diff options
Diffstat (limited to 'kernel')
| -rw-r--r-- | kernel/cpu.c | 19 | ||||
| -rw-r--r-- | kernel/irq/proc.c | 5 | ||||
| -rw-r--r-- | kernel/locking/rwsem-xadd.c | 35 | ||||
| -rw-r--r-- | kernel/panic.c | 2 | ||||
| -rw-r--r-- | kernel/sched/loadavg.c | 4 | ||||
| -rw-r--r-- | kernel/signal.c | 20 | ||||
| -rw-r--r-- | kernel/time/timekeeping.c | 47 |
7 files changed, 108 insertions, 24 deletions
diff --git a/kernel/cpu.c b/kernel/cpu.c index 1a26ef5b7d58..1d6b0a209bc0 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -375,6 +375,21 @@ static int _cpu_down(unsigned int cpu, int tasks_frozen) goto out_release; } + /* + * By now we've cleared cpu_active_mask, wait for all preempt-disabled + * and RCU users of this state to go away such that all new such users + * will observe it. + * + * For CONFIG_PREEMPT we have preemptible RCU and its sync_rcu() might + * not imply sync_sched(), so wait for both. + * + * Do sync before park smpboot threads to take care the rcu boost case. + */ + if (IS_ENABLED(CONFIG_PREEMPT)) + synchronize_rcu_mult(call_rcu, call_rcu_sched); + else + synchronize_rcu(); + smpboot_park_threads(cpu); /* @@ -508,8 +523,8 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen) ret = __cpu_notify(CPU_UP_PREPARE | mod, hcpu, -1, &nr_calls); if (ret) { nr_calls--; - pr_warn("%s: attempt to bring up CPU %u failed\n", - __func__, cpu); + pr_warn_ratelimited("%s: attempt to bring up CPU %u failed\n", + __func__, cpu); goto out_notify; } diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index a24c5b909047..b05509af0352 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -114,6 +114,11 @@ static ssize_t write_irq_affinity(int type, struct file *file, goto free_cpumask; } + if (cpumask_subset(new_value, cpu_isolated_mask)) { + err = -EINVAL; + goto free_cpumask; + } + /* * Do not allow disabling IRQs completely - it's a too easy * way to make the system unusable accidentally :-) At least diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index a4d4de05b2d1..75c950ede9c7 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -511,6 +511,41 @@ struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem) unsigned long flags; /* + * If a spinner is present, there is a chance that the load of + * rwsem_has_spinner() in rwsem_wake() can be reordered with + * respect to decrement of rwsem count in __up_write() leading + * to wakeup being missed. + * + * spinning writer up_write caller + * --------------- ----------------------- + * [S] osq_unlock() [L] osq + * spin_lock(wait_lock) + * sem->count=0xFFFFFFFF00000001 + * +0xFFFFFFFF00000000 + * count=sem->count + * MB + * sem->count=0xFFFFFFFE00000001 + * -0xFFFFFFFF00000001 + * RMB + * spin_trylock(wait_lock) + * return + * rwsem_try_write_lock(count) + * spin_unlock(wait_lock) + * schedule() + * + * Reordering of atomic_long_sub_return_release() in __up_write() + * and rwsem_has_spinner() in rwsem_wake() can cause missing of + * wakeup in up_write() context. In spinning writer, sem->count + * and local variable count is 0XFFFFFFFE00000001. It would result + * in rwsem_try_write_lock() failing to acquire rwsem and spinning + * writer going to sleep in rwsem_down_write_failed(). + * + * The smp_rmb() here is to make sure that the spinner state is + * consulted after sem->count is updated in up_write context. + */ + smp_rmb(); + + /* * If a spinner is present, it is not necessary to do the wakeup. * Try to do wakeup only if the trylock succeeds to minimize * spinlock contention which may introduce too much delay in the diff --git a/kernel/panic.c b/kernel/panic.c index 982a52352cfc..679254405510 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -172,7 +172,7 @@ void panic(const char *fmt, ...) * Delay timeout seconds before rebooting the machine. * We can't use the "normal" timers since we just panicked. */ - pr_emerg("Rebooting in %d seconds..", panic_timeout); + pr_emerg("Rebooting in %d seconds..