audit: Fixes and tasklist_lock -> RCU conversion - Resend
Subsystems (3)
cover audit: Fixes and tasklist_lock -> RCU conversion - Resend
Hi,
the following patches result from auditing read_lock(&tasklist_lock) sites whether they can be converted to RCU.
Resend of http://lkml.org/lkml/2009/12/9/216
Thanks,
tglx
PATCH 1/3 audit: Call tty_audit_push_task() outside preempt disabled
While auditing all tasklist_lock read_lock sites I stumbled over the following call chain:
audit_prepare_user_tty()
read_lock(&tasklist_lock);
tty_audit_push_task();
mutex_lock(&buf->mutex);
--> buf->mutex is locked with preemption disabled.Solve this by acquiring a reference to the task struct under rcu_read_lock and call tty_audit_push_task outside of the preempt disabled region.
Move all code which needs to be protected by sighand lock into tty_audit_push_task() and use lock/unlock_sighand as we do not hold tasklist_lock.
---drivers/char/tty_audit.c | 38 ++++++++++++++++++++++++++++----------
drivers/char/tty_audit.c | 38 ++++++++++++++++++++++++++++---------- include/linux/tty.h | 8 ++------ kernel/audit.c | 25 +++++++++---------------- 3 files changed, 39 insertions(+), 32 deletions(-)
drivers/char/tty_audit.c +28 -10
@@ -188,25 +188,43 @@ void tty_audit_tiocsti(struct tty_struct }/** -* tty_audit_push_task - Flush task's pending audit data +* tty_audit_push_task - Flush task's pending audit data +* @tsk: task pointer +* @loginuid: sender login uid +* @sessionid: sender session id +* +* Called with a ref on @tsk held. Try to lock sighand and get a +* reference to the tty audit buffer if available. +* Flush the buffer or return an appropriate error code. */ -void tty_audit_push_task (struct task_struct *tsk,uid_t loginuid,u32 sessionid) +int tty_audit_push_task (struct task_struct *tsk,uid_t loginuid,u32 sessionid) { -struct tty_audit_buf *buf; +struct tty_audit_buf *buf =ERR_PTR (-EPERM ); +unsigned long flags; -spin_lock_irq (&tsk->sighand->siglock); - buf = tsk->signal->tty_audit_buf; -if (buf) -atomic_inc (&buf->count); -spin_unlock_irq (&tsk->sighand->siglock); -if (!buf) -return ; +if (!lock_task_sighand (tsk, &flags)) +return -ESRCH ; + +if (tsk->signal->audit_tty) { + buf = tsk->signal->tty_audit_buf; +if (buf) +atomic_inc (&buf->count); + } +unlock_task_sighand (tsk, &flags); + +/* +* Return 0 when signal->audit_tty set +* but tsk->signal->tty_audit_buf == NULL. +*/ +if (!buf ||IS_ERR (buf)) +return PTR_ERR (buf);mutex_lock (&buf->mutex);tty_audit_buf_push (tsk, loginuid, sessionid, buf);mutex_unlock (&buf->mutex);tty_audit_buf_put (buf); +return 0 ; }/**
include/linux/tty.h +2 -6
@@ -539,8 +539,8 @@ extern void tty_audit_exit(void);extern void tty_audit_fork (struct signal_struct *sig);extern void tty_audit_tiocsti (struct tty_struct *tty,char ch);extern void tty_audit_push (struct tty_struct *tty); -extern void tty_audit_push_task (struct task_struct *tsk, -uid_t loginuid,u32 sessionid); +extern int tty_audit_push_task (struct task_struct *tsk, +uid_t loginuid,u32 sessionid);#else static inline void tty_audit_add_data (struct tty_struct *tty,unsigned char *data,size_t size)
@@ -558,10 +558,6 @@ static inline void tty_audit_fork(structstatic inline void tty_audit_push (struct tty_struct *tty) { } -static inline void tty_audit_push_task (struct task_struct *tsk, -uid_t loginuid,u32 sessionid) -{ -}#endif /* tty_io.c */
kernel/audit.c +9 -16
@@ -467,23 +467,16 @@ static int audit_prepare_user_tty(pid_tstruct task_struct *tsk;int err; -read_lock (&tasklist_lock); +rcu_read_lock (); tsk =find_task_by_vpid (pid); - err = -ESRCH ; -if (!tsk) - goto out; - err =0 ; - -spin_lock_irq (&tsk->sighand->siglock); -if (!tsk->signal->audit_tty) - err = -EPERM ; -spin_unlock_irq (&tsk->sighand->siglock); -if (err) - goto out; - -tty_audit_push_task (tsk, loginuid, sessionid); -out: -read_unlock (&tasklist_lock); +if (!tsk) { +rcu_read_unlock (); +return -ESRCH ; + } +get_task_struct (tsk); +rcu_read_unlock (); + err =tty_audit_push_task (tsk, loginuid, sessionid); +put_task_struct (tsk);return err; }
PATCH 2/3 audit: Do not send uninitialized data for AUDIT_TTY_GET
In reply to Thomas Gleixneraudit_receive_msg() sends uninitialized data for AUDIT_TTY_GET when the task was not found.
