From bfd3057087cd6607f826def12d950a54da24e454 Mon Sep 17 00:00:00 2001
From: Charan Teja Reddy <charante@codeaurora.org>
Date: Thu, 2 Sep 2021 14:59:56 -0700
Subject: [PATCH] mm: compaction: optimize proactive compaction deferrals

References: bsc#1190208 (MM functional and performance backports)
Patch-mainline: v5.15-rc1
Git-commit: e1e92bfa3825b72be4957f9fef267b3106d20aa6

Vlastimil Babka figured out that when fragmentation score didn't go down
across the proactive compaction i.e.  when no progress is made, next wake
up for proactive compaction is deferred for 1 << COMPACT_MAX_DEFER_SHIFT,
i.e.  64 times, with each wakeup interval of
HPAGE_FRAG_CHECK_INTERVAL_MSEC(=500).  In each of this wakeup, it just
decrement 'proactive_defer' counter and goes sleep i.e.  it is getting
woken to just decrement a counter.

The same deferral time can also achieved by simply doing the
HPAGE_FRAG_CHECK_INTERVAL_MSEC << COMPACT_MAX_DEFER_SHIFT thus unnecessary
wakeup of kcompact thread is avoided thus also removes the need of
'proactive_defer' thread counter.

[akpm@linux-foundation.org: tweak comment]

Link: https://lore.kernel.org/linux-fsdevel/88abfdb6-2c13-b5a6-5b46-742d12d1c910@suse.cz/
Link: https://lkml.kernel.org/r/1626869599-25412-1-git-send-email-charante@codeaurora.org
Signed-off-by: Charan Teja Reddy <charante@codeaurora.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Khalid Aziz <khalid.aziz@oracle.com>
Acked-by: David Rientjes <rientjes@google.com>
Cc: Nitin Gupta <nigupta@nvidia.com>
Cc: Vinayak Menon <vinmenon@codeaurora.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/compaction.c | 29 +++++++++++++++++++----------
 1 file changed, 19 insertions(+), 10 deletions(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index 621508e0ecd5..767f7243793e 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -2885,7 +2885,8 @@ static int kcompactd(void *p)
 {
 	pg_data_t *pgdat = (pg_data_t *)p;
 	struct task_struct *tsk = current;
-	unsigned int proactive_defer = 0;
+	long default_timeout = msecs_to_jiffies(HPAGE_FRAG_CHECK_INTERVAL_MSEC);
+	long timeout = default_timeout;
 
 	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
 
@@ -2902,23 +2903,30 @@ static int kcompactd(void *p)
 
 		trace_mm_compaction_kcompactd_sleep(pgdat->node_id);
 		if (wait_event_freezable_timeout(pgdat->kcompactd_wait,
-			kcompactd_work_requested(pgdat),
-			msecs_to_jiffies(HPAGE_FRAG_CHECK_INTERVAL_MSEC))) {
+			kcompactd_work_requested(pgdat), timeout)) {
 
 			psi_memstall_enter(&pflags);
 			kcompactd_do_work(pgdat);
 			psi_memstall_leave(&pflags);
+			/*
+			 * Reset the timeout value. The defer timeout from
+			 * proactive compaction is lost here but that is fine
+			 * as the condition of the zone changing substantionally
+			 * then carrying on with the previous defer interval is
+			 * not useful.
+			 */
+			timeout = default_timeout;
 			continue;
 		}
 
-		/* kcompactd wait timeout */
+		/*
+		 * Start the proactive work with default timeout. Based
+		 * on the fragmentation score, this timeout is updated.
+		 */
+		timeout = default_timeout;
 		if (should_proactive_compact_node(pgdat)) {
 			unsigned int prev_score, score;
 
-			if (proactive_defer) {
-				proactive_defer--;
-				continue;
-			}
 			prev_score = fragmentation_score_node(pgdat);
 			proactive_compact_node(pgdat);
 			score = fragmentation_score_node(pgdat);
@@ -2926,8 +2934,9 @@ static int kcompactd(void *p)
 			 * Defer proactive compaction if the fragmentation
 			 * score did not go down i.e. no progress made.
 			 */
-			proactive_defer = score < prev_score ?
-					0 : 1 << COMPACT_MAX_DEFER_SHIFT;
+			if (unlikely(score >= prev_score))
+				timeout =
+				   default_timeout << COMPACT_MAX_DEFER_SHIFT;
 		}
 	}