From: Xin Wang <x.wang@intel.com>
To: intel-xe@lists.freedesktop.org
Cc: Xin Wang <x.wang@intel.com>, Matt Roper <matthew.d.roper@intel.com>
Subject: [PATCH] drm/xe/query: Avoid global forcewake in cycle query path
Date: Thu, 4 Jun 2026 22:19:44 -0700 [thread overview]
Message-ID: <20260605051944.1541085-1-x.wang@intel.com> (raw)
Engine cycle query is a lightweight timestamp path and should not wake
unrelated GT domains. Limit forcewake scope to what the query actually
needs.
Suggested-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Xin Wang <x.wang@intel.com>
---
drivers/gpu/drm/xe/xe_query.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/xe/xe_query.c b/drivers/gpu/drm/xe/xe_query.c
index 8c7d54498f38..dc975f595368 100644
--- a/drivers/gpu/drm/xe/xe_query.c
+++ b/drivers/gpu/drm/xe/xe_query.c
@@ -119,6 +119,7 @@ query_engine_cycles(struct xe_device *xe,
struct drm_xe_engine_class_instance *eci;
struct drm_xe_query_engine_cycles resp;
size_t size = sizeof(resp);
+ enum xe_force_wake_domains fw_domain;
__ktime_func_t cpu_clock;
struct xe_hw_engine *hwe;
struct xe_gt *gt;
@@ -154,8 +155,10 @@ query_engine_cycles(struct xe_device *xe,
if (!hwe)
return -EINVAL;
- xe_with_force_wake(fw_ref, gt_to_fw(gt), XE_FORCEWAKE_ALL) {
- if (!xe_force_wake_ref_has_domain(fw_ref.domains, XE_FORCEWAKE_ALL))
+ fw_domain = xe_hw_engine_to_fw_domain(hwe);
+
+ xe_with_force_wake(fw_ref, gt_to_fw(gt), fw_domain) {
+ if (!xe_force_wake_ref_has_domain(fw_ref.domains, fw_domain))
return -EIO;
hwe_read_timestamp(hwe, &resp.engine_cycles, &resp.cpu_timestamp,
--
2.43.0
next reply other threads:[~2026-06-05 5:19 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-06-05 5:19 Xin Wang [this message]
2026-06-05 5:26 ` ✓ CI.KUnit: success for drm/xe/query: Avoid global forcewake in cycle query path Patchwork
2026-06-05 6:20 ` ✓ Xe.CI.BAT: " Patchwork
2026-06-05 16:57 ` ✓ Xe.CI.FULL: " Patchwork
2026-06-11 20:52 ` [PATCH] " Matt Roper
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=20260605051944.1541085-1-x.wang@intel.com \
--to=x.wang@intel.com \
--cc=intel-xe@lists.freedesktop.org \
--cc=matthew.d.roper@intel.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox