mm: get rid of radix tree gfp mask for pagecache_get_page

commit 45f87de57f8fad59302fd263dd81ffa4843b5b24 upstream.

Commit 2457aec63745 ("mm: non-atomically mark page accessed during page
cache allocation where possible") has added a separate parameter for
specifying gfp mask for radix tree allocations.

Not only this is less than optimal from the API point of view because it
is error prone, it is also buggy currently because
grab_cache_page_write_begin is using GFP_KERNEL for radix tree and if
fgp_flags doesn't contain FGP_NOFS (mostly controlled by fs by
AOP_FLAG_NOFS flag) but the mapping_gfp_mask has __GFP_FS cleared then
the radix tree allocation wouldn't obey the restriction and might
recurse into filesystem and cause deadlocks.  This is the case for most
filesystems unfortunately because only ext4 and gfs2 are using
AOP_FLAG_NOFS.

Let's simply remove radix_gfp_mask parameter because the allocation
context is same for both page cache and for the radix tree.  Just make
sure that the radix tree gets only the sane subset of the mask (e.g.  do
not pass __GFP_WRITE).

Long term it is more preferable to convert remaining users of
AOP_FLAG_NOFS to use mapping_gfp_mask instead and simplify this
interface even further.

Reported-by: Dave Chinner <david@fromorbit.com>
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 9 insertions, 11 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 8aa817460cc7..217cfd3b3264 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -897,7 +897,7 @@ EXPORT_SYMBOL(find_lock_entry);
  * @mapping: the address_space to search
  * @offset: the page index
  * @fgp_flags: PCG flags
- * @gfp_mask: gfp mask to use if a page is to be allocated
+ * @gfp_mask: gfp mask to use for the page cache data page allocation
  *
  * Looks up the page cache slot at @mapping & @offset.
  *
@@ -916,7 +916,7 @@ EXPORT_SYMBOL(find_lock_entry);
  * If there is a page cache page, it is returned with an increased refcount.
  */
 struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
-	int fgp_flags, gfp_t cache_gfp_mask, gfp_t radix_gfp_mask)
+	int fgp_flags, gfp_t gfp_mask)
 {
 	struct page *page;
 
@@ -953,13 +953,11 @@ no_page:
 	if (!page && (fgp_flags & FGP_CREAT)) {
 		int err;
 		if ((fgp_flags & FGP_WRITE) && mapping_cap_account_dirty(mapping))
-			cache_gfp_mask |= __GFP_WRITE;
-		if (fgp_flags & FGP_NOFS) {
-			cache_gfp_mask &= ~__GFP_FS;
-			radix_gfp_mask &= ~__GFP_FS;
-		}
+			gfp_mask |= __GFP_WRITE;
+		if (fgp_flags & FGP_NOFS)
+			gfp_mask &= ~__GFP_FS;
 
-		page = __page_cache_alloc(cache_gfp_mask);
+		page = __page_cache_alloc(gfp_mask);
 		if (!page)
 			return NULL;
 
@@ -970,7 +968,8 @@ no_page:
 		if (fgp_flags & FGP_ACCESSED)
 			init_page_accessed(page);
 
-		err = add_to_page_cache_lru(page, mapping, offset, radix_gfp_mask);
+		err = add_to_page_cache_lru(page, mapping, offset,
+				gfp_mask & GFP_RECLAIM_MASK);
 		if (unlikely(err)) {
 			page_cache_release(page);
 			page = NULL;
@@ -2460,8 +2459,7 @@ struct page *grab_cache_page_write_begin(struct address_space *mapping,
 		fgp_flags |= FGP_NOFS;
 
 	page = pagecache_get_page(mapping, index, fgp_flags,
-			mapping_gfp_mask(mapping),
-			GFP_KERNEL);
+			mapping_gfp_mask(mapping));
 	if (page)
 		wait_for_stable_page(page);