Re: [PATCH 15/15] parallel lookups: actual switch to rwsem

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On Apr 15, 2016, at 6:55 PM, Al Viro <viro@xxxxxxxxxxxxxxxxxx> wrote:
> 
> From: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
> 
> ta-da!
> 
> The main issue is the lack of down_write_killable(), so the places
> like readdir.c switched to plain inode_lock(); once killable
> variants of rwsem primitives appear, that'll be dealt with.
> 
> lockdep side also might need more work
> 
> Signed-off-by: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
> ---
> fs/btrfs/ioctl.c       | 16 ++++++++++------
> fs/configfs/inode.c    |  2 +-
> fs/dcache.c            |  9 +++++----
> fs/gfs2/ops_fstype.c   |  2 +-
> fs/inode.c             | 12 ++++++------
> fs/namei.c             |  4 ++--
> fs/ocfs2/inode.c       |  2 +-
> fs/overlayfs/readdir.c |  4 +++-
> fs/readdir.c           |  7 ++++---
> include/linux/fs.h     | 12 ++++++------
> 10 files changed, 39 insertions(+), 31 deletions(-)
> 
> diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
> index 053e677..db1e830 100644
> --- a/fs/btrfs/ioctl.c
> +++ b/fs/btrfs/ioctl.c
> @@ -837,9 +837,11 @@ static noinline int btrfs_mksubvol(struct path *parent,
> 	struct dentry *dentry;
> 	int error;
> 
> -	error = mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT);
> -	if (error == -EINTR)
> -		return error;
> +	inode_lock_nested(dir, I_MUTEX_PARENT);
> +	// XXX: should've been
> +	// mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT);
> +	// if (error == -EINTR)
> +	//	return error;
> 
> 	dentry = lookup_one_len(name, parent->dentry, namelen);
> 	error = PTR_ERR(dentry);
> @@ -2366,9 +2368,11 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
> 		goto out;
> 
> 
> -	err = mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT);
> -	if (err == -EINTR)
> -		goto out_drop_write;
> +	inode_lock_nested(dir, I_MUTEX_PARENT);
> +	// XXX: should've been
> +	// err = mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT);
> +	// if (err == -EINTR)
> +	//	goto out_drop_write;
> 	dentry = lookup_one_len(vol_args->name, parent, namelen);
> 	if (IS_ERR(dentry)) {
> 		err = PTR_ERR(dentry);
> diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
> index 03d124a..0387968 100644
> --- a/fs/configfs/inode.c
> +++ b/fs/configfs/inode.c
> @@ -156,7 +156,7 @@ static void configfs_set_inode_lock_class(struct configfs_dirent *sd,
> 
> 	if (depth > 0) {
> 		if (depth <= ARRAY_SIZE(default_group_class)) {
> -			lockdep_set_class(&inode->i_mutex,
> +			lockdep_set_class(&inode->i_rwsem,
> 					  &default_group_class[depth - 1]);
> 		} else {
> 			/*
> diff --git a/fs/dcache.c b/fs/dcache.c
> index 5965588..d110040 100644
> --- a/fs/dcache.c
> +++ b/fs/dcache.c
> @@ -2911,7 +2911,8 @@ struct dentry *d_ancestor(struct dentry *p1, struct dentry *p2)
> static int __d_unalias(struct inode *inode,