\n", panic_timeout); for (i = 0; i < panic_timeout * 1000; i += PANIC_TIMER_STEP) { touch_nmi_watchdog(); diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index b0b93fd33af9..f8e8d68ed3fd 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -201,8 +201,9 @@ void calc_load_exit_idle(void) struct rq *this_rq = this_rq(); /* - * If we're still before the sample window, we're done. + * If we're still before the pending sample window, we're done. */ + this_rq->calc_load_update = calc_load_update; if (time_before(jiffies, this_rq->calc_load_update)) return; @@ -211,7 +212,6 @@ void calc_load_exit_idle(void) * accounted through the nohz accounting, so skip the entire deal and * sync up for the next window. */ - this_rq->calc_load_update = calc_load_update; if (time_before(jiffies, this_rq->calc_load_update + 10)) this_rq->calc_load_update += LOAD_FREQ; } diff --git a/kernel/signal.c b/kernel/signal.c index f3f1f7a972fd..b92a047ddc82 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -503,7 +503,8 @@ int unhandled_signal(struct task_struct *tsk, int sig) return !tsk->ptrace; } -static void collect_signal(int sig, struct sigpending *list, siginfo_t *info) +static void collect_signal(int sig, struct sigpending *list, siginfo_t *info, + bool *resched_timer) { struct sigqueue *q, *first = NULL; @@ -525,6 +526,12 @@ static void collect_signal(int sig, struct sigpending *list, siginfo_t *info) still_pending: list_del_init(&first->list); copy_siginfo(info, &first->info); + + *resched_timer = + (first->flags & SIGQUEUE_PREALLOC) && + (info->si_code == SI_TIMER) && + (info->si_sys_private); + __sigqueue_free(first); } else { /* @@ -541,12 +548,12 @@ still_pending: } static int __dequeue_signal(struct sigpending *pending, sigset_t *mask, - siginfo_t *info) + siginfo_t *info, bool *resched_timer) { int sig = next_signal(pending, mask); if (sig) - collect_signal(sig, pending, info); + collect_signal(sig, pending, info, resched_timer); return sig; } @@ -558,15 +565,16 @@ static int __dequeue_signal(struct sigpending *pending, sigset_t *mask, */ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) { + bool resched_timer = false; int signr; /* We only dequeue private signals from ourselves, we don't let * signalfd steal them */ - signr = __dequeue_signal(&tsk->pending, mask, info); + signr = __dequeue_signal(&tsk->pending, mask, info, &resched_timer); if (!signr) { signr = __dequeue_signal(&tsk->signal->shared_pending, - mask, info); + mask, info, &resched_timer); /* * itimer signal ? * @@ -611,7 +619,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) */ current->jobctl |= JOBCTL_STOP_DEQUEUED; } - if ((info->si_code & __SI_MASK) == __SI_TIMER && info->si_sys_private) { + if (resched_timer) { /* * Release the siglock to ensure proper locking order * of timer locks outside of siglocks. Note, we leave diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 5fa544f3f560..738f3467d169 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -116,6 +116,26 @@ static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) tk->offs_boot = ktime_add(tk->offs_boot, delta); } +/* + * tk_clock_read - atomic clocksource read() helper + * + * This helper is necessary to use in the read paths because, while the + * seqlock ensures we don't return a bad value while structures are updated, + * it doesn't protect from potential crashes. There is the possibility that + * the tkr's clocksource may change between the read reference, and the + * clock reference passed to the read function. This can cause crashes if + * the wrong clocksource is passed to the wrong read