2006-03-31 03:30:42 -07:00
|
|
|
/*
|
|
|
|
* High-level sync()-related operations
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/file.h>
|
|
|
|
#include <linux/fs.h>
|
|
|
|
#include <linux/module.h>
|
2006-10-18 11:55:46 -06:00
|
|
|
#include <linux/sched.h>
|
2006-03-31 03:30:42 -07:00
|
|
|
#include <linux/writeback.h>
|
|
|
|
#include <linux/syscalls.h>
|
|
|
|
#include <linux/linkage.h>
|
|
|
|
#include <linux/pagemap.h>
|
2006-08-29 12:05:54 -06:00
|
|
|
#include <linux/quotaops.h>
|
|
|
|
#include <linux/buffer_head.h>
|
2006-03-31 03:30:42 -07:00
|
|
|
|
|
|
|
#define VALID_FLAGS (SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE| \
|
|
|
|
SYNC_FILE_RANGE_WAIT_AFTER)
|
|
|
|
|
2006-08-29 12:05:54 -06:00
|
|
|
/*
|
|
|
|
* sync everything. Start out by waking pdflush, because that writes back
|
|
|
|
* all queues in parallel.
|
|
|
|
*/
|
|
|
|
static void do_sync(unsigned long 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();
|
|
|
|
}
|
|
|
|
|
|
|
|
asmlinkage long sys_sync(void)
|
|
|
|
{
|
|
|
|
do_sync(1);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
void emergency_sync(void)
|
|
|
|
{
|
|
|
|
pdflush_operation(do_sync, 0);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Generic function to fsync a file.
|
|
|
|
*
|
|
|
|
* filp may be NULL if called via the msync of a vma.
|
|
|
|
*/
|
|
|
|
int file_fsync(struct file *filp, struct dentry *dentry, int datasync)
|
|
|
|
{
|
|
|
|
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);
|
2008-04-29 01:59:42 -06:00
|
|
|
if (sb->s_dirt && sb->s_op->write_super)
|
2006-08-29 12:05:54 -06:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
|
|
|
long do_fsync(struct file *file, int datasync)
|
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
int err;
|
|
|
|
struct address_space *mapping = file->f_mapping;
|
|
|
|
|
|
|
|
if (!file->f_op || !file->f_op->fsync) {
|
|
|
|
/* Why? We can still call filemap_fdatawrite */
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
ret = filemap_fdatawrite(mapping);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We need to protect against concurrent writers, which could cause
|
|
|
|
* livelocks in fsync_buffers_list().
|
|
|
|
*/
|
|
|
|
mutex_lock(&mapping->host->i_mutex);
|
2006-12-08 03:36:35 -07:00
|
|
|
err = file->f_op->fsync(file, file->f_path.dentry, datasync);
|
2006-08-29 12:05:54 -06:00
|
|
|
if (!ret)
|
|
|
|
ret = err;
|
|
|
|
mutex_unlock(&mapping->host->i_mutex);
|
|
|
|
err = filemap_fdatawait(mapping);
|
|
|
|
if (!ret)
|
|
|
|
ret = err;
|
|
|
|
out:
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static long __do_fsync(unsigned int fd, int datasync)
|
|
|
|
{
|
|
|
|
struct file *file;
|
|
|
|
int ret = -EBADF;
|
|
|
|
|
|
|
|
file = fget(fd);
|
|
|
|
if (file) {
|
|
|
|
ret = do_fsync(file, datasync);
|
|
|
|
fput(file);
|
|
|
|
}
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
asmlinkage long sys_fsync(unsigned int fd)
|
|
|
|
{
|
|
|
|
return __do_fsync(fd, 0);
|
|
|
|
}
|
|
|
|
|
|
|
|
asmlinkage long sys_fdatasync(unsigned int fd)
|
|
|
|
{
|
|
|
|
return __do_fsync(fd, 1);
|
|
|
|
}
|
|
|
|
|
2006-03-31 03:30:42 -07:00
|
|
|
/*
|
|
|
|
* 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
|
2008-07-23 22:27:36 -06:00
|
|
|
* range which are not presently under writeback. Note that this may block for
|
|
|
|
* significant periods due to exhaustion of disk request structures.
|
2006-03-31 03:30:42 -07:00
|
|
|
*
|
|
|
|
* 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.
|
|
|
|
*/
|
|
|
|
asmlinkage long sys_sync_file_range(int fd, loff_t offset, loff_t nbytes,
|
2006-04-10 23:53:57 -06:00
|
|
|
unsigned int flags)
|
2006-03-31 03:30:42 -07:00
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
struct file *file;
|
|
|
|
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)
|
[PATCH] writeback: fix range handling
When a writeback_control's `start' and `end' fields are used to
indicate a one-byte-range starting at file offset zero, the required
values of .start=0,.end=0 mean that the ->writepages() implementation
has no way of telling that it is being asked to perform a range
request. Because we're currently overloading (start == 0 && end == 0)
to mean "this is not a write-a-range request".
To make all this sane, the patch changes range of writeback_control.
