diff options
author | Paul E. McKenney <paulmck@kernel.org> | 2022-07-22 03:46:18 +0300 |
---|---|---|
committer | Paul E. McKenney <paulmck@kernel.org> | 2022-07-22 03:46:18 +0300 |
commit | 34bc7b454dc31f75a0be7ee8ab378135523d7c51 (patch) | |
tree | a1891ee085290746b6835e5e33e3c31cec2489fa /kernel | |
parent | d38c8fe48354af9c7120291938574e1ebb221d52 (diff) | |
parent | 1dcaa3b462265f688613163a1562a65ee53a3311 (diff) | |
download | linux-34bc7b454dc31f75a0be7ee8ab378135523d7c51.tar.xz |
Merge branch 'ctxt.2022.07.05a' into HEAD
ctxt.2022.07.05a: Linux-kernel memory model development branch.
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/cfi.c | 4 | ||||
-rw-r--r-- | kernel/context_tracking.c | 617 | ||||
-rw-r--r-- | kernel/cpu_pm.c | 8 | ||||
-rw-r--r-- | kernel/entry/common.c | 16 | ||||
-rw-r--r-- | kernel/extable.c | 4 | ||||
-rw-r--r-- | kernel/locking/lockdep.c | 2 | ||||
-rw-r--r-- | kernel/rcu/Kconfig | 2 | ||||
-rw-r--r-- | kernel/rcu/rcu.h | 4 | ||||
-rw-r--r-- | kernel/rcu/tree.c | 476 | ||||
-rw-r--r-- | kernel/rcu/tree.h | 8 | ||||
-rw-r--r-- | kernel/rcu/tree_exp.h | 2 | ||||
-rw-r--r-- | kernel/rcu/tree_plugin.h | 38 | ||||
-rw-r--r-- | kernel/rcu/tree_stall.h | 55 | ||||
-rw-r--r-- | kernel/rcu/update.c | 2 | ||||
-rw-r--r-- | kernel/sched/core.c | 2 | ||||
-rw-r--r-- | kernel/sched/idle.c | 10 | ||||
-rw-r--r-- | kernel/sched/sched.h | 1 | ||||
-rw-r--r-- | kernel/softirq.c | 4 | ||||
-rw-r--r-- | kernel/time/Kconfig | 37 | ||||
-rw-r--r-- | kernel/time/tick-sched.c | 2 | ||||
-rw-r--r-- | kernel/trace/trace.c | 8 |
21 files changed, 675 insertions, 627 deletions
diff --git a/kernel/cfi.c b/kernel/cfi.c index 08102d19ec15..2046276ee234 100644 --- a/kernel/cfi.c +++ b/kernel/cfi.c @@ -295,7 +295,7 @@ static inline cfi_check_fn find_check_fn(unsigned long ptr) rcu_idle = !rcu_is_watching(); if (rcu_idle) { local_irq_save(flags); - rcu_irq_enter(); + ct_irq_enter(); } if (IS_ENABLED(CONFIG_CFI_CLANG_SHADOW)) @@ -304,7 +304,7 @@ static inline cfi_check_fn find_check_fn(unsigned long ptr) fn = find_module_check_fn(ptr); if (rcu_idle) { - rcu_irq_exit(); + ct_irq_exit(); local_irq_restore(flags); } diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index 36a98c48aedc..77978e372377 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -1,18 +1,20 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Context tracking: Probe on high level context boundaries such as kernel - * and userspace. This includes syscalls and exceptions entry/exit. + * Context tracking: Probe on high level context boundaries such as kernel, + * userspace, guest or idle. * * This is used by RCU to remove its dependency on the timer tick while a CPU - * runs in userspace. + * runs in idle, userspace or guest mode. * - * Started by Frederic Weisbecker: + * User/guest tracking started by Frederic Weisbecker: * - * Copyright (C) 2012 Red Hat, Inc., Frederic Weisbecker <fweisbec@redhat.com> + * Copyright (C) 2012 Red Hat, Inc., Frederic Weisbecker * * Many thanks to Gilad Ben-Yossef, Paul McKenney, Ingo Molnar, Andrew Morton, * Steven Rostedt, Peter Zijlstra for suggestions and improvements. * + * RCU extended quiescent state bits imported from kernel/rcu/tree.c + * where the relevant authorship may be found. */ #include <linux/context_tracking.h> @@ -21,6 +23,411 @@ #include <linux/hardirq.h> #include <linux/export.h> #include <linux/kprobes.h> +#include <trace/events/rcu.h> + + +DEFINE_PER_CPU(struct context_tracking, context_tracking) = { +#ifdef CONFIG_CONTEXT_TRACKING_IDLE + .dynticks_nesting = 1, + .dynticks_nmi_nesting = DYNTICK_IRQ_NONIDLE, +#endif + .state = ATOMIC_INIT(RCU_DYNTICKS_IDX), +}; +EXPORT_SYMBOL_GPL(context_tracking); + +#ifdef CONFIG_CONTEXT_TRACKING_IDLE +#define TPS(x) tracepoint_string(x) + +/* Record the current task on dyntick-idle entry. */ +static __always_inline void rcu_dynticks_task_enter(void) +{ +#if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) + WRITE_ONCE(current->rcu_tasks_idle_cpu, smp_processor_id()); +#endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */ +} + +/* Record no current task on dyntick-idle exit. */ +static __always_inline void rcu_dynticks_task_exit(void) +{ +#if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) + WRITE_ONCE(current->rcu_tasks_idle_cpu, -1); +#endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */ +} + +/* Turn on heavyweight RCU tasks trace readers on idle/user entry. */ +static __always_inline void rcu_dynticks_task_trace_enter(void) +{ +#ifdef CONFIG_TASKS_TRACE_RCU + if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB)) + current->trc_reader_special.b.need_mb = true; +#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ +} + +/* Turn off heavyweight RCU tasks trace readers on idle/user exit. */ +static __always_inline void rcu_dynticks_task_trace_exit(void) +{ +#ifdef CONFIG_TASKS_TRACE_RCU + if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB)) + current->trc_reader_special.b.need_mb = false; +#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ +} + +/* + * Record entry into an extended quiescent state. This is only to be + * called when not already in an extended quiescent state, that is, + * RCU is watching prior to the call to this function and is no longer + * watching upon return. + */ +static noinstr void ct_kernel_exit_state(int offset) +{ + int seq; + + /* + * CPUs seeing atomic_add_return() must see prior RCU read-side + * critical sections, and we also must force ordering with the + * next idle sojourn. + */ + rcu_dynticks_task_trace_enter(); // Before ->dynticks update! + seq = ct_state_inc(offset); + // RCU is no longer watching. Better be in extended quiescent state! + WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && (seq & RCU_DYNTICKS_IDX)); +} + +/* + * Record exit from an extended quiescent state. This is only to be + * called from an extended quiescent state, that is, RCU is not watching + * prior to the call to this function and is watching upon return. + */ +static noinstr void ct_kernel_enter_state(int offset) +{ + int seq; + + /* + * CPUs seeing atomic_add_return() must see prior idle sojourns, + * and we also must force ordering with the next RCU read-side + * critical section. + */ + seq = ct_state_inc(offset); + // RCU is now watching. Better not be in an extended quiescent state! + rcu_dynticks_task_trace_exit(); // After ->dynticks update! + WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !(seq & RCU_DYNTICKS_IDX)); +} + +/* + * Enter an RCU extended quiescent state, which can be either the + * idle loop or adaptive-tickless usermode execution. + * + * We crowbar the ->dynticks_nmi_nesting field to zero to allow for + * the possibility of usermode upcalls having messed up our count + * of interrupt nesting level during the prior busy period. + */ +static void noinstr ct_kernel_exit(bool user, int offset) +{ + struct context_tracking *ct = this_cpu_ptr(&context_tracking); + + WARN_ON_ONCE(ct_dynticks_nmi_nesting() != DYNTICK_IRQ_NONIDLE); + WRITE_ONCE(ct->dynticks_nmi_nesting, 0); + WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && + ct_dynticks_nesting() == 0); + if (ct_dynticks_nesting() != 1) { + // RCU will still be watching, so just do accounting and leave. + ct->dynticks_nesting--; + return; + } + + instrumentation_begin(); + lockdep_assert_irqs_disabled(); + trace_rcu_dyntick(TPS("Start"), ct_dynticks_nesting(), 0, ct_dynticks()); + WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current)); + rcu_preempt_deferred_qs(current); + + // instrumentation for the noinstr ct_kernel_exit_state() + instrument_atomic_write(&ct->state, sizeof(ct->state)); + + instrumentation_end(); + WRITE_ONCE(ct->dynticks_nesting, 0); /* Avoid irq-access tearing. */ + // RCU is watching here ... + ct_kernel_exit_state(offset); + // ... but is no longer watching here. + rcu_dynticks_task_enter(); +} + +/* + * Exit an RCU extended quiescent state, which can be either the + * idle loop or adaptive-tickless usermode execution. + * + * We crowbar the ->dynticks_nmi_nesting field to DYNTICK_IRQ_NONIDLE to + * allow for the possibility of usermode upcalls messing up our count of + * interrupt nesting level during the busy period that is just now starting. + */ +static void noinstr ct_kernel_enter(bool user, int offset) +{ + struct context_tracking *ct = this_cpu_ptr(&context_tracking); + long oldval; + + WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !raw_irqs_disabled()); + oldval = ct_dynticks_nesting(); + WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && oldval < 0); + if (oldval) { + // RCU was already watching, so