[PATCH] drm/i915: Make suspend idle wait uninterruptible
Weifeng Liu <[email protected]> Wed, 5 Aug 2026 14:45:39 +0800
| Newsgroups | gmane.comp.freedesktop.xorg.drivers.intel,gmane.comp.video.dri.devel |
|---|---|
| Message-ID | <[email protected]> |
wait_for_suspend() only handles -ETIME from the GT idle wait. However, the wait can also be interrupted by a pending signal while retiring requests or waiting for GuC messages, e.g., during the reboot process invoked by init. This skips the wedge and cleanup path and may leave suspend waiting indefinitely for a leaked wakeref. Make only the suspend idle wait uninterruptible while preserving its existing timeout. Other callers remain interruptible, and the GT is still wedged only when the timeout expires. Cc: Matthew Brost <[email protected]> Assisted-by: OpenCode:GPT-5.6-Sol Signed-off-by: Weifeng Liu <[email protected]> --- drivers/gpu/drm/i915/gt/intel_gt.c | 24 +++++++++++++++---- drivers/gpu/drm/i915/gt/intel_gt.h | 1 + drivers/gpu/drm/i915/gt/intel_gt_pm.c | 3 ++- drivers/gpu/drm/i915/gt/intel_gt_requests.c | 8 ++++--- drivers/gpu/drm/i915/gt/intel_gt_requests.h | 13 ++++++++-- drivers/gpu/drm/i915/gt/uc/intel_guc.h | 3 ++- .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 5 ++-- drivers/gpu/drm/i915/gt/uc/intel_uc.h | 6 +++-- 8 files changed, 47 insertions(+), 16 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c index 5c7f862f7100..5eaa52f535d4 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.c +++ b/drivers/gpu/drm/i915/gt/intel_gt.c @@ -659,7 +659,9 @@ static void __intel_gt_disable(struct intel_gt *gt) GEM_BUG_ON(intel_gt_pm_is_awake(gt)); } -int intel_gt_wait_for_idle(struct intel_gt *gt, long timeout) +static int __intel_gt_wait_for_idle(struct intel_gt *gt, + bool interruptible, + long timeout) { long remaining_timeout; @@ -667,10 +669,11 @@ int intel_gt_wait_for_idle(struct intel_gt *gt, long timeout) if (!intel_gt_pm_is_awake(gt)) return 0; - while ((timeout = intel_gt_retire_requests_timeout(gt, timeout, - &remaining_timeout)) > 0) { + while ((timeout = __intel_gt_retire_requests_timeout(gt, interruptible, + timeout, + &remaining_timeout)) > 0) { cond_resched(); - if (signal_pending(current)) + if (interruptible && signal_pending(current)) return -EINTR; } @@ -680,7 +683,18 @@ int intel_gt_wait_for_idle(struct intel_gt *gt, long timeout) if (remaining_timeout < 0) remaining_timeout = 0; - return intel_uc_wait_for_idle(>->uc, remaining_timeout); + return intel_uc_wait_for_idle(>->uc, interruptible, + remaining_timeout); +} + +int intel_gt_wait_for_idle(struct intel_gt *gt, long timeout) +{ + return __intel_gt_wait_for_idle(gt, true, timeout); +} + +int intel_gt_wait_for_idle_uninterruptible(struct intel_gt *gt, long timeout) +{ + return __intel_gt_wait_for_idle(gt, false, timeout); } int intel_gt_init(struct intel_gt *gt) diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h index 998ca029b73a..6c7e5415f1dc 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.h +++ b/drivers/gpu/drm/i915/gt/intel_gt.h @@ -143,6 +143,7 @@ void intel_gt_driver_release(struct intel_gt *gt); void intel_gt_driver_late_release_all(struct drm_i915_private *i915); int intel_gt_wait_for_idle(struct intel_gt *gt, long timeout); +int intel_gt_wait_for_idle_uninterruptible(struct intel_gt *gt, long timeout); void intel_gt_check_and_clear_faults(struct intel_gt *gt); i915_reg_t intel_gt_perf_limit_reasons_reg(struct intel_gt *gt); diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c index c7f59d60fac6..9fe31aa07ae8 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c @@ -315,7 +315,8 @@ static void wait_for_suspend(struct intel_gt *gt) if (!intel_gt_pm_is_awake(gt)) return; - if (intel_gt_wait_for_idle(gt, I915_GT_SUSPEND_IDLE_TIMEOUT) == -ETIME) { + if (intel_gt_wait_for_idle_uninterruptible(gt, + I915_GT_SUSPEND_IDLE_TIMEOUT) == -ETIME) { /* * Forcibly cancel outstanding work and leave * the gpu quiet. diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c index 93298820bee2..b37e8f1d0b5c 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c @@ -130,8 +130,10 @@ void intel_engine_fini_retire(struct intel_engine_cs *engine) GEM_BUG_ON(engine->retire); } -long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout, - long *remaining_timeout) +long __intel_gt_retire_requests_timeout(struct intel_gt *gt, + bool interruptible, + long timeout, + long *remaining_timeout) { struct intel_gt_timelines *timelines = >->timelines; struct intel_timeline *tl, *tn; @@ -159,7 +161,7 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout, mutex_unlock(&tl->mutex); timeout = dma_fence_wait_timeout(fence, - true, + interruptible, timeout); dma_fence_put(fence); diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.h b/drivers/gpu/drm/i915/gt/intel_gt_requests.h index d2969f68dd64..9242f85f4040 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_requests.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.h @@ -12,8 +12,17 @@ struct intel_engine_cs; struct intel_gt; struct intel_timeline; -long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout, - long *remaining_timeout); +long __intel_gt_retire_requests_timeout(struct intel_gt *gt, + bool interruptible, + long timeout, + long *remaining_timeout); +static inline long +intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout, + long *remaining_timeout) +{ + return __intel_gt_retire_requests_timeout(gt, true, timeout, + remaining_timeout); +} static inline void intel_gt_retire_requests(struct intel_gt *gt) { intel_gt_retire_requests_timeout(gt, 0, NULL); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h index 053780f562c1..b5f4fddf5c1d 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h @@ -509,7 +509,8 @@ static inline void intel_guc_disable_msg(struct intel_guc *guc, u32 mask) spin_unlock_irq(&guc->irq_lock); } -int intel_guc_wait_for_idle(struct intel_guc *guc, long timeout); +int intel_guc_wait_for_idle(struct intel_guc *guc, bool interruptible, + long timeout); int intel_guc_deregister_done_process_msg(struct intel_guc *guc, const u32 *msg, u32 len); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index 788e59cdfac9..aa74208c2b4e 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -680,14 +680,15 @@ int intel_guc_wait_for_pending_msg(struct intel_guc *guc, return (timeout < 0) ? timeout : 0; } -int intel_guc_wait_for_idle(struct intel_guc *guc, long timeout) +int intel_guc_wait_for_idle(struct intel_guc *guc, bool interruptible, + long timeout) { if (!intel_uc_uses_guc_submission(&guc_to_gt(guc)->uc)) return 0; return intel_guc_wait_for_pending_msg(guc, &guc->outstanding_submission_g2h, - true, timeout); + interruptible, timeout); } static int guc_context_policy_init_v70(struct intel_context *ce, bool loop); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.h b/drivers/gpu/drm/i915/gt/uc/intel_uc.h index 014bb7d83689..b62fe3b96b64 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.h @@ -96,9 +96,11 @@ uc_state_checkers(gsc, gsc_uc); #undef uc_state_checkers #undef __uc_state_checker -static inline int intel_uc_wait_for_idle(struct intel_uc *uc, long timeout) +static inline int intel_uc_wait_for_idle(struct intel_uc *uc, + bool interruptible, + long timeout) { - return intel_guc_wait_for_idle(&uc->guc, timeout); + return intel_guc_wait_for_idle(&uc->guc, interruptible, timeout); } #define intel_uc_ops_function(_NAME, _OPS, _TYPE, _RET) \ -- 2.55.0