[PATCH v2 3/5] drm/amdgpu: Add ras helper to query boot errors v2
Zhang, Morris
Shiwu.Zhang at amd.com
Wed Jan 3 09:46:00 UTC 2024
[AMD Official Use Only - General]
--Brs,
Morris Zhang
MLSE Linux ML SRDC
Ext. 25147
> -----Original Message-----
> From: amd-gfx <amd-gfx-bounces at lists.freedesktop.org> On Behalf Of Hawking
> Zhang
> Sent: Tuesday, January 2, 2024 10:08 PM
> To: amd-gfx at lists.freedesktop.org; Zhou1, Tao <Tao.Zhou1 at amd.com>; Yang,
> Stanley <Stanley.Yang at amd.com>; Wang, Yang(Kevin)
> <KevinYang.Wang at amd.com>; Chai, Thomas <YiPeng.Chai at amd.com>; Li,
> Candice <Candice.Li at amd.com>
> Cc: Deucher, Alexander <Alexander.Deucher at amd.com>; Ma, Le
> <Le.Ma at amd.com>; Lazar, Lijo <Lijo.Lazar at amd.com>; Zhang, Hawking
> <Hawking.Zhang at amd.com>
> Subject: [PATCH v2 3/5] drm/amdgpu: Add ras helper to query boot errors v2
>
> Add ras helper function to query boot time gpu errors.
> v2: use aqua_vanjaram smn addressing pattern
>
> Signed-off-by: Hawking Zhang <Hawking.Zhang at amd.com>
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 +
> drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 95
> +++++++++++++++++++++++++ drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h |
> 15 +++-
> 3 files changed, 110 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> index 616b6c911767..cd91533d641c 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> @@ -1328,6 +1328,7 @@ int emu_soc_asic_init(struct amdgpu_device *adev);
> #define WREG32_FIELD_OFFSET(reg, offset, field, val) \
> WREG32(mm##reg + offset, (RREG32(mm##reg + offset) &
> ~REG_FIELD_MASK(reg, field)) | (val) << REG_FIELD_SHIFT(reg, field))
>
> +#define AMDGPU_GET_REG_FIELD(x, h, l) (((x) & GENMASK_ULL(h, l)) >>
> +(l))
> /*
> * BIOS helpers.
> */
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
> index fc42fb6ee191..a901b00d4949 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
> @@ -3763,3 +3763,98 @@ int amdgpu_ras_error_statistic_ce_count(struct
> ras_err_data *err_data,
>
> return 0;
> }
> +
> +#define mmMP0_SMN_C2PMSG_92 0x1609C
> +#define mmMP0_SMN_C2PMSG_126 0x160BE
> +static void amdgpu_ras_boot_time_error_reporting(struct amdgpu_device
> *adev,
> + u32 instance, u32 boot_error)
> +{
> + u32 socket_id, aid_id, hbm_id;
> + u32 reg_data;
> + u64 reg_addr;
> +
> + socket_id = AMDGPU_RAS_GPU_ERR_SOCKET_ID(boot_error);
> + aid_id = AMDGPU_RAS_GPU_ERR_AID_ID(boot_error);
> + hbm_id = AMDGPU_RAS_GPU_ERR_HBM_ID(boot_error);
> +
> + /* The pattern for smn addressing in other SOC could be different from
> + * the one for aqua_vanjaram. We should revisit the code if the pattern
> + * is changed. In such case, replace the aqua_vanjaram implementation
> + * with more common helper */
> + reg_addr = (mmMP0_SMN_C2PMSG_92 << 2) +
> + aqua_vanjaram_encode_ext_smn_addressing(instance);
> +
> + reg_data = amdgpu_device_indirect_rreg_ext(adev, reg_addr);
> + dev_err(adev->dev, "socket: %d, aid: %d, firmware boot failed, fw status
> is 0x%x\n",
> + socket_id, aid_id, reg_data);
> +
> + if (AMDGPU_RAS_GPU_ERR_MEM_TRAINING(boot_error))
> + dev_info(adev->dev, "socket: %d, aid: %d, hbm: %d, memory
> training failed\n",
> + socket_id, aid_id, hbm_id);
> +
> + if (AMDGPU_RAS_GPU_ERR_FW_LOAD(boot_error))
> + dev_info(adev->dev, "socket: %d, aid: %d, firmware load failed at
> boot time\n",
> + socket_id, aid_id);
> +
> + if (AMDGPU_RAS_GPU_ERR_WAFL_LINK_TRAINING(boot_error))
> + dev_info(adev->dev, "socket: %d, aid: %d, wafl link training
> failed\n",
> + socket_id, aid_id);
> +
> + if (AMDGPU_RAS_GPU_ERR_XGMI_LINK_TRAINING(boot_error))
> + dev_info(adev->dev, "socket: %d, aid: %d, xgmi link training
> failed\n",
> + socket_id, aid_id);
> +
