mm/migrate: fix deadlock in migrate_pages_batch() on large folios

Currently, migrate_pages_batch() can lock multiple locked folios with an
arbitrary order.  Although folio_trylock() is used to avoid deadlock as
commit 2ef7dbb269 ("migrate_pages: try migrate in batch asynchronously
firstly") mentioned, it seems try_split_folio() is still missing.

It was found by compaction stress test when I explicitly enable EROFS
compressed files to use large folios, which case I cannot reproduce with
the same workload if large folio support is off (current mainline). 
Typically, filesystem reads (with locked file-backed folios) could use
another bdev/meta inode to load some other I/Os (e.g.  inode extent
metadata or caching compressed data), so the locking order will be:

  file-backed folios  (A)
     bdev/meta folios (B)

The following calltrace shows the deadlock:
   Thread 1 takes (B) lock and tries to take folio (A) lock
   Thread 2 takes (A) lock and tries to take folio (B) lock

[Thread 1]
INFO: task stress:1824 blocked for more than 30 seconds.
      Tainted: G           OE      6.10.0-rc7+ #6
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
task:stress          state:D stack:0     pid:1824  tgid:1824  ppid:1822   flags:0x0000000c
Call trace:
 __switch_to+0xec/0x138
 __schedule+0x43c/0xcb0
 schedule+0x54/0x198
 io_schedule+0x44/0x70
 folio_wait_bit_common+0x184/0x3f8
			<-- folio mapping ffff00036d69cb18 index 996  (**)
 __folio_lock+0x24/0x38
 migrate_pages_batch+0x77c/0xea0	// try_split_folio (mm/migrate.c:1486:2)
					// migrate_pages_batch (mm/migrate.c:1734:16)
		<--- LIST_HEAD(unmap_folios) has
			..
			folio mapping 0xffff0000d184f1d8 index 1711;   (*)
			folio mapping 0xffff0000d184f1d8 index 1712;
			..
 migrate_pages+0xb28/0xe90
 compact_zone+0xa08/0x10f0
 compact_node+0x9c/0x180
 sysctl_compaction_handler+0x8c/0x118
 proc_sys_call_handler+0x1a8/0x280
 proc_sys_write+0x1c/0x30
 vfs_write+0x240/0x380
 ksys_write+0x78/0x118
 __arm64_sys_write+0x24/0x38
 invoke_syscall+0x78/0x108
 el0_svc_common.constprop.0+0x48/0xf0
 do_el0_svc+0x24/0x38
 el0_svc+0x3c/0x148
 el0t_64_sync_handler+0x100/0x130
 el0t_64_sync+0x190/0x198

[Thread 2]
INFO: task stress:1825 blocked for more than 30 seconds.
      Tainted: G           OE      6.10.0-rc7+ #6
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
task:stress          state:D stack:0     pid:1825  tgid:1825  ppid:1822   flags:0x0000000c
Call trace:
 __switch_to+0xec/0x138
 __schedule+0x43c/0xcb0
 schedule+0x54/0x198
 io_schedule+0x44/0x70
 folio_wait_bit_common+0x184/0x3f8
			<-- folio = 0xfffffdffc6b503c0 (mapping == 0xffff0000d184f1d8 index == 1711) (*)
 __folio_lock+0x24/0x38
 z_erofs_runqueue+0x384/0x9c0 [erofs]
 z_erofs_readahead+0x21c/0x350 [erofs]       <-- folio mapping 0xffff00036d69cb18 range from [992, 1024] (**)
 read_pages+0x74/0x328
 page_cache_ra_order+0x26c/0x348
 ondemand_readahead+0x1c0/0x3a0
 page_cache_sync_ra+0x9c/0xc0
 filemap_get_pages+0xc4/0x708
 filemap_read+0x104/0x3a8
 generic_file_read_iter+0x4c/0x150
 vfs_read+0x27c/0x330
 ksys_pread64+0x84/0xd0
 __arm64_sys_pread64+0x28/0x40
 invoke_syscall+0x78/0x108
 el0_svc_common.constprop.0+0x48/0xf0
 do_el0_svc+0x24/0x38
 el0_svc+0x3c/0x148
 el0t_64_sync_handler+0x100/0x130
 el0t_64_sync+0x190/0x198

Link: https://lkml.kernel.org/r/20240729021306.398286-1-hsiangkao@linux.alibaba.com
Fixes: 5dfab109d5 ("migrate_pages: batch _unmap and _move")
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This commit is contained in:
Gao Xiang 2024-07-29 10:13:06 +08:00 committed by Andrew Morton
parent 766c163c20
commit 2e6506e1c4

View File

@ -1479,11 +1479,17 @@ out:
return rc; return rc;
} }
static inline int try_split_folio(struct folio *folio, struct list_head *split_folios) static inline int try_split_folio(struct folio *folio, struct list_head *split_folios,
enum migrate_mode mode)
{ {
int rc; int rc;
folio_lock(folio); if (mode == MIGRATE_ASYNC) {
if (!folio_trylock(folio))
return -EAGAIN;
} else {
folio_lock(folio);
}
rc = split_folio_to_list(folio, split_folios); rc = split_folio_to_list(folio, split_folios);
folio_unlock(folio); folio_unlock(folio);
if (!rc) if (!rc)
@ -1677,7 +1683,7 @@ static int migrate_pages_batch(struct list_head *from,
*/ */
if (nr_pages > 2 && if (nr_pages > 2 &&
!list_empty(&folio->_deferred_list)) { !list_empty(&folio->_deferred_list)) {
if (try_split_folio(folio, split_folios) == 0) { if (!try_split_folio(folio, split_folios, mode)) {
nr_failed++; nr_failed++;
stats->nr_thp_failed += is_thp; stats->nr_thp_failed += is_thp;
stats->nr_thp_split += is_thp; stats->nr_thp_split += is_thp;
@ -1699,7 +1705,7 @@ static int migrate_pages_batch(struct list_head *from,
if (!thp_migration_supported() && is_thp) { if (!thp_migration_supported() && is_thp) {
nr_failed++; nr_failed++;
stats->nr_thp_failed++; stats->nr_thp_failed++;
if (!try_split_folio(folio, split_folios)) { if (!try_split_folio(folio, split_folios, mode)) {
stats->nr_thp_split++; stats->nr_thp_split++;
stats->nr_split++; stats->nr_split++;
continue; continue;
@ -1731,7 +1737,7 @@ static int migrate_pages_batch(struct list_head *from,
stats->nr_thp_failed += is_thp; stats->nr_thp_failed += is_thp;
/* Large folio NUMA faulting doesn't split to retry. */ /* Large folio NUMA faulting doesn't split to retry. */
if (is_large && !nosplit) { if (is_large && !nosplit) {
int ret = try_split_folio(folio, split_folios); int ret = try_split_folio(folio, split_folios, mode);
if (!ret) { if (!ret) {
stats->nr_thp_split += is_thp; stats->nr_thp_split += is_thp;