Merge tag 'amd-drm-next-6.12-2024-08-26' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.12-2024-08-26:

amdgpu:
- SDMA devcoredump support
- DCN 4.0.1 updates
- DC SUBVP fixes
- Refactor OPP in DC
- Refactor MMHUBBUB in DC
- DC DML 2.1 updates
- DC FAMS2 updates
- RAS updates
- GFX12 updates
- VCN 4.0.3 updates
- JPEG 4.0.3 updates
- Enable wave kill (soft recovery) for compute queues
- Clean up CP error interrupt handling
- Enable CP bad opcode interrupts
- VCN 4.x fixes
- VCN 5.x fixes
- GPU reset fixes
- Fix vbios embedded EDID size handling
- SMU 14.x updates
- Misc code cleanups and spelling fixes
- VCN devcoredump support
- ISP MFD i2c support
- DC vblank fixes
- GFX 12 fixes
- PSR fixes
- Convert vbios embedded EDID to drm_edid
- DCN 3.5 updates
- DMCUB updates
- Cursor fixes
- Overdrive support for SMU 14.x
- GFX CP padding optimizations
- DCC fixes
- DSC fixes
- Preliminary per queue reset infrastructure
- Initial per queue reset support for GFX 9
- Initial per queue reset support for GFX 7, 8
- DCN 3.2 fixes
- DP MST fixes
- SR-IOV fixes
- GFX 9.4.3/4 devcoredump support
- Add process isolation framework
- Enable process isolation support for GFX 9.4.3/4
- Take IOMMU remapping into account for P2P DMA checks

amdkfd:
- CRIU fixes
- Improved input validation for user queues
- HMM fix
- Enable process isolation support for GFX 9.4.3/4
- Initial per queue reset support for GFX 9
- Allow users to target recommended SDMA engines

radeon:
- remove .load and drm_dev_alloc
- Fix vbios embedded EDID size handling
- Convert vbios embedded EDID to drm_edid
- Use GEM references instead of TTM
- r100 cp init cleanup
- Fix potential overflows in evergreen CS offset tracking

UAPI:
- KFD support for targetting queues on recommended SDMA engines
  Proposed userspace:
  https://github.com/ROCm/ROCR-Runtime/commit/2f588a24065f41c208c3701945e20be746d8faf7
  https://github.com/ROCm/ROCR-Runtime/commit/eb30a5bbc7719c6ffcf2d2dd2878bc53a47b3f30

drm/buddy:
- Add start address support for trim function

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240826201528.55307-1-alexander.deucher@amd.com

1 files changed, 35 insertions, 38 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index d0307c55da50..61a2f386d9fb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1223,11 +1223,11 @@ static void amdgpu_rasmgr_error_data_statistic_update(struct ras_manager *obj, s
 		for_each_ras_error(err_node, err_data) {
 			err_info = &err_node->err_info;
 			amdgpu_ras_error_statistic_de_count(&obj->err_data,
-					&err_info->mcm_info, NULL, err_info->de_count);
+					&err_info->mcm_info, err_info->de_count);
 			amdgpu_ras_error_statistic_ce_count(&obj->err_data,
-					&err_info->mcm_info, NULL, err_info->ce_count);
+					&err_info->mcm_info, err_info->ce_count);
 			amdgpu_ras_error_statistic_ue_count(&obj->err_data,
-					&err_info->mcm_info, NULL, err_info->ue_count);
+					&err_info->mcm_info, err_info->ue_count);
 		}
 	} else {
 		/* for legacy asic path which doesn't has error source info */
@@ -2153,7 +2153,7 @@ static void amdgpu_ras_interrupt_poison_consumption_handler(struct ras_manager *
 	/* gpu reset is fallback for failed and default cases.
 	 * For RMA case, amdgpu_umc_poison_handler will handle gpu reset.
 	 */
-	if (poison_stat && !con->is_rma) {
+	if (poison_stat && !amdgpu_ras_is_rma(adev)) {
 		event_id = amdgpu_ras_acquire_event_id(adev, type);
 		RAS_EVENT_LOG(adev, event_id,
 			      "GPU reset for %s RAS poison consumption is issued!\n",
@@ -2881,9 +2881,6 @@ static void amdgpu_ras_ecc_log_init(struct ras_ecc_log_info *ecc_log)
 {
 	mutex_init(&ecc_log->lock);
 
-	/* Set any value as siphash key */
-	memset(&ecc_log->ecc_key, 0xad, sizeof(ecc_log->ecc_key));
-
 	INIT_RADIX_TREE(&ecc_log->de_page_tree, GFP_KERNEL);
 	ecc_log->de_queried_count = 0;
 	ecc_log->prev_de_queried_count = 0;
@@ -2948,7 +2945,7 @@ static void amdgpu_ras_do_page_retirement(struct work_struct *work)
 
 	amdgpu_ras_error_data_fini(&err_data);
 
-	if (err_cnt && con->is_rma)
+	if (err_cnt && amdgpu_ras_is_rma(adev))
 		amdgpu_ras_reset_gpu(adev);
 
 	amdgpu_ras_schedule_retirement_dwork(con,
@@ -3049,7 +3046,7 @@ static int amdgpu_ras_poison_consumption_handler(struct amdgpu_device *adev,
 	}
 
