kernel-ark/mm/msync.c
Matthew Wilcox 7fc34a62ca mm/msync.c: sync only the requested range in msync()
msync() currently syncs more than POSIX requires or BSD or Solaris
implement.  It is supposed to be equivalent to fdatasync(), not fsync(),
and it is only supposed to sync the portion of the file that overlaps the
range passed to msync.

If the VMA is non-linear, fall back to syncing the entire file, but we
still optimise to only fdatasync() the entire file, not the full fsync().

akpm: there are obvious concerns with bck-compatibility: is anyone relying
on the undocumented side-effect for their data integrity?  And how would
they ever know if this change broke their data integrity?

We think the risk is reasonably low, and this patch brings the kernel into
line with other OS's and with what the manpage has always said...

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Jeff Moyer <jmoyer@redhat.com>
Cc: Chris Mason <clm@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 16:54:11 -07:00

110 lines
2.6 KiB
C

/*
* linux/mm/msync.c
*
* Copyright (C) 1994-1999 Linus Torvalds
*/
/*
* The msync() system call.
*/
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/file.h>
#include <linux/syscalls.h>
#include <linux/sched.h>
/*
* MS_SYNC syncs the entire file - including mappings.
*
* MS_ASYNC does not start I/O (it used to, up to 2.5.67).
* Nor does it marks the relevant pages dirty (it used to up to 2.6.17).
* Now it doesn't do anything, since dirty pages are properly tracked.
*
* The application may now run fsync() to
* write out the dirty pages and wait on the writeout and check the result.
* Or the application may run fadvise(FADV_DONTNEED) against the fd to start
* async writeout immediately.
* So by _not_ starting I/O in MS_ASYNC we provide complete flexibility to
* applications.
*/
SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags)
{
unsigned long end;
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
int unmapped_error = 0;
int error = -EINVAL;
if (flags & ~(MS_ASYNC | MS_INVALIDATE | MS_SYNC))
goto out;
if (start & ~PAGE_MASK)
goto out;
if ((flags & MS_ASYNC) && (flags & MS_SYNC))
goto out;
error = -ENOMEM;
len = (len + ~PAGE_MASK) & PAGE_MASK;
end = start + len;
if (end < start)
goto out;
error = 0;
if (end == start)
goto out;
/*
* If the interval [start,end) covers some unmapped address ranges,
* just ignore them, but return -ENOMEM at the end.
*/
down_read(&mm->mmap_sem);
vma = find_vma(mm, start);
for (;;) {
struct file *file;
loff_t fstart, fend;
/* Still start < end. */
error = -ENOMEM;
if (!vma)
goto out_unlock;
/* Here start < vma->vm_end. */
if (start < vma->vm_start) {
start = vma->vm_start;
if (start >= end)
goto out_unlock;
unmapped_error = -ENOMEM;
}
/* Here vma->vm_start <= start < vma->vm_end. */
if ((flags & MS_INVALIDATE) &&
(vma->vm_flags & VM_LOCKED)) {
error = -EBUSY;
goto out_unlock;
}
file = vma->vm_file;
fstart = start + ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
fend = fstart + (min(end, vma->vm_end) - start) - 1;
start = vma->vm_end;
if ((flags & MS_SYNC) && file &&
(vma->vm_flags & VM_SHARED)) {
get_file(file);
up_read(&mm->mmap_sem);
if (vma->vm_flags & VM_NONLINEAR)
error = vfs_fsync(file, 1);
else
error = vfs_fsync_range(file, fstart, fend, 1);
fput(file);
if (error || start >= end)
goto out;
down_read(&mm->mmap_sem);
vma = find_vma(mm, start);
} else {
if (start >= end) {
error = 0;
goto out_unlock;
}
vma = vma->vm_next;
}
}
out_unlock:
up_read(&mm->mmap_sem);
out:
return error ? : unmapped_error;
}