/* * 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)
{ int ret = 0;
/* * 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_rdonly(sb)) return 0;
/* * Do the filesystem syncing work. For simple filesystems * writeback_inodes_sb(sb) just dirties buffers with inodes so we have * to submit I/O for these buffers via sync_blockdev(). This also * speeds up the wait == 1 case since in that case write_inode() * methods call sync_dirty_buffer() and thus effectively write one block * at a time.
*/
writeback_inodes_sb(sb, WB_REASON_SYNC); if (sb->s_op->sync_fs) {
ret = sb->s_op->sync_fs(sb, 0); if (ret) return ret;
}
ret = sync_blockdev_nowait(sb->s_bdev); if (ret) return ret;
sync_inodes_sb(sb); if (sb->s_op->sync_fs) {
ret = sb->s_op->sync_fs(sb, 1); if (ret) return ret;
} return sync_blockdev(sb->s_bdev);
}
EXPORT_SYMBOL(sync_filesystem);
/* * 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)
{ int nowait = 0, wait = 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)
{ struct inode *inode = file->f_mapping->host;
if (!file->f_op->fsync) return -EINVAL; if (!datasync && (inode->i_state & I_DIRTY_TIME))
mark_inode_dirty_sync(inode); 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);
staticint do_fsync(unsignedint fd, int datasync)
{ CLASS(fd, f)(fd);
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_SHIFT)) { /* * The range starts outside a 32 bit machine's * pagecache addressing capabilities. Let it "succeed"
*/
ret = 0; goto out;
} if (endbyte >= (0x100000000ULL << PAGE_SHIFT)) { /* * Out to EOF
*/
nbytes = 0;
}
}
i_mode = file_inode(file)->i_mode;
ret = -ESPIPE; if (!S_ISREG(i_mode) && !S_ISBLK(i_mode) && !S_ISDIR(i_mode) &&
!S_ISLNK(i_mode)) goto out;
mapping = file->f_mapping;
ret = 0; if (flags & SYNC_FILE_RANGE_WAIT_BEFORE) {
ret = file_fdatawait_range(file, offset, endbyte); if (ret < 0) goto out;
}
if (flags & SYNC_FILE_RANGE_WRITE) { int sync_mode = WB_SYNC_NONE;
if ((flags & SYNC_FILE_RANGE_WRITE_AND_WAIT) ==
SYNC_FILE_RANGE_WRITE_AND_WAIT)
sync_mode = WB_SYNC_ALL;
ret = __filemap_fdatawrite_range(mapping, offset, endbyte,
sync_mode); if (ret < 0) goto out;
}
if (flags & SYNC_FILE_RANGE_WAIT_AFTER)
ret = file_fdatawait_range(file, offset, endbyte);
out: return ret;
}
/* * 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, unsignedint flags)
{ CLASS(fd, f)(fd);
/* 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, unsignedint, flags,
loff_t, offset, loff_t, nbytes)
{ return ksys_sync_file_range(fd, offset, nbytes, flags);
}
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.