[PATCH] drm/amdkfd: Restore all process on post reset

[Eric Huang]

It is to fix a bug of gpu_recovery on multiple GPUs,
When one gpu is reset, the application running on other
gpu hangs, because kfd post reset doesn't restore the
running process. And it also fixes a bug in the function
kfd_process_evict_queues, when one gpu hangs, process
running on other gpus can't be evicted.

Signed-off-by: Eric Huang <jinhuieric.hu...@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_device.c  |  2 +-
 drivers/gpu/drm/amd/amdkfd/kfd_process.c | 24 +-----------------------
 2 files changed, 2 insertions(+), 24 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c 
b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 24b5e0aa1eac..daf1c19bd799 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -984,7 +984,7 @@ int kgd2kfd_post_reset(struct kfd_dev *kfd)
        if (!kfd->init_complete)
                return 0;
 
-       ret = kfd_resume(kfd);
+       ret = kgd2kfd_resume(kfd, false, true);
        if (ret)
                return ret;
        atomic_dec(&kfd_locked);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c 
b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 38a9dee40785..9272a12c1db8 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -1879,36 +1879,14 @@ int kfd_process_evict_queues(struct kfd_process *p)
 {
        int r = 0;
        int i;
-       unsigned int n_evicted = 0;
 
        for (i = 0; i < p->n_pdds; i++) {
                struct kfd_process_device *pdd = p->pdds[i];
 
                r = pdd->dev->dqm->ops.evict_process_queues(pdd->dev->dqm,
                                                            &pdd->qpd);
-               if (r) {
+               if (r)
                        pr_err("Failed to evict process queues\n");
-                       goto fail;
-               }
-               n_evicted++;
-       }
-
-       return r;
-
-fail:
-       /* To keep state consistent, roll back partial eviction by
-        * restoring queues
-        */
-       for (i = 0; i < p->n_pdds; i++) {
-               struct kfd_process_device *pdd = p->pdds[i];
-
-               if (n_evicted == 0)
-                       break;
-               if (pdd->dev->dqm->ops.restore_process_queues(pdd->dev->dqm,
-                                                             &pdd->qpd))
-                       pr_err("Failed to restore queues\n");
-
-               n_evicted--;
        }
 
        return r;
-- 
2.25.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx