diff --git a/Documentation/bpf/libbpf/libbpf_naming_convention.rst b/Documentation/bpf/libbpf/libbpf_naming_convention.rst index 3de1d51e41..6bf9c5ac75 100644 --- a/Documentation/bpf/libbpf/libbpf_naming_convention.rst +++ b/Documentation/bpf/libbpf/libbpf_naming_convention.rst @@ -108,7 +108,7 @@ This bump in ABI version is at most once per kernel development cycle. For example, if current state of ``libbpf.map`` is: -.. code-block:: c +.. code-block:: none LIBBPF_0.0.1 { global: @@ -121,7 +121,7 @@ For example, if current state of ``libbpf.map`` is: , and a new symbol ``bpf_func_c`` is being introduced, then ``libbpf.map`` should be changed like this: -.. code-block:: c +.. code-block:: none LIBBPF_0.0.1 { global: diff --git a/Documentation/devicetree/bindings/iio/st,st-sensors.yaml b/Documentation/devicetree/bindings/iio/st,st-sensors.yaml index b2a1e42c56..71de5631eb 100644 --- a/Documentation/devicetree/bindings/iio/st,st-sensors.yaml +++ b/Documentation/devicetree/bindings/iio/st,st-sensors.yaml @@ -152,47 +152,6 @@ allOf: maxItems: 1 st,drdy-int-pin: false - - if: - properties: - compatible: - enum: - # Two intertial interrupts i.e. accelerometer/gyro interrupts - - st,h3lis331dl-accel - - st,l3g4200d-gyro - - st,l3g4is-gyro - - st,l3gd20-gyro - - st,l3gd20h-gyro - - st,lis2de12 - - st,lis2dw12 - - st,lis2hh12 - - st,lis2dh12-accel - - st,lis331dl-accel - - st,lis331dlh-accel - - st,lis3de - - st,lis3dh-accel - - st,lis3dhh - - st,lis3mdl-magn - - st,lng2dm-accel - - st,lps331ap-press - - st,lsm303agr-accel - - st,lsm303dlh-accel - - st,lsm303dlhc-accel - - st,lsm303dlm-accel - - st,lsm330-accel - - st,lsm330-gyro - - st,lsm330d-accel - - st,lsm330d-gyro - - st,lsm330dl-accel - - st,lsm330dl-gyro - - st,lsm330dlc-accel - - st,lsm330dlc-gyro - - st,lsm9ds0-gyro - - st,lsm9ds1-magn - then: - properties: - interrupts: - maxItems: 2 - required: - compatible - reg diff --git a/Documentation/gpu/rfc/i915_gem_lmem.rst b/Documentation/gpu/rfc/i915_gem_lmem.rst index 675ba8620d..b421a3c180 100644 --- a/Documentation/gpu/rfc/i915_gem_lmem.rst +++ b/Documentation/gpu/rfc/i915_gem_lmem.rst @@ -18,114 +18,5 @@ real, with all the uAPI bits is: * Route shmem backend over to TTM SYSTEM for discrete * TTM purgeable object support * Move i915 buddy allocator over to TTM - * MMAP ioctl mode(see `I915 MMAP`_) - * SET/GET ioctl caching(see `I915 SET/GET CACHING`_) * Send RFC(with mesa-dev on cc) for final sign off on the uAPI * Add pciid for DG1 and turn on uAPI for real - -New object placement and region query uAPI -========================================== -Starting from DG1 we need to give userspace the ability to allocate buffers from -device local-memory. Currently the driver supports gem_create, which can place -buffers in system memory via shmem, and the usual assortment of other -interfaces, like dumb buffers and userptr. - -To support this new capability, while also providing a uAPI which will work -beyond just DG1, we propose to offer three new bits of uAPI: - -DRM_I915_QUERY_MEMORY_REGIONS ------------------------------ -New query ID which allows userspace to discover the list of supported memory -regions(like system-memory and local-memory) for a given device. We identify -each region with a class and instance pair, which should be unique. The class -here would be DEVICE or SYSTEM, and the instance would be zero, on platforms -like DG1. - -Side note: The class/instance design is borrowed from our existing engine uAPI, -where we describe every physical engine in terms of its class, and the -particular instance, since we can have more than one per class. - -In the future we also want to expose more information which can further -describe the capabilities of a region. - -.. kernel-doc:: include/uapi/drm/i915_drm.h - :functions: drm_i915_gem_memory_class drm_i915_gem_memory_class_instance drm_i915_memory_region_info drm_i915_query_memory_regions - -GEM_CREATE_EXT --------------- -New ioctl which is basically just gem_create but now allows userspace to provide -a chain of possible extensions. Note that if we don't provide any extensions and -set flags=0 then we get the exact same behaviour as gem_create. - -Side note: We also need to support PXP[1] in the near future, which is also -applicable to integrated platforms, and adds its own gem_create_ext extension, -which basically lets userspace mark a buffer as "protected". - -.. kernel-doc:: include/uapi/drm/i915_drm.h - :functions: drm_i915_gem_create_ext - -I915_GEM_CREATE_EXT_MEMORY_REGIONS ----------------------------------- -Implemented as an extension for gem_create_ext, we would now allow userspace to -optionally provide an immutable list of preferred placements at creation time, -in priority order, for a given buffer object. For the placements we expect -them each to use the class/instance encoding, as per the output of the regions -query. Having the list in priority order will be useful in the future when -placing an object, say during eviction. - -.. kernel-doc:: include/uapi/drm/i915_drm.h - :functions: drm_i915_gem_create_ext_memory_regions - -One fair criticism here is that this seems a little over-engineered[2]. If we -just consider DG1 then yes, a simple gem_create.flags or something is totally -all that's needed to tell the kernel to allocate the buffer in local-memory or -whatever. However looking to the future we need uAPI which can also support -upcoming Xe HP multi-tile architecture in a sane way, where there can be -multiple local-memory instances for a given device, and so using both class and -instance in our uAPI to describe regions is desirable, although specifically -for DG1 it's uninteresting, since we only have a single local-memory instance. - -Existing uAPI issues -==================== -Some potential issues we still need to resolve. - -I915 MMAP ---------- -In i915 there are multiple ways to MMAP GEM object, including mapping the same -object using different mapping types(WC vs WB), i.e multiple active mmaps per -object. TTM expects one MMAP at most for the lifetime of the object. If it -turns out that we have to backpedal here, there might be some potential -userspace fallout. - -I915 SET/GET CACHING --------------------- -In i915 we have set/get_caching ioctl. TTM doesn't let us to change this, but -DG1 doesn't support non-snooped pcie transactions, so we can just always -allocate as WB for smem-only buffers. If/when our hw gains support for -non-snooped pcie transactions then we must fix this mode at allocation time as -a new GEM extension. - -This is related to the mmap problem, because in general (meaning, when we're -not running on intel cpus) the cpu mmap must not, ever, be inconsistent with -allocation mode. - -Possible idea is to let the kernel picks the mmap mode for userspace from the -following table: - -smem-only: WB. Userspace does not need to call clflush. - -smem+lmem: We only ever allow a single mode, so simply allocate this as uncached -memory, and always give userspace a WC mapping. GPU still does snooped access -here(assuming we can't turn it off like on DG1), which is a bit inefficient. - -lmem only: always WC - -This means on discrete you only get a single mmap mode, all others must be -rejected. That's probably going to be a new default mode or something like -that. - -Links -===== -[1] https://patchwork.freedesktop.org/series/86798/ - -[2] https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5599#note_553791 diff --git a/Documentation/i2c/index.rst b/Documentation/i2c/index.rst index 8b76217e37..6270f1fd7d 100644 --- a/Documentation/i2c/index.rst +++ b/Documentation/i2c/index.rst @@ -17,6 +17,7 @@ Introduction busses/index i2c-topology muxes/i2c-mux-gpio + i2c-sysfs Writing device drivers ====================== diff --git a/Documentation/networking/nf_conntrack-sysctl.rst b/Documentation/networking/nf_conntrack-sysctl.rst index d31ed6c1cb..024d784157 100644 --- a/Documentation/networking/nf_conntrack-sysctl.rst +++ b/Documentation/networking/nf_conntrack-sysctl.rst @@ -191,19 +191,9 @@ nf_flowtable_tcp_timeout - INTEGER (seconds) TCP connections may be offloaded from nf conntrack to nf flow table. Once aged, the connection is returned to nf conntrack with tcp pickup timeout. -nf_flowtable_tcp_pickup - INTEGER (seconds) - default 120 - - TCP connection timeout after being aged from nf flow table offload. - nf_flowtable_udp_timeout - INTEGER (seconds) default 30 Control offload timeout for udp connections. UDP connections may be offloaded from nf conntrack to nf flow table. Once aged, the connection is returned to nf conntrack with udp pickup timeout. - -nf_flowtable_udp_pickup - INTEGER (seconds) - default 30 - - UDP connection timeout after being aged from nf flow table offload. diff --git a/Documentation/userspace-api/seccomp_filter.rst b/Documentation/userspace-api/seccomp_filter.rst index d61219889e..539e9d4a48 100644 --- a/Documentation/userspace-api/seccomp_filter.rst +++ b/Documentation/userspace-api/seccomp_filter.rst @@ -263,7 +263,7 @@ Userspace can also add file descriptors to the notifying process via ``ioctl(SECCOMP_IOCTL_NOTIF_ADDFD)``. The ``id`` member of ``struct seccomp_notif_addfd`` should be the same ``id`` as in ``struct seccomp_notif``. The ``newfd_flags`` flag may be used to set flags -like O_EXEC on the file descriptor in the notifying process. If the supervisor +like O_CLOEXEC on the file descriptor in the notifying process. If the supervisor wants to inject the file descriptor with a specific number, the ``SECCOMP_ADDFD_FLAG_SETFD`` flag can be used, and set the ``newfd`` member to the specific number to use. If that file descriptor is already open in the diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst index 35eca37754..88fa495abb 100644 --- a/Documentation/virt/kvm/locking.rst +++ b/Documentation/virt/kvm/locking.rst @@ -25,10 +25,10 @@ On x86: - vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock -- kvm->arch.mmu_lock is an rwlock. kvm->arch.tdp_mmu_pages_lock is - taken inside kvm->arch.mmu_lock, and cannot be taken without already - holding kvm->arch.mmu_lock (typically with ``read_lock``, otherwise - there's no need to take kvm->arch.tdp_mmu_pages_lock at all). +- kvm->arch.mmu_lock is an rwlock. kvm->arch.tdp_mmu_pages_lock and + kvm->arch.mmu_unsync_pages_lock are taken inside kvm->arch.mmu_lock, and + cannot be taken without already holding kvm->arch.mmu_lock (typically with + ``read_lock`` for the TDP MMU, thus the need for additional spinlocks). Everything else is a leaf: no other lock is taken inside the critical sections. diff --git a/arch/arc/include/asm/checksum.h b/arch/arc/include/asm/checksum.h index 69debd77cd..0b485800a3 100644 --- a/arch/arc/include/asm/checksum.h +++ b/arch/arc/include/asm/checksum.h @@ -24,7 +24,7 @@ */ static inline __sum16 csum_fold(__wsum s) { - unsigned r = s << 16 | s >> 16; /* ror */ + unsigned int r = s << 16 | s >> 16; /* ror */ s = ~s; s -= r; return s >> 16; diff --git a/arch/arc/include/asm/perf_event.h b/arch/arc/include/asm/perf_event.h index 30b9ae511e..e1971d34ef 100644 --- a/arch/arc/include/asm/perf_event.h +++ b/arch/arc/include/asm/perf_event.h @@ -123,7 +123,7 @@ static const char * const arc_pmu_ev_hw_map[] = { #define C(_x) PERF_COUNT_HW_CACHE_##_x #define CACHE_OP_UNSUPPORTED 0xffff -static const unsigned arc_pmu_cache_map[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { +static const unsigned int arc_pmu_cache_map[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(L1D)] = { [C(OP_READ)] = { [C(RESULT_ACCESS)] = PERF_COUNT_ARC_LDC, diff --git a/arch/arc/kernel/fpu.c b/arch/arc/kernel/fpu.c index c67c0f0f5f..ec640219d9 100644 --- a/arch/arc/kernel/fpu.c +++ b/arch/arc/kernel/fpu.c @@ -57,23 +57,26 @@ void fpu_save_restore(struct task_struct *prev, struct task_struct *next) void fpu_init_task(struct pt_regs *regs) { + const unsigned int fwe = 0x80000000; + /* default rounding mode */ write_aux_reg(ARC_REG_FPU_CTRL, 0x100); - /* set "Write enable" to allow explicit write to exception flags */ - write_aux_reg(ARC_REG_FPU_STATUS, 0x80000000); + /* Initialize to zero: setting requires FWE be set */ + write_aux_reg(ARC_REG_FPU_STATUS, fwe); } void fpu_save_restore(struct task_struct *prev, struct task_struct *next) { struct arc_fpu *save = &prev->thread.fpu; struct arc_fpu *restore = &next->thread.fpu; + const unsigned int fwe = 0x80000000; save->ctrl = read_aux_reg(ARC_REG_FPU_CTRL); save->status = read_aux_reg(ARC_REG_FPU_STATUS); write_aux_reg(ARC_REG_FPU_CTRL, restore->ctrl); - write_aux_reg(ARC_REG_FPU_STATUS, restore->status); + write_aux_reg(ARC_REG_FPU_STATUS, (fwe | restore->status)); } #endif diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c index 47bab67f86..9e28058cdb 100644 --- a/arch/arc/kernel/unwind.c +++ b/arch/arc/kernel/unwind.c @@ -260,7 +260,7 @@ static void init_unwind_hdr(struct unwind_table *table, { const u8 *ptr; unsigned long tableSize = table->size, hdrSize; - unsigned n; + unsigned int n; const u32 *fde; struct { u8 version; @@ -462,7 +462,7 @@ static uleb128_t get_uleb128(const u8 **pcur, const u8 *end) { const u8 *cur = *pcur; uleb128_t value; - unsigned shift; + unsigned int shift; for (shift = 0, value = 0; cur < end; shift += 7) { if (shift + 7 > 8 * sizeof(value) @@ -483,7 +483,7 @@ static sleb128_t get_sleb128(const u8 **pcur, const u8 *end) { const u8 *cur = *pcur; sleb128_t value; - unsigned shift; + unsigned int shift; for (shift = 0, value = 0; cur < end; shift += 7) { if (shift + 7 > 8 * sizeof(value) @@ -609,7 +609,7 @@ static unsigned long read_pointer(const u8 **pLoc, const void *end, static signed fde_pointer_type(const u32 *cie) { const u8 *ptr = (const u8 *)(cie + 2); - unsigned version = *ptr; + unsigned int version = *ptr; if (*++ptr) { const char *aug; @@ -904,7 +904,7 @@ int arc_unwind(struct unwind_frame_info *frame) const u8 *ptr = NULL, *end = NULL; unsigned long pc = UNW_PC(frame) - frame->call_frame; unsigned long startLoc = 0, endLoc = 0, cfa; - unsigned i; + unsigned int i; signed ptrType = -1; uleb128_t retAddrReg = 0; const struct unwind_table *table; diff --git a/arch/arc/kernel/vmlinux.lds.S b/arch/arc/kernel/vmlinux.lds.S index e2146a8da1..529ae50f9f 100644 --- a/arch/arc/kernel/vmlinux.lds.S +++ b/arch/arc/kernel/vmlinux.lds.S @@ -88,6 +88,8 @@ SECTIONS CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT + IRQENTRY_TEXT + SOFTIRQENTRY_TEXT *(.fixup) *(.gnu.warning) } diff --git a/arch/arm/boot/dts/overlays/Makefile b/arch/arm/boot/dts/overlays/Makefile index 6ab8969f9d..fbcc3e35a7 100644 --- a/arch/arm/boot/dts/overlays/Makefile +++ b/arch/arm/boot/dts/overlays/Makefile @@ -123,6 +123,10 @@ dtbo-$(CONFIG_ARCH_BCM2835) += \ merus-amp.dtbo \ midi-uart0.dtbo \ midi-uart1.dtbo \ + midi-uart2.dtbo \ + midi-uart3.dtbo \ + midi-uart4.dtbo \ + midi-uart5.dtbo \ minipitft13.dtbo \ miniuart-bt.dtbo \ mmc.dtbo \ diff --git a/arch/arm/boot/dts/overlays/README b/arch/arm/boot/dts/overlays/README index fafec158c1..708ebaac9c 100644 --- a/arch/arm/boot/dts/overlays/README +++ b/arch/arm/boot/dts/overlays/README @@ -1390,6 +1390,8 @@ Params: abx80x Select one of the ABx80x family: AB0801, AB0803, AB0804, AB0805, AB1801, AB1803, AB1804, AB1805 + bq32000 Select the TI BQ32000 device + ds1307 Select the DS1307 device ds1339 Select the DS1339 device @@ -1434,6 +1436,9 @@ Params: abx80x Select one of the ABx80x family: device must be configured to use the specified address. + trickle-diode-disable Do not use the internal trickle charger diode + (BQ32000 only) + trickle-diode-type Diode type for trickle charge - "standard" or "schottky" (ABx80x and RV1805 only) @@ -1455,6 +1460,8 @@ Params: abx80x Select one of the ABx80x family: AB0801, AB0803, AB0804, AB0805, AB1801, AB1803, AB1804, AB1805 + bq32000 Select the TI BQ32000 device + ds1307 Select the DS1307 device ds1339 Select the DS1339 device @@ -1495,6 +1502,9 @@ Params: abx80x Select one of the ABx80x family: device must be configured to use the specified address. + trickle-diode-disable Do not use the internal trickle charger diode + (BQ32000 only) + trickle-diode-type Diode type for trickle charge - "standard" or "schottky" (ABx80x and RV1805 only) @@ -2088,6 +2098,34 @@ Load: dtoverlay=midi-uart1 Params: +Name: midi-uart2 +Info: Configures UART2 (ttyAMA1) so that a requested 38.4kbaud actually gets + 31.25kbaud, the frequency required for MIDI +Load: dtoverlay=midi-uart2 +Params: + + +Name: midi-uart3 +Info: Configures UART3 (ttyAMA2) so that a requested 38.4kbaud actually gets + 31.25kbaud, the frequency required for MIDI +Load: dtoverlay=midi-uart3 +Params: + + +Name: midi-uart4 +Info: Configures UART4 (ttyAMA3) so that a requested 38.4kbaud actually gets + 31.25kbaud, the frequency required for MIDI +Load: dtoverlay=midi-uart4 +Params: + + +Name: midi-uart5 +Info: Configures UART5 (ttyAMA4) so that a requested 38.4kbaud actually gets + 31.25kbaud, the frequency required for MIDI +Load: dtoverlay=midi-uart5 +Params: + + Name: minipitft13 Info: Overlay for AdaFruit Mini Pi 1.3" TFT via SPI using fbtft driver. Load: dtoverlay=minipitft13,= diff --git a/arch/arm/boot/dts/overlays/i2c-rtc-common.dtsi b/arch/arm/boot/dts/overlays/i2c-rtc-common.dtsi index f51981aafd..7f749fc2d8 100644 --- a/arch/arm/boot/dts/overlays/i2c-rtc-common.dtsi +++ b/arch/arm/boot/dts/overlays/i2c-rtc-common.dtsi @@ -256,6 +256,21 @@ s35390a: s35390a@30 { }; }; + fragment@19 { + target = <&i2cbus>; + __dormant__ { + #address-cells = <1>; + #size-cells = <0>; + + bq32000: bq32000@68 { + compatible = "ti,bq32000"; + trickle-resistor-ohms = <0>; + reg = <0x68>; + }; + }; + }; + + __overrides__ { abx80x = <0>,"+0"; ds1307 = <0>,"+1"; @@ -276,6 +291,7 @@ __overrides__ { pcf85063 = <0>,"+15"; pcf85063a = <0>,"+16"; s35390a = <0>,"+18"; + bq32000 = <0>,"+19"; addr = <&abx80x>, "reg:0", <&ds1307>, "reg:0", @@ -288,13 +304,15 @@ __overrides__ { <&m41t62>, "reg:0", <&rv1805>, "reg:0", <&s35390a>, "reg:0"; + trickle-diode-disable = <&bq32000>,"trickle-diode-disable?"; trickle-diode-type = <&abx80x>,"abracon,tc-diode", <&rv1805>,"abracon,tc-diode"; trickle-resistor-ohms = <&ds1339>,"trickle-resistor-ohms:0", <&ds1340>,"trickle-resistor-ohms:0", <&abx80x>,"abracon,tc-resistor:0", <&rv3028>,"trickle-resistor-ohms:0", - <&rv1805>,"abracon,tc-resistor:0"; + <&rv1805>,"abracon,tc-resistor:0", + <&bq32000>,"abracon,tc-resistor:0"; backup-switchover-mode = <&rv3028>,"backup-switchover-mode:0"; wakeup-source = <&ds1339>,"wakeup-source?", <&ds3231>,"wakeup-source?", diff --git a/arch/arm/boot/dts/overlays/midi-uart2-overlay.dts b/arch/arm/boot/dts/overlays/midi-uart2-overlay.dts new file mode 100644 index 0000000000..66f3092e9a --- /dev/null +++ b/arch/arm/boot/dts/overlays/midi-uart2-overlay.dts @@ -0,0 +1,37 @@ +/dts-v1/; +/plugin/; + +#include + +/* + * Fake a higher clock rate to get a larger divisor, and thereby a lower + * baudrate. The real clock is 48MHz, which we scale so that requesting + * 38.4kHz results in an actual 31.25kHz. + * + * 48000000*38400/31250 = 58982400 + */ + +/{ + compatible = "brcm,bcm2835"; + + fragment@0 { + target-path = "/"; + __overlay__ { + midi_clk: midi_clk2 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-output-names = "uart2_pclk"; + clock-frequency = <58982400>; + }; + }; + }; + + fragment@1 { + target = <&uart2>; + __overlay__ { + clocks = <&midi_clk>, + <&clocks BCM2835_CLOCK_VPU>; + }; + }; +}; + diff --git a/arch/arm/boot/dts/overlays/midi-uart3-overlay.dts b/arch/arm/boot/dts/overlays/midi-uart3-overlay.dts new file mode 100644 index 0000000000..55c6cb94f9 --- /dev/null +++ b/arch/arm/boot/dts/overlays/midi-uart3-overlay.dts @@ -0,0 +1,38 @@ +/dts-v1/; +/plugin/; + +#include + +/* + * Fake a higher clock rate to get a larger divisor, and thereby a lower + * baudrate. The real clock is 48MHz, which we scale so that requesting + * 38.4kHz results in an actual 31.25kHz. + * + * 48000000*38400/31250 = 58982400 + */ + +/{ + compatible = "brcm,bcm2835"; + + fragment@0 { + target-path = "/"; + __overlay__ { + midi_clk: midi_clk3 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-output-names = "uart3_pclk"; + clock-frequency = <58982400>; + }; + }; + }; + + fragment@1 { + target = <&uart3>; + __overlay__ { + clocks = <&midi_clk>, + <&clocks BCM2835_CLOCK_VPU>; + }; + }; +}; + + diff --git a/arch/arm/boot/dts/overlays/midi-uart4-overlay.dts b/arch/arm/boot/dts/overlays/midi-uart4-overlay.dts new file mode 100644 index 0000000000..5819df1a6b --- /dev/null +++ b/arch/arm/boot/dts/overlays/midi-uart4-overlay.dts @@ -0,0 +1,38 @@ +/dts-v1/; +/plugin/; + +#include + +/* + * Fake a higher clock rate to get a larger divisor, and thereby a lower + * baudrate. The real clock is 48MHz, which we scale so that requesting + * 38.4kHz results in an actual 31.25kHz. + * + * 48000000*38400/31250 = 58982400 + */ + +/{ + compatible = "brcm,bcm2835"; + + fragment@0 { + target-path = "/"; + __overlay__ { + midi_clk: midi_clk4 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-output-names = "uart4_pclk"; + clock-frequency = <58982400>; + }; + }; + }; + + fragment@1 { + target = <&uart4>; + __overlay__ { + clocks = <&midi_clk>, + <&clocks BCM2835_CLOCK_VPU>; + }; + }; +}; + + diff --git a/arch/arm/boot/dts/overlays/midi-uart5-overlay.dts b/arch/arm/boot/dts/overlays/midi-uart5-overlay.dts new file mode 100644 index 0000000000..a1d37f7103 --- /dev/null +++ b/arch/arm/boot/dts/overlays/midi-uart5-overlay.dts @@ -0,0 +1,38 @@ +/dts-v1/; +/plugin/; + +#include + +/* + * Fake a higher clock rate to get a larger divisor, and thereby a lower + * baudrate. The real clock is 48MHz, which we scale so that requesting + * 38.4kHz results in an actual 31.25kHz. + * + * 48000000*38400/31250 = 58982400 + */ + +/{ + compatible = "brcm,bcm2835"; + + fragment@0 { + target-path = "/"; + __overlay__ { + midi_clk: midi_clk5 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-output-names = "uart5_pclk"; + clock-frequency = <58982400>; + }; + }; + }; + + fragment@1 { + target = <&uart5>; + __overlay__ { + clocks = <&midi_clk>, + <&clocks BCM2835_CLOCK_VPU>; + }; + }; +}; + + diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index e9a2b8f277..0ca72f5cda 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -94,10 +94,14 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, kvm->arch.return_nisv_io_abort_to_user = true; break; case KVM_CAP_ARM_MTE: - if (!system_supports_mte() || kvm->created_vcpus) - return -EINVAL; - r = 0; - kvm->arch.mte_enabled = true; + mutex_lock(&kvm->lock); + if (!system_supports_mte() || kvm->created_vcpus) { + r = -EINVAL; + } else { + r = 0; + kvm->arch.mte_enabled = true; + } + mutex_unlock(&kvm->lock); break; default: r = -EINVAL; diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index d938ce95d3..a6ce991b14 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -193,7 +193,7 @@ static bool range_is_memory(u64 start, u64 end) { struct kvm_mem_range r1, r2; - if (!find_mem_range(start, &r1) || !find_mem_range(end, &r2)) + if (!find_mem_range(start, &r1) || !find_mem_range(end - 1, &r2)) return false; if (r1.start != r2.start) return false; diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h index d4bdf7d274..6b800d3e26 100644 --- a/arch/powerpc/include/asm/interrupt.h +++ b/arch/powerpc/include/asm/interrupt.h @@ -583,6 +583,9 @@ DECLARE_INTERRUPT_HANDLER_NMI(hmi_exception_realmode); DECLARE_INTERRUPT_HANDLER_ASYNC(TAUException); +/* irq.c */ +DECLARE_INTERRUPT_HANDLER_ASYNC(do_IRQ); + void __noreturn unrecoverable_exception(struct pt_regs *regs); void replay_system_reset(void); diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h index 4982f3711f..2b3278534b 100644 --- a/arch/powerpc/include/asm/irq.h +++ b/arch/powerpc/include/asm/irq.h @@ -52,7 +52,7 @@ extern void *mcheckirq_ctx[NR_CPUS]; extern void *hardirq_ctx[NR_CPUS]; extern void *softirq_ctx[NR_CPUS]; -extern void do_IRQ(struct pt_regs *regs); +void __do_IRQ(struct pt_regs *regs); extern void __init init_IRQ(void); extern void __do_irq(struct pt_regs *regs); diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h index 3e5d470a61..14422e8514 100644 --- a/arch/powerpc/include/asm/ptrace.h +++ b/arch/powerpc/include/asm/ptrace.h @@ -70,6 +70,22 @@ struct pt_regs unsigned long __pad[4]; /* Maintain 16 byte interrupt stack alignment */ }; #endif +#if defined(CONFIG_PPC32) && defined(CONFIG_BOOKE) + struct { /* Must be a multiple of 16 bytes */ + unsigned long mas0; + unsigned long mas1; + unsigned long mas2; + unsigned long mas3; + unsigned long mas6; + unsigned long mas7; + unsigned long srr0; + unsigned long srr1; + unsigned long csrr0; + unsigned long csrr1; + unsigned long dsrr0; + unsigned long dsrr1; + }; +#endif }; #endif diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index a47eefa09b..5bee245d83 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -309,24 +309,21 @@ int main(void) STACK_PT_REGS_OFFSET(STACK_REGS_IAMR, iamr); #endif -#if defined(CONFIG_PPC32) -#if defined(CONFIG_BOOKE) || defined(CONFIG_40x) - DEFINE(EXC_LVL_SIZE, STACK_EXC_LVL_FRAME_SIZE); - DEFINE(MAS0, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas0)); +#if defined(CONFIG_PPC32) && defined(CONFIG_BOOKE) + STACK_PT_REGS_OFFSET(MAS0, mas0); /* we overload MMUCR for 44x on MAS0 since they are mutually exclusive */ - DEFINE(MMUCR, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas0)); - DEFINE(MAS1, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas1)); - DEFINE(MAS2, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas2)); - DEFINE(MAS3, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas3)); - DEFINE(MAS6, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas6)); - DEFINE(MAS7, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas7)); - DEFINE(_SRR0, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, srr0)); - DEFINE(_SRR1, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, srr1)); - DEFINE(_CSRR0, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, csrr0)); - DEFINE(_CSRR1, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, csrr1)); - DEFINE(_DSRR0, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, dsrr0)); - DEFINE(_DSRR1, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, dsrr1)); -#endif + STACK_PT_REGS_OFFSET(MMUCR, mas0); + STACK_PT_REGS_OFFSET(MAS1, mas1); + STACK_PT_REGS_OFFSET(MAS2, mas2); + STACK_PT_REGS_OFFSET(MAS3, mas3); + STACK_PT_REGS_OFFSET(MAS6, mas6); + STACK_PT_REGS_OFFSET(MAS7, mas7); + STACK_PT_REGS_OFFSET(_SRR0, srr0); + STACK_PT_REGS_OFFSET(_SRR1, srr1); + STACK_PT_REGS_OFFSET(_CSRR0, csrr0); + STACK_PT_REGS_OFFSET(_CSRR1, csrr1); + STACK_PT_REGS_OFFSET(_DSRR0, dsrr0); + STACK_PT_REGS_OFFSET(_DSRR1, dsrr1); #endif /* About the CPU features table */ diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S index 764edd860e..68e5c0a7e9 100644 --- a/arch/powerpc/kernel/head_book3s_32.S +++ b/arch/powerpc/kernel/head_book3s_32.S @@ -300,7 +300,7 @@ ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_HPTE_TABLE) EXCEPTION_PROLOG_1 EXCEPTION_PROLOG_2 INTERRUPT_DATA_STORAGE DataAccess handle_dar_dsisr=1 prepare_transfer_to_handler - lwz r5, _DSISR(r11) + lwz r5, _DSISR(r1) andis. r0, r5, DSISR_DABRMATCH@h bne- 1f bl do_page_fault diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h index 87b806e8ed..e5503420b6 100644 --- a/arch/powerpc/kernel/head_booke.h +++ b/arch/powerpc/kernel/head_booke.h @@ -168,20 +168,18 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV) /* only on e500mc */ #define DBG_STACK_BASE dbgirq_ctx -#define EXC_LVL_FRAME_OVERHEAD (THREAD_SIZE - INT_FRAME_SIZE - EXC_LVL_SIZE) - #ifdef CONFIG_SMP #define BOOKE_LOAD_EXC_LEVEL_STACK(level) \ mfspr r8,SPRN_PIR; \ slwi r8,r8,2; \ addis r8,r8,level##_STACK_BASE@ha; \ lwz r8,level##_STACK_BASE@l(r8); \ - addi r8,r8,EXC_LVL_FRAME_OVERHEAD; + addi r8,r8,THREAD_SIZE - INT_FRAME_SIZE; #else #define BOOKE_LOAD_EXC_LEVEL_STACK(level) \ lis r8,level##_STACK_BASE@ha; \ lwz r8,level##_STACK_BASE@l(r8); \ - addi r8,r8,EXC_LVL_FRAME_OVERHEAD; + addi r8,r8,THREAD_SIZE - INT_FRAME_SIZE; #endif /* @@ -208,7 +206,7 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV) mtmsr r11; \ mfspr r11,SPRN_SPRG_THREAD; /* if from user, start at top of */\ lwz r11, TASK_STACK - THREAD(r11); /* this thread's kernel stack */\ - addi r11,r11,EXC_LVL_FRAME_OVERHEAD; /* allocate stack frame */\ + addi r11,r11,THREAD_SIZE - INT_FRAME_SIZE; /* allocate stack frame */\ beq 1f; \ /* COMING FROM USER MODE */ \ stw r9,_CCR(r11); /* save CR */\ @@ -516,24 +514,5 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV) bl kernel_fp_unavailable_exception; \ b interrupt_return -#else /* __ASSEMBLY__ */ -struct exception_regs { - unsigned long mas0; - unsigned long mas1; - unsigned long mas2; - unsigned long mas3; - unsigned long mas6; - unsigned long mas7; - unsigned long srr0; - unsigned long srr1; - unsigned long csrr0; - unsigned long csrr1; - unsigned long dsrr0; - unsigned long dsrr1; -}; - -/* ensure this structure is always sized to a multiple of the stack alignment */ -#define STACK_EXC_LVL_FRAME_SIZE ALIGN(sizeof (struct exception_regs), 16) - #endif /* __ASSEMBLY__ */ #endif /* __HEAD_BOOKE_H__ */ diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 91e63eac4e..551b653228 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -750,7 +750,7 @@ void __do_irq(struct pt_regs *regs) trace_irq_exit(regs); } -DEFINE_INTERRUPT_HANDLER_ASYNC(do_IRQ) +void __do_IRQ(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); void *cursp, *irqsp, *sirqsp; @@ -774,6 +774,11 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(do_IRQ) set_irq_regs(old_regs); } +DEFINE_INTERRUPT_HANDLER_ASYNC(do_IRQ) +{ + __do_IRQ(regs); +} + static void *__init alloc_vm_stack(void) { return __vmalloc_node(THREAD_SIZE, THREAD_ALIGN, THREADINFO_GFP, diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index cbc28d1a2e..7a7cd6bda5 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -292,7 +292,8 @@ int kprobe_handler(struct pt_regs *regs) if (user_mode(regs)) return 0; - if (!(regs->msr & MSR_IR) || !(regs->msr & MSR_DR)) + if (!IS_ENABLED(CONFIG_BOOKE) && + (!(regs->msr & MSR_IR) || !(regs->msr & MSR_DR))) return 0; /* diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 5ff0e55d0d..defecb3b1b 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -1167,7 +1167,7 @@ static int __init topology_init(void) * CPU. For instance, the boot cpu might never be valid * for hotplugging. */ - if (smp_ops->cpu_offline_self) + if (smp_ops && smp_ops->cpu_offline_self) c->hotpluggable = 1; #endif diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index e45ce427bf..c487ba5a6e 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -586,7 +586,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt) #if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC) if (atomic_read(&ppc_n_lost_interrupts) != 0) - do_IRQ(regs); + __do_IRQ(regs); #endif old_regs = set_irq_regs(regs); diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index dfbce527c9..d56254f05e 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -1104,7 +1104,7 @@ DEFINE_INTERRUPT_HANDLER(RunModeException) _exception(SIGTRAP, regs, TRAP_UNK, 0); } -DEFINE_INTERRUPT_HANDLER(single_step_exception) +static void __single_step_exception(struct pt_regs *regs) { clear_single_step(regs); clear_br_trace(regs); @@ -1121,6 +1121,11 @@ DEFINE_INTERRUPT_HANDLER(single_step_exception) _exception(SIGTRAP, regs, TRAP_TRACE, regs->nip); } +DEFINE_INTERRUPT_HANDLER(single_step_exception) +{ + __single_step_exception(regs); +} + /* * After we have successfully emulated an instruction, we have to * check if the instruction was being single-stepped, and if so, @@ -1130,7 +1135,7 @@ DEFINE_INTERRUPT_HANDLER(single_step_exception) static void emulate_single_step(struct pt_regs *regs) { if (single_stepping(regs)) - single_step_exception(regs); + __single_step_exception(regs); } static inline int __parse_fpscr(unsigned long fpscr) diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 6b08866684..0dfaa6ab44 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -539,9 +539,10 @@ static void init_cpu_char_feature_flags(struct h_cpu_char_result *result) * H_CPU_BEHAV_FAVOUR_SECURITY_H could be set only if * H_CPU_BEHAV_FAVOUR_SECURITY is. */ - if (!(result->behaviour & H_CPU_BEHAV_FAVOUR_SECURITY)) + if (!(result->behaviour & H_CPU_BEHAV_FAVOUR_SECURITY)) { security_ftr_clear(SEC_FTR_FAVOUR_SECURITY); - else if (result->behaviour & H_CPU_BEHAV_FAVOUR_SECURITY_H) + pseries_security_flavor = 0; + } else if (result->behaviour & H_CPU_BEHAV_FAVOUR_SECURITY_H) pseries_security_flavor = 1; else pseries_security_flavor = 2; diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index dbdbbc2f1d..943fd30095 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -67,6 +67,7 @@ static struct irq_domain *xive_irq_domain; static struct xive_ipi_desc { unsigned int irq; char name[16]; + atomic_t started; } *xive_ipis; /* @@ -1120,7 +1121,7 @@ static const struct irq_domain_ops xive_ipi_irq_domain_ops = { .alloc = xive_ipi_irq_domain_alloc, }; -static int __init xive_request_ipi(void) +static int __init xive_init_ipis(void) { struct fwnode_handle *fwnode; struct irq_domain *ipi_domain; @@ -1144,10 +1145,6 @@ static int __init xive_request_ipi(void) struct xive_ipi_desc *xid = &xive_ipis[node]; struct xive_ipi_alloc_info info = { node }; - /* Skip nodes without CPUs */ - if (cpumask_empty(cpumask_of_node(node))) - continue; - /* * Map one IPI interrupt per node for all cpus of that node. * Since the HW interrupt number doesn't have any meaning, @@ -1159,11 +1156,6 @@ static int __init xive_request_ipi(void) xid->irq = ret; snprintf(xid->name, sizeof(xid->name), "IPI-%d", node); - - ret = request_irq(xid->irq, xive_muxed_ipi_action, - IRQF_PERCPU | IRQF_NO_THREAD, xid->name, NULL); - - WARN(ret < 0, "Failed to request IPI %d: %d\n", xid->irq, ret); } return ret; @@ -1178,6 +1170,22 @@ static int __init xive_request_ipi(void) return ret; } +static int __init xive_request_ipi(unsigned int cpu) +{ + struct xive_ipi_desc *xid = &xive_ipis[early_cpu_to_node(cpu)]; + int ret; + + if (atomic_inc_return(&xid->started) > 1) + return 0; + + ret = request_irq(xid->irq, xive_muxed_ipi_action, + IRQF_PERCPU | IRQF_NO_THREAD, + xid->name, NULL); + + WARN(ret < 0, "Failed to request IPI %d: %d\n", xid->irq, ret); + return ret; +} + static int xive_setup_cpu_ipi(unsigned int cpu) { unsigned int xive_ipi_irq = xive_ipi_cpu_to_irq(cpu); @@ -1192,6 +1200,9 @@ static int xive_setup_cpu_ipi(unsigned int cpu) if (xc->hw_ipi != XIVE_BAD_IRQ) return 0; + /* Register the IPI */ + xive_request_ipi(cpu); + /* Grab an IPI from the backend, this will populate xc->hw_ipi */ if (xive_ops->get_ipi(cpu, xc)) return -EIO; @@ -1231,6 +1242,8 @@ static void xive_cleanup_cpu_ipi(unsigned int cpu, struct xive_cpu *xc) if (xc->hw_ipi == XIVE_BAD_IRQ) return; + /* TODO: clear IPI mapping */ + /* Mask the IPI */ xive_do_source_set_mask(&xc->ipi_data, true); @@ -1253,7 +1266,7 @@ void __init xive_smp_probe(void) smp_ops->cause_ipi = xive_cause_ipi; /* Register the IPI */ - xive_request_ipi(); + xive_init_ipis(); /* Allocate and setup IPI for the boot CPU */ xive_setup_cpu_ipi(smp_processor_id()); diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index d3081e4d96..3397ddac1a 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -11,7 +11,7 @@ endif CFLAGS_syscall_table.o += $(call cc-option,-Wno-override-init,) ifdef CONFIG_KEXEC -AFLAGS_kexec_relocate.o := -mcmodel=medany -mno-relax +AFLAGS_kexec_relocate.o := -mcmodel=medany $(call cc-option,-mno-relax) endif extra-y += head.o diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 88134cc288..7cb4f391d1 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -197,7 +197,7 @@ static void __init setup_bootmem(void) * if end of dram is equal to maximum addressable memory. For 64-bit * kernel, this problem can't happen here as the end of the virtual * address space is occupied by the kernel mapping then this check must - * be done in create_kernel_page_table. + * be done as soon as the kernel mapping base address is determined. */ max_mapped_addr = __pa(~(ulong)0); if (max_mapped_addr == (phys_ram_end - 1)) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 974cbfb1ee..af6ce8d4c8 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1038,6 +1038,13 @@ struct kvm_arch { struct list_head lpage_disallowed_mmu_pages; struct kvm_page_track_notifier_node mmu_sp_tracker; struct kvm_page_track_notifier_head track_notifier_head; + /* + * Protects marking pages unsync during page faults, as TDP MMU page + * faults only take mmu_lock for read. For simplicity, the unsync + * pages lock is always taken when marking pages unsync regardless of + * whether mmu_lock is held for read or write. + */ + spinlock_t mmu_unsync_pages_lock; struct list_head assigned_dev_head; struct iommu_domain *iommu_domain; diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index d5c691a320..39224e035e 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1986,7 +1986,8 @@ static struct irq_chip ioapic_chip __read_mostly = { .irq_set_affinity = ioapic_set_affinity, .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_get_irqchip_state = ioapic_irq_get_chip_state, - .flags = IRQCHIP_SKIP_SET_WAKE, + .flags = IRQCHIP_SKIP_SET_WAKE | + IRQCHIP_AFFINITY_PRE_STARTUP, }; static struct irq_chip ioapic_ir_chip __read_mostly = { @@ -1999,7 +2000,8 @@ static struct irq_chip ioapic_ir_chip __read_mostly = { .irq_set_affinity = ioapic_set_affinity, .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_get_irqchip_state = ioapic_irq_get_chip_state, - .flags = IRQCHIP_SKIP_SET_WAKE, + .flags = IRQCHIP_SKIP_SET_WAKE | + IRQCHIP_AFFINITY_PRE_STARTUP, }; static inline void init_IO_APIC_traps(void) diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index 44ebe25e77..dbacb9ec88 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -58,11 +58,13 @@ msi_set_affinity(struct irq_data *irqd, const struct cpumask *mask, bool force) * The quirk bit is not set in this case. * - The new vector is the same as the old vector * - The old vector is MANAGED_IRQ_SHUTDOWN_VECTOR (interrupt starts up) + * - The interrupt is not yet started up * - The new destination CPU is the same as the old destination CPU */ if (!irqd_msi_nomask_quirk(irqd) || cfg->vector == old_cfg.vector || old_cfg.vector == MANAGED_IRQ_SHUTDOWN_VECTOR || + !irqd_is_started(irqd) || cfg->dest_apicid == old_cfg.dest_apicid) { irq_msi_update_msg(irqd, cfg); return ret; @@ -150,7 +152,8 @@ static struct irq_chip pci_msi_controller = { .irq_ack = irq_chip_ack_parent, .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_set_affinity = msi_set_affinity, - .flags = IRQCHIP_SKIP_SET_WAKE, + .flags = IRQCHIP_SKIP_SET_WAKE | + IRQCHIP_AFFINITY_PRE_STARTUP, }; int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, @@ -219,7 +222,8 @@ static struct irq_chip pci_msi_ir_controller = { .irq_mask = pci_msi_mask_irq, .irq_ack = irq_chip_ack_parent, .irq_retrigger = irq_chip_retrigger_hierarchy, - .flags = IRQCHIP_SKIP_SET_WAKE, + .flags = IRQCHIP_SKIP_SET_WAKE | + IRQCHIP_AFFINITY_PRE_STARTUP, }; static struct msi_domain_info pci_msi_ir_domain_info = { @@ -273,7 +277,8 @@ static struct irq_chip dmar_msi_controller = { .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_compose_msi_msg = dmar_msi_compose_msg, .irq_write_msi_msg = dmar_msi_write_msg, - .flags = IRQCHIP_SKIP_SET_WAKE, + .flags = IRQCHIP_SKIP_SET_WAKE | + IRQCHIP_AFFINITY_PRE_STARTUP, }; static int dmar_msi_init(struct irq_domain *domain, diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index f07c10b87a..57e4bb695f 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -285,15 +285,14 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width) return chunks >>= shift; } -static int __mon_event_count(u32 rmid, struct rmid_read *rr) +static u64 __mon_event_count(u32 rmid, struct rmid_read *rr) { struct mbm_state *m; u64 chunks, tval; tval = __rmid_read(rmid, rr->evtid); if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) { - rr->val = tval; - return -EINVAL; + return tval; } switch (rr->evtid) { case QOS_L3_OCCUP_EVENT_ID: @@ -305,12 +304,6 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr) case QOS_L3_MBM_LOCAL_EVENT_ID: m = &rr->d->mbm_local[rmid]; break; - default: - /* - * Code would never reach here because - * an invalid event id would fail the __rmid_read. - */ - return -EINVAL; } if (rr->first) { @@ -361,23 +354,29 @@ void mon_event_count(void *info) struct rdtgroup *rdtgrp, *entry; struct rmid_read *rr = info; struct list_head *head; + u64 ret_val; rdtgrp = rr->rgrp; - if (__mon_event_count(rdtgrp->mon.rmid, rr)) - return; + ret_val = __mon_event_count(rdtgrp->mon.rmid, rr); /* - * For Ctrl groups read data from child monitor groups. + * For Ctrl groups read data from child monitor groups and + * add them together. Count events which are read successfully. + * Discard the rmid_read's reporting errors. */ head = &rdtgrp->mon.crdtgrp_list; if (rdtgrp->type == RDTCTRL_GROUP) { list_for_each_entry(entry, head, mon.crdtgrp_list) { - if (__mon_event_count(entry->mon.rmid, rr)) - return; + if (__mon_event_count(entry->mon.rmid, rr) == 0) + ret_val = 0; } } + + /* Report error if none of rmid_reads are successful */ + if (ret_val) + rr->val = ret_val; } /* diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 08651a4e6a..42fc41dd0e 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -508,7 +508,7 @@ static struct irq_chip hpet_msi_controller __ro_after_init = { .irq_set_affinity = msi_domain_set_affinity, .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_write_msi_msg = hpet_msi_write_msg, - .flags = IRQCHIP_SKIP_SET_WAKE, + .flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_AFFINITY_PRE_STARTUP, }; static int hpet_msi_init(struct irq_domain *domain, diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 739be5da3b..fe03bd9787 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -208,30 +208,6 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) kvm_mmu_after_set_cpuid(vcpu); } -static int is_efer_nx(void) -{ - return host_efer & EFER_NX; -} - -static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu) -{ - int i; - struct kvm_cpuid_entry2 *e, *entry; - - entry = NULL; - for (i = 0; i < vcpu->arch.cpuid_nent; ++i) { - e = &vcpu->arch.cpuid_entries[i]; - if (e->function == 0x80000001) { - entry = e; - break; - } - } - if (entry && cpuid_entry_has(entry, X86_FEATURE_NX) && !is_efer_nx()) { - cpuid_entry_clear(entry, X86_FEATURE_NX); - printk(KERN_INFO "kvm: guest NX capability removed\n"); - } -} - int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; @@ -302,7 +278,6 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, vcpu->arch.cpuid_entries = e2; vcpu->arch.cpuid_nent = cpuid->nent; - cpuid_fix_nx_cap(vcpu); kvm_update_cpuid_runtime(vcpu); kvm_vcpu_after_set_cpuid(vcpu); @@ -401,7 +376,6 @@ static __always_inline void kvm_cpu_cap_mask(enum cpuid_leafs leaf, u32 mask) void kvm_set_cpu_caps(void) { - unsigned int f_nx = is_efer_nx() ? F(NX) : 0; #ifdef CONFIG_X86_64 unsigned int f_gbpages = F(GBPAGES); unsigned int f_lm = F(LM); @@ -515,7 +489,7 @@ void kvm_set_cpu_caps(void) F(CX8) | F(APIC) | 0 /* Reserved */ | F(SYSCALL) | F(MTRR) | F(PGE) | F(MCA) | F(CMOV) | F(PAT) | F(PSE36) | 0 /* Reserved */ | - f_nx | 0 /* Reserved */ | F(MMXEXT) | F(MMX) | + F(NX) | 0 /* Reserved */ | F(MMXEXT) | F(MMX) | F(FXSR) | F(FXSR_OPT) | f_gbpages | F(RDTSCP) | 0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW) ); diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 0b38f944c6..41d2a53c5d 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1933,7 +1933,7 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *entry; - struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + struct kvm_vcpu_hv *hv_vcpu; entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_INTERFACE, 0); if (entry && entry->eax == HYPERV_CPUID_SIGNATURE_EAX) { diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index c4f4fa2332..47b7652702 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -2535,6 +2535,7 @@ static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync) { struct kvm_mmu_page *sp; + bool locked = false; /* * Force write-protection if the page is being tracked. Note, the page @@ -2557,9 +2558,34 @@ int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync) if (sp->unsync) continue; + /* + * TDP MMU page faults require an additional spinlock as they + * run with mmu_lock held for read, not write, and the unsync + * logic is not thread safe. Take the spinklock regardless of + * the MMU type to avoid extra conditionals/parameters, there's + * no meaningful penalty if mmu_lock is held for write. + */ + if (!locked) { + locked = true; + spin_lock(&vcpu->kvm->arch.mmu_unsync_pages_lock); + + /* + * Recheck after taking the spinlock, a different vCPU + * may have since marked the page unsync. A false + * positive on the unprotected check above is not + * possible as clearing sp->unsync _must_ hold mmu_lock + * for write, i.e. unsync cannot transition from 0->1 + * while this CPU holds mmu_lock for read (or write). + */ + if (READ_ONCE(sp->unsync)) + continue; + } + WARN_ON(sp->role.level != PG_LEVEL_4K); kvm_unsync_page(vcpu, sp); } + if (locked) + spin_unlock(&vcpu->kvm->arch.mmu_unsync_pages_lock); /* * We need to ensure that the marking of unsync pages is visible @@ -5537,6 +5563,8 @@ void kvm_mmu_init_vm(struct kvm *kvm) { struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker; + spin_lock_init(&kvm->arch.mmu_unsync_pages_lock); + if (!kvm_mmu_init_tdp_mmu(kvm)) /* * No smp_load/store wrappers needed here as we are in diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 0853370bd8..d80cb122b5 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -43,6 +43,7 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) if (!kvm->arch.tdp_mmu_enabled) return; + WARN_ON(!list_empty(&kvm->arch.tdp_mmu_pages)); WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots)); /* @@ -81,8 +82,6 @@ static void tdp_mmu_free_sp_rcu_callback(struct rcu_head *head) void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, bool shared) { - gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT); - kvm_lockdep_assert_mmu_lock_held(kvm, shared); if (!refcount_dec_and_test(&root->tdp_mmu_root_count)) @@ -94,7 +93,7 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, list_del_rcu(&root->link); spin_unlock(&kvm->arch.tdp_mmu_pages_lock); - zap_gfn_range(kvm, root, 0, max_gfn, false, false, shared); + zap_gfn_range(kvm, root, 0, -1ull, false, false, shared); call_rcu(&root->rcu_head, tdp_mmu_free_sp_rcu_callback); } @@ -724,13 +723,29 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t start, gfn_t end, bool can_yield, bool flush, bool shared) { + gfn_t max_gfn_host = 1ULL << (shadow_phys_bits - PAGE_SHIFT); + bool zap_all = (start == 0 && end >= max_gfn_host); struct tdp_iter iter; + /* + * No need to try to step down in the iterator when zapping all SPTEs, + * zapping the top-level non-leaf SPTEs will recurse on their children. + */ + int min_level = zap_all ? root->role.level : PG_LEVEL_4K; + + /* + * Bound the walk at host.MAXPHYADDR, guest accesses beyond that will + * hit a #PF(RSVD) and never get to an EPT Violation/Misconfig / #NPF, + * and so KVM will never install a SPTE for such addresses. + */ + end = min(end, max_gfn_host); + kvm_lockdep_assert_mmu_lock_held(kvm, shared); rcu_read_lock(); - tdp_root_for_each_pte(iter, root, start, end) { + for_each_tdp_pte_min_level(iter, root->spt, root->role.level, + min_level, start, end) { retry: if (can_yield && tdp_mmu_iter_cond_resched(kvm, &iter, flush, shared)) { @@ -744,9 +759,10 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, /* * If this is a non-last-level SPTE that covers a larger range * than should be zapped, continue, and zap the mappings at a - * lower level. + * lower level, except when zapping all SPTEs. */ - if ((iter.gfn < start || + if (!zap_all && + (iter.gfn < start || iter.gfn + KVM_PAGES_PER_HPAGE(iter.level) > end) && !is_last_spte(iter.old_spte, iter.level)) continue; @@ -794,12 +810,11 @@ bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, int as_id, gfn_t start, void kvm_tdp_mmu_zap_all(struct kvm *kvm) { - gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT); bool flush = false; int i; for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) - flush = kvm_tdp_mmu_zap_gfn_range(kvm, i, 0, max_gfn, + flush = kvm_tdp_mmu_zap_gfn_range(kvm, i, 0, -1ull, flush, false); if (flush) @@ -838,7 +853,6 @@ static struct kvm_mmu_page *next_invalidated_root(struct kvm *kvm, */ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) { - gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT); struct kvm_mmu_page *next_root; struct kvm_mmu_page *root; bool flush = false; @@ -854,8 +868,7 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) rcu_read_unlock(); - flush = zap_gfn_range(kvm, root, 0, max_gfn, true, flush, - true); + flush = zap_gfn_range(kvm, root, 0, -1ull, true, flush, true); /* * Put the reference acquired in diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 1a52134b0c..b3f77d18eb 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -330,6 +330,31 @@ void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu) vcpu_put(vcpu); } +#define EPTP_PA_MASK GENMASK_ULL(51, 12) + +static bool nested_ept_root_matches(hpa_t root_hpa, u64 root_eptp, u64 eptp) +{ + return VALID_PAGE(root_hpa) && + ((root_eptp & EPTP_PA_MASK) == (eptp & EPTP_PA_MASK)); +} + +static void nested_ept_invalidate_addr(struct kvm_vcpu *vcpu, gpa_t eptp, + gpa_t addr) +{ + uint i; + struct kvm_mmu_root_info *cached_root; + + WARN_ON_ONCE(!mmu_is_nested(vcpu)); + + for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { + cached_root = &vcpu->arch.mmu->prev_roots[i]; + + if (nested_ept_root_matches(cached_root->hpa, cached_root->pgd, + eptp)) + vcpu->arch.mmu->invlpg(vcpu, addr, cached_root->hpa); + } +} + static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) { @@ -342,10 +367,22 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu, vm_exit_reason = EXIT_REASON_PML_FULL; vmx->nested.pml_full = false; exit_qualification &= INTR_INFO_UNBLOCK_NMI; - } else if (fault->error_code & PFERR_RSVD_MASK) - vm_exit_reason = EXIT_REASON_EPT_MISCONFIG; - else - vm_exit_reason = EXIT_REASON_EPT_VIOLATION; + } else { + if (fault->error_code & PFERR_RSVD_MASK) + vm_exit_reason = EXIT_REASON_EPT_MISCONFIG; + else + vm_exit_reason = EXIT_REASON_EPT_VIOLATION; + + /* + * Although the caller (kvm_inject_emulated_page_fault) would + * have already synced the faulting address in the shadow EPT + * tables for the current EPTP12, we also need to sync it for + * any other cached EPTP02s based on the same EP4TA, since the + * TLB associates mappings to the EP4TA rather than the full EPTP. + */ + nested_ept_invalidate_addr(vcpu, vmcs12->ept_pointer, + fault->address); + } nested_vmx_vmexit(vcpu, vm_exit_reason, 0, exit_qualification); vmcs12->guest_physical_address = fault->address; @@ -5325,14 +5362,6 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu) return nested_vmx_succeed(vcpu); } -#define EPTP_PA_MASK GENMASK_ULL(51, 12) - -static bool nested_ept_root_matches(hpa_t root_hpa, u64 root_eptp, u64 eptp) -{ - return VALID_PAGE(root_hpa) && - ((root_eptp & EPTP_PA_MASK) == (eptp & EPTP_PA_MASK)); -} - /* Emulate the INVEPT instruction */ static int handle_invept(struct kvm_vcpu *vcpu) { @@ -5826,7 +5855,8 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu, if (is_nmi(intr_info)) return true; else if (is_page_fault(intr_info)) - return vcpu->arch.apf.host_apf_flags || !enable_ept; + return vcpu->arch.apf.host_apf_flags || + vmx_need_pf_intercept(vcpu); else if (is_debug(intr_info) && vcpu->guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index db88ed4f21..17a1cb4b05 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -522,7 +522,7 @@ static inline struct vmcs *alloc_vmcs(bool shadow) static inline bool vmx_has_waitpkg(struct vcpu_vmx *vmx) { - return vmx->secondary_exec_control & + return secondary_exec_controls_get(vmx) & SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE; } diff --git a/arch/x86/tools/chkobjdump.awk b/arch/x86/tools/chkobjdump.awk index fd1ab80be0..a4cf678cf5 100644 --- a/arch/x86/tools/chkobjdump.awk +++ b/arch/x86/tools/chkobjdump.awk @@ -10,6 +10,7 @@ BEGIN { /^GNU objdump/ { verstr = "" + gsub(/\(.