just do accounting and leave. + ct->dynticks_nesting++; + return; + } + rcu_dynticks_task_exit(); + // RCU is not watching here ... + ct_kernel_enter_state(offset); + // ... but is watching here. + instrumentation_begin(); + + // instrumentation for the noinstr ct_kernel_enter_state() + instrument_atomic_write(&ct->state, sizeof(ct->state)); + + trace_rcu_dyntick(TPS("End"), ct_dynticks_nesting(), 1, ct_dynticks()); + WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current)); + WRITE_ONCE(ct->dynticks_nesting, 1); + WARN_ON_ONCE(ct_dynticks_nmi_nesting()); + WRITE_ONCE(ct->dynticks_nmi_nesting, DYNTICK_IRQ_NONIDLE); + instrumentation_end(); +} + +/** + * ct_nmi_exit - inform RCU of exit from NMI context + * + * If we are returning from the outermost NMI handler that interrupted an + * RCU-idle period, update ct->state and ct->dynticks_nmi_nesting + * to let the RCU grace-period handling know that the CPU is back to + * being RCU-idle. + * + * If you add or remove a call to ct_nmi_exit(), be sure to test + * with CONFIG_RCU_EQS_DEBUG=y. + */ +void noinstr ct_nmi_exit(void) +{ + struct context_tracking *ct = this_cpu_ptr(&context_tracking); + + instrumentation_begin(); + /* + * Check for ->dynticks_nmi_nesting underflow and bad ->dynticks. + * (We are exiting an NMI handler, so RCU better be paying attention + * to us!) + */ + WARN_ON_ONCE(ct_dynticks_nmi_nesting() <= 0); + WARN_ON_ONCE(rcu_dynticks_curr_cpu_in_eqs()); + + /* + * If the nesting level is not 1, the CPU wasn't RCU-idle, so + * leave it in non-RCU-idle state. + */ + if (ct_dynticks_nmi_nesting() != 1) { + trace_rcu_dyntick(TPS("--="), ct_dynticks_nmi_nesting(), ct_dynticks_nmi_nesting() - 2, + ct_dynticks()); + WRITE_ONCE(ct->dynticks_nmi_nesting, /* No store tearing. */ + ct_dynticks_nmi_nesting() - 2); + instrumentation_end(); + return; + } + + /* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */ + trace_rcu_dyntick(TPS("Startirq"), ct_dynticks_nmi_nesting(), 0, ct_dynticks()); + WRITE_ONCE(ct->dynticks_nmi_nesting, 0); /* Avoid store tearing. */ + + // instrumentation for the noinstr ct_kernel_exit_state() + instrument_atomic_write(&ct->state, sizeof(ct->state)); + instrumentation_end(); + + // RCU is watching here ... + ct_kernel_exit_state(RCU_DYNTICKS_IDX); + // ... but is no longer watching here. + + if (!in_nmi()) + rcu_dynticks_task_enter(); +} + +/** + * ct_nmi_enter - inform RCU of entry to NMI context + * + * If the CPU was idle from RCU's viewpoint, update ct->state and + * ct->dynticks_nmi_nesting to let the RCU grace-period handling know + * that the CPU is active. This implementation permits nested NMIs, as + * long as the nesting level does not overflow an int. (You will probably + * run out of stack space first.) + * + * If you add or remove a call to ct_nmi_enter(), be sure to test + * with CONFIG_RCU_EQS_DEBUG=y. + */ +void noinstr ct_nmi_enter(void) +{ + long incby = 2; + struct context_tracking *ct = this_cpu_ptr(&context_tracking); + + /* Complain about underflow. */ + WARN_ON_ONCE(ct_dynticks_nmi_nesting() < 0); + + /* + * If idle from RCU viewpoint, atomically increment ->dynticks + * to mark non-idle and increment ->dynticks_nmi_nesting by one. + * Otherwise, increment ->dynticks_nmi_nesting by two. This means + * if ->dynticks_nmi_nesting is equal to one, we are guaranteed + * to be in the outermost NMI handler that interrupted an RCU-idle + * period (observation due to Andy Lutomirski). + */ + if (rcu_dynticks_curr_cpu_in_eqs()) { + + if (!in_nmi()) + rcu_dynticks_task_exit(); + + // RCU is not watching here ... + ct_kernel_enter_state(RCU_DYNTICKS_IDX); + // ... but is watching here. + + instrumentation_begin(); + // instrumentation for the noinstr rcu_dynticks_curr_cpu_in_eqs() + instrument_atomic_read(&ct->state, sizeof(ct->state)); + // instrumentation for the noinstr ct_kernel_enter_state() + instrument_atomic_write(&ct->state, sizeof(ct->state)); + + incby = 1; + } else if (!in_nmi()) { + instrumentation_begin(); + rcu_irq_enter_check_tick(); + } else { + instrumentation_begin(); + } + + trace_rcu_dyntick(incby == 1 ? TPS("Endirq") : TPS("++="), + ct_dynticks_nmi_nesting(), + ct_dynticks_nmi_nesting() + incby, ct_dynticks()); + instrumentation_end(); + WRITE_ONCE(ct->dynticks_nmi_nesting, /* Prevent store tearing. */ + ct_dynticks_nmi_nesting() + incby); + barrier(); +} + +/** + * ct_idle_enter - inform RCU that current CPU is entering idle + * + * Enter idle mode, in other words, -leave- the mode in which RCU + * read-side critical sections can occur. (Though RCU read-side + * critical sections can occur in irq handlers in idle, a possibility + * handled by irq_enter() and irq_exit().) + * + * If you add or remove a call to ct_idle_enter(), be sure to test with + * CONFIG_RCU_EQS_DEBUG=y. + */ +void noinstr ct_idle_enter(void) +{ + WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !raw_irqs_disabled()); + ct_kernel_exit(false, RCU_DYNTICKS_IDX + CONTEXT_IDLE); +} +EXPORT_SYMBOL_GPL(ct_idle_enter); + +/** + * ct_idle_exit - inform RCU that current CPU is leaving idle + * + * Exit idle mode, in other words, -enter- the mode in which RCU + * read-side critical sections can occur. + * + * If you add or remove a call to ct_idle_exit(), be sure to test with + * CONFIG_RCU_EQS_DEBUG=y. + */ +void noinstr ct_idle_exit(void) +{ + unsigned long flags; + + raw_local_irq_save(flags); + ct_kernel_enter(false, RCU_DYNTICKS_IDX - CONTEXT_IDLE); + raw_local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(ct_idle_exit); + +/** + * ct_irq_enter - inform RCU that current CPU is entering irq away from idle + * + * Enter an interrupt handler, which might possibly result in exiting + * idle mode, in other words, entering the mode in which read-side critical + * sections can occur. The caller must have disabled interrupts. + * + * Note that the Linux kernel is fully capable of entering an interrupt + * handler that it never exits, for example when doing upcalls to user mode! + * This code assumes that the idle loop never does upcalls to user mode. + * If your architecture's idle loop does do upcalls to user mode (or does + * anything else that results in unbalanced calls to the irq_enter() and + * irq_exit() functions), RCU will give you what you deserve, good and hard. + * But very infrequently and irreproducibly. + * + * Use things like work queues to work around this limitation. + * + * You have been warned. + * + * If you add or remove a call to ct_irq_enter(), be sure to test with + * CONFIG_RCU_EQS_DEBUG=y. + */ +noinstr void ct_irq_enter(void) +{ + lockdep_assert_irqs_disabled(); + ct_nmi_enter(); +} + +/** + * ct_irq_exit - inform RCU that current CPU is exiting irq towards idle + * + * Exit from an interrupt handler, which might possibly result in entering + * idle mode, in other words, leaving the mode in which read-side critical + * sections can occur. The caller must have disabled interrupts. + * + * This code assumes that the idle loop never does anything that might + * result in unbalanced calls to irq_enter() and irq_exit(). If your + * architecture's idle loop violates this assumption, RCU will give you what + * you deserve, good and hard. But very infrequently and irreproducibly. + * + * Use things like work queues to work around this limitation. + * + * You have been warned. + * + * If you add or remove a call to ct_irq_exit(), be sure to test with + * CONFIG_RCU_EQS_DEBUG=y. + */ +noinstr void ct_irq_exit(void) +{ + lockdep_assert_irqs_disabled(); + ct_nmi_exit(); +} + +/* + * Wrapper for ct_irq_enter() where interrupts are enabled. + * + * If you add or remove a call to ct_irq_enter_irqson(), be sure to test + * with CONFIG_RCU_EQS_DEBUG=y. + */ +void ct_irq_enter_irqson(void) +{ + unsigned long flags; + + local_irq_save(flags); + ct_irq_enter(); + local_irq_restore(flags); +} + +/* + * Wrapper for ct_irq_exit() where interrupts are enabled. + * + * If you add or remove a call to ct_irq_exit_irqson(), be sure to test + * with CONFIG_RCU_EQS_DEBUG=y. + */ +void ct_irq_exit_irqson(void) +{ + unsigned long flags; + + local_irq_save(flags); + ct_irq_exit(); + local_irq_restore(flags); +} +#else +static __always_inline void ct_kernel_exit(bool user, int offset) { } +static __always_inline void ct_kernel_enter(bool user, int offset) { } +#endif /* #ifdef CONFIG_CONTEXT_TRACKING_IDLE */ + +#ifdef CONFIG_CONTEXT_TRACKING_USER #define CREATE_TRACE_POINTS #include <trace/events/context_tracking.h> @@ -28,9 +435,6 @@ DEFINE_STATIC_KEY_FALSE(context_tracking_key); EXPORT_SYMBOL_GPL(context_tracking_key); -DEFINE_PER_CPU(struct