drm/scheduler: Avoid accessing freed bad job.

[ Upstream commit 135517d3565b48f4def3b1b82008bc17eb5d1c90 ]

Problem:
Due to a race between drm_sched_cleanup_jobs in sched thread and
drm_sched_job_timedout in timeout work there is a possiblity that
bad job was already freed while still being accessed from the
timeout thread.

Fix:
Instead of just peeking at the bad job in the mirror list
remove it from the list under lock and then put it back later when
we are garanteed no race with main sched thread is possible which
is after the thread is parked.

v2: Lock around processing ring_mirror_list in drm_sched_cleanup_jobs.

v3: Rebase on top of drm-misc-next. v2 is not needed anymore as
drm_sched_get_cleanup_job already has a lock there.

v4: Fix comments to relfect latest code in drm-misc.

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Emily Deng <Emily.Deng@amd.com>
Tested-by: Emily Deng <Emily.Deng@amd.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/342356
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 30c5ddd6d081c76ea9e6fbb9410636a20686e044..134e9106ebac1c7ff077bb051714e6e8fcf195a8 100644 (file)
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -284,10 +284,21 @@ static void drm_sched_job_timedout(struct work_struct *work)
        unsigned long flags;
 
        sched = container_of(work, struct drm_gpu_scheduler, work_tdr.work);
+
+       /* Protects against concurrent deletion in drm_sched_get_cleanup_job */
+       spin_lock_irqsave(&sched->job_list_lock, flags);
        job = list_first_entry_or_null(&sched->ring_mirror_list,
                                       struct drm_sched_job, node);
 
        if (job) {
+               /*
+                * Remove the bad job so it cannot be freed by concurrent
+                * drm_sched_cleanup_jobs. It will be reinserted back after sched->thread
+                * is parked at which point it's safe.
+                */
+               list_del_init(&job->node);
+               spin_unlock_irqrestore(&sched->job_list_lock, flags);
+
                job->sched->ops->timedout_job(job);
 
                /*
@@ -298,6 +309,8 @@ static void drm_sched_job_timedout(struct work_struct *work)
                        job->sched->ops->free_job(job);
                        sched->free_guilty = false;
                }
+       } else {
+               spin_unlock_irqrestore(&sched->job_list_lock, flags);
        }
 
        spin_lock_irqsave(&sched->job_list_lock, flags);
@@ -369,6 +382,20 @@ void drm_sched_stop(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad)
 
        kthread_park(sched->thread);
 
+       /*
+        * Reinsert back the bad job here - now it's safe as
+        * drm_sched_get_cleanup_job cannot race against us and release the
+        * bad job at this point - we parked (waited for) any in progress
+        * (earlier) cleanups and drm_sched_get_cleanup_job will not be called
+        * now until the scheduler thread is unparked.
+        */
+       if (bad && bad->sched == sched)
+               /*
+                * Add at the head of the queue to reflect it was the earliest
+                * job extracted.
+                */
+               list_add(&bad->node, &sched->ring_mirror_list);
+
        /*
         * Iterate the job list from later to  earlier one and either deactive
         * their HW callbacks or remove them from mirror list if they already