OpenCloudOS-Kernel/kernel/sched/idle.c

504 lines
12 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Generic entry points for the idle threads and
* implementation of the idle task scheduling class.
*
* (NOTE: these are not related to SCHED_IDLE batch scheduled
* tasks which are handled in sched/fair.c )
*/
/* Linker adds these: start and end of __cpuidle functions */
extern char __cpuidle_text_start[], __cpuidle_text_end[];
/**
* sched_idle_set_state - Record idle state for the current CPU.
* @idle_state: State to record.
*/
void sched_idle_set_state(struct cpuidle_state *idle_state)
{
idle_set_state(this_rq(), idle_state);
}
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 noinline int __cpuidle cpu_idle_poll(void)
{
instrumentation_begin();
trace_cpu_idle(0, smp_processor_id());
stop_critical_timings();
ct_cpuidle_enter();
raw_local_irq_enable();
while (!tif_need_resched() &&
(cpu_idle_force_poll || tick_check_broadcast_expired()))
cpu_relax();
raw_local_irq_disable();
ct_cpuidle_exit();
start_critical_timings();
trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
local_irq_enable();
instrumentation_end();
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 __noreturn arch_cpu_idle_dead(void) { while (1); }
void __weak arch_cpu_idle(void)
{
cpu_idle_force_poll = 1;
}
/**
* default_idle_call - Default CPU idle routine.
*
* To use when the cpuidle framework cannot be used.
*/
void __cpuidle default_idle_call(void)
{
instrumentation_begin();
if (!current_clr_polling_and_test()) {
trace_cpu_idle(1, smp_processor_id());
stop_critical_timings();
ct_cpuidle_enter();
arch_cpu_idle();
ct_cpuidle_exit();
start_critical_timings();
trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
}
local_irq_enable();
instrumentation_end();
}
static int call_cpuidle_s2idle(struct cpuidle_driver *drv,
struct cpuidle_device *dev)
{
if (current_clr_polling_and_test())
return -EBUSY;
return cpuidle_enter_s2idle(drv, dev);
}
static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev,
int next_state)
{
/*
* The idle task must be scheduled, it is pointless to go to idle, just
* update no idle residency and return.
*/
if (current_clr_polling_and_test()) {
dev->last_residency_ns = 0;
local_irq_enable();
return -EBUSY;
}
/*
* Enter the idle state previously returned by the governor decision.
* This function will block until an interrupt occurs and will take
* care of re-enabling the local interrupts
*/
return cpuidle_enter(drv, dev, next_state);
}
/**
* cpuidle_idle_call - the main idle function
*
* NOTE: no locks or semaphores should be used here
*
* On architectures that support TIF_POLLING_NRFLAG, is called with polling
* set, and it returns with polling set. If it ever stops polling, it
* must clear the polling bit.
*/
static void cpuidle_idle_call(void)
{
struct cpuidle_device *dev = cpuidle_get_device();
struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
int next_state, entered_state;
/*
* Check if the idle task must be rescheduled. If it is the
* case, exit the function after re-enabling the local irq.
*/
if (need_resched()) {
local_irq_enable();
return;
}
/*
* The RCU framework needs to be told that we are entering an idle
* section, so no more rcu read side critical sections and one more
* step to the grace period
*/
if (cpuidle_not_available(drv, dev)) {
tick_nohz_idle_stop_tick();
default_idle_call();
goto exit_idle;
}
/*
* Suspend-to-idle ("s2idle") is a system state in which all user space
* has been frozen, all I/O devices have been suspended and the only
* activity happens here and in interrupts (if any). In that case bypass
* the cpuidle governor and go straight for the deepest idle state
* available. Possibly also suspend the local tick and the entire
* timekeeping to prevent timer interrupts from kicking us out of idle
* until a proper wakeup interrupt happens.
