1 files changed, 33 insertions, 25 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 75572b5f237..83a45d35468 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -102,9 +102,6 @@
  *    ->inode_lock		(zap_pte_range->set_page_dirty)
  *    ->private_lock		(zap_pte_range->__set_page_dirty_buffers)
  *
- *  ->task->proc_lock
- *    ->dcache_lock		(proc_pid_lookup)
- *
  *  (code doesn't rely on that order, so you could switch it around)
  *  ->tasklist_lock             (memory_failure, collect_procs_ao)
  *    ->i_mmap_lock
@@ -143,13 +140,18 @@ void __remove_from_page_cache(struct page *page)
 void remove_from_page_cache(struct page *page)
 {
 	struct address_space *mapping = page->mapping;
+	void (*freepage)(struct page *);
 
 	BUG_ON(!PageLocked(page));
 
+	freepage = mapping->a_ops->freepage;
 	spin_lock_irq(&mapping->tree_lock);
 	__remove_from_page_cache(page);
 	spin_unlock_irq(&mapping->tree_lock);
 	mem_cgroup_uncharge_cache_page(page);
+
+	if (freepage)
+		freepage(page);
 }
 EXPORT_SYMBOL(remove_from_page_cache);
 
@@ -296,7 +298,7 @@ int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte,
 				continue;
 
 			wait_on_page_writeback(page);
-			if (PageError(page))
+			if (TestClearPageError(page))
 				ret = -EIO;
 		}
 		pagevec_release(&pvec);
@@ -644,7 +646,9 @@ repeat:
 	pagep = radix_tree_lookup_slot(&mapping->page_tree, offset);
 	if (pagep) {
 		page = radix_tree_deref_slot(pagep);
-		if (unlikely(!page || page == RADIX_TREE_RETRY))
+		if (unlikely(!page))
+			goto out;
+		if (radix_tree_deref_retry(page))
 			goto repeat;
 
 		if (!page_cache_get_speculative(page))
@@ -660,6 +664,7 @@ repeat:
 			goto repeat;
 		}
 	}
+out:
 	rcu_read_unlock();
 
 	return page;
@@ -777,12 +782,11 @@ repeat:
 		page = radix_tree_deref_slot((void **)pages[i]);
 		if (unlikely(!page))
 			continue;
-		/*
-		 * this can only trigger if nr_found == 1, making livelock
-		 * a non issue.
-		 */
-		if (unlikely(page == RADIX_TREE_RETRY))
+		if (radix_tree_deref_retry(page)) {
+			if (ret)
+				start = pages[ret-1]->index;
 			goto restart;
+		}
 
 		if (!page_cache_get_speculative(page))
 			goto repeat;
@@ -830,16 +834,9 @@ repeat:
 		page = radix_tree_deref_slot((void **)pages[i]);
 		if (unlikely(!page))
 			continue;
-		/*
-		 * this can only trigger if nr_found == 1, making livelock
-		 * a non issue.
-		 */
-		if (unlikely(page == RADIX_TREE_RETRY))
+		if (radix_tree_deref_retry(page))
 			goto restart;
 
-		if (page->mapping == NULL || page->index != index)
-			break;
-
 		if (!page_cache_get_speculative(page))
 			goto repeat;
 
@@ -849,6 +846,16 @@ repeat:
 			goto repeat;
 		}
 
+		/*
+		 * must check mapping and index after taking the ref.
+		 * otherwise we can get both false positives and false
+		 * negatives, which is just confusing to the caller.
+		 */
+		if (page->mapping == NULL || page->index != index) {
+			page_cache_release(page);
+			break;
+		}
+
 		pages[ret] = page;
 		ret++;
 		index++;
@@ -887,11 +894,7 @@ repeat:
 		page = radix_tree_deref_slot((void **)pages[i]);
 		if (unlikely(!page))
 			continue;
-		/*
-		 * this can only trigger if nr_found == 1, making livelock
-		 * a non issue.
-		 */
-		if (unlikely(page == RADIX_TREE_RETRY))
+		if (radix_tree_deref_retry(page))
 			goto restart;
 
 		if (!page_cache_get_speculative(page))
@@ -1029,6 +1032,9 @@ find_page:
 				goto page_not_up_to_date;
 			if (!trylock_page(page))
 				goto page_not_up_to_date;
+			/* Did it get truncated before we got the lock? */
+			if (!page->mapping)
+				goto page_not_up_to_date_locked;
 			if (!mapping->a_ops->is_partially_uptodate(page,
 								desc, offset))
 				goto page_not_up_to_date_locked;
@@ -1563,8 +1569,10 @@ retry_find:
 			goto no_cached_page;
 	}
 
-	if (!lock_page_or_retry(page, vma->vm_mm, vmf->flags))
+	if (!lock_page_or_retry(page, vma->vm_mm, vmf->flags)) {
+		page_cache_release(page);
 		return ret | VM_FAULT_RETRY;
+	}
 
 	/* Did it get truncated? */
 	if (unlikely(page->mapping != mapping)) {
@@ -2219,7 +2227,7 @@ struct page *grab_cache_page_write_begin(struct address_space *mapping,
 		gfp_notmask = __GFP_FS;
 repeat:
 	page = find_lock_page(mapping, index);
-	if (likely(page))
+	if (page)
 		return page;
 
 	page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~gfp_notmask);