All of lore.kernel.org
 help / color / mirror / Atom feed
From: Matthew Brost <matthew.brost@intel.com>
To: intel-xe@lists.freedesktop.org, dri-devel@lists.freedesktop.org
Cc: "Carlos Santa" <carlos.santa@intel.com>,
	"Ryan Neph" <ryanneph@google.com>,
	"Christian Koenig" <christian.koenig@amd.com>,
	"Huang Rui" <ray.huang@amd.com>,
	"Matthew Auld" <matthew.auld@intel.com>,
	"Maarten Lankhorst" <maarten.lankhorst@linux.intel.com>,
	"Maxime Ripard" <mripard@kernel.org>,
	"Thomas Zimmermann" <tzimmermann@suse.de>,
	"David Airlie" <airlied@gmail.com>,
	"Simona Vetter" <simona@ffwll.ch>,
	linux-kernel@vger.kernel.org,
	"Thomas Hellström" <thomas.hellstrom@linux.intel.com>
Subject: [PATCH v3 01/33] drm/ttm/pool: Allow backing off reclaim at the beneficial order
Date: Fri, 10 Jul 2026 19:55:47 -0700	[thread overview]
Message-ID: <20260711025619.2540575-2-matthew.brost@intel.com> (raw)
In-Reply-To: <20260711025619.2540575-1-matthew.brost@intel.com>

Allocating at the pool's beneficial order normally uses
__GFP_RETRY_MAYFAIL to push hard for a contiguous high-order page. When
beneficial-order allocations have recently been failing, this retry just
burns CPU cycles in reclaim/compaction before falling back to a smaller
order anyway.

Add a beneficial_reclaim_backoff flag to struct ttm_operation_ctx and
plumb it through to ttm_pool_alloc_page(). When set, the beneficial
order is treated like the orders we already consider not worth stalling
for: __GFP_RECLAIM is cleared so the allocation skips reclaim/compaction
entirely, and the __GFP_NORETRY clearing / __GFP_RETRY_MAYFAIL promotion
is skipped. Together this makes the allocator back off quickly to a
smaller order instead of stalling.

This is a no-op until a caller opts in.

Cc: Carlos Santa <carlos.santa@intel.com>
Cc: Ryan Neph <ryanneph@google.com>
Cc: Christian Koenig <christian.koenig@amd.com>
Cc: Huang Rui <ray.huang@amd.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Maxime Ripard <mripard@kernel.org>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: David Airlie <airlied@gmail.com>
Cc: Simona Vetter <simona@ffwll.ch>
Cc: dri-devel@lists.freedesktop.org
Cc: linux-kernel@vger.kernel.org
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Assisted-by: GitHub_Copilot:claude-opus-4.8
Signed-off-by: Matthew Brost <matthew.brost@intel.com>

---

v3:
 - Require a valid beneficial order before backing off reclaim in
   ttm_pool_alloc_page() (Sashiko)
---
 drivers/gpu/drm/ttm/ttm_pool.c | 12 ++++++++----
 include/drm/ttm/ttm_bo.h       |  7 +++++++
 2 files changed, 15 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
index 3d5f2ae0a456..ab242ad4339e 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -145,7 +145,8 @@ static int ttm_pool_nid(struct ttm_pool *pool)
 
 /* Allocate pages of size 1 << order with the given gfp_flags */
 static struct page *ttm_pool_alloc_page(struct ttm_pool *pool, gfp_t gfp_flags,
-					unsigned int order)
+					unsigned int order,
+					bool beneficial_reclaim_backoff)
 {
 	const unsigned int beneficial_order = ttm_pool_beneficial_order(pool);
 	unsigned long attr = DMA_ATTR_FORCE_CONTIGUOUS;
@@ -165,10 +166,12 @@ static struct page *ttm_pool_alloc_page(struct ttm_pool *pool, gfp_t gfp_flags,
 	 * Do not add latency to the allocation path for allocations orders
 	 * device tolds us do not bring them additional performance gains.
 	 */
-	if (order && beneficial_order && order != beneficial_order)
+	if (order && beneficial_order &&
+	    (beneficial_reclaim_backoff || order != beneficial_order))
 		gfp_flags &= ~__GFP_RECLAIM;
 