Send reply only when task was found.
---kernel/audit.c | 6 ++++--
kernel/audit.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)
kernel/audit.c +4 -2
@@ -884,8 +884,10 @@ static int audit_receive_msg(struct sk_bspin_unlock_irq (&tsk->sighand->siglock); }read_unlock (&tasklist_lock); -audit_send_reply (NETLINK_CB (skb).pid, seq,AUDIT_TTY_GET ,0 ,0 , - &s,sizeof (s)); + +if (!err) +audit_send_reply (NETLINK_CB (skb).pid, seq, +AUDIT_TTY_GET ,0 ,0 , &s,sizeof (s));break ; }case AUDIT_TTY_SET : {
PATCH 3/3 audit: Use rcu for task lookup protection
In reply to Thomas GleixnerProtect the task lookups in audit_receive_msg() with rcu_read_lock() instead of tasklist_lock and use lock/unlock_sighand to protect against the exit race.
---kernel/audit.c | 30 ++++++++++++++----------------
kernel/audit.c | 30 ++++++++++++++---------------- 1 file changed, 14 insertions(+), 16 deletions(-)
kernel/audit.c +14 -16
@@ -873,17 +873,16 @@ static int audit_receive_msg(struct sk_bcase AUDIT_TTY_GET : {struct audit_tty_status s;struct task_struct *tsk; +unsigned long flags; -read_lock (&tasklist_lock); +rcu_read_lock (); tsk =find_task_by_vpid (pid); -if (!tsk) - err = -ESRCH ; -else { -spin_lock_irq (&tsk->sighand->siglock); +if (tsk &&lock_task_sighand (tsk, &flags)) { s.enabled = tsk->signal->audit_tty !=0 ; -spin_unlock_irq (&tsk->sighand->siglock); - } -read_unlock (&tasklist_lock); +unlock_task_sighand (tsk, &flags); + }else + err = -ESRCH ; +rcu_read_unlock ();if (!err) audit_send_reply(NETLINK_CB(skb).pid, seq,
@@ -893,22 +892,21 @@ static int audit_receive_msg(struct sk_bcase AUDIT_TTY_SET : {struct audit_tty_status *s;struct task_struct *tsk; +unsigned long flags;if (nlh->nlmsg_len <sizeof (struct audit_tty_status ))return -EINVAL ; s = data;if (s->enabled !=0 && s->enabled !=1 )return -EINVAL ; -read_lock (&tasklist_lock); +rcu_read_lock (); tsk =find_task_by_vpid (pid); -if (!tsk) - err = -ESRCH ; -else { -spin_lock_irq (&tsk->sighand->siglock); +if (tsk &&lock_task_sighand (tsk, &flags)) { tsk->signal->audit_tty = s->enabled !=0 ; -spin_unlock_irq (&tsk->sighand->siglock); - } -read_unlock (&tasklist_lock); +unlock_task_sighand (tsk, &flags); + }else + err = -ESRCH ; +rcu_read_unlock ();break ; }default :
Re: [patch 3/3] audit: Use rcu for task lookup protection
Quoted 4 lines · Thomas Gleixner
Protect the task lookups in
audit_receive_msg()withrcu_read_lock()instead oftasklist_lockand use lock/unlock_sighand to protect against the exit race.
I do not understand audit, but I belive both 1/3 and 3/3 patches are fine (I didn't get 2/3).
But, sorry, can't resists ;) off-topic nit.
