[PATCH] drm/amdgpu: Skip poison aca bank from UE channel

[Xiang Liu]

Avoid GFX poison consumption errors logged when fatal error occurs.

Signed-off-by: Xiang Liu <xiang....@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c | 47 ++++++++++++++-----------
 1 file changed, 26 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c 
b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
index 3835f2592914..59dbb9257096 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
@@ -125,6 +125,27 @@ 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)
@@ -163,6 +184,11 @@ static int aca_smu_get_valid_aca_banks(struct 
amdgpu_device *adev, enum aca_smu_
 
                bank.smu_err_type = type;
 
+               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);
@@ -173,27 +199,6 @@ 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;
-- 
2.34.1