summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
diff options
context:
space:
mode:
authorDave Airlie <airlied@redhat.com>2025-05-12 07:14:27 +1000
committerDave Airlie <airlied@redhat.com>2025-05-12 07:14:34 +1000
commit1faeeb315fdbd005bbc1bc74214e39087971dda9 (patch)
treed390ef6948a417cd63a252e70cef96bbb0bd5434 /drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
parentf9fa01229339daea915c8f2a3df8d6f6a89f9b84 (diff)
parentafc6053d4c4b0a6be500b9e643aa17221e93a57b (diff)
Merge tag 'amd-drm-next-6.16-2025-05-09' of https://gitlab.freedesktop.org/agd5f/linux into drm-next
amd-drm-next-6.16-2025-05-09: amdgpu: - IPS fixes - DSC cleanup - DC Scaling updates - DC FP fixes - Fused I2C-over-AUX updates - SubVP fixes - Freesync fix - DMUB AUX fixes - VCN fix - Hibernation fixes - HDP fixes - DCN 2.1 fixes - DPIA fixes - DMUB updates - Use drm_file_err in amdgpu - Enforce isolation updates - Use new dma_fence helpers - USERQ fixes - Documentation updates - Misc code cleanups - SR-IOV updates - RAS updates - PSP 12 cleanups amdkfd: - Update error messages for SDMA - Userptr updates drm: - Add drm_file_err function dma-buf: - Add a helper to sort and deduplicate dma_fence arrays From: Alex Deucher <alexander.deucher@amd.com> Link: https://lore.kernel.org/r/20250509230951.3871914-1-alexander.deucher@amd.com Signed-off-by: Dave Airlie <airlied@redhat.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c15
1 files changed, 10 insertions, 5 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 443409d4f4b0..f40b35f7f679 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1498,6 +1498,9 @@ int amdgpu_ras_reset_error_count(struct amdgpu_device *adev,
!amdgpu_ras_get_aca_debug_mode(adev))
return -EOPNOTSUPP;
+ if (amdgpu_sriov_vf(adev))
+ return -EOPNOTSUPP;
+
/* skip ras error reset in gpu reset */
if ((amdgpu_in_reset(adev) || amdgpu_ras_in_recovery(adev)) &&
((smu_funcs && smu_funcs->set_debug_mode) ||
@@ -2161,7 +2164,7 @@ void amdgpu_ras_interrupt_fatal_error_handler(struct amdgpu_device *adev)
/* Fatal error events are handled on host side */
if (amdgpu_sriov_vf(adev))
return;
- /**
+ /*
* If the current interrupt is caused by a non-fatal RAS error, skip
* check for fatal error. For fatal errors, FED status of all devices
* in XGMI hive gets set when the first device gets fatal error
@@ -3793,10 +3796,12 @@ init_ras_enabled_flag:
adev->ras_hw_enabled & amdgpu_ras_mask;
/* aca is disabled by default except for psp v13_0_6/v13_0_12/v13_0_14 */
- adev->aca.is_enabled =
- (amdgpu_ip_version(adev, MP0_HWIP, 0) == IP_VERSION(13, 0, 6) ||
- amdgpu_ip_version(adev, MP0_HWIP, 0) == IP_VERSION(13, 0, 12) ||
- amdgpu_ip_version(adev, MP0_HWIP, 0) == IP_VERSION(13, 0, 14));
+ if (!amdgpu_sriov_vf(adev)) {
+ adev->aca.is_enabled =
+ (amdgpu_ip_version(adev, MP0_HWIP, 0) == IP_VERSION(13, 0, 6) ||
+ amdgpu_ip_version(adev, MP0_HWIP, 0) == IP_VERSION(13, 0, 12) ||
+ amdgpu_ip_version(adev, MP0_HWIP, 0) == IP_VERSION(13, 0, 14));
+ }
/* bad page feature is not applicable to specific app platform */
if (adev->gmc.is_app_apu &&