1 files changed, 128 insertions, 85 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 226e4d89ef5d..38cacca05d77 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -109,6 +109,48 @@
  *   ->tasklist_lock            (memory_failure, collect_procs_ao)
  */
 
+static int page_cache_tree_insert(struct address_space *mapping,
+				  struct page *page, void **shadowp)
+{
+	struct radix_tree_node *node;
+	void **slot;
+	int error;
+
+	error = __radix_tree_create(&mapping->page_tree, page->index,
+				    &node, &slot);
+	if (error)
+		return error;
+	if (*slot) {
+		void *p;
+
+		p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock);
+		if (!radix_tree_exceptional_entry(p))
+			return -EEXIST;
+		if (shadowp)
+			*shadowp = p;
+		mapping->nrshadows--;
+		if (node)
+			workingset_node_shadows_dec(node);
+	}
+	radix_tree_replace_slot(slot, page);
+	mapping->nrpages++;
+	if (node) {
+		workingset_node_pages_inc(node);
+		/*
+		 * Don't track node that contains actual pages.
+		 *
+		 * Avoid acquiring the list_lru lock if already
+		 * untracked.  The list_empty() test is safe as
+		 * node->private_list is protected by
+		 * mapping->tree_lock.
+		 */
+		if (!list_empty(&node->private_list))
+			list_lru_del(&workingset_shadow_nodes,
+				     &node->private_list);
+	}
+	return 0;
+}
+
 static void page_cache_tree_delete(struct address_space *mapping,
 				   struct page *page, void *shadow)
 {
@@ -122,6 +164,14 @@ static void page_cache_tree_delete(struct address_space *mapping,
 
 	__radix_tree_lookup(&mapping->page_tree, page->index, &node, &slot);
 
+	if (!node) {
+		/*
+		 * We need a node to properly account shadow
+		 * entries. Don't plant any without. XXX
+		 */
+		shadow = NULL;
+	}
+
 	if (shadow) {
 		mapping->nrshadows++;
 		/*
@@ -519,7 +569,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 	VM_BUG_ON_PAGE(!PageLocked(new), new);
 	VM_BUG_ON_PAGE(new->mapping, new);
 
-	error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM);
+	error = radix_tree_preload(gfp_mask & GFP_RECLAIM_MASK);
 	if (!error) {
 		struct address_space *mapping = old->mapping;
 		void (*freepage)(struct page *);
@@ -536,9 +586,8 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 		memcg = mem_cgroup_begin_page_stat(old);
 		spin_lock_irqsave(&mapping->tree_lock, flags);
 		__delete_from_page_cache(old, NULL, memcg);
-		error = radix_tree_insert(&mapping->page_tree, offset, new);
+		error = page_cache_tree_insert(mapping, new, NULL);
 		BUG_ON(error);
-		mapping->nrpages++;
 
 		/*
 		 * hugetlb pages do not participate in page cache accounting.
@@ -560,48 +609,6 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 }
 EXPORT_SYMBOL_GPL(replace_page_cache_page);
 
-static int page_cache_tree_insert(struct address_space *mapping,
-				  struct page *page, void **shadowp)
-{
-	struct radix_tree_node *node;
-	void **slot;
-	int error;
-
-	error = __radix_tree_create(&mapping->page_tree, page->index,
-				    &node, &slot);
-	if (error)
-		return error;
-	if (*slot) {
-		void *p;
-
-		p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock);
-		if (!radix_tree_exceptional_entry(p))
-			return -EEXIST;
-		if (shadowp)
-			*shadowp = p;
-		mapping->nrshadows--;
-		if (node)
-			workingset_node_shadows_dec(node);
-	}
-	radix_tree_replace_slot(slot, page);
-	mapping->nrpages++;
-	if (node) {
-		workingset_node_pages_inc(node);
-		/*
-		 * Don't track node that contains actual pages.
-		 *
-		 * Avoid acquiring the list_lru lock if already
-		 * untracked.  The list_empty() test is safe as
-		 * node->private_list is protected by
-		 * mapping->tree_lock.
-		 */
-		if (!list_empty(&node->private_list))
-			list_lru_del(&workingset_shadow_nodes,
-				     &node->private_list);
-	}
-	return 0;
-}
-
 static int __add_to_page_cache_locked(struct page *page,
 				      struct address_space *mapping,
 				      pgoff_t offset, gfp_t gfp_mask,
@@ -621,7 +628,7 @@ static int __add_to_page_cache_locked(struct page *page,
 			return error;
 	}
 
