Merge tag 'amd-drm-next-6.18-2025-08-29' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.18-2025-08-29:

amdgpu:
- Replay fixes
- RAS updates
- VCN SRAM load fixes
- EDID read fixes
- eDP ALPM support
- AUX fixes
- Documenation updates
- Rework how PTE flags are generated
- DCE6 fixes
- VCN devcoredump cleanup
- MMHUB client id fixes
- SR-IOV fixes
- VRR fixes
- VCN 5.0.1 RAS support
- Backlight fixes
- UserQ fixes
- Misc code cleanups
- SMU 13.0.12 updates
- Expanded PCIe DPC support
- Expanded VCN reset support
- SMU 13.0.x Updates
- VPE per queue reset support
- Cusor rotation fix
- DSC fixes
- GC 12 MES TLB invalidation update
- Cursor fixes
- Non-DC TMDS clock validation fix

amdkfd:
- debugfs fixes
- Misc code cleanups
- Page migration fixes
- Partition fixes
- SVM fixes

radeon:
- Misc code cleanups

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

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://lore.kernel.org/r/20250829190848.1921648-1-alexander.deucher@amd.com

1 files changed, 32 insertions, 21 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
index cbc40cad581b..9b3180449150 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
@@ -76,6 +76,7 @@ static void aca_banks_release(struct aca_banks *banks)
 	list_for_each_entry_safe(node, tmp, &banks->list, node) {
 		list_del(&node->node);
 		kvfree(node);
+		banks->nr_banks--;
 	}
 }
 
@@ -130,6 +131,27 @@ static void aca_smu_bank_dump(struct amdgpu_device *adev, int idx, int total, st
 		RAS_EVENT_LOG(adev, event_id, HW_ERR "hardware error logged by the scrubber\n");
 }
 
+static bool aca_bank_hwip_is_matched(struct aca_bank *bank, enum aca_hwip_type type)
+{
+
+	struct aca_hwip *hwip;
+	int hwid, mcatype;
+	u64 ipid;
+
+	if (!bank || type == ACA_HWIP_TYPE_UNKNOW)
+		return false;
+
+	hwip = &aca_hwid_mcatypes[type];
+	if (!hwip->hwid)
+		return false;
+
+	ipid = bank->regs[ACA_REG_IDX_IPID];
+	hwid = ACA_REG__IPID__HARDWAREID(ipid);
+	mcatype = ACA_REG__IPID__MCATYPE(ipid);
+
+	return hwip->hwid == hwid && hwip->mcatype == mcatype;
+}
+
 static int aca_smu_get_valid_aca_banks(struct amdgpu_device *adev, enum aca_smu_type type,
 				       int start, int count,
 				       struct aca_banks *banks, struct ras_query_context *qctx)
@@ -168,6 +190,15 @@ static int aca_smu_get_valid_aca_banks(struct amdgpu_device *adev, enum aca_smu_
 
 		bank.smu_err_type = type;
 
+		/*
+		 * Poison being consumed when injecting a UE while running background workloads,
+		 * which are unexpected.
+		 */
+		if (type == ACA_SMU_TYPE_UE &&
+		    ACA_REG__STATUS__POISON(bank.regs[ACA_REG_IDX_STATUS]) &&
+		    !aca_bank_hwip_is_matched(&bank, ACA_HWIP_TYPE_UMC))
+			continue;
+
 		aca_smu_bank_dump(adev, i, count, &bank, qctx);
 
 		ret = aca_banks_add_bank(banks, &bank);
@@ -178,27 +209,6 @@ static int aca_smu_get_valid_aca_banks(struct amdgpu_device *adev, enum aca_smu_
 	return 0;
 }
 
-static bool aca_bank_hwip_is_matched(struct aca_bank *bank, enum aca_hwip_type type)
-{
-
-	struct aca_hwip *hwip;
-	int hwid, mcatype;
-	u64 ipid;
-
-	if (!bank || type == ACA_HWIP_TYPE_UNKNOW)
-		return false;
-
-	hwip = &aca_hwid_mcatypes[type];
-	if (!hwip->hwid)
-		return false;
-
-	ipid = bank->regs[ACA_REG_IDX_IPID];
-	hwid = ACA_REG__IPID__HARDWAREID(ipid);
-	mcatype = ACA_REG__IPID__MCATYPE(ipid);
-
-	return hwip->hwid == hwid && hwip->mcatype == mcatype;
-}
-
 static bool aca_bank_is_valid(struct aca_handle *handle, struct aca_bank *bank, enum aca_smu_type type)
 {
 	const struct aca_bank_ops *bank_ops = handle->bank_ops;
@@ -229,6 +239,7 @@ static struct aca_bank_error *new_bank_error(struct aca_error *aerr, struct aca_
 
 	mutex_lock(&aerr->lock);
 	list_add_tail(&bank_error->node, &aerr->list);
+	aerr->nr_errors++;
 	mutex_unlock(&aerr->lock);
 
 	return bank_error;