@@ -709,7 +709,6 @@ static bool buffer_migrate_lock_buffers(struct buffer_head *head,
/* Simple case, sync compaction */
if (mode != MIGRATE_ASYNC) {
do {
- get_bh(bh);
lock_buffer(bh);
bh = bh->b_this_page;
@@ -720,18 +719,15 @@ static bool buffer_migrate_lock_buffers(struct buffer_head *head,
/* async case, we cannot block on lock_buffer so use trylock_buffer */
do {
- get_bh(bh);
if (!trylock_buffer(bh)) {
/*
* We failed to lock the buffer and cannot stall in
* async migration. Release the taken locks
*/
struct buffer_head *failed_bh = bh;
- put_bh(failed_bh);
bh = head;
while (bh != failed_bh) {
unlock_buffer(bh);
- put_bh(bh);
bh = bh->b_this_page;
}
return false;
@@ -818,7 +814,6 @@ static int __buffer_migrate_page(struct address_space *mapping,
bh = head;
do {
unlock_buffer(bh);
- put_bh(bh);
bh = bh->b_this_page;
} while (bh != head);
Currently, buffer_migrate_page_norefs() was constantly failing because buffer_migrate_lock_buffers() grabbed reference on each buffer. In fact, there's no reason for buffer_migrate_lock_buffers() to grab any buffer references as the page is locked during all our operation and thus nobody can reclaim buffers from the page. So remove grabbing of buffer references which also makes buffer_migrate_page_norefs() succeed. Fixes: 89cb0888ca14 "mm: migrate: provide buffer_migrate_page_norefs()" Signed-off-by: Jan Kara <jack@suse.cz> --- mm/migrate.c | 5 ----- 1 file changed, 5 deletions(-) Andrew, can you please merge this patch? Sadly my previous testing only tested that page migration in general didn't get broken but I forgot to test whether the new migrate page callback actually results in more successful migrations for block device pages. So the bug got only revealed by customer testing. Now I've reproduced the workload internally and verified that the patch indeed fixes the issue.