context_tracking, context_tracking); -EXPORT_SYMBOL_GPL(context_tracking); - static noinstr bool context_tracking_recursion_enter(void) { int recursion; @@ -51,29 +455,32 @@ static __always_inline void context_tracking_recursion_exit(void) } /** - * context_tracking_enter - Inform the context tracking that the CPU is going - * enter user or guest space mode. + * __ct_user_enter - Inform the context tracking that the CPU is going + * to enter user or guest space mode. * * This function must be called right before we switch from the kernel * to user or guest space, when it's guaranteed the remaining kernel * instructions to execute won't use any RCU read side critical section * because this function sets RCU in extended quiescent state. */ -void noinstr __context_tracking_enter(enum ctx_state state) +void noinstr __ct_user_enter(enum ctx_state state) { + struct context_tracking *ct = this_cpu_ptr(&context_tracking); + lockdep_assert_irqs_disabled(); + /* Kernel threads aren't supposed to go to userspace */ WARN_ON_ONCE(!current->mm); if (!context_tracking_recursion_enter()) return; - if ( __this_cpu_read(context_tracking.state) != state) { - if (__this_cpu_read(context_tracking.active)) { + if (__ct_state() != state) { + if (ct->active) { /* * At this stage, only low level arch entry code remains and * then we'll run in userspace. We can assume there won't be * any RCU read-side critical section until the next call to - * user_exit() or rcu_irq_enter(). Let's remove RCU's dependency + * user_exit() or ct_irq_enter(). Let's remove RCU's dependency * on the tick. */ if (state == CONTEXT_USER) { @@ -82,35 +489,77 @@ void noinstr __context_tracking_enter(enum ctx_state state) vtime_user_enter(current); instrumentation_end(); } - rcu_user_enter(); + /* + * Other than generic entry implementation, we may be past the last + * rescheduling opportunity in the entry code. Trigger a self IPI + * that will fire and reschedule once we resume in user/guest mode. + */ + rcu_irq_work_resched(); + + /* + * Enter RCU idle mode right before resuming userspace. No use of RCU + * is permitted between this call and rcu_eqs_exit(). This way the + * CPU doesn't need to maintain the tick for RCU maintenance purposes + * when the CPU runs in userspace. + */ + ct_kernel_exit(true, RCU_DYNTICKS_IDX + state); + + /* + * Special case if we only track user <-> kernel transitions for tickless + * cputime accounting but we don't support RCU extended quiescent state. + * In this we case we don't care about any concurrency/ordering. + */ + if (!IS_ENABLED(CONFIG_CONTEXT_TRACKING_IDLE)) + atomic_set(&ct->state, state); + } else { + /* + * Even if context tracking is disabled on this CPU, because it's outside + * the full dynticks mask for example, we still have to keep track of the + * context transitions and states to prevent inconsistency on those of + * other CPUs. + * If a task triggers an exception in userspace, sleep on the exception + * handler and then migrate to another CPU, that new CPU must know where + * the exception returns by the time we call exception_exit(). + * This information can only be provided by the previous CPU when it called + * exception_enter(). + * OTOH we can spare the calls to vtime and RCU when context_tracking.active + * is false because we know that CPU is not tickless. + */ + if (!IS_ENABLED(CONFIG_CONTEXT_TRACKING_IDLE)) { + /* Tracking for vtime only, no concurrent RCU EQS accounting */ + atomic_set(&ct->state, state); + } else { + /* + * Tracking for vtime and RCU EQS. Make sure we don't race + * with NMIs. OTOH we don't care about ordering here since + * RCU only requires RCU_DYNTICKS_IDX increments to be fully + * ordered. + */ + atomic_add(state, &ct->state); + } } - /* - * Even if context tracking is disabled on this CPU, because it's outside - * the full dynticks mask for example, we still have to keep track of the - * context transitions and states to prevent inconsistency on those of - * other CPUs. - * If a task triggers an exception in userspace, sleep on the exception - * handler and then migrate to another CPU, that new CPU must know where - * the exception returns by the time we call exception_exit(). - * This information can only be provided by the previous CPU when it called - * exception_enter(). - * OTOH we can spare the calls to vtime and RCU when context_tracking.active - * is false because we know that CPU is not tickless. - */ - __this_cpu_write(context_tracking.state, state); } context_tracking_recursion_exit(); } -EXPORT_SYMBOL_GPL(__context_tracking_enter); +EXPORT_SYMBOL_GPL(__ct_user_enter); -void context_tracking_enter(enum ctx_state state) +/* + * OBSOLETE: + * This function should be noinstr but the below local_irq_restore() is + * unsafe because it involves illegal RCU uses through tracing and lockdep. + * This is unlikely to be fixed as this function is obsolete. The preferred + * way is to call __context_tracking_enter() through user_enter_irqoff() + * or context_tracking_guest_enter(). It should be the arch entry code + * responsibility to call into context tracking with IRQs disabled. + */ +void ct_user_enter(enum ctx_state state) { unsigned long flags; /* * Some contexts may involve an exception occuring in an irq, * leading to that nesting: - * rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit() + * ct_irq_enter() rcu_eqs_exit(true) rcu_eqs_enter(true) ct_irq_exit() * This would mess up the dyntick_nesting count though. And rcu_irq_*() * helpers are enough to protect RCU uses inside the exception. So * just return immediately if we detect we are in an IRQ. @@ -119,21 +568,32 @@ void context_tracking_enter(enum ctx_state state) return; local_irq_save(flags); - __context_tracking_enter(state); + __ct_user_enter(state); local_irq_restore(flags); } -NOKPROBE_SYMBOL(context_tracking_enter); -EXPORT_SYMBOL_GPL(context_tracking_enter); +NOKPROBE_SYMBOL(ct_user_enter); +EXPORT_SYMBOL_GPL(ct_user_enter); -void context_tracking_user_enter(void) +/** + * user_enter_callable() - Unfortunate ASM callable version of user_enter() for + * archs that didn't manage to check the context tracking + * static key from low level code. + * + * This OBSOLETE function should be noinstr but it unsafely calls + * local_irq_restore(), involving illegal RCU uses through tracing and lockdep. + * This is unlikely to be fixed as this function is obsolete. The preferred + * way is to call user_enter_irqoff(). It should be the arch entry code + * responsibility to call into context tracking with IRQs disabled. + */ +void user_enter_callable(void) { user_enter(); } -NOKPROBE_SYMBOL(context_tracking_user_enter); +NOKPROBE_SYMBOL(user_enter_callable); /** - * context_tracking_exit - Inform the context tracking that the CPU is - * exiting user or guest mode and entering the kernel. + * __ct_user_exit - Inform the context tracking that the CPU is + * exiting user or guest mode and entering the kernel. * * This function must be called after we entered the kernel from user or * guest space before any use of RCU read side critical section. This @@ -143,32 +603,64 @@ NOKPROBE_SYMBOL(context_tracking_user_enter); * This call supports re-entrancy. This way it can be called from any exception * handler without needing to know if we came from userspace or not. */ -void noinstr __context_tracking_exit(enum ctx_state state) +void noinstr __ct_user_exit(enum ctx_state state) { + struct context_tracking *ct = this_cpu_ptr(&context_tracking); + if (!context_tracking_recursion_enter()) return; - if (__this_cpu_read(context_tracking.state) == state) { - if (__this_cpu_read(context_tracking.active)) { + if (__ct_state() == state) { + if (ct->active) { /* - * We are going to run code that may use RCU. Inform - * RCU core about that (ie: we may need the tick again). + * Exit RCU idle mode while entering the kernel because it can + * run a RCU read side critical section anytime. */ - rcu_user_exit(); + ct_kernel_enter(true, RCU_DYNTICKS_IDX - state); if (state == CONTEXT_USER) { instrumentation_begin(); vtime_user_exit(current); trace_user_exit(0); instrumentation_end(); } + + /* + * Special case if we only track user <-> kernel transitions for tickless + * cputime accounting but we don't support RCU extended quiescent state. + * In this we case we don't care about any concurrency/ordering. + */ + if (!IS_ENABLED(CONFIG_CONTEXT_TRACKING_IDLE)) + atomic_set(&ct->state, CONTEXT_KERNEL); + + } else { + if (!IS_ENABLED(CONFIG_CONTEXT_TRACKING_IDLE)) { + /* Tracking for vtime only, no concurrent RCU EQS accounting */ + atomic_set(&ct->state, CONTEXT_KERNEL); + } else { + /* + * Tracking