diff options
| author | Lijo Lazar <lijo.lazar@amd.com> | 2025-06-13 16:30:30 +0530 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2025-06-18 12:19:21 -0400 |
| commit | 04141c05f36afe6d053a964fd2c609d4744d19e5 (patch) | |
| tree | 05d1d09bc4357505a6996eaadbc02b2a0eb6c3a9 /drivers/gpu/drm/amd/amdgpu | |
| parent | 167049012e693ddffb888b61905962a45b75ca95 (diff) | |
drm/amdgpu: Extend bus status check to more cases
In case of unexpected errors, check if device is alive on the bus.
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu.h | 15 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 7 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c | 5 |
3 files changed, 20 insertions, 7 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 5e2f086d2c99..42278e9a2d75 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1762,4 +1762,19 @@ extern const struct attribute_group amdgpu_flash_attr_group; void amdgpu_set_init_level(struct amdgpu_device *adev, enum amdgpu_init_lvl_id lvl); + +static inline int amdgpu_device_bus_status_check(struct amdgpu_device *adev) +{ + u32 status; + int r; + + r = pci_read_config_dword(adev->pdev, PCI_COMMAND, &status); + if (r || PCI_POSSIBLE_ERROR(status)) { + dev_err(adev->dev, "device lost from bus!"); + return -ENODEV; + } + + return 0; +} + #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index dbe36fdb0a3c..c2d10be53d3e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -6071,14 +6071,9 @@ static int amdgpu_device_health_check(struct list_head *device_list_handle) { struct amdgpu_device *tmp_adev; int ret = 0; - u32 status; list_for_each_entry(tmp_adev, device_list_handle, reset_list) { - pci_read_config_dword(tmp_adev->pdev, PCI_COMMAND, &status); - if (PCI_POSSIBLE_ERROR(status)) { - dev_err(tmp_adev->dev, "device lost from bus!"); - ret = -ENODEV; - } + ret |= amdgpu_device_bus_status_check(tmp_adev); } return ret; diff --git a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c index 1c083304ae77..41acc1ce0b3e 100644 --- a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c +++ b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c @@ -353,11 +353,14 @@ static int aqua_vanjaram_query_partition_mode(struct amdgpu_xcp_mgr *xcp_mgr) if (adev->nbio.funcs->get_compute_partition_mode) { mode = adev->nbio.funcs->get_compute_partition_mode(adev); - if (mode != derv_mode) + if (mode != derv_mode) { dev_warn( adev->dev, "Mismatch in compute partition mode - reported : %d derived : %d", mode, derv_mode); + if (derv_mode == AMDGPU_UNKNOWN_COMPUTE_PARTITION_MODE) + amdgpu_device_bus_status_check(adev); + } } return mode; |