August 2020 - Linux-stable-mirror

FAILED: patch "[PATCH] drm/i915: Skip signaling a signaled request" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 1d9221e9d395c8c80d99d002bea3c9b6dd192d6a Mon Sep 17 00:00:00 2001 From: Chris Wilson <chris(a)chris-wilson.co.uk> Date: Mon, 13 Jul 2020 15:16:36 +0100 Subject: [PATCH] drm/i915: Skip signaling a signaled request Preempt-to-busy introduces various fascinating complications in that the requests may complete as we are unsubmitting them from HW. As they may then signal after unsubmission, we may find ourselves having to cleanup the signaling request from within the signaling callback. This causes us to recurse onto the same i915_request.lock. However, if the request is already signaled (as it will be before we enter the signal callbacks), we know we can skip the signaling of that request during submission, neatly evading the spinlock recursion. unsubmit(ve.rq0) # timeslice expiration or other preemption -> virtual_submit_request(ve.rq0) dma_fence_signal(ve.rq0) # request completed before preemption ack -> submit_notify(ve.rq1) -> virtual_submit_request(ve.rq1) # sees that we have completed ve.rq0 -> __i915_request_submit(ve.rq0) [ 264.210142] BUG: spinlock recursion on CPU#2, sample_multi_tr/2093 [ 264.210150] lock: 0xffff9efd6ac55080, .magic: dead4ead, .owner: sample_multi_tr/2093, .owner_cpu: 2 [ 264.210155] CPU: 2 PID: 2093 Comm: sample_multi_tr Tainted: G U [ 264.210158] Hardware name: Intel Corporation CoffeeLake Client Platform/CoffeeLake S UDIMM RVP, BIOS CNLSFWR1.R00.X212.B01.1909060036 09/06/2019 [ 264.210160] Call Trace: [ 264.210167] dump_stack+0x98/0xda [ 264.210174] spin_dump.cold+0x24/0x3c [ 264.210178] do_raw_spin_lock+0x9a/0xd0 [ 264.210184] _raw_spin_lock_nested+0x6a/0x70 [ 264.210314] __i915_request_submit+0x10a/0x3c0 [i915] [ 264.210415] virtual_submit_request+0x9b/0x380 [i915] [ 264.210516] submit_notify+0xaf/0x14c [i915] [ 264.210602] __i915_sw_fence_complete+0x8a/0x230 [i915] [ 264.210692] i915_sw_fence_complete+0x2d/0x40 [i915] [ 264.210762] __dma_i915_sw_fence_wake+0x19/0x30 [i915] [ 264.210767] dma_fence_signal_locked+0xb1/0x1c0 [ 264.210772] dma_fence_signal+0x29/0x50 [ 264.210871] i915_request_wait+0x5cb/0x830 [i915] [ 264.210876] ? dma_resv_get_fences_rcu+0x294/0x5d0 [ 264.210974] i915_gem_object_wait_fence+0x2f/0x40 [i915] [ 264.211084] i915_gem_object_wait+0xce/0x400 [i915] [ 264.211178] i915_gem_wait_ioctl+0xff/0x290 [i915] Fixes: 22b7a426bbe1 ("drm/i915/execlists: Preempt-to-busy") References: 6d06779e8672 ("drm/i915: Load balancing across a virtual engine") Signed-off-by: Chris Wilson <chris(a)chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin(a)intel.com> Cc: "Nayana, Venkata Ramana" <venkata.ramana.nayana(a)intel.com> Cc: <stable(a)vger.kernel.org> # v5.4+ Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin(a)intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200713141636.29326-1-chris@… diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c index d907d538176e..91786310c114 100644 --- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c @@ -314,13 +314,18 @@ bool i915_request_enable_breadcrumb(struct i915_request *rq) { lockdep_assert_held(&rq->lock); + if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &rq->fence.flags)) + return true; + if (test_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags)) { struct intel_breadcrumbs *b = &rq->engine->breadcrumbs; struct intel_context *ce = rq->context; struct list_head *pos; spin_lock(&b->irq_lock); - GEM_BUG_ON(test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags)); + + if (test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags)) + goto unlock; if (!__intel_breadcrumbs_arm_irq(b)) goto unlock; diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 3bb7320249ae..0b2fe55e6194 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -560,22 +560,25 @@ bool __i915_request_submit(struct i915_request *request) engine->serial++; result = true; -xfer: /* We may be recursing from the signal callback of another i915 fence */ - spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING); - +xfer: if (!test_and_set_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags)) { list_move_tail(&request->sched.link, &engine->active.requests); clear_bit(I915_FENCE_FLAG_PQUEUE, &request->fence.flags); - __notify_execute_cb(request); } - GEM_BUG_ON(!llist_empty(&request->execute_cb)); - if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &request->fence.flags) && - !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &request->fence.flags) && - !i915_request_enable_breadcrumb(request)) - intel_engine_signal_breadcrumbs(engine); + /* We may be recursing from the signal callback of another i915 fence */ + if (!i915_request_signaled(request)) { + spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING); + + __notify_execute_cb(request); + if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, + &request->fence.flags) && + !i915_request_enable_breadcrumb(request)) + intel_engine_signal_breadcrumbs(engine); - spin_unlock(&request->lock); + spin_unlock(&request->lock); + GEM_BUG_ON(!llist_empty(&request->execute_cb)); + } return result; }

