From 01573e231f18eb2d99162747186f59511f56b64d Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Fri, 08 Dec 2023 10:40:48 +0000
Subject: [PATCH] 移去rt
---
kernel/kernel/irq_work.c | 239 ++++++++++++++++++++++++++++++++++++++---------------------
1 files changed, 153 insertions(+), 86 deletions(-)
diff --git a/kernel/kernel/irq_work.c b/kernel/kernel/irq_work.c
index b6d9d35..820798c 100644
--- a/kernel/kernel/irq_work.c
+++ b/kernel/kernel/irq_work.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra
*
@@ -17,36 +18,53 @@
#include <linux/cpu.h>
#include <linux/notifier.h>
#include <linux/smp.h>
+#include <linux/smpboot.h>
#include <linux/interrupt.h>
#include <asm/processor.h>
static DEFINE_PER_CPU(struct llist_head, raised_list);
static DEFINE_PER_CPU(struct llist_head, lazy_list);
+static DEFINE_PER_CPU(struct task_struct *, irq_workd);
+
+static void wake_irq_workd(void)
+{
+ struct task_struct *tsk = __this_cpu_read(irq_workd);
+
+ if (!llist_empty(this_cpu_ptr(&lazy_list)) && tsk)
+ wake_up_process(tsk);
+}
+
+#ifdef CONFIG_SMP
+static void irq_work_wake(struct irq_work *entry)
+{
+ wake_irq_workd();
+}
+
+static DEFINE_PER_CPU(struct irq_work, irq_work_wakeup) =
+ IRQ_WORK_INIT_HARD(irq_work_wake);
+#endif
+
+static int irq_workd_should_run(unsigned int cpu)
+{
+ return !llist_empty(this_cpu_ptr(&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;
+ int oflags;
+ oflags = atomic_fetch_or(IRQ_WORK_CLAIMED | CSD_TYPE_IRQ_WORK, &work->flags);
/*
- * Start with our best wish as a premise but only trust any
- * flag value after cmpxchg() result.
+ * 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.
*/
- flags = work->flags & ~IRQ_WORK_PENDING;
- for (;;) {
- nflags = flags | IRQ_WORK_CLAIMED;
- oflags = cmpxchg(&work->flags, flags, nflags);
- if (oflags == flags)
- break;
- if (oflags & IRQ_WORK_PENDING)
- return false;
- flags = oflags;
- cpu_relax();
- }
-
+ if (oflags & IRQ_WORK_PENDING)
+ return false;
return true;
}
@@ -58,40 +76,43 @@
}
/* Enqueue on current CPU, work must already be claimed and preempt disabled */
-static void __irq_work_queue_local(struct irq_work *work, struct llist_head *list)
+static void __irq_work_queue_local(struct irq_work *work)
{
- bool empty;
+ struct llist_head *list;
+ bool rt_lazy_work = false;
+ bool lazy_work = false;
+ int work_flags;
- empty = llist_add(&work->llnode, list);
+ work_flags = atomic_read(&work->flags);
+ if (work_flags & IRQ_WORK_LAZY)
+ lazy_work = true;
+ else if (IS_ENABLED(CONFIG_PREEMPT_RT) &&
+ !(work_flags & IRQ_WORK_HARD_IRQ))
+ rt_lazy_work = true;
- if (empty &&
- (!(work->flags & IRQ_WORK_LAZY) ||
- tick_nohz_tick_stopped()))
+ if (lazy_work || rt_lazy_work)
+ list = this_cpu_ptr(&lazy_list);
+ else
+ list = this_cpu_ptr(&raised_list);
+
+ if (!llist_add(&work->llnode, list))
+ return;
+
+ /* If the work is "lazy", handle it from next tick if any */
+ if (!lazy_work || tick_nohz_tick_stopped())
arch_irq_work_raise();
-}
-
-static inline bool use_lazy_list(struct irq_work *work)
-{
- return (IS_ENABLED(CONFIG_PREEMPT_RT_FULL) && !(work->flags & IRQ_WORK_HARD_IRQ))
- || (work->flags & IRQ_WORK_LAZY);
}
/* Enqueue the irq work @work on the current CPU */
bool irq_work_queue(struct irq_work *work)
{
- struct llist_head *list;
-
/* 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 (use_lazy_list(work))
- list = this_cpu_ptr(&lazy_list);
- else
- list = this_cpu_ptr(&raised_list);
- __irq_work_queue_local(work, list);
+ __irq_work_queue_local(work);
preempt_enable();
return true;
@@ -110,8 +131,6 @@
return irq_work_queue(work);
#else /* CONFIG_SMP: */
- struct llist_head *list;
-
/* All work should have been flushed before going offline */
WARN_ON_ONCE(cpu_is_offline(cpu));
@@ -120,25 +139,37 @@
return false;
preempt_disable();
- if (use_lazy_list(work))
- list = &per_cpu(lazy_list, cpu);
- else
- list = &per_cpu(raised_list, cpu);
-
if (cpu != smp_processor_id()) {
/* Arch remote IPI send/receive backend aren't NMI safe */
WARN_ON_ONCE(in_nmi());
- if (llist_add(&work->llnode, list))
- arch_send_call_function_single_ipi(cpu);
+
+ /*
+ * On PREEMPT_RT the items which are not marked as
+ * IRQ_WORK_HARD_IRQ are added to the lazy list and a HARD work
+ * item is used on the remote CPU to wake the thread.
