1 files changed, 68 insertions, 167 deletions

diff --git a/fs/buffer.c b/fs/buffer.c
index 891e1c78e4f..6e35762b616 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -166,151 +166,6 @@ void end_buffer_write_sync(struct buffer_head *bh, int uptodate)
 }
 
 /*
- * Write out and wait upon all the dirty data associated with a block
- * device via its mapping.  Does not take the superblock lock.
- */
-int sync_blockdev(struct block_device *bdev)
-{
-	int ret = 0;
-
-	if (bdev)
-		ret = filemap_write_and_wait(bdev->bd_inode->i_mapping);
-	return ret;
-}
-EXPORT_SYMBOL(sync_blockdev);
-
-/*
- * Write out and wait upon all dirty data associated with this
- * device.   Filesystem data as well as the underlying block
- * device.  Takes the superblock lock.
- */
-int fsync_bdev(struct block_device *bdev)
-{
-	struct super_block *sb = get_super(bdev);
-	if (sb) {
-		int res = fsync_super(sb);
-		drop_super(sb);
-		return res;
-	}
-	return sync_blockdev(bdev);
-}
-
-/**
- * freeze_bdev  --  lock a filesystem and force it into a consistent state
- * @bdev:	blockdevice to lock
- *
- * This takes the block device bd_mount_sem to make sure no new mounts
- * happen on bdev until thaw_bdev() is called.
- * If a superblock is found on this device, we take the s_umount semaphore
- * on it to make sure nobody unmounts until the snapshot creation is done.
- * The reference counter (bd_fsfreeze_count) guarantees that only the last
- * unfreeze process can unfreeze the frozen filesystem actually when multiple
- * freeze requests arrive simultaneously. It counts up in freeze_bdev() and
- * count down in thaw_bdev(). When it becomes 0, thaw_bdev() will unfreeze
- * actually.
- */
-struct super_block *freeze_bdev(struct block_device *bdev)
-{
-	struct super_block *sb;
-	int error = 0;
-
-	mutex_lock(&bdev->bd_fsfreeze_mutex);
-	if (bdev->bd_fsfreeze_count > 0) {
-		bdev->bd_fsfreeze_count++;
-		sb = get_super(bdev);
-		mutex_unlock(&bdev->bd_fsfreeze_mutex);
-		return sb;
-	}
-	bdev->bd_fsfreeze_count++;
-
-	down(&bdev->bd_mount_sem);
-	sb = get_super(bdev);
-	if (sb && !(sb->s_flags & MS_RDONLY)) {
-		sb->s_frozen = SB_FREEZE_WRITE;
-		smp_wmb();
-
-		__fsync_super(sb);
-
-		sb->s_frozen = SB_FREEZE_TRANS;
-		smp_wmb();
-
-		sync_blockdev(sb->s_bdev);
-
-		if (sb->s_op->freeze_fs) {
-			error = sb->s_op->freeze_fs(sb);
-			if (error) {
-				printk(KERN_ERR
-					"VFS:Filesystem freeze failed\n");
-				sb->s_frozen = SB_UNFROZEN;
-				drop_super(sb);
-				up(&bdev->bd_mount_sem);
-				bdev->bd_fsfreeze_count--;
-				mutex_unlock(&bdev->bd_fsfreeze_mutex);
-				return ERR_PTR(error);
-			}
-		}
-	}
-
-	sync_blockdev(bdev);
-	mutex_unlock(&bdev->bd_fsfreeze_mutex);
-
-	return sb;	/* thaw_bdev releases s->s_umount and bd_mount_sem */
-}
-EXPORT_SYMBOL(freeze_bdev);
-
-/**
- * thaw_bdev  -- unlock filesystem
- * @bdev:	blockdevice to unlock
- * @sb:		associated superblock
- *
- * Unlocks the filesystem and marks it writeable again after freeze_bdev().
- */
-int thaw_bdev(struct block_device *bdev, struct super_block *sb)
-{
-	int error = 0;
-
-	mutex_lock(&bdev->bd_fsfreeze_mutex);
-	if (!bdev->bd_fsfreeze_count) {
-		mutex_unlock(&bdev->bd_fsfreeze_mutex);
-		return -EINVAL;
-	}
-
-	bdev->bd_fsfreeze_count--;
-	if (bdev->bd_fsfreeze_count > 0) {
-		if (sb)
-			drop_super(sb);
-		mutex_unlock(&bdev->bd_fsfreeze_mutex);
-		return 0;
-	}
-
-	if (sb) {
-		BUG_ON(sb->s_bdev != bdev);
-		if (!(sb->s_flags & MS_RDONLY)) {
-			if (sb->s_op->unfreeze_fs) {
-				error = sb->s_op->unfreeze_fs(sb);
-				if (error) {
-					printk(KERN_ERR
-						"VFS:Filesystem thaw failed\n");
-					sb->s_frozen = SB_FREEZE_TRANS;
-					bdev->bd_fsfreeze_count++;
-					mutex_unlock(&bdev->bd_fsfreeze_mutex);
-					return error;
-				}
-			}
-			sb->s_frozen = SB_UNFROZEN;
-			smp_wmb();
-			wake_up(&sb->s_wait_unfrozen);
-		}
-		drop_super(sb);
-	}
-
-	up(&bdev->bd_mount_sem);
-	mutex_unlock(&bdev->bd_fsfreeze_mutex);
-	return 0;
-}
-EXPORT_SYMBOL(thaw_bdev);
-
-/*
  * Various filesystems appear to want __find_get_block to be non-blocking.
  * But it's the page lock which protects the buffers.  To get around this,
  * we get exclusion from try_to_free_buffers with the blockdev mapping's
@@ -344,13 +199,13 @@ __find_get_block_slow(struct block_device *bdev, sector_t block)
 	head = page_buffers(page);
 	bh = head;
 	do {
-		if (bh->b_blocknr == block) {
+		if (!buffer_mapped(bh))
+			all_mapped = 0;
+		else if (bh->b_blocknr == block) {
 			ret = bh;
 			get_bh(bh);
 			goto out_unlock;
 		}
-		if (!buffer_mapped(bh))
-			all_mapped = 0;
 		bh = bh->b_this_page;
 	} while (bh != head);
 
