1 files changed, 195 insertions, 121 deletions

diff --git a/fs/sync.c b/fs/sync.c
index 7cd005ea763..b28d1dd10e8 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -5,127 +5,218 @@
 #include <linux/kernel.h>
 #include <linux/file.h>
 #include <linux/fs.h>
-#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/export.h>
+#include <linux/namei.h>
 #include <linux/sched.h>
 #include <linux/writeback.h>
 #include <linux/syscalls.h>
 #include <linux/linkage.h>
 #include <linux/pagemap.h>
 #include <linux/quotaops.h>
-#include <linux/buffer_head.h>
+#include <linux/backing-dev.h>
+#include "internal.h"
 
 #define VALID_FLAGS (SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE| \
 			SYNC_FILE_RANGE_WAIT_AFTER)
 
 /*
- * sync everything.  Start out by waking pdflush, because that writes back
- * all queues in parallel.
+ * Do the filesystem syncing work. For simple filesystems
+ * writeback_inodes_sb(sb) just dirties buffers with inodes so we have to
+ * submit IO for these buffers via __sync_blockdev(). This also speeds up the
+ * wait == 1 case since in that case write_inode() functions do
+ * sync_dirty_buffer() and thus effectively write one block at a time.
  */
-static void do_sync(unsigned long wait)
+static int __sync_filesystem(struct super_block *sb, int wait)
 {
-	wakeup_pdflush(0);
-	sync_inodes(0);		/* All mappings, inodes and their blockdevs */
-	DQUOT_SYNC(NULL);
-	sync_supers();		/* Write the superblocks */
-	sync_filesystems(0);	/* Start syncing the filesystems */
-	sync_filesystems(wait);	/* Waitingly sync the filesystems */
-	sync_inodes(wait);	/* Mappings, inodes and blockdevs, again. */
-	if (!wait)
-		printk("Emergency Sync complete\n");
-	if (unlikely(laptop_mode))
-		laptop_sync_completion();
+	if (wait)
+		sync_inodes_sb(sb);
+	else
+		writeback_inodes_sb(sb, WB_REASON_SYNC);
+
+	if (sb->s_op->sync_fs)
+		sb->s_op->sync_fs(sb, wait);
+	return __sync_blockdev(sb->s_bdev, wait);
 }
 
-asmlinkage long sys_sync(void)
+/*
+ * Write out and wait upon all dirty data associated with this
+ * superblock.  Filesystem data as well as the underlying block
+ * device.  Takes the superblock lock.
+ */
+int sync_filesystem(struct super_block *sb)
 {
-	do_sync(1);
-	return 0;
+	int ret;
+
+	/*
+	 * We need to be protected against the filesystem going from
+	 * r/o to r/w or vice versa.
+	 */
+	WARN_ON(!rwsem_is_locked(&sb->s_umount));
+
+	/*
+	 * No point in syncing out anything if the filesystem is read-only.
+	 */
+	if (sb->s_flags & MS_RDONLY)
+		return 0;
+
+	ret = __sync_filesystem(sb, 0);
+	if (ret < 0)
+		return ret;
+	return __sync_filesystem(sb, 1);
 }
+EXPORT_SYMBOL_GPL(sync_filesystem);
 
-void emergency_sync(void)
+static void sync_inodes_one_sb(struct super_block *sb, void *arg)
 {
-	pdflush_operation(do_sync, 0);
+	if (!(sb->s_flags & MS_RDONLY))
+		sync_inodes_sb(sb);
+}
+
+static void sync_fs_one_sb(struct super_block *sb, void *arg)
+{
+	if (!(sb->s_flags & MS_RDONLY) && sb->s_op->sync_fs)
+		sb->s_op->sync_fs(sb, *(int *)arg);
+}
+
+static void fdatawrite_one_bdev(struct block_device *bdev, void *arg)
+{
+	filemap_fdatawrite(bdev->bd_inode->i_mapping);
+}
+
+static void fdatawait_one_bdev(struct block_device *bdev, void *arg)
+{
+	filemap_fdatawait(bdev->bd_inode->i_mapping);
 }
 
