bnxt_dl_unregister(bp); - } + bnxt_dl_fw_reporters_destroy(bp, true); + bnxt_dl_unregister(bp); pci_disable_pcie_error_reporting(pdev); unregister_netdev(dev); bnxt_shutdown_tc(bp); @@ -11337,6 +11362,8 @@ static void bnxt_remove_one(struct pci_dev *pdev) bnxt_dcb_free(bp); kfree(bp->edev); bp->edev = NULL; + kfree(bp->fw_health); + bp->fw_health = NULL; bnxt_cleanup_pci(bp); bnxt_free_ctx_mem(bp); kfree(bp->ctx); @@ -11816,8 +11843,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (rc) goto init_err_cleanup_tc; - if (BNXT_PF(bp)) - bnxt_dl_register(bp); + bnxt_dl_register(bp); + bnxt_dl_fw_reporters_create(bp); netdev_info(dev, "%s found at mem %lx, node addr %pM\n", board_info[ent->driver_data].name, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index d333589811a5..dc26e3ace43f 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -927,6 +927,7 @@ struct bnxt_cp_ring_info { dma_addr_t hw_stats_map; u32 hw_stats_ctx_id; u64 rx_l4_csum_errors; + u64 rx_buf_errors; u64 missed_irqs; struct bnxt_ring_struct cp_ring_struct; @@ -1657,6 +1658,7 @@ struct bnxt { #define BNXT_FW_CAP_PCIE_STATS_SUPPORTED 0x00020000 #define BNXT_FW_CAP_EXT_STATS_SUPPORTED 0x00040000 #define BNXT_FW_CAP_ERR_RECOVER_RELOAD 0x00100000 + #define BNXT_FW_CAP_HOT_RESET 0x00200000 #define BNXT_NEW_RM(bp) ((bp)->fw_cap & BNXT_FW_CAP_NEW_RM) u32 hwrm_spec_code; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index 7151244f8c7d..1e236e74ff2f 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -19,11 +19,10 @@ static int bnxt_fw_reporter_diagnose(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg) { struct bnxt *bp = devlink_health_reporter_priv(reporter); - struct bnxt_fw_health *health = bp->fw_health; u32 val, health_status; int rc; - if (!health || test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) + if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) return 0; val = bnxt_fw_health_readl(bp, BNXT_FW_HEALTH_REG); @@ -103,21 +102,15 @@ struct devlink_health_reporter_ops bnxt_dl_fw_fatal_reporter_ops = { .recover = bnxt_fw_fatal_recover, }; -static void bnxt_dl_fw_reporters_create(struct bnxt *bp) +void bnxt_dl_fw_reporters_create(struct bnxt *bp) { struct bnxt_fw_health *health = bp->fw_health; - if (!health) + if (!bp->dl || !health) return; - health->fw_reporter = - devlink_health_reporter_create(bp->dl, &bnxt_dl_fw_reporter_ops, - 0, false, bp); - if (IS_ERR(health->fw_reporter)) { - netdev_warn(bp->dev, "Failed to create FW health reporter, rc = %ld\n", - PTR_ERR(health->fw_reporter)); - health->fw_reporter = NULL; - } + if (!(bp->fw_cap & BNXT_FW_CAP_HOT_RESET) || health->fw_reset_reporter) + goto err_recovery; health->fw_reset_reporter = devlink_health_reporter_create(bp->dl, @@ -127,8 +120,30 @@ static void bnxt_dl_fw_reporters_create(struct bnxt *bp) netdev_warn(bp->dev, "Failed to create FW fatal health reporter, rc = %ld\n", PTR_ERR(health->fw_reset_reporter)); health->fw_reset_reporter = NULL; + bp->fw_cap &= ~BNXT_FW_CAP_HOT_RESET; + } + +err_recovery: + if (!(bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY)) + return; + + if (!health->fw_reporter) { + health->fw_reporter = + devlink_health_reporter_create(bp->dl, + &bnxt_dl_fw_reporter_ops, + 0, false, bp); + if (IS_ERR(health->fw_reporter)) { + netdev_warn(bp->dev, "Failed to create FW health reporter, rc = %ld\n", + PTR_ERR(health->fw_reporter)); + health->fw_reporter = NULL; + bp->fw_cap &= ~BNXT_FW_CAP_ERROR_RECOVERY; + return; + } } + if (health->fw_fatal_reporter) + return; + health->fw_fatal_reporter = devlink_health_reporter_create(bp->dl, &bnxt_dl_fw_fatal_reporter_ops, @@ -137,24 +152,35 @@ static void bnxt_dl_fw_reporters_create(struct bnxt *bp) netdev_warn(bp->dev, "Failed to create FW fatal health reporter, rc = %ld\n", PTR_ERR(health->fw_fatal_reporter)); health->fw_fatal_reporter = NULL; + bp->fw_cap &= ~BNXT_FW_CAP_ERROR_RECOVERY; } } -static void bnxt_dl_fw_reporters_destroy(struct bnxt *bp) +void bnxt_dl_fw_reporters_destroy(struct bnxt *bp, bool all) { struct bnxt_fw_health *health = bp->fw_health; - if (!health) + if (!bp->dl || !health) return; - if (health->fw_reporter) - devlink_health_reporter_destroy(health->fw_reporter); - - if (health->fw_reset_reporter) + if ((all || !(bp->fw_cap & BNXT_FW_CAP_HOT_RESET)) && + health->fw_reset_reporter) { devlink_health_reporter_destroy(health->fw_reset_reporter); + health->fw_reset_reporter = NULL; + } - if (health->fw_fatal_reporter) + if ((bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY) && !all) + return; + + if (health->fw_reporter) { + devlink_health_reporter_destroy(health->fw_reporter); + health->fw_reporter = NULL; + } + + if (health->fw_fatal_reporter) { devlink_health_reporter_destroy(health->fw_fatal_reporter); + health->fw_fatal_reporter = NULL; + } } void bnxt_devlink_health_report(struct bnxt *bp, unsigned long event) @@ -162,9 +188,6 @@ void bnxt_devlink_health_report(struct bnxt *bp, unsigned long event) struct bnxt_fw_health *fw_health = bp->fw_health; struct bnxt_fw_reporter_ctx fw_reporter_ctx; - if (!fw_health) - return; - fw_reporter_ctx.sp_event = event; switch (event) { case BNXT_FW_RESET_NOTIFY_SP_EVENT: @@ -203,6 +226,8 @@ static const struct devlink_ops bnxt_dl_ops = { #endif /* CONFIG_BNXT_SRIOV */ }; +static const struct devlink_ops bnxt_vf_dl_ops; + enum bnxt_dl_param_id { BNXT_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, BNXT_DEVLINK_PARAM_ID_GRE_VER_CHECK, @@ -311,10 +336,17 @@ static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg, } else { rc = hwrm_send_message_silent(bp, msg, msg_len, HWRM_CMD_TIMEOUT); - if (!rc) + if (!rc) { bnxt_copy_from_nvm_data(val, data, nvm_param.nvm_num_bits, nvm_param.dl_num_bytes); + } else { + struct hwrm_err_output *resp = bp->hwrm_cmd_resp_addr; + + if (resp->cmd_err == + NVM_GET_VARIABLE_CMD_ERR_CODE_VAR_NOT_EXIST) + rc = -EOPNOTSUPP; + } } dma_free_coherent(&bp->pdev->dev, sizeof(*data), data, data_dma_addr); if (rc == -EACCES) @@ -409,7 +441,10 @@ int bnxt_dl_register(struct bnxt *bp) return -ENOTSUPP; } - dl = devlink_alloc(&bnxt_dl_ops, sizeof(struct bnxt_dl)); + if (BNXT_PF(bp)) + dl = devlink_alloc(&bnxt_dl_ops, sizeof(struct bnxt_dl)); + else + dl = devlink_alloc(&bnxt_vf_dl_ops, sizeof(struct bnxt_dl)); if (!dl) { netdev_warn(bp->dev, "devlink_alloc failed"); return -ENOMEM; @@ -428,6 +463,9 @@ int bnxt_dl_register(struct bnxt *bp) goto err_dl_free; } + if (!BNXT_PF(bp)) + return 0; + rc = devlink_params_register(dl, bnxt_dl_params, ARRAY_SIZE(bnxt_dl_params)); if (rc) { @@ -455,8 +493,6 @@ int bnxt_dl_register(struct bnxt *bp) devlink_params_publish(dl); - bnxt_dl_fw_reporters_create(bp); - return 0; err_dl_port_unreg: @@ -479,12 +515,14 @@ void bnxt_dl_unregister(struct bnxt *bp) if (!dl) return; - bnxt_dl_fw_reporters_destroy(bp); - devlink_port_params_unregister(&bp->dl_port, bnxt_dl_port_params, - ARRAY_SIZE(bnxt_dl_port_params)); - devlink_port_unregister(&bp->dl_port); - devlink_params_unregister(dl, bnxt_dl_params, - ARRAY_SIZE(bnxt_dl_params)); + if (BNXT_PF(bp)) { + devlink_port_params_unregister(&bp->dl_port, + bnxt_dl_port_params, + ARRAY_SIZE(bnxt_dl_port_params)); + devlink_port_unregister(&bp->dl_port); + devlink_params_unregister(dl, bnxt_dl_params, + ARRAY_SIZE(bnxt_dl_params)); + } devlink_unregister(dl); devlink_free(dl); } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h index 2f4fd0a7d04b..689c47ab2155 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h @@ -57,6 +57,8 @@ struct bnxt_dl_nvm_param { }; void bnxt_devlink_health_report(struct bnxt *bp, unsigned long event); +void bnxt_dl_fw_reporters_create(struct bnxt *bp); +void bnxt_dl_fw_reporters_destroy(struct bnxt *bp, bool all); int bnxt_dl_register(struct bnxt *bp); void bnxt_dl_unregister(struct bnxt *bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 51c140476717..ece70f61c89a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -173,6 +173,7 @@ static const char * const bnxt_ring_tpa2_stats_str[] = { static const char * const bnxt_ring_sw_stats_str[] = { "rx_l4_csum_errors", + "rx_buf_errors", "missed_irqs", }; @@ -552,6 +553,7 @@ static void bnxt_get_ethtool_stats(struct net_device *dev, for (k = 0; k < stat_fields; j++, k++) buf[j] = le64_to_cpu(hw_stats[k]); buf[j++] = cpr->rx_l4_csum_errors; + buf[j++] = cpr->rx_buf_errors; buf[j++] = cpr->missed_irqs; bnxt_sw_func_stats[RX_TOTAL_DISCARDS].counter += @@ -3062,8 +3064,15 @@ static int bnxt_hwrm_dbg_dma_data(struct bnxt *bp, void *msg, int msg_len, } } - if (info->dest_buf) - memcpy(info->dest_buf + off, dma_buf, len); + if (info->dest_buf) { + if ((info->seg_start + off + len) <= + BNXT_COREDUMP_BUF_LEN(info->buf_len)) { + memcpy(info->dest_buf + off, dma_buf, len); + } else { + rc = -ENOBUFS; + break; + } + } if (cmn_req->req_type == cpu_to_le16(HWRM_DBG_COREDUMP_RETRIEVE)) @@ -3117,7 +3126,7 @@ static int bnxt_hwrm_dbg_coredump_initiate(struct bnxt *bp, u16 component_id, static int bnxt_hwrm_dbg_coredump_retrieve(struct bnxt *bp, u16 component_id, u16 segment_id, u32 *seg_len, - void *buf, u32 offset) + void *buf, u32 buf_len, u32 offset) { struct hwrm_dbg_coredump_retrieve_input req = {0}; struct bnxt_hwrm_dbg_dma_info info = {NULL}; @@ -3132,8 +3141,11 @@ static int bnxt_hwrm_dbg_coredump_retrieve(struct bnxt *bp, u16 component_id, seq_no); info.data_len_off = offsetof(struct hwrm_dbg_coredump_retrieve_output, data_len); - if (buf) + if (buf) { info.dest_buf = buf + offset; + info.buf_len = buf_len; + info.seg_start = offset; + } rc = bnxt_hwrm_dbg_dma_data(bp, &req, sizeof(req), &info); if (!rc) @@ -3223,14 +3235,17 @@ bnxt_fill_coredump_record(struct bnxt *bp, struct bnxt_coredump_record *record, static int bnxt_get_coredump(struct bnxt *bp, void *buf, u32 *dump_len) { u32 ver_get_resp_len = sizeof(struct hwrm_ver_get_output); + u32 offset = 0, seg_hdr_len, seg_record_len, buf_len = 0; struct coredump_segment_record *seg_record = NULL; - u32 offset = 0, seg_hdr_len, seg_record_len; struct bnxt_coredump_segment_hdr seg_hdr; struct bnxt_coredump coredump = {NULL}; time64_t start_time; u16 start_utc; int rc = 0, i; + if (buf) + buf_len = *dump_len; + start_time = ktime_get_real_seconds(); start_utc = sys_tz.tz_minuteswest * 60; seg_hdr_len = sizeof(seg_hdr); @@ -3263,6 +3278,12 @@ static int bnxt_get_coredump(struct bnxt *bp, void *buf, u32 *dump_len) u32 duration = 0, seg_len = 0; unsigned long start, end; + if (buf && ((offset + seg_hdr_len) > + BNXT_COREDUMP_BUF_LEN(buf_len))) { + rc = -ENOBUFS; + goto err; + } + start = jiffies; rc = bnxt_hwrm_dbg_coredump_initiate(bp, comp_id, seg_id); @@ -3275,9 +3296,11 @@ static int bnxt_get_coredump(struct bnxt *bp, void *buf, u32 *dump_len) /* Write segment data into the buffer */ rc = bnxt_hwrm_dbg_coredump_retrieve(bp, comp_id, seg_id, - &seg_len, buf, + &seg_len, buf, buf_len, offset + seg_hdr_len); - if (rc) + if (rc && rc == -ENOBUFS) + goto err; + else if (rc) netdev_err(bp->dev, "Failed to retrieve coredump for seg = %d\n", seg_record->segment_id); @@ -3307,7 +3330,8 @@ static int bnxt_get_coredump(struct bnxt *bp, void *buf, u32 *dump_len) rc); kfree(coredump.data); *dump_len += sizeof(struct bnxt_coredump_record); - + if (rc == -ENOBUFS) + netdev_err(bp->dev, "Firmware returned large coredump buffer"); return rc; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h index b5b65b3f8534..3998f6e809a9 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h @@ -31,6 +31,8 @@ struct bnxt_coredump { u16 total_segs; }; +#define BNXT_COREDUMP_BUF_LEN(len) ((len) - sizeof(struct bnxt_coredump_record)) + struct bnxt_hwrm_dbg_dma_info { void *dest_buf; int dest_buf_size; @@ -38,6 +40,8 @@ struct bnxt_hwrm_dbg_dma_info { u16 seq_off; u16 data_len_off; u16 segs; + u32 seg_start; + u32 buf_len; }; struct hwrm_dbg_cmn_input { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c index b2c160947fc8..30816ec4fa91 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c @@ -113,8 +113,10 @@ static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, int ulp_id, { struct net_device *dev = edev->net; struct bnxt *bp = netdev_priv(dev); + struct bnxt_hw_resc *hw_resc; int max_idx, max_cp_rings; int avail_msix, idx; + int total_vecs; int rc = 0; ASSERT_RTNL(); @@ -142,7 +144,10 @@ static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, int ulp_id, } edev->ulp_tbl[ulp_id].msix_base = idx; edev->ulp_tbl[ulp_id].msix_requested = avail_msix; - if (bp->total_irqs < (idx + avail_msix)) { + hw_resc = &bp->hw_resc; + total_vecs = idx + avail_msix; + if (bp->total_irqs < total_vecs || + (BNXT_NEW_RM(bp) && hw_resc->resv_irqs < total_vecs)) { if (netif_running(dev)) { bnxt_close_nic(bp, true, false); rc = bnxt_open_nic(bp, true, false); @@ -156,7 +161,6 @@ static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, int ulp_id, } if (BNXT_NEW_RM(bp)) { - struct bnxt_hw_resc *hw_resc = &bp->hw_resc; int resv_msix; resv_msix = hw_resc->resv_irqs - bp->cp_nr_rings; diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 1e1b774e1953..f496b248bda3 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -4027,7 +4027,7 @@ static int fu540_c000_clk_init(struct platform_device *pdev, struct clk **pclk, mgmt->rate = 0; mgmt->hw.init = &init; - *tx_clk = clk_register(NULL, &mgmt->hw); + *tx_clk = devm_clk_register(&pdev->dev, &mgmt->hw); if (IS_ERR(*tx_clk)) return PTR_ERR(*tx_clk); @@ -4361,7 +4361,6 @@ static int macb_probe(struct platform_device *pdev) err_disable_clocks: clk_disable_unprepare(tx_clk); - clk_unregister(tx_clk); clk_disable_unprepare(hclk); clk_disable_unprepare(pclk); clk_disable_unprepare(rx_clk); @@ -4392,11 +4391,11 @@ static int macb_remove(struct platform_device *pdev) mdiobus_free(bp->mii_bus); unregister_netdev(dev); + tasklet_kill(&bp->hresp_err_tasklet); pm_runtime_disable(&pdev->dev); pm_runtime_dont_use_autosuspend(&pdev->dev); if (!pm_runtime_suspended(&pdev->dev)) { clk_disable_unprepare(bp->tx_clk); - clk_unregister(bp->tx_clk); clk_disable_unprepare(bp->hclk); clk_disable_unprepare(bp->pclk); clk_disable_unprepare(bp->rx_clk); diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index acb016834f04..6cc100e7d5c0 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -1115,7 +1115,7 @@ static int bgx_lmac_enable(struct bgx *bgx, u8 lmacid) phy_interface_mode(lmac->lmac_type))) return -ENODEV; - phy_start_aneg(lmac->phydev); + phy_start(lmac->phydev); return 0; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index 1fbb640e896a..4025a683fa7d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -503,6 +503,7 @@ struct link_config { enum cc_pause requested_fc; /* flow control user has requested */ enum cc_pause fc; /* actual link flow control */ + enum cc_pause advertised_fc; /* actual advertised flow control */ enum cc_fec requested_fec; /* Forward Error Correction: */ enum cc_fec fec; /* requested and actual in use */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c index ae6a47dd7dc9..fb8ade9a05a9 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c @@ -2996,6 +2996,9 @@ static int sge_queue_entries(const struct adapter *adap) int tot_uld_entries = 0; int i; + if (!is_uld(adap)) + goto lld_only; + mutex_lock(&uld_mutex); for (i = 0; i < CXGB4_TX_MAX; i++) tot_uld_entries += sge_qinfo_uld_txq_entries(adap, i); @@ -3006,6 +3009,7 @@ static int sge_queue_entries(const struct adapter *adap) } mutex_unlock(&uld_mutex); +lld_only: return DIV_ROUND_UP(adap->sge.ethqsets, 4) + tot_uld_entries + DIV_ROUND_UP(MAX_CTRL_QUEUES, 4) + 1; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c index 76538f4cd595..f537be9cb315 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c @@ -793,8 +793,8 @@ static void get_pauseparam(struct net_device *dev, struct port_info *p = netdev_priv(dev); epause->autoneg = (p->link_cfg.requested_fc & PAUSE_AUTONEG) != 0; - epause->rx_pause = (p->link_cfg.fc & PAUSE_RX) != 0; - epause->tx_pause = (p->link_cfg.fc & PAUSE_TX) != 0; + epause->rx_pause = (p->link_cfg.advertised_fc & PAUSE_RX) != 0; + epause->tx_pause = (p->link_cfg.advertised_fc & PAUSE_TX) != 0; } static int set_pauseparam(struct net_device *dev, diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index f2a7824da42b..3f6813daf3c1 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -4089,7 +4089,8 @@ static inline fw_port_cap32_t cc_to_fwcap_pause(enum cc_pause cc_pause) if (cc_pause & PAUSE_TX) fw_pause |= FW_PORT_CAP32_802_3_PAUSE; else - fw_pause |= FW_PORT_CAP32_802_3_ASM_DIR; + fw_pause |= FW_PORT_CAP32_802_3_ASM_DIR | + FW_PORT_CAP32_802_3_PAUSE; } else if (cc_pause & PAUSE_TX) { fw_pause |= FW_PORT_CAP32_802_3_ASM_DIR; } @@ -8563,17 +8564,17 @@ static fw_port_cap32_t lstatus_to_fwcap(u32 lstatus) void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl) { const struct fw_port_cmd *cmd = (const void *)rpl; - int action = FW_PORT_CMD_ACTION_G(be32_to_cpu(cmd->action_to_len16)); - struct adapter *adapter = pi->adapter; + fw_port_cap32_t pcaps, acaps, lpacaps, linkattr; struct link_config *lc = &pi->link_cfg; - int link_ok, linkdnrc; - enum fw_port_type port_type; + struct adapter *adapter = pi->adapter; + unsigned int speed, fc, fec, adv_fc; enum fw_port_module_type mod_type; - unsigned int speed, fc, fec; - fw_port_cap32_t pcaps, acaps, lpacaps, linkattr; + int action, link_ok, linkdnrc; + enum fw_port_type port_type; /* Extract the various fields from the Port Information message. */ + action = FW_PORT_CMD_ACTION_G(be32_to_cpu(cmd->action_to_len16)); switch (action) { case FW_PORT_ACTION_GET_PORT_INFO: { u32 lstatus = be32_to_cpu(cmd->u.info.lstatus_to_modtype); @@ -8611,6 +8612,7 @@ void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl) } fec = fwcap_to_cc_fec(acaps); + adv_fc = fwcap_to_cc_pause(acaps); fc = fwcap_to_cc_pause(linkattr); speed = fwcap_to_speed(linkattr); @@ -8667,7 +8669,9 @@ void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl) } if (link_ok != lc->link_ok || speed != lc->speed || - fc != lc->fc || fec != lc->fec) { /* something changed */ + fc != lc->fc || adv_fc != lc->advertised_fc || + fec != lc->fec) { + /* something changed */ if (!link_ok && lc->link_ok) { lc->link_down_rc = linkdnrc; dev_warn_ratelimited(adapter->pdev_dev, @@ -8677,6 +8681,7 @@ void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl) } lc->link_ok = link_ok; lc->speed = speed; + lc->advertised_fc = adv_fc; lc->fc = fc; lc->fec = fec; diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index f6fc0875d5b0..f4d41f968afa 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -1690,8 +1690,8 @@ static void cxgb4vf_get_pauseparam(struct net_device *dev, struct port_info *pi = netdev_priv(dev); pauseparam->autoneg = (pi->link_cfg.requested_fc & PAUSE_AUTONEG) != 0; - pauseparam->rx_pause = (pi->link_cfg.fc & PAUSE_RX) != 0; - pauseparam->tx_pause = (pi->link_cfg.fc & PAUSE_TX) != 0; + pauseparam->rx_pause = (pi->link_cfg.advertised_fc & PAUSE_RX) != 0; + pauseparam->tx_pause = (pi->link_cfg.advertised_fc & PAUSE_TX) != 0; } /* diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h index ccca67cf4487..57cfd10a99ec 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h +++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h @@ -135,6 +135,7 @@ struct link_config { enum cc_pause requested_fc; /* flow control user has requested */ enum cc_pause fc; /* actual link flow control */ + enum cc_pause advertised_fc; /* actual advertised flow control */ enum cc_fec auto_fec; /* Forward Error Correction: */ enum cc_fec requested_fec; /* "automatic" (IEEE 802.3), */ diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c index 8a389d617a23..9d49ff211cc1 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c @@ -1913,16 +1913,16 @@ static const char *t4vf_link_down_rc_str(unsigned char link_down_rc) static void t4vf_handle_get_port_info(struct port_info *pi, const struct fw_port_cmd *cmd) { - int action = FW_PORT_CMD_ACTION_G(be32_to_cpu(cmd->action_to_len16)); - struct adapter *adapter = pi->adapter; + fw_port_cap32_t pcaps, acaps, lpacaps, linkattr; struct link_config *lc = &pi->link_cfg; - int link_ok, linkdnrc; - enum fw_port_type port_type; + struct adapter *adapter = pi->adapter; + unsigned int speed, fc, fec, adv_fc; enum fw_port_module_type mod_type; - unsigned int speed, fc, fec; - fw_port_cap32_t pcaps, acaps, lpacaps, linkattr; + int action, link_ok, linkdnrc; + enum fw_port_type port_type; /* Extract the various fields from the Port Information message. */ + action = FW_PORT_CMD_ACTION_G(be32_to_cpu(cmd->action_to_len16)); switch (action) { case FW_PORT_ACTION_GET_PORT_INFO: { u32 lstatus = be32_to_cpu(cmd->u.info.lstatus_to_modtype); @@ -1982,6 +1982,7 @@ static void t4vf_handle_get_port_info(struct port_info *pi, } fec = fwcap_to_cc_fec(acaps); + adv_fc = fwcap_to_cc_pause(acaps); fc = fwcap_to_cc_pause(linkattr); speed = fwcap_to_speed(linkattr); @@ -2012,7 +2013,9 @@ static void t4vf_handle_get_port_info(struct port_info *pi, } if (link_ok != lc->link_ok || speed != lc->speed || - fc != lc->fc || fec != lc->fec) { /* something changed */ + fc != lc->fc || adv_fc != lc->advertised_fc || + fec != lc->fec) { + /* something changed */ if (!link_ok && lc->link_ok) { lc->link_down_rc = linkdnrc; dev_warn_ratelimited(adapter->pdev_dev, @@ -2022,6 +2025,7 @@ static void t4vf_handle_get_port_info(struct port_info *pi, } lc->link_ok = link_ok; lc->speed = speed; + lc->advertised_fc = adv_fc; lc->fc = fc; lc->fec = fec; diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index a8f4c69252ff..2814b96751b4 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -576,6 +576,8 @@ static int gmac_setup_txqs(struct net_device *netdev) if (port->txq_dma_base & ~DMA_Q_BASE_MASK) { dev_warn(geth->dev, "TX queue base is not aligned\n"); + dma_free_coherent(geth->dev, len * sizeof(*desc_ring), + desc_ring, port->txq_dma_base); kfree(skb_tab); return -ENOMEM; } diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c index a9503aea527f..6437fe6b9abf 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c @@ -160,10 +160,10 @@ static int dpaa2_ptp_probe(struct fsl_mc_device *mc_dev) irq = mc_dev->irqs[0]; ptp_qoriq->irq = irq->msi_desc->irq; - err = devm_request_threaded_irq(dev, ptp_qoriq->irq, NULL, - dpaa2_ptp_irq_handler_thread, - IRQF_NO_SUSPEND | IRQF_ONESHOT, - dev_name(dev), ptp_qoriq); + err = request_threaded_irq(ptp_qoriq->irq, NULL, + dpaa2_ptp_irq_handler_thread, + IRQF_NO_SUSPEND | IRQF_ONESHOT, + dev_name(dev), ptp_qoriq); if (err < 0) { dev_err(dev, "devm_request_threaded_irq(): %d\n", err); goto err_free_mc_irq; @@ -173,18 +173,20 @@ static int dpaa2_ptp_probe(struct fsl_mc_device *mc_dev) DPRTC_IRQ_INDEX, 1); if (err < 0) { dev_err(dev, "dprtc_set_irq_enable(): %d\n", err); - goto err_free_mc_irq; + goto err_free_threaded_irq; } err = ptp_qoriq_init(ptp_qoriq, base, &dpaa2_ptp_caps); if (err) - goto err_free_mc_irq; + goto err_free_threaded_irq; dpaa2_phc_index = ptp_qoriq->phc_index; dev_set_drvdata(dev, ptp_qoriq); return 0; +err_free_threaded_irq: + free_irq(ptp_qoriq->irq, ptp_qoriq); err_free_mc_irq: fsl_mc_free_irqs(mc_dev); err_unmap: diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 4bb30761abfc..8336f4cbaf95 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -2199,8 +2199,14 @@ static void fec_enet_get_regs(struct net_device *ndev, { struct fec_enet_private *fep = netdev_priv(ndev); u32 __iomem *theregs = (u32 __iomem *)fep->hwp; + struct device *dev = &fep->pdev->dev; u32 *buf = (u32 *)regbuf; u32 i, off; + int ret; + + ret = pm_runtime_get_sync(dev); + if (ret < 0) + return; regs->version = fec_enet_register_version; @@ -2216,6 +2222,9 @@ static void fec_enet_get_regs(struct net_device *ndev, off >>= 2; buf[off] = readl(&theregs[off]); } + + pm_runtime_mark_last_busy(dev); + pm_runtime_put_autosuspend(dev); } static int fec_enet_get_ts_info(struct net_device *ndev, diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index aca95f64bde8..9b7a8db9860f 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -544,7 +544,7 @@ static int gve_alloc_queue_page_list(struct gve_priv *priv, u32 id, } qpl->id = id; - qpl->num_entries = pages; + qpl->num_entries = 0; qpl->pages = kvzalloc(pages * sizeof(*qpl->pages), GFP_KERNEL); /* caller handles clean up */ if (!qpl->pages) @@ -562,6 +562,7 @@ static int gve_alloc_queue_page_list(struct gve_priv *priv, u32 id, /* caller handles clean up */ if (err) return -ENOMEM; + qpl->num_entries++; } priv->num_registered_pages += pages; diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c index 4606a7e4a6d1..2ffe035e96d6 100644 --- a/drivers/net/ethernet/hisilicon/hip04_eth.c +++ b/drivers/net/ethernet/hisilicon/hip04_eth.c @@ -543,9 +543,9 @@ hip04_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev) skb_tx_timestamp(skb); hip04_set_xmit_desc(priv, phys); - priv->tx_head = TX_NEXT(tx_head); count++; netdev_sent_queue(ndev, skb->len); + priv->tx_head = TX_NEXT(tx_head); stats->tx_bytes += skb->len; stats->tx_packets++; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 616cad0faa21..84d8816c8681 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -1692,6 +1692,9 @@ static bool hns3_get_tx_timeo_queue_info(struct net_device *ndev) time_after(jiffies, (trans_start + ndev->watchdog_timeo))) { timeout_queue = i; + netdev_info(ndev, "queue state: 0x%lx, delta msecs: %u\n", + q->state, + jiffies_to_msecs(jiffies - trans_start)); break; } } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index c052bb33b3d3..162881005a6d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -9443,6 +9443,9 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev) return ret; } + /* Log and clear the hw errors those already occurred */ + hclge_handle_all_hns_hw_errors(ae_dev); + /* Re-enable the hw error interrupts because * the interrupts get disabled on global reset. */ diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 0686ded7ad3a..e1ab2feeae53 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -176,7 +176,7 @@ static int alloc_long_term_buff(struct ibmvnic_adapter *adapter, ltb->map_id = adapter->map_id; adapter->map_id++; - init_completion(&adapter->fw_done); + reinit_completion(&adapter->fw_done); rc = send_request_map(adapter, ltb->addr, ltb->size, ltb->map_id); if (rc) { @@ -215,7 +215,7 @@ static int reset_long_term_buff(struct ibmvnic_adapter *adapter, memset(ltb->buff, 0, ltb->size); - init_completion(&adapter->fw_done); + reinit_completion(&adapter->fw_done); rc = send_request_map(adapter, ltb->addr, ltb->size, ltb->map_id); if (rc) return rc; @@ -943,7 +943,7 @@ static int ibmvnic_get_vpd(struct ibmvnic_adapter *adapter) if (adapter->vpd->buff) len = adapter->vpd->len; - init_completion(&adapter->fw_done); + reinit_completion(&adapter->fw_done); crq.get_vpd_size.first = IBMVNIC_CRQ_CMD; crq.get_vpd_size.cmd = GET_VPD_SIZE; rc = ibmvnic_send_crq(adapter, &crq); @@ -1689,7 +1689,7 @@ static int __ibmvnic_set_mac(struct net_device *netdev, u8 *dev_addr) crq.change_mac_addr.cmd = CHANGE_MAC_ADDR; ether_addr_copy(&crq.change_mac_addr.mac_addr[0], dev_addr); - init_completion(&adapter->fw_done); + reinit_completion(&adapter->fw_done); rc = ibmvnic_send_crq(adapter, &crq); if (rc) { rc = -EIO; @@ -2316,7 +2316,7 @@ static int wait_for_reset(struct ibmvnic_adapter *adapter) adapter->fallback.rx_entries = adapter->req_rx_add_entries_per_subcrq; adapter->fallback.tx_entries = adapter->req_tx_entries_per_subcrq; - init_completion(&adapter->reset_done); + reinit_completion(&adapter->reset_done); adapter->wait_for_reset = true; rc = ibmvnic_reset(adapter, VNIC_RESET_CHANGE_PARAM); if (rc) @@ -2332,7 +2332,7 @@ static int wait_for_reset(struct ibmvnic_adapter *adapter) adapter->desired.rx_entries = adapter->fallback.rx_entries; adapter->desired.tx_entries = adapter->fallback.tx_entries; - init_completion(&adapter->reset_done); + reinit_completion(&adapter->reset_done); adapter->wait_for_reset = true; rc = ibmvnic_reset(adapter, VNIC_RESET_CHANGE_PARAM); if (rc) @@ -2603,7 +2603,7 @@ static void ibmvnic_get_ethtool_stats(struct net_device *dev, cpu_to_be32(sizeof(struct ibmvnic_statistics)); /* Wait for data to be written */ - init_completion(&adapter->stats_done); + reinit_completion(&adapter->stats_done); rc = ibmvnic_send_crq(adapter, &crq); if (rc) return; @@ -4408,7 +4408,7 @@ static int send_query_phys_parms(struct ibmvnic_adapter *adapter) memset(&crq, 0, sizeof(crq)); crq.query_phys_parms.first = IBMVNIC_CRQ_CMD; crq.query_phys_parms.cmd = QUERY_PHYS_PARMS; - init_completion(&adapter->fw_done); + reinit_completion(&adapter->fw_done); rc = ibmvnic_send_crq(adapter, &crq); if (rc) return rc; @@ -4960,6 +4960,9 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) INIT_LIST_HEAD(&adapter->rwi_list); spin_lock_init(&adapter->rwi_lock); init_completion(&adapter->init_done); + init_completion(&adapter->fw_done); + init_completion(&adapter->reset_done); + init_completion(&adapter->stats_done); clear_bit(0, &adapter->resetting); do { diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index 6c51b1bad8c4..37a2314d3e6b 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -185,13 +185,12 @@ struct e1000_phy_regs { /* board specific private data structure */ struct e1000_adapter { + struct timer_list watchdog_timer; struct timer_list phy_info_timer; struct timer_list blink_timer; struct work_struct reset_task; - struct delayed_work watchdog_task; - - struct workqueue_struct *e1000_workqueue; + struct work_struct watchdog_task; const struct e1000_info *ei; diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index d7d56e42a6aa..060daf66bf63 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -1780,8 +1780,7 @@ static irqreturn_t e1000_intr_msi(int __always_unused irq, void *data) } /* guard against interrupt when we're going down */ if (!test_bit(__E1000_DOWN, &adapter->state)) - mod_delayed_work(adapter->e1000_workqueue, - &adapter->watchdog_task, HZ); + mod_timer(&adapter->watchdog_timer, jiffies + 1); } /* Reset on uncorrectable ECC error */ @@ -1861,8 +1860,7 @@ static irqreturn_t e1000_intr(int __always_unused irq, void *data) } /* guard against interrupt when we're going down */ if (!test_bit(__E1000_DOWN, &adapter->state)) - mod_delayed_work(adapter->e1000_workqueue, - &adapter->watchdog_task, HZ); + mod_timer(&adapter->watchdog_timer, jiffies + 1); } /* Reset on uncorrectable ECC error */ @@ -1907,8 +1905,7 @@ static irqreturn_t e1000_msix_other(int __always_unused irq, void *data) hw->mac.get_link_status = true; /* guard against interrupt when we're going down */ if (!test_bit(__E1000_DOWN, &adapter->state)) - mod_delayed_work(adapter->e1000_workqueue, - &adapter->watchdog_task, HZ); + mod_timer(&adapter->watchdog_timer, jiffies + 1); } if (!test_bit(__E1000_DOWN, &adapter->state)) @@ -4281,6 +4278,7 @@ void e1000e_down(struct e1000_adapter *adapter, bool reset) napi_synchronize(&adapter->napi); + del_timer_sync(&adapter->watchdog_timer); del_timer_sync(&adapter->phy_info_timer); spin_lock(&adapter->stats64_lock); @@ -5152,11 +5150,25 @@ static void e1000e_check_82574_phy_workaround(struct e1000_adapter *adapter) } } +/** + * e1000_watchdog - Timer Call-back + * @data: pointer to adapter cast into an unsigned long + **/ +static void e1000_watchdog(struct timer_list *t) +{ + struct e1000_adapter *adapter = from_timer(adapter, t, watchdog_timer); + + /* Do the rest outside of interrupt context */ + schedule_work(&adapter->watchdog_task); + + /* TODO: make this use queue_delayed_work() */ +} + static void e1000_watchdog_task(struct work_struct *work) { struct e1000_adapter *adapter = container_of(work, struct e1000_adapter, - watchdog_task.work); + watchdog_task); struct net_device *netdev = adapter->netdev; struct e1000_mac_info *mac = &adapter->hw.mac; struct e1000_phy_info *phy = &adapter->hw.phy; @@ -5404,9 +5416,8 @@ static void e1000_watchdog_task(struct work_struct *work) /* Reset the timer */ if (!test_bit(__E1000_DOWN, &adapter->state)) - queue_delayed_work(adapter->e1000_workqueue, - &adapter->watchdog_task, - round_jiffies(2 * HZ)); + mod_timer(&adapter->watchdog_timer, + round_jiffies(jiffies + 2 * HZ)); } #define E1000_TX_FLAGS_CSUM 0x00000001 @@ -7259,21 +7270,11 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_eeprom; } - adapter->e1000_workqueue = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0, - e1000e_driver_name); - - if (!adapter->e1000_workqueue) { - err = -ENOMEM; - goto err_workqueue; - } - - INIT_DELAYED_WORK(&adapter->watchdog_task, e1000_watchdog_task); - queue_delayed_work(adapter->e1000_workqueue, &adapter->watchdog_task, - 0); - + timer_setup(&adapter->watchdog_timer, e1000_watchdog, 0); timer_setup(&adapter->phy_info_timer, e1000_update_phy_info, 0); INIT_WORK(&adapter->reset_task, e1000_reset_task); + INIT_WORK(&adapter->watchdog_task, e1000_watchdog_task); INIT_WORK(&adapter->downshift_task, e1000e_downshift_workaround); INIT_WORK(&adapter->update_phy_task, e1000e_update_phy_task); INIT_WORK(&adapter->print_hang_task, e1000_print_hw_hang); @@ -7367,9 +7368,6 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return 0; err_register: - flush_workqueue(adapter->e1000_workqueue); - destroy_workqueue(adapter->e1000_workqueue); -err_workqueue: if (!(adapter->flags & FLAG_HAS_AMT)) e1000e_release_hw_control(adapter); err_eeprom: @@ -7416,17 +7414,15 @@ static void e1000_remove(struct pci_dev *pdev) */ if (!down) set_bit(__E1000_DOWN, &adapter->state); + del_timer_sync(&adapter->watchdog_timer); del_timer_sync(&adapter->phy_info_timer); cancel_work_sync(&adapter->reset_task); + cancel_work_sync(&adapter->watchdog_task); cancel_work_sync(&adapter->downshift_task); cancel_work_sync(&adapter->update_phy_task); cancel_work_sync(&adapter->print_hang_task); - cancel_delayed_work(&adapter->watchdog_task); - flush_workqueue(adapter->e1000_workqueue); - destroy_workqueue(adapter->e1000_workqueue); - if (adapter->flags & FLAG_HAS_HW_TIMESTAMP) { cancel_work_sync(&adapter->tx_hwtstamp_work); if (adapter->tx_hwtstamp_skb) { diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 2af9f6308f84..401304d4d553 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -1151,7 +1151,7 @@ void i40e_set_fec_in_flags(u8 fec_cfg, u32 *flags); static inline bool i40e_enabled_xdp_vsi(struct i40e_vsi *vsi) { - return !!vsi->xdp_prog; + return !!READ_ONCE(vsi->xdp_prog); } int i40e_create_queue_channel(struct i40e_vsi *vsi, struct i40e_channel *ch); diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index 7560f06768e0..3160b5bbe672 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -2571,9 +2571,16 @@ noinline_for_stack i40e_status i40e_update_link_info(struct i40e_hw *hw) if (status) return status; - hw->phy.link_info.req_fec_info = - abilities.fec_cfg_curr_mod_ext_info & - (I40E_AQ_REQUEST_FEC_KR | I40E_AQ_REQUEST_FEC_RS); + if (abilities.fec_cfg_curr_mod_ext_info & + I40E_AQ_ENABLE_FEC_AUTO) + hw->phy.link_info.req_fec_info = + (I40E_AQ_REQUEST_FEC_KR | + I40E_AQ_REQUEST_FEC_RS); + else + hw->phy.link_info.req_fec_info = + abilities.fec_cfg_curr_mod_ext_info & + (I40E_AQ_REQUEST_FEC_KR | + I40E_AQ_REQUEST_FEC_RS); memcpy(hw->phy.link_info.module_type, &abilities.module_type, sizeof(hw->phy.link_info.module_type)); diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 41e1240acaea..b577e6adf3bf 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -722,7 +722,14 @@ static void i40e_get_settings_link_up_fec(u8 req_fec_info, ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS); ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER); - if (I40E_AQ_SET_FEC_REQUEST_RS & req_fec_info) { + if ((I40E_AQ_SET_FEC_REQUEST_RS & req_fec_info) && + (I40E_AQ_SET_FEC_REQUEST_KR & req_fec_info)) { + ethtool_link_ksettings_add_link_mode(ks, advertising, + FEC_NONE); + ethtool_link_ksettings_add_link_mode(ks, advertising, + FEC_BASER); + ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS); + } else if (I40E_AQ_SET_FEC_REQUEST_RS & req_fec_info) { ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS); } else if (I40E_AQ_SET_FEC_REQUEST_KR & req_fec_info) { ethtool_link_ksettings_add_link_mode(ks, advertising, @@ -730,12 +737,6 @@ static void i40e_get_settings_link_up_fec(u8 req_fec_info, } else { ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_NONE); - if (I40E_AQ_SET_FEC_AUTO & req_fec_info) { - ethtool_link_ksettings_add_link_mode(ks, advertising, - FEC_RS); - ethtool_link_ksettings_add_link_mode(ks, advertising, - FEC_BASER); - } } } @@ -1437,6 +1438,7 @@ static int i40e_get_fec_param(struct net_device *netdev, struct i40e_hw *hw = &pf->hw; i40e_status status = 0; int err = 0; + u8 fec_cfg; /* Get the current phy config */ memset(&abilities, 0, sizeof(abilities)); @@ -1448,18 +1450,16 @@ static int i40e_get_fec_param(struct net_device *netdev, } fecparam->fec = 0; - if (abilities.fec_cfg_curr_mod_ext_info & I40E_AQ_SET_FEC_AUTO) + fec_cfg = abilities.fec_cfg_curr_mod_ext_info; + if (fec_cfg & I40E_AQ_SET_FEC_AUTO) fecparam->fec |= ETHTOOL_FEC_AUTO; - if ((abilities.fec_cfg_curr_mod_ext_info & - I40E_AQ_SET_FEC_REQUEST_RS) || - (abilities.fec_cfg_curr_mod_ext_info & - I40E_AQ_SET_FEC_ABILITY_RS)) + else if (fec_cfg & (I40E_AQ_SET_FEC_REQUEST_RS | + I40E_AQ_SET_FEC_ABILITY_RS)) fecparam->fec |= ETHTOOL_FEC_RS; - if ((abilities.fec_cfg_curr_mod_ext_info & - I40E_AQ_SET_FEC_REQUEST_KR) || - (abilities.fec_cfg_curr_mod_ext_info & I40E_AQ_SET_FEC_ABILITY_KR)) + else if (fec_cfg & (I40E_AQ_SET_FEC_REQUEST_KR | + I40E_AQ_SET_FEC_ABILITY_KR)) fecparam->fec |= ETHTOOL_FEC_BASER; - if (abilities.fec_cfg_curr_mod_ext_info == 0) + if (fec_cfg == 0) fecparam->fec |= ETHTOOL_FEC_OFF; if (hw->phy.link_info.fec_info & I40E_AQ_CONFIG_FEC_KR_ENA) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 6031223eafab..4960c9c3e773 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -3534,14 +3534,14 @@ static void i40e_vsi_configure_msix(struct i40e_vsi *vsi) q_vector->rx.target_itr = ITR_TO_REG(vsi->rx_rings[i]->itr_setting); wr32(hw, I40E_PFINT_ITRN(I40E_RX_ITR, vector - 1), - q_vector->rx.target_itr); + q_vector->rx.target_itr >> 1); q_vector->rx.current_itr = q_vector->rx.target_itr; q_vector->tx.next_update = jiffies + 1; q_vector->tx.target_itr = ITR_TO_REG(vsi->tx_rings[i]->itr_setting); wr32(hw, I40E_PFINT_ITRN(I40E_TX_ITR, vector - 1), - q_vector->tx.target_itr); + q_vector->tx.target_itr >> 1); q_vector->tx.current_itr = q_vector->tx.target_itr; wr32(hw, I40E_PFINT_RATEN(vector - 1), @@ -3646,11 +3646,11 @@ static void i40e_configure_msi_and_legacy(struct i40e_vsi *vsi) /* set the ITR configuration */ q_vector->rx.next_update = jiffies + 1; q_vector->rx.target_itr = ITR_TO_REG(vsi->rx_rings[0]->itr_setting); - wr32(hw, I40E_PFINT_ITR0(I40E_RX_ITR), q_vector->rx.target_itr); + wr32(hw, I40E_PFINT_ITR0(I40E_RX_ITR), q_vector->rx.target_itr >> 1); q_vector->rx.current_itr = q_vector->rx.target_itr; q_vector->tx.next_update = jiffies + 1; q_vector->tx.target_itr = ITR_TO_REG(vsi->tx_rings[0]->itr_setting); - wr32(hw, I40E_PFINT_ITR0(I40E_TX_ITR), q_vector->tx.target_itr); + wr32(hw, I40E_PFINT_ITR0(I40E_TX_ITR), q_vector->tx.target_itr >> 1); q_vector->tx.current_itr = q_vector->tx.target_itr; i40e_enable_misc_int_causes(pf); @@ -6804,8 +6804,8 @@ void i40e_down(struct i40e_vsi *vsi) for (i = 0; i < vsi->num_queue_pairs; i++) { i40e_clean_tx_ring(vsi->tx_rings[i]); if (i40e_enabled_xdp_vsi(vsi)) { - /* Make sure that in-progress ndo_xdp_xmit - * calls are completed. + /* Make sure that in-progress ndo_xdp_xmit and + * ndo_xsk_wakeup calls are completed. */ synchronize_rcu(); i40e_clean_tx_ring(vsi->xdp_rings[i]); @@ -11396,7 +11396,7 @@ static int i40e_setup_misc_vector(struct i40e_pf *pf) /* associate no queues to the misc vector */ wr32(hw, I40E_PFINT_LNKLST0, I40E_QUEUE_END_OF_LIST); - wr32(hw, I40E_PFINT_ITR0(I40E_RX_ITR), I40E_ITR_8K); + wr32(hw, I40E_PFINT_ITR0(I40E_RX_ITR), I40E_ITR_8K >> 1); i40e_flush(hw); @@ -12526,8 +12526,12 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, old_prog = xchg(&vsi->xdp_prog, prog); - if (need_reset) + if (need_reset) { + if (!prog) + /* Wait until ndo_xsk_wakeup completes. */ + synchronize_rcu(); i40e_reset_and_rebuild(pf, true, true); + } for (i = 0; i < vsi->num_queue_pairs; i++) WRITE_ONCE(vsi->rx_rings[i]->xdp_prog, vsi->xdp_prog); diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index d07e1a890428..f73cd917c44f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -787,8 +787,12 @@ int i40e_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags) { struct i40e_netdev_priv *np = netdev_priv(dev); struct i40e_vsi *vsi = np->vsi; + struct i40e_pf *pf = vsi->back; struct i40e_ring *ring; + if (test_bit(__I40E_CONFIG_BUSY, pf->state)) + return -ENETDOWN; + if (test_bit(__I40E_VSI_DOWN, vsi->state)) return -ENETDOWN; diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c index 2353166c654e..c68709c7ef81 100644 --- a/drivers/net/ethernet/intel/ice/ice_controlq.c +++ b/drivers/net/ethernet/intel/ice/ice_controlq.c @@ -948,7 +948,7 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, if (ice_sq_done(hw, cq)) break; - mdelay(1); + udelay(ICE_CTL_Q_SQ_CMD_USEC); total_delay++; } while (total_delay < cq->sq_cmd_timeout); diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.h b/drivers/net/ethernet/intel/ice/ice_controlq.h index 44945c2165d8..4df9da359135 100644 --- a/drivers/net/ethernet/intel/ice/ice_controlq.h +++ b/drivers/net/ethernet/intel/ice/ice_controlq.h @@ -31,8 +31,9 @@ enum ice_ctl_q { ICE_CTL_Q_MAILBOX, }; -/* Control Queue default settings */ -#define ICE_CTL_Q_SQ_CMD_TIMEOUT 250 /* msecs */ +/* Control Queue timeout settings - max delay 250ms */ +#define ICE_CTL_Q_SQ_CMD_TIMEOUT 2500 /* Count 2500 times */ +#define ICE_CTL_Q_SQ_CMD_USEC 100 /* Check every 100usec */ struct ice_ctl_q_ring { void *dma_head; /* Virtual address to DMA head */ diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 7e23034df955..1fe9f6050635 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -3368,10 +3368,17 @@ __ice_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec, struct ice_vsi *vsi = np->vsi; if (q_num < 0) { - int i; + int v_idx; + + ice_for_each_q_vector(vsi, v_idx) { + /* In some cases if DCB is configured the num_[rx|tx]q + * can be less than vsi->num_q_vectors. This check + * accounts for that so we don't report a false failure + */ + if (v_idx >= vsi->num_rxq && v_idx >= vsi->num_txq) + goto set_complete; - ice_for_each_q_vector(vsi, i) { - if (ice_set_q_coalesce(vsi, ec, i)) + if (ice_set_q_coalesce(vsi, ec, v_idx)) return -EINVAL; } goto set_complete; diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 214cd6eca405..2408f0de95fc 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -3970,8 +3970,13 @@ int ice_vsi_setup_tx_rings(struct ice_vsi *vsi) } ice_for_each_txq(vsi, i) { - vsi->tx_rings[i]->netdev = vsi->netdev; - err = ice_setup_tx_ring(vsi->tx_rings[i]); + struct ice_ring *ring = vsi->tx_rings[i]; + + if (!ring) + return -EINVAL; + + ring->netdev = vsi->netdev; + err = ice_setup_tx_ring(ring); if (err) break; } @@ -3996,8 +4001,13 @@ int ice_vsi_setup_rx_rings(struct ice_vsi *vsi) } ice_for_each_rxq(vsi, i) { - vsi->rx_rings[i]->netdev = vsi->netdev; - err = ice_setup_rx_ring(vsi->rx_rings[i]); + struct ice_ring *ring = vsi->rx_rings[i]; + + if (!ring) + return -EINVAL; + + ring->netdev = vsi->netdev; + err = ice_setup_rx_ring(ring); if (err) break; } diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index b45797f39b2f..c0637a0cbfe8 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -317,8 +317,9 @@ void ice_free_vfs(struct ice_pf *pf) pf->num_alloc_vfs = 0; for (i = 0; i < tmp; i++) { if (test_bit(ICE_VF_STATE_INIT, pf->vf[i].vf_states)) { - /* disable VF qp mappings */ + /* disable VF qp mappings and set VF disable state */ ice_dis_vf_mappings(&pf->vf[i]); + set_bit(ICE_VF_STATE_DIS, pf->vf[i].vf_states); ice_free_vf_res(&pf->vf[i]); } } @@ -1287,9 +1288,12 @@ static void ice_vc_notify_vf_reset(struct ice_vf *vf) if (!vf || vf->vf_id >= vf->pf->num_alloc_vfs) return; - /* verify if the VF is in either init or active before proceeding */ - if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states) && - !test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) + /* Bail out if VF is in disabled state, neither initialized, nor active + * state - otherwise proceed with notifications + */ + if ((!test_bit(ICE_VF_STATE_INIT, vf->vf_states) && + !test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) || + test_bit(ICE_VF_STATE_DIS, vf->vf_states)) return; pfe.event = VIRTCHNL_EVENT_RESET_IMPENDING; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 91b3780ddb04..c6404abf2dd1 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -8639,7 +8639,8 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && adapter->ptp_clock) { - if (!test_and_set_bit_lock(__IXGBE_PTP_TX_IN_PROGRESS, + if (adapter->tstamp_config.tx_type == HWTSTAMP_TX_ON && + !test_and_set_bit_lock(__IXGBE_PTP_TX_IN_PROGRESS, &adapter->state)) { skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; tx_flags |= IXGBE_TX_FLAGS_TSTAMP; @@ -10247,7 +10248,12 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) /* If transitioning XDP modes reconfigure rings */ if (need_reset) { - int err = ixgbe_setup_tc(dev, adapter->hw_tcs); + int err; + + if (!prog) + /* Wait until ndo_xsk_wakeup completes. */ + synchronize_rcu(); + err = ixgbe_setup_tc(dev, adapter->hw_tcs); if (err) { rcu_assign_pointer(adapter->xdp_prog, old_prog); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index d6feaacfbf89..b43be9f14105 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -709,10 +709,14 @@ int ixgbe_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) if (qid >= adapter->num_xdp_queues) return -ENXIO; - if (!adapter->xdp_ring[qid]->xsk_umem) + ring = adapter->xdp_ring[qid]; + + if (test_bit(__IXGBE_TX_DISABLED, &ring->state)) + return -ENETDOWN; + + if (!ring->xsk_umem) return -ENXIO; - ring = adapter->xdp_ring[qid]; if (!napi_if_scheduled_mark_missed(&ring->q_vector->napi)) { u64 eics = BIT_ULL(ring->q_vector->v_idx); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 111b3b8239e1..ef44c6979a31 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -3674,7 +3674,7 @@ static int mvpp2_open(struct net_device *dev) valid = true; } - if (priv->hw_version == MVPP22 && port->link_irq && !port->phylink) { + if (priv->hw_version == MVPP22 && port->link_irq) { err = request_irq(port->link_irq, mvpp2_link_status_isr, 0, dev->name, port); if (err) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index f1a7bc46f1c0..9c8427698238 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -760,7 +760,7 @@ enum { MLX5E_STATE_OPENED, MLX5E_STATE_DESTROYING, MLX5E_STATE_XDP_TX_ENABLED, - MLX5E_STATE_XDP_OPEN, + MLX5E_STATE_XDP_ACTIVE, }; struct mlx5e_rqt { @@ -816,7 +816,7 @@ struct mlx5e_xsk { struct mlx5e_priv { /* priv data path fields - start */ struct mlx5e_txqsq *txq2sq[MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC]; - int channel_tc2txq[MLX5E_MAX_NUM_CHANNELS][MLX5E_MAX_NUM_TC]; + int channel_tc2realtxq[MLX5E_MAX_NUM_CHANNELS][MLX5E_MAX_NUM_TC]; #ifdef CONFIG_MLX5_CORE_EN_DCB struct mlx5e_dcbx_dp dcbx_dp; #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h index 68d593074f6c..d48292ccda29 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h @@ -122,6 +122,22 @@ enum { #endif }; +#define MLX5E_TTC_NUM_GROUPS 3 +#define MLX5E_TTC_GROUP1_SIZE (BIT(3) + MLX5E_NUM_TUNNEL_TT) +#define MLX5E_TTC_GROUP2_SIZE BIT(1) +#define MLX5E_TTC_GROUP3_SIZE BIT(0) +#define MLX5E_TTC_TABLE_SIZE (MLX5E_TTC_GROUP1_SIZE +\ + MLX5E_TTC_GROUP2_SIZE +\ + MLX5E_TTC_GROUP3_SIZE) + +#define MLX5E_INNER_TTC_NUM_GROUPS 3 +#define MLX5E_INNER_TTC_GROUP1_SIZE BIT(3) +#define MLX5E_INNER_TTC_GROUP2_SIZE BIT(1) +#define MLX5E_INNER_TTC_GROUP3_SIZE BIT(0) +#define MLX5E_INNER_TTC_TABLE_SIZE (MLX5E_INNER_TTC_GROUP1_SIZE +\ + MLX5E_INNER_TTC_GROUP2_SIZE +\ + MLX5E_INNER_TTC_GROUP3_SIZE) + #ifdef CONFIG_MLX5_EN_RXNFC struct mlx5e_ethtool_table { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c index 1d6b58860da6..3a975641f902 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c @@ -197,9 +197,10 @@ int mlx5e_health_report(struct mlx5e_priv *priv, struct devlink_health_reporter *reporter, char *err_str, struct mlx5e_err_ctx *err_ctx) { - if (!reporter) { - netdev_err(priv->netdev, err_str); + netdev_err(priv->netdev, err_str); + + if (!reporter) return err_ctx->recover(&err_ctx->ctx); - } + return devlink_health_report(reporter, err_str, err_ctx); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c index f777994f3005..fce6eccdcf8b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c @@ -73,6 +73,7 @@ static const u32 mlx5e_ext_link_speed[MLX5E_EXT_LINK_MODES_NUMBER] = { [MLX5E_50GAUI_2_LAUI_2_50GBASE_CR2_KR2] = 50000, [MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR] = 50000, [MLX5E_CAUI_4_100GBASE_CR4_KR4] = 100000, + [MLX5E_100GAUI_2_100GBASE_CR2_KR2] = 100000, [MLX5E_200GAUI_4_200GBASE_CR4_KR4] = 200000, [MLX5E_400GAUI_8] = 400000, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c index 633b117eb13e..99c7cdd0404a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c @@ -155,8 +155,11 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer, } if (port_buffer->buffer[i].size < - (xoff + max_mtu + (1 << MLX5E_BUFFER_CELL_SHIFT))) + (xoff + max_mtu + (1 << MLX5E_BUFFER_CELL_SHIFT))) { + pr_err("buffer_size[%d]=%d is not enough for lossless buffer\n", + i, port_buffer->buffer[i].size); return -ENOMEM; + } port_buffer->buffer[i].xoff = port_buffer->buffer[i].size - xoff; port_buffer->buffer[i].xon = @@ -232,6 +235,26 @@ static int update_buffer_lossy(unsigned int max_mtu, return 0; } +static int fill_pfc_en(struct mlx5_core_dev *mdev, u8 *pfc_en) +{ + u32 g_rx_pause, g_tx_pause; + int err; + + err = mlx5_query_port_pause(mdev, &g_rx_pause, &g_tx_pause); + if (err) + return err; + + /* If global pause enabled, set all active buffers to lossless. + * Otherwise, check PFC setting. + */ + if (g_rx_pause || g_tx_pause) + *pfc_en = 0xff; + else + err = mlx5_query_port_pfc(mdev, pfc_en, NULL); + + return err; +} + #define MINIMUM_MAX_MTU 9216 int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, u32 change, unsigned int mtu, @@ -277,7 +300,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, if (change & MLX5E_PORT_BUFFER_PRIO2BUFFER) { update_prio2buffer = true; - err = mlx5_query_port_pfc(priv->mdev, &curr_pfc_en, NULL); + err = fill_pfc_en(priv->mdev, &curr_pfc_en); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index 745ab6cd7c30..362f01bc8372 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -144,10 +144,10 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv, #if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6) int ret; - ret = ipv6_stub->ipv6_dst_lookup(dev_net(mirred_dev), NULL, &dst, - fl6); - if (ret < 0) - return ret; + dst = ipv6_stub->ipv6_dst_lookup_flow(dev_net(mirred_dev), NULL, fl6, + NULL); + if (IS_ERR(dst)) + return PTR_ERR(dst); if (!(*out_ttl)) *out_ttl = ip6_dst_hoplimit(dst); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h index 36ac1e3816b9..d7587f40ecae 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h @@ -75,12 +75,18 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, static inline void mlx5e_xdp_tx_enable(struct mlx5e_priv *priv) { set_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state); + + if (priv->channels.params.xdp_prog) + set_bit(MLX5E_STATE_XDP_ACTIVE, &priv->state); } static inline void mlx5e_xdp_tx_disable(struct mlx5e_priv *priv) { + if (priv->channels.params.xdp_prog) + clear_bit(MLX5E_STATE_XDP_ACTIVE, &priv->state); + clear_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state); - /* let other device's napi(s) see our new state */ + /* Let other device's napi(s) and XSK wakeups see our new state. */ synchronize_rcu(); } @@ -89,19 +95,9 @@ static inline bool mlx5e_xdp_tx_is_enabled(struct mlx5e_priv *priv) return test_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state); } -static inline void mlx5e_xdp_set_open(struct mlx5e_priv *priv) -{ - set_bit(MLX5E_STATE_XDP_OPEN, &priv->state); -} - -static inline void mlx5e_xdp_set_closed(struct mlx5e_priv *priv) -{ - clear_bit(MLX5E_STATE_XDP_OPEN, &priv->state); -} - -static inline bool mlx5e_xdp_is_open(struct mlx5e_priv *priv) +static inline bool mlx5e_xdp_is_active(struct mlx5e_priv *priv) { - return test_bit(MLX5E_STATE_XDP_OPEN, &priv->state); + return test_bit(MLX5E_STATE_XDP_ACTIVE, &priv->state); } static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c index 631af8dee517..c28cbae42331 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c @@ -144,6 +144,7 @@ void mlx5e_close_xsk(struct mlx5e_channel *c) { clear_bit(MLX5E_CHANNEL_STATE_XSK, c->state); napi_synchronize(&c->napi); + synchronize_rcu(); /* Sync with the XSK wakeup. */ mlx5e_close_rq(&c->xskrq); mlx5e_close_cq(&c->xskrq.cq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c index 87827477d38c..fe2d596cb361 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c @@ -14,7 +14,7 @@ int mlx5e_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) struct mlx5e_channel *c; u16 ix; - if (unlikely(!mlx5e_xdp_is_open(priv))) + if (unlikely(!mlx5e_xdp_is_active(priv))) return -ENETDOWN; if (unlikely(!mlx5e_qid_get_ch_if_in_group(params, qid, MLX5E_RQ_GROUP_XSK, &ix))) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 95601269fa2e..c6776f308d5e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1027,18 +1027,11 @@ static bool ext_link_mode_requested(const unsigned long *adver) return bitmap_intersects(modes, adver, __ETHTOOL_LINK_MODE_MASK_NBITS); } -static bool ext_speed_requested(u32 speed) -{ -#define MLX5E_MAX_PTYS_LEGACY_SPEED 100000 - return !!(speed > MLX5E_MAX_PTYS_LEGACY_SPEED); -} - -static bool ext_requested(u8 autoneg, const unsigned long *adver, u32 speed) +static bool ext_requested(u8 autoneg, const unsigned long *adver, bool ext_supported) { bool ext_link_mode = ext_link_mode_requested(adver); - bool ext_speed = ext_speed_requested(speed); - return autoneg == AUTONEG_ENABLE ? ext_link_mode : ext_speed; + return autoneg == AUTONEG_ENABLE ? ext_link_mode : ext_supported; } int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv, @@ -1065,8 +1058,8 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv, autoneg = link_ksettings->base.autoneg; speed = link_ksettings->base.speed; - ext = ext_requested(autoneg, adver, speed), ext_supported = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet); + ext = ext_requested(autoneg, adver, ext_supported); if (!ext_supported && ext) return -EOPNOTSUPP; @@ -1643,7 +1636,7 @@ static int mlx5e_get_module_info(struct net_device *netdev, break; case MLX5_MODULE_ID_SFP: modinfo->type = ETH_MODULE_SFF_8472; - modinfo->eeprom_len = MLX5_EEPROM_PAGE_LENGTH; + modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN; break; default: netdev_err(priv->netdev, "%s: cable type not recognized:0x%x\n", diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index 15b7f0f1427c..73d3dc07331f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -904,22 +904,6 @@ static int mlx5e_generate_ttc_table_rules(struct mlx5e_priv *priv, return err; } -#define MLX5E_TTC_NUM_GROUPS 3 -#define MLX5E_TTC_GROUP1_SIZE (BIT(3) + MLX5E_NUM_TUNNEL_TT) -#define MLX5E_TTC_GROUP2_SIZE BIT(1) -#define MLX5E_TTC_GROUP3_SIZE BIT(0) -#define MLX5E_TTC_TABLE_SIZE (MLX5E_TTC_GROUP1_SIZE +\ - MLX5E_TTC_GROUP2_SIZE +\ - MLX5E_TTC_GROUP3_SIZE) - -#define MLX5E_INNER_TTC_NUM_GROUPS 3 -#define MLX5E_INNER_TTC_GROUP1_SIZE BIT(3) -#define MLX5E_INNER_TTC_GROUP2_SIZE BIT(1) -#define MLX5E_INNER_TTC_GROUP3_SIZE BIT(0) -#define MLX5E_INNER_TTC_TABLE_SIZE (MLX5E_INNER_TTC_GROUP1_SIZE +\ - MLX5E_INNER_TTC_GROUP2_SIZE +\ - MLX5E_INNER_TTC_GROUP3_SIZE) - static int mlx5e_create_ttc_table_groups(struct mlx5e_ttc_table *ttc, bool use_ipv) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 2a56e66f58d8..29a5a8c894e3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1693,11 +1693,10 @@ static int mlx5e_open_sqs(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_channel_param *cparam) { - struct mlx5e_priv *priv = c->priv; int err, tc; for (tc = 0; tc < params->num_tc; tc++) { - int txq_ix = c->ix + tc * priv->max_nch; + int txq_ix = c->ix + tc * params->num_channels; err = mlx5e_open_txqsq(c, c->priv->tisn[c->lag_port][tc], txq_ix, params, &cparam->sq, &c->sq[tc], tc); @@ -2878,26 +2877,21 @@ static void mlx5e_netdev_set_tcs(struct net_device *netdev) netdev_set_tc_queue(netdev, tc, nch, 0); } -static void mlx5e_build_tc2txq_maps(struct mlx5e_priv *priv) +static void mlx5e_build_txq_maps(struct mlx5e_priv *priv) { - int i, tc; + int i, ch; - for (i = 0; i < priv->max_nch; i++) - for (tc = 0; tc < priv->profile->max_tc; tc++) - priv->channel_tc2txq[i][tc] = i + tc * priv->max_nch; -} + ch = priv->channels.num; -static void mlx5e_build_tx2sq_maps(struct mlx5e_priv *priv) -{ - struct mlx5e_channel *c; - struct mlx5e_txqsq *sq; - int i, tc; + for (i = 0; i < ch; i++) { + int tc; + + for (tc = 0; tc < priv->channels.params.num_tc; tc++) { + struct mlx5e_channel *c = priv->channels.c[i]; + struct mlx5e_txqsq *sq = &c->sq[tc]; - for (i = 0; i < priv->channels.num; i++) { - c = priv->channels.c[i]; - for (tc = 0; tc < c->num_tc; tc++) { - sq = &c->sq[tc]; priv->txq2sq[sq->txq_ix] = sq; + priv->channel_tc2realtxq[i][tc] = i + tc * ch; } } } @@ -2912,7 +2906,7 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv) netif_set_real_num_tx_queues(netdev, num_txqs); netif_set_real_num_rx_queues(netdev, num_rxqs); - mlx5e_build_tx2sq_maps(priv); + mlx5e_build_txq_maps(priv); mlx5e_activate_channels(&priv->channels); mlx5e_xdp_tx_enable(priv); netif_tx_start_all_queues(priv->netdev); @@ -3008,12 +3002,9 @@ void mlx5e_timestamp_init(struct mlx5e_priv *priv) int mlx5e_open_locked(struct net_device *netdev) { struct mlx5e_priv *priv = netdev_priv(netdev); - bool is_xdp = priv->channels.params.xdp_prog; int err; set_bit(MLX5E_STATE_OPENED, &priv->state); - if (is_xdp) - mlx5e_xdp_set_open(priv); err = mlx5e_open_channels(priv, &priv->channels); if (err) @@ -3028,8 +3019,6 @@ int mlx5e_open_locked(struct net_device *netdev) return 0; err_clear_state_opened_flag: - if (is_xdp) - mlx5e_xdp_set_closed(priv); clear_bit(MLX5E_STATE_OPENED, &priv->state); return err; } @@ -3061,8 +3050,6 @@ int mlx5e_close_locked(struct net_device *netdev) if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) return 0; - if (priv->channels.params.xdp_prog) - mlx5e_xdp_set_closed(priv); clear_bit(MLX5E_STATE_OPENED, &priv->state); netif_carrier_off(priv->netdev); @@ -4379,16 +4366,6 @@ static int mlx5e_xdp_allowed(struct mlx5e_priv *priv, struct bpf_prog *prog) return 0; } -static int mlx5e_xdp_update_state(struct mlx5e_priv *priv) -{ - if (priv->channels.params.xdp_prog) - mlx5e_xdp_set_open(priv); - else - mlx5e_xdp_set_closed(priv); - - return 0; -} - static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -4428,7 +4405,7 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) mlx5e_set_rq_type(priv->mdev, &new_channels.params); old_prog = priv->channels.params.xdp_prog; - err = mlx5e_safe_switch_channels(priv, &new_channels, mlx5e_xdp_update_state); + err = mlx5e_safe_switch_channels(priv, &new_channels, NULL); if (err) goto unlock; } else { @@ -5028,7 +5005,6 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev, if (err) mlx5_core_err(mdev, "TLS initialization failed, %d\n", err); mlx5e_build_nic_netdev(netdev); - mlx5e_build_tc2txq_maps(priv); mlx5e_health_create_reporters(priv); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 7e6ebd0505cc..9f09253f9f46 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -1601,7 +1601,7 @@ static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data, for (j = 0; j < NUM_SQ_STATS; j++) sprintf(data + (idx++) * ETH_GSTRING_LEN, sq_stats_desc[j].format, - priv->channel_tc2txq[i][tc]); + i + tc * max_nch); for (i = 0; i < max_nch; i++) { for (j = 0; j < NUM_XSKSQ_STATS * is_xsk; j++) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index f90a9f8e0fc6..947122c68493 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -586,7 +586,7 @@ static void mlx5e_hairpin_set_ttc_params(struct mlx5e_hairpin *hp, for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) ttc_params->indir_tirn[tt] = hp->indir_tirn[tt]; - ft_attr->max_fte = MLX5E_NUM_TT; + ft_attr->max_fte = MLX5E_TTC_TABLE_SIZE; ft_attr->level = MLX5E_TC_TTC_FT_LEVEL; ft_attr->prio = MLX5E_TC_PRIO; } @@ -1616,7 +1616,7 @@ static void __mlx5e_tc_del_fdb_peer_flow(struct mlx5e_tc_flow *flow) flow_flag_clear(flow, DUP); mlx5e_tc_del_fdb_flow(flow->peer_flow->priv, flow->peer_flow); - kvfree(flow->peer_flow); + kfree(flow->peer_flow); flow->peer_flow = NULL; } @@ -3443,6 +3443,12 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; } + if (!(attr->action & + (MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_DROP))) { + NL_SET_ERR_MSG(extack, "Rule must have at least one forward/drop action"); + return -EOPNOTSUPP; + } + if (attr->split_count > 0 && !mlx5_esw_has_fwd_fdb(priv->mdev)) { NL_SET_ERR_MSG_MOD(extack, "current firmware doesn't support split rule for port mirroring"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 67dc4f0921b6..dee12f17f9c2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -93,7 +93,7 @@ u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb, if (txq_ix >= num_channels) txq_ix = priv->txq2sq[txq_ix]->ch_ix; - return priv->channel_tc2txq[txq_ix][up]; + return priv->channel_tc2realtxq[txq_ix][up]; } static inline int mlx5e_skb_l2_header_offset(struct sk_buff *skb) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 50ab88d80033..051ab845b501 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1197,6 +1197,12 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, bool boot) if (err) goto err_load; + if (boot) { + err = mlx5_devlink_register(priv_to_devlink(dev), dev->device); + if (err) + goto err_devlink_reg; + } + if (mlx5_device_registered(dev)) { mlx5_attach_device(dev); } else { @@ -1214,6 +1220,9 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, bool boot) return err; err_reg_dev: + if (boot) + mlx5_devlink_unregister(priv_to_devlink(dev)); +err_devlink_reg: mlx5_unload(dev); err_load: if (boot) @@ -1353,10 +1362,6 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id) request_module_nowait(MLX5_IB_MOD); - err = mlx5_devlink_register(devlink, &pdev->dev); - if (err) - goto clean_load; - err = mlx5_crdump_enable(dev); if (err) dev_err(&pdev->dev, "mlx5_crdump_enable failed with error code %d\n", err); @@ -1364,9 +1369,6 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id) pci_save_state(pdev); return 0; -clean_load: - mlx5_unload_one(dev, true); - err_load_one: mlx5_pci_close(dev); pci_init_err: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c index bd1699e62142..e1a647dde978 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c @@ -209,7 +209,7 @@ static void dr_rule_rehash_copy_ste_ctrl(struct mlx5dr_matcher *matcher, /* We need to copy the refcount since this ste * may have been traversed several times */ - refcount_set(&new_ste->refcount, refcount_read(&cur_ste->refcount)); + new_ste->refcount = cur_ste->refcount; /* Link old STEs rule_mem list to the new ste */ mlx5dr_rule_update_rule_member(cur_ste, new_ste); @@ -638,6 +638,9 @@ static int dr_rule_add_member(struct mlx5dr_rule_rx_tx *nic_rule, if (!rule_mem) return -ENOMEM; + INIT_LIST_HEAD(&rule_mem->list); + INIT_LIST_HEAD(&rule_mem->use_ste_list); + rule_mem->ste = ste; list_add_tail(&rule_mem->list, &nic_rule->rule_members_list); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c index 3cbf74b44d1f..2739ed2a2911 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c @@ -340,7 +340,7 @@ static void dr_ste_replace(struct mlx5dr_ste *dst, struct mlx5dr_ste *src) if (dst->next_htbl) dst->next_htbl->pointing_ste = dst; - refcount_set(&dst->refcount, refcount_read(&src->refcount)); + dst->refcount = src->refcount; INIT_LIST_HEAD(&dst->rule_list); list_splice_tail_init(&src->rule_list, &dst->rule_list); @@ -557,7 +557,7 @@ bool mlx5dr_ste_is_not_valid_entry(u8 *p_hw_ste) bool mlx5dr_ste_not_used_ste(struct mlx5dr_ste *ste) { - return !refcount_read(&ste->refcount); + return !ste->refcount; } /* Init one ste as a pattern for ste data array */ @@ -681,14 +681,14 @@ struct mlx5dr_ste_htbl *mlx5dr_ste_htbl_alloc(struct mlx5dr_icm_pool *pool, htbl->ste_arr = chunk->ste_arr; htbl->hw_ste_arr = chunk->hw_ste_arr; htbl->miss_list = chunk->miss_list; - refcount_set(&htbl->refcount, 0); + htbl->refcount = 0; for (i = 0; i < chunk->num_of_entries; i++) { struct mlx5dr_ste *ste = &htbl->ste_arr[i]; ste->hw_ste = htbl->hw_ste_arr + i * DR_STE_SIZE_REDUCED; ste->htbl = htbl; - refcount_set(&ste->refcount, 0); + ste->refcount = 0; INIT_LIST_HEAD(&ste->miss_list_node); INIT_LIST_HEAD(&htbl->miss_list[i]); INIT_LIST_HEAD(&ste->rule_list); @@ -705,7 +705,7 @@ struct mlx5dr_ste_htbl *mlx5dr_ste_htbl_alloc(struct mlx5dr_icm_pool *pool, int mlx5dr_ste_htbl_free(struct mlx5dr_ste_htbl *htbl) { - if (refcount_read(&htbl->refcount)) + if (htbl->refcount) return -EBUSY; mlx5dr_icm_free_chunk(htbl->chunk); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h index 1cb3769d4e3c..31737dfca4ea 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -117,7 +117,7 @@ struct mlx5dr_matcher_rx_tx; struct mlx5dr_ste { u8 *hw_ste; /* refcount: indicates the num of rules that using this ste */ - refcount_t refcount; + u32 refcount; /* attached to the miss_list head at each htbl entry */ struct list_head miss_list_node; @@ -149,7 +149,7 @@ struct mlx5dr_ste_htbl_ctrl { struct mlx5dr_ste_htbl { u8 lu_type; u16 byte_mask; - refcount_t refcount; + u32 refcount; struct mlx5dr_icm_chunk *chunk; struct mlx5dr_ste *ste_arr; u8 *hw_ste_arr; @@ -200,13 +200,14 @@ int mlx5dr_ste_htbl_free(struct mlx5dr_ste_htbl *htbl); static inline void mlx5dr_htbl_put(struct mlx5dr_ste_htbl *htbl) { - if (refcount_dec_and_test(&htbl->refcount)) + htbl->refcount--; + if (!htbl->refcount) mlx5dr_ste_htbl_free(htbl); } static inline void mlx5dr_htbl_get(struct mlx5dr_ste_htbl *htbl) { - refcount_inc(&htbl->refcount); + htbl->refcount++; } /* STE utils */ @@ -248,14 +249,15 @@ static inline void mlx5dr_ste_put(struct mlx5dr_ste *ste, struct mlx5dr_matcher *matcher, struct mlx5dr_matcher_rx_tx *nic_matcher) { - if (refcount_dec_and_test(&ste->refcount)) + ste->refcount--; + if (!ste->refcount) mlx5dr_ste_free(ste, matcher, nic_matcher); } /* initial as 0, increased only when ste appears in a new rule */ static inline void mlx5dr_ste_get(struct mlx5dr_ste *ste) { - refcount_inc(&ste->refcount); + ste->refcount++; } void mlx5dr_ste_set_hit_addr_by_next_htbl(u8 *hw_ste, diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c index 544344ac4894..79057af4fe99 100644 --- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c +++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include "mlxfw_mfa2.h" #include "mlxfw_mfa2_file.h" @@ -548,7 +549,7 @@ mlxfw_mfa2_file_component_get(const struct mlxfw_mfa2_file *mfa2_file, comp_size = be32_to_cpu(comp->size); comp_buf_size = comp_size + mlxfw_mfa2_comp_magic_len; - comp_data = kmalloc(sizeof(*comp_data) + comp_buf_size, GFP_KERNEL); + comp_data = vzalloc(sizeof(*comp_data) + comp_buf_size); if (!comp_data) return ERR_PTR(-ENOMEM); comp_data->comp.data_size = comp_size; @@ -570,7 +571,7 @@ mlxfw_mfa2_file_component_get(const struct mlxfw_mfa2_file *mfa2_file, comp_data->comp.data = comp_data->buff + mlxfw_mfa2_comp_magic_len; return &comp_data->comp; err_out: - kfree(comp_data); + vfree(comp_data); return ERR_PTR(err); } @@ -579,7 +580,7 @@ void mlxfw_mfa2_file_component_put(struct mlxfw_mfa2_component *comp) const struct mlxfw_mfa2_comp_data *comp_data; comp_data = container_of(comp, struct mlxfw_mfa2_comp_data, comp); - kfree(comp_data); + vfree(comp_data); } void mlxfw_mfa2_file_fini(struct mlxfw_mfa2_file *mfa2_file) diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 5494cf93f34c..8e42ebdbd487 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -5421,6 +5421,7 @@ enum mlxsw_reg_htgt_trap_group { MLXSW_REG_HTGT_TRAP_GROUP_SP_LBERROR, MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP0, MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP1, + MLXSW_REG_HTGT_TRAP_GROUP_SP_VRRP, __MLXSW_REG_HTGT_TRAP_GROUP_MAX, MLXSW_REG_HTGT_TRAP_GROUP_MAX = __MLXSW_REG_HTGT_TRAP_GROUP_MAX - 1 diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index dcf9562bce8a..3ec18fb0d479 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4398,8 +4398,8 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = { MLXSW_SP_RXL_MARK(ROUTER_ALERT_IPV6, TRAP_TO_CPU, ROUTER_EXP, false), MLXSW_SP_RXL_MARK(IPIP_DECAP_ERROR, TRAP_TO_CPU, ROUTER_EXP, false), MLXSW_SP_RXL_MARK(DECAP_ECN0, TRAP_TO_CPU, ROUTER_EXP, false), - MLXSW_SP_RXL_MARK(IPV4_VRRP, TRAP_TO_CPU, ROUTER_EXP, false), - MLXSW_SP_RXL_MARK(IPV6_VRRP, TRAP_TO_CPU, ROUTER_EXP, false), + MLXSW_SP_RXL_MARK(IPV4_VRRP, TRAP_TO_CPU, VRRP, false), + MLXSW_SP_RXL_MARK(IPV6_VRRP, TRAP_TO_CPU, VRRP, false), /* PKT Sample trap */ MLXSW_RXL(mlxsw_sp_rx_listener_sample_func, PKT_SAMPLE, MIRROR_TO_CPU, false, SP_IP2ME, DISCARD), @@ -4483,6 +4483,10 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core) rate = 19 * 1024; burst_size = 12; break; + case MLXSW_REG_HTGT_TRAP_GROUP_SP_VRRP: + rate = 360; + burst_size = 7; + break; default: continue; } @@ -4522,6 +4526,7 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core) case MLXSW_REG_HTGT_TRAP_GROUP_SP_OSPF: case MLXSW_REG_HTGT_TRAP_GROUP_SP_PIM: case MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP0: + case MLXSW_REG_HTGT_TRAP_GROUP_SP_VRRP: priority = 5; tc = 5; break; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c index bdf53cf350f6..720514b5c006 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c @@ -650,6 +650,13 @@ mlxsw_sp_qdisc_prio_graft(struct mlxsw_sp_port *mlxsw_sp_port, mlxsw_sp_port->tclass_qdiscs[tclass_num].handle == p->child_handle) return 0; + if (!p->child_handle) { + /* This is an invisible FIFO replacing the original Qdisc. + * Ignore it--the original Qdisc's destroy will follow. + */ + return 0; + } + /* See if the grafted qdisc is already offloaded on any tclass. If so, * unoffload it. */ diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 39d600c8b92d..efdf8cb5114c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -5637,8 +5637,13 @@ static void mlxsw_sp_router_fib6_del(struct mlxsw_sp *mlxsw_sp, if (mlxsw_sp_fib6_rt_should_ignore(rt)) return; + /* Multipath routes are first added to the FIB trie and only then + * notified. If we vetoed the addition, we will get a delete + * notification for a route we do not have. Therefore, do not warn if + * route was not found. + */ fib6_entry = mlxsw_sp_fib6_entry_lookup(mlxsw_sp, rt); - if (WARN_ON(!fib6_entry)) + if (!fib6_entry) return; /* If not all the nexthops are deleted, then only reduce the nexthop @@ -6980,6 +6985,9 @@ static int mlxsw_sp_router_port_check_rif_addr(struct mlxsw_sp *mlxsw_sp, for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) { rif = mlxsw_sp->router->rifs[i]; + if (rif && rif->ops && + rif->ops->type == MLXSW_SP_RIF_TYPE_IPIP_LB) + continue; if (rif && rif->dev && rif->dev != dev && !ether_addr_equal_masked(rif->dev->dev_addr, dev_addr, mlxsw_sp->mac_mask)) { diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 672ea1342add..da1fd0e08c36 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1979,14 +1979,18 @@ static struct ptp_clock_info ocelot_ptp_clock_info = { static int ocelot_init_timestamp(struct ocelot *ocelot) { + struct ptp_clock *ptp_clock; + ocelot->ptp_info = ocelot_ptp_clock_info; - ocelot->ptp_clock = ptp_clock_register(&ocelot->ptp_info, ocelot->dev); - if (IS_ERR(ocelot->ptp_clock)) - return PTR_ERR(ocelot->ptp_clock); + ptp_clock = ptp_clock_register(&ocelot->ptp_info, ocelot->dev); + if (IS_ERR(ptp_clock)) + return PTR_ERR(ptp_clock); /* Check if PHC support is missing at the configuration level */ - if (!ocelot->ptp_clock) + if (!ptp_clock) return 0; + ocelot->ptp_clock = ptp_clock; + ocelot_write(ocelot, SYS_PTP_CFG_PTP_STAMP_WID(30), SYS_PTP_CFG); ocelot_write(ocelot, 0xffffffff, ANA_TABLES_PTP_ID_LOW); ocelot_write(ocelot, 0xffffffff, ANA_TABLES_PTP_ID_HIGH); @@ -2213,6 +2217,8 @@ void ocelot_deinit(struct ocelot *ocelot) destroy_workqueue(ocelot->stats_queue); mutex_destroy(&ocelot->stats_lock); ocelot_ace_deinit(); + if (ocelot->ptp_clock) + ptp_clock_unregister(ocelot->ptp_clock); for (i = 0; i < ocelot->num_phys_ports; i++) { port = ocelot->ports[i]; diff --git a/drivers/net/ethernet/netronome/nfp/flower/metadata.c b/drivers/net/ethernet/netronome/nfp/flower/metadata.c index 7c4a15e967df..5defd31d481c 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/metadata.c +++ b/drivers/net/ethernet/netronome/nfp/flower/metadata.c @@ -65,17 +65,17 @@ static int nfp_get_stats_entry(struct nfp_app *app, u32 *stats_context_id) freed_stats_id = priv->stats_ring_size; /* Check for unallocated entries first. */ if (priv->stats_ids.init_unalloc > 0) { - if (priv->active_mem_unit == priv->total_mem_units) { - priv->stats_ids.init_unalloc--; - priv->active_mem_unit = 0; - } - *stats_context_id = FIELD_PREP(NFP_FL_STAT_ID_STAT, priv->stats_ids.init_unalloc - 1) | FIELD_PREP(NFP_FL_STAT_ID_MU_NUM, priv->active_mem_unit); - priv->active_mem_unit++; + + if (++priv->active_mem_unit == priv->total_mem_units) { + priv->stats_ids.init_unalloc--; + priv->active_mem_unit = 0; + } + return 0; } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 20faa8d24c9f..134640412d7b 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -1364,12 +1364,9 @@ int ionic_lif_rss_config(struct ionic_lif *lif, const u16 types, static int ionic_lif_rss_init(struct ionic_lif *lif) { - u8 rss_key[IONIC_RSS_HASH_KEY_SIZE]; unsigned int tbl_sz; unsigned int i; - netdev_rss_key_fill(rss_key, IONIC_RSS_HASH_KEY_SIZE); - lif->rss_types = IONIC_RSS_TYPE_IPV4 | IONIC_RSS_TYPE_IPV4_TCP | IONIC_RSS_TYPE_IPV4_UDP | @@ -1382,12 +1379,18 @@ static int ionic_lif_rss_init(struct ionic_lif *lif) for (i = 0; i < tbl_sz; i++) lif->rss_ind_tbl[i] = ethtool_rxfh_indir_default(i, lif->nxqs); - return ionic_lif_rss_config(lif, lif->rss_types, rss_key, NULL); + return ionic_lif_rss_config(lif, lif->rss_types, NULL, NULL); } -static int ionic_lif_rss_deinit(struct ionic_lif *lif) +static void ionic_lif_rss_deinit(struct ionic_lif *lif) { - return ionic_lif_rss_config(lif, 0x0, NULL, NULL); + int tbl_sz; + + tbl_sz = le16_to_cpu(lif->ionic->ident.lif.eth.rss_ind_tbl_sz); + memset(lif->rss_ind_tbl, 0, tbl_sz); + memset(lif->rss_hash_key, 0, IONIC_RSS_HASH_KEY_SIZE); + + ionic_lif_rss_config(lif, 0x0, NULL, NULL); } static void ionic_txrx_disable(struct ionic_lif *lif) @@ -1710,6 +1713,7 @@ static struct ionic_lif *ionic_lif_alloc(struct ionic *ionic, unsigned int index dev_err(dev, "Failed to allocate rss indirection table, aborting\n"); goto err_out_free_qcqs; } + netdev_rss_key_fill(lif->rss_hash_key, IONIC_RSS_HASH_KEY_SIZE); list_add_tail(&lif->list, &ionic->lifs); diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c index 9a6a9a008714..c8bdbf057d5a 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_filter.c +++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c @@ -1230,7 +1230,7 @@ qede_configure_mcast_filtering(struct net_device *ndev, netif_addr_lock_bh(ndev); mc_count = netdev_mc_count(ndev); - if (mc_count < 64) { + if (mc_count <= 64) { netdev_for_each_mc_addr(ha, ndev) { ether_addr_copy(temp, ha->addr); temp += ETH_ALEN; diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index a220cc7c947a..ba53612ae0df 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -1406,6 +1406,7 @@ static int qede_alloc_mem_rxq(struct qede_dev *edev, struct qede_rx_queue *rxq) rxq->rx_buf_seg_size = roundup_pow_of_two(size); } else { rxq->rx_buf_seg_size = PAGE_SIZE; + edev->ndev->features &= ~NETIF_F_GRO_HW; } /* Allocate the parallel driver ring for Rx buffers */ @@ -1450,6 +1451,7 @@ static int qede_alloc_mem_rxq(struct qede_dev *edev, struct qede_rx_queue *rxq) } } + edev->gro_disable = !(edev->ndev->features & NETIF_F_GRO_HW); if (!edev->gro_disable) qede_set_tpa_param(rxq); err: @@ -1702,8 +1704,6 @@ static void qede_init_fp(struct qede_dev *edev) snprintf(fp->name, sizeof(fp->name), "%s-fp-%d", edev->ndev->name, queue_id); } - - edev->gro_disable = !(edev->ndev->features & NETIF_F_GRO_HW); } static int qede_set_real_num_queues(struct qede_dev *edev) diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c index b4b8ba00ee01..986f26578d34 100644 --- a/drivers/net/ethernet/qlogic/qla3xxx.c +++ b/drivers/net/ethernet/qlogic/qla3xxx.c @@ -2756,6 +2756,9 @@ static int ql_alloc_large_buffers(struct ql3_adapter *qdev) int err; for (i = 0; i < qdev->num_large_buffers; i++) { + lrg_buf_cb = &qdev->lrg_buf[i]; + memset(lrg_buf_cb, 0, sizeof(struct ql_rcv_buf_cb)); + skb = netdev_alloc_skb(qdev->ndev, qdev->lrg_buffer_len); if (unlikely(!skb)) { @@ -2766,11 +2769,7 @@ static int ql_alloc_large_buffers(struct ql3_adapter *qdev) ql_free_large_buffers(qdev); return -ENOMEM; } else { - - lrg_buf_cb = &qdev->lrg_buf[i]; - memset(lrg_buf_cb, 0, sizeof(struct ql_rcv_buf_cb)); lrg_buf_cb->index = i; - lrg_buf_cb->skb = skb; /* * We save some space to copy the ethhdr from first * buffer @@ -2792,6 +2791,7 @@ static int ql_alloc_large_buffers(struct ql3_adapter *qdev) return -ENOMEM; } + lrg_buf_cb->skb = skb; dma_unmap_addr_set(lrg_buf_cb, mapaddr, map); dma_unmap_len_set(lrg_buf_cb, maplen, qdev->lrg_buffer_len - diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index c33c438850cc..5ae0b5663d54 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -680,6 +680,7 @@ struct rtl8169_private { struct rtl8169_counters *counters; struct rtl8169_tc_offsets tc_offset; u32 saved_wolopts; + int eee_adv; const char *fw_name; struct rtl_fw *rtl_fw; @@ -1516,6 +1517,7 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts) rtl_lock_config_regs(tp); device_set_wakeup_enable(tp_to_dev(tp), wolopts); + tp->dev->wol_enabled = wolopts ? 1 : 0; } static int rtl8169_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) @@ -2074,6 +2076,10 @@ static int rtl8169_set_eee(struct net_device *dev, struct ethtool_eee *data) } ret = phy_ethtool_set_eee(tp->phydev, data); + + if (!ret) + tp->eee_adv = phy_read_mmd(dev->phydev, MDIO_MMD_AN, + MDIO_AN_EEE_ADV); out: pm_runtime_put_noidle(d); return ret; @@ -2104,10 +2110,16 @@ static const struct ethtool_ops rtl8169_ethtool_ops = { static void rtl_enable_eee(struct rtl8169_private *tp) { struct phy_device *phydev = tp->phydev; - int supported = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_PCS_EEE_ABLE); + int adv; + + /* respect EEE advertisement the user may have set */ + if (tp->eee_adv >= 0) + adv = tp->eee_adv; + else + adv = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_PCS_EEE_ABLE); - if (supported > 0) - phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV, supported); + if (adv >= 0) + phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV, adv); } static void rtl8169_get_mac_version(struct rtl8169_private *tp) @@ -3919,7 +3931,7 @@ static void rtl_wol_suspend_quirk(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_32: case RTL_GIGA_MAC_VER_33: case RTL_GIGA_MAC_VER_34: - case RTL_GIGA_MAC_VER_37 ... RTL_GIGA_MAC_VER_51: + case RTL_GIGA_MAC_VER_37 ... RTL_GIGA_MAC_VER_61: RTL_W32(tp, RxConfig, RTL_R32(tp, RxConfig) | AcceptBroadcast | AcceptMulticast | AcceptMyPhys); break; @@ -4118,7 +4130,7 @@ static void rtl_hw_jumbo_enable(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_27 ... RTL_GIGA_MAC_VER_28: r8168dp_hw_jumbo_enable(tp); break; - case RTL_GIGA_MAC_VER_31 ... RTL_GIGA_MAC_VER_34: + case RTL_GIGA_MAC_VER_31 ... RTL_GIGA_MAC_VER_33: r8168e_hw_jumbo_enable(tp); break; default: @@ -4144,7 +4156,7 @@ static void rtl_hw_jumbo_disable(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_27 ... RTL_GIGA_MAC_VER_28: r8168dp_hw_jumbo_disable(tp); break; - case RTL_GIGA_MAC_VER_31 ... RTL_GIGA_MAC_VER_34: + case RTL_GIGA_MAC_VER_31 ... RTL_GIGA_MAC_VER_33: r8168e_hw_jumbo_disable(tp); break; default: @@ -7063,6 +7075,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) tp->pci_dev = pdev; tp->msg_enable = netif_msg_init(debug.msg_enable, R8169_MSG_DEFAULT); tp->supports_gmii = ent->driver_data == RTL_CFG_NO_GBIT ? 0 : 1; + tp->eee_adv = -1; /* Get the *optional* external "ether_clk" used on some boards */ rc = rtl_get_ether_clk(tp); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c index 306da8f6b7d5..33ce139f090f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c @@ -112,6 +112,14 @@ static int meson8b_init_rgmii_tx_clk(struct meson8b_dwmac *dwmac) struct device *dev = dwmac->dev; const char *parent_name, *mux_parent_names[MUX_CLK_NUM_PARENTS]; struct meson8b_dwmac_clk_configs *clk_configs; + static const struct clk_div_table div_table[] = { + { .div = 2, .val = 2, }, + { .div = 3, .val = 3, }, + { .div = 4, .val = 4, }, + { .div = 5, .val = 5, }, + { .div = 6, .val = 6, }, + { .div = 7, .val = 7, }, + }; clk_configs = devm_kzalloc(dev, sizeof(*clk_configs), GFP_KERNEL); if (!clk_configs) @@ -146,9 +154,9 @@ static int meson8b_init_rgmii_tx_clk(struct meson8b_dwmac *dwmac) clk_configs->m250_div.reg = dwmac->regs + PRG_ETH0; clk_configs->m250_div.shift = PRG_ETH0_CLK_M250_DIV_SHIFT; clk_configs->m250_div.width = PRG_ETH0_CLK_M250_DIV_WIDTH; - clk_configs->m250_div.flags = CLK_DIVIDER_ONE_BASED | - CLK_DIVIDER_ALLOW_ZERO | - CLK_DIVIDER_ROUND_CLOSEST; + clk_configs->m250_div.table = div_table; + clk_configs->m250_div.flags = CLK_DIVIDER_ALLOW_ZERO | + CLK_DIVIDER_ROUND_CLOSEST; clk = meson8b_dwmac_register_clk(dwmac, "m250_div", &parent_name, 1, &clk_divider_ops, &clk_configs->m250_div.hw); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index 6e47be63a43c..e9e0867ec139 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -957,6 +957,9 @@ static int sun8i_dwmac_set_syscon(struct stmmac_priv *priv) /* default */ break; case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: reg |= SYSCON_EPIT | SYSCON_ETCS_INT_GMII; break; case PHY_INTERFACE_MODE_RMII: diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c index a299da3971b4..102d637bc84a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c @@ -44,7 +44,7 @@ static int sun7i_gmac_init(struct platform_device *pdev, void *priv) * rate, which then uses the auto-reparenting feature of the * clock driver, and enabling/disabling the clock. */ - if (gmac->interface == PHY_INTERFACE_MODE_RGMII) { + if (phy_interface_mode_is_rgmii(gmac->interface)) { clk_set_rate(gmac->tx_clk, SUN7I_GMAC_GMII_RGMII_RATE); clk_prepare_enable(gmac->tx_clk); gmac->clk_enabled = 1; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h index 9d08a934fe4f..ff751ab3d765 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h @@ -343,6 +343,8 @@ #define XGMAC_DMA_CH_RX_CONTROL(x) (0x00003108 + (0x80 * (x))) #define XGMAC_RxPBL GENMASK(21, 16) #define XGMAC_RxPBL_SHIFT 16 +#define XGMAC_RBSZ GENMASK(14, 1) +#define XGMAC_RBSZ_SHIFT 1 #define XGMAC_RXST BIT(0) #define XGMAC_DMA_CH_TxDESC_HADDR(x) (0x00003110 + (0x80 * (x))) #define XGMAC_DMA_CH_TxDESC_LADDR(x) (0x00003114 + (0x80 * (x))) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c index f70ca5300b82..4af7271cea56 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c @@ -489,7 +489,8 @@ static void dwxgmac2_set_bfsize(void __iomem *ioaddr, int bfsize, u32 chan) u32 value; value = readl(ioaddr + XGMAC_DMA_CH_RX_CONTROL(chan)); - value |= bfsize << 1; + value &= ~XGMAC_RBSZ; + value |= bfsize << XGMAC_RBSZ_SHIFT; writel(value, ioaddr + XGMAC_DMA_CH_RX_CONTROL(chan)); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index f826365c979d..903c5d8a226e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -45,7 +45,7 @@ #include "dwxgmac2.h" #include "hwif.h" -#define STMMAC_ALIGN(x) __ALIGN_KERNEL(x, SMP_CACHE_BYTES) +#define STMMAC_ALIGN(x) ALIGN(ALIGN(x, SMP_CACHE_BYTES), 16) #define TSO_MAX_BUFF_SIZE (SZ_16K - 1) /* Module parameters */ @@ -1292,19 +1292,9 @@ static int init_dma_rx_desc_rings(struct net_device *dev, gfp_t flags) struct stmmac_priv *priv = netdev_priv(dev); u32 rx_count = priv->plat->rx_queues_to_use; int ret = -ENOMEM; - int bfsize = 0; int queue; int i; - bfsize = stmmac_set_16kib_bfsize(priv, dev->mtu); - if (bfsize < 0) - bfsize = 0; - - if (bfsize < BUF_SIZE_16KiB) - bfsize = stmmac_set_bfsize(dev->mtu, priv->dma_buf_sz); - - priv->dma_buf_sz = bfsize; - /* RX INITIALIZATION */ netif_dbg(priv, probe, priv->dev, "SKB addresses:\nskb\t\tskb data\tdma data\n"); @@ -1346,8 +1336,6 @@ static int init_dma_rx_desc_rings(struct net_device *dev, gfp_t flags) } } - buf_sz = bfsize; - return 0; err_init_rx_buffers: @@ -1502,10 +1490,8 @@ static void free_dma_rx_desc_resources(struct stmmac_priv *priv) rx_q->dma_erx, rx_q->dma_rx_phy); kfree(rx_q->buf_pool); - if (rx_q->page_pool) { - page_pool_request_shutdown(rx_q->page_pool); + if (rx_q->page_pool) page_pool_destroy(rx_q->page_pool); - } } } @@ -2656,6 +2642,7 @@ static void stmmac_hw_teardown(struct net_device *dev) static int stmmac_open(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); + int bfsize = 0; u32 chan; int ret; @@ -2675,7 +2662,16 @@ static int stmmac_open(struct net_device *dev) memset(&priv->xstats, 0, sizeof(struct stmmac_extra_stats)); priv->xstats.threshold = tc; - priv->dma_buf_sz = STMMAC_ALIGN(buf_sz); + bfsize = stmmac_set_16kib_bfsize(priv, dev->mtu); + if (bfsize < 0) + bfsize = 0; + + if (bfsize < BUF_SIZE_16KiB) + bfsize = stmmac_set_bfsize(dev->mtu, priv->dma_buf_sz); + + priv->dma_buf_sz = bfsize; + buf_sz = bfsize; + priv->rx_copybreak = STMMAC_RX_COPYBREAK; ret = alloc_dma_desc_resources(priv); @@ -3105,6 +3101,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) tx_q->tx_tail_addr = tx_q->dma_tx_phy + (tx_q->cur_tx * sizeof(*desc)); stmmac_set_tx_tail_ptr(priv, priv->ioaddr, tx_q->tx_tail_addr, queue); + stmmac_tx_timer_arm(priv, queue); return NETDEV_TX_OK; @@ -3332,6 +3329,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) tx_q->tx_tail_addr = tx_q->dma_tx_phy + (tx_q->cur_tx * sizeof(*desc)); stmmac_set_tx_tail_ptr(priv, priv->ioaddr, tx_q->tx_tail_addr, queue); + stmmac_tx_timer_arm(priv, queue); return NETDEV_TX_OK; @@ -3749,12 +3747,24 @@ static void stmmac_set_rx_mode(struct net_device *dev) static int stmmac_change_mtu(struct net_device *dev, int new_mtu) { struct stmmac_priv *priv = netdev_priv(dev); + int txfifosz = priv->plat->tx_fifo_size; + + if (txfifosz == 0) + txfifosz = priv->dma_cap.tx_fifo_size; + + txfifosz /= priv->plat->tx_queues_to_use; if (netif_running(dev)) { netdev_err(priv->dev, "must be stopped to change its MTU\n"); return -EBUSY; } + new_mtu = STMMAC_ALIGN(new_mtu); + + /* If condition true, FIFO is too small or MTU too large */ + if ((txfifosz < new_mtu) || (new_mtu > BUF_SIZE_16KiB)) + return -EINVAL; + dev->mtu = new_mtu; netdev_update_features(dev); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 170c3a052b14..5150551c28be 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -320,7 +320,7 @@ static int stmmac_mtl_setup(struct platform_device *pdev, static int stmmac_dt_phy(struct plat_stmmacenet_data *plat, struct device_node *np, struct device *dev) { - bool mdio = true; + bool mdio = !of_phy_is_fixed_link(np); static const struct of_device_id need_mdio_ids[] = { { .compatible = "snps,dwc-qos-ethernet-4.10" }, {}, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c index ac3f658105c0..a0513deab1a0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c @@ -624,6 +624,8 @@ static int stmmac_test_mcfilt(struct stmmac_priv *priv) return -EOPNOTSUPP; if (netdev_uc_count(priv->dev) >= priv->hw->unicast_filter_entries) return -EOPNOTSUPP; + if (netdev_mc_count(priv->dev) >= priv->hw->multicast_filter_bins) + return -EOPNOTSUPP; while (--tries) { /* We only need to check the mc_addr for collisions */ @@ -666,6 +668,8 @@ static int stmmac_test_ucfilt(struct stmmac_priv *priv) if (stmmac_filter_check(priv)) return -EOPNOTSUPP; + if (netdev_uc_count(priv->dev) >= priv->hw->unicast_filter_entries) + return -EOPNOTSUPP; if (netdev_mc_count(priv->dev) >= priv->hw->multicast_filter_bins) return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig index 834afca3a019..137632b09c72 100644 --- a/drivers/net/ethernet/ti/Kconfig +++ b/drivers/net/ethernet/ti/Kconfig @@ -22,6 +22,7 @@ config TI_DAVINCI_EMAC depends on ARM && ( ARCH_DAVINCI || ARCH_OMAP3 ) || COMPILE_TEST select TI_DAVINCI_MDIO select PHYLIB + select GENERIC_ALLOCATOR ---help--- This driver supports TI's DaVinci Ethernet . diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index f298d714efd6..d7a953c647b4 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -890,8 +890,8 @@ static irqreturn_t cpsw_rx_interrupt(int irq, void *dev_id) { struct cpsw_common *cpsw = dev_id; - cpdma_ctlr_eoi(cpsw->dma, CPDMA_EOI_RX); writel(0, &cpsw->wr_regs->rx_en); + cpdma_ctlr_eoi(cpsw->dma, CPDMA_EOI_RX); if (cpsw->quirk_irq) { disable_irq_nosync(cpsw->irqs_table[0]); diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c index 84025dcc78d5..e7c24396933e 100644 --- a/drivers/net/ethernet/ti/cpsw_ale.c +++ b/drivers/net/ethernet/ti/cpsw_ale.c @@ -779,6 +779,7 @@ void cpsw_ale_start(struct cpsw_ale *ale) void cpsw_ale_stop(struct cpsw_ale *ale) { del_timer_sync(&ale->timer); + cpsw_ale_control_set(ale, 0, ALE_CLEAR, 1); cpsw_ale_control_set(ale, 0, ALE_ENABLE, 0); } @@ -862,6 +863,7 @@ struct cpsw_ale *cpsw_ale_create(struct cpsw_ale_params *params) ALE_UNKNOWNVLAN_FORCE_UNTAG_EGRESS; } + cpsw_ale_control_set(ale, 0, ALE_CLEAR, 1); return ale; } diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c index 37ba708ac781..6614fa3089b2 100644 --- a/drivers/net/ethernet/ti/davinci_cpdma.c +++ b/drivers/net/ethernet/ti/davinci_cpdma.c @@ -1018,7 +1018,6 @@ static int cpdma_chan_submit_si(struct submit_info *si) struct cpdma_chan *chan = si->chan; struct cpdma_ctlr *ctlr = chan->ctlr; int len = si->len; - int swlen = len; struct cpdma_desc __iomem *desc; dma_addr_t buffer; u32 mode; @@ -1046,7 +1045,6 @@ static int cpdma_chan_submit_si(struct submit_info *si) if (si->data_dma) { buffer = si->data_dma; dma_sync_single_for_device(ctlr->dev, buffer, len, chan->dir); - swlen |= CPDMA_DMA_EXT_MAP; } else { buffer = dma_map_single(ctlr->dev, si->data_virt, len, chan->dir); ret = dma_mapping_error(ctlr->dev, buffer); @@ -1065,7 +1063,8 @@ static int cpdma_chan_submit_si(struct submit_info *si) writel_relaxed(mode | len, &desc->hw_mode); writel_relaxed((uintptr_t)si->token, &desc->sw_token); writel_relaxed(buffer, &desc->sw_buffer); - writel_relaxed(swlen, &desc->sw_len); + writel_relaxed(si->data_dma ? len | CPDMA_DMA_EXT_MAP : len, + &desc->sw_len); desc_read(desc, sw_len); __cpdma_chan_submit(chan, desc); diff --git a/drivers/net/fjes/fjes_main.c b/drivers/net/fjes/fjes_main.c index b517c1af9de0..91a1059517f5 100644 --- a/drivers/net/fjes/fjes_main.c +++ b/drivers/net/fjes/fjes_main.c @@ -166,6 +166,9 @@ static int fjes_acpi_add(struct acpi_device *device) /* create platform_device */ plat_dev = platform_device_register_simple(DRV_NAME, 0, fjes_resource, ARRAY_SIZE(fjes_resource)); + if (IS_ERR(plat_dev)) + return PTR_ERR(plat_dev); + device->driver_data = plat_dev; return 0; diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 3ab24fdccd3b..5c6b7fc04ea6 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -853,7 +853,9 @@ static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb, if (dst) return dst; } - if (ipv6_stub->ipv6_dst_lookup(geneve->net, gs6->sock->sk, &dst, fl6)) { + dst = ipv6_stub->ipv6_dst_lookup_flow(geneve->net, gs6->sock->sk, fl6, + NULL); + if (IS_ERR(dst)) { netdev_dbg(dev, "no route to %pI6\n", &fl6->daddr); return ERR_PTR(-ENETUNREACH); } diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index ecfe26215935..f6222ada6818 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -38,7 +38,6 @@ struct pdp_ctx { struct hlist_node hlist_addr; union { - u64 tid; struct { u64 tid; u16 flow; @@ -541,7 +540,7 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev, mtu = dst_mtu(&rt->dst); } - rt->dst.ops->update_pmtu(&rt->dst, NULL, skb, mtu); + rt->dst.ops->update_pmtu(&rt->dst, NULL, skb, mtu, false); if (!skb_is_gso(skb) && (iph->frag_off & htons(IP_DF)) && mtu < ntohs(iph->tot_len)) { @@ -641,9 +640,16 @@ static void gtp_link_setup(struct net_device *dev) } static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize); -static void gtp_hashtable_free(struct gtp_dev *gtp); static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[]); +static void gtp_destructor(struct net_device *dev) +{ + struct gtp_dev *gtp = netdev_priv(dev); + + kfree(gtp->addr_hash); + kfree(gtp->tid_hash); +} + static int gtp_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) @@ -661,10 +667,13 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev, if (err < 0) return err; - if (!data[IFLA_GTP_PDP_HASHSIZE]) + if (!data[IFLA_GTP_PDP_HASHSIZE]) { hashsize = 1024; - else + } else { hashsize = nla_get_u32(data[IFLA_GTP_PDP_HASHSIZE]); + if (!hashsize) + hashsize = 1024; + } err = gtp_hashtable_new(gtp, hashsize); if (err < 0) @@ -678,13 +687,15 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev, gn = net_generic(dev_net(dev), gtp_net_id); list_add_rcu(>p->list, &gn->gtp_dev_list); + dev->priv_destructor = gtp_destructor; netdev_dbg(dev, "registered new GTP interface\n"); return 0; out_hashtable: - gtp_hashtable_free(gtp); + kfree(gtp->addr_hash); + kfree(gtp->tid_hash); out_encap: gtp_encap_disable(gtp); return err; @@ -693,8 +704,13 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev, static void gtp_dellink(struct net_device *dev, struct list_head *head) { struct gtp_dev *gtp = netdev_priv(dev); + struct pdp_ctx *pctx; + int i; + + for (i = 0; i < gtp->hash_size; i++) + hlist_for_each_entry_rcu(pctx, >p->tid_hash[i], hlist_tid) + pdp_context_delete(pctx); - gtp_hashtable_free(gtp); list_del_rcu(>p->list); unregister_netdevice_queue(dev, head); } @@ -772,20 +788,6 @@ static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize) return -ENOMEM; } -static void gtp_hashtable_free(struct gtp_dev *gtp) -{ - struct pdp_ctx *pctx; - int i; - - for (i = 0; i < gtp->hash_size; i++) - hlist_for_each_entry_rcu(pctx, >p->tid_hash[i], hlist_tid) - pdp_context_delete(pctx); - - synchronize_rcu(); - kfree(gtp->addr_hash); - kfree(gtp->tid_hash); -} - static struct sock *gtp_encap_enable_socket(int fd, int type, struct gtp_dev *gtp) { @@ -811,7 +813,7 @@ static struct sock *gtp_encap_enable_socket(int fd, int type, lock_sock(sock->sk); if (sock->sk->sk_user_data) { sk = ERR_PTR(-EBUSY); - goto out_sock; + goto out_rel_sock; } sk = sock->sk; @@ -824,8 +826,9 @@ static struct sock *gtp_encap_enable_socket(int fd, int type, setup_udp_tunnel_sock(sock_net(sock->sk), sock, &tuncfg); -out_sock: +out_rel_sock: release_sock(sock->sk); +out_sock: sockfd_put(sock); return sk; } @@ -926,24 +929,31 @@ static void ipv4_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info) } } -static int ipv4_pdp_add(struct gtp_dev *gtp, struct sock *sk, - struct genl_info *info) +static int gtp_pdp_add(struct gtp_dev *gtp, struct sock *sk, + struct genl_info *info) { + struct pdp_ctx *pctx, *pctx_tid = NULL; struct net_device *dev = gtp->dev; u32 hash_ms, hash_tid = 0; - struct pdp_ctx *pctx; + unsigned int version; bool found = false; __be32 ms_addr; ms_addr = nla_get_be32(info->attrs[GTPA_MS_ADDRESS]); hash_ms = ipv4_hashfn(ms_addr) % gtp->hash_size; + version = nla_get_u32(info->attrs[GTPA_VERSION]); - hlist_for_each_entry_rcu(pctx, >p->addr_hash[hash_ms], hlist_addr) { - if (pctx->ms_addr_ip4.s_addr == ms_addr) { - found = true; - break; - } - } + pctx = ipv4_pdp_find(gtp, ms_addr); + if (pctx) + found = true; + if (version == GTP_V0) + pctx_tid = gtp0_pdp_find(gtp, + nla_get_u64(info->attrs[GTPA_TID])); + else if (version == GTP_V1) + pctx_tid = gtp1_pdp_find(gtp, + nla_get_u32(info->attrs[GTPA_I_TEI])); + if (pctx_tid) + found = true; if (found) { if (info->nlhdr->nlmsg_flags & NLM_F_EXCL) @@ -951,6 +961,11 @@ static int ipv4_pdp_add(struct gtp_dev *gtp, struct sock *sk, if (info->nlhdr->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; + if (pctx && pctx_tid) + return -EEXIST; + if (!pctx) + pctx = pctx_tid; + ipv4_pdp_fill(pctx, info); if (pctx->gtp_version == GTP_V0) @@ -1074,7 +1089,7 @@ static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info) goto out_unlock; } - err = ipv4_pdp_add(gtp, sk, info); + err = gtp_pdp_add(gtp, sk, info); out_unlock: rcu_read_unlock(); @@ -1232,43 +1247,46 @@ static int gtp_genl_dump_pdp(struct sk_buff *skb, struct netlink_callback *cb) { struct gtp_dev *last_gtp = (struct gtp_dev *)cb->args[2], *gtp; + int i, j, bucket = cb->args[0], skip = cb->args[1]; struct net *net = sock_net(skb->sk); - struct gtp_net *gn = net_generic(net, gtp_net_id); - unsigned long tid = cb->args[1]; - int i, k = cb->args[0], ret; struct pdp_ctx *pctx; + struct gtp_net *gn; + + gn = net_generic(net, gtp_net_id); if (cb->args[4]) return 0; + rcu_read_lock(); list_for_each_entry_rcu(gtp, &gn->gtp_dev_list, list) { if (last_gtp && last_gtp != gtp) continue; else last_gtp = NULL; - for (i = k; i < gtp->hash_size; i++) { - hlist_for_each_entry_rcu(pctx, >p->tid_hash[i], hlist_tid) { - if (tid && tid != pctx->u.tid) - continue; - else - tid = 0; - - ret = gtp_genl_fill_info(skb, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - cb->nlh->nlmsg_type, pctx); - if (ret < 0) { + for (i = bucket; i < gtp->hash_size; i++) { + j = 0; + hlist_for_each_entry_rcu(pctx, >p->tid_hash[i], + hlist_tid) { + if (j >= skip && + gtp_genl_fill_info(skb, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + cb->nlh->nlmsg_type, pctx)) { cb->args[0] = i; - cb->args[1] = pctx->u.tid; + cb->args[1] = j; cb->args[2] = (unsigned long)gtp; goto out; } + j++; } + skip = 0; } + bucket = 0; } cb->args[4] = 1; out: + rcu_read_unlock(); return skb->len; } diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c index 23281aeeb222..71d6629e65c9 100644 --- a/drivers/net/hamradio/6pack.c +++ b/drivers/net/hamradio/6pack.c @@ -654,10 +654,10 @@ static void sixpack_close(struct tty_struct *tty) { struct sixpack *sp; - write_lock_bh(&disc_data_lock); + write_lock_irq(&disc_data_lock); sp = tty->disc_data; tty->disc_data = NULL; - write_unlock_bh(&disc_data_lock); + write_unlock_irq(&disc_data_lock); if (!sp) return; diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c index c5bfa19ddb93..deef14215110 100644 --- a/drivers/net/hamradio/mkiss.c +++ b/drivers/net/hamradio/mkiss.c @@ -773,10 +773,10 @@ static void mkiss_close(struct tty_struct *tty) { struct mkiss *ax; - write_lock_bh(&disc_data_lock); + write_lock_irq(&disc_data_lock); ax = tty->disc_data; tty->disc_data = NULL; - write_unlock_bh(&disc_data_lock); + write_unlock_irq(&disc_data_lock); if (!ax) return; diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index fb547f37af1e..e74f2d1def80 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -169,7 +169,6 @@ struct rndis_device { u8 hw_mac_adr[ETH_ALEN]; u8 rss_key[NETVSC_HASH_KEYLEN]; - u16 rx_table[ITAB_NUM]; }; @@ -938,6 +937,8 @@ struct net_device_context { u32 tx_table[VRSS_SEND_TAB_SIZE]; + u16 rx_table[ITAB_NUM]; + /* Ethtool settings */ u8 duplex; u32 speed; diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 963509add611..78e3e689a733 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -1659,7 +1659,7 @@ static int netvsc_get_rxfh(struct net_device *dev, u32 *indir, u8 *key, rndis_dev = ndev->extension; if (indir) { for (i = 0; i < ITAB_NUM; i++) - indir[i] = rndis_dev->rx_table[i]; + indir[i] = ndc->rx_table[i]; } if (key) @@ -1689,7 +1689,7 @@ static int netvsc_set_rxfh(struct net_device *dev, const u32 *indir, return -EINVAL; for (i = 0; i < ITAB_NUM; i++) - rndis_dev->rx_table[i] = indir[i]; + ndc->rx_table[i] = indir[i]; } if (!key) { diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index abaf8156d19d..f81e58267a6e 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -767,6 +767,7 @@ static int rndis_set_rss_param_msg(struct rndis_device *rdev, const u8 *rss_key, u16 flag) { struct net_device *ndev = rdev->ndev; + struct net_device_context *ndc = netdev_priv(ndev); struct rndis_request *request; struct rndis_set_request *set; struct rndis_set_complete *set_complete; @@ -806,7 +807,7 @@ static int rndis_set_rss_param_msg(struct rndis_device *rdev, /* Set indirection table entries */ itab = (u32 *)(rssp + 1); for (i = 0; i < ITAB_NUM; i++) - itab[i] = rdev->rx_table[i]; + itab[i] = ndc->rx_table[i]; /* Set hask key values */ keyp = (u8 *)((unsigned long)rssp + rssp->hashkey_offset); @@ -1165,6 +1166,9 @@ int rndis_set_subchannel(struct net_device *ndev, wait_event(nvdev->subchan_open, atomic_read(&nvdev->open_chn) == nvdev->num_chn); + for (i = 0; i < VRSS_SEND_TAB_SIZE; i++) + ndev_ctx->tx_table[i] = i % nvdev->num_chn; + /* ignore failures from setting rss parameters, still have channels */ if (dev_info) rndis_filter_set_rss_param(rdev, dev_info->rss_key); @@ -1174,9 +1178,6 @@ int rndis_set_subchannel(struct net_device *ndev, netif_set_real_num_tx_queues(ndev, nvdev->num_chn); netif_set_real_num_rx_queues(ndev, nvdev->num_chn); - for (i = 0; i < VRSS_SEND_TAB_SIZE; i++) - ndev_ctx->tx_table[i] = i % nvdev->num_chn; - return 0; } @@ -1305,6 +1306,7 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev, struct netvsc_device_info *device_info) { struct net_device *net = hv_get_drvdata(dev); + struct net_device_context *ndc = netdev_priv(net); struct netvsc_device *net_device; struct rndis_device *rndis_device; struct ndis_recv_scale_cap rsscap; @@ -1391,9 +1393,11 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev, /* We will use the given number of channels if available. */ net_device->num_chn = min(net_device->max_chn, device_info->num_chn); - for (i = 0; i < ITAB_NUM; i++) - rndis_device->rx_table[i] = ethtool_rxfh_indir_default( + if (!netif_is_rxfh_configured(net)) { + for (i = 0; i < ITAB_NUM; i++) + ndc->rx_table[i] = ethtool_rxfh_indir_default( i, net_device->num_chn); + } atomic_set(&net_device->open_chn, 1); vmbus_set_sc_create_callback(dev->channel, netvsc_sc_open); diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 34fc59bd1e20..747c0542a53c 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -259,7 +259,7 @@ static void macvlan_broadcast(struct sk_buff *skb, struct net_device *src, enum macvlan_mode mode) { - const struct ethhdr *eth = eth_hdr(skb); + const struct ethhdr *eth = skb_eth_hdr(skb); const struct macvlan_dev *vlan; struct sk_buff *nskb; unsigned int i; @@ -359,10 +359,11 @@ static void macvlan_broadcast_enqueue(struct macvlan_port *port, } spin_unlock(&port->bc_queue.lock); + schedule_work(&port->bc_work); + if (err) goto free_nskb; - schedule_work(&port->bc_work); return; free_nskb: diff --git a/drivers/net/phy/aquantia_main.c b/drivers/net/phy/aquantia_main.c index 3b29d381116f..975789d9349d 100644 --- a/drivers/net/phy/aquantia_main.c +++ b/drivers/net/phy/aquantia_main.c @@ -627,6 +627,8 @@ static struct phy_driver aqr_driver[] = { .config_intr = aqr_config_intr, .ack_interrupt = aqr_ack_interrupt, .read_status = aqr_read_status, + .suspend = aqr107_suspend, + .resume = aqr107_resume, }, { PHY_ID_MATCH_MODEL(PHY_ID_AQR106), diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index 37fceaf9fa10..cf4455bbf888 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -95,6 +95,10 @@ #define DP83867_IO_MUX_CFG_CLK_O_SEL_MASK (0x1f << 8) #define DP83867_IO_MUX_CFG_CLK_O_SEL_SHIFT 8 +/* CFG3 bits */ +#define DP83867_CFG3_INT_OE BIT(7) +#define DP83867_CFG3_ROBUST_AUTO_MDIX BIT(9) + /* CFG4 bits */ #define DP83867_CFG4_PORT_MIRROR_EN BIT(0) @@ -410,12 +414,13 @@ static int dp83867_config_init(struct phy_device *phydev) phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_SGMIICTL, val); } + val = phy_read(phydev, DP83867_CFG3); /* Enable Interrupt output INT_OE in CFG3 register */ - if (phy_interrupt_is_valid(phydev)) { - val = phy_read(phydev, DP83867_CFG3); - val |= BIT(7); - phy_write(phydev, DP83867_CFG3, val); - } + if (phy_interrupt_is_valid(phydev)) + val |= DP83867_CFG3_INT_OE; + + val |= DP83867_CFG3_ROBUST_AUTO_MDIX; + phy_write(phydev, DP83867_CFG3, val); if (dp83867->port_mirroring != DP83867_PORT_MIRROING_KEEP) dp83867_config_port_mirroring(phydev); diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index dbacb0031877..229e480179ff 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -62,8 +62,8 @@ static int mdiobus_register_reset(struct mdio_device *mdiodev) struct reset_control *reset = NULL; if (mdiodev->dev.of_node) - reset = devm_reset_control_get_exclusive(&mdiodev->dev, - "phy"); + reset = of_reset_control_get_exclusive(mdiodev->dev.of_node, + "phy"); if (IS_ERR(reset)) { if (PTR_ERR(reset) == -ENOENT || PTR_ERR(reset) == -ENOTSUPP) reset = NULL; @@ -107,6 +107,8 @@ int mdiobus_unregister_device(struct mdio_device *mdiodev) if (mdiodev->bus->mdio_map[mdiodev->addr] != mdiodev) return -EINVAL; + reset_control_put(mdiodev->reset_ctrl); + mdiodev->bus->mdio_map[mdiodev->addr] = NULL; return 0; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index adb66a2fae18..2bf0fda209a8 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -488,7 +488,7 @@ static int phy_bus_match(struct device *dev, struct device_driver *drv) if (phydev->is_c45) { for (i = 1; i < num_ids; i++) { - if (!(phydev->c45_ids.devices_in_package & (1 << i))) + if (phydev->c45_ids.device_ids[i] == 0xffffffff) continue; if ((phydrv->phy_id & phydrv->phy_id_mask) == @@ -552,7 +552,7 @@ static const struct device_type mdio_bus_phy_type = { .pm = MDIO_BUS_PHY_PM_OPS, }; -static int phy_request_driver_module(struct phy_device *dev, int phy_id) +static int phy_request_driver_module(struct phy_device *dev, u32 phy_id) { int ret; @@ -564,15 +564,15 @@ static int phy_request_driver_module(struct phy_device *dev, int phy_id) * then modprobe isn't available. */ if (IS_ENABLED(CONFIG_MODULES) && ret < 0 && ret != -ENOENT) { - phydev_err(dev, "error %d loading PHY driver module for ID 0x%08x\n", - ret, phy_id); + phydev_err(dev, "error %d loading PHY driver module for ID 0x%08lx\n", + ret, (unsigned long)phy_id); return ret; } return 0; } -struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id, +struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id, bool is_c45, struct phy_c45_device_ids *c45_ids) { @@ -596,8 +596,8 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id, mdiodev->device_free = phy_mdio_device_free; mdiodev->device_remove = phy_mdio_device_remove; - dev->speed = 0; - dev->duplex = -1; + dev->speed = SPEED_UNKNOWN; + dev->duplex = DUPLEX_UNKNOWN; dev->pause = 0; dev->asym_pause = 0; dev->link = 0; @@ -632,7 +632,7 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id, int i; for (i = 1; i < num_ids; i++) { - if (!(c45_ids->devices_in_package & (1 << i))) + if (c45_ids->device_ids[i] == 0xffffffff) continue; ret = phy_request_driver_module(dev, @@ -812,10 +812,13 @@ static int get_phy_id(struct mii_bus *bus, int addr, u32 *phy_id, */ struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45) { - struct phy_c45_device_ids c45_ids = {0}; + struct phy_c45_device_ids c45_ids; u32 phy_id = 0; int r; + c45_ids.devices_in_package = 0; + memset(c45_ids.device_ids, 0xff, sizeof(c45_ids.device_ids)); + r = get_phy_id(bus, addr, &phy_id, is_c45, &c45_ids); if (r) return ERR_PTR(r); diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 536236fdb232..bf5bbb565cf5 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -444,8 +444,7 @@ static void phylink_mac_link_up(struct phylink *pl, pl->cur_interface = link_state.interface; pl->ops->mac_link_up(pl->config, pl->link_an_mode, - pl->phy_state.interface, - pl->phydev); + pl->cur_interface, pl->phydev); if (ndev) netif_carrier_on(ndev); diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c index 4d479e3c817d..2a91c192659f 100644 --- a/drivers/net/slip/slip.c +++ b/drivers/net/slip/slip.c @@ -855,6 +855,7 @@ static int slip_open(struct tty_struct *tty) sl->tty = NULL; tty->disc_data = NULL; clear_bit(SLF_INUSE, &sl->flags); + sl_free_netdev(sl->dev); free_netdev(sl->dev); err_exit: diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 8156b33ee3e7..ca70a1d840eb 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -2074,7 +2074,8 @@ static int team_ethtool_get_link_ksettings(struct net_device *dev, cmd->base.duplex = DUPLEX_UNKNOWN; cmd->base.port = PORT_OTHER; - list_for_each_entry(port, &team->port_list, list) { + rcu_read_lock(); + list_for_each_entry_rcu(port, &team->port_list, list) { if (team_port_txable(port)) { if (port->state.speed != SPEED_UNKNOWN) speed += port->state.speed; @@ -2083,6 +2084,8 @@ static int team_ethtool_get_link_ksettings(struct net_device *dev, cmd->base.duplex = port->state.duplex; } } + rcu_read_unlock(); + cmd->base.speed = speed ? : SPEED_UNKNOWN; return 0; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index a8d3141582a5..16564ebcde50 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -313,8 +313,8 @@ static void tun_napi_init(struct tun_struct *tun, struct tun_file *tfile, tfile->napi_enabled = napi_en; tfile->napi_frags_enabled = napi_en && napi_frags; if (napi_en) { - netif_napi_add(tun->dev, &tfile->napi, tun_napi_poll, - NAPI_POLL_WEIGHT); + netif_tx_napi_add(tun->dev, &tfile->napi, tun_napi_poll, + NAPI_POLL_WEIGHT); napi_enable(&tfile->napi); } } diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index f24a1b0b801f..3e5f2f7a155e 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -511,7 +511,7 @@ static int lan78xx_read_stats(struct lan78xx_net *dev, } } else { netdev_warn(dev->net, - "Failed to read stat ret = 0x%x", ret); + "Failed to read stat ret = %d", ret); } kfree(stats); @@ -1808,6 +1808,7 @@ static int lan78xx_mdio_init(struct lan78xx_net *dev) dev->mdiobus->read = lan78xx_mdiobus_read; dev->mdiobus->write = lan78xx_mdiobus_write; dev->mdiobus->name = "lan78xx-mdiobus"; + dev->mdiobus->parent = &dev->udev->dev; snprintf(dev->mdiobus->id, MII_BUS_ID_SIZE, "usb-%03d:%03d", dev->udev->bus->busnum, dev->udev->devnum); @@ -2723,11 +2724,6 @@ static int lan78xx_stop(struct net_device *net) return 0; } -static int lan78xx_linearize(struct sk_buff *skb) -{ - return skb_linearize(skb); -} - static struct sk_buff *lan78xx_tx_prep(struct lan78xx_net *dev, struct sk_buff *skb, gfp_t flags) { @@ -2739,8 +2735,10 @@ static struct sk_buff *lan78xx_tx_prep(struct lan78xx_net *dev, return NULL; } - if (lan78xx_linearize(skb) < 0) + if (skb_linearize(skb)) { + dev_kfree_skb_any(skb); return NULL; + } tx_cmd_a = (u32)(skb->len & TX_CMD_A_LEN_MASK_) | TX_CMD_A_FCS_; diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 8869154fad88..283dfeb406ad 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2276,7 +2276,6 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan, bool use_cache = ip_tunnel_dst_cache_usable(skb, info); struct dst_entry *ndst; struct flowi6 fl6; - int err; if (!sock6) return ERR_PTR(-EIO); @@ -2299,10 +2298,9 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan, fl6.fl6_dport = dport; fl6.fl6_sport = sport; - err = ipv6_stub->ipv6_dst_lookup(vxlan->net, - sock6->sock->sk, - &ndst, &fl6); - if (unlikely(err < 0)) { + ndst = ipv6_stub->ipv6_dst_lookup_flow(vxlan->net, sock6->sock->sk, + &fl6, NULL); + if (unlikely(IS_ERR(ndst))) { netdev_dbg(dev, "no route to %pI6\n", daddr); return ERR_PTR(-ENETUNREACH); } @@ -2544,7 +2542,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, ndst = &rt->dst; skb_tunnel_check_pmtu(skb, ndst, VXLAN_HEADROOM); - tos = ip_tunnel_ecn_encap(tos, old_iph, skb); + tos = ip_tunnel_ecn_encap(RT_TOS(tos), old_iph, skb); ttl = ttl ? : ip4_dst_hoplimit(&rt->dst); err = vxlan_build_skb(skb, ndst, sizeof(struct iphdr), vni, md, flags, udp_sum); @@ -2584,7 +2582,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, skb_tunnel_check_pmtu(skb, ndst, VXLAN6_HEADROOM); - tos = ip_tunnel_ecn_encap(tos, old_iph, skb); + tos = ip_tunnel_ecn_encap(RT_TOS(tos), old_iph, skb); ttl = ttl ? : ip6_dst_hoplimit(ndst); skb_scrub_packet(skb, xnet); err = vxlan_build_skb(skb, ndst, sizeof(struct ipv6hdr), diff --git a/drivers/net/wireless/ath/ar5523/ar5523.c b/drivers/net/wireless/ath/ar5523/ar5523.c index b94759daeacc..da2d179430ca 100644 --- a/drivers/net/wireless/ath/ar5523/ar5523.c +++ b/drivers/net/wireless/ath/ar5523/ar5523.c @@ -255,7 +255,8 @@ static int ar5523_cmd(struct ar5523 *ar, u32 code, const void *idata, if (flags & AR5523_CMD_FLAG_MAGIC) hdr->magic = cpu_to_be32(1 << 24); - memcpy(hdr + 1, idata, ilen); + if (ilen) + memcpy(hdr + 1, idata, ilen); cmd->odata = odata; cmd->olen = olen; diff --git a/drivers/net/wireless/ath/ath10k/coredump.c b/drivers/net/wireless/ath/ath10k/coredump.c index b6d2932383cf..1cfe75a2d0c3 100644 --- a/drivers/net/wireless/ath/ath10k/coredump.c +++ b/drivers/net/wireless/ath/ath10k/coredump.c @@ -1208,9 +1208,11 @@ static struct ath10k_dump_file_data *ath10k_coredump_build(struct ath10k *ar) dump_tlv = (struct ath10k_tlv_dump_data *)(buf + sofar); dump_tlv->type = cpu_to_le32(ATH10K_FW_CRASH_DUMP_RAM_DATA); dump_tlv->tlv_len = cpu_to_le32(crash_data->ramdump_buf_len); - memcpy(dump_tlv->tlv_data, crash_data->ramdump_buf, - crash_data->ramdump_buf_len); - sofar += sizeof(*dump_tlv) + crash_data->ramdump_buf_len; + if (crash_data->ramdump_buf_len) { + memcpy(dump_tlv->tlv_data, crash_data->ramdump_buf, + crash_data->ramdump_buf_len); + sofar += sizeof(*dump_tlv) + crash_data->ramdump_buf_len; + } } mutex_unlock(&ar->dump_mutex); @@ -1257,6 +1259,9 @@ int ath10k_coredump_register(struct ath10k *ar) if (test_bit(ATH10K_FW_CRASH_DUMP_RAM_DATA, &ath10k_coredump_mask)) { crash_data->ramdump_buf_len = ath10k_coredump_get_ramdump_size(ar); + if (!crash_data->ramdump_buf_len) + return 0; + crash_data->ramdump_buf = vzalloc(crash_data->ramdump_buf_len); if (!crash_data->ramdump_buf) return -ENOMEM; diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c index 53f1095de8ff..9f0e7b4943ec 100644 --- a/drivers/net/wireless/ath/ath10k/htt_rx.c +++ b/drivers/net/wireless/ath/ath10k/htt_rx.c @@ -2726,7 +2726,7 @@ static void ath10k_htt_rx_tx_compl_ind(struct ath10k *ar, spin_lock_bh(&ar->data_lock); peer = ath10k_peer_find_by_id(ar, peer_id); - if (!peer) { + if (!peer || !peer->sta) { spin_unlock_bh(&ar->data_lock); rcu_read_unlock(); continue; diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c index a6d21856b7e7..36d24ea126a2 100644 --- a/drivers/net/wireless/ath/ath10k/mac.c +++ b/drivers/net/wireless/ath/ath10k/mac.c @@ -3708,7 +3708,7 @@ static int ath10k_mac_tx(struct ath10k *ar, struct ieee80211_vif *vif, enum ath10k_hw_txrx_mode txmode, enum ath10k_mac_tx_path txpath, - struct sk_buff *skb) + struct sk_buff *skb, bool noque_offchan) { struct ieee80211_hw *hw = ar->hw; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); @@ -3738,10 +3738,10 @@ static int ath10k_mac_tx(struct ath10k *ar, } } - if (info->flags & IEEE80211_TX_CTL_TX_OFFCHAN) { + if (!noque_offchan && info->flags & IEEE80211_TX_CTL_TX_OFFCHAN) { if (!ath10k_mac_tx_frm_has_freq(ar)) { - ath10k_dbg(ar, ATH10K_DBG_MAC, "queued offchannel skb %pK\n", - skb); + ath10k_dbg(ar, ATH10K_DBG_MAC, "mac queued offchannel skb %pK len %d\n", + skb, skb->len); skb_queue_tail(&ar->offchan_tx_queue, skb); ieee80211_queue_work(hw, &ar->offchan_tx_work); @@ -3803,8 +3803,8 @@ void ath10k_offchan_tx_work(struct work_struct *work) mutex_lock(&ar->conf_mutex); - ath10k_dbg(ar, ATH10K_DBG_MAC, "mac offchannel skb %pK\n", - skb); + ath10k_dbg(ar, ATH10K_DBG_MAC, "mac offchannel skb %pK len %d\n", + skb, skb->len); hdr = (struct ieee80211_hdr *)skb->data; peer_addr = ieee80211_get_DA(hdr); @@ -3850,7 +3850,7 @@ void ath10k_offchan_tx_work(struct work_struct *work) txmode = ath10k_mac_tx_h_get_txmode(ar, vif, sta, skb); txpath = ath10k_mac_tx_h_get_txpath(ar, skb, txmode); - ret = ath10k_mac_tx(ar, vif, txmode, txpath, skb); + ret = ath10k_mac_tx(ar, vif, txmode, txpath, skb, true); if (ret) { ath10k_warn(ar, "failed to transmit offchannel frame: %d\n", ret); @@ -3860,8 +3860,8 @@ void ath10k_offchan_tx_work(struct work_struct *work) time_left = wait_for_completion_timeout(&ar->offchan_tx_completed, 3 * HZ); if (time_left == 0) - ath10k_warn(ar, "timed out waiting for offchannel skb %pK\n", - skb); + ath10k_warn(ar, "timed out waiting for offchannel skb %pK, len: %d\n", + skb, skb->len); if (!peer && tmp_peer_created) { ret = ath10k_peer_delete(ar, vdev_id, peer_addr); @@ -3903,8 +3903,10 @@ void ath10k_mgmt_over_wmi_tx_work(struct work_struct *work) ar->running_fw->fw_file.fw_features)) { paddr = dma_map_single(ar->dev, skb->data, skb->len, DMA_TO_DEVICE); - if (!paddr) + if (dma_mapping_error(ar->dev, paddr)) { + ieee80211_free_txskb(ar->hw, skb); continue; + } ret = ath10k_wmi_mgmt_tx_send(ar, skb, paddr); if (ret) { ath10k_warn(ar, "failed to transmit management frame by ref via WMI: %d\n", @@ -4097,7 +4099,7 @@ int ath10k_mac_tx_push_txq(struct ieee80211_hw *hw, spin_unlock_bh(&ar->htt.tx_lock); } - ret = ath10k_mac_tx(ar, vif, txmode, txpath, skb); + ret = ath10k_mac_tx(ar, vif, txmode, txpath, skb, false); if (unlikely(ret)) { ath10k_warn(ar, "failed to push frame: %d\n", ret); @@ -4378,7 +4380,7 @@ static void ath10k_mac_op_tx(struct ieee80211_hw *hw, spin_unlock_bh(&ar->htt.tx_lock); } - ret = ath10k_mac_tx(ar, vif, txmode, txpath, skb); + ret = ath10k_mac_tx(ar, vif, txmode, txpath, skb, false); if (ret) { ath10k_warn(ar, "failed to transmit frame: %d\n", ret); if (is_htt) { diff --git a/drivers/net/wireless/ath/ath10k/pci.c b/drivers/net/wireless/ath/ath10k/pci.c index a0b4d265c6eb..347bb92e4130 100644 --- a/drivers/net/wireless/ath/ath10k/pci.c +++ b/drivers/net/wireless/ath/ath10k/pci.c @@ -3490,7 +3490,7 @@ static int ath10k_pci_probe(struct pci_dev *pdev, struct ath10k_pci *ar_pci; enum ath10k_hw_rev hw_rev; struct ath10k_bus_params bus_params = {}; - bool pci_ps; + bool pci_ps, is_qca988x = false; int (*pci_soft_reset)(struct ath10k *ar); int (*pci_hard_reset)(struct ath10k *ar); u32 (*targ_cpu_to_ce_addr)(struct ath10k *ar, u32 addr); @@ -3500,6 +3500,7 @@ static int ath10k_pci_probe(struct pci_dev *pdev, case QCA988X_2_0_DEVICE_ID: hw_rev = ATH10K_HW_QCA988X; pci_ps = false; + is_qca988x = true; pci_soft_reset = ath10k_pci_warm_reset; pci_hard_reset = ath10k_pci_qca988x_chip_reset; targ_cpu_to_ce_addr = ath10k_pci_qca988x_targ_cpu_to_ce_addr; @@ -3619,25 +3620,34 @@ static int ath10k_pci_probe(struct pci_dev *pdev, goto err_deinit_irq; } + bus_params.dev_type = ATH10K_DEV_TYPE_LL; + bus_params.link_can_suspend = true; + /* Read CHIP_ID before reset to catch QCA9880-AR1A v1 devices that + * fall off the bus during chip_reset. These chips have the same pci + * device id as the QCA9880 BR4A or 2R4E. So that's why the check. + */ + if (is_qca988x) { + bus_params.chip_id = + ath10k_pci_soc_read32(ar, SOC_CHIP_ID_ADDRESS); + if (bus_params.chip_id != 0xffffffff) { + if (!ath10k_pci_chip_is_supported(pdev->device, + bus_params.chip_id)) + goto err_unsupported; + } + } + ret = ath10k_pci_chip_reset(ar); if (ret) { ath10k_err(ar, "failed to reset chip: %d\n", ret); goto err_free_irq; } - bus_params.dev_type = ATH10K_DEV_TYPE_LL; - bus_params.link_can_suspend = true; bus_params.chip_id = ath10k_pci_soc_read32(ar, SOC_CHIP_ID_ADDRESS); - if (bus_params.chip_id == 0xffffffff) { - ath10k_err(ar, "failed to get chip id\n"); - goto err_free_irq; - } + if (bus_params.chip_id == 0xffffffff) + goto err_unsupported; - if (!ath10k_pci_chip_is_supported(pdev->device, bus_params.chip_id)) { - ath10k_err(ar, "device %04x with chip_id %08x isn't supported\n", - pdev->device, bus_params.chip_id); + if (!ath10k_pci_chip_is_supported(pdev->device, bus_params.chip_id)) goto err_free_irq; - } ret = ath10k_core_register(ar, &bus_params); if (ret) { @@ -3647,6 +3657,10 @@ static int ath10k_pci_probe(struct pci_dev *pdev, return 0; +err_unsupported: + ath10k_err(ar, "device %04x with chip_id %08x isn't supported\n", + pdev->device, bus_params.chip_id); + err_free_irq: ath10k_pci_free_irq(ar); ath10k_pci_rx_retry_sync(ar); diff --git a/drivers/net/wireless/ath/ath10k/qmi.c b/drivers/net/wireless/ath/ath10k/qmi.c index 3b63b6257c43..545ac1f06997 100644 --- a/drivers/net/wireless/ath/ath10k/qmi.c +++ b/drivers/net/wireless/ath/ath10k/qmi.c @@ -581,22 +581,29 @@ static int ath10k_qmi_host_cap_send_sync(struct ath10k_qmi *qmi) { struct wlfw_host_cap_resp_msg_v01 resp = {}; struct wlfw_host_cap_req_msg_v01 req = {}; + struct qmi_elem_info *req_ei; struct ath10k *ar = qmi->ar; + struct ath10k_snoc *ar_snoc = ath10k_snoc_priv(ar); struct qmi_txn txn; int ret; req.daemon_support_valid = 1; req.daemon_support = 0; - ret = qmi_txn_init(&qmi->qmi_hdl, &txn, - wlfw_host_cap_resp_msg_v01_ei, &resp); + ret = qmi_txn_init(&qmi->qmi_hdl, &txn, wlfw_host_cap_resp_msg_v01_ei, + &resp); if (ret < 0) goto out; + if (test_bit(ATH10K_SNOC_FLAG_8BIT_HOST_CAP_QUIRK, &ar_snoc->flags)) + req_ei = wlfw_host_cap_8bit_req_msg_v01_ei; + else + req_ei = wlfw_host_cap_req_msg_v01_ei; + ret = qmi_send_request(&qmi->qmi_hdl, NULL, &txn, QMI_WLFW_HOST_CAP_REQ_V01, WLFW_HOST_CAP_REQ_MSG_V01_MAX_MSG_LEN, - wlfw_host_cap_req_msg_v01_ei, &req); + req_ei, &req); if (ret < 0) { qmi_txn_cancel(&txn); ath10k_err(ar, "failed to send host capability request: %d\n", ret); diff --git a/drivers/net/wireless/ath/ath10k/qmi_wlfw_v01.c b/drivers/net/wireless/ath/ath10k/qmi_wlfw_v01.c index 1fe05c6218c3..86fcf4e1de5f 100644 --- a/drivers/net/wireless/ath/ath10k/qmi_wlfw_v01.c +++ b/drivers/net/wireless/ath/ath10k/qmi_wlfw_v01.c @@ -1988,6 +1988,28 @@ struct qmi_elem_info wlfw_host_cap_req_msg_v01_ei[] = { {} }; +struct qmi_elem_info wlfw_host_cap_8bit_req_msg_v01_ei[] = { + { + .data_type = QMI_OPT_FLAG, + .elem_len = 1, + .elem_size = sizeof(u8), + .array_type = NO_ARRAY, + .tlv_type = 0x10, + .offset = offsetof(struct wlfw_host_cap_req_msg_v01, + daemon_support_valid), + }, + { + .data_type = QMI_UNSIGNED_1_BYTE, + .elem_len = 1, + .elem_size = sizeof(u8), + .array_type = NO_ARRAY, + .tlv_type = 0x10, + .offset = offsetof(struct wlfw_host_cap_req_msg_v01, + daemon_support), + }, + {} +}; + struct qmi_elem_info wlfw_host_cap_resp_msg_v01_ei[] = { { .data_type = QMI_STRUCT, diff --git a/drivers/net/wireless/ath/ath10k/qmi_wlfw_v01.h b/drivers/net/wireless/ath/ath10k/qmi_wlfw_v01.h index bca1186e1560..4d107e1364a8 100644 --- a/drivers/net/wireless/ath/ath10k/qmi_wlfw_v01.h +++ b/drivers/net/wireless/ath/ath10k/qmi_wlfw_v01.h @@ -575,6 +575,7 @@ struct wlfw_host_cap_req_msg_v01 { #define WLFW_HOST_CAP_REQ_MSG_V01_MAX_MSG_LEN 189 extern struct qmi_elem_info wlfw_host_cap_req_msg_v01_ei[]; +extern struct qmi_elem_info wlfw_host_cap_8bit_req_msg_v01_ei[]; struct wlfw_host_cap_resp_msg_v01 { struct qmi_response_type_v01 resp; diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c index b491361e6ed4..fc15a0037f0e 100644 --- a/drivers/net/wireless/ath/ath10k/snoc.c +++ b/drivers/net/wireless/ath/ath10k/snoc.c @@ -1261,6 +1261,15 @@ static int ath10k_snoc_resource_init(struct ath10k *ar) return ret; } +static void ath10k_snoc_quirks_init(struct ath10k *ar) +{ + struct ath10k_snoc *ar_snoc = ath10k_snoc_priv(ar); + struct device *dev = &ar_snoc->dev->dev; + + if (of_property_read_bool(dev->of_node, "qcom,snoc-host-cap-8bit-quirk")) + set_bit(ATH10K_SNOC_FLAG_8BIT_HOST_CAP_QUIRK, &ar_snoc->flags); +} + int ath10k_snoc_fw_indication(struct ath10k *ar, u64 type) { struct ath10k_snoc *ar_snoc = ath10k_snoc_priv(ar); @@ -1678,6 +1687,8 @@ static int ath10k_snoc_probe(struct platform_device *pdev) ar->ce_priv = &ar_snoc->ce; msa_size = drv_data->msa_size; + ath10k_snoc_quirks_init(ar); + ret = ath10k_snoc_resource_init(ar); if (ret) { ath10k_warn(ar, "failed to initialize resource: %d\n", ret); diff --git a/drivers/net/wireless/ath/ath10k/snoc.h b/drivers/net/wireless/ath/ath10k/snoc.h index d62f53501fbb..9db823e46314 100644 --- a/drivers/net/wireless/ath/ath10k/snoc.h +++ b/drivers/net/wireless/ath/ath10k/snoc.h @@ -63,6 +63,7 @@ enum ath10k_snoc_flags { ATH10K_SNOC_FLAG_REGISTERED, ATH10K_SNOC_FLAG_UNREGISTERING, ATH10K_SNOC_FLAG_RECOVERY, + ATH10K_SNOC_FLAG_8BIT_HOST_CAP_QUIRK, }; struct ath10k_snoc { diff --git a/drivers/net/wireless/ath/ath10k/txrx.c b/drivers/net/wireless/ath/ath10k/txrx.c index 4102df016931..39abf8b12903 100644 --- a/drivers/net/wireless/ath/ath10k/txrx.c +++ b/drivers/net/wireless/ath/ath10k/txrx.c @@ -95,6 +95,8 @@ int ath10k_txrx_tx_unref(struct ath10k_htt *htt, info = IEEE80211_SKB_CB(msdu); memset(&info->status, 0, sizeof(info->status)); + info->status.rates[0].idx = -1; + trace_ath10k_txrx_tx_unref(ar, tx_done->msdu_id); if (!(info->flags & IEEE80211_TX_CTL_NO_ACK)) diff --git a/drivers/net/wireless/ath/ath10k/usb.c b/drivers/net/wireless/ath/ath10k/usb.c index e1420f67f776..1e0343081be9 100644 --- a/drivers/net/wireless/ath/ath10k/usb.c +++ b/drivers/net/wireless/ath/ath10k/usb.c @@ -38,6 +38,10 @@ ath10k_usb_alloc_urb_from_pipe(struct ath10k_usb_pipe *pipe) struct ath10k_urb_context *urb_context = NULL; unsigned long flags; + /* bail if this pipe is not initialized */ + if (!pipe->ar_usb) + return NULL; + spin_lock_irqsave(&pipe->ar_usb->cs_lock, flags); if (!list_empty(&pipe->urb_list_head)) { urb_context = list_first_entry(&pipe->urb_list_head, @@ -55,6 +59,10 @@ static void ath10k_usb_free_urb_to_pipe(struct ath10k_usb_pipe *pipe, { unsigned long flags; + /* bail if this pipe is not initialized */ + if (!pipe->ar_usb) + return; + spin_lock_irqsave(&pipe->ar_usb->cs_lock, flags); pipe->urb_cnt++; @@ -435,6 +443,7 @@ static int ath10k_usb_hif_tx_sg(struct ath10k *ar, u8 pipe_id, ath10k_dbg(ar, ATH10K_DBG_USB_BULK, "usb bulk transmit failed: %d\n", ret); usb_unanchor_urb(urb); + usb_free_urb(urb); ret = -EINVAL; goto err_free_urb_to_pipe; } diff --git a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c index 2b29bf4730f6..b4885a700296 100644 --- a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c +++ b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c @@ -4183,7 +4183,7 @@ static void ar9003_hw_thermometer_apply(struct ath_hw *ah) static void ar9003_hw_thermo_cal_apply(struct ath_hw *ah) { - u32 data, ko, kg; + u32 data = 0, ko, kg; if (!AR_SREV_9462_20_OR_LATER(ah)) return; diff --git a/drivers/net/wireless/ath/ath9k/ath9k_pci_owl_loader.c b/drivers/net/wireless/ath/ath9k/ath9k_pci_owl_loader.c index 159490f5a111..60731e07f681 100644 --- a/drivers/net/wireless/ath/ath9k/ath9k_pci_owl_loader.c +++ b/drivers/net/wireless/ath/ath9k/ath9k_pci_owl_loader.c @@ -84,7 +84,7 @@ static int ath9k_pci_fixup(struct pci_dev *pdev, const u16 *cal_data, val = swahb32(val); } - __raw_writel(val, mem + reg); + iowrite32(val, mem + reg); usleep_range(100, 120); } diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c index 4e8e80ac8341..9cec5c216e1f 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c @@ -973,6 +973,8 @@ static bool ath9k_rx_prepare(struct ath9k_htc_priv *priv, struct ath_htc_rx_status *rxstatus; struct ath_rx_status rx_stats; bool decrypt_error = false; + __be16 rs_datalen; + bool is_phyerr; if (skb->len < HTC_RX_FRAME_HEADER_SIZE) { ath_err(common, "Corrupted RX frame, dropping (len: %d)\n", @@ -982,11 +984,24 @@ static bool ath9k_rx_prepare(struct ath9k_htc_priv *priv, rxstatus = (struct ath_htc_rx_status *)skb->data; - if (be16_to_cpu(rxstatus->rs_datalen) - - (skb->len - HTC_RX_FRAME_HEADER_SIZE) != 0) { + rs_datalen = be16_to_cpu(rxstatus->rs_datalen); + if (unlikely(rs_datalen - + (skb->len - HTC_RX_FRAME_HEADER_SIZE) != 0)) { ath_err(common, "Corrupted RX data len, dropping (dlen: %d, skblen: %d)\n", - rxstatus->rs_datalen, skb->len); + rs_datalen, skb->len); + goto rx_next; + } + + is_phyerr = rxstatus->rs_status & ATH9K_RXERR_PHY; + /* + * Discard zero-length packets and packets smaller than an ACK + * which are not PHY_ERROR (short radar pulses have a length of 3) + */ + if (unlikely(!rs_datalen || (rs_datalen < 10 && !is_phyerr))) { + ath_warn(common, + "Short RX data len, dropping (dlen: %d)\n", + rs_datalen); goto rx_next; } @@ -1011,7 +1026,7 @@ static bool ath9k_rx_prepare(struct ath9k_htc_priv *priv, * Process PHY errors and return so that the packet * can be dropped. */ - if (rx_stats.rs_status & ATH9K_RXERR_PHY) { + if (unlikely(is_phyerr)) { /* TODO: Not using DFS processing now. */ if (ath_cmn_process_fft(&priv->spec_priv, hdr, &rx_stats, rx_status->mactime)) { diff --git a/drivers/net/wireless/ath/wil6210/wmi.c b/drivers/net/wireless/ath/wil6210/wmi.c index 153b84447e40..41389c1eb252 100644 --- a/drivers/net/wireless/ath/wil6210/wmi.c +++ b/drivers/net/wireless/ath/wil6210/wmi.c @@ -2505,7 +2505,8 @@ int wmi_set_ie(struct wil6210_vif *vif, u8 type, u16 ie_len, const void *ie) cmd->mgmt_frm_type = type; /* BUG: FW API define ieLen as u8. Will fix FW */ cmd->ie_len = cpu_to_le16(ie_len); - memcpy(cmd->ie_info, ie, ie_len); + if (ie_len) + memcpy(cmd->ie_info, ie, ie_len); rc = wmi_send(wil, WMI_SET_APPIE_CMDID, vif->mid, cmd, len); kfree(cmd); out: @@ -2541,7 +2542,8 @@ int wmi_update_ft_ies(struct wil6210_vif *vif, u16 ie_len, const void *ie) } cmd->ie_len = cpu_to_le16(ie_len); - memcpy(cmd->ie_info, ie, ie_len); + if (ie_len) + memcpy(cmd->ie_info, ie, ie_len); rc = wmi_send(wil, WMI_UPDATE_FT_IES_CMDID, vif->mid, cmd, len); kfree(cmd); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c index 406b367c284c..85cf96461dde 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c @@ -1350,6 +1350,11 @@ void brcmf_detach(struct device *dev) brcmf_fweh_detach(drvr); brcmf_proto_detach(drvr); + if (drvr->mon_if) { + brcmf_net_detach(drvr->mon_if->ndev, false); + drvr->mon_if = NULL; + } + /* make sure primary interface removed last */ for (i = BRCMF_MAX_IFS - 1; i > -1; i--) { if (drvr->iflist[i]) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c index 6c463475e90b..3be60aef5465 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c @@ -1427,6 +1427,8 @@ static int brcmf_pcie_reset(struct device *dev) struct brcmf_fw_request *fwreq; int err; + brcmf_pcie_intr_disable(devinfo); + brcmf_pcie_bus_console_read(devinfo, true); brcmf_detach(dev); diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/led.c b/drivers/net/wireless/intel/iwlwifi/dvm/led.c index dd387aba3317..e8a4d604b910 100644 --- a/drivers/net/wireless/intel/iwlwifi/dvm/led.c +++ b/drivers/net/wireless/intel/iwlwifi/dvm/led.c @@ -171,6 +171,9 @@ void iwl_leds_init(struct iwl_priv *priv) priv->led.name = kasprintf(GFP_KERNEL, "%s-led", wiphy_name(priv->hw->wiphy)); + if (!priv->led.name) + return; + priv->led.brightness_set = iwl_led_brightness_set; priv->led.blink_set = iwl_led_blink_set; priv->led.max_brightness = 1; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index d9eb2b286438..c59cbb8cbdd7 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -514,6 +514,18 @@ static int iwl_send_phy_cfg_cmd(struct iwl_mvm *mvm) struct iwl_phy_cfg_cmd phy_cfg_cmd; enum iwl_ucode_type ucode_type = mvm->fwrt.cur_fw_img; + if (iwl_mvm_has_unified_ucode(mvm) && + !mvm->trans->cfg->tx_with_siso_diversity) { + return 0; + } else if (mvm->trans->cfg->tx_with_siso_diversity) { + /* + * TODO: currently we don't set the antenna but letting the NIC + * to decide which antenna to use. This should come from BIOS. + */ + phy_cfg_cmd.phy_cfg = + cpu_to_le32(FW_PHY_CFG_CHAIN_SAD_ENABLED); + } + /* Set parameters */ phy_cfg_cmd.phy_cfg = cpu_to_le32(iwl_mvm_get_phy_config(mvm)); @@ -1344,12 +1356,12 @@ int iwl_mvm_up(struct iwl_mvm *mvm) ret = iwl_send_phy_db_data(mvm->phy_db); if (ret) goto error; - - ret = iwl_send_phy_cfg_cmd(mvm); - if (ret) - goto error; } + ret = iwl_send_phy_cfg_cmd(mvm); + if (ret) + goto error; + ret = iwl_mvm_send_bt_init_conf(mvm); if (ret) goto error; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/led.c b/drivers/net/wireless/intel/iwlwifi/mvm/led.c index d104da9170ca..72c4b2b8399d 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/led.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/led.c @@ -129,6 +129,9 @@ int iwl_mvm_leds_init(struct iwl_mvm *mvm) mvm->led.name = kasprintf(GFP_KERNEL, "%s-led", wiphy_name(mvm->hw->wiphy)); + if (!mvm->led.name) + return -ENOMEM; + mvm->led.brightness_set = iwl_led_brightness_set; mvm->led.max_brightness = 1; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c index 8f50e2b121bd..098d48153a38 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c @@ -350,7 +350,13 @@ void iwl_mvm_tlc_update_notif(struct iwl_mvm *mvm, u16 size = le32_to_cpu(notif->amsdu_size); int i; - if (WARN_ON(sta->max_amsdu_len < size)) + /* + * In debug sta->max_amsdu_len < size + * so also check with orig_amsdu_len which holds the original + * data before debugfs changed the value + */ + if (WARN_ON(sta->max_amsdu_len < size && + mvmsta->orig_amsdu_len < size)) goto out; mvmsta->amsdu_enabled = le32_to_cpu(notif->amsdu_enabled); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c index 0ad8ed23a455..5ee33c8ae9d2 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c @@ -60,6 +60,7 @@ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. *****************************************************************************/ +#include #include #include #include "iwl-trans.h" @@ -357,7 +358,7 @@ void iwl_mvm_rx_rx_mpdu(struct iwl_mvm *mvm, struct napi_struct *napi, rx_res = (struct iwl_rx_mpdu_res_start *)pkt->data; hdr = (struct ieee80211_hdr *)(pkt->data + sizeof(*rx_res)); len = le16_to_cpu(rx_res->byte_count); - rx_pkt_status = le32_to_cpup((__le32 *) + rx_pkt_status = get_unaligned_le32((__le32 *) (pkt->data + sizeof(*rx_res) + len)); /* Dont use dev_alloc_skb(), we'll have enough headroom once diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c index fcafa22ec6ce..8aa567d7912c 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c @@ -1220,7 +1220,7 @@ static int iwl_mvm_legacy_config_scan(struct iwl_mvm *mvm) cmd_size = sizeof(struct iwl_scan_config_v2); else cmd_size = sizeof(struct iwl_scan_config_v1); - cmd_size += num_channels; + cmd_size += mvm->fw->ucode_capa.n_scan_channels; cfg = kzalloc(cmd_size, GFP_KERNEL); if (!cfg) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index 8a059da7a1fa..e3b2a2bf3863 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -935,7 +935,12 @@ static int iwl_mvm_tx_tso(struct iwl_mvm *mvm, struct sk_buff *skb, !(mvmsta->amsdu_enabled & BIT(tid))) return iwl_mvm_tx_tso_segment(skb, 1, netdev_flags, mpdus_skb); - max_amsdu_len = iwl_mvm_max_amsdu_size(mvm, sta, tid); + /* + * Take the min of ieee80211 station and mvm station + */ + max_amsdu_len = + min_t(unsigned int, sta->max_amsdu_len, + iwl_mvm_max_amsdu_size(mvm, sta, tid)); /* * Limit A-MSDU in A-MPDU to 4095 bytes when VHT is not diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index 040cec17d3ad..de62a6dc4e73 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -1107,22 +1107,26 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) cfg = &iwl9560_2ac_cfg_qu_c0_jf_b0; else if (cfg == &iwl9560_2ac_160_cfg_qu_b0_jf_b0) cfg = &iwl9560_2ac_160_cfg_qu_c0_jf_b0; + else if (cfg == &killer1650s_2ax_cfg_qu_b0_hr_b0) + cfg = &killer1650s_2ax_cfg_qu_c0_hr_b0; + else if (cfg == &killer1650i_2ax_cfg_qu_b0_hr_b0) + cfg = &killer1650i_2ax_cfg_qu_c0_hr_b0; } /* same thing for QuZ... */ if (iwl_trans->hw_rev == CSR_HW_REV_TYPE_QUZ) { - if (iwl_trans->cfg == &iwl_ax101_cfg_qu_hr) - iwl_trans->cfg = &iwl_ax101_cfg_quz_hr; - else if (iwl_trans->cfg == &iwl_ax201_cfg_qu_hr) - iwl_trans->cfg = &iwl_ax201_cfg_quz_hr; - else if (iwl_trans->cfg == &iwl9461_2ac_cfg_qu_b0_jf_b0) - iwl_trans->cfg = &iwl9461_2ac_cfg_quz_a0_jf_b0_soc; - else if (iwl_trans->cfg == &iwl9462_2ac_cfg_qu_b0_jf_b0) - iwl_trans->cfg = &iwl9462_2ac_cfg_quz_a0_jf_b0_soc; - else if (iwl_trans->cfg == &iwl9560_2ac_cfg_qu_b0_jf_b0) - iwl_trans->cfg = &iwl9560_2ac_cfg_quz_a0_jf_b0_soc; - else if (iwl_trans->cfg == &iwl9560_2ac_160_cfg_qu_b0_jf_b0) - iwl_trans->cfg = &iwl9560_2ac_160_cfg_quz_a0_jf_b0_soc; + if (cfg == &iwl_ax101_cfg_qu_hr) + cfg = &iwl_ax101_cfg_quz_hr; + else if (cfg == &iwl_ax201_cfg_qu_hr) + cfg = &iwl_ax201_cfg_quz_hr; + else if (cfg == &iwl9461_2ac_cfg_qu_b0_jf_b0) + cfg = &iwl9461_2ac_cfg_quz_a0_jf_b0_soc; + else if (cfg == &iwl9462_2ac_cfg_qu_b0_jf_b0) + cfg = &iwl9462_2ac_cfg_quz_a0_jf_b0_soc; + else if (cfg == &iwl9560_2ac_cfg_qu_b0_jf_b0) + cfg = &iwl9560_2ac_cfg_quz_a0_jf_b0_soc; + else if (cfg == &iwl9560_2ac_160_cfg_qu_b0_jf_b0) + cfg = &iwl9560_2ac_160_cfg_quz_a0_jf_b0_soc; } #endif diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c index 19dd075f2f63..041dd75ac72b 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c @@ -1429,6 +1429,7 @@ static struct iwl_rx_mem_buffer *iwl_pcie_get_rxb(struct iwl_trans *trans, static void iwl_pcie_rx_handle(struct iwl_trans *trans, int queue) { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); + struct napi_struct *napi; struct iwl_rxq *rxq; u32 r, i, count = 0; bool emergency = false; @@ -1534,8 +1535,16 @@ static void iwl_pcie_rx_handle(struct iwl_trans *trans, int queue) if (unlikely(emergency && count)) iwl_pcie_rxq_alloc_rbs(trans, GFP_ATOMIC, rxq); - if (rxq->napi.poll) - napi_gro_flush(&rxq->napi, false); + napi = &rxq->napi; + if (napi->poll) { + if (napi->rx_count) { + netif_receive_skb_list(&napi->rx_list); + INIT_LIST_HEAD(&napi->rx_list); + napi->rx_count = 0; + } + + napi_gro_flush(napi, false); + } iwl_pcie_rxq_restock(trans, rxq); } diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c index ca3bb4d65b00..df8455f14e4d 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c @@ -57,24 +57,6 @@ #include "internal.h" #include "fw/dbg.h" -static int iwl_pcie_gen2_force_power_gating(struct iwl_trans *trans) -{ - iwl_set_bits_prph(trans, HPM_HIPM_GEN_CFG, - HPM_HIPM_GEN_CFG_CR_FORCE_ACTIVE); - udelay(20); - iwl_set_bits_prph(trans, HPM_HIPM_GEN_CFG, - HPM_HIPM_GEN_CFG_CR_PG_EN | - HPM_HIPM_GEN_CFG_CR_SLP_EN); - udelay(20); - iwl_clear_bits_prph(trans, HPM_HIPM_GEN_CFG, - HPM_HIPM_GEN_CFG_CR_FORCE_ACTIVE); - - iwl_trans_sw_reset(trans); - iwl_clear_bit(trans, CSR_GP_CNTRL, CSR_GP_CNTRL_REG_FLAG_INIT_DONE); - - return 0; -} - /* * Start up NIC's basic functionality after it has been reset * (e.g. after platform boot, or shutdown via iwl_pcie_apm_stop()) @@ -110,13 +92,6 @@ int iwl_pcie_gen2_apm_init(struct iwl_trans *trans) iwl_pcie_apm_config(trans); - if (trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_22000 && - trans->cfg->integrated) { - ret = iwl_pcie_gen2_force_power_gating(trans); - if (ret) - return ret; - } - ret = iwl_finish_nic_init(trans, trans->trans_cfg); if (ret) return ret; diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c index 6961f00ff812..d3db38c3095b 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c @@ -1783,6 +1783,29 @@ static int iwl_trans_pcie_clear_persistence_bit(struct iwl_trans *trans) return 0; } +static int iwl_pcie_gen2_force_power_gating(struct iwl_trans *trans) +{ + int ret; + + ret = iwl_finish_nic_init(trans, trans->trans_cfg); + if (ret < 0) + return ret; + + iwl_set_bits_prph(trans, HPM_HIPM_GEN_CFG, + HPM_HIPM_GEN_CFG_CR_FORCE_ACTIVE); + udelay(20); + iwl_set_bits_prph(trans, HPM_HIPM_GEN_CFG, + HPM_HIPM_GEN_CFG_CR_PG_EN | + HPM_HIPM_GEN_CFG_CR_SLP_EN); + udelay(20); + iwl_clear_bits_prph(trans, HPM_HIPM_GEN_CFG, + HPM_HIPM_GEN_CFG_CR_FORCE_ACTIVE); + + iwl_trans_pcie_sw_reset(trans); + + return 0; +} + static int _iwl_trans_pcie_start_hw(struct iwl_trans *trans) { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); @@ -1802,6 +1825,13 @@ static int _iwl_trans_pcie_start_hw(struct iwl_trans *trans) iwl_trans_pcie_sw_reset(trans); + if (trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_22000 && + trans->cfg->integrated) { + err = iwl_pcie_gen2_force_power_gating(trans); + if (err) + return err; + } + err = iwl_pcie_apm_init(trans); if (err) return err; diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c index d80f71f82a6d..97cb3a8d505c 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c @@ -468,6 +468,7 @@ iwl_tfh_tfd *iwl_pcie_gen2_build_tx(struct iwl_trans *trans, dma_addr_t tb_phys; int len, tb1_len, tb2_len; void *tb1_addr; + struct sk_buff *frag; tb_phys = iwl_pcie_get_first_tb_dma(txq, idx); @@ -516,6 +517,19 @@ iwl_tfh_tfd *iwl_pcie_gen2_build_tx(struct iwl_trans *trans, if (iwl_pcie_gen2_tx_add_frags(trans, skb, tfd, out_meta)) goto out_err; + skb_walk_frags(skb, frag) { + tb_phys = dma_map_single(trans->dev, frag->data, + skb_headlen(frag), DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(trans->dev, tb_phys))) + goto out_err; + iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, skb_headlen(frag)); + trace_iwlwifi_dev_tx_tb(trans->dev, skb, + frag->data, + skb_headlen(frag)); + if (iwl_pcie_gen2_tx_add_frags(trans, frag, tfd, out_meta)) + goto out_err; + } + return tfd; out_err: diff --git a/drivers/net/wireless/marvell/libertas/if_sdio.c b/drivers/net/wireless/marvell/libertas/if_sdio.c index 242d8845da3f..30f1025ecb9b 100644 --- a/drivers/net/wireless/marvell/libertas/if_sdio.c +++ b/drivers/net/wireless/marvell/libertas/if_sdio.c @@ -1179,6 +1179,10 @@ static int if_sdio_probe(struct sdio_func *func, spin_lock_init(&card->lock); card->workqueue = alloc_workqueue("libertas_sdio", WQ_MEM_RECLAIM, 0); + if (unlikely(!card->workqueue)) { + ret = -ENOMEM; + goto err_queue; + } INIT_WORK(&card->packet_worker, if_sdio_host_to_card_worker); init_waitqueue_head(&card->pwron_waitq); @@ -1230,6 +1234,7 @@ static int if_sdio_probe(struct sdio_func *func, lbs_remove_card(priv); free: destroy_workqueue(card->workqueue); +err_queue: while (card->packets) { packet = card->packets; card->packets = card->packets->next; diff --git a/drivers/net/wireless/marvell/mwifiex/main.c b/drivers/net/wireless/marvell/mwifiex/main.c index a9657ae6d782..d14e55e3c9da 100644 --- a/drivers/net/wireless/marvell/mwifiex/main.c +++ b/drivers/net/wireless/marvell/mwifiex/main.c @@ -631,6 +631,7 @@ static int _mwifiex_fw_dpc(const struct firmware *firmware, void *context) mwifiex_drv_get_driver_version(adapter, fmt, sizeof(fmt) - 1); mwifiex_dbg(adapter, MSG, "driver_version = %s\n", fmt); + adapter->is_up = true; goto done; err_add_intf: @@ -1469,6 +1470,7 @@ int mwifiex_shutdown_sw(struct mwifiex_adapter *adapter) mwifiex_deauthenticate(priv, NULL); mwifiex_uninit_sw(adapter); + adapter->is_up = false; if (adapter->if_ops.down_dev) adapter->if_ops.down_dev(adapter); @@ -1730,7 +1732,8 @@ int mwifiex_remove_card(struct mwifiex_adapter *adapter) if (!adapter) return 0; - mwifiex_uninit_sw(adapter); + if (adapter->is_up) + mwifiex_uninit_sw(adapter); if (adapter->irq_wakeup >= 0) device_init_wakeup(adapter->dev, false); diff --git a/drivers/net/wireless/marvell/mwifiex/main.h b/drivers/net/wireless/marvell/mwifiex/main.h index 095837fba300..547ff3c578ee 100644 --- a/drivers/net/wireless/marvell/mwifiex/main.h +++ b/drivers/net/wireless/marvell/mwifiex/main.h @@ -1017,6 +1017,7 @@ struct mwifiex_adapter { /* For synchronizing FW initialization with device lifecycle. */ struct completion *fw_done; + bool is_up; bool ext_scan; u8 fw_api_ver; diff --git a/drivers/net/wireless/marvell/mwifiex/pcie.c b/drivers/net/wireless/marvell/mwifiex/pcie.c index eff06d59e9df..fc1706d0647d 100644 --- a/drivers/net/wireless/marvell/mwifiex/pcie.c +++ b/drivers/net/wireless/marvell/mwifiex/pcie.c @@ -687,8 +687,11 @@ static int mwifiex_pcie_init_evt_ring(struct mwifiex_adapter *adapter) skb_put(skb, MAX_EVENT_SIZE); if (mwifiex_map_pci_memory(adapter, skb, MAX_EVENT_SIZE, - PCI_DMA_FROMDEVICE)) + PCI_DMA_FROMDEVICE)) { + kfree_skb(skb); + kfree(card->evtbd_ring_vbase); return -1; + } buf_pa = MWIFIEX_SKB_DMA_ADDR(skb); @@ -1029,8 +1032,10 @@ static int mwifiex_pcie_alloc_cmdrsp_buf(struct mwifiex_adapter *adapter) } skb_put(skb, MWIFIEX_UPLD_SIZE); if (mwifiex_map_pci_memory(adapter, skb, MWIFIEX_UPLD_SIZE, - PCI_DMA_FROMDEVICE)) + PCI_DMA_FROMDEVICE)) { + kfree_skb(skb); return -1; + } card->cmdrsp_buf = skb; diff --git a/drivers/net/wireless/marvell/mwifiex/sdio.c b/drivers/net/wireless/marvell/mwifiex/sdio.c index 24c041dad9f6..fec38b6e86ff 100644 --- a/drivers/net/wireless/marvell/mwifiex/sdio.c +++ b/drivers/net/wireless/marvell/mwifiex/sdio.c @@ -444,6 +444,9 @@ static int mwifiex_sdio_suspend(struct device *dev) return 0; } + if (!adapter->is_up) + return -EBUSY; + mwifiex_enable_wake(adapter); /* Enable the Host Sleep */ @@ -2220,22 +2223,30 @@ static void mwifiex_sdio_card_reset_work(struct mwifiex_adapter *adapter) struct sdio_func *func = card->func; int ret; + /* Prepare the adapter for the reset. */ mwifiex_shutdown_sw(adapter); + clear_bit(MWIFIEX_IFACE_WORK_DEVICE_DUMP, &card->work_flags); + clear_bit(MWIFIEX_IFACE_WORK_CARD_RESET, &card->work_flags); - /* power cycle the adapter */ + /* Run a HW reset of the SDIO interface. */ sdio_claim_host(func); - mmc_hw_reset(func->card->host); + ret = mmc_hw_reset(func->card->host); sdio_release_host(func); - /* Previous save_adapter won't be valid after this. We will cancel - * pending work requests. - */ - clear_bit(MWIFIEX_IFACE_WORK_DEVICE_DUMP, &card->work_flags); - clear_bit(MWIFIEX_IFACE_WORK_CARD_RESET, &card->work_flags); - - ret = mwifiex_reinit_sw(adapter); - if (ret) - dev_err(&func->dev, "reinit failed: %d\n", ret); + switch (ret) { + case 1: + dev_dbg(&func->dev, "SDIO HW reset asynchronous\n"); + complete_all(adapter->fw_done); + break; + case 0: + ret = mwifiex_reinit_sw(adapter); + if (ret) + dev_err(&func->dev, "reinit failed: %d\n", ret); + break; + default: + dev_err(&func->dev, "SDIO HW reset failed: %d\n", ret); + break; + } } /* This function read/write firmware */ diff --git a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c index 74e50566db1f..6dd835f1efc2 100644 --- a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c +++ b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c @@ -229,6 +229,14 @@ static int mwifiex_process_country_ie(struct mwifiex_private *priv, "11D: skip setting domain info in FW\n"); return 0; } + + if (country_ie_len > + (IEEE80211_COUNTRY_STRING_LEN + MWIFIEX_MAX_TRIPLET_802_11D)) { + mwifiex_dbg(priv->adapter, ERROR, + "11D: country_ie_len overflow!, deauth AP\n"); + return -EINVAL; + } + memcpy(priv->adapter->country_code, &country_ie[2], 2); domain_info->country_code[0] = country_ie[2]; @@ -272,8 +280,9 @@ int mwifiex_bss_start(struct mwifiex_private *priv, struct cfg80211_bss *bss, priv->scan_block = false; if (bss) { - if (adapter->region_code == 0x00) - mwifiex_process_country_ie(priv, bss); + if (adapter->region_code == 0x00 && + mwifiex_process_country_ie(priv, bss)) + return -EINVAL; /* Allocate and fill new bss descriptor */ bss_desc = kzalloc(sizeof(struct mwifiex_bssdescriptor), diff --git a/drivers/net/wireless/marvell/mwifiex/tdls.c b/drivers/net/wireless/marvell/mwifiex/tdls.c index 09313047beed..7caf1d26124a 100644 --- a/drivers/net/wireless/marvell/mwifiex/tdls.c +++ b/drivers/net/wireless/marvell/mwifiex/tdls.c @@ -953,59 +953,117 @@ void mwifiex_process_tdls_action_frame(struct mwifiex_private *priv, switch (*pos) { case WLAN_EID_SUPP_RATES: + if (pos[1] > 32) + return; sta_ptr->tdls_cap.rates_len = pos[1]; for (i = 0; i < pos[1]; i++) sta_ptr->tdls_cap.rates[i] = pos[i + 2]; break; case WLAN_EID_EXT_SUPP_RATES: + if (pos[1] > 32) + return; basic = sta_ptr->tdls_cap.rates_len; + if (pos[1] > 32 - basic) + return; for (i = 0; i < pos[1]; i++) sta_ptr->tdls_cap.rates[basic + i] = pos[i + 2]; sta_ptr->tdls_cap.rates_len += pos[1]; break; case WLAN_EID_HT_CAPABILITY: - memcpy((u8 *)&sta_ptr->tdls_cap.ht_capb, pos, + if (pos > end - sizeof(struct ieee80211_ht_cap) - 2) + return; + if (pos[1] != sizeof(struct ieee80211_ht_cap)) + return; + /* copy the ie's value into ht_capb*/ + memcpy((u8 *)&sta_ptr->tdls_cap.ht_capb, pos + 2, sizeof(struct ieee80211_ht_cap)); sta_ptr->is_11n_enabled = 1; break; case WLAN_EID_HT_OPERATION: - memcpy(&sta_ptr->tdls_cap.ht_oper, pos, + if (pos > end - + sizeof(struct ieee80211_ht_operation) - 2) + return; + if (pos[1] != sizeof(struct ieee80211_ht_operation)) + return; + /* copy the ie's value into ht_oper*/ + memcpy(&sta_ptr->tdls_cap.ht_oper, pos + 2, sizeof(struct ieee80211_ht_operation)); break; case WLAN_EID_BSS_COEX_2040: + if (pos > end - 3) + return; + if (pos[1] != 1) + return; sta_ptr->tdls_cap.coex_2040 = pos[2]; break; case WLAN_EID_EXT_CAPABILITY: + if (pos > end - sizeof(struct ieee_types_header)) + return; + if (pos[1] < sizeof(struct ieee_types_header)) + return; + if (pos[1] > 8) + return; memcpy((u8 *)&sta_ptr->tdls_cap.extcap, pos, sizeof(struct ieee_types_header) + min_t(u8, pos[1], 8)); break; case WLAN_EID_RSN: + if (pos > end - sizeof(struct ieee_types_header)) + return; + if (pos[1] < sizeof(struct ieee_types_header)) + return; + if (pos[1] > IEEE_MAX_IE_SIZE - + sizeof(struct ieee_types_header)) + return; memcpy((u8 *)&sta_ptr->tdls_cap.rsn_ie, pos, sizeof(struct ieee_types_header) + min_t(u8, pos[1], IEEE_MAX_IE_SIZE - sizeof(struct ieee_types_header))); break; case WLAN_EID_QOS_CAPA: + if (pos > end - 3) + return; + if (pos[1] != 1) + return; sta_ptr->tdls_cap.qos_info = pos[2]; break; case WLAN_EID_VHT_OPERATION: - if (priv->adapter->is_hw_11ac_capable) - memcpy(&sta_ptr->tdls_cap.vhtoper, pos, + if (priv->adapter->is_hw_11ac_capable) { + if (pos > end - + sizeof(struct ieee80211_vht_operation) - 2) + return; + if (pos[1] != + sizeof(struct ieee80211_vht_operation)) + return; + /* copy the ie's value into vhtoper*/ + memcpy(&sta_ptr->tdls_cap.vhtoper, pos + 2, sizeof(struct ieee80211_vht_operation)); + } break; case WLAN_EID_VHT_CAPABILITY: if (priv->adapter->is_hw_11ac_capable) { - memcpy((u8 *)&sta_ptr->tdls_cap.vhtcap, pos, + if (pos > end - + sizeof(struct ieee80211_vht_cap) - 2) + return; + if (pos[1] != sizeof(struct ieee80211_vht_cap)) + return; + /* copy the ie's value into vhtcap*/ + memcpy((u8 *)&sta_ptr->tdls_cap.vhtcap, pos + 2, sizeof(struct ieee80211_vht_cap)); sta_ptr->is_11ac_enabled = 1; } break; case WLAN_EID_AID: - if (priv->adapter->is_hw_11ac_capable) + if (priv->adapter->is_hw_11ac_capable) { + if (pos > end - 4) + return; + if (pos[1] != 2) + return; sta_ptr->tdls_cap.aid = get_unaligned_le16((pos + 2)); + } + break; default: break; } diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/mac.c b/drivers/net/wireless/mediatek/mt76/mt7603/mac.c index c328192307c4..ff3f3d98b625 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7603/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7603/mac.c @@ -1032,8 +1032,10 @@ mt7603_fill_txs(struct mt7603_dev *dev, struct mt7603_sta *sta, if (idx && (cur_rate->idx != info->status.rates[i].idx || cur_rate->flags != info->status.rates[i].flags)) { i++; - if (i == ARRAY_SIZE(info->status.rates)) + if (i == ARRAY_SIZE(info->status.rates)) { + i--; break; + } info->status.rates[i] = *cur_rate; info->status.rates[i].count = 0; diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c index e07ce2c10013..111e38ff954a 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c @@ -914,8 +914,10 @@ static bool mt7615_fill_txs(struct mt7615_dev *dev, struct mt7615_sta *sta, if (idx && (cur_rate->idx != info->status.rates[i].idx || cur_rate->flags != info->status.rates[i].flags)) { i++; - if (i == ARRAY_SIZE(info->status.rates)) + if (i == ARRAY_SIZE(info->status.rates)) { + i--; break; + } info->status.rates[i] = *cur_rate; info->status.rates[i].count = 0; diff --git a/drivers/net/wireless/quantenna/qtnfmac/commands.c b/drivers/net/wireless/quantenna/qtnfmac/commands.c index dc0c7244b60e..c0c32805fb8d 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/commands.c +++ b/drivers/net/wireless/quantenna/qtnfmac/commands.c @@ -83,6 +83,7 @@ static int qtnf_cmd_send_with_reply(struct qtnf_bus *bus, struct qlink_cmd *cmd; struct qlink_resp *resp = NULL; struct sk_buff *resp_skb = NULL; + int resp_res = 0; u16 cmd_id; u8 mac_id; u8 vif_id; @@ -113,6 +114,7 @@ static int qtnf_cmd_send_with_reply(struct qtnf_bus *bus, } resp = (struct qlink_resp *)resp_skb->data; + resp_res = le16_to_cpu(resp->result); ret = qtnf_cmd_check_reply_header(resp, cmd_id, mac_id, vif_id, const_resp_size); if (ret) @@ -128,8 +130,8 @@ static int qtnf_cmd_send_with_reply(struct qtnf_bus *bus, else consume_skb(resp_skb); - if (!ret && resp) - return qtnf_cmd_resp_result_decode(le16_to_cpu(resp->result)); + if (!ret) + return qtnf_cmd_resp_result_decode(resp_res); pr_warn("VIF%u.%u: cmd 0x%.4X failed: %d\n", mac_id, vif_id, cmd_id, ret); diff --git a/drivers/net/wireless/quantenna/qtnfmac/event.c b/drivers/net/wireless/quantenna/qtnfmac/event.c index b57c8c18a8d0..7846383c8828 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/event.c +++ b/drivers/net/wireless/quantenna/qtnfmac/event.c @@ -171,8 +171,9 @@ qtnf_event_handle_bss_join(struct qtnf_vif *vif, return -EPROTO; } - pr_debug("VIF%u.%u: BSSID:%pM status:%u\n", - vif->mac->macid, vif->vifid, join_info->bssid, status); + pr_debug("VIF%u.%u: BSSID:%pM chan:%u status:%u\n", + vif->mac->macid, vif->vifid, join_info->bssid, + le16_to_cpu(join_info->chan.chan.center_freq), status); if (status != WLAN_STATUS_SUCCESS) goto done; @@ -181,7 +182,7 @@ qtnf_event_handle_bss_join(struct qtnf_vif *vif, if (!cfg80211_chandef_valid(&chandef)) { pr_warn("MAC%u.%u: bad channel freq=%u cf1=%u cf2=%u bw=%u\n", vif->mac->macid, vif->vifid, - chandef.chan->center_freq, + chandef.chan ? chandef.chan->center_freq : 0, chandef.center_freq1, chandef.center_freq2, chandef.width); diff --git a/drivers/net/wireless/quantenna/qtnfmac/pcie/pcie.c b/drivers/net/wireless/quantenna/qtnfmac/pcie/pcie.c index 8ae318b5fe54..4824be0c6231 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/pcie/pcie.c +++ b/drivers/net/wireless/quantenna/qtnfmac/pcie/pcie.c @@ -130,6 +130,8 @@ static int qtnf_dbg_shm_stats(struct seq_file *s, void *data) int qtnf_pcie_fw_boot_done(struct qtnf_bus *bus) { + struct qtnf_pcie_bus_priv *priv = get_bus_priv(bus); + char card_id[64]; int ret; bus->fw_state = QTNF_FW_STATE_BOOT_DONE; @@ -137,7 +139,9 @@ int qtnf_pcie_fw_boot_done(struct qtnf_bus *bus) if (ret) { pr_err("failed to attach core\n"); } else { - qtnf_debugfs_init(bus, DRV_NAME); + snprintf(card_id, sizeof(card_id), "%s:%s", + DRV_NAME, pci_name(priv->pdev)); + qtnf_debugfs_init(bus, card_id); qtnf_debugfs_add_entry(bus, "mps", qtnf_dbg_mps_show); qtnf_debugfs_add_entry(bus, "msi_enabled", qtnf_dbg_msi_show); qtnf_debugfs_add_entry(bus, "shm_stats", qtnf_dbg_shm_stats); diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h index ade057d868f7..5e9ce03067de 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h @@ -1341,6 +1341,7 @@ struct rtl8xxxu_fileops { u8 has_s0s1:1; u8 has_tx_report:1; u8 gen2_thermal_meter:1; + u8 needs_full_init:1; u32 adda_1t_init; u32 adda_1t_path_on; u32 adda_2t_path_on_a; diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8723b.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8723b.c index ceffe05bd65b..f3cd314d1a9c 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8723b.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8723b.c @@ -1670,6 +1670,7 @@ struct rtl8xxxu_fileops rtl8723bu_fops = { .has_s0s1 = 1, .has_tx_report = 1, .gen2_thermal_meter = 1, + .needs_full_init = 1, .adda_1t_init = 0x01c00014, .adda_1t_path_on = 0x01c00014, .adda_2t_path_on_a = 0x01c00014, diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c index c6c41fb962ff..e7d96ac673b7 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c @@ -3902,6 +3902,9 @@ static int rtl8xxxu_init_device(struct ieee80211_hw *hw) else macpower = true; + if (fops->needs_full_init) + macpower = false; + ret = fops->power_on(priv); if (ret < 0) { dev_warn(dev, "%s: Failed power on\n", __func__); @@ -5444,6 +5447,7 @@ static int rtl8xxxu_submit_int_urb(struct ieee80211_hw *hw) ret = usb_submit_urb(urb, GFP_KERNEL); if (ret) { usb_unanchor_urb(urb); + usb_free_urb(urb); goto error; } diff --git a/drivers/net/wireless/realtek/rtlwifi/regd.c b/drivers/net/wireless/realtek/rtlwifi/regd.c index c10432cd703e..8be31e0ad878 100644 --- a/drivers/net/wireless/realtek/rtlwifi/regd.c +++ b/drivers/net/wireless/realtek/rtlwifi/regd.c @@ -386,7 +386,7 @@ int rtl_regd_init(struct ieee80211_hw *hw, struct wiphy *wiphy = hw->wiphy; struct country_code_to_enum_rd *country = NULL; - if (wiphy == NULL || &rtlpriv->regd == NULL) + if (!wiphy) return -EINVAL; /* init country_code from efuse channel plan */ diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/hw.c index 56cc3bc30860..f070f25bb735 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/hw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/hw.c @@ -1540,6 +1540,8 @@ static bool usb_cmd_send_packet(struct ieee80211_hw *hw, struct sk_buff *skb) * This is maybe necessary: * rtlpriv->cfg->ops->fill_tx_cmddesc(hw, buffer, 1, 1, skb); */ + dev_kfree_skb(skb); + return true; } diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.c index c7f29a9be50d..146fe144f5f5 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.c @@ -1176,6 +1176,7 @@ void rtl92de_enable_interrupt(struct ieee80211_hw *hw) rtl_write_dword(rtlpriv, REG_HIMR, rtlpci->irq_mask[0] & 0xFFFFFFFF); rtl_write_dword(rtlpriv, REG_HIMRE, rtlpci->irq_mask[1] & 0xFFFFFFFF); + rtlpci->irq_enabled = true; } void rtl92de_disable_interrupt(struct ieee80211_hw *hw) @@ -1185,7 +1186,7 @@ void rtl92de_disable_interrupt(struct ieee80211_hw *hw) rtl_write_dword(rtlpriv, REG_HIMR, IMR8190_DISABLED); rtl_write_dword(rtlpriv, REG_HIMRE, IMR8190_DISABLED); - synchronize_irq(rtlpci->pdev->irq); + rtlpci->irq_enabled = false; } static void _rtl92de_poweroff_adapter(struct ieee80211_hw *hw) @@ -1351,7 +1352,7 @@ void rtl92de_set_beacon_related_registers(struct ieee80211_hw *hw) bcn_interval = mac->beacon_interval; atim_window = 2; - /*rtl92de_disable_interrupt(hw); */ + rtl92de_disable_interrupt(hw); rtl_write_word(rtlpriv, REG_ATIMWND, atim_window); rtl_write_word(rtlpriv, REG_BCN_INTERVAL, bcn_interval); rtl_write_word(rtlpriv, REG_BCNTCFG, 0x660f); @@ -1371,9 +1372,9 @@ void rtl92de_set_beacon_interval(struct ieee80211_hw *hw) RT_TRACE(rtlpriv, COMP_BEACON, DBG_DMESG, "beacon_interval:%d\n", bcn_interval); - /* rtl92de_disable_interrupt(hw); */ + rtl92de_disable_interrupt(hw); rtl_write_word(rtlpriv, REG_BCN_INTERVAL, bcn_interval); - /* rtl92de_enable_interrupt(hw); */ + rtl92de_enable_interrupt(hw); } void rtl92de_update_interrupt_mask(struct ieee80211_hw *hw, diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c index 99e5cd9a5c86..1dbdddce0823 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c @@ -216,6 +216,7 @@ static struct rtl_hal_ops rtl8192de_hal_ops = { .led_control = rtl92de_led_control, .set_desc = rtl92de_set_desc, .get_desc = rtl92de_get_desc, + .is_tx_desc_closed = rtl92de_is_tx_desc_closed, .tx_polling = rtl92de_tx_polling, .enable_hw_sec = rtl92de_enable_hw_security_config, .set_key = rtl92de_set_key, diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.c index 2494e1f118f8..92c9fb45f800 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.c @@ -804,13 +804,15 @@ u64 rtl92de_get_desc(struct ieee80211_hw *hw, break; } } else { - struct rx_desc_92c *pdesc = (struct rx_desc_92c *)p_desc; switch (desc_name) { case HW_DESC_OWN: - ret = GET_RX_DESC_OWN(pdesc); + ret = GET_RX_DESC_OWN(p_desc); break; case HW_DESC_RXPKT_LEN: - ret = GET_RX_DESC_PKT_LEN(pdesc); + ret = GET_RX_DESC_PKT_LEN(p_desc); + break; + case HW_DESC_RXBUFF_ADDR: + ret = GET_RX_DESC_BUFF_ADDR(p_desc); break; default: WARN_ONCE(true, "rtl8192de: ERR rxdesc :%d not processed\n", @@ -821,6 +823,23 @@ u64 rtl92de_get_desc(struct ieee80211_hw *hw, return ret; } +bool rtl92de_is_tx_desc_closed(struct ieee80211_hw *hw, + u8 hw_queue, u16 index) +{ + struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); + struct rtl8192_tx_ring *ring = &rtlpci->tx_ring[hw_queue]; + u8 *entry = (u8 *)(&ring->desc[ring->idx]); + u8 own = (u8)rtl92de_get_desc(hw, entry, true, HW_DESC_OWN); + + /* a beacon packet will only use the first + * descriptor by defaut, and the own bit may not + * be cleared by the hardware + */ + if (own) + return false; + return true; +} + void rtl92de_tx_polling(struct ieee80211_hw *hw, u8 hw_queue) { struct rtl_priv *rtlpriv = rtl_priv(hw); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.h index 36820070fd76..635989e15282 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.h +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.h @@ -715,6 +715,8 @@ void rtl92de_set_desc(struct ieee80211_hw *hw, u8 *pdesc, bool istx, u8 desc_name, u8 *val); u64 rtl92de_get_desc(struct ieee80211_hw *hw, u8 *p_desc, bool istx, u8 desc_name); +bool rtl92de_is_tx_desc_closed(struct ieee80211_hw *hw, + u8 hw_queue, u16 index); void rtl92de_tx_polling(struct ieee80211_hw *hw, u8 hw_queue); void rtl92de_tx_fill_cmddesc(struct ieee80211_hw *hw, u8 *pdesc, bool b_firstseg, bool b_lastseg, diff --git a/drivers/net/wireless/realtek/rtlwifi/usb.c b/drivers/net/wireless/realtek/rtlwifi/usb.c index 4b59f3b46b28..348b0072cdd6 100644 --- a/drivers/net/wireless/realtek/rtlwifi/usb.c +++ b/drivers/net/wireless/realtek/rtlwifi/usb.c @@ -1021,8 +1021,10 @@ int rtl_usb_probe(struct usb_interface *intf, rtlpriv->hw = hw; rtlpriv->usb_data = kcalloc(RTL_USB_MAX_RX_COUNT, sizeof(u32), GFP_KERNEL); - if (!rtlpriv->usb_data) + if (!rtlpriv->usb_data) { + ieee80211_free_hw(hw); return -ENOMEM; + } /* this spin lock must be initialized early */ spin_lock_init(&rtlpriv->locks.usb_lock); @@ -1083,6 +1085,7 @@ int rtl_usb_probe(struct usb_interface *intf, _rtl_usb_io_handler_release(hw); usb_put_dev(udev); complete(&rtlpriv->firmware_loading_complete); + kfree(rtlpriv->usb_data); return -ENODEV; } EXPORT_SYMBOL(rtl_usb_probe); diff --git a/drivers/net/wireless/realtek/rtw88/coex.c b/drivers/net/wireless/realtek/rtw88/coex.c index 793b40bdbf7c..3e95ad198912 100644 --- a/drivers/net/wireless/realtek/rtw88/coex.c +++ b/drivers/net/wireless/realtek/rtw88/coex.c @@ -1308,6 +1308,7 @@ static void rtw_coex_action_bt_inquiry(struct rtw_dev *rtwdev) struct rtw_chip_info *chip = rtwdev->chip; bool wl_hi_pri = false; u8 table_case, tdma_case; + u32 slot_type = 0; if (coex_stat->wl_linkscan_proc || coex_stat->wl_hi_pri_task1 || coex_stat->wl_hi_pri_task2) @@ -1318,14 +1319,16 @@ static void rtw_coex_action_bt_inquiry(struct rtw_dev *rtwdev) if (wl_hi_pri) { table_case = 15; if (coex_stat->bt_a2dp_exist && - !coex_stat->bt_pan_exist) + !coex_stat->bt_pan_exist) { + slot_type = TDMA_4SLOT; tdma_case = 11; - else if (coex_stat->wl_hi_pri_task1) + } else if (coex_stat->wl_hi_pri_task1) { tdma_case = 6; - else if (!coex_stat->bt_page) + } else if (!coex_stat->bt_page) { tdma_case = 8; - else + } else { tdma_case = 9; + } } else if (coex_stat->wl_connected) { table_case = 10; tdma_case = 10; @@ -1361,7 +1364,7 @@ static void rtw_coex_action_bt_inquiry(struct rtw_dev *rtwdev) rtw_coex_set_ant_path(rtwdev, false, COEX_SET_ANT_2G); rtw_coex_set_rf_para(rtwdev, chip->wl_rf_para_rx[0]); rtw_coex_table(rtwdev, table_case); - rtw_coex_tdma(rtwdev, false, tdma_case); + rtw_coex_tdma(rtwdev, false, tdma_case | slot_type); } static void rtw_coex_action_bt_hfp(struct rtw_dev *rtwdev) @@ -1475,13 +1478,13 @@ static void rtw_coex_action_bt_a2dp(struct rtw_dev *rtwdev) if (efuse->share_ant) { /* Shared-Ant */ + slot_type = TDMA_4SLOT; + if (coex_stat->wl_gl_busy && coex_stat->wl_noisy_level == 0) table_case = 10; else table_case = 9; - slot_type = TDMA_4SLOT; - if (coex_stat->wl_gl_busy) tdma_case = 13; else @@ -1585,13 +1588,14 @@ static void rtw_coex_action_bt_a2dp_hid(struct rtw_dev *rtwdev) if (efuse->share_ant) { /* Shared-Ant */ + slot_type = TDMA_4SLOT; + if (coex_stat->bt_ble_exist) table_case = 26; else table_case = 9; if (coex_stat->wl_gl_busy) { - slot_type = TDMA_4SLOT; tdma_case = 13; } else { tdma_case = 14; @@ -1794,10 +1798,12 @@ static void rtw_coex_action_wl_linkscan(struct rtw_dev *rtwdev) struct rtw_efuse *efuse = &rtwdev->efuse; struct rtw_chip_info *chip = rtwdev->chip; u8 table_case, tdma_case; + u32 slot_type = 0; if (efuse->share_ant) { /* Shared-Ant */ if (coex_stat->bt_a2dp_exist) { + slot_type = TDMA_4SLOT; table_case = 9; tdma_case = 11; } else { @@ -1818,7 +1824,7 @@ static void rtw_coex_action_wl_linkscan(struct rtw_dev *rtwdev) rtw_coex_set_ant_path(rtwdev, true, COEX_SET_ANT_2G); rtw_coex_set_rf_para(rtwdev, chip->wl_rf_para_rx[0]); rtw_coex_table(rtwdev, table_case); - rtw_coex_tdma(rtwdev, false, tdma_case); + rtw_coex_tdma(rtwdev, false, tdma_case | slot_type); } static void rtw_coex_action_wl_not_connected(struct rtw_dev *rtwdev) diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c index 6dd457741b15..7a3a4911bde2 100644 --- a/drivers/net/wireless/realtek/rtw88/main.c +++ b/drivers/net/wireless/realtek/rtw88/main.c @@ -1020,7 +1020,8 @@ static int rtw_dump_hw_feature(struct rtw_dev *rtwdev) rtw_hw_config_rf_ant_num(rtwdev, efuse->hw_cap.ant_num); - if (efuse->hw_cap.nss == EFUSE_HW_CAP_IGNORE) + if (efuse->hw_cap.nss == EFUSE_HW_CAP_IGNORE || + efuse->hw_cap.nss > rtwdev->hal.rf_path_num) efuse->hw_cap.nss = rtwdev->hal.rf_path_num; rtw_dbg(rtwdev, RTW_DBG_EFUSE, diff --git a/drivers/net/wireless/rsi/rsi_91x_mgmt.c b/drivers/net/wireless/rsi/rsi_91x_mgmt.c index 6c7f26ef6476..9cc8a335d519 100644 --- a/drivers/net/wireless/rsi/rsi_91x_mgmt.c +++ b/drivers/net/wireless/rsi/rsi_91x_mgmt.c @@ -1756,6 +1756,7 @@ static int rsi_send_beacon(struct rsi_common *common) skb_pull(skb, (64 - dword_align_bytes)); if (rsi_prepare_beacon(common, skb)) { rsi_dbg(ERR_ZONE, "Failed to prepare beacon\n"); + dev_kfree_skb(skb); return -EINVAL; } skb_queue_tail(&common->tx_queue[MGMT_BEACON_Q], skb); diff --git a/drivers/net/wireless/rsi/rsi_91x_usb.c b/drivers/net/wireless/rsi/rsi_91x_usb.c index 760eaffeebd6..23a1d00b5f38 100644 --- a/drivers/net/wireless/rsi/rsi_91x_usb.c +++ b/drivers/net/wireless/rsi/rsi_91x_usb.c @@ -793,7 +793,7 @@ static int rsi_probe(struct usb_interface *pfunction, adapter->device_model = RSI_DEV_9116; } else { rsi_dbg(ERR_ZONE, "%s: Unsupported RSI device id 0x%x\n", - __func__, id->idProduct); + __func__, id ? id->idProduct : 0x0); goto err1; } diff --git a/drivers/net/wireless/virt_wifi.c b/drivers/net/wireless/virt_wifi.c index 7997cc6de334..01305ba2d3aa 100644 --- a/drivers/net/wireless/virt_wifi.c +++ b/drivers/net/wireless/virt_wifi.c @@ -450,7 +450,6 @@ static void virt_wifi_net_device_destructor(struct net_device *dev) */ kfree(dev->ieee80211_ptr); dev->ieee80211_ptr = NULL; - free_netdev(dev); } /* No lock interaction. */ @@ -458,7 +457,7 @@ static void virt_wifi_setup(struct net_device *dev) { ether_setup(dev); dev->netdev_ops = &virt_wifi_ops; - dev->priv_destructor = virt_wifi_net_device_destructor; + dev->needs_free_netdev = true; } /* Called in a RCU read critical section from netif_receive_skb */ @@ -544,6 +543,7 @@ static int virt_wifi_newlink(struct net *src_net, struct net_device *dev, goto unregister_netdev; } + dev->priv_destructor = virt_wifi_net_device_destructor; priv->being_deleted = false; priv->is_connected = false; priv->is_up = false; diff --git a/drivers/nfc/nxp-nci/i2c.c b/drivers/nfc/nxp-nci/i2c.c index 4d1909aecd6c..9f60e4dc5a90 100644 --- a/drivers/nfc/nxp-nci/i2c.c +++ b/drivers/nfc/nxp-nci/i2c.c @@ -278,7 +278,7 @@ static int nxp_nci_i2c_probe(struct i2c_client *client, r = devm_acpi_dev_add_driver_gpios(dev, acpi_nxp_nci_gpios); if (r) - return r; + dev_dbg(dev, "Unable to add GPIO mapping table\n"); phy->gpiod_en = devm_gpiod_get(dev, "enable", GPIOD_OUT_LOW); if (IS_ERR(phy->gpiod_en)) { diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c index 3e9f45aec8d1..5129543a0473 100644 --- a/drivers/nvdimm/btt.c +++ b/drivers/nvdimm/btt.c @@ -1261,11 +1261,11 @@ static int btt_read_pg(struct btt *btt, struct bio_integrity_payload *bip, ret = btt_data_read(arena, page, off, postmap, cur_len); if (ret) { - int rc; - /* Media error - set the e_flag */ - rc = btt_map_write(arena, premap, postmap, 0, 1, - NVDIMM_IO_ATOMIC); + if (btt_map_write(arena, premap, postmap, 0, 1, NVDIMM_IO_ATOMIC)) + dev_warn_ratelimited(to_dev(arena), + "Error persistently tracking bad blocks at %#x\n", + premap); goto out_rtt; } diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index fa7ba09dca77..a6b7b242d516 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -313,7 +313,7 @@ bool nvme_cancel_request(struct request *req, void *data, bool reserved) if (blk_mq_request_completed(req)) return true; - nvme_req(req)->status = NVME_SC_HOST_PATH_ERROR; + nvme_req(req)->status = NVME_SC_HOST_ABORTED_CMD; blk_mq_complete_request(req); return true; } @@ -611,8 +611,14 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req, struct nvme_dsm_range *range; struct bio *bio; - range = kmalloc_array(segments, sizeof(*range), - GFP_ATOMIC | __GFP_NOWARN); + /* + * Some devices do not consider the DSM 'Number of Ranges' field when + * determining how much data to DMA. Always allocate memory for maximum + * number of segments to prevent device reading beyond end of buffer. + */ + static const size_t alloc_size = sizeof(*range) * NVME_DSM_MAX_RANGES; + + range = kzalloc(alloc_size, GFP_ATOMIC | __GFP_NOWARN); if (!range) { /* * If we fail allocation our range, fallback to the controller @@ -652,7 +658,7 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req, req->special_vec.bv_page = virt_to_page(range); req->special_vec.bv_offset = offset_in_page(range); - req->special_vec.bv_len = sizeof(*range) * segments; + req->special_vec.bv_len = alloc_size; req->rq_flags |= RQF_SPECIAL_PAYLOAD; return BLK_STS_OK; @@ -1727,6 +1733,8 @@ static int nvme_report_ns_ids(struct nvme_ctrl *ctrl, unsigned int nsid, if (ret) dev_warn(ctrl->device, "Identify Descriptors failed (%d)\n", ret); + if (ret > 0) + ret = 0; } return ret; } @@ -2404,16 +2412,6 @@ static const struct nvme_core_quirk_entry core_quirks[] = { .vid = 0x14a4, .fr = "22301111", .quirks = NVME_QUIRK_SIMPLE_SUSPEND, - }, - { - /* - * This Kingston E8FK11.T firmware version has no interrupt - * after resume with actions related to suspend to idle - * https://bugzilla.kernel.org/show_bug.cgi?id=204887 - */ - .vid = 0x2646, - .fr = "E8FK11.T", - .quirks = NVME_QUIRK_SIMPLE_SUSPEND, } }; diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 265f89e11d8b..59474bd0c728 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -342,7 +342,8 @@ nvme_fc_register_localport(struct nvme_fc_port_info *pinfo, !template->ls_req || !template->fcp_io || !template->ls_abort || !template->fcp_abort || !template->max_hw_queues || !template->max_sgl_segments || - !template->max_dif_sgl_segments || !template->dma_boundary) { + !template->max_dif_sgl_segments || !template->dma_boundary || + !template->module) { ret = -EINVAL; goto out_reghost_failed; } @@ -2015,6 +2016,7 @@ nvme_fc_ctrl_free(struct kref *ref) { struct nvme_fc_ctrl *ctrl = container_of(ref, struct nvme_fc_ctrl, ref); + struct nvme_fc_lport *lport = ctrl->lport; unsigned long flags; if (ctrl->ctrl.tagset) { @@ -2041,6 +2043,7 @@ nvme_fc_ctrl_free(struct kref *ref) if (ctrl->ctrl.opts) nvmf_free_options(ctrl->ctrl.opts); kfree(ctrl); + module_put(lport->ops->module); } static void @@ -2907,10 +2910,22 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status) static void __nvme_fc_terminate_io(struct nvme_fc_ctrl *ctrl) { - nvme_stop_keep_alive(&ctrl->ctrl); + /* + * if state is connecting - the error occurred as part of a + * reconnect attempt. The create_association error paths will + * clean up any outstanding io. + * + * if it's a different state - ensure all pending io is + * terminated. Given this can delay while waiting for the + * aborted io to return, we recheck adapter state below + * before changing state. + */ + if (ctrl->ctrl.state != NVME_CTRL_CONNECTING) { + nvme_stop_keep_alive(&ctrl->ctrl); - /* will block will waiting for io to terminate */ - nvme_fc_delete_association(ctrl); + /* will block will waiting for io to terminate */ + nvme_fc_delete_association(ctrl); + } if (ctrl->ctrl.state != NVME_CTRL_CONNECTING && !nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) @@ -3056,10 +3071,15 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, goto out_fail; } + if (!try_module_get(lport->ops->module)) { + ret = -EUNATCH; + goto out_free_ctrl; + } + idx = ida_simple_get(&nvme_fc_ctrl_cnt, 0, 0, GFP_KERNEL); if (idx < 0) { ret = -ENOSPC; - goto out_free_ctrl; + goto out_mod_put; } ctrl->ctrl.opts = opts; @@ -3212,6 +3232,8 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, out_free_ida: put_device(ctrl->dev); ida_simple_remove(&nvme_fc_ctrl_cnt, ctrl->cnum); +out_mod_put: + module_put(lport->ops->module); out_free_ctrl: kfree(ctrl); out_fail: diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index e0f064dcbd02..132ade51ee87 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -95,6 +95,7 @@ void nvme_failover_req(struct request *req) } break; case NVME_SC_HOST_PATH_ERROR: + case NVME_SC_HOST_ABORTED_CMD: /* * Temporary transport disruption in talking to the controller. * Try to send on a new path. diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 869f462e6b6e..14d513087a14 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -68,14 +68,14 @@ static int io_queue_depth = 1024; module_param_cb(io_queue_depth, &io_queue_depth_ops, &io_queue_depth, 0644); MODULE_PARM_DESC(io_queue_depth, "set io queue depth, should >= 2"); -static int write_queues; -module_param(write_queues, int, 0644); +static unsigned int write_queues; +module_param(write_queues, uint, 0644); MODULE_PARM_DESC(write_queues, "Number of queues to use for writes. If not set, reads and writes " "will share a queue set."); -static int poll_queues; -module_param(poll_queues, int, 0644); +static unsigned int poll_queues; +module_param(poll_queues, uint, 0644); MODULE_PARM_DESC(poll_queues, "Number of queues to use for polled IO."); struct nvme_dev; @@ -2060,7 +2060,6 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues) .priv = dev, }; unsigned int irq_queues, this_p_queues; - unsigned int nr_cpus = num_possible_cpus(); /* * Poll queues don't need interrupts, but we need at least one IO @@ -2071,10 +2070,7 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues) this_p_queues = nr_io_queues - 1; irq_queues = 1; } else { - if (nr_cpus < nr_io_queues - this_p_queues) - irq_queues = nr_cpus + 1; - else - irq_queues = nr_io_queues - this_p_queues + 1; + irq_queues = nr_io_queues - this_p_queues + 1; } dev->io_queues[HCTX_TYPE_POLL] = this_p_queues; diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index b50b53db3746..1c50af6219f3 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -850,6 +850,7 @@ fcloop_targetport_delete(struct nvmet_fc_target_port *targetport) #define FCLOOP_DMABOUND_4G 0xFFFFFFFF static struct nvme_fc_port_template fctemplate = { + .module = THIS_MODULE, .localport_delete = fcloop_localport_delete, .remoteport_delete = fcloop_remoteport_delete, .create_queue = fcloop_create_queue, diff --git a/drivers/nvmem/imx-ocotp.c b/drivers/nvmem/imx-ocotp.c index dff2f3c357f5..fc40555ca4cd 100644 --- a/drivers/nvmem/imx-ocotp.c +++ b/drivers/nvmem/imx-ocotp.c @@ -521,6 +521,10 @@ static int imx_ocotp_probe(struct platform_device *pdev) if (IS_ERR(priv->clk)) return PTR_ERR(priv->clk); + clk_prepare_enable(priv->clk); + imx_ocotp_clr_err_if_set(priv->base); + clk_disable_unprepare(priv->clk); + priv->params = of_device_get_match_data(&pdev->dev); imx_ocotp_nvmem_config.size = 4 * priv->params->nregs; imx_ocotp_nvmem_config.dev = dev; diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c index c423e94baf0f..9617b7df7c4d 100644 --- a/drivers/of/overlay.c +++ b/drivers/of/overlay.c @@ -305,7 +305,6 @@ static int add_changeset_property(struct overlay_changeset *ovcs, { struct property *new_prop = NULL, *prop; int ret = 0; - bool check_for_non_overlay_node = false; if (target->in_livetree) if (!of_prop_cmp(overlay_prop->name, "name") || @@ -318,6 +317,25 @@ static int add_changeset_property(struct overlay_changeset *ovcs, else prop = NULL; + if (prop) { + if (!of_prop_cmp(prop->name, "#address-cells")) { + if (!of_prop_val_eq(prop, overlay_prop)) { + pr_err("ERROR: changing value of #address-cells is not allowed in %pOF\n", + target->np); + ret = -EINVAL; + } + return ret; + + } else if (!of_prop_cmp(prop->name, "#size-cells")) { + if (!of_prop_val_eq(prop, overlay_prop)) { + pr_err("ERROR: changing value of #size-cells is not allowed in %pOF\n", + target->np); + ret = -EINVAL; + } + return ret; + } + } + if (is_symbols_prop) { if (prop) return -EINVAL; @@ -330,33 +348,18 @@ static int add_changeset_property(struct overlay_changeset *ovcs, return -ENOMEM; if (!prop) { - check_for_non_overlay_node = true; if (!target->in_livetree) { new_prop->next = target->np->deadprops; target->np->deadprops = new_prop; } ret = of_changeset_add_property(&ovcs->cset, target->np, new_prop); - } else if (!of_prop_cmp(prop->name, "#address-cells")) { - if (!of_prop_val_eq(prop, new_prop)) { - pr_err("ERROR: changing value of #address-cells is not allowed in %pOF\n", - target->np); - ret = -EINVAL; - } - } else if (!of_prop_cmp(prop->name, "#size-cells")) { - if (!of_prop_val_eq(prop, new_prop)) { - pr_err("ERROR: changing value of #size-cells is not allowed in %pOF\n", - target->np); - ret = -EINVAL; - } } else { - check_for_non_overlay_node = true; ret = of_changeset_update_property(&ovcs->cset, target->np, new_prop); } - if (check_for_non_overlay_node && - !of_node_check_flag(target->np, OF_OVERLAY)) + if (!of_node_check_flag(target->np, OF_OVERLAY)) pr_err("WARNING: memory leak will occur if overlay removed, property: %pOF/%s\n", target->np, new_prop->name); diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index 92e895d86458..ca7823eef2b4 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -1146,8 +1146,10 @@ static void attach_node_and_children(struct device_node *np) full_name = kasprintf(GFP_KERNEL, "%pOF", np); if (!strcmp(full_name, "/__local_fixups__") || - !strcmp(full_name, "/__fixups__")) + !strcmp(full_name, "/__fixups__")) { + kfree(full_name); return; + } dup = of_find_node_by_path(full_name); kfree(full_name); diff --git a/drivers/parport/share.c b/drivers/parport/share.c index 7b4ee33c1935..15c81cffd2de 100644 --- a/drivers/parport/share.c +++ b/drivers/parport/share.c @@ -230,6 +230,18 @@ static int port_check(struct device *dev, void *dev_drv) return 0; } +/* + * Iterates through all the devices connected to the bus and return 1 + * if the device is a parallel port. + */ + +static int port_detect(struct device *dev, void *dev_drv) +{ + if (is_parport(dev)) + return 1; + return 0; +} + /** * parport_register_driver - register a parallel port device driver * @drv: structure describing the driver @@ -282,6 +294,15 @@ int __parport_register_driver(struct parport_driver *drv, struct module *owner, if (ret) return ret; + /* + * check if bus has any parallel port registered, if + * none is found then load the lowlevel driver. + */ + ret = bus_for_each_dev(&parport_bus_type, NULL, NULL, + port_detect); + if (!ret) + get_lowlevel_driver(); + mutex_lock(®istration_lock); if (drv->match_port) bus_for_each_dev(&parport_bus_type, NULL, drv, diff --git a/drivers/pci/controller/dwc/pci-meson.c b/drivers/pci/controller/dwc/pci-meson.c index e35e9eaa50ee..b927a92e3463 100644 --- a/drivers/pci/controller/dwc/pci-meson.c +++ b/drivers/pci/controller/dwc/pci-meson.c @@ -250,15 +250,15 @@ static int meson_pcie_probe_clocks(struct meson_pcie *mp) if (IS_ERR(res->port_clk)) return PTR_ERR(res->port_clk); - res->mipi_gate = meson_pcie_probe_clock(dev, "pcie_mipi_en", 0); + res->mipi_gate = meson_pcie_probe_clock(dev, "mipi", 0); if (IS_ERR(res->mipi_gate)) return PTR_ERR(res->mipi_gate); - res->general_clk = meson_pcie_probe_clock(dev, "pcie_general", 0); + res->general_clk = meson_pcie_probe_clock(dev, "general", 0); if (IS_ERR(res->general_clk)) return PTR_ERR(res->general_clk); - res->clk = meson_pcie_probe_clock(dev, "pcie", 0); + res->clk = meson_pcie_probe_clock(dev, "pclk", 0); if (IS_ERR(res->clk)) return PTR_ERR(res->clk); diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c index 0f36a926059a..8615f1548882 100644 --- a/drivers/pci/controller/dwc/pcie-designware-host.c +++ b/drivers/pci/controller/dwc/pcie-designware-host.c @@ -78,7 +78,8 @@ static struct msi_domain_info dw_pcie_msi_domain_info = { irqreturn_t dw_handle_msi_irq(struct pcie_port *pp) { int i, pos, irq; - u32 val, num_ctrls; + unsigned long val; + u32 status, num_ctrls; irqreturn_t ret = IRQ_NONE; num_ctrls = pp->num_vectors / MAX_MSI_IRQS_PER_CTRL; @@ -86,14 +87,14 @@ irqreturn_t dw_handle_msi_irq(struct pcie_port *pp) for (i = 0; i < num_ctrls; i++) { dw_pcie_rd_own_conf(pp, PCIE_MSI_INTR0_STATUS + (i * MSI_REG_CTRL_BLOCK_SIZE), - 4, &val); - if (!val) + 4, &status); + if (!status) continue; ret = IRQ_HANDLED; + val = status; pos = 0; - while ((pos = find_next_bit((unsigned long *) &val, - MAX_MSI_IRQS_PER_CTRL, + while ((pos = find_next_bit(&val, MAX_MSI_IRQS_PER_CTRL, pos)) != MAX_MSI_IRQS_PER_CTRL) { irq = irq_find_mapping(pp->irq_domain, (i * MAX_MSI_IRQS_PER_CTRL) + diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index fc0fe4d4de49..97245e076548 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -180,6 +180,8 @@ #define LINK_WAIT_MAX_RETRIES 10 #define LINK_WAIT_USLEEP_MIN 90000 #define LINK_WAIT_USLEEP_MAX 100000 +#define RETRAIN_WAIT_MAX_RETRIES 10 +#define RETRAIN_WAIT_USLEEP_US 2000 #define MSI_IRQ_NUM 32 @@ -239,6 +241,17 @@ static int advk_pcie_wait_for_link(struct advk_pcie *pcie) return -ETIMEDOUT; } +static void advk_pcie_wait_for_retrain(struct advk_pcie *pcie) +{ + size_t retries; + + for (retries = 0; retries < RETRAIN_WAIT_MAX_RETRIES; ++retries) { + if (!advk_pcie_link_up(pcie)) + break; + udelay(RETRAIN_WAIT_USLEEP_US); + } +} + static void advk_pcie_setup_hw(struct advk_pcie *pcie) { u32 reg; @@ -415,7 +428,7 @@ advk_pci_bridge_emul_pcie_conf_read(struct pci_bridge_emul *bridge, case PCI_EXP_RTCTL: { u32 val = advk_readl(pcie, PCIE_ISR0_MASK_REG); - *value = (val & PCIE_MSG_PM_PME_MASK) ? PCI_EXP_RTCTL_PMEIE : 0; + *value = (val & PCIE_MSG_PM_PME_MASK) ? 0 : PCI_EXP_RTCTL_PMEIE; return PCI_BRIDGE_EMUL_HANDLED; } @@ -426,11 +439,20 @@ advk_pci_bridge_emul_pcie_conf_read(struct pci_bridge_emul *bridge, return PCI_BRIDGE_EMUL_HANDLED; } + case PCI_EXP_LNKCTL: { + /* u32 contains both PCI_EXP_LNKCTL and PCI_EXP_LNKSTA */ + u32 val = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + reg) & + ~(PCI_EXP_LNKSTA_LT << 16); + if (!advk_pcie_link_up(pcie)) + val |= (PCI_EXP_LNKSTA_LT << 16); + *value = val; + return PCI_BRIDGE_EMUL_HANDLED; + } + case PCI_CAP_LIST_ID: case PCI_EXP_DEVCAP: case PCI_EXP_DEVCTL: case PCI_EXP_LNKCAP: - case PCI_EXP_LNKCTL: *value = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + reg); return PCI_BRIDGE_EMUL_HANDLED; default: @@ -447,14 +469,24 @@ advk_pci_bridge_emul_pcie_conf_write(struct pci_bridge_emul *bridge, switch (reg) { case PCI_EXP_DEVCTL: + advk_writel(pcie, new, PCIE_CORE_PCIEXP_CAP + reg); + break; + case PCI_EXP_LNKCTL: advk_writel(pcie, new, PCIE_CORE_PCIEXP_CAP + reg); + if (new & PCI_EXP_LNKCTL_RL) + advk_pcie_wait_for_retrain(pcie); break; - case PCI_EXP_RTCTL: - new = (new & PCI_EXP_RTCTL_PMEIE) << 3; - advk_writel(pcie, new, PCIE_ISR0_MASK_REG); + case PCI_EXP_RTCTL: { + /* Only mask/unmask PME interrupt */ + u32 val = advk_readl(pcie, PCIE_ISR0_MASK_REG) & + ~PCIE_MSG_PM_PME_MASK; + if ((new & PCI_EXP_RTCTL_PMEIE) == 0) + val |= PCIE_MSG_PM_PME_MASK; + advk_writel(pcie, val, PCIE_ISR0_MASK_REG); break; + } case PCI_EXP_RTSTA: new = (new & PCI_EXP_RTSTA_PME) >> 9; diff --git a/drivers/pci/controller/pcie-rcar.c b/drivers/pci/controller/pcie-rcar.c index f6a669a9af41..1ad0b56f11b4 100644 --- a/drivers/pci/controller/pcie-rcar.c +++ b/drivers/pci/controller/pcie-rcar.c @@ -93,8 +93,11 @@ #define LINK_SPEED_2_5GTS (1 << 16) #define LINK_SPEED_5_0GTS (2 << 16) #define MACCTLR 0x011058 +#define MACCTLR_NFTS_MASK GENMASK(23, 16) /* The name is from SH7786 */ #define SPEED_CHANGE BIT(24) #define SCRAMBLE_DISABLE BIT(27) +#define LTSMDIS BIT(31) +#define MACCTLR_INIT_VAL (LTSMDIS | MACCTLR_NFTS_MASK) #define PMSR 0x01105c #define MACS2R 0x011078 #define MACCGSPSETR 0x011084 @@ -615,6 +618,8 @@ static int rcar_pcie_hw_init(struct rcar_pcie *pcie) if (IS_ENABLED(CONFIG_PCI_MSI)) rcar_pci_write_reg(pcie, 0x801f0000, PCIEMSITXR); + rcar_pci_write_reg(pcie, MACCTLR_INIT_VAL, MACCTLR); + /* Finish initialization - establish a PCI Express link */ rcar_pci_write_reg(pcie, CFINIT, PCIETCTLR); @@ -1237,6 +1242,7 @@ static int rcar_pcie_resume_noirq(struct device *dev) return 0; /* Re-establish the PCIe link */ + rcar_pci_write_reg(pcie, MACCTLR_INIT_VAL, MACCTLR); rcar_pci_write_reg(pcie, CFINIT, PCIETCTLR); return rcar_pcie_wait_for_dl(pcie); } diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index e4c46637f32f..b3869951c0eb 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -449,8 +449,15 @@ static void acpiphp_native_scan_bridge(struct pci_dev *bridge) /* Scan non-hotplug bridges that need to be reconfigured */ for_each_pci_bridge(dev, bus) { - if (!hotplug_is_native(dev)) - max = pci_scan_bridge(bus, dev, max, 1); + if (hotplug_is_native(dev)) + continue; + + max = pci_scan_bridge(bus, dev, max, 1); + if (dev->subordinate) { + pcibios_resource_survey_bus(dev->subordinate); + pci_bus_size_bridges(dev->subordinate); + pci_bus_assign_resources(dev->subordinate); + } } } @@ -480,7 +487,6 @@ static void enable_slot(struct acpiphp_slot *slot, bool bridge) if (PCI_SLOT(dev->devfn) == slot->device) acpiphp_native_scan_bridge(dev); } - pci_assign_unassigned_bridge_resources(bus->self); } else { LIST_HEAD(add_list); int max, pass; diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h index 654c972b8ea0..aa61d4c219d7 100644 --- a/drivers/pci/hotplug/pciehp.h +++ b/drivers/pci/hotplug/pciehp.h @@ -72,6 +72,7 @@ extern int pciehp_poll_time; * @reset_lock: prevents access to the Data Link Layer Link Active bit in the * Link Status register and to the Presence Detect State bit in the Slot * Status register during a slot reset which may cause them to flap + * @ist_running: flag to keep user request waiting while IRQ thread is running * @request_result: result of last user request submitted to the IRQ thread * @requester: wait queue to wake up on completion of user request, * used for synchronous slot enable/disable request via sysfs @@ -101,6 +102,7 @@ struct controller { struct hotplug_slot hotplug_slot; /* hotplug core interface */ struct rw_semaphore reset_lock; + unsigned int ist_running; int request_result; wait_queue_head_t requester; }; @@ -172,10 +174,10 @@ void pciehp_set_indicators(struct controller *ctrl, int pwr, int attn); void pciehp_get_latch_status(struct controller *ctrl, u8 *status); int pciehp_query_power_fault(struct controller *ctrl); -bool pciehp_card_present(struct controller *ctrl); -bool pciehp_card_present_or_link_active(struct controller *ctrl); +int pciehp_card_present(struct controller *ctrl); +int pciehp_card_present_or_link_active(struct controller *ctrl); int pciehp_check_link_status(struct controller *ctrl); -bool pciehp_check_link_active(struct controller *ctrl); +int pciehp_check_link_active(struct controller *ctrl); void pciehp_release_ctrl(struct controller *ctrl); int pciehp_sysfs_enable_slot(struct hotplug_slot *hotplug_slot); diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c index b3122c151b80..312cc45c44c7 100644 --- a/drivers/pci/hotplug/pciehp_core.c +++ b/drivers/pci/hotplug/pciehp_core.c @@ -139,10 +139,15 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value) { struct controller *ctrl = to_ctrl(hotplug_slot); struct pci_dev *pdev = ctrl->pcie->port; + int ret; pci_config_pm_runtime_get(pdev); - *value = pciehp_card_present_or_link_active(ctrl); + ret = pciehp_card_present_or_link_active(ctrl); pci_config_pm_runtime_put(pdev); + if (ret < 0) + return ret; + + *value = ret; return 0; } @@ -158,13 +163,13 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value) */ static void pciehp_check_presence(struct controller *ctrl) { - bool occupied; + int occupied; down_read(&ctrl->reset_lock); mutex_lock(&ctrl->state_lock); occupied = pciehp_card_present_or_link_active(ctrl); - if ((occupied && (ctrl->state == OFF_STATE || + if ((occupied > 0 && (ctrl->state == OFF_STATE || ctrl->state == BLINKINGON_STATE)) || (!occupied && (ctrl->state == ON_STATE || ctrl->state == BLINKINGOFF_STATE))) @@ -253,7 +258,7 @@ static bool pme_is_native(struct pcie_device *dev) return pcie_ports_native || host->native_pme; } -static int pciehp_suspend(struct pcie_device *dev) +static void pciehp_disable_interrupt(struct pcie_device *dev) { /* * Disable hotplug interrupt so that it does not trigger @@ -261,7 +266,19 @@ static int pciehp_suspend(struct pcie_device *dev) */ if (pme_is_native(dev)) pcie_disable_interrupt(get_service_data(dev)); +} + +#ifdef CONFIG_PM_SLEEP +static int pciehp_suspend(struct pcie_device *dev) +{ + /* + * If the port is already runtime suspended we can keep it that + * way. + */ + if (dev_pm_smart_suspend_and_suspended(&dev->port->dev)) + return 0; + pciehp_disable_interrupt(dev); return 0; } @@ -279,6 +296,7 @@ static int pciehp_resume_noirq(struct pcie_device *dev) return 0; } +#endif static int pciehp_resume(struct pcie_device *dev) { @@ -292,6 +310,12 @@ static int pciehp_resume(struct pcie_device *dev) return 0; } +static int pciehp_runtime_suspend(struct pcie_device *dev) +{ + pciehp_disable_interrupt(dev); + return 0; +} + static int pciehp_runtime_resume(struct pcie_device *dev) { struct controller *ctrl = get_service_data(dev); @@ -318,10 +342,12 @@ static struct pcie_port_service_driver hpdriver_portdrv = { .remove = pciehp_remove, #ifdef CONFIG_PM +#ifdef CONFIG_PM_SLEEP .suspend = pciehp_suspend, .resume_noirq = pciehp_resume_noirq, .resume = pciehp_resume, - .runtime_suspend = pciehp_suspend, +#endif + .runtime_suspend = pciehp_runtime_suspend, .runtime_resume = pciehp_runtime_resume, #endif /* PM */ }; diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c index 21af7b16d7a4..6503d15effbb 100644 --- a/drivers/pci/hotplug/pciehp_ctrl.c +++ b/drivers/pci/hotplug/pciehp_ctrl.c @@ -226,7 +226,7 @@ void pciehp_handle_disable_request(struct controller *ctrl) void pciehp_handle_presence_or_link_change(struct controller *ctrl, u32 events) { - bool present, link_active; + int present, link_active; /* * If the slot is on and presence or link has changed, turn it off. @@ -257,7 +257,7 @@ void pciehp_handle_presence_or_link_change(struct controller *ctrl, u32 events) mutex_lock(&ctrl->state_lock); present = pciehp_card_present(ctrl); link_active = pciehp_check_link_active(ctrl); - if (!present && !link_active) { + if (present <= 0 && link_active <= 0) { mutex_unlock(&ctrl->state_lock); return; } @@ -375,7 +375,8 @@ int pciehp_sysfs_enable_slot(struct hotplug_slot *hotplug_slot) ctrl->request_result = -ENODEV; pciehp_request(ctrl, PCI_EXP_SLTSTA_PDC); wait_event(ctrl->requester, - !atomic_read(&ctrl->pending_events)); + !atomic_read(&ctrl->pending_events) && + !ctrl->ist_running); return ctrl->request_result; case POWERON_STATE: ctrl_info(ctrl, "Slot(%s): Already in powering on state\n", @@ -408,7 +409,8 @@ int pciehp_sysfs_disable_slot(struct hotplug_slot *hotplug_slot) mutex_unlock(&ctrl->state_lock); pciehp_request(ctrl, DISABLE_SLOT); wait_event(ctrl->requester, - !atomic_read(&ctrl->pending_events)); + !atomic_read(&ctrl->pending_events) && + !ctrl->ist_running); return ctrl->request_result; case POWEROFF_STATE: ctrl_info(ctrl, "Slot(%s): Already in powering off state\n", diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c index 1a522c1c4177..a2a263764ef8 100644 --- a/drivers/pci/hotplug/pciehp_hpc.c +++ b/drivers/pci/hotplug/pciehp_hpc.c @@ -201,17 +201,29 @@ static void pcie_write_cmd_nowait(struct controller *ctrl, u16 cmd, u16 mask) pcie_do_write_cmd(ctrl, cmd, mask, false); } -bool pciehp_check_link_active(struct controller *ctrl) +/** + * pciehp_check_link_active() - Is the link active + * @ctrl: PCIe hotplug controller + * + * Check whether the downstream link is currently active. Note it is + * possible that the card is removed immediately after this so the + * caller may need to take it into account. + * + * If the hotplug controller itself is not available anymore returns + * %-ENODEV. + */ +int pciehp_check_link_active(struct controller *ctrl) { struct pci_dev *pdev = ctrl_dev(ctrl); u16 lnk_status; - bool ret; + int ret; - pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnk_status); - ret = !!(lnk_status & PCI_EXP_LNKSTA_DLLLA); + ret = pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnk_status); + if (ret == PCIBIOS_DEVICE_NOT_FOUND || lnk_status == (u16)~0) + return -ENODEV; - if (ret) - ctrl_dbg(ctrl, "%s: lnk_status = %x\n", __func__, lnk_status); + ret = !!(lnk_status & PCI_EXP_LNKSTA_DLLLA); + ctrl_dbg(ctrl, "%s: lnk_status = %x\n", __func__, lnk_status); return ret; } @@ -373,13 +385,29 @@ void pciehp_get_latch_status(struct controller *ctrl, u8 *status) *status = !!(slot_status & PCI_EXP_SLTSTA_MRLSS); } -bool pciehp_card_present(struct controller *ctrl) +/** + * pciehp_card_present() - Is the card present + * @ctrl: PCIe hotplug controller + * + * Function checks whether the card is currently present in the slot and + * in that case returns true. Note it is possible that the card is + * removed immediately after the check so the caller may need to take + * this into account. + * + * It the hotplug controller itself is not available anymore returns + * %-ENODEV. + */ +int pciehp_card_present(struct controller *ctrl) { struct pci_dev *pdev = ctrl_dev(ctrl); u16 slot_status; + int ret; - pcie_capability_read_word(pdev, PCI_EXP_SLTSTA, &slot_status); - return slot_status & PCI_EXP_SLTSTA_PDS; + ret = pcie_capability_read_word(pdev, PCI_EXP_SLTSTA, &slot_status); + if (ret == PCIBIOS_DEVICE_NOT_FOUND || slot_status == (u16)~0) + return -ENODEV; + + return !!(slot_status & PCI_EXP_SLTSTA_PDS); } /** @@ -390,10 +418,19 @@ bool pciehp_card_present(struct controller *ctrl) * Presence Detect State bit, this helper also returns true if the Link Active * bit is set. This is a concession to broken hotplug ports which hardwire * Presence Detect State to zero, such as Wilocity's [1ae9:0200]. + * + * Returns: %1 if the slot is occupied and %0 if it is not. If the hotplug + * port is not present anymore returns %-ENODEV. */ -bool pciehp_card_present_or_link_active(struct controller *ctrl) +int pciehp_card_present_or_link_active(struct controller *ctrl) { - return pciehp_card_present(ctrl) || pciehp_check_link_active(ctrl); + int ret; + + ret = pciehp_card_present(ctrl); + if (ret) + return ret; + + return pciehp_check_link_active(ctrl); } int pciehp_query_power_fault(struct controller *ctrl) @@ -583,6 +620,7 @@ static irqreturn_t pciehp_ist(int irq, void *dev_id) irqreturn_t ret; u32 events; + ctrl->ist_running = true; pci_config_pm_runtime_get(pdev); /* rerun pciehp_isr() if the port was inaccessible on interrupt */ @@ -629,6 +667,7 @@ static irqreturn_t pciehp_ist(int irq, void *dev_id) up_read(&ctrl->reset_lock); pci_config_pm_runtime_put(pdev); + ctrl->ist_running = false; wake_up(&ctrl->requester); return IRQ_HANDLED; } diff --git a/drivers/pci/hotplug/rpaphp_core.c b/drivers/pci/hotplug/rpaphp_core.c index 18627bb21e9e..32eab1776cfe 100644 --- a/drivers/pci/hotplug/rpaphp_core.c +++ b/drivers/pci/hotplug/rpaphp_core.c @@ -154,11 +154,11 @@ static enum pci_bus_speed get_max_bus_speed(struct slot *slot) return speed; } -static int get_children_props(struct device_node *dn, const int **drc_indexes, - const int **drc_names, const int **drc_types, - const int **drc_power_domains) +static int get_children_props(struct device_node *dn, const __be32 **drc_indexes, + const __be32 **drc_names, const __be32 **drc_types, + const __be32 **drc_power_domains) { - const int *indexes, *names, *types, *domains; + const __be32 *indexes, *names, *types, *domains; indexes = of_get_property(dn, "ibm,drc-indexes", NULL); names = of_get_property(dn, "ibm,drc-names", NULL); @@ -194,8 +194,8 @@ static int rpaphp_check_drc_props_v1(struct device_node *dn, char *drc_name, char *drc_type, unsigned int my_index) { char *name_tmp, *type_tmp; - const int *indexes, *names; - const int *types, *domains; + const __be32 *indexes, *names; + const __be32 *types, *domains; int i, rc; rc = get_children_props(dn->parent, &indexes, &names, &types, &domains); @@ -208,7 +208,7 @@ static int rpaphp_check_drc_props_v1(struct device_node *dn, char *drc_name, /* Iterate through parent properties, looking for my-drc-index */ for (i = 0; i < be32_to_cpu(indexes[0]); i++) { - if ((unsigned int) indexes[i + 1] == my_index) + if (be32_to_cpu(indexes[i + 1]) == my_index) break; name_tmp += (strlen(name_tmp) + 1); @@ -239,6 +239,8 @@ static int rpaphp_check_drc_props_v2(struct device_node *dn, char *drc_name, value = of_prop_next_u32(info, NULL, &entries); if (!value) return -EINVAL; + else + value++; for (j = 0; j < entries; j++) { of_read_drc_info_cell(&info, &value, &drc); @@ -246,9 +248,10 @@ static int rpaphp_check_drc_props_v2(struct device_node *dn, char *drc_name, /* Should now know end of current entry */ /* Found it */ - if (my_index <= drc.last_drc_index) { + if (my_index >= drc.drc_index_start && my_index <= drc.last_drc_index) { + int index = my_index - drc.drc_index_start; sprintf(cell_drc_name, "%s%d", drc.drc_name_prefix, - my_index); + drc.drc_name_suffix_start + index); break; } } @@ -265,7 +268,7 @@ static int rpaphp_check_drc_props_v2(struct device_node *dn, char *drc_name, int rpaphp_check_drc_props(struct device_node *dn, char *drc_name, char *drc_type) { - const unsigned int *my_index; + const __be32 *my_index; my_index = of_get_property(dn, "ibm,my-drc-index", NULL); if (!my_index) { @@ -273,12 +276,12 @@ int rpaphp_check_drc_props(struct device_node *dn, char *drc_name, return -EINVAL; } - if (firmware_has_feature(FW_FEATURE_DRC_INFO)) + if (of_find_property(dn->parent, "ibm,drc-info", NULL)) return rpaphp_check_drc_props_v2(dn, drc_name, drc_type, - *my_index); + be32_to_cpu(*my_index)); else return rpaphp_check_drc_props_v1(dn, drc_name, drc_type, - *my_index); + be32_to_cpu(*my_index)); } EXPORT_SYMBOL_GPL(rpaphp_check_drc_props); @@ -309,10 +312,11 @@ static int is_php_type(char *drc_type) * for built-in pci slots (even when the built-in slots are * dlparable.) */ -static int is_php_dn(struct device_node *dn, const int **indexes, - const int **names, const int **types, const int **power_domains) +static int is_php_dn(struct device_node *dn, const __be32 **indexes, + const __be32 **names, const __be32 **types, + const __be32 **power_domains) { - const int *drc_types; + const __be32 *drc_types; int rc; rc = get_children_props(dn, indexes, names, &drc_types, power_domains); @@ -347,7 +351,7 @@ int rpaphp_add_slot(struct device_node *dn) struct slot *slot; int retval = 0; int i; - const int *indexes, *names, *types, *power_domains; + const __be32 *indexes, *names, *types, *power_domains; char *name, *type; if (!dn->name || strcmp(dn->name, "pci")) diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 0884bedcfc7a..771041784e64 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -213,12 +213,13 @@ u32 __pci_msix_desc_mask_irq(struct msi_desc *desc, u32 flag) if (pci_msi_ignore_mask) return 0; + desc_addr = pci_msix_desc_addr(desc); if (!desc_addr) return 0; mask_bits &= ~PCI_MSIX_ENTRY_CTRL_MASKBIT; - if (flag) + if (flag & PCI_MSIX_ENTRY_CTRL_MASKBIT) mask_bits |= PCI_MSIX_ENTRY_CTRL_MASKBIT; writel(mask_bits, desc_addr + PCI_MSIX_ENTRY_VECTOR_CTRL); diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index a8124e47bf6e..0c3086793e4e 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -941,12 +941,11 @@ static int pci_pm_resume_noirq(struct device *dev) pci_pm_default_resume_early(pci_dev); pci_fixup_device(pci_fixup_resume_early, pci_dev); + pcie_pme_root_status_cleanup(pci_dev); if (pci_has_legacy_pm_support(pci_dev)) return pci_legacy_resume_early(dev); - pcie_pme_root_status_cleanup(pci_dev); - if (drv && drv->pm && drv->pm->resume_noirq) error = drv->pm->resume_noirq(dev); @@ -1076,17 +1075,22 @@ static int pci_pm_thaw_noirq(struct device *dev) return error; } - if (pci_has_legacy_pm_support(pci_dev)) - return pci_legacy_resume_early(dev); - /* - * pci_restore_state() requires the device to be in D0 (because of MSI - * restoration among other things), so force it into D0 in case the - * driver's "freeze" callbacks put it into a low-power state directly. + * Both the legacy ->resume_early() and the new pm->thaw_noirq() + * callbacks assume the device has been returned to D0 and its + * config state has been restored. + * + * In addition, pci_restore_state() restores MSI-X state in MMIO + * space, which requires the device to be in D0, so return it to D0 + * in case the driver's "freeze" callbacks put it into a low-power + * state. */ pci_set_power_state(pci_dev, PCI_D0); pci_restore_state(pci_dev); + if (pci_has_legacy_pm_support(pci_dev)) + return pci_legacy_resume_early(dev); + if (drv && drv->pm && drv->pm->thaw_noirq) error = drv->pm->thaw_noirq(dev); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index a97e2571a527..fcfaadc774ee 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -5854,6 +5854,24 @@ int pci_set_vga_state(struct pci_dev *dev, bool decode, return 0; } +#ifdef CONFIG_ACPI +bool pci_pr3_present(struct pci_dev *pdev) +{ + struct acpi_device *adev; + + if (acpi_disabled) + return false; + + adev = ACPI_COMPANION(&pdev->dev); + if (!adev) + return false; + + return adev->power.flags.power_resources && + acpi_has_method(adev->handle, "_PR3"); +} +EXPORT_SYMBOL_GPL(pci_pr3_present); +#endif + /** * pci_add_dma_alias - Add a DMA devfn alias for a device * @dev: the PCI device for which alias is added diff --git a/drivers/pci/pcie/ptm.c b/drivers/pci/pcie/ptm.c index 98cfa30f3fae..9361f3aa26ab 100644 --- a/drivers/pci/pcie/ptm.c +++ b/drivers/pci/pcie/ptm.c @@ -21,7 +21,7 @@ static void pci_ptm_info(struct pci_dev *dev) snprintf(clock_desc, sizeof(clock_desc), ">254ns"); break; default: - snprintf(clock_desc, sizeof(clock_desc), "%udns", + snprintf(clock_desc, sizeof(clock_desc), "%uns", dev->ptm_granularity); break; } diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 3d5271a7a849..d3033873395d 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -572,6 +572,7 @@ static void devm_pci_release_host_bridge_dev(struct device *dev) bridge->release_fn(bridge); pci_free_resource_list(&bridge->windows); + pci_free_resource_list(&bridge->dma_ranges); } static void pci_release_host_bridge_dev(struct device *dev) @@ -1089,14 +1090,15 @@ static unsigned int pci_scan_child_bus_extend(struct pci_bus *bus, * @sec: updated with secondary bus number from EA * @sub: updated with subordinate bus number from EA * - * If @dev is a bridge with EA capability, update @sec and @sub with - * fixed bus numbers from the capability and return true. Otherwise, - * return false. + * If @dev is a bridge with EA capability that specifies valid secondary + * and subordinate bus numbers, return true with the bus numbers in @sec + * and @sub. Otherwise return false. */ static bool pci_ea_fixed_busnrs(struct pci_dev *dev, u8 *sec, u8 *sub) { int ea, offset; u32 dw; + u8 ea_sec, ea_sub; if (dev->hdr_type != PCI_HEADER_TYPE_BRIDGE) return false; @@ -1108,8 +1110,13 @@ static bool pci_ea_fixed_busnrs(struct pci_dev *dev, u8 *sec, u8 *sub) offset = ea + PCI_EA_FIRST_ENT; pci_read_config_dword(dev, offset, &dw); - *sec = dw & PCI_EA_SEC_BUS_MASK; - *sub = (dw & PCI_EA_SUB_BUS_MASK) >> PCI_EA_SUB_BUS_SHIFT; + ea_sec = dw & PCI_EA_SEC_BUS_MASK; + ea_sub = (dw & PCI_EA_SUB_BUS_MASK) >> PCI_EA_SUB_BUS_SHIFT; + if (ea_sec == 0 || ea_sub < ea_sec) + return false; + + *sec = ea_sec; + *sub = ea_sub; return true; } diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 320255e5e8f8..308f744393eb 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -4313,15 +4313,21 @@ static int pci_quirk_amd_sb_acs(struct pci_dev *dev, u16 acs_flags) static bool pci_quirk_cavium_acs_match(struct pci_dev *dev) { + if (!pci_is_pcie(dev) || pci_pcie_type(dev) != PCI_EXP_TYPE_ROOT_PORT) + return false; + + switch (dev->device) { /* - * Effectively selects all downstream ports for whole ThunderX 1 - * family by 0xf800 mask (which represents 8 SoCs), while the lower - * bits of device ID are used to indicate which subdevice is used - * within the SoC. + * Effectively selects all downstream ports for whole ThunderX1 + * (which represents 8 SoCs). */ - return (pci_is_pcie(dev) && - (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) && - ((dev->device & 0xf800) == 0xa000)); + case 0xa000 ... 0xa7ff: /* ThunderX1 */ + case 0xaf84: /* ThunderX2 */ + case 0xb884: /* ThunderX3 */ + return true; + default: + return false; + } } static int pci_quirk_cavium_acs(struct pci_dev *dev, u16 acs_flags) @@ -4706,7 +4712,7 @@ int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags) #define INTEL_BSPR_REG_BPPD (1 << 9) /* Upstream Peer Decode Configuration Register */ -#define INTEL_UPDCR_REG 0x1114 +#define INTEL_UPDCR_REG 0x1014 /* 5:0 Peer Decode Enable bits */ #define INTEL_UPDCR_REG_MASK 0x3f diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c index 8c94cd3fd1f2..465d6afd826e 100644 --- a/drivers/pci/switch/switchtec.c +++ b/drivers/pci/switch/switchtec.c @@ -675,7 +675,7 @@ static int ioctl_event_summary(struct switchtec_dev *stdev, return -ENOMEM; s->global = ioread32(&stdev->mmio_sw_event->global_summary); - s->part_bitmap = ioread32(&stdev->mmio_sw_event->part_event_bitmap); + s->part_bitmap = ioread64(&stdev->mmio_sw_event->part_event_bitmap); s->local_part = ioread32(&stdev->mmio_part_cfg->part_event_summary); for (i = 0; i < stdev->partition_count; i++) { diff --git a/drivers/perf/arm_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c index abcf54f7d19c..191f410cf35c 100644 --- a/drivers/perf/arm_smmuv3_pmu.c +++ b/drivers/perf/arm_smmuv3_pmu.c @@ -815,7 +815,7 @@ static int smmu_pmu_probe(struct platform_device *pdev) if (err) { dev_err(dev, "Error %d registering hotplug, PMU @%pa\n", err, &res_0->start); - goto out_cpuhp_err; + return err; } err = perf_pmu_register(&smmu_pmu->pmu, name, -1); @@ -834,8 +834,6 @@ static int smmu_pmu_probe(struct platform_device *pdev) out_unregister: cpuhp_state_remove_instance_nocalls(cpuhp_state_num, &smmu_pmu->node); -out_cpuhp_err: - put_cpu(); return err; } diff --git a/drivers/phy/motorola/phy-cpcap-usb.c b/drivers/phy/motorola/phy-cpcap-usb.c index ead06c6c2601..9a38741d3546 100644 --- a/drivers/phy/motorola/phy-cpcap-usb.c +++ b/drivers/phy/motorola/phy-cpcap-usb.c @@ -207,6 +207,19 @@ static int cpcap_phy_get_ints_state(struct cpcap_phy_ddata *ddata, static int cpcap_usb_set_uart_mode(struct cpcap_phy_ddata *ddata); static int cpcap_usb_set_usb_mode(struct cpcap_phy_ddata *ddata); +static void cpcap_usb_try_musb_mailbox(struct cpcap_phy_ddata *ddata, + enum musb_vbus_id_status status) +{ + int error; + + error = musb_mailbox(status); + if (!error) + return; + + dev_dbg(ddata->dev, "%s: musb_mailbox failed: %i\n", + __func__, error); +} + static void cpcap_usb_detect(struct work_struct *work) { struct cpcap_phy_ddata *ddata; @@ -226,9 +239,7 @@ static void cpcap_usb_detect(struct work_struct *work) if (error) goto out_err; - error = musb_mailbox(MUSB_ID_GROUND); - if (error) - goto out_err; + cpcap_usb_try_musb_mailbox(ddata, MUSB_ID_GROUND); error = regmap_update_bits(ddata->reg, CPCAP_REG_USBC3, CPCAP_BIT_VBUSSTBY_EN | @@ -257,9 +268,7 @@ static void cpcap_usb_detect(struct work_struct *work) error = cpcap_usb_set_usb_mode(ddata); if (error) goto out_err; - error = musb_mailbox(MUSB_ID_GROUND); - if (error) - goto out_err; + cpcap_usb_try_musb_mailbox(ddata, MUSB_ID_GROUND); return; } @@ -269,22 +278,18 @@ static void cpcap_usb_detect(struct work_struct *work) error = cpcap_usb_set_usb_mode(ddata); if (error) goto out_err; - error = musb_mailbox(MUSB_VBUS_VALID); - if (error) - goto out_err; + cpcap_usb_try_musb_mailbox(ddata, MUSB_VBUS_VALID); return; } + cpcap_usb_try_musb_mailbox(ddata, MUSB_VBUS_OFF); + /* Default to debug UART mode */ error = cpcap_usb_set_uart_mode(ddata); if (error) goto out_err; - error = musb_mailbox(MUSB_VBUS_OFF); - if (error) - goto out_err; - dev_dbg(ddata->dev, "set UART mode\n"); return; @@ -649,9 +654,7 @@ static int cpcap_usb_phy_remove(struct platform_device *pdev) if (error) dev_err(ddata->dev, "could not set UART mode\n"); - error = musb_mailbox(MUSB_VBUS_OFF); - if (error) - dev_err(ddata->dev, "could not set mailbox\n"); + cpcap_usb_try_musb_mailbox(ddata, MUSB_VBUS_OFF); usb_remove_phy(&ddata->phy); cancel_delayed_work_sync(&ddata->detect_work); diff --git a/drivers/phy/motorola/phy-mapphone-mdm6600.c b/drivers/phy/motorola/phy-mapphone-mdm6600.c index ee184d5607bd..f20524f0c21d 100644 --- a/drivers/phy/motorola/phy-mapphone-mdm6600.c +++ b/drivers/phy/motorola/phy-mapphone-mdm6600.c @@ -200,7 +200,7 @@ static void phy_mdm6600_status(struct work_struct *work) struct phy_mdm6600 *ddata; struct device *dev; DECLARE_BITMAP(values, PHY_MDM6600_NR_STATUS_LINES); - int error, i, val = 0; + int error; ddata = container_of(work, struct phy_mdm6600, status_work.work); dev = ddata->dev; @@ -212,16 +212,11 @@ static void phy_mdm6600_status(struct work_struct *work) if (error) return; - for (i = 0; i < PHY_MDM6600_NR_STATUS_LINES; i++) { - val |= test_bit(i, values) << i; - dev_dbg(ddata->dev, "XXX %s: i: %i values[i]: %i val: %i\n", - __func__, i, test_bit(i, values), val); - } - ddata->status = values[0]; + ddata->status = values[0] & ((1 << PHY_MDM6600_NR_STATUS_LINES) - 1); dev_info(dev, "modem status: %i %s\n", ddata->status, - phy_mdm6600_status_name[ddata->status & 7]); + phy_mdm6600_status_name[ddata->status]); complete(&ddata->ack); } diff --git a/drivers/phy/qualcomm/phy-qcom-usb-hs.c b/drivers/phy/qualcomm/phy-qcom-usb-hs.c index b163b3a1558d..61054272a7c8 100644 --- a/drivers/phy/qualcomm/phy-qcom-usb-hs.c +++ b/drivers/phy/qualcomm/phy-qcom-usb-hs.c @@ -158,8 +158,8 @@ static int qcom_usb_hs_phy_power_on(struct phy *phy) /* setup initial state */ qcom_usb_hs_phy_vbus_notifier(&uphy->vbus_notify, state, uphy->vbus_edev); - ret = devm_extcon_register_notifier(&ulpi->dev, uphy->vbus_edev, - EXTCON_USB, &uphy->vbus_notify); + ret = extcon_register_notifier(uphy->vbus_edev, EXTCON_USB, + &uphy->vbus_notify); if (ret) goto err_ulpi; } @@ -180,6 +180,9 @@ static int qcom_usb_hs_phy_power_off(struct phy *phy) { struct qcom_usb_hs_phy *uphy = phy_get_drvdata(phy); + if (uphy->vbus_edev) + extcon_unregister_notifier(uphy->vbus_edev, EXTCON_USB, + &uphy->vbus_notify); regulator_disable(uphy->v3p3); regulator_disable(uphy->v1p8); clk_disable_unprepare(uphy->sleep_clk); diff --git a/drivers/phy/renesas/phy-rcar-gen2.c b/drivers/phy/renesas/phy-rcar-gen2.c index 2926e4937301..2e279ac0fa4d 100644 --- a/drivers/phy/renesas/phy-rcar-gen2.c +++ b/drivers/phy/renesas/phy-rcar-gen2.c @@ -71,6 +71,7 @@ struct rcar_gen2_phy_driver { struct rcar_gen2_phy_data { const struct phy_ops *gen2_phy_ops; const u32 (*select_value)[PHYS_PER_CHANNEL]; + const u32 num_channels; }; static int rcar_gen2_phy_init(struct phy *p) @@ -271,11 +272,13 @@ static const u32 usb20_select_value[][PHYS_PER_CHANNEL] = { static const struct rcar_gen2_phy_data rcar_gen2_usb_phy_data = { .gen2_phy_ops = &rcar_gen2_phy_ops, .select_value = pci_select_value, + .num_channels = ARRAY_SIZE(pci_select_value), }; static const struct rcar_gen2_phy_data rz_g1c_usb_phy_data = { .gen2_phy_ops = &rz_g1c_phy_ops, .select_value = usb20_select_value, + .num_channels = ARRAY_SIZE(usb20_select_value), }; static const struct of_device_id rcar_gen2_phy_match_table[] = { @@ -389,7 +392,7 @@ static int rcar_gen2_phy_probe(struct platform_device *pdev) channel->selected_phy = -1; error = of_property_read_u32(np, "reg", &channel_num); - if (error || channel_num > 2) { + if (error || channel_num >= data->num_channels) { dev_err(dev, "Invalid \"reg\" property\n"); of_node_put(np); return error; diff --git a/drivers/phy/renesas/phy-rcar-gen3-usb2.c b/drivers/phy/renesas/phy-rcar-gen3-usb2.c index b7f6b1324395..bfb22f868857 100644 --- a/drivers/phy/renesas/phy-rcar-gen3-usb2.c +++ b/drivers/phy/renesas/phy-rcar-gen3-usb2.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include @@ -320,9 +321,9 @@ static ssize_t role_store(struct device *dev, struct device_attribute *attr, if (!ch->is_otg_channel || !rcar_gen3_is_any_rphy_initialized(ch)) return -EIO; - if (!strncmp(buf, "host", strlen("host"))) + if (sysfs_streq(buf, "host")) new_mode = PHY_MODE_USB_HOST; - else if (!strncmp(buf, "peripheral", strlen("peripheral"))) + else if (sysfs_streq(buf, "peripheral")) new_mode = PHY_MODE_USB_DEVICE; else return -EINVAL; @@ -614,7 +615,7 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev) return PTR_ERR(channel->base); /* call request_irq for OTG */ - irq = platform_get_irq(pdev, 0); + irq = platform_get_irq_optional(pdev, 0); if (irq >= 0) { INIT_WORK(&channel->work, rcar_gen3_phy_usb2_work); irq = devm_request_irq(dev, irq, rcar_gen3_phy_usb2_irq, diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c b/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c index c6800d220920..bb07024d22ed 100644 --- a/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c +++ b/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c @@ -1088,60 +1088,52 @@ SSSF_PIN_DECL(AF15, GPIOV7, LPCSMI, SIG_DESC_SET(SCU434, 15)); #define AB7 176 SIG_EXPR_LIST_DECL_SESG(AB7, LAD0, LPC, SIG_DESC_SET(SCU434, 16), - SIG_DESC_CLEAR(SCU510, 6)); -SIG_EXPR_LIST_DECL_SESG(AB7, ESPID0, ESPI, SIG_DESC_SET(SCU434, 16), SIG_DESC_SET(SCU510, 6)); +SIG_EXPR_LIST_DECL_SESG(AB7, ESPID0, ESPI, SIG_DESC_SET(SCU434, 16)); PIN_DECL_2(AB7, GPIOW0, LAD0, ESPID0); #define AB8 177 SIG_EXPR_LIST_DECL_SESG(AB8, LAD1, LPC, SIG_DESC_SET(SCU434, 17), - SIG_DESC_CLEAR(SCU510, 6)); -SIG_EXPR_LIST_DECL_SESG(AB8, ESPID1, ESPI, SIG_DESC_SET(SCU434, 17), SIG_DESC_SET(SCU510, 6)); +SIG_EXPR_LIST_DECL_SESG(AB8, ESPID1, ESPI, SIG_DESC_SET(SCU434, 17)); PIN_DECL_2(AB8, GPIOW1, LAD1, ESPID1); #define AC8 178 SIG_EXPR_LIST_DECL_SESG(AC8, LAD2, LPC, SIG_DESC_SET(SCU434, 18), - SIG_DESC_CLEAR(SCU510, 6)); -SIG_EXPR_LIST_DECL_SESG(AC8, ESPID2, ESPI, SIG_DESC_SET(SCU434, 18), SIG_DESC_SET(SCU510, 6)); +SIG_EXPR_LIST_DECL_SESG(AC8, ESPID2, ESPI, SIG_DESC_SET(SCU434, 18)); PIN_DECL_2(AC8, GPIOW2, LAD2, ESPID2); #define AC7 179 SIG_EXPR_LIST_DECL_SESG(AC7, LAD3, LPC, SIG_DESC_SET(SCU434, 19), - SIG_DESC_CLEAR(SCU510, 6)); -SIG_EXPR_LIST_DECL_SESG(AC7, ESPID3, ESPI, SIG_DESC_SET(SCU434, 19), SIG_DESC_SET(SCU510, 6)); +SIG_EXPR_LIST_DECL_SESG(AC7, ESPID3, ESPI, SIG_DESC_SET(SCU434, 19)); PIN_DECL_2(AC7, GPIOW3, LAD3, ESPID3); #define AE7 180 SIG_EXPR_LIST_DECL_SESG(AE7, LCLK, LPC, SIG_DESC_SET(SCU434, 20), - SIG_DESC_CLEAR(SCU510, 6)); -SIG_EXPR_LIST_DECL_SESG(AE7, ESPICK, ESPI, SIG_DESC_SET(SCU434, 20), SIG_DESC_SET(SCU510, 6)); +SIG_EXPR_LIST_DECL_SESG(AE7, ESPICK, ESPI, SIG_DESC_SET(SCU434, 20)); PIN_DECL_2(AE7, GPIOW4, LCLK, ESPICK); #define AF7 181 SIG_EXPR_LIST_DECL_SESG(AF7, LFRAME, LPC, SIG_DESC_SET(SCU434, 21), - SIG_DESC_CLEAR(SCU510, 6)); -SIG_EXPR_LIST_DECL_SESG(AF7, ESPICS, ESPI, SIG_DESC_SET(SCU434, 21), SIG_DESC_SET(SCU510, 6)); +SIG_EXPR_LIST_DECL_SESG(AF7, ESPICS, ESPI, SIG_DESC_SET(SCU434, 21)); PIN_DECL_2(AF7, GPIOW5, LFRAME, ESPICS); #define AD7 182 SIG_EXPR_LIST_DECL_SESG(AD7, LSIRQ, LSIRQ, SIG_DESC_SET(SCU434, 22), - SIG_DESC_CLEAR(SCU510, 6)); -SIG_EXPR_LIST_DECL_SESG(AD7, ESPIALT, ESPIALT, SIG_DESC_SET(SCU434, 22), SIG_DESC_SET(SCU510, 6)); +SIG_EXPR_LIST_DECL_SESG(AD7, ESPIALT, ESPIALT, SIG_DESC_SET(SCU434, 22)); PIN_DECL_2(AD7, GPIOW6, LSIRQ, ESPIALT); FUNC_GROUP_DECL(LSIRQ, AD7); FUNC_GROUP_DECL(ESPIALT, AD7); #define AD8 183 SIG_EXPR_LIST_DECL_SESG(AD8, LPCRST, LPC, SIG_DESC_SET(SCU434, 23), - SIG_DESC_CLEAR(SCU510, 6)); -SIG_EXPR_LIST_DECL_SESG(AD8, ESPIRST, ESPI, SIG_DESC_SET(SCU434, 23), SIG_DESC_SET(SCU510, 6)); +SIG_EXPR_LIST_DECL_SESG(AD8, ESPIRST, ESPI, SIG_DESC_SET(SCU434, 23)); PIN_DECL_2(AD8, GPIOW7, LPCRST, ESPIRST); FUNC_GROUP_DECL(LPC, AB7, AB8, AC8, AC7, AE7, AF7, AD8); diff --git a/drivers/pinctrl/cirrus/Kconfig b/drivers/pinctrl/cirrus/Kconfig index f1806fd781a0..530426a74f75 100644 --- a/drivers/pinctrl/cirrus/Kconfig +++ b/drivers/pinctrl/cirrus/Kconfig @@ -2,6 +2,7 @@ config PINCTRL_LOCHNAGAR tristate "Cirrus Logic Lochnagar pinctrl driver" depends on MFD_LOCHNAGAR + select GPIOLIB select PINMUX select PINCONF select GENERIC_PINCONF diff --git a/drivers/pinctrl/devicetree.c b/drivers/pinctrl/devicetree.c index 5d6d8b1e9062..dbaacde1b36a 100644 --- a/drivers/pinctrl/devicetree.c +++ b/drivers/pinctrl/devicetree.c @@ -29,6 +29,13 @@ struct pinctrl_dt_map { static void dt_free_map(struct pinctrl_dev *pctldev, struct pinctrl_map *map, unsigned num_maps) { + int i; + + for (i = 0; i < num_maps; ++i) { + kfree_const(map[i].dev_name); + map[i].dev_name = NULL; + } + if (pctldev) { const struct pinctrl_ops *ops = pctldev->desc->pctlops; if (ops->dt_free_map) @@ -63,7 +70,13 @@ static int dt_remember_or_free_map(struct pinctrl *p, const char *statename, /* Initialize common mapping table entry fields */ for (i = 0; i < num_maps; i++) { - map[i].dev_name = dev_name(p->dev); + const char *devname; + + devname = kstrdup_const(dev_name(p->dev), GFP_KERNEL); + if (!devname) + goto err_free_map; + + map[i].dev_name = devname; map[i].name = statename; if (pctldev) map[i].ctrl_dev_name = dev_name(pctldev->dev); @@ -71,10 +84,8 @@ static int dt_remember_or_free_map(struct pinctrl *p, const char *statename, /* Remember the converted mapping table entries */ dt_map = kzalloc(sizeof(*dt_map), GFP_KERNEL); - if (!dt_map) { - dt_free_map(pctldev, map, num_maps); - return -ENOMEM; - } + if (!dt_map) + goto err_free_map; dt_map->pctldev = pctldev; dt_map->map = map; @@ -82,6 +93,10 @@ static int dt_remember_or_free_map(struct pinctrl *p, const char *statename, list_add_tail(&dt_map->node, &p->dt_maps); return pinctrl_register_map(map, num_maps, false); + +err_free_map: + dt_free_map(pctldev, map, num_maps); + return -ENOMEM; } struct pinctrl_dev *of_pinctrl_get(struct device_node *np) diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c index 9ffb22211d2b..7d658e6627e7 100644 --- a/drivers/pinctrl/intel/pinctrl-baytrail.c +++ b/drivers/pinctrl/intel/pinctrl-baytrail.c @@ -110,7 +110,6 @@ struct byt_gpio { struct platform_device *pdev; struct pinctrl_dev *pctl_dev; struct pinctrl_desc pctl_desc; - raw_spinlock_t lock; const struct intel_pinctrl_soc_data *soc_data; struct intel_community *communities_copy; struct byt_gpio_pin_context *saved_context; @@ -549,6 +548,8 @@ static const struct intel_pinctrl_soc_data *byt_soc_data[] = { NULL }; +static DEFINE_RAW_SPINLOCK(byt_lock); + static struct intel_community *byt_get_community(struct byt_gpio *vg, unsigned int pin) { @@ -658,7 +659,7 @@ static void byt_set_group_simple_mux(struct byt_gpio *vg, unsigned long flags; int i; - raw_spin_lock_irqsave(&vg->lock, flags); + raw_spin_lock_irqsave(&byt_lock, flags); for (i = 0; i < group.npins; i++) { void __iomem *padcfg0; @@ -678,7 +679,7 @@ static void byt_set_group_simple_mux(struct byt_gpio *vg, writel(value, padcfg0); } - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); } static void byt_set_group_mixed_mux(struct byt_gpio *vg, @@ -688,7 +689,7 @@ static void byt_set_group_mixed_mux(struct byt_gpio *vg, unsigned long flags; int i; - raw_spin_lock_irqsave(&vg->lock, flags); + raw_spin_lock_irqsave(&byt_lock, flags); for (i = 0; i < group.npins; i++) { void __iomem *padcfg0; @@ -708,7 +709,7 @@ static void byt_set_group_mixed_mux(struct byt_gpio *vg, writel(value, padcfg0); } - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); } static int byt_set_mux(struct pinctrl_dev *pctldev, unsigned int func_selector, @@ -749,11 +750,11 @@ static void byt_gpio_clear_triggering(struct byt_gpio *vg, unsigned int offset) unsigned long flags; u32 value; - raw_spin_lock_irqsave(&vg->lock, flags); + raw_spin_lock_irqsave(&byt_lock, flags); value = readl(reg); value &= ~(BYT_TRIG_POS | BYT_TRIG_NEG | BYT_TRIG_LVL); writel(value, reg); - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); } static int byt_gpio_request_enable(struct pinctrl_dev *pctl_dev, @@ -765,7 +766,7 @@ static int byt_gpio_request_enable(struct pinctrl_dev *pctl_dev, u32 value, gpio_mux; unsigned long flags; - raw_spin_lock_irqsave(&vg->lock, flags); + raw_spin_lock_irqsave(&byt_lock, flags); /* * In most cases, func pin mux 000 means GPIO function. @@ -787,7 +788,7 @@ static int byt_gpio_request_enable(struct pinctrl_dev *pctl_dev, "pin %u forcibly re-configured as GPIO\n", offset); } - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); pm_runtime_get(&vg->pdev->dev); @@ -815,7 +816,7 @@ static int byt_gpio_set_direction(struct pinctrl_dev *pctl_dev, unsigned long flags; u32 value; - raw_spin_lock_irqsave(&vg->lock, flags); + raw_spin_lock_irqsave(&byt_lock, flags); value = readl(val_reg); value &= ~BYT_DIR_MASK; @@ -832,7 +833,7 @@ static int byt_gpio_set_direction(struct pinctrl_dev *pctl_dev, "Potential Error: Setting GPIO with direct_irq_en to output"); writel(value, val_reg); - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); return 0; } @@ -901,11 +902,11 @@ static int byt_pin_config_get(struct pinctrl_dev *pctl_dev, unsigned int offset, u32 conf, pull, val, debounce; u16 arg = 0; - raw_spin_lock_irqsave(&vg->lock, flags); + raw_spin_lock_irqsave(&byt_lock, flags); conf = readl(conf_reg); pull = conf & BYT_PULL_ASSIGN_MASK; val = readl(val_reg); - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); switch (param) { case PIN_CONFIG_BIAS_DISABLE: @@ -932,9 +933,9 @@ static int byt_pin_config_get(struct pinctrl_dev *pctl_dev, unsigned int offset, if (!(conf & BYT_DEBOUNCE_EN)) return -EINVAL; - raw_spin_lock_irqsave(&vg->lock, flags); + raw_spin_lock_irqsave(&byt_lock, flags); debounce = readl(db_reg); - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); switch (debounce & BYT_DEBOUNCE_PULSE_MASK) { case BYT_DEBOUNCE_PULSE_375US: @@ -986,7 +987,7 @@ static int byt_pin_config_set(struct pinctrl_dev *pctl_dev, u32 conf, val, debounce; int i, ret = 0; - raw_spin_lock_irqsave(&vg->lock, flags); + raw_spin_lock_irqsave(&byt_lock, flags); conf = readl(conf_reg); val = readl(val_reg); @@ -1094,7 +1095,7 @@ static int byt_pin_config_set(struct pinctrl_dev *pctl_dev, if (!ret) writel(conf, conf_reg); - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); return ret; } @@ -1119,9 +1120,9 @@ static int byt_gpio_get(struct gpio_chip *chip, unsigned int offset) unsigned long flags; u32 val; - raw_spin_lock_irqsave(&vg->lock, flags); + raw_spin_lock_irqsave(&byt_lock, flags); val = readl(reg); - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); return !!(val & BYT_LEVEL); } @@ -1136,13 +1137,13 @@ static void byt_gpio_set(struct gpio_chip *chip, unsigned int offset, int value) if (!reg) return; - raw_spin_lock_irqsave(&vg->lock, flags); + raw_spin_lock_irqsave(&byt_lock, flags); old_val = readl(reg); if (value) writel(old_val | BYT_LEVEL, reg); else writel(old_val & ~BYT_LEVEL, reg); - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); } static int byt_gpio_get_direction(struct gpio_chip *chip, unsigned int offset) @@ -1155,9 +1156,9 @@ static int byt_gpio_get_direction(struct gpio_chip *chip, unsigned int offset) if (!reg) return -EINVAL; - raw_spin_lock_irqsave(&vg->lock, flags); + raw_spin_lock_irqsave(&byt_lock, flags); value = readl(reg); - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); if (!(value & BYT_OUTPUT_EN)) return 0; @@ -1200,14 +1201,14 @@ static void byt_gpio_dbg_show(struct seq_file *s, struct gpio_chip *chip) const char *label; unsigned int pin; - raw_spin_lock_irqsave(&vg->lock, flags); + raw_spin_lock_irqsave(&byt_lock, flags); pin = vg->soc_data->pins[i].number; reg = byt_gpio_reg(vg, pin, BYT_CONF0_REG); if (!reg) { seq_printf(s, "Could not retrieve pin %i conf0 reg\n", pin); - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); continue; } conf0 = readl(reg); @@ -1216,11 +1217,11 @@ static void byt_gpio_dbg_show(struct seq_file *s, struct gpio_chip *chip) if (!reg) { seq_printf(s, "Could not retrieve pin %i val reg\n", pin); - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); continue; } val = readl(reg); - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); comm = byt_get_community(vg, pin); if (!comm) { @@ -1304,9 +1305,9 @@ static void byt_irq_ack(struct irq_data *d) if (!reg) return; - raw_spin_lock(&vg->lock); + raw_spin_lock(&byt_lock); writel(BIT(offset % 32), reg); - raw_spin_unlock(&vg->lock); + raw_spin_unlock(&byt_lock); } static void byt_irq_mask(struct irq_data *d) @@ -1330,7 +1331,7 @@ static void byt_irq_unmask(struct irq_data *d) if (!reg) return; - raw_spin_lock_irqsave(&vg->lock, flags); + raw_spin_lock_irqsave(&byt_lock, flags); value = readl(reg); switch (irqd_get_trigger_type(d)) { @@ -1353,7 +1354,7 @@ static void byt_irq_unmask(struct irq_data *d) writel(value, reg); - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); } static int byt_irq_type(struct irq_data *d, unsigned int type) @@ -1367,7 +1368,7 @@ static int byt_irq_type(struct irq_data *d, unsigned int type) if (!reg || offset >= vg->chip.ngpio) return -EINVAL; - raw_spin_lock_irqsave(&vg->lock, flags); + raw_spin_lock_irqsave(&byt_lock, flags); value = readl(reg); WARN(value & BYT_DIRECT_IRQ_EN, @@ -1389,7 +1390,7 @@ static int byt_irq_type(struct irq_data *d, unsigned int type) else if (type & IRQ_TYPE_LEVEL_MASK) irq_set_handler_locked(d, handle_level_irq); - raw_spin_unlock_irqrestore(&vg->lock, flags); + raw_spin_unlock_irqrestore(&byt_lock, flags); return 0; } @@ -1425,9 +1426,9 @@ static void byt_gpio_irq_handler(struct irq_desc *desc) continue; } - raw_spin_lock(&vg->lock); + raw_spin_lock(&byt_lock); pending = readl(reg); - raw_spin_unlock(&vg->lock); + raw_spin_unlock(&byt_lock); for_each_set_bit(pin, &pending, 32) { virq = irq_find_mapping(vg->chip.irq.domain, base + pin); generic_handle_irq(virq); @@ -1638,8 +1639,6 @@ static int byt_pinctrl_probe(struct platform_device *pdev) return PTR_ERR(vg->pctl_dev); } - raw_spin_lock_init(&vg->lock); - ret = byt_gpio_probe(vg); if (ret) return ret; @@ -1654,8 +1653,11 @@ static int byt_pinctrl_probe(struct platform_device *pdev) static int byt_gpio_suspend(struct device *dev) { struct byt_gpio *vg = dev_get_drvdata(dev); + unsigned long flags; int i; + raw_spin_lock_irqsave(&byt_lock, flags); + for (i = 0; i < vg->soc_data->npins; i++) { void __iomem *reg; u32 value; @@ -1676,14 +1678,18 @@ static int byt_gpio_suspend(struct device *dev) vg->saved_context[i].val = value; } + raw_spin_unlock_irqrestore(&byt_lock, flags); return 0; } static int byt_gpio_resume(struct device *dev) { struct byt_gpio *vg = dev_get_drvdata(dev); + unsigned long flags; int i; + raw_spin_lock_irqsave(&byt_lock, flags); + for (i = 0; i < vg->soc_data->npins; i++) { void __iomem *reg; u32 value; @@ -1721,6 +1727,7 @@ static int byt_gpio_resume(struct device *dev) } } + raw_spin_unlock_irqrestore(&byt_lock, flags); return 0; } #endif diff --git a/drivers/pinctrl/intel/pinctrl-lewisburg.c b/drivers/pinctrl/intel/pinctrl-lewisburg.c index 2e06fb1464ab..7fdf4257df1e 100644 --- a/drivers/pinctrl/intel/pinctrl-lewisburg.c +++ b/drivers/pinctrl/intel/pinctrl-lewisburg.c @@ -33,6 +33,7 @@ .npins = ((e) - (s) + 1), \ } +/* Lewisburg */ static const struct pinctrl_pin_desc lbg_pins[] = { /* GPP_A */ PINCTRL_PIN(0, "RCINB"), @@ -72,7 +73,7 @@ static const struct pinctrl_pin_desc lbg_pins[] = { PINCTRL_PIN(33, "SRCCLKREQB_4"), PINCTRL_PIN(34, "SRCCLKREQB_5"), PINCTRL_PIN(35, "GPP_B_11"), - PINCTRL_PIN(36, "GLB_RST_WARN_N"), + PINCTRL_PIN(36, "SLP_S0B"), PINCTRL_PIN(37, "PLTRSTB"), PINCTRL_PIN(38, "SPKR"), PINCTRL_PIN(39, "GPP_B_15"), @@ -185,96 +186,96 @@ static const struct pinctrl_pin_desc lbg_pins[] = { PINCTRL_PIN(141, "GBE_PCI_DIS"), PINCTRL_PIN(142, "GBE_LAN_DIS"), PINCTRL_PIN(143, "GPP_I_10"), - PINCTRL_PIN(144, "GPIO_RCOMP_3P3"), /* GPP_J */ - PINCTRL_PIN(145, "GBE_LED_0_0"), - PINCTRL_PIN(146, "GBE_LED_0_1"), - PINCTRL_PIN(147, "GBE_LED_1_0"), - PINCTRL_PIN(148, "GBE_LED_1_1"), - PINCTRL_PIN(149, "GBE_LED_2_0"), - PINCTRL_PIN(150, "GBE_LED_2_1"), - PINCTRL_PIN(151, "GBE_LED_3_0"), - PINCTRL_PIN(152, "GBE_LED_3_1"), - PINCTRL_PIN(153, "GBE_SCL_0"), - PINCTRL_PIN(154, "GBE_SDA_0"), - PINCTRL_PIN(155, "GBE_SCL_1"), - PINCTRL_PIN(156, "GBE_SDA_1"), - PINCTRL_PIN(157, "GBE_SCL_2"), - PINCTRL_PIN(158, "GBE_SDA_2"), - PINCTRL_PIN(159, "GBE_SCL_3"), - PINCTRL_PIN(160, "GBE_SDA_3"), - PINCTRL_PIN(161, "GBE_SDP_0_0"), - PINCTRL_PIN(162, "GBE_SDP_0_1"), - PINCTRL_PIN(163, "GBE_SDP_1_0"), - PINCTRL_PIN(164, "GBE_SDP_1_1"), - PINCTRL_PIN(165, "GBE_SDP_2_0"), - PINCTRL_PIN(166, "GBE_SDP_2_1"), - PINCTRL_PIN(167, "GBE_SDP_3_0"), - PINCTRL_PIN(168, "GBE_SDP_3_1"), + PINCTRL_PIN(144, "GBE_LED_0_0"), + PINCTRL_PIN(145, "GBE_LED_0_1"), + PINCTRL_PIN(146, "GBE_LED_1_0"), + PINCTRL_PIN(147, "GBE_LED_1_1"), + PINCTRL_PIN(148, "GBE_LED_2_0"), + PINCTRL_PIN(149, "GBE_LED_2_1"), + PINCTRL_PIN(150, "GBE_LED_3_0"), + PINCTRL_PIN(151, "GBE_LED_3_1"), + PINCTRL_PIN(152, "GBE_SCL_0"), + PINCTRL_PIN(153, "GBE_SDA_0"), + PINCTRL_PIN(154, "GBE_SCL_1"), + PINCTRL_PIN(155, "GBE_SDA_1"), + PINCTRL_PIN(156, "GBE_SCL_2"), + PINCTRL_PIN(157, "GBE_SDA_2"), + PINCTRL_PIN(158, "GBE_SCL_3"), + PINCTRL_PIN(159, "GBE_SDA_3"), + PINCTRL_PIN(160, "GBE_SDP_0_0"), + PINCTRL_PIN(161, "GBE_SDP_0_1"), + PINCTRL_PIN(162, "GBE_SDP_1_0"), + PINCTRL_PIN(163, "GBE_SDP_1_1"), + PINCTRL_PIN(164, "GBE_SDP_2_0"), + PINCTRL_PIN(165, "GBE_SDP_2_1"), + PINCTRL_PIN(166, "GBE_SDP_3_0"), + PINCTRL_PIN(167, "GBE_SDP_3_1"), /* GPP_K */ - PINCTRL_PIN(169, "GBE_RMIICLK"), - PINCTRL_PIN(170, "GBE_RMII_TXD_0"), - PINCTRL_PIN(171, "GBE_RMII_TXD_1"), + PINCTRL_PIN(168, "GBE_RMIICLK"), + PINCTRL_PIN(169, "GBE_RMII_RXD_0"), + PINCTRL_PIN(170, "GBE_RMII_RXD_1"), + PINCTRL_PIN(171, "GBE_RMII_CRS_DV"), PINCTRL_PIN(172, "GBE_RMII_TX_EN"), - PINCTRL_PIN(173, "GBE_RMII_CRS_DV"), - PINCTRL_PIN(174, "GBE_RMII_RXD_0"), - PINCTRL_PIN(175, "GBE_RMII_RXD_1"), - PINCTRL_PIN(176, "GBE_RMII_RX_ER"), - PINCTRL_PIN(177, "GBE_RMII_ARBIN"), - PINCTRL_PIN(178, "GBE_RMII_ARB_OUT"), - PINCTRL_PIN(179, "PE_RST_N"), - PINCTRL_PIN(180, "GPIO_RCOMP_1P8_3P3"), + PINCTRL_PIN(173, "GBE_RMII_TXD_0"), + PINCTRL_PIN(174, "GBE_RMII_TXD_1"), + PINCTRL_PIN(175, "GBE_RMII_RX_ER"), + PINCTRL_PIN(176, "GBE_RMII_ARBIN"), + PINCTRL_PIN(177, "GBE_RMII_ARB_OUT"), + PINCTRL_PIN(178, "PE_RST_N"), /* GPP_G */ - PINCTRL_PIN(181, "FAN_TACH_0"), - PINCTRL_PIN(182, "FAN_TACH_1"), - PINCTRL_PIN(183, "FAN_TACH_2"), - PINCTRL_PIN(184, "FAN_TACH_3"), - PINCTRL_PIN(185, "FAN_TACH_4"), - PINCTRL_PIN(186, "FAN_TACH_5"), - PINCTRL_PIN(187, "FAN_TACH_6"), - PINCTRL_PIN(188, "FAN_TACH_7"), - PINCTRL_PIN(189, "FAN_PWM_0"), - PINCTRL_PIN(190, "FAN_PWM_1"), - PINCTRL_PIN(191, "FAN_PWM_2"), - PINCTRL_PIN(192, "FAN_PWM_3"), - PINCTRL_PIN(193, "GSXDOUT"), - PINCTRL_PIN(194, "GSXSLOAD"), - PINCTRL_PIN(195, "GSXDIN"), - PINCTRL_PIN(196, "GSXSRESETB"), - PINCTRL_PIN(197, "GSXCLK"), - PINCTRL_PIN(198, "ADR_COMPLETE"), - PINCTRL_PIN(199, "NMIB"), - PINCTRL_PIN(200, "SMIB"), - PINCTRL_PIN(201, "SSATA_DEVSLP_0"), - PINCTRL_PIN(202, "SSATA_DEVSLP_1"), - PINCTRL_PIN(203, "SSATA_DEVSLP_2"), - PINCTRL_PIN(204, "SSATAXPCIE0_SSATAGP0"), + PINCTRL_PIN(179, "FAN_TACH_0"), + PINCTRL_PIN(180, "FAN_TACH_1"), + PINCTRL_PIN(181, "FAN_TACH_2"), + PINCTRL_PIN(182, "FAN_TACH_3"), + PINCTRL_PIN(183, "FAN_TACH_4"), + PINCTRL_PIN(184, "FAN_TACH_5"), + PINCTRL_PIN(185, "FAN_TACH_6"), + PINCTRL_PIN(186, "FAN_TACH_7"), + PINCTRL_PIN(187, "FAN_PWM_0"), + PINCTRL_PIN(188, "FAN_PWM_1"), + PINCTRL_PIN(189, "FAN_PWM_2"), + PINCTRL_PIN(190, "FAN_PWM_3"), + PINCTRL_PIN(191, "GSXDOUT"), + PINCTRL_PIN(192, "GSXSLOAD"), + PINCTRL_PIN(193, "GSXDIN"), + PINCTRL_PIN(194, "GSXSRESETB"), + PINCTRL_PIN(195, "GSXCLK"), + PINCTRL_PIN(196, "ADR_COMPLETE"), + PINCTRL_PIN(197, "NMIB"), + PINCTRL_PIN(198, "SMIB"), + PINCTRL_PIN(199, "SSATA_DEVSLP_0"), + PINCTRL_PIN(200, "SSATA_DEVSLP_1"), + PINCTRL_PIN(201, "SSATA_DEVSLP_2"), + PINCTRL_PIN(202, "SSATAXPCIE0_SSATAGP0"), /* GPP_H */ - PINCTRL_PIN(205, "SRCCLKREQB_6"), - PINCTRL_PIN(206, "SRCCLKREQB_7"), - PINCTRL_PIN(207, "SRCCLKREQB_8"), - PINCTRL_PIN(208, "SRCCLKREQB_9"), - PINCTRL_PIN(209, "SRCCLKREQB_10"), - PINCTRL_PIN(210, "SRCCLKREQB_11"), - PINCTRL_PIN(211, "SRCCLKREQB_12"), - PINCTRL_PIN(212, "SRCCLKREQB_13"), - PINCTRL_PIN(213, "SRCCLKREQB_14"), - PINCTRL_PIN(214, "SRCCLKREQB_15"), - PINCTRL_PIN(215, "SML2CLK"), - PINCTRL_PIN(216, "SML2DATA"), - PINCTRL_PIN(217, "SML2ALERTB"), - PINCTRL_PIN(218, "SML3CLK"), - PINCTRL_PIN(219, "SML3DATA"), - PINCTRL_PIN(220, "SML3ALERTB"), - PINCTRL_PIN(221, "SML4CLK"), - PINCTRL_PIN(222, "SML4DATA"), - PINCTRL_PIN(223, "SML4ALERTB"), - PINCTRL_PIN(224, "SSATAXPCIE1_SSATAGP1"), - PINCTRL_PIN(225, "SSATAXPCIE2_SSATAGP2"), - PINCTRL_PIN(226, "SSATAXPCIE3_SSATAGP3"), - PINCTRL_PIN(227, "SSATAXPCIE4_SSATAGP4"), - PINCTRL_PIN(228, "SSATAXPCIE5_SSATAGP5"), + PINCTRL_PIN(203, "SRCCLKREQB_6"), + PINCTRL_PIN(204, "SRCCLKREQB_7"), + PINCTRL_PIN(205, "SRCCLKREQB_8"), + PINCTRL_PIN(206, "SRCCLKREQB_9"), + PINCTRL_PIN(207, "SRCCLKREQB_10"), + PINCTRL_PIN(208, "SRCCLKREQB_11"), + PINCTRL_PIN(209, "SRCCLKREQB_12"), + PINCTRL_PIN(210, "SRCCLKREQB_13"), + PINCTRL_PIN(211, "SRCCLKREQB_14"), + PINCTRL_PIN(212, "SRCCLKREQB_15"), + PINCTRL_PIN(213, "SML2CLK"), + PINCTRL_PIN(214, "SML2DATA"), + PINCTRL_PIN(215, "SML2ALERTB"), + PINCTRL_PIN(216, "SML3CLK"), + PINCTRL_PIN(217, "SML3DATA"), + PINCTRL_PIN(218, "SML3ALERTB"), + PINCTRL_PIN(219, "SML4CLK"), + PINCTRL_PIN(220, "SML4DATA"), + PINCTRL_PIN(221, "SML4ALERTB"), + PINCTRL_PIN(222, "SSATAXPCIE1_SSATAGP1"), + PINCTRL_PIN(223, "SSATAXPCIE2_SSATAGP2"), + PINCTRL_PIN(224, "SSATAXPCIE3_SSATAGP3"), + PINCTRL_PIN(225, "SSATAXPCIE4_SSATAGP4"), + PINCTRL_PIN(226, "SSATAXPCIE5_SSATAGP5"), /* GPP_L */ + PINCTRL_PIN(227, "GPP_L_0"), + PINCTRL_PIN(228, "EC_CSME_INTR_OUT"), PINCTRL_PIN(229, "VISA2CH0_D0"), PINCTRL_PIN(230, "VISA2CH0_D1"), PINCTRL_PIN(231, "VISA2CH0_D2"), diff --git a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c index 44d7f50bbc82..d936e7aa74c4 100644 --- a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c +++ b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c @@ -49,6 +49,7 @@ .padown_offset = SPT_PAD_OWN, \ .padcfglock_offset = SPT_PADCFGLOCK, \ .hostown_offset = SPT_HOSTSW_OWN, \ + .is_offset = SPT_GPI_IS, \ .ie_offset = SPT_GPI_IE, \ .pin_base = (s), \ .npins = ((e) - (s) + 1), \ diff --git a/drivers/pinctrl/meson/pinctrl-meson.c b/drivers/pinctrl/meson/pinctrl-meson.c index 8bba9d053d9f..aba479a1150c 100644 --- a/drivers/pinctrl/meson/pinctrl-meson.c +++ b/drivers/pinctrl/meson/pinctrl-meson.c @@ -441,6 +441,7 @@ static int meson_pinconf_get_drive_strength(struct meson_pinctrl *pc, return ret; meson_calc_reg_and_bit(bank, pin, REG_DS, ®, &bit); + bit = bit << 1; ret = regmap_read(pc->reg_ds, reg, &val); if (ret) diff --git a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c index f2f5fcd9a237..83e585c5a613 100644 --- a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c +++ b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c @@ -595,10 +595,10 @@ static int armada_37xx_irq_set_type(struct irq_data *d, unsigned int type) regmap_read(info->regmap, in_reg, &in_val); /* Set initial polarity based on current input level. */ - if (in_val & d->mask) - val |= d->mask; /* falling */ + if (in_val & BIT(d->hwirq % GPIO_PER_REG)) + val |= BIT(d->hwirq % GPIO_PER_REG); /* falling */ else - val &= ~d->mask; /* rising */ + val &= ~(BIT(d->hwirq % GPIO_PER_REG)); /* rising */ break; } default: diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 2c61141519f8..eab078244a4c 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -540,7 +540,8 @@ static irqreturn_t amd_gpio_irq_handler(int irq, void *dev_id) irqreturn_t ret = IRQ_NONE; unsigned int i, irqnr; unsigned long flags; - u32 *regs, regval; + u32 __iomem *regs; + u32 regval; u64 status, mask; /* Read the wake status */ diff --git a/drivers/pinctrl/pinctrl-rza2.c b/drivers/pinctrl/pinctrl-rza2.c index 3be1d833bf25..eda88cdf870d 100644 --- a/drivers/pinctrl/pinctrl-rza2.c +++ b/drivers/pinctrl/pinctrl-rza2.c @@ -213,8 +213,8 @@ static const char * const rza2_gpio_names[] = { "PC_0", "PC_1", "PC_2", "PC_3", "PC_4", "PC_5", "PC_6", "PC_7", "PD_0", "PD_1", "PD_2", "PD_3", "PD_4", "PD_5", "PD_6", "PD_7", "PE_0", "PE_1", "PE_2", "PE_3", "PE_4", "PE_5", "PE_6", "PE_7", - "PF_0", "PF_1", "PF_2", "PF_3", "P0_4", "PF_5", "PF_6", "PF_7", - "PG_0", "PG_1", "PG_2", "P0_3", "PG_4", "PG_5", "PG_6", "PG_7", + "PF_0", "PF_1", "PF_2", "PF_3", "PF_4", "PF_5", "PF_6", "PF_7", + "PG_0", "PG_1", "PG_2", "PG_3", "PG_4", "PG_5", "PG_6", "PG_7", "PH_0", "PH_1", "PH_2", "PH_3", "PH_4", "PH_5", "PH_6", "PH_7", /* port I does not exist */ "PJ_0", "PJ_1", "PJ_2", "PJ_3", "PJ_4", "PJ_5", "PJ_6", "PJ_7", diff --git a/drivers/pinctrl/pinmux.c b/drivers/pinctrl/pinmux.c index e914f6efd39e..9503ddf2edc7 100644 --- a/drivers/pinctrl/pinmux.c +++ b/drivers/pinctrl/pinmux.c @@ -85,7 +85,7 @@ bool pinmux_can_be_used_for_gpio(struct pinctrl_dev *pctldev, unsigned pin) const struct pinmux_ops *ops = pctldev->desc->pmxops; /* Can't inspect pin, assume it can be used */ - if (!desc) + if (!desc || !ops) return true; if (ops->strict && desc->mux_usecount) diff --git a/drivers/pinctrl/qcom/pinctrl-sc7180.c b/drivers/pinctrl/qcom/pinctrl-sc7180.c index 6399c8a2bc22..d6cfad7417b1 100644 --- a/drivers/pinctrl/qcom/pinctrl-sc7180.c +++ b/drivers/pinctrl/qcom/pinctrl-sc7180.c @@ -77,6 +77,7 @@ enum { .intr_cfg_reg = 0, \ .intr_status_reg = 0, \ .intr_target_reg = 0, \ + .tile = SOUTH, \ .mux_bit = -1, \ .pull_bit = pull, \ .drv_bit = drv, \ @@ -102,6 +103,7 @@ enum { .intr_cfg_reg = 0, \ .intr_status_reg = 0, \ .intr_target_reg = 0, \ + .tile = SOUTH, \ .mux_bit = -1, \ .pull_bit = 3, \ .drv_bit = 0, \ @@ -1087,14 +1089,14 @@ static const struct msm_pingroup sc7180_groups[] = { [116] = PINGROUP(116, WEST, qup04, qup04, _, _, _, _, _, _, _), [117] = PINGROUP(117, WEST, dp_hot, _, _, _, _, _, _, _, _), [118] = PINGROUP(118, WEST, _, _, _, _, _, _, _, _, _), - [119] = UFS_RESET(ufs_reset, 0x97f000), - [120] = SDC_QDSD_PINGROUP(sdc1_rclk, 0x97a000, 15, 0), - [121] = SDC_QDSD_PINGROUP(sdc1_clk, 0x97a000, 13, 6), - [122] = SDC_QDSD_PINGROUP(sdc1_cmd, 0x97a000, 11, 3), - [123] = SDC_QDSD_PINGROUP(sdc1_data, 0x97a000, 9, 0), - [124] = SDC_QDSD_PINGROUP(sdc2_clk, 0x97b000, 14, 6), - [125] = SDC_QDSD_PINGROUP(sdc2_cmd, 0x97b000, 11, 3), - [126] = SDC_QDSD_PINGROUP(sdc2_data, 0x97b000, 9, 0), + [119] = UFS_RESET(ufs_reset, 0x7f000), + [120] = SDC_QDSD_PINGROUP(sdc1_rclk, 0x7a000, 15, 0), + [121] = SDC_QDSD_PINGROUP(sdc1_clk, 0x7a000, 13, 6), + [122] = SDC_QDSD_PINGROUP(sdc1_cmd, 0x7a000, 11, 3), + [123] = SDC_QDSD_PINGROUP(sdc1_data, 0x7a000, 9, 0), + [124] = SDC_QDSD_PINGROUP(sdc2_clk, 0x7b000, 14, 6), + [125] = SDC_QDSD_PINGROUP(sdc2_cmd, 0x7b000, 11, 3), + [126] = SDC_QDSD_PINGROUP(sdc2_data, 0x7b000, 9, 0), }; static const struct msm_pinctrl_soc_data sc7180_pinctrl = { diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.c b/drivers/pinctrl/samsung/pinctrl-exynos.c index ebc27b06718c..0599f5127b01 100644 --- a/drivers/pinctrl/samsung/pinctrl-exynos.c +++ b/drivers/pinctrl/samsung/pinctrl-exynos.c @@ -486,8 +486,10 @@ int exynos_eint_wkup_init(struct samsung_pinctrl_drv_data *d) if (match) { irq_chip = kmemdup(match->data, sizeof(*irq_chip), GFP_KERNEL); - if (!irq_chip) + if (!irq_chip) { + of_node_put(np); return -ENOMEM; + } wkup_np = np; break; } @@ -504,6 +506,7 @@ int exynos_eint_wkup_init(struct samsung_pinctrl_drv_data *d) bank->nr_pins, &exynos_eint_irqd_ops, bank); if (!bank->irq_domain) { dev_err(dev, "wkup irq domain add failed\n"); + of_node_put(wkup_np); return -ENXIO; } @@ -518,8 +521,10 @@ int exynos_eint_wkup_init(struct samsung_pinctrl_drv_data *d) weint_data = devm_kcalloc(dev, bank->nr_pins, sizeof(*weint_data), GFP_KERNEL); - if (!weint_data) + if (!weint_data) { + of_node_put(wkup_np); return -ENOMEM; + } for (idx = 0; idx < bank->nr_pins; ++idx) { irq = irq_of_parse_and_map(bank->of_node, idx); @@ -536,10 +541,13 @@ int exynos_eint_wkup_init(struct samsung_pinctrl_drv_data *d) } } - if (!muxed_banks) + if (!muxed_banks) { + of_node_put(wkup_np); return 0; + } irq = irq_of_parse_and_map(wkup_np, 0); + of_node_put(wkup_np); if (!irq) { dev_err(dev, "irq number for muxed EINTs not found\n"); return 0; diff --git a/drivers/pinctrl/samsung/pinctrl-s3c24xx.c b/drivers/pinctrl/samsung/pinctrl-s3c24xx.c index 7e824e4d20f4..9bd0a3de101d 100644 --- a/drivers/pinctrl/samsung/pinctrl-s3c24xx.c +++ b/drivers/pinctrl/samsung/pinctrl-s3c24xx.c @@ -490,8 +490,10 @@ static int s3c24xx_eint_init(struct samsung_pinctrl_drv_data *d) return -ENODEV; eint_data = devm_kzalloc(dev, sizeof(*eint_data), GFP_KERNEL); - if (!eint_data) + if (!eint_data) { + of_node_put(eint_np); return -ENOMEM; + } eint_data->drvdata = d; @@ -503,12 +505,14 @@ static int s3c24xx_eint_init(struct samsung_pinctrl_drv_data *d) irq = irq_of_parse_and_map(eint_np, i); if (!irq) { dev_err(dev, "failed to get wakeup EINT IRQ %d\n", i); + of_node_put(eint_np); return -ENXIO; } eint_data->parents[i] = irq; irq_set_chained_handler_and_data(irq, handlers[i], eint_data); } + of_node_put(eint_np); bank = d->pin_banks; for (i = 0; i < d->nr_banks; ++i, ++bank) { diff --git a/drivers/pinctrl/samsung/pinctrl-s3c64xx.c b/drivers/pinctrl/samsung/pinctrl-s3c64xx.c index c399f0932af5..f97f8179f2b1 100644 --- a/drivers/pinctrl/samsung/pinctrl-s3c64xx.c +++ b/drivers/pinctrl/samsung/pinctrl-s3c64xx.c @@ -704,8 +704,10 @@ static int s3c64xx_eint_eint0_init(struct samsung_pinctrl_drv_data *d) return -ENODEV; data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); - if (!data) + if (!data) { + of_node_put(eint0_np); return -ENOMEM; + } data->drvdata = d; for (i = 0; i < NUM_EINT0_IRQ; ++i) { @@ -714,6 +716,7 @@ static int s3c64xx_eint_eint0_init(struct samsung_pinctrl_drv_data *d) irq = irq_of_parse_and_map(eint0_np, i); if (!irq) { dev_err(dev, "failed to get wakeup EINT IRQ %d\n", i); + of_node_put(eint0_np); return -ENXIO; } @@ -721,6 +724,7 @@ static int s3c64xx_eint_eint0_init(struct samsung_pinctrl_drv_data *d) s3c64xx_eint0_handlers[i], data); } + of_node_put(eint0_np); bank = d->pin_banks; for (i = 0; i < d->nr_banks; ++i, ++bank) { diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.c b/drivers/pinctrl/samsung/pinctrl-samsung.c index de0477bb469d..f26574ef234a 100644 --- a/drivers/pinctrl/samsung/pinctrl-samsung.c +++ b/drivers/pinctrl/samsung/pinctrl-samsung.c @@ -272,6 +272,7 @@ static int samsung_dt_node_to_map(struct pinctrl_dev *pctldev, &reserved_maps, num_maps); if (ret < 0) { samsung_dt_free_map(pctldev, *map, *num_maps); + of_node_put(np); return ret; } } @@ -785,8 +786,10 @@ static struct samsung_pmx_func *samsung_pinctrl_create_functions( if (!of_get_child_count(cfg_np)) { ret = samsung_pinctrl_create_function(dev, drvdata, cfg_np, func); - if (ret < 0) + if (ret < 0) { + of_node_put(cfg_np); return ERR_PTR(ret); + } if (ret > 0) { ++func; ++func_cnt; @@ -797,8 +800,11 @@ static struct samsung_pmx_func *samsung_pinctrl_create_functions( for_each_child_of_node(cfg_np, func_np) { ret = samsung_pinctrl_create_function(dev, drvdata, func_np, func); - if (ret < 0) + if (ret < 0) { + of_node_put(func_np); + of_node_put(cfg_np); return ERR_PTR(ret); + } if (ret > 0) { ++func; ++func_cnt; diff --git a/drivers/pinctrl/sh-pfc/core.c b/drivers/pinctrl/sh-pfc/core.c index b8640ad41bef..ce983247c9e2 100644 --- a/drivers/pinctrl/sh-pfc/core.c +++ b/drivers/pinctrl/sh-pfc/core.c @@ -29,12 +29,12 @@ static int sh_pfc_map_resources(struct sh_pfc *pfc, struct platform_device *pdev) { - unsigned int num_windows, num_irqs; struct sh_pfc_window *windows; unsigned int *irqs = NULL; + unsigned int num_windows; struct resource *res; unsigned int i; - int irq; + int num_irqs; /* Count the MEM and IRQ resources. */ for (num_windows = 0;; num_windows++) { @@ -42,17 +42,13 @@ static int sh_pfc_map_resources(struct sh_pfc *pfc, if (!res) break; } - for (num_irqs = 0;; num_irqs++) { - irq = platform_get_irq(pdev, num_irqs); - if (irq == -EPROBE_DEFER) - return irq; - if (irq < 0) - break; - } - if (num_windows == 0) return -EINVAL; + num_irqs = platform_irq_count(pdev); + if (num_irqs < 0) + return num_irqs; + /* Allocate memory windows and IRQs arrays. */ windows = devm_kcalloc(pfc->dev, num_windows, sizeof(*windows), GFP_KERNEL); diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a77990.c b/drivers/pinctrl/sh-pfc/pfc-r8a77990.c index 2dfb8d9cfda1..5200dadd6b3e 100644 --- a/drivers/pinctrl/sh-pfc/pfc-r8a77990.c +++ b/drivers/pinctrl/sh-pfc/pfc-r8a77990.c @@ -448,6 +448,8 @@ FM(IP12_31_28) IP12_31_28 FM(IP13_31_28) IP13_31_28 FM(IP14_31_28) IP14_31_28 FM #define MOD_SEL0_1_0 REV4(FM(SEL_SPEED_PULSE_IF_0), FM(SEL_SPEED_PULSE_IF_1), FM(SEL_SPEED_PULSE_IF_2), F_(0, 0)) /* MOD_SEL1 */ /* 0 */ /* 1 */ /* 2 */ /* 3 */ /* 4 */ /* 5 */ /* 6 */ /* 7 */ +#define MOD_SEL1_31 FM(SEL_SIMCARD_0) FM(SEL_SIMCARD_1) +#define MOD_SEL1_30 FM(SEL_SSI2_0) FM(SEL_SSI2_1) #define MOD_SEL1_29 FM(SEL_TIMER_TMU_0) FM(SEL_TIMER_TMU_1) #define MOD_SEL1_28 FM(SEL_USB_20_CH0_0) FM(SEL_USB_20_CH0_1) #define MOD_SEL1_26 FM(SEL_DRIF2_0) FM(SEL_DRIF2_1) @@ -468,7 +470,8 @@ FM(IP12_31_28) IP12_31_28 FM(IP13_31_28) IP13_31_28 FM(IP14_31_28) IP14_31_28 FM #define PINMUX_MOD_SELS \ \ -MOD_SEL0_30_29 \ + MOD_SEL1_31 \ +MOD_SEL0_30_29 MOD_SEL1_30 \ MOD_SEL1_29 \ MOD_SEL0_28 MOD_SEL1_28 \ MOD_SEL0_27_26 \ @@ -1058,7 +1061,7 @@ static const u16 pinmux_data[] = { PINMUX_IPSR_MSEL(IP10_27_24, RIF0_CLK_B, SEL_DRIF0_1), PINMUX_IPSR_MSEL(IP10_27_24, SCL2_B, SEL_I2C2_1), PINMUX_IPSR_MSEL(IP10_27_24, TCLK1_A, SEL_TIMER_TMU_0), - PINMUX_IPSR_GPSR(IP10_27_24, SSI_SCK2_B), + PINMUX_IPSR_MSEL(IP10_27_24, SSI_SCK2_B, SEL_SSI2_1), PINMUX_IPSR_GPSR(IP10_27_24, TS_SCK0), PINMUX_IPSR_GPSR(IP10_31_28, SD0_WP), @@ -1067,7 +1070,7 @@ static const u16 pinmux_data[] = { PINMUX_IPSR_MSEL(IP10_31_28, RIF0_D0_B, SEL_DRIF0_1), PINMUX_IPSR_MSEL(IP10_31_28, SDA2_B, SEL_I2C2_1), PINMUX_IPSR_MSEL(IP10_31_28, TCLK2_A, SEL_TIMER_TMU_0), - PINMUX_IPSR_GPSR(IP10_31_28, SSI_WS2_B), + PINMUX_IPSR_MSEL(IP10_31_28, SSI_WS2_B, SEL_SSI2_1), PINMUX_IPSR_GPSR(IP10_31_28, TS_SDAT0), /* IPSR11 */ @@ -1085,13 +1088,13 @@ static const u16 pinmux_data[] = { PINMUX_IPSR_MSEL(IP11_11_8, RX0_A, SEL_SCIF0_0), PINMUX_IPSR_MSEL(IP11_11_8, HRX1_A, SEL_HSCIF1_0), - PINMUX_IPSR_GPSR(IP11_11_8, SSI_SCK2_A), + PINMUX_IPSR_MSEL(IP11_11_8, SSI_SCK2_A, SEL_SSI2_0), PINMUX_IPSR_GPSR(IP11_11_8, RIF1_SYNC), PINMUX_IPSR_GPSR(IP11_11_8, TS_SCK1), PINMUX_IPSR_MSEL(IP11_15_12, TX0_A, SEL_SCIF0_0), PINMUX_IPSR_GPSR(IP11_15_12, HTX1_A), - PINMUX_IPSR_GPSR(IP11_15_12, SSI_WS2_A), + PINMUX_IPSR_MSEL(IP11_15_12, SSI_WS2_A, SEL_SSI2_0), PINMUX_IPSR_GPSR(IP11_15_12, RIF1_D0), PINMUX_IPSR_GPSR(IP11_15_12, TS_SDAT1), @@ -1196,7 +1199,7 @@ static const u16 pinmux_data[] = { PINMUX_IPSR_MSEL(IP13_19_16, RIF0_D1_A, SEL_DRIF0_0), PINMUX_IPSR_MSEL(IP13_19_16, SDA1_B, SEL_I2C1_1), PINMUX_IPSR_MSEL(IP13_19_16, TCLK2_B, SEL_TIMER_TMU_1), - PINMUX_IPSR_GPSR(IP13_19_16, SIM0_D_A), + PINMUX_IPSR_MSEL(IP13_19_16, SIM0_D_A, SEL_SIMCARD_0), PINMUX_IPSR_GPSR(IP13_23_20, MLB_DAT), PINMUX_IPSR_MSEL(IP13_23_20, TX0_B, SEL_SCIF0_1), @@ -1264,7 +1267,7 @@ static const u16 pinmux_data[] = { PINMUX_IPSR_GPSR(IP15_15_12, TPU0TO2), PINMUX_IPSR_MSEL(IP15_15_12, SDA1_D, SEL_I2C1_3), PINMUX_IPSR_MSEL(IP15_15_12, FSO_CFE_1_N_B, SEL_FSO_1), - PINMUX_IPSR_GPSR(IP15_15_12, SIM0_D_B), + PINMUX_IPSR_MSEL(IP15_15_12, SIM0_D_B, SEL_SIMCARD_1), PINMUX_IPSR_GPSR(IP15_19_16, SSI_SDATA6), PINMUX_IPSR_MSEL(IP15_19_16, HRTS2_N_A, SEL_HSCIF2_0), @@ -4957,11 +4960,11 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { MOD_SEL0_1_0 )) }, { PINMUX_CFG_REG_VAR("MOD_SEL1", 0xe6060504, 32, - GROUP(2, 1, 1, 1, 1, 1, 3, 3, 1, 1, 1, 1, - 2, 2, 2, 1, 1, 2, 1, 4), + GROUP(1, 1, 1, 1, 1, 1, 1, 3, 3, 1, 1, 1, + 1, 2, 2, 2, 1, 1, 2, 1, 4), GROUP( - /* RESERVED 31, 30 */ - 0, 0, 0, 0, + MOD_SEL1_31 + MOD_SEL1_30 MOD_SEL1_29 MOD_SEL1_28 /* RESERVED 27 */ diff --git a/drivers/pinctrl/sh-pfc/pfc-sh7734.c b/drivers/pinctrl/sh-pfc/pfc-sh7734.c index 5dfd991ffdaa..dbc36079c381 100644 --- a/drivers/pinctrl/sh-pfc/pfc-sh7734.c +++ b/drivers/pinctrl/sh-pfc/pfc-sh7734.c @@ -1450,7 +1450,7 @@ static const struct pinmux_func pinmux_func_gpios[] = { GPIO_FN(ET0_ETXD2_A), GPIO_FN(EX_CS5), GPIO_FN(SD1_CMD_A), GPIO_FN(ATADIR), GPIO_FN(QSSL_B), GPIO_FN(ET0_ETXD3_A), - GPIO_FN(RD_WR), GPIO_FN(TCLK1_B), + GPIO_FN(RD_WR), GPIO_FN(TCLK0), GPIO_FN(CAN_CLK_B), GPIO_FN(ET0_ETXD4), GPIO_FN(EX_WAIT0), GPIO_FN(TCLK1_B), GPIO_FN(EX_WAIT1), GPIO_FN(SD1_DAT0_A), GPIO_FN(DREQ2), GPIO_FN(CAN1_TX_C), GPIO_FN(ET0_LINK_C), GPIO_FN(ET0_ETXD5_A), @@ -1949,7 +1949,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { /* IP3_20 [1] */ FN_EX_WAIT0, FN_TCLK1_B, /* IP3_19_18 [2] */ - FN_RD_WR, FN_TCLK1_B, 0, 0, + FN_RD_WR, FN_TCLK0, FN_CAN_CLK_B, FN_ET0_ETXD4, /* IP3_17_15 [3] */ FN_EX_CS5, FN_SD1_CMD_A, FN_ATADIR, FN_QSSL_B, FN_ET0_ETXD3_A, 0, 0, 0, diff --git a/drivers/pinctrl/sh-pfc/sh_pfc.h b/drivers/pinctrl/sh-pfc/sh_pfc.h index 835148fc0f28..cab7da130925 100644 --- a/drivers/pinctrl/sh-pfc/sh_pfc.h +++ b/drivers/pinctrl/sh-pfc/sh_pfc.h @@ -422,12 +422,12 @@ extern const struct sh_pfc_soc_info shx3_pinmux_info; /* * Describe a pinmux configuration in which a pin is physically multiplexed * with other pins. - * - ipsr: IPSR field (unused, for documentation purposes only) + * - ipsr: IPSR field * - fn: Function name * - psel: Physical multiplexing selector */ #define PINMUX_IPSR_PHYS(ipsr, fn, psel) \ - PINMUX_DATA(fn##_MARK, FN_##psel) + PINMUX_DATA(fn##_MARK, FN_##psel, FN_##ipsr) /* * Describe a pinmux configuration for a single-function pin with GPIO diff --git a/drivers/pinctrl/ti/pinctrl-ti-iodelay.c b/drivers/pinctrl/ti/pinctrl-ti-iodelay.c index e5e7f1f22813..b522ca010332 100644 --- a/drivers/pinctrl/ti/pinctrl-ti-iodelay.c +++ b/drivers/pinctrl/ti/pinctrl-ti-iodelay.c @@ -496,7 +496,7 @@ static int ti_iodelay_dt_node_to_map(struct pinctrl_dev *pctldev, return -EINVAL; rows = pinctrl_count_index_with_args(np, name); - if (rows == -EINVAL) + if (rows < 0) return rows; *map = devm_kzalloc(iod->dev, sizeof(**map), GFP_KERNEL); diff --git a/drivers/platform/mellanox/mlxbf-tmfifo.c b/drivers/platform/mellanox/mlxbf-tmfifo.c index 9a5c9fd2dbc6..5739a9669b29 100644 --- a/drivers/platform/mellanox/mlxbf-tmfifo.c +++ b/drivers/platform/mellanox/mlxbf-tmfifo.c @@ -149,7 +149,7 @@ struct mlxbf_tmfifo_irq_info { * @work: work struct for deferred process * @timer: background timer * @vring: Tx/Rx ring - * @spin_lock: spin lock + * @spin_lock: Tx/Rx spin lock * @is_ready: ready flag */ struct mlxbf_tmfifo { @@ -164,7 +164,7 @@ struct mlxbf_tmfifo { struct work_struct work; struct timer_list timer; struct mlxbf_tmfifo_vring *vring[2]; - spinlock_t spin_lock; /* spin lock */ + spinlock_t spin_lock[2]; /* spin lock */ bool is_ready; }; @@ -525,7 +525,7 @@ static void mlxbf_tmfifo_console_tx(struct mlxbf_tmfifo *fifo, int avail) writeq(*(u64 *)&hdr, fifo->tx_base + MLXBF_TMFIFO_TX_DATA); /* Use spin-lock to protect the 'cons->tx_buf'. */ - spin_lock_irqsave(&fifo->spin_lock, flags); + spin_lock_irqsave(&fifo->spin_lock[0], flags); while (size > 0) { addr = cons->tx_buf.buf + cons->tx_buf.tail; @@ -552,7 +552,7 @@ static void mlxbf_tmfifo_console_tx(struct mlxbf_tmfifo *fifo, int avail) } } - spin_unlock_irqrestore(&fifo->spin_lock, flags); + spin_unlock_irqrestore(&fifo->spin_lock[0], flags); } /* Rx/Tx one word in the descriptor buffer. */ @@ -731,9 +731,9 @@ static bool mlxbf_tmfifo_rxtx_one_desc(struct mlxbf_tmfifo_vring *vring, fifo->vring[is_rx] = NULL; /* Notify upper layer that packet is done. */ - spin_lock_irqsave(&fifo->spin_lock, flags); + spin_lock_irqsave(&fifo->spin_lock[is_rx], flags); vring_interrupt(0, vring->vq); - spin_unlock_irqrestore(&fifo->spin_lock, flags); + spin_unlock_irqrestore(&fifo->spin_lock[is_rx], flags); } mlxbf_tmfifo_desc_done: @@ -852,10 +852,10 @@ static bool mlxbf_tmfifo_virtio_notify(struct virtqueue *vq) * worker handler. */ if (vring->vdev_id == VIRTIO_ID_CONSOLE) { - spin_lock_irqsave(&fifo->spin_lock, flags); + spin_lock_irqsave(&fifo->spin_lock[0], flags); tm_vdev = fifo->vdev[VIRTIO_ID_CONSOLE]; mlxbf_tmfifo_console_output(tm_vdev, vring); - spin_unlock_irqrestore(&fifo->spin_lock, flags); + spin_unlock_irqrestore(&fifo->spin_lock[0], flags); } else if (test_and_set_bit(MLXBF_TM_TX_LWM_IRQ, &fifo->pend_events)) { return true; @@ -1189,7 +1189,8 @@ static int mlxbf_tmfifo_probe(struct platform_device *pdev) if (!fifo) return -ENOMEM; - spin_lock_init(&fifo->spin_lock); + spin_lock_init(&fifo->spin_lock[0]); + spin_lock_init(&fifo->spin_lock[1]); INIT_WORK(&fifo->work, mlxbf_tmfifo_work_handler); mutex_init(&fifo->lock); diff --git a/drivers/platform/mips/cpu_hwmon.c b/drivers/platform/mips/cpu_hwmon.c index a7f184bb47e0..3d29a11c1d6b 100644 --- a/drivers/platform/mips/cpu_hwmon.c +++ b/drivers/platform/mips/cpu_hwmon.c @@ -161,7 +161,7 @@ static int __init loongson_hwmon_init(void) cpu_hwmon_dev = hwmon_device_register(NULL); if (IS_ERR(cpu_hwmon_dev)) { - ret = -ENOMEM; + ret = PTR_ERR(cpu_hwmon_dev); pr_err("hwmon_device_register fail!\n"); goto fail_hwmon_device_register; } diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index ae21d08c65e8..1cab99320514 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -806,7 +806,6 @@ config PEAQ_WMI tristate "PEAQ 2-in-1 WMI hotkey driver" depends on ACPI_WMI depends on INPUT - select INPUT_POLLDEV help Say Y here if you want to support WMI-based hotkeys on PEAQ 2-in-1s. diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 821b08e01635..982f0cc8270c 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -512,13 +512,7 @@ static void kbd_led_update(struct asus_wmi *asus) { int ctrl_param = 0; - /* - * bits 0-2: level - * bit 7: light on/off - */ - if (asus->kbd_led_wk > 0) - ctrl_param = 0x80 | (asus->kbd_led_wk & 0x7F); - + ctrl_param = 0x80 | (asus->kbd_led_wk & 0x7F); asus_wmi_set_devstate(ASUS_WMI_DEVID_KBD_BACKLIGHT, ctrl_param, NULL); } diff --git a/drivers/platform/x86/dell-wmi.c b/drivers/platform/x86/dell-wmi.c index 6669db2555fb..9ff5c5da1a2f 100644 --- a/drivers/platform/x86/dell-wmi.c +++ b/drivers/platform/x86/dell-wmi.c @@ -173,6 +173,11 @@ static const struct key_entry dell_wmi_keymap_type_0000[] = { /* Dell Support Center key */ { KE_IGNORE, 0xe06e, { KEY_RESERVED } }, + /* Dell Vostro 3360 multimedia keys with mangled DSDT */ + { KE_KEY, 0xe0f1, { KEY_PROG1 } }, + { KE_KEY, 0xe0f2, { KEY_PROG2 } }, + { KE_KEY, 0xe0f3, { KEY_PROG3 } }, + { KE_IGNORE, 0xe0f7, { KEY_MUTE } }, { KE_IGNORE, 0xe0f8, { KEY_VOLUMEDOWN } }, { KE_IGNORE, 0xe0f9, { KEY_VOLUMEUP } }, diff --git a/drivers/platform/x86/gpd-pocket-fan.c b/drivers/platform/x86/gpd-pocket-fan.c index be85ed966bf3..73eb1572b966 100644 --- a/drivers/platform/x86/gpd-pocket-fan.c +++ b/drivers/platform/x86/gpd-pocket-fan.c @@ -16,17 +16,27 @@ #define MAX_SPEED 3 -static int temp_limits[3] = { 55000, 60000, 65000 }; +#define TEMP_LIMIT0_DEFAULT 55000 +#define TEMP_LIMIT1_DEFAULT 60000 +#define TEMP_LIMIT2_DEFAULT 65000 + +#define HYSTERESIS_DEFAULT 3000 + +#define SPEED_ON_AC_DEFAULT 2 + +static int temp_limits[3] = { + TEMP_LIMIT0_DEFAULT, TEMP_LIMIT1_DEFAULT, TEMP_LIMIT2_DEFAULT, +}; module_param_array(temp_limits, int, NULL, 0444); MODULE_PARM_DESC(temp_limits, "Millicelsius values above which the fan speed increases"); -static int hysteresis = 3000; +static int hysteresis = HYSTERESIS_DEFAULT; module_param(hysteresis, int, 0444); MODULE_PARM_DESC(hysteresis, "Hysteresis in millicelsius before lowering the fan speed"); -static int speed_on_ac = 2; +static int speed_on_ac = SPEED_ON_AC_DEFAULT; module_param(speed_on_ac, int, 0444); MODULE_PARM_DESC(speed_on_ac, "minimum fan speed to allow when system is powered by AC"); @@ -120,18 +130,21 @@ static int gpd_pocket_fan_probe(struct platform_device *pdev) if (temp_limits[i] < 40000 || temp_limits[i] > 70000) { dev_err(&pdev->dev, "Invalid temp-limit %d (must be between 40000 and 70000)\n", temp_limits[i]); - return -EINVAL; + temp_limits[0] = TEMP_LIMIT0_DEFAULT; + temp_limits[1] = TEMP_LIMIT1_DEFAULT; + temp_limits[2] = TEMP_LIMIT2_DEFAULT; + break; } } if (hysteresis < 1000 || hysteresis > 10000) { dev_err(&pdev->dev, "Invalid hysteresis %d (must be between 1000 and 10000)\n", hysteresis); - return -EINVAL; + hysteresis = HYSTERESIS_DEFAULT; } if (speed_on_ac < 0 || speed_on_ac > MAX_SPEED) { dev_err(&pdev->dev, "Invalid speed_on_ac %d (must be between 0 and 3)\n", speed_on_ac); - return -EINVAL; + speed_on_ac = SPEED_ON_AC_DEFAULT; } fan = devm_kzalloc(&pdev->dev, sizeof(*fan), GFP_KERNEL); diff --git a/drivers/platform/x86/hp-wmi.c b/drivers/platform/x86/hp-wmi.c index 6bcbbb375401..a881b709af25 100644 --- a/drivers/platform/x86/hp-wmi.c +++ b/drivers/platform/x86/hp-wmi.c @@ -65,7 +65,7 @@ struct bios_args { u32 command; u32 commandtype; u32 datasize; - u32 data; + u8 data[128]; }; enum hp_wmi_commandtype { @@ -216,7 +216,7 @@ static int hp_wmi_perform_query(int query, enum hp_wmi_command command, .command = command, .commandtype = query, .datasize = insize, - .data = 0, + .data = { 0 }, }; struct acpi_buffer input = { sizeof(struct bios_args), &args }; struct acpi_buffer output = { ACPI_ALLOCATE_BUFFER, NULL }; @@ -228,7 +228,7 @@ static int hp_wmi_perform_query(int query, enum hp_wmi_command command, if (WARN_ON(insize > sizeof(args.data))) return -EINVAL; - memcpy(&args.data, buffer, insize); + memcpy(&args.data[0], buffer, insize); wmi_evaluate_method(HPWMI_BIOS_GUID, 0, mid, &input, &output); @@ -300,7 +300,7 @@ static int __init hp_wmi_bios_2008_later(void) static int __init hp_wmi_bios_2009_later(void) { - int state = 0; + u8 state[128]; int ret = hp_wmi_perform_query(HPWMI_FEATURE2_QUERY, HPWMI_READ, &state, sizeof(state), sizeof(state)); if (!ret) @@ -380,7 +380,7 @@ static int hp_wmi_rfkill2_refresh(void) int err, i; err = hp_wmi_perform_query(HPWMI_WIRELESS2_QUERY, HPWMI_READ, &state, - 0, sizeof(state)); + sizeof(state), sizeof(state)); if (err) return err; @@ -778,7 +778,7 @@ static int __init hp_wmi_rfkill2_setup(struct platform_device *device) int err, i; err = hp_wmi_perform_query(HPWMI_WIRELESS2_QUERY, HPWMI_READ, &state, - 0, sizeof(state)); + sizeof(state), sizeof(state)); if (err) return err < 0 ? err : -EINVAL; diff --git a/drivers/platform/x86/intel_pmc_core.c b/drivers/platform/x86/intel_pmc_core.c index 94a008efb09b..571b4754477c 100644 --- a/drivers/platform/x86/intel_pmc_core.c +++ b/drivers/platform/x86/intel_pmc_core.c @@ -158,8 +158,9 @@ static const struct pmc_reg_map spt_reg_map = { .pm_vric1_offset = SPT_PMC_VRIC1_OFFSET, }; -/* Cannonlake: PGD PFET Enable Ack Status Register(s) bitmap */ +/* Cannon Lake: PGD PFET Enable Ack Status Register(s) bitmap */ static const struct pmc_bit_map cnp_pfear_map[] = { + /* Reserved for Cannon Lake but valid for Comet Lake */ {"PMC", BIT(0)}, {"OPI-DMI", BIT(1)}, {"SPI/eSPI", BIT(2)}, @@ -185,7 +186,7 @@ static const struct pmc_bit_map cnp_pfear_map[] = { {"SDX", BIT(4)}, {"SPE", BIT(5)}, {"Fuse", BIT(6)}, - /* Reserved for Cannonlake but valid for Icelake */ + /* Reserved for Cannon Lake but valid for Ice Lake and Comet Lake */ {"SBR8", BIT(7)}, {"CSME_FSC", BIT(0)}, @@ -229,12 +230,12 @@ static const struct pmc_bit_map cnp_pfear_map[] = { {"HDA_PGD4", BIT(2)}, {"HDA_PGD5", BIT(3)}, {"HDA_PGD6", BIT(4)}, - /* Reserved for Cannonlake but valid for Icelake */ + /* Reserved for Cannon Lake but valid for Ice Lake and Comet Lake */ {"PSF6", BIT(5)}, {"PSF7", BIT(6)}, {"PSF8", BIT(7)}, - /* Icelake generation onwards only */ + /* Ice Lake generation onwards only */ {"RES_65", BIT(0)}, {"RES_66", BIT(1)}, {"RES_67", BIT(2)}, @@ -324,7 +325,7 @@ static const struct pmc_bit_map cnp_ltr_show_map[] = { {"ISH", CNP_PMC_LTR_ISH}, {"UFSX2", CNP_PMC_LTR_UFSX2}, {"EMMC", CNP_PMC_LTR_EMMC}, - /* Reserved for Cannonlake but valid for Icelake */ + /* Reserved for Cannon Lake but valid for Ice Lake */ {"WIGIG", ICL_PMC_LTR_WIGIG}, /* Below two cannot be used for LTR_IGNORE */ {"CURRENT_PLATFORM", CNP_PMC_LTR_CUR_PLT}, @@ -813,6 +814,8 @@ static const struct x86_cpu_id intel_pmc_core_ids[] = { INTEL_CPU_FAM6(CANNONLAKE_L, cnp_reg_map), INTEL_CPU_FAM6(ICELAKE_L, icl_reg_map), INTEL_CPU_FAM6(ICELAKE_NNPI, icl_reg_map), + INTEL_CPU_FAM6(COMETLAKE, cnp_reg_map), + INTEL_CPU_FAM6(COMETLAKE_L, cnp_reg_map), {} }; @@ -871,8 +874,8 @@ static int pmc_core_probe(struct platform_device *pdev) pmcdev->map = (struct pmc_reg_map *)cpu_id->driver_data; /* - * Coffeelake has CPU ID of Kabylake and Cannonlake PCH. So here - * Sunrisepoint PCH regmap can't be used. Use Cannonlake PCH regmap + * Coffee Lake has CPU ID of Kaby Lake and Cannon Lake PCH. So here + * Sunrisepoint PCH regmap can't be used. Use Cannon Lake PCH regmap * in this case. */ if (pmcdev->map == &spt_reg_map && !pci_dev_present(pmc_pci_ids)) diff --git a/drivers/platform/x86/pcengines-apuv2.c b/drivers/platform/x86/pcengines-apuv2.c index 48b112b4f0b0..c32daf087640 100644 --- a/drivers/platform/x86/pcengines-apuv2.c +++ b/drivers/platform/x86/pcengines-apuv2.c @@ -95,7 +95,7 @@ static struct gpiod_lookup_table gpios_led_table = { NULL, 1, GPIO_ACTIVE_LOW), GPIO_LOOKUP_IDX(AMD_FCH_GPIO_DRIVER_NAME, APU2_GPIO_LINE_LED3, NULL, 2, GPIO_ACTIVE_LOW), - GPIO_LOOKUP_IDX(AMD_FCH_GPIO_DRIVER_NAME, APU2_GPIO_REG_SIMSWAP, + GPIO_LOOKUP_IDX(AMD_FCH_GPIO_DRIVER_NAME, APU2_GPIO_LINE_SIMSWAP, NULL, 3, GPIO_ACTIVE_LOW), } }; diff --git a/drivers/platform/x86/peaq-wmi.c b/drivers/platform/x86/peaq-wmi.c index fdeb3624c529..cf9c44c20a82 100644 --- a/drivers/platform/x86/peaq-wmi.c +++ b/drivers/platform/x86/peaq-wmi.c @@ -6,7 +6,7 @@ #include #include -#include +#include #include #include @@ -18,8 +18,7 @@ MODULE_ALIAS("wmi:"PEAQ_DOLBY_BUTTON_GUID); -static unsigned int peaq_ignore_events_counter; -static struct input_polled_dev *peaq_poll_dev; +static struct input_dev *peaq_poll_dev; /* * The Dolby button (yes really a Dolby button) causes an ACPI variable to get @@ -28,8 +27,10 @@ static struct input_polled_dev *peaq_poll_dev; * (if polling after the release) or twice (polling between press and release). * We ignore events for 0.5s after the first event to avoid reporting 2 presses. */ -static void peaq_wmi_poll(struct input_polled_dev *dev) +static void peaq_wmi_poll(struct input_dev *input_dev) { + static unsigned long last_event_time; + static bool had_events; union acpi_object obj; acpi_status status; u32 dummy = 0; @@ -44,22 +45,25 @@ static void peaq_wmi_poll(struct input_polled_dev *dev) return; if (obj.type != ACPI_TYPE_INTEGER) { - dev_err(&peaq_poll_dev->input->dev, + dev_err(&input_dev->dev, "Error WMBC did not return an integer\n"); return; } - if (peaq_ignore_events_counter && peaq_ignore_events_counter--) + if (!obj.integer.value) return; - if (obj.integer.value) { - input_event(peaq_poll_dev->input, EV_KEY, KEY_SOUND, 1); - input_sync(peaq_poll_dev->input); - input_event(peaq_poll_dev->input, EV_KEY, KEY_SOUND, 0); - input_sync(peaq_poll_dev->input); - peaq_ignore_events_counter = max(1u, - PEAQ_POLL_IGNORE_MS / peaq_poll_dev->poll_interval); - } + if (had_events && time_before(jiffies, last_event_time + + msecs_to_jiffies(PEAQ_POLL_IGNORE_MS))) + return; + + input_event(input_dev, EV_KEY, KEY_SOUND, 1); + input_sync(input_dev); + input_event(input_dev, EV_KEY, KEY_SOUND, 0); + input_sync(input_dev); + + last_event_time = jiffies; + had_events = true; } /* Some other devices (Shuttle XS35) use the same WMI GUID for other purposes */ @@ -75,6 +79,8 @@ static const struct dmi_system_id peaq_dmi_table[] __initconst = { static int __init peaq_wmi_init(void) { + int err; + /* WMI GUID is not unique, also check for a DMI match */ if (!dmi_check_system(peaq_dmi_table)) return -ENODEV; @@ -82,24 +88,36 @@ static int __init peaq_wmi_init(void) if (!wmi_has_guid(PEAQ_DOLBY_BUTTON_GUID)) return -ENODEV; - peaq_poll_dev = input_allocate_polled_device(); + peaq_poll_dev = input_allocate_device(); if (!peaq_poll_dev) return -ENOMEM; - peaq_poll_dev->poll = peaq_wmi_poll; - peaq_poll_dev->poll_interval = PEAQ_POLL_INTERVAL_MS; - peaq_poll_dev->poll_interval_max = PEAQ_POLL_MAX_MS; - peaq_poll_dev->input->name = "PEAQ WMI hotkeys"; - peaq_poll_dev->input->phys = "wmi/input0"; - peaq_poll_dev->input->id.bustype = BUS_HOST; - input_set_capability(peaq_poll_dev->input, EV_KEY, KEY_SOUND); + peaq_poll_dev->name = "PEAQ WMI hotkeys"; + peaq_poll_dev->phys = "wmi/input0"; + peaq_poll_dev->id.bustype = BUS_HOST; + input_set_capability(peaq_poll_dev, EV_KEY, KEY_SOUND); + + err = input_setup_polling(peaq_poll_dev, peaq_wmi_poll); + if (err) + goto err_out; + + input_set_poll_interval(peaq_poll_dev, PEAQ_POLL_INTERVAL_MS); + input_set_max_poll_interval(peaq_poll_dev, PEAQ_POLL_MAX_MS); + + err = input_register_device(peaq_poll_dev); + if (err) + goto err_out; + + return 0; - return input_register_polled_device(peaq_poll_dev); +err_out: + input_free_device(peaq_poll_dev); + return err; } static void __exit peaq_wmi_exit(void) { - input_unregister_polled_device(peaq_poll_dev); + input_unregister_device(peaq_poll_dev); } module_init(peaq_wmi_init); diff --git a/drivers/platform/x86/pmc_atom.c b/drivers/platform/x86/pmc_atom.c index 07d1b911e72f..52ef1419b671 100644 --- a/drivers/platform/x86/pmc_atom.c +++ b/drivers/platform/x86/pmc_atom.c @@ -429,6 +429,14 @@ static const struct dmi_system_id critclk_systems[] = { DMI_MATCH(DMI_PRODUCT_VERSION, "6AV7882-0"), }, }, + { + .ident = "CONNECT X300", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "SIEMENS AG"), + DMI_MATCH(DMI_PRODUCT_VERSION, "A5E45074588"), + }, + }, + { /*sentinel*/ } }; diff --git a/drivers/power/supply/cpcap-battery.c b/drivers/power/supply/cpcap-battery.c index 61d6447d1966..00a96e4a1cdc 100644 --- a/drivers/power/supply/cpcap-battery.c +++ b/drivers/power/supply/cpcap-battery.c @@ -562,12 +562,14 @@ static irqreturn_t cpcap_battery_irq_thread(int irq, void *data) switch (d->action) { case CPCAP_BATTERY_IRQ_ACTION_BATTERY_LOW: if (latest->current_ua >= 0) - dev_warn(ddata->dev, "Battery low at 3.3V!\n"); + dev_warn(ddata->dev, "Battery low at %imV!\n", + latest->voltage / 1000); break; case CPCAP_BATTERY_IRQ_ACTION_POWEROFF: - if (latest->current_ua >= 0) { + if (latest->current_ua >= 0 && latest->voltage <= 3200000) { dev_emerg(ddata->dev, - "Battery empty at 3.1V, powering off\n"); + "Battery empty at %imV, powering off\n", + latest->voltage / 1000); orderly_poweroff(true); } break; diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c index 94ddd7d659c8..925b0004a0ed 100644 --- a/drivers/powercap/intel_rapl_common.c +++ b/drivers/powercap/intel_rapl_common.c @@ -1293,6 +1293,9 @@ struct rapl_package *rapl_add_package(int cpu, struct rapl_if_priv *priv) struct cpuinfo_x86 *c = &cpu_data(cpu); int ret; + if (!rapl_defaults) + return ERR_PTR(-ENODEV); + rp = kzalloc(sizeof(struct rapl_package), GFP_KERNEL); if (!rp) return ERR_PTR(-ENOMEM); diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index e60eab7f8a61..b84f16bbd6f2 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -166,10 +166,11 @@ static struct posix_clock_operations ptp_clock_ops = { .read = ptp_read, }; -static void delete_ptp_clock(struct posix_clock *pc) +static void ptp_clock_release(struct device *dev) { - struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock); + struct ptp_clock *ptp = container_of(dev, struct ptp_clock, dev); + ptp_cleanup_pin_groups(ptp); mutex_destroy(&ptp->tsevq_mux); mutex_destroy(&ptp->pincfg_mux); ida_simple_remove(&ptp_clocks_map, ptp->index); @@ -213,7 +214,6 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, } ptp->clock.ops = ptp_clock_ops; - ptp->clock.release = delete_ptp_clock; ptp->info = info; ptp->devid = MKDEV(major, index); ptp->index = index; @@ -236,15 +236,6 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, if (err) goto no_pin_groups; - /* Create a new device in our class. */ - ptp->dev = device_create_with_groups(ptp_class, parent, ptp->devid, - ptp, ptp->pin_attr_groups, - "ptp%d", ptp->index); - if (IS_ERR(ptp->dev)) { - err = PTR_ERR(ptp->dev); - goto no_device; - } - /* Register a new PPS source. */ if (info->pps) { struct pps_source_info pps; @@ -260,8 +251,18 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, } } - /* Create a posix clock. */ - err = posix_clock_register(&ptp->clock, ptp->devid); + /* Initialize a new device of our class in our clock structure. */ + device_initialize(&ptp->dev); + ptp->dev.devt = ptp->devid; + ptp->dev.class = ptp_class; + ptp->dev.parent = parent; + ptp->dev.groups = ptp->pin_attr_groups; + ptp->dev.release = ptp_clock_release; + dev_set_drvdata(&ptp->dev, ptp); + dev_set_name(&ptp->dev, "ptp%d", ptp->index); + + /* Create a posix clock and link it to the device. */ + err = posix_clock_register(&ptp->clock, &ptp->dev); if (err) { pr_err("failed to create posix clock\n"); goto no_clock; @@ -273,8 +274,6 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, if (ptp->pps_source) pps_unregister_source(ptp->pps_source); no_pps: - device_destroy(ptp_class, ptp->devid); -no_device: ptp_cleanup_pin_groups(ptp); no_pin_groups: if (ptp->kworker) @@ -304,10 +303,8 @@ int ptp_clock_unregister(struct ptp_clock *ptp) if (ptp->pps_source) pps_unregister_source(ptp->pps_source); - device_destroy(ptp_class, ptp->devid); - ptp_cleanup_pin_groups(ptp); - posix_clock_unregister(&ptp->clock); + return 0; } EXPORT_SYMBOL(ptp_clock_unregister); diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h index 9171d42468fd..6b97155148f1 100644 --- a/drivers/ptp/ptp_private.h +++ b/drivers/ptp/ptp_private.h @@ -28,7 +28,7 @@ struct timestamp_event_queue { struct ptp_clock { struct posix_clock clock; - struct device *dev; + struct device dev; struct ptp_clock_info *info; dev_t devid; int index; /* index into clocks.map */ diff --git a/drivers/regulator/ab8500.c b/drivers/regulator/ab8500.c index efb2f01a9101..f60e1b26c2d2 100644 --- a/drivers/regulator/ab8500.c +++ b/drivers/regulator/ab8500.c @@ -953,23 +953,6 @@ static struct ab8500_regulator_info .update_val_idle = 0x82, .update_val_normal = 0x02, }, - [AB8505_LDO_USB] = { - .desc = { - .name = "LDO-USB", - .ops = &ab8500_regulator_mode_ops, - .type = REGULATOR_VOLTAGE, - .id = AB8505_LDO_USB, - .owner = THIS_MODULE, - .n_voltages = 1, - .volt_table = fixed_3300000_voltage, - }, - .update_bank = 0x03, - .update_reg = 0x82, - .update_mask = 0x03, - .update_val = 0x01, - .update_val_idle = 0x03, - .update_val_normal = 0x01, - }, [AB8505_LDO_AUDIO] = { .desc = { .name = "LDO-AUDIO", diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c index 989506bd90b1..16f0c8570036 100644 --- a/drivers/regulator/axp20x-regulator.c +++ b/drivers/regulator/axp20x-regulator.c @@ -413,10 +413,13 @@ static int axp20x_set_ramp_delay(struct regulator_dev *rdev, int ramp) int i; for (i = 0; i < rate_count; i++) { - if (ramp <= slew_rates[i]) - cfg = AXP20X_DCDC2_LDO3_V_RAMP_LDO3_RATE(i); - else + if (ramp > slew_rates[i]) break; + + if (id == AXP20X_DCDC2) + cfg = AXP20X_DCDC2_LDO3_V_RAMP_DCDC2_RATE(i); + else + cfg = AXP20X_DCDC2_LDO3_V_RAMP_LDO3_RATE(i); } if (cfg == 0xff) { @@ -605,7 +608,7 @@ static const struct regulator_desc axp22x_regulators[] = { AXP22X_PWR_OUT_CTRL2, AXP22X_PWR_OUT_ELDO1_MASK), AXP_DESC(AXP22X, ELDO2, "eldo2", "eldoin", 700, 3300, 100, AXP22X_ELDO2_V_OUT, AXP22X_ELDO2_V_OUT_MASK, - AXP22X_PWR_OUT_CTRL2, AXP22X_PWR_OUT_ELDO1_MASK), + AXP22X_PWR_OUT_CTRL2, AXP22X_PWR_OUT_ELDO2_MASK), AXP_DESC(AXP22X, ELDO3, "eldo3", "eldoin", 700, 3300, 100, AXP22X_ELDO3_V_OUT, AXP22X_ELDO3_V_OUT_MASK, AXP22X_PWR_OUT_CTRL2, AXP22X_PWR_OUT_ELDO3_MASK), diff --git a/drivers/regulator/bd70528-regulator.c b/drivers/regulator/bd70528-regulator.c index 0248a61f1006..6041839ec38c 100644 --- a/drivers/regulator/bd70528-regulator.c +++ b/drivers/regulator/bd70528-regulator.c @@ -101,7 +101,6 @@ static const struct regulator_ops bd70528_ldo_ops = { .set_voltage_sel = regulator_set_voltage_sel_regmap, .get_voltage_sel = regulator_get_voltage_sel_regmap, .set_voltage_time_sel = regulator_set_voltage_time_sel, - .set_ramp_delay = bd70528_set_ramp_delay, }; static const struct regulator_ops bd70528_led_ops = { diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index a46be221dbdc..1dba0bdf3762 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -1403,7 +1403,9 @@ static int set_machine_constraints(struct regulator_dev *rdev, rdev_err(rdev, "failed to enable\n"); return ret; } - rdev->use_count++; + + if (rdev->constraints->always_on) + rdev->use_count++; } print_constraints(rdev); @@ -1935,8 +1937,8 @@ struct regulator *_regulator_get(struct device *dev, const char *id, regulator = create_regulator(rdev, dev, id); if (regulator == NULL) { regulator = ERR_PTR(-ENOMEM); - put_device(&rdev->dev); module_put(rdev->owner); + put_device(&rdev->dev); return regulator; } @@ -2057,13 +2059,13 @@ static void _regulator_put(struct regulator *regulator) rdev->open_count--; rdev->exclusive = 0; - put_device(&rdev->dev); regulator_unlock(rdev); kfree_const(regulator->supply_name); kfree(regulator); module_put(rdev->owner); + put_device(&rdev->dev); } /** @@ -4990,6 +4992,7 @@ regulator_register(const struct regulator_desc *regulator_desc, struct regulator_dev *rdev; bool dangling_cfg_gpiod = false; bool dangling_of_gpiod = false; + bool reg_device_fail = false; struct device *dev; int ret, i; @@ -5175,7 +5178,7 @@ regulator_register(const struct regulator_desc *regulator_desc, dev_set_drvdata(&rdev->dev, rdev); ret = device_register(&rdev->dev); if (ret != 0) { - put_device(&rdev->dev); + reg_device_fail = true; goto unset_supplies; } @@ -5198,6 +5201,7 @@ regulator_register(const struct regulator_desc *regulator_desc, regulator_remove_coupling(rdev); mutex_unlock(®ulator_list_mutex); wash: + kfree(rdev->coupling_desc.coupled_rdevs); kfree(rdev->constraints); mutex_lock(®ulator_list_mutex); regulator_ena_gpio_free(rdev); @@ -5205,7 +5209,10 @@ regulator_register(const struct regulator_desc *regulator_desc, clean: if (dangling_of_gpiod) gpiod_put(config->ena_gpiod); - kfree(rdev); + if (reg_device_fail) + put_device(&rdev->dev); + else + kfree(rdev); kfree(config); rinse: if (dangling_cfg_gpiod) diff --git a/drivers/regulator/max8907-regulator.c b/drivers/regulator/max8907-regulator.c index 76152aaa330b..96dc0eea7659 100644 --- a/drivers/regulator/max8907-regulator.c +++ b/drivers/regulator/max8907-regulator.c @@ -296,7 +296,10 @@ static int max8907_regulator_probe(struct platform_device *pdev) memcpy(pmic->desc, max8907_regulators, sizeof(pmic->desc)); /* Backwards compatibility with MAX8907B; SD1 uses different voltages */ - regmap_read(max8907->regmap_gen, MAX8907_REG_II2RR, &val); + ret = regmap_read(max8907->regmap_gen, MAX8907_REG_II2RR, &val); + if (ret) + return ret; + if ((val & MAX8907_II2RR_VERSION_MASK) == MAX8907_II2RR_VERSION_REV_B) { pmic->desc[MAX8907_SD1].min_uV = 637500; @@ -333,14 +336,20 @@ static int max8907_regulator_probe(struct platform_device *pdev) } if (pmic->desc[i].ops == &max8907_ldo_ops) { - regmap_read(config.regmap, pmic->desc[i].enable_reg, + ret = regmap_read(config.regmap, pmic->desc[i].enable_reg, &val); + if (ret) + return ret; + if ((val & MAX8907_MASK_LDO_SEQ) != MAX8907_MASK_LDO_SEQ) pmic->desc[i].ops = &max8907_ldo_hwctl_ops; } else if (pmic->desc[i].ops == &max8907_out5v_ops) { - regmap_read(config.regmap, pmic->desc[i].enable_reg, + ret = regmap_read(config.regmap, pmic->desc[i].enable_reg, &val); + if (ret) + return ret; + if ((val & (MAX8907_MASK_OUT5V_VINEN | MAX8907_MASK_OUT5V_ENSRC)) != MAX8907_MASK_OUT5V_ENSRC) diff --git a/drivers/regulator/rn5t618-regulator.c b/drivers/regulator/rn5t618-regulator.c index eb807a059479..aa6e7c5341ce 100644 --- a/drivers/regulator/rn5t618-regulator.c +++ b/drivers/regulator/rn5t618-regulator.c @@ -148,6 +148,7 @@ static struct platform_driver rn5t618_regulator_driver = { module_platform_driver(rn5t618_regulator_driver); +MODULE_ALIAS("platform:rn5t618-regulator"); MODULE_AUTHOR("Beniamino Galvani "); MODULE_DESCRIPTION("RN5T618 regulator driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/reset/core.c b/drivers/reset/core.c index 3c9a64c1b7a8..f343bd814d32 100644 --- a/drivers/reset/core.c +++ b/drivers/reset/core.c @@ -787,7 +787,7 @@ struct reset_control *__devm_reset_control_get(struct device *dev, return ERR_PTR(-ENOMEM); rstc = __reset_control_get(dev, id, index, shared, optional, acquired); - if (!IS_ERR(rstc)) { + if (!IS_ERR_OR_NULL(rstc)) { *ptr = rstc; devres_add(dev, ptr); } else { @@ -930,7 +930,7 @@ devm_reset_control_array_get(struct device *dev, bool shared, bool optional) return ERR_PTR(-ENOMEM); rstc = of_reset_control_array_get(dev->of_node, shared, optional, true); - if (IS_ERR(rstc)) { + if (IS_ERR_OR_NULL(rstc)) { devres_free(devres); return rstc; } diff --git a/drivers/reset/reset-brcmstb.c b/drivers/reset/reset-brcmstb.c index a608f445dad6..f213264c8567 100644 --- a/drivers/reset/reset-brcmstb.c +++ b/drivers/reset/reset-brcmstb.c @@ -91,12 +91,6 @@ static int brcmstb_reset_probe(struct platform_device *pdev) return -ENOMEM; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!IS_ALIGNED(res->start, SW_INIT_BANK_SIZE) || - !IS_ALIGNED(resource_size(res), SW_INIT_BANK_SIZE)) { - dev_err(kdev, "incorrect register range\n"); - return -EINVAL; - } - priv->base = devm_ioremap_resource(kdev, res); if (IS_ERR(priv->base)) return PTR_ERR(priv->base); diff --git a/drivers/rpmsg/qcom_glink_native.c b/drivers/rpmsg/qcom_glink_native.c index 621f1afd4d6b..1995f5b3ea67 100644 --- a/drivers/rpmsg/qcom_glink_native.c +++ b/drivers/rpmsg/qcom_glink_native.c @@ -241,10 +241,31 @@ static void qcom_glink_channel_release(struct kref *ref) { struct glink_channel *channel = container_of(ref, struct glink_channel, refcount); + struct glink_core_rx_intent *intent; + struct glink_core_rx_intent *tmp; unsigned long flags; + int iid; + + /* cancel pending rx_done work */ + cancel_work_sync(&channel->intent_work); spin_lock_irqsave(&channel->intent_lock, flags); + /* Free all non-reuse intents pending rx_done work */ + list_for_each_entry_safe(intent, tmp, &channel->done_intents, node) { + if (!intent->reuse) { + kfree(intent->data); + kfree(intent); + } + } + + idr_for_each_entry(&channel->liids, tmp, iid) { + kfree(tmp->data); + kfree(tmp); + } idr_destroy(&channel->liids); + + idr_for_each_entry(&channel->riids, tmp, iid) + kfree(tmp); idr_destroy(&channel->riids); spin_unlock_irqrestore(&channel->intent_lock, flags); @@ -1094,13 +1115,12 @@ static int qcom_glink_create_remote(struct qcom_glink *glink, close_link: /* * Send a close request to "undo" our open-ack. The close-ack will - * release the last reference. + * release qcom_glink_send_open_req() reference and the last reference + * will be relesed after receiving remote_close or transport unregister + * by calling qcom_glink_native_remove(). */ qcom_glink_send_close_req(glink, channel); - /* Release qcom_glink_send_open_req() reference */ - kref_put(&channel->refcount, qcom_glink_channel_release); - return ret; } @@ -1415,15 +1435,13 @@ static int qcom_glink_rx_open(struct qcom_glink *glink, unsigned int rcid, ret = rpmsg_register_device(rpdev); if (ret) - goto free_rpdev; + goto rcid_remove; channel->rpdev = rpdev; } return 0; -free_rpdev: - kfree(rpdev); rcid_remove: spin_lock_irqsave(&glink->idr_lock, flags); idr_remove(&glink->rcids, channel->rcid); @@ -1544,6 +1562,18 @@ static void qcom_glink_work(struct work_struct *work) } } +static void qcom_glink_cancel_rx_work(struct qcom_glink *glink) +{ + struct glink_defer_cmd *dcmd; + struct glink_defer_cmd *tmp; + + /* cancel any pending deferred rx_work */ + cancel_work_sync(&glink->rx_work); + + list_for_each_entry_safe(dcmd, tmp, &glink->rx_queue, node) + kfree(dcmd); +} + struct qcom_glink *qcom_glink_native_probe(struct device *dev, unsigned long features, struct qcom_glink_pipe *rx, @@ -1619,23 +1649,24 @@ void qcom_glink_native_remove(struct qcom_glink *glink) struct glink_channel *channel; int cid; int ret; - unsigned long flags; disable_irq(glink->irq); - cancel_work_sync(&glink->rx_work); + qcom_glink_cancel_rx_work(glink); ret = device_for_each_child(glink->dev, NULL, qcom_glink_remove_device); if (ret) dev_warn(glink->dev, "Can't remove GLINK devices: %d\n", ret); - spin_lock_irqsave(&glink->idr_lock, flags); /* Release any defunct local channels, waiting for close-ack */ idr_for_each_entry(&glink->lcids, channel, cid) kref_put(&channel->refcount, qcom_glink_channel_release); + /* Release any defunct local channels, waiting for close-req */ + idr_for_each_entry(&glink->rcids, channel, cid) + kref_put(&channel->refcount, qcom_glink_channel_release); + idr_destroy(&glink->lcids); idr_destroy(&glink->rcids); - spin_unlock_irqrestore(&glink->idr_lock, flags); mbox_free_channel(glink->mbox_chan); } EXPORT_SYMBOL_GPL(qcom_glink_native_remove); diff --git a/drivers/rpmsg/qcom_glink_smem.c b/drivers/rpmsg/qcom_glink_smem.c index 4238383d8685..579bc4443f6d 100644 --- a/drivers/rpmsg/qcom_glink_smem.c +++ b/drivers/rpmsg/qcom_glink_smem.c @@ -105,7 +105,7 @@ static void glink_smem_rx_advance(struct qcom_glink_pipe *np, tail = le32_to_cpu(*pipe->tail); tail += count; - if (tail > pipe->native.length) + if (tail >= pipe->native.length) tail -= pipe->native.length; *pipe->tail = cpu_to_le32(tail); diff --git a/drivers/rpmsg/rpmsg_char.c b/drivers/rpmsg/rpmsg_char.c index eea5ebbb5119..c655074c07c2 100644 --- a/drivers/rpmsg/rpmsg_char.c +++ b/drivers/rpmsg/rpmsg_char.c @@ -227,8 +227,10 @@ static ssize_t rpmsg_eptdev_write_iter(struct kiocb *iocb, if (!kbuf) return -ENOMEM; - if (!copy_from_iter_full(kbuf, len, from)) - return -EFAULT; + if (!copy_from_iter_full(kbuf, len, from)) { + ret = -EFAULT; + goto free_kbuf; + } if (mutex_lock_interruptible(&eptdev->ept_lock)) { ret = -ERESTARTSYS; diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c index c93ef33b01d3..5c1378d2fab3 100644 --- a/drivers/rtc/interface.c +++ b/drivers/rtc/interface.c @@ -125,7 +125,7 @@ EXPORT_SYMBOL_GPL(rtc_read_time); int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm) { - int err; + int err, uie; err = rtc_valid_tm(tm); if (err != 0) @@ -137,6 +137,17 @@ int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm) rtc_subtract_offset(rtc, tm); +#ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL + uie = rtc->uie_rtctimer.enabled || rtc->uie_irq_active; +#else + uie = rtc->uie_rtctimer.enabled; +#endif + if (uie) { + err = rtc_update_irq_enable(rtc, 0); + if (err) + return err; + } + err = mutex_lock_interruptible(&rtc->ops_lock); if (err) return err; @@ -153,6 +164,12 @@ int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm) /* A timer might have just expired */ schedule_work(&rtc->irqwork); + if (uie) { + err = rtc_update_irq_enable(rtc, 1); + if (err) + return err; + } + trace_rtc_set_time(rtc_tm_to_time64(tm), err); return err; } diff --git a/drivers/rtc/rtc-bd70528.c b/drivers/rtc/rtc-bd70528.c index 7744333b0f40..ddfef4d43bab 100644 --- a/drivers/rtc/rtc-bd70528.c +++ b/drivers/rtc/rtc-bd70528.c @@ -491,3 +491,4 @@ module_platform_driver(bd70528_rtc); MODULE_AUTHOR("Matti Vaittinen "); MODULE_DESCRIPTION("BD70528 RTC driver"); MODULE_LICENSE("GPL"); +MODULE_ALIAS("platofrm:bd70528-rtc"); diff --git a/drivers/rtc/rtc-brcmstb-waketimer.c b/drivers/rtc/rtc-brcmstb-waketimer.c index 3e9800f9878a..82d2ab0b3e9c 100644 --- a/drivers/rtc/rtc-brcmstb-waketimer.c +++ b/drivers/rtc/rtc-brcmstb-waketimer.c @@ -277,6 +277,7 @@ static int brcmstb_waketmr_remove(struct platform_device *pdev) struct brcmstb_waketmr *timer = dev_get_drvdata(&pdev->dev); unregister_reboot_notifier(&timer->reboot_notifier); + clk_disable_unprepare(timer->clk); return 0; } diff --git a/drivers/rtc/rtc-msm6242.c b/drivers/rtc/rtc-msm6242.c index 1c2d3c4a4963..b1f2bedee77e 100644 --- a/drivers/rtc/rtc-msm6242.c +++ b/drivers/rtc/rtc-msm6242.c @@ -133,7 +133,8 @@ static int msm6242_read_time(struct device *dev, struct rtc_time *tm) msm6242_read(priv, MSM6242_SECOND1); tm->tm_min = msm6242_read(priv, MSM6242_MINUTE10) * 10 + msm6242_read(priv, MSM6242_MINUTE1); - tm->tm_hour = (msm6242_read(priv, MSM6242_HOUR10 & 3)) * 10 + + tm->tm_hour = (msm6242_read(priv, MSM6242_HOUR10) & + MSM6242_HOUR10_HR_MASK) * 10 + msm6242_read(priv, MSM6242_HOUR1); tm->tm_mday = msm6242_read(priv, MSM6242_DAY10) * 10 + msm6242_read(priv, MSM6242_DAY1); diff --git a/drivers/rtc/rtc-mt6397.c b/drivers/rtc/rtc-mt6397.c index 704229eb0cac..b216bdcba0da 100644 --- a/drivers/rtc/rtc-mt6397.c +++ b/drivers/rtc/rtc-mt6397.c @@ -47,6 +47,14 @@ #define RTC_AL_SEC 0x0018 +#define RTC_AL_SEC_MASK 0x003f +#define RTC_AL_MIN_MASK 0x003f +#define RTC_AL_HOU_MASK 0x001f +#define RTC_AL_DOM_MASK 0x001f +#define RTC_AL_DOW_MASK 0x0007 +#define RTC_AL_MTH_MASK 0x000f +#define RTC_AL_YEA_MASK 0x007f + #define RTC_PDN2 0x002e #define RTC_PDN2_PWRON_ALARM BIT(4) @@ -103,7 +111,7 @@ static irqreturn_t mtk_rtc_irq_handler_thread(int irq, void *data) irqen = irqsta & ~RTC_IRQ_EN_AL; mutex_lock(&rtc->lock); if (regmap_write(rtc->regmap, rtc->addr_base + RTC_IRQ_EN, - irqen) < 0) + irqen) == 0) mtk_rtc_write_trigger(rtc); mutex_unlock(&rtc->lock); @@ -225,12 +233,12 @@ static int mtk_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alm) alm->pending = !!(pdn2 & RTC_PDN2_PWRON_ALARM); mutex_unlock(&rtc->lock); - tm->tm_sec = data[RTC_OFFSET_SEC]; - tm->tm_min = data[RTC_OFFSET_MIN]; - tm->tm_hour = data[RTC_OFFSET_HOUR]; - tm->tm_mday = data[RTC_OFFSET_DOM]; - tm->tm_mon = data[RTC_OFFSET_MTH]; - tm->tm_year = data[RTC_OFFSET_YEAR]; + tm->tm_sec = data[RTC_OFFSET_SEC] & RTC_AL_SEC_MASK; + tm->tm_min = data[RTC_OFFSET_MIN] & RTC_AL_MIN_MASK; + tm->tm_hour = data[RTC_OFFSET_HOUR] & RTC_AL_HOU_MASK; + tm->tm_mday = data[RTC_OFFSET_DOM] & RTC_AL_DOM_MASK; + tm->tm_mon = data[RTC_OFFSET_MTH] & RTC_AL_MTH_MASK; + tm->tm_year = data[RTC_OFFSET_YEAR] & RTC_AL_YEA_MASK; tm->tm_year += RTC_MIN_YEAR_OFFSET; tm->tm_mon--; @@ -251,14 +259,25 @@ static int mtk_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alm) tm->tm_year -= RTC_MIN_YEAR_OFFSET; tm->tm_mon++; - data[RTC_OFFSET_SEC] = tm->tm_sec; - data[RTC_OFFSET_MIN] = tm->tm_min; - data[RTC_OFFSET_HOUR] = tm->tm_hour; - data[RTC_OFFSET_DOM] = tm->tm_mday; - data[RTC_OFFSET_MTH] = tm->tm_mon; - data[RTC_OFFSET_YEAR] = tm->tm_year; - mutex_lock(&rtc->lock); + ret = regmap_bulk_read(rtc->regmap, rtc->addr_base + RTC_AL_SEC, + data, RTC_OFFSET_COUNT); + if (ret < 0) + goto exit; + + data[RTC_OFFSET_SEC] = ((data[RTC_OFFSET_SEC] & ~(RTC_AL_SEC_MASK)) | + (tm->tm_sec & RTC_AL_SEC_MASK)); + data[RTC_OFFSET_MIN] = ((data[RTC_OFFSET_MIN] & ~(RTC_AL_MIN_MASK)) | + (tm->tm_min & RTC_AL_MIN_MASK)); + data[RTC_OFFSET_HOUR] = ((data[RTC_OFFSET_HOUR] & ~(RTC_AL_HOU_MASK)) | + (tm->tm_hour & RTC_AL_HOU_MASK)); + data[RTC_OFFSET_DOM] = ((data[RTC_OFFSET_DOM] & ~(RTC_AL_DOM_MASK)) | + (tm->tm_mday & RTC_AL_DOM_MASK)); + data[RTC_OFFSET_MTH] = ((data[RTC_OFFSET_MTH] & ~(RTC_AL_MTH_MASK)) | + (tm->tm_mon & RTC_AL_MTH_MASK)); + data[RTC_OFFSET_YEAR] = ((data[RTC_OFFSET_YEAR] & ~(RTC_AL_YEA_MASK)) | + (tm->tm_year & RTC_AL_YEA_MASK)); + if (alm->enabled) { ret = regmap_bulk_write(rtc->regmap, rtc->addr_base + RTC_AL_SEC, diff --git a/drivers/rtc/rtc-sun6i.c b/drivers/rtc/rtc-sun6i.c index 5e2bd9f1d01e..fc32be687606 100644 --- a/drivers/rtc/rtc-sun6i.c +++ b/drivers/rtc/rtc-sun6i.c @@ -380,6 +380,22 @@ static void __init sun50i_h6_rtc_clk_init(struct device_node *node) CLK_OF_DECLARE_DRIVER(sun50i_h6_rtc_clk, "allwinner,sun50i-h6-rtc", sun50i_h6_rtc_clk_init); +/* + * The R40 user manual is self-conflicting on whether the prescaler is + * fixed or configurable. The clock diagram shows it as fixed, but there + * is also a configurable divider in the RTC block. + */ +static const struct sun6i_rtc_clk_data sun8i_r40_rtc_data = { + .rc_osc_rate = 16000000, + .fixed_prescaler = 512, +}; +static void __init sun8i_r40_rtc_clk_init(struct device_node *node) +{ + sun6i_rtc_clk_init(node, &sun8i_r40_rtc_data); +} +CLK_OF_DECLARE_DRIVER(sun8i_r40_rtc_clk, "allwinner,sun8i-r40-rtc", + sun8i_r40_rtc_clk_init); + static const struct sun6i_rtc_clk_data sun8i_v3_rtc_data = { .rc_osc_rate = 32000, .has_out_clk = 1, diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index c94184d080f8..a28b9ff82378 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -1128,7 +1128,8 @@ static u32 get_fcx_max_data(struct dasd_device *device) { struct dasd_eckd_private *private = device->private; int fcx_in_css, fcx_in_gneq, fcx_in_features; - int tpm, mdc; + unsigned int mdc; + int tpm; if (dasd_nofcx) return 0; @@ -1142,7 +1143,7 @@ static u32 get_fcx_max_data(struct dasd_device *device) return 0; mdc = ccw_device_get_mdc(device->cdev, 0); - if (mdc < 0) { + if (mdc == 0) { dev_warn(&device->cdev->dev, "Detecting the maximum supported data size for zHPF requests failed\n"); return 0; } else { @@ -1153,12 +1154,12 @@ static u32 get_fcx_max_data(struct dasd_device *device) static int verify_fcx_max_data(struct dasd_device *device, __u8 lpm) { struct dasd_eckd_private *private = device->private; - int mdc; + unsigned int mdc; u32 fcx_max_data; if (private->fcx_max_data) { mdc = ccw_device_get_mdc(device->cdev, lpm); - if ((mdc < 0)) { + if (mdc == 0) { dev_warn(&device->cdev->dev, "Detecting the maximum data size for zHPF " "requests failed (rc=%d) for a new path %x\n", @@ -2073,7 +2074,7 @@ dasd_eckd_check_characteristics(struct dasd_device *device) dasd_free_block(device->block); device->block = NULL; out_err1: - kfree(private->conf_data); + dasd_eckd_clear_conf_data(device); kfree(device->private); device->private = NULL; return rc; @@ -2082,7 +2083,6 @@ dasd_eckd_check_characteristics(struct dasd_device *device) static void dasd_eckd_uncheck_device(struct dasd_device *device) { struct dasd_eckd_private *private = device->private; - int i; if (!private) return; @@ -2092,21 +2092,7 @@ static void dasd_eckd_uncheck_device(struct dasd_device *device) private->sneq = NULL; private->vdsneq = NULL; private->gneq = NULL; - private->conf_len = 0; - for (i = 0; i < 8; i++) { - kfree(device->path[i].conf_data); - if ((__u8 *)device->path[i].conf_data == - private->conf_data) { - private->conf_data = NULL; - private->conf_len = 0; - } - device->path[i].conf_data = NULL; - device->path[i].cssid = 0; - device->path[i].ssid = 0; - device->path[i].chpid = 0; - } - kfree(private->conf_data); - private->conf_data = NULL; + dasd_eckd_clear_conf_data(device); } static struct dasd_ccw_req * diff --git a/drivers/s390/cio/device_ops.c b/drivers/s390/cio/device_ops.c index 65841af15748..ccecf6b9504e 100644 --- a/drivers/s390/cio/device_ops.c +++ b/drivers/s390/cio/device_ops.c @@ -635,7 +635,7 @@ EXPORT_SYMBOL(ccw_device_tm_start_timeout); * @mask: mask of paths to use * * Return the number of 64K-bytes blocks all paths at least support - * for a transport command. Return values <= 0 indicate failures. + * for a transport command. Return value 0 indicates failure. */ int ccw_device_get_mdc(struct ccw_device *cdev, u8 mask) { diff --git a/drivers/s390/crypto/zcrypt_error.h b/drivers/s390/crypto/zcrypt_error.h index f34ee41cbed8..4f4dd9d727c9 100644 --- a/drivers/s390/crypto/zcrypt_error.h +++ b/drivers/s390/crypto/zcrypt_error.h @@ -61,6 +61,7 @@ struct error_hdr { #define REP82_ERROR_EVEN_MOD_IN_OPND 0x85 #define REP82_ERROR_RESERVED_FIELD 0x88 #define REP82_ERROR_INVALID_DOMAIN_PENDING 0x8A +#define REP82_ERROR_FILTERED_BY_HYPERVISOR 0x8B #define REP82_ERROR_TRANSPORT_FAIL 0x90 #define REP82_ERROR_PACKET_TRUNCATED 0xA0 #define REP82_ERROR_ZERO_BUFFER_LEN 0xB0 @@ -91,6 +92,7 @@ static inline int convert_error(struct zcrypt_queue *zq, case REP82_ERROR_INVALID_DOMAIN_PRECHECK: case REP82_ERROR_INVALID_DOMAIN_PENDING: case REP82_ERROR_INVALID_SPECIAL_CMD: + case REP82_ERROR_FILTERED_BY_HYPERVISOR: // REP88_ERROR_INVALID_KEY // '82' CEX2A // REP88_ERROR_OPERAND // '84' CEX2A // REP88_ERROR_OPERAND_EVEN_MOD // '85' CEX2A diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 83794d7494d4..5be4d800e4ba 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -653,17 +653,17 @@ static int qeth_check_idx_response(struct qeth_card *card, unsigned char *buffer) { QETH_DBF_HEX(CTRL, 2, buffer, QETH_DBF_CTRL_LEN); - if ((buffer[2] & 0xc0) == 0xc0) { + if ((buffer[2] & QETH_IDX_TERMINATE_MASK) == QETH_IDX_TERMINATE) { QETH_DBF_MESSAGE(2, "received an IDX TERMINATE with cause code %#04x\n", buffer[4]); QETH_CARD_TEXT(card, 2, "ckidxres"); QETH_CARD_TEXT(card, 2, " idxterm"); - QETH_CARD_TEXT_(card, 2, " rc%d", -EIO); - if (buffer[4] == 0xf6) { + QETH_CARD_TEXT_(card, 2, "rc%x", buffer[4]); + if (buffer[4] == QETH_IDX_TERM_BAD_TRANSPORT || + buffer[4] == QETH_IDX_TERM_BAD_TRANSPORT_VM) { dev_err(&card->gdev->dev, - "The qeth device is not configured " - "for the OSI layer required by z/VM\n"); - return -EPERM; + "The device does not support the configured transport mode\n"); + return -EPROTONOSUPPORT; } return -EIO; } @@ -740,10 +740,10 @@ static void qeth_issue_next_read_cb(struct qeth_card *card, case 0: break; case -EIO: - qeth_clear_ipacmd_list(card); qeth_schedule_recovery(card); /* fall through */ default: + qeth_clear_ipacmd_list(card); goto out; } @@ -2451,50 +2451,46 @@ static int qeth_mpc_initialize(struct qeth_card *card) rc = qeth_cm_enable(card); if (rc) { QETH_CARD_TEXT_(card, 2, "2err%d", rc); - goto out_qdio; + return rc; } rc = qeth_cm_setup(card); if (rc) { QETH_CARD_TEXT_(card, 2, "3err%d", rc); - goto out_qdio; + return rc; } rc = qeth_ulp_enable(card); if (rc) { QETH_CARD_TEXT_(card, 2, "4err%d", rc); - goto out_qdio; + return rc; } rc = qeth_ulp_setup(card); if (rc) { QETH_CARD_TEXT_(card, 2, "5err%d", rc); - goto out_qdio; + return rc; } rc = qeth_alloc_qdio_queues(card); if (rc) { QETH_CARD_TEXT_(card, 2, "5err%d", rc); - goto out_qdio; + return rc; } rc = qeth_qdio_establish(card); if (rc) { QETH_CARD_TEXT_(card, 2, "6err%d", rc); qeth_free_qdio_queues(card); - goto out_qdio; + return rc; } rc = qeth_qdio_activate(card); if (rc) { QETH_CARD_TEXT_(card, 2, "7err%d", rc); - goto out_qdio; + return rc; } rc = qeth_dm_act(card); if (rc) { QETH_CARD_TEXT_(card, 2, "8err%d", rc); - goto out_qdio; + return rc; } return 0; -out_qdio: - qeth_qdio_clear_card(card, !IS_IQD(card)); - qdio_free(CARD_DDEV(card)); - return rc; } void qeth_print_status_message(struct qeth_card *card) @@ -3382,11 +3378,6 @@ int qeth_configure_cq(struct qeth_card *card, enum qeth_cq cq) goto out; } - if (card->state != CARD_STATE_DOWN) { - rc = -1; - goto out; - } - qeth_free_qdio_queues(card); card->options.cq = cq; rc = 0; @@ -4972,10 +4963,8 @@ int qeth_core_hardsetup_card(struct qeth_card *card, bool *carrier_ok) } if (qeth_adp_supported(card, IPA_SETADP_SET_DIAG_ASSIST)) { rc = qeth_query_setdiagass(card); - if (rc < 0) { + if (rc) QETH_CARD_TEXT_(card, 2, "8err%d", rc); - goto out; - } } return 0; out: diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h index 6420b58cf42b..b7c17b5c823b 100644 --- a/drivers/s390/net/qeth_core_mpc.h +++ b/drivers/s390/net/qeth_core_mpc.h @@ -912,6 +912,11 @@ extern unsigned char IDX_ACTIVATE_WRITE[]; #define QETH_IDX_ACT_ERR_AUTH 0x1E #define QETH_IDX_ACT_ERR_AUTH_USER 0x20 +#define QETH_IDX_TERMINATE 0xc0 +#define QETH_IDX_TERMINATE_MASK 0xc0 +#define QETH_IDX_TERM_BAD_TRANSPORT 0x41 +#define QETH_IDX_TERM_BAD_TRANSPORT_VM 0xf6 + #define PDU_ENCAPSULATION(buffer) \ (buffer + *(buffer + (*(buffer + 0x0b)) + \ *(buffer + *(buffer + 0x0b) + 0x11) + 0x07)) diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c index 9f392497d570..4c3e222e5572 100644 --- a/drivers/s390/net/qeth_core_sys.c +++ b/drivers/s390/net/qeth_core_sys.c @@ -227,7 +227,7 @@ static ssize_t qeth_dev_prioqing_store(struct device *dev, card->qdio.default_out_queue = QETH_DEFAULT_QUEUE; } else if (sysfs_streq(buf, "prio_queueing_vlan")) { if (IS_LAYER3(card)) { - rc = -ENOTSUPP; + rc = -EOPNOTSUPP; goto out; } card->qdio.do_prio_queueing = QETH_PRIO_Q_ING_VLAN; diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 4bccdce19b5a..11e3292c0adf 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -287,14 +287,15 @@ static void qeth_l2_stop_card(struct qeth_card *card) card->state = CARD_STATE_HARDSETUP; } if (card->state == CARD_STATE_HARDSETUP) { - qeth_qdio_clear_card(card, 0); qeth_drain_output_queues(card); qeth_clear_working_pool_list(card); card->state = CARD_STATE_DOWN; } + qeth_qdio_clear_card(card, 0); flush_workqueue(card->event_wq); card->info.mac_bits &= ~QETH_LAYER2_MAC_REGISTERED; + card->info.promisc_mode = 0; } static int qeth_l2_process_inbound_buffer(struct qeth_card *card, @@ -1982,8 +1983,7 @@ int qeth_l2_vnicc_get_timeout(struct qeth_card *card, u32 *timeout) /* check if VNICC is currently enabled */ bool qeth_l2_vnicc_is_in_use(struct qeth_card *card) { - /* if everything is turned off, VNICC is not active */ - if (!card->options.vnicc.cur_chars) + if (!card->options.vnicc.sup_chars) return false; /* default values are only OK if rx_bcast was not enabled by user * or the card is offline. @@ -2070,8 +2070,9 @@ static void qeth_l2_vnicc_init(struct qeth_card *card) /* enforce assumed default values and recover settings, if changed */ error |= qeth_l2_vnicc_recover_timeout(card, QETH_VNICC_LEARNING, timeout); - chars_tmp = card->options.vnicc.wanted_chars ^ QETH_VNICC_DEFAULT; - chars_tmp |= QETH_VNICC_BRIDGE_INVISIBLE; + /* Change chars, if necessary */ + chars_tmp = card->options.vnicc.wanted_chars ^ + card->options.vnicc.cur_chars; chars_len = sizeof(card->options.vnicc.wanted_chars) * BITS_PER_BYTE; for_each_set_bit(i, &chars_tmp, chars_len) { vnicc = BIT(i); diff --git a/drivers/s390/net/qeth_l2_sys.c b/drivers/s390/net/qeth_l2_sys.c index e2bcb26105a3..fc7101ad84de 100644 --- a/drivers/s390/net/qeth_l2_sys.c +++ b/drivers/s390/net/qeth_l2_sys.c @@ -279,7 +279,8 @@ void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card) return; mutex_lock(&card->sbp_lock); - if (card->options.sbp.role != QETH_SBP_ROLE_NONE) { + if (!card->options.sbp.reflect_promisc && + card->options.sbp.role != QETH_SBP_ROLE_NONE) { /* Conditional to avoid spurious error messages */ qeth_bridgeport_setrole(card, card->options.sbp.role); /* Let the callback function refresh the stored role value. */ diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index d7bfc7a0e4c0..5152970a9aa4 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -1426,13 +1426,14 @@ static void qeth_l3_stop_card(struct qeth_card *card) card->state = CARD_STATE_HARDSETUP; } if (card->state == CARD_STATE_HARDSETUP) { - qeth_qdio_clear_card(card, 0); qeth_drain_output_queues(card); qeth_clear_working_pool_list(card); card->state = CARD_STATE_DOWN; } + qeth_qdio_clear_card(card, 0); flush_workqueue(card->event_wq); + card->info.promisc_mode = 0; } static void qeth_l3_set_promisc_mode(struct qeth_card *card) diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c index 2f73b33c9347..333fd4619dc6 100644 --- a/drivers/s390/net/qeth_l3_sys.c +++ b/drivers/s390/net/qeth_l3_sys.c @@ -270,24 +270,36 @@ static ssize_t qeth_l3_dev_hsuid_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct qeth_card *card = dev_get_drvdata(dev); + int rc = 0; char *tmp; - int rc; if (!card) return -EINVAL; if (!IS_IQD(card)) return -EPERM; - if (card->state != CARD_STATE_DOWN) - return -EPERM; - if (card->options.sniffer) - return -EPERM; - if (card->options.cq == QETH_CQ_NOTAVAILABLE) - return -EPERM; + + mutex_lock(&card->conf_mutex); + if (card->state != CARD_STATE_DOWN) { + rc = -EPERM; + goto out; + } + + if (card->options.sniffer) { + rc = -EPERM; + goto out; + } + + if (card->options.cq == QETH_CQ_NOTAVAILABLE) { + rc = -EPERM; + goto out; + } tmp = strsep((char **)&buf, "\n"); - if (strlen(tmp) > 8) - return -EINVAL; + if (strlen(tmp) > 8) { + rc = -EINVAL; + goto out; + } if (card->options.hsuid[0]) /* delete old ip address */ @@ -298,11 +310,13 @@ static ssize_t qeth_l3_dev_hsuid_store(struct device *dev, card->options.hsuid[0] = '\0'; memcpy(card->dev->perm_addr, card->options.hsuid, 9); qeth_configure_cq(card, QETH_CQ_DISABLED); - return count; + goto out; } - if (qeth_configure_cq(card, QETH_CQ_ENABLED)) - return -EPERM; + if (qeth_configure_cq(card, QETH_CQ_ENABLED)) { + rc = -EPERM; + goto out; + } snprintf(card->options.hsuid, sizeof(card->options.hsuid), "%-8s", tmp); @@ -311,6 +325,8 @@ static ssize_t qeth_l3_dev_hsuid_store(struct device *dev, rc = qeth_l3_modify_hsuid(card, true); +out: + mutex_unlock(&card->conf_mutex); return rc ? rc : count; } diff --git a/drivers/s390/scsi/zfcp_dbf.c b/drivers/s390/scsi/zfcp_dbf.c index dccdb41bed8c..1234294700c4 100644 --- a/drivers/s390/scsi/zfcp_dbf.c +++ b/drivers/s390/scsi/zfcp_dbf.c @@ -95,11 +95,9 @@ void zfcp_dbf_hba_fsf_res(char *tag, int level, struct zfcp_fsf_req *req) memcpy(rec->u.res.fsf_status_qual, &q_head->fsf_status_qual, FSF_STATUS_QUALIFIER_SIZE); - if (q_head->fsf_command != FSF_QTCB_FCP_CMND) { - rec->pl_len = q_head->log_length; - zfcp_dbf_pl_write(dbf, (char *)q_pref + q_head->log_start, - rec->pl_len, "fsf_res", req->req_id); - } + rec->pl_len = q_head->log_length; + zfcp_dbf_pl_write(dbf, (char *)q_pref + q_head->log_start, + rec->pl_len, "fsf_res", req->req_id); debug_event(dbf->hba, level, rec, sizeof(*rec)); spin_unlock_irqrestore(&dbf->hba_lock, flags); diff --git a/drivers/scsi/NCR5380.c b/drivers/scsi/NCR5380.c index 536426f25e86..d4401c768a0c 100644 --- a/drivers/scsi/NCR5380.c +++ b/drivers/scsi/NCR5380.c @@ -129,6 +129,9 @@ #define NCR5380_release_dma_irq(x) #endif +static unsigned int disconnect_mask = ~0; +module_param(disconnect_mask, int, 0444); + static int do_abort(struct Scsi_Host *); static void do_reset(struct Scsi_Host *); static void bus_reset_cleanup(struct Scsi_Host *); @@ -954,7 +957,8 @@ static bool NCR5380_select(struct Scsi_Host *instance, struct scsi_cmnd *cmd) int err; bool ret = true; bool can_disconnect = instance->irq != NO_IRQ && - cmd->cmnd[0] != REQUEST_SENSE; + cmd->cmnd[0] != REQUEST_SENSE && + (disconnect_mask & BIT(scmd_id(cmd))); NCR5380_dprint(NDEBUG_ARBITRATION, instance); dsprintk(NDEBUG_ARBITRATION, instance, "starting arbitration, id = %d\n", diff --git a/drivers/scsi/atari_scsi.c b/drivers/scsi/atari_scsi.c index e809493d0d06..a82b63a66635 100644 --- a/drivers/scsi/atari_scsi.c +++ b/drivers/scsi/atari_scsi.c @@ -742,7 +742,7 @@ static int __init atari_scsi_probe(struct platform_device *pdev) atari_scsi_template.sg_tablesize = SG_ALL; } else { atari_scsi_template.can_queue = 1; - atari_scsi_template.sg_tablesize = SG_NONE; + atari_scsi_template.sg_tablesize = 1; } if (setup_can_queue > 0) @@ -751,8 +751,8 @@ static int __init atari_scsi_probe(struct platform_device *pdev) if (setup_cmd_per_lun > 0) atari_scsi_template.cmd_per_lun = setup_cmd_per_lun; - /* Leave sg_tablesize at 0 on a Falcon! */ - if (ATARIHW_PRESENT(TT_SCSI) && setup_sg_tablesize >= 0) + /* Don't increase sg_tablesize on Falcon! */ + if (ATARIHW_PRESENT(TT_SCSI) && setup_sg_tablesize > 0) atari_scsi_template.sg_tablesize = setup_sg_tablesize; if (setup_hostid >= 0) { diff --git a/drivers/scsi/bfa/bfad_attr.c b/drivers/scsi/bfa/bfad_attr.c index 29ab81df75c0..fbfce02e5b93 100644 --- a/drivers/scsi/bfa/bfad_attr.c +++ b/drivers/scsi/bfa/bfad_attr.c @@ -275,8 +275,10 @@ bfad_im_get_stats(struct Scsi_Host *shost) rc = bfa_port_get_stats(BFA_FCPORT(&bfad->bfa), fcstats, bfad_hcb_comp, &fcomp); spin_unlock_irqrestore(&bfad->bfad_lock, flags); - if (rc != BFA_STATUS_OK) + if (rc != BFA_STATUS_OK) { + kfree(fcstats); return NULL; + } wait_for_completion(&fcomp.comp); diff --git a/drivers/scsi/csiostor/csio_lnode.c b/drivers/scsi/csiostor/csio_lnode.c index 66e58f0a75dc..23cbe4cda760 100644 --- a/drivers/scsi/csiostor/csio_lnode.c +++ b/drivers/scsi/csiostor/csio_lnode.c @@ -301,6 +301,7 @@ csio_ln_fdmi_rhba_cbfn(struct csio_hw *hw, struct csio_ioreq *fdmi_req) struct fc_fdmi_port_name *port_name; uint8_t buf[64]; uint8_t *fc4_type; + unsigned long flags; if (fdmi_req->wr_status != FW_SUCCESS) { csio_ln_dbg(ln, "WR error:%x in processing fdmi rhba cmd\n", @@ -385,13 +386,13 @@ csio_ln_fdmi_rhba_cbfn(struct csio_hw *hw, struct csio_ioreq *fdmi_req) len = (uint32_t)(pld - (uint8_t *)cmd); /* Submit FDMI RPA request */ - spin_lock_irq(&hw->lock); + spin_lock_irqsave(&hw->lock, flags); if (csio_ln_mgmt_submit_req(fdmi_req, csio_ln_fdmi_done, FCOE_CT, &fdmi_req->dma_buf, len)) { CSIO_INC_STATS(ln, n_fdmi_err); csio_ln_dbg(ln, "Failed to issue fdmi rpa req\n"); } - spin_unlock_irq(&hw->lock); + spin_unlock_irqrestore(&hw->lock, flags); } /* @@ -412,6 +413,7 @@ csio_ln_fdmi_dprt_cbfn(struct csio_hw *hw, struct csio_ioreq *fdmi_req) struct fc_fdmi_rpl *reg_pl; struct fs_fdmi_attrs *attrib_blk; uint8_t buf[64]; + unsigned long flags; if (fdmi_req->wr_status != FW_SUCCESS) { csio_ln_dbg(ln, "WR error:%x in processing fdmi dprt cmd\n", @@ -491,13 +493,13 @@ csio_ln_fdmi_dprt_cbfn(struct csio_hw *hw, struct csio_ioreq *fdmi_req) attrib_blk->numattrs = htonl(numattrs); /* Submit FDMI RHBA request */ - spin_lock_irq(&hw->lock); + spin_lock_irqsave(&hw->lock, flags); if (csio_ln_mgmt_submit_req(fdmi_req, csio_ln_fdmi_rhba_cbfn, FCOE_CT, &fdmi_req->dma_buf, len)) { CSIO_INC_STATS(ln, n_fdmi_err); csio_ln_dbg(ln, "Failed to issue fdmi rhba req\n"); } - spin_unlock_irq(&hw->lock); + spin_unlock_irqrestore(&hw->lock, flags); } /* @@ -512,6 +514,7 @@ csio_ln_fdmi_dhba_cbfn(struct csio_hw *hw, struct csio_ioreq *fdmi_req) void *cmd; struct fc_fdmi_port_name *port_name; uint32_t len; + unsigned long flags; if (fdmi_req->wr_status != FW_SUCCESS) { csio_ln_dbg(ln, "WR error:%x in processing fdmi dhba cmd\n", @@ -542,13 +545,13 @@ csio_ln_fdmi_dhba_cbfn(struct csio_hw *hw, struct csio_ioreq *fdmi_req) len += sizeof(*port_name); /* Submit FDMI request */ - spin_lock_irq(&hw->lock); + spin_lock_irqsave(&hw->lock, flags); if (csio_ln_mgmt_submit_req(fdmi_req, csio_ln_fdmi_dprt_cbfn, FCOE_CT, &fdmi_req->dma_buf, len)) { CSIO_INC_STATS(ln, n_fdmi_err); csio_ln_dbg(ln, "Failed to issue fdmi dprt req\n"); } - spin_unlock_irq(&hw->lock); + spin_unlock_irqrestore(&hw->lock, flags); } /** diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c index 3e17af8aedeb..2cd2761bd249 100644 --- a/drivers/scsi/cxgbi/libcxgbi.c +++ b/drivers/scsi/cxgbi/libcxgbi.c @@ -121,7 +121,8 @@ static inline void cxgbi_device_destroy(struct cxgbi_device *cdev) "cdev 0x%p, p# %u.\n", cdev, cdev->nports); cxgbi_hbas_remove(cdev); cxgbi_device_portmap_cleanup(cdev); - cxgbi_ppm_release(cdev->cdev2ppm(cdev)); + if (cdev->cdev2ppm) + cxgbi_ppm_release(cdev->cdev2ppm(cdev)); if (cdev->pmap.max_connect) cxgbi_free_big_mem(cdev->pmap.port_csk); kfree(cdev); diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index 0847e682797b..633effb09c9c 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -587,7 +587,13 @@ static int hisi_sas_task_exec(struct sas_task *task, gfp_t gfp_flags, dev = hisi_hba->dev; if (unlikely(test_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags))) { - if (in_softirq()) + /* + * For IOs from upper layer, it may already disable preempt + * in the IO path, if disable preempt again in down(), + * function schedule() will report schedule_bug(), so check + * preemptible() before goto down(). + */ + if (!preemptible()) return -EINVAL; down(&hisi_hba->sem); @@ -2676,6 +2682,7 @@ int hisi_sas_probe(struct platform_device *pdev, err_out_register_ha: scsi_remove_host(shost); err_out_ha: + hisi_sas_debugfs_exit(hisi_hba); hisi_sas_free(hisi_hba); scsi_host_put(shost); return rc; diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index cb8d087762db..ef32ee12f606 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -3259,6 +3259,7 @@ hisi_sas_v3_probe(struct pci_dev *pdev, const struct pci_device_id *id) err_out_register_ha: scsi_remove_host(shost); err_out_ha: + hisi_sas_debugfs_exit(hisi_hba); scsi_host_put(shost); err_out_regions: pci_release_regions(pdev); diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c index 7bedbe877704..0bc63a7ab41c 100644 --- a/drivers/scsi/iscsi_tcp.c +++ b/drivers/scsi/iscsi_tcp.c @@ -369,8 +369,16 @@ static int iscsi_sw_tcp_pdu_xmit(struct iscsi_task *task) { struct iscsi_conn *conn = task->conn; unsigned int noreclaim_flag; + struct iscsi_tcp_conn *tcp_conn = conn->dd_data; + struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data; int rc = 0; + if (!tcp_sw_conn->sock) { + iscsi_conn_printk(KERN_ERR, conn, + "Transport not bound to socket!\n"); + return -EINVAL; + } + noreclaim_flag = memalloc_noreclaim_save(); while (iscsi_sw_tcp_xmit_qlen(conn)) { diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index ebd47c0cf9e9..70b99c0e2e67 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -1945,7 +1945,7 @@ enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc) ISCSI_DBG_EH(session, "scsi cmd %p timedout\n", sc); - spin_lock(&session->frwd_lock); + spin_lock_bh(&session->frwd_lock); task = (struct iscsi_task *)sc->SCp.ptr; if (!task) { /* @@ -2072,7 +2072,7 @@ enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc) done: if (task) task->last_timeout = jiffies; - spin_unlock(&session->frwd_lock); + spin_unlock_bh(&session->frwd_lock); ISCSI_DBG_EH(session, "return %s\n", rc == BLK_EH_RESET_TIMER ? "timer reset" : "shutdown or nh"); return rc; diff --git a/drivers/scsi/libsas/sas_discover.c b/drivers/scsi/libsas/sas_discover.c index f47b4b281b14..d7302c2052f9 100644 --- a/drivers/scsi/libsas/sas_discover.c +++ b/drivers/scsi/libsas/sas_discover.c @@ -81,12 +81,21 @@ static int sas_get_port_device(struct asd_sas_port *port) else dev->dev_type = SAS_SATA_DEV; dev->tproto = SAS_PROTOCOL_SATA; - } else { + } else if (port->oob_mode == SAS_OOB_MODE) { struct sas_identify_frame *id = (struct sas_identify_frame *) dev->frame_rcvd; dev->dev_type = id->dev_type; dev->iproto = id->initiator_bits; dev->tproto = id->target_bits; + } else { + /* If the oob mode is OOB_NOT_CONNECTED, the port is + * disconnected due to race with PHY down. We cannot + * continue to discover this port + */ + sas_put_device(dev); + pr_warn("Port %016llx is disconnected when discovering\n", + SAS_ADDR(port->attached_sas_addr)); + return -ENODEV; } sas_init_dev(dev); diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c index 39a736b887b1..6c2b03415a2c 100644 --- a/drivers/scsi/lpfc/lpfc_bsg.c +++ b/drivers/scsi/lpfc/lpfc_bsg.c @@ -4489,12 +4489,6 @@ lpfc_bsg_write_ebuf_set(struct lpfc_hba *phba, struct bsg_job *job, phba->mbox_ext_buf_ctx.seqNum++; nemb_tp = phba->mbox_ext_buf_ctx.nembType; - dd_data = kmalloc(sizeof(struct bsg_job_data), GFP_KERNEL); - if (!dd_data) { - rc = -ENOMEM; - goto job_error; - } - pbuf = (uint8_t *)dmabuf->virt; size = job->request_payload.payload_len; sg_copy_to_buffer(job->request_payload.sg_list, @@ -4531,6 +4525,13 @@ lpfc_bsg_write_ebuf_set(struct lpfc_hba *phba, struct bsg_job *job, "2968 SLI_CONFIG ext-buffer wr all %d " "ebuffers received\n", phba->mbox_ext_buf_ctx.numBuf); + + dd_data = kmalloc(sizeof(struct bsg_job_data), GFP_KERNEL); + if (!dd_data) { + rc = -ENOMEM; + goto job_error; + } + /* mailbox command structure for base driver */ pmboxq = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL); if (!pmboxq) { @@ -4579,6 +4580,8 @@ lpfc_bsg_write_ebuf_set(struct lpfc_hba *phba, struct bsg_job *job, return SLI_CONFIG_HANDLED; job_error: + if (pmboxq) + mempool_free(pmboxq, phba->mbox_mem_pool); lpfc_bsg_dma_page_free(phba, dmabuf); kfree(dd_data); diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c index 25e86706e207..f883fac2d2b1 100644 --- a/drivers/scsi/lpfc/lpfc_ct.c +++ b/drivers/scsi/lpfc/lpfc_ct.c @@ -1868,6 +1868,12 @@ lpfc_cmpl_ct_disc_fdmi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, if (irsp->ulpStatus == IOSTAT_LOCAL_REJECT) { switch ((irsp->un.ulpWord[4] & IOERR_PARAM_MASK)) { case IOERR_SLI_ABORTED: + case IOERR_SLI_DOWN: + /* Driver aborted this IO. No retry as error + * is likely Offline->Online or some adapter + * error. Recovery will try again. + */ + break; case IOERR_ABORT_IN_PROGRESS: case IOERR_SEQUENCE_TIMEOUT: case IOERR_ILLEGAL_FRAME: diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c index d5303994bfd6..66f8867dd837 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -2236,6 +2236,7 @@ lpfc_cmpl_els_prli(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, struct Scsi_Host *shost = lpfc_shost_from_vport(vport); IOCB_t *irsp; struct lpfc_nodelist *ndlp; + char *mode; /* we pass cmdiocb to state machine which needs rspiocb as well */ cmdiocb->context_un.rsp_iocb = rspiocb; @@ -2273,8 +2274,17 @@ lpfc_cmpl_els_prli(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, goto out; } + /* If we don't send GFT_ID to Fabric, a PRLI error + * could be expected. + */ + if ((vport->fc_flag & FC_FABRIC) || + (vport->cfg_enable_fc4_type != LPFC_ENABLE_BOTH)) + mode = KERN_ERR; + else + mode = KERN_INFO; + /* PRLI failed */ - lpfc_printf_vlog(vport, KERN_ERR, LOG_ELS, + lpfc_printf_vlog(vport, mode, LOG_ELS, "2754 PRLI failure DID:%06X Status:x%x/x%x, " "data: x%x\n", ndlp->nlp_DID, irsp->ulpStatus, @@ -4430,7 +4440,7 @@ lpfc_cmpl_els_rsp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, mempool_free(mbox, phba->mbox_mem_pool); } out: - if (ndlp && NLP_CHK_NODE_ACT(ndlp)) { + if (ndlp && NLP_CHK_NODE_ACT(ndlp) && shost) { spin_lock_irq(shost->host_lock); ndlp->nlp_flag &= ~(NLP_ACC_REGLOGIN | NLP_RM_DFLT_RPI); spin_unlock_irq(shost->host_lock); @@ -6455,7 +6465,7 @@ lpfc_els_rcv_rscn(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb, uint32_t payload_len, length, nportid, *cmd; int rscn_cnt; int rscn_id = 0, hba_id = 0; - int i; + int i, tmo; pcmd = (struct lpfc_dmabuf *) cmdiocb->context2; lp = (uint32_t *) pcmd->virt; @@ -6561,6 +6571,13 @@ lpfc_els_rcv_rscn(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb, spin_lock_irq(shost->host_lock); vport->fc_flag |= FC_RSCN_DEFERRED; + + /* Restart disctmo if its already running */ + if (vport->fc_flag & FC_DISC_TMO) { + tmo = ((phba->fc_ratov * 3) + 3); + mod_timer(&vport->fc_disctmo, + jiffies + msecs_to_jiffies(1000 * tmo)); + } if ((rscn_cnt < FC_MAX_HOLD_RSCN) && !(vport->fc_flag & FC_RSCN_DISCOVERY)) { vport->fc_flag |= FC_RSCN_MODE; @@ -7986,20 +8003,22 @@ lpfc_els_flush_cmd(struct lpfc_vport *vport) struct lpfc_sli_ring *pring; struct lpfc_iocbq *tmp_iocb, *piocb; IOCB_t *cmd = NULL; + unsigned long iflags = 0; lpfc_fabric_abort_vport(vport); + /* * For SLI3, only the hbalock is required. But SLI4 needs to coordinate * with the ring insert operation. Because lpfc_sli_issue_abort_iotag * ultimately grabs the ring_lock, the driver must splice the list into * a working list and release the locks before calling the abort. */ - spin_lock_irq(&phba->hbalock); + spin_lock_irqsave(&phba->hbalock, iflags); pring = lpfc_phba_elsring(phba); /* Bail out if we've no ELS wq, like in PCI error recovery case. */ if (unlikely(!pring)) { - spin_unlock_irq(&phba->hbalock); + spin_unlock_irqrestore(&phba->hbalock, iflags); return; } @@ -8014,6 +8033,9 @@ lpfc_els_flush_cmd(struct lpfc_vport *vport) if (piocb->vport != vport) continue; + if (piocb->iocb_flag & LPFC_DRIVER_ABORTED) + continue; + /* On the ELS ring we can have ELS_REQUESTs or * GEN_REQUESTs waiting for a response. */ @@ -8037,21 +8059,21 @@ lpfc_els_flush_cmd(struct lpfc_vport *vport) if (phba->sli_rev == LPFC_SLI_REV4) spin_unlock(&pring->ring_lock); - spin_unlock_irq(&phba->hbalock); + spin_unlock_irqrestore(&phba->hbalock, iflags); /* Abort each txcmpl iocb on aborted list and remove the dlist links. */ list_for_each_entry_safe(piocb, tmp_iocb, &abort_list, dlist) { - spin_lock_irq(&phba->hbalock); + spin_lock_irqsave(&phba->hbalock, iflags); list_del_init(&piocb->dlist); lpfc_sli_issue_abort_iotag(phba, pring, piocb); - spin_unlock_irq(&phba->hbalock); + spin_unlock_irqrestore(&phba->hbalock, iflags); } if (!list_empty(&abort_list)) lpfc_printf_vlog(vport, KERN_ERR, LOG_ELS, "3387 abort list for txq not empty\n"); INIT_LIST_HEAD(&abort_list); - spin_lock_irq(&phba->hbalock); + spin_lock_irqsave(&phba->hbalock, iflags); if (phba->sli_rev == LPFC_SLI_REV4) spin_lock(&pring->ring_lock); @@ -8091,7 +8113,7 @@ lpfc_els_flush_cmd(struct lpfc_vport *vport) if (phba->sli_rev == LPFC_SLI_REV4) spin_unlock(&pring->ring_lock); - spin_unlock_irq(&phba->hbalock); + spin_unlock_irqrestore(&phba->hbalock, iflags); /* Cancel all the IOCBs from the completions list */ lpfc_sli_cancel_iocbs(phba, &abort_list, diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index 749286acdc17..ee70d14e7a9d 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -700,7 +700,10 @@ lpfc_work_done(struct lpfc_hba *phba) if (!(phba->hba_flag & HBA_SP_QUEUE_EVT)) set_bit(LPFC_DATA_READY, &phba->data_flags); } else { - if (phba->link_state >= LPFC_LINK_UP || + /* Driver could have abort request completed in queue + * when link goes down. Allow for this transition. + */ + if (phba->link_state >= LPFC_LINK_DOWN || phba->link_flag & LS_MDS_LOOPBACK) { pring->flag &= ~LPFC_DEFERRED_RING_EVENT; lpfc_sli_handle_slow_ring_event(phba, pring, @@ -4840,6 +4843,44 @@ lpfc_nlp_logo_unreg(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) } } +/* + * Sets the mailbox completion handler to be used for the + * unreg_rpi command. The handler varies based on the state of + * the port and what will be happening to the rpi next. + */ +static void +lpfc_set_unreg_login_mbx_cmpl(struct lpfc_hba *phba, struct lpfc_vport *vport, + struct lpfc_nodelist *ndlp, LPFC_MBOXQ_t *mbox) +{ + unsigned long iflags; + + if (ndlp->nlp_flag & NLP_ISSUE_LOGO) { + mbox->ctx_ndlp = ndlp; + mbox->mbox_cmpl = lpfc_nlp_logo_unreg; + + } else if (phba->sli_rev == LPFC_SLI_REV4 && + (!(vport->load_flag & FC_UNLOADING)) && + (bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) >= + LPFC_SLI_INTF_IF_TYPE_2) && + (kref_read(&ndlp->kref) > 0)) { + mbox->ctx_ndlp = lpfc_nlp_get(ndlp); + mbox->mbox_cmpl = lpfc_sli4_unreg_rpi_cmpl_clr; + } else { + if (vport->load_flag & FC_UNLOADING) { + if (phba->sli_rev == LPFC_SLI_REV4) { + spin_lock_irqsave(&vport->phba->ndlp_lock, + iflags); + ndlp->nlp_flag |= NLP_RELEASE_RPI; + spin_unlock_irqrestore(&vport->phba->ndlp_lock, + iflags); + } + lpfc_nlp_get(ndlp); + } + mbox->ctx_ndlp = ndlp; + mbox->mbox_cmpl = lpfc_sli_def_mbox_cmpl; + } +} + /* * Free rpi associated with LPFC_NODELIST entry. * This routine is called from lpfc_freenode(), when we are removing @@ -4890,33 +4931,12 @@ lpfc_unreg_rpi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) lpfc_unreg_login(phba, vport->vpi, rpi, mbox); mbox->vport = vport; - if (ndlp->nlp_flag & NLP_ISSUE_LOGO) { - mbox->ctx_ndlp = ndlp; - mbox->mbox_cmpl = lpfc_nlp_logo_unreg; - } else { - if (phba->sli_rev == LPFC_SLI_REV4 && - (!(vport->load_flag & FC_UNLOADING)) && - (bf_get(lpfc_sli_intf_if_type, - &phba->sli4_hba.sli_intf) >= - LPFC_SLI_INTF_IF_TYPE_2) && - (kref_read(&ndlp->kref) > 0)) { - mbox->ctx_ndlp = lpfc_nlp_get(ndlp); - mbox->mbox_cmpl = - lpfc_sli4_unreg_rpi_cmpl_clr; - /* - * accept PLOGIs after unreg_rpi_cmpl - */ - acc_plogi = 0; - } else if (vport->load_flag & FC_UNLOADING) { - mbox->ctx_ndlp = NULL; - mbox->mbox_cmpl = - lpfc_sli_def_mbox_cmpl; - } else { - mbox->ctx_ndlp = ndlp; - mbox->mbox_cmpl = - lpfc_sli_def_mbox_cmpl; - } - } + lpfc_set_unreg_login_mbx_cmpl(phba, vport, ndlp, mbox); + if (mbox->mbox_cmpl == lpfc_sli4_unreg_rpi_cmpl_clr) + /* + * accept PLOGIs after unreg_rpi_cmpl + */ + acc_plogi = 0; if (((ndlp->nlp_DID & Fabric_DID_MASK) != Fabric_DID_MASK) && (!(vport->fc_flag & FC_OFFLINE_MODE))) @@ -5057,6 +5077,7 @@ lpfc_cleanup_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) struct lpfc_hba *phba = vport->phba; LPFC_MBOXQ_t *mb, *nextmb; struct lpfc_dmabuf *mp; + unsigned long iflags; /* Cleanup node for NPort */ lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE, @@ -5138,8 +5159,20 @@ lpfc_cleanup_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) lpfc_cleanup_vports_rrqs(vport, ndlp); if (phba->sli_rev == LPFC_SLI_REV4) ndlp->nlp_flag |= NLP_RELEASE_RPI; - lpfc_unreg_rpi(vport, ndlp); - + if (!lpfc_unreg_rpi(vport, ndlp)) { + /* Clean up unregistered and non freed rpis */ + if ((ndlp->nlp_flag & NLP_RELEASE_RPI) && + !(ndlp->nlp_rpi == LPFC_RPI_ALLOC_ERROR)) { + lpfc_sli4_free_rpi(vport->phba, + ndlp->nlp_rpi); + spin_lock_irqsave(&vport->phba->ndlp_lock, + iflags); + ndlp->nlp_flag &= ~NLP_RELEASE_RPI; + ndlp->nlp_rpi = LPFC_RPI_ALLOC_ERROR; + spin_unlock_irqrestore(&vport->phba->ndlp_lock, + iflags); + } + } return 0; } @@ -5405,9 +5438,14 @@ lpfc_setup_disc_node(struct lpfc_vport *vport, uint32_t did) /* If we've already received a PLOGI from this NPort * we don't need to try to discover it again. */ - if (ndlp->nlp_flag & NLP_RCV_PLOGI) + if (ndlp->nlp_flag & NLP_RCV_PLOGI && + !(ndlp->nlp_type & + (NLP_FCP_TARGET | NLP_NVME_TARGET))) return NULL; + ndlp->nlp_prev_state = ndlp->nlp_state; + lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE); + spin_lock_irq(shost->host_lock); ndlp->nlp_flag |= NLP_NPR_2B_DISC; spin_unlock_irq(shost->host_lock); diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c index fc6e4546d738..696171382558 100644 --- a/drivers/scsi/lpfc/lpfc_nportdisc.c +++ b/drivers/scsi/lpfc/lpfc_nportdisc.c @@ -484,8 +484,10 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, * single discovery thread, this will cause a huge delay in * discovery. Also this will cause multiple state machines * running in parallel for this node. + * This only applies to a fabric environment. */ - if (ndlp->nlp_state == NLP_STE_PLOGI_ISSUE) { + if ((ndlp->nlp_state == NLP_STE_PLOGI_ISSUE) && + (vport->fc_flag & FC_FABRIC)) { /* software abort outstanding PLOGI */ lpfc_els_abort(phba, ndlp); } diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c index a227e36cbdc2..8e0f03ef346b 100644 --- a/drivers/scsi/lpfc/lpfc_nvme.c +++ b/drivers/scsi/lpfc/lpfc_nvme.c @@ -1976,6 +1976,8 @@ lpfc_nvme_fcp_abort(struct nvme_fc_local_port *pnvme_lport, /* Declare and initialization an instance of the FC NVME template. */ static struct nvme_fc_port_template lpfc_nvme_template = { + .module = THIS_MODULE, + /* initiator-based functions */ .localport_delete = lpfc_nvme_localport_delete, .remoteport_delete = lpfc_nvme_remoteport_delete, diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index 6822cd9ff8f1..aa82d538a18a 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -526,7 +526,7 @@ lpfc_sli4_io_xri_aborted(struct lpfc_hba *phba, &qp->lpfc_abts_io_buf_list, list) { if (psb->cur_iocbq.sli4_xritag == xri) { list_del_init(&psb->list); - psb->exch_busy = 0; + psb->flags &= ~LPFC_SBUF_XBUSY; psb->status = IOSTAT_SUCCESS; if (psb->cur_iocbq.iocb_flag == LPFC_IO_NVME) { qp->abts_nvme_io_bufs--; @@ -566,7 +566,7 @@ lpfc_sli4_io_xri_aborted(struct lpfc_hba *phba, if (iocbq->sli4_xritag != xri) continue; psb = container_of(iocbq, struct lpfc_io_buf, cur_iocbq); - psb->exch_busy = 0; + psb->flags &= ~LPFC_SBUF_XBUSY; spin_unlock_irqrestore(&phba->hbalock, iflag); if (!list_empty(&pring->txq)) lpfc_worker_wake_up(phba); @@ -786,7 +786,7 @@ lpfc_release_scsi_buf_s4(struct lpfc_hba *phba, struct lpfc_io_buf *psb) psb->prot_seg_cnt = 0; qp = psb->hdwq; - if (psb->exch_busy) { + if (psb->flags & LPFC_SBUF_XBUSY) { spin_lock_irqsave(&qp->abts_io_buf_list_lock, iflag); psb->pCmd = NULL; list_add_tail(&psb->list, &qp->lpfc_abts_io_buf_list); @@ -3835,7 +3835,10 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn, lpfc_cmd->result = (pIocbOut->iocb.un.ulpWord[4] & IOERR_PARAM_MASK); lpfc_cmd->status = pIocbOut->iocb.ulpStatus; /* pick up SLI4 exhange busy status from HBA */ - lpfc_cmd->exch_busy = pIocbOut->iocb_flag & LPFC_EXCHANGE_BUSY; + if (pIocbOut->iocb_flag & LPFC_EXCHANGE_BUSY) + lpfc_cmd->flags |= LPFC_SBUF_XBUSY; + else + lpfc_cmd->flags &= ~LPFC_SBUF_XBUSY; #ifdef CONFIG_SCSI_LPFC_DEBUG_FS if (lpfc_cmd->prot_data_type) { @@ -4843,20 +4846,21 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd) ret_val = __lpfc_sli_issue_iocb(phba, LPFC_FCP_RING, abtsiocb, 0); } - /* no longer need the lock after this point */ - spin_unlock_irqrestore(&phba->hbalock, flags); if (ret_val == IOCB_ERROR) { /* Indicate the IO is not being aborted by the driver. */ iocb->iocb_flag &= ~LPFC_DRIVER_ABORTED; lpfc_cmd->waitq = NULL; spin_unlock(&lpfc_cmd->buf_lock); + spin_unlock_irqrestore(&phba->hbalock, flags); lpfc_sli_release_iocbq(phba, abtsiocb); ret = FAILED; goto out; } + /* no longer need the lock after this point */ spin_unlock(&lpfc_cmd->buf_lock); + spin_unlock_irqrestore(&phba->hbalock, flags); if (phba->cfg_poll & DISABLE_FCP_RING_INT) lpfc_sli_handle_fast_ring_event(phba, diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index 614f78dddafe..8860f41af3ff 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -2526,6 +2526,8 @@ lpfc_sli_def_mbox_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) } else { __lpfc_sli_rpi_release(vport, ndlp); } + if (vport->load_flag & FC_UNLOADING) + lpfc_nlp_put(ndlp); pmb->ctx_ndlp = NULL; } } @@ -11050,9 +11052,6 @@ lpfc_sli_abort_els_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, irsp->ulpStatus, irsp->un.ulpWord[4]); spin_unlock_irq(&phba->hbalock); - if (irsp->ulpStatus == IOSTAT_LOCAL_REJECT && - irsp->un.ulpWord[4] == IOERR_SLI_ABORTED) - lpfc_sli_release_iocbq(phba, abort_iocb); } release_iocb: lpfc_sli_release_iocbq(phba, cmdiocb); @@ -11736,7 +11735,10 @@ lpfc_sli_wake_iocb_wait(struct lpfc_hba *phba, !(cmdiocbq->iocb_flag & LPFC_IO_LIBDFC)) { lpfc_cmd = container_of(cmdiocbq, struct lpfc_io_buf, cur_iocbq); - lpfc_cmd->exch_busy = rspiocbq->iocb_flag & LPFC_EXCHANGE_BUSY; + if (rspiocbq && (rspiocbq->iocb_flag & LPFC_EXCHANGE_BUSY)) + lpfc_cmd->flags |= LPFC_SBUF_XBUSY; + else + lpfc_cmd->flags &= ~LPFC_SBUF_XBUSY; } pdone_q = cmdiocbq->context_un.wait_queue; @@ -13158,13 +13160,19 @@ lpfc_sli4_sp_handle_mbox_event(struct lpfc_hba *phba, struct lpfc_mcqe *mcqe) phba->sli.sli_flag &= ~LPFC_SLI_MBOX_ACTIVE; /* Setting active mailbox pointer need to be in sync to flag clear */ phba->sli.mbox_active = NULL; + if (bf_get(lpfc_trailer_consumed, mcqe)) + lpfc_sli4_mq_release(phba->sli4_hba.mbx_wq); spin_unlock_irqrestore(&phba->hbalock, iflags); /* Wake up worker thread to post the next pending mailbox command */ lpfc_worker_wake_up(phba); + return workposted; + out_no_mqe_complete: + spin_lock_irqsave(&phba->hbalock, iflags); if (bf_get(lpfc_trailer_consumed, mcqe)) lpfc_sli4_mq_release(phba->sli4_hba.mbx_wq); - return workposted; + spin_unlock_irqrestore(&phba->hbalock, iflags); + return false; } /** @@ -18181,6 +18189,13 @@ lpfc_sli4_alloc_rpi(struct lpfc_hba *phba) static void __lpfc_sli4_free_rpi(struct lpfc_hba *phba, int rpi) { + /* + * if the rpi value indicates a prior unreg has already + * been done, skip the unreg. + */ + if (rpi == LPFC_RPI_ALLOC_ERROR) + return; + if (test_and_clear_bit(rpi, phba->sli4_hba.rpi_bmask)) { phba->sli4_hba.rpi_count--; phba->sli4_hba.max_cfg_param.rpi_used--; diff --git a/drivers/scsi/lpfc/lpfc_sli.h b/drivers/scsi/lpfc/lpfc_sli.h index 37fbcb46387e..7bcf922a8be2 100644 --- a/drivers/scsi/lpfc/lpfc_sli.h +++ b/drivers/scsi/lpfc/lpfc_sli.h @@ -384,14 +384,13 @@ struct lpfc_io_buf { struct lpfc_nodelist *ndlp; uint32_t timeout; - uint16_t flags; /* TBD convert exch_busy to flags */ + uint16_t flags; #define LPFC_SBUF_XBUSY 0x1 /* SLI4 hba reported XB on WCQE cmpl */ #define LPFC_SBUF_BUMP_QDEPTH 0x2 /* bumped queue depth counter */ /* External DIF device IO conversions */ #define LPFC_SBUF_NORMAL_DIF 0x4 /* normal mode to insert/strip */ #define LPFC_SBUF_PASS_DIF 0x8 /* insert/strip mode to passthru */ #define LPFC_SBUF_NOT_POSTED 0x10 /* SGL failed post to FW. */ - uint16_t exch_busy; /* SLI4 hba reported XB on complete WCQE */ uint16_t status; /* From IOCB Word 7- ulpStatus */ uint32_t result; /* From IOCB Word 4. */ diff --git a/drivers/scsi/mac_scsi.c b/drivers/scsi/mac_scsi.c index 9c5566217ef6..b5dde9d0d054 100644 --- a/drivers/scsi/mac_scsi.c +++ b/drivers/scsi/mac_scsi.c @@ -464,7 +464,7 @@ static int __init mac_scsi_probe(struct platform_device *pdev) mac_scsi_template.can_queue = setup_can_queue; if (setup_cmd_per_lun > 0) mac_scsi_template.cmd_per_lun = setup_cmd_per_lun; - if (setup_sg_tablesize >= 0) + if (setup_sg_tablesize > 0) mac_scsi_template.sg_tablesize = setup_sg_tablesize; if (setup_hostid >= 0) mac_scsi_template.this_id = setup_hostid & 7; diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index fea3cb6a090b..752b71cfbe12 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -5234,7 +5234,6 @@ _base_allocate_memory_pools(struct MPT3SAS_ADAPTER *ioc) &ct->chain_buffer_dma); if (!ct->chain_buffer) { ioc_err(ioc, "chain_lookup: pci_pool_alloc failed\n"); - _base_release_memory_pools(ioc); goto out; } } diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c index 7d696952b376..b95f7d062ea4 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c +++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c @@ -778,6 +778,18 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg, case MPI2_FUNCTION_NVME_ENCAPSULATED: { nvme_encap_request = (Mpi26NVMeEncapsulatedRequest_t *)request; + if (!ioc->pcie_sg_lookup) { + dtmprintk(ioc, ioc_info(ioc, + "HBA doesn't support NVMe. Rejecting NVMe Encapsulated request.\n" + )); + + if (ioc->logging_level & MPT_DEBUG_TM) + _debug_dump_mf(nvme_encap_request, + ioc->request_sz/4); + mpt3sas_base_free_smid(ioc, smid); + ret = -EINVAL; + goto out; + } /* * Get the Physical Address of the sense buffer. * Use Error Response buffer address field to hold the sense @@ -1584,7 +1596,8 @@ _ctl_diag_register_2(struct MPT3SAS_ADAPTER *ioc, ioc_err(ioc, "%s: failed allocating memory for diag buffers, requested size(%d)\n", __func__, request_data_sz); mpt3sas_base_free_smid(ioc, smid); - return -ENOMEM; + rc = -ENOMEM; + goto out; } ioc->diag_buffer[buffer_type] = request_data; ioc->diag_buffer_sz[buffer_type] = request_data_sz; diff --git a/drivers/scsi/pm8001/pm80xx_hwi.c b/drivers/scsi/pm8001/pm80xx_hwi.c index 73261902d75d..161bf4760eac 100644 --- a/drivers/scsi/pm8001/pm80xx_hwi.c +++ b/drivers/scsi/pm8001/pm80xx_hwi.c @@ -2382,6 +2382,8 @@ mpi_sata_completion(struct pm8001_hba_info *pm8001_ha, void *piomb) pm8001_printk("task 0x%p done with io_status 0x%x" " resp 0x%x stat 0x%x but aborted by upper layer!\n", t, status, ts->resp, ts->stat)); + if (t->slow_task) + complete(&t->slow_task->completion); pm8001_ccb_task_free(pm8001_ha, t, ccb, tag); } else { spin_unlock_irqrestore(&t->task_state_lock, flags); diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c index 7259bce85e0e..1fbc5c6c6c14 100644 --- a/drivers/scsi/qla2xxx/qla_attr.c +++ b/drivers/scsi/qla2xxx/qla_attr.c @@ -176,6 +176,7 @@ qla2x00_sysfs_read_nvram(struct file *filp, struct kobject *kobj, faddr = ha->flt_region_nvram; if (IS_QLA28XX(ha)) { + qla28xx_get_aux_images(vha, &active_regions); if (active_regions.aux.vpd_nvram == QLA27XX_SECONDARY_IMAGE) faddr = ha->flt_region_nvram_sec; } diff --git a/drivers/scsi/qla2xxx/qla_bsg.c b/drivers/scsi/qla2xxx/qla_bsg.c index 99f0a1a08143..cbaf178fc979 100644 --- a/drivers/scsi/qla2xxx/qla_bsg.c +++ b/drivers/scsi/qla2xxx/qla_bsg.c @@ -2399,7 +2399,7 @@ qla2x00_get_flash_image_status(struct bsg_job *bsg_job) struct qla_active_regions regions = { }; struct active_regions active_regions = { }; - qla28xx_get_aux_images(vha, &active_regions); + qla27xx_get_active_image(vha, &active_regions); regions.global_image = active_regions.global; if (IS_QLA28XX(ha)) { diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index 6ffa9877c28b..1eb3fe281cc3 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -591,19 +591,23 @@ typedef struct srb { */ uint8_t cmd_type; uint8_t pad[3]; - atomic_t ref_count; struct kref cmd_kref; /* need to migrate ref_count over to this */ void *priv; wait_queue_head_t nvme_ls_waitq; struct fc_port *fcport; struct scsi_qla_host *vha; unsigned int start_timer:1; + unsigned int abort:1; + unsigned int aborted:1; + unsigned int completed:1; + uint32_t handle; uint16_t flags; uint16_t type; const char *name; int iocbs; struct qla_qpair *qpair; + struct srb *cmd_sp; struct list_head elem; u32 gen1; /* scratch */ u32 gen2; /* scratch */ @@ -2397,6 +2401,7 @@ typedef struct fc_port { unsigned int id_changed:1; unsigned int scan_needed:1; unsigned int n2n_flag:1; + unsigned int explicit_logout:1; struct completion nvme_del_done; uint32_t nvme_prli_service_param; diff --git a/drivers/scsi/qla2xxx/qla_fw.h b/drivers/scsi/qla2xxx/qla_fw.h index 732bb871c433..dc2366a29665 100644 --- a/drivers/scsi/qla2xxx/qla_fw.h +++ b/drivers/scsi/qla2xxx/qla_fw.h @@ -1523,6 +1523,10 @@ struct qla_flt_header { #define FLT_REG_NVRAM_SEC_28XX_1 0x10F #define FLT_REG_NVRAM_SEC_28XX_2 0x111 #define FLT_REG_NVRAM_SEC_28XX_3 0x113 +#define FLT_REG_MPI_PRI_28XX 0xD3 +#define FLT_REG_MPI_SEC_28XX 0xF0 +#define FLT_REG_PEP_PRI_28XX 0xD1 +#define FLT_REG_PEP_SEC_28XX 0xF1 struct qla_flt_region { uint16_t code; diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c index 5298ed10059f..84bb4a048016 100644 --- a/drivers/scsi/qla2xxx/qla_gs.c +++ b/drivers/scsi/qla2xxx/qla_gs.c @@ -3005,7 +3005,7 @@ static void qla24xx_async_gpsc_sp_done(srb_t *sp, int res) fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE); if (res == QLA_FUNCTION_TIMEOUT) - return; + goto done; if (res == (DID_ERROR << 16)) { /* entry status error */ diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 1d041313ec52..80f276d67c14 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -101,8 +101,22 @@ static void qla24xx_abort_iocb_timeout(void *data) u32 handle; unsigned long flags; + if (sp->cmd_sp) + ql_dbg(ql_dbg_async, sp->vha, 0x507c, + "Abort timeout - cmd hdl=%x, cmd type=%x hdl=%x, type=%x\n", + sp->cmd_sp->handle, sp->cmd_sp->type, + sp->handle, sp->type); + else + ql_dbg(ql_dbg_async, sp->vha, 0x507c, + "Abort timeout 2 - hdl=%x, type=%x\n", + sp->handle, sp->type); + spin_lock_irqsave(qpair->qp_lock_ptr, flags); for (handle = 1; handle < qpair->req->num_outstanding_cmds; handle++) { + if (sp->cmd_sp && (qpair->req->outstanding_cmds[handle] == + sp->cmd_sp)) + qpair->req->outstanding_cmds[handle] = NULL; + /* removing the abort */ if (qpair->req->outstanding_cmds[handle] == sp) { qpair->req->outstanding_cmds[handle] = NULL; @@ -111,6 +125,9 @@ static void qla24xx_abort_iocb_timeout(void *data) } spin_unlock_irqrestore(qpair->qp_lock_ptr, flags); + if (sp->cmd_sp) + sp->cmd_sp->done(sp->cmd_sp, QLA_OS_TIMER_EXPIRED); + abt->u.abt.comp_status = CS_TIMEOUT; sp->done(sp, QLA_OS_TIMER_EXPIRED); } @@ -142,6 +159,7 @@ static int qla24xx_async_abort_cmd(srb_t *cmd_sp, bool wait) sp->type = SRB_ABT_CMD; sp->name = "abort"; sp->qpair = cmd_sp->qpair; + sp->cmd_sp = cmd_sp; if (wait) sp->flags = SRB_WAKEUP_ON_COMP; @@ -516,6 +534,7 @@ static int qla_post_els_plogi_work(struct scsi_qla_host *vha, fc_port_t *fcport) e->u.fcport.fcport = fcport; fcport->flags |= FCF_ASYNC_ACTIVE; + fcport->disc_state = DSC_LOGIN_PEND; return qla2x00_post_work(vha, e); } @@ -1135,19 +1154,18 @@ static void qla24xx_async_gpdb_sp_done(srb_t *sp, int res) "Async done-%s res %x, WWPN %8phC mb[1]=%x mb[2]=%x \n", sp->name, res, fcport->port_name, mb[1], mb[2]); - if (res == QLA_FUNCTION_TIMEOUT) { - dma_pool_free(sp->vha->hw->s_dma_pool, sp->u.iocb_cmd.u.mbx.in, - sp->u.iocb_cmd.u.mbx.in_dma); - return; - } - fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE); + + if (res == QLA_FUNCTION_TIMEOUT) + goto done; + memset(&ea, 0, sizeof(ea)); ea.fcport = fcport; ea.sp = sp; qla24xx_handle_gpdb_event(vha, &ea); +done: dma_pool_free(ha->s_dma_pool, sp->u.iocb_cmd.u.mbx.in, sp->u.iocb_cmd.u.mbx.in_dma); @@ -4830,6 +4848,7 @@ qla2x00_alloc_fcport(scsi_qla_host_t *vha, gfp_t flags) } INIT_WORK(&fcport->del_work, qla24xx_delete_sess_fn); + INIT_WORK(&fcport->free_work, qlt_free_session_done); INIT_WORK(&fcport->reg_work, qla_register_fcport_fn); INIT_LIST_HEAD(&fcport->gnl_entry); INIT_LIST_HEAD(&fcport->list); @@ -4908,14 +4927,8 @@ qla2x00_configure_loop(scsi_qla_host_t *vha) set_bit(RSCN_UPDATE, &flags); clear_bit(LOCAL_LOOP_UPDATE, &flags); - } else if (ha->current_topology == ISP_CFG_N) { - clear_bit(RSCN_UPDATE, &flags); - if (qla_tgt_mode_enabled(vha)) { - /* allow the other side to start the login */ - clear_bit(LOCAL_LOOP_UPDATE, &flags); - set_bit(RELOGIN_NEEDED, &vha->dpc_flags); - } - } else if (ha->current_topology == ISP_CFG_NL) { + } else if (ha->current_topology == ISP_CFG_NL || + ha->current_topology == ISP_CFG_N) { clear_bit(RSCN_UPDATE, &flags); set_bit(LOCAL_LOOP_UPDATE, &flags); } else if (!vha->flags.online || @@ -5032,7 +5045,6 @@ qla2x00_configure_local_loop(scsi_qla_host_t *vha) memcpy(&ha->plogi_els_payld.data, (void *)ha->init_cb, sizeof(ha->plogi_els_payld.data)); - set_bit(RELOGIN_NEEDED, &vha->dpc_flags); } else { ql_dbg(ql_dbg_init, vha, 0x00d1, "PLOGI ELS param read fail.\n"); @@ -9003,8 +9015,6 @@ int qla2xxx_delete_qpair(struct scsi_qla_host *vha, struct qla_qpair *qpair) struct qla_hw_data *ha = qpair->hw; qpair->delete_in_progress = 1; - while (atomic_read(&qpair->ref_count)) - msleep(500); ret = qla25xx_delete_req_que(vha, qpair->req); if (ret != QLA_SUCCESS) diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c index 518eb954cf42..bdf1994251b9 100644 --- a/drivers/scsi/qla2xxx/qla_iocb.c +++ b/drivers/scsi/qla2xxx/qla_iocb.c @@ -2405,11 +2405,19 @@ qla2x00_login_iocb(srb_t *sp, struct mbx_entry *mbx) static void qla24xx_logout_iocb(srb_t *sp, struct logio_entry_24xx *logio) { + u16 control_flags = LCF_COMMAND_LOGO; logio->entry_type = LOGINOUT_PORT_IOCB_TYPE; - logio->control_flags = - cpu_to_le16(LCF_COMMAND_LOGO|LCF_IMPL_LOGO); - if (!sp->fcport->keep_nport_handle) - logio->control_flags |= cpu_to_le16(LCF_FREE_NPORT); + + if (sp->fcport->explicit_logout) { + control_flags |= LCF_EXPL_LOGO|LCF_FREE_NPORT; + } else { + control_flags |= LCF_IMPL_LOGO; + + if (!sp->fcport->keep_nport_handle) + control_flags |= LCF_FREE_NPORT; + } + + logio->control_flags = cpu_to_le16(control_flags); logio->nport_handle = cpu_to_le16(sp->fcport->loop_id); logio->port_id[0] = sp->fcport->d_id.b.al_pa; logio->port_id[1] = sp->fcport->d_id.b.area; @@ -2676,7 +2684,8 @@ qla24xx_els_logo_iocb(srb_t *sp, struct els_entry_24xx *els_iocb) ql_dbg(ql_dbg_io + ql_dbg_buffer, vha, 0x3073, "PLOGI ELS IOCB:\n"); ql_dump_buffer(ql_log_info, vha, 0x0109, - (uint8_t *)els_iocb, 0x70); + (uint8_t *)els_iocb, + sizeof(*els_iocb)); } else { els_iocb->control_flags = 1 << 13; els_iocb->tx_byte_count = @@ -2842,7 +2851,8 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode, ql_dbg(ql_dbg_disc + ql_dbg_buffer, vha, 0x3073, "PLOGI buffer:\n"); ql_dump_buffer(ql_dbg_disc + ql_dbg_buffer, vha, 0x0109, - (uint8_t *)elsio->u.els_plogi.els_plogi_pyld, 0x70); + (uint8_t *)elsio->u.els_plogi.els_plogi_pyld, + sizeof(*elsio->u.els_plogi.els_plogi_pyld)); rval = qla2x00_start_sp(sp); if (rval != QLA_SUCCESS) { diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index 009fd5a33fcd..b3766b1879e3 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -1061,8 +1061,6 @@ qla2x00_async_event(scsi_qla_host_t *vha, struct rsp_que *rsp, uint16_t *mb) ql_dbg(ql_dbg_async, vha, 0x5011, "Asynchronous PORT UPDATE ignored %04x/%04x/%04x.\n", mb[1], mb[2], mb[3]); - - qlt_async_event(mb[0], vha, mb); break; } @@ -1079,8 +1077,6 @@ qla2x00_async_event(scsi_qla_host_t *vha, struct rsp_que *rsp, uint16_t *mb) set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags); set_bit(LOCAL_LOOP_UPDATE, &vha->dpc_flags); set_bit(VP_CONFIG_OK, &vha->vp_flags); - - qlt_async_event(mb[0], vha, mb); break; case MBA_RSCN_UPDATE: /* State Change Registration */ @@ -2466,6 +2462,11 @@ qla2x00_status_entry(scsi_qla_host_t *vha, struct rsp_que *rsp, void *pkt) return; } + if (sp->abort) + sp->aborted = 1; + else + sp->completed = 1; + if (sp->cmd_type != TYPE_SRB) { req->outstanding_cmds[handle] = NULL; ql_dbg(ql_dbg_io, vha, 0x3015, diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index 4a1f21c11758..eac76e934cbe 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -3920,6 +3920,7 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha, vha->d_id.b24 = 0; vha->d_id.b.al_pa = 1; ha->flags.n2n_bigger = 1; + ha->flags.n2n_ae = 0; id.b.al_pa = 2; ql_dbg(ql_dbg_async, vha, 0x5075, @@ -3930,6 +3931,7 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha, "Format 1: Remote login - Waiting for WWPN %8phC.\n", rptid_entry->u.f1.port_name); ha->flags.n2n_bigger = 0; + ha->flags.n2n_ae = 1; } qla24xx_post_newsess_work(vha, &id, rptid_entry->u.f1.port_name, @@ -3941,7 +3943,6 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha, /* if our portname is higher then initiate N2N login */ set_bit(N2N_LOGIN_NEEDED, &vha->dpc_flags); - ha->flags.n2n_ae = 1; return; break; case TOPO_FL: @@ -6287,17 +6288,13 @@ int qla24xx_send_mb_cmd(struct scsi_qla_host *vha, mbx_cmd_t *mcp) case QLA_SUCCESS: ql_dbg(ql_dbg_mbx, vha, 0x119d, "%s: %s done.\n", __func__, sp->name); - sp->free(sp); break; default: ql_dbg(ql_dbg_mbx, vha, 0x119e, "%s: %s Failed. %x.\n", __func__, sp->name, rval); - sp->free(sp); break; } - return rval; - done_free_sp: sp->free(sp); done: diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c index 238240984bc1..eabc5127174e 100644 --- a/drivers/scsi/qla2xxx/qla_mid.c +++ b/drivers/scsi/qla2xxx/qla_mid.c @@ -946,7 +946,7 @@ int qla24xx_control_vp(scsi_qla_host_t *vha, int cmd) sp = qla2x00_get_sp(base_vha, NULL, GFP_KERNEL); if (!sp) - goto done; + return rval; sp->type = SRB_CTRL_VP; sp->name = "ctrl_vp"; @@ -962,7 +962,7 @@ int qla24xx_control_vp(scsi_qla_host_t *vha, int cmd) ql_dbg(ql_dbg_async, vha, 0xffff, "%s: %s Failed submission. %x.\n", __func__, sp->name, rval); - goto done_free_sp; + goto done; } ql_dbg(ql_dbg_vport, vha, 0x113f, "%s hndl %x submitted\n", @@ -980,16 +980,13 @@ int qla24xx_control_vp(scsi_qla_host_t *vha, int cmd) case QLA_SUCCESS: ql_dbg(ql_dbg_vport, vha, 0xffff, "%s: %s done.\n", __func__, sp->name); - goto done_free_sp; + break; default: ql_dbg(ql_dbg_vport, vha, 0xffff, "%s: %s Failed. %x.\n", __func__, sp->name, rval); - goto done_free_sp; + break; } done: - return rval; - -done_free_sp: sp->free(sp); return rval; } diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c index 6cc19e060afc..bfcd02fdf2b8 100644 --- a/drivers/scsi/qla2xxx/qla_nvme.c +++ b/drivers/scsi/qla2xxx/qla_nvme.c @@ -224,8 +224,8 @@ static void qla_nvme_abort_work(struct work_struct *work) if (ha->flags.host_shutting_down) { ql_log(ql_log_info, sp->fcport->vha, 0xffff, - "%s Calling done on sp: %p, type: 0x%x, sp->ref_count: 0x%x\n", - __func__, sp, sp->type, atomic_read(&sp->ref_count)); + "%s Calling done on sp: %p, type: 0x%x\n", + __func__, sp, sp->type); sp->done(sp, 0); goto out; } @@ -610,6 +610,7 @@ static void qla_nvme_remoteport_delete(struct nvme_fc_remote_port *rport) } static struct nvme_fc_port_template qla_nvme_fc_transport = { + .module = THIS_MODULE, .localport_delete = qla_nvme_localport_delete, .remoteport_delete = qla_nvme_remoteport_delete, .create_queue = qla_nvme_alloc_queue, diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 726ad4cbf4a6..06037e3c7854 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -698,11 +698,6 @@ void qla2x00_sp_compl(srb_t *sp, int res) struct scsi_cmnd *cmd = GET_CMD_SP(sp); struct completion *comp = sp->comp; - if (WARN_ON_ONCE(atomic_read(&sp->ref_count) == 0)) - return; - - atomic_dec(&sp->ref_count); - sp->free(sp); cmd->result = res; CMD_SP(cmd) = NULL; @@ -794,11 +789,6 @@ void qla2xxx_qpair_sp_compl(srb_t *sp, int res) struct scsi_cmnd *cmd = GET_CMD_SP(sp); struct completion *comp = sp->comp; - if (WARN_ON_ONCE(atomic_read(&sp->ref_count) == 0)) - return; - - atomic_dec(&sp->ref_count); - sp->free(sp); cmd->result = res; CMD_SP(cmd) = NULL; @@ -903,7 +893,7 @@ qla2xxx_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd) sp->u.scmd.cmd = cmd; sp->type = SRB_SCSI_CMD; - atomic_set(&sp->ref_count, 1); + CMD_SP(cmd) = (void *)sp; sp->free = qla2x00_sp_free_dma; sp->done = qla2x00_sp_compl; @@ -985,18 +975,16 @@ qla2xxx_mqueuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd, sp->u.scmd.cmd = cmd; sp->type = SRB_SCSI_CMD; - atomic_set(&sp->ref_count, 1); CMD_SP(cmd) = (void *)sp; sp->free = qla2xxx_qpair_sp_free_dma; sp->done = qla2xxx_qpair_sp_compl; - sp->qpair = qpair; rval = ha->isp_ops->start_scsi_mq(sp); if (rval != QLA_SUCCESS) { ql_dbg(ql_dbg_io + ql_dbg_verbose, vha, 0x3078, "Start scsi failed rval=%d for cmd=%p.\n", rval, cmd); if (rval == QLA_INTERFACE_ERROR) - goto qc24_fail_command; + goto qc24_free_sp_fail_command; goto qc24_host_busy_free_sp; } @@ -1008,6 +996,11 @@ qla2xxx_mqueuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd, qc24_target_busy: return SCSI_MLQUEUE_TARGET_BUSY; +qc24_free_sp_fail_command: + sp->free(sp); + CMD_SP(cmd) = NULL; + qla2xxx_rel_qpair_sp(sp->qpair, sp); + qc24_fail_command: cmd->scsi_done(cmd); @@ -1184,16 +1177,6 @@ qla2x00_wait_for_chip_reset(scsi_qla_host_t *vha) return return_status; } -static int -sp_get(struct srb *sp) -{ - if (!refcount_inc_not_zero((refcount_t *)&sp->ref_count)) - /* kref get fail */ - return ENXIO; - else - return 0; -} - #define ISP_REG_DISCONNECT 0xffffffffU /************************************************************************** * qla2x00_isp_reg_stat @@ -1249,6 +1232,9 @@ qla2xxx_eh_abort(struct scsi_cmnd *cmd) uint64_t lun; int rval; struct qla_hw_data *ha = vha->hw; + uint32_t ratov_j; + struct qla_qpair *qpair; + unsigned long flags; if (qla2x00_isp_reg_stat(ha)) { ql_log(ql_log_info, vha, 0x8042, @@ -1261,13 +1247,26 @@ qla2xxx_eh_abort(struct scsi_cmnd *cmd) return ret; sp = scsi_cmd_priv(cmd); + qpair = sp->qpair; - if (sp->fcport && sp->fcport->deleted) + if ((sp->fcport && sp->fcport->deleted) || !qpair) return SUCCESS; - /* Return if the command has already finished. */ - if (sp_get(sp)) + spin_lock_irqsave(qpair->qp_lock_ptr, flags); + if (sp->completed) { + spin_unlock_irqrestore(qpair->qp_lock_ptr, flags); return SUCCESS; + } + + if (sp->abort || sp->aborted) { + spin_unlock_irqrestore(qpair->qp_lock_ptr, flags); + return FAILED; + } + + sp->abort = 1; + sp->comp = ∁ + spin_unlock_irqrestore(qpair->qp_lock_ptr, flags); + id = cmd->device->id; lun = cmd->device->lun; @@ -1276,47 +1275,37 @@ qla2xxx_eh_abort(struct scsi_cmnd *cmd) "Aborting from RISC nexus=%ld:%d:%llu sp=%p cmd=%p handle=%x\n", vha->host_no, id, lun, sp, cmd, sp->handle); + /* + * Abort will release the original Command/sp from FW. Let the + * original command call scsi_done. In return, he will wakeup + * this sleeping thread. + */ rval = ha->isp_ops->abort_command(sp); + ql_dbg(ql_dbg_taskm, vha, 0x8003, "Abort command mbx cmd=%p, rval=%x.\n", cmd, rval); + /* Wait for the command completion. */ + ratov_j = ha->r_a_tov/10 * 4 * 1000; + ratov_j = msecs_to_jiffies(ratov_j); switch (rval) { case QLA_SUCCESS: - /* - * The command has been aborted. That means that the firmware - * won't report a completion. - */ - sp->done(sp, DID_ABORT << 16); - ret = SUCCESS; - break; - case QLA_FUNCTION_PARAMETER_ERROR: { - /* Wait for the command completion. */ - uint32_t ratov = ha->r_a_tov/10; - uint32_t ratov_j = msecs_to_jiffies(4 * ratov * 1000); - - WARN_ON_ONCE(sp->comp); - sp->comp = ∁ if (!wait_for_completion_timeout(&comp, ratov_j)) { ql_dbg(ql_dbg_taskm, vha, 0xffff, "%s: Abort wait timer (4 * R_A_TOV[%d]) expired\n", - __func__, ha->r_a_tov); + __func__, ha->r_a_tov/10); ret = FAILED; } else { ret = SUCCESS; } break; - } default: - /* - * Either abort failed or abort and completion raced. Let - * the SCSI core retry the abort in the former case. - */ ret = FAILED; break; } sp->comp = NULL; - atomic_dec(&sp->ref_count); + ql_log(ql_log_info, vha, 0x801c, "Abort command issued nexus=%ld:%d:%llu -- %x.