Quoted 5 lines
kernel/audit.c +1
-0@@ -873,17 +873,16 @@ static int audit_receive_msg(struct sk_bcase AUDIT_TTY_GET : {struct audit_tty_status s;struct task_struct *tsk; +unsigned long flags;
kernel/audit.c static int audit_receive_msg(struct sk_b · line 881
Quoted 10 lines
kernel/audit.c +2
-5-read_lock (&tasklist_lock); +rcu_read_lock (); tsk =find_task_by_vpid (pid); -if (!tsk) - err = -ESRCH ; -else { -spin_lock_irq (&tsk->sighand->siglock); +if (tsk &&lock_task_sighand (tsk, &flags)) { s.enabled = tsk->signal->audit_tty !=0 ;
Yes, this is what original code does, it takes ->siglock every time around read/write of ->audit_tty. And this looks absolutely bogus. Say, tty_audit_fork(). Why does it take ->siglock ?
As for ->tty_audit_buf, I am not sure ->siglock is the best choice, perhaps task_lock() would be better.
Once again, I think the patch is fine. Just it seems to me this code needs more cleanups.
Oleg.
Re: [patch 3/3] audit: Use rcu for task lookup protection
Quoted 33 lines · Oleg Nesterov
Quoted 4 lines · Thomas Gleixner
Protect the task lookups in
audit_receive_msg()withrcu_read_lock()instead oftasklist_lockand use lock/unlock_sighand to protect against the exit race.I do not understand audit, but I belive both 1/3 and 3/3 patches are fine (I didn't get 2/3).
But, sorry, can't resists ;) off-topic nit.
Quoted 5 lines
kernel/audit.c +1
-0@@ -873,17 +873,16 @@ static int audit_receive_msg(struct sk_bcase AUDIT_TTY_GET : {struct audit_tty_status s;struct task_struct *tsk; +unsigned long flags;kernel/audit.c static int audit_receive_msg(struct sk_b · line 881
Quoted 10 lines
kernel/audit.c +2
-5-read_lock (&tasklist_lock); +rcu_read_lock (); tsk =find_task_by_vpid (pid); -if (!tsk) - err = -ESRCH ; -else { -spin_lock_irq (&tsk->sighand->siglock); +if (tsk &&lock_task_sighand (tsk, &flags)) { s.enabled = tsk->signal->audit_tty !=0 ;Yes, this is what original code does, it takes ->siglock every time around read/write of ->audit_tty. And this looks absolutely bogus. Say,
tty_audit_fork(). Why does it take ->siglock ?
Quoted 5 lines
As for ->tty_audit_buf, I am not sure ->siglock is the best choice, perhaps
task_lock()would be better.Once again, I think the patch is fine. Just it seems to me this code needs more cleanups.
Yeah, thought about that, but that's not in the scope of what I was working on. I leave that to the audit folks. :)
Thanks,
tglx
Re: [patch 3/3] audit: Use rcu for task lookup protection
Quoted 11 lines · Thomas Gleixner
Quoted 8 lines · Oleg Nesterov
But, sorry, can't resists ;) off-topic nit.
Quoted 6 lines
kernel/audit.c +1
-0@@ -873,17 +873,16 @@ static int audit_receive_msg(struct sk_bcase AUDIT_TTY_GET : {struct audit_tty_status s;struct task_struct *tsk; +unsigned long flags;
Quoted 13 lines
Quoted 5 lines
Quoted 5 lines
kernel/audit.c +1
-3-read_lock (&tasklist_lock); +rcu_read_lock (); tsk =find_task_by_vpid (pid); -if (!tsk) - err = -ESRCH ;Quoted 8 lines
kernel/audit.c static int audit_receive_msg(struct sk_b · line 881
Quoted 4 lines
kernel/audit.c +1
-2-else { -spin_lock_irq (&tsk->sighand->siglock); +if (tsk &&lock_task_sighand (tsk, &flags)) { s.enabled = tsk->signal->audit_tty !=0 ;Yes, this is what original code does, it takes ->siglock every time around read/write of ->audit_tty. And this looks absolutely bogus. Say,
tty_audit_fork(). Why does it take ->siglock ?
Yes, I still think ->audit_tty doesn't need the locking.
Quoted 2 lines
Quoted 2 lines
As for ->tty_audit_buf, I am not sure ->siglock is the best choice, perhaps
task_lock()would be better.
OOPS, I misread the code. ->tty_audit_buf is per-process (of course!). Well, unless I missed something again, tty_audit_push() and tty_audit_tiocsti() can access ->tty_audit_buf lockless.
Quoted 5 lines
Quoted 2 lines
Once again, I think the patch is fine. Just it seems to me this code needs more cleanups.
Yeah, thought about that, but that's not in the scope of what I was working on. I leave that to the audit folks. :)
Yes, yes, sure.
Oleg.