diff options
Diffstat (limited to 'kernel/rcu/tree.c')
-rw-r--r-- | kernel/rcu/tree.c | 2814 |
1 files changed, 1901 insertions, 913 deletions
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index d91c9156fab2..93416afebd59 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1,12 +1,12 @@ // SPDX-License-Identifier: GPL-2.0+ /* - * Read-Copy Update mechanism for mutual exclusion + * Read-Copy Update mechanism for mutual exclusion (tree-based version) * * Copyright IBM Corporation, 2008 * * Authors: Dipankar Sarma <dipankar@in.ibm.com> * Manfred Spraul <manfred@colorfullife.com> - * Paul E. McKenney <paulmck@linux.ibm.com> Hierarchical version + * Paul E. McKenney <paulmck@linux.ibm.com> * * Based on the original work by Paul McKenney <paulmck@linux.ibm.com> * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen. @@ -32,6 +32,8 @@ #include <linux/export.h> #include <linux/completion.h> #include <linux/moduleparam.h> +#include <linux/panic.h> +#include <linux/panic_notifier.h> #include <linux/percpu.h> #include <linux/notifier.h> #include <linux/cpu.h> @@ -57,6 +59,10 @@ #include <linux/slab.h> #include <linux/sched/isolation.h> #include <linux/sched/clock.h> +#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" @@ -69,39 +75,33 @@ /* Data structures. */ -/* - * Steal a bit from the bottom of ->dynticks for idle entry/exit - * control. Initially this is for TLB flushing. - */ -#define RCU_DYNTICK_CTRL_MASK 0x1 -#define RCU_DYNTICK_CTRL_CTR (RCU_DYNTICK_CTRL_MASK + 1) -#ifndef rcu_eqs_special_exit -#define rcu_eqs_special_exit() do { } while (0) -#endif - static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, rcu_data) = { - .dynticks_nesting = 1, - .dynticks_nmi_nesting = DYNTICK_IRQ_NONIDLE, - .dynticks = ATOMIC_INIT(RCU_DYNTICK_CTRL_CTR), + .gpwrap = true, +#ifdef CONFIG_RCU_NOCB_CPU + .cblist.flags = SEGCBLIST_RCU_CORE, +#endif }; static struct rcu_state rcu_state = { .level = { &rcu_state.node[0] }, .gp_state = RCU_GP_IDLE, .gp_seq = (0UL - 300UL) << RCU_SEQ_CTR_SHIFT, .barrier_mutex = __MUTEX_INITIALIZER(rcu_state.barrier_mutex), + .barrier_lock = __RAW_SPIN_LOCK_UNLOCKED(rcu_state.barrier_lock), .name = RCU_NAME, .abbr = RCU_ABBR, .exp_mutex = __MUTEX_INITIALIZER(rcu_state.exp_mutex), .exp_wake_mutex = __MUTEX_INITIALIZER(rcu_state.exp_wake_mutex), - .ofl_lock = __RAW_SPIN_LOCK_UNLOCKED(rcu_state.ofl_lock), + .ofl_lock = __ARCH_SPIN_LOCK_UNLOCKED, }; /* Dump rcu_node combining tree at boot to verify correct setup. */ static bool dump_tree; module_param(dump_tree, bool, 0444); /* By default, use RCU_SOFTIRQ instead of rcuc kthreads. */ -static bool use_softirq = 1; +static bool use_softirq = !IS_ENABLED(CONFIG_PREEMPT_RT); +#ifndef CONFIG_PREEMPT_RT module_param(use_softirq, bool, 0444); +#endif /* Control rcu_node-tree auto-balancing at boot time. */ static bool rcu_fanout_exact; module_param(rcu_fanout_exact, bool, 0444); @@ -150,8 +150,14 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) static void invoke_rcu_core(void); static void rcu_report_exp_rdp(struct rcu_data *rdp); static void sync_sched_exp_online_cleanup(int cpu); +static void check_cb_ovld_locked(struct rcu_data *rdp, struct rcu_node *rnp); +static bool rcu_rdp_is_offloaded(struct rcu_data *rdp); -/* rcuc/rcub kthread realtime priority */ +/* + * rcuc/rcub/rcuop kthread realtime priority. The "rcuop" + * real-time priority(enabling/disabling) is controlled by + * the extra CONFIG_RCU_NOCB_CPU_CB_BOOST configuration. + */ static int kthread_prio = IS_ENABLED(CONFIG_RCU_BOOST) ? 1 : 0; module_param(kthread_prio, int, 0444); @@ -164,6 +170,32 @@ module_param(gp_init_delay, int, 0444); static int gp_cleanup_delay; module_param(gp_cleanup_delay, int, 0444); +// Add delay to rcu_read_unlock() for strict grace periods. +static int rcu_unlock_delay; +#ifdef CONFIG_RCU_STRICT_GRACE_PERIOD +module_param(rcu_unlock_delay, int, 0444); +#endif + +/* + * This rcu parameter is runtime-read-only. It reflects + * a minimum allowed number of objects which can be cached + * per-CPU. Object size is equal to one page. This value + * can be changed at boot time. + */ +static int rcu_min_cached_objs = 5; +module_param(rcu_min_cached_objs, int, 0444); + +// A page shrinker can ask for pages to be freed to make them +// available for other parts of the system. This usually happens +// under low memory conditions, and in that case we should also +// defer page-cache filling for a short time period. +// +// The default value is 5 seconds, which is long enough to reduce +// interference with the shrinker while it asks other systems to +// drain their caches. +static int rcu_delay_page_cache_fill_msec = 5000; +module_param(rcu_delay_page_cache_fill_msec, int, 0444); + /* Retrieve RCU kthreads priority for rcutorture */ int rcu_get_gp_kthreads_prio(void) { @@ -180,7 +212,7 @@ EXPORT_SYMBOL_GPL(rcu_get_gp_kthreads_prio); * the need for long delays to increase some race probabilities with the * need for fast grace periods to increase other race probabilities. */ -#define PER_RCU_NODE_PERIOD 3 /* Number of grace periods between delays. */ +#define PER_RCU_NODE_PERIOD 3 /* Number of grace periods between delays for debugging. */ /* * Compute the mask of online CPUs for the specified rcu_node structure. @@ -194,6 +226,16 @@ static unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp) } /* + * Is the CPU corresponding to the specified rcu_data structure online + * from RCU's perspective? This perspective is given by that structure's + * ->qsmaskinitnext field rather than by the global cpu_online_mask. + */ +static bool rcu_rdp_cpu_online(struct rcu_data *rdp) +{ + return !!(rdp->grpmask & rcu_rnp_online_cpus(rdp->mynode)); +} + +/* * Return true if an RCU grace period is in progress. The READ_ONCE()s * permit this function to be invoked without holding the root rcu_node * structure's ->lock, but of course results can be subject to change. @@ -220,54 +262,7 @@ void rcu_softirq_qs(void) { rcu_qs(); rcu_preempt_deferred_qs(current); -} - -/* - * Record entry into an extended quiescent state. This is only to be - * called when not already in an extended quiescent state. - */ -static void rcu_dynticks_eqs_enter(void) -{ - struct rcu_data *rdp = this_cpu_ptr(&rcu_data); - 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. - */ - seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks); - /* Better be in an extended quiescent state! */ - WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && - (seq & RCU_DYNTICK_CTRL_CTR)); - /* Better not have special action (TLB flush) pending! */ - WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && - (seq & RCU_DYNTICK_CTRL_MASK)); -} - -/* - * Record exit from an extended quiescent state. This is only to be - * called from an extended quiescent state. - */ -static void rcu_dynticks_eqs_exit(void) -{ - struct rcu_data *rdp = this_cpu_ptr(&rcu_data); - 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 = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks); - WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && - !(seq & RCU_DYNTICK_CTRL_CTR)); - if (seq & RCU_DYNTICK_CTRL_MASK) { - atomic_andnot(RCU_DYNTICK_CTRL_MASK, &rdp->dynticks); - smp_mb__after_atomic(); /* _exit after clearing mask. */ - /* Prefer duplicate flushes to losing a flush. */ - rcu_eqs_special_exit(); - } + rcu_tasks_qs(current, false); } /* @@ -282,34 +277,19 @@ static 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) & RCU_DYNTICK_CTRL_CTR) + if (ct_dynticks() & RCU_DYNTICKS_IDX) return; - atomic_add(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks); -} - -/* - * Is the current CPU in an extended quiescent state? - * - * No ordering, as we are sampling CPU-local information. - */ -static bool rcu_dynticks_curr_cpu_in_eqs(void) -{ - struct rcu_data *rdp = this_cpu_ptr(&rcu_data); - - return !(atomic_read(&rdp->dynticks) & RCU_DYNTICK_CTRL_CTR); + 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) { - int snap = atomic_add_return(0, &rdp->dynticks); - - return snap & ~RCU_DYNTICK_CTRL_MASK; + smp_mb(); // Fundamental RCU ordering guarantee. + return ct_dynticks_cpu_acquire(cpu); } /* @@ -318,7 +298,13 @@ static int rcu_dynticks_snap(struct rcu_data *rdp) */ static bool rcu_dynticks_in_eqs(int snap) { - return !(snap & RCU_DYNTICK_CTRL_CTR); + 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) +{ + return rcu_dynticks_in_eqs(rcu_dynticks_snap(cpu)); } /* @@ -328,29 +314,26 @@ static bool rcu_dynticks_in_eqs(int snap) */ 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); } /* - * Set the special (bottom) bit of the specified CPU so that it - * will take special action (such as flushing its TLB) on the - * next exit from an extended quiescent state. Returns true if - * the bit was successfully set, or false if the CPU was not in - * an extended quiescent state. + * Return true if the referenced integer is zero while the specified + * CPU remains within a single extended quiescent state. */ -bool rcu_eqs_special_set(int cpu) +bool rcu_dynticks_zero_in_eqs(int cpu, int *vp) { - int old; - int new; - struct rcu_data *rdp = &per_cpu(rcu_data, cpu); + int snap; - do { - old = atomic_read(&rdp->dynticks); - if (old & RCU_DYNTICK_CTRL_CTR) - return false; - new = old | RCU_DYNTICK_CTRL_MASK; - } while (atomic_cmpxchg(&rdp->dynticks, old, new) != old); - return true; + // If not quiescent, force back to earlier extended quiescent state. + 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 == ct_dynticks_cpu(cpu); } /* @@ -364,58 +347,76 @@ bool rcu_eqs_special_set(int cpu) * * The caller must have disabled interrupts and must not be idle. */ -void rcu_momentary_dyntick_idle(void) +notrace void rcu_momentary_dyntick_idle(void) { - int special; + int seq; raw_cpu_write(rcu_data.rcu_need_heavy_qs, false); - special = atomic_add_return(2 * RCU_DYNTICK_CTRL_CTR, - &this_cpu_ptr(&rcu_data)->dynticks); + seq = ct_state_inc(2 * RCU_DYNTICKS_IDX); /* It is illegal to call this from idle state. */ - WARN_ON_ONCE(!(special & RCU_DYNTICK_CTRL_CTR)); + WARN_ON_ONCE(!(seq & RCU_DYNTICKS_IDX)); rcu_preempt_deferred_qs(current); } EXPORT_SYMBOL_GPL(rcu_momentary_dyntick_idle); /** - * rcu_is_cpu_rrupt_from_idle - see if interrupted from idle + * rcu_is_cpu_rrupt_from_idle - see if 'interrupted' from idle * * If the current CPU is idle and running at a first-level (not nested) - * interrupt from idle, return true. The caller must have at least - * disabled preemption. + * interrupt, or directly, from idle, return true. + * + * The caller must have at least disabled IRQs. */ static int rcu_is_cpu_rrupt_from_idle(void) { - /* Called only from within the scheduling-clock interrupt */ - lockdep_assert_in_irq(); + long nesting; + + /* + * Usually called from the tick; but also used from smp_function_call() + * for expedited grace periods. This latter can result in running from + * the idle task, instead of an actual IPI. + */ + 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? */ - if (__this_cpu_read(rcu_data.dynticks_nmi_nesting) != 1) + nesting = ct_dynticks_nmi_nesting(); + if (nesting > 1) return false; + /* + * If we're not in an interrupt, we must be in the idle task! + */ + 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 10 /* Maximum callbacks per rcu_do_batch ... */ -#define DEFAULT_MAX_RCU_BLIMIT 10000 /* ... even during callback flood. */ +#define DEFAULT_RCU_BLIMIT (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) ? 1000 : 10) + // Maximum callbacks per rcu_do_batch ... +#define DEFAULT_MAX_RCU_BLIMIT 10000 // ... even during callback flood. static long blimit = DEFAULT_RCU_BLIMIT; -#define DEFAULT_RCU_QHIMARK 10000 /* If this many pending, ignore blimit. */ +#define DEFAULT_RCU_QHIMARK 10000 // If this many pending, ignore blimit. static long qhimark = DEFAULT_RCU_QHIMARK; -#define DEFAULT_RCU_QLOMARK 100 /* Once only this many pending, use blimit. */ +#define DEFAULT_RCU_QLOMARK 100 // Once only this many pending, use blimit. static long qlowmark = DEFAULT_RCU_QLOMARK; +#define DEFAULT_RCU_QOVLD_MULT 2 +#define DEFAULT_RCU_QOVLD (DEFAULT_RCU_QOVLD_MULT * DEFAULT_RCU_QHIMARK) +static long qovld = DEFAULT_RCU_QOVLD; // If this many pending, hammer QS. +static long qovld_calc = -1; // No pre-initialization lock acquisitions! module_param(blimit, long, 0444); module_param(qhimark, long, 0444); module_param(qlowmark, long, 0444); +module_param(qovld, long, 0444); -static ulong jiffies_till_first_fqs = ULONG_MAX; +static ulong jiffies_till_first_fqs = IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) ? 0 : ULONG_MAX; static ulong jiffies_till_next_fqs = ULONG_MAX; static bool rcu_kick_kthreads; static int rcu_divisor = 7; @@ -482,12 +483,12 @@ static int param_set_next_fqs_jiffies(const char *val, const struct kernel_param return ret; } -static struct kernel_param_ops first_fqs_jiffies_ops = { +static const struct kernel_param_ops first_fqs_jiffies_ops = { .set = param_set_first_fqs_jiffies, .get = param_get_ulong, }; -static struct kernel_param_ops next_fqs_jiffies_ops = { +static const struct kernel_param_ops next_fqs_jiffies_ops = { .set = param_set_next_fqs_jiffies, .get = param_get_ulong, }; @@ -545,346 +546,142 @@ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, } EXPORT_SYMBOL_GPL(rcutorture_get_gp_data); +#if defined(CONFIG_NO_HZ_FULL) && (!defined(CONFIG_GENERIC_ENTRY) || !defined(CONFIG_KVM_XFER_TO_GUEST_WORK)) /* - * 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. + * An empty function that will trigger a reschedule on + * IRQ tail once IRQs get re-enabled on userspace/guest resume. */ -static void rcu_eqs_enter(bool user) +static void late_wakeup_func(struct irq_work *work) { - 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) { - rdp->dynticks_nesting--; - return; - } - - lockdep_assert_irqs_disabled(); - 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)); - rdp = this_cpu_ptr(&rcu_data); - do_nocb_deferred_wakeup(rdp); - rcu_prepare_for_idle(); - rcu_preempt_deferred_qs(current); - WRITE_ONCE(rdp->dynticks_nesting, 0); /* Avoid irq-access tearing. */ - rcu_dynticks_eqs_enter(); - 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); -} - -#ifdef CONFIG_NO_HZ_FULL -/** - * 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. - */ -void rcu_user_enter(void) -{ - lockdep_assert_irqs_disabled(); - rcu_eqs_enter(true); -} -#endif /* CONFIG_NO_HZ_FULL */ +static DEFINE_PER_CPU(struct irq_work, late_wakeup_work) = + IRQ_WORK_INIT(late_wakeup_func); /* - * 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 either: + * + * 1) the task is about to enter in guest mode and $ARCH doesn't support KVM generic work + * 2) the task is about to enter in user mode and $ARCH doesn't support generic entry. * - * If you add or remove a call to rcu_nmi_exit_common(), be sure to test - * with CONFIG_RCU_EQS_DEBUG=y. + * In these cases the late RCU wake ups aren't supported in the resched loops and our + * last resort is to fire a local irq_work that will trigger a reschedule once IRQs + * get re-enabled again. */ -static __always_inline void rcu_nmi_exit_common(bool irq) +noinstr void rcu_irq_work_resched(void) { struct rcu_data *rdp = this_cpu_ptr(&rcu_data); - /* - * 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); + if (IS_ENABLED(CONFIG_GENERIC_ENTRY) && !