Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Ashutosh Dixit <ashutosh.dixit@intel.com>
To: intel-xe@lists.freedesktop.org
Cc: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>,
	Guy Zadicario <guy.zadicario@intel.com>
Subject: [PATCH] drm/xe/oa: Insert wmb/sfence before enabling OA
Date: Mon, 26 Aug 2024 16:29:06 -0700	[thread overview]
Message-ID: <20240826232906.1849613-1-ashutosh.dixit@intel.com> (raw)

In some simulation environments, we occasionally see warnings such as "OAG
Buffer register is not programmed (has value 0). Register offset db08".
This means OA has been enabled before it has been fully configured. Or, the
register write enabling OA has overtaken previous OA configuration register
writes.

Therefore, insert a wmb/sfence to preserve OA register write ordering
before enabling OA.

Reported-by: Guy Zadicario <guy.zadicario@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
---
 drivers/gpu/drm/xe/xe_oa.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c
index 4d4541e0b24c0..02a6baa3c37d9 100644
--- a/drivers/gpu/drm/xe/xe_oa.c
+++ b/drivers/gpu/drm/xe/xe_oa.c
@@ -440,6 +440,9 @@ static void xe_oa_enable(struct xe_oa_stream *stream)
 	val = __format_to_oactrl(format, regs->oa_ctrl_counter_select_mask) |
 		__oa_ccs_select(stream) | OAG_OACONTROL_OA_COUNTER_ENABLE;
 
+	/* Flush previous writes to HW before enabling OA */
+	wmb();
+
 	xe_mmio_write32(stream->gt, regs->oa_ctrl, val);
 }
 
-- 
2.41.0


             reply	other threads:[~2024-08-26 23:29 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-08-26 23:29 Ashutosh Dixit [this message]
2024-08-26 23:34 ` ✓ CI.Patch_applied: success for drm/xe/oa: Insert wmb/sfence before enabling OA Patchwork
2024-08-26 23:35 ` ✗ CI.checkpatch: warning " Patchwork
2024-08-26 23:36 ` ✓ CI.KUnit: success " Patchwork
2024-08-26 23:48 ` ✓ CI.Build: " Patchwork
2024-08-26 23:50 ` ✓ CI.Hooks: " Patchwork
2024-08-26 23:52 ` ✓ CI.checksparse: " Patchwork
2024-08-27  0:11 ` ✓ CI.BAT: " Patchwork
2024-08-27  5:44 ` ✗ CI.FULL: failure " Patchwork
  -- strict thread matches above, loose matches on Subject: below --
2024-08-26 23:34 [PATCH] " Ashutosh Dixit
2024-08-28 15:55 Ashutosh Dixit
2024-09-10  0:43 Ashutosh Dixit
2024-09-10  1:39 Ashutosh Dixit
2024-09-10  2:59 Ashutosh Dixit
2024-09-10 10:14 ` Jani Nikula
2024-09-10 16:17   ` Dixit, Ashutosh
2024-09-10 16:14 ` Matthew Brost
2024-09-10 20:28   ` Dixit, Ashutosh

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=20240826232906.1849613-1-ashutosh.dixit@intel.com \
    --to=ashutosh.dixit@intel.com \
    --cc=guy.zadicario@intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=umesh.nerlige.ramappa@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