\n", vha->host_no, id, lun, ret); @@ -1708,32 +1697,53 @@ static void qla2x00_abort_srb(struct qla_qpair *qp, srb_t *sp, const int res, scsi_qla_host_t *vha = qp->vha; struct qla_hw_data *ha = vha->hw; int rval; + bool ret_cmd; + uint32_t ratov_j; - if (sp_get(sp)) + if (qla2x00_chip_is_down(vha)) { + sp->done(sp, res); return; + } if (sp->type == SRB_NVME_CMD || sp->type == SRB_NVME_LS || (sp->type == SRB_SCSI_CMD && !ha->flags.eeh_busy && !test_bit(ABORT_ISP_ACTIVE, &vha->dpc_flags) && !qla2x00_isp_reg_stat(ha))) { + if (sp->comp) { + sp->done(sp, res); + return; + } + sp->comp = ∁ + sp->abort = 1; spin_unlock_irqrestore(qp->qp_lock_ptr, *flags); - rval = ha->isp_ops->abort_command(sp); + rval = ha->isp_ops->abort_command(sp); + /* Wait for command completion. */ + ret_cmd = false; + ratov_j = ha->r_a_tov/10 * 4 * 1000; + ratov_j = msecs_to_jiffies(ratov_j); switch (rval) { case QLA_SUCCESS: - sp->done(sp, res); + if (wait_for_completion_timeout(&comp, ratov_j)) { + ql_dbg(ql_dbg_taskm, vha, 0xffff, + "%s: Abort wait timer (4 * R_A_TOV[%d]) expired\n", + __func__, ha->r_a_tov/10); + ret_cmd = true; + } + /* else FW return SP to driver */ break; - case QLA_FUNCTION_PARAMETER_ERROR: - wait_for_completion(&comp); + default: + ret_cmd = true; break; } spin_lock_irqsave(qp->qp_lock_ptr, *flags); - sp->comp = NULL; + if (ret_cmd && (!sp->completed || !sp->aborted)) + sp->done(sp, res); + } else { + sp->done(sp, res); } - - atomic_dec(&sp->ref_count); } static void @@ -1755,7 +1765,6 @@ __qla2x00_abort_all_cmds(struct qla_qpair *qp, int res) for (cnt = 1; cnt < req->num_outstanding_cmds; cnt++) { sp = req->outstanding_cmds[cnt]; if (sp) { - req->outstanding_cmds[cnt] = NULL; switch (sp->cmd_type) { case TYPE_SRB: qla2x00_abort_srb(qp, sp, res, &flags); @@ -1777,6 +1786,7 @@ __qla2x00_abort_all_cmds(struct qla_qpair *qp, int res) default: break; } + req->outstanding_cmds[cnt] = NULL; } } spin_unlock_irqrestore(qp->qp_lock_ptr, flags); @@ -4666,7 +4676,8 @@ qla2x00_mem_free(struct qla_hw_data *ha) ha->sfp_data = NULL; if (ha->flt) - dma_free_coherent(&ha->pdev->dev, SFP_DEV_SIZE, + dma_free_coherent(&ha->pdev->dev, + sizeof(struct qla_flt_header) + FLT_REGIONS_SIZE, ha->flt, ha->flt_dma); ha->flt = NULL; ha->flt_dma = 0; diff --git a/drivers/scsi/qla2xxx/qla_sup.c b/drivers/scsi/qla2xxx/qla_sup.c index f2d5115b2d8d..bbe90354f49b 100644 --- a/drivers/scsi/qla2xxx/qla_sup.c +++ b/drivers/scsi/qla2xxx/qla_sup.c @@ -847,15 +847,15 @@ qla2xxx_get_flt_info(scsi_qla_host_t *vha, uint32_t flt_addr) ha->flt_region_img_status_pri = start; break; case FLT_REG_IMG_SEC_27XX: - if (IS_QLA27XX(ha) && !IS_QLA28XX(ha)) + if (IS_QLA27XX(ha) || IS_QLA28XX(ha)) ha->flt_region_img_status_sec = start; break; case FLT_REG_FW_SEC_27XX: - if (IS_QLA27XX(ha) && !IS_QLA28XX(ha)) + if (IS_QLA27XX(ha) || IS_QLA28XX(ha)) ha->flt_region_fw_sec = start; break; case FLT_REG_BOOTLOAD_SEC_27XX: - if (IS_QLA27XX(ha) && !IS_QLA28XX(ha)) + if (IS_QLA27XX(ha) || IS_QLA28XX(ha)) ha->flt_region_boot_sec = start; break; case FLT_REG_AUX_IMG_PRI_28XX: @@ -2725,8 +2725,11 @@ qla28xx_write_flash_data(scsi_qla_host_t *vha, uint32_t *dwptr, uint32_t faddr, ql_log(ql_log_warn + ql_dbg_verbose, vha, 0xffff, "Region %x is secure\n", region.code); - if (region.code == FLT_REG_FW || - region.code == FLT_REG_FW_SEC_27XX) { + switch (region.code) { + case FLT_REG_FW: + case FLT_REG_FW_SEC_27XX: + case FLT_REG_MPI_PRI_28XX: + case FLT_REG_MPI_SEC_28XX: fw_array = dwptr; /* 1st fw array */ @@ -2757,9 +2760,23 @@ qla28xx_write_flash_data(scsi_qla_host_t *vha, uint32_t *dwptr, uint32_t faddr, buf_size_without_sfub += risc_size; fw_array += risc_size; } - } else { - ql_log(ql_log_warn + ql_dbg_verbose, vha, 0xffff, - "Secure region %x not supported\n", + break; + + case FLT_REG_PEP_PRI_28XX: + case FLT_REG_PEP_SEC_28XX: + fw_array = dwptr; + + /* 1st fw array */ + risc_size = be32_to_cpu(fw_array[3]); + risc_attr = be32_to_cpu(fw_array[9]); + + buf_size_without_sfub = risc_size; + fw_array += risc_size; + break; + + default: + ql_log(ql_log_warn + ql_dbg_verbose, vha, + 0xffff, "Secure region %x not supported\n", region.code); rval = QLA_COMMAND_ERROR; goto done; @@ -2880,7 +2897,7 @@ qla28xx_write_flash_data(scsi_qla_host_t *vha, uint32_t *dwptr, uint32_t faddr, "Sending Secure Flash MB Cmd\n"); rval = qla28xx_secure_flash_update(vha, 0, region.code, buf_size_without_sfub, sfub_dma, - sizeof(struct secure_flash_update_block)); + sizeof(struct secure_flash_update_block) >> 2); if (rval != QLA_SUCCESS) { ql_log(ql_log_warn, vha, 0xffff, "Secure Flash MB Cmd failed %x.", rval); diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index a06e56224a55..74a378a91b71 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -1104,6 +1104,7 @@ void qlt_free_session_done(struct work_struct *work) } } + sess->explicit_logout = 0; spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); sess->free_pending = 0; @@ -1160,7 +1161,6 @@ void qlt_unreg_sess(struct fc_port *sess) sess->last_rscn_gen = sess->rscn_gen; sess->last_login_gen = sess->login_gen; - INIT_WORK(&sess->free_work, qlt_free_session_done); queue_work(sess->vha->hw->wq, &sess->free_work); } EXPORT_SYMBOL(qlt_unreg_sess); @@ -1265,7 +1265,6 @@ void qlt_schedule_sess_for_deletion(struct fc_port *sess) "Scheduling sess %p for deletion %8phC\n", sess, sess->port_name); - INIT_WORK(&sess->del_work, qla24xx_delete_sess_fn); WARN_ON(!queue_work(sess->vha->hw->wq, &sess->del_work)); } @@ -4804,6 +4803,7 @@ static int qlt_handle_login(struct scsi_qla_host *vha, switch (sess->disc_state) { case DSC_DELETED: + case DSC_LOGIN_PEND: qlt_plogi_ack_unref(vha, pla); break; diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c index 042a24314edc..abe7f79bb789 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c @@ -246,6 +246,8 @@ static void tcm_qla2xxx_complete_mcmd(struct work_struct *work) */ static void tcm_qla2xxx_free_mcmd(struct qla_tgt_mgmt_cmd *mcmd) { + if (!mcmd) + return; INIT_WORK(&mcmd->free_work, tcm_qla2xxx_complete_mcmd); queue_work(tcm_qla2xxx_free_wq, &mcmd->free_work); } @@ -348,6 +350,7 @@ static void tcm_qla2xxx_close_session(struct se_session *se_sess) target_sess_cmd_list_set_waiting(se_sess); spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); + sess->explicit_logout = 1; tcm_qla2xxx_put_sess(sess); } diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c index 8c674eca09f1..2323432a0edb 100644 --- a/drivers/scsi/qla4xxx/ql4_os.c +++ b/drivers/scsi/qla4xxx/ql4_os.c @@ -4275,7 +4275,6 @@ static int qla4xxx_mem_alloc(struct scsi_qla_host *ha) return QLA_SUCCESS; mem_alloc_error_exit: - qla4xxx_mem_free(ha); return QLA_ERROR; } diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index d323523f5f9d..32965ec76965 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -5263,6 +5263,11 @@ static int __init scsi_debug_init(void) return -EINVAL; } + if (sdebug_num_tgts < 0) { + pr_err("num_tgts must be >= 0\n"); + return -EINVAL; + } + if (sdebug_guard > 1) { pr_err("guard must be 0 or 1\n"); return -EINVAL; diff --git a/drivers/scsi/scsi_trace.c b/drivers/scsi/scsi_trace.c index 0f17e7dac1b0..07a2425ffa2c 100644 --- a/drivers/scsi/scsi_trace.c +++ b/drivers/scsi/scsi_trace.c @@ -18,15 +18,18 @@ static const char * scsi_trace_rw6(struct trace_seq *p, unsigned char *cdb, int len) { const char *ret = trace_seq_buffer_ptr(p); - sector_t lba = 0, txlen = 0; + u32 lba = 0, txlen; lba |= ((cdb[1] & 0x1F) << 16); lba |= (cdb[2] << 8); lba |= cdb[3]; - txlen = cdb[4]; + /* + * From SBC-2: a TRANSFER LENGTH field set to zero specifies that 256 + * logical blocks shall be read (READ(6)) or written (WRITE(6)). + */ + txlen = cdb[4] ? cdb[4] : 256; - trace_seq_printf(p, "lba=%llu txlen=%llu", - (unsigned long long)lba, (unsigned long long)txlen); + trace_seq_printf(p, "lba=%u txlen=%u", lba, txlen); trace_seq_putc(p, 0); return ret; diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index 417b868d8735..ed8d9709b9b9 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -24,6 +24,8 @@ #define ISCSI_TRANSPORT_VERSION "2.0-870" +#define ISCSI_SEND_MAX_ALLOWED 10 + #define CREATE_TRACE_POINTS #include @@ -3682,6 +3684,7 @@ iscsi_if_rx(struct sk_buff *skb) struct nlmsghdr *nlh; struct iscsi_uevent *ev; uint32_t group; + int retries = ISCSI_SEND_MAX_ALLOWED; nlh = nlmsg_hdr(skb); if (nlh->nlmsg_len < sizeof(*nlh) + sizeof(*ev) || @@ -3712,6 +3715,10 @@ iscsi_if_rx(struct sk_buff *skb) break; err = iscsi_if_send_reply(portid, nlh->nlmsg_type, ev, sizeof(*ev)); + if (err == -EAGAIN && --retries < 0) { + printk(KERN_WARNING "Send reply failed, error %d\n", err); + break; + } } while (err < 0 && err != -ECONNREFUSED && err != -ESRCH); skb_pull(skb, rlen); } diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index ebb40160539f..ac2e88ec1190 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1694,20 +1694,30 @@ static void sd_rescan(struct device *dev) static int sd_compat_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { - struct scsi_device *sdev = scsi_disk(bdev->bd_disk)->device; + struct gendisk *disk = bdev->bd_disk; + struct scsi_disk *sdkp = scsi_disk(disk); + struct scsi_device *sdev = sdkp->device; + void __user *p = compat_ptr(arg); int error; + error = scsi_verify_blk_ioctl(bdev, cmd); + if (error < 0) + return error; + error = scsi_ioctl_block_when_processing_errors(sdev, cmd, (mode & FMODE_NDELAY) != 0); if (error) return error; + + if (is_sed_ioctl(cmd)) + return sed_ioctl(sdkp->opal_dev, cmd, p); /* * Let the static ioctl translation table take care of it. */ if (!sdev->host->hostt->compat_ioctl) return -ENOIOCTLCMD; - return sdev->host->hostt->compat_ioctl(sdev, cmd, (void __user *)arg); + return sdev->host->hostt->compat_ioctl(sdev, cmd, p); } #endif @@ -2192,8 +2202,10 @@ static int sd_read_protection_type(struct scsi_disk *sdkp, unsigned char *buffer u8 type; int ret = 0; - if (scsi_device_protection(sdp) == 0 || (buffer[12] & 1) == 0) + if (scsi_device_protection(sdp) == 0 || (buffer[12] & 1) == 0) { + sdkp->protection_type = 0; return ret; + } type = ((buffer[12] >> 1) & 7) + 1; /* P_TYPE 0 = Type 1 */ diff --git a/drivers/scsi/sun3_scsi.c b/drivers/scsi/sun3_scsi.c index 955e4c938d49..701b842296f0 100644 --- a/drivers/scsi/sun3_scsi.c +++ b/drivers/scsi/sun3_scsi.c @@ -501,7 +501,7 @@ static struct scsi_host_template sun3_scsi_template = { .eh_host_reset_handler = sun3scsi_host_reset, .can_queue = 16, .this_id = 7, - .sg_tablesize = SG_NONE, + .sg_tablesize = 1, .cmd_per_lun = 2, .dma_boundary = PAGE_SIZE - 1, .cmd_size = NCR5380_CMD_SIZE, @@ -523,7 +523,7 @@ static int __init sun3_scsi_probe(struct platform_device *pdev) sun3_scsi_template.can_queue = setup_can_queue; if (setup_cmd_per_lun > 0) sun3_scsi_template.cmd_per_lun = setup_cmd_per_lun; - if (setup_sg_tablesize >= 0) + if (setup_sg_tablesize > 0) sun3_scsi_template.sg_tablesize = setup_sg_tablesize; if (setup_hostid >= 0) sun3_scsi_template.this_id = setup_hostid & 7; diff --git a/drivers/scsi/ufs/cdns-pltfrm.c b/drivers/scsi/ufs/cdns-pltfrm.c index b2af04c57a39..6feeb0faf123 100644 --- a/drivers/scsi/ufs/cdns-pltfrm.c +++ b/drivers/scsi/ufs/cdns-pltfrm.c @@ -99,6 +99,12 @@ static int cdns_ufs_link_startup_notify(struct ufs_hba *hba, */ ufshcd_dme_set(hba, UIC_ARG_MIB(PA_LOCAL_TX_LCC_ENABLE), 0); + /* + * Disabling Autohibern8 feature in cadence UFS + * to mask unexpected interrupt trigger. + */ + hba->ahit = 0; + return 0; } diff --git a/drivers/scsi/ufs/ufs-sysfs.c b/drivers/scsi/ufs/ufs-sysfs.c index 969a36b15897..ad2abc96c0f1 100644 --- a/drivers/scsi/ufs/ufs-sysfs.c +++ b/drivers/scsi/ufs/ufs-sysfs.c @@ -126,13 +126,16 @@ static void ufshcd_auto_hibern8_update(struct ufs_hba *hba, u32 ahit) return; spin_lock_irqsave(hba->host->host_lock, flags); - if (hba->ahit == ahit) - goto out_unlock; - hba->ahit = ahit; - if (!pm_runtime_suspended(hba->dev)) - ufshcd_writel(hba, hba->ahit, REG_AUTO_HIBERNATE_IDLE_TIMER); -out_unlock: + if (hba->ahit != ahit) + hba->ahit = ahit; spin_unlock_irqrestore(hba->host->host_lock, flags); + if (!pm_runtime_suspended(hba->dev)) { + pm_runtime_get_sync(hba->dev); + ufshcd_hold(hba, false); + ufshcd_auto_hibern8_enable(hba); + ufshcd_release(hba); + pm_runtime_put(hba->dev); + } } /* Convert Auto-Hibernate Idle Timer register value to microseconds */ diff --git a/drivers/scsi/ufs/ufs_bsg.c b/drivers/scsi/ufs/ufs_bsg.c index dc2f6d2b46ed..d2197a31abe5 100644 --- a/drivers/scsi/ufs/ufs_bsg.c +++ b/drivers/scsi/ufs/ufs_bsg.c @@ -202,7 +202,7 @@ int ufs_bsg_probe(struct ufs_hba *hba) bsg_dev->parent = get_device(parent); bsg_dev->release = ufs_bsg_node_release; - dev_set_name(bsg_dev, "ufs-bsg"); + dev_set_name(bsg_dev, "ufs-bsg%u", shost->host_no); ret = device_add(bsg_dev); if (ret) diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 11a87f51c442..25a6a25b17a2 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -2986,10 +2986,10 @@ static int __ufshcd_query_descriptor(struct ufs_hba *hba, goto out_unlock; } - hba->dev_cmd.query.descriptor = NULL; *buf_len = be16_to_cpu(response->upiu_res.length); out_unlock: + hba->dev_cmd.query.descriptor = NULL; mutex_unlock(&hba->dev_cmd.lock); out: ufshcd_release(hba); @@ -3885,15 +3885,24 @@ static int __ufshcd_uic_hibern8_enter(struct ufs_hba *hba) ktime_to_us(ktime_sub(ktime_get(), start)), ret); if (ret) { + int err; + dev_err(hba->dev, "%s: hibern8 enter failed. ret = %d\n", __func__, ret); /* - * If link recovery fails then return error so that caller - * don't retry the hibern8 enter again. + * If link recovery fails then return error code returned from + * ufshcd_link_recovery(). + * If link recovery succeeds then return -EAGAIN to attempt + * hibern8 enter retry again. */ - if (ufshcd_link_recovery(hba)) - ret = -ENOLINK; + err = ufshcd_link_recovery(hba); + if (err) { + dev_err(hba->dev, "%s: link recovery failed", __func__); + ret = err; + } else { + ret = -EAGAIN; + } } else ufshcd_vops_hibern8_notify(hba, UIC_CMD_DME_HIBER_ENTER, POST_CHANGE); @@ -3907,7 +3916,7 @@ static int ufshcd_uic_hibern8_enter(struct ufs_hba *hba) for (retries = UIC_HIBERN8_ENTER_RETRIES; retries > 0; retries--) { ret = __ufshcd_uic_hibern8_enter(hba); - if (!ret || ret == -ENOLINK) + if (!ret) goto out; } out: @@ -3941,7 +3950,7 @@ static int ufshcd_uic_hibern8_exit(struct ufs_hba *hba) return ret; } -static void ufshcd_auto_hibern8_enable(struct ufs_hba *hba) +void ufshcd_auto_hibern8_enable(struct ufs_hba *hba) { unsigned long flags; @@ -6881,9 +6890,6 @@ static int ufshcd_probe_hba(struct ufs_hba *hba) /* UniPro link is active now */ ufshcd_set_link_active(hba); - /* Enable Auto-Hibernate if configured */ - ufshcd_auto_hibern8_enable(hba); - ret = ufshcd_verify_dev_init(hba); if (ret) goto out; @@ -6934,6 +6940,9 @@ static int ufshcd_probe_hba(struct ufs_hba *hba) /* set the state as operational after switching to desired gear */ hba->ufshcd_state = UFSHCD_STATE_OPERATIONAL; + /* Enable Auto-Hibernate if configured */ + ufshcd_auto_hibern8_enable(hba); + /* * If we are in error handling context or in power management callbacks * context, no need to scan the host @@ -7950,12 +7959,12 @@ static int ufshcd_resume(struct ufs_hba *hba, enum ufs_pm_op pm_op) if (hba->clk_scaling.is_allowed) ufshcd_resume_clkscaling(hba); - /* Schedule clock gating in case of no access to UFS device yet */ - ufshcd_release(hba); - /* Enable Auto-Hibernate if configured */ ufshcd_auto_hibern8_enable(hba); + /* Schedule clock gating in case of no access to UFS device yet */ + ufshcd_release(hba); + goto out; set_old_link_state: diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h index c94cfda52829..52c9676a1242 100644 --- a/drivers/scsi/ufs/ufshcd.h +++ b/drivers/scsi/ufs/ufshcd.h @@ -916,6 +916,8 @@ int ufshcd_query_attr(struct ufs_hba *hba, enum query_opcode opcode, int ufshcd_query_flag(struct ufs_hba *hba, enum query_opcode opcode, enum flag_idn idn, bool *flag_res); +void ufshcd_auto_hibern8_enable(struct ufs_hba *hba); + #define SD_ASCII_STD true #define SD_RAW false int ufshcd_read_string_desc(struct ufs_hba *hba, u8 desc_index, diff --git a/drivers/scsi/zorro_esp.c b/drivers/scsi/zorro_esp.c index ca8e3abeb2c7..a23a8e5794f5 100644 --- a/drivers/scsi/zorro_esp.c +++ b/drivers/scsi/zorro_esp.c @@ -218,7 +218,14 @@ static int fastlane_esp_irq_pending(struct esp *esp) static u32 zorro_esp_dma_length_limit(struct esp *esp, u32 dma_addr, u32 dma_len) { - return dma_len > 0xFFFF ? 0xFFFF : dma_len; + return dma_len > (1U << 16) ? (1U << 16) : dma_len; +} + +static u32 fastlane_esp_dma_length_limit(struct esp *esp, u32 dma_addr, + u32 dma_len) +{ + /* The old driver used 0xfffc as limit, so do that here too */ + return dma_len > 0xfffc ? 0xfffc : dma_len; } static void zorro_esp_reset_dma(struct esp *esp) @@ -604,7 +611,7 @@ static const struct esp_driver_ops fastlane_esp_ops = { .esp_write8 = zorro_esp_write8, .esp_read8 = zorro_esp_read8, .irq_pending = fastlane_esp_irq_pending, - .dma_length_limit = zorro_esp_dma_length_limit, + .dma_length_limit = fastlane_esp_dma_length_limit, .reset_dma = zorro_esp_reset_dma, .dma_drain = zorro_esp_dma_drain, .dma_invalidate = fastlane_esp_dma_invalidate, diff --git a/drivers/soc/mediatek/mtk-cmdq-helper.c b/drivers/soc/mediatek/mtk-cmdq-helper.c index 7aa0517ff2f3..3c82de5f9417 100644 --- a/drivers/soc/mediatek/mtk-cmdq-helper.c +++ b/drivers/soc/mediatek/mtk-cmdq-helper.c @@ -155,7 +155,7 @@ int cmdq_pkt_write_mask(struct cmdq_pkt *pkt, u8 subsys, err = cmdq_pkt_append_command(pkt, CMDQ_CODE_MASK, 0, ~mask); offset_mask |= CMDQ_WRITE_ENABLE_MASK; } - err |= cmdq_pkt_write(pkt, value, subsys, offset_mask); + err |= cmdq_pkt_write(pkt, subsys, offset_mask, value); return err; } diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c index 13c54eac0cc3..d1839707128a 100644 --- a/drivers/soundwire/intel.c +++ b/drivers/soundwire/intel.c @@ -479,7 +479,10 @@ intel_pdi_shim_configure(struct sdw_intel *sdw, struct sdw_cdns_pdi *pdi) unsigned int link_id = sdw->instance; int pdi_conf = 0; - pdi->intel_alh_id = (link_id * 16) + pdi->num + 5; + /* the Bulk and PCM streams are not contiguous */ + pdi->intel_alh_id = (link_id * 16) + pdi->num + 3; + if (pdi->num >= 2) + pdi->intel_alh_id += 2; /* * Program stream parameters to stream SHIM register @@ -508,7 +511,10 @@ intel_pdi_alh_configure(struct sdw_intel *sdw, struct sdw_cdns_pdi *pdi) unsigned int link_id = sdw->instance; unsigned int conf; - pdi->intel_alh_id = (link_id * 16) + pdi->num + 5; + /* the Bulk and PCM streams are not contiguous */ + pdi->intel_alh_id = (link_id * 16) + pdi->num + 3; + if (pdi->num >= 2) + pdi->intel_alh_id += 2; /* Program Stream config ALH register */ conf = intel_readl(alh, SDW_ALH_STRMZCFG(pdi->intel_alh_id)); diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c index acf318e7330c..abbc1582f457 100644 --- a/drivers/spi/spi-atmel.c +++ b/drivers/spi/spi-atmel.c @@ -302,7 +302,6 @@ struct atmel_spi { bool use_cs_gpios; bool keep_cs; - bool cs_active; u32 fifo_size; }; @@ -1183,10 +1182,8 @@ static int atmel_spi_setup(struct spi_device *spi) as = spi_master_get_devdata(spi->master); /* see notes above re chipselect */ - if (!atmel_spi_is_v2(as) - && spi->chip_select == 0 - && (spi->mode & SPI_CS_HIGH)) { - dev_dbg(&spi->dev, "setup: can't be active-high\n"); + if (!as->use_cs_gpios && (spi->mode & SPI_CS_HIGH)) { + dev_warn(&spi->dev, "setup: non GPIO CS can't be active-high\n"); return -EINVAL; } @@ -1376,11 +1373,9 @@ static int atmel_spi_one_transfer(struct spi_master *master, &msg->transfers)) { as->keep_cs = true; } else { - as->cs_active = !as->cs_active; - if (as->cs_active) - cs_activate(as, msg->spi); - else - cs_deactivate(as, msg->spi); + cs_deactivate(as, msg->spi); + udelay(10); + cs_activate(as, msg->spi); } } @@ -1403,7 +1398,6 @@ static int atmel_spi_transfer_one_message(struct spi_master *master, atmel_spi_lock(as); cs_activate(as, spi); - as->cs_active = true; as->keep_cs = false; msg->status = 0; diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c index c36587b42e95..82a0ee09cbe1 100644 --- a/drivers/spi/spi-cadence.c +++ b/drivers/spi/spi-cadence.c @@ -168,16 +168,16 @@ static void cdns_spi_init_hw(struct cdns_spi *xspi) /** * cdns_spi_chipselect - Select or deselect the chip select line * @spi: Pointer to the spi_device structure - * @enable: Select (1) or deselect (0) the chip select line + * @is_high: Select(0) or deselect (1) the chip select line */ -static void cdns_spi_chipselect(struct spi_device *spi, bool enable) +static void cdns_spi_chipselect(struct spi_device *spi, bool is_high) { struct cdns_spi *xspi = spi_master_get_devdata(spi->master); u32 ctrl_reg; ctrl_reg = cdns_spi_read(xspi, CDNS_SPI_CR); - if (!enable) { + if (is_high) { /* Deselect the slave */ ctrl_reg |= CDNS_SPI_CR_SSCTRL; } else { diff --git a/drivers/spi/spi-cavium-thunderx.c b/drivers/spi/spi-cavium-thunderx.c index d12e149f1a41..fd6b9caffaf0 100644 --- a/drivers/spi/spi-cavium-thunderx.c +++ b/drivers/spi/spi-cavium-thunderx.c @@ -82,6 +82,7 @@ static int thunderx_spi_probe(struct pci_dev *pdev, error: clk_disable_unprepare(p->clk); + pci_release_regions(pdev); spi_master_put(master); return ret; } @@ -96,6 +97,7 @@ static void thunderx_spi_remove(struct pci_dev *pdev) return; clk_disable_unprepare(p->clk); + pci_release_regions(pdev); /* Put everything in a known state. */ writeq(0, p->register_base + OCTEON_SPI_CFG(p)); } diff --git a/drivers/spi/spi-dw.c b/drivers/spi/spi-dw.c index 9a49e073e8b7..45972056ed8c 100644 --- a/drivers/spi/spi-dw.c +++ b/drivers/spi/spi-dw.c @@ -129,10 +129,11 @@ void dw_spi_set_cs(struct spi_device *spi, bool enable) struct dw_spi *dws = spi_controller_get_devdata(spi->controller); struct chip_data *chip = spi_get_ctldata(spi); + /* Chip select logic is inverted from spi_set_cs() */ if (chip && chip->cs_control) - chip->cs_control(enable); + chip->cs_control(!enable); - if (enable) + if (!enable) dw_writel(dws, DW_SPI_SER, BIT(spi->chip_select)); else if (dws->cs_override) dw_writel(dws, DW_SPI_SER, 0); @@ -308,7 +309,8 @@ static int dw_spi_transfer_one(struct spi_controller *master, cr0 = (transfer->bits_per_word - 1) | (chip->type << SPI_FRF_OFFSET) | ((((spi->mode & SPI_CPOL) ? 1 : 0) << SPI_SCOL_OFFSET) | - (((spi->mode & SPI_CPHA) ? 1 : 0) << SPI_SCPH_OFFSET)) + (((spi->mode & SPI_CPHA) ? 1 : 0) << SPI_SCPH_OFFSET) | + (((spi->mode & SPI_LOOP) ? 1 : 0) << SPI_SRL_OFFSET)) | (chip->tmode << SPI_TMOD_OFFSET); /* diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c index bec758e978fb..d47bd26577b3 100644 --- a/drivers/spi/spi-fsl-dspi.c +++ b/drivers/spi/spi-fsl-dspi.c @@ -583,21 +583,14 @@ static void dspi_tcfq_write(struct fsl_dspi *dspi) dspi->tx_cmd |= SPI_PUSHR_CMD_CTCNT; if (dspi->devtype_data->xspi_mode && dspi->bits_per_word > 16) { - /* Write two TX FIFO entries first, and then the corresponding - * CMD FIFO entry. + /* Write the CMD FIFO entry first, and then the two + * corresponding TX FIFO entries. */ u32 data = dspi_pop_tx(dspi); - if (dspi->cur_chip->ctar_val & SPI_CTAR_LSBFE) { - /* LSB */ - tx_fifo_write(dspi, data & 0xFFFF); - tx_fifo_write(dspi, data >> 16); - } else { - /* MSB */ - tx_fifo_write(dspi, data >> 16); - tx_fifo_write(dspi, data & 0xFFFF); - } cmd_fifo_write(dspi); + tx_fifo_write(dspi, data & 0xFFFF); + tx_fifo_write(dspi, data >> 16); } else { /* Write one entry to both TX FIFO and CMD FIFO * simultaneously. diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c index d08e9324140e..3528ed5eea9b 100644 --- a/drivers/spi/spi-fsl-lpspi.c +++ b/drivers/spi/spi-fsl-lpspi.c @@ -938,7 +938,7 @@ static int fsl_lpspi_probe(struct platform_device *pdev) ret = pm_runtime_get_sync(fsl_lpspi->dev); if (ret < 0) { dev_err(fsl_lpspi->dev, "failed to enable clock\n"); - return ret; + goto out_controller_put; } temp = readl(fsl_lpspi->base + IMX7ULP_PARAM); diff --git a/drivers/spi/spi-fsl-qspi.c b/drivers/spi/spi-fsl-qspi.c index c02e24c01136..63c9f7edaf6c 100644 --- a/drivers/spi/spi-fsl-qspi.c +++ b/drivers/spi/spi-fsl-qspi.c @@ -63,6 +63,11 @@ #define QUADSPI_IPCR 0x08 #define QUADSPI_IPCR_SEQID(x) ((x) << 24) +#define QUADSPI_FLSHCR 0x0c +#define QUADSPI_FLSHCR_TCSS_MASK GENMASK(3, 0) +#define QUADSPI_FLSHCR_TCSH_MASK GENMASK(11, 8) +#define QUADSPI_FLSHCR_TDH_MASK GENMASK(17, 16) + #define QUADSPI_BUF3CR 0x1c #define QUADSPI_BUF3CR_ALLMST_MASK BIT(31) #define QUADSPI_BUF3CR_ADATSZ(x) ((x) << 8) @@ -95,6 +100,9 @@ #define QUADSPI_FR 0x160 #define QUADSPI_FR_TFF_MASK BIT(0) +#define QUADSPI_RSER 0x164 +#define QUADSPI_RSER_TFIE BIT(0) + #define QUADSPI_SPTRCLR 0x16c #define QUADSPI_SPTRCLR_IPPTRC BIT(8) #define QUADSPI_SPTRCLR_BFPTRC BIT(0) @@ -112,9 +120,6 @@ #define QUADSPI_LCKER_LOCK BIT(0) #define QUADSPI_LCKER_UNLOCK BIT(1) -#define QUADSPI_RSER 0x164 -#define QUADSPI_RSER_TFIE BIT(0) - #define QUADSPI_LUT_BASE 0x310 #define QUADSPI_LUT_OFFSET (SEQID_LUT * 4 * 4) #define QUADSPI_LUT_REG(idx) \ @@ -181,6 +186,12 @@ */ #define QUADSPI_QUIRK_BASE_INTERNAL BIT(4) +/* + * Controller uses TDH bits in register QUADSPI_FLSHCR. + * They need to be set in accordance with the DDR/SDR mode. + */ +#define QUADSPI_QUIRK_USE_TDH_SETTING BIT(5) + struct fsl_qspi_devtype_data { unsigned int rxfifo; unsigned int txfifo; @@ -209,7 +220,8 @@ static const struct fsl_qspi_devtype_data imx7d_data = { .rxfifo = SZ_128, .txfifo = SZ_512, .ahb_buf_size = SZ_1K, - .quirks = QUADSPI_QUIRK_TKT253890 | QUADSPI_QUIRK_4X_INT_CLK, + .quirks = QUADSPI_QUIRK_TKT253890 | QUADSPI_QUIRK_4X_INT_CLK | + QUADSPI_QUIRK_USE_TDH_SETTING, .little_endian = true, }; @@ -217,7 +229,8 @@ static const struct fsl_qspi_devtype_data imx6ul_data = { .rxfifo = SZ_128, .txfifo = SZ_512, .ahb_buf_size = SZ_1K, - .quirks = QUADSPI_QUIRK_TKT253890 | QUADSPI_QUIRK_4X_INT_CLK, + .quirks = QUADSPI_QUIRK_TKT253890 | QUADSPI_QUIRK_4X_INT_CLK | + QUADSPI_QUIRK_USE_TDH_SETTING, .little_endian = true, }; @@ -275,6 +288,11 @@ static inline int needs_amba_base_offset(struct fsl_qspi *q) return !(q->devtype_data->quirks & QUADSPI_QUIRK_BASE_INTERNAL); } +static inline int needs_tdh_setting(struct fsl_qspi *q) +{ + return q->devtype_data->quirks & QUADSPI_QUIRK_USE_TDH_SETTING; +} + /* * An IC bug makes it necessary to rearrange the 32-bit data. * Later chips, such as IMX6SLX, have fixed this bug. @@ -710,6 +728,16 @@ static int fsl_qspi_default_setup(struct fsl_qspi *q) qspi_writel(q, QUADSPI_MCR_MDIS_MASK | QUADSPI_MCR_RESERVED_MASK, base + QUADSPI_MCR); + /* + * Previous boot stages (BootROM, bootloader) might have used DDR + * mode and did not clear the TDH bits. As we currently use SDR mode + * only, clear the TDH bits if necessary. + */ + if (needs_tdh_setting(q)) + qspi_writel(q, qspi_readl(q, base + QUADSPI_FLSHCR) & + ~QUADSPI_FLSHCR_TDH_MASK, + base + QUADSPI_FLSHCR); + reg = qspi_readl(q, base + QUADSPI_SMPR); qspi_writel(q, reg & ~(QUADSPI_SMPR_FSDLY_MASK | QUADSPI_SMPR_FSPHS_MASK diff --git a/drivers/spi/spi-fsl-spi.c b/drivers/spi/spi-fsl-spi.c index 4b80ace1d137..be7c6ba73072 100644 --- a/drivers/spi/spi-fsl-spi.c +++ b/drivers/spi/spi-fsl-spi.c @@ -612,6 +612,7 @@ static struct spi_master * fsl_spi_probe(struct device *dev, master->setup = fsl_spi_setup; master->cleanup = fsl_spi_cleanup; master->transfer_one_message = fsl_spi_do_one_msg; + master->use_gpio_descriptors = true; mpc8xxx_spi = spi_master_get_devdata(master); mpc8xxx_spi->max_bits_per_word = 32; @@ -728,17 +729,27 @@ static int of_fsl_spi_probe(struct platform_device *ofdev) } } #endif - - pdata->cs_control = fsl_spi_cs_control; + /* + * Handle the case where we have one hardwired (always selected) + * device on the first "chipselect". Else we let the core code + * handle any GPIOs or native chip selects and assign the + * appropriate callback for dealing with the CS lines. This isn't + * supported on the GRLIB variant. + */ + ret = gpiod_count(dev, "cs"); + if (ret <= 0) + pdata->max_chipselect = 1; + else + pdata->cs_control = fsl_spi_cs_control; } ret = of_address_to_resource(np, 0, &mem); if (ret) goto err; - irq = irq_of_parse_and_map(np, 0); - if (!irq) { - ret = -EINVAL; + irq = platform_get_irq(ofdev, 0); + if (irq < 0) { + ret = irq; goto err; } @@ -751,7 +762,6 @@ static int of_fsl_spi_probe(struct platform_device *ofdev) return 0; err: - irq_dispose_mapping(irq); return ret; } diff --git a/drivers/spi/spi-gpio.c b/drivers/spi/spi-gpio.c index 1d3e23ec20a6..f9c5bbb74714 100644 --- a/drivers/spi/spi-gpio.c +++ b/drivers/spi/spi-gpio.c @@ -371,8 +371,10 @@ static int spi_gpio_probe(struct platform_device *pdev) return -ENOMEM; status = devm_add_action_or_reset(&pdev->dev, spi_gpio_put, master); - if (status) + if (status) { + spi_master_put(master); return status; + } if (of_id) status = spi_gpio_probe_dt(pdev, master); diff --git a/drivers/spi/spi-img-spfi.c b/drivers/spi/spi-img-spfi.c index 439b01e4a2c8..f4a8f470aecc 100644 --- a/drivers/spi/spi-img-spfi.c +++ b/drivers/spi/spi-img-spfi.c @@ -673,6 +673,8 @@ static int img_spfi_probe(struct platform_device *pdev) dma_release_channel(spfi->tx_ch); if (spfi->rx_ch) dma_release_channel(spfi->rx_ch); + spfi->tx_ch = NULL; + spfi->rx_ch = NULL; dev_warn(spfi->dev, "Failed to get DMA channels, falling back to PIO mode\n"); } else { master->dma_tx = spfi->tx_ch; diff --git a/drivers/spi/spi-nxp-fspi.c b/drivers/spi/spi-nxp-fspi.c index 501b923f2c27..28ae5229f889 100644 --- a/drivers/spi/spi-nxp-fspi.c +++ b/drivers/spi/spi-nxp-fspi.c @@ -439,7 +439,7 @@ static bool nxp_fspi_supports_op(struct spi_mem *mem, op->data.nbytes > f->devtype_data->txfifo) return false; - return true; + return spi_mem_default_supports_op(mem, op); } /* Instead of busy looping invoke readl_poll_timeout functionality. */ diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c index bb6a14d1ab0f..9f92165fe09f 100644 --- a/drivers/spi/spi-pxa2xx.c +++ b/drivers/spi/spi-pxa2xx.c @@ -1441,6 +1441,10 @@ static const struct pci_device_id pxa2xx_spi_pci_compound_match[] = { { PCI_VDEVICE(INTEL, 0x4b2a), LPSS_BXT_SSP }, { PCI_VDEVICE(INTEL, 0x4b2b), LPSS_BXT_SSP }, { PCI_VDEVICE(INTEL, 0x4b37), LPSS_BXT_SSP }, + /* JSL */ + { PCI_VDEVICE(INTEL, 0x4daa), LPSS_CNL_SSP }, + { PCI_VDEVICE(INTEL, 0x4dab), LPSS_CNL_SSP }, + { PCI_VDEVICE(INTEL, 0x4dfb), LPSS_CNL_SSP }, /* APL */ { PCI_VDEVICE(INTEL, 0x5ac2), LPSS_BXT_SSP }, { PCI_VDEVICE(INTEL, 0x5ac4), LPSS_BXT_SSP }, @@ -1565,7 +1569,13 @@ pxa2xx_spi_init_pdata(struct platform_device *pdev) #endif ssp->clk = devm_clk_get(&pdev->dev, NULL); + if (IS_ERR(ssp->clk)) + return NULL; + ssp->irq = platform_get_irq(pdev, 0); + if (ssp->irq < 0) + return NULL; + ssp->type = type; ssp->pdev = pdev; ssp->port_id = pxa2xx_spi_get_port_id(adev); @@ -1602,6 +1612,11 @@ static int pxa2xx_spi_fw_translate_cs(struct spi_controller *controller, return cs; } +static size_t pxa2xx_spi_max_dma_transfer_size(struct spi_device *spi) +{ + return MAX_DMA_LEN; +} + static int pxa2xx_spi_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -1707,6 +1722,8 @@ static int pxa2xx_spi_probe(struct platform_device *pdev) } else { controller->can_dma = pxa2xx_spi_can_dma; controller->max_dma_len = MAX_DMA_LEN; + controller->max_transfer_size = + pxa2xx_spi_max_dma_transfer_size; } } diff --git a/drivers/spi/spi-rspi.c b/drivers/spi/spi-rspi.c index 15f5723d9f95..7222c7689c3c 100644 --- a/drivers/spi/spi-rspi.c +++ b/drivers/spi/spi-rspi.c @@ -1257,9 +1257,9 @@ static int rspi_probe(struct platform_device *pdev) ctlr->flags = ops->flags; ctlr->dev.of_node = pdev->dev.of_node; - ret = platform_get_irq_byname(pdev, "rx"); + ret = platform_get_irq_byname_optional(pdev, "rx"); if (ret < 0) { - ret = platform_get_irq_byname(pdev, "mux"); + ret = platform_get_irq_byname_optional(pdev, "mux"); if (ret < 0) ret = platform_get_irq(pdev, 0); if (ret >= 0) @@ -1270,10 +1270,6 @@ static int rspi_probe(struct platform_device *pdev) if (ret >= 0) rspi->tx_irq = ret; } - if (ret < 0) { - dev_err(&pdev->dev, "platform_get_irq error\n"); - goto error2; - } if (rspi->rx_irq == rspi->tx_irq) { /* Single multiplexed interrupt */ diff --git a/drivers/spi/spi-sifive.c b/drivers/spi/spi-sifive.c index 35254bdc42c4..f7c1e20432e0 100644 --- a/drivers/spi/spi-sifive.c +++ b/drivers/spi/spi-sifive.c @@ -357,14 +357,14 @@ static int sifive_spi_probe(struct platform_device *pdev) if (!cs_bits) { dev_err(&pdev->dev, "Could not auto probe CS lines\n"); ret = -EINVAL; - goto put_master; + goto disable_clk; } num_cs = ilog2(cs_bits) + 1; if (num_cs > SIFIVE_SPI_MAX_CS) { dev_err(&pdev->dev, "Invalid number of spi slaves\n"); ret = -EINVAL; - goto put_master; + goto disable_clk; } /* Define our master */ @@ -393,7 +393,7 @@ static int sifive_spi_probe(struct platform_device *pdev) dev_name(&pdev->dev), spi); if (ret) { dev_err(&pdev->dev, "Unable to bind to interrupt\n"); - goto put_master; + goto disable_clk; } dev_info(&pdev->dev, "mapped; irq=%d, cs=%d\n", @@ -402,11 +402,13 @@ static int sifive_spi_probe(struct platform_device *pdev) ret = devm_spi_register_master(&pdev->dev, master); if (ret < 0) { dev_err(&pdev->dev, "spi_register_master failed\n"); - goto put_master; + goto disable_clk; } return 0; +disable_clk: + clk_disable_unprepare(spi->clk); put_master: spi_master_put(master); @@ -420,6 +422,7 @@ static int sifive_spi_remove(struct platform_device *pdev) /* Disable all the interrupts just in case */ sifive_spi_write(spi, SIFIVE_SPI_REG_IE, 0); + clk_disable_unprepare(spi->clk); return 0; } diff --git a/drivers/spi/spi-sprd-adi.c b/drivers/spi/spi-sprd-adi.c index 9a051286f120..9613cfe3c0a2 100644 --- a/drivers/spi/spi-sprd-adi.c +++ b/drivers/spi/spi-sprd-adi.c @@ -393,6 +393,9 @@ static int sprd_adi_restart_handler(struct notifier_block *this, val |= BIT_WDG_RUN | BIT_WDG_RST; sprd_adi_write(sadi, sadi->slave_pbase + REG_WDG_CTRL, val); + /* Lock the watchdog */ + sprd_adi_write(sadi, sadi->slave_pbase + REG_WDG_LOCK, ~WDG_UNLOCK_KEY); + mdelay(1000); dev_emerg(sadi->dev, "Unable to restart system\n"); diff --git a/drivers/spi/spi-sprd.c b/drivers/spi/spi-sprd.c index 8c9021b7f7a9..fa597e27be17 100644 --- a/drivers/spi/spi-sprd.c +++ b/drivers/spi/spi-sprd.c @@ -674,7 +674,7 @@ static void sprd_spi_init_hw(struct sprd_spi *ss, struct spi_transfer *t) u16 word_delay, interval; u32 val; - val = readl_relaxed(ss->base + SPRD_SPI_CTL7); + val = readl_relaxed(ss->base + SPRD_SPI_CTL0); val &= ~(SPRD_SPI_SCK_REV | SPRD_SPI_NG_TX | SPRD_SPI_NG_RX); /* Set default chip selection, clock phase and clock polarity */ val |= ss->hw_mode & SPI_CPHA ? SPRD_SPI_NG_RX : SPRD_SPI_NG_TX; diff --git a/drivers/spi/spi-st-ssc4.c b/drivers/spi/spi-st-ssc4.c index 0c24c494f386..77d26d64541a 100644 --- a/drivers/spi/spi-st-ssc4.c +++ b/drivers/spi/spi-st-ssc4.c @@ -381,6 +381,7 @@ static int spi_st_probe(struct platform_device *pdev) return 0; clk_disable: + pm_runtime_disable(&pdev->dev); clk_disable_unprepare(spi_st->clk); put_master: spi_master_put(master); @@ -392,6 +393,8 @@ static int spi_st_remove(struct platform_device *pdev) struct spi_master *master = platform_get_drvdata(pdev); struct spi_st *spi_st = spi_master_get_devdata(master); + pm_runtime_disable(&pdev->dev); + clk_disable_unprepare(spi_st->clk); pinctrl_pm_select_sleep_state(&pdev->dev); diff --git a/drivers/spi/spi-stm32-qspi.c b/drivers/spi/spi-stm32-qspi.c index 9ac6f9fe13cf..4e726929bb4f 100644 --- a/drivers/spi/spi-stm32-qspi.c +++ b/drivers/spi/spi-stm32-qspi.c @@ -528,7 +528,6 @@ static void stm32_qspi_release(struct stm32_qspi *qspi) stm32_qspi_dma_free(qspi); mutex_destroy(&qspi->lock); clk_disable_unprepare(qspi->clk); - spi_master_put(qspi->ctrl); } static int stm32_qspi_probe(struct platform_device *pdev) @@ -626,6 +625,8 @@ static int stm32_qspi_probe(struct platform_device *pdev) err: stm32_qspi_release(qspi); + spi_master_put(qspi->ctrl); + return ret; } diff --git a/drivers/spi/spi-tegra20-slink.c b/drivers/spi/spi-tegra20-slink.c index 111fffc91435..374a2a32edcd 100644 --- a/drivers/spi/spi-tegra20-slink.c +++ b/drivers/spi/spi-tegra20-slink.c @@ -1073,7 +1073,7 @@ static int tegra_slink_probe(struct platform_device *pdev) ret = clk_enable(tspi->clk); if (ret < 0) { dev_err(&pdev->dev, "Clock enable failed %d\n", ret); - goto exit_free_master; + goto exit_clk_unprepare; } spi_irq = platform_get_irq(pdev, 0); @@ -1146,6 +1146,8 @@ static int tegra_slink_probe(struct platform_device *pdev) free_irq(spi_irq, tspi); exit_clk_disable: clk_disable(tspi->clk); +exit_clk_unprepare: + clk_unprepare(tspi->clk); exit_free_master: spi_master_put(master); return ret; @@ -1159,6 +1161,7 @@ static int tegra_slink_remove(struct platform_device *pdev) free_irq(tspi->irq, tspi); clk_disable(tspi->clk); + clk_unprepare(tspi->clk); if (tspi->tx_dma_chan) tegra_slink_deinit_dma_param(tspi, false); diff --git a/drivers/spi/spi-ti-qspi.c b/drivers/spi/spi-ti-qspi.c index 3cb65371ae3b..66dcb6128539 100644 --- a/drivers/spi/spi-ti-qspi.c +++ b/drivers/spi/spi-ti-qspi.c @@ -62,6 +62,7 @@ struct ti_qspi { u32 dc; bool mmap_enabled; + int current_cs; }; #define QSPI_PID (0x0) @@ -487,6 +488,7 @@ static void ti_qspi_enable_memory_map(struct spi_device *spi) MEM_CS_EN(spi->chip_select)); } qspi->mmap_enabled = true; + qspi->current_cs = spi->chip_select; } static void ti_qspi_disable_memory_map(struct spi_device *spi) @@ -498,6 +500,7 @@ static void ti_qspi_disable_memory_map(struct spi_device *spi) regmap_update_bits(qspi->ctrl_base, qspi->ctrl_reg, MEM_CS_MASK, 0); qspi->mmap_enabled = false; + qspi->current_cs = -1; } static void ti_qspi_setup_mmap_read(struct spi_device *spi, u8 opcode, @@ -543,7 +546,7 @@ static int ti_qspi_exec_mem_op(struct spi_mem *mem, mutex_lock(&qspi->list_lock); - if (!qspi->mmap_enabled) + if (!qspi->mmap_enabled || qspi->current_cs != mem->spi->chip_select) ti_qspi_enable_memory_map(mem->spi); ti_qspi_setup_mmap_read(mem->spi, op->cmd.opcode, op->data.buswidth, op->addr.nbytes, op->dummy.nbytes); @@ -799,6 +802,7 @@ static int ti_qspi_probe(struct platform_device *pdev) } } qspi->mmap_enabled = false; + qspi->current_cs = -1; ret = devm_spi_register_master(&pdev->dev, master); if (!ret) diff --git a/drivers/spi/spi-uniphier.c b/drivers/spi/spi-uniphier.c index 47cde1864630..ce9b30112e26 100644 --- a/drivers/spi/spi-uniphier.c +++ b/drivers/spi/spi-uniphier.c @@ -290,25 +290,32 @@ static void uniphier_spi_recv(struct uniphier_spi_priv *priv) } } -static void uniphier_spi_fill_tx_fifo(struct uniphier_spi_priv *priv) +static void uniphier_spi_set_fifo_threshold(struct uniphier_spi_priv *priv, + unsigned int threshold) { - unsigned int fifo_threshold, fill_bytes; u32 val; - fifo_threshold = DIV_ROUND_UP(priv->rx_bytes, - bytes_per_word(priv->bits_per_word)); - fifo_threshold = min(fifo_threshold, SSI_FIFO_DEPTH); - - fill_bytes = fifo_threshold - (priv->rx_bytes - priv->tx_bytes); - - /* set fifo threshold */ val = readl(priv->base + SSI_FC); val &= ~(SSI_FC_TXFTH_MASK | SSI_FC_RXFTH_MASK); - val |= FIELD_PREP(SSI_FC_TXFTH_MASK, fifo_threshold); - val |= FIELD_PREP(SSI_FC_RXFTH_MASK, fifo_threshold); + val |= FIELD_PREP(SSI_FC_TXFTH_MASK, SSI_FIFO_DEPTH - threshold); + val |= FIELD_PREP(SSI_FC_RXFTH_MASK, threshold); writel(val, priv->base + SSI_FC); +} + +static void uniphier_spi_fill_tx_fifo(struct uniphier_spi_priv *priv) +{ + unsigned int fifo_threshold, fill_words; + unsigned int bpw = bytes_per_word(priv->bits_per_word); + + fifo_threshold = DIV_ROUND_UP(priv->rx_bytes, bpw); + fifo_threshold = min(fifo_threshold, SSI_FIFO_DEPTH); + + uniphier_spi_set_fifo_threshold(priv, fifo_threshold); + + fill_words = fifo_threshold - + DIV_ROUND_UP(priv->rx_bytes - priv->tx_bytes, bpw); - while (fill_bytes--) + while (fill_words--) uniphier_spi_send(priv); } diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index f9502dbbb5c1..26b91ee0855d 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -1711,15 +1711,7 @@ static int of_spi_parse_dt(struct spi_controller *ctlr, struct spi_device *spi, spi->mode |= SPI_3WIRE; if (of_property_read_bool(nc, "spi-lsb-first")) spi->mode |= SPI_LSB_FIRST; - - /* - * For descriptors associated with the device, polarity inversion is - * handled in the gpiolib, so all chip selects are "active high" in - * the logical sense, the gpiolib will invert the line if need be. - */ - if (ctlr->use_gpio_descriptors) - spi->mode |= SPI_CS_HIGH; - else if (of_property_read_bool(nc, "spi-cs-high")) + if (of_property_read_bool(nc, "spi-cs-high")) spi->mode |= SPI_CS_HIGH; /* Device DUAL/QUAD mode */ @@ -1783,6 +1775,15 @@ static int of_spi_parse_dt(struct spi_controller *ctlr, struct spi_device *spi, } spi->chip_select = value; + /* + * For descriptors associated with the device, polarity inversion is + * handled in the gpiolib, so all gpio chip selects are "active high" + * in the logical sense, the gpiolib will invert the line if need be. + */ + if ((ctlr->use_gpio_descriptors) && ctlr->cs_gpiods && + ctlr->cs_gpiods[spi->chip_select]) + spi->mode |= SPI_CS_HIGH; + /* Device speed */ rc = of_property_read_u32(nc, "spi-max-frequency", &value); if (rc) { diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c index 255786f2e844..3ea9d8a3e6e8 100644 --- a/drivers/spi/spidev.c +++ b/drivers/spi/spidev.c @@ -627,6 +627,9 @@ static int spidev_release(struct inode *inode, struct file *filp) if (dofree) kfree(spidev); } +#ifdef CONFIG_SPI_SLAVE + spi_slave_abort(spidev->spi); +#endif mutex_unlock(&device_list_lock); return 0; diff --git a/drivers/staging/axis-fifo/Kconfig b/drivers/staging/axis-fifo/Kconfig index 3fffe4d6f327..f180a8e9f58a 100644 --- a/drivers/staging/axis-fifo/Kconfig +++ b/drivers/staging/axis-fifo/Kconfig @@ -4,7 +4,7 @@ # config XIL_AXIS_FIFO tristate "Xilinx AXI-Stream FIFO IP core driver" - depends on OF + depends on OF && HAS_IOMEM help This adds support for the Xilinx AXI-Stream FIFO IP core driver. The AXI Streaming FIFO allows memory mapped access to a AXI Streaming diff --git a/drivers/staging/comedi/drivers/adv_pci1710.c b/drivers/staging/comedi/drivers/adv_pci1710.c index dbff0f7e7cf5..ddc0dc93d08b 100644 --- a/drivers/staging/comedi/drivers/adv_pci1710.c +++ b/drivers/staging/comedi/drivers/adv_pci1710.c @@ -46,8 +46,8 @@ #define PCI171X_RANGE_UNI BIT(4) #define PCI171X_RANGE_GAIN(x) (((x) & 0x7) << 0) #define PCI171X_MUX_REG 0x04 /* W: A/D multiplexor control */ -#define PCI171X_MUX_CHANH(x) (((x) & 0xf) << 8) -#define PCI171X_MUX_CHANL(x) (((x) & 0xf) << 0) +#define PCI171X_MUX_CHANH(x) (((x) & 0xff) << 8) +#define PCI171X_MUX_CHANL(x) (((x) & 0xff) << 0) #define PCI171X_MUX_CHAN(x) (PCI171X_MUX_CHANH(x) | PCI171X_MUX_CHANL(x)) #define PCI171X_STATUS_REG 0x06 /* R: status register */ #define PCI171X_STATUS_IRQ BIT(11) /* 1=IRQ occurred */ diff --git a/drivers/staging/comedi/drivers/gsc_hpdi.c b/drivers/staging/comedi/drivers/gsc_hpdi.c index 4bdf44d82879..dc62db1ee1dd 100644 --- a/drivers/staging/comedi/drivers/gsc_hpdi.c +++ b/drivers/staging/comedi/drivers/gsc_hpdi.c @@ -623,6 +623,11 @@ static int gsc_hpdi_auto_attach(struct comedi_device *dev, dma_alloc_coherent(&pcidev->dev, DMA_BUFFER_SIZE, &devpriv->dio_buffer_phys_addr[i], GFP_KERNEL); + if (!devpriv->dio_buffer[i]) { + dev_warn(dev->class_dev, + "failed to allocate DMA buffer\n"); + return -ENOMEM; + } } /* allocate dma descriptors */ devpriv->dma_desc = dma_alloc_coherent(&pcidev->dev, @@ -630,6 +635,11 @@ static int gsc_hpdi_auto_attach(struct comedi_device *dev, NUM_DMA_DESCRIPTORS, &devpriv->dma_desc_phys_addr, GFP_KERNEL); + if (!devpriv->dma_desc) { + dev_warn(dev->class_dev, + "failed to allocate DMA descriptors\n"); + return -ENOMEM; + } if (devpriv->dma_desc_phys_addr & 0xf) { dev_warn(dev->class_dev, " dma descriptors not quad-word aligned (bug)\n"); diff --git a/drivers/staging/comedi/drivers/usbduxfast.c b/drivers/staging/comedi/drivers/usbduxfast.c index 04bc488385e6..4af012968cb6 100644 --- a/drivers/staging/comedi/drivers/usbduxfast.c +++ b/drivers/staging/comedi/drivers/usbduxfast.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0+ /* - * Copyright (C) 2004-2014 Bernd Porr, mail@berndporr.me.uk + * Copyright (C) 2004-2019 Bernd Porr, mail@berndporr.me.uk */ /* @@ -8,7 +8,7 @@ * Description: University of Stirling USB DAQ & INCITE Technology Limited * Devices: [ITL] USB-DUX-FAST (usbduxfast) * Author: Bernd Porr - * Updated: 10 Oct 2014 + * Updated: 16 Nov 2019 * Status: stable */ @@ -22,6 +22,7 @@ * * * Revision history: + * 1.0: Fixed a rounding error in usbduxfast_ai_cmdtest * 0.9: Dropping the first data packet which seems to be from the last transfer. * Buffer overflows in the FX2 are handed over to comedi. * 0.92: Dropping now 4 packets. The quad buffer has to be emptied. @@ -350,6 +351,7 @@ static int usbduxfast_ai_cmdtest(struct comedi_device *dev, struct comedi_cmd *cmd) { int err = 0; + int err2 = 0; unsigned int steps; unsigned int arg; @@ -399,11 +401,16 @@ static int usbduxfast_ai_cmdtest(struct comedi_device *dev, */ steps = (cmd->convert_arg * 30) / 1000; if (cmd->chanlist_len != 1) - err |= comedi_check_trigger_arg_min(&steps, - MIN_SAMPLING_PERIOD); - err |= comedi_check_trigger_arg_max(&steps, MAX_SAMPLING_PERIOD); - arg = (steps * 1000) / 30; - err |= comedi_check_trigger_arg_is(&cmd->convert_arg, arg); + err2 |= comedi_check_trigger_arg_min(&steps, + MIN_SAMPLING_PERIOD); + else + err2 |= comedi_check_trigger_arg_min(&steps, 1); + err2 |= comedi_check_trigger_arg_max(&steps, MAX_SAMPLING_PERIOD); + if (err2) { + err |= err2; + arg = (steps * 1000) / 30; + err |= comedi_check_trigger_arg_is(&cmd->convert_arg, arg); + } if (cmd->stop_src == TRIG_COUNT) err |= comedi_check_trigger_arg_min(&cmd->stop_arg, 1); diff --git a/drivers/staging/exfat/exfat.h b/drivers/staging/exfat/exfat.h index 3abab33e932c..4973c9edc26e 100644 --- a/drivers/staging/exfat/exfat.h +++ b/drivers/staging/exfat/exfat.h @@ -943,8 +943,8 @@ s32 create_dir(struct inode *inode, struct chain_t *p_dir, s32 create_file(struct inode *inode, struct chain_t *p_dir, struct uni_name_t *p_uniname, u8 mode, struct file_id_t *fid); void remove_file(struct inode *inode, struct chain_t *p_dir, s32 entry); -s32 rename_file(struct inode *inode, struct chain_t *p_dir, s32 old_entry, - struct uni_name_t *p_uniname, struct file_id_t *fid); +s32 exfat_rename_file(struct inode *inode, struct chain_t *p_dir, s32 old_entry, + struct uni_name_t *p_uniname, struct file_id_t *fid); s32 move_file(struct inode *inode, struct chain_t *p_olddir, s32 oldentry, struct chain_t *p_newdir, struct uni_name_t *p_uniname, struct file_id_t *fid); diff --git a/drivers/staging/exfat/exfat_core.c b/drivers/staging/exfat/exfat_core.c index 79174e5c4145..f3774a1912d1 100644 --- a/drivers/staging/exfat/exfat_core.c +++ b/drivers/staging/exfat/exfat_core.c @@ -3381,8 +3381,8 @@ void remove_file(struct inode *inode, struct chain_t *p_dir, s32 entry) fs_func->delete_dir_entry(sb, p_dir, entry, 0, num_entries); } -s32 rename_file(struct inode *inode, struct chain_t *p_dir, s32 oldentry, - struct uni_name_t *p_uniname, struct file_id_t *fid) +s32 exfat_rename_file(struct inode *inode, struct chain_t *p_dir, s32 oldentry, + struct uni_name_t *p_uniname, struct file_id_t *fid) { s32 ret, newentry = -1, num_old_entries, num_new_entries; sector_t sector_old, sector_new; diff --git a/drivers/staging/exfat/exfat_super.c b/drivers/staging/exfat/exfat_super.c index 3b2b0ceb7297..58c7d66060f7 100644 --- a/drivers/staging/exfat/exfat_super.c +++ b/drivers/staging/exfat/exfat_super.c @@ -1308,8 +1308,8 @@ static int ffsMoveFile(struct inode *old_parent_inode, struct file_id_t *fid, fs_set_vol_flags(sb, VOL_DIRTY); if (olddir.dir == newdir.dir) - ret = rename_file(new_parent_inode, &olddir, dentry, &uni_name, - fid); + ret = exfat_rename_file(new_parent_inode, &olddir, dentry, + &uni_name, fid); else ret = move_file(new_parent_inode, &olddir, dentry, &newdir, &uni_name, fid); diff --git a/drivers/staging/fbtft/fbtft-core.c b/drivers/staging/fbtft/fbtft-core.c index a0a67aa517f0..61f0286fb157 100644 --- a/drivers/staging/fbtft/fbtft-core.c +++ b/drivers/staging/fbtft/fbtft-core.c @@ -666,7 +666,7 @@ struct fb_info *fbtft_framebuffer_alloc(struct fbtft_display *display, fbdefio->deferred_io = fbtft_deferred_io; fb_deferred_io_init(info); - strncpy(info->fix.id, dev->driver->name, 16); + snprintf(info->fix.id, sizeof(info->fix.id), "%s", dev->driver->name); info->fix.type = FB_TYPE_PACKED_PIXELS; info->fix.visual = FB_VISUAL_TRUECOLOR; info->fix.xpanstep = 0; diff --git a/drivers/staging/iio/frequency/ad9834.c b/drivers/staging/iio/frequency/ad9834.c index 038d6732c3fd..23026978a5a5 100644 --- a/drivers/staging/iio/frequency/ad9834.c +++ b/drivers/staging/iio/frequency/ad9834.c @@ -417,6 +417,10 @@ static int ad9834_probe(struct spi_device *spi) st = iio_priv(indio_dev); mutex_init(&st->lock); st->mclk = devm_clk_get(&spi->dev, NULL); + if (IS_ERR(st->mclk)) { + ret = PTR_ERR(st->mclk); + goto error_disable_reg; + } ret = clk_prepare_enable(st->mclk); if (ret) { diff --git a/drivers/staging/isdn/gigaset/usb-gigaset.c b/drivers/staging/isdn/gigaset/usb-gigaset.c index 1b9b43659bdf..a20c0bfa68f3 100644 --- a/drivers/staging/isdn/gigaset/usb-gigaset.c +++ b/drivers/staging/isdn/gigaset/usb-gigaset.c @@ -571,8 +571,7 @@ static int gigaset_initcshw(struct cardstate *cs) { struct usb_cardstate *ucs; - cs->hw.usb = ucs = - kmalloc(sizeof(struct usb_cardstate), GFP_KERNEL); + cs->hw.usb = ucs = kzalloc(sizeof(struct usb_cardstate), GFP_KERNEL); if (!ucs) { pr_err("out of memory\n"); return -ENOMEM; @@ -584,9 +583,6 @@ static int gigaset_initcshw(struct cardstate *cs) ucs->bchars[3] = 0; ucs->bchars[4] = 0x11; ucs->bchars[5] = 0x13; - ucs->bulk_out_buffer = NULL; - ucs->bulk_out_urb = NULL; - ucs->read_urb = NULL; tasklet_init(&cs->write_tasklet, gigaset_modem_fill, (unsigned long) cs); @@ -685,6 +681,11 @@ static int gigaset_probe(struct usb_interface *interface, return -ENODEV; } + if (hostif->desc.bNumEndpoints < 2) { + dev_err(&interface->dev, "missing endpoints\n"); + return -ENODEV; + } + dev_info(&udev->dev, "%s: Device matched ... !\n", __func__); /* allocate memory for our device state and initialize it */ @@ -704,6 +705,12 @@ static int gigaset_probe(struct usb_interface *interface, endpoint = &hostif->endpoint[0].desc; + if (!usb_endpoint_is_bulk_out(endpoint)) { + dev_err(&interface->dev, "missing bulk-out endpoint\n"); + retval = -ENODEV; + goto error; + } + buffer_size = le16_to_cpu(endpoint->wMaxPacketSize); ucs->bulk_out_size = buffer_size; ucs->bulk_out_epnum = usb_endpoint_num(endpoint); @@ -723,6 +730,12 @@ static int gigaset_probe(struct usb_interface *interface, endpoint = &hostif->endpoint[1].desc; + if (!usb_endpoint_is_int_in(endpoint)) { + dev_err(&interface->dev, "missing int-in endpoint\n"); + retval = -ENODEV; + goto error; + } + ucs->busy = 0; ucs->read_urb = usb_alloc_urb(0, GFP_KERNEL); diff --git a/drivers/staging/media/hantro/hantro_g1_h264_dec.c b/drivers/staging/media/hantro/hantro_g1_h264_dec.c index 7ab534936843..5f29b7a836db 100644 --- a/drivers/staging/media/hantro/hantro_g1_h264_dec.c +++ b/drivers/staging/media/hantro/hantro_g1_h264_dec.c @@ -34,9 +34,11 @@ static void set_params(struct hantro_ctx *ctx) reg = G1_REG_DEC_CTRL0_DEC_AXI_WR_ID(0x0); if (sps->flags & V4L2_H264_SPS_FLAG_MB_ADAPTIVE_FRAME_FIELD) reg |= G1_REG_DEC_CTRL0_SEQ_MBAFF_E; - reg |= G1_REG_DEC_CTRL0_PICORD_COUNT_E; - if (dec_param->nal_ref_idc) - reg |= G1_REG_DEC_CTRL0_WRITE_MVS_E; + if (sps->profile_idc > 66) { + reg |= G1_REG_DEC_CTRL0_PICORD_COUNT_E; + if (dec_param->nal_ref_idc) + reg |= G1_REG_DEC_CTRL0_WRITE_MVS_E; + } if (!(sps->flags & V4L2_H264_SPS_FLAG_FRAME_MBS_ONLY) && (sps->flags & V4L2_H264_SPS_FLAG_MB_ADAPTIVE_FRAME_FIELD || @@ -61,7 +63,7 @@ static void set_params(struct hantro_ctx *ctx) /* always use the matrix sent from userspace */ reg |= G1_REG_DEC_CTRL2_TYPE1_QUANT_E; - if (slices[0].flags & V4L2_H264_SLICE_FLAG_FIELD_PIC) + if (!(sps->flags & V4L2_H264_SPS_FLAG_FRAME_MBS_ONLY)) reg |= G1_REG_DEC_CTRL2_FIELDPIC_FLAG_E; vdpu_write_relaxed(vpu, reg, G1_REG_DEC_CTRL2); @@ -246,7 +248,7 @@ static void set_buffers(struct hantro_ctx *ctx) vdpu_write_relaxed(vpu, dst_dma, G1_REG_ADDR_DST); /* Higher profiles require DMV buffer appended to reference frames. */ - if (ctrls->sps->profile_idc > 66) { + if (ctrls->sps->profile_idc > 66 && ctrls->decode->nal_ref_idc) { size_t pic_size = ctx->h264_dec.pic_size; size_t mv_offset = round_up(pic_size, 8); diff --git a/drivers/staging/media/hantro/hantro_h264.c b/drivers/staging/media/hantro/hantro_h264.c index 0d758e0c0f99..a9c134204351 100644 --- a/drivers/staging/media/hantro/hantro_h264.c +++ b/drivers/staging/media/hantro/hantro_h264.c @@ -20,7 +20,7 @@ /* Size with u32 units. */ #define CABAC_INIT_BUFFER_SIZE (460 * 2) #define POC_BUFFER_SIZE 34 -#define SCALING_LIST_SIZE (6 * 16 + 6 * 64) +#define SCALING_LIST_SIZE (6 * 16 + 2 * 64) #define POC_CMP(p0, p1) ((p0) < (p1) ? -1 : 1) @@ -194,23 +194,6 @@ static const u32 h264_cabac_table[] = { 0x1f0c2517, 0x1f261440 }; -/* - * NOTE: The scaling lists are in zig-zag order, apply inverse scanning process - * to get the values in matrix order. In addition, the hardware requires bytes - * swapped within each subsequent 4 bytes. Both arrays below include both - * transformations. - */ -static const u32 zig_zag_4x4[] = { - 3, 2, 7, 11, 6, 1, 0, 5, 10, 15, 14, 9, 4, 8, 13, 12 -}; - -static const u32 zig_zag_8x8[] = { - 3, 2, 11, 19, 10, 1, 0, 9, 18, 27, 35, 26, 17, 8, 7, 6, - 15, 16, 25, 34, 43, 51, 42, 33, 24, 23, 14, 5, 4, 13, 22, 31, - 32, 41, 50, 59, 58, 49, 40, 39, 30, 21, 12, 20, 29, 38, 47, 48, - 57, 56, 55, 46, 37, 28, 36, 45, 54, 63, 62, 53, 44, 52, 61, 60 -}; - static void reorder_scaling_list(struct hantro_ctx *ctx) { @@ -218,33 +201,23 @@ reorder_scaling_list(struct hantro_ctx *ctx) const struct v4l2_ctrl_h264_scaling_matrix *scaling = ctrls->scaling; const size_t num_list_4x4 = ARRAY_SIZE(scaling->scaling_list_4x4); const size_t list_len_4x4 = ARRAY_SIZE(scaling->scaling_list_4x4[0]); - const size_t num_list_8x8 = ARRAY_SIZE(scaling->scaling_list_8x8); const size_t list_len_8x8 = ARRAY_SIZE(scaling->scaling_list_8x8[0]); struct hantro_h264_dec_priv_tbl *tbl = ctx->h264_dec.priv.cpu; - u8 *dst = tbl->scaling_list; - const u8 *src; + u32 *dst = (u32 *)tbl->scaling_list; + const u32 *src; int i, j; - BUILD_BUG_ON(ARRAY_SIZE(zig_zag_4x4) != list_len_4x4); - BUILD_BUG_ON(ARRAY_SIZE(zig_zag_8x8) != list_len_8x8); - BUILD_BUG_ON(ARRAY_SIZE(tbl->scaling_list) != - num_list_4x4 * list_len_4x4 + - num_list_8x8 * list_len_8x8); - - src = &scaling->scaling_list_4x4[0][0]; - for (i = 0; i < num_list_4x4; ++i) { - for (j = 0; j < list_len_4x4; ++j) - dst[zig_zag_4x4[j]] = src[j]; - src += list_len_4x4; - dst += list_len_4x4; + for (i = 0; i < num_list_4x4; i++) { + src = (u32 *)&scaling->scaling_list_4x4[i]; + for (j = 0; j < list_len_4x4 / 4; j++) + *dst++ = swab32(src[j]); } - src = &scaling->scaling_list_8x8[0][0]; - for (i = 0; i < num_list_8x8; ++i) { - for (j = 0; j < list_len_8x8; ++j) - dst[zig_zag_8x8[j]] = src[j]; - src += list_len_8x8; - dst += list_len_8x8; + /* Only Intra/Inter Y lists */ + for (i = 0; i < 2; i++) { + src = (u32 *)&scaling->scaling_list_8x8[i]; + for (j = 0; j < list_len_8x8 / 4; j++) + *dst++ = swab32(src[j]); } } @@ -271,6 +244,7 @@ struct hantro_h264_reflist_builder { const struct v4l2_h264_dpb_entry *dpb; s32 pocs[HANTRO_H264_DPB_SIZE]; u8 unordered_reflist[HANTRO_H264_DPB_SIZE]; + int frame_nums[HANTRO_H264_DPB_SIZE]; s32 curpoc; u8 num_valid; }; @@ -294,13 +268,20 @@ static void init_reflist_builder(struct hantro_ctx *ctx, struct hantro_h264_reflist_builder *b) { + const struct v4l2_ctrl_h264_slice_params *slice_params; const struct v4l2_ctrl_h264_decode_params *dec_param; + const struct v4l2_ctrl_h264_sps *sps; struct vb2_v4l2_buffer *buf = hantro_get_dst_buf(ctx); const struct v4l2_h264_dpb_entry *dpb = ctx->h264_dec.dpb; struct vb2_queue *cap_q = &ctx->fh.m2m_ctx->cap_q_ctx.q; + int cur_frame_num, max_frame_num; unsigned int i; dec_param = ctx->h264_dec.ctrls.decode; + slice_params = &ctx->h264_dec.ctrls.slices[0]; + sps = ctx->h264_dec.ctrls.sps; + max_frame_num = 1 << (sps->log2_max_frame_num_minus4 + 4); + cur_frame_num = slice_params->frame_num; memset(b, 0, sizeof(*b)); b->dpb = dpb; @@ -318,6 +299,18 @@ init_reflist_builder(struct hantro_ctx *ctx, continue; buf = to_vb2_v4l2_buffer(vb2_get_buffer(cap_q, buf_idx)); + + /* + * Handle frame_num wraparound as described in section + * '8.2.4.1 Decoding process for picture numbers' of the spec. + * TODO: This logic will have to be adjusted when we start + * supporting interlaced content. + */ + if (dpb[i].frame_num > cur_frame_num) + b->frame_nums[i] = (int)dpb[i].frame_num - max_frame_num; + else + b->frame_nums[i] = dpb[i].frame_num; + b->pocs[i] = get_poc(buf->field, dpb[i].top_field_order_cnt, dpb[i].bottom_field_order_cnt); b->unordered_reflist[b->num_valid] = i; @@ -353,7 +346,7 @@ static int p_ref_list_cmp(const void *ptra, const void *ptrb, const void *data) * ascending order. */ if (!(a->flags & V4L2_H264_DPB_ENTRY_FLAG_LONG_TERM)) - return b->frame_num - a->frame_num; + return builder->frame_nums[idxb] - builder->frame_nums[idxa]; return a->pic_num - b->pic_num; } diff --git a/drivers/staging/media/hantro/hantro_v4l2.c b/drivers/staging/media/hantro/hantro_v4l2.c index 3dae52abb96c..fcf95c1d39ca 100644 --- a/drivers/staging/media/hantro/hantro_v4l2.c +++ b/drivers/staging/media/hantro/hantro_v4l2.c @@ -367,19 +367,26 @@ vidioc_s_fmt_out_mplane(struct file *file, void *priv, struct v4l2_format *f) { struct v4l2_pix_format_mplane *pix_mp = &f->fmt.pix_mp; struct hantro_ctx *ctx = fh_to_ctx(priv); + struct vb2_queue *vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, f->type); const struct hantro_fmt *formats; unsigned int num_fmts; - struct vb2_queue *vq; int ret; - /* Change not allowed if queue is busy. */ - vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, f->type); - if (vb2_is_busy(vq)) - return -EBUSY; + ret = vidioc_try_fmt_out_mplane(file, priv, f); + if (ret) + return ret; if (!hantro_is_encoder_ctx(ctx)) { struct vb2_queue *peer_vq; + /* + * In order to support dynamic resolution change, + * the decoder admits a resolution change, as long + * as the pixelformat remains. Can't be done if streaming. + */ + if (vb2_is_streaming(vq) || (vb2_is_busy(vq) && + pix_mp->pixelformat != ctx->src_fmt.pixelformat)) + return -EBUSY; /* * Since format change on the OUTPUT queue will reset * the CAPTURE queue, we can't allow doing so @@ -389,12 +396,15 @@ vidioc_s_fmt_out_mplane(struct file *file, void *priv, struct v4l2_format *f) V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE); if (vb2_is_busy(peer_vq)) return -EBUSY; + } else { + /* + * The encoder doesn't admit a format change if + * there are OUTPUT buffers allocated. + */ + if (vb2_is_busy(vq)) + return -EBUSY; } - ret = vidioc_try_fmt_out_mplane(file, priv, f); - if (ret) - return ret; - formats = hantro_get_formats(ctx, &num_fmts); ctx->vpu_src_fmt = hantro_find_format(formats, num_fmts, pix_mp->pixelformat); diff --git a/drivers/staging/media/imx/imx-media-capture.c b/drivers/staging/media/imx/imx-media-capture.c index b33a07bc9105..46576e32581f 100644 --- a/drivers/staging/media/imx/imx-media-capture.c +++ b/drivers/staging/media/imx/imx-media-capture.c @@ -26,6 +26,8 @@ #include #include "imx-media.h" +#define IMX_CAPTURE_NAME "imx-capture" + struct capture_priv { struct imx_media_video_dev vdev; @@ -69,8 +71,8 @@ static int vidioc_querycap(struct file *file, void *fh, { struct capture_priv *priv = video_drvdata(file); - strscpy(cap->driver, "imx-media-capture", sizeof(cap->driver)); - strscpy(cap->card, "imx-media-capture", sizeof(cap->card)); + strscpy(cap->driver, IMX_CAPTURE_NAME, sizeof(cap->driver)); + strscpy(cap->card, IMX_CAPTURE_NAME, sizeof(cap->card)); snprintf(cap->bus_info, sizeof(cap->bus_info), "platform:%s", priv->src_sd->name); diff --git a/drivers/staging/media/imx/imx7-mipi-csis.c b/drivers/staging/media/imx/imx7-mipi-csis.c index 73d8354e618c..e50b1f88e25b 100644 --- a/drivers/staging/media/imx/imx7-mipi-csis.c +++ b/drivers/staging/media/imx/imx7-mipi-csis.c @@ -350,6 +350,8 @@ static void mipi_csis_sw_reset(struct csi_state *state) static int mipi_csis_phy_init(struct csi_state *state) { state->mipi_phy_regulator = devm_regulator_get(state->dev, "phy"); + if (IS_ERR(state->mipi_phy_regulator)) + return PTR_ERR(state->mipi_phy_regulator); return regulator_set_voltage(state->mipi_phy_regulator, 1000000, 1000000); @@ -966,7 +968,10 @@ static int mipi_csis_probe(struct platform_device *pdev) return ret; } - mipi_csis_phy_init(state); + ret = mipi_csis_phy_init(state); + if (ret < 0) + return ret; + mipi_csis_phy_reset(state); mem_res = platform_get_resource(pdev, IORESOURCE_MEM, 0); diff --git a/drivers/staging/media/ipu3/include/intel-ipu3.h b/drivers/staging/media/ipu3/include/intel-ipu3.h index c7cd27efac8a..0b1cb9f9cbd1 100644 --- a/drivers/staging/media/ipu3/include/intel-ipu3.h +++ b/drivers/staging/media/ipu3/include/intel-ipu3.h @@ -449,7 +449,7 @@ struct ipu3_uapi_awb_fr_config_s { __u16 reserved1; __u32 bayer_sign; __u8 bayer_nf; - __u8 reserved2[3]; + __u8 reserved2[7]; } __attribute__((aligned(32))) __packed; /** diff --git a/drivers/staging/media/sunxi/cedrus/cedrus.c b/drivers/staging/media/sunxi/cedrus/cedrus.c index 2d3ea8b74dfd..3439f6ad6338 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus.c +++ b/drivers/staging/media/sunxi/cedrus/cedrus.c @@ -357,6 +357,8 @@ static int cedrus_probe(struct platform_device *pdev) dev->mdev.dev = &pdev->dev; strscpy(dev->mdev.model, CEDRUS_NAME, sizeof(dev->mdev.model)); + strscpy(dev->mdev.bus_info, "platform:" CEDRUS_NAME, + sizeof(dev->mdev.bus_info)); media_device_init(&dev->mdev); dev->mdev.ops = &cedrus_m2m_media_ops; diff --git a/drivers/staging/media/sunxi/cedrus/cedrus.h b/drivers/staging/media/sunxi/cedrus/cedrus.h index 2f017a651848..3758a1c4e2d0 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus.h +++ b/drivers/staging/media/sunxi/cedrus/cedrus.h @@ -179,12 +179,16 @@ static inline dma_addr_t cedrus_buf_addr(struct vb2_buffer *buf, static inline dma_addr_t cedrus_dst_buf_addr(struct cedrus_ctx *ctx, int index, unsigned int plane) { - struct vb2_buffer *buf; + struct vb2_buffer *buf = NULL; + struct vb2_queue *vq; if (index < 0) return 0; - buf = ctx->fh.m2m_ctx->cap_q_ctx.q.bufs[index]; + vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE); + if (vq) + buf = vb2_get_buffer(vq, index); + return buf ? cedrus_buf_addr(buf, &ctx->dst_fmt, plane) : 0; } diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_h264.c b/drivers/staging/media/sunxi/cedrus/cedrus_h264.c index d6a782703c9b..c07526c12629 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus_h264.c +++ b/drivers/staging/media/sunxi/cedrus/cedrus_h264.c @@ -96,7 +96,7 @@ static void cedrus_write_frame_list(struct cedrus_ctx *ctx, const struct v4l2_ctrl_h264_decode_params *decode = run->h264.decode_params; const struct v4l2_ctrl_h264_slice_params *slice = run->h264.slice_params; const struct v4l2_ctrl_h264_sps *sps = run->h264.sps; - struct vb2_queue *cap_q = &ctx->fh.m2m_ctx->cap_q_ctx.q; + struct vb2_queue *cap_q; struct cedrus_buffer *output_buf; struct cedrus_dev *dev = ctx->dev; unsigned long used_dpbs = 0; @@ -104,6 +104,8 @@ static void cedrus_write_frame_list(struct cedrus_ctx *ctx, unsigned int output = 0; unsigned int i; + cap_q = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE); + memset(pic_list, 0, sizeof(pic_list)); for (i = 0; i < ARRAY_SIZE(decode->dpb); i++) { @@ -167,12 +169,14 @@ static void _cedrus_write_ref_list(struct cedrus_ctx *ctx, enum cedrus_h264_sram_off sram) { const struct v4l2_ctrl_h264_decode_params *decode = run->h264.decode_params; - struct vb2_queue *cap_q = &ctx->fh.m2m_ctx->cap_q_ctx.q; + struct vb2_queue *cap_q; struct cedrus_dev *dev = ctx->dev; u8 sram_array[CEDRUS_MAX_REF_IDX]; unsigned int i; size_t size; + cap_q = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE); + memset(sram_array, 0, sizeof(sram_array)); for (i = 0; i < num_ref; i++) { @@ -240,8 +244,8 @@ static void cedrus_write_scaling_lists(struct cedrus_ctx *ctx, sizeof(scaling->scaling_list_8x8[0])); cedrus_h264_write_sram(dev, CEDRUS_SRAM_H264_SCALING_LIST_8x8_1, - scaling->scaling_list_8x8[3], - sizeof(scaling->scaling_list_8x8[3])); + scaling->scaling_list_8x8[1], + sizeof(scaling->scaling_list_8x8[1])); cedrus_h264_write_sram(dev, CEDRUS_SRAM_H264_SCALING_LIST_4x4, scaling->scaling_list_4x4, diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_regs.h b/drivers/staging/media/sunxi/cedrus/cedrus_regs.h index ddd29788d685..f9dd8cbf3458 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus_regs.h +++ b/drivers/staging/media/sunxi/cedrus/cedrus_regs.h @@ -10,6 +10,9 @@ #ifndef _CEDRUS_REGS_H_ #define _CEDRUS_REGS_H_ +#define SHIFT_AND_MASK_BITS(v, h, l) \ + (((unsigned long)(v) << (l)) & GENMASK(h, l)) + /* * Common acronyms and contractions used in register descriptions: * * VLD : Variable-Length Decoder @@ -37,8 +40,8 @@ #define VE_PRIMARY_CHROMA_BUF_LEN 0xc4 #define VE_PRIMARY_FB_LINE_STRIDE 0xc8 -#define VE_PRIMARY_FB_LINE_STRIDE_CHROMA(s) (((s) << 16) & GENMASK(31, 16)) -#define VE_PRIMARY_FB_LINE_STRIDE_LUMA(s) (((s) << 0) & GENMASK(15, 0)) +#define VE_PRIMARY_FB_LINE_STRIDE_CHROMA(s) SHIFT_AND_MASK_BITS(s, 31, 16) +#define VE_PRIMARY_FB_LINE_STRIDE_LUMA(s) SHIFT_AND_MASK_BITS(s, 15, 0) #define VE_CHROMA_BUF_LEN 0xe8 @@ -46,7 +49,7 @@ #define VE_SECONDARY_OUT_FMT_EXT (0x01 << 30) #define VE_SECONDARY_OUT_FMT_YU12 (0x02 << 30) #define VE_SECONDARY_OUT_FMT_YV12 (0x03 << 30) -#define VE_CHROMA_BUF_LEN_SDRT(l) ((l) & GENMASK(27, 0)) +#define VE_CHROMA_BUF_LEN_SDRT(l) SHIFT_AND_MASK_BITS(l, 27, 0) #define VE_PRIMARY_OUT_FMT 0xec @@ -69,15 +72,15 @@ #define VE_DEC_MPEG_MP12HDR (VE_ENGINE_DEC_MPEG + 0x00) -#define VE_DEC_MPEG_MP12HDR_SLICE_TYPE(t) (((t) << 28) & GENMASK(30, 28)) +#define VE_DEC_MPEG_MP12HDR_SLICE_TYPE(t) SHIFT_AND_MASK_BITS(t, 30, 28) #define VE_DEC_MPEG_MP12HDR_F_CODE_SHIFT(x, y) (24 - 4 * (y) - 8 * (x)) #define VE_DEC_MPEG_MP12HDR_F_CODE(__x, __y, __v) \ - (((__v) & GENMASK(3, 0)) << VE_DEC_MPEG_MP12HDR_F_CODE_SHIFT(__x, __y)) + (((unsigned long)(__v) & GENMASK(3, 0)) << VE_DEC_MPEG_MP12HDR_F_CODE_SHIFT(__x, __y)) #define VE_DEC_MPEG_MP12HDR_INTRA_DC_PRECISION(p) \ - (((p) << 10) & GENMASK(11, 10)) + SHIFT_AND_MASK_BITS(p, 11, 10) #define VE_DEC_MPEG_MP12HDR_INTRA_PICTURE_STRUCTURE(s) \ - (((s) << 8) & GENMASK(9, 8)) + SHIFT_AND_MASK_BITS(s, 9, 8) #define VE_DEC_MPEG_MP12HDR_TOP_FIELD_FIRST(v) \ ((v) ? BIT(7) : 0) #define VE_DEC_MPEG_MP12HDR_FRAME_PRED_FRAME_DCT(v) \ @@ -98,19 +101,19 @@ #define VE_DEC_MPEG_PICCODEDSIZE (VE_ENGINE_DEC_MPEG + 0x08) #define VE_DEC_MPEG_PICCODEDSIZE_WIDTH(w) \ - ((DIV_ROUND_UP((w), 16) << 8) & GENMASK(15, 8)) + SHIFT_AND_MASK_BITS(DIV_ROUND_UP((w), 16), 15, 8) #define VE_DEC_MPEG_PICCODEDSIZE_HEIGHT(h) \ - ((DIV_ROUND_UP((h), 16) << 0) & GENMASK(7, 0)) + SHIFT_AND_MASK_BITS(DIV_ROUND_UP((h), 16), 7, 0) #define VE_DEC_MPEG_PICBOUNDSIZE (VE_ENGINE_DEC_MPEG + 0x0c) -#define VE_DEC_MPEG_PICBOUNDSIZE_WIDTH(w) (((w) << 16) & GENMASK(27, 16)) -#define VE_DEC_MPEG_PICBOUNDSIZE_HEIGHT(h) (((h) << 0) & GENMASK(11, 0)) +#define VE_DEC_MPEG_PICBOUNDSIZE_WIDTH(w) SHIFT_AND_MASK_BITS(w, 27, 16) +#define VE_DEC_MPEG_PICBOUNDSIZE_HEIGHT(h) SHIFT_AND_MASK_BITS(h, 11, 0) #define VE_DEC_MPEG_MBADDR (VE_ENGINE_DEC_MPEG + 0x10) -#define VE_DEC_MPEG_MBADDR_X(w) (((w) << 8) & GENMASK(15, 8)) -#define VE_DEC_MPEG_MBADDR_Y(h) (((h) << 0) & GENMASK(7, 0)) +#define VE_DEC_MPEG_MBADDR_X(w) SHIFT_AND_MASK_BITS(w, 15, 8) +#define VE_DEC_MPEG_MBADDR_Y(h) SHIFT_AND_MASK_BITS(h, 7, 0) #define VE_DEC_MPEG_CTRL (VE_ENGINE_DEC_MPEG + 0x14) @@ -225,7 +228,7 @@ #define VE_DEC_MPEG_IQMINPUT_FLAG_INTRA (0x01 << 14) #define VE_DEC_MPEG_IQMINPUT_FLAG_NON_INTRA (0x00 << 14) #define VE_DEC_MPEG_IQMINPUT_WEIGHT(i, v) \ - (((v) & GENMASK(7, 0)) | (((i) << 8) & GENMASK(13, 8))) + (SHIFT_AND_MASK_BITS(i, 13, 8) | SHIFT_AND_MASK_BITS(v, 7, 0)) #define VE_DEC_MPEG_ERROR (VE_ENGINE_DEC_MPEG + 0xc4) #define VE_DEC_MPEG_CRTMBADDR (VE_ENGINE_DEC_MPEG + 0xc8) diff --git a/drivers/staging/mt7621-pci/Kconfig b/drivers/staging/mt7621-pci/Kconfig index af928b75a940..ce58042f2f21 100644 --- a/drivers/staging/mt7621-pci/Kconfig +++ b/drivers/staging/mt7621-pci/Kconfig @@ -2,7 +2,6 @@ config PCI_MT7621 tristate "MediaTek MT7621 PCI Controller" depends on RALINK - depends on PCI select PCI_DRIVERS_GENERIC help This selects a driver for the MediaTek MT7621 PCI Controller. diff --git a/drivers/staging/octeon/octeon-ethernet.h b/drivers/staging/octeon/octeon-ethernet.h index a8a864b40913..042220d86d33 100644 --- a/drivers/staging/octeon/octeon-ethernet.h +++ b/drivers/staging/octeon/octeon-ethernet.h @@ -14,7 +14,7 @@ #include #include -#ifdef CONFIG_MIPS +#ifdef CONFIG_CAVIUM_OCTEON_SOC #include diff --git a/drivers/staging/octeon/octeon-stubs.h b/drivers/staging/octeon/octeon-stubs.h index b78ce9eaab85..ae014265064a 100644 --- a/drivers/staging/octeon/octeon-stubs.h +++ b/drivers/staging/octeon/octeon-stubs.h @@ -1,5 +1,8 @@ #define CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE 512 -#define XKPHYS_TO_PHYS(p) (p) + +#ifndef XKPHYS_TO_PHYS +# define XKPHYS_TO_PHYS(p) (p) +#endif #define OCTEON_IRQ_WORKQ0 0 #define OCTEON_IRQ_RML 0 diff --git a/drivers/staging/rtl8188eu/core/rtw_xmit.c b/drivers/staging/rtl8188eu/core/rtw_xmit.c index 952f2ab51347..c37591657bac 100644 --- a/drivers/staging/rtl8188eu/core/rtw_xmit.c +++ b/drivers/staging/rtl8188eu/core/rtw_xmit.c @@ -776,7 +776,7 @@ s32 rtw_make_wlanhdr(struct adapter *padapter, u8 *hdr, struct pkt_attrib *pattr memcpy(pwlanhdr->addr2, get_bssid(pmlmepriv), ETH_ALEN); memcpy(pwlanhdr->addr3, pattrib->src, ETH_ALEN); - if (psta->qos_option) + if (psta && psta->qos_option) qos_option = true; } else if (check_fwstate(pmlmepriv, WIFI_ADHOC_STATE) || check_fwstate(pmlmepriv, WIFI_ADHOC_MASTER_STATE)) { @@ -784,7 +784,7 @@ s32 rtw_make_wlanhdr(struct adapter *padapter, u8 *hdr, struct pkt_attrib *pattr memcpy(pwlanhdr->addr2, pattrib->src, ETH_ALEN); memcpy(pwlanhdr->addr3, get_bssid(pmlmepriv), ETH_ALEN); - if (psta->qos_option) + if (psta && psta->qos_option) qos_option = true; } else { RT_TRACE(_module_rtl871x_xmit_c_, _drv_err_, ("fw_state:%x is not allowed to xmit frame\n", get_fwstate(pmlmepriv))); diff --git a/drivers/staging/rtl8188eu/os_dep/usb_intf.c b/drivers/staging/rtl8188eu/os_dep/usb_intf.c index 4fac9dca798e..b5d42f411dd8 100644 --- a/drivers/staging/rtl8188eu/os_dep/usb_intf.c +++ b/drivers/staging/rtl8188eu/os_dep/usb_intf.c @@ -37,6 +37,7 @@ static const struct usb_device_id rtw_usb_id_tbl[] = { {USB_DEVICE(0x2001, 0x3311)}, /* DLink GO-USB-N150 REV B1 */ {USB_DEVICE(0x2001, 0x331B)}, /* D-Link DWA-121 rev B1 */ {USB_DEVICE(0x2357, 0x010c)}, /* TP-Link TL-WN722N v2 */ + {USB_DEVICE(0x2357, 0x0111)}, /* TP-Link TL-WN727N v5.21 */ {USB_DEVICE(0x0df6, 0x0076)}, /* Sitecom N150 v2 */ {USB_DEVICE(USB_VENDER_ID_REALTEK, 0xffef)}, /* Rosewill RNX-N150NUB */ {} /* Terminating entry */ @@ -70,7 +71,7 @@ static struct dvobj_priv *usb_dvobj_init(struct usb_interface *usb_intf) phost_conf = pusbd->actconfig; pconf_desc = &phost_conf->desc; - phost_iface = &usb_intf->altsetting[0]; + phost_iface = usb_intf->cur_altsetting; piface_desc = &phost_iface->desc; pdvobjpriv->NumInterfaces = pconf_desc->bNumInterfaces; diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index f932cb15e4e5..c702ee9691b1 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -1616,14 +1616,15 @@ static void _rtl92e_hard_data_xmit(struct sk_buff *skb, struct net_device *dev, memcpy((unsigned char *)(skb->cb), &dev, sizeof(dev)); skb_push(skb, priv->rtllib->tx_headroom); ret = _rtl92e_tx(dev, skb); - if (ret != 0) - kfree_skb(skb); if (queue_index != MGNT_QUEUE) { priv->rtllib->stats.tx_bytes += (skb->len - priv->rtllib->tx_headroom); priv->rtllib->stats.tx_packets++; } + + if (ret != 0) + kfree_skb(skb); } static int _rtl92e_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) diff --git a/drivers/staging/rtl8192u/r8192U_core.c b/drivers/staging/rtl8192u/r8192U_core.c index 2821411878ce..511136dce3a4 100644 --- a/drivers/staging/rtl8192u/r8192U_core.c +++ b/drivers/staging/rtl8192u/r8192U_core.c @@ -1422,7 +1422,7 @@ short rtl8192_tx(struct net_device *dev, struct sk_buff *skb) (struct tx_fwinfo_819x_usb *)(skb->data + USB_HWDESC_HEADER_LEN); struct usb_device *udev = priv->udev; int pend; - int status; + int status, rt = -1; struct urb *tx_urb = NULL, *tx_urb_zero = NULL; unsigned int idx_pipe; @@ -1566,8 +1566,10 @@ short rtl8192_tx(struct net_device *dev, struct sk_buff *skb) } if (bSend0Byte) { tx_urb_zero = usb_alloc_urb(0, GFP_ATOMIC); - if (!tx_urb_zero) - return -ENOMEM; + if (!tx_urb_zero) { + rt = -ENOMEM; + goto error; + } usb_fill_bulk_urb(tx_urb_zero, udev, usb_sndbulkpipe(udev, idx_pipe), &zero, 0, tx_zero_isr, dev); @@ -1577,7 +1579,7 @@ short rtl8192_tx(struct net_device *dev, struct sk_buff *skb) "Error TX URB for zero byte %d, error %d", atomic_read(&priv->tx_pending[tcb_desc->queue_index]), status); - return -1; + goto error; } } netif_trans_update(dev); @@ -1588,7 +1590,12 @@ short rtl8192_tx(struct net_device *dev, struct sk_buff *skb) RT_TRACE(COMP_ERR, "Error TX URB %d, error %d", atomic_read(&priv->tx_pending[tcb_desc->queue_index]), status); - return -1; + +error: + dev_kfree_skb_any(skb); + usb_free_urb(tx_urb); + usb_free_urb(tx_urb_zero); + return rt; } static short rtl8192_usb_initendpoints(struct net_device *dev) diff --git a/drivers/staging/rtl8712/usb_intf.c b/drivers/staging/rtl8712/usb_intf.c index ba1288297ee4..a87562f632a7 100644 --- a/drivers/staging/rtl8712/usb_intf.c +++ b/drivers/staging/rtl8712/usb_intf.c @@ -247,7 +247,7 @@ static uint r8712_usb_dvobj_init(struct _adapter *padapter) pdvobjpriv->padapter = padapter; padapter->eeprom_address_size = 6; - phost_iface = &pintf->altsetting[0]; + phost_iface = pintf->cur_altsetting; piface_desc = &phost_iface->desc; pdvobjpriv->nr_endpoint = piface_desc->bNumEndpoints; if (pusbd->speed == USB_SPEED_HIGH) { diff --git a/drivers/staging/rtl8723bs/os_dep/sdio_intf.c b/drivers/staging/rtl8723bs/os_dep/sdio_intf.c index d3784c44f6d0..3784a27641a6 100644 --- a/drivers/staging/rtl8723bs/os_dep/sdio_intf.c +++ b/drivers/staging/rtl8723bs/os_dep/sdio_intf.c @@ -18,18 +18,13 @@ static const struct sdio_device_id sdio_ids[] = { { SDIO_DEVICE(0x024c, 0x0523), }, + { SDIO_DEVICE(0x024c, 0x0525), }, { SDIO_DEVICE(0x024c, 0x0623), }, { SDIO_DEVICE(0x024c, 0x0626), }, { SDIO_DEVICE(0x024c, 0xb723), }, { /* end: all zeroes */ }, }; -static const struct acpi_device_id acpi_ids[] = { - {"OBDA8723", 0x0000}, - {} -}; - MODULE_DEVICE_TABLE(sdio, sdio_ids); -MODULE_DEVICE_TABLE(acpi, acpi_ids); static int rtw_drv_init(struct sdio_func *func, const struct sdio_device_id *id); static void rtw_dev_remove(struct sdio_func *func); diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c index b1595b13dea8..af6bf0736b52 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c @@ -3299,7 +3299,7 @@ static int __init vchiq_driver_init(void) return 0; region_unregister: - platform_driver_unregister(&vchiq_driver); + unregister_chrdev_region(vchiq_devid, 1); class_destroy: class_destroy(vchiq_class); diff --git a/drivers/staging/vt6656/baseband.c b/drivers/staging/vt6656/baseband.c index 8d19ae71e7cc..4e651b698617 100644 --- a/drivers/staging/vt6656/baseband.c +++ b/drivers/staging/vt6656/baseband.c @@ -449,8 +449,8 @@ int vnt_vt3184_init(struct vnt_private *priv) memcpy(array, addr, length); - ret = vnt_control_out(priv, MESSAGE_TYPE_WRITE, 0, - MESSAGE_REQUEST_BBREG, length, array); + ret = vnt_control_out_blocks(priv, VNT_REG_BLOCK_SIZE, + MESSAGE_REQUEST_BBREG, length, array); if (ret) goto end; diff --git a/drivers/staging/vt6656/card.c b/drivers/staging/vt6656/card.c index 56cd77fd9ea0..7958fc165462 100644 --- a/drivers/staging/vt6656/card.c +++ b/drivers/staging/vt6656/card.c @@ -719,7 +719,7 @@ int vnt_radio_power_off(struct vnt_private *priv) */ int vnt_radio_power_on(struct vnt_private *priv) { - int ret = true; + int ret = 0; vnt_exit_deep_sleep(priv); diff --git a/drivers/staging/vt6656/device.h b/drivers/staging/vt6656/device.h index 6074ceda78bf..50e1c8918040 100644 --- a/drivers/staging/vt6656/device.h +++ b/drivers/staging/vt6656/device.h @@ -259,6 +259,7 @@ struct vnt_private { u8 mac_hw; /* netdev */ struct usb_device *usb; + struct usb_interface *intf; u64 tsf_time; u8 rx_rate; diff --git a/drivers/staging/vt6656/main_usb.c b/drivers/staging/vt6656/main_usb.c index 856ba97aec4f..c26882e2bb80 100644 --- a/drivers/staging/vt6656/main_usb.c +++ b/drivers/staging/vt6656/main_usb.c @@ -950,7 +950,7 @@ static const struct ieee80211_ops vnt_mac_ops = { int vnt_init(struct vnt_private *priv) { - if (!(vnt_init_registers(priv))) + if (vnt_init_registers(priv)) return -EAGAIN; SET_IEEE80211_PERM_ADDR(priv->hw, priv->permanent_net_addr); @@ -993,6 +993,7 @@ vt6656_probe(struct usb_interface *intf, const struct usb_device_id *id) priv = hw->priv; priv->hw = hw; priv->usb = udev; + priv->intf = intf; vnt_set_options(priv); diff --git a/drivers/staging/vt6656/usbpipe.c b/drivers/staging/vt6656/usbpipe.c index d3304df6bd53..d977d4777e4f 100644 --- a/drivers/staging/vt6656/usbpipe.c +++ b/drivers/staging/vt6656/usbpipe.c @@ -59,7 +59,9 @@ int vnt_control_out(struct vnt_private *priv, u8 request, u16 value, kfree(usb_buffer); - if (ret >= 0 && ret < (int)length) + if (ret == (int)length) + ret = 0; + else ret = -EIO; end_unlock: @@ -74,6 +76,23 @@ int vnt_control_out_u8(struct vnt_private *priv, u8 reg, u8 reg_off, u8 data) reg_off, reg, sizeof(u8), &data); } +int vnt_control_out_blocks(struct vnt_private *priv, + u16 block, u8 reg, u16 length, u8 *data) +{ + int ret = 0, i; + + for (i = 0; i < length; i += block) { + u16 len = min_t(int, length - i, block); + + ret = vnt_control_out(priv, MESSAGE_TYPE_WRITE, + i, reg, len, data + i); + if (ret) + goto end; + } +end: + return ret; +} + int vnt_control_in(struct vnt_private *priv, u8 request, u16 value, u16 index, u16 length, u8 *buffer) { @@ -103,7 +122,9 @@ int vnt_control_in(struct vnt_private *priv, u8 request, u16 value, kfree(usb_buffer); - if (ret >= 0 && ret < (int)length) + if (ret == (int)length) + ret = 0; + else ret = -EIO; end_unlock: diff --git a/drivers/staging/vt6656/usbpipe.h b/drivers/staging/vt6656/usbpipe.h index 95147ec7b96a..b65d9c01a211 100644 --- a/drivers/staging/vt6656/usbpipe.h +++ b/drivers/staging/vt6656/usbpipe.h @@ -18,6 +18,8 @@ #include "device.h" +#define VNT_REG_BLOCK_SIZE 64 + int vnt_control_out(struct vnt_private *priv, u8 request, u16 value, u16 index, u16 length, u8 *buffer); int vnt_control_in(struct vnt_private *priv, u8 request, u16 value, @@ -26,6 +28,9 @@ int vnt_control_in(struct vnt_private *priv, u8 request, u16 value, int vnt_control_out_u8(struct vnt_private *priv, u8 reg, u8 ref_off, u8 data); int vnt_control_in_u8(struct vnt_private *priv, u8 reg, u8 reg_off, u8 *data); +int vnt_control_out_blocks(struct vnt_private *priv, + u16 block, u8 reg, u16 len, u8 *data); + int vnt_start_interrupt_urb(struct vnt_private *priv); int vnt_submit_rx_urb(struct vnt_private *priv, struct vnt_rcb *rcb); int vnt_tx_context(struct vnt_private *priv, diff --git a/drivers/staging/vt6656/wcmd.c b/drivers/staging/vt6656/wcmd.c index 3eb2f11a5de1..2c5250ca2801 100644 --- a/drivers/staging/vt6656/wcmd.c +++ b/drivers/staging/vt6656/wcmd.c @@ -99,6 +99,7 @@ void vnt_run_command(struct work_struct *work) if (vnt_init(priv)) { /* If fail all ends TODO retry */ dev_err(&priv->usb->dev, "failed to start\n"); + usb_set_intfdata(priv->intf, NULL); ieee80211_free_hw(priv->hw); return; } diff --git a/drivers/staging/wilc1000/wilc_hif.c b/drivers/staging/wilc1000/wilc_hif.c index f2b7d5a1be17..77d0732f451b 100644 --- a/drivers/staging/wilc1000/wilc_hif.c +++ b/drivers/staging/wilc1000/wilc_hif.c @@ -473,20 +473,27 @@ void *wilc_parse_join_bss_param(struct cfg80211_bss *bss, rates_ie = cfg80211_find_ie(WLAN_EID_SUPP_RATES, ies->data, ies->len); if (rates_ie) { rates_len = rates_ie[1]; + if (rates_len > WILC_MAX_RATES_SUPPORTED) + rates_len = WILC_MAX_RATES_SUPPORTED; param->supp_rates[0] = rates_len; memcpy(¶m->supp_rates[1], rates_ie + 2, rates_len); } - supp_rates_ie = cfg80211_find_ie(WLAN_EID_EXT_SUPP_RATES, ies->data, - ies->len); - if (supp_rates_ie) { - if (supp_rates_ie[1] > (WILC_MAX_RATES_SUPPORTED - rates_len)) - param->supp_rates[0] = WILC_MAX_RATES_SUPPORTED; - else - param->supp_rates[0] += supp_rates_ie[1]; + if (rates_len < WILC_MAX_RATES_SUPPORTED) { + supp_rates_ie = cfg80211_find_ie(WLAN_EID_EXT_SUPP_RATES, + ies->data, ies->len); + if (supp_rates_ie) { + u8 ext_rates = supp_rates_ie[1]; - memcpy(¶m->supp_rates[rates_len + 1], supp_rates_ie + 2, - (param->supp_rates[0] - rates_len)); + if (ext_rates > (WILC_MAX_RATES_SUPPORTED - rates_len)) + param->supp_rates[0] = WILC_MAX_RATES_SUPPORTED; + else + param->supp_rates[0] += ext_rates; + + memcpy(¶m->supp_rates[rates_len + 1], + supp_rates_ie + 2, + (param->supp_rates[0] - rates_len)); + } } ht_ie = cfg80211_find_ie(WLAN_EID_HT_CAPABILITY, ies->data, ies->len); diff --git a/drivers/staging/wilc1000/wilc_wfi_cfgoperations.c b/drivers/staging/wilc1000/wilc_wfi_cfgoperations.c index 22f21831649b..c3cd6f389a98 100644 --- a/drivers/staging/wilc1000/wilc_wfi_cfgoperations.c +++ b/drivers/staging/wilc1000/wilc_wfi_cfgoperations.c @@ -1419,8 +1419,10 @@ static int change_virtual_intf(struct wiphy *wiphy, struct net_device *dev, if (vif->iftype == WILC_AP_MODE || vif->iftype == WILC_GO_MODE) wilc_wfi_deinit_mon_interface(wl, true); vif->iftype = WILC_STATION_MODE; - wilc_set_operation_mode(vif, wilc_get_vif_idx(vif), - WILC_STATION_MODE, vif->idx); + + if (wl->initialized) + wilc_set_operation_mode(vif, wilc_get_vif_idx(vif), + WILC_STATION_MODE, vif->idx); memset(priv->assoc_stainfo.sta_associated_bss, 0, WILC_MAX_NUM_STA * ETH_ALEN); @@ -1432,8 +1434,10 @@ static int change_virtual_intf(struct wiphy *wiphy, struct net_device *dev, priv->wdev.iftype = type; vif->monitor_flag = 0; vif->iftype = WILC_CLIENT_MODE; - wilc_set_operation_mode(vif, wilc_get_vif_idx(vif), - WILC_STATION_MODE, vif->idx); + + if (wl->initialized) + wilc_set_operation_mode(vif, wilc_get_vif_idx(vif), + WILC_STATION_MODE, vif->idx); break; case NL80211_IFTYPE_AP: @@ -1450,8 +1454,10 @@ static int change_virtual_intf(struct wiphy *wiphy, struct net_device *dev, dev->ieee80211_ptr->iftype = type; priv->wdev.iftype = type; vif->iftype = WILC_GO_MODE; - wilc_set_operation_mode(vif, wilc_get_vif_idx(vif), - WILC_AP_MODE, vif->idx); + + if (wl->initialized) + wilc_set_operation_mode(vif, wilc_get_vif_idx(vif), + WILC_AP_MODE, vif->idx); break; default: diff --git a/drivers/staging/wlan-ng/Kconfig b/drivers/staging/wlan-ng/Kconfig index ac136663fa8e..082c16a31616 100644 --- a/drivers/staging/wlan-ng/Kconfig +++ b/drivers/staging/wlan-ng/Kconfig @@ -4,6 +4,7 @@ config PRISM2_USB depends on WLAN && USB && CFG80211 select WIRELESS_EXT select WEXT_PRIV + select CRC32 help This is the wlan-ng prism 2.5/3 USB driver for a wide range of old USB wireless devices. diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index d19e051f2bc2..f194ffc4699e 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -1165,7 +1165,9 @@ int iscsit_setup_scsi_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, hdr->cmdsn, be32_to_cpu(hdr->data_length), payload_length, conn->cid); - target_get_sess_cmd(&cmd->se_cmd, true); + if (target_get_sess_cmd(&cmd->se_cmd, true) < 0) + return iscsit_add_reject_cmd(cmd, + ISCSI_REASON_WAITING_FOR_LOGOUT, buf); cmd->sense_reason = transport_lookup_cmd_lun(&cmd->se_cmd, scsilun_to_int(&hdr->lun)); @@ -2002,7 +2004,9 @@ iscsit_handle_task_mgt_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, conn->sess->se_sess, 0, DMA_NONE, TCM_SIMPLE_TAG, cmd->sense_buffer + 2); - target_get_sess_cmd(&cmd->se_cmd, true); + if (target_get_sess_cmd(&cmd->se_cmd, true) < 0) + return iscsit_add_reject_cmd(cmd, + ISCSI_REASON_WAITING_FOR_LOGOUT, buf); /* * TASK_REASSIGN for ERL=2 / connection stays inside of @@ -4232,6 +4236,8 @@ int iscsit_close_connection( * must wait until they have completed. */ iscsit_check_conn_usage_count(conn); + target_sess_cmd_list_set_waiting(sess->se_sess); + target_wait_for_sess_cmds(sess->se_sess); ahash_request_free(conn->conn_tx_hash); if (conn->conn_rx_hash) { diff --git a/drivers/target/iscsi/iscsi_target_auth.c b/drivers/target/iscsi/iscsi_target_auth.c index 51ddca2033e0..8fe9b12a07a4 100644 --- a/drivers/target/iscsi/iscsi_target_auth.c +++ b/drivers/target/iscsi/iscsi_target_auth.c @@ -70,7 +70,7 @@ static int chap_check_algorithm(const char *a_str) if (!token) goto out; - if (!strncmp(token, "5", 1)) { + if (!strcmp(token, "5")) { pr_debug("Selected MD5 Algorithm\n"); kfree(orig); return CHAP_DIGEST_MD5; diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index 6949ea8bc387..51ffd5c002de 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -646,7 +646,9 @@ iblock_alloc_bip(struct se_cmd *cmd, struct bio *bio, } bip->bip_iter.bi_size = bio_integrity_bytes(bi, bio_sectors(bio)); - bip_set_seed(bip, bio->bi_iter.bi_sector); + /* virtual start sector must be in integrity interval units */ + bip_set_seed(bip, bio->bi_iter.bi_sector >> + (bi->interval_exp - SECTOR_SHIFT)); pr_debug("IBLOCK BIP Size: %u Sector: %llu\n", bip->bip_iter.bi_size, (unsigned long long)bip->bip_iter.bi_sector); diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 7f06a62f8661..eda8b4736c15 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -584,6 +584,15 @@ void transport_free_session(struct se_session *se_sess) } EXPORT_SYMBOL(transport_free_session); +static int target_release_res(struct se_device *dev, void *data) +{ + struct se_session *sess = data; + + if (dev->reservation_holder == sess) + target_release_reservation(dev); + return 0; +} + void transport_deregister_session(struct se_session *se_sess) { struct se_portal_group *se_tpg = se_sess->se_tpg; @@ -600,6 +609,12 @@ void transport_deregister_session(struct se_session *se_sess) se_sess->fabric_sess_ptr = NULL; spin_unlock_irqrestore(&se_tpg->session_lock, flags); + /* + * Since the session is being removed, release SPC-2 + * reservations held by the session that is disappearing. + */ + target_for_each_device(target_release_res, se_sess); + pr_debug("TARGET_CORE[%s]: Deregistered fabric_sess\n", se_tpg->se_tpg_tfo->fabric_name); /* diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index d4481cc8958f..c28271817e43 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -304,7 +304,7 @@ static void thermal_zone_device_set_polling(struct thermal_zone_device *tz, &tz->poll_queue, msecs_to_jiffies(delay)); else - cancel_delayed_work_sync(&tz->poll_queue); + cancel_delayed_work(&tz->poll_queue); } static void monitor_thermal_zone(struct thermal_zone_device *tz) @@ -1414,7 +1414,7 @@ void thermal_zone_device_unregister(struct thermal_zone_device *tz) mutex_unlock(&thermal_list_lock); - thermal_zone_device_set_polling(tz, 0); + cancel_delayed_work_sync(&tz->poll_queue); thermal_set_governor(tz, NULL); diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 5ea8db667e83..c5974c9af841 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -168,7 +168,7 @@ static int nvm_validate_and_write(struct tb_switch *sw) static int nvm_authenticate_host(struct tb_switch *sw) { - int ret; + int ret = 0; /* * Root switch NVM upgrade requires that we disconnect the @@ -176,6 +176,8 @@ static int nvm_authenticate_host(struct tb_switch *sw) * already). */ if (!sw->safe_mode) { + u32 status; + ret = tb_domain_disconnect_all_paths(sw->tb); if (ret) return ret; @@ -184,7 +186,16 @@ static int nvm_authenticate_host(struct tb_switch *sw) * everything goes well so getting timeout is expected. */ ret = dma_port_flash_update_auth(sw->dma_port); - return ret == -ETIMEDOUT ? 0 : ret; + if (!ret || ret == -ETIMEDOUT) + return 0; + + /* + * Any error from update auth operation requires power + * cycling of the host router. + */ + tb_sw_warn(sw, "failed to authenticate NVM, power cycling\n"); + if (dma_port_flash_update_auth_status(sw->dma_port, &status) > 0) + nvm_set_auth_status(sw, status); } /* @@ -192,7 +203,7 @@ static int nvm_authenticate_host(struct tb_switch *sw) * switch. */ dma_port_power_cycle(sw->dma_port); - return 0; + return ret; } static int nvm_authenticate_device(struct tb_switch *sw) @@ -200,8 +211,16 @@ static int nvm_authenticate_device(struct tb_switch *sw) int ret, retries = 10; ret = dma_port_flash_update_auth(sw->dma_port); - if (ret && ret != -ETIMEDOUT) + switch (ret) { + case 0: + case -ETIMEDOUT: + case -EACCES: + case -EINVAL: + /* Power cycle is required */ + break; + default: return ret; + } /* * Poll here for the authentication status. It takes some time @@ -1246,8 +1265,6 @@ static ssize_t nvm_authenticate_store(struct device *dev, */ nvm_authenticate_start(sw); ret = nvm_authenticate_host(sw); - if (ret) - nvm_authenticate_complete(sw); } else { ret = nvm_authenticate_device(sw); } @@ -1690,13 +1707,16 @@ static int tb_switch_add_dma_port(struct tb_switch *sw) int ret; switch (sw->generation) { - case 3: - break; - case 2: /* Only root switch can be upgraded */ if (tb_route(sw)) return 0; + + /* fallthrough */ + case 3: + ret = tb_switch_set_uuid(sw); + if (ret) + return ret; break; default: @@ -1720,6 +1740,19 @@ static int tb_switch_add_dma_port(struct tb_switch *sw) if (sw->no_nvm_upgrade) return 0; + /* + * If there is status already set then authentication failed + * when the dma_port_flash_update_auth() returned. Power cycling + * is not needed (it was done already) so only thing we do here + * is to unblock runtime PM of the root port. + */ + nvm_get_auth_status(sw, &status); + if (status) { + if (!tb_route(sw)) + nvm_authenticate_complete(sw); + return 0; + } + /* * Check status of the previous flash authentication. If there * is one we need to power cycle the switch in any case to make @@ -1735,9 +1768,6 @@ static int tb_switch_add_dma_port(struct tb_switch *sw) if (status) { tb_sw_info(sw, "switch flash authentication failed\n"); - ret = tb_switch_set_uuid(sw); - if (ret) - return ret; nvm_set_auth_status(sw, status); } diff --git a/drivers/tty/serdev/core.c b/drivers/tty/serdev/core.c index a0ac16ee6575..a9719858c950 100644 --- a/drivers/tty/serdev/core.c +++ b/drivers/tty/serdev/core.c @@ -582,6 +582,12 @@ static acpi_status acpi_serdev_register_device(struct serdev_controller *ctrl, return AE_OK; } +static const struct acpi_device_id serdev_acpi_devices_blacklist[] = { + { "INT3511", 0 }, + { "INT3512", 0 }, + { }, +}; + static acpi_status acpi_serdev_add_device(acpi_handle handle, u32 level, void *data, void **return_value) { @@ -591,6 +597,10 @@ static acpi_status acpi_serdev_add_device(acpi_handle handle, u32 level, if (acpi_bus_get_device(handle, &adev)) return AE_OK; + /* Skip if black listed */ + if (!acpi_match_device_ids(adev, serdev_acpi_devices_blacklist)) + return AE_OK; + return acpi_serdev_register_device(ctrl, adev); } diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c index 1c72fdc2dd37..51a7d3b19b39 100644 --- a/drivers/tty/serial/8250/8250_dw.c +++ b/drivers/tty/serial/8250/8250_dw.c @@ -386,10 +386,10 @@ static int dw8250_probe(struct platform_device *pdev) { struct uart_8250_port uart = {}, *up = &uart; struct resource *regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); - int irq = platform_get_irq(pdev, 0); struct uart_port *p = &up->port; struct device *dev = &pdev->dev; struct dw8250_data *data; + int irq; int err; u32 val; @@ -398,11 +398,9 @@ static int dw8250_probe(struct platform_device *pdev) return -EINVAL; } - if (irq < 0) { - if (irq != -EPROBE_DEFER) - dev_err(dev, "cannot get irq\n"); + irq = platform_get_irq(pdev, 0); + if (irq < 0) return irq; - } spin_lock_init(&p->lock); p->mapbase = regs->start; diff --git a/drivers/tty/serial/8250/8250_mtk.c b/drivers/tty/serial/8250/8250_mtk.c index b411ba4eb5e9..4d067f515f74 100644 --- a/drivers/tty/serial/8250/8250_mtk.c +++ b/drivers/tty/serial/8250/8250_mtk.c @@ -544,7 +544,7 @@ static int mtk8250_probe(struct platform_device *pdev) pm_runtime_set_active(&pdev->dev); pm_runtime_enable(&pdev->dev); - data->rx_wakeup_irq = platform_get_irq(pdev, 1); + data->rx_wakeup_irq = platform_get_irq_optional(pdev, 1); return 0; } diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index 6adbadd6a56a..8a01d034f9d1 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -745,16 +745,8 @@ static int pci_ni8430_init(struct pci_dev *dev) } /* UART Port Control Register */ -#define NI16550_PCR_OFFSET 0x0f -#define NI16550_PCR_RS422 0x00 -#define NI16550_PCR_ECHO_RS485 0x01 -#define NI16550_PCR_DTR_RS485 0x02 -#define NI16550_PCR_AUTO_RS485 0x03 -#define NI16550_PCR_WIRE_MODE_MASK 0x03 -#define NI16550_PCR_TXVR_ENABLE_BIT BIT(3) -#define NI16550_PCR_RS485_TERMINATION_BIT BIT(6) -#define NI16550_ACR_DTR_AUTO_DTR (0x2 << 3) -#define NI16550_ACR_DTR_MANUAL_DTR (0x0 << 3) +#define NI8430_PORTCON 0x0f +#define NI8430_PORTCON_TXVR_ENABLE (1 << 3) static int pci_ni8430_setup(struct serial_private *priv, @@ -776,117 +768,14 @@ pci_ni8430_setup(struct serial_private *priv, return -ENOMEM; /* enable the transceiver */ - writeb(readb(p + offset + NI16550_PCR_OFFSET) | NI16550_PCR_TXVR_ENABLE_BIT, - p + offset + NI16550_PCR_OFFSET); + writeb(readb(p + offset + NI8430_PORTCON) | NI8430_PORTCON_TXVR_ENABLE, + p + offset + NI8430_PORTCON); iounmap(p); return setup_port(priv, port, bar, offset, board->reg_shift); } -static int pci_ni8431_config_rs485(struct uart_port *port, - struct serial_rs485 *rs485) -{ - u8 pcr, acr; - struct uart_8250_port *up; - - up = container_of(port, struct uart_8250_port, port); - acr = up->acr; - pcr = port->serial_in(port, NI16550_PCR_OFFSET); - pcr &= ~NI16550_PCR_WIRE_MODE_MASK; - - if (rs485->flags & SER_RS485_ENABLED) { - /* RS-485 */ - if ((rs485->flags & SER_RS485_RX_DURING_TX) && - (rs485->flags & SER_RS485_RTS_ON_SEND)) { - dev_dbg(port->dev, "Invalid 2-wire mode\n"); - return -EINVAL; - } - - if (rs485->flags & SER_RS485_RX_DURING_TX) { - /* Echo */ - dev_vdbg(port->dev, "2-wire DTR with echo\n"); - pcr |= NI16550_PCR_ECHO_RS485; - acr |= NI16550_ACR_DTR_MANUAL_DTR; - } else { - /* Auto or DTR */ - if (rs485->flags & SER_RS485_RTS_ON_SEND) { - /* Auto */ - dev_vdbg(port->dev, "2-wire Auto\n"); - pcr |= NI16550_PCR_AUTO_RS485; - acr |= NI16550_ACR_DTR_AUTO_DTR; - } else { - /* DTR-controlled */ - /* No Echo */ - dev_vdbg(port->dev, "2-wire DTR no echo\n"); - pcr |= NI16550_PCR_DTR_RS485; - acr |= NI16550_ACR_DTR_MANUAL_DTR; - } - } - } else { - /* RS-422 */ - dev_vdbg(port->dev, "4-wire\n"); - pcr |= NI16550_PCR_RS422; - acr |= NI16550_ACR_DTR_MANUAL_DTR; - } - - dev_dbg(port->dev, "write pcr: 0x%08x\n", pcr); - port->serial_out(port, NI16550_PCR_OFFSET, pcr); - - up->acr = acr; - port->serial_out(port, UART_SCR, UART_ACR); - port->serial_out(port, UART_ICR, up->acr); - - /* Update the cache. */ - port->rs485 = *rs485; - - return 0; -} - -static int pci_ni8431_setup(struct serial_private *priv, - const struct pciserial_board *board, - struct uart_8250_port *uart, int idx) -{ - u8 pcr, acr; - struct pci_dev *dev = priv->dev; - void __iomem *addr; - unsigned int bar, offset = board->first_offset; - - if (idx >= board->num_ports) - return 1; - - bar = FL_GET_BASE(board->flags); - offset += idx * board->uart_offset; - - addr = pci_ioremap_bar(dev, bar); - if (!addr) - return -ENOMEM; - - /* enable the transceiver */ - writeb(readb(addr + NI16550_PCR_OFFSET) | NI16550_PCR_TXVR_ENABLE_BIT, - addr + NI16550_PCR_OFFSET); - - pcr = readb(addr + NI16550_PCR_OFFSET); - pcr &= ~NI16550_PCR_WIRE_MODE_MASK; - - /* set wire mode to default RS-422 */ - pcr |= NI16550_PCR_RS422; - acr = NI16550_ACR_DTR_MANUAL_DTR; - - /* write port configuration to register */ - writeb(pcr, addr + NI16550_PCR_OFFSET); - - /* access and write to UART acr register */ - writeb(UART_ACR, addr + UART_SCR); - writeb(acr, addr + UART_ICR); - - uart->port.rs485_config = &pci_ni8431_config_rs485; - - iounmap(addr); - - return setup_port(priv, uart, bar, offset, board->reg_shift); -} - static int pci_netmos_9900_setup(struct serial_private *priv, const struct pciserial_board *board, struct uart_8250_port *port, int idx) @@ -2023,15 +1912,6 @@ pci_moxa_setup(struct serial_private *priv, #define PCI_DEVICE_ID_ACCESIO_PCIE_COM_8SM 0x10E9 #define PCI_DEVICE_ID_ACCESIO_PCIE_ICM_4SM 0x11D8 -#define PCIE_DEVICE_ID_NI_PXIE8430_2328 0x74C2 -#define PCIE_DEVICE_ID_NI_PXIE8430_23216 0x74C1 -#define PCI_DEVICE_ID_NI_PXI8431_4852 0x7081 -#define PCI_DEVICE_ID_NI_PXI8431_4854 0x70DE -#define PCI_DEVICE_ID_NI_PXI8431_4858 0x70E3 -#define PCI_DEVICE_ID_NI_PXI8433_4852 0x70E9 -#define PCI_DEVICE_ID_NI_PXI8433_4854 0x70ED -#define PCIE_DEVICE_ID_NI_PXIE8431_4858 0x74C4 -#define PCIE_DEVICE_ID_NI_PXIE8431_48516 0x74C3 #define PCI_DEVICE_ID_MOXA_CP102E 0x1024 #define PCI_DEVICE_ID_MOXA_CP102EL 0x1025 @@ -2269,87 +2149,6 @@ static struct pci_serial_quirk pci_serial_quirks[] __refdata = { .setup = pci_ni8430_setup, .exit = pci_ni8430_exit, }, - { - .vendor = PCI_VENDOR_ID_NI, - .device = PCIE_DEVICE_ID_NI_PXIE8430_2328, - .subvendor = PCI_ANY_ID, - .subdevice = PCI_ANY_ID, - .init = pci_ni8430_init, - .setup = pci_ni8430_setup, - .exit = pci_ni8430_exit, - }, - { - .vendor = PCI_VENDOR_ID_NI, - .device = PCIE_DEVICE_ID_NI_PXIE8430_23216, - .subvendor = PCI_ANY_ID, - .subdevice = PCI_ANY_ID, - .init = pci_ni8430_init, - .setup = pci_ni8430_setup, - .exit = pci_ni8430_exit, - }, - { - .vendor = PCI_VENDOR_ID_NI, - .device = PCI_DEVICE_ID_NI_PXI8431_4852, - .subvendor = PCI_ANY_ID, - .subdevice = PCI_ANY_ID, - .init = pci_ni8430_init, - .setup = pci_ni8431_setup, - .exit = pci_ni8430_exit, - }, - { - .vendor = PCI_VENDOR_ID_NI, - .device = PCI_DEVICE_ID_NI_PXI8431_4854, - .subvendor = PCI_ANY_ID, - .subdevice = PCI_ANY_ID, - .init = pci_ni8430_init, - .setup = pci_ni8431_setup, - .exit = pci_ni8430_exit, - }, - { - .vendor = PCI_VENDOR_ID_NI, - .device = PCI_DEVICE_ID_NI_PXI8431_4858, - .subvendor = PCI_ANY_ID, - .subdevice = PCI_ANY_ID, - .init = pci_ni8430_init, - .setup = pci_ni8431_setup, - .exit = pci_ni8430_exit, - }, - { - .vendor = PCI_VENDOR_ID_NI, - .device = PCI_DEVICE_ID_NI_PXI8433_4852, - .subvendor = PCI_ANY_ID, - .subdevice = PCI_ANY_ID, - .init = pci_ni8430_init, - .setup = pci_ni8431_setup, - .exit = pci_ni8430_exit, - }, - { - .vendor = PCI_VENDOR_ID_NI, - .device = PCI_DEVICE_ID_NI_PXI8433_4854, - .subvendor = PCI_ANY_ID, - .subdevice = PCI_ANY_ID, - .init = pci_ni8430_init, - .setup = pci_ni8431_setup, - .exit = pci_ni8430_exit, - }, - { - .vendor = PCI_VENDOR_ID_NI, - .device = PCIE_DEVICE_ID_NI_PXIE8431_4858, - .subvendor = PCI_ANY_ID, - .subdevice = PCI_ANY_ID, - .init = pci_ni8430_init, - .setup = pci_ni8431_setup, - .exit = pci_ni8430_exit, - }, - { - .vendor = PCI_VENDOR_ID_NI, - .device = PCIE_DEVICE_ID_NI_PXIE8431_48516, - .subvendor = PCI_ANY_ID, - .subdevice = PCI_ANY_ID, - .init = pci_ni8430_init, - .setup = pci_ni8431_setup, - .exit = pci_ni8430_exit, - }, /* Quatech */ { .vendor = PCI_VENDOR_ID_QUATECH, @@ -3106,13 +2905,6 @@ enum pci_board_num_t { pbn_ni8430_4, pbn_ni8430_8, pbn_ni8430_16, - pbn_ni8430_pxie_8, - pbn_ni8430_pxie_16, - pbn_ni8431_2, - pbn_ni8431_4, - pbn_ni8431_8, - pbn_ni8431_pxie_8, - pbn_ni8431_pxie_16, pbn_ADDIDATA_PCIe_1_3906250, pbn_ADDIDATA_PCIe_2_3906250, pbn_ADDIDATA_PCIe_4_3906250, @@ -3765,55 +3557,6 @@ static struct pciserial_board pci_boards[] = { .uart_offset = 0x10, .first_offset = 0x800, }, - [pbn_ni8430_pxie_16] = { - .flags = FL_BASE0, - .num_ports = 16, - .base_baud = 3125000, - .uart_offset = 0x10, - .first_offset = 0x800, - }, - [pbn_ni8430_pxie_8] = { - .flags = FL_BASE0, - .num_ports = 8, - .base_baud = 3125000, - .uart_offset = 0x10, - .first_offset = 0x800, - }, - [pbn_ni8431_8] = { - .flags = FL_BASE0, - .num_ports = 8, - .base_baud = 3686400, - .uart_offset = 0x10, - .first_offset = 0x800, - }, - [pbn_ni8431_4] = { - .flags = FL_BASE0, - .num_ports = 4, - .base_baud = 3686400, - .uart_offset = 0x10, - .first_offset = 0x800, - }, - [pbn_ni8431_2] = { - .flags = FL_BASE0, - .num_ports = 2, - .base_baud = 3686400, - .uart_offset = 0x10, - .first_offset = 0x800, - }, - [pbn_ni8431_pxie_16] = { - .flags = FL_BASE0, - .num_ports = 16, - .base_baud = 3125000, - .uart_offset = 0x10, - .first_offset = 0x800, - }, - [pbn_ni8431_pxie_8] = { - .flags = FL_BASE0, - .num_ports = 8, - .base_baud = 3125000, - .uart_offset = 0x10, - .first_offset = 0x800, - }, /* * ADDI-DATA GmbH PCI-Express communication cards */ @@ -5567,33 +5310,6 @@ static const struct pci_device_id serial_pci_tbl[] = { { PCI_VENDOR_ID_NI, PCI_DEVICE_ID_NI_PCI8432_2324, PCI_ANY_ID, PCI_ANY_ID, 0, 0, pbn_ni8430_4 }, - { PCI_VENDOR_ID_NI, PCIE_DEVICE_ID_NI_PXIE8430_2328, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, - pbn_ni8430_pxie_8 }, - { PCI_VENDOR_ID_NI, PCIE_DEVICE_ID_NI_PXIE8430_23216, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, - pbn_ni8430_pxie_16 }, - { PCI_VENDOR_ID_NI, PCI_DEVICE_ID_NI_PXI8431_4852, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, - pbn_ni8431_2 }, - { PCI_VENDOR_ID_NI, PCI_DEVICE_ID_NI_PXI8431_4854, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, - pbn_ni8431_4 }, - { PCI_VENDOR_ID_NI, PCI_DEVICE_ID_NI_PXI8431_4858, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, - pbn_ni8431_8 }, - { PCI_VENDOR_ID_NI, PCIE_DEVICE_ID_NI_PXIE8431_4858, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, - pbn_ni8431_pxie_8 }, - { PCI_VENDOR_ID_NI, PCIE_DEVICE_ID_NI_PXIE8431_48516, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, - pbn_ni8431_pxie_16 }, - { PCI_VENDOR_ID_NI, PCI_DEVICE_ID_NI_PXI8433_4852, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, - pbn_ni8431_2 }, - { PCI_VENDOR_ID_NI, PCI_DEVICE_ID_NI_PXI8433_4854, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, - pbn_ni8431_4 }, /* * MOXA diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index 3a7d1a66f79c..b0b689546395 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -813,10 +813,8 @@ __acquires(&uap->port.lock) if (!uap->using_tx_dma) return; - /* Avoid deadlock with the DMA engine callback */ - spin_unlock(&uap->port.lock); - dmaengine_terminate_all(uap->dmatx.chan); - spin_lock(&uap->port.lock); + dmaengine_terminate_async(uap->dmatx.chan); + if (uap->dmatx.queued) { dma_unmap_sg(uap->dmatx.chan->device->dev, &uap->dmatx.sg, 1, DMA_TO_DEVICE); diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c index a8dc8af83f39..1ba9bc667e13 100644 --- a/drivers/tty/serial/atmel_serial.c +++ b/drivers/tty/serial/atmel_serial.c @@ -2270,27 +2270,6 @@ static void atmel_set_termios(struct uart_port *port, struct ktermios *termios, mode |= ATMEL_US_USMODE_NORMAL; } - /* set the mode, clock divisor, parity, stop bits and data size */ - atmel_uart_writel(port, ATMEL_US_MR, mode); - - /* - * when switching the mode, set the RTS line state according to the - * new mode, otherwise keep the former state - */ - if ((old_mode & ATMEL_US_USMODE) != (mode & ATMEL_US_USMODE)) { - unsigned int rts_state; - - if ((mode & ATMEL_US_USMODE) == ATMEL_US_USMODE_HWHS) { - /* let the hardware control the RTS line */ - rts_state = ATMEL_US_RTSDIS; - } else { - /* force RTS line to low level */ - rts_state = ATMEL_US_RTSEN; - } - - atmel_uart_writel(port, ATMEL_US_CR, rts_state); - } - /* * Set the baud rate: * Fractional baudrate allows to setup output frequency more @@ -2317,6 +2296,28 @@ static void atmel_set_termios(struct uart_port *port, struct ktermios *termios, if (!(port->iso7816.flags & SER_ISO7816_ENABLED)) atmel_uart_writel(port, ATMEL_US_BRGR, quot); + + /* set the mode, clock divisor, parity, stop bits and data size */ + atmel_uart_writel(port, ATMEL_US_MR, mode); + + /* + * when switching the mode, set the RTS line state according to the + * new mode, otherwise keep the former state + */ + if ((old_mode & ATMEL_US_USMODE) != (mode & ATMEL_US_USMODE)) { + unsigned int rts_state; + + if ((mode & ATMEL_US_USMODE) == ATMEL_US_USMODE_HWHS) { + /* let the hardware control the RTS line */ + rts_state = ATMEL_US_RTSDIS; + } else { + /* force RTS line to low level */ + rts_state = ATMEL_US_RTSEN; + } + + atmel_uart_writel(port, ATMEL_US_CR, rts_state); + } + atmel_uart_writel(port, ATMEL_US_CR, ATMEL_US_RSTSTA | ATMEL_US_RSTRX); atmel_uart_writel(port, ATMEL_US_CR, ATMEL_US_TXEN | ATMEL_US_RXEN); atmel_port->tx_stopped = false; diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index 537896c4d887..3f64b08f50ef 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -437,8 +437,8 @@ static void lpuart_dma_tx(struct lpuart_port *sport) } sport->dma_tx_desc = dmaengine_prep_slave_sg(sport->dma_tx_chan, sgl, - sport->dma_tx_nents, - DMA_MEM_TO_DEV, DMA_PREP_INTERRUPT); + ret, DMA_MEM_TO_DEV, + DMA_PREP_INTERRUPT); if (!sport->dma_tx_desc) { dma_unmap_sg(dev, sgl, sport->dma_tx_nents, DMA_TO_DEVICE); dev_err(dev, "Cannot prepare TX slave DMA!\n"); diff --git a/drivers/tty/serial/ifx6x60.c b/drivers/tty/serial/ifx6x60.c index ffefd218761e..31033d517e82 100644 --- a/drivers/tty/serial/ifx6x60.c +++ b/drivers/tty/serial/ifx6x60.c @@ -1230,6 +1230,9 @@ static int ifx_spi_spi_remove(struct spi_device *spi) struct ifx_spi_device *ifx_dev = spi_get_drvdata(spi); /* stop activity */ tasklet_kill(&ifx_dev->io_work_tasklet); + + pm_runtime_disable(&spi->dev); + /* free irq */ free_irq(gpio_to_irq(ifx_dev->gpio.reset_out), ifx_dev); free_irq(gpio_to_irq(ifx_dev->gpio.srdy), ifx_dev); diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index 5e08f2657b90..34f602c3a882 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -619,7 +619,7 @@ static void imx_uart_dma_tx(struct imx_port *sport) dev_err(dev, "DMA mapping error for TX.\n"); return; } - desc = dmaengine_prep_slave_sg(chan, sgl, sport->dma_tx_nents, + desc = dmaengine_prep_slave_sg(chan, sgl, ret, DMA_MEM_TO_DEV, DMA_PREP_INTERRUPT); if (!desc) { dma_unmap_sg(dev, sgl, sport->dma_tx_nents, diff --git a/drivers/tty/serial/msm_serial.c b/drivers/tty/serial/msm_serial.c index 3657a24913fc..e0718ee5d42a 100644 --- a/drivers/tty/serial/msm_serial.c +++ b/drivers/tty/serial/msm_serial.c @@ -980,6 +980,7 @@ static unsigned int msm_get_mctrl(struct uart_port *port) static void msm_reset(struct uart_port *port) { struct msm_port *msm_port = UART_TO_MSM(port); + unsigned int mr; /* reset everything */ msm_write(port, UART_CR_CMD_RESET_RX, UART_CR); @@ -987,7 +988,10 @@ static void msm_reset(struct uart_port *port) msm_write(port, UART_CR_CMD_RESET_ERR, UART_CR); msm_write(port, UART_CR_CMD_RESET_BREAK_INT, UART_CR); msm_write(port, UART_CR_CMD_RESET_CTS, UART_CR); - msm_write(port, UART_CR_CMD_SET_RFR, UART_CR); + msm_write(port, UART_CR_CMD_RESET_RFR, UART_CR); + mr = msm_read(port, UART_MR1); + mr &= ~UART_MR1_RX_RDY_CTL; + msm_write(port, mr, UART_MR1); /* Disable DM modes */ if (msm_port->is_uartdm) @@ -1576,6 +1580,7 @@ static void __msm_console_write(struct uart_port *port, const char *s, int num_newlines = 0; bool replaced = false; void __iomem *tf; + int locked = 1; if (is_uartdm) tf = port->membase + UARTDM_TF; @@ -1588,7 +1593,13 @@ static void __msm_console_write(struct uart_port *port, const char *s, num_newlines++; count += num_newlines; - spin_lock(&port->lock); + if (port->sysrq) + locked = 0; + else if (oops_in_progress) + locked = spin_trylock(&port->lock); + else + spin_lock(&port->lock); + if (is_uartdm) msm_reset_dm_count(port, count); @@ -1624,7 +1635,9 @@ static void __msm_console_write(struct uart_port *port, const char *s, iowrite32_rep(tf, buf, 1); i += num_chars; } - spin_unlock(&port->lock); + + if (locked) + spin_unlock(&port->lock); } static void msm_console_write(struct console *co, const char *s, diff --git a/drivers/tty/serial/pch_uart.c b/drivers/tty/serial/pch_uart.c index 6157213a8359..c16234bca78f 100644 --- a/drivers/tty/serial/pch_uart.c +++ b/drivers/tty/serial/pch_uart.c @@ -233,6 +233,7 @@ struct eg20t_port { struct dma_chan *chan_rx; struct scatterlist *sg_tx_p; int nent; + int orig_nent; struct scatterlist sg_rx; int tx_dma_use; void *rx_buf_virt; @@ -787,9 +788,10 @@ static void pch_dma_tx_complete(void *arg) } xmit->tail &= UART_XMIT_SIZE - 1; async_tx_ack(priv->desc_tx); - dma_unmap_sg(port->dev, sg, priv->nent, DMA_TO_DEVICE); + dma_unmap_sg(port->dev, sg, priv->orig_nent, DMA_TO_DEVICE); priv->tx_dma_use = 0; priv->nent = 0; + priv->orig_nent = 0; kfree(priv->sg_tx_p); pch_uart_hal_enable_interrupt(priv, PCH_UART_HAL_TX_INT); } @@ -1010,6 +1012,7 @@ static unsigned int dma_handle_tx(struct eg20t_port *priv) dev_err(priv->port.dev, "%s:dma_map_sg Failed\n", __func__); return 0; } + priv->orig_nent = num; priv->nent = nent; for (i = 0; i < nent; i++, sg++) { diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index c4a414a46c7f..7c2782785736 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -1111,7 +1111,7 @@ static int uart_break_ctl(struct tty_struct *tty, int break_state) if (!uport) goto out; - if (uport->type != PORT_UNKNOWN) + if (uport->type != PORT_UNKNOWN && uport->ops->break_ctl) uport->ops->break_ctl(uport, break_state); ret = 0; out: @@ -2834,6 +2834,7 @@ int uart_add_one_port(struct uart_driver *drv, struct uart_port *uport) if (uport->cons && uport->dev) of_console_check(uport->dev->of_node, uport->cons->name, uport->line); + tty_port_link_device(port, drv->tty_driver, uport->line); uart_configure_port(drv, state, uport); port->console = uart_console(uport); diff --git a/drivers/tty/serial/sprd_serial.c b/drivers/tty/serial/sprd_serial.c index 771d11196523..494e2672ebd7 100644 --- a/drivers/tty/serial/sprd_serial.c +++ b/drivers/tty/serial/sprd_serial.c @@ -679,6 +679,9 @@ static irqreturn_t sprd_handle_irq(int irq, void *dev_id) if (ims & SPRD_IMSR_TIMEOUT) serial_out(port, SPRD_ICLR, SPRD_ICLR_TIMEOUT); + if (ims & SPRD_IMSR_BREAK_DETECT) + serial_out(port, SPRD_ICLR, SPRD_IMSR_BREAK_DETECT); + if (ims & (SPRD_IMSR_RX_FIFO_FULL | SPRD_IMSR_BREAK_DETECT | SPRD_IMSR_TIMEOUT)) sprd_rx(port); diff --git a/drivers/tty/serial/stm32-usart.c b/drivers/tty/serial/stm32-usart.c index df90747ee3a8..2f72514d63ed 100644 --- a/drivers/tty/serial/stm32-usart.c +++ b/drivers/tty/serial/stm32-usart.c @@ -240,8 +240,8 @@ static void stm32_receive_chars(struct uart_port *port, bool threaded) * cleared by the sequence [read SR - read DR]. */ if ((sr & USART_SR_ERR_MASK) && ofs->icr != UNDEF_REG) - stm32_clr_bits(port, ofs->icr, USART_ICR_ORECF | - USART_ICR_PECF | USART_ICR_FECF); + writel_relaxed(sr & USART_SR_ERR_MASK, + port->membase + ofs->icr); c = stm32_get_char(port, &sr, &stm32_port->last_res); port->icount.rx++; @@ -435,7 +435,7 @@ static void stm32_transmit_chars(struct uart_port *port) if (ofs->icr == UNDEF_REG) stm32_clr_bits(port, ofs->isr, USART_SR_TC); else - stm32_set_bits(port, ofs->icr, USART_ICR_TCCF); + writel_relaxed(USART_ICR_TCCF, port->membase + ofs->icr); if (stm32_port->tx_ch) stm32_transmit_chars_dma(port); diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c index 515fc095e3b4..15d33fa0c925 100644 --- a/drivers/tty/vt/keyboard.c +++ b/drivers/tty/vt/keyboard.c @@ -1491,7 +1491,7 @@ static void kbd_event(struct input_handle *handle, unsigned int event_type, if (event_type == EV_MSC && event_code == MSC_RAW && HW_RAW(handle->dev)) kbd_rawcode(value); - if (event_type == EV_KEY) + if (event_type == EV_KEY && event_code <= KEY_MAX) kbd_keycode(event_code, value, HW_RAW(handle->dev)); spin_unlock(&kbd_event_lock); diff --git a/drivers/tty/vt/vc_screen.c b/drivers/tty/vt/vc_screen.c index 1f042346e722..778f83ea2249 100644 --- a/drivers/tty/vt/vc_screen.c +++ b/drivers/tty/vt/vc_screen.c @@ -456,6 +456,9 @@ vcs_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) size_t ret; char *con_buf; + if (use_unicode(inode)) + return -EOPNOTSUPP; + con_buf = (char *) __get_free_page(GFP_KERNEL); if (!con_buf) return -ENOMEM; diff --git a/drivers/usb/atm/ueagle-atm.c b/drivers/usb/atm/ueagle-atm.c index 8b0ea8c70d73..635cf0466b59 100644 --- a/drivers/usb/atm/ueagle-atm.c +++ b/drivers/usb/atm/ueagle-atm.c @@ -2124,10 +2124,11 @@ static void uea_intr(struct urb *urb) /* * Start the modem : init the data and start kernel thread */ -static int uea_boot(struct uea_softc *sc) +static int uea_boot(struct uea_softc *sc, struct usb_interface *intf) { - int ret, size; struct intr_pkt *intr; + int ret = -ENOMEM; + int size; uea_enters(INS_TO_USBDEV(sc)); @@ -2152,6 +2153,11 @@ static int uea_boot(struct uea_softc *sc) if (UEA_CHIP_VERSION(sc) == ADI930) load_XILINX_firmware(sc); + if (intf->cur_altsetting->desc.bNumEndpoints < 1) { + ret = -ENODEV; + goto err0; + } + intr = kmalloc(size, GFP_KERNEL); if (!intr) goto err0; @@ -2163,8 +2169,7 @@ static int uea_boot(struct uea_softc *sc) usb_fill_int_urb(sc->urb_int, sc->usb_dev, usb_rcvintpipe(sc->usb_dev, UEA_INTR_PIPE), intr, size, uea_intr, sc, - sc->usb_dev->actconfig->interface[0]->altsetting[0]. - endpoint[0].desc.bInterval); + intf->cur_altsetting->endpoint[0].desc.bInterval); ret = usb_submit_urb(sc->urb_int, GFP_KERNEL); if (ret < 0) { @@ -2179,6 +2184,7 @@ static int uea_boot(struct uea_softc *sc) sc->kthread = kthread_create(uea_kthread, sc, "ueagle-atm"); if (IS_ERR(sc->kthread)) { uea_err(INS_TO_USBDEV(sc), "failed to create thread\n"); + ret = PTR_ERR(sc->kthread); goto err2; } @@ -2193,7 +2199,7 @@ static int uea_boot(struct uea_softc *sc) kfree(intr); err0: uea_leaves(INS_TO_USBDEV(sc)); - return -ENOMEM; + return ret; } /* @@ -2548,7 +2554,7 @@ static int uea_bind(struct usbatm_data *usbatm, struct usb_interface *intf, } } - ret = uea_boot(sc); + ret = uea_boot(sc, intf); if (ret < 0) goto error; diff --git a/drivers/usb/cdns3/gadget.c b/drivers/usb/cdns3/gadget.c index 4c1e75509303..02f6ca2cb1ba 100644 --- a/drivers/usb/cdns3/gadget.c +++ b/drivers/usb/cdns3/gadget.c @@ -1375,13 +1375,10 @@ static void cdns3_check_usb_interrupt_proceed(struct cdns3_device *priv_dev, */ static irqreturn_t cdns3_device_irq_handler(int irq, void *data) { - struct cdns3_device *priv_dev; - struct cdns3 *cdns = data; + struct cdns3_device *priv_dev = data; irqreturn_t ret = IRQ_NONE; u32 reg; - priv_dev = cdns->gadget_dev; - /* check USB device interrupt */ reg = readl(&priv_dev->regs->usb_ists); if (reg) { @@ -1419,14 +1416,12 @@ static irqreturn_t cdns3_device_irq_handler(int irq, void *data) */ static irqreturn_t cdns3_device_thread_irq_handler(int irq, void *data) { - struct cdns3_device *priv_dev; - struct cdns3 *cdns = data; + struct cdns3_device *priv_dev = data; irqreturn_t ret = IRQ_NONE; unsigned long flags; int bit; u32 reg; - priv_dev = cdns->gadget_dev; spin_lock_irqsave(&priv_dev->lock, flags); reg = readl(&priv_dev->regs->usb_ists); @@ -2539,7 +2534,7 @@ void cdns3_gadget_exit(struct cdns3 *cdns) priv_dev = cdns->gadget_dev; - devm_free_irq(cdns->dev, cdns->dev_irq, cdns); + devm_free_irq(cdns->dev, cdns->dev_irq, priv_dev); pm_runtime_mark_last_busy(cdns->dev); pm_runtime_put_autosuspend(cdns->dev); @@ -2710,7 +2705,8 @@ static int __cdns3_gadget_init(struct cdns3 *cdns) ret = devm_request_threaded_irq(cdns->dev, cdns->dev_irq, cdns3_device_irq_handler, cdns3_device_thread_irq_handler, - IRQF_SHARED, dev_name(cdns->dev), cdns); + IRQF_SHARED, dev_name(cdns->dev), + cdns->gadget_dev); if (ret) goto err0; diff --git a/drivers/usb/chipidea/host.c b/drivers/usb/chipidea/host.c index b45ceb91c735..48e4a5ca1835 100644 --- a/drivers/usb/chipidea/host.c +++ b/drivers/usb/chipidea/host.c @@ -26,6 +26,7 @@ static int (*orig_bus_suspend)(struct usb_hcd *hcd); struct ehci_ci_priv { struct regulator *reg_vbus; + bool enabled; }; static int ehci_ci_portpower(struct usb_hcd *hcd, int portnum, bool enable) @@ -37,7 +38,7 @@ static int ehci_ci_portpower(struct usb_hcd *hcd, int portnum, bool enable) int ret = 0; int port = HCS_N_PORTS(ehci->hcs_params); - if (priv->reg_vbus) { + if (priv->reg_vbus && enable != priv->enabled) { if (port > 1) { dev_warn(dev, "Not support multi-port regulator control\n"); @@ -53,6 +54,7 @@ static int ehci_ci_portpower(struct usb_hcd *hcd, int portnum, bool enable) enable ? "enable" : "disable", ret); return ret; } + priv->enabled = enable; } if (enable && (ci->platdata->phy_mode == USBPHY_INTERFACE_MODE_HSIC)) { diff --git a/drivers/usb/common/usb-conn-gpio.c b/drivers/usb/common/usb-conn-gpio.c index 87338f9eb5be..ed204cbb63ea 100644 --- a/drivers/usb/common/usb-conn-gpio.c +++ b/drivers/usb/common/usb-conn-gpio.c @@ -156,7 +156,8 @@ static int usb_conn_probe(struct platform_device *pdev) info->vbus = devm_regulator_get(dev, "vbus"); if (IS_ERR(info->vbus)) { - dev_err(dev, "failed to get vbus\n"); + if (PTR_ERR(info->vbus) != -EPROBE_DEFER) + dev_err(dev, "failed to get vbus\n"); return PTR_ERR(info->vbus); } diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c index 1ac1095bfeac..3e94259406d7 100644 --- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -203,9 +203,58 @@ static const unsigned short super_speed_maxpacket_maxes[4] = { [USB_ENDPOINT_XFER_INT] = 1024, }; -static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum, - int asnum, struct usb_host_interface *ifp, int num_ep, - unsigned char *buffer, int size) +static bool endpoint_is_duplicate(struct usb_endpoint_descriptor *e1, + struct usb_endpoint_descriptor *e2) +{ + if (e1->bEndpointAddress == e2->bEndpointAddress) + return true; + + if (usb_endpoint_xfer_control(e1) || usb_endpoint_xfer_control(e2)) { + if (usb_endpoint_num(e1) == usb_endpoint_num(e2)) + return true; + } + + return false; +} + +/* + * Check for duplicate endpoint addresses in other interfaces and in the + * altsetting currently being parsed. + */ +static bool config_endpoint_is_duplicate(struct usb_host_config *config, + int inum, int asnum, struct usb_endpoint_descriptor *d) +{ + struct usb_endpoint_descriptor *epd; + struct usb_interface_cache *intfc; + struct usb_host_interface *alt; + int i, j, k; + + for (i = 0; i < config->desc.bNumInterfaces; ++i) { + intfc = config->intf_cache[i]; + + for (j = 0; j < intfc->num_altsetting; ++j) { + alt = &intfc->altsetting[j]; + + if (alt->desc.bInterfaceNumber == inum && + alt->desc.bAlternateSetting != asnum) + continue; + + for (k = 0; k < alt->desc.bNumEndpoints; ++k) { + epd = &alt->endpoint[k].desc; + + if (endpoint_is_duplicate(epd, d)) + return true; + } + } + } + + return false; +} + +static int usb_parse_endpoint(struct device *ddev, int cfgno, + struct usb_host_config *config, int inum, int asnum, + struct usb_host_interface *ifp, int num_ep, + unsigned char *buffer, int size) { unsigned char *buffer0 = buffer; struct usb_endpoint_descriptor *d; @@ -242,13 +291,10 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum, goto skip_to_next_endpoint_or_interface_descriptor; /* Check for duplicate endpoint addresses */ - for (i = 0; i < ifp->desc.bNumEndpoints; ++i) { - if (ifp->endpoint[i].desc.bEndpointAddress == - d->bEndpointAddress) { - dev_warn(ddev, "config %d interface %d altsetting %d has a duplicate endpoint with address 0x%X, skipping\n", - cfgno, inum, asnum, d->bEndpointAddress); - goto skip_to_next_endpoint_or_interface_descriptor; - } + if (config_endpoint_is_duplicate(config, inum, asnum, d)) { + dev_warn(ddev, "config %d interface %d altsetting %d has a duplicate endpoint with address 0x%X, skipping\n", + cfgno, inum, asnum, d->bEndpointAddress); + goto skip_to_next_endpoint_or_interface_descriptor; } endpoint = &ifp->endpoint[ifp->desc.bNumEndpoints]; @@ -346,12 +392,16 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum, endpoint->desc.wMaxPacketSize = cpu_to_le16(8); } - /* Validate the wMaxPacketSize field */ + /* + * Validate the wMaxPacketSize field. + * Some devices have isochronous endpoints in altsetting 0; + * the USB-2 spec requires such endpoints to have wMaxPacketSize = 0 + * (see the end of section 5.6.3), so don't warn about them. + */ maxp = usb_endpoint_maxp(&endpoint->desc); - if (maxp == 0) { - dev_warn(ddev, "config %d interface %d altsetting %d endpoint 0x%X has wMaxPacketSize 0, skipping\n", + if (maxp == 0 && !(usb_endpoint_xfer_isoc(d) && asnum == 0)) { + dev_warn(ddev, "config %d interface %d altsetting %d endpoint 0x%X has invalid wMaxPacketSize 0\n", cfgno, inum, asnum, d->bEndpointAddress); - goto skip_to_next_endpoint_or_interface_descriptor; } /* Find the highest legal maxpacket size for this endpoint */ @@ -522,8 +572,8 @@ static int usb_parse_interface(struct device *ddev, int cfgno, if (((struct usb_descriptor_header *) buffer)->bDescriptorType == USB_DT_INTERFACE) break; - retval = usb_parse_endpoint(ddev, cfgno, inum, asnum, alt, - num_ep, buffer, size); + retval = usb_parse_endpoint(ddev, cfgno, config, inum, asnum, + alt, num_ep, buffer, size); if (retval < 0) return retval; ++n; diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index 3f899552f6e3..6ca40d135430 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -764,8 +764,15 @@ static int claimintf(struct usb_dev_state *ps, unsigned int ifnum) intf = usb_ifnum_to_if(dev, ifnum); if (!intf) err = -ENOENT; - else + else { + unsigned int old_suppress; + + /* suppress uevents while claiming interface */ + old_suppress = dev_get_uevent_suppress(&intf->dev); + dev_set_uevent_suppress(&intf->dev, 1); err = usb_driver_claim_interface(&usbfs_driver, intf, ps); + dev_set_uevent_suppress(&intf->dev, old_suppress); + } if (err == 0) set_bit(ifnum, &ps->ifclaimed); return err; @@ -785,7 +792,13 @@ static int releaseintf(struct usb_dev_state *ps, unsigned int ifnum) if (!intf) err = -ENOENT; else if (test_and_clear_bit(ifnum, &ps->ifclaimed)) { + unsigned int old_suppress; + + /* suppress uevents while releasing interface */ + old_suppress = dev_get_uevent_suppress(&intf->dev); + dev_set_uevent_suppress(&intf->dev, 1); usb_driver_release_interface(&usbfs_driver, intf); + dev_set_uevent_suppress(&intf->dev, old_suppress); err = 0; } return err; diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index f225eaa98ff8..d0f45600b669 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -1409,7 +1409,17 @@ int usb_hcd_map_urb_for_dma(struct usb_hcd *hcd, struct urb *urb, if (usb_endpoint_xfer_control(&urb->ep->desc)) { if (hcd->self.uses_pio_for_control) return ret; - if (hcd_uses_dma(hcd)) { + if (hcd->localmem_pool) { + ret = hcd_alloc_coherent( + urb->dev->bus, mem_flags, + &urb->setup_dma, + (void **)&urb->setup_packet, + sizeof(struct usb_ctrlrequest), + DMA_TO_DEVICE); + if (ret) + return ret; + urb->transfer_flags |= URB_SETUP_MAP_LOCAL; + } else if (hcd_uses_dma(hcd)) { if (is_vmalloc_addr(urb->setup_packet)) { WARN_ONCE(1, "setup packet is not dma capable\n"); return -EAGAIN; @@ -1427,23 +1437,22 @@ int usb_hcd_map_urb_for_dma(struct usb_hcd *hcd, struct urb *urb, urb->setup_dma)) return -EAGAIN; urb->transfer_flags |= URB_SETUP_MAP_SINGLE; - } else if (hcd->localmem_pool) { - ret = hcd_alloc_coherent( - urb->dev->bus, mem_flags, - &urb->setup_dma, - (void **)&urb->setup_packet, - sizeof(struct usb_ctrlrequest), - DMA_TO_DEVICE); - if (ret) - return ret; - urb->transfer_flags |= URB_SETUP_MAP_LOCAL; } } dir = usb_urb_dir_in(urb) ? DMA_FROM_DEVICE : DMA_TO_DEVICE; if (urb->transfer_buffer_length != 0 && !(urb->transfer_flags & URB_NO_TRANSFER_DMA_MAP)) { - if (hcd_uses_dma(hcd)) { + if (hcd->localmem_pool) { + ret = hcd_alloc_coherent( + urb->dev->bus, mem_flags, + &urb->transfer_dma, + &urb->transfer_buffer, + urb->transfer_buffer_length, + dir); + if (ret == 0) + urb->transfer_flags |= URB_MAP_LOCAL; + } else if (hcd_uses_dma(hcd)) { if (urb->num_sgs) { int n; @@ -1497,15 +1506,6 @@ int usb_hcd_map_urb_for_dma(struct usb_hcd *hcd, struct urb *urb, else urb->transfer_flags |= URB_DMA_MAP_SINGLE; } - } else if (hcd->localmem_pool) { - ret = hcd_alloc_coherent( - urb->dev->bus, mem_flags, - &urb->transfer_dma, - &urb->transfer_buffer, - urb->transfer_buffer_length, - dir); - if (ret == 0) - urb->transfer_flags |= URB_MAP_LOCAL; } if (ret && (urb->transfer_flags & (URB_SETUP_MAP_SINGLE | URB_SETUP_MAP_LOCAL))) diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 236313f41f4a..8b23162e4239 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -2691,7 +2691,7 @@ static unsigned hub_is_wusb(struct usb_hub *hub) #define SET_ADDRESS_TRIES 2 #define GET_DESCRIPTOR_TRIES 2 #define SET_CONFIG_TRIES (2 * (use_both_schemes + 1)) -#define USE_NEW_SCHEME(i, scheme) ((i) / 2 == (int)scheme) +#define USE_NEW_SCHEME(i, scheme) ((i) / 2 == (int)(scheme)) #define HUB_ROOT_RESET_TIME 60 /* times are in msec */ #define HUB_SHORT_RESET_TIME 10 @@ -5814,7 +5814,7 @@ static int usb_reset_and_verify_device(struct usb_device *udev) /** * usb_reset_device - warn interface drivers and perform a USB port reset - * @udev: device to reset (not in SUSPENDED or NOTATTACHED state) + * @udev: device to reset (not in NOTATTACHED state) * * Warns all drivers bound to registered interfaces (using their pre_reset * method), performs the port reset, and then lets the drivers know that @@ -5842,8 +5842,7 @@ int usb_reset_device(struct usb_device *udev) struct usb_host_config *config = udev->actconfig; struct usb_hub *hub = usb_hub_to_struct_hub(udev->parent); - if (udev->state == USB_STATE_NOTATTACHED || - udev->state == USB_STATE_SUSPENDED) { + if (udev->state == USB_STATE_NOTATTACHED) { dev_dbg(&udev->dev, "device reset not allowed in state %d\n", udev->state); return -EINVAL; diff --git a/drivers/usb/core/urb.c b/drivers/usb/core/urb.c index 0eab79f82ce4..da923ec17612 100644 --- a/drivers/usb/core/urb.c +++ b/drivers/usb/core/urb.c @@ -45,6 +45,7 @@ void usb_init_urb(struct urb *urb) if (urb) { memset(urb, 0, sizeof(*urb)); kref_init(&urb->kref); + INIT_LIST_HEAD(&urb->urb_list); INIT_LIST_HEAD(&urb->anchor_list); } } diff --git a/drivers/usb/dwc2/core.c b/drivers/usb/dwc2/core.c index 8e41d70fd298..78a4925aa118 100644 --- a/drivers/usb/dwc2/core.c +++ b/drivers/usb/dwc2/core.c @@ -524,7 +524,7 @@ int dwc2_core_reset(struct dwc2_hsotg *hsotg, bool skip_wait) greset |= GRSTCTL_CSFTRST; dwc2_writel(hsotg, greset, GRSTCTL); - if (dwc2_hsotg_wait_bit_clear(hsotg, GRSTCTL, GRSTCTL_CSFTRST, 50)) { + if (dwc2_hsotg_wait_bit_clear(hsotg, GRSTCTL, GRSTCTL_CSFTRST, 10000)) { dev_warn(hsotg->dev, "%s: HANG! Soft Reset timeout GRSTCTL GRSTCTL_CSFTRST\n", __func__); return -EBUSY; diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index 023f0357efd7..294276f7deb9 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -29,7 +29,8 @@ #define PCI_DEVICE_ID_INTEL_BXT_M 0x1aaa #define PCI_DEVICE_ID_INTEL_APL 0x5aaa #define PCI_DEVICE_ID_INTEL_KBP 0xa2b0 -#define PCI_DEVICE_ID_INTEL_CMLH 0x02ee +#define PCI_DEVICE_ID_INTEL_CMLLP 0x02ee +#define PCI_DEVICE_ID_INTEL_CMLH 0x06ee #define PCI_DEVICE_ID_INTEL_GLK 0x31aa #define PCI_DEVICE_ID_INTEL_CNPLP 0x9dee #define PCI_DEVICE_ID_INTEL_CNPH 0xa36e @@ -308,6 +309,9 @@ static const struct pci_device_id dwc3_pci_id_table[] = { { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MRFLD), (kernel_ulong_t) &dwc3_pci_mrfld_properties, }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_CMLLP), + (kernel_ulong_t) &dwc3_pci_intel_properties, }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_CMLH), (kernel_ulong_t) &dwc3_pci_intel_properties, }, diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c index 3996b9c4ff8d..fd1b100d2927 100644 --- a/drivers/usb/dwc3/ep0.c +++ b/drivers/usb/dwc3/ep0.c @@ -1117,6 +1117,9 @@ static void dwc3_ep0_xfernotready(struct dwc3 *dwc, void dwc3_ep0_interrupt(struct dwc3 *dwc, const struct dwc3_event_depevt *event) { + struct dwc3_ep *dep = dwc->eps[event->endpoint_number]; + u8 cmd; + switch (event->endpoint_event) { case DWC3_DEPEVT_XFERCOMPLETE: dwc3_ep0_xfer_complete(dwc, event); @@ -1129,7 +1132,12 @@ void dwc3_ep0_interrupt(struct dwc3 *dwc, case DWC3_DEPEVT_XFERINPROGRESS: case DWC3_DEPEVT_RXTXFIFOEVT: case DWC3_DEPEVT_STREAMEVT: + break; case DWC3_DEPEVT_EPCMDCMPLT: + cmd = DEPEVT_PARAMETER_CMD(event->parameters); + + if (cmd == DWC3_DEPCMD_ENDTRANSFER) + dep->flags &= ~DWC3_EP_TRANSFER_STARTED; break; } } diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index a9aba716bf80..154f3f3e8cff 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -2467,6 +2467,13 @@ static int dwc3_gadget_ep_reclaim_trb_linear(struct dwc3_ep *dep, static bool dwc3_gadget_ep_request_completed(struct dwc3_request *req) { + /* + * For OUT direction, host may send less than the setup + * length. Return true for all OUT requests. + */ + if (!req->direction) + return true; + return req->request.actual == req->request.length; } @@ -2491,7 +2498,7 @@ static int dwc3_gadget_ep_cleanup_completed_request(struct dwc3_ep *dep, req->request.actual = req->request.length - req->remaining; - if (!dwc3_gadget_ep_request_completed(req) && + if (!dwc3_gadget_ep_request_completed(req) || req->num_pending_sgs) { __dwc3_gadget_kick_transfer(dep); goto out; @@ -2719,6 +2726,9 @@ static void dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force, WARN_ON_ONCE(ret); dep->resource_index = 0; + if (!interrupt) + dep->flags &= ~DWC3_EP_TRANSFER_STARTED; + if (dwc3_is_usb31(dwc) || dwc->revision < DWC3_REVISION_310A) udelay(100); } diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index 33852c2b29d1..ab9ac48a751a 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -1544,6 +1544,7 @@ static struct config_group *gadgets_make( gi->composite.resume = NULL; gi->composite.max_speed = USB_SPEED_SUPER; + spin_lock_init(&gi->spinlock); mutex_init(&gi->lock); INIT_LIST_HEAD(&gi->string_list); INIT_LIST_HEAD(&gi->available_func); diff --git a/drivers/usb/gadget/function/f_ecm.c b/drivers/usb/gadget/function/f_ecm.c index 6ce044008cf6..460d5d7c984f 100644 --- a/drivers/usb/gadget/function/f_ecm.c +++ b/drivers/usb/gadget/function/f_ecm.c @@ -621,8 +621,12 @@ static void ecm_disable(struct usb_function *f) DBG(cdev, "ecm deactivated\n"); - if (ecm->port.in_ep->enabled) + if (ecm->port.in_ep->enabled) { gether_disconnect(&ecm->port); + } else { + ecm->port.in_ep->desc = NULL; + ecm->port.out_ep->desc = NULL; + } usb_ep_disable(ecm->notify); ecm->notify->desc = NULL; diff --git a/drivers/usb/gadget/function/f_rndis.c b/drivers/usb/gadget/function/f_rndis.c index d48df36622b7..0d8e4a364ca6 100644 --- a/drivers/usb/gadget/function/f_rndis.c +++ b/drivers/usb/gadget/function/f_rndis.c @@ -618,6 +618,7 @@ static void rndis_disable(struct usb_function *f) gether_disconnect(&rndis->port); usb_ep_disable(rndis->notify); + rndis->notify->desc = NULL; } /*-------------------------------------------------------------------------*/ diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c index 65f634ec7fc2..bb1e2e1d0076 100644 --- a/drivers/usb/gadget/function/u_serial.c +++ b/drivers/usb/gadget/function/u_serial.c @@ -1239,8 +1239,10 @@ int gserial_alloc_line(unsigned char *line_num) __func__, port_num, PTR_ERR(tty_dev)); ret = PTR_ERR(tty_dev); + mutex_lock(&ports[port_num].lock); port = ports[port_num].port; ports[port_num].port = NULL; + mutex_unlock(&ports[port_num].lock); gserial_free_port(port); goto err; } diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c index 3d499d93c083..4c9d1e49d5ed 100644 --- a/drivers/usb/gadget/udc/dummy_hcd.c +++ b/drivers/usb/gadget/udc/dummy_hcd.c @@ -1321,7 +1321,7 @@ static int dummy_perform_transfer(struct urb *urb, struct dummy_request *req, u32 this_sg; bool next_sg; - to_host = usb_pipein(urb->pipe); + to_host = usb_urb_dir_in(urb); rbuf = req->req.buf + req->req.actual; if (!urb->num_sgs) { @@ -1409,7 +1409,7 @@ static int transfer(struct dummy_hcd *dum_hcd, struct urb *urb, /* FIXME update emulated data toggle too */ - to_host = usb_pipein(urb->pipe); + to_host = usb_urb_dir_in(urb); if (unlikely(len == 0)) is_short = 1; else { @@ -1830,7 +1830,7 @@ static void dummy_timer(struct timer_list *t) /* find the gadget's ep for this request (if configured) */ address = usb_pipeendpoint (urb->pipe); - if (usb_pipein(urb->pipe)) + if (usb_urb_dir_in(urb)) address |= USB_DIR_IN; ep = find_endpoint(dum, address); if (!ep) { @@ -2385,7 +2385,7 @@ static inline ssize_t show_urb(char *buf, size_t size, struct urb *urb) s = "?"; break; } s; }), - ep, ep ? (usb_pipein(urb->pipe) ? "in" : "out") : "", + ep, ep ? (usb_urb_dir_in(urb) ? "in" : "out") : "", ({ char *s; \ switch (usb_pipetype(urb->pipe)) { \ case PIPE_CONTROL: \ @@ -2725,7 +2725,7 @@ static struct platform_driver dummy_hcd_driver = { }; /*-------------------------------------------------------------------------*/ -#define MAX_NUM_UDC 2 +#define MAX_NUM_UDC 32 static struct platform_device *the_udc_pdev[MAX_NUM_UDC]; static struct platform_device *the_hcd_pdev[MAX_NUM_UDC]; diff --git a/drivers/usb/gadget/udc/pch_udc.c b/drivers/usb/gadget/udc/pch_udc.c index 265dab2bbfac..3344fb8c4181 100644 --- a/drivers/usb/gadget/udc/pch_udc.c +++ b/drivers/usb/gadget/udc/pch_udc.c @@ -1519,7 +1519,6 @@ static void pch_udc_free_dma_chain(struct pch_udc_dev *dev, td = phys_to_virt(addr); addr2 = (dma_addr_t)td->next; dma_pool_free(dev->data_requests, td, addr); - td->next = 0x00; addr = addr2; } req->chain_len = 1; diff --git a/drivers/usb/host/ehci-q.c b/drivers/usb/host/ehci-q.c index aa2f77f1506d..8a5c9b3ebe1e 100644 --- a/drivers/usb/host/ehci-q.c +++ b/drivers/usb/host/ehci-q.c @@ -27,6 +27,10 @@ /*-------------------------------------------------------------------------*/ +/* PID Codes that are used here, from EHCI specification, Table 3-16. */ +#define PID_CODE_IN 1 +#define PID_CODE_SETUP 2 + /* fill a qtd, returning how much of the buffer we were able to queue up */ static int @@ -190,7 +194,7 @@ static int qtd_copy_status ( int status = -EINPROGRESS; /* count IN/OUT bytes, not SETUP (even short packets) */ - if (likely (QTD_PID (token) != 2)) + if (likely(QTD_PID(token) != PID_CODE_SETUP)) urb->actual_length += length - QTD_LENGTH (token); /* don't modify error codes */ @@ -206,6 +210,13 @@ static int qtd_copy_status ( if (token & QTD_STS_BABBLE) { /* FIXME "must" disable babbling device's port too */ status = -EOVERFLOW; + /* + * When MMF is active and PID Code is IN, queue is halted. + * EHCI Specification, Table 4-13. + */ + } else if ((token & QTD_STS_MMF) && + (QTD_PID(token) == PID_CODE_IN)) { + status = -EPROTO; /* CERR nonzero + halt --> stall */ } else if (QTD_CERR(token)) { status = -EPIPE; diff --git a/drivers/usb/host/ohci-da8xx.c b/drivers/usb/host/ohci-da8xx.c index 38183ac438c6..1371b0c249ec 100644 --- a/drivers/usb/host/ohci-da8xx.c +++ b/drivers/usb/host/ohci-da8xx.c @@ -415,13 +415,17 @@ static int ohci_da8xx_probe(struct platform_device *pdev) } da8xx_ohci->oc_gpio = devm_gpiod_get_optional(dev, "oc", GPIOD_IN); - if (IS_ERR(da8xx_ohci->oc_gpio)) + if (IS_ERR(da8xx_ohci->oc_gpio)) { + error = PTR_ERR(da8xx_ohci->oc_gpio); goto err; + } if (da8xx_ohci->oc_gpio) { oc_irq = gpiod_to_irq(da8xx_ohci->oc_gpio); - if (oc_irq < 0) + if (oc_irq < 0) { + error = oc_irq; goto err; + } error = devm_request_threaded_irq(dev, oc_irq, NULL, ohci_da8xx_oc_thread, IRQF_TRIGGER_RISING | diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index b7d23c438756..7a3a29e5e9d2 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -806,7 +806,7 @@ static void xhci_del_comp_mod_timer(struct xhci_hcd *xhci, u32 status, static int xhci_handle_usb2_port_link_resume(struct xhci_port *port, u32 *status, u32 portsc, - unsigned long flags) + unsigned long *flags) { struct xhci_bus_state *bus_state; struct xhci_hcd *xhci; @@ -860,11 +860,11 @@ static int xhci_handle_usb2_port_link_resume(struct xhci_port *port, xhci_test_and_clear_bit(xhci, port, PORT_PLC); xhci_set_link_state(xhci, port, XDEV_U0); - spin_unlock_irqrestore(&xhci->lock, flags); + spin_unlock_irqrestore(&xhci->lock, *flags); time_left = wait_for_completion_timeout( &bus_state->rexit_done[wIndex], msecs_to_jiffies(XHCI_MAX_REXIT_TIMEOUT_MS)); - spin_lock_irqsave(&xhci->lock, flags); + spin_lock_irqsave(&xhci->lock, *flags); if (time_left) { slot_id = xhci_find_slot_id_by_port(hcd, xhci, @@ -920,11 +920,13 @@ static void xhci_get_usb3_port_status(struct xhci_port *port, u32 *status, { struct xhci_bus_state *bus_state; struct xhci_hcd *xhci; + struct usb_hcd *hcd; u32 link_state; u32 portnum; bus_state = &port->rhub->bus_state; xhci = hcd_to_xhci(port->rhub->hcd); + hcd = port->rhub->hcd; link_state = portsc & PORT_PLS_MASK; portnum = port->hcd_portnum; @@ -952,12 +954,20 @@ static void xhci_get_usb3_port_status(struct xhci_port *port, u32 *status, bus_state->suspended_ports &= ~(1 << portnum); } + /* remote wake resume signaling complete */ + if (bus_state->port_remote_wakeup & (1 << portnum) && + link_state != XDEV_RESUME && + link_state != XDEV_RECOVERY) { + bus_state->port_remote_wakeup &= ~(1 << portnum); + usb_hcd_end_port_resume(&hcd->self, portnum); + } + xhci_hub_report_usb3_link_state(xhci, status, portsc); xhci_del_comp_mod_timer(xhci, portsc, portnum); } static void xhci_get_usb2_port_status(struct xhci_port *port, u32 *status, - u32 portsc, unsigned long flags) + u32 portsc, unsigned long *flags) { struct xhci_bus_state *bus_state; u32 link_state; @@ -1007,7 +1017,7 @@ static void xhci_get_usb2_port_status(struct xhci_port *port, u32 *status, static u32 xhci_get_port_status(struct usb_hcd *hcd, struct xhci_bus_state *bus_state, u16 wIndex, u32 raw_port_status, - unsigned long flags) + unsigned long *flags) __releases(&xhci->lock) __acquires(&xhci->lock) { @@ -1130,7 +1140,7 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, } trace_xhci_get_port_status(wIndex, temp); status = xhci_get_port_status(hcd, bus_state, wIndex, temp, - flags); + &flags); if (status == 0xffffffff) goto error; diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index e16eda6e2b8b..3b1388fa2f36 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -1909,13 +1909,17 @@ void xhci_mem_cleanup(struct xhci_hcd *xhci) xhci->usb3_rhub.num_ports = 0; xhci->num_active_eps = 0; kfree(xhci->usb2_rhub.ports); + kfree(xhci->usb2_rhub.psi); kfree(xhci->usb3_rhub.ports); + kfree(xhci->usb3_rhub.psi); kfree(xhci->hw_ports); kfree(xhci->rh_bw); kfree(xhci->ext_caps); xhci->usb2_rhub.ports = NULL; + xhci->usb2_rhub.psi = NULL; xhci->usb3_rhub.ports = NULL; + xhci->usb3_rhub.psi = NULL; xhci->hw_ports = NULL; xhci->rh_bw = NULL; xhci->ext_caps = NULL; diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 1e0236e90687..4917c5b033fa 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -48,6 +48,7 @@ #define PCI_DEVICE_ID_INTEL_TITAN_RIDGE_2C_XHCI 0x15e9 #define PCI_DEVICE_ID_INTEL_TITAN_RIDGE_4C_XHCI 0x15ec #define PCI_DEVICE_ID_INTEL_TITAN_RIDGE_DD_XHCI 0x15f0 +#define PCI_DEVICE_ID_INTEL_ICE_LAKE_XHCI 0x8a13 #define PCI_DEVICE_ID_AMD_PROMONTORYA_4 0x43b9 #define PCI_DEVICE_ID_AMD_PROMONTORYA_3 0x43ba @@ -212,7 +213,8 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) pdev->device == PCI_DEVICE_ID_INTEL_ALPINE_RIDGE_C_4C_XHCI || pdev->device == PCI_DEVICE_ID_INTEL_TITAN_RIDGE_2C_XHCI || pdev->device == PCI_DEVICE_ID_INTEL_TITAN_RIDGE_4C_XHCI || - pdev->device == PCI_DEVICE_ID_INTEL_TITAN_RIDGE_DD_XHCI)) + pdev->device == PCI_DEVICE_ID_INTEL_TITAN_RIDGE_DD_XHCI || + pdev->device == PCI_DEVICE_ID_INTEL_ICE_LAKE_XHCI)) xhci->quirks |= XHCI_DEFAULT_PM_RUNTIME_ALLOW; if (pdev->vendor == PCI_VENDOR_ID_ETRON && @@ -517,6 +519,18 @@ static int xhci_pci_resume(struct usb_hcd *hcd, bool hibernated) retval = xhci_resume(xhci, hibernated); return retval; } + +static void xhci_pci_shutdown(struct usb_hcd *hcd) +{ + struct xhci_hcd *xhci = hcd_to_xhci(hcd); + struct pci_dev *pdev = to_pci_dev(hcd->self.controller); + + xhci_shutdown(hcd); + + /* Yet another workaround for spurious wakeups at shutdown with HSW */ + if (xhci->quirks & XHCI_SPURIOUS_WAKEUP) + pci_set_power_state(pdev, PCI_D3hot); +} #endif /* CONFIG_PM */ /*-------------------------------------------------------------------------*/ @@ -554,6 +568,7 @@ static int __init xhci_pci_init(void) #ifdef CONFIG_PM xhci_pci_hc_driver.pci_suspend = xhci_pci_suspend; xhci_pci_hc_driver.pci_resume = xhci_pci_resume; + xhci_pci_hc_driver.shutdown = xhci_pci_shutdown; #endif return pci_register_driver(&xhci_pci_driver); } diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index e7aab31fd9a5..4a2fe56940bd 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -1624,7 +1624,6 @@ static void handle_port_status(struct xhci_hcd *xhci, slot_id = xhci_find_slot_id_by_port(hcd, xhci, hcd_portnum + 1); if (slot_id && xhci->devs[slot_id]) xhci->devs[slot_id]->flags |= VDEV_PORT_ERROR; - bus_state->port_remote_wakeup &= ~(1 << hcd_portnum); } if ((portsc & PORT_PLC) && (portsc & PORT_PLS_MASK) == XDEV_RESUME) { @@ -1644,6 +1643,7 @@ static void handle_port_status(struct xhci_hcd *xhci, */ bus_state->port_remote_wakeup |= 1 << hcd_portnum; xhci_test_and_clear_bit(xhci, port, PORT_PLC); + usb_hcd_start_port_resume(&hcd->self, hcd_portnum); xhci_set_link_state(xhci, port, XDEV_U0); /* Need to wait until the next link state change * indicates the device is actually in U0. @@ -1684,7 +1684,6 @@ static void handle_port_status(struct xhci_hcd *xhci, if (slot_id && xhci->devs[slot_id]) xhci_ring_device(xhci, slot_id); if (bus_state->port_remote_wakeup & (1 << hcd_portnum)) { - bus_state->port_remote_wakeup &= ~(1 << hcd_portnum); xhci_test_and_clear_bit(xhci, port, PORT_PLC); usb_wakeup_notification(hcd->self.root_hub, hcd_portnum + 1); @@ -2378,7 +2377,8 @@ static int handle_tx_event(struct xhci_hcd *xhci, case COMP_SUCCESS: if (EVENT_TRB_LEN(le32_to_cpu(event->transfer_len)) == 0) break; - if (xhci->quirks & XHCI_TRUST_TX_LENGTH) + if (xhci->quirks & XHCI_TRUST_TX_LENGTH || + ep_ring->last_td_was_short) trb_comp_code = COMP_SHORT_PACKET; else xhci_warn_ratelimited(xhci, diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c index 2ff7c911fbd0..dc172513a4aa 100644 --- a/drivers/usb/host/xhci-tegra.c +++ b/drivers/usb/host/xhci-tegra.c @@ -755,7 +755,6 @@ static int tegra_xusb_runtime_suspend(struct device *dev) { struct tegra_xusb *tegra = dev_get_drvdata(dev); - tegra_xusb_phy_disable(tegra); regulator_bulk_disable(tegra->soc->num_supplies, tegra->supplies); tegra_xusb_clk_disable(tegra); @@ -779,16 +778,8 @@ static int tegra_xusb_runtime_resume(struct device *dev) goto disable_clk; } - err = tegra_xusb_phy_enable(tegra); - if (err < 0) { - dev_err(dev, "failed to enable PHYs: %d\n", err); - goto disable_regulator; - } - return 0; -disable_regulator: - regulator_bulk_disable(tegra->soc->num_supplies, tegra->supplies); disable_clk: tegra_xusb_clk_disable(tegra); return err; @@ -1181,6 +1172,12 @@ static int tegra_xusb_probe(struct platform_device *pdev) */ platform_set_drvdata(pdev, tegra); + err = tegra_xusb_phy_enable(tegra); + if (err < 0) { + dev_err(&pdev->dev, "failed to enable PHYs: %d\n", err); + goto put_hcd; + } + pm_runtime_enable(&pdev->dev); if (pm_runtime_enabled(&pdev->dev)) err = pm_runtime_get_sync(&pdev->dev); @@ -1189,7 +1186,7 @@ static int tegra_xusb_probe(struct platform_device *pdev) if (err < 0) { dev_err(&pdev->dev, "failed to enable device: %d\n", err); - goto disable_rpm; + goto disable_phy; } tegra_xusb_config(tegra, regs); @@ -1275,9 +1272,11 @@ static int tegra_xusb_probe(struct platform_device *pdev) put_rpm: if (!pm_runtime_status_suspended(&pdev->dev)) tegra_xusb_runtime_suspend(&pdev->dev); -disable_rpm: - pm_runtime_disable(&pdev->dev); +put_hcd: usb_put_hcd(tegra->hcd); +disable_phy: + tegra_xusb_phy_disable(tegra); + pm_runtime_disable(&pdev->dev); put_powerdomains: if (!of_property_read_bool(pdev->dev.of_node, "power-domains")) { tegra_powergate_power_off(TEGRA_POWERGATE_XUSBC); @@ -1314,6 +1313,8 @@ static int tegra_xusb_remove(struct platform_device *pdev) tegra_xusb_powerdomain_remove(&pdev->dev, tegra); } + tegra_xusb_phy_disable(tegra); + tegra_xusb_padctl_put(tegra->padctl); return 0; diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 6c17e3fe181a..9b3b1b16eafb 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -770,7 +770,7 @@ static void xhci_stop(struct usb_hcd *hcd) * * This will only ever be called with the main usb_hcd (the USB3 roothub). */ -static void xhci_shutdown(struct usb_hcd *hcd) +void xhci_shutdown(struct usb_hcd *hcd) { struct xhci_hcd *xhci = hcd_to_xhci(hcd); @@ -789,11 +789,8 @@ static void xhci_shutdown(struct usb_hcd *hcd) xhci_dbg_trace(xhci, trace_xhci_dbg_init, "xhci_shutdown completed - status = %x", readl(&xhci->op_regs->status)); - - /* Yet another workaround for spurious wakeups at shutdown with HSW */ - if (xhci->quirks & XHCI_SPURIOUS_WAKEUP) - pci_set_power_state(to_pci_dev(hcd->self.sysdev), PCI_D3hot); } +EXPORT_SYMBOL_GPL(xhci_shutdown); #ifdef CONFIG_PM static void xhci_save_registers(struct xhci_hcd *xhci) @@ -973,7 +970,7 @@ static bool xhci_pending_portevent(struct xhci_hcd *xhci) int xhci_suspend(struct xhci_hcd *xhci, bool do_wakeup) { int rc = 0; - unsigned int delay = XHCI_MAX_HALT_USEC; + unsigned int delay = XHCI_MAX_HALT_USEC * 2; struct usb_hcd *hcd = xhci_to_hcd(xhci); u32 command; u32 res; diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index f9f88626a57a..973d665052a2 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -2050,6 +2050,7 @@ int xhci_start(struct xhci_hcd *xhci); int xhci_reset(struct xhci_hcd *xhci); int xhci_run(struct usb_hcd *hcd); int xhci_gen_setup(struct usb_hcd *hcd, xhci_get_quirks_t get_quirks); +void xhci_shutdown(struct usb_hcd *hcd); void xhci_init_driver(struct hc_driver *drv, const struct xhci_driver_overrides *over); int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id); diff --git a/drivers/usb/misc/adutux.c b/drivers/usb/misc/adutux.c index 6f5edb9fc61e..d8d157c4c271 100644 --- a/drivers/usb/misc/adutux.c +++ b/drivers/usb/misc/adutux.c @@ -669,7 +669,7 @@ static int adu_probe(struct usb_interface *interface, init_waitqueue_head(&dev->read_wait); init_waitqueue_head(&dev->write_wait); - res = usb_find_common_endpoints_reverse(&interface->altsetting[0], + res = usb_find_common_endpoints_reverse(interface->cur_altsetting, NULL, NULL, &dev->interrupt_in_endpoint, &dev->interrupt_out_endpoint); diff --git a/drivers/usb/misc/appledisplay.c b/drivers/usb/misc/appledisplay.c index ac92725458b5..ba1eaabc7796 100644 --- a/drivers/usb/misc/appledisplay.c +++ b/drivers/usb/misc/appledisplay.c @@ -164,7 +164,12 @@ static int appledisplay_bl_get_brightness(struct backlight_device *bd) 0, pdata->msgdata, 2, ACD_USB_TIMEOUT); - brightness = pdata->msgdata[1]; + if (retval < 2) { + if (retval >= 0) + retval = -EMSGSIZE; + } else { + brightness = pdata->msgdata[1]; + } mutex_unlock(&pdata->sysfslock); if (retval < 0) @@ -299,6 +304,7 @@ static int appledisplay_probe(struct usb_interface *iface, if (pdata) { if (pdata->urb) { usb_kill_urb(pdata->urb); + cancel_delayed_work_sync(&pdata->work); if (pdata->urbdata) usb_free_coherent(pdata->udev, ACD_URB_BUFFER_LEN, pdata->urbdata, pdata->urb->transfer_dma); diff --git a/drivers/usb/misc/chaoskey.c b/drivers/usb/misc/chaoskey.c index 34e6cd6f40d3..87067c3d6109 100644 --- a/drivers/usb/misc/chaoskey.c +++ b/drivers/usb/misc/chaoskey.c @@ -384,13 +384,17 @@ static int _chaoskey_fill(struct chaoskey *dev) !dev->reading, (started ? NAK_TIMEOUT : ALEA_FIRST_TIMEOUT) ); - if (result < 0) + if (result < 0) { + usb_kill_urb(dev->urb); goto out; + } - if (result == 0) + if (result == 0) { result = -ETIMEDOUT; - else + usb_kill_urb(dev->urb); + } else { result = dev->valid; + } out: /* Let the device go back to sleep eventually */ usb_autopm_put_interface(dev->interface); @@ -526,7 +530,21 @@ static int chaoskey_suspend(struct usb_interface *interface, static int chaoskey_resume(struct usb_interface *interface) { + struct chaoskey *dev; + struct usb_device *udev = interface_to_usbdev(interface); + usb_dbg(interface, "resume"); + dev = usb_get_intfdata(interface); + + /* + * We may have lost power. + * In that case the device that needs a long time + * for the first requests needs an extended timeout + * again + */ + if (le16_to_cpu(udev->descriptor.idVendor) == ALEA_VENDOR_ID) + dev->reads_started = false; + return 0; } #else diff --git a/drivers/usb/misc/idmouse.c b/drivers/usb/misc/idmouse.c index 20b0f91a5d9b..bb24527f3c70 100644 --- a/drivers/usb/misc/idmouse.c +++ b/drivers/usb/misc/idmouse.c @@ -337,7 +337,7 @@ static int idmouse_probe(struct usb_interface *interface, int result; /* check if we have gotten the data or the hid interface */ - iface_desc = &interface->altsetting[0]; + iface_desc = interface->cur_altsetting; if (iface_desc->desc.bInterfaceClass != 0x0A) return -ENODEV; diff --git a/drivers/usb/mon/mon_bin.c b/drivers/usb/mon/mon_bin.c index ac2b4fcc265f..f48a23adbc35 100644 --- a/drivers/usb/mon/mon_bin.c +++ b/drivers/usb/mon/mon_bin.c @@ -1039,12 +1039,18 @@ static long mon_bin_ioctl(struct file *file, unsigned int cmd, unsigned long arg mutex_lock(&rp->fetch_lock); spin_lock_irqsave(&rp->b_lock, flags); - mon_free_buff(rp->b_vec, rp->b_size/CHUNK_SIZE); - kfree(rp->b_vec); - rp->b_vec = vec; - rp->b_size = size; - rp->b_read = rp->b_in = rp->b_out = rp->b_cnt = 0; - rp->cnt_lost = 0; + if (rp->mmap_active) { + mon_free_buff(vec, size/CHUNK_SIZE); + kfree(vec); + ret = -EBUSY; + } else { + mon_free_buff(rp->b_vec, rp->b_size/CHUNK_SIZE); + kfree(rp->b_vec); + rp->b_vec = vec; + rp->b_size = size; + rp->b_read = rp->b_in = rp->b_out = rp->b_cnt = 0; + rp->cnt_lost = 0; + } spin_unlock_irqrestore(&rp->b_lock, flags); mutex_unlock(&rp->fetch_lock); } @@ -1216,13 +1222,21 @@ mon_bin_poll(struct file *file, struct poll_table_struct *wait) static void mon_bin_vma_open(struct vm_area_struct *vma) { struct mon_reader_bin *rp = vma->vm_private_data; + unsigned long flags; + + spin_lock_irqsave(&rp->b_lock, flags); rp->mmap_active++; + spin_unlock_irqrestore(&rp->b_lock, flags); } static void mon_bin_vma_close(struct vm_area_struct *vma) { + unsigned long flags; + struct mon_reader_bin *rp = vma->vm_private_data; + spin_lock_irqsave(&rp->b_lock, flags); rp->mmap_active--; + spin_unlock_irqrestore(&rp->b_lock, flags); } /* @@ -1234,16 +1248,12 @@ static vm_fault_t mon_bin_vma_fault(struct vm_fault *vmf) unsigned long offset, chunk_idx; struct page *pageptr; - mutex_lock(&rp->fetch_lock); offset = vmf->pgoff << PAGE_SHIFT; - if (offset >= rp->b_size) { - mutex_unlock(&rp->fetch_lock); + if (offset >= rp->b_size) return VM_FAULT_SIGBUS; - } chunk_idx = offset / CHUNK_SIZE; pageptr = rp->b_vec[chunk_idx].pg; get_page(pageptr); - mutex_unlock(&rp->fetch_lock); vmf->page = pageptr; return 0; } diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c index bd63450af76a..bf083c1f997f 100644 --- a/drivers/usb/musb/musb_core.c +++ b/drivers/usb/musb/musb_core.c @@ -1840,6 +1840,9 @@ ATTRIBUTE_GROUPS(musb); #define MUSB_QUIRK_B_INVALID_VBUS_91 (MUSB_DEVCTL_BDEVICE | \ (2 << MUSB_DEVCTL_VBUS_SHIFT) | \ MUSB_DEVCTL_SESSION) +#define MUSB_QUIRK_B_DISCONNECT_99 (MUSB_DEVCTL_BDEVICE | \ + (3 << MUSB_DEVCTL_VBUS_SHIFT) | \ + MUSB_DEVCTL_SESSION) #define MUSB_QUIRK_A_DISCONNECT_19 ((3 << MUSB_DEVCTL_VBUS_SHIFT) | \ MUSB_DEVCTL_SESSION) @@ -1862,6 +1865,11 @@ static void musb_pm_runtime_check_session(struct musb *musb) s = MUSB_DEVCTL_FSDEV | MUSB_DEVCTL_LSDEV | MUSB_DEVCTL_HR; switch (devctl & ~s) { + case MUSB_QUIRK_B_DISCONNECT_99: + musb_dbg(musb, "Poll devctl in case of suspend after disconnect\n"); + schedule_delayed_work(&musb->irq_work, + msecs_to_jiffies(1000)); + break; case MUSB_QUIRK_B_INVALID_VBUS_91: if (musb->quirk_retries && !musb->flush_irq_work) { musb_dbg(musb, @@ -2310,6 +2318,9 @@ musb_init_controller(struct device *dev, int nIrq, void __iomem *ctrl) musb_disable_interrupts(musb); musb_writeb(musb->mregs, MUSB_DEVCTL, 0); + /* MUSB_POWER_SOFTCONN might be already set, JZ4740 does this. */ + musb_writeb(musb->mregs, MUSB_POWER, 0); + /* Init IRQ workqueue before request_irq */ INIT_DELAYED_WORK(&musb->irq_work, musb_irq_work); INIT_DELAYED_WORK(&musb->deassert_reset_work, musb_deassert_reset); diff --git a/drivers/usb/musb/musbhsdma.c b/drivers/usb/musb/musbhsdma.c index 5fc6825745f2..2d3751d885b4 100644 --- a/drivers/usb/musb/musbhsdma.c +++ b/drivers/usb/musb/musbhsdma.c @@ -425,7 +425,7 @@ struct dma_controller *musbhs_dma_controller_create(struct musb *musb, controller->controller.channel_abort = dma_channel_abort; if (request_irq(irq, dma_controller_irq, 0, - dev_name(musb->controller), &controller->controller)) { + dev_name(musb->controller), controller)) { dev_err(dev, "request_irq %d failed!\n", irq); musb_dma_controller_destroy(&controller->controller); diff --git a/drivers/usb/renesas_usbhs/common.h b/drivers/usb/renesas_usbhs/common.h index 0824099b905e..ef1735d014da 100644 --- a/drivers/usb/renesas_usbhs/common.h +++ b/drivers/usb/renesas_usbhs/common.h @@ -161,11 +161,12 @@ struct usbhs_priv; #define VBSTS (1 << 7) /* VBUS_0 and VBUSIN_0 Input Status */ #define VALID (1 << 3) /* USB Request Receive */ -#define DVSQ_MASK (0x3 << 4) /* Device State */ +#define DVSQ_MASK (0x7 << 4) /* Device State */ #define POWER_STATE (0 << 4) #define DEFAULT_STATE (1 << 4) #define ADDRESS_STATE (2 << 4) #define CONFIGURATION_STATE (3 << 4) +#define SUSPENDED_STATE (4 << 4) #define CTSQ_MASK (0x7) /* Control Transfer Stage */ #define IDLE_SETUP_STAGE 0 /* Idle stage or setup stage */ diff --git a/drivers/usb/renesas_usbhs/mod_gadget.c b/drivers/usb/renesas_usbhs/mod_gadget.c index cd38d74b3223..53489cafecc1 100644 --- a/drivers/usb/renesas_usbhs/mod_gadget.c +++ b/drivers/usb/renesas_usbhs/mod_gadget.c @@ -457,12 +457,18 @@ static int usbhsg_irq_dev_state(struct usbhs_priv *priv, { struct usbhsg_gpriv *gpriv = usbhsg_priv_to_gpriv(priv); struct device *dev = usbhsg_gpriv_to_dev(gpriv); + int state = usbhs_status_get_device_state(irq_state); gpriv->gadget.speed = usbhs_bus_get_speed(priv); - dev_dbg(dev, "state = %x : speed : %d\n", - usbhs_status_get_device_state(irq_state), - gpriv->gadget.speed); + dev_dbg(dev, "state = %x : speed : %d\n", state, gpriv->gadget.speed); + + if (gpriv->gadget.speed != USB_SPEED_UNKNOWN && + (state & SUSPENDED_STATE)) { + if (gpriv->driver && gpriv->driver->suspend) + gpriv->driver->suspend(&gpriv->gadget); + usb_gadget_set_state(&gpriv->gadget, USB_STATE_SUSPENDED); + } return 0; } diff --git a/drivers/usb/roles/class.c b/drivers/usb/roles/class.c index 94b4e7db2b94..97e3d75b19a3 100644 --- a/drivers/usb/roles/class.c +++ b/drivers/usb/roles/class.c @@ -169,8 +169,8 @@ EXPORT_SYMBOL_GPL(fwnode_usb_role_switch_get); void usb_role_switch_put(struct usb_role_switch *sw) { if (!IS_ERR_OR_NULL(sw)) { - put_device(&sw->dev); module_put(sw->dev.parent->driver->owner); + put_device(&sw->dev); } } EXPORT_SYMBOL_GPL(usb_role_switch_put); diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index 979bef9bfb6b..f5143eedbc48 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -125,6 +125,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x8341) }, /* Siemens MC35PU GPRS Modem */ { USB_DEVICE(0x10C4, 0x8382) }, /* Cygnal Integrated Products, Inc. */ { USB_DEVICE(0x10C4, 0x83A8) }, /* Amber Wireless AMB2560 */ + { USB_DEVICE(0x10C4, 0x83AA) }, /* Mark-10 Digital Force Gauge */ { USB_DEVICE(0x10C4, 0x83D8) }, /* DekTec DTA Plus VHF/UHF Booster/Attenuator */ { USB_DEVICE(0x10C4, 0x8411) }, /* Kyocera GPS Module */ { USB_DEVICE(0x10C4, 0x8418) }, /* IRZ Automation Teleport SG-10 GSM/GPRS Modem */ diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 25e81faf4c24..9ad44a96dfe3 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -1033,6 +1033,9 @@ static const struct usb_device_id id_table_combined[] = { /* Sienna devices */ { USB_DEVICE(FTDI_VID, FTDI_SIENNA_PID) }, { USB_DEVICE(ECHELON_VID, ECHELON_U20_PID) }, + /* U-Blox devices */ + { USB_DEVICE(UBLOX_VID, UBLOX_C099F9P_ZED_PID) }, + { USB_DEVICE(UBLOX_VID, UBLOX_C099F9P_ODIN_PID) }, { } /* Terminating entry */ }; diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index 22d66217cb41..e8373528264c 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -1558,3 +1558,10 @@ */ #define UNJO_VID 0x22B7 #define UNJO_ISODEBUG_V1_PID 0x150D + +/* + * U-Blox products (http://www.u-blox.com). + */ +#define UBLOX_VID 0x1546 +#define UBLOX_C099F9P_ZED_PID 0x0502 +#define UBLOX_C099F9P_ODIN_PID 0x0503 diff --git a/drivers/usb/serial/io_edgeport.c b/drivers/usb/serial/io_edgeport.c index 48a439298a68..9690a5f4b9d6 100644 --- a/drivers/usb/serial/io_edgeport.c +++ b/drivers/usb/serial/io_edgeport.c @@ -2901,16 +2901,18 @@ static int edge_startup(struct usb_serial *serial) response = 0; if (edge_serial->is_epic) { + struct usb_host_interface *alt; + + alt = serial->interface->cur_altsetting; + /* EPIC thing, set up our interrupt polling now and our read * urb, so that the device knows it really is connected. */ interrupt_in_found = bulk_in_found = bulk_out_found = false; - for (i = 0; i < serial->interface->altsetting[0] - .desc.bNumEndpoints; ++i) { + for (i = 0; i < alt->desc.bNumEndpoints; ++i) { struct usb_endpoint_descriptor *endpoint; int buffer_size; - endpoint = &serial->interface->altsetting[0]. - endpoint[i].desc; + endpoint = &alt->endpoint[i].desc; buffer_size = usb_endpoint_maxp(endpoint); if (!interrupt_in_found && (usb_endpoint_is_int_in(endpoint))) { diff --git a/drivers/usb/serial/mos7720.c b/drivers/usb/serial/mos7720.c index 18110225d506..2ec4eeacebc7 100644 --- a/drivers/usb/serial/mos7720.c +++ b/drivers/usb/serial/mos7720.c @@ -1833,10 +1833,6 @@ static int mos7720_startup(struct usb_serial *serial) product = le16_to_cpu(serial->dev->descriptor.idProduct); dev = serial->dev; - /* setting configuration feature to one */ - usb_control_msg(serial->dev, usb_sndctrlpipe(serial->dev, 0), - (__u8)0x03, 0x00, 0x01, 0x00, NULL, 0x00, 5000); - if (product == MOSCHIP_DEVICE_ID_7715) { struct urb *urb = serial->port[0]->interrupt_in_urb; diff --git a/drivers/usb/serial/mos7840.c b/drivers/usb/serial/mos7840.c index a698d46ba773..ab4bf8d6d7df 100644 --- a/drivers/usb/serial/mos7840.c +++ b/drivers/usb/serial/mos7840.c @@ -119,11 +119,15 @@ /* This driver also supports * ATEN UC2324 device using Moschip MCS7840 * ATEN UC2322 device using Moschip MCS7820 + * MOXA UPort 2210 device using Moschip MCS7820 */ #define USB_VENDOR_ID_ATENINTL 0x0557 #define ATENINTL_DEVICE_ID_UC2324 0x2011 #define ATENINTL_DEVICE_ID_UC2322 0x7820 +#define USB_VENDOR_ID_MOXA 0x110a +#define MOXA_DEVICE_ID_2210 0x2210 + /* Interrupt Routine Defines */ #define SERIAL_IIR_RLS 0x06 @@ -195,6 +199,7 @@ static const struct usb_device_id id_table[] = { {USB_DEVICE(USB_VENDOR_ID_BANDB, BANDB_DEVICE_ID_USOPTL2_4)}, {USB_DEVICE(USB_VENDOR_ID_ATENINTL, ATENINTL_DEVICE_ID_UC2324)}, {USB_DEVICE(USB_VENDOR_ID_ATENINTL, ATENINTL_DEVICE_ID_UC2322)}, + {USB_DEVICE(USB_VENDOR_ID_MOXA, MOXA_DEVICE_ID_2210)}, {} /* terminating entry */ }; MODULE_DEVICE_TABLE(usb, id_table); @@ -2020,6 +2025,7 @@ static int mos7840_probe(struct usb_serial *serial, const struct usb_device_id *id) { u16 product = le16_to_cpu(serial->dev->descriptor.idProduct); + u16 vid = le16_to_cpu(serial->dev->descriptor.idVendor); u8 *buf; int device_type; @@ -2030,6 +2036,11 @@ static int mos7840_probe(struct usb_serial *serial, goto out; } + if (vid == USB_VENDOR_ID_MOXA && product == MOXA_DEVICE_ID_2210) { + device_type = MOSCHIP_DEVICE_ID_7820; + goto out; + } + buf = kzalloc(VENDOR_READ_LENGTH, GFP_KERNEL); if (!buf) return -ENOMEM; @@ -2279,11 +2290,6 @@ static int mos7840_port_probe(struct usb_serial_port *port) goto error; } else dev_dbg(&port->dev, "ZLP_REG5 Writing success status%d\n", status); - - /* setting configuration feature to one */ - usb_control_msg(serial->dev, usb_sndctrlpipe(serial->dev, 0), - 0x03, 0x00, 0x01, 0x00, NULL, 0x00, - MOS_WDR_TIMEOUT); } return 0; error: diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 06ab016be0b6..2d919d0e6e45 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -197,6 +197,7 @@ static void option_instat_callback(struct urb *urb); #define DELL_PRODUCT_5804_MINICARD_ATT 0x819b /* Novatel E371 */ #define DELL_PRODUCT_5821E 0x81d7 +#define DELL_PRODUCT_5821E_ESIM 0x81e0 #define KYOCERA_VENDOR_ID 0x0c88 #define KYOCERA_PRODUCT_KPC650 0x17da @@ -566,6 +567,9 @@ static void option_instat_callback(struct urb *urb); /* Interface must have two endpoints */ #define NUMEP2 BIT(16) +/* Device needs ZLP */ +#define ZLP BIT(17) + static const struct usb_device_id option_ids[] = { { USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_COLT) }, @@ -1044,6 +1048,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(DELL_VENDOR_ID, DELL_PRODUCT_5804_MINICARD_ATT, 0xff, 0xff, 0xff) }, { USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5821E), .driver_info = RSVD(0) | RSVD(1) | RSVD(6) }, + { USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5821E_ESIM), + .driver_info = RSVD(0) | RSVD(1) | RSVD(6) }, { USB_DEVICE(ANYDATA_VENDOR_ID, ANYDATA_PRODUCT_ADU_E100A) }, /* ADU-E100, ADU-310 */ { USB_DEVICE(ANYDATA_VENDOR_ID, ANYDATA_PRODUCT_ADU_500A) }, { USB_DEVICE(ANYDATA_VENDOR_ID, ANYDATA_PRODUCT_ADU_620UW) }, @@ -1169,6 +1175,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(0) | RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1102, 0xff), /* Telit ME910 (ECM) */ .driver_info = NCTRL(0) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x110a, 0xff), /* Telit ME910G1 */ + .driver_info = NCTRL(0) | RSVD(3) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910), .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910_USBCFG4), @@ -1193,6 +1201,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(0) | RSVD(1) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1901, 0xff), /* Telit LN940 (MBIM) */ .driver_info = NCTRL(0) }, + { USB_DEVICE(TELIT_VENDOR_ID, 0x9010), /* Telit SBL FN980 flashing device */ + .driver_info = NCTRL(0) | ZLP }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MF622, 0xff, 0xff, 0xff) }, /* ZTE WCDMA products */ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0002, 0xff, 0xff, 0xff), .driver_info = RSVD(1) }, @@ -1990,6 +2000,10 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0xa31d, 0xff, 0x06, 0x13) }, { USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0xa31d, 0xff, 0x06, 0x14) }, { USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0xa31d, 0xff, 0x06, 0x1b) }, + { USB_DEVICE(0x0489, 0xe0b4), /* Foxconn T77W968 */ + .driver_info = RSVD(0) | RSVD(1) | RSVD(6) }, + { USB_DEVICE(0x0489, 0xe0b5), /* Foxconn T77W968 ESIM */ + .driver_info = RSVD(0) | RSVD(1) | RSVD(6) }, { USB_DEVICE(0x1508, 0x1001), /* Fibocom NL668 */ .driver_info = RSVD(4) | RSVD(5) | RSVD(6) }, { USB_DEVICE(0x2cb7, 0x0104), /* Fibocom NL678 series */ @@ -2090,6 +2104,9 @@ static int option_attach(struct usb_serial *serial) if (!(device_flags & NCTRL(iface_desc->bInterfaceNumber))) data->use_send_setup = 1; + if (device_flags & ZLP) + data->use_zlp = 1; + spin_lock_init(&data->susp_lock); usb_set_serial_data(serial, data); diff --git a/drivers/usb/serial/usb-wwan.h b/drivers/usb/serial/usb-wwan.h index 1c120eaf4091..934e9361cf6b 100644 --- a/drivers/usb/serial/usb-wwan.h +++ b/drivers/usb/serial/usb-wwan.h @@ -38,6 +38,7 @@ struct usb_wwan_intf_private { spinlock_t susp_lock; unsigned int suspended:1; unsigned int use_send_setup:1; + unsigned int use_zlp:1; int in_flight; unsigned int open_ports; void *private; diff --git a/drivers/usb/serial/usb_wwan.c b/drivers/usb/serial/usb_wwan.c index 7e855c87e4f7..13be21aad2f4 100644 --- a/drivers/usb/serial/usb_wwan.c +++ b/drivers/usb/serial/usb_wwan.c @@ -461,6 +461,7 @@ static struct urb *usb_wwan_setup_urb(struct usb_serial_port *port, void (*callback) (struct urb *)) { struct usb_serial *serial = port->serial; + struct usb_wwan_intf_private *intfdata = usb_get_serial_data(serial); struct urb *urb; urb = usb_alloc_urb(0, GFP_KERNEL); /* No ISO */ @@ -471,6 +472,9 @@ static struct urb *usb_wwan_setup_urb(struct usb_serial_port *port, usb_sndbulkpipe(serial->dev, endpoint) | dir, buf, len, callback, ctx); + if (intfdata->use_zlp && dir == USB_DIR_OUT) + urb->transfer_flags |= URB_ZERO_PACKET; + return urb; } diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c index 54a3c8195c96..2adcabe060c5 100644 --- a/drivers/usb/storage/scsiglue.c +++ b/drivers/usb/storage/scsiglue.c @@ -135,7 +135,8 @@ static int slave_configure(struct scsi_device *sdev) * For such controllers we need to make sure the block layer sets * up bounce buffers in addressable memory. */ - if (!hcd_uses_dma(bus_to_hcd(us->pusb_dev->bus))) + if (!hcd_uses_dma(bus_to_hcd(us->pusb_dev->bus)) || + (bus_to_hcd(us->pusb_dev->bus)->localmem_pool != NULL)) blk_queue_bounce_limit(sdev->request_queue, BLK_BOUNCE_HIGH); /* diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index 34538253f12c..475b9c692827 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -825,6 +825,10 @@ static int uas_slave_configure(struct scsi_device *sdev) sdev->wce_default_on = 1; } + /* Some disks cannot handle READ_CAPACITY_16 */ + if (devinfo->flags & US_FL_NO_READ_CAPACITY_16) + sdev->no_read_capacity_16 = 1; + /* * Some disks return the total number of blocks in response * to READ CAPACITY rather than the highest block number. @@ -833,6 +837,12 @@ static int uas_slave_configure(struct scsi_device *sdev) if (devinfo->flags & US_FL_FIX_CAPACITY) sdev->fix_capacity = 1; + /* + * in some cases we have to guess + */ + if (devinfo->flags & US_FL_CAPACITY_HEURISTICS) + sdev->guess_capacity = 1; + /* * Some devices don't like MODE SENSE with page=0x3f, * which is the command used for checking if a device diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c index 94a3eda62add..a400b65cf17b 100644 --- a/drivers/usb/typec/class.c +++ b/drivers/usb/typec/class.c @@ -1592,14 +1592,16 @@ struct typec_port *typec_register_port(struct device *parent, port->sw = typec_switch_get(&port->dev); if (IS_ERR(port->sw)) { + ret = PTR_ERR(port->sw); put_device(&port->dev); - return ERR_CAST(port->sw); + return ERR_PTR(ret); } port->mux = typec_mux_get(&port->dev, NULL); if (IS_ERR(port->mux)) { + ret = PTR_ERR(port->mux); put_device(&port->dev); - return ERR_CAST(port->mux); + return ERR_PTR(ret); } ret = device_add(&port->dev); diff --git a/drivers/usb/typec/tcpm/Kconfig b/drivers/usb/typec/tcpm/Kconfig index 72481bbb2af3..5b986d6c801d 100644 --- a/drivers/usb/typec/tcpm/Kconfig +++ b/drivers/usb/typec/tcpm/Kconfig @@ -32,6 +32,7 @@ endif # TYPEC_TCPCI config TYPEC_FUSB302 tristate "Fairchild FUSB302 Type-C chip driver" depends on I2C + depends on EXTCON || !EXTCON help The Fairchild FUSB302 Type-C chip driver that works with Type-C Port Controller Manager to provide USB PD and USB diff --git a/drivers/usb/typec/tcpm/tcpci.c b/drivers/usb/typec/tcpm/tcpci.c index c1f7073a56de..8b4ff9fff340 100644 --- a/drivers/usb/typec/tcpm/tcpci.c +++ b/drivers/usb/typec/tcpm/tcpci.c @@ -432,20 +432,30 @@ irqreturn_t tcpci_irq(struct tcpci *tcpci) if (status & TCPC_ALERT_RX_STATUS) { struct pd_message msg; - unsigned int cnt; + unsigned int cnt, payload_cnt; u16 header; regmap_read(tcpci->regmap, TCPC_RX_BYTE_CNT, &cnt); + /* + * 'cnt' corresponds to READABLE_BYTE_COUNT in section 4.4.14 + * of the TCPCI spec [Rev 2.0 Ver 1.0 October 2017] and is + * defined in table 4-36 as one greater than the number of + * bytes received. And that number includes the header. So: + */ + if (cnt > 3) + payload_cnt = cnt - (1 + sizeof(msg.header)); + else + payload_cnt = 0; tcpci_read16(tcpci, TCPC_RX_HDR, &header); msg.header = cpu_to_le16(header); - if (WARN_ON(cnt > sizeof(msg.payload))) - cnt = sizeof(msg.payload); + if (WARN_ON(payload_cnt > sizeof(msg.payload))) + payload_cnt = sizeof(msg.payload); - if (cnt > 0) + if (payload_cnt > 0) regmap_raw_read(tcpci->regmap, TCPC_RX_DATA, - &msg.payload, cnt); + &msg.payload, payload_cnt); /* Read complete, clear RX status alert bit */ tcpci_write16(tcpci, TCPC_ALERT, TCPC_ALERT_RX_STATUS); diff --git a/drivers/usb/usbip/Kconfig b/drivers/usb/usbip/Kconfig index 2f86b28fa3da..7bbae7a08642 100644 --- a/drivers/usb/usbip/Kconfig +++ b/drivers/usb/usbip/Kconfig @@ -4,6 +4,7 @@ config USBIP_CORE tristate "USB/IP support" depends on NET select USB_COMMON + select SGL_ALLOC ---help--- This enables pushing USB packets over IP to allow remote machines direct access to USB devices. It provides the diff --git a/drivers/usb/usbip/stub_rx.c b/drivers/usb/usbip/stub_rx.c index 66edfeea68fe..e2b019532234 100644 --- a/drivers/usb/usbip/stub_rx.c +++ b/drivers/usb/usbip/stub_rx.c @@ -470,18 +470,50 @@ static void stub_recv_cmd_submit(struct stub_device *sdev, if (pipe == -1) return; + /* + * Smatch reported the error case where use_sg is true and buf_len is 0. + * In this case, It adds SDEV_EVENT_ERROR_MALLOC and stub_priv will be + * released by stub event handler and connection will be shut down. + */ priv = stub_priv_alloc(sdev, pdu); if (!priv) return; buf_len = (unsigned long long)pdu->u.cmd_submit.transfer_buffer_length; + if (use_sg && !buf_len) { + dev_err(&udev->dev, "sg buffer with zero length\n"); + goto err_malloc; + } + /* allocate urb transfer buffer, if needed */ if (buf_len) { if (use_sg) { sgl = sgl_alloc(buf_len, GFP_KERNEL, &nents); if (!sgl) goto err_malloc; + + /* Check if the server's HCD supports SG */ + if (!udev->bus->sg_tablesize) { + /* + * If the server's HCD doesn't support SG, break + * a single SG request into several URBs and map + * each SG list entry to corresponding URB + * buffer. The previously allocated SG list is + * stored in priv->sgl (If the server's HCD + * support SG, SG list is stored only in + * urb->sg) and it is used as an indicator that + * the server split single SG request into + * several URBs. Later, priv->sgl is used by + * stub_complete() and stub_send_ret_submit() to + * reassemble the divied URBs. + */ + support_sg = 0; + num_urbs = nents; + priv->completed_urbs = 0; + pdu->u.cmd_submit.transfer_flags &= + ~URB_DMA_MAP_SG; + } } else { buffer = kzalloc(buf_len, GFP_KERNEL); if (!buffer) @@ -489,24 +521,6 @@ static void stub_recv_cmd_submit(struct stub_device *sdev, } } - /* Check if the server's HCD supports SG */ - if (use_sg && !udev->bus->sg_tablesize) { - /* - * If the server's HCD doesn't support SG, break a single SG - * request into several URBs and map each SG list entry to - * corresponding URB buffer. The previously allocated SG - * list is stored in priv->sgl (If the server's HCD support SG, - * SG list is stored only in urb->sg) and it is used as an - * indicator that the server split single SG request into - * several URBs. Later, priv->sgl is used by stub_complete() and - * stub_send_ret_submit() to reassemble the divied URBs. - */ - support_sg = 0; - num_urbs = nents; - priv->completed_urbs = 0; - pdu->u.cmd_submit.transfer_flags &= ~URB_DMA_MAP_SG; - } - /* allocate urb array */ priv->num_urbs = num_urbs; priv->urbs = kmalloc_array(num_urbs, sizeof(*priv->urbs), GFP_KERNEL); diff --git a/drivers/usb/usbip/usbip_common.c b/drivers/usb/usbip/usbip_common.c index 6532d68e8808..e4b96674c405 100644 --- a/drivers/usb/usbip/usbip_common.c +++ b/drivers/usb/usbip/usbip_common.c @@ -727,6 +727,9 @@ int usbip_recv_xbuff(struct usbip_device *ud, struct urb *urb) copy -= recv; ret += recv; + + if (!copy) + break; } if (ret != size) diff --git a/drivers/usb/usbip/vhci_rx.c b/drivers/usb/usbip/vhci_rx.c index 33f8972ba842..00fc98741c5d 100644 --- a/drivers/usb/usbip/vhci_rx.c +++ b/drivers/usb/usbip/vhci_rx.c @@ -77,16 +77,21 @@ static void vhci_recv_ret_submit(struct vhci_device *vdev, usbip_pack_pdu(pdu, urb, USBIP_RET_SUBMIT, 0); /* recv transfer buffer */ - if (usbip_recv_xbuff(ud, urb) < 0) - return; + if (usbip_recv_xbuff(ud, urb) < 0) { + urb->status = -EPROTO; + goto error; + } /* recv iso_packet_descriptor */ - if (usbip_recv_iso(ud, urb) < 0) - return; + if (usbip_recv_iso(ud, urb) < 0) { + urb->status = -EPROTO; + goto error; + } /* restore the padding in iso packets */ usbip_pad_iso(ud, urb); +error: if (usbip_dbg_flag_vhci_rx) usbip_dump_urb(urb); diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c index 3fa3f728fb39..2056f3f85f59 100644 --- a/drivers/vfio/pci/vfio_pci_intrs.c +++ b/drivers/vfio/pci/vfio_pci_intrs.c @@ -294,8 +294,8 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev, irq = pci_irq_vector(pdev, vector); if (vdev->ctx[vector].trigger) { - free_irq(irq, vdev->ctx[vector].trigger); irq_bypass_unregister_producer(&vdev->ctx[vector].producer); + free_irq(irq, vdev->ctx[vector].trigger); kfree(vdev->ctx[vector].name); eventfd_ctx_put(vdev->ctx[vector].trigger); vdev->ctx[vector].trigger = NULL; diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 9f57736fe15e..88a5aa6624b4 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -437,7 +437,9 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work) virtio_transport_deliver_tap_pkt(pkt); /* Only accept correctly addressed packets */ - if (le64_to_cpu(pkt->hdr.src_cid) == vsock->guest_cid) + if (le64_to_cpu(pkt->hdr.src_cid) == vsock->guest_cid && + le64_to_cpu(pkt->hdr.dst_cid) == + vhost_transport_get_local_cid()) virtio_transport_recv_pkt(pkt); else virtio_transport_free_pkt(pkt); diff --git a/drivers/video/hdmi.c b/drivers/video/hdmi.c index b939bc28d886..9c82e2a0a411 100644 --- a/drivers/video/hdmi.c +++ b/drivers/video/hdmi.c @@ -1576,12 +1576,12 @@ static int hdmi_avi_infoframe_unpack(struct hdmi_avi_infoframe *frame, if (ptr[0] & 0x10) frame->active_aspect = ptr[1] & 0xf; if (ptr[0] & 0x8) { - frame->top_bar = (ptr[5] << 8) + ptr[6]; - frame->bottom_bar = (ptr[7] << 8) + ptr[8]; + frame->top_bar = (ptr[6] << 8) | ptr[5]; + frame->bottom_bar = (ptr[8] << 8) | ptr[7]; } if (ptr[0] & 0x4) { - frame->left_bar = (ptr[9] << 8) + ptr[10]; - frame->right_bar = (ptr[11] << 8) + ptr[12]; + frame->left_bar = (ptr[10] << 8) | ptr[9]; + frame->right_bar = (ptr[12] << 8) | ptr[11]; } frame->scan_mode = ptr[0] & 0x3; diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index e05679c478e2..9f4117766bb1 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -721,6 +721,17 @@ static int virtballoon_migratepage(struct balloon_dev_info *vb_dev_info, get_page(newpage); /* balloon reference */ + /* + * When we migrate a page to a different zone and adjusted the + * managed page count when inflating, we have to fixup the count of + * both involved zones. + */ + if (!virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM) && + page_zone(page) != page_zone(newpage)) { + adjust_managed_page_count(page, 1); + adjust_managed_page_count(newpage, -1); + } + /* balloon's page migration 1st step -- inflate "newpage" */ spin_lock_irqsave(&vb_dev_info->pages_lock, flags); balloon_page_insert(vb_dev_info, newpage); diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig index 58e7c100b6ad..4c761abc5688 100644 --- a/drivers/watchdog/Kconfig +++ b/drivers/watchdog/Kconfig @@ -1444,6 +1444,7 @@ config SMSC37B787_WDT config TQMX86_WDT tristate "TQ-Systems TQMX86 Watchdog Timer" depends on X86 + select WATCHDOG_CORE help This is the driver for the hardware watchdog timer in the TQMX86 IO controller found on some of their ComExpress Modules. diff --git a/drivers/watchdog/aspeed_wdt.c b/drivers/watchdog/aspeed_wdt.c index 4ec0906bf12c..7e00960651fa 100644 --- a/drivers/watchdog/aspeed_wdt.c +++ b/drivers/watchdog/aspeed_wdt.c @@ -258,11 +258,6 @@ static int aspeed_wdt_probe(struct platform_device *pdev) if (IS_ERR(wdt->base)) return PTR_ERR(wdt->base); - /* - * The ast2400 wdt can run at PCLK, or 1MHz. The ast2500 only - * runs at 1MHz. We chose to always run at 1MHz, as there's no - * good reason to have a faster watchdog counter. - */ wdt->wdd.info = &aspeed_wdt_info; wdt->wdd.ops = &aspeed_wdt_ops; wdt->wdd.max_hw_heartbeat_ms = WDT_MAX_TIMEOUT_MS; @@ -278,7 +273,16 @@ static int aspeed_wdt_probe(struct platform_device *pdev) return -EINVAL; config = ofdid->data; - wdt->ctrl = WDT_CTRL_1MHZ_CLK; + /* + * On clock rates: + * - ast2400 wdt can run at PCLK, or 1MHz + * - ast2500 only runs at 1MHz, hard coding bit 4 to 1 + * - ast2600 always runs at 1MHz + * + * Set the ast2400 to run at 1MHz as it simplifies the driver. + */ + if (of_device_is_compatible(np, "aspeed,ast2400-wdt")) + wdt->ctrl = WDT_CTRL_1MHZ_CLK; /* * Control reset on a per-device basis to ensure the diff --git a/drivers/watchdog/imx7ulp_wdt.c b/drivers/watchdog/imx7ulp_wdt.c index 5ce51026989a..ba5d535a6db2 100644 --- a/drivers/watchdog/imx7ulp_wdt.c +++ b/drivers/watchdog/imx7ulp_wdt.c @@ -106,12 +106,28 @@ static int imx7ulp_wdt_set_timeout(struct watchdog_device *wdog, return 0; } +static int imx7ulp_wdt_restart(struct watchdog_device *wdog, + unsigned long action, void *data) +{ + struct imx7ulp_wdt_device *wdt = watchdog_get_drvdata(wdog); + + imx7ulp_wdt_enable(wdt->base, true); + imx7ulp_wdt_set_timeout(&wdt->wdd, 1); + + /* wait for wdog to fire */ + while (true) + ; + + return NOTIFY_DONE; +} + static const struct watchdog_ops imx7ulp_wdt_ops = { .owner = THIS_MODULE, .start = imx7ulp_wdt_start, .stop = imx7ulp_wdt_stop, .ping = imx7ulp_wdt_ping, .set_timeout = imx7ulp_wdt_set_timeout, + .restart = imx7ulp_wdt_restart, }; static const struct watchdog_info imx7ulp_wdt_info = { diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c index dbd2ad4c9294..62483a99105c 100644 --- a/drivers/watchdog/watchdog_dev.c +++ b/drivers/watchdog/watchdog_dev.c @@ -34,7 +34,6 @@ #include /* For __init/__exit/... */ #include /* For hrtimers */ #include /* For printk/panic/... */ -#include /* For data references */ #include /* For kthread_work */ #include /* For handling misc devices */ #include /* For module stuff/... */ @@ -52,14 +51,14 @@ /* * struct watchdog_core_data - watchdog core internal data - * @kref: Reference count. + * @dev: The watchdog's internal device * @cdev: The watchdog's Character device. * @wdd: Pointer to watchdog device. * @lock: Lock for watchdog core. * @status: Watchdog core internal status bits. */ struct watchdog_core_data { - struct kref kref; + struct device dev; struct cdev cdev; struct watchdog_device *wdd; struct mutex lock; @@ -158,7 +157,8 @@ static inline void watchdog_update_worker(struct watchdog_device *wdd) ktime_t t = watchdog_next_keepalive(wdd); if (t > 0) - hrtimer_start(&wd_data->timer, t, HRTIMER_MODE_REL); + hrtimer_start(&wd_data->timer, t, + HRTIMER_MODE_REL_HARD); } else { hrtimer_cancel(&wd_data->timer); } @@ -177,7 +177,7 @@ static int __watchdog_ping(struct watchdog_device *wdd) if (ktime_after(earliest_keepalive, now)) { hrtimer_start(&wd_data->timer, ktime_sub(earliest_keepalive, now), - HRTIMER_MODE_REL); + HRTIMER_MODE_REL_HARD); return 0; } @@ -839,7 +839,7 @@ static int watchdog_open(struct inode *inode, struct file *file) file->private_data = wd_data; if (!hw_running) - kref_get(&wd_data->kref); + get_device(&wd_data->dev); /* * open_timeout only applies for the first open from @@ -860,11 +860,11 @@ static int watchdog_open(struct inode *inode, struct file *file) return err; } -static void watchdog_core_data_release(struct kref *kref) +static void watchdog_core_data_release(struct device *dev) { struct watchdog_core_data *wd_data; - wd_data = container_of(kref, struct watchdog_core_data, kref); + wd_data = container_of(dev, struct watchdog_core_data, dev); kfree(wd_data); } @@ -924,7 +924,7 @@ static int watchdog_release(struct inode *inode, struct file *file) */ if (!running) { module_put(wd_data->cdev.owner); - kref_put(&wd_data->kref, watchdog_core_data_release); + put_device(&wd_data->dev); } return 0; } @@ -943,17 +943,22 @@ static struct miscdevice watchdog_miscdev = { .fops = &watchdog_fops, }; +static struct class watchdog_class = { + .name = "watchdog", + .owner = THIS_MODULE, + .dev_groups = wdt_groups, +}; + /* * watchdog_cdev_register: register watchdog character device * @wdd: watchdog device - * @devno: character device number * * Register a watchdog character device including handling the legacy * /dev/watchdog node. /dev/watchdog is actually a miscdevice and * thus we set it up like that. */ -static int watchdog_cdev_register(struct watchdog_device *wdd, dev_t devno) +static int watchdog_cdev_register(struct watchdog_device *wdd) { struct watchdog_core_data *wd_data; int err; @@ -961,7 +966,6 @@ static int watchdog_cdev_register(struct watchdog_device *wdd, dev_t devno) wd_data = kzalloc(sizeof(struct watchdog_core_data), GFP_KERNEL); if (!wd_data) return -ENOMEM; - kref_init(&wd_data->kref); mutex_init(&wd_data->lock); wd_data->wdd = wdd; @@ -971,7 +975,7 @@ static int watchdog_cdev_register(struct watchdog_device *wdd, dev_t devno) return -ENODEV; kthread_init_work(&wd_data->work, watchdog_ping_work); - hrtimer_init(&wd_data->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer_init(&wd_data->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); wd_data->timer.function = watchdog_timer_expired; if (wdd->id == 0) { @@ -990,23 +994,33 @@ static int watchdog_cdev_register(struct watchdog_device *wdd, dev_t devno) } } + device_initialize(&wd_data->dev); + wd_data->dev.devt = MKDEV(MAJOR(watchdog_devt), wdd->id); + wd_data->dev.class = &watchdog_class; + wd_data->dev.parent = wdd->parent; + wd_data->dev.groups = wdd->groups; + wd_data->dev.release = watchdog_core_data_release; + dev_set_drvdata(&wd_data->dev, wdd); + dev_set_name(&wd_data->dev, "watchdog%d", wdd->id); + /* Fill in the data structures */ cdev_init(&wd_data->cdev, &watchdog_fops); - wd_data->cdev.owner = wdd->ops->owner; /* Add the device */ - err = cdev_add(&wd_data->cdev, devno, 1); + err = cdev_device_add(&wd_data->cdev, &wd_data->dev); if (err) { pr_err("watchdog%d unable to add device %d:%d\n", wdd->id, MAJOR(watchdog_devt), wdd->id); if (wdd->id == 0) { misc_deregister(&watchdog_miscdev); old_wd_data = NULL; - kref_put(&wd_data->kref, watchdog_core_data_release); + put_device(&wd_data->dev); } return err; } + wd_data->cdev.owner = wdd->ops->owner; + /* Record time of most recent heartbeat as 'just before now'. */ wd_data->last_hw_keepalive = ktime_sub(ktime_get(), 1); watchdog_set_open_deadline(wd_data); @@ -1017,9 +1031,10 @@ static int watchdog_cdev_register(struct watchdog_device *wdd, dev_t devno) */ if (watchdog_hw_running(wdd)) { __module_get(wdd->ops->owner); - kref_get(&wd_data->kref); + get_device(&wd_data->dev); if (handle_boot_enabled) - hrtimer_start(&wd_data->timer, 0, HRTIMER_MODE_REL); + hrtimer_start(&wd_data->timer, 0, + HRTIMER_MODE_REL_HARD); else pr_info("watchdog%d running and kernel based pre-userspace handler disabled\n", wdd->id); @@ -1040,7 +1055,7 @@ static void watchdog_cdev_unregister(struct watchdog_device *wdd) { struct watchdog_core_data *wd_data = wdd->wd_data; - cdev_del(&wd_data->cdev); + cdev_device_del(&wd_data->cdev, &wd_data->dev); if (wdd->id == 0) { misc_deregister(&watchdog_miscdev); old_wd_data = NULL; @@ -1059,15 +1074,9 @@ static void watchdog_cdev_unregister(struct watchdog_device *wdd) hrtimer_cancel(&wd_data->timer); kthread_cancel_work_sync(&wd_data->work); - kref_put(&wd_data->kref, watchdog_core_data_release); + put_device(&wd_data->dev); } -static struct class watchdog_class = { - .name = "watchdog", - .owner = THIS_MODULE, - .dev_groups = wdt_groups, -}; - static int watchdog_reboot_notifier(struct notifier_block *nb, unsigned long code, void *data) { @@ -1098,27 +1107,14 @@ static int watchdog_reboot_notifier(struct notifier_block *nb, int watchdog_dev_register(struct watchdog_device *wdd) { - struct device *dev; - dev_t devno; int ret; - devno = MKDEV(MAJOR(watchdog_devt), wdd->id); - - ret = watchdog_cdev_register(wdd, devno); + ret = watchdog_cdev_register(wdd); if (ret) return ret; - dev = device_create_with_groups(&watchdog_class, wdd->parent, - devno, wdd, wdd->groups, - "watchdog%d", wdd->id); - if (IS_ERR(dev)) { - watchdog_cdev_unregister(wdd); - return PTR_ERR(dev); - } - ret = watchdog_register_pretimeout(wdd); if (ret) { - device_destroy(&watchdog_class, devno); watchdog_cdev_unregister(wdd); return ret; } @@ -1126,7 +1122,8 @@ int watchdog_dev_register(struct watchdog_device *wdd) if (test_bit(WDOG_STOP_ON_REBOOT, &wdd->status)) { wdd->reboot_nb.notifier_call = watchdog_reboot_notifier; - ret = devm_register_reboot_notifier(dev, &wdd->reboot_nb); + ret = devm_register_reboot_notifier(&wdd->wd_data->dev, + &wdd->reboot_nb); if (ret) { pr_err("watchdog%d: Cannot register reboot notifier (%d)\n", wdd->id, ret); @@ -1148,7 +1145,6 @@ int watchdog_dev_register(struct watchdog_device *wdd) void watchdog_dev_unregister(struct watchdog_device *wdd) { watchdog_unregister_pretimeout(wdd); - device_destroy(&watchdog_class, wdd->wd_data->cdev.dev); watchdog_cdev_unregister(wdd); } diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index 79cc75096f42..a50dadd01093 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -141,7 +141,8 @@ config XEN_GNTDEV config XEN_GNTDEV_DMABUF bool "Add support for dma-buf grant access device driver extension" - depends on XEN_GNTDEV && XEN_GRANT_DMA_ALLOC && DMA_SHARED_BUFFER + depends on XEN_GNTDEV && XEN_GRANT_DMA_ALLOC + select DMA_SHARED_BUFFER help Allows userspace processes and kernel modules to use Xen backed dma-buf implementation. With this extension grant references to diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 5bae515c8e25..bed90d612e48 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -395,7 +395,8 @@ static struct notifier_block xen_memory_nb = { #else static enum bp_state reserve_additional_memory(void) { - balloon_stats.target_pages = balloon_stats.current_pages; + balloon_stats.target_pages = balloon_stats.current_pages + + balloon_stats.target_unpopulated; return BP_ECANCELED; } #endif /* CONFIG_XEN_BALLOON_MEMORY_HOTPLUG */ diff --git a/fs/affs/super.c b/fs/affs/super.c index cc463ae47c12..3812f7bc3a7f 100644 --- a/fs/affs/super.c +++ b/fs/affs/super.c @@ -561,14 +561,9 @@ affs_remount(struct super_block *sb, int *flags, char *data) int root_block; unsigned long mount_flags; int res = 0; - char *new_opts; char volume[32]; char *prefix = NULL; - new_opts = kstrdup(data, GFP_KERNEL); - if (data && !new_opts) - return -ENOMEM; - pr_debug("%s(flags=0x%x,opts=\"%s\")\n", __func__, *flags, data); sync_filesystem(sb); @@ -579,7 +574,6 @@ affs_remount(struct super_block *sb, int *flags, char *data) &blocksize, &prefix, volume, &mount_flags)) { kfree(prefix); - kfree(new_opts); return -EINVAL; } diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 497f979018c2..5c794f4b051a 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -908,6 +908,7 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct afs_vnode *dvnode = AFS_FS_I(dir); + struct afs_fid fid = {}; struct inode *inode; struct dentry *d; struct key *key; @@ -951,21 +952,18 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, afs_stat_v(dvnode, n_lookup); inode = afs_do_lookup(dir, dentry, key); key_put(key); - if (inode == ERR_PTR(-ENOENT)) { + if (inode == ERR_PTR(-ENOENT)) inode = afs_try_auto_mntpt(dentry, dir); - } else { - dentry->d_fsdata = - (void *)(unsigned long)dvnode->status.data_version; - } + + if (!IS_ERR_OR_NULL(inode)) + fid = AFS_FS_I(inode)->fid; + d = d_splice_alias(inode, dentry); if (!IS_ERR_OR_NULL(d)) { d->d_fsdata = dentry->d_fsdata; - trace_afs_lookup(dvnode, &d->d_name, - inode ? AFS_FS_I(inode) : NULL); + trace_afs_lookup(dvnode, &d->d_name, &fid); } else { - trace_afs_lookup(dvnode, &dentry->d_name, - IS_ERR_OR_NULL(inode) ? NULL - : AFS_FS_I(inode)); + trace_afs_lookup(dvnode, &dentry->d_name, &fid); } return d; } diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index 4150280509ff..7503899c0a1b 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -136,6 +136,9 @@ static struct dentry *afs_dynroot_lookup(struct inode *dir, struct dentry *dentr ASSERTCMP(d_inode(dentry), ==, NULL); + if (flags & LOOKUP_CREATE) + return ERR_PTR(-EOPNOTSUPP); + if (dentry->d_name.len >= AFSNAMEMAX) { _leave(" = -ENAMETOOLONG"); return ERR_PTR(-ENAMETOOLONG); diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c index f532d6d3bd28..79bc5f1338ed 100644 --- a/fs/afs/mntpt.c +++ b/fs/afs/mntpt.c @@ -126,7 +126,7 @@ static int afs_mntpt_set_params(struct fs_context *fc, struct dentry *mntpt) if (src_as->cell) ctx->cell = afs_get_cell(src_as->cell); - if (size > PAGE_SIZE - 1) + if (size < 2 || size > PAGE_SIZE - 1) return -EINVAL; page = read_mapping_page(d_inode(mntpt)->i_mapping, 0, NULL); @@ -140,7 +140,9 @@ static int afs_mntpt_set_params(struct fs_context *fc, struct dentry *mntpt) } buf = kmap(page); - ret = vfs_parse_fs_string(fc, "source", buf, size); + ret = -EINVAL; + if (buf[size - 1] == '.') + ret = vfs_parse_fs_string(fc, "source", buf, size - 1); kunmap(page); put_page(page); if (ret < 0) diff --git a/fs/afs/server.c b/fs/afs/server.c index 64d440aaabc0..ca8115ba1724 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -32,18 +32,11 @@ static void afs_dec_servers_outstanding(struct afs_net *net) struct afs_server *afs_find_server(struct afs_net *net, const struct sockaddr_rxrpc *srx) { - const struct sockaddr_in6 *a = &srx->transport.sin6, *b; const struct afs_addr_list *alist; struct afs_server *server = NULL; unsigned int i; - bool ipv6 = true; int seq = 0, diff; - if (srx->transport.sin6.sin6_addr.s6_addr32[0] == 0 || - srx->transport.sin6.sin6_addr.s6_addr32[1] == 0 || - srx->transport.sin6.sin6_addr.s6_addr32[2] == htonl(0xffff)) - ipv6 = false; - rcu_read_lock(); do { @@ -52,7 +45,8 @@ struct afs_server *afs_find_server(struct afs_net *net, server = NULL; read_seqbegin_or_lock(&net->fs_addr_lock, &seq); - if (ipv6) { + if (srx->transport.family == AF_INET6) { + const struct sockaddr_in6 *a = &srx->transport.sin6, *b; hlist_for_each_entry_rcu(server, &net->fs_addresses6, addr6_link) { alist = rcu_dereference(server->addresses); for (i = alist->nr_ipv4; i < alist->nr_addrs; i++) { @@ -68,15 +62,16 @@ struct afs_server *afs_find_server(struct afs_net *net, } } } else { + const struct sockaddr_in *a = &srx->transport.sin, *b; hlist_for_each_entry_rcu(server, &net->fs_addresses4, addr4_link) { alist = rcu_dereference(server->addresses); for (i = 0; i < alist->nr_ipv4; i++) { - b = &alist->addrs[i].transport.sin6; - diff = ((u16 __force)a->sin6_port - - (u16 __force)b->sin6_port); + b = &alist->addrs[i].transport.sin; + diff = ((u16 __force)a->sin_port - + (u16 __force)b->sin_port); if (diff == 0) - diff = ((u32 __force)a->sin6_addr.s6_addr32[3] - - (u32 __force)b->sin6_addr.s6_addr32[3]); + diff = ((u32 __force)a->sin_addr.s_addr - + (u32 __force)b->sin_addr.s_addr); if (diff == 0) goto found; } diff --git a/fs/afs/super.c b/fs/afs/super.c index 488641b1a418..7f8a9b3137bf 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -404,6 +404,7 @@ static int afs_test_super(struct super_block *sb, struct fs_context *fc) return (as->net_ns == fc->net_ns && as->volume && as->volume->vid == ctx->volume->vid && + as->cell == ctx->cell && !as->dyn_root); } @@ -448,7 +449,6 @@ static int afs_fill_super(struct super_block *sb, struct afs_fs_context *ctx) /* allocate the root inode and dentry */ if (as->dyn_root) { inode = afs_iget_pseudo_dir(sb, true); - sb->s_flags |= SB_RDONLY; } else { sprintf(sb->s_id, "%llu", as->volume->vid); afs_activate_volume(as->volume); diff --git a/fs/block_dev.c b/fs/block_dev.c index 9c073dbdc1b0..d612468ee66b 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1403,11 +1403,7 @@ static void flush_disk(struct block_device *bdev, bool kill_dirty) "resized disk %s\n", bdev->bd_disk ? bdev->bd_disk->disk_name : ""); } - - if (!bdev->bd_disk) - return; - if (disk_part_scan_enabled(bdev->bd_disk)) - bdev->bd_invalidated = 1; + bdev->bd_invalidated = 1; } /** @@ -1512,6 +1508,19 @@ EXPORT_SYMBOL(bd_set_size); static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part); +static void bdev_disk_changed(struct block_device *bdev, bool invalidate) +{ + if (disk_part_scan_enabled(bdev->bd_disk)) { + if (invalidate) + invalidate_partitions(bdev->bd_disk, bdev); + else + rescan_partitions(bdev->bd_disk, bdev); + } else { + check_disk_size_change(bdev->bd_disk, bdev, !invalidate); + bdev->bd_invalidated = 0; + } +} + /* * bd_mutex locking: * @@ -1594,12 +1603,9 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) * The latter is necessary to prevent ghost * partitions on a removed medium. */ - if (bdev->bd_invalidated) { - if (!ret) - rescan_partitions(disk, bdev); - else if (ret == -ENOMEDIUM) - invalidate_partitions(disk, bdev); - } + if (bdev->bd_invalidated && + (!ret || ret == -ENOMEDIUM)) + bdev_disk_changed(bdev, ret == -ENOMEDIUM); if (ret) goto out_clear; @@ -1632,12 +1638,9 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) if (bdev->bd_disk->fops->open) ret = bdev->bd_disk->fops->open(bdev, mode); /* the same as first opener case, read comment there */ - if (bdev->bd_invalidated) { - if (!ret) - rescan_partitions(bdev->bd_disk, bdev); - else if (ret == -ENOMEDIUM) - invalidate_partitions(bdev->bd_disk, bdev); - } + if (bdev->bd_invalidated && + (!ret || ret == -ENOMEDIUM)) + bdev_disk_changed(bdev, ret == -ENOMEDIUM); if (ret) goto out_unlock_bdev; } diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c index 2e9e13ffbd08..3f3110975f88 100644 --- a/fs/btrfs/async-thread.c +++ b/fs/btrfs/async-thread.c @@ -53,16 +53,6 @@ struct btrfs_workqueue { struct __btrfs_workqueue *high; }; -static void normal_work_helper(struct btrfs_work *work); - -#define BTRFS_WORK_HELPER(name) \ -noinline_for_stack void btrfs_##name(struct work_struct *arg) \ -{ \ - struct btrfs_work *work = container_of(arg, struct btrfs_work, \ - normal_work); \ - normal_work_helper(work); \ -} - struct btrfs_fs_info * btrfs_workqueue_owner(const struct __btrfs_workqueue *wq) { @@ -89,29 +79,6 @@ bool btrfs_workqueue_normal_congested(const struct btrfs_workqueue *wq) return atomic_read(&wq->normal->pending) > wq->normal->thresh * 2; } -BTRFS_WORK_HELPER(worker_helper); -BTRFS_WORK_HELPER(delalloc_helper); -BTRFS_WORK_HELPER(flush_delalloc_helper); -BTRFS_WORK_HELPER(cache_helper); -BTRFS_WORK_HELPER(submit_helper); -BTRFS_WORK_HELPER(fixup_helper); -BTRFS_WORK_HELPER(endio_helper); -BTRFS_WORK_HELPER(endio_meta_helper); -BTRFS_WORK_HELPER(endio_meta_write_helper); -BTRFS_WORK_HELPER(endio_raid56_helper); -BTRFS_WORK_HELPER(endio_repair_helper); -BTRFS_WORK_HELPER(rmw_helper); -BTRFS_WORK_HELPER(endio_write_helper); -BTRFS_WORK_HELPER(freespace_write_helper); -BTRFS_WORK_HELPER(delayed_meta_helper); -BTRFS_WORK_HELPER(readahead_helper); -BTRFS_WORK_HELPER(qgroup_rescan_helper); -BTRFS_WORK_HELPER(extent_refs_helper); -BTRFS_WORK_HELPER(scrub_helper); -BTRFS_WORK_HELPER(scrubwrc_helper); -BTRFS_WORK_HELPER(scrubnc_helper); -BTRFS_WORK_HELPER(scrubparity_helper); - static struct __btrfs_workqueue * __btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info, const char *name, unsigned int flags, int limit_active, int thresh) @@ -252,16 +219,17 @@ static inline void thresh_exec_hook(struct __btrfs_workqueue *wq) } } -static void run_ordered_work(struct __btrfs_workqueue *wq) +static void run_ordered_work(struct __btrfs_workqueue *wq, + struct btrfs_work *self) { struct list_head *list = &wq->ordered_list; struct btrfs_work *work; spinlock_t *lock = &wq->list_lock; unsigned long flags; + void *wtag; + bool free_self = false; while (1) { - void *wtag; - spin_lock_irqsave(lock, flags); if (list_empty(list)) break; @@ -287,20 +255,54 @@ static void run_ordered_work(struct __btrfs_workqueue *wq) list_del(&work->ordered_list); spin_unlock_irqrestore(lock, flags); - /* - * We don't want to call the ordered free functions with the - * lock held though. Save the work as tag for the trace event, - * because the callback could free the structure. - */ - wtag = work; - work->ordered_free(work); - trace_btrfs_all_work_done(wq->fs_info, wtag); + if (work == self) { + /* + * This is the work item that the worker is currently + * executing. + * + * The kernel workqueue code guarantees non-reentrancy + * of work items. I.e., if a work item with the same + * address and work function is queued twice, the second + * execution is blocked until the first one finishes. A + * work item may be freed and recycled with the same + * work function; the workqueue code assumes that the + * original work item cannot depend on the recycled work + * item in that case (see find_worker_executing_work()). + * + * Note that different types of Btrfs work can depend on + * each other, and one type of work on one Btrfs + * filesystem may even depend on the same type of work + * on another Btrfs filesystem via, e.g., a loop device. + * Therefore, we must not allow the current work item to + * be recycled until we are really done, otherwise we + * break the above assumption and can deadlock. + */ + free_self = true; + } else { + /* + * We don't want to call the ordered free functions with + * the lock held though. Save the work as tag for the + * trace event, because the callback could free the + * structure. + */ + wtag = work; + work->ordered_free(work); + trace_btrfs_all_work_done(wq->fs_info, wtag); + } } spin_unlock_irqrestore(lock, flags); + + if (free_self) { + wtag = self; + self->ordered_free(self); + trace_btrfs_all_work_done(wq->fs_info, wtag); + } } -static void normal_work_helper(struct btrfs_work *work) +static void btrfs_work_helper(struct work_struct *normal_work) { + struct btrfs_work *work = container_of(normal_work, struct btrfs_work, + normal_work); struct __btrfs_workqueue *wq; void *wtag; int need_order = 0; @@ -324,21 +326,19 @@ static void normal_work_helper(struct btrfs_work *work) work->func(work); if (need_order) { set_bit(WORK_DONE_BIT, &work->flags); - run_ordered_work(wq); + run_ordered_work(wq, work); } if (!need_order) trace_btrfs_all_work_done(wq->fs_info, wtag); } -void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t uniq_func, - btrfs_func_t func, - btrfs_func_t ordered_func, - btrfs_func_t ordered_free) +void btrfs_init_work(struct btrfs_work *work, btrfs_func_t func, + btrfs_func_t ordered_func, btrfs_func_t ordered_free) { work->func = func; work->ordered_func = ordered_func; work->ordered_free = ordered_free; - INIT_WORK(&work->normal_work, uniq_func); + INIT_WORK(&work->normal_work, btrfs_work_helper); INIT_LIST_HEAD(&work->ordered_list); work->flags = 0; } diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h index 7861c9feba5f..c5bf2b117c05 100644 --- a/fs/btrfs/async-thread.h +++ b/fs/btrfs/async-thread.h @@ -29,42 +29,13 @@ struct btrfs_work { unsigned long flags; }; -#define BTRFS_WORK_HELPER_PROTO(name) \ -void btrfs_##name(struct work_struct *arg) - -BTRFS_WORK_HELPER_PROTO(worker_helper); -BTRFS_WORK_HELPER_PROTO(delalloc_helper); -BTRFS_WORK_HELPER_PROTO(flush_delalloc_helper); -BTRFS_WORK_HELPER_PROTO(cache_helper); -BTRFS_WORK_HELPER_PROTO(submit_helper); -BTRFS_WORK_HELPER_PROTO(fixup_helper); -BTRFS_WORK_HELPER_PROTO(endio_helper); -BTRFS_WORK_HELPER_PROTO(endio_meta_helper); -BTRFS_WORK_HELPER_PROTO(endio_meta_write_helper); -BTRFS_WORK_HELPER_PROTO(endio_raid56_helper); -BTRFS_WORK_HELPER_PROTO(endio_repair_helper); -BTRFS_WORK_HELPER_PROTO(rmw_helper); -BTRFS_WORK_HELPER_PROTO(endio_write_helper); -BTRFS_WORK_HELPER_PROTO(freespace_write_helper); -BTRFS_WORK_HELPER_PROTO(delayed_meta_helper); -BTRFS_WORK_HELPER_PROTO(readahead_helper); -BTRFS_WORK_HELPER_PROTO(qgroup_rescan_helper); -BTRFS_WORK_HELPER_PROTO(extent_refs_helper); -BTRFS_WORK_HELPER_PROTO(scrub_helper); -BTRFS_WORK_HELPER_PROTO(scrubwrc_helper); -BTRFS_WORK_HELPER_PROTO(scrubnc_helper); -BTRFS_WORK_HELPER_PROTO(scrubparity_helper); - - struct btrfs_workqueue *btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info, const char *name, unsigned int flags, int limit_active, int thresh); -void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t helper, - btrfs_func_t func, - btrfs_func_t ordered_func, - btrfs_func_t ordered_free); +void btrfs_init_work(struct btrfs_work *work, btrfs_func_t func, + btrfs_func_t ordered_func, btrfs_func_t ordered_free); void btrfs_queue_work(struct btrfs_workqueue *wq, struct btrfs_work *work); void btrfs_destroy_workqueue(struct btrfs_workqueue *wq); diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 670700cb1110..7dcfa7d7632a 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -695,8 +695,7 @@ int btrfs_cache_block_group(struct btrfs_block_group_cache *cache, caching_ctl->block_group = cache; caching_ctl->progress = cache->key.objectid; refcount_set(&caching_ctl->count, 1); - btrfs_init_work(&caching_ctl->work, btrfs_cache_helper, - caching_thread, NULL, NULL); + btrfs_init_work(&caching_ctl->work, caching_thread, NULL, NULL); spin_lock(&cache->lock); /* @@ -2662,7 +2661,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans, * is because we need the unpinning stage to actually add the * space back to the block group, otherwise we will leak space. */ - if (!alloc && cache->cached == BTRFS_CACHE_NO) + if (!alloc && !btrfs_block_group_cache_done(cache)) btrfs_cache_block_group(cache, 1); byte_in_group = bytenr - cache->key.objectid; diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index e59cde204b2f..da9b0f060a9d 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -383,7 +383,7 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info, for (node = rb_first(tm_root); node; node = next) { next = rb_next(node); tm = rb_entry(node, struct tree_mod_elem, node); - if (tm->seq > min_seq) + if (tm->seq >= min_seq) continue; rb_erase(node, tm_root); kfree(tm); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index fe2b8765d9e6..5e9f80b28fcf 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2785,7 +2785,7 @@ struct btrfs_inode_extref *btrfs_find_name_in_ext_backref( /* file-item.c */ struct btrfs_dio_private; int btrfs_del_csums(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, u64 bytenr, u64 len); + struct btrfs_root *root, u64 bytenr, u64 len); blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u8 *dst); blk_status_t btrfs_lookup_bio_sums_dio(struct inode *inode, struct bio *bio, diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 1f7f39b10bd0..c7a53e79c66d 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1367,8 +1367,8 @@ static int btrfs_wq_run_delayed_node(struct btrfs_delayed_root *delayed_root, return -ENOMEM; async_work->delayed_root = delayed_root; - btrfs_init_work(&async_work->work, btrfs_delayed_meta_helper, - btrfs_async_run_delayed_root, NULL, NULL); + btrfs_init_work(&async_work->work, btrfs_async_run_delayed_root, NULL, + NULL); async_work->nr = nr; btrfs_queue_work(fs_info->delayed_workers, &async_work->work); @@ -1949,12 +1949,19 @@ void btrfs_kill_all_delayed_nodes(struct btrfs_root *root) } inode_id = delayed_nodes[n - 1]->inode_id + 1; - - for (i = 0; i < n; i++) - refcount_inc(&delayed_nodes[i]->refs); + for (i = 0; i < n; i++) { + /* + * Don't increase refs in case the node is dead and + * about to be removed from the tree in the loop below + */ + if (!refcount_inc_not_zero(&delayed_nodes[i]->refs)) + delayed_nodes[i] = NULL; + } spin_unlock(&root->inode_lock); for (i = 0; i < n; i++) { + if (!delayed_nodes[i]) + continue; __btrfs_kill_delayed_node(delayed_nodes[i]); btrfs_release_delayed_node(delayed_nodes[i]); } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 402b61bf345c..bae334212ee2 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -706,43 +706,31 @@ static void end_workqueue_bio(struct bio *bio) struct btrfs_end_io_wq *end_io_wq = bio->bi_private; struct btrfs_fs_info *fs_info; struct btrfs_workqueue *wq; - btrfs_work_func_t func; fs_info = end_io_wq->info; end_io_wq->status = bio->bi_status; if (bio_op(bio) == REQ_OP_WRITE) { - if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA) { + if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA) wq = fs_info->endio_meta_write_workers; - func = btrfs_endio_meta_write_helper; - } else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE) { + else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE) wq = fs_info->endio_freespace_worker; - func = btrfs_freespace_write_helper; - } else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) { + else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) wq = fs_info->endio_raid56_workers; - func = btrfs_endio_raid56_helper; - } else { + else wq = fs_info->endio_write_workers; - func = btrfs_endio_write_helper; - } } else { - if (unlikely(end_io_wq->metadata == - BTRFS_WQ_ENDIO_DIO_REPAIR)) { + if (unlikely(end_io_wq->metadata == BTRFS_WQ_ENDIO_DIO_REPAIR)) wq = fs_info->endio_repair_workers; - func = btrfs_endio_repair_helper; - } else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) { + else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) wq = fs_info->endio_raid56_workers; - func = btrfs_endio_raid56_helper; - } else if (end_io_wq->metadata) { + else if (end_io_wq->metadata) wq = fs_info->endio_meta_workers; - func = btrfs_endio_meta_helper; - } else { + else wq = fs_info->endio_workers; - func = btrfs_endio_helper; - } } - btrfs_init_work(&end_io_wq->work, func, end_workqueue_fn, NULL, NULL); + btrfs_init_work(&end_io_wq->work, end_workqueue_fn, NULL, NULL); btrfs_queue_work(wq, &end_io_wq->work); } @@ -835,8 +823,8 @@ blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio, async->mirror_num = mirror_num; async->submit_bio_start = submit_bio_start; - btrfs_init_work(&async->work, btrfs_worker_helper, run_one_async_start, - run_one_async_done, run_one_async_free); + btrfs_init_work(&async->work, run_one_async_start, run_one_async_done, + run_one_async_free); async->bio_offset = bio_offset; @@ -1657,8 +1645,8 @@ static void end_workqueue_fn(struct btrfs_work *work) bio->bi_status = end_io_wq->status; bio->bi_private = end_io_wq->private; bio->bi_end_io = end_io_wq->end_io; - kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq); bio_endio(bio); + kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq); } static int cleaner_kthread(void *arg) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 49cb26fa7c63..dc50605ecbda 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1848,8 +1848,8 @@ static int cleanup_ref_head(struct btrfs_trans_handle *trans, btrfs_pin_extent(fs_info, head->bytenr, head->num_bytes, 1); if (head->is_data) { - ret = btrfs_del_csums(trans, fs_info, head->bytenr, - head->num_bytes); + ret = btrfs_del_csums(trans, fs_info->csum_root, + head->bytenr, head->num_bytes); } } @@ -3155,7 +3155,8 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, btrfs_release_path(path); if (is_data) { - ret = btrfs_del_csums(trans, info, bytenr, num_bytes); + ret = btrfs_del_csums(trans, info->csum_root, bytenr, + num_bytes); if (ret) { btrfs_abort_transaction(trans, ret); goto out; @@ -3780,6 +3781,7 @@ static noinline int find_free_extent(struct btrfs_fs_info *fs_info, u64 flags, int delalloc) { int ret = 0; + int cache_block_group_error = 0; struct btrfs_free_cluster *last_ptr = NULL; struct btrfs_block_group_cache *block_group = NULL; struct find_free_extent_ctl ffe_ctl = {0}; @@ -3939,7 +3941,20 @@ static noinline int find_free_extent(struct btrfs_fs_info *fs_info, if (unlikely(!ffe_ctl.cached)) { ffe_ctl.have_caching_bg = true; ret = btrfs_cache_block_group(block_group, 0); - BUG_ON(ret < 0); + + /* + * If we get ENOMEM here or something else we want to + * try other block groups, because it may not be fatal. + * However if we can't find anything else we need to + * save our return here so that we return the actual + * error that caused problems, not ENOSPC. + */ + if (ret < 0) { + if (!cache_block_group_error) + cache_block_group_error = ret; + ret = 0; + goto loop; + } ret = 0; } @@ -4026,7 +4041,7 @@ static noinline int find_free_extent(struct btrfs_fs_info *fs_info, if (ret > 0) goto search; - if (ret == -ENOSPC) { + if (ret == -ENOSPC && !cache_block_group_error) { /* * Use ffe_ctl->total_free_space as fallback if we can't find * any contiguous hole. @@ -4037,6 +4052,8 @@ static noinline int find_free_extent(struct btrfs_fs_info *fs_info, space_info->max_extent_size = ffe_ctl.max_extent_size; spin_unlock(&space_info->lock); ins->offset = ffe_ctl.max_extent_size; + } else if (ret == -ENOSPC) { + ret = cache_block_group_error; } return ret; } diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index cceaf05aada2..33c6b191ca59 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1899,7 +1899,7 @@ static int __process_pages_contig(struct address_space *mapping, if (page_ops & PAGE_SET_PRIVATE2) SetPagePrivate2(pages[i]); - if (pages[i] == locked_page) { + if (locked_page && pages[i] == locked_page) { put_page(pages[i]); pages_locked++; continue; @@ -4121,7 +4121,7 @@ static int extent_write_cache_pages(struct address_space *mapping, for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; - done_index = page->index; + done_index = page->index + 1; /* * At this point we hold neither the i_pages lock nor * the page lock: the page may be truncated or @@ -4156,16 +4156,6 @@ static int extent_write_cache_pages(struct address_space *mapping, ret = __extent_writepage(page, wbc, epd); if (ret < 0) { - /* - * done_index is set past this page, - * so media errors will not choke - * background writeout for the entire - * file. This has consequences for - * range_cyclic semantics (ie. it may - * not be suitable for data integrity - * writeout). - */ - done_index = page->index + 1; done = 1; break; } @@ -5076,12 +5066,14 @@ struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info, return eb; eb = alloc_dummy_extent_buffer(fs_info, start); if (!eb) - return NULL; + return ERR_PTR(-ENOMEM); eb->fs_info = fs_info; 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, start >> PAGE_SHIFT, eb); diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 1a599f50837b..c878bc25d046 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -590,9 +590,9 @@ static noinline void truncate_one_csum(struct btrfs_fs_info *fs_info, * range of bytes. */ int btrfs_del_csums(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, u64 bytenr, u64 len) + struct btrfs_root *root, u64 bytenr, u64 len) { - struct btrfs_root *root = fs_info->csum_root; + struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_path *path; struct btrfs_key key; u64 end_byte = bytenr + len; @@ -602,6 +602,9 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans, u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); int blocksize_bits = fs_info->sb->s_blocksize_bits; + ASSERT(root == fs_info->csum_root || + root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID); + path = btrfs_alloc_path(); if (!path) return -ENOMEM; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 435a502a3226..5739b8fc7fff 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1636,6 +1636,7 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, break; } + only_release_metadata = false; sector_offset = pos & (fs_info->sectorsize - 1); reserve_bytes = round_up(write_bytes + sector_offset, fs_info->sectorsize); @@ -1791,7 +1792,6 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend, EXTENT_NORESERVE, NULL, NULL, GFP_NOFS); - only_release_metadata = false; } btrfs_drop_pages(pages, num_pages); @@ -1903,9 +1903,10 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, (iocb->ki_flags & IOCB_NOWAIT)) return -EOPNOTSUPP; - if (!inode_trylock(inode)) { - if (iocb->ki_flags & IOCB_NOWAIT) + if (iocb->ki_flags & IOCB_NOWAIT) { + if (!inode_trylock(inode)) return -EAGAIN; + } else { inode_lock(inode); } @@ -2601,8 +2602,8 @@ int btrfs_punch_hole_range(struct inode *inode, struct btrfs_path *path, } } - if (clone_info) { - u64 clone_len = drop_end - cur_offset; + if (clone_info && drop_end > clone_info->file_offset) { + u64 clone_len = drop_end - clone_info->file_offset; ret = btrfs_insert_clone_extent(trans, inode, path, clone_info, clone_len); diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index d54dcd0ab230..d86ada9c3c54 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -385,6 +385,12 @@ static int io_ctl_prepare_pages(struct btrfs_io_ctl *io_ctl, struct inode *inode if (uptodate && !PageUptodate(page)) { btrfs_readpage(NULL, page); lock_page(page); + if (page->mapping != inode->i_mapping) { + btrfs_err(BTRFS_I(inode)->root->fs_info, + "free space cache page truncated"); + io_ctl_drop_pages(io_ctl); + return -EIO; + } if (!PageUptodate(page)) { btrfs_err(BTRFS_I(inode)->root->fs_info, "error reading free space cache"); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 015910079e73..0b2758961b1c 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -712,10 +712,12 @@ static noinline int compress_file_range(struct async_chunk *async_chunk) * to our extent and set things up for the async work queue to run * cow_file_range to do the normal delalloc dance. */ - if (page_offset(async_chunk->locked_page) >= start && - page_offset(async_chunk->locked_page) <= end) + if (async_chunk->locked_page && + (page_offset(async_chunk->locked_page) >= start && + page_offset(async_chunk->locked_page)) <= end) { __set_page_dirty_nobuffers(async_chunk->locked_page); /* unlocked later on in the async handlers */ + } if (redirty) extent_range_redirty_for_io(inode, start, end); @@ -795,7 +797,7 @@ static noinline void submit_compressed_extents(struct async_chunk *async_chunk) async_extent->start + async_extent->ram_size - 1, WB_SYNC_ALL); - else if (ret) + else if (ret && async_chunk->locked_page) unlock_page(async_chunk->locked_page); kfree(async_extent); cond_resched(); @@ -1264,14 +1266,27 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page, async_chunk[i].inode = inode; async_chunk[i].start = start; async_chunk[i].end = cur_end; - async_chunk[i].locked_page = locked_page; async_chunk[i].write_flags = write_flags; INIT_LIST_HEAD(&async_chunk[i].extents); - btrfs_init_work(&async_chunk[i].work, - btrfs_delalloc_helper, - async_cow_start, async_cow_submit, - async_cow_free); + /* + * The locked_page comes all the way from writepage and its + * the original page we were actually given. As we spread + * this large delalloc region across multiple async_chunk + * structs, only the first struct needs a pointer to locked_page + * + * This way we don't need racey decisions about who is supposed + * to unlock it. + */ + if (locked_page) { + async_chunk[i].locked_page = locked_page; + locked_page = NULL; + } else { + async_chunk[i].locked_page = NULL; + } + + btrfs_init_work(&async_chunk[i].work, async_cow_start, + async_cow_submit, async_cow_free); nr_pages = DIV_ROUND_UP(cur_end - start, PAGE_SIZE); atomic_add(nr_pages, &fs_info->async_delalloc_pages); @@ -1439,10 +1454,10 @@ static noinline int run_delalloc_nocow(struct inode *inode, disk_num_bytes = btrfs_file_extent_disk_num_bytes(leaf, fi); /* - * If extent we got ends before our range starts, skip - * to next extent + * If the extent we got ends before our current offset, + * skip to the next extent. */ - if (extent_end <= start) { + if (extent_end <= cur_offset) { path->slots[0]++; goto next_slot; } @@ -2214,12 +2229,16 @@ static void btrfs_writepage_fixup_worker(struct btrfs_work *work) mapping_set_error(page->mapping, ret); end_extent_writepage(page, ret, page_start, page_end); ClearPageChecked(page); - goto out; + goto out_reserved; } ClearPageChecked(page); set_page_dirty(page); +out_reserved: btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE); + if (ret) + btrfs_delalloc_release_space(inode, data_reserved, page_start, + PAGE_SIZE, true); out: unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start, page_end, &cached_state); @@ -2260,8 +2279,7 @@ int btrfs_writepage_cow_fixup(struct page *page, u64 start, u64 end) SetPageChecked(page); get_page(page); - btrfs_init_work(&fixup->work, btrfs_fixup_helper, - btrfs_writepage_fixup_worker, NULL, NULL); + btrfs_init_work(&fixup->work, btrfs_writepage_fixup_worker, NULL, NULL); fixup->page = page; btrfs_queue_work(fs_info->fixup_workers, &fixup->work); return -EBUSY; @@ -3254,7 +3272,6 @@ void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start, struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_ordered_extent *ordered_extent = NULL; struct btrfs_workqueue *wq; - btrfs_work_func_t func; trace_btrfs_writepage_end_io_hook(page, start, end, uptodate); @@ -3263,16 +3280,12 @@ void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start, end - start + 1, uptodate)) return; - if (btrfs_is_free_space_inode(BTRFS_I(inode))) { + if (btrfs_is_free_space_inode(BTRFS_I(inode))) wq = fs_info->endio_freespace_worker; - func = btrfs_freespace_write_helper; - } else { + else wq = fs_info->endio_write_workers; - func = btrfs_endio_write_helper; - } - btrfs_init_work(&ordered_extent->work, func, finish_ordered_fn, NULL, - NULL); + btrfs_init_work(&ordered_extent->work, finish_ordered_fn, NULL, NULL); btrfs_queue_work(wq, &ordered_extent->work); } @@ -5693,7 +5706,6 @@ static void inode_tree_add(struct inode *inode) static void inode_tree_del(struct inode *inode) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_root *root = BTRFS_I(inode)->root; int empty = 0; @@ -5706,7 +5718,6 @@ static void inode_tree_del(struct inode *inode) spin_unlock(&root->inode_lock); if (empty && btrfs_root_refs(&root->root_item) == 0) { - synchronize_srcu(&fs_info->subvol_srcu); spin_lock(&root->inode_lock); empty = RB_EMPTY_ROOT(&root->inode_tree); spin_unlock(&root->inode_lock); @@ -8211,18 +8222,14 @@ static void __endio_write_update_ordered(struct inode *inode, struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_ordered_extent *ordered = NULL; struct btrfs_workqueue *wq; - btrfs_work_func_t func; u64 ordered_offset = offset; u64 ordered_bytes = bytes; u64 last_offset; - if (btrfs_is_free_space_inode(BTRFS_I(inode))) { + if (btrfs_is_free_space_inode(BTRFS_I(inode))) wq = fs_info->endio_freespace_worker; - func = btrfs_freespace_write_helper; - } else { + else wq = fs_info->endio_write_workers; - func = btrfs_endio_write_helper; - } while (ordered_offset < offset + bytes) { last_offset = ordered_offset; @@ -8230,9 +8237,8 @@ static void __endio_write_update_ordered(struct inode *inode, &ordered_offset, ordered_bytes, uptodate)) { - btrfs_init_work(&ordered->work, func, - finish_ordered_fn, - NULL, NULL); + btrfs_init_work(&ordered->work, finish_ordered_fn, NULL, + NULL); btrfs_queue_work(wq, &ordered->work); } /* @@ -9531,9 +9537,8 @@ static int btrfs_rename_exchange(struct inode *old_dir, btrfs_init_log_ctx(&ctx_dest, new_inode); /* close the race window with snapshot create/destroy ioctl */ - if (old_ino == BTRFS_FIRST_FREE_OBJECTID) - down_read(&fs_info->subvol_sem); - if (new_ino == BTRFS_FIRST_FREE_OBJECTID) + if (old_ino == BTRFS_FIRST_FREE_OBJECTID || + new_ino == BTRFS_FIRST_FREE_OBJECTID) down_read(&fs_info->subvol_sem); /* @@ -9550,6 +9555,9 @@ static int btrfs_rename_exchange(struct inode *old_dir, goto out_notrans; } + if (dest != root) + btrfs_record_root_in_trans(trans, dest); + /* * We need to find a free sequence number both in the source and * in the destination directory for the exchange. @@ -9764,9 +9772,8 @@ static int btrfs_rename_exchange(struct inode *old_dir, ret = ret ? ret : ret2; } out_notrans: - if (new_ino == BTRFS_FIRST_FREE_OBJECTID) - up_read(&fs_info->subvol_sem); - if (old_ino == BTRFS_FIRST_FREE_OBJECTID) + if (new_ino == BTRFS_FIRST_FREE_OBJECTID || + old_ino == BTRFS_FIRST_FREE_OBJECTID) up_read(&fs_info->subvol_sem); ASSERT(list_empty(&ctx_root.list)); @@ -10116,8 +10123,7 @@ static struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode init_completion(&work->completion); INIT_LIST_HEAD(&work->list); work->inode = inode; - btrfs_init_work(&work->work, btrfs_flush_delalloc_helper, - btrfs_run_delalloc_work, NULL, NULL); + btrfs_init_work(&work->work, btrfs_run_delalloc_work, NULL, NULL); return work; } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 23272d9154f3..5720e450a46f 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -705,11 +705,17 @@ static noinline int create_subvol(struct inode *dir, btrfs_i_size_write(BTRFS_I(dir), dir->i_size + namelen * 2); ret = btrfs_update_inode(trans, root, dir); - BUG_ON(ret); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto fail; + } ret = btrfs_add_root_ref(trans, objectid, root->root_key.objectid, btrfs_ino(BTRFS_I(dir)), index, name, namelen); - BUG_ON(ret); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto fail; + } ret = btrfs_uuid_tree_add(trans, root_item->uuid, BTRFS_UUID_KEY_SUBVOL, objectid); @@ -3721,24 +3727,18 @@ static int btrfs_clone(struct inode *src, struct inode *inode, ret = 0; if (last_dest_end < destoff + len) { - struct btrfs_clone_extent_info clone_info = { 0 }; /* - * We have an implicit hole (NO_HOLES feature is enabled) that - * fully or partially overlaps our cloning range at its end. + * We have an implicit hole that fully or partially overlaps our + * cloning range at its end. This means that we either have the + * NO_HOLES feature enabled or the implicit hole happened due to + * mixing buffered and direct IO writes against this file. */ btrfs_release_path(path); path->leave_spinning = 0; - /* - * We are dealing with a hole and our clone_info already has a - * disk_offset of 0, we only need to fill the data length and - * file offset. - */ - clone_info.data_len = destoff + len - last_dest_end; - clone_info.file_offset = last_dest_end; ret = btrfs_punch_hole_range(inode, path, last_dest_end, destoff + len - 1, - &clone_info, &trans); + NULL, &trans); if (ret) goto out; diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 24b6c72b9a59..6240a5a1f2c0 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -547,7 +547,6 @@ u64 btrfs_wait_ordered_extents(struct btrfs_root *root, u64 nr, spin_unlock(&root->ordered_extent_lock); btrfs_init_work(&ordered->flush_work, - btrfs_flush_delalloc_helper, btrfs_run_ordered_extent_work, NULL, NULL); list_add_tail(&ordered->work_list, &works); btrfs_queue_work(fs_info->flush_workers, &ordered->flush_work); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 3ad151655eb8..aeb5f2f3cdd7 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -3232,12 +3232,12 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid, if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN)) { btrfs_warn(fs_info, - "qgroup rescan init failed, qgroup is not enabled"); + "qgroup rescan init failed, qgroup rescan is not queued"); ret = -EINVAL; } else if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON)) { btrfs_warn(fs_info, - "qgroup rescan init failed, qgroup rescan is not queued"); + "qgroup rescan init failed, qgroup is not enabled"); ret = -EINVAL; } @@ -3280,7 +3280,6 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid, memset(&fs_info->qgroup_rescan_work, 0, sizeof(fs_info->qgroup_rescan_work)); btrfs_init_work(&fs_info->qgroup_rescan_work, - btrfs_qgroup_rescan_helper, btrfs_qgroup_rescan_worker, NULL, NULL); return 0; } diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 57a2ac721985..8f47a85944eb 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -190,7 +190,7 @@ static void scrub_parity_work(struct btrfs_work *work); static void start_async_work(struct btrfs_raid_bio *rbio, btrfs_func_t work_func) { - btrfs_init_work(&rbio->work, btrfs_rmw_helper, work_func, NULL, NULL); + btrfs_init_work(&rbio->work, work_func, NULL, NULL); btrfs_queue_work(rbio->fs_info->rmw_workers, &rbio->work); } @@ -1743,8 +1743,7 @@ static void btrfs_raid_unplug(struct blk_plug_cb *cb, bool from_schedule) plug = container_of(cb, struct btrfs_plug_cb, cb); if (from_schedule) { - btrfs_init_work(&plug->work, btrfs_rmw_helper, - unplug_work, NULL, NULL); + btrfs_init_work(&plug->work, unplug_work, NULL, NULL); btrfs_queue_work(plug->info->rmw_workers, &plug->work); return; diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c index ee6f60547a8d..1feaeadc8cf5 100644 --- a/fs/btrfs/reada.c +++ b/fs/btrfs/reada.c @@ -752,21 +752,19 @@ static int reada_start_machine_dev(struct btrfs_device *dev) static void reada_start_machine_worker(struct btrfs_work *work) { struct reada_machine_work *rmw; - struct btrfs_fs_info *fs_info; int old_ioprio; rmw = container_of(work, struct reada_machine_work, work); - fs_info = rmw->fs_info; - - kfree(rmw); old_ioprio = IOPRIO_PRIO_VALUE(task_nice_ioclass(current), task_nice_ioprio(current)); set_task_ioprio(current, BTRFS_IOPRIO_READA); - __reada_start_machine(fs_info); + __reada_start_machine(rmw->fs_info); set_task_ioprio(current, old_ioprio); - atomic_dec(&fs_info->reada_works_cnt); + atomic_dec(&rmw->fs_info->reada_works_cnt); + + kfree(rmw); } static void __reada_start_machine(struct btrfs_fs_info *fs_info) @@ -821,8 +819,7 @@ static void reada_start_machine(struct btrfs_fs_info *fs_info) /* FIXME we cannot handle this properly right now */ BUG(); } - btrfs_init_work(&rmw->work, btrfs_readahead_helper, - reada_start_machine_worker, NULL, NULL); + btrfs_init_work(&rmw->work, reada_start_machine_worker, NULL, NULL); rmw->fs_info = fs_info; btrfs_queue_work(fs_info->readahead_workers, &rmw->work); diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 5cd42b66818c..fd0f4c1696c8 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -4555,6 +4555,7 @@ int btrfs_recover_relocation(struct btrfs_root *root) fs_root = read_fs_root(fs_info, reloc_root->root_key.offset); if (IS_ERR(fs_root)) { err = PTR_ERR(fs_root); + list_add_tail(&reloc_root->root_list, &reloc_roots); goto out_free; } diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index f7d4e03f4c5d..a7b043fd7a57 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -598,8 +598,8 @@ static noinline_for_stack struct scrub_ctx *scrub_setup_ctx( sbio->index = i; sbio->sctx = sctx; sbio->page_count = 0; - btrfs_init_work(&sbio->work, btrfs_scrub_helper, - scrub_bio_end_io_worker, NULL, NULL); + btrfs_init_work(&sbio->work, scrub_bio_end_io_worker, NULL, + NULL); if (i != SCRUB_BIOS_PER_SCTX - 1) sctx->bios[i]->next_free = i + 1; @@ -1720,8 +1720,7 @@ static void scrub_wr_bio_end_io(struct bio *bio) sbio->status = bio->bi_status; sbio->bio = bio; - btrfs_init_work(&sbio->work, btrfs_scrubwrc_helper, - scrub_wr_bio_end_io_worker, NULL, NULL); + btrfs_init_work(&sbio->work, scrub_wr_bio_end_io_worker, NULL, NULL); btrfs_queue_work(fs_info->scrub_wr_completion_workers, &sbio->work); } @@ -2149,14 +2148,13 @@ static void scrub_missing_raid56_worker(struct btrfs_work *work) scrub_write_block_to_dev_replace(sblock); } - scrub_block_put(sblock); - if (sctx->is_dev_replace && sctx->flush_all_writes) { mutex_lock(&sctx->wr_lock); scrub_wr_submit(sctx); mutex_unlock(&sctx->wr_lock); } + scrub_block_put(sblock); scrub_pending_bio_dec(sctx); } @@ -2204,8 +2202,7 @@ static void scrub_missing_raid56_pages(struct scrub_block *sblock) raid56_add_scrub_pages(rbio, spage->page, spage->logical); } - btrfs_init_work(&sblock->work, btrfs_scrub_helper, - scrub_missing_raid56_worker, NULL, NULL); + btrfs_init_work(&sblock->work, scrub_missing_raid56_worker, NULL, NULL); scrub_block_get(sblock); scrub_pending_bio_inc(sctx); raid56_submit_missing_rbio(rbio); @@ -2743,8 +2740,8 @@ static void scrub_parity_bio_endio(struct bio *bio) bio_put(bio); - btrfs_init_work(&sparity->work, btrfs_scrubparity_helper, - scrub_parity_bio_endio_worker, NULL, NULL); + btrfs_init_work(&sparity->work, scrub_parity_bio_endio_worker, NULL, + NULL); btrfs_queue_work(fs_info->scrub_parity_workers, &sparity->work); } diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 123ac54af071..3eb0fec2488a 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -24,6 +24,14 @@ #include "transaction.h" #include "compression.h" +/* + * Maximum number of references an extent can have in order for us to attempt to + * issue clone operations instead of write operations. This currently exists to + * avoid hitting limitations of the backreference walking code (taking a lot of + * time and using too much memory for extents with large number of references). + */ +#define SEND_MAX_EXTENT_REFS 64 + /* * A fs_path is a helper to dynamically build path names with unknown size. * It reallocates the internal buffer on demand. @@ -1302,6 +1310,7 @@ static int find_extent_clone(struct send_ctx *sctx, struct clone_root *cur_clone_root; struct btrfs_key found_key; struct btrfs_path *tmp_path; + struct btrfs_extent_item *ei; int compressed; u32 i; @@ -1349,7 +1358,6 @@ static int find_extent_clone(struct send_ctx *sctx, ret = extent_from_logical(fs_info, disk_byte, tmp_path, &found_key, &flags); up_read(&fs_info->commit_root_sem); - btrfs_release_path(tmp_path); if (ret < 0) goto out; @@ -1358,6 +1366,21 @@ static int find_extent_clone(struct send_ctx *sctx, goto out; } + ei = btrfs_item_ptr(tmp_path->nodes[0], tmp_path->slots[0], + struct btrfs_extent_item); + /* + * Backreference walking (iterate_extent_inodes() below) is currently + * too expensive when an extent has a large number of references, both + * in time spent and used memory. So for now just fallback to write + * operations instead of clone operations when an extent has more than + * a certain amount of references. + */ + if (btrfs_extent_refs(tmp_path->nodes[0], ei) > SEND_MAX_EXTENT_REFS) { + ret = -ENOENT; + goto out; + } + btrfs_release_path(tmp_path); + /* * Setup the clone roots. */ @@ -7052,12 +7075,6 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg) send_root->send_in_progress++; spin_unlock(&send_root->root_item_lock); - /* - * This is done when we lookup the root, it should already be complete - * by the time we get here. - */ - WARN_ON(send_root->orphan_cleanup_state != ORPHAN_CLEANUP_DONE); - /* * Userspace tools do the checks and warn the user if it's * not RO. diff --git a/fs/btrfs/tests/free-space-tree-tests.c b/fs/btrfs/tests/free-space-tree-tests.c index bc92df977630..6e774d055402 100644 --- a/fs/btrfs/tests/free-space-tree-tests.c +++ b/fs/btrfs/tests/free-space-tree-tests.c @@ -463,9 +463,9 @@ static int run_test(test_func_t test_func, int bitmaps, u32 sectorsize, root->fs_info->tree_root = root; root->node = alloc_test_extent_buffer(root->fs_info, nodesize); - if (!root->node) { + if (IS_ERR(root->node)) { test_std_err(TEST_ALLOC_EXTENT_BUFFER); - ret = -ENOMEM; + ret = PTR_ERR(root->node); goto out; } btrfs_set_header_level(root->node, 0); diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c index 09aaca1efd62..ac035a6fa003 100644 --- a/fs/btrfs/tests/qgroup-tests.c +++ b/fs/btrfs/tests/qgroup-tests.c @@ -484,9 +484,9 @@ int btrfs_test_qgroups(u32 sectorsize, u32 nodesize) * *cough*backref walking code*cough* */ root->node = alloc_test_extent_buffer(root->fs_info, nodesize); - if (!root->node) { + if (IS_ERR(root->node)) { test_err("couldn't allocate dummy buffer"); - ret = -ENOMEM; + ret = PTR_ERR(root->node); goto out; } btrfs_set_header_level(root->node, 0); diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 076d5b8014fb..0e44db066641 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -243,7 +243,7 @@ static int check_extent_data_item(struct extent_buffer *leaf, } static int check_csum_item(struct extent_buffer *leaf, struct btrfs_key *key, - int slot) + int slot, struct btrfs_key *prev_key) { struct btrfs_fs_info *fs_info = leaf->fs_info; u32 sectorsize = fs_info->sectorsize; @@ -267,6 +267,20 @@ static int check_csum_item(struct extent_buffer *leaf, struct btrfs_key *key, btrfs_item_size_nr(leaf, slot), csumsize); return -EUCLEAN; } + if (slot > 0 && prev_key->type == BTRFS_EXTENT_CSUM_KEY) { + u64 prev_csum_end; + u32 prev_item_size; + + prev_item_size = btrfs_item_size_nr(leaf, slot - 1); + prev_csum_end = (prev_item_size / csumsize) * sectorsize; + prev_csum_end += prev_key->offset; + if (prev_csum_end > key->offset) { + generic_err(leaf, slot - 1, +"csum end range (%llu) goes beyond the start range (%llu) of the next csum item", + prev_csum_end, key->offset); + return -EUCLEAN; + } + } return 0; } @@ -1239,7 +1253,7 @@ static int check_leaf_item(struct extent_buffer *leaf, ret = check_extent_data_item(leaf, key, slot, prev_key); break; case BTRFS_EXTENT_CSUM_KEY: - ret = check_csum_item(leaf, key, slot); + ret = check_csum_item(leaf, key, slot, prev_key); break; case BTRFS_DIR_ITEM_KEY: case BTRFS_DIR_INDEX_KEY: diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 8a6cc600bf18..ab27e6cd9b3e 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -808,7 +808,8 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, struct btrfs_ordered_sum, list); if (!ret) - ret = btrfs_del_csums(trans, fs_info, + ret = btrfs_del_csums(trans, + fs_info->csum_root, sums->bytenr, sums->len); if (!ret) @@ -3927,6 +3928,28 @@ static int log_inode_item(struct btrfs_trans_handle *trans, return 0; } +static int log_csums(struct btrfs_trans_handle *trans, + struct btrfs_root *log_root, + struct btrfs_ordered_sum *sums) +{ + int ret; + + /* + * Due to extent cloning, we might have logged a csum item that covers a + * subrange of a cloned extent, and later we can end up logging a csum + * item for a larger subrange of the same extent or the entire range. + * This would leave csum items in the log tree that cover the same range + * and break the searches for checksums in the log tree, resulting in + * some checksums missing in the fs/subvolume tree. So just delete (or + * trim and adjust) any existing csum items in the log for this range. + */ + ret = btrfs_del_csums(trans, log_root, sums->bytenr, sums->len); + if (ret) + return ret; + + return btrfs_csum_file_blocks(trans, log_root, sums); +} + static noinline int copy_items(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *dst_path, @@ -4072,7 +4095,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans, struct btrfs_ordered_sum, list); if (!ret) - ret = btrfs_csum_file_blocks(trans, log, sums); + ret = log_csums(trans, log, sums); list_del(&sums->list); kfree(sums); } @@ -4292,7 +4315,7 @@ static int log_extent_csums(struct btrfs_trans_handle *trans, struct btrfs_ordered_sum, list); if (!ret) - ret = btrfs_csum_file_blocks(trans, log_root, sums); + ret = log_csums(trans, log_root, sums); list_del(&sums->list); kfree(sums); } @@ -6314,9 +6337,28 @@ int btrfs_recover_log_trees(struct btrfs_root *log_root_tree) wc.replay_dest = btrfs_read_fs_root_no_name(fs_info, &tmp_key); if (IS_ERR(wc.replay_dest)) { ret = PTR_ERR(wc.replay_dest); + + /* + * We didn't find the subvol, likely because it was + * deleted. This is ok, simply skip this log and go to + * the next one. + * + * We need to exclude the root because we can't have + * other log replays overwriting this log as we'll read + * it back in a few more times. This will keep our + * block from being modified, and we'll just bail for + * each subsequent pass. + */ + if (ret == -ENOENT) + ret = btrfs_pin_extent_for_log_replay(fs_info, + log->node->start, + log->node->len); free_extent_buffer(log->node); free_extent_buffer(log->commit_root); kfree(log); + + if (!ret) + goto next; btrfs_handle_fs_error(fs_info, ret, "Couldn't read target root for tree log recovery."); goto error; @@ -6348,7 +6390,6 @@ int btrfs_recover_log_trees(struct btrfs_root *log_root_tree) &root->highest_objectid); } - key.offset = found_key.offset - 1; wc.replay_dest->log_root = NULL; free_extent_buffer(log->node); free_extent_buffer(log->commit_root); @@ -6356,9 +6397,10 @@ int btrfs_recover_log_trees(struct btrfs_root *log_root_tree) if (ret) goto error; - +next: if (found_key.offset == 0) break; + key.offset = found_key.offset - 1; } btrfs_release_path(path); diff --git a/fs/btrfs/uuid-tree.c b/fs/btrfs/uuid-tree.c index 91caab63bdf5..76b84f2397b1 100644 --- a/fs/btrfs/uuid-tree.c +++ b/fs/btrfs/uuid-tree.c @@ -324,6 +324,8 @@ int btrfs_uuid_tree_iterate(struct btrfs_fs_info *fs_info, } if (ret < 0 && ret != -ENOENT) goto out; + key.offset++; + goto again_search_slot; } item_size -= sizeof(subid_le); offset += sizeof(subid_le); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index e04409f85063..d8d7b1ee83ca 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -6676,8 +6676,7 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info, else generate_random_uuid(dev->uuid); - btrfs_init_work(&dev->work, btrfs_submit_helper, - pending_bios_fn, NULL, NULL); + btrfs_init_work(&dev->work, pending_bios_fn, NULL, NULL); return dev; } diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index a7da1f3e3627..5acf5c507ec2 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -330,7 +330,6 @@ struct btrfs_bio { u64 map_type; /* get from map_lookup->type */ bio_end_io_t *end_io; struct bio *orig_bio; - unsigned long flags; void *private; atomic_t error; int max_errors; diff --git a/fs/buffer.c b/fs/buffer.c index 86a38b979323..91ceca52d14f 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2991,11 +2991,9 @@ static void end_bio_bh_io_sync(struct bio *bio) * errors, this only handles the "we need to be able to * do IO at the final sector" case. */ -void guard_bio_eod(int op, struct bio *bio) +void guard_bio_eod(struct bio *bio) { sector_t maxsector; - struct bio_vec *bvec = bio_last_bvec_all(bio); - unsigned truncated_bytes; struct hd_struct *part; rcu_read_lock(); @@ -3021,28 +3019,7 @@ void guard_bio_eod(int op, struct bio *bio) if (likely((bio->bi_iter.bi_size >> 9) <= maxsector)) return; - /* Uhhuh. We've got a bio that straddles the device size! */ - truncated_bytes = bio->bi_iter.bi_size - (maxsector << 9); - - /* - * The bio contains more than one segment which spans EOD, just return - * and let IO layer turn it into an EIO - */ - if (truncated_bytes > bvec->bv_len) - return; - - /* Truncate the bio.. */ - bio->bi_iter.bi_size -= truncated_bytes; - bvec->bv_len -= truncated_bytes; - - /* ..and clear the end of the buffer for reads */ - if (op == REQ_OP_READ) { - struct bio_vec bv; - - mp_bvec_last_segment(bvec, &bv); - zero_user(bv.bv_page, bv.bv_offset + bv.bv_len, - truncated_bytes); - } + bio_truncate(bio, maxsector << 9); } static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, @@ -3078,15 +3055,15 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, bio->bi_end_io = end_bio_bh_io_sync; bio->bi_private = bh; - /* Take care of bh's that straddle the end of the device */ - guard_bio_eod(op, bio); - if (buffer_meta(bh)) op_flags |= REQ_META; if (buffer_prio(bh)) op_flags |= REQ_PRIO; bio_set_op_attrs(bio, op, op_flags); + /* Take care of bh's that straddle the end of the device */ + guard_bio_eod(bio); + if (wbc) { wbc_init_bio(wbc, bio); wbc_account_cgroup_owner(wbc, bh->b_page, bh->b_size); diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index d17a789fd856..2e4764fd1872 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1809,6 +1809,7 @@ const struct file_operations ceph_dir_fops = { .open = ceph_open, .release = ceph_release, .unlocked_ioctl = ceph_ioctl, + .compat_ioctl = compat_ptr_ioctl, .fsync = ceph_fsync, .lock = ceph_lock, .flock = ceph_flock, diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 8de633964dc3..11929d2bb594 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -2188,7 +2188,7 @@ const struct file_operations ceph_file_fops = { .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, .unlocked_ioctl = ceph_ioctl, - .compat_ioctl = ceph_ioctl, + .compat_ioctl = compat_ptr_ioctl, .fallocate = ceph_fallocate, .copy_file_range = ceph_copy_file_range, }; diff --git a/fs/char_dev.c b/fs/char_dev.c index 00dfe17871ac..c5e6eff5a381 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -352,7 +352,7 @@ static struct kobject *cdev_get(struct cdev *p) if (owner && !try_module_get(owner)) return NULL; - kobj = kobject_get(&p->kobj); + kobj = kobject_get_unless_zero(&p->kobj); if (!kobj) module_put(owner); return kobj; diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 0b4eee3bed66..efb2928ff6c8 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -256,6 +256,11 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v) if (!server->rdma) goto skip_rdma; + if (!server->smbd_conn) { + seq_printf(m, "\nSMBDirect transport not available"); + goto skip_rdma; + } + seq_printf(m, "\nSMBDirect (in hex) protocol version: %x " "transport status: %x", server->smbd_conn->protocol, diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 1a135d1b85bd..07d8ace61f77 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -119,6 +119,7 @@ extern mempool_t *cifs_mid_poolp; struct workqueue_struct *cifsiod_wq; struct workqueue_struct *decrypt_wq; +struct workqueue_struct *fileinfo_put_wq; struct workqueue_struct *cifsoplockd_wq; __u32 cifs_lock_secret; @@ -1554,11 +1555,18 @@ init_cifs(void) goto out_destroy_cifsiod_wq; } + fileinfo_put_wq = alloc_workqueue("cifsfileinfoput", + WQ_UNBOUND|WQ_FREEZABLE|WQ_MEM_RECLAIM, 0); + if (!fileinfo_put_wq) { + rc = -ENOMEM; + goto out_destroy_decrypt_wq; + } + cifsoplockd_wq = alloc_workqueue("cifsoplockd", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0); if (!cifsoplockd_wq) { rc = -ENOMEM; - goto out_destroy_decrypt_wq; + goto out_destroy_fileinfo_put_wq; } rc = cifs_fscache_register(); @@ -1624,6 +1632,8 @@ init_cifs(void) cifs_fscache_unregister(); out_destroy_cifsoplockd_wq: destroy_workqueue(cifsoplockd_wq); +out_destroy_fileinfo_put_wq: + destroy_workqueue(fileinfo_put_wq); out_destroy_decrypt_wq: destroy_workqueue(decrypt_wq); out_destroy_cifsiod_wq: @@ -1653,6 +1663,7 @@ exit_cifs(void) cifs_fscache_unregister(); destroy_workqueue(cifsoplockd_wq); destroy_workqueue(decrypt_wq); + destroy_workqueue(fileinfo_put_wq); destroy_workqueue(cifsiod_wq); cifs_proc_clean(); } diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index d78bfcc19156..f55e53486e74 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -1265,6 +1265,7 @@ struct cifsFileInfo { struct mutex fh_mutex; /* prevents reopen race after dead ses*/ struct cifs_search_info srch_inf; struct work_struct oplock_break; /* work for oplock breaks */ + struct work_struct put; /* work for the final part of _put */ }; struct cifs_io_parms { @@ -1370,7 +1371,8 @@ cifsFileInfo_get_locked(struct cifsFileInfo *cifs_file) } struct cifsFileInfo *cifsFileInfo_get(struct cifsFileInfo *cifs_file); -void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_hdlr); +void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_hdlr, + bool offload); void cifsFileInfo_put(struct cifsFileInfo *cifs_file); #define CIFS_CACHE_READ_FLG 1 @@ -1524,6 +1526,7 @@ struct mid_q_entry { struct TCP_Server_Info *server; /* server corresponding to this mid */ __u64 mid; /* multiplex id */ __u16 credits; /* number of credits consumed by this mid */ + __u16 credits_received; /* number of credits from the response */ __u32 pid; /* process id */ __u32 sequence_number; /* for CIFS signing */ unsigned long when_alloc; /* when mid was created */ @@ -1907,6 +1910,7 @@ void cifs_queue_oplock_break(struct cifsFileInfo *cfile); extern const struct slow_work_ops cifs_oplock_break_ops; extern struct workqueue_struct *cifsiod_wq; extern struct workqueue_struct *decrypt_wq; +extern struct workqueue_struct *fileinfo_put_wq; extern struct workqueue_struct *cifsoplockd_wq; extern __u32 cifs_lock_secret; diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index ccaa8bad336f..02451d085ddd 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -387,7 +387,7 @@ static inline int reconn_set_ipaddr(struct TCP_Server_Info *server) #ifdef CONFIG_CIFS_DFS_UPCALL struct super_cb_data { struct TCP_Server_Info *server; - struct cifs_sb_info *cifs_sb; + struct super_block *sb; }; /* These functions must be called with server->srv_mutex held */ @@ -398,25 +398,39 @@ static void super_cb(struct super_block *sb, void *arg) struct cifs_sb_info *cifs_sb; struct cifs_tcon *tcon; - if (d->cifs_sb) + if (d->sb) return; cifs_sb = CIFS_SB(sb); tcon = cifs_sb_master_tcon(cifs_sb); if (tcon->ses->server == d->server) - d->cifs_sb = cifs_sb; + d->sb = sb; } -static inline struct cifs_sb_info * -find_super_by_tcp(struct TCP_Server_Info *server) +static struct super_block *get_tcp_super(struct TCP_Server_Info *server) { struct super_cb_data d = { .server = server, - .cifs_sb = NULL, + .sb = NULL, }; iterate_supers_type(&cifs_fs_type, super_cb, &d); - return d.cifs_sb ? d.cifs_sb : ERR_PTR(-ENOENT); + + if (unlikely(!d.sb)) + return ERR_PTR(-ENOENT); + /* + * Grab an active reference in order to prevent automounts (DFS links) + * of expiring and then freeing up our cifs superblock pointer while + * we're doing failover. + */ + cifs_sb_active(d.sb); + return d.sb; +} + +static inline void put_tcp_super(struct super_block *sb) +{ + if (!IS_ERR_OR_NULL(sb)) + cifs_sb_deactive(sb); } static void reconn_inval_dfs_target(struct TCP_Server_Info *server, @@ -480,6 +494,7 @@ cifs_reconnect(struct TCP_Server_Info *server) struct mid_q_entry *mid_entry; struct list_head retry_list; #ifdef CONFIG_CIFS_DFS_UPCALL + struct super_block *sb = NULL; struct cifs_sb_info *cifs_sb = NULL; struct dfs_cache_tgt_list tgt_list = {0}; struct dfs_cache_tgt_iterator *tgt_it = NULL; @@ -489,13 +504,15 @@ cifs_reconnect(struct TCP_Server_Info *server) server->nr_targets = 1; #ifdef CONFIG_CIFS_DFS_UPCALL spin_unlock(&GlobalMid_Lock); - cifs_sb = find_super_by_tcp(server); - if (IS_ERR(cifs_sb)) { - rc = PTR_ERR(cifs_sb); + sb = get_tcp_super(server); + if (IS_ERR(sb)) { + rc = PTR_ERR(sb); cifs_dbg(FYI, "%s: will not do DFS failover: rc = %d\n", __func__, rc); - cifs_sb = NULL; + sb = NULL; } else { + cifs_sb = CIFS_SB(sb); + rc = reconn_setup_dfs_targets(cifs_sb, &tgt_list, &tgt_it); if (rc && (rc != -EOPNOTSUPP)) { cifs_server_dbg(VFS, "%s: no target servers for DFS failover\n", @@ -512,6 +529,10 @@ cifs_reconnect(struct TCP_Server_Info *server) /* the demux thread will exit normally next time through the loop */ spin_unlock(&GlobalMid_Lock); +#ifdef CONFIG_CIFS_DFS_UPCALL + dfs_cache_free_tgts(&tgt_list); + put_tcp_super(sb); +#endif return rc; } else server->tcpStatus = CifsNeedReconnect; @@ -638,7 +659,10 @@ cifs_reconnect(struct TCP_Server_Info *server) __func__, rc); } dfs_cache_free_tgts(&tgt_list); + } + + put_tcp_super(sb); #endif if (server->tcpStatus == CifsNeedNegotiate) mod_delayed_work(cifsiod_wq, &server->echo, 0); @@ -905,6 +929,20 @@ dequeue_mid(struct mid_q_entry *mid, bool malformed) spin_unlock(&GlobalMid_Lock); } +static unsigned int +smb2_get_credits_from_hdr(char *buffer, struct TCP_Server_Info *server) +{ + struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)buffer; + + /* + * SMB1 does not use credits. + */ + if (server->vals->header_preamble_size) + return 0; + + return le16_to_cpu(shdr->CreditRequest); +} + static void handle_mid(struct mid_q_entry *mid, struct TCP_Server_Info *server, char *buf, int malformed) @@ -912,6 +950,7 @@ handle_mid(struct mid_q_entry *mid, struct TCP_Server_Info *server, if (server->ops->check_trans2 && server->ops->check_trans2(mid, server, buf, malformed)) return; + mid->credits_received = smb2_get_credits_from_hdr(buf, server); mid->resp_buf = buf; mid->large_buf = server->large_buf; /* Was previous buf put in mpx struct for multi-rsp? */ @@ -1222,12 +1261,6 @@ cifs_demultiplex_thread(void *p) for (i = 0; i < num_mids; i++) { if (mids[i] != NULL) { mids[i]->resp_buf_size = server->pdu_size; - if ((mids[i]->mid_flags & MID_WAIT_CANCELLED) && - mids[i]->mid_state == MID_RESPONSE_RECEIVED && - server->ops->handle_cancelled_mid) - server->ops->handle_cancelled_mid( - mids[i]->resp_buf, - server); if (!mids[i]->multiRsp || mids[i]->multiEnd) mids[i]->callback(mids[i]); @@ -4700,6 +4733,17 @@ static int is_path_remote(struct cifs_sb_info *cifs_sb, struct smb_vol *vol, } #ifdef CONFIG_CIFS_DFS_UPCALL +static inline void set_root_tcon(struct cifs_sb_info *cifs_sb, + struct cifs_tcon *tcon, + struct cifs_tcon **root) +{ + spin_lock(&cifs_tcp_ses_lock); + tcon->tc_count++; + tcon->remap = cifs_remap(cifs_sb); + spin_unlock(&cifs_tcp_ses_lock); + *root = tcon; +} + int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *vol) { int rc = 0; @@ -4801,18 +4845,10 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *vol) /* Cache out resolved root server */ (void)dfs_cache_find(xid, ses, cifs_sb->local_nls, cifs_remap(cifs_sb), root_path + 1, NULL, NULL); - /* - * Save root tcon for additional DFS requests to update or create a new - * DFS cache entry, or even perform DFS failover. - */ - spin_lock(&cifs_tcp_ses_lock); - tcon->tc_count++; - tcon->dfs_path = root_path; + kfree(root_path); root_path = NULL; - tcon->remap = cifs_remap(cifs_sb); - spin_unlock(&cifs_tcp_ses_lock); - root_tcon = tcon; + set_root_tcon(cifs_sb, tcon, &root_tcon); for (count = 1; ;) { if (!rc && tcon) { @@ -4849,6 +4885,15 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *vol) mount_put_conns(cifs_sb, xid, server, ses, tcon); rc = mount_get_conns(vol, cifs_sb, &xid, &server, &ses, &tcon); + /* + * Ensure that DFS referrals go through new root server. + */ + if (!rc && tcon && + (tcon->share_flags & (SHI1005_FLAGS_DFS | + SHI1005_FLAGS_DFS_ROOT))) { + cifs_put_tcon(root_tcon); + set_root_tcon(cifs_sb, tcon, &root_tcon); + } } if (rc) { if (rc == -EACCES || rc == -EOPNOTSUPP) diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c index 1692c0c6c23a..2faa05860a48 100644 --- a/fs/cifs/dfs_cache.c +++ b/fs/cifs/dfs_cache.c @@ -1317,7 +1317,6 @@ static struct cifs_ses *find_root_ses(struct dfs_cache_vol_info *vi, int rc; struct dfs_info3_param ref = {0}; char *mdata = NULL, *devname = NULL; - bool is_smb3 = tcon->ses->server->vals->header_preamble_size == 0; struct TCP_Server_Info *server; struct cifs_ses *ses; struct smb_vol vol; @@ -1344,7 +1343,7 @@ static struct cifs_ses *find_root_ses(struct dfs_cache_vol_info *vi, goto out; } - rc = cifs_setup_volume_info(&vol, mdata, devname, is_smb3); + rc = cifs_setup_volume_info(&vol, mdata, devname, false); kfree(devname); if (rc) { diff --git a/fs/cifs/file.c b/fs/cifs/file.c index fa7b0fa72bb3..969543034b4d 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -288,6 +288,8 @@ cifs_down_write(struct rw_semaphore *sem) msleep(10); } +static void cifsFileInfo_put_work(struct work_struct *work); + struct cifsFileInfo * cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, struct tcon_link *tlink, __u32 oplock) @@ -313,9 +315,6 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, INIT_LIST_HEAD(&fdlocks->locks); fdlocks->cfile = cfile; cfile->llist = fdlocks; - cifs_down_write(&cinode->lock_sem); - list_add(&fdlocks->llist, &cinode->llist); - up_write(&cinode->lock_sem); cfile->count = 1; cfile->pid = current->tgid; @@ -325,6 +324,7 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, cfile->invalidHandle = false; cfile->tlink = cifs_get_tlink(tlink); INIT_WORK(&cfile->oplock_break, cifs_oplock_break); + INIT_WORK(&cfile->put, cifsFileInfo_put_work); mutex_init(&cfile->fh_mutex); spin_lock_init(&cfile->file_info_lock); @@ -339,6 +339,10 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, oplock = 0; } + cifs_down_write(&cinode->lock_sem); + list_add(&fdlocks->llist, &cinode->llist); + up_write(&cinode->lock_sem); + spin_lock(&tcon->open_file_lock); if (fid->pending_open->oplock != CIFS_OPLOCK_NO_CHANGE && oplock) oplock = fid->pending_open->oplock; @@ -375,6 +379,41 @@ cifsFileInfo_get(struct cifsFileInfo *cifs_file) return cifs_file; } +static void cifsFileInfo_put_final(struct cifsFileInfo *cifs_file) +{ + struct inode *inode = d_inode(cifs_file->dentry); + struct cifsInodeInfo *cifsi = CIFS_I(inode); + struct cifsLockInfo *li, *tmp; + struct super_block *sb = inode->i_sb; + + /* + * Delete any outstanding lock records. We'll lose them when the file + * is closed anyway. + */ + cifs_down_write(&cifsi->lock_sem); + list_for_each_entry_safe(li, tmp, &cifs_file->llist->locks, llist) { + list_del(&li->llist); + cifs_del_lock_waiters(li); + kfree(li); + } + list_del(&cifs_file->llist->llist); + kfree(cifs_file->llist); + up_write(&cifsi->lock_sem); + + cifs_put_tlink(cifs_file->tlink); + dput(cifs_file->dentry); + cifs_sb_deactive(sb); + kfree(cifs_file); +} + +static void cifsFileInfo_put_work(struct work_struct *work) +{ + struct cifsFileInfo *cifs_file = container_of(work, + struct cifsFileInfo, put); + + cifsFileInfo_put_final(cifs_file); +} + /** * cifsFileInfo_put - release a reference of file priv data * @@ -382,15 +421,15 @@ cifsFileInfo_get(struct cifsFileInfo *cifs_file) */ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) { - _cifsFileInfo_put(cifs_file, true); + _cifsFileInfo_put(cifs_file, true, true); } /** * _cifsFileInfo_put - release a reference of file priv data * * This may involve closing the filehandle @cifs_file out on the - * server. Must be called without holding tcon->open_file_lock and - * cifs_file->file_info_lock. + * server. Must be called without holding tcon->open_file_lock, + * cinode->open_file_lock and cifs_file->file_info_lock. * * If @wait_for_oplock_handler is true and we are releasing the last * reference, wait for any running oplock break handler of the file @@ -398,7 +437,8 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) * oplock break handler, you need to pass false. * */ -void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler) +void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, + bool wait_oplock_handler, bool offload) { struct inode *inode = d_inode(cifs_file->dentry); struct cifs_tcon *tcon = tlink_tcon(cifs_file->tlink); @@ -406,7 +446,6 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler) struct cifsInodeInfo *cifsi = CIFS_I(inode); struct super_block *sb = inode->i_sb; struct cifs_sb_info *cifs_sb = CIFS_SB(sb); - struct cifsLockInfo *li, *tmp; struct cifs_fid fid; struct cifs_pending_open open; bool oplock_break_cancelled; @@ -467,24 +506,10 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler) cifs_del_pending_open(&open); - /* - * Delete any outstanding lock records. We'll lose them when the file - * is closed anyway. - */ - cifs_down_write(&cifsi->lock_sem); - list_for_each_entry_safe(li, tmp, &cifs_file->llist->locks, llist) { - list_del(&li->llist); - cifs_del_lock_waiters(li); - kfree(li); - } - list_del(&cifs_file->llist->llist); - kfree(cifs_file->llist); - up_write(&cifsi->lock_sem); - - cifs_put_tlink(cifs_file->tlink); - dput(cifs_file->dentry); - cifs_sb_deactive(sb); - kfree(cifs_file); + if (offload) + queue_work(fileinfo_put_wq, &cifs_file->put); + else + cifsFileInfo_put_final(cifs_file); } int cifs_open(struct inode *inode, struct file *file) @@ -728,6 +753,13 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) if (backup_cred(cifs_sb)) create_options |= CREATE_OPEN_BACKUP_INTENT; + /* O_SYNC also has bit for O_DSYNC so following check picks up either */ + if (cfile->f_flags & O_SYNC) + create_options |= CREATE_WRITE_THROUGH; + + if (cfile->f_flags & O_DIRECT) + create_options |= CREATE_NO_BUFFER; + if (server->ops->get_lease_key) server->ops->get_lease_key(inode, &cfile->fid); @@ -808,7 +840,7 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) int cifs_close(struct inode *inode, struct file *file) { if (file->private_data != NULL) { - cifsFileInfo_put(file->private_data); + _cifsFileInfo_put(file->private_data, true, false); file->private_data = NULL; } @@ -4680,7 +4712,7 @@ void cifs_oplock_break(struct work_struct *work) cinode); cifs_dbg(FYI, "Oplock release rc = %d\n", rc); } - _cifsFileInfo_put(cfile, false /* do not wait for ourself */); + _cifsFileInfo_put(cfile, false /* do not wait for ourself */, false); cifs_done_oplock_break(cinode); } diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index df9377828e2f..ed59e4a8db59 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -163,7 +163,7 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr) spin_lock(&inode->i_lock); /* we do not want atime to be less than mtime, it broke some apps */ - if (timespec64_compare(&fattr->cf_atime, &fattr->cf_mtime)) + if (timespec64_compare(&fattr->cf_atime, &fattr->cf_mtime) < 0) inode->i_atime = fattr->cf_mtime; else inode->i_atime = fattr->cf_atime; diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index 8b0b512c5792..afe1f03aabe3 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -67,7 +67,7 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, goto out; - if (oparms->tcon->use_resilient) { + if (oparms->tcon->use_resilient) { /* default timeout is 0, servers pick default (120 seconds) */ nr_ioctl_req.Timeout = cpu_to_le32(oparms->tcon->handle_timeout); diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index e311f58dc1c8..766974fe637a 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -673,10 +673,10 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) 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(tmp1, &ses->tcon_list) { tcon = list_entry(tmp1, struct cifs_tcon, tcon_list); - cifs_stats_inc(&tcon->stats.cifs_stats.num_oplock_brks); spin_lock(&tcon->open_file_lock); list_for_each(tmp2, &tcon->openFileList) { cfile = list_entry(tmp2, struct cifsFileInfo, @@ -688,6 +688,8 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) continue; cifs_dbg(FYI, "file id match, oplock break\n"); + cifs_stats_inc( + &tcon->stats.cifs_stats.num_oplock_brks); cinode = CIFS_I(d_inode(cfile->dentry)); spin_lock(&cfile->file_info_lock); if (!CIFS_CACHE_WRITE(cinode) && @@ -720,9 +722,6 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) return true; } spin_unlock(&tcon->open_file_lock); - spin_unlock(&cifs_tcp_ses_lock); - cifs_dbg(FYI, "No matching file for oplock break\n"); - return true; } } spin_unlock(&cifs_tcp_ses_lock); @@ -744,36 +743,67 @@ smb2_cancelled_close_fid(struct work_struct *work) kfree(cancelled); } +/* Caller should already has an extra reference to @tcon */ +static int +__smb2_handle_cancelled_close(struct cifs_tcon *tcon, __u64 persistent_fid, + __u64 volatile_fid) +{ + struct close_cancelled_open *cancelled; + + cancelled = kzalloc(sizeof(*cancelled), GFP_KERNEL); + if (!cancelled) + return -ENOMEM; + + cancelled->fid.persistent_fid = persistent_fid; + cancelled->fid.volatile_fid = volatile_fid; + cancelled->tcon = tcon; + INIT_WORK(&cancelled->work, smb2_cancelled_close_fid); + WARN_ON(queue_work(cifsiod_wq, &cancelled->work) == false); + + return 0; +} + +int +smb2_handle_cancelled_close(struct cifs_tcon *tcon, __u64 persistent_fid, + __u64 volatile_fid) +{ + int rc; + + cifs_dbg(FYI, "%s: tc_count=%d\n", __func__, tcon->tc_count); + spin_lock(&cifs_tcp_ses_lock); + tcon->tc_count++; + spin_unlock(&cifs_tcp_ses_lock); + + rc = __smb2_handle_cancelled_close(tcon, persistent_fid, volatile_fid); + if (rc) + cifs_put_tcon(tcon); + + return rc; +} + int smb2_handle_cancelled_mid(char *buffer, struct TCP_Server_Info *server) { struct smb2_sync_hdr *sync_hdr = (struct smb2_sync_hdr *)buffer; struct smb2_create_rsp *rsp = (struct smb2_create_rsp *)buffer; struct cifs_tcon *tcon; - struct close_cancelled_open *cancelled; + int rc; if (sync_hdr->Command != SMB2_CREATE || sync_hdr->Status != STATUS_SUCCESS) return 0; - cancelled = kzalloc(sizeof(*cancelled), GFP_KERNEL); - if (!cancelled) - return -ENOMEM; - tcon = smb2_find_smb_tcon(server, sync_hdr->SessionId, sync_hdr->TreeId); - if (!tcon) { - kfree(cancelled); + if (!tcon) return -ENOENT; - } - cancelled->fid.persistent_fid = rsp->PersistentFileId; - cancelled->fid.volatile_fid = rsp->VolatileFileId; - cancelled->tcon = tcon; - INIT_WORK(&cancelled->work, smb2_cancelled_close_fid); - queue_work(cifsiod_wq, &cancelled->work); + rc = __smb2_handle_cancelled_close(tcon, rsp->PersistentFileId, + rsp->VolatileFileId); + if (rc) + cifs_put_tcon(tcon); - return 0; + return rc; } /** diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index cd55af9b7cc5..b5c1cba3e6a1 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -151,13 +151,7 @@ smb2_get_credits_field(struct TCP_Server_Info *server, const int optype) static unsigned int smb2_get_credits(struct mid_q_entry *mid) { - struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)mid->resp_buf; - - if (mid->mid_state == MID_RESPONSE_RECEIVED - || mid->mid_state == MID_RESPONSE_MALFORMED) - return le16_to_cpu(shdr->CreditRequest); - - return 0; + return mid->credits_received; } static int diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 05149862aea4..e1d8cec6ba2e 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -252,7 +252,7 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon) if (tcon == NULL) return 0; - if (smb2_command == SMB2_TREE_CONNECT || smb2_command == SMB2_IOCTL) + if (smb2_command == SMB2_TREE_CONNECT) return 0; if (tcon->tidStatus == CifsExiting) { @@ -426,16 +426,9 @@ fill_small_buf(__le16 smb2_command, struct cifs_tcon *tcon, void *buf, * SMB information in the SMB header. If the return code is zero, this * function must have filled in request_buf pointer. */ -static int -smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon, - void **request_buf, unsigned int *total_len) +static int __smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon, + void **request_buf, unsigned int *total_len) { - int rc; - - rc = smb2_reconnect(smb2_command, tcon); - if (rc) - return rc; - /* BB eventually switch this to SMB2 specific small buf size */ if (smb2_command == SMB2_SET_INFO) *request_buf = cifs_buf_get(); @@ -456,7 +449,31 @@ smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon, cifs_stats_inc(&tcon->num_smbs_sent); } - return rc; + return 0; +} + +static int smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon, + void **request_buf, unsigned int *total_len) +{ + int rc; + + rc = smb2_reconnect(smb2_command, tcon); + if (rc) + return rc; + + return __smb2_plain_req_init(smb2_command, tcon, request_buf, + total_len); +} + +static int smb2_ioctl_req_init(u32 opcode, struct cifs_tcon *tcon, + void **request_buf, unsigned int *total_len) +{ + /* Skip reconnect only for FSCTL_VALIDATE_NEGOTIATE_INFO IOCTLs */ + if (opcode == FSCTL_VALIDATE_NEGOTIATE_INFO) { + return __smb2_plain_req_init(SMB2_IOCTL, tcon, request_buf, + total_len); + } + return smb2_plain_req_init(SMB2_IOCTL, tcon, request_buf, total_len); } /* For explanation of negotiate contexts see MS-SMB2 section 2.2.3.1 */ @@ -2661,7 +2678,7 @@ SMB2_ioctl_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, int rc; char *in_data_buf; - rc = smb2_plain_req_init(SMB2_IOCTL, tcon, (void **) &req, &total_len); + rc = smb2_ioctl_req_init(opcode, tcon, (void **) &req, &total_len); if (rc) return rc; @@ -2972,7 +2989,21 @@ int SMB2_close(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid) { - return SMB2_close_flags(xid, tcon, persistent_fid, volatile_fid, 0); + int rc; + int tmp_rc; + + rc = SMB2_close_flags(xid, tcon, persistent_fid, volatile_fid, 0); + + /* retry close in a worker thread if this one is interrupted */ + if (rc == -EINTR) { + tmp_rc = smb2_handle_cancelled_close(tcon, persistent_fid, + volatile_fid); + if (tmp_rc) + cifs_dbg(VFS, "handle cancelled close fid 0x%llx returned error %d\n", + persistent_fid, tmp_rc); + } + + return rc; } int diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 71b2930b8e0b..2a12a2fa38a2 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -212,6 +212,9 @@ extern int SMB2_set_compression(const unsigned int xid, struct cifs_tcon *tcon, extern int SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon, const u64 persistent_fid, const u64 volatile_fid, const __u8 oplock_level); +extern int smb2_handle_cancelled_close(struct cifs_tcon *tcon, + __u64 persistent_fid, + __u64 volatile_fid); extern int smb2_handle_cancelled_mid(char *buffer, struct TCP_Server_Info *server); void smb2_cancelled_close_fid(struct work_struct *work); diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c index 3c91fa97c9a8..5b1b97e9e0c9 100644 --- a/fs/cifs/smbdirect.c +++ b/fs/cifs/smbdirect.c @@ -1069,7 +1069,7 @@ static int smbd_post_send_data( if (n_vec > SMBDIRECT_MAX_SGE) { cifs_dbg(VFS, "Can't fit data to SGL, n_vec=%d\n", n_vec); - return -ENOMEM; + return -EINVAL; } sg_init_table(sgl, n_vec); @@ -1476,6 +1476,7 @@ void smbd_destroy(struct TCP_Server_Info *server) info->transport_status = SMBD_DESTROYED; destroy_workqueue(info->workqueue); + log_rdma_event(INFO, "rdma session destroyed\n"); kfree(info); } @@ -1505,8 +1506,9 @@ int smbd_reconnect(struct TCP_Server_Info *server) log_rdma_event(INFO, "creating rdma session\n"); server->smbd_conn = smbd_get_connection( server, (struct sockaddr *) &server->dstaddr); - log_rdma_event(INFO, "created rdma session info=%p\n", - server->smbd_conn); + + if (server->smbd_conn) + cifs_dbg(VFS, "RDMA transport re-established\n"); return server->smbd_conn ? 0 : -ENOENT; } @@ -1970,7 +1972,7 @@ static int smbd_recv_buf(struct smbd_connection *info, char *buf, if (info->transport_status != SMBD_CONNECTED) { log_read(ERR, "disconnected\n"); - return 0; + return -ECONNABORTED; } goto again; @@ -2269,12 +2271,7 @@ static void smbd_mr_recovery_work(struct work_struct *work) int rc; list_for_each_entry(smbdirect_mr, &info->mr_list, list) { - if (smbdirect_mr->state == MR_INVALIDATED) - ib_dma_unmap_sg( - info->id->device, smbdirect_mr->sgl, - smbdirect_mr->sgl_count, - smbdirect_mr->dir); - else if (smbdirect_mr->state == MR_ERROR) { + if (smbdirect_mr->state == MR_ERROR) { /* recover this MR entry */ rc = ib_dereg_mr(smbdirect_mr->mr); @@ -2602,11 +2599,20 @@ int smbd_deregister_mr(struct smbd_mr *smbdirect_mr) */ smbdirect_mr->state = MR_INVALIDATED; - /* - * Schedule the work to do MR recovery for future I/Os - * MR recovery is slow and we don't want it to block the current I/O - */ - queue_work(info->workqueue, &info->mr_recovery_work); + if (smbdirect_mr->state == MR_INVALIDATED) { + ib_dma_unmap_sg( + info->id->device, smbdirect_mr->sgl, + smbdirect_mr->sgl_count, + smbdirect_mr->dir); + smbdirect_mr->state = MR_READY; + if (atomic_inc_return(&info->mr_ready_count) == 1) + wake_up_interruptible(&info->wait_mr); + } else + /* + * Schedule the work to do MR recovery for future I/Os MR + * recovery is slow and don't want it to block current I/O + */ + queue_work(info->workqueue, &info->mr_recovery_work); done: if (atomic_dec_and_test(&info->mr_used_count)) diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index ca3de62688d6..755434d5e4e7 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -93,8 +93,14 @@ static void _cifs_mid_q_entry_release(struct kref *refcount) __u16 smb_cmd = le16_to_cpu(midEntry->command); unsigned long now; unsigned long roundtrip_time; - struct TCP_Server_Info *server = midEntry->server; #endif + struct TCP_Server_Info *server = midEntry->server; + + if (midEntry->resp_buf && (midEntry->mid_flags & MID_WAIT_CANCELLED) && + midEntry->mid_state == MID_RESPONSE_RECEIVED && + server->ops->handle_cancelled_mid) + server->ops->handle_cancelled_mid(midEntry->resp_buf, server); + midEntry->mid_state = MID_FREE; atomic_dec(&midCount); if (midEntry->large_buf) @@ -319,8 +325,11 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, int val = 1; __be32 rfc1002_marker; - if (cifs_rdma_enabled(server) && server->smbd_conn) { - rc = smbd_send(server, num_rqst, rqst); + if (cifs_rdma_enabled(server)) { + /* return -EAGAIN when connecting or reconnecting */ + rc = -EAGAIN; + if (server->smbd_conn) + rc = smbd_send(server, num_rqst, rqst); goto smbd_done; } @@ -1119,8 +1128,8 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, midQ[i]->mid, le16_to_cpu(midQ[i]->command)); send_cancel(server, &rqst[i], midQ[i]); spin_lock(&GlobalMid_Lock); + midQ[i]->mid_flags |= MID_WAIT_CANCELLED; if (midQ[i]->mid_state == MID_REQUEST_SUBMITTED) { - midQ[i]->mid_flags |= MID_WAIT_CANCELLED; midQ[i]->callback = cifs_cancelled_callback; cancelled_mid[i] = true; credits[i].value = 0; diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index a7ec2d3dff92..e0226b2138d6 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -1032,10 +1032,11 @@ COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, #endif case FICLONE: + goto do_ioctl; case FICLONERANGE: case FIDEDUPERANGE: case FS_IOC_FIEMAP: - goto do_ioctl; + goto found_handler; case FIBMAP: case FIGETBSZ: diff --git a/fs/drop_caches.c b/fs/drop_caches.c index d31b6c72b476..dc1a1d5d825b 100644 --- a/fs/drop_caches.c +++ b/fs/drop_caches.c @@ -35,11 +35,11 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused) spin_unlock(&inode->i_lock); spin_unlock(&sb->s_inode_list_lock); - cond_resched(); invalidate_mapping_pages(inode->i_mapping, 0, -1); iput(toput_inode); toput_inode = inode; + cond_resched(); spin_lock(&sb->s_inode_list_lock); } spin_unlock(&sb->s_inode_list_lock); diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c index a13a78725c57..b766c3ee5fa8 100644 --- a/fs/erofs/xattr.c +++ b/fs/erofs/xattr.c @@ -649,6 +649,8 @@ ssize_t erofs_listxattr(struct dentry *dentry, struct listxattr_iter it; ret = init_inode_xattrs(d_inode(dentry)); + if (ret == -ENOATTR) + return 0; if (ret) return ret; diff --git a/fs/exec.c b/fs/exec.c index 555e93c7dec8..c27231234764 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1015,7 +1015,7 @@ static int exec_mmap(struct mm_struct *mm) /* Notify parent that we're no longer interested in the old VM */ tsk = current; old_mm = current->mm; - mm_release(tsk, old_mm); + exec_mm_release(tsk, old_mm); if (old_mm) { sync_mm_rss(old_mm); diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 7004ce581a32..a16c53655e77 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -701,10 +701,13 @@ static int ext2_get_blocks(struct inode *inode, if (!partial) { count++; mutex_unlock(&ei->truncate_mutex); - if (err) - goto cleanup; goto got_it; } + + if (err) { + mutex_unlock(&ei->truncate_mutex); + goto cleanup; + } } /* diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index 9fdd2b269d61..6305d5ec25af 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -81,6 +81,11 @@ int __ext4_check_dir_entry(const char *function, unsigned int line, error_msg = "rec_len is too small for name_len"; else if (unlikely(((char *) de - buf) + rlen > size)) error_msg = "directory entry overrun"; + else if (unlikely(((char *) de - buf) + rlen > + size - EXT4_DIR_REC_LEN(1) && + ((char *) de - buf) + rlen != size)) { + error_msg = "directory entry too close to block end"; + } else if (unlikely(le32_to_cpu(de->inode) > le32_to_cpu(EXT4_SB(dir->i_sb)->s_es->s_inodes_count))) error_msg = "inode out of bounds"; diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 764ff4c56233..564e2ceb8417 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -265,13 +265,8 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) ext4_debug("freeing inode %lu\n", ino); trace_ext4_free_inode(inode); - /* - * Note: we must free any quota before locking the superblock, - * as writing the quota to disk may need the lock as well. - */ dquot_initialize(inode); dquot_free_inode(inode); - dquot_drop(inode); is_directory = S_ISDIR(inode->i_mode); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 516faa280ced..8bba6cd5e870 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -196,7 +196,12 @@ void ext4_evict_inode(struct inode *inode) { handle_t *handle; int err; - int extra_credits = 3; + /* + * Credits for final inode cleanup and freeing: + * sb + inode (ext4_orphan_del()), block bitmap, group descriptor + * (xattr block freeing), bitmap, group descriptor (inode freeing) + */ + int extra_credits = 6; struct ext4_xattr_inode_array *ea_inode_array = NULL; trace_ext4_evict_inode(inode); @@ -252,8 +257,12 @@ void ext4_evict_inode(struct inode *inode) if (!IS_NOQUOTA(inode)) extra_credits += EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb); + /* + * Block bitmap, group descriptor, and inode are accounted in both + * ext4_blocks_for_truncate() and extra_credits. So subtract 3. + */ handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, - ext4_blocks_for_truncate(inode)+extra_credits); + ext4_blocks_for_truncate(inode) + extra_credits - 3); if (IS_ERR(handle)) { ext4_std_error(inode->i_sb, PTR_ERR(handle)); /* @@ -3523,8 +3532,14 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length, return ret; } + /* + * Writes that span EOF might trigger an I/O size update on completion, + * so consider them to be dirty for the purposes of O_DSYNC, even if + * there is no other metadata changes being made or are pending here. + */ iomap->flags = 0; - if (ext4_inode_datasync_dirty(inode)) + if (ext4_inode_datasync_dirty(inode) || + offset + length > i_size_read(inode)) iomap->flags |= IOMAP_F_DIRTY; iomap->bdev = inode->i_sb->s_bdev; iomap->dax_dev = sbi->s_daxdev; @@ -3827,7 +3842,13 @@ static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter) * writes & truncates and since we take care of writing back page cache, * we are protected against page writeback as well. */ - inode_lock_shared(inode); + if (iocb->ki_flags & IOCB_NOWAIT) { + if (!inode_trylock_shared(inode)) + return -EAGAIN; + } else { + inode_lock_shared(inode); + } + ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, iocb->ki_pos + count - 1); if (ret) @@ -5450,11 +5471,15 @@ static void ext4_wait_for_tail_page_commit(struct inode *inode) offset = inode->i_size & (PAGE_SIZE - 1); /* - * All buffers in the last page remain valid? Then there's nothing to - * do. We do the check mainly to optimize the common PAGE_SIZE == - * blocksize case + * If the page is fully truncated, we don't need to wait for any commit + * (and we even should not as __ext4_journalled_invalidatepage() may + * strip all buffers from the page but keep the page dirty which can then + * confuse e.g. concurrent ext4_writepage() seeing dirty page without + * buffers). Also we don't need to wait for any commit if all buffers in + * the page remain valid. This is most beneficial for the common case of + * blocksize == PAGESIZE. */ - if (offset > PAGE_SIZE - i_blocksize(inode)) + if (!offset || offset > (PAGE_SIZE - i_blocksize(inode))) return; while (1) { page = find_lock_page(inode->i_mapping, @@ -5912,8 +5937,23 @@ static int __ext4_expand_extra_isize(struct inode *inode, { struct ext4_inode *raw_inode; struct ext4_xattr_ibody_header *header; + unsigned int inode_size = EXT4_INODE_SIZE(inode->i_sb); + struct ext4_inode_info *ei = EXT4_I(inode); int error; + /* this was checked at iget time, but double check for good measure */ + if ((EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize > inode_size) || + (ei->i_extra_isize & 3)) { + EXT4_ERROR_INODE(inode, "bad extra_isize %u (inode size %u)", + ei->i_extra_isize, + EXT4_INODE_SIZE(inode->i_sb)); + return -EFSCORRUPTED; + } + if ((new_extra_isize < ei->i_extra_isize) || + (new_extra_isize < 4) || + (new_extra_isize > inode_size - EXT4_GOOD_OLD_INODE_SIZE)) + return -EINVAL; /* Should never happen */ + raw_inode = ext4_raw_inode(iloc); header = IHDR(inode, raw_inode); @@ -6007,7 +6047,7 @@ int ext4_expand_extra_isize(struct inode *inode, error = ext4_journal_get_write_access(handle, iloc->bh); if (error) { brelse(iloc->bh); - goto out_stop; + goto out_unlock; } error = __ext4_expand_extra_isize(inode, new_extra_isize, iloc, @@ -6017,8 +6057,8 @@ int ext4_expand_extra_isize(struct inode *inode, if (!error) error = rc; +out_unlock: ext4_write_unlock_xattr(inode, &no_expand); -out_stop: ext4_journal_stop(handle); return error; } diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index a427d2031a8d..f56402e9c11c 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2808,7 +2808,7 @@ bool ext4_empty_dir(struct inode *inode) { unsigned int offset; struct buffer_head *bh; - struct ext4_dir_entry_2 *de, *de1; + struct ext4_dir_entry_2 *de; struct super_block *sb; if (ext4_has_inline_data(inode)) { @@ -2833,19 +2833,25 @@ bool ext4_empty_dir(struct inode *inode) return true; de = (struct ext4_dir_entry_2 *) bh->b_data; - de1 = ext4_next_entry(de, sb->s_blocksize); - if (le32_to_cpu(de->inode) != inode->i_ino || - le32_to_cpu(de1->inode) == 0 || - strcmp(".", de->name) || strcmp("..", de1->name)) { - ext4_warning_inode(inode, "directory missing '.' and/or '..'"); + if (ext4_check_dir_entry(inode, NULL, de, bh, bh->b_data, bh->b_size, + 0) || + le32_to_cpu(de->inode) != inode->i_ino || strcmp(".", de->name)) { + ext4_warning_inode(inode, "directory missing '.'"); + brelse(bh); + return true; + } + offset = ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); + de = ext4_next_entry(de, sb->s_blocksize); + if (ext4_check_dir_entry(inode, NULL, de, bh, bh->b_data, bh->b_size, + offset) || + le32_to_cpu(de->inode) == 0 || strcmp("..", de->name)) { + ext4_warning_inode(inode, "directory missing '..'"); brelse(bh); return true; } - offset = ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize) + - ext4_rec_len_from_disk(de1->rec_len, sb->s_blocksize); - de = ext4_next_entry(de1, sb->s_blocksize); + offset += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); while (offset < inode->i_size) { - if ((void *) de >= (void *) (bh->b_data+sb->s_blocksize)) { + if (!(offset & (sb->s_blocksize - 1))) { unsigned int lblock; brelse(bh); lblock = offset >> EXT4_BLOCK_SIZE_BITS(sb); @@ -2856,12 +2862,11 @@ bool ext4_empty_dir(struct inode *inode) } if (IS_ERR(bh)) return true; - de = (struct ext4_dir_entry_2 *) bh->b_data; } + de = (struct ext4_dir_entry_2 *) (bh->b_data + + (offset & (sb->s_blocksize - 1))); if (ext4_check_dir_entry(inode, NULL, de, bh, bh->b_data, bh->b_size, offset)) { - de = (struct ext4_dir_entry_2 *)(bh->b_data + - sb->s_blocksize); offset = (offset | (sb->s_blocksize - 1)) + 1; continue; } @@ -2870,7 +2875,6 @@ bool ext4_empty_dir(struct inode *inode) return false; } offset += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); - de = ext4_next_entry(de, sb->s_blocksize); } brelse(bh); return true; @@ -3182,18 +3186,17 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) if (IS_DIRSYNC(dir)) ext4_handle_sync(handle); - if (inode->i_nlink == 0) { - ext4_warning_inode(inode, "Deleting file '%.*s' with no links", - dentry->d_name.len, dentry->d_name.name); - set_nlink(inode, 1); - } retval = ext4_delete_entry(handle, dir, de, bh); if (retval) goto end_unlink; dir->i_ctime = dir->i_mtime = current_time(dir); ext4_update_dx_flag(dir); ext4_mark_inode_dirty(handle, dir); - drop_nlink(inode); + if (inode->i_nlink == 0) + ext4_warning_inode(inode, "Deleting file '%.*s' with no links", + dentry->d_name.len, dentry->d_name.name); + else + drop_nlink(inode); if (!inode->i_nlink) ext4_orphan_add(handle, inode); inode->i_ctime = current_time(inode); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index dd654e53ba3d..66162b430edc 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1172,9 +1172,9 @@ void ext4_clear_inode(struct inode *inode) { invalidate_inode_buffers(inode); clear_inode(inode); - dquot_drop(inode); ext4_discard_preallocations(inode); ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS); + dquot_drop(inode); if (EXT4_I(inode)->jinode) { jbd2_journal_release_jbd_inode(EXT4_JOURNAL(inode), EXT4_I(inode)->jinode); @@ -1887,6 +1887,13 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, } sbi->s_commit_interval = HZ * arg; } else if (token == Opt_debug_want_extra_isize) { + if ((arg & 1) || + (arg < 4) || + (arg > (sbi->s_inode_size - EXT4_GOOD_OLD_INODE_SIZE))) { + ext4_msg(sb, KERN_ERR, + "Invalid want_extra_isize %d", arg); + return -1; + } sbi->s_want_extra_isize = arg; } else if (token == Opt_max_batch_time) { sbi->s_max_batch_time = arg; @@ -3551,37 +3558,6 @@ int ext4_calculate_overhead(struct super_block *sb) return 0; } -static void ext4_clamp_want_extra_isize(struct super_block *sb) -{ - struct ext4_sb_info *sbi = EXT4_SB(sb); - struct ext4_super_block *es = sbi->s_es; - - /* determine the minimum size of new large inodes, if present */ - if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE && - sbi->s_want_extra_isize == 0) { - sbi->s_want_extra_isize = sizeof(struct ext4_inode) - - EXT4_GOOD_OLD_INODE_SIZE; - if (ext4_has_feature_extra_isize(sb)) { - if (sbi->s_want_extra_isize < - le16_to_cpu(es->s_want_extra_isize)) - sbi->s_want_extra_isize = - le16_to_cpu(es->s_want_extra_isize); - if (sbi->s_want_extra_isize < - le16_to_cpu(es->s_min_extra_isize)) - sbi->s_want_extra_isize = - le16_to_cpu(es->s_min_extra_isize); - } - } - /* Check if enough inode space is available */ - if (EXT4_GOOD_OLD_INODE_SIZE + sbi->s_want_extra_isize > - sbi->s_inode_size) { - sbi->s_want_extra_isize = sizeof(struct ext4_inode) - - EXT4_GOOD_OLD_INODE_SIZE; - ext4_msg(sb, KERN_INFO, - "required extra inode space not available"); - } -} - static void ext4_set_resv_clusters(struct super_block *sb) { ext4_fsblk_t resv_clusters; @@ -3789,6 +3765,68 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) */ sbi->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT; + if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) { + sbi->s_inode_size = EXT4_GOOD_OLD_INODE_SIZE; + sbi->s_first_ino = EXT4_GOOD_OLD_FIRST_INO; + } else { + sbi->s_inode_size = le16_to_cpu(es->s_inode_size); + sbi->s_first_ino = le32_to_cpu(es->s_first_ino); + if (sbi->s_first_ino < EXT4_GOOD_OLD_FIRST_INO) { + ext4_msg(sb, KERN_ERR, "invalid first ino: %u", + sbi->s_first_ino); + goto failed_mount; + } + if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) || + (!is_power_of_2(sbi->s_inode_size)) || + (sbi->s_inode_size > blocksize)) { + ext4_msg(sb, KERN_ERR, + "unsupported inode size: %d", + sbi->s_inode_size); + goto failed_mount; + } + /* + * i_atime_extra is the last extra field available for + * [acm]times in struct ext4_inode. Checking for that + * field should suffice to ensure we have extra space + * for all three. + */ + if (sbi->s_inode_size >= offsetof(struct ext4_inode, i_atime_extra) + + sizeof(((struct ext4_inode *)0)->i_atime_extra)) { + sb->s_time_gran = 1; + sb->s_time_max = EXT4_EXTRA_TIMESTAMP_MAX; + } else { + sb->s_time_gran = NSEC_PER_SEC; + sb->s_time_max = EXT4_NON_EXTRA_TIMESTAMP_MAX; + } + sb->s_time_min = EXT4_TIMESTAMP_MIN; + } + if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) { + sbi->s_want_extra_isize = sizeof(struct ext4_inode) - + EXT4_GOOD_OLD_INODE_SIZE; + if (ext4_has_feature_extra_isize(sb)) { + unsigned v, max = (sbi->s_inode_size - + EXT4_GOOD_OLD_INODE_SIZE); + + v = le16_to_cpu(es->s_want_extra_isize); + if (v > max) { + ext4_msg(sb, KERN_ERR, + "bad s_want_extra_isize: %d", v); + goto failed_mount; + } + if (sbi->s_want_extra_isize < v) + sbi->s_want_extra_isize = v; + + v = le16_to_cpu(es->s_min_extra_isize); + if (v > max) { + ext4_msg(sb, KERN_ERR, + "bad s_min_extra_isize: %d", v); + goto failed_mount; + } + if (sbi->s_want_extra_isize < v) + sbi->s_want_extra_isize = v; + } + } + if (sbi->s_es->s_mount_opts[0]) { char *s_mount_opts = kstrndup(sbi->s_es->s_mount_opts, sizeof(sbi->s_es->s_mount_opts), @@ -4027,42 +4065,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) has_huge_files); sb->s_maxbytes = ext4_max_size(sb->s_blocksize_bits, has_huge_files); - if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) { - sbi->s_inode_size = EXT4_GOOD_OLD_INODE_SIZE; - sbi->s_first_ino = EXT4_GOOD_OLD_FIRST_INO; - } else { - sbi->s_inode_size = le16_to_cpu(es->s_inode_size); - sbi->s_first_ino = le32_to_cpu(es->s_first_ino); - if (sbi->s_first_ino < EXT4_GOOD_OLD_FIRST_INO) { - ext4_msg(sb, KERN_ERR, "invalid first ino: %u", - sbi->s_first_ino); - goto failed_mount; - } - if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) || - (!is_power_of_2(sbi->s_inode_size)) || - (sbi->s_inode_size > blocksize)) { - ext4_msg(sb, KERN_ERR, - "unsupported inode size: %d", - sbi->s_inode_size); - goto failed_mount; - } - /* - * i_atime_extra is the last extra field available for [acm]times in - * struct ext4_inode. Checking for that field should suffice to ensure - * we have extra space for all three. - */ - if (sbi->s_inode_size >= offsetof(struct ext4_inode, i_atime_extra) + - sizeof(((struct ext4_inode *)0)->i_atime_extra)) { - sb->s_time_gran = 1; - sb->s_time_max = EXT4_EXTRA_TIMESTAMP_MAX; - } else { - sb->s_time_gran = NSEC_PER_SEC; - sb->s_time_max = EXT4_NON_EXTRA_TIMESTAMP_MAX; - } - - sb->s_time_min = EXT4_TIMESTAMP_MIN; - } - sbi->s_desc_size = le16_to_cpu(es->s_desc_size); if (ext4_has_feature_64bit(sb)) { if (sbi->s_desc_size < EXT4_MIN_DESC_SIZE_64BIT || @@ -4518,8 +4520,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } else if (ret) goto failed_mount4a; - ext4_clamp_want_extra_isize(sb); - ext4_set_resv_clusters(sb); err = ext4_setup_system_zone(sb); @@ -5307,8 +5307,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) goto restore_opts; } - ext4_clamp_want_extra_isize(sb); - if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^ test_opt(sb, JOURNAL_CHECKSUM)) { ext4_msg(sb, KERN_ERR, "changing journal_checksum " diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 5755e897a5f0..2e9c73165800 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -2098,7 +2098,7 @@ static int __write_data_page(struct page *page, bool *submitted, loff_t i_size = i_size_read(inode); const pgoff_t end_index = ((unsigned long long) i_size) >> PAGE_SHIFT; - loff_t psize = (page->index + 1) << PAGE_SHIFT; + loff_t psize = (loff_t)(page->index + 1) << PAGE_SHIFT; unsigned offset = 0; bool need_balance_fs = false; int err = 0; diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 4024790028aa..9046432b87c2 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1289,6 +1289,7 @@ struct f2fs_sb_info { unsigned int gc_mode; /* current GC state */ unsigned int next_victim_seg[2]; /* next segment in victim section */ /* for skip statistic */ + unsigned int atomic_files; /* # of opened atomic file */ unsigned long long skipped_atomic_files[2]; /* FG_GC and BG_GC */ unsigned long long skipped_gc_rwsem; /* FG_GC only */ @@ -2704,6 +2705,20 @@ static inline void clear_file(struct inode *inode, int type) f2fs_mark_inode_dirty_sync(inode, true); } +static inline bool f2fs_is_time_consistent(struct inode *inode) +{ + if (!timespec64_equal(F2FS_I(inode)->i_disk_time, &inode->i_atime)) + return false; + if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 1, &inode->i_ctime)) + return false; + if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 2, &inode->i_mtime)) + return false; + if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 3, + &F2FS_I(inode)->i_crtime)) + return false; + return true; +} + static inline bool f2fs_skip_inode_update(struct inode *inode, int dsync) { bool ret; @@ -2721,14 +2736,7 @@ static inline bool f2fs_skip_inode_update(struct inode *inode, int dsync) i_size_read(inode) & ~PAGE_MASK) return false; - if (!timespec64_equal(F2FS_I(inode)->i_disk_time, &inode->i_atime)) - return false; - if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 1, &inode->i_ctime)) - return false; - if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 2, &inode->i_mtime)) - return false; - if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 3, - &F2FS_I(inode)->i_crtime)) + if (!f2fs_is_time_consistent(inode)) return false; down_read(&F2FS_I(inode)->i_sem); diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 29bc0a542759..fae665691481 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1139,7 +1139,7 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode, } dn.ofs_in_node++; i++; - new_size = (dst + i) << PAGE_SHIFT; + new_size = (loff_t)(dst + i) << PAGE_SHIFT; if (dst_inode->i_size < new_size) f2fs_i_size_write(dst_inode, new_size); } while (--ilen && (do_replace[i] || blkaddr[i] == NULL_ADDR)); @@ -1890,6 +1890,7 @@ static int f2fs_ioc_start_atomic_write(struct file *filp) spin_lock(&sbi->inode_lock[ATOMIC_FILE]); if (list_empty(&fi->inmem_ilist)) list_add_tail(&fi->inmem_ilist, &sbi->inode_list[ATOMIC_FILE]); + sbi->atomic_files++; spin_unlock(&sbi->inode_lock[ATOMIC_FILE]); /* add inode in inmem_list first and set atomic_file */ diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index db4fec30c30d..386ad54c13c3 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -615,7 +615,11 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc) inode->i_ino == F2FS_META_INO(sbi)) return 0; - if (!is_inode_flag_set(inode, FI_DIRTY_INODE)) + /* + * atime could be updated without dirtying f2fs inode in lazytime mode + */ + if (f2fs_is_time_consistent(inode) && + !is_inode_flag_set(inode, FI_DIRTY_INODE)) return 0; if (!f2fs_is_checkpoint_ready(sbi)) diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 4faf06e8bf89..a1c507b0b4ac 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -981,7 +981,8 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, if (!old_dir_entry || whiteout) file_lost_pino(old_inode); else - F2FS_I(old_inode)->i_pino = new_dir->i_ino; + /* adjust dir's i_pino to pass fsck check */ + f2fs_i_pino_write(old_inode, new_dir->i_ino); up_write(&F2FS_I(old_inode)->i_sem); old_inode->i_ctime = current_time(old_inode); @@ -1141,7 +1142,11 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, f2fs_set_link(old_dir, old_entry, old_page, new_inode); down_write(&F2FS_I(old_inode)->i_sem); - file_lost_pino(old_inode); + if (!old_dir_entry) + file_lost_pino(old_inode); + else + /* adjust dir's i_pino to pass fsck check */ + f2fs_i_pino_write(old_inode, new_dir->i_ino); up_write(&F2FS_I(old_inode)->i_sem); old_dir->i_ctime = current_time(old_dir); @@ -1156,7 +1161,11 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, f2fs_set_link(new_dir, new_entry, new_page, old_inode); down_write(&F2FS_I(new_inode)->i_sem); - file_lost_pino(new_inode); + if (!new_dir_entry) + file_lost_pino(new_inode); + else + /* adjust dir's i_pino to pass fsck check */ + f2fs_i_pino_write(new_inode, old_dir->i_ino); up_write(&F2FS_I(new_inode)->i_sem); new_dir->i_ctime = current_time(new_dir); diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 808709581481..7d8578401267 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -288,6 +288,8 @@ void f2fs_drop_inmem_pages_all(struct f2fs_sb_info *sbi, bool gc_failure) struct list_head *head = &sbi->inode_list[ATOMIC_FILE]; struct inode *inode; struct f2fs_inode_info *fi; + unsigned int count = sbi->atomic_files; + unsigned int looped = 0; next: spin_lock(&sbi->inode_lock[ATOMIC_FILE]); if (list_empty(head)) { @@ -296,22 +298,26 @@ void f2fs_drop_inmem_pages_all(struct f2fs_sb_info *sbi, bool gc_failure) } fi = list_first_entry(head, struct f2fs_inode_info, inmem_ilist); inode = igrab(&fi->vfs_inode); + if (inode) + list_move_tail(&fi->inmem_ilist, head); spin_unlock(&sbi->inode_lock[ATOMIC_FILE]); if (inode) { if (gc_failure) { - if (fi->i_gc_failures[GC_FAILURE_ATOMIC]) - goto drop; - goto skip; + if (!fi->i_gc_failures[GC_FAILURE_ATOMIC]) + goto skip; } -drop: set_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST); f2fs_drop_inmem_pages(inode); +skip: iput(inode); } -skip: congestion_wait(BLK_RW_ASYNC, HZ/50); cond_resched(); + if (gc_failure) { + if (++looped >= count) + return; + } goto next; } @@ -327,13 +333,16 @@ void f2fs_drop_inmem_pages(struct inode *inode) mutex_unlock(&fi->inmem_lock); } - clear_inode_flag(inode, FI_ATOMIC_FILE); fi->i_gc_failures[GC_FAILURE_ATOMIC] = 0; stat_dec_atomic_write(inode); spin_lock(&sbi->inode_lock[ATOMIC_FILE]); if (!list_empty(&fi->inmem_ilist)) list_del_init(&fi->inmem_ilist); + if (f2fs_is_atomic_file(inode)) { + clear_inode_flag(inode, FI_ATOMIC_FILE); + sbi->atomic_files--; + } spin_unlock(&sbi->inode_lock[ATOMIC_FILE]); } diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 54d638f9ba1c..ee190119f45c 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -248,7 +248,8 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) kfree(forget); if (ret == -ENOMEM) goto out; - if (ret || (outarg.attr.mode ^ inode->i_mode) & S_IFMT) + if (ret || fuse_invalid_attr(&outarg.attr) || + (outarg.attr.mode ^ inode->i_mode) & S_IFMT) goto invalid; forget_all_cached_acls(inode); @@ -319,6 +320,12 @@ int fuse_valid_type(int m) S_ISBLK(m) || S_ISFIFO(m) || S_ISSOCK(m); } +bool fuse_invalid_attr(struct fuse_attr *attr) +{ + return !fuse_valid_type(attr->mode) || + attr->size > LLONG_MAX; +} + int fuse_lookup_name(struct super_block *sb, u64 nodeid, const struct qstr *name, struct fuse_entry_out *outarg, struct inode **inode) { @@ -350,7 +357,7 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, const struct qstr *name err = -EIO; if (!outarg->nodeid) goto out_put_forget; - if (!fuse_valid_type(outarg->attr.mode)) + if (fuse_invalid_attr(&outarg->attr)) goto out_put_forget; *inode = fuse_iget(sb, outarg->nodeid, outarg->generation, @@ -475,7 +482,8 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, goto out_free_ff; err = -EIO; - if (!S_ISREG(outentry.attr.mode) || invalid_nodeid(outentry.nodeid)) + if (!S_ISREG(outentry.attr.mode) || invalid_nodeid(outentry.nodeid) || + fuse_invalid_attr(&outentry.attr)) goto out_free_ff; ff->fh = outopen.fh; @@ -583,7 +591,7 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_args *args, goto out_put_forget_req; err = -EIO; - if (invalid_nodeid(outarg.nodeid)) + if (invalid_nodeid(outarg.nodeid) || fuse_invalid_attr(&outarg.attr)) goto out_put_forget_req; if ((outarg.attr.mode ^ mode) & S_IFMT) @@ -862,7 +870,8 @@ static int fuse_link(struct dentry *entry, struct inode *newdir, spin_lock(&fi->lock); fi->attr_version = atomic64_inc_return(&fc->attr_version); - inc_nlink(inode); + if (likely(inode->i_nlink < UINT_MAX)) + inc_nlink(inode); spin_unlock(&fi->lock); fuse_invalidate_attr(inode); fuse_update_ctime(inode); @@ -942,7 +951,8 @@ static int fuse_do_getattr(struct inode *inode, struct kstat *stat, args.out_args[0].value = &outarg; err = fuse_simple_request(fc, &args); if (!err) { - if ((inode->i_mode ^ outarg.attr.mode) & S_IFMT) { + if (fuse_invalid_attr(&outarg.attr) || + (inode->i_mode ^ outarg.attr.mode) & S_IFMT) { make_bad_inode(inode); err = -EIO; } else { @@ -1563,7 +1573,8 @@ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr, goto error; } - if ((inode->i_mode ^ outarg.attr.mode) & S_IFMT) { + if (fuse_invalid_attr(&outarg.attr) || + (inode->i_mode ^ outarg.attr.mode) & S_IFMT) { make_bad_inode(inode); err = -EIO; goto error; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index db48a5cf8620..a63d779eac10 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -713,8 +713,10 @@ static ssize_t fuse_async_req_send(struct fuse_conn *fc, ia->ap.args.end = fuse_aio_complete_req; err = fuse_simple_background(fc, &ia->ap.args, GFP_KERNEL); + if (err) + fuse_aio_complete_req(fc, &ia->ap.args, err); - return err ?: num_bytes; + return num_bytes; } static ssize_t fuse_send_read(struct fuse_io_args *ia, loff_t pos, size_t count, @@ -1096,6 +1098,8 @@ static ssize_t fuse_send_write_pages(struct fuse_io_args *ia, ia->write.in.flags = fuse_write_flags(iocb); err = fuse_simple_request(fc, &ap->args); + if (!err && ia->write.out.size > count) + err = -EIO; offset = ap->descs[0].offset; count = ia->write.out.size; diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index d148188cfca4..aa75e2305b75 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -989,6 +989,8 @@ void fuse_ctl_remove_conn(struct fuse_conn *fc); */ int fuse_valid_type(int m); +bool fuse_invalid_attr(struct fuse_attr *attr); + /** * Is current process allowed to perform filesystem operation? */ diff --git a/fs/fuse/readdir.c b/fs/fuse/readdir.c index 5c38b9d84c6e..6a40f75a0d25 100644 --- a/fs/fuse/readdir.c +++ b/fs/fuse/readdir.c @@ -184,7 +184,7 @@ static int fuse_direntplus_link(struct file *file, if (invalid_nodeid(o->nodeid)) return -EIO; - if (!fuse_valid_type(o->attr.mode)) + if (fuse_invalid_attr(&o->attr)) return -EIO; fc = get_fuse_conn(dir); diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 997b326247e2..01ff37b76652 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -6,6 +6,7 @@ #include #include +#include #include #include #include @@ -354,6 +355,31 @@ static long gfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return -ENOTTY; } +#ifdef CONFIG_COMPAT +static long gfs2_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) +{ + switch(cmd) { + /* These are just misnamed, they actually get/put from/to user an int */ + case FS_IOC32_GETFLAGS: + cmd = FS_IOC_GETFLAGS; + break; + case FS_IOC32_SETFLAGS: + cmd = FS_IOC_SETFLAGS; + break; + /* Keep this list in sync with gfs2_ioctl */ + case FITRIM: + case FS_IOC_GETFSLABEL: + break; + default: + return -ENOIOCTLCMD; + } + + return gfs2_ioctl(filp, cmd, (unsigned long)compat_ptr(arg)); +} +#else +#define gfs2_compat_ioctl NULL +#endif + /** * gfs2_size_hint - Give a hint to the size of a write request * @filep: The struct file @@ -381,27 +407,28 @@ static void gfs2_size_hint(struct file *filep, loff_t offset, size_t size) /** * gfs2_allocate_page_backing - Allocate blocks for a write fault * @page: The (locked) page to allocate backing for + * @length: Size of the allocation * * We try to allocate all the blocks required for the page in one go. This * might fail for various reasons, so we keep trying until all the blocks to * back this page are allocated. If some of the blocks are already allocated, * that is ok too. */ -static int gfs2_allocate_page_backing(struct page *page) +static int gfs2_allocate_page_backing(struct page *page, unsigned int length) { u64 pos = page_offset(page); - u64 size = PAGE_SIZE; do { struct iomap iomap = { }; - if (gfs2_iomap_get_alloc(page->mapping->host, pos, 1, &iomap)) + if (gfs2_iomap_get_alloc(page->mapping->host, pos, length, &iomap)) return -EIO; - iomap.length = min(iomap.length, size); - size -= iomap.length; + if (length < iomap.length) + iomap.length = length; + length -= iomap.length; pos += iomap.length; - } while (size > 0); + } while (length > 0); return 0; } @@ -501,7 +528,7 @@ static vm_fault_t gfs2_page_mkwrite(struct vm_fault *vmf) if (gfs2_is_stuffed(ip)) ret = gfs2_unstuff_dinode(ip, page); if (ret == 0) - ret = gfs2_allocate_page_backing(page); + ret = gfs2_allocate_page_backing(page, PAGE_SIZE); out_trans_end: if (ret) @@ -1293,6 +1320,7 @@ const struct file_operations gfs2_file_fops = { .write_iter = gfs2_file_write_iter, .iopoll = iomap_dio_iopoll, .unlocked_ioctl = gfs2_ioctl, + .compat_ioctl = gfs2_compat_ioctl, .mmap = gfs2_mmap, .open = gfs2_open, .release = gfs2_release, @@ -1308,6 +1336,7 @@ const struct file_operations gfs2_file_fops = { const struct file_operations gfs2_dir_fops = { .iterate_shared = gfs2_readdir, .unlocked_ioctl = gfs2_ioctl, + .compat_ioctl = gfs2_compat_ioctl, .open = gfs2_open, .release = gfs2_release, .fsync = gfs2_fsync, @@ -1324,6 +1353,7 @@ const struct file_operations gfs2_file_fops_nolock = { .write_iter = gfs2_file_write_iter, .iopoll = iomap_dio_iopoll, .unlocked_ioctl = gfs2_ioctl, + .compat_ioctl = gfs2_compat_ioctl, .mmap = gfs2_mmap, .open = gfs2_open, .release = gfs2_release, @@ -1337,6 +1367,7 @@ const struct file_operations gfs2_file_fops_nolock = { const struct file_operations gfs2_dir_fops_nolock = { .iterate_shared = gfs2_readdir, .unlocked_ioctl = gfs2_ioctl, + .compat_ioctl = gfs2_compat_ioctl, .open = gfs2_open, .release = gfs2_release, .fsync = gfs2_fsync, diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 58e237fba565..2aed73666a65 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -609,6 +609,14 @@ void gfs2_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) list_add(&bd->bd_list, &sdp->sd_log_revokes); } +void gfs2_glock_remove_revoke(struct gfs2_glock *gl) +{ + if (atomic_dec_return(&gl->gl_revokes) == 0) { + clear_bit(GLF_LFLUSH, &gl->gl_flags); + gfs2_glock_queue_put(gl); + } +} + void gfs2_write_revokes(struct gfs2_sbd *sdp) { struct gfs2_trans *tr; diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h index 2315fca47a2b..c762da494546 100644 --- a/fs/gfs2/log.h +++ b/fs/gfs2/log.h @@ -77,6 +77,7 @@ extern void gfs2_ail1_flush(struct gfs2_sbd *sdp, struct writeback_control *wbc) extern void gfs2_log_shutdown(struct gfs2_sbd *sdp); extern int gfs2_logd(void *data); extern void gfs2_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd); +extern void gfs2_glock_remove_revoke(struct gfs2_glock *gl); extern void gfs2_write_revokes(struct gfs2_sbd *sdp); #endif /* __LOG_DOT_H__ */ diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 5b17979af539..e2437b775456 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -882,10 +882,7 @@ static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) bd = list_entry(head->next, struct gfs2_bufdata, bd_list); list_del_init(&bd->bd_list); gl = bd->bd_gl; - if (atomic_dec_return(&gl->gl_revokes) == 0) { - clear_bit(GLF_LFLUSH, &gl->gl_flags); - gfs2_glock_queue_put(gl); - } + gfs2_glock_remove_revoke(gl); kmem_cache_free(gfs2_bufdata_cachep, bd); } } diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c index 35e3059255fe..9d4227330de4 100644 --- a/fs/gfs2/trans.c +++ b/fs/gfs2/trans.c @@ -262,6 +262,8 @@ void gfs2_trans_remove_revoke(struct gfs2_sbd *sdp, u64 blkno, unsigned int len) list_del_init(&bd->bd_list); gfs2_assert_withdraw(sdp, sdp->sd_log_num_revoke); sdp->sd_log_num_revoke--; + if (bd->bd_gl) + gfs2_glock_remove_revoke(bd->bd_gl); kmem_cache_free(gfs2_bufdata_cachep, bd); tr->tr_num_revoke--; if (--n == 0) diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index a478df035651..40306c1eab07 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -1461,28 +1461,43 @@ static int __init init_hugetlbfs_fs(void) sizeof(struct hugetlbfs_inode_info), 0, SLAB_ACCOUNT, init_once); if (hugetlbfs_inode_cachep == NULL) - goto out2; + goto out; error = register_filesystem(&hugetlbfs_fs_type); if (error) - goto out; + goto out_free; + /* default hstate mount is required */ + mnt = mount_one_hugetlbfs(&hstates[default_hstate_idx]); + if (IS_ERR(mnt)) { + error = PTR_ERR(mnt); + goto out_unreg; + } + hugetlbfs_vfsmount[default_hstate_idx] = mnt; + + /* other hstates are optional */ i = 0; for_each_hstate(h) { - mnt = mount_one_hugetlbfs(h); - if (IS_ERR(mnt) && i == 0) { - error = PTR_ERR(mnt); - goto out; + if (i == default_hstate_idx) { + i++; + continue; } - hugetlbfs_vfsmount[i] = mnt; + + mnt = mount_one_hugetlbfs(h); + if (IS_ERR(mnt)) + hugetlbfs_vfsmount[i] = NULL; + else + hugetlbfs_vfsmount[i] = mnt; i++; } return 0; - out: + out_unreg: + (void)unregister_filesystem(&hugetlbfs_fs_type); + out_free: kmem_cache_destroy(hugetlbfs_inode_cachep); - out2: + out: return error; } fs_initcall(init_hugetlbfs_fs) diff --git a/fs/inode.c b/fs/inode.c index fef457a42882..96d62d97694e 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -676,6 +676,7 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty) struct inode *inode, *next; LIST_HEAD(dispose); +again: spin_lock(&sb->s_inode_list_lock); list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) { spin_lock(&inode->i_lock); @@ -698,6 +699,12 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty) inode_lru_list_del(inode); spin_unlock(&inode->i_lock); list_add(&inode->i_lru, &dispose); + if (need_resched()) { + spin_unlock(&sb->s_inode_list_lock); + cond_resched(); + dispose_list(&dispose); + goto again; + } } spin_unlock(&sb->s_inode_list_lock); diff --git a/fs/internal.h b/fs/internal.h index 315fcd8d237c..7651e8b8ef13 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -38,7 +38,7 @@ static inline int __sync_blockdev(struct block_device *bdev, int wait) /* * buffer.c */ -extern void guard_bio_eod(int rw, struct bio *bio); +extern void guard_bio_eod(struct bio *bio); extern int __block_write_begin_int(struct page *page, loff_t pos, unsigned len, get_block_t *get_block, struct iomap *iomap); diff --git a/fs/io_uring.c b/fs/io_uring.c index 2c819c3c855d..709671faaed6 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -70,6 +70,7 @@ #include #include #include +#include #include @@ -238,6 +239,8 @@ struct io_ring_ctx { struct user_struct *user; + const struct cred *creds; + struct completion ctx_done; struct { @@ -1349,9 +1352,19 @@ static ssize_t loop_rw_iter(int rw, struct file *file, struct kiocb *kiocb, return -EAGAIN; while (iov_iter_count(iter)) { - struct iovec iovec = iov_iter_iovec(iter); + struct iovec iovec; ssize_t nr; + if (!iov_iter_is_bvec(iter)) { + iovec = iov_iter_iovec(iter); + } else { + /* fixed buffers import bvec */ + iovec.iov_base = kmap(iter->bvec->bv_page) + + iter->iov_offset; + iovec.iov_len = min(iter->count, + iter->bvec->bv_len - iter->iov_offset); + } + if (rw == READ) { nr = file->f_op->read(file, iovec.iov_base, iovec.iov_len, &kiocb->ki_pos); @@ -1360,6 +1373,9 @@ static ssize_t loop_rw_iter(int rw, struct file *file, struct kiocb *kiocb, iovec.iov_len, &kiocb->ki_pos); } + if (iov_iter_is_bvec(iter)) + kunmap(iter->bvec->bv_page); + if (nr < 0) { if (!ret) ret = nr; @@ -1652,6 +1668,8 @@ static int io_send_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe, ret = fn(sock, msg, flags); if (force_nonblock && ret == -EAGAIN) return ret; + if (ret == -ERESTARTSYS) + ret = -EINTR; } io_cqring_add_event(req->ctx, sqe->user_data, ret); @@ -1752,8 +1770,11 @@ static void io_poll_complete_work(struct work_struct *work) struct io_poll_iocb *poll = &req->poll; struct poll_table_struct pt = { ._key = poll->events }; struct io_ring_ctx *ctx = req->ctx; + const struct cred *old_cred; __poll_t mask = 0; + old_cred = override_creds(ctx->creds); + if (!READ_ONCE(poll->canceled)) mask = vfs_poll(poll->file, &pt) & poll->events; @@ -1768,7 +1789,7 @@ static void io_poll_complete_work(struct work_struct *work) if (!mask && !READ_ONCE(poll->canceled)) { add_wait_queue(poll->head, &poll->wait); spin_unlock_irq(&ctx->completion_lock); - return; + goto out; } list_del_init(&req->list); io_poll_complete(ctx, req, mask); @@ -1776,6 +1797,8 @@ static void io_poll_complete_work(struct work_struct *work) io_cqring_ev_posted(ctx); io_put_req(req); +out: + revert_creds(old_cred); } static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, @@ -2016,7 +2039,7 @@ static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe) } static int io_req_defer(struct io_ring_ctx *ctx, struct io_kiocb *req, - const struct io_uring_sqe *sqe) + struct sqe_submit *s) { struct io_uring_sqe *sqe_copy; @@ -2034,7 +2057,8 @@ static int io_req_defer(struct io_ring_ctx *ctx, struct io_kiocb *req, return 0; } - memcpy(sqe_copy, sqe, sizeof(*sqe_copy)); + memcpy(&req->submit, s, sizeof(*s)); + memcpy(sqe_copy, s->sqe, sizeof(*sqe_copy)); req->submit.sqe = sqe_copy; INIT_WORK(&req->work, io_sq_wq_submit_work); @@ -2147,10 +2171,12 @@ static void io_sq_wq_submit_work(struct work_struct *work) struct io_ring_ctx *ctx = req->ctx; struct mm_struct *cur_mm = NULL; struct async_list *async_list; + const struct cred *old_cred; LIST_HEAD(req_list); mm_segment_t old_fs; int ret; + old_cred = override_creds(ctx->creds); async_list = io_async_list_from_sqe(ctx, req->submit.sqe); restart: do { @@ -2258,6 +2284,7 @@ static void io_sq_wq_submit_work(struct work_struct *work) unuse_mm(cur_mm); mmput(cur_mm); } + revert_creds(old_cred); } /* @@ -2399,7 +2426,7 @@ static int io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, { int ret; - ret = io_req_defer(ctx, req, s->sqe); + ret = io_req_defer(ctx, req, s); if (ret) { if (ret != -EIOCBQUEUED) { io_free_req(req); @@ -2426,7 +2453,7 @@ static int io_queue_link_head(struct io_ring_ctx *ctx, struct io_kiocb *req, * list. */ req->flags |= REQ_F_IO_DRAIN; - ret = io_req_defer(ctx, req, s->sqe); + ret = io_req_defer(ctx, req, s); if (ret) { if (ret != -EIOCBQUEUED) { io_free_req(req); @@ -2663,6 +2690,7 @@ static int io_sq_thread(void *data) { struct io_ring_ctx *ctx = data; struct mm_struct *cur_mm = NULL; + const struct cred *old_cred; mm_segment_t old_fs; DEFINE_WAIT(wait); unsigned inflight; @@ -2672,6 +2700,7 @@ static int io_sq_thread(void *data) old_fs = get_fs(); set_fs(USER_DS); + old_cred = override_creds(ctx->creds); timeout = inflight = 0; while (!kthread_should_park()) { @@ -2782,6 +2811,7 @@ static int io_sq_thread(void *data) unuse_mm(cur_mm); mmput(cur_mm); } + revert_creds(old_cred); kthread_parkme(); @@ -3567,6 +3597,8 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx) io_unaccount_mem(ctx->user, ring_pages(ctx->sq_entries, ctx->cq_entries)); free_uid(ctx->user); + if (ctx->creds) + put_cred(ctx->creds); kfree(ctx); } @@ -3689,6 +3721,9 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, mutex_lock(&ctx->uring_lock); submitted = io_ring_submit(ctx, to_submit); mutex_unlock(&ctx->uring_lock); + + if (submitted != to_submit) + goto out; } if (flags & IORING_ENTER_GETEVENTS) { unsigned nr_events = 0; @@ -3702,6 +3737,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, } } +out: percpu_ref_put(&ctx->refs); out_fput: fdput(f); @@ -3741,12 +3777,18 @@ static int io_allocate_scq_urings(struct io_ring_ctx *ctx, ctx->cq_entries = rings->cq_ring_entries; size = array_size(sizeof(struct io_uring_sqe), p->sq_entries); - if (size == SIZE_MAX) + if (size == SIZE_MAX) { + io_mem_free(ctx->rings); + ctx->rings = NULL; return -EOVERFLOW; + } ctx->sq_sqes = io_mem_alloc(size); - if (!ctx->sq_sqes) + if (!ctx->sq_sqes) { + io_mem_free(ctx->rings); + ctx->rings = NULL; return -ENOMEM; + } return 0; } @@ -3838,6 +3880,12 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p) ctx->account_mem = account_mem; ctx->user = user; + ctx->creds = get_current_cred(); + if (!ctx->creds) { + ret = -ENOMEM; + goto err; + } + ret = io_allocate_scq_urings(ctx, p); if (ret) goto err; diff --git a/fs/ioctl.c b/fs/ioctl.c index fef3a6bf7c78..3118da0de158 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include #include @@ -719,3 +720,37 @@ SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { return ksys_ioctl(fd, cmd, arg); } + +#ifdef CONFIG_COMPAT +/** + * compat_ptr_ioctl - generic implementation of .compat_ioctl file operation + * + * This is not normally called as a function, but instead set in struct + * file_operations as + * + * .compat_ioctl = compat_ptr_ioctl, + * + * On most architectures, the compat_ptr_ioctl() just passes all arguments + * to the corresponding ->ioctl handler. The exception is arch/s390, where + * compat_ptr() clears the top bit of a 32-bit pointer value, so user space + * pointers to the second 2GB alias the first 2GB, as is the case for + * native 32-bit s390 user space. + * + * The compat_ptr_ioctl() function must therefore be used only with ioctl + * functions that either ignore the argument or pass a pointer to a + * compatible data type. + * + * If any ioctl command handled by fops->unlocked_ioctl passes a plain + * integer instead of a pointer, or any of the passed data types + * is incompatible between 32-bit and 64-bit architectures, a proper + * handler is required instead of compat_ptr_ioctl. + */ +long compat_ptr_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + if (!file->f_op->unlocked_ioctl) + return -ENOIOCTLCMD; + + return file->f_op->unlocked_ioctl(file, cmd, (unsigned long)compat_ptr(arg)); +} +EXPORT_SYMBOL(compat_ptr_ioctl); +#endif diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 1fc28c2da279..7b5f76efef02 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -318,7 +318,9 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length, if (pad) iomap_dio_zero(dio, iomap, pos, fs_block_size - pad); } - return copied ? copied : ret; + if (copied) + return copied; + return ret; } static loff_t @@ -497,8 +499,15 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, } pos += ret; - if (iov_iter_rw(iter) == READ && pos >= dio->i_size) + if (iov_iter_rw(iter) == READ && pos >= dio->i_size) { + /* + * We only report that we've read data up to i_size. + * Revert iter to a state corresponding to that as + * some callers (such as splice code) rely on it. + */ + iov_iter_revert(iter, pos - dio->i_size); break; + } } while ((count = iov_iter_count(iter)) > 0); blk_finish_plug(&plug); diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 132fb92098c7..c43591cd70f1 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -727,7 +727,6 @@ void jbd2_journal_commit_transaction(journal_t *journal) submit_bh(REQ_OP_WRITE, REQ_SYNC, bh); } cond_resched(); - stats.run.rs_blocks_logged += bufs; /* Force a new descriptor to be generated next time round the loop. */ @@ -814,6 +813,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) if (unlikely(!buffer_uptodate(bh))) err = -EIO; jbd2_unfile_log_bh(bh); + stats.run.rs_blocks_logged++; /* * The list contains temporary buffer heads created by @@ -859,6 +859,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) BUFFER_TRACE(bh, "ph5: control buffer writeout done: unfile"); clear_buffer_jwrite(bh); jbd2_unfile_log_bh(bh); + stats.run.rs_blocks_logged++; __brelse(bh); /* One for getblk */ /* AKPM: bforget here */ } @@ -880,6 +881,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) } if (cbh) err = journal_wait_on_commit_record(journal, cbh); + stats.run.rs_blocks_logged++; if (jbd2_has_feature_async_commit(journal) && journal->j_flags & JBD2_BARRIER) { blkdev_issue_flush(journal->j_dev, GFP_NOFS, NULL); diff --git a/fs/jffs2/nodelist.c b/fs/jffs2/nodelist.c index 021a4a2190ee..b86c78d178c6 100644 --- a/fs/jffs2/nodelist.c +++ b/fs/jffs2/nodelist.c @@ -226,7 +226,7 @@ static int jffs2_add_frag_to_fragtree(struct jffs2_sb_info *c, struct rb_root *r lastend = this->ofs + this->size; } else { dbg_fragtree2("lookup gave no frag\n"); - return -EINVAL; + lastend = 0; } /* See if we ran off the end of the fragtree */ diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 6ebae6bbe6a5..7d4af6cea2a6 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -622,7 +622,6 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, { struct kernfs_node *kn; u32 gen; - int cursor; int ret; name = kstrdup_const(name, GFP_KERNEL); @@ -635,11 +634,11 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, idr_preload(GFP_KERNEL); spin_lock(&kernfs_idr_lock); - cursor = idr_get_cursor(&root->ino_idr); ret = idr_alloc_cyclic(&root->ino_idr, kn, 1, 0, GFP_ATOMIC); - if (ret >= 0 && ret < cursor) + if (ret >= 0 && ret < root->last_ino) root->next_generation++; gen = root->next_generation; + root->last_ino = ret; spin_unlock(&kernfs_idr_lock); idr_preload_end(); if (ret < 0) diff --git a/fs/locks.c b/fs/locks.c index 6970f55daf54..44b6da032842 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -2853,7 +2853,7 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl, } if (inode) { /* userspace relies on this representation of dev_t */ - seq_printf(f, "%d %02x:%02x:%ld ", fl_pid, + seq_printf(f, "%d %02x:%02x:%lu ", fl_pid, MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), inode->i_ino); } else { diff --git a/fs/mpage.c b/fs/mpage.c index a63620cdb73a..ccba3c4c4479 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -62,7 +62,7 @@ static struct bio *mpage_bio_submit(int op, int op_flags, struct bio *bio) { bio->bi_end_io = mpage_end_io; bio_set_op_attrs(bio, op, op_flags); - guard_bio_eod(op, bio); + guard_bio_eod(bio); submit_bio(bio); return NULL; } diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index cbc17a203248..887f9136a9db 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -370,7 +370,7 @@ static void encode_sattr(struct xdr_stream *xdr, const struct iattr *attr, } else p = xdr_time_not_set(p); if (attr->ia_valid & ATTR_MTIME_SET) { - ts = timespec64_to_timespec(attr->ia_atime); + ts = timespec64_to_timespec(attr->ia_mtime); xdr_encode_time(p, &ts); } else if (attr->ia_valid & ATTR_MTIME) { ts = timespec64_to_timespec(attr->ia_mtime); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index caacf5e7f5e1..f26d714f9f28 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -521,9 +521,7 @@ static int nfs4_do_handle_exception(struct nfs_server *server, case -NFS4ERR_DEADSESSION: case -NFS4ERR_SEQ_FALSE_RETRY: case -NFS4ERR_SEQ_MISORDERED: - dprintk("%s ERROR: %d Reset session\n", __func__, - errorcode); - nfs4_schedule_session_recovery(clp->cl_session, errorcode); + /* Handled in nfs41_sequence_process() */ goto wait_on_recovery; #endif /* defined(CONFIG_NFS_V4_1) */ case -NFS4ERR_FILE_OPEN: @@ -782,6 +780,7 @@ static int nfs41_sequence_process(struct rpc_task *task, struct nfs4_session *session; struct nfs4_slot *slot = res->sr_slot; struct nfs_client *clp; + int status; int ret = 1; if (slot == NULL) @@ -793,8 +792,13 @@ static int nfs41_sequence_process(struct rpc_task *task, session = slot->table->session; trace_nfs4_sequence_done(session, res); + + status = res->sr_status; + if (task->tk_status == -NFS4ERR_DEADSESSION) + status = -NFS4ERR_DEADSESSION; + /* Check the SEQUENCE operation status */ - switch (res->sr_status) { + switch (status) { case 0: /* Mark this sequence number as having been acked */ nfs4_slot_sequence_acked(slot, slot->seq_nr); @@ -866,6 +870,10 @@ static int nfs41_sequence_process(struct rpc_task *task, */ slot->seq_nr = slot->seq_nr_highest_sent; goto out_retry; + case -NFS4ERR_BADSESSION: + case -NFS4ERR_DEADSESSION: + case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: + goto session_recover; default: /* Just update the slot sequence no. */ slot->seq_done = 1; @@ -876,8 +884,10 @@ static int nfs41_sequence_process(struct rpc_task *task, out_noaction: return ret; session_recover: - nfs4_schedule_session_recovery(session, res->sr_status); - goto retry_nowait; + nfs4_schedule_session_recovery(session, status); + dprintk("%s ERROR: %d Reset session\n", __func__, status); + nfs41_sequence_free_slot(res); + goto out; retry_new_seq: ++slot->seq_nr; retry_nowait: @@ -2188,7 +2198,6 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct case -NFS4ERR_BAD_HIGH_SLOT: case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: case -NFS4ERR_DEADSESSION: - nfs4_schedule_session_recovery(server->nfs_client->cl_session, err); return -EAGAIN; case -NFS4ERR_STALE_CLIENTID: case -NFS4ERR_STALE_STATEID: @@ -6243,8 +6252,10 @@ static void nfs4_delegreturn_prepare(struct rpc_task *task, void *data) d_data = (struct nfs4_delegreturndata *)data; - if (!d_data->lr.roc && nfs4_wait_on_layoutreturn(d_data->inode, task)) + if (!d_data->lr.roc && nfs4_wait_on_layoutreturn(d_data->inode, task)) { + nfs4_sequence_done(task, &d_data->res.seq_res); return; + } lo = d_data->args.lr_args ? d_data->args.lr_args->layout : NULL; if (lo && !pnfs_layout_is_valid(lo)) { @@ -7820,6 +7831,15 @@ nfs41_same_server_scope(struct nfs41_server_scope *a, static void nfs4_bind_one_conn_to_session_done(struct rpc_task *task, void *calldata) { + struct nfs41_bind_conn_to_session_args *args = task->tk_msg.rpc_argp; + struct nfs_client *clp = args->client; + + switch (task->tk_status) { + case -NFS4ERR_BADSESSION: + case -NFS4ERR_DEADSESSION: + nfs4_schedule_session_recovery(clp->cl_session, + task->tk_status); + } } static const struct rpc_call_ops nfs4_bind_one_conn_to_session_ops = { @@ -8867,8 +8887,6 @@ static int nfs41_reclaim_complete_handle_errors(struct rpc_task *task, struct nf case -NFS4ERR_BADSESSION: case -NFS4ERR_DEADSESSION: case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: - nfs4_schedule_session_recovery(clp->cl_session, - task->tk_status); break; default: nfs4_schedule_lease_recovery(clp); diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig index 10cefb0c07c7..c4b1a89b8845 100644 --- a/fs/nfsd/Kconfig +++ b/fs/nfsd/Kconfig @@ -73,7 +73,7 @@ config NFSD_V4 select NFSD_V3 select FS_POSIX_ACL select SUNRPC_GSS - select CRYPTO + select CRYPTO_SHA256 select GRACE_PERIOD help This option enables support in your system's NFS server for diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 4e3e77b76411..4798667af647 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1077,7 +1077,8 @@ nfsd4_clone(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; status = nfsd4_clone_file_range(src->nf_file, clone->cl_src_pos, - dst->nf_file, clone->cl_dst_pos, clone->cl_count); + dst->nf_file, clone->cl_dst_pos, clone->cl_count, + EX_ISSYNC(cstate->current_fh.fh_export)); nfsd_file_put(dst); nfsd_file_put(src); @@ -1297,7 +1298,8 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, out: return status; out_err: - cleanup_async_copy(async_copy); + if (async_copy) + cleanup_async_copy(async_copy); goto out; } diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index cdc75ad4438b..c35c0ebaf722 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -1578,6 +1578,7 @@ nfsd4_cld_tracking_init(struct net *net) struct nfsd_net *nn = net_generic(net, nfsd_net_id); bool running; int retries = 10; + struct crypto_shash *tfm; status = nfs4_cld_state_init(net); if (status) @@ -1586,11 +1587,6 @@ nfsd4_cld_tracking_init(struct net *net) status = __nfsd4_init_cld_pipe(net); if (status) goto err_shutdown; - nn->cld_net->cn_tfm = crypto_alloc_shash("sha256", 0, 0); - if (IS_ERR(nn->cld_net->cn_tfm)) { - status = PTR_ERR(nn->cld_net->cn_tfm); - goto err_remove; - } /* * rpc pipe upcalls take 30 seconds to time out, so we don't want to @@ -1607,6 +1603,12 @@ nfsd4_cld_tracking_init(struct net *net) status = -ETIMEDOUT; goto err_remove; } + tfm = crypto_alloc_shash("sha256", 0, 0); + if (IS_ERR(tfm)) { + status = PTR_ERR(tfm); + goto err_remove; + } + nn->cld_net->cn_tfm = tfm; status = nfsd4_cld_get_version(nn); if (status == -EOPNOTSUPP) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index c65aeaa812d4..08f6eb2b73f8 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -3548,12 +3548,17 @@ static bool replay_matches_cache(struct svc_rqst *rqstp, (bool)seq->cachethis) return false; /* - * If there's an error than the reply can have fewer ops than - * the call. But if we cached a reply with *more* ops than the - * call you're sending us now, then this new call is clearly not - * really a replay of the old one: + * If there's an error then the reply can have fewer ops than + * the call. */ - if (slot->sl_opcnt < argp->opcnt) + if (slot->sl_opcnt < argp->opcnt && !slot->sl_status) + return false; + /* + * But if we cached a reply with *more* ops than the call you're + * sending us now, then this new call is clearly not really a + * replay of the old one: + */ + if (slot->sl_opcnt > argp->opcnt) return false; /* This is the only check explicitly called by spec: */ if (!same_creds(&rqstp->rq_cred, &slot->sl_cred)) diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index fdf7ed4bd5dd..e8bee8ff30c5 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -95,12 +95,11 @@ static const struct svc_version *nfsd_acl_version[] = { #define NFSD_ACL_MINVERS 2 #define NFSD_ACL_NRVERS ARRAY_SIZE(nfsd_acl_version) -static const struct svc_version *nfsd_acl_versions[NFSD_ACL_NRVERS]; static struct svc_program nfsd_acl_program = { .pg_prog = NFS_ACL_PROGRAM, .pg_nvers = NFSD_ACL_NRVERS, - .pg_vers = nfsd_acl_versions, + .pg_vers = nfsd_acl_version, .pg_name = "nfsacl", .pg_class = "nfsd", .pg_stats = &nfsd_acl_svcstats, diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index bd0a385df3fc..cf423fea0c6f 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -525,7 +525,7 @@ __be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp, #endif __be32 nfsd4_clone_file_range(struct file *src, u64 src_pos, struct file *dst, - u64 dst_pos, u64 count) + u64 dst_pos, u64 count, bool sync) { loff_t cloned; @@ -534,6 +534,12 @@ __be32 nfsd4_clone_file_range(struct file *src, u64 src_pos, struct file *dst, return nfserrno(cloned); if (count && cloned != count) return nfserrno(-EINVAL); + if (sync) { + loff_t dst_end = count ? dst_pos + count - 1 : LLONG_MAX; + int status = vfs_fsync_range(dst, dst_pos, dst_end, 0); + if (status < 0) + return nfserrno(status); + } return 0; } diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index a13fd9d7e1f5..cc110a10bfe8 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -56,7 +56,7 @@ __be32 nfsd4_set_nfs4_label(struct svc_rqst *, struct svc_fh *, __be32 nfsd4_vfs_fallocate(struct svc_rqst *, struct svc_fh *, struct file *, loff_t, loff_t, int); __be32 nfsd4_clone_file_range(struct file *, u64, struct file *, - u64, u64); + u64, u64, bool); #endif /* CONFIG_NFSD_V4 */ __be32 nfsd_create_locked(struct svc_rqst *, struct svc_fh *, char *name, int len, struct iattr *attrs, diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 2ecef6155fc0..f44e39c68328 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -57,6 +57,9 @@ static void fsnotify_unmount_inodes(struct super_block *sb) * doing an __iget/iput with SB_ACTIVE clear would actually * evict all inodes with zero i_count from icache which is * unnecessarily violent and may in fact be illegal to do. + * However, we should have been called /after/ evict_inodes + * removed all zero refcount inodes, in any case. Test to + * be sure. */ if (!atomic_read(&inode->i_count)) { spin_unlock(&inode->i_lock); @@ -77,6 +80,7 @@ static void fsnotify_unmount_inodes(struct super_block *sb) iput_inode = inode; + cond_resched(); spin_lock(&sb->s_inode_list_lock); } spin_unlock(&sb->s_inode_list_lock); diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c index 3e7da392aa6f..bb981ec76456 100644 --- a/fs/ocfs2/acl.c +++ b/fs/ocfs2/acl.c @@ -327,8 +327,8 @@ int ocfs2_acl_chmod(struct inode *inode, struct buffer_head *bh) down_read(&OCFS2_I(inode)->ip_xattr_sem); acl = ocfs2_get_acl_nolock(inode, ACL_TYPE_ACCESS, bh); up_read(&OCFS2_I(inode)->ip_xattr_sem); - if (IS_ERR(acl) || !acl) - return PTR_ERR(acl); + if (IS_ERR_OR_NULL(acl)) + return PTR_ERR_OR_ZERO(acl); ret = __posix_acl_chmod(&acl, GFP_KERNEL, inode->i_mode); if (ret) return ret; diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 6e774c5ea13b..8a2e284ccfcd 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -3282,6 +3282,7 @@ static void ocfs2_dlm_init_debug(struct ocfs2_super *osb) debugfs_create_u32("locking_filter", 0600, osb->osb_debug_root, &dlm_debug->d_filter_secs); + ocfs2_get_dlm_debug(dlm_debug); } static void ocfs2_dlm_shutdown_debug(struct ocfs2_super *osb) diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 699a560efbb0..900e4ef686bf 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -1066,6 +1066,14 @@ int ocfs2_journal_load(struct ocfs2_journal *journal, int local, int replayed) ocfs2_clear_journal_error(osb->sb, journal->j_journal, osb->slot_num); + if (replayed) { + jbd2_journal_lock_updates(journal->j_journal); + status = jbd2_journal_flush(journal->j_journal); + jbd2_journal_unlock_updates(journal->j_journal); + if (status < 0) + mlog_errno(status); + } + status = ocfs2_journal_toggle_dirty(osb, 1, replayed); if (status < 0) { mlog_errno(status); diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c index 7a922190a8c7..eda83487c9ec 100644 --- a/fs/ocfs2/quota_global.c +++ b/fs/ocfs2/quota_global.c @@ -728,7 +728,7 @@ static int ocfs2_release_dquot(struct dquot *dquot) mutex_lock(&dquot->dq_lock); /* Check whether we are not racing with some other dqget() */ - if (atomic_read(&dquot->dq_count) > 1) + if (dquot_is_busy(dquot)) goto out; /* Running from downconvert thread? Postpone quota processing to wq */ if (current == osb->dc_task) { diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 702aa63f6774..29abdb1d3b5c 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -1170,7 +1170,7 @@ static int ovl_rename(struct inode *olddir, struct dentry *old, if (newdentry == trap) goto out_dput; - if (WARN_ON(olddentry->d_inode == newdentry->d_inode)) + if (olddentry->d_inode == newdentry->d_inode) goto out_dput; err = 0; diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index bc14781886bf..b045cf1826fc 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -200,8 +200,14 @@ int ovl_getattr(const struct path *path, struct kstat *stat, if (ovl_test_flag(OVL_INDEX, d_inode(dentry)) || (!ovl_verify_lower(dentry->d_sb) && (is_dir || lowerstat.nlink == 1))) { - stat->ino = lowerstat.ino; lower_layer = ovl_layer_lower(dentry); + /* + * Cannot use origin st_dev;st_ino because + * origin inode content may differ from overlay + * inode content. + */ + if (samefs || lower_layer->fsid) + stat->ino = lowerstat.ino; } /* diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index e9717c2f7d45..f47c591402d7 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -325,6 +325,14 @@ int ovl_check_origin_fh(struct ovl_fs *ofs, struct ovl_fh *fh, bool connected, int i; for (i = 0; i < ofs->numlower; i++) { + /* + * If lower fs uuid is not unique among lower fs we cannot match + * fh->uuid to layer. + */ + if (ofs->lower_layers[i].fsid && + ofs->lower_layers[i].fs->bad_uuid) + continue; + origin = ovl_decode_real_fh(fh, ofs->lower_layers[i].mnt, connected); if (origin) diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h index a8279280e88d..28348c44ea5b 100644 --- a/fs/overlayfs/ovl_entry.h +++ b/fs/overlayfs/ovl_entry.h @@ -22,6 +22,8 @@ struct ovl_config { struct ovl_sb { struct super_block *sb; dev_t pseudo_dev; + /* Unusable (conflicting) uuid */ + bool bad_uuid; }; struct ovl_layer { diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index afbcb116a7f1..7621ff176d15 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1255,7 +1255,7 @@ static bool ovl_lower_uuid_ok(struct ovl_fs *ofs, const uuid_t *uuid) { unsigned int i; - if (!ofs->config.nfs_export && !(ofs->config.index && ofs->upper_mnt)) + if (!ofs->config.nfs_export && !ofs->upper_mnt) return true; for (i = 0; i < ofs->numlowerfs; i++) { @@ -1263,9 +1263,13 @@ static bool ovl_lower_uuid_ok(struct ovl_fs *ofs, const uuid_t *uuid) * We use uuid to associate an overlay lower file handle with a * lower layer, so we can accept lower fs with null uuid as long * as all lower layers with null uuid are on the same fs. + * if we detect multiple lower fs with the same uuid, we + * disable lower file handle decoding on all of them. */ - if (uuid_equal(&ofs->lower_fs[i].sb->s_uuid, uuid)) + if (uuid_equal(&ofs->lower_fs[i].sb->s_uuid, uuid)) { + ofs->lower_fs[i].bad_uuid = true; return false; + } } return true; } @@ -1277,6 +1281,7 @@ static int ovl_get_fsid(struct ovl_fs *ofs, const struct path *path) unsigned int i; dev_t dev; int err; + bool bad_uuid = false; /* fsid 0 is reserved for upper fs even with non upper overlay */ if (ofs->upper_mnt && ofs->upper_mnt->mnt_sb == sb) @@ -1288,11 +1293,15 @@ static int ovl_get_fsid(struct ovl_fs *ofs, const struct path *path) } if (!ovl_lower_uuid_ok(ofs, &sb->s_uuid)) { - ofs->config.index = false; - ofs->config.nfs_export = false; - pr_warn("overlayfs: %s uuid detected in lower fs '%pd2', falling back to index=off,nfs_export=off.\n", - uuid_is_null(&sb->s_uuid) ? "null" : "conflicting", - path->dentry); + bad_uuid = true; + if (ofs->config.index || ofs->config.nfs_export) { + ofs->config.index = false; + ofs->config.nfs_export = false; + pr_warn("overlayfs: %s uuid detected in lower fs '%pd2', falling back to index=off,nfs_export=off.\n", + uuid_is_null(&sb->s_uuid) ? "null" : + "conflicting", + path->dentry); + } } err = get_anon_bdev(&dev); @@ -1303,6 +1312,7 @@ static int ovl_get_fsid(struct ovl_fs *ofs, const struct path *path) ofs->lower_fs[ofs->numlowerfs].sb = sb; ofs->lower_fs[ofs->numlowerfs].pseudo_dev = dev; + ofs->lower_fs[ofs->numlowerfs].bad_uuid = bad_uuid; ofs->numlowerfs++; return ofs->numlowerfs; diff --git a/fs/proc/base.c b/fs/proc/base.c index ebea9501afb8..8c55eda3e4fe 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -94,6 +94,8 @@ #include #include #include +#include +#include #include #include "internal.h" #include "fd.h" @@ -477,7 +479,7 @@ static int proc_pid_schedstat(struct seq_file *m, struct pid_namespace *ns, seq_puts(m, "0 0 0\n"); else seq_printf(m, "%llu %llu %lu\n", - (unsigned long long)task->se.sum_exec_runtime, + (unsigned long long)tsk_seruntime(task), (unsigned long long)task->sched_info.run_delay, task->sched_info.pcount); @@ -2990,6 +2992,149 @@ static int proc_stack_depth(struct seq_file *m, struct pid_namespace *ns, } #endif /* CONFIG_STACKLEAK_METRICS */ +#ifdef CONFIG_KSM +static int ksm_open(struct inode *inode, struct file *file) +{ + struct task_struct *task; + struct mm_struct *mm; + int err; + + task = get_proc_task(inode); + if (!task) { + err = -ESRCH; + goto out; + } + if (task->flags & PF_KTHREAD) { + put_task_struct(task); + err = -EINVAL; + goto out; + } + + mm = mm_access(task, PTRACE_MODE_ATTACH_FSCREDS); + put_task_struct(task); + if (!mm) { + err = -EINVAL; + goto out; + } + if (IS_ERR(mm)) { + err = PTR_ERR(mm); + goto out; + } + + /* ensure this mm_struct can't be freed */ + mmgrab(mm); + /* but do not pin its memory */ + mmput(mm); + + err = 0; + file->private_data = mm; + +out: + return err; +} + +static ssize_t ksm_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + char kbuf[PROC_NUMBUF]; + char *pos; + int behaviour; + struct mm_struct *mm = file->private_data; + int err; + int last_err; + struct vm_area_struct *vma; + + if (!mm) { + err = -EINVAL; + goto out; + } + + /* Only allow a very narrow range of strings to be written */ + if ((*ppos != 0) || (count >= sizeof(kbuf))) { + err = -EINVAL; + goto out; + } + + /* What was written? */ + if (copy_from_user(kbuf, buf, count)) { + err = -EFAULT; + goto out; + } + kbuf[count] = '\0'; + pos = kbuf; + + /* What is being requested? */ + if (strncmp(pos, "merge", 5) == 0) { + pos += 5; + behaviour = MADV_MERGEABLE; + } + else if (strncmp(pos, "unmerge", 7) == 0) { + pos += 7; + behaviour = MADV_UNMERGEABLE; + } + else { + err = -EINVAL; + goto out; + } + + /* Verify there is not trailing junk on the line */ + pos = skip_spaces(pos); + if (*pos != '\0') { + err = -EINVAL; + goto out; + } + + if (!mmget_not_zero(mm)) { + err = -EINVAL; + goto out; + } + + down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) { + err = -EINVAL; + goto skip_mm; + } + + err = 0; + + vma = mm->mmap; + while (vma) { + if (behaviour == MADV_MERGEABLE) + last_err = ksm_madvise_merge(vma->vm_mm, vma, &vma->vm_flags); + else + last_err = ksm_madvise_unmerge(vma, vma->vm_start, vma->vm_end, &vma->vm_flags); + if (last_err) + err = last_err; + vma = vma->vm_next; + } + +skip_mm: + up_write(&mm->mmap_sem); + + mmput(mm); + +out: + return err ? err : count; +} + +static int ksm_release(struct inode *inode, struct file *file) +{ + struct mm_struct *mm = file->private_data; + + if (mm) + mmdrop(mm); + + return 0; +} + +static const struct file_operations proc_ksm_operations = { + .open = ksm_open, + .write = ksm_write, + .llseek = noop_llseek, + .release = ksm_release, +}; +#endif /* CONFIG_KSM */ + /* * Thread groups */ @@ -3097,6 +3242,9 @@ static const struct pid_entry tgid_base_stuff[] = { #ifdef CONFIG_PROC_PID_ARCH_STATUS ONE("arch_status", S_IRUGO, proc_pid_arch_status), #endif +#ifdef CONFIG_KSM + REG("ksm", S_IRUGO|S_IWUSR, proc_ksm_operations), +#endif }; static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx) diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 8caff834f002..013486b5125e 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -407,6 +407,17 @@ static int notrace ramoops_pstore_write(struct pstore_record *record) prz = cxt->dprzs[cxt->dump_write_cnt]; + /* + * Since this is a new crash dump, we need to reset the buffer in + * case it still has an old dump present. Without this, the new dump + * will get appended, which would seriously confuse anything trying + * to check dump file contents. Specifically, ramoops_read_kmsg_hdr() + * expects to find a dump header in the beginning of buffer data, so + * we must to reset the buffer values, in order to ensure that the + * header will be written to the beginning of the buffer. + */ + persistent_ram_zap(prz); + /* Build header and append record contents. */ hlen = ramoops_write_kmsg_hdr(prz, record); if (!hlen) @@ -572,6 +583,7 @@ static int ramoops_init_przs(const char *name, prz_ar[i] = persistent_ram_new(*paddr, zone_sz, sig, &cxt->ecc_info, cxt->memtype, flags, label); + kfree(label); if (IS_ERR(prz_ar[i])) { err = PTR_ERR(prz_ar[i]); dev_err(dev, "failed to request %s mem region (0x%zx@0x%llx): %d\n", @@ -617,6 +629,7 @@ static int ramoops_init_prz(const char *name, label = kasprintf(GFP_KERNEL, "ramoops:%s", name); *prz = persistent_ram_new(*paddr, sz, sig, &cxt->ecc_info, cxt->memtype, PRZ_FLAG_ZAP_OLD, label); + kfree(label); if (IS_ERR(*prz)) { int err = PTR_ERR(*prz); diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c index 8823f65888f0..1f4d8c06f9be 100644 --- a/fs/pstore/ram_core.c +++ b/fs/pstore/ram_core.c @@ -574,7 +574,7 @@ struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size, /* Initialize general buffer state. */ raw_spin_lock_init(&prz->buffer_lock); prz->flags = flags; - prz->label = label; + prz->label = kstrdup(label, GFP_KERNEL); ret = persistent_ram_buffer_map(start, size, prz, memtype); if (ret) diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 6e826b454082..7abc3230c21a 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -497,7 +497,7 @@ int dquot_release(struct dquot *dquot) mutex_lock(&dquot->dq_lock); /* Check whether we are not racing with some other dqget() */ - if (atomic_read(&dquot->dq_count) > 1) + if (dquot_is_busy(dquot)) goto out_dqlock; if (dqopt->ops[dquot->dq_id.type]->release_dqblk) { ret = dqopt->ops[dquot->dq_id.type]->release_dqblk(dquot); @@ -623,7 +623,7 @@ EXPORT_SYMBOL(dquot_scan_active); /* Write all dquot structures to quota files */ int dquot_writeback_dquots(struct super_block *sb, int type) { - struct list_head *dirty; + struct list_head dirty; struct dquot *dquot; struct quota_info *dqopt = sb_dqopt(sb); int cnt; @@ -637,9 +637,10 @@ int dquot_writeback_dquots(struct super_block *sb, int type) if (!sb_has_quota_active(sb, cnt)) continue; spin_lock(&dq_list_lock); - dirty = &dqopt->info[cnt].dqi_dirty_list; - while (!list_empty(dirty)) { - dquot = list_first_entry(dirty, struct dquot, + /* Move list away to avoid livelock. */ + list_replace_init(&dqopt->info[cnt].dqi_dirty_list, &dirty); + while (!list_empty(&dirty)) { + dquot = list_first_entry(&dirty, struct dquot, dq_dirty); WARN_ON(!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)); @@ -985,6 +986,7 @@ static int add_dquot_ref(struct super_block *sb, int type) * later. */ old_inode = inode; + cond_resched(); spin_lock(&sb->s_inode_list_lock); } spin_unlock(&sb->s_inode_list_lock); @@ -2860,68 +2862,73 @@ EXPORT_SYMBOL(dquot_quotactl_sysfile_ops); static int do_proc_dqstats(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - unsigned int type = (int *)table->data - dqstats.stat; + unsigned int type = (unsigned long *)table->data - dqstats.stat; + s64 value = percpu_counter_sum(&dqstats.counter[type]); + + /* Filter negative values for non-monotonic counters */ + if (value < 0 && (type == DQST_ALLOC_DQUOTS || + type == DQST_FREE_DQUOTS)) + value = 0; /* Update global table */ - dqstats.stat[type] = - percpu_counter_sum_positive(&dqstats.counter[type]); - return proc_dointvec(table, write, buffer, lenp, ppos); + dqstats.stat[type] = value; + return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } static struct ctl_table fs_dqstats_table[] = { { .procname = "lookups", .data = &dqstats.stat[DQST_LOOKUPS], - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "drops", .data = &dqstats.stat[DQST_DROPS], - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "reads", .data = &dqstats.stat[DQST_READS], - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "writes", .data = &dqstats.stat[DQST_WRITES], - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "cache_hits", .data = &dqstats.stat[DQST_CACHE_HITS], - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "allocated_dquots", .data = &dqstats.stat[DQST_ALLOC_DQUOTS], - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "free_dquots", .data = &dqstats.stat[DQST_FREE_DQUOTS], - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "syncs", .data = &dqstats.stat[DQST_SYNCS], - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 132ec4406ed0..6419e6dacc39 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -2097,6 +2097,15 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th, goto out_inserted_sd; } + /* + * Mark it private if we're creating the privroot + * or something under it. + */ + if (IS_PRIVATE(dir) || dentry == REISERFS_SB(sb)->priv_root) { + inode->i_flags |= S_PRIVATE; + inode->i_opflags &= ~IOP_XATTR; + } + if (reiserfs_posixacl(inode->i_sb)) { reiserfs_write_unlock(inode->i_sb); retval = reiserfs_inherit_default_acl(th, dir, dentry, inode); @@ -2111,8 +2120,7 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th, reiserfs_warning(inode->i_sb, "jdm-13090", "ACLs aren't enabled in the fs, " "but vfs thinks they are!"); - } else if (IS_PRIVATE(dir)) - inode->i_flags |= S_PRIVATE; + } if (security->name) { reiserfs_write_unlock(inode->i_sb); diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c index 97f3fc4fdd79..959a066b7bb0 100644 --- a/fs/reiserfs/namei.c +++ b/fs/reiserfs/namei.c @@ -377,10 +377,13 @@ static struct dentry *reiserfs_lookup(struct inode *dir, struct dentry *dentry, /* * Propagate the private flag so we know we're - * in the priv tree + * in the priv tree. Also clear IOP_XATTR + * since we don't have xattrs on xattr files. */ - if (IS_PRIVATE(dir)) + if (IS_PRIVATE(dir)) { inode->i_flags |= S_PRIVATE; + inode->i_opflags &= ~IOP_XATTR; + } } reiserfs_write_unlock(dir->i_sb); if (retval == IO_ERROR) { diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h index e5ca9ed79e54..726580114d55 100644 --- a/fs/reiserfs/reiserfs.h +++ b/fs/reiserfs/reiserfs.h @@ -1168,6 +1168,8 @@ static inline int bmap_would_wrap(unsigned bmap_nr) return bmap_nr > ((1LL << 16) - 1); } +extern const struct xattr_handler *reiserfs_xattr_handlers[]; + /* * this says about version of key of all items (but stat data) the * object consists of diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index d69b4ac0ae2f..3244037b1286 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -2049,6 +2049,8 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent) if (replay_only(s)) goto error_unlocked; + s->s_xattr = reiserfs_xattr_handlers; + if (bdev_read_only(s->s_bdev) && !sb_rdonly(s)) { SWARN(silent, s, "clm-7000", "Detected readonly device, marking FS readonly"); diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index b5b26d8a192c..62b40df36c98 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -122,13 +122,13 @@ static struct dentry *open_xa_root(struct super_block *sb, int flags) struct dentry *xaroot; if (d_really_is_negative(privroot)) - return ERR_PTR(-ENODATA); + return ERR_PTR(-EOPNOTSUPP); inode_lock_nested(d_inode(privroot), I_MUTEX_XATTR); xaroot = dget(REISERFS_SB(sb)->xattr_root); if (!xaroot) - xaroot = ERR_PTR(-ENODATA); + xaroot = ERR_PTR(-EOPNOTSUPP); else if (d_really_is_negative(xaroot)) { int err = -ENODATA; @@ -619,6 +619,10 @@ int reiserfs_xattr_set(struct inode *inode, const char *name, int error, error2; size_t jbegin_count = reiserfs_xattr_nblocks(inode, buffer_size); + /* Check before we start a transaction and then do nothing. */ + if (!d_really_is_positive(REISERFS_SB(inode->i_sb)->priv_root)) + return -EOPNOTSUPP; + if (!(flags & XATTR_REPLACE)) jbegin_count += reiserfs_xattr_jcreate_nblocks(inode); @@ -841,8 +845,7 @@ ssize_t reiserfs_listxattr(struct dentry * dentry, char *buffer, size_t size) if (d_really_is_negative(dentry)) return -EINVAL; - if (!dentry->d_sb->s_xattr || - get_inode_sd_version(d_inode(dentry)) == STAT_DATA_V1) + if (get_inode_sd_version(d_inode(dentry)) == STAT_DATA_V1) return -EOPNOTSUPP; dir = open_xa_dir(d_inode(dentry), XATTR_REPLACE); @@ -882,6 +885,7 @@ static int create_privroot(struct dentry *dentry) } d_inode(dentry)->i_flags |= S_PRIVATE; + d_inode(dentry)->i_opflags &= ~IOP_XATTR; reiserfs_info(dentry->d_sb, "Created %s - reserved for xattr " "storage.\n", PRIVROOT_NAME); @@ -895,7 +899,7 @@ static int create_privroot(struct dentry *dentry) { return 0; } #endif /* Actual operations that are exported to VFS-land */ -static const struct xattr_handler *reiserfs_xattr_handlers[] = { +const struct xattr_handler *reiserfs_xattr_handlers[] = { #ifdef CONFIG_REISERFS_FS_XATTR &reiserfs_xattr_user_handler, &reiserfs_xattr_trusted_handler, @@ -966,8 +970,10 @@ int reiserfs_lookup_privroot(struct super_block *s) if (!IS_ERR(dentry)) { REISERFS_SB(s)->priv_root = dentry; d_set_d_op(dentry, &xattr_lookup_poison_ops); - if (d_really_is_positive(dentry)) + if (d_really_is_positive(dentry)) { d_inode(dentry)->i_flags |= S_PRIVATE; + d_inode(dentry)->i_opflags &= ~IOP_XATTR; + } } else err = PTR_ERR(dentry); inode_unlock(d_inode(s->s_root)); @@ -996,7 +1002,6 @@ int reiserfs_xattr_init(struct super_block *s, int mount_flags) } if (d_really_is_positive(privroot)) { - s->s_xattr = reiserfs_xattr_handlers; inode_lock(d_inode(privroot)); if (!REISERFS_SB(s)->xattr_root) { struct dentry *dentry; diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c index aa9380bac196..05f666794561 100644 --- a/fs/reiserfs/xattr_acl.c +++ b/fs/reiserfs/xattr_acl.c @@ -320,10 +320,8 @@ reiserfs_inherit_default_acl(struct reiserfs_transaction_handle *th, * would be useless since permissions are ignored, and a pain because * it introduces locking cycles */ - if (IS_PRIVATE(dir)) { - inode->i_flags |= S_PRIVATE; + if (IS_PRIVATE(inode)) goto apply_umask; - } err = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl); if (err) diff --git a/fs/splice.c b/fs/splice.c index 98412721f056..e509239d7e06 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -945,12 +945,13 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd, WARN_ON_ONCE(pipe->nrbufs != 0); while (len) { + unsigned int pipe_pages; size_t read_len; loff_t pos = sd->pos, prev_pos = pos; /* Don't try to read more the pipe has space for. */ - read_len = min_t(size_t, len, - (pipe->buffers - pipe->nrbufs) << PAGE_SHIFT); + pipe_pages = pipe->buffers - pipe->nrbufs; + read_len = min(len, (size_t)pipe_pages << PAGE_SHIFT); ret = do_splice_to(in, &pos, pipe, read_len, flags); if (unlikely(ret <= 0)) goto out_release; @@ -1180,8 +1181,15 @@ static long do_splice(struct file *in, loff_t __user *off_in, pipe_lock(opipe); ret = wait_for_space(opipe, flags); - if (!ret) + if (!ret) { + unsigned int pipe_pages; + + /* Don't try to read more the pipe has space for. */ + pipe_pages = opipe->buffers - opipe->nrbufs; + len = min(len, (size_t)pipe_pages << PAGE_SHIFT); + ret = do_splice_to(in, &offset, opipe, len, flags); + } pipe_unlock(opipe); if (ret > 0) wakeup_pipe_readers(opipe); diff --git a/fs/super.c b/fs/super.c index cfadab2cbf35..cd352530eca9 100644 --- a/fs/super.c +++ b/fs/super.c @@ -448,10 +448,12 @@ void generic_shutdown_super(struct super_block *sb) sync_filesystem(sb); sb->s_flags &= ~SB_ACTIVE; - fsnotify_sb_delete(sb); cgroup_writeback_umount(); + /* evict all inodes with zero refcount */ evict_inodes(sb); + /* only nonzero refcount inodes can have marks */ + fsnotify_sb_delete(sb); if (sb->s_dio_done_wq) { destroy_workqueue(sb->s_dio_done_wq); diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c index 4fd9683b8245..826dad0243dc 100644 --- a/fs/ubifs/journal.c +++ b/fs/ubifs/journal.c @@ -899,7 +899,7 @@ int ubifs_jnl_write_inode(struct ubifs_info *c, const struct inode *inode) fname_name(&nm) = xent->name; fname_len(&nm) = le16_to_cpu(xent->nlen); - xino = ubifs_iget(c->vfs_sb, xent->inum); + xino = ubifs_iget(c->vfs_sb, le64_to_cpu(xent->inum)); if (IS_ERR(xino)) { err = PTR_ERR(xino); ubifs_err(c, "dead directory entry '%s', error %d", diff --git a/fs/ubifs/orphan.c b/fs/ubifs/orphan.c index 3b4b4114f208..54d6db61106f 100644 --- a/fs/ubifs/orphan.c +++ b/fs/ubifs/orphan.c @@ -631,12 +631,17 @@ static int do_kill_orphans(struct ubifs_info *c, struct ubifs_scan_leb *sleb, ino_t inum; int i, n, err, first = 1; + ino = kmalloc(UBIFS_MAX_INO_NODE_SZ, GFP_NOFS); + if (!ino) + return -ENOMEM; + list_for_each_entry(snod, &sleb->nodes, list) { if (snod->type != UBIFS_ORPH_NODE) { ubifs_err(c, "invalid node type %d in orphan area at %d:%d", snod->type, sleb->lnum, snod->offs); ubifs_dump_node(c, snod->node); - return -EINVAL; + err = -EINVAL; + goto out_free; } orph = snod->node; @@ -663,20 +668,18 @@ static int do_kill_orphans(struct ubifs_info *c, struct ubifs_scan_leb *sleb, ubifs_err(c, "out of order commit number %llu in orphan node at %d:%d", cmt_no, sleb->lnum, snod->offs); ubifs_dump_node(c, snod->node); - return -EINVAL; + err = -EINVAL; + goto out_free; } dbg_rcvry("out of date LEB %d", sleb->lnum); *outofdate = 1; - return 0; + err = 0; + goto out_free; } if (first) first = 0; - ino = kmalloc(UBIFS_MAX_INO_NODE_SZ, GFP_NOFS); - if (!ino) - return -ENOMEM; - n = (le32_to_cpu(orph->ch.len) - UBIFS_ORPH_NODE_SZ) >> 3; for (i = 0; i < n; i++) { union ubifs_key key1, key2; diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 7d4547e5202d..5e1e8ec0589e 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -2267,10 +2267,8 @@ static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags, } } else { err = ubifs_fill_super(sb, data, flags & SB_SILENT ? 1 : 0); - if (err) { - kfree(c); + if (err) goto out_deact; - } /* We do not support atime */ sb->s_flags |= SB_ACTIVE; if (IS_ENABLED(CONFIG_UBIFS_ATIME_SUPPORT)) diff --git a/fs/ubifs/tnc_commit.c b/fs/ubifs/tnc_commit.c index a384a0f9ff32..234be1c4dc87 100644 --- a/fs/ubifs/tnc_commit.c +++ b/fs/ubifs/tnc_commit.c @@ -212,7 +212,7 @@ static int is_idx_node_in_use(struct ubifs_info *c, union ubifs_key *key, /** * layout_leb_in_gaps - layout index nodes using in-the-gaps method. * @c: UBIFS file-system description object - * @p: return LEB number here + * @p: return LEB number in @c->gap_lebs[p] * * This function lays out new index nodes for dirty znodes using in-the-gaps * method of TNC commit. @@ -221,7 +221,7 @@ static int is_idx_node_in_use(struct ubifs_info *c, union ubifs_key *key, * This function returns the number of index nodes written into the gaps, or a * negative error code on failure. */ -static int layout_leb_in_gaps(struct ubifs_info *c, int *p) +static int layout_leb_in_gaps(struct ubifs_info *c, int p) { struct ubifs_scan_leb *sleb; struct ubifs_scan_node *snod; @@ -236,7 +236,7 @@ static int layout_leb_in_gaps(struct ubifs_info *c, int *p) * filled, however we do not check there at present. */ return lnum; /* Error code */ - *p = lnum; + c->gap_lebs[p] = lnum; dbg_gc("LEB %d", lnum); /* * Scan the index LEB. We use the generic scan for this even though @@ -355,7 +355,7 @@ static int get_leb_cnt(struct ubifs_info *c, int cnt) */ static int layout_in_gaps(struct ubifs_info *c, int cnt) { - int err, leb_needed_cnt, written, *p; + int err, leb_needed_cnt, written, p = 0, old_idx_lebs, *gap_lebs; dbg_gc("%d znodes to write", cnt); @@ -364,9 +364,9 @@ static int layout_in_gaps(struct ubifs_info *c, int cnt) if (!c->gap_lebs) return -ENOMEM; - p = c->gap_lebs; + old_idx_lebs = c->lst.idx_lebs; do { - ubifs_assert(c, p < c->gap_lebs + c->lst.idx_lebs); + ubifs_assert(c, p < c->lst.idx_lebs); written = layout_leb_in_gaps(c, p); if (written < 0) { err = written; @@ -392,9 +392,29 @@ static int layout_in_gaps(struct ubifs_info *c, int cnt) leb_needed_cnt = get_leb_cnt(c, cnt); dbg_gc("%d znodes remaining, need %d LEBs, have %d", cnt, leb_needed_cnt, c->ileb_cnt); + /* + * Dynamically change the size of @c->gap_lebs to prevent + * oob, because @c->lst.idx_lebs could be increased by + * function @get_idx_gc_leb (called by layout_leb_in_gaps-> + * ubifs_find_dirty_idx_leb) during loop. Only enlarge + * @c->gap_lebs when needed. + * + */ + if (leb_needed_cnt > c->ileb_cnt && p >= old_idx_lebs && + old_idx_lebs < c->lst.idx_lebs) { + old_idx_lebs = c->lst.idx_lebs; + gap_lebs = krealloc(c->gap_lebs, sizeof(int) * + (old_idx_lebs + 1), GFP_NOFS); + if (!gap_lebs) { + kfree(c->gap_lebs); + c->gap_lebs = NULL; + return -ENOMEM; + } + c->gap_lebs = gap_lebs; + } } while (leb_needed_cnt > c->ileb_cnt); - *p = -1; + c->gap_lebs[p] = -1; return 0; } diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index f9fd18670e22..d99d166fd892 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1834,13 +1834,12 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx, if (copy_from_user(&uffdio_api, buf, sizeof(uffdio_api))) goto out; features = uffdio_api.features; - if (uffdio_api.api != UFFD_API || (features & ~UFFD_API_FEATURES)) { - memset(&uffdio_api, 0, sizeof(uffdio_api)); - if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api))) - goto out; - ret = -EINVAL; - goto out; - } + ret = -EINVAL; + if (uffdio_api.api != UFFD_API || (features & ~UFFD_API_FEATURES)) + goto err_out; + ret = -EPERM; + if ((features & UFFD_FEATURE_EVENT_FORK) && !capable(CAP_SYS_PTRACE)) + goto err_out; /* report all available features and ioctls to userland */ uffdio_api.features = UFFD_API_FEATURES; uffdio_api.ioctls = UFFD_API_IOCTLS; @@ -1853,6 +1852,11 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx, ret = 0; out: return ret; +err_out: + memset(&uffdio_api, 0, sizeof(uffdio_api)); + if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api))) + ret = -EFAULT; + goto out; } static long userfaultfd_ioctl(struct file *file, unsigned cmd, diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 02469d59c787..3f76da11197c 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -5300,7 +5300,7 @@ __xfs_bunmapi( * Make sure we don't touch multiple AGF headers out of order * in a single transaction, as that could cause AB-BA deadlocks. */ - if (!wasdel) { + if (!wasdel && !isrt) { agno = XFS_FSB_TO_AGNO(mp, del.br_startblock); if (prev_agno != NULLAGNUMBER && prev_agno > agno) break; diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h index 003a772cd26c..2e50d146105d 100644 --- a/fs/xfs/scrub/common.h +++ b/fs/xfs/scrub/common.h @@ -14,8 +14,15 @@ static inline bool xchk_should_terminate( struct xfs_scrub *sc, - int *error) + int *error) { + /* + * If preemption is disabled, we need to yield to the scheduler every + * few seconds so that we don't run afoul of the soft lockup watchdog + * or RCU stall detector. + */ + cond_resched(); + if (fatal_signal_pending(current)) { if (*error == 0) *error = -EAGAIN; diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 641d07f30a27..7b0d9ad8cb1a 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -1495,6 +1495,8 @@ xlog_alloc_log( prev_iclog = iclog->ic_next; kmem_free(iclog->ic_data); kmem_free(iclog); + if (prev_iclog == log->l_iclog) + break; } out_free_log: kmem_free(log); diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 175f7b40c585..3f6fddeb7519 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -78,9 +78,6 @@ acpi_evaluate_dsm_typed(acpi_handle handle, const guid_t *guid, u64 rev, bool acpi_dev_found(const char *hid); bool acpi_dev_present(const char *hid, const char *uid, s64 hrv); -struct acpi_device * -acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv); - #ifdef CONFIG_ACPI #include @@ -683,6 +680,9 @@ static inline bool acpi_device_can_poweroff(struct acpi_device *adev) adev->power.states[ACPI_STATE_D3_HOT].flags.explicit_set); } +struct acpi_device * +acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv); + static inline void acpi_dev_put(struct acpi_device *adev) { put_device(&adev->dev); diff --git a/include/asm-generic/cacheflush.h b/include/asm-generic/cacheflush.h index a950a22c4890..cac7404b2bdd 100644 --- a/include/asm-generic/cacheflush.h +++ b/include/asm-generic/cacheflush.h @@ -11,71 +11,102 @@ * The cache doesn't need to be flushed when TLB entries change when * the cache is mapped to physical memory, not virtual memory */ +#ifndef flush_cache_all static inline void flush_cache_all(void) { } +#endif +#ifndef flush_cache_mm static inline void flush_cache_mm(struct mm_struct *mm) { } +#endif +#ifndef flush_cache_dup_mm static inline void flush_cache_dup_mm(struct mm_struct *mm) { } +#endif +#ifndef flush_cache_range static inline void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { } +#endif +#ifndef flush_cache_page static inline void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn) { } +#endif +#ifndef flush_dcache_page static inline void flush_dcache_page(struct page *page) { } +#endif +#ifndef flush_dcache_mmap_lock static inline void flush_dcache_mmap_lock(struct address_space *mapping) { } +#endif +#ifndef flush_dcache_mmap_unlock static inline void flush_dcache_mmap_unlock(struct address_space *mapping) { } +#endif +#ifndef flush_icache_range static inline void flush_icache_range(unsigned long start, unsigned long end) { } +#endif +#ifndef flush_icache_page static inline void flush_icache_page(struct vm_area_struct *vma, struct page *page) { } +#endif +#ifndef flush_icache_user_range static inline void flush_icache_user_range(struct vm_area_struct *vma, struct page *page, unsigned long addr, int len) { } +#endif +#ifndef flush_cache_vmap static inline void flush_cache_vmap(unsigned long start, unsigned long end) { } +#endif +#ifndef flush_cache_vunmap static inline void flush_cache_vunmap(unsigned long start, unsigned long end) { } +#endif -#define copy_to_user_page(vma, page, vaddr, dst, src, len) \ +#ifndef copy_to_user_page +#define copy_to_user_page(vma, page, vaddr, dst, src, len) \ do { \ memcpy(dst, src, len); \ flush_icache_user_range(vma, page, vaddr, len); \ } while (0) +#endif + +#ifndef copy_from_user_page #define copy_from_user_page(vma, page, vaddr, dst, src, len) \ memcpy(dst, src, len) +#endif #endif /* __ASM_CACHEFLUSH_H */ diff --git a/include/asm-generic/resource.h b/include/asm-generic/resource.h index 8874f681b056..59eb72bf7d5f 100644 --- a/include/asm-generic/resource.h +++ b/include/asm-generic/resource.h @@ -23,7 +23,7 @@ [RLIMIT_LOCKS] = { RLIM_INFINITY, RLIM_INFINITY }, \ [RLIMIT_SIGPENDING] = { 0, 0 }, \ [RLIMIT_MSGQUEUE] = { MQ_BYTES_MAX, MQ_BYTES_MAX }, \ - [RLIMIT_NICE] = { 0, 0 }, \ + [RLIMIT_NICE] = { 30, 30 }, \ [RLIMIT_RTPRIO] = { 0, 0 }, \ [RLIMIT_RTTIME] = { RLIM_INFINITY, RLIM_INFINITY }, \ } diff --git a/include/crypto/internal/skcipher.h b/include/crypto/internal/skcipher.h index 734b6f7081b8..3175dfeaed2c 100644 --- a/include/crypto/internal/skcipher.h +++ b/include/crypto/internal/skcipher.h @@ -205,19 +205,6 @@ static inline unsigned int crypto_skcipher_alg_max_keysize( return alg->max_keysize; } -static inline unsigned int crypto_skcipher_alg_chunksize( - struct skcipher_alg *alg) -{ - if ((alg->base.cra_flags & CRYPTO_ALG_TYPE_MASK) == - CRYPTO_ALG_TYPE_BLKCIPHER) - return alg->base.cra_blocksize; - - if (alg->base.cra_ablkcipher.encrypt) - return alg->base.cra_blocksize; - - return alg->chunksize; -} - static inline unsigned int crypto_skcipher_alg_walksize( struct skcipher_alg *alg) { @@ -231,23 +218,6 @@ static inline unsigned int crypto_skcipher_alg_walksize( return alg->walksize; } -/** - * crypto_skcipher_chunksize() - obtain chunk size - * @tfm: cipher handle - * - * The block size is set to one for ciphers such as CTR. However, - * you still need to provide incremental updates in multiples of - * the underlying block size as the IV does not have sub-block - * granularity. This is known in this API as the chunk size. - * - * Return: chunk size in bytes - */ -static inline unsigned int crypto_skcipher_chunksize( - struct crypto_skcipher *tfm) -{ - return crypto_skcipher_alg_chunksize(crypto_skcipher_alg(tfm)); -} - /** * crypto_skcipher_walksize() - obtain walk size * @tfm: cipher handle diff --git a/include/crypto/skcipher.h b/include/crypto/skcipher.h index 37c164234d97..aada87916918 100644 --- a/include/crypto/skcipher.h +++ b/include/crypto/skcipher.h @@ -304,6 +304,36 @@ static inline unsigned int crypto_skcipher_blocksize( return crypto_tfm_alg_blocksize(crypto_skcipher_tfm(tfm)); } +static inline unsigned int crypto_skcipher_alg_chunksize( + struct skcipher_alg *alg) +{ + if ((alg->base.cra_flags & CRYPTO_ALG_TYPE_MASK) == + CRYPTO_ALG_TYPE_BLKCIPHER) + return alg->base.cra_blocksize; + + if (alg->base.cra_ablkcipher.encrypt) + return alg->base.cra_blocksize; + + return alg->chunksize; +} + +/** + * crypto_skcipher_chunksize() - obtain chunk size + * @tfm: cipher handle + * + * The block size is set to one for ciphers such as CTR. However, + * you still need to provide incremental updates in multiples of + * the underlying block size as the IV does not have sub-block + * granularity. This is known in this API as the chunk size. + * + * Return: chunk size in bytes + */ +static inline unsigned int crypto_skcipher_chunksize( + struct crypto_skcipher *tfm) +{ + return crypto_skcipher_alg_chunksize(crypto_skcipher_alg(tfm)); +} + static inline unsigned int crypto_sync_skcipher_blocksize( struct crypto_sync_skcipher *tfm) { diff --git a/include/drm/drm_dp_mst_helper.h b/include/drm/drm_dp_mst_helper.h index 2ba6253ea6d3..fc349204a71b 100644 --- a/include/drm/drm_dp_mst_helper.h +++ b/include/drm/drm_dp_mst_helper.h @@ -334,7 +334,7 @@ struct drm_dp_resource_status_notify { struct drm_dp_query_payload_ack_reply { u8 port_number; - u8 allocated_pbn; + u16 allocated_pbn; }; struct drm_dp_sideband_msg_req_body { diff --git a/include/linux/ahci_platform.h b/include/linux/ahci_platform.h index 6782f0d45ebe..49e5383d4222 100644 --- a/include/linux/ahci_platform.h +++ b/include/linux/ahci_platform.h @@ -19,6 +19,8 @@ struct ahci_host_priv; struct platform_device; struct scsi_host_template; +int ahci_platform_enable_phys(struct ahci_host_priv *hpriv); +void ahci_platform_disable_phys(struct ahci_host_priv *hpriv); int ahci_platform_enable_clks(struct ahci_host_priv *hpriv); void ahci_platform_disable_clks(struct ahci_host_priv *hpriv); int ahci_platform_enable_regulators(struct ahci_host_priv *hpriv); diff --git a/include/linux/bio.h b/include/linux/bio.h index 3cdb84cdc488..853d92ceee64 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -470,6 +470,7 @@ extern struct bio *bio_copy_user_iov(struct request_queue *, gfp_t); extern int bio_uncopy_user(struct bio *); void zero_fill_bio_iter(struct bio *bio, struct bvec_iter iter); +void bio_truncate(struct bio *bio, unsigned new_size); static inline void zero_fill_bio(struct bio *bio) { diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index bed9e43f9426..5669e3cfa1bc 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -815,6 +815,11 @@ static inline void blkcg_clear_delay(struct blkcg_gq *blkg) void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta); void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay); void blkcg_maybe_throttle_current(void); + +#ifdef CONFIG_BLK_CGROUP_IOCOST +extern struct blkcg_policy blkcg_policy_iocost; +#endif + #else /* CONFIG_BLK_CGROUP */ struct blkcg { diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 9b3c720a31b1..5e3d45525bd3 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -18,6 +18,7 @@ #include #include #include +#include #include /* @@ -91,6 +92,36 @@ struct can_priv { #define get_can_dlc(i) (min_t(__u8, (i), CAN_MAX_DLC)) #define get_canfd_dlc(i) (min_t(__u8, (i), CANFD_MAX_DLC)) +/* Check for outgoing skbs that have not been created by the CAN subsystem */ +static inline bool can_skb_headroom_valid(struct net_device *dev, + struct sk_buff *skb) +{ + /* af_packet creates a headroom of HH_DATA_MOD bytes which is fine */ + if (WARN_ON_ONCE(skb_headroom(skb) < sizeof(struct can_skb_priv))) + return false; + + /* af_packet does not apply CAN skb specific settings */ + if (skb->ip_summed == CHECKSUM_NONE) { + /* init headroom */ + can_skb_prv(skb)->ifindex = dev->ifindex; + can_skb_prv(skb)->skbcnt = 0; + + skb->ip_summed = CHECKSUM_UNNECESSARY; + + /* preform proper loopback on capable devices */ + if (dev->flags & IFF_ECHO) + skb->pkt_type = PACKET_LOOPBACK; + else + skb->pkt_type = PACKET_HOST; + + skb_reset_mac_header(skb); + skb_reset_network_header(skb); + skb_reset_transport_header(skb); + } + + return true; +} + /* Drop a given socketbuffer if it does not contain a valid CAN frame. */ static inline bool can_dropped_invalid_skb(struct net_device *dev, struct sk_buff *skb) @@ -108,6 +139,9 @@ static inline bool can_dropped_invalid_skb(struct net_device *dev, } else goto inval_skb; + if (!can_skb_headroom_valid(dev, skb)) + goto inval_skb; + return false; inval_skb: diff --git a/include/linux/compat.h b/include/linux/compat.h index 16dafd9f4b86..c4c389c7e1b4 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -410,8 +410,6 @@ struct compat_kexec_segment; struct compat_mq_attr; struct compat_msgbuf; -extern void compat_exit_robust_list(struct task_struct *curr); - #define BITS_PER_COMPAT_LONG (8*sizeof(compat_long_t)) #define BITS_TO_COMPAT_LONGS(bits) DIV_ROUND_UP(bits, BITS_PER_COMPAT_LONG) diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 92d5fdc8154e..31b1b0e03df8 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -595,17 +595,6 @@ struct governor_attr { size_t count); }; -static inline bool cpufreq_this_cpu_can_update(struct cpufreq_policy *policy) -{ - /* - * Allow remote callbacks if: - * - dvfs_possible_from_any_cpu flag is set - * - the local and remote CPUs share cpufreq policy - */ - return policy->dvfs_possible_from_any_cpu || - cpumask_test_cpu(smp_processor_id(), policy->cpus); -} - /********************************************************************* * FREQUENCY TABLE HELPERS * *********************************************************************/ diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index adf993a3bd58..6a18a97b76a8 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -3,8 +3,11 @@ #define _LINUX_DMA_DIRECT_H 1 #include +#include /* for min_low_pfn */ #include +static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr); + #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA #include #else @@ -24,11 +27,16 @@ static inline phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dev_addr) static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) { + dma_addr_t end = addr + size - 1; + if (!dev->dma_mask) return false; - return addr + size - 1 <= - min_not_zero(*dev->dma_mask, dev->bus_dma_mask); + if (!IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT) && + min(addr, end) < phys_to_dma(dev, PFN_PHYS(min_low_pfn))) + return false; + + return end <= min_not_zero(*dev->dma_mask, dev->bus_dma_mask); } #endif /* !CONFIG_ARCH_HAS_PHYS_TO_DMA */ diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 4a1c4fca475a..4d450672b7d6 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -162,7 +162,7 @@ int dma_release_from_dev_coherent(struct device *dev, int order, void *vaddr); int dma_mmap_from_dev_coherent(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, size_t size, int *ret); -void *dma_alloc_from_global_coherent(ssize_t size, dma_addr_t *dma_handle); +void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size, dma_addr_t *dma_handle); int dma_release_from_global_coherent(int order, void *vaddr); int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *cpu_addr, size_t size, int *ret); @@ -172,7 +172,7 @@ int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *cpu_addr, #define dma_release_from_dev_coherent(dev, order, vaddr) (0) #define dma_mmap_from_dev_coherent(dev, vma, vaddr, order, ret) (0) -static inline void *dma_alloc_from_global_coherent(ssize_t size, +static inline void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size, dma_addr_t *dma_handle) { return NULL; @@ -583,6 +583,10 @@ static inline unsigned long dma_get_merge_boundary(struct device *dev) static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr, size_t size, enum dma_data_direction dir, unsigned long attrs) { + /* DMA must never operate on areas that might be remapped. */ + if (dev_WARN_ONCE(dev, is_vmalloc_addr(ptr), + "rejecting DMA map of vmalloc memory\n")) + return DMA_MAPPING_ERROR; debug_dma_map_single(dev, ptr, size); return dma_map_page_attrs(dev, virt_to_page(ptr), offset_in_page(ptr), size, dir, attrs); diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 8fcdee1c0cf9..dad4a68fa009 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -1364,8 +1364,11 @@ static inline int dma_get_slave_caps(struct dma_chan *chan, static inline int dmaengine_desc_set_reuse(struct dma_async_tx_descriptor *tx) { struct dma_slave_caps caps; + int ret; - dma_get_slave_caps(tx->chan, &caps); + ret = dma_get_slave_caps(tx->chan, &caps); + if (ret) + return ret; if (caps.descriptor_reuse) { tx->flags |= DMA_CTRL_REUSE; diff --git a/include/linux/fs.h b/include/linux/fs.h index e0d909d35763..0b4d8fc79e0f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1727,6 +1727,13 @@ int vfs_mkobj(struct dentry *, umode_t, extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); +#ifdef CONFIG_COMPAT +extern long compat_ptr_ioctl(struct file *file, unsigned int cmd, + unsigned long arg); +#else +#define compat_ptr_ioctl NULL +#endif + /* * VFS file helper functions. */ diff --git a/include/linux/futex.h b/include/linux/futex.h index ccaef0097785..5cc3fed27d4c 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -2,7 +2,9 @@ #ifndef _LINUX_FUTEX_H #define _LINUX_FUTEX_H +#include #include + #include struct inode; @@ -48,15 +50,35 @@ union futex_key { #define FUTEX_KEY_INIT (union futex_key) { .both = { .ptr = NULL } } #ifdef CONFIG_FUTEX -extern void exit_robust_list(struct task_struct *curr); +enum { + FUTEX_STATE_OK, + FUTEX_STATE_EXITING, + FUTEX_STATE_DEAD, +}; -long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, - u32 __user *uaddr2, u32 val2, u32 val3); -#else -static inline void exit_robust_list(struct task_struct *curr) +static inline void futex_init_task(struct task_struct *tsk) { + tsk->robust_list = NULL; +#ifdef CONFIG_COMPAT + tsk->compat_robust_list = NULL; +#endif + INIT_LIST_HEAD(&tsk->pi_state_list); + tsk->pi_state_cache = NULL; + tsk->futex_state = FUTEX_STATE_OK; + mutex_init(&tsk->futex_exit_mutex); } +void futex_exit_recursive(struct task_struct *tsk); +void futex_exit_release(struct task_struct *tsk); +void futex_exec_release(struct task_struct *tsk); + +long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, + u32 __user *uaddr2, u32 val2, u32 val3); +#else +static inline void futex_init_task(struct task_struct *tsk) { } +static inline void futex_exit_recursive(struct task_struct *tsk) { } +static inline void futex_exit_release(struct task_struct *tsk) { } +static inline void futex_exec_release(struct task_struct *tsk) { } static inline long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, u32 __user *uaddr2, u32 val2, u32 val3) @@ -65,12 +87,4 @@ static inline long do_futex(u32 __user *uaddr, int op, u32 val, } #endif -#ifdef CONFIG_FUTEX_PI -extern void exit_pi_state_list(struct task_struct *curr); -#else -static inline void exit_pi_state_list(struct task_struct *curr) -{ -} -#endif - #endif diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 1b9a51a1bccb..1f98b52118f0 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -456,12 +456,18 @@ extern u64 hrtimer_next_event_without(const struct hrtimer *exclude); extern bool hrtimer_active(const struct hrtimer *timer); -/* - * Helper function to check, whether the timer is on one of the queues +/** + * hrtimer_is_queued = check, whether the timer is on one of the queues + * @timer: Timer to check + * + * Returns: True if the timer is queued, false otherwise + * + * The function can be used lockless, but it gives only a current snapshot. */ -static inline int hrtimer_is_queued(struct hrtimer *timer) +static inline bool hrtimer_is_queued(struct hrtimer *timer) { - return timer->state & HRTIMER_STATE_ENQUEUED; + /* The READ_ONCE pairs with the update functions of timer->state */ + return !!