So caller does: If it is calling ->writepages() to write pages, it
sets range (range_start/end or range_cyclic) always.
And if range_cyclic is true, ->writepages() thinks the range is
cyclic, otherwise it just uses range_start and range_end.
This patch does,
- Add LLONG_MAX, LLONG_MIN, ULLONG_MAX to include/linux/kernel.h
-1 is usually ok for range_end (type is long long). But, if someone did,
range_end += val; range_end is "val - 1"
u64val = range_end >> bits; u64val is "~(0ULL)"
or something, they are wrong. So, this adds LLONG_MAX to avoid nasty
things, and uses LLONG_MAX for range_end.
- All callers of ->writepages() sets range_start/end or range_cyclic.
- Fix updates of ->writeback_index. It seems already bit strange.
If it starts at 0 and ended by check of nr_to_write, this last
index may reduce chance to scan end of file. So, this updates
->writeback_index only if range_cyclic is true or whole-file is
scanned.
Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Cc: Nathan Scott <nathans@sgi.com>
Cc: Anton Altaparmakov <aia21@cantab.net>
Cc: Steven French <sfrench@us.ibm.com>
Cc: "Vladimir V. Saveliev" <vs@namesys.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 03:03:26 -06:00
|
|
|
endbyte = LLONG_MAX;
|
2006-03-31 03:30:42 -07:00
|
|
|
else
|
|
|
|
endbyte--; /* inclusive */
|
|
|
|
|
|
|
|
ret = -EBADF;
|
|
|
|
file = fget_light(fd, &fput_needed);
|
|
|
|
if (!file)
|
|
|
|
goto out;
|
|
|
|
|
2006-12-08 03:36:35 -07:00
|
|
|
i_mode = file->f_path.dentry->d_inode->i_mode;
|
2006-03-31 03:30:42 -07:00
|
|
|
ret = -ESPIPE;
|
|
|
|
if (!S_ISREG(i_mode) && !S_ISBLK(i_mode) && !S_ISDIR(i_mode) &&
|
|
|
|
!S_ISLNK(i_mode))
|
|
|
|
goto out_put;
|
|
|
|
|
2007-05-08 01:27:10 -06:00
|
|
|
ret = do_sync_mapping_range(file->f_mapping, offset, endbyte, flags);
|
2006-03-31 03:30:42 -07:00
|
|
|
out_put:
|
|
|
|
fput_light(file, fput_needed);
|
|
|
|
out:
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
Introduce fixed sys_sync_file_range2() syscall, implement on PowerPC and ARM
Not all the world is an i386. Many architectures need 64-bit arguments to be
aligned in suitable pairs of registers, and the original
sys_sync_file_range(int, loff_t, loff_t, int) was therefore wasting an
argument register for padding after the first integer. Since we don't
normally have more than 6 arguments for system calls, that left no room for
the final argument on some architectures.
Fix this by introducing sys_sync_file_range2(int, int, loff_t, loff_t) which
all fits nicely. In fact, ARM already had that, but called it
sys_arm_sync_file_range. Move it to fs/sync.c and rename it, then implement
the needed compatibility routine. And stop the missing syscall check from
bitching about the absence of sys_sync_file_range() if we've implemented
sys_sync_file_range2() instead.
Tested on PPC32 and with 32-bit and 64-bit userspace on PPC64.
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Acked-by: Russell King <rmk+kernel@arm.linux.org.uk>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-06-27 15:10:09 -06:00
|
|
|
/* 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);
|
|
|
|
}
|
|
|
|
|
2006-03-31 03:30:42 -07:00
|
|
|
/*
|
|
|
|
* `endbyte' is inclusive
|
|
|
|
*/
|
2007-03-01 12:01:55 -07:00
|
|
|
int do_sync_mapping_range(struct address_space *mapping, loff_t offset,
|
|
|
|
loff_t endbyte, unsigned int flags)
|
2006-03-31 03:30:42 -07:00
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
if (!mapping) {
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
ret = 0;
|
|
|
|
if (flags & SYNC_FILE_RANGE_WAIT_BEFORE) {
|
|
|
|
ret = wait_on_page_writeback_range(mapping,
|
|
|
|
offset >> PAGE_CACHE_SHIFT,
|
|
|
|
endbyte >> PAGE_CACHE_SHIFT);
|
|
|
|
if (ret < 0)
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (flags & SYNC_FILE_RANGE_WRITE) {
|
|
|
|
ret = __filemap_fdatawrite_range(mapping, offset, endbyte,
|
|
|
|
WB_SYNC_NONE);
|
|
|
|
if (ret < 0)
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (flags & SYNC_FILE_RANGE_WAIT_AFTER) {
|
|
|
|
ret = wait_on_page_writeback_range(mapping,
|
|
|
|
offset >> PAGE_CACHE_SHIFT,
|
|
|
|
endbyte >> PAGE_CACHE_SHIFT);
|
|
|
|
}
|
|
|
|
out:
|
|
|
|
return ret;
|
|
|
|
}
|
2007-03-01 12:01:55 -07:00
|
|
|
EXPORT_SYMBOL_GPL(do_sync_mapping_range);
|