 /*
- * Generic function to fsync a file.
- *
- * filp may be NULL if called via the msync of a vma.
+ * Sync everything. We start by waking flusher threads so that most of
+ * writeback runs on all devices in parallel. Then we sync all inodes reliably
+ * which effectively also waits for all flusher threads to finish doing
+ * writeback. At this point all data is on disk so metadata should be stable
+ * and we tell filesystems to sync their metadata via ->sync_fs() calls.
+ * Finally, we writeout all block devices because some filesystems (e.g. ext2)
+ * just write metadata (such as inodes or bitmaps) to block device page cache
+ * and do not sync it on their own in ->sync_fs().
  */
-int file_fsync(struct file *filp, struct dentry *dentry, int datasync)
+SYSCALL_DEFINE0(sync)
 {
-	struct inode * inode = dentry->d_inode;
-	struct super_block * sb;
-	int ret, err;
-
-	/* sync the inode to buffers */
-	ret = write_inode_now(inode, 0);
-
-	/* sync the superblock to buffers */
-	sb = inode->i_sb;
-	lock_super(sb);
-	if (sb->s_op->write_super)
-		sb->s_op->write_super(sb);
-	unlock_super(sb);
-
-	/* .. finally sync the buffers to disk */
-	err = sync_blockdev(sb->s_bdev);
-	if (!ret)
-		ret = err;
-	return ret;
+	int nowait = 0, wait = 1;
+
+	wakeup_flusher_threads(0, WB_REASON_SYNC);
+	iterate_supers(sync_inodes_one_sb, NULL);
+	iterate_supers(sync_fs_one_sb, &nowait);
+	iterate_supers(sync_fs_one_sb, &wait);
+	iterate_bdevs(fdatawrite_one_bdev, NULL);
+	iterate_bdevs(fdatawait_one_bdev, NULL);
+	if (unlikely(laptop_mode))
+		laptop_sync_completion();
+	return 0;
 }
 
-long do_fsync(struct file *file, int datasync)
+static void do_sync_work(struct work_struct *work)
 {
-	int ret;
-	int err;
-	struct address_space *mapping = file->f_mapping;
+	int nowait = 0;
 
-	if (!file->f_op || !file->f_op->fsync) {
-		/* Why?  We can still call filemap_fdatawrite */
-		ret = -EINVAL;
-		goto out;
+	/*
+	 * Sync twice to reduce the possibility we skipped some inodes / pages
+	 * because they were temporarily locked
+	 */
+	iterate_supers(sync_inodes_one_sb, &nowait);
+	iterate_supers(sync_fs_one_sb, &nowait);
+	iterate_bdevs(fdatawrite_one_bdev, NULL);
+	iterate_supers(sync_inodes_one_sb, &nowait);
+	iterate_supers(sync_fs_one_sb, &nowait);
+	iterate_bdevs(fdatawrite_one_bdev, NULL);
+	printk("Emergency Sync complete\n");
+	kfree(work);
+}
+
+void emergency_sync(void)
+{
+	struct work_struct *work;
+
+	work = kmalloc(sizeof(*work), GFP_ATOMIC);
+	if (work) {
+		INIT_WORK(work, do_sync_work);
+		schedule_work(work);
 	}
+}
 
-	ret = filemap_fdatawrite(mapping);
+/*
+ * sync a single super
+ */
+SYSCALL_DEFINE1(syncfs, int, fd)
+{
+	struct fd f = fdget(fd);
+	struct super_block *sb;
+	int ret;
 
-	/*
-	 * We need to protect against concurrent writers, which could cause
-	 * livelocks in fsync_buffers_list().
-	 */
-	mutex_lock(&mapping->host->i_mutex);
-	err = file->f_op->fsync(file, file->f_path.dentry, datasync);
-	if (!ret)
-		ret = err;
-	mutex_unlock(&mapping->host->i_mutex);
-	err = filemap_fdatawait(mapping);
-	if (!ret)
-		ret = err;
-out:
+	if (!f.file)
+		return -EBADF;
+	sb = f.file->f_dentry->d_sb;
+
+	down_read(&sb->s_umount);
+	ret = sync_filesystem(sb);
+	up_read(&sb->s_umount);
+
+	fdput(f);
 	return ret;
 }
 
-static long __do_fsync(unsigned int fd, int datasync)
+/**
+ * vfs_fsync_range - helper to sync a range of data & metadata to disk
+ * @file:		file to sync
+ * @start:		offset in bytes of the beginning of data range to sync
+ * @end:		offset in bytes of the end of data range (inclusive)
+ * @datasync:		perform only datasync
+ *
+ * Write back data in range @start..@end and metadata for @file to disk.  If
+ * @datasync is set only metadata needed to access modified file data is
+ * written.
+ */
+int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync)
+{
+	if (!file->f_op->fsync)
+		return -EINVAL;
+	return file->f_op->fsync(file, start, end, datasync);
+}
+EXPORT_SYMBOL(vfs_fsync_range);
+
+/**
+ * vfs_fsync - perform a fsync or fdatasync on a file
+ * @file:		file to sync
+ * @datasync:		only perform a fdatasync operation
+ *
+ * Write back data and metadata for @file to disk.  If @datasync is
+ * set only metadata needed to access modified file data is written.
+ */
+int vfs_fsync(struct file *file, int datasync)
+{
+	return vfs_fsync_range(file, 0, LLONG_MAX, datasync);
+}
+EXPORT_SYMBOL(vfs_fsync);
+
+static int do_fsync(unsigned int fd, int datasync)
 {
-	struct file *file;
+	struct fd f = fdget(fd);
 	int ret = -EBADF;
 
-	file = fget(fd);
-	if (file) {
-		ret = do_fsync(file, datasync);
-		fput(file);
+	if (f.file) {
+		ret = vfs_fsync(f.file, datasync);
+		fdput(f);
 	}
 	return ret;
 }
 
