1 files changed, 62 insertions, 55 deletions

diff --git a/fs/buffer.c b/fs/buffer.c
index 2219a76e2ca..698c6b2cc46 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -41,6 +41,7 @@
 #include <linux/bitops.h>
 #include <linux/mpage.h>
 #include <linux/bit_spinlock.h>
+#include <linux/cleancache.h>
 
 static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
 
@@ -54,23 +55,15 @@ init_buffer(struct buffer_head *bh, bh_end_io_t *handler, void *private)
 }
 EXPORT_SYMBOL(init_buffer);
 
-static int sync_buffer(void *word)
+static int sleep_on_buffer(void *word)
 {
-	struct block_device *bd;
-	struct buffer_head *bh
-		= container_of(word, struct buffer_head, b_state);
-
-	smp_mb();
-	bd = bh->b_bdev;
-	if (bd)
-		blk_run_address_space(bd->bd_inode->i_mapping);
 	io_schedule();
 	return 0;
 }
 
 void __lock_buffer(struct buffer_head *bh)
 {
-	wait_on_bit_lock(&bh->b_state, BH_Lock, sync_buffer,
+	wait_on_bit_lock(&bh->b_state, BH_Lock, sleep_on_buffer,
 							TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL(__lock_buffer);
@@ -90,7 +83,7 @@ EXPORT_SYMBOL(unlock_buffer);
  */
 void __wait_on_buffer(struct buffer_head * bh)
 {
-	wait_on_bit(&bh->b_state, BH_Lock, sync_buffer, TASK_UNINTERRUPTIBLE);
+	wait_on_bit(&bh->b_state, BH_Lock, sleep_on_buffer, TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL(__wait_on_buffer);
 
@@ -277,6 +270,10 @@ void invalidate_bdev(struct block_device *bdev)
 	invalidate_bh_lrus();
 	lru_add_drain_all();	/* make sure all lru add caches are flushed */
 	invalidate_mapping_pages(mapping, 0, -1);
+	/* 99% of the time, we don't need to flush the cleancache on the bdev.
+	 * But, for the strange corners, lets be cautious
+	 */
+	cleancache_flush_inode(mapping);
 }
 EXPORT_SYMBOL(invalidate_bdev);
 
@@ -749,10 +746,12 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list)
 {
 	struct buffer_head *bh;
 	struct list_head tmp;
-	struct address_space *mapping, *prev_mapping = NULL;
+	struct address_space *mapping;
 	int err = 0, err2;
+	struct blk_plug plug;
 
 	INIT_LIST_HEAD(&tmp);
+	blk_start_plug(&plug);
 
 	spin_lock(lock);
 	while (!list_empty(list)) {
@@ -775,7 +774,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list)
 				 * still in flight on potentially older
 				 * contents.
 				 */
-				write_dirty_buffer(bh, WRITE_SYNC_PLUG);
+				write_dirty_buffer(bh, WRITE_SYNC);
 
 				/*
 				 * Kick off IO for the previous mapping. Note
@@ -783,16 +782,16 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list)
 				 * wait_on_buffer() will do that for us
 				 * through sync_buffer().
 				 */
-				if (prev_mapping && prev_mapping != mapping)
-					blk_run_address_space(prev_mapping);
-				prev_mapping = mapping;
-
 				brelse(bh);
 				spin_lock(lock);
 			}
 		}
 	}
 
+	spin_unlock(lock);
+	blk_finish_plug(&plug);
+	spin_lock(lock);
+
 	while (!list_empty(&tmp)) {
 		bh = BH_ENTRY(tmp.prev);
 		get_bh(bh);
@@ -1144,7 +1143,7 @@ __getblk_slow(struct block_device *bdev, sector_t block, int size)
  * inode list.
  *
  * mark_buffer_dirty() is atomic.  It takes bh->b_page->mapping->private_lock,
- * mapping->tree_lock and the global inode_lock.
+ * mapping->tree_lock and mapping->host->i_lock.
  */
 void mark_buffer_dirty(struct buffer_head *bh)
 {
@@ -1614,14 +1613,8 @@ EXPORT_SYMBOL(unmap_underlying_metadata);
  * prevents this contention from occurring.
  *
  * If block_write_full_page() is called with wbc->sync_mode ==
- * WB_SYNC_ALL, the writes are posted using WRITE_SYNC_PLUG; this
- * causes the writes to be flagged as synchronous writes, but the
- * block device queue will NOT be unplugged, since usually many pages
- * will be pushed to the out before the higher-level caller actually
- * waits for the writes to be completed.  The various wait functions,
- * such as wait_on_writeback_range() will ultimately call sync_page()
- * which will ultimately call blk_run_backing_dev(), which will end up
- * unplugging the device queue.
+ * WB_SYNC_ALL, the writes are posted using WRITE_SYNC; this
+ * causes the writes to be flagged as synchronous writes.
  */
 static int __block_write_full_page(struct inode *inode, struct page *page,
 			get_block_t *get_block, struct writeback_control *wbc,
@@ -1634,7 +1627,7 @@ static int __block_write_full_page(struct inode *inode, struct page *page,
 	const unsigned blocksize = 1 << inode->i_blkbits;
 	int nr_underway = 0;
 	int write_op = (wbc->sync_mode == WB_SYNC_ALL ?
-			WRITE_SYNC_PLUG : WRITE);
+			WRITE_SYNC : WRITE);
 
 	BUG_ON(!PageLocked(page));
 
@@ -2343,24 +2336,26 @@ EXPORT_SYMBOL(block_commit_write);
  * page lock we can determine safely if the page is beyond EOF. If it is not
  * beyond EOF, then the page is guaranteed safe against truncation until we
  * unlock the page.
+ *
+ * Direct callers of this function should call vfs_check_frozen() so that page
+ * fault does not busyloop until the fs is thawed.
  */
-int
-block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
-		   get_block_t get_block)
+int __block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
+			 get_block_t get_block)
 {
 	struct page *page = vmf->page;
 	struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
 	unsigned long end;
 	loff_t size;
-	int ret = VM_FAULT_NOPAGE; /* make the VM retry the fault */
+	int ret;
 
 	lock_page(page);
 	size = i_size_read(inode);
 	if ((page->mapping != inode->i_mapping) ||
 	    (page_offset(page) > size)) {
-		/* page got truncated out from underneath us */
-		unlock_page(page);
-		goto out;
+		/* We overload EFAULT to mean page got truncated */
+		ret = -EFAULT;
+		goto out_unlock;
 	}
 
 	/* page is wholly or partially inside EOF */
@@ -2373,18 +2368,41 @@ block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
 	if (!ret)
 		ret = block_commit_write(page, 0, end);
 
-	if (unlikely(ret)) {
-		unlock_page(page);
-		if (ret == -ENOMEM)
-			ret = VM_FAULT_OOM;
-		else /* -ENOSPC, -EIO, etc */
-			ret = VM_FAULT_SIGBUS;
-	} else
-		ret = VM_FAULT_LOCKED;
-
-out:
+	if (unlikely(ret < 0))
+		goto out_unlock;
+	/*
+	 * Freezing in progress? We check after the page is marked dirty and
+	 * with page lock held so if the test here fails, we are sure freezing
+	 * code will wait during syncing until the page fault is done - at that
+	 * point page will be dirty and unlocked so freezing code will write it
+	 * and writeprotect it again.
+	 */
+	set_page_dirty(page);
+	if (inode->i_sb->s_frozen != SB_UNFROZEN) {
+		ret = -EAGAIN;
+		goto out_unlock;
+	}
+	return 0;
+out_unlock:
+	unlock_page(page);
 	return ret;
 }
+EXPORT_SYMBOL(__block_page_mkwrite);
+
+int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
+		   get_block_t get_block)
+{
+	int ret;
+	struct super_block *sb = vma->vm_file->f_path.dentry->d_inode->i_sb;
+
+	/*
+	 * This check is racy but catches the common case. The check in
+	 * __block_page_mkwrite() is reliable.
+	 */
+	vfs_check_frozen(sb, SB_FREEZE_WRITE);
+	ret = __block_page_mkwrite(vma, vmf, get_block);
+	return block_page_mkwrite_return(ret);
+}
 EXPORT_SYMBOL(block_page_mkwrite);
 
 /*
@@ -3138,17 +3156,6 @@ out:
 }
 EXPORT_SYMBOL(try_to_free_buffers);
 
-void block_sync_page(struct page *page)
-{
-	struct address_space *mapping;
-
-	smp_mb();
-	mapping = page_mapping(page);
-	if (mapping)
-		blk_run_backing_dev(mapping->backing_dev_info, page);
-}
-EXPORT_SYMBOL(block_sync_page);
-
 /*
  * There are no bdflush tunables left.  But distributions are
  * still running obsolete flush daemons, so we terminate them here.