From 37865e02e6ccecdda240f33b4332105a5c734984 Mon Sep 17 00:00:00 2001 From: Felix Kuehling Date: Wed, 17 Apr 2024 21:13:59 -0400 Subject: drm/amdkfd: Fix eviction fence handling 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 Reviewed-by: Philip Yang Tested-by: Gang BA Reviewed-by: Gang BA Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- 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 b79986412cd839..aafdf064651fae 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); -- cgit 1.2.3-korg