From 0365aeba50841e087b3d6a0eca1bddccc5e650c8 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 22 Jan 2019 16:21:39 +0100 Subject: futex: No need to check return value of debugfs_create functions When calling debugfs functions, there is no need to ever check the return value. The function can work or not, but the code logic should never do something different based on this. Signed-off-by: Greg Kroah-Hartman Signed-off-by: Thomas Gleixner Reviewed-by: Darren Hart (VMware) Cc: Peter Zijlstra Link: https://lkml.kernel.org/r/20190122152151.16139-40-gregkh@linuxfoundation.org --- kernel/futex.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'kernel/futex.c') diff --git a/kernel/futex.c b/kernel/futex.c index fdd312da0992..69e619baf709 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -321,12 +321,8 @@ static int __init fail_futex_debugfs(void) if (IS_ERR(dir)) return PTR_ERR(dir); - if (!debugfs_create_bool("ignore-private", mode, dir, - &fail_futex.ignore_private)) { - debugfs_remove_recursive(dir); - return -ENOMEM; - } - + debugfs_create_bool("ignore-private", mode, dir, + &fail_futex.ignore_private); return 0; } -- cgit v1.2.3-70-g09d2 From 07879c6a3740fbbf3c8891a0ab484c20a12794d8 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Tue, 18 Dec 2018 11:53:52 -0800 Subject: sched/wake_q: Reduce reference counting for special users Some users, specifically futexes and rwsems, required fixes that allowed the callers to be safe when wakeups occur before they are expected by wake_up_q(). Such scenarios also play games and rely on reference counting, and until now were pivoting on wake_q doing it. With the wake_q_add() call being moved down, this can no longer be the case. As such we end up with a a double task refcounting overhead; and these callers care enough about this (being rather core-ish). This patch introduces a wake_q_add_safe() call that serves for callers that have already done refcounting and therefore the task is 'safe' from wake_q point of view (int that it requires reference throughout the entire queue/>wakeup cycle). In the one case it has internal reference counting, in the other case it consumes the reference counting. Signed-off-by: Davidlohr Bueso Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Waiman Long Cc: Will Deacon Cc: Xie Yongji Cc: Yongji Xie Cc: andrea.parri@amarulasolutions.com Cc: lilin24@baidu.com Cc: liuqi16@baidu.com Cc: nixun@baidu.com Cc: yuanlinsi01@baidu.com Cc: zhangyu31@baidu.com Link: https://lkml.kernel.org/r/20181218195352.7orq3upiwfdbrdne@linux-r8p5 Signed-off-by: Ingo Molnar --- include/linux/sched/wake_q.h | 4 +-- kernel/futex.c | 3 +-- kernel/locking/rwsem-xadd.c | 4 +-- kernel/sched/core.c | 60 ++++++++++++++++++++++++++++++++------------ 4 files changed, 48 insertions(+), 23 deletions(-) (limited to 'kernel/futex.c') diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h index 545f37138057..ad826d2a4557 100644 --- a/include/linux/sched/wake_q.h +++ b/include/linux/sched/wake_q.h @@ -51,8 +51,8 @@ static inline void wake_q_init(struct wake_q_head *head) head->lastp = &head->first; } -extern void wake_q_add(struct wake_q_head *head, - struct task_struct *task); +extern void wake_q_add(struct wake_q_head *head, struct task_struct *task); +extern void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task); extern void wake_up_q(struct wake_q_head *head); #endif /* _LINUX_SCHED_WAKE_Q_H */ diff --git a/kernel/futex.c b/kernel/futex.c index 69e619baf709..2abe1a0b3062 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1463,8 +1463,7 @@ static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q) * Queue the task for later wakeup for after we've released * the hb->lock. wake_q_add() grabs reference to p. */ - wake_q_add(wake_q, p); - put_task_struct(p); + wake_q_add_safe(wake_q, p); } /* diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index 50d9af615dc4..fbe96341beee 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -211,9 +211,7 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem, * Ensure issuing the wakeup (either by us or someone else) * after setting the reader waiter to nil. */ - wake_q_add(wake_q, tsk); - /* wake_q_add() already take the task ref */ - put_task_struct(tsk); + wake_q_add_safe(wake_q, tsk); } adjustment = woken * RWSEM_ACTIVE_READ_BIAS - adjustment; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 3c8b4dba3d2d..64ceaa5158c5 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -396,19 +396,7 @@ static bool set_nr_if_polling(struct task_struct *p) #endif #endif -/** - * wake_q_add() - queue a wakeup for 'later' waking. - * @head: the wake_q_head to add @task to - * @task: the task to queue for 'later' wakeup - * - * Queue a task for later wakeup, most likely by the wake_up_q() call in the - * same context, _HOWEVER_ this is not guaranteed, the wakeup can come - * instantly. - * - * This function must be used as-if it were wake_up_process(); IOW the task - * must be ready to be woken at this location. - */ -void wake_q_add(struct wake_q_head *head, struct task_struct *task) +static bool __wake_q_add(struct wake_q_head *head, struct task_struct *task) { struct wake_q_node *node = &task->wake_q; @@ -422,15 +410,55 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task) */ smp_mb__before_atomic(); if (unlikely(cmpxchg_relaxed(&node->next, NULL, WAKE_Q_TAIL))) - return; - - get_task_struct(task); + return false; /* * The head is context local, there can be no concurrency. */ *head->lastp = node; head->lastp = &node->next; + return true; +} + +/** + * wake_q_add() - queue a wakeup for 'later' waking. + * @head: the wake_q_head to add @task to + * @task: the task to queue for 'later' wakeup + * + * Queue a task for later wakeup, most likely by the wake_up_q() call in the + * same context, _HOWEVER_ this is not guaranteed, the wakeup can come + * instantly. + * + * This function must be used as-if it were wake_up_process(); IOW the task + * must be ready to be woken at this location. + */ +void wake_q_add(struct wake_q_head *head, struct task_struct *task) +{ + if (__wake_q_add(head, task)) + get_task_struct(task); +} + +/** + * wake_q_add_safe() - safely queue a wakeup for 'later' waking. + * @head: the wake_q_head to add @task to + * @task: the task to queue for 'later' wakeup + * + * Queue a task for later wakeup, most likely by the wake_up_q() call in the + * same context, _HOWEVER_ this is not guaranteed, the wakeup can come + * instantly. + * + * This function must be used as-if it were wake_up_process(); IOW the task + * must be ready to be woken at this location. + * + * This function is essentially a task-safe equivalent to wake_q_add(). Callers + * that already hold reference to @task can call the 'safe' version and trust + * wake_q to do the right thing depending whether or not the @task is already + * queued for wakeup. + */ +void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task) +{ + if (!__wake_q_add(head, task)) + put_task_struct(task); } void wake_up_q(struct wake_q_head *head) -- cgit v1.2.3-70-g09d2 From 49262de2270e09882d7bd8866a691cdd69ab32f6 Mon Sep 17 00:00:00 2001 From: Elena Reshetova Date: Tue, 5 Feb 2019 14:24:27 +0200 Subject: futex: Convert futex_pi_state.refcount to refcount_t atomic_t variables are currently used to implement reference counters with the following properties: - counter is initialized to 1 using atomic_set() - a resource is freed upon counter reaching zero - once counter reaches zero, its further increments aren't allowed - counter schema uses basic atomic operations (set, inc, inc_not_zero, dec_and_test, etc.) Such atomic variables should be converted to a newly provided refcount_t type and API that prevents accidental counter overflows and underflows. This is important since overflows and underflows can lead to use-after-free situation and be exploitable. The variable futex_pi_state.refcount is used as pure reference counter. Convert it to refcount_t and fix up the operations. **Important note for maintainers: Some functions from refcount_t API defined in lib/refcount.c have different memory ordering guarantees than their atomic counterparts. Please check Documentation/core-api/refcount-vs-atomic.rst for more information. Normally the differences should not matter since refcount_t provides enough guarantees to satisfy the refcounting use cases, but in some rare cases it might matter. Please double check that you don't have some undocumented memory guarantees for this variable usage. For the futex_pi_state.refcount it might make a difference in following places: - get_pi_state() and exit_pi_state_list(): increment in refcount_inc_not_zero() only guarantees control dependency on success vs. fully ordered atomic counterpart - put_pi_state(): decrement in refcount_dec_and_test() provides RELEASE ordering and ACQUIRE ordering on success vs. fully ordered atomic counterpart Suggested-by: Kees Cook Signed-off-by: Elena Reshetova Reviewed-by: David Windsor Reviewed-by: Hans Liljestrand Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Cc: dvhart@infradead.org Link: http://lkml.kernel.org/r/1549369467-3505-1-git-send-email-elena.reshetova@intel.com Signed-off-by: Ingo Molnar --- kernel/futex.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'kernel/futex.c') diff --git a/kernel/futex.c b/kernel/futex.c index 2abe1a0b3062..113f1c042250 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -68,6 +68,7 @@ #include #include #include +#include #include @@ -212,7 +213,7 @@ struct futex_pi_state { struct rt_mutex pi_mutex; struct task_struct *owner; - atomic_t refcount; + refcount_t refcount; union futex_key key; } __randomize_layout; @@ -799,7 +800,7 @@ static int refill_pi_state_cache(void) INIT_LIST_HEAD(&pi_state->list); /* pi_mutex gets initialized later */ pi_state->owner = NULL; - atomic_set(&pi_state->refcount, 1); + refcount_set(&pi_state->refcount, 1); pi_state->key = FUTEX_KEY_INIT; current->pi_state_cache = pi_state; @@ -819,7 +820,7 @@ static struct futex_pi_state *alloc_pi_state(void) static void get_pi_state(struct futex_pi_state *pi_state) { - WARN_ON_ONCE(!atomic_inc_not_zero(&pi_state->refcount)); + WARN_ON_ONCE(!refcount_inc_not_zero(&pi_state->refcount)); } /* @@ -831,7 +832,7 @@ static void put_pi_state(struct futex_pi_state *pi_state) if (!pi_state) return; - if (!atomic_dec_and_test(&pi_state->refcount)) + if (!refcount_dec_and_test(&pi_state->refcount)) return; /* @@ -861,7 +862,7 @@ static void put_pi_state(struct futex_pi_state *pi_state) * refcount is at 0 - put it back to 1. */ pi_state->owner = NULL; - atomic_set(&pi_state->refcount, 1); + refcount_set(&pi_state->refcount, 1); current->pi_state_cache = pi_state; } } @@ -904,7 +905,7 @@ void exit_pi_state_list(struct task_struct *curr) * In that case; drop the locks to let put_pi_state() make * progress and retry the loop. */ - if (!atomic_inc_not_zero(&pi_state->refcount)) { + if (!refcount_inc_not_zero(&pi_state->refcount)) { raw_spin_unlock_irq(&curr->pi_lock); cpu_relax(); raw_spin_lock_irq(&curr->pi_lock); @@ -1060,7 +1061,7 @@ static int attach_to_pi_state(u32 __user *uaddr, u32 uval, * and futex_wait_requeue_pi() as it cannot go to 0 and consequently * free pi_state before we can take a reference ourselves. */ - WARN_ON(!atomic_read(&pi_state->refcount)); + WARN_ON(!refcount_read(&pi_state->refcount)); /* * Now that we have a pi_state, we can acquire wait_lock -- cgit v1.2.3-70-g09d2