> + if (AMDGPU_RAS_GPU_ERR_USR_CP_LINK_TRAINING(boot_error))
> + dev_info(adev->dev, "socket: %d, aid: %d, usr cp link training
> failed\n",
> + socket_id, aid_id);
> +
> + if (AMDGPU_RAS_GPU_ERR_USR_DP_LINK_TRAINING(boot_error))
> + dev_info(adev->dev, "socket: %d, aid: %d, usr dp link training
> failed\n",
> + socket_id, aid_id);
> +
> + if (AMDGPU_RAS_GPU_ERR_HBM_MEM_TEST(boot_error))
> + dev_info(adev->dev, "socket: %d, aid: %d, hbm: %d, hbm
> memory test failed\n",
> + socket_id, aid_id, hbm_id);
> +
> + if (AMDGPU_RAS_GPU_ERR_HBM_BIST_TEST(boot_error))
> + dev_info(adev->dev, "socket: %d, aid: %d, hbm: %d, hbm bist
> test failed\n",
> + socket_id, aid_id, hbm_id);
> +}
> +
> +static int amdgpu_ras_wait_for_boot_complete(struct amdgpu_device *adev,
> + u32 instance, u32 *boot_error) {
> + u32 reg_addr;
> + u32 reg_data;
> + int retry_loop;
> +
> + /* The pattern for smn addressing in other SOC could be different from
> + * the one for aqua_vanjaram. We should revisit the code if the pattern
> + * is changed. In such case, replace the aqua_vanjaram implementation
> + * with more common helper */
> + reg_addr = (mmMP0_SMN_C2PMSG_126 << 2) +
> + aqua_vanjaram_encode_ext_smn_addressing(instance);
> +
> + for (retry_loop = 0; retry_loop < 1000; retry_loop++) {
> + reg_data = amdgpu_device_indirect_rreg_ext(adev, reg_addr);
> + if (AMDGPU_RAS_GPU_ERR_BOOT_STATUS(reg_data)) {
> + *boot_error = reg_data;
> + return 0;
> + }
> + msleep(1);
> + }
> +
> + *boot_error = reg_data;
> + return -ETIME;
> +}
> +
> +void amdgpu_ras_query_boot_status(struct amdgpu_device *adev, u32
> +num_instances) {
> + u32 boot_error = 0;
> + u32 i;
> +
> + for (i = 0; i < num_instances; i++) {
> + if (amdgpu_ras_wait_for_boot_complete(adev, i, &boot_error))
I suppose we need to check the boot_error value returned to report them in case that before timeout an error happens, right?
> + amdgpu_ras_boot_time_error_reporting(adev, i,
> boot_error);
> + }
> +}
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
> index 76fb85628716..5785b705c692 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
> @@ -32,6 +32,19 @@
>
> struct amdgpu_iv_entry;
>
> +#define AMDGPU_RAS_GPU_ERR_MEM_TRAINING(x)
> AMDGPU_GET_REG_FIELD(x, 0, 0)
> +#define AMDGPU_RAS_GPU_ERR_FW_LOAD(x)
> AMDGPU_GET_REG_FIELD(x, 1, 1)
> +#define AMDGPU_RAS_GPU_ERR_WAFL_LINK_TRAINING(x)
> AMDGPU_GET_REG_FIELD(x, 2, 2)
> +#define AMDGPU_RAS_GPU_ERR_XGMI_LINK_TRAINING(x)
> AMDGPU_GET_REG_FIELD(x, 3, 3)
> +#define AMDGPU_RAS_GPU_ERR_USR_CP_LINK_TRAINING(x)
> AMDGPU_GET_REG_FIELD(x, 4, 4)
> +#define AMDGPU_RAS_GPU_ERR_USR_DP_LINK_TRAINING(x)
> AMDGPU_GET_REG_FIELD(x, 5, 5)
> +#define AMDGPU_RAS_GPU_ERR_HBM_MEM_TEST(x)
> AMDGPU_GET_REG_FIELD(x, 6, 6)
> +#define AMDGPU_RAS_GPU_ERR_HBM_BIST_TEST(x)
> AMDGPU_GET_REG_FIELD(x, 7, 7)
> +#define AMDGPU_RAS_GPU_ERR_SOCKET_ID(x)
> AMDGPU_GET_REG_FIELD(x, 10, 8)
> +#define AMDGPU_RAS_GPU_ERR_AID_ID(x)
> AMDGPU_GET_REG_FIELD(x, 12, 11)
> +#define AMDGPU_RAS_GPU_ERR_HBM_ID(x)
> AMDGPU_GET_REG_FIELD(x, 13, 13)
> +#define AMDGPU_RAS_GPU_ERR_BOOT_STATUS(x)
> AMDGPU_GET_REG_FIELD(x, 31, 31)
> +
> #define AMDGPU_RAS_FLAG_INIT_BY_VBIOS (0x1 << 0)
> /* position of instance value in sub_block_index of
> * ta_ras_trigger_error_input, the sub block uses lower 12 bits @@ -818,5
> +831,5 @@ int amdgpu_ras_error_statistic_ce_count(struct ras_err_data
> *err_data, int amdgpu_ras_error_statistic_ue_count(struct ras_err_data
> *err_data,
> struct amdgpu_smuio_mcm_config_info *mcm_info,
> struct ras_err_addr *err_addr, u64 count);
> -
> +void amdgpu_ras_query_boot_status(struct amdgpu_device *adev, u32
> +num_instances);
> #endif
> --
> 2.17.1
More information about the amd-gfx
mailing list