summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
authorJohannes Weiner <hannes@cmpxchg.org>2024-03-24 17:04:47 -0400
committerAndrew Morton <akpm@linux-foundation.org>2024-03-26 11:14:12 -0700
commit25cd241408a2adc1ed0ebc90ae0793576c111880 (patch)
treef2a276d3dd6ac5cc48be97e485e0e1ef6b3145f5 /mm
parent8c864371b2a15a23ce35aa7e2bd241baaad6fbe8 (diff)
mm: zswap: fix data loss on SWP_SYNCHRONOUS_IO devices
Zhongkun He reports data corruption when combining zswap with zram. The issue is the exclusive loads we're doing in zswap. They assume that all reads are going into the swapcache, which can assume authoritative ownership of the data and so the zswap copy can go. However, zram files are marked SWP_SYNCHRONOUS_IO, and faults will try to bypass the swapcache. This results in an optimistic read of the swap data into a page that will be dismissed if the fault fails due to races. In this case, zswap mustn't drop its authoritative copy. Link: https://lore.kernel.org/all/CACSyD1N+dUvsu8=zV9P691B9bVq33erwOXNTmEaUbi9DrDeJzw@mail.gmail.com/ Fixes: b9c91c43412f ("mm: zswap: support exclusive loads") Link: https://lkml.kernel.org/r/20240324210447.956973-1-hannes@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reported-by: Zhongkun He <hezhongkun.hzk@bytedance.com> Tested-by: Zhongkun He <hezhongkun.hzk@bytedance.com> Acked-by: Yosry Ahmed <yosryahmed@google.com> Acked-by: Barry Song <baohua@kernel.org> Reviewed-by: Chengming Zhou <chengming.zhou@linux.dev> Reviewed-by: Nhat Pham <nphamcs@gmail.com> Acked-by: Chris Li <chrisl@kernel.org> Cc: <stable@vger.kernel.org> [6.5+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/zswap.c23
1 files changed, 19 insertions, 4 deletions
diff --git a/mm/zswap.c b/mm/zswap.c
index 36612f34b5d7..caed028945b0 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -1636,6 +1636,7 @@ bool zswap_load(struct folio *folio)
swp_entry_t swp = folio->swap;
pgoff_t offset = swp_offset(swp);
struct page *page = &folio->page;
+ bool swapcache = folio_test_swapcache(folio);
struct zswap_tree *tree = swap_zswap_tree(swp);
struct zswap_entry *entry;
u8 *dst;
@@ -1648,7 +1649,20 @@ bool zswap_load(struct folio *folio)
spin_unlock(&tree->lock);
return false;
}
- zswap_rb_erase(&tree->rbroot, entry);
+ /*
+ * When reading into the swapcache, invalidate our entry. The
+ * swapcache can be the authoritative owner of the page and
+ * its mappings, and the pressure that results from having two
+ * in-memory copies outweighs any benefits of caching the
+ * compression work.
+ *
+ * (Most swapins go through the swapcache. The notable
+ * exception is the singleton fault on SWP_SYNCHRONOUS_IO
+ * files, which reads into a private page and may free it if
+ * the fault fails. We remain the primary owner of the entry.)
+ */
+ if (swapcache)
+ zswap_rb_erase(&tree->rbroot, entry);
spin_unlock(&tree->lock);
if (entry->length)
@@ -1663,9 +1677,10 @@ bool zswap_load(struct folio *folio)
if (entry->objcg)
count_objcg_event(entry->objcg, ZSWPIN);
- zswap_entry_free(entry);
-
- folio_mark_dirty(folio);
+ if (swapcache) {
+ zswap_entry_free(entry);
+ folio_mark_dirty(folio);
+ }
return true;
}