Commit 96029c4e authored by npiggin@suse.de's avatar npiggin@suse.de Committed by Al Viro
Browse files

fs: introduce mnt_clone_write 



This patch speeds up lmbench lat_mmap test by about another 2% after the
first patch.

Before:
 avg = 462.286
 std = 5.46106

After:
 avg = 453.12
 std = 9.58257

(50 runs of each, stddev gives a reasonable confidence)

It does this by introducing mnt_clone_write, which avoids some heavyweight
operations of mnt_want_write if called on a vfsmount which we know already
has a write count; and mnt_want_write_file, which can call mnt_clone_write
if the file is open for write.

After these two patches, mnt_want_write and mnt_drop_write go from 7% on
the profile down to 1.3% (including mnt_clone_write).

[AV: mnt_want_write_file() should take file alone and derive mnt from it;
not only all callers have that form, but that's the only mnt about which
we know that it's already held for write if file is opened for write]

Cc: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: default avatarNick Piggin <npiggin@suse.de>
Signed-off-by: default avatarAl Viro <viro@zeniv.linux.org.uk>
parent d3ef3d73

fs/file_table.c

+1 −1
Original line number Diff line number Diff line
@@ -214,7 +214,7 @@ int init_file(struct file *file, struct vfsmount *mnt, struct dentry *dentry, 
	 */

	if ((mode & FMODE_WRITE) && !special_file(dentry->d_inode->i_mode)) {

		file_take_write(file);

		error = mnt_want_write(mnt);

		error = mnt_clone_write(mnt);

		WARN_ON(error);

	}

	return error;

fs/inode.c

+1 −1
Original line number Diff line number Diff line
@@ -1422,7 +1422,7 @@ void file_update_time(struct file *file) 
	if (IS_NOCMTIME(inode))

		return;



	err = mnt_want_write(file->f_path.mnt);

	err = mnt_want_write_file(file);

	if (err)

		return;

fs/namespace.c

+40 −0
Original line number Diff line number Diff line
@@ -264,6 +264,46 @@ out: 
}

EXPORT_SYMBOL_GPL(mnt_want_write);



/**

 * mnt_clone_write - get write access to a mount

 * @mnt: the mount on which to take a write

 *

 * This is effectively like mnt_want_write, except

 * it must only be used to take an extra write reference

 * on a mountpoint that we already know has a write reference

 * on it. This allows some optimisation.

 *

 * After finished, mnt_drop_write must be called as usual to

 * drop the reference.

 */

int mnt_clone_write(struct vfsmount *mnt)

{

	/* superblock may be r/o */

	if (__mnt_is_readonly(mnt))

		return -EROFS;

	preempt_disable();

	inc_mnt_writers(mnt);

	preempt_enable();

	return 0;

}

EXPORT_SYMBOL_GPL(mnt_clone_write);



/**

 * mnt_want_write_file - get write access to a file's mount

 * @file: the file who's mount on which to take a write

 *

 * This is like mnt_want_write, but it takes a file and can

 * do some optimisations if the file is open for write already

 */

int mnt_want_write_file(struct file *file)

{

	if (!(file->f_mode & FMODE_WRITE))

		return mnt_want_write(file->f_path.mnt);

	else

		return mnt_clone_write(file->f_path.mnt);

}

EXPORT_SYMBOL_GPL(mnt_want_write_file);



/**

 * mnt_drop_write - give up write access to a mount

 * @mnt: the mount on which to give up write access

fs/open.c

+2 −2
Original line number Diff line number Diff line
@@ -612,7 +612,7 @@ SYSCALL_DEFINE2(fchmod, unsigned int, fd, mode_t, mode) 


	audit_inode(NULL, dentry);



	err = mnt_want_write(file->f_path.mnt);

	err = mnt_want_write_file(file);

	if (err)

		goto out_putf;

	mutex_lock(&inode->i_mutex);
@@ -761,7 +761,7 @@ SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group) 
	if (!file)

		goto out;



	error = mnt_want_write(file->f_path.mnt);

	error = mnt_want_write_file(file);

	if (error)

		goto out_fput;

	dentry = file->f_path.dentry;

fs/xattr.c

+2 −2
Original line number Diff line number Diff line
@@ -297,7 +297,7 @@ SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name, 
		return error;

	dentry = f->f_path.dentry;

	audit_inode(NULL, dentry);

	error = mnt_want_write(f->f_path.mnt);

	error = mnt_want_write_file(f);

	if (!error) {

		error = setxattr(dentry, name, value, size, flags);

		mnt_drop_write(f->f_path.mnt);
@@ -524,7 +524,7 @@ SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name) 
		return error;

	dentry = f->f_path.dentry;

	audit_inode(NULL, dentry);

	error = mnt_want_write(f->f_path.mnt);

	error = mnt_want_write_file(f);

	if (!error) {

		error = removexattr(dentry, name);

		mnt_drop_write(f->f_path.mnt);

CRA Git | Maintained and supported by SUSTech CRA and CCSE