diff options
Diffstat (limited to 'kernel/rcu/tree.c')
| -rw-r--r-- | kernel/rcu/tree.c | 5975 |
1 files changed, 3327 insertions, 2648 deletions
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 51d4c3acf32d..293bbd9ac3f4 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1,32 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0+ /* - * Read-Copy Update mechanism for mutual exclusion - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, you can access it online at - * http://www.gnu.org/licenses/gpl-2.0.html. + * 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.vnet.ibm.com> Hierarchical version + * Paul E. McKenney <paulmck@linux.ibm.com> * - * Based on the original work by Paul McKenney <paulmck@us.ibm.com> + * Based on the original work by Paul McKenney <paulmck@linux.ibm.com> * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen. * * For detailed explanation of Read-Copy Update mechanism see - * Documentation/RCU */ + +#define pr_fmt(fmt) "rcu: " fmt + #include <linux/types.h> #include <linux/kernel.h> #include <linux/init.h> @@ -41,7 +31,10 @@ #include <linux/bitops.h> #include <linux/export.h> #include <linux/completion.h> +#include <linux/kmemleak.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> @@ -53,11 +46,25 @@ #include <uapi/linux/sched/types.h> #include <linux/prefetch.h> #include <linux/delay.h> -#include <linux/stop_machine.h> #include <linux/random.h> #include <linux/trace_events.h> #include <linux/suspend.h> #include <linux/ftrace.h> +#include <linux/tick.h> +#include <linux/sysrq.h> +#include <linux/kprobes.h> +#include <linux/gfp.h> +#include <linux/oom.h> +#include <linux/smpboot.h> +#include <linux/jiffies.h> +#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" #include "rcu.h" @@ -68,54 +75,47 @@ #define MODULE_PARAM_PREFIX "rcutree." /* Data structures. */ +static void rcu_sr_normal_gp_cleanup_work(struct work_struct *); -/* - * In order to export the rcu_state name to the tracing tools, it - * needs to be added in the __tracepoint_string section. - * This requires defining a separate variable tp_<sname>_varname - * that points to the string being used, and this will allow - * the tracing userspace tools to be able to decipher the string - * address to the matching string. - */ -#ifdef CONFIG_TRACING -# define DEFINE_RCU_TPS(sname) \ -static char sname##_varname[] = #sname; \ -static const char *tp_##sname##_varname __used __tracepoint_string = sname##_varname; -# define RCU_STATE_NAME(sname) sname##_varname -#else -# define DEFINE_RCU_TPS(sname) -# define RCU_STATE_NAME(sname) __stringify(sname) -#endif +static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, rcu_data) = { + .gpwrap = true, +}; -#define RCU_STATE_INITIALIZER(sname, sabbr, cr) \ -DEFINE_RCU_TPS(sname) \ -static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, sname##_data); \ -struct rcu_state sname##_state = { \ - .level = { &sname##_state.node[0] }, \ - .rda = &sname##_data, \ - .call = cr, \ - .gp_state = RCU_GP_IDLE, \ - .gpnum = 0UL - 300UL, \ - .completed = 0UL - 300UL, \ - .orphan_lock = __RAW_SPIN_LOCK_UNLOCKED(&sname##_state.orphan_lock), \ - .orphan_pend = RCU_CBLIST_INITIALIZER(sname##_state.orphan_pend), \ - .orphan_done = RCU_CBLIST_INITIALIZER(sname##_state.orphan_done), \ - .barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \ - .name = RCU_STATE_NAME(sname), \ - .abbr = sabbr, \ - .exp_mutex = __MUTEX_INITIALIZER(sname##_state.exp_mutex), \ - .exp_wake_mutex = __MUTEX_INITIALIZER(sname##_state.exp_wake_mutex), \ -} - -RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched); -RCU_STATE_INITIALIZER(rcu_bh, 'b', call_rcu_bh); - -static struct rcu_state *const rcu_state_p; -LIST_HEAD(rcu_struct_flavors); +int rcu_get_gpwrap_count(int cpu) +{ + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); + + return READ_ONCE(rdp->gpwrap_count); +} +EXPORT_SYMBOL_GPL(rcu_get_gpwrap_count); + +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 = __ARCH_SPIN_LOCK_UNLOCKED, + .srs_cleanup_work = __WORK_INITIALIZER(rcu_state.srs_cleanup_work, + rcu_sr_normal_gp_cleanup_work), + .srs_cleanups_pending = ATOMIC_INIT(0), +#ifdef CONFIG_RCU_NOCB_CPU + .nocb_mutex = __MUTEX_INITIALIZER(rcu_state.nocb_mutex), +#endif +}; /* 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 = !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); @@ -126,8 +126,6 @@ int rcu_num_lvls __read_mostly = RCU_NUM_LVLS; /* Number of rcu_nodes at specified level. */ int num_rcu_lvl[] = NUM_RCU_LVL_INIT; int rcu_num_nodes __read_mostly = NUM_RCU_NODES; /* Total # rcu_nodes in use. */ -/* panic() on RCU Stall sysctl. */ -int sysctl_panic_on_rcu_stall __read_mostly; /* * The rcu_scheduler_active variable is initialized to the value @@ -158,18 +156,24 @@ EXPORT_SYMBOL_GPL(rcu_scheduler_active); */ static int rcu_scheduler_fully_active __read_mostly; -static void rcu_init_new_rnp(struct rcu_node *rnp_leaf); -static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf); -static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu); +static void rcu_report_qs_rnp(unsigned long mask, struct rcu_node *rnp, + unsigned long gps, unsigned long flags); static void invoke_rcu_core(void); -static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp); -static void rcu_report_exp_rdp(struct rcu_state *rsp, - struct rcu_data *rdp, bool wake); -static void sync_sched_exp_online_cleanup(int cpu); +static void rcu_report_exp_rdp(struct rcu_data *rdp); +static void check_cb_ovld_locked(struct rcu_data *rdp, struct rcu_node *rnp); +static bool rcu_rdp_is_offloaded(struct rcu_data *rdp); +static bool rcu_rdp_cpu_online(struct rcu_data *rdp); +static bool rcu_init_invoked(void); +static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf); +static void rcu_init_new_rnp(struct rcu_node *rnp_leaf); -/* 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, 0644); +module_param(kthread_prio, int, 0444); /* Delay in jiffies for grace-period initialization delays, debug only. */ @@ -179,6 +183,22 @@ static int gp_init_delay; module_param(gp_init_delay, int, 0444); static int gp_cleanup_delay; module_param(gp_cleanup_delay, int, 0444); +static int nohz_full_patience_delay; +module_param(nohz_full_patience_delay, int, 0444); +static int nohz_full_patience_delay_jiffies; + +// 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 + +/* Retrieve RCU kthreads priority for rcutorture */ +int rcu_get_gp_kthreads_prio(void) +{ + return kthread_prio; +} +EXPORT_SYMBOL_GPL(rcu_get_gp_kthreads_prio); /* * Number of grace periods between delays, normalized by the duration of @@ -189,246 +209,138 @@ module_param(gp_cleanup_delay, int, 0444); * 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. */ - -/* - * Track the rcutorture test sequence number and the update version - * number within a given test. The rcutorture_testseq is incremented - * on every rcutorture module load and unload, so has an odd value - * when a test is running. The rcutorture_vernum is set to zero - * when rcutorture starts and is incremented on each rcutorture update. - * These variables enable correlating rcutorture output with the - * RCU tracing information. - */ -unsigned long rcutorture_testseq; -unsigned long rcutorture_vernum; - -/* - * Compute the mask of online CPUs for the specified rcu_node structure. - * This will not be stable unless the rcu_node structure's ->lock is - * held, but the bit corresponding to the current CPU will be stable - * in most contexts. - */ -unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp) -{ - return READ_ONCE(rnp->qsmaskinitnext); -} +#define PER_RCU_NODE_PERIOD 3 /* Number of grace periods between delays for debugging. */ /* * 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. */ -static int rcu_gp_in_progress(struct rcu_state *rsp) -{ - return READ_ONCE(rsp->completed) != READ_ONCE(rsp->gpnum); -} - -/* - * Note a quiescent state. Because we do not need to know - * how many quiescent states passed, just if there was at least - * one since the start of the grace period, this just sets a flag. - * The caller must have disabled preemption. - */ -void rcu_sched_qs(void) -{ - RCU_LOCKDEP_WARN(preemptible(), "rcu_sched_qs() invoked with preemption enabled!!!"); - if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.s)) - return; - trace_rcu_grace_period(TPS("rcu_sched"), - __this_cpu_read(rcu_sched_data.gpnum), - TPS("cpuqs")); - __this_cpu_write(rcu_sched_data.cpu_no_qs.b.norm, false); - if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp)) - return; - __this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, false); - rcu_report_exp_rdp(&rcu_sched_state, - this_cpu_ptr(&rcu_sched_data), true); -} - -void rcu_bh_qs(void) -{ - RCU_LOCKDEP_WARN(preemptible(), "rcu_bh_qs() invoked with preemption enabled!!!"); - if (__this_cpu_read(rcu_bh_data.cpu_no_qs.s)) { - trace_rcu_grace_period(TPS("rcu_bh"), - __this_cpu_read(rcu_bh_data.gpnum), - TPS("cpuqs")); - __this_cpu_write(rcu_bh_data.cpu_no_qs.b.norm, false); - } -} - -/* - * 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(struct rcu_dynticks, rcu_dynticks) = { - .dynticks_nesting = DYNTICK_TASK_EXIT_IDLE, - .dynticks = ATOMIC_INIT(RCU_DYNTICK_CTRL_CTR), -}; - -/* - * There's a few places, currently just in the tracing infrastructure, - * that uses rcu_irq_enter() to make sure RCU is watching. But there's - * a small location where that will not even work. In those cases - * rcu_irq_enter_disabled() needs to be checked to make sure rcu_irq_enter() - * can be called. - */ -static DEFINE_PER_CPU(bool, disable_rcu_irq_enter); - -bool rcu_irq_enter_disabled(void) +static int rcu_gp_in_progress(void) { - return this_cpu_read(disable_rcu_irq_enter); + return rcu_seq_state(rcu_seq_current(&rcu_state.gp_seq)); } /* - * Record entry into an extended quiescent state. This is only to be - * called when not already in an extended quiescent state. + * Return the number of callbacks queued on the specified CPU. + * Handles both the nocbs and normal cases. */ -static void rcu_dynticks_eqs_enter(void) +static long rcu_get_n_cbs_cpu(int cpu) { - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); - int seq; + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); - /* - * 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, &rdtp->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)); + if (rcu_segcblist_is_enabled(&rdp->cblist)) + return rcu_segcblist_n_cbs(&rdp->cblist); + return 0; } -/* - * Record exit from an extended quiescent state. This is only to be - * called from an extended quiescent state. +/** + * rcu_softirq_qs - Provide a set of RCU quiescent states in softirq processing + * + * Mark a quiescent state for RCU, Tasks RCU, and Tasks Trace RCU. + * This is a special-purpose function to be used in the softirq + * infrastructure and perhaps the occasional long-running softirq + * handler. + * + * Note that from RCU's viewpoint, a call to rcu_softirq_qs() is + * equivalent to momentarily completely enabling preemption. For + * example, given this code:: + * + * local_bh_disable(); + * do_something(); + * rcu_softirq_qs(); // A + * do_something_else(); + * local_bh_enable(); // B + * + * A call to synchronize_rcu() that began concurrently with the + * call to do_something() would be guaranteed to wait only until + * execution reached statement A. Without that rcu_softirq_qs(), + * that same synchronize_rcu() would instead be guaranteed to wait + * until execution reached statement B. */ -static void rcu_dynticks_eqs_exit(void) +void rcu_softirq_qs(void) { - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); - 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, &rdtp->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, &rdtp->dynticks); - smp_mb__after_atomic(); /* _exit after clearing mask. */ - /* Prefer duplicate flushes to losing a flush. */ - rcu_eqs_special_exit(); - } + RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) || + lock_is_held(&rcu_lock_map) || + lock_is_held(&rcu_sched_lock_map), + "Illegal rcu_softirq_qs() in RCU read-side critical section"); + rcu_qs(); + rcu_preempt_deferred_qs(current); + rcu_tasks_qs(current, false); } /* - * Reset the current CPU's ->dynticks counter to indicate that the + * Reset the current CPU's RCU_WATCHING counter to indicate that the * newly onlined CPU is no longer in an extended quiescent state. * This will either leave the counter unchanged, or increment it * to the next non-quiescent value. * * The non-atomic test/increment sequence works because the upper bits - * of the ->dynticks counter are manipulated only by the corresponding CPU, + * of the ->state variable are manipulated only by the corresponding CPU, * or when the corresponding CPU is offline. */ -static void rcu_dynticks_eqs_online(void) +static void rcu_watching_online(void) { - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); - - if (atomic_read(&rdtp->dynticks) & RCU_DYNTICK_CTRL_CTR) + if (ct_rcu_watching() & CT_RCU_WATCHING) return; - atomic_add(RCU_DYNTICK_CTRL_CTR, &rdtp->dynticks); + ct_state_inc(CT_RCU_WATCHING); } /* - * Is the current CPU in an extended quiescent state? - * - * No ordering, as we are sampling CPU-local information. - */ -bool rcu_dynticks_curr_cpu_in_eqs(void) -{ - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); - - return !(atomic_read(&rdtp->dynticks) & RCU_DYNTICK_CTRL_CTR); -} - -/* - * Snapshot the ->dynticks counter with full ordering so as to allow - * stable comparison of this counter with past and future snapshots. - */ -int rcu_dynticks_snap(struct rcu_dynticks *rdtp) -{ - int snap = atomic_add_return(0, &rdtp->dynticks); - - return snap & ~RCU_DYNTICK_CTRL_MASK; -} - -/* - * Return true if the snapshot returned from rcu_dynticks_snap() + * Return true if the snapshot returned from ct_rcu_watching() * indicates that RCU is in an extended quiescent state. */ -static bool rcu_dynticks_in_eqs(int snap) +static bool rcu_watching_snap_in_eqs(int snap) { - return !(snap & RCU_DYNTICK_CTRL_CTR); + return !(snap & CT_RCU_WATCHING); } -/* - * Return true if the CPU corresponding to the specified rcu_dynticks - * structure has spent some time in an extended quiescent state since - * rcu_dynticks_snap() returned the specified snapshot. +/** + * rcu_watching_snap_stopped_since() - Has RCU stopped watching a given CPU + * since the specified @snap? + * + * @rdp: The rcu_data corresponding to the CPU for which to check EQS. + * @snap: rcu_watching snapshot taken when the CPU wasn't in an EQS. + * + * Returns true if the CPU corresponding to @rdp has spent some time in an + * extended quiescent state since @snap. Note that this doesn't check if it + * /still/ is in an EQS, just that it went through one since @snap. + * + * This is meant to be used in a loop waiting for a CPU to go through an EQS. */ -static bool rcu_dynticks_in_eqs_since(struct rcu_dynticks *rdtp, int snap) +static bool rcu_watching_snap_stopped_since(struct rcu_data *rdp, int snap) { - return snap != rcu_dynticks_snap(rdtp); + /* + * The first failing snapshot is already ordered against the accesses + * performed by the remote CPU after it exits idle. + * + * The second snapshot therefore only needs to order against accesses + * performed by the remote CPU prior to entering idle and therefore can + * rely solely on acquire semantics. + */ + if (WARN_ON_ONCE(rcu_watching_snap_in_eqs(snap))) + return true; + + return snap != ct_rcu_watching_cpu_acquire(rdp->cpu); } /* - * Do a double-increment of the ->dynticks counter to emulate a - * momentary idle-CPU quiescent state. + * Return true if the referenced integer is zero while the specified + * CPU remains within a single extended quiescent state. */ -static void rcu_dynticks_momentary_idle(void) +bool rcu_watching_zero_in_eqs(int cpu, int *vp) { - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); - int special = atomic_add_return(2 * RCU_DYNTICK_CTRL_CTR, - &rdtp->dynticks); + int snap; - /* It is illegal to call this from idle state. */ - WARN_ON_ONCE(!(special & RCU_DYNTICK_CTRL_CTR)); -} + // If not quiescent, force back to earlier extended quiescent state. + snap = ct_rcu_watching_cpu(cpu) & ~CT_RCU_WATCHING; + smp_rmb(); // Order CT state and *vp reads. + if (READ_ONCE(*vp)) + return false; // Non-zero, so report failure; + smp_rmb(); // Order *vp read and CT state re-read. -/* - * 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. - */ -bool rcu_eqs_special_set(int cpu) -{ - int old; - int new; - struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); - - do { - old = atomic_read(&rdtp->dynticks); - if (old & RCU_DYNTICK_CTRL_CTR) - return false; - new = old | RCU_DYNTICK_CTRL_MASK; - } while (atomic_cmpxchg(&rdtp->dynticks, old, new) != old); - return true; + // If still in the same extended quiescent state, we are good! + return snap == ct_rcu_watching_cpu(cpu); } /* @@ -440,165 +352,176 @@ bool rcu_eqs_special_set(int cpu) * * We inform the RCU core by emulating a zero-duration dyntick-idle period. * - * The caller must have disabled interrupts. + * The caller must have disabled interrupts and must not be idle. */ -static void rcu_momentary_dyntick_idle(void) +notrace void rcu_momentary_eqs(void) { - raw_cpu_write(rcu_dynticks.rcu_need_heavy_qs, false); - rcu_dynticks_momentary_idle(); -} + int seq; -/* - * Note a context switch. This is a quiescent state for RCU-sched, - * and requires special handling for preemptible RCU. - * The caller must have disabled interrupts. - */ -void rcu_note_context_switch(bool preempt) -{ - barrier(); /* Avoid RCU read-side critical sections leaking down. */ - trace_rcu_utilization(TPS("Start context switch")); - rcu_sched_qs(); - rcu_preempt_note_context_switch(preempt); - /* Load rcu_urgent_qs before other flags. */ - if (!smp_load_acquire(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs))) - goto out; - this_cpu_write(rcu_dynticks.rcu_urgent_qs, false); - if (unlikely(raw_cpu_read(rcu_dynticks.rcu_need_heavy_qs))) - rcu_momentary_dyntick_idle(); - this_cpu_inc(rcu_dynticks.rcu_qs_ctr); - if (!preempt) - rcu_note_voluntary_context_switch_lite(current); -out: - trace_rcu_utilization(TPS("End context switch")); - barrier(); /* Avoid RCU read-side critical sections leaking up. */ -} -EXPORT_SYMBOL_GPL(rcu_note_context_switch); + raw_cpu_write(rcu_data.rcu_need_heavy_qs, false); + seq = ct_state_inc(2 * CT_RCU_WATCHING); + /* It is illegal to call this from idle state. */ + WARN_ON_ONCE(!(seq & CT_RCU_WATCHING)); + rcu_preempt_deferred_qs(current); +} +EXPORT_SYMBOL_GPL(rcu_momentary_eqs); -/* - * Register a quiescent state for all RCU flavors. If there is an - * emergency, invoke rcu_momentary_dyntick_idle() to do a heavy-weight - * dyntick-idle quiescent state visible to other CPUs (but only for those - * RCU flavors in desperate need of a quiescent state, which will normally - * be none of them). Either way, do a lightweight quiescent state for - * all RCU flavors. +/** + * rcu_is_cpu_rrupt_from_idle - see if 'interrupted' from idle * - * The barrier() calls are redundant in the common case when this is - * called externally, but just in case this is called from within this - * file. + * If the current CPU is idle and running at a first-level (not nested) + * interrupt, or directly, from idle, return true. * + * The caller must have at least disabled IRQs. */ -void rcu_all_qs(void) +static int rcu_is_cpu_rrupt_from_idle(void) { - unsigned long flags; + long nmi_nesting = ct_nmi_nesting(); - if (!raw_cpu_read(rcu_dynticks.rcu_urgent_qs)) - return; - preempt_disable(); - /* Load rcu_urgent_qs before other flags. */ - if (!smp_load_acquire(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs))) { - preempt_enable(); - return; - } - this_cpu_write(rcu_dynticks.rcu_urgent_qs, false); - barrier(); /* Avoid RCU read-side critical sections leaking down. */ - if (unlikely(raw_cpu_read(rcu_dynticks.rcu_need_heavy_qs))) { - local_irq_save(flags); - rcu_momentary_dyntick_idle(); - local_irq_restore(flags); + /* + * 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(ct_nesting() < 0, + "RCU nesting counter underflow!"); + + /* Non-idle interrupt or nested idle interrupt */ + if (nmi_nesting > 1) + return false; + + /* + * Non nested idle interrupt (interrupting section where RCU + * wasn't watching). + */ + if (nmi_nesting == 1) + return true; + + /* Not in an interrupt */ + if (!nmi_nesting) { + RCU_LOCKDEP_WARN(!in_task() || !is_idle_task(current), + "RCU nmi_nesting counter not in idle task!"); + return !rcu_is_watching_curr_cpu(); } - if (unlikely(raw_cpu_read(rcu_sched_data.cpu_no_qs.b.exp))) - rcu_sched_qs(); - this_cpu_inc(rcu_dynticks.rcu_qs_ctr); - barrier(); /* Avoid RCU read-side critical sections leaking up. */ - preempt_enable(); + + RCU_LOCKDEP_WARN(1, "RCU nmi_nesting counter underflow/zero!"); + + return false; } -EXPORT_SYMBOL_GPL(rcu_all_qs); -#define DEFAULT_RCU_BLIMIT 10 /* Maximum callbacks per rcu_do_batch. */ +#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; +module_param(rcu_divisor, int, 0644); -module_param(jiffies_till_first_fqs, ulong, 0644); -module_param(jiffies_till_next_fqs, ulong, 0644); -module_param(rcu_kick_kthreads, bool, 0644); +/* Force an exit from rcu_do_batch() after 3 milliseconds. */ +static long rcu_resched_ns = 3 * NSEC_PER_MSEC; +module_param(rcu_resched_ns, long, 0644); /* * How long the grace period must be before we start recruiting * quiescent-state help from rcu_note_context_switch(). */ -static ulong jiffies_till_sched_qs = HZ / 20; -module_param(jiffies_till_sched_qs, ulong, 0644); - -static bool rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp, - struct rcu_data *rdp); -static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp)); -static void force_quiescent_state(struct rcu_state *rsp); -static int rcu_pending(void); +static ulong jiffies_till_sched_qs = ULONG_MAX; +module_param(jiffies_till_sched_qs, ulong, 0444); +static ulong jiffies_to_sched_qs; /* See adjust_jiffies_till_sched_qs(). */ +module_param(jiffies_to_sched_qs, ulong, 0444); /* Display only! */ /* - * Return the number of RCU batches started thus far for debug & stats. + * Make sure that we give the grace-period kthread time to detect any + * idle CPUs before taking active measures to force quiescent states. + * However, don't go below 100 milliseconds, adjusted upwards for really + * large systems. */ -unsigned long rcu_batches_started(void) +static void adjust_jiffies_till_sched_qs(void) { - return rcu_state_p->gpnum; -} -EXPORT_SYMBOL_GPL(rcu_batches_started); + unsigned long j; -/* - * Return the number of RCU-sched batches started thus far for debug & stats. - */ -unsigned long rcu_batches_started_sched(void) -{ - return rcu_sched_state.gpnum; + /* If jiffies_till_sched_qs was specified, respect the request. */ + if (jiffies_till_sched_qs != ULONG_MAX) { + WRITE_ONCE(jiffies_to_sched_qs, jiffies_till_sched_qs); + return; + } + /* Otherwise, set to third fqs scan, but bound below on large system. */ + j = READ_ONCE(jiffies_till_first_fqs) + + 2 * READ_ONCE(jiffies_till_next_fqs); + if (j < HZ / 10 + nr_cpu_ids / RCU_JIFFIES_FQS_DIV) + j = HZ / 10 + nr_cpu_ids / RCU_JIFFIES_FQS_DIV; + pr_info("RCU calculated value of scheduler-enlistment delay is %ld jiffies.\n", j); + WRITE_ONCE(jiffies_to_sched_qs, j); } -EXPORT_SYMBOL_GPL(rcu_batches_started_sched); -/* - * Return the number of RCU BH batches started thus far for debug & stats. - */ -unsigned long rcu_batches_started_bh(void) +static int param_set_first_fqs_jiffies(const char *val, const struct kernel_param *kp) { - return rcu_bh_state.gpnum; -} -EXPORT_SYMBOL_GPL(rcu_batches_started_bh); + ulong j; + int ret = kstrtoul(val, 0, &j); -/* - * Return the number of RCU batches completed thus far for debug & stats. - */ -unsigned long rcu_batches_completed(void) -{ - return rcu_state_p->completed; + if (!ret) { + WRITE_ONCE(*(ulong *)kp->arg, (j > HZ) ? HZ : j); + adjust_jiffies_till_sched_qs(); + } + return ret; } -EXPORT_SYMBOL_GPL(rcu_batches_completed); -/* - * Return the number of RCU-sched batches completed thus far for debug & stats. - */ -unsigned long rcu_batches_completed_sched(void) +static int param_set_next_fqs_jiffies(const char *val, const struct kernel_param *kp) { - return rcu_sched_state.completed; + ulong j; + int ret = kstrtoul(val, 0, &j); + + if (!ret) { + WRITE_ONCE(*(ulong *)kp->arg, (j > HZ) ? HZ : (j ?: 1)); + adjust_jiffies_till_sched_qs(); + } + return ret; } -EXPORT_SYMBOL_GPL(rcu_batches_completed_sched); + +static const struct kernel_param_ops first_fqs_jiffies_ops = { + .set = param_set_first_fqs_jiffies, + .get = param_get_ulong, +}; + +static const struct kernel_param_ops next_fqs_jiffies_ops = { + .set = param_set_next_fqs_jiffies, + .get = param_get_ulong, +}; + +module_param_cb(jiffies_till_first_fqs, &first_fqs_jiffies_ops, &jiffies_till_first_fqs, 0644); +module_param_cb(jiffies_till_next_fqs, &next_fqs_jiffies_ops, &jiffies_till_next_fqs, 0644); +module_param(rcu_kick_kthreads, bool, 0644); + +static void force_qs_rnp(int (*f)(struct rcu_data *rdp)); +static int rcu_pending(int user); /* - * Return the number of RCU BH batches completed thus far for debug & stats. + * Return the number of RCU GPs completed thus far for debug & stats. */ -unsigned long rcu_batches_completed_bh(void) +unsigned long rcu_get_gp_seq(void) { - return rcu_bh_state.completed; + return READ_ONCE(rcu_state.gp_seq); } -EXPORT_SYMBOL_GPL(rcu_batches_completed_bh); +EXPORT_SYMBOL_GPL(rcu_get_gp_seq); /* * Return the number of RCU expedited batches completed thus far for @@ -608,521 +531,224 @@ EXPORT_SYMBOL_GPL(rcu_batches_completed_bh); */ unsigned long rcu_exp_batches_completed(void) { - return rcu_state_p->expedited_sequence; + return rcu_state.expedited_sequence; } EXPORT_SYMBOL_GPL(rcu_exp_batches_completed); /* - * Return the number of RCU-sched expedited batches completed thus far - * for debug & stats. Similar to rcu_exp_batches_completed(). - */ -unsigned long rcu_exp_batches_completed_sched(void) -{ - return rcu_sched_state.expedited_sequence; -} -EXPORT_SYMBOL_GPL(rcu_exp_batches_completed_sched); - -/* - * Force a quiescent state. - */ -void rcu_force_quiescent_state(void) -{ - force_quiescent_state(rcu_state_p); -} -EXPORT_SYMBOL_GPL(rcu_force_quiescent_state); - -/* - * Force a quiescent state for RCU BH. + * Return the root node of the rcu_state structure. */ -void rcu_bh_force_quiescent_state(void) +static struct rcu_node *rcu_get_root(void) { - force_quiescent_state(&rcu_bh_state); + return &rcu_state.node[0]; } -EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state); - -/* - * Force a quiescent state for RCU-sched. - */ -void rcu_sched_force_quiescent_state(void) -{ - force_quiescent_state(&rcu_sched_state); -} -EXPORT_SYMBOL_GPL(rcu_sched_force_quiescent_state); - -/* - * Show the state of the grace-period kthreads. - */ -void show_rcu_gp_kthreads(void) -{ - struct rcu_state *rsp; - - for_each_rcu_flavor(rsp) { - pr_info("%s: wait state: %d ->state: %#lx\n", - rsp->name, rsp->gp_state, rsp->gp_kthread->state); - /* sched_show_task(rsp->gp_kthread); */ - } -} -EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads); - -/* - * Record the number of times rcutorture tests have been initiated and - * terminated. This information allows the debugfs tracing stats to be - * correlated to the rcutorture messages, even when the rcutorture module - * is being repeatedly loaded and unloaded. In other words, we cannot - * store this state in rcutorture itself. - */ -void rcutorture_record_test_transition(void) -{ - rcutorture_testseq++; - rcutorture_vernum = 0; -} -EXPORT_SYMBOL_GPL(rcutorture_record_test_transition); /* * Send along grace-period-related data for rcutorture diagnostics. */ -void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, - unsigned long *gpnum, unsigned long *completed) +void rcutorture_get_gp_data(int *flags, unsigned long *gp_seq) { - struct rcu_state *rsp = NULL; - - switch (test_type) { - case RCU_FLAVOR: - rsp = rcu_state_p; - break; - case RCU_BH_FLAVOR: - rsp = &rcu_bh_state; - break; - case RCU_SCHED_FLAVOR: - rsp = &rcu_sched_state; - break; - default: - break; - } - if (rsp == NULL) - return; - *flags = READ_ONCE(rsp->gp_flags); - *gpnum = READ_ONCE(rsp->gpnum); - *completed = READ_ONCE(rsp->completed); + *flags = READ_ONCE(rcu_state.gp_flags); + *gp_seq = rcu_seq_current(&rcu_state.gp_seq); } EXPORT_SYMBOL_GPL(rcutorture_get_gp_data); -/* - * Record the number of writer passes through the current rcutorture test. - * This is also used to correlate debugfs tracing stats with the rcutorture - * messages. - */ -void rcutorture_record_progress(unsigned long vernum) +/* Gather grace-period sequence numbers for rcutorture diagnostics. */ +unsigned long long rcutorture_gather_gp_seqs(void) { - rcutorture_vernum++; + return ((READ_ONCE(rcu_state.gp_seq) & 0xffffULL) << 40) | + ((READ_ONCE(rcu_state.expedited_sequence) & 0xffffffULL) << 16) | + (READ_ONCE(rcu_state.gp_seq_polled) & 0xffffULL); } -EXPORT_SYMBOL_GPL(rcutorture_record_progress); +EXPORT_SYMBOL_GPL(rcutorture_gather_gp_seqs); -/* - * Return the root node of the specified rcu_state structure. - */ -static struct rcu_node *rcu_get_root(struct rcu_state *rsp) +/* Format grace-period sequence numbers for rcutorture diagnostics. */ +void rcutorture_format_gp_seqs(unsigned long long seqs, char *cp, size_t len) { - return &rsp->node[0]; + unsigned int egp = (seqs >> 16) & 0xffffffULL; + unsigned int ggp = (seqs >> 40) & 0xffffULL; + unsigned int pgp = seqs & 0xffffULL; + + snprintf(cp, len, "g%04x:e%06x:p%04x", ggp, egp, pgp); } +EXPORT_SYMBOL_GPL(rcutorture_format_gp_seqs); +#if defined(CONFIG_NO_HZ_FULL) && (!defined(CONFIG_GENERIC_ENTRY) || !defined(CONFIG_VIRT_XFER_TO_GUEST_WORK)) /* - * Is there any need for future grace periods? - * Interrupts must be disabled. If the caller does not hold the root - * rnp_node structure's ->lock, the results are advisory only. + * An empty function that will trigger a reschedule on + * IRQ tail once IRQs get re-enabled on userspace/guest resume. */ -static int rcu_future_needs_gp(struct rcu_state *rsp) +static void late_wakeup_func(struct irq_work *work) { - struct rcu_node *rnp = rcu_get_root(rsp); - int idx = (READ_ONCE(rnp->completed) + 1) & 0x1; - int *fp = &rnp->need_future_gp[idx]; - - RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_future_needs_gp() invoked with irqs enabled!!!"); - return READ_ONCE(*fp); } -/* - * Does the current CPU require a not-yet-started grace period? - * The caller must have disabled interrupts to prevent races with - * normal callback registry. - */ -static bool -cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp) -{ - RCU_LOCKDEP_WARN(!irqs_disabled(), "cpu_needs_another_gp() invoked with irqs enabled!!!"); - if (rcu_gp_in_progress(rsp)) - return false; /* No, a grace period is already in progress. */ - if (rcu_future_needs_gp(rsp)) - return true; /* Yes, a no-CBs CPU needs one. */ - if (!rcu_segcblist_is_enabled(&rdp->cblist)) - return false; /* No, this is a no-CBs (or offline) CPU. */ - if (!