From: Xiang Liu <xiang.liu@amd.com>
Date: Wed, 30 Jul 2025 03:07:43 +0000 (+0800)
Subject: drm/amdgpu: Skip poison aca bank from UE channel
X-Git-Tag: v6.18-rc1~134^2~19^2~179
X-Git-Url: http://git.ipfire.org/gitweb.cgi?a=commitdiff_plain;h=8e8e08c831f088ed581444c58a635c49ea1222ab;p=thirdparty%2Flinux.git

drm/amdgpu: Skip poison aca bank from UE channel

Avoid GFX poison consumption errors logged when fatal error occurs.

Signed-off-by: Xiang Liu <xiang.liu@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
index cbc40cad581b4..d1e431818212d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
@@ -130,6 +130,27 @@ 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 +189,15 @@ 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 +208,6 @@ 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;