Re: [PATCH] drm/amdgpu: Decode deferred error type in gfx aca bank parser

[Liu, Xiang(Dean)]

[AMD Official Use Only - AMD Internal Distribution Only]

Thanks, will improve it.

Best Regards,

Dean

________________________________
From: Zhang, Hawking <hawking.zh...@amd.com>
Sent: Thursday, March 20, 2025 2:22 PM
To: Liu, Xiang(Dean) <xiang....@amd.com>; amd-gfx@lists.freedesktop.org 
<amd-gfx@lists.freedesktop.org>
Cc: Wang, Yang(Kevin) <kevinyang.w...@amd.com>; Zhou1, Tao <tao.zh...@amd.com>; 
Chai, Thomas <yipeng.c...@amd.com>
Subject: RE: [PATCH] drm/amdgpu: Decode deferred error type in gfx aca bank 
parser

[AMD Official Use Only - AMD Internal Distribution Only]

+               bank->aca_err_type = (ACA_REG__STATUS__POISON(status) ||
+                                     ACA_REG__STATUS__DEFERRED(status)) ?
+                                               ACA_ERROR_TYPE_DEFERRED :
+                                               ACA_ERROR_TYPE_UE;

Does it make more sense to create a macro similar to ACA_BANK_ERR_CE_DE_DECODE 
for above code segment?

Regards,
Hawking

-----Original Message-----
From: Liu, Xiang(Dean) <xiang....@amd.com>
Sent: Thursday, March 20, 2025 14:15
To: amd-gfx@lists.freedesktop.org
Cc: Zhang, Hawking <hawking.zh...@amd.com>; Wang, Yang(Kevin) 
<kevinyang.w...@amd.com>; Zhou1, Tao <tao.zh...@amd.com>; Chai, Thomas 
<yipeng.c...@amd.com>; Liu, Xiang(Dean) <xiang....@amd.com>
Subject: [PATCH] drm/amdgpu: Decode deferred error type in gfx aca bank parser

In the case of injecting uncorrected error with background workload, the 
deferred error among uncorrected errors need to be specified by checking the 
deferred and poison bits of status register.

Signed-off-by: Xiang Liu <xiang....@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c |  3 +++  
drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c | 11 +++++++----
 2 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c 
b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
index ffd4c64e123c..3f45a600f547 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
@@ -541,6 +541,9 @@ static int __aca_get_error_data(struct amdgpu_device *adev, 
struct aca_handle *h
        if (ret)
                return ret;

+       if (type == ACA_ERROR_TYPE_UE)
+               aca_log_aca_error(handle, ACA_ERROR_TYPE_DEFERRED, err_data);
+
        return aca_log_aca_error(handle, type, err_data);  }

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c 
b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
index c0de682b7774..b21d784a7f9c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
@@ -876,7 +876,7 @@ static int gfx_v9_4_3_aca_bank_parser(struct aca_handle 
*handle,
                                      void *data)
 {
        struct aca_bank_info info;
-       u64 misc0;
+       u64 misc0, status;
        u32 instlo;
        int ret;

@@ -890,12 +890,15 @@ static int gfx_v9_4_3_aca_bank_parser(struct aca_handle 
*handle,
        info.die_id = instlo == mmSMNAID_XCD0_MCA_SMU ? 0 : 1;

        misc0 = bank->regs[ACA_REG_IDX_MISC0];
+       status = bank->regs[ACA_REG_IDX_STATUS];

        switch (type) {
        case ACA_SMU_TYPE_UE:
-               bank->aca_err_type = ACA_ERROR_TYPE_UE;
-               ret = aca_error_cache_log_bank_error(handle, &info,
-                                                    ACA_ERROR_TYPE_UE, 1ULL);
+               bank->aca_err_type = (ACA_REG__STATUS__POISON(status) ||
+                                     ACA_REG__STATUS__DEFERRED(status)) ?
+                                               ACA_ERROR_TYPE_DEFERRED :
+                                               ACA_ERROR_TYPE_UE;
+               ret = aca_error_cache_log_bank_error(handle, &info,
+bank->aca_err_type, 1ULL);
                break;
        case ACA_SMU_TYPE_CE:
                bank->aca_err_type = ACA_BANK_ERR_CE_DE_DECODE(bank);
--
2.34.1