*\)/, ""); for (i = 3; i <= NF; i++) if (match($(i), "^[0-9]")) { verstr = $(i); diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched index 64053d67a9..2f2158e05a 100644 --- a/block/Kconfig.iosched +++ b/block/Kconfig.iosched @@ -9,12 +9,6 @@ config MQ_IOSCHED_DEADLINE help MQ version of the deadline IO scheduler. -config MQ_IOSCHED_DEADLINE_CGROUP - tristate - default y - depends on MQ_IOSCHED_DEADLINE - depends on BLK_CGROUP - config MQ_IOSCHED_KYBER tristate "Kyber I/O scheduler" default y diff --git a/block/Makefile b/block/Makefile index bfbe4e13ca..1e1afa10f8 100644 --- a/block/Makefile +++ b/block/Makefile @@ -22,8 +22,6 @@ obj-$(CONFIG_BLK_CGROUP_IOPRIO) += blk-ioprio.o obj-$(CONFIG_BLK_CGROUP_IOLATENCY) += blk-iolatency.o obj-$(CONFIG_BLK_CGROUP_IOCOST) += blk-iocost.o obj-$(CONFIG_MQ_IOSCHED_DEADLINE) += mq-deadline.o -mq-deadline-y += mq-deadline-main.o -mq-deadline-$(CONFIG_MQ_IOSCHED_DEADLINE_CGROUP)+= mq-deadline-cgroup.o obj-$(CONFIG_MQ_IOSCHED_KYBER) += kyber-iosched.o bfq-y := bfq-iosched.o bfq-wf2q.o bfq-cgroup.o obj-$(CONFIG_IOSCHED_BFQ) += bfq.o diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 575d7a2e72..31fe9be179 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -790,6 +790,7 @@ static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu) struct blkcg_gq *parent = blkg->parent; struct blkg_iostat_set *bisc = per_cpu_ptr(blkg->iostat_cpu, cpu); struct blkg_iostat cur, delta; + unsigned long flags; unsigned int seq; /* fetch the current per-cpu values */ @@ -799,21 +800,21 @@ static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu) } while (u64_stats_fetch_retry(&bisc->sync, seq)); /* propagate percpu delta to global */ - u64_stats_update_begin(&blkg->iostat.sync); + flags = u64_stats_update_begin_irqsave(&blkg->iostat.sync); blkg_iostat_set(&delta, &cur); blkg_iostat_sub(&delta, &bisc->last); blkg_iostat_add(&blkg->iostat.cur, &delta); blkg_iostat_add(&bisc->last, &delta); - u64_stats_update_end(&blkg->iostat.sync); + u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags); /* propagate global delta to parent (unless that's root) */ if (parent && parent->parent) { - u64_stats_update_begin(&parent->iostat.sync); + flags = u64_stats_update_begin_irqsave(&parent->iostat.sync); blkg_iostat_set(&delta, &blkg->iostat.cur); blkg_iostat_sub(&delta, &blkg->iostat.last); blkg_iostat_add(&parent->iostat.cur, &delta); blkg_iostat_add(&blkg->iostat.last, &delta); - u64_stats_update_end(&parent->iostat.sync); + u64_stats_update_end_irqrestore(&parent->iostat.sync, flags); } } @@ -848,6 +849,7 @@ static void blkcg_fill_root_iostats(void) memset(&tmp, 0, sizeof(tmp)); for_each_possible_cpu(cpu) { struct disk_stats *cpu_dkstats; + unsigned long flags; cpu_dkstats = per_cpu_ptr(bdev->bd_stats, cpu); tmp.ios[BLKG_IOSTAT_READ] += @@ -864,9 +866,9 @@ static void blkcg_fill_root_iostats(void) tmp.bytes[BLKG_IOSTAT_DISCARD] += cpu_dkstats->sectors[STAT_DISCARD] << 9; - u64_stats_update_begin(&blkg->iostat.sync); + flags = u64_stats_update_begin_irqsave(&blkg->iostat.sync); blkg_iostat_set(&blkg->iostat.cur, &tmp); - u64_stats_update_end(&blkg->iostat.sync); + u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags); } } } diff --git a/block/blk-mq.c b/block/blk-mq.c index 2c4ac51e54..2fe396385a 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2994,10 +2994,12 @@ static void queue_set_hctx_shared(struct request_queue *q, bool shared) int i; queue_for_each_hw_ctx(q, hctx, i) { - if (shared) + if (shared) { hctx->flags |= BLK_MQ_F_TAG_QUEUE_SHARED; - else + } else { + blk_mq_tag_idle(hctx); hctx->flags &= ~BLK_MQ_F_TAG_QUEUE_SHARED; + } } } diff --git a/block/mq-deadline.c b/block/mq-deadline.c index 8eea2cbf2b..a09761cbdf 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -31,45 +31,132 @@ */ static const int read_expire = HZ / 2; /* max time before a read is submitted. */ static const int write_expire = 5 * HZ; /* ditto for writes, these limits are SOFT! */ +/* + * Time after which to dispatch lower priority requests even if higher + * priority requests are pending. + */ +static const int aging_expire = 10 * HZ; static const int writes_starved = 2; /* max times reads can starve a write */ static const int fifo_batch = 16; /* # of sequential requests treated as one by the above parameters. For throughput. */ +enum dd_data_dir { + DD_READ = READ, + DD_WRITE = WRITE, +}; + +enum { DD_DIR_COUNT = 2 }; + +enum dd_prio { + DD_RT_PRIO = 0, + DD_BE_PRIO = 1, + DD_IDLE_PRIO = 2, + DD_PRIO_MAX = 2, +}; + +enum { DD_PRIO_COUNT = 3 }; + +/* I/O statistics per I/O priority. */ +struct io_stats_per_prio { + local_t inserted; + local_t merged; + local_t dispatched; + local_t completed; +}; + +/* I/O statistics for all I/O priorities (enum dd_prio). */ +struct io_stats { + struct io_stats_per_prio stats[DD_PRIO_COUNT]; +}; + +/* + * Deadline scheduler data per I/O priority (enum dd_prio). Requests are + * present on both sort_list[] and fifo_list[]. + */ +struct dd_per_prio { + struct list_head dispatch; + struct rb_root sort_list[DD_DIR_COUNT]; + struct list_head fifo_list[DD_DIR_COUNT]; + /* Next request in FIFO order. Read, write or both are NULL. */ + struct request *next_rq[DD_DIR_COUNT]; +}; + struct deadline_data { /* * run time data */ - /* - * requests (deadline_rq s) are present on both sort_list and fifo_list - */ - struct rb_root sort_list[2]; - struct list_head fifo_list[2]; + struct dd_per_prio per_prio[DD_PRIO_COUNT]; - /* - * next in sort order. read, write or both are NULL - */ - struct request *next_rq[2]; + /* Data direction of latest dispatched request. */ + enum dd_data_dir last_dir; unsigned int batching; /* number of sequential requests made */ unsigned int starved; /* times reads have starved writes */ + struct io_stats __percpu *stats; + /* * settings that change how the i/o scheduler behaves */ - int fifo_expire[2]; + int fifo_expire[DD_DIR_COUNT]; int fifo_batch; int writes_starved; int front_merges; + u32 async_depth; + int aging_expire; spinlock_t lock; spinlock_t zone_lock; - struct list_head dispatch; +}; + +/* Count one event of type 'event_type' and with I/O priority 'prio' */ +#define dd_count(dd, event_type, prio) do { \ + struct io_stats *io_stats = get_cpu_ptr((dd)->stats); \ + \ + BUILD_BUG_ON(!__same_type((dd), struct deadline_data *)); \ + BUILD_BUG_ON(!__same_type((prio), enum dd_prio)); \ + local_inc(&io_stats->stats[(prio)].event_type); \ + put_cpu_ptr(io_stats); \ +} while (0) + +/* + * Returns the total number of dd_count(dd, event_type, prio) calls across all + * CPUs. No locking or barriers since it is fine if the returned sum is slightly + * outdated. + */ +#define dd_sum(dd, event_type, prio) ({ \ + unsigned int cpu; \ + u32 sum = 0; \ + \ + BUILD_BUG_ON(!__same_type((dd), struct deadline_data *)); \ + BUILD_BUG_ON(!__same_type((prio), enum dd_prio)); \ + for_each_present_cpu(cpu) \ + sum += local_read(&per_cpu_ptr((dd)->stats, cpu)-> \ + stats[(prio)].event_type); \ + sum; \ +}) + +/* Maps an I/O priority class to a deadline scheduler priority. */ +static const enum dd_prio ioprio_class_to_prio[] = { + [IOPRIO_CLASS_NONE] = DD_BE_PRIO, + [IOPRIO_CLASS_RT] = DD_RT_PRIO, + [IOPRIO_CLASS_BE] = DD_BE_PRIO, + [IOPRIO_CLASS_IDLE] = DD_IDLE_PRIO, }; static inline struct rb_root * -deadline_rb_root(struct deadline_data *dd, struct request *rq) +deadline_rb_root(struct dd_per_prio *per_prio, struct request *rq) { - return &dd->sort_list[rq_data_dir(rq)]; + return &per_prio->sort_list[rq_data_dir(rq)]; +} + +/* + * Returns the I/O priority class (IOPRIO_CLASS_*) that has been assigned to a + * request. + */ +static u8 dd_rq_ioclass(struct request *rq) +{ + return IOPRIO_PRIO_CLASS(req_get_ioprio(rq)); } /* @@ -87,38 +174,38 @@ deadline_latter_request(struct request *rq) } static void -deadline_add_rq_rb(struct deadline_data *dd, struct request *rq) +deadline_add_rq_rb(struct dd_per_prio *per_prio, struct request *rq) { - struct rb_root *root = deadline_rb_root(dd, rq); + struct rb_root *root = deadline_rb_root(per_prio, rq); elv_rb_add(root, rq); } static inline void -deadline_del_rq_rb(struct deadline_data *dd, struct request *rq) +deadline_del_rq_rb(struct dd_per_prio *per_prio, struct request *rq) { - const int data_dir = rq_data_dir(rq); + const enum dd_data_dir data_dir = rq_data_dir(rq); - if (dd->next_rq[data_dir] == rq) - dd->next_rq[data_dir] = deadline_latter_request(rq); + if (per_prio->next_rq[data_dir] == rq) + per_prio->next_rq[data_dir] = deadline_latter_request(rq); - elv_rb_del(deadline_rb_root(dd, rq), rq); + elv_rb_del(deadline_rb_root(per_prio, rq), rq); } /* * remove rq from rbtree and fifo. */ -static void deadline_remove_request(struct request_queue *q, struct request *rq) +static void deadline_remove_request(struct request_queue *q, + struct dd_per_prio *per_prio, + struct request *rq) { - struct deadline_data *dd = q->elevator->elevator_data; - list_del_init(&rq->queuelist); /* * We might not be on the rbtree, if we are doing an insert merge */ if (!RB_EMPTY_NODE(&rq->rb_node)) - deadline_del_rq_rb(dd, rq); + deadline_del_rq_rb(per_prio, rq); elv_rqhash_del(q, rq); if (q->last_merge == rq) @@ -129,19 +216,31 @@ static void dd_request_merged(struct request_queue *q, struct request *req, enum elv_merge type) { struct deadline_data *dd = q->elevator->elevator_data; + const u8 ioprio_class = dd_rq_ioclass(req); + const enum dd_prio prio = ioprio_class_to_prio[ioprio_class]; + struct dd_per_prio *per_prio = &dd->per_prio[prio]; /* * if the merge was a front merge, we need to reposition request */ if (type == ELEVATOR_FRONT_MERGE) { - elv_rb_del(deadline_rb_root(dd, req), req); - deadline_add_rq_rb(dd, req); + elv_rb_del(deadline_rb_root(per_prio, req), req); + deadline_add_rq_rb(per_prio, req); } } +/* + * Callback function that is invoked after @next has been merged into @req. + */ static void dd_merged_requests(struct request_queue *q, struct request *req, struct request *next) { + struct deadline_data *dd = q->elevator->elevator_data; + const u8 ioprio_class = dd_rq_ioclass(next); + const enum dd_prio prio = ioprio_class_to_prio[ioprio_class]; + + dd_count(dd, merged, prio); + /* * if next expires before rq, assign its expire time to rq * and move into next position (next will be deleted) in fifo @@ -157,34 +256,40 @@ static void dd_merged_requests(struct request_queue *q, struct request *req, /* * kill knowledge of next, this one is a goner */ - deadline_remove_request(q, next); + deadline_remove_request(q, &dd->per_prio[prio], next); } /* * move an entry to dispatch queue */ static void -deadline_move_request(struct deadline_data *dd, struct request *rq) +deadline_move_request(struct deadline_data *dd, struct dd_per_prio *per_prio, + struct request *rq) { - const int data_dir = rq_data_dir(rq); + const enum dd_data_dir data_dir = rq_data_dir(rq); - dd->next_rq[READ] = NULL; - dd->next_rq[WRITE] = NULL; - dd->next_rq[data_dir] = deadline_latter_request(rq); + per_prio->next_rq[data_dir] = deadline_latter_request(rq); /* * take it off the sort and fifo list */ - deadline_remove_request(rq->q, rq); + deadline_remove_request(rq->q, per_prio, rq); +} + +/* Number of requests queued for a given priority level. */ +static u32 dd_queued(struct deadline_data *dd, enum dd_prio prio) +{ + return dd_sum(dd, inserted, prio) - dd_sum(dd, completed, prio); } /* * deadline_check_fifo returns 0 if there are no expired requests on the fifo, * 1 otherwise. Requires !list_empty(&dd->fifo_list[data_dir]) */ -static inline int deadline_check_fifo(struct deadline_data *dd, int ddir) +static inline int deadline_check_fifo(struct dd_per_prio *per_prio, + enum dd_data_dir data_dir) { - struct request *rq = rq_entry_fifo(dd->fifo_list[ddir].next); + struct request *rq = rq_entry_fifo(per_prio->fifo_list[data_dir].next); /* * rq is expired! @@ -200,19 +305,17 @@ static inline int deadline_check_fifo(struct deadline_data *dd, int ddir) * dispatch using arrival ordered lists. */ static struct request * -deadline_fifo_request(struct deadline_data *dd, int data_dir) +deadline_fifo_request(struct deadline_data *dd, struct dd_per_prio *per_prio, + enum dd_data_dir data_dir) { struct request *rq; unsigned long flags; - if (WARN_ON_ONCE(data_dir != READ && data_dir != WRITE)) + if (list_empty(&per_prio->fifo_list[data_dir])) return NULL; - if (list_empty(&dd->fifo_list[data_dir])) - return NULL; - - rq = rq_entry_fifo(dd->fifo_list[data_dir].next); - if (data_dir == READ || !blk_queue_is_zoned(rq->q)) + rq = rq_entry_fifo(per_prio->fifo_list[data_dir].next); + if (data_dir == DD_READ || !blk_queue_is_zoned(rq->q)) return rq; /* @@ -220,7 +323,7 @@ deadline_fifo_request(struct deadline_data *dd, int data_dir) * an unlocked target zone. */ spin_lock_irqsave(&dd->zone_lock, flags); - list_for_each_entry(rq, &dd->fifo_list[WRITE], queuelist) { + list_for_each_entry(rq, &per_prio->fifo_list[DD_WRITE], queuelist) { if (blk_req_can_dispatch_to_zone(rq)) goto out; } @@ -236,19 +339,17 @@ deadline_fifo_request(struct deadline_data *dd, int data_dir) * dispatch using sector position sorted lists. */ static struct request * -deadline_next_request(struct deadline_data *dd, int data_dir) +deadline_next_request(struct deadline_data *dd, struct dd_per_prio *per_prio, + enum dd_data_dir data_dir) { struct request *rq; unsigned long flags; - if (WARN_ON_ONCE(data_dir != READ && data_dir != WRITE)) - return NULL; - - rq = dd->next_rq[data_dir]; + rq = per_prio->next_rq[data_dir]; if (!rq) return NULL; - if (data_dir == READ || !blk_queue_is_zoned(rq->q)) + if (data_dir == DD_READ || !blk_queue_is_zoned(rq->q)) return rq; /* @@ -268,30 +369,32 @@ deadline_next_request(struct deadline_data *dd, int data_dir) /* * deadline_dispatch_requests selects the best request according to - * read/write expire, fifo_batch, etc + * read/write expire, fifo_batch, etc and with a start time <= @latest. */ -static struct request *__dd_dispatch_request(struct deadline_data *dd) +static struct request *__dd_dispatch_request(struct deadline_data *dd, + struct dd_per_prio *per_prio, + u64 latest_start_ns) { struct request *rq, *next_rq; - bool reads, writes; - int data_dir; + enum dd_data_dir data_dir; + enum dd_prio prio; + u8 ioprio_class; - if (!list_empty(&dd->dispatch)) { - rq = list_first_entry(&dd->dispatch, struct request, queuelist); + lockdep_assert_held(&dd->lock); + + if (!list_empty(&per_prio->dispatch)) { + rq = list_first_entry(&per_prio->dispatch, struct request, + queuelist); + if (rq->start_time_ns > latest_start_ns) + return NULL; list_del_init(&rq->queuelist); goto done; } - reads = !list_empty(&dd->fifo_list[READ]); - writes = !list_empty(&dd->fifo_list[WRITE]); - /* * batches are currently reads XOR writes */ - rq = deadline_next_request(dd, WRITE); - if (!rq) - rq = deadline_next_request(dd, READ); - + rq = deadline_next_request(dd, per_prio, dd->last_dir); if (rq && dd->batching < dd->fifo_batch) /* we have a next request are still entitled to batch */ goto dispatch_request; @@ -301,14 +404,14 @@ static struct request *__dd_dispatch_request(struct deadline_data *dd) * data direction (read / write) */ - if (reads) { - BUG_ON(RB_EMPTY_ROOT(&dd->sort_list[READ])); + if (!list_empty(&per_prio->fifo_list[DD_READ])) { + BUG_ON(RB_EMPTY_ROOT(&per_prio->sort_list[DD_READ])); - if (deadline_fifo_request(dd, WRITE) && + if (deadline_fifo_request(dd, per_prio, DD_WRITE) && (dd->starved++ >= dd->writes_starved)) goto dispatch_writes; - data_dir = READ; + data_dir = DD_READ; goto dispatch_find_request; } @@ -317,13 +420,13 @@ static struct request *__dd_dispatch_request(struct deadline_data *dd) * there are either no reads or writes have been starved */ - if (writes) { + if (!list_empty(&per_prio->fifo_list[DD_WRITE])) { dispatch_writes: - BUG_ON(RB_EMPTY_ROOT(&dd->sort_list[WRITE])); + BUG_ON(RB_EMPTY_ROOT(&per_prio->sort_list[DD_WRITE])); dd->starved = 0; - data_dir = WRITE; + data_dir = DD_WRITE; goto dispatch_find_request; } @@ -334,14 +437,14 @@ static struct request *__dd_dispatch_request(struct deadline_data *dd) /* * we are not running a batch, find best request for selected data_dir */ - next_rq = deadline_next_request(dd, data_dir); - if (deadline_check_fifo(dd, data_dir) || !next_rq) { + next_rq = deadline_next_request(dd, per_prio, data_dir); + if (deadline_check_fifo(per_prio, data_dir) || !next_rq) { /* * A deadline has expired, the last request was in the other * direction, or we have run out of higher-sectored requests. * Start again from the request with the earliest expiry time. */ - rq = deadline_fifo_request(dd, data_dir); + rq = deadline_fifo_request(dd, per_prio, data_dir); } else { /* * The last req was the same dir and we have a next request in @@ -357,15 +460,21 @@ static struct request *__dd_dispatch_request(struct deadline_data *dd) if (!rq) return NULL; + dd->last_dir = data_dir; dd->batching = 0; dispatch_request: + if (rq->start_time_ns > latest_start_ns) + return NULL; /* * rq is the selected appropriate request. */ dd->batching++; - deadline_move_request(dd, rq); + deadline_move_request(dd, per_prio, rq); done: + ioprio_class = dd_rq_ioclass(rq); + prio = ioprio_class_to_prio[ioprio_class]; + dd_count(dd, dispatched, prio); /* * If the request needs its target zone locked, do it. */ @@ -375,6 +484,8 @@ static struct request *__dd_dispatch_request(struct deadline_data *dd) } /* + * Called from blk_mq_run_hw_queue() -> __blk_mq_sched_dispatch_requests(). + * * One confusing aspect here is that we get called for a specific * hardware queue, but we may return a request that is for a * different hardware queue. This is because mq-deadline has shared @@ -383,21 +494,88 @@ static struct request *__dd_dispatch_request(struct deadline_data *dd) static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx) { struct deadline_data *dd = hctx->queue->elevator->elevator_data; - struct request *rq; + const u64 now_ns = ktime_get_ns(); + struct request *rq = NULL; + enum dd_prio prio; spin_lock(&dd->lock); - rq = __dd_dispatch_request(dd); + /* + * Start with dispatching requests whose deadline expired more than + * aging_expire jiffies ago. + */ + for (prio = DD_BE_PRIO; prio <= DD_PRIO_MAX; prio++) { + rq = __dd_dispatch_request(dd, &dd->per_prio[prio], now_ns - + jiffies_to_nsecs(dd->aging_expire)); + if (rq) + goto unlock; + } + /* + * Next, dispatch requests in priority order. Ignore lower priority + * requests if any higher priority requests are pending. + */ + for (prio = 0; prio <= DD_PRIO_MAX; prio++) { + rq = __dd_dispatch_request(dd, &dd->per_prio[prio], now_ns); + if (rq || dd_queued(dd, prio)) + break; + } + +unlock: spin_unlock(&dd->lock); return rq; } -static void dd_exit_queue(struct elevator_queue *e) +/* + * Called by __blk_mq_alloc_request(). The shallow_depth value set by this + * function is used by __blk_mq_get_tag(). + */ +static void dd_limit_depth(unsigned int op, struct blk_mq_alloc_data *data) +{ + struct deadline_data *dd = data->q->elevator->elevator_data; + + /* Do not throttle synchronous reads. */ + if (op_is_sync(op) && !op_is_write(op)) + return; + + /* + * Throttle asynchronous requests and writes such that these requests + * do not block the allocation of synchronous requests. + */ + data->shallow_depth = dd->async_depth; +} + +/* Called by blk_mq_update_nr_requests(). */ +static void dd_depth_updated(struct blk_mq_hw_ctx *hctx) +{ + struct request_queue *q = hctx->queue; + struct deadline_data *dd = q->elevator->elevator_data; + struct blk_mq_tags *tags = hctx->sched_tags; + + dd->async_depth = max(1UL, 3 * q->nr_requests / 4); + + sbitmap_queue_min_shallow_depth(tags->bitmap_tags, dd->async_depth); +} + +/* Called by blk_mq_init_hctx() and blk_mq_init_sched(). */ +static int dd_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) +{ + dd_depth_updated(hctx); + return 0; +} + +static void dd_exit_sched(struct elevator_queue *e) { struct deadline_data *dd = e->elevator_data; + enum dd_prio prio; - BUG_ON(!list_empty(&dd->fifo_list[READ])); - BUG_ON(!list_empty(&dd->fifo_list[WRITE])); + for (prio = 0; prio <= DD_PRIO_MAX; prio++) { + struct dd_per_prio *per_prio = &dd->per_prio[prio]; + + WARN_ON_ONCE(!list_empty(&per_prio->fifo_list[DD_READ])); + WARN_ON_ONCE(!list_empty(&per_prio->fifo_list[DD_WRITE])); + } + + free_percpu(dd->stats); kfree(dd); } @@ -405,50 +583,76 @@ static void dd_exit_queue(struct elevator_queue *e) /* * initialize elevator private data (deadline_data). */ -static int dd_init_queue(struct request_queue *q, struct elevator_type *e) +static int dd_init_sched(struct request_queue *q, struct elevator_type *e) { struct deadline_data *dd; struct elevator_queue *eq; + enum dd_prio prio; + int ret = -ENOMEM; eq = elevator_alloc(q, e); if (!eq) - return -ENOMEM; + return ret; dd = kzalloc_node(sizeof(*dd), GFP_KERNEL, q->node); - if (!dd) { - kobject_put(&eq->kobj); - return -ENOMEM; - } + if (!dd) + goto put_eq; + eq->elevator_data = dd; - INIT_LIST_HEAD(&dd->fifo_list[READ]); - INIT_LIST_HEAD(&dd->fifo_list[WRITE]); - dd->sort_list[READ] = RB_ROOT; - dd->sort_list[WRITE] = RB_ROOT; - dd->fifo_expire[READ] = read_expire; - dd->fifo_expire[WRITE] = write_expire; + dd->stats = alloc_percpu_gfp(typeof(*dd->stats), + GFP_KERNEL | __GFP_ZERO); + if (!dd->stats) + goto free_dd; + + for (prio = 0; prio <= DD_PRIO_MAX; prio++) { + struct dd_per_prio *per_prio = &dd->per_prio[prio]; + + INIT_LIST_HEAD(&per_prio->dispatch); + INIT_LIST_HEAD(&per_prio->fifo_list[DD_READ]); + INIT_LIST_HEAD(&per_prio->fifo_list[DD_WRITE]); + per_prio->sort_list[DD_READ] = RB_ROOT; + per_prio->sort_list[DD_WRITE] = RB_ROOT; + } + dd->fifo_expire[DD_READ] = read_expire; + dd->fifo_expire[DD_WRITE] = write_expire; dd->writes_starved = writes_starved; dd->front_merges = 1; + dd->last_dir = DD_WRITE; dd->fifo_batch = fifo_batch; + dd->aging_expire = aging_expire; spin_lock_init(&dd->lock); spin_lock_init(&dd->zone_lock); - INIT_LIST_HEAD(&dd->dispatch); q->elevator = eq; return 0; + +free_dd: + kfree(dd); + +put_eq: + kobject_put(&eq->kobj); + return ret; } +/* + * Try to merge @bio into an existing request. If @bio has been merged into + * an existing request, store the pointer to that request into *@rq. + */ static int dd_request_merge(struct request_queue *q, struct request **rq, struct bio *bio) { struct deadline_data *dd = q->elevator->elevator_data; + const u8 ioprio_class = IOPRIO_PRIO_CLASS(bio->bi_ioprio); + const enum dd_prio prio = ioprio_class_to_prio[ioprio_class]; + struct dd_per_prio *per_prio = &dd->per_prio[prio]; sector_t sector = bio_end_sector(bio); struct request *__rq; if (!dd->front_merges) return ELEVATOR_NO_MERGE; - __rq = elv_rb_find(&dd->sort_list[bio_data_dir(bio)], sector); + __rq = elv_rb_find(&per_prio->sort_list[bio_data_dir(bio)], sector); if (__rq) { BUG_ON(sector != blk_rq_pos(__rq)); @@ -461,6 +665,10 @@ static int dd_request_merge(struct request_queue *q, struct request **rq, return ELEVATOR_NO_MERGE; } +/* + * Attempt to merge a bio into an existing request. This function is called + * before @bio is associated with a request. + */ static bool dd_bio_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs) { @@ -486,7 +694,14 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, { struct request_queue *q = hctx->queue; struct deadline_data *dd = q->elevator->elevator_data; - const int data_dir = rq_data_dir(rq); + const enum dd_data_dir data_dir = rq_data_dir(rq); + u16 ioprio = req_get_ioprio(rq); + u8 ioprio_class = IOPRIO_PRIO_CLASS(ioprio); + struct dd_per_prio *per_prio; + enum dd_prio prio; + LIST_HEAD(free); + + lockdep_assert_held(&dd->lock); /* * This may be a requeue of a write request that has locked its @@ -494,15 +709,21 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, */ blk_req_zone_write_unlock(rq); - if (blk_mq_sched_try_insert_merge(q, rq)) + prio = ioprio_class_to_prio[ioprio_class]; + dd_count(dd, inserted, prio); + + if (blk_mq_sched_try_insert_merge(q, rq, &free)) { + blk_mq_free_requests(&free); return; + } trace_block_rq_insert(rq); + per_prio = &dd->per_prio[prio]; if (at_head) { - list_add(&rq->queuelist, &dd->dispatch); + list_add(&rq->queuelist, &per_prio->dispatch); } else { - deadline_add_rq_rb(dd, rq); + deadline_add_rq_rb(per_prio, rq); if (rq_mergeable(rq)) { elv_rqhash_add(q, rq); @@ -514,10 +735,13 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, * set expire time and add to fifo list */ rq->fifo_time = jiffies + dd->fifo_expire[data_dir]; - list_add_tail(&rq->queuelist, &dd->fifo_list[data_dir]); + list_add_tail(&rq->queuelist, &per_prio->fifo_list[data_dir]); } } +/* + * Called from blk_mq_sched_insert_request() or blk_mq_sched_insert_requests(). + */ static void dd_insert_requests(struct blk_mq_hw_ctx *hctx, struct list_head *list, bool at_head) { @@ -544,6 +768,8 @@ static void dd_prepare_request(struct request *rq) } /* + * Callback from inside blk_mq_free_request(). + * * For zoned block devices, write unlock the target zone of * completed write requests. Do this while holding the zone lock * spinlock so that the zone is never unlocked while deadline_fifo_request() @@ -560,83 +786,94 @@ static void dd_prepare_request(struct request *rq) static void dd_finish_request(struct request *rq) { struct request_queue *q = rq->q; + struct deadline_data *dd = q->elevator->elevator_data; + const u8 ioprio_class = dd_rq_ioclass(rq); + const enum dd_prio prio = ioprio_class_to_prio[ioprio_class]; + struct dd_per_prio *per_prio = &dd->per_prio[prio]; + + dd_count(dd, completed, prio); if (blk_queue_is_zoned(q)) { - struct deadline_data *dd = q->elevator->elevator_data; unsigned long flags; spin_lock_irqsave(&dd->zone_lock, flags); blk_req_zone_write_unlock(rq); - if (!list_empty(&dd->fifo_list[WRITE])) + if (!list_empty(&per_prio->fifo_list[DD_WRITE])) blk_mq_sched_mark_restart_hctx(rq->mq_hctx); spin_unlock_irqrestore(&dd->zone_lock, flags); } } +static bool dd_has_work_for_prio(struct dd_per_prio *per_prio) +{ + return !list_empty_careful(&per_prio->dispatch) || + !list_empty_careful(&per_prio->fifo_list[DD_READ]) || + !list_empty_careful(&per_prio->fifo_list[DD_WRITE]); +} + static bool dd_has_work(struct blk_mq_hw_ctx *hctx) { struct deadline_data *dd = hctx->queue->elevator->elevator_data; + enum dd_prio prio; - return !list_empty_careful(&dd->dispatch) || - !list_empty_careful(&dd->fifo_list[0]) || - !list_empty_careful(&dd->fifo_list[1]); + for (prio = 0; prio <= DD_PRIO_MAX; prio++) + if (dd_has_work_for_prio(&dd->per_prio[prio])) + return true; + + return false; } /* * sysfs parts below */ -static ssize_t -deadline_var_show(int var, char *page) -{ - return sprintf(page, "%d\n", var); -} - -static void -deadline_var_store(int *var, const char *page) -{ - char *p = (char *) page; - - *var = simple_strtol(p, &p, 10); -} - -#define SHOW_FUNCTION(__FUNC, __VAR, __CONV) \ +#define SHOW_INT(__FUNC, __VAR) \ static ssize_t __FUNC(struct elevator_queue *e, char *page) \ { \ struct deadline_data *dd = e->elevator_data; \ - int __data = __VAR; \ - if (__CONV) \ - __data = jiffies_to_msecs(__data); \ - return deadline_var_show(__data, (page)); \ + \ + return sysfs_emit(page, "%d\n", __VAR); \ } -SHOW_FUNCTION(deadline_read_expire_show, dd->fifo_expire[READ], 1); -SHOW_FUNCTION(deadline_write_expire_show, dd->fifo_expire[WRITE], 1); -SHOW_FUNCTION(deadline_writes_starved_show, dd->writes_starved, 0); -SHOW_FUNCTION(deadline_front_merges_show, dd->front_merges, 0); -SHOW_FUNCTION(deadline_fifo_batch_show, dd->fifo_batch, 0); -#undef SHOW_FUNCTION +#define SHOW_JIFFIES(__FUNC, __VAR) SHOW_INT(__FUNC, jiffies_to_msecs(__VAR)) +SHOW_JIFFIES(deadline_read_expire_show, dd->fifo_expire[DD_READ]); +SHOW_JIFFIES(deadline_write_expire_show, dd->fifo_expire[DD_WRITE]); +SHOW_JIFFIES(deadline_aging_expire_show, dd->aging_expire); +SHOW_INT(deadline_writes_starved_show, dd->writes_starved); +SHOW_INT(deadline_front_merges_show, dd->front_merges); +SHOW_INT(deadline_async_depth_show, dd->front_merges); +SHOW_INT(deadline_fifo_batch_show, dd->fifo_batch); +#undef SHOW_INT +#undef SHOW_JIFFIES #define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV) \ static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count) \ { \ struct deadline_data *dd = e->elevator_data; \ - int __data; \ - deadline_var_store(&__data, (page)); \ + int __data, __ret; \ + \ + __ret = kstrtoint(page, 0, &__data); \ + if (__ret < 0) \ + return __ret; \ if (__data < (MIN)) \ __data = (MIN); \ else if (__data > (MAX)) \ __data = (MAX); \ - if (__CONV) \ - *(__PTR) = msecs_to_jiffies(__data); \ - else \ - *(__PTR) = __data; \ + *(__PTR) = __CONV(__data); \ return count; \ } -STORE_FUNCTION(deadline_read_expire_store, &dd->fifo_expire[READ], 0, INT_MAX, 1); -STORE_FUNCTION(deadline_write_expire_store, &dd->fifo_expire[WRITE], 0, INT_MAX, 1); -STORE_FUNCTION(deadline_writes_starved_store, &dd->writes_starved, INT_MIN, INT_MAX, 0); -STORE_FUNCTION(deadline_front_merges_store, &dd->front_merges, 0, 1, 0); -STORE_FUNCTION(deadline_fifo_batch_store, &dd->fifo_batch, 0, INT_MAX, 0); +#define STORE_INT(__FUNC, __PTR, MIN, MAX) \ + STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, ) +#define STORE_JIFFIES(__FUNC, __PTR, MIN, MAX) \ + STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, msecs_to_jiffies) +STORE_JIFFIES(deadline_read_expire_store, &dd->fifo_expire[DD_READ], 0, INT_MAX); +STORE_JIFFIES(deadline_write_expire_store, &dd->fifo_expire[DD_WRITE], 0, INT_MAX); +STORE_JIFFIES(deadline_aging_expire_store, &dd->aging_expire, 0, INT_MAX); +STORE_INT(deadline_writes_starved_store, &dd->writes_starved, INT_MIN, INT_MAX); +STORE_INT(deadline_front_merges_store, &dd->front_merges, 0, 1); +STORE_INT(deadline_async_depth_store, &dd->front_merges, 1, INT_MAX); +STORE_INT(deadline_fifo_batch_store, &dd->fifo_batch, 0, INT_MAX); #undef STORE_FUNCTION +#undef STORE_INT +#undef STORE_JIFFIES #define DD_ATTR(name) \ __ATTR(name, 0644, deadline_##name##_show, deadline_##name##_store) @@ -646,21 +883,24 @@ static struct elv_fs_entry deadline_attrs[] = { DD_ATTR(write_expire), DD_ATTR(writes_starved), DD_ATTR(front_merges), + DD_ATTR(async_depth), DD_ATTR(fifo_batch), + DD_ATTR(aging_expire), __ATTR_NULL }; #ifdef CONFIG_BLK_DEBUG_FS -#define DEADLINE_DEBUGFS_DDIR_ATTRS(ddir, name) \ +#define DEADLINE_DEBUGFS_DDIR_ATTRS(prio, data_dir, name) \ static void *deadline_##name##_fifo_start(struct seq_file *m, \ loff_t *pos) \ __acquires(&dd->lock) \ { \ struct request_queue *q = m->private; \ struct deadline_data *dd = q->elevator->elevator_data; \ + struct dd_per_prio *per_prio = &dd->per_prio[prio]; \ \ spin_lock(&dd->lock); \ - return seq_list_start(&dd->fifo_list[ddir], *pos); \ + return seq_list_start(&per_prio->fifo_list[data_dir], *pos); \ } \ \ static void *deadline_##name##_fifo_next(struct seq_file *m, void *v, \ @@ -668,8 +908,9 @@ static void *deadline_##name##_fifo_next(struct seq_file *m, void *v, \ { \ struct request_queue *q = m->private; \ struct deadline_data *dd = q->elevator->elevator_data; \ + struct dd_per_prio *per_prio = &dd->per_prio[prio]; \ \ - return seq_list_next(v, &dd->fifo_list[ddir], pos); \ + return seq_list_next(v, &per_prio->fifo_list[data_dir], pos); \ } \ \ static void deadline_##name##_fifo_stop(struct seq_file *m, void *v) \ @@ -693,14 +934,20 @@ static int deadline_##name##_next_rq_show(void *data, \ { \ struct request_queue *q = data; \ struct deadline_data *dd = q->elevator->elevator_data; \ - struct request *rq = dd->next_rq[ddir]; \ + struct dd_per_prio *per_prio = &dd->per_prio[prio]; \ + struct request *rq = per_prio->next_rq[data_dir]; \ \ if (rq) \ __blk_mq_debugfs_rq_show(m, rq); \ return 0; \ } -DEADLINE_DEBUGFS_DDIR_ATTRS(READ, read) -DEADLINE_DEBUGFS_DDIR_ATTRS(WRITE, write) + +DEADLINE_DEBUGFS_DDIR_ATTRS(DD_RT_PRIO, DD_READ, read0); +DEADLINE_DEBUGFS_DDIR_ATTRS(DD_RT_PRIO, DD_WRITE, write0); +DEADLINE_DEBUGFS_DDIR_ATTRS(DD_BE_PRIO, DD_READ, read1); +DEADLINE_DEBUGFS_DDIR_ATTRS(DD_BE_PRIO, DD_WRITE, write1); +DEADLINE_DEBUGFS_DDIR_ATTRS(DD_IDLE_PRIO, DD_READ, read2); +DEADLINE_DEBUGFS_DDIR_ATTRS(DD_IDLE_PRIO, DD_WRITE, write2); #undef DEADLINE_DEBUGFS_DDIR_ATTRS static int deadline_batching_show(void *data, struct seq_file *m) @@ -721,49 +968,114 @@ static int deadline_starved_show(void *data, struct seq_file *m) return 0; } -static void *deadline_dispatch_start(struct seq_file *m, loff_t *pos) - __acquires(&dd->lock) +static int dd_async_depth_show(void *data, struct seq_file *m) { - struct request_queue *q = m->private; + struct request_queue *q = data; struct deadline_data *dd = q->elevator->elevator_data; - spin_lock(&dd->lock); - return seq_list_start(&dd->dispatch, *pos); + seq_printf(m, "%u\n", dd->async_depth); + return 0; } -static void *deadline_dispatch_next(struct seq_file *m, void *v, loff_t *pos) +static int dd_queued_show(void *data, struct seq_file *m) { - struct request_queue *q = m->private; + struct request_queue *q = data; struct deadline_data *dd = q->elevator->elevator_data; - return seq_list_next(v, &dd->dispatch, pos); + seq_printf(m, "%u %u %u\n", dd_queued(dd, DD_RT_PRIO), + dd_queued(dd, DD_BE_PRIO), + dd_queued(dd, DD_IDLE_PRIO)); + return 0; } -static void deadline_dispatch_stop(struct seq_file *m, void *v) - __releases(&dd->lock) +/* Number of requests owned by the block driver for a given priority. */ +static u32 dd_owned_by_driver(struct deadline_data *dd, enum dd_prio prio) { - struct request_queue *q = m->private; + return dd_sum(dd, dispatched, prio) + dd_sum(dd, merged, prio) + - dd_sum(dd, completed, prio); +} + +static int dd_owned_by_driver_show(void *data, struct seq_file *m) +{ + struct request_queue *q = data; struct deadline_data *dd = q->elevator->elevator_data; - spin_unlock(&dd->lock); + seq_printf(m, "%u %u %u\n", dd_owned_by_driver(dd, DD_RT_PRIO), + dd_owned_by_driver(dd, DD_BE_PRIO), + dd_owned_by_driver(dd, DD_IDLE_PRIO)); + return 0; } -static const struct seq_operations deadline_dispatch_seq_ops = { - .start = deadline_dispatch_start, - .next = deadline_dispatch_next, - .stop = deadline_dispatch_stop, - .show = blk_mq_debugfs_rq_show, -}; +#define DEADLINE_DISPATCH_ATTR(prio) \ +static void *deadline_dispatch##prio##_start(struct seq_file *m, \ + loff_t *pos) \ + __acquires(&dd->lock) \ +{ \ + struct request_queue *q = m->private; \ + struct deadline_data *dd = q->elevator->elevator_data; \ + struct dd_per_prio *per_prio = &dd->per_prio[prio]; \ + \ + spin_lock(&dd->lock); \ + return seq_list_start(&per_prio->dispatch, *pos); \ +} \ + \ +static void *deadline_dispatch##prio##_next(struct seq_file *m, \ + void *v, loff_t *pos) \ +{ \ + struct request_queue *q = m->private; \ + struct deadline_data *dd = q->elevator->elevator_data; \ + struct dd_per_prio *per_prio = &dd->per_prio[prio]; \ + \ + return seq_list_next(v, &per_prio->dispatch, pos); \ +} \ + \ +static void deadline_dispatch##prio##_stop(struct seq_file *m, void *v) \ + __releases(&dd->lock) \ +{ \ + struct request_queue *q = m->private; \ + struct deadline_data *dd = q->elevator->elevator_data; \ + \ + spin_unlock(&dd->lock); \ +} \ + \ +static const struct seq_operations deadline_dispatch##prio##_seq_ops = { \ + .start = deadline_dispatch##prio##_start, \ + .next = deadline_dispatch##prio##_next, \ + .stop = deadline_dispatch##prio##_stop, \ + .show = blk_mq_debugfs_rq_show, \ +} -#define DEADLINE_QUEUE_DDIR_ATTRS(name) \ - {#name "_fifo_list", 0400, .seq_ops = &deadline_##name##_fifo_seq_ops}, \ +DEADLINE_DISPATCH_ATTR(0); +DEADLINE_DISPATCH_ATTR(1); +DEADLINE_DISPATCH_ATTR(2); +#undef DEADLINE_DISPATCH_ATTR + +#define DEADLINE_QUEUE_DDIR_ATTRS(name) \ + {#name "_fifo_list", 0400, \ + .seq_ops = &deadline_##name##_fifo_seq_ops} +#define DEADLINE_NEXT_RQ_ATTR(name) \ {#name "_next_rq", 0400, deadline_##name##_next_rq_show} static const struct blk_mq_debugfs_attr deadline_queue_debugfs_attrs[] = { - DEADLINE_QUEUE_DDIR_ATTRS(read), - DEADLINE_QUEUE_DDIR_ATTRS(write), + DEADLINE_QUEUE_DDIR_ATTRS(read0), + DEADLINE_QUEUE_DDIR_ATTRS(write0), + DEADLINE_QUEUE_DDIR_ATTRS(read1), + DEADLINE_QUEUE_DDIR_ATTRS(write1), + DEADLINE_QUEUE_DDIR_ATTRS(read2), + DEADLINE_QUEUE_DDIR_ATTRS(write2), + DEADLINE_NEXT_RQ_ATTR(read0), + DEADLINE_NEXT_RQ_ATTR(write0), + DEADLINE_NEXT_RQ_ATTR(read1), + DEADLINE_NEXT_RQ_ATTR(write1), + DEADLINE_NEXT_RQ_ATTR(read2), + DEADLINE_NEXT_RQ_ATTR(write2), {"batching", 0400, deadline_batching_show}, {"starved", 0400, deadline_starved_show}, - {"dispatch", 0400, .seq_ops = &deadline_dispatch_seq_ops}, + {"async_depth", 0400, dd_async_depth_show}, + {"dispatch0", 0400, .seq_ops = &deadline_dispatch0_seq_ops}, + {"dispatch1", 0400, .seq_ops = &deadline_dispatch1_seq_ops}, + {"dispatch2", 0400, .seq_ops = &deadline_dispatch2_seq_ops}, + {"owned_by_driver", 0400, dd_owned_by_driver_show}, + {"queued", 0400, dd_queued_show}, {}, }; #undef DEADLINE_QUEUE_DDIR_ATTRS @@ -771,6 +1083,8 @@ static const struct blk_mq_debugfs_attr deadline_queue_debugfs_attrs[] = { static struct elevator_type mq_deadline = { .ops = { + .depth_updated = dd_depth_updated, + .limit_depth = dd_limit_depth, .insert_requests = dd_insert_requests, .dispatch_request = dd_dispatch_request, .prepare_request = dd_prepare_request, @@ -782,8 +1096,9 @@ static struct elevator_type mq_deadline = { .requests_merged = dd_merged_requests, .request_merged = dd_request_merged, .has_work = dd_has_work, - .init_sched = dd_init_queue, - .exit_sched = dd_exit_queue, + .init_sched = dd_init_sched, + .exit_sched = dd_exit_sched, + .init_hctx = dd_init_hctx, }, #ifdef CONFIG_BLK_DEBUG_FS @@ -810,6 +1125,6 @@ static void __exit deadline_exit(void) module_init(deadline_init); module_exit(deadline_exit); -MODULE_AUTHOR("Jens Axboe"); +MODULE_AUTHOR("Jens Axboe, Damien Le Moal and Bart Van Assche"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("MQ deadline IO scheduler"); diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 23d9a09d70..a3ef6cce64 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -3021,6 +3021,9 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc, struct acpi_nfit_memory_map *memdev = nfit_memdev->memdev; struct nd_mapping_desc *mapping; + /* range index 0 == unmapped in SPA or invalid-SPA */ + if (memdev->range_index == 0 || spa->range_index == 0) + continue; if (memdev->range_index != spa->range_index) continue; if (count >= ND_MAX_MAPPINGS) { diff --git a/drivers/base/core.c b/drivers/base/core.c index f6360490a4..6c0ef9d55a 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2837,6 +2837,7 @@ void device_initialize(struct device *dev) device_pm_init(dev); set_dev_node(dev, -1); #ifdef CONFIG_GENERIC_MSI_IRQ + raw_spin_lock_init(&dev->msi_lock); INIT_LIST_HEAD(&dev->msi_list); #endif INIT_LIST_HEAD(&dev->links.consumers); diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index b7d663736d..19f5d5a8b1 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -239,8 +239,8 @@ static void nbd_dev_remove(struct nbd_device *nbd) if (disk) { del_gendisk(disk); - blk_mq_free_tag_set(&nbd->tag_set); blk_cleanup_disk(disk); + blk_mq_free_tag_set(&nbd->tag_set); } /* @@ -818,6 +818,10 @@ static bool nbd_clear_req(struct request *req, void *data, bool reserved) { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req); + /* don't abort one completed request */ + if (blk_mq_request_completed(req)) + return true; + mutex_lock(&cmd->lock); cmd->status = BLK_STS_IOERR; mutex_unlock(&cmd->lock); @@ -2004,15 +2008,19 @@ static void nbd_disconnect_and_put(struct nbd_device *nbd) { mutex_lock(&nbd->config_lock); nbd_disconnect(nbd); - nbd_clear_sock(nbd); - mutex_unlock(&nbd->config_lock); + sock_shutdown(nbd); /* * Make sure recv thread has finished, so it does not drop the last * config ref and try to destroy the workqueue from inside the work - * queue. + * queue. And this also ensure that we can safely call nbd_clear_que() + * to cancel the inflight I/Os. */ if (nbd->recv_workq) flush_workqueue(nbd->recv_workq); + nbd_clear_que(nbd); + nbd->task_setup = NULL; + mutex_unlock(&nbd->config_lock); + if (test_and_clear_bit(NBD_RT_HAS_CONFIG_REF, &nbd->config->runtime_flags)) nbd_config_put(nbd); diff --git a/drivers/dax/super.c b/drivers/dax/super.c index 5fa6ae9dbc..44736cbd44 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -313,7 +313,7 @@ long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, return -ENXIO; if (nr_pages < 0) - return nr_pages; + return -EINVAL; avail = dax_dev->ops->direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn); diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c index 7bf0a7acae..2363fee921 100644 --- a/drivers/firmware/efi/libstub/arm64-stub.c +++ b/drivers/firmware/efi/libstub/arm64-stub.c @@ -35,15 +35,48 @@ efi_status_t check_platform_features(void) } /* - * Although relocatable kernels can fix up the misalignment with respect to - * MIN_KIMG_ALIGN, the resulting virtual text addresses are subtly out of - * sync with those recorded in the vmlinux when kaslr is disabled but the - * image required relocation anyway. Therefore retain 2M alignment unless - * KASLR is in use. + * Distro versions of GRUB may ignore the BSS allocation entirely (i.e., fail + * to provide space, and fail to zero it). Check for this condition by double + * checking that the first and the last byte of the image are covered by the + * same EFI memory map entry. */ -static u64 min_kimg_align(void) +static bool check_image_region(u64 base, u64 size) { - return efi_nokaslr ? MIN_KIMG_ALIGN : EFI_KIMG_ALIGN; + unsigned long map_size, desc_size, buff_size; + efi_memory_desc_t *memory_map; + struct efi_boot_memmap map; + efi_status_t status; + bool ret = false; + int map_offset; + + map.map = &memory_map; + map.map_size = &map_size; + map.desc_size = &desc_size; + map.desc_ver = NULL; + map.key_ptr = NULL; + map.buff_size = &buff_size; + + status = efi_get_memory_map(&map); + if (status != EFI_SUCCESS) + return false; + + for (map_offset = 0; map_offset < map_size; map_offset += desc_size) { + efi_memory_desc_t *md = (void *)memory_map + map_offset; + u64 end = md->phys_addr + md->num_pages * EFI_PAGE_SIZE; + + /* + * Find the region that covers base, and return whether + * it covers base+size bytes. + */ + if (base >= md->phys_addr && base < end) { + ret = (base + size) <= end; + break; + } + } + + efi_bs_call(free_pool, memory_map); + + return ret; } efi_status_t handle_kernel_image(unsigned long *image_addr, @@ -56,6 +89,16 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, unsigned long kernel_size, kernel_memsize = 0; u32 phys_seed = 0; + /* + * Although relocatable kernels can fix up the misalignment with + * respect to MIN_KIMG_ALIGN, the resulting virtual text addresses are + * subtly out of sync with those recorded in the vmlinux when kaslr is + * disabled but the image required relocation anyway. Therefore retain + * 2M alignment if KASLR was explicitly disabled, even if it was not + * going to be activated to begin with. + */ + u64 min_kimg_align = efi_nokaslr ? MIN_KIMG_ALIGN : EFI_KIMG_ALIGN; + if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) { if (!efi_nokaslr) { status = efi_get_random_bytes(sizeof(phys_seed), @@ -76,6 +119,10 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, if (image->image_base != _text) efi_err("FIRMWARE BUG: efi_loaded_image_t::image_base has bogus value\n"); + if (!IS_ALIGNED((u64)_text, EFI_KIMG_ALIGN)) + efi_err("FIRMWARE BUG: kernel image not aligned on %ldk boundary\n", + EFI_KIMG_ALIGN >> 10); + kernel_size = _edata - _text; kernel_memsize = kernel_size + (_end - _edata); *reserve_size = kernel_memsize; @@ -85,14 +132,18 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, * If KASLR is enabled, and we have some randomness available, * locate the kernel at a randomized offset in physical memory. */ - status = efi_random_alloc(*reserve_size, min_kimg_align(), + status = efi_random_alloc(*reserve_size, min_kimg_align, reserve_addr, phys_seed); + if (status != EFI_SUCCESS) + efi_warn("efi_random_alloc() failed: 0x%lx\n", status); } else { status = EFI_OUT_OF_RESOURCES; } if (status != EFI_SUCCESS) { - if (IS_ALIGNED((u64)_text, min_kimg_align())) { + if (!check_image_region((u64)_text, kernel_memsize)) { + efi_err("FIRMWARE BUG: Image BSS overlaps adjacent EFI memory region\n"); + } else if (IS_ALIGNED((u64)_text, min_kimg_align)) { /* * Just execute from wherever we were loaded by the * UEFI PE/COFF loader if the alignment is suitable. @@ -103,7 +154,7 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, } status = efi_allocate_pages_aligned(*reserve_size, reserve_addr, - ULONG_MAX, min_kimg_align()); + ULONG_MAX, min_kimg_align); if (status != EFI_SUCCESS) { efi_err("Failed to relocate kernel\n"); diff --git a/drivers/firmware/efi/libstub/randomalloc.c b/drivers/firmware/efi/libstub/randomalloc.c index a408df474d..724155b9e1 100644 --- a/drivers/firmware/efi/libstub/randomalloc.c +++ b/drivers/firmware/efi/libstub/randomalloc.c @@ -30,6 +30,8 @@ static unsigned long get_entry_num_slots(efi_memory_desc_t *md, region_end = min(md->phys_addr + md->num_pages * EFI_PAGE_SIZE - 1, (u64)ULONG_MAX); + if (region_end < size) + return 0; first_slot = round_up(md->phys_addr, align); last_slot = round_down(region_end - size + 1, align); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c index 3b5d131890..8f53837d4d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c @@ -468,6 +468,46 @@ bool amdgpu_atomfirmware_dynamic_boot_config_supported(struct amdgpu_device *ade return (fw_cap & ATOM_FIRMWARE_CAP_DYNAMIC_BOOT_CFG_ENABLE) ? true : false; } +/* + * Helper function to query RAS EEPROM address + * + * @adev: amdgpu_device pointer + * + * Return true if vbios supports ras rom address reporting + */ +bool amdgpu_atomfirmware_ras_rom_addr(struct amdgpu_device *adev, uint8_t* i2c_address) +{ + struct amdgpu_mode_info *mode_info = &adev->mode_info; + int index; + u16 data_offset, size; + union firmware_info *firmware_info; + u8 frev, crev; + + if (i2c_address == NULL) + return false; + + *i2c_address = 0; + + index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1, + firmwareinfo); + + if (amdgpu_atom_parse_data_header(adev->mode_info.atom_context, + index, &size, &frev, &crev, &data_offset)) { + /* support firmware_info 3.4 + */ + if ((frev == 3 && crev >=4) || (frev > 3)) { + firmware_info = (union firmware_info *) + (mode_info->atom_context->bios + data_offset); + *i2c_address = firmware_info->v34.ras_rom_i2c_slave_addr; + } + } + + if (*i2c_address != 0) + return true; + + return false; +} + + union smu_info { struct atom_smu_info_v3_1 v31; }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h index 1bbbb19501..751248b253 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h @@ -36,6 +36,7 @@ int amdgpu_atomfirmware_get_clock_info(struct amdgpu_device *adev); int amdgpu_atomfirmware_get_gfx_info(struct amdgpu_device *adev); bool amdgpu_atomfirmware_mem_ecc_supported(struct amdgpu_device *adev); bool amdgpu_atomfirmware_sram_ecc_supported(struct amdgpu_device *adev); +bool amdgpu_atomfirmware_ras_rom_addr(struct amdgpu_device *adev, uint8_t* i2c_address); bool amdgpu_atomfirmware_mem_training_supported(struct amdgpu_device *adev); bool amdgpu_atomfirmware_dynamic_boot_config_supported(struct amdgpu_device *adev); int amdgpu_atomfirmware_get_fw_reserved_fb_size(struct amdgpu_device *adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index 43e7b61d1c..ada7bc1911 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -299,6 +299,9 @@ int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev) ip->major, ip->minor, ip->revision); + if (le16_to_cpu(ip->hw_id) == VCN_HWID) + adev->vcn.num_vcn_inst++; + for (k = 0; k < num_base_address; k++) { /* * convert the endianness of base addresses in place, @@ -385,7 +388,7 @@ void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev) { struct binary_header *bhdr; struct harvest_table *harvest_info; - int i; + int i, vcn_harvest_count = 0; bhdr = (struct binary_header *)adev->mman.discovery_bin; harvest_info = (struct harvest_table *)(adev->mman.discovery_bin + @@ -397,8 +400,7 @@ void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev) switch (le32_to_cpu(harvest_info->list[i].hw_id)) { case VCN_HWID: - adev->harvest_ip_mask |= AMD_HARVEST_IP_VCN_MASK; - adev->harvest_ip_mask |= AMD_HARVEST_IP_JPEG_MASK; + vcn_harvest_count++; break; case DMU_HWID: adev->harvest_ip_mask |= AMD_HARVEST_IP_DMU_MASK; @@ -407,6 +409,10 @@ void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev) break; } } + if (vcn_harvest_count == adev->vcn.num_vcn_inst) { + adev->harvest_ip_mask |= AMD_HARVEST_IP_VCN_MASK; + adev->harvest_ip_mask |= AMD_HARVEST_IP_JPEG_MASK; + } } int amdgpu_discovery_get_gfx_info(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 5ed8381ae0..971c5b8e75 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -1571,6 +1571,8 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev) pci_ignore_hotplug(pdev); pci_set_power_state(pdev, PCI_D3cold); drm_dev->switch_power_state = DRM_SWITCH_POWER_DYNAMIC_OFF; + } else if (amdgpu_device_supports_boco(drm_dev)) { + /* nothing to do */ } else if (amdgpu_device_supports_baco(drm_dev)) { amdgpu_device_baco_enter(drm_dev); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c index f40c871da0..38222de921 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c @@ -26,6 +26,7 @@ #include "amdgpu_ras.h" #include #include "atom.h" +#include "amdgpu_atomfirmware.h" #define EEPROM_I2C_TARGET_ADDR_VEGA20 0xA0 #define EEPROM_I2C_TARGET_ADDR_ARCTURUS 0xA8 @@ -96,6 +97,9 @@ static bool __get_eeprom_i2c_addr(struct amdgpu_device *adev, if (!i2c_addr) return false; + if (amdgpu_atomfirmware_ras_rom_addr(adev, (uint8_t*)i2c_addr)) + return true; + switch (adev->asic_type) { case CHIP_VEGA20: *i2c_addr = EEPROM_I2C_TARGET_ADDR_VEGA20; 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 c0ae73b069..afa96c8f72 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -9605,7 +9605,12 @@ static int dm_update_crtc_state(struct amdgpu_display_manager *dm, } else if (amdgpu_freesync_vid_mode && aconnector && is_freesync_video_mode(&new_crtc_state->mode, aconnector)) { - set_freesync_fixed_config(dm_new_crtc_state); + struct drm_display_mode *high_mode; + + high_mode = get_highest_refresh_rate_mode(aconnector, false); + if (!drm_mode_equal(&new_crtc_state->mode, high_mode)) { + set_freesync_fixed_config(dm_new_crtc_state); + } } ret = dm_atomic_get_state(state, &dm_state); diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c index 253654d605..28e15ebf2f 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c @@ -1788,7 +1788,6 @@ static bool dcn30_split_stream_for_mpc_or_odm( } pri_pipe->next_odm_pipe = sec_pipe; sec_pipe->prev_odm_pipe = pri_pipe; - ASSERT(sec_pipe->top_pipe == NULL); if (!sec_pipe->top_pipe) sec_pipe->stream_res.opp = pool->opps[pipe_idx]; diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h index 3811e58dd8..44955458fe 100644 --- a/drivers/gpu/drm/amd/include/atomfirmware.h +++ b/drivers/gpu/drm/amd/include/atomfirmware.h @@ -590,7 +590,7 @@ struct atom_firmware_info_v3_4 { uint8_t board_i2c_feature_id; // enum of atom_board_i2c_feature_id_def uint8_t board_i2c_feature_gpio_id; // i2c id find in gpio_lut data table gpio_id uint8_t board_i2c_feature_slave_addr; - uint8_t reserved3; + uint8_t ras_rom_i2c_slave_addr; uint16_t bootup_mvddq_mv; uint16_t bootup_mvpp_mv; uint32_t zfbstartaddrin16mb; diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v13_0_1_pmfw.h b/drivers/gpu/drm/amd/pm/inc/smu_v13_0_1_pmfw.h index 5627de7342..c5e26d619b 100644 --- a/drivers/gpu/drm/amd/pm/inc/smu_v13_0_1_pmfw.h +++ b/drivers/gpu/drm/amd/pm/inc/smu_v13_0_1_pmfw.h @@ -111,7 +111,9 @@ typedef struct { uint32_t InWhisperMode : 1; uint32_t spare0 : 1; uint32_t ZstateStatus : 4; - uint32_t spare1 :12; + uint32_t spare1 : 4; + uint32_t DstateFun : 4; + uint32_t DstateDev : 4; // MP1_EXT_SCRATCH2 uint32_t P2JobHandler :24; uint32_t RsmuPmiP2FinishedCnt : 8; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index c751f717a0..d92dd2c744 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -353,8 +353,7 @@ static void sienna_cichlid_check_bxco_support(struct smu_context *smu) struct amdgpu_device *adev = smu->adev; uint32_t val; - if (powerplay_table->platform_caps & SMU_11_0_7_PP_PLATFORM_CAP_BACO || - powerplay_table->platform_caps & SMU_11_0_7_PP_PLATFORM_CAP_MACO) { + if (powerplay_table->platform_caps & SMU_11_0_7_PP_PLATFORM_CAP_BACO) { val = RREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP0); smu_baco->platform_support = (val & RCC_BIF_STRAP0__STRAP_PX_CAPABLE_MASK) ? true : diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c index 18681dc458..bcaaa086fc 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c @@ -256,7 +256,7 @@ static int vangogh_tables_init(struct smu_context *smu) return 0; err3_out: - kfree(smu_table->clocks_table); + kfree(smu_table->watermarks_table); err2_out: kfree(smu_table->gpu_metrics_table); err1_out: diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 2d5d21740c..0a8a2395c8 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -5746,16 +5746,18 @@ static void bdw_set_pipemisc(const struct intel_crtc_state *crtc_state) switch (crtc_state->pipe_bpp) { case 18: - val |= PIPEMISC_DITHER_6_BPC; + val |= PIPEMISC_6_BPC; break; case 24: - val |= PIPEMISC_DITHER_8_BPC; + val |= PIPEMISC_8_BPC; break; case 30: - val |= PIPEMISC_DITHER_10_BPC; + val |= PIPEMISC_10_BPC; break; case 36: - val |= PIPEMISC_DITHER_12_BPC; + /* Port output 12BPC defined for ADLP+ */ + if (DISPLAY_VER(dev_priv) > 12) + val |= PIPEMISC_12_BPC_ADLP; break; default: MISSING_CASE(crtc_state->pipe_bpp); @@ -5808,15 +5810,27 @@ int bdw_get_pipemisc_bpp(struct intel_crtc *crtc) tmp = intel_de_read(dev_priv, PIPEMISC(crtc->pipe)); - switch (tmp & PIPEMISC_DITHER_BPC_MASK) { - case PIPEMISC_DITHER_6_BPC: + switch (tmp & PIPEMISC_BPC_MASK) { + case PIPEMISC_6_BPC: return 18; - case PIPEMISC_DITHER_8_BPC: + case PIPEMISC_8_BPC: return 24; - case PIPEMISC_DITHER_10_BPC: + case PIPEMISC_10_BPC: return 30; - case PIPEMISC_DITHER_12_BPC: - return 36; + /* + * PORT OUTPUT 12 BPC defined for ADLP+. + * + * TODO: + * For previous platforms with DSI interface, bits 5:7 + * are used for storing pipe_bpp irrespective of dithering. + * Since the value of 12 BPC is not defined for these bits + * on older platforms, need to find a workaround for 12 BPC + * MIPI DSI HW readout. + */ + case PIPEMISC_12_BPC_ADLP: + if (DISPLAY_VER(dev_priv) > 12) + return 36; + fallthrough; default: MISSING_CASE(tmp); return 0; diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index 06024d321a..cde0a477fb 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -3149,6 +3149,7 @@ static int init_bdw_mmio_info(struct intel_gvt *gvt) MMIO_DFH(_MMIO(0xb100), D_BDW, F_CMD_ACCESS, NULL, NULL); MMIO_DFH(_MMIO(0xb10c), D_BDW, F_CMD_ACCESS, NULL, NULL); MMIO_D(_MMIO(0xb110), D_BDW); + MMIO_D(GEN9_SCRATCH_LNCF1, D_BDW_PLUS); MMIO_F(_MMIO(0x24d0), 48, F_CMD_ACCESS | F_CMD_WRITE_PATCH, 0, 0, D_BDW_PLUS, NULL, force_nonpriv_write); diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c index b8ac807654..f776c47091 100644 --- a/drivers/gpu/drm/i915/gvt/mmio_context.c +++ b/drivers/gpu/drm/i915/gvt/mmio_context.c @@ -105,6 +105,8 @@ static struct engine_mmio gen9_engine_mmio_list[] __cacheline_aligned = { {RCS0, COMMON_SLICE_CHICKEN2, 0xffff, true}, /* 0x7014 */ {RCS0, GEN9_CS_DEBUG_MODE1, 0xffff, false}, /* 0x20ec */ {RCS0, GEN8_L3SQCREG4, 0, false}, /* 0xb118 */ + {RCS0, GEN9_SCRATCH1, 0, false}, /* 0xb11c */ + {RCS0, GEN9_SCRATCH_LNCF1, 0, false}, /* 0xb008 */ {RCS0, GEN7_HALF_SLICE_CHICKEN1, 0xffff, true}, /* 0xe100 */ {RCS0, HALF_SLICE_CHICKEN2, 0xffff, true}, /* 0xe180 */ {RCS0, HALF_SLICE_CHICKEN3, 0xffff, true}, /* 0xe184 */ diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 35c97c39f1..966664610c 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -727,9 +727,18 @@ static void err_print_gt(struct drm_i915_error_state_buf *m, if (GRAPHICS_VER(m->i915) >= 12) { int i; - for (i = 0; i < GEN12_SFC_DONE_MAX; i++) + for (i = 0; i < GEN12_SFC_DONE_MAX; i++) { + /* + * SFC_DONE resides in the VD forcewake domain, so it + * only exists if the corresponding VCS engine is + * present. + */ + if (!HAS_ENGINE(gt->_gt, _VCS(i * 2))) + continue; + err_printf(m, " SFC_DONE[%d]: 0x%08x\n", i, gt->sfc_done[i]); + } err_printf(m, " GAM_DONE: 0x%08x\n", gt->gam_done); } @@ -1581,6 +1590,14 @@ static void gt_record_regs(struct intel_gt_coredump *gt) if (GRAPHICS_VER(i915) >= 12) { for (i = 0; i < GEN12_SFC_DONE_MAX; i++) { + /* + * SFC_DONE resides in the VD forcewake domain, so it + * only exists if the corresponding VCS engine is + * present. + */ + if (!HAS_ENGINE(gt->_gt, _VCS(i * 2))) + continue; + gt->sfc_done[i] = intel_uncore_read(uncore, GEN12_SFC_DONE(i)); } diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 41186c1f77..476bb3b9ad 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -6163,11 +6163,17 @@ enum { #define PIPEMISC_HDR_MODE_PRECISION (1 << 23) /* icl+ */ #define PIPEMISC_OUTPUT_COLORSPACE_YUV (1 << 11) #define PIPEMISC_PIXEL_ROUNDING_TRUNC REG_BIT(8) /* tgl+ */ -#define PIPEMISC_DITHER_BPC_MASK (7 << 5) -#define PIPEMISC_DITHER_8_BPC (0 << 5) -#define PIPEMISC_DITHER_10_BPC (1 << 5) -#define PIPEMISC_DITHER_6_BPC (2 << 5) -#define PIPEMISC_DITHER_12_BPC (3 << 5) +/* + * For Display < 13, Bits 5-7 of PIPE MISC represent DITHER BPC with + * valid values of: 6, 8, 10 BPC. + * ADLP+, the bits 5-7 represent PORT OUTPUT BPC with valid values of: + * 6, 8, 10, 12 BPC. + */ +#define PIPEMISC_BPC_MASK (7 << 5) +#define PIPEMISC_8_BPC (0 << 5) +#define PIPEMISC_10_BPC (1 << 5) +#define PIPEMISC_6_BPC (2 << 5) +#define PIPEMISC_12_BPC_ADLP (4 << 5) /* adlp+ */ #define PIPEMISC_DITHER_ENABLE (1 << 4) #define PIPEMISC_DITHER_TYPE_MASK (3 << 2) #define PIPEMISC_DITHER_TYPE_SP (0 << 2) diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c index bced555648..e94738fe4d 100644 --- a/drivers/gpu/drm/mediatek/mtk_dpi.c +++ b/drivers/gpu/drm/mediatek/mtk_dpi.c @@ -605,11 +605,15 @@ static int mtk_dpi_bridge_atomic_check(struct drm_bridge *bridge, struct drm_crtc_state *crtc_state, struct drm_connector_state *conn_state) { - struct mtk_dpi *dpi = bridge->driver_private; + struct mtk_dpi *dpi = bridge_to_dpi(bridge); unsigned int out_bus_format; out_bus_format = bridge_state->output_bus_cfg.format; + if (out_bus_format == MEDIA_BUS_FMT_FIXED) + if (dpi->conf->num_output_fmts) + out_bus_format = dpi->conf->output_fmts[0]; + dev_dbg(dpi->dev, "input format 0x%04x, output format 0x%04x\n", bridge_state->input_bus_cfg.format, bridge_state->output_bus_cfg.format); diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c index 474efb8442..735efe79f0 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c @@ -532,13 +532,10 @@ void mtk_drm_crtc_async_update(struct drm_crtc *crtc, struct drm_plane *plane, struct drm_atomic_state *state) { struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc); - const struct drm_plane_helper_funcs *plane_helper_funcs = - plane->helper_private; if (!mtk_crtc->enabled) return; - plane_helper_funcs->atomic_update(plane, state); mtk_drm_crtc_update_config(mtk_crtc, false); } diff --git a/drivers/gpu/drm/mediatek/mtk_drm_plane.c b/drivers/gpu/drm/mediatek/mtk_drm_plane.c index b5582dcf56..e6dcb34d30 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_plane.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_plane.c @@ -110,6 +110,35 @@ static int mtk_plane_atomic_async_check(struct drm_plane *plane, true, true); } +static void mtk_plane_update_new_state(struct drm_plane_state *new_state, + struct mtk_plane_state *mtk_plane_state) +{ + struct drm_framebuffer *fb = new_state->fb; + struct drm_gem_object *gem; + struct mtk_drm_gem_obj *mtk_gem; + unsigned int pitch, format; + dma_addr_t addr; + + gem = fb->obj[0]; + mtk_gem = to_mtk_gem_obj(gem); + addr = mtk_gem->dma_addr; + pitch = fb->pitches[0]; + format = fb->format->format; + + addr += (new_state->src.x1 >> 16) * fb->format->cpp[0]; + addr += (new_state->src.y1 >> 16) * pitch; + + mtk_plane_state->pending.enable = true; + mtk_plane_state->pending.pitch = pitch; + mtk_plane_state->pending.format = format; + mtk_plane_state->pending.addr = addr; + mtk_plane_state->pending.x = new_state->dst.x1; + mtk_plane_state->pending.y = new_state->dst.y1; + mtk_plane_state->pending.width = drm_rect_width(&new_state->dst); + mtk_plane_state->pending.height = drm_rect_height(&new_state->dst); + mtk_plane_state->pending.rotation = new_state->rotation; +} + static void mtk_plane_atomic_async_update(struct drm_plane *plane, struct drm_atomic_state *state) { @@ -126,8 +155,10 @@ static void mtk_plane_atomic_async_update(struct drm_plane *plane, plane->state->src_h = new_state->src_h; plane->state->src_w = new_state->src_w; swap(plane->state->fb, new_state->fb); - new_plane_state->pending.async_dirty = true; + mtk_plane_update_new_state(new_state, new_plane_state); + wmb(); /* Make sure the above parameters are set before update */ + new_plane_state->pending.async_dirty = true; mtk_drm_crtc_async_update(new_state->crtc, plane, state); } @@ -189,14 +220,8 @@ static void mtk_plane_atomic_update(struct drm_plane *plane, struct drm_plane_state *new_state = drm_atomic_get_new_plane_state(state, plane); struct mtk_plane_state *mtk_plane_state = to_mtk_plane_state(new_state); - struct drm_crtc *crtc = new_state->crtc; - struct drm_framebuffer *fb = new_state->fb; - struct drm_gem_object *gem; - struct mtk_drm_gem_obj *mtk_gem; - unsigned int pitch, format; - dma_addr_t addr; - if (!crtc || WARN_ON(!fb)) + if (!new_state->crtc || WARN_ON(!new_state->fb)) return; if (!new_state->visible) { @@ -204,24 +229,7 @@ static void mtk_plane_atomic_update(struct drm_plane *plane, return; } - gem = fb->obj[0]; - mtk_gem = to_mtk_gem_obj(gem); - addr = mtk_gem->dma_addr; - pitch = fb->pitches[0]; - format = fb->format->format; - - addr += (new_state->src.x1 >> 16) * fb->format->cpp[0]; - addr += (new_state->src.y1 >> 16) * pitch; - - mtk_plane_state->pending.enable = true; - mtk_plane_state->pending.pitch = pitch; - mtk_plane_state->pending.format = format; - mtk_plane_state->pending.addr = addr; - mtk_plane_state->pending.x = new_state->dst.x1; - mtk_plane_state->pending.y = new_state->dst.y1; - mtk_plane_state->pending.width = drm_rect_width(&new_state->dst); - mtk_plane_state->pending.height = drm_rect_height(&new_state->dst); - mtk_plane_state->pending.rotation = new_state->rotation; + mtk_plane_update_new_state(new_state, mtk_plane_state); wmb(); /* Make sure the above parameters are set before update */ mtk_plane_state->pending.dirty = true; } diff --git a/drivers/gpu/drm/meson/meson_registers.h b/drivers/gpu/drm/meson/meson_registers.h index 446e7961da..0f3cafab88 100644 --- a/drivers/gpu/drm/meson/meson_registers.h +++ b/drivers/gpu/drm/meson/meson_registers.h @@ -634,6 +634,11 @@ #define VPP_WRAP_OSD3_MATRIX_PRE_OFFSET2 0x3dbc #define VPP_WRAP_OSD3_MATRIX_EN_CTRL 0x3dbd +/* osd1 HDR */ +#define OSD1_HDR2_CTRL 0x38a0 +#define OSD1_HDR2_CTRL_VDIN0_HDR2_TOP_EN BIT(13) +#define OSD1_HDR2_CTRL_REG_ONLY_MAT BIT(16) + /* osd2 scaler */ #define OSD2_VSC_PHASE_STEP 0x3d00 #define OSD2_VSC_INI_PHASE 0x3d01 diff --git a/drivers/gpu/drm/meson/meson_viu.c b/drivers/gpu/drm/meson/meson_viu.c index aede0c67a5..259f3e6bec 100644 --- a/drivers/gpu/drm/meson/meson_viu.c +++ b/drivers/gpu/drm/meson/meson_viu.c @@ -425,9 +425,14 @@ void meson_viu_init(struct meson_drm *priv) if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXM) || meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXL)) meson_viu_load_matrix(priv); - else if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A)) + else if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A)) { meson_viu_set_g12a_osd1_matrix(priv, RGB709_to_YUV709l_coeff, true); + /* fix green/pink color distortion from vendor u-boot */ + writel_bits_relaxed(OSD1_HDR2_CTRL_REG_ONLY_MAT | + OSD1_HDR2_CTRL_VDIN0_HDR2_TOP_EN, 0, + priv->io_base + _REG(OSD1_HDR2_CTRL)); + } /* Initialize OSD1 fifo control register */ reg = VIU_OSD_DDR_PRIORITY_URGENT | diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c index cb64fe6493..77f576e516 100644 --- a/drivers/i2c/i2c-dev.c +++ b/drivers/i2c/i2c-dev.c @@ -141,7 +141,7 @@ static ssize_t i2cdev_read(struct file *file, char __user *buf, size_t count, if (count > 8192) count = 8192; - tmp = kmalloc(count, GFP_KERNEL); + tmp = kzalloc(count, GFP_KERNEL); if (tmp == NULL) return -ENOMEM; @@ -150,7 +150,8 @@ static ssize_t i2cdev_read(struct file *file, char __user *buf, size_t count, ret = i2c_master_recv(client, tmp, count); if (ret >= 0) - ret = copy_to_user(buf, tmp, count) ? -EFAULT : ret; + if (copy_to_user(buf, tmp, ret)) + ret = -EFAULT; kfree(tmp); return ret; } diff --git a/drivers/iio/accel/Kconfig b/drivers/iio/accel/Kconfig index 0e56ace611..8d8b1ba42f 100644 --- a/drivers/iio/accel/Kconfig +++ b/drivers/iio/accel/Kconfig @@ -231,6 +231,7 @@ config DMARD10 config FXLS8962AF tristate + depends on I2C || !I2C # cannot be built-in for modular I2C config FXLS8962AF_I2C tristate "NXP FXLS8962AF/FXLS8964AF Accelerometer I2C Driver" @@ -247,6 +248,7 @@ config FXLS8962AF_I2C config FXLS8962AF_SPI tristate "NXP FXLS8962AF/FXLS8964AF Accelerometer SPI Driver" depends on SPI + depends on I2C || !I2C select FXLS8962AF select REGMAP_SPI help diff --git a/drivers/iio/accel/fxls8962af-core.c b/drivers/iio/accel/fxls8962af-core.c index 078d87865f..0019f1ea7d 100644 --- a/drivers/iio/accel/fxls8962af-core.c +++ b/drivers/iio/accel/fxls8962af-core.c @@ -637,7 +637,7 @@ static int fxls8962af_i2c_raw_read_errata3(struct fxls8962af_data *data, return ret; } - return ret; + return 0; } static int fxls8962af_fifo_transfer(struct fxls8962af_data *data, diff --git a/drivers/iio/adc/palmas_gpadc.c b/drivers/iio/adc/palmas_gpadc.c index 6ef09609be..f9c8385c72 100644 --- a/drivers/iio/adc/palmas_gpadc.c +++ b/drivers/iio/adc/palmas_gpadc.c @@ -664,8 +664,8 @@ static int palmas_adc_wakeup_configure(struct palmas_gpadc *adc) adc_period = adc->auto_conversion_period; for (i = 0; i < 16; ++i) { - if (((1000 * (1 << i)) / 32) < adc_period) - continue; + if (((1000 * (1 << i)) / 32) >= adc_period) + break; } if (i > 0) i--; diff --git a/drivers/iio/adc/ti-ads7950.c b/drivers/iio/adc/ti-ads7950.c index 2383eacada..a2b83f0bd5 100644 --- a/drivers/iio/adc/ti-ads7950.c +++ b/drivers/iio/adc/ti-ads7950.c @@ -568,7 +568,6 @@ static int ti_ads7950_probe(struct spi_device *spi) st->ring_xfer.tx_buf = &st->tx_buf[0]; st->ring_xfer.rx_buf = &st->rx_buf[0]; /* len will be set later */ - st->ring_xfer.cs_change = true; spi_message_add_tail(&st->ring_xfer, &st->ring_msg); diff --git a/drivers/iio/humidity/hdc100x.c b/drivers/iio/humidity/hdc100x.c index 2a957f1904..9e0fce917c 100644 --- a/drivers/iio/humidity/hdc100x.c +++ b/drivers/iio/humidity/hdc100x.c @@ -25,6 +25,8 @@ #include #include +#include + #define HDC100X_REG_TEMP 0x00 #define HDC100X_REG_HUMIDITY 0x01 @@ -166,7 +168,7 @@ static int hdc100x_get_measurement(struct hdc100x_data *data, struct iio_chan_spec const *chan) { struct i2c_client *client = data->client; - int delay = data->adc_int_us[chan->address]; + int delay = data->adc_int_us[chan->address] + 1*USEC_PER_MSEC; int ret; __be16 val; @@ -316,7 +318,7 @@ static irqreturn_t hdc100x_trigger_handler(int irq, void *p) struct iio_dev *indio_dev = pf->indio_dev; struct hdc100x_data *data = iio_priv(indio_dev); struct i2c_client *client = data->client; - int delay = data->adc_int_us[0] + data->adc_int_us[1]; + int delay = data->adc_int_us[0] + data->adc_int_us[1] + 2*USEC_PER_MSEC; int ret; /* dual read starts at temp register */ diff --git a/drivers/iio/imu/adis.c b/drivers/iio/imu/adis.c index a5b421f422..b9a06ca29b 100644 --- a/drivers/iio/imu/adis.c +++ b/drivers/iio/imu/adis.c @@ -411,12 +411,11 @@ int __adis_initial_startup(struct adis *adis) int ret; /* check if the device has rst pin low */ - gpio = devm_gpiod_get_optional(&adis->spi->dev, "reset", GPIOD_ASIS); + gpio = devm_gpiod_get_optional(&adis->spi->dev, "reset", GPIOD_OUT_HIGH); if (IS_ERR(gpio)) return PTR_ERR(gpio); if (gpio) { - gpiod_set_value_cansleep(gpio, 1); msleep(10); /* bring device out of reset */ gpiod_set_value_cansleep(gpio, 0); diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c index 7abeb576b3..b8e5e371bb 100644 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@ -945,7 +945,6 @@ int mlx5_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, u32 *cqb = NULL; void *cqc; int cqe_size; - unsigned int irqn; int eqn; int err; @@ -984,7 +983,7 @@ int mlx5_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, INIT_WORK(&cq->notify_work, notify_soft_wc_handler); } - err = mlx5_vector2eqn(dev->mdev, vector, &eqn, &irqn); + err = mlx5_vector2eqn(dev->mdev, vector, &eqn); if (err) goto err_cqb; @@ -1007,7 +1006,6 @@ int mlx5_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, goto err_cqb; mlx5_ib_dbg(dev, "cqn 0x%x\n", cq->mcq.cqn); - cq->mcq.irqn = irqn; if (udata) cq->mcq.tasklet_ctx.comp = mlx5_ib_cq_comp; else diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index eb9b0a2707..c869b2a91a 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -975,7 +975,6 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_QUERY_EQN)( struct mlx5_ib_dev *dev; int user_vector; int dev_eqn; - unsigned int irqn; int err; if (uverbs_copy_from(&user_vector, attrs, @@ -987,7 +986,7 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_QUERY_EQN)( return PTR_ERR(c); dev = to_mdev(c->ibucontext.device); - err = mlx5_vector2eqn(dev->mdev, user_vector, &dev_eqn, &irqn); + err = mlx5_vector2eqn(dev->mdev, user_vector, &dev_eqn); if (err < 0) return err; diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c index a7ee0af1af..54e321a695 100644 --- a/drivers/net/bareudp.c +++ b/drivers/net/bareudp.c @@ -71,12 +71,18 @@ static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) family = AF_INET6; if (bareudp->ethertype == htons(ETH_P_IP)) { - struct iphdr *iphdr; + __u8 ipversion; - iphdr = (struct iphdr *)(skb->data + BAREUDP_BASE_HLEN); - if (iphdr->version == 4) { - proto = bareudp->ethertype; - } else if (bareudp->multi_proto_mode && (iphdr->version == 6)) { + if (skb_copy_bits(skb, BAREUDP_BASE_HLEN, &ipversion, + sizeof(ipversion))) { + bareudp->dev->stats.rx_dropped++; + goto drop; + } + ipversion >>= 4; + + if (ipversion == 4) { + proto = htons(ETH_P_IP); + } else if (ipversion == 6 && bareudp->multi_proto_mode) { proto = htons(ETH_P_IPV6); } else { bareudp->dev->stats.rx_dropped++; diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index bba2a449ac..43bca315a6 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -1164,10 +1164,10 @@ static int m_can_set_bittiming(struct net_device *dev) FIELD_PREP(TDCR_TDCO_MASK, tdco)); } - reg_btp = FIELD_PREP(NBTP_NBRP_MASK, brp) | - FIELD_PREP(NBTP_NSJW_MASK, sjw) | - FIELD_PREP(NBTP_NTSEG1_MASK, tseg1) | - FIELD_PREP(NBTP_NTSEG2_MASK, tseg2); + reg_btp |= FIELD_PREP(DBTP_DBRP_MASK, brp) | + FIELD_PREP(DBTP_DSJW_MASK, sjw) | + FIELD_PREP(DBTP_DTSEG1_MASK, tseg1) | + FIELD_PREP(DBTP_DTSEG2_MASK, tseg2); m_can_write(cdev, M_CAN_DBTP, reg_btp); } diff --git a/drivers/net/dsa/hirschmann/hellcreek.c b/drivers/net/dsa/hirschmann/hellcreek.c index 9fdcc4bde4..5c54ae1be6 100644 --- a/drivers/net/dsa/hirschmann/hellcreek.c +++ b/drivers/net/dsa/hirschmann/hellcreek.c @@ -912,6 +912,7 @@ static int hellcreek_fdb_dump(struct dsa_switch *ds, int port, { struct hellcreek *hellcreek = ds->priv; u16 entries; + int ret = 0; size_t i; mutex_lock(&hellcreek->reg_lock); @@ -943,12 +944,14 @@ static int hellcreek_fdb_dump(struct dsa_switch *ds, int port, if (!(entry.portmask & BIT(port))) continue; - cb(entry.mac, 0, entry.is_static, data); + ret = cb(entry.mac, 0, entry.is_static, data); + if (ret) + break; } mutex_unlock(&hellcreek->reg_lock); - return 0; + return ret; } static int hellcreek_vlan_filtering(struct dsa_switch *ds, int port, diff --git a/drivers/net/dsa/lan9303-core.c b/drivers/net/dsa/lan9303-core.c index 3443740254..d7ce281570 100644 --- a/drivers/net/dsa/lan9303-core.c +++ b/drivers/net/dsa/lan9303-core.c @@ -557,12 +557,12 @@ static int lan9303_alr_make_entry_raw(struct lan9303 *chip, u32 dat0, u32 dat1) return 0; } -typedef void alr_loop_cb_t(struct lan9303 *chip, u32 dat0, u32 dat1, - int portmap, void *ctx); +typedef int alr_loop_cb_t(struct lan9303 *chip, u32 dat0, u32 dat1, + int portmap, void *ctx); -static void lan9303_alr_loop(struct lan9303 *chip, alr_loop_cb_t *cb, void *ctx) +static int lan9303_alr_loop(struct lan9303 *chip, alr_loop_cb_t *cb, void *ctx) { - int i; + int ret = 0, i; mutex_lock(&chip->alr_mutex); lan9303_write_switch_reg(chip, LAN9303_SWE_ALR_CMD, @@ -582,13 +582,17 @@ static void lan9303_alr_loop(struct lan9303 *chip, alr_loop_cb_t *cb, void *ctx) LAN9303_ALR_DAT1_PORT_BITOFFS; portmap = alrport_2_portmap[alrport]; - cb(chip, dat0, dat1, portmap, ctx); + ret = cb(chip, dat0, dat1, portmap, ctx); + if (ret) + break; lan9303_write_switch_reg(chip, LAN9303_SWE_ALR_CMD, LAN9303_ALR_CMD_GET_NEXT); lan9303_write_switch_reg(chip, LAN9303_SWE_ALR_CMD, 0); } mutex_unlock(&chip->alr_mutex); + + return ret; } static void alr_reg_to_mac(u32 dat0, u32 dat1, u8 mac[6]) @@ -606,18 +610,20 @@ struct del_port_learned_ctx { }; /* Clear learned (non-static) entry on given port */ -static void alr_loop_cb_del_port_learned(struct lan9303 *chip, u32 dat0, - u32 dat1, int portmap, void *ctx) +static int alr_loop_cb_del_port_learned(struct lan9303 *chip, u32 dat0, + u32 dat1, int portmap, void *ctx) { struct del_port_learned_ctx *del_ctx = ctx; int port = del_ctx->port; if (((BIT(port) & portmap) == 0) || (dat1 & LAN9303_ALR_DAT1_STATIC)) - return; + return 0; /* learned entries has only one port, we can just delete */ dat1 &= ~LAN9303_ALR_DAT1_VALID; /* delete entry */ lan9303_alr_make_entry_raw(chip, dat0, dat1); + + return 0; } struct port_fdb_dump_ctx { @@ -626,19 +632,19 @@ struct port_fdb_dump_ctx { dsa_fdb_dump_cb_t *cb; }; -static void alr_loop_cb_fdb_port_dump(struct lan9303 *chip, u32 dat0, - u32 dat1, int portmap, void *ctx) +static int alr_loop_cb_fdb_port_dump(struct lan9303 *chip, u32 dat0, + u32 dat1, int portmap, void *ctx) { struct port_fdb_dump_ctx *dump_ctx = ctx; u8 mac[ETH_ALEN]; bool is_static; if ((BIT(dump_ctx->port) & portmap) == 0) - return; + return 0; alr_reg_to_mac(dat0, dat1, mac); is_static = !!(dat1 & LAN9303_ALR_DAT1_STATIC); - dump_ctx->cb(mac, 0, is_static, dump_ctx->data); + return dump_ctx->cb(mac, 0, is_static, dump_ctx->data); } /* Set a static ALR entry. Delete entry if port_map is zero */ @@ -1210,9 +1216,7 @@ static int lan9303_port_fdb_dump(struct dsa_switch *ds, int port, }; dev_dbg(chip->dev, "%s(%d)\n", __func__, port); - lan9303_alr_loop(chip, alr_loop_cb_fdb_port_dump, &dump_ctx); - - return 0; + return lan9303_alr_loop(chip, alr_loop_cb_fdb_port_dump, &dump_ctx); } static int lan9303_port_mdb_prepare(struct dsa_switch *ds, int port, diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c index 314ae78bbd..e78026ef6d 100644 --- a/drivers/net/dsa/lantiq_gswip.c +++ b/drivers/net/dsa/lantiq_gswip.c @@ -1404,11 +1404,17 @@ static int gswip_port_fdb_dump(struct dsa_switch *ds, int port, addr[1] = mac_bridge.key[2] & 0xff; addr[0] = (mac_bridge.key[2] >> 8) & 0xff; if (mac_bridge.val[1] & GSWIP_TABLE_MAC_BRIDGE_STATIC) { - if (mac_bridge.val[0] & BIT(port)) - cb(addr, 0, true, data); + if (mac_bridge.val[0] & BIT(port)) { + err = cb(addr, 0, true, data); + if (err) + return err; + } } else { - if (((mac_bridge.val[0] & GENMASK(7, 4)) >> 4) == port) - cb(addr, 0, false, data); + if (((mac_bridge.val[0] & GENMASK(7, 4)) >> 4) == port) { + err = cb(addr, 0, false, data); + if (err) + return err; + } } } return 0; diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index 560f6843bb..c5142f86a3 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -687,8 +687,8 @@ static void ksz8_r_vlan_entries(struct ksz_device *dev, u16 addr) shifts = ksz8->shifts; ksz8_r_table(dev, TABLE_VLAN, addr, &data); - addr *= dev->phy_port_cnt; - for (i = 0; i < dev->phy_port_cnt; i++) { + addr *= 4; + for (i = 0; i < 4; i++) { dev->vlan_cache[addr + i].table[0] = (u16)data; data >>= shifts[VLAN_TABLE]; } @@ -702,7 +702,7 @@ static void ksz8_r_vlan_table(struct ksz_device *dev, u16 vid, u16 *vlan) u64 buf; data = (u16 *)&buf; - addr = vid / dev->phy_port_cnt; + addr = vid / 4; index = vid & 3; ksz8_r_table(dev, TABLE_VLAN, addr, &buf); *vlan = data[index]; @@ -716,7 +716,7 @@ static void ksz8_w_vlan_table(struct ksz_device *dev, u16 vid, u16 vlan) u64 buf; data = (u16 *)&buf; - addr = vid / dev->phy_port_cnt; + addr = vid / 4; index = vid & 3; ksz8_r_table(dev, TABLE_VLAN, addr, &buf); data[index] = vlan; @@ -1119,24 +1119,67 @@ static int ksz8_port_vlan_filtering(struct dsa_switch *ds, int port, bool flag, if (ksz_is_ksz88x3(dev)) return -ENOTSUPP; + /* Discard packets with VID not enabled on the switch */ ksz_cfg(dev, S_MIRROR_CTRL, SW_VLAN_ENABLE, flag); + /* Discard packets with VID not enabled on the ingress port */ + for (port = 0; port < dev->phy_port_cnt; ++port) + ksz_port_cfg(dev, port, REG_PORT_CTRL_2, PORT_INGRESS_FILTER, + flag); + return 0; } +static void ksz8_port_enable_pvid(struct ksz_device *dev, int port, bool state) +{ + if (ksz_is_ksz88x3(dev)) { + ksz_cfg(dev, REG_SW_INSERT_SRC_PVID, + 0x03 << (4 - 2 * port), state); + } else { + ksz_pwrite8(dev, port, REG_PORT_CTRL_12, state ? 0x0f : 0x00); + } +} + static int ksz8_port_vlan_add(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan, struct netlink_ext_ack *extack) { bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED; struct ksz_device *dev = ds->priv; + struct ksz_port *p = &dev->ports[port]; u16 data, new_pvid = 0; u8 fid, member, valid; if (ksz_is_ksz88x3(dev)) return -ENOTSUPP; - ksz_port_cfg(dev, port, P_TAG_CTRL, PORT_REMOVE_TAG, untagged); + /* If a VLAN is added with untagged flag different from the + * port's Remove Tag flag, we need to change the latter. + * Ignore VID 0, which is always untagged. + * Ignore CPU port, which will always be tagged. + */ + if (untagged != p->remove_tag && vlan->vid != 0 && + port != dev->cpu_port) { + unsigned int vid; + + /* Reject attempts to add a VLAN that requires the + * Remove Tag flag to be changed, unless there are no + * other VLANs currently configured. + */ + for (vid = 1; vid < dev->num_vlans; ++vid) { + /* Skip the VID we are going to add or reconfigure */ + if (vid == vlan->vid) + continue; + + ksz8_from_vlan(dev, dev->vlan_cache[vid].table[0], + &fid, &member, &valid); + if (valid && (member & BIT(port))) + return -EINVAL; + } + + ksz_port_cfg(dev, port, P_TAG_CTRL, PORT_REMOVE_TAG, untagged); + p->remove_tag = untagged; + } ksz8_r_vlan_table(dev, vlan->vid, &data); ksz8_from_vlan(dev, data, &fid, &member, &valid); @@ -1160,9 +1203,11 @@ static int ksz8_port_vlan_add(struct dsa_switch *ds, int port, u16 vid; ksz_pread16(dev, port, REG_PORT_CTRL_VID, &vid); - vid &= 0xfff; + vid &= ~VLAN_VID_MASK; vid |= new_pvid; ksz_pwrite16(dev, port, REG_PORT_CTRL_VID, vid); + + ksz8_port_enable_pvid(dev, port, true); } return 0; @@ -1171,9 +1216,8 @@ static int ksz8_port_vlan_add(struct dsa_switch *ds, int port, static int ksz8_port_vlan_del(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan) { - bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED; struct ksz_device *dev = ds->priv; - u16 data, pvid, new_pvid = 0; + u16 data, pvid; u8 fid, member, valid; if (ksz_is_ksz88x3(dev)) @@ -1182,8 +1226,6 @@ static int ksz8_port_vlan_del(struct dsa_switch *ds, int port, ksz_pread16(dev, port, REG_PORT_CTRL_VID, &pvid); pvid = pvid & 0xFFF; - ksz_port_cfg(dev, port, P_TAG_CTRL, PORT_REMOVE_TAG, untagged); - ksz8_r_vlan_table(dev, vlan->vid, &data); ksz8_from_vlan(dev, data, &fid, &member, &valid); @@ -1195,14 +1237,11 @@ static int ksz8_port_vlan_del(struct dsa_switch *ds, int port, valid = 0; } - if (pvid == vlan->vid) - new_pvid = 1; - ksz8_to_vlan(dev, fid, member, valid, &data); ksz8_w_vlan_table(dev, vlan->vid, data); - if (new_pvid != pvid) - ksz_pwrite16(dev, port, REG_PORT_CTRL_VID, pvid); + if (pvid == vlan->vid) + ksz8_port_enable_pvid(dev, port, false); return 0; } @@ -1435,6 +1474,9 @@ static int ksz8_setup(struct dsa_switch *ds) ksz_cfg(dev, S_MIRROR_CTRL, SW_MIRROR_RX_TX, false); + if (!ksz_is_ksz88x3(dev)) + ksz_cfg(dev, REG_SW_CTRL_19, SW_INS_TAG_ENABLE, true); + /* set broadcast storm protection 10% rate */ regmap_update_bits(dev->regmap[1], S_REPLACE_VID_CTRL, BROADCAST_STORM_RATE, @@ -1717,6 +1759,16 @@ static int ksz8_switch_init(struct ksz_device *dev) /* set the real number of ports */ dev->ds->num_ports = dev->port_cnt; + /* We rely on software untagging on the CPU port, so that we + * can support both tagged and untagged VLANs + */ + dev->ds->untag_bridge_pvid = true; + + /* VLAN filtering is partly controlled by the global VLAN + * Enable flag + */ + dev->ds->vlan_filtering_is_global = true; + return 0; } diff --git a/drivers/net/dsa/microchip/ksz8795_reg.h b/drivers/net/dsa/microchip/ksz8795_reg.h index a32355624f..6b40bc25f7 100644 --- a/drivers/net/dsa/microchip/ksz8795_reg.h +++ b/drivers/net/dsa/microchip/ksz8795_reg.h @@ -631,6 +631,10 @@ #define REG_PORT_4_OUT_RATE_3 0xEE #define REG_PORT_5_OUT_RATE_3 0xFE +/* 88x3 specific */ + +#define REG_SW_INSERT_SRC_PVID 0xC2 + /* PME */ #define SW_PME_OUTPUT_ENABLE BIT(1) diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index 2e6bfd333f..1597c63988 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -27,6 +27,7 @@ struct ksz_port_mib { struct ksz_port { u16 member; u16 vid_member; + bool remove_tag; /* Remove Tag flag set, for ksz8795 only */ int stp_state; struct phy_device phydev; @@ -205,12 +206,8 @@ static inline int ksz_read64(struct ksz_device *dev, u32 reg, u64 *val) int ret; ret = regmap_bulk_read(dev->regmap[2], reg, value, 2); - if (!ret) { - /* Ick! ToDo: Add 64bit R/W to regmap on 32bit systems */ - value[0] = swab32(value[0]); - value[1] = swab32(value[1]); - *val = swab64((u64)*value); - } + if (!ret) + *val = (u64)value[0] << 32 | value[1]; return ret; } diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 69f21b7161..632f0fcc5a 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -47,6 +47,7 @@ static const struct mt7530_mib_desc mt7530_mib[] = { MIB_DESC(2, 0x48, "TxBytes"), MIB_DESC(1, 0x60, "RxDrop"), MIB_DESC(1, 0x64, "RxFiltering"), + MIB_DESC(1, 0x68, "RxUnicast"), MIB_DESC(1, 0x6c, "RxMulticast"), MIB_DESC(1, 0x70, "RxBroadcast"), MIB_DESC(1, 0x74, "RxAlignErr"), diff --git a/drivers/net/dsa/qca/ar9331.c b/drivers/net/dsa/qca/ar9331.c index 6686192e18..563d8a2790 100644 --- a/drivers/net/dsa/qca/ar9331.c +++ b/drivers/net/dsa/qca/ar9331.c @@ -101,6 +101,23 @@ AR9331_SW_PORT_STATUS_RX_FLOW_EN | AR9331_SW_PORT_STATUS_TX_FLOW_EN | \ AR9331_SW_PORT_STATUS_SPEED_M) +#define AR9331_SW_REG_PORT_CTRL(_port) (0x104 + (_port) * 0x100) +#define AR9331_SW_PORT_CTRL_HEAD_EN BIT(11) +#define AR9331_SW_PORT_CTRL_PORT_STATE GENMASK(2, 0) +#define AR9331_SW_PORT_CTRL_PORT_STATE_DISABLED 0 +#define AR9331_SW_PORT_CTRL_PORT_STATE_BLOCKING 1 +#define AR9331_SW_PORT_CTRL_PORT_STATE_LISTENING 2 +#define AR9331_SW_PORT_CTRL_PORT_STATE_LEARNING 3 +#define AR9331_SW_PORT_CTRL_PORT_STATE_FORWARD 4 + +#define AR9331_SW_REG_PORT_VLAN(_port) (0x108 + (_port) * 0x100) +#define AR9331_SW_PORT_VLAN_8021Q_MODE GENMASK(31, 30) +#define AR9331_SW_8021Q_MODE_SECURE 3 +#define AR9331_SW_8021Q_MODE_CHECK 2 +#define AR9331_SW_8021Q_MODE_FALLBACK 1 +#define AR9331_SW_8021Q_MODE_NONE 0 +#define AR9331_SW_PORT_VLAN_PORT_VID_MEMBER GENMASK(25, 16) + /* MIB registers */ #define AR9331_MIB_COUNTER(x) (0x20000 + ((x) * 0x100)) @@ -371,11 +388,59 @@ static int ar9331_sw_mbus_init(struct ar9331_sw_priv *priv) return 0; } +static int ar9331_sw_setup_port(struct dsa_switch *ds, int port) +{ + struct ar9331_sw_priv *priv = (struct ar9331_sw_priv *)ds->priv; + struct regmap *regmap = priv->regmap; + u32 port_mask, port_ctrl, val; + int ret; + + /* Generate default port settings */ + port_ctrl = FIELD_PREP(AR9331_SW_PORT_CTRL_PORT_STATE, + AR9331_SW_PORT_CTRL_PORT_STATE_FORWARD); + + if (dsa_is_cpu_port(ds, port)) { + /* CPU port should be allowed to communicate with all user + * ports. + */ + port_mask = dsa_user_ports(ds); + /* Enable Atheros header on CPU port. This will allow us + * communicate with each port separately + */ + port_ctrl |= AR9331_SW_PORT_CTRL_HEAD_EN; + } else if (dsa_is_user_port(ds, port)) { + /* User ports should communicate only with the CPU port. + */ + port_mask = BIT(dsa_upstream_port(ds, port)); + } else { + /* Other ports do not need to communicate at all */ + port_mask = 0; + } + + val = FIELD_PREP(AR9331_SW_PORT_VLAN_8021Q_MODE, + AR9331_SW_8021Q_MODE_NONE) | + FIELD_PREP(AR9331_SW_PORT_VLAN_PORT_VID_MEMBER, port_mask); + + ret = regmap_write(regmap, AR9331_SW_REG_PORT_VLAN(port), val); + if (ret) + goto error; + + ret = regmap_write(regmap, AR9331_SW_REG_PORT_CTRL(port), port_ctrl); + if (ret) + goto error; + + return 0; +error: + dev_err(priv->dev, "%s: error: %i\n", __func__, ret); + + return ret; +} + static int ar9331_sw_setup(struct dsa_switch *ds) { struct ar9331_sw_priv *priv = (struct ar9331_sw_priv *)ds->priv; struct regmap *regmap = priv->regmap; - int ret; + int ret, i; ret = ar9331_sw_reset(priv); if (ret) @@ -402,6 +467,12 @@ static int ar9331_sw_setup(struct dsa_switch *ds) if (ret) goto error; + for (i = 0; i < ds->num_ports; i++) { + ret = ar9331_sw_setup_port(ds, i); + if (ret) + goto error; + } + ds->configure_vlan_while_not_filtering = false; return 0; diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 8667c97543..49eb0ac41b 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -1635,7 +1635,9 @@ static int sja1105_fdb_dump(struct dsa_switch *ds, int port, /* We need to hide the dsa_8021q VLANs from the user. */ if (priv->vlan_state == SJA1105_VLAN_UNAWARE) l2_lookup.vlanid = 0; - cb(macaddr, l2_lookup.vlanid, l2_lookup.lockeds, data); + rc = cb(macaddr, l2_lookup.vlanid, l2_lookup.lockeds, data); + if (rc) + return rc; } return 0; } @@ -3185,6 +3187,7 @@ static void sja1105_teardown(struct dsa_switch *ds) } sja1105_devlink_teardown(ds); + sja1105_mdiobus_unregister(ds); sja1105_flower_teardown(ds); sja1105_tas_teardown(ds); sja1105_ptp_clock_unregister(ds); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 89606587b1..2fe7435039 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -426,7 +426,10 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev) if (ptp && ptp->tx_tstamp_en && !skb_is_gso(skb) && atomic_dec_if_positive(&ptp->tx_avail) >= 0) { - if (!bnxt_ptp_parse(skb, &ptp->tx_seqid)) { + if (!bnxt_ptp_parse(skb, &ptp->tx_seqid, + &ptp->tx_hdr_off)) { + if (vlan_tag_flags) + ptp->tx_hdr_off += VLAN_HLEN; lflags |= cpu_to_le32(TX_BD_FLAGS_STAMP); skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; } else { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h index 3fc6781c5b..94d07a9f70 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h @@ -368,6 +368,7 @@ struct cmd_nums { #define HWRM_FUNC_PTP_TS_QUERY 0x19fUL #define HWRM_FUNC_PTP_EXT_CFG 0x1a0UL #define HWRM_FUNC_PTP_EXT_QCFG 0x1a1UL + #define HWRM_FUNC_KEY_CTX_ALLOC 0x1a2UL #define HWRM_SELFTEST_QLIST 0x200UL #define HWRM_SELFTEST_EXEC 0x201UL #define HWRM_SELFTEST_IRQ 0x202UL @@ -531,8 +532,8 @@ struct hwrm_err_output { #define HWRM_VERSION_MAJOR 1 #define HWRM_VERSION_MINOR 10 #define HWRM_VERSION_UPDATE 2 -#define HWRM_VERSION_RSVD 47 -#define HWRM_VERSION_STR "1.10.2.47" +#define HWRM_VERSION_RSVD 52 +#define HWRM_VERSION_STR "1.10.2.52" /* hwrm_ver_get_input (size:192b/24B) */ struct hwrm_ver_get_input { @@ -585,6 +586,7 @@ struct hwrm_ver_get_output { #define VER_GET_RESP_DEV_CAPS_CFG_CFA_ADV_FLOW_MGNT_SUPPORTED 0x1000UL #define VER_GET_RESP_DEV_CAPS_CFG_CFA_TFLIB_SUPPORTED 0x2000UL #define VER_GET_RESP_DEV_CAPS_CFG_CFA_TRUFLOW_SUPPORTED 0x4000UL + #define VER_GET_RESP_DEV_CAPS_CFG_SECURE_BOOT_CAPABLE 0x8000UL u8 roce_fw_maj_8b; u8 roce_fw_min_8b; u8 roce_fw_bld_8b; @@ -886,7 +888,8 @@ struct hwrm_async_event_cmpl_reset_notify { #define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_EXCEPTION_FATAL (0x2UL << 8) #define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_EXCEPTION_NON_FATAL (0x3UL << 8) #define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FAST_RESET (0x4UL << 8) - #define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_LAST ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FAST_RESET + #define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_ACTIVATION (0x5UL << 8) + #define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_LAST ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_ACTIVATION #define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DELAY_IN_100MS_TICKS_MASK 0xffff0000UL #define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DELAY_IN_100MS_TICKS_SFT 16 }; @@ -1236,13 +1239,14 @@ struct hwrm_async_event_cmpl_error_report_base { u8 timestamp_lo; __le16 timestamp_hi; __le32 event_data1; - #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_MASK 0xffUL - #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_SFT 0 - #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_RESERVED 0x0UL - #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_PAUSE_STORM 0x1UL - #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_INVALID_SIGNAL 0x2UL - #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_NVM 0x3UL - #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_NVM + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_MASK 0xffUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_SFT 0 + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_RESERVED 0x0UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_PAUSE_STORM 0x1UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_INVALID_SIGNAL 0x2UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_NVM 0x3UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DOORBELL_DROP_THRESHOLD 0x4UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DOORBELL_DROP_THRESHOLD }; /* hwrm_async_event_cmpl_error_report_pause_storm (size:128b/16B) */ @@ -1446,6 +1450,8 @@ struct hwrm_func_vf_cfg_input { #define FUNC_VF_CFG_REQ_ENABLES_NUM_VNICS 0x200UL #define FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS 0x400UL #define FUNC_VF_CFG_REQ_ENABLES_NUM_HW_RING_GRPS 0x800UL + #define FUNC_VF_CFG_REQ_ENABLES_NUM_TX_KEY_CTXS 0x1000UL + #define FUNC_VF_CFG_REQ_ENABLES_NUM_RX_KEY_CTXS 0x2000UL __le16 mtu; __le16 guest_vlan; __le16 async_event_cr; @@ -1469,7 +1475,8 @@ struct hwrm_func_vf_cfg_input { __le16 num_vnics; __le16 num_stat_ctxs; __le16 num_hw_ring_grps; - u8 unused_0[4]; + __le16 num_tx_key_ctxs; + __le16 num_rx_key_ctxs; }; /* hwrm_func_vf_cfg_output (size:128b/16B) */ @@ -1493,7 +1500,7 @@ struct hwrm_func_qcaps_input { u8 unused_0[6]; }; -/* hwrm_func_qcaps_output (size:704b/88B) */ +/* hwrm_func_qcaps_output (size:768b/96B) */ struct hwrm_func_qcaps_output { __le16 error_code; __le16 req_type; @@ -1587,7 +1594,8 @@ struct hwrm_func_qcaps_output { #define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_TE_CFA 