@@ -435,7 +290,7 @@ static void free_more_memory(void)
 						&zone);
 		if (zone)
 			try_to_free_pages(node_zonelist(nid, GFP_NOFS), 0,
-						GFP_NOFS);
+						GFP_NOFS, NULL);
 	}
 }
 
@@ -692,6 +547,39 @@ repeat:
 	return err;
 }
 
+void do_thaw_all(unsigned long unused)
+{
+	struct super_block *sb;
+	char b[BDEVNAME_SIZE];
+
+	spin_lock(&sb_lock);
+restart:
+	list_for_each_entry(sb, &super_blocks, s_list) {
+		sb->s_count++;
+		spin_unlock(&sb_lock);
+		down_read(&sb->s_umount);
+		while (sb->s_bdev && !thaw_bdev(sb->s_bdev, sb))
+			printk(KERN_WARNING "Emergency Thaw on %s\n",
+			       bdevname(sb->s_bdev, b));
+		up_read(&sb->s_umount);
+		spin_lock(&sb_lock);
+		if (__put_super_and_need_restart(sb))
+			goto restart;
+	}
+	spin_unlock(&sb_lock);
+	printk(KERN_WARNING "Emergency Thaw complete\n");
+}
+
+/**
+ * emergency_thaw_all -- forcibly thaw every frozen filesystem
+ *
+ * Used for emergency unfreeze of all filesystems via SysRq
+ */
+void emergency_thaw_all(void)
+{
+	pdflush_operation(do_thaw_all, 0);
+}
+
 /**
  * sync_mapping_buffers - write out & wait upon a mapping's "associated" buffers
  * @mapping: the mapping which wants those buffers written
@@ -766,14 +654,7 @@ static void __set_page_dirty(struct page *page,
 	spin_lock_irq(&mapping->tree_lock);
 	if (page->mapping) {	/* Race with truncate? */
 		WARN_ON_ONCE(warn && !PageUptodate(page));
-
-		if (mapping_cap_account_dirty(mapping)) {
-			__inc_zone_page_state(page, NR_FILE_DIRTY);
-			__inc_bdi_stat(mapping->backing_dev_info,
-					BDI_RECLAIMABLE);
-			task_dirty_inc(current);
-			task_io_account_write(PAGE_CACHE_SIZE);
-		}
+		account_page_dirtied(page, mapping);
 		radix_tree_tag_set(&mapping->page_tree,
 				page_index(page), PAGECACHE_TAG_DIRTY);
 	}
@@ -856,7 +737,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list)
 {
 	struct buffer_head *bh;
 	struct list_head tmp;
-	struct address_space *mapping;
+	struct address_space *mapping, *prev_mapping = NULL;
 	int err = 0, err2;
 
