linux-kernel - Re: acl_permission_check: disgusting performance

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

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20110513040214.GA25270@mail.hallyn.com>
Date:	Thu, 12 May 2011 23:02:14 -0500
From:	"Serge E. Hallyn" <serge@...lyn.com>
To:	"Serge E. Hallyn" <serge@...lyn.com>
Cc:	Linus Torvalds <torvalds@...ux-foundation.org>,
	"Serge E. Hallyn" <serge.hallyn@...onical.com>,
	"Eric W. Biederman" <ebiederm@...ssion.com>,
	Daniel Lezcano <daniel.lezcano@...e.fr>,
	David Howells <dhowells@...hat.com>,
	James Morris <jmorris@...ei.org>,
	Andrew Morton <akpm@...ux-foundation.org>,
	Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
	containers@...ts.linux-foundation.org,
	Al Viro <viro@...iv.linux.org.uk>
Subject: Re: acl_permission_check: disgusting performance

I wonder how much this would help:  (only compile-tested)

I will look into how to do some profiling tomorrow.

From: Serge E. Hallyn <serge.hallyn@...onical.com>
Date: Fri, 13 May 2011 04:27:54 +0100
Subject: [PATCH 1/1] Cache struct cred in acl_permission_check, and cache user_ns
 in struct cred.

Signed-off-by: Serge E. Hallyn <serge.hallyn@...onical.com>
---
 fs/namei.c           |    5 +++--
 include/linux/cred.h |    3 ++-
 kernel/cred.c        |    6 ++++++
 3 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index 54fc993..eb0f4ea 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -180,13 +180,14 @@ static int acl_permission_check(struct inode *inode, int mask, unsigned int flag
 		int (*check_acl)(struct inode *inode, int mask, unsigned int flags))
 {
 	umode_t			mode = inode->i_mode;
+	const struct cred	*cred = current_cred();
 
 	mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
 
-	if (current_user_ns() != inode_userns(inode))
+	if (cred->user_ns != inode_userns(inode))
 		goto other_perms;
 
-	if (current_fsuid() == inode->i_uid)
+	if (cred->fsuid == inode->i_uid)
 		mode >>= 6;
 	else {
 		if (IS_POSIXACL(inode) && (mode & S_IRWXG) && check_acl) {
diff --git a/include/linux/cred.h b/include/linux/cred.h
index 9aeeb0b..a2a892c 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -146,6 +146,7 @@ struct cred {
 	void		*security;	/* subjective LSM security */
 #endif
 	struct user_struct *user;	/* real user ID subscription */
+	struct user_namespace *user_ns; /* cached user->user_ns */
 	struct group_info *group_info;	/* supplementary groups for euid/fsgid */
 	struct rcu_head	rcu;		/* RCU deletion hook */
 };
@@ -354,7 +355,7 @@ static inline void put_cred(const struct cred *_cred)
 #define current_fsgid() 	(current_cred_xxx(fsgid))
 #define current_cap()		(current_cred_xxx(cap_effective))
 #define current_user()		(current_cred_xxx(user))
-#define _current_user_ns()	(current_cred_xxx(user)->user_ns)
+#define _current_user_ns()	(current_cred_xxx(user_ns))
 #define current_security()	(current_cred_xxx(security))
 
 extern struct user_namespace *current_user_ns(void);
diff --git a/kernel/cred.c b/kernel/cred.c
index 5557b55..a3dcf28 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -54,6 +54,7 @@ struct cred init_cred = {
 	.cap_effective		= CAP_INIT_EFF_SET,
 	.cap_bset		= CAP_INIT_BSET,
 	.user			= INIT_USER,
+	.user_ns		= &init_user_ns,
 	.group_info		= &init_groups,
 #ifdef CONFIG_KEYS
 	.tgcred			= &init_tgcred,
@@ -410,6 +411,11 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
 			goto error_put;
 	}
 
+	/* cache user_ns in cred.  Doesn't need a refcount because it will
+	 * stay pinned by cred->user
+	 */
+	new->user_ns = new->user->user_ns;
+
 #ifdef CONFIG_KEYS
 	/* new threads get their own thread keyrings if their parent already
 	 * had one */
-- 
1.7.0.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/