[PATCH] drm/amdgpu: Switch to aca bank for xgmi pcs err cnt

[Wang, Yang(Kevin)]

[AMD Official Use Only - General]

Reviewed-by: Yang Wang <kevinyang.wang at amd.com>

Best Regards,
Kevin

-----Original Message-----
From: Zhang, Hawking <Hawking.Zhang at amd.com>
Sent: Tuesday, December 12, 2023 10:03 PM
To: amd-gfx at lists.freedesktop.org; Yang, Stanley <Stanley.Yang at amd.com>; Wang, Yang(Kevin) <KevinYang.Wang at amd.com>
Cc: Zhang, Hawking <Hawking.Zhang at amd.com>
Subject: [PATCH] drm/amdgpu: Switch to aca bank for xgmi pcs err cnt

Instead of software managed counters.

Signed-off-by: Hawking Zhang <Hawking.Zhang at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h              | 2 ++
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c | 6 ++++--
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h
index e51e8918e667..b399f1b62887 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h
@@ -46,6 +46,8 @@
 #define MCA_REG__STATUS__ERRORCODEEXT(x)       MCA_REG_FIELD(x, 21, 16)
 #define MCA_REG__STATUS__ERRORCODE(x)          MCA_REG_FIELD(x, 15, 0)

+#define MCA_REG__MISC0__ERRCNT(x)              MCA_REG_FIELD(x, 43, 32)
+
 #define MCA_REG__SYND__ERRORINFORMATION(x)     MCA_REG_FIELD(x, 17, 0)

 enum amdgpu_mca_ip {
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index ddd782fbee7a..3998c9b31d07 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -2537,13 +2537,15 @@ static int mca_pcs_xgmi_mca_get_err_count(const struct mca_ras_info *mca_ras, st
                                          uint32_t *count)
 {
        u32 ext_error_code;
+       u32 err_cnt;

        ext_error_code = MCA_REG__STATUS__ERRORCODEEXT(entry->regs[MCA_REG_IDX_STATUS]);
+       err_cnt = MCA_REG__MISC0__ERRCNT(entry->regs[MCA_REG_IDX_MISC0]);

        if (type == AMDGPU_MCA_ERROR_TYPE_UE && ext_error_code == 0)
-               *count = 1;
+               *count = err_cnt;
        else if (type == AMDGPU_MCA_ERROR_TYPE_CE && ext_error_code == 6)
-               *count = 1;
+               *count = err_cnt;

        return 0;
 }
--
2.17.1