0x4UL #define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_RE_CFA 0x8UL #define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_PRIMATE 0x10UL - u8 unused_1; + __le16 max_key_ctxs_alloc; + u8 unused_1[7]; u8 valid; }; @@ -1602,7 +1610,7 @@ struct hwrm_func_qcfg_input { u8 unused_0[6]; }; -/* hwrm_func_qcfg_output (size:832b/104B) */ +/* hwrm_func_qcfg_output (size:896b/112B) */ struct hwrm_func_qcfg_output { __le16 error_code; __le16 req_type; @@ -1749,11 +1757,13 @@ struct hwrm_func_qcfg_output { #define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100 (0x1UL << 29) #define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_LAST FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100 __le16 host_mtu; - u8 unused_3; + __le16 alloc_tx_key_ctxs; + __le16 alloc_rx_key_ctxs; + u8 unused_3[5]; u8 valid; }; -/* hwrm_func_cfg_input (size:832b/104B) */ +/* hwrm_func_cfg_input (size:896b/112B) */ struct hwrm_func_cfg_input { __le16 req_type; __le16 cmpl_ring; @@ -1820,6 +1830,8 @@ struct hwrm_func_cfg_input { #define FUNC_CFG_REQ_ENABLES_PARTITION_MAX_BW 0x8000000UL #define FUNC_CFG_REQ_ENABLES_TPID 0x10000000UL #define FUNC_CFG_REQ_ENABLES_HOST_MTU 0x20000000UL + #define FUNC_CFG_REQ_ENABLES_TX_KEY_CTXS 0x40000000UL + #define FUNC_CFG_REQ_ENABLES_RX_KEY_CTXS 0x80000000UL __le16 admin_mtu; __le16 mru; __le16 num_rsscos_ctxs; @@ -1929,6 +1941,9 @@ struct hwrm_func_cfg_input { #define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_LAST FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100 __be16 tpid; __le16 host_mtu; + __le16 num_tx_key_ctxs; + __le16 num_rx_key_ctxs; + u8 unused_0[4]; }; /* hwrm_func_cfg_output (size:128b/16B) */ @@ -2099,6 +2114,7 @@ struct hwrm_func_drv_rgtr_input { #define FUNC_DRV_RGTR_REQ_FLAGS_MASTER_SUPPORT 0x40UL #define FUNC_DRV_RGTR_REQ_FLAGS_FAST_RESET_SUPPORT 0x80UL #define FUNC_DRV_RGTR_REQ_FLAGS_RSS_STRICT_HASH_TYPE_SUPPORT 0x100UL + #define FUNC_DRV_RGTR_REQ_FLAGS_NPAR_1_2_SUPPORT 0x200UL __le32 enables; #define FUNC_DRV_RGTR_REQ_ENABLES_OS_TYPE 0x1UL #define FUNC_DRV_RGTR_REQ_ENABLES_VER 0x2UL @@ -2268,7 +2284,7 @@ struct hwrm_func_resource_qcaps_input { u8 unused_0[6]; }; -/* hwrm_func_resource_qcaps_output (size:448b/56B) */ +/* hwrm_func_resource_qcaps_output (size:512b/64B) */ struct hwrm_func_resource_qcaps_output { __le16 error_code; __le16 req_type; @@ -2300,11 +2316,15 @@ struct hwrm_func_resource_qcaps_output { __le16 max_tx_scheduler_inputs; __le16 flags; #define FUNC_RESOURCE_QCAPS_RESP_FLAGS_MIN_GUARANTEED 0x1UL + __le16 min_tx_key_ctxs; + __le16 max_tx_key_ctxs; + __le16 min_rx_key_ctxs; + __le16 max_rx_key_ctxs; u8 unused_0[5]; u8 valid; }; -/* hwrm_func_vf_resource_cfg_input (size:448b/56B) */ +/* hwrm_func_vf_resource_cfg_input (size:512b/64B) */ struct hwrm_func_vf_resource_cfg_input { __le16 req_type; __le16 cmpl_ring; @@ -2331,6 +2351,10 @@ struct hwrm_func_vf_resource_cfg_input { __le16 max_hw_ring_grps; __le16 flags; #define FUNC_VF_RESOURCE_CFG_REQ_FLAGS_MIN_GUARANTEED 0x1UL + __le16 min_tx_key_ctxs; + __le16 max_tx_key_ctxs; + __le16 min_rx_key_ctxs; + __le16 max_rx_key_ctxs; u8 unused_0[2]; }; @@ -2348,7 +2372,9 @@ struct hwrm_func_vf_resource_cfg_output { __le16 reserved_vnics; __le16 reserved_stat_ctx; __le16 reserved_hw_ring_grps; - u8 unused_0[7]; + __le16 reserved_tx_key_ctxs; + __le16 reserved_rx_key_ctxs; + u8 unused_0[3]; u8 valid; }; @@ -4220,7 +4246,7 @@ struct hwrm_port_lpbk_clr_stats_output { u8 valid; }; -/* hwrm_port_ts_query_input (size:256b/32B) */ +/* hwrm_port_ts_query_input (size:320b/40B) */ struct hwrm_port_ts_query_input { __le16 req_type; __le16 cmpl_ring; @@ -4238,8 +4264,11 @@ struct hwrm_port_ts_query_input { __le16 enables; #define PORT_TS_QUERY_REQ_ENABLES_TS_REQ_TIMEOUT 0x1UL #define PORT_TS_QUERY_REQ_ENABLES_PTP_SEQ_ID 0x2UL + #define PORT_TS_QUERY_REQ_ENABLES_PTP_HDR_OFFSET 0x4UL __le16 ts_req_timeout; __le32 ptp_seq_id; + __le16 ptp_hdr_offset; + u8 unused_1[6]; }; /* hwrm_port_ts_query_output (size:192b/24B) */ @@ -8172,6 +8201,7 @@ struct hwrm_fw_reset_input { u8 host_idx; u8 flags; #define FW_RESET_REQ_FLAGS_RESET_GRACEFUL 0x1UL + #define FW_RESET_REQ_FLAGS_FW_ACTIVATION 0x2UL u8 unused_0[4]; }; @@ -8952,7 +8982,7 @@ struct hwrm_nvm_get_dir_info_output { u8 valid; }; -/* hwrm_nvm_write_input (size:384b/48B) */ +/* hwrm_nvm_write_input (size:448b/56B) */ struct hwrm_nvm_write_input { __le16 req_type; __le16 cmpl_ring; @@ -8968,7 +8998,11 @@ struct hwrm_nvm_write_input { __le16 option; __le16 flags; #define NVM_WRITE_REQ_FLAGS_KEEP_ORIG_ACTIVE_IMG 0x1UL + #define NVM_WRITE_REQ_FLAGS_BATCH_MODE 0x2UL + #define NVM_WRITE_REQ_FLAGS_BATCH_LAST 0x4UL __le32 dir_item_length; + __le32 offset; + __le32 len; __le32 unused_0; }; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c index ec381c2423..81f40ab748 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c @@ -20,7 +20,7 @@ #include "bnxt.h" #include "bnxt_ptp.h" -int bnxt_ptp_parse(struct sk_buff *skb, u16 *seq_id) +int bnxt_ptp_parse(struct sk_buff *skb, u16 *seq_id, u16 *hdr_off) { unsigned int ptp_class; struct ptp_header *hdr; @@ -34,6 +34,7 @@ int bnxt_ptp_parse(struct sk_buff *skb, u16 *seq_id) if (!hdr) return -EINVAL; + *hdr_off = (u8 *)hdr - skb->data; *seq_id = ntohs(hdr->sequence_id); return 0; default: @@ -91,6 +92,7 @@ static int bnxt_hwrm_port_ts_query(struct bnxt *bp, u32 flags, u64 *ts) PORT_TS_QUERY_REQ_FLAGS_PATH_TX) { req.enables = cpu_to_le16(BNXT_PTP_QTS_TX_ENABLES); req.ptp_seq_id = cpu_to_le32(bp->ptp_cfg->tx_seqid); + req.ptp_hdr_offset = cpu_to_le16(bp->ptp_cfg->tx_hdr_off); req.ts_req_timeout = cpu_to_le16(BNXT_PTP_QTS_TIMEOUT); } mutex_lock(&bp->hwrm_cmd_lock); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h index 254ba7bc0f..524f1c2720 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h @@ -10,8 +10,8 @@ #ifndef BNXT_PTP_H #define BNXT_PTP_H -#define BNXT_PTP_GRC_WIN 5 -#define BNXT_PTP_GRC_WIN_BASE 0x5000 +#define BNXT_PTP_GRC_WIN 6 +#define BNXT_PTP_GRC_WIN_BASE 0x6000 #define BNXT_MAX_PHC_DRIFT 31000000 #define BNXT_LO_TIMER_MASK 0x0000ffffffffUL @@ -19,7 +19,8 @@ #define BNXT_PTP_QTS_TIMEOUT 1000 #define BNXT_PTP_QTS_TX_ENABLES (PORT_TS_QUERY_REQ_ENABLES_PTP_SEQ_ID | \ - PORT_TS_QUERY_REQ_ENABLES_TS_REQ_TIMEOUT) + PORT_TS_QUERY_REQ_ENABLES_TS_REQ_TIMEOUT | \ + PORT_TS_QUERY_REQ_ENABLES_PTP_HDR_OFFSET) struct bnxt_ptp_cfg { struct ptp_clock_info ptp_info; @@ -37,6 +38,7 @@ struct bnxt_ptp_cfg { #define BNXT_PHC_OVERFLOW_PERIOD (19 * 3600 * HZ) u16 tx_seqid; + u16 tx_hdr_off; struct bnxt *bp; atomic_t tx_avail; #define BNXT_MAX_TX_TS 1 @@ -74,7 +76,7 @@ do { \ ((dst) = READ_ONCE(src)) #endif -int bnxt_ptp_parse(struct sk_buff *skb, u16 *seq_id); +int bnxt_ptp_parse(struct sk_buff *skb, u16 *seq_id, u16 *hdr_off); int bnxt_hwtstamp_set(struct net_device *dev, struct ifreq *ifr); int bnxt_hwtstamp_get(struct net_device *dev, struct ifreq *ifr); int bnxt_get_tx_ts_p5(struct bnxt *bp, struct sk_buff *skb); diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 44bafedd09..244ec74cec 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -1506,11 +1506,6 @@ static int iavf_reinit_interrupt_scheme(struct iavf_adapter *adapter) set_bit(__IAVF_VSI_DOWN, adapter->vsi.state); iavf_map_rings_to_vectors(adapter); - - if (RSS_AQ(adapter)) - adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_RSS; - else - err = iavf_init_rss(adapter); err: return err; } @@ -2200,6 +2195,14 @@ static void iavf_reset_task(struct work_struct *work) goto reset_err; } + if (RSS_AQ(adapter)) { + adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_RSS; + } else { + err = iavf_init_rss(adapter); + if (err) + goto reset_err; + } + adapter->aq_required |= IAVF_FLAG_AQ_GET_CONFIG; adapter->aq_required |= IAVF_FLAG_AQ_MAP_VECTORS; diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index a450343fbb..eadcb99583 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -234,6 +234,7 @@ enum ice_pf_state { ICE_VFLR_EVENT_PENDING, ICE_FLTR_OVERFLOW_PROMISC, ICE_VF_DIS, + ICE_VF_DEINIT_IN_PROGRESS, ICE_CFG_BUSY, ICE_SERVICE_SCHED, ICE_SERVICE_DIS, diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index ef8d1815af..fe2ded775f 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -191,6 +191,14 @@ static int ice_add_mac_to_unsync_list(struct net_device *netdev, const u8 *addr) struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; + /* Under some circumstances, we might receive a request to delete our + * own device address from our uc list. Because we store the device + * address in the VSI's MAC filter list, we need to ignore such + * requests and not delete our device address from this list. + */ + if (ether_addr_equal(addr, netdev->dev_addr)) + return 0; + if (ice_fltr_add_mac_to_list(vsi, &vsi->tmp_unsync_list, addr, ICE_FWD_TO_VSI)) return -EINVAL; @@ -4194,6 +4202,11 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) struct ice_hw *hw; int i, err; + if (pdev->is_virtfn) { + dev_err(dev, "can't probe a virtual function\n"); + return -EINVAL; + } + /* this driver uses devres, see * Documentation/driver-api/driver-model/devres.rst */ @@ -5119,7 +5132,7 @@ static int ice_set_mac_address(struct net_device *netdev, void *pi) return -EADDRNOTAVAIL; if (ether_addr_equal(netdev->dev_addr, mac)) { - netdev_warn(netdev, "already using mac %pM\n", mac); + netdev_dbg(netdev, "already using mac %pM\n", mac); return 0; } @@ -5130,6 +5143,7 @@ static int ice_set_mac_address(struct net_device *netdev, void *pi) return -EBUSY; } + netif_addr_lock_bh(netdev); /* Clean up old MAC filter. Not an error if old filter doesn't exist */ status = ice_fltr_remove_mac(vsi, netdev->dev_addr, ICE_FWD_TO_VSI); if (status && status != ICE_ERR_DOES_NOT_EXIST) { @@ -5139,30 +5153,28 @@ static int ice_set_mac_address(struct net_device *netdev, void *pi) /* Add filter for new MAC. If filter exists, return success */ status = ice_fltr_add_mac(vsi, mac, ICE_FWD_TO_VSI); - if (status == ICE_ERR_ALREADY_EXISTS) { + if (status == ICE_ERR_ALREADY_EXISTS) /* Although this MAC filter is already present in hardware it's * possible in some cases (e.g. bonding) that dev_addr was * modified outside of the driver and needs to be restored back * to this value. */ - memcpy(netdev->dev_addr, mac, netdev->addr_len); netdev_dbg(netdev, "filter for MAC %pM already exists\n", mac); - return 0; - } - - /* error if the new filter addition failed */ - if (status) + else if (status) + /* error if the new filter addition failed */ err = -EADDRNOTAVAIL; err_update_filters: if (err) { netdev_err(netdev, "can't set MAC %pM. filter update failed\n", mac); + netif_addr_unlock_bh(netdev); return err; } /* change the netdev's MAC address */ memcpy(netdev->dev_addr, mac, netdev->addr_len); + netif_addr_unlock_bh(netdev); netdev_dbg(vsi->netdev, "updated MAC address to %pM\n", netdev->dev_addr); diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index 2826570dab..e93430ab37 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -615,6 +615,8 @@ void ice_free_vfs(struct ice_pf *pf) struct ice_hw *hw = &pf->hw; unsigned int tmp, i; + set_bit(ICE_VF_DEINIT_IN_PROGRESS, pf->state); + if (!pf->vf) return; @@ -680,6 +682,7 @@ void ice_free_vfs(struct ice_pf *pf) i); clear_bit(ICE_VF_DIS, pf->state); + clear_bit(ICE_VF_DEINIT_IN_PROGRESS, pf->state); clear_bit(ICE_FLAG_SRIOV_ENA, pf->flags); } @@ -4415,6 +4418,10 @@ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) struct device *dev; int err = 0; + /* if de-init is underway, don't process messages from VF */ + if (test_bit(ICE_VF_DEINIT_IN_PROGRESS, pf->state)) + return; + dev = ice_pf_to_dev(pf); if (ice_validate_vf_id(pf, vf_id)) { err = -EINVAL; diff --git a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c index 0b3e8f2db2..9a309169db 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c @@ -748,7 +748,7 @@ static void prestera_fdb_offload_notify(struct prestera_port *port, struct switchdev_notifier_fdb_info *info) { - struct switchdev_notifier_fdb_info send_info; + struct switchdev_notifier_fdb_info send_info = {}; send_info.addr = info->addr; send_info.vid = info->vid; @@ -1123,7 +1123,7 @@ static int prestera_switchdev_blk_event(struct notifier_block *unused, static void prestera_fdb_event(struct prestera_switch *sw, struct prestera_event *evt, void *arg) { - struct switchdev_notifier_fdb_info info; + struct switchdev_notifier_fdb_info info = {}; struct net_device *dev = NULL; struct prestera_port *port; struct prestera_lag *lag; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c index df3e4938ec..360e093874 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c @@ -134,6 +134,7 @@ int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, cq->cqn); cq->uar = dev->priv.uar; + cq->irqn = eq->core.irqn; return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index 01a1d02dcf..3f8a98093f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -1019,12 +1019,19 @@ int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer) MLX5_NB_INIT(&tracer->nb, fw_tracer_event, DEVICE_TRACER); mlx5_eq_notifier_register(dev, &tracer->nb); - mlx5_fw_tracer_start(tracer); - + err = mlx5_fw_tracer_start(tracer); + if (err) { + mlx5_core_warn(dev, "FWTracer: Failed to start tracer %d\n", err); + goto err_notifier_unregister; + } return 0; +err_notifier_unregister: + mlx5_eq_notifier_unregister(dev, &tracer->nb); + mlx5_core_destroy_mkey(dev, &tracer->buff.mkey); err_dealloc_pd: mlx5_core_dealloc_pd(dev, tracer->buff.pdn); + cancel_work_sync(&tracer->read_fw_strings_work); 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 8f79f04ecc..1e2d117082 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -124,6 +124,11 @@ static int mlx5e_route_lookup_ipv4_get(struct mlx5e_priv *priv, if (IS_ERR(rt)) return PTR_ERR(rt); + if (rt->rt_type != RTN_UNICAST) { + ret = -ENETUNREACH; + goto err_rt_release; + } + if (mlx5_lag_is_multipath(mdev) && rt->rt_gw_family != AF_INET) { ret = -ENETUNREACH; goto err_rt_release; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 37c4408379..24f919ef9b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1535,15 +1535,9 @@ static int mlx5e_alloc_cq_common(struct mlx5e_priv *priv, { struct mlx5_core_dev *mdev = priv->mdev; struct mlx5_core_cq *mcq = &cq->mcq; - int eqn_not_used; - unsigned int irqn; int err; u32 i; - err = mlx5_vector2eqn(mdev, param->eq_ix, &eqn_not_used, &irqn); - if (err) - return err; - err = mlx5_cqwq_create(mdev, ¶m->wq, param->cqc, &cq->wq, &cq->wq_ctrl); if (err) @@ -1557,7 +1551,6 @@ static int mlx5e_alloc_cq_common(struct mlx5e_priv *priv, mcq->vector = param->eq_ix; mcq->comp = mlx5e_completion_event; mcq->event = mlx5e_cq_error_event; - mcq->irqn = irqn; for (i = 0; i < mlx5_cqwq_get_size(&cq->wq); i++) { struct mlx5_cqe64 *cqe = mlx5_cqwq_get_wqe(&cq->wq, i); @@ -1605,11 +1598,10 @@ static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param) void *in; void *cqc; int inlen; - unsigned int irqn_not_used; int eqn; int err; - err = mlx5_vector2eqn(mdev, param->eq_ix, &eqn, &irqn_not_used); + err = mlx5_vector2eqn(mdev, param->eq_ix, &eqn); if (err) return err; @@ -1891,30 +1883,30 @@ static int mlx5e_open_queues(struct mlx5e_channel *c, if (err) goto err_close_icosq; + err = mlx5e_open_rxq_rq(c, params, &cparam->rq); + if (err) + goto err_close_sqs; + if (c->xdp) { err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, NULL, &c->rq_xdpsq, false); if (err) - goto err_close_sqs; + goto err_close_rq; } - err = mlx5e_open_rxq_rq(c, params, &cparam->rq); - if (err) - goto err_close_xdp_sq; - err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, NULL, &c->xdpsq, true); if (err) - goto err_close_rq; + goto err_close_xdp_sq; return 0; -err_close_rq: - mlx5e_close_rq(&c->rq); - err_close_xdp_sq: if (c->xdp) mlx5e_close_xdpsq(&c->rq_xdpsq); +err_close_rq: + mlx5e_close_rq(&c->rq); + err_close_sqs: mlx5e_close_sqs(c); @@ -1949,9 +1941,9 @@ static int mlx5e_open_queues(struct mlx5e_channel *c, static void mlx5e_close_queues(struct mlx5e_channel *c) { mlx5e_close_xdpsq(&c->xdpsq); - mlx5e_close_rq(&c->rq); if (c->xdp) mlx5e_close_xdpsq(&c->rq_xdpsq); + mlx5e_close_rq(&c->rq); mlx5e_close_sqs(c); mlx5e_close_icosq(&c->icosq); mlx5e_close_icosq(&c->async_icosq); @@ -1983,9 +1975,8 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, struct mlx5e_channel *c; unsigned int irq; int err; - int eqn; - err = mlx5_vector2eqn(priv->mdev, ix, &eqn, &irq); + err = mlx5_vector2irqn(priv->mdev, ix, &irq); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 6e074cc457..605c8ecc36 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -855,8 +855,8 @@ static int create_comp_eqs(struct mlx5_core_dev *dev) return err; } -int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, - unsigned int *irqn) +static int vector2eqnirqn(struct mlx5_core_dev *dev, int vector, int *eqn, + unsigned int *irqn) { struct mlx5_eq_table *table = dev->priv.eq_table; struct mlx5_eq_comp *eq, *n; @@ -865,8 +865,10 @@ int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, list_for_each_entry_safe(eq, n, &table->comp_eqs_list, list) { if (i++ == vector) { - *eqn = eq->core.eqn; - *irqn = eq->core.irqn; + if (irqn) + *irqn = eq->core.irqn; + if (eqn) + *eqn = eq->core.eqn; err = 0; break; } @@ -874,8 +876,18 @@ int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, return err; } + +int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn) +{ + return vector2eqnirqn(dev, vector, eqn, NULL); +} EXPORT_SYMBOL(mlx5_vector2eqn); +int mlx5_vector2irqn(struct mlx5_core_dev *dev, int vector, unsigned int *irqn) +{ + return vector2eqnirqn(dev, vector, NULL, irqn); +} + unsigned int mlx5_comp_vectors_count(struct mlx5_core_dev *dev) { return dev->priv.eq_table->num_comp_eqs; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c index a6e1d4f782..69a3630818 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c @@ -69,7 +69,7 @@ static void mlx5_esw_bridge_fdb_offload_notify(struct net_device *dev, const unsigned char *addr, u16 vid, unsigned long val) { - struct switchdev_notifier_fdb_info send_info; + struct switchdev_notifier_fdb_info send_info = {}; send_info.addr = addr; send_info.vid = vid; @@ -579,7 +579,7 @@ static struct mlx5_esw_bridge *mlx5_esw_bridge_create(int ifindex, xa_init(&bridge->vports); bridge->ifindex = ifindex; bridge->refcnt = 1; - bridge->ageing_time = BR_DEFAULT_AGEING_TIME; + bridge->ageing_time = clock_t_to_jiffies(BR_DEFAULT_AGEING_TIME); list_add(&bridge->list, &br_offloads->bridges); return bridge; @@ -1006,7 +1006,7 @@ int mlx5_esw_bridge_ageing_time_set(unsigned long ageing_time, struct mlx5_eswit if (!vport->bridge) return -EINVAL; - vport->bridge->ageing_time = ageing_time; + vport->bridge->ageing_time = clock_t_to_jiffies(ageing_time); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/sample.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/sample.c index 794012c5c4..d3ad78aa9d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/sample.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/sample.c @@ -501,6 +501,7 @@ mlx5_esw_sample_offload(struct mlx5_esw_psample *esw_psample, err_offload_rule: mlx5_esw_vporttbl_put(esw, &per_vport_tbl_attr); err_default_tbl: + kfree(sample_flow); return ERR_PTR(err); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 011e766e4f..3bb71a1860 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -48,6 +48,7 @@ #include "lib/fs_chains.h" #include "en_tc.h" #include "en/mapping.h" +#include "devlink.h" #define mlx5_esw_for_each_rep(esw, i, rep) \ xa_for_each(&((esw)->offloads.vport_reps), i, rep) @@ -3001,12 +3002,19 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, if (cur_mlx5_mode == mlx5_mode) goto unlock; - if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) + if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) { + if (mlx5_devlink_trap_get_num_active(esw->dev)) { + NL_SET_ERR_MSG_MOD(extack, + "Can't change mode while devlink traps are active"); + err = -EOPNOTSUPP; + goto unlock; + } err = esw_offloads_start(esw, extack); - else if (mode == DEVLINK_ESWITCH_MODE_LEGACY) + } else if (mode == DEVLINK_ESWITCH_MODE_LEGACY) { err = esw_offloads_stop(esw, extack); - else + } else { err = -EINVAL; + } unlock: mlx5_esw_unlock(esw); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c index bd66ab2af5..d5da4ab657 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c @@ -417,7 +417,6 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size) struct mlx5_wq_param wqp; struct mlx5_cqe64 *cqe; int inlen, err, eqn; - unsigned int irqn; void *cqc, *in; __be64 *pas; u32 i; @@ -446,7 +445,7 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size) goto err_cqwq; } - err = mlx5_vector2eqn(mdev, smp_processor_id(), &eqn, &irqn); + err = mlx5_vector2eqn(mdev, smp_processor_id(), &eqn); if (err) { kvfree(in); goto err_cqwq; @@ -476,7 +475,6 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size) *conn->cq.mcq.arm_db = 0; conn->cq.mcq.vector = 0; conn->cq.mcq.comp = mlx5_fpga_conn_cq_complete; - conn->cq.mcq.irqn = irqn; conn->cq.mcq.uar = fdev->conn_res.uar; tasklet_setup(&conn->cq.tasklet, mlx5_fpga_conn_cq_tasklet); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h index 624cedebb5..d3d628b862 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h @@ -104,4 +104,6 @@ void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev); struct cpu_rmap *mlx5_eq_table_get_rmap(struct mlx5_core_dev *dev); #endif +int mlx5_vector2irqn(struct mlx5_core_dev *dev, int vector, unsigned int *irqn); + #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index eb1b316560..c84ad87c99 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1784,16 +1784,14 @@ static int __init init(void) if (err) goto err_sf; -#ifdef CONFIG_MLX5_CORE_EN err = mlx5e_init(); - if (err) { - pci_unregister_driver(&mlx5_core_driver); - goto err_debug; - } -#endif + if (err) + goto err_en; return 0; +err_en: + mlx5_sf_driver_unregister(); err_sf: pci_unregister_driver(&mlx5_core_driver); err_debug: @@ -1803,9 +1801,7 @@ static int __init init(void) static void __exit cleanup(void) { -#ifdef CONFIG_MLX5_CORE_EN mlx5e_cleanup(); -#endif mlx5_sf_driver_unregister(); pci_unregister_driver(&mlx5_core_driver); mlx5_unregister_debugfs(); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 343807ac20..da365b8f01 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -206,8 +206,13 @@ int mlx5_firmware_flash(struct mlx5_core_dev *dev, const struct firmware *fw, int mlx5_fw_version_query(struct mlx5_core_dev *dev, u32 *running_ver, u32 *stored_ver); +#ifdef CONFIG_MLX5_CORE_EN int mlx5e_init(void); void mlx5e_cleanup(void); +#else +static inline int mlx5e_init(void){ return 0; } +static inline void mlx5e_cleanup(void){} +#endif static inline bool mlx5_sriov_is_enabled(struct mlx5_core_dev *dev) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index b25f764daa..3465b363fc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -214,6 +214,7 @@ static struct mlx5_irq *irq_request(struct mlx5_irq_pool *pool, int i) err = -ENOMEM; goto err_cpumask; } + irq->pool = pool; kref_init(&irq->kref); irq->index = i; err = xa_err(xa_store(&pool->irqs, irq->index, irq, GFP_KERNEL)); @@ -222,7 +223,6 @@ static struct mlx5_irq *irq_request(struct mlx5_irq_pool *pool, int i) irq->index, err); goto err_xa; } - irq->pool = pool; return irq; err_xa: free_cpumask_var(irq->mask); @@ -251,8 +251,11 @@ int mlx5_irq_attach_nb(struct mlx5_irq *irq, struct notifier_block *nb) int mlx5_irq_detach_nb(struct mlx5_irq *irq, struct notifier_block *nb) { + int err = 0; + + err = atomic_notifier_chain_unregister(&irq->nh, nb); irq_put(irq); - return atomic_notifier_chain_unregister(&irq->nh, nb); + return err; } struct cpumask *mlx5_irq_get_affinity_mask(struct mlx5_irq *irq) @@ -437,6 +440,7 @@ irq_pool_alloc(struct mlx5_core_dev *dev, int start, int size, char *name, if (!pool) return ERR_PTR(-ENOMEM); pool->dev = dev; + mutex_init(&pool->lock); xa_init_flags(&pool->irqs, XA_FLAGS_ALLOC); pool->xa_num_irqs.min = start; pool->xa_num_irqs.max = start + size - 1; @@ -445,7 +449,6 @@ irq_pool_alloc(struct mlx5_core_dev *dev, int start, int size, char *name, name); pool->min_threshold = min_threshold * MLX5_EQ_REFS_PER_IRQ; pool->max_threshold = max_threshold * MLX5_EQ_REFS_PER_IRQ; - mutex_init(&pool->lock); mlx5_core_dbg(dev, "pool->name = %s, pool->size = %d, pool->start = %d", name, size, start); return pool; @@ -459,6 +462,7 @@ static void irq_pool_free(struct mlx5_irq_pool *pool) xa_for_each(&pool->irqs, index, irq) irq_release(&irq->kref); xa_destroy(&pool->irqs); + mutex_destroy(&pool->lock); kvfree(pool); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c index 12cf323a59..9df0e73d1c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c @@ -749,7 +749,6 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, struct mlx5_cqe64 *cqe; struct mlx5dr_cq *cq; int inlen, err, eqn; - unsigned int irqn; void *cqc, *in; __be64 *pas; int vector; @@ -782,7 +781,7 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, goto err_cqwq; vector = raw_smp_processor_id() % mlx5_comp_vectors_count(mdev); - err = mlx5_vector2eqn(mdev, vector, &eqn, &irqn); + err = mlx5_vector2eqn(mdev, vector, &eqn); if (err) { kvfree(in); goto err_cqwq; @@ -818,7 +817,6 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, *cq->mcq.arm_db = cpu_to_be32(2 << 28); cq->mcq.vector = 0; - cq->mcq.irqn = irqn; cq->mcq.uar = uar; return cq; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c index f1950e4968..e4dd4eed5a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c @@ -352,6 +352,7 @@ static void dr_ste_v0_set_rx_decap(u8 *hw_ste_p) { MLX5_SET(ste_rx_steering_mult, hw_ste_p, tunneling_action, DR_STE_TUNL_ACTION_DECAP); + MLX5_SET(ste_rx_steering_mult, hw_ste_p, fail_on_error, 1); } static void dr_ste_v0_set_rx_pop_vlan(u8 *hw_ste_p) @@ -365,6 +366,7 @@ static void dr_ste_v0_set_rx_decap_l3(u8 *hw_ste_p, bool vlan) MLX5_SET(ste_rx_steering_mult, hw_ste_p, tunneling_action, DR_STE_TUNL_ACTION_L3_DECAP); MLX5_SET(ste_modify_packet, hw_ste_p, action_description, vlan ? 1 : 0); + MLX5_SET(ste_rx_steering_mult, hw_ste_p, fail_on_error, 1); } static void dr_ste_v0_set_rewrite_actions(u8 *hw_ste_p, u16 num_of_actions, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 7e221ef014..f69cbb3852 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -9079,7 +9079,7 @@ mlxsw_sp_rif_fid_fid_get(struct mlxsw_sp_rif *rif, static void mlxsw_sp_rif_fid_fdb_del(struct mlxsw_sp_rif *rif, const char *mac) { - struct switchdev_notifier_fdb_info info; + struct switchdev_notifier_fdb_info info = {}; struct net_device *dev; dev = br_fdb_find_port(rif->dev, mac, 0); @@ -9127,8 +9127,8 @@ mlxsw_sp_rif_vlan_fid_get(struct mlxsw_sp_rif *rif, static void mlxsw_sp_rif_vlan_fdb_del(struct mlxsw_sp_rif *rif, const char *mac) { + struct switchdev_notifier_fdb_info info = {}; u16 vid = mlxsw_sp_fid_8021q_vid(rif->fid); - struct switchdev_notifier_fdb_info info; struct net_device *br_dev; struct net_device *dev; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index c5ef9aa64e..8f90cd323d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -2508,7 +2508,7 @@ mlxsw_sp_fdb_call_notifiers(enum switchdev_notifier_type type, const char *mac, u16 vid, struct net_device *dev, bool offloaded) { - struct switchdev_notifier_fdb_info info; + struct switchdev_notifier_fdb_info info = {}; info.addr = mac; info.vid = vid; diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c b/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c index 0443f66b55..9a8e4f201e 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c @@ -277,7 +277,7 @@ static void sparx5_fdb_call_notifiers(enum switchdev_notifier_type type, const char *mac, u16 vid, struct net_device *dev, bool offloaded) { - struct switchdev_notifier_fdb_info info; + struct switchdev_notifier_fdb_info info = {}; info.addr = mac; info.vid = vid; diff --git a/drivers/net/ethernet/mscc/ocelot_io.c b/drivers/net/ethernet/mscc/ocelot_io.c index ea4e83410f..7390fa3980 100644 --- a/drivers/net/ethernet/mscc/ocelot_io.c +++ b/drivers/net/ethernet/mscc/ocelot_io.c @@ -21,7 +21,7 @@ u32 __ocelot_read_ix(struct ocelot *ocelot, u32 reg, u32 offset) ocelot->map[target][reg & REG_MASK] + offset, &val); return val; } -EXPORT_SYMBOL(__ocelot_read_ix); +EXPORT_SYMBOL_GPL(__ocelot_read_ix); void __ocelot_write_ix(struct ocelot *ocelot, u32 val, u32 reg, u32 offset) { @@ -32,7 +32,7 @@ void __ocelot_write_ix(struct ocelot *ocelot, u32 val, u32 reg, u32 offset) regmap_write(ocelot->targets[target], ocelot->map[target][reg & REG_MASK] + offset, val); } -EXPORT_SYMBOL(__ocelot_write_ix); +EXPORT_SYMBOL_GPL(__ocelot_write_ix); void __ocelot_rmw_ix(struct ocelot *ocelot, u32 val, u32 mask, u32 reg, u32 offset) @@ -45,7 +45,7 @@ void __ocelot_rmw_ix(struct ocelot *ocelot, u32 val, u32 mask, u32 reg, ocelot->map[target][reg & REG_MASK] + offset, mask, val); } -EXPORT_SYMBOL(__ocelot_rmw_ix); +EXPORT_SYMBOL_GPL(__ocelot_rmw_ix); u32 ocelot_port_readl(struct ocelot_port *port, u32 reg) { @@ -58,7 +58,7 @@ u32 ocelot_port_readl(struct ocelot_port *port, u32 reg) regmap_read(port->target, ocelot->map[target][reg & REG_MASK], &val); return val; } -EXPORT_SYMBOL(ocelot_port_readl); +EXPORT_SYMBOL_GPL(ocelot_port_readl); void ocelot_port_writel(struct ocelot_port *port, u32 val, u32 reg) { @@ -69,7 +69,7 @@ void ocelot_port_writel(struct ocelot_port *port, u32 val, u32 reg) regmap_write(port->target, ocelot->map[target][reg & REG_MASK], val); } -EXPORT_SYMBOL(ocelot_port_writel); +EXPORT_SYMBOL_GPL(ocelot_port_writel); void ocelot_port_rmwl(struct ocelot_port *port, u32 val, u32 mask, u32 reg) { @@ -77,7 +77,7 @@ void ocelot_port_rmwl(struct ocelot_port *port, u32 val, u32 mask, u32 reg) ocelot_port_writel(port, (cur & (~mask)) | val, reg); } -EXPORT_SYMBOL(ocelot_port_rmwl); +EXPORT_SYMBOL_GPL(ocelot_port_rmwl); u32 __ocelot_target_read_ix(struct ocelot *ocelot, enum ocelot_target target, u32 reg, u32 offset) @@ -128,7 +128,7 @@ int ocelot_regfields_init(struct ocelot *ocelot, return 0; } -EXPORT_SYMBOL(ocelot_regfields_init); +EXPORT_SYMBOL_GPL(ocelot_regfields_init); static struct regmap_config ocelot_regmap_config = { .reg_bits = 32, @@ -148,4 +148,4 @@ struct regmap *ocelot_regmap_init(struct ocelot *ocelot, struct resource *res) return devm_regmap_init_mmio(ocelot->dev, regs, &ocelot_regmap_config); } -EXPORT_SYMBOL(ocelot_regmap_init); +EXPORT_SYMBOL_GPL(ocelot_regmap_init); diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index c7af5bc3b8..4d8e337f50 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -3502,12 +3502,16 @@ static void rtl_hw_start_8106(struct rtl8169_private *tp) RTL_W8(tp, MCU, RTL_R8(tp, MCU) | EN_NDP | EN_OOB_RESET); RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~PFM_EN); + /* The default value is 0x13. Change it to 0x2f */ + rtl_csi_access_enable(tp, 0x2f); + rtl_eri_write(tp, 0x1d0, ERIAR_MASK_0011, 0x0000); /* disable EEE */ rtl_eri_write(tp, 0x1b0, ERIAR_MASK_0011, 0x0000); rtl_pcie_state_l2l3_disable(tp); + rtl_hw_aspm_clkreq_enable(tp, true); } DECLARE_RTL_COND(rtl_mac_ocp_e00e_cond) diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index a46633606c..1f06b92ee5 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -2715,7 +2715,7 @@ static void rocker_fdb_offload_notify(struct rocker_port *rocker_port, struct switchdev_notifier_fdb_info *recv_info) { - struct switchdev_notifier_fdb_info info; + struct switchdev_notifier_fdb_info info = {}; info.addr = recv_info->addr; info.vid = recv_info->vid; diff --git a/drivers/net/ethernet/rocker/rocker_ofdpa.c b/drivers/net/ethernet/rocker/rocker_ofdpa.c index 967a634ee9..e33a9d283a 100644 --- a/drivers/net/ethernet/rocker/rocker_ofdpa.c +++ b/drivers/net/ethernet/rocker/rocker_ofdpa.c @@ -1822,7 +1822,7 @@ static void ofdpa_port_fdb_learn_work(struct work_struct *work) container_of(work, struct ofdpa_fdb_learn_work, work); bool removing = (lw->flags & OFDPA_OP_FLAG_REMOVE); bool learned = (lw->flags & OFDPA_OP_FLAG_LEARNED); - struct switchdev_notifier_fdb_info info; + struct switchdev_notifier_fdb_info info = {}; info.addr = lw->addr; info.vid = lw->vid; diff --git a/drivers/net/ethernet/ti/am65-cpsw-switchdev.c b/drivers/net/ethernet/ti/am65-cpsw-switchdev.c index 9c29b363e9..599708a3e8 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-switchdev.c +++ b/drivers/net/ethernet/ti/am65-cpsw-switchdev.c @@ -358,7 +358,7 @@ static int am65_cpsw_port_obj_del(struct net_device *ndev, const void *ctx, static void am65_cpsw_fdb_offload_notify(struct net_device *ndev, struct switchdev_notifier_fdb_info *rcv) { - struct switchdev_notifier_fdb_info info; + struct switchdev_notifier_fdb_info info = {}; info.addr = rcv->addr; info.vid = rcv->vid; diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index 57d279fdcc..d1d02001ce 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -920,7 +920,7 @@ static netdev_tx_t cpsw_ndo_start_xmit(struct sk_buff *skb, struct cpdma_chan *txch; int ret, q_idx; - if (skb_padto(skb, CPSW_MIN_PACKET_SIZE)) { + if (skb_put_padto(skb, READ_ONCE(priv->tx_packet_min))) { cpsw_err(priv, tx_err, "packet pad failed\n"); ndev->stats.tx_dropped++; return NET_XMIT_DROP; @@ -1100,7 +1100,7 @@ static int cpsw_ndo_xdp_xmit(struct net_device *ndev, int n, for (i = 0; i < n; i++) { xdpf = frames[i]; - if (xdpf->len < CPSW_MIN_PACKET_SIZE) + if (xdpf->len < READ_ONCE(priv->tx_packet_min)) break; if (cpsw_xdp_tx_frame(priv, xdpf, NULL, priv->emac_port)) @@ -1389,6 +1389,7 @@ static int cpsw_create_ports(struct cpsw_common *cpsw) priv->dev = dev; priv->msg_enable = netif_msg_init(debug_level, CPSW_DEBUG); priv->emac_port = i + 1; + priv->tx_packet_min = CPSW_MIN_PACKET_SIZE; if (is_valid_ether_addr(slave_data->mac_addr)) { ether_addr_copy(priv->mac_addr, slave_data->mac_addr); @@ -1686,6 +1687,7 @@ static int cpsw_dl_switch_mode_set(struct devlink *dl, u32 id, priv = netdev_priv(sl_ndev); slave->port_vlan = vlan; + WRITE_ONCE(priv->tx_packet_min, CPSW_MIN_PACKET_SIZE_VLAN); if (netif_running(sl_ndev)) cpsw_port_add_switch_def_ale_entries(priv, slave); @@ -1714,6 +1716,7 @@ static int cpsw_dl_switch_mode_set(struct devlink *dl, u32 id, priv = netdev_priv(slave->ndev); slave->port_vlan = slave->data->dual_emac_res_vlan; + WRITE_ONCE(priv->tx_packet_min, CPSW_MIN_PACKET_SIZE); cpsw_port_add_dual_emac_def_ale_entries(priv, slave); } diff --git a/drivers/net/ethernet/ti/cpsw_priv.h b/drivers/net/ethernet/ti/cpsw_priv.h index a323bea54f..2951fb7b9d 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.h +++ b/drivers/net/ethernet/ti/cpsw_priv.h @@ -89,7 +89,8 @@ do { \ #define CPSW_POLL_WEIGHT 64 #define CPSW_RX_VLAN_ENCAP_HDR_SIZE 4 -#define CPSW_MIN_PACKET_SIZE (VLAN_ETH_ZLEN) +#define CPSW_MIN_PACKET_SIZE_VLAN (VLAN_ETH_ZLEN) +#define CPSW_MIN_PACKET_SIZE (ETH_ZLEN) #define CPSW_MAX_PACKET_SIZE (VLAN_ETH_FRAME_LEN +\ ETH_FCS_LEN +\ CPSW_RX_VLAN_ENCAP_HDR_SIZE) @@ -380,6 +381,7 @@ struct cpsw_priv { u32 emac_port; struct cpsw_common *cpsw; int offload_fwd_mark; + u32 tx_packet_min; }; #define ndev_to_cpsw(ndev) (((struct cpsw_priv *)netdev_priv(ndev))->cpsw) diff --git a/drivers/net/ethernet/ti/cpsw_switchdev.c b/drivers/net/ethernet/ti/cpsw_switchdev.c index f7fb6e17da..a7d97d429e 100644 --- a/drivers/net/ethernet/ti/cpsw_switchdev.c +++ b/drivers/net/ethernet/ti/cpsw_switchdev.c @@ -368,7 +368,7 @@ static int cpsw_port_obj_del(struct net_device *ndev, const void *ctx, static void cpsw_fdb_offload_notify(struct net_device *ndev, struct switchdev_notifier_fdb_info *rcv) { - struct switchdev_notifier_fdb_info info; + struct switchdev_notifier_fdb_info info = {}; info.addr = rcv->addr; info.vid = rcv->vid; diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index 63fda3fc40..4bd6133982 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -1089,7 +1089,7 @@ struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev, xpcs = kzalloc(sizeof(*xpcs), GFP_KERNEL); if (!xpcs) - return NULL; + return ERR_PTR(-ENOMEM); xpcs->mdiodev = mdiodev; diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 53bdd673ae..5c928f8271 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -1760,8 +1760,6 @@ static struct phy_driver ksphy_driver[] = { .name = "Micrel KSZ87XX Switch", /* PHY_BASIC_FEATURES */ .config_init = kszphy_config_init, - .config_aneg = ksz8873mll_config_aneg, - .read_status = ksz8873mll_read_status, .match_phy_device = ksz8795_match_phy_device, .suspend = genphy_suspend, .resume = genphy_resume, diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 930e49ef15..7a099c3752 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -284,7 +284,7 @@ static struct channel *ppp_find_channel(struct ppp_net *pn, int unit); static int ppp_connect_channel(struct channel *pch, int unit); static int ppp_disconnect_channel(struct channel *pch); static void ppp_destroy_channel(struct channel *pch); -static int unit_get(struct idr *p, void *ptr); +static int unit_get(struct idr *p, void *ptr, int min); static int unit_set(struct idr *p, void *ptr, int n); static void unit_put(struct idr *p, int n); static void *unit_find(struct idr *p, int n); @@ -1155,9 +1155,20 @@ static int ppp_unit_register(struct ppp *ppp, int unit, bool ifname_is_set) mutex_lock(&pn->all_ppp_mutex); if (unit < 0) { - ret = unit_get(&pn->units_idr, ppp); + ret = unit_get(&pn->units_idr, ppp, 0); if (ret < 0) goto err; + if (!ifname_is_set) { + while (1) { + snprintf(ppp->dev->name, IFNAMSIZ, "ppp%i", ret); + if (!__dev_get_by_name(ppp->ppp_net, ppp->dev->name)) + break; + unit_put(&pn->units_idr, ret); + ret = unit_get(&pn->units_idr, ppp, ret + 1); + if (ret < 0) + goto err; + } + } } else { /* Caller asked for a specific unit number. Fail with -EEXIST * if unavailable. For backward compatibility, return -EEXIST @@ -1306,7 +1317,7 @@ static int ppp_nl_newlink(struct net *src_net, struct net_device *dev, * the PPP unit identifer as suffix (i.e. ppp). This allows * userspace to infer the device name using to the PPPIOCGUNIT ioctl. */ - if (!tb[IFLA_IFNAME]) + if (!tb[IFLA_IFNAME] || !nla_len(tb[IFLA_IFNAME]) || !*(char *)nla_data(tb[IFLA_IFNAME])) conf.ifname_is_set = false; err = ppp_dev_configure(src_net, dev, &conf); @@ -3552,9 +3563,9 @@ static int unit_set(struct idr *p, void *ptr, int n) } /* get new free unit number and associate pointer with it */ -static int unit_get(struct idr *p, void *ptr) +static int unit_get(struct idr *p, void *ptr, int min) { - return idr_alloc(p, ptr, 0, 0, GFP_KERNEL); + return idr_alloc(p, ptr, min, 0, GFP_KERNEL); } /* put unit number back to a pool */ diff --git a/drivers/net/wwan/mhi_wwan_ctrl.c b/drivers/net/wwan/mhi_wwan_ctrl.c index 1e18420ce4..d0a98f34c5 100644 --- a/drivers/net/wwan/mhi_wwan_ctrl.c +++ b/drivers/net/wwan/mhi_wwan_ctrl.c @@ -41,14 +41,14 @@ struct mhi_wwan_dev { /* Increment RX budget and schedule RX refill if necessary */ static void mhi_wwan_rx_budget_inc(struct mhi_wwan_dev *mhiwwan) { - spin_lock(&mhiwwan->rx_lock); + spin_lock_bh(&mhiwwan->rx_lock); mhiwwan->rx_budget++; if (test_bit(MHI_WWAN_RX_REFILL, &mhiwwan->flags)) schedule_work(&mhiwwan->rx_refill); - spin_unlock(&mhiwwan->rx_lock); + spin_unlock_bh(&mhiwwan->rx_lock); } /* Decrement RX budget if non-zero and return true on success */ @@ -56,7 +56,7 @@ static bool mhi_wwan_rx_budget_dec(struct mhi_wwan_dev *mhiwwan) { bool ret = false; - spin_lock(&mhiwwan->rx_lock); + spin_lock_bh(&mhiwwan->rx_lock); if (mhiwwan->rx_budget) { mhiwwan->rx_budget--; @@ -64,7 +64,7 @@ static bool mhi_wwan_rx_budget_dec(struct mhi_wwan_dev *mhiwwan) ret = true; } - spin_unlock(&mhiwwan->rx_lock); + spin_unlock_bh(&mhiwwan->rx_lock); return ret; } @@ -130,9 +130,9 @@ static void mhi_wwan_ctrl_stop(struct wwan_port *port) { struct mhi_wwan_dev *mhiwwan = wwan_port_get_drvdata(port); - spin_lock(&mhiwwan->rx_lock); + spin_lock_bh(&mhiwwan->rx_lock); clear_bit(MHI_WWAN_RX_REFILL, &mhiwwan->flags); - spin_unlock(&mhiwwan->rx_lock); + spin_unlock_bh(&mhiwwan->rx_lock); cancel_work_sync(&mhiwwan->rx_refill); diff --git a/drivers/net/wwan/wwan_core.c b/drivers/net/wwan/wwan_core.c index 674a81d79d..35ece98134 100644 --- a/drivers/net/wwan/wwan_core.c +++ b/drivers/net/wwan/wwan_core.c @@ -164,11 +164,14 @@ static struct wwan_device *wwan_create_dev(struct device *parent) goto done_unlock; id = ida_alloc(&wwan_dev_ids, GFP_KERNEL); - if (id < 0) + if (id < 0) { + wwandev = ERR_PTR(id); goto done_unlock; + } wwandev = kzalloc(sizeof(*wwandev), GFP_KERNEL); if (!wwandev) { + wwandev = ERR_PTR(-ENOMEM); ida_free(&wwan_dev_ids, id); goto done_unlock; } @@ -182,7 +185,8 @@ static struct wwan_device *wwan_create_dev(struct device *parent) err = device_register(&wwandev->dev); if (err) { put_device(&wwandev->dev); - wwandev = NULL; + wwandev = ERR_PTR(err); + goto done_unlock; } done_unlock: @@ -1014,8 +1018,8 @@ int wwan_register_ops(struct device *parent, const struct wwan_ops *ops, return -EINVAL; wwandev = wwan_create_dev(parent); - if (!wwandev) - return -ENOMEM; + if (IS_ERR(wwandev)) + return PTR_ERR(wwandev); if (WARN_ON(wwandev->ops)) { wwan_remove_dev(wwandev); diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index 2403b71b60..745478213f 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -2527,7 +2527,7 @@ static void deactivate_labels(void *region) static int init_active_labels(struct nd_region *nd_region) { - int i; + int i, rc = 0; for (i = 0; i < nd_region->ndr_mappings; i++) { struct nd_mapping *nd_mapping = &nd_region->mapping[i]; @@ -2546,13 +2546,14 @@ static int init_active_labels(struct nd_region *nd_region) else if (test_bit(NDD_LABELING, &nvdimm->flags)) /* fail, labels needed to disambiguate dpa */; else - return 0; + continue; dev_err(&nd_region->dev, "%s: is %s, failing probe\n", dev_name(&nd_mapping->nvdimm->dev), test_bit(NDD_LOCKED, &nvdimm->flags) ? "locked" : "disabled"); - return -ENXIO; + rc = -ENXIO; + goto out; } nd_mapping->ndd = ndd; atomic_inc(&nvdimm->busy); @@ -2586,13 +2587,17 @@ static int init_active_labels(struct nd_region *nd_region) break; } - if (i < nd_region->ndr_mappings) { + if (i < nd_region->ndr_mappings) + rc = -ENOMEM; + +out: + if (rc) { deactivate_labels(nd_region); - return -ENOMEM; + return rc; } return devm_add_action_or_reset(&nd_region->dev, deactivate_labels, - nd_region); + nd_region); } int nd_region_register_namespaces(struct nd_region *nd_region, int *err) diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 9232255c85..e5e75331b4 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -143,24 +143,25 @@ static inline __attribute_const__ u32 msi_mask(unsigned x) * reliably as devices without an INTx disable bit will then generate a * level IRQ which will never be cleared. */ -u32 __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) +void __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) { - u32 mask_bits = desc->masked; + raw_spinlock_t *lock = &desc->dev->msi_lock; + unsigned long flags; if (pci_msi_ignore_mask || !desc->msi_attrib.maskbit) - return 0; + return; - mask_bits &= ~mask; - mask_bits |= flag; + raw_spin_lock_irqsave(lock, flags); + desc->masked &= ~mask; + desc->masked |= flag; pci_write_config_dword(msi_desc_to_pci_dev(desc), desc->mask_pos, - mask_bits); - - return mask_bits; + desc->masked); + raw_spin_unlock_irqrestore(lock, flags); } static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) { - desc->masked = __pci_msi_desc_mask_irq(desc, mask, flag); + __pci_msi_desc_mask_irq(desc, mask, flag); } static void __iomem *pci_msix_desc_addr(struct msi_desc *desc) @@ -289,13 +290,31 @@ void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg) /* Don't touch the hardware now */ } else if (entry->msi_attrib.is_msix) { void __iomem *base = pci_msix_desc_addr(entry); + bool unmasked = !