76a33061b9
The nohz full kick, which restarts the tick when any resource depend on it, can't be executed anywhere given the operation it does on timers. If it is called from the scheduler or timers code, chances are that we run into a deadlock. This is why we run the nohz full kick from an irq work. That way we make sure that the kick runs on a virgin context. However if that's the case when irq work runs in its own dedicated self-ipi, things are different for the big bunch of archs that don't support the self triggered way. In order to support them, irq works are also handled by the timer interrupt as fallback. Now when irq works run on the timer interrupt, the context isn't blank. More precisely, they can run in the context of the hrtimer that runs the tick. But the nohz kick cancels and restarts this hrtimer and cancelling an hrtimer from itself isn't allowed. This is why we run in an endless loop: Kernel panic - not syncing: Watchdog detected hard LOCKUP on cpu 2 CPU: 2 PID: 7538 Comm: kworker/u8:8 Not tainted 3.16.0+ #34 Workqueue: btrfs-endio-write normal_work_helper [btrfs] ffff880244c06c88 000000001b486fe1 ffff880244c06bf0 ffffffff8a7f1e37 ffffffff8ac52a18 ffff880244c06c78 ffffffff8a7ef928 0000000000000010 ffff880244c06c88 ffff880244c06c20 000000001b486fe1 0000000000000000 Call Trace: <NMI[<ffffffff8a7f1e37>] dump_stack+0x4e/0x7a [<ffffffff8a7ef928>] panic+0xd4/0x207 [<ffffffff8a1450e8>] watchdog_overflow_callback+0x118/0x120 [<ffffffff8a186b0e>] __perf_event_overflow+0xae/0x350 [<ffffffff8a184f80>] ? perf_event_task_disable+0xa0/0xa0 [<ffffffff8a01a4cf>] ? x86_perf_event_set_period+0xbf/0x150 [<ffffffff8a187934>] perf_event_overflow+0x14/0x20 [<ffffffff8a020386>] intel_pmu_handle_irq+0x206/0x410 [<ffffffff8a01937b>] perf_event_nmi_handler+0x2b/0x50 [<ffffffff8a007b72>] nmi_handle+0xd2/0x390 [<ffffffff8a007aa5>] ? nmi_handle+0x5/0x390 [<ffffffff8a0cb7f8>] ? match_held_lock+0x8/0x1b0 [<ffffffff8a008062>] default_do_nmi+0x72/0x1c0 [<ffffffff8a008268>] do_nmi+0xb8/0x100 [<ffffffff8a7ff66a>] end_repeat_nmi+0x1e/0x2e [<ffffffff8a0cb7f8>] ? match_held_lock+0x8/0x1b0 [<ffffffff8a0cb7f8>] ? match_held_lock+0x8/0x1b0 [<ffffffff8a0cb7f8>] ? match_held_lock+0x8/0x1b0 <<EOE><IRQ[<ffffffff8a0ccd2f>] lock_acquired+0xaf/0x450 [<ffffffff8a0f74c5>] ? lock_hrtimer_base.isra.20+0x25/0x50 [<ffffffff8a7fc678>] _raw_spin_lock_irqsave+0x78/0x90 [<ffffffff8a0f74c5>] ? lock_hrtimer_base.isra.20+0x25/0x50 [<ffffffff8a0f74c5>] lock_hrtimer_base.isra.20+0x25/0x50 [<ffffffff8a0f7723>] hrtimer_try_to_cancel+0x33/0x1e0 [<ffffffff8a0f78ea>] hrtimer_cancel+0x1a/0x30 [<ffffffff8a109237>] tick_nohz_restart+0x17/0x90 [<ffffffff8a10a213>] __tick_nohz_full_check+0xc3/0x100 [<ffffffff8a10a25e>] nohz_full_kick_work_func+0xe/0x10 [<ffffffff8a17c884>] irq_work_run_list+0x44/0x70 [<ffffffff8a17c8da>] irq_work_run+0x2a/0x50 [<ffffffff8a0f700b>] update_process_times+0x5b/0x70 [<ffffffff8a109005>] tick_sched_handle.isra.21+0x25/0x60 [<ffffffff8a109b81>] tick_sched_timer+0x41/0x60 [<ffffffff8a0f7aa2>] __run_hrtimer+0x72/0x470 [<ffffffff8a109b40>] ? tick_sched_do_timer+0xb0/0xb0 [<ffffffff8a0f8707>] hrtimer_interrupt+0x117/0x270 [<ffffffff8a034357>] local_apic_timer_interrupt+0x37/0x60 [<ffffffff8a80010f>] smp_apic_timer_interrupt+0x3f/0x50 [<ffffffff8a7fe52f>] apic_timer_interrupt+0x6f/0x80 To fix this we force non-lazy irq works to run on irq work self-IPIs when available. That ability of the arch to trigger irq work self IPIs is available with arch_irq_work_has_interrupt(). Reported-by: Catalin Iacob <iacobcatalin@gmail.com> Reported-by: Dave Jones <davej@redhat.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
197 lines
4.5 KiB
C
197 lines
4.5 KiB
C
/*
|
|
* Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
|
|
*
|
|
* Provides a framework for enqueueing and running callbacks from hardirq
|
|
* context. The enqueueing is NMI-safe.
|
|
*/
|
|
|
|
#include <linux/bug.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/export.h>
|
|
#include <linux/irq_work.h>
|
|
#include <linux/percpu.h>
|
|
#include <linux/hardirq.h>
|
|
#include <linux/irqflags.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/tick.h>
|
|
#include <linux/cpu.h>
|
|
#include <linux/notifier.h>
|
|
#include <linux/smp.h>
|
|
#include <asm/processor.h>
|
|
|
|
|
|
static DEFINE_PER_CPU(struct llist_head, raised_list);
|
|
static DEFINE_PER_CPU(struct llist_head, lazy_list);
|
|
|
|
/*
|
|
* Claim the entry so that no one else will poke at it.
|
|
*/
|
|
static bool irq_work_claim(struct irq_work *work)
|
|
{
|
|
unsigned long flags, oflags, nflags;
|
|
|
|
/*
|
|
* Start with our best wish as a premise but only trust any
|
|
* flag value after cmpxchg() result.
|
|
*/
|
|
flags = work->flags & ~IRQ_WORK_PENDING;
|
|
for (;;) {
|
|
nflags = flags | IRQ_WORK_FLAGS;
|
|
oflags = cmpxchg(&work->flags, flags, nflags);
|
|
if (oflags == flags)
|
|
break;
|
|
if (oflags & IRQ_WORK_PENDING)
|
|
return false;
|
|
flags = oflags;
|
|
cpu_relax();
|
|
}
|
|
|
|
return true;
|
|
}
|
|
|
|
void __weak arch_irq_work_raise(void)
|
|
{
|
|
/*
|
|
* Lame architectures will get the timer tick callback
|
|
*/
|
|
}
|
|
|
|
#ifdef CONFIG_SMP
|
|
/*
|
|
* Enqueue the irq_work @work on @cpu unless it's already pending
|
|
* somewhere.
|
|
*
|
|
* Can be re-enqueued while the callback is still in progress.
|
|
*/
|
|
bool irq_work_queue_on(struct irq_work *work, int cpu)
|
|
{
|
|
/* All work should have been flushed before going offline */
|
|
WARN_ON_ONCE(cpu_is_offline(cpu));
|
|
|
|
/* Arch remote IPI send/receive backend aren't NMI safe */
|
|
WARN_ON_ONCE(in_nmi());
|
|
|
|
/* Only queue if not already pending */
|
|
if (!irq_work_claim(work))
|
|
return false;
|
|
|
|
if (llist_add(&work->llnode, &per_cpu(raised_list, cpu)))
|
|
arch_send_call_function_single_ipi(cpu);
|
|
|
|
return true;
|
|
}
|
|
EXPORT_SYMBOL_GPL(irq_work_queue_on);
|
|
#endif
|
|
|
|
/* Enqueue the irq work @work on the current CPU */
|
|
bool irq_work_queue(struct irq_work *work)
|
|
{
|
|
/* Only queue if not already pending */
|
|
if (!irq_work_claim(work))
|
|
return false;
|
|
|
|
/* Queue the entry and raise the IPI if needed. */
|
|
preempt_disable();
|
|
|
|
/* If the work is "lazy", handle it from next tick if any */
|
|
if (work->flags & IRQ_WORK_LAZY) {
|
|
if (llist_add(&work->llnode, &__get_cpu_var(lazy_list)) &&
|
|
tick_nohz_tick_stopped())
|
|
arch_irq_work_raise();
|
|
} else {
|
|
if (llist_add(&work->llnode, &__get_cpu_var(raised_list)))
|
|
arch_irq_work_raise();
|
|
}
|
|
|
|
preempt_enable();
|
|
|
|
return true;
|
|
}
|
|
EXPORT_SYMBOL_GPL(irq_work_queue);
|
|
|
|
bool irq_work_needs_cpu(void)
|
|
{
|
|
struct llist_head *raised, *lazy;
|
|
|
|
raised = &__get_cpu_var(raised_list);
|
|
lazy = &__get_cpu_var(lazy_list);
|
|
|
|
if (llist_empty(raised) || arch_irq_work_has_interrupt())
|
|
if (llist_empty(lazy))
|
|
return false;
|
|
|
|
/* All work should have been flushed before going offline */
|
|
WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
|
|
|
|
return true;
|
|
}
|
|
|
|
static void irq_work_run_list(struct llist_head *list)
|
|
{
|
|
unsigned long flags;
|
|
struct irq_work *work;
|
|
struct llist_node *llnode;
|
|
|
|
BUG_ON(!irqs_disabled());
|
|
|
|
if (llist_empty(list))
|
|
return;
|
|
|
|
llnode = llist_del_all(list);
|
|
while (llnode != NULL) {
|
|
work = llist_entry(llnode, struct irq_work, llnode);
|
|
|
|
llnode = llist_next(llnode);
|
|
|
|
/*
|
|
* Clear the PENDING bit, after this point the @work
|
|
* can be re-used.
|
|
* Make it immediately visible so that other CPUs trying
|
|
* to claim that work don't rely on us to handle their data
|
|
* while we are in the middle of the func.
|
|
*/
|
|
flags = work->flags & ~IRQ_WORK_PENDING;
|
|
xchg(&work->flags, flags);
|
|
|
|
work->func(work);
|
|
/*
|
|
* Clear the BUSY bit and return to the free state if
|
|
* no-one else claimed it meanwhile.
|
|
*/
|
|
(void)cmpxchg(&work->flags, flags, flags & ~IRQ_WORK_BUSY);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* hotplug calls this through:
|
|
* hotplug_cfd() -> flush_smp_call_function_queue()
|
|
*/
|
|
void irq_work_run(void)
|
|
{
|
|
irq_work_run_list(&__get_cpu_var(raised_list));
|
|
irq_work_run_list(&__get_cpu_var(lazy_list));
|
|
}
|
|
EXPORT_SYMBOL_GPL(irq_work_run);
|
|
|
|
void irq_work_tick(void)
|
|
{
|
|
struct llist_head *raised = &__get_cpu_var(raised_list);
|
|
|
|
if (!llist_empty(raised) && !arch_irq_work_has_interrupt())
|
|
irq_work_run_list(raised);
|
|
irq_work_run_list(&__get_cpu_var(lazy_list));
|
|
}
|
|
|
|
/*
|
|
* Synchronize against the irq_work @entry, ensures the entry is not
|
|
* currently in use.
|
|
*/
|
|
void irq_work_sync(struct irq_work *work)
|
|
{
|
|
WARN_ON_ONCE(irqs_disabled());
|
|
|
|
while (work->flags & IRQ_WORK_BUSY)
|
|
cpu_relax();
|
|
}
|
|
EXPORT_SYMBOL_GPL(irq_work_sync);
|