 	INIT_LIST_HEAD(&tmp);
@@ -881,7 +762,18 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list)
 				 * contents - it is a noop if I/O is still in
 				 * flight on potentially older contents.
 				 */
-				ll_rw_block(SWRITE_SYNC, 1, &bh);
+				ll_rw_block(SWRITE_SYNC_PLUG, 1, &bh);
+
+				/*
+				 * Kick off IO for the previous mapping. Note
+				 * that we will not run the very last mapping,
+				 * 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);
 			}
@@ -1714,6 +1606,7 @@ static int __block_write_full_page(struct inode *inode, struct page *page,
 	struct buffer_head *bh, *head;
 	const unsigned blocksize = 1 << inode->i_blkbits;
 	int nr_underway = 0;
+	int write_op = (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE);
 
 	BUG_ON(!PageLocked(page));
 
@@ -1805,7 +1698,7 @@ static int __block_write_full_page(struct inode *inode, struct page *page,
 	do {
 		struct buffer_head *next = bh->b_this_page;
 		if (buffer_async_write(bh)) {
-			submit_bh(WRITE, bh);
+			submit_bh(write_op, bh);
 			nr_underway++;
 		}
 		bh = next;
@@ -1859,7 +1752,7 @@ recover:
 		struct buffer_head *next = bh->b_this_page;
 		if (buffer_async_write(bh)) {
 			clear_buffer_dirty(bh);
-			submit_bh(WRITE, bh);
+			submit_bh(write_op, bh);
 			nr_underway++;
 		}
 		bh = next;
@@ -2465,13 +2358,14 @@ int block_commit_write(struct page *page, unsigned from, unsigned to)
  * unlock the page.
  */
 int
-block_page_mkwrite(struct vm_area_struct *vma, struct page *page,
+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 = -EINVAL;
+	int ret = VM_FAULT_NOPAGE; /* make the VM retry the fault */
 
 	lock_page(page);
 	size = i_size_read(inode);
@@ -2491,6 +2385,13 @@ block_page_mkwrite(struct vm_area_struct *vma, struct page *page,
 	if (!ret)
 		ret = block_commit_write(page, 0, end);
 
+	if (unlikely(ret)) {
+		if (ret == -ENOMEM)
+			ret = VM_FAULT_OOM;
+		else /* -ENOSPC, -EIO, etc */
+			ret = VM_FAULT_SIGBUS;
+	}
+
 out_unlock:
 	unlock_page(page);
 	return ret;
@@ -3067,12 +2968,13 @@ void ll_rw_block(int rw, int nr, struct buffer_head *bhs[])
 	for (i = 0; i < nr; i++) {
 		struct buffer_head *bh = bhs[i];
 
-		if (rw == SWRITE || rw == SWRITE_SYNC)
+		if (rw == SWRITE || rw == SWRITE_SYNC || rw == SWRITE_SYNC_PLUG)
 			lock_buffer(bh);
 		else if (!trylock_buffer(bh))
 			continue;
 
-		if (rw == WRITE || rw == SWRITE || rw == SWRITE_SYNC) {
+		if (rw == WRITE || rw == SWRITE || rw == SWRITE_SYNC ||
+		    rw == SWRITE_SYNC_PLUG) {
 			if (test_clear_buffer_dirty(bh)) {
 				bh->b_end_io = end_buffer_write_sync;
 				get_bh(bh);
@@ -3108,7 +3010,7 @@ int sync_dirty_buffer(struct buffer_head *bh)
 	if (test_clear_buffer_dirty(bh)) {
 		get_bh(bh);
 		bh->b_end_io = end_buffer_write_sync;
-		ret = submit_bh(WRITE, bh);
+		ret = submit_bh(WRITE_SYNC, bh);
 		wait_on_buffer(bh);
 		if (buffer_eopnotsupp(bh)) {
 			clear_buffer_eopnotsupp(bh);
@@ -3426,7 +3328,6 @@ EXPORT_SYMBOL(cont_write_begin);
 EXPORT_SYMBOL(end_buffer_read_sync);
 EXPORT_SYMBOL(end_buffer_write_sync);
 EXPORT_SYMBOL(file_fsync);
-EXPORT_SYMBOL(fsync_bdev);
 EXPORT_SYMBOL(generic_block_bmap);
 EXPORT_SYMBOL(generic_cont_expand_simple);
 EXPORT_SYMBOL(init_buffer);