linux/kernel/softirq.c
Tim Chen 3c829c367a [PATCH] Reducing local_bh_enable/disable overhead in irqtrace
The recent changes from irqtrace feature has added overheads to
local_bh_disable and local_bh_enable that reduces UDP performance across
x86_64 and IA64, even though IA64 does not support the irqtrace feature.
Patch in question is

[PATCH]lockdep: irqtrace subsystem, core
http://www.kernel.org/git/?p=linux/kernel/git/torvalds/linux-2.6.git;a=c
ommit;h=de30a2b355ea85350ca2f58f3b9bf4e5bc007986

Prior to this patch, local_bh_disable was a short macro.  Now it is a
function which calls __local_bh_disable with added irq flags save and
restore.  The irq flags save and restore were also added to
local_bh_enable, probably for injecting the trace irqs code.

This overhead is on the generic code path across all architectures.  On a
IA_64 test machine (Itanium-2 1.6 GHz) running a benchmark like netperf's
UDP streaming test, the added overhead results in a drop of 3% in
throughput, as udp_sendmsg calls the local_bh_enable/disable several times.

Other workloads that have heavy usages of local_bh_enable/disable could
also be affected.  The patch ideally should not have affected IA-64
performance as it does not have IRQ tracing support.  A significant portion
of the overhead is in the added irq flags save and restore, which I think
is not needed if IRQ tracing is unused.  A suggested patch is attached
below that recovers the lost performance.  However, the "ifdef"s in the
patch are a bit ugly.

Signed-off-by: Tim Chen <tim.c.chen@intel.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-07-31 13:28:42 -07:00

