[PATCH 1/2] drm/amdgpu: split ras_eeprom_init into init and check functions

Tao Zhou tao.zhou1 at amd.com
Mon Dec 2 10:24:32 UTC 2024


Init function is for ras table header read and check function is
responsible for the validation of the header. Call them in different
stages.

Signed-off-by: Tao Zhou <tao.zhou1 at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c       | 15 ++++++++++----
 .../gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c    | 20 +++++++++++++++++++
 .../gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h    |  2 ++
 3 files changed, 33 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 98bd2ff5aed9..da072ab3fb5c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -3006,9 +3006,20 @@ static int amdgpu_ras_load_bad_pages(struct amdgpu_device *adev)
 				control->rec_type = AMDGPU_RAS_EEPROM_REC_MCA;
 		}
 
+		ret = amdgpu_ras_eeprom_check(control);
+		if (ret)
+			goto out;
+
+		/* HW not usable */
+		if (amdgpu_ras_is_rma(adev)) {
+			ret = -EHWPOISON;
+			goto out;
+		}
+
 		ret = amdgpu_ras_add_bad_pages(adev, bps, control->ras_num_recs, true);
 	}
 
+out:
 	kfree(bps);
 	return ret;
 }
@@ -3407,10 +3418,6 @@ int amdgpu_ras_init_badpage_info(struct amdgpu_device *adev)
 	if (ret)
 		return ret;
 
-	/* HW not usable */
-	if (amdgpu_ras_is_rma(adev))
-		return -EHWPOISON;
-
 	if (!adev->umc.ras || !adev->umc.ras->convert_ras_err_addr)
 		control->rec_type = AMDGPU_RAS_EEPROM_REC_PA;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index f4a9e15389ae..9dae4ac2f5d0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -1382,6 +1382,26 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control)
 	}
 	control->ras_fri = RAS_OFFSET_TO_INDEX(control, hdr->first_rec_offset);
 
+	return res < 0 ? res : 0;
+}
+
+int amdgpu_ras_eeprom_check(struct amdgpu_ras_eeprom_control *control)
+{
+	struct amdgpu_device *adev = to_amdgpu_device(control);
+	struct amdgpu_ras_eeprom_table_header *hdr = &control->tbl_hdr;
+	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
+	int res;
+
+	if (!__is_ras_eeprom_supported(adev))
+		return 0;
+
+	/* Verify i2c adapter is initialized */
+	if (!adev->pm.ras_eeprom_i2c_bus || !adev->pm.ras_eeprom_i2c_bus->algo)
+		return -ENOENT;
+
+	if (!__get_eeprom_i2c_addr(adev, control))
+		return -EINVAL;
+
 	if (hdr->header == RAS_TABLE_HDR_VAL) {
 		DRM_DEBUG_DRIVER("Found existing EEPROM table with %d records",
 				 control->ras_num_recs);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
index d3a6f7205a2f..b87422df52fd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
@@ -159,6 +159,8 @@ uint32_t amdgpu_ras_eeprom_max_record_count(struct amdgpu_ras_eeprom_control *co
 
 void amdgpu_ras_debugfs_set_ret_size(struct amdgpu_ras_eeprom_control *control);
 
+int amdgpu_ras_eeprom_check(struct amdgpu_ras_eeprom_control *control);
+
 extern const struct file_operations amdgpu_ras_debugfs_eeprom_size_ops;
 extern const struct file_operations amdgpu_ras_debugfs_eeprom_table_ops;
 
-- 
2.34.1



More information about the amd-gfx mailing list