linux/fs/sync.c

// SPDX-License-Identifier: GPL-2.0
/*
 * High-level sync()-related operations
 */

#include <linux/blkdev.h>
#include <linux/kernel.h>
#include <linux/file.h>
#include <linux/fs.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/backing-dev.h>
#include "internal.h"

#define VALID_FLAGS …

/*
 * 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)
{ … }
EXPORT_SYMBOL(…);

static void sync_inodes_one_sb(struct super_block *sb, void *arg)
{ … }

static void sync_fs_one_sb(struct super_block *sb, void *arg)
{ … }

/*
 * 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().
 */
void ksys_sync(void)
{ … }

SYSCALL_DEFINE0(…)
{ …

static void do_sync_work(struct work_struct *work)
{ … }

void emergency_sync(void)
{ … }

/*
 * sync a single super
 */
SYSCALL_DEFINE1(syncfs, int, fd)
{ … }

/**
 * 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)
{ … }
EXPORT_SYMBOL(…);

/**
 * 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)
{ … }
EXPORT_SYMBOL(…);

static int do_fsync(unsigned int fd, int datasync)
{ … }

SYSCALL_DEFINE1(fsync, unsigned int, fd)
{ … }

SYSCALL_DEFINE1(fdatasync, unsigned int, fd)
{ … }

int sync_file_range(struct file *file, loff_t offset, loff_t nbytes,
		    unsigned int flags)
{ … }

/*
 * ksys_sync_file_range() permits finely controlled syncing over a segment of
 * a file in the range offset .. (offset+nbytes-1) inclusive.  If nbytes is
 * zero then ksys_sync_file_range() will operate from offset out to EOF.
 *
 * The flag bits are:
 *
 * SYNC_FILE_RANGE_WAIT_BEFORE: wait upon writeout of all pages in the range
 * before performing the write.
 *
 * SYNC_FILE_RANGE_WRITE: initiate writeout of all those dirty pages in the
 * 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.
 *
 * Useful combinations of the flag bits are:
 *
 * SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE: ensures that all pages
 * in the range which were dirty on entry to ksys_sync_file_range() are placed
 * under writeout.  This is a start-write-for-data-integrity operation.
 *
 * SYNC_FILE_RANGE_WRITE: start writeout of all dirty pages in the range which
 * are not presently under writeout.  This is an asynchronous flush-to-disk
 * operation.  Not suitable for data integrity operations.
 *
 * SYNC_FILE_RANGE_WAIT_BEFORE (or SYNC_FILE_RANGE_WAIT_AFTER): wait for
 * completion of writeout of all pages in the range.  This will be used after an
 * earlier SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE operation to wait
 * for that operation to complete and to return the result.
 *
 * SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE|SYNC_FILE_RANGE_WAIT_AFTER
 * (a.k.a. SYNC_FILE_RANGE_WRITE_AND_WAIT):
 * a traditional sync() operation.  This is a write-for-data-integrity operation
 * which will ensure that all pages in the range which were dirty on entry to
 * ksys_sync_file_range() are written to disk.  It should be noted that disk
 * caches are not flushed by this call, so there are no guarantees here that the
 * data will be available on disk after a crash.
 *
 *
 * SYNC_FILE_RANGE_WAIT_BEFORE and SYNC_FILE_RANGE_WAIT_AFTER will detect any
 * I/O errors or ENOSPC conditions and will return those to the caller, after
 * clearing the EIO and ENOSPC flags in the address_space.
 *
 * It should be noted that none of these operations write out the file's
 * metadata.  So unless the application is strictly performing overwrites of
 * already-instantiated disk blocks, there are no guarantees here that the data
 * will be available after a crash.
 */
int ksys_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)
{ … }

#if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_SYNC_FILE_RANGE)
COMPAT_SYSCALL_DEFINE6(sync_file_range, int, fd, compat_arg_u64_dual(offset),
		       compat_arg_u64_dual(nbytes), unsigned int, flags)
{
	return ksys_sync_file_range(fd, compat_arg_u64_glue(offset),
				    compat_arg_u64_glue(nbytes), flags);
}
#endif

/* 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)
{ … }