for vtime and RCU EQS. Make sure we don't race + * with NMIs. OTOH we don't care about ordering here since + * RCU only requires RCU_DYNTICKS_IDX increments to be fully + * ordered. + */ + atomic_sub(state, &ct->state); + } } - __this_cpu_write(context_tracking.state, CONTEXT_KERNEL); } context_tracking_recursion_exit(); } -EXPORT_SYMBOL_GPL(__context_tracking_exit); +EXPORT_SYMBOL_GPL(__ct_user_exit); -void context_tracking_exit(enum ctx_state state) +/* + * OBSOLETE: + * This function should be noinstr but the below local_irq_save() is + * unsafe because it involves illegal RCU uses through tracing and lockdep. + * This is unlikely to be fixed as this function is obsolete. The preferred + * way is to call __context_tracking_exit() through user_exit_irqoff() + * or context_tracking_guest_exit(). It should be the arch entry code + * responsibility to call into context tracking with IRQs disabled. + */ +void ct_user_exit(enum ctx_state state) { unsigned long flags; @@ -176,19 +668,30 @@ void context_tracking_exit(enum ctx_state state) return; local_irq_save(flags); - __context_tracking_exit(state); + __ct_user_exit(state); local_irq_restore(flags); } -NOKPROBE_SYMBOL(context_tracking_exit); -EXPORT_SYMBOL_GPL(context_tracking_exit); +NOKPROBE_SYMBOL(ct_user_exit); +EXPORT_SYMBOL_GPL(ct_user_exit); -void context_tracking_user_exit(void) +/** + * user_exit_callable() - Unfortunate ASM callable version of user_exit() for + * archs that didn't manage to check the context tracking + * static key from low level code. + * + * This OBSOLETE function should be noinstr but it unsafely calls local_irq_save(), + * involving illegal RCU uses through tracing and lockdep. This is unlikely + * to be fixed as this function is obsolete. The preferred way is to call + * user_exit_irqoff(). It should be the arch entry code responsibility to + * call into context tracking with IRQs disabled. + */ +void user_exit_callable(void) { user_exit(); } -NOKPROBE_SYMBOL(context_tracking_user_exit); +NOKPROBE_SYMBOL(user_exit_callable); -void __init context_tracking_cpu_set(int cpu) +void __init ct_cpu_track_user(int cpu) { static __initdata bool initialized = false; @@ -212,12 +715,14 @@ void __init context_tracking_cpu_set(int cpu) initialized = true; } -#ifdef CONFIG_CONTEXT_TRACKING_FORCE +#ifdef CONFIG_CONTEXT_TRACKING_USER_FORCE void __init context_tracking_init(void) { int cpu; for_each_possible_cpu(cpu) - context_tracking_cpu_set(cpu); + ct_cpu_track_user(cpu); } #endif + +#endif /* #ifdef CONFIG_CONTEXT_TRACKING_USER */ diff --git a/kernel/cpu_pm.c b/kernel/cpu_pm.c index 246efc74e3f3..ba4ba71facf9 100644 --- a/kernel/cpu_pm.c +++ b/kernel/cpu_pm.c @@ -35,11 +35,11 @@ static int cpu_pm_notify(enum cpu_pm_event event) * disfunctional in cpu idle. Copy RCU_NONIDLE code to let RCU know * this. */ - rcu_irq_enter_irqson(); + ct_irq_enter_irqson(); rcu_read_lock(); ret = raw_notifier_call_chain(&cpu_pm_notifier.chain, event, NULL); rcu_read_unlock(); - rcu_irq_exit_irqson(); + ct_irq_exit_irqson(); return notifier_to_errno(ret); } @@ -49,11 +49,11 @@ static int cpu_pm_notify_robust(enum cpu_pm_event event_up, enum cpu_pm_event ev unsigned long flags; int ret; - rcu_irq_enter_irqson(); + ct_irq_enter_irqson(); raw_spin_lock_irqsave(&cpu_pm_notifier.lock, flags); ret = raw_notifier_call_chain_robust(&cpu_pm_notifier.chain, event_up, event_down, NULL); raw_spin_unlock_irqrestore(&cpu_pm_notifier.lock, flags); - rcu_irq_exit_irqson(); + ct_irq_exit_irqson(); return notifier_to_errno(ret); } diff --git a/kernel/entry/common.c b/kernel/entry/common.c index 032f164abe7c..063068a9ea9b 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -321,7 +321,7 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs) } /* - * If this entry hit the idle task invoke rcu_irq_enter() whether + * If this entry hit the idle task invoke ct_irq_enter() whether * RCU is watching or not. * * Interrupts can nest when the first interrupt invokes softirq @@ -332,12 +332,12 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs) * not nested into another interrupt. * * Checking for rcu_is_watching() here would prevent the nesting - * interrupt to invoke rcu_irq_enter(). If that nested interrupt is + * interrupt to invoke ct_irq_enter(). If that nested interrupt is * the tick then rcu_flavor_sched_clock_irq() would wrongfully * assume that it is the first interrupt and eventually claim * quiescent state and end grace periods prematurely. * - * Unconditionally invoke rcu_irq_enter() so RCU state stays + * Unconditionally invoke ct_irq_enter() so RCU state stays * consistent. * * TINY_RCU does not support EQS, so let the compiler eliminate @@ -350,7 +350,7 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs) * as in irqentry_enter_from_user_mode(). */ lockdep_hardirqs_off(CALLER_ADDR0); - rcu_irq_enter(); + ct_irq_enter(); instrumentation_begin(); trace_hardirqs_off_finish(); instrumentation_end(); @@ -418,7 +418,7 @@ noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state) trace_hardirqs_on_prepare(); lockdep_hardirqs_on_prepare(); instrumentation_end(); - rcu_irq_exit(); + ct_irq_exit(); lockdep_hardirqs_on(CALLER_ADDR0); return; } @@ -436,7 +436,7 @@ noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state) * was not watching on entry. */ if (state.exit_rcu) - rcu_irq_exit(); + ct_irq_exit(); } } @@ -449,7 +449,7 @@ irqentry_state_t noinstr irqentry_nmi_enter(struct pt_regs *regs) __nmi_enter(); lockdep_hardirqs_off(CALLER_ADDR0); lockdep_hardirq_enter(); - rcu_nmi_enter(); + ct_nmi_enter(); instrumentation_begin(); trace_hardirqs_off_finish(); @@ -469,7 +469,7 @@ void noinstr irqentry_nmi_exit(struct pt_regs *regs, irqentry_state_t irq_state) } instrumentation_end(); - rcu_nmi_exit(); + ct_nmi_exit(); lockdep_hardirq_exit(); if (irq_state.lockdep) lockdep_hardirqs_on(CALLER_ADDR0); diff --git a/kernel/extable.c b/kernel/extable.c index bda5e9761541..71f482581cab 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -114,7 +114,7 @@ int kernel_text_address(unsigned long addr) /* Treat this like an NMI as it can happen anywhere */ if (no_rcu) - rcu_nmi_enter(); + ct_nmi_enter(); if (is_module_text_address(addr)) goto out; @@ -127,7 +127,7 @@ int kernel_text_address(unsigned long addr) ret = 0; out: if (no_rcu) - rcu_nmi_exit(); + ct_nmi_exit(); return ret; } diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index f06b91ca6482..5ea690cb4f7a 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -6570,7 +6570,7 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s) /* * If a CPU is in the RCU-free window in idle (ie: in the section - * between rcu_idle_enter() and rcu_idle_exit(), then RCU + * between ct_idle_enter() and ct_idle_exit(), then RCU * considers that CPU to be in an "extended quiescent state", * which means that RCU will be completely ignoring that CPU. * Therefore, rcu_read_lock() and friends have absolutely no diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig index c05ca52cdf64..d471d22a5e21 100644 --- a/kernel/rcu/Kconfig +++ b/kernel/rcu/Kconfig @@ -8,6 +8,8 @@ menu "RCU Subsystem" config TREE_RCU bool default y if SMP + # Dynticks-idle tracking + select CONTEXT_TRACKING_IDLE help This option selects the RCU implementation that is designed for very large SMP system with hundreds or diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index 32291f4eefde..be5979da07f5 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -12,10 +12,6 @@ #include <trace/events/rcu.h> -/* Offset to allow distinguishing irq vs. task-based idle entry/exit. */ -#define DYNTICK_IRQ_NONIDLE ((LONG_MAX / 2) + 1) - - /* * Grace-period counter management. */ diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 62e514713f7a..3dc968006ad0 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -62,6 +62,7 @@ #include <linux/vmalloc.h> #include <linux/mm.h> #include <linux/kasan.h> +#include <linux/context_tracking.h> #include "../time/tick-internal.h" #include "tree.h" @@ -75,9 +76,6 @@ /* Data structures. */ static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, rcu_data) = { - .dynticks_nesting = 1, - .dynticks_nmi_nesting = DYNTICK_IRQ_NONIDLE, - .dynticks = ATOMIC_INIT(1), #ifdef CONFIG_RCU_NOCB_CPU .cblist.flags = SEGCBLIST_RCU_CORE, #endif @@ -267,56 +265,6 @@ void rcu_softirq_qs(void) } /* - * Increment the current CPU's rcu_data structure's ->dynticks field - * with ordering. Return the new value. - */ -static noinline noinstr unsigned long rcu_dynticks_inc(int incby) -{ - return arch_atomic_add_return(incby, this_cpu_ptr(&rcu_data.dynticks)); -} - -/* - * Record entry into an extended