| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Tue, 26 Jul 2011 11:36:34 +0200
From: Eric Dumazet <eric.dumazet@...il.com>
To: Christoph Hellwig <hch@...radead.org>
Cc: Tim Chen <tim.c.chen@...ux.intel.com>,
Al Viro <viro@...IV.linux.org.uk>,
David Miller <davem@...emloft.net>,
Andi Kleen <andi@...stfloor.org>,
Matthew Wilcox <matthew@....cx>,
Anton Blanchard <anton@...ba.org>, npiggin@...nel.dk,
linux-kernel@...r.kernel.org, linux-fsdevel@...r.kernel.org,
netdev <netdev@...r.kernel.org>
Subject: Re: [PATCH] vfs: dont chain pipe/anon/socket on superblock
s_inodes list
Le mardi 26 juillet 2011 à 05:03 -0400, Christoph Hellwig a écrit :
> On Tue, Jul 26, 2011 at 10:21:06AM +0200, Eric Dumazet wrote:
> > Well, not 'last' contention point, as we still hit remove_inode_hash(),
>
> There should be no ned to put pipe or anon inodes on the inode hash.
> Probably sockets don't need it either, but I'd need to look at it in
> detail.
>
> > inode_wb_list_del()
>
> The should never be on the wb list either, doing an unlocked check for
> actually beeing on the list before taking the lock should help you.
Yes, it might even help regular inodes ;)
>
> > inode_lru_list_del(),
>
> No real need to keep inodes in the LRU if we only allocate them using
> new_inode but never look them up either. You might want to try setting
> .drop_inode to generic_delete_inode for these.
Yes, I'll take a look, thanks.
>
> > +struct inode *__new_inode(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;
> > +}
>
> This needs a much better name like new_inode_pseudo, and a kerneldoc
> comment explaining when it is safe to use, and the consequences, which
> appear to me:
>
> - fs may never be unmount
> - quotas can't work on the filesystem
> - writeback can't work on the filesystem
Thanks for reviewing, here is v2 of the patch, addressing your comments.
[PATCH v2] 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@...il.com>
---
v2: address Christoph comments
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(-)
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 @@ 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 96c77b8..319b93b 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)
@@ -797,6 +799,29 @@ 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 1b7f9af..0e0be1d 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 a665804..cc363fa 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 02dc82d..26ed35c 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;
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists