drm/i915: Request watchdog infrastructure

Prepares the plumbing for setting request/fence expiration time. All code
is put in place but is never activated due yet missing ability to actually
configure the timer.

Outline of the basic operation:

A timer is started when request is ready for execution. If the request
completes (retires) before the timer fires, timer is cancelled and nothing
further happens.

If the timer fires request is added to a lockless list and worker queued.
Purpose of this is twofold: a) It allows request cancellation from a more
friendly context and b) coalesces multiple expirations into a single event
of consuming the list.

Worker locklessly consumes the list of expired requests and cancels them
all using previous added i915_request_cancel().

Associated timeout value is stored in rq->context.watchdog.timeout_us.

v2:
 * Log expiration.

v3:
 * Include more information about user timeline in the log message.

v4:
 * Remove obsolete comment and fix formatting. (Matt)

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20210324121335.2307063-6-tvrtko.ursulin@linux.intel.com

1 files changed, 52 insertions, 0 deletions

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, &gt->watchdog.list))
+			schedule_work(&gt->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));