From 14d8c9f3c09e7fd7b9af80904289fe204f5b93c6 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 10 Dec 2009 00:53:17 +0000 Subject: [PATCH 1/3] signal: Fix racy access to __task_cred in kill_pid_info_as_uid() kill_pid_info_as_uid() accesses __task_cred() without being in a RCU read side critical section. tasklist_lock is not protecting that when CONFIG_TREE_PREEMPT_RCU=y. Convert the whole tasklist_lock section to rcu and use lock_task_sighand to prevent the exit race. Signed-off-by: Thomas Gleixner LKML-Reference: <20091210004703.232302055@linutronix.de> Acked-by: Oleg Nesterov --- kernel/signal.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/kernel/signal.c b/kernel/signal.c index 6b982f2cf52..73316568a69 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1175,11 +1175,12 @@ int kill_pid_info_as_uid(int sig, struct siginfo *info, struct pid *pid, int ret = -EINVAL; struct task_struct *p; const struct cred *pcred; + unsigned long flags; if (!valid_signal(sig)) return ret; - read_lock(&tasklist_lock); + rcu_read_lock(); p = pid_task(pid, PIDTYPE_PID); if (!p) { ret = -ESRCH; @@ -1196,14 +1197,16 @@ int kill_pid_info_as_uid(int sig, struct siginfo *info, struct pid *pid, ret = security_task_kill(p, info, sig, secid); if (ret) goto out_unlock; - if (sig && p->sighand) { - unsigned long flags; - spin_lock_irqsave(&p->sighand->siglock, flags); - ret = __send_signal(sig, info, p, 1, 0); - spin_unlock_irqrestore(&p->sighand->siglock, flags); + + if (sig) { + if (lock_task_sighand(p, &flags)) { + ret = __send_signal(sig, info, p, 1, 0); + unlock_task_sighand(p, &flags); + } else + ret = -ESRCH; } out_unlock: - read_unlock(&tasklist_lock); + rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(kill_pid_info_as_uid); From 7cf7db8df0b78076eafa4ead47559344ca7b7a43 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 10 Dec 2009 00:53:21 +0000 Subject: [PATCH 2/3] signals: Fix more rcu assumptions 1) Remove the misleading comment in __sigqueue_alloc() which claims that holding a spinlock is equivalent to rcu_read_lock(). 2) Add a rcu_read_lock/unlock around the __task_cred() access in __sigqueue_alloc() This needs to be revisited to remove the remaining users of read_lock(&tasklist_lock) but that's outside the scope of this patch. Signed-off-by: Thomas Gleixner LKML-Reference: <20091210004703.269843657@linutronix.de> --- kernel/signal.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/kernel/signal.c b/kernel/signal.c index 73316568a69..f67545f9394 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -218,13 +218,13 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimi struct user_struct *user; /* - * We won't get problems with the target's UID changing under us - * because changing it requires RCU be used, and if t != current, the - * caller must be holding the RCU readlock (by way of a spinlock) and - * we use RCU protection here + * Protect access to @t credentials. This can go away when all + * callers hold rcu read lock. */ + rcu_read_lock(); user = get_uid(__task_cred(t)->user); atomic_inc(&user->sigpending); + rcu_read_unlock(); if (override_rlimit || atomic_read(&user->sigpending) <= From d4581a239a40319205762b76c01eb6363f277efa Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 10 Dec 2009 00:52:51 +0000 Subject: [PATCH 3/3] sys: Fix missing rcu protection for __task_cred() access commit c69e8d9 (CRED: Use RCU to access another task's creds and to release a task's own creds) added non rcu_read_lock() protected access to task creds of the target task in set_prio_one(). The comment above the function says: * - the caller must hold the RCU read lock The calling code in sys_setpriority does read_lock(&tasklist_lock) but not rcu_read_lock(). This works only when CONFIG_TREE_PREEMPT_RCU=n. With CONFIG_TREE_PREEMPT_RCU=y the rcu_callbacks can run in the tick interrupt when they see no read side critical section. There is another instance of __task_cred() in sys_setpriority() itself which is equally unprotected. Wrap the whole code section into a rcu read side critical section to fix this quick and dirty. Will be revisited in course of the read_lock(&tasklist_lock) -> rcu crusade. Oleg noted further: This also fixes another bug here. find_task_by_vpid() is not safe without rcu_read_lock(). I do not mean it is not safe to use the result, just find_pid_ns() by itself is not safe. Usually tasklist gives enough protection, but if copy_process() fails it calls free_pid() lockless and does call_rcu(delayed_put_pid(). This means, without rcu lock find_pid_ns() can't scan the hash table safely. Signed-off-by: Thomas Gleixner LKML-Reference: <20091210004703.029784964@linutronix.de> Acked-by: Paul E. McKenney --- kernel/sys.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/sys.c b/kernel/sys.c index 9968c5fb55b..bc1dc61c31e 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -163,6 +163,7 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval) if (niceval > 19) niceval = 19; + rcu_read_lock(); read_lock(&tasklist_lock); switch (which) { case PRIO_PROCESS: @@ -200,6 +201,7 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval) } out_unlock: read_unlock(&tasklist_lock); + rcu_read_unlock(); out: return error; }