+ */
+ if (IS_ENABLED(CONFIG_PREEMPT_RT) &&
+ !(atomic_read(&work->flags) & IRQ_WORK_HARD_IRQ)) {
+
+ if (!llist_add(&work->llnode, &per_cpu(lazy_list, cpu)))
+ goto out;
+
+ work = &per_cpu(irq_work_wakeup, cpu);
+ if (!irq_work_claim(work))
+ goto out;
+ }
+
+ __smp_call_single_queue(cpu, &work->llnode);
} else {
- __irq_work_queue_local(work, list);
+ __irq_work_queue_local(work);
}
+out:
preempt_enable();
return true;
#endif /* CONFIG_SMP */
}
-
+EXPORT_SYMBOL_GPL(irq_work_queue_on);
bool irq_work_needs_cpu(void)
{
@@ -156,40 +187,53 @@
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);
+
+ if ((IS_ENABLED(CONFIG_PREEMPT_RT) && !irq_work_is_hard(work)) ||
+ !arch_irq_work_has_interrupt())
+ rcuwait_wake_up(&work->irqwait);
+}
+
static void irq_work_run_list(struct llist_head *list)
{
struct irq_work *work, *tmp;
struct llist_node *llnode;
- unsigned long flags;
-#ifndef CONFIG_PREEMPT_RT_FULL
/*
- * nort: On RT IRQ-work may run in SOFTIRQ context.
+ * On PREEMPT_RT IRQ-work which is not marked as HARD will be processed
+ * in a per-CPU thread in preemptible context. Only the items which are
+ * marked as IRQ_WORK_HARD_IRQ will be processed in hardirq context.
*/
- BUG_ON(!irqs_disabled());
-#endif
+ BUG_ON(!irqs_disabled() && !IS_ENABLED(CONFIG_PREEMPT_RT));
+
if (llist_empty(list))
return;
llnode = llist_del_all(list);
- llist_for_each_entry_safe(work, tmp, llnode, 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);
- }
+ llist_for_each_entry_safe(work, tmp, llnode, llnode)
+ irq_work_single(work);
}
/*
@@ -199,16 +243,10 @@
void irq_work_run(void)
{
irq_work_run_list(this_cpu_ptr(&raised_list));
- if (IS_ENABLED(CONFIG_PREEMPT_RT_FULL)) {
- /*
- * NOTE: we raise softirq via IPI for safety,
- * and execute in irq_work_tick() to move the
- * overhead from hard to soft irq context.
- */
- if (!llist_empty(this_cpu_ptr(&lazy_list)))
- raise_softirq(TIMER_SOFTIRQ);
- } else
+ if (!IS_ENABLED(CONFIG_PREEMPT_RT))
irq_work_run_list(this_cpu_ptr(&lazy_list));
+ else
+ wake_irq_workd();
}
EXPORT_SYMBOL_GPL(irq_work_run);
@@ -219,16 +257,11 @@
if (!llist_empty(raised) && !arch_irq_work_has_interrupt())
irq_work_run_list(raised);
- if (!IS_ENABLED(CONFIG_PREEMPT_RT_FULL))
+ if (!IS_ENABLED(CONFIG_PREEMPT_RT))
irq_work_run_list(this_cpu_ptr(&lazy_list));
+ else
+ wake_irq_workd();
}
-
-#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL)
-void irq_work_tick_soft(void)
-{
- irq_work_run_list(this_cpu_ptr(&lazy_list));
-}
-#endif
/*
* Synchronize against the irq_work @entry, ensures the entry is not
@@ -237,8 +270,42 @@
void irq_work_sync(struct irq_work *work)
{
lockdep_assert_irqs_enabled();
+ might_sleep();
- while (work->flags & IRQ_WORK_BUSY)
+ if ((IS_ENABLED(CONFIG_PREEMPT_RT) && !irq_work_is_hard(work)) ||
+ !arch_irq_work_has_interrupt()) {
+ rcuwait_wait_event(&work->irqwait, !irq_work_is_busy(work),
+ TASK_UNINTERRUPTIBLE);
+ return;
+ }
+
+ while (atomic_read(&work->flags) & IRQ_WORK_BUSY)
cpu_relax();
}
EXPORT_SYMBOL_GPL(irq_work_sync);
+
+static void run_irq_workd(unsigned int cpu)
+{
+ irq_work_run_list(this_cpu_ptr(&lazy_list));
+}
+
+static void irq_workd_setup(unsigned int cpu)
+{
+ sched_set_fifo_low(current);
+}
+
+static struct smp_hotplug_thread irqwork_threads = {
+ .store = &irq_workd,
+ .setup = irq_workd_setup,
+ .thread_should_run = irq_workd_should_run,
+ .thread_fn = run_irq_workd,
+ .thread_comm = "irq_work/%u",
+};
+
+static __init int irq_work_init_threads(void)
+{
+ if (IS_ENABLED(CONFIG_PREEMPT_RT))
+ BUG_ON(smpboot_register_percpu_thread(&irqwork_threads));
+ return 0;
+}
+early_initcall(irq_work_init_threads);
--
Gitblit v1.6.2