Merge tag 'amd-drm-next-6.11-2024-06-07' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.11-2024-06-07:

amdgpu:
- DCN 4.0.x support
- DCN 3.5 updates
- GC 12.0 support
- DP MST fixes
- Cursor fixes
- MES11 updates
- MMHUB 4.1 support
- DML2 Updates
- DCN 3.1.5 fixes
- IPS fixes
- Various code cleanups
- GMC 12.0 support
- SDMA 7.0 support
- SMU 13 updates
- SR-IOV fixes
- VCN 5.x fixes
- MES12 support
- SMU 14.x updates
- Devcoredump improvements
- Fixes for HDP flush on platforms with >4k pages
- GC 9.4.3 fixes
- RAS ACA updates
- Silence UBSAN flex array warnings
- MMHUB 3.3 updates

amdkfd:
- Contiguous VRAM allocations
- GC 12.0 support
- SDMA 7.0 support
- SR-IOV fixes

radeon:
- Backlight workaround for iMac
- Silence UBSAN flex array warnings

UAPI:
- GFX12 modifier and DCC support
  Proposed Mesa changes:
  https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29510
- KFD GFX ALU exceptions
  Proposed ROCdebugger changes:
  https://github.com/ROCm/ROCdbgapi/commit/08c760622b6601abf906f75abbc5e21d9fd425df
  https://github.com/ROCm/ROCgdb/commit/944fe1c1414a68700414e86e32273b6bfa62ba6f
- KFD Contiguous VRAM allocation flag
  Proposed ROCr/HIP changes:
  https://github.com/ROCm/ROCT-Thunk-Interface/commit/f7b4a269914a3ab4f1e2453c2879adb97b5cc9e5
  https://github.com/ROCm/ROCR-Runtime/pull/214/commits/26e8530d05a775872cb06dde6693db72be0c454a
  https://github.com/ROCm/clr/commit/1d48f2a1ab38b632919c4b7274899b3faf4279ff

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240607195900.902537-1-alexander.deucher@amd.com

1 files changed, 15 insertions, 21 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h
index e5bf07ce3451..c3c184c88dad 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h
@@ -77,11 +77,23 @@ struct amdgpu_mca_ras {
 	struct amdgpu_mca_ras_block *ras;
 };
 
+struct mca_bank_set {
+	int nr_entries;
+	struct list_head list;
+};
+
+struct mca_bank_cache {
+	struct mca_bank_set mca_set;
+	spinlock_t lock;
+};
+
 struct amdgpu_mca {
 	struct amdgpu_mca_ras mp0;
 	struct amdgpu_mca_ras mp1;
 	struct amdgpu_mca_ras mpio;
 	const struct amdgpu_mca_smu_funcs *mca_funcs;
+	struct mca_bank_cache mca_caches[AMDGPU_MCA_ERROR_TYPE_DE];
+	atomic_t ue_update_flag;
 };
 
 enum mca_reg_idx {
@@ -113,17 +125,10 @@ struct mca_bank_node {
 	struct list_head node;
 };
 
-struct mca_bank_set {
-	int nr_entries;
-	struct list_head list;
-};
-
 struct amdgpu_mca_smu_funcs {
 	int max_ue_count;
 	int max_ce_count;
 	int (*mca_set_debug_mode)(struct amdgpu_device *adev, bool enable);
-	int (*mca_get_ras_mca_set)(struct amdgpu_device *adev, enum amdgpu_ras_block blk, enum amdgpu_mca_error_type type,
-				   struct mca_bank_set *mca_set);
 	int (*mca_parse_mca_error_count)(struct amdgpu_device *adev, enum amdgpu_ras_block blk, enum amdgpu_mca_error_type type,
 					 struct mca_bank_entry *entry, uint32_t *count);
 	int (*mca_get_valid_mca_count)(struct amdgpu_device *adev, enum amdgpu_mca_error_type type,
@@ -151,24 +156,13 @@ int amdgpu_mca_mp1_ras_sw_init(struct amdgpu_device *adev);
 int amdgpu_mca_mpio_ras_sw_init(struct amdgpu_device *adev);
 
 void amdgpu_mca_smu_init_funcs(struct amdgpu_device *adev, const struct amdgpu_mca_smu_funcs *mca_funcs);
+int amdgpu_mca_init(struct amdgpu_device *adev);
+void amdgpu_mca_fini(struct amdgpu_device *adev);
+int amdgpu_mca_reset(struct amdgpu_device *adev);
 int amdgpu_mca_smu_set_debug_mode(struct amdgpu_device *adev, bool enable);
-int amdgpu_mca_smu_get_valid_mca_count(struct amdgpu_device *adev, enum amdgpu_mca_error_type type, uint32_t *count);
 int amdgpu_mca_smu_get_mca_set_error_count(struct amdgpu_device *adev, enum amdgpu_ras_block blk,
 					   enum amdgpu_mca_error_type type, uint32_t *total);
-int amdgpu_mca_smu_get_error_count(struct amdgpu_device *adev, enum amdgpu_ras_block blk,
-				   enum amdgpu_mca_error_type type, uint32_t *count);
-int amdgpu_mca_smu_parse_mca_error_count(struct amdgpu_device *adev, enum amdgpu_ras_block blk,
-					 enum amdgpu_mca_error_type type, struct mca_bank_entry *entry, uint32_t *count);
-int amdgpu_mca_smu_get_mca_set(struct amdgpu_device *adev, enum amdgpu_ras_block blk,
-			       enum amdgpu_mca_error_type type, struct mca_bank_set *mca_set);
-int amdgpu_mca_smu_get_mca_entry(struct amdgpu_device *adev, enum amdgpu_mca_error_type type,
-				 int idx, struct mca_bank_entry *entry);
-
 void amdgpu_mca_smu_debugfs_init(struct amdgpu_device *adev, struct dentry *root);
-
-void amdgpu_mca_bank_set_init(struct mca_bank_set *mca_set);
-int amdgpu_mca_bank_set_add_entry(struct mca_bank_set *mca_set, struct mca_bank_entry *entry);
-void amdgpu_mca_bank_set_release(struct mca_bank_set *mca_set);
 int amdgpu_mca_smu_log_ras_error(struct amdgpu_device *adev, enum amdgpu_ras_block blk, enum amdgpu_mca_error_type type,
 				 struct ras_err_data *err_data, struct ras_query_context *qctx);