[PATCH v2 01/33] drm/ttm/pool: Allow backing off reclaim at the beneficial order

[Matthew Brost]

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@xxxxxxxxx>
Cc: Ryan Neph <ryanneph@xxxxxxxxxx>
Cc: Christian Koenig <christian.koenig@xxxxxxx>
Cc: Huang Rui <ray.huang@xxxxxxx>
Cc: Matthew Auld <matthew.auld@xxxxxxxxx>
Cc: Maarten Lankhorst <maarten.lankhorst@xxxxxxxxxxxxxxx>
Cc: Maxime Ripard <mripard@xxxxxxxxxx>
Cc: Thomas Zimmermann <tzimmermann@xxxxxxx>
Cc: David Airlie <airlied@xxxxxxxxx>
Cc: Simona Vetter <simona@xxxxxxxx>
Cc: dri-devel@xxxxxxxxxxxxxxxxxxxxx
Cc: linux-kernel@xxxxxxxxxxxxxxx
Cc: Thomas Hellström <thomas.hellstrom@xxxxxxxxxxxxxxx>
Assisted-by: GitHub_Copilot:claude-opus-4.8
Signed-off-by: Matthew Brost <matthew.brost@xxxxxxxxx>
---
 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..dbe977412a81 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_reclaim_backoff ||
+		      (beneficial_order && 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