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 <eric.dumazet@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index 4d433d34736f2e45784142012e1969f712443c93..f11e43ed907d14c55047c3e2d692d3400c0263d4 100644 (file)
--- 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 96c77b81167c81b75bfdbaf6f8c1ea0566892748..319b93b555709b14e69e2f750274522ee1e0d27b 100644 (file)
--- 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 1b7f9af67ccfff8ca6aaacb9ecdd8ddc87fa99a0..0e0be1dc0f8ef67e433cefb9d46c708b2a2ca52d 100644 (file)
--- 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 a6658043258a923e3132da31ad2d502db22dc0da..cc363fa7bb8274275efc4af74ccf2a3558cb39d6 100644 (file)
--- 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 02dc82db3d232c79173d271370f7ff2bd68f5dc7..26ed35c7751e230361d3ef5fc461b1e30c99c5ea 100644 (file)
--- 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;