quiescent state. This is only to be - * called when not already in an extended quiescent state, that is, - * RCU is watching prior to the call to this function and is no longer - * watching upon return. - */ -static noinstr void rcu_dynticks_eqs_enter(void) -{ - int seq; - - /* - * CPUs seeing atomic_add_return() must see prior RCU read-side - * critical sections, and we also must force ordering with the - * next idle sojourn. - */ - rcu_dynticks_task_trace_enter(); // Before ->dynticks update! - seq = rcu_dynticks_inc(1); - // RCU is no longer watching. Better be in extended quiescent state! - WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && (seq & 0x1)); -} - -/* - * Record exit from an extended quiescent state. This is only to be - * called from an extended quiescent state, that is, RCU is not watching - * prior to the call to this function and is watching upon return. - */ -static noinstr void rcu_dynticks_eqs_exit(void) -{ - int seq; - - /* - * CPUs seeing atomic_add_return() must see prior idle sojourns, - * and we also must force ordering with the next RCU read-side - * critical section. - */ - seq = rcu_dynticks_inc(1); - // RCU is now watching. Better not be in an extended quiescent state! - rcu_dynticks_task_trace_exit(); // After ->dynticks update! - WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !(seq & 0x1)); -} - -/* * Reset the current CPU's ->dynticks counter to indicate that the * newly onlined CPU is no longer in an extended quiescent state. * This will either leave the counter unchanged, or increment it @@ -328,31 +276,19 @@ static noinstr void rcu_dynticks_eqs_exit(void) */ static void rcu_dynticks_eqs_online(void) { - struct rcu_data *rdp = this_cpu_ptr(&rcu_data); - - if (atomic_read(&rdp->dynticks) & 0x1) + if (ct_dynticks() & RCU_DYNTICKS_IDX) return; - rcu_dynticks_inc(1); -} - -/* - * Is the current CPU in an extended quiescent state? - * - * No ordering, as we are sampling CPU-local information. - */ -static __always_inline bool rcu_dynticks_curr_cpu_in_eqs(void) -{ - return !(arch_atomic_read(this_cpu_ptr(&rcu_data.dynticks)) & 0x1); + ct_state_inc(RCU_DYNTICKS_IDX); } /* * Snapshot the ->dynticks counter with full ordering so as to allow * stable comparison of this counter with past and future snapshots. */ -static int rcu_dynticks_snap(struct rcu_data *rdp) +static int rcu_dynticks_snap(int cpu) { smp_mb(); // Fundamental RCU ordering guarantee. - return atomic_read_acquire(&rdp->dynticks); + return ct_dynticks_cpu_acquire(cpu); } /* @@ -361,15 +297,13 @@ static int rcu_dynticks_snap(struct rcu_data *rdp) */ static bool rcu_dynticks_in_eqs(int snap) { - return !(snap & 0x1); + return !(snap & RCU_DYNTICKS_IDX); } /* Return true if the specified CPU is currently idle from an RCU viewpoint. */ bool rcu_is_idle_cpu(int cpu) { - struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); - - return rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp)); + return rcu_dynticks_in_eqs(rcu_dynticks_snap(cpu)); } /* @@ -379,7 +313,7 @@ bool rcu_is_idle_cpu(int cpu) */ static bool rcu_dynticks_in_eqs_since(struct rcu_data *rdp, int snap) { - return snap != rcu_dynticks_snap(rdp); + return snap != rcu_dynticks_snap(rdp->cpu); } /* @@ -388,19 +322,17 @@ static bool rcu_dynticks_in_eqs_since(struct rcu_data *rdp, int snap) */ bool rcu_dynticks_zero_in_eqs(int cpu, int *vp) { - struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); int snap; // If not quiescent, force back to earlier extended quiescent state. - snap = atomic_read(&rdp->dynticks) & ~0x1; - + snap = ct_dynticks_cpu(cpu) & ~RCU_DYNTICKS_IDX; smp_rmb(); // Order ->dynticks and *vp reads. if (READ_ONCE(*vp)) return false; // Non-zero, so report failure; smp_rmb(); // Order *vp read and ->dynticks re-read. // If still in the same extended quiescent state, we are good! - return snap == atomic_read(&rdp->dynticks); + return snap == ct_dynticks_cpu(cpu); } /* @@ -419,9 +351,9 @@ notrace void rcu_momentary_dyntick_idle(void) int seq; raw_cpu_write(rcu_data.rcu_need_heavy_qs, false); - seq = rcu_dynticks_inc(2); + seq = ct_state_inc(2 * RCU_DYNTICKS_IDX); /* It is illegal to call this from idle state. */ - WARN_ON_ONCE(!(seq & 0x1)); + WARN_ON_ONCE(!(seq & RCU_DYNTICKS_IDX)); rcu_preempt_deferred_qs(current); } EXPORT_SYMBOL_GPL(rcu_momentary_dyntick_idle); @@ -446,13 +378,13 @@ static int rcu_is_cpu_rrupt_from_idle(void) lockdep_assert_irqs_disabled(); /* Check for counter underflows */ - RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nesting) < 0, + RCU_LOCKDEP_WARN(ct_dynticks_nesting() < 0, "RCU dynticks_nesting counter underflow!"); - RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nmi_nesting) <= 0, + RCU_LOCKDEP_WARN(ct_dynticks_nmi_nesting() <= 0, "RCU dynticks_nmi_nesting counter underflow/zero!"); /* Are we at first interrupt nesting level? */ - nesting = __this_cpu_read(rcu_data.dynticks_nmi_nesting); + nesting = ct_dynticks_nmi_nesting(); if (nesting > 1) return false; @@ -462,7 +394,7 @@ static int rcu_is_cpu_rrupt_from_idle(void) WARN_ON_ONCE(!nesting && !is_idle_task(current)); /* Does CPU appear to be idle from an RCU standpoint? */ - return __this_cpu_read(rcu_data.dynticks_nesting) == 0; + return ct_dynticks_nesting() == 0; } #define DEFAULT_RCU_BLIMIT (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) ? 1000 : 10) @@ -613,66 +545,7 @@ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, } EXPORT_SYMBOL_GPL(rcutorture_get_gp_data); -/* - * Enter an RCU extended quiescent state, which can be either the - * idle loop or adaptive-tickless usermode execution. - * - * We crowbar the ->dynticks_nmi_nesting field to zero to allow for - * the possibility of usermode upcalls having messed up our count - * of interrupt nesting level during the prior busy period. - */ -static noinstr void rcu_eqs_enter(bool user) -{ - struct rcu_data *rdp = this_cpu_ptr(&rcu_data); - - WARN_ON_ONCE(rdp->dynticks_nmi_nesting != DYNTICK_IRQ_NONIDLE); - WRITE_ONCE(rdp->dynticks_nmi_nesting, 0); - WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && - rdp->dynticks_nesting == 0); - if (rdp->dynticks_nesting != 1) { - // RCU will still be watching, so just do accounting and leave. - rdp->dynticks_nesting--; - return; - } - - lockdep_assert_irqs_disabled(); - instrumentation_begin(); - trace_rcu_dyntick(TPS("Start"), rdp->dynticks_nesting, 0, atomic_read(&rdp->dynticks)); - WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current)); - rcu_preempt_deferred_qs(current); - - // instrumentation for the noinstr rcu_dynticks_eqs_enter() - instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks)); - - instrumentation_end(); - WRITE_ONCE(rdp->dynticks_nesting, 0); /* Avoid irq-access tearing. */ - // RCU is watching here ... - rcu_dynticks_eqs_enter(); - // ... but is no longer watching here. - rcu_dynticks_task_enter(); -} - -/** - * rcu_idle_enter - inform RCU that current CPU is entering idle - * - * Enter idle mode, in other words, -leave- the mode in which RCU - * read-side critical sections can occur. (Though RCU read-side - * critical sections can occur in irq handlers in idle, a possibility - * handled by irq_enter() and irq_exit().) - * - * If you add or remove a call to rcu_idle_enter(), be sure to test with - * CONFIG_RCU_EQS_DEBUG=y. - */ -void rcu_idle_enter(void) -{ - lockdep_assert_irqs_disabled(); - rcu_eqs_enter(false); -} -EXPORT_SYMBOL_GPL(rcu_idle_enter); - -#ifdef CONFIG_NO_HZ_FULL - -#if !defined(CONFIG_GENERIC_ENTRY) || !defined(CONFIG_KVM_XFER_TO_GUEST_WORK) +#if defined(CONFIG_NO_HZ_FULL) && (!defined(CONFIG_GENERIC_ENTRY) || !defined(CONFIG_KVM_XFER_TO_GUEST_WORK)) /* * An empty function that will trigger a reschedule on * IRQ tail once IRQs get re-enabled on userspace/guest resume. @@ -694,7 +567,7 @@ static DEFINE_PER_CPU(struct irq_work, late_wakeup_work) = * last resort is to fire a local irq_work that will trigger a reschedule once IRQs * get re-enabled again. */ -noinstr static void rcu_irq_work_resched(void) +noinstr void rcu_irq_work_resched(void) { struct rcu_data *rdp = this_cpu_ptr(&rcu_data); @@ -710,114 +583,7 @@ noinstr static void rcu_irq_work_resched(void) } instrumentation_end(); } - -#else -static inline void rcu_irq_work_resched(void) { } -#endif - -/** - * rcu_user_enter - inform RCU that we are resuming userspace. - * - * Enter RCU idle mode right before resuming userspace. No use of RCU - * is permitted between this call and rcu_user_exit(). This way the - * CPU doesn't need to maintain the tick for RCU maintenance purposes - * when the CPU runs in userspace. - * - * If you add or remove a call to