4 years, 4 months

1
0
0 0

FAILED: patch "[PATCH] drm/i915: Skip signaling a signaled request" failed to apply to 5.8-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.8-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 1d9221e9d395c8c80d99d002bea3c9b6dd192d6a Mon Sep 17 00:00:00 2001 From: Chris Wilson <chris(a)chris-wilson.co.uk> Date: Mon, 13 Jul 2020 15:16:36 +0100 Subject: [PATCH] drm/i915: Skip signaling a signaled request Preempt-to-busy introduces various fascinating complications in that the requests may complete as we are unsubmitting them from HW. As they may then signal after unsubmission, we may find ourselves having to cleanup the signaling request from within the signaling callback. This causes us to recurse onto the same i915_request.lock. However, if the request is already signaled (as it will be before we enter the signal callbacks), we know we can skip the signaling of that request during submission, neatly evading the spinlock recursion. unsubmit(ve.rq0) # timeslice expiration or other preemption -> virtual_submit_request(ve.rq0) dma_fence_signal(ve.rq0) # request completed before preemption ack -> submit_notify(ve.rq1) -> virtual_submit_request(ve.rq1) # sees that we have completed ve.rq0 -> __i915_request_submit(ve.rq0) [ 264.210142] BUG: spinlock recursion on CPU#2, sample_multi_tr/2093 [ 264.210150] lock: 0xffff9efd6ac55080, .magic: dead4ead, .owner: sample_multi_tr/2093, .owner_cpu: 2 [ 264.210155] CPU: 2 PID: 2093 Comm: sample_multi_tr Tainted: G U [ 264.210158] Hardware name: Intel Corporation CoffeeLake Client Platform/CoffeeLake S UDIMM RVP, BIOS CNLSFWR1.R00.X212.B01.1909060036 09/06/2019 [ 264.210160] Call Trace: [ 264.210167] dump_stack+0x98/0xda [ 264.210174] spin_dump.cold+0x24/0x3c [ 264.210178] do_raw_spin_lock+0x9a/0xd0 [ 264.210184] _raw_spin_lock_nested+0x6a/0x70 [ 264.210314] __i915_request_submit+0x10a/0x3c0 [i915] [ 264.210415] virtual_submit_request+0x9b/0x380 [i915] [ 264.210516] submit_notify+0xaf/0x14c [i915] [ 264.210602] __i915_sw_fence_complete+0x8a/0x230 [i915] [ 264.210692] i915_sw_fence_complete+0x2d/0x40 [i915] [ 264.210762] __dma_i915_sw_fence_wake+0x19/0x30 [i915] [ 264.210767] dma_fence_signal_locked+0xb1/0x1c0 [ 264.210772] dma_fence_signal+0x29/0x50 [ 264.210871] i915_request_wait+0x5cb/0x830 [i915] [ 264.210876] ? dma_resv_get_fences_rcu+0x294/0x5d0 [ 264.210974] i915_gem_object_wait_fence+0x2f/0x40 [i915] [ 264.211084] i915_gem_object_wait+0xce/0x400 [i915] [ 264.211178] i915_gem_wait_ioctl+0xff/0x290 [i915] Fixes: 22b7a426bbe1 ("drm/i915/execlists: Preempt-to-busy") References: 6d06779e8672 ("drm/i915: Load balancing across a virtual engine") Signed-off-by: Chris Wilson <chris(a)chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin(a)intel.com> Cc: "Nayana, Venkata Ramana" <venkata.ramana.nayana(a)intel.com> Cc: <stable(a)vger.kernel.org> # v5.4+ Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin(a)intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200713141636.29326-1-chris@… diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c index d907d538176e..91786310c114 100644 --- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c @@ -314,13 +314,18 @@ bool i915_request_enable_breadcrumb(struct i915_request *rq) { lockdep_assert_held(&rq->lock); + if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &rq->fence.flags)) + return true; + if (test_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags)) { struct intel_breadcrumbs *b = &rq->engine->breadcrumbs; struct intel_context *ce = rq->context; struct list_head *pos; spin_lock(&b->irq_lock); - GEM_BUG_ON(test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags)); + + if (test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags)) + goto unlock; if (!__intel_breadcrumbs_arm_irq(b)) goto unlock; diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 3bb7320249ae..0b2fe55e6194 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -560,22 +560,25 @@ bool __i915_request_submit(struct i915_request *request) engine->serial++; result = true; -xfer: /* We may be recursing from the signal callback of another i915 fence */ - spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING); - +xfer: if (!test_and_set_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags)) { list_move_tail(&request->sched.link, &engine->active.requests); clear_bit(I915_FENCE_FLAG_PQUEUE, &request->fence.flags); - __notify_execute_cb(request); } - GEM_BUG_ON(!llist_empty(&request->execute_cb)); - if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &request->fence.flags) && - !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &request->fence.flags) && - !i915_request_enable_breadcrumb(request)) - intel_engine_signal_breadcrumbs(engine); + /* We may be recursing from the signal callback of another i915 fence */ + if (!i915_request_signaled(request)) { + spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING); + + __notify_execute_cb(request); + if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, + &request->fence.flags) && + !i915_request_enable_breadcrumb(request)) + intel_engine_signal_breadcrumbs(engine); - spin_unlock(&request->lock); + spin_unlock(&request->lock); + GEM_BUG_ON(!llist_empty(&request->execute_cb)); + } return result; }