 	/* for RMA, amdgpu_ras_poison_creation_handler will trigger gpu reset */
-	if (reset_flags && !con->is_rma) {
+	if (reset_flags && !amdgpu_ras_is_rma(adev)) {
 		if (reset_flags & AMDGPU_RAS_GPU_RESET_MODE1_RESET)
 			reset = AMDGPU_RAS_GPU_RESET_MODE1_RESET;
 		else if (reset_flags & AMDGPU_RAS_GPU_RESET_MODE2_RESET)
@@ -3195,7 +3192,7 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev)
 	 * This calling fails when is_rma is true or
 	 * ret != 0.
 	 */
-	if (con->is_rma || ret)
+	if (amdgpu_ras_is_rma(adev) || ret)
 		goto free;
 
 	if (con->eeprom_control.ras_num_recs) {
@@ -3244,7 +3241,7 @@ out:
 	 * Except error threshold exceeding case, other failure cases in this
 	 * function would not fail amdgpu driver init.
 	 */
-	if (!con->is_rma)
+	if (!amdgpu_ras_is_rma(adev))
 		ret = 0;
 	else
 		ret = -EINVAL;
@@ -4287,7 +4284,7 @@ int amdgpu_ras_reset_gpu(struct amdgpu_device *adev)
 	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
 
 	/* mode1 is the only selection for RMA status */
-	if (ras->is_rma) {
+	if (amdgpu_ras_is_rma(adev)) {
 		ras->gpu_reset_flags = 0;
 		ras->gpu_reset_flags |= AMDGPU_RAS_GPU_RESET_MODE1_RESET;
 	}
@@ -4611,8 +4608,6 @@ static struct ras_err_info *amdgpu_ras_error_get_info(struct ras_err_data *err_d
 	if (!err_node)
 		return NULL;
 
-	INIT_LIST_HEAD(&err_node->err_info.err_addr_list);
-
 	memcpy(&err_node->err_info.mcm_info, mcm_info, sizeof(*mcm_info));
 
 	err_data->err_list_count++;
@@ -4622,21 +4617,9 @@ static struct ras_err_info *amdgpu_ras_error_get_info(struct ras_err_data *err_d
 	return &err_node->err_info;
 }
 
-void amdgpu_ras_add_mca_err_addr(struct ras_err_info *err_info, struct ras_err_addr *err_addr)
-{
-	/* This function will be retired. */
-	return;
-}
-
-void amdgpu_ras_del_mca_err_addr(struct ras_err_info *err_info, struct ras_err_addr *mca_err_addr)
-{
-	list_del(&mca_err_addr->node);
-	kfree(mca_err_addr);
-}
-
 int amdgpu_ras_error_statistic_ue_count(struct ras_err_data *err_data,
-		struct amdgpu_smuio_mcm_config_info *mcm_info,
-		struct ras_err_addr *err_addr, u64 count)
+					struct amdgpu_smuio_mcm_config_info *mcm_info,
+					u64 count)
 {
 	struct ras_err_info *err_info;
 
@@ -4650,9 +4633,6 @@ int amdgpu_ras_error_statistic_ue_count(struct ras_err_data *err_data,
 	if (!err_info)
 		return -EINVAL;
 
-	if (err_addr && err_addr->err_status)
-		amdgpu_ras_add_mca_err_addr(err_info, err_addr);
-
 	err_info->ue_count += count;
 	err_data->ue_count += count;
 
@@ -4660,8 +4640,8 @@ int amdgpu_ras_error_statistic_ue_count(struct ras_err_data *err_data,
 }
 
 int amdgpu_ras_error_statistic_ce_count(struct ras_err_data *err_data,
-		struct amdgpu_smuio_mcm_config_info *mcm_info,
-		struct ras_err_addr *err_addr, u64 count)
+					struct amdgpu_smuio_mcm_config_info *mcm_info,
+					u64 count)
 {
 	struct ras_err_info *err_info;
 
@@ -4682,8 +4662,8 @@ int amdgpu_ras_error_statistic_ce_count(struct ras_err_data *err_data,
 }
 
 int amdgpu_ras_error_statistic_de_count(struct ras_err_data *err_data,
-		struct amdgpu_smuio_mcm_config_info *mcm_info,
-		struct ras_err_addr *err_addr, u64 count)
+					struct amdgpu_smuio_mcm_config_info *mcm_info,
+					u64 count)
 {
 	struct ras_err_info *err_info;
 
@@ -4697,9 +4677,6 @@ int amdgpu_ras_error_statistic_de_count(struct ras_err_data *err_data,
 	if (!err_info)
 		return -EINVAL;
 
-	if (err_addr && err_addr->err_status)
-		amdgpu_ras_add_mca_err_addr(err_info, err_addr);
-
 	err_info->de_count += count;
 	err_data->de_count += count;
 
@@ -4771,6 +4748,16 @@ static void amdgpu_ras_boot_time_error_reporting(struct amdgpu_device *adev,
 		dev_info(adev->dev,
 			 "socket: %d, aid: %d, hbm: %d, fw_status: 0x%x, hbm bist test failed\n",
 			 socket_id, aid_id, hbm_id, fw_status);
+
+	if (AMDGPU_RAS_GPU_ERR_DATA_ABORT(boot_error))
+		dev_info(adev->dev,
+			 "socket: %d, aid: %d, fw_status: 0x%x, data abort exception\n",
+			 socket_id, aid_id, fw_status);
+
+	if (AMDGPU_RAS_GPU_ERR_UNKNOWN(boot_error))
+		dev_info(adev->dev,
+			 "socket: %d, aid: %d, fw_status: 0x%x, unknown boot time errors\n",
+			 socket_id, aid_id, fw_status);
 }
 
 static bool amdgpu_ras_boot_error_detected(struct amdgpu_device *adev,
@@ -4837,3 +4824,13 @@ void amdgpu_ras_event_log_print(struct amdgpu_device *adev, u64 event_id,
 
 	va_end(args);
 }
+
+bool amdgpu_ras_is_rma(struct amdgpu_device *adev)
+{
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+
+	if (!con)
+		return false;
+
+	return con->is_rma;
+}