[RFC LPC2025 PATCH 2/4] mm/vmscan/page_alloc: Remove node_reclaim

[Joshua Hahn <joshua.hahnjy@gmail.com>]

node_reclaim() is currently only called when the zone_reclaim_mode
sysctl is set, during get_page_from_freelist if the current node is
full.

With the zone_reclaim_mode sysctl being deprecated later in the series,
there are no more callsites for node_reclaim. Remove node_reclaim and
its associated return values NODE_RECLAIM_{NOSCAN, FULL, SOME, SUCCESS},
as well as the zone_reclaim_{success, failed} vmstat items.

We can also remove zone_allows_reclaim, since with node_reclaim_enabled
always returning false, it will never get evaluated.

Signed-off-by: Joshua Hahn <joshua.hahnjy@gmail.com>
---
 include/linux/vm_event_item.h |  4 ---
 mm/internal.h                 | 11 ------
 mm/page_alloc.c               | 34 ------------------
 mm/vmscan.c                   | 67 -----------------------------------
 mm/vmstat.c                   |  4 ---
 5 files changed, 120 deletions(-)

diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 92f80b4d69a6..2520200b65f0 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -53,10 +53,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		PGSCAN_FILE,
 		PGSTEAL_ANON,
 		PGSTEAL_FILE,
-#ifdef CONFIG_NUMA
-		PGSCAN_ZONE_RECLAIM_SUCCESS,
-		PGSCAN_ZONE_RECLAIM_FAILED,
-#endif
 		PGINODESTEAL, SLABS_SCANNED, KSWAPD_INODESTEAL,
 		KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY,
 		PAGEOUTRUN, PGROTATED,
diff --git a/mm/internal.h b/mm/internal.h
index 04c307ee33ae..743fcebe53a8 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1196,24 +1196,13 @@ static inline void mminit_verify_zonelist(void)
 }
 #endif /* CONFIG_DEBUG_MEMORY_INIT */
 
-#define NODE_RECLAIM_NOSCAN	-2
-#define NODE_RECLAIM_FULL	-1
-#define NODE_RECLAIM_SOME	0
-#define NODE_RECLAIM_SUCCESS	1
-
 #ifdef CONFIG_NUMA
 extern int node_reclaim_mode;
 
-extern int node_reclaim(struct pglist_data *, gfp_t, unsigned int);
 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)
-{
-	return NODE_RECLAIM_NOSCAN;
-}
 static inline int find_next_best_node(int node, nodemask_t *used_node_mask)
 {
 	return NUMA_NO_NODE;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d0f026ec10b6..010a035e81bd 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3684,17 +3684,6 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
 
 #ifdef CONFIG_NUMA
 int __read_mostly node_reclaim_distance = RECLAIM_DISTANCE;
-
-static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
-{
-	return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) <=
-				node_reclaim_distance;
-}
-#else	/* CONFIG_NUMA */
-static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
-{
-	return true;
-}
 #endif	/* CONFIG_NUMA */
 
 /*
@@ -3868,8 +3857,6 @@ 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;
 
@@ -3885,27 +3872,6 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
 			BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK);
 			if (alloc_flags & ALLOC_NO_WATERMARKS)
 				goto try_this_zone;
-
-			if (!node_reclaim_enabled() ||
-			    !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 */
-				continue;
-			default:
-				/* did we reclaim enough */
-				if (zone_watermark_ok(zone, order, mark,
-					ac->highest_zoneidx, alloc_flags))
-					goto try_this_zone;
-
-				continue;
-			}
 		}
 
 try_this_zone:
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 3b85652a42b9..d07acd76fdea 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -7537,13 +7537,6 @@ module_init(kswapd_init)
  */
 int node_reclaim_mode __read_mostly;
 
-/*
- * Priority for NODE_RECLAIM. This determines the fraction of pages
- * of a node considered for each zone_reclaim. 4 scans 1/16th of
- * a zone.
- */
-#define NODE_RECLAIM_PRIORITY 4
-
 /*
  * Percentage of pages in a zone that must be unmapped for node_reclaim to
  * occur.
@@ -7646,66 +7639,6 @@ 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)
-{
-	int ret;
-	/* Minimum pages needed in order to stay on node */
-	const unsigned long nr_pages = 1 << order;
-	struct scan_control sc = {
-		.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
-		.gfp_mask = current_gfp_context(gfp_mask),
-		.order = order,
-		.priority = NODE_RECLAIM_PRIORITY,
-		.may_writepage = !!(node_reclaim_mode & RECLAIM_WRITE),
-		.may_unmap = !!(node_reclaim_mode & RECLAIM_UNMAP),
-		.may_swap = 1,
-		.reclaim_idx = gfp_zone(gfp_mask),
-	};
-
-	/*
-	 * Node reclaim reclaims unmapped file backed pages and
-	 * slab pages if we are over the defined limits.
-	 *
-	 * A small portion of unmapped file backed pages is needed for
-	 * file I/O otherwise pages read by file I/O will be immediately
-	 * thrown out if the node is overallocated. So we do not reclaim
-	 * if less than a specified percentage of the node is used by
-	 * unmapped file backed pages.
-	 */
-	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;
-
-	/*
-	 * Do not scan if the allocation should not be delayed.
-	 */
-	if (!gfpflags_allow_blocking(gfp_mask) || (current->flags & PF_MEMALLOC))
-		return NODE_RECLAIM_NOSCAN;
-
-	/*
-	 * Only run node reclaim on the local node or on nodes that do not
-	 * have associated processors. This will favor the local processor
-	 * over remote processors and spread off node memory allocations
-	 * as wide as possible.
-	 */
-	if (node_state(pgdat->node_id, N_CPU) && pgdat->node_id != numa_node_id())
-		return NODE_RECLAIM_NOSCAN;
-
-	if (test_and_set_bit_lock(PGDAT_RECLAIM_LOCKED, &pgdat->flags))
-		return NODE_RECLAIM_NOSCAN;
-
-	ret = __node_reclaim(pgdat, gfp_mask, nr_pages, &sc) >= nr_pages;
-	clear_bit_unlock(PGDAT_RECLAIM_LOCKED, &pgdat->flags);
-
-	if (ret)
-		count_vm_event(PGSCAN_ZONE_RECLAIM_SUCCESS);
-	else
-		count_vm_event(PGSCAN_ZONE_RECLAIM_FAILED);
-
-	return ret;
-}
-
 enum {
 	MEMORY_RECLAIM_SWAPPINESS = 0,
 	MEMORY_RECLAIM_SWAPPINESS_MAX,
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 65de88cdf40e..3564bc62325a 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1349,10 +1349,6 @@ const char * const vmstat_text[] = {
 	[I(PGSTEAL_ANON)]			= "pgsteal_anon",
 	[I(PGSTEAL_FILE)]			= "pgsteal_file",
 
-#ifdef CONFIG_NUMA
-	[I(PGSCAN_ZONE_RECLAIM_SUCCESS)]	= "zone_reclaim_success",
-	[I(PGSCAN_ZONE_RECLAIM_FAILED)]		= "zone_reclaim_failed",
-#endif
 	[I(PGINODESTEAL)]			= "pginodesteal",
 	[I(SLABS_SCANNED)]			= "slabs_scanned",
 	[I(KSWAPD_INODESTEAL)]			= "kswapd_inodesteal",
-- 
2.47.3