From dc434e056fe1dada20df7ba07f32739d3a701adf Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 14 Mar 2017 16:06:45 +0100 Subject: cpu/hotplug: Serialize callback invocations proper The setup/remove_state/instance() functions in the hotplug core code are serialized against concurrent CPU hotplug, but unfortunately not serialized against themself. As a consequence a concurrent invocation of these function results in corruption of the callback machinery because two instances try to invoke callbacks on remote cpus at the same time. This results in missing callback invocations and initiator threads waiting forever on the completion. The obvious solution to replace get_cpu_online() with cpu_hotplug_begin() is not possible because at least one callsite calls into these functions from a get_online_cpu() locked region. Extend the protection scope of the cpuhp_state_mutex from solely protecting the state arrays to cover the callback invocation machinery as well. Fixes: 5b7aa87e0482 ("cpu/hotplug: Implement setup/removal interface") Reported-and-tested-by: Bart Van Assche Signed-off-by: Sebastian Andrzej Siewior Cc: hpa@zytor.com Cc: mingo@kernel.org Cc: akpm@linux-foundation.org Cc: torvalds@linux-foundation.org Link: http://lkml.kernel.org/r/20170314150645.g4tdyoszlcbajmna@linutronix.de Signed-off-by: Thomas Gleixner --- kernel/cpu.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) (limited to 'kernel') diff --git a/kernel/cpu.c b/kernel/cpu.c index f7c063239fa5..37b223e4fc05 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1335,26 +1335,21 @@ static int cpuhp_store_callbacks(enum cpuhp_state state, const char *name, struct cpuhp_step *sp; int ret = 0; - mutex_lock(&cpuhp_state_mutex); - if (state == CPUHP_AP_ONLINE_DYN || state == CPUHP_BP_PREPARE_DYN) { ret = cpuhp_reserve_state(state); if (ret < 0) - goto out; + return ret; state = ret; } sp = cpuhp_get_step(state); - if (name && sp->name) { - ret = -EBUSY; - goto out; - } + if (name && sp->name) + return -EBUSY; + sp->startup.single = startup; sp->teardown.single = teardown; sp->name = name; sp->multi_instance = multi_instance; INIT_HLIST_HEAD(&sp->list); -out: - mutex_unlock(&cpuhp_state_mutex); return ret; } @@ -1428,6 +1423,7 @@ int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node, return -EINVAL; get_online_cpus(); + mutex_lock(&cpuhp_state_mutex); if (!invoke || !sp->startup.multi) goto add_node; @@ -1447,16 +1443,14 @@ int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node, if (ret) { if (sp->teardown.multi) cpuhp_rollback_install(cpu, state, node); - goto err; + goto unlock; } } add_node: ret = 0; - mutex_lock(&cpuhp_state_mutex); hlist_add_head(node, &sp->list); +unlock: mutex_unlock(&cpuhp_state_mutex); - -err: put_online_cpus(); return ret; } @@ -1491,6 +1485,7 @@ int __cpuhp_setup_state(enum cpuhp_state state, return -EINVAL; get_online_cpus(); + mutex_lock(&cpuhp_state_mutex); ret = cpuhp_store_callbacks(state, name, startup, teardown, multi_instance); @@ -1524,6 +1519,7 @@ int __cpuhp_setup_state(enum cpuhp_state state, } } out: + mutex_unlock(&cpuhp_state_mutex); put_online_cpus(); /* * If the requested state is CPUHP_AP_ONLINE_DYN, return the @@ -1547,6 +1543,8 @@ int __cpuhp_state_remove_instance(enum cpuhp_state state, return -EINVAL; get_online_cpus(); + mutex_lock(&cpuhp_state_mutex); + if (!invoke || !cpuhp_get_teardown_cb(state)) goto remove; /* @@ -1563,7 +1561,6 @@ int __cpuhp_state_remove_instance(enum cpuhp_state state, } remove: - mutex_lock(&cpuhp_state_mutex); hlist_del(node); mutex_unlock(&cpuhp_state_mutex); put_online_cpus(); @@ -1571,6 +1568,7 @@ remove: return 0; } EXPORT_SYMBOL_GPL(__cpuhp_state_remove_instance); + /** * __cpuhp_remove_state - Remove the callbacks for an hotplug machine state * @state: The state to remove @@ -1589,6 +1587,7 @@ void __cpuhp_remove_state(enum cpuhp_state state, bool invoke) get_online_cpus(); + mutex_lock(&cpuhp_state_mutex); if (sp->multi_instance) { WARN(!hlist_empty(&sp->list), "Error: Removing state %d which has instances left.\n", @@ -1613,6 +1612,7 @@ void __cpuhp_remove_state(enum cpuhp_state state, bool invoke) } remove: cpuhp_store_callbacks(state, NULL, NULL, NULL, false); + mutex_unlock(&cpuhp_state_mutex); put_online_cpus(); } EXPORT_SYMBOL(__cpuhp_remove_state); -- cgit v1.2.3 From c236c8e95a3d395b0494e7108f0d41cf36ec107c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Sat, 4 Mar 2017 10:27:18 +0100 Subject: futex: Fix potential use-after-free in FUTEX_REQUEUE_PI While working on the futex code, I stumbled over this potential use-after-free scenario. Dmitry triggered it later with syzkaller. pi_mutex is a pointer into pi_state, which we drop the reference on in unqueue_me_pi(). So any access to that pointer after that is bad. Since other sites already do rt_mutex_unlock() with hb->lock held, see for example futex_lock_pi(), simply move the unlock before unqueue_me_pi(). Reported-by: Dmitry Vyukov Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Darren Hart 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 Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/20170304093558.801744246@infradead.org Signed-off-by: Thomas Gleixner --- kernel/futex.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/kernel/futex.c b/kernel/futex.c index 229a744b1781..3a4775fd7468 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -2815,7 +2815,6 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, { struct hrtimer_sleeper timeout, *to = NULL; struct rt_mutex_waiter rt_waiter; - struct rt_mutex *pi_mutex = NULL; struct futex_hash_bucket *hb; union futex_key key2 = FUTEX_KEY_INIT; struct futex_q q = futex_q_init; @@ -2907,6 +2906,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, spin_unlock(q.lock_ptr); } } else { + struct rt_mutex *pi_mutex; + /* * We have been woken up by futex_unlock_pi(), a timeout, or a * signal. futex_unlock_pi() will not destroy the lock_ptr nor @@ -2930,18 +2931,19 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, if (res) ret = (res < 0) ? res : 0; + /* + * If fixup_pi_state_owner() faulted and was unable to handle + * the fault, unlock the rt_mutex and return the fault to + * userspace. + */ + if (ret && rt_mutex_owner(pi_mutex) == current) + rt_mutex_unlock(pi_mutex); + /* Unqueue and drop the lock. */ unqueue_me_pi(&q); } - /* - * If fixup_pi_state_owner() faulted and was unable to handle the - * fault, unlock the rt_mutex and return the fault to userspace. - */ - if (ret == -EFAULT) { - if (pi_mutex && rt_mutex_owner(pi_mutex) == current) - rt_mutex_unlock(pi_mutex); - } else if (ret == -EINTR) { + if (ret == -EINTR) { /* * We've already been requeued, but cannot restart by calling * futex_lock_pi() directly. We could restart this syscall, but -- cgit v1.2.3 From 9bbb25afeb182502ca4f2c4f3f88af0681b34cae Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Sat, 4 Mar 2017 10:27:19 +0100 Subject: futex: Add missing error handling to FUTEX_REQUEUE_PI Thomas spotted that fixup_pi_state_owner() can return errors and we fail to unlock the rt_mutex in that case. Reported-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Darren Hart 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 Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/20170304093558.867401760@infradead.org Signed-off-by: Thomas Gleixner --- kernel/futex.