mirror of
https://github.com/torvalds/linux.git
synced 2024-11-02 10:11:36 +00:00
a5ccfee05a
Tracepoints should not be called inside an rcu_idle_enter/rcu_idle_exit
region. Since pSeries calls H_CEDE in the idle loop, we were violating
this rule.
commit a7b152d534 (powerpc: Tell RCU about idle after hcall tracing)
tried to work around it by delaying the rcu_idle_enter until after we
called the hcall tracepoint, but there are a number of issues with it.
The hcall tracepoint trampoline code is called conditionally when the
tracepoint is enabled. If the tracepoint is not enabled we never call
rcu_idle_enter. The idle_uses_rcu check was also done at compile time
which breaks multiplatform builds.
The simple fix is to avoid tracing H_CEDE and rely on other tracepoints
and the hypervisor dispatch trace log to work out if we called H_CEDE.
This fixes a hang during boot on pSeries.
Signed-off-by: Anton Blanchard <anton@samba.org>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
169 lines
3.7 KiB
C
169 lines
3.7 KiB
C
/*
|
|
* Idle daemon for PowerPC. Idle daemon will handle any action
|
|
* that needs to be taken when the system becomes idle.
|
|
*
|
|
* Originally written by Cort Dougan (cort@cs.nmt.edu).
|
|
* Subsequent 32-bit hacking by Tom Rini, Armin Kuster,
|
|
* Paul Mackerras and others.
|
|
*
|
|
* iSeries supported added by Mike Corrigan <mikejc@us.ibm.com>
|
|
*
|
|
* Additional shared processor, SMT, and firmware support
|
|
* Copyright (c) 2003 Dave Engebretsen <engebret@us.ibm.com>
|
|
*
|
|
* 32-bit and 64-bit versions merged by Paul Mackerras <paulus@samba.org>
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License
|
|
* as published by the Free Software Foundation; either version
|
|
* 2 of the License, or (at your option) any later version.
|
|
*/
|
|
|
|
#include <linux/sched.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/cpu.h>
|
|
#include <linux/sysctl.h>
|
|
#include <linux/tick.h>
|
|
|
|
#include <asm/system.h>
|
|
#include <asm/processor.h>
|
|
#include <asm/cputable.h>
|
|
#include <asm/time.h>
|
|
#include <asm/machdep.h>
|
|
#include <asm/smp.h>
|
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
#define cpu_should_die() cpu_is_offline(smp_processor_id())
|
|
#else
|
|
#define cpu_should_die() 0
|
|
#endif
|
|
|
|
unsigned long cpuidle_disable = IDLE_NO_OVERRIDE;
|
|
EXPORT_SYMBOL(cpuidle_disable);
|
|
|
|
static int __init powersave_off(char *arg)
|
|
{
|
|
ppc_md.power_save = NULL;
|
|
cpuidle_disable = IDLE_POWERSAVE_OFF;
|
|
return 0;
|
|
}
|
|
__setup("powersave=off", powersave_off);
|
|
|
|
/*
|
|
* The body of the idle task.
|
|
*/
|
|
void cpu_idle(void)
|
|
{
|
|
if (ppc_md.idle_loop)
|
|
ppc_md.idle_loop(); /* doesn't return */
|
|
|
|
set_thread_flag(TIF_POLLING_NRFLAG);
|
|
while (1) {
|
|
tick_nohz_idle_enter();
|
|
rcu_idle_enter();
|
|
|
|
while (!need_resched() && !cpu_should_die()) {
|
|
ppc64_runlatch_off();
|
|
|
|
if (ppc_md.power_save) {
|
|
clear_thread_flag(TIF_POLLING_NRFLAG);
|
|
/*
|
|
* smp_mb is so clearing of TIF_POLLING_NRFLAG
|
|
* is ordered w.r.t. need_resched() test.
|
|
*/
|
|
smp_mb();
|
|
local_irq_disable();
|
|
|
|
/* Don't trace irqs off for idle */
|
|
stop_critical_timings();
|
|
|
|
/* check again after disabling irqs */
|
|
if (!need_resched() && !cpu_should_die())
|
|
ppc_md.power_save();
|
|
|
|
start_critical_timings();
|
|
|
|
local_irq_enable();
|
|
set_thread_flag(TIF_POLLING_NRFLAG);
|
|
|
|
} else {
|
|
/*
|
|
* Go into low thread priority and possibly
|
|
* low power mode.
|
|
*/
|
|
HMT_low();
|
|
HMT_very_low();
|
|
}
|
|
}
|
|
|
|
HMT_medium();
|
|
ppc64_runlatch_on();
|
|
rcu_idle_exit();
|
|
tick_nohz_idle_exit();
|
|
preempt_enable_no_resched();
|
|
if (cpu_should_die())
|
|
cpu_die();
|
|
schedule();
|
|
preempt_disable();
|
|
}
|
|
}
|
|
|
|
|
|
/*
|
|
* cpu_idle_wait - Used to ensure that all the CPUs come out of the old
|
|
* idle loop and start using the new idle loop.
|
|
* Required while changing idle handler on SMP systems.
|
|
* Caller must have changed idle handler to the new value before the call.
|
|
* This window may be larger on shared systems.
|
|
*/
|
|
void cpu_idle_wait(void)
|
|
{
|
|
int cpu;
|
|
smp_mb();
|
|
|
|
/* kick all the CPUs so that they exit out of old idle routine */
|
|
get_online_cpus();
|
|
for_each_online_cpu(cpu) {
|
|
if (cpu != smp_processor_id())
|
|
smp_send_reschedule(cpu);
|
|
}
|
|
put_online_cpus();
|
|
}
|
|
EXPORT_SYMBOL_GPL(cpu_idle_wait);
|
|
|
|
int powersave_nap;
|
|
|
|
#ifdef CONFIG_SYSCTL
|
|
/*
|
|
* Register the sysctl to set/clear powersave_nap.
|
|
*/
|
|
static ctl_table powersave_nap_ctl_table[]={
|
|
{
|
|
.procname = "powersave-nap",
|
|
.data = &powersave_nap,
|
|
.maxlen = sizeof(int),
|
|
.mode = 0644,
|
|
.proc_handler = proc_dointvec,
|
|
},
|
|
{}
|
|
};
|
|
static ctl_table powersave_nap_sysctl_root[] = {
|
|
{
|
|
.procname = "kernel",
|
|
.mode = 0555,
|
|
.child = powersave_nap_ctl_table,
|
|
},
|
|
{}
|
|
};
|
|
|
|
static int __init
|
|
register_powersave_nap_sysctl(void)
|
|
{
|
|
register_sysctl_table(powersave_nap_sysctl_root);
|
|
|
|
return 0;
|
|
}
|
|
__initcall(register_powersave_nap_sysctl);
|
|
#endif
|