-	if (beneficial_order && order == beneficial_order) {
+	if (!beneficial_reclaim_backoff &&
+	    beneficial_order && order == beneficial_order) {
 		gfp_flags &= ~__GFP_NORETRY;
 		gfp_flags |= __GFP_RETRY_MAYFAIL;
 	}
@@ -814,7 +817,8 @@ static int __ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt,
 		if (!p) {
 			page_caching = ttm_cached;
 			allow_pools = false;
-			p = ttm_pool_alloc_page(pool, gfp_flags, order);
+			p = ttm_pool_alloc_page(pool, gfp_flags, order,
+						ctx->beneficial_reclaim_backoff);
 		}
 		/* If that fails, lower the order if possible and retry. */
 		if (!p) {
diff --git a/include/drm/ttm/ttm_bo.h b/include/drm/ttm/ttm_bo.h
index 8310bc3d55f9..fd814b5cf535 100644
--- a/include/drm/ttm/ttm_bo.h
+++ b/include/drm/ttm/ttm_bo.h
@@ -187,6 +187,13 @@ struct ttm_operation_ctx {
 	 * when multiple BOs share the same reservation object @resv.
 	 */
 	bool allow_res_evict;
+	/**
+	 * @beneficial_reclaim_backoff: Back off from direct reclaim at the
+	 * pool's beneficial order. Useful when beneficial-order allocation has
+	 * recently been failing, to avoid burning CPU cycles in
+	 * reclaim/compaction before falling back to a smaller order anyway.
+	 */
+	bool beneficial_reclaim_backoff;
 	/**
 	 * @resv: Reservation object to be used together with
 	 * @allow_res_evict.
-- 
2.34.1


  reply	other threads:[~2026-07-11  2:56 UTC|newest]