638 lines
14 KiB
C

/*
* linux/kernel/softirq.c
*
* Copyright (C) 1992 Linus Torvalds
*
* Rewritten. Old one was good in 2.2, but in 2.3 it was immoral. --ANK (990903)
*/
#include <linux/module.h>
#include <linux/kernel_stat.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/notifier.h>
#include <linux/percpu.h>
#include <linux/cpu.h>
#include <linux/kthread.h>
#include <linux/rcupdate.h>
#include <linux/smp.h>
#include <asm/irq.h>
/*
- No shared variables, all the data are CPU local.
- If a softirq needs serialization, let it serialize itself
by its own spinlocks.
- Even if softirq is serialized, only local cpu is marked for
execution. Hence, we get something sort of weak cpu binding.
Though it is still not clear, will it result in better locality
or will not.
Examples:
- NET RX softirq. It is multithreaded and does not require
any global serialization.
- NET TX softirq. It kicks software netdevice queues, hence
it is logically serialized per device, but this serialization
is invisible to common code.
- Tasklets: serialized wrt itself.
*/
#ifndef __ARCH_IRQ_STAT
irq_cpustat_t irq_stat[NR_CPUS] ____cacheline_aligned;
EXPORT_SYMBOL(irq_stat);
#endif
static struct softirq_action softirq_vec[32] __cacheline_aligned_in_smp;
static DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
/*
* we cannot loop indefinitely here to avoid userspace starvation,
* but we also don't want to introduce a worst case 1/HZ latency
* to the pending events, so lets the scheduler to balance
* the softirq load for us.
*/
static inline void wakeup_softirqd(void)
{
/* Interrupts are disabled: no need to stop preemption */
struct task_struct *tsk = __get_cpu_var(ksoftirqd);
if (tsk && tsk->state != TASK_RUNNING)
wake_up_process(tsk);
}
/*
* This one is for softirq.c-internal use,
* where hardirqs are disabled legitimately:
*/
#ifdef CONFIG_TRACE_IRQFLAGS
static void __local_bh_disable(unsigned long ip)
{
unsigned long flags;
WARN_ON_ONCE(in_irq());
raw_local_irq_save(flags);
add_preempt_count(SOFTIRQ_OFFSET);
/*
* Were softirqs turned off above:
*/
if (softirq_count() == SOFTIRQ_OFFSET)
trace_softirqs_off(ip);
raw_local_irq_restore(flags);
}
#else /* !CONFIG_TRACE_IRQFLAGS */
static inline void __local_bh_disable(unsigned long ip)
{
add_preempt_count(SOFTIRQ_OFFSET);
barrier();
}
#endif /* CONFIG_TRACE_IRQFLAGS */
void local_bh_disable(void)
{
__local_bh_disable((unsigned long)__builtin_return_address(0));
}
EXPORT_SYMBOL(local_bh_disable);
void __local_bh_enable(void)
{
WARN_ON_ONCE(in_irq());
/*
* softirqs should never be enabled by __local_bh_enable(),
* it always nests inside local_bh_enable() sections:
*/
WARN_ON_ONCE(softirq_count() == SOFTIRQ_OFFSET);
sub_preempt_count(SOFTIRQ_OFFSET);
}
EXPORT_SYMBOL_GPL(__local_bh_enable);
/*
* Special-case - softirqs can safely be enabled in
* cond_resched_softirq(), or by __do_softirq(),
* without processing still-pending softirqs:
*/
void _local_bh_enable(void)
{
WARN_ON_ONCE(in_irq());
WARN_ON_ONCE(!irqs_disabled());
if (softirq_count() == SOFTIRQ_OFFSET)
trace_softirqs_on((unsigned long)__builtin_return_address(0));
sub_preempt_count(SOFTIRQ_OFFSET);
}
EXPORT_SYMBOL(_local_bh_enable);
void local_bh_enable(void)
{
#ifdef CONFIG_TRACE_IRQFLAGS
unsigned long flags;
WARN_ON_ONCE(in_irq());
#endif
WARN_ON_ONCE(irqs_disabled());
#ifdef CONFIG_TRACE_IRQFLAGS
local_irq_save(flags);
#endif
/*
* Are softirqs going to be turned on now:
*/
if (softirq_count() == SOFTIRQ_OFFSET)
trace_softirqs_on((unsigned long)__builtin_return_address(0));
/*
* Keep preemption disabled until we are done with
* softirq processing:
*/
sub_preempt_count(SOFTIRQ_OFFSET - 1);
if (unlikely(!in_interrupt() && local_softirq_pending()))
do_softirq();
dec_preempt_count();
#ifdef CONFIG_TRACE_IRQFLAGS
local_irq_restore(flags);
#endif
preempt_check_resched();
}
EXPORT_SYMBOL(local_bh_enable);
void local_bh_enable_ip(unsigned long ip)
{
#ifdef CONFIG_TRACE_IRQFLAGS
unsigned long flags;
WARN_ON_ONCE(in_irq());
local_irq_save(flags);
#endif
/*
* Are softirqs going to be turned on now:
*/
if (softirq_count() == SOFTIRQ_OFFSET)
trace_softirqs_on(ip);
/*
* Keep preemption disabled until we are done with
* softirq processing:
*/
sub_preempt_count(SOFTIRQ_OFFSET - 1);
if (unlikely(!in_interrupt() && local_softirq_pending()))
do_softirq();
dec_preempt_count();
#ifdef CONFIG_TRACE_IRQFLAGS
local_irq_restore(flags);
#endif
preempt_check_resched();
}
EXPORT_SYMBOL(local_bh_enable_ip);
/*
* We restart softirq processing MAX_SOFTIRQ_RESTART times,
* and we fall back to softirqd after that.
*