4 years, 4 months

1
0
0 0

FAILED: patch "[PATCH] drm/i915: Skip signaling a signaled request" failed to apply to 5.7-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.7-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 1d9221e9d395c8c80d99d002bea3c9b6dd192d6a Mon Sep 17 00:00:00 2001 From: Chris Wilson <chris(a)chris-wilson.co.uk> Date: Mon, 13 Jul 2020 15:16:36 +0100 Subject: [PATCH] drm/i915: Skip signaling a signaled request Preempt-to-busy introduces various fascinating complications in that the requests may complete as we are unsubmitting them from HW. As they may then signal after unsubmission, we may find ourselves having to cleanup the signaling request from within the signaling callback. This causes us to recurse onto the same i915_request.lock. However, if the request is already signaled (as it will be before we enter the signal callbacks), we know we can skip the signaling of that request during submission, neatly evading the spinlock recursion. unsubmit(ve.rq0) # timeslice expiration or other preemption -> virtual_submit_request(ve.rq0) dma_fence_signal(ve.rq0) # request completed before preemption ack -> submit_notify(ve.rq1) -> virtual_submit_request(ve.rq1) # sees that we have completed ve.rq0 -> __i915_request_submit(ve.rq0) [ 264.210142] BUG: spinlock recursion on CPU#2, sample_multi_tr/2093 [ 264.210150] lock: 0xffff9efd6ac55080, .magic: dead4ead, .owner: sample_multi_tr/2093, .owner_cpu: 2 [ 264.210155] CPU: 2 PID: 2093 Comm: sample_multi_tr Tainted: G U [ 264.210158] Hardware name: Intel Corporation CoffeeLake Client Platform/CoffeeLake S UDIMM RVP, BIOS CNLSFWR1.R00.X212.B01.1909060036 09/06/2019 [ 264.210160] Call Trace: [ 264.210167] dump_stack+0x98/0xda [ 264.210174] spin_dump.cold+0x24/0x3c [ 264.210178] do_raw_spin_lock+0x9a/0xd0 [ 264.210184] _raw_spin_lock_nested+0x6a/0x70 [ 264.210314] __i915_request_submit+0x10a/0x3c0 [i915] [ 264.210415] virtual_submit_request+0x9b/0x380 [i915] [ 264.210516] submit_notify+0xaf/0x14c [i915] [ 264.210602] __i915_sw_fence_complete+0x8a/0x230 [i915] [ 264.210692] i915_sw_fence_complete+0x2d/0x40 [i915] [ 264.210762] __dma_i915_sw_fence_wake+0x19/0x30 [i915] [ 264.210767] dma_fence_signal_locked+0xb1/0x1c0 [ 264.210772] dma_fence_signal+0x29/0x50 [ 264.210871] i915_request_wait+0x5cb/0x830 [i915] [ 264.210876] ? dma_resv_get_fences_rcu+0x294/0x5d0 [ 264.210974] i915_gem_object_wait_fence+0x2f/0x40 [i915] [ 264.211084] i915_gem_object_wait+0xce/0x400 [i915] [ 264.211178] i915_gem_wait_ioctl+0xff/0x290 [i915] Fixes: 22b7a426bbe1 ("drm/i915/execlists: Preempt-to-busy") References: 6d06779e8672 ("drm/i915: Load balancing across a virtual engine") Signed-off-by: Chris Wilson <chris(a)chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin(a)intel.com> Cc: "Nayana, Venkata Ramana" <venkata.ramana.nayana(a)intel.com> Cc: <stable(a)vger.kernel.org> # v5.4+ Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin(a)intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200713141636.29326-1-chris@… diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c index d907d538176e..91786310c114 100644 --- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c @@ -314,13 +314,18 @@ bool i915_request_enable_breadcrumb(struct i915_request *rq) { lockdep_assert_held(&rq->lock); + if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &rq->fence.flags)) + return true; + if (test_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags)) { struct intel_breadcrumbs *b = &rq->engine->breadcrumbs; struct intel_context *ce = rq->context; struct list_head *pos; spin_lock(&b->irq_lock); - GEM_BUG_ON(test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags)); + + if (test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags)) + goto unlock; if (!__intel_breadcrumbs_arm_irq(b)) goto unlock; diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 3bb7320249ae..0b2fe55e6194 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -560,22 +560,25 @@ bool __i915_request_submit(struct i915_request *request) engine->serial++; result = true; -xfer: /* We may be recursing from the signal callback of another i915 fence */ - spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING); - +xfer: if (!test_and_set_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags)) { list_move_tail(&request->sched.link, &engine->active.requests); clear_bit(I915_FENCE_FLAG_PQUEUE, &request->fence.flags); - __notify_execute_cb(request); } - GEM_BUG_ON(!llist_empty(&request->execute_cb)); - if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &request->fence.flags) && - !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &request->fence.flags) && - !i915_request_enable_breadcrumb(request)) - intel_engine_signal_breadcrumbs(engine); + /* We may be recursing from the signal callback of another i915 fence */ + if (!i915_request_signaled(request)) { + spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING); + + __notify_execute_cb(request); + if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, + &request->fence.flags) && + !i915_request_enable_breadcrumb(request)) + intel_engine_signal_breadcrumbs(engine); - spin_unlock(&request->lock); + spin_unlock(&request->lock); + GEM_BUG_ON(!llist_empty(&request->execute_cb)); + } return result; }

