summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
diff options
context:
space:
mode:
authorThomas Hellström <thomas.hellstrom@linux.intel.com>2025-12-04 22:54:56 +0100
committerThomas Hellström <thomas.hellstrom@linux.intel.com>2025-12-04 22:54:56 +0100
commit3f1c07fc21c68bd3bd2df9d2c9441f6485e934d9 (patch)
tree2bbe746323ca53170b1c6f18f67178021d5854f5 /drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
parentd72312d730450aab225a80bc84436757b85b08b5 (diff)
parent0692602defb0c273f80dec9c564ca50726404aca (diff)
Merge drm/drm-next into drm-xe-next-fixes
Backmerging to be able do to a clean PR. Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c28
1 files changed, 27 insertions, 1 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 9e2e098af86c..2a6cf7963dde 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -150,6 +150,8 @@ static void amdgpu_ras_critical_region_fini(struct amdgpu_device *adev);
#ifdef CONFIG_X86_MCE_AMD
static void amdgpu_register_bad_pages_mca_notifier(struct amdgpu_device *adev);
+static void
+amdgpu_unregister_bad_pages_mca_notifier(struct amdgpu_device *adev);
struct mce_notifier_adev_list {
struct amdgpu_device *devs[MAX_GPU_INSTANCE];
int num_gpu;
@@ -3954,7 +3956,9 @@ static int amdgpu_ras_recovery_fini(struct amdgpu_device *adev)
mutex_unlock(&con->recovery_lock);
amdgpu_ras_critical_region_init(adev);
-
+#ifdef CONFIG_X86_MCE_AMD
+ amdgpu_unregister_bad_pages_mca_notifier(adev);
+#endif
return 0;
}
/* recovery end */
@@ -4988,6 +4992,28 @@ static void amdgpu_register_bad_pages_mca_notifier(struct amdgpu_device *adev)
notifier_registered = true;
}
}
+static void amdgpu_unregister_bad_pages_mca_notifier(struct amdgpu_device *adev)
+{
+ int i, j;
+
+ if (!notifier_registered && !mce_adev_list.num_gpu)
+ return;
+ for (i = 0, j = 0; i < mce_adev_list.num_gpu; i++) {
+ if (mce_adev_list.devs[i] == adev)
+ mce_adev_list.devs[i] = NULL;
+ if (!mce_adev_list.devs[i])
+ ++j;
+ }
+
+ if (j == mce_adev_list.num_gpu) {
+ mce_adev_list.num_gpu = 0;
+ /* Unregister x86 notifier with MCE subsystem. */
+ if (notifier_registered) {
+ mce_unregister_decode_chain(&amdgpu_bad_page_nb);
+ notifier_registered = false;
+ }
+ }
+}
#endif
struct amdgpu_ras *amdgpu_ras_get_context(struct amdgpu_device *adev)