* This number has been established via experimentation.
* The two things to balance is latency against fairness -
* we want to handle softirqs as soon as possible, but they
* should not be able to lock up the box.
*/
#define MAX_SOFTIRQ_RESTART 10
asmlinkage void __do_softirq(void)
{
struct softirq_action *h;
__u32 pending;
int max_restart = MAX_SOFTIRQ_RESTART;
int cpu;
pending = local_softirq_pending();
account_system_vtime(current);
__local_bh_disable((unsigned long)__builtin_return_address(0));
trace_softirq_enter();
cpu = smp_processor_id();
restart:
/* Reset the pending bitmask before enabling irqs */
set_softirq_pending(0);
local_irq_enable();
h = softirq_vec;
do {
if (pending & 1) {
h->action(h);
rcu_bh_qsctr_inc(cpu);
}
h++;
pending >>= 1;
} while (pending);
local_irq_disable();
pending = local_softirq_pending();
if (pending && --max_restart)
goto restart;
if (pending)
wakeup_softirqd();
trace_softirq_exit();
account_system_vtime(current);
_local_bh_enable();
}
#ifndef __ARCH_HAS_DO_SOFTIRQ
asmlinkage void do_softirq(void)
{
__u32 pending;
unsigned long flags;
if (in_interrupt())
return;
local_irq_save(flags);
pending = local_softirq_pending();
if (pending)
__do_softirq();
local_irq_restore(flags);
}
EXPORT_SYMBOL(do_softirq);
#endif
#ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED
# define invoke_softirq() __do_softirq()
#else
# define invoke_softirq() do_softirq()
#endif
/*
* Exit an interrupt context. Process softirqs if needed and possible:
*/
void irq_exit(void)
{
account_system_vtime(current);
trace_hardirq_exit();
sub_preempt_count(IRQ_EXIT_OFFSET);
if (!in_interrupt() && local_softirq_pending())
invoke_softirq();
preempt_enable_no_resched();
}
/*
* This function must run with irqs disabled!
*/
inline fastcall void raise_softirq_irqoff(unsigned int nr)
{
__raise_softirq_irqoff(nr);
/*
* If we're in an interrupt or softirq, we're done
* (this also catches softirq-disabled code). We will
* actually run the softirq once we return from
* the irq or softirq.
*
* Otherwise we wake up ksoftirqd to make sure we
* schedule the softirq soon.
*/
if (!in_interrupt())
wakeup_softirqd();
}
EXPORT_SYMBOL(raise_softirq_irqoff);
void fastcall raise_softirq(unsigned int nr)
{
unsigned long flags;
local_irq_save(flags);
raise_softirq_irqoff(nr);
local_irq_restore(flags);
}
void open_softirq(int nr, void (*action)(struct softirq_action*), void *data)
{
softirq_vec[nr].data = data;
softirq_vec[nr].action = action;
}
/* Tasklets */
struct tasklet_head
{
struct tasklet_struct *list;
};
/* Some compilers disobey section attribute on statics when not
initialized -- RR */
static DEFINE_PER_CPU(struct tasklet_head, tasklet_vec) = { NULL };
static DEFINE_PER_CPU(struct tasklet_head, tasklet_hi_vec) = { NULL };
void fastcall __tasklet_schedule(struct tasklet_struct *t)
{
unsigned long flags;
local_irq_save(flags);
t->next = __get_cpu_var(tasklet_vec).list;
__get_cpu_var(tasklet_vec).list = t;
raise_softirq_irqoff(TASKLET_SOFTIRQ);
local_irq_restore(flags);
}
EXPORT_SYMBOL(__tasklet_schedule);
void fastcall __tasklet_hi_schedule(struct tasklet_struct *t)
{
unsigned long flags;
local_irq_save(flags);
t->next = __get_cpu_var(tasklet_hi_vec).list;
__get_cpu_var(tasklet_hi_vec).list = t;
raise_softirq_irqoff(HI_SOFTIRQ);
local_irq_restore(flags);
}
EXPORT_SYMBOL(__tasklet_hi_schedule);
static void tasklet_action(struct softirq_action *a)
{
struct tasklet_struct *list;
local_irq_disable();
list = __get_cpu_var(tasklet_vec).list;
__get_cpu_var(tasklet_vec).list = NULL;
local_irq_enable();
while (list) {
struct tasklet_struct *t = list;
list = list->next;
if (tasklet_trylock(t)) {
if (!atomic_read(&t->count)) {
if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state))
BUG();
t->func(t->data);
tasklet_unlock(t);
continue;
}
tasklet_unlock(t);
}
local_irq_disable();
t->next = __get_cpu_var(tasklet_vec).list;
__get_cpu_var(tasklet_vec).list = t;
__raise_softirq_irqoff(TASKLET_SOFTIRQ);
local_irq_enable();
}
}
static void tasklet_hi_action(struct softirq_action *a)
{
struct tasklet_struct *list;
local_irq_disable();
list = __get_cpu_var(tasklet_hi_vec).list;
__get_cpu_var(tasklet_hi_vec).list = NULL;
local_irq_enable();
while (list) {
struct tasklet_struct *t = list;
list = list->next;
if (tasklet_trylock(t)) {
if (!atomic_read(&t->count)) {
if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state))
BUG();
t->func(t->data);
tasklet_unlock(t);
continue;
}
tasklet_unlock(t);
}
local_irq_disable();
t->next = __get_cpu_var(tasklet_hi_vec).list;
__get_cpu_var(tasklet_hi_vec).list = t;
__raise_softirq_irqoff(HI_SOFTIRQ);
local_irq_enable();