4 years, 4 months

1
0
0 0

FAILED: patch "[PATCH] arm64: hw_breakpoint: Don't invoke overflow handler on" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 24ebec25fb270100e252b19c288e21bd7d8cc7f7 Mon Sep 17 00:00:00 2001 From: Will Deacon <will(a)kernel.org> Date: Fri, 29 May 2020 14:12:18 +0100 Subject: [PATCH] arm64: hw_breakpoint: Don't invoke overflow handler on uaccess watchpoints Unprivileged memory accesses generated by the so-called "translated" instructions (e.g. STTR) at EL1 can cause EL0 watchpoints to fire unexpectedly if kernel debugging is enabled. In such cases, the hw_breakpoint logic will invoke the user overflow handler which will typically raise a SIGTRAP back to the current task. This is futile when returning back to the kernel because (a) the signal won't have been delivered and (b) userspace can't handle the thing anyway. Avoid invoking the user overflow handler for watchpoints triggered by kernel uaccess routines, and instead single-step over the faulting instruction as we would if no overflow handler had been installed. (Fixes tag identifies the introduction of unprivileged memory accesses, which exposed this latent bug in the hw_breakpoint code) Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: James Morse <james.morse(a)arm.com> Fixes: 57f4959bad0a ("arm64: kernel: Add support for User Access Override") Reported-by: Luis Machado <luis.machado(a)linaro.org> Signed-off-by: Will Deacon <will(a)kernel.org> diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 0b727edf4104..af234a1e08b7 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -730,6 +730,27 @@ static u64 get_distance_from_watchpoint(unsigned long addr, u64 val, return 0; } +static int watchpoint_report(struct perf_event *wp, unsigned long addr, + struct pt_regs *regs) +{ + int step = is_default_overflow_handler(wp); + struct arch_hw_breakpoint *info = counter_arch_bp(wp); + + info->trigger = addr; + + /* + * If we triggered a user watchpoint from a uaccess routine, then + * handle the stepping ourselves since userspace really can't help + * us with this. + */ + if (!user_mode(regs) && info->ctrl.privilege == AARCH64_BREAKPOINT_EL0) + step = 1; + else + perf_bp_event(wp, regs); + + return step; +} + static int watchpoint_handler(unsigned long addr, unsigned int esr, struct pt_regs *regs) { @@ -739,7 +760,6 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr, u64 val; struct perf_event *wp, **slots; struct debug_info *debug_info; - struct arch_hw_breakpoint *info; struct arch_hw_breakpoint_ctrl ctrl; slots = this_cpu_ptr(wp_on_reg); @@ -777,25 +797,13 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr, if (dist != 0) continue; - info = counter_arch_bp(wp); - info->trigger = addr; - perf_bp_event(wp, regs); - - /* Do we need to handle the stepping? */ - if (is_default_overflow_handler(wp)) - step = 1; + step = watchpoint_report(wp, addr, regs); } - if (min_dist > 0 && min_dist != -1) { - /* No exact match found. */ - wp = slots[closest_match]; - info = counter_arch_bp(wp); - info->trigger = addr; - perf_bp_event(wp, regs); - /* Do we need to handle the stepping? */ - if (is_default_overflow_handler(wp)) - step = 1; - } + /* No exact match found? */ + if (min_dist > 0 && min_dist != -1) + step = watchpoint_report(slots[closest_match], addr, regs); + rcu_read_unlock(); if (!step)

4 years, 4 months

1
0
0 0

FAILED: patch "[PATCH] arm64: hw_breakpoint: Don't invoke overflow handler on" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 24ebec25fb270100e252b19c288e21bd7d8cc7f7 Mon Sep 17 00:00:00 2001 From: Will Deacon <will(a)kernel.org> Date: Fri, 29 May 2020 14:12:18 +0100 Subject: [PATCH] arm64: hw_breakpoint: Don't invoke overflow handler on uaccess watchpoints Unprivileged memory accesses generated by the so-called "translated" instructions (e.g. STTR) at EL1 can cause EL0 watchpoints to fire unexpectedly if kernel debugging is enabled. In such cases, the hw_breakpoint logic will invoke the user overflow handler which will typically raise a SIGTRAP back to the current task. This is futile when returning back to the kernel because (a) the signal won't have been delivered and (b) userspace can't handle the thing anyway. Avoid invoking the user overflow handler for watchpoints triggered by kernel uaccess routines, and instead single-step over the faulting instruction as we would if no overflow handler had been installed. (Fixes tag identifies the introduction of unprivileged memory accesses, which exposed this latent bug in the hw_breakpoint code) Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: James Morse <james.morse(a)arm.com> Fixes: 57f4959bad0a ("arm64: kernel: Add support for User Access Override") Reported-by: Luis Machado <luis.machado(a)linaro.org> Signed-off-by: Will Deacon <will(a)kernel.org> diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 0b727edf4104..af234a1e08b7 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -730,6 +730,27 @@ static u64 get_distance_from_watchpoint(unsigned long addr, u64 val, return 0; } +static int watchpoint_report(struct perf_event *wp, unsigned long addr, + struct pt_regs *regs) +{ + int step = is_default_overflow_handler(wp); + struct arch_hw_breakpoint *info = counter_arch_bp(wp); + + info->trigger = addr; + + /* + * If we triggered a user watchpoint from a uaccess routine, then + * handle the stepping ourselves since userspace really can't help + * us with this. + */ + if (!user_mode(regs) && info->ctrl.privilege == AARCH64_BREAKPOINT_EL0) + step = 1; + else + perf_bp_event(wp, regs); + + return step; +} + static int watchpoint_handler(unsigned long addr, unsigned int esr, struct pt_regs *regs) { @@ -739,7 +760,6 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr, u64 val; struct perf_event *wp, **slots; struct debug_info *debug_info; - struct arch_hw_breakpoint *info; struct arch_hw_breakpoint_ctrl ctrl; slots = this_cpu_ptr(wp_on_reg); @@ -777,25 +797,13 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr, if (dist != 0) continue; - info = counter_arch_bp(wp); - info->trigger = addr; - perf_bp_event(wp, regs); - - /* Do we need to handle the stepping? */ - if (is_default_overflow_handler(wp)) - step = 1; + step = watchpoint_report(wp, addr, regs); } - if (min_dist > 0 && min_dist != -1) { - /* No exact match found. */ - wp = slots[closest_match]; - info = counter_arch_bp(wp); - info->trigger = addr; - perf_bp_event(wp, regs); - /* Do we need to handle the stepping? */ - if (is_default_overflow_handler(wp)) - step = 1; - } + /* No exact match found? */ + if (min_dist > 0 && min_dist != -1) + step = watchpoint_report(slots[closest_match], addr, regs); + rcu_read_unlock(); if (!step)