(current->flags & PF_VCPU)) 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. */ - - if (irq) - rcu_prepare_for_idle(); - - rcu_dynticks_eqs_enter(); - - if (irq) - rcu_dynticks_task_enter(); -} - -/** - * rcu_nmi_exit - inform RCU of exit from NMI context - * - * If you add or remove a call to rcu_nmi_exit(), be sure to test - * with CONFIG_RCU_EQS_DEBUG=y. - */ -void rcu_nmi_exit(void) -{ - rcu_nmi_exit_common(false); -} -/** - * 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 rcu_irq_exit(void) -{ - lockdep_assert_irqs_disabled(); - rcu_nmi_exit_common(true); -} - -/* - * 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 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) { - rdp->dynticks_nesting++; + if (IS_ENABLED(CONFIG_KVM_XFER_TO_GUEST_WORK) && (current->flags & PF_VCPU)) return; + + instrumentation_begin(); + if (do_nocb_deferred_wakeup(rdp) && need_resched()) { + irq_work_queue(this_cpu_ptr(&late_wakeup_work)); } - rcu_dynticks_task_exit(); - rcu_dynticks_eqs_exit(); - rcu_cleanup_after_idle(); - 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(); } +#endif /* #if defined(CONFIG_NO_HZ_FULL) && (!defined(CONFIG_GENERIC_ENTRY) || !defined(CONFIG_KVM_XFER_TO_GUEST_WORK)) */ +#ifdef CONFIG_PROVE_RCU /** - * 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. + * rcu_irq_exit_check_preempt - Validate that scheduling is possible */ -void rcu_idle_exit(void) +void rcu_irq_exit_check_preempt(void) { - unsigned long flags; + lockdep_assert_irqs_disabled(); - local_irq_save(flags); - rcu_eqs_exit(false); - local_irq_restore(flags); + RCU_LOCKDEP_WARN(ct_dynticks_nesting() <= 0, + "RCU dynticks_nesting counter underflow/zero!"); + 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(), + "RCU in extended quiescent state!"); } +#endif /* #ifdef CONFIG_PROVE_RCU */ #ifdef CONFIG_NO_HZ_FULL /** - * rcu_user_exit - inform RCU that we are exiting userspace. + * __rcu_irq_enter_check_tick - Enable scheduler tick on CPU if RCU needs it. * - * Exit RCU idle mode while entering the kernel because it can - * run a RCU read side critical section anytime. + * The scheduler tick is not normally enabled when CPUs enter the kernel + * from nohz_full userspace execution. After all, nohz_full userspace + * execution is an RCU quiescent state and the time executing in the kernel + * is quite short. Except of course when it isn't. And it is not hard to + * cause a large system to spend tens of seconds or even minutes looping + * in the kernel, which can cause a number of problems, include RCU CPU + * stall warnings. * - * If you add or remove a call to rcu_user_exit(), be sure to test with - * CONFIG_RCU_EQS_DEBUG=y. - */ -void rcu_user_exit(void) -{ - rcu_eqs_exit(1); -} -#endif /* CONFIG_NO_HZ_FULL */ - -/** - * rcu_nmi_enter_common - inform RCU of entry to NMI context - * @irq: Is this call from rcu_irq_enter? - * - * 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.) + * Therefore, if a nohz_full CPU fails to report a quiescent state + * in a timely manner, the RCU grace-period kthread sets that CPU's + * ->rcu_urgent_qs flag with the expectation that the next interrupt or + * exception will invoke this function, which will turn on the scheduler + * tick, which will enable RCU to detect that CPU's quiescent states, + * for example, due to cond_resched() calls in CONFIG_PREEMPT=n kernels. + * The tick will be disabled once a quiescent state is reported for + * this CPU. * - * If you add or remove a call to rcu_nmi_enter_common(), be sure to test - * with CONFIG_RCU_EQS_DEBUG=y. + * Of course, in carefully tuned systems, there might never be an + * interrupt or exception. In that case, the RCU grace-period kthread + * will eventually cause one to happen. However, in less carefully + * controlled environments, this function allows RCU to get what it + * needs without creating otherwise useless interruptions. */ -static __always_inline void rcu_nmi_enter_common(bool irq) +void __rcu_irq_enter_check_tick(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 (irq) - rcu_dynticks_task_exit(); - - rcu_dynticks_eqs_exit(); + // If we're here from NMI there's nothing to do. + if (in_nmi()) + return; - if (irq) - rcu_cleanup_after_idle(); + RCU_LOCKDEP_WARN(rcu_dynticks_curr_cpu_in_eqs(), + "Illegal rcu_irq_enter_check_tick() from extended quiescent state"); - incby = 1; - } else if (tick_nohz_full_cpu(rdp->cpu) && - rdp->dynticks_nmi_nesting == DYNTICK_IRQ_NONIDLE && - READ_ONCE(rdp->rcu_urgent_qs) && !rdp->rcu_forced_tick) { - raw_spin_lock_rcu_node(rdp->mynode); - // Recheck under lock. - if (rdp->rcu_urgent_qs && !rdp->rcu_forced_tick) { - rdp->rcu_forced_tick = true; - tick_dep_set_cpu(rdp->cpu, TICK_DEP_BIT_RCU); - } - raw_spin_unlock_rcu_node(rdp->mynode); + if (!tick_nohz_full_cpu(rdp->cpu) || + !READ_ONCE(rdp->rcu_urgent_qs) || + READ_ONCE(rdp->rcu_forced_tick)) { + // RCU doesn't need nohz_full help from this CPU, or it is + // already getting that help. + return; } - trace_rcu_dyntick(incby == 1 ? TPS("Endirq") : TPS("++="), - rdp->dynticks_nmi_nesting, - rdp->dynticks_nmi_nesting + incby, atomic_read(&rdp->dynticks)); - WRITE_ONCE(rdp->dynticks_nmi_nesting, /* Prevent store tearing. */ - rdp->dynticks_nmi_nesting + incby); - barrier(); -} - -/** - * rcu_nmi_enter - inform RCU of entry to NMI context - */ -void rcu_nmi_enter(void) -{ - rcu_nmi_enter_common(false); -} -NOKPROBE_SYMBOL(rcu_nmi_enter); -/** - * 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. - */ -void rcu_irq_enter(void) -{ - lockdep_assert_irqs_disabled(); - rcu_nmi_enter_common(true); + // We get here only when not in an extended quiescent state and + // from interrupts (as opposed to NMIs). Therefore, (1) RCU is + // already watching and (2) The fact that we are in an interrupt + // handler and that the rcu_node lock is an irq-disabled lock + // prevents self-deadlock. So we can safely recheck under the lock. + // Note that the nohz_full state currently cannot change. + raw_spin_lock_rcu_node(rdp->mynode); + if (rdp->rcu_urgent_qs && !rdp->rcu_forced_tick) { + // A nohz_full CPU is in the kernel and RCU needs a + // quiescent state. Turn on the tick! + WRITE_ONCE(rdp->rcu_forced_tick, true); + tick_dep_set_cpu(rdp->cpu, TICK_DEP_BIT_RCU); + } + raw_spin_unlock_rcu_node(rdp->mynode); } +#endif /* CONFIG_NO_HZ_FULL */ /* - * Wrapper for rcu_irq_enter() where interrupts are enabled. + * 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, + * returning 1 if so. This function is part of the RCU implementation; + * it is -not- an exported member of the RCU API. This is used by + * the idle-entry code to figure out whether it is safe to disable the + * scheduler-clock interrupt. * - * If you add or remove a call to rcu_irq_enter_irqson(), be sure to test - * with CONFIG_RCU_EQS_DEBUG=y. + * Just check whether or not this CPU has non-offloaded RCU callbacks + * queued. */ -void rcu_irq_enter_irqson(void) +int rcu_needs_cpu(void) { - unsigned long flags; - - local_irq_save(flags); - rcu_irq_enter(); - local_irq_restore(flags); + return !rcu_segcblist_empty(&this_cpu_ptr(&rcu_data)->cblist) && + !rcu_rdp_is_offloaded(this_cpu_ptr(&rcu_data)); } /* @@ -899,7 +696,7 @@ static void rcu_disable_urgency_upon_qs(struct rcu_data *rdp) WRITE_ONCE(rdp->rcu_need_heavy_qs, false); if (tick_nohz_full_cpu(rdp->cpu) && rdp->rcu_forced_tick) { tick_dep_clear_cpu(rdp->cpu, TICK_DEP_BIT_RCU); - rdp->rcu_forced_tick = false; + WRITE_ONCE(rdp->rcu_forced_tick, false); } } @@ -910,8 +707,11 @@ static void rcu_disable_urgency_upon_qs(struct rcu_data *rdp) * CPU can safely enter RCU read-side critical sections. In other words, * if the current CPU is not in its idle loop or is in an interrupt or * NMI handler, return true. + * + * Make notrace because it can be called by the internal functions of + * ftrace, and making this notrace removes unnecessary recursion calls. */ -bool notrace rcu_is_watching(void) +notrace bool rcu_is_watching(void) { bool ret; @@ -958,17 +758,22 @@ void rcu_request_urgent_qs_task(struct task_struct *t) bool rcu_lockdep_current_cpu_online(void) { struct rcu_data *rdp; - struct rcu_node *rnp; bool ret = false; if (in_nmi() || !rcu_scheduler_fully_active) return true; - preempt_disable(); + preempt_disable_notrace(); rdp = this_cpu_ptr(&rcu_data); - rnp = rdp->mynode; - if (rdp->grpmask & rcu_rnp_online_cpus(rnp)) + /* + * Strictly, we care here about the case where the current CPU is + * in rcu_cpu_starting() and thus has an excuse for rdp->grpmask + * not being up to date. So arch_spin_is_locked() might have a + * false positive if it's held by some *other* CPU, but that's + * OK because that just means a false *negative* on the warning. + */ + if (rcu_rdp_cpu_online(rdp) || arch_spin_is_locked(&rcu_state.ofl_lock)) ret = true; - preempt_enable(); + preempt_enable_notrace(); return ret; } EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online); @@ -976,7 +781,7 @@ EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online); #endif /* #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) */ /* - * We are reporting a quiescent state on behalf of some other CPU, so + * When trying to report a quiescent state on behalf of some other CPU, * it is our responsibility to check for and handle potential overflow * of the rcu_node ->gp_seq counter with respect to the rcu_data counters. * After all, the CPU might be in deep idle state, and thus executing no @@ -999,7 +804,7 @@ 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); @@ -1017,8 +822,6 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp) static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) { unsigned long jtsq; - bool *rnhqp; - bool *ruqp; struct rcu_node *rnp = rdp->mynode; /* @@ -1035,22 +838,35 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) return 1; } - /* If waiting too long on an offline CPU, complain. */ - if (!(rdp->grpmask & rcu_rnp_online_cpus(rnp)) && - time_after(jiffies, rcu_state.gp_start + HZ)) { - bool onl; + /* + * Complain if a CPU that is considered to be offline from RCU's + * perspective has not yet reported a quiescent state. After all, + * the offline CPU should have reported a quiescent state during + * the CPU-offline process, or, failing that, by rcu_gp_init() + * if it ran concurrently with either the CPU going offline or the + * last task on a leaf rcu_node structure exiting its RCU read-side + * critical section while all CPUs corresponding to that structure + * are offline. This added warning detects bugs in any of these + * code paths. + * + * The rcu_node structure's ->lock is held here, which excludes + * the relevant portions the CPU-hotplug code, the grace-period + * initialization code, and the rcu_read_unlock() code paths. + * + * For more detail, please refer to the "Hotplug CPU" section + * of RCU's Requirements documentation. + */ + if (WARN_ON_ONCE(!rcu_rdp_cpu_online(rdp))) { struct rcu_node *rnp1; - WARN_ON(1); /* Offline CPUs are supposed to report QS! */ pr_info("%s: grp: %d-%d level: %d ->gp_seq %ld ->completedqs %ld\n", __func__, rnp->grplo, rnp->grphi, rnp->level, (long)rnp->gp_seq, (long)rnp->completedqs); for (rnp1 = rnp; rnp1; rnp1 = rnp1->parent) pr_info("%s: %d:%d ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx ->rcu_gp_init_mask %#lx\n", __func__, rnp1->grplo, rnp1->grphi, rnp1->qsmask, rnp1->qsmaskinit, rnp1->qsmaskinitnext, rnp1->rcu_gp_init_mask); - onl = !!(rdp->grpmask & rcu_rnp_online_cpus(rnp)); pr_info("%s %d: %c online: %ld(%d) offline: %ld(%d)\n", - __func__, rdp->cpu, ".o"[onl], + __func__, rdp->cpu, ".o"[rcu_rdp_cpu_online(rdp)], (long)rdp->rcu_onl_gp_seq, rdp->rcu_onl_gp_flags, (long)rdp->rcu_ofl_gp_seq, rdp->rcu_ofl_gp_flags); return 1; /* Break things loose after complaining. */ @@ -1068,16 +884,15 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) * is set way high. */ jtsq = READ_ONCE(jiffies_to_sched_qs); - ruqp = per_cpu_ptr(&rcu_data.rcu_urgent_qs, rdp->cpu); - rnhqp = &per_cpu(rcu_data.rcu_need_heavy_qs, rdp->cpu); - if (!READ_ONCE(*rnhqp) && + if (!READ_ONCE(rdp->rcu_need_heavy_qs) && (time_after(jiffies, rcu_state.gp_start + jtsq * 2) || - time_after(jiffies, rcu_state.jiffies_resched))) { - WRITE_ONCE(*rnhqp, true); + time_after(jiffies, rcu_state.jiffies_resched) || + rcu_state.cbovld)) { + WRITE_ONCE(rdp->rcu_need_heavy_qs, true); /* Store rcu_need_heavy_qs before rcu_urgent_qs. */ - smp_store_release(ruqp, true); + smp_store_release(&rdp->rcu_urgent_qs, true); } else if (time_after(jiffies, rcu_state.gp_start + jtsq)) { - WRITE_ONCE(*ruqp, true); + WRITE_ONCE(rdp->rcu_urgent_qs, true); } /* @@ -1089,9 +904,9 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) * So hit them over the head with the resched_cpu() hammer! */ if (tick_nohz_full_cpu(rdp->cpu) && - time_after(jiffies, - READ_ONCE(rdp->last_fqs_resched) + jtsq * 3)) { - WRITE_ONCE(*ruqp, true); + (time_after(jiffies, READ_ONCE(rdp->last_fqs_resched) + jtsq * 3) || + rcu_state.cbovld)) { + WRITE_ONCE(rdp->rcu_urgent_qs, true); resched_cpu(rdp->cpu); WRITE_ONCE(rdp->last_fqs_resched, jiffies); } @@ -1112,7 +927,6 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) if (IS_ENABLED(CONFIG_IRQ_WORK) && !rdp->rcu_iw_pending && rdp->rcu_iw_gp_seq != rnp->gp_seq && (rnp->ffmask & rdp->grpmask)) { - init_irq_work(&rdp->rcu_iw, rcu_iw_handler); rdp->rcu_iw_pending = true; rdp->rcu_iw_gp_seq = rnp->gp_seq; irq_work_queue_on(&rdp->rcu_iw, rdp->cpu); @@ -1126,8 +940,9 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp, unsigned long gp_seq_req, const char *s) { - trace_rcu_future_grace_period(rcu_state.name, rnp->gp_seq, gp_seq_req, - rnp->level, rnp->grplo, rnp->grphi, s); + trace_rcu_future_grace_period(rcu_state.name, READ_ONCE(rnp->gp_seq), + gp_seq_req, rnp->level, + rnp->grplo, rnp->grphi, s); } /* @@ -1174,7 +989,7 @@ static bool rcu_start_this_gp(struct rcu_node *rnp_start, struct rcu_data *rdp, TPS("Prestarted")); goto unlock_out; } - rnp->gp_seq_needed = gp_seq_req; + WRITE_ONCE(rnp->gp_seq_needed, gp_seq_req); if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq))) { /* * We just marked the leaf or internal node, and a @@ -1199,18 +1014,18 @@ static bool rcu_start_this_gp(struct rcu_node *rnp_start, struct rcu_data *rdp, } trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startedroot")); WRITE_ONCE(rcu_state.gp_flags, rcu_state.gp_flags | RCU_GP_FLAG_INIT); - rcu_state.gp_req_activity = jiffies; - if (!rcu_state.gp_kthread) { + WRITE_ONCE(rcu_state.gp_req_activity, jiffies); + if (!READ_ONCE(rcu_state.gp_kthread)) { trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("NoGPkthread")); goto unlock_out; } - trace_rcu_grace_period(rcu_state.name, READ_ONCE(rcu_state.gp_seq), TPS("newreq")); + trace_rcu_grace_period(rcu_state.name, data_race(rcu_state.gp_seq), TPS("newreq")); ret = true; /* Caller must wake GP kthread. */ unlock_out: /* Push furthest requested GP to leaf node and rcu_data structure. */ if (ULONG_CMP_LT(gp_seq_req, rnp->gp_seq_needed)) { - rnp_start->gp_seq_needed = rnp->gp_seq_needed; - rdp->gp_seq_needed = rnp->gp_seq_needed; + WRITE_ONCE(rnp_start->gp_seq_needed, rnp->gp_seq_needed); + WRITE_ONCE(rdp->gp_seq_needed, rnp->gp_seq_needed); } if (rnp != rnp_start) raw_spin_unlock_rcu_node(rnp); @@ -1235,12 +1050,13 @@ static bool rcu_future_gp_cleanup(struct rcu_node *rnp) } /* - * Awaken the grace-period kthread. Don't do a self-awaken (unless in - * an interrupt or softirq handler), and don't bother awakening when there - * is nothing for the grace-period kthread to do (as in several CPUs raced - * to awaken, and we lost), and finally don't try to awaken a kthread that - * has not yet been created. If all those checks are passed, track some - * debug information and awaken. + * Awaken the grace-period kthread. Don't do a self-awaken (unless in an + * interrupt or softirq handler, in which case we just might immediately + * sleep upon return, resulting in a grace-period hang), and don't bother + * awakening when there is nothing for the grace-period kthread to do + * (as in several CPUs raced to awaken, we lost), and finally don't try + * to awaken a kthread that has not yet been created. If all those checks + * are passed, track some debug information and awaken. * * So why do the self-wakeup when in an interrupt or softirq handler * in the grace-period kthread's context? Because the kthread might have @@ -1250,10 +1066,10 @@ static bool rcu_future_gp_cleanup(struct rcu_node *rnp) */ static void rcu_gp_kthread_wake(void) { - if ((current == rcu_state.gp_kthread && - !in_irq() && !in_serving_softirq()) || - !READ_ONCE(rcu_state.gp_flags) || - !rcu_state.gp_kthread) + struct task_struct *t = READ_ONCE(rcu_state.gp_kthread); + + if ((current == t && !in_hardirq() && !in_serving_softirq()) || + !READ_ONCE(rcu_state.gp_flags) || !t) return; WRITE_ONCE(rcu_state.gp_wake_time, jiffies); WRITE_ONCE(rcu_state.gp_wake_seq, READ_ONCE(rcu_state.gp_seq)); @@ -1284,6 +1100,8 @@ static bool rcu_accelerate_cbs(struct rcu_node *rnp, struct rcu_data *rdp) if (!rcu_segcblist_pend_cbs(&rdp->cblist)) return false; + trace_rcu_segcb_stats(&rdp->cblist, TPS("SegCbPreAcc")); + /* * Callbacks are often registered with incomplete grace-period * information. Something about the fact that getting exact @@ -1300,9 +1118,12 @@ static bool rcu_accelerate_cbs(struct rcu_node *rnp, struct rcu_data *rdp) /* Trace depending on how much we were able to accelerate. */ if (rcu_segcblist_restempty(&rdp->cblist, RCU_WAIT_TAIL)) - trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("AccWaitCB")); + trace_rcu_grace_period(rcu_state.name, gp_seq_req, TPS("AccWaitCB")); else - trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("AccReadyCB")); + trace_rcu_grace_period(rcu_state.name, gp_seq_req, TPS("AccReadyCB")); + + trace_rcu_segcb_stats(&rdp->cblist, TPS("SegCbPostAcc")); + return ret; } @@ -1321,7 +1142,7 @@ static void rcu_accelerate_cbs_unlocked(struct rcu_node *rnp, rcu_lockdep_assert_cblist_protected(rdp); c = rcu_seq_snap(&rcu_state.gp_seq); - if (!rdp->gpwrap && ULONG_CMP_GE(rdp->gp_seq_needed, c)) { + if (!READ_ONCE(rdp->gpwrap) && ULONG_CMP_GE(rdp->gp_seq_needed, c)) { /* Old request still live, so mark recent callbacks. */ (void)rcu_segcblist_accelerate(&rdp->cblist, c); return; @@ -1370,14 +1191,28 @@ static void __maybe_unused rcu_advance_cbs_nowake(struct rcu_node *rnp, struct rcu_data *rdp) { rcu_lockdep_assert_cblist_protected(rdp); - if (!rcu_seq_state(rcu_seq_current(&rnp->gp_seq)) || - !raw_spin_trylock_rcu_node(rnp)) + if (!rcu_seq_state(rcu_seq_current(&rnp->gp_seq)) || !raw_spin_trylock_rcu_node(rnp)) return; - WARN_ON_ONCE(rcu_advance_cbs(rnp, rdp)); + // The grace period cannot end while we hold the rcu_node lock. + if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq))) + WARN_ON_ONCE(rcu_advance_cbs(rnp, rdp)); raw_spin_unlock_rcu_node(rnp); } /* + * In CONFIG_RCU_STRICT_GRACE_PERIOD=y kernels, attempt to generate a + * quiescent state. This is intended to be invoked when the CPU notices + * a new grace period. + */ +static void rcu_strict_gp_check_qs(void) +{ + if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) { + rcu_read_lock(); + rcu_read_unlock(); + } +} + +/* * Update CPU-local rcu_data state to record the beginnings and ends of * grace periods. The caller must hold the ->lock of the leaf rcu_node * structure corresponding to the current CPU, and must have irqs disabled. @@ -1386,9 +1221,8 @@ static void __maybe_unused rcu_advance_cbs_nowake(struct rcu_node *rnp, static bool __note_gp_changes(struct rcu_node *rnp, struct rcu_data *rdp) { bool ret = false; - bool need_gp; - const bool offloaded = IS_ENABLED(CONFIG_RCU_NOCB_CPU) && - rcu_segcblist_is_offloaded(&rdp->cblist); + bool need_qs; + const bool offloaded = rcu_rdp_is_offloaded(rdp); raw_lockdep_assert_held_rcu_node(rnp); @@ -1400,10 +1234,13 @@ static bool __note_gp_changes(struct rcu_node *rnp, struct rcu_data *rdp) unlikely(READ_ONCE(rdp->gpwrap))) { if (!offloaded) ret = rcu_advance_cbs(rnp, rdp); /* Advance CBs. */ + rdp->core_needs_qs = false; trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("cpuend")); } else { if (!offloaded) ret = rcu_accelerate_cbs(rnp, rdp); /* Recent CBs. */ + if (rdp->core_needs_qs) + rdp->core_needs_qs = !!(rnp->qsmask & rdp->grpmask); } /* Now handle the beginnings of any new-to-this-CPU grace periods. */ @@ -1415,14 +1252,16 @@ static bool __note_gp_changes(struct rcu_node *rnp, struct rcu_data *rdp) * go looking for one. */ trace_rcu_grace_period(rcu_state.name, rnp->gp_seq, TPS("cpustart")); - need_gp = !!(rnp->qsmask & rdp->grpmask); - rdp->cpu_no_qs.b.norm = need_gp; - rdp->core_needs_qs = need_gp; + need_qs = !!(rnp->qsmask & rdp->grpmask); + rdp->cpu_no_qs.b.norm = need_qs; + rdp->core_needs_qs = need_qs; zero_cpu_stall_ticks(rdp); } rdp->gp_seq = rnp->gp_seq; /* Remember new grace-period state. */ if (ULONG_CMP_LT(rdp->gp_seq_needed, rnp->gp_seq_needed) || rdp->gpwrap) - rdp->gp_seq_needed = rnp->gp_seq_needed; + WRITE_ONCE(rdp->gp_seq_needed, rnp->gp_seq_needed); + if (IS_ENABLED(CONFIG_PROVE_RCU) && READ_ONCE(rdp->gpwrap)) + WRITE_ONCE(rdp->last_sched_clock, jiffies); WRITE_ONCE(rdp->gpwrap, false); rcu_gpnum_ovf(rnp, rdp); return ret; @@ -1444,22 +1283,158 @@ static void note_gp_changes(struct rcu_data *rdp) } needwake = __note_gp_changes(rnp, rdp); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + rcu_strict_gp_check_qs(); if (needwake) rcu_gp_kthread_wake(); } +static atomic_t *rcu_gp_slow_suppress; + +/* Register a counter to suppress debugging grace-period delays. */ +void rcu_gp_slow_register(atomic_t *rgssp) +{ + WARN_ON_ONCE(rcu_gp_slow_suppress); + + WRITE_ONCE(rcu_gp_slow_suppress, rgssp); +} +EXPORT_SYMBOL_GPL(rcu_gp_slow_register); + +/* Unregister a counter, with NULL for not caring which. */ +void rcu_gp_slow_unregister(atomic_t *rgssp) +{ + WARN_ON_ONCE(rgssp && rgssp != rcu_gp_slow_suppress); + + WRITE_ONCE(rcu_gp_slow_suppress, NULL); +} +EXPORT_SYMBOL_GPL(rcu_gp_slow_unregister); + +static bool rcu_gp_slow_is_suppressed(void) +{ + atomic_t *rgssp = READ_ONCE(rcu_gp_slow_suppress); + + return rgssp && atomic_read(rgssp); +} + static void rcu_gp_slow(int delay) { - if (delay > 0 && - !(rcu_seq_ctr(rcu_state.gp_seq) % - (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay))) - schedule_timeout_uninterruptible(delay); + if (!rcu_gp_slow_is_suppressed() && delay > 0 && + !(rcu_seq_ctr(rcu_state.gp_seq) % (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay))) + schedule_timeout_idle(delay); +} + +static unsigned long sleep_duration; + +/* Allow rcutorture to stall the grace-period kthread. */ +void rcu_gp_set_torture_wait(int duration) +{ + if (IS_ENABLED(CONFIG_RCU_TORTURE_TEST) && duration > 0) + WRITE_ONCE(sleep_duration, duration); +} +EXPORT_SYMBOL_GPL(rcu_gp_set_torture_wait); + +/* Actually implement the aforementioned wait. */ +static void rcu_gp_torture_wait(void) +{ + unsigned long duration; + + if (!IS_ENABLED(CONFIG_RCU_TORTURE_TEST)) + return; + duration = xchg(&sleep_duration, 0UL); + if (duration > 0) { + pr_alert("%s: Waiting %lu jiffies\n", __func__, duration); + schedule_timeout_idle(duration); + pr_alert("%s: Wait complete\n", __func__); + } +} + +/* + * Handler for on_each_cpu() to invoke the target CPU's RCU core + * processing. + */ +static void rcu_strict_gp_boundary(void *unused) +{ + invoke_rcu_core(); +} + +// Has rcu_init() been invoked? This is used (for example) to determine +// whether spinlocks may be acquired safely. +static bool rcu_init_invoked(void) +{ + return !!rcu_state.n_online_cpus; +} + +// Make the polled API aware of the beginning of a grace period. +static void rcu_poll_gp_seq_start(unsigned long *snap) +{ + struct rcu_node *rnp = rcu_get_root(); + + if (rcu_init_invoked()) + raw_lockdep_assert_held_rcu_node(rnp); + + // If RCU was idle, note beginning of GP. + if (!rcu_seq_state(rcu_state.gp_seq_polled)) + rcu_seq_start(&rcu_state.gp_seq_polled); + + // Either way, record current state. + *snap = rcu_state.gp_seq_polled; +} + +// Make the polled API aware of the end of a grace period. +static void rcu_poll_gp_seq_end(unsigned long *snap) +{ + struct rcu_node *rnp = rcu_get_root(); + + if (rcu_init_invoked()) + raw_lockdep_assert_held_rcu_node(rnp); + + // If the previously noted GP is still in effect, record the + // end of that GP. Either way, zero counter to avoid counter-wrap + // problems. + if (*snap && *snap == rcu_state.gp_seq_polled) { + rcu_seq_end(&rcu_state.gp_seq_polled); + rcu_state.gp_seq_polled_snap = 0; + rcu_state.gp_seq_polled_exp_snap = 0; + } else { + *snap = 0; + } +} + +// Make the polled API aware of the beginning of a grace period, but +// where caller does not hold the root rcu_node structure's lock. +static void rcu_poll_gp_seq_start_unlocked(unsigned long *snap) +{ + unsigned long flags; + struct rcu_node *rnp = rcu_get_root(); + + if (rcu_init_invoked()) { + lockdep_assert_irqs_enabled(); + raw_spin_lock_irqsave_rcu_node(rnp, flags); + } + rcu_poll_gp_seq_start(snap); + if (rcu_init_invoked()) + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); +} + +// Make the polled API aware of the end of a grace period, but where +// caller does not hold the root rcu_node structure's lock. +static void rcu_poll_gp_seq_end_unlocked(unsigned long *snap) +{ + unsigned long flags; + struct rcu_node *rnp = rcu_get_root(); + + if (rcu_init_invoked()) { + lockdep_assert_irqs_enabled(); + raw_spin_lock_irqsave_rcu_node(rnp, flags); + } + rcu_poll_gp_seq_end(snap); + if (rcu_init_invoked()) + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } /* * Initialize a new grace period. Return false if no grace period required. */ -static bool rcu_gp_init(void) +static noinline_for_stack bool rcu_gp_init(void) { unsigned long flags; unsigned long oldmask; @@ -1489,24 +1464,32 @@ static bool rcu_gp_init(void) record_gp_stall_check_time(); /* Record GP times before starting GP, hence rcu_seq_start(). */ rcu_seq_start(&rcu_state.gp_seq); + ASSERT_EXCLUSIVE_WRITER(rcu_state.gp_seq); trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("start")); + rcu_poll_gp_seq_start(&rcu_state.gp_seq_polled_snap); raw_spin_unlock_irq_rcu_node(rnp); /* - * Apply per-leaf buffered online and offline operations to the - * rcu_node tree. Note that this new grace period need not wait - * for subsequent online CPUs, and that quiescent-state forcing - * will handle subsequent offline CPUs. + * Apply per-leaf buffered online and offline operations to + * the rcu_node tree. Note that this new grace period need not + * wait for subsequent online CPUs, and that RCU hooks in the CPU + * offlining path, when combined with checks in this function, + * will handle CPUs that are currently going offline or that will + * go offline later. Please also refer to "Hotplug CPU" section + * of RCU's Requirements documentation. */ - rcu_state.gp_state = RCU_GP_ONOFF; + WRITE_ONCE(rcu_state.gp_state, RCU_GP_ONOFF); + /* Exclude CPU hotplug operations. */ rcu_for_each_leaf_node(rnp) { - raw_spin_lock(&rcu_state.ofl_lock); - raw_spin_lock_irq_rcu_node(rnp); + local_irq_save(flags); + arch_spin_lock(&rcu_state.ofl_lock); + raw_spin_lock_rcu_node(rnp); if (rnp->qsmaskinit == rnp->qsmaskinitnext && !rnp->wait_blkd_tasks) { /* Nothing to do on this leaf rcu_node structure. */ - raw_spin_unlock_irq_rcu_node(rnp); - raw_spin_unlock(&rcu_state.ofl_lock); + raw_spin_unlock_rcu_node(rnp); + arch_spin_unlock(&rcu_state.ofl_lock); + local_irq_restore(flags); continue; } @@ -1541,8 +1524,9 @@ static bool rcu_gp_init(void) rcu_cleanup_dead_rnp(rnp); } - raw_spin_unlock_irq_rcu_node(rnp); - raw_spin_unlock(&rcu_state.ofl_lock); + raw_spin_unlock_rcu_node(rnp); + arch_spin_unlock(&rcu_state.ofl_lock); + local_irq_restore(flags); } rcu_gp_slow(gp_preinit_delay); /* Races with CPU hotplug. */ @@ -1558,7 +1542,7 @@ static bool rcu_gp_init(void) * The grace period cannot complete until the initialization * process finishes, because this kthread handles both. */ - rcu_state.gp_state = RCU_GP_INIT; + WRITE_ONCE(rcu_state.gp_state, RCU_GP_INIT); rcu_for_each_node_breadth_first(rnp) { rcu_gp_slow(gp_init_delay); raw_spin_lock_irqsave_rcu_node(rnp, flags); @@ -1583,6 +1567,10 @@ static bool rcu_gp_init(void) WRITE_ONCE(rcu_state.gp_activity, jiffies); } + // If strict, make all CPUs aware of new grace period. + if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) + on_each_cpu(rcu_strict_gp_boundary, NULL, 0); + return true; } @@ -1594,12 +1582,16 @@ static bool rcu_gp_fqs_check_wake(int *gfp) { struct rcu_node *rnp = rcu_get_root(); - /* Someone like call_rcu() requested a force-quiescent-state scan. */ + // If under overload conditions, force an immediate FQS scan. + if (*gfp & RCU_GP_FLAG_OVLD) + return true; + + // Someone like call_rcu() requested a force-quiescent-state scan. *gfp = READ_ONCE(rcu_state.gp_flags); if (*gfp & RCU_GP_FLAG_FQS) return true; - /* The current grace period has completed. */ + // The current grace period has completed. if (!READ_ONCE(rnp->qsmask) && !rcu_preempt_blocked_readers_cgp(rnp)) return true; @@ -1614,7 +1606,7 @@ static void rcu_gp_fqs(bool first_time) struct rcu_node *rnp = rcu_get_root(); WRITE_ONCE(rcu_state.gp_activity, jiffies); - rcu_state.n_force_qs++; + WRITE_ONCE(rcu_state.n_force_qs, rcu_state.n_force_qs + 1); if (first_time) { /* Collect dyntick-idle snapshots. */ force_qs_rnp(dyntick_save_progress_counter); @@ -1634,45 +1626,66 @@ static void rcu_gp_fqs(bool first_time) /* * Loop doing repeated quiescent-state forcing until the grace period ends. */ -static void rcu_gp_fqs_loop(void) +static noinline_for_stack void rcu_gp_fqs_loop(void) { - bool first_gp_fqs; - int gf; + bool first_gp_fqs = true; + int gf = 0; unsigned long j; int ret; struct rcu_node *rnp = rcu_get_root(); - first_gp_fqs = true; j = READ_ONCE(jiffies_till_first_fqs); + if (rcu_state.cbovld) + gf = RCU_GP_FLAG_OVLD; ret = 0; for (;;) { - if (!ret) { - rcu_state.jiffies_force_qs = jiffies + j; + if (rcu_state.cbovld) { + j = (j + 2) / 3; + if (j <= 0) + j = 1; + } + if (!ret || time_before(jiffies + j, rcu_state.jiffies_force_qs)) { + WRITE_ONCE(rcu_state.jiffies_force_qs, jiffies + j); + /* + * jiffies_force_qs before RCU_GP_WAIT_FQS state + * update; required for stall checks. + */ + smp_wmb(); WRITE_ONCE(rcu_state.jiffies_kick_kthreads, jiffies + (j ? 3 * j : 2)); } - trace_rcu_grace_period(rcu_state.name, - READ_ONCE(rcu_state.gp_seq), + trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("fqswait")); - rcu_state.gp_state = RCU_GP_WAIT_FQS; - ret = swait_event_idle_timeout_exclusive( - rcu_state.gp_wq, rcu_gp_fqs_check_wake(&gf), j); - rcu_state.gp_state = RCU_GP_DOING_FQS; + WRITE_ONCE(rcu_state.gp_state, RCU_GP_WAIT_FQS); + (void)swait_event_idle_timeout_exclusive(rcu_state.gp_wq, + rcu_gp_fqs_check_wake(&gf), j); + rcu_gp_torture_wait(); + WRITE_ONCE(rcu_state.gp_state, RCU_GP_DOING_FQS); /* Locking provides needed memory barriers. */ - /* If grace period done, leave loop. */ + /* + * Exit the loop if the root rcu_node structure indicates that the grace period + * has ended, leave the loop. The rcu_preempt_blocked_readers_cgp(rnp) check + * is required only for single-node rcu_node trees because readers blocking + * the current grace period are queued only on leaf rcu_node structures. + * For multi-node trees, checking the root node's ->qsmask suffices, because a + * given root node's ->qsmask bit is cleared only when all CPUs and tasks from + * the corresponding leaf nodes have passed through their quiescent state. + */ if (!READ_ONCE(rnp->qsmask) && !rcu_preempt_blocked_readers_cgp(rnp)) break; /* If time for quiescent-state forcing, do it. */ - if (ULONG_CMP_GE(jiffies, rcu_state.jiffies_force_qs) || - (gf & RCU_GP_FLAG_FQS)) { - trace_rcu_grace_period(rcu_state.name, - READ_ONCE(rcu_state.gp_seq), + if (!time_after(rcu_state.jiffies_force_qs, jiffies) || + (gf & (RCU_GP_FLAG_FQS | RCU_GP_FLAG_OVLD))) { + trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("fqsstart")); rcu_gp_fqs(first_gp_fqs); - first_gp_fqs = false; - trace_rcu_grace_period(rcu_state.name, - READ_ONCE(rcu_state.gp_seq), + gf = 0; + if (first_gp_fqs) { + first_gp_fqs = false; + gf = rcu_state.cbovld ? RCU_GP_FLAG_OVLD : 0; + } + trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("fqsend")); cond_resched_tasks_rcu_qs(); WRITE_ONCE(rcu_state.gp_activity, jiffies); @@ -1683,8 +1696,7 @@ static void rcu_gp_fqs_loop(void) cond_resched_tasks_rcu_qs(); WRITE_ONCE(rcu_state.gp_activity, jiffies); WARN_ON(signal_pending(current)); - trace_rcu_grace_period(rcu_state.name, - READ_ONCE(rcu_state.gp_seq), + trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("fqswaitsig")); ret = 1; /* Keep old FQS timing. */ j = jiffies; @@ -1692,6 +1704,7 @@ static void rcu_gp_fqs_loop(void) j = 1; else j = rcu_state.jiffies_force_qs - j; + gf = 0; } } } @@ -1699,10 +1712,11 @@ static void rcu_gp_fqs_loop(void) /* * Clean up after the old grace period. */ -static void rcu_gp_cleanup(void) +static noinline void rcu_gp_cleanup(void) { - unsigned long gp_duration; + int cpu; bool needgp = false; + unsigned long gp_duration; unsigned long new_gp_seq; bool offloaded; struct rcu_data *rdp; @@ -1724,6 +1738,7 @@ static void rcu_gp_cleanup(void) * safe for us to drop the lock in order to mark the grace * period as completed in all of the rcu_node structures. */ + rcu_poll_gp_seq_end(&rcu_state.gp_seq_polled_snap); raw_spin_unlock_irq_rcu_node(rnp); /* @@ -1743,11 +1758,19 @@ static void rcu_gp_cleanup(void) dump_blkd_tasks(rnp, 10); WARN_ON_ONCE(rnp->qsmask); WRITE_ONCE(rnp->gp_seq, new_gp_seq); + if (!rnp->parent) + smp_mb(); // Order against failing poll_state_synchronize_rcu_full(). rdp = this_cpu_ptr(&rcu_data); if (rnp == rdp->mynode) needgp = __note_gp_changes(rnp, rdp) || needgp; /* smp_mb() provided by prior unlock-lock pair. */ needgp = rcu_future_gp_cleanup(rnp) || needgp; + // Reset overload indication for CPUs no longer overloaded + if (rcu_is_leaf_node(rnp)) + for_each_leaf_node_cpu_mask(rnp, cpu, rnp->cbovldmask) { + rdp = per_cpu_ptr(&rcu_data, cpu); + check_cb_ovld_locked(rdp, rnp); + } sq = rcu_nocb_gp_get(rnp); raw_spin_unlock_irq_rcu_node(rnp); rcu_nocb_gp_cleanup(sq); @@ -1761,7 +1784,8 @@ static void rcu_gp_cleanup(void) /* Declare grace period done, trace first to use old GP number. */ trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("end")); rcu_seq_end(&rcu_state.gp_seq); - rcu_state.gp_state = RCU_GP_IDLE; + ASSERT_EXCLUSIVE_WRITER(rcu_state.gp_seq); + WRITE_ONCE(rcu_state.gp_state, RCU_GP_IDLE); /* Check for GP requests since above loop. */ rdp = this_cpu_ptr(&rcu_data); if (!needgp && ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed)) { @@ -1770,19 +1794,37 @@ static void rcu_gp_cleanup(void) needgp = true; } /* Advance CBs to reduce false positives below. */ - offloaded = IS_ENABLED(CONFIG_RCU_NOCB_CPU) && - rcu_segcblist_is_offloaded(&rdp->cblist); + offloaded = rcu_rdp_is_offloaded(rdp); if ((offloaded || !rcu_accelerate_cbs(rnp, rdp)) && needgp) { + + // We get here if a grace period was needed (“needgp”) + // and the above call to rcu_accelerate_cbs() did not set + // the RCU_GP_FLAG_INIT bit in ->gp_state (which records + // the need for another grace period). The purpose + // of the “offloaded” check is to avoid invoking + // rcu_accelerate_cbs() on an offloaded CPU because we do not + // hold the ->nocb_lock needed to safely access an offloaded + // ->cblist. We do not want to acquire that lock because + // it can be heavily contended during callback floods. + WRITE_ONCE(rcu_state.gp_flags, RCU_GP_FLAG_INIT); - rcu_state.gp_req_activity = jiffies; - trace_rcu_grace_period(rcu_state.name, - READ_ONCE(rcu_state.gp_seq), - TPS("newreq")); + WRITE_ONCE(rcu_state.gp_req_activity, jiffies); + trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("newreq")); } else { - WRITE_ONCE(rcu_state.gp_flags, - rcu_state.gp_flags & RCU_GP_FLAG_INIT); + + // We get here either if there is no need for an + // additional grace period or if rcu_accelerate_cbs() has + // already set the RCU_GP_FLAG_INIT bit in ->gp_flags. + // So all we need to do is to clear all of the other + // ->gp_flags bits. + + WRITE_ONCE(rcu_state.gp_flags, rcu_state.gp_flags & RCU_GP_FLAG_INIT); } raw_spin_unlock_irq_rcu_node(rnp); + + // If strict, make all CPUs aware of the end of the old grace period. + if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) + on_each_cpu(rcu_strict_gp_boundary, NULL, 0); } /* @@ -1795,22 +1837,21 @@ static int __noreturn rcu_gp_kthread(void *unused) /* Handle grace-period start. */ for (;;) { - trace_rcu_grace_period(rcu_state.name, - READ_ONCE(rcu_state.gp_seq), + trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("reqwait")); - rcu_state.gp_state = RCU_GP_WAIT_GPS; + WRITE_ONCE(rcu_state.gp_state, RCU_GP_WAIT_GPS); swait_event_idle_exclusive(rcu_state.gp_wq, READ_ONCE(rcu_state.gp_flags) & RCU_GP_FLAG_INIT); - rcu_state.gp_state = RCU_GP_DONE_GPS; + rcu_gp_torture_wait(); + WRITE_ONCE(rcu_state.gp_state, RCU_GP_DONE_GPS); /* Locking provides needed memory barrier. */ if (rcu_gp_init()) break; cond_resched_tasks_rcu_qs(); WRITE_ONCE(rcu_state.gp_activity, jiffies); WARN_ON(signal_pending(current)); - trace_rcu_grace_period(rcu_state.name, - READ_ONCE(rcu_state.gp_seq), + trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("reqwaitsig")); } @@ -1818,9 +1859,9 @@ static int __noreturn rcu_gp_kthread(void *unused) rcu_gp_fqs_loop(); /* Handle grace-period end. */ - rcu_state.gp_state = RCU_GP_CLEANUP; + WRITE_ONCE(rcu_state.gp_state, RCU_GP_CLEANUP); rcu_gp_cleanup(); - rcu_state.gp_state = RCU_GP_CLEANED; + WRITE_ONCE(rcu_state.gp_state, RCU_GP_CLEANED); } } @@ -1881,7 +1922,7 @@ static void rcu_report_qs_rnp(unsigned long mask, struct rcu_node *rnp, WARN_ON_ONCE(oldmask); /* Any child must be all zeroed! */ WARN_ON_ONCE(!rcu_is_leaf_node(rnp) && rcu_preempt_blocked_readers_cgp(rnp)); - rnp->qsmask &= ~mask; + WRITE_ONCE(rnp->qsmask, rnp->qsmask & ~mask); trace_rcu_quiescent_state_report(rcu_state.name, rnp->gp_seq, mask, rnp->qsmask, rnp->level, rnp->grplo, rnp->grphi, @@ -1904,7 +1945,7 @@ static void rcu_report_qs_rnp(unsigned long mask, struct rcu_node *rnp, rnp_c = rnp; rnp = rnp->parent; raw_spin_lock_irqsave_rcu_node(rnp, flags); - oldmask = rnp_c->qsmask; + oldmask = READ_ONCE(rnp_c->qsmask); } /* @@ -1962,15 +2003,15 @@ rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags) * structure. This must be called from the specified CPU. */ static void -rcu_report_qs_rdp(int cpu, struct rcu_data *rdp) +rcu_report_qs_rdp(struct rcu_data *rdp) { unsigned long flags; unsigned long mask; bool needwake = false; - const bool offloaded = IS_ENABLED(CONFIG_RCU_NOCB_CPU) && - rcu_segcblist_is_offloaded(&rdp->cblist); + bool needacc = false; struct rcu_node *rnp; + WARN_ON_ONCE(rdp->cpu != smp_processor_id()); rnp = rdp->mynode; raw_spin_lock_irqsave_rcu_node(rnp, flags); if (rdp->cpu_no_qs.b.norm || rdp->gp_seq != rnp->gp_seq || @@ -1987,21 +2028,37 @@ rcu_report_qs_rdp(int cpu, struct rcu_data *rdp) return; } mask = rdp->grpmask; + rdp->core_needs_qs = false; if ((rnp->qsmask & mask) == 0) { raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } else { /* * This GP can't end until cpu checks in, so all of our * callbacks can be processed during the next GP. + * + * NOCB kthreads have their own way to deal with that... */ - if (!offloaded) + if (!rcu_rdp_is_offloaded(rdp)) { needwake = rcu_accelerate_cbs(rnp, rdp); + } else if (!rcu_segcblist_completely_offloaded(&rdp->cblist)) { + /* + * ...but NOCB kthreads may miss or delay callbacks acceleration + * if in the middle of a (de-)offloading process. + */ + needacc = true; + } rcu_disable_urgency_upon_qs(rdp); rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags); /* ^^^ Released rnp->lock */ if (needwake) rcu_gp_kthread_wake(); + + if (needacc) { + rcu_nocb_lock_irqsave(rdp, flags); + rcu_accelerate_cbs_unlocked(rnp, rdp); + rcu_nocb_unlock_irqrestore(rdp, flags); + } } } @@ -2035,7 +2092,7 @@ rcu_check_quiescent_state(struct rcu_data *rdp) * Tell RCU we are done (but rcu_report_qs_rdp() will be the * judge of that). */ - rcu_report_qs_rdp(rdp->cpu, rdp); + rcu_report_qs_rdp(rdp); } /* @@ -2045,15 +2102,15 @@ rcu_check_quiescent_state(struct rcu_data *rdp) int rcutree_dying_cpu(unsigned int cpu) { bool blkd; - struct rcu_data *rdp = this_cpu_ptr(&rcu_data); + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); struct rcu_node *rnp = rdp->mynode; if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) return 0; blkd = !!(rnp->qsmask & rdp->grpmask); - trace_rcu_grace_period(rcu_state.name, rnp->gp_seq, - blkd ? TPS("cpuofl") : TPS("cpuofl-bgp")); + trace_rcu_grace_period(rcu_state.name, READ_ONCE(rnp->gp_seq), + blkd ? TPS("cpuofl-bgp") : TPS("cpuofl")); return 0; } @@ -2116,11 +2173,9 @@ int rcutree_dead_cpu(unsigned int cpu) if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) return 0; + WRITE_ONCE(rcu_state.n_online_cpus, rcu_state.n_online_cpus - 1); /* Adjust any no-longer-needed kthreads. */ rcu_boost_kthread_setaffinity(rnp, -1); - /* Do any needed no-CB deferred wakeups from this CPU. */ - do_nocb_deferred_wakeup(per_cpu_ptr(&rcu_data, cpu)); - // Stop-machine done, so allow nohz_full to disable tick. tick_dep_clear(TICK_DEP_BIT_RCU); return 0; @@ -2128,16 +2183,16 @@ int rcutree_dead_cpu(unsigned int cpu) /* * Invoke any RCU callbacks that have made it to the end of their grace - * period. Thottle as specified by rdp->blimit. + * period. Throttle as specified by rdp->blimit. */ static void rcu_do_batch(struct rcu_data *rdp) { + int div; + bool __maybe_unused empty; unsigned long flags; - const bool offloaded = IS_ENABLED(CONFIG_RCU_NOCB_CPU) && - rcu_segcblist_is_offloaded(&rdp->cblist); struct rcu_head *rhp; struct rcu_cblist rcl = RCU_CBLIST_INITIALIZER(rcl); - long bl, count; + long bl, count = 0; long pending, tlimit = 0; /* If no callbacks are ready, just return. */ @@ -2147,35 +2202,44 @@ static void rcu_do_batch(struct rcu_data *rdp) trace_rcu_batch_end(rcu_state.name, 0, !rcu_segcblist_empty(&rdp->cblist), need_resched(), is_idle_task(current), - rcu_is_callbacks_kthread()); + rcu_is_callbacks_kthread(rdp)); return; } /* - * Extract the list of ready callbacks, disabling to prevent + * Extract the list of ready callbacks, disabling IRQs to prevent * races with call_rcu() from interrupt handlers. Leave the * callback counts, as rcu_barrier() needs to be conservative. */ - local_irq_save(flags); - rcu_nocb_lock(rdp); + rcu_nocb_lock_irqsave(rdp, flags); WARN_ON_ONCE(cpu_is_offline(smp_processor_id())); pending = rcu_segcblist_n_cbs(&rdp->cblist); - bl = max(rdp->blimit, pending >> rcu_divisor); - if (unlikely(bl > 100)) - tlimit = local_clock() + rcu_resched_ns; + div = READ_ONCE(rcu_divisor); + div = div < 0 ? 7 : div > sizeof(long) * 8 - 2 ? sizeof(long) * 8 - 2 : div; + bl = max(rdp->blimit, pending >> div); + if (in_serving_softirq() && unlikely(bl > 100)) { + long rrn = READ_ONCE(rcu_resched_ns); + + rrn = rrn < NSEC_PER_MSEC ? NSEC_PER_MSEC : rrn > NSEC_PER_SEC ? NSEC_PER_SEC : rrn; + tlimit = local_clock() + rrn; + } trace_rcu_batch_start(rcu_state.name, rcu_segcblist_n_cbs(&rdp->cblist), bl); rcu_segcblist_extract_done_cbs(&rdp->cblist, &rcl); - if (offloaded) + if (rcu_rdp_is_offloaded(rdp)) rdp->qlen_last_fqs_check = rcu_segcblist_n_cbs(&rdp->cblist); + + trace_rcu_segcb_stats(&rdp->cblist, TPS("SegCbDequeued")); rcu_nocb_unlock_irqrestore(rdp, flags); /* Invoke callbacks. */ tick_dep_set_task(current, TICK_DEP_BIT_RCU); rhp = rcu_cblist_dequeue(&rcl); + for (; rhp; rhp = rcu_cblist_dequeue(&rcl)) { rcu_callback_t f; + count++; debug_rcu_head_unqueue(rhp); rcu_lock_acquire(&rcu_callback_map); @@ -2189,21 +2253,22 @@ static void rcu_do_batch(struct rcu_data *rdp) /* * Stop only if limit reached and CPU has something to do. - * Note: The rcl structure counts down from zero. */ - if (-rcl.len >= bl && !offloaded && - (need_resched() || - (!is_idle_task(current) && !rcu_is_callbacks_kthread()))) - break; - if (unlikely(tlimit)) { - /* only call local_clock() every 32 callbacks */ - if (likely((-rcl.len & 31) || local_clock() < tlimit)) - continue; - /* Exceeded the time limit, so leave. */ - break; - } - if (offloaded) { - WARN_ON_ONCE(in_serving_softirq()); + if (in_serving_softirq()) { + if (count >= bl && (need_resched() || !is_idle_task(current))) + break; + /* + * Make sure we don't spend too much time here and deprive other + * softirq vectors of CPU cycles. + */ + if (unlikely(tlimit)) { + /* only call local_clock() every 32 callbacks */ + if (likely((count & 31) || local_clock() < tlimit)) + continue; + /* Exceeded the time limit, so leave. */ + break; + } + } else { local_bh_enable(); lockdep_assert_irqs_enabled(); cond_resched_tasks_rcu_qs(); @@ -2212,16 +2277,14 @@ static void rcu_do_batch(struct rcu_data *rdp) } } - local_irq_save(flags); - rcu_nocb_lock(rdp); - count = -rcl.len; + rcu_nocb_lock_irqsave(rdp, flags); + rdp->n_cbs_invoked += count; trace_rcu_batch_end(rcu_state.name, count, !!rcl.head, need_resched(), - is_idle_task(current), rcu_is_callbacks_kthread()); + is_idle_task(current), rcu_is_callbacks_kthread(rdp)); /* Update counts and requeue any remaining callbacks. */ rcu_segcblist_insert_done_cbs(&rdp->cblist, &rcl); - smp_mb(); /* List handling before counting for rcu_barrier(). */ - rcu_segcblist_insert_count(&rdp->cblist, &rcl); + rcu_segcblist_add_len(&rdp->cblist, -count); /* Reinstate batch limit if we have worked down the excess. */ count = rcu_segcblist_n_cbs(&rdp->cblist); @@ -2231,7 +2294,7 @@ static void rcu_do_batch(struct rcu_data *rdp) /* Reset ->qlen_last_fqs_check trigger if enough CBs have drained. */ if (count == 0 && rdp->qlen_last_fqs_check != 0) { rdp->qlen_last_fqs_check = 0; - rdp->n_force_qs_snap = rcu_state.n_force_qs; + rdp->n_force_qs_snap = READ_ONCE(rcu_state.n_force_qs); } else if (count < rdp->qlen_last_fqs_check - qhimark) rdp->qlen_last_fqs_check = count; @@ -2239,15 +2302,15 @@ static void rcu_do_batch(struct rcu_data *rdp) * The following usually indicates a double call_rcu(). To track * this down, try building with CONFIG_DEBUG_OBJECTS_RCU_HEAD=y. */ - WARN_ON_ONCE(count == 0 && !rcu_segcblist_empty(&rdp->cblist)); + empty = rcu_segcblist_empty(&rdp->cblist); + WARN_ON_ONCE(count == 0 && !empty); WARN_ON_ONCE(!IS_ENABLED(CONFIG_RCU_NOCB_CPU) && - count != 0 && rcu_segcblist_empty(&rdp->cblist)); + count != 0 && empty); + WARN_ON_ONCE(count == 0 && rcu_segcblist_n_segment_cbs(&rdp->cblist) != 0); + WARN_ON_ONCE(!empty && rcu_segcblist_n_segment_cbs(&rdp->cblist) == 0); rcu_nocb_unlock_irqrestore(rdp, flags); - /* Re-invoke RCU core processing if there are callbacks remaining. */ - if (!offloaded && rcu_segcblist_ready_cbs(&rdp->cblist)) - invoke_rcu_core(); tick_dep_clear_task(current, TICK_DEP_BIT_RCU); } @@ -2257,11 +2320,19 @@ static void rcu_do_batch(struct rcu_data *rdp) * state, for example, user mode or idle loop. It also schedules RCU * core processing. If the current grace period has gone on too long, * it will ask the scheduler to manufacture a context switch for the sole - * purpose of providing a providing the needed quiescent state. + * purpose of providing the needed quiescent state. */ void rcu_sched_clock_irq(int user) { + unsigned long j; + + if (IS_ENABLED(CONFIG_PROVE_RCU)) { + j = jiffies; + WARN_ON_ONCE(time_before(j, __this_cpu_read(rcu_data.last_sched_clock))); + __this_cpu_write(rcu_data.last_sched_clock, j); + } trace_rcu_utilization(TPS("Start scheduler-tick")); + lockdep_assert_irqs_disabled(); raw_cpu_inc(rcu_data.ticks_this_gp); /* The load-acquire pairs with the store-release setting to true. */ if (smp_load_acquire(this_cpu_ptr(&rcu_data.rcu_urgent_qs))) { @@ -2275,6 +2346,9 @@ void rcu_sched_clock_irq(int user) rcu_flavor_sched_clock_irq(user); if (rcu_pending(user)) invoke_rcu_core(); + if (user || rcu_is_cpu_rrupt_from_idle()) + rcu_note_voluntary_context_switch(current); + lockdep_assert_irqs_disabled(); trace_rcu_utilization(TPS("End scheduler-tick")); } @@ -2294,13 +2368,15 @@ static void force_qs_rnp(int (*f)(struct rcu_data *rdp)) struct rcu_data *rdp; struct rcu_node *rnp; + rcu_state.cbovld = rcu_state.cbovldnext; + rcu_state.cbovldnext = false; rcu_for_each_leaf_node(rnp) { cond_resched_tasks_rcu_qs(); mask = 0; raw_spin_lock_irqsave_rcu_node(rnp, flags); + rcu_state.cbovldnext |= !!rnp->cbovldmask; if (rnp->qsmask == 0) { - if (!IS_ENABLED(CONFIG_PREEMPT_RCU) || - rcu_preempt_blocked_readers_cgp(rnp)) { + if (rcu_preempt_blocked_readers_cgp(rnp)) { /* * No point in scanning bits because they * are all zero. But we might need to @@ -2368,14 +2444,38 @@ void rcu_force_quiescent_state(void) } EXPORT_SYMBOL_GPL(rcu_force_quiescent_state); +// Workqueue handler for an RCU reader for kernels enforcing struct RCU +// grace periods. +static void strict_work_handler(struct work_struct *work) +{ + rcu_read_lock(); + rcu_read_unlock(); +} + /* Perform RCU core processing work for the current CPU. */ static __latent_entropy void rcu_core(void) { unsigned long flags; struct rcu_data *rdp = raw_cpu_ptr(&rcu_data); struct rcu_node *rnp = rdp->mynode; - const bool offloaded = IS_ENABLED(CONFIG_RCU_NOCB_CPU) && - rcu_segcblist_is_offloaded(&rdp->cblist); + /* + * On RT rcu_core() can be preempted when IRQs aren't disabled. + * Therefore this function can race with concurrent NOCB (de-)offloading + * on this CPU and the below condition must be considered volatile. + * However if we race with: + * + * _ Offloading: In the worst case we accelerate or process callbacks + * concurrently with NOCB kthreads. We are guaranteed to + * call rcu_nocb_lock() if that happens. + * + * _ Deoffloading: In the worst case we miss callbacks acceleration or + * processing. This is fine because the early stage + * of deoffloading invokes rcu_core() after setting + * SEGCBLIST_RCU_CORE. So we guarantee that we'll process + * what could have been dismissed without the need to wait + * for the next rcu_pending() check in the next jiffy. + */ + const bool do_batch = !rcu_segcblist_completely_offloaded(&rdp->cblist); if (cpu_is_offline(smp_processor_id())) return; @@ -2383,7 +2483,7 @@ static __latent_entropy void rcu_core(void) WARN_ON_ONCE(!rdp->beenonline); /* Report any deferred quiescent states if preemption enabled. */ - if (!(preempt_count() & PREEMPT_MASK)) { + if (IS_ENABLED(CONFIG_PREEMPT_COUNT) && (!(preempt_count() & PREEMPT_MASK))) { rcu_preempt_deferred_qs(current); } else if (rcu_preempt_need_deferred_qs(current)) { set_tsk_need_resched(current); @@ -2395,23 +2495,31 @@ static __latent_entropy void rcu_core(void) /* No grace period and unregistered callbacks? */ if (!rcu_gp_in_progress() && - rcu_segcblist_is_enabled(&rdp->cblist) && !offloaded) { - local_irq_save(flags); + rcu_segcblist_is_enabled(&rdp->cblist) && do_batch) { + rcu_nocb_lock_irqsave(rdp, flags); if (!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) rcu_accelerate_cbs_unlocked(rnp, rdp); - local_irq_restore(flags); + rcu_nocb_unlock_irqrestore(rdp, flags); } rcu_check_gp_start_stall(rnp, rdp, rcu_jiffies_till_stall_check()); /* If there are callbacks ready, invoke them. */ - if (!offloaded && rcu_segcblist_ready_cbs(&rdp->cblist) && - likely(READ_ONCE(rcu_scheduler_fully_active))) + if (do_batch && rcu_segcblist_ready_cbs(&rdp->cblist) && + likely(READ_ONCE(rcu_scheduler_fully_active))) { rcu_do_batch(rdp); + /* Re-invoke RCU core processing if there are callbacks remaining. */ + if (rcu_segcblist_ready_cbs(&rdp->cblist)) + invoke_rcu_core(); + } /* Do any needed deferred wakeups of rcuo kthreads. */ do_nocb_deferred_wakeup(rdp); trace_rcu_utilization(TPS("End RCU core")); + + // If strict GPs, schedule an RCU reader in a clean environment. + if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) + queue_work_on(rdp->cpu, rcu_gp_wq, &rdp->strict_work); } static void rcu_core_si(struct softirq_action *h) @@ -2474,10 +2582,12 @@ static void rcu_cpu_kthread(unsigned int cpu) { unsigned int *statusp = this_cpu_ptr(&rcu_data.rcu_cpu_kthread_status); char work, *workp = this_cpu_ptr(&rcu_data.rcu_cpu_has_work); + unsigned long *j = this_cpu_ptr(&rcu_data.rcuc_activity); int spincnt; trace_rcu_utilization(TPS("Start CPU kthread@rcu_run")); for (spincnt = 0; spincnt < 10; spincnt++) { + WRITE_ONCE(*j, jiffies); local_bh_disable(); *statusp = RCU_KTHREAD_RUNNING; local_irq_disable(); @@ -2495,9 +2605,10 @@ static void rcu_cpu_kthread(unsigned int cpu) } *statusp = RCU_KTHREAD_YIELDING; trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield")); - schedule_timeout_interruptible(2); + schedule_timeout_idle(2); trace_rcu_utilization(TPS("End CPU kthread@rcu_yield")); *statusp = RCU_KTHREAD_WAITING; + WRITE_ONCE(*j, jiffies); } static struct smp_hotplug_thread rcu_cpu_thread_spec = { @@ -2518,13 +2629,12 @@ static int __init rcu_spawn_core_kthreads(void) for_each_possible_cpu(cpu) per_cpu(rcu_data.rcu_cpu_has_work, cpu) = 0; - if (!IS_ENABLED(CONFIG_RCU_BOOST) && use_softirq) + if (use_softirq) return 0; WARN_ONCE(smpboot_register_percpu_thread(&rcu_cpu_thread_spec), "%s: Could not start rcuc kthread, OOM is now expected behavior\n", __func__); return 0; } -early_initcall(rcu_spawn_core_kthreads); /* * Handle any core-RCU processing required by a call_rcu() invocation. @@ -2562,10 +2672,10 @@ static void __call_rcu_core(struct rcu_data *rdp, struct rcu_head *head, } else { /* Give the grace period a kick. */ rdp->blimit = DEFAULT_MAX_RCU_BLIMIT; - if (rcu_state.n_force_qs == rdp->n_force_qs_snap && + if (READ_ONCE(rcu_state.n_force_qs) == rdp->n_force_qs_snap && rcu_segcblist_first_pend_cb(&rdp->cblist) != head) rcu_force_quiescent_state(); - rdp->n_force_qs_snap = rcu_state.n_force_qs; + rdp->n_force_qs_snap = READ_ONCE(rcu_state.n_force_qs); rdp->qlen_last_fqs_check = rcu_segcblist_n_cbs(&rdp->cblist); } } @@ -2579,14 +2689,90 @@ static void rcu_leak_callback(struct rcu_head *rhp) } /* - * Helper function for call_rcu() and friends. The cpu argument will - * normally be -1, indicating "currently running CPU". It may specify - * a CPU only if that CPU is a no-CBs CPU. Currently, only rcu_barrier() - * is expected to specify a CPU. + * Check and if necessary update the leaf rcu_node structure's + * ->cbovldmask bit corresponding to the current CPU based on that CPU's + * number of queued RCU callbacks. The caller must hold the leaf rcu_node + * structure's ->lock. */ -static void -__call_rcu(struct rcu_head *head, rcu_callback_t func) +static void check_cb_ovld_locked(struct rcu_data *rdp, struct rcu_node *rnp) { + raw_lockdep_assert_held_rcu_node(rnp); + if (qovld_calc <= 0) + return; // Early boot and wildcard value set. + if (rcu_segcblist_n_cbs(&rdp->cblist) >= qovld_calc) + WRITE_ONCE(rnp->cbovldmask, rnp->cbovldmask | rdp->grpmask); + else + WRITE_ONCE(rnp->cbovldmask, rnp->cbovldmask & ~rdp->grpmask); +} + +/* + * Check and if necessary update the leaf rcu_node structure's + * ->cbovldmask bit corresponding to the current CPU based on that CPU's + * number of queued RCU callbacks. No locks need be held, but the + * caller must have disabled interrupts. + * + * Note that this function ignores the possibility that there are a lot + * of callbacks all of which have already seen the end of their respective + * grace periods. This omission is due to the need for no-CBs CPUs to + * be holding ->nocb_lock to do this check, which is too heavy for a + * common-case operation. + */ +static void check_cb_ovld(struct rcu_data *rdp) +{ + struct rcu_node *const rnp = rdp->mynode; + + if (qovld_calc <= 0 || + ((rcu_segcblist_n_cbs(&rdp->cblist) >= qovld_calc) == + !!(READ_ONCE(rnp->cbovldmask) & rdp->grpmask))) + return; // Early boot wildcard value or already set correctly. + raw_spin_lock_rcu_node(rnp); + check_cb_ovld_locked(rdp, rnp); + raw_spin_unlock_rcu_node(rnp); +} + +/** + * call_rcu() - Queue an RCU callback for invocation after a grace period. + * @head: structure to be used for queueing the RCU updates. + * @func: actual callback function to be invoked after the grace period + * + * The callback function will be invoked some time after a full grace + * period elapses, in other words after all pre-existing RCU read-side + * critical sections have completed. However, the callback function + * might well execute concurrently with RCU read-side critical sections + * that started after call_rcu() was invoked. + * + * RCU read-side critical sections are delimited by rcu_read_lock() + * and rcu_read_unlock(), and may be nested. In addition, but only in + * v5.0 and later, regions of code across which interrupts, preemption, + * or softirqs have been disabled also serve as RCU read-side critical + * sections. This includes hardware interrupt handlers, softirq handlers, + * and NMI handlers. + * + * Note that all CPUs must agree that the grace period extended beyond + * all pre-existing RCU read-side critical section. On systems with more + * than one CPU, this means that when "func()" is invoked, each CPU is + * guaranteed to have executed a full memory barrier since the end of its + * last RCU read-side critical section whose beginning preceded the call + * to call_rcu(). It also means that each CPU executing an RCU read-side + * critical section that continues beyond the start of "func()" must have + * executed a memory barrier after the call_rcu() but before the beginning + * of that RCU read-side critical section. Note that these guarantees + * include CPUs that are offline, idle, or executing in user mode, as + * well as CPUs that are executing in the kernel. + * + * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the + * resulting RCU callback function "func()", then both CPU A and CPU B are + * guaranteed to execute a full memory barrier during the time interval + * between the call to call_rcu() and the invocation of "func()" -- even + * if CPU A and CPU B are the same CPU (but again only if the system has + * more than one CPU). + * + * Implementation of these memory-ordering guarantees is described here: + * Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst. + */ +void call_rcu(struct rcu_head *head, rcu_callback_t func) +{ + static atomic_t doublefrees; unsigned long flags; struct rcu_data *rdp; bool was_alldone; @@ -2598,15 +2784,18 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func) /* * Probable double call_rcu(), so leak the callback. * Use rcu:rcu_callback trace event to find the previous - * time callback was passed to __call_rcu(). + * time callback was passed to call_rcu(). */ - WARN_ONCE(1, "__call_rcu(): Double-freed CB %p->%pS()!!!\n", - head, head->func); + if (atomic_inc_return(&doublefrees) < 4) { + pr_err("%s(): Double-freed CB %p->%pS()!!! ", __func__, head, head->func); + mem_dump_obj(head); + } WRITE_ONCE(head->func, rcu_leak_callback); return; } head->func = func; head->next = NULL; + kasan_record_aux_stack_noalloc(head); local_irq_save(flags); rdp = this_cpu_ptr(&rcu_data); @@ -2621,95 +2810,91 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func) rcu_segcblist_init(&rdp->cblist); } + check_cb_ovld(rdp); if (rcu_nocb_try_bypass(rdp, head, &was_alldone, flags)) return; // Enqueued onto ->nocb_bypass, so just leave. - /* If we get here, rcu_nocb_try_bypass() acquired ->nocb_lock. */ + // If no-CBs CPU gets here, rcu_nocb_try_bypass() acquired ->nocb_lock. rcu_segcblist_enqueue(&rdp->cblist, head); - if (__is_kfree_rcu_offset((unsigned long)func)) - trace_rcu_kfree_callback(rcu_state.name, head, + if (__is_kvfree_rcu_offset((unsigned long)func)) + trace_rcu_kvfree_callback(rcu_state.name, head, (unsigned long)func, rcu_segcblist_n_cbs(&rdp->cblist)); else trace_rcu_callback(rcu_state.name, head, rcu_segcblist_n_cbs(&rdp->cblist)); + trace_rcu_segcb_stats(&rdp->cblist, TPS("SegCBQueued")); + /* Go handle any RCU core processing required. */ - if (IS_ENABLED(CONFIG_RCU_NOCB_CPU) && - unlikely(rcu_segcblist_is_offloaded(&rdp->cblist))) { + if (unlikely(rcu_rdp_is_offloaded(rdp))) { __call_rcu_nocb_wake(rdp, was_alldone, flags); /* unlocks */ } else { __call_rcu_core(rdp, head, flags); local_irq_restore(flags); } } - -/** - * call_rcu() - Queue an RCU callback for invocation after a grace period. - * @head: structure to be used for queueing the RCU updates. - * @func: actual callback function to be invoked after the grace period - * - * The callback function will be invoked some time after a full grace - * period elapses, in other words after all pre-existing RCU read-side - * critical sections have completed. However, the callback function - * might well execute concurrently with RCU read-side critical sections - * that started after call_rcu() was invoked. RCU read-side critical - * sections are delimited by rcu_read_lock() and rcu_read_unlock(), and - * may be nested. In addition, regions of code across which interrupts, - * preemption, or softirqs have been disabled also serve as RCU read-side - * critical sections. This includes hardware interrupt handlers, softirq - * handlers, and NMI handlers. - * - * Note that all CPUs must agree that the grace period extended beyond - * all pre-existing RCU read-side critical section. On systems with more - * than one CPU, this means that when "func()" is invoked, each CPU is - * guaranteed to have executed a full memory barrier since the end of its - * last RCU read-side critical section whose beginning preceded the call - * to call_rcu(). It also means that each CPU executing an RCU read-side - * critical section that continues beyond the start of "func()" must have - * executed a memory barrier after the call_rcu() but before the beginning - * of that RCU read-side critical section. Note that these guarantees - * include CPUs that are offline, idle, or executing in user mode, as - * well as CPUs that are executing in the kernel. - * - * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the - * resulting RCU callback function "func()", then both CPU A and CPU B are - * guaranteed to execute a full memory barrier during the time interval - * between the call to call_rcu() and the invocation of "func()" -- even - * if CPU A and CPU B are the same CPU (but again only if the system has - * more than one CPU). - */ -void call_rcu(struct rcu_head *head, rcu_callback_t func) -{ - __call_rcu(head, func); -} EXPORT_SYMBOL_GPL(call_rcu); /* Maximum number of jiffies to wait before draining a batch. */ -#define KFREE_DRAIN_JIFFIES (HZ / 50) +#define KFREE_DRAIN_JIFFIES (5 * HZ) #define KFREE_N_BATCHES 2 +#define FREE_N_CHANNELS 2 + +/** + * struct kvfree_rcu_bulk_data - single block to store kvfree_rcu() pointers + * @nr_records: Number of active pointers in the array + * @next: Next bulk object in the block chain + * @records: Array of the kvfree_rcu() pointers + */ +struct kvfree_rcu_bulk_data { + unsigned long nr_records; + struct kvfree_rcu_bulk_data *next; + void *records[]; +}; + +/* + * This macro defines how many entries the "records" array + * will contain. It is based on the fact that the size of + * kvfree_rcu_bulk_data structure becomes exactly one page. + */ +#define KVFREE_BULK_MAX_ENTR \ + ((PAGE_SIZE - sizeof(struct kvfree_rcu_bulk_data)) / sizeof(void *)) /** * struct kfree_rcu_cpu_work - single batch of kfree_rcu() requests * @rcu_work: Let queue_rcu_work() invoke workqueue handler after grace period * @head_free: List of kfree_rcu() objects waiting for a grace period + * @bkvhead_free: Bulk-List of kvfree_rcu() objects waiting for a grace period * @krcp: Pointer to @kfree_rcu_cpu structure */ struct kfree_rcu_cpu_work { struct rcu_work rcu_work; struct rcu_head *head_free; + struct kvfree_rcu_bulk_data *bkvhead_free[FREE_N_CHANNELS]; struct kfree_rcu_cpu *krcp; }; /** * struct kfree_rcu_cpu - batch up kfree_rcu() requests for RCU grace period * @head: List of kfree_rcu() objects not yet waiting for a grace period + * @bkvhead: Bulk-List of kvfree_rcu() objects not yet waiting for a grace period * @krw_arr: Array of batches of kfree_rcu() objects waiting for a grace period * @lock: Synchronize access to this structure * @monitor_work: Promote @head to @head_free after KFREE_DRAIN_JIFFIES - * @monitor_todo: Tracks whether a @monitor_work delayed work is pending - * @initialized: The @lock and @rcu_work fields have been initialized + * @initialized: The @rcu_work fields have been initialized + * @count: Number of objects for which GP not started + * @bkvcache: + * A simple cache list that contains objects for reuse purpose. + * In order to save some per-cpu space the list is singular. + * Even though it is lockless an access has to be protected by the + * per-cpu lock. + * @page_cache_work: A work to refill the cache when it is empty + * @backoff_page_cache_fill: Delay cache refills + * @work_in_progress: Indicates that page_cache_work is running + * @hrtimer: A hrtimer for scheduling a page_cache_work + * @nr_bkv_objs: number of allocated objects at @bkvcache. * * This is a per-CPU structure. The reason that it is not included in * the rcu_data structure is to permit this code to be extracted from @@ -2718,210 +2903,559 @@ struct kfree_rcu_cpu_work { */ struct kfree_rcu_cpu { struct rcu_head *head; + struct kvfree_rcu_bulk_data *bkvhead[FREE_N_CHANNELS]; struct kfree_rcu_cpu_work krw_arr[KFREE_N_BATCHES]; - spinlock_t lock; + raw_spinlock_t lock; struct delayed_work monitor_work; - bool monitor_todo; bool initialized; + int count; + + struct delayed_work page_cache_work; + atomic_t backoff_page_cache_fill; + atomic_t work_in_progress; + struct hrtimer hrtimer; + + struct llist_head bkvcache; + int nr_bkv_objs; }; -static DEFINE_PER_CPU(struct kfree_rcu_cpu, krc); +static DEFINE_PER_CPU(struct kfree_rcu_cpu, krc) = { + .lock = __RAW_SPIN_LOCK_UNLOCKED(krc.lock), +}; + +static __always_inline void +debug_rcu_bhead_unqueue(struct kvfree_rcu_bulk_data *bhead) +{ +#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD + int i; + + for (i = 0; i < bhead->nr_records; i++) + debug_rcu_head_unqueue((struct rcu_head *)(bhead->records[i])); +#endif +} + +static inline struct kfree_rcu_cpu * +krc_this_cpu_lock(unsigned long *flags) +{ + struct kfree_rcu_cpu *krcp; + + local_irq_save(*flags); // For safely calling this_cpu_ptr(). + krcp = this_cpu_ptr(&krc); + raw_spin_lock(&krcp->lock); + + return krcp; +} + +static inline void +krc_this_cpu_unlock(struct kfree_rcu_cpu *krcp, unsigned long flags) +{ + raw_spin_unlock_irqrestore(&krcp->lock, flags); +} + +static inline struct kvfree_rcu_bulk_data * +get_cached_bnode(struct kfree_rcu_cpu *krcp) +{ + if (!krcp->nr_bkv_objs) + return NULL; + + WRITE_ONCE(krcp->nr_bkv_objs, krcp->nr_bkv_objs - 1); + return (struct kvfree_rcu_bulk_data *) + llist_del_first(&krcp->bkvcache); +} + +static inline bool +put_cached_bnode(struct kfree_rcu_cpu *krcp, + struct kvfree_rcu_bulk_data *bnode) +{ + // Check the limit. + if (krcp->nr_bkv_objs >= rcu_min_cached_objs) + return false; + + llist_add((struct llist_node *) bnode, &krcp->bkvcache); + WRITE_ONCE(krcp->nr_bkv_objs, krcp->nr_bkv_objs + 1); + return true; +} + +static int +drain_page_cache(struct kfree_rcu_cpu *krcp) +{ + unsigned long flags; + struct llist_node *page_list, *pos, *n; + int freed = 0; + + raw_spin_lock_irqsave(&krcp->lock, flags); + page_list = llist_del_all(&krcp->bkvcache); + WRITE_ONCE(krcp->nr_bkv_objs, 0); + raw_spin_unlock_irqrestore(&krcp->lock, flags); + + llist_for_each_safe(pos, n, page_list) { + free_page((unsigned long)pos); + freed++; + } + + return freed; +} /* * This function is invoked in workqueue context after a grace period. - * It frees all the objects queued on ->head_free. + * It frees all the objects queued on ->bkvhead_free or ->head_free. */ static void kfree_rcu_work(struct work_struct *work) { unsigned long flags; + struct kvfree_rcu_bulk_data *bkvhead[FREE_N_CHANNELS], *bnext; struct rcu_head *head, *next; struct kfree_rcu_cpu *krcp; struct kfree_rcu_cpu_work *krwp; + int i, j; krwp = container_of(to_rcu_work(work), struct kfree_rcu_cpu_work, rcu_work); krcp = krwp->krcp; - spin_lock_irqsave(&krcp->lock, flags); + + raw_spin_lock_irqsave(&krcp->lock, flags); + // Channels 1 and 2. + for (i = 0; i < FREE_N_CHANNELS; i++) { + bkvhead[i] = krwp->bkvhead_free[i]; + krwp->bkvhead_free[i] = NULL; + } + + // Channel 3. head = krwp->head_free; krwp->head_free = NULL; - spin_unlock_irqrestore(&krcp->lock, flags); + raw_spin_unlock_irqrestore(&krcp->lock, flags); + + // Handle the first two channels. + for (i = 0; i < FREE_N_CHANNELS; i++) { + for (; bkvhead[i]; bkvhead[i] = bnext) { + bnext = bkvhead[i]->next; + debug_rcu_bhead_unqueue(bkvhead[i]); + + rcu_lock_acquire(&rcu_callback_map); + if (i == 0) { // kmalloc() / kfree(). + trace_rcu_invoke_kfree_bulk_callback( + rcu_state.name, bkvhead[i]->nr_records, + bkvhead[i]->records); + + kfree_bulk(bkvhead[i]->nr_records, + bkvhead[i]->records); + } else { // vmalloc() / vfree(). + for (j = 0; j < bkvhead[i]->nr_records; j++) { + trace_rcu_invoke_kvfree_callback( + rcu_state.name, + bkvhead[i]->records[j], 0); + + vfree(bkvhead[i]->records[j]); + } + } + rcu_lock_release(&rcu_callback_map); + + raw_spin_lock_irqsave(&krcp->lock, flags); + if (put_cached_bnode(krcp, bkvhead[i])) + bkvhead[i] = NULL; + raw_spin_unlock_irqrestore(&krcp->lock, flags); + + if (bkvhead[i]) + free_page((unsigned long) bkvhead[i]); + + cond_resched_tasks_rcu_qs(); + } + } - // List "head" is now private, so traverse locklessly. + /* + * This is used when the "bulk" path can not be used for the + * double-argument of kvfree_rcu(). This happens when the + * page-cache is empty, which means that objects are instead + * queued on a linked list through their rcu_head structures. + * This list is named "Channel 3". + */ for (; head; head = next) { unsigned long offset = (unsigned long)head->func; + void *ptr = (void *)head - offset; next = head->next; - // Potentially optimize with kfree_bulk in future. - debug_rcu_head_unqueue(head); + debug_rcu_head_unqueue((struct rcu_head *)ptr); rcu_lock_acquire(&rcu_callback_map); - trace_rcu_invoke_kfree_callback(rcu_state.name, head, offset); + trace_rcu_invoke_kvfree_callback(rcu_state.name, head, offset); - if (!WARN_ON_ONCE(!__is_kfree_rcu_offset(offset))) { - /* Could be optimized with kfree_bulk() in future. */ - kfree((void *)head - offset); - } + if (!WARN_ON_ONCE(!__is_kvfree_rcu_offset(offset))) + kvfree(ptr); rcu_lock_release(&rcu_callback_map); cond_resched_tasks_rcu_qs(); } } -/* - * Schedule the kfree batch RCU work to run in workqueue context after a GP. - * - * This function is invoked by kfree_rcu_monitor() when the KFREE_DRAIN_JIFFIES - * timeout has been reached. - */ -static inline bool queue_kfree_rcu_work(struct kfree_rcu_cpu *krcp) +static bool +need_offload_krc(struct kfree_rcu_cpu *krcp) { int i; - struct kfree_rcu_cpu_work *krwp = NULL; - lockdep_assert_held(&krcp->lock); - for (i = 0; i < KFREE_N_BATCHES; i++) - if (!krcp->krw_arr[i].head_free) { - krwp = &(krcp->krw_arr[i]); - break; - } + for (i = 0; i < FREE_N_CHANNELS; i++) + if (krcp->bkvhead[i]) + return true; - // If a previous RCU batch is in progress, we cannot immediately - // queue another one, so return false to tell caller to retry. - if (!krwp) - return false; - - krwp->head_free = krcp->head; - krcp->head = NULL; - INIT_RCU_WORK(&krwp->rcu_work, kfree_rcu_work); - queue_rcu_work(system_wq, &krwp->rcu_work); - return true; + return !!krcp->head; } -static inline void kfree_rcu_drain_unlock(struct kfree_rcu_cpu *krcp, - unsigned long flags) +static void +schedule_delayed_monitor_work(struct kfree_rcu_cpu *krcp) { - // Attempt to start a new batch. - krcp->monitor_todo = false; - if (queue_kfree_rcu_work(krcp)) { - // Success! Our job is done here. - spin_unlock_irqrestore(&krcp->lock, flags); + long delay, delay_left; + + delay = READ_ONCE(krcp->count) >= KVFREE_BULK_MAX_ENTR ? 1:KFREE_DRAIN_JIFFIES; + if (delayed_work_pending(&krcp->monitor_work)) { + delay_left = krcp->monitor_work.timer.expires - jiffies; + if (delay < delay_left) + mod_delayed_work(system_wq, &krcp->monitor_work, delay); return; } - - // Previous RCU batch still in progress, try again later. - krcp->monitor_todo = true; - schedule_delayed_work(&krcp->monitor_work, KFREE_DRAIN_JIFFIES); - spin_unlock_irqrestore(&krcp->lock, flags); + queue_delayed_work(system_wq, &krcp->monitor_work, delay); } /* * This function is invoked after the KFREE_DRAIN_JIFFIES timeout. - * It invokes kfree_rcu_drain_unlock() to attempt to start another batch. */ static void kfree_rcu_monitor(struct work_struct *work) { + struct kfree_rcu_cpu *krcp = container_of(work, + struct kfree_rcu_cpu, monitor_work.work); unsigned long flags; - struct kfree_rcu_cpu *krcp = container_of(work, struct kfree_rcu_cpu, - monitor_work.work); + int i, j; - spin_lock_irqsave(&krcp->lock, flags); - if (krcp->monitor_todo) - kfree_rcu_drain_unlock(krcp, flags); - else - spin_unlock_irqrestore(&krcp->lock, flags); + raw_spin_lock_irqsave(&krcp->lock, flags); + + // Attempt to start a new batch. + for (i = 0; i < KFREE_N_BATCHES; i++) { + struct kfree_rcu_cpu_work *krwp = &(krcp->krw_arr[i]); + + // Try to detach bkvhead or head and attach it over any + // available corresponding free channel. It can be that + // a previous RCU batch is in progress, it means that + // immediately to queue another one is not possible so + // in that case the monitor work is rearmed. + if ((krcp->bkvhead[0] && !krwp->bkvhead_free[0]) || + (krcp->bkvhead[1] && !krwp->bkvhead_free[1]) || + (krcp->head && !krwp->head_free)) { + // Channel 1 corresponds to the SLAB-pointer bulk path. + // Channel 2 corresponds to vmalloc-pointer bulk path. + for (j = 0; j < FREE_N_CHANNELS; j++) { + if (!krwp->bkvhead_free[j]) { + krwp->bkvhead_free[j] = krcp->bkvhead[j]; + krcp->bkvhead[j] = NULL; + } + } + + // Channel 3 corresponds to both SLAB and vmalloc + // objects queued on the linked list. + if (!krwp->head_free) { + krwp->head_free = krcp->head; + krcp->head = NULL; + } + + WRITE_ONCE(krcp->count, 0); + + // One work is per one batch, so there are three + // "free channels", the batch can handle. It can + // be that the work is in the pending state when + // channels have been detached following by each + // other. + queue_rcu_work(system_wq, &krwp->rcu_work); + } + } + + // If there is nothing to detach, it means that our job is + // successfully done here. In case of having at least one + // of the channels that is still busy we should rearm the + // work to repeat an attempt. Because previous batches are + // still in progress. + if (need_offload_krc(krcp)) + schedule_delayed_monitor_work(krcp); + + raw_spin_unlock_irqrestore(&krcp->lock, flags); +} + +static enum hrtimer_restart +schedule_page_work_fn(struct hrtimer *t) +{ + struct kfree_rcu_cpu *krcp = + container_of(t, struct kfree_rcu_cpu, hrtimer); + + queue_delayed_work(system_highpri_wq, &krcp->page_cache_work, 0); + return HRTIMER_NORESTART; +} + +static void fill_page_cache_func(struct work_struct *work) +{ + struct kvfree_rcu_bulk_data *bnode; + struct kfree_rcu_cpu *krcp = + container_of(work, struct kfree_rcu_cpu, + page_cache_work.work); + unsigned long flags; + int nr_pages; + bool pushed; + int i; + + nr_pages = atomic_read(&krcp->backoff_page_cache_fill) ? + 1 : rcu_min_cached_objs; + + for (i = 0; i < nr_pages; i++) { + bnode = (struct kvfree_rcu_bulk_data *) + __get_free_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN); + + if (!bnode) + break; + + raw_spin_lock_irqsave(&krcp->lock, flags); + pushed = put_cached_bnode(krcp, bnode); + raw_spin_unlock_irqrestore(&krcp->lock, flags); + + if (!pushed) { + free_page((unsigned long) bnode); + break; + } + } + + atomic_set(&krcp->work_in_progress, 0); + atomic_set(&krcp->backoff_page_cache_fill, 0); +} + +static void +run_page_cache_worker(struct kfree_rcu_cpu *krcp) +{ + if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING && + !atomic_xchg(&krcp->work_in_progress, 1)) { + if (atomic_read(&krcp->backoff_page_cache_fill)) { + queue_delayed_work(system_wq, + &krcp->page_cache_work, + msecs_to_jiffies(rcu_delay_page_cache_fill_msec)); + } else { + hrtimer_init(&krcp->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + krcp->hrtimer.function = schedule_page_work_fn; + hrtimer_start(&krcp->hrtimer, 0, HRTIMER_MODE_REL); + } + } +} + +// Record ptr in a page managed by krcp, with the pre-krc_this_cpu_lock() +// state specified by flags. If can_alloc is true, the caller must +// be schedulable and not be holding any locks or mutexes that might be +// acquired by the memory allocator or anything that it might invoke. +// Returns true if ptr was successfully recorded, else the caller must +// use a fallback. +static inline bool +add_ptr_to_bulk_krc_lock(struct kfree_rcu_cpu **krcp, + unsigned long *flags, void *ptr, bool can_alloc) +{ + struct kvfree_rcu_bulk_data *bnode; + int idx; + + *krcp = krc_this_cpu_lock(flags); + if (unlikely(!(*krcp)->initialized)) + return false; + + idx = !!is_vmalloc_addr(ptr); + + /* Check if a new block is required. */ + if (!(*krcp)->bkvhead[idx] || + (*krcp)->bkvhead[idx]->nr_records == KVFREE_BULK_MAX_ENTR) { + bnode = get_cached_bnode(*krcp); + if (!bnode && can_alloc) { + krc_this_cpu_unlock(*krcp, *flags); + + // __GFP_NORETRY - allows a light-weight direct reclaim + // what is OK from minimizing of fallback hitting point of + // view. Apart of that it forbids any OOM invoking what is + // also beneficial since we are about to release memory soon. + // + // __GFP_NOMEMALLOC - prevents from consuming of all the + // memory reserves. Please note we have a fallback path. + // + // __GFP_NOWARN - it is supposed that an allocation can + // be failed under low memory or high memory pressure + // scenarios. + bnode = (struct kvfree_rcu_bulk_data *) + __get_free_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN); + *krcp = krc_this_cpu_lock(flags); + } + + if (!bnode) + return false; + + /* Initialize the new block. */ + bnode->nr_records = 0; + bnode->next = (*krcp)->bkvhead[idx]; + + /* Attach it to the head. */ + (*krcp)->bkvhead[idx] = bnode; + } + + /* Finally insert. */ + (*krcp)->bkvhead[idx]->records + [(*krcp)->bkvhead[idx]->nr_records++] = ptr; + + return true; } /* - * Queue a request for lazy invocation of kfree() after a grace period. + * Queue a request for lazy invocation of the appropriate free routine + * after a grace period. Please note that three paths are maintained, + * two for the common case using arrays of pointers and a third one that + * is used only when the main paths cannot be used, for example, due to + * memory pressure. * - * Each kfree_call_rcu() request is added to a batch. The batch will be drained - * every KFREE_DRAIN_JIFFIES number of jiffies. All the objects in the batch - * will be kfree'd in workqueue context. This allows us to: - * - * 1. Batch requests together to reduce the number of grace periods during - * heavy kfree_rcu() load. - * - * 2. It makes it possible to use kfree_bulk() on a large number of - * kfree_rcu() requests thus reducing cache misses and the per-object - * overhead of kfree(). + * Each kvfree_call_rcu() request is added to a batch. The batch will be drained + * every KFREE_DRAIN_JIFFIES number of jiffies. All the objects in the batch will + * be free'd in workqueue context. This allows us to: batch requests together to + * reduce the number of grace periods during heavy kfree_rcu()/kvfree_rcu() load. */ -void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func) +void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func) { unsigned long flags; struct kfree_rcu_cpu *krcp; + bool success; + void *ptr; - local_irq_save(flags); // For safely calling this_cpu_ptr(). - krcp = this_cpu_ptr(&krc); - if (krcp->initialized) - spin_lock(&krcp->lock); + if (head) { + ptr = (void *) head - (unsigned long) func; + } else { + /* + * Please note there is a limitation for the head-less + * variant, that is why there is a clear rule for such + * objects: it can be used from might_sleep() context + * only. For other places please embed an rcu_head to + * your data. + */ + might_sleep(); + ptr = (unsigned long *) func; + } // Queue the object but don't yet schedule the batch. - if (debug_rcu_head_queue(head)) { + if (debug_rcu_head_queue(ptr)) { // Probable double kfree_rcu(), just leak. WARN_ONCE(1, "%s(): Double-freed call. rcu_head %p\n", __func__, head); - goto unlock_return; + + // Mark as success and leave. + return; } - head->func = func; - head->next = krcp->head; - krcp->head = head; - // Set timer to drain after KFREE_DRAIN_JIFFIES. - if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING && - !krcp->monitor_todo) { - krcp->monitor_todo = true; - schedule_delayed_work(&krcp->monitor_work, KFREE_DRAIN_JIFFIES); + kasan_record_aux_stack_noalloc(ptr); + success = add_ptr_to_bulk_krc_lock(&krcp, &flags, ptr, !head); + if (!success) { + run_page_cache_worker(krcp); + + if (head == NULL) + // Inline if kvfree_rcu(one_arg) call. + goto unlock_return; + + head->func = func; + head->next = krcp->head; + krcp->head = head; + success = true; } + WRITE_ONCE(krcp->count, krcp->count + 1); + + // Set timer to drain after KFREE_DRAIN_JIFFIES. + if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING) + schedule_delayed_monitor_work(krcp); + unlock_return: - if (krcp->initialized) - spin_unlock(&krcp->lock); - local_irq_restore(flags); + krc_this_cpu_unlock(krcp, flags); + + /* + * Inline kvfree() after synchronize_rcu(). We can do + * it from might_sleep() context only, so the current + * CPU can pass the QS state. + */ + if (!success) { + debug_rcu_head_unqueue((struct rcu_head *) ptr); + synchronize_rcu(); + kvfree(ptr); + } +} +EXPORT_SYMBOL_GPL(kvfree_call_rcu); + +static unsigned long +kfree_rcu_shrink_count(struct shrinker *shrink, struct shrink_control *sc) +{ + int cpu; + unsigned long count = 0; + + /* Snapshot count of all CPUs */ + for_each_possible_cpu(cpu) { + struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu); + + count += READ_ONCE(krcp->count); + count += READ_ONCE(krcp->nr_bkv_objs); + atomic_set(&krcp->backoff_page_cache_fill, 1); + } + + return count == 0 ? SHRINK_EMPTY : count; +} + +static unsigned long +kfree_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) +{ + int cpu, freed = 0; + + for_each_possible_cpu(cpu) { + int count; + struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu); + + count = krcp->count; + count += drain_page_cache(krcp); + kfree_rcu_monitor(&krcp->monitor_work.work); + + sc->nr_to_scan -= count; + freed += count; + + if (sc->nr_to_scan <= 0) + break; + } + + return freed == 0 ? SHRINK_STOP : freed; } -EXPORT_SYMBOL_GPL(kfree_call_rcu); + +static struct shrinker kfree_rcu_shrinker = { + .count_objects = kfree_rcu_shrink_count, + .scan_objects = kfree_rcu_shrink_scan, + .batch = 0, + .seeks = DEFAULT_SEEKS, +}; void __init kfree_rcu_scheduler_running(void) { int cpu; unsigned long flags; - for_each_online_cpu(cpu) { + for_each_possible_cpu(cpu) { struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu); - spin_lock_irqsave(&krcp->lock, flags); - if (!krcp->head || krcp->monitor_todo) { - spin_unlock_irqrestore(&krcp->lock, flags); - continue; - } - krcp->monitor_todo = true; - schedule_delayed_work_on(cpu, &krcp->monitor_work, - KFREE_DRAIN_JIFFIES); - spin_unlock_irqrestore(&krcp->lock, flags); + raw_spin_lock_irqsave(&krcp->lock, flags); + if (need_offload_krc(krcp)) + schedule_delayed_monitor_work(krcp); + raw_spin_unlock_irqrestore(&krcp->lock, flags); } } /* * During early boot, any blocking grace-period wait automatically - * implies a grace period. Later on, this is never the case for PREEMPTION. + * implies a grace period. * - * Howevr, because a context switch is a grace period for !PREEMPTION, any - * blocking grace-period wait automatically implies a grace period if - * there is only one CPU online at any point time during execution of - * either synchronize_rcu() or synchronize_rcu_expedited(). It is OK to - * occasionally incorrectly indicate that there are multiple CPUs online - * when there was in fact only one the whole time, as this just adds some - * overhead: RCU still operates correctly. + * Later on, this could in theory be the case for kernels built with + * CONFIG_SMP=y && CONFIG_PREEMPTION=y running on a single CPU, but this + * is not a common case. Furthermore, this optimization would cause + * the rcu_gp_oldstate structure to expand by 50%, so this potential + * grace-period optimization is ignored once the scheduler is running. */ static int rcu_blocking_is_gp(void) { - int ret; - - if (IS_ENABLED(CONFIG_PREEMPTION)) - return rcu_scheduler_active == RCU_SCHEDULER_INACTIVE; + if (rcu_scheduler_active != RCU_SCHEDULER_INACTIVE) + return false; might_sleep(); /* Check for RCU read-side critical section. */ - preempt_disable(); - ret = num_online_cpus() <= 1; - preempt_enable(); - return ret; + return true; } /** @@ -2932,10 +3466,12 @@ static int rcu_blocking_is_gp(void) * read-side critical sections have completed. Note, however, that * upon return from synchronize_rcu(), the caller might well be executing * concurrently with new RCU read-side critical sections that began while - * synchronize_rcu() was waiting. RCU read-side critical sections are - * delimited by rcu_read_lock() and rcu_read_unlock(), and may be nested. - * In addition, regions of code across which interrupts, preemption, or - * softirqs have been disabled also serve as RCU read-side critical + * synchronize_rcu() was waiting. + * + * RCU read-side critical sections are delimited by rcu_read_lock() + * and rcu_read_unlock(), and may be nested. In addition, but only in + * v5.0 and later, regions of code across which interrupts, preemption, + * or softirqs have been disabled also serve as RCU read-side critical * sections. This includes hardware interrupt handlers, softirq handlers, * and NMI handlers. * @@ -2956,28 +3492,70 @@ static int rcu_blocking_is_gp(void) * to have executed a full memory barrier during the execution of * synchronize_rcu() -- even if CPU A and CPU B are the same CPU (but * again only if the system has more than one CPU). + * + * Implementation of these memory-ordering guarantees is described here: + * Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst. */ void synchronize_rcu(void) { + unsigned long flags; + struct rcu_node *rnp; + RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) || lock_is_held(&rcu_lock_map) || lock_is_held(&rcu_sched_lock_map), "Illegal synchronize_rcu() in RCU read-side critical section"); - if (rcu_blocking_is_gp()) + if (!rcu_blocking_is_gp()) { + if (rcu_gp_is_expedited()) + synchronize_rcu_expedited(); + else + wait_rcu_gp(call_rcu); return; - if (rcu_gp_is_expedited()) - synchronize_rcu_expedited(); - else - wait_rcu_gp(call_rcu); + } + + // Context allows vacuous grace periods. + // Note well that this code runs with !PREEMPT && !SMP. + // In addition, all code that advances grace periods runs at + // process level. Therefore, this normal GP overlaps with other + // normal GPs only by being fully nested within them, which allows + // reuse of ->gp_seq_polled_snap. + rcu_poll_gp_seq_start_unlocked(&rcu_state.gp_seq_polled_snap); + rcu_poll_gp_seq_end_unlocked(&rcu_state.gp_seq_polled_snap); + + // Update the normal grace-period counters to record + // this grace period, but only those used by the boot CPU. + // The rcu_scheduler_starting() will take care of the rest of + // these counters. + local_irq_save(flags); + WARN_ON_ONCE(num_online_cpus() > 1); + rcu_state.gp_seq += (1 << RCU_SEQ_CTR_SHIFT); + for (rnp = this_cpu_ptr(&rcu_data)->mynode; rnp; rnp = rnp->parent) + rnp->gp_seq_needed = rnp->gp_seq = rcu_state.gp_seq; + local_irq_restore(flags); } EXPORT_SYMBOL_GPL(synchronize_rcu); /** + * get_completed_synchronize_rcu_full - Return a full pre-completed polled state cookie + * @rgosp: Place to put state cookie + * + * Stores into @rgosp a value that will always be treated by functions + * like poll_state_synchronize_rcu_full() as a cookie whose grace period + * has already completed. + */ +void get_completed_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp) +{ + rgosp->rgos_norm = RCU_GET_STATE_COMPLETED; + rgosp->rgos_exp = RCU_GET_STATE_COMPLETED; +} +EXPORT_SYMBOL_GPL(get_completed_synchronize_rcu_full); + +/** * get_state_synchronize_rcu - Snapshot current RCU state * * Returns a cookie that is used by a later call to cond_synchronize_rcu() - * to determine whether or not a full grace period has elapsed in the - * meantime. + * or poll_state_synchronize_rcu() to determine whether or not a full + * grace period has elapsed in the meantime. */ unsigned long get_state_synchronize_rcu(void) { @@ -2986,33 +3564,248 @@ unsigned long get_state_synchronize_rcu(void) * before the load from ->gp_seq. */ smp_mb(); /* ^^^ */ - return rcu_seq_snap(&rcu_state.gp_seq); + return rcu_seq_snap(&rcu_state.gp_seq_polled); } EXPORT_SYMBOL_GPL(get_state_synchronize_rcu); /** - * cond_synchronize_rcu - Conditionally wait for an RCU grace period + * get_state_synchronize_rcu_full - Snapshot RCU state, both normal and expedited + * @rgosp: location to place combined normal/expedited grace-period state * - * @oldstate: return value from earlier call to get_state_synchronize_rcu() + * Places the normal and expedited grace-period states in @rgosp. This + * state value can be passed to a later call to cond_synchronize_rcu_full() + * or poll_state_synchronize_rcu_full() to determine whether or not a + * grace period (whether normal or expedited) has elapsed in the meantime. + * The rcu_gp_oldstate structure takes up twice the memory of an unsigned + * long, but is guaranteed to see all grace periods. In contrast, the + * combined state occupies less memory, but can sometimes fail to take + * grace periods into account. + * + * This does not guarantee that the needed grace period will actually + * start. + */ +void get_state_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp) +{ + struct rcu_node *rnp = rcu_get_root(); + + /* + * Any prior manipulation of RCU-protected data must happen + * before the loads from ->gp_seq and ->expedited_sequence. + */ + smp_mb(); /* ^^^ */ + rgosp->rgos_norm = rcu_seq_snap(&rnp->gp_seq); + rgosp->rgos_exp = rcu_seq_snap(&rcu_state.expedited_sequence); +} +EXPORT_SYMBOL_GPL(get_state_synchronize_rcu_full); + +/* + * Helper function for start_poll_synchronize_rcu() and + * start_poll_synchronize_rcu_full(). + */ +static void start_poll_synchronize_rcu_common(void) +{ + unsigned long flags; + bool needwake; + struct rcu_data *rdp; + struct rcu_node *rnp; + + lockdep_assert_irqs_enabled(); + local_irq_save(flags); + rdp = this_cpu_ptr(&rcu_data); + rnp = rdp->mynode; + raw_spin_lock_rcu_node(rnp); // irqs already disabled. + // Note it is possible for a grace period to have elapsed between + // the above call to get_state_synchronize_rcu() and the below call + // to rcu_seq_snap. This is OK, the worst that happens is that we + // get a grace period that no one needed. These accesses are ordered + // by smp_mb(), and we are accessing them in the opposite order + // from which they are updated at grace-period start, as required. + needwake = rcu_start_this_gp(rnp, rdp, rcu_seq_snap(&rcu_state.gp_seq)); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + if (needwake) + rcu_gp_kthread_wake(); +} + +/** + * start_poll_synchronize_rcu - Snapshot and start RCU grace period + * + * Returns a cookie that is used by a later call to cond_synchronize_rcu() + * or poll_state_synchronize_rcu() to determine whether or not a full + * grace period has elapsed in the meantime. If the needed grace period + * is not already slated to start, notifies RCU core of the need for that + * grace period. + * + * Interrupts must be enabled for the case where it is necessary to awaken + * the grace-period kthread. + */ +unsigned long start_poll_synchronize_rcu(void) +{ + unsigned long gp_seq = get_state_synchronize_rcu(); + + start_poll_synchronize_rcu_common(); + return gp_seq; +} +EXPORT_SYMBOL_GPL(start_poll_synchronize_rcu); + +/** + * start_poll_synchronize_rcu_full - Take a full snapshot and start RCU grace period + * @rgosp: value from get_state_synchronize_rcu_full() or start_poll_synchronize_rcu_full() + * + * Places the normal and expedited grace-period states in *@rgos. This + * state value can be passed to a later call to cond_synchronize_rcu_full() + * or poll_state_synchronize_rcu_full() to determine whether or not a + * grace period (whether normal or expedited) has elapsed in the meantime. + * If the needed grace period is not already slated to start, notifies + * RCU core of the need for that grace period. + * + * Interrupts must be enabled for the case where it is necessary to awaken + * the grace-period kthread. + */ +void start_poll_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp) +{ + get_state_synchronize_rcu_full(rgosp); + + start_poll_synchronize_rcu_common(); +} +EXPORT_SYMBOL_GPL(start_poll_synchronize_rcu_full); + +/** + * poll_state_synchronize_rcu - Has the specified RCU grace period completed? + * @oldstate: value from get_state_synchronize_rcu() or start_poll_synchronize_rcu() + * + * If a full RCU grace period has elapsed since the earlier call from + * which @oldstate was obtained, return @true, otherwise return @false. + * If @false is returned, it is the caller's responsibility to invoke this + * function later on until it does return @true. Alternatively, the caller + * can explicitly wait for a grace period, for example, by passing @oldstate + * to cond_synchronize_rcu() or by directly invoking synchronize_rcu(). + * + * Yes, this function does not take counter wrap into account. + * But counter wrap is harmless. If the counter wraps, we have waited for + * more than a billion grace periods (and way more on a 64-bit system!). + * Those needing to keep old state values for very long time periods + * (many hours even on 32-bit systems) should check them occasionally and + * either refresh them or set a flag indicating that the grace period has + * completed. Alternatively, they can use get_completed_synchronize_rcu() + * to get a guaranteed-completed grace-period state. + * + * This function provides the same memory-ordering guarantees that + * would be provided by a synchronize_rcu() that was invoked at the call + * to the function that provided @oldstate, and that returned at the end + * of this function. + */ +bool poll_state_synchronize_rcu(unsigned long oldstate) +{ + if (oldstate == RCU_GET_STATE_COMPLETED || + rcu_seq_done_exact(&rcu_state.gp_seq_polled, oldstate)) { + smp_mb(); /* Ensure GP ends before subsequent accesses. */ + return true; + } + return false; +} +EXPORT_SYMBOL_GPL(poll_state_synchronize_rcu); + +/** + * poll_state_synchronize_rcu_full - Has the specified RCU grace period completed? + * @rgosp: value from get_state_synchronize_rcu_full() or start_poll_synchronize_rcu_full() + * + * If a full RCU grace period has elapsed since the earlier call from + * which *rgosp was obtained, return @true, otherwise return @false. + * If @false is returned, it is the caller's responsibility to invoke this + * function later on until it does return @true. Alternatively, the caller + * can explicitly wait for a grace period, for example, by passing @rgosp + * to cond_synchronize_rcu() or by directly invoking synchronize_rcu(). + * + * Yes, this function does not take counter wrap into account. + * But counter wrap is harmless. If the counter wraps, we have waited + * for more than a billion grace periods (and way more on a 64-bit + * system!). Those needing to keep rcu_gp_oldstate values for very + * long time periods (many hours even on 32-bit systems) should check + * them occasionally and either refresh them or set a flag indicating + * that the grace period has completed. Alternatively, they can use + * get_completed_synchronize_rcu_full() to get a guaranteed-completed + * grace-period state. + * + * This function provides the same memory-ordering guarantees that would + * be provided by a synchronize_rcu() that was invoked at the call to + * the function that provided @rgosp, and that returned at the end of this + * function. And this guarantee requires that the root rcu_node structure's + * ->gp_seq field be checked instead of that of the rcu_state structure. + * The problem is that the just-ending grace-period's callbacks can be + * invoked between the time that the root rcu_node structure's ->gp_seq + * field is updated and the time that the rcu_state structure's ->gp_seq + * field is updated. Therefore, if a single synchronize_rcu() is to + * cause a subsequent poll_state_synchronize_rcu_full() to return @true, + * then the root rcu_node structure is the one that needs to be polled. + */ +bool poll_state_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp) +{ + struct rcu_node *rnp = rcu_get_root(); + + smp_mb(); // Order against root rcu_node structure grace-period cleanup. + if (rgosp->rgos_norm == RCU_GET_STATE_COMPLETED || + rcu_seq_done_exact(&rnp->gp_seq, rgosp->rgos_norm) || + rgosp->rgos_exp == RCU_GET_STATE_COMPLETED || + rcu_seq_done_exact(&rcu_state.expedited_sequence, rgosp->rgos_exp)) { + smp_mb(); /* Ensure GP ends before subsequent accesses. */ + return true; + } + return false; +} +EXPORT_SYMBOL_GPL(poll_state_synchronize_rcu_full); + +/** + * cond_synchronize_rcu - Conditionally wait for an RCU grace period + * @oldstate: value from get_state_synchronize_rcu(), start_poll_synchronize_rcu(), or start_poll_synchronize_rcu_expedited() * * If a full RCU grace period has elapsed since the earlier call to - * get_state_synchronize_rcu(), just return. Otherwise, invoke - * synchronize_rcu() to wait for a full grace period. + * get_state_synchronize_rcu() or start_poll_synchronize_rcu(), just return. + * Otherwise, invoke synchronize_rcu() to wait for a full grace period. * - * Yes, this function does not take counter wrap into account. But - * counter wrap is harmless. If the counter wraps, we have waited for + * Yes, this function does not take counter wrap into account. + * But counter wrap is harmless. If the counter wraps, we have waited for * more than 2 billion grace periods (and way more on a 64-bit system!), - * so waiting for one additional grace period should be just fine. + * so waiting for a couple of additional grace periods should be just fine. + * + * This function provides the same memory-ordering guarantees that + * would be provided by a synchronize_rcu() that was invoked at the call + * to the function that provided @oldstate and that returned at the end + * of this function. */ void cond_synchronize_rcu(unsigned long oldstate) { - if (!rcu_seq_done(&rcu_state.gp_seq, oldstate)) + if (!poll_state_synchronize_rcu(oldstate)) synchronize_rcu(); - else - smp_mb(); /* Ensure GP ends before subsequent accesses. */ } EXPORT_SYMBOL_GPL(cond_synchronize_rcu); +/** + * cond_synchronize_rcu_full - Conditionally wait for an RCU grace period + * @rgosp: value from get_state_synchronize_rcu_full(), start_poll_synchronize_rcu_full(), or start_poll_synchronize_rcu_expedited_full() + * + * If a full RCU grace period has elapsed since the call to + * get_state_synchronize_rcu_full(), start_poll_synchronize_rcu_full(), + * or start_poll_synchronize_rcu_expedited_full() from which @rgosp was + * obtained, just return. Otherwise, invoke synchronize_rcu() to wait + * for a full grace period. + * + * Yes, this function does not take counter wrap into account. + * But counter wrap is harmless. If the counter wraps, we have waited for + * more than 2 billion grace periods (and way more on a 64-bit system!), + * so waiting for a couple of additional grace periods should be just fine. + * + * This function provides the same memory-ordering guarantees that + * would be provided by a synchronize_rcu() that was invoked at the call + * to the function that provided @rgosp and that returned at the end of + * this function. + */ +void cond_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp) +{ + if (!poll_state_synchronize_rcu_full(rgosp)) + synchronize_rcu(); +} +EXPORT_SYMBOL_GPL(cond_synchronize_rcu_full); + /* * Check to see if there is any immediate RCU-related work to be done by * the current CPU, returning 1 if so and zero otherwise. The checks are @@ -3026,11 +3819,13 @@ static int rcu_pending(int user) struct rcu_data *rdp = this_cpu_ptr(&rcu_data); struct rcu_node *rnp = rdp->mynode; + lockdep_assert_irqs_disabled(); + /* Check for CPU stalls, if enabled. */ check_cpu_stall(rdp); /* Does this CPU need a deferred NOCB wakeup? */ - if (rcu_nocb_need_deferred_wakeup(rdp)) + if (rcu_nocb_need_deferred_wakeup(rdp, RCU_NOCB_WAKE)) return 1; /* Is this a nohz_full CPU in userspace or idle? (Ignore RCU if so.) */ @@ -3043,13 +3838,13 @@ static int rcu_pending(int user) return 1; /* Does this CPU have callbacks ready to invoke? */ - if (rcu_segcblist_ready_cbs(&rdp->cblist)) + if (!rcu_rdp_is_offloaded(rdp) && + rcu_segcblist_ready_cbs(&rdp->cblist)) return 1; /* Has RCU gone idle with this CPU needing another grace period? */ if (!gp_in_progress && rcu_segcblist_is_enabled(&rdp->cblist) && - (!IS_ENABLED(CONFIG_RCU_NOCB_CPU) || - !rcu_segcblist_is_offloaded(&rdp->cblist)) && + !rcu_rdp_is_offloaded(rdp) && !rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) return 1; @@ -3075,25 +3870,36 @@ static void rcu_barrier_trace(const char *s, int cpu, unsigned long done) /* * RCU callback function for rcu_barrier(). If we are last, wake * up the task executing rcu_barrier(). + * + * Note that the value of rcu_state.barrier_sequence must be captured + * before the atomic_dec_and_test(). Otherwise, if this CPU is not last, + * other CPUs might count the value down to zero before this CPU gets + * around to invoking rcu_barrier_trace(), which might result in bogus + * data from the next instance of rcu_barrier(). */ static void rcu_barrier_callback(struct rcu_head *rhp) { + unsigned long __maybe_unused s = rcu_state.barrier_sequence; + if (atomic_dec_and_test(&rcu_state.barrier_cpu_count)) { - rcu_barrier_trace(TPS("LastCB"), -1, - rcu_state.barrier_sequence); + rcu_barrier_trace(TPS("LastCB"), -1, s); complete(&rcu_state.barrier_completion); } else { - rcu_barrier_trace(TPS("CB"), -1, rcu_state.barrier_sequence); + rcu_barrier_trace(TPS("CB"), -1, s); } } /* - * Called with preemption disabled, and from cross-cpu IRQ context. + * If needed, entrain an rcu_barrier() callback on rdp->cblist. */ -static void rcu_barrier_func(void *unused) +static void rcu_barrier_entrain(struct rcu_data *rdp) { - struct rcu_data *rdp = raw_cpu_ptr(&rcu_data); + unsigned long gseq = READ_ONCE(rcu_state.barrier_sequence); + unsigned long lseq = READ_ONCE(rdp->barrier_seq_snap); + lockdep_assert_held(&rcu_state.barrier_lock); + if (rcu_seq_state(lseq) || !rcu_seq_state(gseq) || rcu_seq_ctr(lseq) != rcu_seq_ctr(gseq)) + return; rcu_barrier_trace(TPS("IRQ"), -1, rcu_state.barrier_sequence); rdp->barrier_head.func = rcu_barrier_callback; debug_rcu_head_queue(&rdp->barrier_head); @@ -3103,10 +3909,26 @@ static void rcu_barrier_func(void *unused) atomic_inc(&rcu_state.barrier_cpu_count); } else { debug_rcu_head_unqueue(&rdp->barrier_head); - rcu_barrier_trace(TPS("IRQNQ"), -1, - rcu_state.barrier_sequence); + rcu_barrier_trace(TPS("IRQNQ"), -1, rcu_state.barrier_sequence); } rcu_nocb_unlock(rdp); + smp_store_release(&rdp->barrier_seq_snap, gseq); +} + +/* + * Called with preemption disabled, and from cross-cpu IRQ context. + */ +static void rcu_barrier_handler(void *cpu_in) +{ + uintptr_t cpu = (uintptr_t)cpu_in; + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); + + lockdep_assert_irqs_disabled(); + WARN_ON_ONCE(cpu != rdp->cpu); + WARN_ON_ONCE(cpu != smp_processor_id()); + raw_spin_lock(&rcu_state.barrier_lock); + rcu_barrier_entrain(rdp); + raw_spin_unlock(&rcu_state.barrier_lock); } /** @@ -3119,7 +3941,9 @@ static void rcu_barrier_func(void *unused) */ void rcu_barrier(void) { - int cpu; + uintptr_t cpu; + unsigned long flags; + unsigned long gseq; struct rcu_data *rdp; unsigned long s = rcu_seq_snap(&rcu_state.barrier_sequence); @@ -3130,26 +3954,28 @@ void rcu_barrier(void) /* Did someone else do our work for us? */ if (rcu_seq_done(&rcu_state.barrier_sequence, s)) { - rcu_barrier_trace(TPS("EarlyExit"), -1, - rcu_state.barrier_sequence); + rcu_barrier_trace(TPS("EarlyExit"), -1, rcu_state.barrier_sequence); smp_mb(); /* caller's subsequent code after above check. */ mutex_unlock(&rcu_state.barrier_mutex); return; } /* Mark the start of the barrier operation. */ + raw_spin_lock_irqsave(&rcu_state.barrier_lock, flags); rcu_seq_start(&rcu_state.barrier_sequence); + gseq = rcu_state.barrier_sequence; rcu_barrier_trace(TPS("Inc1"), -1, rcu_state.barrier_sequence); /* - * Initialize the count to one rather than to zero in order to - * avoid a too-soon return to zero in case of a short grace period - * (or preemption of this task). Exclude CPU-hotplug operations - * to ensure that no offline CPU has callbacks queued. + * Initialize the count to two rather than to zero in order + * to avoid a too-soon return to zero in case of an immediate + * invocation of the just-enqueued callback (or preemption of + * this task). Exclude CPU-hotplug operations to ensure that no + * offline non-offloaded CPU has callbacks queued. */ init_completion(&rcu_state.barrier_completion); - atomic_set(&rcu_state.barrier_cpu_count, 1); - get_online_cpus(); + atomic_set(&rcu_state.barrier_cpu_count, 2); + raw_spin_unlock_irqrestore(&rcu_state.barrier_lock, flags); /* * Force each CPU with callbacks to register a new callback. @@ -3158,25 +3984,37 @@ void rcu_barrier(void) */ for_each_possible_cpu(cpu) { rdp = per_cpu_ptr(&rcu_data, cpu); - if (!cpu_online(cpu) && - !rcu_segcblist_is_offloaded(&rdp->cblist)) +retry: + if (smp_load_acquire(&rdp->barrier_seq_snap) == gseq) continue; - if (rcu_segcblist_n_cbs(&rdp->cblist)) { - rcu_barrier_trace(TPS("OnlineQ"), cpu, - rcu_state.barrier_sequence); - smp_call_function_single(cpu, rcu_barrier_func, NULL, 1); - } else { - rcu_barrier_trace(TPS("OnlineNQ"), cpu, - rcu_state.barrier_sequence); + raw_spin_lock_irqsave(&rcu_state.barrier_lock, flags); + if (!rcu_segcblist_n_cbs(&rdp->cblist)) { + WRITE_ONCE(rdp->barrier_seq_snap, gseq); + raw_spin_unlock_irqrestore(&rcu_state.barrier_lock, flags); + rcu_barrier_trace(TPS("NQ"), cpu, rcu_state.barrier_sequence); + continue; + } + if (!rcu_rdp_cpu_online(rdp)) { + rcu_barrier_entrain(rdp); + WARN_ON_ONCE(READ_ONCE(rdp->barrier_seq_snap) != gseq); + raw_spin_unlock_irqrestore(&rcu_state.barrier_lock, flags); + rcu_barrier_trace(TPS("OfflineNoCBQ"), cpu, rcu_state.barrier_sequence); + continue; + } + raw_spin_unlock_irqrestore(&rcu_state.barrier_lock, flags); + if (smp_call_function_single(cpu, rcu_barrier_handler, (void *)cpu, 1)) { + schedule_timeout_uninterruptible(1); + goto retry; } + WARN_ON_ONCE(READ_ONCE(rdp->barrier_seq_snap) != gseq); + rcu_barrier_trace(TPS("OnlineQ"), cpu, rcu_state.barrier_sequence); } - put_online_cpus(); /* * Now that we have an rcu_barrier_callback() callback on each * CPU, and thus each counted, remove the initial count. */ - if (atomic_dec_and_test(&rcu_state.barrier_cpu_count)) + if (atomic_sub_and_test(2, &rcu_state.barrier_cpu_count)) complete(&rcu_state.barrier_completion); /* Wait for all rcu_barrier_callback() callbacks to be invoked. */ @@ -3185,6 +4023,12 @@ void rcu_barrier(void) /* Mark the end of the barrier operation. */ rcu_barrier_trace(TPS("Inc2"), -1, rcu_state.barrier_sequence); rcu_seq_end(&rcu_state.barrier_sequence); + gseq = rcu_state.barrier_sequence; + for_each_possible_cpu(cpu) { + rdp = per_cpu_ptr(&rcu_data, cpu); + + WRITE_ONCE(rdp->barrier_seq_snap, gseq); + } /* Other rcu_barrier() invocations can now safely proceed. */ mutex_unlock(&rcu_state.barrier_mutex); @@ -3194,7 +4038,7 @@ EXPORT_SYMBOL_GPL(rcu_barrier); /* * Propagate ->qsinitmask bits up the rcu_node tree to account for the * first CPU in a given leaf rcu_node structure coming online. The caller - * must hold the corresponding leaf rcu_node ->lock with interrrupts + * must hold the corresponding leaf rcu_node ->lock with interrupts * disabled. */ static void rcu_init_new_rnp(struct rcu_node *rnp_leaf) @@ -3225,16 +4069,20 @@ 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); - WARN_ON_ONCE(rdp->dynticks_nesting != 1); - WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp))); + INIT_WORK(&rdp->strict_work, strict_work_handler); + 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; rdp->rcu_onl_gp_seq = rcu_state.gp_seq; rdp->rcu_onl_gp_flags = RCU_GP_CLEANED; + rdp->last_sched_clock = jiffies; rdp->cpu = cpu; rcu_boot_init_nocb_percpu_data(rdp); } @@ -3252,22 +4100,26 @@ 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(); /* Set up local state, ensuring consistent view of global state. */ raw_spin_lock_irqsave_rcu_node(rnp, flags); rdp->qlen_last_fqs_check = 0; - rdp->n_force_qs_snap = rcu_state.n_force_qs; + rdp->n_force_qs_snap = READ_ONCE(rcu_state.n_force_qs); rdp->blimit = blimit; - if (rcu_segcblist_empty(&rdp->cblist) && /* No early-boot CBs? */ - !rcu_segcblist_is_offloaded(&rdp->cblist)) - rcu_segcblist_init(&rdp->cblist); /* Re-enable callbacks. */ - rdp->dynticks_nesting = 1; /* CPU not up, no tearing. */ - rcu_dynticks_eqs_online(); + ct->dynticks_nesting = 1; /* CPU not up, no tearing. */ raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ /* + * Only non-NOCB CPUs that didn't have early-boot callbacks need to be + * (re-)initialized. + */ + if (!rcu_segcblist_is_enabled(&rdp->cblist)) + rcu_segcblist_init(&rdp->cblist); /* Re-enable callbacks. */ + + /* * Add CPU to leaf rcu_node pending-online bitmask. Any needed * propagation up the rcu_node tree will happen at the beginning * of the next grace period. @@ -3275,16 +4127,18 @@ int rcutree_prepare_cpu(unsigned int cpu) rnp = rdp->mynode; raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ rdp->beenonline = true; /* We have now been online. */ - rdp->gp_seq = rnp->gp_seq; - rdp->gp_seq_needed = rnp->gp_seq; + rdp->gp_seq = READ_ONCE(rnp->gp_seq); + rdp->gp_seq_needed = rdp->gp_seq; rdp->cpu_no_qs.b.norm = true; rdp->core_needs_qs = false; rdp->rcu_iw_pending = false; - rdp->rcu_iw_gp_seq = rnp->gp_seq - 1; + rdp->rcu_iw = IRQ_WORK_INIT_HARD(rcu_iw_handler); + rdp->rcu_iw_gp_seq = rdp->gp_seq - 1; trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("cpuonl")); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - rcu_prepare_kthreads(cpu); + rcu_spawn_one_boost_kthread(rnp); rcu_spawn_cpu_nocb_kthread(cpu); + WRITE_ONCE(rcu_state.n_online_cpus, rcu_state.n_online_cpus + 1); return 0; } @@ -3347,8 +4201,6 @@ int rcutree_offline_cpu(unsigned int cpu) return 0; } -static DEFINE_PER_CPU(int, rcu_cpu_started); - /* * Mark the specified CPU as being online so that subsequent grace periods * (both expedited and normal) will wait on it. Note that this means that @@ -3364,41 +4216,50 @@ void rcu_cpu_starting(unsigned int cpu) { unsigned long flags; unsigned long mask; - int nbits; - unsigned long oldmask; struct rcu_data *rdp; struct rcu_node *rnp; + bool newcpu; - if (per_cpu(rcu_cpu_started, cpu)) + rdp = per_cpu_ptr(&rcu_data, cpu); + if (rdp->cpu_started) return; + rdp->cpu_started = true; - per_cpu(rcu_cpu_started, cpu) = 1; - - rdp = per_cpu_ptr(&rcu_data, cpu); rnp = rdp->mynode; mask = rdp->grpmask; - raw_spin_lock_irqsave_rcu_node(rnp, flags); - rnp->qsmaskinitnext |= mask; - oldmask = rnp->expmaskinitnext; + local_irq_save(flags); + arch_spin_lock(&rcu_state.ofl_lock); + rcu_dynticks_eqs_online(); + raw_spin_lock(&rcu_state.barrier_lock); + raw_spin_lock_rcu_node(rnp); + WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext | mask); + raw_spin_unlock(&rcu_state.barrier_lock); + newcpu = !(rnp->expmaskinitnext & mask); rnp->expmaskinitnext |= mask; - oldmask ^= rnp->expmaskinitnext; - nbits = bitmap_weight(&oldmask, BITS_PER_LONG); /* Allow lockless access for expedited grace periods. */ - smp_store_release(&rcu_state.ncpus, rcu_state.ncpus + nbits); /* ^^^ */ + smp_store_release(&rcu_state.ncpus, rcu_state.ncpus + newcpu); /* ^^^ */ + ASSERT_EXCLUSIVE_WRITER(rcu_state.ncpus); rcu_gpnum_ovf(rnp, rdp); /* Offline-induced counter wrap? */ rdp->rcu_onl_gp_seq = READ_ONCE(rcu_state.gp_seq); rdp->rcu_onl_gp_flags = READ_ONCE(rcu_state.gp_flags); - if (rnp->qsmask & mask) { /* RCU waiting on incoming CPU? */ + + /* An incoming CPU should never be blocking a grace period. */ + if (WARN_ON_ONCE(rnp->qsmask & mask)) { /* RCU waiting on incoming CPU? */ + /* rcu_report_qs_rnp() *really* wants some flags to restore */ + unsigned long flags2; + + local_irq_save(flags2); rcu_disable_urgency_upon_qs(rdp); /* Report QS -after- changing ->qsmaskinitnext! */ - rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags); + rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags2); } else { - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + raw_spin_unlock_rcu_node(rnp); } + arch_spin_unlock(&rcu_state.ofl_lock); + local_irq_restore(flags); smp_mb(); /* Ensure RCU read-side usage follows above initialization. */ } -#ifdef CONFIG_HOTPLUG_CPU /* * The outgoing function has no further need of RCU, so remove it from * the rcu_node tree's ->qsmaskinitnext bit masks. @@ -3409,35 +4270,40 @@ void rcu_cpu_starting(unsigned int cpu) */ void rcu_report_dead(unsigned int cpu) { - unsigned long flags; + unsigned long flags, seq_flags; unsigned long mask; struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */ + // Do any dangling deferred wakeups. + do_nocb_deferred_wakeup(rdp); + /* QS for any half-done expedited grace period. */ - preempt_disable(); - rcu_report_exp_rdp(this_cpu_ptr(&rcu_data)); - preempt_enable(); + rcu_report_exp_rdp(rdp); rcu_preempt_deferred_qs(current); /* Remove outgoing CPU from mask in the leaf rcu_node structure. */ mask = rdp->grpmask; - raw_spin_lock(&rcu_state.ofl_lock); + local_irq_save(seq_flags); + arch_spin_lock(&rcu_state.ofl_lock); raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */ rdp->rcu_ofl_gp_seq = READ_ONCE(rcu_state.gp_seq); rdp->rcu_ofl_gp_flags = READ_ONCE(rcu_state.gp_flags); if (rnp->qsmask & mask) { /* RCU waiting on outgoing CPU? */ /* Report quiescent state -before- changing ->qsmaskinitnext! */ + rcu_disable_urgency_upon_qs(rdp); rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags); raw_spin_lock_irqsave_rcu_node(rnp, flags); } - rnp->qsmaskinitnext &= ~mask; + WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext & ~mask); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - raw_spin_unlock(&rcu_state.ofl_lock); + arch_spin_unlock(&rcu_state.ofl_lock); + local_irq_restore(seq_flags); - per_cpu(rcu_cpu_started, cpu) = 0; + rdp->cpu_started = false; } +#ifdef CONFIG_HOTPLUG_CPU /* * The outgoing CPU has just passed through the dying-idle state, and we * are being invoked from the CPU that was IPIed to continue the offline @@ -3451,11 +4317,13 @@ void rcutree_migrate_callbacks(int cpu) struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); bool needwake; - if (rcu_segcblist_is_offloaded(&rdp->cblist) || + if (rcu_rdp_is_offloaded(rdp) || rcu_segcblist_empty(&rdp->cblist)) return; /* No callbacks to migrate. */ - local_irq_save(flags); + raw_spin_lock_irqsave(&rcu_state.barrier_lock, flags); + WARN_ON_ONCE(rcu_rdp_cpu_online(rdp)); + rcu_barrier_entrain(rdp); my_rdp = this_cpu_ptr(&rcu_data); my_rnp = my_rdp->mynode; rcu_nocb_lock(my_rdp); /* irqs already disabled. */ @@ -3465,11 +4333,12 @@ void rcutree_migrate_callbacks(int cpu) needwake = rcu_advance_cbs(my_rnp, rdp) || rcu_advance_cbs(my_rnp, my_rdp); rcu_segcblist_merge(&my_rdp->cblist, &rdp->cblist); + raw_spin_unlock(&rcu_state.barrier_lock); /* irqs remain disabled. */ needwake = needwake || rcu_advance_cbs(my_rnp, my_rdp); rcu_segcblist_disable(&rdp->cblist); - WARN_ON_ONCE(rcu_segcblist_empty(&my_rdp->cblist) != - !rcu_segcblist_n_cbs(&my_rdp->cblist)); - if (rcu_segcblist_is_offloaded(&my_rdp->cblist)) { + WARN_ON_ONCE(rcu_segcblist_empty(&my_rdp->cblist) != !rcu_segcblist_n_cbs(&my_rdp->cblist)); + check_cb_ovld_locked(my_rdp, my_rnp); + if (rcu_rdp_is_offloaded(my_rdp)) { raw_spin_unlock_rcu_node(my_rnp); /* irqs remain disabled. */ __call_rcu_nocb_wake(my_rdp, true, flags); } else { @@ -3509,31 +4378,61 @@ static int rcu_pm_notify(struct notifier_block *self, return NOTIFY_OK; } +#ifdef CONFIG_RCU_EXP_KTHREAD +struct kthread_worker *rcu_exp_gp_kworker; +struct kthread_worker *rcu_exp_par_gp_kworker; + +static void __init rcu_start_exp_gp_kworkers(void) +{ + const char *par_gp_kworker_name = "rcu_exp_par_gp_kthread_worker"; + const char *gp_kworker_name = "rcu_exp_gp_kthread_worker"; + struct sched_param param = { .sched_priority = kthread_prio }; + + rcu_exp_gp_kworker = kthread_create_worker(0, gp_kworker_name); + if (IS_ERR_OR_NULL(rcu_exp_gp_kworker)) { + pr_err("Failed to create %s!\n", gp_kworker_name); + return; + } + + rcu_exp_par_gp_kworker = kthread_create_worker(0, par_gp_kworker_name); + if (IS_ERR_OR_NULL(rcu_exp_par_gp_kworker)) { + pr_err("Failed to create %s!\n", par_gp_kworker_name); + kthread_destroy_worker(rcu_exp_gp_kworker); + return; + } + + sched_setscheduler_nocheck(rcu_exp_gp_kworker->task, SCHED_FIFO, ¶m); + sched_setscheduler_nocheck(rcu_exp_par_gp_kworker->task, SCHED_FIFO, + ¶m); +} + +static inline void rcu_alloc_par_gp_wq(void) +{ +} +#else /* !CONFIG_RCU_EXP_KTHREAD */ +struct workqueue_struct *rcu_par_gp_wq; + +static void __init rcu_start_exp_gp_kworkers(void) +{ +} + +static inline void rcu_alloc_par_gp_wq(void) +{ + rcu_par_gp_wq = alloc_workqueue("rcu_par_gp", WQ_MEM_RECLAIM, 0); + WARN_ON(!rcu_par_gp_wq); +} +#endif /* CONFIG_RCU_EXP_KTHREAD */ + /* * Spawn the kthreads that handle RCU's grace periods. */ static int __init rcu_spawn_gp_kthread(void) { unsigned long flags; - int kthread_prio_in = kthread_prio; struct rcu_node *rnp; struct sched_param sp; struct task_struct *t; - - /* Force priority into range. */ - if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 2 - && IS_BUILTIN(CONFIG_RCU_TORTURE_TEST)) - kthread_prio = 2; - else if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 1) - kthread_prio = 1; - else if (kthread_prio < 0) - kthread_prio = 0; - else if (kthread_prio > 99) - kthread_prio = 99; - - if (kthread_prio != kthread_prio_in) - pr_alert("rcu_spawn_gp_kthread(): Limited prio to %d from %d\n", - kthread_prio, kthread_prio_in); + struct rcu_data *rdp = this_cpu_ptr(&rcu_data); rcu_scheduler_fully_active = 1; t = kthread_create(rcu_gp_kthread, NULL, "%s", rcu_state.name); @@ -3545,11 +4444,23 @@ static int __init rcu_spawn_gp_kthread(void) } rnp = rcu_get_root(); raw_spin_lock_irqsave_rcu_node(rnp, flags); - rcu_state.gp_kthread = t; + WRITE_ONCE(rcu_state.gp_activity, jiffies); + WRITE_ONCE(rcu_state.gp_req_activity, jiffies); + // Reset .gp_activity and .gp_req_activity before setting .gp_kthread. + smp_store_release(&rcu_state.gp_kthread, t); /* ^^^ */ raw_spin_unlock_irqrestore_rcu_node(rnp, flags); wake_up_process(t); - rcu_spawn_nocb_kthreads(); - rcu_spawn_boost_kthreads(); + /* This is a pre-SMP initcall, we expect a single CPU */ + WARN_ON(num_online_cpus() > 1); + /* + * Those kthreads couldn't be created on rcu_init() -> rcutree_prepare_cpu() + * due to rcu_scheduler_fully_active. + */ + rcu_spawn_cpu_nocb_kthread(smp_processor_id()); + rcu_spawn_one_boost_kthread(rdp->mynode); + rcu_spawn_core_kthreads(); + /* Create kthread worker for expedited GPs */ + rcu_start_exp_gp_kworkers(); return 0; } early_initcall(rcu_spawn_gp_kthread); @@ -3566,9 +4477,20 @@ early_initcall(rcu_spawn_gp_kthread); */ void rcu_scheduler_starting(void) { + unsigned long flags; + struct rcu_node *rnp; + WARN_ON(num_online_cpus() != 1); WARN_ON(nr_context_switches() > 0); rcu_test_sync_prims(); + + // Fix up the ->gp_seq counters. + local_irq_save(flags); + rcu_for_each_node_breadth_first(rnp) + rnp->gp_seq_needed = rnp->gp_seq = rcu_state.gp_seq; + local_irq_restore(flags); + + // Switch out of early boot mode. rcu_scheduler_active = RCU_SCHEDULER_INIT; rcu_test_sync_prims(); } @@ -3641,6 +4563,10 @@ static void __init rcu_init_one(void) init_waitqueue_head(&rnp->exp_wq[2]); init_waitqueue_head(&rnp->exp_wq[3]); spin_lock_init(&rnp->exp_lock); + mutex_init(&rnp->boost_kthread_mutex); + raw_spin_lock_init(&rnp->exp_poll_lock); + rnp->exp_seq_poll_rq = RCU_GET_STATE_COMPLETED; + INIT_WORK(&rnp->exp_poll_wq, sync_rcu_do_polled_gp); } } @@ -3656,15 +4582,51 @@ static void __init rcu_init_one(void) } /* + * Force priority from the kernel command-line into range. + */ +static void __init sanitize_kthread_prio(void) +{ + int kthread_prio_in = kthread_prio; + + if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 2 + && IS_BUILTIN(CONFIG_RCU_TORTURE_TEST)) + kthread_prio = 2; + else if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 1) + kthread_prio = 1; + else if (kthread_prio < 0) + kthread_prio = 0; + else if (kthread_prio > 99) + kthread_prio = 99; + + if (kthread_prio != kthread_prio_in) + pr_alert("%s: Limited prio to %d from %d\n", + __func__, kthread_prio, kthread_prio_in); +} + +/* * Compute the rcu_node tree geometry from kernel parameters. This cannot * replace the definitions in tree.h because those are needed to size * the ->node array in the rcu_state structure. */ -static void __init rcu_init_geometry(void) +void rcu_init_geometry(void) { ulong d; int i; + static unsigned long old_nr_cpu_ids; int rcu_capacity[RCU_NUM_LVLS]; + static bool initialized; + + if (initialized) { + /* + * Warn if setup_nr_cpu_ids() had not yet been invoked, + * unless nr_cpus_ids == NR_CPUS, in which case who cares? + */ + WARN_ON_ONCE(old_nr_cpu_ids != nr_cpu_ids); + return; + } + + old_nr_cpu_ids = nr_cpu_ids; + initialized = true; /* * Initialize any unspecified boot parameters. @@ -3758,32 +4720,49 @@ static void __init rcu_dump_rcu_node_tree(void) } struct workqueue_struct *rcu_gp_wq; -struct workqueue_struct *rcu_par_gp_wq; static void __init kfree_rcu_batch_init(void) { int cpu; int i; + /* Clamp it to [0:100] seconds interval. */ + if (rcu_delay_page_cache_fill_msec < 0 || + rcu_delay_page_cache_fill_msec > 100 * MSEC_PER_SEC) { + + rcu_delay_page_cache_fill_msec = + clamp(rcu_delay_page_cache_fill_msec, 0, + (int) (100 * MSEC_PER_SEC)); + + pr_info("Adjusting rcutree.rcu_delay_page_cache_fill_msec to %d ms.\n", + rcu_delay_page_cache_fill_msec); + } + for_each_possible_cpu(cpu) { struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu); - spin_lock_init(&krcp->lock); - for (i = 0; i < KFREE_N_BATCHES; i++) + for (i = 0; i < KFREE_N_BATCHES; i++) { + INIT_RCU_WORK(&krcp->krw_arr[i].rcu_work, kfree_rcu_work); krcp->krw_arr[i].krcp = krcp; + } + INIT_DELAYED_WORK(&krcp->monitor_work, kfree_rcu_monitor); + INIT_DELAYED_WORK(&krcp->page_cache_work, fill_page_cache_func); krcp->initialized = true; } + if (register_shrinker(&kfree_rcu_shrinker, "rcu-kfree")) + pr_err("Failed to register kfree_rcu() shrinker!\n"); } void __init rcu_init(void) { - int cpu; + int cpu = smp_processor_id(); rcu_early_boot_tests(); kfree_rcu_batch_init(); rcu_bootup_announce(); + sanitize_kthread_prio(); rcu_init_geometry(); rcu_init_one(); if (dump_tree) @@ -3797,20 +4776,29 @@ void __init rcu_init(void) * or the scheduler are operational. */ pm_notifier(rcu_pm_notify, 0); - for_each_online_cpu(cpu) { - rcutree_prepare_cpu(cpu); - rcu_cpu_starting(cpu); - rcutree_online_cpu(cpu); - } + WARN_ON(num_online_cpus() > 1); // Only one CPU this early in boot. + rcutree_prepare_cpu(cpu); + rcu_cpu_starting(cpu); + rcutree_online_cpu(cpu); - /* Create workqueue for expedited GPs and for Tree SRCU. */ + /* Create workqueue for Tree SRCU and for expedited GPs. */ rcu_gp_wq = alloc_workqueue("rcu_gp", WQ_MEM_RECLAIM, 0); WARN_ON(!rcu_gp_wq); - rcu_par_gp_wq = alloc_workqueue("rcu_par_gp", WQ_MEM_RECLAIM, 0); - WARN_ON(!rcu_par_gp_wq); - srcu_init(); + rcu_alloc_par_gp_wq(); + + /* Fill in default value for rcutree.qovld boot parameter. */ + /* -After- the rcu_node ->lock fields are initialized! */ + if (qovld < 0) + qovld_calc = DEFAULT_RCU_QOVLD_MULT * qhimark; + else + qovld_calc = qovld; + + // Kick-start any polled grace periods that started early. + if (!(per_cpu_ptr(&rcu_data, cpu)->mynode->exp_seq_poll_rq & 0x1)) + (void)start_poll_synchronize_rcu_expedited(); } #include "tree_stall.h" #include "tree_exp.h" +#include "tree_nocb.h" #include "tree_plugin.h" |