[PATCH] drm/amd/pm: Retrieve UMC ODECC error count from aca bank

[Zhou1, Tao]

[AMD Official Use Only - General]

Reviewed-by: Tao Zhou <tao.zhou1 at amd.com>

> -----Original Message-----
> From: amd-gfx <amd-gfx-bounces at lists.freedesktop.org> On Behalf Of Candice Li
> Sent: Friday, February 2, 2024 7:13 PM
> To: amd-gfx at lists.freedesktop.org
> Cc: Li, Candice <Candice.Li at amd.com>
> Subject: [PATCH] drm/amd/pm: Retrieve UMC ODECC error count from aca bank
>
> Instead of software managed counters.
>
> Signed-off-by: Candice Li <candice.li at amd.com>
> ---
>  drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c | 6 +++++-
>  1 file changed, 5 insertions(+), 1 deletion(-)
>
> 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 d6e14a5f406e63..03873d784be6d6 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
> @@ -2552,8 +2552,12 @@ static int mca_umc_mca_get_err_count(const struct
> mca_ras_info *mca_ras, struct
>                                    enum amdgpu_mca_error_type type, struct
> mca_bank_entry *entry, uint32_t *count)  {
>       uint64_t status0;
> +     uint32_t ext_error_code;
> +     uint32_t odecc_err_cnt;
>
>       status0 = entry->regs[MCA_REG_IDX_STATUS];
> +     ext_error_code = MCA_REG__STATUS__ERRORCODEEXT(status0);
> +     odecc_err_cnt =
> +MCA_REG__MISC0__ERRCNT(entry->regs[MCA_REG_IDX_MISC0]);
>
>       if (!REG_GET_FIELD(status0, MCMP1_STATUST0, Val)) {
>               *count = 0;
> @@ -2563,7 +2567,7 @@ static int mca_umc_mca_get_err_count(const struct
> mca_ras_info *mca_ras, struct
>       if (umc_v12_0_is_deferred_error(adev, status0) ||
>           umc_v12_0_is_uncorrectable_error(adev, status0) ||
>           umc_v12_0_is_correctable_error(adev, status0))
> -             *count = 1;
> +             *count = (ext_error_code == 0) ? odecc_err_cnt : 1;
>
>       return 0;
>  }
> --
> 2.25.1