commit a209dfc7b0d94bd6fa94553c097836a2e6d0f0ba
author Eric Dumazet <eric.dumazet@gmail.com> Tue Jul 26 11:36:34 2011 +0200
committer Al Viro <viro@zeniv.linux.org.uk> Tue Jul 26 12:57:09 2011 -0400
tree 7dacc92b08264c675a0dfcbae83982b7d3ad5135
parent 5b9f4567726513a359e70f85029482c7c3714dbd

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>

fs/anon_inodes.c

diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index 4d433d3..f11e43e 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -187,7 +187,7 @@
  */
 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);

fs/inode.c

diff --git a/fs/inode.c b/fs/inode.c
index 96c77b8..319b93b 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -362,9 +362,11 @@
 
 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)
@@ -797,6 +799,29 @@
 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 @@
 
 	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);

fs/pipe.c

diff --git a/fs/pipe.c b/fs/pipe.c
index 1b7f9af..0e0be1d 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -948,7 +948,7 @@
 
 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)

include/linux/fs.h

diff --git a/include/linux/fs.h b/include/linux/fs.h
index a665804..cc363fa 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2310,7 +2310,8 @@
 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 *);

net/socket.c

diff --git a/net/socket.c b/net/socket.c
index 02dc82d..26ed35c 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -467,7 +467,7 @@
 	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;