*/
if (idle_should_enter_s2idle() || dev->forced_idle_latency_limit_ns) {
u64 max_latency_ns;
if (idle_should_enter_s2idle()) {
entered_state = call_cpuidle_s2idle(drv, dev);
if (entered_state > 0)
goto exit_idle;
max_latency_ns = U64_MAX;
} else {
max_latency_ns = dev->forced_idle_latency_limit_ns;
}
tick_nohz_idle_stop_tick();
next_state = cpuidle_find_deepest_state(drv, dev, max_latency_ns);
call_cpuidle(drv, dev, next_state);
} else {
cpuidle: Return nohz hint from cpuidle_select() Add a new pointer argument to cpuidle_select() and to the ->select cpuidle governor callback to allow a boolean value indicating whether or not the tick should be stopped before entering the selected state to be returned from there. Make the ladder governor ignore that pointer (to preserve its current behavior) and make the menu governor return 'false" through it if: (1) the idle exit latency is constrained at 0, or (2) the selected state is a polling one, or (3) the expected idle period duration is within the tick period range. In addition to that, the correction factor computations in the menu governor need to take the possibility that the tick may not be stopped into account to avoid artificially small correction factor values. To that end, add a mechanism to record tick wakeups, as suggested by Peter Zijlstra, and use it to modify the menu_update() behavior when tick wakeup occurs. Namely, if the CPU is woken up by the tick and the return value of tick_nohz_get_sleep_length() is not within the tick boundary, the predicted idle duration is likely too short, so make menu_update() try to compensate for that by updating the governor statistics as though the CPU was idle for a long time. Since the value returned through the new argument pointer of cpuidle_select() is not used by its caller yet, this change by itself is not expected to alter the functionality of the code. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
2018-03-23 00:50:49 +08:00
bool stop_tick = true;
/*
* Ask the cpuidle framework to choose a convenient idle state.
*/
cpuidle: Return nohz hint from cpuidle_select() Add a new pointer argument to cpuidle_select() and to the ->select cpuidle governor callback to allow a boolean value indicating whether or not the tick should be stopped before entering the selected state to be returned from there. Make the ladder governor ignore that pointer (to preserve its current behavior) and make the menu governor return 'false" through it if: (1) the idle exit latency is constrained at 0, or (2) the selected state is a polling one, or (3) the expected idle period duration is within the tick period range. In addition to that, the correction factor computations in the menu governor need to take the possibility that the tick may not be stopped into account to avoid artificially small correction factor values. To that end, add a mechanism to record tick wakeups, as suggested by Peter Zijlstra, and use it to modify the menu_update() behavior when tick wakeup occurs. Namely, if the CPU is woken up by the tick and the return value of tick_nohz_get_sleep_length() is not within the tick boundary, the predicted idle duration is likely too short, so make menu_update() try to compensate for that by updating the governor statistics as though the CPU was idle for a long time. Since the value returned through the new argument pointer of cpuidle_select() is not used by its caller yet, this change by itself is not expected to alter the functionality of the code. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
2018-03-23 00:50:49 +08:00
next_state = cpuidle_select(drv, dev, &stop_tick);
sched: idle: Select idle state before stopping the tick In order to address the issue with short idle duration predictions by the idle governor after the scheduler tick has been stopped, reorder the code in cpuidle_idle_call() so that the governor idle state selection runs before tick_nohz_idle_go_idle() and use the "nohz" hint returned by cpuidle_select() to decide whether or not to stop the tick. This isn't straightforward, because menu_select() invokes tick_nohz_get_sleep_length() to get the time to the next timer event and the number returned by the latter comes from __tick_nohz_idle_stop_tick(). Fortunately, however, it is possible to compute that number without actually stopping the tick and with the help of the existing code. Namely, tick_nohz_get_sleep_length() can be made call tick_nohz_next_event(), introduced earlier, to get the time to the next non-highres timer event. If that happens, tick_nohz_next_event() need not be called by __tick_nohz_idle_stop_tick() again. If it turns out that the scheduler tick cannot be stopped going forward or the next timer event is too close for the tick to be stopped, tick_nohz_get_sleep_length() can simply return the time to the next event currently programmed into the corresponding clock event device. In addition to knowing the return value of tick_nohz_next_event(), however, tick_nohz_get_sleep_length() needs to know the time to the next highres timer event, but with the scheduler tick timer excluded, which can be computed with the help of hrtimer_get_next_event(). That minimum of that number and the tick_nohz_next_event() return value is the total time to the next timer event with the assumption that the tick will be stopped. It can be returned to the idle governor which can use it for predicting idle duration (under the assumption that the tick will be stopped) and deciding whether or not it makes sense to stop the tick before putting the CPU into the selected idle state. With the above, the sleep_length field in struct tick_sched is not necessary any more, so drop it. Link: https://bugzilla.kernel.org/show_bug.cgi?id=199227 Reported-by: Doug Smythies <dsmythies@telus.net> Reported-by: Thomas Ilsche <thomas.ilsche@tu-dresden.de> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
2018-04-04 05:17:11 +08:00
if (stop_tick || tick_nohz_tick_stopped())
sched: idle: Select idle state before stopping the tick In order to address the issue with short idle duration predictions by the idle governor after the scheduler tick has been stopped, reorder the code in cpuidle_idle_call() so that the governor idle state selection runs before tick_nohz_idle_go_idle() and use the "nohz" hint returned by cpuidle_select() to decide whether or not to stop the tick. This isn't straightforward, because menu_select() invokes tick_nohz_get_sleep_length() to get the time to the next timer event and the number returned by the latter comes from __tick_nohz_idle_stop_tick(). Fortunately, however, it is possible to compute that number without actually stopping the tick and with the help of the existing code. Namely, tick_nohz_get_sleep_length() can be made call tick_nohz_next_event(), introduced earlier, to get the time to the next non-highres timer event. If that happens, tick_nohz_next_event() need not be called by __tick_nohz_idle_stop_tick() again. If it turns out that the scheduler tick cannot be stopped going forward or the next timer event is too close for the tick to be stopped, tick_nohz_get_sleep_length() can simply return the time to the next event currently programmed into the corresponding clock event device. In addition to knowing the return value of tick_nohz_next_event(), however, tick_nohz_get_sleep_length() needs to know the time to the next highres timer event, but with the scheduler tick timer excluded, which can be computed with the help of hrtimer_get_next_event(). That minimum of that number and the tick_nohz_next_event() return value is the total time to the next timer event with the assumption that the tick will be stopped. It can be returned to the idle governor which can use it for predicting idle duration (under the assumption that the tick will be stopped) and deciding whether or not it makes sense to stop the tick before putting the CPU into the selected idle state. With the above, the sleep_length field in struct tick_sched is not necessary any more, so drop it. Link: https://bugzilla.kernel.org/show_bug.cgi?id=199227 Reported-by: Doug Smythies <dsmythies@telus.net> Reported-by: Thomas Ilsche <thomas.ilsche@tu-dresden.de> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
2018-04-04 05:17:11 +08:00
tick_nohz_idle_stop_tick();
else
tick_nohz_idle_retain_tick();
entered_state = call_cpuidle(drv, dev, next_state);
/*
* Give the governor an opportunity to reflect on the outcome
*/
cpuidle_reflect(dev, entered_state);
}
exit_idle:
__current_set_polling();
/*
* It is up to the idle functions to reenable local interrupts
*/
if (WARN_ON_ONCE(irqs_disabled()))
local_irq_enable();
}
/*
* Generic idle loop implementation
*
* Called with polling cleared.
*/
static void do_idle(void)
{
2017-10-25 19:28:27 +08:00
int cpu = smp_processor_id();
/*
* Check if we need to update blocked load
*/
nohz_run_idle_balance(cpu);
/*
* If the arch has a polling bit, we maintain an invariant:
*
* Our polling bit is clear if we're not scheduled (i.e. if rq->curr !=
* rq->idle). This means that, if rq->idle has the polling bit set,
* then setting need_resched is guaranteed to cause the CPU to
* reschedule.
*/
__current_set_polling();
tick_nohz_idle_enter();
while (!need_resched()) {
rmb();
