Merge tag 'amd-drm-next-6.15-2025-02-21' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.15-2025-02-21:

amdgpu:
- Add OEM i2c support for RGB lights, etc.
- Add support for GC 11.5.3
- Add support for GC 11.5.2
- Add support for SDMA 6.1.3
- Add support for NBIO 7.11.2
- Add support for NBIO 7.9.1
- Add support for MMHUB 3.3.2
- Add support for MMHUB 1.8.1
- Add support for SMU 14.0.5
- Add support for SMUIO 13.0.11
- Add support for PSP 14.0.5
- Add support for UMC 12.5.0
- Add support for DCN 3.6.0
- JPEG 4.0.3 updates
- Add dynamic workload profile switching for GC 10-12
- support larger vbios sizes
- GC 9.5.0 updates
- SMU 13.0.12 updates
- SMU 13.0.6 updates
- IP discovery updates
- GC 10 queue reset updates
- DCN 4.0.1 updates
- UHBR link rate fixes
- Aborted suspend fix
- Mark gttsize parameter as deprecated
- GC 10 cleaner shader updates
- PSR-SU fixes
- Clean up PM4 headers
- Cursor fixes
- Enable devcoredump for JPEG
- Misc cleanups
- Runpm cleanups
- MES updates
- GC 9 gfxoff fixes
- Vbios fetching cleanups
- Documentation updates
- Update secondary plane handling
- DML2 updates
- SDMA fixes for MI
- Cleaner shader fixes for GC 11/12
- ACA updates
- Initial JPEG queue reset support
- RAS updates
- Initial RAS CPER support
- DCN/DCE panic screen handling cleanup
- BT2020 fixes
- SR-IOV fixes

amdkfd:
- synchronize pasid values between KGD and KFD
- Misc cleanups
- Improve GTT/VRAM handling for APUs
- Topology updates
- Fix user queue validation on GC 7/8

UAPI:
- Enable "Broadcast RGB" drm property
- Add INFO IOCTL query for virtualization mode
  Proposed userspace:
  https://github.com/ROCm/amdsmi/commit/e663bed7d6b3df79f5959e73981749b1f22ec698

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250221213651.4176031-1-alexander.deucher@amd.com
Signed-off-by: Dave Airlie <airlied@redhat.com>

1 files changed, 34 insertions, 12 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
index 9d6345146495f..d11593cd19229 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
@@ -30,16 +30,6 @@
 
 typedef int bank_handler_t(struct aca_handle *handle, struct aca_bank *bank, enum aca_smu_type type, void *data);
 
-struct aca_banks {
-	int nr_banks;
-	struct list_head list;
-};
-
-struct aca_hwip {
-	int hwid;
-	int mcatype;
-};
-
 static struct aca_hwip aca_hwid_mcatypes[ACA_HWIP_TYPE_COUNT] = {
 	ACA_BANK_HWID(SMU,	0x01,	0x01),
 	ACA_BANK_HWID(PCS_XGMI, 0x50,	0x00),
@@ -111,7 +101,7 @@ static struct aca_regs_dump {
 	{"STATUS",		ACA_REG_IDX_STATUS},
 	{"ADDR",		ACA_REG_IDX_ADDR},
 	{"MISC",		ACA_REG_IDX_MISC0},
-	{"CONFIG",		ACA_REG_IDX_CONFG},
+	{"CONFIG",		ACA_REG_IDX_CONFIG},
 	{"IPID",		ACA_REG_IDX_IPID},
 	{"SYND",		ACA_REG_IDX_SYND},
 	{"DESTAT",		ACA_REG_IDX_DESTAT},
@@ -168,7 +158,7 @@ static int aca_smu_get_valid_aca_banks(struct amdgpu_device *adev, enum aca_smu_
 		if (ret)
 			return ret;
 
-		bank.type = type;
+		bank.smu_err_type = type;
 
 		aca_smu_bank_dump(adev, i, count, &bank, qctx);
 
@@ -394,6 +384,36 @@ static bool aca_bank_should_update(struct amdgpu_device *adev, enum aca_smu_type
 	return ret;
 }
 
+static void aca_banks_generate_cper(struct amdgpu_device *adev,
+				    enum aca_smu_type type,
+				    struct aca_banks *banks,
+				    int count)
+{
+	struct aca_bank_node *node;
+	struct aca_bank *bank;
+
+	if (!banks || !count) {
+		dev_warn(adev->dev, "fail to generate cper records\n");
+		return;
+	}
+
+	/* UEs must be encoded into separate CPER entries */
+	if (type == ACA_SMU_TYPE_UE) {
+		list_for_each_entry(node, &banks->list, node) {
+			bank = &node->bank;
+			if (amdgpu_cper_generate_ue_record(adev, bank))
+				dev_warn(adev->dev, "fail to generate ue cper records\n");
+		}
+	} else {
+		/*
+		 * SMU_TYPE_CE banks are combined into 1 CPER entries,
+		 * they could be CEs or DEs or both
+		 */
+		if (amdgpu_cper_generate_ce_records(adev, banks, count))
+			dev_warn(adev->dev, "fail to generate ce cper records\n");
+	}
+}
+
 static int aca_banks_update(struct amdgpu_device *adev, enum aca_smu_type type,
 			    bank_handler_t handler, struct ras_query_context *qctx, void *data)
 {
@@ -431,6 +451,8 @@ static int aca_banks_update(struct amdgpu_device *adev, enum aca_smu_type type,
 	if (ret)
 		goto err_release_banks;
 
+	aca_banks_generate_cper(adev, type, &banks, count);
+
 err_release_banks:
 	aca_banks_release(&banks);