4 years, 4 months

1
0
0 0

[(resend) PATCH v3: {linux-4.14.y} ] dm cache: submit writethrough writes in parallel to origin and cache

by John Donnelly

From: Mike Snitzer <snitzer(a)redhat.com> Discontinue issuing writethrough write IO in series to the origin and then cache. Use bio_clone_fast() to create a new origin clone bio that will be mapped to the origin device and then bio_chain() it to the bio that gets remapped to the cache device. The origin clone bio does _not_ have a copy of the per_bio_data -- as such check_if_tick_bio_needed() will not be called. The cache bio (parent bio) will not complete until the origin bio has completed -- this fulfills bio_clone_fast()'s requirements as well as the requirement to not complete the original IO until the write IO has completed to both the origin and cache device. Signed-off-by: Mike Snitzer <snitzer(a)redhat.com> (cherry picked from commit 2df3bae9a6543e90042291707b8db0cbfbae9ee9) Fixes: 4ec34f2196d125ff781170ddc6c3058c08ec5e73 (dm bio record: save/restore bi_end_io and bi_integrity ) 4ec34f21 introduced a mkfs.ext4 hang on a LVM device that has been modified with lvconvert --cachemode=writethrough. CC:stable@vger.kernel.org for 4.14.y Signed-off-by: John Donnelly <john.p.donnelly(a)oracle.com> Reviewed-by: Somasundaram Krishnasamy <somasundaram.krishnasamy(a)oracle.com> conflicts: drivers/md/dm-cache-target.c. - Corrected usage of writethrough_mode(&cache->feature) that was caught by compiler, and removed unused static functions : writethrough_endio(), defer_writethrough_bio(), wake_deferred_writethrough_worker() that generated warnings. --- drivers/md/dm-cache-target.c | 92 ++++++++++++++++++-------------------------- 1 file changed, 37 insertions(+), 55 deletions(-) diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 69cdb29ef6be..2732d1df05fa 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -450,6 +450,7 @@ struct cache { struct work_struct migration_worker; struct delayed_work waker; struct dm_bio_prison_v2 *prison; + struct bio_set *bs; mempool_t *migration_pool; @@ -537,11 +538,6 @@ static void wake_deferred_bio_worker(struct cache *cache) queue_work(cache->wq, &cache->deferred_bio_worker); } -static void wake_deferred_writethrough_worker(struct cache *cache) -{ - queue_work(cache->wq, &cache->deferred_writethrough_worker); -} - static void wake_migration_worker(struct cache *cache) { if (passthrough_mode(&cache->features)) @@ -868,16 +864,23 @@ static void check_if_tick_bio_needed(struct cache *cache, struct bio *bio) spin_unlock_irqrestore(&cache->lock, flags); } -static void remap_to_origin_clear_discard(struct cache *cache, struct bio *bio, - dm_oblock_t oblock) +static void __remap_to_origin_clear_discard(struct cache *cache, struct bio *bio, + dm_oblock_t oblock, bool bio_has_pbd) { - // FIXME: this is called way too much. - check_if_tick_bio_needed(cache, bio); + if (bio_has_pbd) + check_if_tick_bio_needed(cache, bio); remap_to_origin(cache, bio); if (bio_data_dir(bio) == WRITE) clear_discard(cache, oblock_to_dblock(cache, oblock)); } +static void remap_to_origin_clear_discard(struct cache *cache, struct bio *bio, + dm_oblock_t oblock) +{ + // FIXME: check_if_tick_bio_needed() is called way too much through this interface + __remap_to_origin_clear_discard(cache, bio, oblock, true); +} + static void remap_to_cache_dirty(struct cache *cache, struct bio *bio, dm_oblock_t oblock, dm_cblock_t cblock) { @@ -937,57 +940,26 @@ static void issue_op(struct bio *bio, void *context) accounted_request(cache, bio); } -static void defer_writethrough_bio(struct cache *cache, struct bio *bio) -{ - unsigned long flags; - - spin_lock_irqsave(&cache->lock, flags); - bio_list_add(&cache->deferred_writethrough_bios, bio); - spin_unlock_irqrestore(&cache->lock, flags); - - wake_deferred_writethrough_worker(cache); -} - -static void writethrough_endio(struct bio *bio) -{ - struct per_bio_data *pb = get_per_bio_data(bio, PB_DATA_SIZE_WT); - - dm_unhook_bio(&pb->hook_info, bio); - - if (bio->bi_status) { - bio_endio(bio); - return; - } - - dm_bio_restore(&pb->bio_details, bio); - remap_to_cache(pb->cache, bio, pb->cblock); - - /* - * We can't issue this bio directly, since we're in interrupt - * context. So it gets put on a bio list for processing by the - * worker thread. - */ - defer_writethrough_bio(pb->cache, bio); -} - /* - * FIXME: send in parallel, huge latency as is. * When running in writethrough mode we need to send writes to clean blocks - * to both the cache and origin devices. In future we'd like to clone the - * bio and send them in parallel, but for now we're doing them in - * series as this is easier. + * to both the cache and origin devices. Clone the bio and send them in parallel. */ -static void remap_to_origin_then_cache(struct cache *cache, struct bio *bio, - dm_oblock_t oblock, dm_cblock_t cblock) +static void remap_to_origin_and_cache(struct cache *cache, struct bio *bio, + dm_oblock_t oblock, dm_cblock_t cblock) { - struct per_bio_data *pb = get_per_bio_data(bio, PB_DATA_SIZE_WT); + struct bio *origin_bio = bio_clone_fast(bio, GFP_NOIO, cache->bs); + + BUG_ON(!origin_bio); - pb->cache = cache; - pb->cblock = cblock; - dm_hook_bio(&pb->hook_info, bio, writethrough_endio, NULL); - dm_bio_record(&pb->bio_details, bio); + bio_chain(origin_bio, bio); + /* + * Passing false to __remap_to_origin_clear_discard() skips + * all code that might use per_bio_data (since clone doesn't have it) + */ + __remap_to_origin_clear_discard(cache, origin_bio, oblock, false); + submit_bio(origin_bio); - remap_to_origin_clear_discard(pb->cache, bio, oblock); + remap_to_cache(cache, bio, cblock); } /*---------------------------------------------------------------- @@ -1873,7 +1845,7 @@ static int map_bio(struct cache *cache, struct bio *bio, dm_oblock_t block, } else { if (bio_data_dir(bio) == WRITE && writethrough_mode(&cache->features) && !is_dirty(cache, cblock)) { - remap_to_origin_then_cache(cache, bio, block, cblock); + remap_to_origin_and_cache(cache, bio, block, cblock); accounted_begin(cache, bio); } else remap_to_cache_dirty(cache, bio, block, cblock); @@ -2132,6 +2104,9 @@ static void destroy(struct cache *cache) kfree(cache->ctr_args[i]); kfree(cache->ctr_args); + if (cache->bs) + bioset_free(cache->bs); + kfree(cache); } @@ -2589,6 +2564,13 @@ static int cache_create(struct cache_args *ca, struct cache **result) cache->features = ca->features; ti->per_io_data_size = get_per_bio_data_size(cache); + if (writethrough_mode(&cache->features)) { + /* Create bioset for writethrough bios issued to origin */ + cache->bs = bioset_create(BIO_POOL_SIZE, 0, 0); + if (!cache->bs) + goto bad; + } + cache->callbacks.congested_fn = cache_is_congested; dm_table_add_target_callbacks(ti->table, &cache->callbacks); -- 1.8.3.1

