This is a note to let you know that I've just added the patch titled
drm/amdkfd: Fix eviction fence handling
to the 6.8-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
drm-amdkfd-fix-eviction-fence-handling.patch
and it can be found in the queue-6.8 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From 37865e02e6ccecdda240f33b4332105a5c734984 Mon Sep 17 00:00:00 2001
From: Felix Kuehling <felix.kuehling@xxxxxxx>
Date: Wed, 17 Apr 2024 21:13:59 -0400
Subject: drm/amdkfd: Fix eviction fence handling
From: Felix Kuehling <felix.kuehling@xxxxxxx>
commit 37865e02e6ccecdda240f33b4332105a5c734984 upstream.
Handle case that dma_fence_get_rcu_safe returns NULL.
If restore work is already scheduled, only update its timer. The same
work item cannot be queued twice, so undo the extra queue eviction.
Fixes: 9a1c1339abf9 ("drm/amdkfd: Run restore_workers on freezable WQs")
Signed-off-by: Felix Kuehling <felix.kuehling@xxxxxxx>
Reviewed-by: Philip Yang <Philip.Yang@xxxxxxx>
Tested-by: Gang BA <Gang.Ba@xxxxxxx>
Reviewed-by: Gang BA <Gang.Ba@xxxxxxx>
Signed-off-by: Alex Deucher <alexander.deucher@xxxxxxx>
Cc: stable@xxxxxxxxxxxxxxx
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
drivers/gpu/drm/amd/amdkfd/kfd_process.c | 9 +++++----
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index b79986412cd8..aafdf064651f 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -1922,6 +1922,8 @@ static int signal_eviction_fence(struct kfd_process *p)
rcu_read_lock();
ef = dma_fence_get_rcu_safe(&p->ef);
rcu_read_unlock();
+ if (!ef)
+ return -EINVAL;
ret = dma_fence_signal(ef);
dma_fence_put(ef);
@@ -1949,10 +1951,9 @@ static void evict_process_worker(struct work_struct *work)
* they are responsible stopping the queues and scheduling
* the restore work.
*/
- if (!signal_eviction_fence(p))
- queue_delayed_work(kfd_restore_wq, &p->restore_work,
- msecs_to_jiffies(PROCESS_RESTORE_TIME_MS));
- else
+ if (signal_eviction_fence(p) ||
+ mod_delayed_work(kfd_restore_wq, &p->restore_work,
+ msecs_to_jiffies(PROCESS_RESTORE_TIME_MS)))
kfd_process_restore_queues(p);
pr_debug("Finished evicting pasid 0x%x\n", p->pasid);
--
2.44.0
Patches currently in stable-queue which might be from felix.kuehling@xxxxxxx are
queue-6.8/drm-amdkfd-fix-eviction-fence-handling.patch
queue-6.8/drm-amdkfd-fix-rescheduling-of-restore-worker.patch