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) - return true; /* Yes, CPU has newly registered callbacks. */ - if (rcu_segcblist_future_gp_needed(&rdp->cblist, - READ_ONCE(rsp->completed))) - return true; /* Yes, CBs for future grace period. */ - return false; /* No grace period needed. */ -} +static DEFINE_PER_CPU(struct irq_work, late_wakeup_work) = + IRQ_WORK_INIT(late_wakeup_func); /* - * rcu_eqs_enter_common - current CPU is entering an extended quiescent state + * 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. * - * Enter idle, doing appropriate accounting. The caller must have - * disabled interrupts. + * 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 void rcu_eqs_enter_common(bool user) +noinstr void rcu_irq_work_resched(void) { - struct rcu_state *rsp; - struct rcu_data *rdp; - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); - - RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_eqs_enter_common() invoked with irqs enabled!!!"); - trace_rcu_dyntick(TPS("Start"), rdtp->dynticks_nesting, 0); - if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && - !user && !is_idle_task(current)) { - struct task_struct *idle __maybe_unused = - idle_task(smp_processor_id()); - - trace_rcu_dyntick(TPS("Error on entry: not idle task"), rdtp->dynticks_nesting, 0); - rcu_ftrace_dump(DUMP_ORIG); - WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s", - current->pid, current->comm, - idle->pid, idle->comm); /* must be idle task! */ - } - for_each_rcu_flavor(rsp) { - rdp = this_cpu_ptr(rsp->rda); - do_nocb_deferred_wakeup(rdp); - } - rcu_prepare_for_idle(); - __this_cpu_inc(disable_rcu_irq_enter); - rdtp->dynticks_nesting = 0; /* Breaks tracing momentarily. */ - rcu_dynticks_eqs_enter(); /* After this, tracing works again. */ - __this_cpu_dec(disable_rcu_irq_enter); - rcu_dynticks_task_enter(); + struct rcu_data *rdp = this_cpu_ptr(&rcu_data); - /* - * It is illegal to enter an extended quiescent state while - * in an RCU read-side critical section. - */ - RCU_LOCKDEP_WARN(lock_is_held(&rcu_lock_map), - "Illegal idle entry in RCU read-side critical section."); - RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map), - "Illegal idle entry in RCU-bh read-side critical section."); - RCU_LOCKDEP_WARN(lock_is_held(&rcu_sched_lock_map), - "Illegal idle entry in RCU-sched read-side critical section."); -} + if (IS_ENABLED(CONFIG_GENERIC_ENTRY) && !(current->flags & PF_VCPU)) + return; -/* - * Enter an RCU extended quiescent state, which can be either the - * idle loop or adaptive-tickless usermode execution. - */ -static void rcu_eqs_enter(bool user) -{ - struct rcu_dynticks *rdtp; + if (IS_ENABLED(CONFIG_VIRT_XFER_TO_GUEST_WORK) && (current->flags & PF_VCPU)) + return; - rdtp = this_cpu_ptr(&rcu_dynticks); - WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && - (rdtp->dynticks_nesting & DYNTICK_TASK_NEST_MASK) == 0); - if ((rdtp->dynticks_nesting & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) - rcu_eqs_enter_common(user); - else - rdtp->dynticks_nesting -= DYNTICK_TASK_NEST_VALUE; + instrumentation_begin(); + if (do_nocb_deferred_wakeup(rdp) && need_resched()) { + irq_work_queue(this_cpu_ptr(&late_wakeup_work)); + } + instrumentation_end(); } +#endif /* #if defined(CONFIG_NO_HZ_FULL) && (!defined(CONFIG_GENERIC_ENTRY) || !defined(CONFIG_VIRT_XFER_TO_GUEST_WORK)) */ +#ifdef CONFIG_PROVE_RCU /** - * 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().) - * - * We crowbar the ->dynticks_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. + * rcu_irq_exit_check_preempt - Validate that scheduling is possible */ -void rcu_idle_enter(void) +void rcu_irq_exit_check_preempt(void) { - unsigned long flags; + lockdep_assert_irqs_disabled(); - local_irq_save(flags); - rcu_eqs_enter(false); - local_irq_restore(flags); + RCU_LOCKDEP_WARN(ct_nesting() <= 0, + "RCU nesting counter underflow/zero!"); + RCU_LOCKDEP_WARN(ct_nmi_nesting() != + CT_NESTING_IRQ_NONIDLE, + "Bad RCU nmi_nesting counter\n"); + RCU_LOCKDEP_WARN(!rcu_is_watching_curr_cpu(), + "RCU in extended quiescent state!"); } -EXPORT_SYMBOL_GPL(rcu_idle_enter); +#endif /* #ifdef CONFIG_PROVE_RCU */ #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. - */ -void rcu_user_enter(void) -{ - rcu_eqs_enter(1); -} -#endif /* CONFIG_NO_HZ_FULL */ - -/** - * 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. + * __rcu_irq_enter_check_tick - Enable scheduler tick on CPU if RCU needs it. * - * 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 violates this assumption, RCU will give you what you - * deserve, good and hard. But very infrequently and irreproducibly. + * 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. * - * Use things like work queues to work around this limitation. + * 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. * - * You have been warned. + * 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. */ -void rcu_irq_exit(void) +void __rcu_irq_enter_check_tick(void) { - struct rcu_dynticks *rdtp; + struct rcu_data *rdp = this_cpu_ptr(&rcu_data); - RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_exit() invoked with irqs enabled!!!"); - rdtp = this_cpu_ptr(&rcu_dynticks); - WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && - rdtp->dynticks_nesting < 1); - if (rdtp->dynticks_nesting <= 1) { - rcu_eqs_enter_common(true); - } else { - trace_rcu_dyntick(TPS("--="), rdtp->dynticks_nesting, rdtp->dynticks_nesting - 1); - rdtp->dynticks_nesting--; - } -} - -/* - * Wrapper for rcu_irq_exit() where interrupts are enabled. - */ -void rcu_irq_exit_irqson(void) -{ - unsigned long flags; + // If we're here from NMI there's nothing to do. + if (in_nmi()) + return; - local_irq_save(flags); - rcu_irq_exit(); - local_irq_restore(flags); -} + RCU_LOCKDEP_WARN(!rcu_is_watching_curr_cpu(), + "Illegal rcu_irq_enter_check_tick() from extended quiescent state"); -/* - * rcu_eqs_exit_common - current CPU moving away from extended quiescent state - * - * If the new value of the ->dynticks_nesting counter was previously zero, - * we really have exited idle, and must do the appropriate accounting. - * The caller must have disabled interrupts. - */ -static void rcu_eqs_exit_common(long long oldval, int user) -{ - RCU_TRACE(struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);) - - rcu_dynticks_task_exit(); - rcu_dynticks_eqs_exit(); - rcu_cleanup_after_idle(); - trace_rcu_dyntick(TPS("End"), oldval, rdtp->dynticks_nesting); - if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && - !user && !is_idle_task(current)) { - struct task_struct *idle __maybe_unused = - idle_task(smp_processor_id()); - - trace_rcu_dyntick(TPS("Error on exit: not idle task"), - oldval, rdtp->dynticks_nesting); - rcu_ftrace_dump(DUMP_ORIG); - WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s", - current->pid, current->comm, - idle->pid, idle->comm); /* must be idle task! */ + 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; } -} -/* - * Exit an RCU extended quiescent state, which can be either the - * idle loop or adaptive-tickless usermode execution. - */ -static void rcu_eqs_exit(bool user) -{ - struct rcu_dynticks *rdtp; - long long oldval; - - RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_eqs_exit() invoked with irqs enabled!!!"); - rdtp = this_cpu_ptr(&rcu_dynticks); - oldval = rdtp->dynticks_nesting; - WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && oldval < 0); - if (oldval & DYNTICK_TASK_NEST_MASK) { - rdtp->dynticks_nesting += DYNTICK_TASK_NEST_VALUE; - } else { - rdtp->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; - rcu_eqs_exit_common(oldval, user); + // 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 (READ_ONCE(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); } - -/** - * 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. - * - * We crowbar the ->dynticks_nesting field to DYNTICK_TASK_NEST 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. - */ -void rcu_idle_exit(void) -{ - unsigned long flags; - - local_irq_save(flags); - rcu_eqs_exit(false); - local_irq_restore(flags); -} -EXPORT_SYMBOL_GPL(rcu_idle_exit); - -#ifdef CONFIG_NO_HZ_FULL -/** - * rcu_user_exit - inform RCU that we are exiting userspace. - * - * Exit RCU idle mode while entering the kernel because it can - * run a RCU read side critical section anytime. - */ -void rcu_user_exit(void) -{ - rcu_eqs_exit(1); -} +NOKPROBE_SYMBOL(__rcu_irq_enter_check_tick); #endif /* CONFIG_NO_HZ_FULL */ -/** - * 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 does do upcalls from the idle loop (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. - */ -void rcu_irq_enter(void) -{ - struct rcu_dynticks *rdtp; - long long oldval; - - RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_enter() invoked with irqs enabled!!!"); - rdtp = this_cpu_ptr(&rcu_dynticks); - oldval = rdtp->dynticks_nesting; - rdtp->dynticks_nesting++; - WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && - rdtp->dynticks_nesting == 0); - if (oldval) - trace_rcu_dyntick(TPS("++="), oldval, rdtp->dynticks_nesting); - else - rcu_eqs_exit_common(oldval, true); -} - /* - * Wrapper for rcu_irq_enter() where interrupts are enabled. - */ -void rcu_irq_enter_irqson(void) -{ - unsigned long flags; - - local_irq_save(flags); - rcu_irq_enter(); - local_irq_restore(flags); -} - -/** - * rcu_nmi_enter - inform RCU of entry to NMI context + * 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 the CPU was idle from RCU's viewpoint, update rdtp->dynticks and - * rdtp->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.) + * Just check whether or not this CPU has non-offloaded RCU callbacks + * queued. */ -void rcu_nmi_enter(void) +int rcu_needs_cpu(void) { - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); - int incby = 2; - - /* Complain about underflow. */ - WARN_ON_ONCE(rdtp->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()) { - rcu_dynticks_eqs_exit(); - incby = 1; - } - rdtp->dynticks_nmi_nesting += incby; - barrier(); + return !rcu_segcblist_empty(&this_cpu_ptr(&rcu_data)->cblist) && + !rcu_rdp_is_offloaded(this_cpu_ptr(&rcu_data)); } -/** - * rcu_nmi_exit - inform RCU of exit from NMI context - * - * If we are returning from the outermost NMI handler that interrupted an - * RCU-idle period, update rdtp->dynticks and rdtp->dynticks_nmi_nesting - * to let the RCU grace-period handling know that the CPU is back to - * being RCU-idle. - */ -void rcu_nmi_exit(void) -{ - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); - - /* - * 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(rdtp->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 (rdtp->dynticks_nmi_nesting != 1) { - rdtp->dynticks_nmi_nesting -= 2; - return; +/* + * If any sort of urgency was applied to the current CPU (for example, + * the scheduler-clock interrupt was enabled on a nohz_full CPU) in order + * to get to a quiescent state, disable it. + */ +static void rcu_disable_urgency_upon_qs(struct rcu_data *rdp) +{ + raw_lockdep_assert_held_rcu_node(rdp->mynode); + WRITE_ONCE(rdp->rcu_urgent_qs, false); + 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); + WRITE_ONCE(rdp->rcu_forced_tick, false); } - - /* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */ - rdtp->dynticks_nmi_nesting = 0; - rcu_dynticks_eqs_enter(); } /** - * rcu_is_watching - see if RCU thinks that the current CPU is idle + * rcu_is_watching - RCU read-side critical sections permitted on current CPU? * - * Return true if RCU is watching the running CPU, which means that this - * CPU can safely enter RCU read-side critical sections. In other words, - * if the current CPU is in its idle loop and is neither in an interrupt - * or NMI handler, return true. + * Return @true if RCU is watching the running CPU and @false otherwise. + * An @true return means that this CPU can safely enter RCU read-side + * critical sections. + * + * Although calls to rcu_is_watching() from most parts of the kernel + * will return @true, there are important exceptions. For example, if the + * current CPU is deep within its idle loop, in kernel entry/exit code, + * or offline, rcu_is_watching() will return @false. + * + * 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; preempt_disable_notrace(); - ret = !rcu_dynticks_curr_cpu_in_eqs(); + ret = rcu_is_watching_curr_cpu(); preempt_enable_notrace(); return ret; } @@ -1143,95 +769,93 @@ void rcu_request_urgent_qs_task(struct task_struct *t) cpu = task_cpu(t); if (!task_curr(t)) return; /* This task is not running on that CPU. */ - smp_store_release(per_cpu_ptr(&rcu_dynticks.rcu_urgent_qs, cpu), true); + smp_store_release(per_cpu_ptr(&rcu_data.rcu_urgent_qs, cpu), true); } -#if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) +static unsigned long seq_gpwrap_lag = ULONG_MAX / 4; -/* - * Is the current CPU online? Disable preemption to avoid false positives - * that could otherwise happen due to the current CPU number being sampled, - * this task being preempted, its old CPU being taken offline, resuming - * on some other CPU, then determining that its old CPU is now offline. - * It is OK to use RCU on an offline processor during initial boot, hence - * the check for rcu_scheduler_fully_active. Note also that it is OK - * for a CPU coming online to use RCU for one jiffy prior to marking itself - * online in the cpu_online_mask. Similarly, it is OK for a CPU going - * offline to continue to use RCU for one jiffy after marking itself - * offline in the cpu_online_mask. This leniency is necessary given the - * non-atomic nature of the online and offline processing, for example, - * the fact that a CPU enters the scheduler after completing the teardown - * of the CPU. - * - * This is also why RCU internally marks CPUs online during in the - * preparation phase and offline after the CPU has been taken down. - * - * Disable checking if in an NMI handler because we cannot safely report - * errors from NMI handlers anyway. +/** + * rcu_set_gpwrap_lag - Set RCU GP sequence overflow lag value. + * @lag_gps: Set overflow lag to this many grace period worth of counters + * which is used by rcutorture to quickly force a gpwrap situation. + * @lag_gps = 0 means we reset it back to the boot-time value. */ -bool rcu_lockdep_current_cpu_online(void) +void rcu_set_gpwrap_lag(unsigned long lag_gps) { - struct rcu_data *rdp; - struct rcu_node *rnp; - bool ret; + unsigned long lag_seq_count; - if (in_nmi()) - return true; - preempt_disable(); - rdp = this_cpu_ptr(&rcu_sched_data); - rnp = rdp->mynode; - ret = (rdp->grpmask & rcu_rnp_online_cpus(rnp)) || - !rcu_scheduler_fully_active; - preempt_enable(); - return ret; + lag_seq_count = (lag_gps == 0) + ? ULONG_MAX / 4 + : lag_gps << RCU_SEQ_CTR_SHIFT; + WRITE_ONCE(seq_gpwrap_lag, lag_seq_count); } -EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online); +EXPORT_SYMBOL_GPL(rcu_set_gpwrap_lag); -#endif /* #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) */ - -/** - * rcu_is_cpu_rrupt_from_idle - see if idle or