rcu_user_enter(), be sure to test with - * CONFIG_RCU_EQS_DEBUG=y. - */ -noinstr void rcu_user_enter(void) -{ - lockdep_assert_irqs_disabled(); - - /* - * Other than generic entry implementation, we may be past the last - * rescheduling opportunity in the entry code. Trigger a self IPI - * that will fire and reschedule once we resume in user/guest mode. - */ - rcu_irq_work_resched(); - rcu_eqs_enter(true); -} - -#endif /* CONFIG_NO_HZ_FULL */ - -/** - * rcu_nmi_exit - inform RCU of exit from NMI context - * - * If we are returning from the outermost NMI handler that interrupted an - * RCU-idle period, update rdp->dynticks and rdp->dynticks_nmi_nesting - * to let the RCU grace-period handling know that the CPU is back to - * being RCU-idle. - * - * If you add or remove a call to rcu_nmi_exit(), be sure to test - * with CONFIG_RCU_EQS_DEBUG=y. - */ -noinstr void rcu_nmi_exit(void) -{ - struct rcu_data *rdp = this_cpu_ptr(&rcu_data); - - instrumentation_begin(); - /* - * Check for ->dynticks_nmi_nesting underflow and bad ->dynticks. - * (We are exiting an NMI handler, so RCU better be paying attention - * to us!) - */ - WARN_ON_ONCE(rdp->dynticks_nmi_nesting <= 0); - WARN_ON_ONCE(rcu_dynticks_curr_cpu_in_eqs()); - - /* - * If the nesting level is not 1, the CPU wasn't RCU-idle, so - * leave it in non-RCU-idle state. - */ - if (rdp->dynticks_nmi_nesting != 1) { - trace_rcu_dyntick(TPS("--="), rdp->dynticks_nmi_nesting, rdp->dynticks_nmi_nesting - 2, - atomic_read(&rdp->dynticks)); - WRITE_ONCE(rdp->dynticks_nmi_nesting, /* No store tearing. */ - rdp->dynticks_nmi_nesting - 2); - instrumentation_end(); - return; - } - - /* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */ - trace_rcu_dyntick(TPS("Startirq"), rdp->dynticks_nmi_nesting, 0, atomic_read(&rdp->dynticks)); - WRITE_ONCE(rdp->dynticks_nmi_nesting, 0); /* Avoid store tearing. */ - - // instrumentation for the noinstr rcu_dynticks_eqs_enter() - instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks)); - instrumentation_end(); - - // RCU is watching here ... - rcu_dynticks_eqs_enter(); - // ... but is no longer watching here. - - if (!in_nmi()) - rcu_dynticks_task_enter(); -} - -/** - * rcu_irq_exit - inform RCU that current CPU is exiting irq towards idle - * - * Exit from an interrupt handler, which might possibly result in entering - * idle mode, in other words, leaving the mode in which read-side critical - * sections can occur. The caller must have disabled interrupts. - * - * This code assumes that the idle loop never does anything that might - * result in unbalanced calls to irq_enter() and irq_exit(). If your - * architecture's idle loop violates this assumption, RCU will give you what - * you deserve, good and hard. But very infrequently and irreproducibly. - * - * Use things like work queues to work around this limitation. - * - * You have been warned. - * - * If you add or remove a call to rcu_irq_exit(), be sure to test with - * CONFIG_RCU_EQS_DEBUG=y. - */ -void noinstr rcu_irq_exit(void) -{ - lockdep_assert_irqs_disabled(); - rcu_nmi_exit(); -} +#endif /* #if defined(CONFIG_NO_HZ_FULL) && (!defined(CONFIG_GENERIC_ENTRY) || !defined(CONFIG_KVM_XFER_TO_GUEST_WORK)) */ #ifdef CONFIG_PROVE_RCU /** @@ -827,9 +593,9 @@ void rcu_irq_exit_check_preempt(void) { lockdep_assert_irqs_disabled(); - RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nesting) <= 0, + RCU_LOCKDEP_WARN(ct_dynticks_nesting() <= 0, "RCU dynticks_nesting counter underflow/zero!"); - RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nmi_nesting) != + RCU_LOCKDEP_WARN(ct_dynticks_nmi_nesting() != DYNTICK_IRQ_NONIDLE, "Bad RCU dynticks_nmi_nesting counter\n"); RCU_LOCKDEP_WARN(rcu_dynticks_curr_cpu_in_eqs(), @@ -837,95 +603,8 @@ void rcu_irq_exit_check_preempt(void) } #endif /* #ifdef CONFIG_PROVE_RCU */ -/* - * Wrapper for rcu_irq_exit() where interrupts are enabled. - * - * If you add or remove a call to rcu_irq_exit_irqson(), be sure to test - * with CONFIG_RCU_EQS_DEBUG=y. - */ -void rcu_irq_exit_irqson(void) -{ - unsigned long flags; - - local_irq_save(flags); - rcu_irq_exit(); - local_irq_restore(flags); -} - -/* - * Exit an RCU extended quiescent state, which can be either the - * idle loop or adaptive-tickless usermode execution. - * - * We crowbar the ->dynticks_nmi_nesting field to DYNTICK_IRQ_NONIDLE to - * allow for the possibility of usermode upcalls messing up our count of - * interrupt nesting level during the busy period that is just now starting. - */ -static void noinstr rcu_eqs_exit(bool user) -{ - struct rcu_data *rdp; - long oldval; - - lockdep_assert_irqs_disabled(); - rdp = this_cpu_ptr(&rcu_data); - oldval = rdp->dynticks_nesting; - WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && oldval < 0); - if (oldval) { - // RCU was already watching, so just do accounting and leave. - rdp->dynticks_nesting++; - return; - } - rcu_dynticks_task_exit(); - // RCU is not watching here ... - rcu_dynticks_eqs_exit(); - // ... but is watching here. - instrumentation_begin(); - - // instrumentation for the noinstr rcu_dynticks_eqs_exit() - instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks)); - - trace_rcu_dyntick(TPS("End"), rdp->dynticks_nesting, 1, atomic_read(&rdp->dynticks)); - WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current)); - WRITE_ONCE(rdp->dynticks_nesting, 1); - WARN_ON_ONCE(rdp->dynticks_nmi_nesting); - WRITE_ONCE(rdp->dynticks_nmi_nesting, DYNTICK_IRQ_NONIDLE); - instrumentation_end(); -} - -/** - * rcu_idle_exit - inform RCU that current CPU is leaving idle - * - * Exit idle mode, in other words, -enter- the mode in which RCU - * read-side critical sections can occur. - * - * If you add or remove a call to rcu_idle_exit(), be sure to test with - * CONFIG_RCU_EQS_DEBUG=y. - */ -void rcu_idle_exit(void) -{ - unsigned long flags; - - local_irq_save(flags); - rcu_eqs_exit(false); - local_irq_restore(flags); -} -EXPORT_SYMBOL_GPL(rcu_idle_exit); - #ifdef CONFIG_NO_HZ_FULL /** - * rcu_user_exit - inform RCU that we are exiting userspace. - * - * Exit RCU idle mode while entering the kernel because it can - * run a RCU read side critical section anytime. - * - * If you add or remove a call to rcu_user_exit(), be sure to test with - * CONFIG_RCU_EQS_DEBUG=y. - */ -void noinstr rcu_user_exit(void) -{ - rcu_eqs_exit(true); -} - -/** * __rcu_irq_enter_check_tick - Enable scheduler tick on CPU if RCU needs it. * * The scheduler tick is not normally enabled when CPUs enter the kernel @@ -987,109 +666,6 @@ void __rcu_irq_enter_check_tick(void) } #endif /* CONFIG_NO_HZ_FULL */ -/** - * rcu_nmi_enter - inform RCU of entry to NMI context - * - * If the CPU was idle from RCU's viewpoint, update rdp->dynticks and - * rdp->dynticks_nmi_nesting to let the RCU grace-period handling know - * that the CPU is active. This implementation permits nested NMIs, as - * long as the nesting level does not overflow an int. (You will probably - * run out of stack space first.) - * - * If you add or remove a call to rcu_nmi_enter(), be sure to test - * with CONFIG_RCU_EQS_DEBUG=y. - */ -noinstr void rcu_nmi_enter(void) -{ - long incby = 2; - struct rcu_data *rdp = this_cpu_ptr(&rcu_data); - - /* Complain about underflow. */ - WARN_ON_ONCE(rdp->dynticks_nmi_nesting < 0); - - /* - * If idle from RCU viewpoint, atomically increment ->dynticks - * to mark non-idle and increment ->dynticks_nmi_nesting by one. - * Otherwise, increment ->dynticks_nmi_nesting by two. This means - * if ->dynticks_nmi_nesting is equal to one, we are guaranteed - * to be in the outermost NMI handler that interrupted an RCU-idle - * period (observation due to Andy Lutomirski). - */ - if (rcu_dynticks_curr_cpu_in_eqs()) { - - if (!in_nmi()) - rcu_dynticks_task_exit(); - - // RCU is not watching here ... - rcu_dynticks_eqs_exit(); - // ... but is watching here. - - instrumentation_begin(); - // instrumentation for the noinstr rcu_dynticks_curr_cpu_in_eqs() - instrument_atomic_read(&rdp->dynticks, sizeof(rdp->dynticks)); - // instrumentation for the noinstr rcu_dynticks_eqs_exit() - instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks)); - - incby = 1; - } else if (!in_nmi()) { - instrumentation_begin(); - rcu_irq_enter_check_tick(); - } else { - instrumentation_begin(); - } - - trace_rcu_dyntick(incby == 1 ? TPS("Endirq") : TPS("++="), - rdp->dynticks_nmi_nesting, - rdp->dynticks_nmi_nesting + incby, atomic_read(&rdp->dynticks)); - instrumentation_end(); - WRITE_ONCE(rdp->dynticks_nmi_nesting, /* Prevent store tearing. */ - rdp->dynticks_nmi_nesting + incby); - barrier(); -} - -/** - * rcu_irq_enter - inform RCU that current