-asmlinkage long sys_fsync(unsigned int fd)
+SYSCALL_DEFINE1(fsync, unsigned int, fd)
 {
-	return __do_fsync(fd, 0);
+	return do_fsync(fd, 0);
 }
 
-asmlinkage long sys_fdatasync(unsigned int fd)
+SYSCALL_DEFINE1(fdatasync, unsigned int, fd)
 {
-	return __do_fsync(fd, 1);
+	return do_fsync(fd, 1);
 }
 
 /*
@@ -139,7 +230,8 @@ asmlinkage long sys_fdatasync(unsigned int fd)
  * before performing the write.
  *
  * SYNC_FILE_RANGE_WRITE: initiate writeout of all those dirty pages in the
- * range which are not presently under writeback.
+ * range which are not presently under writeback. Note that this may block for
+ * significant periods due to exhaustion of disk request structures.
  *
  * SYNC_FILE_RANGE_WAIT_AFTER: wait upon writeout of all pages in the range
  * after performing the write.
@@ -174,13 +266,13 @@ asmlinkage long sys_fdatasync(unsigned int fd)
  * already-instantiated disk blocks, there are no guarantees here that the data
  * will be available after a crash.
  */
-asmlinkage long sys_sync_file_range(int fd, loff_t offset, loff_t nbytes,
-					unsigned int flags)
+SYSCALL_DEFINE4(sync_file_range, int, fd, loff_t, offset, loff_t, nbytes,
+				unsigned int, flags)
 {
 	int ret;
-	struct file *file;
+	struct fd f;
+	struct address_space *mapping;
 	loff_t endbyte;			/* inclusive */
-	int fput_needed;
 	umode_t i_mode;
 
 	ret = -EINVAL;
@@ -219,66 +311,48 @@ asmlinkage long sys_sync_file_range(int fd, loff_t offset, loff_t nbytes,
 		endbyte--;		/* inclusive */
 
 	ret = -EBADF;
-	file = fget_light(fd, &fput_needed);
-	if (!file)
+	f = fdget(fd);
+	if (!f.file)
 		goto out;
 
-	i_mode = file->f_path.dentry->d_inode->i_mode;
+	i_mode = file_inode(f.file)->i_mode;
 	ret = -ESPIPE;
 	if (!S_ISREG(i_mode) && !S_ISBLK(i_mode) && !S_ISDIR(i_mode) &&
 			!S_ISLNK(i_mode))
 		goto out_put;
 
-	ret = do_sync_mapping_range(file->f_mapping, offset, endbyte, flags);
-out_put:
-	fput_light(file, fput_needed);
-out:
-	return ret;
-}
-
-/* It would be nice if people remember that not all the world's an i386
-   when they introduce new system calls */
-asmlinkage long sys_sync_file_range2(int fd, unsigned int flags,
-				     loff_t offset, loff_t nbytes)
-{
-	return sys_sync_file_range(fd, offset, nbytes, flags);
-}
-
-/*
- * `endbyte' is inclusive
- */
-int do_sync_mapping_range(struct address_space *mapping, loff_t offset,
-			  loff_t endbyte, unsigned int flags)
-{
-	int ret;
-
+	mapping = f.file->f_mapping;
 	if (!mapping) {
 		ret = -EINVAL;
-		goto out;
+		goto out_put;
 	}
 
 	ret = 0;
 	if (flags & SYNC_FILE_RANGE_WAIT_BEFORE) {
-		ret = wait_on_page_writeback_range(mapping,
-					offset >> PAGE_CACHE_SHIFT,
-					endbyte >> PAGE_CACHE_SHIFT);
+		ret = filemap_fdatawait_range(mapping, offset, endbyte);
 		if (ret < 0)
-			goto out;
+			goto out_put;
 	}
 
 	if (flags & SYNC_FILE_RANGE_WRITE) {
-		ret = __filemap_fdatawrite_range(mapping, offset, endbyte,
-						WB_SYNC_NONE);
+		ret = filemap_fdatawrite_range(mapping, offset, endbyte);
 		if (ret < 0)
-			goto out;
+			goto out_put;
 	}
 
-	if (flags & SYNC_FILE_RANGE_WAIT_AFTER) {
-		ret = wait_on_page_writeback_range(mapping,
-					offset >> PAGE_CACHE_SHIFT,
-					endbyte >> PAGE_CACHE_SHIFT);
-	}
+	if (flags & SYNC_FILE_RANGE_WAIT_AFTER)
+		ret = filemap_fdatawait_range(mapping, offset, endbyte);
+
+out_put:
+	fdput(f);
 out:
 	return ret;
 }
-EXPORT_SYMBOL_GPL(do_sync_mapping_range);
+
+/* It would be nice if people remember that not all the world's an i386
+   when they introduce new system calls */
+SYSCALL_DEFINE4(sync_file_range2, int, fd, unsigned int, flags,
+				 loff_t, offset, loff_t, nbytes)
+{
+	return sys_sync_file_range(fd, offset, nbytes, flags);
+}