---

yaml
---
r: 376967
b: refs/heads/master
c: cbab0e4
h: refs/heads/master
i:
  376965: 009cef3
  376963: 26f1513
  376959: 3f0d9f7
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 24b8256a1fb28d357bc6fa09184ba29b4255ba5c
+refs/heads/master: cbab0e4eec299e9059199ebe6daf48730be46d2b

trunk/mm/swap_state.c

@@ -336,8 +336,24 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		 * Swap entry may have been freed since our caller observed it.
 		 */
 		err = swapcache_prepare(entry);
-		if (err == -EEXIST) {	/* seems racy */
+		if (err == -EEXIST) {
 			radix_tree_preload_end();
+			/*
+			 * We might race against get_swap_page() and stumble
+			 * across a SWAP_HAS_CACHE swap_map entry whose page
+			 * has not been brought into the swapcache yet, while
+			 * the other end is scheduled away waiting on discard
+			 * I/O completion at scan_swap_map().
+			 *
+			 * In order to avoid turning this transitory state
+			 * into a permanent loop around this -EEXIST case
+			 * if !CONFIG_PREEMPT and the I/O completion happens
+			 * to be waiting on the CPU waitqueue where we are now
+			 * busy looping, we just conditionally invoke the
+			 * scheduler here, if there are some more important
+			 * tasks to run.
+			 */
+			cond_resched();
 			continue;
 		}
 		if (err) {		/* swp entry is obsolete ? */