CPU is entering irq away from idle - * - * Enter an interrupt handler, which might possibly result in exiting - * idle mode, in other words, entering the mode in which read-side critical - * sections can occur. The caller must have disabled interrupts. - * - * Note that the Linux kernel is fully capable of entering an interrupt - * handler that it never exits, for example when doing upcalls to user mode! - * This code assumes that the idle loop never does upcalls to user mode. - * If your architecture's idle loop does do upcalls to user mode (or does - * anything else that results in unbalanced calls to the irq_enter() and - * irq_exit() functions), RCU will give you what you deserve, good and hard. - * But very infrequently and irreproducibly. - * - * Use things like work queues to work around this limitation. - * - * You have been warned. - * - * If you add or remove a call to rcu_irq_enter(), be sure to test with - * CONFIG_RCU_EQS_DEBUG=y. - */ -noinstr void rcu_irq_enter(void) -{ - lockdep_assert_irqs_disabled(); - rcu_nmi_enter(); -} - -/* - * Wrapper for rcu_irq_enter() where interrupts are enabled. - * - * If you add or remove a call to rcu_irq_enter_irqson(), be sure to test - * with CONFIG_RCU_EQS_DEBUG=y. - */ -void rcu_irq_enter_irqson(void) -{ - unsigned long flags; - - local_irq_save(flags); - rcu_irq_enter(); - local_irq_restore(flags); -} - /* * Check to see if any future non-offloaded RCU-related work will need * to be done by the current CPU, even if none need be done immediately, @@ -1227,7 +803,7 @@ static void rcu_gpnum_ovf(struct rcu_node *rnp, struct rcu_data *rdp) */ static int dyntick_save_progress_counter(struct rcu_data *rdp) { - rdp->dynticks_snap = rcu_dynticks_snap(rdp); + rdp->dynticks_snap = rcu_dynticks_snap(rdp->cpu); if (rcu_dynticks_in_eqs(rdp->dynticks_snap)) { trace_rcu_fqs(rcu_state.name, rdp->gp_seq, rdp->cpu, TPS("dti")); rcu_gpnum_ovf(rdp->mynode, rdp); @@ -4328,13 +3904,14 @@ static void rcu_init_new_rnp(struct rcu_node *rnp_leaf) static void __init rcu_boot_init_percpu_data(int cpu) { + struct context_tracking *ct = this_cpu_ptr(&context_tracking); struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); /* Set up local state, ensuring consistent view of global state. */ rdp->grpmask = leaf_node_cpu_bit(rdp->mynode, cpu); INIT_WORK(&rdp->strict_work, strict_work_handler); - WARN_ON_ONCE(rdp->dynticks_nesting != 1); - WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp))); + WARN_ON_ONCE(ct->dynticks_nesting != 1); + WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(cpu))); rdp->barrier_seq_snap = rcu_state.barrier_sequence; rdp->rcu_ofl_gp_seq = rcu_state.gp_seq; rdp->rcu_ofl_gp_flags = RCU_GP_CLEANED; @@ -4358,6 +3935,7 @@ rcu_boot_init_percpu_data(int cpu) int rcutree_prepare_cpu(unsigned int cpu) { unsigned long flags; + struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); struct rcu_node *rnp = rcu_get_root(); @@ -4366,7 +3944,7 @@ int rcutree_prepare_cpu(unsigned int cpu) rdp->qlen_last_fqs_check = 0; rdp->n_force_qs_snap = READ_ONCE(rcu_state.n_force_qs); rdp->blimit = blimit; - rdp->dynticks_nesting = 1; /* CPU not up, no tearing. */ + ct->dynticks_nesting = 1; /* CPU not up, no tearing. */ raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ /* diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 3cdc18997a38..d4a97e40ea9c 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -191,9 +191,6 @@ struct rcu_data { /* 3) dynticks interface. */ int dynticks_snap; /* Per-GP tracking for dynticks. */ - long dynticks_nesting; /* Track process nesting level. */ - long dynticks_nmi_nesting; /* Track irq/NMI nesting level. */ - atomic_t dynticks; /* Even value for idle, else odd. */ bool rcu_need_heavy_qs; /* GP old, so heavy quiescent state! */ bool rcu_urgent_qs; /* GP old need light quiescent state. */ bool rcu_forced_tick; /* Forced tick to provide QS. */ @@ -438,7 +435,6 @@ static void rcu_cpu_kthread_setup(unsigned int cpu); static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp); static bool rcu_preempt_has_tasks(struct rcu_node *rnp); static bool rcu_preempt_need_deferred_qs(struct task_struct *t); -static void rcu_preempt_deferred_qs(struct task_struct *t); static void zero_cpu_stall_ticks(struct rcu_data *rdp); static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp); static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq); @@ -478,10 +474,6 @@ do { \ static void rcu_bind_gp_kthread(void); static bool rcu_nohz_full_cpu(void); -static void rcu_dynticks_task_enter(void); -static void rcu_dynticks_task_exit(void); -static void rcu_dynticks_task_trace_enter(void); -static void rcu_dynticks_task_trace_exit(void); /* Forward declarations for tree_stall.h */ static void record_gp_stall_check_time(void); diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index f092c7f18a5f..be667583a554 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -358,7 +358,7 @@ static void __sync_rcu_exp_select_node_cpus(struct rcu_exp_work *rewp) !(rnp->qsmaskinitnext & mask)) { mask_ofl_test |= mask; } else { - snap = rcu_dynticks_snap(rdp); + snap = rcu_dynticks_snap(cpu); if (rcu_dynticks_in_eqs(snap)) mask_ofl_test |= mask; else diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 7ae1551479a2..438ecae6bd7e 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -595,7 +595,7 @@ static notrace bool rcu_preempt_need_deferred_qs(struct task_struct *t) * evaluate safety in terms of interrupt, softirq, and preemption * disabling. */ -static notrace void rcu_preempt_deferred_qs(struct task_struct *t) +notrace void rcu_preempt_deferred_qs(struct task_struct *t) { unsigned long flags; @@ -935,7 +935,7 @@ static notrace bool rcu_preempt_need_deferred_qs(struct task_struct *t) // period for a quiescent state from this CPU. Note that requests from // tasks are handled when removing the task from the blocked-tasks list // below. -static notrace void rcu_preempt_deferred_qs(struct task_struct *t) +notrace void rcu_preempt_deferred_qs(struct task_struct *t) { struct rcu_data *rdp = this_cpu_ptr(&rcu_data); @@ -1296,37 +1296,3 @@ static void rcu_bind_gp_kthread(void) return; housekeeping_affine(current, HK_TYPE_RCU); } - -/* Record the current task on dyntick-idle entry. */ -static __always_inline void rcu_dynticks_task_enter(void) -{ -#if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) - WRITE_ONCE(current->rcu_tasks_idle_cpu, smp_processor_id()); -#endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */ -} - -/* Record no current task on dyntick-idle exit. */ -static __always_inline void rcu_dynticks_task_exit(void) -{ -#if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) - WRITE_ONCE(current->rcu_tasks_idle_cpu, -1); -#endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */ -} - -/* Turn on heavyweight RCU tasks trace readers on idle/user entry. */ -static __always_inline void rcu_dynticks_task_trace_enter(void) -{ -#ifdef CONFIG_TASKS_TRACE_RCU - if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB)) - current->trc_reader_special.b.need_mb = true; -#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ -} - -/* Turn off heavyweight RCU tasks trace readers on idle/user exit. */ -static __always_inline void rcu_dynticks_task_trace_exit(void) -{ -#ifdef CONFIG_TASKS_TRACE_RCU - if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB)) - current->trc_reader_special.b.need_mb = false; -#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ -} diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index 4995c078cff9..195cad14742d 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -409,7 +409,19 @@ static bool rcu_is_gp_kthread_starving(unsigned long *jp) static bool rcu_is_rcuc_kthread_starving(struct rcu_data *rdp, unsigned long *jp) { - unsigned long j = jiffies - READ_ONCE(rdp->rcuc_activity); + int cpu; + struct task_struct *rcuc; + unsigned long j; + + rcuc = rdp->rcu_cpu_kthread_task; + if (!rcuc) + return false; + + cpu = task_cpu(rcuc); + if (cpu_is_offline(cpu) || idle_cpu(cpu)) + return false; + + j = jiffies - READ_ONCE(rdp->rcuc_activity); if (jp) *jp = j; @@ -434,6 +446,9 @@ static void print_cpu_stall_info(int cpu) struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); char *ticks_title; unsigned long ticks_value; + bool rcuc_starved; + unsigned long j; + char buf[32]; /* * We could be printing a lot while holding a spinlock. Avoid @@ -450,8 +465,11 @@ static void print_cpu_stall_info(int cpu) } delta = rcu_seq_ctr(rdp->mynode->gp_seq - rdp->rcu_iw_gp_seq); falsepositive = rcu_is_gp_kthread_starving(NULL) && - rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp)); - pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s\n", + rcu_dynticks_in_eqs(rcu_dynticks_snap(cpu)); + rcuc_starved = rcu_is_rcuc_kthread_starving(rdp, &j); + if (rcuc_starved) + sprintf(buf, " rcuc=%ld jiffies(starved)", j); + pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%04x/%ld/%#lx softirq=%u/%u fqs=%ld%s%s\n", cpu, "O."