Merge tag 'please-pull-noboot' of git://git.kernel.org/pub/scm/linux/kernel/git/aegl...

[linux.git] / fs / buffer.c

diff --git a/fs/buffer.c b/fs/buffer.c
index cabc045f483d1b7a4d7693f8388a57f3cbbec650..4cc679d5bf58c7bc0d0a7eb09cbc07ab0575197d 100644 (file)
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -45,6 +45,7 @@
 #include <linux/mpage.h>
 #include <linux/bit_spinlock.h>
 #include <linux/pagevec.h>
+#include <linux/sched/mm.h>
 #include <trace/events/block.h>
 
 static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
@@ -813,12 +814,16 @@ struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size,
                bool retry)
 {
        struct buffer_head *bh, *head;
-       gfp_t gfp = GFP_NOFS;
+       gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT;
        long offset;
+       struct mem_cgroup *memcg;
 
        if (retry)
                gfp |= __GFP_NOFAIL;
 
+       memcg = get_mem_cgroup_from_page(page);
+       memalloc_use_memcg(memcg);
+
        head = NULL;
        offset = PAGE_SIZE;
        while ((offset -= size) >= 0) {
@@ -835,6 +840,9 @@ struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size,
                /* Link the buffer to its page */
                set_bh_page(bh, page, offset);
        }
+out:
+       memalloc_unuse_memcg();
+       mem_cgroup_put(memcg);
        return head;
 /*
  * In case anything failed, we just free everything we got.
@@ -848,7 +856,7 @@ struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size,
                } while (head);
        }
 
-       return NULL;
+       goto out;
 }
 EXPORT_SYMBOL_GPL(alloc_page_buffers);
 
@@ -1900,15 +1908,16 @@ iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh,
                break;
        case IOMAP_UNWRITTEN:
                /*
-                * For unwritten regions, we always need to ensure that
-                * sub-block writes cause the regions in the block we are not
-                * writing to are zeroed. Set the buffer as new to ensure this.
+                * For unwritten regions, we always need to ensure that regions
+                * in the block we are not writing to are zeroed. Mark the
+                * buffer as new to ensure this.
                 */
                set_buffer_new(bh);
                set_buffer_unwritten(bh);
                /* FALLTHRU */
        case IOMAP_MAPPED:
-               if (offset >= i_size_read(inode))
+               if ((iomap->flags & IOMAP_F_NEW) ||
+                   offset >= i_size_read(inode))
                        set_buffer_new(bh);
                bh->b_blocknr = (iomap->addr + offset - iomap->offset) >>
                                inode->i_blkbits;
@@ -2076,6 +2085,40 @@ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
 }
 EXPORT_SYMBOL(block_write_begin);
 
+int __generic_write_end(struct inode *inode, loff_t pos, unsigned copied,
+               struct page *page)
+{
+       loff_t old_size = inode->i_size;
+       bool i_size_changed = false;
+
+       /*
+        * No need to use i_size_read() here, the i_size cannot change under us
+        * because we hold i_rwsem.
+        *
+        * But it's important to update i_size while still holding page lock:
+        * page writeout could otherwise come in and zero beyond i_size.
+        */
+       if (pos + copied > inode->i_size) {
+               i_size_write(inode, pos + copied);
+               i_size_changed = true;
+       }
+
+       unlock_page(page);
+       put_page(page);
+
+       if (old_size < pos)
+               pagecache_isize_extended(inode, old_size, pos);
+       /*
+        * Don't mark the inode dirty under page lock. First, it unnecessarily
+        * makes the holding time of page lock longer. Second, it forces lock
+        * ordering of page lock and transaction start for journaling
+        * filesystems.
+        */
+       if (i_size_changed)
+               mark_inode_dirty(inode);
+       return copied;
+}
+
 int block_write_end(struct file *file, struct address_space *mapping,
                        loff_t pos, unsigned len, unsigned copied,
                        struct page *page, void *fsdata)
@@ -2116,39 +2159,8 @@ int generic_write_end(struct file *file, struct address_space *mapping,
                        loff_t pos, unsigned len, unsigned copied,
                        struct page *page, void *fsdata)
 {
-       struct inode *inode = mapping->host;
-       loff_t old_size = inode->i_size;
-       int i_size_changed = 0;
-
        copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
-
-       /*
-        * No need to use i_size_read() here, the i_size
-        * cannot change under us because we hold i_mutex.
-        *
-        * But it's important to update i_size while still holding page lock:
-        * page writeout could otherwise come in and zero beyond i_size.
-        */
-       if (pos+copied > inode->i_size) {
-               i_size_write(inode, pos+copied);
-               i_size_changed = 1;
-       }
-
-       unlock_page(page);
-       put_page(page);
-
-       if (old_size < pos)
-               pagecache_isize_extended(inode, old_size, pos);
-       /*
-        * Don't mark the inode dirty under page lock. First, it unnecessarily
-        * makes the holding time of page lock longer. Second, it forces lock
-        * ordering of page lock and transaction start for journaling
-        * filesystems.
-        */
-       if (i_size_changed)
-               mark_inode_dirty(inode);
-
-       return copied;
+       return __generic_write_end(mapping->host, pos, copied, page);
 }
 EXPORT_SYMBOL(generic_write_end);