Thread overview: 59+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-07-11  2:55 [PATCH v3 00/33] drm/ttm, drm/xe: Minimize dma-resv hold times and defragment sub-optimally backed BOs Matthew Brost
2026-07-11  2:55 ` Matthew Brost [this message]
2026-07-11  2:55 ` [PATCH v3 02/33] drm/ttm/pool: Add ttm_pool_page_order_nodma() helper Matthew Brost
2026-07-11  2:55 ` [PATCH v3 03/33] drm/ttm: Record sub-optimal page order allocations in ttm_tt Matthew Brost
2026-07-11  2:55 ` [PATCH v3 04/33] drm/ttm: Introduce ttm_pool_alloc_iter for __ttm_pool_alloc() Matthew Brost
2026-07-11  2:55 ` [PATCH v3 05/33] drm/ttm: Support defragmentation moves Matthew Brost
2026-07-11  3:12   ` sashiko-bot
2026-07-11  2:55 ` [PATCH v3 06/33] drm/ttm: Add fault injection for beneficial-order allocation failures Matthew Brost
2026-07-11  2:55 ` [PATCH v3 07/33] drm/ttm: Harvest beneficial-order pages on defragmentation moves Matthew Brost
2026-07-11  3:16   ` sashiko-bot
2026-07-11  2:55 ` [PATCH v3 08/33] drm/ttm: Bound page (re)allocation per defragmentation move Matthew Brost
2026-07-11  3:12   ` sashiko-bot
2026-07-11  2:55 ` [PATCH v3 09/33] drm/ttm: Preallocate beneficial-order defrag pages outside the lock Matthew Brost
2026-07-11  3:08   ` sashiko-bot
2026-07-11  2:55 ` [PATCH v3 10/33] drm/ttm: Add full out-of-lock preallocation for ttm_pool_alloc() Matthew Brost
2026-07-11  2:55 ` [PATCH v3 11/33] drm/gpusvm: Add a DMA-mapping accounting callback Matthew Brost
2026-07-11  3:10   ` sashiko-bot
2026-07-11  2:55 ` [PATCH v3 12/33] drm/xe: Add debugfs stats for DMA-mapped pages per order Matthew Brost
2026-07-11  3:21   ` sashiko-bot
2026-07-11  2:55 ` [PATCH v3 13/33] drm/xe: Flush L2 asynchronously in xe_bo_trigger_rebind() Matthew Brost
2026-07-11  2:56 ` [PATCH v3 14/33] drm/xe: Destroy page tables after unlinking all VMAs on VM close Matthew Brost
2026-07-11  2:56 ` [PATCH v3 15/33] drm/xe: Track BOs backed at a sub-optimal page order Matthew Brost
2026-07-11  2:56 ` [PATCH v3 16/33] drm/xe: Back off beneficial-order reclaim under defrag pressure Matthew Brost
2026-07-11  3:11   ` sashiko-bot
2026-07-11  2:56 ` [PATCH v3 17/33] drm/xe: Add xe_migrate_copy_defrag() for on-GPU defrag copies Matthew Brost
2026-07-11  2:56 ` [PATCH v3 18/33] drm/xe: Handle defrag moves in xe_bo_move() Matthew Brost
2026-07-11  3:21   ` sashiko-bot
2026-07-11  2:56 ` [PATCH v3 19/33] drm/xe: Skip self-copies for borrowed pages on defrag moves Matthew Brost
2026-07-11  2:56 ` [PATCH v3 20/33] drm/xe: Add a page defragmentation worker Matthew Brost
2026-07-11  3:18   ` sashiko-bot
2026-07-11  2:56 ` [PATCH v3 21/33] drm/xe: Add defrag GT stats Matthew Brost
2026-07-11  3:12   ` sashiko-bot
2026-07-11  2:56 ` [PATCH v3 22/33] drm/xe: Add Kconfig.profile options for BO defrag configuration Matthew Brost
2026-07-11  2:56 ` [PATCH v3 23/33] drm/xe: Defrag using out-of-lock page preallocation Matthew Brost
2026-07-11  2:56 ` [PATCH v3 24/33] drm/xe: Add defrag profiling tracepoints Matthew Brost
2026-07-11  2:56 ` [PATCH v3 25/33] drm/xe: Preallocate system BO backing outside the dma-resv lock Matthew Brost
2026-07-11  3:19   ` sashiko-bot
2026-07-11  2:56 ` [PATCH v3 26/33] drm/xe: Add tracepoint for xe_gem_create_ioctl Matthew Brost
2026-07-11  3:23   ` sashiko-bot
2026-07-11  2:56 ` [PATCH v3 27/33] drm/xe: Add IOVA-based xe_res_cursor variant Matthew Brost
2026-07-11  3:15   ` sashiko-bot
2026-07-11  2:56 ` [PATCH v3 28/33] drm/xe: Use IOVA-based DMA mapping for eligible tt BOs Matthew Brost
2026-07-11  2:56 ` [PATCH v3 29/33] drm/xe: Add per-device dependency scheduler for IOVA defrag finalize Matthew Brost
2026-07-11  3:21   ` sashiko-bot
2026-07-11  2:56 ` [PATCH v3 30/33] drm/xe: Add packed copy-step IOVA mapping for defrag Matthew Brost
2026-07-11  2:56 ` [PATCH v3 31/33] drm/xe: Blit src-natural to dst-packed for defrag-IOVA copies Matthew Brost
2026-07-11  3:24   ` sashiko-bot
2026-07-11  2:56 ` [PATCH v3 32/33] drm/xe: Finalize defrag-IOVA moves with post-copy job Matthew Brost
2026-07-11  2:56 ` [PATCH v3 33/33] drm/amdgpu: Preallocate system BO pages outside the reservation lock Matthew Brost
2026-07-11  3:28   ` sashiko-bot
2026-07-11 10:46   ` Christian König
2026-07-13 20:24     ` Matthew Brost
2026-07-14  9:17       ` Christian König
2026-07-14 15:15         ` Matthew Brost
2026-07-11  3:05 ` ✗ CI.checkpatch: warning for drm/ttm, drm/xe: Minimize dma-resv hold times and defragment sub-optimally backed BOs (rev2) Patchwork
2026-07-11  3:07 ` ✓ CI.KUnit: success " Patchwork
2026-07-11  3:22 ` ✗ CI.checksparse: warning " Patchwork
2026-07-11  3:42 ` ✓ Xe.CI.BAT: success " Patchwork
2026-07-11 10:20 ` ✓ Xe.CI.FULL: " 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=20260711025619.2540575-2-matthew.brost@intel.com \
    --to=matthew.brost@intel.com \
    --cc=airlied@gmail.com \
    --cc=carlos.santa@intel.com \
    --cc=christian.koenig@amd.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=maarten.lankhorst@linux.intel.com \
    --cc=matthew.auld@intel.com \
    --cc=mripard@kernel.org \
    --cc=ray.huang@amd.com \
    --cc=ryanneph@google.com \
    --cc=simona@ffwll.ch \
    --cc=thomas.hellstrom@linux.intel.com \
    --cc=tzimmermann@suse.de \
    /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.