drm/amdgpu: update ras capability's query based on mem ecc configuration

RAS support capability needs to be updated on top of different
memeory ECC enablement, and remove redundant memory ecc check
in gmc module for vega20 and arcturus.

v2: check HBM ECC enablement and set ras mask accordingly.
v3: avoid to invoke atomfirmware interface to query twice.

Suggested-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Guchun Chen <guchun.chen@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index ce8548d..c3dca4c 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1765,18 +1765,30 @@ static void amdgpu_ras_check_supported(struct amdgpu_device *adev,
        *hw_supported = 0;
        *supported = 0;
 
-       if (amdgpu_sriov_vf(adev) ||
+       if (amdgpu_sriov_vf(adev) || !adev->is_atom_fw ||
            (adev->asic_type != CHIP_VEGA20 &&
             adev->asic_type != CHIP_ARCTURUS))
                return;
 
-       if (adev->is_atom_fw &&
-                       (amdgpu_atomfirmware_mem_ecc_supported(adev) ||
-                        amdgpu_atomfirmware_sram_ecc_supported(adev)))
-               *hw_supported = AMDGPU_RAS_BLOCK_MASK;
+       if (amdgpu_atomfirmware_mem_ecc_supported(adev)) {
+               DRM_INFO("HBM ECC is active.\n");
+               *hw_supported |= (1 << AMDGPU_RAS_BLOCK__UMC |
+                               1 << AMDGPU_RAS_BLOCK__DF);
+       } else
+               DRM_INFO("HBM ECC is not presented.\n");
+
+       if (amdgpu_atomfirmware_sram_ecc_supported(adev)) {
+               DRM_INFO("SRAM ECC is active.\n");
+               *hw_supported |= ~(1 << AMDGPU_RAS_BLOCK__UMC |
+                               1 << AMDGPU_RAS_BLOCK__DF);
+       } else
+               DRM_INFO("SRAM ECC is not presented.\n");
+
+       /* hw_supported needs to be aligned with RAS block mask. */
+       *hw_supported &= AMDGPU_RAS_BLOCK_MASK;
 
        *supported = amdgpu_ras_enable == 0 ?
-                               0 : *hw_supported & amdgpu_ras_mask;
+                       0 : *hw_supported & amdgpu_ras_mask;
 }
 
 int amdgpu_ras_init(struct amdgpu_device *adev)

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 6ceaab5..8606f87 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -922,30 +922,20 @@ static int gmc_v9_0_late_init(void *handle)
        if (r)
                return r;
        /* Check if ecc is available */
-       if (!amdgpu_sriov_vf(adev)) {
-               switch (adev->asic_type) {
-               case CHIP_VEGA10:
-               case CHIP_VEGA20:
-               case CHIP_ARCTURUS:
-                       r = amdgpu_atomfirmware_mem_ecc_supported(adev);
-                       if (!r) {
-                               DRM_INFO("ECC is not present.\n");
-                               if (adev->df.funcs->enable_ecc_force_par_wr_rmw)
-                                       adev->df.funcs->enable_ecc_force_par_wr_rmw(adev, false);
-                       } else {
-                               DRM_INFO("ECC is active.\n");
-                       }
-
-                       r = amdgpu_atomfirmware_sram_ecc_supported(adev);
-                       if (!r) {
-                               DRM_INFO("SRAM ECC is not present.\n");
-                       } else {
-                               DRM_INFO("SRAM ECC is active.\n");
-                       }
-                       break;
-               default:
-                       break;
-               }
+       if (!amdgpu_sriov_vf(adev) && (adev->asic_type == CHIP_VEGA10)) {
+               r = amdgpu_atomfirmware_mem_ecc_supported(adev);
+               if (!r) {
+                       DRM_INFO("ECC is not present.\n");
+                       if (adev->df.funcs->enable_ecc_force_par_wr_rmw)
+                               adev->df.funcs->enable_ecc_force_par_wr_rmw(adev, false);
+               } else
+                       DRM_INFO("ECC is active.\n");
+
+               r = amdgpu_atomfirmware_sram_ecc_supported(adev);
+               if (!r)
+                       DRM_INFO("SRAM ECC is not present.\n");
+               else
+                       DRM_INFO("SRAM ECC is active.\n");
        }
 
        if (adev->mmhub.funcs && adev->mmhub.funcs->reset_ras_error_count)