Commit e1ca536e authored by Tao Zhou's avatar Tao Zhou Committed by Alex Deucher
Browse files

drm/amdgpu: support to load RAS bad pages from PMFW 



PMFW manages eeprom bad page records, update bad page loading
accrodingly.

Signed-off-by: default avatarTao Zhou <tao.zhou1@amd.com>
Reviewed-by: default avatarHawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: default avatarAlex Deucher <alexander.deucher@amd.com>
parent 1ad25fd2

drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c

+10 −4
Original line number Diff line number Diff line
@@ -3158,8 +3158,12 @@ static int __amdgpu_ras_convert_rec_from_rom(struct amdgpu_device *adev, 
	int i = 0;

	enum amdgpu_memory_partition save_nps;



	if (!amdgpu_ras_smu_eeprom_supported(adev)) {

		save_nps = (bps->retired_page >> UMC_NPS_SHIFT) & UMC_NPS_MASK;

		bps->retired_page &= ~(UMC_NPS_MASK << UMC_NPS_SHIFT);

	} else {

		save_nps = nps;

	}



	if (save_nps == nps) {

		if (amdgpu_umc_pages_in_a_row(adev, err_data,
@@ -3225,7 +3229,8 @@ int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev, 


	if (from_rom) {

		/* there is no pa recs in V3, so skip pa recs processing */

		if (control->tbl_hdr.version < RAS_TABLE_VER_V3) {

		if ((control->tbl_hdr.version < RAS_TABLE_VER_V3) &&

		    !amdgpu_ras_smu_eeprom_supported(adev)) {

			for (i = 0; i < pages; i++) {

				if (control->ras_num_recs - i >= adev->umc.retire_unit) {

					if ((bps[i].address == bps[i + 1].address) &&
@@ -3356,7 +3361,8 @@ static int amdgpu_ras_load_bad_pages(struct amdgpu_device *adev) 
			/*In V3, there is no pa recs, and some cases(when address==0) may be parsed

			as pa recs, so add verion check to avoid it.

			*/

			if (control->tbl_hdr.version < RAS_TABLE_VER_V3) {

			if ((control->tbl_hdr.version < RAS_TABLE_VER_V3) &&

			    !amdgpu_ras_smu_eeprom_supported(adev)) {

				for (i = 0; i < control->ras_num_recs; i++) {

					if ((control->ras_num_recs - i) >= adev->umc.retire_unit) {

						if ((bps[i].address == bps[i + 1].address) &&