[!!cpu_online(cpu)], "o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)], @@ -460,36 +478,14 @@ static void print_cpu_stall_info(int cpu) rdp->rcu_iw_pending ? (int)min(delta, 9UL) + '0' : "!."[!delta], ticks_value, ticks_title, - rcu_dynticks_snap(rdp) & 0xfff, - rdp->dynticks_nesting, rdp->dynticks_nmi_nesting, + rcu_dynticks_snap(cpu) & 0xffff, + ct_dynticks_nesting_cpu(cpu), ct_dynticks_nmi_nesting_cpu(cpu), rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu), data_race(rcu_state.n_force_qs) - rcu_state.n_force_qs_gpstart, + rcuc_starved ? buf : "", falsepositive ? " (false positive?)" : ""); } -static void rcuc_kthread_dump(struct rcu_data *rdp) -{ - int cpu; - unsigned long j; - struct task_struct *rcuc; - - rcuc = rdp->rcu_cpu_kthread_task; - if (!rcuc) - return; - - cpu = task_cpu(rcuc); - if (cpu_is_offline(cpu) || idle_cpu(cpu)) - return; - - if (!rcu_is_rcuc_kthread_starving(rdp, &j)) - return; - - pr_err("%s kthread starved for %ld jiffies\n", rcuc->comm, j); - sched_show_task(rcuc); - if (!trigger_single_cpu_backtrace(cpu)) - dump_cpu_task(cpu); -} - /* Complain about starvation of grace-period kthread. */ static void rcu_check_gp_kthread_starvation(void) { @@ -662,9 +658,6 @@ static void print_cpu_stall(unsigned long gps) rcu_check_gp_kthread_expired_fqs_timer(); rcu_check_gp_kthread_starvation(); - if (!use_softirq) - rcuc_kthread_dump(rdp); - rcu_dump_cpu_stacks(); raw_spin_lock_irqsave_rcu_node(rnp, flags); diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 2e93acad1e31..738842c4886b 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -85,7 +85,7 @@ module_param(rcu_normal_after_boot, int, 0444); * and while lockdep is disabled. * * Note that if the CPU is in the idle loop from an RCU point of view (ie: - * that we are in the section between rcu_idle_enter() and rcu_idle_exit()) + * that we are in the section between ct_idle_enter() and ct_idle_exit()) * then rcu_read_lock_held() sets ``*ret`` to false even if the CPU did an * rcu_read_lock(). The reason for this is that RCU ignores CPUs that are * in such a section, considering these as in extended quiescent state, diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 9568019be124..f53c0096860b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6591,7 +6591,7 @@ void __sched schedule_idle(void) } while (need_resched()); } -#if defined(CONFIG_CONTEXT_TRACKING) && !defined(CONFIG_HAVE_CONTEXT_TRACKING_OFFSTACK) +#if defined(CONFIG_CONTEXT_TRACKING_USER) && !defined(CONFIG_HAVE_CONTEXT_TRACKING_USER_OFFSTACK) asmlinkage __visible void __sched schedule_user(void) { /* diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 328cccbee444..f26ab2675f7d 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -53,14 +53,14 @@ static noinline int __cpuidle cpu_idle_poll(void) { trace_cpu_idle(0, smp_processor_id()); stop_critical_timings(); - rcu_idle_enter(); + ct_idle_enter(); local_irq_enable(); while (!tif_need_resched() && (cpu_idle_force_poll || tick_check_broadcast_expired())) cpu_relax(); - rcu_idle_exit(); + ct_idle_exit(); start_critical_timings(); trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id()); @@ -98,12 +98,12 @@ void __cpuidle default_idle_call(void) * * Trace IRQs enable here, then switch off RCU, and have * arch_cpu_idle() use raw_local_irq_enable(). Note that - * rcu_idle_enter() relies on lockdep IRQ state, so switch that + * ct_idle_enter() relies on lockdep IRQ state, so switch that * last -- this is very similar to the entry code. */ trace_hardirqs_on_prepare(); lockdep_hardirqs_on_prepare(); - rcu_idle_enter(); + ct_idle_enter(); lockdep_hardirqs_on(_THIS_IP_); arch_cpu_idle(); @@ -116,7 +116,7 @@ void __cpuidle default_idle_call(void) */ raw_local_irq_disable(); lockdep_hardirqs_off(_THIS_IP_); - rcu_idle_exit(); + ct_idle_exit(); lockdep_hardirqs_on(_THIS_IP_); raw_local_irq_enable(); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 47b89a0fc6e5..0cfe2d0af294 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -27,6 +27,7 @@ #include <linux/capability.h> #include <linux/cgroup_api.h> #include <linux/cgroup.h> +#include <linux/context_tracking.h> #include <linux/cpufreq.h> #include <linux/cpumask_api.h> #include <linux/ctype.h> diff --git a/kernel/softirq.c b/kernel/softirq.c index 9f0aef8aa9ff..c8a6913c067d 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -620,7 +620,7 @@ void irq_enter_rcu(void) */ void irq_enter(void) { - rcu_irq_enter(); + ct_irq_enter(); irq_enter_rcu(); } @@ -672,7 +672,7 @@ void irq_exit_rcu(void) void irq_exit(void) { __irq_exit_rcu(); - rcu_irq_exit(); + ct_irq_exit(); /* must be last! */ lockdep_hardirq_exit(); } diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index 27b7868b5c30..a41753be1a2b 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -73,6 +73,15 @@ config TIME_KUNIT_TEST If unsure, say N. +config CONTEXT_TRACKING + bool + +config CONTEXT_TRACKING_IDLE + bool + select CONTEXT_TRACKING + help + Tracks idle state on behalf of RCU. + if GENERIC_CLOCKEVENTS menu "Timers subsystem" @@ -111,7 +120,7 @@ config NO_HZ_FULL # NO_HZ_COMMON dependency # We need at least one periodic CPU for timekeeping depends on SMP - depends on HAVE_CONTEXT_TRACKING + depends on HAVE_CONTEXT_TRACKING_USER # VIRT_CPU_ACCOUNTING_GEN dependency depends on HAVE_VIRT_CPU_ACCOUNTING_GEN select NO_HZ_COMMON @@ -137,31 +146,37 @@ config NO_HZ_FULL endchoice -config CONTEXT_TRACKING - bool +config CONTEXT_TRACKING_USER + bool + depends on HAVE_CONTEXT_TRACKING_USER + select CONTEXT_TRACKING + help + Track transitions between kernel and user on behalf of RCU and + tickless cputime accounting. The former case relies on context + tracking to enter/exit RCU extended quiescent states. -config CONTEXT_TRACKING_FORCE - bool "Force context tracking" - depends on CONTEXT_TRACKING +config CONTEXT_TRACKING_USER_FORCE + bool "Force user context tracking" + depends on CONTEXT_TRACKING_USER default y if !NO_HZ_FULL help The major pre-requirement for full dynticks to work is to - support the context tracking subsystem. But there are also + support the user context tracking subsystem. But there are also other dependencies to provide in order to make the full dynticks working. This option stands for testing when an arch implements the - context tracking backend but doesn't yet fulfill all the + user context tracking backend but doesn't yet fulfill all the requirements to make the full dynticks feature working. Without the full dynticks, there is no way to test the support - for context tracking and the subsystems that rely on it: RCU + for user context tracking and the subsystems that rely on it: RCU userspace extended quiescent state and tickless cputime accounting. This option copes with the absence of the full - dynticks subsystem by forcing the context tracking on all + dynticks subsystem by forcing the user context tracking on all CPUs in the system. Say Y only if you're working on the development of an - architecture backend for the context tracking. + architecture backend for the user context tracking. Say N otherwise, this option brings an overhead that you don't want in production. diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 58a11f859ac7..de192dcff828 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -571,7 +571,7 @@ void __init tick_nohz_init(void) } for_each_cpu(cpu, tick_nohz_full_mask) - context_tracking_cpu_set(cpu); + ct_cpu_track_user(cpu); ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "kernel/nohz:predown", NULL, diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 2c95992e2c71..5fc7f17f5ec7 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3105,17 +3105,17 @@ void __trace_stack(struct trace_array *tr, unsigned int trace_ctx, } /* - * When an NMI triggers, RCU is enabled via rcu_nmi_enter(), + * When an NMI triggers, RCU is enabled via ct_nmi_enter(), * but if the above rcu_is_watching() failed, then the NMI - * triggered someplace critical, and rcu_irq_enter() should + * triggered someplace critical, and ct_irq_enter() should * not be called from NMI. */ if (unlikely(in_nmi())) return; - rcu_irq_enter_irqson(); + ct_irq_enter_irqson(); __ftrace_trace_stack(buffer, trace_ctx, skip, NULL); - rcu_irq_exit_irqson(); + ct_irq_exit_irqson(); } /** |