linux-pinenote/arch/powerpc/kernel/idle.c

139 lines
3 KiB
C
Raw Normal View History

/*
* 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
static int __init powersave_off(char *arg)
{
ppc_md.power_save = NULL;
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) {
nohz: Separate out irq exit and idle loop dyntick logic The tick_nohz_stop_sched_tick() function, which tries to delay the next timer tick as long as possible, can be called from two places: - From the idle loop to start the dytick idle mode - From interrupt exit if we have interrupted the dyntick idle mode, so that we reprogram the next tick event in case the irq changed some internal state that requires this action. There are only few minor differences between both that are handled by that function, driven by the ts->inidle cpu variable and the inidle parameter. The whole guarantees that we only update the dyntick mode on irq exit if we actually interrupted the dyntick idle mode, and that we enter in RCU extended quiescent state from idle loop entry only. Split this function into: - tick_nohz_idle_enter(), which sets ts->inidle to 1, enters dynticks idle mode unconditionally if it can, and enters into RCU extended quiescent state. - tick_nohz_irq_exit() which only updates the dynticks idle mode when ts->inidle is set (ie: if tick_nohz_idle_enter() has been called). To maintain symmetry, tick_nohz_restart_sched_tick() has been renamed into tick_nohz_idle_exit(). This simplifies the code and micro-optimize the irq exit path (no need for local_irq_save there). This also prepares for the split between dynticks and rcu extended quiescent state logics. We'll need this split to further fix illegal uses of RCU in extended quiescent states in the idle loop. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: David Miller <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Hans-Christian Egtvedt <hans-christian.egtvedt@atmel.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
2011-10-07 18:22:06 +02:00
tick_nohz_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();
nohz: Separate out irq exit and idle loop dyntick logic The tick_nohz_stop_sched_tick() function, which tries to delay the next timer tick as long as possible, can be called from two places: - From the idle loop to start the dytick idle mode - From interrupt exit if we have interrupted the dyntick idle mode, so that we reprogram the next tick event in case the irq changed some internal state that requires this action. There are only few minor differences between both that are handled by that function, driven by the ts->inidle cpu variable and the inidle parameter. The whole guarantees that we only update the dyntick mode on irq exit if we actually interrupted the dyntick idle mode, and that we enter in RCU extended quiescent state from idle loop entry only. Split this function into: - tick_nohz_idle_enter(), which sets ts->inidle to 1, enters dynticks idle mode unconditionally if it can, and enters into RCU extended quiescent state. - tick_nohz_irq_exit() which only updates the dynticks idle mode when ts->inidle is set (ie: if tick_nohz_idle_enter() has been called). To maintain symmetry, tick_nohz_restart_sched_tick() has been renamed into tick_nohz_idle_exit(). This simplifies the code and micro-optimize the irq exit path (no need for local_irq_save there). This also prepares for the split between dynticks and rcu extended quiescent state logics. We'll need this split to further fix illegal uses of RCU in extended quiescent states in the idle loop. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: David Miller <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Hans-Christian Egtvedt <hans-christian.egtvedt@atmel.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
2011-10-07 18:22:06 +02:00
tick_nohz_idle_exit();
powerpc: Re-enable preemption before cpu_die() start_secondary() is called shortly after _start and also via cpu_idle()->cpu_die()->pseries_mach_cpu_die() start_secondary() expects a preempt_count() of 0. pseries_mach_cpu_die() is called via the cpu_idle() routine with preemption disabled, resulting in the following repeating message during rapid cpu offline/online tests with CONFIG_PREEMPT=y: BUG: scheduling while atomic: swapper/0/0x00000002 Modules linked in: autofs4 binfmt_misc dm_mirror dm_region_hash dm_log [last unloaded: scsi_wait_scan] Call Trace: [c00000010e7079c0] [c0000000000133ec] .show_stack+0xd8/0x218 (unreliable) [c00000010e707aa0] [c0000000006a47f0] .dump_stack+0x28/0x3c [c00000010e707b20] [c00000000006e7a4] .__schedule_bug+0x7c/0x9c [c00000010e707bb0] [c000000000699d9c] .schedule+0x104/0x800 [c00000010e707cd0] [c000000000015b24] .cpu_idle+0x1c4/0x1d8 [c00000010e707d70] [c0000000006aa1b4] .start_secondary+0x398/0x3d4 [c00000010e707e30] [c000000000008278] .start_secondary_resume+0x10/0x14 Move the cpu_die() call inside the existing preemption enabled block of cpu_idle(). This is safe as the idle task is affined to a single CPU so the debug_smp_processor_id() tests (from cpu_should_die()) won't trigger as we are in a "migration disabled" region. Signed-off-by: Darren Hart <dvhltc@us.ibm.com> Acked-by: Will Schmidt <will_schmidt@vnet.ibm.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Nathan Fontenot <nfont@austin.ibm.com> Cc: Robert Jennings <rcj@linux.vnet.ibm.com> Cc: Brian King <brking@linux.vnet.ibm.com> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2010-08-04 18:28:33 +00:00
preempt_enable_no_resched();
if (cpu_should_die())
cpu_die();
schedule();
preempt_disable();
}
}
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)
{
[PATCH] sysctl: remove insert_at_head from register_sysctl The semantic effect of insert_at_head is that it would allow new registered sysctl entries to override existing sysctl entries of the same name. Which is pain for caching and the proc interface never implemented. I have done an audit and discovered that none of the current users of register_sysctl care as (excpet for directories) they do not register duplicate sysctl entries. So this patch simply removes the support for overriding existing entries in the sys_sysctl interface since no one uses it or cares and it makes future enhancments harder. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Russell King <rmk@arm.linux.org.uk> Cc: David Howells <dhowells@redhat.com> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Andi Kleen <ak@muc.de> Cc: Jens Axboe <axboe@kernel.dk> Cc: Corey Minyard <minyard@acm.org> Cc: Neil Brown <neilb@suse.de> Cc: "John W. Linville" <linville@tuxdriver.com> Cc: James Bottomley <James.Bottomley@steeleye.com> Cc: Jan Kara <jack@ucw.cz> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Mark Fasheh <mark.fasheh@oracle.com> Cc: David Chinner <dgc@sgi.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Patrick McHardy <kaber@trash.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-14 00:34:09 -08:00
register_sysctl_table(powersave_nap_sysctl_root);
return 0;
}
__initcall(register_powersave_nap_sysctl);
#endif