Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
To: intel-xe@lists.freedesktop.org,
	Ashutosh Dixit <ashutosh.dixit@intel.com>
Subject: [PATCH 1/3] drm/xe/xe_oa: Clear status only if relevant bits are set
Date: Fri, 21 Aug 2026 15:23:40 -0700	[thread overview]
Message-ID: <20260821222338.1053887-6-umesh.nerlige.ramappa@intel.com> (raw)
In-Reply-To: <20260821222338.1053887-5-umesh.nerlige.ramappa@intel.com>

OA monitors only a few bits in the status field. The current
read-modify-write will write to the MMIO even if none of the relevant
bits are set. Clear the status only if relevant bits are set.

Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
---
v2: Move comment (Ashutosh)
---
 drivers/gpu/drm/xe/xe_oa.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c
index b460fcdfca15..024940478c06 100644
--- a/drivers/gpu/drm/xe/xe_oa.c
+++ b/drivers/gpu/drm/xe/xe_oa.c
@@ -542,15 +542,17 @@ static int xe_oa_wait_unlocked(struct xe_oa_stream *stream)
 static int __xe_oa_read(struct xe_oa_stream *stream, char __user *buf,
 			size_t count, size_t *offset)
 {
-	/* Only clear our bits to avoid side-effects */
-	stream->oa_status = xe_mmio_rmw32(&stream->gt->mmio, __oa_regs(stream)->oa_status,
-					  OASTATUS_RELEVANT_BITS, 0);
+	stream->oa_status = xe_mmio_read32(&stream->gt->mmio, __oa_regs(stream)->oa_status);
 	/*
 	 * Signal to userspace that there is non-zero OA status to read via
 	 * @DRM_XE_OBSERVATION_IOCTL_STATUS observation stream fd ioctl
 	 */
-	if (stream->oa_status & OASTATUS_RELEVANT_BITS)
+	if (stream->oa_status & OASTATUS_RELEVANT_BITS) {
+		/* Only clear our bits to avoid side-effects */
+		xe_mmio_write32(&stream->gt->mmio, __oa_regs(stream)->oa_status,
+				stream->oa_status & ~OASTATUS_RELEVANT_BITS);
 		return -EIO;
+	}
 
 	return xe_oa_append_reports(stream, buf, count, offset);
 }
-- 
2.51.0


  reply	other threads:[~2026-08-21 22:23 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-08-21 22:23 [PATCH 0/3] Modify the SW tail logic in OA Umesh Nerlige Ramappa
2026-08-21 22:23 ` Umesh Nerlige Ramappa [this message]
2026-08-21 22:23 ` [PATCH 2/3] drm/xe/xe_oa: Avoid checking and setting fields in the OA report Umesh Nerlige Ramappa
2026-08-21 22:34   ` sashiko-bot
2026-08-24 15:39   ` Dixit, Ashutosh
2026-08-26 23:30     ` Umesh Nerlige Ramappa
2026-08-26 23:44       ` Dixit, Ashutosh
2026-08-21 22:23 ` [PATCH 3/3] drm/xe/xe_oa: Add a lag to the reports that is exported to user Umesh Nerlige Ramappa
2026-08-21 22:37   ` sashiko-bot
2026-08-24 15:57   ` Dixit, Ashutosh
2026-08-21 22:30 ` ✓ CI.KUnit: success for Modify the SW tail logic in OA Patchwork
2026-08-21 23:25 ` ✓ Xe.CI.BAT: " Patchwork
2026-08-22  0:33 ` ✓ Xe.CI.FULL: " Patchwork
  -- strict thread matches above, loose matches on Subject: below --
2026-08-21 20:07 [PATCH 0/3] " Umesh Nerlige Ramappa
2026-08-21 20:07 ` [PATCH 1/3] drm/xe/xe_oa: Clear status only if relevant bits are set Umesh Nerlige Ramappa
2026-08-06 22:47 [PATCH 0/3] Modify the SW tail logic in OA Umesh Nerlige Ramappa
2026-08-06 22:47 ` [PATCH 1/3] drm/xe/xe_oa: Clear status only if relevant bits are set Umesh Nerlige Ramappa
2026-08-10 22:37   ` Dixit, Ashutosh
2026-07-30 23:35 [PATCH 0/3] Modify the SW tail logic in OA Umesh Nerlige Ramappa
2026-07-30 23:35 ` [PATCH 1/3] drm/xe/xe_oa: Clear status only if relevant bits are set Umesh Nerlige Ramappa
2026-07-22 21:54 [PATCH 0/3] Modify the SW tail logic in OA Umesh Nerlige Ramappa
2026-07-22 21:54 ` [PATCH 1/3] drm/xe/xe_oa: Clear status only if relevant bits are set Umesh Nerlige Ramappa
2026-07-21 23:48 [PATCH 0/3] Modify the SW tail logic in OA Umesh Nerlige Ramappa
2026-07-21 23:48 ` [PATCH 1/3] drm/xe/xe_oa: Clear status only if relevant bits are set Umesh Nerlige Ramappa

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=20260821222338.1053887-6-umesh.nerlige.ramappa@intel.com \
    --to=umesh.nerlige.ramappa@intel.com \
    --cc=ashutosh.dixit@intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    /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