(READ_ONCE(timer->state) & HRTIMER_STATE_ENQUEUED); } /* diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h index 76cf11e905e1..8a9792a6427a 100644 --- a/include/linux/if_ether.h +++ b/include/linux/if_ether.h @@ -24,6 +24,14 @@ static inline struct ethhdr *eth_hdr(const struct sk_buff *skb) return (struct ethhdr *)skb_mac_header(skb); } +/* Prefer this version in TX path, instead of + * skb_reset_mac_header() + eth_hdr() + */ +static inline struct ethhdr *skb_eth_hdr(const struct sk_buff *skb) +{ + return (struct ethhdr *)skb->data; +} + static inline struct ethhdr *inner_eth_hdr(const struct sk_buff *skb) { return (struct ethhdr *)skb_inner_mac_header(skb); diff --git a/include/linux/io.h b/include/linux/io.h index accac822336a..a59834bc0a11 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -64,6 +64,8 @@ static inline void devm_ioport_unmap(struct device *dev, void __iomem *addr) void __iomem *devm_ioremap(struct device *dev, resource_size_t offset, resource_size_t size); +void __iomem *devm_ioremap_uc(struct device *dev, resource_size_t offset, + resource_size_t size); void __iomem *devm_ioremap_nocache(struct device *dev, resource_size_t offset, resource_size_t size); void __iomem *devm_ioremap_wc(struct device *dev, resource_size_t offset, diff --git a/include/linux/ipmi_smi.h b/include/linux/ipmi_smi.h index 4dc66157d872..deec18b8944a 100644 --- a/include/linux/ipmi_smi.h +++ b/include/linux/ipmi_smi.h @@ -224,10 +224,14 @@ static inline int ipmi_demangle_device_id(uint8_t netfn, uint8_t cmd, * is called, and the lower layer must get the interface from that * call. */ -int ipmi_register_smi(const struct ipmi_smi_handlers *handlers, - void *send_info, - struct device *dev, - unsigned char slave_addr); +int ipmi_add_smi(struct module *owner, + const struct ipmi_smi_handlers *handlers, + void *send_info, + struct device *dev, + unsigned char slave_addr); + +#define ipmi_register_smi(handlers, send_info, dev, slave_addr) \ + ipmi_add_smi(THIS_MODULE, handlers, send_info, dev, slave_addr) /* * Remove a low-level interface from the IPMI driver. This will diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 603fbc4e2f70..10e6049c0ba9 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1582,7 +1582,7 @@ static inline int jbd2_space_needed(journal_t *journal) static inline unsigned long jbd2_log_space_left(journal_t *journal) { /* Allow for rounding errors */ - unsigned long free = journal->j_free - 32; + long free = journal->j_free - 32; if (journal->j_committing_transaction) { unsigned long committing = atomic_read(&journal-> @@ -1591,7 +1591,7 @@ static inline unsigned long jbd2_log_space_left(journal_t *journal) /* Transaction + control blocks */ free -= committing + (committing >> JBD2_CONTROL_BLOCKS_SHIFT); } - return free; + return max_t(long, free, 0); } /* diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index 1b6d31da7cbc..dea181bdb1dd 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -171,7 +171,7 @@ static inline u64 get_jiffies_64(void) * Have the 32 bit jiffies value wrap 5 minutes after boot * so jiffies wrap bugs show up earlier. */ -#define INITIAL_JIFFIES ((unsigned long)(unsigned int) (-300*HZ)) +#define INITIAL_JIFFIES ((unsigned long)(unsigned int) (-10*HZ)) /* * Change timeval to jiffies, trying to avoid the diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 936b61bd504e..f797ccc650e7 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -187,6 +187,7 @@ struct kernfs_root { /* private fields, do not use outside kernfs proper */ struct idr ino_idr; + u32 last_ino; u32 next_generation; struct kernfs_syscall_ops *syscall_ops; diff --git a/include/linux/ksm.h b/include/linux/ksm.h index e48b1e453ff5..a91a7cfc87a1 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -19,6 +19,10 @@ struct stable_node; struct mem_cgroup; #ifdef CONFIG_KSM +int ksm_madvise_merge(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long *vm_flags); +int ksm_madvise_unmerge(struct vm_area_struct *vma, unsigned long start, + unsigned long end, unsigned long *vm_flags); int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags); int __ksm_enter(struct mm_struct *mm); diff --git a/include/linux/libata.h b/include/linux/libata.h index 207e7ee764ce..fa0c3dae2094 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1174,6 +1174,7 @@ extern unsigned int ata_do_dev_read_id(struct ata_device *dev, struct ata_taskfile *tf, u16 *id); extern void ata_qc_complete(struct ata_queued_cmd *qc); extern int ata_qc_complete_multiple(struct ata_port *ap, u64 qc_active); +extern u64 ata_qc_get_active(struct ata_port *ap); extern void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd); extern int ata_std_bios_param(struct scsi_device *sdev, struct block_device *bdev, diff --git a/include/linux/libfdt_env.h b/include/linux/libfdt_env.h index edb0f0c30904..1adf54aad2df 100644 --- a/include/linux/libfdt_env.h +++ b/include/linux/libfdt_env.h @@ -7,6 +7,9 @@ #include +#define INT32_MAX S32_MAX +#define UINT32_MAX U32_MAX + typedef __be16 fdt16_t; typedef __be32 fdt32_t; typedef __be64 fdt64_t; diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index f46ea71b4ffd..451efd4499cc 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -125,8 +125,8 @@ static inline bool movable_node_is_enabled(void) extern void arch_remove_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap); -extern void __remove_pages(struct zone *zone, unsigned long start_pfn, - unsigned long nr_pages, struct vmem_altmap *altmap); +extern void __remove_pages(unsigned long start_pfn, unsigned long nr_pages, + struct vmem_altmap *altmap); /* reasonably generic interface to expand the physical pages */ extern int __add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, @@ -345,6 +345,9 @@ extern int add_memory(int nid, u64 start, u64 size); extern int add_memory_resource(int nid, struct resource *resource); extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages, struct vmem_altmap *altmap); +extern void remove_pfn_range_from_zone(struct zone *zone, + unsigned long start_pfn, + unsigned long nr_pages); extern bool is_memblock_offlined(struct memory_block *mem); extern int sparse_add_section(int nid, unsigned long pfn, unsigned long nr_pages, struct vmem_altmap *altmap); diff --git a/include/linux/mfd/rk808.h b/include/linux/mfd/rk808.h index 7cfd2b0504df..a59bf323f713 100644 --- a/include/linux/mfd/rk808.h +++ b/include/linux/mfd/rk808.h @@ -610,7 +610,7 @@ enum { RK808_ID = 0x0000, RK809_ID = 0x8090, RK817_ID = 0x8170, - RK818_ID = 0x8181, + RK818_ID = 0x8180, }; struct rk808 { diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h index 3247a3dc7934..b06b75776a32 100644 --- a/include/linux/miscdevice.h +++ b/include/linux/miscdevice.h @@ -57,6 +57,7 @@ #define UHID_MINOR 239 #define USERIO_MINOR 240 #define VHOST_VSOCK_MINOR 241 +#define RFKILL_MINOR 242 #define MISC_DYNAMIC_MINOR 255 struct device; diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 9b6336ad3266..e459b38ef33c 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -291,6 +291,7 @@ struct mmc_card { struct sd_switch_caps sw_caps; /* switch (CMD6) caps */ unsigned int sdio_funcs; /* number of SDIO functions */ + atomic_t sdio_funcs_probed; /* number of probed SDIO funcs */ struct sdio_cccr cccr; /* common card info */ struct sdio_cis cis; /* common tuple info */ struct sdio_func *sdio_func[SDIO_MAX_FUNCS]; /* SDIO functions (devices) */ diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 5714fd35a83c..e3596db077dc 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -587,9 +587,9 @@ struct platform_device_id { #define MDIO_NAME_SIZE 32 #define MDIO_MODULE_PREFIX "mdio:" -#define MDIO_ID_FMT "%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d" +#define MDIO_ID_FMT "%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u" #define MDIO_ID_ARGS(_id) \ - (_id)>>31, ((_id)>>30) & 1, ((_id)>>29) & 1, ((_id)>>28) & 1, \ + ((_id)>>31) & 1, ((_id)>>30) & 1, ((_id)>>29) & 1, ((_id)>>28) & 1, \ ((_id)>>27) & 1, ((_id)>>26) & 1, ((_id)>>25) & 1, ((_id)>>24) & 1, \ ((_id)>>23) & 1, ((_id)>>22) & 1, ((_id)>>21) & 1, ((_id)>>20) & 1, \ ((_id)>>19) & 1, ((_id)>>18) & 1, ((_id)>>17) & 1, ((_id)>>16) & 1, \ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c20f190b4c18..76d952aeb0fc 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1867,6 +1867,11 @@ struct net_device { unsigned char if_port; unsigned char dma; + /* Note : dev->mtu is often read without holding a lock. + * Writers usually hold RTNL. + * It is recommended to use READ_ONCE() to annotate the reads, + * and to use WRITE_ONCE() to annotate the writes. + */ unsigned int mtu; unsigned int min_mtu; unsigned int max_mtu; diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index 10f81629b9ce..6d0d70f3219c 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -270,6 +270,8 @@ struct nvme_fc_remote_port { * * Host/Initiator Transport Entrypoints/Parameters: * + * @module: The LLDD module using the interface + * * @localport_delete: The LLDD initiates deletion of a localport via * nvme_fc_deregister_localport(). However, the teardown is * asynchronous. This routine is called upon the completion of the @@ -383,6 +385,8 @@ struct nvme_fc_remote_port { * Value is Mandatory. Allowed to be zero. */ struct nvme_fc_port_template { + struct module *module; + /* initiator-based functions */ void (*localport_delete)(struct nvme_fc_local_port *); void (*remoteport_delete)(struct nvme_fc_remote_port *); diff --git a/include/linux/nvme.h b/include/linux/nvme.h index f61d6906e59d..a260cd754f28 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -1368,6 +1368,7 @@ enum { NVME_SC_ANA_INACCESSIBLE = 0x302, NVME_SC_ANA_TRANSITION = 0x303, NVME_SC_HOST_PATH_ERROR = 0x370, + NVME_SC_HOST_ABORTED_CMD = 0x371, NVME_SC_CRD = 0x1800, NVME_SC_DNR = 0x4000, diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index 8f8be5b00060..5c17cb733224 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -118,7 +118,7 @@ static inline void *nvmem_cell_read(struct nvmem_cell *cell, size_t *len) } static inline int nvmem_cell_write(struct nvmem_cell *cell, - const char *buf, size_t len) + void *buf, size_t len) { return -EOPNOTSUPP; } diff --git a/include/linux/pci.h b/include/linux/pci.h index f9088c89a534..be529d311122 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2310,9 +2310,11 @@ struct irq_domain *pci_host_bridge_acpi_msi_domain(struct pci_bus *bus); void pci_msi_register_fwnode_provider(struct fwnode_handle *(*fn)(struct device *)); +bool pci_pr3_present(struct pci_dev *pdev); #else static inline struct irq_domain * pci_host_bridge_acpi_msi_domain(struct pci_bus *bus) { return NULL; } +static inline bool pci_pr3_present(struct pci_dev *pdev) { return false; } #endif #ifdef CONFIG_EEH diff --git a/include/linux/phy.h b/include/linux/phy.h index 9a0e981df502..3d5d53313e6c 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -993,7 +993,7 @@ int phy_modify_paged_changed(struct phy_device *phydev, int page, u32 regnum, int phy_modify_paged(struct phy_device *phydev, int page, u32 regnum, u16 mask, u16 set); -struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id, +struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id, bool is_c45, struct phy_c45_device_ids *c45_ids); #if IS_ENABLED(CONFIG_PHYLIB) diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h index ebf5ef17cc2a..24a6263c9931 100644 --- a/include/linux/pm_qos.h +++ b/include/linux/pm_qos.h @@ -256,7 +256,7 @@ static inline s32 dev_pm_qos_raw_resume_latency(struct device *dev) #endif #define FREQ_QOS_MIN_DEFAULT_VALUE 0 -#define FREQ_QOS_MAX_DEFAULT_VALUE (-1) +#define FREQ_QOS_MAX_DEFAULT_VALUE S32_MAX enum freq_qos_req_type { FREQ_QOS_MIN = 1, diff --git a/include/linux/posix-clock.h b/include/linux/posix-clock.h index fe6cfdcfbc26..468328b1e1dd 100644 --- a/include/linux/posix-clock.h +++ b/include/linux/posix-clock.h @@ -69,29 +69,32 @@ struct posix_clock_operations { * * @ops: Functional interface to the clock * @cdev: Character device instance for this clock - * @kref: Reference count. + * @dev: Pointer to the clock's device. * @rwsem: Protects the 'zombie' field from concurrent access. * @zombie: If 'zombie' is true, then the hardware has disappeared. - * @release: A function to free the structure when the reference count reaches - * zero. May be NULL if structure is statically allocated. * * Drivers should embed their struct posix_clock within a private * structure, obtaining a reference to it during callbacks using * container_of(). + * + * Drivers should supply an initialized but not exposed struct device + * to posix_clock_register(). It is used to manage lifetime of the + * driver's private structure. It's 'release' field should be set to + * a release function for this private structure. */ struct posix_clock { struct posix_clock_operations ops; struct cdev cdev; - struct kref kref; + struct device *dev; struct rw_semaphore rwsem; bool zombie; - void (*release)(struct posix_clock *clk); }; /** * posix_clock_register() - register a new clock - * @clk: Pointer to the clock. Caller must provide 'ops' and 'release' - * @devid: Allocated device id + * @clk: Pointer to the clock. Caller must provide 'ops' field + * @dev: Pointer to the initialized device. Caller must provide + * 'release' field * * A clock driver calls this function to register itself with the * clock device subsystem. If 'clk' points to dynamically allocated @@ -100,7 +103,7 @@ struct posix_clock { * * Returns zero on success, non-zero otherwise. */ -int posix_clock_register(struct posix_clock *clk, dev_t devid); +int posix_clock_register(struct posix_clock *clk, struct device *dev); /** * posix_clock_unregister() - unregister a clock diff --git a/include/linux/quota.h b/include/linux/quota.h index f32dd270b8e3..27aab84fcbaa 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -263,7 +263,7 @@ enum { }; struct dqstats { - int stat[_DQST_DQSTAT_LAST]; + unsigned long stat[_DQST_DQSTAT_LAST]; struct percpu_counter counter[_DQST_DQSTAT_LAST]; }; diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 185d94829701..91e0b7624053 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -54,6 +54,16 @@ static inline struct dquot *dqgrab(struct dquot *dquot) atomic_inc(&dquot->dq_count); return dquot; } + +static inline bool dquot_is_busy(struct dquot *dquot) +{ + if (test_bit(DQ_MOD_B, &dquot->dq_flags)) + return true; + if (atomic_read(&dquot->dq_count) > 1) + return true; + return false; +} + void dqput(struct dquot *dquot); int dquot_scan_active(struct super_block *sb, int (*fn)(struct dquot *dquot, unsigned long priv), diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h index bc8206a8f30e..61974c4c566b 100644 --- a/include/linux/rculist_nulls.h +++ b/include/linux/rculist_nulls.h @@ -100,6 +100,43 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n, first->pprev = &n->next; } +/** + * hlist_nulls_add_tail_rcu + * @n: the element to add to the hash list. + * @h: the list to add to. + * + * Description: + * Adds the specified element to the specified hlist_nulls, + * while permitting racing traversals. + * + * The caller must take whatever precautions are necessary + * (such as holding appropriate locks) to avoid racing + * with another list-mutation primitive, such as hlist_nulls_add_head_rcu() + * or hlist_nulls_del_rcu(), running on this same list. + * However, it is perfectly legal to run concurrently with + * the _rcu list-traversal primitives, such as + * hlist_nulls_for_each_entry_rcu(), used to prevent memory-consistency + * problems on Alpha CPUs. Regardless of the type of CPU, the + * list-traversal primitive must be guarded by rcu_read_lock(). + */ +static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n, + struct hlist_nulls_head *h) +{ + struct hlist_nulls_node *i, *last = NULL; + + /* Note: write side code, so rcu accessors are not needed. */ + for (i = h->first; !is_a_nulls(i); i = i->next) + last = i; + + if (last) { + n->next = last->next; + n->pprev = &last->next; + rcu_assign_pointer(hlist_next_rcu(last), n); + } else { + hlist_nulls_add_head_rcu(n, h); + } +} + /** * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type * @tpos: the type * to use as a loop cursor. diff --git a/include/linux/regulator/ab8500.h b/include/linux/regulator/ab8500.h index 7cf8f797e13a..505e94a6e3e8 100644 --- a/include/linux/regulator/ab8500.h +++ b/include/linux/regulator/ab8500.h @@ -37,7 +37,6 @@ enum ab8505_regulator_id { AB8505_LDO_AUX6, AB8505_LDO_INTCORE, AB8505_LDO_ADC, - AB8505_LDO_USB, AB8505_LDO_AUDIO, AB8505_LDO_ANAMIC1, AB8505_LDO_ANAMIC2, diff --git a/include/linux/sched.h b/include/linux/sched.h index 67a1d86981a9..68543826b382 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -644,13 +644,18 @@ struct task_struct { unsigned int flags; unsigned int ptrace; -#ifdef CONFIG_SMP +#if defined(CONFIG_SMP) && !defined(CONFIG_SCHED_BMQ) struct llist_node wake_entry; +#endif +#if defined(CONFIG_SMP) || defined(CONFIG_SCHED_BMQ) int on_cpu; +#endif +#ifdef CONFIG_SMP #ifdef CONFIG_THREAD_INFO_IN_TASK /* Current CPU: */ unsigned int cpu; #endif +#ifndef CONFIG_SCHED_BMQ unsigned int wakee_flips; unsigned long wakee_flip_decay_ts; struct task_struct *last_wakee; @@ -664,6 +669,7 @@ struct task_struct { */ int recent_used_cpu; int wake_cpu; +#endif /* !CONFIG_SCHED_BMQ */ #endif int on_rq; @@ -672,13 +678,23 @@ struct task_struct { int normal_prio; unsigned int rt_priority; +#ifdef CONFIG_SCHED_BMQ + u64 last_ran; + s64 time_slice; + int boost_prio; + int bmq_idx; + struct list_head bmq_node; + /* sched_clock time spent running */ + u64 sched_time; +#else /* !CONFIG_SCHED_BMQ */ const struct sched_class *sched_class; struct sched_entity se; struct sched_rt_entity rt; + struct sched_dl_entity dl; +#endif #ifdef CONFIG_CGROUP_SCHED struct task_group *sched_task_group; #endif - struct sched_dl_entity dl; #ifdef CONFIG_UCLAMP_TASK /* Clamp values requested for a scheduling entity */ @@ -1054,6 +1070,8 @@ struct task_struct { #endif struct list_head pi_state_list; struct futex_pi_state *pi_state_cache; + struct mutex futex_exit_mutex; + unsigned int futex_state; #endif #ifdef CONFIG_PERF_EVENTS struct perf_event_context *perf_event_ctxp[perf_nr_task_contexts]; @@ -1283,6 +1301,15 @@ struct task_struct { */ }; +#ifdef CONFIG_SCHED_BMQ +#define tsk_seruntime(t) ((t)->sched_time) +/* replace the uncertian rt_timeout with 0UL */ +#define tsk_rttimeout(t) (0UL) +#else /* CFS */ +#define tsk_seruntime(t) ((t)->se.sum_exec_runtime) +#define tsk_rttimeout(t) ((t)->rt.timeout) +#endif /* !CONFIG_SCHED_BMQ */ + static inline struct pid *task_pid(struct task_struct *task) { return task->thread_pid; @@ -1442,7 +1469,6 @@ extern struct pid *cad_pid; */ #define PF_IDLE 0x00000002 /* I am an IDLE thread */ #define PF_EXITING 0x00000004 /* Getting shut down */ -#define PF_EXITPIDONE 0x00000008 /* PI exit done on shut down */ #define PF_VCPU 0x00000010 /* I'm a virtual CPU */ #define PF_WQ_WORKER 0x00000020 /* I'm a workqueue worker */ #define PF_FORKNOEXEC 0x00000040 /* Forked but didn't exec */ diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h index afa940cd50dc..cc6bcc1e96bc 100644 --- a/include/linux/sched/cpufreq.h +++ b/include/linux/sched/cpufreq.h @@ -12,6 +12,8 @@ #define SCHED_CPUFREQ_MIGRATION (1U << 1) #ifdef CONFIG_CPU_FREQ +struct cpufreq_policy; + struct update_util_data { void (*func)(struct update_util_data *data, u64 time, unsigned int flags); }; @@ -20,6 +22,7 @@ void cpufreq_add_update_util_hook(int cpu, struct update_util_data *data, void (*func)(struct update_util_data *data, u64 time, unsigned int flags)); void cpufreq_remove_update_util_hook(int cpu); +bool cpufreq_this_cpu_can_update(struct cpufreq_policy *policy); static inline unsigned long map_util_freq(unsigned long util, unsigned long freq, unsigned long cap) diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h index 1aff00b65f3c..02a3c5d34ee4 100644 --- a/include/linux/sched/deadline.h +++ b/include/linux/sched/deadline.h @@ -1,5 +1,22 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#ifdef CONFIG_SCHED_BMQ + +#define __tsk_deadline(p) (0UL) + +static inline int dl_prio(int prio) +{ + return 0; +} + +static inline int dl_task(struct task_struct *p) +{ + return (SCHED_NORMAL == p->policy); +} +#else + +#define __tsk_deadline(p) ((p)->dl.deadline) + /* * SCHED_DEADLINE tasks has negative priorities, reflecting * the fact that any of them has higher prio than RT and @@ -19,6 +36,7 @@ static inline int dl_task(struct task_struct *p) { return dl_prio(p->prio); } +#endif /* CONFIG_SCHED_BMQ */ static inline bool dl_time_before(u64 a, u64 b) { diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index e6770012db18..c49257a3b510 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -117,8 +117,10 @@ extern struct mm_struct *get_task_mm(struct task_struct *task); * succeeds. */ extern struct mm_struct *mm_access(struct task_struct *task, unsigned int mode); -/* Remove the current tasks stale references to the old mm_struct */ -extern void mm_release(struct task_struct *, struct mm_struct *); +/* Remove the current tasks stale references to the old mm_struct on exit() */ +extern void exit_mm_release(struct task_struct *, struct mm_struct *); +/* Remove the current tasks stale references to the old mm_struct on exec() */ +extern void exec_mm_release(struct task_struct *, struct mm_struct *); #ifdef CONFIG_MEMCG extern void mm_update_next_owner(struct mm_struct *mm); diff --git a/include/linux/sched/prio.h b/include/linux/sched/prio.h index 7d64feafc408..d9dc5d3ccd2e 100644 --- a/include/linux/sched/prio.h +++ b/include/linux/sched/prio.h @@ -20,11 +20,17 @@ */ #define MAX_USER_RT_PRIO 100 + #define MAX_RT_PRIO MAX_USER_RT_PRIO #define MAX_PRIO (MAX_RT_PRIO + NICE_WIDTH) #define DEFAULT_PRIO (MAX_RT_PRIO + NICE_WIDTH / 2) +#ifdef CONFIG_SCHED_BMQ +/* +/- priority levels from the base priority */ +#define MAX_PRIORITY_ADJ 4 +#endif + /* * Convert user-nice values [ -20 ... 0 ... 19 ] * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ], diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h index e5af028c08b4..6387c8ea9832 100644 --- a/include/linux/sched/rt.h +++ b/include/linux/sched/rt.h @@ -24,8 +24,10 @@ static inline bool task_is_realtime(struct task_struct *tsk) if (policy == SCHED_FIFO || policy == SCHED_RR) return true; +#ifndef CONFIG_SCHED_BMQ if (policy == SCHED_DEADLINE) return true; +#endif return false; } diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 4b1c3b664f51..f0f966219695 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -99,7 +99,7 @@ extern long kernel_wait4(pid_t, int __user *, int, struct rusage *); extern void free_task(struct task_struct *tsk); /* sched_exec is called by processes performing an exec */ -#ifdef CONFIG_SMP +#if defined(CONFIG_SMP) && !defined(CONFIG_SCHED_BMQ) extern void sched_exec(void); #else #define sched_exec() {} diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 8688f7adfda7..6ae88b0c1c31 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1795,7 +1795,7 @@ static inline struct sk_buff *skb_peek_next(struct sk_buff *skb, */ static inline struct sk_buff *skb_peek_tail(const struct sk_buff_head *list_) { - struct sk_buff *skb = list_->prev; + struct sk_buff *skb = READ_ONCE(list_->prev); if (skb == (struct sk_buff *)list_) skb = NULL; @@ -1861,7 +1861,9 @@ static inline void __skb_insert(struct sk_buff *newsk, struct sk_buff *prev, struct sk_buff *next, struct sk_buff_head *list) { - /* see skb_queue_empty_lockless() for the opposite READ_ONCE() */ + /* See skb_queue_empty_lockless() and skb_peek_tail() + * for the opposite READ_ONCE() + */ WRITE_ONCE(newsk->next, next); WRITE_ONCE(newsk->prev, prev); WRITE_ONCE(next->prev, newsk); @@ -3527,8 +3529,9 @@ int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci); int skb_vlan_pop(struct sk_buff *skb); int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, - int mac_len); -int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len); + int mac_len, bool ethernet); +int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len, + bool ethernet); int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse); int skb_mpls_dec_ttl(struct sk_buff *skb); struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy, diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index ce7055259877..da4caff7efa4 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -14,6 +14,7 @@ #include #define MAX_MSG_FRAGS MAX_SKB_FRAGS +#define NR_MSG_FRAG_IDS (MAX_MSG_FRAGS + 1) enum __sk_action { __SK_DROP = 0, @@ -29,11 +30,13 @@ struct sk_msg_sg { u32 size; u32 copybreak; bool copy[MAX_MSG_FRAGS]; - /* The extra element is used for chaining the front and sections when - * the list becomes partitioned (e.g. end < start). The crypto APIs - * require the chaining. + /* The extra two elements: + * 1) used for chaining the front and sections when the list becomes + * partitioned (e.g. end < start). The crypto APIs require the + * chaining; + * 2) to chain tailer SG entries after the message. */ - struct scatterlist data[MAX_MSG_FRAGS + 1]; + struct scatterlist data[MAX_MSG_FRAGS + 2]; }; /* UAPI in filter.c depends on struct sk_msg_sg being first element. */ @@ -141,13 +144,13 @@ static inline void sk_msg_apply_bytes(struct sk_psock *psock, u32 bytes) static inline u32 sk_msg_iter_dist(u32 start, u32 end) { - return end >= start ? end - start : end + (MAX_MSG_FRAGS - start); + return end >= start ? end - start : end + (NR_MSG_FRAG_IDS - start); } #define sk_msg_iter_var_prev(var) \ do { \ if (var == 0) \ - var = MAX_MSG_FRAGS - 1; \ + var = NR_MSG_FRAG_IDS - 1; \ else \ var--; \ } while (0) @@ -155,7 +158,7 @@ static inline u32 sk_msg_iter_dist(u32 start, u32 end) #define sk_msg_iter_var_next(var) \ do { \ var++; \ - if (var == MAX_MSG_FRAGS) \ + if (var == NR_MSG_FRAG_IDS) \ var = 0; \ } while (0) @@ -172,9 +175,9 @@ static inline void sk_msg_clear_meta(struct sk_msg *msg) static inline void sk_msg_init(struct sk_msg *msg) { - BUILD_BUG_ON(ARRAY_SIZE(msg->sg.data) - 1 != MAX_MSG_FRAGS); + BUILD_BUG_ON(ARRAY_SIZE(msg->sg.data) - 1 != NR_MSG_FRAG_IDS); memset(msg, 0, sizeof(*msg)); - sg_init_marker(msg->sg.data, MAX_MSG_FRAGS); + sg_init_marker(msg->sg.data, NR_MSG_FRAG_IDS); } static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src, @@ -195,14 +198,11 @@ static inline void sk_msg_xfer_full(struct sk_msg *dst, struct sk_msg *src) static inline bool sk_msg_full(const struct sk_msg *msg) { - return (msg->sg.end == msg->sg.start) && msg->sg.size; + return sk_msg_iter_dist(msg->sg.start, msg->sg.end) == MAX_MSG_FRAGS; } static inline u32 sk_msg_elem_used(const struct sk_msg *msg) { - if (sk_msg_full(msg)) - return MAX_MSG_FRAGS; - return sk_msg_iter_dist(msg->sg.start, msg->sg.end); } diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index 659a4400517b..e93e249a4e9b 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -147,6 +147,8 @@ check_copy_size(const void *addr, size_t bytes, bool is_source) __bad_copy_to(); return false; } + if (WARN_ON_ONCE(bytes > INT_MAX)) + return false; check_object_size(addr, bytes, is_source); return true; } diff --git a/include/linux/time.h b/include/linux/time.h index 27d83fd2ae61..5f3e49978837 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -96,4 +96,17 @@ static inline bool itimerspec64_valid(const struct itimerspec64 *its) */ #define time_after32(a, b) ((s32)((u32)(b) - (u32)(a)) < 0) #define time_before32(b, a) time_after32(a, b) + +/** + * time_between32 - check if a 32-bit timestamp is within a given time range + * @t: the time which may be within [l,h] + * @l: the lower bound of the range + * @h: the higher bound of the range + * + * time_before32(t, l, h) returns true if @l <= @t <= @h. All operands are + * treated as 32-bit integers. + * + * Equivalent to !(time_before32(@t, @l) || time_after32(@t, @h)). + */ +#define time_between32(t, l, h) ((u32)(h) - (u32)(l) >= (u32)(t) - (u32)(l)) #endif diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index d4ee6e942562..38555435a64a 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -337,6 +337,18 @@ extern long __probe_user_read(void *dst, const void __user *src, size_t size); extern long notrace probe_kernel_write(void *dst, const void *src, size_t size); extern long notrace __probe_kernel_write(void *dst, const void *src, size_t size); +/* + * probe_user_write(): safely attempt to write to a location in user space + * @dst: address to write to + * @src: pointer to the data that shall be written + * @size: size of the data chunk + * + * Safely write to address @dst from the buffer at @src. If a kernel fault + * happens, handle that and return -EFAULT. + */ +extern long notrace probe_user_write(void __user *dst, const void *src, size_t size); +extern long notrace __probe_user_write(void __user *dst, const void *src, size_t size); + extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); extern long strncpy_from_unsafe_user(char *dst, const void __user *unsafe_addr, long count); diff --git a/include/net/arp.h b/include/net/arp.h index c8f580a0e6b1..4950191f6b2b 100644 --- a/include/net/arp.h +++ b/include/net/arp.h @@ -57,8 +57,8 @@ static inline void __ipv4_confirm_neigh(struct net_device *dev, u32 key) unsigned long now = jiffies; /* avoid dirtying neighbour */ - if (n->confirmed != now) - n->confirmed = now; + if (READ_ONCE(n->confirmed) != now) + WRITE_ONCE(n->confirmed, now); } rcu_read_unlock_bh(); } diff --git a/include/net/dst.h b/include/net/dst.h index fe62fe2eb781..3448cf865ede 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -82,7 +82,7 @@ struct dst_entry { struct dst_metrics { u32 metrics[RTAX_MAX]; refcount_t refcnt; -}; +} __aligned(4); /* Low pointer bits contain DST_METRICS_FLAGS */ extern const struct dst_metrics dst_default_metrics; u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old); @@ -516,7 +516,16 @@ static inline void skb_dst_update_pmtu(struct sk_buff *skb, u32 mtu) struct dst_entry *dst = skb_dst(skb); if (dst && dst->ops->update_pmtu) - dst->ops->update_pmtu(dst, NULL, skb, mtu); + dst->ops->update_pmtu(dst, NULL, skb, mtu, true); +} + +/* update dst pmtu but not do neighbor confirm */ +static inline void skb_dst_update_pmtu_no_confirm(struct sk_buff *skb, u32 mtu) +{ + struct dst_entry *dst = skb_dst(skb); + + if (dst && dst->ops->update_pmtu) + dst->ops->update_pmtu(dst, NULL, skb, mtu, false); } static inline void skb_tunnel_check_pmtu(struct sk_buff *skb, @@ -526,7 +535,7 @@ static inline void skb_tunnel_check_pmtu(struct sk_buff *skb, u32 encap_mtu = dst_mtu(encap_dst); if (skb->len > encap_mtu - headroom) - skb_dst_update_pmtu(skb, encap_mtu - headroom); + skb_dst_update_pmtu_no_confirm(skb, encap_mtu - headroom); } #endif /* _NET_DST_H */ diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 5ec645f27ee3..443863c7b8da 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -27,7 +27,8 @@ struct dst_ops { struct dst_entry * (*negative_advice)(struct dst_entry *); void (*link_failure)(struct sk_buff *); void (*update_pmtu)(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu); + struct sk_buff *skb, u32 mtu, + bool confirm_neigh); void (*redirect)(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); int (*local_out)(struct net *net, struct sock *sk, struct sk_buff *skb); diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 5cd12276ae21..e5fc8db1f783 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -229,6 +229,7 @@ enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_IPV4_ADDRS, /* struct flow_dissector_key_ipv4_addrs */ FLOW_DISSECTOR_KEY_IPV6_ADDRS, /* struct flow_dissector_key_ipv6_addrs */ FLOW_DISSECTOR_KEY_PORTS, /* struct flow_dissector_key_ports */ + FLOW_DISSECTOR_KEY_PORTS_RANGE, /* struct flow_dissector_key_ports */ FLOW_DISSECTOR_KEY_ICMP, /* struct flow_dissector_key_icmp */ FLOW_DISSECTOR_KEY_ETH_ADDRS, /* struct flow_dissector_key_eth_addrs */ FLOW_DISSECTOR_KEY_TIPC, /* struct flow_dissector_key_tipc */ diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 86c567f531f3..c6f7bd22db60 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -380,19 +380,18 @@ static inline void flow_block_init(struct flow_block *flow_block) typedef int flow_indr_block_bind_cb_t(struct net_device *dev, void *cb_priv, enum tc_setup_type type, void *type_data); -typedef void flow_indr_block_ing_cmd_t(struct net_device *dev, - flow_indr_block_bind_cb_t *cb, - void *cb_priv, - enum flow_block_command command); +typedef void flow_indr_block_cmd_t(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, void *cb_priv, + enum flow_block_command command); -struct flow_indr_block_ing_entry { - flow_indr_block_ing_cmd_t *cb; +struct flow_indr_block_entry { + flow_indr_block_cmd_t *cb; struct list_head list; }; -void flow_indr_add_block_ing_cb(struct flow_indr_block_ing_entry *entry); +void flow_indr_add_block_cb(struct flow_indr_block_entry *entry); -void flow_indr_del_block_ing_cb(struct flow_indr_block_ing_entry *entry); +void flow_indr_del_block_cb(struct flow_indr_block_entry *entry); int __flow_indr_block_cb_register(struct net_device *dev, void *cb_priv, flow_indr_block_bind_cb_t *cb, diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index af2b4c065a04..d0019d3395cf 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -103,13 +103,19 @@ struct inet_bind_hashbucket { struct hlist_head chain; }; -/* - * Sockets can be hashed in established or listening table +/* Sockets can be hashed in established or listening table. + * We must use different 'nulls' end-of-chain value for all hash buckets : + * A socket might transition from ESTABLISH to LISTEN state without + * RCU grace period. A lookup in ehash table needs to handle this case. */ +#define LISTENING_NULLS_BASE (1U << 29) struct inet_listen_hashbucket { spinlock_t lock; unsigned int count; - struct hlist_head head; + union { + struct hlist_head head; + struct hlist_nulls_head nulls_head; + }; }; /* This is for listening sockets, thus all sockets which possess wildcards. */ diff --git a/include/net/ip.h b/include/net/ip.h index a2c61c36dc4a..4b15cc1c224c 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -760,4 +760,9 @@ int ip_misc_proc_init(void); int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, u8 family, struct netlink_ext_ack *extack); +static inline bool inetdev_valid_mtu(unsigned int mtu) +{ + return likely(mtu >= IPV4_MIN_MTU); +} + #endif /* _IP_H */ diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 009605c56f20..b59b3dae0f71 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -1017,7 +1017,7 @@ static inline struct sk_buff *ip6_finish_skb(struct sock *sk) int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6); -struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6, +struct dst_entry *ip6_dst_lookup_flow(struct net *net, const struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst); struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst, diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h index 5c93e942c50b..3e7d2c0e79ca 100644 --- a/include/net/ipv6_stubs.h +++ b/include/net/ipv6_stubs.h @@ -24,8 +24,10 @@ struct ipv6_stub { const struct in6_addr *addr); int (*ipv6_sock_mc_drop)(struct sock *sk, int ifindex, const struct in6_addr *addr); - int (*ipv6_dst_lookup)(struct net *net, struct sock *sk, - struct dst_entry **dst, struct flowi6 *fl6); + struct dst_entry *(*ipv6_dst_lookup_flow)(struct net *net, + const struct sock *sk, + struct flowi6 *fl6, + const struct in6_addr *final_dst); int (*ipv6_route_input)(struct sk_buff *skb); struct fib6_table *(*fib6_get_table)(struct net *net, u32 id); diff --git a/include/net/ndisc.h b/include/net/ndisc.h index b2f715ca0567..b5ebeb3b0de0 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -414,8 +414,8 @@ static inline void __ipv6_confirm_neigh(struct net_device *dev, unsigned long now = jiffies; /* avoid dirtying neighbour */ - if (n->confirmed != now) - n->confirmed = now; + if (READ_ONCE(n->confirmed) != now) + WRITE_ONCE(n->confirmed, now); } rcu_read_unlock_bh(); } @@ -431,8 +431,8 @@ static inline void __ipv6_confirm_neigh_stub(struct net_device *dev, unsigned long now = jiffies; /* avoid dirtying neighbour */ - if (n->confirmed != now) - n->confirmed = now; + if (READ_ONCE(n->confirmed) != now) + WRITE_ONCE(n->confirmed, now); } rcu_read_unlock_bh(); } diff --git a/include/net/neighbour.h b/include/net/neighbour.h index b8452cc0e059..8ec77bfdc1a4 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -72,7 +72,6 @@ struct neigh_parms { struct net_device *dev; struct list_head list; int (*neigh_setup)(struct neighbour *); - void (*neigh_cleanup)(struct neighbour *); struct neigh_table *tbl; void *sysctl_table; @@ -468,7 +467,7 @@ static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb do { seq = read_seqbegin(&hh->hh_lock); - hh_len = hh->hh_len; + hh_len = READ_ONCE(hh->hh_len); if (likely(hh_len <= HH_DATA_MOD)) { hh_alen = HH_DATA_MOD; diff --git a/include/net/page_pool.h b/include/net/page_pool.h index 2cbcdbdec254..1121faa99c12 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -70,7 +70,12 @@ struct page_pool_params { struct page_pool { struct page_pool_params p; - u32 pages_state_hold_cnt; + struct delayed_work release_dw; + void (*disconnect)(void *); + unsigned long defer_start; + unsigned long defer_warn; + + u32 pages_state_hold_cnt; /* * Data structure for allocation side @@ -129,25 +134,19 @@ inline enum dma_data_direction page_pool_get_dma_dir(struct page_pool *pool) struct page_pool *page_pool_create(const struct page_pool_params *params); -void __page_pool_free(struct page_pool *pool); -static inline void page_pool_free(struct page_pool *pool) -{ - /* When page_pool isn't compiled-in, net/core/xdp.c doesn't - * allow registering MEM_TYPE_PAGE_POOL, but shield linker. - */ #ifdef CONFIG_PAGE_POOL - __page_pool_free(pool); -#endif -} - -/* Drivers use this instead of page_pool_free */ +void page_pool_destroy(struct page_pool *pool); +void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *)); +#else static inline void page_pool_destroy(struct page_pool *pool) { - if (!pool) - return; +} - page_pool_free(pool); +static inline void page_pool_use_xdp_mem(struct page_pool *pool, + void (*disconnect)(void *)) +{ } +#endif /* Never call this directly, use helpers below */ void __page_pool_put_page(struct page_pool *pool, @@ -170,24 +169,6 @@ static inline void page_pool_recycle_direct(struct page_pool *pool, __page_pool_put_page(pool, page, true); } -/* API user MUST have disconnected alloc-side (not allowed to call - * page_pool_alloc_pages()) before calling this. The free-side can - * still run concurrently, to handle in-flight packet-pages. - * - * A request to shutdown can fail (with false) if there are still - * in-flight packet-pages. - */ -bool __page_pool_request_shutdown(struct page_pool *pool); -static inline bool page_pool_request_shutdown(struct page_pool *pool) -{ - bool safe_to_remove = false; - -#ifdef CONFIG_PAGE_POOL - safe_to_remove = __page_pool_request_shutdown(pool); -#endif - return safe_to_remove; -} - /* Disconnects a page (from a page_pool). API users can have a need * to disconnect a page (from a page_pool), to allow it to be used as * a regular page (that will eventually be returned to the normal @@ -216,11 +197,6 @@ static inline bool is_page_pool_compiled_in(void) #endif } -static inline void page_pool_get(struct page_pool *pool) -{ - refcount_inc(&pool->user_cnt); -} - static inline bool page_pool_put(struct page_pool *pool) { return refcount_dec_and_test(&pool->user_cnt); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index d80acda231ae..32e418dba133 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -149,8 +149,8 @@ static inline bool qdisc_is_percpu_stats(const struct Qdisc *q) static inline bool qdisc_is_empty(const struct Qdisc *qdisc) { if (qdisc_is_percpu_stats(qdisc)) - return qdisc->empty; - return !qdisc->q.qlen; + return READ_ONCE(qdisc->empty); + return !READ_ONCE(qdisc->q.qlen); } static inline bool qdisc_run_begin(struct Qdisc *qdisc) @@ -158,7 +158,7 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc) if (qdisc->flags & TCQ_F_NOLOCK) { if (!spin_trylock(&qdisc->seqlock)) return false; - qdisc->empty = false; + WRITE_ONCE(qdisc->empty, false); } else if (qdisc_is_running(qdisc)) { return false; } @@ -308,6 +308,7 @@ struct tcf_proto_ops { int (*delete)(struct tcf_proto *tp, void *arg, bool *last, bool rtnl_held, struct netlink_ext_ack *); + bool (*delete_empty)(struct tcf_proto *tp); void (*walk)(struct tcf_proto *tp, struct tcf_walker *arg, bool rtnl_held); int (*reoffload)(struct tcf_proto *tp, bool add, @@ -336,6 +337,10 @@ struct tcf_proto_ops { int flags; }; +/* Classifiers setting TCF_PROTO_OPS_DOIT_UNLOCKED in tcf_proto_ops->flags + * are expected to implement tcf_proto_ops->delete_empty(), otherwise race + * conditions can occur when filters are inserted/deleted simultaneously. + */ enum tcf_proto_ops_flags { TCF_PROTO_OPS_DOIT_UNLOCKED = 1, }; diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 503fbc3cd819..2b6f3f13d5bc 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1239,6 +1239,9 @@ struct sctp_ep_common { /* What socket does this endpoint belong to? */ struct sock *sk; + /* Cache netns and it won't change once set */ + struct net *net; + /* This is where we receive inbound chunks. */ struct sctp_inq inqueue; diff --git a/include/net/sock.h b/include/net/sock.h index 718e62fbe869..6c5a3809483e 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -723,6 +723,11 @@ static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_h hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list); } +static inline void __sk_nulls_add_node_tail_rcu(struct sock *sk, struct hlist_nulls_head *list) +{ + hlist_nulls_add_tail_rcu(&sk->sk_nulls_node, list); +} + static inline void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list) { sock_hold(sk); @@ -1940,8 +1945,8 @@ struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie); static inline void sk_dst_confirm(struct sock *sk) { - if (!sk->sk_dst_pending_confirm) - sk->sk_dst_pending_confirm = 1; + if (!READ_ONCE(sk->sk_dst_pending_confirm)) + WRITE_ONCE(sk->sk_dst_pending_confirm, 1); } static inline void sock_confirm_neigh(struct sk_buff *skb, struct neighbour *n) @@ -1951,10 +1956,10 @@ static inline void sock_confirm_neigh(struct sk_buff *skb, struct neighbour *n) unsigned long now = jiffies; /* avoid dirtying neighbour */ - if (n->confirmed != now) - n->confirmed = now; - if (sk && sk->sk_dst_pending_confirm) - sk->sk_dst_pending_confirm = 0; + if (READ_ONCE(n->confirmed) != now) + WRITE_ONCE(n->confirmed, now); + if (sk && READ_ONCE(sk->sk_dst_pending_confirm)) + WRITE_ONCE(sk->sk_dst_pending_confirm, 0); } } @@ -2584,9 +2589,9 @@ static inline int sk_get_rmem0(const struct sock *sk, const struct proto *proto) */ static inline void sk_pacing_shift_update(struct sock *sk, int val) { - if (!sk || !sk_fullsock(sk) || sk->sk_pacing_shift == val) + if (!sk || !sk_fullsock(sk) || READ_ONCE(sk->sk_pacing_shift) == val) return; - sk->sk_pacing_shift = val; + WRITE_ONCE(sk->sk_pacing_shift, val); } /* if a socket is bound to a device, check that the given device diff --git a/include/net/tcp.h b/include/net/tcp.h index ab4eb5eb5d07..b2367cfe0bda 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -494,15 +494,16 @@ static inline void tcp_synq_overflow(const struct sock *sk) reuse = rcu_dereference(sk->sk_reuseport_cb); if (likely(reuse)) { last_overflow = READ_ONCE(reuse->synq_overflow_ts); - if (time_after32(now, last_overflow + HZ)) + if (!time_between32(now, last_overflow, + last_overflow + HZ)) WRITE_ONCE(reuse->synq_overflow_ts, now); return; } } - last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp; - if (time_after32(now, last_overflow + HZ)) - tcp_sk(sk)->rx_opt.ts_recent_stamp = now; + last_overflow = READ_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp); + if (!time_between32(now, last_overflow, last_overflow + HZ)) + WRITE_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp, now); } /* syncookies: no recent synqueue overflow on this listening socket? */ @@ -517,13 +518,23 @@ static inline bool tcp_synq_no_recent_overflow(const struct sock *sk) reuse = rcu_dereference(sk->sk_reuseport_cb); if (likely(reuse)) { last_overflow = READ_ONCE(reuse->synq_overflow_ts); - return time_after32(now, last_overflow + - TCP_SYNCOOKIE_VALID); + return !time_between32(now, last_overflow - HZ, + last_overflow + + TCP_SYNCOOKIE_VALID); } } - last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp; - return time_after32(now, last_overflow + TCP_SYNCOOKIE_VALID); + last_overflow = READ_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp); + + /* If last_overflow <= jiffies <= last_overflow + TCP_SYNCOOKIE_VALID, + * then we're under synflood. However, we have to use + * 'last_overflow - HZ' as lower bound. That's because a concurrent + * tcp_synq_overflow() could update .ts_recent_stamp after we read + * jiffies but before we store .ts_recent_stamp into last_overflow, + * which could lead to rejecting a valid syncookie. + */ + return !time_between32(now, last_overflow - HZ, + last_overflow + TCP_SYNCOOKIE_VALID); } static inline u32 tcp_cookie_time(void) diff --git a/include/net/tls.h b/include/net/tls.h index f4ad831eaa02..093abb5a3dff 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -122,7 +122,6 @@ struct tls_rec { struct list_head list; int tx_ready; int tx_flags; - int inplace_crypto; struct sk_msg msg_plaintext; struct sk_msg msg_encrypted; @@ -396,7 +395,7 @@ int tls_push_sg(struct sock *sk, struct tls_context *ctx, int flags); int tls_push_partial_record(struct sock *sk, struct tls_context *ctx, int flags); -bool tls_free_partial_record(struct sock *sk, struct tls_context *ctx); +void tls_free_partial_record(struct sock *sk, struct tls_context *ctx); static inline struct tls_msg *tls_msg(struct sk_buff *skb) { diff --git a/include/net/xdp_priv.h b/include/net/xdp_priv.h index 6a8cba6ea79a..a9d5b7603b89 100644 --- a/include/net/xdp_priv.h +++ b/include/net/xdp_priv.h @@ -12,12 +12,8 @@ struct xdp_mem_allocator { struct page_pool *page_pool; struct zero_copy_allocator *zc_alloc; }; - int disconnect_cnt; - unsigned long defer_start; struct rhash_head node; struct rcu_head rcu; - struct delayed_work defer_wq; - unsigned long defer_warn; }; #endif /* __LINUX_NET_XDP_PRIV_H__ */ diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index e7e733add99f..44c52639db55 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -4043,9 +4043,7 @@ static inline void ib_dma_unmap_sg_attrs(struct ib_device *dev, */ static inline unsigned int ib_dma_max_seg_size(struct ib_device *dev) { - struct device_dma_parameters *p = dev->dma_device->dma_parms; - - return p ? p->max_segment_size : UINT_MAX; + return dma_get_max_seg_size(dev->dma_device); } /** diff --git a/include/scsi/iscsi_proto.h b/include/scsi/iscsi_proto.h index b71b5c4f418c..533f56733ba8 100644 --- a/include/scsi/iscsi_proto.h +++ b/include/scsi/iscsi_proto.h @@ -627,6 +627,7 @@ struct iscsi_reject { #define ISCSI_REASON_BOOKMARK_INVALID 9 #define ISCSI_REASON_BOOKMARK_NO_RESOURCES 10 #define ISCSI_REASON_NEGOTIATION_RESET 11 +#define ISCSI_REASON_WAITING_FOR_LOGOUT 12 /* Max. number of Key=Value pairs in a text message */ #define MAX_KEY_VALUE_PAIRS 8192 diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h index b260c5fd2337..e05b95e83d5a 100644 --- a/include/sound/hdaudio.h +++ b/include/sound/hdaudio.h @@ -493,6 +493,7 @@ struct hdac_stream { bool prepared:1; bool no_period_wakeup:1; bool locked:1; + bool stripe:1; /* apply stripe control */ /* timestamp */ unsigned long start_wallclk; /* start + minimum wallclk */ diff --git a/include/sound/simple_card_utils.h b/include/sound/simple_card_utils.h index 31f76b6abf71..bbdd1542d6f1 100644 --- a/include/sound/simple_card_utils.h +++ b/include/sound/simple_card_utils.h @@ -8,6 +8,7 @@ #ifndef __SIMPLE_CARD_UTILS_H #define __SIMPLE_CARD_UTILS_H +#include #include #define asoc_simple_init_hp(card, sjack, prefix) \ diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h index d5ec4fac82ae..564ba1b5cf57 100644 --- a/include/trace/events/afs.h +++ b/include/trace/events/afs.h @@ -915,9 +915,9 @@ TRACE_EVENT(afs_call_state, TRACE_EVENT(afs_lookup, TP_PROTO(struct afs_vnode *dvnode, const struct qstr *name, - struct afs_vnode *vnode), + struct afs_fid *fid), - TP_ARGS(dvnode, name, vnode), + TP_ARGS(dvnode, name, fid), TP_STRUCT__entry( __field_struct(struct afs_fid, dfid ) @@ -928,13 +928,7 @@ TRACE_EVENT(afs_lookup, TP_fast_assign( int __len = min_t(int, name->len, 23); __entry->dfid = dvnode->fid; - if (vnode) { - __entry->fid = vnode->fid; - } else { - __entry->fid.vid = 0; - __entry->fid.vnode = 0; - __entry->fid.unique = 0; - } + __entry->fid = *fid; memcpy(__entry->name, name->name, __len); __entry->name[__len] = 0; ), diff --git a/include/trace/events/preemptirq.h b/include/trace/events/preemptirq.h index 95fba0471e5b..3f249e150c0c 100644 --- a/include/trace/events/preemptirq.h +++ b/include/trace/events/preemptirq.h @@ -18,13 +18,13 @@ DECLARE_EVENT_CLASS(preemptirq_template, TP_ARGS(ip, parent_ip), TP_STRUCT__entry( - __field(u32, caller_offs) - __field(u32, parent_offs) + __field(s32, caller_offs) + __field(s32, parent_offs) ), TP_fast_assign( - __entry->caller_offs = (u32)(ip - (unsigned long)_stext); - __entry->parent_offs = (u32)(parent_ip - (unsigned long)_stext); + __entry->caller_offs = (s32)(ip - (unsigned long)_stext); + __entry->parent_offs = (s32)(parent_ip - (unsigned long)_stext); ), TP_printk("caller=%pS parent=%pS", diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index a13830616107..7fd11ec1c9a4 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -735,6 +735,31 @@ TRACE_EVENT(xprtrdma_post_recvs, ) ); +TRACE_EVENT(xprtrdma_post_linv, + TP_PROTO( + const struct rpcrdma_req *req, + int status + ), + + TP_ARGS(req, status), + + TP_STRUCT__entry( + __field(const void *, req) + __field(int, status) + __field(u32, xid) + ), + + TP_fast_assign( + __entry->req = req; + __entry->status = status; + __entry->xid = be32_to_cpu(req->rl_slot.rq_xid); + ), + + TP_printk("req=%p xid=0x%08x status=%d", + __entry->req, __entry->xid, __entry->status + ) +); + /** ** Completion events **/ diff --git a/include/trace/events/wbt.h b/include/trace/events/wbt.h index b048694070e2..37342a13c9cb 100644 --- a/include/trace/events/wbt.h +++ b/include/trace/events/wbt.h @@ -33,7 +33,8 @@ TRACE_EVENT(wbt_stat, ), TP_fast_assign( - strncpy(__entry->name, dev_name(bdi->dev), 32); + strlcpy(__entry->name, dev_name(bdi->dev), + ARRAY_SIZE(__entry->name)); __entry->rmean = stat[0].mean; __entry->rmin = stat[0].min; __entry->rmax = stat[0].max; @@ -67,7 +68,8 @@ TRACE_EVENT(wbt_lat, ), TP_fast_assign( - strncpy(__entry->name, dev_name(bdi->dev), 32); + strlcpy(__entry->name, dev_name(bdi->dev), + ARRAY_SIZE(__entry->name)); __entry->lat = div_u64(lat, 1000); ), @@ -103,7 +105,8 @@ TRACE_EVENT(wbt_step, ), TP_fast_assign( - strncpy(__entry->name, dev_name(bdi->dev), 32); + strlcpy(__entry->name, dev_name(bdi->dev), + ARRAY_SIZE(__entry->name)); __entry->msg = msg; __entry->step = step; __entry->window = div_u64(window, 1000); @@ -138,7 +141,8 @@ TRACE_EVENT(wbt_timer, ), TP_fast_assign( - strncpy(__entry->name, dev_name(bdi->dev), 32); + strlcpy(__entry->name, dev_name(bdi->dev), + ARRAY_SIZE(__entry->name)); __entry->status = status; __entry->step = step; __entry->inflight = inflight; diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h index 8c8420230a10..c79943e82a54 100644 --- a/include/trace/events/xdp.h +++ b/include/trace/events/xdp.h @@ -317,19 +317,15 @@ __MEM_TYPE_MAP(__MEM_TYPE_TP_FN) TRACE_EVENT(mem_disconnect, - TP_PROTO(const struct xdp_mem_allocator *xa, - bool safe_to_remove, bool force), + TP_PROTO(const struct xdp_mem_allocator *xa), - TP_ARGS(xa, safe_to_remove, force), + TP_ARGS(xa), TP_STRUCT__entry( __field(const struct xdp_mem_allocator *, xa) __field(u32, mem_id) __field(u32, mem_type) __field(const void *, allocator) - __field(bool, safe_to_remove) - __field(bool, force) - __field(int, disconnect_cnt) ), TP_fast_assign( @@ -337,19 +333,12 @@ TRACE_EVENT(mem_disconnect, __entry->mem_id = xa->mem.id; __entry->mem_type = xa->mem.type; __entry->allocator = xa->allocator; - __entry->safe_to_remove = safe_to_remove; - __entry->force = force; - __entry->disconnect_cnt = xa->disconnect_cnt; ), - TP_printk("mem_id=%d mem_type=%s allocator=%p" - " safe_to_remove=%s force=%s disconnect_cnt=%d", + TP_printk("mem_id=%d mem_type=%s allocator=%p", __entry->mem_id, __print_symbolic(__entry->mem_type, __MEM_TYPE_SYM_TAB), - __entry->allocator, - __entry->safe_to_remove ? "true" : "false", - __entry->force ? "true" : "false", - __entry->disconnect_cnt + __entry->allocator ) ); diff --git a/include/uapi/linux/cec-funcs.h b/include/uapi/linux/cec-funcs.h index 8997d5068c08..4511b85c84df 100644 --- a/include/uapi/linux/cec-funcs.h +++ b/include/uapi/linux/cec-funcs.h @@ -923,7 +923,8 @@ static inline void cec_msg_give_deck_status(struct cec_msg *msg, msg->len = 3; msg->msg[1] = CEC_MSG_GIVE_DECK_STATUS; msg->msg[2] = status_req; - msg->reply = reply ? CEC_MSG_DECK_STATUS : 0; + msg->reply = (reply && status_req != CEC_OP_STATUS_REQ_OFF) ? + CEC_MSG_DECK_STATUS : 0; } static inline void cec_ops_give_deck_status(const struct cec_msg *msg, @@ -1027,7 +1028,8 @@ static inline void cec_msg_give_tuner_device_status(struct cec_msg *msg, msg->len = 3; msg->msg[1] = CEC_MSG_GIVE_TUNER_DEVICE_STATUS; msg->msg[2] = status_req; - msg->reply = reply ? CEC_MSG_TUNER_DEVICE_STATUS : 0; + msg->reply = (reply && status_req != CEC_OP_STATUS_REQ_OFF) ? + CEC_MSG_TUNER_DEVICE_STATUS : 0; } static inline void cec_ops_give_tuner_device_status(const struct cec_msg *msg, diff --git a/include/uapi/linux/cec.h b/include/uapi/linux/cec.h index 5704fa0292b5..423859e489c7 100644 --- a/include/uapi/linux/cec.h +++ b/include/uapi/linux/cec.h @@ -768,8 +768,8 @@ struct cec_event { #define CEC_MSG_SELECT_DIGITAL_SERVICE 0x93 #define CEC_MSG_TUNER_DEVICE_STATUS 0x07 /* Recording Flag Operand (rec_flag) */ -#define CEC_OP_REC_FLAG_USED 0 -#define CEC_OP_REC_FLAG_NOT_USED 1 +#define CEC_OP_REC_FLAG_NOT_USED 0 +#define CEC_OP_REC_FLAG_USED 1 /* Tuner Display Info Operand (tuner_display_info) */ #define CEC_OP_TUNER_DISPLAY_INFO_DIGITAL 0 #define CEC_OP_TUNER_DISPLAY_INFO_NONE 1 diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h index f056b2a00d5c..9a61c28ed3ae 100644 --- a/include/uapi/linux/input.h +++ b/include/uapi/linux/input.h @@ -34,6 +34,7 @@ struct input_event { __kernel_ulong_t __sec; #if defined(__sparc__) && defined(__arch64__) unsigned int __usec; + unsigned int __pad; #else __kernel_ulong_t __usec; #endif diff --git a/include/uapi/linux/netfilter/xt_sctp.h b/include/uapi/linux/netfilter/xt_sctp.h index 4bc6d1a08781..b4d804a9fccb 100644 --- a/include/uapi/linux/netfilter/xt_sctp.h +++ b/include/uapi/linux/netfilter/xt_sctp.h @@ -41,19 +41,19 @@ struct xt_sctp_info { #define SCTP_CHUNKMAP_SET(chunkmap, type) \ do { \ (chunkmap)[type / bytes(__u32)] |= \ - 1 << (type % bytes(__u32)); \ + 1u << (type % bytes(__u32)); \ } while (0) #define SCTP_CHUNKMAP_CLEAR(chunkmap, type) \ do { \ (chunkmap)[type / bytes(__u32)] &= \ - ~(1 << (type % bytes(__u32))); \ + ~(1u << (type % bytes(__u32))); \ } while (0) #define SCTP_CHUNKMAP_IS_SET(chunkmap, type) \ ({ \ ((chunkmap)[type / bytes (__u32)] & \ - (1 << (type % bytes (__u32)))) ? 1: 0; \ + (1u << (type % bytes (__u32)))) ? 1: 0; \ }) #define SCTP_CHUNKMAP_RESET(chunkmap) \ diff --git a/include/uapi/rdma/nes-abi.h b/include/uapi/rdma/nes-abi.h deleted file mode 100644 index f80495baa969..000000000000 --- a/include/uapi/rdma/nes-abi.h +++ /dev/null @@ -1,115 +0,0 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */ -/* - * Copyright (c) 2006 - 2011 Intel Corporation. All rights reserved. - * Copyright (c) 2005 Topspin Communications. All rights reserved. - * Copyright (c) 2005 Cisco Systems. All rights reserved. - * Copyright (c) 2005 Open Grid Computing, Inc. All rights reserved. - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and/or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - * - */ - -#ifndef NES_ABI_USER_H -#define NES_ABI_USER_H - -#include - -#define NES_ABI_USERSPACE_VER 2 -#define NES_ABI_KERNEL_VER 2 - -/* - * Make sure that all structs defined in this file remain laid out so - * that they pack the same way on 32-bit and 64-bit architectures (to - * avoid incompatibility between 32-bit userspace and 64-bit kernels). - * In particular do not use pointer types -- pass pointers in __u64 - * instead. - */ - -struct nes_alloc_ucontext_req { - __u32 reserved32; - __u8 userspace_ver; - __u8 reserved8[3]; -}; - -struct nes_alloc_ucontext_resp { - __u32 max_pds; /* maximum pds allowed for this user process */ - __u32 max_qps; /* maximum qps allowed for this user process */ - __u32 wq_size; /* size of the WQs (sq+rq) allocated to the mmaped area */ - __u8 virtwq; /* flag to indicate if virtual WQ are to be used or not */ - __u8 kernel_ver; - __u8 reserved[2]; -}; - -struct nes_alloc_pd_resp { - __u32 pd_id; - __u32 mmap_db_index; -}; - -struct nes_create_cq_req { - __aligned_u64 user_cq_buffer; - __u32 mcrqf; - __u8 reserved[4]; -}; - -struct nes_create_qp_req { - __aligned_u64 user_wqe_buffers; - __aligned_u64 user_qp_buffer; -}; - -enum iwnes_memreg_type { - IWNES_MEMREG_TYPE_MEM = 0x0000, - IWNES_MEMREG_TYPE_QP = 0x0001, - IWNES_MEMREG_TYPE_CQ = 0x0002, - IWNES_MEMREG_TYPE_MW = 0x0003, - IWNES_MEMREG_TYPE_FMR = 0x0004, - IWNES_MEMREG_TYPE_FMEM = 0x0005, -}; - -struct nes_mem_reg_req { - __u32 reg_type; /* indicates if id is memory, QP or CQ */ - __u32 reserved; -}; - -struct nes_create_cq_resp { - __u32 cq_id; - __u32 cq_size; - __u32 mmap_db_index; - __u32 reserved; -}; - -struct nes_create_qp_resp { - __u32 qp_id; - __u32 actual_sq_size; - __u32 actual_rq_size; - __u32 mmap_sq_db_index; - __u32 mmap_rq_db_index; - __u32 nes_drv_opt; -}; - -#endif /* NES_ABI_USER_H */ diff --git a/init/Kconfig b/init/Kconfig index b4daad2bac23..3c29ad2ebda9 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -717,9 +717,28 @@ config GENERIC_SCHED_CLOCK menu "Scheduler features" +config SCHED_BMQ + bool "BMQ CPU scheduler" + help + The BitMap Queue CPU scheduler for excellent interactivity and + responsiveness on the desktop and solid scalability on normal + hardware and commodity servers. + + Say Y here. + default y + +config SCHED_TIMESLICE + int "Scheduler Task time slice" + depends on SCHED_BMQ + help + Time slice in ms for BMQ CPU scheduler, default 4 ms. + default 2 if PREEMPT + default 4 if !PREEMPT + config UCLAMP_TASK bool "Enable utilization clamping for RT/FAIR tasks" depends on CPU_FREQ_GOV_SCHEDUTIL + depends on !SCHED_BMQ help This feature enables the scheduler to track the clamped utilization of each CPU based on RUNNABLE tasks scheduled on that CPU. @@ -802,6 +821,7 @@ config NUMA_BALANCING depends on ARCH_SUPPORTS_NUMA_BALANCING depends on !ARCH_WANT_NUMA_VARIABLE_LOCALITY depends on SMP && NUMA && MIGRATION + depends on !SCHED_BMQ help This option adds support for automatic NUMA aware memory/task placement. The mechanism is quite primitive and is based on migrating memory when @@ -903,7 +923,7 @@ menuconfig CGROUP_SCHED bandwidth allocation to such task groups. It uses cgroups to group tasks. -if CGROUP_SCHED +if CGROUP_SCHED && !SCHED_BMQ config FAIR_GROUP_SCHED bool "Group scheduling for SCHED_OTHER" depends on CGROUP_SCHED @@ -1118,6 +1138,22 @@ config USER_NS If unsure, say N. +config USER_NS_UNPRIVILEGED + bool "Allow unprivileged users to create namespaces" + default y + depends on USER_NS + help + When disabled, unprivileged users will not be able to create + new namespaces. Allowing users to create their own namespaces + has been part of several recent local privilege escalation + exploits, so if you need user namespaces but are + paranoid^Wsecurity-conscious you want to disable this. + + This setting can be overridden at runtime via the + kernel.unprivileged_userns_clone sysctl. + + If unsure, say Y. + config PID_NS bool "PID Namespaces" default y @@ -1150,6 +1186,7 @@ config CHECKPOINT_RESTORE config SCHED_AUTOGROUP bool "Automatic process group scheduling" + depends on !SCHED_BMQ select CGROUPS select CGROUP_SCHED select FAIR_GROUP_SCHED @@ -1244,7 +1281,6 @@ config CC_OPTIMIZE_FOR_PERFORMANCE config CC_OPTIMIZE_FOR_PERFORMANCE_O3 bool "Optimize more for performance (-O3)" - depends on ARC imply CC_DISABLE_WARN_MAYBE_UNINITIALIZED # avoid false positives help Choosing this option will pass "-O3" to your compiler to optimize diff --git a/init/init_task.c b/init/init_task.c index 9e5cbe5eab7b..c293de91d90f 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -66,9 +66,15 @@ struct task_struct init_task .stack = init_stack, .usage = REFCOUNT_INIT(2), .flags = PF_KTHREAD, +#ifdef CONFIG_SCHED_BMQ + .prio = DEFAULT_PRIO + MAX_PRIORITY_ADJ, + .static_prio = DEFAULT_PRIO, + .normal_prio = DEFAULT_PRIO + MAX_PRIORITY_ADJ, +#else .prio = MAX_PRIO - 20, .static_prio = MAX_PRIO - 20, .normal_prio = MAX_PRIO - 20, +#endif .policy = SCHED_NORMAL, .cpus_ptr = &init_task.cpus_mask, .cpus_mask = CPU_MASK_ALL, @@ -78,6 +84,12 @@ struct task_struct init_task .restart_block = { .fn = do_no_restart_syscall, }, +#ifdef CONFIG_SCHED_BMQ + .boost_prio = 0, + .bmq_idx = 15, + .bmq_node = LIST_HEAD_INIT(init_task.bmq_node), + .time_slice = HZ, +#else .se = { .group_node = LIST_HEAD_INIT(init_task.se.group_node), }, @@ -85,6 +97,7 @@ struct task_struct init_task .run_list = LIST_HEAD_INIT(init_task.rt.run_list), .time_slice = RR_TIMESLICE, }, +#endif .tasks = LIST_HEAD_INIT(init_task.tasks), #ifdef CONFIG_SMP .pushable_tasks = PLIST_NODE_INIT(init_task.pushable_tasks, MAX_PRIO), diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index a3eaf08e7dd3..8bd69062fbe5 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -35,8 +35,8 @@ void cgroup_bpf_offline(struct cgroup *cgrp) */ static void cgroup_bpf_release(struct work_struct *work) { - struct cgroup *cgrp = container_of(work, struct cgroup, - bpf.release_work); + struct cgroup *p, *cgrp = container_of(work, struct cgroup, + bpf.release_work); enum bpf_cgroup_storage_type stype; struct bpf_prog_array *old_array; unsigned int type; @@ -65,6 +65,9 @@ static void cgroup_bpf_release(struct work_struct *work) mutex_unlock(&cgroup_mutex); + for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p)) + cgroup_bpf_put(p); + percpu_ref_exit(&cgrp->bpf.refcnt); cgroup_put(cgrp); } @@ -199,6 +202,7 @@ int cgroup_bpf_inherit(struct cgroup *cgrp) */ #define NR ARRAY_SIZE(cgrp->bpf.effective) struct bpf_prog_array *arrays[NR] = {}; + struct cgroup *p; int ret, i; ret = percpu_ref_init(&cgrp->bpf.refcnt, cgroup_bpf_release_fn, 0, @@ -206,6 +210,9 @@ int cgroup_bpf_inherit(struct cgroup *cgrp) if (ret) return ret; + for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p)) + cgroup_bpf_get(p); + for (i = 0; i < NR; i++) INIT_LIST_HEAD(&cgrp->bpf.progs[i]); diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 052580c33d26..173e983619d7 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -287,7 +287,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, bool irq_work_busy = false; struct stack_map_irq_work *work = NULL; - if (in_nmi()) { + if (irqs_disabled()) { work = this_cpu_ptr(&up_read_work); if (work->irq_work.flags & IRQ_WORK_BUSY) /* cannot queue more up_read, fallback */ @@ -295,8 +295,9 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, } /* - * We cannot do up_read() in nmi context. To do build_id lookup - * in nmi context, we need to run up_read() in irq_work. We use + * We cannot do up_read() when the irq is disabled, because of + * risk to deadlock with rq_lock. To do build_id lookup when the + * irqs are disabled, we need to run up_read() in irq_work. We use * a percpu variable to do the irq_work. If the irq_work is * already used by another lookup, we fall back to report ips. * diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index ffc3e53f5300..9c74c98f6501 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -852,7 +852,8 @@ static const int caller_saved[CALLER_SAVED_REGS] = { BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5 }; -static void __mark_reg_not_init(struct bpf_reg_state *reg); +static void __mark_reg_not_init(const struct bpf_verifier_env *env, + struct bpf_reg_state *reg); /* Mark the unknown part of a register (variable offset or scalar value) as * known to have the value @imm. @@ -890,7 +891,7 @@ static void mark_reg_known_zero(struct bpf_verifier_env *env, verbose(env, "mark_reg_known_zero(regs, %u)\n", regno); /* Something bad happened, let's kill all regs */ for (regno = 0; regno < MAX_BPF_REG; regno++) - __mark_reg_not_init(regs + regno); + __mark_reg_not_init(env, regs + regno); return; } __mark_reg_known_zero(regs + regno); @@ -978,6 +979,17 @@ static void __reg_bound_offset(struct bpf_reg_state *reg) reg->umax_value)); } +static void __reg_bound_offset32(struct bpf_reg_state *reg) +{ + u64 mask = 0xffffFFFF; + struct tnum range = tnum_range(reg->umin_value & mask, + reg->umax_value & mask); + struct tnum lo32 = tnum_cast(reg->var_off, 4); + struct tnum hi32 = tnum_lshift(tnum_rshift(reg->var_off, 32), 32); + + reg->var_off = tnum_or(hi32, tnum_intersect(lo32, range)); +} + /* Reset the min/max bounds of a register */ static void __mark_reg_unbounded(struct bpf_reg_state *reg) { @@ -988,7 +1000,8 @@ static void __mark_reg_unbounded(struct bpf_reg_state *reg) } /* Mark a register as having a completely unknown (scalar) value. */ -static void __mark_reg_unknown(struct bpf_reg_state *reg) +static void __mark_reg_unknown(const struct bpf_verifier_env *env, + struct bpf_reg_state *reg) { /* * Clear type, id, off, and union(map_ptr, range) and @@ -998,6 +1011,8 @@ static void __mark_reg_unknown(struct bpf_reg_state *reg) reg->type = SCALAR_VALUE; reg->var_off = tnum_unknown; reg->frameno = 0; + reg->precise = env->subprog_cnt > 1 || !env->allow_ptr_leaks ? + true : false; __mark_reg_unbounded(reg); } @@ -1008,19 +1023,16 @@ static void mark_reg_unknown(struct bpf_verifier_env *env, verbose(env, "mark_reg_unknown(regs, %u)\n", regno); /* Something bad happened, let's kill all regs except FP */ for (regno = 0; regno < BPF_REG_FP; regno++) - __mark_reg_not_init(regs + regno); + __mark_reg_not_init(env, regs + regno); return; } - regs += regno; - __mark_reg_unknown(regs); - /* constant backtracking is enabled for root without bpf2bpf calls */ - regs->precise = env->subprog_cnt > 1 || !env->allow_ptr_leaks ? - true : false; + __mark_reg_unknown(env, regs + regno); } -static void __mark_reg_not_init(struct bpf_reg_state *reg) +static void __mark_reg_not_init(const struct bpf_verifier_env *env, + struct bpf_reg_state *reg) { - __mark_reg_unknown(reg); + __mark_reg_unknown(env, reg); reg->type = NOT_INIT; } @@ -1031,10 +1043,10 @@ static void mark_reg_not_init(struct bpf_verifier_env *env, verbose(env, "mark_reg_not_init(regs, %u)\n", regno); /* Something bad happened, let's kill all regs except FP */ for (regno = 0; regno < BPF_REG_FP; regno++) - __mark_reg_not_init(regs + regno); + __mark_reg_not_init(env, regs + regno); return; } - __mark_reg_not_init(regs + regno); + __mark_reg_not_init(env, regs + regno); } #define DEF_NOT_SUBREG (0) @@ -3055,7 +3067,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, } if (state->stack[spi].slot_type[0] == STACK_SPILL && state->stack[spi].spilled_ptr.type == SCALAR_VALUE) { - __mark_reg_unknown(&state->stack[spi].spilled_ptr); + __mark_reg_unknown(env, &state->stack[spi].spilled_ptr); for (j = 0; j < BPF_REG_SIZE; j++) state->stack[spi].slot_type[j] = STACK_MISC; goto mark; @@ -3695,7 +3707,7 @@ static void __clear_all_pkt_pointers(struct bpf_verifier_env *env, if (!reg) continue; if (reg_is_pkt_pointer_any(reg)) - __mark_reg_unknown(reg); + __mark_reg_unknown(env, reg); } } @@ -3723,7 +3735,7 @@ static void release_reg_references(struct bpf_verifier_env *env, if (!reg) continue; if (reg->ref_obj_id == ref_obj_id) - __mark_reg_unknown(reg); + __mark_reg_unknown(env, reg); } } @@ -4346,7 +4358,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, /* Taint dst register if offset had invalid bounds derived from * e.g. dead branches. */ - __mark_reg_unknown(dst_reg); + __mark_reg_unknown(env, dst_reg); return 0; } @@ -4598,13 +4610,13 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, /* Taint dst register if offset had invalid bounds derived from * e.g. dead branches. */ - __mark_reg_unknown(dst_reg); + __mark_reg_unknown(env, dst_reg); return 0; } if (!src_known && opcode != BPF_ADD && opcode != BPF_SUB && opcode != BPF_AND) { - __mark_reg_unknown(dst_reg); + __mark_reg_unknown(env, dst_reg); return 0; } @@ -5433,6 +5445,10 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg, /* We might have learned some bits from the bounds. */ __reg_bound_offset(false_reg); __reg_bound_offset(true_reg); + if (is_jmp32) { + __reg_bound_offset32(false_reg); + __reg_bound_offset32(true_reg); + } /* Intersecting with the old var_off might have improved our bounds * slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc), * then new var_off is (0; 0x7f...fc) which improves our umax. @@ -5542,6 +5558,10 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg, /* We might have learned some bits from the bounds. */ __reg_bound_offset(false_reg); __reg_bound_offset(true_reg); + if (is_jmp32) { + __reg_bound_offset32(false_reg); + __reg_bound_offset32(true_reg); + } /* Intersecting with the old var_off might have improved our bounds * slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc), * then new var_off is (0; 0x7f...fc) which improves our umax. @@ -6019,6 +6039,7 @@ static bool may_access_skb(enum bpf_prog_type type) static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_reg_state *regs = cur_regs(env); + static const int ctx_reg = BPF_REG_6; u8 mode = BPF_MODE(insn->code); int i, err; @@ -6052,7 +6073,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) } /* check whether implicit source operand (register R6) is readable */ - err = check_reg_arg(env, BPF_REG_6, SRC_OP); + err = check_reg_arg(env, ctx_reg, SRC_OP); if (err) return err; @@ -6071,7 +6092,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return -EINVAL; } - if (regs[BPF_REG_6].type != PTR_TO_CTX) { + if (regs[ctx_reg].type != PTR_TO_CTX) { verbose(env, "at the time of BPF_LD_ABS|IND R6 != pointer to skb\n"); return -EINVAL; @@ -6084,6 +6105,10 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return err; } + err = check_ctx_reg(env, ®s[ctx_reg], ctx_reg); + if (err < 0) + return err; + /* reset caller saved regs to unreadable */ for (i = 0; i < CALLER_SAVED_REGS; i++) { mark_reg_not_init(env, regs, caller_saved[i]); @@ -6727,7 +6752,7 @@ static void clean_func_state(struct bpf_verifier_env *env, /* since the register is unused, clear its state * to make further comparison simpler */ - __mark_reg_not_init(&st->regs[i]); + __mark_reg_not_init(env, &st->regs[i]); } for (i = 0; i < st->allocated_stack / BPF_REG_SIZE; i++) { @@ -6735,7 +6760,7 @@ static void clean_func_state(struct bpf_verifier_env *env, /* liveness must not touch this stack slot anymore */ st->stack[i].spilled_ptr.live |= REG_LIVE_DONE; if (!(live & REG_LIVE_READ)) { - __mark_reg_not_init(&st->stack[i].spilled_ptr); + __mark_reg_not_init(env, &st->stack[i].spilled_ptr); for (j = 0; j < BPF_REG_SIZE; j++) st->stack[i].slot_type[j] = STACK_INVALID; } diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index ef4242e5d4bc..d1dbc6bf7fac 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -4060,6 +4060,7 @@ int cgroup_rm_cftypes(struct cftype *cfts) mutex_unlock(&cgroup_mutex); return ret; } +EXPORT_SYMBOL_GPL(cgroup_rm_cftypes); /** * cgroup_add_cftypes - add an array of cftypes to a subsystem @@ -4116,6 +4117,7 @@ int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) cft->flags |= __CFTYPE_ONLY_ON_DFL; return cgroup_add_cftypes(ss, cfts); } +EXPORT_SYMBOL_GPL(cgroup_add_dfl_cftypes); /** * cgroup_add_legacy_cftypes - add an array of cftypes for legacy hierarchies diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index c87ee6412b36..45fac7b9c940 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -632,7 +632,7 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial) return ret; } -#ifdef CONFIG_SMP +#if defined(CONFIG_SMP) && !defined(CONFIG_SCHED_BMQ) /* * Helper routine for generate_sched_domains(). * Do cpusets a, b have overlapping effective cpus_allowed masks? @@ -1007,7 +1007,7 @@ static void rebuild_sched_domains_locked(void) /* Have scheduler rebuild the domains */ partition_and_rebuild_sched_domains(ndoms, doms, attr); } -#else /* !CONFIG_SMP */ +#else /* !CONFIG_SMP || CONFIG_SCHED_BMQ */ static void rebuild_sched_domains_locked(void) { } diff --git a/kernel/cgroup/freezer.c b/kernel/cgroup/freezer.c index 8cf010680678..3984dd6b8ddb 100644 --- a/kernel/cgroup/freezer.c +++ b/kernel/cgroup/freezer.c @@ -230,6 +230,15 @@ void cgroup_freezer_migrate_task(struct task_struct *task, if (task->flags & PF_KTHREAD) return; + /* + * It's not necessary to do changes if both of the src and dst cgroups + * are not freezing and task is not frozen. + */ + if (!test_bit(CGRP_FREEZE, &src->flags) && + !test_bit(CGRP_FREEZE, &dst->flags) && + !task->frozen) + return; + /* * Adjust counters of freezing and frozen tasks. * Note, that if the task is frozen, but the destination cgroup is not diff --git a/kernel/cgroup/pids.c b/kernel/cgroup/pids.c index 8e513a573fe9..138059eb730d 100644 --- a/kernel/cgroup/pids.c +++ b/kernel/cgroup/pids.c @@ -45,7 +45,7 @@ struct pids_cgroup { * %PIDS_MAX = (%PID_MAX_LIMIT + 1). */ atomic64_t counter; - int64_t limit; + atomic64_t limit; /* Handle for "pids.events" */ struct cgroup_file events_file; @@ -73,8 +73,8 @@ pids_css_alloc(struct cgroup_subsys_state *parent) if (!pids) return ERR_PTR(-ENOMEM); - pids->limit = PIDS_MAX; atomic64_set(&pids->counter, 0); + atomic64_set(&pids->limit, PIDS_MAX); atomic64_set(&pids->events_limit, 0); return &pids->css; } @@ -146,13 +146,14 @@ static int pids_try_charge(struct pids_cgroup *pids, int num) for (p = pids; parent_pids(p); p = parent_pids(p)) { int64_t new = atomic64_add_return(num, &p->counter); + int64_t limit = atomic64_read(&p->limit); /* * Since new is capped to the maximum number of pid_t, if * p->limit is %PIDS_MAX then we know that this test will never * fail. */ - if (new > p->limit) + if (new > limit) goto revert; } @@ -277,7 +278,7 @@ static ssize_t pids_max_write(struct kernfs_open_file *of, char *buf, * Limit updates don't need to be mutex'd, since it isn't * critical that any racing fork()s follow the new limit. */ - pids->limit = limit; + atomic64_set(&pids->limit, limit); return nbytes; } @@ -285,7 +286,7 @@ static int pids_max_show(struct seq_file *sf, void *v) { struct cgroup_subsys_state *css = seq_css(sf); struct pids_cgroup *pids = css_pids(css); - int64_t limit = pids->limit; + int64_t limit = atomic64_read(&pids->limit); if (limit >= PIDS_MAX) seq_printf(sf, "%s\n", PIDS_MAX_STR); diff --git a/kernel/cred.c b/kernel/cred.c index c0a4c12d38b2..809a985b1793 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -175,8 +175,8 @@ void exit_creds(struct task_struct *tsk) put_cred(cred); #ifdef CONFIG_KEYS_REQUEST_CACHE - key_put(current->cached_requested_key); - current->cached_requested_key = NULL; + key_put(tsk->cached_requested_key); + tsk->cached_requested_key = NULL; #endif } @@ -223,7 +223,7 @@ struct cred *cred_alloc_blank(void) new->magic = CRED_MAGIC; #endif - if (security_cred_alloc_blank(new, GFP_KERNEL) < 0) + if (security_cred_alloc_blank(new, GFP_KERNEL_ACCOUNT) < 0) goto error; return new; @@ -282,7 +282,7 @@ struct cred *prepare_creds(void) new->security = NULL; #endif - if (security_prepare_creds(new, old, GFP_KERNEL) < 0) + if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0) goto error; validate_creds(new); return new; @@ -715,7 +715,7 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) #ifdef CONFIG_SECURITY new->security = NULL; #endif - if (security_prepare_creds(new, old, GFP_KERNEL) < 0) + if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0) goto error; put_cred(old); diff --git a/kernel/delayacct.c b/kernel/delayacct.c index 27725754ac99..769d773c7182 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -106,7 +106,7 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) */ t1 = tsk->sched_info.pcount; t2 = tsk->sched_info.run_delay; - t3 = tsk->se.sum_exec_runtime; + t3 = tsk_seruntime(tsk); d->cpu_count += t1; diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c index 545e3869b0e3..551b0eb7028a 100644 --- a/kernel/dma/coherent.c +++ b/kernel/dma/coherent.c @@ -123,8 +123,9 @@ int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr, return ret; } -static void *__dma_alloc_from_coherent(struct dma_coherent_mem *mem, - ssize_t size, dma_addr_t *dma_handle) +static void *__dma_alloc_from_coherent(struct device *dev, + struct dma_coherent_mem *mem, + ssize_t size, dma_addr_t *dma_handle) { int order = get_order(size); unsigned long flags; @@ -143,7 +144,7 @@ static void *__dma_alloc_from_coherent(struct dma_coherent_mem *mem, /* * Memory was found in the coherent area. */ - *dma_handle = mem->device_base + (pageno << PAGE_SHIFT); + *dma_handle = dma_get_device_base(dev, mem) + (pageno << PAGE_SHIFT); ret = mem->virt_base + (pageno << PAGE_SHIFT); spin_unlock_irqrestore(&mem->spinlock, flags); memset(ret, 0, size); @@ -175,17 +176,18 @@ int dma_alloc_from_dev_coherent(struct device *dev, ssize_t size, if (!mem) return 0; - *ret = __dma_alloc_from_coherent(mem, size, dma_handle); + *ret = __dma_alloc_from_coherent(dev, mem, size, dma_handle); return 1; } -void *dma_alloc_from_global_coherent(ssize_t size, dma_addr_t *dma_handle) +void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size, + dma_addr_t *dma_handle) { if (!dma_coherent_default_memory) return NULL; - return __dma_alloc_from_coherent(dma_coherent_default_memory, size, - dma_handle); + return __dma_alloc_from_coherent(dev, dma_coherent_default_memory, size, + dma_handle); } static int __dma_release_from_coherent(struct dma_coherent_mem *mem, diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index 099002d84f46..4ad74f5987ea 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -420,6 +420,7 @@ void debug_dma_dump_mappings(struct device *dev) } spin_unlock_irqrestore(&bucket->lock, flags); + cond_resched(); } } diff --git a/kernel/events/core.c b/kernel/events/core.c index 00a014670ed0..8f66a4833ded 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -5607,10 +5607,8 @@ static void perf_mmap_close(struct vm_area_struct *vma) perf_pmu_output_stop(event); /* now it's safe to free the pages */ - if (!rb->aux_mmap_locked) - atomic_long_sub(rb->aux_nr_pages, &mmap_user->locked_vm); - else - atomic64_sub(rb->aux_mmap_locked, &vma->vm_mm->pinned_vm); + atomic_long_sub(rb->aux_nr_pages - rb->aux_mmap_locked, &mmap_user->locked_vm); + atomic64_sub(rb->aux_mmap_locked, &vma->vm_mm->pinned_vm); /* this has to be the last one */ rb_free_aux(rb); diff --git a/kernel/exit.c b/kernel/exit.c index a46a50d67002..30b2fd6325fa 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -131,7 +131,7 @@ static void __exit_signal(struct task_struct *tsk) sig->curr_target = next_thread(tsk); } - add_device_randomness((const void*) &tsk->se.sum_exec_runtime, + add_device_randomness((const void*) &tsk_seruntime(tsk), sizeof(unsigned long long)); /* @@ -152,7 +152,7 @@ static void __exit_signal(struct task_struct *tsk) sig->inblock += task_io_get_inblock(tsk); sig->oublock += task_io_get_oublock(tsk); task_io_accounting_add(&sig->ioac, &tsk->ioac); - sig->sum_sched_runtime += tsk->se.sum_exec_runtime; + sig->sum_sched_runtime += tsk_seruntime(tsk); sig->nr_threads--; __unhash_process(tsk, group_dead); write_sequnlock(&sig->stats_lock); @@ -437,7 +437,7 @@ static void exit_mm(void) struct mm_struct *mm = current->mm; struct core_state *core_state; - mm_release(current, mm); + exit_mm_release(current, mm); if (!mm) return; sync_mm_rss(mm); @@ -517,10 +517,6 @@ static struct task_struct *find_child_reaper(struct task_struct *father, } write_unlock_irq(&tasklist_lock); - if (unlikely(pid_ns == &init_pid_ns)) { - panic("Attempted to kill init! exitcode=0x%08x\n", - father->signal->group_exit_code ?: father->exit_code); - } list_for_each_entry_safe(p, n, dead, ptrace_entry) { list_del_init(&p->ptrace_entry); @@ -746,32 +742,12 @@ void __noreturn do_exit(long code) */ if (unlikely(tsk->flags & PF_EXITING)) { pr_alert("Fixing recursive fault but reboot is needed!\n"); - /* - * We can do this unlocked here. The futex code uses - * this flag just to verify whether the pi state - * cleanup has been done or not. In the worst case it - * loops once more. We pretend that the cleanup was - * done as there is no way to return. Either the - * OWNER_DIED bit is set by now or we push the blocked - * task into the wait for ever nirwana as well. - */ - tsk->flags |= PF_EXITPIDONE; + futex_exit_recursive(tsk); set_current_state(TASK_UNINTERRUPTIBLE); schedule(); } exit_signals(tsk); /* sets PF_EXITING */ - /* - * Ensure that all new tsk->pi_lock acquisitions must observe - * PF_EXITING. Serializes against futex.c:attach_to_pi_owner(). - */ - smp_mb(); - /* - * Ensure that we must observe the pi_state in exit_mm() -> - * mm_release() -> exit_pi_state_list(). - */ - raw_spin_lock_irq(&tsk->pi_lock); - raw_spin_unlock_irq(&tsk->pi_lock); if (unlikely(in_atomic())) { pr_info("note: %s[%d] exited with preempt_count %d\n", @@ -786,6 +762,14 @@ void __noreturn do_exit(long code) acct_update_integrals(tsk); group_dead = atomic_dec_and_test(&tsk->signal->live); if (group_dead) { + /* + * If the last thread of global init has exited, panic + * immediately to get a useable coredump. + */ + if (unlikely(is_global_init(tsk))) + panic("Attempted to kill init! exitcode=0x%08x\n", + tsk->signal->group_exit_code ?: (int)code); + #ifdef CONFIG_POSIX_TIMERS hrtimer_cancel(&tsk->signal->real_timer); exit_itimers(tsk->signal); @@ -846,12 +830,6 @@ void __noreturn do_exit(long code) * Make sure we are holding no locks: */ debug_check_no_locks_held(); - /* - * We can do this unlocked here. The futex code uses this flag - * just to verify whether the pi state cleanup has been done - * or not. In the worst case it loops once more. - */ - tsk->flags |= PF_EXITPIDONE; if (tsk->io_context) exit_io_context(tsk); diff --git a/kernel/fork.c b/kernel/fork.c index 13b38794efb5..ed909f8050b2 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -106,6 +106,11 @@ #define CREATE_TRACE_POINTS #include +#ifdef CONFIG_USER_NS +extern int unprivileged_userns_clone; +#else +#define unprivileged_userns_clone 0 +#endif /* * Minimum number of threads to boot the kernel @@ -1283,24 +1288,8 @@ static int wait_for_vfork_done(struct task_struct *child, * restoring the old one. . . * Eric Biederman 10 January 1998 */ -void mm_release(struct task_struct *tsk, struct mm_struct *mm) +static void mm_release(struct task_struct *tsk, struct mm_struct *mm) { - /* Get rid of any futexes when releasing the mm */ -#ifdef CONFIG_FUTEX - if (unlikely(tsk->robust_list)) { - exit_robust_list(tsk); - tsk->robust_list = NULL; - } -#ifdef CONFIG_COMPAT - if (unlikely(tsk->compat_robust_list)) { - compat_exit_robust_list(tsk); - tsk->compat_robust_list = NULL; - } -#endif - if (unlikely(!list_empty(&tsk->pi_state_list))) - exit_pi_state_list(tsk); -#endif - uprobe_free_utask(tsk); /* Get rid of any cached register state */ @@ -1333,6 +1322,18 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm) complete_vfork_done(tsk); } +void exit_mm_release(struct task_struct *tsk, struct mm_struct *mm) +{ + futex_exit_release(tsk); + mm_release(tsk, mm); +} + +void exec_mm_release(struct task_struct *tsk, struct mm_struct *mm) +{ + futex_exec_release(tsk); + mm_release(tsk, mm); +} + /** * dup_mm() - duplicates an existing mm structure * @tsk: the task_struct with which the new mm will be associated. @@ -1783,6 +1784,10 @@ static __latent_entropy struct task_struct *copy_process( if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|CLONE_FS)) return ERR_PTR(-EINVAL); + if ((clone_flags & CLONE_NEWUSER) && !unprivileged_userns_clone) + if (!capable(CAP_SYS_ADMIN)) + return ERR_PTR(-EPERM); + /* * Thread groups must share signals as well, and detached threads * can only be started up within the thread group. @@ -2062,14 +2067,8 @@ static __latent_entropy struct task_struct *copy_process( #ifdef CONFIG_BLOCK p->plug = NULL; #endif -#ifdef CONFIG_FUTEX - p->robust_list = NULL; -#ifdef CONFIG_COMPAT - p->compat_robust_list = NULL; -#endif - INIT_LIST_HEAD(&p->pi_state_list); - p->pi_state_cache = NULL; -#endif + futex_init_task(p); + /* * sigaltstack should be cleared when sharing the same VM */ @@ -2523,6 +2522,16 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, #endif #ifdef __ARCH_WANT_SYS_CLONE3 + +/* + * copy_thread implementations handle CLONE_SETTLS by reading the TLS value from + * the registers containing the syscall arguments for clone. This doesn't work + * with clone3 since the TLS value is passed in clone_args instead. + */ +#ifndef CONFIG_HAVE_COPY_THREAD_TLS +#error clone3 requires copy_thread_tls support in arch +#endif + noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs, struct clone_args __user *uargs, size_t usize) @@ -2836,6 +2845,12 @@ int ksys_unshare(unsigned long unshare_flags) if (unshare_flags & CLONE_NEWNS) unshare_flags |= CLONE_FS; + if ((unshare_flags & CLONE_NEWUSER) && !unprivileged_userns_clone) { + err = -EPERM; + if (!capable(CAP_SYS_ADMIN)) + goto bad_unshare_out; + } + err = check_unshare_flags(unshare_flags); if (err) goto bad_unshare_out; diff --git a/kernel/futex.c b/kernel/futex.c index bd18f60e4c6c..afbf928d6a6b 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -325,6 +325,12 @@ static inline bool should_fail_futex(bool fshared) } #endif /* CONFIG_FAIL_FUTEX */ +#ifdef CONFIG_COMPAT +static void compat_exit_robust_list(struct task_struct *curr); +#else +static inline void compat_exit_robust_list(struct task_struct *curr) { } +#endif + static inline void futex_get_mm(union futex_key *key) { mmgrab(key->private.mm); @@ -890,7 +896,7 @@ static void put_pi_state(struct futex_pi_state *pi_state) * Kernel cleans up PI-state, but userspace is likely hosed. * (Robust-futex cleanup is separate and might save the day for userspace.) */ -void exit_pi_state_list(struct task_struct *curr) +static void exit_pi_state_list(struct task_struct *curr) { struct list_head *next, *head = &curr->pi_state_list; struct futex_pi_state *pi_state; @@ -960,7 +966,8 @@ void exit_pi_state_list(struct task_struct *curr) } raw_spin_unlock_irq(&curr->pi_lock); } - +#else +static inline void exit_pi_state_list(struct task_struct *curr) { } #endif /* @@ -1169,16 +1176,47 @@ static int attach_to_pi_state(u32 __user *uaddr, u32 uval, return ret; } +/** + * wait_for_owner_exiting - Block until the owner has exited + * @exiting: Pointer to the exiting task + * + * Caller must hold a refcount on @exiting. + */ +static void wait_for_owner_exiting(int ret, struct task_struct *exiting) +{ + if (ret != -EBUSY) { + WARN_ON_ONCE(exiting); + return; + } + + if (WARN_ON_ONCE(ret == -EBUSY && !exiting)) + return; + + mutex_lock(&exiting->futex_exit_mutex); + /* + * No point in doing state checking here. If the waiter got here + * while the task was in exec()->exec_futex_release() then it can + * have any FUTEX_STATE_* value when the waiter has acquired the + * mutex. OK, if running, EXITING or DEAD if it reached exit() + * already. Highly unlikely and not a problem. Just one more round + * through the futex maze. + */ + mutex_unlock(&exiting->futex_exit_mutex); + + put_task_struct(exiting); +} + static int handle_exit_race(u32 __user *uaddr, u32 uval, struct task_struct *tsk) { u32 uval2; /* - * If PF_EXITPIDONE is not yet set, then try again. + * If the futex exit state is not yet FUTEX_STATE_DEAD, tell the + * caller that the alleged owner is busy. */ - if (tsk && !(tsk->flags & PF_EXITPIDONE)) - return -EAGAIN; + if (tsk && tsk->futex_state != FUTEX_STATE_DEAD) + return -EBUSY; /* * Reread the user space value to handle the following situation: @@ -1196,8 +1234,9 @@ static int handle_exit_race(u32 __user *uaddr, u32 uval, * *uaddr = 0xC0000000; tsk = get_task(PID); * } if (!tsk->flags & PF_EXITING) { * ... attach(); - * tsk->flags |= PF_EXITPIDONE; } else { - * if (!(tsk->flags & PF_EXITPIDONE)) + * tsk->futex_state = } else { + * FUTEX_STATE_DEAD; if (tsk->futex_state != + * FUTEX_STATE_DEAD) * return -EAGAIN; * return -ESRCH; <--- FAIL * } @@ -1228,7 +1267,8 @@ static int handle_exit_race(u32 __user *uaddr, u32 uval, * it after doing proper sanity checks. */ static int attach_to_pi_owner(u32 __user *uaddr, u32 uval, union futex_key *key, - struct futex_pi_state **ps) + struct futex_pi_state **ps, + struct task_struct **exiting) { pid_t pid = uval & FUTEX_TID_MASK; struct futex_pi_state *pi_state; @@ -1253,22 +1293,33 @@ static int attach_to_pi_owner(u32 __user *uaddr, u32 uval, union futex_key *key, } /* - * We need to look at the task state flags to figure out, - * whether the task is exiting. To protect against the do_exit - * change of the task flags, we do this protected by - * p->pi_lock: + * We need to look at the task state to figure out, whether the + * task is exiting. To protect against the change of the task state + * in futex_exit_release(), we do this protected by p->pi_lock: */ raw_spin_lock_irq(&p->pi_lock); - if (unlikely(p->flags & PF_EXITING)) { + if (unlikely(p->futex_state != FUTEX_STATE_OK)) { /* - * The task is on the way out. When PF_EXITPIDONE is - * set, we know that the task has finished the - * cleanup: + * The task is on the way out. When the futex state is + * FUTEX_STATE_DEAD, we know that the task has finished + * the cleanup: */ int ret = handle_exit_race(uaddr, uval, p); raw_spin_unlock_irq(&p->pi_lock); - put_task_struct(p); + /* + * If the owner task is between FUTEX_STATE_EXITING and + * FUTEX_STATE_DEAD then store the task pointer and keep + * the reference on the task struct. The calling code will + * drop all locks, wait for the task to reach + * FUTEX_STATE_DEAD and then drop the refcount. This is + * required to prevent a live lock when the current task + * preempted the exiting task between the two states. + */ + if (ret == -EBUSY) + *exiting = p; + else + put_task_struct(p); return ret; } @@ -1307,7 +1358,8 @@ static int attach_to_pi_owner(u32 __user *uaddr, u32 uval, union futex_key *key, static int lookup_pi_state(u32 __user *uaddr, u32 uval, struct futex_hash_bucket *hb, - union futex_key *key, struct futex_pi_state **ps) + union futex_key *key, struct futex_pi_state **ps, + struct task_struct **exiting) { struct futex_q *top_waiter = futex_top_waiter(hb, key); @@ -1322,7 +1374,7 @@ static int lookup_pi_state(u32 __user *uaddr, u32 uval, * We are the first waiter - try to look up the owner based on * @uval and attach to it. */ - return attach_to_pi_owner(uaddr, uval, key, ps); + return attach_to_pi_owner(uaddr, uval, key, ps, exiting); } static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval) @@ -1350,6 +1402,8 @@ static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval) * lookup * @task: the task to perform the atomic lock work for. This will * be "current" except in the case of requeue pi. + * @exiting: Pointer to store the task pointer of the owner task + * which is in the middle of exiting * @set_waiters: force setting the FUTEX_WAITERS bit (1) or not (0) * * Return: @@ -1358,11 +1412,17 @@ static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval) * - <0 - error * * The hb->lock and futex_key refs shall be held by the caller. + * + * @exiting is only set when the return value is -EBUSY. If so, this holds + * a refcount on the exiting task on return and the caller needs to drop it + * after waiting for the exit to complete. */ static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb, union futex_key *key, struct futex_pi_state **ps, - struct task_struct *task, int set_waiters) + struct task_struct *task, + struct task_struct **exiting, + int set_waiters) { u32 uval, newval, vpid = task_pid_vnr(task); struct futex_q *top_waiter; @@ -1432,7 +1492,7 @@ static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb, * attach to the owner. If that fails, no harm done, we only * set the FUTEX_WAITERS bit in the user space variable. */ - return attach_to_pi_owner(uaddr, newval, key, ps); + return attach_to_pi_owner(uaddr, newval, key, ps, exiting); } /** @@ -1850,6 +1910,8 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key, * @key1: the from futex key * @key2: the to futex key * @ps: address to store the pi_state pointer + * @exiting: Pointer to store the task pointer of the owner task + * which is in the middle of exiting * @set_waiters: force setting the FUTEX_WAITERS bit (1) or not (0) * * Try and get the lock on behalf of the top waiter if we can do it atomically. @@ -1857,16 +1919,20 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key, * then direct futex_lock_pi_atomic() to force setting the FUTEX_WAITERS bit. * hb1 and hb2 must be held by the caller. * + * @exiting is only set when the return value is -EBUSY. If so, this holds + * a refcount on the exiting task on return and the caller needs to drop it + * after waiting for the exit to complete. + * * Return: * - 0 - failed to acquire the lock atomically; * - >0 - acquired the lock, return value is vpid of the top_waiter * - <0 - error */ -static int futex_proxy_trylock_atomic(u32 __user *pifutex, - struct futex_hash_bucket *hb1, - struct futex_hash_bucket *hb2, - union futex_key *key1, union futex_key *key2, - struct futex_pi_state **ps, int set_waiters) +static int +futex_proxy_trylock_atomic(u32 __user *pifutex, struct futex_hash_bucket *hb1, + struct futex_hash_bucket *hb2, union futex_key *key1, + union futex_key *key2, struct futex_pi_state **ps, + struct task_struct **exiting, int set_waiters) { struct futex_q *top_waiter = NULL; u32 curval; @@ -1903,7 +1969,7 @@ static int futex_proxy_trylock_atomic(u32 __user *pifutex, */ vpid = task_pid_vnr(top_waiter->task); ret = futex_lock_pi_atomic(pifutex, hb2, key2, ps, top_waiter->task, - set_waiters); + exiting, set_waiters); if (ret == 1) { requeue_pi_wake_futex(top_waiter, key2, hb2); return vpid; @@ -2032,6 +2098,8 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags, } if (requeue_pi && (task_count - nr_wake < nr_requeue)) { + struct task_struct *exiting = NULL; + /* * Attempt to acquire uaddr2 and wake the top waiter. If we * intend to requeue waiters, force setting the FUTEX_WAITERS @@ -2039,7 +2107,8 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags, * faults rather in the requeue loop below. */ ret = futex_proxy_trylock_atomic(uaddr2, hb1, hb2, &key1, - &key2, &pi_state, nr_requeue); + &key2, &pi_state, + &exiting, nr_requeue); /* * At this point the top_waiter has either taken uaddr2 or is @@ -2066,7 +2135,8 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags, * If that call succeeds then we have pi_state and an * initial refcount on it. */ - ret = lookup_pi_state(uaddr2, ret, hb2, &key2, &pi_state); + ret = lookup_pi_state(uaddr2, ret, hb2, &key2, + &pi_state, &exiting); } switch (ret) { @@ -2084,17 +2154,24 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags, if (!ret) goto retry; goto out; + case -EBUSY: case -EAGAIN: /* * Two reasons for this: - * - Owner is exiting and we just wait for the + * - EBUSY: Owner is exiting and we just wait for the * exit to complete. - * - The user space value changed. + * - EAGAIN: The user space value changed. */ double_unlock_hb(hb1, hb2); hb_waiters_dec(hb2); put_futex_key(&key2); put_futex_key(&key1); + /* + * Handle the case where the owner is in the middle of + * exiting. Wait for the exit to complete otherwise + * this task might loop forever, aka. live lock. + */ + wait_for_owner_exiting(ret, exiting); cond_resched(); goto retry; default: @@ -2801,6 +2878,7 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags, { struct hrtimer_sleeper timeout, *to; struct futex_pi_state *pi_state = NULL; + struct task_struct *exiting = NULL; struct rt_mutex_waiter rt_waiter; struct futex_hash_bucket *hb; struct futex_q q = futex_q_init; @@ -2822,7 +2900,8 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags, retry_private: hb = queue_lock(&q); - ret = futex_lock_pi_atomic(uaddr, hb, &q.key, &q.pi_state, current, 0); + ret = futex_lock_pi_atomic(uaddr, hb, &q.key, &q.pi_state, current, + &exiting, 0); if (unlikely(ret)) { /* * Atomic work succeeded and we got the lock, @@ -2835,15 +2914,22 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags, goto out_unlock_put_key; case -EFAULT: goto uaddr_faulted; + case -EBUSY: case -EAGAIN: /* * Two reasons for this: - * - Task is exiting and we just wait for the + * - EBUSY: Task is exiting and we just wait for the * exit to complete. - * - The user space value changed. + * - EAGAIN: The user space value changed. */ queue_unlock(hb); put_futex_key(&q.key); + /* + * Handle the case where the owner is in the middle of + * exiting. Wait for the exit to complete otherwise + * this task might loop forever, aka. live lock. + */ + wait_for_owner_exiting(ret, exiting); cond_resched(); goto retry; default: @@ -3452,11 +3538,16 @@ SYSCALL_DEFINE3(get_robust_list, int, pid, return ret; } +/* Constants for the pending_op argument of handle_futex_death */ +#define HANDLE_DEATH_PENDING true +#define HANDLE_DEATH_LIST false + /* * Process a futex-list entry, check whether it's owned by the * dying task, and do notification if so: */ -static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi) +static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, + bool pi, bool pending_op) { u32 uval, uninitialized_var(nval), mval; int err; @@ -3469,6 +3560,42 @@ static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int p if (get_user(uval, uaddr)) return -1; + /* + * Special case for regular (non PI) futexes. The unlock path in + * user space has two race scenarios: + * + * 1. The unlock path releases the user space futex value and + * before it can execute the futex() syscall to wake up + * waiters it is killed. + * + * 2. A woken up waiter is killed before it can acquire the + * futex in user space. + * + * In both cases the TID validation below prevents a wakeup of + * potential waiters which can cause these waiters to block + * forever. + * + * In both cases the following conditions are met: + * + * 1) task->robust_list->list_op_pending != NULL + * @pending_op == true + * 2) User space futex value == 0 + * 3) Regular futex: @pi == false + * + * If these conditions are met, it is safe to attempt waking up a + * potential waiter without touching the user space futex value and + * trying to set the OWNER_DIED bit. The user space futex value is + * uncontended and the rest of the user space mutex state is + * consistent, so a woken waiter will just take over the + * uncontended futex. Setting the OWNER_DIED bit would create + * inconsistent state and malfunction of the user space owner died + * handling. + */ + if (pending_op && !pi && !uval) { + futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY); + return 0; + } + if ((uval & FUTEX_TID_MASK) != task_pid_vnr(curr)) return 0; @@ -3547,7 +3674,7 @@ static inline int fetch_robust_entry(struct robust_list __user **entry, * * We silently return on any sign of list-walking problem. */ -void exit_robust_list(struct task_struct *curr) +static void exit_robust_list(struct task_struct *curr) { struct robust_list_head __user *head = curr->robust_list; struct robust_list __user *entry, *next_entry, *pending; @@ -3588,10 +3715,11 @@ void exit_robust_list(struct task_struct *curr) * A pending lock might already be on the list, so * don't process it twice: */ - if (entry != pending) + if (entry != pending) { if (handle_futex_death((void __user *)entry + futex_offset, - curr, pi)) + curr, pi, HANDLE_DEATH_LIST)) return; + } if (rc) return; entry = next_entry; @@ -3605,9 +3733,118 @@ void exit_robust_list(struct task_struct *curr) cond_resched(); } - if (pending) + if (pending) { handle_futex_death((void __user *)pending + futex_offset, - curr, pip); + curr, pip, HANDLE_DEATH_PENDING); + } +} + +static void futex_cleanup(struct task_struct *tsk) +{ + if (unlikely(tsk->robust_list)) { + exit_robust_list(tsk); + tsk->robust_list = NULL; + } + +#ifdef CONFIG_COMPAT + if (unlikely(tsk->compat_robust_list)) { + compat_exit_robust_list(tsk); + tsk->compat_robust_list = NULL; + } +#endif + + if (unlikely(!list_empty(&tsk->pi_state_list))) + exit_pi_state_list(tsk); +} + +/** + * futex_exit_recursive - Set the tasks futex state to FUTEX_STATE_DEAD + * @tsk: task to set the state on + * + * Set the futex exit state of the task lockless. The futex waiter code + * observes that state when a task is exiting and loops until the task has + * actually finished the futex cleanup. The worst case for this is that the + * waiter runs through the wait loop until the state becomes visible. + * + * This is called from the recursive fault handling path in do_exit(). + * + * This is best effort. Either the futex exit code has run already or + * not. If the OWNER_DIED bit has been set on the futex then the waiter can + * take it over. If not, the problem is pushed back to user space. If the + * futex exit code did not run yet, then an already queued waiter might + * block forever, but there is nothing which can be done about that. + */ +void futex_exit_recursive(struct task_struct *tsk) +{ + /* If the state is FUTEX_STATE_EXITING then futex_exit_mutex is held */ + if (tsk->futex_state == FUTEX_STATE_EXITING) + mutex_unlock(&tsk->futex_exit_mutex); + tsk->futex_state = FUTEX_STATE_DEAD; +} + +static void futex_cleanup_begin(struct task_struct *tsk) +{ + /* + * Prevent various race issues against a concurrent incoming waiter + * including live locks by forcing the waiter to block on + * tsk->futex_exit_mutex when it observes FUTEX_STATE_EXITING in + * attach_to_pi_owner(). + */ + mutex_lock(&tsk->futex_exit_mutex); + + /* + * Switch the state to FUTEX_STATE_EXITING under tsk->pi_lock. + * + * This ensures that all subsequent checks of tsk->futex_state in + * attach_to_pi_owner() must observe FUTEX_STATE_EXITING with + * tsk->pi_lock held. + * + * It guarantees also that a pi_state which was queued right before + * the state change under tsk->pi_lock by a concurrent waiter must + * be observed in exit_pi_state_list(). + */ + raw_spin_lock_irq(&tsk->pi_lock); + tsk->futex_state = FUTEX_STATE_EXITING; + raw_spin_unlock_irq(&tsk->pi_lock); +} + +static void futex_cleanup_end(struct task_struct *tsk, int state) +{ + /* + * Lockless store. The only side effect is that an observer might + * take another loop until it becomes visible. + */ + tsk->futex_state = state; + /* + * Drop the exit protection. This unblocks waiters which observed + * FUTEX_STATE_EXITING to reevaluate the state. + */ + mutex_unlock(&tsk->futex_exit_mutex); +} + +void futex_exec_release(struct task_struct *tsk) +{ + /* + * The state handling is done for consistency, but in the case of + * exec() there is no way to prevent futher damage as the PID stays + * the same. But for the unlikely and arguably buggy case that a + * futex is held on exec(), this provides at least as much state + * consistency protection which is possible. + */ + futex_cleanup_begin(tsk); + futex_cleanup(tsk); + /* + * Reset the state to FUTEX_STATE_OK. The task is alive and about + * exec a new binary. + */ + futex_cleanup_end(tsk, FUTEX_STATE_OK); +} + +void futex_exit_release(struct task_struct *tsk) +{ + futex_cleanup_begin(tsk); + futex_cleanup(tsk); + futex_cleanup_end(tsk, FUTEX_STATE_DEAD); } long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, @@ -3737,7 +3974,7 @@ static void __user *futex_uaddr(struct robust_list __user *entry, * * We silently return on any sign of list-walking problem. */ -void compat_exit_robust_list(struct task_struct *curr) +static void compat_exit_robust_list(struct task_struct *curr) { struct compat_robust_list_head __user *head = curr->compat_robust_list; struct robust_list __user *entry, *next_entry, *pending; @@ -3784,7 +4021,8 @@ void compat_exit_robust_list(struct task_struct *curr) if (entry != pending) { void __user *uaddr = futex_uaddr(entry, futex_offset); - if (handle_futex_death(uaddr, curr, pi)) + if (handle_futex_death(uaddr, curr, pi, + HANDLE_DEATH_LIST)) return; } if (rc) @@ -3803,7 +4041,7 @@ void compat_exit_robust_list(struct task_struct *curr) if (pending) { void __user *uaddr = futex_uaddr(pending, futex_offset); - handle_futex_death(uaddr, curr, pip); + handle_futex_death(uaddr, curr, pip, HANDLE_DEATH_PENDING); } } diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c index cdf318d86dd6..b3bd1e65c002 100644 --- a/kernel/livepatch/transition.c +++ b/kernel/livepatch/transition.c @@ -306,7 +306,11 @@ static bool klp_try_switch_task(struct task_struct *task) */ rq = task_rq_lock(task, &flags); +#ifdef CONFIG_SCHED_BMQ + if (task_running(task) && task != current) { +#else if (task_running(rq, task) && task != current) { +#endif snprintf(err_buf, STACK_ERR_BUF_SIZE, "%s: %s:%d is running\n", __func__, task->comm, task->pid); diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 2874bf556162..fad8a279fdfa 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -229,7 +229,7 @@ static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock, * Only use with rt_mutex_waiter_{less,equal}() */ #define task_to_waiter(p) \ - &(struct rt_mutex_waiter){ .prio = (p)->prio, .deadline = (p)->dl.deadline } + &(struct rt_mutex_waiter){ .prio = (p)->prio, .deadline = __tsk_deadline(p) } static inline int rt_mutex_waiter_less(struct rt_mutex_waiter *left, @@ -680,7 +680,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, * the values of the node being removed. */ waiter->prio = task->prio; - waiter->deadline = task->dl.deadline; + waiter->deadline = __tsk_deadline(task); rt_mutex_enqueue(lock, waiter); @@ -953,7 +953,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, waiter->task = task; waiter->lock = lock; waiter->prio = task->prio; - waiter->deadline = task->dl.deadline; + waiter->deadline = __tsk_deadline(task); /* Get the top priority waiter on the lock */ if (rt_mutex_has_waiters(lock)) diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c index 399669f7eba8..472dd462a40c 100644 --- a/kernel/locking/spinlock_debug.c +++ b/kernel/locking/spinlock_debug.c @@ -51,19 +51,19 @@ EXPORT_SYMBOL(__rwlock_init); static void spin_dump(raw_spinlock_t *lock, const char *msg) { - struct task_struct *owner = NULL; + struct task_struct *owner = READ_ONCE(lock->owner); - if (lock->owner && lock->owner != SPINLOCK_OWNER_INIT) - owner = lock->owner; + if (owner == SPINLOCK_OWNER_INIT) + owner = NULL; printk(KERN_EMERG "BUG: spinlock %s on CPU#%d, %s/%d\n", msg, raw_smp_processor_id(), current->comm, task_pid_nr(current)); printk(KERN_EMERG " lock: %pS, .magic: %08x, .owner: %s/%d, " ".owner_cpu: %d\n", - lock, lock->magic, + lock, READ_ONCE(lock->magic), owner ? owner->comm : "", owner ? task_pid_nr(owner) : -1, - lock->owner_cpu); + READ_ONCE(lock->owner_cpu)); dump_stack(); } @@ -80,16 +80,16 @@ static void spin_bug(raw_spinlock_t *lock, const char *msg) static inline void debug_spin_lock_before(raw_spinlock_t *lock) { - SPIN_BUG_ON(lock->magic != SPINLOCK_MAGIC, lock, "bad magic"); - SPIN_BUG_ON(lock->owner == current, lock, "recursion"); - SPIN_BUG_ON(lock->owner_cpu == raw_smp_processor_id(), + SPIN_BUG_ON(READ_ONCE(lock->magic) != SPINLOCK_MAGIC, lock, "bad magic"); + SPIN_BUG_ON(READ_ONCE(lock->owner) == current, lock, "recursion"); + SPIN_BUG_ON(READ_ONCE(lock->owner_cpu) == raw_smp_processor_id(), lock, "cpu recursion"); } static inline void debug_spin_lock_after(raw_spinlock_t *lock) { - lock->owner_cpu = raw_smp_processor_id(); - lock->owner = current; + WRITE_ONCE(lock->owner_cpu, raw_smp_processor_id()); + WRITE_ONCE(lock->owner, current); } static inline void debug_spin_unlock(raw_spinlock_t *lock) @@ -99,8 +99,8 @@ static inline void debug_spin_unlock(raw_spinlock_t *lock) SPIN_BUG_ON(lock->owner != current, lock, "wrong owner"); SPIN_BUG_ON(lock->owner_cpu != raw_smp_processor_id(), lock, "wrong CPU"); - lock->owner = SPINLOCK_OWNER_INIT; - lock->owner_cpu = -1; + WRITE_ONCE(lock->owner, SPINLOCK_OWNER_INIT); + WRITE_ONCE(lock->owner_cpu, -1); } /* @@ -187,8 +187,8 @@ static inline void debug_write_lock_before(rwlock_t *lock) static inline void debug_write_lock_after(rwlock_t *lock) { - lock->owner_cpu = raw_smp_processor_id(); - lock->owner = current; + WRITE_ONCE(lock->owner_cpu, raw_smp_processor_id()); + WRITE_ONCE(lock->owner, current); } static inline void debug_write_unlock(rwlock_t *lock) @@ -197,8 +197,8 @@ static inline void debug_write_unlock(rwlock_t *lock) RWLOCK_BUG_ON(lock->owner != current, lock, "wrong owner"); RWLOCK_BUG_ON(lock->owner_cpu != raw_smp_processor_id(), lock, "wrong CPU"); - lock->owner = SPINLOCK_OWNER_INIT; - lock->owner_cpu = -1; + WRITE_ONCE(lock->owner, SPINLOCK_OWNER_INIT); + WRITE_ONCE(lock->owner_cpu, -1); } void do_raw_write_lock(rwlock_t *lock) diff --git a/kernel/module.c b/kernel/module.c index ff2d7359a418..cb09a5f37a5f 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1033,6 +1033,8 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user, strlcpy(last_unloaded_module, mod->name, sizeof(last_unloaded_module)); free_module(mod); + /* someone could wait for the module in add_unformed_module() */ + wake_up_all(&module_wq); return 0; out: mutex_unlock(&module_mutex); diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 83105874f255..26b9168321e7 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -734,8 +734,15 @@ static int memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn, * We have found the zone. Now walk the radix tree to find the leaf node * for our PFN. */ + + /* + * If the zone we wish to scan is the the current zone and the + * pfn falls into the current node then we do not need to walk + * the tree. + */ node = bm->cur.node; - if (((pfn - zone->start_pfn) & ~BM_BLOCK_MASK) == bm->cur.node_pfn) + if (zone == bm->cur.zone && + ((pfn - zone->start_pfn) & ~BM_BLOCK_MASK) == bm->cur.node_pfn) goto node_found; node = zone->rtree; diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 21fb5a5662b5..cab4e5c5b38e 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -16,14 +16,20 @@ ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y) CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer endif -obj-y += core.o loadavg.o clock.o cputime.o -obj-y += idle.o fair.o rt.o deadline.o -obj-y += wait.o wait_bit.o swait.o completion.o - -obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o pelt.o +ifdef CONFIG_SCHED_BMQ +obj-y += bmq.o +else +obj-y += core.o +obj-y += fair.o rt.o deadline.o +obj-$(CONFIG_SMP) += cpudeadline.o topology.o stop_task.o obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o -obj-$(CONFIG_SCHEDSTATS) += stats.o obj-$(CONFIG_SCHED_DEBUG) += debug.o +endif +obj-y += loadavg.o clock.o cputime.o +obj-y += idle.o +obj-y += wait.o wait_bit.o swait.o completion.o +obj-$(CONFIG_SMP) += cpupri.o pelt.o +obj-$(CONFIG_SCHEDSTATS) += stats.o obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o obj-$(CONFIG_CPU_FREQ) += cpufreq.o obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o diff --git a/kernel/sched/bmq.c b/kernel/sched/bmq.c new file mode 100644 index 000000000000..42a2a5b3d172 --- /dev/null +++ b/kernel/sched/bmq.c @@ -0,0 +1,6102 @@ +/* + * kernel/sched/bmq.c + * + * BMQ Core kernel scheduler code and related syscalls + * + * Copyright (C) 1991-2002 Linus Torvalds + * + * 2009-08-13 Brainfuck deadline scheduling policy by Con Kolivas deletes + * a whole lot of those previous things. + * 2017-09-06 Priority and Deadline based Skip list multiple queue kernel + * scheduler by Alfred Chen. + * 2019-02-20 BMQ(BitMap Queue) kernel scheduler by Alfred Chen. + */ +#include "bmq_sched.h" + +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include + +#include "../workqueue_internal.h" +#include "../smpboot.h" + +#include "pelt.h" + +#define CREATE_TRACE_POINTS +#include + +/* rt_prio(prio) defined in include/linux/sched/rt.h */ +#define rt_task(p) rt_prio((p)->prio) +#define rt_policy(policy) ((policy) == SCHED_FIFO || (policy) == SCHED_RR) +#define task_has_rt_policy(p) (rt_policy((p)->policy)) + +#define STOP_PRIO (MAX_RT_PRIO - 1) + +#define SCHED_TIMESLICE_NS (CONFIG_SCHED_TIMESLICE * 1000 * 1000) + +/* Reschedule if less than this many μs left */ +#define RESCHED_NS (100 * 1000) + +/* + * This allows printing both to /proc/sched_debug and + * to the console + */ +#define SEQ_printf(m, x...) \ + do { \ + if (m) \ + seq_printf(m, x); \ + else \ + pr_cont(x); \ + } while (0) + +static inline void print_scheduler_version(void) +{ + printk(KERN_INFO "bmq: BMQ CPU Scheduler 5.4-r2 by Alfred Chen.\n"); +} + +/** + * sched_yield_type - Choose what sort of yield sched_yield will perform. + * 0: No yield. + * 1: Deboost and requeue task. (default) + * 2: Set rq skip task. + */ +int sched_yield_type __read_mostly = 1; + +#define rq_switch_time(rq) ((rq)->clock - (rq)->last_ts_switch) +#define boost_threshold(p) (SCHED_TIMESLICE_NS >>\ + (10 - MAX_PRIORITY_ADJ - (p)->boost_prio)) + +static inline void boost_task(struct task_struct *p) +{ + int limit; + + switch (p->policy) { + case SCHED_NORMAL: + limit = -MAX_PRIORITY_ADJ; + break; + case SCHED_BATCH: + case SCHED_IDLE: + limit = 0; + break; + default: + return; + } + + if (p->boost_prio > limit) + p->boost_prio--; +} + +static inline void deboost_task(struct task_struct *p) +{ + if (p->boost_prio < MAX_PRIORITY_ADJ) + p->boost_prio++; +} + +#ifdef CONFIG_SMP +static cpumask_t sched_rq_pending_mask ____cacheline_aligned_in_smp; + +enum { + BASE_CPU_AFFINITY_CHK_LEVEL = 1, +#ifdef CONFIG_SCHED_SMT + SMT_CPU_AFFINITY_CHK_LEVEL_SPACE_HOLDER, +#endif +#ifdef CONFIG_SCHED_MC + MC_CPU_AFFINITY_CHK_LEVEL_SPACE_HOLDER, +#endif + NR_CPU_AFFINITY_CHK_LEVEL +}; + +DEFINE_PER_CPU(cpumask_t [NR_CPU_AFFINITY_CHK_LEVEL], sched_cpu_affinity_masks); +DEFINE_PER_CPU(cpumask_t *, sched_cpu_affinity_end_mask); + +#ifdef CONFIG_SCHED_SMT +DEFINE_STATIC_KEY_FALSE(sched_smt_present); +EXPORT_SYMBOL_GPL(sched_smt_present); +#endif + +/* + * Keep a unique ID per domain (we use the first CPUs number in the cpumask of + * the domain), this allows us to quickly tell if two cpus are in the same cache + * domain, see cpus_share_cache(). + */ +DEFINE_PER_CPU(int, sd_llc_id); + +int __weak arch_sd_sibling_asym_packing(void) +{ + return 0*SD_ASYM_PACKING; +} +#endif /* CONFIG_SMP */ + +static DEFINE_MUTEX(sched_hotcpu_mutex); + +DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); + +#ifndef prepare_arch_switch +# define prepare_arch_switch(next) do { } while (0) +#endif +#ifndef finish_arch_post_lock_switch +# define finish_arch_post_lock_switch() do { } while (0) +#endif + +#define IDLE_WM (IDLE_TASK_SCHED_PRIO) + +static cpumask_t sched_sg_idle_mask ____cacheline_aligned_in_smp; +static cpumask_t sched_rq_watermark[bmq_BITS] ____cacheline_aligned_in_smp; + +#if (bmq_BITS <= BITS_PER_LONG) +#define bmq_find_first_bit(bm) __ffs((bm[0])) +#define bmq_find_next_bit(bm, start) __ffs(BITMAP_FIRST_WORD_MASK(start) & bm[0]) +#else +#define bmq_find_first_bit(bm) find_first_bit((bm), bmq_BITS) +#define bmq_find_next_bit(bm, start) find_next_bit(bm, bmq_BITS, start) +#endif + +static inline void update_sched_rq_watermark(struct rq *rq) +{ + unsigned long watermark = bmq_find_first_bit(rq->queue.bitmap); + unsigned long last_wm = rq->watermark; + unsigned long i; + int cpu; + + if (watermark == last_wm) + return; + + rq->watermark = watermark; + cpu = cpu_of(rq); + if (watermark < last_wm) { + for (i = watermark + 1; i <= last_wm; i++) + cpumask_andnot(&sched_rq_watermark[i], + &sched_rq_watermark[i], cpumask_of(cpu)); +#ifdef CONFIG_SCHED_SMT + if (!static_branch_likely(&sched_smt_present)) + return; + if (IDLE_WM == last_wm) + cpumask_andnot(&sched_sg_idle_mask, + &sched_sg_idle_mask, cpu_smt_mask(cpu)); +#endif + return; + } + /* last_wm < watermark */ + for (i = last_wm + 1; i <= watermark; i++) + cpumask_set_cpu(cpu, &sched_rq_watermark[i]); +#ifdef CONFIG_SCHED_SMT + if (!static_branch_likely(&sched_smt_present)) + return; + if (IDLE_WM == watermark) { + cpumask_t tmp; + cpumask_and(&tmp, cpu_smt_mask(cpu), &sched_rq_watermark[IDLE_WM]); + if (cpumask_equal(&tmp, cpu_smt_mask(cpu))) + cpumask_or(&sched_sg_idle_mask, cpu_smt_mask(cpu), + &sched_sg_idle_mask); + } +#endif +} + +static inline int task_sched_prio(struct task_struct *p) +{ + return (p->prio < MAX_RT_PRIO)? 0:p->prio - MAX_RT_PRIO + p->boost_prio + 1; +} + +static inline void bmq_init(struct bmq *q) +{ + int i; + + bitmap_zero(q->bitmap, bmq_BITS); + for(i = 0; i < bmq_BITS; i++) + INIT_LIST_HEAD(&q->heads[i]); +} + +static inline void bmq_init_idle(struct bmq *q, struct task_struct *idle) +{ + INIT_LIST_HEAD(&q->heads[IDLE_TASK_SCHED_PRIO]); + list_add(&idle->bmq_node, &q->heads[IDLE_TASK_SCHED_PRIO]); + set_bit(IDLE_TASK_SCHED_PRIO, q->bitmap); +} + +static inline void bmq_add_task(struct task_struct *p, struct bmq *q, int idx) +{ + struct list_head *n; + + if (likely(idx)) { + list_add_tail(&p->bmq_node, &q->heads[idx]); + return; + } + + list_for_each(n, &q->heads[idx]) + if (list_entry(n, struct task_struct, bmq_node)->prio > p->prio) + break; + __list_add(&p->bmq_node, n->prev, n); +} + +/* + * This routine used in bmq scheduler only which assume the idle task in the bmq + */ +static inline struct task_struct *rq_first_bmq_task(struct rq *rq) +{ + unsigned long idx = bmq_find_first_bit(rq->queue.bitmap); + const struct list_head *head = &rq->queue.heads[idx]; + + return list_first_entry(head, struct task_struct, bmq_node); +} + +static inline struct task_struct * +rq_next_bmq_task(struct task_struct *p, struct rq *rq) +{ + unsigned long idx = p->bmq_idx; + struct list_head *head = &rq->queue.heads[idx]; + + if (list_is_last(&p->bmq_node, head)) { + idx = bmq_find_next_bit(rq->queue.bitmap, idx + 1); + head = &rq->queue.heads[idx]; + + return list_first_entry(head, struct task_struct, bmq_node); + } + + return list_next_entry(p, bmq_node); +} + +static inline struct task_struct *rq_runnable_task(struct rq *rq) +{ + struct task_struct *next = rq_first_bmq_task(rq); + + if (unlikely(next == rq->skip)) + next = rq_next_bmq_task(next, rq); + + return next; +} + +/* + * Context: p->pi_lock + */ +static inline struct rq +*__task_access_lock(struct task_struct *p, raw_spinlock_t **plock) +{ + struct rq *rq; + for (;;) { + rq = task_rq(p); + if (p->on_cpu || task_on_rq_queued(p)) { + raw_spin_lock(&rq->lock); + if (likely((p->on_cpu || task_on_rq_queued(p)) + && rq == task_rq(p))) { + *plock = &rq->lock; + return rq; + } + raw_spin_unlock(&rq->lock); + } else if (task_on_rq_migrating(p)) { + do { + cpu_relax(); + } while (unlikely(task_on_rq_migrating(p))); + } else { + *plock = NULL; + return rq; + } + } +} + +static inline void +__task_access_unlock(struct task_struct *p, raw_spinlock_t *lock) +{ + if (NULL != lock) + raw_spin_unlock(lock); +} + +static inline struct rq +*task_access_lock_irqsave(struct task_struct *p, raw_spinlock_t **plock, + unsigned long *flags) +{ + struct rq *rq; + for (;;) { + rq = task_rq(p); + if (p->on_cpu || task_on_rq_queued(p)) { + raw_spin_lock_irqsave(&rq->lock, *flags); + if (likely((p->on_cpu || task_on_rq_queued(p)) + && rq == task_rq(p))) { + *plock = &rq->lock; + return rq; + } + raw_spin_unlock_irqrestore(&rq->lock, *flags); + } else if (task_on_rq_migrating(p)) { + do { + cpu_relax(); + } while (unlikely(task_on_rq_migrating(p))); + } else { + raw_spin_lock_irqsave(&p->pi_lock, *flags); + if (likely(!p->on_cpu && !p->on_rq && + rq == task_rq(p))) { + *plock = &p->pi_lock; + return rq; + } + raw_spin_unlock_irqrestore(&p->pi_lock, *flags); + } + } +} + +static inline void +task_access_unlock_irqrestore(struct task_struct *p, raw_spinlock_t *lock, + unsigned long *flags) +{ + raw_spin_unlock_irqrestore(lock, *flags); +} + +/* + * __task_rq_lock - lock the rq @p resides on. + */ +struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf) + __acquires(rq->lock) +{ + struct rq *rq; + + lockdep_assert_held(&p->pi_lock); + + for (;;) { + rq = task_rq(p); + raw_spin_lock(&rq->lock); + if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) + return rq; + raw_spin_unlock(&rq->lock); + + while (unlikely(task_on_rq_migrating(p))) + cpu_relax(); + } +} + +/* + * task_rq_lock - lock p->pi_lock and lock the rq @p resides on. + */ +struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf) + __acquires(p->pi_lock) + __acquires(rq->lock) +{ + struct rq *rq; + + for (;;) { + raw_spin_lock_irqsave(&p->pi_lock, rf->flags); + rq = task_rq(p); + raw_spin_lock(&rq->lock); + /* + * move_queued_task() task_rq_lock() + * + * ACQUIRE (rq->lock) + * [S] ->on_rq = MIGRATING [L] rq = task_rq() + * WMB (__set_task_cpu()) ACQUIRE (rq->lock); + * [S] ->cpu = new_cpu [L] task_rq() + * [L] ->on_rq + * RELEASE (rq->lock) + * + * If we observe the old CPU in task_rq_lock(), the acquire of + * the old rq->lock will fully serialize against the stores. + * + * If we observe the new CPU in task_rq_lock(), the address + * dependency headed by '[L] rq = task_rq()' and the acquire + * will pair with the WMB to ensure we then also see migrating. + */ + if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) { + return rq; + } + raw_spin_unlock(&rq->lock); + raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags); + + while (unlikely(task_on_rq_migrating(p))) + cpu_relax(); + } +} + +/* + * RQ-clock updating methods: + */ + +static void update_rq_clock_task(struct rq *rq, s64 delta) +{ +/* + * In theory, the compile should just see 0 here, and optimize out the call + * to sched_rt_avg_update. But I don't trust it... + */ + s64 __maybe_unused steal = 0, irq_delta = 0; + +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time; + + /* + * Since irq_time is only updated on {soft,}irq_exit, we might run into + * this case when a previous update_rq_clock() happened inside a + * {soft,}irq region. + * + * When this happens, we stop ->clock_task and only update the + * prev_irq_time stamp to account for the part that fit, so that a next + * update will consume the rest. This ensures ->clock_task is + * monotonic. + * + * It does however cause some slight miss-attribution of {soft,}irq + * time, a more accurate solution would be to update the irq_time using + * the current rq->clock timestamp, except that would require using + * atomic ops. + */ + if (irq_delta > delta) + irq_delta = delta; + + rq->prev_irq_time += irq_delta; + delta -= irq_delta; +#endif +#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING + if (static_key_false((¶virt_steal_rq_enabled))) { + steal = paravirt_steal_clock(cpu_of(rq)); + steal -= rq->prev_steal_time_rq; + + if (unlikely(steal > delta)) + steal = delta; + + rq->prev_steal_time_rq += steal; + delta -= steal; + } +#endif + + rq->clock_task += delta; + +#ifdef CONFIG_HAVE_SCHED_AVG_IRQ + if ((irq_delta + steal)) + update_irq_load_avg(rq, irq_delta + steal); +#endif +} + +static inline void update_rq_clock(struct rq *rq) +{ + s64 delta = sched_clock_cpu(cpu_of(rq)) - rq->clock; + + if (unlikely(delta <= 0)) + return; + rq->clock += delta; + update_rq_clock_task(rq, delta); +} + +/* + * cmpxchg based fetch_or, macro so it works for different integer types + */ +#define fetch_or(ptr, mask) \ + ({ \ + typeof(ptr) _ptr = (ptr); \ + typeof(mask) _mask = (mask); \ + typeof(*_ptr) _old, _val = *_ptr; \ + \ + for (;;) { \ + _old = cmpxchg(_ptr, _val, _val | _mask); \ + if (_old == _val) \ + break; \ + _val = _old; \ + } \ + _old; \ +}) + +#if defined(CONFIG_SMP) && defined(TIF_POLLING_NRFLAG) +/* + * Atomically set TIF_NEED_RESCHED and test for TIF_POLLING_NRFLAG, + * this avoids any races wrt polling state changes and thereby avoids + * spurious IPIs. + */ +static bool set_nr_and_not_polling(struct task_struct *p) +{ + struct thread_info *ti = task_thread_info(p); + return !(fetch_or(&ti->flags, _TIF_NEED_RESCHED) & _TIF_POLLING_NRFLAG); +} + +/* + * Atomically set TIF_NEED_RESCHED if TIF_POLLING_NRFLAG is set. + * + * If this returns true, then the idle task promises to call + * sched_ttwu_pending() and reschedule soon. + */ +static bool set_nr_if_polling(struct task_struct *p) +{ + struct thread_info *ti = task_thread_info(p); + typeof(ti->flags) old, val = READ_ONCE(ti->flags); + + for (;;) { + if (!(val & _TIF_POLLING_NRFLAG)) + return false; + if (val & _TIF_NEED_RESCHED) + return true; + old = cmpxchg(&ti->flags, val, val | _TIF_NEED_RESCHED); + if (old == val) + break; + val = old; + } + return true; +} + +#else +static bool set_nr_and_not_polling(struct task_struct *p) +{ + set_tsk_need_resched(p); + return true; +} + +#ifdef CONFIG_SMP +static bool set_nr_if_polling(struct task_struct *p) +{ + return false; +} +#endif +#endif + +#ifdef CONFIG_NO_HZ_FULL +/* + * Tick may be needed by tasks in the runqueue depending on their policy and + * requirements. If tick is needed, lets send the target an IPI to kick it out + * of nohz mode if necessary. + */ +static inline void sched_update_tick_dependency(struct rq *rq) +{ + int cpu; + + if (!tick_nohz_full_enabled()) + return; + + cpu = cpu_of(rq); + + if (!tick_nohz_full_cpu(cpu)) + return; + + if (rq->nr_running < 2) + tick_nohz_dep_clear_cpu(cpu, TICK_DEP_BIT_SCHED); + else + tick_nohz_dep_set_cpu(cpu, TICK_DEP_BIT_SCHED); +} +#else /* !CONFIG_NO_HZ_FULL */ +static inline void sched_update_tick_dependency(struct rq *rq) { } +#endif + +/* + * Add/Remove/Requeue task to/from the runqueue routines + * Context: rq->lock + */ +static inline void dequeue_task(struct task_struct *p, struct rq *rq, int flags) +{ + lockdep_assert_held(&rq->lock); + + WARN_ONCE(task_rq(p) != rq, "bmq: dequeue task reside on cpu%d from cpu%d\n", + task_cpu(p), cpu_of(rq)); + + list_del(&p->bmq_node); + if (list_empty(&rq->queue.heads[p->bmq_idx])) { + clear_bit(p->bmq_idx, rq->queue.bitmap); + update_sched_rq_watermark(rq); + } + --rq->nr_running; +#ifdef CONFIG_SMP + if (1 == rq->nr_running) + cpumask_clear_cpu(cpu_of(rq), &sched_rq_pending_mask); +#endif + + sched_update_tick_dependency(rq); + psi_dequeue(p, flags & DEQUEUE_SLEEP); + + sched_info_dequeued(rq, p); +} + +static inline void enqueue_task(struct task_struct *p, struct rq *rq, int flags) +{ + lockdep_assert_held(&rq->lock); + + WARN_ONCE(task_rq(p) != rq, "bmq: enqueue task reside on cpu%d to cpu%d\n", + task_cpu(p), cpu_of(rq)); + + p->bmq_idx = task_sched_prio(p); + bmq_add_task(p, &rq->queue, p->bmq_idx); + set_bit(p->bmq_idx, rq->queue.bitmap); + update_sched_rq_watermark(rq); + ++rq->nr_running; +#ifdef CONFIG_SMP + if (2 == rq->nr_running) + cpumask_set_cpu(cpu_of(rq), &sched_rq_pending_mask); +#endif + + sched_update_tick_dependency(rq); + + sched_info_queued(rq, p); + psi_enqueue(p, flags); + + /* + * If in_iowait is set, the code below may not trigger any cpufreq + * utilization updates, so do it here explicitly with the IOWAIT flag + * passed. + */ + if (p->in_iowait) + cpufreq_update_util(rq, SCHED_CPUFREQ_IOWAIT); +} + +static inline void requeue_task(struct task_struct *p, struct rq *rq) +{ + int idx = task_sched_prio(p); + + lockdep_assert_held(&rq->lock); + WARN_ONCE(task_rq(p) != rq, "bmq: cpu[%d] requeue task reside on cpu%d\n", + cpu_of(rq), task_cpu(p)); + + list_del(&p->bmq_node); + bmq_add_task(p, &rq->queue, idx); + if (idx != p->bmq_idx) { + if (list_empty(&rq->queue.heads[p->bmq_idx])) + clear_bit(p->bmq_idx, rq->queue.bitmap); + p->bmq_idx = idx; + set_bit(p->bmq_idx, rq->queue.bitmap); + update_sched_rq_watermark(rq); + } +} + +/* + * resched_curr - mark rq's current task 'to be rescheduled now'. + * + * On UP this means the setting of the need_resched flag, on SMP it + * might also involve a cross-CPU call to trigger the scheduler on + * the target CPU. + */ +void resched_curr(struct rq *rq) +{ + struct task_struct *curr = rq->curr; + int cpu; + + lockdep_assert_held(&rq->lock); + + if (test_tsk_need_resched(curr)) + return; + + cpu = cpu_of(rq); + if (cpu == smp_processor_id()) { + set_tsk_need_resched(curr); + set_preempt_need_resched(); + return; + } + + if (set_nr_and_not_polling(curr)) + smp_send_reschedule(cpu); + else + trace_sched_wake_idle_without_ipi(cpu); +} + +void resched_cpu(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + + raw_spin_lock_irqsave(&rq->lock, flags); + if (cpu_online(cpu) || cpu == smp_processor_id()) + resched_curr(cpu_rq(cpu)); + raw_spin_unlock_irqrestore(&rq->lock, flags); +} + +static inline void check_preempt_curr(struct rq *rq) +{ + if (rq_first_bmq_task(rq) != rq->curr) + resched_curr(rq); +} + +#ifdef CONFIG_SCHED_HRTICK +/* + * Use HR-timers to deliver accurate preemption points. + */ + +static void hrtick_clear(struct rq *rq) +{ + if (hrtimer_active(&rq->hrtick_timer)) + hrtimer_cancel(&rq->hrtick_timer); +} + +/* + * High-resolution timer tick. + * Runs from hardirq context with interrupts disabled. + */ +static enum hrtimer_restart hrtick(struct hrtimer *timer) +{ + struct rq *rq = container_of(timer, struct rq, hrtick_timer); + struct task_struct *p; + + WARN_ON_ONCE(cpu_of(rq) != smp_processor_id()); + + raw_spin_lock(&rq->lock); + p = rq->curr; + p->time_slice = 0; + resched_curr(rq); + raw_spin_unlock(&rq->lock); + + return HRTIMER_NORESTART; +} + +/* + * Use hrtick when: + * - enabled by features + * - hrtimer is actually high res + */ +static inline int hrtick_enabled(struct rq *rq) +{ + /** + * BMQ doesn't support sched_feat yet + if (!sched_feat(HRTICK)) + return 0; + */ + if (!cpu_active(cpu_of(rq))) + return 0; + return hrtimer_is_hres_active(&rq->hrtick_timer); +} + +#ifdef CONFIG_SMP + +static void __hrtick_restart(struct rq *rq) +{ + struct hrtimer *timer = &rq->hrtick_timer; + + hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED_HARD); +} + +/* + * called from hardirq (IPI) context + */ +static void __hrtick_start(void *arg) +{ + struct rq *rq = arg; + + raw_spin_lock(&rq->lock); + __hrtick_restart(rq); + rq->hrtick_csd_pending = 0; + raw_spin_unlock(&rq->lock); +} + +/* + * Called to set the hrtick timer state. + * + * called with rq->lock held and irqs disabled + */ +void hrtick_start(struct rq *rq, u64 delay) +{ + struct hrtimer *timer = &rq->hrtick_timer; + ktime_t time; + s64 delta; + + /* + * Don't schedule slices shorter than 10000ns, that just + * doesn't make sense and can cause timer DoS. + */ + delta = max_t(s64, delay, 10000LL); + time = ktime_add_ns(timer->base->get_time(), delta); + + hrtimer_set_expires(timer, time); + + if (rq == this_rq()) { + __hrtick_restart(rq); + } else if (!rq->hrtick_csd_pending) { + smp_call_function_single_async(cpu_of(rq), &rq->hrtick_csd); + rq->hrtick_csd_pending = 1; + } +} + +#else +/* + * Called to set the hrtick timer state. + * + * called with rq->lock held and irqs disabled + */ +void hrtick_start(struct rq *rq, u64 delay) +{ + /* + * Don't schedule slices shorter than 10000ns, that just + * doesn't make sense. Rely on vruntime for fairness. + */ + delay = max_t(u64, delay, 10000LL); + hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay), + HRTIMER_MODE_REL_PINNED_HARD); +} +#endif /* CONFIG_SMP */ + +static void hrtick_rq_init(struct rq *rq) +{ +#ifdef CONFIG_SMP + rq->hrtick_csd_pending = 0; + + rq->hrtick_csd.flags = 0; + rq->hrtick_csd.func = __hrtick_start; + rq->hrtick_csd.info = rq; +#endif + + hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); + rq->hrtick_timer.function = hrtick; +} +#else /* CONFIG_SCHED_HRTICK */ +static inline int hrtick_enabled(struct rq *rq) +{ + return 0; +} + +static inline void hrtick_clear(struct rq *rq) +{ +} + +static inline void hrtick_rq_init(struct rq *rq) +{ +} +#endif /* CONFIG_SCHED_HRTICK */ + +static inline int normal_prio(struct task_struct *p) +{ + if (task_has_rt_policy(p)) + return MAX_RT_PRIO - 1 - p->rt_priority; + + return p->static_prio + MAX_PRIORITY_ADJ; +} + +/* + * Calculate the current priority, i.e. the priority + * taken into account by the scheduler. This value might + * be boosted by RT tasks as it will be RT if the task got + * RT-boosted. If not then it returns p->normal_prio. + */ +static int effective_prio(struct task_struct *p) +{ + p->normal_prio = normal_prio(p); + /* + * If we are RT tasks or we were boosted to RT priority, + * keep the priority unchanged. Otherwise, update priority + * to the normal priority: + */ + if (!rt_prio(p->prio)) + return p->normal_prio; + return p->prio; +} + +/* + * activate_task - move a task to the runqueue. + * + * Context: rq->lock + */ +static void activate_task(struct task_struct *p, struct rq *rq) +{ + if (task_contributes_to_load(p)) + rq->nr_uninterruptible--; + enqueue_task(p, rq, ENQUEUE_WAKEUP); + p->on_rq = TASK_ON_RQ_QUEUED; + cpufreq_update_util(rq, 0); +} + +/* + * deactivate_task - remove a task from the runqueue. + * + * Context: rq->lock + */ +static inline void deactivate_task(struct task_struct *p, struct rq *rq) +{ + if (task_contributes_to_load(p)) + rq->nr_uninterruptible++; + dequeue_task(p, rq, DEQUEUE_SLEEP); + p->on_rq = 0; + cpufreq_update_util(rq, 0); +} + +static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu) +{ +#ifdef CONFIG_SMP + /* + * After ->cpu is set up to a new value, task_access_lock(p, ...) can be + * successfully executed on another CPU. We must ensure that updates of + * per-task data have been completed by this moment. + */ + smp_wmb(); + +#ifdef CONFIG_THREAD_INFO_IN_TASK + WRITE_ONCE(p->cpu, cpu); +#else + WRITE_ONCE(task_thread_info(p)->cpu, cpu); +#endif +#endif +} + +#ifdef CONFIG_SMP +void set_task_cpu(struct task_struct *p, unsigned int new_cpu) +{ +#ifdef CONFIG_SCHED_DEBUG + /* + * We should never call set_task_cpu() on a blocked task, + * ttwu() will sort out the placement. + */ + WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING && + !p->on_rq); +#ifdef CONFIG_LOCKDEP + /* + * The caller should hold either p->pi_lock or rq->lock, when changing + * a task's CPU. ->pi_lock for waking tasks, rq->lock for runnable tasks. + * + * sched_move_task() holds both and thus holding either pins the cgroup, + * see task_group(). + */ + WARN_ON_ONCE(debug_locks && !(lockdep_is_held(&p->pi_lock) || + lockdep_is_held(&task_rq(p)->lock))); +#endif + /* + * Clearly, migrating tasks to offline CPUs is a fairly daft thing. + */ + WARN_ON_ONCE(!cpu_online(new_cpu)); +#endif + if (task_cpu(p) == new_cpu) + return; + trace_sched_migrate_task(p, new_cpu); + rseq_migrate(p); + perf_event_task_migrate(p); + + __set_task_cpu(p, new_cpu); +} + +static inline bool is_per_cpu_kthread(struct task_struct *p) +{ + return ((p->flags & PF_KTHREAD) && (1 == p->nr_cpus_allowed)); +} + +/* + * Per-CPU kthreads are allowed to run on !active && online CPUs, see + * __set_cpus_allowed_ptr() and select_fallback_rq(). + */ +static inline bool is_cpu_allowed(struct task_struct *p, int cpu) +{ + if (!cpumask_test_cpu(cpu, p->cpus_ptr)) + return false; + + if (is_per_cpu_kthread(p)) + return cpu_online(cpu); + + return cpu_active(cpu); +} + +/* + * This is how migration works: + * + * 1) we invoke migration_cpu_stop() on the target CPU using + * stop_one_cpu(). + * 2) stopper starts to run (implicitly forcing the migrated thread + * off the CPU) + * 3) it checks whether the migrated task is still in the wrong runqueue. + * 4) if it's in the wrong runqueue then the migration thread removes + * it and puts it into the right queue. + * 5) stopper completes and stop_one_cpu() returns and the migration + * is done. + */ + +/* + * move_queued_task - move a queued task to new rq. + * + * Returns (locked) new rq. Old rq's lock is released. + */ +static struct rq *move_queued_task(struct rq *rq, struct task_struct *p, int + new_cpu) +{ + lockdep_assert_held(&rq->lock); + + WRITE_ONCE(p->on_rq, TASK_ON_RQ_MIGRATING); + dequeue_task(p, rq, 0); + set_task_cpu(p, new_cpu); + raw_spin_unlock(&rq->lock); + + rq = cpu_rq(new_cpu); + + raw_spin_lock(&rq->lock); + BUG_ON(task_cpu(p) != new_cpu); + enqueue_task(p, rq, 0); + p->on_rq = TASK_ON_RQ_QUEUED; + check_preempt_curr(rq); + + return rq; +} + +struct migration_arg { + struct task_struct *task; + int dest_cpu; +}; + +/* + * Move (not current) task off this CPU, onto the destination CPU. We're doing + * this because either it can't run here any more (set_cpus_allowed() + * away from this CPU, or CPU going down), or because we're + * attempting to rebalance this task on exec (sched_exec). + * + * So we race with normal scheduler movements, but that's OK, as long + * as the task is no longer on this CPU. + */ +static struct rq *__migrate_task(struct rq *rq, struct task_struct *p, int + dest_cpu) +{ + /* Affinity changed (again). */ + if (!is_cpu_allowed(p, dest_cpu)) + return rq; + + update_rq_clock(rq); + return move_queued_task(rq, p, dest_cpu); +} + +/* + * migration_cpu_stop - this will be executed by a highprio stopper thread + * and performs thread migration by bumping thread off CPU then + * 'pushing' onto another runqueue. + */ +static int migration_cpu_stop(void *data) +{ + struct migration_arg *arg = data; + struct task_struct *p = arg->task; + struct rq *rq = this_rq(); + + /* + * The original target CPU might have gone down and we might + * be on another CPU but it doesn't matter. + */ + local_irq_disable(); + + raw_spin_lock(&p->pi_lock); + raw_spin_lock(&rq->lock); + /* + * If task_rq(p) != rq, it cannot be migrated here, because we're + * holding rq->lock, if p->on_rq == 0 it cannot get enqueued because + * we're holding p->pi_lock. + */ + if (task_rq(p) == rq && task_on_rq_queued(p)) + rq = __migrate_task(rq, p, arg->dest_cpu); + raw_spin_unlock(&rq->lock); + raw_spin_unlock(&p->pi_lock); + + local_irq_enable(); + return 0; +} + +static inline void +set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask) +{ + cpumask_copy(&p->cpus_mask, new_mask); + p->nr_cpus_allowed = cpumask_weight(new_mask); +} + +void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) +{ + set_cpus_allowed_common(p, new_mask); +} +#endif + +/* Enter with rq lock held. We know p is on the local CPU */ +static inline void __set_tsk_resched(struct task_struct *p) +{ + set_tsk_need_resched(p); + set_preempt_need_resched(); +} + +/** + * task_curr - is this task currently executing on a CPU? + * @p: the task in question. + * + * Return: 1 if the task is currently executing. 0 otherwise. + */ +inline int task_curr(const struct task_struct *p) +{ + return cpu_curr(task_cpu(p)) == p; +} + +#ifdef CONFIG_SMP +/* + * wait_task_inactive - wait for a thread to unschedule. + * + * If @match_state is nonzero, it's the @p->state value just checked and + * not expected to change. If it changes, i.e. @p might have woken up, + * then return zero. When we succeed in waiting for @p to be off its CPU, + * we return a positive number (its total switch count). If a second call + * a short while later returns the same number, the caller can be sure that + * @p has remained unscheduled the whole time. + * + * The caller must ensure that the task *will* unschedule sometime soon, + * else this function might spin for a *long* time. This function can't + * be called with interrupts off, or it may introduce deadlock with + * smp_call_function() if an IPI is sent by the same process we are + * waiting to become inactive. + */ +unsigned long wait_task_inactive(struct task_struct *p, long match_state) +{ + unsigned long flags; + bool running, on_rq; + unsigned long ncsw; + struct rq *rq; + raw_spinlock_t *lock; + + for (;;) { + rq = task_rq(p); + + /* + * If the task is actively running on another CPU + * still, just relax and busy-wait without holding + * any locks. + * + * NOTE! Since we don't hold any locks, it's not + * even sure that "rq" stays as the right runqueue! + * But we don't care, since this will return false + * if the runqueue has changed and p is actually now + * running somewhere else! + */ + while (task_running(p) && p == rq->curr) { + if (match_state && unlikely(p->state != match_state)) + return 0; + cpu_relax(); + } + + /* + * Ok, time to look more closely! We need the rq + * lock now, to be *sure*. If we're wrong, we'll + * just go back and repeat. + */ + task_access_lock_irqsave(p, &lock, &flags); + trace_sched_wait_task(p); + running = task_running(p); + on_rq = p->on_rq; + ncsw = 0; + if (!match_state || p->state == match_state) + ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ + task_access_unlock_irqrestore(p, lock, &flags); + + /* + * If it changed from the expected state, bail out now. + */ + if (unlikely(!ncsw)) + break; + + /* + * Was it really running after all now that we + * checked with the proper locks actually held? + * + * Oops. Go back and try again.. + */ + if (unlikely(running)) { + cpu_relax(); + continue; + } + + /* + * It's not enough that it's not actively running, + * it must be off the runqueue _entirely_, and not + * preempted! + * + * So if it was still runnable (but just not actively + * running right now), it's preempted, and we should + * yield - it could be a while. + */ + if (unlikely(on_rq)) { + ktime_t to = NSEC_PER_SEC / HZ; + + set_current_state(TASK_UNINTERRUPTIBLE); + schedule_hrtimeout(&to, HRTIMER_MODE_REL); + continue; + } + + /* + * Ahh, all good. It wasn't running, and it wasn't + * runnable, which means that it will never become + * running in the future either. We're all done! + */ + break; + } + + return ncsw; +} + +/*** + * kick_process - kick a running thread to enter/exit the kernel + * @p: the to-be-kicked thread + * + * Cause a process which is running on another CPU to enter + * kernel-mode, without any delay. (to get signals handled.) + * + * NOTE: this function doesn't have to take the runqueue lock, + * because all it wants to ensure is that the remote task enters + * the kernel. If the IPI races and the task has been migrated + * to another CPU then no harm is done and the purpose has been + * achieved as well. + */ +void kick_process(struct task_struct *p) +{ + int cpu; + + preempt_disable(); + cpu = task_cpu(p); + if ((cpu != smp_processor_id()) && task_curr(p)) + smp_send_reschedule(cpu); + preempt_enable(); +} +EXPORT_SYMBOL_GPL(kick_process); + +/* + * ->cpus_ptr is protected by both rq->lock and p->pi_lock + * + * A few notes on cpu_active vs cpu_online: + * + * - cpu_active must be a subset of cpu_online + * + * - on CPU-up we allow per-CPU kthreads on the online && !active CPU, + * see __set_cpus_allowed_ptr(). At this point the newly online + * CPU isn't yet part of the sched domains, and balancing will not + * see it. + * + * - on cpu-down we clear cpu_active() to mask the sched domains and + * avoid the load balancer to place new tasks on the to be removed + * CPU. Existing tasks will remain running there and will be taken + * off. + * + * This means that fallback selection must not select !active CPUs. + * And can assume that any active CPU must be online. Conversely + * select_task_rq() below may allow selection of !active CPUs in order + * to satisfy the above rules. + */ +static int select_fallback_rq(int cpu, struct task_struct *p) +{ + int nid = cpu_to_node(cpu); + const struct cpumask *nodemask = NULL; + enum { cpuset, possible, fail } state = cpuset; + int dest_cpu; + + /* + * If the node that the CPU is on has been offlined, cpu_to_node() + * will return -1. There is no CPU on the node, and we should + * select the CPU on the other node. + */ + if (nid != -1) { + nodemask = cpumask_of_node(nid); + + /* Look for allowed, online CPU in same node. */ + for_each_cpu(dest_cpu, nodemask) { + if (!cpu_active(dest_cpu)) + continue; + if (cpumask_test_cpu(dest_cpu, p->cpus_ptr)) + return dest_cpu; + } + } + + for (;;) { + /* Any allowed, online CPU? */ + for_each_cpu(dest_cpu, p->cpus_ptr) { + if (!is_cpu_allowed(p, dest_cpu)) + continue; + goto out; + } + + /* No more Mr. Nice Guy. */ + switch (state) { + case cpuset: + if (IS_ENABLED(CONFIG_CPUSETS)) { + cpuset_cpus_allowed_fallback(p); + state = possible; + break; + } + /* Fall-through */ + case possible: + do_set_cpus_allowed(p, cpu_possible_mask); + state = fail; + break; + + case fail: + BUG(); + break; + } + } + +out: + if (state != cpuset) { + /* + * Don't tell them about moving exiting tasks or + * kernel threads (both mm NULL), since they never + * leave kernel. + */ + if (p->mm && printk_ratelimit()) { + printk_deferred("process %d (%s) no longer affine to cpu%d\n", + task_pid_nr(p), p->comm, cpu); + } + } + + return dest_cpu; +} + +static inline int __best_mask_cpu(int cpu, const cpumask_t *cpumask) +{ + cpumask_t *mask = &(per_cpu(sched_cpu_affinity_masks, cpu)[0]); + while ((cpu = cpumask_any_and(cpumask, mask)) >= nr_cpu_ids) + mask++; + return cpu; +} + +static inline int best_mask_cpu(int cpu, const cpumask_t *cpumask) +{ + return cpumask_test_cpu(cpu, cpumask)? cpu:__best_mask_cpu(cpu, cpumask); +} + +/* + * wake flags + */ +#define WF_SYNC 0x01 /* waker goes to sleep after wakeup */ +#define WF_FORK 0x02 /* child wakeup after fork */ +#define WF_MIGRATED 0x04 /* internal use, task got migrated */ + +static inline int select_task_rq(struct task_struct *p) +{ + cpumask_t chk_mask, tmp; + + if (unlikely(!cpumask_and(&chk_mask, p->cpus_ptr, cpu_online_mask))) + return select_fallback_rq(task_cpu(p), p); + + if ( +#ifdef CONFIG_SCHED_SMT + cpumask_and(&tmp, &chk_mask, &sched_sg_idle_mask) || +#endif + cpumask_and(&tmp, &chk_mask, &sched_rq_watermark[IDLE_WM]) || + cpumask_and(&tmp, &chk_mask, + &sched_rq_watermark[task_sched_prio(p) + 1])) + return best_mask_cpu(task_cpu(p), &tmp); + + return best_mask_cpu(task_cpu(p), &chk_mask); +} +#else /* CONFIG_SMP */ +static inline int select_task_rq(struct task_struct *p) +{ + return 0; +} +#endif /* CONFIG_SMP */ + +static void +ttwu_stat(struct task_struct *p, int cpu, int wake_flags) +{ + struct rq *rq; + + if (!schedstat_enabled()) + return; + + rq= this_rq(); + +#ifdef CONFIG_SMP + if (cpu == rq->cpu) + __schedstat_inc(rq->ttwu_local); + else { + /** BMQ ToDo: + * How to do ttwu_wake_remote + */ + } +#endif /* CONFIG_SMP */ + + __schedstat_inc(rq->ttwu_count); +} + +/* + * Mark the task runnable and perform wakeup-preemption. + */ +static inline void +ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags) +{ + p->state = TASK_RUNNING; + trace_sched_wakeup(p); +} + +static inline void +ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags) +{ +#ifdef CONFIG_SMP + if (p->sched_contributes_to_load) + rq->nr_uninterruptible--; +#endif + + activate_task(p, rq); + ttwu_do_wakeup(rq, p, 0); +} + +static inline void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) +{ + struct rq *rq = cpu_rq(cpu); + + raw_spin_lock(&rq->lock); + update_rq_clock(rq); + ttwu_do_activate(rq, p, wake_flags); + check_preempt_curr(rq); + raw_spin_unlock(&rq->lock); +} + +static int ttwu_remote(struct task_struct *p, int wake_flags) +{ + struct rq *rq; + raw_spinlock_t *lock; + int ret = 0; + + rq = __task_access_lock(p, &lock); + if (task_on_rq_queued(p)) { + ttwu_do_wakeup(rq, p, wake_flags); + ret = 1; + } + __task_access_unlock(p, lock); + + return ret; +} + +/* + * Notes on Program-Order guarantees on SMP systems. + * + * MIGRATION + * + * The basic program-order guarantee on SMP systems is that when a task [t] + * migrates, all its activity on its old CPU [c0] happens-before any subsequent + * execution on its new CPU [c1]. + * + * For migration (of runnable tasks) this is provided by the following means: + * + * A) UNLOCK of the rq(c0)->lock scheduling out task t + * B) migration for t is required to synchronize *both* rq(c0)->lock and + * rq(c1)->lock (if not at the same time, then in that order). + * C) LOCK of the rq(c1)->lock scheduling in task + * + * Transitivity guarantees that B happens after A and C after B. + * Note: we only require RCpc transitivity. + * Note: the CPU doing B need not be c0 or c1 + * + * Example: + * + * CPU0 CPU1 CPU2 + * + * LOCK rq(0)->lock + * sched-out X + * sched-in Y + * UNLOCK rq(0)->lock + * + * LOCK rq(0)->lock // orders against CPU0 + * dequeue X + * UNLOCK rq(0)->lock + * + * LOCK rq(1)->lock + * enqueue X + * UNLOCK rq(1)->lock + * + * LOCK rq(1)->lock // orders against CPU2 + * sched-out Z + * sched-in X + * UNLOCK rq(1)->lock + * + * + * BLOCKING -- aka. SLEEP + WAKEUP + * + * For blocking we (obviously) need to provide the same guarantee as for + * migration. However the means are completely different as there is no lock + * chain to provide order. Instead we do: + * + * 1) smp_store_release(X->on_cpu, 0) + * 2) smp_cond_load_acquire(!X->on_cpu) + * + * Example: + * + * CPU0 (schedule) CPU1 (try_to_wake_up) CPU2 (schedule) + * + * LOCK rq(0)->lock LOCK X->pi_lock + * dequeue X + * sched-out X + * smp_store_release(X->on_cpu, 0); + * + * smp_cond_load_acquire(&X->on_cpu, !VAL); + * X->state = WAKING + * set_task_cpu(X,2) + * + * LOCK rq(2)->lock + * enqueue X + * X->state = RUNNING + * UNLOCK rq(2)->lock + * + * LOCK rq(2)->lock // orders against CPU1 + * sched-out Z + * sched-in X + * UNLOCK rq(2)->lock + * + * UNLOCK X->pi_lock + * UNLOCK rq(0)->lock + * + * + * However; for wakeups there is a second guarantee we must provide, namely we + * must observe the state that lead to our wakeup. That is, not only must our + * task observe its own prior state, it must also observe the stores prior to + * its wakeup. + * + * This means that any means of doing remote wakeups must order the CPU doing + * the wakeup against the CPU the task is going to end up running on. This, + * however, is already required for the regular Program-Order guarantee above, + * since the waking CPU is the one issueing the ACQUIRE (smp_cond_load_acquire). + * + */ + +/*** + * try_to_wake_up - wake up a thread + * @p: the thread to be awakened + * @state: the mask of task states that can be woken + * @wake_flags: wake modifier flags (WF_*) + * + * Put it on the run-queue if it's not already there. The "current" + * thread is always on the run-queue (except when the actual + * re-schedule is in progress), and as such you're allowed to do + * the simpler "current->state = TASK_RUNNING" to mark yourself + * runnable without the overhead of this. + * + * Return: %true if @p was woken up, %false if it was already running. + * or @state didn't match @p's state. + */ +static int try_to_wake_up(struct task_struct *p, unsigned int state, + int wake_flags) +{ + unsigned long flags; + int cpu, success = 0; + + preempt_disable(); + if (p == current) { + /* + * We're waking current, this means 'p->on_rq' and 'task_cpu(p) + * == smp_processor_id()'. Together this means we can special + * case the whole 'p->on_rq && ttwu_remote()' case below + * without taking any locks. + * + * In particular: + * - we rely on Program-Order guarantees for all the ordering, + * - we're serialized against set_special_state() by virtue of + * it disabling IRQs (this allows not taking ->pi_lock). + */ + if (!(p->state & state)) + goto out; + + success = 1; + cpu = task_cpu(p); + trace_sched_waking(p); + p->state = TASK_RUNNING; + trace_sched_wakeup(p); + goto out; + } + + /* + * If we are going to wake up a thread waiting for CONDITION we + * need to ensure that CONDITION=1 done by the caller can not be + * reordered with p->state check below. This pairs with mb() in + * set_current_state() the waiting thread does. + */ + raw_spin_lock_irqsave(&p->pi_lock, flags); + smp_mb__after_spinlock(); + if (!(p->state & state)) + goto unlock; + + trace_sched_waking(p); + + /* We're going to change ->state: */ + success = 1; + cpu = task_cpu(p); + + /* + * Ensure we load p->on_rq _after_ p->state, otherwise it would + * be possible to, falsely, observe p->on_rq == 0 and get stuck + * in smp_cond_load_acquire() below. + * + * sched_ttwu_pending() try_to_wake_up() + * STORE p->on_rq = 1 LOAD p->state + * UNLOCK rq->lock + * + * __schedule() (switch to task 'p') + * LOCK rq->lock smp_rmb(); + * smp_mb__after_spinlock(); + * UNLOCK rq->lock + * + * [task p] + * STORE p->state = UNINTERRUPTIBLE LOAD p->on_rq + * + * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in + * __schedule(). See the comment for smp_mb__after_spinlock(). + */ + smp_rmb(); + if (p->on_rq && ttwu_remote(p, wake_flags)) + goto unlock; + +#ifdef CONFIG_SMP + /* + * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be + * possible to, falsely, observe p->on_cpu == 0. + * + * One must be running (->on_cpu == 1) in order to remove oneself + * from the runqueue. + * + * __schedule() (switch to task 'p') try_to_wake_up() + * STORE p->on_cpu = 1 LOAD p->on_rq + * UNLOCK rq->lock + * + * __schedule() (put 'p' to sleep) + * LOCK rq->lock smp_rmb(); + * smp_mb__after_spinlock(); + * STORE p->on_rq = 0 LOAD p->on_cpu + * + * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in + * __schedule(). See the comment for smp_mb__after_spinlock(). + */ + smp_rmb(); + + /* + * If the owning (remote) CPU is still in the middle of schedule() with + * this task as prev, wait until its done referencing the task. + * + * Pairs with the smp_store_release() in finish_task(). + * + * This ensures that tasks getting woken will be fully ordered against + * their previous state and preserve Program Order. + */ + smp_cond_load_acquire(&p->on_cpu, !VAL); + + p->sched_contributes_to_load = !!task_contributes_to_load(p); + p->state = TASK_WAKING; + + if (p->in_iowait) { + delayacct_blkio_end(p); + atomic_dec(&task_rq(p)->nr_iowait); + } + + if(cpu_rq(smp_processor_id())->clock - p->last_ran > SCHED_TIMESLICE_NS) + boost_task(p); + + cpu = select_task_rq(p); + + if (cpu != task_cpu(p)) { + wake_flags |= WF_MIGRATED; + psi_ttwu_dequeue(p); + set_task_cpu(p, cpu); + } +#else /* CONFIG_SMP */ + if (p->in_iowait) { + delayacct_blkio_end(p); + atomic_dec(&task_rq(p)->nr_iowait); + } +#endif /* CONFIG_SMP */ + + ttwu_queue(p, cpu, wake_flags); +unlock: + raw_spin_unlock_irqrestore(&p->pi_lock, flags); +out: + if (success) + ttwu_stat(p, cpu, wake_flags); + preempt_enable(); + + return success; +} + +/** + * wake_up_process - Wake up a specific process + * @p: The process to be woken up. + * + * Attempt to wake up the nominated process and move it to the set of runnable + * processes. + * + * Return: 1 if the process was woken up, 0 if it was already running. + * + * This function executes a full memory barrier before accessing the task state. + */ +int wake_up_process(struct task_struct *p) +{ + return try_to_wake_up(p, TASK_NORMAL, 0); +} +EXPORT_SYMBOL(wake_up_process); + +int wake_up_state(struct task_struct *p, unsigned int state) +{ + return try_to_wake_up(p, state, 0); +} + +/* + * Perform scheduler related setup for a newly forked process p. + * p is forked by current. + */ +int sched_fork(unsigned long __maybe_unused clone_flags, struct task_struct *p) +{ + unsigned long flags; + int cpu = get_cpu(); + struct rq *rq = this_rq(); + +#ifdef CONFIG_PREEMPT_NOTIFIERS + INIT_HLIST_HEAD(&p->preempt_notifiers); +#endif + /* Should be reset in fork.c but done here for ease of BMQ patching */ + p->on_cpu = + p->on_rq = + p->utime = + p->stime = + p->sched_time = 0; + +#ifdef CONFIG_COMPACTION + p->capture_control = NULL; +#endif + + /* + * We mark the process as NEW here. This guarantees that + * nobody will actually run it, and a signal or other external + * event cannot wake it up and insert it on the runqueue either. + */ + p->state = TASK_NEW; + + /* + * Make sure we do not leak PI boosting priority to the child. + */ + p->prio = current->normal_prio; + + /* + * Revert to default priority/policy on fork if requested. + */ + if (unlikely(p->sched_reset_on_fork)) { + if (task_has_rt_policy(p)) { + p->policy = SCHED_NORMAL; + p->static_prio = NICE_TO_PRIO(0); + p->rt_priority = 0; + } else if (PRIO_TO_NICE(p->static_prio) < 0) + p->static_prio = NICE_TO_PRIO(0); + + p->prio = p->normal_prio = normal_prio(p); + + /* + * We don't need the reset flag anymore after the fork. It has + * fulfilled its duty: + */ + p->sched_reset_on_fork = 0; + } + + p->boost_prio = (p->boost_prio < 0) ? + p->boost_prio + MAX_PRIORITY_ADJ : MAX_PRIORITY_ADJ; + /* + * Share the timeslice between parent and child, thus the + * total amount of pending timeslices in the system doesn't change, + * resulting in more scheduling fairness. + */ + raw_spin_lock_irqsave(&rq->lock, flags); + rq->curr->time_slice /= 2; + p->time_slice = rq->curr->time_slice; +#ifdef CONFIG_SCHED_HRTICK + hrtick_start(rq, rq->curr->time_slice); +#endif + + if (p->time_slice < RESCHED_NS) { + p->time_slice = SCHED_TIMESLICE_NS; + resched_curr(rq); + } + raw_spin_unlock_irqrestore(&rq->lock, flags); + + /* + * The child is not yet in the pid-hash so no cgroup attach races, + * and the cgroup is pinned to this child due to cgroup_fork() + * is ran before sched_fork(). + * + * Silence PROVE_RCU. + */ + raw_spin_lock_irqsave(&p->pi_lock, flags); + /* + * We're setting the CPU for the first time, we don't migrate, + * so use __set_task_cpu(). + */ + __set_task_cpu(p, cpu); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + +#ifdef CONFIG_SCHED_INFO + if (unlikely(sched_info_on())) + memset(&p->sched_info, 0, sizeof(p->sched_info)); +#endif + init_task_preempt_count(p); + + put_cpu(); + return 0; +} + +#ifdef CONFIG_SCHEDSTATS + +DEFINE_STATIC_KEY_FALSE(sched_schedstats); +static bool __initdata __sched_schedstats = false; + +static void set_schedstats(bool enabled) +{ + if (enabled) + static_branch_enable(&sched_schedstats); + else + static_branch_disable(&sched_schedstats); +} + +void force_schedstat_enabled(void) +{ + if (!schedstat_enabled()) { + pr_info("kernel profiling enabled schedstats, disable via kernel.sched_schedstats.\n"); + static_branch_enable(&sched_schedstats); + } +} + +static int __init setup_schedstats(char *str) +{ + int ret = 0; + if (!str) + goto out; + + /* + * This code is called before jump labels have been set up, so we can't + * change the static branch directly just yet. Instead set a temporary + * variable so init_schedstats() can do it later. + */ + if (!strcmp(str, "enable")) { + __sched_schedstats = true; + ret = 1; + } else if (!strcmp(str, "disable")) { + __sched_schedstats = false; + ret = 1; + } +out: + if (!ret) + pr_warn("Unable to parse schedstats=\n"); + + return ret; +} +__setup("schedstats=", setup_schedstats); + +static void __init init_schedstats(void) +{ + set_schedstats(__sched_schedstats); +} + +#ifdef CONFIG_PROC_SYSCTL +int sysctl_schedstats(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct ctl_table t; + int err; + int state = static_branch_likely(&sched_schedstats); + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + t = *table; + t.data = &state; + err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); + if (err < 0) + return err; + if (write) + set_schedstats(state); + return err; +} +#endif /* CONFIG_PROC_SYSCTL */ +#else /* !CONFIG_SCHEDSTATS */ +static inline void init_schedstats(void) {} +#endif /* CONFIG_SCHEDSTATS */ + +/* + * wake_up_new_task - wake up a newly created task for the first time. + * + * This function will do some initial scheduler statistics housekeeping + * that must be done for every newly created context, then puts the task + * on the runqueue and wakes it. + */ +void wake_up_new_task(struct task_struct *p) +{ + unsigned long flags; + struct rq *rq; + + raw_spin_lock_irqsave(&p->pi_lock, flags); + + p->state = TASK_RUNNING; + + rq = cpu_rq(select_task_rq(p)); +#ifdef CONFIG_SMP + /* + * Fork balancing, do it here and not earlier because: + * - cpus_ptr can change in the fork path + * - any previously selected CPU might disappear through hotplug + * Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq, + * as we're not fully set-up yet. + */ + __set_task_cpu(p, cpu_of(rq)); +#endif + + raw_spin_lock(&rq->lock); + + update_rq_clock(rq); + activate_task(p, rq); + trace_sched_wakeup_new(p); + check_preempt_curr(rq); + + raw_spin_unlock(&rq->lock); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); +} + +#ifdef CONFIG_PREEMPT_NOTIFIERS + +static DEFINE_STATIC_KEY_FALSE(preempt_notifier_key); + +void preempt_notifier_inc(void) +{ + static_branch_inc(&preempt_notifier_key); +} +EXPORT_SYMBOL_GPL(preempt_notifier_inc); + +void preempt_notifier_dec(void) +{ + static_branch_dec(&preempt_notifier_key); +} +EXPORT_SYMBOL_GPL(preempt_notifier_dec); + +/** + * preempt_notifier_register - tell me when current is being preempted & rescheduled + * @notifier: notifier struct to register + */ +void preempt_notifier_register(struct preempt_notifier *notifier) +{ + if (!static_branch_unlikely(&preempt_notifier_key)) + WARN(1, "registering preempt_notifier while notifiers disabled\n"); + + hlist_add_head(¬ifier->link, ¤t->preempt_notifiers); +} +EXPORT_SYMBOL_GPL(preempt_notifier_register); + +/** + * preempt_notifier_unregister - no longer interested in preemption notifications + * @notifier: notifier struct to unregister + * + * This is *not* safe to call from within a preemption notifier. + */ +void preempt_notifier_unregister(struct preempt_notifier *notifier) +{ + hlist_del(¬ifier->link); +} +EXPORT_SYMBOL_GPL(preempt_notifier_unregister); + +static void __fire_sched_in_preempt_notifiers(struct task_struct *curr) +{ + struct preempt_notifier *notifier; + + hlist_for_each_entry(notifier, &curr->preempt_notifiers, link) + notifier->ops->sched_in(notifier, raw_smp_processor_id()); +} + +static __always_inline void fire_sched_in_preempt_notifiers(struct task_struct *curr) +{ + if (static_branch_unlikely(&preempt_notifier_key)) + __fire_sched_in_preempt_notifiers(curr); +} + +static void +__fire_sched_out_preempt_notifiers(struct task_struct *curr, + struct task_struct *next) +{ + struct preempt_notifier *notifier; + + hlist_for_each_entry(notifier, &curr->preempt_notifiers, link) + notifier->ops->sched_out(notifier, next); +} + +static __always_inline void +fire_sched_out_preempt_notifiers(struct task_struct *curr, + struct task_struct *next) +{ + if (static_branch_unlikely(&preempt_notifier_key)) + __fire_sched_out_preempt_notifiers(curr, next); +} + +#else /* !CONFIG_PREEMPT_NOTIFIERS */ + +static inline void fire_sched_in_preempt_notifiers(struct task_struct *curr) +{ +} + +static inline void +fire_sched_out_preempt_notifiers(struct task_struct *curr, + struct task_struct *next) +{ +} + +#endif /* CONFIG_PREEMPT_NOTIFIERS */ + +static inline void prepare_task(struct task_struct *next) +{ + /* + * Claim the task as running, we do this before switching to it + * such that any running task will have this set. + */ + next->on_cpu = 1; +} + +static inline void finish_task(struct task_struct *prev) +{ +#ifdef CONFIG_SMP + /* + * After ->on_cpu is cleared, the task can be moved to a different CPU. + * We must ensure this doesn't happen until the switch is completely + * finished. + * + * In particular, the load of prev->state in finish_task_switch() must + * happen before this. + * + * Pairs with the smp_cond_load_acquire() in try_to_wake_up(). + */ + smp_store_release(&prev->on_cpu, 0); +#else + prev->on_cpu = 0; +#endif +} + +static inline void +prepare_lock_switch(struct rq *rq, struct task_struct *next) +{ + /* + * Since the runqueue lock will be released by the next + * task (which is an invalid locking op but in the case + * of the scheduler it's an obvious special-case), so we + * do an early lockdep release here: + */ + spin_release(&rq->lock.dep_map, 1, _THIS_IP_); +#ifdef CONFIG_DEBUG_SPINLOCK + /* this is a valid case when another task releases the spinlock */ + rq->lock.owner = next; +#endif +} + +static inline void finish_lock_switch(struct rq *rq) +{ + /* + * If we are tracking spinlock dependencies then we have to + * fix up the runqueue lock - which gets 'carried over' from + * prev into current: + */ + spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_); + raw_spin_unlock_irq(&rq->lock); +} + +/** + * prepare_task_switch - prepare to switch tasks + * @rq: the runqueue preparing to switch + * @next: the task we are going to switch to. + * + * This is called with the rq lock held and interrupts off. It must + * be paired with a subsequent finish_task_switch after the context + * switch. + * + * prepare_task_switch sets up locking and calls architecture specific + * hooks. + */ +static inline void +prepare_task_switch(struct rq *rq, struct task_struct *prev, + struct task_struct *next) +{ + kcov_prepare_switch(prev); + sched_info_switch(rq, prev, next); + perf_event_task_sched_out(prev, next); + rseq_preempt(prev); + fire_sched_out_preempt_notifiers(prev, next); + prepare_task(next); + prepare_arch_switch(next); +} + +/** + * finish_task_switch - clean up after a task-switch + * @rq: runqueue associated with task-switch + * @prev: the thread we just switched away from. + * + * finish_task_switch must be called after the context switch, paired + * with a prepare_task_switch call before the context switch. + * finish_task_switch will reconcile locking set up by prepare_task_switch, + * and do any other architecture-specific cleanup actions. + * + * Note that we may have delayed dropping an mm in context_switch(). If + * so, we finish that here outside of the runqueue lock. (Doing it + * with the lock held can cause deadlocks; see schedule() for + * details.) + * + * The context switch have flipped the stack from under us and restored the + * local variables which were saved when this task called schedule() in the + * past. prev == current is still correct but we need to recalculate this_rq + * because prev may have moved to another CPU. + */ +static struct rq *finish_task_switch(struct task_struct *prev) + __releases(rq->lock) +{ + struct rq *rq = this_rq(); + struct mm_struct *mm = rq->prev_mm; + long prev_state; + + /* + * The previous task will have left us with a preempt_count of 2 + * because it left us after: + * + * schedule() + * preempt_disable(); // 1 + * __schedule() + * raw_spin_lock_irq(&rq->lock) // 2 + * + * Also, see FORK_PREEMPT_COUNT. + */ + if (WARN_ONCE(preempt_count() != 2*PREEMPT_DISABLE_OFFSET, + "corrupted preempt_count: %s/%d/0x%x\n", + current->comm, current->pid, preempt_count())) + preempt_count_set(FORK_PREEMPT_COUNT); + + rq->prev_mm = NULL; + + /* + * A task struct has one reference for the use as "current". + * If a task dies, then it sets TASK_DEAD in tsk->state and calls + * schedule one last time. The schedule call will never return, and + * the scheduled task must drop that reference. + * + * We must observe prev->state before clearing prev->on_cpu (in + * finish_task), otherwise a concurrent wakeup can get prev + * running on another CPU and we could rave with its RUNNING -> DEAD + * transition, resulting in a double drop. + */ + prev_state = prev->state; + vtime_task_switch(prev); + perf_event_task_sched_in(prev, current); + finish_task(prev); + finish_lock_switch(rq); + finish_arch_post_lock_switch(); + kcov_finish_switch(current); + + fire_sched_in_preempt_notifiers(current); + /* + * When switching through a kernel thread, the loop in + * membarrier_{private,global}_expedited() may have observed that + * kernel thread and not issued an IPI. It is therefore possible to + * schedule between user->kernel->user threads without passing though + * switch_mm(). Membarrier requires a barrier after storing to + * rq->curr, before returning to userspace, so provide them here: + * + * - a full memory barrier for {PRIVATE,GLOBAL}_EXPEDITED, implicitly + * provided by mmdrop(), + * - a sync_core for SYNC_CORE. + */ + if (mm) { + membarrier_mm_sync_core_before_usermode(mm); + mmdrop(mm); + } + if (unlikely(prev_state == TASK_DEAD)) { + /* + * Remove function-return probe instances associated with this + * task and put them back on the free list. + */ + kprobe_flush_task(prev); + + /* Task is done with its stack. */ + put_task_stack(prev); + + put_task_struct_rcu_user(prev); + } + + tick_nohz_task_switch(); + return rq; +} + +/** + * schedule_tail - first thing a freshly forked thread must call. + * @prev: the thread we just switched away from. + */ +asmlinkage __visible void schedule_tail(struct task_struct *prev) + __releases(rq->lock) +{ + struct rq *rq; + + /* + * New tasks start with FORK_PREEMPT_COUNT, see there and + * finish_task_switch() for details. + * + * finish_task_switch() will drop rq->lock() and lower preempt_count + * and the preempt_enable() will end up enabling preemption (on + * PREEMPT_COUNT kernels). + */ + + rq = finish_task_switch(prev); + preempt_enable(); + + if (current->set_child_tid) + put_user(task_pid_vnr(current), current->set_child_tid); + + calculate_sigpending(); +} + +/* + * context_switch - switch to the new MM and the new thread's register state. + */ +static __always_inline struct rq * +context_switch(struct rq *rq, struct task_struct *prev, + struct task_struct *next) +{ + prepare_task_switch(rq, prev, next); + + /* + * For paravirt, this is coupled with an exit in switch_to to + * combine the page table reload and the switch backend into + * one hypercall. + */ + arch_start_context_switch(prev); + + /* + * kernel -> kernel lazy + transfer active + * user -> kernel lazy + mmgrab() active + * + * kernel -> user switch + mmdrop() active + * user -> user switch + */ + if (!next->mm) { // to kernel + enter_lazy_tlb(prev->active_mm, next); + + next->active_mm = prev->active_mm; + if (prev->mm) // from user + mmgrab(prev->active_mm); + else + prev->active_mm = NULL; + } else { // to user + membarrier_switch_mm(rq, prev->active_mm, next->mm); + /* + * sys_membarrier() requires an smp_mb() between setting + * rq->curr / membarrier_switch_mm() and returning to userspace. + * + * The below provides this either through switch_mm(), or in + * case 'prev->active_mm == next->mm' through + * finish_task_switch()'s mmdrop(). + */ + switch_mm_irqs_off(prev->active_mm, next->mm, next); + + if (!prev->mm) { // from kernel + /* will mmdrop() in finish_task_switch(). */ + rq->prev_mm = prev->active_mm; + prev->active_mm = NULL; + } + } + + prepare_lock_switch(rq, next); + + /* Here we just switch the register state and the stack. */ + switch_to(prev, next, prev); + barrier(); + + return finish_task_switch(prev); +} + +/* + * nr_running, nr_uninterruptible and nr_context_switches: + * + * externally visible scheduler statistics: current number of runnable + * threads, total number of context switches performed since bootup. + */ +unsigned long nr_running(void) +{ + unsigned long i, sum = 0; + + for_each_online_cpu(i) + sum += cpu_rq(i)->nr_running; + + return sum; +} + +/* + * Check if only the current task is running on the CPU. + * + * Caution: this function does not check that the caller has disabled + * preemption, thus the result might have a time-of-check-to-time-of-use + * race. The caller is responsible to use it correctly, for example: + * + * - from a non-preemptible section (of course) + * + * - from a thread that is bound to a single CPU + * + * - in a loop with very short iterations (e.g. a polling loop) + */ +bool single_task_running(void) +{ + return raw_rq()->nr_running == 1; +} +EXPORT_SYMBOL(single_task_running); + +unsigned long long nr_context_switches(void) +{ + int i; + unsigned long long sum = 0; + + for_each_possible_cpu(i) + sum += cpu_rq(i)->nr_switches; + + return sum; +} + +/* + * Consumers of these two interfaces, like for example the cpuidle menu + * governor, are using nonsensical data. Preferring shallow idle state selection + * for a CPU that has IO-wait which might not even end up running the task when + * it does become runnable. + */ + +unsigned long nr_iowait_cpu(int cpu) +{ + return atomic_read(&cpu_rq(cpu)->nr_iowait); +} + +/* + * IO-wait accounting, and how its mostly bollocks (on SMP). + * + * The idea behind IO-wait account is to account the idle time that we could + * have spend running if it were not for IO. That is, if we were to improve the + * storage performance, we'd have a proportional reduction in IO-wait time. + * + * This all works nicely on UP, where, when a task blocks on IO, we account + * idle time as IO-wait, because if the storage were faster, it could've been + * running and we'd not be idle. + * + * This has been extended to SMP, by doing the same for each CPU. This however + * is broken. + * + * Imagine for instance the case where two tasks block on one CPU, only the one + * CPU will have IO-wait accounted, while the other has regular idle. Even + * though, if the storage were faster, both could've ran at the same time, + * utilising both CPUs. + * + * This means, that when looking globally, the current IO-wait accounting on + * SMP is a lower bound, by reason of under accounting. + * + * Worse, since the numbers are provided per CPU, they are sometimes + * interpreted per CPU, and that is nonsensical. A blocked task isn't strictly + * associated with any one particular CPU, it can wake to another CPU than it + * blocked on. This means the per CPU IO-wait number is meaningless. + * + * Task CPU affinities can make all that even more 'interesting'. + */ + +unsigned long nr_iowait(void) +{ + unsigned long i, sum = 0; + + for_each_possible_cpu(i) + sum += nr_iowait_cpu(i); + + return sum; +} + +DEFINE_PER_CPU(struct kernel_stat, kstat); +DEFINE_PER_CPU(struct kernel_cpustat, kernel_cpustat); + +EXPORT_PER_CPU_SYMBOL(kstat); +EXPORT_PER_CPU_SYMBOL(kernel_cpustat); + +static inline void update_curr(struct rq *rq, struct task_struct *p) +{ + s64 ns = rq->clock_task - p->last_ran; + + p->sched_time += ns; + account_group_exec_runtime(p, ns); + + p->time_slice -= ns; + p->last_ran = rq->clock_task; +} + +/* + * Return accounted runtime for the task. + * Return separately the current's pending runtime that have not been + * accounted yet. + */ +unsigned long long task_sched_runtime(struct task_struct *p) +{ + unsigned long flags; + struct rq *rq; + raw_spinlock_t *lock; + u64 ns; + +#if defined(CONFIG_64BIT) && defined(CONFIG_SMP) + /* + * 64-bit doesn't need locks to atomically read a 64-bit value. + * So we have a optimization chance when the task's delta_exec is 0. + * Reading ->on_cpu is racy, but this is ok. + * + * If we race with it leaving CPU, we'll take a lock. So we're correct. + * If we race with it entering CPU, unaccounted time is 0. This is + * indistinguishable from the read occurring a few cycles earlier. + * If we see ->on_cpu without ->on_rq, the task is leaving, and has + * been accounted, so we're correct here as well. + */ + if (!p->on_cpu || !task_on_rq_queued(p)) + return tsk_seruntime(p); +#endif + + rq = task_access_lock_irqsave(p, &lock, &flags); + /* + * Must be ->curr _and_ ->on_rq. If dequeued, we would + * project cycles that may never be accounted to this + * thread, breaking clock_gettime(). + */ + if (p == rq->curr && task_on_rq_queued(p)) { + update_rq_clock(rq); + update_curr(rq, p); + } + ns = tsk_seruntime(p); + task_access_unlock_irqrestore(p, lock, &flags); + + return ns; +} + +/* This manages tasks that have run out of timeslice during a scheduler_tick */ +static inline void scheduler_task_tick(struct rq *rq) +{ + struct task_struct *p = rq->curr; + + if (is_idle_task(p)) + return; + + update_curr(rq, p); + cpufreq_update_util(rq, 0); + + /* + * Tasks have less than RESCHED_NS of time slice left they will be + * rescheduled. + */ + if (p->time_slice >= RESCHED_NS) + return; + __set_tsk_resched(p); +} + +#ifdef CONFIG_SCHED_SMT +static inline int active_load_balance_cpu_stop(void *data) +{ + struct rq *rq = this_rq(); + struct task_struct *p = data; + cpumask_t tmp; + unsigned long flags; + + local_irq_save(flags); + + raw_spin_lock(&p->pi_lock); + raw_spin_lock(&rq->lock); + + rq->active_balance = 0; + /* _something_ may have changed the task, double check again */ + if (task_on_rq_queued(p) && task_rq(p) == rq && + cpumask_and(&tmp, p->cpus_ptr, &sched_sg_idle_mask)) + rq = move_queued_task(rq, p, __best_mask_cpu(cpu_of(rq), &tmp)); + + raw_spin_unlock(&rq->lock); + raw_spin_unlock(&p->pi_lock); + + local_irq_restore(flags); + + return 0; +} + +/* sg_balance_trigger - trigger slibing group balance for @cpu */ +static inline int sg_balance_trigger(const int cpu, struct rq *rq) +{ + unsigned long flags; + struct task_struct *curr; + int res; + + if (!raw_spin_trylock_irqsave(&rq->lock, flags)) + return 0; + curr = rq->curr; + res = (!is_idle_task(curr)) && (1 == rq->nr_running) &&\ + cpumask_intersects(curr->cpus_ptr, &sched_sg_idle_mask) &&\ + (!rq->active_balance); + + if (res) + rq->active_balance = 1; + + raw_spin_unlock_irqrestore(&rq->lock, flags); + + if (res) + stop_one_cpu_nowait(cpu, active_load_balance_cpu_stop, + curr, &rq->active_balance_work); + return res; +} + +/* + * sg_balance_check - slibing group balance check for run queue @rq + */ +static inline void sg_balance_check(struct rq *rq) +{ + cpumask_t chk; + int cpu; + + /* exit when no sg in idle */ + if (cpumask_empty(&sched_sg_idle_mask)) + return; + + cpu = cpu_of(rq); + /* Only cpu in slibing idle group will do the checking */ + if (cpumask_test_cpu(cpu, &sched_sg_idle_mask)) { + /* Find potential cpus which can migrate the currently running task */ + if (cpumask_andnot(&chk, cpu_online_mask, &sched_rq_pending_mask) && + cpumask_andnot(&chk, &chk, &sched_rq_watermark[IDLE_WM])) { + int i, tried = 0; + + for_each_cpu_wrap(i, &chk, cpu) { + /* skip the cpu which has idle slibing cpu */ + if (cpumask_intersects(cpu_smt_mask(i), + &sched_rq_watermark[IDLE_WM])) + continue; + if (cpumask_intersects(cpu_smt_mask(i), + &sched_rq_pending_mask)) + continue; + if (sg_balance_trigger(i, cpu_rq(i))) + return; + if (tried) + return; + tried++; + } + } + return; + } + + if (1 != rq->nr_running) + return; + + if (cpumask_andnot(&chk, cpu_smt_mask(cpu), &sched_rq_pending_mask) && + cpumask_andnot(&chk, &chk, &sched_rq_watermark[IDLE_WM]) && + cpumask_equal(&chk, cpu_smt_mask(cpu))) + sg_balance_trigger(cpu, rq); +} +#endif /* CONFIG_SCHED_SMT */ + +/* + * This function gets called by the timer code, with HZ frequency. + * We call it with interrupts disabled. + */ +void scheduler_tick(void) +{ + int cpu __maybe_unused = smp_processor_id(); + struct rq *rq = cpu_rq(cpu); + + sched_clock_tick(); + + raw_spin_lock(&rq->lock); + update_rq_clock(rq); + + scheduler_task_tick(rq); + calc_global_load_tick(rq); + psi_task_tick(rq); + + rq->last_tick = rq->clock; + raw_spin_unlock(&rq->lock); + + perf_event_task_tick(); +} + +#ifdef CONFIG_NO_HZ_FULL +struct tick_work { + int cpu; + atomic_t state; + struct delayed_work work; +}; +/* Values for ->state, see diagram below. */ +#define TICK_SCHED_REMOTE_OFFLINE 0 +#define TICK_SCHED_REMOTE_OFFLINING 1 +#define TICK_SCHED_REMOTE_RUNNING 2 + +/* + * State diagram for ->state: + * + * + * TICK_SCHED_REMOTE_OFFLINE + * | ^ + * | | + * | | sched_tick_remote() + * | | + * | | + * +--TICK_SCHED_REMOTE_OFFLINING + * | ^ + * | | + * sched_tick_start() | | sched_tick_stop() + * | | + * V | + * TICK_SCHED_REMOTE_RUNNING + * + * + * Other transitions get WARN_ON_ONCE(), except that sched_tick_remote() + * and sched_tick_start() are happy to leave the state in RUNNING. + */ + +static struct tick_work __percpu *tick_work_cpu; + +static void sched_tick_remote(struct work_struct *work) +{ + struct delayed_work *dwork = to_delayed_work(work); + struct tick_work *twork = container_of(dwork, struct tick_work, work); + int cpu = twork->cpu; + struct rq *rq = cpu_rq(cpu); + struct task_struct *curr; + unsigned long flags; + u64 delta; + int os; + + /* + * Handle the tick only if it appears the remote CPU is running in full + * dynticks mode. The check is racy by nature, but missing a tick or + * having one too much is no big deal because the scheduler tick updates + * statistics and checks timeslices in a time-independent way, regardless + * of when exactly it is running. + */ + if (idle_cpu(cpu) || !tick_nohz_tick_stopped_cpu(cpu)) + goto out_requeue; + + raw_spin_lock_irqsave(&rq->lock, flags); + curr = rq->curr; + + if (is_idle_task(curr) || cpu_is_offline(cpu)) + goto out_unlock; + + update_rq_clock(rq); + delta = rq_clock_task(rq) - curr->last_ran; + + /* + * Make sure the next tick runs within a reasonable + * amount of time. + */ + WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3); + scheduler_task_tick(rq); + +out_unlock: + raw_spin_unlock_irqrestore(&rq->lock, flags); + +out_requeue: + /* + * Run the remote tick once per second (1Hz). This arbitrary + * frequency is large enough to avoid overload but short enough + * to keep scheduler internal stats reasonably up to date. But + * first update state to reflect hotplug activity if required. + */ + os = atomic_fetch_add_unless(&twork->state, -1, TICK_SCHED_REMOTE_RUNNING); + WARN_ON_ONCE(os == TICK_SCHED_REMOTE_OFFLINE); + if (os == TICK_SCHED_REMOTE_RUNNING) + queue_delayed_work(system_unbound_wq, dwork, HZ); +} + +static void sched_tick_start(int cpu) +{ + int os; + struct tick_work *twork; + + if (housekeeping_cpu(cpu, HK_FLAG_TICK)) + return; + + WARN_ON_ONCE(!tick_work_cpu); + + twork = per_cpu_ptr(tick_work_cpu, cpu); + os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_RUNNING); + WARN_ON_ONCE(os == TICK_SCHED_REMOTE_RUNNING); + if (os == TICK_SCHED_REMOTE_OFFLINE) { + twork->cpu = cpu; + INIT_DELAYED_WORK(&twork->work, sched_tick_remote); + queue_delayed_work(system_unbound_wq, &twork->work, HZ); + } +} + +#ifdef CONFIG_HOTPLUG_CPU +static void sched_tick_stop(int cpu) +{ + struct tick_work *twork; + + if (housekeeping_cpu(cpu, HK_FLAG_TICK)) + return; + + WARN_ON_ONCE(!tick_work_cpu); + + twork = per_cpu_ptr(tick_work_cpu, cpu); + cancel_delayed_work_sync(&twork->work); +} +#endif /* CONFIG_HOTPLUG_CPU */ + +int __init sched_tick_offload_init(void) +{ + tick_work_cpu = alloc_percpu(struct tick_work); + BUG_ON(!tick_work_cpu); + return 0; +} + +#else /* !CONFIG_NO_HZ_FULL */ +static inline void sched_tick_start(int cpu) { } +static inline void sched_tick_stop(int cpu) { } +#endif + +#if defined(CONFIG_PREEMPTION) && (defined(CONFIG_DEBUG_PREEMPT) || \ + defined(CONFIG_PREEMPT_TRACER)) +/* + * If the value passed in is equal to the current preempt count + * then we just disabled preemption. Start timing the latency. + */ +static inline void preempt_latency_start(int val) +{ + if (preempt_count() == val) { + unsigned long ip = get_lock_parent_ip(); +#ifdef CONFIG_DEBUG_PREEMPT + current->preempt_disable_ip = ip; +#endif + trace_preempt_off(CALLER_ADDR0, ip); + } +} + +void preempt_count_add(int val) +{ +#ifdef CONFIG_DEBUG_PREEMPT + /* + * Underflow? + */ + if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0))) + return; +#endif + __preempt_count_add(val); +#ifdef CONFIG_DEBUG_PREEMPT + /* + * Spinlock count overflowing soon? + */ + DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >= + PREEMPT_MASK - 10); +#endif + preempt_latency_start(val); +} +EXPORT_SYMBOL(preempt_count_add); +NOKPROBE_SYMBOL(preempt_count_add); + +/* + * If the value passed in equals to the current preempt count + * then we just enabled preemption. Stop timing the latency. + */ +static inline void preempt_latency_stop(int val) +{ + if (preempt_count() == val) + trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip()); +} + +void preempt_count_sub(int val) +{ +#ifdef CONFIG_DEBUG_PREEMPT + /* + * Underflow? + */ + if (DEBUG_LOCKS_WARN_ON(val > preempt_count())) + return; + /* + * Is the spinlock portion underflowing? + */ + if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) && + !(preempt_count() & PREEMPT_MASK))) + return; +#endif + + preempt_latency_stop(val); + __preempt_count_sub(val); +} +EXPORT_SYMBOL(preempt_count_sub); +NOKPROBE_SYMBOL(preempt_count_sub); + +#else +static inline void preempt_latency_start(int val) { } +static inline void preempt_latency_stop(int val) { } +#endif + +/* + * Timeslices below RESCHED_NS are considered as good as expired as there's no + * point rescheduling when there's so little time left. + */ +static inline void check_curr(struct task_struct *p, struct rq *rq) +{ + if (rq->idle == p) + return; + + update_curr(rq, p); + + if (p->time_slice < RESCHED_NS) { + p->time_slice = SCHED_TIMESLICE_NS; + if (SCHED_FIFO != p->policy && task_on_rq_queued(p)) { + if (SCHED_RR != p->policy) + deboost_task(p); + requeue_task(p, rq); + } + } +} + +#ifdef CONFIG_SMP + +#define SCHED_RQ_NR_MIGRATION (32UL) +/* + * Migrate pending tasks in @rq to @dest_cpu + * Will try to migrate mininal of half of @rq nr_running tasks and + * SCHED_RQ_NR_MIGRATION to @dest_cpu + */ +static inline int +migrate_pending_tasks(struct rq *rq, struct rq *dest_rq, const int dest_cpu) +{ + struct task_struct *p, *skip = rq->curr; + int nr_migrated = 0; + int nr_tries = min(rq->nr_running / 2, SCHED_RQ_NR_MIGRATION); + + while (skip != rq->idle && nr_tries && + (p = rq_next_bmq_task(skip, rq)) != rq->idle) { + skip = rq_next_bmq_task(p, rq); + if (cpumask_test_cpu(dest_cpu, p->cpus_ptr)) { + dequeue_task(p, rq, 0); + set_task_cpu(p, dest_cpu); + enqueue_task(p, dest_rq, 0); + nr_migrated++; + } + nr_tries--; + } + + return nr_migrated; +} + +static inline int take_other_rq_tasks(struct rq *rq, int cpu) +{ + struct cpumask *affinity_mask, *end_mask; + + if (cpumask_empty(&sched_rq_pending_mask)) + return 0; + + affinity_mask = &(per_cpu(sched_cpu_affinity_masks, cpu)[0]); + end_mask = per_cpu(sched_cpu_affinity_end_mask, cpu); + do { + int i; + for_each_cpu_and(i, &sched_rq_pending_mask, affinity_mask) { + int nr_migrated; + struct rq *src_rq; + + src_rq = cpu_rq(i); + if (!do_raw_spin_trylock(&src_rq->lock)) + continue; + spin_acquire(&src_rq->lock.dep_map, + SINGLE_DEPTH_NESTING, 1, _RET_IP_); + + nr_migrated = migrate_pending_tasks(src_rq, rq, cpu); + + spin_release(&src_rq->lock.dep_map, 1, _RET_IP_); + do_raw_spin_unlock(&src_rq->lock); + + if (nr_migrated) { + cpufreq_update_util(rq, 0); + return 1; + } + } + } while (++affinity_mask < end_mask); + + return 0; +} +#endif + +static inline struct task_struct * +choose_next_task(struct rq *rq, int cpu, struct task_struct *prev) +{ + struct task_struct *next; + + if (unlikely(rq->skip)) { + next = rq_runnable_task(rq); +#ifdef CONFIG_SMP + if (likely(rq->online)) + if (next == rq->idle && take_other_rq_tasks(rq, cpu)) + next = rq_runnable_task(rq); +#endif + rq->skip = NULL; + return next; + } + + next = rq_first_bmq_task(rq); +#ifdef CONFIG_SMP + if (likely(rq->online)) + if (next == rq->idle && take_other_rq_tasks(rq, cpu)) + return rq_first_bmq_task(rq); +#endif + return next; +} + +static inline unsigned long get_preempt_disable_ip(struct task_struct *p) +{ +#ifdef CONFIG_DEBUG_PREEMPT + return p->preempt_disable_ip; +#else + return 0; +#endif +} + +/* + * Print scheduling while atomic bug: + */ +static noinline void __schedule_bug(struct task_struct *prev) +{ + /* Save this before calling printk(), since that will clobber it */ + unsigned long preempt_disable_ip = get_preempt_disable_ip(current); + + if (oops_in_progress) + return; + + printk(KERN_ERR "BUG: scheduling while atomic: %s/%d/0x%08x\n", + prev->comm, prev->pid, preempt_count()); + + debug_show_held_locks(prev); + print_modules(); + if (irqs_disabled()) + print_irqtrace_events(prev); + if (IS_ENABLED(CONFIG_DEBUG_PREEMPT) + && in_atomic_preempt_off()) { + pr_err("Preemption disabled at:"); + print_ip_sym(preempt_disable_ip); + pr_cont("\n"); + } + if (panic_on_warn) + panic("scheduling while atomic\n"); + + dump_stack(); + add_taint(TAINT_WARN, LOCKDEP_STILL_OK); +} + +/* + * Various schedule()-time debugging checks and statistics: + */ +static inline void schedule_debug(struct task_struct *prev, bool preempt) +{ +#ifdef CONFIG_SCHED_STACK_END_CHECK + if (task_stack_end_corrupted(prev)) + panic("corrupted stack end detected inside scheduler\n"); +#endif + +#ifdef CONFIG_DEBUG_ATOMIC_SLEEP + if (!preempt && prev->state && prev->non_block_count) { + printk(KERN_ERR "BUG: scheduling in a non-blocking section: %s/%d/%i\n", + prev->comm, prev->pid, prev->non_block_count); + dump_stack(); + add_taint(TAINT_WARN, LOCKDEP_STILL_OK); + } +#endif + + if (unlikely(in_atomic_preempt_off())) { + __schedule_bug(prev); + preempt_count_set(PREEMPT_DISABLED); + } + rcu_sleep_check(); + + profile_hit(SCHED_PROFILING, __builtin_return_address(0)); + + schedstat_inc(this_rq()->sched_count); +} + +static inline void set_rq_task(struct rq *rq, struct task_struct *p) +{ + p->last_ran = rq->clock_task; + + if (unlikely(SCHED_TIMESLICE_NS == p->time_slice)) + rq->last_ts_switch = rq->clock; +#ifdef CONFIG_HIGH_RES_TIMERS + if (p != rq->idle) + hrtick_start(rq, p->time_slice); +#endif +} + +/* + * schedule() is the main scheduler function. + * + * The main means of driving the scheduler and thus entering this function are: + * + * 1. Explicit blocking: mutex, semaphore, waitqueue, etc. + * + * 2. TIF_NEED_RESCHED flag is checked on interrupt and userspace return + * paths. For example, see arch/x86/entry_64.S. + * + * To drive preemption between tasks, the scheduler sets the flag in timer + * interrupt handler scheduler_tick(). + * + * 3. Wakeups don't really cause entry into schedule(). They add a + * task to the run-queue and that's it. + * + * Now, if the new task added to the run-queue preempts the current + * task, then the wakeup sets TIF_NEED_RESCHED and schedule() gets + * called on the nearest possible occasion: + * + * - If the kernel is preemptible (CONFIG_PREEMPTION=y): + * + * - in syscall or exception context, at the next outmost + * preempt_enable(). (this might be as soon as the wake_up()'s + * spin_unlock()!) + * + * - in IRQ context, return from interrupt-handler to + * preemptible context + * + * - If the kernel is not preemptible (CONFIG_PREEMPTION is not set) + * then at the next: + * + * - cond_resched() call + * - explicit schedule() call + * - return from syscall or exception to user-space + * - return from interrupt-handler to user-space + * + * WARNING: must be called with preemption disabled! + */ +static void __sched notrace __schedule(bool preempt) +{ + struct task_struct *prev, *next; + unsigned long *switch_count; + struct rq *rq; + int cpu; + + cpu = smp_processor_id(); + rq = cpu_rq(cpu); + prev = rq->curr; + + schedule_debug(prev, preempt); + + /* by passing sched_feat(HRTICK) checking which BMQ doesn't support */ + hrtick_clear(rq); + + local_irq_disable(); + rcu_note_context_switch(preempt); + + /* + * Make sure that signal_pending_state()->signal_pending() below + * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE) + * done by the caller to avoid the race with signal_wake_up(). + * + * The membarrier system call requires a full memory barrier + * after coming from user-space, before storing to rq->curr. + */ + raw_spin_lock(&rq->lock); + smp_mb__after_spinlock(); + + update_rq_clock(rq); + + switch_count = &prev->nivcsw; + if (!preempt && prev->state) { + if (signal_pending_state(prev->state, prev)) { + prev->state = TASK_RUNNING; + } else { + if (rq_switch_time(rq) < boost_threshold(prev)) + boost_task(prev); + deactivate_task(prev, rq); + + if (prev->in_iowait) { + atomic_inc(&rq->nr_iowait); + delayacct_blkio_start(); + } + } + switch_count = &prev->nvcsw; + } + + clear_tsk_need_resched(prev); + clear_preempt_need_resched(); + + check_curr(prev, rq); + + next = choose_next_task(rq, cpu, prev); + + set_rq_task(rq, next); + + if (prev != next) { + if (MAX_PRIO == next->prio) + schedstat_inc(rq->sched_goidle); + + /* + * RCU users of rcu_dereference(rq->curr) may not see + * changes to task_struct made by pick_next_task(). + */ + RCU_INIT_POINTER(rq->curr, next); + /* + * The membarrier system call requires each architecture + * to have a full memory barrier after updating + * rq->curr, before returning to user-space. + * + * Here are the schemes providing that barrier on the + * various architectures: + * - mm ? switch_mm() : mmdrop() for x86, s390, sparc, PowerPC. + * switch_mm() rely on membarrier_arch_switch_mm() on PowerPC. + * - finish_lock_switch() for weakly-ordered + * architectures where spin_unlock is a full barrier, + * - switch_to() for arm64 (weakly-ordered, spin_unlock + * is a RELEASE barrier), + */ + ++*switch_count; + rq->nr_switches++; + rq->last_ts_switch = rq->clock; + + trace_sched_switch(preempt, prev, next); + + /* Also unlocks the rq: */ + rq = context_switch(rq, prev, next); +#ifdef CONFIG_SCHED_SMT + sg_balance_check(rq); +#endif + } else + raw_spin_unlock_irq(&rq->lock); +} + +void __noreturn do_task_dead(void) +{ + /* Causes final put_task_struct in finish_task_switch(): */ + set_special_state(TASK_DEAD); + + /* Tell freezer to ignore us: */ + current->flags |= PF_NOFREEZE; + __schedule(false); + + BUG(); + + /* Avoid "noreturn function does return" - but don't continue if BUG() is a NOP: */ + for (;;) + cpu_relax(); +} + +static inline void sched_submit_work(struct task_struct *tsk) +{ + if (!tsk->state) + return; + + /* + * If a worker went to sleep, notify and ask workqueue whether + * it wants to wake up a task to maintain concurrency. + * As this function is called inside the schedule() context, + * we disable preemption to avoid it calling schedule() again + * in the possible wakeup of a kworker. + */ + if (tsk->flags & PF_WQ_WORKER) { + preempt_disable(); + wq_worker_sleeping(tsk); + preempt_enable_no_resched(); + } + + if (tsk_is_pi_blocked(tsk)) + return; + + /* + * If we are going to sleep and we have plugged IO queued, + * make sure to submit it to avoid deadlocks. + */ + if (blk_needs_flush_plug(tsk)) + blk_schedule_flush_plug(tsk); +} + +static void sched_update_worker(struct task_struct *tsk) +{ + if (tsk->flags & PF_WQ_WORKER) + wq_worker_running(tsk); +} + +asmlinkage __visible void __sched schedule(void) +{ + struct task_struct *tsk = current; + + sched_submit_work(tsk); + do { + preempt_disable(); + __schedule(false); + sched_preempt_enable_no_resched(); + } while (need_resched()); + sched_update_worker(tsk); +} +EXPORT_SYMBOL(schedule); + +/* + * synchronize_rcu_tasks() makes sure that no task is stuck in preempted + * state (have scheduled out non-voluntarily) by making sure that all + * tasks have either left the run queue or have gone into user space. + * As idle tasks do not do either, they must not ever be preempted + * (schedule out non-voluntarily). + * + * schedule_idle() is similar to schedule_preempt_disable() except that it + * never enables preemption because it does not call sched_submit_work(). + */ +void __sched schedule_idle(void) +{ + /* + * As this skips calling sched_submit_work(), which the idle task does + * regardless because that function is a nop when the task is in a + * TASK_RUNNING state, make sure this isn't used someplace that the + * current task can be in any other state. Note, idle is always in the + * TASK_RUNNING state. + */ + WARN_ON_ONCE(current->state); + do { + __schedule(false); + } while (need_resched()); +} + +#ifdef CONFIG_CONTEXT_TRACKING +asmlinkage __visible void __sched schedule_user(void) +{ + /* + * If we come here after a random call to set_need_resched(), + * or we have been woken up remotely but the IPI has not yet arrived, + * we haven't yet exited the RCU idle mode. Do it here manually until + * we find a better solution. + * + * NB: There are buggy callers of this function. Ideally we + * should warn if prev_state != CONTEXT_USER, but that will trigger + * too frequently to make sense yet. + */ + enum ctx_state prev_state = exception_enter(); + schedule(); + exception_exit(prev_state); +} +#endif + +/** + * schedule_preempt_disabled - called with preemption disabled + * + * Returns with preemption disabled. Note: preempt_count must be 1 + */ +void __sched schedule_preempt_disabled(void) +{ + sched_preempt_enable_no_resched(); + schedule(); + preempt_disable(); +} + +static void __sched notrace preempt_schedule_common(void) +{ + do { + /* + * Because the function tracer can trace preempt_count_sub() + * and it also uses preempt_enable/disable_notrace(), if + * NEED_RESCHED is set, the preempt_enable_notrace() called + * by the function tracer will call this function again and + * cause infinite recursion. + * + * Preemption must be disabled here before the function + * tracer can trace. Break up preempt_disable() into two + * calls. One to disable preemption without fear of being + * traced. The other to still record the preemption latency, + * which can also be traced by the function tracer. + */ + preempt_disable_notrace(); + preempt_latency_start(1); + __schedule(true); + preempt_latency_stop(1); + preempt_enable_no_resched_notrace(); + + /* + * Check again in case we missed a preemption opportunity + * between schedule and now. + */ + } while (need_resched()); +} + +#ifdef CONFIG_PREEMPTION +/* + * This is the entry point to schedule() from in-kernel preemption + * off of preempt_enable. + */ +asmlinkage __visible void __sched notrace preempt_schedule(void) +{ + /* + * If there is a non-zero preempt_count or interrupts are disabled, + * we do not want to preempt the current task. Just return.. + */ + if (likely(!preemptible())) + return; + + preempt_schedule_common(); +} +NOKPROBE_SYMBOL(preempt_schedule); +EXPORT_SYMBOL(preempt_schedule); + +/** + * preempt_schedule_notrace - preempt_schedule called by tracing + * + * The tracing infrastructure uses preempt_enable_notrace to prevent + * recursion and tracing preempt enabling caused by the tracing + * infrastructure itself. But as tracing can happen in areas coming + * from userspace or just about to enter userspace, a preempt enable + * can occur before user_exit() is called. This will cause the scheduler + * to be called when the system is still in usermode. + * + * To prevent this, the preempt_enable_notrace will use this function + * instead of preempt_schedule() to exit user context if needed before + * calling the scheduler. + */ +asmlinkage __visible void __sched notrace preempt_schedule_notrace(void) +{ + enum ctx_state prev_ctx; + + if (likely(!preemptible())) + return; + + do { + /* + * Because the function tracer can trace preempt_count_sub() + * and it also uses preempt_enable/disable_notrace(), if + * NEED_RESCHED is set, the preempt_enable_notrace() called + * by the function tracer will call this function again and + * cause infinite recursion. + * + * Preemption must be disabled here before the function + * tracer can trace. Break up preempt_disable() into two + * calls. One to disable preemption without fear of being + * traced. The other to still record the preemption latency, + * which can also be traced by the function tracer. + */ + preempt_disable_notrace(); + preempt_latency_start(1); + /* + * Needs preempt disabled in case user_exit() is traced + * and the tracer calls preempt_enable_notrace() causing + * an infinite recursion. + */ + prev_ctx = exception_enter(); + __schedule(true); + exception_exit(prev_ctx); + + preempt_latency_stop(1); + preempt_enable_no_resched_notrace(); + } while (need_resched()); +} +EXPORT_SYMBOL_GPL(preempt_schedule_notrace); + +#endif /* CONFIG_PREEMPTION */ + +/* + * This is the entry point to schedule() from kernel preemption + * off of irq context. + * Note, that this is called and return with irqs disabled. This will + * protect us against recursive calling from irq. + */ +asmlinkage __visible void __sched preempt_schedule_irq(void) +{ + enum ctx_state prev_state; + + /* Catch callers which need to be fixed */ + BUG_ON(preempt_count() || !irqs_disabled()); + + prev_state = exception_enter(); + + do { + preempt_disable(); + local_irq_enable(); + __schedule(true); + local_irq_disable(); + sched_preempt_enable_no_resched(); + } while (need_resched()); + + exception_exit(prev_state); +} + +int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flags, + void *key) +{ + return try_to_wake_up(curr->private, mode, wake_flags); +} +EXPORT_SYMBOL(default_wake_function); + +static inline void check_task_changed(struct rq *rq, struct task_struct *p) +{ + /* Trigger resched if task sched_prio has been modified. */ + if (task_on_rq_queued(p) && task_sched_prio(p) != p->bmq_idx) { + requeue_task(p, rq); + check_preempt_curr(rq); + } +} + +#ifdef CONFIG_RT_MUTEXES + +static inline int __rt_effective_prio(struct task_struct *pi_task, int prio) +{ + if (pi_task) + prio = min(prio, pi_task->prio); + + return prio; +} + +static inline int rt_effective_prio(struct task_struct *p, int prio) +{ + struct task_struct *pi_task = rt_mutex_get_top_task(p); + + return __rt_effective_prio(pi_task, prio); +} + +/* + * rt_mutex_setprio - set the current priority of a task + * @p: task to boost + * @pi_task: donor task + * + * This function changes the 'effective' priority of a task. It does + * not touch ->normal_prio like __setscheduler(). + * + * Used by the rt_mutex code to implement priority inheritance + * logic. Call site only calls if the priority of the task changed. + */ +void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) +{ + int prio; + struct rq *rq; + raw_spinlock_t *lock; + + /* XXX used to be waiter->prio, not waiter->task->prio */ + prio = __rt_effective_prio(pi_task, p->normal_prio); + + /* + * If nothing changed; bail early. + */ + if (p->pi_top_task == pi_task && prio == p->prio) + return; + + rq = __task_access_lock(p, &lock); + /* + * Set under pi_lock && rq->lock, such that the value can be used under + * either lock. + * + * Note that there is loads of tricky to make this pointer cache work + * right. rt_mutex_slowunlock()+rt_mutex_postunlock() work together to + * ensure a task is de-boosted (pi_task is set to NULL) before the + * task is allowed to run again (and can exit). This ensures the pointer + * points to a blocked task -- which guaratees the task is present. + */ + p->pi_top_task = pi_task; + + /* + * For FIFO/RR we only need to set prio, if that matches we're done. + */ + if (prio == p->prio) + goto out_unlock; + + /* + * Idle task boosting is a nono in general. There is one + * exception, when PREEMPT_RT and NOHZ is active: + * + * The idle task calls get_next_timer_interrupt() and holds + * the timer wheel base->lock on the CPU and another CPU wants + * to access the timer (probably to cancel it). We can safely + * ignore the boosting request, as the idle CPU runs this code + * with interrupts disabled and will complete the lock + * protected section without being interrupted. So there is no + * real need to boost. + */ + if (unlikely(p == rq->idle)) { + WARN_ON(p != rq->curr); + WARN_ON(p->pi_blocked_on); + goto out_unlock; + } + + trace_sched_pi_setprio(p, pi_task); + p->prio = prio; + + check_task_changed(rq, p); +out_unlock: + __task_access_unlock(p, lock); +} +#else +static inline int rt_effective_prio(struct task_struct *p, int prio) +{ + return prio; +} +#endif + +void set_user_nice(struct task_struct *p, long nice) +{ + unsigned long flags; + struct rq *rq; + raw_spinlock_t *lock; + + if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE) + return; + /* + * We have to be careful, if called from sys_setpriority(), + * the task might be in the middle of scheduling on another CPU. + */ + raw_spin_lock_irqsave(&p->pi_lock, flags); + rq = __task_access_lock(p, &lock); + + p->static_prio = NICE_TO_PRIO(nice); + /* + * The RT priorities are set via sched_setscheduler(), but we still + * allow the 'normal' nice value to be set - but as expected + * it wont have any effect on scheduling until the task is + * not SCHED_NORMAL/SCHED_BATCH: + */ + if (task_has_rt_policy(p)) + goto out_unlock; + + p->prio = effective_prio(p); + check_task_changed(rq, p); +out_unlock: + __task_access_unlock(p, lock); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); +} +EXPORT_SYMBOL(set_user_nice); + +/* + * can_nice - check if a task can reduce its nice value + * @p: task + * @nice: nice value + */ +int can_nice(const struct task_struct *p, const int nice) +{ + /* Convert nice value [19,-20] to rlimit style value [1,40] */ + int nice_rlim = nice_to_rlimit(nice); + + return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) || + capable(CAP_SYS_NICE)); +} + +#ifdef __ARCH_WANT_SYS_NICE + +/* + * sys_nice - change the priority of the current process. + * @increment: priority increment + * + * sys_setpriority is a more generic, but much slower function that + * does similar things. + */ +SYSCALL_DEFINE1(nice, int, increment) +{ + long nice, retval; + + /* + * Setpriority might change our priority at the same moment. + * We don't have to worry. Conceptually one call occurs first + * and we have a single winner. + */ + + increment = clamp(increment, -NICE_WIDTH, NICE_WIDTH); + nice = task_nice(current) + increment; + + nice = clamp_val(nice, MIN_NICE, MAX_NICE); + if (increment < 0 && !can_nice(current, nice)) + return -EPERM; + + retval = security_task_setnice(current, nice); + if (retval) + return retval; + + set_user_nice(current, nice); + return 0; +} + +#endif + +/** + * task_prio - return the priority value of a given task. + * @p: the task in question. + * + * Return: The priority value as seen by users in /proc. + * RT tasks are offset by -100. Normal tasks are centered around 1, value goes + * from 0(SCHED_ISO) up to 82 (nice +19 SCHED_IDLE). + */ +int task_prio(const struct task_struct *p) +{ + if (p->prio < MAX_RT_PRIO) + return (p->prio - MAX_RT_PRIO); + return (p->prio - MAX_RT_PRIO + p->boost_prio); +} + +/** + * idle_cpu - is a given CPU idle currently? + * @cpu: the processor in question. + * + * Return: 1 if the CPU is currently idle. 0 otherwise. + */ +int idle_cpu(int cpu) +{ + return cpu_curr(cpu) == cpu_rq(cpu)->idle; +} + +/** + * idle_task - return the idle task for a given CPU. + * @cpu: the processor in question. + * + * Return: The idle task for the cpu @cpu. + */ +struct task_struct *idle_task(int cpu) +{ + return cpu_rq(cpu)->idle; +} + +/** + * find_process_by_pid - find a process with a matching PID value. + * @pid: the pid in question. + * + * The task of @pid, if found. %NULL otherwise. + */ +static inline struct task_struct *find_process_by_pid(pid_t pid) +{ + return pid ? find_task_by_vpid(pid) : current; +} + +#ifdef CONFIG_SMP +void sched_set_stop_task(int cpu, struct task_struct *stop) +{ + struct sched_param stop_param = { .sched_priority = STOP_PRIO }; + struct sched_param start_param = { .sched_priority = 0 }; + struct task_struct *old_stop = cpu_rq(cpu)->stop; + + if (stop) { + /* + * Make it appear like a SCHED_FIFO task, its something + * userspace knows about and won't get confused about. + * + * Also, it will make PI more or less work without too + * much confusion -- but then, stop work should not + * rely on PI working anyway. + */ + sched_setscheduler_nocheck(stop, SCHED_FIFO, &stop_param); + } + + cpu_rq(cpu)->stop = stop; + + if (old_stop) { + /* + * Reset it back to a normal scheduling policy so that + * it can die in pieces. + */ + sched_setscheduler_nocheck(old_stop, SCHED_NORMAL, &start_param); + } +} + +/* + * Change a given task's CPU affinity. Migrate the thread to a + * proper CPU and schedule it away if the CPU it's executing on + * is removed from the allowed bitmask. + * + * NOTE: the caller must have a valid reference to the task, the + * task must not exit() & deallocate itself prematurely. The + * call is not atomic; no spinlocks may be held. + */ +static int __set_cpus_allowed_ptr(struct task_struct *p, + const struct cpumask *new_mask, bool check) +{ + const struct cpumask *cpu_valid_mask = cpu_active_mask; + int dest_cpu; + unsigned long flags; + struct rq *rq; + raw_spinlock_t *lock; + int ret = 0; + + raw_spin_lock_irqsave(&p->pi_lock, flags); + rq = __task_access_lock(p, &lock); + + if (p->flags & PF_KTHREAD) { + /* + * Kernel threads are allowed on online && !active CPUs + */ + cpu_valid_mask = cpu_online_mask; + } + + /* + * Must re-check here, to close a race against __kthread_bind(), + * sched_setaffinity() is not guaranteed to observe the flag. + */ + if (check && (p->flags & PF_NO_SETAFFINITY)) { + ret = -EINVAL; + goto out; + } + + if (cpumask_equal(p->cpus_ptr, new_mask)) + goto out; + + dest_cpu = cpumask_any_and(cpu_valid_mask, new_mask); + if (dest_cpu >= nr_cpu_ids) { + ret = -EINVAL; + goto out; + } + + do_set_cpus_allowed(p, new_mask); + + if (p->flags & PF_KTHREAD) { + /* + * For kernel threads that do indeed end up on online && + * !active we want to ensure they are strict per-CPU threads. + */ + WARN_ON(cpumask_intersects(new_mask, cpu_online_mask) && + !cpumask_intersects(new_mask, cpu_active_mask) && + p->nr_cpus_allowed != 1); + } + + /* Can the task run on the task's current CPU? If so, we're done */ + if (cpumask_test_cpu(task_cpu(p), new_mask)) + goto out; + + if (task_running(p) || p->state == TASK_WAKING) { + struct migration_arg arg = { p, dest_cpu }; + + /* Need help from migration thread: drop lock and wait. */ + __task_access_unlock(p, lock); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); + return 0; + } + if (task_on_rq_queued(p)) { + /* + * OK, since we're going to drop the lock immediately + * afterwards anyway. + */ + update_rq_clock(rq); + rq = move_queued_task(rq, p, dest_cpu); + lock = &rq->lock; + } + +out: + __task_access_unlock(p, lock); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + + return ret; +} + +int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) +{ + return __set_cpus_allowed_ptr(p, new_mask, false); +} +EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr); + +#else +static inline int +__set_cpus_allowed_ptr(struct task_struct *p, + const struct cpumask *new_mask, bool check) +{ + return set_cpus_allowed_ptr(p, new_mask); +} +#endif + +/* + * sched_setparam() passes in -1 for its policy, to let the functions + * it calls know not to change it. + */ +#define SETPARAM_POLICY -1 + +static void __setscheduler_params(struct task_struct *p, + const struct sched_attr *attr) +{ + int policy = attr->sched_policy; + + if (policy == SETPARAM_POLICY) + policy = p->policy; + + p->policy = policy; + + /* + * allow normal nice value to be set, but will not have any + * effect on scheduling until the task not SCHED_NORMAL/ + * SCHED_BATCH + */ + p->static_prio = NICE_TO_PRIO(attr->sched_nice); + + /* + * __sched_setscheduler() ensures attr->sched_priority == 0 when + * !rt_policy. Always setting this ensures that things like + * getparam()/getattr() don't report silly values for !rt tasks. + */ + p->rt_priority = attr->sched_priority; + p->normal_prio = normal_prio(p); +} + +/* Actually do priority change: must hold rq lock. */ +static void __setscheduler(struct rq *rq, struct task_struct *p, + const struct sched_attr *attr, bool keep_boost) +{ + __setscheduler_params(p, attr); + + /* + * Keep a potential priority boosting if called from + * sched_setscheduler(). + */ + p->prio = normal_prio(p); + if (keep_boost) + p->prio = rt_effective_prio(p, p->prio); +} + +/* + * check the target process has a UID that matches the current process's + */ +static bool check_same_owner(struct task_struct *p) +{ + const struct cred *cred = current_cred(), *pcred; + bool match; + + rcu_read_lock(); + pcred = __task_cred(p); + match = (uid_eq(cred->euid, pcred->euid) || + uid_eq(cred->euid, pcred->uid)); + rcu_read_unlock(); + return match; +} + +static int __sched_setscheduler(struct task_struct *p, + const struct sched_attr *attr, + bool user, bool pi) +{ + const struct sched_attr dl_squash_attr = { + .size = sizeof(struct sched_attr), + .sched_policy = SCHED_FIFO, + .sched_nice = 0, + .sched_priority = 99, + }; + int newprio = MAX_RT_PRIO - 1 - attr->sched_priority; + int retval, oldpolicy = -1; + int policy = attr->sched_policy; + unsigned long flags; + struct rq *rq; + int reset_on_fork; + raw_spinlock_t *lock; + + /* The pi code expects interrupts enabled */ + BUG_ON(pi && in_interrupt()); + + /* + * BMQ supports SCHED_DEADLINE by squash it as prio 0 SCHED_FIFO + */ + if (unlikely(SCHED_DEADLINE == policy)) { + attr = &dl_squash_attr; + policy = attr->sched_policy; + newprio = MAX_RT_PRIO - 1 - attr->sched_priority; + } +recheck: + /* Double check policy once rq lock held */ + if (policy < 0) { + reset_on_fork = p->sched_reset_on_fork; + policy = oldpolicy = p->policy; + } else { + reset_on_fork = !!(attr->sched_flags & SCHED_RESET_ON_FORK); + + if (policy > SCHED_IDLE) + return -EINVAL; + } + + if (attr->sched_flags & ~(SCHED_FLAG_ALL)) + return -EINVAL; + + /* + * Valid priorities for SCHED_FIFO and SCHED_RR are + * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL and + * SCHED_BATCH and SCHED_IDLE is 0. + */ + if (attr->sched_priority < 0 || + (p->mm && attr->sched_priority > MAX_USER_RT_PRIO - 1) || + (!p->mm && attr->sched_priority > MAX_RT_PRIO - 1)) + return -EINVAL; + if ((SCHED_RR == policy || SCHED_FIFO == policy) != + (attr->sched_priority != 0)) + return -EINVAL; + + /* + * Allow unprivileged RT tasks to decrease priority: + */ + if (user && !capable(CAP_SYS_NICE)) { + if (SCHED_FIFO == policy || SCHED_RR == policy) { + unsigned long rlim_rtprio = + task_rlimit(p, RLIMIT_RTPRIO); + + /* Can't set/change the rt policy */ + if (policy != p->policy && !rlim_rtprio) + return -EPERM; + + /* Can't increase priority */ + if (attr->sched_priority > p->rt_priority && + attr->sched_priority > rlim_rtprio) + return -EPERM; + } + + /* Can't change other user's priorities */ + if (!check_same_owner(p)) + return -EPERM; + + /* Normal users shall not reset the sched_reset_on_fork flag */ + if (p->sched_reset_on_fork && !reset_on_fork) + return -EPERM; + } + + if (user) { + retval = security_task_setscheduler(p); + if (retval) + return retval; + } + + if (pi) + cpuset_read_lock(); + + /* + * Make sure no PI-waiters arrive (or leave) while we are + * changing the priority of the task: + */ + raw_spin_lock_irqsave(&p->pi_lock, flags); + + /* + * To be able to change p->policy safely, task_access_lock() + * must be called. + * IF use task_access_lock() here: + * For the task p which is not running, reading rq->stop is + * racy but acceptable as ->stop doesn't change much. + * An enhancemnet can be made to read rq->stop saftly. + */ + rq = __task_access_lock(p, &lock); + + /* + * Changing the policy of the stop threads its a very bad idea + */ + if (p == rq->stop) { + retval = -EINVAL; + goto unlock; + } + + /* + * If not changing anything there's no need to proceed further: + */ + if (unlikely(policy == p->policy)) { + if (rt_policy(policy) && attr->sched_priority != p->rt_priority) + goto change; + if (!rt_policy(policy) && + NICE_TO_PRIO(attr->sched_nice) != p->static_prio) + goto change; + + p->sched_reset_on_fork = reset_on_fork; + retval = 0; + goto unlock; + } +change: + + /* Re-check policy now with rq lock held */ + if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { + policy = oldpolicy = -1; + __task_access_unlock(p, lock); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + if (pi) + cpuset_read_unlock(); + goto recheck; + } + + p->sched_reset_on_fork = reset_on_fork; + + if (pi) { + /* + * Take priority boosted tasks into account. If the new + * effective priority is unchanged, we just store the new + * normal parameters and do not touch the scheduler class and + * the runqueue. This will be done when the task deboost + * itself. + */ + if (rt_effective_prio(p, newprio) == p->prio) { + __setscheduler_params(p, attr); + retval = 0; + goto unlock; + } + } + + __setscheduler(rq, p, attr, pi); + + check_task_changed(rq, p); + + /* Avoid rq from going away on us: */ + preempt_disable(); + __task_access_unlock(p, lock); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + + if (pi) { + cpuset_read_unlock(); + rt_mutex_adjust_pi(p); + } + + preempt_enable(); + + return 0; + +unlock: + __task_access_unlock(p, lock); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + if (pi) + cpuset_read_unlock(); + return retval; +} + +static int _sched_setscheduler(struct task_struct *p, int policy, + const struct sched_param *param, bool check) +{ + struct sched_attr attr = { + .sched_policy = policy, + .sched_priority = param->sched_priority, + .sched_nice = PRIO_TO_NICE(p->static_prio), + }; + + /* Fixup the legacy SCHED_RESET_ON_FORK hack. */ + if ((policy != SETPARAM_POLICY) && (policy & SCHED_RESET_ON_FORK)) { + attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK; + policy &= ~SCHED_RESET_ON_FORK; + attr.sched_policy = policy; + } + + return __sched_setscheduler(p, &attr, check, true); +} + +/** + * sched_setscheduler - change the scheduling policy and/or RT priority of a thread. + * @p: the task in question. + * @policy: new policy. + * @param: structure containing the new RT priority. + * + * Return: 0 on success. An error code otherwise. + * + * NOTE that the task may be already dead. + */ +int sched_setscheduler(struct task_struct *p, int policy, + const struct sched_param *param) +{ + return _sched_setscheduler(p, policy, param, true); +} + +EXPORT_SYMBOL_GPL(sched_setscheduler); + +int sched_setattr(struct task_struct *p, const struct sched_attr *attr) +{ + return __sched_setscheduler(p, attr, true, true); +} +EXPORT_SYMBOL_GPL(sched_setattr); + +int sched_setattr_nocheck(struct task_struct *p, const struct sched_attr *attr) +{ + return __sched_setscheduler(p, attr, false, true); +} + +/** + * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace. + * @p: the task in question. + * @policy: new policy. + * @param: structure containing the new RT priority. + * + * Just like sched_setscheduler, only don't bother checking if the + * current context has permission. For example, this is needed in + * stop_machine(): we create temporary high priority worker threads, + * but our caller might not have that capability. + * + * Return: 0 on success. An error code otherwise. + */ +int sched_setscheduler_nocheck(struct task_struct *p, int policy, + const struct sched_param *param) +{ + return _sched_setscheduler(p, policy, param, false); +} +EXPORT_SYMBOL_GPL(sched_setscheduler_nocheck); + +static int +do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) +{ + struct sched_param lparam; + struct task_struct *p; + int retval; + + if (!param || pid < 0) + return -EINVAL; + if (copy_from_user(&lparam, param, sizeof(struct sched_param))) + return -EFAULT; + + rcu_read_lock(); + retval = -ESRCH; + p = find_process_by_pid(pid); + if (likely(p)) + get_task_struct(p); + rcu_read_unlock(); + + if (likely(p)) { + retval = sched_setscheduler(p, policy, &lparam); + put_task_struct(p); + } + + return retval; +} + +/* + * Mimics kernel/events/core.c perf_copy_attr(). + */ +static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *attr) +{ + u32 size; + int ret; + + /* Zero the full structure, so that a short copy will be nice: */ + memset(attr, 0, sizeof(*attr)); + + ret = get_user(size, &uattr->size); + if (ret) + return ret; + + /* ABI compatibility quirk: */ + if (!size) + size = SCHED_ATTR_SIZE_VER0; + + if (size < SCHED_ATTR_SIZE_VER0 || size > PAGE_SIZE) + goto err_size; + + ret = copy_struct_from_user(attr, sizeof(*attr), uattr, size); + if (ret) { + if (ret == -E2BIG) + goto err_size; + return ret; + } + + /* + * XXX: Do we want to be lenient like existing syscalls; or do we want + * to be strict and return an error on out-of-bounds values? + */ + attr->sched_nice = clamp(attr->sched_nice, -20, 19); + + /* sched/core.c uses zero here but we already know ret is zero */ + return 0; + +err_size: + put_user(sizeof(*attr), &uattr->size); + return -E2BIG; +} + +/** + * sys_sched_setscheduler - set/change the scheduler policy and RT priority + * @pid: the pid in question. + * @policy: new policy. + * + * Return: 0 on success. An error code otherwise. + * @param: structure containing the new RT priority. + */ +SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, struct sched_param __user *, param) +{ + if (policy < 0) + return -EINVAL; + + return do_sched_setscheduler(pid, policy, param); +} + +/** + * sys_sched_setparam - set/change the RT priority of a thread + * @pid: the pid in question. + * @param: structure containing the new RT priority. + * + * Return: 0 on success. An error code otherwise. + */ +SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param) +{ + return do_sched_setscheduler(pid, SETPARAM_POLICY, param); +} + +/** + * sys_sched_setattr - same as above, but with extended sched_attr + * @pid: the pid in question. + * @uattr: structure containing the extended parameters. + */ +SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr, + unsigned int, flags) +{ + struct sched_attr attr; + struct task_struct *p; + int retval; + + if (!uattr || pid < 0 || flags) + return -EINVAL; + + retval = sched_copy_attr(uattr, &attr); + if (retval) + return retval; + + if ((int)attr.sched_policy < 0) + return -EINVAL; + + rcu_read_lock(); + retval = -ESRCH; + p = find_process_by_pid(pid); + if (p != NULL) + retval = sched_setattr(p, &attr); + rcu_read_unlock(); + + return retval; +} + +/** + * sys_sched_getscheduler - get the policy (scheduling class) of a thread + * @pid: the pid in question. + * + * Return: On success, the policy of the thread. Otherwise, a negative error + * code. + */ +SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid) +{ + struct task_struct *p; + int retval = -EINVAL; + + if (pid < 0) + goto out_nounlock; + + retval = -ESRCH; + rcu_read_lock(); + p = find_process_by_pid(pid); + if (p) { + retval = security_task_getscheduler(p); + if (!retval) + retval = p->policy; + } + rcu_read_unlock(); + +out_nounlock: + return retval; +} + +/** + * sys_sched_getscheduler - get the RT priority of a thread + * @pid: the pid in question. + * @param: structure containing the RT priority. + * + * Return: On success, 0 and the RT priority is in @param. Otherwise, an error + * code. + */ +SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param) +{ + struct sched_param lp = { .sched_priority = 0 }; + struct task_struct *p; + int retval = -EINVAL; + + if (!param || pid < 0) + goto out_nounlock; + + rcu_read_lock(); + p = find_process_by_pid(pid); + retval = -ESRCH; + if (!p) + goto out_unlock; + + retval = security_task_getscheduler(p); + if (retval) + goto out_unlock; + + if (task_has_rt_policy(p)) + lp.sched_priority = p->rt_priority; + rcu_read_unlock(); + + /* + * This one might sleep, we cannot do it with a spinlock held ... + */ + retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0; + +out_nounlock: + return retval; + +out_unlock: + rcu_read_unlock(); + return retval; +} + +/* + * Copy the kernel size attribute structure (which might be larger + * than what user-space knows about) to user-space. + * + * Note that all cases are valid: user-space buffer can be larger or + * smaller than the kernel-space buffer. The usual case is that both + * have the same size. + */ +static int +sched_attr_copy_to_user(struct sched_attr __user *uattr, + struct sched_attr *kattr, + unsigned int usize) +{ + unsigned int ksize = sizeof(*kattr); + + if (!access_ok(uattr, usize)) + return -EFAULT; + + /* + * sched_getattr() ABI forwards and backwards compatibility: + * + * If usize == ksize then we just copy everything to user-space and all is good. + * + * If usize < ksize then we only copy as much as user-space has space for, + * this keeps ABI compatibility as well. We skip the rest. + * + * If usize > ksize then user-space is using a newer version of the ABI, + * which part the kernel doesn't know about. Just ignore it - tooling can + * detect the kernel's knowledge of attributes from the attr->size value + * which is set to ksize in this case. + */ + kattr->size = min(usize, ksize); + + if (copy_to_user(uattr, kattr, kattr->size)) + return -EFAULT; + + return 0; +} + +/** + * sys_sched_getattr - similar to sched_getparam, but with sched_attr + * @pid: the pid in question. + * @uattr: structure containing the extended parameters. + * @usize: sizeof(attr) for fwd/bwd comp. + * @flags: for future extension. + */ +SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr, + unsigned int, usize, unsigned int, flags) +{ + struct sched_attr kattr = { }; + struct task_struct *p; + int retval; + + if (!uattr || pid < 0 || usize > PAGE_SIZE || + usize < SCHED_ATTR_SIZE_VER0 || flags) + return -EINVAL; + + rcu_read_lock(); + p = find_process_by_pid(pid); + retval = -ESRCH; + if (!p) + goto out_unlock; + + retval = security_task_getscheduler(p); + if (retval) + goto out_unlock; + + kattr.sched_policy = p->policy; + if (p->sched_reset_on_fork) + kattr.sched_flags |= SCHED_FLAG_RESET_ON_FORK; + if (task_has_rt_policy(p)) + kattr.sched_priority = p->rt_priority; + else + kattr.sched_nice = task_nice(p); + +#ifdef CONFIG_UCLAMP_TASK + kattr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value; + kattr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value; +#endif + + rcu_read_unlock(); + + return sched_attr_copy_to_user(uattr, &kattr, usize); + +out_unlock: + rcu_read_unlock(); + return retval; +} + +long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) +{ + cpumask_var_t cpus_allowed, new_mask; + struct task_struct *p; + int retval; + + get_online_cpus(); + rcu_read_lock(); + + p = find_process_by_pid(pid); + if (!p) { + rcu_read_unlock(); + put_online_cpus(); + return -ESRCH; + } + + /* Prevent p going away */ + get_task_struct(p); + rcu_read_unlock(); + + if (p->flags & PF_NO_SETAFFINITY) { + retval = -EINVAL; + goto out_put_task; + } + if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) { + retval = -ENOMEM; + goto out_put_task; + } + if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) { + retval = -ENOMEM; + goto out_free_cpus_allowed; + } + retval = -EPERM; + if (!check_same_owner(p)) { + rcu_read_lock(); + if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) { + rcu_read_unlock(); + goto out_unlock; + } + rcu_read_unlock(); + } + + retval = security_task_setscheduler(p); + if (retval) + goto out_unlock; + + cpuset_cpus_allowed(p, cpus_allowed); + cpumask_and(new_mask, in_mask, cpus_allowed); +again: + retval = __set_cpus_allowed_ptr(p, new_mask, true); + + if (!retval) { + cpuset_cpus_allowed(p, cpus_allowed); + if (!cpumask_subset(new_mask, cpus_allowed)) { + /* + * We must have raced with a concurrent cpuset + * update. Just reset the cpus_allowed to the + * cpuset's cpus_allowed + */ + cpumask_copy(new_mask, cpus_allowed); + goto again; + } + } +out_unlock: + free_cpumask_var(new_mask); +out_free_cpus_allowed: + free_cpumask_var(cpus_allowed); +out_put_task: + put_task_struct(p); + put_online_cpus(); + return retval; +} + +static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len, + struct cpumask *new_mask) +{ + if (len < cpumask_size()) + cpumask_clear(new_mask); + else if (len > cpumask_size()) + len = cpumask_size(); + + return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0; +} + +/** + * sys_sched_setaffinity - set the CPU affinity of a process + * @pid: pid of the process + * @len: length in bytes of the bitmask pointed to by user_mask_ptr + * @user_mask_ptr: user-space pointer to the new CPU mask + * + * Return: 0 on success. An error code otherwise. + */ +SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len, + unsigned long __user *, user_mask_ptr) +{ + cpumask_var_t new_mask; + int retval; + + if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) + return -ENOMEM; + + retval = get_user_cpu_mask(user_mask_ptr, len, new_mask); + if (retval == 0) + retval = sched_setaffinity(pid, new_mask); + free_cpumask_var(new_mask); + return retval; +} + +long sched_getaffinity(pid_t pid, cpumask_t *mask) +{ + struct task_struct *p; + raw_spinlock_t *lock; + unsigned long flags; + int retval; + + rcu_read_lock(); + + retval = -ESRCH; + p = find_process_by_pid(pid); + if (!p) + goto out_unlock; + + retval = security_task_getscheduler(p); + if (retval) + goto out_unlock; + + task_access_lock_irqsave(p, &lock, &flags); + cpumask_and(mask, &p->cpus_mask, cpu_active_mask); + task_access_unlock_irqrestore(p, lock, &flags); + +out_unlock: + rcu_read_unlock(); + + return retval; +} + +/** + * sys_sched_getaffinity - get the CPU affinity of a process + * @pid: pid of the process + * @len: length in bytes of the bitmask pointed to by user_mask_ptr + * @user_mask_ptr: user-space pointer to hold the current CPU mask + * + * Return: size of CPU mask copied to user_mask_ptr on success. An + * error code otherwise. + */ +SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, + unsigned long __user *, user_mask_ptr) +{ + int ret; + cpumask_var_t mask; + + if ((len * BITS_PER_BYTE) < nr_cpu_ids) + return -EINVAL; + if (len & (sizeof(unsigned long)-1)) + return -EINVAL; + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + + ret = sched_getaffinity(pid, mask); + if (ret == 0) { + unsigned int retlen = min_t(size_t, len, cpumask_size()); + + if (copy_to_user(user_mask_ptr, mask, retlen)) + ret = -EFAULT; + else + ret = retlen; + } + free_cpumask_var(mask); + + return ret; +} + +/** + * sys_sched_yield - yield the current processor to other threads. + * + * This function yields the current CPU to other tasks. It does this by + * scheduling away the current task. If it still has the earliest deadline + * it will be scheduled again as the next task. + * + * Return: 0. + */ +static void do_sched_yield(void) +{ + struct rq *rq; + struct rq_flags rf; + + if (!sched_yield_type) + return; + + rq = this_rq_lock_irq(&rf); + + schedstat_inc(rq->yld_count); + + if (1 == sched_yield_type) { + if (!rt_task(current)) { + current->boost_prio = MAX_PRIORITY_ADJ; + requeue_task(current, rq); + } + } else if (2 == sched_yield_type) { + if (rq->nr_running > 1) + rq->skip = current; + } + + /* + * Since we are going to call schedule() anyway, there's + * no need to preempt or enable interrupts: + */ + preempt_disable(); + raw_spin_unlock(&rq->lock); + sched_preempt_enable_no_resched(); + + schedule(); +} + +SYSCALL_DEFINE0(sched_yield) +{ + do_sched_yield(); + return 0; +} + +#ifndef CONFIG_PREEMPTION +int __sched _cond_resched(void) +{ + if (should_resched(0)) { + preempt_schedule_common(); + return 1; + } + rcu_all_qs(); + return 0; +} +EXPORT_SYMBOL(_cond_resched); +#endif + +/* + * __cond_resched_lock() - if a reschedule is pending, drop the given lock, + * call schedule, and on return reacquire the lock. + * + * This works OK both with and without CONFIG_PREEMPTION. We do strange low-level + * operations here to prevent schedule() from being called twice (once via + * spin_unlock(), once by hand). + */ +int __cond_resched_lock(spinlock_t *lock) +{ + int resched = should_resched(PREEMPT_LOCK_OFFSET); + int ret = 0; + + lockdep_assert_held(lock); + + if (spin_needbreak(lock) || resched) { + spin_unlock(lock); + if (resched) + preempt_schedule_common(); + else + cpu_relax(); + ret = 1; + spin_lock(lock); + } + return ret; +} +EXPORT_SYMBOL(__cond_resched_lock); + +/** + * yield - yield the current processor to other threads. + * + * Do not ever use this function, there's a 99% chance you're doing it wrong. + * + * The scheduler is at all times free to pick the calling task as the most + * eligible task to run, if removing the yield() call from your code breaks + * it, its already broken. + * + * Typical broken usage is: + * + * while (!event) + * yield(); + * + * where one assumes that yield() will let 'the other' process run that will + * make event true. If the current task is a SCHED_FIFO task that will never + * happen. Never use yield() as a progress guarantee!! + * + * If you want to use yield() to wait for something, use wait_event(). + * If you want to use yield() to be 'nice' for others, use cond_resched(). + * If you still want to use yield(), do not! + */ +void __sched yield(void) +{ + set_current_state(TASK_RUNNING); + do_sched_yield(); +} +EXPORT_SYMBOL(yield); + +/** + * yield_to - yield the current processor to another thread in + * your thread group, or accelerate that thread toward the + * processor it's on. + * @p: target task + * @preempt: whether task preemption is allowed or not + * + * It's the caller's job to ensure that the target task struct + * can't go away on us before we can do any checks. + * + * In BMQ, yield_to is not supported. + * + * Return: + * true (>0) if we indeed boosted the target task. + * false (0) if we failed to boost the target. + * -ESRCH if there's no task to yield to. + */ +int __sched yield_to(struct task_struct *p, bool preempt) +{ + return 0; +} +EXPORT_SYMBOL_GPL(yield_to); + +int io_schedule_prepare(void) +{ + int old_iowait = current->in_iowait; + + current->in_iowait = 1; + blk_schedule_flush_plug(current); + + return old_iowait; +} + +void io_schedule_finish(int token) +{ + current->in_iowait = token; +} + +/* + * This task is about to go to sleep on IO. Increment rq->nr_iowait so + * that process accounting knows that this is a task in IO wait state. + * + * But don't do that if it is a deliberate, throttling IO wait (this task + * has set its backing_dev_info: the queue against which it should throttle) + */ + +long __sched io_schedule_timeout(long timeout) +{ + int token; + long ret; + + token = io_schedule_prepare(); + ret = schedule_timeout(timeout); + io_schedule_finish(token); + + return ret; +} +EXPORT_SYMBOL(io_schedule_timeout); + +void __sched io_schedule(void) +{ + int token; + + token = io_schedule_prepare(); + schedule(); + io_schedule_finish(token); +} +EXPORT_SYMBOL(io_schedule); + +/** + * sys_sched_get_priority_max - return maximum RT priority. + * @policy: scheduling class. + * + * Return: On success, this syscall returns the maximum + * rt_priority that can be used by a given scheduling class. + * On failure, a negative error code is returned. + */ +SYSCALL_DEFINE1(sched_get_priority_max, int, policy) +{ + int ret = -EINVAL; + + switch (policy) { + case SCHED_FIFO: + case SCHED_RR: + ret = MAX_USER_RT_PRIO-1; + break; + case SCHED_NORMAL: + case SCHED_BATCH: + case SCHED_IDLE: + ret = 0; + break; + } + return ret; +} + +/** + * sys_sched_get_priority_min - return minimum RT priority. + * @policy: scheduling class. + * + * Return: On success, this syscall returns the minimum + * rt_priority that can be used by a given scheduling class. + * On failure, a negative error code is returned. + */ +SYSCALL_DEFINE1(sched_get_priority_min, int, policy) +{ + int ret = -EINVAL; + + switch (policy) { + case SCHED_FIFO: + case SCHED_RR: + ret = 1; + break; + case SCHED_NORMAL: + case SCHED_BATCH: + case SCHED_IDLE: + ret = 0; + break; + } + return ret; +} + +static int sched_rr_get_interval(pid_t pid, struct timespec64 *t) +{ + struct task_struct *p; + int retval; + + if (pid < 0) + return -EINVAL; + + retval = -ESRCH; + rcu_read_lock(); + p = find_process_by_pid(pid); + if (!p) + goto out_unlock; + + retval = security_task_getscheduler(p); + if (retval) + goto out_unlock; + rcu_read_unlock(); + + *t = ns_to_timespec64(SCHED_TIMESLICE_NS); + return 0; + +out_unlock: + rcu_read_unlock(); + return retval; +} + +/** + * sys_sched_rr_get_interval - return the default timeslice of a process. + * @pid: pid of the process. + * @interval: userspace pointer to the timeslice value. + * + * + * Return: On success, 0 and the timeslice is in @interval. Otherwise, + * an error code. + */ +SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, + struct __kernel_timespec __user *, interval) +{ + struct timespec64 t; + int retval = sched_rr_get_interval(pid, &t); + + if (retval == 0) + retval = put_timespec64(&t, interval); + + return retval; +} + +#ifdef CONFIG_COMPAT_32BIT_TIME +SYSCALL_DEFINE2(sched_rr_get_interval_time32, pid_t, pid, + struct old_timespec32 __user *, interval) +{ + struct timespec64 t; + int retval = sched_rr_get_interval(pid, &t); + + if (retval == 0) + retval = put_old_timespec32(&t, interval); + return retval; +} +#endif + +void sched_show_task(struct task_struct *p) +{ + unsigned long free = 0; + int ppid; + + if (!try_get_task_stack(p)) + return; + + printk(KERN_INFO "%-15.15s %c", p->comm, task_state_to_char(p)); + + if (p->state == TASK_RUNNING) + printk(KERN_CONT " running task "); +#ifdef CONFIG_DEBUG_STACK_USAGE + free = stack_not_used(p); +#endif + ppid = 0; + rcu_read_lock(); + if (pid_alive(p)) + ppid = task_pid_nr(rcu_dereference(p->real_parent)); + rcu_read_unlock(); + printk(KERN_CONT "%5lu %5d %6d 0x%08lx\n", free, + task_pid_nr(p), ppid, + (unsigned long)task_thread_info(p)->flags); + + print_worker_info(KERN_INFO, p); + show_stack(p, NULL); + put_task_stack(p); +} +EXPORT_SYMBOL_GPL(sched_show_task); + +static inline bool +state_filter_match(unsigned long state_filter, struct task_struct *p) +{ + /* no filter, everything matches */ + if (!state_filter) + return true; + + /* filter, but doesn't match */ + if (!(p->state & state_filter)) + return false; + + /* + * When looking for TASK_UNINTERRUPTIBLE skip TASK_IDLE (allows + * TASK_KILLABLE). + */ + if (state_filter == TASK_UNINTERRUPTIBLE && p->state == TASK_IDLE) + return false; + + return true; +} + + +void show_state_filter(unsigned long state_filter) +{ + struct task_struct *g, *p; + +#if BITS_PER_LONG == 32 + printk(KERN_INFO + " task PC stack pid father\n"); +#else + printk(KERN_INFO + " task PC stack pid father\n"); +#endif + rcu_read_lock(); + for_each_process_thread(g, p) { + /* + * 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_match(state_filter, p)) + sched_show_task(p); + } + +#ifdef CONFIG_SCHED_DEBUG + /* TODO: BMQ should support this + if (!state_filter) + sysrq_sched_debug_show(); + */ +#endif + rcu_read_unlock(); + /* + * Only show locks if all tasks are dumped: + */ + if (!state_filter) + debug_show_all_locks(); +} + +void dump_cpu_task(int cpu) +{ + pr_info("Task dump for CPU %d:\n", cpu); + sched_show_task(cpu_curr(cpu)); +} + +/** + * init_idle - set up an idle thread for a given CPU + * @idle: task in question + * @cpu: cpu the idle task belongs to + * + * NOTE: this function does not set the idle thread's NEED_RESCHED + * flag, to make booting more robust. + */ +void init_idle(struct task_struct *idle, int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + + raw_spin_lock_irqsave(&idle->pi_lock, flags); + raw_spin_lock(&rq->lock); + update_rq_clock(rq); + + idle->last_ran = rq->clock_task; + idle->state = TASK_RUNNING; + idle->flags |= PF_IDLE; + /* Setting prio to illegal value shouldn't matter when never queued */ + idle->prio = MAX_PRIO; + + idle->bmq_idx = IDLE_TASK_SCHED_PRIO; + bmq_init_idle(&rq->queue, idle); + + kasan_unpoison_task_stack(idle); + +#ifdef CONFIG_SMP + /* + * It's possible that init_idle() gets called multiple times on a task, + * in that case do_set_cpus_allowed() will not do the right thing. + * + * And since this is boot we can forgo the serialisation. + */ + set_cpus_allowed_common(idle, cpumask_of(cpu)); +#endif + + /* Silence PROVE_RCU */ + rcu_read_lock(); + __set_task_cpu(idle, cpu); + rcu_read_unlock(); + + rq->idle = idle; + rcu_assign_pointer(rq->curr, idle); + idle->on_cpu = 1; + + raw_spin_unlock(&rq->lock); + raw_spin_unlock_irqrestore(&idle->pi_lock, flags); + + /* Set the preempt count _outside_ the spinlocks! */ + init_idle_preempt_count(idle, cpu); + + ftrace_graph_init_idle_task(idle, cpu); + vtime_init_idle(idle, cpu); +#ifdef CONFIG_SMP + sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu); +#endif +} + +static bool __wake_q_add(struct wake_q_head *head, struct task_struct *task) +{ + struct wake_q_node *node = &task->wake_q; + + /* + * Atomically grab the task, if ->wake_q is !nil already it means + * its already queued (either by us or someone else) and will get the + * wakeup due to that. + * + * In order to ensure that a pending wakeup will observe our pending + * state, even in the failed case, an explicit smp_mb() must be used. + */ + smp_mb__before_atomic(); + if (unlikely(cmpxchg_relaxed(&node->next, NULL, WAKE_Q_TAIL))) + return false; + + /* + * The head is context local, there can be no concurrency. + */ + *head->lastp = node; + head->lastp = &node->next; + return true; +} + +/** + * wake_q_add() - queue a wakeup for 'later' waking. + * @head: the wake_q_head to add @task to + * @task: the task to queue for 'later' wakeup + * + * Queue a task for later wakeup, most likely by the wake_up_q() call in the + * same context, _HOWEVER_ this is not guaranteed, the wakeup can come + * instantly. + * + * This function must be used as-if it were wake_up_process(); IOW the task + * must be ready to be woken at this location. + */ +void wake_q_add(struct wake_q_head *head, struct task_struct *task) +{ + if (__wake_q_add(head, task)) + get_task_struct(task); +} + +/** + * wake_q_add_safe() - safely queue a wakeup for 'later' waking. + * @head: the wake_q_head to add @task to + * @task: the task to queue for 'later' wakeup + * + * Queue a task for later wakeup, most likely by the wake_up_q() call in the + * same context, _HOWEVER_ this is not guaranteed, the wakeup can come + * instantly. + * + * This function must be used as-if it were wake_up_process(); IOW the task + * must be ready to be woken at this location. + * + * This function is essentially a task-safe equivalent to wake_q_add(). Callers + * that already hold reference to @task can call the 'safe' version and trust + * wake_q to do the right thing depending whether or not the @task is already + * queued for wakeup. + */ +void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task) +{ + if (!__wake_q_add(head, task)) + put_task_struct(task); +} + +void wake_up_q(struct wake_q_head *head) +{ + struct wake_q_node *node = head->first; + + while (node != WAKE_Q_TAIL) { + struct task_struct *task; + + task = container_of(node, struct task_struct, wake_q); + BUG_ON(!task); + /* task can safely be re-inserted now: */ + node = node->next; + task->wake_q.next = NULL; + + /* + * wake_up_process() executes a full barrier, which pairs with + * the queueing in wake_q_add() so as not to miss wakeups. + */ + wake_up_process(task); + put_task_struct(task); + } +} + +#ifdef CONFIG_SMP + +int cpuset_cpumask_can_shrink(const struct cpumask __maybe_unused *cur, + const struct cpumask __maybe_unused *trial) +{ + return 1; +} + +int task_can_attach(struct task_struct *p, + const struct cpumask *cs_cpus_allowed) +{ + int ret = 0; + + /* + * Kthreads which disallow setaffinity shouldn't be moved + * to a new cpuset; we don't want to change their CPU + * affinity and isolating such threads by their set of + * allowed nodes is unnecessary. Thus, cpusets are not + * applicable for such threads. This prevents checking for + * success of set_cpus_allowed_ptr() on all attached tasks + * before cpus_mask may be changed. + */ + if (p->flags & PF_NO_SETAFFINITY) + ret = -EINVAL; + + return ret; +} + +static bool sched_smp_initialized __read_mostly; + +#ifdef CONFIG_NO_HZ_COMMON +void nohz_balance_enter_idle(int cpu) +{ +} + +void select_nohz_load_balancer(int stop_tick) +{ +} + +void set_cpu_sd_state_idle(void) {} + +/* + * In the semi idle case, use the nearest busy CPU for migrating timers + * from an idle CPU. This is good for power-savings. + * + * We don't do similar optimization for completely idle system, as + * selecting an idle CPU will add more delays to the timers than intended + * (as that CPU's timer base may not be uptodate wrt jiffies etc). + */ +int get_nohz_timer_target(void) +{ + int i, cpu = smp_processor_id(); + struct cpumask *mask; + + if (!idle_cpu(cpu) && housekeeping_cpu(cpu, HK_FLAG_TIMER)) + return cpu; + + for (mask = &(per_cpu(sched_cpu_affinity_masks, cpu)[0]); + mask < per_cpu(sched_cpu_affinity_end_mask, cpu); mask++) + for_each_cpu(i, mask) + if (!idle_cpu(i) && housekeeping_cpu(i, HK_FLAG_TIMER)) + return i; + + if (!housekeeping_cpu(cpu, HK_FLAG_TIMER)) + cpu = housekeeping_any_cpu(HK_FLAG_TIMER); + + return cpu; +} + +/* + * When add_timer_on() enqueues a timer into the timer wheel of an + * idle CPU then this timer might expire before the next timer event + * which is scheduled to wake up that CPU. In case of a completely + * idle system the next event might even be infinite time into the + * future. wake_up_idle_cpu() ensures that the CPU is woken up and + * leaves the inner idle loop so the newly added timer is taken into + * account when the CPU goes back to idle and evaluates the timer + * wheel for the next timer event. + */ +void wake_up_idle_cpu(int cpu) +{ + if (cpu == smp_processor_id()) + return; + + set_tsk_need_resched(cpu_rq(cpu)->idle); + smp_send_reschedule(cpu); +} + +void wake_up_nohz_cpu(int cpu) +{ + wake_up_idle_cpu(cpu); +} +#endif /* CONFIG_NO_HZ_COMMON */ + +#ifdef CONFIG_HOTPLUG_CPU +/* + * Ensures that the idle task is using init_mm right before its CPU goes + * offline. + */ +void idle_task_exit(void) +{ + struct mm_struct *mm = current->active_mm; + + BUG_ON(cpu_online(smp_processor_id())); + + if (mm != &init_mm) { + switch_mm(mm, &init_mm, current); + current->active_mm = &init_mm; + finish_arch_post_lock_switch(); + } + mmdrop(mm); +} + +/* + * Migrate all tasks from the rq, sleeping tasks will be migrated by + * try_to_wake_up()->select_task_rq(). + * + * Called with rq->lock held even though we'er in stop_machine() and + * there's no concurrency possible, we hold the required locks anyway + * because of lock validation efforts. + */ +static void migrate_tasks(struct rq *dead_rq) +{ + struct rq *rq = dead_rq; + struct task_struct *p, *stop = rq->stop; + int count = 0; + + /* + * Fudge the rq selection such that the below task selection loop + * doesn't get stuck on the currently eligible stop task. + * + * We're currently inside stop_machine() and the rq is either stuck + * in the stop_machine_cpu_stop() loop, or we're executing this code, + * either way we should never end up calling schedule() until we're + * done here. + */ + rq->stop = NULL; + + p = rq_first_bmq_task(rq); + while (p != rq->idle) { + int dest_cpu; + + /* skip the running task */ + if (task_running(p) || 1 == p->nr_cpus_allowed) { + p = rq_next_bmq_task(p, rq); + continue; + } + + /* + * Rules for changing task_struct::cpus_allowed are holding + * both pi_lock and rq->lock, such that holding either + * stabilizes the mask. + * + * Drop rq->lock is not quite as disastrous as it usually is + * because !cpu_active at this point, which means load-balance + * will not interfere. Also, stop-machine. + */ + raw_spin_unlock(&rq->lock); + raw_spin_lock(&p->pi_lock); + raw_spin_lock(&rq->lock); + + /* + * Since we're inside stop-machine, _nothing_ should have + * changed the task, WARN if weird stuff happened, because in + * that case the above rq->lock drop is a fail too. + */ + if (WARN_ON(task_rq(p) != rq || !task_on_rq_queued(p))) { + raw_spin_unlock(&p->pi_lock); + p = rq_next_bmq_task(p, rq); + continue; + } + + count++; + /* Find suitable destination for @next, with force if needed. */ + dest_cpu = select_fallback_rq(dead_rq->cpu, p); + rq = __migrate_task(rq, p, dest_cpu); + raw_spin_unlock(&rq->lock); + raw_spin_unlock(&p->pi_lock); + + rq = dead_rq; + raw_spin_lock(&rq->lock); + /* Check queued task all over from the header again */ + p = rq_first_bmq_task(rq); + } + + rq->stop = stop; +} + +static void set_rq_offline(struct rq *rq) +{ + if (rq->online) + rq->online = false; +} +#endif /* CONFIG_HOTPLUG_CPU */ + +static void set_rq_online(struct rq *rq) +{ + if (!rq->online) + rq->online = true; +} + +#ifdef CONFIG_SCHED_DEBUG + +static __read_mostly int sched_debug_enabled; + +static int __init sched_debug_setup(char *str) +{ + sched_debug_enabled = 1; + + return 0; +} +early_param("sched_debug", sched_debug_setup); + +static inline bool sched_debug(void) +{ + return sched_debug_enabled; +} +#else /* !CONFIG_SCHED_DEBUG */ +static inline bool sched_debug(void) +{ + return false; +} +#endif /* CONFIG_SCHED_DEBUG */ + +#ifdef CONFIG_SMP +void scheduler_ipi(void) +{ + /* + * Fold TIF_NEED_RESCHED into the preempt_count; anybody setting + * TIF_NEED_RESCHED remotely (for the first time) will also send + * this IPI. + */ + preempt_fold_need_resched(); + + if (!idle_cpu(smp_processor_id()) || need_resched()) + return; + + irq_enter(); + irq_exit(); +} + +void wake_up_if_idle(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + + rcu_read_lock(); + + if (!is_idle_task(rcu_dereference(rq->curr))) + goto out; + + if (set_nr_if_polling(rq->idle)) { + trace_sched_wake_idle_without_ipi(cpu); + } else { + raw_spin_lock_irqsave(&rq->lock, flags); + if (is_idle_task(rq->curr)) + smp_send_reschedule(cpu); + /* Else CPU is not idle, do nothing here */ + raw_spin_unlock_irqrestore(&rq->lock, flags); + } + +out: + rcu_read_unlock(); +} + +bool cpus_share_cache(int this_cpu, int that_cpu) +{ + return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu); +} +#endif /* CONFIG_SMP */ + +/* + * Topology list, bottom-up. + */ +static struct sched_domain_topology_level default_topology[] = { +#ifdef CONFIG_SCHED_SMT + { cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) }, +#endif +#ifdef CONFIG_SCHED_MC + { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) }, +#endif + { cpu_cpu_mask, SD_INIT_NAME(DIE) }, + { NULL, }, +}; + +static struct sched_domain_topology_level *sched_domain_topology = + default_topology; + +#define for_each_sd_topology(tl) \ + for (tl = sched_domain_topology; tl->mask; tl++) + +void set_sched_topology(struct sched_domain_topology_level *tl) +{ + if (WARN_ON_ONCE(sched_smp_initialized)) + return; + + sched_domain_topology = tl; +} + +/* + * Initializers for schedule domains + * Non-inlined to reduce accumulated stack pressure in build_sched_domains() + */ + +int sched_domain_level_max; + +/* + * Partition sched domains as specified by the 'ndoms_new' + * cpumasks in the array doms_new[] of cpumasks. This compares + * doms_new[] to the current sched domain partitioning, doms_cur[]. + * It destroys each deleted domain and builds each new domain. + * + * 'doms_new' is an array of cpumask_var_t's of length 'ndoms_new'. + * The masks don't intersect (don't overlap.) We should setup one + * sched domain for each mask. CPUs not in any of the cpumasks will + * not be load balanced. If the same cpumask appears both in the + * current 'doms_cur' domains and in the new 'doms_new', we can leave + * it as it is. + * + * The passed in 'doms_new' should be allocated using + * alloc_sched_domains. This routine takes ownership of it and will + * free_sched_domains it when done with it. If the caller failed the + * alloc call, then it can pass in doms_new == NULL && ndoms_new == 1, + * and partition_sched_domains() will fallback to the single partition + * 'fallback_doms', it also forces the domains to be rebuilt. + * + * If doms_new == NULL it will be replaced with cpu_online_mask. + * ndoms_new == 0 is a special case for destroying existing domains, + * and it will not create the default domain. + * + * Call with hotplug lock held + */ +void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], + struct sched_domain_attr *dattr_new) +{ + /** + * BMQ doesn't depend on sched domains, but just keep this api + */ +} + +/* + * used to mark begin/end of suspend/resume: + */ +static int num_cpus_frozen; + +#ifdef CONFIG_NUMA +int __read_mostly node_reclaim_distance = RECLAIM_DISTANCE; + +/* + * sched_numa_find_closest() - given the NUMA topology, find the cpu + * closest to @cpu from @cpumask. + * cpumask: cpumask to find a cpu from + * cpu: cpu to be close to + * + * returns: cpu, or nr_cpu_ids when nothing found. + */ +int sched_numa_find_closest(const struct cpumask *cpus, int cpu) +{ + return best_mask_cpu(cpu, cpus); +} +#endif /* CONFIG_NUMA */ + +/* + * Update cpusets according to cpu_active mask. If cpusets are + * disabled, cpuset_update_active_cpus() becomes a simple wrapper + * around partition_sched_domains(). + * + * If we come here as part of a suspend/resume, don't touch cpusets because we + * want to restore it back to its original state upon resume anyway. + */ +static void cpuset_cpu_active(void) +{ + if (cpuhp_tasks_frozen) { + /* + * num_cpus_frozen tracks how many CPUs are involved in suspend + * resume sequence. As long as this is not the last online + * operation in the resume sequence, just build a single sched + * domain, ignoring cpusets. + */ + partition_sched_domains(1, NULL, NULL); + if (--num_cpus_frozen) + return; + /* + * This is the last CPU online operation. So fall through and + * restore the original sched domains by considering the + * cpuset configurations. + */ + cpuset_force_rebuild(); + } + + cpuset_update_active_cpus(); +} + +static int cpuset_cpu_inactive(unsigned int cpu) +{ + if (!cpuhp_tasks_frozen) { + cpuset_update_active_cpus(); + } else { + num_cpus_frozen++; + partition_sched_domains(1, NULL, NULL); + } + return 0; +} + +int sched_cpu_activate(unsigned int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + +#ifdef CONFIG_SCHED_SMT + /* + * When going up, increment the number of cores with SMT present. + */ + if (cpumask_weight(cpu_smt_mask(cpu)) == 2) + static_branch_inc_cpuslocked(&sched_smt_present); +#endif + set_cpu_active(cpu, true); + + if (sched_smp_initialized) + cpuset_cpu_active(); + + /* + * Put the rq online, if not already. This happens: + * + * 1) In the early boot process, because we build the real domains + * after all cpus have been brought up. + * + * 2) At runtime, if cpuset_cpu_active() fails to rebuild the + * domains. + */ + raw_spin_lock_irqsave(&rq->lock, flags); + set_rq_online(rq); + raw_spin_unlock_irqrestore(&rq->lock, flags); + + return 0; +} + +int sched_cpu_deactivate(unsigned int cpu) +{ + int ret; + + set_cpu_active(cpu, false); + /* + * We've cleared cpu_active_mask, wait for all preempt-disabled and RCU + * users of this state to go away such that all new such users will + * observe it. + * + * Do sync before park smpboot threads to take care the rcu boost case. + */ + synchronize_rcu(); + +#ifdef CONFIG_SCHED_SMT + /* + * When going down, decrement the number of cores with SMT present. + */ + if (cpumask_weight(cpu_smt_mask(cpu)) == 2) { + static_branch_dec_cpuslocked(&sched_smt_present); + if (!static_branch_likely(&sched_smt_present)) + cpumask_clear(&sched_sg_idle_mask); + } +#endif + + if (!sched_smp_initialized) + return 0; + + ret = cpuset_cpu_inactive(cpu); + if (ret) { + set_cpu_active(cpu, true); + return ret; + } + return 0; +} + +static void sched_rq_cpu_starting(unsigned int cpu) +{ + struct rq *rq = cpu_rq(cpu); + + rq->calc_load_update = calc_load_update; +} + +int sched_cpu_starting(unsigned int cpu) +{ + sched_rq_cpu_starting(cpu); + sched_tick_start(cpu); + return 0; +} + +#ifdef CONFIG_HOTPLUG_CPU +int sched_cpu_dying(unsigned int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + + sched_tick_stop(cpu); + raw_spin_lock_irqsave(&rq->lock, flags); + set_rq_offline(rq); + migrate_tasks(rq); + raw_spin_unlock_irqrestore(&rq->lock, flags); + + hrtick_clear(rq); + return 0; +} +#endif + +#ifdef CONFIG_SMP +static void sched_init_topology_cpumask_early(void) +{ + int cpu, level; + cpumask_t *tmp; + + for_each_possible_cpu(cpu) { + for (level = 0; level < NR_CPU_AFFINITY_CHK_LEVEL; level++) { + tmp = &(per_cpu(sched_cpu_affinity_masks, cpu)[level]); + cpumask_copy(tmp, cpu_possible_mask); + cpumask_clear_cpu(cpu, tmp); + } + per_cpu(sched_cpu_affinity_end_mask, cpu) = + &(per_cpu(sched_cpu_affinity_masks, cpu)[1]); + } +} + +static void sched_init_topology_cpumask(void) +{ + int cpu; + cpumask_t *chk; + + for_each_online_cpu(cpu) { + chk = &(per_cpu(sched_cpu_affinity_masks, cpu)[0]); + +#ifdef CONFIG_SCHED_SMT + cpumask_setall(chk); + cpumask_clear_cpu(cpu, chk); + if (cpumask_and(chk, chk, topology_sibling_cpumask(cpu))) { + printk(KERN_INFO "bmq: cpu #%d affinity check mask - smt 0x%08lx", + cpu, (chk++)->bits[0]); + } + cpumask_complement(chk, topology_sibling_cpumask(cpu)); +#else + cpumask_clear_cpu(cpu, chk); +#endif +#ifdef CONFIG_SCHED_MC + if (cpumask_and(chk, chk, cpu_coregroup_mask(cpu))) + printk(KERN_INFO "bmq: cpu #%d affinity check mask - coregroup 0x%08lx", + cpu, (chk++)->bits[0]); + cpumask_complement(chk, cpu_coregroup_mask(cpu)); + + /** + * Set up sd_llc_id per CPU + */ + per_cpu(sd_llc_id, cpu) = + cpumask_first(cpu_coregroup_mask(cpu)); +#else + per_cpu(sd_llc_id, cpu) = + cpumask_first(topology_core_cpumask(cpu)); + + cpumask_setall(chk); + cpumask_clear_cpu(cpu, chk); +#endif /* NOT CONFIG_SCHED_MC */ + if (cpumask_and(chk, chk, topology_core_cpumask(cpu))) + printk(KERN_INFO "bmq: cpu #%d affinity check mask - core 0x%08lx", + cpu, (chk++)->bits[0]); + cpumask_complement(chk, topology_core_cpumask(cpu)); + + if (cpumask_and(chk, chk, cpu_online_mask)) + printk(KERN_INFO "bmq: cpu #%d affinity check mask - others 0x%08lx", + cpu, (chk++)->bits[0]); + + per_cpu(sched_cpu_affinity_end_mask, cpu) = chk; + } +} +#endif + +void __init sched_init_smp(void) +{ + /* Move init over to a non-isolated CPU */ + if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_DOMAIN)) < 0) + BUG(); + + sched_init_topology_cpumask(); + + sched_smp_initialized = true; +} +#else +void __init sched_init_smp(void) +{ +} +#endif /* CONFIG_SMP */ + +int in_sched_functions(unsigned long addr) +{ + return in_lock_functions(addr) || + (addr >= (unsigned long)__sched_text_start + && addr < (unsigned long)__sched_text_end); +} + +#ifdef CONFIG_CGROUP_SCHED +/* task group related information */ +struct task_group { + struct cgroup_subsys_state css; + + struct rcu_head rcu; + struct list_head list; + + struct task_group *parent; + struct list_head siblings; + struct list_head children; +}; + +/* + * Default task group. + * Every task in system belongs to this group at bootup. + */ +struct task_group root_task_group; +LIST_HEAD(task_groups); + +/* Cacheline aligned slab cache for task_group */ +static struct kmem_cache *task_group_cache __read_mostly; +#endif /* CONFIG_CGROUP_SCHED */ + +void __init sched_init(void) +{ + int i; + struct rq *rq; + + print_scheduler_version(); + + wait_bit_init(); + +#ifdef CONFIG_SMP + for (i = 0; i < bmq_BITS; i++) + cpumask_copy(&sched_rq_watermark[i], cpu_present_mask); +#endif + +#ifdef CONFIG_CGROUP_SCHED + task_group_cache = KMEM_CACHE(task_group, 0); + + list_add(&root_task_group.list, &task_groups); + INIT_LIST_HEAD(&root_task_group.children); + INIT_LIST_HEAD(&root_task_group.siblings); +#endif /* CONFIG_CGROUP_SCHED */ + for_each_possible_cpu(i) { + rq = cpu_rq(i); + + bmq_init(&rq->queue); + rq->watermark = IDLE_WM; + rq->skip = NULL; + + raw_spin_lock_init(&rq->lock); + rq->nr_running = rq->nr_uninterruptible = 0; + rq->calc_load_active = 0; + rq->calc_load_update = jiffies + LOAD_FREQ; +#ifdef CONFIG_SMP + rq->online = false; + rq->cpu = i; + +#ifdef CONFIG_SCHED_SMT + rq->active_balance = 0; +#endif +#endif + rq->nr_switches = 0; + atomic_set(&rq->nr_iowait, 0); + hrtick_rq_init(rq); + } +#ifdef CONFIG_SMP + /* Set rq->online for cpu 0 */ + cpu_rq(0)->online = true; +#endif + + /* + * The boot idle thread does lazy MMU switching as well: + */ + mmgrab(&init_mm); + enter_lazy_tlb(&init_mm, current); + + /* + * Make us the idle thread. Technically, schedule() should not be + * called from this thread, however somewhere below it might be, + * but because we are the idle thread, we just pick up running again + * when this runqueue becomes "idle". + */ + init_idle(current, smp_processor_id()); + + calc_load_update = jiffies + LOAD_FREQ; + +#ifdef CONFIG_SMP + idle_thread_set_boot_cpu(); + + sched_init_topology_cpumask_early(); +#endif /* SMP */ + + init_schedstats(); + + psi_init(); +} + +#ifdef CONFIG_DEBUG_ATOMIC_SLEEP +static inline int preempt_count_equals(int preempt_offset) +{ + int nested = preempt_count() + rcu_preempt_depth(); + + return (nested == preempt_offset); +} + +void __might_sleep(const char *file, int line, int preempt_offset) +{ + /* + * Blocking primitives will set (and therefore destroy) current->state, + * since we will exit with TASK_RUNNING make sure we enter with it, + * otherwise we will destroy state. + */ + WARN_ONCE(current->state != TASK_RUNNING && current->task_state_change, + "do not call blocking ops when !TASK_RUNNING; " + "state=%lx set at [<%p>] %pS\n", + current->state, + (void *)current->task_state_change, + (void *)current->task_state_change); + + ___might_sleep(file, line, preempt_offset); +} +EXPORT_SYMBOL(__might_sleep); + +void ___might_sleep(const char *file, int line, int preempt_offset) +{ + /* Ratelimiting timestamp: */ + static unsigned long prev_jiffy; + + unsigned long preempt_disable_ip; + + /* WARN_ON_ONCE() by default, no rate limit required: */ + rcu_sleep_check(); + + if ((preempt_count_equals(preempt_offset) && !irqs_disabled() && + !is_idle_task(current) && !current->non_block_count) || + system_state == SYSTEM_BOOTING || system_state > SYSTEM_RUNNING || + oops_in_progress) + return; + if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy) + return; + prev_jiffy = jiffies; + + /* Save this before calling printk(), since that will clobber it: */ + preempt_disable_ip = get_preempt_disable_ip(current); + + printk(KERN_ERR + "BUG: sleeping function called from invalid context at %s:%d\n", + file, line); + printk(KERN_ERR + "in_atomic(): %d, irqs_disabled(): %d, non_block: %d, pid: %d, name: %s\n", + in_atomic(), irqs_disabled(), current->non_block_count, + current->pid, current->comm); + + if (task_stack_end_corrupted(current)) + printk(KERN_EMERG "Thread overran stack, or stack corrupted\n"); + + debug_show_held_locks(current); + if (irqs_disabled()) + print_irqtrace_events(current); +#ifdef CONFIG_DEBUG_PREEMPT + if (!preempt_count_equals(preempt_offset)) { + pr_err("Preemption disabled at:"); + print_ip_sym(preempt_disable_ip); + pr_cont("\n"); + } +#endif + dump_stack(); + add_taint(TAINT_WARN, LOCKDEP_STILL_OK); +} +EXPORT_SYMBOL(___might_sleep); + +void __cant_sleep(const char *file, int line, int preempt_offset) +{ + static unsigned long prev_jiffy; + + if (irqs_disabled()) + return; + + if (!IS_ENABLED(CONFIG_PREEMPT_COUNT)) + return; + + if (preempt_count() > preempt_offset) + return; + + if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy) + return; + prev_jiffy = jiffies; + + printk(KERN_ERR "BUG: assuming atomic context at %s:%d\n", file, line); + printk(KERN_ERR "in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n", + in_atomic(), irqs_disabled(), + current->pid, current->comm); + + debug_show_held_locks(current); + dump_stack(); + add_taint(TAINT_WARN, LOCKDEP_STILL_OK); +} +EXPORT_SYMBOL_GPL(__cant_sleep); +#endif + +#ifdef CONFIG_MAGIC_SYSRQ +void normalize_rt_tasks(void) +{ + struct task_struct *g, *p; + struct sched_attr attr = { + .sched_policy = SCHED_NORMAL, + }; + + read_lock(&tasklist_lock); + for_each_process_thread(g, p) { + /* + * Only normalize user tasks: + */ + if (p->flags & PF_KTHREAD) + continue; + + if (!rt_task(p)) { + /* + * Renice negative nice level userspace + * tasks back to 0: + */ + if (task_nice(p) < 0) + set_user_nice(p, 0); + continue; + } + + __sched_setscheduler(p, &attr, false, false); + } + read_unlock(&tasklist_lock); +} +#endif /* CONFIG_MAGIC_SYSRQ */ + +#if defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) +/* + * These functions are only useful for the IA64 MCA handling, or kdb. + * + * They can only be called when the whole system has been + * stopped - every CPU needs to be quiescent, and no scheduling + * activity can take place. Using them for anything else would + * be a serious bug, and as a result, they aren't even visible + * under any other configuration. + */ + +/** + * curr_task - return the current task for a given CPU. + * @cpu: the processor in question. + * + * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED! + * + * Return: The current task for @cpu. + */ +struct task_struct *curr_task(int cpu) +{ + return cpu_curr(cpu); +} + +#endif /* defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) */ + +#ifdef CONFIG_IA64 +/** + * ia64_set_curr_task - set the current task for a given CPU. + * @cpu: the processor in question. + * @p: the task pointer to set. + * + * Description: This function must only be used when non-maskable interrupts + * are serviced on a separate stack. It allows the architecture to switch the + * notion of the current task on a CPU in a non-blocking manner. This function + * must be called with all CPU's synchronised, and interrupts disabled, the + * and caller must save the original value of the current task (see + * curr_task() above) and restore that value before reenabling interrupts and + * re-starting the system. + * + * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED! + */ +void ia64_set_curr_task(int cpu, struct task_struct *p) +{ + cpu_curr(cpu) = p; +} + +#endif + +#ifdef CONFIG_SCHED_DEBUG +void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, + struct seq_file *m) +{ + SEQ_printf(m, "%s (%d, #threads: %d)\n", p->comm, task_pid_nr_ns(p, ns), + get_nr_threads(p)); +} + +void proc_sched_set_task(struct task_struct *p) +{} +#endif + +#ifdef CONFIG_CGROUP_SCHED +static void sched_free_group(struct task_group *tg) +{ + kmem_cache_free(task_group_cache, tg); +} + +/* allocate runqueue etc for a new task group */ +struct task_group *sched_create_group(struct task_group *parent) +{ + struct task_group *tg; + + tg = kmem_cache_alloc(task_group_cache, GFP_KERNEL | __GFP_ZERO); + if (!tg) + return ERR_PTR(-ENOMEM); + + return tg; +} + +void sched_online_group(struct task_group *tg, struct task_group *parent) +{ +} + +/* rcu callback to free various structures associated with a task group */ +static void sched_free_group_rcu(struct rcu_head *rhp) +{ + /* Now it should be safe to free those cfs_rqs */ + sched_free_group(container_of(rhp, struct task_group, rcu)); +} + +void sched_destroy_group(struct task_group *tg) +{ + /* Wait for possible concurrent references to cfs_rqs complete */ + call_rcu(&tg->rcu, sched_free_group_rcu); +} + +void sched_offline_group(struct task_group *tg) +{ +} + +static inline struct task_group *css_tg(struct cgroup_subsys_state *css) +{ + return css ? container_of(css, struct task_group, css) : NULL; +} + +static struct cgroup_subsys_state * +cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) +{ + struct task_group *parent = css_tg(parent_css); + struct task_group *tg; + + if (!parent) { + /* This is early initialization for the top cgroup */ + return &root_task_group.css; + } + + tg = sched_create_group(parent); + if (IS_ERR(tg)) + return ERR_PTR(-ENOMEM); + return &tg->css; +} + +/* Expose task group only after completing cgroup initialization */ +static int cpu_cgroup_css_online(struct cgroup_subsys_state *css) +{ + struct task_group *tg = css_tg(css); + struct task_group *parent = css_tg(css->parent); + + if (parent) + sched_online_group(tg, parent); + return 0; +} + +static void cpu_cgroup_css_released(struct cgroup_subsys_state *css) +{ + struct task_group *tg = css_tg(css); + + sched_offline_group(tg); +} + +static void cpu_cgroup_css_free(struct cgroup_subsys_state *css) +{ + struct task_group *tg = css_tg(css); + + /* + * Relies on the RCU grace period between css_released() and this. + */ + sched_free_group(tg); +} + +static void cpu_cgroup_fork(struct task_struct *task) +{ +} + +static int cpu_cgroup_can_attach(struct cgroup_taskset *tset) +{ + return 0; +} + +static void cpu_cgroup_attach(struct cgroup_taskset *tset) +{ +} + +static struct cftype cpu_legacy_files[] = { + { } /* Terminate */ +}; + +static struct cftype cpu_files[] = { + { } /* terminate */ +}; + +static int cpu_extra_stat_show(struct seq_file *sf, + struct cgroup_subsys_state *css) +{ + return 0; +} + +struct cgroup_subsys cpu_cgrp_subsys = { + .css_alloc = cpu_cgroup_css_alloc, + .css_online = cpu_cgroup_css_online, + .css_released = cpu_cgroup_css_released, + .css_free = cpu_cgroup_css_free, + .css_extra_stat_show = cpu_extra_stat_show, + .fork = cpu_cgroup_fork, + .can_attach = cpu_cgroup_can_attach, + .attach = cpu_cgroup_attach, + .legacy_cftypes = cpu_files, + .legacy_cftypes = cpu_legacy_files, + .dfl_cftypes = cpu_files, + .early_init = true, + .threaded = true, +}; +#endif /* CONFIG_CGROUP_SCHED */ + +#undef CREATE_TRACE_POINTS diff --git a/kernel/sched/bmq_sched.h b/kernel/sched/bmq_sched.h new file mode 100644 index 000000000000..ed08dd0b8227 --- /dev/null +++ b/kernel/sched/bmq_sched.h @@ -0,0 +1,472 @@ +#ifndef BMQ_SCHED_H +#define BMQ_SCHED_H + +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#ifdef CONFIG_PARAVIRT +# include +#endif + +#include "cpupri.h" + +/* task_struct::on_rq states: */ +#define TASK_ON_RQ_QUEUED 1 +#define TASK_ON_RQ_MIGRATING 2 + +static inline int task_on_rq_queued(struct task_struct *p) +{ + return p->on_rq == TASK_ON_RQ_QUEUED; +} + +static inline int task_on_rq_migrating(struct task_struct *p) +{ + return READ_ONCE(p->on_rq) == TASK_ON_RQ_MIGRATING; +} + +/* bits: + * RT, Low prio adj range, nice width, high prio adj range, cpu idle task */ +#define bmq_BITS (NICE_WIDTH + 2 * MAX_PRIORITY_ADJ + 2) +#define IDLE_TASK_SCHED_PRIO (bmq_BITS - 1) + +struct bmq { + DECLARE_BITMAP(bitmap, bmq_BITS); + struct list_head heads[bmq_BITS]; +}; + +/* + * This is the main, per-CPU runqueue data structure. + * This data should only be modified by the local cpu. + */ +struct rq { + /* runqueue lock: */ + raw_spinlock_t lock; + + struct task_struct *curr, *idle, *stop, *skip; + struct mm_struct *prev_mm; + + struct bmq queue; + unsigned long watermark; + + /* switch count */ + u64 nr_switches; + + atomic_t nr_iowait; + +#ifdef CONFIG_MEMBARRIER + int membarrier_state; +#endif + +#ifdef CONFIG_SMP + int cpu; /* cpu of this runqueue */ + bool online; + +#ifdef CONFIG_HAVE_SCHED_AVG_IRQ + struct sched_avg avg_irq; +#endif + +#ifdef CONFIG_SCHED_SMT + int active_balance; + struct cpu_stop_work active_balance_work; +#endif +#endif /* CONFIG_SMP */ +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + u64 prev_irq_time; +#endif /* CONFIG_IRQ_TIME_ACCOUNTING */ +#ifdef CONFIG_PARAVIRT + u64 prev_steal_time; +#endif /* CONFIG_PARAVIRT */ +#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING + u64 prev_steal_time_rq; +#endif /* CONFIG_PARAVIRT_TIME_ACCOUNTING */ + + /* calc_load related fields */ + unsigned long calc_load_update; + long calc_load_active; + + u64 clock, last_tick; + u64 last_ts_switch; + u64 clock_task; + + unsigned long nr_running; + unsigned long nr_uninterruptible; + +#ifdef CONFIG_SCHED_HRTICK +#ifdef CONFIG_SMP + int hrtick_csd_pending; + call_single_data_t hrtick_csd; +#endif + struct hrtimer hrtick_timer; +#endif + +#ifdef CONFIG_SCHEDSTATS + + /* latency stats */ + struct sched_info rq_sched_info; + unsigned long long rq_cpu_time; + /* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */ + + /* sys_sched_yield() stats */ + unsigned int yld_count; + + /* schedule() stats */ + unsigned int sched_switch; + unsigned int sched_count; + unsigned int sched_goidle; + + /* try_to_wake_up() stats */ + unsigned int ttwu_count; + unsigned int ttwu_local; +#endif /* CONFIG_SCHEDSTATS */ +#ifdef CONFIG_CPU_IDLE + /* Must be inspected within a rcu lock section */ + struct cpuidle_state *idle_state; +#endif +}; + +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, long adjust); + +DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); +#define cpu_rq(cpu) (&per_cpu(runqueues, (cpu))) +#define this_rq() this_cpu_ptr(&runqueues) +#define task_rq(p) cpu_rq(task_cpu(p)) +#define cpu_curr(cpu) (cpu_rq(cpu)->curr) +#define raw_rq() raw_cpu_ptr(&runqueues) + +#ifdef CONFIG_SMP +#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL) +void register_sched_domain_sysctl(void); +void unregister_sched_domain_sysctl(void); +#else +static inline void register_sched_domain_sysctl(void) +{ +} +static inline void unregister_sched_domain_sysctl(void) +{ +} +#endif +#endif /* CONFIG_SMP */ + +#ifndef arch_scale_freq_capacity +static __always_inline +unsigned long arch_scale_freq_capacity(int cpu) +{ + return SCHED_CAPACITY_SCALE; +} +#endif + +static inline u64 __rq_clock_broken(struct rq *rq) +{ + return READ_ONCE(rq->clock); +} + +static inline u64 rq_clock(struct rq *rq) +{ + /* + * Relax lockdep_assert_held() checking as in VRQ, call to + * sched_info_xxxx() may not held rq->lock + * lockdep_assert_held(&rq->lock); + */ + return rq->clock; +} + +static inline u64 rq_clock_task(struct rq *rq) +{ + /* + * Relax lockdep_assert_held() checking as in VRQ, call to + * sched_info_xxxx() may not held rq->lock + * lockdep_assert_held(&rq->lock); + */ + return rq->clock_task; +} + +/* + * {de,en}queue flags: + * + * DEQUEUE_SLEEP - task is no longer runnable + * ENQUEUE_WAKEUP - task just became runnable + * + */ + +#define DEQUEUE_SLEEP 0x01 + +#define ENQUEUE_WAKEUP 0x01 + + +/* + * Below are scheduler API which using in other kernel code + * It use the dummy rq_flags + * ToDo : BMQ need to support these APIs for compatibility with mainline + * scheduler code. + */ +struct rq_flags { + unsigned long flags; +}; + +struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf) + __acquires(rq->lock); + +struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf) + __acquires(p->pi_lock) + __acquires(rq->lock); + +static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf) + __releases(rq->lock) +{ + raw_spin_unlock(&rq->lock); +} + +static inline void +task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf) + __releases(rq->lock) + __releases(p->pi_lock) +{ + raw_spin_unlock(&rq->lock); + raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags); +} + +static inline void +rq_unlock_irq(struct rq *rq, struct rq_flags *rf) + __releases(rq->lock) +{ + raw_spin_unlock_irq(&rq->lock); +} + +static inline struct rq * +this_rq_lock_irq(struct rq_flags *rf) + __acquires(rq->lock) +{ + struct rq *rq; + + local_irq_disable(); + rq = this_rq(); + raw_spin_lock(&rq->lock); + + return rq; +} + +static inline bool task_running(struct task_struct *p) +{ + return p->on_cpu; +} + +extern struct static_key_false sched_schedstats; + +static inline void sched_ttwu_pending(void) { } + +#ifdef CONFIG_CPU_IDLE +static inline void idle_set_state(struct rq *rq, + struct cpuidle_state *idle_state) +{ + rq->idle_state = idle_state; +} + +static inline struct cpuidle_state *idle_get_state(struct rq *rq) +{ + WARN_ON(!rcu_read_lock_held()); + return rq->idle_state; +} +#else +static inline void idle_set_state(struct rq *rq, + struct cpuidle_state *idle_state) +{ +} + +static inline struct cpuidle_state *idle_get_state(struct rq *rq) +{ + return NULL; +} +#endif + +static inline int cpu_of(const struct rq *rq) +{ +#ifdef CONFIG_SMP + return rq->cpu; +#else + return 0; +#endif +} + +#include "stats.h" + +#ifdef CONFIG_IRQ_TIME_ACCOUNTING +struct irqtime { + u64 total; + u64 tick_delta; + u64 irq_start_time; + struct u64_stats_sync sync; +}; + +DECLARE_PER_CPU(struct irqtime, cpu_irqtime); + +/* + * Returns the irqtime minus the softirq time computed by ksoftirqd. + * Otherwise ksoftirqd's sum_exec_runtime is substracted its own runtime + * and never move forward. + */ +static inline u64 irq_time_read(int cpu) +{ + struct irqtime *irqtime = &per_cpu(cpu_irqtime, cpu); + unsigned int seq; + u64 total; + + do { + seq = __u64_stats_fetch_begin(&irqtime->sync); + total = irqtime->total; + } while (__u64_stats_fetch_retry(&irqtime->sync, seq)); + + return total; +} +#endif /* CONFIG_IRQ_TIME_ACCOUNTING */ + +#ifdef CONFIG_CPU_FREQ +DECLARE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data); + +/** + * cpufreq_update_util - Take a note about CPU utilization changes. + * @rq: Runqueue to carry out the update for. + * @flags: Update reason flags. + * + * This function is called by the scheduler on the CPU whose utilization is + * being updated. + * + * It can only be called from RCU-sched read-side critical sections. + * + * The way cpufreq is currently arranged requires it to evaluate the CPU + * performance state (frequency/voltage) on a regular basis to prevent it from + * being stuck in a completely inadequate performance level for too long. + * That is not guaranteed to happen if the updates are only triggered from CFS + * and DL, though, because they may not be coming in if only RT tasks are + * active all the time (or there are RT tasks only). + * + * As a workaround for that issue, this function is called periodically by the + * RT sched class to trigger extra cpufreq updates to prevent it from stalling, + * but that really is a band-aid. Going forward it should be replaced with + * solutions targeted more specifically at RT tasks. + */ +static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) +{ + struct update_util_data *data; + + data = rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data)); + if (data) + data->func(data, rq_clock(rq), flags); +} +#else +static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {} +#endif /* CONFIG_CPU_FREQ */ + +#ifdef CONFIG_NO_HZ_FULL +extern int __init sched_tick_offload_init(void); +#else +static inline int sched_tick_offload_init(void) { return 0; } +#endif + +#ifdef arch_scale_freq_capacity +#ifndef arch_scale_freq_invariant +#define arch_scale_freq_invariant() (true) +#endif +#else /* arch_scale_freq_capacity */ +#define arch_scale_freq_invariant() (false) +#endif + +extern void schedule_idle(void); + +/* + * !! For sched_setattr_nocheck() (kernel) only !! + * + * This is actually gross. :( + * + * It is used to make schedutil kworker(s) higher priority than SCHED_DEADLINE + * tasks, but still be able to sleep. We need this on platforms that cannot + * atomically change clock frequency. Remove once fast switching will be + * available on such platforms. + * + * SUGOV stands for SchedUtil GOVernor. + */ +#define SCHED_FLAG_SUGOV 0x10000000 + +#ifdef CONFIG_MEMBARRIER +/* + * The scheduler provides memory barriers required by membarrier between: + * - prior user-space memory accesses and store to rq->membarrier_state, + * - store to rq->membarrier_state and following user-space memory accesses. + * In the same way it provides those guarantees around store to rq->curr. + */ +static inline void membarrier_switch_mm(struct rq *rq, + struct mm_struct *prev_mm, + struct mm_struct *next_mm) +{ + int membarrier_state; + + if (prev_mm == next_mm) + return; + + membarrier_state = atomic_read(&next_mm->membarrier_state); + if (READ_ONCE(rq->membarrier_state) == membarrier_state) + return; + + WRITE_ONCE(rq->membarrier_state, membarrier_state); +} +#else +static inline void membarrier_switch_mm(struct rq *rq, + struct mm_struct *prev_mm, + struct mm_struct *next_mm) +{ +} +#endif + +static inline int task_running_nice(struct task_struct *p) +{ + return (p->prio + p->boost_prio > DEFAULT_PRIO + MAX_PRIORITY_ADJ); +} + +#ifdef CONFIG_NUMA +extern int sched_numa_find_closest(const struct cpumask *cpus, int cpu); +#else +static inline int sched_numa_find_closest(const struct cpumask *cpus, int cpu) +{ + return nr_cpu_ids; +} +#endif +#endif /* BMQ_SCHED_H */ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 44123b4d14e8..8dacda4b0362 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -810,7 +810,7 @@ static inline unsigned int uclamp_bucket_base_value(unsigned int clamp_value) return UCLAMP_BUCKET_DELTA * uclamp_bucket_id(clamp_value); } -static inline enum uclamp_id uclamp_none(enum uclamp_id clamp_id) +static inline unsigned int uclamp_none(enum uclamp_id clamp_id) { if (clamp_id == UCLAMP_MIN) return 0; @@ -853,7 +853,7 @@ static inline void uclamp_idle_reset(struct rq *rq, enum uclamp_id clamp_id, } static inline -enum uclamp_id uclamp_rq_max_value(struct rq *rq, enum uclamp_id clamp_id, +unsigned int uclamp_rq_max_value(struct rq *rq, enum uclamp_id clamp_id, unsigned int clamp_value) { struct uclamp_bucket *bucket = rq->uclamp[clamp_id].bucket; @@ -918,7 +918,7 @@ uclamp_eff_get(struct task_struct *p, enum uclamp_id clamp_id) return uc_req; } -enum uclamp_id uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id) +unsigned int uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id) { struct uclamp_se uc_eff; diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c index b5dcd1d83c7f..7c2fe50fd76d 100644 --- a/kernel/sched/cpufreq.c +++ b/kernel/sched/cpufreq.c @@ -5,6 +5,8 @@ * Copyright (C) 2016, Intel Corporation * Author: Rafael J. Wysocki */ +#include + #include "sched.h" DEFINE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data); @@ -57,3 +59,19 @@ void cpufreq_remove_update_util_hook(int cpu) rcu_assign_pointer(per_cpu(cpufreq_update_util_data, cpu), NULL); } EXPORT_SYMBOL_GPL(cpufreq_remove_update_util_hook); + +/** + * cpufreq_this_cpu_can_update - Check if cpufreq policy can be updated. + * @policy: cpufreq policy to check. + * + * Return 'true' if: + * - the local and remote CPUs share @policy, + * - dvfs_possible_from_any_cpu is set in @policy and the local CPU is not going + * offline (in which case it is not expected to run cpufreq updates any more). + */ +bool cpufreq_this_cpu_can_update(struct cpufreq_policy *policy) +{ + return cpumask_test_cpu(smp_processor_id(), policy->cpus) || + (policy->dvfs_possible_from_any_cpu && + rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data))); +} diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 86800b4d5453..05b05679ca5b 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -82,12 +82,10 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time) * by the hardware, as calculating the frequency is pointless if * we cannot in fact act on it. * - * For the slow switching platforms, the kthread is always scheduled on - * the right set of CPUs and any CPU can find the next frequency and - * schedule the kthread. + * This is needed on the slow switching platforms too to prevent CPUs + * going offline from leaving stale IRQ work items behind. */ - if (sg_policy->policy->fast_switch_enabled && - !cpufreq_this_cpu_can_update(sg_policy->policy)) + if (!cpufreq_this_cpu_can_update(sg_policy->policy)) return false; if (unlikely(sg_policy->limits_changed)) { @@ -185,6 +183,7 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy, return cpufreq_driver_resolve_freq(policy, freq); } +#ifndef CONFIG_SCHED_BMQ /* * This function computes an effective utilization for the given CPU, to be * used for frequency selection given the linear relation: f = u * f_max. @@ -302,6 +301,13 @@ static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu) return schedutil_cpu_util(sg_cpu->cpu, util, max, FREQUENCY_UTIL, NULL); } +#else /* CONFIG_SCHED_BMQ */ +static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu) +{ + sg_cpu->max = arch_scale_cpu_capacity(sg_cpu->cpu); + return sg_cpu->max; +} +#endif /** * sugov_iowait_reset() - Reset the IO boost status of a CPU. @@ -445,7 +451,9 @@ static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; } */ static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu, struct sugov_policy *sg_policy) { +#ifndef CONFIG_SCHED_BMQ if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_dl) +#endif sg_policy->limits_changed = true; } @@ -688,6 +696,7 @@ static int sugov_kthread_create(struct sugov_policy *sg_policy) } ret = sched_setattr_nocheck(thread, &attr); + if (ret) { kthread_stop(thread); pr_warn("%s: failed to set SCHED_DEADLINE\n", __func__); @@ -918,6 +927,7 @@ static int __init sugov_register(void) fs_initcall(sugov_register); #ifdef CONFIG_ENERGY_MODEL +#ifndef CONFIG_SCHED_BMQ extern bool sched_energy_update; extern struct mutex sched_energy_mutex; @@ -948,4 +958,10 @@ void sched_cpufreq_governor_change(struct cpufreq_policy *policy, } } +#else /* CONFIG_SCHED_BMQ */ +void sched_cpufreq_governor_change(struct cpufreq_policy *policy, + struct cpufreq_governor *old_gov) +{ +} +#endif #endif diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 46ed4e1383e2..51460a446da0 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -122,7 +122,7 @@ void account_user_time(struct task_struct *p, u64 cputime) p->utime += cputime; account_group_user_time(p, cputime); - index = (task_nice(p) > 0) ? CPUTIME_NICE : CPUTIME_USER; + index = task_running_nice(p) ? CPUTIME_NICE : CPUTIME_USER; /* Add user time to cpustat. */ task_group_account_field(p, index, cputime); @@ -146,7 +146,7 @@ void account_guest_time(struct task_struct *p, u64 cputime) p->gtime += cputime; /* Add guest time to cpustat. */ - if (task_nice(p) > 0) { + if (task_running_nice(p)) { cpustat[CPUTIME_NICE] += cputime; cpustat[CPUTIME_GUEST_NICE] += cputime; } else { @@ -269,7 +269,7 @@ static inline u64 account_other_time(u64 max) #ifdef CONFIG_64BIT static inline u64 read_sum_exec_runtime(struct task_struct *t) { - return t->se.sum_exec_runtime; + return tsk_seruntime(t); } #else static u64 read_sum_exec_runtime(struct task_struct *t) @@ -279,7 +279,7 @@ static u64 read_sum_exec_runtime(struct task_struct *t) struct rq *rq; rq = task_rq_lock(t, &rf); - ns = t->se.sum_exec_runtime; + ns = tsk_seruntime(t); task_rq_unlock(rq, t, &rf); return ns; @@ -663,7 +663,7 @@ void cputime_adjust(struct task_cputime *curr, struct prev_cputime *prev, void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st) { struct task_cputime cputime = { - .sum_exec_runtime = p->se.sum_exec_runtime, + .sum_exec_runtime = tsk_seruntime(p), }; task_cputime(p, &cputime.utime, &cputime.stime); diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index f65ef1e2f204..77bf219444fa 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -355,6 +355,7 @@ void cpu_startup_entry(enum cpuhp_state state) do_idle(); } +#ifndef CONFIG_SCHED_BMQ /* * idle-task scheduling class. */ @@ -479,3 +480,4 @@ const struct sched_class idle_sched_class = { .switched_to = switched_to_idle, .update_curr = update_curr_idle, }; +#endif diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c index a96db50d40e0..22c20e28b613 100644 --- a/kernel/sched/pelt.c +++ b/kernel/sched/pelt.c @@ -236,6 +236,7 @@ ___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runna WRITE_ONCE(sa->util_avg, sa->util_sum / divider); } +#ifndef CONFIG_SCHED_BMQ /* * sched_entity: * @@ -352,6 +353,7 @@ int update_dl_rq_load_avg(u64 now, struct rq *rq, int running) return 0; } +#endif #ifdef CONFIG_HAVE_SCHED_AVG_IRQ /* diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h index afff644da065..4da52afaeff8 100644 --- a/kernel/sched/pelt.h +++ b/kernel/sched/pelt.h @@ -1,11 +1,13 @@ #ifdef CONFIG_SMP #include "sched-pelt.h" +#ifndef CONFIG_SCHED_BMQ int __update_load_avg_blocked_se(u64 now, struct sched_entity *se); int __update_load_avg_se(u64 now, struct cfs_rq *cfs_rq, struct sched_entity *se); int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq); int update_rt_rq_load_avg(u64 now, struct rq *rq, int running); int update_dl_rq_load_avg(u64 now, struct rq *rq, int running); +#endif #ifdef CONFIG_HAVE_SCHED_AVG_IRQ int update_irq_load_avg(struct rq *rq, u64 running); @@ -17,6 +19,7 @@ update_irq_load_avg(struct rq *rq, u64 running) } #endif +#ifndef CONFIG_SCHED_BMQ /* * When a task is dequeued, its estimated utilization should not be update if * its util_avg has not been updated at least once. @@ -137,9 +140,11 @@ static inline u64 cfs_rq_clock_pelt(struct cfs_rq *cfs_rq) return rq_clock_pelt(rq_of(cfs_rq)); } #endif +#endif /* CONFIG_SCHED_BMQ */ #else +#ifndef CONFIG_SCHED_BMQ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) { @@ -157,6 +162,7 @@ update_dl_rq_load_avg(u64 now, struct rq *rq, int running) { return 0; } +#endif static inline int update_irq_load_avg(struct rq *rq, u64 running) diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 517e3719027e..ce8f6748678a 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -185,7 +185,8 @@ static void group_init(struct psi_group *group) for_each_possible_cpu(cpu) seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq); - group->avg_next_update = sched_clock() + psi_period; + group->avg_last_update = sched_clock(); + group->avg_next_update = group->avg_last_update + psi_period; INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work); mutex_init(&group->avgs_lock); /* Init trigger-related members */ @@ -481,7 +482,7 @@ static u64 window_update(struct psi_window *win, u64 now, u64 value) u32 remaining; remaining = win->size - elapsed; - growth += div_u64(win->prev_growth * remaining, win->size); + growth += div64_u64(win->prev_growth * remaining, win->size); } return growth; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index c8870c5bd7df..d77a48d9e3b7 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -2,6 +2,10 @@ /* * Scheduler internal types and methods: */ +#ifdef CONFIG_SCHED_BMQ +#include "bmq_sched.h" +#else + #include #include @@ -2309,7 +2313,7 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {} #endif /* CONFIG_CPU_FREQ */ #ifdef CONFIG_UCLAMP_TASK -enum uclamp_id uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id); +unsigned int uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id); static __always_inline unsigned int uclamp_util_with(struct rq *rq, unsigned int util, @@ -2496,3 +2500,9 @@ static inline void membarrier_switch_mm(struct rq *rq, { } #endif + +static inline int task_running_nice(struct task_struct *p) +{ + return (task_nice(p) > 0); +} +#endif /* !CONFIG_SCHED_BMQ */ diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c index 750fb3c67eed..0cc040a28d3f 100644 --- a/kernel/sched/stats.c +++ b/kernel/sched/stats.c @@ -22,8 +22,10 @@ static int show_schedstat(struct seq_file *seq, void *v) } else { struct rq *rq; #ifdef CONFIG_SMP +#ifndef CONFIG_SCHED_BMQ struct sched_domain *sd; int dcount = 0; +#endif #endif cpu = (unsigned long)(v - 2); rq = cpu_rq(cpu); @@ -40,6 +42,7 @@ static int show_schedstat(struct seq_file *seq, void *v) seq_printf(seq, "\n"); #ifdef CONFIG_SMP +#ifndef CONFIG_SCHED_BMQ /* domain-specific stats */ rcu_read_lock(); for_each_domain(cpu, sd) { @@ -68,6 +71,7 @@ static int show_schedstat(struct seq_file *seq, void *v) sd->ttwu_move_balance); } rcu_read_unlock(); +#endif #endif } return 0; diff --git a/kernel/seccomp.c b/kernel/seccomp.c index dba52a7db5e8..614a557a0814 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -1015,6 +1015,13 @@ static long seccomp_notify_recv(struct seccomp_filter *filter, struct seccomp_notif unotif; ssize_t ret; + /* Verify that we're not given garbage to keep struct extensible. */ + ret = check_zeroed_user(buf, sizeof(unotif)); + if (ret < 0) + return ret; + if (!ret) + return -EINVAL; + memset(&unotif, 0, sizeof(unotif)); ret = down_interruptible(&filter->notif->request); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index b6f2f35d0bcf..6d56b110fa2e 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -110,6 +110,9 @@ extern int core_uses_pid; extern char core_pattern[]; extern unsigned int core_pipe_limit; #endif +#ifdef CONFIG_USER_NS +extern int unprivileged_userns_clone; +#endif extern int pid_max; extern int pid_max_min, pid_max_max; extern int percpu_pagelist_fraction; @@ -132,6 +135,10 @@ static unsigned long one_ul = 1; static unsigned long long_max = LONG_MAX; static int one_hundred = 100; static int one_thousand = 1000; +#ifdef CONFIG_SCHED_BMQ +static int __maybe_unused zero = 0; +extern int sched_yield_type; +#endif #ifdef CONFIG_PRINTK static int ten_thousand = 10000; #endif @@ -300,7 +307,7 @@ static struct ctl_table sysctl_base_table[] = { { } }; -#ifdef CONFIG_SCHED_DEBUG +#if defined(CONFIG_SCHED_DEBUG) && !defined(CONFIG_SCHED_BMQ) static int min_sched_granularity_ns = 100000; /* 100 usecs */ static int max_sched_granularity_ns = NSEC_PER_SEC; /* 1 second */ static int min_wakeup_granularity_ns; /* 0 usecs */ @@ -317,6 +324,7 @@ static int max_extfrag_threshold = 1000; #endif static struct ctl_table kern_table[] = { +#ifndef CONFIG_SCHED_BMQ { .procname = "sched_child_runs_first", .data = &sysctl_sched_child_runs_first, @@ -498,6 +506,7 @@ static struct ctl_table kern_table[] = { .extra2 = SYSCTL_ONE, }, #endif +#endif /* !CONFIG_SCHED_BMQ */ #ifdef CONFIG_PROVE_LOCKING { .procname = "prove_locking", @@ -546,6 +555,15 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_dointvec, }, #endif +#ifdef CONFIG_USER_NS + { + .procname = "unprivileged_userns_clone", + .data = &unprivileged_userns_clone, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif #ifdef CONFIG_PROC_SYSCTL { .procname = "tainted", @@ -1070,6 +1088,17 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_dointvec, }, #endif +#ifdef CONFIG_SCHED_BMQ + { + .procname = "yield_type", + .data = &sched_yield_type, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &two, + }, +#endif #if defined(CONFIG_S390) && defined(CONFIG_SMP) { .procname = "spin_retry", @@ -1466,7 +1495,7 @@ static struct ctl_table vm_table[] = { .procname = "drop_caches", .data = &sysctl_drop_caches, .maxlen = sizeof(int), - .mode = 0644, + .mode = 0200, .proc_handler = drop_caches_sysctl_handler, .extra1 = SYSCTL_ONE, .extra2 = &four, diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 13a0f2e6ebc2..e2ac0e37c4ae 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -554,25 +554,33 @@ static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info) static struct taskstats *taskstats_tgid_alloc(struct task_struct *tsk) { struct signal_struct *sig = tsk->signal; - struct taskstats *stats; + struct taskstats *stats_new, *stats; - if (sig->stats || thread_group_empty(tsk)) - goto ret; + /* Pairs with smp_store_release() below. */ + stats = smp_load_acquire(&sig->stats); + if (stats || thread_group_empty(tsk)) + return stats; /* No problem if kmem_cache_zalloc() fails */ - stats = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL); + stats_new = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL); spin_lock_irq(&tsk->sighand->siglock); - if (!sig->stats) { - sig->stats = stats; - stats = NULL; + stats = sig->stats; + if (!stats) { + /* + * Pairs with smp_store_release() above and order the + * kmem_cache_zalloc(). + */ + smp_store_release(&sig->stats, stats_new); + stats = stats_new; + stats_new = NULL; } spin_unlock_irq(&tsk->sighand->siglock); - if (stats) - kmem_cache_free(taskstats_cache, stats); -ret: - return sig->stats; + if (stats_new) + kmem_cache_free(taskstats_cache, stats_new); + + return stats; } /* Send pid data out on exit */ diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 65605530ee34..7f31932216a1 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -966,7 +966,8 @@ static int enqueue_hrtimer(struct hrtimer *timer, base->cpu_base->active_bases |= 1 << base->index; - timer->state = HRTIMER_STATE_ENQUEUED; + /* Pairs with the lockless read in hrtimer_is_queued() */ + WRITE_ONCE(timer->state, HRTIMER_STATE_ENQUEUED); return timerqueue_add(&base->active, &timer->node); } @@ -988,7 +989,8 @@ static void __remove_hrtimer(struct hrtimer *timer, struct hrtimer_cpu_base *cpu_base = base->cpu_base; u8 state = timer->state; - timer->state = newstate; + /* Pairs with the lockless read in hrtimer_is_queued() */ + WRITE_ONCE(timer->state, newstate); if (!(state & HRTIMER_STATE_ENQUEUED)) return; @@ -1013,8 +1015,9 @@ static void __remove_hrtimer(struct hrtimer *timer, static inline int remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool restart) { - if (hrtimer_is_queued(timer)) { - u8 state = timer->state; + u8 state = timer->state; + + if (state & HRTIMER_STATE_ENQUEUED) { int reprogram; /* diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c index ec960bb939fd..200fb2d3be99 100644 --- a/kernel/time/posix-clock.c +++ b/kernel/time/posix-clock.c @@ -14,8 +14,6 @@ #include "posix-timers.h" -static void delete_clock(struct kref *kref); - /* * Returns NULL if the posix_clock instance attached to 'fp' is old and stale. */ @@ -125,7 +123,7 @@ static int posix_clock_open(struct inode *inode, struct file *fp) err = 0; if (!err) { - kref_get(&clk->kref); + get_device(clk->dev); fp->private_data = clk; } out: @@ -141,7 +139,7 @@ static int posix_clock_release(struct inode *inode, struct file *fp) if (clk->ops.release) err = clk->ops.release(clk); - kref_put(&clk->kref, delete_clock); + put_device(clk->dev); fp->private_data = NULL; @@ -161,38 +159,35 @@ static const struct file_operations posix_clock_file_operations = { #endif }; -int posix_clock_register(struct posix_clock *clk, dev_t devid) +int posix_clock_register(struct posix_clock *clk, struct device *dev) { int err; - kref_init(&clk->kref); init_rwsem(&clk->rwsem); cdev_init(&clk->cdev, &posix_clock_file_operations); + err = cdev_device_add(&clk->cdev, dev); + if (err) { + pr_err("%s unable to add device %d:%d\n", + dev_name(dev), MAJOR(dev->devt), MINOR(dev->devt)); + return err; + } clk->cdev.owner = clk->ops.owner; - err = cdev_add(&clk->cdev, devid, 1); + clk->dev = dev; - return err; + return 0; } EXPORT_SYMBOL_GPL(posix_clock_register); -static void delete_clock(struct kref *kref) -{ - struct posix_clock *clk = container_of(kref, struct posix_clock, kref); - - if (clk->release) - clk->release(clk); -} - void posix_clock_unregister(struct posix_clock *clk) { - cdev_del(&clk->cdev); + cdev_device_del(&clk->cdev, clk->dev); down_write(&clk->rwsem); clk->zombie = true; up_write(&clk->rwsem); - kref_put(&clk->kref, delete_clock); + put_device(clk->dev); } EXPORT_SYMBOL_GPL(posix_clock_unregister); diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 42d512fcfda2..70b97fe0ff44 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -226,7 +226,7 @@ static void task_sample_cputime(struct task_struct *p, u64 *samples) u64 stime, utime; task_cputime(p, &utime, &stime); - store_samples(samples, stime, utime, p->se.sum_exec_runtime); + store_samples(samples, stime, utime, tsk_seruntime(p)); } static void proc_sample_cputime_atomic(struct task_cputime_atomic *at, @@ -796,6 +796,7 @@ static void collect_posix_cputimers(struct posix_cputimers *pct, u64 *samples, } } +#ifndef CONFIG_SCHED_BMQ static inline void check_dl_overrun(struct task_struct *tsk) { if (tsk->dl.dl_overrun) { @@ -803,6 +804,7 @@ static inline void check_dl_overrun(struct task_struct *tsk) __group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk); } } +#endif static bool check_rlimit(u64 time, u64 limit, int signo, bool rt, bool hard) { @@ -830,8 +832,10 @@ static void check_thread_timers(struct task_struct *tsk, u64 samples[CPUCLOCK_MAX]; unsigned long soft; +#ifndef CONFIG_SCHED_BMQ if (dl_task(tsk)) check_dl_overrun(tsk); +#endif if (expiry_cache_is_inactive(pct)) return; @@ -845,7 +849,7 @@ static void check_thread_timers(struct task_struct *tsk, soft = task_rlimit(tsk, RLIMIT_RTTIME); if (soft != RLIM_INFINITY) { /* Task RT timeout is accounted in jiffies. RTTIME is usec */ - unsigned long rttime = tsk->rt.timeout * (USEC_PER_SEC / HZ); + unsigned long rttime = tsk_rttimeout(tsk) * (USEC_PER_SEC / HZ); unsigned long hard = task_rlimit_max(tsk, RLIMIT_RTTIME); /* At the hard limit, send SIGKILL. No further action. */ @@ -1099,8 +1103,10 @@ static inline bool fastpath_timer_check(struct task_struct *tsk) return true; } +#ifndef CONFIG_SCHED_BMQ if (dl_task(tsk) && tsk->dl.dl_overrun) return true; +#endif return false; } diff --git a/kernel/time/time.c b/kernel/time/time.c index 5c54ca632d08..83f403e7a15c 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -881,7 +881,8 @@ int get_timespec64(struct timespec64 *ts, ts->tv_sec = kts.tv_sec; /* Zero out the padding for 32 bit systems or in compat mode */ - if (IS_ENABLED(CONFIG_64BIT_TIME) && in_compat_syscall()) + if (IS_ENABLED(CONFIG_64BIT_TIME) && (!IS_ENABLED(CONFIG_64BIT) || + in_compat_syscall())) kts.tv_nsec &= 0xFFFFFFFFUL; ts->tv_nsec = kts.tv_nsec; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 44bd08f2443b..89bdac61233d 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -163,7 +163,7 @@ static const struct bpf_func_proto bpf_probe_read_proto = { .arg3_type = ARG_ANYTHING, }; -BPF_CALL_3(bpf_probe_write_user, void *, unsafe_ptr, const void *, src, +BPF_CALL_3(bpf_probe_write_user, void __user *, unsafe_ptr, const void *, src, u32, size) { /* @@ -186,10 +186,8 @@ BPF_CALL_3(bpf_probe_write_user, void *, unsafe_ptr, const void *, src, return -EPERM; if (unlikely(!nmi_uaccess_okay())) return -EPERM; - if (!access_ok(unsafe_ptr, size)) - return -EPERM; - return probe_kernel_write(unsafe_ptr, src, size); + return probe_user_write(unsafe_ptr, src, size); } static const struct bpf_func_proto bpf_probe_write_user_proto = { diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index f296d89be757..0708a41cfe2d 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -524,8 +524,7 @@ static int function_stat_show(struct seq_file *m, void *v) } #ifdef CONFIG_FUNCTION_GRAPH_TRACER - avg = rec->time; - do_div(avg, rec->counter); + avg = div64_ul(rec->time, rec->counter); if (tracing_thresh && (avg < tracing_thresh)) goto out; #endif @@ -551,7 +550,8 @@ static int function_stat_show(struct seq_file *m, void *v) * Divide only 1000 for ns^2 -> us^2 conversion. * trace_print_graph_duration will divide 1000 again. */ - do_div(stddev, rec->counter * (rec->counter - 1) * 1000); + stddev = div64_ul(stddev, + rec->counter * (rec->counter - 1) * 1000); } trace_seq_init(&s); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 66358d66c933..4bf050fcfe3b 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include /* for self test */ @@ -5068,6 +5069,11 @@ static __init int test_ringbuffer(void) int cpu; int ret = 0; + if (security_locked_down(LOCKDOWN_TRACEFS)) { + pr_warning("Lockdown is enabled, skipping ring buffer tests\n"); + return 0; + } + pr_info("Running ring buffer tests...\n"); buffer = ring_buffer_alloc(RB_TEST_BUFFER_SIZE, RB_FL_OVERWRITE); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 6a0ee9178365..bcb72f102613 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1804,6 +1804,12 @@ int __init register_tracer(struct tracer *type) return -1; } + if (security_locked_down(LOCKDOWN_TRACEFS)) { + pr_warning("Can not register tracer %s due to lockdown\n", + type->name); + return -EPERM; + } + mutex_lock(&trace_types_lock); tracing_selftest_running = true; @@ -4590,6 +4596,10 @@ int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set) int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled) { + if ((mask == TRACE_ITER_RECORD_TGID) || + (mask == TRACE_ITER_RECORD_CMD)) + lockdep_assert_held(&event_mutex); + /* do nothing if flag is already set */ if (!!(tr->trace_flags & mask) == !!enabled) return 0; @@ -4609,7 +4619,7 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled) if (mask == TRACE_ITER_RECORD_TGID) { if (!tgid_map) - tgid_map = kcalloc(PID_MAX_DEFAULT + 1, + tgid_map = kvcalloc(PID_MAX_DEFAULT + 1, sizeof(*tgid_map), GFP_KERNEL); if (!tgid_map) { @@ -4657,6 +4667,7 @@ static int trace_set_options(struct trace_array *tr, char *option) cmp += len; + mutex_lock(&event_mutex); mutex_lock(&trace_types_lock); ret = match_string(trace_options, -1, cmp); @@ -4667,6 +4678,7 @@ static int trace_set_options(struct trace_array *tr, char *option) ret = set_tracer_flag(tr, 1 << ret, !neg); mutex_unlock(&trace_types_lock); + mutex_unlock(&event_mutex); /* * If the first trailing whitespace is replaced with '\0' by strstrip, @@ -7972,9 +7984,11 @@ trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt, if (val != 0 && val != 1) return -EINVAL; + mutex_lock(&event_mutex); mutex_lock(&trace_types_lock); ret = set_tracer_flag(tr, 1 << index, val); mutex_unlock(&trace_types_lock); + mutex_unlock(&event_mutex); if (ret < 0) return ret; @@ -8639,6 +8653,11 @@ struct dentry *tracing_init_dentry(void) { struct trace_array *tr = &global_trace; + if (security_locked_down(LOCKDOWN_TRACEFS)) { + pr_warning("Tracing disabled due to lockdown\n"); + return ERR_PTR(-EPERM); + } + /* The top level trace array uses NULL as parent */ if (tr->dir) return NULL; @@ -9081,6 +9100,12 @@ __init static int tracer_alloc_buffers(void) int ring_buf_size; int ret = -ENOMEM; + + if (security_locked_down(LOCKDOWN_TRACEFS)) { + pr_warning("Tracing disabled due to lockdown\n"); + return -EPERM; + } + /* * Make sure we don't accidently add more trace options * than we have bits for. diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index fba87d10f0c1..995061bb2dec 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -320,7 +320,8 @@ void trace_event_enable_cmd_record(bool enable) struct trace_event_file *file; struct trace_array *tr; - mutex_lock(&event_mutex); + lockdep_assert_held(&event_mutex); + do_for_each_event_file(tr, file) { if (!(file->flags & EVENT_FILE_FL_ENABLED)) @@ -334,7 +335,6 @@ void trace_event_enable_cmd_record(bool enable) clear_bit(EVENT_FILE_FL_RECORDED_CMD_BIT, &file->flags); } } while_for_each_event_file(); - mutex_unlock(&event_mutex); } void trace_event_enable_tgid_record(bool enable) @@ -342,7 +342,8 @@ void trace_event_enable_tgid_record(bool enable) struct trace_event_file *file; struct trace_array *tr; - mutex_lock(&event_mutex); + lockdep_assert_held(&event_mutex); + do_for_each_event_file(tr, file) { if (!(file->flags & EVENT_FILE_FL_ENABLED)) continue; @@ -356,7 +357,6 @@ void trace_event_enable_tgid_record(bool enable) &file->flags); } } while_for_each_event_file(); - mutex_unlock(&event_mutex); } static int __ftrace_event_enable_disable(struct trace_event_file *file, diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index c9a74f82b14a..bf44f6bbd0c3 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1662,7 +1662,7 @@ static int process_system_preds(struct trace_subsystem_dir *dir, parse_error(pe, FILT_ERR_BAD_SUBSYS_FILTER, 0); return -EINVAL; fail_mem: - kfree(filter); + __free_filter(filter); /* If any call succeeded, we still need to sync */ if (!fail) tracepoint_synchronize_unregister(); diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 7482a1466ebf..c2783915600c 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -911,7 +911,26 @@ static notrace void trace_event_raw_event_synth(void *__data, strscpy(str_field, str_val, STR_VAR_LEN_MAX); n_u64 += STR_VAR_LEN_MAX / sizeof(u64); } else { - entry->fields[n_u64] = var_ref_vals[var_ref_idx + i]; + struct synth_field *field = event->fields[i]; + u64 val = var_ref_vals[var_ref_idx + i]; + + switch (field->size) { + case 1: + *(u8 *)&entry->fields[n_u64] = (u8)val; + break; + + case 2: + *(u16 *)&entry->fields[n_u64] = (u16)val; + break; + + case 4: + *(u32 *)&entry->fields[n_u64] = (u32)val; + break; + + default: + entry->fields[n_u64] = val; + break; + } n_u64++; } } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 1552a95c743b..7f890262c8a3 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -435,11 +435,10 @@ static int disable_trace_kprobe(struct trace_event_call *call, #if defined(CONFIG_KPROBES_ON_FTRACE) && \ !defined(CONFIG_KPROBE_EVENTS_ON_NOTRACE) -static bool within_notrace_func(struct trace_kprobe *tk) +static bool __within_notrace_func(unsigned long addr) { - unsigned long offset, size, addr; + unsigned long offset, size; - addr = trace_kprobe_address(tk); if (!addr || !kallsyms_lookup_size_offset(addr, &size, &offset)) return false; @@ -452,6 +451,28 @@ static bool within_notrace_func(struct trace_kprobe *tk) */ return !ftrace_location_range(addr, addr + size - 1); } + +static bool within_notrace_func(struct trace_kprobe *tk) +{ + unsigned long addr = addr = trace_kprobe_address(tk); + char symname[KSYM_NAME_LEN], *p; + + if (!__within_notrace_func(addr)) + return false; + + /* Check if the address is on a suffixed-symbol */ + if (!lookup_symbol_name(addr, symname)) { + p = strchr(symname, '.'); + if (!p) + return true; + *p = '\0'; + addr = (unsigned long)kprobe_lookup_name(symname, 0); + if (addr) + return __within_notrace_func(addr); + } + + return true; +} #else #define within_notrace_func(tk) (false) #endif diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 5e43b9664eca..617e297f46dc 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -630,7 +630,7 @@ static void start_wakeup_tracer(struct trace_array *tr) if (ret) { pr_info("wakeup trace: Couldn't activate tracepoint" " probe to kernel_sched_migrate_task\n"); - return; + goto fail_deprobe_sched_switch; } wakeup_reset(tr); @@ -648,6 +648,8 @@ static void start_wakeup_tracer(struct trace_array *tr) printk(KERN_ERR "failed to start wakeup tracer\n"); return; +fail_deprobe_sched_switch: + unregister_trace_sched_switch(probe_wakeup_sched_switch, NULL); fail_deprobe_wake_new: unregister_trace_sched_wakeup_new(probe_wakeup, NULL); fail_deprobe: diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 69ee8ef12cee..208788fcbb0e 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -1048,10 +1048,15 @@ static int trace_wakeup_test_thread(void *data) { /* Make this a -deadline thread */ static const struct sched_attr attr = { +#ifdef CONFIG_SCHED_BMQ + /* No deadline on BMQ, use RR */ + .sched_policy = SCHED_RR, +#else .sched_policy = SCHED_DEADLINE, .sched_runtime = 100000ULL, .sched_deadline = 10000000ULL, .sched_period = 10000000ULL +#endif }; struct wakeup_test_data *x = data; diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 4df9a209f7ca..c557f42a9397 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -283,6 +283,11 @@ static void check_stack(unsigned long ip, unsigned long *stack) local_irq_restore(flags); } +/* Some archs may not define MCOUNT_INSN_SIZE */ +#ifndef MCOUNT_INSN_SIZE +# define MCOUNT_INSN_SIZE 0 +#endif + static void stack_trace_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct pt_regs *pt_regs) diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c index 9a1c22310323..9e31bfc818ff 100644 --- a/kernel/trace/tracing_map.c +++ b/kernel/trace/tracing_map.c @@ -148,8 +148,8 @@ static int tracing_map_cmp_atomic64(void *val_a, void *val_b) #define DEFINE_TRACING_MAP_CMP_FN(type) \ static int tracing_map_cmp_##type(void *val_a, void *val_b) \ { \ - type a = *(type *)val_a; \ - type b = *(type *)val_b; \ + type a = (type)(*(u64 *)val_a); \ + type b = (type)(*(u64 *)val_b); \ \ return (a > b) ? 1 : ((a < b) ? -1 : 0); \ } diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 8eadadc478f9..c36ecd19562c 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -21,6 +21,13 @@ #include #include +/* sysctl */ +#ifdef CONFIG_USER_NS_UNPRIVILEGED +int unprivileged_userns_clone = 1; +#else +int unprivileged_userns_clone; +#endif + static struct kmem_cache *user_ns_cachep __read_mostly; static DEFINE_MUTEX(userns_state_mutex); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index bc2e09a8ea61..649687622654 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2532,8 +2532,14 @@ static int rescuer_thread(void *__rescuer) */ if (need_to_create_worker(pool)) { spin_lock(&wq_mayday_lock); - get_pwq(pwq); - list_move_tail(&pwq->mayday_node, &wq->maydays); + /* + * Queue iff we aren't racing destruction + * and somebody else hasn't queued it already. + */ + if (wq->rescuer && list_empty(&pwq->mayday_node)) { + get_pwq(pwq); + list_add_tail(&pwq->mayday_node, &wq->maydays); + } spin_unlock(&wq_mayday_lock); } } @@ -4325,9 +4331,29 @@ void destroy_workqueue(struct workqueue_struct *wq) struct pool_workqueue *pwq; int node; + /* + * Remove it from sysfs first so that sanity check failure doesn't + * lead to sysfs name conflicts. + */ + workqueue_sysfs_unregister(wq); + /* drain it before proceeding with destruction */ drain_workqueue(wq); + /* kill rescuer, if sanity checks fail, leave it w/o rescuer */ + if (wq->rescuer) { + struct worker *rescuer = wq->rescuer; + + /* this prevents new queueing */ + spin_lock_irq(&wq_mayday_lock); + wq->rescuer = NULL; + spin_unlock_irq(&wq_mayday_lock); + + /* rescuer will empty maydays list before exiting */ + kthread_stop(rescuer->task); + kfree(rescuer); + } + /* sanity checks */ mutex_lock(&wq->mutex); for_each_pwq(pwq, wq) { @@ -4359,11 +4385,6 @@ void destroy_workqueue(struct workqueue_struct *wq) list_del_rcu(&wq->list); mutex_unlock(&wq_pool_mutex); - workqueue_sysfs_unregister(wq); - - if (wq->rescuer) - kthread_stop(wq->rescuer->task); - if (!(wq->flags & WQ_UNBOUND)) { wq_unregister_lockdep(wq); /* @@ -4638,7 +4659,8 @@ static void show_pwq(struct pool_workqueue *pwq) pr_info(" pwq %d:", pool->id); pr_cont_pool_info(pool); - pr_cont(" active=%d/%d%s\n", pwq->nr_active, pwq->max_active, + pr_cont(" active=%d/%d refcnt=%d%s\n", + pwq->nr_active, pwq->max_active, pwq->refcnt, !list_empty(&pwq->mayday_node) ? " MAYDAY" : ""); hash_for_each(pool->busy_hash, bkt, worker, hentry) { diff --git a/lib/devres.c b/lib/devres.c index 6a0e9bd6524a..17624d35e82d 100644 --- a/lib/devres.c +++ b/lib/devres.c @@ -9,6 +9,7 @@ enum devm_ioremap_type { DEVM_IOREMAP = 0, DEVM_IOREMAP_NC, + DEVM_IOREMAP_UC, DEVM_IOREMAP_WC, }; @@ -39,6 +40,9 @@ static void __iomem *__devm_ioremap(struct device *dev, resource_size_t offset, case DEVM_IOREMAP_NC: addr = ioremap_nocache(offset, size); break; + case DEVM_IOREMAP_UC: + addr = ioremap_uc(offset, size); + break; case DEVM_IOREMAP_WC: addr = ioremap_wc(offset, size); break; @@ -68,6 +72,21 @@ void __iomem *devm_ioremap(struct device *dev, resource_size_t offset, } EXPORT_SYMBOL(devm_ioremap); +/** + * devm_ioremap_uc - Managed ioremap_uc() + * @dev: Generic device to remap IO address for + * @offset: Resource address to map + * @size: Size of map + * + * Managed ioremap_uc(). Map is automatically unmapped on driver detach. + */ +void __iomem *devm_ioremap_uc(struct device *dev, resource_size_t offset, + resource_size_t size) +{ + return __devm_ioremap(dev, offset, size, DEVM_IOREMAP_UC); +} +EXPORT_SYMBOL_GPL(devm_ioremap_uc); + /** * devm_ioremap_nocache - Managed ioremap_nocache() * @dev: Generic device to remap IO address for diff --git a/lib/raid6/unroll.awk b/lib/raid6/unroll.awk index c6aa03631df8..0809805a7e23 100644 --- a/lib/raid6/unroll.awk +++ b/lib/raid6/unroll.awk @@ -13,7 +13,7 @@ BEGIN { for (i = 0; i < rep; ++i) { tmp = $0 gsub(/\$\$/, i, tmp) - gsub(/\$\#/, n, tmp) + gsub(/\$#/, n, tmp) gsub(/\$\*/, "$", tmp) print tmp } diff --git a/lib/sbitmap.c b/lib/sbitmap.c index 969e5400a615..ee3ce1494568 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -667,8 +667,8 @@ void sbitmap_add_wait_queue(struct sbitmap_queue *sbq, if (!sbq_wait->sbq) { sbq_wait->sbq = sbq; atomic_inc(&sbq->ws_active); + add_wait_queue(&ws->wait, &sbq_wait->wait); } - add_wait_queue(&ws->wait, &sbq_wait->wait); } EXPORT_SYMBOL_GPL(sbitmap_add_wait_queue); diff --git a/lib/ubsan.c b/lib/ubsan.c index e7d31735950d..f007a406f89c 100644 --- a/lib/ubsan.c +++ b/lib/ubsan.c @@ -140,25 +140,21 @@ static void val_to_string(char *str, size_t size, struct type_descriptor *type, } } -static DEFINE_SPINLOCK(report_lock); - -static void ubsan_prologue(struct source_location *location, - unsigned long *flags) +static void ubsan_prologue(struct source_location *location) { current->in_ubsan++; - spin_lock_irqsave(&report_lock, *flags); pr_err("========================================" "========================================\n"); print_source_location("UBSAN: Undefined behaviour in", location); } -static void ubsan_epilogue(unsigned long *flags) +static void ubsan_epilogue(void) { dump_stack(); pr_err("========================================" "========================================\n"); - spin_unlock_irqrestore(&report_lock, *flags); + current->in_ubsan--; } @@ -167,14 +163,13 @@ static void handle_overflow(struct overflow_data *data, void *lhs, { struct type_descriptor *type = data->type; - unsigned long flags; char lhs_val_str[VALUE_LENGTH]; char rhs_val_str[VALUE_LENGTH]; if (suppress_report(&data->location)) return; - ubsan_prologue(&data->location, &flags); + ubsan_prologue(&data->location); val_to_string(lhs_val_str, sizeof(lhs_val_str), type, lhs); val_to_string(rhs_val_str, sizeof(rhs_val_str), type, rhs); @@ -186,7 +181,7 @@ static void handle_overflow(struct overflow_data *data, void *lhs, rhs_val_str, type->type_name); - ubsan_epilogue(&flags); + ubsan_epilogue(); } void __ubsan_handle_add_overflow(struct overflow_data *data, @@ -214,20 +209,19 @@ EXPORT_SYMBOL(__ubsan_handle_mul_overflow); void __ubsan_handle_negate_overflow(struct overflow_data *data, void *old_val) { - unsigned long flags; char old_val_str[VALUE_LENGTH]; if (suppress_report(&data->location)) return; - ubsan_prologue(&data->location, &flags); + ubsan_prologue(&data->location); val_to_string(old_val_str, sizeof(old_val_str), data->type, old_val); pr_err("negation of %s cannot be represented in type %s:\n", old_val_str, data->type->type_name); - ubsan_epilogue(&flags); + ubsan_epilogue(); } EXPORT_SYMBOL(__ubsan_handle_negate_overflow); @@ -235,13 +229,12 @@ EXPORT_SYMBOL(__ubsan_handle_negate_overflow); void __ubsan_handle_divrem_overflow(struct overflow_data *data, void *lhs, void *rhs) { - unsigned long flags; char rhs_val_str[VALUE_LENGTH]; if (suppress_report(&data->location)) return; - ubsan_prologue(&data->location, &flags); + ubsan_prologue(&data->location); val_to_string(rhs_val_str, sizeof(rhs_val_str), data->type, rhs); @@ -251,58 +244,52 @@ void __ubsan_handle_divrem_overflow(struct overflow_data *data, else pr_err("division by zero\n"); - ubsan_epilogue(&flags); + ubsan_epilogue(); } EXPORT_SYMBOL(__ubsan_handle_divrem_overflow); static void handle_null_ptr_deref(struct type_mismatch_data_common *data) { - unsigned long flags; - if (suppress_report(data->location)) return; - ubsan_prologue(data->location, &flags); + ubsan_prologue(data->location); pr_err("%s null pointer of type %s\n", type_check_kinds[data->type_check_kind], data->type->type_name); - ubsan_epilogue(&flags); + ubsan_epilogue(); } static void handle_misaligned_access(struct type_mismatch_data_common *data, unsigned long ptr) { - unsigned long flags; - if (suppress_report(data->location)) return; - ubsan_prologue(data->location, &flags); + ubsan_prologue(data->location); pr_err("%s misaligned address %p for type %s\n", type_check_kinds[data->type_check_kind], (void *)ptr, data->type->type_name); pr_err("which requires %ld byte alignment\n", data->alignment); - ubsan_epilogue(&flags); + ubsan_epilogue(); } static void handle_object_size_mismatch(struct type_mismatch_data_common *data, unsigned long ptr) { - unsigned long flags; - if (suppress_report(data->location)) return; - ubsan_prologue(data->location, &flags); + ubsan_prologue(data->location); pr_err("%s address %p with insufficient space\n", type_check_kinds[data->type_check_kind], (void *) ptr); pr_err("for an object of type %s\n", data->type->type_name); - ubsan_epilogue(&flags); + ubsan_epilogue(); } static void ubsan_type_mismatch_common(struct type_mismatch_data_common *data, @@ -351,34 +338,33 @@ EXPORT_SYMBOL(__ubsan_handle_type_mismatch_v1); void __ubsan_handle_out_of_bounds(struct out_of_bounds_data *data, void *index) { - unsigned long flags; char index_str[VALUE_LENGTH]; if (suppress_report(&data->location)) return; - ubsan_prologue(&data->location, &flags); + ubsan_prologue(&data->location); val_to_string(index_str, sizeof(index_str), data->index_type, index); pr_err("index %s is out of range for type %s\n", index_str, data->array_type->type_name); - ubsan_epilogue(&flags); + ubsan_epilogue(); } EXPORT_SYMBOL(__ubsan_handle_out_of_bounds); void __ubsan_handle_shift_out_of_bounds(struct shift_out_of_bounds_data *data, void *lhs, void *rhs) { - unsigned long flags; struct type_descriptor *rhs_type = data->rhs_type; struct type_descriptor *lhs_type = data->lhs_type; char rhs_str[VALUE_LENGTH]; char lhs_str[VALUE_LENGTH]; + unsigned long ua_flags = user_access_save(); if (suppress_report(&data->location)) - return; + goto out; - ubsan_prologue(&data->location, &flags); + ubsan_prologue(&data->location); val_to_string(rhs_str, sizeof(rhs_str), rhs_type, rhs); val_to_string(lhs_str, sizeof(lhs_str), lhs_type, lhs); @@ -401,18 +387,18 @@ void __ubsan_handle_shift_out_of_bounds(struct shift_out_of_bounds_data *data, lhs_str, rhs_str, lhs_type->type_name); - ubsan_epilogue(&flags); + ubsan_epilogue(); +out: + user_access_restore(ua_flags); } EXPORT_SYMBOL(__ubsan_handle_shift_out_of_bounds); void __ubsan_handle_builtin_unreachable(struct unreachable_data *data) { - unsigned long flags; - - ubsan_prologue(&data->location, &flags); + ubsan_prologue(&data->location); pr_err("calling __builtin_unreachable()\n"); - ubsan_epilogue(&flags); + ubsan_epilogue(); panic("can't return from __builtin_unreachable()"); } EXPORT_SYMBOL(__ubsan_handle_builtin_unreachable); @@ -420,19 +406,18 @@ EXPORT_SYMBOL(__ubsan_handle_builtin_unreachable); void __ubsan_handle_load_invalid_value(struct invalid_value_data *data, void *val) { - unsigned long flags; char val_str[VALUE_LENGTH]; if (suppress_report(&data->location)) return; - ubsan_prologue(&data->location, &flags); + ubsan_prologue(&data->location); val_to_string(val_str, sizeof(val_str), data->type, val); pr_err("load of value %s is not a valid value for type %s\n", val_str, data->type->type_name); - ubsan_epilogue(&flags); + ubsan_epilogue(); } EXPORT_SYMBOL(__ubsan_handle_load_invalid_value); diff --git a/mm/filemap.c b/mm/filemap.c index 85b7d087eb45..1f5731768222 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2329,27 +2329,6 @@ EXPORT_SYMBOL(generic_file_read_iter); #ifdef CONFIG_MMU #define MMAP_LOTSAMISS (100) -static struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf, - struct file *fpin) -{ - int flags = vmf->flags; - - if (fpin) - return fpin; - - /* - * FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or - * anything, so we only pin the file and drop the mmap_sem if only - * FAULT_FLAG_ALLOW_RETRY is set. - */ - if ((flags & (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT)) == - FAULT_FLAG_ALLOW_RETRY) { - fpin = get_file(vmf->vma->vm_file); - up_read(&vmf->vma->vm_mm->mmap_sem); - } - return fpin; -} - /* * lock_page_maybe_drop_mmap - lock the page, possibly dropping the mmap_sem * @vmf - the vm_fault for this fault. diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c index 7dd602d7f8db..ad9d5b1c4473 100644 --- a/mm/gup_benchmark.c +++ b/mm/gup_benchmark.c @@ -26,6 +26,7 @@ static int __gup_benchmark_ioctl(unsigned int cmd, unsigned long i, nr_pages, addr, next; int nr; struct page **pages; + int ret = 0; if (gup->size > ULONG_MAX) return -EINVAL; @@ -63,7 +64,9 @@ static int __gup_benchmark_ioctl(unsigned int cmd, NULL); break; default: - return -1; + kvfree(pages); + ret = -EINVAL; + goto out; } if (nr <= 0) @@ -85,7 +88,8 @@ static int __gup_benchmark_ioctl(unsigned int cmd, gup->put_delta_usec = ktime_us_delta(end_time, start_time); kvfree(pages); - return 0; +out: + return ret; } static long gup_benchmark_ioctl(struct file *filep, unsigned int cmd, diff --git a/mm/hugetlb.c b/mm/hugetlb.c index b45a95363a84..e0afd582ca01 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include @@ -1255,7 +1256,7 @@ static inline void ClearPageHugeTemporary(struct page *page) page[2].mapping = NULL; } -void free_huge_page(struct page *page) +static void __free_huge_page(struct page *page) { /* * Can't pass hstate in here because it is called from the @@ -1318,6 +1319,54 @@ void free_huge_page(struct page *page) spin_unlock(&hugetlb_lock); } +/* + * As free_huge_page() can be called from a non-task context, we have + * to defer the actual freeing in a workqueue to prevent potential + * hugetlb_lock deadlock. + * + * free_hpage_workfn() locklessly retrieves the linked list of pages to + * be freed and frees them one-by-one. As the page->mapping pointer is + * going to be cleared in __free_huge_page() anyway, it is reused as the + * llist_node structure of a lockless linked list of huge pages to be freed. + */ +static LLIST_HEAD(hpage_freelist); + +static void free_hpage_workfn(struct work_struct *work) +{ + struct llist_node *node; + struct page *page; + + node = llist_del_all(&hpage_freelist); + + while (node) { + page = container_of((struct address_space **)node, + struct page, mapping); + node = node->next; + __free_huge_page(page); + } +} +static DECLARE_WORK(free_hpage_work, free_hpage_workfn); + +void free_huge_page(struct page *page) +{ + /* + * Defer freeing if in non-task context to avoid hugetlb_lock deadlock. + */ + if (!in_task()) { + /* + * Only call schedule_work() if hpage_freelist is previously + * empty. Otherwise, schedule_work() had been called but the + * workfn hasn't retrieved the list yet. + */ + if (llist_add((struct llist_node *)&page->mapping, + &hpage_freelist)) + schedule_work(&free_hpage_work); + return; + } + + __free_huge_page(page); +} + static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) { INIT_LIST_HEAD(&page->lru); diff --git a/mm/internal.h b/mm/internal.h index 0d5f720c75ab..7dd7fbb577a9 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -362,6 +362,27 @@ vma_address(struct page *page, struct vm_area_struct *vma) return max(start, vma->vm_start); } +static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf, + struct file *fpin) +{ + int flags = vmf->flags; + + if (fpin) + return fpin; + + /* + * FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or + * anything, so we only pin the file and drop the mmap_sem if only + * FAULT_FLAG_ALLOW_RETRY is set. + */ + if ((flags & (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT)) == + FAULT_FLAG_ALLOW_RETRY) { + fpin = get_file(vmf->vma->vm_file); + up_read(&vmf->vma->vm_mm->mmap_sem); + } + return fpin; +} + #else /* !CONFIG_MMU */ static inline void clear_page_mlock(struct page *page) { } static inline void mlock_vma_page(struct page *page) { } diff --git a/mm/ksm.c b/mm/ksm.c index 7905934cd3ad..252e69ae5b69 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -2425,54 +2425,78 @@ static int ksm_scan_thread(void *nothing) return 0; } -int ksm_madvise(struct vm_area_struct *vma, unsigned long start, - unsigned long end, int advice, unsigned long *vm_flags) +int ksm_madvise_merge(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long *vm_flags) { - struct mm_struct *mm = vma->vm_mm; int err; - switch (advice) { - case MADV_MERGEABLE: - /* - * Be somewhat over-protective for now! - */ - if (*vm_flags & (VM_MERGEABLE | VM_SHARED | VM_MAYSHARE | - VM_PFNMAP | VM_IO | VM_DONTEXPAND | - VM_HUGETLB | VM_MIXEDMAP)) - return 0; /* just ignore the advice */ + /* + * Be somewhat over-protective for now! + */ + if (*vm_flags & (VM_MERGEABLE | VM_SHARED | VM_MAYSHARE | + VM_PFNMAP | VM_IO | VM_DONTEXPAND | + VM_HUGETLB | VM_MIXEDMAP)) + return 0; /* just ignore the advice */ - if (vma_is_dax(vma)) - return 0; + if (vma_is_dax(vma)) + return 0; #ifdef VM_SAO - if (*vm_flags & VM_SAO) - return 0; + if (*vm_flags & VM_SAO) + return 0; #endif #ifdef VM_SPARC_ADI - if (*vm_flags & VM_SPARC_ADI) - return 0; + if (*vm_flags & VM_SPARC_ADI) + return 0; #endif - if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) { - err = __ksm_enter(mm); - if (err) - return err; - } + if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) { + err = __ksm_enter(mm); + if (err) + return err; + } - *vm_flags |= VM_MERGEABLE; - break; + *vm_flags |= VM_MERGEABLE; - case MADV_UNMERGEABLE: - if (!(*vm_flags & VM_MERGEABLE)) - return 0; /* just ignore the advice */ + return 0; +} - if (vma->anon_vma) { - err = unmerge_ksm_pages(vma, start, end); - if (err) - return err; - } +int ksm_madvise_unmerge(struct vm_area_struct *vma, unsigned long start, + unsigned long end, unsigned long *vm_flags) +{ + int err; + + if (!(*vm_flags & VM_MERGEABLE)) + return 0; /* just ignore the advice */ + + if (vma->anon_vma) { + err = unmerge_ksm_pages(vma, start, end); + if (err) + return err; + } + + *vm_flags &= ~VM_MERGEABLE; + + return 0; +} + +int ksm_madvise(struct vm_area_struct *vma, unsigned long start, + unsigned long end, int advice, unsigned long *vm_flags) +{ + struct mm_struct *mm = vma->vm_mm; + int err; - *vm_flags &= ~VM_MERGEABLE; + switch (advice) { + case MADV_MERGEABLE: + err = ksm_madvise_merge(mm, vma, vm_flags); + if (err) + return err; + break; + + case MADV_UNMERGEABLE: + err = ksm_madvise_unmerge(vma, start, end, vm_flags); + if (err) + return err; break; } diff --git a/mm/maccess.c b/mm/maccess.c index d065736f6b87..2d3c3d01064c 100644 --- a/mm/maccess.c +++ b/mm/maccess.c @@ -18,6 +18,18 @@ probe_read_common(void *dst, const void __user *src, size_t size) return ret ? -EFAULT : 0; } +static __always_inline long +probe_write_common(void __user *dst, const void *src, size_t size) +{ + long ret; + + pagefault_disable(); + ret = __copy_to_user_inatomic(dst, src, size); + pagefault_enable(); + + return ret ? -EFAULT : 0; +} + /** * probe_kernel_read(): safely attempt to read from a kernel-space location * @dst: pointer to the buffer that shall take the data @@ -85,6 +97,7 @@ EXPORT_SYMBOL_GPL(probe_user_read); * Safely write to address @dst from the buffer at @src. If a kernel fault * happens, handle that and return -EFAULT. */ + long __weak probe_kernel_write(void *dst, const void *src, size_t size) __attribute__((alias("__probe_kernel_write"))); @@ -94,15 +107,39 @@ long __probe_kernel_write(void *dst, const void *src, size_t size) mm_segment_t old_fs = get_fs(); set_fs(KERNEL_DS); - pagefault_disable(); - ret = __copy_to_user_inatomic((__force void __user *)dst, src, size); - pagefault_enable(); + ret = probe_write_common((__force void __user *)dst, src, size); set_fs(old_fs); - return ret ? -EFAULT : 0; + return ret; } EXPORT_SYMBOL_GPL(probe_kernel_write); +/** + * probe_user_write(): safely attempt to write to a user-space location + * @dst: address to write to + * @src: pointer to the data that shall be written + * @size: size of the data chunk + * + * Safely write to address @dst from the buffer at @src. If a kernel fault + * happens, handle that and return -EFAULT. + */ + +long __weak probe_user_write(void __user *dst, const void *src, size_t size) + __attribute__((alias("__probe_user_write"))); + +long __probe_user_write(void __user *dst, const void *src, size_t size) +{ + long ret = -EFAULT; + mm_segment_t old_fs = get_fs(); + + set_fs(USER_DS); + if (access_ok(dst, size)) + ret = probe_write_common(dst, src, size); + set_fs(old_fs); + + return ret; +} +EXPORT_SYMBOL_GPL(probe_user_write); /** * strncpy_from_unsafe: - Copy a NUL terminated string from unsafe address. diff --git a/mm/memory.c b/mm/memory.c index b1ca51a079f2..cb7c940cf800 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2227,10 +2227,11 @@ static vm_fault_t do_page_mkwrite(struct vm_fault *vmf) * * The function expects the page to be locked and unlocks it. */ -static void fault_dirty_shared_page(struct vm_area_struct *vma, - struct page *page) +static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf) { + struct vm_area_struct *vma = vmf->vma; struct address_space *mapping; + struct page *page = vmf->page; bool dirtied; bool page_mkwrite = vma->vm_ops && vma->vm_ops->page_mkwrite; @@ -2245,16 +2246,30 @@ static void fault_dirty_shared_page(struct vm_area_struct *vma, mapping = page_rmapping(page); unlock_page(page); + if (!page_mkwrite) + file_update_time(vma->vm_file); + + /* + * Throttle page dirtying rate down to writeback speed. + * + * mapping may be NULL here because some device drivers do not + * set page.mapping but still dirty their pages + * + * Drop the mmap_sem before waiting on IO, if we can. The file + * is pinning the mapping, as per above. + */ if ((dirtied || page_mkwrite) && mapping) { - /* - * Some device drivers do not set page.mapping - * but still dirty their pages - */ + struct file *fpin; + + fpin = maybe_unlock_mmap_for_io(vmf, NULL); balance_dirty_pages_ratelimited(mapping); + if (fpin) { + fput(fpin); + return VM_FAULT_RETRY; + } } - if (!page_mkwrite) - file_update_time(vma->vm_file); + return 0; } /* @@ -2497,6 +2512,7 @@ static vm_fault_t wp_page_shared(struct vm_fault *vmf) __releases(vmf->ptl) { struct vm_area_struct *vma = vmf->vma; + vm_fault_t ret = VM_FAULT_WRITE; get_page(vmf->page); @@ -2520,10 +2536,10 @@ static vm_fault_t wp_page_shared(struct vm_fault *vmf) wp_page_reuse(vmf); lock_page(vmf->page); } - fault_dirty_shared_page(vma, vmf->page); + ret |= fault_dirty_shared_page(vmf); put_page(vmf->page); - return VM_FAULT_WRITE; + return ret; } /* @@ -3567,7 +3583,7 @@ static vm_fault_t do_shared_fault(struct vm_fault *vmf) return ret; } - fault_dirty_shared_page(vma, vmf->page); + ret |= fault_dirty_shared_page(vmf); return ret; } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index f307bd82d750..fab540685279 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -465,8 +465,9 @@ static void update_pgdat_span(struct pglist_data *pgdat) pgdat->node_spanned_pages = node_end_pfn - node_start_pfn; } -static void __remove_zone(struct zone *zone, unsigned long start_pfn, - unsigned long nr_pages) +void __ref remove_pfn_range_from_zone(struct zone *zone, + unsigned long start_pfn, + unsigned long nr_pages) { struct pglist_data *pgdat = zone->zone_pgdat; unsigned long flags; @@ -481,28 +482,30 @@ static void __remove_zone(struct zone *zone, unsigned long start_pfn, return; #endif + clear_zone_contiguous(zone); + pgdat_resize_lock(zone->zone_pgdat, &flags); shrink_zone_span(zone, start_pfn, start_pfn + nr_pages); update_pgdat_span(pgdat); pgdat_resize_unlock(zone->zone_pgdat, &flags); + + set_zone_contiguous(zone); } -static void __remove_section(struct zone *zone, unsigned long pfn, - unsigned long nr_pages, unsigned long map_offset, - struct vmem_altmap *altmap) +static void __remove_section(unsigned long pfn, unsigned long nr_pages, + unsigned long map_offset, + struct vmem_altmap *altmap) { struct mem_section *ms = __nr_to_section(pfn_to_section_nr(pfn)); if (WARN_ON_ONCE(!valid_section(ms))) return; - __remove_zone(zone, pfn, nr_pages); sparse_remove_section(ms, pfn, nr_pages, map_offset, altmap); } /** - * __remove_pages() - remove sections of pages from a zone - * @zone: zone from which pages need to be removed + * __remove_pages() - remove sections of pages * @pfn: starting pageframe (must be aligned to start of a section) * @nr_pages: number of pages to remove (must be multiple of section size) * @altmap: alternative device page map or %NULL if default memmap is used @@ -512,16 +515,14 @@ static void __remove_section(struct zone *zone, unsigned long pfn, * sure that pages are marked reserved and zones are adjust properly by * calling offline_pages(). */ -void __remove_pages(struct zone *zone, unsigned long pfn, - unsigned long nr_pages, struct vmem_altmap *altmap) +void __remove_pages(unsigned long pfn, unsigned long nr_pages, + struct vmem_altmap *altmap) { unsigned long map_offset = 0; unsigned long nr, start_sec, end_sec; map_offset = vmem_altmap_offset(altmap); - clear_zone_contiguous(zone); - if (check_pfn_span(pfn, nr_pages, "remove")) return; @@ -533,13 +534,11 @@ void __remove_pages(struct zone *zone, unsigned long pfn, cond_resched(); pfns = min(nr_pages, PAGES_PER_SECTION - (pfn & ~PAGE_SECTION_MASK)); - __remove_section(zone, pfn, pfns, map_offset, altmap); + __remove_section(pfn, pfns, map_offset, altmap); pfn += pfns; nr_pages -= pfns; map_offset = 0; } - - set_zone_contiguous(zone); } int set_online_page_callback(online_page_callback_t callback) @@ -867,6 +866,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ (unsigned long long) pfn << PAGE_SHIFT, (((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1); memory_notify(MEM_CANCEL_ONLINE, &arg); + remove_pfn_range_from_zone(zone, pfn, nr_pages); mem_hotplug_done(); return ret; } @@ -1602,6 +1602,7 @@ static int __ref __offline_pages(unsigned long start_pfn, writeback_set_ratelimit(); memory_notify(MEM_OFFLINE, &arg); + remove_pfn_range_from_zone(zone, start_pfn, nr_pages); mem_hotplug_done(); return 0; diff --git a/mm/memremap.c b/mm/memremap.c index 03ccbdfeb697..c51c6bd2fe34 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -120,7 +120,7 @@ void memunmap_pages(struct dev_pagemap *pgmap) mem_hotplug_begin(); if (pgmap->type == MEMORY_DEVICE_PRIVATE) { - __remove_pages(page_zone(first_page), PHYS_PFN(res->start), + __remove_pages(PHYS_PFN(res->start), PHYS_PFN(resource_size(res)), NULL); } else { arch_remove_memory(nid, res->start, resource_size(res), diff --git a/mm/migrate.c b/mm/migrate.c index 4fe45d1428c8..45d3303e0022 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1516,9 +1516,11 @@ static int do_move_pages_to_node(struct mm_struct *mm, /* * Resolves the given address to a struct page, isolates it from the LRU and * puts it to the given pagelist. - * Returns -errno if the page cannot be found/isolated or 0 when it has been - * queued or the page doesn't need to be migrated because it is already on - * the target node + * Returns: + * errno - if the page cannot be found/isolated + * 0 - when it doesn't have to be migrated because it is already on the + * target node + * 1 - when it has been queued */ static int add_page_for_migration(struct mm_struct *mm, unsigned long addr, int node, struct list_head *pagelist, bool migrate_all) @@ -1557,7 +1559,7 @@ static int add_page_for_migration(struct mm_struct *mm, unsigned long addr, if (PageHuge(page)) { if (PageHead(page)) { isolate_huge_page(page, pagelist); - err = 0; + err = 1; } } else { struct page *head; @@ -1567,7 +1569,7 @@ static int add_page_for_migration(struct mm_struct *mm, unsigned long addr, if (err) goto out_putpage; - err = 0; + err = 1; list_add_tail(&head->lru, pagelist); mod_node_page_state(page_pgdat(head), NR_ISOLATED_ANON + page_is_file_cache(head), @@ -1644,8 +1646,17 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes, */ err = add_page_for_migration(mm, addr, current_node, &pagelist, flags & MPOL_MF_MOVE_ALL); - if (!err) + + if (!err) { + /* The page is already on the target node */ + err = store_status(status, i, current_node, 1); + if (err) + goto out_flush; continue; + } else if (err > 0) { + /* The page is successfully queued for migration */ + continue; + } err = store_status(status, i, err, 1); if (err) diff --git a/mm/mmap.c b/mm/mmap.c index a7d8c84d19b7..4390dbea4aa5 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -90,12 +90,6 @@ static void unmap_region(struct mm_struct *mm, * MAP_PRIVATE r: (no) no r: (yes) yes r: (no) yes r: (no) yes * w: (no) no w: (no) no w: (copy) copy w: (no) no * x: (no) no x: (no) yes x: (no) yes x: (yes) yes - * - * On arm64, PROT_EXEC has the following behaviour for both MAP_SHARED and - * MAP_PRIVATE: - * r: (no) no - * w: (no) no - * x: (yes) yes */ pgprot_t protection_map[16] __ro_after_init = { __P000, __P001, __P010, __P011, __P100, __P101, __P110, __P111, diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 71e3acea7817..d58c481b3df8 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -890,7 +890,7 @@ static void __oom_kill_process(struct task_struct *victim, const char *message) K(get_mm_counter(mm, MM_FILEPAGES)), K(get_mm_counter(mm, MM_SHMEMPAGES)), from_kuid(&init_user_ns, task_uid(victim)), - mm_pgtables_bytes(mm), victim->signal->oom_score_adj); + mm_pgtables_bytes(mm) >> 10, victim->signal->oom_score_adj); task_unlock(victim); /* diff --git a/mm/shmem.c b/mm/shmem.c index 220be9fa2c41..6074714fdbd4 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2022,16 +2022,14 @@ static vm_fault_t shmem_fault(struct vm_fault *vmf) shmem_falloc->waitq && vmf->pgoff >= shmem_falloc->start && vmf->pgoff < shmem_falloc->next) { + struct file *fpin; wait_queue_head_t *shmem_falloc_waitq; DEFINE_WAIT_FUNC(shmem_fault_wait, synchronous_wake_function); ret = VM_FAULT_NOPAGE; - if ((vmf->flags & FAULT_FLAG_ALLOW_RETRY) && - !