mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-22 23:22:24 +07:00
4b44a21dd6
Currently irq_work_queue_on() will issue an unconditional arch_send_call_function_single_ipi() and has the handler do irq_work_run(). This is unfortunate in that it makes the IPI handler look at a second cacheline and it misses the opportunity to avoid the IPI. Instead note that struct irq_work and struct __call_single_data are very similar in layout, so use a few bits in the flags word to encode a type and stick the irq_work on the call_single_queue list. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Ingo Molnar <mingo@kernel.org> Link: https://lore.kernel.org/r/20200526161908.011635912@infradead.org
205 lines
4.8 KiB
C
205 lines
4.8 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/*
|
|
* Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra
|
|
*
|
|
* 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)
|
|
{
|
|
int oflags;
|
|
|
|
oflags = atomic_fetch_or(IRQ_WORK_CLAIMED | CSD_TYPE_IRQ_WORK, &work->flags);
|
|
/*
|
|
* If the work is already pending, no need to raise the IPI.
|
|
* The pairing atomic_fetch_andnot() in irq_work_run() makes sure
|
|
* everything we did before is visible.
|
|
*/
|
|
if (oflags & IRQ_WORK_PENDING)
|
|
return false;
|
|
return true;
|
|
}
|
|
|
|
void __weak arch_irq_work_raise(void)
|
|
{
|
|
/*
|
|
* Lame architectures will get the timer tick callback
|
|
*/
|
|
}
|
|
|
|
/* Enqueue on current CPU, work must already be claimed and preempt disabled */
|
|
static void __irq_work_queue_local(struct irq_work *work)
|
|
{
|
|
/* If the work is "lazy", handle it from next tick if any */
|
|
if (atomic_read(&work->flags) & IRQ_WORK_LAZY) {
|
|
if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) &&
|
|
tick_nohz_tick_stopped())
|
|
arch_irq_work_raise();
|
|
} else {
|
|
if (llist_add(&work->llnode, this_cpu_ptr(&raised_list)))
|
|
arch_irq_work_raise();
|
|
}
|
|
}
|
|
|
|
/* 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();
|
|
__irq_work_queue_local(work);
|
|
preempt_enable();
|
|
|
|
return true;
|
|
}
|
|
EXPORT_SYMBOL_GPL(irq_work_queue);
|
|
|
|
/*
|
|
* 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)
|
|
{
|
|
#ifndef CONFIG_SMP
|
|
return irq_work_queue(work);
|
|
|
|
#else /* CONFIG_SMP: */
|
|
/* All work should have been flushed before going offline */
|
|
WARN_ON_ONCE(cpu_is_offline(cpu));
|
|
|
|
/* Only queue if not already pending */
|
|
if (!irq_work_claim(work))
|
|
return false;
|
|
|
|
preempt_disable();
|
|
if (cpu != smp_processor_id()) {
|
|
/* Arch remote IPI send/receive backend aren't NMI safe */
|
|
WARN_ON_ONCE(in_nmi());
|
|
__smp_call_single_queue(cpu, &work->llnode);
|
|
} else {
|
|
__irq_work_queue_local(work);
|
|
}
|
|
preempt_enable();
|
|
|
|
return true;
|
|
#endif /* CONFIG_SMP */
|
|
}
|
|
|
|
|
|
bool irq_work_needs_cpu(void)
|
|
{
|
|
struct llist_head *raised, *lazy;
|
|
|
|
raised = this_cpu_ptr(&raised_list);
|
|
lazy = this_cpu_ptr(&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;
|
|
}
|
|
|
|
void irq_work_single(void *arg)
|
|
{
|
|
struct irq_work *work = arg;
|
|
int flags;
|
|
|
|
/*
|
|
* 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 = atomic_fetch_andnot(IRQ_WORK_PENDING, &work->flags);
|
|
|
|
lockdep_irq_work_enter(work);
|
|
work->func(work);
|
|
lockdep_irq_work_exit(work);
|
|
/*
|
|
* Clear the BUSY bit and return to the free state if
|
|
* no-one else claimed it meanwhile.
|
|
*/
|
|
flags &= ~IRQ_WORK_PENDING;
|
|
(void)atomic_cmpxchg(&work->flags, flags, flags & ~IRQ_WORK_BUSY);
|
|
}
|
|
|
|
static void irq_work_run_list(struct llist_head *list)
|
|
{
|
|
struct irq_work *work, *tmp;
|
|
struct llist_node *llnode;
|
|
|
|
BUG_ON(!irqs_disabled());
|
|
|
|
if (llist_empty(list))
|
|
return;
|
|
|
|
llnode = llist_del_all(list);
|
|
llist_for_each_entry_safe(work, tmp, llnode, llnode)
|
|
irq_work_single(work);
|
|
}
|
|
|
|
/*
|
|
* hotplug calls this through:
|
|
* hotplug_cfd() -> flush_smp_call_function_queue()
|
|
*/
|
|
void irq_work_run(void)
|
|
{
|
|
irq_work_run_list(this_cpu_ptr(&raised_list));
|
|
irq_work_run_list(this_cpu_ptr(&lazy_list));
|
|
}
|
|
EXPORT_SYMBOL_GPL(irq_work_run);
|
|
|
|
void irq_work_tick(void)
|
|
{
|
|
struct llist_head *raised = this_cpu_ptr(&raised_list);
|
|
|
|
if (!llist_empty(raised) && !arch_irq_work_has_interrupt())
|
|
irq_work_run_list(raised);
|
|
irq_work_run_list(this_cpu_ptr(&lazy_list));
|
|
}
|
|
|
|
/*
|
|
* Synchronize against the irq_work @entry, ensures the entry is not
|
|
* currently in use.
|
|
*/
|
|
void irq_work_sync(struct irq_work *work)
|
|
{
|
|
lockdep_assert_irqs_enabled();
|
|
|
|
while (atomic_read(&work->flags) & IRQ_WORK_BUSY)
|
|
cpu_relax();
|
|
}
|
|
EXPORT_SYMBOL_GPL(irq_work_sync);
|