idle: Prevent late-arriving interrupts from disrupting offline Scheduling-clock interrupts can arrive late in the CPU-offline process, after idle entry and the subsequent call to cpuhp_report_idle_dead(). Once execution passes the call to rcu_report_dead(), RCU is ignoring the CPU, which results in lockdep complaints when the interrupt handler uses RCU: ------------------------------------------------------------------------ ============================= WARNING: suspicious RCU usage 5.2.0-rc1+ #681 Not tainted ----------------------------- kernel/sched/fair.c:9542 suspicious rcu_dereference_check() usage! other info that might help us debug this: RCU used illegally from offline CPU! rcu_scheduler_active = 2, debug_locks = 1 no locks held by swapper/5/0. stack backtrace: CPU: 5 PID: 0 Comm: swapper/5 Not tainted 5.2.0-rc1+ #681 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS Bochs 01/01/2011 Call Trace: <IRQ> dump_stack+0x5e/0x8b trigger_load_balance+0xa8/0x390 ? tick_sched_do_timer+0x60/0x60 update_process_times+0x3b/0x50 tick_sched_handle+0x2f/0x40 tick_sched_timer+0x32/0x70 __hrtimer_run_queues+0xd3/0x3b0 hrtimer_interrupt+0x11d/0x270 ? sched_clock_local+0xc/0x74 smp_apic_timer_interrupt+0x79/0x200 apic_timer_interrupt+0xf/0x20 </IRQ> RIP: 0010:delay_tsc+0x22/0x50 Code: ff 0f 1f 80 00 00 00 00 65 44 8b 05 18 a7 11 48 0f ae e8 0f 31 48 89 d6 48 c1 e6 20 48 09 c6 eb 0e f3 90 65 8b 05 fe a6 11 48 <41> 39 c0 75 18 0f ae e8 0f 31 48 c1 e2 20 48 09 c2 48 89 d0 48 29 RSP: 0000:ffff8f92c0157ed0 EFLAGS: 00000212 ORIG_RAX: ffffffffffffff13 RAX: 0000000000000005 RBX: ffff8c861f356400 RCX: ffff8f92c0157e64 RDX: 000000321214c8cc RSI: 00000032120daa7f RDI: 0000000000260f15 RBP: 0000000000000005 R08: 0000000000000005 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000001 R12: 0000000000000000 R13: 0000000000000000 R14: ffff8c861ee18000 R15: ffff8c861ee18000 cpuhp_report_idle_dead+0x31/0x60 do_idle+0x1d5/0x200 ? _raw_spin_unlock_irqrestore+0x2d/0x40 cpu_startup_entry+0x14/0x20 start_secondary+0x151/0x170 secondary_startup_64+0xa4/0xb0 ------------------------------------------------------------------------ This happens rarely, but can be forced by happen more often by placing delays in cpuhp_report_idle_dead() following the call to rcu_report_dead(). With this in place, the following rcutorture scenario reproduces the problem within a few minutes: tools/testing/selftests/rcutorture/bin/kvm.sh --cpus 8 --duration 5 --kconfig "CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y" --configs "TREE04" This commit uses the crude but effective expedient of moving the disabling of interrupts within the idle loop to precede the cpu_is_offline() check. It also invokes tick_nohz_idle_stop_tick() instead of tick_nohz_idle_stop_tick_protected() to shut off the scheduling-clock interrupt. Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@kernel.org> [ paulmck: Revert tick_nohz_idle_stop_tick_protected() removal, new callers. ] Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
2019-06-05 22:46:43 +08:00
local_irq_disable();
2017-10-25 19:28:27 +08:00
if (cpu_is_offline(cpu)) {
idle: Prevent late-arriving interrupts from disrupting offline Scheduling-clock interrupts can arrive late in the CPU-offline process, after idle entry and the subsequent call to cpuhp_report_idle_dead(). Once execution passes the call to rcu_report_dead(), RCU is ignoring the CPU, which results in lockdep complaints when the interrupt handler uses RCU: ------------------------------------------------------------------------ ============================= WARNING: suspicious RCU usage 5.2.0-rc1+ #681 Not tainted ----------------------------- kernel/sched/fair.c:9542 suspicious rcu_dereference_check() usage! other info that might help us debug this: RCU used illegally from offline CPU! rcu_scheduler_active = 2, debug_locks = 1 no locks held by swapper/5/0. stack backtrace: CPU: 5 PID: 0 Comm: swapper/5 Not tainted 5.2.0-rc1+ #681 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS Bochs 01/01/2011 Call Trace: <IRQ> dump_stack+0x5e/0x8b trigger_load_balance+0xa8/0x390 ? tick_sched_do_timer+0x60/0x60 update_process_times+0x3b/0x50 tick_sched_handle+0x2f/0x40 tick_sched_timer+0x32/0x70 __hrtimer_run_queues+0xd3/0x3b0 hrtimer_interrupt+0x11d/0x270 ? sched_clock_local+0xc/0x74 smp_apic_timer_interrupt+0x79/0x200 apic_timer_interrupt+0xf/0x20 </IRQ> RIP: 0010:delay_tsc+0x22/0x50 Code: ff 0f 1f 80 00 00 00 00 65 44 8b 05 18 a7 11 48 0f ae e8 0f 31 48 89 d6 48 c1 e6 20 48 09 c6 eb 0e f3 90 65 8b 05 fe a6 11 48 <41> 39 c0 75 18 0f ae e8 0f 31 48 c1 e2 20 48 09 c2 48 89 d0 48 29 RSP: 0000:ffff8f92c0157ed0 EFLAGS: 00000212 ORIG_RAX: ffffffffffffff13 RAX: 0000000000000005 RBX: ffff8c861f356400 RCX: ffff8f92c0157e64 RDX: 000000321214c8cc RSI: 00000032120daa7f RDI: 0000000000260f15 RBP: 0000000000000005 R08: 0000000000000005 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000001 R12: 0000000000000000 R13: 0000000000000000 R14: ffff8c861ee18000 R15: ffff8c861ee18000 cpuhp_report_idle_dead+0x31/0x60 do_idle+0x1d5/0x200 ? _raw_spin_unlock_irqrestore+0x2d/0x40 cpu_startup_entry+0x14/0x20 start_secondary+0x151/0x170 secondary_startup_64+0xa4/0xb0 ------------------------------------------------------------------------ This happens rarely, but can be forced by happen more often by placing delays in cpuhp_report_idle_dead() following the call to rcu_report_dead(). With this in place, the following rcutorture scenario reproduces the problem within a few minutes: tools/testing/selftests/rcutorture/bin/kvm.sh --cpus 8 --duration 5 --kconfig "CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y" --configs "TREE04" This commit uses the crude but effective expedient of moving the disabling of interrupts within the idle loop to precede the cpu_is_offline() check. It also invokes tick_nohz_idle_stop_tick() instead of tick_nohz_idle_stop_tick_protected() to shut off the scheduling-clock interrupt. Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@kernel.org> [ paulmck: Revert tick_nohz_idle_stop_tick_protected() removal, new callers. ] Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
2019-06-05 22:46:43 +08:00
tick_nohz_idle_stop_tick();
cpuhp_report_idle_dead();
arch_cpu_idle_dead();
}
arch_cpu_idle_enter();
rcu_nocb_flush_deferred_wakeup();
/*
* 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()) {
tick_nohz_idle_restart_tick();
cpu_idle_poll();
} else {
cpuidle_idle_call();
}
arch_cpu_idle_exit();
}
/*
* Since we fell out of the loop above, we know TIF_NEED_RESCHED must
* be set, propagate it into PREEMPT_NEED_RESCHED.
*
* This is required because for polling idle loops we will not have had
* an IPI to fold the state for us.
*/
preempt_set_need_resched();
tick_nohz_idle_exit();
__current_clr_polling();
/*
* We promise to call sched_ttwu_pending() and reschedule if
* need_resched() is set while polling is set. That means that clearing
* polling needs to be visible before doing these things.
*/
smp_mb__after_atomic();
/*
* RCU relies on this call to be done outside of an RCU read-side
* critical section.
*/
flush_smp_call_function_queue();
sched/core: Call __schedule() from do_idle() without enabling preemption I finally got around to creating trampolines for dynamically allocated ftrace_ops with using synchronize_rcu_tasks(). For users of the ftrace function hook callbacks, like perf, that allocate the ftrace_ops descriptor via kmalloc() and friends, ftrace was not able to optimize the functions being traced to use a trampoline because they would also need to be allocated dynamically. The problem is that they cannot be freed when CONFIG_PREEMPT is set, as there's no way to tell if a task was preempted on the trampoline. That was before Paul McKenney implemented synchronize_rcu_tasks() that would make sure all tasks (except idle) have scheduled out or have entered user space. While testing this, I triggered this bug: BUG: unable to handle kernel paging request at ffffffffa0230077 ... RIP: 0010:0xffffffffa0230077 ... Call Trace: schedule+0x5/0xe0 schedule_preempt_disabled+0x18/0x30 do_idle+0x172/0x220 What happened was that the idle task was preempted on the trampoline. As synchronize_rcu_tasks() ignores the idle thread, there's nothing that lets ftrace know that the idle task was preempted on a trampoline. The idle task shouldn't need to ever enable preemption. The idle task is simply a loop that calls schedule or places the cpu into idle mode. In fact, having preemption enabled is inefficient, because it can happen when idle is just about to call schedule anyway, which would cause schedule to be called twice. Once for when the interrupt came in and was returning back to normal context, and then again in the normal path that the idle loop is running in, which would be pointless, as it had already scheduled. The only reason schedule_preempt_disable() enables preemption is to be able to call sched_submit_work(), which requires preemption enabled. As this is a nop when the task is in the RUNNING state, and idle is always in the running state, there's no reason that idle needs to enable preemption. But that means it cannot use schedule_preempt_disable() as other callers of that function require calling sched_submit_work(). Adding a new function local to kernel/sched/ that allows idle to call the scheduler without enabling preemption, fixes the synchronize_rcu_tasks() issue, as well as removes the pointless spurious schedule calls caused by interrupts happening in the brief window where preemption is enabled just before it calls schedule. Reviewed: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20170414084809.3dacde2a@gandalf.local.home Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-04-14 20:48:09 +08:00
schedule_idle();