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/futex.c b/kernel/futex.c index 3a4775fd7468..45858ec73941 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -2898,6 +2898,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, if (q.pi_state && (q.pi_state->owner != current)) { spin_lock(q.lock_ptr); ret = fixup_pi_state_owner(uaddr2, &q, current); + if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current) + rt_mutex_unlock(&q.pi_state->pi_mutex); /* * Drop the reference to the pi state which * the requeue_pi() code acquired for us. -- cgit v1.2.3 From dcc3b5ffe1b32771c9a22e2c916fb94c4fcf5b79 Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Mon, 6 Mar 2017 21:51:28 -0800 Subject: sched/deadline: Add missing update_rq_clock() in dl_task_timer() The following warning can be triggered by hot-unplugging the CPU on which an active SCHED_DEADLINE task is running on: ------------[ cut here ]------------ WARNING: CPU: 7 PID: 0 at kernel/sched/sched.h:833 replenish_dl_entity+0x71e/0xc40 rq->clock_update_flags < RQCF_ACT_SKIP CPU: 7 PID: 0 Comm: swapper/7 Tainted: G B 4.11.0-rc1+ #24 Hardware name: LENOVO ThinkCentre M8500t-N000/SHARKBAY, BIOS FBKTC1AUS 02/16/2016 Call Trace: dump_stack+0x85/0xc4 __warn+0x172/0x1b0 warn_slowpath_fmt+0xb4/0xf0 ? __warn+0x1b0/0x1b0 ? debug_check_no_locks_freed+0x2c0/0x2c0 ? cpudl_set+0x3d/0x2b0 replenish_dl_entity+0x71e/0xc40 enqueue_task_dl+0x2ea/0x12e0 ? dl_task_timer+0x777/0x990 ? __hrtimer_run_queues+0x270/0xa50 dl_task_timer+0x316/0x990 ? enqueue_task_dl+0x12e0/0x12e0 ? enqueue_task_dl+0x12e0/0x12e0 __hrtimer_run_queues+0x270/0xa50 ? hrtimer_cancel+0x20/0x20 ? hrtimer_interrupt+0x119/0x600 hrtimer_interrupt+0x19c/0x600 ? trace_hardirqs_off+0xd/0x10 local_apic_timer_interrupt+0x74/0xe0 smp_apic_timer_interrupt+0x76/0xa0 apic_timer_interrupt+0x93/0xa0 The DL task will be migrated to a suitable later deadline rq once the DL timer fires and currnet rq is offline. The rq clock of the new rq should be updated. This patch fixes it by updating the rq clock after holding the new rq's rq lock. Signed-off-by: Wanpeng Li Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Matt Fleming Cc: Juri Lelli Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1488865888-15894-1-git-send-email-wanpeng.li@hotmail.com Signed-off-by: Ingo Molnar --- kernel/sched/deadline.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 99b2c33a9fbc..c6db3fd727fe 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -638,6 +638,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) lockdep_unpin_lock(&rq->lock, rf.cookie); rq = dl_task_offline_migration(rq, p); rf.cookie = lockdep_pin_lock(&rq->lock); + update_rq_clock(rq); /* * Now that the task has been migrated to the new RQ and we -- cgit v1.2.3 From 6e5f32f7a43f45ee55c401c0b9585eb01f9629a8 Mon Sep 17 00:00:00 2001 From: Matt Fleming Date: Fri, 17 Feb 2017 12:07:30 +0000 Subject: sched/loadavg: Avoid loadavg spikes caused by delayed NO_HZ accounting If we crossed a sample window while in NO_HZ we will add LOAD_FREQ to the pending sample window time on exit, setting the next update not one window into the future, but two. This situation on exiting NO_HZ is described by: this_rq->calc_load_update < jiffies < calc_load_update In this scenario, what we should be doing is: this_rq->calc_load_update = calc_load_update [ next window ] But what we actually do is: this_rq->calc_load_update = calc_load_update + LOAD_FREQ [ next+1 window ] This has the effect of delaying load average updates for potentially up to ~9seconds. This can result in huge spikes in the load average values due to per-cpu uninterruptible task counts being out of sync when accumulated across all CPUs. It's safe to update the per-cpu active count if we wake between sample windows because any load that we left in 'calc_load_idle' will have been zero'd when the idle load was folded in calc_global_load(). This issue is easy to reproduce before, commit 9d89c257dfb9 ("sched/fair: Rewrite runnable load and utilization average tracking") just by forking short-lived process pipelines built from ps(1) and grep(1) in a loop. I'm unable to reproduce the spikes after that commit, but the bug still seems to be present from code review. Signed-off-by: Matt Fleming Signed-off-by: Peter Zijlstra (Intel) Cc: Frederic Weisbecker Cc: Linus Torvalds Cc: Mike Galbraith Cc: Mike Galbraith Cc: Morten Rasmussen Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Vincent Guittot Fixes: commit 5167e8d ("sched/nohz: Rewrite and fix load-avg computation -- again") Link: http://lkml.kernel.org/r/20170217120731.11868-2-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar --- kernel/sched/loadavg.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index 7296b7308eca..3a55f3f9ffe4 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -202,8 +202,9 @@ 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; @@ -212,7 +213,6 @@ 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; } -- cgit v1.2.3 From caeb5882979bc6f3c8766fcf59c6269b38f521bc Mon Sep 17 00:00:00 2001 From: Matt Fleming Date: Fri, 17 Feb 2017 12:07:31 +0000 Subject: sched/loadavg: Use {READ,WRITE}_ONCE() for sample window 'calc_load_update' is accessed without any kind of locking and there's a clear assumption in the code that only a single value is read or written. Make this explicit by using READ_ONCE() and WRITE_ONCE(), and avoid unintentionally seeing multiple values, or having the load/stores split. Technically the loads in calc_global_*() don't require this since those are the only functions that update 'calc_load_update', but I've added the READ_ONCE() for consistency. Suggested-by: Peter Zijlstra Signed-off-by: Matt Fleming Signed-off-by: Peter Zijlstra (Intel) Cc: Frederic Weisbecker Cc: Linus Torvalds Cc: Mike