[PATCH v3 1/1] mm: let node_reclaim() return the number of pages reclaimed

[PATCH v3 1/1] mm: let node_reclaim() return the number of pages reclaimed

[Petr Tesarik]

There is only one caller, get_page_from_freelist(), and it does not make
any use of the reason for skipping the reclaim, nor does it make any
distinction between a full and partially successful reclaim.

Therefore, node_reclaim() can simply return the number of pages that have
been reclaimed, same as __node_reclaim(), and the NODE_RECLAIM_xxx macros
can be removed.

There is one small change of behavior when __node_reclaim() was attempted
but returned zero. The allocation now skips the zone immediately; before
this patch, the zone watermarks were checked first. I believe it was an
oversight rather than intention, because the chances that zone watermark is
OK after __node_reclaim() did not reclaim any pages are very close to zero.

Originally, I was looking for occurences of NODE_RECLAIM_SOME and
NODE_RECLAIM_SUCCESS, but I couldn't find any. That's because they are
typecast from the result of a relational operator. This seemed a bit
fragile, so I dug a bit deeper and came up with this proposed cleanup.

Signed-off-by: Petr Tesarik <ptesarik@suse.com>

--

Changes from v2:
- remove the enum and return the number of pages reclaimed

Changes from v1:
- use an enum instead of a bool
---
 mm/internal.h   |  9 +++++----
 mm/page_alloc.c | 19 ++++---------------
 mm/vmscan.c     | 16 ++++++++--------
 3 files changed, 17 insertions(+), 27 deletions(-)

diff --git a/mm/internal.h b/mm/internal.h
index e5dcab69eb4f6..585705daad1a5 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1102,15 +1102,16 @@ static inline void mlock_drain_remote(int cpu) { }
 #ifdef CONFIG_NUMA
 extern int node_reclaim_mode;
 
-extern int node_reclaim(struct pglist_data *, gfp_t, unsigned int);
+extern unsigned long node_reclaim(struct pglist_data *pgdat,
+				  gfp_t gfp_mask, unsigned int order);
 extern int find_next_best_node(int node, nodemask_t *used_node_mask);
 #else
 #define node_reclaim_mode 0
 
-static inline int node_reclaim(struct pglist_data *pgdat, gfp_t mask,
-				unsigned int order)
+static inline unsigned long node_reclaim(struct pglist_data *pgdat,
+					 gfp_t mask, unsigned int order)
 {
-	return NODE_RECLAIM_NOSCAN;
+	return 0;
 }
 static inline int find_next_best_node(int node, nodemask_t *used_node_mask)
 {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 9c97a86da2b9f..af63558391345 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3908,8 +3908,6 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
 		if (!zone_watermark_fast(zone, order, mark,
 				       ac->highest_zoneidx, alloc_flags,
 				       gfp_mask)) {
-			int ret;
-
 			if (cond_accept_memory(zone, order, alloc_flags))
 				goto try_this_zone;
 
@@ -3930,22 +3928,13 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
 			    !zone_allows_reclaim(zonelist_zone(ac->preferred_zoneref), zone))
 				continue;
 
-			ret = node_reclaim(zone->zone_pgdat, gfp_mask, order);
-			switch (ret) {
-			case NODE_RECLAIM_NOSCAN:
-				/* did not scan */
-				continue;
-			case NODE_RECLAIM_FULL:
-				/* scanned but unreclaimable */
+			if (!node_reclaim(zone->zone_pgdat, gfp_mask, order))
 				continue;
-			default:
-				/* did we reclaim enough */
-				if (zone_watermark_ok(zone, order, mark,
-					ac->highest_zoneidx, alloc_flags))
-					goto try_this_zone;
 
+			/* did we reclaim enough */
+			if (!zone_watermark_ok(zone, order, mark,
+					       ac->highest_zoneidx, alloc_flags))
 				continue;
-			}
 		}
 
 try_this_zone:
diff --git a/mm/vmscan.c b/mm/vmscan.c
index f8faa7d06329b..639ea6175c98d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -7800,9 +7800,9 @@ static unsigned long __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask,
 	return sc->nr_reclaimed;
 }
 
-int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
+unsigned long node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
 {
-	int ret;
+	unsigned long ret;
 	/* Minimum pages needed in order to stay on node */
 	const unsigned long nr_pages = 1 << order;
 	struct scan_control sc = {
@@ -7829,13 +7829,13 @@ int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
 	if (node_pagecache_reclaimable(pgdat) <= pgdat->min_unmapped_pages &&
 	    node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) <=
 	    pgdat->min_slab_pages)
-		return NODE_RECLAIM_FULL;
+		return 0;
 
 	/*
 	 * Do not scan if the allocation should not be delayed.
 	 */
 	if (!gfpflags_allow_blocking(gfp_mask) || (current->flags & PF_MEMALLOC))
-		return NODE_RECLAIM_NOSCAN;
+		return 0;
 
 	/*
 	 * Only run node reclaim on the local node or on nodes that do not
@@ -7844,15 +7844,15 @@ int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
 	 * as wide as possible.
 	 */
 	if (node_state(pgdat->node_id, N_CPU) && pgdat->node_id != numa_node_id())
-		return NODE_RECLAIM_NOSCAN;
+		return 0;
 
 	if (test_and_set_bit_lock(PGDAT_RECLAIM_LOCKED, &pgdat->flags))
-		return NODE_RECLAIM_NOSCAN;
+		return 0;
 
-	ret = __node_reclaim(pgdat, gfp_mask, nr_pages, &sc) >= nr_pages;
+	ret = __node_reclaim(pgdat, gfp_mask, nr_pages, &sc);
 	clear_bit_unlock(PGDAT_RECLAIM_LOCKED, &pgdat->flags);
 
-	if (ret)
+	if (ret >= nr_pages)
 		count_vm_event(PGSCAN_ZONE_RECLAIM_SUCCESS);
 	else
 		count_vm_event(PGSCAN_ZONE_RECLAIM_FAILED);
-- 
2.54.0

Re: [PATCH v3 1/1] mm: let node_reclaim() return the number of pages reclaimed

[Andrew Morton]

On Fri, 10 Jul 2026 17:23:20 +0200 Petr Tesarik <ptesarik@suse.com> wrote:

> There is only one caller, get_page_from_freelist(), and it does not make
> any use of the reason for skipping the reclaim, nor does it make any
> distinction between a full and partially successful reclaim.
> 
> Therefore, node_reclaim() can simply return the number of pages that have
> been reclaimed, same as __node_reclaim(), and the NODE_RECLAIM_xxx macros
> can be removed.

AI review
(https://sashiko.dev/#/patchset/20260710152320.2024283-1-ptesarik@suse.com)
points out that the macros weren't actually removed.  Perhaps you meant
"use of the macros can be removed" or similar.  But it does seem they
can indeed be removed:

hp2:/usr/src/25> grep NODE_RECLAIM_ mm/*.[ch] include/linux/*.h
mm/internal.h:#define NODE_RECLAIM_NOSCAN	-2
mm/internal.h:#define NODE_RECLAIM_FULL	-1
mm/internal.h:#define NODE_RECLAIM_SOME	0
mm/internal.h:#define NODE_RECLAIM_SUCCESS	1
mm/vmscan.c:#define NODE_RECLAIM_PRIORITY 4
mm/vmscan.c:		.priority = NODE_RECLAIM_PRIORITY,

(NODE_RECLAIM_PRIORITY looks like it belongs, but it's an unrelated
thing).

Let's not do an immediate resend to address this please - let's give
reviewers a week or so to do their thing.