4 years, 4 months

3
5
0 0

Request to pick up couple NVIDIA Tegra ASoC patches into 5.7 kernel

by Dmitry Osipenko

Hello, stable-kernel maintainers! Could you please cherry-pick these commits into the v5.7.x kernel? commit 0de6db30ef79b391cedd749801a49c485d2daf4b Author: Sowjanya Komatineni <skomatineni(a)nvidia.com> Date: Mon Jan 13 23:24:17 2020 -0800 ASoC: tegra: Use device managed resource APIs to get the clock commit 1e4e0bf136aa4b4aa59c1e6af19844bd6d807794 Author: Sowjanya Komatineni <skomatineni(a)nvidia.com> Date: Mon Jan 13 23:24:23 2020 -0800 ASoC: tegra: Add audio mclk parent configuration commit ff5d18cb04f4ecccbcf05b7f83ab6df2a0d95c16 Author: Sowjanya Komatineni <skomatineni(a)nvidia.com> Date: Mon Jan 13 23:24:24 2020 -0800 ASoC: tegra: Enable audio mclk during tegra_asoc_utils_init() It will fix a huge warnings splat during of kernel boot on NVIDIA Tegra SoCs. For some reason these patches haven't made into 5.7 when it was released and several people complained about the warnings. Thanks in advance!