Galbraith Cc: Mike Galbraith Cc: Morten Rasmussen Cc: Thomas Gleixner Cc: Vincent Guittot Link: http://lkml.kernel.org/r/20170217120731.11868-3-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar --- kernel/sched/loadavg.c | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index 3a55f3f9ffe4..f15fb2bdbc0d 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -169,7 +169,7 @@ static inline int calc_load_write_idx(void) * If the folding window started, make sure we start writing in the * next idle-delta. */ - if (!time_before(jiffies, calc_load_update)) + if (!time_before(jiffies, READ_ONCE(calc_load_update))) idx++; return idx & 1; @@ -204,7 +204,7 @@ void calc_load_exit_idle(void) /* * If we're still before the pending sample window, we're done. */ - this_rq->calc_load_update = calc_load_update; + this_rq->calc_load_update = READ_ONCE(calc_load_update); if (time_before(jiffies, this_rq->calc_load_update)) return; @@ -308,13 +308,15 @@ calc_load_n(unsigned long load, unsigned long exp, */ static void calc_global_nohz(void) { + unsigned long sample_window; long delta, active, n; - if (!time_before(jiffies, calc_load_update + 10)) { + sample_window = READ_ONCE(calc_load_update); + if (!time_before(jiffies, sample_window + 10)) { /* * Catch-up, fold however many we are behind still */ - delta = jiffies - calc_load_update - 10; + delta = jiffies - sample_window - 10; n = 1 + (delta / LOAD_FREQ); active = atomic_long_read(&calc_load_tasks); @@ -324,7 +326,7 @@ static void calc_global_nohz(void) avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n); avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n); - calc_load_update += n * LOAD_FREQ; + WRITE_ONCE(calc_load_update, sample_window + n * LOAD_FREQ); } /* @@ -352,9 +354,11 @@ static inline void calc_global_nohz(void) { } */ void calc_global_load(unsigned long ticks) { + unsigned long sample_window; long active, delta; - if (time_before(jiffies, calc_load_update + 10)) + sample_window = READ_ONCE(calc_load_update); + if (time_before(jiffies, sample_window + 10)) return; /* @@ -371,7 +375,7 @@ void calc_global_load(unsigned long ticks) avenrun[1] = calc_load(avenrun[1], EXP_5, active); avenrun[2] = calc_load(avenrun[2], EXP_15, active); - calc_load_update += LOAD_FREQ; + WRITE_ONCE(calc_load_update, sample_window + LOAD_FREQ); /* * In case we idled for multiple LOAD_FREQ intervals, catch up in bulk. -- cgit v1.2.3 From 17fcbd590d0c3e35bd9646e2215f86586378bc42 Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Sat, 25 Feb 2017 01:17:53 +0100 Subject: locking/rwsem: Fix down_write_killable() for CONFIG_RWSEM_GENERIC_SPINLOCK=y We hang if SIGKILL has been sent, but the task is stuck in down_read() (after do_exit()), even though no task is doing down_write() on the rwsem in question: INFO: task libupnp:21868 blocked for more than 120 seconds. libupnp D 0 21868 1 0x08100008 ... Call Trace: __schedule() schedule() __down_read() do_exit() do_group_exit() __wake_up_parent() This bug has already been fixed for CONFIG_RWSEM_XCHGADD_ALGORITHM=y in the following commit: 04cafed7fc19 ("locking/rwsem: Fix down_write_killable()") ... however, this bug also exists for CONFIG_RWSEM_GENERIC_SPINLOCK=y. Signed-off-by: Niklas Cassel Signed-off-by: Peter Zijlstra (Intel) Cc: Cc: Cc: Andrew Morton Cc: Linus Torvalds Cc: Niklas Cassel Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: d47996082f52 ("locking/rwsem: Introduce basis for down_write_killable()") Link: http://lkml.kernel.org/r/1487981873-12649-1-git-send-email-niklass@axis.com Signed-off-by: Ingo Molnar --- kernel/locking/rwsem-spinlock.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c index 7bc24d477805..c65f7989f850 100644 --- a/kernel/locking/rwsem-spinlock.c +++ b/kernel/locking/rwsem-spinlock.c @@ -213,10 +213,9 @@ int __sched __down_write_common(struct rw_semaphore *sem, int state) */ if (sem->count == 0) break; - if (signal_pending_state(state, current)) { - ret = -EINTR; - goto out; - } + if (signal_pending_state(state, current)) + goto out_nolock; + set_current_state(state); raw_spin_unlock_irqrestore(&sem->wait_lock, flags); schedule(); @@ -224,12 +223,19 @@ int __sched __down_write_common(struct rw_semaphore *sem, int state) } /* got the lock */ sem->count = -1; -out: list_del(&waiter.list); raw_spin_unlock_irqrestore(&sem->wait_lock, flags); return ret; + +out_nolock: + list_del(&waiter.list); + if (!list_empty(&sem->wait_list)) + __rwsem_do_wake(sem, 1); + raw_spin_unlock_irqrestore(&sem->wait_lock, flags); + + return -EINTR; } void __sched __down_write(struct rw_semaphore *sem) -- cgit v1.2.3 From 5ac69d37784b237707a7b15d199cdb6c6fdb6780 Mon Sep 17 00:00:00 2001 From: Daniel Bristot de Oliveira Date: Thu, 2 Mar 2017 15:10:57 +0100 Subject: sched/deadline: Make sure the replenishment timer fires in the next period Currently, the replenishment timer is set to fire at the deadline of a task. Although that works for implicit deadline tasks because the deadline is equals to the begin of the next period, that is not correct for constrained deadline tasks (deadline < period). For instance: f.c: --------------- %< --------------- int main (void) { for(;;); } --------------- >% --------------- # gcc -o f f.c # trace-cmd record -e sched:sched_switch \ -e syscalls:sys_exit_sched_setattr \ chrt -d --sched-runtime 490000000 \ --sched-deadline 500000000 \ --sched-period 1000000000 0 ./f # trace-cmd report | grep "{pid of ./f}" After setting parameters, the task is replenished and continue running until being throttled: f-11295 [003] 13322.113776: sys_exit_sched_setattr: 0x0 The task is throttled after running 492318 ms, as expected: f-11295 [003] 13322.606094: sched_switch: f:11295 [-1] R ==> watchdog/3:32 [0] But then, the task is replenished 500719 ms after the first replenishment: -0 [003] 13322.614495: sched_switch: swapper/3:0 [120] R ==> f:11295 [-1] Running for 490277 ms: f-11295 [003] 13323.104772: sched_switch: f:11295 [-1] R ==> swapper/3:0 [120] Hence, in the first period, the task runs 2 * runtime, and that is a bug. During the first replenishment, the next deadline is set one period away. So the runtime / period starts to be respected. However, as the second replenishment took place in the wrong instant, the next replenishment will also be held in a wrong instant of time. Rather than occurring in the nth period away from the first activation, it is taking place in the (nth period - relative deadline). Signed-off-by: Daniel Bristot de Oliveira Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Luca Abeni Reviewed-by: Steven Rostedt (VMware) Reviewed-by: Juri Lelli Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Romulo Silva de Oliveira Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Tommaso Cucinotta Link: http://lkml.kernel.org/r/ac50d89887c25285b47465638354b63362f8adff.1488392936.git.bristot@redhat.com Signed-off-by: Ingo Molnar --- kernel/sched/deadline.