immediately interrupted from idle - * - * If the current CPU is idle or running at a first-level (not nested) - * interrupt from idle, return true. The caller must have at least - * disabled preemption. - */ -static int rcu_is_cpu_rrupt_from_idle(void) -{ - return __this_cpu_read(rcu_dynticks.dynticks_nesting) <= 1; +/* + * 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 + * code whatsoever. + */ +static void rcu_gpnum_ovf(struct rcu_node *rnp, struct rcu_data *rdp) +{ + raw_lockdep_assert_held_rcu_node(rnp); + if (ULONG_CMP_LT(rcu_seq_current(&rdp->gp_seq) + seq_gpwrap_lag, + rnp->gp_seq)) { + WRITE_ONCE(rdp->gpwrap, true); + WRITE_ONCE(rdp->gpwrap_count, READ_ONCE(rdp->gpwrap_count) + 1); + } + if (ULONG_CMP_LT(rdp->rcu_iw_gp_seq + ULONG_MAX / 4, rnp->gp_seq)) + rdp->rcu_iw_gp_seq = rnp->gp_seq + ULONG_MAX / 4; } /* - * Snapshot the specified CPU's dynticks counter so that we can later + * Snapshot the specified CPU's RCU_WATCHING counter so that we can later * credit them with an implicit quiescent state. Return 1 if this CPU * is in dynticks idle mode, which is an extended quiescent state. */ -static int dyntick_save_progress_counter(struct rcu_data *rdp) -{ - rdp->dynticks_snap = rcu_dynticks_snap(rdp->dynticks); - if (rcu_dynticks_in_eqs(rdp->dynticks_snap)) { - trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti")); - if (ULONG_CMP_LT(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4, - rdp->mynode->gpnum)) - WRITE_ONCE(rdp->gpwrap, true); +static int rcu_watching_snap_save(struct rcu_data *rdp) +{ + /* + * Full ordering between remote CPU's post idle accesses and updater's + * accesses prior to current GP (and also the started GP sequence number) + * is enforced by rcu_seq_start() implicit barrier and even further by + * smp_mb__after_unlock_lock() barriers chained all the way throughout the + * rnp locking tree since rcu_gp_init() and up to the current leaf rnp + * locking. + * + * Ordering between remote CPU's pre idle accesses and post grace period + * updater's accesses is enforced by the below acquire semantic. + */ + rdp->watching_snap = ct_rcu_watching_cpu_acquire(rdp->cpu); + if (rcu_watching_snap_in_eqs(rdp->watching_snap)) { + trace_rcu_fqs(rcu_state.name, rdp->gp_seq, rdp->cpu, TPS("dti")); + rcu_gpnum_ovf(rdp->mynode, rdp); return 1; } return 0; } +#ifndef arch_irq_stat_cpu +#define arch_irq_stat_cpu(cpu) 0 +#endif + /* - * Return true if the specified CPU has passed through a quiescent - * state by virtue of being in or having passed through an dynticks - * idle state since the last call to dyntick_save_progress_counter() - * for this same CPU, or by virtue of having been offline. + * Returns positive if the specified CPU has passed through a quiescent state + * by virtue of being in or having passed through an dynticks idle state since + * the last call to rcu_watching_snap_save() for this same CPU, or by + * virtue of having been offline. + * + * Returns negative if the specified CPU needs a force resched. + * + * Returns zero otherwise. */ -static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) +static int rcu_watching_snap_recheck(struct rcu_data *rdp) { unsigned long jtsq; - bool *rnhqp; - bool *ruqp; - unsigned long rjtsc; - struct rcu_node *rnp; + int ret = 0; + struct rcu_node *rnp = rdp->mynode; /* * If the CPU passed through or entered a dynticks idle phase with @@ -1241,527 +865,221 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) * read-side critical section that started before the beginning * of the current RCU grace period. */ - if (rcu_dynticks_in_eqs_since(rdp->dynticks, rdp->dynticks_snap)) { - trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti")); - rdp->dynticks_fqs++; + if (rcu_watching_snap_stopped_since(rdp, rdp->watching_snap)) { + trace_rcu_fqs(rcu_state.name, rdp->gp_seq, rdp->cpu, TPS("dti")); + rcu_gpnum_ovf(rnp, rdp); return 1; } - /* Compute and saturate jiffies_till_sched_qs. */ - jtsq = jiffies_till_sched_qs; - rjtsc = rcu_jiffies_till_stall_check(); - if (jtsq > rjtsc / 2) { - WRITE_ONCE(jiffies_till_sched_qs, rjtsc); - jtsq = rjtsc / 2; - } else if (jtsq < 1) { - WRITE_ONCE(jiffies_till_sched_qs, 1); - jtsq = 1; - } - /* - * Has this CPU encountered a cond_resched_rcu_qs() since the - * beginning of the grace period? For this to be the case, - * the CPU has to have noticed the current grace period. This - * might not be the case for nohz_full CPUs looping in the kernel. + * 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. */ - rnp = rdp->mynode; - ruqp = per_cpu_ptr(&rcu_dynticks.rcu_urgent_qs, rdp->cpu); - if (time_after(jiffies, rdp->rsp->gp_start + jtsq) && - READ_ONCE(rdp->rcu_qs_ctr_snap) != per_cpu(rcu_dynticks.rcu_qs_ctr, rdp->cpu) && - READ_ONCE(rdp->gpnum) == rnp->gpnum && !rdp->gpwrap) { - trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("rqc")); - return 1; - } else { - /* Load rcu_qs_ctr before store to rcu_urgent_qs. */ - smp_store_release(ruqp, true); - } - - /* Check for the CPU being offline. */ - if (!(rdp->grpmask & rcu_rnp_online_cpus(rnp))) { - trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("ofl")); - rdp->offline_fqs++; - return 1; + if (WARN_ON_ONCE(!rcu_rdp_cpu_online(rdp))) { + struct rcu_node *rnp1; + + 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); + pr_info("%s %d: %c online: %ld(%d) offline: %ld(%d)\n", + __func__, rdp->cpu, ".o"[rcu_rdp_cpu_online(rdp)], + (long)rdp->rcu_onl_gp_seq, rdp->rcu_onl_gp_state, + (long)rdp->rcu_ofl_gp_seq, rdp->rcu_ofl_gp_state); + return 1; /* Break things loose after complaining. */ } /* * A CPU running for an extended time within the kernel can - * delay RCU grace periods. When the CPU is in NO_HZ_FULL mode, - * even context-switching back and forth between a pair of - * in-kernel CPU-bound tasks cannot advance grace periods. - * So if the grace period is old enough, make the CPU pay attention. - * Note that the unsynchronized assignments to the per-CPU - * rcu_need_heavy_qs variable are safe. Yes, setting of - * bits can be lost, but they will be set again on the next - * force-quiescent-state pass. So lost bit sets do not result - * in incorrect behavior, merely in a grace period lasting - * a few jiffies longer than it might otherwise. Because - * there are at most four threads involved, and because the - * updates are only once every few jiffies, the probability of - * lossage (and thus of slight grace-period extension) is - * quite low. - * - * Note that if the jiffies_till_sched_qs boot/sysfs parameter - * is set too high, we override with half of the RCU CPU stall - * warning delay. + * delay RCU grace periods: (1) At age jiffies_to_sched_qs, + * set .rcu_urgent_qs, (2) At age 2*jiffies_to_sched_qs, set + * both .rcu_need_heavy_qs and .rcu_urgent_qs. Note that the + * unsynchronized assignments to the per-CPU rcu_need_heavy_qs + * variable are safe because the assignments are repeated if this + * CPU failed to pass through a quiescent state. This code + * also checks .jiffies_resched in case jiffies_to_sched_qs + * is set way high. */ - rnhqp = &per_cpu(rcu_dynticks.rcu_need_heavy_qs, rdp->cpu); - if (!READ_ONCE(*rnhqp) && - (time_after(jiffies, rdp->rsp->gp_start + jtsq) || - time_after(jiffies, rdp->rsp->jiffies_resched))) { - WRITE_ONCE(*rnhqp, true); + jtsq = READ_ONCE(jiffies_to_sched_qs); + if (!READ_ONCE(rdp->rcu_need_heavy_qs) && + (time_after(jiffies, rcu_state.gp_start + jtsq * 2) || + 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); - rdp->rsp->jiffies_resched += 5; /* Re-enable beating. */ + smp_store_release(&rdp->rcu_urgent_qs, true); + } else if (time_after(jiffies, rcu_state.gp_start + jtsq)) { + WRITE_ONCE(rdp->rcu_urgent_qs, true); } /* - * If more than halfway to RCU CPU stall-warning time, do - * a resched_cpu() to try to loosen things up a bit. + * NO_HZ_FULL CPUs can run in-kernel without rcu_sched_clock_irq! + * The above code handles this, but only for straight cond_resched(). + * And some in-kernel loops check need_resched() before calling + * cond_resched(), which defeats the above code for CPUs that are + * running in-kernel with scheduling-clock interrupts disabled. + * So hit them over the head with the resched_cpu() hammer! */ - if (jiffies - rdp->rsp->gp_start > rcu_jiffies_till_stall_check() / 2) - resched_cpu(rdp->cpu); - - return 0; -} - -static void record_gp_stall_check_time(struct rcu_state *rsp) -{ - unsigned long j = jiffies; - unsigned long j1; - - rsp->gp_start = j; - smp_wmb(); /* Record start time before stall time. */ - j1 = rcu_jiffies_till_stall_check(); - WRITE_ONCE(rsp->jiffies_stall, j + j1); - rsp->jiffies_resched = j + j1 / 2; - rsp->n_force_qs_gpstart = READ_ONCE(rsp->n_force_qs); -} - -/* - * Convert a ->gp_state value to a character string. - */ -static const char *gp_state_getname(short gs) -{ - if (gs < 0 || gs >= ARRAY_SIZE(gp_state_names)) - return "???"; - return gp_state_names[gs]; -} - -/* - * Complain about starvation of grace-period kthread. - */ -static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp) -{ - unsigned long gpa; - unsigned long j; - - j = jiffies; - gpa = READ_ONCE(rsp->gp_activity); - if (j - gpa > 2 * HZ) { - pr_err("%s kthread starved for %ld jiffies! g%lu c%lu f%#x %s(%d) ->state=%#lx\n", - rsp->name, j - gpa, - rsp->gpnum, rsp->completed, - rsp->gp_flags, - gp_state_getname(rsp->gp_state), rsp->gp_state, - rsp->gp_kthread ? rsp->gp_kthread->state : ~0); - if (rsp->gp_kthread) { - sched_show_task(rsp->gp_kthread); - wake_up_process(rsp->gp_kthread); - } - } -} - -/* - * Dump stacks of all tasks running on stalled CPUs. First try using - * NMIs, but fall back to manual remote stack tracing on architectures - * that don't support NMI-based stack dumps. The NMI-triggered stack - * traces are more accurate because they are printed by the target CPU. - */ -static void rcu_dump_cpu_stacks(struct rcu_state *rsp) -{ - int cpu; - unsigned long flags; - struct rcu_node *rnp; - - rcu_for_each_leaf_node(rsp, rnp) { - raw_spin_lock_irqsave_rcu_node(rnp, flags); - for_each_leaf_node_possible_cpu(rnp, cpu) - if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) - if (!trigger_single_cpu_backtrace(cpu)) - dump_cpu_task(cpu); - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + if (tick_nohz_full_cpu(rdp->cpu) && + (time_after(jiffies, READ_ONCE(rdp->last_fqs_resched) + jtsq * 3) || + rcu_state.cbovld)) { + WRITE_ONCE(rdp->rcu_urgent_qs, true); + WRITE_ONCE(rdp->last_fqs_resched, jiffies); + ret = -1; } -} - -/* - * If too much time has passed in the current grace period, and if - * so configured, go kick the relevant kthreads. - */ -static void rcu_stall_kick_kthreads(struct rcu_state *rsp) -{ - unsigned long j; - - if (!rcu_kick_kthreads) - return; - j = READ_ONCE(rsp->jiffies_kick_kthreads); - if (time_after(jiffies, j) && rsp->gp_kthread && - (rcu_gp_in_progress(rsp) || READ_ONCE(rsp->gp_flags))) { - WARN_ONCE(1, "Kicking %s grace-period kthread\n", rsp->name); - rcu_ftrace_dump(DUMP_ALL); - wake_up_process(rsp->gp_kthread); - WRITE_ONCE(rsp->jiffies_kick_kthreads, j + HZ); - } -} - -static inline void panic_on_rcu_stall(void) -{ - if (sysctl_panic_on_rcu_stall) - panic("RCU Stall\n"); -} - -static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum) -{ - int cpu; - long delta; - unsigned long flags; - unsigned long gpa; - unsigned long j; - int ndetected = 0; - struct rcu_node *rnp = rcu_get_root(rsp); - long totqlen = 0; - - /* Kick and suppress, if so configured. */ - rcu_stall_kick_kthreads(rsp); - if (rcu_cpu_stall_suppress) - return; - - /* Only let one CPU complain about others per time interval. */ - - raw_spin_lock_irqsave_rcu_node(rnp, flags); - delta = jiffies - READ_ONCE(rsp->jiffies_stall); - if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) { - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - return; - } - WRITE_ONCE(rsp->jiffies_stall, - jiffies + 3 * rcu_jiffies_till_stall_check() + 3); - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); /* - * OK, time to rat on our buddy... - * See Documentation/RCU/stallwarn.txt for info on how to debug - * RCU CPU stall warnings. + * If more than halfway to RCU CPU stall-warning time, invoke + * resched_cpu() more frequently to try to loosen things up a bit. + * Also check to see if the CPU is getting hammered with interrupts, + * but only once per grace period, just to keep the IPIs down to + * a dull roar. */ - pr_err("INFO: %s detected stalls on CPUs/tasks:", - rsp->name); - print_cpu_stall_info_begin(); - rcu_for_each_leaf_node(rsp, rnp) { - raw_spin_lock_irqsave_rcu_node(rnp, flags); - ndetected += rcu_print_task_stall(rnp); - if (rnp->qsmask != 0) { - for_each_leaf_node_possible_cpu(rnp, cpu) - if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) { - print_cpu_stall_info(rsp, cpu); - ndetected++; - } + if (time_after(jiffies, rcu_state.jiffies_resched)) { + if (time_after(jiffies, + READ_ONCE(rdp->last_fqs_resched) + jtsq)) { + WRITE_ONCE(rdp->last_fqs_resched, jiffies); + ret = -1; } - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - } - - print_cpu_stall_info_end(); - for_each_possible_cpu(cpu) - totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(rsp->rda, - cpu)->cblist); - pr_cont("(detected by %d, t=%ld jiffies, g=%ld, c=%ld, q=%lu)\n", - smp_processor_id(), (long)(jiffies - rsp->gp_start), - (long)rsp->gpnum, (long)rsp->completed, totqlen); - if (ndetected) { - rcu_dump_cpu_stacks(rsp); - - /* Complain about tasks blocking the grace period. */ - rcu_print_detail_task_stall(rsp); - } else { - if (READ_ONCE(rsp->gpnum) != gpnum || - READ_ONCE(rsp->completed) == gpnum) { - pr_err("INFO: Stall ended before state dump start\n"); - } else { - j = jiffies; - gpa = READ_ONCE(rsp->gp_activity); - pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld, root ->qsmask %#lx\n", - rsp->name, j - gpa, j, gpa, - jiffies_till_next_fqs, - rcu_get_root(rsp)->qsmask); - /* In this case, the current CPU might be at fault. */ - sched_show_task(current); + if (IS_ENABLED(CONFIG_IRQ_WORK) && + !rdp->rcu_iw_pending && rdp->rcu_iw_gp_seq != rnp->gp_seq && + (rnp->ffmask & rdp->grpmask)) { + rdp->rcu_iw_pending = true; + rdp->rcu_iw_gp_seq = rnp->gp_seq; + irq_work_queue_on(&rdp->rcu_iw, rdp->cpu); } - } - - rcu_check_gp_kthread_starvation(rsp); - - panic_on_rcu_stall(); - - force_quiescent_state(rsp); /* Kick them all. */ -} - -static void print_cpu_stall(struct rcu_state *rsp) -{ - int cpu; - unsigned long flags; - struct rcu_node *rnp = rcu_get_root(rsp); - long totqlen = 0; - - /* Kick and suppress, if so configured. */ - rcu_stall_kick_kthreads(rsp); - if (rcu_cpu_stall_suppress) - return; - - /* - * OK, time to rat on ourselves... - * See Documentation/RCU/stallwarn.txt for info on how to debug - * RCU CPU stall warnings. - */ - pr_err("INFO: %s self-detected stall on CPU", rsp->name); - print_cpu_stall_info_begin(); - print_cpu_stall_info(rsp, smp_processor_id()); - print_cpu_stall_info_end(); - for_each_possible_cpu(cpu) - totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(rsp->rda, - cpu)->cblist); - pr_cont(" (t=%lu jiffies g=%ld c=%ld q=%lu)\n", - jiffies - rsp->gp_start, - (long)rsp->gpnum, (long)rsp->completed, totqlen); - - rcu_check_gp_kthread_starvation(rsp); - - rcu_dump_cpu_stacks(rsp); - - raw_spin_lock_irqsave_rcu_node(rnp, flags); - if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall))) - WRITE_ONCE(rsp->jiffies_stall, - jiffies + 3 * rcu_jiffies_till_stall_check() + 3); - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - - panic_on_rcu_stall(); - /* - * Attempt to revive the RCU machinery by forcing a context switch. - * - * A context switch would normally allow the RCU state machine to make - * progress and it could be we're stuck in kernel space without context - * switches for an entirely unreasonable amount of time. - */ - resched_cpu(smp_processor_id()); -} - -static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp) -{ - unsigned long completed; - unsigned long gpnum; - unsigned long gps; - unsigned long j; - unsigned long js; - struct rcu_node *rnp; - - if ((rcu_cpu_stall_suppress && !rcu_kick_kthreads) || - !rcu_gp_in_progress(rsp)) - return; - rcu_stall_kick_kthreads(rsp); - j = jiffies; - - /* - * Lots of memory barriers to reject false positives. - * - * The idea is to pick up rsp->gpnum, then rsp->jiffies_stall, - * then rsp->gp_start, and finally rsp->completed. These values - * are updated in the opposite order with memory barriers (or - * equivalent) during grace-period initialization and cleanup. - * Now, a false positive can occur if we get an new value of - * rsp->gp_start and a old value of rsp->jiffies_stall. But given - * the memory barriers, the only way that this can happen is if one - * grace period ends and another starts between these two fetches. - * Detect this by comparing rsp->completed with the previous fetch - * from rsp->gpnum. - * - * Given this check, comparisons of jiffies, rsp->jiffies_stall, - * and rsp->gp_start suffice to forestall false positives. - */ - gpnum = READ_ONCE(rsp->gpnum); - smp_rmb(); /* Pick up ->gpnum first... */ - js = READ_ONCE(rsp->jiffies_stall); - smp_rmb(); /* ...then ->jiffies_stall before the rest... */ - gps = READ_ONCE(rsp->gp_start); - smp_rmb(); /* ...and finally ->gp_start before ->completed. */ - completed = READ_ONCE(rsp->completed); - if (ULONG_CMP_GE(completed, gpnum) || - ULONG_CMP_LT(j, js) || - ULONG_CMP_GE(gps, js)) - return; /* No stall or GP completed since entering function. */ - rnp = rdp->mynode; - if (rcu_gp_in_progress(rsp) && - (READ_ONCE(rnp->qsmask) & rdp->grpmask)) { - - /* We haven't checked in, so go dump stack. */ - print_cpu_stall(rsp); - - } else if (rcu_gp_in_progress(rsp) && - ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY)) { - - /* They had a few time units to dump stack, so complain. */ - print_other_cpu_stall(rsp, gpnum); + if (rcu_cpu_stall_cputime && rdp->snap_record.gp_seq != rdp->gp_seq) { + int cpu = rdp->cpu; + struct rcu_snap_record *rsrp; + struct kernel_cpustat *kcsp; + + kcsp = &kcpustat_cpu(cpu); + + rsrp = &rdp->snap_record; + rsrp->cputime_irq = kcpustat_field(kcsp, CPUTIME_IRQ, cpu); + rsrp->cputime_softirq = kcpustat_field(kcsp, CPUTIME_SOFTIRQ, cpu); + rsrp->cputime_system = kcpustat_field(kcsp, CPUTIME_SYSTEM, cpu); + rsrp->nr_hardirqs = kstat_cpu_irqs_sum(cpu) + arch_irq_stat_cpu(cpu); + rsrp->nr_softirqs = kstat_cpu_softirqs_sum(cpu); + rsrp->nr_csw = nr_context_switches_cpu(cpu); + rsrp->jiffies = jiffies; + rsrp->gp_seq = rdp->gp_seq; + } } -} - -/** - * rcu_cpu_stall_reset - prevent further stall warnings in current grace period - * - * Set the stall-warning timeout way off into the future, thus preventing - * any RCU CPU stall-warning messages from appearing in the current set of - * RCU grace periods. - * - * The caller must disable hard irqs. - */ -void rcu_cpu_stall_reset(void) -{ - struct rcu_state *rsp; - for_each_rcu_flavor(rsp) - WRITE_ONCE(rsp->jiffies_stall, jiffies + ULONG_MAX / 2); -} - -/* - * Determine the value that ->completed will have at the end of the - * next subsequent grace period. This is used to tag callbacks so that - * a CPU can invoke callbacks in a timely fashion even if that CPU has - * been dyntick-idle for an extended period with callbacks under the - * influence of RCU_FAST_NO_HZ. - * - * The caller must hold rnp->lock with interrupts disabled. - */ -static unsigned long rcu_cbs_completed(struct rcu_state *rsp, - struct rcu_node *rnp) -{ - lockdep_assert_held(&rnp->lock); - - /* - * If RCU is idle, we just wait for the next grace period. - * But we can only be sure that RCU is idle if we are looking - * at the root rcu_node structure -- otherwise, a new grace - * period might have started, but just not yet gotten around - * to initializing the current non-root rcu_node structure. - */ - if (rcu_get_root(rsp) == rnp && rnp->gpnum == rnp->completed) - return rnp->completed + 1; - - /* - * Otherwise, wait for a possible partial grace period and - * then the subsequent full grace period. - */ - return rnp->completed + 2; + return ret; } -/* - * Trace-event helper function for rcu_start_future_gp() and - * rcu_nocb_wait_gp(). - */ -static void trace_rcu_future_gp(struct rcu_node *rnp, struct rcu_data *rdp, - unsigned long c, const char *s) +/* Trace-event wrapper function for trace_rcu_future_grace_period. */ +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(rdp->rsp->name, rnp->gpnum, - rnp->completed, c, rnp->level, + trace_rcu_future_grace_period(rcu_state.name, READ_ONCE(rnp->gp_seq), + gp_seq_req, rnp->level, rnp->grplo, rnp->grphi, s); } /* - * Start some future grace period, as needed to handle newly arrived + * rcu_start_this_gp - Request the start of a particular grace period + * @rnp_start: The leaf node of the CPU from which to start. + * @rdp: The rcu_data corresponding to the CPU from which to start. + * @gp_seq_req: The gp_seq of the grace period to start. + * + * Start the specified grace period, as needed to handle newly arrived * callbacks. The required future grace periods are recorded in each - * rcu_node structure's ->need_future_gp field. Returns true if there + * rcu_node structure's ->gp_seq_needed field. Returns true if there * is reason to awaken the grace-period kthread. * - * The caller must hold the specified rcu_node structure's ->lock. + * The caller must hold the specified rcu_node structure's ->lock, which + * is why the caller is responsible for waking the grace-period kthread. + * + * Returns true if the GP thread needs to be awakened else false. */ -static bool __maybe_unused -rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp, - unsigned long *c_out) +static bool rcu_start_this_gp(struct rcu_node *rnp_start, struct rcu_data *rdp, + unsigned long gp_seq_req) { - unsigned long c; bool ret = false; - struct rcu_node *rnp_root = rcu_get_root(rdp->rsp); - - lockdep_assert_held(&rnp->lock); - - /* - * Pick up grace-period number for new callbacks. If this - * grace period is already marked as needed, return to the caller. - */ - c = rcu_cbs_completed(rdp->rsp, rnp); - trace_rcu_future_gp(rnp, rdp, c, TPS("Startleaf")); - if (rnp->need_future_gp[c & 0x1]) { - trace_rcu_future_gp(rnp, rdp, c, TPS("Prestartleaf")); - goto out; - } + struct rcu_node *rnp; /* - * If either this rcu_node structure or the root rcu_node structure - * believe that a grace period is in progress, then we must wait - * for the one following, which is in "c". Because our request - * will be noticed at the end of the current grace period, we don't - * need to explicitly start one. We only do the lockless check - * of rnp_root's fields if the current rcu_node structure thinks - * there is no grace period in flight, and because we hold rnp->lock, - * the only possible change is when rnp_root's two fields are - * equal, in which case rnp_root->gpnum might be concurrently - * incremented. But that is OK, as it will just result in our - * doing some extra useless work. + * Use funnel locking to either acquire the root rcu_node + * structure's lock or bail out if the need for this grace period + * has already been recorded -- or if that grace period has in + * fact already started. If there is already a grace period in + * progress in a non-leaf node, no recording is needed because the + * end of the grace period will scan the leaf rcu_node structures. + * Note that rnp_start->lock must not be released. */ - if (rnp->gpnum != rnp->completed || - READ_ONCE(rnp_root->gpnum) != READ_ONCE(rnp_root->completed)) { - rnp->need_future_gp[c & 0x1]++; - trace_rcu_future_gp(rnp, rdp, c, TPS("Startedleaf")); - goto out; + raw_lockdep_assert_held_rcu_node(rnp_start); + trace_rcu_this_gp(rnp_start, rdp, gp_seq_req, TPS("Startleaf")); + for (rnp = rnp_start; 1; rnp = rnp->parent) { + if (rnp != rnp_start) + raw_spin_lock_rcu_node(rnp); + if (ULONG_CMP_GE(rnp->gp_seq_needed, gp_seq_req) || + rcu_seq_started(&rnp->gp_seq, gp_seq_req) || + (rnp != rnp_start && + rcu_seq_state(rcu_seq_current(&rnp->gp_seq)))) { + trace_rcu_this_gp(rnp, rdp, gp_seq_req, + TPS("Prestarted")); + goto unlock_out; + } + 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 + * grace period is in progress, which means that + * rcu_gp_cleanup() will see the marking. Bail to + * reduce contention. + */ + trace_rcu_this_gp(rnp_start, rdp, gp_seq_req, + TPS("Startedleaf")); + goto unlock_out; + } + if (rnp != rnp_start && rnp->parent != NULL) + raw_spin_unlock_rcu_node(rnp); + if (!rnp->parent) + break; /* At root, and perhaps also leaf. */ } - /* - * There might be no grace period in progress. If we don't already - * hold it, acquire the root rcu_node structure's lock in order to - * start one (if needed). - */ - if (rnp != rnp_root) - raw_spin_lock_rcu_node(rnp_root); - - /* - * Get a new grace-period number. If there really is no grace - * period in progress, it will be smaller than the one we obtained - * earlier. Adjust callbacks as needed. - */ - c = rcu_cbs_completed(rdp->rsp, rnp_root); - if (!rcu_is_nocb_cpu(rdp->cpu)) - (void)rcu_segcblist_accelerate(&rdp->cblist, c); - - /* - * If the needed for the required grace period is already - * recorded, trace and leave. - */ - if (rnp_root->need_future_gp[c & 0x1]) { - trace_rcu_future_gp(rnp, rdp, c, TPS("Prestartedroot")); + /* If GP already in progress, just leave, otherwise start one. */ + if (rcu_gp_in_progress()) { + trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startedleafroot")); goto unlock_out; } - - /* Record the need for the future grace period. */ - rnp_root->need_future_gp[c & 0x1]++; - - /* If a grace period is not already in progress, start one. */ - if (rnp_root->gpnum != rnp_root->completed) { - trace_rcu_future_gp(rnp, rdp, c, TPS("Startedleafroot")); - } else { - trace_rcu_future_gp(rnp, rdp, c, TPS("Startedroot")); - ret = rcu_start_gp_advanced(rdp->rsp, rnp_root, 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); + 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, data_race(rcu_state.gp_seq), TPS("newreq")); + ret = true; /* Caller must wake GP kthread. */ unlock_out: - if (rnp != rnp_root) - raw_spin_unlock_rcu_node(rnp_root); -out: - if (c_out != NULL) - *c_out = c; + /* Push furthest requested GP to leaf node and rcu_data structure. */ + if (ULONG_CMP_LT(gp_seq_req, 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); return ret; } @@ -1769,58 +1087,72 @@ out: * Clean up any old requests for the just-ended grace period. Also return * whether any additional grace periods have been requested. */ -static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) +static bool rcu_future_gp_cleanup(struct rcu_node *rnp) { - int c = rnp->completed; - int needmore; - struct rcu_data *rdp = this_cpu_ptr(rsp->rda); + bool needmore; + struct rcu_data *rdp = this_cpu_ptr(&rcu_data); - rnp->need_future_gp[c & 0x1] = 0; - needmore = rnp->need_future_gp[(c + 1) & 0x1]; - trace_rcu_future_gp(rnp, rdp, c, - needmore ? TPS("CleanupMore") : TPS("Cleanup")); + needmore = ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed); + if (!needmore) + rnp->gp_seq_needed = rnp->gp_seq; /* Avoid counter wrap. */ + trace_rcu_this_gp(rnp, rdp, rnp->gp_seq, + needmore ? TPS("CleanupMore") : TPS("Cleanup")); return needmore; } /* - * Awaken the grace-period kthread for the specified flavor of RCU. - * Don't do a self-awaken, 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. + * 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 + * been interrupted just as it was going to sleep, and just after the final + * pre-sleep check of the awaken condition. In this case, a wakeup really + * is required, and is therefore supplied. */ -static void rcu_gp_kthread_wake(struct rcu_state *rsp) +static void rcu_gp_kthread_wake(void) { - if (current == rsp->gp_kthread || - !READ_ONCE(rsp->gp_flags) || - !rsp->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; - swake_up(&rsp->gp_wq); + WRITE_ONCE(rcu_state.gp_wake_time, jiffies); + WRITE_ONCE(rcu_state.gp_wake_seq, READ_ONCE(rcu_state.gp_seq)); + swake_up_one(&rcu_state.gp_wq); } /* - * If there is room, assign a ->completed number to any callbacks on - * this CPU that have not already been assigned. Also accelerate any - * callbacks that were previously assigned a ->completed number that has - * since proven to be too conservative, which can happen if callbacks get - * assigned a ->completed number while RCU is idle, but with reference to - * a non-root rcu_node structure. This function is idempotent, so it does - * not hurt to call it repeatedly. Returns an flag saying that we should - * awaken the RCU grace-period kthread. + * If there is room, assign a ->gp_seq number to any callbacks on this + * CPU that have not already been assigned. Also accelerate any callbacks + * that were previously assigned a ->gp_seq number that has since proven + * to be too conservative, which can happen if callbacks get assigned a + * ->gp_seq number while RCU is idle, but with reference to a non-root + * rcu_node structure. This function is idempotent, so it does not hurt + * to call it repeatedly. Returns an flag saying that we should awaken + * the RCU grace-period kthread. * * The caller must hold rnp->lock with interrupts disabled. */ -static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, - struct rcu_data *rdp) +static bool rcu_accelerate_cbs(struct rcu_node *rnp, struct rcu_data *rdp) { + unsigned long gp_seq_req; bool ret = false; - lockdep_assert_held(&rnp->lock); + rcu_lockdep_assert_cblist_protected(rdp); + raw_lockdep_assert_held_rcu_node(rnp); /* If no pending (not yet ready to invoke) callbacks, nothing to do. */ 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 @@ -1831,44 +1163,104 @@ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, * accelerating callback invocation to an earlier grace-period * number. */ - if (rcu_segcblist_accelerate(&rdp->cblist, rcu_cbs_completed(rsp, rnp))) - ret = rcu_start_future_gp(rnp, rdp, NULL); + gp_seq_req = rcu_seq_snap(&rcu_state.gp_seq); + if (rcu_segcblist_accelerate(&rdp->cblist, gp_seq_req)) + ret = rcu_start_this_gp(rnp, rdp, gp_seq_req); /* Trace depending on how much we were able to accelerate. */ if (rcu_segcblist_restempty(&rdp->cblist, RCU_WAIT_TAIL)) - trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccWaitCB")); + trace_rcu_grace_period(rcu_state.name, gp_seq_req, TPS("AccWaitCB")); else - trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccReadyCB")); + trace_rcu_grace_period(rcu_state.name, gp_seq_req, TPS("AccReadyCB")); + + trace_rcu_segcb_stats(&rdp->cblist, TPS("SegCbPostAcc")); + return ret; } /* + * Similar to rcu_accelerate_cbs(), but does not require that the leaf + * rcu_node structure's ->lock be held. It consults the cached value + * of ->gp_seq_needed in the rcu_data structure, and if that indicates + * that a new grace-period request be made, invokes rcu_accelerate_cbs() + * while holding the leaf rcu_node structure's ->lock. + */ +static void rcu_accelerate_cbs_unlocked(struct rcu_node *rnp, + struct rcu_data *rdp) +{ + unsigned long c; + bool needwake; + + rcu_lockdep_assert_cblist_protected(rdp); + c = rcu_seq_snap(&rcu_state.gp_seq); + 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; + } + raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ + needwake = rcu_accelerate_cbs(rnp, rdp); + raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ + if (needwake) + rcu_gp_kthread_wake(); +} + +/* * Move any callbacks whose grace period has completed to the * RCU_DONE_TAIL sublist, then compact the remaining sublists and - * assign ->completed numbers to any callbacks in the RCU_NEXT_TAIL + * assign ->gp_seq numbers to any callbacks in the RCU_NEXT_TAIL * sublist. This function is idempotent, so it does not hurt to * invoke it repeatedly. As long as it is not invoked -too- often... * Returns true if the RCU grace-period kthread needs to be awakened. * * The caller must hold rnp->lock with interrupts disabled. */ -static bool rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp, - struct rcu_data *rdp) +static bool rcu_advance_cbs(struct rcu_node *rnp, struct rcu_data *rdp) { - lockdep_assert_held(&rnp->lock); + rcu_lockdep_assert_cblist_protected(rdp); + raw_lockdep_assert_held_rcu_node(rnp); /* If no pending (not yet ready to invoke) callbacks, nothing to do. */ if (!rcu_segcblist_pend_cbs(&rdp->cblist)) return false; /* - * Find all callbacks whose ->completed numbers indicate that they + * Find all callbacks whose ->gp_seq numbers indicate that they * are ready to invoke, and put them into the RCU_DONE_TAIL sublist. */ - rcu_segcblist_advance(&rdp->cblist, rnp->completed); + rcu_segcblist_advance(&rdp->cblist, rnp->gp_seq); /* Classify any remaining callbacks. */ - return rcu_accelerate_cbs(rsp, rnp, rdp); + return rcu_accelerate_cbs(rnp, rdp); +} + +/* + * Move and classify callbacks, but only if doing so won't require + * that the RCU grace-period kthread be awakened. + */ +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)) + return; + // 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(); + } } /* @@ -1877,50 +1269,56 @@ static bool rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp, * structure corresponding to the current CPU, and must have irqs disabled. * Returns true if the grace-period kthread needs to be awakened. */ -static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, - struct rcu_data *rdp) +static bool __note_gp_changes(struct rcu_node *rnp, struct rcu_data *rdp) { - bool ret; - bool need_gp; + bool ret = false; + bool need_qs; + const bool offloaded = rcu_rdp_is_offloaded(rdp); - lockdep_assert_held(&rnp->lock); + raw_lockdep_assert_held_rcu_node(rnp); - /* Handle the ends of any preceding grace periods first. */ - if (rdp->completed == rnp->completed && - !unlikely(READ_ONCE(rdp->gpwrap))) { - - /* No grace period end, so just accelerate recent callbacks. */ - ret = rcu_accelerate_cbs(rsp, rnp, rdp); + if (rdp->gp_seq == rnp->gp_seq) + return false; /* Nothing to do. */ + /* Handle the ends of any preceding grace periods first. */ + if (rcu_seq_completed_gp(rdp->gp_seq, rnp->gp_seq) || + unlikely(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 { - - /* Advance callbacks. */ - ret = rcu_advance_cbs(rsp, rnp, rdp); - - /* Remember that we saw this grace-period completion. */ - rdp->completed = rnp->completed; - trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuend")); + if (!offloaded) + ret = rcu_accelerate_cbs(rnp, rdp); /* Recent CBs. */ + if (rdp->core_needs_qs) + rdp->core_needs_qs = !!(rnp->qsmask & rdp->grpmask); } - if (rdp->gpnum != rnp->gpnum || unlikely(READ_ONCE(rdp->gpwrap))) { + /* Now handle the beginnings of any new-to-this-CPU grace periods. */ + if (rcu_seq_new_gp(rdp->gp_seq, rnp->gp_seq) || + unlikely(rdp->gpwrap)) { /* * If the current grace period is waiting for this CPU, * set up to detect a quiescent state, otherwise don't * go looking for one. */ - rdp->gpnum = rnp->gpnum; - trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpustart")); - need_gp = !!(rnp->qsmask & rdp->grpmask); - rdp->cpu_no_qs.b.norm = need_gp; - rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_dynticks.rcu_qs_ctr); - rdp->core_needs_qs = need_gp; + trace_rcu_grace_period(rcu_state.name, rnp->gp_seq, TPS("cpustart")); + 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); - WRITE_ONCE(rdp->gpwrap, false); } + 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) + WRITE_ONCE(rdp->gp_seq_needed, rnp->gp_seq_needed); + if (IS_ENABLED(CONFIG_PROVE_RCU) && rdp->gpwrap) + WRITE_ONCE(rdp->last_sched_clock, jiffies); + WRITE_ONCE(rdp->gpwrap, false); + rcu_gpnum_ovf(rnp, rdp); return ret; } -static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp) +static void note_gp_changes(struct rcu_data *rdp) { unsigned long flags; bool needwake; @@ -1928,45 +1326,500 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp) local_irq_save(flags); rnp = rdp->mynode; - if ((rdp->gpnum == READ_ONCE(rnp->gpnum) && - rdp->completed == READ_ONCE(rnp->completed) && + if ((rdp->gp_seq == rcu_seq_current(&rnp->gp_seq) && !unlikely(READ_ONCE(rdp->gpwrap))) || /* w/out lock. */ !raw_spin_trylock_rcu_node(rnp)) { /* irqs already off, so later. */ local_irq_restore(flags); return; } - needwake = __note_gp_changes(rsp, rnp, 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(rsp); + rcu_gp_kthread_wake(); } -static void rcu_gp_slow(struct rcu_state *rsp, int delay) +static atomic_t *rcu_gp_slow_suppress; + +/* Register a counter to suppress debugging grace-period delays. */ +void rcu_gp_slow_register(atomic_t *rgssp) { - if (delay > 0 && - !(rsp->gpnum % (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay))) - schedule_timeout_uninterruptible(delay); + 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 && rcu_gp_slow_suppress != NULL); + + 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 (!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(); +} + +// 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_scheduler_active != RCU_SCHEDULER_INACTIVE) + 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_scheduler_active != RCU_SCHEDULER_INACTIVE) + 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()) { + if (rcu_scheduler_active != RCU_SCHEDULER_INACTIVE) + 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()) { + if (rcu_scheduler_active != RCU_SCHEDULER_INACTIVE) + 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); +} + +/* + * There is a single llist, which is used for handling + * synchronize_rcu() users' enqueued rcu_synchronize nodes. + * Within this llist, there are two tail pointers: + * + * wait tail: Tracks the set of nodes, which need to + * wait for the current GP to complete. + * done tail: Tracks the set of nodes, for which grace + * period has elapsed. These nodes processing + * will be done as part of the cleanup work + * execution by a kworker. + * + * At every grace period init, a new wait node is added + * to the llist. This wait node is used as wait tail + * for this new grace period. Given that there are a fixed + * number of wait nodes, if all wait nodes are in use + * (which can happen when kworker callback processing + * is delayed) and additional grace period is requested. + * This means, a system is slow in processing callbacks. + * + * TODO: If a slow processing is detected, a first node + * in the llist should be used as a wait-tail for this + * grace period, therefore users which should wait due + * to a slow process are handled by _this_ grace period + * and not next. + * + * Below is an illustration of how the done and wait + * tail pointers move from one set of rcu_synchronize nodes + * to the other, as grace periods start and finish and + * nodes are processed by kworker. + * + * + * a. Initial llist callbacks list: + * + * +----------+ +--------+ +-------+ + * | | | | | | + * | head |---------> | cb2 |--------->| cb1 | + * | | | | | | + * +----------+ +--------+ +-------+ + * + * + * + * b. New GP1 Start: + * + * WAIT TAIL + * | + * | + * v + * +----------+ +--------+ +--------+ +-------+ + * | | | | | | | | + * | head ------> wait |------> cb2 |------> | cb1 | + * | | | head1 | | | | | + * +----------+ +--------+ +--------+ +-------+ + * + * + * + * c. GP completion: + * + * WAIT_TAIL == DONE_TAIL + * + * DONE TAIL + * | + * | + * v + * +----------+ +--------+ +--------+ +-------+ + * | | | | | | | | + * | head ------> wait |------> cb2 |------> | cb1 | + * | | | head1 | | | | | + * +----------+ +--------+ +--------+ +-------+ + * + * + * + * d. New callbacks and GP2 start: + * + * WAIT TAIL DONE TAIL + * | | + * | | + * v v + * +----------+ +------+ +------+ +------+ +-----+ +-----+ +-----+ + * | | | | | | | | | | | | | | + * | head ------> wait |--->| cb4 |--->| cb3 |--->|wait |--->| cb2 |--->| cb1 | + * | | | head2| | | | | |head1| | | | | + * +----------+ +------+ +------+ +------+ +-----+ +-----+ +-----+ + * + * + * + * e. GP2 completion: + * + * WAIT_TAIL == DONE_TAIL + * DONE TAIL + * | + * | + * v + * +----------+ +------+ +------+ +------+ +-----+ +-----+ +-----+ + * | | | | | | | | | | | | | | + * | head ------> wait |--->| cb4 |--->| cb3 |--->|wait |--->| cb2 |--->| cb1 | + * | | | head2| | | | | |head1| | | | | + * +----------+ +------+ +------+ +------+ +-----+ +-----+ +-----+ + * + * + * While the llist state transitions from d to e, a kworker + * can start executing rcu_sr_normal_gp_cleanup_work() and + * can observe either the old done tail (@c) or the new + * done tail (@e). So, done tail updates and reads need + * to use the rel-acq semantics. If the concurrent kworker + * observes the old done tail, the newly queued work + * execution will process the updated done tail. If the + * concurrent kworker observes the new done tail, then + * the newly queued work will skip processing the done + * tail, as workqueue semantics guarantees that the new + * work is executed only after the previous one completes. + * + * f. kworker callbacks processing complete: + * + * + * DONE TAIL + * | + * | + * v + * +----------+ +--------+ + * | | | | + * | head ------> wait | + * | | | head2 | + * +----------+ +--------+ + * + */ +static bool rcu_sr_is_wait_head(struct llist_node *node) +{ + return &(rcu_state.srs_wait_nodes)[0].node <= node && + node <= &(rcu_state.srs_wait_nodes)[SR_NORMAL_GP_WAIT_HEAD_MAX - 1].node; +} + +static struct llist_node *rcu_sr_get_wait_head(void) +{ + struct sr_wait_node *sr_wn; + int i; + + for (i = 0; i < SR_NORMAL_GP_WAIT_HEAD_MAX; i++) { + sr_wn = &(rcu_state.srs_wait_nodes)[i]; + + if (!atomic_cmpxchg_acquire(&sr_wn->inuse, 0, 1)) + return &sr_wn->node; + } + + return NULL; +} + +static void rcu_sr_put_wait_head(struct llist_node *node) +{ + struct sr_wait_node *sr_wn = container_of(node, struct sr_wait_node, node); + + atomic_set_release(&sr_wn->inuse, 0); +} + +/* Enable rcu_normal_wake_from_gp automatically on small systems. */ +#define WAKE_FROM_GP_CPU_THRESHOLD 16 + +static int rcu_normal_wake_from_gp = -1; +module_param(rcu_normal_wake_from_gp, int, 0644); +static struct workqueue_struct *sync_wq; + +static void rcu_sr_normal_complete(struct llist_node *node) +{ + struct rcu_synchronize *rs = container_of( + (struct rcu_head *) node, struct rcu_synchronize, head); + + WARN_ONCE(IS_ENABLED(CONFIG_PROVE_RCU) && + !poll_state_synchronize_rcu_full(&rs->oldstate), + "A full grace period is not passed yet!\n"); + + /* Finally. */ + complete(&rs->completion); +} + +static void rcu_sr_normal_gp_cleanup_work(struct work_struct *work) +{ + struct llist_node *done, *rcu, *next, *head; + + /* + * This work execution can potentially execute + * while a new done tail is being updated by + * grace period kthread in rcu_sr_normal_gp_cleanup(). + * So, read and updates of done tail need to + * follow acq-rel semantics. + * + * Given that wq semantics guarantees that a single work + * cannot execute concurrently by multiple kworkers, + * the done tail list manipulations are protected here. + */ + done = smp_load_acquire(&rcu_state.srs_done_tail); + if (WARN_ON_ONCE(!done)) + return; + + WARN_ON_ONCE(!rcu_sr_is_wait_head(done)); + head = done->next; + done->next = NULL; + + /* + * The dummy node, which is pointed to by the + * done tail which is acq-read above is not removed + * here. This allows lockless additions of new + * rcu_synchronize nodes in rcu_sr_normal_add_req(), + * while the cleanup work executes. The dummy + * nodes is removed, in next round of cleanup + * work execution. + */ + llist_for_each_safe(rcu, next, head) { + if (!rcu_sr_is_wait_head(rcu)) { + rcu_sr_normal_complete(rcu); + continue; + } + + rcu_sr_put_wait_head(rcu); + } + + /* Order list manipulations with atomic access. */ + atomic_dec_return_release(&rcu_state.srs_cleanups_pending); +} + +/* + * Helper function for rcu_gp_cleanup(). + */ +static void rcu_sr_normal_gp_cleanup(void) +{ + struct llist_node *wait_tail, *next = NULL, *rcu = NULL; + int done = 0; + + wait_tail = rcu_state.srs_wait_tail; + if (wait_tail == NULL) + return; + + rcu_state.srs_wait_tail = NULL; + ASSERT_EXCLUSIVE_WRITER(rcu_state.srs_wait_tail); + WARN_ON_ONCE(!rcu_sr_is_wait_head(wait_tail)); + + /* + * Process (a) and (d) cases. See an illustration. + */ + llist_for_each_safe(rcu, next, wait_tail->next) { + if (rcu_sr_is_wait_head(rcu)) + break; + + rcu_sr_normal_complete(rcu); + // It can be last, update a next on this step. + wait_tail->next = next; + + if (++done == SR_MAX_USERS_WAKE_FROM_GP) + break; + } + + /* + * Fast path, no more users to process except putting the second last + * wait head if no inflight-workers. If there are in-flight workers, + * they will remove the last wait head. + * + * Note that the ACQUIRE orders atomic access with list manipulation. + */ + if (wait_tail->next && wait_tail->next->next == NULL && + rcu_sr_is_wait_head(wait_tail->next) && + !atomic_read_acquire(&rcu_state.srs_cleanups_pending)) { + rcu_sr_put_wait_head(wait_tail->next); + wait_tail->next = NULL; + } + + /* Concurrent sr_normal_gp_cleanup work might observe this update. */ + ASSERT_EXCLUSIVE_WRITER(rcu_state.srs_done_tail); + smp_store_release(&rcu_state.srs_done_tail, wait_tail); + + /* + * We schedule a work in order to perform a final processing + * of outstanding users(if still left) and releasing wait-heads + * added by rcu_sr_normal_gp_init() call. + */ + if (wait_tail->next) { + atomic_inc(&rcu_state.srs_cleanups_pending); + if (!queue_work(sync_wq, &rcu_state.srs_cleanup_work)) + atomic_dec(&rcu_state.srs_cleanups_pending); + } +} + +/* + * Helper function for rcu_gp_init(). + */ +static bool rcu_sr_normal_gp_init(void) +{ + struct llist_node *first; + struct llist_node *wait_head; + bool start_new_poll = false; + + first = READ_ONCE(rcu_state.srs_next.first); + if (!first || rcu_sr_is_wait_head(first)) + return start_new_poll; + + wait_head = rcu_sr_get_wait_head(); + if (!wait_head) { + // Kick another GP to retry. + start_new_poll = true; + return start_new_poll; + } + + /* Inject a wait-dummy-node. */ + llist_add(wait_head, &rcu_state.srs_next); + + /* + * A waiting list of rcu_synchronize nodes should