4 years, 4 months

3
3
0 0

[PATCH STABLE 4.9] mm: Avoid calling build_all_zonelists_init under hotplug context

by Oscar Salvador

Recently a customer of ours experienced a crash when booting the system while enabling memory-hotplug. The problem is that Normal zones on different nodes don't get their private zone->pageset allocated, and keep sharing the initial boot_pageset. The sharing between zones is normally safe as explained by the comment for boot_pageset - it's a percpu structure, and manipulations are done with disabled interrupts, and boot_pageset is set up in a way that any page placed on its pcplist is immediately flushed to shared zone's freelist, because pcp->high == 1. However, the hotplug operation updates pcp->high to a higher value as it expects to be operating on a private pageset. The problem is in build_all_zonelists(), which is called when the first range of pages is onlined for the Normal zone of node X or Y: if (system_state == SYSTEM_BOOTING) { build_all_zonelists_init(); } else { #ifdef CONFIG_MEMORY_HOTPLUG if (zone) setup_zone_pageset(zone); #endif /* we have to stop all cpus to guarantee there is no user of zonelist */ stop_machine(__build_all_zonelists, pgdat, NULL); /* cpuset refresh routine should be here */ } When called during hotplug, it should execute the setup_zone_pageset(zone) which allocates the private pageset. However, with memhp_default_state=online, this happens early while system_state == SYSTEM_BOOTING is still true, hence this step is skipped. (and build_all_zonelists_init() is probably unsafe anyway at this point). Another hotplug operation on the same zone then leads to zone_pcp_update(zone) called from online_pages(), which updates the pcp->high for the shared boot_pageset to a value higher than 1. At that point, pages freed from Node X and Y Normal zones can end up on the same pcplist and from there they can be freed to the wrong zone's freelist, leading to the corruption and crashes. Please, note that upstream has fixed that differently (and unintentionally) by adding another boot state (SYSTEM_SCHEDULING), which is set before smp_init(). That should happen before memory hotplug events even with memhp_default_state=online. Backporting that would be too intrusive. Signed-off-by: Oscar Salvador <osalvador(a)suse.de> Debugged-by: Vlastimil Babka <vbabka(a)suse.cz> --- include/linux/mmzone.h | 3 ++- init/main.c | 2 +- mm/memory_hotplug.c | 10 +++++----- mm/page_alloc.c | 7 ++++--- 4 files changed, 12 insertions(+), 10 deletions(-) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index e3d7754f25f0..5c7645e156a5 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -756,7 +756,8 @@ static inline bool is_dev_zone(const struct zone *zone) #include <linux/memory_hotplug.h> extern struct mutex zonelists_mutex; -void build_all_zonelists(pg_data_t *pgdat, struct zone *zone); +void build_all_zonelists(pg_data_t *pgdat, struct zone *zone, + bool hotplug_context); void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx); bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int classzone_idx, unsigned int alloc_flags, diff --git a/init/main.c b/init/main.c index d47860dbe896..7ad08957dd18 100644 --- a/init/main.c +++ b/init/main.c @@ -512,7 +512,7 @@ asmlinkage __visible void __init start_kernel(void) smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */ boot_cpu_hotplug_init(); - build_all_zonelists(NULL, NULL); + build_all_zonelists(NULL, NULL, false); page_alloc_init(); pr_notice("Kernel command line: %s\n", boot_command_line); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 449999657c0b..a4ffe5996317 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1125,7 +1125,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ mutex_lock(&zonelists_mutex); if (!populated_zone(zone)) { need_zonelists_rebuild = 1; - build_all_zonelists(NULL, zone); + build_all_zonelists(NULL, zone, true); } ret = walk_system_ram_range(pfn, nr_pages, &onlined_pages, @@ -1146,7 +1146,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ if (onlined_pages) { node_states_set_node(nid, &arg); if (need_zonelists_rebuild) - build_all_zonelists(NULL, NULL); + build_all_zonelists(NULL, NULL, true); else zone_pcp_update(zone); } @@ -1220,7 +1220,7 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) * to access not-initialized zonelist, build here. */ mutex_lock(&zonelists_mutex); - build_all_zonelists(pgdat, NULL); + build_all_zonelists(pgdat, NULL, true); mutex_unlock(&zonelists_mutex); /* @@ -1276,7 +1276,7 @@ int try_online_node(int nid) if (pgdat->node_zonelists->_zonerefs->zone == NULL) { mutex_lock(&zonelists_mutex); - build_all_zonelists(NULL, NULL); + build_all_zonelists(NULL, NULL, true); mutex_unlock(&zonelists_mutex); } @@ -2016,7 +2016,7 @@ static int __ref __offline_pages(unsigned long start_pfn, if (!populated_zone(zone)) { zone_pcp_reset(zone); mutex_lock(&zonelists_mutex); - build_all_zonelists(NULL, NULL); + build_all_zonelists(NULL, NULL, true); mutex_unlock(&zonelists_mutex); } else zone_pcp_update(zone); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index de00e0fec484..f394dd87fa03 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4608,7 +4608,7 @@ int numa_zonelist_order_handler(struct ctl_table *table, int write, user_zonelist_order = oldval; } else if (oldval != user_zonelist_order) { mutex_lock(&zonelists_mutex); - build_all_zonelists(NULL, NULL); + build_all_zonelists(NULL, NULL, false); mutex_unlock(&zonelists_mutex); } } @@ -4988,11 +4988,12 @@ build_all_zonelists_init(void) * (2) call of __init annotated helper build_all_zonelists_init * [protected by SYSTEM_BOOTING]. */ -void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone) +void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone, + bool hotplug_context) { set_zonelist_order(); - if (system_state == SYSTEM_BOOTING) { + if (system_state == SYSTEM_BOOTING && !hotplug_context) { build_all_zonelists_init(); } else { #ifdef CONFIG_MEMORY_HOTPLUG -- 2.26.2

