diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/bpf/verifier.c | 3 | ||||
-rw-r--r-- | kernel/futex.c | 69 | ||||
-rw-r--r-- | kernel/locking/qspinlock.c | 71 | ||||
-rw-r--r-- | kernel/panic.c | 6 | ||||
-rw-r--r-- | kernel/time/posix-timers.c | 5 |
5 files changed, 114 insertions, 40 deletions
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 56acfbb80104..2954e4b3abd5 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4792,6 +4792,9 @@ static int do_check(struct bpf_verifier_env *env) goto process_bpf_exit; } + if (signal_pending(current)) + return -EAGAIN; + if (need_resched()) cond_resched(); diff --git a/kernel/futex.c b/kernel/futex.c index 11fc3bb456d6..f89abca89513 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1148,11 +1148,65 @@ out_error: return ret; } +static int handle_exit_race(u32 __user *uaddr, u32 uval, + struct task_struct *tsk) +{ + u32 uval2; + + /* + * If PF_EXITPIDONE is not yet set, then try again. + */ + if (tsk && !(tsk->flags & PF_EXITPIDONE)) + return -EAGAIN; + + /* + * Reread the user space value to handle the following situation: + * + * CPU0 CPU1 + * + * sys_exit() sys_futex() + * do_exit() futex_lock_pi() + * futex_lock_pi_atomic() + * exit_signals(tsk) No waiters: + * tsk->flags |= PF_EXITING; *uaddr == 0x00000PID + * mm_release(tsk) Set waiter bit + * exit_robust_list(tsk) { *uaddr = 0x80000PID; + * Set owner died attach_to_pi_owner() { + * *uaddr = 0xC0000000; tsk = get_task(PID); + * } if (!tsk->flags & PF_EXITING) { + * ... attach(); + * tsk->flags |= PF_EXITPIDONE; } else { + * if (!(tsk->flags & PF_EXITPIDONE)) + * return -EAGAIN; + * return -ESRCH; <--- FAIL + * } + * + * Returning ESRCH unconditionally is wrong here because the + * user space value has been changed by the exiting task. + * + * The same logic applies to the case where the exiting task is + * already gone. + */ + if (get_futex_value_locked(&uval2, uaddr)) + return -EFAULT; + + /* If the user space value has changed, try again. */ + if (uval2 != uval) + return -EAGAIN; + + /* + * The exiting task did not have a robust list, the robust list was + * corrupted or the user space value in *uaddr is simply bogus. + * Give up and tell user space. + */ + return -ESRCH; +} + /* * Lookup the task for the TID provided from user space and attach to * it after doing proper sanity checks. */ -static int attach_to_pi_owner(u32 uval, union futex_key *key, +static int attach_to_pi_owner(u32 __user *uaddr, u32 uval, union futex_key *key, struct futex_pi_state **ps) { pid_t pid = uval & FUTEX_TID_MASK; @@ -1162,12 +1216,15 @@ static int attach_to_pi_owner(u32 uval, union futex_key *key, /* * We are the first waiter - try to look up the real owner and attach * the new pi_state to it, but bail out when TID = 0 [1] + * + * The !pid check is paranoid. None of the call sites should end up + * with pid == 0, but better safe than sorry. Let the caller retry */ if (!pid) - return -ESRCH; + return -EAGAIN; p = find_get_task_by_vpid(pid); if (!p) - return -ESRCH; + return handle_exit_race(uaddr, uval, NULL); if (unlikely(p->flags & PF_KTHREAD)) { put_task_struct(p); @@ -1187,7 +1244,7 @@ static int attach_to_pi_owner(u32 uval, union futex_key *key, * set, we know that the task has finished the * cleanup: */ - int ret = (p->flags & PF_EXITPIDONE) ? -ESRCH : -EAGAIN; + int ret = handle_exit_race(uaddr, uval, p); raw_spin_unlock_irq(&p->pi_lock); put_task_struct(p); @@ -1244,7 +1301,7 @@ static int lookup_pi_state(u32 __user *uaddr, u32 uval, * We are the first waiter - try to look up the owner based on * @uval and attach to it. */ - return attach_to_pi_owner(uval, key, ps); + return attach_to_pi_owner(uaddr, uval, key, ps); } static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval) @@ -1352,7 +1409,7 @@ static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb, * attach to the owner. If that fails, no harm done, we only * set the FUTEX_WAITERS bit in the user space variable. */ - return attach_to_pi_owner(uval, key, ps); + return attach_to_pi_owner(uaddr, newval, key, ps); } /** diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index bfaeb05123ff..edd75e0c7d96 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -232,6 +232,20 @@ static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail) #endif /* _Q_PENDING_BITS == 8 */ /** + * queued_fetch_set_pending_acquire - fetch the whole lock value and set pending + * @lock : Pointer to queued spinlock structure + * Return: The previous lock value + * + * *,*,* -> *,1,* + */ +#ifndef queued_fetch_set_pending_acquire +static __always_inline u32 queued_fetch_set_pending_acquire(struct qspinlock *lock) +{ + return atomic_fetch_or_acquire(_Q_PENDING_VAL, &lock->val); +} +#endif + +/** * set_locked - Set the lock bit and own the lock * @lock: Pointer to queued spinlock structure * @@ -329,40 +343,39 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val) * 0,0,0 -> 0,0,1 ; trylock * 0,0,1 -> 0,1,1 ; pending */ - val = atomic_fetch_or_acquire(_Q_PENDING_VAL, &lock->val); - if (!(val & ~_Q_LOCKED_MASK)) { - /* - * We're pending, wait for the owner to go away. - * - * *,1,1 -> *,1,0 - * - * this wait loop must be a load-acquire such that we match the - * store-release that clears the locked bit and create lock - * sequentiality; this is because not all - * clear_pending_set_locked() implementations imply full - * barriers. - */ - if (val & _Q_LOCKED_MASK) { - atomic_cond_read_acquire(&lock->val, - !(VAL & _Q_LOCKED_MASK)); - } + val = queued_fetch_set_pending_acquire(lock); - /* - * take ownership and clear the pending bit. - * - * *,1,0 -> *,0,1 - */ - clear_pending_set_locked(lock); - qstat_inc(qstat_lock_pending, true); - return; + /* + * If we observe any contention; undo and queue. + */ + if (unlikely(val & ~_Q_LOCKED_MASK)) { + if (!(val & _Q_PENDING_MASK)) + clear_pending(lock); + goto queue; } /* - * If pending was clear but there are waiters in the queue, then - * we need to undo our setting of pending before we queue ourselves. + * We're pending, wait for the owner to go away. + * + * 0,1,1 -> 0,1,0 + * + * this wait loop must be a load-acquire such that we match the + * store-release that clears the locked bit and create lock + * sequentiality; this is because not all + * clear_pending_set_locked() implementations imply full + * barriers. + */ + if (val & _Q_LOCKED_MASK) + atomic_cond_read_acquire(&lock->val, !(VAL & _Q_LOCKED_MASK)); + + /* + * take ownership and clear the pending bit. + * + * 0,1,0 -> 0,0,1 */ - if (!(val & _Q_PENDING_MASK)) - clear_pending(lock); + clear_pending_set_locked(lock); + qstat_inc(qstat_lock_pending, true); + return; /* * End of pending bit optimistic spinning and beginning of MCS diff --git a/kernel/panic.c b/kernel/panic.c index 8b2e002d52eb..6a6df23acd1a 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -14,6 +14,7 @@ #include <linux/kmsg_dump.h> #include <linux/kallsyms.h> #include <linux/notifier.h> +#include <linux/vt_kern.h> #include <linux/module.h> #include <linux/random.h> #include <linux/ftrace.h> @@ -233,7 +234,10 @@ void panic(const char *fmt, ...) if (_crash_kexec_post_notifiers) __crash_kexec(NULL); - bust_spinlocks(0); +#ifdef CONFIG_VT + unblank_screen(); +#endif + console_unblank(); /* * We may have ended up stopping the CPU holding the lock (in diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 4b9127e95430..5a01c4fdbfef 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -289,9 +289,6 @@ static void common_hrtimer_rearm(struct k_itimer *timr) { struct hrtimer *timer = &timr->it.real.timer; - if (!timr->it_interval) - return; - timr->it_overrun += hrtimer_forward(timer, timer->base->get_time(), timr->it_interval); hrtimer_restart(timer); @@ -317,7 +314,7 @@ void posixtimer_rearm(struct siginfo *info) if (!timr) return; - if (timr->it_requeue_pending == info->si_sys_private) { + if (timr->it_interval && timr->it_requeue_pending == info->si_sys_private) { timr->kclock->timer_rearm(timr); timr->it_active = 1; |