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index c6db3fd727fe..445e2787bf80 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -505,10 +505,15 @@ static void update_dl_entity(struct sched_dl_entity *dl_se, } } +static inline u64 dl_next_period(struct sched_dl_entity *dl_se) +{ + return dl_se->deadline - dl_se->dl_deadline + dl_se->dl_period; +} + /* * If the entity depleted all its runtime, and if we want it to sleep * while waiting for some new execution time to become available, we - * set the bandwidth enforcement timer to the replenishment instant + * set the bandwidth replenishment timer to the replenishment instant * and try to activate it. * * Notice that it is important for the caller to know if the timer @@ -530,7 +535,7 @@ static int start_dl_timer(struct task_struct *p) * that it is actually coming from rq->clock and not from * hrtimer's time base reading. */ - act = ns_to_ktime(dl_se->deadline); + act = ns_to_ktime(dl_next_period(dl_se)); now = hrtimer_cb_get_time(timer); delta = ktime_to_ns(now) - rq_clock(rq); act = ktime_add_ns(act, delta); -- cgit v1.2.3 From df8eac8cafce7d086be3bd5cf5a838fa37594dfb Mon Sep 17 00:00:00 2001 From: Daniel Bristot de Oliveira Date: Thu, 2 Mar 2017 15:10:58 +0100 Subject: sched/deadline: Throttle a constrained deadline task activated after the deadline During the activation, CBS checks if it can reuse the current task's runtime and period. If the deadline of the task is in the past, CBS cannot use the runtime, and so it replenishes the task. This rule works fine for implicit deadline tasks (deadline == period), and the CBS was designed for implicit deadline tasks. However, a task with constrained deadline (deadine < period) might be awakened after the deadline, but before the next period. In this case, replenishing the task would allow it to run for runtime / deadline. As in this case deadline < period, CBS enables a task to run for more than the runtime / period. In a very loaded system, this can cause a domino effect, making other tasks miss their deadlines. To avoid this problem, in the activation of a constrained deadline task after the deadline but before the next period, throttle the task and set the replenishing timer to the begin of the next period, unless it is boosted. Reproducer: --------------- %< --------------- int main (int argc, char **argv) { int ret; int flags = 0; unsigned long l = 0; struct timespec ts; struct sched_attr attr; memset(&attr, 0, sizeof(attr)); attr.size = sizeof(attr); attr.sched_policy = SCHED_DEADLINE; attr.sched_runtime = 2 * 1000 * 1000; /* 2 ms */ attr.sched_deadline = 2 * 1000 * 1000; /* 2 ms */ attr.sched_period = 2 * 1000 * 1000 * 1000; /* 2 s */ ts.tv_sec = 0; ts.tv_nsec = 2000 * 1000; /* 2 ms */ ret = sched_setattr(0, &attr, flags); if (ret < 0) { perror("sched_setattr"); exit(-1); } for(;;) { /* XXX: you may need to adjust the loop */ for (l = 0; l < 150000; l++); /* * The ideia is to go to sleep right before the deadline * and then wake up before the next period to receive * a new replenishment. */ nanosleep(&ts, NULL); } exit(0); } --------------- >% --------------- On my box, this reproducer uses almost 50% of the CPU time, which is obviously wrong for a task with 2/2000 reservation. Signed-off-by: Daniel Bristot de Oliveira Signed-off-by: Peter Zijlstra (Intel) Cc: Juri Lelli Cc: Linus Torvalds Cc: Luca Abeni Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Romulo Silva de Oliveira Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Tommaso Cucinotta Link: http://lkml.kernel.org/r/edf58354e01db46bf42df8d2dd32418833f68c89.1488392936.git.bristot@redhat.com Signed-off-by: Ingo Molnar --- kernel/sched/deadline.c | 45 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) (limited to 'kernel') diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 445e2787bf80..736d8b9d9bab 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -695,6 +695,37 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se) timer->function = dl_task_timer; } +/* + * During the activation, CBS checks if it can reuse the current task's + * runtime and period. If the deadline of the task is in the past, CBS + * cannot use the runtime, and so it replenishes the task. This rule + * works fine for implicit deadline tasks (deadline == period), and the + * CBS was designed for implicit deadline tasks. However, a task with + * constrained deadline (deadine < period) might be awakened after the + * deadline, but before the next period. In this case, replenishing the + * task would allow it to run for runtime / deadline. As in this case + * deadline < period, CBS enables a task to run for more than the + * runtime / period. In a very loaded system, this can cause a domino + * effect, making other tasks miss their deadlines. + * + * To avoid this problem, in the activation of a constrained deadline + * task after the deadline but before the next period, throttle the + * task and set the replenishing timer to the begin of the next period, + * unless it is boosted. + */ +static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se) +{ + struct task_struct *p = dl_task_of(dl_se); + struct rq *rq = rq_of_dl_rq(dl_rq_of_se(dl_se)); + + if (dl_time_before(dl_se->deadline, rq_clock(rq)) && + dl_time_before(rq_clock(rq), dl_next_period(dl_se))) { + if (unlikely(dl_se->dl_boosted || !start_dl_timer(p))) + return; + dl_se->dl_throttled = 1; + } +} + static int dl_runtime_exceeded(struct sched_dl_entity *dl_se) { @@ -928,6 +959,11 @@ static void dequeue_dl_entity(struct sched_dl_entity *dl_se) __dequeue_dl_entity(dl_se); } +static inline bool dl_is_constrained(struct sched_dl_entity *dl_se) +{ + return dl_se->dl_deadline < dl_se->dl_period; +} + static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) { struct task_struct *pi_task = rt_mutex_get_top_task(p); @@ -953,6 +989,15 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) return; } + /* + * Check if a constrained deadline task was activated + * after the deadline but before the next period. + * If that is the case, the task will be throttled and + * the replenishment timer will be set to the next period. + */ + if (!p->dl.dl_throttled && dl_is_constrained(&p->dl)) + dl_check_constrained_dl(&p->dl); + /* * If