summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
diff options
context:
space:
mode:
authorTao Zhou <tao.zhou1@amd.com>2021-09-17 18:24:09 +0800
committerAlex Deucher <alexander.deucher@amd.com>2021-09-28 09:30:07 -0400
commite43488493cbb46e862f83c66887f3e6cb854c6f0 (patch)
tree1fc7e3f0c6aa1e68ad9809abbbc43d51e1e2fa2b /drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
parentaaca8c386136c27d199b318a1f3571d8a25edea3 (diff)
drm/amdgpu: set poison supported flag for RAS (v2)
Add RAS poison supported flag and tell PSP RAS TA about the info. v2: rename poison mode to poison supported, we can also disable poison mode even we support it. print value of poison supported if ras feature enablement fails. Signed-off-by: Tao Zhou <tao.zhou1@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@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.c32
1 files changed, 30 insertions, 2 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index e1c34eef76b7..4c547eee5702 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -710,10 +710,10 @@ int amdgpu_ras_feature_enable(struct amdgpu_device *adev,
if (!amdgpu_ras_intr_triggered()) {
ret = psp_ras_enable_features(&adev->psp, info, enable);
if (ret) {
- dev_err(adev->dev, "ras %s %s failed %d\n",
+ dev_err(adev->dev, "ras %s %s failed poison:%d ret:%d\n",
enable ? "enable":"disable",
get_ras_block_str(head),
- ret);
+ amdgpu_ras_is_poison_mode_supported(adev), ret);
goto out;
}
}
@@ -2238,6 +2238,7 @@ int amdgpu_ras_init(struct amdgpu_device *adev)
{
struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
int r;
+ bool df_poison, umc_poison;
if (con)
return 0;
@@ -2308,6 +2309,23 @@ int amdgpu_ras_init(struct amdgpu_device *adev)
goto release_con;
}
+ /* Init poison supported flag, the default value is false */
+ if (adev->df.funcs &&
+ adev->df.funcs->query_ras_poison_mode &&
+ adev->umc.ras_funcs &&
+ adev->umc.ras_funcs->query_ras_poison_mode) {
+ df_poison =
+ adev->df.funcs->query_ras_poison_mode(adev);
+ umc_poison =
+ adev->umc.ras_funcs->query_ras_poison_mode(adev);
+ /* Only poison is set in both DF and UMC, we can support it */
+ if (df_poison && umc_poison)
+ con->poison_supported = true;
+ else if (df_poison != umc_poison)
+ dev_warn(adev->dev, "Poison setting is inconsistent in DF/UMC(%d:%d)!\n",
+ df_poison, umc_poison);
+ }
+
if (amdgpu_ras_fs_init(adev)) {
r = -EINVAL;
goto release_con;
@@ -2351,6 +2369,16 @@ static int amdgpu_persistent_edc_harvesting(struct amdgpu_device *adev,
return 0;
}
+bool amdgpu_ras_is_poison_mode_supported(struct amdgpu_device *adev)
+{
+ struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+
+ if (!con)
+ return false;
+
+ return con->poison_supported;
+}
+
/* helper function to handle common stuff in ip late init phase */
int amdgpu_ras_late_init(struct amdgpu_device *adev,
struct ras_common_if *ras_block,