(entry->masked & PCI_MSIX_ENTRY_CTRL_MASKBIT); if (!base) goto skip; + /* + * The specification mandates that the entry is masked + * when the message is modified: + * + * "If software changes the Address or Data value of an + * entry while the entry is unmasked, the result is + * undefined." + */ + if (unmasked) + __pci_msix_desc_mask_irq(entry, PCI_MSIX_ENTRY_CTRL_MASKBIT); + writel(msg->address_lo, base + PCI_MSIX_ENTRY_LOWER_ADDR); writel(msg->address_hi, base + PCI_MSIX_ENTRY_UPPER_ADDR); writel(msg->data, base + PCI_MSIX_ENTRY_DATA); + + if (unmasked) + __pci_msix_desc_mask_irq(entry, 0); + + /* Ensure that the writes are visible in the device */ + readl(base + PCI_MSIX_ENTRY_DATA); } else { int pos = dev->msi_cap; u16 msgctl; @@ -316,6 +335,8 @@ void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg) pci_write_config_word(dev, pos + PCI_MSI_DATA_32, msg->data); } + /* Ensure that the writes are visible in the device */ + pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &msgctl); } skip: @@ -636,21 +657,21 @@ static int msi_capability_init(struct pci_dev *dev, int nvec, /* Configure MSI capability structure */ ret = pci_msi_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSI); if (ret) { - msi_mask_irq(entry, mask, ~mask); + msi_mask_irq(entry, mask, 0); free_msi_irqs(dev); return ret; } ret = msi_verify_entries(dev); if (ret) { - msi_mask_irq(entry, mask, ~mask); + msi_mask_irq(entry, mask, 0); free_msi_irqs(dev); return ret; } ret = populate_msi_sysfs(dev); if (ret) { - msi_mask_irq(entry, mask, ~mask); + msi_mask_irq(entry, mask, 0); free_msi_irqs(dev); return ret; } @@ -691,6 +712,7 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base, { struct irq_affinity_desc *curmsk, *masks = NULL; struct msi_desc *entry; + void __iomem *addr; int ret, i; int vec_count = pci_msix_vec_count(dev); @@ -711,6 +733,7 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base, entry->msi_attrib.is_msix = 1; entry->msi_attrib.is_64 = 1; + if (entries) entry->msi_attrib.entry_nr = entries[i].entry; else @@ -722,6 +745,10 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base, entry->msi_attrib.default_irq = dev->irq; entry->mask_base = base; + addr = pci_msix_desc_addr(entry); + if (addr) + entry->masked = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL); + list_add_tail(&entry->list, dev_to_msi_list(&dev->dev)); if (masks) curmsk++; @@ -732,28 +759,27 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base, return ret; } -static void msix_program_entries(struct pci_dev *dev, - struct msix_entry *entries) +static void msix_update_entries(struct pci_dev *dev, struct msix_entry *entries) { struct msi_desc *entry; - int i = 0; - void __iomem *desc_addr; for_each_pci_msi_entry(entry, dev) { - if (entries) - entries[i++].vector = entry->irq; - - desc_addr = pci_msix_desc_addr(entry); - if (desc_addr) - entry->masked = readl(desc_addr + - PCI_MSIX_ENTRY_VECTOR_CTRL); - else - entry->masked = 0; - - msix_mask_irq(entry, 1); + if (entries) { + entries->vector = entry->irq; + entries++; + } } } +static void msix_mask_all(void __iomem *base, int tsize) +{ + u32 ctrl = PCI_MSIX_ENTRY_CTRL_MASKBIT; + int i; + + for (i = 0; i < tsize; i++, base += PCI_MSIX_ENTRY_SIZE) + writel(ctrl, base + PCI_MSIX_ENTRY_VECTOR_CTRL); +} + /** * msix_capability_init - configure device's MSI-X capability * @dev: pointer to the pci_dev data structure of MSI-X device function @@ -768,22 +794,33 @@ static void msix_program_entries(struct pci_dev *dev, static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries, int nvec, struct irq_affinity *affd) { - int ret; - u16 control; void __iomem *base; + int ret, tsize; + u16 control; - /* Ensure MSI-X is disabled while it is set up */ - pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0); + /* + * Some devices require MSI-X to be enabled before the MSI-X + * registers can be accessed. Mask all the vectors to prevent + * interrupts coming in before they're fully set up. + */ + pci_msix_clear_and_set_ctrl(dev, 0, PCI_MSIX_FLAGS_MASKALL | + PCI_MSIX_FLAGS_ENABLE); pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &control); /* Request & Map MSI-X table region */ - base = msix_map_region(dev, msix_table_size(control)); - if (!base) - return -ENOMEM; + tsize = msix_table_size(control); + base = msix_map_region(dev, tsize); + if (!base) { + ret = -ENOMEM; + goto out_disable; + } + + /* Ensure that all table entries are masked. */ + msix_mask_all(base, tsize); ret = msix_setup_entries(dev, base, entries, nvec, affd); if (ret) - return ret; + goto out_disable; ret = pci_msi_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSIX); if (ret) @@ -794,15 +831,7 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries, if (ret) goto out_free; - /* - * Some devices require MSI-X to be enabled before we can touch the - * MSI-X registers. We need to mask all the vectors to prevent - * interrupts coming in before they're fully set up. - */ - pci_msix_clear_and_set_ctrl(dev, 0, - PCI_MSIX_FLAGS_MASKALL | PCI_MSIX_FLAGS_ENABLE); - - msix_program_entries(dev, entries); + msix_update_entries(dev, entries); ret = populate_msi_sysfs(dev); if (ret) @@ -836,6 +865,9 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries, out_free: free_msi_irqs(dev); +out_disable: + pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0); + return ret; } @@ -930,8 +962,7 @@ static void pci_msi_shutdown(struct pci_dev *dev) /* Return the device with MSI unmasked as initial states */ mask = msi_mask(desc->msi_attrib.multi_cap); - /* Keep cached state to be restored */ - __pci_msi_desc_mask_irq(desc, mask, ~mask); + msi_mask_irq(desc, mask, 0); /* Restore dev->irq to its default pin-assertion IRQ */ dev->irq = desc->msi_attrib.default_irq; @@ -1016,10 +1047,8 @@ static void pci_msix_shutdown(struct pci_dev *dev) } /* Return the device with MSI-X masked as initial states */ - for_each_pci_msi_entry(entry, dev) { - /* Keep cached states to be restored */ + for_each_pci_msi_entry(entry, dev) __pci_msix_desc_mask_irq(entry, 1); - } pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0); pci_intx_for_msi(dev, 1); diff --git a/drivers/pinctrl/intel/pinctrl-tigerlake.c b/drivers/pinctrl/intel/pinctrl-tigerlake.c index 3e4ef2b875..0bcd19597e 100644 --- a/drivers/pinctrl/intel/pinctrl-tigerlake.c +++ b/drivers/pinctrl/intel/pinctrl-tigerlake.c @@ -701,32 +701,32 @@ static const struct pinctrl_pin_desc tglh_pins[] = { static const struct intel_padgroup tglh_community0_gpps[] = { TGL_GPP(0, 0, 24, 0), /* GPP_A */ - TGL_GPP(1, 25, 44, 128), /* GPP_R */ - TGL_GPP(2, 45, 70, 32), /* GPP_B */ - TGL_GPP(3, 71, 78, INTEL_GPIO_BASE_NOMAP), /* vGPIO_0 */ + TGL_GPP(1, 25, 44, 32), /* GPP_R */ + TGL_GPP(2, 45, 70, 64), /* GPP_B */ + TGL_GPP(3, 71, 78, 96), /* vGPIO_0 */ }; static const struct intel_padgroup tglh_community1_gpps[] = { - TGL_GPP(0, 79, 104, 96), /* GPP_D */ - TGL_GPP(1, 105, 128, 64), /* GPP_C */ - TGL_GPP(2, 129, 136, 160), /* GPP_S */ - TGL_GPP(3, 137, 153, 192), /* GPP_G */ - TGL_GPP(4, 154, 180, 224), /* vGPIO */ + TGL_GPP(0, 79, 104, 128), /* GPP_D */ + TGL_GPP(1, 105, 128, 160), /* GPP_C */ + TGL_GPP(2, 129, 136, 192), /* GPP_S */ + TGL_GPP(3, 137, 153, 224), /* GPP_G */ + TGL_GPP(4, 154, 180, 256), /* vGPIO */ }; static const struct intel_padgroup tglh_community3_gpps[] = { - TGL_GPP(0, 181, 193, 256), /* GPP_E */ - TGL_GPP(1, 194, 217, 288), /* GPP_F */ + TGL_GPP(0, 181, 193, 288), /* GPP_E */ + TGL_GPP(1, 194, 217, 320), /* GPP_F */ }; static const struct intel_padgroup tglh_community4_gpps[] = { - TGL_GPP(0, 218, 241, 320), /* GPP_H */ + TGL_GPP(0, 218, 241, 352), /* GPP_H */ TGL_GPP(1, 242, 251, 384), /* GPP_J */ - TGL_GPP(2, 252, 266, 352), /* GPP_K */ + TGL_GPP(2, 252, 266, 416), /* GPP_K */ }; static const struct intel_padgroup tglh_community5_gpps[] = { - TGL_GPP(0, 267, 281, 416), /* GPP_I */ + TGL_GPP(0, 267, 281, 448), /* GPP_I */ TGL_GPP(1, 282, 290, INTEL_GPIO_BASE_NOMAP), /* JTAG */ }; diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c index 5b3b048725..45ebdeba98 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c +++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c @@ -925,12 +925,10 @@ int mtk_pinconf_adv_pull_set(struct mtk_pinctrl *hw, err = hw->soc->bias_set(hw, desc, pullup); if (err) return err; - } else if (hw->soc->bias_set_combo) { - err = hw->soc->bias_set_combo(hw, desc, pullup, arg); - if (err) - return err; } else { - return -ENOTSUPP; + err = mtk_pinconf_bias_set_rev1(hw, desc, pullup); + if (err) + err = mtk_pinconf_bias_set(hw, desc, pullup); } } diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index a76be6cc26..5b764740b8 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -444,8 +444,7 @@ static int amd_gpio_irq_set_wake(struct irq_data *d, unsigned int on) unsigned long flags; struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct amd_gpio *gpio_dev = gpiochip_get_data(gc); - u32 wake_mask = BIT(WAKE_CNTRL_OFF_S0I3) | BIT(WAKE_CNTRL_OFF_S3) | - BIT(WAKE_CNTRL_OFF_S4); + u32 wake_mask = BIT(WAKE_CNTRL_OFF_S0I3) | BIT(WAKE_CNTRL_OFF_S3); raw_spin_lock_irqsave(&gpio_dev->lock, flags); pin_reg = readl(gpio_dev->base + (d->hwirq)*4); diff --git a/drivers/pinctrl/pinctrl-k210.c b/drivers/pinctrl/pinctrl-k210.c index f831526d06..49e32684db 100644 --- a/drivers/pinctrl/pinctrl-k210.c +++ b/drivers/pinctrl/pinctrl-k210.c @@ -950,23 +950,37 @@ static int k210_fpioa_probe(struct platform_device *pdev) return ret; pdata->pclk = devm_clk_get_optional(dev, "pclk"); - if (!IS_ERR(pdata->pclk)) - clk_prepare_enable(pdata->pclk); + if (!IS_ERR(pdata->pclk)) { + ret = clk_prepare_enable(pdata->pclk); + if (ret) + goto disable_clk; + } pdata->sysctl_map = syscon_regmap_lookup_by_phandle_args(np, "canaan,k210-sysctl-power", 1, &pdata->power_offset); - if (IS_ERR(pdata->sysctl_map)) - return PTR_ERR(pdata->sysctl_map); + if (IS_ERR(pdata->sysctl_map)) { + ret = PTR_ERR(pdata->sysctl_map); + goto disable_pclk; + } k210_fpioa_init_ties(pdata); pdata->pctl = pinctrl_register(&k210_pinctrl_desc, dev, (void *)pdata); - if (IS_ERR(pdata->pctl)) - return PTR_ERR(pdata->pctl); + if (IS_ERR(pdata->pctl)) { + ret = PTR_ERR(pdata->pctl); + goto disable_pclk; + } return 0; + +disable_pclk: + clk_disable_unprepare(pdata->pclk); +disable_clk: + clk_disable_unprepare(pdata->clk); + + return ret; } static const struct of_device_id k210_fpioa_dt_ids[] = { diff --git a/drivers/pinctrl/qcom/Kconfig b/drivers/pinctrl/qcom/Kconfig index 2f51b4f993..cad4e60df6 100644 --- a/drivers/pinctrl/qcom/Kconfig +++ b/drivers/pinctrl/qcom/Kconfig @@ -13,7 +13,7 @@ config PINCTRL_MSM config PINCTRL_APQ8064 tristate "Qualcomm APQ8064 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -21,7 +21,7 @@ config PINCTRL_APQ8064 config PINCTRL_APQ8084 tristate "Qualcomm APQ8084 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -29,7 +29,7 @@ config PINCTRL_APQ8084 config PINCTRL_IPQ4019 tristate "Qualcomm IPQ4019 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -37,7 +37,7 @@ config PINCTRL_IPQ4019 config PINCTRL_IPQ8064 tristate "Qualcomm IPQ8064 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -45,7 +45,7 @@ config PINCTRL_IPQ8064 config PINCTRL_IPQ8074 tristate "Qualcomm Technologies, Inc. IPQ8074 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for @@ -55,7 +55,7 @@ config PINCTRL_IPQ8074 config PINCTRL_IPQ6018 tristate "Qualcomm Technologies, Inc. IPQ6018 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for @@ -65,7 +65,7 @@ config PINCTRL_IPQ6018 config PINCTRL_MSM8226 tristate "Qualcomm 8226 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -74,7 +74,7 @@ config PINCTRL_MSM8226 config PINCTRL_MSM8660 tristate "Qualcomm 8660 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -82,7 +82,7 @@ config PINCTRL_MSM8660 config PINCTRL_MSM8960 tristate "Qualcomm 8960 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -90,7 +90,7 @@ config PINCTRL_MSM8960 config PINCTRL_MDM9615 tristate "Qualcomm 9615 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -98,7 +98,7 @@ config PINCTRL_MDM9615 config PINCTRL_MSM8X74 tristate "Qualcomm 8x74 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -106,7 +106,7 @@ config PINCTRL_MSM8X74 config PINCTRL_MSM8916 tristate "Qualcomm 8916 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -114,7 +114,7 @@ config PINCTRL_MSM8916 config PINCTRL_MSM8953 tristate "Qualcomm 8953 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -124,7 +124,7 @@ config PINCTRL_MSM8953 config PINCTRL_MSM8976 tristate "Qualcomm 8976 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -134,7 +134,7 @@ config PINCTRL_MSM8976 config PINCTRL_MSM8994 tristate "Qualcomm 8994 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -143,7 +143,7 @@ config PINCTRL_MSM8994 config PINCTRL_MSM8996 tristate "Qualcomm MSM8996 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -151,7 +151,7 @@ config PINCTRL_MSM8996 config PINCTRL_MSM8998 tristate "Qualcomm MSM8998 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -159,7 +159,7 @@ config PINCTRL_MSM8998 config PINCTRL_QCS404 tristate "Qualcomm QCS404 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -167,7 +167,7 @@ config PINCTRL_QCS404 config PINCTRL_QDF2XXX tristate "Qualcomm Technologies QDF2xxx pin controller driver" - depends on GPIOLIB && ACPI + depends on ACPI depends on PINCTRL_MSM help This is the GPIO driver for the TLMM block found on the @@ -175,7 +175,7 @@ config PINCTRL_QDF2XXX config PINCTRL_QCOM_SPMI_PMIC tristate "Qualcomm SPMI PMIC pin controller driver" - depends on GPIOLIB && OF && SPMI + depends on OF && SPMI select REGMAP_SPMI select PINMUX select PINCONF @@ -190,7 +190,7 @@ config PINCTRL_QCOM_SPMI_PMIC config PINCTRL_QCOM_SSBI_PMIC tristate "Qualcomm SSBI PMIC pin controller driver" - depends on GPIOLIB && OF + depends on OF select PINMUX select PINCONF select GENERIC_PINCONF @@ -204,7 +204,7 @@ config PINCTRL_QCOM_SSBI_PMIC config PINCTRL_SC7180 tristate "Qualcomm Technologies Inc SC7180 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -213,7 +213,7 @@ config PINCTRL_SC7180 config PINCTRL_SC7280 tristate "Qualcomm Technologies Inc SC7280 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -222,7 +222,7 @@ config PINCTRL_SC7280 config PINCTRL_SC8180X tristate "Qualcomm Technologies Inc SC8180x pin controller driver" - depends on GPIOLIB && (OF || ACPI) + depends on (OF || ACPI) depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -231,7 +231,7 @@ config PINCTRL_SC8180X config PINCTRL_SDM660 tristate "Qualcomm Technologies Inc SDM660 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -240,7 +240,7 @@ config PINCTRL_SDM660 config PINCTRL_SDM845 tristate "Qualcomm Technologies Inc SDM845 pin controller driver" - depends on GPIOLIB && (OF || ACPI) + depends on (OF || ACPI) depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -249,7 +249,7 @@ config PINCTRL_SDM845 config PINCTRL_SDX55 tristate "Qualcomm Technologies Inc SDX55 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -258,7 +258,7 @@ config PINCTRL_SDX55 config PINCTRL_SM6125 tristate "Qualcomm Technologies Inc SM6125 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -267,7 +267,7 @@ config PINCTRL_SM6125 config PINCTRL_SM8150 tristate "Qualcomm Technologies Inc SM8150 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -276,7 +276,7 @@ config PINCTRL_SM8150 config PINCTRL_SM8250 tristate "Qualcomm Technologies Inc SM8250 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -285,8 +285,7 @@ config PINCTRL_SM8250 config PINCTRL_SM8350 tristate "Qualcomm Technologies Inc SM8350 pin controller driver" - depends on GPIOLIB && OF - select PINCTRL_MSM + depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the Qualcomm Technologies Inc TLMM block found on the Qualcomm diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c index dc8d39ae04..9c7679c06d 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c +++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c @@ -1219,10 +1219,12 @@ static int sunxi_pinctrl_build_state(struct platform_device *pdev) } /* - * We suppose that we won't have any more functions than pins, - * we'll reallocate that later anyway + * Find an upper bound for the maximum number of functions: in + * the worst case we have gpio_in, gpio_out, irq and up to four + * special functions per pin, plus one entry for the sentinel. + * We'll reallocate that later anyway. */ - pctl->functions = kcalloc(pctl->ngroups, + pctl->functions = kcalloc(4 * pctl->ngroups + 4, sizeof(*pctl->functions), GFP_KERNEL); if (!pctl->functions) diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index 7d385c3b22..d12db6c316 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -508,6 +508,7 @@ config THINKPAD_ACPI depends on RFKILL || RFKILL = n depends on ACPI_VIDEO || ACPI_VIDEO = n depends on BACKLIGHT_CLASS_DEVICE + depends on I2C select ACPI_PLATFORM_PROFILE select HWMON select NVRAM @@ -691,6 +692,7 @@ config INTEL_HID_EVENT tristate "INTEL HID Event" depends on ACPI depends on INPUT + depends on I2C select INPUT_SPARSEKMAP help This driver provides support for the Intel HID Event hotkey interface. @@ -742,6 +744,7 @@ config INTEL_VBTN tristate "INTEL VIRTUAL BUTTON" depends on ACPI depends on INPUT + depends on I2C select INPUT_SPARSEKMAP help This driver provides support for the Intel Virtual Button interface. diff --git a/drivers/platform/x86/dual_accel_detect.h b/drivers/platform/x86/dual_accel_detect.h new file mode 100644 index 0000000000..a9eae17cc4 --- /dev/null +++ b/drivers/platform/x86/dual_accel_detect.h @@ -0,0 +1,76 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Helper code to detect 360 degree hinges (yoga) style 2-in-1 devices using 2 accelerometers + * to allow the OS to determine the angle between the display and the base of the device. + * + * On Windows these are read by a special HingeAngleService process which calls undocumented + * ACPI methods, to let the firmware know if the 2-in-1 is in tablet- or laptop-mode. + * The firmware may use this to disable the kbd and touchpad to avoid spurious input in + * tablet-mode as well as to report SW_TABLET_MODE info to the OS. + * + * Since Linux does not call these undocumented methods, the SW_TABLET_MODE info reported + * by various drivers/platform/x86 drivers is incorrect. These drivers use the detection + * code in this file to disable SW_TABLET_MODE reporting to avoid reporting broken info + * (instead userspace can derive the status itself by directly reading the 2 accels). + */ + +#include +#include + +static int dual_accel_i2c_resource_count(struct acpi_resource *ares, void *data) +{ + struct acpi_resource_i2c_serialbus *sb; + int *count = data; + + if (i2c_acpi_get_i2c_resource(ares, &sb)) + *count = *count + 1; + + return 1; +} + +static int dual_accel_i2c_client_count(struct acpi_device *adev) +{ + int ret, count = 0; + LIST_HEAD(r); + + ret = acpi_dev_get_resources(adev, &r, dual_accel_i2c_resource_count, &count); + if (ret < 0) + return ret; + + acpi_dev_free_resource_list(&r); + return count; +} + +static bool dual_accel_detect_bosc0200(void) +{ + struct acpi_device *adev; + int count; + + adev = acpi_dev_get_first_match_dev("BOSC0200", NULL, -1); + if (!adev) + return false; + + count = dual_accel_i2c_client_count(adev); + + acpi_dev_put(adev); + + return count == 2; +} + +static bool dual_accel_detect(void) +{ + /* Systems which use a pair of accels with KIOX010A / KIOX020A ACPI ids */ + if (acpi_dev_present("KIOX010A", NULL, -1) && + acpi_dev_present("KIOX020A", NULL, -1)) + return true; + + /* Systems which use a single DUAL250E ACPI device to model 2 accels */ + if (acpi_dev_present("DUAL250E", NULL, -1)) + return true; + + /* Systems which use a single BOSC0200 ACPI device to model 2 accels */ + if (dual_accel_detect_bosc0200()) + return true; + + return false; +} diff --git a/drivers/platform/x86/intel-hid.c b/drivers/platform/x86/intel-hid.c index e5fbe017f8..2e4e97a626 100644 --- a/drivers/platform/x86/intel-hid.c +++ b/drivers/platform/x86/intel-hid.c @@ -14,6 +14,7 @@ #include #include #include +#include "dual_accel_detect.h" /* When NOT in tablet mode, VGBS returns with the flag 0x40 */ #define TABLET_MODE_FLAG BIT(6) @@ -122,6 +123,7 @@ struct intel_hid_priv { struct input_dev *array; struct input_dev *switches; bool wakeup_mode; + bool dual_accel; }; #define HID_EVENT_FILTER_UUID "eeec56b3-4442-408f-a792-4edd4d758054" @@ -451,22 +453,9 @@ static void notify_handler(acpi_handle handle, u32 event, void *context) * SW_TABLET_MODE report, in these cases we enable support when receiving * the first event instead of during driver setup. * - * Some 360 degree hinges (yoga) style 2-in-1 devices use 2 accelerometers - * to allow the OS to determine the angle between the display and the base - * of the device. On Windows these are read by a special HingeAngleService - * process which calls an ACPI DSM (Device Specific Method) on the - * ACPI KIOX010A device node for the sensor in the display, to let the - * firmware know if the 2-in-1 is in tablet- or laptop-mode so that it can - * disable the kbd and touchpad to avoid spurious input in tablet-mode. - * - * The linux kxcjk1013 driver calls the DSM for this once at probe time - * to ensure that the builtin kbd and touchpad work. On some devices this - * causes a "spurious" 0xcd event on the intel-hid ACPI dev. In this case - * there is not a functional tablet-mode switch, so we should not register - * the tablet-mode switch device. + * See dual_accel_detect.h for more info on the dual_accel check. */ - if (!priv->switches && (event == 0xcc || event == 0xcd) && - !acpi_dev_present("KIOX010A", NULL, -1)) { + if (!priv->switches && !priv->dual_accel && (event == 0xcc || event == 0xcd)) { dev_info(&device->dev, "switch event received, enable switches supports\n"); err = intel_hid_switches_setup(device); if (err) @@ -607,6 +596,8 @@ static int intel_hid_probe(struct platform_device *device) return -ENOMEM; dev_set_drvdata(&device->dev, priv); + priv->dual_accel = dual_accel_detect(); + err = intel_hid_input_setup(device); if (err) { pr_err("Failed to setup Intel HID hotkeys\n"); diff --git a/drivers/platform/x86/intel-vbtn.c b/drivers/platform/x86/intel-vbtn.c index 888a764efa..3091664310 100644 --- a/drivers/platform/x86/intel-vbtn.c +++ b/drivers/platform/x86/intel-vbtn.c @@ -14,6 +14,7 @@ #include #include #include +#include "dual_accel_detect.h" /* Returned when NOT in tablet mode on some HP Stream x360 11 models */ #define VGBS_TABLET_MODE_FLAG_ALT 0x10 @@ -66,6 +67,7 @@ static const struct key_entry intel_vbtn_switchmap[] = { struct intel_vbtn_priv { struct input_dev *buttons_dev; struct input_dev *switches_dev; + bool dual_accel; bool has_buttons; bool has_switches; bool wakeup_mode; @@ -160,6 +162,10 @@ static void notify_handler(acpi_handle handle, u32 event, void *context) input_dev = priv->buttons_dev; } else if ((ke = sparse_keymap_entry_from_scancode(priv->switches_dev, event))) { if (!priv->has_switches) { + /* See dual_accel_detect.h for more info */ + if (priv->dual_accel) + return; + dev_info(&device->dev, "Registering Intel Virtual Switches input-dev after receiving a switch event\n"); ret = input_register_device(priv->switches_dev); if (ret) @@ -248,11 +254,15 @@ static const struct dmi_system_id dmi_switches_allow_list[] = { {} /* Array terminator */ }; -static bool intel_vbtn_has_switches(acpi_handle handle) +static bool intel_vbtn_has_switches(acpi_handle handle, bool dual_accel) { unsigned long long vgbs; acpi_status status; + /* See dual_accel_detect.h for more info */ + if (dual_accel) + return false; + if (!dmi_check_system(dmi_switches_allow_list)) return false; @@ -263,13 +273,14 @@ static bool intel_vbtn_has_switches(acpi_handle handle) static int intel_vbtn_probe(struct platform_device *device) { acpi_handle handle = ACPI_HANDLE(&device->dev); - bool has_buttons, has_switches; + bool dual_accel, has_buttons, has_switches; struct intel_vbtn_priv *priv; acpi_status status; int err; + dual_accel = dual_accel_detect(); has_buttons = acpi_has_method(handle, "VBDL"); - has_switches = intel_vbtn_has_switches(handle); + has_switches = intel_vbtn_has_switches(handle, dual_accel); if (!has_buttons && !has_switches) { dev_warn(&device->dev, "failed to read Intel Virtual Button driver\n"); @@ -281,6 +292,7 @@ static int intel_vbtn_probe(struct platform_device *device) return -ENOMEM; dev_set_drvdata(&device->dev, priv); + priv->dual_accel = dual_accel; priv->has_buttons = has_buttons; priv->has_switches = has_switches; diff --git a/drivers/platform/x86/pcengines-apuv2.c b/drivers/platform/x86/pcengines-apuv2.c index c37349f97b..d063d91db9 100644 --- a/drivers/platform/x86/pcengines-apuv2.c +++ b/drivers/platform/x86/pcengines-apuv2.c @@ -94,6 +94,7 @@ 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), + {} /* Terminating entry */ } }; @@ -123,6 +124,7 @@ static struct gpiod_lookup_table gpios_key_table = { .table = { GPIO_LOOKUP_IDX(AMD_FCH_GPIO_DRIVER_NAME, APU2_GPIO_LINE_MODESW, NULL, 0, GPIO_ACTIVE_LOW), + {} /* Terminating entry */ } }; diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 603156a6e3..50ff04c846 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -73,6 +73,7 @@ #include #include #include +#include "dual_accel_detect.h" /* ThinkPad CMOS commands */ #define TP_CMOS_VOLUME_DOWN 0 @@ -3232,7 +3233,7 @@ static int hotkey_init_tablet_mode(void) * the laptop/tent/tablet mode to the EC. The bmc150 iio driver * does not support this, so skip the hotkey on these models. */ - if (has_tablet_mode && !acpi_dev_present("BOSC0200", "1", -1)) + if (has_tablet_mode && !dual_accel_detect()) tp_features.hotkey_tablet = TP_HOTKEY_TABLET_USES_GMMS; type = "GMMS"; } else if (acpi_evalf(hkey_handle, &res, "MHKG", "qd")) { diff --git a/drivers/ptp/ptp_sysfs.c b/drivers/ptp/ptp_sysfs.c index b3d96b7472..41b92dc2f0 100644 --- a/drivers/ptp/ptp_sysfs.c +++ b/drivers/ptp/ptp_sysfs.c @@ -154,7 +154,7 @@ static int unregister_vclock(struct device *dev, void *data) struct ptp_clock *ptp = dev_get_drvdata(dev); struct ptp_clock_info *info = ptp->info; struct ptp_vclock *vclock; - u8 *num = data; + u32 *num = data; vclock = info_to_vclock(info); dev_info(dev->parent, "delete virtual clock ptp%d\n", diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 2abf86c104..d7cdd9cfe4 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -279,7 +279,7 @@ static void qeth_l2_set_pnso_mode(struct qeth_card *card, static void qeth_l2_dev2br_fdb_flush(struct qeth_card *card) { - struct switchdev_notifier_fdb_info info; + struct switchdev_notifier_fdb_info info = {}; QETH_CARD_TEXT(card, 2, "fdbflush"); @@ -679,7 +679,7 @@ static void qeth_l2_dev2br_fdb_notify(struct qeth_card *card, u8 code, struct net_if_token *token, struct mac_addr_lnid *addr_lnid) { - struct switchdev_notifier_fdb_info info; + struct switchdev_notifier_fdb_info info = {}; u8 ntfy_mac[ETH_ALEN]; ether_addr_copy(ntfy_mac, addr_lnid->mac); diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 5983e05b64..e29523a1b5 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -13193,6 +13193,8 @@ lpfc_pci_probe_one_s4(struct pci_dev *pdev, const struct pci_device_id *pid) if (!phba) return -ENOMEM; + INIT_LIST_HEAD(&phba->poll_list); + /* Perform generic PCI device enabling operation */ error = lpfc_enable_pci_dev(phba); if (error) @@ -13327,7 +13329,6 @@ lpfc_pci_probe_one_s4(struct pci_dev *pdev, const struct pci_device_id *pid) /* Enable RAS FW log support */ lpfc_sli4_ras_setup(phba); - INIT_LIST_HEAD(&phba->poll_list); timer_setup(&phba->cpuhp_poll_timer, lpfc_sli4_poll_hbtimer, 0); cpuhp_state_add_instance_nocalls(lpfc_cpuhp_state, &phba->cpuhp); diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 19b1c0cf5f..cf4a3a2c22 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -7851,7 +7851,7 @@ _base_make_ioc_operational(struct MPT3SAS_ADAPTER *ioc) return r; } - rc = _base_static_config_pages(ioc); + r = _base_static_config_pages(ioc); if (r) return r; diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 328bb961c2..37506b3fe5 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1199,14 +1199,24 @@ static void storvsc_on_io_completion(struct storvsc_device *stor_device, vstor_packet->vm_srb.sense_info_length); if (vstor_packet->vm_srb.scsi_status != 0 || - vstor_packet->vm_srb.srb_status != SRB_STATUS_SUCCESS) - storvsc_log(device, STORVSC_LOGGING_ERROR, + vstor_packet->vm_srb.srb_status != SRB_STATUS_SUCCESS) { + + /* + * Log TEST_UNIT_READY errors only as warnings. Hyper-V can + * return errors when detecting devices using TEST_UNIT_READY, + * and logging these as errors produces unhelpful noise. + */ + int loglevel = (stor_pkt->vm_srb.cdb[0] == TEST_UNIT_READY) ? + STORVSC_LOGGING_WARN : STORVSC_LOGGING_ERROR; + + storvsc_log(device, loglevel, "tag#%d cmd 0x%x status: scsi 0x%x srb 0x%x hv 0x%x\n", request->cmd->request->tag, stor_pkt->vm_srb.cdb[0], vstor_packet->vm_srb.scsi_status, vstor_packet->vm_srb.srb_status, vstor_packet->status); + } if (vstor_packet->vm_srb.scsi_status == SAM_STAT_CHECK_CONDITION && (vstor_packet->vm_srb.srb_status & SRB_STATUS_AUTOSENSE_VALID)) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index b8d4b2d327..84fe57ef5a 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1741,13 +1741,9 @@ static void dwc3_gadget_ep_cleanup_cancelled_requests(struct dwc3_ep *dep) { struct dwc3_request *req; struct dwc3_request *tmp; - struct list_head local; struct dwc3 *dwc = dep->dwc; -restart: - list_replace_init(&dep->cancelled_list, &local); - - list_for_each_entry_safe(req, tmp, &local, list) { + list_for_each_entry_safe(req, tmp, &dep->cancelled_list, list) { dwc3_gadget_ep_skip_trbs(dep, req); switch (req->status) { case DWC3_REQUEST_STATUS_DISCONNECTED: @@ -1765,9 +1761,6 @@ static void dwc3_gadget_ep_cleanup_cancelled_requests(struct dwc3_ep *dep) break; } } - - if (!list_empty(&dep->cancelled_list)) - goto restart; } static int dwc3_gadget_ep_dequeue(struct usb_ep *ep, @@ -2976,12 +2969,8 @@ static void dwc3_gadget_ep_cleanup_completed_requests(struct dwc3_ep *dep, { struct dwc3_request *req; struct dwc3_request *tmp; - struct list_head local; -restart: - list_replace_init(&dep->started_list, &local); - - list_for_each_entry_safe(req, tmp, &local, list) { + list_for_each_entry_safe(req, tmp, &dep->started_list, list) { int ret; ret = dwc3_gadget_ep_cleanup_completed_request(dep, event, @@ -2989,9 +2978,6 @@ static void dwc3_gadget_ep_cleanup_completed_requests(struct dwc3_ep *dep, if (ret) break; } - - if (!list_empty(&dep->started_list)) - goto restart; } static bool dwc3_gadget_ep_should_continue(struct dwc3_ep *dep) diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 8fea44bbc2..5f6f1b5582 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -641,9 +641,9 @@ static int xhci_move_dequeue_past_td(struct xhci_hcd *xhci, } if ((ep->ep_state & SET_DEQ_PENDING)) { - xhci_warn(xhci, "Set TR Deq already pending, don't submit for 0x%pad\n", - &addr); - return -EBUSY; + xhci_warn(xhci, "WARN A Set TR Deq Ptr command is pending for slot %u ep %u\n", + slot_id, ep_index); + ep->ep_state &= ~SET_DEQ_PENDING; } /* This function gets called from contexts where it cannot sleep */ diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index a952a09e16..306b0f6a42 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -1,3 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * xHCI host controller driver + * + * Copyright (C) 2008 Intel Corp. + * + * Author: Sarah Sharp + * Some code borrowed from the Linux EHCI driver. + */ + #include #include #include @@ -10,11 +20,10 @@ #include "xhci.h" #include "xhci-trace.h" -#include "xhci-mtk.h" #include "xhci-debugfs.h" #include "xhci-dbgcap.h" -#define DRIVER_AUTHOR "Qortal Project" +#define DRIVER_AUTHOR "Sarah Sharp" #define DRIVER_DESC "'eXtensible' Host Controller (xHC) Driver" #define PORT_WAKE_BITS (PORT_WKOC_E | PORT_WKDISC_E | PORT_WKCONN_E) @@ -43,6 +52,19 @@ static bool td_on_ring(struct xhci_td *td, struct xhci_ring *ring) return false; } +/* + * xhci_handshake - spin reading hc until handshake completes or fails + * @ptr: address of hc register to be read + * @mask: bits to look at in result of read + * @done: value of those bits when handshake succeeds + * @usec: timeout in microseconds + * + * Returns negative errno, or zero on success + * + * Success happens when the "mask" bits have the specified value (hardware + * handshake done). There are two failure modes: "usec" have passed (major + * hardware flakeout), or the register reads as all-ones (hardware removed). + */ int xhci_handshake(void __iomem *ptr, u32 mask, u32 done, int usec) { u32 result; @@ -58,6 +80,9 @@ int xhci_handshake(void __iomem *ptr, u32 mask, u32 done, int usec) return ret; } +/* + * Disable interrupts and begin the xHCI halting process. + */ void xhci_quiesce(struct xhci_hcd *xhci) { u32 halted; @@ -74,6 +99,14 @@ void xhci_quiesce(struct xhci_hcd *xhci) writel(cmd, &xhci->op_regs->command); } +/* + * Force HC into halt state. + * + * Disable any IRQs and clear the run/stop bit. + * HC will complete any current and actively pipelined transactions, and + * should halt within 16 ms of the run/stop bit being cleared. + * Read HC Halted bit in the status register to see when the HC is finished. + */ int xhci_halt(struct xhci_hcd *xhci) { int ret; @@ -91,6 +124,9 @@ int xhci_halt(struct xhci_hcd *xhci) return ret; } +/* + * Set the run bit and wait for the host to be running. + */ int xhci_start(struct xhci_hcd *xhci) { u32 temp; @@ -119,6 +155,13 @@ int xhci_start(struct xhci_hcd *xhci) return ret; } +/* + * Reset a halted HC. + * + * This resets pipelines, timers, counters, state machines, etc. + * Transactions will be terminated immediately, and operational registers + * will be set to their defaults. + */ int xhci_reset(struct xhci_hcd *xhci) { u32 command; @@ -142,6 +185,13 @@ int xhci_reset(struct xhci_hcd *xhci) command |= CMD_RESET; writel(command, &xhci->op_regs->command); + /* Existing Intel xHCI controllers require a delay of 1 mS, + * after setting the CMD_RESET bit, and before accessing any + * HC registers. This allows the HC to complete the + * reset operation and be ready for HC register access. + * Without this delay, the subsequent HC register access, + * may result in a system hang very rarely. + */ if (xhci->quirks & XHCI_INTEL_HOST) udelay(1000); @@ -155,7 +205,10 @@ int xhci_reset(struct xhci_hcd *xhci) xhci_dbg_trace(xhci, trace_xhci_dbg_init, "Wait for controller to be ready for doorbell rings"); - + /* + * xHCI cannot write to any doorbells or operational registers other + * than status until the "Controller Not Ready" flag is cleared. + */ ret = xhci_handshake(&xhci->op_regs->status, STS_CNR, 0, 10 * 1000 * 1000); @@ -176,11 +229,26 @@ static void xhci_zero_64b_regs(struct xhci_hcd *xhci) u64 val; u32 intrs; + /* + * Some Renesas controllers get into a weird state if they are + * reset while programmed with 64bit addresses (they will preserve + * the top half of the address in internal, non visible + * registers). You end up with half the address coming from the + * kernel, and the other half coming from the firmware. Also, + * changing the programming leads to extra accesses even if the + * controller is supposed to be halted. The controller ends up with + * a fatal fault, and is then ripe for being properly reset. + * + * Special care is taken to only apply this if the device is behind + * an iommu. Doing anything when there is no iommu is definitely + * unsafe... + */ if (!(xhci->quirks & XHCI_ZERO_64B_REGS) || !device_iommu_mapped(dev)) return; xhci_info(xhci, "Zeroing 64bit base registers, expecting fault\n"); + /* Clear HSEIE so that faults do not get signaled */ val = readl(&xhci->op_regs->command); val &= ~CMD_HSEIE; writel(val, &xhci->op_regs->command); @@ -190,6 +258,7 @@ static void xhci_zero_64b_regs(struct xhci_hcd *xhci) val |= STS_FATAL; writel(val, &xhci->op_regs->status); + /* Now zero the registers, and brace for impact */ val = xhci_read_64(xhci, &xhci->op_regs->dcbaa_ptr); if (upper_32_bits(val)) xhci_write_64(xhci, 0, &xhci->op_regs->dcbaa_ptr); @@ -227,7 +296,9 @@ static void xhci_zero_64b_regs(struct xhci_hcd *xhci) static int xhci_setup_msi(struct xhci_hcd *xhci) { int ret; - + /* + * TODO:Check with MSI Soc for sysdev + */ struct pci_dev *pdev = to_pci_dev(xhci_to_hcd(xhci)->self.controller); ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI); @@ -257,6 +328,13 @@ static int xhci_setup_msix(struct xhci_hcd *xhci) struct usb_hcd *hcd = xhci_to_hcd(xhci); struct pci_dev *pdev = to_pci_dev(hcd->self.controller); + /* + * calculate number of msi-x vectors supported. + * - HCS_MAX_INTRS: the max number of interrupts the host can handle, + * with max number of interrupters based on the xhci HCSPARAMS1. + * - num_online_cpus: maximum msi-x vectors per CPUs core. + * Add additional 1 vector to ensure always available interrupt. + */ xhci->msix_count = min(num_online_cpus() + 1, HCS_MAX_INTRS(xhci->hcs_params1)); @@ -286,6 +364,7 @@ static int xhci_setup_msix(struct xhci_hcd *xhci) return ret; } +/* Free any IRQs and disable MSI-X */ static void xhci_cleanup_msix(struct xhci_hcd *xhci) { struct usb_hcd *hcd = xhci_to_hcd(xhci); @@ -433,6 +512,16 @@ static void compliance_mode_recovery(struct timer_list *t) jiffies + msecs_to_jiffies(COMP_MODE_RCVRY_MSECS)); } +/* + * Quirk to work around issue generated by the SN65LVPE502CP USB3.0 re-driver + * that causes ports behind that hardware to enter compliance mode sometimes. + * The quirk creates a timer that polls every 2 seconds the link state of + * each host controller's port and recovers it by issuing a Warm reset + * if Compliance mode is detected, otherwise the port will become "dead" (no + * device connections or disconnections will be detected anymore). Becasue no + * status event is generated when entering compliance mode (per xhci spec), + * this quirk is needed on systems that have the failing hardware installed. + */ static void compliance_mode_recovery_timer_init(struct xhci_hcd *xhci) { xhci->port_status_u0 = 0; @@ -446,6 +535,12 @@ static void compliance_mode_recovery_timer_init(struct xhci_hcd *xhci) "Compliance mode recovery timer initialized"); } +/* + * This function identifies the systems that have installed the SN65LVPE502CP + * USB3.0 re-driver and that need the Compliance Mode Quirk. + * Systems: + * Vendor: Hewlett-Packard -> System Models: Z420, Z620 and Z820 + */ static bool xhci_compliance_mode_recovery_timer_quirk_check(void) { const char *dmi_product_name, *dmi_sys_vendor; @@ -472,6 +567,14 @@ static int xhci_all_ports_seen_u0(struct xhci_hcd *xhci) return (xhci->port_status_u0 == ((1 << xhci->usb3_rhub.num_ports) - 1)); } + +/* + * Initialize memory for HCD and xHC (one-time init). + * + * Program the PAGESIZE register, initialize the device context array, create + * device contexts (?), set up a command ring segment (or two?), create event + * ring (one for now). + */ static int xhci_init(struct usb_hcd *hcd) { struct xhci_hcd *xhci = hcd_to_xhci(hcd); @@ -499,6 +602,8 @@ static int xhci_init(struct usb_hcd *hcd) return retval; } +/*-------------------------------------------------------------------------*/ + static int xhci_run_finished(struct xhci_hcd *xhci) { @@ -517,6 +622,18 @@ static int xhci_run_finished(struct xhci_hcd *xhci) return 0; } +/* + * Start the HC after it was halted. + * + * This function is called by the USB core when the HC driver is added. + * Its opposite is xhci_stop(). + * + * xhci_init() must be called once before this function can be called. + * Reset the HC, enable device slot contexts, program DCBAAP, and + * set command ring pointer and event ring pointer. + * + * Setup MSI-X vectors and enable interrupts. + */ int xhci_run(struct usb_hcd *hcd) { u32 temp; @@ -524,6 +641,10 @@ int xhci_run(struct usb_hcd *hcd) int ret; struct xhci_hcd *xhci = hcd_to_xhci(hcd); + /* Start the xHCI host controller running only after the USB 2.0 roothub + * is setup. + */ + hcd->uses_new_polling = 1; if (!usb_hcd_is_primary_hcd(hcd)) return xhci_run_finished(xhci); @@ -582,6 +703,15 @@ int xhci_run(struct usb_hcd *hcd) } EXPORT_SYMBOL_GPL(xhci_run); +/* + * Stop xHCI driver. + * + * This function is called by the USB core when the HC driver is removed. + * Its opposite is xhci_run(). + * + * Disable device contexts, disable IRQs, and quiesce the HC. + * Reset the HC, finish any completed transactions, and cleanup memory. + */ static void xhci_stop(struct usb_hcd *hcd) { u32 temp; @@ -634,6 +764,15 @@ static void xhci_stop(struct usb_hcd *hcd) mutex_unlock(&xhci->mutex); } +/* + * Shutdown HC (not bus-specific) + * + * This is called when the machine is rebooting or halting. We assume that the + * machine will be powered off, and the HC's internal state will be reset. + * Don't bother to free memory. + * + * This will only ever be called with the main usb_hcd (the USB3 roothub). + */ void xhci_shutdown(struct usb_hcd *hcd) { struct xhci_hcd *xhci = hcd_to_xhci(hcd); @@ -700,6 +839,15 @@ static void xhci_set_cmd_ring_deq(struct xhci_hcd *xhci) xhci_write_64(xhci, val_64, &xhci->op_regs->cmd_ring); } +/* + * The whole command ring must be cleared to zero when we suspend the host. + * + * The host doesn't save the command ring pointer in the suspend well, so we + * need to re-program it on resume. Unfortunately, the pointer must be 64-byte + * aligned, because of the reserved bits in the command ring dequeue pointer + * register. Therefore, we can't just set the dequeue pointer back in the + * middle of the ring (TRBs are 16-byte aligned). + */ static void xhci_clear_command_ring(struct xhci_hcd *xhci) { struct xhci_ring *ring; @@ -728,9 +876,25 @@ static void xhci_clear_command_ring(struct xhci_hcd *xhci) */ ring->cycle_state = 1; + /* + * Reset the hardware dequeue pointer. + * Yes, this will need to be re-written after resume, but we're paranoid + * and want to make sure the hardware doesn't access bogus memory + * because, say, the BIOS or an SMI started the host without changing + * the command ring pointers. + */ xhci_set_cmd_ring_deq(xhci); } +/* + * Disable port wake bits if do_wakeup is not set. + * + * Also clear a possible internal port wake state left hanging for ports that + * detected termination but never successfully enumerated (trained to 0U). + * Internal wake causes immediate xHCI wake after suspend. PORT_CSC write done + * at enumeration clears this wake, force one here as well for unconnected ports + */ + static void xhci_disable_hub_port_wake(struct xhci_hcd *xhci, struct xhci_hub *rhub, bool do_wakeup) @@ -1106,6 +1270,113 @@ EXPORT_SYMBOL_GPL(xhci_resume); /*-------------------------------------------------------------------------*/ +static int xhci_map_temp_buffer(struct usb_hcd *hcd, struct urb *urb) +{ + void *temp; + int ret = 0; + unsigned int buf_len; + enum dma_data_direction dir; + + dir = usb_urb_dir_in(urb) ? DMA_FROM_DEVICE : DMA_TO_DEVICE; + buf_len = urb->transfer_buffer_length; + + temp = kzalloc_node(buf_len, GFP_ATOMIC, + dev_to_node(hcd->self.sysdev)); + + if (usb_urb_dir_out(urb)) + sg_pcopy_to_buffer(urb->sg, urb->num_sgs, + temp, buf_len, 0); + + urb->transfer_buffer = temp; + urb->transfer_dma = dma_map_single(hcd->self.sysdev, + urb->transfer_buffer, + urb->transfer_buffer_length, + dir); + + if (dma_mapping_error(hcd->self.sysdev, + urb->transfer_dma)) { + ret = -EAGAIN; + kfree(temp); + } else { + urb->transfer_flags |= URB_DMA_MAP_SINGLE; + } + + return ret; +} + +static bool xhci_urb_temp_buffer_required(struct usb_hcd *hcd, + struct urb *urb) +{ + bool ret = false; + unsigned int i; + unsigned int len = 0; + unsigned int trb_size; + unsigned int max_pkt; + struct scatterlist *sg; + struct scatterlist *tail_sg; + + tail_sg = urb->sg; + max_pkt = usb_endpoint_maxp(&urb->ep->desc); + + if (!urb->num_sgs) + return ret; + + if (urb->dev->speed >= USB_SPEED_SUPER) + trb_size = TRB_CACHE_SIZE_SS; + else + trb_size = TRB_CACHE_SIZE_HS; + + if (urb->transfer_buffer_length != 0 && + !(urb->transfer_flags & URB_NO_TRANSFER_DMA_MAP)) { + for_each_sg(urb->sg, sg, urb->num_sgs, i) { + len = len + sg->length; + if (i > trb_size - 2) { + len = len - tail_sg->length; + if (len < max_pkt) { + ret = true; + break; + } + + tail_sg = sg_next(tail_sg); + } + } + } + return ret; +} + +static void xhci_unmap_temp_buf(struct usb_hcd *hcd, struct urb *urb) +{ + unsigned int len; + unsigned int buf_len; + enum dma_data_direction dir; + + dir = usb_urb_dir_in(urb) ? DMA_FROM_DEVICE : DMA_TO_DEVICE; + + buf_len = urb->transfer_buffer_length; + + if (IS_ENABLED(CONFIG_HAS_DMA) && + (urb->transfer_flags & URB_DMA_MAP_SINGLE)) + dma_unmap_single(hcd->self.sysdev, + urb->transfer_dma, + urb->transfer_buffer_length, + dir); + + if (usb_urb_dir_in(urb)) { + len = sg_pcopy_from_buffer(urb->sg, urb->num_sgs, + urb->transfer_buffer, + buf_len, + 0); + if (len != buf_len) { + xhci_dbg(hcd_to_xhci(hcd), + "Copy from tmp buf to urb sg list failed\n"); + urb->actual_length = len; + } + } + urb->transfer_flags &= ~URB_DMA_MAP_SINGLE; + kfree(urb->transfer_buffer); + urb->transfer_buffer = NULL; +} + /* * Bypass the DMA mapping if URB is suitable for Immediate Transfer (IDT), * we'll copy the actual data into the TRB address register. This is limited to @@ -1115,13 +1386,37 @@ EXPORT_SYMBOL_GPL(xhci_resume); static int xhci_map_urb_for_dma(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flags) { + struct xhci_hcd *xhci; + + xhci = hcd_to_xhci(hcd); + if (xhci_urb_suitable_for_idt(urb)) return 0; + if (xhci->quirks & XHCI_SG_TRB_CACHE_SIZE_QUIRK) { + if (xhci_urb_temp_buffer_required(hcd, urb)) + return xhci_map_temp_buffer(hcd, urb); + } return usb_hcd_map_urb_for_dma(hcd, urb, mem_flags); } -/* +static void xhci_unmap_urb_for_dma(struct usb_hcd *hcd, struct urb *urb) +{ + struct xhci_hcd *xhci; + bool unmap_temp_buf = false; + + xhci = hcd_to_xhci(hcd); + + if (urb->num_sgs && (urb->transfer_flags & URB_DMA_MAP_SINGLE)) + unmap_temp_buf = true; + + if ((xhci->quirks & XHCI_SG_TRB_CACHE_SIZE_QUIRK) && unmap_temp_buf) + xhci_unmap_temp_buf(hcd, urb); + else + usb_hcd_unmap_urb_for_dma(hcd, urb); +} + +/** * xhci_get_endpoint_index - Used for passing endpoint bitmasks between the core and * HCDs. Find the index for an endpoint given its descriptor. Use the return * value to right shift 1 for the bitmask. @@ -1141,6 +1436,7 @@ unsigned int xhci_get_endpoint_index(struct usb_endpoint_descriptor *desc) (usb_endpoint_dir_in(desc) ? 1 : 0) - 1; return index; } +EXPORT_SYMBOL_GPL(xhci_get_endpoint_index); /* The reverse operation to xhci_get_endpoint_index. Calculate the USB endpoint * address from the XHCI endpoint index. @@ -1161,15 +1457,6 @@ static unsigned int xhci_get_endpoint_flag(struct usb_endpoint_descriptor *desc) return 1 << (xhci_get_endpoint_index(desc) + 1); } -/* Find the flag for this endpoint (for use in the control context). Use the - * endpoint index to create a bitmask. The slot context is bit 0, endpoint 0 is - * bit 1, etc. - */ -static unsigned int xhci_get_endpoint_flag_from_index(unsigned int ep_index) -{ - return 1 << (ep_index + 1); -} - /* Compute the last valid endpoint context index. Basically, this is the * endpoint index plus one. For slot contexts with more than valid endpoint, * we find the most significant bit set in the added contexts flags. @@ -1308,6 +1595,12 @@ static int xhci_check_maxpacket(struct xhci_hcd *xhci, unsigned int slot_id, * - force an endpoint configure command * XXX: bandwidth is not recalculated. We should probably do that. */ + +static unsigned int xhci_get_endpoint_flag_from_index(unsigned int ep_index) +{ + return 1 << (ep_index + 1); +} + static void xhci_fixup_endpoint(struct usb_hcd *hcd, struct usb_device *udev, struct usb_host_endpoint *ep, int interval) { @@ -1420,11 +1713,9 @@ static int xhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flag ep_index = xhci_get_endpoint_index(&urb->ep->desc); ep_state = &xhci->devs[slot_id]->eps[ep_index].ep_state; - if (!HCD_HW_ACCESSIBLE(hcd)) { - if (!in_interrupt()) - xhci_dbg(xhci, "urb submitted during PCI suspend\n"); + if (!HCD_HW_ACCESSIBLE(hcd)) return -ESHUTDOWN; - } + if (xhci->devs[slot_id]->flags & VDEV_PORT_ERROR) { xhci_dbg(xhci, "Can't queue urb, port error, link inactive\n"); return -ENODEV; @@ -1630,7 +1921,12 @@ static int xhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status) for (; i < urb_priv->num_tds; i++) { td = &urb_priv->td[i]; - list_add_tail(&td->cancelled_td_list, &ep->cancelled_td_list); + /* TD can already be on cancelled list if ep halted on it */ + if (list_empty(&td->cancelled_td_list)) { + td->cancel_status = TD_DIRTY; + list_add_tail(&td->cancelled_td_list, + &ep->cancelled_td_list); + } } /* Queue a stop endpoint command, but only if this is @@ -1676,8 +1972,8 @@ static int xhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status) * disabled, so there's no need for mutual exclusion to protect * the xhci->devs[slot_id] structure. */ -static int xhci_drop_endpoint(struct usb_hcd *hcd, struct usb_device *udev, - struct usb_host_endpoint *ep) +int xhci_drop_endpoint(struct usb_hcd *hcd, struct usb_device *udev, + struct usb_host_endpoint *ep) { struct xhci_hcd *xhci; struct xhci_container_ctx *in_ctx, *out_ctx; @@ -1737,9 +2033,6 @@ static int xhci_drop_endpoint(struct usb_hcd *hcd, struct usb_device *udev, xhci_endpoint_zero(xhci, xhci->devs[udev->slot_id], ep); - if (xhci->quirks & XHCI_MTK_HOST) - xhci_mtk_drop_ep_quirk(hcd, udev, ep); - xhci_dbg(xhci, "drop ep 0x%x, slot id %d, new drop flags = %#x, new add flags = %#x\n", (unsigned int) ep->desc.bEndpointAddress, udev->slot_id, @@ -1747,6 +2040,7 @@ static int xhci_drop_endpoint(struct usb_hcd *hcd, struct usb_device *udev, (unsigned int) new_add_flags); return 0; } +EXPORT_SYMBOL_GPL(xhci_drop_endpoint); /* Add an endpoint to a new possible bandwidth configuration for this device. * Only one call to this function is allowed per endpoint before @@ -1761,8 +2055,8 @@ static int xhci_drop_endpoint(struct usb_hcd *hcd, struct usb_device *udev, * configuration or alt setting is installed in the device, so there's no need * for mutual exclusion to protect the xhci->devs[slot_id] structure. */ -static int xhci_add_endpoint(struct usb_hcd *hcd, struct usb_device *udev, - struct usb_host_endpoint *ep) +int xhci_add_endpoint(struct usb_hcd *hcd, struct usb_device *udev, + struct usb_host_endpoint *ep) { struct xhci_hcd *xhci; struct xhci_container_ctx *in_ctx; @@ -1836,15 +2130,6 @@ static int xhci_add_endpoint(struct usb_hcd *hcd, struct usb_device *udev, return -ENOMEM; } - if (xhci->quirks & XHCI_MTK_HOST) { - ret = xhci_mtk_add_ep_quirk(hcd, udev, ep); - if (ret < 0) { - xhci_ring_free(xhci, virt_dev->eps[ep_index].new_ring); - virt_dev->eps[ep_index].new_ring = NULL; - return ret; - } - } - ctrl_ctx->add_flags |= cpu_to_le32(added_ctxs); new_add_flags = le32_to_cpu(ctrl_ctx->add_flags); @@ -1869,6 +2154,7 @@ static int xhci_add_endpoint(struct usb_hcd *hcd, struct usb_device *udev, (unsigned int) new_add_flags); return 0; } +EXPORT_SYMBOL_GPL(xhci_add_endpoint); static void xhci_zero_in_ctx(struct xhci_hcd *xhci, struct xhci_virt_device *virt_dev) { @@ -2902,6 +3188,7 @@ int xhci_check_bandwidth(struct usb_hcd *hcd, struct usb_device *udev) return ret; } +EXPORT_SYMBOL_GPL(xhci_check_bandwidth); void xhci_reset_bandwidth(struct usb_hcd *hcd, struct usb_device *udev) { @@ -2926,6 +3213,7 @@ void xhci_reset_bandwidth(struct usb_hcd *hcd, struct usb_device *udev) } xhci_zero_in_ctx(xhci, virt_dev); } +EXPORT_SYMBOL_GPL(xhci_reset_bandwidth); static void xhci_setup_input_ctx_for_config_ep(struct xhci_hcd *xhci, struct xhci_container_ctx *in_ctx, @@ -2939,84 +3227,6 @@ static void xhci_setup_input_ctx_for_config_ep(struct xhci_hcd *xhci, ctrl_ctx->add_flags |= cpu_to_le32(SLOT_FLAG); } -static void xhci_setup_input_ctx_for_quirk(struct xhci_hcd *xhci, - unsigned int slot_id, unsigned int ep_index, - struct xhci_dequeue_state *deq_state) -{ - struct xhci_input_control_ctx *ctrl_ctx; - struct xhci_container_ctx *in_ctx; - struct xhci_ep_ctx *ep_ctx; - u32 added_ctxs; - dma_addr_t addr; - - in_ctx = xhci->devs[slot_id]->in_ctx; - ctrl_ctx = xhci_get_input_control_ctx(in_ctx); - if (!ctrl_ctx) { - xhci_warn(xhci, "%s: Could not get input context, bad type.\n", - __func__); - return; - } - - xhci_endpoint_copy(xhci, xhci->devs[slot_id]->in_ctx, - xhci->devs[slot_id]->out_ctx, ep_index); - ep_ctx = xhci_get_ep_ctx(xhci, in_ctx, ep_index); - addr = xhci_trb_virt_to_dma(deq_state->new_deq_seg, - deq_state->new_deq_ptr); - if (addr == 0) { - xhci_warn(xhci, "WARN Cannot submit config ep after " - "reset ep command\n"); - xhci_warn(xhci, "WARN deq seg = %p, deq ptr = %p\n", - deq_state->new_deq_seg, - deq_state->new_deq_ptr); - return; - } - ep_ctx->deq = cpu_to_le64(addr | deq_state->new_cycle_state); - - added_ctxs = xhci_get_endpoint_flag_from_index(ep_index); - xhci_setup_input_ctx_for_config_ep(xhci, xhci->devs[slot_id]->in_ctx, - xhci->devs[slot_id]->out_ctx, ctrl_ctx, - added_ctxs, added_ctxs); -} - -void xhci_cleanup_stalled_ring(struct xhci_hcd *xhci, unsigned int slot_id, - unsigned int ep_index, unsigned int stream_id, - struct xhci_td *td) -{ - struct xhci_dequeue_state deq_state; - - xhci_dbg_trace(xhci, trace_xhci_dbg_reset_ep, - "Cleaning up stalled endpoint ring"); - /* We need to move the HW's dequeue pointer past this TD, - * or it will attempt to resend it on the next doorbell ring. - */ - xhci_find_new_dequeue_state(xhci, slot_id, ep_index, stream_id, td, - &deq_state); - - if (!deq_state.new_deq_ptr || !deq_state.new_deq_seg) - return; - - /* HW with the reset endpoint quirk will use the saved dequeue state to - * issue a configure endpoint command later. - */ - if (!(xhci->quirks & XHCI_RESET_EP_QUIRK)) { - xhci_dbg_trace(xhci, trace_xhci_dbg_reset_ep, - "Queueing new dequeue state"); - xhci_queue_new_dequeue_state(xhci, slot_id, - ep_index, &deq_state); - } else { - /* Better hope no one uses the input context between now and the - * reset endpoint completion! - * XXX: No idea how this hardware will react when stream rings - * are enabled. - */ - xhci_dbg_trace(xhci, trace_xhci_dbg_quirks, - "Setting up input context for " - "configure endpoint command"); - xhci_setup_input_ctx_for_quirk(xhci, slot_id, - ep_index, &deq_state); - } -} - static void xhci_endpoint_disable(struct usb_hcd *hcd, struct usb_host_endpoint *host_ep) { @@ -4743,7 +4953,6 @@ static int xhci_update_timeout_for_interface(struct xhci_hcd *xhci, if (xhci_update_timeout_for_endpoint(xhci, udev, &alt->endpoint[j].desc, state, timeout)) return -E2BIG; - continue; } return 0; } @@ -5141,10 +5350,12 @@ int xhci_gen_setup(struct usb_hcd *hcd, xhci_get_quirks_t get_quirks) hcd->self.root_hub->speed = USB_SPEED_SUPER_PLUS; hcd->self.root_hub->rx_lanes = 2; hcd->self.root_hub->tx_lanes = 2; + hcd->self.root_hub->ssp_rate = USB_SSP_GEN_2x2; break; case 1: hcd->speed = HCD_USB31; hcd->self.root_hub->speed = USB_SPEED_SUPER_PLUS; + hcd->self.root_hub->ssp_rate = USB_SSP_GEN_2x1; break; } xhci_info(xhci, "Host supports USB 3.%x %sSuperSpeed\n", @@ -5286,6 +5497,7 @@ static const struct hc_driver xhci_hc_driver = { * managing i/o requests and associated device resources */ .map_urb_for_dma = xhci_map_urb_for_dma, + .unmap_urb_for_dma = xhci_unmap_urb_for_dma, .urb_enqueue = xhci_urb_enqueue, .urb_dequeue = xhci_urb_dequeue, .alloc_dev = xhci_alloc_dev, @@ -5343,6 +5555,10 @@ void xhci_init_driver(struct hc_driver *drv, drv->reset = over->reset; if (over->start) drv->start = over->start; + if (over->add_endpoint) + drv->add_endpoint = over->add_endpoint; + if (over->drop_endpoint) + drv->drop_endpoint = over->drop_endpoint; if (over->check_bandwidth) drv->check_bandwidth = over->check_bandwidth; if (over->reset_bandwidth) diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 2a31467f7a..379a19144a 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -526,7 +526,6 @@ static int cq_create(struct mlx5_vdpa_net *ndev, u16 idx, u32 num_ent) void __iomem *uar_page = ndev->mvdev.res.uar->map; u32 out[MLX5_ST_SZ_DW(create_cq_out)]; struct mlx5_vdpa_cq *vcq = &mvq->cq; - unsigned int irqn; __be64 *pas; int inlen; void *cqc; @@ -566,7 +565,7 @@ static int cq_create(struct mlx5_vdpa_net *ndev, u16 idx, u32 num_ent) /* Use vector 0 by default. Consider adding code to choose least used * vector. */ - err = mlx5_vector2eqn(mdev, 0, &eqn, &irqn); + err = mlx5_vector2eqn(mdev, 0, &eqn); if (err) goto err_vec; diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index d7e361fb05..a78704ae36 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -198,12 +198,12 @@ static void disable_dynirq(struct irq_data *data); static DEFINE_PER_CPU(unsigned int, irq_epoch); -static void clear_evtchn_to_irq_row(unsigned row) +static void clear_evtchn_to_irq_row(int *evtchn_row) { unsigned col; for (col = 0; col < EVTCHN_PER_ROW; col++) - WRITE_ONCE(evtchn_to_irq[row][col], -1); + WRITE_ONCE(evtchn_row[col], -1); } static void clear_evtchn_to_irq_all(void) @@ -213,7 +213,7 @@ static void clear_evtchn_to_irq_all(void) for (row = 0; row < EVTCHN_ROW(xen_evtchn_max_channels()); row++) { if (evtchn_to_irq[row] == NULL) continue; - clear_evtchn_to_irq_row(row); + clear_evtchn_to_irq_row(evtchn_to_irq[row]); } } @@ -221,6 +221,7 @@ static int set_evtchn_to_irq(evtchn_port_t evtchn, unsigned int irq) { unsigned row; unsigned col; + int *evtchn_row; if (evtchn >= xen_evtchn_max_channels()) return -EINVAL; @@ -233,11 +234,18 @@ static int set_evtchn_to_irq(evtchn_port_t evtchn, unsigned int irq) if (irq == -1) return 0; - evtchn_to_irq[row] = (int *)get_zeroed_page(GFP_KERNEL); - if (evtchn_to_irq[row] == NULL) + evtchn_row = (int *) __get_free_pages(GFP_KERNEL, 0); + if (evtchn_row == NULL) return -ENOMEM; - clear_evtchn_to_irq_row(row); + clear_evtchn_to_irq_row(evtchn_row); + + /* + * We've prepared an empty row for the mapping. If a different + * thread was faster inserting it, we can drop ours. + */ + if (cmpxchg(&evtchn_to_irq[row], NULL, evtchn_row) != NULL) + free_page((unsigned long) evtchn_row); } WRITE_ONCE(evtchn_to_irq[row][col], irq); @@ -1009,7 +1017,7 @@ static void __unbind_from_irq(unsigned int irq) int xen_bind_pirq_gsi_to_irq(unsigned gsi, unsigned pirq, int shareable, char *name) { - int irq = -1; + int irq; struct physdev_irq irq_op; int ret; diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 7bdefd0c78..2a2900903f 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -4150,11 +4150,19 @@ void ceph_handle_caps(struct ceph_mds_session *session, /* * Delayed work handler to process end of delayed cap release LRU list. + * + * If new caps are added to the list while processing it, these won't get + * processed in this run. In this case, the ci->i_hold_caps_max will be + * returned so that the work can be scheduled accordingly. */ -void ceph_check_delayed_caps(struct ceph_mds_client *mdsc) +unsigned long ceph_check_delayed_caps(struct ceph_mds_client *mdsc) { struct inode *inode; struct ceph_inode_info *ci; + struct ceph_mount_options *opt = mdsc->fsc->mount_options; + unsigned long delay_max = opt->caps_wanted_delay_max * HZ; + unsigned long loop_start = jiffies; + unsigned long delay = 0; dout("check_delayed_caps\n"); spin_lock(&mdsc->cap_delay_lock); @@ -4162,6 +4170,11 @@ void ceph_check_delayed_caps(struct ceph_mds_client *mdsc) ci = list_first_entry(&mdsc->cap_delay_list, struct ceph_inode_info, i_cap_delay_list); + if (time_before(loop_start, ci->i_hold_caps_max - delay_max)) { + dout("%s caps added recently. Exiting loop", __func__); + delay = ci->i_hold_caps_max; + break; + } if ((ci->i_ceph_flags & CEPH_I_FLUSH) == 0 && time_before(jiffies, ci->i_hold_caps_max)) break; @@ -4177,6 +4190,8 @@ void ceph_check_delayed_caps(struct ceph_mds_client *mdsc) } } spin_unlock(&mdsc->cap_delay_lock); + + return delay; } /* diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 9db1b39df7..afdc202138 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -4490,22 +4490,29 @@ void inc_session_sequence(struct ceph_mds_session *s) } /* - * delayed work -- periodically trim expired leases, renew caps with mds + * delayed work -- periodically trim expired leases, renew caps with mds. If + * the @delay parameter is set to 0 or if it's more than 5 secs, the default + * workqueue delay value of 5 secs will be used. */ -static void schedule_delayed(struct ceph_mds_client *mdsc) +static void schedule_delayed(struct ceph_mds_client *mdsc, unsigned long delay) { - int delay = 5; - unsigned hz = round_jiffies_relative(HZ * delay); - schedule_delayed_work(&mdsc->delayed_work, hz); + unsigned long max_delay = HZ * 5; + + /* 5 secs default delay */ + if (!delay || (delay > max_delay)) + delay = max_delay; + schedule_delayed_work(&mdsc->delayed_work, + round_jiffies_relative(delay)); } static void delayed_work(struct work_struct *work) { - int i; struct ceph_mds_client *mdsc = container_of(work, struct ceph_mds_client, delayed_work.work); + unsigned long delay; int renew_interval; int renew_caps; + int i; dout("mdsc delayed_work\n"); @@ -4545,7 +4552,7 @@ static void delayed_work(struct work_struct *work) } mutex_unlock(&mdsc->mutex); - ceph_check_delayed_caps(mdsc); + delay = ceph_check_delayed_caps(mdsc); ceph_queue_cap_reclaim_work(mdsc); @@ -4553,7 +4560,7 @@ static void delayed_work(struct work_struct *work) maybe_recover_session(mdsc); - schedule_delayed(mdsc); + schedule_delayed(mdsc, delay); } int ceph_mdsc_init(struct ceph_fs_client *fsc) @@ -5030,7 +5037,7 @@ void ceph_mdsc_handle_mdsmap(struct ceph_mds_client *mdsc, struct ceph_msg *msg) mdsc->mdsmap->m_epoch); mutex_unlock(&mdsc->mutex); - schedule_delayed(mdsc); + schedule_delayed(mdsc, 0); return; bad_unlock: diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 4ac0606dcb..4c6bd1042c 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -67,19 +67,19 @@ void ceph_get_snap_realm(struct ceph_mds_client *mdsc, { lockdep_assert_held(&mdsc->snap_rwsem); - dout("get_realm %p %d -> %d\n", realm, - atomic_read(&realm->nref), atomic_read(&realm->nref)+1); /* - * since we _only_ increment realm refs or empty the empty - * list with snap_rwsem held, adjusting the empty list here is - * safe. we do need to protect against concurrent empty list - * additions, however. + * The 0->1 and 1->0 transitions must take the snap_empty_lock + * atomically with the refcount change. Go ahead and bump the + * nref here, unless it's 0, in which case we take the spinlock + * and then do the increment and remove it from the list. */ - if (atomic_inc_return(&realm->nref) == 1) { - spin_lock(&mdsc->snap_empty_lock); + if (atomic_inc_not_zero(&realm->nref)) + return; + + spin_lock(&mdsc->snap_empty_lock); + if (atomic_inc_return(&realm->nref) == 1) list_del_init(&realm->empty_item); - spin_unlock(&mdsc->snap_empty_lock); - } + spin_unlock(&mdsc->snap_empty_lock); } static void __insert_snap_realm(struct rb_root *root, @@ -208,28 +208,28 @@ static void __put_snap_realm(struct ceph_mds_client *mdsc, { lockdep_assert_held_write(&mdsc->snap_rwsem); - dout("__put_snap_realm %llx %p %d -> %d\n", realm->ino, realm, - atomic_read(&realm->nref), atomic_read(&realm->nref)-1); + /* + * We do not require the snap_empty_lock here, as any caller that + * increments the value must hold the snap_rwsem. + */ if (atomic_dec_and_test(&realm->nref)) __destroy_snap_realm(mdsc, realm); } /* - * caller needn't hold any locks + * See comments in ceph_get_snap_realm. Caller needn't hold any locks. */ void ceph_put_snap_realm(struct ceph_mds_client *mdsc, struct ceph_snap_realm *realm) { - dout("put_snap_realm %llx %p %d -> %d\n", realm->ino, realm, - atomic_read(&realm->nref), atomic_read(&realm->nref)-1); - if (!atomic_dec_and_test(&realm->nref)) + if (!atomic_dec_and_lock(&realm->nref, &mdsc->snap_empty_lock)) return; if (down_write_trylock(&mdsc->snap_rwsem)) { + spin_unlock(&mdsc->snap_empty_lock); __destroy_snap_realm(mdsc, realm); up_write(&mdsc->snap_rwsem); } else { - spin_lock(&mdsc->snap_empty_lock); list_add(&realm->empty_item, &mdsc->snap_empty); spin_unlock(&mdsc->snap_empty_lock); } diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 6b6332a5c1..9215a2f453 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -1167,7 +1167,7 @@ extern void ceph_flush_snaps(struct ceph_inode_info *ci, extern bool __ceph_should_report_size(struct ceph_inode_info *ci); extern void ceph_check_caps(struct ceph_inode_info *ci, int flags, struct ceph_mds_session *session); -extern void ceph_check_delayed_caps(struct ceph_mds_client *mdsc); +extern unsigned long ceph_check_delayed_caps(struct ceph_mds_client *mdsc); extern void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc); extern int ceph_drop_caps_for_unlink(struct inode *inode); extern int ceph_encode_inode_release(void **p, struct inode *inode, diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index c0bfc2f010..c6a9542ca2 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -1611,6 +1611,11 @@ struct dfs_info3_param { int ttl; }; +struct file_list { + struct list_head list; + struct cifsFileInfo *cfile; +}; + /* * common struct for holding inode info when searching for or updating an * inode with new info diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 79402ca0dd..5f8a302ffc 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -100,7 +100,7 @@ build_path_from_dentry_optional_prefix(struct dentry *direntry, void *page, if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH) pplen = cifs_sb->prepath ? strlen(cifs_sb->prepath) + 1 : 0; - s = dentry_path_raw(direntry, page, PAGE_SIZE); + s = dentry_path_raw(direntry, page, PATH_MAX); if (IS_ERR(s)) return s; if (!s[1]) // for root we want "", not "/" diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 0a72840a88..bb98fbdd22 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -4847,6 +4847,22 @@ void cifs_oplock_break(struct work_struct *work) cifs_dbg(VFS, "Push locks rc = %d\n", rc); oplock_break_ack: + /* + * When oplock break is received and there are no active + * file handles but cached, then schedule deferred close immediately. + * So, new open will not use cached handle. + */ + spin_lock(&CIFS_I(inode)->deferred_lock); + is_deferred = cifs_is_deferred_close(cfile, &dclose); + spin_unlock(&CIFS_I(inode)->deferred_lock); + if (is_deferred && + cfile->deferred_close_scheduled && + delayed_work_pending(&cfile->deferred)) { + if (cancel_delayed_work(&cfile->deferred)) { + _cifsFileInfo_put(cfile, false, false); + goto oplock_break_done; + } + } /* * releasing stale oplock after recent reconnect of smb session using * a now incorrect file handle is not a data integrity issue but do @@ -4858,24 +4874,7 @@ void cifs_oplock_break(struct work_struct *work) cinode); cifs_dbg(FYI, "Oplock release rc = %d\n", rc); } - /* - * When oplock break is received and there are no active - * file handles but cached, then schedule deferred close immediately. - * So, new open will not use cached handle. - */ - spin_lock(&CIFS_I(inode)->deferred_lock); - is_deferred = cifs_is_deferred_close(cfile, &dclose); - if (is_deferred && - cfile->deferred_close_scheduled && - delayed_work_pending(&cfile->deferred)) { - /* - * If there is no pending work, mod_delayed_work queues new work. - * So, Increase the ref count to avoid use-after-free. - */ - if (!mod_delayed_work(deferredclose_wq, &cfile->deferred, 0)) - cifsFileInfo_get(cfile); - } - spin_unlock(&CIFS_I(inode)->deferred_lock); +oplock_break_done: _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 b96b253e76..65f8a70cec 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1625,7 +1625,7 @@ int cifs_unlink(struct inode *dir, struct dentry *dentry) goto unlink_out; } - cifs_close_all_deferred_files(tcon); + cifs_close_deferred_file(CIFS_I(inode)); if (cap_unix(tcon->ses) && (CIFS_UNIX_POSIX_PATH_OPS_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability))) { rc = CIFSPOSIXDelFile(xid, tcon, full_path, @@ -2084,6 +2084,7 @@ cifs_rename2(struct user_namespace *mnt_userns, struct inode *source_dir, FILE_UNIX_BASIC_INFO *info_buf_target; unsigned int xid; int rc, tmprc; + int retry_count = 0; if (flags & ~RENAME_NOREPLACE) return -EINVAL; @@ -2113,10 +2114,24 @@ cifs_rename2(struct user_namespace *mnt_userns, struct inode *source_dir, goto cifs_rename_exit; } - cifs_close_all_deferred_files(tcon); + cifs_close_deferred_file(CIFS_I(d_inode(source_dentry))); + if (d_inode(target_dentry) != NULL) + cifs_close_deferred_file(CIFS_I(d_inode(target_dentry))); + rc = cifs_do_rename(xid, source_dentry, from_name, target_dentry, to_name); + if (rc == -EACCES) { + while (retry_count < 3) { + cifs_close_all_deferred_files(tcon); + rc = cifs_do_rename(xid, source_dentry, from_name, target_dentry, + to_name); + if (rc != -EACCES) + break; + retry_count++; + } + } + /* * No-replace is the natural behavior for CIFS, so skip unlink hacks. */ diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 844abeb2b4..9469f1cf0b 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -723,13 +723,31 @@ void cifs_close_deferred_file(struct cifsInodeInfo *cifs_inode) { struct cifsFileInfo *cfile = NULL; - struct cifs_deferred_close *dclose; + struct file_list *tmp_list, *tmp_next_list; + struct list_head file_head; + if (cifs_inode == NULL) + return; + + INIT_LIST_HEAD(&file_head); + spin_lock(&cifs_inode->open_file_lock); list_for_each_entry(cfile, &cifs_inode->openFileList, flist) { - spin_lock(&cifs_inode->deferred_lock); - if (cifs_is_deferred_close(cfile, &dclose)) - mod_delayed_work(deferredclose_wq, &cfile->deferred, 0); - spin_unlock(&cifs_inode->deferred_lock); + if (delayed_work_pending(&cfile->deferred)) { + if (cancel_delayed_work(&cfile->deferred)) { + tmp_list = kmalloc(sizeof(struct file_list), GFP_ATOMIC); + if (tmp_list == NULL) + continue; + tmp_list->cfile = cfile; + list_add_tail(&tmp_list->list, &file_head); + } + } + } + spin_unlock(&cifs_inode->open_file_lock); + + list_for_each_entry_safe(tmp_list, tmp_next_list, &file_head, list) { + _cifsFileInfo_put(tmp_list->cfile, true, false); + list_del(&tmp_list->list); + kfree(tmp_list); } } @@ -738,20 +756,30 @@ cifs_close_all_deferred_files(struct cifs_tcon *tcon) { struct cifsFileInfo *cfile; struct list_head *tmp; + struct file_list *tmp_list, *tmp_next_list; + struct list_head file_head; + INIT_LIST_HEAD(&file_head); spin_lock(&tcon->open_file_lock); list_for_each(tmp, &tcon->openFileList) { cfile = list_entry(tmp, struct cifsFileInfo, tlist); if (delayed_work_pending(&cfile->deferred)) { - /* - * If there is no pending work, mod_delayed_work queues new work. - * So, Increase the ref count to avoid use-after-free. - */ - if (!mod_delayed_work(deferredclose_wq, &cfile->deferred, 0)) - cifsFileInfo_get(cfile); + if (cancel_delayed_work(&cfile->deferred)) { + tmp_list = kmalloc(sizeof(struct file_list), GFP_ATOMIC); + if (tmp_list == NULL) + continue; + tmp_list->cfile = cfile; + list_add_tail(&tmp_list->list, &file_head); + } } } spin_unlock(&tcon->open_file_lock); + + list_for_each_entry_safe(tmp_list, tmp_next_list, &file_head, list) { + _cifsFileInfo_put(tmp_list->cfile, true, false); + list_del(&tmp_list->list); + kfree(tmp_list); + } } /* parses DFS refferal V3 structure diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 781d14e5f2..b6d2e35919 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -2426,7 +2426,7 @@ create_sd_buf(umode_t mode, bool set_owner, unsigned int *len) memcpy(aclptr, &acl, sizeof(struct cifs_acl)); buf->ccontext.DataLength = cpu_to_le32(ptr - (__u8 *)&buf->sd); - *len = ptr - (__u8 *)buf; + *len = roundup(ptr - (__u8 *)buf, 8); return buf; } diff --git a/fs/configfs/file.c b/fs/configfs/file.c index 5a0be9985b..0ad3215061 100644 --- a/fs/configfs/file.c +++ b/fs/configfs/file.c @@ -177,28 +177,22 @@ static ssize_t configfs_bin_read_iter(struct kiocb *iocb, struct iov_iter *to) return retval; } -/* Fill [buffer, buffer + pos) with data coming from @from. */ -static int fill_write_buffer(struct configfs_buffer *buffer, loff_t pos, +/* Fill @buffer with data coming from @from. */ +static int fill_write_buffer(struct configfs_buffer *buffer, struct iov_iter *from) { - loff_t to_copy; int copied; - u8 *to; if (!buffer->page) buffer->page = (char *)__get_free_pages(GFP_KERNEL, 0); if (!buffer->page) return -ENOMEM; - to_copy = SIMPLE_ATTR_SIZE - 1 - pos; - if (to_copy <= 0) - return 0; - to = buffer->page + pos; - copied = copy_from_iter(to, to_copy, from); + copied = copy_from_iter(buffer->page, SIMPLE_ATTR_SIZE - 1, from); buffer->needs_read_fill = 1; /* if buf is assumed to contain a string, terminate it by \0, * so e.g. sscanf() can scan the string easily */ - to[copied] = 0; + buffer->page[copied] = 0; return copied ? : -EFAULT; } @@ -227,10 +221,10 @@ static ssize_t configfs_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct configfs_buffer *buffer = file->private_data; - ssize_t len; + int len; mutex_lock(&buffer->mutex); - len = fill_write_buffer(buffer, iocb->ki_pos, from); + len = fill_write_buffer(buffer, from); if (len > 0) len = flush_write_buffer(file, buffer, len); if (len > 0) diff --git a/fs/dax.c b/fs/dax.c index da41f93635..99b4e78d88 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -722,7 +722,7 @@ static int copy_cow_page_dax(struct block_device *bdev, struct dax_device *dax_d return rc; id = dax_read_lock(); - rc = dax_direct_access(dax_dev, pgoff, PHYS_PFN(PAGE_SIZE), &kaddr, NULL); + rc = dax_direct_access(dax_dev, pgoff, 1, &kaddr, NULL); if (rc < 0) { dax_read_unlock(id); return rc; diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c index e55723744f..9d58371d22 100644 --- a/fs/fuse/dax.c +++ b/fs/fuse/dax.c @@ -1235,8 +1235,6 @@ void fuse_dax_conn_free(struct fuse_conn *fc) static int fuse_dax_mem_range_init(struct fuse_conn_dax *fcd) { long nr_pages, nr_ranges; - void *kaddr; - pfn_t pfn; struct fuse_dax_mapping *range; int ret, id; size_t dax_size = -1; @@ -1248,8 +1246,8 @@ static int fuse_dax_mem_range_init(struct fuse_conn_dax *fcd) INIT_DELAYED_WORK(&fcd->free_work, fuse_dax_free_mem_worker); id = dax_read_lock(); - nr_pages = dax_direct_access(fcd->dev, 0, PHYS_PFN(dax_size), &kaddr, - &pfn); + nr_pages = dax_direct_access(fcd->dev, 0, PHYS_PFN(dax_size), NULL, + NULL); dax_read_unlock(id); if (nr_pages < 0) { pr_debug("dax_direct_access() returned %ld\n", nr_pages); diff --git a/fs/io-wq.c b/fs/io-wq.c index 12fc19353b..7d2ed8c7dd 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -129,7 +129,7 @@ struct io_cb_cancel_data { bool cancel_all; }; -static void create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index); +static void create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index, bool first); static void io_wqe_dec_running(struct io_worker *worker); static bool io_worker_get(struct io_worker *worker) @@ -248,18 +248,20 @@ static void io_wqe_wake_worker(struct io_wqe *wqe, struct io_wqe_acct *acct) rcu_read_unlock(); if (!ret) { - bool do_create = false; + bool do_create = false, first = false; raw_spin_lock_irq(&wqe->lock); if (acct->nr_workers < acct->max_workers) { atomic_inc(&acct->nr_running); atomic_inc(&wqe->wq->worker_refs); + if (!acct->nr_workers) + first = true; acct->nr_workers++; do_create = true; } raw_spin_unlock_irq(&wqe->lock); if (do_create) - create_io_worker(wqe->wq, wqe, acct->index); + create_io_worker(wqe->wq, wqe, acct->index, first); } } @@ -282,16 +284,26 @@ static void create_worker_cb(struct callback_head *cb) struct io_wq *wq; struct io_wqe *wqe; struct io_wqe_acct *acct; + bool do_create = false, first = false; cwd = container_of(cb, struct create_worker_data, work); wqe = cwd->wqe; wq = wqe->wq; acct = &wqe->acct[cwd->index]; raw_spin_lock_irq(&wqe->lock); - if (acct->nr_workers < acct->max_workers) + if (acct->nr_workers < acct->max_workers) { + if (!acct->nr_workers) + first = true; acct->nr_workers++; + do_create = true; + } raw_spin_unlock_irq(&wqe->lock); - create_io_worker(wq, cwd->wqe, cwd->index); + if (do_create) { + create_io_worker(wq, wqe, cwd->index, first); + } else { + atomic_dec(&acct->nr_running); + io_worker_ref_put(wq); + } kfree(cwd); } @@ -629,7 +641,7 @@ void io_wq_worker_sleeping(struct task_struct *tsk) raw_spin_unlock_irq(&worker->wqe->lock); } -static void create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index) +static void create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index, bool first) { struct io_wqe_acct *acct = &wqe->acct[index]; struct io_worker *worker; @@ -670,7 +682,7 @@ static void create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index) worker->flags |= IO_WORKER_F_FREE; if (index == IO_WQ_ACCT_BOUND) worker->flags |= IO_WORKER_F_BOUND; - if ((acct->nr_workers == 1) && (worker->flags & IO_WORKER_F_BOUND)) + if (first && (worker->flags & IO_WORKER_F_BOUND)) worker->flags |= IO_WORKER_F_FIXED; raw_spin_unlock_irq(&wqe->lock); wake_up_new_task(tsk); diff --git a/fs/io_uring.c b/fs/io_uring.c index bf548af042..04c6d059ea 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -78,6 +78,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -1499,7 +1500,8 @@ static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) all_flushed = list_empty(&ctx->cq_overflow_list); if (all_flushed) { clear_bit(0, &ctx->check_cq_overflow); - ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW; + WRITE_ONCE(ctx->rings->sq_flags, + ctx->rings->sq_flags & ~IORING_SQ_CQ_OVERFLOW); } if (posted) @@ -1578,7 +1580,9 @@ static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data, } if (list_empty(&ctx->cq_overflow_list)) { set_bit(0, &ctx->check_cq_overflow); - ctx->rings->sq_flags |= IORING_SQ_CQ_OVERFLOW; + WRITE_ONCE(ctx->rings->sq_flags, + ctx->rings->sq_flags | IORING_SQ_CQ_OVERFLOW); + } ocqe->cqe.user_data = user_data; ocqe->cqe.res = res; @@ -2222,9 +2226,9 @@ static inline unsigned int io_put_rw_kbuf(struct io_kiocb *req) static inline bool io_run_task_work(void) { - if (current->task_works) { + if (test_thread_flag(TIF_NOTIFY_SIGNAL) || current->task_works) { __set_current_state(TASK_RUNNING); - task_work_run(); + tracehook_notify_signal(); return true; } @@ -6803,14 +6807,16 @@ static inline void io_ring_set_wakeup_flag(struct io_ring_ctx *ctx) { /* Tell userspace we may need a wakeup call */ spin_lock_irq(&ctx->completion_lock); - ctx->rings->sq_flags |= IORING_SQ_NEED_WAKEUP; + WRITE_ONCE(ctx->rings->sq_flags, + ctx->rings->sq_flags | IORING_SQ_NEED_WAKEUP); spin_unlock_irq(&ctx->completion_lock); } static inline void io_ring_clear_wakeup_flag(struct io_ring_ctx *ctx) { spin_lock_irq(&ctx->completion_lock); - ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP; + WRITE_ONCE(ctx->rings->sq_flags, + ctx->rings->sq_flags & ~IORING_SQ_NEED_WAKEUP); spin_unlock_irq(&ctx->completion_lock); } @@ -7132,16 +7138,6 @@ static void **io_alloc_page_table(size_t size) return table; } -static inline void io_rsrc_ref_lock(struct io_ring_ctx *ctx) -{ - spin_lock_bh(&ctx->rsrc_ref_lock); -} - -static inline void io_rsrc_ref_unlock(struct io_ring_ctx *ctx) -{ - spin_unlock_bh(&ctx->rsrc_ref_lock); -} - static void io_rsrc_node_destroy(struct io_rsrc_node *ref_node) { percpu_ref_exit(&ref_node->refs); @@ -7158,9 +7154,9 @@ static void io_rsrc_node_switch(struct io_ring_ctx *ctx, struct io_rsrc_node *rsrc_node = ctx->rsrc_node; rsrc_node->rsrc_data = data_to_kill; - io_rsrc_ref_lock(ctx); + spin_lock_irq(&ctx->rsrc_ref_lock); list_add_tail(&rsrc_node->node, &ctx->rsrc_ref_list); - io_rsrc_ref_unlock(ctx); + spin_unlock_irq(&ctx->rsrc_ref_lock); atomic_inc(&data_to_kill->refs); percpu_ref_kill(&rsrc_node->refs); @@ -7199,17 +7195,19 @@ static int io_rsrc_ref_quiesce(struct io_rsrc_data *data, struct io_ring_ctx *ct /* kill initial ref, already quiesced if zero */ if (atomic_dec_and_test(&data->refs)) break; + mutex_unlock(&ctx->uring_lock); flush_delayed_work(&ctx->rsrc_put_work); ret = wait_for_completion_interruptible(&data->done); - if (!ret) + if (!ret) { + mutex_lock(&ctx->uring_lock); break; + } atomic_inc(&data->refs); /* wait for all works potentially completing data->done */ flush_delayed_work(&ctx->rsrc_put_work); reinit_completion(&data->done); - mutex_unlock(&ctx->uring_lock); ret = io_run_task_work_sig(); mutex_lock(&ctx->uring_lock); } while (ret >= 0); @@ -7668,9 +7666,10 @@ static void io_rsrc_node_ref_zero(struct percpu_ref *ref) { struct io_rsrc_node *node = container_of(ref, struct io_rsrc_node, refs); struct io_ring_ctx *ctx = node->rsrc_data->ctx; + unsigned long flags; bool first_add = false; - io_rsrc_ref_lock(ctx); + spin_lock_irqsave(&ctx->rsrc_ref_lock, flags); node->done = true; while (!list_empty(&ctx->rsrc_ref_list)) { @@ -7682,7 +7681,7 @@ static void io_rsrc_node_ref_zero(struct percpu_ref *ref) list_del(&node->node); first_add |= llist_add(&node->llist, &ctx->rsrc_put_llist); } - io_rsrc_ref_unlock(ctx); + spin_unlock_irqrestore(&ctx->rsrc_ref_lock, flags); if (first_add) mod_delayed_work(system_wq, &ctx->rsrc_put_work, HZ); @@ -8653,13 +8652,10 @@ static void io_req_caches_free(struct io_ring_ctx *ctx) mutex_unlock(&ctx->uring_lock); } -static bool io_wait_rsrc_data(struct io_rsrc_data *data) +static void io_wait_rsrc_data(struct io_rsrc_data *data) { - if (!data) - return false; - if (!atomic_dec_and_test(&data->refs)) + if (data && !atomic_dec_and_test(&data->refs)) wait_for_completion(&data->done); - return true; } static void io_ring_ctx_free(struct io_ring_ctx *ctx) @@ -8671,10 +8667,14 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx) ctx->mm_account = NULL; } + /* __io_rsrc_put_work() may need uring_lock to progress, wait w/o it */ + io_wait_rsrc_data(ctx->buf_data); + io_wait_rsrc_data(ctx->file_data); + mutex_lock(&ctx->uring_lock); - if (io_wait_rsrc_data(ctx->buf_data)) + if (ctx->buf_data) __io_sqe_buffers_unregister(ctx); - if (io_wait_rsrc_data(ctx->file_data)) + if (ctx->file_data) __io_sqe_files_unregister(ctx); if (ctx->rings) __io_cqring_overflow_flush(ctx, true); diff --git a/fs/namespace.c b/fs/namespace.c index ab4174a3c8..f79d9471cb 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1938,6 +1938,20 @@ void drop_collected_mounts(struct vfsmount *mnt) namespace_unlock(); } +static bool has_locked_children(struct mount *mnt, struct dentry *dentry) +{ + struct mount *child; + + list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { + if (!is_subdir(child->mnt_mountpoint, dentry)) + continue; + + if (child->mnt.mnt_flags & MNT_LOCKED) + return true; + } + return false; +} + /** * clone_private_mount - create a private clone of a path * @path: path to clone @@ -1953,10 +1967,19 @@ struct vfsmount *clone_private_mount(const struct path *path) struct mount *old_mnt = real_mount(path->mnt); struct mount *new_mnt; + down_read(&namespace_sem); if (IS_MNT_UNBINDABLE(old_mnt)) - return ERR_PTR(-EINVAL); + goto invalid; + + if (!check_mnt(old_mnt)) + goto invalid; + + if (has_locked_children(old_mnt, path->dentry)) + goto invalid; new_mnt = clone_mnt(old_mnt, path->dentry, CL_PRIVATE); + up_read(&namespace_sem); + if (IS_ERR(new_mnt)) return ERR_CAST(new_mnt); @@ -1964,6 +1987,10 @@ struct vfsmount *clone_private_mount(const struct path *path) new_mnt->mnt_ns = MNT_NS_INTERNAL; return &new_mnt->mnt; + +invalid: + up_read(&namespace_sem); + return ERR_PTR(-EINVAL); } EXPORT_SYMBOL_GPL(clone_private_mount); @@ -2315,19 +2342,6 @@ static int do_change_type(struct path *path, int ms_flags) return err; } -static bool has_locked_children(struct mount *mnt, struct dentry *dentry) -{ - struct mount *child; - list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { - if (!is_subdir(child->mnt_mountpoint, dentry)) - continue; - - if (child->mnt.mnt_flags & MNT_LOCKED) - return true; - } - return false; -} - static struct mount *__do_loopback(struct path *old_path, int recurse) { struct mount *mnt = ERR_PTR(-EINVAL), *old = real_mount(old_path->mnt); diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 64864fb40b..28b67cb945 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -54,22 +54,27 @@ static int fanotify_max_queued_events __read_mostly; #include +static long ft_zero = 0; +static long ft_int_max = INT_MAX; + struct ctl_table fanotify_table[] = { { .procname = "max_user_groups", .data = &init_user_ns.ucount_max[UCOUNT_FANOTIFY_GROUPS], - .maxlen = sizeof(int), + .maxlen = sizeof(long), .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, + .proc_handler = proc_doulongvec_minmax, + .extra1 = &ft_zero, + .extra2 = &ft_int_max, }, { .procname = "max_user_marks", .data = &init_user_ns.ucount_max[UCOUNT_FANOTIFY_MARKS], - .maxlen = sizeof(int), + .maxlen = sizeof(long), .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, + .proc_handler = proc_doulongvec_minmax, + .extra1 = &ft_zero, + .extra2 = &ft_int_max, }, { .procname = "max_queued_events", diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 98f61b3174..62051247f6 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -55,22 +55,27 @@ struct kmem_cache *inotify_inode_mark_cachep __read_mostly; #include +static long it_zero = 0; +static long it_int_max = INT_MAX; + struct ctl_table inotify_table[] = { { .procname = "max_user_instances", .data = &init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES], - .maxlen = sizeof(int), + .maxlen = sizeof(long), .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, + .proc_handler = proc_doulongvec_minmax, + .extra1 = &it_zero, + .extra2 = &it_int_max, }, { .procname = "max_user_watches", .data = &init_user_ns.ucount_max[UCOUNT_INOTIFY_WATCHES], - .maxlen = sizeof(int), + .maxlen = sizeof(long), .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, + .proc_handler = proc_doulongvec_minmax, + .extra1 = &it_zero, + .extra2 = &it_int_max, }, { .procname = "max_queued_events", diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 4d53d3b7e5..d081faa55e 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -392,6 +392,51 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter) return ret; } +/* + * Calling iter_file_splice_write() directly from overlay's f_op may deadlock + * due to lock order inversion between pipe->mutex in iter_file_splice_write() + * and file_start_write(real.file) in ovl_write_iter(). + * + * So do everything ovl_write_iter() does and call iter_file_splice_write() on + * the real file. + */ +static ssize_t ovl_splice_write(struct pipe_inode_info *pipe, struct file *out, + loff_t *ppos, size_t len, unsigned int flags) +{ + struct fd real; + const struct cred *old_cred; + struct inode *inode = file_inode(out); + struct inode *realinode = ovl_inode_real(inode); + ssize_t ret; + + inode_lock(inode); + /* Update mode */ + ovl_copyattr(realinode, inode); + ret = file_remove_privs(out); + if (ret) + goto out_unlock; + + ret = ovl_real_fdget(out, &real); + if (ret) + goto out_unlock; + + old_cred = ovl_override_creds(inode->i_sb); + file_start_write(real.file); + + ret = iter_file_splice_write(pipe, real.file, ppos, len, flags); + + file_end_write(real.file); + /* Update size */ + ovl_copyattr(realinode, inode); + revert_creds(old_cred); + fdput(real); + +out_unlock: + inode_unlock(inode); + + return ret; +} + static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync) { struct fd real; @@ -603,7 +648,7 @@ const struct file_operations ovl_file_operations = { .fadvise = ovl_fadvise, .flush = ovl_flush, .splice_read = generic_file_splice_read, - .splice_write = iter_file_splice_write, + .splice_write = ovl_splice_write, .copy_file_range = ovl_copy_file_range, .remap_file_range = ovl_remap_file_range, diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index e8ad2c2c77..150fdf3bc6 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -481,6 +481,8 @@ static int ovl_cache_update_ino(struct path *path, struct ovl_cache_entry *p) } this = lookup_one_len(p->name, dir, p->len); if (IS_ERR_OR_NULL(this) || !this->d_inode) { + /* Mark a stale entry */ + p->is_whiteout = true; if (IS_ERR(this)) { err = PTR_ERR(this); this = NULL; @@ -776,6 +778,9 @@ static int ovl_iterate(struct file *file, struct dir_context *ctx) if (err) goto out; } + } + /* ovl_cache_update_ino() sets is_whiteout on stale entry */ + if (!p->is_whiteout) { if (!dir_emit(ctx, p->name, p->len, p->ino, p->type)) break; } diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 17325416e2..62669b36a7 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -586,6 +586,7 @@ NOINSTR_TEXT \ *(.text..refcount) \ *(.ref.text) \ + *(.text.asan.* .text.tsan.*) \ TEXT_CFI_JT \ MEM_KEEP(init.text*) \ MEM_KEEP(exit.text*) \ diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 8b77d08d4b..6c9b10d82c 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -201,8 +201,8 @@ static inline void bpf_cgroup_storage_unset(void) { int i; - for (i = 0; i < BPF_CGROUP_STORAGE_NEST_MAX; i++) { - if (unlikely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current)) + for (i = BPF_CGROUP_STORAGE_NEST_MAX - 1; i >= 0; i--) { + if (likely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current)) continue; this_cpu_write(bpf_cgroup_storage_info[i].task, NULL); diff --git a/include/linux/device.h b/include/linux/device.h index 59940f1744..65d84b67b0 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -407,6 +407,7 @@ struct dev_links_info { * @em_pd: device's energy model performance domain * @pins: For device pin management. * See Documentation/driver-api/pin-control.rst for details. + * @msi_lock: Lock to protect MSI mask cache and mask register * @msi_list: Hosts MSI descriptors * @msi_domain: The generic MSI domain this device is using. * @numa_node: NUMA node this device is close to. @@ -506,6 +507,7 @@ struct device { struct dev_pin_info *pins; #endif #ifdef CONFIG_GENERIC_MSI_IRQ + raw_spinlock_t msi_lock; struct list_head msi_list; #endif #ifdef CONFIG_DMA_OPS diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 53aa0343bf..aaf4f1b4c2 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -41,7 +41,7 @@ struct in_device { unsigned long mr_qri; /* Query Response Interval */ unsigned char mr_qrv; /* Query Robustness Variable */ unsigned char mr_gq_running; - unsigned char mr_ifc_count; + u32 mr_ifc_count; struct timer_list mr_gq_timer; /* general query timer */ struct timer_list mr_ifc_timer; /* interface change timer */ diff --git a/include/linux/irq.h b/include/linux/irq.h index 8e9a9ae471..c8293c8176 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -569,6 +569,7 @@ struct irq_chip { * IRQCHIP_SUPPORTS_NMI: Chip can deliver NMIs, only for root irqchips * IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND: Invokes __enable_irq()/__disable_irq() for wake irqs * in the suspend path if they are in disabled state + * IRQCHIP_AFFINITY_PRE_STARTUP: Default affinity update before startup */ enum { IRQCHIP_SET_TYPE_MASKED = (1 << 0), @@ -581,6 +582,7 @@ enum { IRQCHIP_SUPPORTS_LEVEL_MSI = (1 << 7), IRQCHIP_SUPPORTS_NMI = (1 << 8), IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND = (1 << 9), + IRQCHIP_AFFINITY_PRE_STARTUP = (1 << 10), }; #include diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 1efe374669..25a8be58d2 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1044,8 +1044,7 @@ void mlx5_unregister_debugfs(void); void mlx5_fill_page_array(struct mlx5_frag_buf *buf, __be64 *pas); void mlx5_fill_page_frag_array_perm(struct mlx5_frag_buf *buf, __be64 *pas, u8 perm); void mlx5_fill_page_frag_array(struct mlx5_frag_buf *frag_buf, __be64 *pas); -int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, - unsigned int *irqn); +int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn); int mlx5_core_attach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); int mlx5_core_detach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); diff --git a/include/linux/msi.h b/include/linux/msi.h index 6aff469e51..e8bdcb8317 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -233,7 +233,7 @@ void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg); void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg); u32 __pci_msix_desc_mask_irq(struct msi_desc *desc, u32 flag); -u32 __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag); +void __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag); void pci_msi_mask_irq(struct irq_data *data); void pci_msi_unmask_irq(struct irq_data *data); diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 10279c4830..ada1296c87 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -196,6 +196,9 @@ struct ip_set_region { u32 elements; /* Number of elements vs timeout */ }; +/* Max range where every element is added/deleted in one step */ +#define IPSET_MAX_RANGE (1<<20) + /* The max revision number supported by any set type + 1 */ #define IPSET_REVISION_MAX 9 diff --git a/include/linux/once.h b/include/linux/once.h index 9225ee6d96..ae6f4eb41c 100644 --- a/include/linux/once.h +++ b/include/linux/once.h @@ -7,7 +7,7 @@ bool __do_once_start(bool *done, unsigned long *flags); void __do_once_done(bool *done, struct static_key_true *once_key, - unsigned long *flags); + unsigned long *flags, struct module *mod); /* Call a function exactly once. The idea of DO_ONCE() is to perform * a function call such as initialization of random seeds, etc, only @@ -46,7 +46,7 @@ void __do_once_done(bool *done, struct static_key_true *once_key, if (unlikely(___ret)) { \ func(__VA_ARGS__); \ __do_once_done(&___done, &___once_key, \ - &___flags); \ + &___flags, THIS_MODULE); \ } \ } \ ___ret; \ diff --git a/include/linux/security.h b/include/linux/security.h index 24eda04221..5b72885213 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -120,10 +120,11 @@ enum lockdown_reason { LOCKDOWN_MMIOTRACE, LOCKDOWN_DEBUGFS, LOCKDOWN_XMON_WR, + LOCKDOWN_BPF_WRITE_USER, LOCKDOWN_INTEGRITY_MAX, LOCKDOWN_KCORE, LOCKDOWN_KPROBES, - LOCKDOWN_BPF_READ, + LOCKDOWN_BPF_READ_KERNEL, LOCKDOWN_PERF, LOCKDOWN_TRACEFS, LOCKDOWN_XMON_RW, diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index 37e5300c7e..fefd38db95 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -30,7 +30,6 @@ struct nf_tcp_net { u8 tcp_ignore_invalid_rst; #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) unsigned int offload_timeout; - unsigned int offload_pickup; #endif }; @@ -44,7 +43,6 @@ struct nf_udp_net { unsigned int timeouts[UDP_CT_MAX]; #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) unsigned int offload_timeout; - unsigned int offload_pickup; #endif }; diff --git a/include/net/psample.h b/include/net/psample.h index e328c51277..0509d2d6be 100644 --- a/include/net/psample.h +++ b/include/net/psample.h @@ -31,6 +31,8 @@ struct psample_group *psample_group_get(struct net *net, u32 group_num); void psample_group_take(struct psample_group *group); void psample_group_put(struct psample_group *group); +struct sk_buff; + #if IS_ENABLED(CONFIG_PSAMPLE) void psample_sample_packet(struct psample_group *group, struct sk_buff *skb, diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h index dc8b72201f..00a60695fa 100644 --- a/include/uapi/linux/neighbour.h +++ b/include/uapi/linux/neighbour.h @@ -66,8 +66,11 @@ enum { #define NUD_NONE 0x00 /* NUD_NOARP & NUD_PERMANENT are pseudostates, they never change - and make no address resolution or NUD. - NUD_PERMANENT also cannot be deleted by garbage collectors. + * and make no address resolution or NUD. + * NUD_PERMANENT also cannot be deleted by garbage collectors. + * When NTF_EXT_LEARNED is set for a bridge fdb entry the different cache entry + * states don't make sense and thus are ignored. Such entries don't age and + * can roam. */ struct nda_cacheinfo { diff --git a/include/uapi/linux/netfilter/nfnetlink_hook.h b/include/uapi/linux/netfilter/nfnetlink_hook.h index 912ec60b26..bbcd285b22 100644 --- a/include/uapi/linux/netfilter/nfnetlink_hook.h +++ b/include/uapi/linux/netfilter/nfnetlink_hook.h @@ -43,6 +43,15 @@ enum nfnl_hook_chain_info_attributes { }; #define NFNLA_HOOK_INFO_MAX (__NFNLA_HOOK_INFO_MAX - 1) +enum nfnl_hook_chain_desc_attributes { + NFNLA_CHAIN_UNSPEC, + NFNLA_CHAIN_TABLE, + NFNLA_CHAIN_FAMILY, + NFNLA_CHAIN_NAME, + __NFNLA_CHAIN_MAX, +}; +#define NFNLA_CHAIN_MAX (__NFNLA_CHAIN_MAX - 1) + /** * enum nfnl_hook_chaintype - chain type * diff --git a/include/uapi/linux/netfilter/xt_DSCP.h b/include/uapi/linux/netfilter/xt_DSCP.h index 223d635e8b..7594e4df85 100644 --- a/include/uapi/linux/netfilter/xt_DSCP.h +++ b/include/uapi/linux/netfilter/xt_DSCP.h @@ -1,27 +1,32 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* x_tables module for setting the IPv4/IPv6 DSCP field +/* x_tables module for matching the IPv4/IPv6 DSCP field * * (C) 2002 Harald Welte - * based on ipt_FTOS.c (C) 2000 by Matthew G. Marsh * This software is distributed under GNU GPL v2, 1991 * * See RFC2474 for a description of the DSCP field within the IP Header. * - * xt_DSCP.h,v 1.7 2002/03/14 12:03:13 laforge Exp + * xt_dscp.h,v 1.3 2002/08/05 19:00:21 laforge Exp */ -#ifndef _XT_DSCP_TARGET_H -#define _XT_DSCP_TARGET_H -#include +#ifndef _XT_DSCP_H +#define _XT_DSCP_H + #include -/* target info */ -struct xt_DSCP_info { +#define XT_DSCP_MASK 0xfc /* 11111100 */ +#define XT_DSCP_SHIFT 2 +#define XT_DSCP_MAX 0x3f /* 00111111 */ + +/* match info */ +struct xt_dscp_info { __u8 dscp; + __u8 invert; }; -struct xt_tos_target_info { - __u8 tos_value; +struct xt_tos_match_info { __u8 tos_mask; + __u8 tos_value; + __u8 invert; }; -#endif /* _XT_DSCP_TARGET_H */ +#endif /* _XT_DSCP_H */ diff --git a/include/uapi/linux/netfilter_ipv4/ipt_ECN.h b/include/uapi/linux/netfilter_ipv4/ipt_ECN.h index 8121bec470..e3630fd045 100644 --- a/include/uapi/linux/netfilter_ipv4/ipt_ECN.h +++ b/include/uapi/linux/netfilter_ipv4/ipt_ECN.h @@ -1,16 +1,34 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef _IPT_ECN_H -#define _IPT_ECN_H +/* Header file for iptables ipt_ECN target + * + * (C) 2002 by Harald Welte + * + * This software is distributed under GNU GPL v2, 1991 + * + * ipt_ECN.h,v 1.3 2002/05/29 12:17:40 laforge Exp +*/ +#ifndef _IPT_ECN_TARGET_H +#define _IPT_ECN_TARGET_H -#include -#define ipt_ecn_info xt_ecn_info +#include +#include -enum { - IPT_ECN_IP_MASK = XT_ECN_IP_MASK, - IPT_ECN_OP_MATCH_IP = XT_ECN_OP_MATCH_IP, - IPT_ECN_OP_MATCH_ECE = XT_ECN_OP_MATCH_ECE, - IPT_ECN_OP_MATCH_CWR = XT_ECN_OP_MATCH_CWR, - IPT_ECN_OP_MATCH_MASK = XT_ECN_OP_MATCH_MASK, +#define IPT_ECN_IP_MASK (~XT_DSCP_MASK) + +#define IPT_ECN_OP_SET_IP 0x01 /* set ECN bits of IPv4 header */ +#define IPT_ECN_OP_SET_ECE 0x10 /* set ECE bit of TCP header */ +#define IPT_ECN_OP_SET_CWR 0x20 /* set CWR bit of TCP header */ + +#define IPT_ECN_OP_MASK 0xce + +struct ipt_ECN_info { + __u8 operation; /* bitset of operations */ + __u8 ip_ect; /* ECT codepoint of IPv4 header, pre-shifted */ + union { + struct { + __u8 ece:1, cwr:1; /* TCP ECT bits */ + } tcp; + } proto; }; -#endif /* IPT_ECN_H */ +#endif /* _IPT_ECN_TARGET_H */ diff --git a/include/uapi/linux/netfilter_ipv4/ipt_ttl.h b/include/uapi/linux/netfilter_ipv4/ipt_ttl.h index ad0226a862..57d2fc67a9 100644 --- a/include/uapi/linux/netfilter_ipv4/ipt_ttl.h +++ b/include/uapi/linux/netfilter_ipv4/ipt_ttl.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* IP tables module for matching the value of the TTL - * (C) 2000 by Harald Welte */ +/* TTL modification module for IP tables + * (C) 2000 by Harald Welte */ #ifndef _IPT_TTL_H #define _IPT_TTL_H @@ -8,14 +8,14 @@ #include enum { - IPT_TTL_EQ = 0, /* equals */ - IPT_TTL_NE, /* not equals */ - IPT_TTL_LT, /* less than */ - IPT_TTL_GT, /* greater than */ + IPT_TTL_SET = 0, + IPT_TTL_INC, + IPT_TTL_DEC }; +#define IPT_TTL_MAXMODE IPT_TTL_DEC -struct ipt_ttl_info { +struct ipt_TTL_info { __u8 mode; __u8 ttl; }; diff --git a/include/uapi/linux/netfilter_ipv6/ip6t_HL.h b/include/uapi/linux/netfilter_ipv6/ip6t_HL.h index 6b62f9418e..eaed56a287 100644 --- a/include/uapi/linux/netfilter_ipv6/ip6t_HL.h +++ b/include/uapi/linux/netfilter_ipv6/ip6t_HL.