linux/fs/sync.c
Al Viro c2bd6c11cd switch do_fsync() to fget_light()
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-05-29 23:28:29 -04:00

383 lines
9.9 KiB
C

/*
* High-level sync()-related operations
*/
#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 (SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE| \
SYNC_FILE_RANGE_WAIT_AFTER)
/*
* 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 int __sync_filesystem(struct super_block *sb, int wait)
{
/*
* This should be safe, as we require bdi backing to actually
* write out data in the first place
*/
if (sb->s_bdi == &noop_backing_dev_info)
return 0;
if (sb->s_qcop && sb->s_qcop->quota_sync)
sb->s_qcop->quota_sync(sb, -1, wait);
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);
}
/*
* 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;
/*
* 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);
static void sync_one_sb(struct super_block *sb, void *arg)
{
if (!(sb->s_flags & MS_RDONLY))
__sync_filesystem(sb, *(int *)arg);
}
/*
* Sync all the data for all the filesystems (called by sys_sync() and
* emergency sync)
*/
static void sync_filesystems(int wait)
{
iterate_supers(sync_one_sb, &wait);
}
/*
* sync everything. Start out by waking pdflush, because that writes back
* all queues in parallel.
*/
SYSCALL_DEFINE0(sync)
{
wakeup_flusher_threads(0, WB_REASON_SYNC);
sync_filesystems(0);
sync_filesystems(1);
if (unlikely(laptop_mode))
laptop_sync_completion();
return 0;
}
static void do_sync_work(struct work_struct *work)
{
/*
* Sync twice to reduce the possibility we skipped some inodes / pages
* because they were temporarily locked
*/
sync_filesystems(0);
sync_filesystems(0);
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);
}
}
/*
* sync a single super
*/
SYSCALL_DEFINE1(syncfs, int, fd)
{
struct file *file;
struct super_block *sb;
int ret;
int fput_needed;
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;
}
/**
* 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 || !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;
int ret = -EBADF;
int fput_needed;
file = fget_light(fd, &fput_needed);
if (file) {
ret = vfs_fsync(file, datasync);
fput_light(file, fput_needed);
}
return ret;
}
SYSCALL_DEFINE1(fsync, unsigned int, fd)
{
return do_fsync(fd, 0);
}
SYSCALL_DEFINE1(fdatasync, unsigned int, fd)
{
return do_fsync(fd, 1);
}
/**
* 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)
{
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);
}
EXPORT_SYMBOL(generic_write_sync);
/*
* 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;
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;
}
#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
asmlinkage long SyS_sync_file_range(long fd, loff_t offset, loff_t nbytes,
long flags)
{
return SYSC_sync_file_range((int) fd, offset, nbytes,
(unsigned int) flags);
}
SYSCALL_ALIAS(sys_sync_file_range, SyS_sync_file_range);
#endif
/* It would be nice if people remember that not all the world's an i386
when they introduce new system calls */
SYSCALL_DEFINE(sync_file_range2)(int fd, unsigned int flags,
loff_t offset, loff_t nbytes)
{
return sys_sync_file_range(fd, offset, nbytes, flags);
}
#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
asmlinkage long SyS_sync_file_range2(long fd, long flags,
loff_t offset, loff_t nbytes)
{
return SYSC_sync_file_range2((int) fd, (unsigned int) flags,
offset, nbytes);
}
SYSCALL_ALIAS(sys_sync_file_range2, SyS_sync_file_range2);
#endif