summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
diff options
context:
space:
mode:
authorLuben Tuikov <luben.tuikov@amd.com>2021-04-29 20:15:42 -0400
committerAlex Deucher <alexander.deucher@amd.com>2021-07-01 00:25:33 -0400
commit1d9d2ca85b32605ac9c74c8fa42d0c1cfbe019d4 (patch)
treea8c19dff506f3d0434b3ac9b18c4653e40d483b5 /drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
parentd456f3875af2eb5bf5a9cbd526622801ffc51037 (diff)
drm/amdgpu: Fix koops when accessing RAS EEPROM
Debugfs RAS EEPROM files are available when the ASIC supports RAS, and when the debugfs is enabled, an also when "ras_enable" module parameter is set to 0. However in this case, we get a kernel oops when accessing some of the "ras_..." controls in debugfs. The reason for this is that struct amdgpu_ras::adev is unset. This commit sets it, thus enabling access to those facilities. Note that this facilitates EEPROM access and not necessarily RAS features or functionality. Cc: Alexander Deucher <Alexander.Deucher@amd.com> Cc: John Clements <john.clements@amd.com> Cc: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Luben Tuikov <luben.tuikov@amd.com> Acked-by: Alexander Deucher <Alexander.Deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c16
1 files changed, 12 insertions, 4 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 53a54ff8edc3..875874ea745e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1947,11 +1947,20 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev)
bool exc_err_limit = false;
int ret;
- if (adev->ras_enabled && con)
- data = &con->eh_data;
- else
+ if (!con)
+ return 0;
+
+ /* Allow access to RAS EEPROM via debugfs, when the ASIC
+ * supports RAS and debugfs is enabled, but when
+ * adev->ras_enabled is unset, i.e. when "ras_enable"
+ * module parameter is set to 0.
+ */
+ con->adev = adev;
+
+ if (!adev->ras_enabled)
return 0;
+ data = &con->eh_data;
*data = kmalloc(sizeof(**data), GFP_KERNEL | __GFP_ZERO);
if (!*data) {
ret = -ENOMEM;
@@ -1961,7 +1970,6 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev)
mutex_init(&con->recovery_lock);
INIT_WORK(&con->recovery_work, amdgpu_ras_do_recovery);
atomic_set(&con->in_recovery, 0);
- con->adev = adev;
max_eeprom_records_count = amdgpu_ras_eeprom_max_record_count();
amdgpu_ras_validate_threshold(adev, max_eeprom_records_count);