tmakin/tegra-linux-noble
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

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

Browse Source 
BugLink: https://bugs.launchpad.net/bugs/2070349

[ 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@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Manuel Diewald <manuel.diewald@canonical.com>
Signed-off-by: Stefan Bader <stefan.bader@canonical.com>
This commit is contained in:
Zhigang Luo
2024-03-18 14:13:10 -04:00
committed by Stefan Bader
parent 7e3ef96a6a
commit 9bcce856f8
1 changed files with 6 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
drivers/gpu/drm/amd/amdkfd/kfd_device.c
+6 -11
View File
@@ -944,7 +944,6 @@ void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm)
{
struct kfd_node *node;
int i;
int count;
if (!kfd->init_complete)
return;
@@ -952,12 +951,10 @@ 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++) {
@@ -968,7 +965,7 @@ 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;
@@ -982,12 +979,10 @@ 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;