From 423e0ab086ad8b33626e45fa94ac7613146b7ffa Mon Sep 17 00:00:00 2001 From: Tim Chen Date: Tue, 19 Jul 2011 09:32:38 -0700 Subject: VFS : mount lock scalability for internal mounts For a number of file systems that don't have a mount point (e.g. sockfs and pipefs), they are not marked as long term. Therefore in mntput_no_expire, all locks in vfs_mount lock are taken instead of just local cpu's lock to aggregate reference counts when we release reference to file objects. In fact, only local lock need to have been taken to update ref counts as these file systems are in no danger of going away until we are ready to unregister them. The attached patch marks file systems using kern_mount without mount point as long term. The contentions of vfs_mount lock is now eliminated. Before un-registering such file system, kern_unmount should be called to remove the long term flag and make the mount point ready to be freed. Signed-off-by: Tim Chen Signed-off-by: Al Viro --- fs/pipe.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/pipe.c') diff --git a/fs/pipe.c b/fs/pipe.c index da42f7db50de..1b7f9af67ccf 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -1291,8 +1291,8 @@ static int __init init_pipe_fs(void) static void __exit exit_pipe_fs(void) { + kern_unmount(pipe_mnt); unregister_filesystem(&pipe_fs_type); - mntput(pipe_mnt); } fs_initcall(init_pipe_fs); -- cgit v1.2.3 From a209dfc7b0d94bd6fa94553c097836a2e6d0f0ba Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 26 Jul 2011 11:36:34 +0200 Subject: vfs: dont chain pipe/anon/socket on superblock s_inodes list Workloads using pipes and sockets hit inode_sb_list_lock contention. superblock s_inodes list is needed for quota, dirty, pagecache and fsnotify management. pipe/anon/socket fs are clearly not candidates for these. Signed-off-by: Eric Dumazet Reviewed-by: Christoph Hellwig Signed-off-by: Al Viro --- fs/anon_inodes.c | 2 +- fs/inode.c | 39 ++++++++++++++++++++++++++++++--------- fs/pipe.c | 2 +- include/linux/fs.h | 3 ++- net/socket.c | 2 +- 5 files changed, 35 insertions(+), 13 deletions(-) (limited to 'fs/pipe.c') diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c index 4d433d34736f..f11e43ed907d 100644 --- a/fs/anon_inodes.c +++ b/fs/anon_inodes.c @@ -187,7 +187,7 @@ EXPORT_SYMBOL_GPL(anon_inode_getfd); */ static struct inode *anon_inode_mkinode(void) { - struct inode *inode = new_inode(anon_inode_mnt->mnt_sb); + struct inode *inode = new_inode_pseudo(anon_inode_mnt->mnt_sb); if (!inode) return ERR_PTR(-ENOMEM); diff --git a/fs/inode.c b/fs/inode.c index 96c77b81167c..319b93b55570 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -362,9 +362,11 @@ EXPORT_SYMBOL_GPL(inode_sb_list_add); static inline void inode_sb_list_del(struct inode *inode) { - spin_lock(&inode_sb_list_lock); - list_del_init(&inode->i_sb_list); - spin_unlock(&inode_sb_list_lock); + if (!list_empty(&inode->i_sb_list)) { + spin_lock(&inode_sb_list_lock); + list_del_init(&inode->i_sb_list); + spin_unlock(&inode_sb_list_lock); + } } static unsigned long hash(struct super_block *sb, unsigned long hashval) @@ -796,6 +798,29 @@ unsigned int get_next_ino(void) } EXPORT_SYMBOL(get_next_ino); +/** + * new_inode_pseudo - obtain an inode + * @sb: superblock + * + * Allocates a new inode for given superblock. + * Inode wont be chained in superblock s_inodes list + * This means : + * - fs can't be unmount + * - quotas, fsnotify, writeback can't work + */ +struct inode *new_inode_pseudo(struct super_block *sb) +{ + struct inode *inode = alloc_inode(sb); + + if (inode) { + spin_lock(&inode->i_lock); + inode->i_state = 0; + spin_unlock(&inode->i_lock); + INIT_LIST_HEAD(&inode->i_sb_list); + } + return inode; +} + /** * new_inode - obtain an inode * @sb: superblock @@ -814,13 +839,9 @@ struct inode *new_inode(struct super_block *sb) spin_lock_prefetch(&inode_sb_list_lock); - inode = alloc_inode(sb); - if (inode) { - spin_lock(&inode->i_lock); - inode->i_state = 0; - spin_unlock(&inode->i_lock); + inode = new_inode_pseudo(sb); + if (inode) inode_sb_list_add(inode); - } return inode; } EXPORT_SYMBOL(new_inode); diff --git a/fs/pipe.c b/fs/pipe.c index 1b7f9af67ccf..0e0be1dc0f8e 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -948,7 +948,7 @@ static const struct dentry_operations pipefs_dentry_operations = { static struct inode * get_pipe_inode(void) { - struct inode *inode = new_inode(pipe_mnt->mnt_sb); + struct inode *inode = new_inode_pseudo(pipe_mnt->mnt_sb); struct pipe_inode_info *pipe; if (!inode) diff --git a/include/linux/fs.h b/include/linux/fs.h index a6658043258a..cc363fa7bb82 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2310,7 +2310,8 @@ extern void __iget(struct inode * inode); extern void iget_failed(struct inode *); extern void end_writeback(struct inode *); extern void __destroy_inode(struct inode *); -extern struct inode *new_inode(struct super_block *); +extern struct inode *new_inode_pseudo(struct super_block *sb); +extern struct inode *new_inode(struct super_block *sb); extern void free_inode_nonrcu(struct inode *inode); extern int should_remove_suid(struct dentry *); extern int file_remove_suid(struct file *); diff --git a/net/socket.c b/net/socket.c index 02dc82db3d23..26ed35c7751e 100644 --- a/net/socket.c +++ b/net/socket.c @@ -467,7 +467,7 @@ static struct socket *sock_alloc(void) struct inode *inode; struct socket *sock; - inode = new_inode(sock_mnt->mnt_sb); + inode = new_inode_pseudo(sock_mnt->mnt_sb); if (!inode) return NULL; -- cgit v1.2.3