livepatch: change to a per-task consistency model Change livepatch to use a basic per-task consistency model. This is the foundation which will eventually enable us to patch those ~10% of security patches which change function or data semantics. This is the biggest remaining piece needed to make livepatch more generally useful. This code stems from the design proposal made by Vojtech [1] in November 2014. It's a hybrid of kGraft and kpatch: it uses kGraft's per-task consistency and syscall barrier switching combined with kpatch's stack trace switching. There are also a number of fallback options which make it quite flexible. Patches are applied on a per-task basis, when the task is deemed safe to switch over. When a patch is enabled, livepatch enters into a transition state where tasks are converging to the patched state. Usually this transition state can complete in a few seconds. The same sequence occurs when a patch is disabled, except the tasks converge from the patched state to the unpatched state. An interrupt handler inherits the patched state of the task it interrupts. The same is true for forked tasks: the child inherits the patched state of the parent. Livepatch uses several complementary approaches to determine when it's safe to patch tasks: 1. The first and most effective approach is stack checking of sleeping tasks. If no affected functions are on the stack of a given task, the task is patched. In most cases this will patch most or all of the tasks on the first try. Otherwise it'll keep trying periodically. This option is only available if the architecture has reliable stacks (HAVE_RELIABLE_STACKTRACE). 2. The second approach, if needed, is kernel exit switching. A task is switched when it returns to user space from a system call, a user space IRQ, or a signal. It's useful in the following cases: a) Patching I/O-bound user tasks which are sleeping on an affected function. In this case you have to send SIGSTOP and SIGCONT to force it to exit the kernel and be patched. b) Patching CPU-bound user tasks. If the task is highly CPU-bound then it will get patched the next time it gets interrupted by an IRQ. c) In the future it could be useful for applying patches for architectures which don't yet have HAVE_RELIABLE_STACKTRACE. In this case you would have to signal most of the tasks on the system. However this isn't supported yet because there's currently no way to patch kthreads without HAVE_RELIABLE_STACKTRACE. 3. For idle "swapper" tasks, since they don't ever exit the kernel, they instead have a klp_update_patch_state() call in the idle loop which allows them to be patched before the CPU enters the idle state. (Note there's not yet such an approach for kthreads.) All the above approaches may be skipped by setting the 'immediate' flag in the 'klp_patch' struct, which will disable per-task consistency and patch all tasks immediately. This can be useful if the patch doesn't change any function or data semantics. Note that, even with this flag set, it's possible that some tasks may still be running with an old version of the function, until that function returns. There's also an 'immediate' flag in the 'klp_func' struct which allows you to specify that certain functions in the patch can be applied without per-task consistency. This might be useful if you want to patch a common function like schedule(), and the function change doesn't need consistency but the rest of the patch does. For architectures which don't have HAVE_RELIABLE_STACKTRACE, the user must set patch->immediate which causes all tasks to be patched immediately. This option should be used with care, only when the patch doesn't change any function or data semantics. In the future, architectures which don't have HAVE_RELIABLE_STACKTRACE may be allowed to use per-task consistency if we can come up with another way to patch kthreads. The /sys/kernel/livepatch/<patch>/transition file shows whether a patch is in transition. Only a single patch (the topmost patch on the stack) can be in transition at a given time. A patch can remain in transition indefinitely, if any of the tasks are stuck in the initial patch state. A transition can be reversed and effectively canceled by writing the opposite value to the /sys/kernel/livepatch/<patch>/enabled file while the transition is in progress. Then all the tasks will attempt to converge back to the original patch state. [1] https://lkml.kernel.org/r/20141107140458.GA21774@suse.cz Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Miroslav Benes <mbenes@suse.cz> Acked-by: Ingo Molnar <mingo@kernel.org> # for the scheduler changes Signed-off-by: Jiri Kosina <jkosina@suse.cz>
2017-02-14 09:42:40 +08:00
if (unlikely(klp_patch_pending(current)))
klp_update_patch_state(current);
}
bool cpu_in_idle(unsigned long pc)
{
return pc >= (unsigned long)__cpuidle_text_start &&
pc < (unsigned long)__cpuidle_text_end;
}
struct idle_timer {
struct hrtimer timer;
int done;
};
static enum hrtimer_restart idle_inject_timer_fn(struct hrtimer *timer)
{
struct idle_timer *it = container_of(timer, struct idle_timer, timer);
WRITE_ONCE(it->done, 1);
set_tsk_need_resched(current);
return HRTIMER_NORESTART;
}
void play_idle_precise(u64 duration_ns, u64 latency_ns)
{
struct idle_timer it;
/*
* Only FIFO tasks can disable the tick since they don't need the forced
* preemption.
*/
WARN_ON_ONCE(current->policy != SCHED_FIFO);
WARN_ON_ONCE(current->nr_cpus_allowed != 1);
WARN_ON_ONCE(!(current->flags & PF_KTHREAD));
WARN_ON_ONCE(!(current->flags & PF_NO_SETAFFINITY));
WARN_ON_ONCE(!duration_ns);
WARN_ON_ONCE(current->mm);
rcu_sleep_check();
preempt_disable();
current->flags |= PF_IDLE;
cpuidle_use_deepest_state(latency_ns);
it.done = 0;
hrtimer_init_on_stack(&it.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
it.timer.function = idle_inject_timer_fn;
hrtimer_start(&it.timer, ns_to_ktime(duration_ns),
HRTIMER_MODE_REL_PINNED_HARD);
while (!READ_ONCE(it.done))
do_idle();
cpuidle_use_deepest_state(0);
current->flags &= ~PF_IDLE;
preempt_fold_need_resched();
preempt_enable();
}
EXPORT_SYMBOL_GPL(play_idle_precise);
void cpu_startup_entry(enum cpuhp_state state)
{
current->flags |= PF_IDLE;
arch_cpu_idle_prepare();
cpuhp_online_idle(state);
while (1)
do_idle();
}
/*
* idle-task scheduling class.
*/
#ifdef CONFIG_SMP
static int
select_task_rq_idle(struct task_struct *p, int cpu, int flags)
{
return task_cpu(p); /* IDLE tasks as never migrated */
}
sched: Fix pick_next_task() vs 'change' pattern race Commit 67692435c411 ("sched: Rework pick_next_task() slow-path") inadvertly introduced a race because it changed a previously unexplored dependency between dropping the rq->lock and sched_class::put_prev_task(). The comments about dropping rq->lock, in for example newidle_balance(), only mentions the task being current and ->on_cpu being set. But when we look at the 'change' pattern (in for example sched_setnuma()): queued = task_on_rq_queued(p); /* p->on_rq == TASK_ON_RQ_QUEUED */ running = task_current(rq, p); /* rq->curr == p */ if (queued) dequeue_task(...); if (running) put_prev_task(...); /* change task properties */ if (queued) enqueue_task(...); if (running) set_next_task(...); It becomes obvious that if we do this after put_prev_task() has already been called on @p, things go sideways. This is exactly what the commit in question allows to happen when it does: prev->sched_class->put_prev_task(rq, prev, rf); if (!rq->nr_running) newidle_balance(rq, rf); The newidle_balance() call will drop rq->lock after we've called put_prev_task() and that allows the above 'change' pattern to interleave and mess up the state. Furthermore, it turns out we lost the RT-pull when we put the last DL task. Fix both problems by extracting the balancing from put_prev_task() and doing a multi-class balance() pass before put_prev_task(). Fixes: 67692435c411 ("sched: Rework pick_next_task() slow-path") Reported-by: Quentin Perret <qperret@google.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: Quentin Perret <qperret@google.com> Tested-by: Valentin Schneider <valentin.schneider@arm.com>
2019-11-08 18:11:52 +08:00
static int
balance_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
return WARN_ON_ONCE(1);
}
#endif
/*
* Idle tasks are unconditionally rescheduled:
*/
static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int flags)
{
resched_curr(rq);
}
sched: Fix pick_next_task() vs 'change' pattern race Commit 67692435c411 ("sched: Rework pick_next_task() slow-path") inadvertly introduced a race because it changed a previously unexplored dependency between dropping the rq->lock and sched_class::put_prev_task(). The comments about dropping rq->lock, in for example newidle_balance(), only mentions the task being current and ->on_cpu being set. But when we look at the 'change' pattern (in for example sched_setnuma()): queued = task_on_rq_queued(p); /* p->on_rq == TASK_ON_RQ_QUEUED */ running = task_current(rq, p); /* rq->curr == p */ if (queued) dequeue_task(...); if (running) put_prev_task(...); /* change task properties */ if (queued) enqueue_task(...); if (running) set_next_task(...); It becomes obvious that if we do this after put_prev_task() has already been called on @p, things go sideways. This is exactly what the commit in question allows to happen when it does: prev->sched_class->put_prev_task(rq, prev, rf); if (!rq->nr_running) newidle_balance(rq, rf); The newidle_balance() call will drop rq->lock after we've called put_prev_task() and that allows the above 'change' pattern to interleave and mess up the state. Furthermore, it turns out we lost the RT-pull when we put the last DL task. Fix both problems by extracting the balancing from put_prev_task() and doing a multi-class balance() pass before put_prev_task(). Fixes: 67692435c411 ("sched: Rework pick_next_task() slow-path") Reported-by: Quentin Perret <qperret@google.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: Quentin Perret <qperret@google.com> Tested-by: Valentin Schneider <valentin.schneider@arm.com>