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) { - /* It's polite to up mmap_sem if we can */ - up_read(&vma->vm_mm->mmap_sem); + fpin = maybe_unlock_mmap_for_io(vmf, NULL); + if (fpin) ret = VM_FAULT_RETRY; - } shmem_falloc_waitq = shmem_falloc->waitq; prepare_to_wait(shmem_falloc_waitq, &shmem_fault_wait, @@ -2049,6 +2047,9 @@ static vm_fault_t shmem_fault(struct vm_fault *vmf) spin_lock(&inode->i_lock); finish_wait(shmem_falloc_waitq, &shmem_fault_wait); spin_unlock(&inode->i_lock); + + if (fpin) + fput(fpin); return ret; } spin_unlock(&inode->i_lock); @@ -2213,11 +2214,14 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma) return -EPERM; /* - * Since the F_SEAL_FUTURE_WRITE seals allow for a MAP_SHARED - * read-only mapping, take care to not allow mprotect to revert - * protections. + * Since an F_SEAL_FUTURE_WRITE sealed memfd can be mapped as + * MAP_SHARED and read-only, take care to not allow mprotect to + * revert protections on such mappings. Do this only for shared + * mappings. For private mappings, don't need to mask + * VM_MAYWRITE as we still want them to be COW-writable. */ - vma->vm_flags &= ~(VM_MAYWRITE); + if (vma->vm_flags & VM_SHARED) + vma->vm_flags &= ~(VM_MAYWRITE); } file_accessed(file); @@ -2742,7 +2746,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, } shmem_falloc.waitq = &shmem_falloc_waitq; - shmem_falloc.start = unmap_start >> PAGE_SHIFT; + shmem_falloc.start = (u64)unmap_start >> PAGE_SHIFT; shmem_falloc.next = (unmap_end + 1) >> PAGE_SHIFT; spin_lock(&inode->i_lock); inode->i_private = &shmem_falloc; diff --git a/mm/slab_common.c b/mm/slab_common.c index f9fb27b4c843..78402b362df9 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -904,6 +904,18 @@ static void flush_memcg_workqueue(struct kmem_cache *s) * previous workitems on workqueue are processed. */ flush_workqueue(memcg_kmem_cache_wq); + + /* + * If we're racing with children kmem_cache deactivation, it might + * take another rcu grace period to complete their destruction. + * At this moment the corresponding percpu_ref_kill() call should be + * done, but it might take another rcu grace period to complete + * switching to the atomic mode. + * Please, note that we check without grabbing the slab_mutex. It's safe + * because at this moment the children list can't grow. + */ + if (!list_empty(&s->memcg_params.children)) + rcu_barrier(); } #else static inline int shutdown_memcg_caches(struct kmem_cache *s) diff --git a/mm/sparse.c b/mm/sparse.c index f6891c1992b1..c2c01b6330af 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -647,7 +647,7 @@ void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn) #endif #ifdef CONFIG_SPARSEMEM_VMEMMAP -static struct page *populate_section_memmap(unsigned long pfn, +static struct page * __meminit populate_section_memmap(unsigned long pfn, unsigned long nr_pages, int nid, struct vmem_altmap *altmap) { return __populate_section_memmap(pfn, nr_pages, nid, altmap); @@ -669,7 +669,7 @@ static void free_map_bootmem(struct page *memmap) vmemmap_free(start, end, NULL); } #else -struct page *populate_section_memmap(unsigned long pfn, +struct page * __meminit populate_section_memmap(unsigned long pfn, unsigned long nr_pages, int nid, struct vmem_altmap *altmap) { struct page *page, *ret; diff --git a/mm/vmscan.c b/mm/vmscan.c index ee4eecc7e1c2..e7f10c4b40f0 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -422,7 +422,7 @@ void register_shrinker_prepared(struct shrinker *shrinker) { down_write(&shrinker_rwsem); list_add_tail(&shrinker->list, &shrinker_list); -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG if (shrinker->flags & SHRINKER_MEMCG_AWARE) idr_replace(&shrinker_idr, shrinker, shrinker->id); #endif diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 2b2b9aae8a3c..22d17ecfe7df 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -2069,6 +2069,11 @@ static int zs_page_migrate(struct address_space *mapping, struct page *newpage, zs_pool_dec_isolated(pool); } + if (page_zone(newpage) != page_zone(page)) { + dec_zone_page_state(page, NR_ZSPAGES); + inc_zone_page_state(newpage, NR_ZSPAGES); + } + reset_page(page); put_page(page); page = newpage; diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index c46daf09a501..bb7ec1a3915d 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -126,6 +126,7 @@ int vlan_check_real_dev(struct net_device *real_dev, void vlan_setup(struct net_device *dev); int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack); void unregister_vlan_dev(struct net_device *dev, struct list_head *head); +void vlan_dev_uninit(struct net_device *dev); bool vlan_dev_inherit_address(struct net_device *dev, struct net_device *real_dev); diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index e5bff5cc6f97..2a78da4072de 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -586,7 +586,8 @@ static int vlan_dev_init(struct net_device *dev) return 0; } -static void vlan_dev_uninit(struct net_device *dev) +/* Note: this function might be called multiple times for the same device. */ +void vlan_dev_uninit(struct net_device *dev) { struct vlan_priority_tci_mapping *pm; struct vlan_dev_priv *vlan = vlan_dev_priv(dev); diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index c482a6fe9393..0db85aeb119b 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -108,11 +108,13 @@ static int vlan_changelink(struct net_device *dev, struct nlattr *tb[], struct ifla_vlan_flags *flags; struct ifla_vlan_qos_mapping *m; struct nlattr *attr; - int rem; + int rem, err; if (data[IFLA_VLAN_FLAGS]) { flags = nla_data(data[IFLA_VLAN_FLAGS]); - vlan_dev_change_flags(dev, flags->flags, flags->mask); + err = vlan_dev_change_flags(dev, flags->flags, flags->mask); + if (err) + return err; } if (data[IFLA_VLAN_INGRESS_QOS]) { nla_for_each_nested(attr, data[IFLA_VLAN_INGRESS_QOS], rem) { @@ -123,7 +125,9 @@ static int vlan_changelink(struct net_device *dev, struct nlattr *tb[], if (data[IFLA_VLAN_EGRESS_QOS]) { nla_for_each_nested(attr, data[IFLA_VLAN_EGRESS_QOS], rem) { m = nla_data(attr); - vlan_dev_set_egress_priority(dev, m->from, m->to); + err = vlan_dev_set_egress_priority(dev, m->from, m->to); + if (err) + return err; } } return 0; @@ -179,10 +183,11 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev, return -EINVAL; err = vlan_changelink(dev, tb, data, extack); - if (err < 0) - return err; - - return register_vlan_dev(dev, extack); + if (!err) + err = register_vlan_dev(dev, extack); + if (err) + vlan_dev_uninit(dev); + return err; } static inline size_t vlan_qos_map_size(unsigned int n) diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index ad5b0ac1f9ce..87691404d0c6 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -934,6 +934,14 @@ static void hci_req_directed_advertising(struct hci_request *req, return; memset(&cp, 0, sizeof(cp)); + + /* Some controllers might reject command if intervals are not + * within range for undirected advertising. + * BCM20702A0 is known to be affected by this. + */ + cp.min_interval = cpu_to_le16(0x0020); + cp.max_interval = cpu_to_le16(0x0020); + cp.type = LE_ADV_DIRECT_IND; cp.own_address_type = own_addr_type; cp.direct_addr_type = conn->dst_type; @@ -1168,8 +1176,10 @@ struct hci_conn *hci_connect_le_scan(struct hci_dev *hdev, bdaddr_t *dst, if (!conn) return ERR_PTR(-ENOMEM); - if (hci_explicit_conn_params_set(hdev, dst, dst_type) < 0) + if (hci_explicit_conn_params_set(hdev, dst, dst_type) < 0) { + hci_conn_del(conn); return ERR_PTR(-EBUSY); + } conn->state = BT_CONNECT; set_bit(HCI_CONN_SCANNING, &conn->flags); diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 04bc79359a17..0cc9ce917222 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -842,8 +842,8 @@ static int hci_init4_req(struct hci_request *req, unsigned long opt) if (hdev->le_features[0] & HCI_LE_DATA_LEN_EXT) { struct hci_cp_le_write_def_data_len cp; - cp.tx_len = hdev->le_max_tx_len; - cp.tx_time = hdev->le_max_tx_time; + cp.tx_len = cpu_to_le16(hdev->le_max_tx_len); + cp.tx_time = cpu_to_le16(hdev->le_max_tx_time); hci_req_add(req, HCI_OP_LE_WRITE_DEF_DATA_LEN, sizeof(cp), &cp); } @@ -4440,7 +4440,14 @@ static void hci_rx_work(struct work_struct *work) hci_send_to_sock(hdev, skb); } - if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { + /* If the device has been opened in HCI_USER_CHANNEL, + * the userspace has exclusive access to device. + * When device is HCI_INIT, we still need to process + * the data packets to the driver in order + * to complete its setup(). + */ + if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && + !test_bit(HCI_INIT, &hdev->flags)) { kfree_skb(skb); continue; } diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index 7f6a581b5b7e..3d25dbf10b26 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -1273,6 +1273,14 @@ static u8 create_instance_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr) instance_flags = get_adv_instance_flags(hdev, instance); + /* If instance already has the flags set skip adding it once + * again. + */ + if (adv_instance && eir_get_data(adv_instance->adv_data, + adv_instance->adv_data_len, EIR_FLAGS, + NULL)) + goto skip_flags; + /* The Add Advertising command allows userspace to set both the general * and limited discoverable flags. */ @@ -1305,6 +1313,7 @@ static u8 create_instance_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr) } } +skip_flags: if (adv_instance) { memcpy(ptr, adv_instance->adv_data, adv_instance->adv_data_len); diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index da7fdbdf9c41..a845786258a0 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -4936,10 +4936,8 @@ void __l2cap_physical_cfm(struct l2cap_chan *chan, int result) BT_DBG("chan %p, result %d, local_amp_id %d, remote_amp_id %d", chan, result, local_amp_id, remote_amp_id); - if (chan->state == BT_DISCONN || chan->state == BT_CLOSED) { - l2cap_chan_unlock(chan); + if (chan->state == BT_DISCONN || chan->state == BT_CLOSED) return; - } if (chan->state != BT_CONNECTED) { l2cap_do_create(chan, result, local_amp_id, remote_amp_id); diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index e804a3016902..022dc6e504c4 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -245,6 +245,12 @@ static int br_set_mac_address(struct net_device *dev, void *p) if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; + /* dev_set_mac_addr() can be called by a master device on bridge's + * NETDEV_UNREGISTER, but since it's being destroyed do nothing + */ + if (dev->reg_state != NETREG_REGISTERED) + return -EBUSY; + spin_lock_bh(&br->lock); if (!ether_addr_equal(dev->dev_addr, addr->sa_data)) { /* Mac address will be changed in br_stp_change_bridge_id(). */ diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index af7800103e51..59980ecfc962 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -662,6 +662,9 @@ static unsigned int br_nf_forward_arp(void *priv, nf_bridge_pull_encap_header(skb); } + if (unlikely(!pskb_may_pull(skb, sizeof(struct arphdr)))) + return NF_DROP; + if (arp_hdr(skb)->ar_pln != 4) { if (is_vlan_arp(skb, state->net)) nf_bridge_push_encap_header(skb); diff --git a/net/bridge/br_nf_core.c b/net/bridge/br_nf_core.c index 2cdfc5d6c25d..8c69f0c95a8e 100644 --- a/net/bridge/br_nf_core.c +++ b/net/bridge/br_nf_core.c @@ -22,7 +22,8 @@ #endif static void fake_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { } diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 4096d8a74a2b..e1256e03a9a8 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1867,7 +1867,7 @@ static int ebt_buf_count(struct ebt_entries_buf_state *state, unsigned int sz) } static int ebt_buf_add(struct ebt_entries_buf_state *state, - void *data, unsigned int sz) + const void *data, unsigned int sz) { if (state->buf_kern_start == NULL) goto count_only; @@ -1901,7 +1901,7 @@ enum compat_mwt { EBT_COMPAT_TARGET, }; -static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt, +static int compat_mtw_from_user(const struct compat_ebt_entry_mwt *mwt, enum compat_mwt compat_mwt, struct ebt_entries_buf_state *state, const unsigned char *base) @@ -1979,22 +1979,23 @@ static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt, /* return size of all matches, watchers or target, including necessary * alignment and padding. */ -static int ebt_size_mwt(struct compat_ebt_entry_mwt *match32, +static int ebt_size_mwt(const struct compat_ebt_entry_mwt *match32, unsigned int size_left, enum compat_mwt type, struct ebt_entries_buf_state *state, const void *base) { + const char *buf = (const char *)match32; int growth = 0; - char *buf; if (size_left == 0) return 0; - buf = (char *) match32; - - while (size_left >= sizeof(*match32)) { + do { struct ebt_entry_match *match_kern; int ret; + if (size_left < sizeof(*match32)) + return -EINVAL; + match_kern = (struct ebt_entry_match *) state->buf_kern_start; if (match_kern) { char *tmp; @@ -2031,22 +2032,18 @@ static int ebt_size_mwt(struct compat_ebt_entry_mwt *match32, if (match_kern) match_kern->match_size = ret; - /* rule should have no remaining data after target */ - if (type == EBT_COMPAT_TARGET && size_left) - return -EINVAL; - match32 = (struct compat_ebt_entry_mwt *) buf; - } + } while (size_left); return growth; } /* called for all ebt_entry structures. */ -static int size_entry_mwt(struct ebt_entry *entry, const unsigned char *base, +static int size_entry_mwt(const struct ebt_entry *entry, const unsigned char *base, unsigned int *total, struct ebt_entries_buf_state *state) { - unsigned int i, j, startoff, new_offset = 0; + unsigned int i, j, startoff, next_expected_off, new_offset = 0; /* stores match/watchers/targets & offset of next struct ebt_entry: */ unsigned int offsets[4]; unsigned int *offsets_update = NULL; @@ -2132,11 +2129,13 @@ static int size_entry_mwt(struct ebt_entry *entry, const unsigned char *base, return ret; } - startoff = state->buf_user_offset - startoff; + next_expected_off = state->buf_user_offset - startoff; + if (next_expected_off != entry->next_offset) + return -EINVAL; - if (WARN_ON(*total < startoff)) + if (*total < entry->next_offset) return -EINVAL; - *total -= startoff; + *total -= entry->next_offset; return 0; } diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index de09b0a65791..f7587428febd 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -423,9 +423,9 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) { struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct j1939_sock *jsk = j1939_sk(sock->sk); - struct j1939_priv *priv = jsk->priv; - struct sock *sk = sock->sk; - struct net *net = sock_net(sk); + struct j1939_priv *priv; + struct sock *sk; + struct net *net; int ret = 0; ret = j1939_sk_sanity_check(addr, len); @@ -434,6 +434,10 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) lock_sock(sock->sk); + priv = jsk->priv; + sk = sock->sk; + net = sock_net(sk); + /* Already bound to an interface? */ if (jsk->state & J1939_SOCK_BOUND) { /* A re-bind() to a different interface is not diff --git a/net/core/dev.c b/net/core/dev.c index 99ac84ff398f..3e11c6bb4dd6 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3386,7 +3386,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, qdisc_calculate_pkt_len(skb, q); if (q->flags & TCQ_F_NOLOCK) { - if ((q->flags & TCQ_F_CAN_BYPASS) && q->empty && + if ((q->flags & TCQ_F_CAN_BYPASS) && READ_ONCE(q->empty) && qdisc_run_begin(q)) { if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) { @@ -7967,7 +7967,8 @@ int __dev_set_mtu(struct net_device *dev, int new_mtu) if (ops->ndo_change_mtu) return ops->ndo_change_mtu(dev, new_mtu); - dev->mtu = new_mtu; + /* Pairs with all the lockless reads of dev->mtu in the stack */ + WRITE_ONCE(dev->mtu, new_mtu); return 0; } EXPORT_SYMBOL(__dev_set_mtu); diff --git a/net/core/filter.c b/net/core/filter.c index 3fed5755494b..2f76461c120d 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2055,6 +2055,7 @@ static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb) } skb->dev = dev; + skb->tstamp = 0; dev_xmit_recursion_inc(); ret = dev_queue_xmit(skb); @@ -2299,7 +2300,7 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start, WARN_ON_ONCE(last_sge == first_sge); shift = last_sge > first_sge ? last_sge - first_sge - 1 : - MAX_SKB_FRAGS - first_sge + last_sge - 1; + NR_MSG_FRAG_IDS - first_sge + last_sge - 1; if (!shift) goto out; @@ -2308,8 +2309,8 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start, do { u32 move_from; - if (i + shift >= MAX_MSG_FRAGS) - move_from = i + shift - MAX_MSG_FRAGS; + if (i + shift >= NR_MSG_FRAG_IDS) + move_from = i + shift - NR_MSG_FRAG_IDS; else move_from = i + shift; if (move_from == msg->sg.end) @@ -2323,7 +2324,7 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start, } while (1); msg->sg.end = msg->sg.end - shift > msg->sg.end ? - msg->sg.end - shift + MAX_MSG_FRAGS : + msg->sg.end - shift + NR_MSG_FRAG_IDS : msg->sg.end - shift; out: msg->data = sg_virt(&msg->sg.data[first_sge]) + start - offset; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 68eda10d0680..1292f3f0f93f 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -683,6 +683,31 @@ __skb_flow_dissect_tcp(const struct sk_buff *skb, key_tcp->flags = (*(__be16 *) &tcp_flag_word(th) & htons(0x0FFF)); } +static void +__skb_flow_dissect_ports(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container, void *data, int nhoff, + u8 ip_proto, int hlen) +{ + enum flow_dissector_key_id dissector_ports = FLOW_DISSECTOR_KEY_MAX; + struct flow_dissector_key_ports *key_ports; + + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) + dissector_ports = FLOW_DISSECTOR_KEY_PORTS; + else if (dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS_RANGE)) + dissector_ports = FLOW_DISSECTOR_KEY_PORTS_RANGE; + + if (dissector_ports == FLOW_DISSECTOR_KEY_MAX) + return; + + key_ports = skb_flow_dissector_target(flow_dissector, + dissector_ports, + target_container); + key_ports->ports = __skb_flow_get_ports(skb, nhoff, ip_proto, + data, hlen); +} + static void __skb_flow_dissect_ipv4(const struct sk_buff *skb, struct flow_dissector *flow_dissector, @@ -852,7 +877,6 @@ bool __skb_flow_dissect(const struct net *net, struct flow_dissector_key_control *key_control; struct flow_dissector_key_basic *key_basic; struct flow_dissector_key_addrs *key_addrs; - struct flow_dissector_key_ports *key_ports; struct flow_dissector_key_icmp *key_icmp; struct flow_dissector_key_tags *key_tags; struct flow_dissector_key_vlan *key_vlan; @@ -870,9 +894,10 @@ bool __skb_flow_dissect(const struct net *net, nhoff = skb_network_offset(skb); hlen = skb_headlen(skb); #if IS_ENABLED(CONFIG_NET_DSA) - if (unlikely(skb->dev && netdev_uses_dsa(skb->dev))) { + if (unlikely(skb->dev && netdev_uses_dsa(skb->dev) && + proto == htons(ETH_P_XDSA))) { const struct dsa_device_ops *ops; - int offset; + int offset = 0; ops = skb->dev->dsa_ptr->tag_ops; if (ops->flow_dissect && @@ -1299,14 +1324,9 @@ bool __skb_flow_dissect(const struct net *net, break; } - if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS) && - !(key_control->flags & FLOW_DIS_IS_FRAGMENT)) { - key_ports = skb_flow_dissector_target(flow_dissector, - FLOW_DISSECTOR_KEY_PORTS, - target_container); - key_ports->ports = __skb_flow_get_ports(skb, nhoff, ip_proto, - data, hlen); - } + if (!(key_control->flags & FLOW_DIS_IS_FRAGMENT)) + __skb_flow_dissect_ports(skb, flow_dissector, target_container, + data, nhoff, ip_proto, hlen); if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ICMP)) { diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c index cf52d9c422fa..45b6a59ac124 100644 --- a/net/core/flow_offload.c +++ b/net/core/flow_offload.c @@ -283,7 +283,7 @@ int flow_block_cb_setup_simple(struct flow_block_offload *f, } EXPORT_SYMBOL(flow_block_cb_setup_simple); -static LIST_HEAD(block_ing_cb_list); +static LIST_HEAD(block_cb_list); static struct rhashtable indr_setup_block_ht; @@ -391,20 +391,19 @@ static void flow_indr_block_cb_del(struct flow_indr_block_cb *indr_block_cb) kfree(indr_block_cb); } -static DEFINE_MUTEX(flow_indr_block_ing_cb_lock); +static DEFINE_MUTEX(flow_indr_block_cb_lock); -static void flow_block_ing_cmd(struct net_device *dev, - flow_indr_block_bind_cb_t *cb, - void *cb_priv, - enum flow_block_command command) +static void flow_block_cmd(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, void *cb_priv, + enum flow_block_command command) { - struct flow_indr_block_ing_entry *entry; + struct flow_indr_block_entry *entry; - mutex_lock(&flow_indr_block_ing_cb_lock); - list_for_each_entry(entry, &block_ing_cb_list, list) { + mutex_lock(&flow_indr_block_cb_lock); + list_for_each_entry(entry, &block_cb_list, list) { entry->cb(dev, cb, cb_priv, command); } - mutex_unlock(&flow_indr_block_ing_cb_lock); + mutex_unlock(&flow_indr_block_cb_lock); } int __flow_indr_block_cb_register(struct net_device *dev, void *cb_priv, @@ -424,8 +423,8 @@ int __flow_indr_block_cb_register(struct net_device *dev, void *cb_priv, if (err) goto err_dev_put; - flow_block_ing_cmd(dev, indr_block_cb->cb, indr_block_cb->cb_priv, - FLOW_BLOCK_BIND); + flow_block_cmd(dev, indr_block_cb->cb, indr_block_cb->cb_priv, + FLOW_BLOCK_BIND); return 0; @@ -464,8 +463,8 @@ void __flow_indr_block_cb_unregister(struct net_device *dev, if (!indr_block_cb) return; - flow_block_ing_cmd(dev, indr_block_cb->cb, indr_block_cb->cb_priv, - FLOW_BLOCK_UNBIND); + flow_block_cmd(dev, indr_block_cb->cb, indr_block_cb->cb_priv, + FLOW_BLOCK_UNBIND); flow_indr_block_cb_del(indr_block_cb); flow_indr_block_dev_put(indr_dev); @@ -499,21 +498,21 @@ void flow_indr_block_call(struct net_device *dev, } EXPORT_SYMBOL_GPL(flow_indr_block_call); -void flow_indr_add_block_ing_cb(struct flow_indr_block_ing_entry *entry) +void flow_indr_add_block_cb(struct flow_indr_block_entry *entry) { - mutex_lock(&flow_indr_block_ing_cb_lock); - list_add_tail(&entry->list, &block_ing_cb_list); - mutex_unlock(&flow_indr_block_ing_cb_lock); + mutex_lock(&flow_indr_block_cb_lock); + list_add_tail(&entry->list, &block_cb_list); + mutex_unlock(&flow_indr_block_cb_lock); } -EXPORT_SYMBOL_GPL(flow_indr_add_block_ing_cb); +EXPORT_SYMBOL_GPL(flow_indr_add_block_cb); -void flow_indr_del_block_ing_cb(struct flow_indr_block_ing_entry *entry) +void flow_indr_del_block_cb(struct flow_indr_block_entry *entry) { - mutex_lock(&flow_indr_block_ing_cb_lock); + mutex_lock(&flow_indr_block_cb_lock); list_del(&entry->list); - mutex_unlock(&flow_indr_block_ing_cb_lock); + mutex_unlock(&flow_indr_block_cb_lock); } -EXPORT_SYMBOL_GPL(flow_indr_del_block_ing_cb); +EXPORT_SYMBOL_GPL(flow_indr_del_block_cb); static int __init init_flow_indr_rhashtable(void) { diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index 74cfb8b5ab33..99a6de52b21d 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -230,9 +230,7 @@ static int bpf_lwt_xmit_reroute(struct sk_buff *skb) fl6.daddr = iph6->daddr; fl6.saddr = iph6->saddr; - err = ipv6_stub->ipv6_dst_lookup(net, skb->sk, &dst, &fl6); - if (unlikely(err)) - goto err; + dst = ipv6_stub->ipv6_dst_lookup_flow(net, skb->sk, &fl6, NULL); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto err; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 5480edff0c86..f2452496ad9f 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -98,9 +98,6 @@ static int neigh_blackhole(struct neighbour *neigh, struct sk_buff *skb) static void neigh_cleanup_and_release(struct neighbour *neigh) { - if (neigh->parms->neigh_cleanup) - neigh->parms->neigh_cleanup(neigh); - trace_neigh_cleanup_and_release(neigh, 0); __neigh_notify(neigh, RTM_DELNEIGH, 0, 0); call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh); @@ -1197,7 +1194,7 @@ static void neigh_update_hhs(struct neighbour *neigh) if (update) { hh = &neigh->hh; - if (hh->hh_len) { + if (READ_ONCE(hh->hh_len)) { write_seqlock_bh(&hh->hh_lock); update(hh, neigh->dev, neigh->ha); write_sequnlock_bh(&hh->hh_lock); @@ -1476,7 +1473,7 @@ int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb) struct net_device *dev = neigh->dev; unsigned int seq; - if (dev->header_ops->cache && !neigh->hh.hh_len) + if (dev->header_ops->cache && !READ_ONCE(neigh->hh.hh_len)) neigh_hh_init(neigh); do { diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index ae3bcb1540ec..b4db68e5caa9 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -919,14 +919,17 @@ static int rx_queue_add_kobject(struct net_device *dev, int index) struct kobject *kobj = &queue->kobj; int error = 0; + /* Kobject_put later will trigger rx_queue_release call which + * decreases dev refcount: Take that reference here + */ + dev_hold(queue->dev); + kobj->kset = dev->queues_kset; error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL, "rx-%u", index); if (error) goto err; - dev_hold(queue->dev); - if (dev->sysfs_rx_queue_group) { error = sysfs_create_group(kobj, dev->sysfs_rx_queue_group); if (error) diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 5bc65587f1c4..dfc2501c35d9 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -18,6 +18,9 @@ #include +#define DEFER_TIME (msecs_to_jiffies(1000)) +#define DEFER_WARN_INTERVAL (60 * HZ) + static int page_pool_init(struct page_pool *pool, const struct page_pool_params *params) { @@ -193,22 +196,14 @@ static s32 page_pool_inflight(struct page_pool *pool) { u32 release_cnt = atomic_read(&pool->pages_state_release_cnt); u32 hold_cnt = READ_ONCE(pool->pages_state_hold_cnt); - s32 distance; - - distance = _distance(hold_cnt, release_cnt); - - trace_page_pool_inflight(pool, distance, hold_cnt, release_cnt); - return distance; -} + s32 inflight; -static bool __page_pool_safe_to_destroy(struct page_pool *pool) -{ - s32 inflight = page_pool_inflight(pool); + inflight = _distance(hold_cnt, release_cnt); - /* The distance should not be able to become negative */ + trace_page_pool_inflight(pool, inflight, hold_cnt, release_cnt); WARN(inflight < 0, "Negative(%d) inflight packet-pages", inflight); - return (inflight == 0); + return inflight; } /* Cleanup page_pool state from page */ @@ -216,6 +211,7 @@ static void __page_pool_clean_page(struct page_pool *pool, struct page *page) { dma_addr_t dma; + int count; if (!(pool->p.flags & PP_FLAG_DMA_MAP)) goto skip_dma_unmap; @@ -227,9 +223,11 @@ static void __page_pool_clean_page(struct page_pool *pool, DMA_ATTR_SKIP_CPU_SYNC); page->dma_addr = 0; skip_dma_unmap: - atomic_inc(&pool->pages_state_release_cnt); - trace_page_pool_state_release(pool, page, - atomic_read(&pool->pages_state_release_cnt)); + /* This may be the last page returned, releasing the pool, so + * it is not safe to reference pool afterwards. + */ + count = atomic_inc_return(&pool->pages_state_release_cnt); + trace_page_pool_state_release(pool, page, count); } /* unmap the page and clean our state */ @@ -338,31 +336,10 @@ static void __page_pool_empty_ring(struct page_pool *pool) } } -static void __warn_in_flight(struct page_pool *pool) +static void page_pool_free(struct page_pool *pool) { - u32 release_cnt = atomic_read(&pool->pages_state_release_cnt); - u32 hold_cnt = READ_ONCE(pool->pages_state_hold_cnt); - s32 distance; - - distance = _distance(hold_cnt, release_cnt); - - /* Drivers should fix this, but only problematic when DMA is used */ - WARN(1, "Still in-flight pages:%d hold:%u released:%u", - distance, hold_cnt, release_cnt); -} - -void __page_pool_free(struct page_pool *pool) -{ - /* Only last user actually free/release resources */ - if (!page_pool_put(pool)) - return; - - WARN(pool->alloc.count, "API usage violation"); - WARN(!ptr_ring_empty(&pool->ring), "ptr_ring is not empty"); - - /* Can happen due to forced shutdown */ - if (!__page_pool_safe_to_destroy(pool)) - __warn_in_flight(pool); + if (pool->disconnect) + pool->disconnect(pool); ptr_ring_cleanup(&pool->ring, NULL); @@ -371,12 +348,8 @@ void __page_pool_free(struct page_pool *pool) kfree(pool); } -EXPORT_SYMBOL(__page_pool_free); -/* Request to shutdown: release pages cached by page_pool, and check - * for in-flight pages - */ -bool __page_pool_request_shutdown(struct page_pool *pool) +static void page_pool_scrub(struct page_pool *pool) { struct page *page; @@ -393,7 +366,64 @@ bool __page_pool_request_shutdown(struct page_pool *pool) * be in-flight. */ __page_pool_empty_ring(pool); +} + +static int page_pool_release(struct page_pool *pool) +{ + int inflight; + + page_pool_scrub(pool); + inflight = page_pool_inflight(pool); + if (!inflight) + page_pool_free(pool); + + return inflight; +} + +static void page_pool_release_retry(struct work_struct *wq) +{ + struct delayed_work *dwq = to_delayed_work(wq); + struct page_pool *pool = container_of(dwq, typeof(*pool), release_dw); + int inflight; + + inflight = page_pool_release(pool); + if (!inflight) + return; + + /* Periodic warning */ + if (time_after_eq(jiffies, pool->defer_warn)) { + int sec = (s32)((u32)jiffies - (u32)pool->defer_start) / HZ; + + pr_warn("%s() stalled pool shutdown %d inflight %d sec\n", + __func__, inflight, sec); + pool->defer_warn = jiffies + DEFER_WARN_INTERVAL; + } + + /* Still not ready to be disconnected, retry later */ + schedule_delayed_work(&pool->release_dw, DEFER_TIME); +} + +void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *)) +{ + refcount_inc(&pool->user_cnt); + pool->disconnect = disconnect; +} + +void page_pool_destroy(struct page_pool *pool) +{ + if (!pool) + return; + + if (!page_pool_put(pool)) + return; + + if (!page_pool_release(pool)) + return; + + pool->defer_start = jiffies; + pool->defer_warn = jiffies + DEFER_WARN_INTERVAL; - return __page_pool_safe_to_destroy(pool); + INIT_DELAYED_WORK(&pool->release_dw, page_pool_release_retry); + schedule_delayed_work(&pool->release_dw, DEFER_TIME); } -EXPORT_SYMBOL(__page_pool_request_shutdown); +EXPORT_SYMBOL(page_pool_destroy); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 867e61df00db..973a71f4bc89 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5484,7 +5484,7 @@ static void skb_mod_eth_type(struct sk_buff *skb, struct ethhdr *hdr, * Returns 0 on success, -errno otherwise. */ int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, - int mac_len) + int mac_len, bool ethernet) { struct mpls_shim_hdr *lse; int err; @@ -5515,7 +5515,7 @@ int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, lse->label_stack_entry = mpls_lse; skb_postpush_rcsum(skb, lse, MPLS_HLEN); - if (skb->dev && skb->dev->type == ARPHRD_ETHER) + if (ethernet) skb_mod_eth_type(skb, eth_hdr(skb), mpls_proto); skb->protocol = mpls_proto; @@ -5529,12 +5529,14 @@ EXPORT_SYMBOL_GPL(skb_mpls_push); * @skb: buffer * @next_proto: ethertype of header after popped MPLS header * @mac_len: length of the MAC header + * @ethernet: flag to indicate if ethernet header is present in packet * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ -int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len) +int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len, + bool ethernet) { int err; @@ -5553,7 +5555,7 @@ int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len) skb_reset_mac_header(skb); skb_set_network_header(skb, mac_len); - if (skb->dev && skb->dev->type == ARPHRD_ETHER) { + if (ethernet) { struct ethhdr *hdr; /* use mpls_hdr() to get ethertype to account for VLANs. */ diff --git a/net/core/skmsg.c b/net/core/skmsg.c index ad31e4e53d0a..ded2d5227678 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -421,7 +421,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) copied = skb->len; msg->sg.start = 0; msg->sg.size = copied; - msg->sg.end = num_sge == MAX_MSG_FRAGS ? 0 : num_sge; + msg->sg.end = num_sge; msg->skb = skb; sk_psock_queue_msg(psock, msg); @@ -793,15 +793,18 @@ static void sk_psock_strp_data_ready(struct sock *sk) static void sk_psock_write_space(struct sock *sk) { struct sk_psock *psock; - void (*write_space)(struct sock *sk); + void (*write_space)(struct sock *sk) = NULL; rcu_read_lock(); psock = sk_psock(sk); - if (likely(psock && sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))) - schedule_work(&psock->work); - write_space = psock->saved_write_space; + if (likely(psock)) { + if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) + schedule_work(&psock->work); + write_space = psock->saved_write_space; + } rcu_read_unlock(); - write_space(sk); + if (write_space) + write_space(sk); } int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock) diff --git a/net/core/sock.c b/net/core/sock.c index ac78a570e43a..b4d1112174c1 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2918,7 +2918,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_max_pacing_rate = ~0UL; sk->sk_pacing_rate = ~0UL; - sk->sk_pacing_shift = 10; + WRITE_ONCE(sk->sk_pacing_shift, 10); sk->sk_incoming_cpu = -1; sk_rx_queue_clear(sk); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index eb29e5adc84d..9f9e00ba3ad7 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -288,6 +288,7 @@ static int proc_dointvec_minmax_bpf_enable(struct ctl_table *table, int write, return ret; } +# ifdef CONFIG_HAVE_EBPF_JIT static int proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, @@ -298,6 +299,7 @@ proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write, return proc_dointvec_minmax(table, write, buffer, lenp, ppos); } +# endif /* CONFIG_HAVE_EBPF_JIT */ static int proc_dolongvec_minmax_bpf_restricted(struct ctl_table *table, int write, diff --git a/net/core/xdp.c b/net/core/xdp.c index d7bf62ffbb5e..b3f463c6543f 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -70,10 +70,6 @@ static void __xdp_mem_allocator_rcu_free(struct rcu_head *rcu) xa = container_of(rcu, struct xdp_mem_allocator, rcu); - /* Allocator have indicated safe to remove before this is called */ - if (xa->mem.type == MEM_TYPE_PAGE_POOL) - page_pool_free(xa->page_pool); - /* Allow this ID to be reused */ ida_simple_remove(&mem_id_pool, xa->mem.id); @@ -85,62 +81,57 @@ static void __xdp_mem_allocator_rcu_free(struct rcu_head *rcu) kfree(xa); } -static bool __mem_id_disconnect(int id, bool force) +static void mem_xa_remove(struct xdp_mem_allocator *xa) +{ + trace_mem_disconnect(xa); + + if (!rhashtable_remove_fast(mem_id_ht, &xa->node, mem_id_rht_params)) + call_rcu(&xa->rcu, __xdp_mem_allocator_rcu_free); +} + +static void mem_allocator_disconnect(void *allocator) { struct xdp_mem_allocator *xa; - bool safe_to_remove = true; + struct rhashtable_iter iter; mutex_lock(&mem_id_lock); - xa = rhashtable_lookup_fast(mem_id_ht, &id, mem_id_rht_params); - if (!xa) { - mutex_unlock(&mem_id_lock); - WARN(1, "Request remove non-existing id(%d), driver bug?", id); - return true; - } - xa->disconnect_cnt++; + rhashtable_walk_enter(mem_id_ht, &iter); + do { + rhashtable_walk_start(&iter); - /* Detects in-flight packet-pages for page_pool */ - if (xa->mem.type == MEM_TYPE_PAGE_POOL) - safe_to_remove = page_pool_request_shutdown(xa->page_pool); + while ((xa = rhashtable_walk_next(&iter)) && !IS_ERR(xa)) { + if (xa->allocator == allocator) + mem_xa_remove(xa); + } - trace_mem_disconnect(xa, safe_to_remove, force); + rhashtable_walk_stop(&iter); - if ((safe_to_remove || force) && - !rhashtable_remove_fast(mem_id_ht, &xa->node, mem_id_rht_params)) - call_rcu(&xa->rcu, __xdp_mem_allocator_rcu_free); + } while (xa == ERR_PTR(-EAGAIN)); + rhashtable_walk_exit(&iter); mutex_unlock(&mem_id_lock); - return (safe_to_remove|force); } -#define DEFER_TIME (msecs_to_jiffies(1000)) -#define DEFER_WARN_INTERVAL (30 * HZ) -#define DEFER_MAX_RETRIES 120 - -static void mem_id_disconnect_defer_retry(struct work_struct *wq) +static void mem_id_disconnect(int id) { - struct delayed_work *dwq = to_delayed_work(wq); - struct xdp_mem_allocator *xa = container_of(dwq, typeof(*xa), defer_wq); - bool force = false; + struct xdp_mem_allocator *xa; - if (xa->disconnect_cnt > DEFER_MAX_RETRIES) - force = true; + mutex_lock(&mem_id_lock); - if (__mem_id_disconnect(xa->mem.id, force)) + xa = rhashtable_lookup_fast(mem_id_ht, &id, mem_id_rht_params); + if (!xa) { + mutex_unlock(&mem_id_lock); + WARN(1, "Request remove non-existing id(%d), driver bug?", id); return; + } - /* Periodic warning */ - if (time_after_eq(jiffies, xa->defer_warn)) { - int sec = (s32)((u32)jiffies - (u32)xa->defer_start) / HZ; + trace_mem_disconnect(xa); - pr_warn("%s() stalled mem.id=%u shutdown %d attempts %d sec\n", - __func__, xa->mem.id, xa->disconnect_cnt, sec); - xa->defer_warn = jiffies + DEFER_WARN_INTERVAL; - } + if (!rhashtable_remove_fast(mem_id_ht, &xa->node, mem_id_rht_params)) + call_rcu(&xa->rcu, __xdp_mem_allocator_rcu_free); - /* Still not ready to be disconnected, retry later */ - schedule_delayed_work(&xa->defer_wq, DEFER_TIME); + mutex_unlock(&mem_id_lock); } void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) @@ -153,38 +144,21 @@ void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) return; } - if (xdp_rxq->mem.type != MEM_TYPE_PAGE_POOL && - xdp_rxq->mem.type != MEM_TYPE_ZERO_COPY) { - return; - } - if (id == 0) return; - if (__mem_id_disconnect(id, false)) - return; - - /* Could not disconnect, defer new disconnect attempt to later */ - mutex_lock(&mem_id_lock); + if (xdp_rxq->mem.type == MEM_TYPE_ZERO_COPY) + return mem_id_disconnect(id); - xa = rhashtable_lookup_fast(mem_id_ht, &id, mem_id_rht_params); - if (!xa) { - mutex_unlock(&mem_id_lock); - return; + if (xdp_rxq->mem.type == MEM_TYPE_PAGE_POOL) { + rcu_read_lock(); + xa = rhashtable_lookup(mem_id_ht, &id, mem_id_rht_params); + page_pool_destroy(xa->page_pool); + rcu_read_unlock(); } - xa->defer_start = jiffies; - xa->defer_warn = jiffies + DEFER_WARN_INTERVAL; - - INIT_DELAYED_WORK(&xa->defer_wq, mem_id_disconnect_defer_retry); - mutex_unlock(&mem_id_lock); - schedule_delayed_work(&xa->defer_wq, DEFER_TIME); } EXPORT_SYMBOL_GPL(xdp_rxq_info_unreg_mem_model); -/* This unregister operation will also cleanup and destroy the - * allocator. The page_pool_free() operation is first called when it's - * safe to remove, possibly deferred to a workqueue. - */ void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq) { /* Simplify driver cleanup code paths, allow unreg "unused" */ @@ -371,7 +345,7 @@ int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, } if (type == MEM_TYPE_PAGE_POOL) - page_pool_get(xdp_alloc->page_pool); + page_pool_use_xdp_mem(allocator, mem_allocator_disconnect); mutex_unlock(&mem_id_lock); @@ -402,15 +376,8 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, /* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */ xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params); page = virt_to_head_page(data); - if (likely(xa)) { - napi_direct &= !xdp_return_frame_no_direct(); - page_pool_put_page(xa->page_pool, page, napi_direct); - } else { - /* Hopefully stack show who to blame for late return */ - WARN_ONCE(1, "page_pool gone mem.id=%d", mem->id); - trace_mem_return_failed(mem, page); - put_page(page); - } + napi_direct &= !xdp_return_frame_no_direct(); + page_pool_put_page(xa->page_pool, page, napi_direct); rcu_read_unlock(); break; case MEM_TYPE_PAGE_SHARED: diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 25aab672fc99..1e5e08cc0bfc 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -210,7 +210,7 @@ static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final); rcu_read_unlock(); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; @@ -282,7 +282,7 @@ static void dccp_v6_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb) security_skb_classify_flow(rxskb, flowi6_to_flowi(&fl6)); /* sk = NULL, but it is safe for now. RST socket required. */ - dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL); + dst = ip6_dst_lookup_flow(sock_net(ctl_sk), ctl_sk, &fl6, NULL); if (!IS_ERR(dst)) { skb_dst_set(skb, dst); ip6_xmit(ctl_sk, skb, &fl6, 0, NULL, 0, 0); @@ -912,7 +912,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk)); final_p = fl6_update_dst(&fl6, opt, &final); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto failure; diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index aea918135ec3..08c3dc45f1a4 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -110,7 +110,8 @@ static void dn_dst_ifdown(struct dst_entry *, struct net_device *dev, int how); static struct dst_entry *dn_dst_negative_advice(struct dst_entry *); static void dn_dst_link_failure(struct sk_buff *); static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb , u32 mtu); + struct sk_buff *skb , u32 mtu, + bool confirm_neigh); static void dn_dst_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); static struct neighbour *dn_dst_neigh_lookup(const struct dst_entry *dst, @@ -251,7 +252,8 @@ static int dn_dst_gc(struct dst_ops *ops) * advertise to the other end). */ static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { struct dn_route *rt = (struct dn_route *) dst; struct neighbour *n = rt->n; diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 17374afee28f..9040fe55e0f5 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -244,7 +244,12 @@ int eth_header_cache(const struct neighbour *neigh, struct hh_cache *hh, __be16 eth->h_proto = type; memcpy(eth->h_source, dev->dev_addr, ETH_ALEN); memcpy(eth->h_dest, neigh->ha, ETH_ALEN); - hh->hh_len = ETH_HLEN; + + /* Pairs with READ_ONCE() in neigh_resolve_output(), + * neigh_hh_output() and neigh_update_hhs(). + */ + smp_store_release(&hh->hh_len, ETH_HLEN); + return 0; } EXPORT_SYMBOL(eth_header_cache); diff --git a/net/hsr/hsr_debugfs.c b/net/hsr/hsr_debugfs.c index 94447974a3c0..d5f709b940ff 100644 --- a/net/hsr/hsr_debugfs.c +++ b/net/hsr/hsr_debugfs.c @@ -20,6 +20,8 @@ #include "hsr_main.h" #include "hsr_framereg.h" +static struct dentry *hsr_debugfs_root_dir; + static void print_mac_address(struct seq_file *sfp, unsigned char *mac) { seq_printf(sfp, "%02x:%02x:%02x:%02x:%02x:%02x:", @@ -63,8 +65,20 @@ hsr_node_table_open(struct inode *inode, struct file *filp) return single_open(filp, hsr_node_table_show, inode->i_private); } +void hsr_debugfs_rename(struct net_device *dev) +{ + struct hsr_priv *priv = netdev_priv(dev); + struct dentry *d; + + d = debugfs_rename(hsr_debugfs_root_dir, priv->node_tbl_root, + hsr_debugfs_root_dir, dev->name); + if (IS_ERR(d)) + netdev_warn(dev, "failed to rename\n"); + else + priv->node_tbl_root = d; +} + static const struct file_operations hsr_fops = { - .owner = THIS_MODULE, .open = hsr_node_table_open, .read = seq_read, .llseek = seq_lseek, @@ -78,15 +92,14 @@ static const struct file_operations hsr_fops = { * When debugfs is configured this routine sets up the node_table file per * hsr device for dumping the node_table entries */ -int hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev) +void hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev) { - int rc = -1; struct dentry *de = NULL; - de = debugfs_create_dir(hsr_dev->name, NULL); - if (!de) { - pr_err("Cannot create hsr debugfs root\n"); - return rc; + de = debugfs_create_dir(hsr_dev->name, hsr_debugfs_root_dir); + if (IS_ERR(de)) { + pr_err("Cannot create hsr debugfs directory\n"); + return; } priv->node_tbl_root = de; @@ -94,13 +107,13 @@ int hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev) de = debugfs_create_file("node_table", S_IFREG | 0444, priv->node_tbl_root, priv, &hsr_fops); - if (!de) { - pr_err("Cannot create hsr node_table directory\n"); - return rc; + if (IS_ERR(de)) { + pr_err("Cannot create hsr node_table file\n"); + debugfs_remove(priv->node_tbl_root); + priv->node_tbl_root = NULL; + return; } priv->node_tbl_file = de; - - return 0; } /* hsr_debugfs_term - Tear down debugfs intrastructure @@ -117,3 +130,18 @@ hsr_debugfs_term(struct hsr_priv *priv) debugfs_remove(priv->node_tbl_root); priv->node_tbl_root = NULL; } + +void hsr_debugfs_create_root(void) +{ + hsr_debugfs_root_dir = debugfs_create_dir("hsr", NULL); + if (IS_ERR(hsr_debugfs_root_dir)) { + pr_err("Cannot create hsr debugfs root directory\n"); + hsr_debugfs_root_dir = NULL; + } +} + +void hsr_debugfs_remove_root(void) +{ + /* debugfs_remove() internally checks NULL and ERROR */ + debugfs_remove(hsr_debugfs_root_dir); +} diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index f509b495451a..c7bd6c49fadf 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -227,8 +227,13 @@ static int hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev) struct hsr_port *master; master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); - skb->dev = master->dev; - hsr_forward_skb(skb, master); + if (master) { + skb->dev = master->dev; + hsr_forward_skb(skb, master); + } else { + atomic_long_inc(&dev->tx_dropped); + dev_kfree_skb_any(skb); + } return NETDEV_TX_OK; } @@ -267,6 +272,8 @@ static void send_hsr_supervision_frame(struct hsr_port *master, skb->dev->dev_addr, skb->len) <= 0) goto out; skb_reset_mac_header(skb); + skb_reset_network_header(skb); + skb_reset_transport_header(skb); if (hsr_ver > 0) { hsr_tag = skb_put(skb, sizeof(struct hsr_tag)); @@ -363,7 +370,7 @@ static void hsr_dev_destroy(struct net_device *hsr_dev) del_timer_sync(&hsr->prune_timer); del_timer_sync(&hsr->announce_timer); - hsr_del_self_node(&hsr->self_node_db); + hsr_del_self_node(hsr); hsr_del_nodes(&hsr->node_db); } @@ -435,11 +442,12 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], INIT_LIST_HEAD(&hsr->ports); INIT_LIST_HEAD(&hsr->node_db); INIT_LIST_HEAD(&hsr->self_node_db); + spin_lock_init(&hsr->list_lock); ether_addr_copy(hsr_dev->dev_addr, slave[0]->dev_addr); /* Make sure we recognize frames from ourselves in hsr_rcv() */ - res = hsr_create_self_node(&hsr->self_node_db, hsr_dev->dev_addr, + res = hsr_create_self_node(hsr, hsr_dev->dev_addr, slave[1]->dev_addr); if (res < 0) return res; @@ -472,31 +480,32 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], res = hsr_add_port(hsr, hsr_dev, HSR_PT_MASTER); if (res) - goto err_add_port; + goto err_add_master; res = register_netdevice(hsr_dev); if (res) - goto fail; + goto err_unregister; res = hsr_add_port(hsr, slave[0], HSR_PT_SLAVE_A); if (res) - goto fail; + goto err_add_slaves; + res = hsr_add_port(hsr, slave[1], HSR_PT_SLAVE_B); if (res) - goto fail; + goto err_add_slaves; + hsr_debugfs_init(hsr, hsr_dev); mod_timer(&hsr->prune_timer, jiffies + msecs_to_jiffies(PRUNE_PERIOD)); - res = hsr_debugfs_init(hsr, hsr_dev); - if (res) - goto fail; return 0; -fail: +err_add_slaves: + unregister_netdevice(hsr_dev); +err_unregister: list_for_each_entry_safe(port, tmp, &hsr->ports, port_list) hsr_del_port(port); -err_add_port: - hsr_del_self_node(&hsr->self_node_db); +err_add_master: + hsr_del_self_node(hsr); return res; } diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 292be446007b..27dc65d7de67 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -75,10 +75,11 @@ static struct hsr_node *find_node_by_addr_A(struct list_head *node_db, /* Helper for device init; the self_node_db is used in hsr_rcv() to recognize * frames from self that's been looped over the HSR ring. */ -int hsr_create_self_node(struct list_head *self_node_db, +int hsr_create_self_node(struct hsr_priv *hsr, unsigned char addr_a[ETH_ALEN], unsigned char addr_b[ETH_ALEN]) { + struct list_head *self_node_db = &hsr->self_node_db; struct hsr_node *node, *oldnode; node = kmalloc(sizeof(*node), GFP_KERNEL); @@ -88,33 +89,33 @@ int hsr_create_self_node(struct list_head *self_node_db, ether_addr_copy(node->macaddress_A, addr_a); ether_addr_copy(node->macaddress_B, addr_b); - rcu_read_lock(); + spin_lock_bh(&hsr->list_lock); oldnode = list_first_or_null_rcu(self_node_db, struct hsr_node, mac_list); if (oldnode) { list_replace_rcu(&oldnode->mac_list, &node->mac_list); - rcu_read_unlock(); - synchronize_rcu(); - kfree(oldnode); + spin_unlock_bh(&hsr->list_lock); + kfree_rcu(oldnode, rcu_head); } else { - rcu_read_unlock(); list_add_tail_rcu(&node->mac_list, self_node_db); + spin_unlock_bh(&hsr->list_lock); } return 0; } -void hsr_del_self_node(struct list_head *self_node_db) +void hsr_del_self_node(struct hsr_priv *hsr) { + struct list_head *self_node_db = &hsr->self_node_db; struct hsr_node *node; - rcu_read_lock(); + spin_lock_bh(&hsr->list_lock); node = list_first_or_null_rcu(self_node_db, struct hsr_node, mac_list); - rcu_read_unlock(); if (node) { list_del_rcu(&node->mac_list); - kfree(node); + kfree_rcu(node, rcu_head); } + spin_unlock_bh(&hsr->list_lock); } void hsr_del_nodes(struct list_head *node_db) @@ -130,30 +131,43 @@ void hsr_del_nodes(struct list_head *node_db) * seq_out is used to initialize filtering of outgoing duplicate frames * originating from the newly added node. */ -struct hsr_node *hsr_add_node(struct list_head *node_db, unsigned char addr[], - u16 seq_out) +static struct hsr_node *hsr_add_node(struct hsr_priv *hsr, + struct list_head *node_db, + unsigned char addr[], + u16 seq_out) { - struct hsr_node *node; + struct hsr_node *new_node, *node; unsigned long now; int i; - node = kzalloc(sizeof(*node), GFP_ATOMIC); - if (!node) + new_node = kzalloc(sizeof(*new_node), GFP_ATOMIC); + if (!new_node) return NULL; - ether_addr_copy(node->macaddress_A, addr); + ether_addr_copy(new_node->macaddress_A, addr); /* We are only interested in time diffs here, so use current jiffies * as initialization. (0 could trigger an spurious ring error warning). */ now = jiffies; for (i = 0; i < HSR_PT_PORTS; i++) - node->time_in[i] = now; + new_node->time_in[i] = now; for (i = 0; i < HSR_PT_PORTS; i++) - node->seq_out[i] = seq_out; - - list_add_tail_rcu(&node->mac_list, node_db); + new_node->seq_out[i] = seq_out; + spin_lock_bh(&hsr->list_lock); + list_for_each_entry_rcu(node, node_db, mac_list) { + if (ether_addr_equal(node->macaddress_A, addr)) + goto out; + if (ether_addr_equal(node->macaddress_B, addr)) + goto out; + } + list_add_tail_rcu(&new_node->mac_list, node_db); + spin_unlock_bh(&hsr->list_lock); + return new_node; +out: + spin_unlock_bh(&hsr->list_lock); + kfree(new_node); return node; } @@ -163,6 +177,7 @@ struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb, bool is_sup) { struct list_head *node_db = &port->hsr->node_db; + struct hsr_priv *hsr = port->hsr; struct hsr_node *node; struct ethhdr *ethhdr; u16 seq_out; @@ -196,7 +211,7 @@ struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb, seq_out = HSR_SEQNR_START; } - return hsr_add_node(node_db, ethhdr->h_source, seq_out); + return hsr_add_node(hsr, node_db, ethhdr->h_source, seq_out); } /* Use the Supervision frame's info about an eventual macaddress_B for merging @@ -206,10 +221,11 @@ struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb, void hsr_handle_sup_frame(struct sk_buff *skb, struct hsr_node *node_curr, struct hsr_port *port_rcv) { - struct ethhdr *ethhdr; - struct hsr_node *node_real; + struct hsr_priv *hsr = port_rcv->hsr; struct hsr_sup_payload *hsr_sp; + struct hsr_node *node_real; struct list_head *node_db; + struct ethhdr *ethhdr; int i; ethhdr = (struct ethhdr *)skb_mac_header(skb); @@ -231,7 +247,7 @@ void hsr_handle_sup_frame(struct sk_buff *skb, struct hsr_node *node_curr, node_real = find_node_by_addr_A(node_db, hsr_sp->macaddress_A); if (!node_real) /* No frame received from AddrA of this node yet */ - node_real = hsr_add_node(node_db, hsr_sp->macaddress_A, + node_real = hsr_add_node(hsr, node_db, hsr_sp->macaddress_A, HSR_SEQNR_START - 1); if (!node_real) goto done; /* No mem */ @@ -252,7 +268,9 @@ void hsr_handle_sup_frame(struct sk_buff *skb, struct hsr_node *node_curr, } node_real->addr_B_port = port_rcv->type; + spin_lock_bh(&hsr->list_lock); list_del_rcu(&node_curr->mac_list); + spin_unlock_bh(&hsr->list_lock); kfree_rcu(node_curr, rcu_head); done: @@ -368,12 +386,13 @@ void hsr_prune_nodes(struct timer_list *t) { struct hsr_priv *hsr = from_timer(hsr, t, prune_timer); struct hsr_node *node; + struct hsr_node *tmp; struct hsr_port *port; unsigned long timestamp; unsigned long time_a, time_b; - rcu_read_lock(); - list_for_each_entry_rcu(node, &hsr->node_db, mac_list) { + spin_lock_bh(&hsr->list_lock); + list_for_each_entry_safe(node, tmp, &hsr->node_db, mac_list) { /* Don't prune own node. Neither time_in[HSR_PT_SLAVE_A] * nor time_in[HSR_PT_SLAVE_B], will ever be updated for * the master port. Thus the master node will be repeatedly @@ -421,7 +440,7 @@ void hsr_prune_nodes(struct timer_list *t) kfree_rcu(node, rcu_head); } } - rcu_read_unlock(); + spin_unlock_bh(&hsr->list_lock); /* Restart timer */ mod_timer(&hsr->prune_timer, diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h index 89a3ce38151d..0f0fa12b4329 100644 --- a/net/hsr/hsr_framereg.h +++ b/net/hsr/hsr_framereg.h @@ -12,10 +12,8 @@ struct hsr_node; -void hsr_del_self_node(struct list_head *self_node_db); +void hsr_del_self_node(struct hsr_priv *hsr); void hsr_del_nodes(struct list_head *node_db); -struct hsr_node *hsr_add_node(struct list_head *node_db, unsigned char addr[], - u16 seq_out); struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb, bool is_sup); void hsr_handle_sup_frame(struct sk_buff *skb, struct hsr_node *node_curr, @@ -33,7 +31,7 @@ int hsr_register_frame_out(struct hsr_port *port, struct hsr_node *node, void hsr_prune_nodes(struct timer_list *t); -int hsr_create_self_node(struct list_head *self_node_db, +int hsr_create_self_node(struct hsr_priv *hsr, unsigned char addr_a[ETH_ALEN], unsigned char addr_b[ETH_ALEN]); diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c index b9988a662ee1..9e389accbfc7 100644 --- a/net/hsr/hsr_main.c +++ b/net/hsr/hsr_main.c @@ -45,6 +45,10 @@ static int hsr_netdev_notify(struct notifier_block *nb, unsigned long event, case NETDEV_CHANGE: /* Link (carrier) state changes */ hsr_check_carrier_and_operstate(hsr); break; + case NETDEV_CHANGENAME: + if (is_hsr_master(dev)) + hsr_debugfs_rename(dev); + break; case NETDEV_CHANGEADDR: if (port->type == HSR_PT_MASTER) { /* This should not happen since there's no @@ -64,7 +68,7 @@ static int hsr_netdev_notify(struct notifier_block *nb, unsigned long event, /* Make sure we recognize frames from ourselves in hsr_rcv() */ port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); - res = hsr_create_self_node(&hsr->self_node_db, + res = hsr_create_self_node(hsr, master->dev->dev_addr, port ? port->dev->dev_addr : @@ -123,6 +127,7 @@ static void __exit hsr_exit(void) { unregister_netdevice_notifier(&hsr_nb); hsr_netlink_exit(); + hsr_debugfs_remove_root(); } module_init(hsr_init); diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index 96fac696a1e1..d40de84a637f 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -160,8 +160,9 @@ struct hsr_priv { int announce_count; u16 sequence_nr; u16 sup_sequence_nr; /* For HSRv1 separate seq_nr for supervision */ - u8 prot_version; /* Indicate if HSRv0 or HSRv1. */ - spinlock_t seqnr_lock; /* locking for sequence_nr */ + u8 prot_version; /* Indicate if HSRv0 or HSRv1. */ + spinlock_t seqnr_lock; /* locking for sequence_nr */ + spinlock_t list_lock; /* locking for node list */ unsigned char sup_multicast_addr[ETH_ALEN]; #ifdef CONFIG_DEBUG_FS struct dentry *node_tbl_root; @@ -184,17 +185,24 @@ static inline u16 hsr_get_skb_sequence_nr(struct sk_buff *skb) } #if IS_ENABLED(CONFIG_DEBUG_FS) -int hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev); +void hsr_debugfs_rename(struct net_device *dev); +void hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev); void hsr_debugfs_term(struct hsr_priv *priv); +void hsr_debugfs_create_root(void); +void hsr_debugfs_remove_root(void); #else -static inline int hsr_debugfs_init(struct hsr_priv *priv, - struct net_device *hsr_dev) +static inline void void hsr_debugfs_rename(struct net_device *dev) { - return 0; } - +static inline void hsr_debugfs_init(struct hsr_priv *priv, + struct net_device *hsr_dev) +{} static inline void hsr_debugfs_term(struct hsr_priv *priv) {} +static inline void hsr_debugfs_create_root(void) +{} +static inline void hsr_debugfs_remove_root(void) +{} #endif #endif /* __HSR_PRIVATE_H */ diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index 8f8337f893ba..8dc0547f01d0 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -476,6 +476,7 @@ int __init hsr_netlink_init(void) if (rc) goto fail_genl_register_family; + hsr_debugfs_create_root(); return 0; fail_genl_register_family: diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index a4b5bd4d2c89..e4632bd2026d 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1496,11 +1496,6 @@ static void inetdev_changename(struct net_device *dev, struct in_device *in_dev) } } -static bool inetdev_valid_mtu(unsigned int mtu) -{ - return mtu >= IPV4_MIN_MTU; -} - static void inetdev_send_gratuitous_arp(struct net_device *dev, struct in_device *in_dev) diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c index 44bfeecac33e..5fd6e8ed02b5 100644 --- a/net/ipv4/gre_demux.c +++ b/net/ipv4/gre_demux.c @@ -127,7 +127,7 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, if (!pskb_may_pull(skb, nhs + hdr_len + sizeof(*ershdr))) return -EINVAL; - ershdr = (struct erspan_base_hdr *)options; + ershdr = (struct erspan_base_hdr *)(skb->data + nhs + hdr_len); tpi->key = cpu_to_be32(get_session_id(ershdr)); } diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 4298aae74e0e..ac95ba78b903 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -249,10 +249,11 @@ bool icmp_global_allow(void) bool rc = false; /* Check if token bucket is empty and cannot be refilled - * without taking the spinlock. + * without taking the spinlock. The READ_ONCE() are paired + * with the following WRITE_ONCE() in this same function. */ - if (!icmp_global.credit) { - delta = min_t(u32, now - icmp_global.stamp, HZ); + if (!READ_ONCE(icmp_global.credit)) { + delta = min_t(u32, now - READ_ONCE(icmp_global.stamp), HZ); if (delta < HZ / 50) return false; } @@ -262,14 +263,14 @@ bool icmp_global_allow(void) if (delta >= HZ / 50) { incr = sysctl_icmp_msgs_per_sec * delta / HZ ; if (incr) - icmp_global.stamp = now; + WRITE_ONCE(icmp_global.stamp, now); } credit = min_t(u32, icmp_global.credit + incr, sysctl_icmp_msgs_burst); if (credit) { credit--; rc = true; } - icmp_global.credit = credit; + WRITE_ONCE(icmp_global.credit, credit); spin_unlock(&icmp_global.lock); return rc; } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index eb30fc1770de..ac05e273bc66 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1086,7 +1086,7 @@ struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu) if (!dst) goto out; } - dst->ops->update_pmtu(dst, sk, NULL, mtu); + dst->ops->update_pmtu(dst, sk, NULL, mtu, true); dst = __sk_dst_check(sk, 0); if (!dst) diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 7dc79b973e6e..6a4c82f96e78 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -914,11 +914,12 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, for (i = s_i; i < INET_LHTABLE_SIZE; i++) { struct inet_listen_hashbucket *ilb; + struct hlist_nulls_node *node; num = 0; ilb = &hashinfo->listening_hash[i]; spin_lock(&ilb->lock); - sk_for_each(sk, &ilb->head) { + sk_nulls_for_each(sk, node, &ilb->nulls_head) { struct inet_sock *inet = inet_sk(sk); if (!net_eq(sock_net(sk), net)) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 83fb00153018..2bbaaf0c7176 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -516,10 +516,11 @@ static int inet_reuseport_add_sock(struct sock *sk, struct inet_listen_hashbucket *ilb) { struct inet_bind_bucket *tb = inet_csk(sk)->icsk_bind_hash; + const struct hlist_nulls_node *node; struct sock *sk2; kuid_t uid = sock_i_uid(sk); - sk_for_each_rcu(sk2, &ilb->head) { + sk_nulls_for_each_rcu(sk2, node, &ilb->nulls_head) { if (sk2 != sk && sk2->sk_family == sk->sk_family && ipv6_only_sock(sk2) == ipv6_only_sock(sk) && @@ -555,9 +556,9 @@ int __inet_hash(struct sock *sk, struct sock *osk) } if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport && sk->sk_family == AF_INET6) - hlist_add_tail_rcu(&sk->sk_node, &ilb->head); + __sk_nulls_add_node_tail_rcu(sk, &ilb->nulls_head); else - hlist_add_head_rcu(&sk->sk_node, &ilb->head); + __sk_nulls_add_node_rcu(sk, &ilb->nulls_head); inet_hash2(hashinfo, sk); ilb->count++; sock_set_flag(sk, SOCK_RCU_FREE); @@ -606,11 +607,9 @@ void inet_unhash(struct sock *sk) reuseport_detach_sock(sk); if (ilb) { inet_unhash2(hashinfo, sk); - __sk_del_node_init(sk); - ilb->count--; - } else { - __sk_nulls_del_node_init_rcu(sk); + ilb->count--; } + __sk_nulls_del_node_init_rcu(sk); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); unlock: spin_unlock_bh(lock); @@ -750,7 +749,8 @@ void inet_hashinfo_init(struct inet_hashinfo *h) for (i = 0; i < INET_LHTABLE_SIZE; i++) { spin_lock_init(&h->listening_hash[i].lock); - INIT_HLIST_HEAD(&h->listening_hash[i].head); + INIT_HLIST_NULLS_HEAD(&h->listening_hash[i].nulls_head, + i + LISTENING_NULLS_BASE); h->listening_hash[i].count = 0; } diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index be778599bfed..ff327a62c9ce 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -160,7 +160,12 @@ static void inet_peer_gc(struct inet_peer_base *base, base->total / inet_peer_threshold * HZ; for (i = 0; i < gc_cnt; i++) { p = gc_stack[i]; - delta = (__u32)jiffies - p->dtime; + + /* The READ_ONCE() pairs with the WRITE_ONCE() + * in inet_putpeer() + */ + delta = (__u32)jiffies - READ_ONCE(p->dtime); + if (delta < ttl || !refcount_dec_if_one(&p->refcnt)) gc_stack[i] = NULL; } @@ -237,7 +242,10 @@ EXPORT_SYMBOL_GPL(inet_getpeer); void inet_putpeer(struct inet_peer *p) { - p->dtime = (__u32)jiffies; + /* The WRITE_ONCE() pairs with itself (we run lockless) + * and the READ_ONCE() in inet_peer_gc() + */ + WRITE_ONCE(p->dtime, (__u32)jiffies); if (refcount_dec_and_test(&p->refcnt)) call_rcu(&p->rcu, inetpeer_free_rcu); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 3d8baaaf7086..b268ee1c1b44 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1258,15 +1258,18 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, cork->addr = ipc->addr; } - /* - * We steal reference to this route, caller should not release it - */ - *rtp = NULL; cork->fragsize = ip_sk_use_pmtu(sk) ? - dst_mtu(&rt->dst) : rt->dst.dev->mtu; + dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu); + + if (!inetdev_valid_mtu(cork->fragsize)) + return -ENETUNREACH; cork->gso_size = ipc->gso_size; + cork->dst = &rt->dst; + /* We stole this route, caller should not release it. */ + *rtp = NULL; + cork->length = 0; cork->ttl = ipc->ttl; cork->tos = ipc->tos; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 38c02bb62e2c..0fe2a5d3e258 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -505,7 +505,7 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; if (skb_valid_dst(skb)) - skb_dst_update_pmtu(skb, mtu); + skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IP)) { if (!skb_is_gso(skb) && diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index cfb025606793..fb9f6d60c27c 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -214,7 +214,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, mtu = dst_mtu(dst); if (skb->len > mtu) { - skb_dst_update_pmtu(skb, mtu); + skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IP)) { icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 214154b47d56..069f72edb264 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -384,10 +384,11 @@ next: ; return 1; } -static inline int check_target(struct arpt_entry *e, const char *name) +static int check_target(struct arpt_entry *e, struct net *net, const char *name) { struct xt_entry_target *t = arpt_get_target(e); struct xt_tgchk_param par = { + .net = net, .table = name, .entryinfo = e, .target = t->u.kernel.target, @@ -399,8 +400,9 @@ static inline int check_target(struct arpt_entry *e, const char *name) return xt_check_target(&par, t->u.target_size - sizeof(*t), 0, false); } -static inline int -find_check_entry(struct arpt_entry *e, const char *name, unsigned int size, +static int +find_check_entry(struct arpt_entry *e, struct net *net, const char *name, + unsigned int size, struct xt_percpu_counter_alloc_state *alloc_state) { struct xt_entry_target *t; @@ -419,7 +421,7 @@ find_check_entry(struct arpt_entry *e, const char *name, unsigned int size, } t->u.kernel.target = target; - ret = check_target(e, name); + ret = check_target(e, net, name); if (ret) goto err; return 0; @@ -512,7 +514,9 @@ static inline void cleanup_entry(struct arpt_entry *e) /* Checks and translates the user-supplied table segment (held in * newinfo). */ -static int translate_table(struct xt_table_info *newinfo, void *entry0, +static int translate_table(struct net *net, + struct xt_table_info *newinfo, + void *entry0, const struct arpt_replace *repl) { struct xt_percpu_counter_alloc_state alloc_state = { 0 }; @@ -569,7 +573,7 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0, /* Finally, each sanity check must pass */ i = 0; xt_entry_foreach(iter, entry0, newinfo->size) { - ret = find_check_entry(iter, repl->name, repl->size, + ret = find_check_entry(iter, net, repl->name, repl->size, &alloc_state); if (ret != 0) break; @@ -974,7 +978,7 @@ static int do_replace(struct net *net, const void __user *user, goto free_newinfo; } - ret = translate_table(newinfo, loc_cpu_entry, &tmp); + ret = translate_table(net, newinfo, loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; @@ -1149,7 +1153,8 @@ compat_copy_entry_from_user(struct compat_arpt_entry *e, void **dstptr, } } -static int translate_compat_table(struct xt_table_info **pinfo, +static int translate_compat_table(struct net *net, + struct xt_table_info **pinfo, void **pentry0, const struct compat_arpt_replace *compatr) { @@ -1217,7 +1222,7 @@ static int translate_compat_table(struct xt_table_info **pinfo, repl.num_counters = 0; repl.counters = NULL; repl.size = newinfo->size; - ret = translate_table(newinfo, entry1, &repl); + ret = translate_table(net, newinfo, entry1, &repl); if (ret) goto free_newinfo; @@ -1270,7 +1275,7 @@ static int compat_do_replace(struct net *net, void __user *user, goto free_newinfo; } - ret = translate_compat_table(&newinfo, &loc_cpu_entry, &tmp); + ret = translate_compat_table(net, &newinfo, &loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; @@ -1546,7 +1551,7 @@ int arpt_register_table(struct net *net, loc_cpu_entry = newinfo->entries; memcpy(loc_cpu_entry, repl->entries, repl->size); - ret = translate_table(newinfo, loc_cpu_entry, repl); + ret = translate_table(net, newinfo, loc_cpu_entry, repl); if (ret != 0) goto out_free; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 621f83434b24..fe34e9e0912a 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -139,7 +139,8 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst); static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu); + struct sk_buff *skb, u32 mtu, + bool confirm_neigh); static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); static void ipv4_dst_destroy(struct dst_entry *dst); @@ -1043,7 +1044,8 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) } static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { struct rtable *rt = (struct rtable *) dst; struct flowi4 fl4; @@ -2648,7 +2650,8 @@ static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst) } static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index d8876f0e9672..e537a4b6531b 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1958,8 +1958,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, struct sk_buff *skb, *last; u32 urg_hole = 0; struct scm_timestamping_internal tss; - bool has_tss = false; - bool has_cmsg; + int cmsg_flags; if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); @@ -1974,7 +1973,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, if (sk->sk_state == TCP_LISTEN) goto out; - has_cmsg = tp->recvmsg_inq; + cmsg_flags = tp->recvmsg_inq ? 1 : 0; timeo = sock_rcvtimeo(sk, nonblock); /* Urgent data needs to be handled specially. */ @@ -2157,8 +2156,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, if (TCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, &tss); - has_tss = true; - has_cmsg = true; + cmsg_flags |= 2; } if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) goto found_fin_ok; @@ -2183,10 +2181,10 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, release_sock(sk); - if (has_cmsg) { - if (has_tss) + if (cmsg_flags) { + if (cmsg_flags & 2) tcp_recv_timestamp(msg, sk, &tss); - if (tp->recvmsg_inq) { + if (cmsg_flags & 1) { inq = tcp_inq_hint(sk); put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(inq), &inq); } diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 32772d6ded4e..a6545ef0d27b 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -306,7 +306,8 @@ static u32 bbr_tso_segs_goal(struct sock *sk) /* Sort of tcp_tso_autosize() but ignoring * driver provided sk_gso_max_size. */ - bytes = min_t(unsigned long, sk->sk_pacing_rate >> sk->sk_pacing_shift, + bytes = min_t(unsigned long, + sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift), GSO_MAX_SIZE - 1 - MAX_TCP_HEADER); segs = max_t(u32, bytes / tp->mss_cache, bbr_min_tso_segs(sk)); diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 8a56e09cfb0e..e38705165ac9 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -301,7 +301,7 @@ EXPORT_SYMBOL_GPL(tcp_bpf_sendmsg_redir); static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock, struct sk_msg *msg, int *copied, int flags) { - bool cork = false, enospc = msg->sg.start == msg->sg.end; + bool cork = false, enospc = sk_msg_full(msg); struct sock *sk_redir; u32 tosend, delta = 0; int ret; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index a2e52ad7cdab..67e44e6717b0 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1727,8 +1727,11 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, } /* Ignore very old stuff early */ - if (!after(sp[used_sacks].end_seq, prior_snd_una)) + if (!after(sp[used_sacks].end_seq, prior_snd_una)) { + if (i == 0) + first_sack_index = -1; continue; + } used_sacks++; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 67b2dc7a1727..eda64871f983 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2149,13 +2149,14 @@ static void *listening_get_next(struct seq_file *seq, void *cur) struct tcp_iter_state *st = seq->private; struct net *net = seq_file_net(seq); struct inet_listen_hashbucket *ilb; + struct hlist_nulls_node *node; struct sock *sk = cur; if (!sk) { get_head: ilb = &tcp_hashinfo.listening_hash[st->bucket]; spin_lock(&ilb->lock); - sk = sk_head(&ilb->head); + sk = sk_nulls_head(&ilb->nulls_head); st->offset = 0; goto get_sk; } @@ -2163,9 +2164,9 @@ static void *listening_get_next(struct seq_file *seq, void *cur) ++st->num; ++st->offset; - sk = sk_next(sk); + sk = sk_nulls_next(sk); get_sk: - sk_for_each_from(sk) { + sk_nulls_for_each_from(sk, node) { if (!net_eq(sock_net(sk), net)) continue; if (sk->sk_family == afinfo->family) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 0488607c5cd3..e4ba915c4bb5 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -72,6 +72,9 @@ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) __skb_unlink(skb, &sk->sk_write_queue); tcp_rbtree_insert(&sk->tcp_rtx_queue, skb); + if (tp->highest_sack == NULL) + tp->highest_sack = skb; + tp->packets_out += tcp_skb_pcount(skb); if (!prior_packets || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) tcp_rearm_rto(sk); @@ -755,8 +758,9 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb min_t(unsigned int, eff_sacks, (remaining - TCPOLEN_SACK_BASE_ALIGNED) / TCPOLEN_SACK_PERBLOCK); - size += TCPOLEN_SACK_BASE_ALIGNED + - opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK; + if (likely(opts->num_sack_blocks)) + size += TCPOLEN_SACK_BASE_ALIGNED + + opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK; } return size; @@ -1724,7 +1728,7 @@ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, u32 bytes, segs; bytes = min_t(unsigned long, - sk->sk_pacing_rate >> sk->sk_pacing_shift, + sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift), sk->sk_gso_max_size - 1 - MAX_TCP_HEADER); /* Goal is to send at least one packet per ms, @@ -2259,7 +2263,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, limit = max_t(unsigned long, 2 * skb->truesize, - sk->sk_pacing_rate >> sk->sk_pacing_shift); + sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift)); if (sk->sk_pacing_status == SK_PACING_NONE) limit = min_t(unsigned long, limit, sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes); @@ -2437,6 +2441,14 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (tcp_small_queue_check(sk, skb, 0)) break; + /* Argh, we hit an empty skb(), presumably a thread + * is sleeping in sendmsg()/sk_stream_wait_memory(). + * We do not want to send a pure-ack packet and have + * a strange looking rtx queue with empty packet(s). + */ + if (TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq) + break; + if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp))) break; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 447defbfccdd..7aa4e77161f6 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1475,7 +1475,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) * queue contains some other skb */ rmem = atomic_add_return(size, &sk->sk_rmem_alloc); - if (rmem > (size + sk->sk_rcvbuf)) + if (rmem > (size + (unsigned int)sk->sk_rcvbuf)) goto uncharge_drop; spin_lock(&list->lock); diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 35b84b52b702..9ebd54752e03 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -100,12 +100,13 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, } static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct dst_entry *path = xdst->route; - path->ops->update_pmtu(path, sk, skb, mtu); + path->ops->update_pmtu(path, sk, skb, mtu, confirm_neigh); } static void xfrm4_redirect(struct dst_entry *dst, struct sock *sk, diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 34ccef18b40e..f9b5690e94fd 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5231,16 +5231,16 @@ static int inet6_rtm_valid_getaddr_req(struct sk_buff *skb, return -EINVAL; } + if (!netlink_strict_get_check(skb)) + return nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, + ifa_ipv6_policy, extack); + ifm = nlmsg_data(nlh); if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) { NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for get address request"); return -EINVAL; } - if (!netlink_strict_get_check(skb)) - return nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, - ifa_ipv6_policy, extack); - err = nlmsg_parse_deprecated_strict(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy, extack); if (err) diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index 2fc079284ca4..ea00ce3d4117 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -129,11 +129,12 @@ int inet6addr_validator_notifier_call_chain(unsigned long val, void *v) } EXPORT_SYMBOL(inet6addr_validator_notifier_call_chain); -static int eafnosupport_ipv6_dst_lookup(struct net *net, struct sock *u1, - struct dst_entry **u2, - struct flowi6 *u3) +static struct dst_entry *eafnosupport_ipv6_dst_lookup_flow(struct net *net, + const struct sock *sk, + struct flowi6 *fl6, + const struct in6_addr *final_dst) { - return -EAFNOSUPPORT; + return ERR_PTR(-EAFNOSUPPORT); } static int eafnosupport_ipv6_route_input(struct sk_buff *skb) @@ -190,7 +191,7 @@ static int eafnosupport_ip6_del_rt(struct net *net, struct fib6_info *rt) } const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) { - .ipv6_dst_lookup = eafnosupport_ipv6_dst_lookup, + .ipv6_dst_lookup_flow = eafnosupport_ipv6_dst_lookup_flow, .ipv6_route_input = eafnosupport_ipv6_route_input, .fib6_get_table = eafnosupport_fib6_get_table, .fib6_table_lookup = eafnosupport_fib6_table_lookup, diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index ef37e0574f54..14ac1d911287 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -765,7 +765,7 @@ int inet6_sk_rebuild_header(struct sock *sk) &final); rcu_read_unlock(); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { sk->sk_route_caps = 0; sk->sk_err_soft = -PTR_ERR(dst); @@ -946,7 +946,7 @@ static int ipv6_route_input(struct sk_buff *skb) static const struct ipv6_stub ipv6_stub_impl = { .ipv6_sock_mc_join = ipv6_sock_mc_join, .ipv6_sock_mc_drop = ipv6_sock_mc_drop, - .ipv6_dst_lookup = ip6_dst_lookup, + .ipv6_dst_lookup_flow = ip6_dst_lookup_flow, .ipv6_route_input = ipv6_route_input, .fib6_get_table = fib6_get_table, .fib6_table_lookup = fib6_table_lookup, diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 96f939248d2f..390bedde21a5 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -85,7 +85,7 @@ int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr) final_p = fl6_update_dst(&fl6, opt, &final); rcu_read_unlock(); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto out; diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 0a0945a5b30d..e315526fa244 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -48,7 +48,7 @@ struct dst_entry *inet6_csk_route_req(const struct sock *sk, fl6->flowi6_uid = sk->sk_uid; security_req_classify_flow(req, flowi6_to_flowi(fl6)); - dst = ip6_dst_lookup_flow(sk, fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p); if (IS_ERR(dst)) return NULL; @@ -103,7 +103,7 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk, dst = __inet6_csk_dst_check(sk, np->dst_cookie); if (!dst) { - dst = ip6_dst_lookup_flow(sk, fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p); if (!IS_ERR(dst)) ip6_dst_store(sk, dst, NULL, NULL); @@ -146,7 +146,7 @@ struct dst_entry *inet6_csk_update_pmtu(struct sock *sk, u32 mtu) if (IS_ERR(dst)) return NULL; - dst->ops->update_pmtu(dst, sk, NULL, mtu); + dst->ops->update_pmtu(dst, sk, NULL, mtu, true); dst = inet6_csk_route_socket(sk, &fl6); return IS_ERR(dst) ? NULL : dst; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 923034c52ce4..189de56f5e36 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1040,7 +1040,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, /* TooBig packet may have updated dst->dev's mtu */ if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu) - dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu); + dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu, false); err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu, NEXTHDR_GRE); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 71827b56c006..78d495581d69 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1144,19 +1144,19 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup); * It returns a valid dst pointer on success, or a pointer encoded * error code. */ -struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6, +struct dst_entry *ip6_dst_lookup_flow(struct net *net, const struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst) { struct dst_entry *dst = NULL; int err; - err = ip6_dst_lookup_tail(sock_net(sk), sk, &dst, fl6); + err = ip6_dst_lookup_tail(net, sk, &dst, fl6); if (err) return ERR_PTR(err); if (final_dst) fl6->daddr = *final_dst; - return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); + return xfrm_lookup_route(net, dst, flowi6_to_flowi(fl6), sk, 0); } EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow); @@ -1188,7 +1188,7 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, if (dst) return dst; - dst = ip6_dst_lookup_flow(sk, fl6, final_dst); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_dst); if (connected && !IS_ERR(dst)) ip6_sk_dst_store_flow(sk, dst_clone(dst), fl6); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 754a484d35df..2f376dbc37d5 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -640,7 +640,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (rel_info > dst_mtu(skb_dst(skb2))) goto out; - skb_dst_update_pmtu(skb2, rel_info); + skb_dst_update_pmtu_no_confirm(skb2, rel_info); } icmp_send(skb2, rel_type, rel_code, htonl(rel_info)); @@ -1132,7 +1132,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, mtu = max(mtu, skb->protocol == htons(ETH_P_IPV6) ? IPV6_MIN_MTU : IPV4_MIN_MTU); - skb_dst_update_pmtu(skb, mtu); + skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->len - t->tun_hlen - eth_hlen > mtu && !skb_is_gso(skb)) { *pmtu = mtu; err = -EMSGSIZE; diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 024db17386d2..6f08b760c2a7 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -479,7 +479,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) mtu = dst_mtu(dst); if (skb->len > mtu) { - skb_dst_update_pmtu(skb, mtu); + skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IPV6)) { if (mtu < IPV6_MIN_MTU) diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index a77f6b7d3a7c..dfe5e603ffe1 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -925,7 +925,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto out; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 3f83ea851ebf..e4ed9c7b43b0 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -95,7 +95,8 @@ static int ip6_pkt_prohibit(struct sk_buff *skb); static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb); static void ip6_link_failure(struct sk_buff *skb); static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu); + struct sk_buff *skb, u32 mtu, + bool confirm_neigh); static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); static int rt6_score_route(const struct fib6_nh *nh, u32 fib6_flags, int oif, @@ -264,7 +265,8 @@ static unsigned int ip6_blackhole_mtu(const struct dst_entry *dst) } static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { } @@ -2695,7 +2697,8 @@ static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt) } static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, - const struct ipv6hdr *iph, u32 mtu) + const struct ipv6hdr *iph, u32 mtu, + bool confirm_neigh) { const struct in6_addr *daddr, *saddr; struct rt6_info *rt6 = (struct rt6_info *)dst; @@ -2713,7 +2716,10 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, daddr = NULL; saddr = NULL; } - dst_confirm_neigh(dst, daddr); + + if (confirm_neigh) + dst_confirm_neigh(dst, daddr); + mtu = max_t(u32, mtu, IPV6_MIN_MTU); if (mtu >= dst_mtu(dst)) return; @@ -2767,9 +2773,11 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, } static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { - __ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu); + __ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu, + confirm_neigh); } void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, @@ -2788,7 +2796,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, dst = ip6_route_output(net, NULL, &fl6); if (!dst->error) - __ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu)); + __ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu), true); dst_release(dst); } EXPORT_SYMBOL_GPL(ip6_update_pmtu); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index b2ccbc473127..98954830c40b 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -944,7 +944,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, } if (tunnel->parms.iph.daddr) - skb_dst_update_pmtu(skb, mtu); + skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->len > mtu && !skb_is_gso(skb)) { icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 16632e02e9b0..30915f6f31e3 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -235,7 +235,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) fl6.flowi6_uid = sk->sk_uid; security_req_classify_flow(req, flowi6_to_flowi(&fl6)); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) goto out_free; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 4804b6dc5e65..b42fa41cfceb 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -275,7 +275,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto failure; @@ -906,7 +906,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 * Underlying function will use this to retrieve the network * namespace */ - dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL); + dst = ip6_dst_lookup_flow(sock_net(ctl_sk), ctl_sk, &fl6, NULL); if (!IS_ERR(dst)) { skb_dst_set(buff, dst); ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, tclass, diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 699e0730ce8e..af7a4b8b1e9c 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -98,12 +98,13 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, } static void xfrm6_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct dst_entry *path = xdst->route; - path->ops->update_pmtu(path, sk, skb, mtu); + path->ops->update_pmtu(path, sk, skb, mtu, confirm_neigh); } static void xfrm6_redirect(struct dst_entry *dst, struct sock *sk, diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 802f19aba7e3..d148766f40d1 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -615,7 +615,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto out; diff --git a/net/llc/llc_station.c b/net/llc/llc_station.c index 204a8351efff..c29170e767a8 100644 --- a/net/llc/llc_station.c +++ b/net/llc/llc_station.c @@ -32,7 +32,7 @@ static int llc_stat_ev_rx_null_dsap_xid_c(struct sk_buff *skb) return LLC_PDU_IS_CMD(pdu) && /* command PDU */ LLC_PDU_TYPE_IS_U(pdu) && /* U type PDU */ LLC_U_PDU_CMD(pdu) == LLC_1_PDU_CMD_XID && - !pdu->dsap ? 0 : 1; /* NULL DSAP value */ + !pdu->dsap; /* NULL DSAP value */ } static int llc_stat_ev_rx_null_dsap_test_c(struct sk_buff *skb) @@ -42,7 +42,7 @@ static int llc_stat_ev_rx_null_dsap_test_c(struct sk_buff *skb) return LLC_PDU_IS_CMD(pdu) && /* command PDU */ LLC_PDU_TYPE_IS_U(pdu) && /* U type PDU */ LLC_U_PDU_CMD(pdu) == LLC_1_PDU_CMD_TEST && - !pdu->dsap ? 0 : 1; /* NULL DSAP */ + !pdu->dsap; /* NULL DSAP */ } static int llc_station_ac_send_xid_r(struct sk_buff *skb) diff --git a/net/mac80211/status.c b/net/mac80211/status.c index ab8ba5835ca0..5a3d645fe1bc 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -1030,7 +1030,8 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, I802_DEBUG_INC(local->dot11FailedCount); } - if (ieee80211_is_nullfunc(fc) && ieee80211_has_pm(fc) && + if ((ieee80211_is_nullfunc(fc) || ieee80211_is_qos_nullfunc(fc)) && + ieee80211_has_pm(fc) && ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS) && !(info->flags & IEEE80211_TX_CTL_INJECTED) && local->ps_sdata && !(local->scanning)) { diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 1fa422782905..cbd273c0b275 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -2263,6 +2263,15 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, payload[7]); } + /* + * Initialize skb->priority for QoS frames. This is put in the TID field + * of the frame before passing it to the driver. + */ + if (ieee80211_is_data_qos(hdr->frame_control)) { + u8 *p = ieee80211_get_qos_ctl(hdr); + skb->priority = *p & IEEE80211_QOS_CTL_TAG1D_MASK; + } + memset(info, 0, sizeof(*info)); info->flags = IEEE80211_TX_CTL_REQ_TX_STATUS | diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index c312741df2ce..4701edffb1f7 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -617,16 +617,15 @@ static struct net_device *inet6_fib_lookup_dev(struct net *net, struct net_device *dev; struct dst_entry *dst; struct flowi6 fl6; - int err; if (!ipv6_stub) return ERR_PTR(-EAFNOSUPPORT); memset(&fl6, 0, sizeof(fl6)); memcpy(&fl6.daddr, addr, sizeof(struct in6_addr)); - err = ipv6_stub->ipv6_dst_lookup(net, NULL, &dst, &fl6); - if (err) - return ERR_PTR(err); + dst = ipv6_stub->ipv6_dst_lookup_flow(net, NULL, &fl6, NULL); + if (IS_ERR(dst)) + return ERR_CAST(dst); dev = dst->dev; dev_hold(dev); diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index d73d1828216a..d8143a8c034d 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1658,6 +1658,7 @@ static int ip_set_utest(struct net *net, struct sock *ctnl, struct sk_buff *skb, struct ip_set *set; struct nlattr *tb[IPSET_ATTR_ADT_MAX + 1] = {}; int ret = 0; + u32 lineno; if (unlikely(protocol_min_failed(attr) || !attr[IPSET_ATTR_SETNAME] || @@ -1674,7 +1675,7 @@ static int ip_set_utest(struct net *net, struct sock *ctnl, struct sk_buff *skb, return -IPSET_ERR_PROTOCOL; rcu_read_lock_bh(); - ret = set->variant->uadt(set, tb, IPSET_TEST, NULL, 0, 0); + ret = set->variant->uadt(set, tb, IPSET_TEST, &lineno, 0, 0); rcu_read_unlock_bh(); /* Userspace can't trigger element to be re-added */ if (ret == -EAGAIN) diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 888d3068a492..c62a131a6094 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -208,7 +208,7 @@ static inline void maybe_update_pmtu(int skb_af, struct sk_buff *skb, int mtu) struct rtable *ort = skb_rtable(skb); if (!skb->dev && sk && sk_fullsock(sk)) - ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu); + ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu, true); } static inline bool ensure_mtu_is_adequate(struct netns_ipvs *ipvs, int skb_af, diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index e2d13cd18875..aa8adf930b3c 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -3602,6 +3602,9 @@ static void __net_exit ctnetlink_net_exit_batch(struct list_head *net_exit_list) list_for_each_entry(net, net_exit_list, exit_list) ctnetlink_net_exit(net); + + /* wait for other cpus until they are done with ctnl_notifiers */ + synchronize_rcu(); } static struct pernet_operations ctnetlink_net_ops = { diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index b6b14db3955b..b3f4a334f9d7 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -677,6 +677,9 @@ static int dccp_timeout_nlattr_to_obj(struct nlattr *tb[], unsigned int *timeouts = data; int i; + if (!timeouts) + timeouts = dn->dccp_timeout; + /* set default DCCP timeouts. */ for (i=0; idccp_timeout[i]; diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index fce3d93f1541..0399ae8f1188 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -594,6 +594,9 @@ static int sctp_timeout_nlattr_to_obj(struct nlattr *tb[], struct nf_sctp_net *sn = nf_sctp_pernet(net); int i; + if (!timeouts) + timeouts = sn->timeouts; + /* set default SCTP timeouts. */ for (i=0; itimeouts[i]; diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index a2b58de82600..f8f52ff99cfb 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -189,7 +189,7 @@ static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state, goto err; } - if (!skb_dst_force(skb) && state->hook != NF_INET_PRE_ROUTING) { + if (skb_dst(skb) && !skb_dst_force(skb)) { status = -ENETDOWN; goto err; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 712a428509ad..67ca47c7ce54 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4252,8 +4252,10 @@ static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set, return err; err = -EINVAL; - if (desc.type != NFT_DATA_VALUE || desc.len != set->klen) + if (desc.type != NFT_DATA_VALUE || desc.len != set->klen) { + nft_data_release(&elem.key.val, desc.type); return err; + } priv = set->ops->get(ctx->net, set, &elem, flags); if (IS_ERR(priv)) @@ -4489,14 +4491,20 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (nla[NFTA_SET_ELEM_DATA] == NULL && !(flags & NFT_SET_ELEM_INTERVAL_END)) return -EINVAL; - if (nla[NFTA_SET_ELEM_DATA] != NULL && - flags & NFT_SET_ELEM_INTERVAL_END) - return -EINVAL; } else { if (nla[NFTA_SET_ELEM_DATA] != NULL) return -EINVAL; } + if ((flags & NFT_SET_ELEM_INTERVAL_END) && + (nla[NFTA_SET_ELEM_DATA] || + nla[NFTA_SET_ELEM_OBJREF] || + nla[NFTA_SET_ELEM_TIMEOUT] || + nla[NFTA_SET_ELEM_EXPIRATION] || + nla[NFTA_SET_ELEM_USERDATA] || + nla[NFTA_SET_ELEM_EXPR])) + return -EINVAL; + timeout = 0; if (nla[NFTA_SET_ELEM_TIMEOUT] != NULL) { if (!(set->flags & NFT_SET_TIMEOUT)) @@ -5209,7 +5217,7 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; - type = nft_obj_type_get(net, objtype); + type = __nft_obj_type_get(objtype); nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); return nf_tables_updobj(&ctx, type, nla[NFTA_OBJ_DATA], obj); diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index e25dab8128db..96a64e7594a5 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -44,6 +44,9 @@ struct nft_flow_rule *nft_flow_rule_create(struct net *net, expr = nft_expr_next(expr); } + if (num_actions == 0) + return ERR_PTR(-EOPNOTSUPP); + flow = nft_flow_rule_alloc(num_actions); if (!flow) return ERR_PTR(-ENOMEM); @@ -355,14 +358,14 @@ int nft_flow_rule_offload_commit(struct net *net) continue; if (trans->ctx.flags & NLM_F_REPLACE || - !(trans->ctx.flags & NLM_F_APPEND)) - return -EOPNOTSUPP; - + !(trans->ctx.flags & NLM_F_APPEND)) { + err = -EOPNOTSUPP; + break; + } err = nft_flow_offload_rule(trans->ctx.chain, nft_trans_rule(trans), nft_trans_flow_rule(trans), FLOW_CLS_REPLACE); - nft_flow_rule_destroy(nft_trans_flow_rule(trans)); break; case NFT_MSG_DELRULE: if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD)) @@ -376,7 +379,23 @@ int nft_flow_rule_offload_commit(struct net *net) } if (err) - return err; + break; + } + + list_for_each_entry(trans, &net->nft.commit_list, list) { + if (trans->ctx.family != NFPROTO_NETDEV) + continue; + + switch (trans->msg_type) { + case NFT_MSG_NEWRULE: + if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD)) + continue; + + nft_flow_rule_destroy(nft_trans_flow_rule(trans)); + break; + default: + break; + } } return err; @@ -446,6 +465,9 @@ static int nft_offload_netdev_event(struct notifier_block *this, struct net *net = dev_net(dev); struct nft_chain *chain; + if (event != NETDEV_UNREGISTER) + return NOTIFY_DONE; + mutex_lock(&net->nft.commit_mutex); chain = __nft_offload_get_chain(dev); if (chain) @@ -455,7 +477,7 @@ static int nft_offload_netdev_event(struct notifier_block *this, return NOTIFY_DONE; } -static struct flow_indr_block_ing_entry block_ing_entry = { +static struct flow_indr_block_entry block_ing_entry = { .cb = nft_indr_block_cb, .list = LIST_HEAD_INIT(block_ing_entry.list), }; @@ -472,13 +494,13 @@ int nft_offload_init(void) if (err < 0) return err; - flow_indr_add_block_ing_cb(&block_ing_entry); + flow_indr_add_block_cb(&block_ing_entry); return 0; } void nft_offload_exit(void) { - flow_indr_del_block_ing_cb(&block_ing_entry); + flow_indr_del_block_cb(&block_ing_entry); unregister_netdevice_notifier(&nft_offload_netdev_notifier); } diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index 02afa752dd2e..10e9d50e4e19 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -80,7 +80,7 @@ static int nft_bitwise_init(const struct nft_ctx *ctx, tb[NFTA_BITWISE_MASK]); if (err < 0) return err; - if (d1.len != priv->len) { + if (d1.type != NFT_DATA_VALUE || d1.len != priv->len) { err = -EINVAL; goto err1; } @@ -89,7 +89,7 @@ static int nft_bitwise_init(const struct nft_ctx *ctx, tb[NFTA_BITWISE_XOR]); if (err < 0) goto err1; - if (d2.len != priv->len) { + if (d2.type != NFT_DATA_VALUE || d2.len != priv->len) { err = -EINVAL; goto err2; } diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c index 0744b2bb46da..ae730dba60c8 100644 --- a/net/netfilter/nft_cmp.c +++ b/net/netfilter/nft_cmp.c @@ -80,6 +80,12 @@ static int nft_cmp_init(const struct nft_ctx *ctx, const struct nft_expr *expr, if (err < 0) return err; + if (desc.type != NFT_DATA_VALUE) { + err = -EINVAL; + nft_data_release(&priv->data, desc.type); + return err; + } + priv->sreg = nft_parse_register(tb[NFTA_CMP_SREG]); err = nft_validate_register_load(priv->sreg, desc.len); if (err < 0) diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index f29bbc74c4bf..ff5ac173e897 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -197,9 +197,6 @@ static void nft_flow_offload_activate(const struct nft_ctx *ctx, static void nft_flow_offload_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { - struct nft_flow_offload *priv = nft_expr_priv(expr); - - priv->flowtable->use--; nf_ct_netns_put(ctx->net, ctx->family); } diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 317e3a9e8c5b..dda1e55d5801 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -33,19 +33,19 @@ static DEFINE_PER_CPU(struct rnd_state, nft_prandom_state); -static u8 nft_meta_weekday(unsigned long secs) +static u8 nft_meta_weekday(time64_t secs) { unsigned int dse; u8 wday; secs -= NFT_META_SECS_PER_MINUTE * sys_tz.tz_minuteswest; - dse = secs / NFT_META_SECS_PER_DAY; + dse = div_u64(secs, NFT_META_SECS_PER_DAY); wday = (4 + dse) % NFT_META_DAYS_PER_WEEK; return wday; } -static u32 nft_meta_hour(unsigned long secs) +static u32 nft_meta_hour(time64_t secs) { struct tm tm; @@ -250,10 +250,10 @@ void nft_meta_get_eval(const struct nft_expr *expr, nft_reg_store64(dest, ktime_get_real_ns()); break; case NFT_META_TIME_DAY: - nft_reg_store8(dest, nft_meta_weekday(get_seconds())); + nft_reg_store8(dest, nft_meta_weekday(ktime_get_real_seconds())); break; case NFT_META_TIME_HOUR: - *dest = nft_meta_hour(get_seconds()); + *dest = nft_meta_hour(ktime_get_real_seconds()); break; default: WARN_ON(1); diff --git a/net/netfilter/nft_range.c b/net/netfilter/nft_range.c index 4701fa8a45e7..89efcc5a533d 100644 --- a/net/netfilter/nft_range.c +++ b/net/netfilter/nft_range.c @@ -66,11 +66,21 @@ static int nft_range_init(const struct nft_ctx *ctx, const struct nft_expr *expr if (err < 0) return err; + if (desc_from.type != NFT_DATA_VALUE) { + err = -EINVAL; + goto err1; + } + err = nft_data_init(NULL, &priv->data_to, sizeof(priv->data_to), &desc_to, tb[NFTA_RANGE_TO_DATA]); if (err < 0) goto err1; + if (desc_to.type != NFT_DATA_VALUE) { + err = -EINVAL; + goto err2; + } + if (desc_from.len != desc_to.len) { err = -EINVAL; goto err2; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 57123259452f..a9f804f7a04a 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -74,8 +74,13 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set parent = rcu_dereference_raw(parent->rb_left); continue; } - if (nft_rbtree_interval_end(rbe)) - goto out; + if (nft_rbtree_interval_end(rbe)) { + if (nft_set_is_anonymous(set)) + return false; + parent = rcu_dereference_raw(parent->rb_left); + interval = NULL; + continue; + } *ext = &rbe->ext; return true; @@ -88,7 +93,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set *ext = &interval->ext; return true; } -out: + return false; } @@ -139,8 +144,10 @@ static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set, if (flags & NFT_SET_ELEM_INTERVAL_END) interval = rbe; } else { - if (!nft_set_elem_active(&rbe->ext, genmask)) + if (!nft_set_elem_active(&rbe->ext, genmask)) { parent = rcu_dereference_raw(parent->rb_left); + continue; + } if (!nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_FLAGS) || (*nft_set_ext_flags(&rbe->ext) & NFT_SET_ELEM_INTERVAL_END) == @@ -148,7 +155,11 @@ static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set, *elem = rbe; return true; } - return false; + + if (nft_rbtree_interval_end(rbe)) + interval = NULL; + + parent = rcu_dereference_raw(parent->rb_left); } } diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c index f92a82c73880..95980154ef02 100644 --- a/net/netfilter/nft_tproxy.c +++ b/net/netfilter/nft_tproxy.c @@ -50,7 +50,7 @@ static void nft_tproxy_eval_v4(const struct nft_expr *expr, taddr = nf_tproxy_laddr4(skb, taddr, iph->daddr); if (priv->sreg_port) - tport = regs->data[priv->sreg_port]; + tport = nft_reg_load16(®s->data[priv->sreg_port]); if (!tport) tport = hp->dest; @@ -117,7 +117,7 @@ static void nft_tproxy_eval_v6(const struct nft_expr *expr, taddr = *nf_tproxy_laddr6(skb, &taddr, &iph->daddr); if (priv->sreg_port) - tport = regs->data[priv->sreg_port]; + tport = nft_reg_load16(®s->data[priv->sreg_port]); if (!tport) tport = hp->dest; diff --git a/net/nfc/nci/uart.c b/net/nfc/nci/uart.c index 78fe622eba65..11b554ce07ff 100644 --- a/net/nfc/nci/uart.c +++ b/net/nfc/nci/uart.c @@ -346,7 +346,7 @@ static int nci_uart_default_recv_buf(struct nci_uart *nu, const u8 *data, nu->rx_packet_len = -1; nu->rx_skb = nci_skb_alloc(nu->ndev, NCI_MAX_PACKET_SIZE, - GFP_KERNEL); + GFP_ATOMIC); if (!nu->rx_skb) return -ENOMEM; } diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 1c77f520f474..99352f09deaa 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -166,7 +166,8 @@ static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key, int err; err = skb_mpls_push(skb, mpls->mpls_lse, mpls->mpls_ethertype, - skb->mac_len); + skb->mac_len, + ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET); if (err) return err; @@ -179,7 +180,8 @@ static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key, { int err; - err = skb_mpls_pop(skb, ethertype, skb->mac_len); + err = skb_mpls_pop(skb, ethertype, skb->mac_len, + ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET); if (err) return err; diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 05249eb45082..283e8f9a5fd2 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -903,6 +903,17 @@ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key, } err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, maniptype); + if (err == NF_ACCEPT && + ct->status & IPS_SRC_NAT && ct->status & IPS_DST_NAT) { + if (maniptype == NF_NAT_MANIP_SRC) + maniptype = NF_NAT_MANIP_DST; + else + maniptype = NF_NAT_MANIP_SRC; + + err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, + maniptype); + } + /* Mark NAT done if successful and update the flow key. */ if (err == NF_ACCEPT) ovs_nat_update_key(key, skb, maniptype); diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index d8c364d637b1..23f67b8fdeaa 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -704,9 +704,13 @@ static size_t ovs_flow_cmd_msg_size(const struct sw_flow_actions *acts, { size_t len = NLMSG_ALIGN(sizeof(struct ovs_header)); - /* OVS_FLOW_ATTR_UFID */ + /* OVS_FLOW_ATTR_UFID, or unmasked flow key as fallback + * see ovs_nla_put_identifier() + */ if (sfid && ovs_identifier_is_ufid(sfid)) len += nla_total_size(sfid->ufid_len); + else + len += nla_total_size(ovs_key_attr_size()); /* OVS_FLOW_ATTR_KEY */ if (!sfid || should_fill_key(sfid, ufid_flags)) @@ -882,7 +886,10 @@ static struct sk_buff *ovs_flow_cmd_build_info(const struct sw_flow *flow, retval = ovs_flow_cmd_fill_info(flow, dp_ifindex, skb, info->snd_portid, info->snd_seq, 0, cmd, ufid_flags); - BUG_ON(retval < 0); + if (WARN_ON_ONCE(retval < 0)) { + kfree_skb(skb); + skb = ERR_PTR(retval); + } return skb; } @@ -1346,7 +1353,10 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info) OVS_FLOW_CMD_DEL, ufid_flags); rcu_read_unlock(); - BUG_ON(err < 0); + if (WARN_ON_ONCE(err < 0)) { + kfree_skb(reply); + goto out_free; + } ovs_notify(&dp_flow_genl_family, reply, info); } else { @@ -1354,6 +1364,7 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info) } } +out_free: ovs_flow_free(flow, true); return 0; unlock: diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 82a50e850245..529d4ce945db 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -544,7 +544,8 @@ static int prb_calc_retire_blk_tmo(struct packet_sock *po, msec = 1; div = ecmd.base.speed / 1000; } - } + } else + return DEFAULT_PRB_RETIRE_TOV; mbits = (blk_size_in_bytes * 8) / (1024 * 1024); diff --git a/net/psample/psample.c b/net/psample/psample.c index a6ceb0533b5b..6f2fbc6b9eb2 100644 --- a/net/psample/psample.c +++ b/net/psample/psample.c @@ -229,7 +229,7 @@ void psample_sample_packet(struct psample_group *group, struct sk_buff *skb, data_len = PSAMPLE_MAX_PACKET_SIZE - meta_len - NLA_HDRLEN - NLA_ALIGNTO; - nl_skb = genlmsg_new(meta_len + data_len, GFP_ATOMIC); + nl_skb = genlmsg_new(meta_len + nla_total_size(data_len), GFP_ATOMIC); if (unlikely(!nl_skb)) return; diff --git a/net/rfkill/core.c b/net/rfkill/core.c index f9b08a6d8dbe..6c089320ae4f 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -1002,10 +1002,13 @@ static void rfkill_sync_work(struct work_struct *work) int __must_check rfkill_register(struct rfkill *rfkill) { static unsigned long rfkill_no; - struct device *dev = &rfkill->dev; + struct device *dev; int error; - BUG_ON(!rfkill); + if (!rfkill) + return -EINVAL; + + dev = &rfkill->dev; mutex_lock(&rfkill_global_mutex); @@ -1316,10 +1319,12 @@ static const struct file_operations rfkill_fops = { .llseek = no_llseek, }; +#define RFKILL_NAME "rfkill" + static struct miscdevice rfkill_miscdev = { - .name = "rfkill", .fops = &rfkill_fops, - .minor = MISC_DYNAMIC_MINOR, + .name = RFKILL_NAME, + .minor = RFKILL_MINOR, }; static int __init rfkill_init(void) @@ -1371,3 +1376,6 @@ static void __exit rfkill_exit(void) class_unregister(&rfkill_class); } module_exit(rfkill_exit); + +MODULE_ALIAS_MISCDEV(RFKILL_MINOR); +MODULE_ALIAS("devname:" RFKILL_NAME); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 7c7d10f2e0c1..5e99df80e80a 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -209,6 +209,7 @@ struct rxrpc_skb_priv { struct rxrpc_security { const char *name; /* name of this service */ u8 security_index; /* security type provided */ + u32 no_key_abort; /* Abort code indicating no key */ /* Initialise a security service */ int (*init)(void); @@ -977,8 +978,9 @@ static inline void rxrpc_reduce_conn_timer(struct rxrpc_connection *conn, struct rxrpc_connection *rxrpc_find_service_conn_rcu(struct rxrpc_peer *, struct sk_buff *); struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *, gfp_t); -void rxrpc_new_incoming_connection(struct rxrpc_sock *, - struct rxrpc_connection *, struct sk_buff *); +void rxrpc_new_incoming_connection(struct rxrpc_sock *, struct rxrpc_connection *, + const struct rxrpc_security *, struct key *, + struct sk_buff *); void rxrpc_unpublish_service_conn(struct rxrpc_connection *); /* @@ -1103,7 +1105,9 @@ extern const struct rxrpc_security rxkad; int __init rxrpc_init_security(void); void rxrpc_exit_security(void); int rxrpc_init_client_conn_security(struct rxrpc_connection *); -int rxrpc_init_server_conn_security(struct rxrpc_connection *); +bool rxrpc_look_up_server_security(struct rxrpc_local *, struct rxrpc_sock *, + const struct rxrpc_security **, struct key **, + struct sk_buff *); /* * sendmsg.c diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 135bf5cd8dd5..70e44abf106c 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -239,6 +239,22 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx) kfree(b); } +/* + * Ping the other end to fill our RTT cache and to retrieve the rwind + * and MTU parameters. + */ +static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + ktime_t now = skb->tstamp; + + if (call->peer->rtt_usage < 3 || + ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), now)) + rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial, + true, true, + rxrpc_propose_ack_ping_for_params); +} + /* * Allocate a new incoming call from the prealloc pool, along with a connection * and a peer as necessary. @@ -247,6 +263,8 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, struct rxrpc_local *local, struct rxrpc_peer *peer, struct rxrpc_connection *conn, + const struct rxrpc_security *sec, + struct key *key, struct sk_buff *skb) { struct rxrpc_backlog *b = rx->backlog; @@ -294,7 +312,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, conn->params.local = rxrpc_get_local(local); conn->params.peer = peer; rxrpc_see_connection(conn); - rxrpc_new_incoming_connection(rx, conn, skb); + rxrpc_new_incoming_connection(rx, conn, sec, key, skb); } else { rxrpc_get_connection(conn); } @@ -333,9 +351,11 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + const struct rxrpc_security *sec = NULL; struct rxrpc_connection *conn; struct rxrpc_peer *peer = NULL; - struct rxrpc_call *call; + struct rxrpc_call *call = NULL; + struct key *key = NULL; _enter(""); @@ -346,9 +366,7 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, sp->hdr.seq, RX_INVALID_OPERATION, ESHUTDOWN); skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; skb->priority = RX_INVALID_OPERATION; - _leave(" = NULL [close]"); - call = NULL; - goto out; + goto no_call; } /* The peer, connection and call may all have sprung into existence due @@ -358,29 +376,19 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, */ conn = rxrpc_find_connection_rcu(local, skb, &peer); - call = rxrpc_alloc_incoming_call(rx, local, peer, conn, skb); + if (!conn && !rxrpc_look_up_server_security(local, rx, &sec, &key, skb)) + goto no_call; + + call = rxrpc_alloc_incoming_call(rx, local, peer, conn, sec, key, skb); + key_put(key); if (!call) { skb->mark = RXRPC_SKB_MARK_REJECT_BUSY; - _leave(" = NULL [busy]"); - call = NULL; - goto out; + goto no_call; } trace_rxrpc_receive(call, rxrpc_receive_incoming, sp->hdr.serial, sp->hdr.seq); - /* Lock the call to prevent rxrpc_kernel_send/recv_data() and - * sendmsg()/recvmsg() inconveniently stealing the mutex once the - * notification is generated. - * - * The BUG should never happen because the kernel should be well - * behaved enough not to access the call before the first notification - * event and userspace is prevented from doing so until the state is - * appropriate. - */ - if (!mutex_trylock(&call->user_mutex)) - BUG(); - /* Make the call live. */ rxrpc_incoming_call(rx, call, skb); conn = call->conn; @@ -421,6 +429,9 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, BUG(); } spin_unlock(&conn->state_lock); + spin_unlock(&rx->incoming_lock); + + rxrpc_send_ping(call, skb); if (call->state == RXRPC_CALL_SERVER_ACCEPTING) rxrpc_notify_socket(call); @@ -433,9 +444,12 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, rxrpc_put_call(call, rxrpc_call_put); _leave(" = %p{%d}", call, call->debug_id); -out: - spin_unlock(&rx->incoming_lock); return call; + +no_call: + spin_unlock(&rx->incoming_lock); + _leave(" = NULL [%u]", skb->mark); + return NULL; } /* diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index a1ceef4f5cd0..808a4723f868 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -376,21 +376,7 @@ static void rxrpc_secure_connection(struct rxrpc_connection *conn) _enter("{%d}", conn->debug_id); ASSERT(conn->security_ix != 0); - - if (!conn->params.key) { - _debug("set up security"); - ret = rxrpc_init_server_conn_security(conn); - switch (ret) { - case 0: - break; - case -ENOENT: - abort_code = RX_CALL_DEAD; - goto abort; - default: - abort_code = RXKADNOAUTH; - goto abort; - } - } + ASSERT(conn->server_key); if (conn->security->issue_challenge(conn) < 0) { abort_code = RX_CALL_DEAD; diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c index 123d6ceab15c..21da48e3d2e5 100644 --- a/net/rxrpc/conn_service.c +++ b/net/rxrpc/conn_service.c @@ -148,6 +148,8 @@ struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *rxn */ void rxrpc_new_incoming_connection(struct rxrpc_sock *rx, struct rxrpc_connection *conn, + const struct rxrpc_security *sec, + struct key *key, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); @@ -160,6 +162,8 @@ void rxrpc_new_incoming_connection(struct rxrpc_sock *rx, conn->service_id = sp->hdr.serviceId; conn->security_ix = sp->hdr.securityIndex; conn->out_clientflag = 0; + conn->security = sec; + conn->server_key = key_get(key); if (conn->security_ix) conn->state = RXRPC_CONN_SERVICE_UNSECURED; else diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 157be1ff8697..86bd133b4fa0 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -192,22 +192,6 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, goto out_no_clear_ca; } -/* - * Ping the other end to fill our RTT cache and to retrieve the rwind - * and MTU parameters. - */ -static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb) -{ - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - ktime_t now = skb->tstamp; - - if (call->peer->rtt_usage < 3 || - ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), now)) - rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial, - true, true, - rxrpc_propose_ack_ping_for_params); -} - /* * Apply a hard ACK by advancing the Tx window. */ @@ -1396,8 +1380,6 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) call = rxrpc_new_incoming_call(local, rx, skb); if (!call) goto reject_packet; - rxrpc_send_ping(call, skb); - mutex_unlock(&call->user_mutex); } /* Process a call packet; this either discards or passes on the ref diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 8d8aa3c230b5..098f1f9ec53b 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -648,9 +648,9 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn) u32 serial; int ret; - _enter("{%d,%x}", conn->debug_id, key_serial(conn->params.key)); + _enter("{%d,%x}", conn->debug_id, key_serial(conn->server_key)); - ret = key_validate(conn->params.key); + ret = key_validate(conn->server_key); if (ret < 0) return ret; @@ -1293,6 +1293,7 @@ static void rxkad_exit(void) const struct rxrpc_security rxkad = { .name = "rxkad", .security_index = RXRPC_SECURITY_RXKAD, + .no_key_abort = RXKADUNKNOWNKEY, .init = rxkad_init, .exit = rxkad_exit, .init_connection_security = rxkad_init_connection_security, diff --git a/net/rxrpc/security.c b/net/rxrpc/security.c index a4c47d2b7054..9b1fb9ed0717 100644 --- a/net/rxrpc/security.c +++ b/net/rxrpc/security.c @@ -101,62 +101,58 @@ int rxrpc_init_client_conn_security(struct rxrpc_connection *conn) } /* - * initialise the security on a server connection + * Find the security key for a server connection. */ -int rxrpc_init_server_conn_security(struct rxrpc_connection *conn) +bool rxrpc_look_up_server_security(struct rxrpc_local *local, struct rxrpc_sock *rx, + const struct rxrpc_security **_sec, + struct key **_key, + struct sk_buff *skb) { const struct rxrpc_security *sec; - struct rxrpc_local *local = conn->params.local; - struct rxrpc_sock *rx; - struct key *key; - key_ref_t kref; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + key_ref_t kref = NULL; char kdesc[5 + 1 + 3 + 1]; _enter(""); - sprintf(kdesc, "%u:%u", conn->service_id, conn->security_ix); + sprintf(kdesc, "%u:%u", sp->hdr.serviceId, sp->hdr.securityIndex); - sec = rxrpc_security_lookup(conn->security_ix); + sec = rxrpc_security_lookup(sp->hdr.securityIndex); if (!sec) { - _leave(" = -ENOKEY [lookup]"); - return -ENOKEY; + trace_rxrpc_abort(0, "SVS", + sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, + RX_INVALID_OPERATION, EKEYREJECTED); + skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; + skb->priority = RX_INVALID_OPERATION; + return false; } - /* find the service */ - read_lock(&local->services_lock); - rx = rcu_dereference_protected(local->service, - lockdep_is_held(&local->services_lock)); - if (rx && (rx->srx.srx_service == conn->service_id || - rx->second_service == conn->service_id)) - goto found_service; + if (sp->hdr.securityIndex == RXRPC_SECURITY_NONE) + goto out; - /* the service appears to have died */ - read_unlock(&local->services_lock); - _leave(" = -ENOENT"); - return -ENOENT; - -found_service: if (!rx->securities) { - read_unlock(&local->services_lock); - _leave(" = -ENOKEY"); - return -ENOKEY; + trace_rxrpc_abort(0, "SVR", + sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, + RX_INVALID_OPERATION, EKEYREJECTED); + skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; + skb->priority = RX_INVALID_OPERATION; + return false; } /* look through the service's keyring */ kref = keyring_search(make_key_ref(rx->securities, 1UL), &key_type_rxrpc_s, kdesc, true); if (IS_ERR(kref)) { - read_unlock(&local->services_lock); - _leave(" = %ld [search]", PTR_ERR(kref)); - return PTR_ERR(kref); + trace_rxrpc_abort(0, "SVK", + sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, + sec->no_key_abort, EKEYREJECTED); + skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; + skb->priority = sec->no_key_abort; + return false; } - key = key_ref_to_ptr(kref); - read_unlock(&local->services_lock); - - conn->server_key = key; - conn->security = sec; - - _leave(" = 0"); - return 0; +out: + *_sec = sec; + *_key = key_ref_to_ptr(kref); + return true; } diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index fcc46025e790..f3232a00970f 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -329,6 +329,7 @@ static int tcf_ct_act_nat(struct sk_buff *skb, bool commit) { #if IS_ENABLED(CONFIG_NF_NAT) + int err; enum nf_nat_manip_type maniptype; if (!(ct_action & TCA_CT_ACT_NAT)) @@ -359,7 +360,17 @@ static int tcf_ct_act_nat(struct sk_buff *skb, return NF_ACCEPT; } - return ct_nat_execute(skb, ct, ctinfo, range, maniptype); + err = ct_nat_execute(skb, ct, ctinfo, range, maniptype); + if (err == NF_ACCEPT && + ct->status & IPS_SRC_NAT && ct->status & IPS_DST_NAT) { + if (maniptype == NF_NAT_MANIP_SRC) + maniptype = NF_NAT_MANIP_DST; + else + maniptype = NF_NAT_MANIP_SRC; + + err = ct_nat_execute(skb, ct, ctinfo, range, maniptype); + } + return err; #else return NF_ACCEPT; #endif diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 08923b21e566..f0df0d90b8bd 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -219,8 +219,10 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, bool use_reinsert; bool want_ingress; bool is_redirect; + bool expects_nh; int m_eaction; int mac_len; + bool at_nh; rec_level = __this_cpu_inc_return(mirred_rec_level); if (unlikely(rec_level > MIRRED_RECURSION_LIMIT)) { @@ -261,19 +263,19 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, goto out; } - /* If action's target direction differs than filter's direction, - * and devices expect a mac header on xmit, then mac push/pull is - * needed. - */ want_ingress = tcf_mirred_act_wants_ingress(m_eaction); - if (skb_at_tc_ingress(skb) != want_ingress && m_mac_header_xmit) { - if (!skb_at_tc_ingress(skb)) { - /* caught at egress, act ingress: pull mac */ - mac_len = skb_network_header(skb) - skb_mac_header(skb); + + expects_nh = want_ingress || !m_mac_header_xmit; + at_nh = skb->data == skb_network_header(skb); + if (at_nh != expects_nh) { + mac_len = skb_at_tc_ingress(skb) ? skb->mac_len : + skb_network_header(skb) - skb_mac_header(skb); + if (expects_nh) { + /* target device/action expect data at nh */ skb_pull_rcsum(skb2, mac_len); } else { - /* caught at ingress, act egress: push mac */ - skb_push_rcsum(skb2, skb->mac_len); + /* target device/action expect data at mac */ + skb_push_rcsum(skb2, mac_len); } } diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index 4cf6c553bb0b..db570d2bd0e0 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) /* Copyright (C) 2019 Netronome Systems, Inc. */ +#include #include #include #include @@ -76,12 +77,14 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a, switch (p->tcfm_action) { case TCA_MPLS_ACT_POP: - if (skb_mpls_pop(skb, p->tcfm_proto, mac_len)) + if (skb_mpls_pop(skb, p->tcfm_proto, mac_len, + skb->dev && skb->dev->type == ARPHRD_ETHER)) goto drop; break; case TCA_MPLS_ACT_PUSH: new_lse = tcf_mpls_get_lse(NULL, p, !eth_p_mpls(skb->protocol)); - if (skb_mpls_push(skb, new_lse, p->tcfm_proto, mac_len)) + if (skb_mpls_push(skb, new_lse, p->tcfm_proto, mac_len, + skb->dev && skb->dev->type == ARPHRD_ETHER)) goto drop; break; case TCA_MPLS_ACT_MODIFY: diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 20d60b8fcb70..76e0d122616a 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -308,33 +308,12 @@ static void tcf_proto_put(struct tcf_proto *tp, bool rtnl_held, tcf_proto_destroy(tp, rtnl_held, true, extack); } -static int walker_check_empty(struct tcf_proto *tp, void *fh, - struct tcf_walker *arg) +static bool tcf_proto_check_delete(struct tcf_proto *tp) { - if (fh) { - arg->nonempty = true; - return -1; - } - return 0; -} + if (tp->ops->delete_empty) + return tp->ops->delete_empty(tp); -static bool tcf_proto_is_empty(struct tcf_proto *tp, bool rtnl_held) -{ - struct tcf_walker walker = { .fn = walker_check_empty, }; - - if (tp->ops->walk) { - tp->ops->walk(tp, &walker, rtnl_held); - return !walker.nonempty; - } - return true; -} - -static bool tcf_proto_check_delete(struct tcf_proto *tp, bool rtnl_held) -{ - spin_lock(&tp->lock); - if (tcf_proto_is_empty(tp, rtnl_held)) - tp->deleting = true; - spin_unlock(&tp->lock); + tp->deleting = true; return tp->deleting; } @@ -626,15 +605,15 @@ static void tcf_chain_flush(struct tcf_chain *chain, bool rtnl_held) static int tcf_block_setup(struct tcf_block *block, struct flow_block_offload *bo); -static void tc_indr_block_ing_cmd(struct net_device *dev, - struct tcf_block *block, - flow_indr_block_bind_cb_t *cb, - void *cb_priv, - enum flow_block_command command) +static void tc_indr_block_cmd(struct net_device *dev, struct tcf_block *block, + flow_indr_block_bind_cb_t *cb, void *cb_priv, + enum flow_block_command command, bool ingress) { struct flow_block_offload bo = { .command = command, - .binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS, + .binder_type = ingress ? + FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS : + FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS, .net = dev_net(dev), .block_shared = tcf_block_non_null_shared(block), }; @@ -652,9 +631,10 @@ static void tc_indr_block_ing_cmd(struct net_device *dev, up_write(&block->cb_lock); } -static struct tcf_block *tc_dev_ingress_block(struct net_device *dev) +static struct tcf_block *tc_dev_block(struct net_device *dev, bool ingress) { const struct Qdisc_class_ops *cops; + const struct Qdisc_ops *ops; struct Qdisc *qdisc; if (!dev_ingress_queue(dev)) @@ -664,24 +644,37 @@ static struct tcf_block *tc_dev_ingress_block(struct net_device *dev) if (!qdisc) return NULL; - cops = qdisc->ops->cl_ops; + ops = qdisc->ops; + if (!ops) + return NULL; + + if (!ingress && !strcmp("ingress", ops->id)) + return NULL; + + cops = ops->cl_ops; if (!cops) return NULL; if (!cops->tcf_block) return NULL; - return cops->tcf_block(qdisc, TC_H_MIN_INGRESS, NULL); + return cops->tcf_block(qdisc, + ingress ? TC_H_MIN_INGRESS : TC_H_MIN_EGRESS, + NULL); } -static void tc_indr_block_get_and_ing_cmd(struct net_device *dev, - flow_indr_block_bind_cb_t *cb, - void *cb_priv, - enum flow_block_command command) +static void tc_indr_block_get_and_cmd(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, + void *cb_priv, + enum flow_block_command command) { - struct tcf_block *block = tc_dev_ingress_block(dev); + struct tcf_block *block; - tc_indr_block_ing_cmd(dev, block, cb, cb_priv, command); + block = tc_dev_block(dev, true); + tc_indr_block_cmd(dev, block, cb, cb_priv, command, true); + + block = tc_dev_block(dev, false); + tc_indr_block_cmd(dev, block, cb, cb_priv, command, false); } static void tc_indr_block_call(struct tcf_block *block, @@ -1737,7 +1730,7 @@ static void tcf_chain_tp_delete_empty(struct tcf_chain *chain, * concurrently. * Mark tp for deletion if it is empty. */ - if (!tp_iter || !tcf_proto_check_delete(tp, rtnl_held)) { + if (!tp_iter || !tcf_proto_check_delete(tp)) { mutex_unlock(&chain->filter_chain_lock); return; } @@ -2721,13 +2714,19 @@ static int tc_chain_tmplt_add(struct tcf_chain *chain, struct net *net, struct netlink_ext_ack *extack) { const struct tcf_proto_ops *ops; + char name[IFNAMSIZ]; void *tmplt_priv; /* If kind is not set, user did not specify template. */ if (!tca[TCA_KIND]) return 0; - ops = tcf_proto_lookup_ops(nla_data(tca[TCA_KIND]), true, extack); + if (tcf_proto_check_kind(tca[TCA_KIND], name)) { + NL_SET_ERR_MSG(extack, "Specified TC chain template name too long"); + return -EINVAL; + } + + ops = tcf_proto_lookup_ops(name, true, extack); if (IS_ERR(ops)) return PTR_ERR(ops); if (!ops->tmplt_create || !ops->tmplt_destroy || !ops->tmplt_dump) { @@ -3626,9 +3625,9 @@ static struct pernet_operations tcf_net_ops = { .size = sizeof(struct tcf_net), }; -static struct flow_indr_block_ing_entry block_ing_entry = { - .cb = tc_indr_block_get_and_ing_cmd, - .list = LIST_HEAD_INIT(block_ing_entry.list), +static struct flow_indr_block_entry block_entry = { + .cb = tc_indr_block_get_and_cmd, + .list = LIST_HEAD_INIT(block_entry.list), }; static int __init tc_filter_init(void) @@ -3643,7 +3642,7 @@ static int __init tc_filter_init(void) if (err) goto err_register_pernet_subsys; - flow_indr_add_block_ing_cb(&block_ing_entry); + flow_indr_add_block_cb(&block_entry); rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_new_tfilter, NULL, RTNL_FLAG_DOIT_UNLOCKED); diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 74221e3351c3..5cf8163710c8 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -54,8 +54,13 @@ struct fl_flow_key { struct flow_dissector_key_ip ip; struct flow_dissector_key_ip enc_ip; struct flow_dissector_key_enc_opts enc_opts; - struct flow_dissector_key_ports tp_min; - struct flow_dissector_key_ports tp_max; + union { + struct flow_dissector_key_ports tp; + struct { + struct flow_dissector_key_ports tp_min; + struct flow_dissector_key_ports tp_max; + }; + } tp_range; struct flow_dissector_key_ct ct; } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */ @@ -198,19 +203,19 @@ static bool fl_range_port_dst_cmp(struct cls_fl_filter *filter, { __be16 min_mask, max_mask, min_val, max_val; - min_mask = htons(filter->mask->key.tp_min.dst); - max_mask = htons(filter->mask->key.tp_max.dst); - min_val = htons(filter->key.tp_min.dst); - max_val = htons(filter->key.tp_max.dst); + min_mask = htons(filter->mask->key.tp_range.tp_min.dst); + max_mask = htons(filter->mask->key.tp_range.tp_max.dst); + min_val = htons(filter->key.tp_range.tp_min.dst); + max_val = htons(filter->key.tp_range.tp_max.dst); if (min_mask && max_mask) { - if (htons(key->tp.dst) < min_val || - htons(key->tp.dst) > max_val) + if (htons(key->tp_range.tp.dst) < min_val || + htons(key->tp_range.tp.dst) > max_val) return false; /* skb does not have min and max values */ - mkey->tp_min.dst = filter->mkey.tp_min.dst; - mkey->tp_max.dst = filter->mkey.tp_max.dst; + mkey->tp_range.tp_min.dst = filter->mkey.tp_range.tp_min.dst; + mkey->tp_range.tp_max.dst = filter->mkey.tp_range.tp_max.dst; } return true; } @@ -221,19 +226,19 @@ static bool fl_range_port_src_cmp(struct cls_fl_filter *filter, { __be16 min_mask, max_mask, min_val, max_val; - min_mask = htons(filter->mask->key.tp_min.src); - max_mask = htons(filter->mask->key.tp_max.src); - min_val = htons(filter->key.tp_min.src); - max_val = htons(filter->key.tp_max.src); + min_mask = htons(filter->mask->key.tp_range.tp_min.src); + max_mask = htons(filter->mask->key.tp_range.tp_max.src); + min_val = htons(filter->key.tp_range.tp_min.src); + max_val = htons(filter->key.tp_range.tp_max.src); if (min_mask && max_mask) { - if (htons(key->tp.src) < min_val || - htons(key->tp.src) > max_val) + if (htons(key->tp_range.tp.src) < min_val || + htons(key->tp_range.tp.src) > max_val) return false; /* skb does not have min and max values */ - mkey->tp_min.src = filter->mkey.tp_min.src; - mkey->tp_max.src = filter->mkey.tp_max.src; + mkey->tp_range.tp_min.src = filter->mkey.tp_range.tp_min.src; + mkey->tp_range.tp_max.src = filter->mkey.tp_range.tp_max.src; } return true; } @@ -715,23 +720,25 @@ static void fl_set_key_val(struct nlattr **tb, static int fl_set_key_port_range(struct nlattr **tb, struct fl_flow_key *key, struct fl_flow_key *mask) { - fl_set_key_val(tb, &key->tp_min.dst, - TCA_FLOWER_KEY_PORT_DST_MIN, &mask->tp_min.dst, - TCA_FLOWER_UNSPEC, sizeof(key->tp_min.dst)); - fl_set_key_val(tb, &key->tp_max.dst, - TCA_FLOWER_KEY_PORT_DST_MAX, &mask->tp_max.dst, - TCA_FLOWER_UNSPEC, sizeof(key->tp_max.dst)); - fl_set_key_val(tb, &key->tp_min.src, - TCA_FLOWER_KEY_PORT_SRC_MIN, &mask->tp_min.src, - TCA_FLOWER_UNSPEC, sizeof(key->tp_min.src)); - fl_set_key_val(tb, &key->tp_max.src, - TCA_FLOWER_KEY_PORT_SRC_MAX, &mask->tp_max.src, - TCA_FLOWER_UNSPEC, sizeof(key->tp_max.src)); - - if ((mask->tp_min.dst && mask->tp_max.dst && - htons(key->tp_max.dst) <= htons(key->tp_min.dst)) || - (mask->tp_min.src && mask->tp_max.src && - htons(key->tp_max.src) <= htons(key->tp_min.src))) + fl_set_key_val(tb, &key->tp_range.tp_min.dst, + TCA_FLOWER_KEY_PORT_DST_MIN, &mask->tp_range.tp_min.dst, + TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_min.dst)); + fl_set_key_val(tb, &key->tp_range.tp_max.dst, + TCA_FLOWER_KEY_PORT_DST_MAX, &mask->tp_range.tp_max.dst, + TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_max.dst)); + fl_set_key_val(tb, &key->tp_range.tp_min.src, + TCA_FLOWER_KEY_PORT_SRC_MIN, &mask->tp_range.tp_min.src, + TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_min.src)); + fl_set_key_val(tb, &key->tp_range.tp_max.src, + TCA_FLOWER_KEY_PORT_SRC_MAX, &mask->tp_range.tp_max.src, + TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_max.src)); + + if ((mask->tp_range.tp_min.dst && mask->tp_range.tp_max.dst && + htons(key->tp_range.tp_max.dst) <= + htons(key->tp_range.tp_min.dst)) || + (mask->tp_range.tp_min.src && mask->tp_range.tp_max.src && + htons(key->tp_range.tp_max.src) <= + htons(key->tp_range.tp_min.src))) return -EINVAL; return 0; @@ -1320,9 +1327,10 @@ static void fl_init_dissector(struct flow_dissector *dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4); FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6); - if (FL_KEY_IS_MASKED(mask, tp) || - FL_KEY_IS_MASKED(mask, tp_min) || FL_KEY_IS_MASKED(mask, tp_max)) - FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_PORTS, tp); + FL_KEY_SET_IF_MASKED(mask, keys, cnt, + FLOW_DISSECTOR_KEY_PORTS, tp); + FL_KEY_SET_IF_MASKED(mask, keys, cnt, + FLOW_DISSECTOR_KEY_PORTS_RANGE, tp_range); FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_IP, ip); FL_KEY_SET_IF_MASKED(mask, keys, cnt, @@ -1371,8 +1379,10 @@ static struct fl_flow_mask *fl_create_new_mask(struct cls_fl_head *head, fl_mask_copy(newmask, mask); - if ((newmask->key.tp_min.dst && newmask->key.tp_max.dst) || - (newmask->key.tp_min.src && newmask->key.tp_max.src)) + if ((newmask->key.tp_range.tp_min.dst && + newmask->key.tp_range.tp_max.dst) || + (newmask->key.tp_range.tp_min.src && + newmask->key.tp_range.tp_max.src)) newmask->flags |= TCA_FLOWER_MASK_FLAGS_RANGE; err = fl_init_mask_hashtable(newmask); @@ -1970,18 +1980,22 @@ static int fl_dump_key_val(struct sk_buff *skb, static int fl_dump_key_port_range(struct sk_buff *skb, struct fl_flow_key *key, struct fl_flow_key *mask) { - if (fl_dump_key_val(skb, &key->tp_min.dst, TCA_FLOWER_KEY_PORT_DST_MIN, - &mask->tp_min.dst, TCA_FLOWER_UNSPEC, - sizeof(key->tp_min.dst)) || - fl_dump_key_val(skb, &key->tp_max.dst, TCA_FLOWER_KEY_PORT_DST_MAX, - &mask->tp_max.dst, TCA_FLOWER_UNSPEC, - sizeof(key->tp_max.dst)) || - fl_dump_key_val(skb, &key->tp_min.src, TCA_FLOWER_KEY_PORT_SRC_MIN, - &mask->tp_min.src, TCA_FLOWER_UNSPEC, - sizeof(key->tp_min.src)) || - fl_dump_key_val(skb, &key->tp_max.src, TCA_FLOWER_KEY_PORT_SRC_MAX, - &mask->tp_max.src, TCA_FLOWER_UNSPEC, - sizeof(key->tp_max.src))) + if (fl_dump_key_val(skb, &key->tp_range.tp_min.dst, + TCA_FLOWER_KEY_PORT_DST_MIN, + &mask->tp_range.tp_min.dst, TCA_FLOWER_UNSPEC, + sizeof(key->tp_range.tp_min.dst)) || + fl_dump_key_val(skb, &key->tp_range.tp_max.dst, + TCA_FLOWER_KEY_PORT_DST_MAX, + &mask->tp_range.tp_max.dst, TCA_FLOWER_UNSPEC, + sizeof(key->tp_range.tp_max.dst)) || + fl_dump_key_val(skb, &key->tp_range.tp_min.src, + TCA_FLOWER_KEY_PORT_SRC_MIN, + &mask->tp_range.tp_min.src, TCA_FLOWER_UNSPEC, + sizeof(key->tp_range.tp_min.src)) || + fl_dump_key_val(skb, &key->tp_range.tp_max.src, + TCA_FLOWER_KEY_PORT_SRC_MAX, + &mask->tp_range.tp_max.src, TCA_FLOWER_UNSPEC, + sizeof(key->tp_range.tp_max.src))) return -1; return 0; @@ -2505,6 +2519,17 @@ static void fl_bind_class(void *fh, u32 classid, unsigned long cl) f->res.class = cl; } +static bool fl_delete_empty(struct tcf_proto *tp) +{ + struct cls_fl_head *head = fl_head_dereference(tp); + + spin_lock(&tp->lock); + tp->deleting = idr_is_empty(&head->handle_idr); + spin_unlock(&tp->lock); + + return tp->deleting; +} + static struct tcf_proto_ops cls_fl_ops __read_mostly = { .kind = "flower", .classify = fl_classify, @@ -2514,6 +2539,7 @@ static struct tcf_proto_ops cls_fl_ops __read_mostly = { .put = fl_put, .change = fl_change, .delete = fl_delete, + .delete_empty = fl_delete_empty, .walk = fl_walk, .reoffload = fl_reoffload, .hw_add = fl_hw_add, diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 53a80bc6b13a..2277369feae5 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -1769,7 +1769,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, q->avg_window_begin)); u64 b = q->avg_window_bytes * (u64)NSEC_PER_SEC; - do_div(b, window_interval); + b = div64_u64(b, window_interval); q->avg_peak_bandwidth = cake_ewma(q->avg_peak_bandwidth, b, b > q->avg_peak_bandwidth ? 2 : 8); @@ -2184,6 +2184,7 @@ static const struct nla_policy cake_policy[TCA_CAKE_MAX + 1] = { [TCA_CAKE_MPU] = { .type = NLA_U32 }, [TCA_CAKE_INGRESS] = { .type = NLA_U32 }, [TCA_CAKE_ACK_FILTER] = { .type = NLA_U32 }, + [TCA_CAKE_SPLIT_GSO] = { .type = NLA_U32 }, [TCA_CAKE_FWMARK] = { .type = NLA_U32 }, }; diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 98dd87ce1510..712ad248d6a7 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -301,6 +301,9 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) f->socket_hash != sk->sk_hash)) { f->credit = q->initial_quantum; f->socket_hash = sk->sk_hash; + if (q->rate_enable) + smp_store_release(&sk->sk_pacing_status, + SK_PACING_FQ); if (fq_flow_is_throttled(f)) fq_flow_unset_throttled(q, f); f->time_next_packet = 0ULL; @@ -322,8 +325,12 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) fq_flow_set_detached(f); f->sk = sk; - if (skb->sk == sk) + if (skb->sk == sk) { f->socket_hash = sk->sk_hash; + if (q->rate_enable) + smp_store_release(&sk->sk_pacing_status, + SK_PACING_FQ); + } f->credit = q->initial_quantum; rb_link_node(&f->fq_node, parent, p); @@ -428,17 +435,9 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, f->qlen++; qdisc_qstats_backlog_inc(sch, skb); if (fq_flow_is_detached(f)) { - struct sock *sk = skb->sk; - fq_flow_add_tail(&q->new_flows, f); if (time_after(jiffies, f->age + q->flow_refill_delay)) f->credit = max_t(u32, f->credit, q->quantum); - if (sk && q->rate_enable) { - if (unlikely(smp_load_acquire(&sk->sk_pacing_status) != - SK_PACING_FQ)) - smp_store_release(&sk->sk_pacing_status, - SK_PACING_FQ); - } q->inactive_flows--; } @@ -788,10 +787,12 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt, if (tb[TCA_FQ_QUANTUM]) { u32 quantum = nla_get_u32(tb[TCA_FQ_QUANTUM]); - if (quantum > 0) + if (quantum > 0 && quantum <= (1 << 20)) { q->quantum = quantum; - else + } else { + NL_SET_ERR_MSG_MOD(extack, "invalid quantum"); err = -EINVAL; + } } if (tb[TCA_FQ_INITIAL_QUANTUM]) diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 8769b4b8807d..7c3c5fdb82a9 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -657,7 +657,7 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc) if (likely(skb)) { qdisc_update_stats_at_dequeue(qdisc, skb); } else { - qdisc->empty = true; + WRITE_ONCE(qdisc->empty, true); } return skb; diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index 0d578333e967..e79f1afe0cfd 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -153,6 +153,7 @@ static int mq_dump(struct Qdisc *sch, struct sk_buff *skb) __gnet_stats_copy_queue(&sch->qstats, qdisc->cpu_qstats, &qdisc->qstats, qlen); + sch->q.qlen += qlen; } else { sch->q.qlen += qdisc->q.qlen; sch->bstats.bytes += qdisc->bstats.bytes; @@ -245,7 +246,8 @@ static int mq_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct netdev_queue *dev_queue = mq_queue_get(sch, cl); sch = dev_queue->qdisc_sleeping; - if (gnet_stats_copy_basic(&sch->running, d, NULL, &sch->bstats) < 0 || + if (gnet_stats_copy_basic(&sch->running, d, sch->cpu_bstats, + &sch->bstats) < 0 || qdisc_qstats_copy(d, sch) < 0) return -1; return 0; diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index 46980b8d66c5..8766ab5b8788 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -411,6 +411,7 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) __gnet_stats_copy_queue(&sch->qstats, qdisc->cpu_qstats, &qdisc->qstats, qlen); + sch->q.qlen += qlen; } else { sch->q.qlen += qdisc->q.qlen; sch->bstats.bytes += qdisc->bstats.bytes; @@ -433,7 +434,7 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) opt.offset[tc] = dev->tc_to_txq[tc].offset; } - if (nla_put(skb, TCA_OPTIONS, NLA_ALIGN(sizeof(opt)), &opt)) + if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) goto nla_put_failure; if ((priv->flags & TC_MQPRIO_F_MODE) && @@ -557,8 +558,8 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl); sch = dev_queue->qdisc_sleeping; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &sch->bstats) < 0 || + if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), d, + sch->cpu_bstats, &sch->bstats) < 0 || qdisc_qstats_copy(d, sch) < 0) return -1; } diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index b2b7fdb06fc6..1330ad224931 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -339,7 +339,7 @@ static int multiq_dump_class_stats(struct Qdisc *sch, unsigned long cl, cl_q = q->queues[cl - 1]; if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &cl_q->bstats) < 0 || + d, cl_q->cpu_bstats, &cl_q->bstats) < 0 || qdisc_qstats_copy(d, cl_q) < 0) return -1; diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 0f8fedb8809a..647941702f9f 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -292,8 +292,14 @@ static int prio_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, struct tc_prio_qopt_offload graft_offload; unsigned long band = arg - 1; - if (new == NULL) - new = &noop_qdisc; + if (!new) { + new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + TC_H_MAKE(sch->handle, arg), extack); + if (!new) + new = &noop_qdisc; + else + qdisc_hash_add(new, true); + } *old = qdisc_replace(sch, new, &q->queues[band]); @@ -356,7 +362,7 @@ static int prio_dump_class_stats(struct Qdisc *sch, unsigned long cl, cl_q = q->queues[cl - 1]; if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &cl_q->bstats) < 0 || + d, cl_q->cpu_bstats, &cl_q->bstats) < 0 || qdisc_qstats_copy(d, cl_q) < 0) return -1; diff --git a/net/sctp/associola.c b/net/sctp/associola.c index d2ffc9a0ba3a..41839b85c268 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -64,6 +64,7 @@ static struct sctp_association *sctp_association_init( /* Discarding const is appropriate here. */ asoc->ep = (struct sctp_endpoint *)ep; asoc->base.sk = (struct sock *)sk; + asoc->base.net = sock_net(sk); sctp_endpoint_hold(asoc->ep); sock_hold(asoc->base.sk); diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index ea53049d1db6..3067deb0fbec 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -110,6 +110,7 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, /* Remember who we are attached to. */ ep->base.sk = sk; + ep->base.net = sock_net(sk); sock_hold(ep->base.sk); return ep; diff --git a/net/sctp/input.c b/net/sctp/input.c index 2277981559d0..4d2bcfc9d7f8 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -882,7 +882,7 @@ static inline int sctp_hash_cmp(struct rhashtable_compare_arg *arg, if (!sctp_transport_hold(t)) return err; - if (!net_eq(sock_net(t->asoc->base.sk), x->net)) + if (!net_eq(t->asoc->base.net, x->net)) goto out; if (x->lport != htons(t->asoc->base.bind_addr.port)) goto out; @@ -897,7 +897,7 @@ static inline __u32 sctp_hash_obj(const void *data, u32 len, u32 seed) { const struct sctp_transport *t = data; - return sctp_hashfn(sock_net(t->asoc->base.sk), + return sctp_hashfn(t->asoc->base.net, htons(t->asoc->base.bind_addr.port), &t->ipaddr, seed); } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index dd860fea0148..bc734cfaa29e 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -275,7 +275,7 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final); rcu_read_unlock(); - dst = ip6_dst_lookup_flow(sk, fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p); if (!asoc || saddr) goto out; @@ -328,7 +328,7 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, fl6->saddr = laddr->a.v6.sin6_addr; fl6->fl6_sport = laddr->a.v6.sin6_port; final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final); - bdst = ip6_dst_lookup_flow(sk, fl6, final_p); + bdst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p); if (IS_ERR(bdst)) continue; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 08d14d86ecfb..681ffb3545db 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -227,6 +227,7 @@ static void sctp_v4_from_skb(union sctp_addr *addr, struct sk_buff *skb, sa->sin_port = sh->dest; sa->sin_addr.s_addr = ip_hdr(skb)->daddr; } + memset(sa->sin_zero, 0, sizeof(sa->sin_zero)); } /* Initialize an sctp_addr from a socket. */ @@ -235,6 +236,7 @@ static void sctp_v4_from_sk(union sctp_addr *addr, struct sock *sk) addr->v4.sin_family = AF_INET; addr->v4.sin_port = 0; addr->v4.sin_addr.s_addr = inet_sk(sk)->inet_rcv_saddr; + memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); } /* Initialize sk->sk_rcv_saddr from sctp_addr. */ @@ -257,6 +259,7 @@ static void sctp_v4_from_addr_param(union sctp_addr *addr, addr->v4.sin_family = AF_INET; addr->v4.sin_port = port; addr->v4.sin_addr.s_addr = param->v4.addr.s_addr; + memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); } /* Initialize an address parameter from a sctp_addr and return the length @@ -281,6 +284,7 @@ static void sctp_v4_dst_saddr(union sctp_addr *saddr, struct flowi4 *fl4, saddr->v4.sin_family = AF_INET; saddr->v4.sin_port = port; saddr->v4.sin_addr.s_addr = fl4->saddr; + memset(saddr->v4.sin_zero, 0, sizeof(saddr->v4.sin_zero)); } /* Compare two addresses exactly. */ @@ -303,6 +307,7 @@ static void sctp_v4_inaddr_any(union sctp_addr *addr, __be16 port) addr->v4.sin_family = AF_INET; addr->v4.sin_addr.s_addr = htonl(INADDR_ANY); addr->v4.sin_port = port; + memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); } /* Is this a wildcard address? */ diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index e52b2128e43b..b06cae508158 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -1358,8 +1358,10 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type, /* Generate an INIT ACK chunk. */ new_obj = sctp_make_init_ack(asoc, chunk, GFP_ATOMIC, 0); - if (!new_obj) - goto nomem; + if (!new_obj) { + error = -ENOMEM; + break; + } sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(new_obj)); @@ -1381,7 +1383,8 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type, if (!new_obj) { if (cmd->obj.chunk) sctp_chunk_free(cmd->obj.chunk); - goto nomem; + error = -ENOMEM; + break; } sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(new_obj)); @@ -1428,8 +1431,10 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type, /* Generate a SHUTDOWN chunk. */ new_obj = sctp_make_shutdown(asoc, chunk); - if (!new_obj) - goto nomem; + if (!new_obj) { + error = -ENOMEM; + break; + } sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(new_obj)); break; @@ -1765,11 +1770,17 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type, break; } - if (error) + if (error) { + cmd = sctp_next_cmd(commands); + while (cmd) { + if (cmd->verb == SCTP_CMD_REPLY) + sctp_chunk_free(cmd->obj.chunk); + cmd = sctp_next_cmd(commands); + } break; + } } -out: /* If this is in response to a received chunk, wait until * we are done with the packet to open the queue so that we don't * send multiple packets in response to a single request. @@ -1784,7 +1795,4 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type, sp->data_ready_signalled = 0; return error; -nomem: - error = -ENOMEM; - goto out; } diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 0c21c52fc408..4ab8208a2dd4 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -2160,8 +2160,10 @@ enum sctp_disposition sctp_sf_do_5_2_4_dupcook( /* Update socket peer label if first association. */ if (security_sctp_assoc_request((struct sctp_endpoint *)ep, - chunk->skb)) + chunk->skb)) { + sctp_association_free(new_asoc); return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + } /* Set temp so that it won't be added into hashtable */ new_asoc->temp = 1; diff --git a/net/sctp/stream.c b/net/sctp/stream.c index e83cdaa2ab76..c1a100d2fed3 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -119,7 +119,7 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, * a new one with new outcnt to save memory if needed. */ if (outcnt == stream->outcnt) - goto in; + goto handle_in; /* Filter out chunks queued on streams that won't exist anymore */ sched->unsched_all(stream); @@ -128,24 +128,28 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, ret = sctp_stream_alloc_out(stream, outcnt, gfp); if (ret) - goto out; + goto out_err; for (i = 0; i < stream->outcnt; i++) SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN; -in: +handle_in: sctp_stream_interleave_init(stream); if (!incnt) goto out; ret = sctp_stream_alloc_in(stream, incnt, gfp); - if (ret) { - sched->free(stream); - genradix_free(&stream->out); - stream->outcnt = 0; - goto out; - } + if (ret) + goto in_err; + goto out; + +in_err: + sched->free(stream); + genradix_free(&stream->in); +out_err: + genradix_free(&stream->out); + stream->outcnt = 0; out: return ret; } diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 7235a6032671..3bbe1a58ec87 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -263,7 +263,7 @@ bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu) pf->af->from_sk(&addr, sk); pf->to_sk_daddr(&t->ipaddr, sk); - dst->ops->update_pmtu(dst, sk, NULL, pmtu); + dst->ops->update_pmtu(dst, sk, NULL, pmtu, true); pf->to_sk_daddr(&addr, sk); dst = sctp_transport_dst_check(t); diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 737b49909a7a..6a6d3b2aa5a9 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -854,6 +854,8 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr, goto out; sock_hold(&smc->sk); /* sock put in passive closing */ + if (smc->use_fallback) + goto out; if (flags & O_NONBLOCK) { if (schedule_work(&smc->connect_work)) smc->connect_nonblock = 1; @@ -1716,8 +1718,6 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, sk->sk_err = smc->clcsock->sk->sk_err; sk->sk_error_report(sk); } - if (rc) - return rc; if (optlen < sizeof(int)) return -EINVAL; @@ -1725,6 +1725,8 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, return -EFAULT; lock_sock(sk); + if (rc || smc->use_fallback) + goto out; switch (optname) { case TCP_ULP: case TCP_FASTOPEN: @@ -1736,15 +1738,14 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, smc_switch_to_fallback(smc); smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP; } else { - if (!smc->use_fallback) - rc = -EINVAL; + rc = -EINVAL; } break; case TCP_NODELAY: if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_CLOSED) { - if (val && !smc->use_fallback) + if (val) mod_delayed_work(system_wq, &smc->conn.tx_work, 0); } @@ -1753,7 +1754,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_CLOSED) { - if (!val && !smc->use_fallback) + if (!val) mod_delayed_work(system_wq, &smc->conn.tx_work, 0); } @@ -1764,6 +1765,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, default: break; } +out: release_sock(sk); return rc; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 2ba97ff325a5..0c5fcb8ed404 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -231,10 +231,12 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini) lgr->conns_all = RB_ROOT; if (ini->is_smcd) { /* SMC-D specific settings */ + get_device(&ini->ism_dev->dev); lgr->peer_gid = ini->ism_gid; lgr->smcd = ini->ism_dev; } else { /* SMC-R specific settings */ + get_device(&ini->ib_dev->ibdev->dev); lgr->role = smc->listen_smc ? SMC_SERV : SMC_CLNT; memcpy(lgr->peer_systemid, ini->ib_lcl->id_for_peer, SMC_SYSTEMID_LEN); @@ -433,10 +435,13 @@ static void smc_lgr_free_bufs(struct smc_link_group *lgr) static void smc_lgr_free(struct smc_link_group *lgr) { smc_lgr_free_bufs(lgr); - if (lgr->is_smcd) + if (lgr->is_smcd) { smc_ism_put_vlan(lgr->smcd, lgr->vlan_id); - else + put_device(&lgr->smcd->dev); + } else { smc_link_clear(&lgr->lnk[SMC_SINGLE_LINK]); + put_device(&lgr->lnk[SMC_SINGLE_LINK].smcibdev->ibdev->dev); + } kfree(lgr); } diff --git a/net/socket.c b/net/socket.c index 6a9ab7a8b1d2..432800b39ddb 100644 --- a/net/socket.c +++ b/net/socket.c @@ -955,7 +955,7 @@ static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to) .msg_iocb = iocb}; ssize_t res; - if (file->f_flags & O_NONBLOCK) + if (file->f_flags & O_NONBLOCK || (iocb->ki_flags & IOCB_NOWAIT)) msg.msg_flags = MSG_DONTWAIT; if (iocb->ki_pos != 0) @@ -980,7 +980,7 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from) if (iocb->ki_pos != 0) return -ESPIPE; - if (file->f_flags & O_NONBLOCK) + if (file->f_flags & O_NONBLOCK || (iocb->ki_flags & IOCB_NOWAIT)) msg.msg_flags = MSG_DONTWAIT; if (sock->type == SOCK_SEQPACKET) @@ -2232,15 +2232,10 @@ static int copy_msghdr_from_user(struct msghdr *kmsg, return err < 0 ? err : 0; } -static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, - struct msghdr *msg_sys, unsigned int flags, - struct used_address *used_address, - unsigned int allowed_msghdr_flags) +static int ____sys_sendmsg(struct socket *sock, struct msghdr *msg_sys, + unsigned int flags, struct used_address *used_address, + unsigned int allowed_msghdr_flags) { - struct compat_msghdr __user *msg_compat = - (struct compat_msghdr __user *)msg; - struct sockaddr_storage address; - struct iovec iovstack[UIO_FASTIOV], *iov = iovstack; unsigned char ctl[sizeof(struct cmsghdr) + 20] __aligned(sizeof(__kernel_size_t)); /* 20 is size of ipv6_pktinfo */ @@ -2248,19 +2243,10 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, int ctl_len; ssize_t err; - msg_sys->msg_name = &address; - - if (MSG_CMSG_COMPAT & flags) - err = get_compat_msghdr(msg_sys, msg_compat, NULL, &iov); - else - err = copy_msghdr_from_user(msg_sys, msg, NULL, &iov); - if (err < 0) - return err; - err = -ENOBUFS; if (msg_sys->msg_controllen > INT_MAX) - goto out_freeiov; + goto out; flags |= (msg_sys->msg_flags & allowed_msghdr_flags); ctl_len = msg_sys->msg_controllen; if ((MSG_CMSG_COMPAT & flags) && ctl_len) { @@ -2268,7 +2254,7 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, cmsghdr_from_user_compat_to_kern(msg_sys, sock->sk, ctl, sizeof(ctl)); if (err) - goto out_freeiov; + goto out; ctl_buf = msg_sys->msg_control; ctl_len = msg_sys->msg_controllen; } else if (ctl_len) { @@ -2277,7 +2263,7 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, if (ctl_len > sizeof(ctl)) { ctl_buf = sock_kmalloc(sock->sk, ctl_len, GFP_KERNEL); if (ctl_buf == NULL) - goto out_freeiov; + goto out; } err = -EFAULT; /* @@ -2323,7 +2309,47 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, out_freectl: if (ctl_buf != ctl) sock_kfree_s(sock->sk, ctl_buf, ctl_len); -out_freeiov: +out: + return err; +} + +static int sendmsg_copy_msghdr(struct msghdr *msg, + struct user_msghdr __user *umsg, unsigned flags, + struct iovec **iov) +{ + int err; + + if (flags & MSG_CMSG_COMPAT) { + struct compat_msghdr __user *msg_compat; + + msg_compat = (struct compat_msghdr __user *) umsg; + err = get_compat_msghdr(msg, msg_compat, NULL, iov); + } else { + err = copy_msghdr_from_user(msg, umsg, NULL, iov); + } + if (err < 0) + return err; + + return 0; +} + +static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, + struct msghdr *msg_sys, unsigned int flags, + struct used_address *used_address, + unsigned int allowed_msghdr_flags) +{ + struct sockaddr_storage address; + struct iovec iovstack[UIO_FASTIOV], *iov = iovstack; + ssize_t err; + + msg_sys->msg_name = &address; + + err = sendmsg_copy_msghdr(msg_sys, msg, flags, &iov); + if (err < 0) + return err; + + err = ____sys_sendmsg(sock, msg_sys, flags, used_address, + allowed_msghdr_flags); kfree(iov); return err; } @@ -2331,12 +2357,27 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, /* * BSD sendmsg interface */ -long __sys_sendmsg_sock(struct socket *sock, struct user_msghdr __user *msg, +long __sys_sendmsg_sock(struct socket *sock, struct user_msghdr __user *umsg, unsigned int flags) { - struct msghdr msg_sys; + struct iovec iovstack[UIO_FASTIOV], *iov = iovstack; + struct sockaddr_storage address; + struct msghdr msg = { .msg_name = &address }; + ssize_t err; + + err = sendmsg_copy_msghdr(&msg, umsg, flags, &iov); + if (err) + return err; + /* disallow ancillary data requests from this path */ + if (msg.msg_control || msg.msg_controllen) { + err = -EINVAL; + goto out; + } - return ___sys_sendmsg(sock, msg, &msg_sys, flags, NULL, 0); + err = ____sys_sendmsg(sock, &msg, flags, NULL, 0); +out: + kfree(iov); + return err; } long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned int flags, @@ -2442,33 +2483,41 @@ SYSCALL_DEFINE4(sendmmsg, int, fd, struct mmsghdr __user *, mmsg, return __sys_sendmmsg(fd, mmsg, vlen, flags, true); } -static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg, - struct msghdr *msg_sys, unsigned int flags, int nosec) +static int recvmsg_copy_msghdr(struct msghdr *msg, + struct user_msghdr __user *umsg, unsigned flags, + struct sockaddr __user **uaddr, + struct iovec **iov) { - struct compat_msghdr __user *msg_compat = - (struct compat_msghdr __user *)msg; - struct iovec iovstack[UIO_FASTIOV]; - struct iovec *iov = iovstack; - unsigned long cmsg_ptr; - int len; ssize_t err; - /* kernel mode address */ - struct sockaddr_storage addr; + if (MSG_CMSG_COMPAT & flags) { + struct compat_msghdr __user *msg_compat; - /* user mode address pointers */ - struct sockaddr __user *uaddr; - int __user *uaddr_len = COMPAT_NAMELEN(msg); - - msg_sys->msg_name = &addr; - - if (MSG_CMSG_COMPAT & flags) - err = get_compat_msghdr(msg_sys, msg_compat, &uaddr, &iov); - else - err = copy_msghdr_from_user(msg_sys, msg, &uaddr, &iov); + msg_compat = (struct compat_msghdr __user *) umsg; + err = get_compat_msghdr(msg, msg_compat, uaddr, iov); + } else { + err = copy_msghdr_from_user(msg, umsg, uaddr, iov); + } if (err < 0) return err; + return 0; +} + +static int ____sys_recvmsg(struct socket *sock, struct msghdr *msg_sys, + struct user_msghdr __user *msg, + struct sockaddr __user *uaddr, + unsigned int flags, int nosec) +{ + struct compat_msghdr __user *msg_compat = + (struct compat_msghdr __user *) msg; + int __user *uaddr_len = COMPAT_NAMELEN(msg); + struct sockaddr_storage addr; + unsigned long cmsg_ptr; + int len; + ssize_t err; + + msg_sys->msg_name = &addr; cmsg_ptr = (unsigned long)msg_sys->msg_control; msg_sys->msg_flags = flags & (MSG_CMSG_CLOEXEC|MSG_CMSG_COMPAT); @@ -2479,7 +2528,7 @@ static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg, flags |= MSG_DONTWAIT; err = (nosec ? sock_recvmsg_nosec : sock_recvmsg)(sock, msg_sys, flags); if (err < 0) - goto out_freeiov; + goto out; len = err; if (uaddr != NULL) { @@ -2487,12 +2536,12 @@ static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg, msg_sys->msg_namelen, uaddr, uaddr_len); if (err < 0) - goto out_freeiov; + goto out; } err = __put_user((msg_sys->msg_flags & ~MSG_CMSG_COMPAT), COMPAT_FLAGS(msg)); if (err) - goto out_freeiov; + goto out; if (MSG_CMSG_COMPAT & flags) err = __put_user((unsigned long)msg_sys->msg_control - cmsg_ptr, &msg_compat->msg_controllen); @@ -2500,10 +2549,25 @@ static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg, err = __put_user((unsigned long)msg_sys->msg_control - cmsg_ptr, &msg->msg_controllen); if (err) - goto out_freeiov; + goto out; err = len; +out: + return err; +} + +static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg, + struct msghdr *msg_sys, unsigned int flags, int nosec) +{ + struct iovec iovstack[UIO_FASTIOV], *iov = iovstack; + /* user mode address pointers */ + struct sockaddr __user *uaddr; + ssize_t err; + + err = recvmsg_copy_msghdr(msg_sys, msg, flags, &uaddr, &iov); + if (err < 0) + return err; -out_freeiov: + err = ____sys_recvmsg(sock, msg_sys, msg, uaddr, flags, nosec); kfree(iov); return err; } @@ -2512,12 +2576,28 @@ static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg, * BSD recvmsg interface */ -long __sys_recvmsg_sock(struct socket *sock, struct user_msghdr __user *msg, +long __sys_recvmsg_sock(struct socket *sock, struct user_msghdr __user *umsg, unsigned int flags) { - struct msghdr msg_sys; + struct iovec iovstack[UIO_FASTIOV], *iov = iovstack; + struct sockaddr_storage address; + struct msghdr msg = { .msg_name = &address }; + struct sockaddr __user *uaddr; + ssize_t err; + + err = recvmsg_copy_msghdr(&msg, umsg, flags, &uaddr, &iov); + if (err) + return err; + /* disallow ancillary data requests from this path */ + if (msg.msg_control || msg.msg_controllen) { + err = -EINVAL; + goto out; + } - return ___sys_recvmsg(sock, msg, &msg_sys, flags, 0); + err = ____sys_recvmsg(sock, &msg, umsg, uaddr, flags, 0); +out: + kfree(iov); + return err; } long __sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned int flags, @@ -3452,6 +3532,7 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, case SIOCSARP: case SIOCGARP: case SIOCDARP: + case SIOCOUTQNSD: case SIOCATMARK: return sock_do_ioctl(net, sock, cmd, arg); } diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index a349094f6fb7..f740cb51802a 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -53,9 +53,6 @@ static void cache_init(struct cache_head *h, struct cache_detail *detail) h->last_refresh = now; } -static inline int cache_is_valid(struct cache_head *h); -static void cache_fresh_locked(struct cache_head *head, time_t expiry, - struct cache_detail *detail); static void cache_fresh_unlocked(struct cache_head *head, struct cache_detail *detail); @@ -105,9 +102,6 @@ static struct cache_head *sunrpc_cache_add_entry(struct cache_detail *detail, if (cache_is_expired(detail, tmp)) { hlist_del_init_rcu(&tmp->cache_list); detail->entries --; - if (cache_is_valid(tmp) == -EAGAIN) - set_bit(CACHE_NEGATIVE, &tmp->flags); - cache_fresh_locked(tmp, 0, detail); freeme = tmp; break; } diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 360afe153193..987c4b1f0b17 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -260,7 +260,7 @@ static void __rpc_init_priority_wait_queue(struct rpc_wait_queue *queue, const c rpc_reset_waitqueue_priority(queue); queue->qlen = 0; queue->timer_list.expires = 0; - INIT_DEFERRABLE_WORK(&queue->timer_list.dwork, __rpc_queue_timer_fn); + INIT_DELAYED_WORK(&queue->timer_list.dwork, __rpc_queue_timer_fn); INIT_LIST_HEAD(&queue->timer_list.list); rpc_assign_waitqueue_name(queue, qname); } diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 30065a28628c..9901a811f598 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -570,7 +570,6 @@ void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) */ bad_wr = NULL; rc = ib_post_send(r_xprt->rx_ia.ri_id->qp, first, &bad_wr); - trace_xprtrdma_post_send(req, rc); /* The final LOCAL_INV WR in the chain is supposed to * do the wake. If it was never posted, the wake will @@ -583,6 +582,7 @@ void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) /* Recycle MRs in the LOCAL_INV chain that did not get posted. */ + trace_xprtrdma_post_linv(req, rc); while (bad_wr) { frwr = container_of(bad_wr, struct rpcrdma_frwr, fr_invwr); @@ -673,12 +673,12 @@ void frwr_unmap_async(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) */ bad_wr = NULL; rc = ib_post_send(r_xprt->rx_ia.ri_id->qp, first, &bad_wr); - trace_xprtrdma_post_send(req, rc); if (!rc) return; /* Recycle MRs in the LOCAL_INV chain that did not get posted. */ + trace_xprtrdma_post_linv(req, rc); while (bad_wr) { frwr = container_of(bad_wr, struct rpcrdma_frwr, fr_invwr); mr = container_of(frwr, struct rpcrdma_mr, frwr); diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index b86b5fd62d9f..ef5102b60589 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -1362,6 +1362,7 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *rep) xprt->cwnd = credits << RPC_CWNDSHIFT; spin_unlock(&xprt->transport_lock); } + rpcrdma_post_recvs(r_xprt, false); req = rpcr_to_rdmar(rqst); if (req->rl_reply) { diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 160558b4135e..c67d465dc062 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -428,8 +428,11 @@ void xprt_rdma_close(struct rpc_xprt *xprt) /* Prepare @xprt for the next connection by reinitializing * its credit grant to one (see RFC 8166, Section 3.3.3). */ + spin_lock(&xprt->transport_lock); r_xprt->rx_buf.rb_credits = 1; + xprt->cong = 0; xprt->cwnd = RPC_CWNDSHIFT; + spin_unlock(&xprt->transport_lock); out: xprt->reestablish_timeout = 0; diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 3a907537e2cf..0f4d39fdb48f 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -75,16 +75,15 @@ * internal functions */ static void rpcrdma_sendctx_put_locked(struct rpcrdma_sendctx *sc); -static void rpcrdma_reps_destroy(struct rpcrdma_buffer *buf); +static void rpcrdma_reqs_reset(struct rpcrdma_xprt *r_xprt); +static void rpcrdma_reps_unmap(struct rpcrdma_xprt *r_xprt); static void rpcrdma_mrs_create(struct rpcrdma_xprt *r_xprt); static void rpcrdma_mrs_destroy(struct rpcrdma_buffer *buf); -static void rpcrdma_mr_free(struct rpcrdma_mr *mr); static struct rpcrdma_regbuf * rpcrdma_regbuf_alloc(size_t size, enum dma_data_direction direction, gfp_t flags); static void rpcrdma_regbuf_dma_unmap(struct rpcrdma_regbuf *rb); static void rpcrdma_regbuf_free(struct rpcrdma_regbuf *rb); -static void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp); /* Wait for outstanding transport work to finish. ib_drain_qp * handles the drains in the wrong order for us, so open code @@ -170,7 +169,6 @@ rpcrdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc) rdmab_addr(rep->rr_rdmabuf), wc->byte_len, DMA_FROM_DEVICE); - rpcrdma_post_recvs(r_xprt, false); rpcrdma_reply_handler(rep); return; @@ -247,6 +245,7 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) ia->ri_id->device->name, rpcrdma_addrstr(r_xprt), rpcrdma_portstr(r_xprt)); #endif + init_completion(&ia->ri_remove_done); set_bit(RPCRDMA_IAF_REMOVING, &ia->ri_flags); ep->rep_connected = -ENODEV; xprt_force_disconnect(xprt); @@ -301,7 +300,6 @@ rpcrdma_create_id(struct rpcrdma_xprt *xprt, struct rpcrdma_ia *ia) trace_xprtrdma_conn_start(xprt); init_completion(&ia->ri_done); - init_completion(&ia->ri_remove_done); id = rdma_create_id(xprt->rx_xprt.xprt_net, rpcrdma_cm_event_handler, xprt, RDMA_PS_TCP, IB_QPT_RC); @@ -431,7 +429,7 @@ rpcrdma_ia_remove(struct rpcrdma_ia *ia) /* The ULP is responsible for ensuring all DMA * mappings and MRs are gone. */ - rpcrdma_reps_destroy(buf); + rpcrdma_reps_unmap(r_xprt); list_for_each_entry(req, &buf->rb_allreqs, rl_all) { rpcrdma_regbuf_dma_unmap(req->rl_rdmabuf); rpcrdma_regbuf_dma_unmap(req->rl_sendbuf); @@ -609,6 +607,7 @@ static int rpcrdma_ep_recreate_xprt(struct rpcrdma_xprt *r_xprt, struct ib_qp_init_attr *qp_init_attr) { struct rpcrdma_ia *ia = &r_xprt->rx_ia; + struct rpcrdma_ep *ep = &r_xprt->rx_ep; int rc, err; trace_xprtrdma_reinsert(r_xprt); @@ -623,6 +622,7 @@ static int rpcrdma_ep_recreate_xprt(struct rpcrdma_xprt *r_xprt, pr_err("rpcrdma: rpcrdma_ep_create returned %d\n", err); goto out2; } + memcpy(qp_init_attr, &ep->rep_attr, sizeof(*qp_init_attr)); rc = -ENETUNREACH; err = rdma_create_qp(ia->ri_id, ia->ri_pd, qp_init_attr); @@ -780,6 +780,7 @@ rpcrdma_ep_disconnect(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia) trace_xprtrdma_disconnect(r_xprt, rc); rpcrdma_xprt_drain(r_xprt); + rpcrdma_reqs_reset(r_xprt); } /* Fixed-size circular FIFO queue. This implementation is wait-free and @@ -965,7 +966,7 @@ rpcrdma_mrs_create(struct rpcrdma_xprt *r_xprt) mr->mr_xprt = r_xprt; spin_lock(&buf->rb_lock); - list_add(&mr->mr_list, &buf->rb_mrs); + rpcrdma_mr_push(mr, &buf->rb_mrs); list_add(&mr->mr_all, &buf->rb_all_mrs); spin_unlock(&buf->rb_lock); } @@ -1042,6 +1043,26 @@ struct rpcrdma_req *rpcrdma_req_create(struct rpcrdma_xprt *r_xprt, size_t size, return NULL; } +/** + * rpcrdma_reqs_reset - Reset all reqs owned by a transport + * @r_xprt: controlling transport instance + * + * ASSUMPTION: the rb_allreqs list is stable for the duration, + * and thus can be walked without holding rb_lock. Eg. the + * caller is holding the transport send lock to exclude + * device removal or disconnection. + */ +static void rpcrdma_reqs_reset(struct rpcrdma_xprt *r_xprt) +{ + struct rpcrdma_buffer *buf = &r_xprt->rx_buf; + struct rpcrdma_req *req; + + list_for_each_entry(req, &buf->rb_allreqs, rl_all) { + /* Credits are valid only for one connection */ + req->rl_slot.rq_cong = 0; + } +} + static struct rpcrdma_rep *rpcrdma_rep_create(struct rpcrdma_xprt *r_xprt, bool temp) { @@ -1065,6 +1086,7 @@ static struct rpcrdma_rep *rpcrdma_rep_create(struct rpcrdma_xprt *r_xprt, rep->rr_recv_wr.sg_list = &rep->rr_rdmabuf->rg_iov; rep->rr_recv_wr.num_sge = 1; rep->rr_temp = temp; + list_add(&rep->rr_all, &r_xprt->rx_buf.rb_all_reps); return rep; out_free: @@ -1075,6 +1097,7 @@ static struct rpcrdma_rep *rpcrdma_rep_create(struct rpcrdma_xprt *r_xprt, static void rpcrdma_rep_destroy(struct rpcrdma_rep *rep) { + list_del(&rep->rr_all); rpcrdma_regbuf_free(rep->rr_rdmabuf); kfree(rep); } @@ -1093,10 +1116,16 @@ static struct rpcrdma_rep *rpcrdma_rep_get_locked(struct rpcrdma_buffer *buf) static void rpcrdma_rep_put(struct rpcrdma_buffer *buf, struct rpcrdma_rep *rep) { - if (!rep->rr_temp) - llist_add(&rep->rr_node, &buf->rb_free_reps); - else - rpcrdma_rep_destroy(rep); + llist_add(&rep->rr_node, &buf->rb_free_reps); +} + +static void rpcrdma_reps_unmap(struct rpcrdma_xprt *r_xprt) +{ + struct rpcrdma_buffer *buf = &r_xprt->rx_buf; + struct rpcrdma_rep *rep; + + list_for_each_entry(rep, &buf->rb_all_reps, rr_all) + rpcrdma_regbuf_dma_unmap(rep->rr_rdmabuf); } static void rpcrdma_reps_destroy(struct rpcrdma_buffer *buf) @@ -1129,6 +1158,7 @@ int rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) INIT_LIST_HEAD(&buf->rb_send_bufs); INIT_LIST_HEAD(&buf->rb_allreqs); + INIT_LIST_HEAD(&buf->rb_all_reps); rc = -ENOMEM; for (i = 0; i < buf->rb_max_requests; i++) { @@ -1163,10 +1193,19 @@ int rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) */ void rpcrdma_req_destroy(struct rpcrdma_req *req) { + struct rpcrdma_mr *mr; + list_del(&req->rl_all); - while (!list_empty(&req->rl_free_mrs)) - rpcrdma_mr_free(rpcrdma_mr_pop(&req->rl_free_mrs)); + while ((mr = rpcrdma_mr_pop(&req->rl_free_mrs))) { + struct rpcrdma_buffer *buf = &mr->mr_xprt->rx_buf; + + spin_lock(&buf->rb_lock); + list_del(&mr->mr_all); + spin_unlock(&buf->rb_lock); + + frwr_release_mr(mr); + } rpcrdma_regbuf_free(req->rl_recvbuf); rpcrdma_regbuf_free(req->rl_sendbuf); @@ -1174,24 +1213,28 @@ void rpcrdma_req_destroy(struct rpcrdma_req *req) kfree(req); } -static void -rpcrdma_mrs_destroy(struct rpcrdma_buffer *buf) +/** + * rpcrdma_mrs_destroy - Release all of a transport's MRs + * @buf: controlling buffer instance + * + * Relies on caller holding the transport send lock to protect + * removing mr->mr_list from req->rl_free_mrs safely. + */ +static void rpcrdma_mrs_destroy(struct rpcrdma_buffer *buf) { struct rpcrdma_xprt *r_xprt = container_of(buf, struct rpcrdma_xprt, rx_buf); struct rpcrdma_mr *mr; - unsigned int count; - count = 0; spin_lock(&buf->rb_lock); while ((mr = list_first_entry_or_null(&buf->rb_all_mrs, struct rpcrdma_mr, mr_all)) != NULL) { + list_del(&mr->mr_list); list_del(&mr->mr_all); spin_unlock(&buf->rb_lock); frwr_release_mr(mr); - count++; spin_lock(&buf->rb_lock); } spin_unlock(&buf->rb_lock); @@ -1264,17 +1307,6 @@ void rpcrdma_mr_put(struct rpcrdma_mr *mr) rpcrdma_mr_push(mr, &mr->mr_req->rl_free_mrs); } -static void rpcrdma_mr_free(struct rpcrdma_mr *mr) -{ - struct rpcrdma_xprt *r_xprt = mr->mr_xprt; - struct rpcrdma_buffer *buf = &r_xprt->rx_buf; - - mr->mr_req = NULL; - spin_lock(&buf->rb_lock); - rpcrdma_mr_push(mr, &buf->rb_mrs); - spin_unlock(&buf->rb_lock); -} - /** * rpcrdma_buffer_get - Get a request buffer * @buffers: Buffer pool from which to obtain a buffer @@ -1455,8 +1487,13 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia, return 0; } -static void -rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp) +/** + * rpcrdma_post_recvs - Refill the Receive Queue + * @r_xprt: controlling transport instance + * @temp: mark Receive buffers to be deleted after use + * + */ +void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp) { struct rpcrdma_buffer *buf = &r_xprt->rx_buf; struct rpcrdma_ep *ep = &r_xprt->rx_ep; @@ -1478,6 +1515,10 @@ rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp) wr = NULL; while (needed) { rep = rpcrdma_rep_get_locked(buf); + if (rep && rep->rr_temp) { + rpcrdma_rep_destroy(rep); + continue; + } if (!rep) rep = rpcrdma_rep_create(r_xprt, temp); if (!rep) diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 65e6b0eb862e..fc761679487c 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -203,6 +203,7 @@ struct rpcrdma_rep { struct xdr_stream rr_stream; struct llist_node rr_node; struct ib_recv_wr rr_recv_wr; + struct list_head rr_all; }; /* To reduce the rate at which a transport invokes ib_post_recv @@ -372,6 +373,7 @@ struct rpcrdma_buffer { struct list_head rb_allreqs; struct list_head rb_all_mrs; + struct list_head rb_all_reps; struct llist_head rb_free_reps; @@ -474,6 +476,7 @@ void rpcrdma_ep_disconnect(struct rpcrdma_ep *, struct rpcrdma_ia *); int rpcrdma_ep_post(struct rpcrdma_ia *, struct rpcrdma_ep *, struct rpcrdma_req *); +void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp); /* * Buffer calls - xprtrdma/verbs.c diff --git a/net/tipc/core.c b/net/tipc/core.c index 8f35060a24e1..12192e7f4050 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -125,14 +125,6 @@ static int __init tipc_init(void) sysctl_tipc_rmem[1] = RCVBUF_DEF; sysctl_tipc_rmem[2] = RCVBUF_MAX; - err = tipc_netlink_start(); - if (err) - goto out_netlink; - - err = tipc_netlink_compat_start(); - if (err) - goto out_netlink_compat; - err = tipc_register_sysctl(); if (err) goto out_sysctl; @@ -153,8 +145,21 @@ static int __init tipc_init(void) if (err) goto out_bearer; + err = tipc_netlink_start(); + if (err) + goto out_netlink; + + err = tipc_netlink_compat_start(); + if (err) + goto out_netlink_compat; + pr_info("Started in single node mode\n"); return 0; + +out_netlink_compat: + tipc_netlink_stop(); +out_netlink: + tipc_bearer_cleanup(); out_bearer: unregister_pernet_device(&tipc_topsrv_net_ops); out_pernet_topsrv: @@ -164,22 +169,18 @@ static int __init tipc_init(void) out_pernet: tipc_unregister_sysctl(); out_sysctl: - tipc_netlink_compat_stop(); -out_netlink_compat: - tipc_netlink_stop(); -out_netlink: pr_err("Unable to start in single node mode\n"); return err; } static void __exit tipc_exit(void) { + tipc_netlink_compat_stop(); + tipc_netlink_stop(); tipc_bearer_cleanup(); unregister_pernet_device(&tipc_topsrv_net_ops); tipc_socket_stop(); unregister_pernet_device(&tipc_net_ops); - tipc_netlink_stop(); - tipc_netlink_compat_stop(); tipc_unregister_sysctl(); pr_info("Deactivated\n"); diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index e135d4e11231..d4d2928424e2 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -550,7 +550,7 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg, if (len <= 0) return -EINVAL; - len = min_t(int, len, TIPC_MAX_BEARER_NAME); + len = min_t(int, len, TIPC_MAX_LINK_NAME); if (!string_is_valid(name, len)) return -EINVAL; @@ -822,7 +822,7 @@ static int tipc_nl_compat_link_reset_stats(struct tipc_nl_compat_cmd_doit *cmd, if (len <= 0) return -EINVAL; - len = min_t(int, len, TIPC_MAX_BEARER_NAME); + len = min_t(int, len, TIPC_MAX_LINK_NAME); if (!string_is_valid(name, len)) return -EINVAL; diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 287df68721df..186c78431217 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -195,10 +195,13 @@ static int tipc_udp_xmit(struct net *net, struct sk_buff *skb, .saddr = src->ipv6, .flowi6_proto = IPPROTO_UDP }; - err = ipv6_stub->ipv6_dst_lookup(net, ub->ubsock->sk, - &ndst, &fl6); - if (err) + ndst = ipv6_stub->ipv6_dst_lookup_flow(net, + ub->ubsock->sk, + &fl6, NULL); + if (IS_ERR(ndst)) { + err = PTR_ERR(ndst); goto tx_error; + } dst_cache_set_ip6(cache, ndst, &fl6.saddr); } ttl = ip6_dst_hoplimit(ndst); diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 683d00837693..3f5209e2d4ee 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -417,7 +417,7 @@ static int tls_push_data(struct sock *sk, if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SENDPAGE_NOTLAST)) - return -ENOTSUPP; + return -EOPNOTSUPP; if (sk->sk_err) return -sk->sk_err; @@ -560,7 +560,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page, lock_sock(sk); if (flags & MSG_OOB) { - rc = -ENOTSUPP; + rc = -EOPNOTSUPP; goto out; } @@ -999,7 +999,7 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx) } if (!(netdev->features & NETIF_F_HW_TLS_TX)) { - rc = -ENOTSUPP; + rc = -EOPNOTSUPP; goto release_netdev; } @@ -1071,7 +1071,7 @@ int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx) } if (!(netdev->features & NETIF_F_HW_TLS_RX)) { - rc = -ENOTSUPP; + rc = -EOPNOTSUPP; goto release_netdev; } diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index f874cc0da45d..82d0beed8f07 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -209,24 +209,15 @@ int tls_push_partial_record(struct sock *sk, struct tls_context *ctx, return tls_push_sg(sk, ctx, sg, offset, flags); } -bool tls_free_partial_record(struct sock *sk, struct tls_context *ctx) +void tls_free_partial_record(struct sock *sk, struct tls_context *ctx) { struct scatterlist *sg; - sg = ctx->partially_sent_record; - if (!sg) - return false; - - while (1) { + for (sg = ctx->partially_sent_record; sg; sg = sg_next(sg)) { put_page(sg_page(sg)); sk_mem_uncharge(sk, sg->length); - - if (sg_is_last(sg)) - break; - sg++; } ctx->partially_sent_record = NULL; - return true; } static void tls_write_space(struct sock *sk) @@ -491,7 +482,7 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, /* check version */ if (crypto_info->version != TLS_1_2_VERSION && crypto_info->version != TLS_1_3_VERSION) { - rc = -ENOTSUPP; + rc = -EINVAL; goto err_crypto_info; } @@ -787,7 +778,7 @@ static int tls_init(struct sock *sk) * share the ulp context. */ if (sk->sk_state != TCP_ESTABLISHED) - return -ENOTSUPP; + return -ENOTCONN; tls_build_proto(sk); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 319735d5c084..c70cf30c5492 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -705,8 +705,7 @@ static int tls_push_record(struct sock *sk, int flags, } i = msg_pl->sg.start; - sg_chain(rec->sg_aead_in, 2, rec->inplace_crypto ? - &msg_en->sg.data[i] : &msg_pl->sg.data[i]); + sg_chain(rec->sg_aead_in, 2, &msg_pl->sg.data[i]); i = msg_en->sg.end; sk_msg_iter_var_prev(i); @@ -766,8 +765,14 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk, policy = !(flags & MSG_SENDPAGE_NOPOLICY); psock = sk_psock_get(sk); - if (!psock || !policy) - return tls_push_record(sk, flags, record_type); + if (!psock || !policy) { + err = tls_push_record(sk, flags, record_type); + if (err) { + *copied -= sk_msg_free(sk, msg); + tls_free_open_rec(sk); + } + return err; + } more_data: enospc = sk_msg_full(msg); if (psock->eval == __SK_NONE) { @@ -895,7 +900,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) int ret = 0; if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL)) - return -ENOTSUPP; + return -EOPNOTSUPP; mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); @@ -965,8 +970,6 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) if (ret) goto fallback_to_reg_send; - rec->inplace_crypto = 0; - num_zc++; copied += try_to_copy; @@ -979,7 +982,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) num_async++; else if (ret == -ENOMEM) goto wait_for_memory; - else if (ret == -ENOSPC) + else if (ctx->open_rec && ret == -ENOSPC) goto rollback_iter; else if (ret != -EAGAIN) goto send_end; @@ -1048,11 +1051,12 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) ret = sk_stream_wait_memory(sk, &timeo); if (ret) { trim_sgl: - tls_trim_both_msgs(sk, orig_size); + if (ctx->open_rec) + tls_trim_both_msgs(sk, orig_size); goto send_end; } - if (msg_en->sg.size < required_size) + if (ctx->open_rec && msg_en->sg.size < required_size) goto alloc_encrypted; } @@ -1164,7 +1168,6 @@ static int tls_sw_do_sendpage(struct sock *sk, struct page *page, tls_ctx->pending_open_record_frags = true; if (full_record || eor || sk_msg_full(msg_pl)) { - rec->inplace_crypto = 0; ret = bpf_exec_tx_verdict(msg_pl, sk, full_record, record_type, &copied, flags); if (ret) { @@ -1185,11 +1188,13 @@ static int tls_sw_do_sendpage(struct sock *sk, struct page *page, wait_for_memory: ret = sk_stream_wait_memory(sk, &timeo); if (ret) { - tls_trim_both_msgs(sk, msg_pl->sg.size); + if (ctx->open_rec) + tls_trim_both_msgs(sk, msg_pl->sg.size); goto sendpage_end; } - goto alloc_payload; + if (ctx->open_rec) + goto alloc_payload; } if (num_async) { @@ -1210,7 +1215,7 @@ int tls_sw_sendpage_locked(struct sock *sk, struct page *page, if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY | MSG_NO_SHARED_FRAGS)) - return -ENOTSUPP; + return -EOPNOTSUPP; return tls_sw_do_sendpage(sk, page, offset, size, flags); } @@ -1223,7 +1228,7 @@ int tls_sw_sendpage(struct sock *sk, struct page *page, if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY)) - return -ENOTSUPP; + return -EOPNOTSUPP; mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); @@ -1922,7 +1927,7 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, /* splice does not support reading control messages */ if (ctx->control != TLS_RECORD_TYPE_DATA) { - err = -ENOTSUPP; + err = -EINVAL; goto splice_read_end; } @@ -2079,7 +2084,8 @@ void tls_sw_release_resources_tx(struct sock *sk) /* Free up un-sent records in tx_list. First, free * the partially sent record if any at head of tx_list. */ - if (tls_free_partial_record(sk, tls_ctx)) { + if (tls_ctx->partially_sent_record) { + tls_free_partial_record(sk, tls_ctx); rec = list_first_entry(&ctx->tx_list, struct tls_rec, list); list_del(&rec->list); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 0d8da809bea2..b3369d678f1a 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -646,6 +646,9 @@ static __poll_t unix_poll(struct file *, struct socket *, poll_table *); static __poll_t unix_dgram_poll(struct file *, struct socket *, poll_table *); static int unix_ioctl(struct socket *, unsigned int, unsigned long); +#ifdef CONFIG_COMPAT +static int unix_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); +#endif static int unix_shutdown(struct socket *, int); static int unix_stream_sendmsg(struct socket *, struct msghdr *, size_t); static int unix_stream_recvmsg(struct socket *, struct msghdr *, size_t, int); @@ -687,6 +690,9 @@ static const struct proto_ops unix_stream_ops = { .getname = unix_getname, .poll = unix_poll, .ioctl = unix_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = unix_compat_ioctl, +#endif .listen = unix_listen, .shutdown = unix_shutdown, .setsockopt = sock_no_setsockopt, @@ -710,6 +716,9 @@ static const struct proto_ops unix_dgram_ops = { .getname = unix_getname, .poll = unix_dgram_poll, .ioctl = unix_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = unix_compat_ioctl, +#endif .listen = sock_no_listen, .shutdown = unix_shutdown, .setsockopt = sock_no_setsockopt, @@ -732,6 +741,9 @@ static const struct proto_ops unix_seqpacket_ops = { .getname = unix_getname, .poll = unix_dgram_poll, .ioctl = unix_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = unix_compat_ioctl, +#endif .listen = unix_listen, .shutdown = unix_shutdown, .setsockopt = sock_no_setsockopt, @@ -2582,6 +2594,13 @@ static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) return err; } +#ifdef CONFIG_COMPAT +static int unix_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) +{ + return unix_ioctl(sock, cmd, (unsigned long)compat_ptr(arg)); +} +#endif + static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; diff --git a/net/wireless/core.c b/net/wireless/core.c index 350513744575..3e25229a059d 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1102,6 +1102,7 @@ static void __cfg80211_unregister_wdev(struct wireless_dev *wdev, bool sync) #ifdef CONFIG_CFG80211_WEXT kzfree(wdev->wext.keys); + wdev->wext.keys = NULL; #endif /* only initialized if we have a netdev */ if (wdev->netdev) diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 9044073fbf22..d426fc01c529 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -305,12 +305,21 @@ bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc) } EXPORT_SYMBOL(xsk_umem_consume_tx); -static int xsk_zc_xmit(struct xdp_sock *xs) +static int xsk_wakeup(struct xdp_sock *xs, u8 flags) { struct net_device *dev = xs->dev; + int err; + + rcu_read_lock(); + err = dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, flags); + rcu_read_unlock(); + + return err; +} - return dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, - XDP_WAKEUP_TX); +static int xsk_zc_xmit(struct xdp_sock *xs) +{ + return xsk_wakeup(xs, XDP_WAKEUP_TX); } static void xsk_destruct_skb(struct sk_buff *skb) @@ -424,19 +433,16 @@ static unsigned int xsk_poll(struct file *file, struct socket *sock, unsigned int mask = datagram_poll(file, sock, wait); struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); - struct net_device *dev; struct xdp_umem *umem; if (unlikely(!xsk_is_bound(xs))) return mask; - dev = xs->dev; umem = xs->umem; if (umem->need_wakeup) { - if (dev->netdev_ops->ndo_xsk_wakeup) - dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, - umem->need_wakeup); + if (xs->zc) + xsk_wakeup(xs, umem->need_wakeup); else /* Poll needs to drive Tx also in copy mode */ __xsk_sendmsg(sk); diff --git a/samples/bpf/syscall_tp_kern.c b/samples/bpf/syscall_tp_kern.c index 1d78819ffef1..630ce8c4d5a2 100644 --- a/samples/bpf/syscall_tp_kern.c +++ b/samples/bpf/syscall_tp_kern.c @@ -47,13 +47,27 @@ static __always_inline void count(void *map) SEC("tracepoint/syscalls/sys_enter_open") int trace_enter_open(struct syscalls_enter_open_args *ctx) { - count((void *)&enter_open_map); + count(&enter_open_map); + return 0; +} + +SEC("tracepoint/syscalls/sys_enter_openat") +int trace_enter_open_at(struct syscalls_enter_open_args *ctx) +{ + count(&enter_open_map); return 0; } SEC("tracepoint/syscalls/sys_exit_open") int trace_enter_exit(struct syscalls_exit_open_args *ctx) { - count((void *)&exit_open_map); + count(&exit_open_map); + return 0; +} + +SEC("tracepoint/syscalls/sys_exit_openat") +int trace_enter_exit_at(struct syscalls_exit_open_args *ctx) +{ + count(&exit_open_map); return 0; } diff --git a/samples/bpf/trace_event_user.c b/samples/bpf/trace_event_user.c index 16a16eadd509..749a50f2f9f3 100644 --- a/samples/bpf/trace_event_user.c +++ b/samples/bpf/trace_event_user.c @@ -37,9 +37,9 @@ static void print_ksym(__u64 addr) } printf("%s;", sym->name); - if (!strcmp(sym->name, "sys_read")) + if (!strstr(sym->name, "sys_read")) sys_read_seen = true; - else if (!strcmp(sym->name, "sys_write")) + else if (!strstr(sym->name, "sys_write")) sys_write_seen = true; } diff --git a/samples/pktgen/functions.sh b/samples/pktgen/functions.sh index 4af4046d71be..40873a5d1461 100644 --- a/samples/pktgen/functions.sh +++ b/samples/pktgen/functions.sh @@ -5,6 +5,8 @@ # Author: Jesper Dangaaard Brouer # License: GPL +set -o errexit + ## -- General shell logging cmds -- function err() { local exitcode=$1 @@ -58,6 +60,7 @@ function pg_set() { function proc_cmd() { local result local proc_file=$1 + local status=0 # after shift, the remaining args are contained in $@ shift local proc_ctrl=${PROC_DIR}/$proc_file @@ -73,13 +76,13 @@ function proc_cmd() { echo "cmd: $@ > $proc_ctrl" fi # Quoting of "$@" is important for space expansion - echo "$@" > "$proc_ctrl" - local status=$? + echo "$@" > "$proc_ctrl" || status=$? - result=$(grep "Result: OK:" $proc_ctrl) - # Due to pgctrl, cannot use exit code $? from grep - if [[ "$result" == "" ]]; then - grep "Result:" $proc_ctrl >&2 + if [[ "$proc_file" != "pgctrl" ]]; then + result=$(grep "Result: OK:" $proc_ctrl) || true + if [[ "$result" == "" ]]; then + grep "Result:" $proc_ctrl >&2 + fi fi if (( $status != 0 )); then err 5 "Write error($status) occurred cmd: \"$@ > $proc_ctrl\"" @@ -105,6 +108,8 @@ function pgset() { fi } +[[ $EUID -eq 0 ]] && trap 'pg_ctrl "reset"' EXIT + ## -- General shell tricks -- function root_check_run_with_sudo() { diff --git a/samples/seccomp/user-trap.c b/samples/seccomp/user-trap.c index 6d0125ca8af7..20291ec6489f 100644 --- a/samples/seccomp/user-trap.c +++ b/samples/seccomp/user-trap.c @@ -298,14 +298,14 @@ int main(void) req = malloc(sizes.seccomp_notif); if (!req) goto out_close; - memset(req, 0, sizeof(*req)); resp = malloc(sizes.seccomp_notif_resp); if (!resp) goto out_req; - memset(resp, 0, sizeof(*resp)); + memset(resp, 0, sizes.seccomp_notif_resp); while (1) { + memset(req, 0, sizes.seccomp_notif); if (ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, req)) { perror("ioctl recv"); goto out_resp; diff --git a/samples/trace_printk/trace-printk.c b/samples/trace_printk/trace-printk.c index 7affc3b50b61..cfc159580263 100644 --- a/samples/trace_printk/trace-printk.c +++ b/samples/trace_printk/trace-printk.c @@ -36,6 +36,7 @@ static int __init trace_printk_init(void) /* Kick off printing in irq context */ irq_work_queue(&irqwork); + irq_work_sync(&irqwork); trace_printk("This is a %s that will use trace_bprintk()\n", "static string"); diff --git a/scripts/dtc/Makefile b/scripts/dtc/Makefile index 82160808765c..b5a5b1c548c9 100644 --- a/scripts/dtc/Makefile +++ b/scripts/dtc/Makefile @@ -11,7 +11,7 @@ dtc-objs += dtc-lexer.lex.o dtc-parser.tab.o # Source files need to get at the userspace version of libfdt_env.h to compile HOST_EXTRACFLAGS := -I $(srctree)/$(src)/libfdt -ifeq ($(wildcard /usr/include/yaml.h),) +ifeq ($(shell pkg-config --exists yaml-0.1 2>/dev/null && echo yes),) ifneq ($(CHECK_DTBS),) $(error dtc needs libyaml for DT schema validation support. \ Install the necessary libyaml development package.) @@ -19,7 +19,7 @@ endif HOST_EXTRACFLAGS += -DNO_YAML else dtc-objs += yamltree.o -HOSTLDLIBS_dtc := -lyaml +HOSTLDLIBS_dtc := $(shell pkg-config yaml-0.1 --libs) endif # Generated files need one more search path to include headers in source tree diff --git a/scripts/gcc-plugins/Kconfig b/scripts/gcc-plugins/Kconfig index d33de0b9f4f5..e3569543bdac 100644 --- a/scripts/gcc-plugins/Kconfig +++ b/scripts/gcc-plugins/Kconfig @@ -14,8 +14,8 @@ config HAVE_GCC_PLUGINS An arch should select this symbol if it supports building with GCC plugins. -config GCC_PLUGINS - bool +menuconfig GCC_PLUGINS + bool "GCC plugins" depends on HAVE_GCC_PLUGINS depends on PLUGIN_HOSTCC != "" default y @@ -25,8 +25,7 @@ config GCC_PLUGINS See Documentation/core-api/gcc-plugins.rst for details. -menu "GCC plugins" - depends on GCC_PLUGINS +if GCC_PLUGINS config GCC_PLUGIN_CYC_COMPLEXITY bool "Compute the cyclomatic complexity of a function" if EXPERT @@ -113,4 +112,4 @@ config GCC_PLUGIN_ARM_SSP_PER_TASK bool depends on GCC_PLUGINS && ARM -endmenu +endif diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index ae6504d07fd6..fb15f09e0e38 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -489,6 +489,8 @@ static void build_initial_tok_table(void) table[pos] = table[i]; learn_symbol(table[pos].sym, table[pos].len); pos++; + } else { + free(table[i].sym); } } table_cnt = pos; diff --git a/scripts/kconfig/expr.c b/scripts/kconfig/expr.c index 77ffff3a053c..9f1de58e9f0c 100644 --- a/scripts/kconfig/expr.c +++ b/scripts/kconfig/expr.c @@ -254,6 +254,13 @@ static int expr_eq(struct expr *e1, struct expr *e2) { int res, old_count; + /* + * A NULL expr is taken to be yes, but there's also a different way to + * represent yes. expr_is_yes() checks for either representation. + */ + if (!e1 || !e2) + return expr_is_yes(e1) && expr_is_yes(e2); + if (e1->type != e2->type) return 0; switch (e1->type) { diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 06495379fcd8..2998ddb323e3 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -127,7 +127,8 @@ gen_btf() cut -d, -f1 | cut -d' ' -f2) bin_format=$(LANG=C ${OBJDUMP} -f ${1} | grep 'file format' | \ awk '{print $4}') - ${OBJCOPY} --dump-section .BTF=.btf.vmlinux.bin ${1} 2>/dev/null + ${OBJCOPY} --set-section-flags .BTF=alloc -O binary \ + --only-section=.BTF ${1} .btf.vmlinux.bin 2>/dev/null ${OBJCOPY} -I binary -O ${bin_format} -B ${bin_arch} \ --rename-section .data=.BTF .btf.vmlinux.bin ${2} } @@ -253,6 +254,10 @@ btf_vmlinux_bin_o="" if [ -n "${CONFIG_DEBUG_INFO_BTF}" ]; then if gen_btf .tmp_vmlinux.btf .btf.vmlinux.bin.o ; then btf_vmlinux_bin_o=.btf.vmlinux.bin.o + else + echo >&2 "Failed to generate BTF for vmlinux" + echo >&2 "Try to disable CONFIG_DEBUG_INFO_BTF" + exit 1 fi fi diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian index e0750b70453f..357dc56bcf30 100755 --- a/scripts/package/mkdebian +++ b/scripts/package/mkdebian @@ -136,7 +136,7 @@ mkdir -p debian/source/ echo "1.0" > debian/source/format echo $debarch > debian/arch -extra_build_depends=", $(if_enabled_echo CONFIG_UNWINDER_ORC libelf-dev)" +extra_build_depends=", $(if_enabled_echo CONFIG_UNWINDER_ORC libelf-dev:native)" extra_build_depends="$extra_build_depends, $(if_enabled_echo CONFIG_SYSTEM_TRUSTED_KEYRING libssl-dev:native)" # Generate a simple changelog template @@ -174,7 +174,7 @@ Source: $sourcename Section: kernel Priority: optional Maintainer: $maintainer -Build-Depends: bc, kmod, cpio, bison, flex | flex:native $extra_build_depends +Build-Depends: bc, rsync, kmod, cpio, bison, flex | flex:native $extra_build_depends Homepage: http://www.kernel.org/ Package: $packagename diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c index 45d13b6462aa..90d21675c3ad 100644 --- a/security/apparmor/apparmorfs.c +++ b/security/apparmor/apparmorfs.c @@ -593,7 +593,7 @@ static __poll_t ns_revision_poll(struct file *file, poll_table *pt) void __aa_bump_ns_revision(struct aa_ns *ns) { - ns->revision++; + WRITE_ONCE(ns->revision, ns->revision + 1); wake_up_interruptible(&ns->wait); } diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c index 9e0492795267..039ca71872ce 100644 --- a/security/apparmor/domain.c +++ b/security/apparmor/domain.c @@ -317,6 +317,7 @@ static int aa_xattrs_match(const struct linux_binprm *bprm, if (!bprm || !profile->xattr_count) return 0; + might_sleep(); /* transition from exec match to xattr set */ state = aa_dfa_null_transition(profile->xmatch, state); @@ -361,10 +362,11 @@ static int aa_xattrs_match(const struct linux_binprm *bprm, } /** - * __attach_match_ - find an attachment match + * find_attach - do attachment search for unconfined processes * @bprm - binprm structure of transitioning task - * @name - to match against (NOT NULL) + * @ns: the current namespace (NOT NULL) * @head - profile list to walk (NOT NULL) + * @name - to match against (NOT NULL) * @info - info message if there was an error (NOT NULL) * * Do a linear search on the profiles in the list. There is a matching @@ -374,12 +376,11 @@ static int aa_xattrs_match(const struct linux_binprm *bprm, * * Requires: @head not be shared or have appropriate locks held * - * Returns: profile or NULL if no match found + * Returns: label or NULL if no match found */ -static struct aa_profile *__attach_match(const struct linux_binprm *bprm, - const char *name, - struct list_head *head, - const char **info) +static struct aa_label *find_attach(const struct linux_binprm *bprm, + struct aa_ns *ns, struct list_head *head, + const char *name, const char **info) { int candidate_len = 0, candidate_xattrs = 0; bool conflict = false; @@ -388,6 +389,8 @@ static struct aa_profile *__attach_match(const struct linux_binprm *bprm, AA_BUG(!name); AA_BUG(!head); + rcu_read_lock(); +restart: list_for_each_entry_rcu(profile, head, base.list) { if (profile->label.flags & FLAG_NULL && &profile->label == ns_unconfined(profile->ns)) @@ -413,16 +416,32 @@ static struct aa_profile *__attach_match(const struct linux_binprm *bprm, perm = dfa_user_allow(profile->xmatch, state); /* any accepting state means a valid match. */ if (perm & MAY_EXEC) { - int ret; + int ret = 0; if (count < candidate_len) continue; - ret = aa_xattrs_match(bprm, profile, state); - /* Fail matching if the xattrs don't match */ - if (ret < 0) - continue; - + if (bprm && profile->xattr_count) { + long rev = READ_ONCE(ns->revision); + + if (!aa_get_profile_not0(profile)) + goto restart; + rcu_read_unlock(); + ret = aa_xattrs_match(bprm, profile, + state); + rcu_read_lock(); + aa_put_profile(profile); + if (rev != + READ_ONCE(ns->revision)) + /* policy changed */ + goto restart; + /* + * Fail matching if the xattrs don't + * match + */ + if (ret < 0) + continue; + } /* * TODO: allow for more flexible best match * @@ -445,43 +464,28 @@ static struct aa_profile *__attach_match(const struct linux_binprm *bprm, candidate_xattrs = ret; conflict = false; } - } else if (!strcmp(profile->base.name, name)) + } else if (!strcmp(profile->base.name, name)) { /* * old exact non-re match, without conditionals such * as xattrs. no more searching required */ - return profile; + candidate = profile; + goto out; + } } - if (conflict) { - *info = "conflicting profile attachments"; + if (!candidate || conflict) { + if (conflict) + *info = "conflicting profile attachments"; + rcu_read_unlock(); return NULL; } - return candidate; -} - -/** - * find_attach - do attachment search for unconfined processes - * @bprm - binprm structure of transitioning task - * @ns: the current namespace (NOT NULL) - * @list: list to search (NOT NULL) - * @name: the executable name to match against (NOT NULL) - * @info: info message if there was an error - * - * Returns: label or NULL if no match found - */ -static struct aa_label *find_attach(const struct linux_binprm *bprm, - struct aa_ns *ns, struct list_head *list, - const char *name, const char **info) -{ - struct aa_profile *profile; - - rcu_read_lock(); - profile = aa_get_profile(__attach_match(bprm, name, list, info)); +out: + candidate = aa_get_newest_profile(candidate); rcu_read_unlock(); - return profile ? &profile->label : NULL; + return &candidate->label; } static const char *next_name(int xtype, const char *name) diff --git a/security/apparmor/label.c b/security/apparmor/label.c index 59f1cc2557a7..470693239e64 100644 --- a/security/apparmor/label.c +++ b/security/apparmor/label.c @@ -1458,11 +1458,13 @@ static inline bool use_label_hname(struct aa_ns *ns, struct aa_label *label, /* helper macro for snprint routines */ #define update_for_len(total, len, size, str) \ do { \ + size_t ulen = len; \ + \ AA_BUG(len < 0); \ - total += len; \ - len = min(len, size); \ - size -= len; \ - str += len; \ + total += ulen; \ + ulen = min(ulen, size); \ + size -= ulen; \ + str += ulen; \ } while (0) /** @@ -1597,7 +1599,7 @@ int aa_label_snxprint(char *str, size_t size, struct aa_ns *ns, struct aa_ns *prev_ns = NULL; struct label_it i; int count = 0, total = 0; - size_t len; + ssize_t len; AA_BUG(!str && size != 0); AA_BUG(!label); diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c index ade333074c8e..06355717ee84 100644 --- a/security/apparmor/policy.c +++ b/security/apparmor/policy.c @@ -1124,8 +1124,8 @@ ssize_t aa_remove_profiles(struct aa_ns *policy_ns, struct aa_label *subj, if (!name) { /* remove namespace - can only happen if fqname[0] == ':' */ mutex_lock_nested(&ns->parent->lock, ns->level); - __aa_remove_ns(ns); __aa_bump_ns_revision(ns); + __aa_remove_ns(ns); mutex_unlock(&ns->parent->lock); } else { /* remove profile */ @@ -1137,9 +1137,9 @@ ssize_t aa_remove_profiles(struct aa_ns *policy_ns, struct aa_label *subj, goto fail_ns_lock; } name = profile->base.hname; + __aa_bump_ns_revision(ns); __remove_profile(profile); __aa_labelset_update_subtree(ns); - __aa_bump_ns_revision(ns); mutex_unlock(&ns->lock); } diff --git a/security/tomoyo/common.c b/security/tomoyo/common.c index dd3d5942e669..c36bafbcd77e 100644 --- a/security/tomoyo/common.c +++ b/security/tomoyo/common.c @@ -951,7 +951,8 @@ static bool tomoyo_manager(void) exe = tomoyo_get_exe(); if (!exe) return false; - list_for_each_entry_rcu(ptr, &tomoyo_kernel_namespace.policy_list[TOMOYO_ID_MANAGER], head.list) { + list_for_each_entry_rcu(ptr, &tomoyo_kernel_namespace.policy_list[TOMOYO_ID_MANAGER], head.list, + srcu_read_lock_held(&tomoyo_ss)) { if (!ptr->head.is_deleted && (!tomoyo_pathcmp(domainname, ptr->manager) || !strcmp(exe, ptr->manager->name))) { @@ -1095,7 +1096,8 @@ static int tomoyo_delete_domain(char *domainname) if (mutex_lock_interruptible(&tomoyo_policy_lock)) return -EINTR; /* Is there an active domain? */ - list_for_each_entry_rcu(domain, &tomoyo_domain_list, list) { + list_for_each_entry_rcu(domain, &tomoyo_domain_list, list, + srcu_read_lock_held(&tomoyo_ss)) { /* Never delete tomoyo_kernel_domain */ if (domain == &tomoyo_kernel_domain) continue; @@ -2778,7 +2780,8 @@ void tomoyo_check_profile(void) tomoyo_policy_loaded = true; pr_info("TOMOYO: 2.6.0\n"); - list_for_each_entry_rcu(domain, &tomoyo_domain_list, list) { + list_for_each_entry_rcu(domain, &tomoyo_domain_list, list, + srcu_read_lock_held(&tomoyo_ss)) { const u8 profile = domain->profile; struct tomoyo_policy_namespace *ns = domain->ns; diff --git a/security/tomoyo/domain.c b/security/tomoyo/domain.c index 8526a0a74023..7869d6a9980b 100644 --- a/security/tomoyo/domain.c +++ b/security/tomoyo/domain.c @@ -41,7 +41,8 @@ int tomoyo_update_policy(struct tomoyo_acl_head *new_entry, const int size, if (mutex_lock_interruptible(&tomoyo_policy_lock)) return -ENOMEM; - list_for_each_entry_rcu(entry, list, list) { + list_for_each_entry_rcu(entry, list, list, + srcu_read_lock_held(&tomoyo_ss)) { if (entry->is_deleted == TOMOYO_GC_IN_PROGRESS) continue; if (!check_duplicate(entry, new_entry)) @@ -119,7 +120,8 @@ int tomoyo_update_domain(struct tomoyo_acl_info *new_entry, const int size, } if (mutex_lock_interruptible(&tomoyo_policy_lock)) goto out; - list_for_each_entry_rcu(entry, list, list) { + list_for_each_entry_rcu(entry, list, list, + srcu_read_lock_held(&tomoyo_ss)) { if (entry->is_deleted == TOMOYO_GC_IN_PROGRESS) continue; if (!tomoyo_same_acl_head(entry, new_entry) || @@ -166,7 +168,8 @@ void tomoyo_check_acl(struct tomoyo_request_info *r, u16 i = 0; retry: - list_for_each_entry_rcu(ptr, list, list) { + list_for_each_entry_rcu(ptr, list, list, + srcu_read_lock_held(&tomoyo_ss)) { if (ptr->is_deleted || ptr->type != r->param_type) continue; if (!check_entry(r, ptr)) @@ -298,7 +301,8 @@ static inline bool tomoyo_scan_transition { const struct tomoyo_transition_control *ptr; - list_for_each_entry_rcu(ptr, list, head.list) { + list_for_each_entry_rcu(ptr, list, head.list, + srcu_read_lock_held(&tomoyo_ss)) { if (ptr->head.is_deleted || ptr->type != type) continue; if (ptr->domainname) { @@ -735,7 +739,8 @@ int tomoyo_find_next_domain(struct linux_binprm *bprm) /* Check 'aggregator' directive. */ candidate = &exename; - list_for_each_entry_rcu(ptr, list, head.list) { + list_for_each_entry_rcu(ptr, list, head.list, + srcu_read_lock_held(&tomoyo_ss)) { if (ptr->head.is_deleted || !tomoyo_path_matches_pattern(&exename, ptr->original_name)) diff --git a/security/tomoyo/group.c b/security/tomoyo/group.c index a37c7dc66e44..1cecdd797597 100644 --- a/security/tomoyo/group.c +++ b/security/tomoyo/group.c @@ -133,7 +133,8 @@ tomoyo_path_matches_group(const struct tomoyo_path_info *pathname, { struct tomoyo_path_group *member; - list_for_each_entry_rcu(member, &group->member_list, head.list) { + list_for_each_entry_rcu(member, &group->member_list, head.list, + srcu_read_lock_held(&tomoyo_ss)) { if (member->head.is_deleted) continue; if (!tomoyo_path_matches_pattern(pathname, member->member_name)) @@ -161,7 +162,8 @@ bool tomoyo_number_matches_group(const unsigned long min, struct tomoyo_number_group *member; bool matched = false; - list_for_each_entry_rcu(member, &group->member_list, head.list) { + list_for_each_entry_rcu(member, &group->member_list, head.list, + srcu_read_lock_held(&tomoyo_ss)) { if (member->head.is_deleted) continue; if (min > member->number.values[1] || @@ -191,7 +193,8 @@ bool tomoyo_address_matches_group(const bool is_ipv6, const __be32 *address, bool matched = false; const u8 size = is_ipv6 ? 16 : 4; - list_for_each_entry_rcu(member, &group->member_list, head.list) { + list_for_each_entry_rcu(member, &group->member_list, head.list, + srcu_read_lock_held(&tomoyo_ss)) { if (member->head.is_deleted) continue; if (member->address.is_ipv6 != is_ipv6) diff --git a/security/tomoyo/realpath.c b/security/tomoyo/realpath.c index e7832448d721..bf38fc1b59b2 100644 --- a/security/tomoyo/realpath.c +++ b/security/tomoyo/realpath.c @@ -217,31 +217,6 @@ static char *tomoyo_get_local_path(struct dentry *dentry, char * const buffer, return ERR_PTR(-ENOMEM); } -/** - * tomoyo_get_socket_name - Get the name of a socket. - * - * @path: Pointer to "struct path". - * @buffer: Pointer to buffer to return value in. - * @buflen: Sizeof @buffer. - * - * Returns the buffer. - */ -static char *tomoyo_get_socket_name(const struct path *path, char * const buffer, - const int buflen) -{ - struct inode *inode = d_backing_inode(path->dentry); - struct socket *sock = inode ? SOCKET_I(inode) : NULL; - struct sock *sk = sock ? sock->sk : NULL; - - if (sk) { - snprintf(buffer, buflen, "socket:[family=%u:type=%u:protocol=%u]", - sk->sk_family, sk->sk_type, sk->sk_protocol); - } else { - snprintf(buffer, buflen, "socket:[unknown]"); - } - return buffer; -} - /** * tomoyo_realpath_from_path - Returns realpath(3) of the given pathname but ignores chroot'ed root. * @@ -279,12 +254,7 @@ char *tomoyo_realpath_from_path(const struct path *path) break; /* To make sure that pos is '\0' terminated. */ buf[buf_len - 1] = '\0'; - /* Get better name for socket. */ - if (sb->s_magic == SOCKFS_MAGIC) { - pos = tomoyo_get_socket_name(path, buf, buf_len - 1); - goto encode; - } - /* For "pipe:[\$]". */ + /* For "pipe:[\$]" and "socket:[\$]". */ if (dentry->d_op && dentry->d_op->d_dname) { pos = dentry->d_op->d_dname(dentry, buf, buf_len - 1); goto encode; diff --git a/security/tomoyo/util.c b/security/tomoyo/util.c index 52752e1a84ed..eba0b3395851 100644 --- a/security/tomoyo/util.c +++ b/security/tomoyo/util.c @@ -594,7 +594,8 @@ struct tomoyo_domain_info *tomoyo_find_domain(const char *domainname) name.name = domainname; tomoyo_fill_path_info(&name); - list_for_each_entry_rcu(domain, &tomoyo_domain_list, list) { + list_for_each_entry_rcu(domain, &tomoyo_domain_list, list, + srcu_read_lock_held(&tomoyo_ss)) { if (!domain->is_deleted && !tomoyo_pathcmp(&name, domain->domainname)) return domain; @@ -1028,7 +1029,8 @@ bool tomoyo_domain_quota_is_ok(struct tomoyo_request_info *r) return false; if (!domain) return true; - list_for_each_entry_rcu(ptr, &domain->acl_info_list, list) { + list_for_each_entry_rcu(ptr, &domain->acl_info_list, list, + srcu_read_lock_held(&tomoyo_ss)) { u16 perm; u8 i; diff --git a/sound/core/oss/linear.c b/sound/core/oss/linear.c index 2045697f449d..797d838a2f9e 100644 --- a/sound/core/oss/linear.c +++ b/sound/core/oss/linear.c @@ -107,6 +107,8 @@ static snd_pcm_sframes_t linear_transfer(struct snd_pcm_plugin *plugin, } } #endif + if (frames > dst_channels[0].frames) + frames = dst_channels[0].frames; convert(plugin, src_channels, dst_channels, frames); return frames; } diff --git a/sound/core/oss/mulaw.c b/sound/core/oss/mulaw.c index 7915564bd394..3788906421a7 100644 --- a/sound/core/oss/mulaw.c +++ b/sound/core/oss/mulaw.c @@ -269,6 +269,8 @@ static snd_pcm_sframes_t mulaw_transfer(struct snd_pcm_plugin *plugin, } } #endif + if (frames > dst_channels[0].frames) + frames = dst_channels[0].frames; data = (struct mulaw_priv *)plugin->extra_data; data->func(plugin, src_channels, dst_channels, frames); return frames; diff --git a/sound/core/oss/route.c b/sound/core/oss/route.c index c8171f5783c8..72dea04197ef 100644 --- a/sound/core/oss/route.c +++ b/sound/core/oss/route.c @@ -57,6 +57,8 @@ static snd_pcm_sframes_t route_transfer(struct snd_pcm_plugin *plugin, return -ENXIO; if (frames == 0) return 0; + if (frames > dst_channels[0].frames) + frames = dst_channels[0].frames; nsrcs = plugin->src_format.channels; ndsts = plugin->dst_format.channels; diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 91c6ad58729f..5c74ea2bb44b 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -222,7 +222,8 @@ static bool hw_support_mmap(struct snd_pcm_substream *substream) return false; if (substream->ops->mmap || - substream->dma_buffer.dev.type != SNDRV_DMA_TYPE_DEV) + (substream->dma_buffer.dev.type != SNDRV_DMA_TYPE_DEV && + substream->dma_buffer.dev.type != SNDRV_DMA_TYPE_DEV_UC)) return true; return dma_can_mmap(substream->dma_buffer.dev.dev); @@ -705,6 +706,10 @@ static int snd_pcm_hw_params(struct snd_pcm_substream *substream, while (runtime->boundary * 2 <= LONG_MAX - runtime->buffer_size) runtime->boundary *= 2; + /* clear the buffer for avoiding possible kernel info leaks */ + if (runtime->dma_area && !substream->ops->copy_user) + memset(runtime->dma_area, 0, runtime->dma_bytes); + snd_pcm_timer_resolution_change(substream); snd_pcm_set_state(substream, SNDRV_PCM_STATE_SETUP); @@ -3403,7 +3408,8 @@ int snd_pcm_lib_default_mmap(struct snd_pcm_substream *substream, #endif /* CONFIG_GENERIC_ALLOCATOR */ #ifndef CONFIG_X86 /* for avoiding warnings arch/x86/mm/pat.c */ if (IS_ENABLED(CONFIG_HAS_DMA) && !substream->ops->page && - substream->dma_buffer.dev.type == SNDRV_DMA_TYPE_DEV) + (substream->dma_buffer.dev.type == SNDRV_DMA_TYPE_DEV || + substream->dma_buffer.dev.type == SNDRV_DMA_TYPE_DEV_UC)) return dma_mmap_coherent(substream->dma_buffer.dev.dev, area, substream->runtime->dma_area, diff --git a/sound/core/timer.c b/sound/core/timer.c index 59ae21b0bb93..013f0e69ff0f 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -74,6 +74,9 @@ static LIST_HEAD(snd_timer_slave_list); /* lock for slave active lists */ static DEFINE_SPINLOCK(slave_active_lock); +#define MAX_SLAVE_INSTANCES 1000 +static int num_slaves; + static DEFINE_MUTEX(register_mutex); static int snd_timer_free(struct snd_timer *timer); @@ -252,6 +255,10 @@ int snd_timer_open(struct snd_timer_instance **ti, err = -EINVAL; goto unlock; } + if (num_slaves >= MAX_SLAVE_INSTANCES) { + err = -EBUSY; + goto unlock; + } timeri = snd_timer_instance_new(owner, NULL); if (!timeri) { err = -ENOMEM; @@ -261,6 +268,7 @@ int snd_timer_open(struct snd_timer_instance **ti, timeri->slave_id = tid->device; timeri->flags |= SNDRV_TIMER_IFLG_SLAVE; list_add_tail(&timeri->open_list, &snd_timer_slave_list); + num_slaves++; err = snd_timer_check_slave(timeri); if (err < 0) { snd_timer_close_locked(timeri, &card_dev_to_put); @@ -356,6 +364,8 @@ static int snd_timer_close_locked(struct snd_timer_instance *timeri, } list_del(&timeri->open_list); + if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE) + num_slaves--; /* force to stop the timer */ snd_timer_stop(timeri); diff --git a/sound/firewire/bebob/bebob_stream.c b/sound/firewire/bebob/bebob_stream.c index 6c1497d9f52b..ce07ea0d4e71 100644 --- a/sound/firewire/bebob/bebob_stream.c +++ b/sound/firewire/bebob/bebob_stream.c @@ -415,15 +415,16 @@ static int make_both_connections(struct snd_bebob *bebob) return 0; } -static void -break_both_connections(struct snd_bebob *bebob) +static void break_both_connections(struct snd_bebob *bebob) { cmp_connection_break(&bebob->in_conn); cmp_connection_break(&bebob->out_conn); - /* These models seems to be in transition state for a longer time. */ - if (bebob->maudio_special_quirk != NULL) - msleep(200); + // These models seem to be in transition state for a longer time. When + // accessing in the state, any transactions is corrupted. In the worst + // case, the device is going to reboot. + if (bebob->version < 2) + msleep(600); } static int diff --git a/sound/firewire/fireface/ff-pcm.c b/sound/firewire/fireface/ff-pcm.c index 9eab3ad283ce..df6ff2df0124 100644 --- a/sound/firewire/fireface/ff-pcm.c +++ b/sound/firewire/fireface/ff-pcm.c @@ -219,7 +219,7 @@ static int pcm_hw_params(struct snd_pcm_substream *substream, mutex_unlock(&ff->mutex); } - return 0; + return err; } static int pcm_hw_free(struct snd_pcm_substream *substream) diff --git a/sound/firewire/motu/motu-proc.c b/sound/firewire/motu/motu-proc.c index ea46fb4c1b5a..126a7bd187bb 100644 --- a/sound/firewire/motu/motu-proc.c +++ b/sound/firewire/motu/motu-proc.c @@ -16,7 +16,7 @@ static const char *const clock_names[] = { [SND_MOTU_CLOCK_SOURCE_SPDIF_ON_OPT] = "S/PDIF on optical interface", [SND_MOTU_CLOCK_SOURCE_SPDIF_ON_OPT_A] = "S/PDIF on optical interface A", [SND_MOTU_CLOCK_SOURCE_SPDIF_ON_OPT_B] = "S/PDIF on optical interface B", - [SND_MOTU_CLOCK_SOURCE_SPDIF_ON_COAX] = "S/PCIF on coaxial interface", + [SND_MOTU_CLOCK_SOURCE_SPDIF_ON_COAX] = "S/PDIF on coaxial interface", [SND_MOTU_CLOCK_SOURCE_AESEBU_ON_XLR] = "AESEBU on XLR interface", [SND_MOTU_CLOCK_SOURCE_WORD_ON_BNC] = "Word clock on BNC interface", }; diff --git a/sound/firewire/oxfw/oxfw-pcm.c b/sound/firewire/oxfw/oxfw-pcm.c index 7c6d1c277d4d..78d906af9c00 100644 --- a/sound/firewire/oxfw/oxfw-pcm.c +++ b/sound/firewire/oxfw/oxfw-pcm.c @@ -255,7 +255,7 @@ static int pcm_playback_hw_params(struct snd_pcm_substream *substream, mutex_unlock(&oxfw->mutex); } - return 0; + return err; } static int pcm_capture_hw_free(struct snd_pcm_substream *substream) diff --git a/sound/hda/hdac_stream.c b/sound/hda/hdac_stream.c index d8fe7ff0cd58..682ed39f79b0 100644 --- a/sound/hda/hdac_stream.c +++ b/sound/hda/hdac_stream.c @@ -96,12 +96,14 @@ void snd_hdac_stream_start(struct hdac_stream *azx_dev, bool fresh_start) 1 << azx_dev->index, 1 << azx_dev->index); /* set stripe control */ - if (azx_dev->substream) - stripe_ctl = snd_hdac_get_stream_stripe_ctl(bus, azx_dev->substream); - else - stripe_ctl = 0; - snd_hdac_stream_updateb(azx_dev, SD_CTL_3B, SD_CTL_STRIPE_MASK, - stripe_ctl); + if (azx_dev->stripe) { + if (azx_dev->substream) + stripe_ctl = snd_hdac_get_stream_stripe_ctl(bus, azx_dev->substream); + else + stripe_ctl = 0; + snd_hdac_stream_updateb(azx_dev, SD_CTL_3B, SD_CTL_STRIPE_MASK, + stripe_ctl); + } /* set DMA start and interrupt mask */ snd_hdac_stream_updateb(azx_dev, SD_CTL, 0, SD_CTL_DMA_START | SD_INT_MASK); @@ -118,7 +120,8 @@ void snd_hdac_stream_clear(struct hdac_stream *azx_dev) snd_hdac_stream_updateb(azx_dev, SD_CTL, SD_CTL_DMA_START | SD_INT_MASK, 0); snd_hdac_stream_writeb(azx_dev, SD_STS, SD_INT_MASK); /* to be sure */ - snd_hdac_stream_updateb(azx_dev, SD_CTL_3B, SD_CTL_STRIPE_MASK, 0); + if (azx_dev->stripe) + snd_hdac_stream_updateb(azx_dev, SD_CTL_3B, SD_CTL_STRIPE_MASK, 0); azx_dev->running = false; } EXPORT_SYMBOL_GPL(snd_hdac_stream_clear); diff --git a/sound/isa/cs423x/cs4236.c b/sound/isa/cs423x/cs4236.c index 78dd213589b4..fa3c39cff5f8 100644 --- a/sound/isa/cs423x/cs4236.c +++ b/sound/isa/cs423x/cs4236.c @@ -278,7 +278,8 @@ static int snd_cs423x_pnp_init_mpu(int dev, struct pnp_dev *pdev) } else { mpu_port[dev] = pnp_port_start(pdev, 0); if (mpu_irq[dev] >= 0 && - pnp_irq_valid(pdev, 0) && pnp_irq(pdev, 0) >= 0) { + pnp_irq_valid(pdev, 0) && + pnp_irq(pdev, 0) != (resource_size_t)-1) { mpu_irq[dev] = pnp_irq(pdev, 0); } else { mpu_irq[dev] = -1; /* disable interrupt */ diff --git a/sound/pci/hda/hda_bind.c b/sound/pci/hda/hda_bind.c index 8272b50b8349..6a8564566375 100644 --- a/sound/pci/hda/hda_bind.c +++ b/sound/pci/hda/hda_bind.c @@ -43,6 +43,10 @@ static void hda_codec_unsol_event(struct hdac_device *dev, unsigned int ev) { struct hda_codec *codec = container_of(dev, struct hda_codec, core); + /* ignore unsol events during shutdown */ + if (codec->bus->shutdown) + return; + if (codec->patch_ops.unsol_event) codec->patch_ops.unsol_event(codec, ev); } diff --git a/sound/pci/hda/hda_controller.c b/sound/pci/hda/hda_controller.c index 6387c7e90918..76b507058cb4 100644 --- a/sound/pci/hda/hda_controller.c +++ b/sound/pci/hda/hda_controller.c @@ -884,7 +884,7 @@ static int azx_rirb_get_response(struct hdac_bus *bus, unsigned int addr, return -EAGAIN; /* give a chance to retry */ } - dev_WARN(chip->card->dev, + dev_err(chip->card->dev, "azx_get_response timeout, switching to single_cmd mode: last cmd=0x%08x\n", bus->last_cmd[addr]); chip->single_cmd = 1; diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index c52419376c74..f6cbb831b86a 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -280,12 +280,13 @@ enum { /* quirks for old Intel chipsets */ #define AZX_DCAPS_INTEL_ICH \ - (AZX_DCAPS_OLD_SSYNC | AZX_DCAPS_NO_ALIGN_BUFSIZE) + (AZX_DCAPS_OLD_SSYNC | AZX_DCAPS_NO_ALIGN_BUFSIZE |\ + AZX_DCAPS_SYNC_WRITE) /* quirks for Intel PCH */ #define AZX_DCAPS_INTEL_PCH_BASE \ (AZX_DCAPS_NO_ALIGN_BUFSIZE | AZX_DCAPS_COUNT_LPIB_DELAY |\ - AZX_DCAPS_SNOOP_TYPE(SCH)) + AZX_DCAPS_SNOOP_TYPE(SCH) | AZX_DCAPS_SYNC_WRITE) /* PCH up to IVB; no runtime PM; bind with i915 gfx */ #define AZX_DCAPS_INTEL_PCH_NOPM \ @@ -300,13 +301,13 @@ enum { #define AZX_DCAPS_INTEL_HASWELL \ (/*AZX_DCAPS_ALIGN_BUFSIZE |*/ AZX_DCAPS_COUNT_LPIB_DELAY |\ AZX_DCAPS_PM_RUNTIME | AZX_DCAPS_I915_COMPONENT |\ - AZX_DCAPS_SNOOP_TYPE(SCH)) + AZX_DCAPS_SNOOP_TYPE(SCH) | AZX_DCAPS_SYNC_WRITE) /* Broadwell HDMI can't use position buffer reliably, force to use LPIB */ #define AZX_DCAPS_INTEL_BROADWELL \ (/*AZX_DCAPS_ALIGN_BUFSIZE |*/ AZX_DCAPS_POSFIX_LPIB |\ AZX_DCAPS_PM_RUNTIME | AZX_DCAPS_I915_COMPONENT |\ - AZX_DCAPS_SNOOP_TYPE(SCH)) + AZX_DCAPS_SNOOP_TYPE(SCH) | AZX_DCAPS_SYNC_WRITE) #define AZX_DCAPS_INTEL_BAYTRAIL \ (AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_I915_COMPONENT) @@ -1280,11 +1281,17 @@ static void init_vga_switcheroo(struct azx *chip) { struct hda_intel *hda = container_of(chip, struct hda_intel, chip); struct pci_dev *p = get_bound_vga(chip->pci); + struct pci_dev *parent; if (p) { dev_info(chip->card->dev, "Handle vga_switcheroo audio client\n"); hda->use_vga_switcheroo = 1; - chip->bus.keep_power = 1; /* cleared in either gpu_bound op or codec probe */ + + /* cleared in either gpu_bound op or codec probe, or when its + * upstream port has _PR3 (i.e. dGPU). + */ + parent = pci_upstream_bridge(p); + chip->bus.keep_power = parent ? !pci_pr3_present(parent) : 1; chip->driver_caps |= AZX_DCAPS_PM_RUNTIME; pci_dev_put(p); } @@ -1382,8 +1389,11 @@ static int azx_free(struct azx *chip) static int azx_dev_disconnect(struct snd_device *device) { struct azx *chip = device->device_data; + struct hdac_bus *bus = azx_bus(chip); chip->bus.shutdown = 1; + cancel_work_sync(&bus->unsol_work); + return 0; } diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index b7a1abb3e231..32ed46464af7 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -1809,13 +1809,14 @@ struct scp_msg { static void dspio_clear_response_queue(struct hda_codec *codec) { + unsigned long timeout = jiffies + msecs_to_jiffies(1000); unsigned int dummy = 0; - int status = -1; + int status; /* clear all from the response queue */ do { status = dspio_read(codec, &dummy); - } while (status == 0); + } while (status == 0 && time_before(jiffies, timeout)); } static int dspio_get_response_data(struct hda_codec *codec) @@ -7588,12 +7589,14 @@ static void ca0132_process_dsp_response(struct hda_codec *codec, struct ca0132_spec *spec = codec->spec; codec_dbg(codec, "ca0132_process_dsp_response\n"); + snd_hda_power_up_pm(codec); if (spec->wait_scp) { if (dspio_get_response_data(codec) >= 0) spec->wait_scp = 0; } dspio_clear_response_queue(codec); + snd_hda_power_down_pm(codec); } static void hp_callback(struct hda_codec *codec, struct hda_jack_callback *cb) @@ -7604,11 +7607,10 @@ static void hp_callback(struct hda_codec *codec, struct hda_jack_callback *cb) /* Delay enabling the HP amp, to let the mic-detection * state machine run. */ - cancel_delayed_work(&spec->unsol_hp_work); - schedule_delayed_work(&spec->unsol_hp_work, msecs_to_jiffies(500)); tbl = snd_hda_jack_tbl_get(codec, cb->nid); if (tbl) tbl->block_report = 1; + schedule_delayed_work(&spec->unsol_hp_work, msecs_to_jiffies(500)); } static void amic_callback(struct hda_codec *codec, struct hda_jack_callback *cb) @@ -8454,12 +8456,25 @@ static void ca0132_reboot_notify(struct hda_codec *codec) codec->patch_ops.free(codec); } +#ifdef CONFIG_PM +static int ca0132_suspend(struct hda_codec *codec) +{ + struct ca0132_spec *spec = codec->spec; + + cancel_delayed_work_sync(&spec->unsol_hp_work); + return 0; +} +#endif + static const struct hda_codec_ops ca0132_patch_ops = { .build_controls = ca0132_build_controls, .build_pcms = ca0132_build_pcms, .init = ca0132_init, .free = ca0132_free, .unsol_event = snd_hda_jack_unsol_event, +#ifdef CONFIG_PM + .suspend = ca0132_suspend, +#endif .reboot_notify = ca0132_reboot_notify, }; diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index 968d3caab6ac..90aa0f400a57 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -910,6 +910,7 @@ static const struct snd_pci_quirk cxt5066_fixups[] = { SND_PCI_QUIRK(0x103c, 0x837f, "HP ProBook 470 G5", CXT_FIXUP_MUTE_LED_GPIO), SND_PCI_QUIRK(0x103c, 0x8299, "HP 800 G3 SFF", CXT_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x829a, "HP 800 G3 DM", CXT_FIXUP_HP_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x103c, 0x8402, "HP ProBook 645 G4", CXT_FIXUP_MUTE_LED_GPIO), SND_PCI_QUIRK(0x103c, 0x8455, "HP Z2 G4", CXT_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x8456, "HP Z2 G4 SFF", CXT_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x8457, "HP Z2 G4 mini", CXT_FIXUP_HP_MIC_NO_PRESENCE), diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 78bd2e3722c7..488c17c9f375 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -32,6 +32,7 @@ #include #include "hda_local.h" #include "hda_jack.h" +#include "hda_controller.h" static bool static_hdmi_pcm; module_param(static_hdmi_pcm, bool, 0644); @@ -1240,6 +1241,10 @@ static int hdmi_pcm_open(struct hda_pcm_stream *hinfo, per_pin->cvt_nid = per_cvt->cvt_nid; hinfo->nid = per_cvt->cvt_nid; + /* flip stripe flag for the assigned stream if supported */ + if (get_wcaps(codec, per_cvt->cvt_nid) & AC_WCAP_STRIPE) + azx_stream(get_azx_dev(substream))->stripe = 1; + snd_hda_set_dev_select(codec, per_pin->pin_nid, per_pin->dev_id); snd_hda_codec_write_cache(codec, per_pin->pin_nid, 0, AC_VERB_SET_CONNECT_SEL, @@ -1978,6 +1983,8 @@ static int hdmi_pcm_close(struct hda_pcm_stream *hinfo, per_cvt->assigned = 0; hinfo->nid = 0; + azx_stream(get_azx_dev(substream))->stripe = 0; + mutex_lock(&spec->pcm_lock); snd_hda_spdif_ctls_unassign(codec, pcm_idx); clear_bit(pcm_idx, &spec->pcm_in_use); @@ -3454,26 +3461,6 @@ static int nvhdmi_chmap_validate(struct hdac_chmap *chmap, return 0; } -/* map from pin NID to port; port is 0-based */ -/* for Nvidia: assume widget NID starting from 4, with step 1 (4, 5, 6, ...) */ -static int nvhdmi_pin2port(void *audio_ptr, int pin_nid) -{ - return pin_nid - 4; -} - -/* reverse-map from port to pin NID: see above */ -static int nvhdmi_port2pin(struct hda_codec *codec, int port) -{ - return port + 4; -} - -static const struct drm_audio_component_audio_ops nvhdmi_audio_ops = { - .pin2port = nvhdmi_pin2port, - .pin_eld_notify = generic_acomp_pin_eld_notify, - .master_bind = generic_acomp_master_bind, - .master_unbind = generic_acomp_master_unbind, -}; - static int patch_nvhdmi(struct hda_codec *codec) { struct hdmi_spec *spec; @@ -3492,8 +3479,6 @@ static int patch_nvhdmi(struct hda_codec *codec) codec->link_down_at_suspend = 1; - generic_acomp_init(codec, &nvhdmi_audio_ops, nvhdmi_port2pin); - return 0; } diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 80f66ba85f87..d293488dc3dd 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -367,9 +367,7 @@ static void alc_fill_eapd_coef(struct hda_codec *codec) case 0x10ec0215: case 0x10ec0233: case 0x10ec0235: - case 0x10ec0236: case 0x10ec0255: - case 0x10ec0256: case 0x10ec0257: case 0x10ec0282: case 0x10ec0283: @@ -381,6 +379,11 @@ static void alc_fill_eapd_coef(struct hda_codec *codec) case 0x10ec0300: alc_update_coef_idx(codec, 0x10, 1<<9, 0); break; + case 0x10ec0236: + case 0x10ec0256: + alc_write_coef_idx(codec, 0x36, 0x5757); + alc_update_coef_idx(codec, 0x10, 1<<9, 0); + break; case 0x10ec0275: alc_update_coef_idx(codec, 0xe, 0, 1<<0); break; @@ -409,6 +412,7 @@ static void alc_fill_eapd_coef(struct hda_codec *codec) case 0x10ec0672: alc_update_coef_idx(codec, 0xd, 0, 1<<14); /* EAPD Ctrl */ break; + case 0x10ec0222: case 0x10ec0623: alc_update_coef_idx(codec, 0x19, 1<<13, 0); break; @@ -427,6 +431,7 @@ static void alc_fill_eapd_coef(struct hda_codec *codec) break; case 0x10ec0899: case 0x10ec0900: + case 0x10ec0b00: case 0x10ec1168: case 0x10ec1220: alc_update_coef_idx(codec, 0x7, 1<<1, 0); @@ -498,6 +503,7 @@ static void alc_shutup_pins(struct hda_codec *codec) struct alc_spec *spec = codec->spec; switch (codec->core.vendor_id) { + case 0x10ec0283: case 0x10ec0286: case 0x10ec0288: case 0x10ec0298: @@ -2522,6 +2528,7 @@ static int patch_alc882(struct hda_codec *codec) case 0x10ec0882: case 0x10ec0885: case 0x10ec0900: + case 0x10ec0b00: case 0x10ec1220: break; default: @@ -5544,6 +5551,16 @@ static void alc295_fixup_disable_dac3(struct hda_codec *codec, } } +/* force NID 0x17 (Bass Speaker) to DAC1 to share it with the main speaker */ +static void alc285_fixup_speaker2_to_dac1(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + if (action == HDA_FIXUP_ACT_PRE_PROBE) { + hda_nid_t conn[1] = { 0x02 }; + snd_hda_override_conn_list(codec, 0x17, 1, conn); + } +} + /* Hook to update amp GPIO4 for automute */ static void alc280_hp_gpio4_automute_hook(struct hda_codec *codec, struct hda_jack_callback *jack) @@ -5846,6 +5863,7 @@ enum { ALC225_FIXUP_DISABLE_MIC_VREF, ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, ALC295_FIXUP_DISABLE_DAC3, + ALC285_FIXUP_SPEAKER2_TO_DAC1, ALC280_FIXUP_HP_HEADSET_MIC, ALC221_FIXUP_HP_FRONT_MIC, ALC292_FIXUP_TPT460, @@ -5890,8 +5908,12 @@ enum { ALC256_FIXUP_ASUS_HEADSET_MIC, ALC256_FIXUP_ASUS_MIC_NO_PRESENCE, ALC299_FIXUP_PREDATOR_SPK, - ALC294_FIXUP_ASUS_INTSPK_HEADSET_MIC, ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE, + ALC289_FIXUP_DELL_SPK2, + ALC289_FIXUP_DUAL_SPK, + ALC294_FIXUP_SPK2_TO_DAC1, + ALC294_FIXUP_ASUS_DUAL_SPK, + }; static const struct hda_fixup alc269_fixups[] = { @@ -6645,6 +6667,10 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc295_fixup_disable_dac3, }, + [ALC285_FIXUP_SPEAKER2_TO_DAC1] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_speaker2_to_dac1, + }, [ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -6962,26 +6988,45 @@ static const struct hda_fixup alc269_fixups[] = { { } } }, - [ALC294_FIXUP_ASUS_INTSPK_HEADSET_MIC] = { + [ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { - { 0x14, 0x411111f0 }, /* disable confusing internal speaker */ - { 0x19, 0x04a11150 }, /* use as headset mic, without its own jack detect */ + { 0x19, 0x04a11040 }, + { 0x21, 0x04211020 }, { } }, .chained = true, - .chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC + .chain_id = ALC256_FIXUP_ASUS_HEADSET_MODE }, - [ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE] = { + [ALC289_FIXUP_DELL_SPK2] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { - { 0x19, 0x04a11040 }, - { 0x21, 0x04211020 }, + { 0x17, 0x90170130 }, /* bass spk */ { } }, .chained = true, - .chain_id = ALC256_FIXUP_ASUS_HEADSET_MODE + .chain_id = ALC269_FIXUP_DELL4_MIC_NO_PRESENCE }, + [ALC289_FIXUP_DUAL_SPK] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_speaker2_to_dac1, + .chained = true, + .chain_id = ALC289_FIXUP_DELL_SPK2 + }, + [ALC294_FIXUP_SPK2_TO_DAC1] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_speaker2_to_dac1, + .chained = true, + .chain_id = ALC294_FIXUP_ASUS_HEADSET_MIC + }, + [ALC294_FIXUP_ASUS_DUAL_SPK] = { + .type = HDA_FIXUP_FUNC, + /* The GPIO must be pulled to initialize the AMP */ + .v.func = alc_fixup_gpio4, + .chained = true, + .chain_id = ALC294_FIXUP_SPK2_TO_DAC1 + }, + }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -7054,6 +7099,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x08ad, "Dell WYSE AIO", ALC225_FIXUP_DELL_WYSE_AIO_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x08ae, "Dell WYSE NB", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0935, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB), + SND_PCI_QUIRK(0x1028, 0x097e, "Dell Precision", ALC289_FIXUP_DUAL_SPK), + SND_PCI_QUIRK(0x1028, 0x097d, "Dell Precision", ALC289_FIXUP_DUAL_SPK), SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2), @@ -7141,7 +7188,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK), SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A), SND_PCI_QUIRK(0x1043, 0x16e3, "ASUS UX50", ALC269_FIXUP_STEREO_DMIC), - SND_PCI_QUIRK(0x1043, 0x17d1, "ASUS UX431FL", ALC294_FIXUP_ASUS_INTSPK_HEADSET_MIC), + SND_PCI_QUIRK(0x1043, 0x17d1, "ASUS UX431FL", ALC294_FIXUP_ASUS_DUAL_SPK), SND_PCI_QUIRK(0x1043, 0x18b1, "Asus MJ401TA", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1a13, "Asus G73Jw", ALC269_FIXUP_ASUS_G73JW), SND_PCI_QUIRK(0x1043, 0x1a30, "ASUS X705UD", ALC256_FIXUP_ASUS_MIC), @@ -7213,6 +7260,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x224c, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x224d, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x225d, "Thinkpad T480", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), + SND_PCI_QUIRK(0x17aa, 0x2292, "Thinkpad X1 Yoga 7th", ALC285_FIXUP_SPEAKER2_TO_DAC1), + SND_PCI_QUIRK(0x17aa, 0x2293, "Thinkpad X1 Carbon 7th", ALC285_FIXUP_SPEAKER2_TO_DAC1), SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION), @@ -7248,6 +7297,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x9e54, "LENOVO NB", ALC269_FIXUP_LENOVO_EAPD), SND_PCI_QUIRK(0x19e5, 0x3204, "Huawei MACH-WX9", ALC256_FIXUP_HUAWEI_MACH_WX9_PINS), SND_PCI_QUIRK(0x1b7d, 0xa831, "Ordissimo EVE2 ", ALC269VB_FIXUP_ORDISSIMO_EVE2), /* Also known as Malata PC-B1303 */ + SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x10ec, 0x118c, "Medion EE4254 MD62100", ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE), #if 0 @@ -7396,6 +7446,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {.id = ALC255_FIXUP_DELL_SPK_NOISE, .name = "dell-spk-noise"}, {.id = ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, .name = "alc225-dell1"}, {.id = ALC295_FIXUP_DISABLE_DAC3, .name = "alc295-disable-dac3"}, + {.id = ALC285_FIXUP_SPEAKER2_TO_DAC1, .name = "alc285-speaker2-to-dac1"}, {.id = ALC280_FIXUP_HP_HEADSET_MIC, .name = "alc280-hp-headset"}, {.id = ALC221_FIXUP_HP_FRONT_MIC, .name = "alc221-hp-mic"}, {.id = ALC298_FIXUP_SPK_VOLUME, .name = "alc298-spk-volume"}, @@ -7660,11 +7711,6 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x1a, 0x90a70130}, {0x1b, 0x90170110}, {0x21, 0x03211020}), - SND_HDA_PIN_QUIRK(0x10ec0274, 0x1028, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB, - {0x12, 0xb7a60130}, - {0x13, 0xb8a61140}, - {0x16, 0x90170110}, - {0x21, 0x04211020}), SND_HDA_PIN_QUIRK(0x10ec0280, 0x103c, "HP", ALC280_FIXUP_HP_GPIO4, {0x12, 0x90a60130}, {0x14, 0x90170110}, @@ -7852,6 +7898,9 @@ static const struct snd_hda_pin_quirk alc269_fallback_pin_fixup_tbl[] = { SND_HDA_PIN_QUIRK(0x10ec0289, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, {0x19, 0x40000000}, {0x1b, 0x40000000}), + SND_HDA_PIN_QUIRK(0x10ec0274, 0x1028, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB, + {0x19, 0x40000000}, + {0x1a, 0x40000000}), {} }; @@ -8455,6 +8504,8 @@ static void alc662_fixup_aspire_ethos_hp(struct hda_codec *codec, case HDA_FIXUP_ACT_PRE_PROBE: snd_hda_jack_detect_enable_callback(codec, 0x1b, alc662_aspire_ethos_mute_speakers); + /* subwoofer needs an extra GPIO setting to become audible */ + alc_setup_gpio(codec, 0x02); break; case HDA_FIXUP_ACT_INIT: /* Make sure to start in a correct state, i.e. if @@ -8537,7 +8588,6 @@ enum { ALC662_FIXUP_USI_HEADSET_MODE, ALC662_FIXUP_LENOVO_MULTI_CODECS, ALC669_FIXUP_ACER_ASPIRE_ETHOS, - ALC669_FIXUP_ACER_ASPIRE_ETHOS_SUBWOOFER, ALC669_FIXUP_ACER_ASPIRE_ETHOS_HEADSET, }; @@ -8869,18 +8919,6 @@ static const struct hda_fixup alc662_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc662_fixup_aspire_ethos_hp, }, - [ALC669_FIXUP_ACER_ASPIRE_ETHOS_SUBWOOFER] = { - .type = HDA_FIXUP_VERBS, - /* subwoofer needs an extra GPIO setting to become audible */ - .v.verbs = (const struct hda_verb[]) { - {0x01, AC_VERB_SET_GPIO_MASK, 0x02}, - {0x01, AC_VERB_SET_GPIO_DIRECTION, 0x02}, - {0x01, AC_VERB_SET_GPIO_DATA, 0x00}, - { } - }, - .chained = true, - .chain_id = ALC669_FIXUP_ACER_ASPIRE_ETHOS_HEADSET - }, [ALC669_FIXUP_ACER_ASPIRE_ETHOS] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -8890,7 +8928,7 @@ static const struct hda_fixup alc662_fixups[] = { { } }, .chained = true, - .chain_id = ALC669_FIXUP_ACER_ASPIRE_ETHOS_SUBWOOFER + .chain_id = ALC669_FIXUP_ACER_ASPIRE_ETHOS_HEADSET }, }; @@ -9261,6 +9299,7 @@ static const struct hda_device_id snd_hda_id_realtek[] = { HDA_CODEC_ENTRY(0x10ec0892, "ALC892", patch_alc662), HDA_CODEC_ENTRY(0x10ec0899, "ALC898", patch_alc882), HDA_CODEC_ENTRY(0x10ec0900, "ALC1150", patch_alc882), + HDA_CODEC_ENTRY(0x10ec0b00, "ALCS1200A", patch_alc882), HDA_CODEC_ENTRY(0x10ec1168, "ALC1220", patch_alc882), HDA_CODEC_ENTRY(0x10ec1220, "ALC1220", patch_alc882), {} /* terminator */ diff --git a/sound/pci/ice1712/ice1724.c b/sound/pci/ice1712/ice1724.c index e62c11816683..f360b33a1042 100644 --- a/sound/pci/ice1712/ice1724.c +++ b/sound/pci/ice1712/ice1724.c @@ -647,6 +647,7 @@ static int snd_vt1724_set_pro_rate(struct snd_ice1712 *ice, unsigned int rate, unsigned long flags; unsigned char mclk_change; unsigned int i, old_rate; + bool call_set_rate = false; if (rate > ice->hw_rates->list[ice->hw_rates->count - 1]) return -EINVAL; @@ -670,7 +671,7 @@ static int snd_vt1724_set_pro_rate(struct snd_ice1712 *ice, unsigned int rate, * setting clock rate for internal clock mode */ old_rate = ice->get_rate(ice); if (force || (old_rate != rate)) - ice->set_rate(ice, rate); + call_set_rate = true; else if (rate == ice->cur_rate) { spin_unlock_irqrestore(&ice->reg_lock, flags); return 0; @@ -678,12 +679,14 @@ static int snd_vt1724_set_pro_rate(struct snd_ice1712 *ice, unsigned int rate, } ice->cur_rate = rate; + spin_unlock_irqrestore(&ice->reg_lock, flags); + + if (call_set_rate) + ice->set_rate(ice, rate); /* setting master clock */ mclk_change = ice->set_mclk(ice, rate); - spin_unlock_irqrestore(&ice->reg_lock, flags); - if (mclk_change && ice->gpio.i2s_mclk_changed) ice->gpio.i2s_mclk_changed(ice); if (ice->gpio.set_pro_rate) diff --git a/sound/soc/codecs/max98090.c b/sound/soc/codecs/max98090.c index f6bf4cfbea23..45da2b51543e 100644 --- a/sound/soc/codecs/max98090.c +++ b/sound/soc/codecs/max98090.c @@ -2103,10 +2103,8 @@ static void max98090_pll_det_disable_work(struct work_struct *work) M98090_IULK_MASK, 0); } -static void max98090_pll_work(struct work_struct *work) +static void max98090_pll_work(struct max98090_priv *max98090) { - struct max98090_priv *max98090 = - container_of(work, struct max98090_priv, pll_work); struct snd_soc_component *component = max98090->component; if (!snd_soc_component_is_active(component)) @@ -2259,7 +2257,7 @@ static irqreturn_t max98090_interrupt(int irq, void *data) if (active & M98090_ULK_MASK) { dev_dbg(component->dev, "M98090_ULK_MASK\n"); - schedule_work(&max98090->pll_work); + max98090_pll_work(max98090); } if (active & M98090_JDET_MASK) { @@ -2422,7 +2420,6 @@ static int max98090_probe(struct snd_soc_component *component) max98090_pll_det_enable_work); INIT_WORK(&max98090->pll_det_disable_work, max98090_pll_det_disable_work); - INIT_WORK(&max98090->pll_work, max98090_pll_work); /* Enable jack detection */ snd_soc_component_write(component, M98090_REG_JACK_DETECT, @@ -2475,7 +2472,6 @@ static void max98090_remove(struct snd_soc_component *component) cancel_delayed_work_sync(&max98090->jack_work); cancel_delayed_work_sync(&max98090->pll_det_enable_work); cancel_work_sync(&max98090->pll_det_disable_work); - cancel_work_sync(&max98090->pll_work); max98090->component = NULL; } diff --git a/sound/soc/codecs/max98090.h b/sound/soc/codecs/max98090.h index 57965cd678b4..a197114b0dad 100644 --- a/sound/soc/codecs/max98090.h +++ b/sound/soc/codecs/max98090.h @@ -1530,7 +1530,6 @@ struct max98090_priv { struct delayed_work jack_work; struct delayed_work pll_det_enable_work; struct work_struct pll_det_disable_work; - struct work_struct pll_work; struct snd_soc_jack *jack; unsigned int dai_fmt; int tdm_slots; diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c index 1c06b3b9218c..19662ee330d6 100644 --- a/sound/soc/codecs/rt5645.c +++ b/sound/soc/codecs/rt5645.c @@ -3270,6 +3270,9 @@ static void rt5645_jack_detect_work(struct work_struct *work) snd_soc_jack_report(rt5645->mic_jack, report, SND_JACK_MICROPHONE); return; + case 4: + val = snd_soc_component_read32(rt5645->component, RT5645_A_JD_CTRL1) & 0x0020; + break; default: /* read rt5645 jd1_1 status */ val = snd_soc_component_read32(rt5645->component, RT5645_INT_IRQ_ST) & 0x1000; break; @@ -3603,7 +3606,7 @@ static const struct rt5645_platform_data intel_braswell_platform_data = { static const struct rt5645_platform_data buddy_platform_data = { .dmic1_data_pin = RT5645_DMIC_DATA_GPIO5, .dmic2_data_pin = RT5645_DMIC_DATA_IN2P, - .jd_mode = 3, + .jd_mode = 4, .level_trigger_irq = true, }; @@ -3999,6 +4002,7 @@ static int rt5645_i2c_probe(struct i2c_client *i2c, RT5645_JD1_MODE_1); break; case 3: + case 4: regmap_update_bits(rt5645->regmap, RT5645_A_JD_CTRL1, RT5645_JD1_MODE_MASK, RT5645_JD1_MODE_2); diff --git a/sound/soc/codecs/rt5677.c b/sound/soc/codecs/rt5677.c index 315a3d39bc09..8bc9450da79c 100644 --- a/sound/soc/codecs/rt5677.c +++ b/sound/soc/codecs/rt5677.c @@ -298,6 +298,7 @@ static bool rt5677_volatile_register(struct device *dev, unsigned int reg) case RT5677_I2C_MASTER_CTRL7: case RT5677_I2C_MASTER_CTRL8: case RT5677_HAP_GENE_CTRL2: + case RT5677_PWR_ANLG2: /* Modified by DSP firmware */ case RT5677_PWR_DSP_ST: case RT5677_PRIV_DATA: case RT5677_ASRC_22: diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c index c50b75ce82e0..05e883a65d7a 100644 --- a/sound/soc/codecs/rt5682.c +++ b/sound/soc/codecs/rt5682.c @@ -72,6 +72,7 @@ struct rt5682_priv { static const struct reg_sequence patch_list[] = { {RT5682_HP_IMP_SENS_CTRL_19, 0x1000}, {RT5682_DAC_ADC_DIG_VOL1, 0xa020}, + {RT5682_I2C_CTRL, 0x000f}, }; static const struct reg_default rt5682_reg[] = { @@ -2481,6 +2482,7 @@ static void rt5682_calibrate(struct rt5682_priv *rt5682) mutex_lock(&rt5682->calibrate_mutex); rt5682_reset(rt5682->regmap); + regmap_write(rt5682->regmap, RT5682_I2C_CTRL, 0x000f); regmap_write(rt5682->regmap, RT5682_PWR_ANLG_1, 0xa2af); usleep_range(15000, 20000); regmap_write(rt5682->regmap, RT5682_PWR_ANLG_1, 0xf2af); diff --git a/sound/soc/codecs/wm2200.c b/sound/soc/codecs/wm2200.c index cf64e109c658..7b087d94141b 100644 --- a/sound/soc/codecs/wm2200.c +++ b/sound/soc/codecs/wm2200.c @@ -2410,6 +2410,8 @@ static int wm2200_i2c_probe(struct i2c_client *i2c, err_pm_runtime: pm_runtime_disable(&i2c->dev); + if (i2c->irq) + free_irq(i2c->irq, wm2200); err_reset: if (wm2200->pdata.reset) gpio_set_value_cansleep(wm2200->pdata.reset, 0); @@ -2426,12 +2428,15 @@ static int wm2200_i2c_remove(struct i2c_client *i2c) { struct wm2200_priv *wm2200 = i2c_get_clientdata(i2c); + pm_runtime_disable(&i2c->dev); if (i2c->irq) free_irq(i2c->irq, wm2200); if (wm2200->pdata.reset) gpio_set_value_cansleep(wm2200->pdata.reset, 0); if (wm2200->pdata.ldo_ena) gpio_set_value_cansleep(wm2200->pdata.ldo_ena, 0); + regulator_bulk_disable(ARRAY_SIZE(wm2200->core_supplies), + wm2200->core_supplies); return 0; } diff --git a/sound/soc/codecs/wm5100.c b/sound/soc/codecs/wm5100.c index 4af0e519e623..91cc63c5a51f 100644 --- a/sound/soc/codecs/wm5100.c +++ b/sound/soc/codecs/wm5100.c @@ -2617,6 +2617,7 @@ static int wm5100_i2c_probe(struct i2c_client *i2c, return ret; err_reset: + pm_runtime_disable(&i2c->dev); if (i2c->irq) free_irq(i2c->irq, wm5100); wm5100_free_gpio(i2c); @@ -2640,6 +2641,7 @@ static int wm5100_i2c_remove(struct i2c_client *i2c) { struct wm5100_priv *wm5100 = i2c_get_clientdata(i2c); + pm_runtime_disable(&i2c->dev); if (i2c->irq) free_irq(i2c->irq, wm5100); wm5100_free_gpio(i2c); diff --git a/sound/soc/codecs/wm8904.c b/sound/soc/codecs/wm8904.c index bcb3c9d5abf0..9e8c564f6e9c 100644 --- a/sound/soc/codecs/wm8904.c +++ b/sound/soc/codecs/wm8904.c @@ -1917,6 +1917,7 @@ static int wm8904_set_bias_level(struct snd_soc_component *component, snd_soc_component_update_bits(component, WM8904_BIAS_CONTROL_0, WM8904_BIAS_ENA, 0); + snd_soc_component_write(component, WM8904_SW_RESET_AND_ID, 0); regcache_cache_only(wm8904->regmap, true); regcache_mark_dirty(wm8904->regmap); diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c index 3e5c69fbc33a..d9d59f45833f 100644 --- a/sound/soc/codecs/wm8962.c +++ b/sound/soc/codecs/wm8962.c @@ -2788,7 +2788,7 @@ static int fll_factors(struct _fll_div *fll_div, unsigned int Fref, if (target % Fref == 0) { fll_div->theta = 0; - fll_div->lambda = 0; + fll_div->lambda = 1; } else { gcd_fll = gcd(target, fratio * Fref); @@ -2858,7 +2858,7 @@ static int wm8962_set_fll(struct snd_soc_component *component, int fll_id, int s return -EINVAL; } - if (fll_div.theta || fll_div.lambda) + if (fll_div.theta) fll1 |= WM8962_FLL_FRAC; /* Stop the FLL while we reconfigure */ diff --git a/sound/soc/fsl/fsl_audmix.c b/sound/soc/fsl/fsl_audmix.c index c7e4e9757dce..a1db1bce330f 100644 --- a/sound/soc/fsl/fsl_audmix.c +++ b/sound/soc/fsl/fsl_audmix.c @@ -286,6 +286,7 @@ static int fsl_audmix_dai_trigger(struct snd_pcm_substream *substream, int cmd, struct snd_soc_dai *dai) { struct fsl_audmix *priv = snd_soc_dai_get_drvdata(dai); + unsigned long lock_flags; /* Capture stream shall not be handled */ if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) @@ -295,12 +296,16 @@ static int fsl_audmix_dai_trigger(struct snd_pcm_substream *substream, int cmd, case SNDRV_PCM_TRIGGER_START: case SNDRV_PCM_TRIGGER_RESUME: case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: + spin_lock_irqsave(&priv->lock, lock_flags); priv->tdms |= BIT(dai->driver->id); + spin_unlock_irqrestore(&priv->lock, lock_flags); break; case SNDRV_PCM_TRIGGER_STOP: case SNDRV_PCM_TRIGGER_SUSPEND: case SNDRV_PCM_TRIGGER_PAUSE_PUSH: + spin_lock_irqsave(&priv->lock, lock_flags); priv->tdms &= ~BIT(dai->driver->id); + spin_unlock_irqrestore(&priv->lock, lock_flags); break; default: return -EINVAL; @@ -491,6 +496,7 @@ static int fsl_audmix_probe(struct platform_device *pdev) return PTR_ERR(priv->ipg_clk); } + spin_lock_init(&priv->lock); platform_set_drvdata(pdev, priv); pm_runtime_enable(dev); diff --git a/sound/soc/fsl/fsl_audmix.h b/sound/soc/fsl/fsl_audmix.h index 7812ffec45c5..479f05695d53 100644 --- a/sound/soc/fsl/fsl_audmix.h +++ b/sound/soc/fsl/fsl_audmix.h @@ -96,6 +96,7 @@ struct fsl_audmix { struct platform_device *pdev; struct regmap *regmap; struct clk *ipg_clk; + spinlock_t lock; /* Protect tdms */ u8 tdms; }; diff --git a/sound/soc/fsl/fsl_esai.c b/sound/soc/fsl/fsl_esai.c index a78e4ab478df..c7a49d03463a 100644 --- a/sound/soc/fsl/fsl_esai.c +++ b/sound/soc/fsl/fsl_esai.c @@ -33,6 +33,7 @@ * @fsysclk: system clock source to derive HCK, SCK and FS * @spbaclk: SPBA clock (optional, depending on SoC design) * @task: tasklet to handle the reset operation + * @lock: spin lock between hw_reset() and trigger() * @fifo_depth: depth of tx/rx FIFO * @slot_width: width of each DAI slot * @slots: number of slots @@ -56,6 +57,7 @@ struct fsl_esai { struct clk *fsysclk; struct clk *spbaclk; struct tasklet_struct task; + spinlock_t lock; /* Protect hw_reset and trigger */ u32 fifo_depth; u32 slot_width; u32 slots; @@ -676,8 +678,10 @@ static void fsl_esai_hw_reset(unsigned long arg) { struct fsl_esai *esai_priv = (struct fsl_esai *)arg; bool tx = true, rx = false, enabled[2]; + unsigned long lock_flags; u32 tfcr, rfcr; + spin_lock_irqsave(&esai_priv->lock, lock_flags); /* Save the registers */ regmap_read(esai_priv->regmap, REG_ESAI_TFCR, &tfcr); regmap_read(esai_priv->regmap, REG_ESAI_RFCR, &rfcr); @@ -715,6 +719,8 @@ static void fsl_esai_hw_reset(unsigned long arg) fsl_esai_trigger_start(esai_priv, tx); if (enabled[rx]) fsl_esai_trigger_start(esai_priv, rx); + + spin_unlock_irqrestore(&esai_priv->lock, lock_flags); } static int fsl_esai_trigger(struct snd_pcm_substream *substream, int cmd, @@ -722,6 +728,7 @@ static int fsl_esai_trigger(struct snd_pcm_substream *substream, int cmd, { struct fsl_esai *esai_priv = snd_soc_dai_get_drvdata(dai); bool tx = substream->stream == SNDRV_PCM_STREAM_PLAYBACK; + unsigned long lock_flags; esai_priv->channels[tx] = substream->runtime->channels; @@ -729,12 +736,16 @@ static int fsl_esai_trigger(struct snd_pcm_substream *substream, int cmd, case SNDRV_PCM_TRIGGER_START: case SNDRV_PCM_TRIGGER_RESUME: case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: + spin_lock_irqsave(&esai_priv->lock, lock_flags); fsl_esai_trigger_start(esai_priv, tx); + spin_unlock_irqrestore(&esai_priv->lock, lock_flags); break; case SNDRV_PCM_TRIGGER_SUSPEND: case SNDRV_PCM_TRIGGER_STOP: case SNDRV_PCM_TRIGGER_PAUSE_PUSH: + spin_lock_irqsave(&esai_priv->lock, lock_flags); fsl_esai_trigger_stop(esai_priv, tx); + spin_unlock_irqrestore(&esai_priv->lock, lock_flags); break; default: return -EINVAL; @@ -1002,6 +1013,7 @@ static int fsl_esai_probe(struct platform_device *pdev) dev_set_drvdata(&pdev->dev, esai_priv); + spin_lock_init(&esai_priv->lock); ret = fsl_esai_hw_init(esai_priv); if (ret) return ret; diff --git a/sound/soc/intel/Kconfig b/sound/soc/intel/Kconfig index 01c99750212a..ef493cae78ff 100644 --- a/sound/soc/intel/Kconfig +++ b/sound/soc/intel/Kconfig @@ -59,6 +59,9 @@ config SND_SOC_INTEL_HASWELL If you have a Intel Haswell or Broadwell platform connected to an I2S codec, then enable this option by saying Y or m. This is typically used for Chromebooks. This is a recommended option. + This option is mutually exclusive with the SOF support on + Broadwell. If you want to enable SOF on Broadwell, you need to + deselect this option first. config SND_SOC_INTEL_BAYTRAIL tristate "Baytrail (legacy) Platforms" diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c index 9c1aa4ec9cba..243f683bc02a 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -405,10 +405,12 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { DMI_MATCH(DMI_SYS_VENDOR, "Acer"), DMI_MATCH(DMI_PRODUCT_NAME, "Aspire SW5-012"), }, - .driver_data = (void *)(BYT_RT5640_IN1_MAP | - BYT_RT5640_MCLK_EN | - BYT_RT5640_SSP0_AIF1), - + .driver_data = (void *)(BYT_RT5640_DMIC1_MAP | + BYT_RT5640_JD_SRC_JD2_IN4N | + BYT_RT5640_OVCD_TH_2000UA | + BYT_RT5640_OVCD_SF_0P75 | + BYT_RT5640_SSP0_AIF1 | + BYT_RT5640_MCLK_EN), }, { .matches = { @@ -705,13 +707,17 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { BYT_RT5640_MCLK_EN), }, { + /* Teclast X89 */ .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "TECLAST"), DMI_MATCH(DMI_BOARD_NAME, "tPAD"), }, .driver_data = (void *)(BYT_RT5640_IN3_MAP | - BYT_RT5640_MCLK_EN | - BYT_RT5640_SSP0_AIF1), + BYT_RT5640_JD_SRC_JD1_IN4P | + BYT_RT5640_OVCD_TH_2000UA | + BYT_RT5640_OVCD_SF_1P0 | + BYT_RT5640_SSP0_AIF1 | + BYT_RT5640_MCLK_EN), }, { /* Toshiba Satellite Click Mini L9W-B */ .matches = { diff --git a/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c b/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c index 74dda8784f1a..67b276a65a8d 100644 --- a/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c +++ b/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c @@ -400,6 +400,9 @@ static int kabylake_dmic_startup(struct snd_pcm_substream *substream) snd_pcm_hw_constraint_list(runtime, 0, SNDRV_PCM_HW_PARAM_CHANNELS, dmic_constraints); + runtime->hw.formats = SNDRV_PCM_FMTBIT_S16_LE; + snd_pcm_hw_constraint_msbits(runtime, 0, 16, 16); + return snd_pcm_hw_constraint_list(substream->runtime, 0, SNDRV_PCM_HW_PARAM_RATE, &constraints_rates); } diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c index e9596c2096cd..a6c1cf987e6e 100644 --- a/sound/soc/sh/rcar/core.c +++ b/sound/soc/sh/rcar/core.c @@ -376,6 +376,17 @@ u32 rsnd_get_adinr_bit(struct rsnd_mod *mod, struct rsnd_dai_stream *io) */ u32 rsnd_get_dalign(struct rsnd_mod *mod, struct rsnd_dai_stream *io) { + static const u32 dalign_values[8][2] = { + {0x76543210, 0x67452301}, + {0x00000032, 0x00000023}, + {0x00007654, 0x00006745}, + {0x00000076, 0x00000067}, + {0xfedcba98, 0xefcdab89}, + {0x000000ba, 0x000000ab}, + {0x0000fedc, 0x0000efcd}, + {0x000000fe, 0x000000ef}, + }; + int id = 0, inv; struct rsnd_mod *ssiu = rsnd_io_to_mod_ssiu(io); struct rsnd_mod *target; struct snd_pcm_runtime *runtime = rsnd_io_to_runtime(io); @@ -411,13 +422,18 @@ u32 rsnd_get_dalign(struct rsnd_mod *mod, struct rsnd_dai_stream *io) target = cmd ? cmd : ssiu; } + if (mod == ssiu) + id = rsnd_mod_id_sub(mod); + /* Non target mod or non 16bit needs normal DALIGN */ if ((snd_pcm_format_width(runtime->format) != 16) || (mod != target)) - return 0x76543210; + inv = 0; /* Target mod needs inverted DALIGN when 16bit */ else - return 0x67452301; + inv = 1; + + return dalign_values[id][inv]; } u32 rsnd_get_busif_shift(struct rsnd_dai_stream *io, struct rsnd_mod *mod) diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 88978a3036c4..9d3b546bae7b 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -1886,6 +1886,8 @@ static void soc_check_tplg_fes(struct snd_soc_card *card) /* convert non BE into BE */ dai_link->no_pcm = 1; + dai_link->dpcm_playback = 1; + dai_link->dpcm_capture = 1; /* override any BE fixups */ dai_link->be_hw_params_fixup = diff --git a/sound/soc/soc-jack.c b/sound/soc/soc-jack.c index a71d2340eb05..b5748dcd490f 100644 --- a/sound/soc/soc-jack.c +++ b/sound/soc/soc-jack.c @@ -82,10 +82,9 @@ void snd_soc_jack_report(struct snd_soc_jack *jack, int status, int mask) unsigned int sync = 0; int enable; - trace_snd_soc_jack_report(jack, mask, status); - if (!jack) return; + trace_snd_soc_jack_report(jack, mask, status); dapm = &jack->card->dapm; diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index b600d3eaaf5c..d07026a846b9 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -877,6 +877,11 @@ static int soc_pcm_hw_params(struct snd_pcm_substream *substream, int i, ret = 0; mutex_lock_nested(&rtd->card->pcm_mutex, rtd->card->pcm_subclass); + + ret = soc_pcm_params_symmetry(substream, params); + if (ret) + goto out; + if (rtd->dai_link->ops->hw_params) { ret = rtd->dai_link->ops->hw_params(substream, params); if (ret < 0) { @@ -958,9 +963,6 @@ static int soc_pcm_hw_params(struct snd_pcm_substream *substream, } component = NULL; - ret = soc_pcm_params_symmetry(substream, params); - if (ret) - goto component_err; out: mutex_unlock(&rtd->card->pcm_mutex); return ret; @@ -1146,7 +1148,9 @@ static int dpcm_be_connect(struct snd_soc_pcm_runtime *fe, { struct snd_soc_dpcm *dpcm; unsigned long flags; +#ifdef CONFIG_DEBUG_FS char *name; +#endif /* only add new dpcms */ for_each_dpcm_be(fe, stream, dpcm) { @@ -1385,6 +1389,7 @@ static int dpcm_prune_paths(struct snd_soc_pcm_runtime *fe, int stream, struct snd_soc_dapm_widget *widget; struct snd_soc_dai *dai; int prune = 0; + int do_prune; /* Destroy any old FE <--> BE connections */ for_each_dpcm_be(fe, stream, dpcm) { @@ -1398,13 +1403,16 @@ static int dpcm_prune_paths(struct snd_soc_pcm_runtime *fe, int stream, continue; /* is there a valid CODEC DAI widget for this BE */ + do_prune = 1; for_each_rtd_codec_dai(dpcm->be, i, dai) { widget = dai_get_widget(dai, stream); /* prune the BE if it's no longer in our active list */ if (widget && widget_in_list(list, widget)) - continue; + do_prune = 0; } + if (!do_prune) + continue; dev_dbg(fe->dev, "ASoC: pruning %s BE %s for %s\n", stream ? "capture" : "playback", diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index 0fd032914a31..fd2d22ddc81b 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -1918,11 +1918,13 @@ static int soc_tplg_fe_link_create(struct soc_tplg *tplg, ret = soc_tplg_dai_link_load(tplg, link, NULL); if (ret < 0) { dev_err(tplg->comp->dev, "ASoC: FE link loading failed\n"); - kfree(link->name); - kfree(link->stream_name); - kfree(link->cpus->dai_name); - kfree(link); - return ret; + goto err; + } + + ret = snd_soc_add_dai_link(tplg->comp->card, link); + if (ret < 0) { + dev_err(tplg->comp->dev, "ASoC: adding FE link failed\n"); + goto err; } link->dobj.index = tplg->index; @@ -1930,8 +1932,13 @@ static int soc_tplg_fe_link_create(struct soc_tplg *tplg, link->dobj.type = SND_SOC_DOBJ_DAI_LINK; list_add(&link->dobj.list, &tplg->comp->dobj_list); - snd_soc_add_dai_link(tplg->comp->card, link); return 0; +err: + kfree(link->name); + kfree(link->stream_name); + kfree(link->cpus->dai_name); + kfree(link); + return ret; } /* create a FE DAI and DAI link from the PCM object */ @@ -2024,6 +2031,7 @@ static int soc_tplg_pcm_elems_load(struct soc_tplg *tplg, int size; int i; bool abi_match; + int ret; count = le32_to_cpu(hdr->count); @@ -2065,7 +2073,12 @@ static int soc_tplg_pcm_elems_load(struct soc_tplg *tplg, } /* create the FE DAIs and DAI links */ - soc_tplg_pcm_create(tplg, _pcm); + ret = soc_tplg_pcm_create(tplg, _pcm); + if (ret < 0) { + if (!abi_match) + kfree(_pcm); + return ret; + } /* offset by version-specific struct size and * real priv data size diff --git a/sound/soc/sof/imx/Kconfig b/sound/soc/sof/imx/Kconfig index 5acae75f5750..71f318bc2c74 100644 --- a/sound/soc/sof/imx/Kconfig +++ b/sound/soc/sof/imx/Kconfig @@ -11,8 +11,8 @@ config SND_SOC_SOF_IMX_TOPLEVEL if SND_SOC_SOF_IMX_TOPLEVEL -config SND_SOC_SOF_IMX8 - tristate "SOF support for i.MX8" +config SND_SOC_SOF_IMX8_SUPPORT + bool "SOF support for i.MX8" depends on IMX_SCU depends on IMX_DSP help @@ -20,4 +20,8 @@ config SND_SOC_SOF_IMX8 Say Y if you have such a device. If unsure select "N". +config SND_SOC_SOF_IMX8 + def_tristate SND_SOC_SOF_OF + depends on SND_SOC_SOF_IMX8_SUPPORT + endif ## SND_SOC_SOF_IMX_IMX_TOPLEVEL diff --git a/sound/soc/sof/imx/imx8.c b/sound/soc/sof/imx/imx8.c index 2a22b18e5ec0..69785f688ddf 100644 --- a/sound/soc/sof/imx/imx8.c +++ b/sound/soc/sof/imx/imx8.c @@ -209,7 +209,7 @@ static int imx8_probe(struct snd_sof_dev *sdev) priv->pd_dev = devm_kmalloc_array(&pdev->dev, priv->num_domains, sizeof(*priv->pd_dev), GFP_KERNEL); - if (!priv) + if (!priv->pd_dev) return -ENOMEM; priv->link = devm_kmalloc_array(&pdev->dev, priv->num_domains, @@ -304,6 +304,9 @@ static int imx8_probe(struct snd_sof_dev *sdev) } sdev->mailbox_bar = SOF_FW_BLK_TYPE_SRAM; + /* set default mailbox offset for FW ready message */ + sdev->dsp_box.offset = MBOX_OFFSET; + return 0; exit_pdev_unregister: diff --git a/sound/soc/sof/intel/Kconfig b/sound/soc/sof/intel/Kconfig index d62f51d33be1..8421b97d949e 100644 --- a/sound/soc/sof/intel/Kconfig +++ b/sound/soc/sof/intel/Kconfig @@ -76,10 +76,18 @@ config SND_SOC_SOF_BAYTRAIL config SND_SOC_SOF_BROADWELL_SUPPORT bool "SOF support for Broadwell" + depends on SND_SOC_INTEL_HASWELL=n help This adds support for Sound Open Firmware for Intel(R) platforms using the Broadwell processors. - Say Y if you have such a device. + This option is mutually exclusive with the Haswell/Broadwell legacy + driver. If you want to enable SOF on Broadwell you need to deselect + the legacy driver first. + SOF does fully support Broadwell yet, so this option is not + recommended for distros. At some point all legacy drivers will be + deprecated but not before all userspace firmware/topology/UCM files + are made available to downstream distros. + Say Y if you want to enable SOF on Broadwell If unsure select "N". config SND_SOC_SOF_BROADWELL diff --git a/sound/soc/sof/intel/byt.c b/sound/soc/sof/intel/byt.c index a1e514f71739..41008c974ac6 100644 --- a/sound/soc/sof/intel/byt.c +++ b/sound/soc/sof/intel/byt.c @@ -24,7 +24,8 @@ #define DRAM_OFFSET 0x100000 #define DRAM_SIZE (160 * 1024) #define SHIM_OFFSET 0x140000 -#define SHIM_SIZE 0x100 +#define SHIM_SIZE_BYT 0x100 +#define SHIM_SIZE_CHT 0x118 #define MBOX_OFFSET 0x144000 #define MBOX_SIZE 0x1000 #define EXCEPT_OFFSET 0x800 @@ -75,7 +76,7 @@ static const struct snd_sof_debugfs_map byt_debugfs[] = { SOF_DEBUGFS_ACCESS_D0_ONLY}, {"dram", BYT_DSP_BAR, DRAM_OFFSET, DRAM_SIZE, SOF_DEBUGFS_ACCESS_D0_ONLY}, - {"shim", BYT_DSP_BAR, SHIM_OFFSET, SHIM_SIZE, + {"shim", BYT_DSP_BAR, SHIM_OFFSET, SHIM_SIZE_BYT, SOF_DEBUGFS_ACCESS_ALWAYS}, }; @@ -102,7 +103,7 @@ static const struct snd_sof_debugfs_map cht_debugfs[] = { SOF_DEBUGFS_ACCESS_D0_ONLY}, {"dram", BYT_DSP_BAR, DRAM_OFFSET, DRAM_SIZE, SOF_DEBUGFS_ACCESS_D0_ONLY}, - {"shim", BYT_DSP_BAR, SHIM_OFFSET, SHIM_SIZE, + {"shim", BYT_DSP_BAR, SHIM_OFFSET, SHIM_SIZE_CHT, SOF_DEBUGFS_ACCESS_ALWAYS}, }; diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c index 06e84679087b..5a5163eef2ef 100644 --- a/sound/soc/sof/intel/hda.c +++ b/sound/soc/sof/intel/hda.c @@ -268,6 +268,7 @@ static int hda_init(struct snd_sof_dev *sdev) bus->use_posbuf = 1; bus->bdl_pos_adj = 0; + bus->sync_write = 1; mutex_init(&hbus->prepare_mutex); hbus->pci = pci; diff --git a/sound/soc/sof/loader.c b/sound/soc/sof/loader.c index 9a9a381a908d..a041adf0669d 100644 --- a/sound/soc/sof/loader.c +++ b/sound/soc/sof/loader.c @@ -66,6 +66,8 @@ int snd_sof_fw_parse_ext_data(struct snd_sof_dev *sdev, u32 bar, u32 offset) ret = get_ext_windows(sdev, ext_hdr); break; default: + dev_warn(sdev->dev, "warning: unknown ext header type %d size 0x%x\n", + ext_hdr->type, ext_hdr->hdr.size); break; } diff --git a/sound/soc/sof/topology.c b/sound/soc/sof/topology.c index 4452594c2e17..fa299e078156 100644 --- a/sound/soc/sof/topology.c +++ b/sound/soc/sof/topology.c @@ -2828,6 +2828,10 @@ static int sof_link_load(struct snd_soc_component *scomp, int index, if (!link->no_pcm) { link->nonatomic = true; + /* set trigger order */ + link->trigger[0] = SND_SOC_DPCM_TRIGGER_POST; + link->trigger[1] = SND_SOC_DPCM_TRIGGER_POST; + /* nothing more to do for FE dai links */ return 0; } diff --git a/sound/soc/stm/stm32_spdifrx.c b/sound/soc/stm/stm32_spdifrx.c index cd4b235fce57..e53fb4bd66b3 100644 --- a/sound/soc/stm/stm32_spdifrx.c +++ b/sound/soc/stm/stm32_spdifrx.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include @@ -220,6 +219,7 @@ * @slave_config: dma slave channel runtime config pointer * @phys_addr: SPDIFRX registers physical base address * @lock: synchronization enabling lock + * @irq_lock: prevent race condition with IRQ on stream state * @cs: channel status buffer * @ub: user data buffer * @irq: SPDIFRX interrupt line @@ -240,6 +240,7 @@ struct stm32_spdifrx_data { struct dma_slave_config slave_config; dma_addr_t phys_addr; spinlock_t lock; /* Sync enabling lock */ + spinlock_t irq_lock; /* Prevent race condition on stream state */ unsigned char cs[SPDIFRX_CS_BYTES_NB]; unsigned char ub[SPDIFRX_UB_BYTES_NB]; int irq; @@ -320,6 +321,7 @@ static void stm32_spdifrx_dma_ctrl_stop(struct stm32_spdifrx_data *spdifrx) static int stm32_spdifrx_start_sync(struct stm32_spdifrx_data *spdifrx) { int cr, cr_mask, imr, ret; + unsigned long flags; /* Enable IRQs */ imr = SPDIFRX_IMR_IFEIE | SPDIFRX_IMR_SYNCDIE | SPDIFRX_IMR_PERRIE; @@ -327,7 +329,7 @@ static int stm32_spdifrx_start_sync(struct stm32_spdifrx_data *spdifrx) if (ret) return ret; - spin_lock(&spdifrx->lock); + spin_lock_irqsave(&spdifrx->lock, flags); spdifrx->refcount++; @@ -360,7 +362,7 @@ static int stm32_spdifrx_start_sync(struct stm32_spdifrx_data *spdifrx) "Failed to start synchronization\n"); } - spin_unlock(&spdifrx->lock); + spin_unlock_irqrestore(&spdifrx->lock, flags); return ret; } @@ -368,11 +370,12 @@ static int stm32_spdifrx_start_sync(struct stm32_spdifrx_data *spdifrx) static void stm32_spdifrx_stop(struct stm32_spdifrx_data *spdifrx) { int cr, cr_mask, reg; + unsigned long flags; - spin_lock(&spdifrx->lock); + spin_lock_irqsave(&spdifrx->lock, flags); if (--spdifrx->refcount) { - spin_unlock(&spdifrx->lock); + spin_unlock_irqrestore(&spdifrx->lock, flags); return; } @@ -391,7 +394,7 @@ static void stm32_spdifrx_stop(struct stm32_spdifrx_data *spdifrx) regmap_read(spdifrx->regmap, STM32_SPDIFRX_DR, ®); regmap_read(spdifrx->regmap, STM32_SPDIFRX_CSR, ®); - spin_unlock(&spdifrx->lock); + spin_unlock_irqrestore(&spdifrx->lock, flags); } static int stm32_spdifrx_dma_ctrl_register(struct device *dev, @@ -478,8 +481,6 @@ static int stm32_spdifrx_get_ctrl_data(struct stm32_spdifrx_data *spdifrx) memset(spdifrx->cs, 0, SPDIFRX_CS_BYTES_NB); memset(spdifrx->ub, 0, SPDIFRX_UB_BYTES_NB); - pinctrl_pm_select_default_state(&spdifrx->pdev->dev); - ret = stm32_spdifrx_dma_ctrl_start(spdifrx); if (ret < 0) return ret; @@ -511,7 +512,6 @@ static int stm32_spdifrx_get_ctrl_data(struct stm32_spdifrx_data *spdifrx) end: clk_disable_unprepare(spdifrx->kclk); - pinctrl_pm_select_sleep_state(&spdifrx->pdev->dev); return ret; } @@ -663,7 +663,6 @@ static const struct regmap_config stm32_h7_spdifrx_regmap_conf = { static irqreturn_t stm32_spdifrx_isr(int irq, void *devid) { struct stm32_spdifrx_data *spdifrx = (struct stm32_spdifrx_data *)devid; - struct snd_pcm_substream *substream = spdifrx->substream; struct platform_device *pdev = spdifrx->pdev; unsigned int cr, mask, sr, imr; unsigned int flags; @@ -731,14 +730,19 @@ static irqreturn_t stm32_spdifrx_isr(int irq, void *devid) regmap_update_bits(spdifrx->regmap, STM32_SPDIFRX_CR, SPDIFRX_CR_SPDIFEN_MASK, cr); - if (substream) - snd_pcm_stop(substream, SNDRV_PCM_STATE_DISCONNECTED); + spin_lock(&spdifrx->irq_lock); + if (spdifrx->substream) + snd_pcm_stop(spdifrx->substream, + SNDRV_PCM_STATE_DISCONNECTED); + spin_unlock(&spdifrx->irq_lock); return IRQ_HANDLED; } - if (err_xrun && substream) - snd_pcm_stop_xrun(substream); + spin_lock(&spdifrx->irq_lock); + if (err_xrun && spdifrx->substream) + snd_pcm_stop_xrun(spdifrx->substream); + spin_unlock(&spdifrx->irq_lock); return IRQ_HANDLED; } @@ -747,9 +751,12 @@ static int stm32_spdifrx_startup(struct snd_pcm_substream *substream, struct snd_soc_dai *cpu_dai) { struct stm32_spdifrx_data *spdifrx = snd_soc_dai_get_drvdata(cpu_dai); + unsigned long flags; int ret; + spin_lock_irqsave(&spdifrx->irq_lock, flags); spdifrx->substream = substream; + spin_unlock_irqrestore(&spdifrx->irq_lock, flags); ret = clk_prepare_enable(spdifrx->kclk); if (ret) @@ -825,8 +832,12 @@ static void stm32_spdifrx_shutdown(struct snd_pcm_substream *substream, struct snd_soc_dai *cpu_dai) { struct stm32_spdifrx_data *spdifrx = snd_soc_dai_get_drvdata(cpu_dai); + unsigned long flags; + spin_lock_irqsave(&spdifrx->irq_lock, flags); spdifrx->substream = NULL; + spin_unlock_irqrestore(&spdifrx->irq_lock, flags); + clk_disable_unprepare(spdifrx->kclk); } @@ -930,6 +941,7 @@ static int stm32_spdifrx_probe(struct platform_device *pdev) spdifrx->pdev = pdev; init_completion(&spdifrx->cs_completion); spin_lock_init(&spdifrx->lock); + spin_lock_init(&spdifrx->irq_lock); platform_set_drvdata(pdev, spdifrx); diff --git a/sound/usb/card.h b/sound/usb/card.h index 2991b9986f66..395403a2d33f 100644 --- a/sound/usb/card.h +++ b/sound/usb/card.h @@ -145,6 +145,7 @@ struct snd_usb_substream { struct snd_usb_endpoint *sync_endpoint; unsigned long flags; bool need_setup_ep; /* (re)configure EP at prepare? */ + bool need_setup_fmt; /* (re)configure fmt after resume? */ unsigned int speed; /* USB_SPEED_XXX */ u64 formats; /* format bitmasks (all or'ed) */ diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 45eee5cc312e..6cd4ff09c5ee 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -2930,6 +2930,9 @@ static int snd_usb_mixer_controls_badd(struct usb_mixer_interface *mixer, continue; iface = usb_ifnum_to_if(dev, intf); + if (!iface) + continue; + num = iface->num_altsetting; if (num < 2) diff --git a/sound/usb/mixer_scarlett_gen2.c b/sound/usb/mixer_scarlett_gen2.c index 7d460b1f1735..94b903d95afa 100644 --- a/sound/usb/mixer_scarlett_gen2.c +++ b/sound/usb/mixer_scarlett_gen2.c @@ -261,34 +261,34 @@ static const struct scarlett2_device_info s6i6_gen2_info = { }, .ports = { - { + [SCARLETT2_PORT_TYPE_NONE] = { .id = 0x000, .num = { 1, 0, 8, 8, 8 }, .src_descr = "Off", .src_num_offset = 0, }, - { + [SCARLETT2_PORT_TYPE_ANALOGUE] = { .id = 0x080, .num = { 4, 4, 4, 4, 4 }, .src_descr = "Analogue %d", .src_num_offset = 1, .dst_descr = "Analogue Output %02d Playback" }, - { + [SCARLETT2_PORT_TYPE_SPDIF] = { .id = 0x180, .num = { 2, 2, 2, 2, 2 }, .src_descr = "S/PDIF %d", .src_num_offset = 1, .dst_descr = "S/PDIF Output %d Playback" }, - { + [SCARLETT2_PORT_TYPE_MIX] = { .id = 0x300, .num = { 10, 18, 18, 18, 18 }, .src_descr = "Mix %c", .src_num_offset = 65, .dst_descr = "Mixer Input %02d Capture" }, - { + [SCARLETT2_PORT_TYPE_PCM] = { .id = 0x600, .num = { 6, 6, 6, 6, 6 }, .src_descr = "PCM %d", @@ -317,44 +317,44 @@ static const struct scarlett2_device_info s18i8_gen2_info = { }, .ports = { - { + [SCARLETT2_PORT_TYPE_NONE] = { .id = 0x000, .num = { 1, 0, 8, 8, 4 }, .src_descr = "Off", .src_num_offset = 0, }, - { + [SCARLETT2_PORT_TYPE_ANALOGUE] = { .id = 0x080, .num = { 8, 6, 6, 6, 6 }, .src_descr = "Analogue %d", .src_num_offset = 1, .dst_descr = "Analogue Output %02d Playback" }, - { + [SCARLETT2_PORT_TYPE_SPDIF] = { + .id = 0x180, /* S/PDIF outputs aren't available at 192KHz * but are included in the USB mux I/O * assignment message anyway */ - .id = 0x180, .num = { 2, 2, 2, 2, 2 }, .src_descr = "S/PDIF %d", .src_num_offset = 1, .dst_descr = "S/PDIF Output %d Playback" }, - { + [SCARLETT2_PORT_TYPE_ADAT] = { .id = 0x200, .num = { 8, 0, 0, 0, 0 }, .src_descr = "ADAT %d", .src_num_offset = 1, }, - { + [SCARLETT2_PORT_TYPE_MIX] = { .id = 0x300, .num = { 10, 18, 18, 18, 18 }, .src_descr = "Mix %c", .src_num_offset = 65, .dst_descr = "Mixer Input %02d Capture" }, - { + [SCARLETT2_PORT_TYPE_PCM] = { .id = 0x600, .num = { 20, 18, 18, 14, 10 }, .src_descr = "PCM %d", @@ -387,20 +387,20 @@ static const struct scarlett2_device_info s18i20_gen2_info = { }, .ports = { - { + [SCARLETT2_PORT_TYPE_NONE] = { .id = 0x000, .num = { 1, 0, 8, 8, 6 }, .src_descr = "Off", .src_num_offset = 0, }, - { + [SCARLETT2_PORT_TYPE_ANALOGUE] = { .id = 0x080, .num = { 8, 10, 10, 10, 10 }, .src_descr = "Analogue %d", .src_num_offset = 1, .dst_descr = "Analogue Output %02d Playback" }, - { + [SCARLETT2_PORT_TYPE_SPDIF] = { /* S/PDIF outputs aren't available at 192KHz * but are included in the USB mux I/O * assignment message anyway @@ -411,21 +411,21 @@ static const struct scarlett2_device_info s18i20_gen2_info = { .src_num_offset = 1, .dst_descr = "S/PDIF Output %d Playback" }, - { + [SCARLETT2_PORT_TYPE_ADAT] = { .id = 0x200, .num = { 8, 8, 8, 4, 0 }, .src_descr = "ADAT %d", .src_num_offset = 1, .dst_descr = "ADAT Output %d Playback" }, - { + [SCARLETT2_PORT_TYPE_MIX] = { .id = 0x300, .num = { 10, 18, 18, 18, 18 }, .src_descr = "Mix %c", .src_num_offset = 65, .dst_descr = "Mixer Input %02d Capture" }, - { + [SCARLETT2_PORT_TYPE_PCM] = { .id = 0x600, .num = { 20, 18, 18, 14, 10 }, .src_descr = "PCM %d", diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index ff5ab24f3bd1..a04c727dcd19 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -506,15 +506,15 @@ static int set_format(struct snd_usb_substream *subs, struct audioformat *fmt) if (WARN_ON(!iface)) return -EINVAL; alts = usb_altnum_to_altsetting(iface, fmt->altsetting); - altsd = get_iface_desc(alts); - if (WARN_ON(altsd->bAlternateSetting != fmt->altsetting)) + if (WARN_ON(!alts)) return -EINVAL; + altsd = get_iface_desc(alts); - if (fmt == subs->cur_audiofmt) + if (fmt == subs->cur_audiofmt && !subs->need_setup_fmt) return 0; /* close the old interface */ - if (subs->interface >= 0 && subs->interface != fmt->iface) { + if (subs->interface >= 0 && (subs->interface != fmt->iface || subs->need_setup_fmt)) { if (!subs->stream->chip->keep_iface) { err = usb_set_interface(subs->dev, subs->interface, 0); if (err < 0) { @@ -528,6 +528,9 @@ static int set_format(struct snd_usb_substream *subs, struct audioformat *fmt) subs->altset_idx = 0; } + if (subs->need_setup_fmt) + subs->need_setup_fmt = false; + /* set interface */ if (iface->cur_altsetting != alts) { err = snd_usb_select_mode_quirk(subs, fmt); @@ -1735,6 +1738,13 @@ static int snd_usb_substream_playback_trigger(struct snd_pcm_substream *substrea subs->data_endpoint->retire_data_urb = retire_playback_urb; subs->running = 0; return 0; + case SNDRV_PCM_TRIGGER_SUSPEND: + if (subs->stream->chip->setup_fmt_after_resume_quirk) { + stop_endpoints(subs, true); + subs->need_setup_fmt = true; + return 0; + } + break; } return -EINVAL; @@ -1767,6 +1777,13 @@ static int snd_usb_substream_capture_trigger(struct snd_pcm_substream *substream subs->data_endpoint->retire_data_urb = retire_capture_urb; subs->running = 1; return 0; + case SNDRV_PCM_TRIGGER_SUSPEND: + if (subs->stream->chip->setup_fmt_after_resume_quirk) { + stop_endpoints(subs, true); + subs->need_setup_fmt = true; + return 0; + } + break; } return -EINVAL; diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index 70c338f3ae24..d187aa6d50db 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -3466,7 +3466,8 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"), .vendor_name = "Dell", .product_name = "WD19 Dock", .profile_name = "Dell-WD15-Dock", - .ifnum = QUIRK_NO_INTERFACE + .ifnum = QUIRK_ANY_INTERFACE, + .type = QUIRK_SETUP_FMT_AFTER_RESUME } }, /* MOTU Microbook II */ diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 349e1e52996d..82184036437b 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -508,6 +508,16 @@ static int create_standard_mixer_quirk(struct snd_usb_audio *chip, return snd_usb_create_mixer(chip, quirk->ifnum, 0); } + +static int setup_fmt_after_resume_quirk(struct snd_usb_audio *chip, + struct usb_interface *iface, + struct usb_driver *driver, + const struct snd_usb_audio_quirk *quirk) +{ + chip->setup_fmt_after_resume_quirk = 1; + return 1; /* Continue with creating streams and mixer */ +} + /* * audio-interface quirks * @@ -546,6 +556,7 @@ int snd_usb_create_quirk(struct snd_usb_audio *chip, [QUIRK_AUDIO_EDIROL_UAXX] = create_uaxx_quirk, [QUIRK_AUDIO_ALIGN_TRANSFER] = create_align_transfer_quirk, [QUIRK_AUDIO_STANDARD_MIXER] = create_standard_mixer_quirk, + [QUIRK_SETUP_FMT_AFTER_RESUME] = setup_fmt_after_resume_quirk, }; if (quirk->type < QUIRK_TYPE_COUNT) { @@ -1386,6 +1397,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip) case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */ case USB_ID(0x0556, 0x0014): /* Phoenix Audio TMX320VC */ case USB_ID(0x05A3, 0x9420): /* ELP HD USB Camera */ + case USB_ID(0x05a7, 0x1020): /* Bose Companion 5 */ case USB_ID(0x074D, 0x3553): /* Outlaw RR2150 (Micronas UAC3553B) */ case USB_ID(0x1395, 0x740a): /* Sennheiser DECT */ case USB_ID(0x1901, 0x0191): /* GE B850V3 CP2114 audio interface */ diff --git a/sound/usb/usbaudio.h b/sound/usb/usbaudio.h index feb30f9c1716..e360680f45f3 100644 --- a/sound/usb/usbaudio.h +++ b/sound/usb/usbaudio.h @@ -33,7 +33,7 @@ struct snd_usb_audio { wait_queue_head_t shutdown_wait; unsigned int txfr_quirk:1; /* Subframe boundaries on transfers */ unsigned int tx_length_quirk:1; /* Put length specifier in transfers */ - + unsigned int setup_fmt_after_resume_quirk:1; /* setup the format to interface after resume */ int num_interfaces; int num_suspended_intf; int sample_rate_read_error; @@ -98,6 +98,7 @@ enum quirk_type { QUIRK_AUDIO_EDIROL_UAXX, QUIRK_AUDIO_ALIGN_TRANSFER, QUIRK_AUDIO_STANDARD_MIXER, + QUIRK_SETUP_FMT_AFTER_RESUME, QUIRK_TYPE_COUNT }; diff --git a/tools/arch/x86/lib/x86-opcode-map.txt b/tools/arch/x86/lib/x86-opcode-map.txt index e0b85930dd77..0a0e9112f284 100644 --- a/tools/arch/x86/lib/x86-opcode-map.txt +++ b/tools/arch/x86/lib/x86-opcode-map.txt @@ -333,7 +333,7 @@ AVXcode: 1 06: CLTS 07: SYSRET (o64) 08: INVD -09: WBINVD +09: WBINVD | WBNOINVD (F3) 0a: 0b: UD2 (1B) 0c: @@ -364,7 +364,7 @@ AVXcode: 1 # a ModR/M byte. 1a: BNDCL Gv,Ev (F3) | BNDCU Gv,Ev (F2) | BNDMOV Gv,Ev (66) | BNDLDX Gv,Ev 1b: BNDCN Gv,Ev (F2) | BNDMOV Ev,Gv (66) | BNDMK Gv,Ev (F3) | BNDSTX Ev,Gv -1c: +1c: Grp20 (1A),(1C) 1d: 1e: 1f: NOP Ev @@ -792,6 +792,8 @@ f3: Grp17 (1A) f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v) f6: ADCX Gy,Ey (66) | ADOX Gy,Ey (F3) | MULX By,Gy,rDX,Ey (F2),(v) f7: BEXTR Gy,Ey,By (v) | SHLX Gy,Ey,By (66),(v) | SARX Gy,Ey,By (F3),(v) | SHRX Gy,Ey,By (F2),(v) +f8: MOVDIR64B Gv,Mdqq (66) | ENQCMD Gv,Mdqq (F2) | ENQCMDS Gv,Mdqq (F3) +f9: MOVDIRI My,Gy EndTable Table: 3-byte opcode 2 (0x0f 0x3a) @@ -943,9 +945,9 @@ GrpTable: Grp6 EndTable GrpTable: Grp7 -0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) -1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) -2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) +0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B) +1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) | ENCLS (111),(11B) +2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) | ENCLU (111),(11B) 3: LIDT Ms 4: SMSW Mw/Rv 5: rdpkru (110),(11B) | wrpkru (111),(11B) @@ -1020,7 +1022,7 @@ GrpTable: Grp15 3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B) 4: XSAVE | ptwrite Ey (F3),(11B) 5: XRSTOR | lfence (11B) -6: XSAVEOPT | clwb (66) | mfence (11B) +6: XSAVEOPT | clwb (66) | mfence (11B) | TPAUSE Rd (66),(11B) | UMONITOR Rv (F3),(11B) | UMWAIT Rd (F2),(11B) 7: clflush | clflushopt (66) | sfence (11B) EndTable @@ -1051,6 +1053,10 @@ GrpTable: Grp19 6: vscatterpf1qps/d Wx (66),(ev) EndTable +GrpTable: Grp20 +0: cldemote Mb +EndTable + # AMD's Prefetch Group GrpTable: GrpP 0: PREFETCH diff --git a/tools/arch/x86/tools/gen-insn-attr-x86.awk b/tools/arch/x86/tools/gen-insn-attr-x86.awk index b02a36b2c14f..a42015b305f4 100644 --- a/tools/arch/x86/tools/gen-insn-attr-x86.awk +++ b/tools/arch/x86/tools/gen-insn-attr-x86.awk @@ -69,7 +69,7 @@ BEGIN { lprefix1_expr = "\\((66|!F3)\\)" lprefix2_expr = "\\(F3\\)" - lprefix3_expr = "\\((F2|!F3|66\\&F2)\\)" + lprefix3_expr = "\\((F2|!F3|66&F2)\\)" lprefix_expr = "\\((66|F2|F3)\\)" max_lprefix = 4 @@ -257,7 +257,7 @@ function convert_operands(count,opnd, i,j,imm,mod) return add_flags(imm, mod) } -/^[0-9a-f]+\:/ { +/^[0-9a-f]+:/ { if (NR == 1) next # get index diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile index 5d1995fd369c..5535650800ab 100644 --- a/tools/bpf/Makefile +++ b/tools/bpf/Makefile @@ -16,7 +16,13 @@ CFLAGS += -D__EXPORTED_HEADERS__ -I$(srctree)/include/uapi -I$(srctree)/include # isn't set and when invoked from selftests build, where srctree # is set to ".". building_out_of_srctree is undefined for in srctree # builds +ifeq ($(srctree),) +update_srctree := 1 +endif ifndef building_out_of_srctree +update_srctree := 1 +endif +ifeq ($(update_srctree),1) srctree := $(patsubst %/,%,$(dir $(CURDIR))) srctree := $(patsubst %/,%,$(dir $(srctree))) endif diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 43fdbbfe41bb..ea0bcd58bcb9 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -493,7 +493,7 @@ static int do_dump(int argc, char **argv) info = &info_linear->info; if (mode == DUMP_JITED) { - if (info->jited_prog_len == 0) { + if (info->jited_prog_len == 0 || !info->jited_prog_insns) { p_info("no instructions returned"); goto err_free; } diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c index 494d7ae3614d..5b91ee65a080 100644 --- a/tools/bpf/bpftool/xlated_dumper.c +++ b/tools/bpf/bpftool/xlated_dumper.c @@ -174,7 +174,7 @@ static const char *print_call(void *private_data, struct kernel_sym *sym; if (insn->src_reg == BPF_PSEUDO_CALL && - (__u32) insn->imm < dd->nr_jited_ksyms) + (__u32) insn->imm < dd->nr_jited_ksyms && dd->jited_ksyms) address = dd->jited_ksyms[insn->imm]; sym = kernel_syms_search(dd, address); diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 56ce6292071b..33e2638ef7f0 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -215,7 +215,7 @@ check_abi: $(OUTPUT)libbpf.so "versioned symbols in $^ ($(VERSIONED_SYM_COUNT))." \ "Please make sure all LIBBPF_API symbols are" \ "versioned in $(VERSION_SCRIPT)." >&2; \ - readelf -s --wide $(OUTPUT)libbpf-in.o | \ + readelf -s --wide $(BPF_IN_SHARED) | \ cut -d "@" -f1 | sed 's/_v[0-9]_[0-9]_[0-9].*//' | \ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$8}'| \ sort -u > $(OUTPUT)libbpf_global_syms.tmp; \ diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index ede55fec3618..87f27e2664c5 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -876,7 +876,6 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, __u16 vlen = btf_vlen(t); packed = is_struct ? btf_is_struct_packed(d->btf, id, t) : 0; - align = packed ? 1 : btf_align_of(d->btf, id); btf_dump_printf(d, "%s%s%s {", is_struct ? "struct" : "union", @@ -906,6 +905,13 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, btf_dump_printf(d, ";"); } + /* pad at the end, if necessary */ + if (is_struct) { + align = packed ? 1 : btf_align_of(d->btf, id); + btf_dump_emit_bit_padding(d, off, t->size * 8, 0, align, + lvl + 1); + } + if (vlen) btf_dump_printf(d, "\n"); btf_dump_printf(d, "%s}", pfx(lvl)); diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index e0276520171b..a267cd0c0ce2 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -1897,16 +1897,22 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd) return -errno; new_fd = open("/", O_RDONLY | O_CLOEXEC); - if (new_fd < 0) + if (new_fd < 0) { + err = -errno; goto err_free_new_name; + } new_fd = dup3(fd, new_fd, O_CLOEXEC); - if (new_fd < 0) + if (new_fd < 0) { + err = -errno; goto err_close_new_fd; + } err = zclose(map->fd); - if (err) + if (err) { + err = -errno; goto err_close_new_fd; + } free(map->name); map->fd = new_fd; @@ -1925,7 +1931,7 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd) close(new_fd); err_free_new_name: free(new_name); - return -errno; + return err; } int bpf_map__resize(struct bpf_map *map, __u32 max_entries) diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index a902838f9fcc..70f9e10de286 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -163,6 +163,7 @@ int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area, umem->umem_area = umem_area; xsk_set_umem_config(&umem->config, usr_config); + memset(&mr, 0, sizeof(mr)); mr.addr = (uintptr_t)umem_area; mr.len = size; mr.chunk_size = umem->config.frame_size; @@ -343,13 +344,18 @@ static int xsk_get_max_queues(struct xsk_socket *xsk) goto out; } - if (err || channels.max_combined == 0) + if (err) { /* If the device says it has no channels, then all traffic * is sent to a single stream, so max queues = 1. */ ret = 1; - else - ret = channels.max_combined; + } else { + /* Take the max of rx, tx, combined. Drivers return + * the number of channels in different ways. + */ + ret = max(channels.max_rx, channels.max_tx); + ret = max(ret, (int)channels.max_combined); + } out: close(fd); @@ -465,6 +471,8 @@ static int xsk_setup_xdp_prog(struct xsk_socket *xsk) } } else { xsk->prog_fd = bpf_prog_get_fd_by_id(prog_id); + if (xsk->prog_fd < 0) + return -errno; err = xsk_lookup_bpf_maps(xsk); if (err) { close(xsk->prog_fd); diff --git a/tools/lib/subcmd/Makefile b/tools/lib/subcmd/Makefile index 5b2cd5e58df0..5dbb0dde208c 100644 --- a/tools/lib/subcmd/Makefile +++ b/tools/lib/subcmd/Makefile @@ -28,7 +28,9 @@ ifeq ($(DEBUG),0) endif endif -ifeq ($(CC_NO_CLANG), 0) +ifeq ($(DEBUG),1) + CFLAGS += -O0 +else ifeq ($(CC_NO_CLANG), 0) CFLAGS += -O3 else CFLAGS += -O6 diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile index 5315f3787f8d..ecf882308d8a 100644 --- a/tools/lib/traceevent/Makefile +++ b/tools/lib/traceevent/Makefile @@ -97,6 +97,7 @@ EVENT_PARSE_VERSION = $(EP_VERSION).$(EP_PATCHLEVEL).$(EP_EXTRAVERSION) LIB_TARGET = libtraceevent.a libtraceevent.so.$(EVENT_PARSE_VERSION) LIB_INSTALL = libtraceevent.a libtraceevent.so* +LIB_INSTALL := $(addprefix $(OUTPUT),$(LIB_INSTALL)) INCLUDES = -I. -I $(srctree)/tools/include $(CONFIG_INCLUDES) @@ -207,10 +208,11 @@ define do_install $(INSTALL) $(if $3,-m $3,) $1 '$(DESTDIR_SQ)$2' endef -PKG_CONFIG_FILE = libtraceevent.pc +PKG_CONFIG_SOURCE_FILE = libtraceevent.pc +PKG_CONFIG_FILE := $(addprefix $(OUTPUT),$(PKG_CONFIG_SOURCE_FILE)) define do_install_pkgconfig_file if [ -n "${pkgconfig_dir}" ]; then \ - cp -f ${PKG_CONFIG_FILE}.template ${PKG_CONFIG_FILE}; \ + cp -f ${PKG_CONFIG_SOURCE_FILE}.template ${PKG_CONFIG_FILE}; \ sed -i "s|INSTALL_PREFIX|${1}|g" ${PKG_CONFIG_FILE}; \ sed -i "s|LIB_VERSION|${EVENT_PARSE_VERSION}|g" ${PKG_CONFIG_FILE}; \ sed -i "s|LIB_DIR|${libdir}|g" ${PKG_CONFIG_FILE}; \ diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c index 552592d153fb..f3cbf86e51ac 100644 --- a/tools/lib/traceevent/parse-filter.c +++ b/tools/lib/traceevent/parse-filter.c @@ -1473,8 +1473,10 @@ static int copy_filter_type(struct tep_event_filter *filter, if (strcmp(str, "TRUE") == 0 || strcmp(str, "FALSE") == 0) { /* Add trivial event */ arg = allocate_arg(); - if (arg == NULL) + if (arg == NULL) { + free(str); return -1; + } arg->type = TEP_FILTER_ARG_BOOLEAN; if (strcmp(str, "TRUE") == 0) @@ -1483,8 +1485,11 @@ static int copy_filter_type(struct tep_event_filter *filter, arg->boolean.value = 0; filter_type = add_filter_type(filter, event->id); - if (filter_type == NULL) + if (filter_type == NULL) { + free(str); + free_arg(arg); return -1; + } filter_type->filter = arg; diff --git a/tools/memory-model/linux-kernel.cat b/tools/memory-model/linux-kernel.cat index ea2ff4b94074..2a9b4fe4a84e 100644 --- a/tools/memory-model/linux-kernel.cat +++ b/tools/memory-model/linux-kernel.cat @@ -197,7 +197,7 @@ empty (wr-incoh | rw-incoh | ww-incoh) as plain-coherence (* Actual races *) let ww-nonrace = ww-vis & ((Marked * W) | rw-xbstar) & ((W * Marked) | wr-vis) let ww-race = (pre-race & co) \ ww-nonrace -let wr-race = (pre-race & (co? ; rf)) \ wr-vis +let wr-race = (pre-race & (co? ; rf)) \ wr-vis \ rw-xbstar^-1 let rw-race = (pre-race & fr) \ rw-xbstar flag ~empty (ww-race | wr-race | rw-race) as data-race diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 044c9a3cb247..f53d3c515cdc 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -481,6 +481,7 @@ static const char *uaccess_safe_builtin[] = { "ubsan_type_mismatch_common", "__ubsan_handle_type_mismatch", "__ubsan_handle_type_mismatch_v1", + "__ubsan_handle_shift_out_of_bounds", /* misc */ "csum_partial_copy_generic", "__memcpy_mcsafe", diff --git a/tools/pci/pcitest.c b/tools/pci/pcitest.c index cb1e51fcc84e..32b7c6f9043d 100644 --- a/tools/pci/pcitest.c +++ b/tools/pci/pcitest.c @@ -129,6 +129,7 @@ static int run_test(struct pci_test *test) } fflush(stdout); + close(fd); return (ret < 0) ? ret : 1 - ret; /* return 0 if test succeeded */ } diff --git a/tools/perf/arch/arm64/util/sym-handling.c b/tools/perf/arch/arm64/util/sym-handling.c index 5df788985130..8dfa3e5229f1 100644 --- a/tools/perf/arch/arm64/util/sym-handling.c +++ b/tools/perf/arch/arm64/util/sym-handling.c @@ -6,9 +6,10 @@ #include "symbol.h" // for the elf__needs_adjust_symbols() prototype #include -#include #ifdef HAVE_LIBELF_SUPPORT +#include + bool elf__needs_adjust_symbols(GElf_Ehdr ehdr) { return ehdr.e_type == ET_EXEC || diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index c37a78677955..265682296836 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -575,8 +575,8 @@ static int64_t block_cycles_diff_cmp(struct hist_entry *left, if (!pairs_left && !pairs_right) return 0; - l = labs(left->diff.cycles); - r = labs(right->diff.cycles); + l = llabs(left->diff.cycles); + r = llabs(right->diff.cycles); return r - l; } diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index aae0e57c60fb..7accaf8ef689 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -399,6 +399,13 @@ static int report__setup_sample_type(struct report *rep) PERF_SAMPLE_BRANCH_ANY)) rep->nonany_branch_mode = true; +#ifndef HAVE_LIBUNWIND_SUPPORT + if (dwarf_callchain_users) { + ui__warning("Please install libunwind development packages " + "during the perf build.\n"); + } +#endif + return 0; } diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 67be8d31afab..3983d6ccd14d 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -448,7 +448,7 @@ static int perf_evsel__check_attr(struct evsel *evsel, "selected. Hence, no address to lookup the source line number.\n"); return -EINVAL; } - if (PRINT_FIELD(BRSTACKINSN) && + if (PRINT_FIELD(BRSTACKINSN) && !allow_user_set && !(perf_evlist__combined_branch_type(session->evlist) & PERF_SAMPLE_BRANCH_ANY)) { pr_err("Display of branch stack assembler requested, but non all-branch filter set\n" @@ -1084,7 +1084,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, insn++; } } - if (off != (unsigned)len) + if (off != end - start) printed += fprintf(fp, "\tmismatch of LBR data and executable\n"); } diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json index 0d1556fcdffe..99f4fc425564 100644 --- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json +++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json @@ -15,7 +15,7 @@ }, { "EventCode": "0x04", - "EventName": "uncore_hisi_ddrc.flux_wr", + "EventName": "uncore_hisi_ddrc.pre_cmd", "BriefDescription": "DDRC precharge commands", "PublicDescription": "DDRC precharge commands", "Unit": "hisi_sccl,ddrc", diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json index 68618152ea2c..89e070727e1b 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json @@ -4,7 +4,7 @@ "EventCode": "128", "EventName": "L1D_RO_EXCL_WRITES", "BriefDescription": "L1D Read-only Exclusive Writes", - "PublicDescription": "L1D_RO_EXCL_WRITES A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line" + "PublicDescription": "A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line" }, { "Unit": "CPU-M-CF", diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index e2837260ca4d..99e3fd04a5cb 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -758,6 +758,7 @@ static int process_mapfile(FILE *outfp, char *fpath) char *line, *p; int line_num; char *tblname; + int ret = 0; pr_info("%s: Processing mapfile %s\n", prog, fpath); @@ -769,6 +770,7 @@ static int process_mapfile(FILE *outfp, char *fpath) if (!mapfp) { pr_info("%s: Error %s opening %s\n", prog, strerror(errno), fpath); + free(line); return -1; } @@ -795,7 +797,8 @@ static int process_mapfile(FILE *outfp, char *fpath) /* TODO Deal with lines longer than 16K */ pr_info("%s: Mapfile %s: line %d too long, aborting\n", prog, fpath, line_num); - return -1; + ret = -1; + goto out; } line[strlen(line)-1] = '\0'; @@ -825,7 +828,9 @@ static int process_mapfile(FILE *outfp, char *fpath) out: print_mapping_table_suffix(outfp); - return 0; + fclose(mapfp); + free(line); + return ret; } /* @@ -1122,6 +1127,7 @@ int main(int argc, char *argv[]) goto empty_map; } else if (rc < 0) { /* Make build fail */ + fclose(eventsfp); free_arch_std_events(); return 1; } else if (rc) { @@ -1134,6 +1140,7 @@ int main(int argc, char *argv[]) goto empty_map; } else if (rc < 0) { /* Make build fail */ + fclose(eventsfp); free_arch_std_events(); return 1; } else if (rc) { @@ -1151,6 +1158,8 @@ int main(int argc, char *argv[]) if (process_mapfile(eventsfp, mapfile)) { pr_info("%s: Error processing mapfile %s\n", prog, mapfile); /* Make build fail */ + fclose(eventsfp); + free_arch_std_events(); return 1; } diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py index 61b3911d91e6..4b28c9d08d5a 100755 --- a/tools/perf/scripts/python/exported-sql-viewer.py +++ b/tools/perf/scripts/python/exported-sql-viewer.py @@ -625,7 +625,7 @@ def __init__(self, glb, params): self.query_done = True if_has_calls = "" if IsSelectable(glb.db, "comms", columns = "has_calls"): - if_has_calls = " WHERE has_calls = TRUE" + if_has_calls = " WHERE has_calls = " + glb.dbref.TRUE query = QSqlQuery(glb.db) QueryExec(query, "SELECT id, comm FROM comms" + if_has_calls) while query.next(): @@ -905,7 +905,7 @@ def __init__(self, glb, params): self.query_done = True if_has_calls = "" if IsSelectable(glb.db, "comms", columns = "has_calls"): - if_has_calls = " WHERE has_calls = TRUE" + if_has_calls = " WHERE has_calls = " + glb.dbref.TRUE query = QSqlQuery(glb.db) QueryExec(query, "SELECT id, comm FROM comms" + if_has_calls) while query.next(): @@ -3509,6 +3509,12 @@ class DBRef(): def __init__(self, is_sqlite3, dbname): self.is_sqlite3 = is_sqlite3 self.dbname = dbname + self.TRUE = "TRUE" + self.FALSE = "FALSE" + # SQLite prior to version 3.23 does not support TRUE and FALSE + if self.is_sqlite3: + self.TRUE = "1" + self.FALSE = "0" def Open(self, connection_name): dbname = self.dbname diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c index 338cd9faa835..5128f727c0ef 100644 --- a/tools/perf/tests/backward-ring-buffer.c +++ b/tools/perf/tests/backward-ring-buffer.c @@ -147,6 +147,15 @@ int test__backward_ring_buffer(struct test *test __maybe_unused, int subtest __m goto out_delete_evlist; } + evlist__close(evlist); + + err = evlist__open(evlist); + if (err < 0) { + pr_debug("perf_evlist__open: %s\n", + str_error_r(errno, sbuf, sizeof(sbuf))); + goto out_delete_evlist; + } + err = do_test(evlist, 1, &sample_count, &comm_count); if (err != TEST_OK) goto out_delete_evlist; diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c index c1c2c13de254..166f411568a5 100644 --- a/tools/perf/tests/bp_signal.c +++ b/tools/perf/tests/bp_signal.c @@ -49,14 +49,6 @@ asm ( "__test_function:\n" "incq (%rdi)\n" "ret\n"); -#elif defined (__aarch64__) -extern void __test_function(volatile long *ptr); -asm ( - ".globl __test_function\n" - "__test_function:\n" - "str x30, [x0]\n" - "ret\n"); - #else static void __test_function(volatile long *ptr) { @@ -302,10 +294,15 @@ bool test__bp_signal_is_supported(void) * stepping into the SIGIO handler and getting stuck on the * breakpointed instruction. * + * Since arm64 has the same issue with arm for the single-step + * handling, this case also gets suck on the breakpointed + * instruction. + * * Just disable the test for these architectures until these * issues are resolved. */ -#if defined(__powerpc__) || defined(__s390x__) || defined(__arm__) +#if defined(__powerpc__) || defined(__s390x__) || defined(__arm__) || \ + defined(__aarch64__) return false; #else return true; diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c index bce3a4cb4c89..d85c9f608564 100644 --- a/tools/perf/tests/task-exit.c +++ b/tools/perf/tests/task-exit.c @@ -53,6 +53,7 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused struct perf_cpu_map *cpus; struct perf_thread_map *threads; struct mmap *md; + int retry_count = 0; signal(SIGCHLD, sig_handler); @@ -110,6 +111,7 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused if (evlist__mmap(evlist, 128) < 0) { pr_debug("failed to mmap events: %d (%s)\n", errno, str_error_r(errno, sbuf, sizeof(sbuf))); + err = -1; goto out_delete_evlist; } @@ -131,6 +133,13 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused out_init: if (!exited || !nr_exit) { evlist__poll(evlist, -1); + + if (retry_count++ > 1000) { + pr_debug("Failed after retrying 1000 times\n"); + err = -1; + goto out_free_maps; + } + goto retry; } diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 4ba0f871f086..f5f855fff412 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -110,7 +110,7 @@ static int cs_etm__decode_data_block(struct cs_etm_queue *etmq); * encode the etm queue number as the upper 16 bit and the channel as * the lower 16 bit. */ -#define TO_CS_QUEUE_NR(queue_nr, trace_id_chan) \ +#define TO_CS_QUEUE_NR(queue_nr, trace_chan_id) \ (queue_nr << 16 | trace_chan_id) #define TO_QUEUE_NR(cs_queue_nr) (cs_queue_nr >> 16) #define TO_TRACE_CHAN_ID(cs_queue_nr) (cs_queue_nr & 0x0000ffff) @@ -819,7 +819,7 @@ static int cs_etm__setup_queue(struct cs_etm_auxtrace *etm, * Note that packets decoded above are still in the traceID's packet * queue and will be processed in cs_etm__process_queues(). */ - cs_queue_nr = TO_CS_QUEUE_NR(queue_nr, trace_id_chan); + cs_queue_nr = TO_CS_QUEUE_NR(queue_nr, trace_chan_id); ret = auxtrace_heap__add(&etm->heap, cs_queue_nr, timestamp); out: return ret; diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index df6cee5c071f..5544bfbd0f6c 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -307,21 +307,51 @@ bool die_is_func_def(Dwarf_Die *dw_die) dwarf_attr(dw_die, DW_AT_declaration, &attr) == NULL); } +/** + * die_entrypc - Returns entry PC (the lowest address) of a DIE + * @dw_die: a DIE + * @addr: where to store entry PC + * + * Since dwarf_entrypc() does not return entry PC if the DIE has only address + * range, we have to use this to retrieve the lowest address from the address + * range attribute. + */ +int die_entrypc(Dwarf_Die *dw_die, Dwarf_Addr *addr) +{ + Dwarf_Addr base, end; + + if (!addr) + return -EINVAL; + + if (dwarf_entrypc(dw_die, addr) == 0) + return 0; + + return dwarf_ranges(dw_die, 0, &base, addr, &end) < 0 ? -ENOENT : 0; +} + /** * die_is_func_instance - Ensure that this DIE is an instance of a subprogram * @dw_die: a DIE * * Ensure that this DIE is an instance (which has an entry address). - * This returns true if @dw_die is a function instance. If not, you need to - * call die_walk_instances() to find actual instances. + * This returns true if @dw_die is a function instance. If not, the @dw_die + * must be a prototype. You can use die_walk_instances() to find actual + * instances. **/ bool die_is_func_instance(Dwarf_Die *dw_die) { Dwarf_Addr tmp; + Dwarf_Attribute attr_mem; + int tag = dwarf_tag(dw_die); - /* Actually gcc optimizes non-inline as like as inlined */ - return !dwarf_func_inline(dw_die) && dwarf_entrypc(dw_die, &tmp) == 0; + if (tag != DW_TAG_subprogram && + tag != DW_TAG_inlined_subroutine) + return false; + + return dwarf_entrypc(dw_die, &tmp) == 0 || + dwarf_attr(dw_die, DW_AT_ranges, &attr_mem) != NULL; } + /** * die_get_data_member_location - Get the data-member offset * @mb_die: a DIE of a member of a data structure @@ -598,6 +628,9 @@ static int __die_walk_instances_cb(Dwarf_Die *inst, void *data) Dwarf_Die *origin; int tmp; + if (!die_is_func_instance(inst)) + return DIE_FIND_CB_CONTINUE; + attr = dwarf_attr(inst, DW_AT_abstract_origin, &attr_mem); if (attr == NULL) return DIE_FIND_CB_CONTINUE; @@ -669,15 +702,14 @@ static int __die_walk_funclines_cb(Dwarf_Die *in_die, void *data) if (dwarf_tag(in_die) == DW_TAG_inlined_subroutine) { fname = die_get_call_file(in_die); lineno = die_get_call_lineno(in_die); - if (fname && lineno > 0 && dwarf_entrypc(in_die, &addr) == 0) { + if (fname && lineno > 0 && die_entrypc(in_die, &addr) == 0) { lw->retval = lw->callback(fname, lineno, addr, lw->data); if (lw->retval != 0) return DIE_FIND_CB_END; } + if (!lw->recursive) + return DIE_FIND_CB_SIBLING; } - if (!lw->recursive) - /* Don't need to search recursively */ - return DIE_FIND_CB_SIBLING; if (addr) { fname = dwarf_decl_file(in_die); @@ -710,7 +742,7 @@ static int __die_walk_funclines(Dwarf_Die *sp_die, bool recursive, /* Handle function declaration line */ fname = dwarf_decl_file(sp_die); if (fname && dwarf_decl_line(sp_die, &lineno) == 0 && - dwarf_entrypc(sp_die, &addr) == 0) { + die_entrypc(sp_die, &addr) == 0) { lw.retval = callback(fname, lineno, addr, data); if (lw.retval != 0) goto done; @@ -724,6 +756,10 @@ static int __die_walk_culines_cb(Dwarf_Die *sp_die, void *data) { struct __line_walk_param *lw = data; + /* + * Since inlined function can include another inlined function in + * the same file, we need to walk in it recursively. + */ lw->retval = __die_walk_funclines(sp_die, true, lw->callback, lw->data); if (lw->retval != 0) return DWARF_CB_ABORT; @@ -748,11 +784,12 @@ int die_walk_lines(Dwarf_Die *rt_die, line_walk_callback_t callback, void *data) Dwarf_Lines *lines; Dwarf_Line *line; Dwarf_Addr addr; - const char *fname, *decf = NULL; + const char *fname, *decf = NULL, *inf = NULL; int lineno, ret = 0; int decl = 0, inl; Dwarf_Die die_mem, *cu_die; size_t nlines, i; + bool flag; /* Get the CU die */ if (dwarf_tag(rt_die) != DW_TAG_compile_unit) { @@ -783,6 +820,12 @@ int die_walk_lines(Dwarf_Die *rt_die, line_walk_callback_t callback, void *data) "Possible error in debuginfo.\n"); continue; } + /* Skip end-of-sequence */ + if (dwarf_lineendsequence(line, &flag) != 0 || flag) + continue; + /* Skip Non statement line-info */ + if (dwarf_linebeginstatement(line, &flag) != 0 || !flag) + continue; /* Filter lines based on address */ if (rt_die != cu_die) { /* @@ -792,13 +835,21 @@ int die_walk_lines(Dwarf_Die *rt_die, line_walk_callback_t callback, void *data) */ if (!dwarf_haspc(rt_die, addr)) continue; + if (die_find_inlinefunc(rt_die, addr, &die_mem)) { + /* Call-site check */ + inf = die_get_call_file(&die_mem); + if ((inf && !strcmp(inf, decf)) && + die_get_call_lineno(&die_mem) == lineno) + goto found; + dwarf_decl_line(&die_mem, &inl); if (inl != decl || decf != dwarf_decl_file(&die_mem)) continue; } } +found: /* Get source line */ fname = dwarf_linesrc(line, NULL, NULL); @@ -813,8 +864,9 @@ int die_walk_lines(Dwarf_Die *rt_die, line_walk_callback_t callback, void *data) */ if (rt_die != cu_die) /* - * Don't need walk functions recursively, because nested - * inlined functions don't have lines of the specified DIE. + * Don't need walk inlined functions recursively, because + * inner inlined functions don't have the lines of the + * specified function. */ ret = __die_walk_funclines(rt_die, false, callback, data); else { @@ -989,7 +1041,7 @@ static int die_get_var_innermost_scope(Dwarf_Die *sp_die, Dwarf_Die *vr_die, bool first = true; const char *name; - ret = dwarf_entrypc(sp_die, &entry); + ret = die_entrypc(sp_die, &entry); if (ret) return ret; @@ -1052,7 +1104,7 @@ int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf) bool first = true; const char *name; - ret = dwarf_entrypc(sp_die, &entry); + ret = die_entrypc(sp_die, &entry); if (ret) return ret; diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h index f204e5892403..506006e0cf66 100644 --- a/tools/perf/util/dwarf-aux.h +++ b/tools/perf/util/dwarf-aux.h @@ -29,6 +29,9 @@ int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr, /* Get DW_AT_linkage_name (should be NULL for C binary) */ const char *die_get_linkage_name(Dwarf_Die *dw_die); +/* Get the lowest PC in DIE (including range list) */ +int die_entrypc(Dwarf_Die *dw_die, Dwarf_Addr *addr); + /* Ensure that this DIE is a subprogram and definition (not declaration) */ bool die_is_func_def(Dwarf_Die *dw_die); diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index becc2d109423..d3412f2c0d18 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1089,21 +1089,18 @@ static void cpu_cache_level__fprintf(FILE *out, struct cpu_cache_level *c) fprintf(out, "L%d %-15s %8s [%s]\n", c->level, c->type, c->size, c->map); } -static int build_caches(struct cpu_cache_level caches[], u32 size, u32 *cntp) +#define MAX_CACHE_LVL 4 + +static int build_caches(struct cpu_cache_level caches[], u32 *cntp) { u32 i, cnt = 0; - long ncpus; u32 nr, cpu; u16 level; - ncpus = sysconf(_SC_NPROCESSORS_CONF); - if (ncpus < 0) - return -1; - - nr = (u32)(ncpus & UINT_MAX); + nr = cpu__max_cpu(); for (cpu = 0; cpu < nr; cpu++) { - for (level = 0; level < 10; level++) { + for (level = 0; level < MAX_CACHE_LVL; level++) { struct cpu_cache_level c; int err; @@ -1123,18 +1120,12 @@ static int build_caches(struct cpu_cache_level caches[], u32 size, u32 *cntp) caches[cnt++] = c; else cpu_cache_level__free(&c); - - if (WARN_ONCE(cnt == size, "way too many cpu caches..")) - goto out; } } - out: *cntp = cnt; return 0; } -#define MAX_CACHE_LVL 4 - static int write_cache(struct feat_fd *ff, struct evlist *evlist __maybe_unused) { @@ -1143,7 +1134,7 @@ static int write_cache(struct feat_fd *ff, u32 cnt = 0, i, version = 1; int ret; - ret = build_caches(caches, max_caches, &cnt); + ret = build_caches(caches, &cnt); if (ret) goto out; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 70a9f8716a4b..888814df758d 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -2403,7 +2403,7 @@ static int thread__resolve_callchain_sample(struct thread *thread, } check_calls: - if (callchain_param.order != ORDER_CALLEE) { + if (chain && callchain_param.order != ORDER_CALLEE) { err = find_prev_cpumode(chain, thread, cursor, parent, root_al, &cpumode, chain->nr - first_call); if (err) diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index a7c0424dbda3..940a6e7a6854 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -103,8 +103,11 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist, if (!strcmp(ev->name, ids[i])) { if (!metric_events[i]) metric_events[i] = ev; + i++; + if (i == idnum) + break; } else { - if (++i == idnum) { + if (i + 1 == idnum) { /* Discard the whole match and start again */ i = 0; memset(metric_events, 0, @@ -124,7 +127,7 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist, } } - if (i != idnum - 1) { + if (i != idnum) { /* Not whole match */ return NULL; } diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index b5e2adef49de..422ad1888e74 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1365,8 +1365,15 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, if (get_config_terms(head_config, &config_terms)) return -ENOMEM; - if (perf_pmu__config(pmu, &attr, head_config, parse_state->error)) + if (perf_pmu__config(pmu, &attr, head_config, parse_state->error)) { + struct perf_evsel_config_term *pos, *tmp; + + list_for_each_entry_safe(pos, tmp, &config_terms, list) { + list_del_init(&pos->list); + free(pos); + } return -EINVAL; + } evsel = __add_event(list, &parse_state->idx, &attr, get_config_name(head_config), pmu, @@ -1927,15 +1934,20 @@ int parse_events(struct evlist *evlist, const char *str, ret = parse_events__scanner(str, &parse_state, PE_START_EVENTS); perf_pmu__parse_cleanup(); + + if (!ret && list_empty(&parse_state.list)) { + WARN_ONCE(true, "WARNING: event parser found nothing\n"); + return -1; + } + + /* + * Add list to the evlist even with errors to allow callers to clean up. + */ + perf_evlist__splice_list_tail(evlist, &parse_state.list); + if (!ret) { struct evsel *last; - if (list_empty(&parse_state.list)) { - WARN_ONCE(true, "WARNING: event parser found nothing\n"); - return -1; - } - - perf_evlist__splice_list_tail(evlist, &parse_state.list); evlist->nr_groups += parse_state.nr_groups; last = evlist__last(evlist); last->cmdline_group_boundary = true; diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h index 47fe34e5f7d5..ec7640cc4c91 100644 --- a/tools/perf/util/perf_regs.h +++ b/tools/perf/util/perf_regs.h @@ -41,7 +41,7 @@ int perf_reg_value(u64 *valp, struct regs_dump *regs, int id); static inline const char *perf_reg_name(int id __maybe_unused) { - return NULL; + return "unknown"; } static inline int perf_reg_value(u64 *valp __maybe_unused, diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index cd9f95e5044e..08cccd86447c 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -756,6 +756,16 @@ static int find_best_scope_cb(Dwarf_Die *fn_die, void *data) return 0; } +/* Return innermost DIE */ +static int find_inner_scope_cb(Dwarf_Die *fn_die, void *data) +{ + struct find_scope_param *fsp = data; + + memcpy(fsp->die_mem, fn_die, sizeof(Dwarf_Die)); + fsp->found = true; + return 1; +} + /* Find an appropriate scope fits to given conditions */ static Dwarf_Die *find_best_scope(struct probe_finder *pf, Dwarf_Die *die_mem) { @@ -767,8 +777,13 @@ static Dwarf_Die *find_best_scope(struct probe_finder *pf, Dwarf_Die *die_mem) .die_mem = die_mem, .found = false, }; + int ret; - cu_walk_functions_at(&pf->cu_die, pf->addr, find_best_scope_cb, &fsp); + ret = cu_walk_functions_at(&pf->cu_die, pf->addr, find_best_scope_cb, + &fsp); + if (!ret && !fsp.found) + cu_walk_functions_at(&pf->cu_die, pf->addr, + find_inner_scope_cb, &fsp); return fsp.found ? die_mem : NULL; } @@ -942,7 +957,7 @@ static int probe_point_inline_cb(Dwarf_Die *in_die, void *data) ret = find_probe_point_lazy(in_die, pf); else { /* Get probe address */ - if (dwarf_entrypc(in_die, &addr) != 0) { + if (die_entrypc(in_die, &addr) != 0) { pr_warning("Failed to get entry address of %s.\n", dwarf_diename(in_die)); return -ENOENT; @@ -994,7 +1009,7 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data) param->retval = find_probe_point_by_line(pf); } else if (die_is_func_instance(sp_die)) { /* Instances always have the entry address */ - dwarf_entrypc(sp_die, &pf->addr); + die_entrypc(sp_die, &pf->addr); /* But in some case the entry address is 0 */ if (pf->addr == 0) { pr_debug("%s has no entry PC. Skipped\n", @@ -1425,6 +1440,18 @@ static int collect_variables_cb(Dwarf_Die *die_mem, void *data) return DIE_FIND_CB_END; } +static bool available_var_finder_overlap(struct available_var_finder *af) +{ + int i; + + for (i = 0; i < af->nvls; i++) { + if (af->pf.addr == af->vls[i].point.address) + return true; + } + return false; + +} + /* Add a found vars into available variables list */ static int add_available_vars(Dwarf_Die *sc_die, struct probe_finder *pf) { @@ -1435,6 +1462,14 @@ static int add_available_vars(Dwarf_Die *sc_die, struct probe_finder *pf) Dwarf_Die die_mem; int ret; + /* + * For some reason (e.g. different column assigned to same address), + * this callback can be called with the address which already passed. + * Ignore it first. + */ + if (available_var_finder_overlap(af)) + return 0; + /* Check number of tevs */ if (af->nvls == af->max_vls) { pr_warning("Too many( > %d) probe point found.\n", af->max_vls); @@ -1578,7 +1613,7 @@ int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr, /* Get function entry information */ func = basefunc = dwarf_diename(&spdie); if (!func || - dwarf_entrypc(&spdie, &baseaddr) != 0 || + die_entrypc(&spdie, &baseaddr) != 0 || dwarf_decl_line(&spdie, &baseline) != 0) { lineno = 0; goto post; @@ -1595,7 +1630,7 @@ int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr, while (die_find_top_inlinefunc(&spdie, (Dwarf_Addr)addr, &indie)) { /* There is an inline function */ - if (dwarf_entrypc(&indie, &_addr) == 0 && + if (die_entrypc(&indie, &_addr) == 0 && _addr == addr) { /* * addr is at an inline function entry. diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 061bb4d6a3f5..5c172845fa5a 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1954,8 +1954,8 @@ static int __perf_session__process_pipe_events(struct perf_session *session) } static union perf_event * -fetch_mmaped_event(struct perf_session *session, - u64 head, size_t mmap_size, char *buf) +prefetch_event(char *buf, u64 head, size_t mmap_size, + bool needs_swap, union perf_event *error) { union perf_event *event; @@ -1967,20 +1967,32 @@ fetch_mmaped_event(struct perf_session *session, return NULL; event = (union perf_event *)(buf + head); + if (needs_swap) + perf_event_header__bswap(&event->header); - if (session->header.needs_swap) + if (head + event->header.size <= mmap_size) + return event; + + /* We're not fetching the event so swap back again */ + if (needs_swap) perf_event_header__bswap(&event->header); - if (head + event->header.size > mmap_size) { - /* We're not fetching the event so swap back again */ - if (session->header.needs_swap) - perf_event_header__bswap(&event->header); - pr_debug("%s: head=%#" PRIx64 " event->header_size=%#x, mmap_size=%#zx: fuzzed perf.data?\n", - __func__, head, event->header.size, mmap_size); - return ERR_PTR(-EINVAL); - } + pr_debug("%s: head=%#" PRIx64 " event->header_size=%#x, mmap_size=%#zx:" + " fuzzed or compressed perf.data?\n",__func__, head, event->header.size, mmap_size); - return event; + return error; +} + +static union perf_event * +fetch_mmaped_event(u64 head, size_t mmap_size, char *buf, bool needs_swap) +{ + return prefetch_event(buf, head, mmap_size, needs_swap, ERR_PTR(-EINVAL)); +} + +static union perf_event * +fetch_decomp_event(u64 head, size_t mmap_size, char *buf, bool needs_swap) +{ + return prefetch_event(buf, head, mmap_size, needs_swap, NULL); } static int __perf_session__process_decomp_events(struct perf_session *session) @@ -1993,10 +2005,8 @@ static int __perf_session__process_decomp_events(struct perf_session *session) return 0; while (decomp->head < decomp->size && !session_done()) { - union perf_event *event = fetch_mmaped_event(session, decomp->head, decomp->size, decomp->data); - - if (IS_ERR(event)) - return PTR_ERR(event); + union perf_event *event = fetch_decomp_event(decomp->head, decomp->size, decomp->data, + session->header.needs_swap); if (!event) break; @@ -2096,7 +2106,7 @@ reader__process_events(struct reader *rd, struct perf_session *session, } more: - event = fetch_mmaped_event(session, head, mmap_size, buf); + event = fetch_mmaped_event(head, mmap_size, buf, session->header.needs_swap); if (IS_ERR(event)) return PTR_ERR(event); diff --git a/tools/power/cpupower/utils/idle_monitor/hsw_ext_idle.c b/tools/power/cpupower/utils/idle_monitor/hsw_ext_idle.c index 7c7451d3f494..58dbdfd4fa13 100644 --- a/tools/power/cpupower/utils/idle_monitor/hsw_ext_idle.c +++ b/tools/power/cpupower/utils/idle_monitor/hsw_ext_idle.c @@ -39,7 +39,6 @@ static cstate_t hsw_ext_cstates[HSW_EXT_CSTATE_COUNT] = { { .name = "PC9", .desc = N_("Processor Package C9"), - .desc = N_("Processor Package C2"), .id = PC9, .range = RANGE_PACKAGE, .get_count_percent = hsw_ext_get_count_percent, diff --git a/tools/power/x86/intel-speed-select/isst-config.c b/tools/power/x86/intel-speed-select/isst-config.c index 2a9890c8395a..21fcfe621d3a 100644 --- a/tools/power/x86/intel-speed-select/isst-config.c +++ b/tools/power/x86/intel-speed-select/isst-config.c @@ -169,7 +169,7 @@ int get_topo_max_cpus(void) static void set_cpu_online_offline(int cpu, int state) { char buffer[128]; - int fd; + int fd, ret; snprintf(buffer, sizeof(buffer), "/sys/devices/system/cpu/cpu%d/online", cpu); @@ -179,9 +179,12 @@ static void set_cpu_online_offline(int cpu, int state) err(-1, "%s open failed", buffer); if (state) - write(fd, "1\n", 2); + ret = write(fd, "1\n", 2); else - write(fd, "0\n", 2); + ret = write(fd, "0\n", 2); + + if (ret == -1) + perror("Online/Offline: Operation failed\n"); close(fd); } diff --git a/tools/power/x86/intel-speed-select/isst-core.c b/tools/power/x86/intel-speed-select/isst-core.c index 6dee5332c9d3..fde3f9cefc6d 100644 --- a/tools/power/x86/intel-speed-select/isst-core.c +++ b/tools/power/x86/intel-speed-select/isst-core.c @@ -553,7 +553,6 @@ int isst_get_process_ctdp(int cpu, int tdp_level, struct isst_pkg_ctdp *pkg_dev) i); ctdp_level = &pkg_dev->ctdp_level[i]; - ctdp_level->processed = 1; ctdp_level->level = i; ctdp_level->control_cpu = cpu; ctdp_level->pkg_id = get_physical_package_id(cpu); @@ -561,7 +560,10 @@ int isst_get_process_ctdp(int cpu, int tdp_level, struct isst_pkg_ctdp *pkg_dev) ret = isst_get_ctdp_control(cpu, i, ctdp_level); if (ret) - return ret; + continue; + + pkg_dev->processed = 1; + ctdp_level->processed = 1; ret = isst_get_tdp_info(cpu, i, ctdp_level); if (ret) @@ -614,8 +616,6 @@ int isst_get_process_ctdp(int cpu, int tdp_level, struct isst_pkg_ctdp *pkg_dev) } } - pkg_dev->processed = 1; - return 0; } diff --git a/tools/power/x86/intel-speed-select/isst-display.c b/tools/power/x86/intel-speed-select/isst-display.c index 40346d534f78..b11575c3e886 100644 --- a/tools/power/x86/intel-speed-select/isst-display.c +++ b/tools/power/x86/intel-speed-select/isst-display.c @@ -314,7 +314,8 @@ void isst_ctdp_display_information(int cpu, FILE *outf, int tdp_level, char value[256]; int i, base_level = 1; - print_package_info(cpu, outf); + if (pkg_dev->processed) + print_package_info(cpu, outf); for (i = 0; i <= pkg_dev->levels; ++i) { struct isst_pkg_ctdp_level_info *ctdp_level; diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 4cdbae6f4e61..612f6757015d 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -213,7 +213,7 @@ ifdef INSTALL_PATH @# included in the generated runlist. for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ - [ ! -d $$INSTALL_PATH/$$TARGET ] && echo "Skipping non-existent dir: $$TARGET" && continue; \ + [ ! -d $(INSTALL_PATH)/$$TARGET ] && echo "Skipping non-existent dir: $$TARGET" && continue; \ echo "[ -w /dev/kmsg ] && echo \"kselftest: Running tests in $$TARGET\" >> /dev/kmsg" >> $(ALL_SCRIPT); \ echo "cd $$TARGET" >> $(ALL_SCRIPT); \ echo -n "run_many" >> $(ALL_SCRIPT); \ diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c index e95c33e333a4..b29a73fe64db 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.c +++ b/tools/testing/selftests/bpf/cgroup_helpers.c @@ -98,7 +98,7 @@ int enable_all_controllers(char *cgroup_path) */ int setup_cgroup_environment(void) { - char cgroup_workdir[PATH_MAX + 1]; + char cgroup_workdir[PATH_MAX - 24]; format_cgroup_path(cgroup_workdir, ""); diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c index 3a62119c7498..35c512818a56 100644 --- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c @@ -62,6 +62,10 @@ struct padded_a_lot { * long: 64; * long: 64; * int b; + * long: 32; + * long: 64; + * long: 64; + * long: 64; *}; * */ @@ -95,7 +99,6 @@ struct zone_padding { struct zone { int a; short b; - short: 16; struct zone_padding __pad__; }; diff --git a/tools/testing/selftests/bpf/progs/test_seg6_loop.c b/tools/testing/selftests/bpf/progs/test_seg6_loop.c index c4d104428643..69880c1e7700 100644 --- a/tools/testing/selftests/bpf/progs/test_seg6_loop.c +++ b/tools/testing/selftests/bpf/progs/test_seg6_loop.c @@ -132,8 +132,10 @@ static __always_inline int is_valid_tlv_boundary(struct __sk_buff *skb, *pad_off = 0; // we can only go as far as ~10 TLVs due to the BPF max stack size + // workaround: define induction variable "i" as "long" instead + // of "int" to prevent alu32 sub-register spilling. #pragma clang loop unroll(disable) - for (int i = 0; i < 100; i++) { + for (long i = 0; i < 100; i++) { struct sr6_tlv_t tlv; if (cur_off == *tlv_off) diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c b/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c index 608a06871572..d22e438198cf 100644 --- a/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c +++ b/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c @@ -44,7 +44,10 @@ int sysctl_tcp_mem(struct bpf_sysctl *ctx) unsigned long tcp_mem[TCP_MEM_LOOPS] = {}; char value[MAX_VALUE_STR_LEN]; unsigned char i, off = 0; - int ret; + /* a workaround to prevent compiler from generating + * codes verifier cannot handle yet. + */ + volatile int ret; if (ctx->write) return 0; diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index af75a1c7a458..3bf18364c67c 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -20,7 +20,7 @@ struct prog_test_def { bool tested; bool need_cgroup_cleanup; - const char *subtest_name; + char *subtest_name; int subtest_num; /* store counts before subtest started */ @@ -81,16 +81,17 @@ void test__end_subtest() fprintf(env.stdout, "#%d/%d %s:%s\n", test->test_num, test->subtest_num, test->subtest_name, sub_error_cnt ? "FAIL" : "OK"); + + free(test->subtest_name); + test->subtest_name = NULL; } bool test__start_subtest(const char *name) { struct prog_test_def *test = env.test; - if (test->subtest_name) { + if (test->subtest_name) test__end_subtest(); - test->subtest_name = NULL; - } test->subtest_num++; @@ -104,7 +105,13 @@ bool test__start_subtest(const char *name) if (!should_run(&env.subtest_selector, test->subtest_num, name)) return false; - test->subtest_name = name; + test->subtest_name = strdup(name); + if (!test->subtest_name) { + fprintf(env.stderr, + "Subtest #%d: failed to copy subtest name!\n", + test->subtest_num); + return false; + } env.test->old_error_cnt = env.test->error_cnt; return true; diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index 3845144e2c91..4a851513c842 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -240,14 +240,14 @@ static int sockmap_init_sockets(int verbose) addr.sin_port = htons(S1_PORT); err = bind(s1, (struct sockaddr *)&addr, sizeof(addr)); if (err < 0) { - perror("bind s1 failed()\n"); + perror("bind s1 failed()"); return errno; } addr.sin_port = htons(S2_PORT); err = bind(s2, (struct sockaddr *)&addr, sizeof(addr)); if (err < 0) { - perror("bind s2 failed()\n"); + perror("bind s2 failed()"); return errno; } @@ -255,14 +255,14 @@ static int sockmap_init_sockets(int verbose) addr.sin_port = htons(S1_PORT); err = listen(s1, 32); if (err < 0) { - perror("listen s1 failed()\n"); + perror("listen s1 failed()"); return errno; } addr.sin_port = htons(S2_PORT); err = listen(s2, 32); if (err < 0) { - perror("listen s1 failed()\n"); + perror("listen s1 failed()"); return errno; } @@ -270,14 +270,14 @@ static int sockmap_init_sockets(int verbose) addr.sin_port = htons(S1_PORT); err = connect(c1, (struct sockaddr *)&addr, sizeof(addr)); if (err < 0 && errno != EINPROGRESS) { - perror("connect c1 failed()\n"); + perror("connect c1 failed()"); return errno; } addr.sin_port = htons(S2_PORT); err = connect(c2, (struct sockaddr *)&addr, sizeof(addr)); if (err < 0 && errno != EINPROGRESS) { - perror("connect c2 failed()\n"); + perror("connect c2 failed()"); return errno; } else if (err < 0) { err = 0; @@ -286,13 +286,13 @@ static int sockmap_init_sockets(int verbose) /* Accept Connecrtions */ p1 = accept(s1, NULL, NULL); if (p1 < 0) { - perror("accept s1 failed()\n"); + perror("accept s1 failed()"); return errno; } p2 = accept(s2, NULL, NULL); if (p2 < 0) { - perror("accept s1 failed()\n"); + perror("accept s1 failed()"); return errno; } @@ -332,6 +332,10 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt, int i, fp; file = fopen(".sendpage_tst.tmp", "w+"); + if (!file) { + perror("create file for sendpage"); + return 1; + } for (i = 0; i < iov_length * cnt; i++, k++) fwrite(&k, sizeof(char), 1, file); fflush(file); @@ -339,12 +343,17 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt, fclose(file); fp = open(".sendpage_tst.tmp", O_RDONLY); + if (fp < 0) { + perror("reopen file for sendpage"); + return 1; + } + clock_gettime(CLOCK_MONOTONIC, &s->start); for (i = 0; i < cnt; i++) { int sent = sendfile(fd, fp, NULL, iov_length); if (!drop && sent < 0) { - perror("send loop error:"); + perror("send loop error"); close(fp); return sent; } else if (drop && sent >= 0) { @@ -463,7 +472,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt, int sent = sendmsg(fd, &msg, flags); if (!drop && sent < 0) { - perror("send loop error:"); + perror("send loop error"); goto out_errno; } else if (drop && sent >= 0) { printf("send loop error expected: %i\n", sent); @@ -499,7 +508,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt, total_bytes -= txmsg_pop_total; err = clock_gettime(CLOCK_MONOTONIC, &s->start); if (err < 0) - perror("recv start time: "); + perror("recv start time"); while (s->bytes_recvd < total_bytes) { if (txmsg_cork) { timeout.tv_sec = 0; @@ -543,7 +552,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt, if (recv < 0) { if (errno != EWOULDBLOCK) { clock_gettime(CLOCK_MONOTONIC, &s->end); - perror("recv failed()\n"); + perror("recv failed()"); goto out_errno; } } @@ -557,7 +566,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt, errno = msg_verify_data(&msg, recv, chunk_sz); if (errno) { - perror("data verify msg failed\n"); + perror("data verify msg failed"); goto out_errno; } if (recvp) { @@ -565,7 +574,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt, recvp, chunk_sz); if (errno) { - perror("data verify msg_peek failed\n"); + perror("data verify msg_peek failed"); goto out_errno; } } @@ -654,7 +663,7 @@ static int sendmsg_test(struct sockmap_options *opt) err = 0; exit(err ? 1 : 0); } else if (rxpid == -1) { - perror("msg_loop_rx: "); + perror("msg_loop_rx"); return errno; } @@ -681,7 +690,7 @@ static int sendmsg_test(struct sockmap_options *opt) s.bytes_recvd, recvd_Bps, recvd_Bps/giga); exit(err ? 1 : 0); } else if (txpid == -1) { - perror("msg_loop_tx: "); + perror("msg_loop_tx"); return errno; } @@ -715,7 +724,7 @@ static int forever_ping_pong(int rate, struct sockmap_options *opt) /* Ping/Pong data from client to server */ sc = send(c1, buf, sizeof(buf), 0); if (sc < 0) { - perror("send failed()\n"); + perror("send failed()"); return sc; } @@ -748,7 +757,7 @@ static int forever_ping_pong(int rate, struct sockmap_options *opt) rc = recv(i, buf, sizeof(buf), 0); if (rc < 0) { if (errno != EWOULDBLOCK) { - perror("recv failed()\n"); + perror("recv failed()"); return rc; } } @@ -760,7 +769,7 @@ static int forever_ping_pong(int rate, struct sockmap_options *opt) sc = send(i, buf, rc, 0); if (sc < 0) { - perror("send failed()\n"); + perror("send failed()"); return sc; } } diff --git a/tools/testing/selftests/bpf/test_tc_tunnel.sh b/tools/testing/selftests/bpf/test_tc_tunnel.sh index ff0d31d38061..7c76b841b17b 100755 --- a/tools/testing/selftests/bpf/test_tc_tunnel.sh +++ b/tools/testing/selftests/bpf/test_tc_tunnel.sh @@ -62,6 +62,10 @@ cleanup() { if [[ -f "${infile}" ]]; then rm "${infile}" fi + + if [[ -n $server_pid ]]; then + kill $server_pid 2> /dev/null + fi } server_listen() { @@ -77,6 +81,7 @@ client_connect() { verify_data() { wait "${server_pid}" + server_pid= # sha1sum returns two fields [sha1] [filepath] # convert to bash array and access first elem insum=($(sha1sum ${infile})) diff --git a/tools/testing/selftests/bpf/xdping.c b/tools/testing/selftests/bpf/xdping.c index d60a343b1371..842d9155d36c 100644 --- a/tools/testing/selftests/bpf/xdping.c +++ b/tools/testing/selftests/bpf/xdping.c @@ -45,7 +45,7 @@ static int get_stats(int fd, __u16 count, __u32 raddr) printf("\nXDP RTT data:\n"); if (bpf_map_lookup_elem(fd, &raddr, &pinginfo)) { - perror("bpf_map_lookup elem: "); + perror("bpf_map_lookup elem"); return 1; } diff --git a/tools/testing/selftests/firmware/fw_lib.sh b/tools/testing/selftests/firmware/fw_lib.sh index b879305a766d..5b8c0fedee76 100755 --- a/tools/testing/selftests/firmware/fw_lib.sh +++ b/tools/testing/selftests/firmware/fw_lib.sh @@ -34,6 +34,12 @@ test_modprobe() check_mods() { + local uid=$(id -u) + if [ $uid -ne 0 ]; then + echo "skip all tests: must be run as root" >&2 + exit $ksft_skip + fi + trap "test_modprobe" EXIT if [ ! -d $DIR ]; then modprobe test_firmware diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc index 36fb59f886ea..1a52f2883fe0 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc @@ -3,6 +3,8 @@ # description: ftrace - stacktrace filter command # flags: instance +[ ! -f set_ftrace_filter ] && exit_unsupported + echo _do_fork:stacktrace >> set_ftrace_filter grep -q "_do_fork:stacktrace:unlimited" set_ftrace_filter diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_cpumask.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_cpumask.tc index 86a1f07ef2ca..71fa3f49e35e 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func_cpumask.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_cpumask.tc @@ -15,6 +15,11 @@ if [ $NP -eq 1 ] ;then exit_unresolved fi +if ! grep -q "function" available_tracers ; then + echo "Function trace is not enabled" + exit_unsupported +fi + ORIG_CPUMASK=`cat tracing_cpumask` do_reset() { diff --git a/tools/testing/selftests/ftrace/test.d/functions b/tools/testing/selftests/ftrace/test.d/functions index 86986c4bba54..5d4550591ff9 100644 --- a/tools/testing/selftests/ftrace/test.d/functions +++ b/tools/testing/selftests/ftrace/test.d/functions @@ -46,6 +46,9 @@ reset_events_filter() { # reset all current setting filters } reset_ftrace_filter() { # reset all triggers in set_ftrace_filter + if [ ! -f set_ftrace_filter ]; then + return 0 + fi echo > set_ftrace_filter grep -v '^#' set_ftrace_filter | while read t; do tr=`echo $t | cut -d: -f2` @@ -93,7 +96,7 @@ initialize_ftrace() { # Reset ftrace to initial-state disable_events [ -f set_event_pid ] && echo > set_event_pid [ -f set_ftrace_pid ] && echo > set_ftrace_pid - [ -f set_ftrace_filter ] && echo | tee set_ftrace_* + [ -f set_ftrace_notrace ] && echo > set_ftrace_notrace [ -f set_graph_function ] && echo | tee set_graph_* [ -f stack_trace_filter ] && echo > stack_trace_filter [ -f kprobe_events ] && echo > kprobe_events diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc b/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc index 5862eee91e1d..6e3dbe5f96b7 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc @@ -20,9 +20,9 @@ while read i; do test $N -eq 256 && break done -L=`wc -l kprobe_events` -if [ $L -ne $N ]; then - echo "The number of kprobes events ($L) is not $N" +L=`cat kprobe_events | wc -l` +if [ $L -ne 256 ]; then + echo "The number of kprobes events ($L) is not 256" exit_fail fi diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-action-hist-xfail.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-action-hist-xfail.tc index 1221240f8cf6..3f2aee115f6e 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-action-hist-xfail.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-action-hist-xfail.tc @@ -21,10 +21,10 @@ grep -q "snapshot()" README || exit_unsupported # version issue echo "Test expected snapshot action failure" -echo 'hist:keys=comm:onmatch(sched.sched_wakeup).snapshot()' >> /sys/kernel/debug/tracing/events/sched/sched_waking/trigger && exit_fail +echo 'hist:keys=comm:onmatch(sched.sched_wakeup).snapshot()' >> events/sched/sched_waking/trigger && exit_fail echo "Test expected save action failure" -echo 'hist:keys=comm:onmatch(sched.sched_wakeup).save(comm,prio)' >> /sys/kernel/debug/tracing/events/sched/sched_waking/trigger && exit_fail +echo 'hist:keys=comm:onmatch(sched.sched_wakeup).save(comm,prio)' >> events/sched/sched_waking/trigger && exit_fail exit_xfail diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onchange-action-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onchange-action-hist.tc index 064a284e4e75..c80007aa9f86 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onchange-action-hist.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onchange-action-hist.tc @@ -16,7 +16,7 @@ grep -q "onchange(var)" README || exit_unsupported # version issue echo "Test onchange action" -echo 'hist:keys=comm:newprio=prio:onchange($newprio).save(comm,prio) if comm=="ping"' >> /sys/kernel/debug/tracing/events/sched/sched_waking/trigger +echo 'hist:keys=comm:newprio=prio:onchange($newprio).save(comm,prio) if comm=="ping"' >> events/sched/sched_waking/trigger ping $LOCALHOST -c 3 nice -n 1 ping $LOCALHOST -c 3 diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-snapshot-action-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-snapshot-action-hist.tc index 18fff69fc433..f546c1b66a9b 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-snapshot-action-hist.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-snapshot-action-hist.tc @@ -23,9 +23,9 @@ grep -q "snapshot()" README || exit_unsupported # version issue echo "Test snapshot action" -echo 1 > /sys/kernel/debug/tracing/events/sched/enable +echo 1 > events/sched/enable -echo 'hist:keys=comm:newprio=prio:onchange($newprio).save(comm,prio):onchange($newprio).snapshot() if comm=="ping"' >> /sys/kernel/debug/tracing/events/sched/sched_waking/trigger +echo 'hist:keys=comm:newprio=prio:onchange($newprio).save(comm,prio):onchange($newprio).snapshot() if comm=="ping"' >> events/sched/sched_waking/trigger ping $LOCALHOST -c 3 nice -n 1 ping $LOCALHOST -c 3 diff --git a/tools/testing/selftests/kselftest/prefix.pl b/tools/testing/selftests/kselftest/prefix.pl index ec7e48118183..31f7c2a0a8bd 100755 --- a/tools/testing/selftests/kselftest/prefix.pl +++ b/tools/testing/selftests/kselftest/prefix.pl @@ -3,6 +3,7 @@ # Prefix all lines with "# ", unbuffered. Command being piped in may need # to have unbuffering forced with "stdbuf -i0 -o0 -e0 $cmd". use strict; +use IO::Handle; binmode STDIN; binmode STDOUT; diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh index 84de7bc74f2c..a8d20cbb711c 100644 --- a/tools/testing/selftests/kselftest/runner.sh +++ b/tools/testing/selftests/kselftest/runner.sh @@ -79,6 +79,7 @@ run_one() if [ $rc -eq $skip_rc ]; then \ echo "not ok $test_num $TEST_HDR_MSG # SKIP" elif [ $rc -eq $timeout_rc ]; then \ + echo "#" echo "not ok $test_num $TEST_HDR_MSG # TIMEOUT" else echo "not ok $test_num $TEST_HDR_MSG # exit=$rc" diff --git a/tools/testing/selftests/net/forwarding/loopback.sh b/tools/testing/selftests/net/forwarding/loopback.sh index 6e4626ae71b0..8f4057310b5b 100755 --- a/tools/testing/selftests/net/forwarding/loopback.sh +++ b/tools/testing/selftests/net/forwarding/loopback.sh @@ -1,6 +1,9 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + ALL_TESTS="loopback_test" NUM_NETIFS=2 source tc_common.sh @@ -72,6 +75,11 @@ setup_prepare() h1_create h2_create + + if ethtool -k $h1 | grep loopback | grep -q fixed; then + log_test "SKIP: dev $h1 does not support loopback feature" + exit $ksft_skip + fi } cleanup() diff --git a/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh b/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh index fef88eb4b873..fa6a88c50750 100755 --- a/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh +++ b/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh @@ -36,7 +36,7 @@ h2_destroy() { ip -6 route del 2001:db8:1::/64 vrf v$h2 ip -4 route del 192.0.2.0/28 vrf v$h2 - simple_if_fini $h2 192.0.2.130/28 + simple_if_fini $h2 192.0.2.130/28 2001:db8:2::2/64 } router_create() diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index ab367e75f095..71a62e7e35b1 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -11,9 +11,9 @@ # R1 and R2 (also implemented with namespaces), with different MTUs: # # segment a_r1 segment b_r1 a_r1: 2000 -# .--------------R1--------------. a_r2: 1500 -# A B a_r3: 2000 -# '--------------R2--------------' a_r4: 1400 +# .--------------R1--------------. b_r1: 1400 +# A B a_r2: 2000 +# '--------------R2--------------' b_r2: 1500 # segment a_r2 segment b_r2 # # Check that PMTU exceptions with the correct PMTU are created. Then @@ -1249,8 +1249,7 @@ test_list_flush_ipv4_exception() { done run_cmd ${ns_a} ping -q -M want -i 0.1 -c 2 -s 1800 "${dst2}" - # Each exception is printed as two lines - if [ "$(${ns_a} ip route list cache | wc -l)" -ne 202 ]; then + if [ "$(${ns_a} ip -oneline route list cache | wc -l)" -ne 101 ]; then err " can't list cached exceptions" fail=1 fi @@ -1300,7 +1299,7 @@ test_list_flush_ipv6_exception() { run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s 1800 "${dst_prefix1}${i}" done run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s 1800 "${dst2}" - if [ "$(${ns_a} ip -6 route list cache | wc -l)" -ne 101 ]; then + if [ "$(${ns_a} ip -oneline -6 route list cache | wc -l)" -ne 101 ]; then err " can't list cached exceptions" fail=1 fi diff --git a/tools/testing/selftests/net/so_txtime.c b/tools/testing/selftests/net/so_txtime.c index 53f598f06647..34df4c8882af 100644 --- a/tools/testing/selftests/net/so_txtime.c +++ b/tools/testing/selftests/net/so_txtime.c @@ -105,8 +105,8 @@ static void do_recv_one(int fdr, struct timed_send *ts) tstop = (gettime_ns() - glob_tstart) / 1000; texpect = ts->delay_us >= 0 ? ts->delay_us : 0; - fprintf(stderr, "payload:%c delay:%ld expected:%ld (us)\n", - rbuf[0], tstop, texpect); + fprintf(stderr, "payload:%c delay:%lld expected:%lld (us)\n", + rbuf[0], (long long)tstop, (long long)texpect); if (rbuf[0] != ts->data) error(1, 0, "payload mismatch. expected %c", ts->data); diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 1c8f194d6556..0ea44d975b6c 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -25,10 +25,6 @@ #define TLS_PAYLOAD_MAX_LEN 16384 #define SOL_TLS 282 -#ifndef ENOTSUPP -#define ENOTSUPP 524 -#endif - FIXTURE(tls_basic) { int fd, cfd; @@ -268,6 +264,38 @@ TEST_F(tls, sendmsg_single) EXPECT_EQ(memcmp(buf, test_str, send_len), 0); } +#define MAX_FRAGS 64 +#define SEND_LEN 13 +TEST_F(tls, sendmsg_fragmented) +{ + char const *test_str = "test_sendmsg"; + char buf[SEND_LEN * MAX_FRAGS]; + struct iovec vec[MAX_FRAGS]; + struct msghdr msg; + int i, frags; + + for (frags = 1; frags <= MAX_FRAGS; frags++) { + for (i = 0; i < frags; i++) { + vec[i].iov_base = (char *)test_str; + vec[i].iov_len = SEND_LEN; + } + + memset(&msg, 0, sizeof(struct msghdr)); + msg.msg_iov = vec; + msg.msg_iovlen = frags; + + EXPECT_EQ(sendmsg(self->fd, &msg, 0), SEND_LEN * frags); + EXPECT_EQ(recv(self->cfd, buf, SEND_LEN * frags, MSG_WAITALL), + SEND_LEN * frags); + + for (i = 0; i < frags; i++) + EXPECT_EQ(memcmp(buf + SEND_LEN * i, + test_str, SEND_LEN), 0); + } +} +#undef MAX_FRAGS +#undef SEND_LEN + TEST_F(tls, sendmsg_large) { void *mem = malloc(16384); @@ -1145,11 +1173,11 @@ TEST(non_established) { /* TLS ULP not supported */ if (errno == ENOENT) return; - EXPECT_EQ(errno, ENOTSUPP); + EXPECT_EQ(errno, ENOTCONN); ret = setsockopt(sfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); EXPECT_EQ(ret, -1); - EXPECT_EQ(errno, ENOTSUPP); + EXPECT_EQ(errno, ENOTCONN); ret = getsockname(sfd, &addr, &len); ASSERT_EQ(ret, 0); diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c index 614b31aad168..c66da6ffd6d8 100644 --- a/tools/testing/selftests/net/udpgso.c +++ b/tools/testing/selftests/net/udpgso.c @@ -440,7 +440,8 @@ static bool __send_one(int fd, struct msghdr *msg, int flags) if (ret == -1) error(1, errno, "sendmsg"); if (ret != msg->msg_iov->iov_len) - error(1, 0, "sendto: %d != %lu", ret, msg->msg_iov->iov_len); + error(1, 0, "sendto: %d != %llu", ret, + (unsigned long long)msg->msg_iov->iov_len); if (msg->msg_flags) error(1, 0, "sendmsg: return flags 0x%x\n", msg->msg_flags); diff --git a/tools/testing/selftests/net/udpgso_bench_tx.c b/tools/testing/selftests/net/udpgso_bench_tx.c index ada99496634a..17512a43885e 100644 --- a/tools/testing/selftests/net/udpgso_bench_tx.c +++ b/tools/testing/selftests/net/udpgso_bench_tx.c @@ -405,7 +405,8 @@ static int send_udp_segment(int fd, char *data) if (ret == -1) error(1, errno, "sendmsg"); if (ret != iov.iov_len) - error(1, 0, "sendmsg: %u != %lu\n", ret, iov.iov_len); + error(1, 0, "sendmsg: %u != %llu\n", ret, + (unsigned long long)iov.iov_len); return 1; } diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh index 1be55e705780..d7e07f4c3d7f 100755 --- a/tools/testing/selftests/netfilter/nft_nat.sh +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -8,9 +8,14 @@ ksft_skip=4 ret=0 test_inet_nat=true +sfx=$(mktemp -u "XXXXXXXX") +ns0="ns0-$sfx" +ns1="ns1-$sfx" +ns2="ns2-$sfx" + cleanup() { - for i in 0 1 2; do ip netns del ns$i;done + for i in 0 1 2; do ip netns del ns$i-"$sfx";done } nft --version > /dev/null 2>&1 @@ -25,40 +30,49 @@ if [ $? -ne 0 ];then exit $ksft_skip fi -ip netns add ns0 +ip netns add "$ns0" if [ $? -ne 0 ];then - echo "SKIP: Could not create net namespace" + echo "SKIP: Could not create net namespace $ns0" exit $ksft_skip fi trap cleanup EXIT -ip netns add ns1 -ip netns add ns2 +ip netns add "$ns1" +if [ $? -ne 0 ];then + echo "SKIP: Could not create net namespace $ns1" + exit $ksft_skip +fi + +ip netns add "$ns2" +if [ $? -ne 0 ];then + echo "SKIP: Could not create net namespace $ns2" + exit $ksft_skip +fi -ip link add veth0 netns ns0 type veth peer name eth0 netns ns1 > /dev/null 2>&1 +ip link add veth0 netns "$ns0" type veth peer name eth0 netns "$ns1" > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: No virtual ethernet pair device support in kernel" exit $ksft_skip fi -ip link add veth1 netns ns0 type veth peer name eth0 netns ns2 +ip link add veth1 netns "$ns0" type veth peer name eth0 netns "$ns2" -ip -net ns0 link set lo up -ip -net ns0 link set veth0 up -ip -net ns0 addr add 10.0.1.1/24 dev veth0 -ip -net ns0 addr add dead:1::1/64 dev veth0 +ip -net "$ns0" link set lo up +ip -net "$ns0" link set veth0 up +ip -net "$ns0" addr add 10.0.1.1/24 dev veth0 +ip -net "$ns0" addr add dead:1::1/64 dev veth0 -ip -net ns0 link set veth1 up -ip -net ns0 addr add 10.0.2.1/24 dev veth1 -ip -net ns0 addr add dead:2::1/64 dev veth1 +ip -net "$ns0" link set veth1 up +ip -net "$ns0" addr add 10.0.2.1/24 dev veth1 +ip -net "$ns0" addr add dead:2::1/64 dev veth1 for i in 1 2; do - ip -net ns$i link set lo up - ip -net ns$i link set eth0 up - ip -net ns$i addr add 10.0.$i.99/24 dev eth0 - ip -net ns$i route add default via 10.0.$i.1 - ip -net ns$i addr add dead:$i::99/64 dev eth0 - ip -net ns$i route add default via dead:$i::1 + ip -net ns$i-$sfx link set lo up + ip -net ns$i-$sfx link set eth0 up + ip -net ns$i-$sfx addr add 10.0.$i.99/24 dev eth0 + ip -net ns$i-$sfx route add default via 10.0.$i.1 + ip -net ns$i-$sfx addr add dead:$i::99/64 dev eth0 + ip -net ns$i-$sfx route add default via dead:$i::1 done bad_counter() @@ -66,8 +80,9 @@ bad_counter() local ns=$1 local counter=$2 local expect=$3 + local tag=$4 - echo "ERROR: $counter counter in $ns has unexpected value (expected $expect)" 1>&2 + echo "ERROR: $counter counter in $ns has unexpected value (expected $expect) at $tag" 1>&2 ip netns exec $ns nft list counter inet filter $counter 1>&2 } @@ -78,24 +93,24 @@ check_counters() cnt=$(ip netns exec $ns nft list counter inet filter ns0in | grep -q "packets 1 bytes 84") if [ $? -ne 0 ]; then - bad_counter $ns ns0in "packets 1 bytes 84" + bad_counter $ns ns0in "packets 1 bytes 84" "check_counters 1" lret=1 fi cnt=$(ip netns exec $ns nft list counter inet filter ns0out | grep -q "packets 1 bytes 84") if [ $? -ne 0 ]; then - bad_counter $ns ns0out "packets 1 bytes 84" + bad_counter $ns ns0out "packets 1 bytes 84" "check_counters 2" lret=1 fi expect="packets 1 bytes 104" cnt=$(ip netns exec $ns nft list counter inet filter ns0in6 | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter $ns ns0in6 "$expect" + bad_counter $ns ns0in6 "$expect" "check_counters 3" lret=1 fi cnt=$(ip netns exec $ns nft list counter inet filter ns0out6 | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter $ns ns0out6 "$expect" + bad_counter $ns ns0out6 "$expect" "check_counters 4" lret=1 fi @@ -107,41 +122,41 @@ check_ns0_counters() local ns=$1 local lret=0 - cnt=$(ip netns exec ns0 nft list counter inet filter ns0in | grep -q "packets 0 bytes 0") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns0in | grep -q "packets 0 bytes 0") if [ $? -ne 0 ]; then - bad_counter ns0 ns0in "packets 0 bytes 0" + bad_counter "$ns0" ns0in "packets 0 bytes 0" "check_ns0_counters 1" lret=1 fi - cnt=$(ip netns exec ns0 nft list counter inet filter ns0in6 | grep -q "packets 0 bytes 0") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns0in6 | grep -q "packets 0 bytes 0") if [ $? -ne 0 ]; then - bad_counter ns0 ns0in6 "packets 0 bytes 0" + bad_counter "$ns0" ns0in6 "packets 0 bytes 0" lret=1 fi - cnt=$(ip netns exec ns0 nft list counter inet filter ns0out | grep -q "packets 0 bytes 0") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns0out | grep -q "packets 0 bytes 0") if [ $? -ne 0 ]; then - bad_counter ns0 ns0out "packets 0 bytes 0" + bad_counter "$ns0" ns0out "packets 0 bytes 0" "check_ns0_counters 2" lret=1 fi - cnt=$(ip netns exec ns0 nft list counter inet filter ns0out6 | grep -q "packets 0 bytes 0") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns0out6 | grep -q "packets 0 bytes 0") if [ $? -ne 0 ]; then - bad_counter ns0 ns0out6 "packets 0 bytes 0" + bad_counter "$ns0" ns0out6 "packets 0 bytes 0" "check_ns0_counters3 " lret=1 fi for dir in "in" "out" ; do expect="packets 1 bytes 84" - cnt=$(ip netns exec ns0 nft list counter inet filter ${ns}${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ${ns}${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns0 $ns$dir "$expect" + bad_counter "$ns0" $ns$dir "$expect" "check_ns0_counters 4" lret=1 fi expect="packets 1 bytes 104" - cnt=$(ip netns exec ns0 nft list counter inet filter ${ns}${dir}6 | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ${ns}${dir}6 | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns0 $ns$dir6 "$expect" + bad_counter "$ns0" $ns$dir6 "$expect" "check_ns0_counters 5" lret=1 fi done @@ -152,7 +167,7 @@ check_ns0_counters() reset_counters() { for i in 0 1 2;do - ip netns exec ns$i nft reset counters inet > /dev/null + ip netns exec ns$i-$sfx nft reset counters inet > /dev/null done } @@ -166,7 +181,7 @@ test_local_dnat6() IPF="ip6" fi -ip netns exec ns0 nft -f - < /dev/null + ip netns exec "$ns0" ping -q -c 1 dead:1::99 > /dev/null if [ $? -ne 0 ]; then lret=1 echo "ERROR: ping6 failed" @@ -189,18 +204,18 @@ EOF expect="packets 0 bytes 0" for dir in "in6" "out6" ; do - cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns0 ns1$dir "$expect" + bad_counter "$ns0" ns1$dir "$expect" "test_local_dnat6 1" lret=1 fi done expect="packets 1 bytes 104" for dir in "in6" "out6" ; do - cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns0 ns2$dir "$expect" + bad_counter "$ns0" ns2$dir "$expect" "test_local_dnat6 2" lret=1 fi done @@ -208,9 +223,9 @@ EOF # expect 0 count in ns1 expect="packets 0 bytes 0" for dir in "in6" "out6" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns0$dir "$expect" + bad_counter "$ns1" ns0$dir "$expect" "test_local_dnat6 3" lret=1 fi done @@ -218,15 +233,15 @@ EOF # expect 1 packet in ns2 expect="packets 1 bytes 104" for dir in "in6" "out6" ; do - cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns2" nft list counter inet filter ns0${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns0$dir "$expect" + bad_counter "$ns2" ns0$dir "$expect" "test_local_dnat6 4" lret=1 fi done - test $lret -eq 0 && echo "PASS: ipv6 ping to ns1 was $family NATted to ns2" - ip netns exec ns0 nft flush chain ip6 nat output + test $lret -eq 0 && echo "PASS: ipv6 ping to $ns1 was $family NATted to $ns2" + ip netns exec "$ns0" nft flush chain ip6 nat output return $lret } @@ -241,7 +256,7 @@ test_local_dnat() IPF="ip" fi -ip netns exec ns0 nft -f - </dev/null +ip netns exec "$ns0" nft -f /dev/stdin </dev/null table $family nat { chain output { type nat hook output priority 0; policy accept; @@ -260,7 +275,7 @@ EOF fi # ping netns1, expect rewrite to netns2 - ip netns exec ns0 ping -q -c 1 10.0.1.99 > /dev/null + ip netns exec "$ns0" ping -q -c 1 10.0.1.99 > /dev/null if [ $? -ne 0 ]; then lret=1 echo "ERROR: ping failed" @@ -269,18 +284,18 @@ EOF expect="packets 0 bytes 0" for dir in "in" "out" ; do - cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns0 ns1$dir "$expect" + bad_counter "$ns0" ns1$dir "$expect" "test_local_dnat 1" lret=1 fi done expect="packets 1 bytes 84" for dir in "in" "out" ; do - cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns0 ns2$dir "$expect" + bad_counter "$ns0" ns2$dir "$expect" "test_local_dnat 2" lret=1 fi done @@ -288,9 +303,9 @@ EOF # expect 0 count in ns1 expect="packets 0 bytes 0" for dir in "in" "out" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns0$dir "$expect" + bad_counter "$ns1" ns0$dir "$expect" "test_local_dnat 3" lret=1 fi done @@ -298,19 +313,19 @@ EOF # expect 1 packet in ns2 expect="packets 1 bytes 84" for dir in "in" "out" ; do - cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns2" nft list counter inet filter ns0${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns0$dir "$expect" + bad_counter "$ns2" ns0$dir "$expect" "test_local_dnat 4" lret=1 fi done - test $lret -eq 0 && echo "PASS: ping to ns1 was $family NATted to ns2" + test $lret -eq 0 && echo "PASS: ping to $ns1 was $family NATted to $ns2" - ip netns exec ns0 nft flush chain $family nat output + ip netns exec "$ns0" nft flush chain $family nat output reset_counters - ip netns exec ns0 ping -q -c 1 10.0.1.99 > /dev/null + ip netns exec "$ns0" ping -q -c 1 10.0.1.99 > /dev/null if [ $? -ne 0 ]; then lret=1 echo "ERROR: ping failed" @@ -319,17 +334,17 @@ EOF expect="packets 1 bytes 84" for dir in "in" "out" ; do - cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns1$dir "$expect" + bad_counter "$ns1" ns1$dir "$expect" "test_local_dnat 5" lret=1 fi done expect="packets 0 bytes 0" for dir in "in" "out" ; do - cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns0 ns2$dir "$expect" + bad_counter "$ns0" ns2$dir "$expect" "test_local_dnat 6" lret=1 fi done @@ -337,9 +352,9 @@ EOF # expect 1 count in ns1 expect="packets 1 bytes 84" for dir in "in" "out" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns0 ns0$dir "$expect" + bad_counter "$ns0" ns0$dir "$expect" "test_local_dnat 7" lret=1 fi done @@ -347,14 +362,14 @@ EOF # expect 0 packet in ns2 expect="packets 0 bytes 0" for dir in "in" "out" ; do - cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns2" nft list counter inet filter ns0${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns2$dir "$expect" + bad_counter "$ns2" ns0$dir "$expect" "test_local_dnat 8" lret=1 fi done - test $lret -eq 0 && echo "PASS: ping to ns1 OK after $family nat output chain flush" + test $lret -eq 0 && echo "PASS: ping to $ns1 OK after $family nat output chain flush" return $lret } @@ -366,26 +381,26 @@ test_masquerade6() local natflags=$2 local lret=0 - ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null + ip netns exec "$ns0" sysctl net.ipv6.conf.all.forwarding=1 > /dev/null - ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 + ip netns exec "$ns2" ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 via ipv6" + echo "ERROR: cannot ping $ns1 from $ns2 via ipv6" return 1 lret=1 fi expect="packets 1 bytes 104" for dir in "in6" "out6" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns2$dir "$expect" + bad_counter "$ns1" ns2$dir "$expect" "test_masquerade6 1" lret=1 fi - cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns1$dir "$expect" + bad_counter "$ns2" ns1$dir "$expect" "test_masquerade6 2" lret=1 fi done @@ -393,7 +408,7 @@ test_masquerade6() reset_counters # add masquerading rule -ip netns exec ns0 nft -f - < /dev/null # ping ns2->ns1 + ip netns exec "$ns2" ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 with active $family masquerade $natflags" + echo "ERROR: cannot ping $ns1 from $ns2 with active $family masquerade $natflags" lret=1 fi # ns1 should have seen packets from ns0, due to masquerade expect="packets 1 bytes 104" for dir in "in6" "out6" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns0$dir "$expect" + bad_counter "$ns1" ns0$dir "$expect" "test_masquerade6 3" lret=1 fi - cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns1$dir "$expect" + bad_counter "$ns2" ns1$dir "$expect" "test_masquerade6 4" lret=1 fi done @@ -431,32 +446,32 @@ EOF # ns1 should not have seen packets from ns2, due to masquerade expect="packets 0 bytes 0" for dir in "in6" "out6" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns0$dir "$expect" + bad_counter "$ns1" ns0$dir "$expect" "test_masquerade6 5" lret=1 fi - cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns1$dir "$expect" + bad_counter "$ns0" ns1$dir "$expect" "test_masquerade6 6" lret=1 fi done - ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 + ip netns exec "$ns2" ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerade $natflags (attempt 2)" + echo "ERROR: cannot ping $ns1 from $ns2 with active ipv6 masquerade $natflags (attempt 2)" lret=1 fi - ip netns exec ns0 nft flush chain $family nat postrouting + ip netns exec "$ns0" nft flush chain $family nat postrouting if [ $? -ne 0 ]; then echo "ERROR: Could not flush $family nat postrouting" 1>&2 lret=1 fi - test $lret -eq 0 && echo "PASS: $family IPv6 masquerade $natflags for ns2" + test $lret -eq 0 && echo "PASS: $family IPv6 masquerade $natflags for $ns2" return $lret } @@ -467,26 +482,26 @@ test_masquerade() local natflags=$2 local lret=0 - ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null - ip netns exec ns0 sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null + ip netns exec "$ns0" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null + ip netns exec "$ns0" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null - ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 $natflags" + echo "ERROR: cannot ping $ns1 from "$ns2" $natflags" lret=1 fi expect="packets 1 bytes 84" for dir in "in" "out" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns2$dir "$expect" + bad_counter "$ns1" ns2$dir "$expect" "test_masquerade 1" lret=1 fi - cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns1$dir "$expect" + bad_counter "$ns2" ns1$dir "$expect" "test_masquerade 2" lret=1 fi done @@ -494,7 +509,7 @@ test_masquerade() reset_counters # add masquerading rule -ip netns exec ns0 nft -f - < /dev/null # ping ns2->ns1 + ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 with active $family masquerade $natflags" + echo "ERROR: cannot ping $ns1 from $ns2 with active $family masquerade $natflags" lret=1 fi # ns1 should have seen packets from ns0, due to masquerade expect="packets 1 bytes 84" for dir in "in" "out" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns0$dir "$expect" + bad_counter "$ns1" ns0$dir "$expect" "test_masquerade 3" lret=1 fi - cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns1$dir "$expect" + bad_counter "$ns2" ns1$dir "$expect" "test_masquerade 4" lret=1 fi done @@ -532,32 +547,32 @@ EOF # ns1 should not have seen packets from ns2, due to masquerade expect="packets 0 bytes 0" for dir in "in" "out" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns0$dir "$expect" + bad_counter "$ns1" ns0$dir "$expect" "test_masquerade 5" lret=1 fi - cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns1$dir "$expect" + bad_counter "$ns0" ns1$dir "$expect" "test_masquerade 6" lret=1 fi done - ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 with active ip masquerade $natflags (attempt 2)" + echo "ERROR: cannot ping $ns1 from $ns2 with active ip masquerade $natflags (attempt 2)" lret=1 fi - ip netns exec ns0 nft flush chain $family nat postrouting + ip netns exec "$ns0" nft flush chain $family nat postrouting if [ $? -ne 0 ]; then echo "ERROR: Could not flush $family nat postrouting" 1>&2 lret=1 fi - test $lret -eq 0 && echo "PASS: $family IP masquerade $natflags for ns2" + test $lret -eq 0 && echo "PASS: $family IP masquerade $natflags for $ns2" return $lret } @@ -567,25 +582,25 @@ test_redirect6() local family=$1 local lret=0 - ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null + ip netns exec "$ns0" sysctl net.ipv6.conf.all.forwarding=1 > /dev/null - ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 + ip netns exec "$ns2" ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannnot ping ns1 from ns2 via ipv6" + echo "ERROR: cannnot ping $ns1 from $ns2 via ipv6" lret=1 fi expect="packets 1 bytes 104" for dir in "in6" "out6" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns2$dir "$expect" + bad_counter "$ns1" ns2$dir "$expect" "test_redirect6 1" lret=1 fi - cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns1$dir "$expect" + bad_counter "$ns2" ns1$dir "$expect" "test_redirect6 2" lret=1 fi done @@ -593,7 +608,7 @@ test_redirect6() reset_counters # add redirect rule -ip netns exec ns0 nft -f - < /dev/null # ping ns2->ns1 + ip netns exec "$ns2" ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 via ipv6 with active $family redirect" + echo "ERROR: cannot ping $ns1 from $ns2 via ipv6 with active $family redirect" lret=1 fi # ns1 should have seen no packets from ns2, due to redirection expect="packets 0 bytes 0" for dir in "in6" "out6" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns0$dir "$expect" + bad_counter "$ns1" ns0$dir "$expect" "test_redirect6 3" lret=1 fi done @@ -625,20 +640,20 @@ EOF # ns0 should have seen packets from ns2, due to masquerade expect="packets 1 bytes 104" for dir in "in6" "out6" ; do - cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns0$dir "$expect" + bad_counter "$ns1" ns0$dir "$expect" "test_redirect6 4" lret=1 fi done - ip netns exec ns0 nft delete table $family nat + ip netns exec "$ns0" nft delete table $family nat if [ $? -ne 0 ]; then echo "ERROR: Could not delete $family nat table" 1>&2 lret=1 fi - test $lret -eq 0 && echo "PASS: $family IPv6 redirection for ns2" + test $lret -eq 0 && echo "PASS: $family IPv6 redirection for $ns2" return $lret } @@ -648,26 +663,26 @@ test_redirect() local family=$1 local lret=0 - ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null - ip netns exec ns0 sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null + ip netns exec "$ns0" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null + ip netns exec "$ns0" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null - ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2" + echo "ERROR: cannot ping $ns1 from $ns2" lret=1 fi expect="packets 1 bytes 84" for dir in "in" "out" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns2$dir "$expect" + bad_counter "$ns1" $ns2$dir "$expect" "test_redirect 1" lret=1 fi - cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns2 ns1$dir "$expect" + bad_counter "$ns2" ns1$dir "$expect" "test_redirect 2" lret=1 fi done @@ -675,7 +690,7 @@ test_redirect() reset_counters # add redirect rule -ip netns exec ns0 nft -f - < /dev/null # ping ns2->ns1 + ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 with active $family ip redirect" + echo "ERROR: cannot ping $ns1 from $ns2 with active $family ip redirect" lret=1 fi @@ -698,9 +713,9 @@ EOF expect="packets 0 bytes 0" for dir in "in" "out" ; do - cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns0$dir "$expect" + bad_counter "$ns1" ns0$dir "$expect" "test_redirect 3" lret=1 fi done @@ -708,28 +723,28 @@ EOF # ns0 should have seen packets from ns2, due to masquerade expect="packets 1 bytes 84" for dir in "in" "out" ; do - cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns2${dir} | grep -q "$expect") if [ $? -ne 0 ]; then - bad_counter ns1 ns0$dir "$expect" + bad_counter "$ns0" ns0$dir "$expect" "test_redirect 4" lret=1 fi done - ip netns exec ns0 nft delete table $family nat + ip netns exec "$ns0" nft delete table $family nat if [ $? -ne 0 ]; then echo "ERROR: Could not delete $family nat table" 1>&2 lret=1 fi - test $lret -eq 0 && echo "PASS: $family IP redirection for ns2" + test $lret -eq 0 && echo "PASS: $family IP redirection for $ns2" return $lret } -# ip netns exec ns0 ping -c 1 -q 10.0.$i.99 +# ip netns exec "$ns0" ping -c 1 -q 10.0.$i.99 for i in 0 1 2; do -ip netns exec ns$i nft -f - < /dev/null + ip netns exec "$ns0" ping -c 1 -q 10.0.$i.99 > /dev/null if [ $? -ne 0 ];then echo "ERROR: Could not reach other namespace(s)" 1>&2 ret=1 fi - ip netns exec ns0 ping -c 1 -q dead:$i::99 > /dev/null + ip netns exec "$ns0" ping -c 1 -q dead:$i::99 > /dev/null if [ $? -ne 0 ];then echo "ERROR: Could not reach other namespace(s) via ipv6" 1>&2 ret=1 fi - check_counters ns$i + check_counters ns$i-$sfx if [ $? -ne 0 ]; then ret=1 fi @@ -820,7 +835,7 @@ for i in 1 2; do done if [ $ret -eq 0 ];then - echo "PASS: netns routing/connectivity: ns0 can reach ns1 and ns2" + echo "PASS: netns routing/connectivity: $ns0 can reach $ns1 and $ns2" fi reset_counters @@ -846,4 +861,9 @@ reset_counters $test_inet_nat && test_redirect inet $test_inet_nat && test_redirect6 inet +if [ $ret -ne 0 ];then + echo -n "FAIL: " + nft --version +fi + exit $ret diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-tar.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-tar.c index 25e23e73c72e..2ecfa1158e2b 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-tar.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-tar.c @@ -73,7 +73,7 @@ void tm_spd_tar(void) [sprn_texasr]"i"(SPRN_TEXASR), [tar_1]"i"(TAR_1), [dscr_1]"i"(DSCR_1), [tar_2]"i"(TAR_2), [dscr_2]"i"(DSCR_2), [tar_3]"i"(TAR_3), [dscr_3]"i"(DSCR_3) - : "memory", "r0", "r1", "r3", "r4", "r5", "r6" + : "memory", "r0", "r3", "r4", "r5", "r6", "lr" ); /* TM failed, analyse */ diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-vsx.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-vsx.c index f603fe5a445b..6f7fb51f0809 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-vsx.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-vsx.c @@ -74,8 +74,8 @@ void tm_spd_vsx(void) "3: ;" : [res] "=r" (result), [texasr] "=r" (texasr) : [sprn_texasr] "i" (SPRN_TEXASR) - : "memory", "r0", "r1", "r3", "r4", - "r7", "r8", "r9", "r10", "r11" + : "memory", "r0", "r3", "r4", + "r7", "r8", "r9", "r10", "r11", "lr" ); if (result) { diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-tar.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-tar.c index e0d37f07bdeb..46ef378a15ec 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-tar.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-tar.c @@ -62,7 +62,7 @@ void tm_tar(void) [sprn_ppr]"i"(SPRN_PPR), [sprn_texasr]"i"(SPRN_TEXASR), [tar_1]"i"(TAR_1), [dscr_1]"i"(DSCR_1), [tar_2]"i"(TAR_2), [dscr_2]"i"(DSCR_2), [cptr1] "b" (&cptr[1]) - : "memory", "r0", "r1", "r3", "r4", "r5", "r6" + : "memory", "r0", "r3", "r4", "r5", "r6" ); /* TM failed, analyse */ diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-vsx.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-vsx.c index 8027457b97b7..70ca01234f79 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-vsx.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-vsx.c @@ -62,8 +62,8 @@ void tm_vsx(void) "3: ;" : [res] "=r" (result), [texasr] "=r" (texasr) : [sprn_texasr] "i" (SPRN_TEXASR), [cptr1] "b" (&cptr[1]) - : "memory", "r0", "r1", "r3", "r4", - "r7", "r8", "r9", "r10", "r11" + : "memory", "r0", "r3", "r4", + "r7", "r8", "r9", "r10", "r11", "lr" ); if (result) { diff --git a/tools/testing/selftests/powerpc/tm/tm-signal-sigreturn-nt.c b/tools/testing/selftests/powerpc/tm/tm-signal-sigreturn-nt.c index 56fbf9f6bbf3..07c388147b75 100644 --- a/tools/testing/selftests/powerpc/tm/tm-signal-sigreturn-nt.c +++ b/tools/testing/selftests/powerpc/tm/tm-signal-sigreturn-nt.c @@ -10,10 +10,12 @@ */ #define _GNU_SOURCE +#include #include #include #include "utils.h" +#include "tm.h" void trap_signal_handler(int signo, siginfo_t *si, void *uc) { @@ -29,6 +31,8 @@ int tm_signal_sigreturn_nt(void) { struct sigaction trap_sa; + SKIP_IF(!have_htm()); + trap_sa.sa_flags = SA_SIGINFO; trap_sa.sa_sigaction = trap_signal_handler; diff --git a/tools/testing/selftests/proc/proc-self-map-files-002.c b/tools/testing/selftests/proc/proc-self-map-files-002.c index 47b7473dedef..e6aa00a183bc 100644 --- a/tools/testing/selftests/proc/proc-self-map-files-002.c +++ b/tools/testing/selftests/proc/proc-self-map-files-002.c @@ -47,7 +47,11 @@ static void fail(const char *fmt, unsigned long a, unsigned long b) int main(void) { const int PAGE_SIZE = sysconf(_SC_PAGESIZE); - const unsigned long va_max = 1UL << 32; + /* + * va_max must be enough bigger than vm.mmap_min_addr, which is + * 64KB/32KB by default. (depends on CONFIG_LSM_MMAP_MIN_ADDR) + */ + const unsigned long va_max = 1UL << 20; unsigned long va; void *p; int fd; diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c index eec2663261f2..e8a657a5f48a 100644 --- a/tools/testing/selftests/rseq/param_test.c +++ b/tools/testing/selftests/rseq/param_test.c @@ -15,7 +15,7 @@ #include #include -static inline pid_t gettid(void) +static inline pid_t rseq_gettid(void) { return syscall(__NR_gettid); } @@ -373,11 +373,12 @@ void *test_percpu_spinlock_thread(void *arg) rseq_percpu_unlock(&data->lock, cpu); #ifndef BENCHMARK if (i != 0 && !(i % (reps / 10))) - printf_verbose("tid %d: count %lld\n", (int) gettid(), i); + printf_verbose("tid %d: count %lld\n", + (int) rseq_gettid(), i); #endif } printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n", - (int) gettid(), nr_abort, signals_delivered); + (int) rseq_gettid(), nr_abort, signals_delivered); if (!opt_disable_rseq && thread_data->reg && rseq_unregister_current_thread()) abort(); @@ -454,11 +455,12 @@ void *test_percpu_inc_thread(void *arg) } while (rseq_unlikely(ret)); #ifndef BENCHMARK if (i != 0 && !(i % (reps / 10))) - printf_verbose("tid %d: count %lld\n", (int) gettid(), i); + printf_verbose("tid %d: count %lld\n", + (int) rseq_gettid(), i); #endif } printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n", - (int) gettid(), nr_abort, signals_delivered); + (int) rseq_gettid(), nr_abort, signals_delivered); if (!opt_disable_rseq && thread_data->reg && rseq_unregister_current_thread()) abort(); @@ -605,7 +607,7 @@ void *test_percpu_list_thread(void *arg) } printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n", - (int) gettid(), nr_abort, signals_delivered); + (int) rseq_gettid(), nr_abort, signals_delivered); if (!opt_disable_rseq && rseq_unregister_current_thread()) abort(); @@ -796,7 +798,7 @@ void *test_percpu_buffer_thread(void *arg) } printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n", - (int) gettid(), nr_abort, signals_delivered); + (int) rseq_gettid(), nr_abort, signals_delivered); if (!opt_disable_rseq && rseq_unregister_current_thread()) abort(); @@ -1011,7 +1013,7 @@ void *test_percpu_memcpy_buffer_thread(void *arg) } printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n", - (int) gettid(), nr_abort, signals_delivered); + (int) rseq_gettid(), nr_abort, signals_delivered); if (!opt_disable_rseq && rseq_unregister_current_thread()) abort(); diff --git a/tools/testing/selftests/rseq/settings b/tools/testing/selftests/rseq/settings new file mode 100644 index 000000000000..e7b9417537fb --- /dev/null +++ b/tools/testing/selftests/rseq/settings @@ -0,0 +1 @@ +timeout=0 diff --git a/tools/testing/selftests/safesetid/Makefile b/tools/testing/selftests/safesetid/Makefile index 98da7a504737..fa02c4d5ec13 100644 --- a/tools/testing/selftests/safesetid/Makefile +++ b/tools/testing/selftests/safesetid/Makefile @@ -1,8 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for mount selftests. -CFLAGS = -Wall -lcap -O2 +CFLAGS = -Wall -O2 +LDLIBS = -lcap -TEST_PROGS := run_tests.sh +TEST_PROGS := safesetid-test.sh TEST_GEN_FILES := safesetid-test include ../lib.mk diff --git a/tools/testing/selftests/safesetid/safesetid-test.c b/tools/testing/selftests/safesetid/safesetid-test.c index 8f40c6ecdad1..0c4d50644c13 100644 --- a/tools/testing/selftests/safesetid/safesetid-test.c +++ b/tools/testing/selftests/safesetid/safesetid-test.c @@ -213,7 +213,8 @@ static void test_setuid(uid_t child_uid, bool expect_success) } if (cpid == 0) { /* Code executed by child */ - setuid(child_uid); + if (setuid(child_uid) < 0) + exit(EXIT_FAILURE); if (getuid() == child_uid) exit(EXIT_SUCCESS); else @@ -291,8 +292,10 @@ int main(int argc, char **argv) // First test to make sure we can write userns mappings from a user // that doesn't have any restrictions (as long as it has CAP_SETUID); - setuid(NO_POLICY_USER); - setgid(NO_POLICY_USER); + if (setuid(NO_POLICY_USER) < 0) + die("Error with set uid(%d)\n", NO_POLICY_USER); + if (setgid(NO_POLICY_USER) < 0) + die("Error with set gid(%d)\n", NO_POLICY_USER); // Take away all but setid caps drop_caps(true); @@ -306,8 +309,10 @@ int main(int argc, char **argv) die("test_userns failed when it should work\n"); } - setuid(RESTRICTED_PARENT); - setgid(RESTRICTED_PARENT); + if (setuid(RESTRICTED_PARENT) < 0) + die("Error with set uid(%d)\n", RESTRICTED_PARENT); + if (setgid(RESTRICTED_PARENT) < 0) + die("Error with set gid(%d)\n", RESTRICTED_PARENT); test_setuid(ROOT_USER, false); test_setuid(ALLOWED_CHILD1, true); diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 7f8b5c8982e3..96bbda4f10fc 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -35,6 +35,7 @@ #include #include #include +#include #include #include #include @@ -3077,7 +3078,7 @@ static int user_trap_syscall(int nr, unsigned int flags) return seccomp(SECCOMP_SET_MODE_FILTER, flags, &prog); } -#define USER_NOTIF_MAGIC 116983961184613L +#define USER_NOTIF_MAGIC INT_MAX TEST(user_notification_basic) { pid_t pid; @@ -3146,7 +3147,18 @@ TEST(user_notification_basic) EXPECT_GT(poll(&pollfd, 1, -1), 0); EXPECT_EQ(pollfd.revents, POLLIN); - EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); + /* Test that we can't pass garbage to the kernel. */ + memset(&req, 0, sizeof(req)); + req.pid = -1; + errno = 0; + ret = ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EINVAL, errno); + + if (ret) { + req.pid = 0; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); + } pollfd.fd = listener; pollfd.events = POLLIN | POLLOUT; @@ -3266,6 +3278,7 @@ TEST(user_notification_signal) close(sk_pair[1]); + memset(&req, 0, sizeof(req)); EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); EXPECT_EQ(kill(pid, SIGUSR1), 0); @@ -3284,6 +3297,7 @@ TEST(user_notification_signal) EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), -1); EXPECT_EQ(errno, ENOENT); + memset(&req, 0, sizeof(req)); EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); resp.id = req.id; diff --git a/tools/testing/selftests/vm/config b/tools/testing/selftests/vm/config index 1c0d76cb5adf..93b90a9b1eeb 100644 --- a/tools/testing/selftests/vm/config +++ b/tools/testing/selftests/vm/config @@ -1,2 +1,3 @@ CONFIG_SYSVIPC=y CONFIG_USERFAULTFD=y +CONFIG_TEST_VMALLOC=m diff --git a/tools/testing/selftests/x86/mov_ss_trap.c b/tools/testing/selftests/x86/mov_ss_trap.c index 3c3a022654f3..6da0ac3f0135 100644 --- a/tools/testing/selftests/x86/mov_ss_trap.c +++ b/tools/testing/selftests/x86/mov_ss_trap.c @@ -257,7 +257,8 @@ int main() err(1, "sigaltstack"); sethandler(SIGSEGV, handle_and_longjmp, SA_RESETHAND | SA_ONSTACK); nr = SYS_getpid; - asm volatile ("mov %[ss], %%ss; SYSENTER" : "+a" (nr) + /* Clear EBP first to make sure we segfault cleanly. */ + asm volatile ("xorl %%ebp, %%ebp; mov %[ss], %%ss; SYSENTER" : "+a" (nr) : [ss] "m" (ss) : "flags", "rcx" #ifdef __x86_64__ , "r11" diff --git a/tools/testing/selftests/x86/sigreturn.c b/tools/testing/selftests/x86/sigreturn.c index 3e49a7873f3e..57c4f67f16ef 100644 --- a/tools/testing/selftests/x86/sigreturn.c +++ b/tools/testing/selftests/x86/sigreturn.c @@ -451,6 +451,19 @@ static void sigusr1(int sig, siginfo_t *info, void *ctx_void) ctx->uc_mcontext.gregs[REG_SP] = (unsigned long)0x8badf00d5aadc0deULL; ctx->uc_mcontext.gregs[REG_CX] = 0; +#ifdef __i386__ + /* + * Make sure the kernel doesn't inadvertently use DS or ES-relative + * accesses in a region where user DS or ES is loaded. + * + * Skip this for 64-bit builds because long mode doesn't care about + * DS and ES and skipping it increases test coverage a little bit, + * since 64-bit kernels can still run the 32-bit build. + */ + ctx->uc_mcontext.gregs[REG_DS] = 0; + ctx->uc_mcontext.gregs[REG_ES] = 0; +#endif + memcpy(&requested_regs, &ctx->uc_mcontext.gregs, sizeof(gregset_t)); requested_regs[REG_CX] = *ssptr(ctx); /* The asm code does this. */ diff --git a/tools/usb/usbip/libsrc/usbip_host_common.c b/tools/usb/usbip/libsrc/usbip_host_common.c index 2813aa821c82..d1d8ba2a4a40 100644 --- a/tools/usb/usbip/libsrc/usbip_host_common.c +++ b/tools/usb/usbip/libsrc/usbip_host_common.c @@ -57,7 +57,7 @@ static int32_t read_attr_usbip_status(struct usbip_usb_device *udev) } value = atoi(status); - + close(fd); return value; } diff --git a/usr/gen_initramfs_list.sh b/usr/gen_initramfs_list.sh index 0aad760fcd8c..2bbac73e6477 100755 --- a/usr/gen_initramfs_list.sh +++ b/usr/gen_initramfs_list.sh @@ -128,7 +128,7 @@ parse() { str="${ftype} ${name} ${location} ${str}" ;; "nod") - local dev=`LC_ALL=C ls -l "${location}"` + local dev="`LC_ALL=C ls -l "${location}"`" local maj=`field 5 ${dev}` local min=`field 6 ${dev}` maj=${maj%,} diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c index 38b4c910b6c3..f23c9cd5684f 100644 --- a/virt/kvm/arm/mmu.c +++ b/virt/kvm/arm/mmu.c @@ -38,6 +38,11 @@ static unsigned long io_map_base; #define KVM_S2PTE_FLAG_IS_IOMAP (1UL << 0) #define KVM_S2_FLAG_LOGGING_ACTIVE (1UL << 1) +static bool is_iomap(unsigned long flags) +{ + return flags & KVM_S2PTE_FLAG_IS_IOMAP; +} + static bool memslot_is_logging(struct kvm_memory_slot *memslot) { return memslot->dirty_bitmap && !(memslot->flags & KVM_MEM_READONLY); @@ -1698,6 +1703,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, vma_pagesize = vma_kernel_pagesize(vma); if (logging_active || + (vma->vm_flags & VM_PFNMAP) || !fault_supports_stage2_huge_mapping(memslot, hva, vma_pagesize)) { force_pte = true; vma_pagesize = PAGE_SIZE; @@ -1760,6 +1766,9 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, writable = false; } + if (exec_fault && is_iomap(flags)) + return -ENOEXEC; + spin_lock(&kvm->mmu_lock); if (mmu_notifier_retry(kvm, mmu_seq)) goto out_unlock; @@ -1781,7 +1790,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (writable) kvm_set_pfn_dirty(pfn); - if (fault_status != FSC_PERM) + if (fault_status != FSC_PERM && !is_iomap(flags)) clean_dcache_guest_page(pfn, vma_pagesize); if (exec_fault) @@ -1948,9 +1957,8 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run) if (kvm_is_error_hva(hva) || (write_fault && !writable)) { if (is_iabt) { /* Prefetch Abort on I/O address */ - kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu)); - ret = 1; - goto out_unlock; + ret = -ENOEXEC; + goto out; } /* @@ -1992,6 +2000,11 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run) ret = user_mem_abort(vcpu, fault_ipa, memslot, hva, fault_status); if (ret == 0) ret = 1; +out: + if (ret == -ENOEXEC) { + kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu)); + ret = 1; + } out_unlock: srcu_read_unlock(&vcpu->kvm->srcu, idx); return ret; diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index 8d69f007dd0c..b3a97dcaa30d 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -363,8 +363,8 @@ int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq) int vgic_v3_save_pending_tables(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; - int last_byte_offset = -1; struct vgic_irq *irq; + gpa_t last_ptr = ~(gpa_t)0; int ret; u8 val; @@ -384,11 +384,11 @@ int vgic_v3_save_pending_tables(struct kvm *kvm) bit_nr = irq->intid % BITS_PER_BYTE; ptr = pendbase + byte_offset; - if (byte_offset != last_byte_offset) { + if (ptr != last_ptr) { ret = kvm_read_guest_lock(kvm, ptr, &val, 1); if (ret) return ret; - last_byte_offset = byte_offset; + last_ptr = ptr; } stored = val & (1U << bit_nr);