function. + * This isn't necessary to use when holding the timekeeper_lock or doing + * a read of the fast-timekeeper tkrs (which is protected by its own locking + * and update logic). + */ +static inline u64 tk_clock_read(struct tk_read_base *tkr) +{ + struct clocksource *clock = READ_ONCE(tkr->clock); + + return clock->read(clock); +} + #ifdef CONFIG_DEBUG_TIMEKEEPING #define WARNING_FREQ (HZ*300) /* 5 minute rate-limiting */ @@ -173,7 +193,7 @@ static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr) */ do { seq = read_seqcount_begin(&tk_core.seq); - now = tkr->read(tkr->clock); + now = tk_clock_read(tkr); last = tkr->cycle_last; mask = tkr->mask; max = tkr->clock->max_cycles; @@ -207,7 +227,7 @@ static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr) cycle_t cycle_now, delta; /* read clocksource */ - cycle_now = tkr->read(tkr->clock); + cycle_now = tk_clock_read(tkr); /* calculate the delta since the last update_wall_time */ delta = clocksource_delta(cycle_now, tkr->cycle_last, tkr->mask); @@ -235,12 +255,10 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) old_clock = tk->tkr_mono.clock; tk->tkr_mono.clock = clock; - tk->tkr_mono.read = clock->read; tk->tkr_mono.mask = clock->mask; - tk->tkr_mono.cycle_last = tk->tkr_mono.read(clock); + tk->tkr_mono.cycle_last = tk_clock_read(&tk->tkr_mono); tk->tkr_raw.clock = clock; - tk->tkr_raw.read = clock->read; tk->tkr_raw.mask = clock->mask; tk->tkr_raw.cycle_last = tk->tkr_mono.cycle_last; @@ -404,7 +422,7 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) now += timekeeping_delta_to_ns(tkr, clocksource_delta( - tkr->read(tkr->clock), + tk_clock_read(tkr), tkr->cycle_last, tkr->mask)); } while (read_seqcount_retry(&tkf->seq, seq)); @@ -461,6 +479,10 @@ static cycle_t dummy_clock_read(struct clocksource *cs) return cycles_at_suspend; } +static struct clocksource dummy_clock = { + .read = dummy_clock_read, +}; + /** * halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource. * @tk: Timekeeper to snapshot. @@ -477,13 +499,13 @@ static void halt_fast_timekeeper(struct timekeeper *tk) struct tk_read_base *tkr = &tk->tkr_mono; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); - cycles_at_suspend = tkr->read(tkr->clock); - tkr_dummy.read = dummy_clock_read; + cycles_at_suspend = tk_clock_read(tkr); + tkr_dummy.clock = &dummy_clock; update_fast_timekeeper(&tkr_dummy, &tk_fast_mono); tkr = &tk->tkr_raw; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); - tkr_dummy.read = dummy_clock_read; + tkr_dummy.clock = &dummy_clock; update_fast_timekeeper(&tkr_dummy, &tk_fast_raw); } @@ -647,11 +669,10 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action) */ static void timekeeping_forward_now(struct timekeeper *tk) { - struct clocksource *clock = tk->tkr_mono.clock; cycle_t cycle_now, delta; s64 nsec; - cycle_now = tk->tkr_mono.read(clock); + cycle_now = tk_clock_read(&tk->tkr_mono); delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask); tk->tkr_mono.cycle_last = cycle_now; tk->tkr_raw.cycle_last = cycle_now; @@ -1434,7 +1455,7 @@ void timekeeping_resume(void) * The less preferred source will only be tried if there is no better * usable source. The rtc part is handled separately in rtc core code. */ - cycle_now = tk->tkr_mono.read(clock); + cycle_now = tk_clock_read(&tk->tkr_mono); if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) && cycle_now > tk->tkr_mono.cycle_last) { u64 num, max = ULLONG_MAX; @@ -1829,7 +1850,7 @@ void update_wall_time(void) #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET offset = real_tk->cycle_interval; #else - offset = clocksource_delta(tk->tkr_mono.read(tk->tkr_mono.clock), + offset = clocksource_delta(tk_clock_read(&tk->tkr_mono), tk->tkr_mono.cycle_last, tk->tkr_mono.mask); #endif |