-	error = radix_tree_maybe_preload(gfp_mask & ~__GFP_HIGHMEM);
+	error = radix_tree_maybe_preload(gfp_mask & GFP_RECLAIM_MASK);
 	if (error) {
 		if (!huge)
 			mem_cgroup_cancel_charge(page, memcg);
@@ -856,9 +863,12 @@ void page_endio(struct page *page, int rw, int err)
 		unlock_page(page);
 	} else { /* rw == WRITE */
 		if (err) {
+			struct address_space *mapping;
+
 			SetPageError(page);
-			if (page->mapping)
-				mapping_set_error(page->mapping, err);
+			mapping = page_mapping(page);
+			if (mapping)
+				mapping_set_error(mapping, err);
 		}
 		end_page_writeback(page);
 	}
@@ -1180,8 +1190,7 @@ no_page:
 		if (fgp_flags & FGP_ACCESSED)
 			__SetPageReferenced(page);
 
-		err = add_to_page_cache_lru(page, mapping, offset,
-				gfp_mask & GFP_RECLAIM_MASK);
+		err = add_to_page_cache_lru(page, mapping, offset, gfp_mask);
 		if (unlikely(err)) {
 			page_cache_release(page);
 			page = NULL;
@@ -1565,6 +1574,11 @@ static ssize_t do_generic_file_read(struct file *filp, loff_t *ppos,
 
 		cond_resched();
 find_page:
+		if (fatal_signal_pending(current)) {
+			error = -EINTR;
+			goto out;
+		}
+
 		page = find_get_page(mapping, index);
 		if (!page) {
 			page_cache_sync_readahead(mapping,
@@ -1580,6 +1594,15 @@ find_page:
 					index, last_index - index);
 		}
 		if (!PageUptodate(page)) {
+			/*
+			 * See comment in do_read_cache_page on why
+			 * wait_on_page_locked is used to avoid unnecessarily
+			 * serialisations and why it's safe.
+			 */
+			wait_on_page_locked_killable(page);
+			if (PageUptodate(page))
+				goto page_ok;
+
 			if (inode->i_blkbits == PAGE_CACHE_SHIFT ||
 					!mapping->a_ops->is_partially_uptodate)
 				goto page_not_up_to_date;
@@ -1825,19 +1848,18 @@ EXPORT_SYMBOL(generic_file_read_iter);
  * This adds the requested page to the page cache if it isn't already there,
  * and schedules an I/O to read in its contents from disk.
  */
-static int page_cache_read(struct file *file, pgoff_t offset)
+static int page_cache_read(struct file *file, pgoff_t offset, gfp_t gfp_mask)
 {
 	struct address_space *mapping = file->f_mapping;
 	struct page *page;
 	int ret;
 
 	do {
-		page = page_cache_alloc_cold(mapping);
+		page = __page_cache_alloc(gfp_mask|__GFP_COLD);
 		if (!page)
 			return -ENOMEM;
 
-		ret = add_to_page_cache_lru(page, mapping, offset,
-				mapping_gfp_constraint(mapping, GFP_KERNEL));
+		ret = add_to_page_cache_lru(page, mapping, offset, gfp_mask);
 		if (ret == 0)
 			ret = mapping->a_ops->readpage(file, page);
 		else if (ret == -EEXIST)
@@ -2018,7 +2040,7 @@ no_cached_page:
 	 * We're only likely to ever get here if MADV_RANDOM is in
 	 * effect.
 	 */
-	error = page_cache_read(file, offset);
+	error = page_cache_read(file, offset, vmf->gfp_mask);
 