> 		struct dentry *dentry, struct dentry *alias)
> {
> -	struct mutex *m1 = NULL, *m2 = NULL;
> +	struct mutex *m1 = NULL;
> +	struct rw_semaphore *m2 = NULL;
> 	int ret = -ESTALE;
> 
> 	/* If alias and dentry share a parent, then no extra locks required */
> @@ -2922,15 +2923,15 @@ static int __d_unalias(struct inode *inode,
> 	if (!mutex_trylock(&dentry->d_sb->s_vfs_rename_mutex))
> 		goto out_err;
> 	m1 = &dentry->d_sb->s_vfs_rename_mutex;
> -	if (!inode_trylock(alias->d_parent->d_inode))
> +	if (!down_read_trylock(&alias->d_parent->d_inode->i_rwsem))
> 		goto out_err;
> -	m2 = &alias->d_parent->d_inode->i_mutex;
> +	m2 = &alias->d_parent->d_inode->i_rwsem;
> out_unalias:
> 	__d_move(alias, dentry, false);
> 	ret = 0;
> out_err:
> 	if (m2)
> -		mutex_unlock(m2);
> +		up_read(m2);
> 	if (m1)
> 		mutex_unlock(m1);
> 	return ret;
> diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
> index c09c63d..4546360 100644
> --- a/fs/gfs2/ops_fstype.c
> +++ b/fs/gfs2/ops_fstype.c
> @@ -824,7 +824,7 @@ static int init_inodes(struct gfs2_sbd *sdp, int undo)
> 	 * i_mutex on quota files is special. Since this inode is hidden system
> 	 * file, we are safe to define locking ourselves.
> 	 */
> -	lockdep_set_class(&sdp->sd_quota_inode->i_mutex,
> +	lockdep_set_class(&sdp->sd_quota_inode->i_rwsem,
> 			  &gfs2_quota_imutex_key);
> 
> 	error = gfs2_rindex_update(sdp);
> diff --git a/fs/inode.c b/fs/inode.c
> index 4b884f7..4ccbc21 100644
> --- a/fs/inode.c
> +++ b/fs/inode.c
> @@ -166,8 +166,8 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
> 	spin_lock_init(&inode->i_lock);
> 	lockdep_set_class(&inode->i_lock, &sb->s_type->i_lock_key);
> 
> -	mutex_init(&inode->i_mutex);
> -	lockdep_set_class(&inode->i_mutex, &sb->s_type->i_mutex_key);
> +	init_rwsem(&inode->i_rwsem);
> +	lockdep_set_class(&inode->i_rwsem, &sb->s_type->i_mutex_key);
> 
> 	atomic_set(&inode->i_dio_count, 0);
> 
> @@ -925,13 +925,13 @@ void lockdep_annotate_inode_mutex_key(struct inode *inode)
> 		struct file_system_type *type = inode->i_sb->s_type;
> 
> 		/* Set new key only if filesystem hasn't already changed it */
> -		if (lockdep_match_class(&inode->i_mutex, &type->i_mutex_key)) {
> +		if (lockdep_match_class(&inode->i_rwsem, &type->i_mutex_key)) {
> 			/*
> 			 * ensure nobody is actually holding i_mutex
> 			 */
> -			mutex_destroy(&inode->i_mutex);
> -			mutex_init(&inode->i_mutex);
> -			lockdep_set_class(&inode->i_mutex,
> +			// mutex_destroy(&inode->i_mutex);
> +			init_rwsem(&inode->i_rwsem);
> +			lockdep_set_class(&inode->i_rwsem,
> 					  &type->i_mutex_dir_key);
> 		}
> 	}
> diff --git a/fs/namei.c b/fs/namei.c
> index eb879d6..877e9ef 100644
> --- a/fs/namei.c
> +++ b/fs/namei.c
> @@ -1607,7 +1607,7 @@ static struct dentry *lookup_slow(const struct qstr *name,
> 	struct inode *inode = dir->d_inode;
> 	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
> 
> -	inode_lock(inode);
> +	down_read(&inode->i_rwsem);

