Patch "amd/amdkfd: sync all devices to wait all processes being evicted" has been added to the 6.6-stable tree

[Sasha Levin <sashal@xxxxxxxxxx>]

This is a note to let you know that I've just added the patch titled

    amd/amdkfd: sync all devices to wait all processes being evicted

to the 6.6-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:
     amd-amdkfd-sync-all-devices-to-wait-all-processes-be.patch
and it can be found in the queue-6.6 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.



commit 69375c526c12f321851c281ef74d474689c79e2c
Author: Zhigang Luo <Zhigang.Luo@xxxxxxx>
Date:   Mon Mar 18 14:13:10 2024 -0400

    amd/amdkfd: sync all devices to wait all processes being evicted
    
    [ Upstream commit d06af584be5a769d124b7302b32a033e9559761d ]
    
    If there are more than one device doing reset in parallel, the first
    device will call kfd_suspend_all_processes() to evict all processes
    on all devices, this call takes time to finish. other device will
    start reset and recover without waiting. if the process has not been
    evicted before doing recover, it will be restored, then caused page
    fault.
    
    Signed-off-by: Zhigang Luo <Zhigang.Luo@xxxxxxx>
    Reviewed-by: Felix Kuehling <felix.kuehling@xxxxxxx>
    Signed-off-by: Alex Deucher <alexander.deucher@xxxxxxx>
    Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 93ce181eb3baa..913c70a0ef44f 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -935,7 +935,6 @@ void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm)
 {
 	struct kfd_node *node;
 	int i;
-	int count;
 
 	if (!kfd->init_complete)
 		return;
@@ -943,12 +942,10 @@ void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm)
 	/* for runtime suspend, skip locking kfd */
 	if (!run_pm) {
 		mutex_lock(&kfd_processes_mutex);
-		count = ++kfd_locked;
-		mutex_unlock(&kfd_processes_mutex);
-
 		/* For first KFD device suspend all the KFD processes */
-		if (count == 1)
+		if (++kfd_locked == 1)
 			kfd_suspend_all_processes();
+		mutex_unlock(&kfd_processes_mutex);
 	}
 
 	for (i = 0; i < kfd->num_nodes; i++) {
@@ -959,7 +956,7 @@ void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm)
 
 int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm)
 {
-	int ret, count, i;
+	int ret, i;
 
 	if (!kfd->init_complete)
 		return 0;
@@ -973,12 +970,10 @@ int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm)
 	/* for runtime resume, skip unlocking kfd */
 	if (!run_pm) {
 		mutex_lock(&kfd_processes_mutex);
-		count = --kfd_locked;
-		mutex_unlock(&kfd_processes_mutex);
-
-		WARN_ONCE(count < 0, "KFD suspend / resume ref. error");
-		if (count == 0)
+		if (--kfd_locked == 0)
 			ret = kfd_resume_all_processes();
+		WARN_ONCE(kfd_locked < 0, "KFD suspend / resume ref. error");
+		mutex_unlock(&kfd_processes_mutex);
 	}
 
 	return ret;