All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Thomas Hellström" <thomas.hellstrom@linux.intel.com>
To: intel-xe@lists.freedesktop.org
Cc: Christian Koenig <christian.koenig@amd.com>,
	dri-devel@lists.freedesktop.org
Subject: [Intel-xe] [PATCH 0/3] drm/ttm: Reservation object individualization update
Date: Thu, 25 May 2023 17:02:02 +0200	[thread overview]
Message-ID: <20230525150205.194098-1-thomas.hellstrom@linux.intel.com> (raw)

A couple of patches to modify the individualizing somewhat:

The motivation is that we run into trouble with the xe driver doing the
resv individualization in a clean way, having to grab the vm-wide sleeping
lock in a close- or release path which isn't really optimal. While
addressing that, some fly-by cleanups.

Patch 1: Makes sure the bulk move is removed at individualizing time, which is
convenient since we have all required locks.

Patch 2: Individualize even if fence copying fails.

Patch 3: Use a define instead of open-coded timeout


Thomas Hellström (3):
  drm/ttm: Clear the buffer object bulk move at individualize time
  drm/ttm: Clean up bo individualizing somewhat
  drm/ttm: Use a define for the resv wait timeout

 drivers/gpu/drm/ttm/ttm_bo.c | 73 +++++++++++++++++++++---------------
 1 file changed, 42 insertions(+), 31 deletions(-)

-- 
2.39.2


WARNING: multiple messages have this Message-ID (diff)
From: "Thomas Hellström" <thomas.hellstrom@linux.intel.com>
To: intel-xe@lists.freedesktop.org
Cc: "Matthew Brost" <matthew.brost@intel.com>,
	"Thomas Hellström" <thomas.hellstrom@linux.intel.com>,
	"Christian Koenig" <christian.koenig@amd.com>,
	dri-devel@lists.freedesktop.org
Subject: [PATCH 0/3] drm/ttm: Reservation object individualization update
Date: Thu, 25 May 2023 17:02:02 +0200	[thread overview]
Message-ID: <20230525150205.194098-1-thomas.hellstrom@linux.intel.com> (raw)

A couple of patches to modify the individualizing somewhat:

The motivation is that we run into trouble with the xe driver doing the
resv individualization in a clean way, having to grab the vm-wide sleeping
lock in a close- or release path which isn't really optimal. While
addressing that, some fly-by cleanups.

Patch 1: Makes sure the bulk move is removed at individualizing time, which is
convenient since we have all required locks.

Patch 2: Individualize even if fence copying fails.

Patch 3: Use a define instead of open-coded timeout


Thomas Hellström (3):
  drm/ttm: Clear the buffer object bulk move at individualize time
  drm/ttm: Clean up bo individualizing somewhat
  drm/ttm: Use a define for the resv wait timeout

 drivers/gpu/drm/ttm/ttm_bo.c | 73 +++++++++++++++++++++---------------
 1 file changed, 42 insertions(+), 31 deletions(-)

-- 
2.39.2


             reply	other threads:[~2023-05-25 15:02 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-05-25 15:02 Thomas Hellström [this message]
2023-05-25 15:02 ` [PATCH 0/3] drm/ttm: Reservation object individualization update Thomas Hellström
2023-05-25 15:02 ` [Intel-xe] [PATCH 1/3] drm/ttm: Clear the buffer object bulk move at individualize time Thomas Hellström
2023-05-25 15:02   ` Thomas Hellström
2023-06-01 10:38   ` [Intel-xe] " Christian König
2023-06-01 10:38     ` Christian König
2023-05-25 15:02 ` [Intel-xe] [PATCH 2/3] drm/ttm: Clean up bo individualizing somewhat Thomas Hellström
2023-05-25 15:02   ` Thomas Hellström
2023-05-25 15:02 ` [Intel-xe] [PATCH 3/3] drm/ttm: Use a define for the resv wait timeout Thomas Hellström
2023-05-25 15:02   ` Thomas Hellström
2023-05-25 15:04 ` [Intel-xe] ✓ CI.Patch_applied: success for drm/ttm: Reservation object individualization update Patchwork
2023-05-25 15:06 ` [Intel-xe] ✓ CI.KUnit: " Patchwork
2023-05-25 15:10 ` [Intel-xe] ✓ CI.Build: " Patchwork
2023-05-25 15:39 ` [Intel-xe] ○ CI.BAT: info " Patchwork

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=20230525150205.194098-1-thomas.hellstrom@linux.intel.com \
    --to=thomas.hellstrom@linux.intel.com \
    --cc=christian.koenig@amd.com \
    --cc=dri-devel@lists.freedesktop.org \
    --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 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.