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* ip6tables module for matching the Hop Limit value +/* Hop Limit modification module for ip6tables * Maciej Soltysiak - * Based on HW's ttl module */ + * Based on HW's TTL module */ #ifndef _IP6T_HL_H #define _IP6T_HL_H @@ -9,14 +9,14 @@ #include enum { - IP6T_HL_EQ = 0, /* equals */ - IP6T_HL_NE, /* not equals */ - IP6T_HL_LT, /* less than */ - IP6T_HL_GT, /* greater than */ + IP6T_HL_SET = 0, + IP6T_HL_INC, + IP6T_HL_DEC }; +#define IP6T_HL_MAXMODE IP6T_HL_DEC -struct ip6t_hl_info { +struct ip6t_HL_info { __u8 mode; __u8 hop_limit; }; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index b1a5fc0449..0a28a8095d 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1362,11 +1362,13 @@ u64 __weak bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr) } /** - * __bpf_prog_run - run eBPF program on a given context + * ___bpf_prog_run - run eBPF program on a given context * @regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers * @insn: is the array of eBPF instructions * * Decode and execute eBPF instructions. + * + * Return: whatever value is in %BPF_R0 at program exit */ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn) { @@ -1878,6 +1880,9 @@ static void bpf_prog_select_func(struct bpf_prog *fp) * * Try to JIT eBPF program, if JIT is not available, use interpreter. * The BPF program will be executed via BPF_PROG_RUN() macro. + * + * Return: the &fp argument along with &err set to 0 for success or + * a negative errno code on failure */ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) { diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 72c58cc516..9c011f3a26 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -1565,8 +1565,8 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map, /* We cannot do copy_from_user or copy_to_user inside * the rcu_read_lock. Allocate enough space here. */ - keys = kvmalloc(key_size * bucket_size, GFP_USER | __GFP_NOWARN); - values = kvmalloc(value_size * bucket_size, GFP_USER | __GFP_NOWARN); + keys = kvmalloc_array(key_size, bucket_size, GFP_USER | __GFP_NOWARN); + values = kvmalloc_array(value_size, bucket_size, GFP_USER | __GFP_NOWARN); if (!keys || !values) { ret = -ENOMEM; goto after_loop; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 62cf003839..7a97b2f474 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -397,8 +397,8 @@ BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags) void *ptr; int i; - for (i = 0; i < BPF_CGROUP_STORAGE_NEST_MAX; i++) { - if (unlikely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current)) + for (i = BPF_CGROUP_STORAGE_NEST_MAX - 1; i >= 0; i--) { + if (likely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current)) continue; storage = this_cpu_read(bpf_cgroup_storage_info[i].storage[stype]); @@ -1070,12 +1070,12 @@ bpf_base_func_proto(enum bpf_func_id func_id) case BPF_FUNC_probe_read_user: return &bpf_probe_read_user_proto; case BPF_FUNC_probe_read_kernel: - return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_kernel_proto; case BPF_FUNC_probe_read_user_str: return &bpf_probe_read_user_str_proto; case BPF_FUNC_probe_read_kernel_str: - return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_kernel_str_proto; case BPF_FUNC_snprintf_btf: return &bpf_snprintf_btf_proto; diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index 7f0e589174..b264ab5652 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -347,19 +347,20 @@ static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu) } static struct cgroup_rstat_cpu * -cgroup_base_stat_cputime_account_begin(struct cgroup *cgrp) +cgroup_base_stat_cputime_account_begin(struct cgroup *cgrp, unsigned long *flags) { struct cgroup_rstat_cpu *rstatc; rstatc = get_cpu_ptr(cgrp->rstat_cpu); - u64_stats_update_begin(&rstatc->bsync); + *flags = u64_stats_update_begin_irqsave(&rstatc->bsync); return rstatc; } static void cgroup_base_stat_cputime_account_end(struct cgroup *cgrp, - struct cgroup_rstat_cpu *rstatc) + struct cgroup_rstat_cpu *rstatc, + unsigned long flags) { - u64_stats_update_end(&rstatc->bsync); + u64_stats_update_end_irqrestore(&rstatc->bsync, flags); cgroup_rstat_updated(cgrp, smp_processor_id()); put_cpu_ptr(rstatc); } @@ -367,18 +368,20 @@ static void cgroup_base_stat_cputime_account_end(struct cgroup *cgrp, void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec) { struct cgroup_rstat_cpu *rstatc; + unsigned long flags; - rstatc = cgroup_base_stat_cputime_account_begin(cgrp); + rstatc = cgroup_base_stat_cputime_account_begin(cgrp, &flags); rstatc->bstat.cputime.sum_exec_runtime += delta_exec; - cgroup_base_stat_cputime_account_end(cgrp, rstatc); + cgroup_base_stat_cputime_account_end(cgrp, rstatc, flags); } void __cgroup_account_cputime_field(struct cgroup *cgrp, enum cpu_usage_stat index, u64 delta_exec) { struct cgroup_rstat_cpu *rstatc; + unsigned long flags; - rstatc = cgroup_base_stat_cputime_account_begin(cgrp); + rstatc = cgroup_base_stat_cputime_account_begin(cgrp, &flags); switch (index) { case CPUTIME_USER: @@ -394,7 +397,7 @@ void __cgroup_account_cputime_field(struct cgroup *cgrp, break; } - cgroup_base_stat_cputime_account_end(cgrp, rstatc); + cgroup_base_stat_cputime_account_end(cgrp, rstatc, flags); } /* diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 7f04c7d829..a98bcfc4be 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -265,8 +265,11 @@ int irq_startup(struct irq_desc *desc, bool resend, bool force) } else { switch (__irq_startup_managed(desc, aff, force)) { case IRQ_STARTUP_NORMAL: + if (d->chip->flags & IRQCHIP_AFFINITY_PRE_STARTUP) + irq_setup_affinity(desc); ret = __irq_startup(desc); - irq_setup_affinity(desc); + if (!(d->chip->flags & IRQCHIP_AFFINITY_PRE_STARTUP)) + irq_setup_affinity(desc); break; case IRQ_STARTUP_MANAGED: irq_do_set_affinity(d, aff, false); diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index b338d622f2..85df3ca03e 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -5,7 +5,7 @@ * * This file is licensed under GPLv2. * - * This file contains common code to support Message Signalled Interrupt for + * This file contains common code to support Message Signaled Interrupts for * PCI compatible and non PCI compatible devices. */ #include @@ -476,11 +476,6 @@ int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, return 0; cleanup: - for_each_msi_vector(desc, i, dev) { - irq_data = irq_domain_get_irq_data(domain, i); - if (irqd_is_activated(irq_data)) - irq_domain_deactivate_irq(irq_data); - } msi_domain_free_irqs(domain, dev); return ret; } @@ -505,7 +500,15 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, void __msi_domain_free_irqs(struct irq_domain *domain, struct device *dev) { + struct irq_data *irq_data; struct msi_desc *desc; + int i; + + for_each_msi_vector(desc, i, dev) { + irq_data = irq_domain_get_irq_data(domain, i); + if (irqd_is_activated(irq_data)) + irq_domain_deactivate_irq(irq_data); + } for_each_msi_entry(desc, dev) { /* diff --git a/kernel/irq/timings.c b/kernel/irq/timings.c index 773b6105c4..4d2a702d7a 100644 --- a/kernel/irq/timings.c +++ b/kernel/irq/timings.c @@ -84,7 +84,7 @@ void irq_timings_disable(void) * 2. Log interval * * We saw the irq timings allow to compute the interval of the - * occurrences for a specific interrupt. We can reasonibly assume the + * occurrences for a specific interrupt. We can reasonably assume the * longer is the interval, the higher is the error for the next event * and we can consider storing those interval values into an array * where each slot in the array correspond to an interval at the power @@ -416,7 +416,7 @@ static u64 __irq_timings_next_event(struct irqt_stat *irqs, int irq, u64 now) * Copy the content of the circular buffer into another buffer * in order to linearize the buffer instead of dealing with * wrapping indexes and shifted array which will be prone to - * error and extremelly difficult to debug. + * error and extremely difficult to debug. */ for (i = 0; i < count; i++) { int index = (start + i) & IRQ_TIMINGS_MASK; @@ -453,6 +453,11 @@ static __always_inline void __irq_timings_store(int irq, struct irqt_stat *irqs, */ index = irq_timings_interval_index(interval); + if (index > PREDICTION_BUFFER_SIZE - 1) { + irqs->count = 0; + return; + } + /* * Store the index as an element of the pattern in another * circular array. @@ -485,7 +490,7 @@ static inline void irq_timings_store(int irq, struct irqt_stat *irqs, u64 ts) /* * The interrupt triggered more than one second apart, that - * ends the sequence as predictible for our purpose. In this + * ends the sequence as predictable for our purpose. In this * case, assume we have the beginning of a sequence and the * timestamp is the first value. As it is impossible to * predict anything at this point, return. @@ -514,7 +519,7 @@ static inline void irq_timings_store(int irq, struct irqt_stat *irqs, u64 ts) * If more than the array size interrupts happened during the * last busy/idle cycle, the index wrapped up and we have to * begin with the next element in the array which is the last one - * in the sequence, otherwise it is a the index 0. + * in the sequence, otherwise it is at the index 0. * * - have an indication of the interrupts activity on this CPU * (eg. irq/sec) diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index b5d9bb5202..ad0db322ed 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -343,7 +343,7 @@ static __always_inline bool rt_mutex_cond_detect_deadlock(struct rt_mutex_waiter *waiter, enum rtmutex_chainwalk chwalk) { - if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEX)) + if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES)) return waiter != NULL; return chwalk == RT_MUTEX_FULL_CHAINWALK; } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index b4916ef388..fdd14072fc 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -990,28 +990,29 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_numa_node_id_proto; case BPF_FUNC_perf_event_read: return &bpf_perf_event_read_proto; - case BPF_FUNC_probe_write_user: - return bpf_get_probe_write_proto(); case BPF_FUNC_current_task_under_cgroup: return &bpf_current_task_under_cgroup_proto; case BPF_FUNC_get_prandom_u32: return &bpf_get_prandom_u32_proto; + case BPF_FUNC_probe_write_user: + return security_locked_down(LOCKDOWN_BPF_WRITE_USER) < 0 ? + NULL : bpf_get_probe_write_proto(); case BPF_FUNC_probe_read_user: return &bpf_probe_read_user_proto; case BPF_FUNC_probe_read_kernel: - return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_kernel_proto; case BPF_FUNC_probe_read_user_str: return &bpf_probe_read_user_str_proto; case BPF_FUNC_probe_read_kernel_str: - return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_kernel_str_proto; #ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE case BPF_FUNC_probe_read: - return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_compat_proto; case BPF_FUNC_probe_read_str: - return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_compat_str_proto; #endif #ifdef CONFIG_CGROUPS diff --git a/kernel/ucount.c b/kernel/ucount.c index 77be3bbe3c..bb51849e63 100644 --- a/kernel/ucount.c +++ b/kernel/ucount.c @@ -58,14 +58,17 @@ static struct ctl_table_root set_root = { .permissions = set_permissions, }; -#define UCOUNT_ENTRY(name) \ - { \ - .procname = name, \ - .maxlen = sizeof(int), \ - .mode = 0644, \ - .proc_handler = proc_dointvec_minmax, \ - .extra1 = SYSCTL_ZERO, \ - .extra2 = SYSCTL_INT_MAX, \ +static long ue_zero = 0; +static long ue_int_max = INT_MAX; + +#define UCOUNT_ENTRY(name) \ + { \ + .procname = name, \ + .maxlen = sizeof(long), \ + .mode = 0644, \ + .proc_handler = proc_doulongvec_minmax, \ + .extra1 = &ue_zero, \ + .extra2 = &ue_int_max, \ } static struct ctl_table user_table[] = { UCOUNT_ENTRY("max_user_namespaces"), diff --git a/lib/devmem_is_allowed.c b/lib/devmem_is_allowed.c index c0d67c5418..60be9e24bd 100644 --- a/lib/devmem_is_allowed.c +++ b/lib/devmem_is_allowed.c @@ -19,7 +19,7 @@ */ int devmem_is_allowed(unsigned long pfn) { - if (iomem_is_exclusive(pfn << PAGE_SHIFT)) + if (iomem_is_exclusive(PFN_PHYS(pfn))) return 0; if (!page_is_ram(pfn)) return 1; diff --git a/lib/once.c b/lib/once.c index 8b7d623521..59149bf3bf 100644 --- a/lib/once.c +++ b/lib/once.c @@ -3,10 +3,12 @@ #include #include #include +#include struct once_work { struct work_struct work; struct static_key_true *key; + struct module *module; }; static void once_deferred(struct work_struct *w) @@ -16,10 +18,11 @@ static void once_deferred(struct work_struct *w) work = container_of(w, struct once_work, work); BUG_ON(!static_key_enabled(work->key)); static_branch_disable(work->key); + module_put(work->module); kfree(work); } -static void once_disable_jump(struct static_key_true *key) +static void once_disable_jump(struct static_key_true *key, struct module *mod) { struct once_work *w; @@ -29,6 +32,8 @@ static void once_disable_jump(struct static_key_true *key) INIT_WORK(&w->work, once_deferred); w->key = key; + w->module = mod; + __module_get(mod); schedule_work(&w->work); } @@ -53,11 +58,11 @@ bool __do_once_start(bool *done, unsigned long *flags) EXPORT_SYMBOL(__do_once_start); void __do_once_done(bool *done, struct static_key_true *once_key, - unsigned long *flags) + unsigned long *flags, struct module *mod) __releases(once_lock) { *done = true; spin_unlock_irqrestore(&once_lock, *flags); - once_disable_jump(once_key); + once_disable_jump(once_key, mod); } EXPORT_SYMBOL(__do_once_done); diff --git a/mm/gup.c b/mm/gup.c index 42b8b1fa65..b94717977d 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1558,9 +1558,12 @@ long faultin_vma_page_range(struct vm_area_struct *vma, unsigned long start, gup_flags |= FOLL_WRITE; /* - * See check_vma_flags(): Will return -EFAULT on incompatible mappings - * or with insufficient permissions. + * We want to report -EINVAL instead of -EFAULT for any permission + * problems or incompatible mappings. */ + if (check_vma_flags(vma, gup_flags)) + return -EINVAL; + return __get_user_pages(mm, start, nr_pages, gup_flags, NULL, NULL, locked); } diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 228a2fbe06..73d46d16d5 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -290,7 +290,7 @@ static void hex_dump_object(struct seq_file *seq, warn_or_seq_printf(seq, " hex dump (first %zu bytes):\n", len); kasan_disable_current(); warn_or_seq_hex_dump(seq, DUMP_PREFIX_NONE, HEX_ROW_SIZE, - HEX_GROUP_SIZE, ptr, len, HEX_ASCII); + HEX_GROUP_SIZE, kasan_reset_tag((void *)ptr), len, HEX_ASCII); kasan_enable_current(); } @@ -1171,7 +1171,7 @@ static bool update_checksum(struct kmemleak_object *object) kasan_disable_current(); kcsan_disable_current(); - object->checksum = crc32(0, (void *)object->pointer, object->size); + object->checksum = crc32(0, kasan_reset_tag((void *)object->pointer), object->size); kasan_enable_current(); kcsan_enable_current(); @@ -1246,7 +1246,7 @@ static void scan_block(void *_start, void *_end, break; kasan_disable_current(); - pointer = *ptr; + pointer = *(unsigned long *)kasan_reset_tag((void *)ptr); kasan_enable_current(); untagged_ptr = (unsigned long)kasan_reset_tag((void *)pointer); diff --git a/mm/madvise.c b/mm/madvise.c index 6d3d348b17..5c065bc8b5 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -862,10 +862,12 @@ static long madvise_populate(struct vm_area_struct *vma, switch (pages) { case -EINTR: return -EINTR; - case -EFAULT: /* Incompatible mappings / permissions. */ + case -EINVAL: /* Incompatible mappings / permissions. */ return -EINVAL; case -EHWPOISON: return -EHWPOISON; + case -EFAULT: /* VM_FAULT_SIGBUS or VM_FAULT_SIGSEGV */ + return -EFAULT; default: pr_warn_once("%s: unhandled return value: %ld\n", __func__, pages); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index eb8e87c483..702a81dfe7 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3106,13 +3106,15 @@ void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat, stock->cached_pgdat = pgdat; } else if (stock->cached_pgdat != pgdat) { /* Flush the existing cached vmstat data */ + struct pglist_data *oldpg = stock->cached_pgdat; + if (stock->nr_slab_reclaimable_b) { - mod_objcg_mlstate(objcg, pgdat, NR_SLAB_RECLAIMABLE_B, + mod_objcg_mlstate(objcg, oldpg, NR_SLAB_RECLAIMABLE_B, stock->nr_slab_reclaimable_b); stock->nr_slab_reclaimable_b = 0; } if (stock->nr_slab_unreclaimable_b) { - mod_objcg_mlstate(objcg, pgdat, NR_SLAB_UNRECLAIMABLE_B, + mod_objcg_mlstate(objcg, oldpg, NR_SLAB_UNRECLAIMABLE_B, stock->nr_slab_unreclaimable_b); stock->nr_slab_unreclaimable_b = 0; } diff --git a/mm/slub.c b/mm/slub.c index af984e4990..f77d8cd79e 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -576,8 +576,8 @@ static void print_section(char *level, char *text, u8 *addr, unsigned int length) { metadata_access_enable(); - print_hex_dump(level, kasan_reset_tag(text), DUMP_PREFIX_ADDRESS, - 16, 1, addr, length, 1); + print_hex_dump(level, text, DUMP_PREFIX_ADDRESS, + 16, 1, kasan_reset_tag((void *)addr), length, 1); metadata_access_disable(); } @@ -1400,12 +1400,13 @@ parse_slub_debug_flags(char *str, slab_flags_t *flags, char **slabs, bool init) static int __init setup_slub_debug(char *str) { slab_flags_t flags; + slab_flags_t global_flags; char *saved_str; char *slab_list; bool global_slub_debug_changed = false; bool slab_list_specified = false; - slub_debug = DEBUG_DEFAULT_FLAGS; + global_flags = DEBUG_DEFAULT_FLAGS; if (*str++ != '=' || !*str) /* * No options specified. Switch on full debugging. @@ -1417,7 +1418,7 @@ static int __init setup_slub_debug(char *str) str = parse_slub_debug_flags(str, &flags, &slab_list, true); if (!slab_list) { - slub_debug = flags; + global_flags = flags; global_slub_debug_changed = true; } else { slab_list_specified = true; @@ -1426,16 +1427,18 @@ static int __init setup_slub_debug(char *str) /* * For backwards compatibility, a single list of flags with list of - * slabs means debugging is only enabled for those slabs, so the global - * slub_debug should be 0. We can extended that to multiple lists as + * slabs means debugging is only changed for those slabs, so the global + * slub_debug should be unchanged (0 or DEBUG_DEFAULT_FLAGS, depending + * on CONFIG_SLUB_DEBUG_ON). We can extended that to multiple lists as * long as there is no option specifying flags without a slab list. */ if (slab_list_specified) { if (!global_slub_debug_changed) - slub_debug = 0; + global_flags = slub_debug; slub_debug_string = saved_str; } out: + slub_debug = global_flags; if (slub_debug != 0 || slub_debug_string) static_branch_enable(&slub_debug_enabled); else @@ -3236,12 +3239,12 @@ struct detached_freelist { struct kmem_cache *s; }; -static inline void free_nonslab_page(struct page *page) +static inline void free_nonslab_page(struct page *page, void *object) { unsigned int order = compound_order(page); VM_BUG_ON_PAGE(!PageCompound(page), page); - kfree_hook(page_address(page)); + kfree_hook(object); mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B, -(PAGE_SIZE << order)); __free_pages(page, order); } @@ -3282,7 +3285,7 @@ int build_detached_freelist(struct kmem_cache *s, size_t size, if (!s) { /* Handle kalloc'ed objects */ if (unlikely(!PageSlab(page))) { - free_nonslab_page(page); + free_nonslab_page(page, object); p[size] = NULL; /* mark object processed */ return size; } @@ -4258,7 +4261,7 @@ void kfree(const void *x) page = virt_to_head_page(x); if (unlikely(!PageSlab(page))) { - free_nonslab_page(page); + free_nonslab_page(page, object); return; } slab_free(page->slab_cache, page, object, NULL, 1, _RET_IP_); diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 1cc75c811e..caa16bf30f 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include @@ -951,7 +952,10 @@ int bpf_prog_test_run_syscall(struct bpf_prog *prog, goto out; } } + + rcu_read_lock_trace(); retval = bpf_prog_run_pin_on_cpu(prog, ctx); + rcu_read_unlock_trace(); if (copy_to_user(&uattr->test.retval, &retval, sizeof(u32))) { err = -EFAULT; diff --git a/net/bridge/br.c b/net/bridge/br.c index bbab9984f2..ef743f9425 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -166,8 +166,7 @@ static int br_switchdev_event(struct notifier_block *unused, case SWITCHDEV_FDB_ADD_TO_BRIDGE: fdb_info = ptr; err = br_fdb_external_learn_add(br, p, fdb_info->addr, - fdb_info->vid, - fdb_info->is_local, false); + fdb_info->vid, false); if (err) { err = notifier_from_errno(err); break; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 835cec1e5a..5dee30966e 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -1044,10 +1044,7 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br, "FDB entry towards bridge must be permanent"); return -EINVAL; } - - err = br_fdb_external_learn_add(br, p, addr, vid, - ndm->ndm_state & NUD_PERMANENT, - true); + err = br_fdb_external_learn_add(br, p, addr, vid, true); } else { spin_lock_bh(&br->hash_lock); err = fdb_add_entry(br, p, addr, ndm, nlh_flags, vid, nfea_tb); @@ -1275,7 +1272,7 @@ void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p) } int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, - const unsigned char *addr, u16 vid, bool is_local, + const unsigned char *addr, u16 vid, bool swdev_notify) { struct net_bridge_fdb_entry *fdb; @@ -1293,7 +1290,7 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, if (swdev_notify) flags |= BIT(BR_FDB_ADDED_BY_USER); - if (is_local) + if (!p) flags |= BIT(BR_FDB_LOCAL); fdb = fdb_create(br, p, addr, vid, flags); @@ -1322,7 +1319,7 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, if (swdev_notify) set_bit(BR_FDB_ADDED_BY_USER, &fdb->flags); - if (is_local) + if (!p) set_bit(BR_FDB_LOCAL, &fdb->flags); if (modified) diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 6e4a32354a..14cd6ef961 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -616,6 +616,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, err = dev_set_allmulti(dev, 1); if (err) { + br_multicast_del_port(p); kfree(p); /* kobject not yet init'd, manually free */ goto err1; } @@ -729,6 +730,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, err3: sysfs_remove_link(br->ifobj, p->dev->name); err2: + br_multicast_del_port(p); kobject_put(&p->kobj); dev_set_allmulti(dev, -1); err1: diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index aa64d8d63c..2b48b20420 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -711,7 +711,7 @@ int br_fdb_get(struct sk_buff *skb, struct nlattr *tb[], struct net_device *dev, int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p); void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p); int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, - const unsigned char *addr, u16 vid, bool is_local, + const unsigned char *addr, u16 vid, bool swdev_notify); int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, u16 vid, diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index 8d033a75a7..fdbed31585 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -88,6 +88,12 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk, skb = ip_fraglist_next(&iter); } + + if (!err) + return 0; + + kfree_skb_list(iter.frag); + return err; } slow_path: diff --git a/net/core/link_watch.c b/net/core/link_watch.c index 75431ca930..1a455847da 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -158,7 +158,7 @@ static void linkwatch_do_dev(struct net_device *dev) clear_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state); rfc2863_policy(dev); - if (dev->flags & IFF_UP && netif_device_present(dev)) { + if (dev->flags & IFF_UP) { if (netif_carrier_ok(dev)) dev_activate(dev); else @@ -204,7 +204,8 @@ static void __linkwatch_run_queue(int urgent_only) dev = list_first_entry(&wrk, struct net_device, link_watch_list); list_del_init(&dev->link_watch_list); - if (urgent_only && !linkwatch_urgent_event(dev)) { + if (!netif_device_present(dev) || + (urgent_only && !linkwatch_urgent_event(dev))) { list_add_tail(&dev->link_watch_list, &lweventlist); continue; } diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 5e4eb45b13..8ab7b40224 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -634,7 +634,15 @@ bool page_pool_return_skb_page(struct page *page) struct page_pool *pp; page = compound_head(page); - if (unlikely(page->pp_magic != PP_SIGNATURE)) + + /* page->pp_magic is OR'ed with PP_SIGNATURE after the allocation + * in order to preserve any existing bits, such as bit 0 for the + * head page of compound page and bit 1 for pfmemalloc page, so + * mask those bits for freeing side when doing below checking, + * and page_is_pfmemalloc() is checked in __page_pool_put_page() + * to avoid recycling the pfmemalloc page. + */ + if (unlikely((page->pp_magic & ~0x3UL) != PP_SIGNATURE)) return false; pp = page->pp; diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 9cc9d1ee6c..c5c1d2b804 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -41,9 +41,9 @@ extern bool dccp_debug; #define dccp_pr_debug_cat(format, a...) DCCP_PRINTK(dccp_debug, format, ##a) #define dccp_debug(fmt, a...) dccp_pr_debug_cat(KERN_DEBUG fmt, ##a) #else -#define dccp_pr_debug(format, a...) -#define dccp_pr_debug_cat(format, a...) -#define dccp_debug(format, a...) +#define dccp_pr_debug(format, a...) do {} while (0) +#define dccp_pr_debug_cat(format, a...) do {} while (0) +#define dccp_debug(format, a...) do {} while (0) #endif extern struct inet_hashinfo dccp_hashinfo; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 532085da8d..23be8e0102 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -2291,8 +2291,8 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, static void dsa_fdb_offload_notify(struct dsa_switchdev_event_work *switchdev_work) { + struct switchdev_notifier_fdb_info info = {}; struct dsa_switch *ds = switchdev_work->ds; - struct switchdev_notifier_fdb_info info; struct dsa_port *dp; if (!dsa_is_user_port(ds, switchdev_work->port)) diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c index a45a0401ad..c25f761777 100644 --- a/net/ieee802154/socket.c +++ b/net/ieee802154/socket.c @@ -984,6 +984,11 @@ static const struct proto_ops ieee802154_dgram_ops = { .sendpage = sock_no_sendpage, }; +static void ieee802154_sock_destruct(struct sock *sk) +{ + skb_queue_purge(&sk->sk_receive_queue); +} + /* Create a socket. Initialise the socket, blank the addresses * set the state. */ @@ -1024,7 +1029,7 @@ static int ieee802154_create(struct net *net, struct socket *sock, sock->ops = ops; sock_init_data(sock, sk); - /* FIXME: sk->sk_destruct */ + sk->sk_destruct = ieee802154_sock_destruct; sk->sk_family = PF_IEEE802154; /* Checksums on by default */ diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 6b3c558a4f..00576bae18 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -803,10 +803,17 @@ static void igmp_gq_timer_expire(struct timer_list *t) static void igmp_ifc_timer_expire(struct timer_list *t) { struct in_device *in_dev = from_timer(in_dev, t, mr_ifc_timer); + u32 mr_ifc_count; igmpv3_send_cr(in_dev); - if (in_dev->mr_ifc_count) { - in_dev->mr_ifc_count--; +restart: + mr_ifc_count = READ_ONCE(in_dev->mr_ifc_count); + + if (mr_ifc_count) { + if (cmpxchg(&in_dev->mr_ifc_count, + mr_ifc_count, + mr_ifc_count - 1) != mr_ifc_count) + goto restart; igmp_ifc_start_timer(in_dev, unsolicited_report_interval(in_dev)); } @@ -818,7 +825,7 @@ static void igmp_ifc_event(struct in_device *in_dev) struct net *net = dev_net(in_dev->dev); if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) return; - in_dev->mr_ifc_count = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + WRITE_ONCE(in_dev->mr_ifc_count, in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv); igmp_ifc_start_timer(in_dev, 1); } @@ -957,7 +964,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, in_dev->mr_qri; } /* cancel the interface change timer */ - in_dev->mr_ifc_count = 0; + WRITE_ONCE(in_dev->mr_ifc_count, 0); if (del_timer(&in_dev->mr_ifc_timer)) __in_dev_put(in_dev); /* clear deleted report items */ @@ -1724,7 +1731,7 @@ void ip_mc_down(struct in_device *in_dev) igmp_group_dropped(pmc); #ifdef CONFIG_IP_MULTICAST - in_dev->mr_ifc_count = 0; + WRITE_ONCE(in_dev->mr_ifc_count, 0); if (del_timer(&in_dev->mr_ifc_timer)) __in_dev_put(in_dev); in_dev->mr_gq_running = 0; @@ -1941,7 +1948,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, pmc->sfmode = MCAST_INCLUDE; #ifdef CONFIG_IP_MULTICAST pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; - in_dev->mr_ifc_count = pmc->crcount; + WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; igmp_ifc_event(pmc->interface); @@ -2120,7 +2127,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, /* else no filters; keep old mode for reports */ pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; - in_dev->mr_ifc_count = pmc->crcount; + WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; igmp_ifc_event(in_dev); diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 6ea3dc2e42..6274462b86 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -1041,7 +1041,7 @@ static void bbr_init(struct sock *sk) bbr->prior_cwnd = 0; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; bbr->rtt_cnt = 0; - bbr->next_rtt_delivered = 0; + bbr->next_rtt_delivered = tp->delivered; bbr->prev_ca_state = TCP_CA_Open; bbr->packet_conservation = 0; diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c index d1bef23fd4..dd30c03d5a 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -132,8 +132,11 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); if (ret) return ret; - if (ip > ip_to) + if (ip > ip_to) { + if (ip_to == 0) + return -IPSET_ERR_HASH_ELEM; swap(ip, ip_to); + } } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); @@ -144,6 +147,10 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], hosts = h->netmask == 32 ? 1 : 2 << (32 - h->netmask - 1); + /* 64bit division is not allowed on 32bit */ + if (((u64)ip_to - ip + 1) >> (32 - h->netmask) > IPSET_MAX_RANGE) + return -ERANGE; + if (retried) { ip = ntohl(h->next.ip); e.ip = htonl(ip); diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c index 18346d18aa..153de34574 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmark.c +++ b/net/netfilter/ipset/ip_set_hash_ipmark.c @@ -121,6 +121,8 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], e.mark = ntohl(nla_get_be32(tb[IPSET_ATTR_MARK])); e.mark &= h->markmask; + if (e.mark == 0 && e.ip == 0) + return -IPSET_ERR_HASH_ELEM; if (adt == IPSET_TEST || !(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR])) { @@ -133,8 +135,11 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); if (ret) return ret; - if (ip > ip_to) + if (ip > ip_to) { + if (e.mark == 0 && ip_to == 0) + return -IPSET_ERR_HASH_ELEM; swap(ip, ip_to); + } } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); @@ -143,6 +148,9 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], ip_set_mask_from_to(ip, ip_to, cidr); } + if (((u64)ip_to - ip + 1) > IPSET_MAX_RANGE) + return -ERANGE; + if (retried) ip = ntohl(h->next.ip); for (; ip <= ip_to; ip++) { diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index e1ca111965..7303138e46 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -173,6 +173,9 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], swap(port, port_to); } + if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE) + return -ERANGE; + if (retried) ip = ntohl(h->next.ip); for (; ip <= ip_to; ip++) { diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c index ab179e0645..334fb1ad0e 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -180,6 +180,9 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], swap(port, port_to); } + if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE) + return -ERANGE; + if (retried) ip = ntohl(h->next.ip); for (; ip <= ip_to; ip++) { diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index 8f075b44cf..7df94f437f 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -253,6 +253,9 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], swap(port, port_to); } + if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE) + return -ERANGE; + ip2_to = ip2_from; if (tb[IPSET_ATTR_IP2_TO]) { ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2_TO], &ip2_to); diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index c1a11f041a..1422739d9a 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -140,7 +140,7 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_net4_elem e = { .cidr = HOST_MASK }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 ip = 0, ip_to = 0; + u32 ip = 0, ip_to = 0, ipn, n = 0; int ret; if (tb[IPSET_ATTR_LINENO]) @@ -188,6 +188,15 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], if (ip + UINT_MAX == ip_to) return -IPSET_ERR_HASH_RANGE; } + ipn = ip; + do { + ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr); + n++; + } while (ipn++ < ip_to); + + if (n > IPSET_MAX_RANGE) + return -ERANGE; + if (retried) ip = ntohl(h->next.ip); do { diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index ddd51c2e1c..9810f5bf63 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -202,7 +202,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netiface4_elem e = { .cidr = HOST_MASK, .elem = 1 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 ip = 0, ip_to = 0; + u32 ip = 0, ip_to = 0, ipn, n = 0; int ret; if (tb[IPSET_ATTR_LINENO]) @@ -256,6 +256,14 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip, ip_to, e.cidr); } + ipn = ip; + do { + ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr); + n++; + } while (ipn++ < ip_to); + + if (n > IPSET_MAX_RANGE) + return -ERANGE; if (retried) ip = ntohl(h->next.ip); diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c index 6532f0505e..3d09eefe99 100644 --- a/net/netfilter/ipset/ip_set_hash_netnet.c +++ b/net/netfilter/ipset/ip_set_hash_netnet.c @@ -168,7 +168,8 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], struct hash_netnet4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip = 0, ip_to = 0; - u32 ip2 = 0, ip2_from = 0, ip2_to = 0; + u32 ip2 = 0, ip2_from = 0, ip2_to = 0, ipn; + u64 n = 0, m = 0; int ret; if (tb[IPSET_ATTR_LINENO]) @@ -244,6 +245,19 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip2_from, ip2_to, e.cidr[1]); } + ipn = ip; + do { + ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr[0]); + n++; + } while (ipn++ < ip_to); + ipn = ip2_from; + do { + ipn = ip_set_range_to_cidr(ipn, ip2_to, &e.cidr[1]); + m++; + } while (ipn++ < ip2_to); + + if (n*m > IPSET_MAX_RANGE) + return -ERANGE; if (retried) { ip = ntohl(h->next.ip[0]); diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index ec1564a1cb..09cf72eb37 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -158,7 +158,8 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport4_elem e = { .cidr = HOST_MASK - 1 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 port, port_to, p = 0, ip = 0, ip_to = 0; + u32 port, port_to, p = 0, ip = 0, ip_to = 0, ipn; + u64 n = 0; bool with_ports = false; u8 cidr; int ret; @@ -235,6 +236,14 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip, ip_to, e.cidr + 1); } + ipn = ip; + do { + ipn = ip_set_range_to_cidr(ipn, ip_to, &cidr); + n++; + } while (ipn++ < ip_to); + + if (n*(port_to - port + 1) > IPSET_MAX_RANGE) + return -ERANGE; if (retried) { ip = ntohl(h->next.ip); diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index 0e91d1e82f..19bcdb3141 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -182,7 +182,8 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], struct hash_netportnet4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip = 0, ip_to = 0, p = 0, port, port_to; - u32 ip2_from = 0, ip2_to = 0, ip2; + u32 ip2_from = 0, ip2_to = 0, ip2, ipn; + u64 n = 0, m = 0; bool with_ports = false; int ret; @@ -284,6 +285,19 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip2_from, ip2_to, e.cidr[1]); } + ipn = ip; + do { + ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr[0]); + n++; + } while (ipn++ < ip_to); + ipn = ip2_from; + do { + ipn = ip_set_range_to_cidr(ipn, ip2_to, &e.cidr[1]); + m++; + } while (ipn++ < ip2_to); + + if (n*m*(port_to - port + 1) > IPSET_MAX_RANGE) + return -ERANGE; if (retried) { ip = ntohl(h->next.ip[0]); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 5c03e51067..d31dbccbe7 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -66,22 +66,17 @@ EXPORT_SYMBOL_GPL(nf_conntrack_hash); struct conntrack_gc_work { struct delayed_work dwork; - u32 last_bucket; + u32 next_bucket; bool exiting; bool early_drop; - long next_gc_run; }; static __read_mostly struct kmem_cache *nf_conntrack_cachep; static DEFINE_SPINLOCK(nf_conntrack_locks_all_lock); static __read_mostly bool nf_conntrack_locks_all; -/* every gc cycle scans at most 1/GC_MAX_BUCKETS_DIV part of table */ -#define GC_MAX_BUCKETS_DIV 128u -/* upper bound of full table scan */ -#define GC_MAX_SCAN_JIFFIES (16u * HZ) -/* desired ratio of entries found to be expired */ -#define GC_EVICT_RATIO 50u +#define GC_SCAN_INTERVAL (120u * HZ) +#define GC_SCAN_MAX_DURATION msecs_to_jiffies(10) static struct conntrack_gc_work conntrack_gc_work; @@ -1363,17 +1358,13 @@ static bool gc_worker_can_early_drop(const struct nf_conn *ct) static void gc_worker(struct work_struct *work) { - unsigned int min_interval = max(HZ / GC_MAX_BUCKETS_DIV, 1u); - unsigned int i, goal, buckets = 0, expired_count = 0; - unsigned int nf_conntrack_max95 = 0; + unsigned long end_time = jiffies + GC_SCAN_MAX_DURATION; + unsigned int i, hashsz, nf_conntrack_max95 = 0; + unsigned long next_run = GC_SCAN_INTERVAL; struct conntrack_gc_work *gc_work; - unsigned int ratio, scanned = 0; - unsigned long next_run; - gc_work = container_of(work, struct conntrack_gc_work, dwork.work); - goal = nf_conntrack_htable_size / GC_MAX_BUCKETS_DIV; - i = gc_work->last_bucket; + i = gc_work->next_bucket; if (gc_work->early_drop) nf_conntrack_max95 = nf_conntrack_max / 100u * 95u; @@ -1381,15 +1372,15 @@ static void gc_worker(struct work_struct *work) struct nf_conntrack_tuple_hash *h; struct hlist_nulls_head *ct_hash; struct hlist_nulls_node *n; - unsigned int hashsz; struct nf_conn *tmp; - i++; rcu_read_lock(); nf_conntrack_get_ht(&ct_hash, &hashsz); - if (i >= hashsz) - i = 0; + if (i >= hashsz) { + rcu_read_unlock(); + break; + } hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[i], hnnode) { struct nf_conntrack_net *cnet; @@ -1397,7 +1388,6 @@ static void gc_worker(struct work_struct *work) tmp = nf_ct_tuplehash_to_ctrack(h); - scanned++; if (test_bit(IPS_OFFLOAD_BIT, &tmp->status)) { nf_ct_offload_timeout(tmp); continue; @@ -1405,7 +1395,6 @@ static void gc_worker(struct work_struct *work) if (nf_ct_is_expired(tmp)) { nf_ct_gc_expired(tmp); - expired_count++; continue; } @@ -1438,7 +1427,14 @@ static void gc_worker(struct work_struct *work) */ rcu_read_unlock(); cond_resched(); - } while (++buckets < goal); + i++; + + if (time_after(jiffies, end_time) && i < hashsz) { + gc_work->next_bucket = i; + next_run = 0; + break; + } + } while (i < hashsz); if (gc_work->exiting) return; @@ -1449,40 +1445,17 @@ static void gc_worker(struct work_struct *work) * * This worker is only here to reap expired entries when system went * idle after a busy period. - * - * The heuristics below are supposed to balance conflicting goals: - * - * 1. Minimize time until we notice a stale entry - * 2. Maximize scan intervals to not waste cycles - * - * Normally, expire ratio will be close to 0. - * - * As soon as a sizeable fraction of the entries have expired - * increase scan frequency. */ - ratio = scanned ? expired_count * 100 / scanned : 0; - if (ratio > GC_EVICT_RATIO) { - gc_work->next_gc_run = min_interval; - } else { - unsigned int max = GC_MAX_SCAN_JIFFIES / GC_MAX_BUCKETS_DIV; - - BUILD_BUG_ON((GC_MAX_SCAN_JIFFIES / GC_MAX_BUCKETS_DIV) == 0); - - gc_work->next_gc_run += min_interval; - if (gc_work->next_gc_run > max) - gc_work->next_gc_run = max; + if (next_run) { + gc_work->early_drop = false; + gc_work->next_bucket = 0; } - - next_run = gc_work->next_gc_run; - gc_work->last_bucket = i; - gc_work->early_drop = false; queue_delayed_work(system_power_efficient_wq, &gc_work->dwork, next_run); } static void conntrack_gc_work_init(struct conntrack_gc_work *gc_work) { INIT_DEFERRABLE_WORK(&gc_work->dwork, gc_worker); - gc_work->next_gc_run = HZ; gc_work->exiting = false; } diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 3259416f2e..af5115e127 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1478,7 +1478,6 @@ void nf_conntrack_tcp_init_net(struct net *net) #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) tn->offload_timeout = 30 * HZ; - tn->offload_pickup = 120 * HZ; #endif } diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 698fee49e7..f8e3c0d260 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -271,7 +271,6 @@ void nf_conntrack_udp_init_net(struct net *net) #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) un->offload_timeout = 30 * HZ; - un->offload_pickup = 30 * HZ; #endif } diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 214d9f9e49..e84b499b7b 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -575,7 +575,6 @@ enum nf_ct_sysctl_index { NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_UNACK, #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD, - NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP, #endif NF_SYSCTL_CT_PROTO_TCP_LOOSE, NF_SYSCTL_CT_PROTO_TCP_LIBERAL, @@ -585,7 +584,6 @@ enum nf_ct_sysctl_index { NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM, #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD, - NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP, #endif NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP, NF_SYSCTL_CT_PROTO_TIMEOUT_ICMPV6, @@ -776,12 +774,6 @@ static struct ctl_table nf_ct_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP] = { - .procname = "nf_flowtable_tcp_pickup", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, #endif [NF_SYSCTL_CT_PROTO_TCP_LOOSE] = { .procname = "nf_conntrack_tcp_loose", @@ -832,12 +824,6 @@ static struct ctl_table nf_ct_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - [NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP] = { - .procname = "nf_flowtable_udp_pickup", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, #endif [NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP] = { .procname = "nf_conntrack_icmp_timeout", @@ -1018,7 +1004,6 @@ static void nf_conntrack_standalone_init_tcp_sysctl(struct net *net, #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) table[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD].data = &tn->offload_timeout; - table[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP].data = &tn->offload_pickup; #endif } @@ -1111,7 +1096,6 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net) table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM].data = &un->timeouts[UDP_CT_REPLIED]; #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD].data = &un->offload_timeout; - table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP].data = &un->offload_pickup; #endif nf_conntrack_standalone_init_tcp_sysctl(net, table); diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 551976e428..8788b51925 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -183,7 +183,7 @@ static void flow_offload_fixup_ct_timeout(struct nf_conn *ct) const struct nf_conntrack_l4proto *l4proto; struct net *net = nf_ct_net(ct); int l4num = nf_ct_protonum(ct); - unsigned int timeout; + s32 timeout; l4proto = nf_ct_l4proto_find(l4num); if (!l4proto) @@ -192,15 +192,20 @@ static void flow_offload_fixup_ct_timeout(struct nf_conn *ct) if (l4num == IPPROTO_TCP) { struct nf_tcp_net *tn = nf_tcp_pernet(net); - timeout = tn->offload_pickup; + timeout = tn->timeouts[TCP_CONNTRACK_ESTABLISHED]; + timeout -= tn->offload_timeout; } else if (l4num == IPPROTO_UDP) { struct nf_udp_net *tn = nf_udp_pernet(net); - timeout = tn->offload_pickup; + timeout = tn->timeouts[UDP_CT_REPLIED]; + timeout -= tn->offload_timeout; } else { return; } + if (timeout < 0) + timeout = 0; + if (nf_flow_timeout_delta(ct->timeout) > (__s32)timeout) ct->timeout = nfct_time_stamp + timeout; } diff --git a/net/netfilter/nfnetlink_hook.c b/net/netfilter/nfnetlink_hook.c index 202f57d17b..f554e2ea32 100644 --- a/net/netfilter/nfnetlink_hook.c +++ b/net/netfilter/nfnetlink_hook.c @@ -89,11 +89,15 @@ static int nfnl_hook_put_nft_chain_info(struct sk_buff *nlskb, if (!nest2) goto cancel_nest; - ret = nla_put_string(nlskb, NFTA_CHAIN_TABLE, chain->table->name); + ret = nla_put_string(nlskb, NFNLA_CHAIN_TABLE, chain->table->name); if (ret) goto cancel_nest; - ret = nla_put_string(nlskb, NFTA_CHAIN_NAME, chain->name); + ret = nla_put_string(nlskb, NFNLA_CHAIN_NAME, chain->name); + if (ret) + goto cancel_nest; + + ret = nla_put_u8(nlskb, NFNLA_CHAIN_FAMILY, chain->table->family); if (ret) goto cancel_nest; @@ -109,18 +113,19 @@ static int nfnl_hook_put_nft_chain_info(struct sk_buff *nlskb, static int nfnl_hook_dump_one(struct sk_buff *nlskb, const struct nfnl_dump_hook_data *ctx, const struct nf_hook_ops *ops, - unsigned int seq) + int family, unsigned int seq) { u16 event = nfnl_msg_type(NFNL_SUBSYS_HOOK, NFNL_MSG_HOOK_GET); unsigned int portid = NETLINK_CB(nlskb).portid; struct nlmsghdr *nlh; int ret = -EMSGSIZE; + u32 hooknum; #ifdef CONFIG_KALLSYMS char sym[KSYM_SYMBOL_LEN]; char *module_name; #endif nlh = nfnl_msg_put(nlskb, portid, seq, event, - NLM_F_MULTI, ops->pf, NFNETLINK_V0, 0); + NLM_F_MULTI, family, NFNETLINK_V0, 0); if (!nlh) goto nla_put_failure; @@ -135,6 +140,7 @@ static int nfnl_hook_dump_one(struct sk_buff *nlskb, if (module_name) { char *end; + *module_name = '\0'; module_name += 2; end = strchr(module_name, ']'); if (end) { @@ -151,7 +157,12 @@ static int nfnl_hook_dump_one(struct sk_buff *nlskb, goto nla_put_failure; #endif - ret = nla_put_be32(nlskb, NFNLA_HOOK_HOOKNUM, htonl(ops->hooknum)); + if (ops->pf == NFPROTO_INET && ops->hooknum == NF_INET_INGRESS) + hooknum = NF_NETDEV_INGRESS; + else + hooknum = ops->hooknum; + + ret = nla_put_be32(nlskb, NFNLA_HOOK_HOOKNUM, htonl(hooknum)); if (ret) goto nla_put_failure; @@ -259,7 +270,8 @@ static int nfnl_hook_dump(struct sk_buff *nlskb, ops = nf_hook_entries_get_hook_ops(e); for (; i < e->num_hook_entries; i++) { - err = nfnl_hook_dump_one(nlskb, ctx, ops[i], cb->seq); + err = nfnl_hook_dump_one(nlskb, ctx, ops[i], family, + cb->nlh->nlmsg_seq); if (err) break; } diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index e586424d8b..9713035b89 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -293,14 +293,14 @@ static bool icmp6hdr_ok(struct sk_buff *skb) } /** - * Parse vlan tag from vlan header. + * parse_vlan_tag - Parse vlan tag from vlan header. * @skb: skb containing frame to parse * @key_vh: pointer to parsed vlan tag * @untag_vlan: should the vlan header be removed from the frame * - * Returns ERROR on memory error. - * Returns 0 if it encounters a non-vlan or incomplete packet. - * Returns 1 after successfully parsing vlan tag. + * Return: ERROR on memory error. + * %0 if it encounters a non-vlan or incomplete packet. + * %1 after successfully parsing vlan tag. */ static int parse_vlan_tag(struct sk_buff *skb, struct vlan_head *key_vh, bool untag_vlan) @@ -532,6 +532,7 @@ static int parse_nsh(struct sk_buff *skb, struct sw_flow_key *key) * L3 header * @key: output flow key * + * Return: %0 if successful, otherwise a negative errno value. */ static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key) { @@ -748,8 +749,6 @@ static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key) * * The caller must ensure that skb->len >= ETH_HLEN. * - * Returns 0 if successful, otherwise a negative errno value. - * * Initializes @skb header fields as follows: * * - skb->mac_header: the L2 header. @@ -764,6 +763,8 @@ static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key) * * - skb->protocol: the type of the data starting at skb->network_header. * Equals