@@ -1140,7 +1140,7 @@ static unsigned int shrink_folio_list(struct list_head *folio_list,
* for immediate reclaim are making it to the end of
* the LRU a second time.
*/
- if (writeback && folio_test_reclaim(folio))
+ if (writeback && folio_test_dropbehind(folio))
stat->nr_congested += nr_pages;
/*
@@ -1149,7 +1149,7 @@ static unsigned int shrink_folio_list(struct list_head *folio_list,
*
* 1) If reclaim is encountering an excessive number
* of folios under writeback and this folio has both
- * the writeback and reclaim flags set, then it
+ * the writeback and dropbehind flags set, then it
* indicates that folios are being queued for I/O but
* are being recycled through the LRU before the I/O
* can complete. Waiting on the folio itself risks an
@@ -1174,7 +1174,7 @@ static unsigned int shrink_folio_list(struct list_head *folio_list,
* would probably show more reasons.
*
* 3) Legacy memcg encounters a folio that already has the
- * reclaim flag set. memcg does not have any dirty folio
+ * dropbehind flag set. memcg does not have any dirty folio
* throttling so we could easily OOM just because too many
* folios are in writeback and there is nothing else to
* reclaim. Wait for the writeback to complete.
@@ -1193,31 +1193,17 @@ static unsigned int shrink_folio_list(struct list_head *folio_list,
/* Case 1 above */
if (current_is_kswapd() &&
- folio_test_reclaim(folio) &&
+ folio_test_dropbehind(folio) &&
test_bit(PGDAT_WRITEBACK, &pgdat->flags)) {
stat->nr_immediate += nr_pages;
goto activate_locked;
/* Case 2 above */
} else if (writeback_throttling_sane(sc) ||
- !folio_test_reclaim(folio) ||
+ !folio_test_dropbehind(folio) ||
!may_enter_fs(folio, sc->gfp_mask) ||
(mapping && mapping_writeback_indeterminate(mapping))) {
- /*
- * This is slightly racy -
- * folio_end_writeback() might have
- * just cleared the reclaim flag, then
- * setting the reclaim flag here ends up
- * interpreted as the readahead flag - but
- * that does not matter enough to care.
- * What we do want is for this folio to
- * have the reclaim flag set next time
- * memcg reclaim reaches the tests above,
- * so it will then wait for writeback to
- * avoid OOM; and it's also appropriate
- * in global reclaim.
- */
- folio_set_reclaim(folio);
+ folio_set_dropbehind(folio);
stat->nr_writeback += nr_pages;
goto activate_locked;
@@ -1372,7 +1358,7 @@ static unsigned int shrink_folio_list(struct list_head *folio_list,
*/
if (folio_is_file_lru(folio) &&
(!current_is_kswapd() ||
- !folio_test_reclaim(folio) ||
+ !folio_test_dropbehind(folio) ||
!test_bit(PGDAT_DIRTY, &pgdat->flags))) {
/*
* Immediately reclaim when written back.
@@ -1382,7 +1368,7 @@ static unsigned int shrink_folio_list(struct list_head *folio_list,
*/
node_stat_mod_folio(folio, NR_VMSCAN_IMMEDIATE,
nr_pages);
- folio_set_reclaim(folio);
+ folio_set_dropbehind(folio);
goto activate_locked;
}
The recently introduced PG_dropbehind allows for freeing folios immediately after writeback. Unlike PG_reclaim, it does not need vmscan to be involved to get the folio freed. Instead of using folio_set_reclaim(), use folio_set_dropbehind() in shrink_folio_list(). It is safe to leave PG_dropbehind on the folio if, for some reason (bug?), the folio is not in a writeback state after ->writepage(). In these cases, the kernel had to clear PG_reclaim as it shared a page flag bit with PG_readahead. Also use PG_dropbehind instead PG_reclaim to detect I/O congestion. Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> --- mm/vmscan.c | 30 ++++++++---------------------- 1 file changed, 8 insertions(+), 22 deletions(-)