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, 4 insertions, 98 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
index 2f84bdb8c594..bb7b9b2eaac1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
@@ -196,7 +196,7 @@ static int amdgpu_umc_do_page_retirement(struct amdgpu_device *adev,
 	amdgpu_umc_handle_bad_pages(adev, ras_error_status);
 
 	if ((err_data->ue_count || err_data->de_count) &&
-	    (reset || (con && con->is_rma))) {
+	    (reset || amdgpu_ras_is_rma(adev))) {
 		con->gpu_reset_flags |= reset;
 		amdgpu_ras_reset_gpu(adev);
 	}
@@ -204,55 +204,6 @@ static int amdgpu_umc_do_page_retirement(struct amdgpu_device *adev,
 	return AMDGPU_RAS_SUCCESS;
 }
 
-int amdgpu_umc_bad_page_polling_timeout(struct amdgpu_device *adev,
-			uint32_t reset, uint32_t timeout_ms)
-{
-	struct ras_err_data err_data;
-	struct ras_common_if head = {
-		.block = AMDGPU_RAS_BLOCK__UMC,
-	};
-	struct ras_manager *obj = amdgpu_ras_find_obj(adev, &head);
-	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
-	uint32_t timeout = timeout_ms;
-
-	memset(&err_data, 0, sizeof(err_data));
-	amdgpu_ras_error_data_init(&err_data);
-
-	do {
-
-		amdgpu_umc_handle_bad_pages(adev, &err_data);
-
-		if (timeout && !err_data.de_count) {
-			msleep(1);
-			timeout--;
-		}
-
-	} while (timeout && !err_data.de_count);
-
-	if (!timeout)
-		dev_warn(adev->dev, "Can't find bad pages\n");
-
-	if (err_data.de_count)
-		dev_info(adev->dev, "%ld new deferred hardware errors detected\n", err_data.de_count);
-
-	if (obj) {
-		obj->err_data.ue_count += err_data.ue_count;
-		obj->err_data.ce_count += err_data.ce_count;
-		obj->err_data.de_count += err_data.de_count;
-	}
-
-	amdgpu_ras_error_data_fini(&err_data);
-
-	kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
-
-	if (reset || (err_data.err_addr_cnt && con && con->is_rma)) {
-		con->gpu_reset_flags |= reset;
-		amdgpu_ras_reset_gpu(adev);
-	}
-
-	return 0;
-}
-
 int amdgpu_umc_pasid_poison_handler(struct amdgpu_device *adev,
 			enum amdgpu_ras_block block, uint16_t pasid,
 			pasid_notify pasid_fn, void *data, uint32_t reset)
@@ -472,43 +423,6 @@ int amdgpu_umc_update_ecc_status(struct amdgpu_device *adev,
 	return 0;
 }
 
-static int amdgpu_umc_uint64_cmp(const void *a, const void *b)
-{
-	uint64_t *addr_a = (uint64_t *)a;
-	uint64_t *addr_b = (uint64_t *)b;
-
-	if (*addr_a > *addr_b)
-		return 1;
-	else if (*addr_a < *addr_b)
-		return -1;
-	else
-		return 0;
-}
-
-/* Use string hash to avoid logging the same bad pages repeatedly */
-int amdgpu_umc_build_pages_hash(struct amdgpu_device *adev,
-		uint64_t *pfns, int len, uint64_t *val)
-{
-	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
-	char buf[MAX_UMC_HASH_STRING_SIZE] = {0};
-	int offset = 0, i = 0;
-	uint64_t hash_val;
-
-	if (!pfns || !len)
-		return -EINVAL;
-
-	sort(pfns, len, sizeof(uint64_t), amdgpu_umc_uint64_cmp, NULL);
-
-	for (i = 0; i < len; i++)
-		offset += snprintf(&buf[offset], sizeof(buf) - offset, "%llx", pfns[i]);
-
-	hash_val = siphash(buf, offset, &con->umc_ecc_log.ecc_key);
-
-	*val = hash_val;
-
-	return 0;
-}
-
 int amdgpu_umc_logs_ecc_err(struct amdgpu_device *adev,
 		struct radix_tree_root *ecc_tree, struct ras_ecc_err *ecc_err)
 {
@@ -519,18 +433,10 @@ int amdgpu_umc_logs_ecc_err(struct amdgpu_device *adev,
 	ecc_log = &con->umc_ecc_log;
 
 	mutex_lock(&ecc_log->lock);
-	ret = radix_tree_insert(ecc_tree, ecc_err->hash_index, ecc_err);
-	if (!ret) {
-		struct ras_err_pages *err_pages = &ecc_err->err_pages;
-		int i;
-
-		/* Reserve memory */
-		for (i = 0; i < err_pages->count; i++)
-			amdgpu_ras_reserve_page(adev, err_pages->pfn[i]);
-
+	ret = radix_tree_insert(ecc_tree, ecc_err->pa_pfn, ecc_err);
+	if (!ret)
 		radix_tree_tag_set(ecc_tree,
-			ecc_err->hash_index, UMC_ECC_NEW_DETECTED_TAG);
-	}
+			ecc_err->pa_pfn, UMC_ECC_NEW_DETECTED_TAG);
 	mutex_unlock(&ecc_log->lock);
 
 	return ret;