Btrfs: use the inode's mapping mask for allocating pages

Johannes pointed out we were allocating only kernel pages for doing writes,
which is kind of a big deal if you are on 32bit and have more than a gig of ram.
So fix our allocations to use the mapping's gfp but still clear __GFP_FS so we
don't re-enter.  Thanks,

Reported-by: Johannes Weiner <jweiner@redhat.com>
Signed-off-by: Josef Bacik <josef@redhat.com>
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 2947e949..88e3956 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3282,6 +3282,7 @@
 	pgoff_t index = from >> PAGE_CACHE_SHIFT;
 	unsigned offset = from & (PAGE_CACHE_SIZE-1);
 	struct page *page;
+	gfp_t mask = btrfs_alloc_write_mask(mapping);
 	int ret = 0;
 	u64 page_start;
 	u64 page_end;
@@ -3294,7 +3295,7 @@
 
 	ret = -ENOMEM;
 again:
-	page = find_or_create_page(mapping, index, GFP_NOFS);
+	page = find_or_create_page(mapping, index, mask);
 	if (!page) {
 		btrfs_delalloc_release_space(inode, PAGE_CACHE_SIZE);
 		goto out;