Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Johannes Weiner <hannes@cmpxchg.org>
To:     Andrew Morton <akpm@linux-foundation.org>
Cc:     Vlastimil Babka <vbabka@suse.cz>,
        Mel Gorman <mgorman@techsingularity.net>, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org
Subject: [PATCH] mm: compaction: fix endless looping over same migrate block
Date:   Mon, 31 Jul 2023 13:24:50 -0400
Message-ID: <20230731172450.1632195-1-hannes@cmpxchg.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

During stress testing, the following situation was observed:

     70 root      39  19       0      0      0 R 100.0   0.0 959:29.92 khugepaged
 310936 root      20   0   84416  25620    512 R  99.7   1.5 642:37.22 hugealloc

Tracing shows isolate_migratepages_block() endlessly looping over the
first block in the DMA zone:

       hugealloc-310936  [001] ..... 237297.415718: mm_compaction_finished: node=0 zone=DMA      order=9 ret=no_suitable_page
       hugealloc-310936  [001] ..... 237297.415718: mm_compaction_isolate_migratepages: range=(0x1 ~ 0x400) nr_scanned=513 nr_taken=0
       hugealloc-310936  [001] ..... 237297.415718: mm_compaction_finished: node=0 zone=DMA      order=9 ret=no_suitable_page
       hugealloc-310936  [001] ..... 237297.415718: mm_compaction_isolate_migratepages: range=(0x1 ~ 0x400) nr_scanned=513 nr_taken=0
       hugealloc-310936  [001] ..... 237297.415718: mm_compaction_finished: node=0 zone=DMA      order=9 ret=no_suitable_page
       hugealloc-310936  [001] ..... 237297.415718: mm_compaction_isolate_migratepages: range=(0x1 ~ 0x400) nr_scanned=513 nr_taken=0
       hugealloc-310936  [001] ..... 237297.415718: mm_compaction_finished: node=0 zone=DMA      order=9 ret=no_suitable_page
       hugealloc-310936  [001] ..... 237297.415718: mm_compaction_isolate_migratepages: range=(0x1 ~ 0x400) nr_scanned=513 nr_taken=0

The problem is that the functions tries to test and set the skip bit
once on the block, to avoid skipping on its own skip-set, using
pageblock_aligned() on the pfn as a test. But because this is the DMA
zone which starts at pfn 1, this is never true for the first block,
and the skip bit isn't set or tested at all. As a result,
fast_find_migrateblock() returns the same pageblock over and over.

If the pfn isn't pageblock-aligned, also check if it's the start of
the zone to ensure test-and-set-exactly-once on unaligned ranges.

Thanks to Vlastimil Babka for the help in debugging this.

Fixes: 90ed667c03fe ("Revert "Revert "mm/compaction: fix set skip in fast_find_migrateblock""")
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
---
 mm/compaction.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index dbc9f86b1934..eacca2794e47 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -912,11 +912,12 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 
 		/*
 		 * Check if the pageblock has already been marked skipped.
-		 * Only the aligned PFN is checked as the caller isolates
+		 * Only the first PFN is checked as the caller isolates
 		 * COMPACT_CLUSTER_MAX at a time so the second call must
 		 * not falsely conclude that the block should be skipped.
 		 */
-		if (!valid_page && pageblock_aligned(low_pfn)) {
+		if (!valid_page && (pageblock_aligned(low_pfn) ||
+				    low_pfn == cc->zone->zone_start_pfn)) {
 			if (!isolation_suitable(cc, page)) {
 				low_pfn = end_pfn;
 				folio = NULL;
@@ -2002,7 +2003,8 @@ static isolate_migrate_t isolate_migratepages(struct compact_control *cc)
 		 * before making it "skip" so other compaction instances do
 		 * not scan the same block.
 		 */
-		if (pageblock_aligned(low_pfn) &&
+		if ((pageblock_aligned(low_pfn) ||
+		     low_pfn == cc->zone->zone_start_pfn) &&
 		    !fast_find_block && !isolation_suitable(cc, page))
 			continue;
 
-- 
2.41.0