p is throttled, we do nothing. In fact, if it exhausted * its budget it needs a replenishment and, since it now is on -- cgit v1.2.3 From 2317d5f1c34913bac5971d93d69fb6c31bb74670 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 2 Mar 2017 15:10:59 +0100 Subject: sched/deadline: Use deadline instead of period when calculating overflow I was testing Daniel's changes with his test case, and tweaked it a little. Instead of having the runtime equal to the deadline, I increased the deadline ten fold. Daniel's test case had: attr.sched_runtime = 2 * 1000 * 1000; /* 2 ms */ attr.sched_deadline = 2 * 1000 * 1000; /* 2 ms */ attr.sched_period = 2 * 1000 * 1000 * 1000; /* 2 s */ To make it more interesting, I changed it to: attr.sched_runtime = 2 * 1000 * 1000; /* 2 ms */ attr.sched_deadline = 20 * 1000 * 1000; /* 20 ms */ attr.sched_period = 2 * 1000 * 1000 * 1000; /* 2 s */ The results were rather surprising. The behavior that Daniel's patch was fixing came back. The task started using much more than .1% of the CPU. More like 20%. Looking into this I found that it was due to the dl_entity_overflow() constantly returning true. That's because it uses the relative period against relative runtime vs the absolute deadline against absolute runtime. runtime / (deadline - t) > dl_runtime / dl_period There's even a comment mentioning this, and saying that when relative deadline equals relative period, that the equation is the same as using deadline instead of period. That comment is backwards! What we really want is: runtime / (deadline - t) > dl_runtime / dl_deadline We care about if the runtime can make its deadline, not its period. And then we can say "when the deadline equals the period, the equation is the same as using dl_period instead of dl_deadline". After correcting this, now when the task gets enqueued, it can throttle correctly, and Daniel's fix to the throttling of sleeping deadline tasks works even when the runtime and deadline are not the same. Signed-off-by: Steven Rostedt (VMware) Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Daniel Bristot de Oliveira Cc: Juri Lelli Cc: Linus Torvalds Cc: Luca Abeni Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Romulo Silva de Oliveira Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Tommaso Cucinotta Link: http://lkml.kernel.org/r/02135a27f1ae3fe5fd032568a5a2f370e190e8d7.1488392936.git.bristot@redhat.com Signed-off-by: Ingo Molnar --- kernel/sched/deadline.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 736d8b9d9bab..a2ce59015642 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -445,13 +445,13 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, * * This function returns true if: * - * runtime / (deadline - t) > dl_runtime / dl_period , + * runtime / (deadline - t) > dl_runtime / dl_deadline , * * IOW we can't recycle current parameters. * - * Notice that the bandwidth check is done against the period. For + * Notice that the bandwidth check is done against the deadline. For * task with deadline equal to period this is the same of using - * dl_deadline instead of dl_period in the equation above. + * dl_period instead of dl_deadline in the equation above. */ static bool dl_entity_overflow(struct sched_dl_entity *dl_se, struct sched_dl_entity *pi_se, u64 t) @@ -476,7 +476,7 @@ static bool dl_entity_overflow(struct sched_dl_entity *dl_se, * of anything below microseconds resolution is actually fiction * (but still we want to give the user that illusion >;). */ - left = (pi_se->dl_period >> DL_SCALE) * (dl_se->runtime >> DL_SCALE); + left = (pi_se->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE); right = ((dl_se->deadline - t) >> DL_SCALE) * (pi_se->dl_runtime >> DL_SCALE); -- cgit v1.2.3 From e552a8389aa409e257b7dcba74f67f128f979ccc Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 16 Mar 2017 13:47:48 +0100 Subject: perf/core: Fix use-after-free in perf_release() Dmitry reported syzcaller tripped a use-after-free in perf_release(). After much puzzlement Oleg spotted the below scenario: Task1 Task2 fork() perf_event_init_task() /* ... */ goto bad_fork_$foo; /* ... */ perf_event_free_task() mutex_lock(ctx->lock) perf_free_event(B) perf_event_release_kernel(A) mutex_lock(A->child_mutex) list_for_each_entry(child, ...) { /* child == B */ ctx = B->ctx; get_ctx(ctx); mutex_unlock(A->child_mutex); mutex_lock(A->child_mutex) list_del_init(B->child_list) mutex_unlock(A->child_mutex) /* ... */ mutex_unlock(ctx->lock); put_ctx() /* >0 */ free_task(); mutex_lock(ctx->lock); mutex_lock(A->child_mutex); /* ... */ mutex_unlock(A->child_mutex); mutex_unlock(ctx->lock) put_ctx() /* 0 */ ctx->task && !TOMBSTONE put_task_struct() /* UAF */ This patch closes the hole by making perf_event_free_task() destroy the task <-> ctx relation such that perf_event_release_kernel() will no longer observe the now dead task. Spotted-by: Oleg Nesterov Reported-by: Dmitry Vyukov Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Mathieu Desnoyers Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: fweisbec@gmail.com Cc: oleg@redhat.com Cc: stable@vger.kernel.org Fixes: c6e5b73242d2 ("perf: Synchronously clean up child events") Link: http://lkml.kernel.org/r/20170314155949.GE32474@worktop Link: http://lkml.kernel.org/r/20170316125823.140295131@infradead.org Signed-off-by: Ingo Molnar --- kernel/events/core.c | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index 1031bdf9f012..4742909c56e6 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -10415,6 +10415,17 @@ void perf_event_free_task(struct task_struct *task) continue; mutex_lock(&ctx->mutex); + raw_spin_lock_irq(&ctx->lock); + /* + * Destroy the task <-> ctx relation and mark the context dead. + * + * This is important because even though the task hasn't been + * exposed yet the context has been (through child_list). + */ + RCU_INIT_POINTER(task->perf_event_ctxp[ctxn], NULL); + WRITE_ONCE(ctx->task, TASK_TOMBSTONE); + put_task_struct(task); /* cannot be last */ + raw_spin_unlock_irq(&ctx->lock); again: list_for_each_entry_safe(event, tmp, &ctx->pinned_groups, group_entry) -- cgit v1.2.3 From e7cc4865f0f31698ef2f7aac01a50e78968985b7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 16 Mar 2017 13:47:49 +0100 Subject: perf/core: Fix event inheritance on fork() While hunting for clues to a use-after-free, Oleg spotted that perf_event_init_context() can loose an error value with the result that fork() can succeed even though we did not fully inherit the perf event context. Spotted-by: Oleg Nesterov Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: Dmitry Vyukov Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Linus Torvalds Cc: Mathieu Desnoyers Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: oleg@redhat.com Cc: stable@vger.kernel.org Fixes: 889ff0150661 ("perf/core: Split context's event group list into pinned and non-pinned lists") Link: http://lkml.kernel.org/r/20170316125823.190342547@infradead.org Signed-off-by: Ingo Molnar --- kernel/events/core.