 	/*
 	 * The page we want has now been added to the page cache.
@@ -2215,7 +2237,7 @@ static struct page *wait_on_page_read(struct page *page)
 	return page;
 }
 
-static struct page *__read_cache_page(struct address_space *mapping,
+static struct page *do_read_cache_page(struct address_space *mapping,
 				pgoff_t index,
 				int (*filler)(void *, struct page *),
 				void *data,
@@ -2237,53 +2259,74 @@ repeat:
 			/* Presumably ENOMEM for radix tree node */
 			return ERR_PTR(err);
 		}
+
+filler:
 		err = filler(data, page);
 		if (err < 0) {
 			page_cache_release(page);
-			page = ERR_PTR(err);
-		} else {
-			page = wait_on_page_read(page);
+			return ERR_PTR(err);
 		}
-	}
-	return page;
-}
 
-static struct page *do_read_cache_page(struct address_space *mapping,
-				pgoff_t index,
-				int (*filler)(void *, struct page *),
-				void *data,
-				gfp_t gfp)
-
-{
-	struct page *page;
-	int err;
+		page = wait_on_page_read(page);
+		if (IS_ERR(page))
+			return page;
+		goto out;
+	}
+	if (PageUptodate(page))
+		goto out;
 
-retry:
-	page = __read_cache_page(mapping, index, filler, data, gfp);
-	if (IS_ERR(page))
-		return page;
+	/*
+	 * Page is not up to date and may be locked due one of the following
+	 * case a: Page is being filled and the page lock is held
+	 * case b: Read/write error clearing the page uptodate status
+	 * case c: Truncation in progress (page locked)
+	 * case d: Reclaim in progress
+	 *
+	 * Case a, the page will be up to date when the page is unlocked.
+	 *    There is no need to serialise on the page lock here as the page
+	 *    is pinned so the lock gives no additional protection. Even if the
+	 *    the page is truncated, the data is still valid if PageUptodate as
+	 *    it's a race vs truncate race.
+	 * Case b, the page will not be up to date
+	 * Case c, the page may be truncated but in itself, the data may still
+	 *    be valid after IO completes as it's a read vs truncate race. The
+	 *    operation must restart if the page is not uptodate on unlock but
+	 *    otherwise serialising on page lock to stabilise the mapping gives
+	 *    no additional guarantees to the caller as the page lock is
+	 *    released before return.
+	 * Case d, similar to truncation. If reclaim holds the page lock, it
+	 *    will be a race with remove_mapping that determines if the mapping
+	 *    is valid on unlock but otherwise the data is valid and there is
+	 *    no need to serialise with page lock.
+	 *
+	 * As the page lock gives no additional guarantee, we optimistically
+	 * wait on the page to be unlocked and check if it's up to date and
+	 * use the page if it is. Otherwise, the page lock is required to
+	 * distinguish between the different cases. The motivation is that we
+	 * avoid spurious serialisations and wakeups when multiple processes
+	 * wait on the same page for IO to complete.
+	 */
+	wait_on_page_locked(page);
 	if (PageUptodate(page))
 		goto out;
 
+	/* Distinguish between all the cases under the safety of the lock */
 	lock_page(page);
+
+	/* Case c or d, restart the operation */
 	if (!page->mapping) {
 		unlock_page(page);
 		page_cache_release(page);
-		goto retry;
+		goto repeat;
 	}
+
+	/* Someone else locked and filled the page in a very small window */
 	if (PageUptodate(page)) {
 		unlock_page(page);
 		goto out;
 	}
-	err = filler(data, page);
-	if (err < 0) {
-		page_cache_release(page);
-		return ERR_PTR(err);
-	} else {
-		page = wait_on_page_read(page);
-		if (IS_ERR(page))
-			return page;
-	}
+	goto filler;
+
 out:
 	mark_page_accessed(page);
 	return page;