summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorSultan Alsawaf <sultan@kerneltoast.com>2022-05-13 15:11:26 -0700
committerAndrew Morton <akpm@linux-foundation.org>2022-05-13 15:11:26 -0700
commit2505a981114dcb715f8977b8433f7540854851d8 (patch)
tree4913158c36d00dadabb3211577f56f4d3c06ef50 /mm
parent60a60e32cf91169840abcb4a80f0b0df31708ba7 (diff)
downloadlinux-stable-2505a981114dcb715f8977b8433f7540854851d8.tar.gz
linux-stable-2505a981114dcb715f8977b8433f7540854851d8.tar.bz2
linux-stable-2505a981114dcb715f8977b8433f7540854851d8.zip
zsmalloc: fix races between asynchronous zspage free and page migration
The asynchronous zspage free worker tries to lock a zspage's entire page list without defending against page migration. Since pages which haven't yet been locked can concurrently migrate off the zspage page list while lock_zspage() churns away, lock_zspage() can suffer from a few different lethal races. It can lock a page which no longer belongs to the zspage and unsafely dereference page_private(), it can unsafely dereference a torn pointer to the next page (since there's a data race), and it can observe a spurious NULL pointer to the next page and thus not lock all of the zspage's pages (since a single page migration will reconstruct the entire page list, and create_page_chain() unconditionally zeroes out each list pointer in the process). Fix the races by using migrate_read_lock() in lock_zspage() to synchronize with page migration. Link: https://lkml.kernel.org/r/20220509024703.243847-1-sultan@kerneltoast.com Fixes: 77ff465799c602 ("zsmalloc: zs_page_migrate: skip unnecessary loops but not return -EBUSY if zspage is not inuse") Signed-off-by: Sultan Alsawaf <sultan@kerneltoast.com> Acked-by: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Sergey Senozhatsky <senozhatsky@chromium.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/zsmalloc.c37
1 files changed, 33 insertions, 4 deletions
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 9152fbde33b5..5d5fc04385b8 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -1718,11 +1718,40 @@ static enum fullness_group putback_zspage(struct size_class *class,
*/
static void lock_zspage(struct zspage *zspage)
{
- struct page *page = get_first_page(zspage);
+ struct page *curr_page, *page;
- do {
- lock_page(page);
- } while ((page = get_next_page(page)) != NULL);
+ /*
+ * Pages we haven't locked yet can be migrated off the list while we're
+ * trying to lock them, so we need to be careful and only attempt to
+ * lock each page under migrate_read_lock(). Otherwise, the page we lock
+ * may no longer belong to the zspage. This means that we may wait for
+ * the wrong page to unlock, so we must take a reference to the page
+ * prior to waiting for it to unlock outside migrate_read_lock().
+ */
+ while (1) {
+ migrate_read_lock(zspage);
+ page = get_first_page(zspage);
+ if (trylock_page(page))
+ break;
+ get_page(page);
+ migrate_read_unlock(zspage);
+ wait_on_page_locked(page);
+ put_page(page);
+ }
+
+ curr_page = page;
+ while ((page = get_next_page(curr_page))) {
+ if (trylock_page(page)) {
+ curr_page = page;
+ } else {
+ get_page(page);
+ migrate_read_unlock(zspage);
+ wait_on_page_locked(page);
+ put_page(page);
+ migrate_read_lock(zspage);
+ }
+ }
+ migrate_read_unlock(zspage);
}
static int zs_init_fs_context(struct fs_context *fc)