linux/mm/fadvise.c
Andrew Morton f79e2abb9b [PATCH] sys_sync_file_range()
Remove the recently-added LINUX_FADV_ASYNC_WRITE and LINUX_FADV_WRITE_WAIT
fadvise() additions, do it in a new sys_sync_file_range() syscall instead.
Reasons:

- It's more flexible.  Things which would require two or three syscalls with
  fadvise() can be done in a single syscall.

- Using fadvise() in this manner is something not covered by POSIX.

The patch wires up the syscall for x86.

The sycall is implemented in the new fs/sync.c.  The intention is that we can
move sys_fsync(), sys_fdatasync() and perhaps sys_sync() into there later.

Documentation for the syscall is in fs/sync.c.

A test app (sync_file_range.c) is in
http://www.zip.com.au/~akpm/linux/patches/stuff/ext3-tools.tar.gz.

The available-to-GPL-modules do_sync_file_range() is for knfsd: "A COMMIT can
say NFS_DATA_SYNC or NFS_FILE_SYNC.  I can skip the ->fsync call for
NFS_DATA_SYNC which is hopefully the more common."

Note: the `async' writeout mode SYNC_FILE_RANGE_WRITE will turn synchronous if
the queue is congested.  This is trivial to fix: add a new flag bit, set
wbc->nonblocking.  But I'm not sure that we want to expose implementation
details down to that level.

Note: it's notable that we can sync an fd which wasn't opened for writing.
Same with fsync() and fdatasync()).

Note: the code takes some care to handle attempts to sync file contents
outside the 16TB offset on 32-bit machines.  It makes such attempts appear to
succeed, for best 32-bit/64-bit compatibility.  Perhaps it should make such
requests fail...

Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Cc: Ulrich Drepper <drepper@redhat.com>
Cc: Neil Brown <neilb@cse.unsw.edu.au>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-31 12:18:54 -08:00

136 lines
3.1 KiB
C

/*
* mm/fadvise.c
*
* Copyright (C) 2002, Linus Torvalds
*
* 11Jan2003 akpm@digeo.com
* Initial version.
*/
#include <linux/kernel.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/backing-dev.h>
#include <linux/pagevec.h>
#include <linux/fadvise.h>
#include <linux/writeback.h>
#include <linux/syscalls.h>
#include <asm/unistd.h>
/*
* POSIX_FADV_WILLNEED could set PG_Referenced, and POSIX_FADV_NOREUSE could
* deactivate the pages and clear PG_Referenced.
*
* LINUX_FADV_ASYNC_WRITE: start async writeout of any dirty pages between file
* offsets `offset' and `offset+len' inclusive. Any pages which are currently
* under writeout are skipped, whether or not they are dirty.
*
* LINUX_FADV_WRITE_WAIT: wait upon writeout of any dirty pages between file
* offsets `offset' and `offset+len'.
*
* By combining these two operations the application may do several things:
*
* LINUX_FADV_ASYNC_WRITE: push some or all of the dirty pages at the disk.
*
*/
asmlinkage long sys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
{
struct file *file = fget(fd);
struct address_space *mapping;
struct backing_dev_info *bdi;
loff_t endbyte; /* inclusive */
pgoff_t start_index;
pgoff_t end_index;
unsigned long nrpages;
int ret = 0;
if (!file)
return -EBADF;
if (S_ISFIFO(file->f_dentry->d_inode->i_mode)) {
ret = -ESPIPE;
goto out;
}
mapping = file->f_mapping;
if (!mapping || len < 0) {
ret = -EINVAL;
goto out;
}
if (mapping->a_ops->get_xip_page)
/* no bad return value, but ignore advice */
goto out;
/* Careful about overflows. Len == 0 means "as much as possible" */
endbyte = offset + len;
if (!len || endbyte < len)
endbyte = -1;
else
endbyte--; /* inclusive */
bdi = mapping->backing_dev_info;
switch (advice) {
case POSIX_FADV_NORMAL:
file->f_ra.ra_pages = bdi->ra_pages;
break;
case POSIX_FADV_RANDOM:
file->f_ra.ra_pages = 0;
break;
case POSIX_FADV_SEQUENTIAL:
file->f_ra.ra_pages = bdi->ra_pages * 2;
break;
case POSIX_FADV_WILLNEED:
case POSIX_FADV_NOREUSE:
if (!mapping->a_ops->readpage) {
ret = -EINVAL;
break;
}
/* First and last PARTIAL page! */
start_index = offset >> PAGE_CACHE_SHIFT;
end_index = endbyte >> PAGE_CACHE_SHIFT;
/* Careful about overflow on the "+1" */
nrpages = end_index - start_index + 1;
if (!nrpages)
nrpages = ~0UL;
ret = force_page_cache_readahead(mapping, file,
start_index,
max_sane_readahead(nrpages));
if (ret > 0)
ret = 0;
break;
case POSIX_FADV_DONTNEED:
if (!bdi_write_congested(mapping->backing_dev_info))
filemap_flush(mapping);
/* First and last FULL page! */
start_index = (offset+(PAGE_CACHE_SIZE-1)) >> PAGE_CACHE_SHIFT;
end_index = (endbyte >> PAGE_CACHE_SHIFT);
if (end_index >= start_index)
invalidate_mapping_pages(mapping, start_index,
end_index);
break;
default:
ret = -EINVAL;
}
out:
fput(file);
return ret;
}
#ifdef __ARCH_WANT_SYS_FADVISE64
asmlinkage long sys_fadvise64(int fd, loff_t offset, size_t len, int advice)
{
return sys_fadvise64_64(fd, offset, len, advice);
}
#endif