diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h index e10d78601bbd..b457d6c49325 100644 --- a/drivers/gpu/drm/i915/gt/intel_context_types.h +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h @@ -97,6 +97,10 @@ struct intel_context { #define CONTEXT_FORCE_SINGLE_SUBMISSION 7 #define CONTEXT_NOPREEMPT 8 + struct { + u64 timeout_us; + } watchdog; + u32 *lrc_reg_state; union { struct { diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.h b/drivers/gpu/drm/i915/gt/intel_execlists_submission.h index a8fd7adefd82..fd61dae820e9 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.h +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.h @@ -6,6 +6,7 @@ #ifndef __INTEL_EXECLISTS_SUBMISSION_H__ #define __INTEL_EXECLISTS_SUBMISSION_H__ +#include #include struct drm_printer; @@ -13,6 +14,7 @@ struct drm_printer; struct i915_request; struct intel_context; struct intel_engine_cs; +struct intel_gt; enum { INTEL_CONTEXT_SCHEDULE_IN = 0, diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c index d8e1ab412634..ff63034cff9c 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.c +++ b/drivers/gpu/drm/i915/gt/intel_gt.c @@ -29,6 +29,9 @@ void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915) INIT_LIST_HEAD(>->closed_vma); spin_lock_init(>->closed_lock); + init_llist_head(>->watchdog.list); + INIT_WORK(>->watchdog.work, intel_gt_watchdog_work); + intel_gt_init_buffer_pool(gt); intel_gt_init_reset(gt); intel_gt_init_requests(gt); diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h index 9157c7411f60..35d3bb13372f 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.h +++ b/drivers/gpu/drm/i915/gt/intel_gt.h @@ -77,4 +77,6 @@ static inline bool intel_gt_is_wedged(const struct intel_gt *gt) void intel_gt_info_print(const struct intel_gt_info *info, struct drm_printer *p); +void intel_gt_watchdog_work(struct work_struct *work); + #endif /* __INTEL_GT_H__ */ diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c index dc06c78c9eeb..f7e5ce2e2291 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c @@ -9,6 +9,7 @@ #include "i915_drv.h" /* for_each_engine() */ #include "i915_request.h" #include "intel_engine_heartbeat.h" +#include "intel_execlists_submission.h" #include "intel_gt.h" #include "intel_gt_pm.h" #include "intel_gt_requests.h" @@ -243,4 +244,31 @@ void intel_gt_fini_requests(struct intel_gt *gt) { /* Wait until the work is marked as finished before unloading! */ cancel_delayed_work_sync(>->requests.retire_work); + + flush_work(>->watchdog.work); +} + +void intel_gt_watchdog_work(struct work_struct *work) +{ + struct intel_gt *gt = + container_of(work, typeof(*gt), watchdog.work); + struct i915_request *rq, *rn; + struct llist_node *first; + + first = llist_del_all(>->watchdog.list); + if (!first) + return; + + llist_for_each_entry_safe(rq, rn, first, watchdog.link) { + if (!i915_request_completed(rq)) { + struct dma_fence *f = &rq->fence; + + pr_notice("Fence expiration time out i915-%s:%s:%llx!\n", + f->ops->get_driver_name(f), + f->ops->get_timeline_name(f), + f->seqno); + i915_request_cancel(rq, -EINTR); + } + i915_request_put(rq); + } } diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h index f7dab4fc926c..0caf6ca0a784 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_types.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h @@ -8,10 +8,12 @@ #include #include +#include #include #include #include #include +#include #include "uc/intel_uc.h" @@ -52,6 +54,11 @@ struct intel_gt { struct delayed_work retire_work; } requests; + struct { + struct llist_head list; + struct work_struct work; + } watchdog; + struct intel_wakeref wakeref; atomic_t user_wakeref; diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index a031b86f8508..63968d163c14 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -321,6 +321,53 @@ static void remove_from_engine(struct i915_request *rq) __notify_execute_cb_imm(rq); } +static void __rq_init_watchdog(struct i915_request *rq) +{ + rq->watchdog.timer.function = NULL; +} + +static enum hrtimer_restart __rq_watchdog_expired(struct hrtimer *hrtimer) +{ + struct i915_request *rq = + container_of(hrtimer, struct i915_request, watchdog.timer); + struct intel_gt *gt = rq->engine->gt; + + if (!i915_request_completed(rq)) { + if (llist_add(&rq->watchdog.link, >->watchdog.list)) + schedule_work(>->watchdog.work); + } else { + i915_request_put(rq); + } + + return HRTIMER_NORESTART; +} + +static void __rq_arm_watchdog(struct i915_request *rq) +{ + struct i915_request_watchdog *wdg = &rq->watchdog; + struct intel_context *ce = rq->context; + + if (!ce->watchdog.timeout_us) + return; + + hrtimer_init(&wdg->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + wdg->timer.function = __rq_watchdog_expired; + hrtimer_start_range_ns(&wdg->timer, + ns_to_ktime(ce->watchdog.timeout_us * + NSEC_PER_USEC), + NSEC_PER_MSEC, + HRTIMER_MODE_REL); + i915_request_get(rq); +} + +static void __rq_cancel_watchdog(struct i915_request *rq) +{ + struct i915_request_watchdog *wdg = &rq->watchdog; + + if (wdg->timer.function && hrtimer_try_to_cancel(&wdg->timer) > 0) + i915_request_put(rq); +} + bool i915_request_retire(struct i915_request *rq) { if (!__i915_request_is_complete(rq)) @@ -332,6 +379,8 @@ bool i915_request_retire(struct i915_request *rq) trace_i915_request_retire(rq); i915_request_mark_complete(rq); + __rq_cancel_watchdog(rq); + /* * We know the GPU must have read the request to have * sent us the seqno + interrupt, so use the position @@ -761,6 +810,8 @@ submit_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state) if (unlikely(fence->error)) i915_request_set_error_once(request, fence->error); + else + __rq_arm_watchdog(request); /* * We need to serialize use of the submit_request() callback @@ -947,6 +998,7 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp) /* No zalloc, everything must be cleared after use */ rq->batch = NULL; + __rq_init_watchdog(rq); GEM_BUG_ON(rq->capture_list); GEM_BUG_ON(!llist_empty(&rq->execute_cb)); diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h index e4d190ab76b2..36071d3d383d 100644 --- a/drivers/gpu/drm/i915/i915_request.h +++ b/drivers/gpu/drm/i915/i915_request.h @@ -26,7 +26,9 @@ #define I915_REQUEST_H #include +#include #include +#include #include #include "gem/i915_gem_context_types.h" @@ -277,6 +279,12 @@ struct i915_request { /** timeline->request entry for this request */ struct list_head link; + /** Watchdog support fields. */ + struct i915_request_watchdog { + struct llist_node link; + struct hrtimer timer; + } watchdog; + I915_SELFTEST_DECLARE(struct { struct list_head link; unsigned long delay;