Merge tag 'drm-next-5.5-2019-10-09' of git://people.freedesktop.org/~agd5f/linux into drm-next

drm-next-5.5-2019-10-09:

amdgpu:
- Additional RAS enablement for vega20
- RAS page retirement and bad page storage in EEPROM
- No GPU reset with unrecoverable RAS errors
- Reserve vram for page tables rather than trying to evict
- Fix issues with GPU reset and xgmi hives
- DC i2c over aux fixes
- Direct submission for clears, PTE/PDE updates
- Improvements to help support recoverable GPU page faults
- Silence harmless SAD block messages
- Clean up code for creating a bo at a fixed location
- Initial DC HDCP support
- Lots of documentation fixes
- GPU reset for renoir
- Add IH clockgating support for soc15 asics
- Powerplay improvements
- DC MST cleanups
- Add support for MSI-X
- Misc cleanups and bug fixes

amdkfd:
- Query KFD device info by asic type rather than pci ids
- Add navi14 support
- Add renoir support
- Add navi12 support
- gfx10 trap handler improvements
- pasid cleanups
- Check against device cgroup

ttm:
- Return -EBUSY with pipelining with no_gpu_wait

radeon:
- Silence harmless SAD block messages

device_cgroup:
- Export devcgroup_check_permission

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Alex Deucher <alexdeucher@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191010041713.3412-1-alexander.deucher@amd.com

1 files changed, 37 insertions, 11 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c b/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c
index 8502e736f721..47c4b96b14d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c
@@ -75,6 +75,17 @@ static void umc_v6_1_disable_umc_index_mode(struct amdgpu_device *adev)
 			RSMU_UMC_INDEX_MODE_EN, 0);
 }
 
+static uint32_t umc_v6_1_get_umc_inst(struct amdgpu_device *adev)
+{
+	uint32_t rsmu_umc_index;
+
+	rsmu_umc_index = RREG32_SOC15(RSMU, 0,
+				mmRSMU_UMC_INDEX_REGISTER_NBIF_VG20_GPU);
+	return REG_GET_FIELD(rsmu_umc_index,
+				RSMU_UMC_INDEX_REGISTER_NBIF_VG20_GPU,
+				RSMU_UMC_INDEX_INSTANCE);
+}
+
 static void umc_v6_1_query_correctable_error_count(struct amdgpu_device *adev,
 						   uint32_t umc_reg_offset,
 						   unsigned long *error_count)
@@ -165,7 +176,8 @@ static void umc_v6_1_query_error_address(struct amdgpu_device *adev,
 					 uint32_t umc_reg_offset, uint32_t channel_index)
 {
 	uint32_t lsb, mc_umc_status_addr;
-	uint64_t mc_umc_status, err_addr;
+	uint64_t mc_umc_status, err_addr, retired_page;
+	struct eeprom_table_record *err_rec;
 
 	mc_umc_status_addr =
 		SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_STATUST0);
@@ -177,6 +189,7 @@ static void umc_v6_1_query_error_address(struct amdgpu_device *adev,
 		return;
 	}
 
+	err_rec = &err_data->err_addr[err_data->err_addr_cnt];
 	mc_umc_status = RREG64_UMC(mc_umc_status_addr + umc_reg_offset);
 
 	/* calculate error address if ue/ce error is detected */
@@ -191,12 +204,24 @@ static void umc_v6_1_query_error_address(struct amdgpu_device *adev,
 		err_addr &= ~((0x1ULL << lsb) - 1);
 
 		/* translate umc channel address to soc pa, 3 parts are included */
-		err_data->err_addr[err_data->err_addr_cnt] =
-						ADDR_OF_8KB_BLOCK(err_addr) |
-						ADDR_OF_256B_BLOCK(channel_index) |
-						OFFSET_IN_256B_BLOCK(err_addr);
-
-		err_data->err_addr_cnt++;
+		retired_page = ADDR_OF_8KB_BLOCK(err_addr) |
+				ADDR_OF_256B_BLOCK(channel_index) |
+				OFFSET_IN_256B_BLOCK(err_addr);
+
+		/* we only save ue error information currently, ce is skipped */
+		if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC)
+				== 1) {
+			err_rec->address = err_addr;
+			/* page frame address is saved */
+			err_rec->retired_page = retired_page >> AMDGPU_GPU_PAGE_SHIFT;
+			err_rec->ts = (uint64_t)ktime_get_real_seconds();
+			err_rec->err_type = AMDGPU_RAS_EEPROM_ERR_NON_RECOVERABLE;
+			err_rec->cu = 0;
+			err_rec->mem_channel = channel_index;
+			err_rec->mcumc_id = umc_v6_1_get_umc_inst(adev);
+
+			err_data->err_addr_cnt++;
+		}
 	}
 
 	/* clear umc status */
@@ -209,7 +234,7 @@ static void umc_v6_1_query_ras_error_address(struct amdgpu_device *adev,
 	amdgpu_umc_for_each_channel(umc_v6_1_query_error_address);
 }
 
-static void umc_v6_1_ras_init_per_channel(struct amdgpu_device *adev,
+static void umc_v6_1_err_cnt_init_per_channel(struct amdgpu_device *adev,
 					 struct ras_err_data *err_data,
 					 uint32_t umc_reg_offset, uint32_t channel_index)
 {
@@ -239,15 +264,16 @@ static void umc_v6_1_ras_init_per_channel(struct amdgpu_device *adev,
 	WREG32(ecc_err_cnt_addr + umc_reg_offset, UMC_V6_1_CE_CNT_INIT);
 }
 
-static void umc_v6_1_ras_init(struct amdgpu_device *adev)
+static void umc_v6_1_err_cnt_init(struct amdgpu_device *adev)
 {
 	void *ras_error_status = NULL;
 
-	amdgpu_umc_for_each_channel(umc_v6_1_ras_init_per_channel);
+	amdgpu_umc_for_each_channel(umc_v6_1_err_cnt_init_per_channel);
 }
 
 const struct amdgpu_umc_funcs umc_v6_1_funcs = {
-	.ras_init = umc_v6_1_ras_init,
+	.err_cnt_init = umc_v6_1_err_cnt_init,
+	.ras_late_init = amdgpu_umc_ras_late_init,
 	.query_ras_error_count = umc_v6_1_query_ras_error_count,
 	.query_ras_error_address = umc_v6_1_query_ras_error_address,
 	.enable_umc_index_mode = umc_v6_1_enable_umc_index_mode,