[101/227] mm/page_alloc: drain the requested list first during bulk free

Commit Message

Andrew Morton March 22, 2022, 9:43 p.m. UTC

From: Mel Gorman <[e-mail]>
Subject: mm/page_alloc: drain the requested list first during bulk free

Prior to the series, pindex 0 (order-0 MIGRATE_UNMOVABLE) was always
skipped first and the precise reason is forgotten.  A potential reason may
have been to artificially preserve MIGRATE_UNMOVABLE but there is no
reason why that would be optimal as it depends on the workload.  The more
likely reason is that it was less complicated to do a pre-increment
instead of a post-increment in terms of overall code flow.  As
free_pcppages_bulk() now typically receives the pindex of the PCP list
that exceeded high, always start draining that list.

Link: https://lkml.kernel.org/r/[e-mail]
Signed-off-by: Mel Gorman <[e-mail]>
Reviewed-by: Vlastimil Babka <[e-mail]>
Tested-by: Aaron Lu <[e-mail]>
Cc: Dave Hansen <[e-mail]>
Cc: Jesper Dangaard Brouer <[e-mail]>
Cc: Michal Hocko <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
---

 mm/page_alloc.c |    4 ++++
 1 file changed, 4 insertions(+)

Patch

--- a/mm/page_alloc.c~mm-page_alloc-drain-the-requested-list-first-during-bulk-free
+++ a/mm/page_alloc.c
@@ -1460,6 +1460,10 @@  static void free_pcppages_bulk(struct zo
 	 * below while (list_empty(list)) loop.
 	 */
 	count = min(pcp->count, count);
+
+	/* Ensure requested pindex is drained first. */
+	pindex = pindex - 1;
+
 	while (count > 0) {
 		struct list_head *list;
 		int nr_pages;