filesystem-dax: Fix dax_layout_busy_page() livelock

djbw · djbw · commit d7782145e1ad · 2018-10-08T11:38:44.000-07:00
In the presence of multi-order entries the typical pagevec_lookup_entries() pattern may loop forever: while (index < end && pagevec_lookup_entries(&pvec, mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE), indices)) { ... for (i = 0; i < pagevec_count(&pvec); i++) { index = indices[i]; ... } index++; /* BUG */ } The loop updates 'index' for each index found and then increments to the next possible page to continue the lookup. However, if the last entry in the pagevec is multi-order then the next possible page index is more than 1 page away. Fix this locally for the filesystem-dax case by checking for dax-multi-order entries. Going forward new users of multi-order entries need to be similarly careful, or we need a generic way to report the page increment in the radix iterator. Fixes: 5fac740 ("mm, fs, dax: handle layout changes to pinned dax...") Cc: <stable@vger.kernel.org> Cc: Ross Zwisler <zwisler@kernel.org> Cc: Matthew Wilcox <willy@infradead.org> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
diff --git a/fs/dax.c b/fs/dax.c
@@ -666,6 +666,8 @@ struct page *dax_layout_busy_page(struct address_space *mapping)
 	while (index < end && pagevec_lookup_entries(&pvec, mapping, index,
 				min(end - index, (pgoff_t)PAGEVEC_SIZE),
 				indices)) {
+		pgoff_t nr_pages = 1;
+
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *pvec_ent = pvec.pages[i];
 			void *entry;
@@ -680,8 +682,15 @@ struct page *dax_layout_busy_page(struct address_space *mapping)
 
 			xa_lock_irq(&mapping->i_pages);
 			entry = get_unlocked_mapping_entry(mapping, index, NULL);
-			if (entry)
+			if (entry) {
 				page = dax_busy_page(entry);
+				/*
+				 * Account for multi-order entries at
+				 * the end of the pagevec.
+				 */
+				if (i + 1 >= pagevec_count(&pvec))
+					nr_pages = 1UL << dax_radix_order(entry);
+			}
 			put_unlocked_mapping_entry(mapping, index, entry);
 			xa_unlock_irq(&mapping->i_pages);
 			if (page)
@@ -696,7 +705,7 @@ struct page *dax_layout_busy_page(struct address_space *mapping)
 		 */
 		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
-		index++;
+		index += nr_pages;
 
 		if (page)
 			break;
