drm/sched: Avoid lockdep spalt on killing a processes

[ Upstream commit 542cff7 ]

Probelm:
Singlaning one sched fence from within another's sched
fence singal callback generates lockdep splat because
the both have same lockdep class of their fence->lock

Fix:
Fix bellow stack by rescheduling to irq work of
signaling and killing of jobs that left when entity is killed.

[11176.741181]  dump_stack+0x10/0x12
[11176.741186] __lock_acquire.cold+0x208/0x2df
[11176.741197]  lock_acquire+0xc6/0x2d0
[11176.741204]  ? dma_fence_signal+0x28/0x80
[11176.741212] _raw_spin_lock_irqsave+0x4d/0x70
[11176.741219]  ? dma_fence_signal+0x28/0x80
[11176.741225]  dma_fence_signal+0x28/0x80
[11176.741230] drm_sched_fence_finished+0x12/0x20 [gpu_sched]
[11176.741240] drm_sched_entity_kill_jobs_cb+0x1c/0x50 [gpu_sched]
[11176.741248] dma_fence_signal_timestamp_locked+0xac/0x1a0
[11176.741254]  dma_fence_signal+0x3b/0x80
[11176.741260] drm_sched_fence_finished+0x12/0x20 [gpu_sched]
[11176.741268] drm_sched_job_done.isra.0+0x7f/0x1a0 [gpu_sched]
[11176.741277] drm_sched_job_done_cb+0x12/0x20 [gpu_sched]
[11176.741284] dma_fence_signal_timestamp_locked+0xac/0x1a0
[11176.741290]  dma_fence_signal+0x3b/0x80
[11176.741296] amdgpu_fence_process+0xd1/0x140 [amdgpu]
[11176.741504] sdma_v4_0_process_trap_irq+0x8c/0xb0 [amdgpu]
[11176.741731]  amdgpu_irq_dispatch+0xce/0x250 [amdgpu]
[11176.741954]  amdgpu_ih_process+0x81/0x100 [amdgpu]
[11176.742174]  amdgpu_irq_handler+0x26/0xa0 [amdgpu]
[11176.742393] __handle_irq_event_percpu+0x4f/0x2c0
[11176.742402] handle_irq_event_percpu+0x33/0x80
[11176.742408]  handle_irq_event+0x39/0x60
[11176.742414]  handle_edge_irq+0x93/0x1d0
[11176.742419]  __common_interrupt+0x50/0xe0
[11176.742426]  common_interrupt+0x80/0x90

Signed-off-by: Andrey Grodzovsky <[email protected]>
Suggested-by: Daniel Vetter  <[email protected]>
Suggested-by: Christian König <[email protected]>
Tested-by: Christian König <[email protected]>
Reviewed-by: Christian König <[email protected]>
Link: https://www.spinics.net/lists/dri-devel/msg321250.html
Signed-off-by: Sasha Levin <[email protected]>

Author: Andrey Grodzovsky

drivers/gpu/drm/scheduler/sched_entity.c

@@ -190,16 +190,25 @@ long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout)
 }
 EXPORT_SYMBOL(drm_sched_entity_flush);
 
+static void drm_sched_entity_kill_jobs_irq_work(struct irq_work *wrk)
+{
+	struct drm_sched_job *job = container_of(wrk, typeof(*job), work);
+
+	drm_sched_fence_finished(job->s_fence);
+	WARN_ON(job->s_fence->parent);
+	job->sched->ops->free_job(job);
+}
+
+
 /* Signal the scheduler finished fence when the entity in question is killed. */
 static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
 					  struct dma_fence_cb *cb)
 {
 	struct drm_sched_job *job = container_of(cb, struct drm_sched_job,
 						 finish_cb);
 
-	drm_sched_fence_finished(job->s_fence);
-	WARN_ON(job->s_fence->parent);
-	job->sched->ops->free_job(job);
+	init_irq_work(&job->work, drm_sched_entity_kill_jobs_irq_work);
+	irq_work_queue(&job->work);
 }
 
 static struct dma_fence *

include/drm/gpu_scheduler.h

@@ -28,6 +28,7 @@
 #include <linux/dma-fence.h>
 #include <linux/completion.h>
 #include <linux/xarray.h>
+#include <linux/irq_work.h>
 
 #define MAX_WAIT_SCHED_ENTITY_Q_EMPTY msecs_to_jiffies(1000)
 
@@ -286,7 +287,16 @@ struct drm_sched_job {
 	struct list_head		list;
 	struct drm_gpu_scheduler	*sched;
 	struct drm_sched_fence		*s_fence;
-	struct dma_fence_cb		finish_cb;
+
+	/*
+	 * work is used only after finish_cb has been used and will not be
+	 * accessed anymore.
+	 */
+	union {
+		struct dma_fence_cb		finish_cb;
+		struct irq_work 		work;
+	};
+
 	uint64_t			id;
 	atomic_t			karma;
 	enum drm_sched_priority		s_priority;