Wouldn't it make sense to have helpers like "inode_read_lock(inode)" or similar,
so that it is consistent with other parts of the code and easier to find?
It's a bit strange to have the filesystems use "inode_lock()" and some places
here use "inode_lock_nested()", but other places use up_read() and down_read()
directly on &inode->i_rwsem.  That would also simplify delegating the directory
locking to the filesystems in the future.

Cheers, Andreas

> 	/* Don't go there if it's already dead */
> 	if (unlikely(IS_DEADDIR(inode)))
> 		goto out;
> @@ -1638,7 +1638,7 @@ again:
> 		}
> 	}
> out:
> -	inode_unlock(inode);
> +	up_read(&inode->i_rwsem);
> 	return dentry;
> }
> 
> diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
> index 12f4a9e..0748777 100644
> --- a/fs/ocfs2/inode.c
> +++ b/fs/ocfs2/inode.c
> @@ -262,7 +262,7 @@ static int ocfs2_init_locked_inode(struct inode *inode, void *opaque)
> 	inode->i_ino = args->fi_ino;
> 	OCFS2_I(inode)->ip_blkno = args->fi_blkno;
> 	if (args->fi_sysfile_type != 0)
> -		lockdep_set_class(&inode->i_mutex,
> +		lockdep_set_class(&inode->i_rwsem,
> 			&ocfs2_sysfile_lock_key[args->fi_sysfile_type]);
> 	if (args->fi_sysfile_type == USER_QUOTA_SYSTEM_INODE ||
> 	    args->fi_sysfile_type == GROUP_QUOTA_SYSTEM_INODE ||
> diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
> index 6ec1e43..da186ee 100644
> --- a/fs/overlayfs/readdir.c
> +++ b/fs/overlayfs/readdir.c
> @@ -218,7 +218,9 @@ static int ovl_check_whiteouts(struct dentry *dir, struct ovl_readdir_data *rdd)
> 	cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE);
> 	old_cred = override_creds(override_cred);
> 
> -	err = mutex_lock_killable(&dir->d_inode->i_mutex);
> +	inode_lock(dir->d_inode);
> +	err = 0;
> +	// XXX: err = mutex_lock_killable(&dir->d_inode->i_mutex);
> 	if (!err) {
> 		while (rdd->first_maybe_whiteout) {
> 			p = rdd->first_maybe_whiteout;
> diff --git a/fs/readdir.c b/fs/readdir.c
> index e69ef3b..bf583e8 100644
> --- a/fs/readdir.c
> +++ b/fs/readdir.c
> @@ -32,9 +32,10 @@ int iterate_dir(struct file *file, struct dir_context *ctx)
> 	if (res)
> 		goto out;
> 
> -	res = mutex_lock_killable(&inode->i_mutex);
> -	if (res)
> -		goto out;
> +	inode_lock(inode);
> +	// res = mutex_lock_killable(&inode->i_mutex);
> +	// if (res)
> +	//	goto out;
> 
> 	res = -ENOENT;
> 	if (!IS_DEADDIR(inode)) {
> diff --git a/include/linux/fs.h b/include/linux/fs.h
> index 0a32045..313ad28 100644
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -647,7 +647,7 @@ struct inode {
> 
> 	/* Misc */
> 	unsigned long		i_state;
> -	struct mutex		i_mutex;
> +	struct rw_semaphore	i_rwsem;
> 
> 	unsigned long		dirtied_when;	/* jiffies of first dirtying */
> 	unsigned long		dirtied_time_when;
> @@ -734,27 +734,27 @@ enum inode_i_mutex_lock_class
> 
> static inline void inode_lock(struct inode *inode)
> {
> -	mutex_lock(&inode->i_mutex);
> +	down_write(&inode->i_rwsem);
> }
> 
> static inline void inode_unlock(struct inode *inode)
> {
> -	mutex_unlock(&inode->i_mutex);
> +	up_write(&inode->i_rwsem);
> }
> 
> static inline int inode_trylock(struct inode *inode)
> {
> -	return mutex_trylock(&inode->i_mutex);
> +	return down_write_trylock(&inode->i_rwsem);
> }
> 
> static inline int inode_is_locked(struct inode *inode)
> {
> -	return mutex_is_locked(&inode->i_mutex);
> +	return rwsem_is_locked(&inode->i_rwsem);
> }
> 
> static inline void inode_lock_nested(struct inode *inode, unsigned subclass)
> {
> -	mutex_lock_nested(&inode->i_mutex, subclass);
> +	down_write_nested(&inode->i_rwsem, subclass);
> }
> 
> void lock_two_nondirectories(struct inode *, struct inode*);
> --
> 2.8.0.rc3
> 
> --
> To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
> the body of a message to majordomo@xxxxxxxxxxxxxxx
> More majordomo info at  http://vger.kernel.org/majordomo-info.html


Cheers, Andreas





Attachment: signature.asc
Description: Message signed with OpenPGP using GPGMail


[Index of Archives]     [Linux Ext4 Filesystem]     [Union Filesystem]     [Filesystem Testing]     [Ceph Users]     [Ecryptfs]     [AutoFS]     [Kernel Newbies]     [Share Photos]     [Security]     [Netfilter]     [Bugtraq]     [Yosemite News]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux Cachefs]     [Reiser Filesystem]     [Linux RAID]     [Samba]     [Device Mapper]     [CEPH Development]
  Powered by Linux