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index 4742909c56e6..fc7c9a85944d 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -10679,7 +10679,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn) ret = inherit_task_group(event, parent, parent_ctx, child, ctxn, &inherited_all); if (ret) - break; + goto out_unlock; } /* @@ -10695,7 +10695,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn) ret = inherit_task_group(event, parent, parent_ctx, child, ctxn, &inherited_all); if (ret) - break; + goto out_unlock; } raw_spin_lock_irqsave(&parent_ctx->lock, flags); @@ -10723,6 +10723,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn) } raw_spin_unlock_irqrestore(&parent_ctx->lock, flags); +out_unlock: mutex_unlock(&parent_ctx->mutex); perf_unpin_context(parent_ctx); -- cgit v1.2.3 From 15121c789e001168decac6483d192bdb7ea29e74 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 16 Mar 2017 13:47:50 +0100 Subject: perf/core: Simplify perf_event_free_task() We have ctx->event_list that contains all events; no need to repeatedly iterate the group lists to find them all. Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: Dmitry Vyukov Cc: Jiri Olsa Cc: Linus Torvalds Cc: Mathieu Desnoyers Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: fweisbec@gmail.com Link: http://lkml.kernel.org/r/20170316125823.239678244@infradead.org Signed-off-by: Ingo Molnar --- kernel/events/core.c | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index fc7c9a85944d..5f21e5e09ba4 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -10426,21 +10426,11 @@ void perf_event_free_task(struct task_struct *task) WRITE_ONCE(ctx->task, TASK_TOMBSTONE); put_task_struct(task); /* cannot be last */ raw_spin_unlock_irq(&ctx->lock); -again: - list_for_each_entry_safe(event, tmp, &ctx->pinned_groups, - group_entry) - perf_free_event(event, ctx); - list_for_each_entry_safe(event, tmp, &ctx->flexible_groups, - group_entry) + list_for_each_entry_safe(event, tmp, &ctx->event_list, event_entry) perf_free_event(event, ctx); - if (!list_empty(&ctx->pinned_groups) || - !list_empty(&ctx->flexible_groups)) - goto again; - mutex_unlock(&ctx->mutex); - put_ctx(ctx); } } -- cgit v1.2.3 From d8a8cfc76919b6c830305266b23ba671623f37ff Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 16 Mar 2017 13:47:51 +0100 Subject: perf/core: Better explain the inherit magic While going through the event inheritance code Oleg got confused. Add some comments to better explain the silent dissapearance of orphaned events. So what happens is that at perf_event_release_kernel() time; when an event looses its connection to userspace (and ceases to exist from the user's perspective) we can still have an arbitrary amount of inherited copies of the event. We want to synchronously find and remove all these child events. Since that requires a bit of lock juggling, there is the possibility that concurrent clone()s will create new child events. Therefore we first mark the parent event as DEAD, which marks all the extant child events as orphaned. We then avoid copying orphaned events; in order to avoid getting more of them. Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: Dmitry Vyukov Cc: Jiri Olsa Cc: Linus Torvalds Cc: Mathieu Desnoyers Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: fweisbec@gmail.com Link: http://lkml.kernel.org/r/20170316125823.289567442@infradead.org Signed-off-by: Ingo Molnar --- kernel/events/core.c | 36 +++++++++++++++++++++++++++++++++--- 1 file changed, 33 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index 5f21e5e09ba4..7298e149b732 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4254,7 +4254,7 @@ int perf_event_release_kernel(struct perf_event *event) raw_spin_lock_irq(&ctx->lock); /* - * Mark this even as STATE_DEAD, there is no external reference to it + * Mark this event as STATE_DEAD, there is no external reference to it * anymore. * * Anybody acquiring event->child_mutex after the below loop _must_ @@ -10468,7 +10468,12 @@ const struct perf_event_attr *perf_event_attrs(struct perf_event *event) } /* - * inherit a event from parent task to child task: + * Inherit a event from parent task to child task. + * + * Returns: + * - valid pointer on success + * - NULL for orphaned events + * - IS_ERR() on error */ static struct perf_event * inherit_event(struct perf_event *parent_event, @@ -10562,6 +10567,16 @@ inherit_event(struct perf_event *parent_event, return child_event; } +/* + * Inherits an event group. + * + * This will quietly suppress orphaned events; !inherit_event() is not an error. + * This matches with perf_event_release_kernel() removing all child events. + * + * Returns: + * - 0 on success + * - <0 on error + */ static int inherit_group(struct perf_event *parent_event, struct task_struct *parent, struct perf_event_context *parent_ctx, @@ -10576,6 +10591,11 @@ static int inherit_group(struct perf_event *parent_event, child, NULL, child_ctx); if (IS_ERR(leader)) return PTR_ERR(leader); + /* + * @leader can be NULL here because of is_orphaned_event(). In this + * case inherit_event() will create individual events, similar to what + * perf_group_detach() would do anyway. + */ list_for_each_entry(sub, &parent_event->sibling_list, group_entry) { child_ctr = inherit_event(sub, parent, parent_ctx, child, leader, child_ctx); @@ -10585,6 +10605,17 @@ static int inherit_group(struct perf_event *parent_event, return 0; } +/* + * Creates the child task context and tries to inherit the event-group. + * + * Clears @inherited_all on !attr.inherited or error. Note that we'll leave + * inherited_all set when we 'fail' to inherit an orphaned event; this is + * consistent with perf_event_release_kernel() removing all child events. + * + * Returns: + * - 0 on success + * - <0 on error + */ static int inherit_task_group(struct perf_event *event, struct task_struct *parent, struct perf_event_context *parent_ctx, @@ -10607,7 +10638,6 @@ inherit_task_group(struct perf_event *event, struct task_struct *parent, * First allocate and initialize a context for the * child. */ - child_ctx = alloc_perf_context(parent_ctx->pmu, child); if (!child_ctx) return -ENOMEM; -- cgit v1.2.3 From 55adc1d05dca9e949cdf46c747cb1e91c0e9143d Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Thu, 16 Mar 2017 16:40:30 -0700 Subject: mm: add private lock to serialize memory hotplug operations Commit bfc8c90139eb ("mem-hotplug: implement get/put_online_mems") introduced new functions get/put_online_mems() and mem_hotplug_begin/end() in order to allow similar semantics for memory hotplug like for cpu hotplug. The corresponding functions for cpu hotplug are get/put_online_cpus() and cpu_hotplug_begin/done() for cpu hotplug. The commit however missed to introduce functions that would serialize memory hotplug operations like they are done for cpu hotplug with cpu_maps_update_begin/done(). This basically leaves mem_hotplug.active_writer unprotected and allows concurrent writers to modify it, which may lead to problems as outlined by commit f931ab479dd2 ("mm: fix devm_memremap_pages crash, use mem_hotplug_{begin, done}"). That commit was extended again with commit b5d24fda9c3d ("mm, devm_memremap_pages: hold device_hotplug lock over mem_hotplug_{begin, done}") which serializes memory hotplug operations for some call sites by using the device_hotplug lock. In addition with commit 3fc21924100b ("mm: validate device_hotplug is held for memory hotplug") a sanity check was added to mem_hotplug_begin() to verify that the device_hotplug lock is held. This in turn triggers the following warning on s390: WARNING: CPU: 6 PID: 1 at drivers/base/core.c:643 assert_held_device_hotplug+0x4a/0x58 Call Trace: assert_held_device_hotplug+0x40/0x58) mem_hotplug_begin+0x34/0xc8 add_memory_resource+0x7e/0x1f8 add_memory+0xda/0x130 add_memory_merged+0x15c/0x178 sclp_detect_standby_memory+0x2ae/0x2f8 do_one_initcall+0xa2/0x150 kernel_init_freeable+0x228/0x2d8 kernel_init+0x2a/0x140 kernel_thread_starter+0x6/0xc One possible fix would be to add more lock_device_hotplug() and unlock_device_hotplug() calls around each call site of mem_hotplug_begin/end(). But that would give the device_hotplug lock additional semantics it better should not have (serialize memory hotplug operations). Instead add a new memory_add_remove_lock which has the similar semantics like cpu_add_remove_lock for cpu hotplug. To keep things hopefully a bit easier the lock will be locked and unlocked within the mem_hotplug_begin/end() functions. Link: http://lkml.kernel.org/r/20170314125226.16779-2-heiko.carstens@de.ibm.com Signed-off-by: Heiko Carstens Reported-by: Sebastian Ott Acked-by: Dan Williams Acked-by: Rafael J. Wysocki Cc: Michal Hocko Cc: Vladimir Davydov Cc: Ben Hutchings Cc: Gerald Schaefer Cc: Martin Schwidefsky Cc: Greg Kroah-Hartman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/memremap.c | 4 ---- 1 file changed, 4 deletions(-) (limited to 'kernel') diff --git a/kernel/memremap.c b/kernel/memremap.c index 06123234f118..07e85e5229da 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -247,11 +247,9 @@ static void devm_memremap_pages_release(struct device *dev, void *data) align_start = res->start & ~(SECTION_SIZE - 1); align_size = ALIGN(resource_size(res), SECTION_SIZE); - lock_device_hotplug(); mem_hotplug_begin(); arch_remove_memory(align_start, align_size); mem_hotplug_done(); - unlock_device_hotplug(); untrack_pfn(NULL, PHYS_PFN(align_start), align_size); pgmap_radix_release(res); @@ -364,11 +362,9 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, if (error) goto err_pfn_remap; - lock_device_hotplug(); mem_hotplug_begin(); error = arch_add_memory(nid, align_start, align_size, true); mem_hotplug_done(); - unlock_device_hotplug(); if (error) goto err_add_memory; -- cgit v1.2.3 From 8c290e60fa2a51806159522331c9ed41252a8fb3 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 21 Mar 2017 19:05:04 -0700 Subject: bpf: fix hashmap extra_elems logic In both kmalloc and prealloc mode the bpf_map_update_elem() is using per-cpu extra_elems to do atomic update when the map is full. There are two issues with it. The logic can be misused, since it allows max_entries+num_cpus elements to be present in the map. And alloc_extra_elems() at map creation time can fail percpu alloc for large map values with a warn: WARNING: CPU: 3 PID: 2752 at ../mm/percpu.c:892 pcpu_alloc+0x119/0xa60 illegal size (32824) or align (8) for percpu allocation The fixes for both of these issues are different for kmalloc and prealloc modes. For prealloc mode allocate extra num_possible_cpus elements and store their pointers into extra_elems array instead of actual elements. Hence we can use these hidden(spare) elements not only when the map is full but during bpf_map_update_elem() that replaces existing element too. That also improves performance, since pcpu_freelist_pop/push is avoided. Unfortunately this approach cannot be used for kmalloc mode which needs to kfree elements after rcu grace period. Therefore switch it back to normal kmalloc even when full and old element exists like it was prior to commit 6c9059817432 ("bpf: pre-allocate hash map elements"). Add tests to check for over max_entries and large map values. Reported-by: Dave Jones Fixes: 6c9059817432 ("bpf: pre-allocate hash map elements") Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Acked-by: Martin KaFai Lau Signed-off-by: David S. Miller --- kernel/bpf/hashtab.c | 144 +++++++++++++++++++++++++-------------------------- 1 file changed, 71 insertions(+), 73 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index afe5bab376c9..361a69dfe543 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -30,18 +30,12 @@ struct bpf_htab { struct pcpu_freelist freelist; struct bpf_lru lru; }; - void __percpu *extra_elems; + struct htab_elem *__percpu *extra_elems; atomic_t count; /* number of elements in this hashtable */ u32 n_buckets; /* number of hash buckets */ u32 elem_size; /* size of each element in bytes */ }; -enum extra_elem_state { - HTAB_NOT_AN_EXTRA_ELEM = 0, - HTAB_EXTRA_ELEM_FREE, - HTAB_EXTRA_ELEM_USED -}; - /* each htab element is struct htab_elem + key + value */ struct htab_elem { union { @@ -56,7 +50,6 @@ struct htab_elem { }; union { struct rcu_head rcu; - enum extra_elem_state state; struct bpf_lru_node lru_node; }; u32 hash; @@ -77,6 +70,11 @@ static bool htab_is_percpu(const struct bpf_htab *htab) htab->map.map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH; } +static bool htab_is_prealloc(const struct bpf_htab *htab) +{ + return !