From 7570acb210618f222920736a0c43fcc99c61f3de Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 22 Mar 2017 11:35:57 +0100 Subject: futex,rt_mutex: Restructure rt_mutex_finish_proxy_lock() commit 38d589f2fd08f1296aea3ce62bebd185125c6d81 upstream. With the ultimate goal of keeping rt_mutex wait_list and futex_q waiters consistent it's necessary to split 'rt_mutex_futex_lock()' into finer parts, such that only the actual blocking can be done without hb->lock held. Split split_mutex_finish_proxy_lock() into two parts, one that does the blocking and one that does remove_waiter() when the lock acquire failed. When the rtmutex was acquired successfully the waiter can be removed in the acquisiton path safely, since there is no concurrency on the lock owner. This means that, except for futex_lock_pi(), all wait_list modifications are done with both hb->lock and wait_lock held. [bigeasy@linutronix.de: fix for futex_requeue_pi_signal_restart] Signed-off-by: Peter Zijlstra (Intel) Cc: juri.lelli@arm.com Cc: bigeasy@linutronix.de Cc: xlpang@redhat.com Cc: rostedt@goodmis.org Cc: mathieu.desnoyers@efficios.com Cc: jdesfossez@efficios.com Cc: dvhart@infradead.org Cc: bristot@redhat.com Link: http://lkml.kernel.org/r/20170322104152.001659630@infradead.org Signed-off-by: Thomas Gleixner Signed-off-by: Zubin Mithra Signed-off-by: Greg Kroah-Hartman --- kernel/futex.c | 7 ++++-- kernel/locking/rtmutex.c | 52 +++++++++++++++++++++++++++++++++++------ kernel/locking/rtmutex_common.h | 8 ++++--- 3 files changed, 55 insertions(+), 12 deletions(-) (limited to 'kernel') diff --git a/kernel/futex.c b/kernel/futex.c index a26d217c99fe..0c92c8d34ffa 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -2923,10 +2923,13 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, */ WARN_ON(!q.pi_state); pi_mutex = &q.pi_state->pi_mutex; - ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter); - debug_rt_mutex_free_waiter(&rt_waiter); + ret = rt_mutex_wait_proxy_lock(pi_mutex, to, &rt_waiter); spin_lock(q.lock_ptr); + if (ret && !rt_mutex_cleanup_proxy_lock(pi_mutex, &rt_waiter)) + ret = 0; + + debug_rt_mutex_free_waiter(&rt_waiter); /* * Fixup the pi_state owner and possibly acquire the lock if we * haven't already. diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index b066724d7a5b..dd173df9ee5e 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1712,21 +1712,23 @@ struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock) } /** - * rt_mutex_finish_proxy_lock() - Complete lock acquisition + * rt_mutex_wait_proxy_lock() - Wait for lock acquisition * @lock: the rt_mutex we were woken on * @to: the timeout, null if none. hrtimer should already have * been started. * @waiter: the pre-initialized rt_mutex_waiter * - * Complete the lock acquisition started our behalf by another thread. + * Wait for the the lock acquisition started on our behalf by + * rt_mutex_start_proxy_lock(). Upon failure, the caller must call + * rt_mutex_cleanup_proxy_lock(). * * Returns: * 0 - success * <0 - error, one of -EINTR, -ETIMEDOUT * - * Special API call for PI-futex requeue support + * Special API call for PI-futex support */ -int rt_mutex_finish_proxy_lock(struct rt_mutex *lock, +int rt_mutex_wait_proxy_lock(struct rt_mutex *lock, struct hrtimer_sleeper *to, struct rt_mutex_waiter *waiter) { @@ -1739,9 +1741,6 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock, /* sleep on the mutex */ ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter); - if (unlikely(ret)) - remove_waiter(lock, waiter); - /* * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might * have to fix that up. @@ -1752,3 +1751,42 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock, return ret; } + +/** + * rt_mutex_cleanup_proxy_lock() - Cleanup failed lock acquisition + * @lock: the rt_mutex we were woken on + * @waiter: the pre-initialized rt_mutex_waiter + * + * Attempt to clean up after a failed rt_mutex_wait_proxy_lock(). + * + * Unless we acquired the lock; we're still enqueued on the wait-list and can + * in fact still be granted ownership until we're removed. Therefore we can + * find we are in fact the owner and must disregard the + * rt_mutex_wait_proxy_lock() failure. + * + * Returns: + * true - did the cleanup, we done. + * false - we acquired the lock after rt_mutex_wait_proxy_lock() returned, + * caller should disregards its return value. + * + * Special API call for PI-futex support + */ +bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock, + struct rt_mutex_waiter *waiter) +{ + bool cleanup = false; + + raw_spin_lock_irq(&lock->wait_lock); + /* + * Unless we're the owner; we're still enqueued on the wait_list. + * So check if we became owner, if not, take us off the wait_list. + */ + if (rt_mutex_owner(lock) != current) { + remove_waiter(lock, waiter); + fixup_rt_mutex_waiters(lock); + cleanup = true; + } + raw_spin_unlock_irq(&lock->wait_lock); + + return cleanup; +} diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h index e317e1cbb3eb..6f8f68edb700 100644 --- a/kernel/locking/rtmutex_common.h +++ b/kernel/locking/rtmutex_common.h @@ -106,9 +106,11 @@ extern void rt_mutex_proxy_unlock(struct rt_mutex *lock, extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, struct task_struct *task); -extern int rt_mutex_finish_proxy_lock(struct rt_mutex *lock, - struct hrtimer_sleeper *to, - struct rt_mutex_waiter *waiter); +extern int rt_mutex_wait_proxy_lock(struct rt_mutex *lock, + struct hrtimer_sleeper *to, + struct rt_mutex_waiter *waiter); +extern bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock, + struct rt_mutex_waiter *waiter); extern int rt_mutex_timed_futex_lock(struct rt_mutex *l, struct hrtimer_sleeper *to); extern bool rt_mutex_futex_unlock(struct rt_mutex *lock, struct wake_q_head *wqh); -- cgit v1.2.3 From 19c53c1f817e1e04fe0a679b5b7790b7eaa3e1f9 Mon Sep 17 00:00:00 2001 From: "zhangyi (F)" Date: Wed, 13 Feb 2019 20:29:06 +0800 Subject: tracing: Do not free iter->trace in fail path of tracing_open_pipe() commit e7f0c424d0806b05d6f47be9f202b037eb701707 upstream. Commit d716ff71dd12 ("tracing: Remove taking of trace_types_lock in pipe files") use the current tracer instead of the copy in tracing_open_pipe(), but it forget to remove the freeing sentence in the error path. There's an error path that can call kfree(iter->trace) after the iter->trace was assigned to tr->current_trace, which would be bad to free. Link: http://lkml.kernel.org/r/1550060946-45984-1-git-send-email-yi.zhang@huawei.com Cc: stable@vger.kernel.org Fixes: d716ff71dd12 ("tracing: Remove taking of trace_types_lock in pipe files") Signed-off-by: zhangyi (F) Signed-off-by: Steven Rostedt (VMware) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace.c | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 1a47a64d623f..8c097de8a596 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4646,7 +4646,6 @@ out: return ret; fail: - kfree(iter->trace); kfree(iter); __trace_array_put(tr); mutex_unlock(&trace_types_lock); -- cgit v1.2.3 From c8d2a21fdf518bea5cf72bf212df85ca50dcb156 Mon Sep 17 00:00:00 2001 From: Zev Weiss Date: Mon, 11 Mar 2019 23:28:02 -0700 Subject: kernel/sysctl.c: add missing range check in do_proc_dointvec_minmax_conv commit 8cf7630b29701d364f8df4a50e4f1f5e752b2778 upstream. This bug has apparently existed since the introduction of this function in the pre-git era (4500e91754d3 in Thomas Gleixner's history.git, "[NET]: Add proc_dointvec_userhz_jiffies, use it for proper handling of neighbour sysctls."). As a minimal fix we can simply duplicate the corresponding check in do_proc_dointvec_conv(). Link: http://lkml.kernel.org/r/20190207123426.9202-3-zev@bewilderbeest.net Signed-off-by: Zev Weiss Cc: Brendan Higgins Cc: Iurii Zaikin Cc: Kees Cook Cc: Luis Chamberlain Cc: [2.6.2+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- kernel/sysctl.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 7e832f9a8f42..beadcf83ceba 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2306,7 +2306,16 @@ static int do_proc_dointvec_minmax_conv(bool *negp, unsigned long *lvalp, { struct do_proc_dointvec_minmax_conv_param *param = data; if (write) { - int val = *negp ? -*lvalp : *lvalp; + int val; + if (*negp) { + if (*lvalp > (unsigned long) INT_MAX + 1) + return -EINVAL; + val = -*lvalp; + } else { + if (*lvalp > (unsigned long) INT_MAX) + return -EINVAL; + val = *lvalp; + } if ((param->min && *param->min > val) || (param->max && *param->max < val)) return -EINVAL; -- cgit v1.2.3 From 25c4c4519352b57c8fc02d7e1a2ff2c4407c1171 Mon Sep 17 00:00:00 2001 From: "Zhang, Jun" Date: Tue, 18 Dec 2018 06:55:01 -0800 Subject: rcu: Do RCU GP kthread self-wakeup from softirq and interrupt commit 1d1f898df6586c5ea9aeaf349f13089c6fa37903 upstream. The rcu_gp_kthread_wake() function is invoked when it might be necessary to wake the RCU grace-period kthread. Because self-wakeups are normally a useless waste of CPU cycles, if rcu_gp_kthread_wake() is invoked from this kthread, it naturally refuses to do the wakeup. Unfortunately, natural though it might be, this heuristic fails when rcu_gp_kthread_wake() is invoked from an interrupt or softirq handler that interrupted the grace-period kthread just after the final check of the wait-event condition but just before the schedule() call. In this case, a wakeup is required, even though the call to rcu_gp_kthread_wake() is within the RCU grace-period kthread's context. Failing to provide this wakeup can result in grace periods failing to start, which in turn results in out-of-memory conditions. This race window is quite narrow, but it actually did happen during real testing. It would of course need to be fixed even if it was strictly theoretical in nature. This patch does not Cc stable because it does not apply cleanly to earlier kernel versions. Fixes: 48a7639ce80c ("rcu: Make callers awaken grace-period kthread") Reported-by: "He, Bo" Co-developed-by: "Zhang, Jun" Co-developed-by: "He, Bo" Co-developed-by: "xiao, jin" Co-developed-by: Bai, Jie A Signed-off: "Zhang, Jun" Signed-off: "He, Bo" Signed-off: "xiao, jin" Signed-off: Bai, Jie A Signed-off-by: "Zhang, Jun" [ paulmck: Switch from !in_softirq() to "!in_interrupt() && !in_serving_softirq() to avoid redundant wakeups and to also handle the interrupt-handler scenario as well as the softirq-handler scenario that actually occurred in testing. ] Signed-off-by: Paul E. McKenney Link: https://lkml.kernel.org/r/CD6925E8781EFD4D8E11882D20FC406D52A11F61@SHSMSX104.ccr.corp.intel.com Signed-off-by: Greg Kroah-Hartman --- kernel/rcu/tree.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 4e886ccd40db..082aedefe29c 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1611,15 +1611,23 @@ static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) } /* - * Awaken the grace-period kthread for the specified flavor of RCU. - * Don't do a self-awaken, and don't bother awakening when there is - * nothing for the grace-period kthread to do (as in several CPUs - * raced to awaken, and we lost), and finally don't try to awaken - * a kthread that has not yet been created. + * Awaken the grace-period kthread. Don't do a self-awaken (unless in + * an interrupt or softirq handler), and don't bother awakening when there + * is nothing for the grace-period kthread to do (as in several CPUs raced + * to awaken, and we lost), and finally don't try to awaken a kthread that + * has not yet been created. If all those checks are passed, track some + * debug information and awaken. + * + * So why do the self-wakeup when in an interrupt or softirq handler + * in the grace-period kthread's context? Because the kthread might have + * been interrupted just as it was going to sleep, and just after the final + * pre-sleep check of the awaken condition. In this case, a wakeup really + * is required, and is therefore supplied. */ static void rcu_gp_kthread_wake(struct rcu_state *rsp) { - if (current == rsp->gp_kthread || + if ((current == rsp->gp_kthread && + !in_interrupt() && !in_serving_softirq()) || !READ_ONCE(rsp->gp_flags) || !rsp->gp_kthread) return; -- cgit v1.2.3