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

6 files changed, 46 insertions, 0 deletions

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 <linux/llist.h>
 #include <linux/types.h>
 
 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(&gt->closed_vma);
 	spin_lock_init(&gt->closed_lock);
 
+	init_llist_head(&gt->watchdog.list);
+	INIT_WORK(&gt->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(&gt->requests.retire_work);
+
+	flush_work(&gt->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(&gt->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 <linux/ktime.h>
 #include <linux/list.h>
+#include <linux/llist.h>
 #include <linux/mutex.h>
 #include <linux/notifier.h>
 #include <linux/spinlock.h>
 #include <linux/types.h>
+#include <linux/workqueue.h>
 
 #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;