(htab->map.map_flags & BPF_F_NO_PREALLOC); +} + static inline void htab_elem_set_ptr(struct htab_elem *l, u32 key_size, void __percpu *pptr) { @@ -128,17 +126,20 @@ static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key, static int prealloc_init(struct bpf_htab *htab) { + u32 num_entries = htab->map.max_entries; int err = -ENOMEM, i; - htab->elems = bpf_map_area_alloc(htab->elem_size * - htab->map.max_entries); + if (!htab_is_percpu(htab) && !htab_is_lru(htab)) + num_entries += num_possible_cpus(); + + htab->elems = bpf_map_area_alloc(htab->elem_size * num_entries); if (!htab->elems) return -ENOMEM; if (!htab_is_percpu(htab)) goto skip_percpu_elems; - for (i = 0; i < htab->map.max_entries; i++) { + for (i = 0; i < num_entries; i++) { u32 size = round_up(htab->map.value_size, 8); void __percpu *pptr; @@ -166,11 +167,11 @@ skip_percpu_elems: if (htab_is_lru(htab)) bpf_lru_populate(&htab->lru, htab->elems, offsetof(struct htab_elem, lru_node), - htab->elem_size, htab->map.max_entries); + htab->elem_size, num_entries); else pcpu_freelist_populate(&htab->freelist, htab->elems + offsetof(struct htab_elem, fnode), - htab->elem_size, htab->map.max_entries); + htab->elem_size, num_entries); return 0; @@ -191,16 +192,22 @@ static void prealloc_destroy(struct bpf_htab *htab) static int alloc_extra_elems(struct bpf_htab *htab) { - void __percpu *pptr; + struct htab_elem *__percpu *pptr, *l_new; + struct pcpu_freelist_node *l; int cpu; - pptr = __alloc_percpu_gfp(htab->elem_size, 8, GFP_USER | __GFP_NOWARN); + pptr = __alloc_percpu_gfp(sizeof(struct htab_elem *), 8, + GFP_USER | __GFP_NOWARN); if (!pptr) return -ENOMEM; for_each_possible_cpu(cpu) { - ((struct htab_elem *)per_cpu_ptr(pptr, cpu))->state = - HTAB_EXTRA_ELEM_FREE; + l = pcpu_freelist_pop(&htab->freelist); + /* pop will succeed, since prealloc_init() + * preallocated extra num_possible_cpus elements + */ + l_new = container_of(l, struct htab_elem, fnode); + *per_cpu_ptr(pptr, cpu) = l_new; } htab->extra_elems = pptr; return 0; @@ -342,25 +349,25 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) raw_spin_lock_init(&htab->buckets[i].lock); } - if (!percpu && !lru) { - /* lru itself can remove the least used element, so - * there is no need for an extra elem during map_update. - */ - err = alloc_extra_elems(htab); - if (err) - goto free_buckets; - } - if (prealloc) { err = prealloc_init(htab); if (err) - goto free_extra_elems; + goto free_buckets; + + if (!percpu && !lru) { + /* lru itself can remove the least used element, so + * there is no need for an extra elem during map_update. + */ + err = alloc_extra_elems(htab); + if (err) + goto free_prealloc; + } } return &htab->map; -free_extra_elems: - free_percpu(htab->extra_elems); +free_prealloc: + prealloc_destroy(htab); free_buckets: bpf_map_area_free(htab->buckets); free_htab: @@ -575,12 +582,7 @@ static void htab_elem_free_rcu(struct rcu_head *head) static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) { - if (l->state == HTAB_EXTRA_ELEM_USED) { - l->state = HTAB_EXTRA_ELEM_FREE; - return; - } - - if (!(htab->map.map_flags & BPF_F_NO_PREALLOC)) { + if (htab_is_prealloc(htab)) { pcpu_freelist_push(&htab->freelist, &l->fnode); } else { atomic_dec(&htab->count); @@ -610,47 +612,43 @@ static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr, static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, void *value, u32 key_size, u32 hash, bool percpu, bool onallcpus, - bool old_elem_exists) + struct htab_elem *old_elem) { u32 size = htab->map.value_size; - bool prealloc = !(htab->map.map_flags & BPF_F_NO_PREALLOC); - struct htab_elem *l_new; + bool prealloc = htab_is_prealloc(htab); + struct htab_elem *l_new, **pl_new; void __percpu *pptr; - int err = 0; if (prealloc) { - struct pcpu_freelist_node *l; + if (old_elem) { + /* if we're updating the existing element, + * use per-cpu extra elems to avoid freelist_pop/push + */ + pl_new = this_cpu_ptr(htab->extra_elems); + l_new = *pl_new; + *pl_new = old_elem; + } else { + struct pcpu_freelist_node *l; - l = pcpu_freelist_pop(&htab->freelist); - if (!l) - err = -E2BIG; - else + l = pcpu_freelist_pop(&htab->freelist); + if (!l) + return ERR_PTR(-E2BIG); l_new = container_of(l, struct htab_elem, fnode); - } else { - if (atomic_inc_return(&htab->count) > htab->map.max_entries) { - atomic_dec(&htab->count); - err = -E2BIG; - } else { - l_new = kmalloc(htab->elem_size, - GFP_ATOMIC | __GFP_NOWARN); - if (!l_new) - return ERR_PTR(-ENOMEM); } - } - - if (err) { - if (!old_elem_exists) - return ERR_PTR(err); - - /* if we're updating the existing element and the hash table - * is full, use per-cpu extra elems - */ - l_new = this_cpu_ptr(htab->extra_elems); - if (l_new->state != HTAB_EXTRA_ELEM_FREE) - return ERR_PTR(-E2BIG); - l_new->state = HTAB_EXTRA_ELEM_USED; } else { - l_new->state = HTAB_NOT_AN_EXTRA_ELEM; + if (atomic_inc_return(&htab->count) > htab->map.max_entries) + if (!old_elem) { + /* when map is full and update() is replacing + * old element, it's ok to allocate, since + * old element will be freed immediately. + * Otherwise return an error + */ + atomic_dec(&htab->count); + return ERR_PTR(-E2BIG); + } + l_new = kmalloc(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN); + if (!l_new) + return ERR_PTR(-ENOMEM); } memcpy(l_new->key, key, key_size); @@ -731,7 +729,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, goto err; l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false, - !!l_old); + l_old); if (IS_ERR(l_new)) { /* all pre-allocated elements are in use or memory exhausted */ ret = PTR_ERR(l_new); @@ -744,7 +742,8 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, hlist_nulls_add_head_rcu(&l_new->hash_node, head); if (l_old) { hlist_nulls_del_rcu(&l_old->hash_node); - free_htab_elem(htab, l_old); + if (!htab_is_prealloc(htab)) + free_htab_elem(htab, l_old); } ret = 0; err: @@ -856,7 +855,7 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, value, onallcpus); } else { l_new = alloc_htab_elem(htab, key, value, key_size, - hash, true, onallcpus, false); + hash, true, onallcpus, NULL); if (IS_ERR(l_new)) { ret = PTR_ERR(l_new); goto err; @@ -1024,8 +1023,7 @@ static void delete_all_elements(struct bpf_htab *htab) hlist_nulls_for_each_entry_safe(l, n, head, hash_node) { hlist_nulls_del_rcu(&l->hash_node); - if (l->state != HTAB_EXTRA_ELEM_USED) - htab_elem_free(htab, l); + htab_elem_free(htab, l); } } } @@ -1045,7 +1043,7 @@ static void htab_map_free(struct bpf_map *map) * not have executed. Wait for them. */ rcu_barrier(); - if (htab->map.map_flags & BPF_F_NO_PREALLOC) + if (!htab_is_prealloc(htab)) delete_all_elements(htab); else prealloc_destroy(htab); -- cgit v1.2.3