to key->eth.type. + * + * Return: %0 if successful, otherwise a negative errno value. */ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) { diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 7153c67f64..2ef4cd2c84 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -273,6 +273,9 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, goto out; } + /* All mirred/redirected skbs should clear previous ct info */ + nf_reset_ct(skb2); + want_ingress = tcf_mirred_act_wants_ingress(m_eaction); expects_nh = want_ingress || !m_mac_header_xmit; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 898389611a..c038efc23c 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -795,7 +795,7 @@ static int smc_connect_rdma(struct smc_sock *smc, reason_code = SMC_CLC_DECL_NOSRVLINK; goto connect_abort; } - smc->conn.lnk = link; + smc_switch_link_and_count(&smc->conn, link); } /* create send buffer and rmb */ diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index cd0d7c908b..c160ff50c0 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -917,8 +917,8 @@ static int smc_switch_cursor(struct smc_sock *smc, struct smc_cdc_tx_pend *pend, return rc; } -static void smc_switch_link_and_count(struct smc_connection *conn, - struct smc_link *to_lnk) +void smc_switch_link_and_count(struct smc_connection *conn, + struct smc_link *to_lnk) { atomic_dec(&conn->lnk->conn_cnt); conn->lnk = to_lnk; diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 6d6fd1397c..c043ecdca5 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -97,6 +97,7 @@ struct smc_link { unsigned long *wr_tx_mask; /* bit mask of used indexes */ u32 wr_tx_cnt; /* number of WR send buffers */ wait_queue_head_t wr_tx_wait; /* wait for free WR send buf */ + atomic_t wr_tx_refcnt; /* tx refs to link */ struct smc_wr_buf *wr_rx_bufs; /* WR recv payload buffers */ struct ib_recv_wr *wr_rx_ibs; /* WR recv meta data */ @@ -109,6 +110,7 @@ struct smc_link { struct ib_reg_wr wr_reg; /* WR register memory region */ wait_queue_head_t wr_reg_wait; /* wait for wr_reg result */ + atomic_t wr_reg_refcnt; /* reg refs to link */ enum smc_wr_reg_state wr_reg_state; /* state of wr_reg request */ u8 gid[SMC_GID_SIZE];/* gid matching used vlan id*/ @@ -444,6 +446,8 @@ void smc_core_exit(void); int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk, u8 link_idx, struct smc_init_info *ini); void smcr_link_clear(struct smc_link *lnk, bool log); +void smc_switch_link_and_count(struct smc_connection *conn, + struct smc_link *to_lnk); int smcr_buf_map_lgr(struct smc_link *lnk); int smcr_buf_reg_lgr(struct smc_link *lnk); void smcr_lgr_set_type(struct smc_link_group *lgr, enum smc_lgr_type new_type); diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index 273eaf1bfe..2e7560eba9 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -888,6 +888,7 @@ int smc_llc_cli_add_link(struct smc_link *link, struct smc_llc_qentry *qentry) if (!rc) goto out; out_clear_lnk: + lnk_new->state = SMC_LNK_INACTIVE; smcr_link_clear(lnk_new, false); out_reject: smc_llc_cli_add_link_reject(qentry); @@ -1184,6 +1185,7 @@ int smc_llc_srv_add_link(struct smc_link *link) goto out_err; return 0; out_err: + link_new->state = SMC_LNK_INACTIVE; smcr_link_clear(link_new, false); return rc; } @@ -1286,10 +1288,8 @@ static void smc_llc_process_cli_delete_link(struct smc_link_group *lgr) del_llc->reason = 0; smc_llc_send_message(lnk, &qentry->msg); /* response */ - if (smc_link_downing(&lnk_del->state)) { - if (smc_switch_conns(lgr, lnk_del, false)) - smc_wr_tx_wait_no_pending_sends(lnk_del); - } + if (smc_link_downing(&lnk_del->state)) + smc_switch_conns(lgr, lnk_del, false); smcr_link_clear(lnk_del, true); active_links = smc_llc_active_link_count(lgr); @@ -1805,8 +1805,6 @@ void smc_llc_link_clear(struct smc_link *link, bool log) link->smcibdev->ibdev->name, link->ibport); complete(&link->llc_testlink_resp); cancel_delayed_work_sync(&link->llc_testlink_wrk); - smc_wr_wakeup_reg_wait(link); - smc_wr_wakeup_tx_wait(link); } /* register a new rtoken at the remote peer (for all links) */ diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index 289025cd54..c79361dfcd 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -496,7 +496,7 @@ static int smc_tx_rdma_writes(struct smc_connection *conn, /* Wakeup sndbuf consumers from any context (IRQ or process) * since there is more data to transmit; usable snd_wnd as max transmit */ -static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn) +static int _smcr_tx_sndbuf_nonempty(struct smc_connection *conn) { struct smc_cdc_producer_flags *pflags = &conn->local_tx_ctrl.prod_flags; struct smc_link *link = conn->lnk; @@ -550,6 +550,22 @@ static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn) return rc; } +static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn) +{ + struct smc_link *link = conn->lnk; + int rc = -ENOLINK; + + if (!link) + return rc; + + atomic_inc(&link->wr_tx_refcnt); + if (smc_link_usable(link)) + rc = _smcr_tx_sndbuf_nonempty(conn); + if (atomic_dec_and_test(&link->wr_tx_refcnt)) + wake_up_all(&link->wr_tx_wait); + return rc; +} + static int smcd_tx_sndbuf_nonempty(struct smc_connection *conn) { struct smc_cdc_producer_flags *pflags = &conn->local_tx_ctrl.prod_flags; diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index cbc73a7e4d..a419e9af36 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -322,9 +322,12 @@ int smc_wr_reg_send(struct smc_link *link, struct ib_mr *mr) if (rc) return rc; + atomic_inc(&link->wr_reg_refcnt); rc = wait_event_interruptible_timeout(link->wr_reg_wait, (link->wr_reg_state != POSTED), SMC_WR_REG_MR_WAIT_TIME); + if (atomic_dec_and_test(&link->wr_reg_refcnt)) + wake_up_all(&link->wr_reg_wait); if (!rc) { /* timeout - terminate link */ smcr_link_down_cond_sched(link); @@ -566,10 +569,15 @@ void smc_wr_free_link(struct smc_link *lnk) return; ibdev = lnk->smcibdev->ibdev; + smc_wr_wakeup_reg_wait(lnk); + smc_wr_wakeup_tx_wait(lnk); + if (smc_wr_tx_wait_no_pending_sends(lnk)) memset(lnk->wr_tx_mask, 0, BITS_TO_LONGS(SMC_WR_BUF_CNT) * sizeof(*lnk->wr_tx_mask)); + wait_event(lnk->wr_reg_wait, (!atomic_read(&lnk->wr_reg_refcnt))); + wait_event(lnk->wr_tx_wait, (!atomic_read(&lnk->wr_tx_refcnt))); if (lnk->wr_rx_dma_addr) { ib_dma_unmap_single(ibdev, lnk->wr_rx_dma_addr, @@ -728,7 +736,9 @@ int smc_wr_create_link(struct smc_link *lnk) memset(lnk->wr_tx_mask, 0, BITS_TO_LONGS(SMC_WR_BUF_CNT) * sizeof(*lnk->wr_tx_mask)); init_waitqueue_head(&lnk->wr_tx_wait); + atomic_set(&lnk->wr_tx_refcnt, 0); init_waitqueue_head(&lnk->wr_reg_wait); + atomic_set(&lnk->wr_reg_refcnt, 0); return rc; dma_unmap: diff --git a/net/tipc/link.c b/net/tipc/link.c index cf586840ca..1b7a487c88 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -913,7 +913,7 @@ static int link_schedule_user(struct tipc_link *l, struct tipc_msg *hdr) skb = tipc_msg_create(SOCK_WAKEUP, 0, INT_H_SIZE, 0, dnode, l->addr, dport, 0, 0); if (!skb) - return -ENOMEM; + return -ENOBUFS; msg_set_dest_droppable(buf_msg(skb), true); TIPC_SKB_CB(skb)->chain_imp = msg_importance(hdr); skb_queue_tail(&l->wakeupq, skb); @@ -1031,7 +1031,7 @@ void tipc_link_reset(struct tipc_link *l) * * Consumes the buffer chain. * Messages at TIPC_SYSTEM_IMPORTANCE are always accepted - * Return: 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS or -ENOMEM + * Return: 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS */ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, struct sk_buff_head *xmitq) @@ -1089,7 +1089,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, if (!_skb) { kfree_skb(skb); __skb_queue_purge(list); - return -ENOMEM; + return -ENOBUFS; } __skb_queue_tail(transmq, skb); tipc_link_set_skb_retransmit_time(skb, l); diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index e0c2c992ad..4f7c99dfd1 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -357,11 +357,14 @@ static void virtio_vsock_event_fill(struct virtio_vsock *vsock) static void virtio_vsock_reset_sock(struct sock *sk) { - lock_sock(sk); + /* vmci_transport.c doesn't take sk_lock here either. At least we're + * under vsock_table_lock so the sock cannot disappear while we're + * executing. + */ + sk->sk_state = TCP_CLOSE; sk->sk_err = ECONNRESET; sk_error_report(sk); - release_sock(sk); } static void virtio_vsock_update_guest_cid(struct virtio_vsock *vsock) diff --git a/security/security.c b/security/security.c index 09533cbb72..9ffa9e9c5c 100644 --- a/security/security.c +++ b/security/security.c @@ -58,10 +58,11 @@ const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX+1] = { [LOCKDOWN_MMIOTRACE] = "unsafe mmio", [LOCKDOWN_DEBUGFS] = "debugfs access", [LOCKDOWN_XMON_WR] = "xmon write access", + [LOCKDOWN_BPF_WRITE_USER] = "use of bpf to write user RAM", [LOCKDOWN_INTEGRITY_MAX] = "integrity", [LOCKDOWN_KCORE] = "/proc/kcore access", [LOCKDOWN_KPROBES] = "use of kprobes", - [LOCKDOWN_BPF_READ] = "use of bpf to read kernel RAM", + [LOCKDOWN_BPF_READ_KERNEL] = "use of bpf to read kernel RAM", [LOCKDOWN_PERF] = "unsafe use of perf", [LOCKDOWN_TRACEFS] = "use of tracefs", [LOCKDOWN_XMON_RW] = "xmon read and write access", diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 09c0e2a648..71323d807d 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -251,7 +251,10 @@ static bool hw_support_mmap(struct snd_pcm_substream *substream) switch (substream->dma_buffer.dev.type) { case SNDRV_DMA_TYPE_UNKNOWN: - return false; + /* we can't know the device, so just assume that the driver does + * everything right + */ + return true; case SNDRV_DMA_TYPE_CONTINUOUS: case SNDRV_DMA_TYPE_VMALLOC: return true; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 21c521596c..a065260d0d 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -8431,6 +8431,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x87f4, "HP", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x87f5, "HP", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x87f7, "HP Spectre x360 14", ALC245_FIXUP_HP_X360_AMP), + SND_PCI_QUIRK(0x103c, 0x8805, "HP ProBook 650 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x880d, "HP EliteBook 830 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8846, "HP EliteBook 850 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8847, "HP EliteBook x360 830 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_LED), @@ -8465,6 +8466,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x16e3, "ASUS UX50", ALC269_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x1043, 0x1740, "ASUS UX430UA", ALC295_FIXUP_ASUS_DACS), SND_PCI_QUIRK(0x1043, 0x17d1, "ASUS UX431FL", ALC294_FIXUP_ASUS_DUAL_SPK), + SND_PCI_QUIRK(0x1043, 0x1662, "ASUS GV301QH", ALC294_FIXUP_ASUS_DUAL_SPK), SND_PCI_QUIRK(0x1043, 0x1881, "ASUS Zephyrus S/M", ALC294_FIXUP_ASUS_GX502_PINS), SND_PCI_QUIRK(0x1043, 0x18b1, "Asus MJ401TA", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x18f1, "Asus FX505DT", ALC256_FIXUP_ASUS_HEADSET_MIC), diff --git a/sound/soc/Kconfig b/sound/soc/Kconfig index 8a13462e1a..5dcf77af07 100644 --- a/sound/soc/Kconfig +++ b/sound/soc/Kconfig @@ -36,6 +36,7 @@ config SND_SOC_COMPRESS config SND_SOC_TOPOLOGY bool + select SND_DYNAMIC_MINORS config SND_SOC_TOPOLOGY_KUNIT_TEST tristate "KUnit tests for SoC topology" diff --git a/sound/soc/amd/acp-da7219-max98357a.c b/sound/soc/amd/acp-da7219-max98357a.c index 9449fb40a9..3c60c5f96d 100644 --- a/sound/soc/amd/acp-da7219-max98357a.c +++ b/sound/soc/amd/acp-da7219-max98357a.c @@ -525,6 +525,7 @@ static struct snd_soc_dai_link cz_dai_7219_98357[] = { | SND_SOC_DAIFMT_CBM_CFM, .init = cz_da7219_init, .dpcm_playback = 1, + .stop_dma_first = 1, .ops = &cz_da7219_play_ops, SND_SOC_DAILINK_REG(designware1, dlgs, platform), }, @@ -534,6 +535,7 @@ static struct snd_soc_dai_link cz_dai_7219_98357[] = { .dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF | SND_SOC_DAIFMT_CBM_CFM, .dpcm_capture = 1, + .stop_dma_first = 1, .ops = &cz_da7219_cap_ops, SND_SOC_DAILINK_REG(designware2, dlgs, platform), }, @@ -543,6 +545,7 @@ static struct snd_soc_dai_link cz_dai_7219_98357[] = { .dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF | SND_SOC_DAIFMT_CBM_CFM, .dpcm_playback = 1, + .stop_dma_first = 1, .ops = &cz_max_play_ops, SND_SOC_DAILINK_REG(designware3, mx, platform), }, @@ -553,6 +556,7 @@ static struct snd_soc_dai_link cz_dai_7219_98357[] = { .dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF | SND_SOC_DAIFMT_CBM_CFM, .dpcm_capture = 1, + .stop_dma_first = 1, .ops = &cz_dmic0_cap_ops, SND_SOC_DAILINK_REG(designware3, adau, platform), }, @@ -563,6 +567,7 @@ static struct snd_soc_dai_link cz_dai_7219_98357[] = { .dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF | SND_SOC_DAIFMT_CBM_CFM, .dpcm_capture = 1, + .stop_dma_first = 1, .ops = &cz_dmic1_cap_ops, SND_SOC_DAILINK_REG(designware2, adau, platform), }, diff --git a/sound/soc/amd/acp-pcm-dma.c b/sound/soc/amd/acp-pcm-dma.c index 143155a840..cc1ce6f22c 100644 --- a/sound/soc/amd/acp-pcm-dma.c +++ b/sound/soc/amd/acp-pcm-dma.c @@ -969,7 +969,7 @@ static int acp_dma_hw_params(struct snd_soc_component *component, acp_set_sram_bank_state(rtd->acp_mmio, 0, true); /* Save for runtime private data */ - rtd->dma_addr = substream->dma_buffer.addr; + rtd->dma_addr = runtime->dma_addr; rtd->order = get_order(size); /* Fill the page table entries in ACP SRAM */ diff --git a/sound/soc/amd/raven/acp3x-pcm-dma.c b/sound/soc/amd/raven/acp3x-pcm-dma.c index 8148b0d22e..597d7c4b2a 100644 --- a/sound/soc/amd/raven/acp3x-pcm-dma.c +++ b/sound/soc/amd/raven/acp3x-pcm-dma.c @@ -286,7 +286,7 @@ static int acp3x_dma_hw_params(struct snd_soc_component *component, pr_err("pinfo failed\n"); } size = params_buffer_bytes(params); - rtd->dma_addr = substream->dma_buffer.addr; + rtd->dma_addr = substream->runtime->dma_addr; rtd->num_pages = (PAGE_ALIGN(size) >> PAGE_SHIFT); config_acp3x_dma(rtd, substream->stream); return 0; diff --git a/sound/soc/amd/renoir/acp3x-pdm-dma.c b/sound/soc/amd/renoir/acp3x-pdm-dma.c index bd20622b09..0391c28dd0 100644 --- a/sound/soc/amd/renoir/acp3x-pdm-dma.c +++ b/sound/soc/amd/renoir/acp3x-pdm-dma.c @@ -242,7 +242,7 @@ static int acp_pdm_dma_hw_params(struct snd_soc_component *component, return -EINVAL; size = params_buffer_bytes(params); period_bytes = params_period_bytes(params); - rtd->dma_addr = substream->dma_buffer.addr; + rtd->dma_addr = substream->runtime->dma_addr; rtd->num_pages = (PAGE_ALIGN(size) >> PAGE_SHIFT); config_acp_dma(rtd, substream->stream); init_pdm_ring_buffer(MEM_WINDOW_START, size, period_bytes, diff --git a/sound/soc/amd/renoir/rn-pci-acp3x.c b/sound/soc/amd/renoir/rn-pci-acp3x.c index 19438da5df..7b8040e812 100644 --- a/sound/soc/amd/renoir/rn-pci-acp3x.c +++ b/sound/soc/amd/renoir/rn-pci-acp3x.c @@ -382,6 +382,8 @@ static const struct dev_pm_ops rn_acp_pm = { .runtime_resume = snd_rn_acp_resume, .suspend = snd_rn_acp_suspend, .resume = snd_rn_acp_resume, + .restore = snd_rn_acp_resume, + .poweroff = snd_rn_acp_suspend, }; static void snd_rn_acp_remove(struct pci_dev *pci) diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig index 28932ab6ca..57930dc916 100644 --- a/sound/soc/codecs/Kconfig +++ b/sound/soc/codecs/Kconfig @@ -1577,6 +1577,7 @@ config SND_SOC_WCD934X config SND_SOC_WCD938X depends on SND_SOC_WCD938X_SDW tristate + depends on SOUNDWIRE || !SOUNDWIRE config SND_SOC_WCD938X_SDW tristate "WCD9380/WCD9385 Codec - SDW" diff --git a/sound/soc/codecs/Makefile b/sound/soc/codecs/Makefile index 0eaf868754..4239280cac 100644 --- a/sound/soc/codecs/Makefile +++ b/sound/soc/codecs/Makefile @@ -591,7 +591,10 @@ obj-$(CONFIG_SND_SOC_WCD_MBHC) += snd-soc-wcd-mbhc.o obj-$(CONFIG_SND_SOC_WCD9335) += snd-soc-wcd9335.o obj-$(CONFIG_SND_SOC_WCD934X) += snd-soc-wcd934x.o obj-$(CONFIG_SND_SOC_WCD938X) += snd-soc-wcd938x.o -obj-$(CONFIG_SND_SOC_WCD938X_SDW) += snd-soc-wcd938x-sdw.o +ifdef CONFIG_SND_SOC_WCD938X_SDW +# avoid link failure by forcing sdw code built-in when needed +obj-$(CONFIG_SND_SOC_WCD938X) += snd-soc-wcd938x-sdw.o +endif obj-$(CONFIG_SND_SOC_WL1273) += snd-soc-wl1273.o obj-$(CONFIG_SND_SOC_WM0010) += snd-soc-wm0010.o obj-$(CONFIG_SND_SOC_WM1250_EV1) += snd-soc-wm1250-ev1.o diff --git a/sound/soc/codecs/cs42l42.c b/sound/soc/codecs/cs42l42.c index eff013f295..99c022be94 100644 --- a/sound/soc/codecs/cs42l42.c +++ b/sound/soc/codecs/cs42l42.c @@ -405,7 +405,7 @@ static const struct regmap_config cs42l42_regmap = { .use_single_write = true, }; -static DECLARE_TLV_DB_SCALE(adc_tlv, -9600, 100, false); +static DECLARE_TLV_DB_SCALE(adc_tlv, -9700, 100, true); static DECLARE_TLV_DB_SCALE(mixer_tlv, -6300, 100, true); static const char * const cs42l42_hpf_freq_text[] = { @@ -425,34 +425,23 @@ static SOC_ENUM_SINGLE_DECL(cs42l42_wnf3_freq_enum, CS42L42_ADC_WNF_HPF_CTL, CS42L42_ADC_WNF_CF_SHIFT, cs42l42_wnf3_freq_text); -static const char * const cs42l42_wnf05_freq_text[] = { - "280Hz", "315Hz", "350Hz", "385Hz", - "420Hz", "455Hz", "490Hz", "525Hz" -}; - -static SOC_ENUM_SINGLE_DECL(cs42l42_wnf05_freq_enum, CS42L42_ADC_WNF_HPF_CTL, - CS42L42_ADC_WNF_CF_SHIFT, - cs42l42_wnf05_freq_text); - static const struct snd_kcontrol_new cs42l42_snd_controls[] = { /* ADC Volume and Filter Controls */ SOC_SINGLE("ADC Notch Switch", CS42L42_ADC_CTL, - CS42L42_ADC_NOTCH_DIS_SHIFT, true, false), + CS42L42_ADC_NOTCH_DIS_SHIFT, true, true), SOC_SINGLE("ADC Weak Force Switch", CS42L42_ADC_CTL, CS42L42_ADC_FORCE_WEAK_VCM_SHIFT, true, false), SOC_SINGLE("ADC Invert Switch", CS42L42_ADC_CTL, CS42L42_ADC_INV_SHIFT, true, false), SOC_SINGLE("ADC Boost Switch", CS42L42_ADC_CTL, CS42L42_ADC_DIG_BOOST_SHIFT, true, false), - SOC_SINGLE_SX_TLV("ADC Volume", CS42L42_ADC_VOLUME, - CS42L42_ADC_VOL_SHIFT, 0xA0, 0x6C, adc_tlv), + SOC_SINGLE_S8_TLV("ADC Volume", CS42L42_ADC_VOLUME, -97, 12, adc_tlv), SOC_SINGLE("ADC WNF Switch", CS42L42_ADC_WNF_HPF_CTL, CS42L42_ADC_WNF_EN_SHIFT, true, false), SOC_SINGLE("ADC HPF Switch", CS42L42_ADC_WNF_HPF_CTL, CS42L42_ADC_HPF_EN_SHIFT, true, false), SOC_ENUM("HPF Corner Freq", cs42l42_hpf_freq_enum), SOC_ENUM("WNF 3dB Freq", cs42l42_wnf3_freq_enum), - SOC_ENUM("WNF 05dB Freq", cs42l42_wnf05_freq_enum), /* DAC Volume and Filter Controls */ SOC_SINGLE("DACA Invert Switch", CS42L42_DAC_CTL1, @@ -471,8 +460,8 @@ static const struct snd_soc_dapm_widget cs42l42_dapm_widgets[] = { SND_SOC_DAPM_OUTPUT("HP"), SND_SOC_DAPM_DAC("DAC", NULL, CS42L42_PWR_CTL1, CS42L42_HP_PDN_SHIFT, 1), SND_SOC_DAPM_MIXER("MIXER", CS42L42_PWR_CTL1, CS42L42_MIXER_PDN_SHIFT, 1, NULL, 0), - SND_SOC_DAPM_AIF_IN("SDIN1", NULL, 0, CS42L42_ASP_RX_DAI0_EN, CS42L42_ASP_RX0_CH1_SHIFT, 0), - SND_SOC_DAPM_AIF_IN("SDIN2", NULL, 1, CS42L42_ASP_RX_DAI0_EN, CS42L42_ASP_RX0_CH2_SHIFT, 0), + SND_SOC_DAPM_AIF_IN("SDIN1", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_IN("SDIN2", NULL, 1, SND_SOC_NOPM, 0, 0), /* Playback Requirements */ SND_SOC_DAPM_SUPPLY("ASP DAI0", CS42L42_PWR_CTL1, CS42L42_ASP_DAI_PDN_SHIFT, 1, NULL, 0), @@ -630,6 +619,8 @@ static int cs42l42_pll_config(struct snd_soc_component *component) for (i = 0; i < ARRAY_SIZE(pll_ratio_table); i++) { if (pll_ratio_table[i].sclk == clk) { + cs42l42->pll_config = i; + /* Configure the internal sample rate */ snd_soc_component_update_bits(component, CS42L42_MCLK_CTL, CS42L42_INTERNAL_FS_MASK, @@ -638,14 +629,9 @@ static int cs42l42_pll_config(struct snd_soc_component *component) (pll_ratio_table[i].mclk_int != 24000000)) << CS42L42_INTERNAL_FS_SHIFT); - /* Set the MCLK src (PLL or SCLK) and the divide - * ratio - */ + snd_soc_component_update_bits(component, CS42L42_MCLK_SRC_SEL, - CS42L42_MCLK_SRC_SEL_MASK | CS42L42_MCLKDIV_MASK, - (pll_ratio_table[i].mclk_src_sel - << CS42L42_MCLK_SRC_SEL_SHIFT) | (pll_ratio_table[i].mclk_div << CS42L42_MCLKDIV_SHIFT)); /* Set up the LRCLK */ @@ -681,15 +667,6 @@ static int cs42l42_pll_config(struct snd_soc_component *component) CS42L42_FSYNC_PULSE_WIDTH_MASK, CS42L42_FRAC1_VAL(fsync - 1) << CS42L42_FSYNC_PULSE_WIDTH_SHIFT); - snd_soc_component_update_bits(component, - CS42L42_ASP_FRM_CFG, - CS42L42_ASP_5050_MASK, - CS42L42_ASP_5050_MASK); - /* Set the frame delay to 1.0 SCLK clocks */ - snd_soc_component_update_bits(component, CS42L42_ASP_FRM_CFG, - CS42L42_ASP_FSD_MASK, - CS42L42_ASP_FSD_1_0 << - CS42L42_ASP_FSD_SHIFT); /* Set the sample rates (96k or lower) */ snd_soc_component_update_bits(component, CS42L42_FS_RATE_EN, CS42L42_FS_EN_MASK, @@ -789,7 +766,18 @@ static int cs42l42_set_dai_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt) /* interface format */ switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) { case SND_SOC_DAIFMT_I2S: - case SND_SOC_DAIFMT_LEFT_J: + /* + * 5050 mode, frame starts on falling edge of LRCLK, + * frame delayed by 1.0 SCLKs + */ + snd_soc_component_update_bits(component, + CS42L42_ASP_FRM_CFG, + CS42L42_ASP_STP_MASK | + CS42L42_ASP_5050_MASK | + CS42L42_ASP_FSD_MASK, + CS42L42_ASP_5050_MASK | + (CS42L42_ASP_FSD_1_0 << + CS42L42_ASP_FSD_SHIFT)); break; default: return -EINVAL; @@ -819,6 +807,25 @@ static int cs42l42_set_dai_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt) return 0; } +static int cs42l42_dai_startup(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) +{ + struct snd_soc_component *component = dai->component; + struct cs42l42_private *cs42l42 = snd_soc_component_get_drvdata(component); + + /* + * Sample rates < 44.1 kHz would produce an out-of-range SCLK with + * a standard I2S frame. If the machine driver sets SCLK it must be + * legal. + */ + if (cs42l42->sclk) + return 0; + + /* Machine driver has not set a SCLK, limit bottom end to 44.1 kHz */ + return snd_pcm_hw_constraint_minmax(substream->runtime, + SNDRV_PCM_HW_PARAM_RATE, + 44100, 192000); +} + static int cs42l42_pcm_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params, struct snd_soc_dai *dai) @@ -832,6 +839,10 @@ static int cs42l42_pcm_hw_params(struct snd_pcm_substream *substream, cs42l42->srate = params_rate(params); cs42l42->bclk = snd_soc_params_to_bclk(params); + /* I2S frame always has 2 channels even for mono audio */ + if (channels == 1) + cs42l42->bclk *= 2; + switch(substream->stream) { case SNDRV_PCM_STREAM_CAPTURE: if (channels == 2) { @@ -855,6 +866,17 @@ static int cs42l42_pcm_hw_params(struct snd_pcm_substream *substream, snd_soc_component_update_bits(component, CS42L42_ASP_RX_DAI0_CH2_AP_RES, CS42L42_ASP_RX_CH_AP_MASK | CS42L42_ASP_RX_CH_RES_MASK, val); + + /* Channel B comes from the last active channel */ + snd_soc_component_update_bits(component, CS42L42_SP_RX_CH_SEL, + CS42L42_SP_RX_CHB_SEL_MASK, + (channels - 1) << CS42L42_SP_RX_CHB_SEL_SHIFT); + + /* Both LRCLK slots must be enabled */ + snd_soc_component_update_bits(component, CS42L42_ASP_RX_DAI0_EN, + CS42L42_ASP_RX0_CH_EN_MASK, + BIT(CS42L42_ASP_RX0_CH1_SHIFT) | + BIT(CS42L42_ASP_RX0_CH2_SHIFT)); break; default: break; @@ -900,13 +922,21 @@ static int cs42l42_mute_stream(struct snd_soc_dai *dai, int mute, int stream) */ regmap_multi_reg_write(cs42l42->regmap, cs42l42_to_osc_seq, ARRAY_SIZE(cs42l42_to_osc_seq)); + + /* Must disconnect PLL before stopping it */ + snd_soc_component_update_bits(component, + CS42L42_MCLK_SRC_SEL, + CS42L42_MCLK_SRC_SEL_MASK, + 0); + usleep_range(100, 200); + snd_soc_component_update_bits(component, CS42L42_PLL_CTL1, CS42L42_PLL_START_MASK, 0); } } else { if (!cs42l42->stream_use) { /* SCLK must be running before codec unmute */ - if ((cs42l42->bclk < 11289600) && (cs42l42->sclk < 11289600)) { + if (pll_ratio_table[cs42l42->pll_config].mclk_src_sel) { snd_soc_component_update_bits(component, CS42L42_PLL_CTL1, CS42L42_PLL_START_MASK, 1); @@ -927,6 +957,12 @@ static int cs42l42_mute_stream(struct snd_soc_dai *dai, int mute, int stream) CS42L42_PLL_LOCK_TIMEOUT_US); if (ret < 0) dev_warn(component->dev, "PLL failed to lock: %d\n", ret); + + /* PLL must be running to drive glitchless switch logic */ + snd_soc_component_update_bits(component, + CS42L42_MCLK_SRC_SEL, + CS42L42_MCLK_SRC_SEL_MASK, + CS42L42_MCLK_SRC_SEL_MASK); } /* Mark SCLK as present, turn off internal oscillator */ @@ -960,8 +996,8 @@ static int cs42l42_mute_stream(struct snd_soc_dai *dai, int mute, int stream) SNDRV_PCM_FMTBIT_S24_LE |\ SNDRV_PCM_FMTBIT_S32_LE ) - static const struct snd_soc_dai_ops cs42l42_ops = { + .startup = cs42l42_dai_startup, .hw_params = cs42l42_pcm_hw_params, .set_fmt = cs42l42_set_dai_fmt, .set_sysclk = cs42l42_set_sysclk, diff --git a/sound/soc/codecs/cs42l42.h b/sound/soc/codecs/cs42l42.h index 206b3c81d3..8734f6828f 100644 --- a/sound/soc/codecs/cs42l42.h +++ b/sound/soc/codecs/cs42l42.h @@ -653,6 +653,8 @@ /* Page 0x25 Audio Port Registers */ #define CS42L42_SP_RX_CH_SEL (CS42L42_PAGE_25 + 0x01) +#define CS42L42_SP_RX_CHB_SEL_SHIFT 2 +#define CS42L42_SP_RX_CHB_SEL_MASK (3 << CS42L42_SP_RX_CHB_SEL_SHIFT) #define CS42L42_SP_RX_ISOC_CTL (CS42L42_PAGE_25 + 0x02) #define CS42L42_SP_RX_RSYNC_SHIFT 6 @@ -775,6 +777,7 @@ struct cs42l42_private { struct gpio_desc *reset_gpio; struct completion pdn_done; struct snd_soc_jack *jack; + int pll_config; int bclk; u32 sclk; u32 srate; diff --git a/sound/soc/codecs/nau8824.c b/sound/soc/codecs/nau8824.c index 15bd8335f6..db88be48c9 100644 --- a/sound/soc/codecs/nau8824.c +++ b/sound/soc/codecs/nau8824.c @@ -828,36 +828,6 @@ static void nau8824_int_status_clear_all(struct regmap *regmap) } } -static void nau8824_dapm_disable_pin(struct nau8824 *nau8824, const char *pin) -{ - struct snd_soc_dapm_context *dapm = nau8824->dapm; - const char *prefix = dapm->component->name_prefix; - char prefixed_pin[80]; - - if (prefix) { - snprintf(prefixed_pin, sizeof(prefixed_pin), "%s %s", - prefix, pin); - snd_soc_dapm_disable_pin(dapm, prefixed_pin); - } else { - snd_soc_dapm_disable_pin(dapm, pin); - } -} - -static void nau8824_dapm_enable_pin(struct nau8824 *nau8824, const char *pin) -{ - struct snd_soc_dapm_context *dapm = nau8824->dapm; - const char *prefix = dapm->component->name_prefix; - char prefixed_pin[80]; - - if (prefix) { - snprintf(prefixed_pin, sizeof(prefixed_pin), "%s %s", - prefix, pin); - snd_soc_dapm_force_enable_pin(dapm, prefixed_pin); - } else { - snd_soc_dapm_force_enable_pin(dapm, pin); - } -} - static void nau8824_eject_jack(struct nau8824 *nau8824) { struct snd_soc_dapm_context *dapm = nau8824->dapm; @@ -866,8 +836,8 @@ static void nau8824_eject_jack(struct nau8824 *nau8824) /* Clear all interruption status */ nau8824_int_status_clear_all(regmap); - nau8824_dapm_disable_pin(nau8824, "SAR"); - nau8824_dapm_disable_pin(nau8824, "MICBIAS"); + snd_soc_dapm_disable_pin(dapm, "SAR"); + snd_soc_dapm_disable_pin(dapm, "MICBIAS"); snd_soc_dapm_sync(dapm); /* Enable the insertion interruption, disable the ejection @@ -897,8 +867,8 @@ static void nau8824_jdet_work(struct work_struct *work) struct regmap *regmap = nau8824->regmap; int adc_value, event = 0, event_mask = 0; - nau8824_dapm_enable_pin(nau8824, "MICBIAS"); - nau8824_dapm_enable_pin(nau8824, "SAR"); + snd_soc_dapm_enable_pin(dapm, "MICBIAS"); + snd_soc_dapm_enable_pin(dapm, "SAR"); snd_soc_dapm_sync(dapm); msleep(100); @@ -909,8 +879,8 @@ static void nau8824_jdet_work(struct work_struct *work) if (adc_value < HEADSET_SARADC_THD) { event |= SND_JACK_HEADPHONE; - nau8824_dapm_disable_pin(nau8824, "SAR"); - nau8824_dapm_disable_pin(nau8824, "MICBIAS"); + snd_soc_dapm_disable_pin(dapm, "SAR"); + snd_soc_dapm_disable_pin(dapm, "MICBIAS"); snd_soc_dapm_sync(dapm); } else { event |= SND_JACK_HEADSET; diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c index abcd6f4837..51ecaa2abc 100644 --- a/sound/soc/codecs/rt5682.c +++ b/sound/soc/codecs/rt5682.c @@ -44,6 +44,7 @@ static const struct reg_sequence patch_list[] = { {RT5682_I2C_CTRL, 0x000f}, {RT5682_PLL2_INTERNAL, 0x8266}, {RT5682_SAR_IL_CMD_3, 0x8365}, + {RT5682_SAR_IL_CMD_6, 0x0180}, }; void rt5682_apply_patch_list(struct rt5682_priv *rt5682, struct device *dev) diff --git a/sound/soc/codecs/tlv320aic31xx.c b/sound/soc/codecs/tlv320aic31xx.c index b504d63385..52d2c968b5 100644 --- a/sound/soc/codecs/tlv320aic31xx.c +++ b/sound/soc/codecs/tlv320aic31xx.c @@ -35,6 +35,9 @@ #include "tlv320aic31xx.h" +static int aic31xx_set_jack(struct snd_soc_component *component, + struct snd_soc_jack *jack, void *data); + static const struct reg_default aic31xx_reg_defaults[] = { { AIC31XX_CLKMUX, 0x00 }, { AIC31XX_PLLPR, 0x11 }, @@ -1256,6 +1259,13 @@ static int aic31xx_power_on(struct snd_soc_component *component) return ret; } + /* + * The jack detection configuration is in the same register + * that is used to report jack detect status so is volatile + * and not covered by the cache sync, restore it separately. + */ + aic31xx_set_jack(component, aic31xx->jack, NULL); + return 0; } diff --git a/sound/soc/codecs/tlv320aic32x4.c b/sound/soc/codecs/tlv320aic32x4.c index dcd8aeb45c..2e9175b37d 100644 --- a/sound/soc/codecs/tlv320aic32x4.c +++ b/sound/soc/codecs/tlv320aic32x4.c @@ -682,11 +682,20 @@ static int aic32x4_set_dosr(struct snd_soc_component *component, u16 dosr) static int aic32x4_set_processing_blocks(struct snd_soc_component *component, u8 r_block, u8 p_block) { - if (r_block > 18 || p_block > 25) - return -EINVAL; + struct aic32x4_priv *aic32x4 = snd_soc_component_get_drvdata(component); - snd_soc_component_write(component, AIC32X4_ADCSPB, r_block); - snd_soc_component_write(component, AIC32X4_DACSPB, p_block); + if (aic32x4->type == AIC32X4_TYPE_TAS2505) { + if (r_block || p_block > 3) + return -EINVAL; + + snd_soc_component_write(component, AIC32X4_DACSPB, p_block); + } else { /* AIC32x4 */ + if (r_block > 18 || p_block > 25) + return -EINVAL; + + snd_soc_component_write(component, AIC32X4_ADCSPB, r_block); + snd_soc_component_write(component, AIC32X4_DACSPB, p_block); + } return 0; } @@ -695,6 +704,7 @@ static int aic32x4_setup_clocks(struct snd_soc_component *component, unsigned int sample_rate, unsigned int channels, unsigned int bit_depth) { + struct aic32x4_priv *aic32x4 = snd_soc_component_get_drvdata(component); u8 aosr; u16 dosr; u8 adc_resource_class, dac_resource_class; @@ -721,19 +731,28 @@ static int aic32x4_setup_clocks(struct snd_soc_component *component, adc_resource_class = 6; dac_resource_class = 8; dosr_increment = 8; - aic32x4_set_processing_blocks(component, 1, 1); + if (aic32x4->type == AIC32X4_TYPE_TAS2505) + aic32x4_set_processing_blocks(component, 0, 1); + else + aic32x4_set_processing_blocks(component, 1, 1); } else if (sample_rate <= 96000) { aosr = 64; adc_resource_class = 6; dac_resource_class = 8; dosr_increment = 4; - aic32x4_set_processing_blocks(component, 1, 9); + if (aic32x4->type == AIC32X4_TYPE_TAS2505) + aic32x4_set_processing_blocks(component, 0, 1); + else + aic32x4_set_processing_blocks(component, 1, 9); } else if (sample_rate == 192000) { aosr = 32; adc_resource_class = 3; dac_resource_class = 4; dosr_increment = 2; - aic32x4_set_processing_blocks(component, 13, 19); + if (aic32x4->type == AIC32X4_TYPE_TAS2505) + aic32x4_set_processing_blocks(component, 0, 1); + else + aic32x4_set_processing_blocks(component, 13, 19); } else { dev_err(component->dev, "Sampling rate not supported\n"); return -EINVAL; diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index 549d98241d..fe15cbc7bc 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -747,7 +747,6 @@ static void wm_adsp2_init_debugfs(struct wm_adsp *dsp, static void wm_adsp2_cleanup_debugfs(struct wm_adsp *dsp) { wm_adsp_debugfs_clear(dsp); - debugfs_remove_recursive(dsp->debugfs_root); } #else static inline void wm_adsp2_init_debugfs(struct wm_adsp *dsp, diff --git a/sound/soc/intel/atom/sst-mfld-platform-pcm.c b/sound/soc/intel/atom/sst-mfld-platform-pcm.c index 4124aa2fc2..5db2f4865b 100644 --- a/sound/soc/intel/atom/sst-mfld-platform-pcm.c +++ b/sound/soc/intel/atom/sst-mfld-platform-pcm.c @@ -127,7 +127,7 @@ static void sst_fill_alloc_params(struct snd_pcm_substream *substream, snd_pcm_uframes_t period_size; ssize_t periodbytes; ssize_t buffer_bytes = snd_pcm_lib_buffer_bytes(substream); - u32 buffer_addr = virt_to_phys(substream->dma_buffer.area); + u32 buffer_addr = substream->runtime->dma_addr; channels = substream->runtime->channels; period_size = substream->runtime->period_size; @@ -233,7 +233,6 @@ static int sst_platform_alloc_stream(struct snd_pcm_substream *substream, /* set codec params and inform SST driver the same */ sst_fill_pcm_params(substream, ¶m); sst_fill_alloc_params(substream, &alloc_params); - substream->runtime->dma_area = substream->dma_buffer.area; str_params.sparams = param; str_params.aparams = alloc_params; str_params.codec = SST_CODEC_TYPE_PCM; diff --git a/sound/soc/intel/boards/sof_da7219_max98373.c b/sound/soc/intel/boards/sof_da7219_max98373.c index 896251d742..b7b3b0bf99 100644 --- a/sound/soc/intel/boards/sof_da7219_max98373.c +++ b/sound/soc/intel/boards/sof_da7219_max98373.c @@ -404,7 +404,7 @@ static int audio_probe(struct platform_device *pdev) return -ENOMEM; /* By default dais[0] is configured for max98373 */ - if (!strcmp(pdev->name, "sof_da7219_max98360a")) { + if (!strcmp(pdev->name, "sof_da7219_mx98360a")) { dais[0] = (struct snd_soc_dai_link) { .name = "SSP1-Codec", .id = 0, diff --git a/sound/soc/kirkwood/kirkwood-dma.c b/sound/soc/kirkwood/kirkwood-dma.c index c2a5933bfc..700a18561a 100644 --- a/sound/soc/kirkwood/kirkwood-dma.c +++ b/sound/soc/kirkwood/kirkwood-dma.c @@ -104,8 +104,6 @@ static int kirkwood_dma_open(struct snd_soc_component *component, int err; struct snd_pcm_runtime *runtime = substream->runtime; struct kirkwood_dma_data *priv = kirkwood_priv(substream); - const struct mbus_dram_target_info *dram; - unsigned long addr; snd_soc_set_runtime_hwparams(substream, &kirkwood_dma_snd_hw); @@ -142,20 +140,14 @@ static int kirkwood_dma_open(struct snd_soc_component *component, writel((unsigned int)-1, priv->io + KIRKWOOD_ERR_MASK); } - dram = mv_mbus_dram_info(); - addr = substream->dma_buffer.addr; if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { if (priv->substream_play) return -EBUSY; priv->substream_play = substream; - kirkwood_dma_conf_mbus_windows(priv->io, - KIRKWOOD_PLAYBACK_WIN, addr, dram); } else { if (priv->substream_rec) return -EBUSY; priv->substream_rec = substream; - kirkwood_dma_conf_mbus_windows(priv->io, - KIRKWOOD_RECORD_WIN, addr, dram); } return 0; @@ -182,6 +174,23 @@ static int kirkwood_dma_close(struct snd_soc_component *component, return 0; } +static int kirkwood_dma_hw_params(struct snd_soc_component *component, + struct snd_pcm_substream *substream, + struct snd_pcm_hw_params *params) +{ + struct kirkwood_dma_data *priv = kirkwood_priv(substream); + const struct mbus_dram_target_info *dram = mv_mbus_dram_info(); + unsigned long addr = substream->runtime->dma_addr; + + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) + kirkwood_dma_conf_mbus_windows(priv->io, + KIRKWOOD_PLAYBACK_WIN, addr, dram); + else + kirkwood_dma_conf_mbus_windows(priv->io, + KIRKWOOD_RECORD_WIN, addr, dram); + return 0; +} + static int kirkwood_dma_prepare(struct snd_soc_component *component, struct snd_pcm_substream *substream) { @@ -246,6 +255,7 @@ const struct snd_soc_component_driver kirkwood_soc_component = { .name = DRV_NAME, .open = kirkwood_dma_open, .close = kirkwood_dma_close, + .hw_params = kirkwood_dma_hw_params, .prepare = kirkwood_dma_prepare, .pointer = kirkwood_dma_pointer, .pcm_construct = kirkwood_dma_new, diff --git a/sound/soc/soc-component.c b/sound/soc/soc-component.c index 3a5e84e16a..c8dfd0de30 100644 --- a/sound/soc/soc-component.c +++ b/sound/soc/soc-component.c @@ -148,86 +148,75 @@ int snd_soc_component_set_bias_level(struct snd_soc_component *component, return soc_component_ret(component, ret); } -static int soc_component_pin(struct snd_soc_component *component, - const char *pin, - int (*pin_func)(struct snd_soc_dapm_context *dapm, - const char *pin)) -{ - struct snd_soc_dapm_context *dapm = - snd_soc_component_get_dapm(component); - char *full_name; - int ret; - - if (!component->name_prefix) { - ret = pin_func(dapm, pin); - goto end; - } - - full_name = kasprintf(GFP_KERNEL, "%s %s", component->name_prefix, pin); - if (!full_name) { - ret = -ENOMEM; - goto end; - } - - ret = pin_func(dapm, full_name); - kfree(full_name); -end: - return soc_component_ret(component, ret); -} - int snd_soc_component_enable_pin(struct snd_soc_component *component, const char *pin) { - return soc_component_pin(component, pin, snd_soc_dapm_enable_pin); + struct snd_soc_dapm_context *dapm = + snd_soc_component_get_dapm(component); + return snd_soc_dapm_enable_pin(dapm, pin); } EXPORT_SYMBOL_GPL(snd_soc_component_enable_pin); int snd_soc_component_enable_pin_unlocked(struct snd_soc_component *component, const char *pin) { - return soc_component_pin(component, pin, snd_soc_dapm_enable_pin_unlocked); + struct snd_soc_dapm_context *dapm = + snd_soc_component_get_dapm(component); + return snd_soc_dapm_enable_pin_unlocked(dapm, pin); } EXPORT_SYMBOL_GPL(snd_soc_component_enable_pin_unlocked); int snd_soc_component_disable_pin(struct snd_soc_component *component, const char *pin) { - return soc_component_pin(component, pin, snd_soc_dapm_disable_pin); + struct snd_soc_dapm_context *dapm = + snd_soc_component_get_dapm(component); + return snd_soc_dapm_disable_pin(dapm, pin); } EXPORT_SYMBOL_GPL(snd_soc_component_disable_pin); int snd_soc_component_disable_pin_unlocked(struct snd_soc_component *component, const char *pin) { - return soc_component_pin(component, pin, snd_soc_dapm_disable_pin_unlocked); + struct snd_soc_dapm_context *dapm = + snd_soc_component_get_dapm(component); + return snd_soc_dapm_disable_pin_unlocked(dapm, pin); } EXPORT_SYMBOL_GPL(snd_soc_component_disable_pin_unlocked); int snd_soc_component_nc_pin(struct snd_soc_component *component, const char *pin) { - return soc_component_pin(component, pin, snd_soc_dapm_nc_pin); + struct snd_soc_dapm_context *dapm = + snd_soc_component_get_dapm(component); + return snd_soc_dapm_nc_pin(dapm, pin); } EXPORT_SYMBOL_GPL(snd_soc_component_nc_pin); int snd_soc_component_nc_pin_unlocked(struct snd_soc_component *component, const char *pin) { - return soc_component_pin(component, pin, snd_soc_dapm_nc_pin_unlocked); + struct snd_soc_dapm_context *dapm = + snd_soc_component_get_dapm(component); + return snd_soc_dapm_nc_pin_unlocked(dapm, pin); } EXPORT_SYMBOL_GPL(snd_soc_component_nc_pin_unlocked); int snd_soc_component_get_pin_status(struct snd_soc_component *component, const char *pin) { - return soc_component_pin(component, pin, snd_soc_dapm_get_pin_status); + struct snd_soc_dapm_context *dapm = + snd_soc_component_get_dapm(component); + return snd_soc_dapm_get_pin_status(dapm, pin); } EXPORT_SYMBOL_GPL(snd_soc_component_get_pin_status); int snd_soc_component_force_enable_pin(struct snd_soc_component *component, const char *pin) { - return soc_component_pin(component, pin, snd_soc_dapm_force_enable_pin); + struct snd_soc_dapm_context *dapm = + snd_soc_component_get_dapm(component); + return snd_soc_dapm_force_enable_pin(dapm, pin); } EXPORT_SYMBOL_GPL(snd_soc_component_force_enable_pin); @@ -235,7 +224,9 @@ int snd_soc_component_force_enable_pin_unlocked( struct snd_soc_component *component, const char *pin) { - return soc_component_pin(component, pin, snd_soc_dapm_force_enable_pin_unlocked); + struct snd_soc_dapm_context *dapm = + snd_soc_component_get_dapm(component); + return snd_soc_dapm_force_enable_pin_unlocked(dapm, pin); } EXPORT_SYMBOL_GPL(snd_soc_component_force_enable_pin_unlocked); diff --git a/sound/soc/sof/intel/Kconfig b/sound/soc/sof/intel/Kconfig index 4bce89b5ea..4447f515e8 100644 --- a/sound/soc/sof/intel/Kconfig +++ b/sound/soc/sof/intel/Kconfig @@ -278,6 +278,8 @@ config SND_SOC_SOF_HDA config SND_SOC_SOF_INTEL_SOUNDWIRE_LINK_BASELINE tristate + select SOUNDWIRE_INTEL if SND_SOC_SOF_INTEL_SOUNDWIRE + select SND_INTEL_SOUNDWIRE_ACPI if SND_SOC_SOF_INTEL_SOUNDWIRE config SND_SOC_SOF_INTEL_SOUNDWIRE tristate "SOF support for SoundWire" @@ -285,8 +287,6 @@ config SND_SOC_SOF_INTEL_SOUNDWIRE depends on SND_SOC_SOF_INTEL_SOUNDWIRE_LINK_BASELINE depends on ACPI && SOUNDWIRE depends on !(SOUNDWIRE=m && SND_SOC_SOF_INTEL_SOUNDWIRE_LINK_BASELINE=y) - select SOUNDWIRE_INTEL - select SND_INTEL_SOUNDWIRE_ACPI help This adds support for SoundWire with Sound Open Firmware for Intel(R) platforms. diff --git a/sound/soc/sof/intel/hda-ipc.c b/sound/soc/sof/intel/hda-ipc.c index c91aa951df..acfeca4260 100644 --- a/sound/soc/sof/intel/hda-ipc.c +++ b/sound/soc/sof/intel/hda-ipc.c @@ -107,8 +107,8 @@ void hda_dsp_ipc_get_reply(struct snd_sof_dev *sdev) } else { /* reply correct size ? */ if (reply.hdr.size != msg->reply_size && - /* getter payload is never known upfront */ - !(reply.hdr.cmd & SOF_IPC_GLB_PROBE)) { + /* getter payload is never known upfront */ + ((reply.hdr.cmd & SOF_GLB_TYPE_MASK) != SOF_IPC_GLB_PROBE)) { dev_err(sdev->dev, "error: reply expected %zu got %u bytes\n", msg->reply_size, reply.hdr.size); ret = -EINVAL; diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c index e1e368ff2b..891e6e1b91 100644 --- a/sound/soc/sof/intel/hda.c +++ b/sound/soc/sof/intel/hda.c @@ -187,12 +187,16 @@ static int hda_sdw_probe(struct snd_sof_dev *sdev) int hda_sdw_startup(struct snd_sof_dev *sdev) { struct sof_intel_hda_dev *hdev; + struct snd_sof_pdata *pdata = sdev->pdata; hdev = sdev->pdata->hw_pdata; if (!hdev->sdw) return 0; + if (pdata->machine && !pdata->machine->mach_params.link_mask) + return 0; + return sdw_intel_startup(hdev->sdw); } @@ -1002,6 +1006,14 @@ static int hda_generic_machine_select(struct snd_sof_dev *sdev) hda_mach->mach_params.dmic_num = dmic_num; pdata->machine = hda_mach; pdata->tplg_filename = tplg_filename; + + if (codec_num == 2) { + /* + * Prevent SoundWire links from starting when an external + * HDaudio codec is used + */ + hda_mach->mach_params.link_mask = 0; + } } } diff --git a/sound/soc/uniphier/aio-dma.c b/sound/soc/uniphier/aio-dma.c index 3c1628a3a1..3d9736e738 100644 --- a/sound/soc/uniphier/aio-dma.c +++ b/sound/soc/uniphier/aio-dma.c @@ -198,7 +198,7 @@ static int uniphier_aiodma_mmap(struct snd_soc_component *component, vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot); return remap_pfn_range(vma, vma->vm_start, - substream->dma_buffer.addr >> PAGE_SHIFT, + substream->runtime->dma_addr >> PAGE_SHIFT, vma->vm_end - vma->vm_start, vma->vm_page_prot); } diff --git a/sound/soc/xilinx/xlnx_formatter_pcm.c b/sound/soc/xilinx/xlnx_formatter_pcm.c index 1d59fb668c..91afea9d5d 100644 --- a/sound/soc/xilinx/xlnx_formatter_pcm.c +++ b/sound/soc/xilinx/xlnx_formatter_pcm.c @@ -452,8 +452,8 @@ static int xlnx_formatter_pcm_hw_params(struct snd_soc_component *component, stream_data->buffer_size = size; - low = lower_32_bits(substream->dma_buffer.addr); - high = upper_32_bits(substream->dma_buffer.addr); + low = lower_32_bits(runtime->dma_addr); + high = upper_32_bits(runtime->dma_addr); writel(low, stream_data->mmio + XLNX_AUD_BUFF_ADDR_LSB); writel(high, stream_data->mmio + XLNX_AUD_BUFF_ADDR_MSB); diff --git a/tools/io_uring/io_uring-cp.c b/tools/io_uring/io_uring-cp.c index 81461813ec..d9bd6f5f8f 100644 --- a/tools/io_uring/io_uring-cp.c +++ b/tools/io_uring/io_uring-cp.c @@ -131,8 +131,7 @@ static int copy_file(struct io_uring *ring, off_t insize) writes = reads = offset = 0; while (insize || write_left) { - unsigned long had_reads; - int got_comp; + int had_reads, got_comp; /* * Queue up as many reads as we can @@ -174,8 +173,13 @@ static int copy_file(struct io_uring *ring, off_t insize) if (!got_comp) { ret = io_uring_wait_cqe(ring, &cqe); got_comp = 1; - } else + } else { ret = io_uring_peek_cqe(ring, &cqe); + if (ret == -EAGAIN) { + cqe = NULL; + ret = 0; + } + } if (ret < 0) { fprintf(stderr, "io_uring_peek_cqe: %s\n", strerror(-ret)); @@ -194,7 +198,7 @@ static int copy_file(struct io_uring *ring, off_t insize) fprintf(stderr, "cqe failed: %s\n", strerror(-cqe->res)); return 1; - } else if ((size_t) cqe->res != data->iov.iov_len) { + } else if (cqe->res != data->iov.iov_len) { /* Short read/write, adjust and requeue */ data->iov.iov_base += cqe->res; data->iov.iov_len -= cqe->res; @@ -221,6 +225,25 @@ static int copy_file(struct io_uring *ring, off_t insize) } } + /* wait out pending writes */ + while (writes) { + struct io_data *data; + + ret = io_uring_wait_cqe(ring, &cqe); + if (ret) { + fprintf(stderr, "wait_cqe=%d\n", ret); + return 1; + } + if (cqe->res < 0) { + fprintf(stderr, "write res=%d\n", cqe->res); + return 1; + } + data = io_uring_cqe_get_data(cqe); + free(data); + writes--; + io_uring_cqe_seen(ring, cqe); + } + return 0; } diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index b46760b93b..7ff3d5ce44 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -804,6 +804,7 @@ static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf) btf->nr_types = 0; btf->start_id = 1; btf->start_str_off = 0; + btf->fd = -1; if (base_btf) { btf->base_btf = base_btf; @@ -832,8 +833,6 @@ static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf) if (err) goto done; - btf->fd = -1; - done: if (err) { btf__free(btf); diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index ecaae2927a..cd8c703dde 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -75,6 +75,9 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: xattr.expected_attach_type = BPF_CGROUP_INET4_CONNECT; break; + case BPF_PROG_TYPE_CGROUP_SOCKOPT: + xattr.expected_attach_type = BPF_CGROUP_GETSOCKOPT; + break; case BPF_PROG_TYPE_SK_LOOKUP: xattr.expected_attach_type = BPF_SK_LOOKUP; break; @@ -104,7 +107,6 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, case BPF_PROG_TYPE_SK_REUSEPORT: case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_CGROUP_SYSCTL: - case BPF_PROG_TYPE_CGROUP_SOCKOPT: case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_STRUCT_OPS: case BPF_PROG_TYPE_EXT: diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index 54f367cbad..b1bff5fb0f 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -434,7 +434,7 @@ static int nd_intel_test_finish_query(struct nfit_test *t, dev_dbg(dev, "%s: transition out verify\n", __func__); fw->state = FW_STATE_UPDATED; fw->missed_activate = false; - /* fall through */ + fallthrough; case FW_STATE_UPDATED: nd_cmd->status = 0; /* bogus test version */ diff --git a/tools/testing/selftests/sgx/sigstruct.c b/tools/testing/selftests/sgx/sigstruct.c index dee7a3d6c5..92bbc5a15c 100644 --- a/tools/testing/selftests/sgx/sigstruct.c +++ b/tools/testing/selftests/sgx/sigstruct.c @@ -55,10 +55,27 @@ static bool alloc_q1q2_ctx(const uint8_t *s, const uint8_t *m, return true; } +static void reverse_bytes(void *data, int length) +{ + int i = 0; + int j = length - 1; + uint8_t temp; + uint8_t *ptr = data; + + while (i < j) { + temp = ptr[i]; + ptr[i] = ptr[j]; + ptr[j] = temp; + i++; + j--; + } +} + static bool calc_q1q2(const uint8_t *s, const uint8_t *m, uint8_t *q1, uint8_t *q2) { struct q1q2_ctx ctx; + int len; if (!alloc_q1q2_ctx(s, m, &ctx)) { fprintf(stderr, "Not enough memory for Q1Q2 calculation\n"); @@ -89,8 +106,10 @@ static bool calc_q1q2(const uint8_t *s, const uint8_t *m, uint8_t *q1, goto out; } - BN_bn2bin(ctx.q1, q1); - BN_bn2bin(ctx.q2, q2); + len = BN_bn2bin(ctx.q1, q1); + reverse_bytes(q1, len); + len = BN_bn2bin(ctx.q2, q2); + reverse_bytes(q2, len); free_q1q2_ctx(&ctx); return true; @@ -152,22 +171,6 @@ static RSA *gen_sign_key(void) return key; } -static void reverse_bytes(void *data, int length) -{ - int i = 0; - int j = length - 1; - uint8_t temp; - uint8_t *ptr = data; - - while (i < j) { - temp = ptr[i]; - ptr[i] = ptr[j]; - ptr[j] = temp; - i++; - j--; - } -} - enum mrtags { MRECREATE = 0x0045544145524345, MREADD = 0x0000000044444145, @@ -367,8 +370,6 @@ bool encl_measure(struct encl *encl) /* BE -> LE */ reverse_bytes(sigstruct->signature, SGX_MODULUS_SIZE); reverse_bytes(sigstruct->modulus, SGX_MODULUS_SIZE); - reverse_bytes(sigstruct->q1, SGX_MODULUS_SIZE); - reverse_bytes(sigstruct->q2, SGX_MODULUS_SIZE); EVP_MD_CTX_destroy(ctx); RSA_free(key);