summaryrefslogtreecommitdiff
path: root/mm/filemap.c
diff options
context:
space:
mode:
authorJohannes Weiner <hannes@cmpxchg.org>2014-05-06 23:50:05 +0400
committerLinus Torvalds <torvalds@linux-foundation.org>2014-05-07 00:04:59 +0400
commit139b6a6fb1539e04b01663d61baff3088c63dbb5 (patch)
tree299fc6452057660ce3626e9e8c00d675d6647423 /mm/filemap.c
parent49e068f0b73dd042c186ffa9b420a9943e90389a (diff)
downloadlinux-139b6a6fb1539e04b01663d61baff3088c63dbb5.tar.xz
mm: filemap: update find_get_pages_tag() to deal with shadow entries
Dave Jones reports the following crash when find_get_pages_tag() runs into an exceptional entry: kernel BUG at mm/filemap.c:1347! RIP: find_get_pages_tag+0x1cb/0x220 Call Trace: find_get_pages_tag+0x36/0x220 pagevec_lookup_tag+0x21/0x30 filemap_fdatawait_range+0xbe/0x1e0 filemap_fdatawait+0x27/0x30 sync_inodes_sb+0x204/0x2a0 sync_inodes_one_sb+0x19/0x20 iterate_supers+0xb2/0x110 sys_sync+0x44/0xb0 ia32_do_call+0x13/0x13 1343 /* 1344 * This function is never used on a shmem/tmpfs 1345 * mapping, so a swap entry won't be found here. 1346 */ 1347 BUG(); After commit 0cd6144aadd2 ("mm + fs: prepare for non-page entries in page cache radix trees") this comment and BUG() are out of date because exceptional entries can now appear in all mappings - as shadows of recently evicted pages. However, as Hugh Dickins notes, "it is truly surprising for a PAGECACHE_TAG_WRITEBACK (and probably any other PAGECACHE_TAG_*) to appear on an exceptional entry. I expect it comes down to an occasional race in RCU lookup of the radix_tree: lacking absolute synchronization, we might sometimes catch an exceptional entry, with the tag which really belongs with the unexceptional entry which was there an instant before." And indeed, not only is the tree walk lockless, the tags are also read in chunks, one radix tree node at a time. There is plenty of time for page reclaim to swoop in and replace a page that was already looked up as tagged with a shadow entry. Remove the BUG() and update the comment. While reviewing all other lookup sites for whether they properly deal with shadow entries of evicted pages, update all the comments and fix memcg file charge moving to not miss shmem/tmpfs swapcache pages. Fixes: 0cd6144aadd2 ("mm + fs: prepare for non-page entries in page cache radix trees") Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reported-by: Dave Jones <davej@redhat.com> Acked-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/filemap.c')
-rw-r--r--mm/filemap.c49
1 files changed, 28 insertions, 21 deletions
diff --git a/mm/filemap.c b/mm/filemap.c
index 5020b280a771..000a220e2a41 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -906,8 +906,8 @@ EXPORT_SYMBOL(page_cache_prev_hole);
* Looks up the page cache slot at @mapping & @offset. If there is a
* page cache page, it is returned with an increased refcount.
*
- * If the slot holds a shadow entry of a previously evicted page, it
- * is returned.
+ * If the slot holds a shadow entry of a previously evicted page, or a
+ * swap entry from shmem/tmpfs, it is returned.
*
* Otherwise, %NULL is returned.
*/
@@ -928,9 +928,9 @@ repeat:
if (radix_tree_deref_retry(page))
goto repeat;
/*
- * Otherwise, shmem/tmpfs must be storing a swap entry
- * here as an exceptional entry: so return it without
- * attempting to raise page count.
+ * A shadow entry of a recently evicted page,
+ * or a swap entry from shmem/tmpfs. Return
+ * it without attempting to raise page count.
*/
goto out;
}
@@ -983,8 +983,8 @@ EXPORT_SYMBOL(find_get_page);
* page cache page, it is returned locked and with an increased
* refcount.
*
- * If the slot holds a shadow entry of a previously evicted page, it
- * is returned.
+ * If the slot holds a shadow entry of a previously evicted page, or a
+ * swap entry from shmem/tmpfs, it is returned.
*
* Otherwise, %NULL is returned.
*
@@ -1099,8 +1099,8 @@ EXPORT_SYMBOL(find_or_create_page);
* with ascending indexes. There may be holes in the indices due to
* not-present pages.
*
- * Any shadow entries of evicted pages are included in the returned
- * array.
+ * Any shadow entries of evicted pages, or swap entries from
+ * shmem/tmpfs, are included in the returned array.
*
* find_get_entries() returns the number of pages and shadow entries
* which were found.
@@ -1128,9 +1128,9 @@ repeat:
if (radix_tree_deref_retry(page))
goto restart;
/*
- * Otherwise, we must be storing a swap entry
- * here as an exceptional entry: so return it
- * without attempting to raise page count.
+ * A shadow entry of a recently evicted page,
+ * or a swap entry from shmem/tmpfs. Return
+ * it without attempting to raise page count.
*/
goto export;
}
@@ -1198,9 +1198,9 @@ repeat:
goto restart;
}
/*
- * Otherwise, shmem/tmpfs must be storing a swap entry
- * here as an exceptional entry: so skip over it -
- * we only reach this from invalidate_mapping_pages().
+ * A shadow entry of a recently evicted page,
+ * or a swap entry from shmem/tmpfs. Skip
+ * over it.
*/
continue;
}
@@ -1265,9 +1265,9 @@ repeat:
goto restart;
}
/*
- * Otherwise, shmem/tmpfs must be storing a swap entry
- * here as an exceptional entry: so stop looking for
- * contiguous pages.
+ * A shadow entry of a recently evicted page,
+ * or a swap entry from shmem/tmpfs. Stop
+ * looking for contiguous pages.
*/
break;
}
@@ -1341,10 +1341,17 @@ repeat:
goto restart;
}
/*
- * This function is never used on a shmem/tmpfs
- * mapping, so a swap entry won't be found here.
+ * A shadow entry of a recently evicted page.
+ *
+ * Those entries should never be tagged, but
+ * this tree walk is lockless and the tags are
+ * looked up in bulk, one radix tree node at a
+ * time, so there is a sizable window for page
+ * reclaim to evict a page we saw tagged.
+ *
+ * Skip over it.
*/
- BUG();
+ continue;
}
if (!page_cache_get_speculative(page))