2019-11-08 18:11:52 +08:00
static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
{
}
static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first)
{
update_idle_core(rq);
schedstat_inc(rq->sched_goidle);
}
#ifdef CONFIG_SMP
static struct task_struct *pick_task_idle(struct rq *rq)
{
return rq->idle;
}
#endif
struct task_struct *pick_next_task_idle(struct rq *rq)
{
struct task_struct *next = rq->idle;
set_next_task_idle(rq, next, true);
return next;
}
/*
* It is not legal to sleep in the idle task - print a warning
* message if some code attempts to do it:
*/
static void
dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags)
{
raw_spin_rq_unlock_irq(rq);
printk(KERN_ERR "bad: scheduling from the idle thread!\n");
dump_stack();
raw_spin_rq_lock_irq(rq);
}
/*
* scheduler tick hitting a task of our scheduling class.
*
* NOTE: This function can be called remotely by the tick offload that
* goes along full dynticks. Therefore no local assumption can be made
* and everything must be accessed through the @rq and @curr passed in
* parameters.
*/
static void task_tick_idle(struct rq *rq, struct task_struct *curr, int queued)
{
}
static void switched_to_idle(struct rq *rq, struct task_struct *p)
{
BUG();
}
static void
prio_changed_idle(struct rq *rq, struct task_struct *p, int oldprio)
{
BUG();
}
static void update_curr_idle(struct rq *rq)
{
}
/*
* Simple, special scheduling class for the per-CPU idle tasks:
*/
DEFINE_SCHED_CLASS(idle) = {
/* no enqueue/yield_task for idle tasks */
/* dequeue is not valid, we print a debug message there: */
.dequeue_task = dequeue_task_idle,
.check_preempt_curr = check_preempt_curr_idle,
.pick_next_task = pick_next_task_idle,
.put_prev_task = put_prev_task_idle,
.set_next_task = set_next_task_idle,
#ifdef CONFIG_SMP
sched: Fix pick_next_task() vs 'change' pattern race Commit 67692435c411 ("sched: Rework pick_next_task() slow-path") inadvertly introduced a race because it changed a previously unexplored dependency between dropping the rq->lock and sched_class::put_prev_task(). The comments about dropping rq->lock, in for example newidle_balance(), only mentions the task being current and ->on_cpu being set. But when we look at the 'change' pattern (in for example sched_setnuma()): queued = task_on_rq_queued(p); /* p->on_rq == TASK_ON_RQ_QUEUED */ running = task_current(rq, p); /* rq->curr == p */ if (queued) dequeue_task(...); if (running) put_prev_task(...); /* change task properties */ if (queued) enqueue_task(...); if (running) set_next_task(...); It becomes obvious that if we do this after put_prev_task() has already been called on @p, things go sideways. This is exactly what the commit in question allows to happen when it does: prev->sched_class->put_prev_task(rq, prev, rf); if (!rq->nr_running) newidle_balance(rq, rf); The newidle_balance() call will drop rq->lock after we've called put_prev_task() and that allows the above 'change' pattern to interleave and mess up the state. Furthermore, it turns out we lost the RT-pull when we put the last DL task. Fix both problems by extracting the balancing from put_prev_task() and doing a multi-class balance() pass before put_prev_task(). Fixes: 67692435c411 ("sched: Rework pick_next_task() slow-path") Reported-by: Quentin Perret <qperret@google.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: Quentin Perret <qperret@google.com> Tested-by: Valentin Schneider <valentin.schneider@arm.com>
2019-11-08 18:11:52 +08:00
.balance = balance_idle,
.pick_task = pick_task_idle,
.select_task_rq = select_task_rq_idle,
.set_cpus_allowed = set_cpus_allowed_common,
#endif
.task_tick = task_tick_idle,
.prio_changed = prio_changed_idle,
.switched_to = switched_to_idle,
.update_curr = update_curr_idle,
};