linux_dsm_epyc7002/kernel/cpu/idle.c

136 lines
3.0 KiB
C
Raw Normal View History

/*
* Generic entry point for the idle threads
*/
#include <linux/sched.h>
#include <linux/cpu.h>
#include <linux/tick.h>
#include <linux/mm.h>
#include <linux/stackprotector.h>
#include <asm/tlb.h>
#include <trace/events/power.h>
static int __read_mostly cpu_idle_force_poll;
void cpu_idle_poll_ctrl(bool enable)
{
if (enable) {
cpu_idle_force_poll++;
} else {
cpu_idle_force_poll--;
WARN_ON_ONCE(cpu_idle_force_poll < 0);
}
}
#ifdef CONFIG_GENERIC_IDLE_POLL_SETUP
static int __init cpu_idle_poll_setup(char *__unused)
{
cpu_idle_force_poll = 1;
return 1;
}
__setup("nohlt", cpu_idle_poll_setup);
static int __init cpu_idle_nopoll_setup(char *__unused)
{
cpu_idle_force_poll = 0;
return 1;
}
__setup("hlt", cpu_idle_nopoll_setup);
#endif
static inline int cpu_idle_poll(void)
{
rcu/idle: Wrap cpu-idle poll mode within rcu_idle_enter/exit Bjørn Mork reported the following warning when running powertop. [ 49.289034] ------------[ cut here ]------------ [ 49.289055] WARNING: at kernel/rcutree.c:502 rcu_eqs_exit_common.isra.48+0x3d/0x125() [ 49.289244] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 3.10.0-bisect-rcu-warn+ #107 [ 49.289251] ffffffff8157d8c8 ffffffff81801e28 ffffffff8137e4e3 ffffffff81801e68 [ 49.289260] ffffffff8103094f ffffffff81801e68 0000000000000000 ffff88023afcd9b0 [ 49.289268] 0000000000000000 0140000000000000 ffff88023bee7700 ffffffff81801e78 [ 49.289276] Call Trace: [ 49.289285] [<ffffffff8137e4e3>] dump_stack+0x19/0x1b [ 49.289293] [<ffffffff8103094f>] warn_slowpath_common+0x62/0x7b [ 49.289300] [<ffffffff8103097d>] warn_slowpath_null+0x15/0x17 [ 49.289306] [<ffffffff810a9006>] rcu_eqs_exit_common.isra.48+0x3d/0x125 [ 49.289314] [<ffffffff81079b49>] ? trace_hardirqs_off_caller+0x37/0xa6 [ 49.289320] [<ffffffff810a9692>] rcu_idle_exit+0x85/0xa8 [ 49.289327] [<ffffffff8107076e>] trace_cpu_idle_rcuidle+0xae/0xff [ 49.289334] [<ffffffff810708b1>] cpu_startup_entry+0x72/0x115 [ 49.289341] [<ffffffff813689e5>] rest_init+0x149/0x150 [ 49.289347] [<ffffffff8136889c>] ? csum_partial_copy_generic+0x16c/0x16c [ 49.289355] [<ffffffff81a82d34>] start_kernel+0x3f0/0x3fd [ 49.289362] [<ffffffff81a8274c>] ? repair_env_string+0x5a/0x5a [ 49.289368] [<ffffffff81a82481>] x86_64_start_reservations+0x2a/0x2c [ 49.289375] [<ffffffff81a82550>] x86_64_start_kernel+0xcd/0xd1 [ 49.289379] ---[ end trace 07a1cc95e29e9036 ]--- The warning is that 'rdtp->dynticks' has an unexpected value, which roughly translates to - the calls to rcu_idle_enter() and rcu_idle_exit() were not made in the correct order, or otherwise messed up. And Bjørn's painstaking debugging indicated that this happens when the idle loop enters the poll mode. Looking at the poll function cpu_idle_poll(), and the implementation of trace_cpu_idle_rcuidle(), the problem becomes very clear: cpu_idle_poll() lacks calls to rcu_idle_enter/exit(), and trace_cpu_idle_rcuidle() calls them in the reverse order - first rcu_idle_exit(), and then rcu_idle_enter(). Hence the even/odd alternative sequencing of rdtp->dynticks goes for a toss. And powertop readily triggers this because powertop uses the idle-tracing infrastructure extensively. So, to fix this, wrap the code in cpu_idle_poll() within rcu_idle_enter/exit(), so that it blends properly with the calls inside trace_cpu_idle_rcuidle() and thus get the function ordering right. Reported-and-tested-by: Bjørn Mork <bjorn@mork.no> Cc: Paul McKenney <paulmck@linux.vnet.ibm.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Dipankar Sarma <dipankar@in.ibm.com> Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/519169BF.4080208@linux.vnet.ibm.com Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2013-05-14 05:31:27 +07:00
rcu_idle_enter();
trace_cpu_idle_rcuidle(0, smp_processor_id());
local_irq_enable();
while (!need_resched())
cpu_relax();
trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
