/**
* 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)
{
struct address_space *mapping = file->f_mapping;
int err, ret;
#ifdef CONFIG_FSYNC_CONTROL
if (!fsynccontrol_fsync_enabled())
return 0;
#endif
if (!file->f_op || !file->f_op->fsync) {
ret = -EINVAL;
goto out;
}
ret = filemap_write_and_wait_range(mapping, start, end);
/*
* 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, datasync);
if (!ret)
ret = err;
mutex_unlock(&mapping->host->i_mutex);
out:
return ret;
}
/*
* sync a single super
*/
SYSCALL_DEFINE1(syncfs, int, fd)
{
struct file *file;
struct super_block *sb;
int ret;
int fput_needed;
#ifdef CONFIG_FSYNC_CONTROL
if (!fsynccontrol_fsync_enabled())
return 0;
#endif
file = fget_light(fd, &fput_needed);
if (!file)
return -EBADF;
sb = file->f_dentry->d_sb;
down_read(&sb->s_umount);
ret = sync_filesystem(sb);
up_read(&sb->s_umount);
fput_light(file, fput_needed);
return ret;
}
SYSCALL_DEFINE1(fdatasync, unsigned int, fd)
{
#ifdef CONFIG_FSYNC_CONTROL
if (!fsynccontrol_fsync_enabled())
return 0;
#endif
return do_fsync(fd, 1);
}
/**
* 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)
{
#ifdef CONFIG_FSYNC_CONTROL
if (!fsynccontrol_fsync_enabled())
return 0;
#endif
return vfs_fsync_range(file, 0, LLONG_MAX, datasync);
}
/**
* generic_write_sync - perform syncing after a write if file / inode is sync
* @file: file to which the write happened
* @pos: offset where the write started
* @count: length of the write
*
* This is just a simple wrapper about our general syncing function.
*/
int generic_write_sync(struct file *file, loff_t pos, loff_t count)
{
#ifdef CONFIG_FSYNC_CONTROL
if (!fsynccontrol_fsync_enabled())
return 0;
#endif
if (!(file->f_flags & O_DSYNC) && !IS_SYNC(file->f_mapping->host))
return 0;
return vfs_fsync_range(file, pos, pos + count - 1,
(file->f_flags & __O_SYNC) ? 0 : 1);
}
/**
* 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)
{
#ifdef CONFIG_FSYNC_CONTROL
if(!fsynccontrol_fsync_enabled())
return 0;
#endif
if (!file->f_op || !file->f_op->fsync)
return -EINVAL;
return file->f_op->fsync(file, start, end, datasync);
}
SYSCALL_DEFINE1(fdatasync, unsigned int, fd)
{
#ifdef CONFIG_DYNAMIC_FSYNC
if (!early_suspend_active)
return 0;
else
#endif
#ifdef CONFIG_FSYNC_CONTROL
if (!fsynccontrol_fsync_enabled())
return 0;
#endif
return do_fsync(fd, 1);
}
static int do_fsync(unsigned int fd, int datasync)
{
struct file *file;
int ret = -EBADF;
#ifdef CONFIG_FSYNC_CONTROL
if (!fsynccontrol_fsync_enabled())
return 0;
#endif
file = fget(fd);
if (file) {
ret = vfs_fsync(file, datasync);
fput(file);
}
return ret;
}
/*
* sys_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 sys_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 sys_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 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
* sys_sync_file_range() are committed to disk.
*
*
* 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.
*/
SYSCALL_DEFINE(sync_file_range)(int fd, loff_t offset, loff_t nbytes,
unsigned int flags)
{
int ret;
struct file *file;
struct address_space *mapping;
loff_t endbyte; /* inclusive */
int fput_needed;
umode_t i_mode;
#ifdef CONFIG_FSYNC_CONTROL
if (!fsynccontrol_fsync_enabled())
return 0;
#endif
ret = -EINVAL;
if (flags & ~VALID_FLAGS)
goto out;
endbyte = offset + nbytes;
if ((s64)offset < 0)
goto out;
if ((s64)endbyte < 0)
goto out;
if (endbyte < offset)
goto out;
if (sizeof(pgoff_t) == 4) {
if (offset >= (0x100000000ULL << PAGE_CACHE_SHIFT)) {
/*
* The range starts outside a 32 bit machine's
* pagecache addressing capabilities. Let it "succeed"
*/
ret = 0;
goto out;
}
if (endbyte >= (0x100000000ULL << PAGE_CACHE_SHIFT)) {
/*
* Out to EOF
*/
nbytes = 0;
}
}
if (nbytes == 0)
endbyte = LLONG_MAX;
else
endbyte--; /* inclusive */
ret = -EBADF;
file = fget_light(fd, &fput_needed);
if (!file)
goto out;
i_mode = file->f_path.dentry->d_inode->i_mode;
ret = -ESPIPE;
if (!S_ISREG(i_mode) && !S_ISBLK(i_mode) && !S_ISDIR(i_mode) &&
!S_ISLNK(i_mode))
goto out_put;
mapping = file->f_mapping;
if (!mapping) {
ret = -EINVAL;
goto out_put;
}
ret = 0;
if (flags & SYNC_FILE_RANGE_WAIT_BEFORE) {
ret = filemap_fdatawait_range(mapping, offset, endbyte);
if (ret < 0)
goto out_put;
}
if (flags & SYNC_FILE_RANGE_WRITE) {
ret = filemap_fdatawrite_range(mapping, offset, endbyte);
if (ret < 0)
goto out_put;
}
if (flags & SYNC_FILE_RANGE_WAIT_AFTER)
ret = filemap_fdatawait_range(mapping, offset, endbyte);
out_put:
fput_light(file, fput_needed);
out:
return ret;
}