4 years, 4 months

4
3
0 0

[PATCH] arm64: dts: marvell: espressobin: add ethernet alias

by Pali Rohár

From: Tomasz Maciej Nowak <tmn505(a)gmail.com> commit 5253cb8c00a6f4356760efb38bca0e0393aa06de upstream. The maker of this board and its variants, stores MAC address in U-Boot environment. Add alias for bootloader to recognise, to which ethernet node inject the factory MAC address. Signed-off-by: Tomasz Maciej Nowak <tmn505(a)gmail.com> Signed-off-by: Gregory CLEMENT <gregory.clement(a)bootlin.com> [pali: Backported to 5.4 and older versions] Signed-off-by: Pali Rohár <pali(a)kernel.org> --- arch/arm64/boot/dts/marvell/armada-3720-espressobin.dts | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dts b/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dts index fbcf03f86c96..05dc58c13fa4 100644 --- a/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dts +++ b/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dts @@ -19,6 +19,12 @@ model = "Globalscale Marvell ESPRESSOBin Board"; compatible = "globalscale,espressobin", "marvell,armada3720", "marvell,armada3710"; + aliases { + ethernet0 = &eth0; + serial0 = &uart0; + serial1 = &uart1; + }; + chosen { stdout-path = "serial0:115200n8"; }; -- 2.20.1

4 years, 4 months

2
2
0 0

[PATCH 4.14 1/2] genirq/affinity: Handle affinity setting on inactive interrupts correctly

by Frank van der Linden

From: Thomas Gleixner <tglx(a)linutronix.de> commit baedb87d1b53532f81b4bd0387f83b05d4f7eb9a upstream. Setting interrupt affinity on inactive interrupts is inconsistent when hierarchical irq domains are enabled. The core code should just store the affinity and not call into the irq chip driver for inactive interrupts because the chip drivers may not be in a state to handle such requests. X86 has a hacky workaround for that but all other irq chips have not which causes problems e.g. on GIC V3 ITS. Instead of adding more ugly hacks all over the place, solve the problem in the core code. If the affinity is set on an inactive interrupt then: - Store it in the irq descriptors affinity mask - Update the effective affinity to reflect that so user space has a consistent view - Don't call into the irq chip driver This is the core equivalent of the X86 workaround and works correctly because the affinity setting is established in the irq chip when the interrupt is activated later on. Note, that this is only effective when hierarchical irq domains are enabled by the architecture. Doing it unconditionally would break legacy irq chip implementations. For hierarchial irq domains this works correctly as none of the drivers can have a dependency on affinity setting in inactive state by design. Remove the X86 workaround as it is not longer required. Fixes: 02edee152d6e ("x86/apic/vector: Ignore set_affinity call for inactive interrupts") Reported-by: Ali Saidi <alisaidi(a)amazon.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Tested-by: Ali Saidi <alisaidi(a)amazon.com> Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/r/20200529015501.15771-1-alisaidi@amazon.com Link: https://lkml.kernel.org/r/877dv2rv25.fsf@nanos.tec.linutronix.de [fllinden(a)amazon.com - 4.14 never had the x86 workaround, so skip x86 changes] Signed-off-by: Frank van der Linden <fllinden(a)amazon.com> --- kernel/irq/manage.c | 37 +++++++++++++++++++++++++++++++++++-- 1 file changed, 35 insertions(+), 2 deletions(-) diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 5277949e82e0..ce6fba446814 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -168,9 +168,9 @@ void irq_set_thread_affinity(struct irq_desc *desc) set_bit(IRQTF_AFFINITY, &action->thread_flags); } +#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK static void irq_validate_effective_affinity(struct irq_data *data) { -#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK const struct cpumask *m = irq_data_get_effective_affinity_mask(data); struct irq_chip *chip = irq_data_get_irq_chip(data); @@ -178,9 +178,19 @@ static void irq_validate_effective_affinity(struct irq_data *data) return; pr_warn_once("irq_chip %s did not update eff. affinity mask of irq %u\n", chip->name, data->irq); -#endif } +static inline void irq_init_effective_affinity(struct irq_data *data, + const struct cpumask *mask) +{ + cpumask_copy(irq_data_get_effective_affinity_mask(data), mask); +} +#else +static inline void irq_validate_effective_affinity(struct irq_data *data) { } +static inline void irq_init_effective_affinity(struct irq_data *data, + const struct cpumask *mask) { } +#endif + int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { @@ -205,6 +215,26 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, return ret; } +static bool irq_set_affinity_deactivated(struct irq_data *data, + const struct cpumask *mask, bool force) +{ + struct irq_desc *desc = irq_data_to_desc(data); + + /* + * If the interrupt is not yet activated, just store the affinity + * mask and do not call the chip driver at all. On activation the + * driver has to make sure anyway that the interrupt is in a + * useable state so startup works. + */ + if (!IS_ENABLED(CONFIG_IRQ_DOMAIN_HIERARCHY) || irqd_is_activated(data)) + return false; + + cpumask_copy(desc->irq_common_data.affinity, mask); + irq_init_effective_affinity(data, mask); + irqd_set(data, IRQD_AFFINITY_SET); + return true; +} + int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask, bool force) { @@ -215,6 +245,9 @@ int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask, if (!chip || !chip->irq_set_affinity) return -EINVAL; + if (irq_set_affinity_deactivated(data, mask, force)) + return 0; + if (irq_can_move_pcntxt(data)) { ret = irq_do_set_affinity(data, mask, force); } else { -- 2.17.2

4 years, 4 months

3
6
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror August 2020