}
}
void tasklet_init(struct tasklet_struct *t,
void (*func)(unsigned long), unsigned long data)
{
t->next = NULL;
t->state = 0;
atomic_set(&t->count, 0);
t->func = func;
t->data = data;
}
EXPORT_SYMBOL(tasklet_init);
void tasklet_kill(struct tasklet_struct *t)
{
if (in_interrupt())
printk("Attempt to kill tasklet from interrupt\n");
while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) {
do
yield();
while (test_bit(TASKLET_STATE_SCHED, &t->state));
}
tasklet_unlock_wait(t);
clear_bit(TASKLET_STATE_SCHED, &t->state);
}
EXPORT_SYMBOL(tasklet_kill);
void __init softirq_init(void)
{
open_softirq(TASKLET_SOFTIRQ, tasklet_action, NULL);
open_softirq(HI_SOFTIRQ, tasklet_hi_action, NULL);
}
static int ksoftirqd(void * __bind_cpu)
{
set_user_nice(current, 19);
current->flags |= PF_NOFREEZE;
set_current_state(TASK_INTERRUPTIBLE);
while (!kthread_should_stop()) {
preempt_disable();
if (!local_softirq_pending()) {
preempt_enable_no_resched();
schedule();
preempt_disable();
}
__set_current_state(TASK_RUNNING);
while (local_softirq_pending()) {
/* Preempt disable stops cpu going offline.
If already offline, we'll be on wrong CPU:
don't process */
if (cpu_is_offline((long)__bind_cpu))
goto wait_to_die;
do_softirq();
preempt_enable_no_resched();
cond_resched();
preempt_disable();
}
preempt_enable();
set_current_state(TASK_INTERRUPTIBLE);
}
__set_current_state(TASK_RUNNING);
return 0;
wait_to_die:
preempt_enable();
/* Wait for kthread_stop */
set_current_state(TASK_INTERRUPTIBLE);
while (!kthread_should_stop()) {
schedule();
set_current_state(TASK_INTERRUPTIBLE);
}
__set_current_state(TASK_RUNNING);
return 0;
}
#ifdef CONFIG_HOTPLUG_CPU
/*
* tasklet_kill_immediate is called to remove a tasklet which can already be
* scheduled for execution on @cpu.
*
* Unlike tasklet_kill, this function removes the tasklet
* _immediately_, even if the tasklet is in TASKLET_STATE_SCHED state.
*
* When this function is called, @cpu must be in the CPU_DEAD state.
*/
void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu)
{
struct tasklet_struct **i;
BUG_ON(cpu_online(cpu));
BUG_ON(test_bit(TASKLET_STATE_RUN, &t->state));
if (!test_bit(TASKLET_STATE_SCHED, &t->state))
return;
/* CPU is dead, so no lock needed. */
for (i = &per_cpu(tasklet_vec, cpu).list; *i; i = &(*i)->next) {
if (*i == t) {
*i = t->next;
return;
}
}
BUG();
}
static void takeover_tasklets(unsigned int cpu)
{
struct tasklet_struct **i;
/* CPU is dead, so no lock needed. */
local_irq_disable();
/* Find end, append list for that CPU. */
for (i = &__get_cpu_var(tasklet_vec).list; *i; i = &(*i)->next);
*i = per_cpu(tasklet_vec, cpu).list;
per_cpu(tasklet_vec, cpu).list = NULL;
raise_softirq_irqoff(TASKLET_SOFTIRQ);
for (i = &__get_cpu_var(tasklet_hi_vec).list; *i; i = &(*i)->next);
*i = per_cpu(tasklet_hi_vec, cpu).list;
per_cpu(tasklet_hi_vec, cpu).list = NULL;
raise_softirq_irqoff(HI_SOFTIRQ);
local_irq_enable();
}
#endif /* CONFIG_HOTPLUG_CPU */
static int __cpuinit cpu_callback(struct notifier_block *nfb,
unsigned long action,
void *hcpu)
{
int hotcpu = (unsigned long)hcpu;
struct task_struct *p;
switch (action) {
case CPU_UP_PREPARE:
BUG_ON(per_cpu(tasklet_vec, hotcpu).list);
BUG_ON(per_cpu(tasklet_hi_vec, hotcpu).list);
p = kthread_create(ksoftirqd, hcpu, "ksoftirqd/%d", hotcpu);
if (IS_ERR(p)) {
printk("ksoftirqd for %i failed\n", hotcpu);
return NOTIFY_BAD;
}
kthread_bind(p, hotcpu);
per_cpu(ksoftirqd, hotcpu) = p;
break;
case CPU_ONLINE:
wake_up_process(per_cpu(ksoftirqd, hotcpu));
break;
#ifdef CONFIG_HOTPLUG_CPU
case CPU_UP_CANCELED:
if (!per_cpu(ksoftirqd, hotcpu))
break;
/* Unbind so it can run. Fall thru. */
kthread_bind(per_cpu(ksoftirqd, hotcpu),
any_online_cpu(cpu_online_map));
case CPU_DEAD:
p = per_cpu(ksoftirqd, hotcpu);
per_cpu(ksoftirqd, hotcpu) = NULL;
kthread_stop(p);
takeover_tasklets(hotcpu);
break;
#endif /* CONFIG_HOTPLUG_CPU */
}
return NOTIFY_OK;
}
static struct notifier_block __cpuinitdata cpu_nfb = {
.notifier_call = cpu_callback
};
__init int spawn_ksoftirqd(void)
{
void *cpu = (void *)(long)smp_processor_id();
cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
cpu_callback(&cpu_nfb, CPU_ONLINE, cpu);
register_cpu_notifier(&cpu_nfb);
return 0;
}
#ifdef CONFIG_SMP
/*
* Call a function on all processors
*/
int on_each_cpu(void (*func) (void *info), void *info, int retry, int wait)
{
int ret = 0;
preempt_disable();
ret = smp_call_function(func, info, retry, wait);
local_irq_disable();
func(info);
local_irq_enable();
preempt_enable();
return ret;
}
EXPORT_SYMBOL(on_each_cpu);
#endif