4c728ef583
Fsync currently has a fdatawrite/fdatawait pair around the method call, and a mutex_lock/unlock of the inode mutex. All callers of fsync have to duplicate this, but we have a few and most of them don't quite get it right. This patch adds a new vfs_fsync that takes care of this. It's a little more complicated as usual as ->fsync might get a NULL file pointer and just a dentry from nfsd, but otherwise gets afile and we want to take the mapping and file operations from it when it is there. Notes on the fsync callers: - ecryptfs wasn't calling filemap_fdatawrite / filemap_fdatawait on the lower file - coda wasn't calling filemap_fdatawrite / filemap_fdatawait on the host file, and returning 0 when ->fsync was missing - shm wasn't calling either filemap_fdatawrite / filemap_fdatawait nor taking i_mutex. Now given that shared memory doesn't have disk backing not doing anything in fsync seems fine and I left it out of the vfs_fsync conversion for now, but in that case we might just not pass it through to the lower file at all but just call the no-op simple_sync_file directly. [and now actually export vfs_fsync] Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
103 lines
2.4 KiB
C
103 lines
2.4 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.
|
|
*/
|
|
asmlinkage long sys_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;
|
|
|
|
/* 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;
|
|
start = vma->vm_end;
|
|
if ((flags & MS_SYNC) && file &&
|
|
(vma->vm_flags & VM_SHARED)) {
|
|
get_file(file);
|
|
up_read(&mm->mmap_sem);
|
|
error = vfs_fsync(file, file->f_path.dentry, 0);
|
|
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;
|
|
}
|