From: "Lazar, Lijo" <lijo.lazar@amd.com>
To: Asad Kamal <asad.kamal@amd.com>, amd-gfx@lists.freedesktop.org
Cc: hawking.zhang@amd.com, le.ma@amd.com, shiwu.zhang@amd.com,
alexander.deucher@amd.com, Kevin.Wang@amd.com
Subject: Re: [PATCH] drm/amd/pm: Report SMU 15.0.8 XGMI bandwidth
Date: Thu, 22 Oct 2026 19:37:51 +0530 [thread overview]
Message-ID: <de20d62d-8d89-4e4e-bc68-1acd14e1d4aa@amd.com> (raw)
In-Reply-To: <20261022123200.2222192-1-asad.kamal@amd.com>
On 22-Oct-26 6:02 PM, Asad Kamal wrote:
> SMU 15.0.8 firmware reports accumulated XGMI read and write bandwidth.
> The driver publishes those counters as transferred data, in KB.
>
> Publish them as xgmi_read_bandwidth_acc and xgmi_write_bandwidth_acc,
> with unit GB/s.
>
> Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Thanks,
Lijo
> ---
> drivers/gpu/drm/amd/include/kgd_pp_interface.h | 2 ++
> drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0_8_ppt.c | 6 ++++--
> drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0_8_ppt.h | 8 ++++----
> 3 files changed, 10 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
> index f92bccb8cb41..17f76071b514 100644
> --- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h
> +++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
> @@ -685,6 +685,8 @@ enum amdgpu_metrics_attr_id {
> AMDGPU_METRICS_ATTR_ID_SYSTEM_TEMP_OAM_4_5_6_7_3V3_VR,
> AMDGPU_METRICS_ATTR_ID_SYSTEM_TEMP_IBC_HSC,
> AMDGPU_METRICS_ATTR_ID_SYSTEM_TEMP_IBC,
> + AMDGPU_METRICS_ATTR_ID_XGMI_READ_BANDWIDTH_ACC,
> + AMDGPU_METRICS_ATTR_ID_XGMI_WRITE_BANDWIDTH_ACC,
> AMDGPU_METRICS_ATTR_ID_MAX,
> };
>
> diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0_8_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0_8_ppt.c
> index 2254c2d414d2..bacdc1a2dd38 100644
> --- a/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0_8_ppt.c
> +++ b/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0_8_ppt.c
> @@ -2041,8 +2041,10 @@ static ssize_t smu_v15_0_8_get_gpu_metrics(struct smu_context *smu, void **table
> gpu_metrics->xgmi_link_status[j] = ret;
> }
>
> - gpu_metrics->xgmi_read_data_acc = SMUQ10_ROUND(metrics->XgmiReadBandwidthAcc);
> - gpu_metrics->xgmi_write_data_acc = SMUQ10_ROUND(metrics->XgmiWriteBandwidthAcc);
> + gpu_metrics->xgmi_read_bandwidth_acc =
> + SMUQ10_ROUND(metrics->XgmiReadBandwidthAcc);
> + gpu_metrics->xgmi_write_bandwidth_acc =
> + SMUQ10_ROUND(metrics->XgmiWriteBandwidthAcc);
>
> for (i = 0; i < NUM_XCC(adev->gfx.xcc_mask); ++i) {
> inst = GET_INST(GC, i);
> diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0_8_ppt.h b/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0_8_ppt.h
> index c3835c81d313..8c7e808aa8eb 100644
> --- a/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0_8_ppt.h
> +++ b/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0_8_ppt.h
> @@ -146,10 +146,10 @@ typedef struct {
> SMU_ARRAY(SMU_MATTR(XGMI_LINK_STATUS), SMU_MUNIT(NONE), \
> SMU_MTYPE(U16), xgmi_link_status, \
> SMU_15_0_8_NUM_XGMI_LINKS); \
> - SMU_SCALAR(SMU_MATTR(XGMI_READ_DATA_ACC), SMU_MUNIT(DATA_1), \
> - SMU_MTYPE(U64), xgmi_read_data_acc); \
> - SMU_SCALAR(SMU_MATTR(XGMI_WRITE_DATA_ACC), SMU_MUNIT(DATA_1), \
> - SMU_MTYPE(U64), xgmi_write_data_acc); \
> + SMU_SCALAR(SMU_MATTR(XGMI_READ_BANDWIDTH_ACC), SMU_MUNIT(BW_1), \
> + SMU_MTYPE(U64), xgmi_read_bandwidth_acc); \
> + SMU_SCALAR(SMU_MATTR(XGMI_WRITE_BANDWIDTH_ACC), SMU_MUNIT(BW_1), \
> + SMU_MTYPE(U64), xgmi_write_bandwidth_acc); \
> SMU_SCALAR(SMU_MATTR(FIRMWARE_TIMESTAMP), SMU_MUNIT(TIME_2), \
> SMU_MTYPE(U64), firmware_timestamp); \
> SMU_ARRAY(SMU_MATTR(CURRENT_GFXCLK), SMU_MUNIT(CLOCK_1), \
prev parent reply other threads:[~2026-10-22 14:08 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-10-22 12:32 [PATCH] drm/amd/pm: Report SMU 15.0.8 XGMI bandwidth Asad Kamal
2026-10-22 14:07 ` Lazar, Lijo [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=de20d62d-8d89-4e4e-bc68-1acd14e1d4aa@amd.com \
--to=lijo.lazar@amd.com \
--cc=Kevin.Wang@amd.com \
--cc=alexander.deucher@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=asad.kamal@amd.com \
--cc=hawking.zhang@amd.com \
--cc=le.ma@amd.com \
--cc=shiwu.zhang@amd.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.