rcu/idle: Wrap cpu-idle poll mode within rcu_idle_enter/exit Bjørn Mork reported the following warning when running powertop. [ 49.289034] ------------[ cut here ]------------ [ 49.289055] WARNING: at kernel/rcutree.c:502 rcu_eqs_exit_common.isra.48+0x3d/0x125() [ 49.289244] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 3.10.0-bisect-rcu-warn+ #107 [ 49.289251] ffffffff8157d8c8 ffffffff81801e28 ffffffff8137e4e3 ffffffff81801e68 [ 49.289260] ffffffff8103094f ffffffff81801e68 0000000000000000 ffff88023afcd9b0 [ 49.289268] 0000000000000000 0140000000000000 ffff88023bee7700 ffffffff81801e78 [ 49.289276] Call Trace: [ 49.289285] [<ffffffff8137e4e3>] dump_stack+0x19/0x1b [ 49.289293] [<ffffffff8103094f>] warn_slowpath_common+0x62/0x7b [ 49.289300] [<ffffffff8103097d>] warn_slowpath_null+0x15/0x17 [ 49.289306] [<ffffffff810a9006>] rcu_eqs_exit_common.isra.48+0x3d/0x125 [ 49.289314] [<ffffffff81079b49>] ? trace_hardirqs_off_caller+0x37/0xa6 [ 49.289320] [<ffffffff810a9692>] rcu_idle_exit+0x85/0xa8 [ 49.289327] [<ffffffff8107076e>] trace_cpu_idle_rcuidle+0xae/0xff [ 49.289334] [<ffffffff810708b1>] cpu_startup_entry+0x72/0x115 [ 49.289341] [<ffffffff813689e5>] rest_init+0x149/0x150 [ 49.289347] [<ffffffff8136889c>] ? csum_partial_copy_generic+0x16c/0x16c [ 49.289355] [<ffffffff81a82d34>] start_kernel+0x3f0/0x3fd [ 49.289362] [<ffffffff81a8274c>] ? repair_env_string+0x5a/0x5a [ 49.289368] [<ffffffff81a82481>] x86_64_start_reservations+0x2a/0x2c [ 49.289375] [<ffffffff81a82550>] x86_64_start_kernel+0xcd/0xd1 [ 49.289379] ---[ end trace 07a1cc95e29e9036 ]--- The warning is that 'rdtp->dynticks' has an unexpected value, which roughly translates to - the calls to rcu_idle_enter() and rcu_idle_exit() were not made in the correct order, or otherwise messed up. And Bjørn's painstaking debugging indicated that this happens when the idle loop enters the poll mode. Looking at the poll function cpu_idle_poll(), and the implementation of trace_cpu_idle_rcuidle(), the problem becomes very clear: cpu_idle_poll() lacks calls to rcu_idle_enter/exit(), and trace_cpu_idle_rcuidle() calls them in the reverse order - first rcu_idle_exit(), and then rcu_idle_enter(). Hence the even/odd alternative sequencing of rdtp->dynticks goes for a toss. And powertop readily triggers this because powertop uses the idle-tracing infrastructure extensively. So, to fix this, wrap the code in cpu_idle_poll() within rcu_idle_enter/exit(), so that it blends properly with the calls inside trace_cpu_idle_rcuidle() and thus get the function ordering right. Reported-and-tested-by: Bjørn Mork <bjorn@mork.no> Cc: Paul McKenney <paulmck@linux.vnet.ibm.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Dipankar Sarma <dipankar@in.ibm.com> Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/519169BF.4080208@linux.vnet.ibm.com Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2013-05-14 05:31:27 +07:00
rcu_idle_exit();
return 1;
}
/* Weak implementations for optional arch specific functions */
void __weak arch_cpu_idle_prepare(void) { }
void __weak arch_cpu_idle_enter(void) { }
void __weak arch_cpu_idle_exit(void) { }
void __weak arch_cpu_idle_dead(void) { }
void __weak arch_cpu_idle(void)
{
cpu_idle_force_poll = 1;
local_irq_enable();
}
/*
* Generic idle loop implementation
*/
static void cpu_idle_loop(void)
{
while (1) {
tick_nohz_idle_enter();
while (!need_resched()) {
check_pgt_cache();
rmb();
if (cpu_is_offline(smp_processor_id()))
arch_cpu_idle_dead();
local_irq_disable();
arch_cpu_idle_enter();
Merge branch 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip Pull core timer updates from Ingo Molnar: "The main changes in this cycle's merge are: - Implement shadow timekeeper to shorten in kernel reader side blocking, by Thomas Gleixner. - Posix timers enhancements by Pavel Emelyanov: - allocate timer ID per process, so that exact timer ID allocations can be re-created be checkpoint/restore code. - debuggability and tooling (/proc/PID/timers, etc.) improvements. - suspend/resume enhancements by Feng Tang: on certain new Intel Atom processors (Penwell and Cloverview), there is a feature that the TSC won't stop in S3 state, so the TSC value won't be reset to 0 after resume. This can be taken advantage of by the generic via the CLOCK_SOURCE_SUSPEND_NONSTOP flag: instead of using the RTC to recover/approximate sleep time, the main (and precise) clocksource can be used. - Fix /proc/timer_list for 4096 CPUs by Nathan Zimmer: on so many CPUs the file goes beyond 4MB of size and thus the current simplistic seqfile approach fails. Convert /proc/timer_list to a proper seq_file with its own iterator. - Cleanups and refactorings of the core timekeeping code by John Stultz. - International Atomic Clock time is managed by the NTP code internally currently but not exposed externally. Separate the TAI code out and add CLOCK_TAI support and TAI support to the hrtimer and posix-timer code, by John Stultz. - Add deep idle support enhacement to the broadcast clockevents core timer code, by Daniel Lezcano: add an opt-in CLOCK_EVT_FEAT_DYNIRQ clockevents feature (which will be utilized by future clockevents driver updates), which allows the use of IRQ affinities to avoid spurious wakeups of idle CPUs - the right CPU with an expiring timer will be woken. - Add new ARM bcm281xx clocksource driver, by Christian Daudt - ... various other fixes and cleanups" * 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (52 commits) clockevents: Set dummy handler on CPU_DEAD shutdown timekeeping: Update tk->cycle_last in resume posix-timers: Remove unused variable clockevents: Switch into oneshot mode even if broadcast registered late timer_list: Convert timer list to be a proper seq_file timer_list: Split timer_list_show_tickdevices posix-timers: Show sigevent info in proc file posix-timers: Introduce /proc/PID/timers file posix timers: Allocate timer id per process (v2) timekeeping: Make sure to notify hrtimers when TAI offset changes hrtimer: Fix ktime_add_ns() overflow on 32bit architectures hrtimer: Add expiry time overflow check in hrtimer_interrupt timekeeping: Shorten seq_count region timekeeping: Implement a shadow timekeeper timekeeping: Delay update of clock->cycle_last timekeeping: Store cycle_last value in timekeeper struct as well ntp: Remove ntp_lock, using the timekeeping locks to protect ntp state timekeeping: Simplify tai updating from do_adjtimex timekeeping: Hold timekeepering locks in do_adjtimex and hardpps timekeeping: Move ADJ_SETOFFSET to top level do_adjtimex() ...
2013-04-30 22:15:40 +07:00
/*
* In poll mode we reenable interrupts and spin.
*
* Also if we detected in the wakeup from idle
* path that the tick broadcast device expired
* for us, we don't want to go deep idle as we
* know that the IPI is going to arrive right
* away
*/
if (cpu_idle_force_poll || tick_check_broadcast_expired()) {
cpu_idle_poll();
} else {
current_clr_polling();
if (!need_resched()) {
stop_critical_timings();
rcu_idle_enter();
arch_cpu_idle();
WARN_ON_ONCE(irqs_disabled());
rcu_idle_exit();
start_critical_timings();
} else {
local_irq_enable();
}
current_set_polling();
}
arch_cpu_idle_exit();
}
tick_nohz_idle_exit();
schedule_preempt_disabled();
}
}
void cpu_startup_entry(enum cpuhp_state state)
{
/*
* This #ifdef needs to die, but it's too late in the cycle to
* make this generic (arm and sh have never invoked the canary
* init for the non boot cpus!). Will be fixed in 3.11
*/
#ifdef CONFIG_X86
/*
* If we're the non-boot CPU, nothing set the stack canary up
* for us. The boot CPU already has it initialized but no harm
* in doing it again. This is a good place for updating it, as
* we wont ever return from this function (so the invalid
* canaries already on the stack wont ever trigger).
*/
boot_init_stack_canary();
#endif
current_set_polling();
arch_cpu_idle_prepare();
cpu_idle_loop();
}