be empty on + * this step, since a GP-kthread, rcu_gp_init() -> gp_cleanup(), + * rolls it over. If not, it is a BUG, warn a user. + */ + WARN_ON_ONCE(rcu_state.srs_wait_tail != NULL); + rcu_state.srs_wait_tail = wait_head; + ASSERT_EXCLUSIVE_WRITER(rcu_state.srs_wait_tail); + + return start_new_poll; +} + +static void rcu_sr_normal_add_req(struct rcu_synchronize *rs) +{ + llist_add((struct llist_node *) &rs->head, &rcu_state.srs_next); } /* * Initialize a new grace period. Return false if no grace period required. */ -static bool rcu_gp_init(struct rcu_state *rsp) +static noinline_for_stack bool rcu_gp_init(void) { + unsigned long flags; unsigned long oldmask; + unsigned long mask; struct rcu_data *rdp; - struct rcu_node *rnp = rcu_get_root(rsp); + struct rcu_node *rnp = rcu_get_root(); + bool start_new_poll; + unsigned long old_gp_seq; - WRITE_ONCE(rsp->gp_activity, jiffies); + WRITE_ONCE(rcu_state.gp_activity, jiffies); raw_spin_lock_irq_rcu_node(rnp); - if (!READ_ONCE(rsp->gp_flags)) { + if (!rcu_state.gp_flags) { /* Spurious wakeup, tell caller to go back to sleep. */ raw_spin_unlock_irq_rcu_node(rnp); return false; } - WRITE_ONCE(rsp->gp_flags, 0); /* Clear all flags: New grace period. */ + WRITE_ONCE(rcu_state.gp_flags, 0); /* Clear all flags: New GP. */ - if (WARN_ON_ONCE(rcu_gp_in_progress(rsp))) { + if (WARN_ON_ONCE(rcu_gp_in_progress())) { /* * Grace period already in progress, don't start another. * Not supposed to be able to happen. @@ -1976,25 +1829,74 @@ static bool rcu_gp_init(struct rcu_state *rsp) } /* Advance to a new grace period and initialize state. */ - record_gp_stall_check_time(rsp); - /* Record GP times before starting GP, hence smp_store_release(). */ - smp_store_release(&rsp->gpnum, rsp->gpnum + 1); - trace_rcu_grace_period(rsp->name, rsp->gpnum, TPS("start")); + record_gp_stall_check_time(); + /* + * A new wait segment must be started before gp_seq advanced, so + * that previous gp waiters won't observe the new gp_seq. + */ + start_new_poll = rcu_sr_normal_gp_init(); + /* Record GP times before starting GP, hence rcu_seq_start(). */ + old_gp_seq = rcu_state.gp_seq; + /* + * Critical ordering: rcu_seq_start() must happen BEFORE the CPU hotplug + * scan below. Otherwise we risk a race where a newly onlining CPU could + * be missed by the current grace period, potentially leading to + * use-after-free errors. For a detailed explanation of this race, see + * Documentation/RCU/Design/Requirements/Requirements.rst in the + * "Hotplug CPU" section. + * + * Also note that the root rnp's gp_seq is kept separate from, and lags, + * the rcu_state's gp_seq, for a reason. See the Quick-Quiz on + * Single-node systems for more details (in Data-Structures.rst). + */ + rcu_seq_start(&rcu_state.gp_seq); + /* Ensure that rcu_seq_done_exact() guardband doesn't give false positives. */ + WARN_ON_ONCE(IS_ENABLED(CONFIG_PROVE_RCU) && + rcu_seq_done_exact(&old_gp_seq, rcu_seq_snap(&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. + * The "start_new_poll" is set to true, only when this GP is not able + * to handle anything and there are outstanding users. It happens when + * the rcu_sr_normal_gp_init() function was not able to insert a dummy + * separator to the llist, because there were no left any dummy-nodes. + * + * Number of dummy-nodes is fixed, it could be that we are run out of + * them, if so we start a new pool request to repeat a try. It is rare + * and it means that a system is doing a slow processing of callbacks. */ - rcu_for_each_leaf_node(rsp, rnp) { - rcu_gp_slow(rsp, gp_preinit_delay); - raw_spin_lock_irq_rcu_node(rnp); + if (start_new_poll) + (void) start_poll_synchronize_rcu(); + + /* + * 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. + */ + WRITE_ONCE(rcu_state.gp_state, RCU_GP_ONOFF); + /* Exclude CPU hotplug operations. */ + rcu_for_each_leaf_node(rnp) { + local_irq_disable(); + /* + * Serialize with CPU offline. See Requirements.rst > Hotplug CPU > + * Concurrent Quiescent State Reporting for Offline CPUs. + */ + 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_node(rnp); + arch_spin_unlock(&rcu_state.ofl_lock); + local_irq_enable(); continue; } @@ -2004,12 +1906,14 @@ static bool rcu_gp_init(struct rcu_state *rsp) /* If zero-ness of ->qsmaskinit changed, propagate up tree. */ if (!oldmask != !rnp->qsmaskinit) { - if (!oldmask) /* First online CPU for this rcu_node. */ - rcu_init_new_rnp(rnp); - else if (rcu_preempt_has_tasks(rnp)) /* blocked tasks */ - rnp->wait_blkd_tasks = true; - else /* Last offline CPU and can propagate. */ + if (!oldmask) { /* First online CPU for rcu_node. */ + if (!rnp->wait_blkd_tasks) /* Ever offline? */ + rcu_init_new_rnp(rnp); + } else if (rcu_preempt_has_tasks(rnp)) { + rnp->wait_blkd_tasks = true; /* blocked tasks */ + } else { /* Last offline CPU and can propagate. */ rcu_cleanup_dead_rnp(rnp); + } } /* @@ -2018,68 +1922,88 @@ static bool rcu_gp_init(struct rcu_state *rsp) * still offline, propagate up the rcu_node tree and * clear ->wait_blkd_tasks. Otherwise, if one of this * rcu_node structure's CPUs has since come back online, - * simply clear ->wait_blkd_tasks (but rcu_cleanup_dead_rnp() - * checks for this, so just call it unconditionally). + * simply clear ->wait_blkd_tasks. */ if (rnp->wait_blkd_tasks && - (!rcu_preempt_has_tasks(rnp) || - rnp->qsmaskinit)) { + (!rcu_preempt_has_tasks(rnp) || rnp->qsmaskinit)) { rnp->wait_blkd_tasks = false; - rcu_cleanup_dead_rnp(rnp); + if (!rnp->qsmaskinit) + rcu_cleanup_dead_rnp(rnp); } - raw_spin_unlock_irq_rcu_node(rnp); + raw_spin_unlock_rcu_node(rnp); + arch_spin_unlock(&rcu_state.ofl_lock); + local_irq_enable(); } + rcu_gp_slow(gp_preinit_delay); /* Races with CPU hotplug. */ /* * Set the quiescent-state-needed bits in all the rcu_node - * structures for all currently online CPUs in breadth-first order, - * starting from the root rcu_node structure, relying on the layout - * of the tree within the rsp->node[] array. Note that other CPUs - * will access only the leaves of the hierarchy, thus seeing that no - * grace period is in progress, at least until the corresponding - * leaf node has been initialized. + * structures for all currently online CPUs in breadth-first + * order, starting from the root rcu_node structure, relying on the + * layout of the tree within the rcu_state.node[] array. Note that + * other CPUs will access only the leaves of the hierarchy, thus + * seeing that no grace period is in progress, at least until the + * corresponding leaf node has been initialized. * * The grace period cannot complete until the initialization * process finishes, because this kthread handles both. */ - rcu_for_each_node_breadth_first(rsp, rnp) { - rcu_gp_slow(rsp, gp_init_delay); - raw_spin_lock_irq_rcu_node(rnp); - rdp = this_cpu_ptr(rsp->rda); + 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); + rdp = this_cpu_ptr(&rcu_data); rcu_preempt_check_blocked_tasks(rnp); rnp->qsmask = rnp->qsmaskinit; - WRITE_ONCE(rnp->gpnum, rsp->gpnum); - if (WARN_ON_ONCE(rnp->completed != rsp->completed)) - WRITE_ONCE(rnp->completed, rsp->completed); + WRITE_ONCE(rnp->gp_seq, rcu_state.gp_seq); if (rnp == rdp->mynode) - (void)__note_gp_changes(rsp, rnp, rdp); + (void)__note_gp_changes(rnp, rdp); rcu_preempt_boost_start_gp(rnp); - trace_rcu_grace_period_init(rsp->name, rnp->gpnum, + trace_rcu_grace_period_init(rcu_state.name, rnp->gp_seq, rnp->level, rnp->grplo, rnp->grphi, rnp->qsmask); - raw_spin_unlock_irq_rcu_node(rnp); - cond_resched_rcu_qs(); - WRITE_ONCE(rsp->gp_activity, jiffies); + /* + * Quiescent states for tasks on any now-offline CPUs. Since we + * released the ofl and rnp lock before this loop, CPUs might + * have gone offline and we have to report QS on their behalf. + * See Requirements.rst > Hotplug CPU > Concurrent QS Reporting. + */ + mask = rnp->qsmask & ~rnp->qsmaskinitnext; + rnp->rcu_gp_init_mask = mask; + if ((mask || rnp->wait_blkd_tasks) && rcu_is_leaf_node(rnp)) + rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags); + else + raw_spin_unlock_irq_rcu_node(rnp); + cond_resched_tasks_rcu_qs(); + 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; } /* - * Helper function for wait_event_interruptible_timeout() wakeup - * at force-quiescent-state time. + * Helper function for swait_event_idle_exclusive() wakeup at force-quiescent-state + * time. */ -static bool rcu_gp_fqs_check_wake(struct rcu_state *rsp, int *gfp) +static bool rcu_gp_fqs_check_wake(int *gfp) { - struct rcu_node *rnp = rcu_get_root(rsp); + struct rcu_node *rnp = rcu_get_root(); - /* Someone like call_rcu() requested a force-quiescent-state scan. */ - *gfp = READ_ONCE(rsp->gp_flags); + // 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; @@ -2089,45 +2013,145 @@ static bool rcu_gp_fqs_check_wake(struct rcu_state *rsp, int *gfp) /* * Do one round of quiescent-state forcing. */ -static void rcu_gp_fqs(struct rcu_state *rsp, bool first_time) +static void rcu_gp_fqs(bool first_time) { - struct rcu_node *rnp = rcu_get_root(rsp); + int nr_fqs = READ_ONCE(rcu_state.nr_fqs_jiffies_stall); + struct rcu_node *rnp = rcu_get_root(); + + WRITE_ONCE(rcu_state.gp_activity, jiffies); + WRITE_ONCE(rcu_state.n_force_qs, rcu_state.n_force_qs + 1); + + WARN_ON_ONCE(nr_fqs > 3); + /* Only countdown nr_fqs for stall purposes if jiffies moves. */ + if (nr_fqs) { + if (nr_fqs == 1) { + WRITE_ONCE(rcu_state.jiffies_stall, + jiffies + rcu_jiffies_till_stall_check()); + } + WRITE_ONCE(rcu_state.nr_fqs_jiffies_stall, --nr_fqs); + } - WRITE_ONCE(rsp->gp_activity, jiffies); - rsp->n_force_qs++; if (first_time) { /* Collect dyntick-idle snapshots. */ - force_qs_rnp(rsp, dyntick_save_progress_counter); + force_qs_rnp(rcu_watching_snap_save); } else { /* Handle dyntick-idle and offline CPUs. */ - force_qs_rnp(rsp, rcu_implicit_dynticks_qs); + force_qs_rnp(rcu_watching_snap_recheck); } /* Clear flag to prevent immediate re-entry. */ - if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) { + if (READ_ONCE(rcu_state.gp_flags) & RCU_GP_FLAG_FQS) { raw_spin_lock_irq_rcu_node(rnp); - WRITE_ONCE(rsp->gp_flags, - READ_ONCE(rsp->gp_flags) & ~RCU_GP_FLAG_FQS); + WRITE_ONCE(rcu_state.gp_flags, rcu_state.gp_flags & ~RCU_GP_FLAG_FQS); raw_spin_unlock_irq_rcu_node(rnp); } } /* + * Loop doing repeated quiescent-state forcing until the grace period ends. + */ +static noinline_for_stack void rcu_gp_fqs_loop(void) +{ + bool first_gp_fqs = true; + int gf = 0; + unsigned long j; + int ret; + struct rcu_node *rnp = rcu_get_root(); + + j = READ_ONCE(jiffies_till_first_fqs); + if (rcu_state.cbovld) + gf = RCU_GP_FLAG_OVLD; + ret = 0; + for (;;) { + 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, rcu_state.gp_seq, + TPS("fqswait")); + 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. */ + /* + * 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 (!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); + 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); + ret = 0; /* Force full wait till next FQS. */ + j = READ_ONCE(jiffies_till_next_fqs); + } else { + /* Deal with stray signal. */ + cond_resched_tasks_rcu_qs(); + WRITE_ONCE(rcu_state.gp_activity, jiffies); + WARN_ON(signal_pending(current)); + trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, + TPS("fqswaitsig")); + ret = 1; /* Keep old FQS timing. */ + j = jiffies; + if (time_after(jiffies, rcu_state.jiffies_force_qs)) + j = 1; + else + j = rcu_state.jiffies_force_qs - j; + gf = 0; + } + } +} + +/* * Clean up after the old grace period. */ -static void rcu_gp_cleanup(struct rcu_state *rsp) +static noinline void rcu_gp_cleanup(void) { - unsigned long gp_duration; + int cpu; bool needgp = false; - int nocb = 0; + unsigned long gp_duration; + unsigned long new_gp_seq; + bool offloaded; struct rcu_data *rdp; - struct rcu_node *rnp = rcu_get_root(rsp); + struct rcu_node *rnp = rcu_get_root(); struct swait_queue_head *sq; - WRITE_ONCE(rsp->gp_activity, jiffies); + WRITE_ONCE(rcu_state.gp_activity, jiffies); raw_spin_lock_irq_rcu_node(rnp); - gp_duration = jiffies - rsp->gp_start; - if (gp_duration > rsp->gp_max) - rsp->gp_max = gp_duration; + rcu_state.gp_end = jiffies; + gp_duration = rcu_state.gp_end - rcu_state.gp_start; + if (gp_duration > rcu_state.gp_max) + rcu_state.gp_max = gp_duration; /* * We know the grace period is complete, but to everyone else @@ -2137,244 +2161,153 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) * 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); /* - * Propagate new ->completed value to rcu_node structures so - * that other CPUs don't have to wait until the start of the next - * grace period to process their callbacks. This also avoids - * some nasty RCU grace-period initialization races by forcing - * the end of the current grace period to be completely recorded in - * all of the rcu_node structures before the beginning of the next - * grace period is recorded in any of the rcu_node structures. + * Propagate new ->gp_seq value to rcu_node structures so that + * other CPUs don't have to wait until the start of the next grace + * period to process their callbacks. This also avoids some nasty + * RCU grace-period initialization races by forcing the end of + * the current grace period to be completely recorded in all of + * the rcu_node structures before the beginning of the next grace + * period is recorded in any of the rcu_node structures. */ - rcu_for_each_node_breadth_first(rsp, rnp) { + new_gp_seq = rcu_state.gp_seq; + rcu_seq_end(&new_gp_seq); + rcu_for_each_node_breadth_first(rnp) { raw_spin_lock_irq_rcu_node(rnp); - WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)); + if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp))) + dump_blkd_tasks(rnp, 10); WARN_ON_ONCE(rnp->qsmask); - WRITE_ONCE(rnp->completed, rsp->gpnum); - rdp = this_cpu_ptr(rsp->rda); + 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(rsp, rnp, rdp) || needgp; + needgp = __note_gp_changes(rnp, rdp) || needgp; /* smp_mb() provided by prior unlock-lock pair. */ - nocb += rcu_future_gp_cleanup(rsp, rnp); + 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); - cond_resched_rcu_qs(); - WRITE_ONCE(rsp->gp_activity, jiffies); - rcu_gp_slow(rsp, gp_cleanup_delay); + cond_resched_tasks_rcu_qs(); + WRITE_ONCE(rcu_state.gp_activity, jiffies); + rcu_gp_slow(gp_cleanup_delay); + } + rnp = rcu_get_root(); + raw_spin_lock_irq_rcu_node(rnp); /* GP before ->gp_seq update. */ + + /* 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); + 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)) { + trace_rcu_this_gp(rnp, rdp, rnp->gp_seq_needed, + TPS("CleanupMore")); + needgp = true; } - rnp = rcu_get_root(rsp); - raw_spin_lock_irq_rcu_node(rnp); /* Order GP before ->completed update. */ - rcu_nocb_gp_set(rnp, nocb); - - /* Declare grace period done. */ - WRITE_ONCE(rsp->completed, rsp->gpnum); - trace_rcu_grace_period(rsp->name, rsp->completed, TPS("end")); - rsp->gp_state = RCU_GP_IDLE; - rdp = this_cpu_ptr(rsp->rda); /* Advance CBs to reduce false positives below. */ - needgp = rcu_advance_cbs(rsp, rnp, rdp) || needgp; - if (needgp || cpu_needs_another_gp(rsp, rdp)) { - WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT); - trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), - TPS("newreq")); + 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); + WRITE_ONCE(rcu_state.gp_req_activity, jiffies); + trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("newreq")); + } else { + + // 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); + + // Make synchronize_rcu() users aware of the end of old grace period. + rcu_sr_normal_gp_cleanup(); + + // 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); } /* * Body of kthread that handles grace periods. */ -static int __noreturn rcu_gp_kthread(void *arg) +static int __noreturn rcu_gp_kthread(void *unused) { - bool first_gp_fqs; - int gf; - unsigned long j; - int ret; - struct rcu_state *rsp = arg; - struct rcu_node *rnp = rcu_get_root(rsp); - rcu_bind_gp_kthread(); for (;;) { /* Handle grace-period start. */ for (;;) { - trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), + trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("reqwait")); - rsp->gp_state = RCU_GP_WAIT_GPS; - swait_event_interruptible(rsp->gp_wq, - READ_ONCE(rsp->gp_flags) & - RCU_GP_FLAG_INIT); - rsp->gp_state = RCU_GP_DONE_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_gp_torture_wait(); + WRITE_ONCE(rcu_state.gp_state, RCU_GP_DONE_GPS); /* Locking provides needed memory barrier. */ - if (rcu_gp_init(rsp)) + if (rcu_gp_init()) break; - cond_resched_rcu_qs(); - WRITE_ONCE(rsp->gp_activity, jiffies); + cond_resched_tasks_rcu_qs(); + WRITE_ONCE(rcu_state.gp_activity, jiffies); WARN_ON(signal_pending(current)); - trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), + trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("reqwaitsig")); } /* Handle quiescent-state forcing. */ - first_gp_fqs = true; - j = jiffies_till_first_fqs; - if (j > HZ) { - j = HZ; - jiffies_till_first_fqs = HZ; - } - ret = 0; - for (;;) { - if (!ret) { - rsp->jiffies_force_qs = jiffies + j; - WRITE_ONCE(rsp->jiffies_kick_kthreads, - jiffies + 3 * j); - } - trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), - TPS("fqswait")); - rsp->gp_state = RCU_GP_WAIT_FQS; - ret = swait_event_interruptible_timeout(rsp->gp_wq, - rcu_gp_fqs_check_wake(rsp, &gf), j); - rsp->gp_state = RCU_GP_DOING_FQS; - /* Locking provides needed memory barriers. */ - /* If grace period done, leave loop. */ - 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, rsp->jiffies_force_qs) || - (gf & RCU_GP_FLAG_FQS)) { - trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), - TPS("fqsstart")); - rcu_gp_fqs(rsp, first_gp_fqs); - first_gp_fqs = false; - trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), - TPS("fqsend")); - cond_resched_rcu_qs(); - WRITE_ONCE(rsp->gp_activity, jiffies); - ret = 0; /* Force full wait till next FQS. */ - j = jiffies_till_next_fqs; - if (j > HZ) { - j = HZ; - jiffies_till_next_fqs = HZ; - } else if (j < 1) { - j = 1; - jiffies_till_next_fqs = 1; - } - } else { - /* Deal with stray signal. */ - cond_resched_rcu_qs(); - WRITE_ONCE(rsp->gp_activity, jiffies); - WARN_ON(signal_pending(current)); - trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), - TPS("fqswaitsig")); - ret = 1; /* Keep old FQS timing. */ - j = jiffies; - if (time_after(jiffies, rsp->jiffies_force_qs)) - j = 1; - else - j = rsp->jiffies_force_qs - j; - } - } + rcu_gp_fqs_loop(); /* Handle grace-period end. */ - rsp->gp_state = RCU_GP_CLEANUP; - rcu_gp_cleanup(rsp); - rsp->gp_state = RCU_GP_CLEANED; + WRITE_ONCE(rcu_state.gp_state, RCU_GP_CLEANUP); + rcu_gp_cleanup(); + WRITE_ONCE(rcu_state.gp_state, RCU_GP_CLEANED); } } /* - * Start a new RCU grace period if warranted, re-initializing the hierarchy - * in preparation for detecting the next grace period. The caller must hold - * the root node's ->lock and hard irqs must be disabled. - * - * Note that it is legal for a dying CPU (which is marked as offline) to - * invoke this function. This can happen when the dying CPU reports its - * quiescent state. - * - * Returns true if the grace-period kthread must be awakened. - */ -static bool -rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp, - struct rcu_data *rdp) -{ - lockdep_assert_held(&rnp->lock); - if (!rsp->gp_kthread || !cpu_needs_another_gp(rsp, rdp)) { - /* - * Either we have not yet spawned the grace-period - * task, this CPU does not need another grace period, - * or a grace period is already in progress. - * Either way, don't start a new grace period. - */ - return false; - } - WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT); - trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum), - TPS("newreq")); - - /* - * We can't do wakeups while holding the rnp->lock, as that - * could cause possible deadlocks with the rq->lock. Defer - * the wakeup to our caller. - */ - return true; -} - -/* - * Similar to rcu_start_gp_advanced(), but also advance the calling CPU's - * callbacks. Note that rcu_start_gp_advanced() cannot do this because it - * is invoked indirectly from rcu_advance_cbs(), which would result in - * endless recursion -- or would do so if it wasn't for the self-deadlock - * that is encountered beforehand. - * - * Returns true if the grace-period kthread needs to be awakened. - */ -static bool rcu_start_gp(struct rcu_state *rsp) -{ - struct rcu_data *rdp = this_cpu_ptr(rsp->rda); - struct rcu_node *rnp = rcu_get_root(rsp); - bool ret = false; - - /* - * If there is no grace period in progress right now, any - * callbacks we have up to this point will be satisfied by the - * next grace period. Also, advancing the callbacks reduces the - * probability of false positives from cpu_needs_another_gp() - * resulting in pointless grace periods. So, advance callbacks - * then start the grace period! - */ - ret = rcu_advance_cbs(rsp, rnp, rdp) || ret; - ret = rcu_start_gp_advanced(rsp, rnp, rdp) || ret; - return ret; -} - -/* - * Report a full set of quiescent states to the specified rcu_state data - * structure. Invoke rcu_gp_kthread_wake() to awaken the grace-period - * kthread if another grace period is required. Whether we wake - * the grace-period kthread or it awakens itself for the next round - * of quiescent-state forcing, that kthread will clean up after the - * just-completed grace period. Note that the caller must hold rnp->lock, - * which is released before return. + * Report a full set of quiescent states to the rcu_state data structure. + * Invoke rcu_gp_kthread_wake() to awaken the grace-period kthread if + * another grace period is required. Whether we wake the grace-period + * kthread or it awakens itself for the next round of quiescent-state + * forcing, that kthread will clean up after the just-completed grace + * period. Note that the caller must hold rnp->lock, which is released + * before return. */ -static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) - __releases(rcu_get_root(rsp)->lock) +static void rcu_report_qs_rsp(unsigned long flags) + __releases(rcu_get_root()->lock) { - lockdep_assert_held(&rcu_get_root(rsp)->lock); - WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); - WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS); - raw_spin_unlock_irqrestore_rcu_node(rcu_get_root(rsp), flags); - rcu_gp_kthread_wake(rsp); + raw_lockdep_assert_held_rcu_node(rcu_get_root()); + WARN_ON_ONCE(!rcu_gp_in_progress()); + WRITE_ONCE(rcu_state.gp_flags, rcu_state.gp_flags | RCU_GP_FLAG_FQS); + raw_spin_unlock_irqrestore_rcu_node(rcu_get_root(), flags); + rcu_gp_kthread_wake(); } /* @@ -2384,22 +2317,25 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) * must be represented by the same rcu_node structure (which need not be a * leaf rcu_node structure, though it often will be). The gps parameter * is the grace-period snapshot, which means that the quiescent states - * are valid only if rnp->gpnum is equal to gps. That structure's lock + * are valid only if rnp->gp_seq is equal to gps. That structure's lock * must be held upon entry, and it is released before return. + * + * As a special case, if mask is zero, the bit-already-cleared check is + * disabled. This allows propagating quiescent state due to resumed tasks + * during grace-period initialization. */ -static void -rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, - struct rcu_node *rnp, unsigned long gps, unsigned long flags) +static void rcu_report_qs_rnp(unsigned long mask, struct rcu_node *rnp, + unsigned long gps, unsigned long flags) __releases(rnp->lock) { unsigned long oldmask = 0; struct rcu_node *rnp_c; - lockdep_assert_held(&rnp->lock); + raw_lockdep_assert_held_rcu_node(rnp); /* Walk up the rcu_node hierarchy. */ for (;;) { - if (!(rnp->qsmask & mask) || rnp->gpnum != gps) { + if ((!(rnp->qsmask & mask) && mask) || rnp->gp_seq != gps) { /* * Our bit has already been cleared, or the @@ -2409,8 +2345,10 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, return; } WARN_ON_ONCE(oldmask); /* Any child must be all zeroed! */ - rnp->qsmask &= ~mask; - trace_rcu_quiescent_state_report(rsp->name, rnp->gpnum, + WARN_ON_ONCE(!rcu_is_leaf_node(rnp) && + rcu_preempt_blocked_readers_cgp(rnp)); + 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, !!rnp->gp_tasks); @@ -2420,6 +2358,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; } + rnp->completedqs = rnp->gp_seq; mask = rnp->grpmask; if (rnp->parent == NULL) { @@ -2431,7 +2370,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, rnp_c = rnp; rnp = rnp->parent; raw_spin_lock_irqsave_rcu_node(rnp, flags); - oldmask = rnp_c->qsmask; + oldmask = READ_ONCE(rnp_c->qsmask); } /* @@ -2439,47 +2378,49 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, * state for this grace period. Invoke rcu_report_qs_rsp() * to clean up and start the next grace period if one is needed. */ - rcu_report_qs_rsp(rsp, flags); /* releases rnp->lock. */ + rcu_report_qs_rsp(flags); /* releases rnp->lock. */ } /* * Record a quiescent state for all tasks that were previously queued * on the specified rcu_node structure and that were blocking the current - * RCU grace period. The caller must hold the specified rnp->lock with + * RCU grace period. The caller must hold the corresponding rnp->lock with * irqs disabled, and this lock is released upon return, but irqs remain * disabled. */ -static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp, - struct rcu_node *rnp, unsigned long flags) +static void __maybe_unused +rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags) __releases(rnp->lock) { unsigned long gps; unsigned long mask; struct rcu_node *rnp_p; - lockdep_assert_held(&rnp->lock); - if (rcu_state_p == &rcu_sched_state || rsp != rcu_state_p || - rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) { + raw_lockdep_assert_held_rcu_node(rnp); + if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT_RCU)) || + WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)) || + rnp->qsmask != 0) { raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; /* Still need more quiescent states! */ } + rnp->completedqs = rnp->gp_seq; rnp_p = rnp->parent; if (rnp_p == NULL) { /* * Only one rcu_node structure in the tree, so don't * try to report up to its nonexistent parent! */ - rcu_report_qs_rsp(rsp, flags); + rcu_report_qs_rsp(flags); return; } - /* Report up the rest of the hierarchy, tracking current ->gpnum. */ - gps = rnp->gpnum; + /* Report up the rest of the hierarchy, tracking current ->gp_seq. */ + gps = rnp->gp_seq; mask = rnp->grpmask; raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ raw_spin_lock_rcu_node(rnp_p); /* irqs already disabled. */ - rcu_report_qs_rnp(mask, rsp, rnp_p, gps, flags); + rcu_report_qs_rnp(mask, rnp_p, gps, flags); } /* @@ -2487,17 +2428,17 @@ static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp, * structure. This must be called from the specified CPU. */ static void -rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) +rcu_report_qs_rdp(struct rcu_data *rdp) { unsigned long flags; unsigned long mask; - bool needwake; 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->gpnum != rnp->gpnum || - rnp->completed == rnp->gpnum || rdp->gpwrap) { + if (rdp->cpu_no_qs.b.norm || rdp->gp_seq != rnp->gp_seq || + rdp->gpwrap) { /* * The grace period in which this quiescent state was @@ -2506,26 +2447,32 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) * within the current grace period. */ rdp->cpu_no_qs.b.norm = true; /* need qs for new gp. */ - rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_dynticks.rcu_qs_ctr); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; } mask = rdp->grpmask; + rdp->core_needs_qs = false; if ((rnp->qsmask & mask) == 0) { raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } else { - rdp->core_needs_qs = false; - /* * 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... */ - needwake = rcu_accelerate_cbs(rsp, rnp, rdp); + if (!rcu_rdp_is_offloaded(rdp)) { + /* + * The current GP has not yet ended, so it + * should not be possible for rcu_accelerate_cbs() + * to return true. So complain, but don't awaken. + */ + WARN_ON_ONCE(rcu_accelerate_cbs(rnp, rdp)); + } - rcu_report_qs_rnp(mask, rsp, rnp, rnp->gpnum, flags); + 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(rsp); } } @@ -2536,10 +2483,10 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) * quiescent state for this grace period, and record that fact if so. */ static void -rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp) +rcu_check_quiescent_state(struct rcu_data *rdp) { /* Check for grace-period ends and beginnings. */ - note_gp_changes(rsp, rdp); + note_gp_changes(rdp); /* * Does this CPU still need to do its part for current grace period? @@ -2559,334 +2506,234 @@ rcu_check_quiescent_state(struct rcu_state *rsp, 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, rsp, rdp); -} - -/* - * Send the specified CPU's RCU callbacks to the orphanage. The - * specified CPU must be offline, and the caller must hold the - * ->orphan_lock. - */ -static void -rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp, - struct rcu_node *rnp, struct rcu_data *rdp) -{ - lockdep_assert_held(&rsp->orphan_lock); - - /* No-CBs CPUs do not have orphanable callbacks. */ - if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) || rcu_is_nocb_cpu(rdp->cpu)) - return; - - /* - * Orphan the callbacks. First adjust the counts. This is safe - * because _rcu_barrier() excludes CPU-hotplug operations, so it - * cannot be running now. Thus no memory barrier is required. - */ - rdp->n_cbs_orphaned += rcu_segcblist_n_cbs(&rdp->cblist); - rcu_segcblist_extract_count(&rdp->cblist, &rsp->orphan_done); - - /* - * Next, move those callbacks still needing a grace period to - * the orphanage, where some other CPU will pick them up. - * Some of the callbacks might have gone partway through a grace - * period, but that is too bad. They get to start over because we - * cannot assume that grace periods are synchronized across CPUs. - */ - rcu_segcblist_extract_pend_cbs(&rdp->cblist, &rsp->orphan_pend); - - /* - * Then move the ready-to-invoke callbacks to the orphanage, - * where some other CPU will pick them up. These will not be - * required to pass though another grace period: They are done. - */ - rcu_segcblist_extract_done_cbs(&rdp->cblist, &rsp->orphan_done); - - /* Finally, disallow further callbacks on this CPU. */ - rcu_segcblist_disable(&rdp->cblist); -} - -/* - * Adopt the RCU callbacks from the specified rcu_state structure's - * orphanage. The caller must hold the ->orphan_lock. - */ -static void rcu_adopt_orphan_cbs(struct rcu_state *rsp, unsigned long flags) -{ - struct rcu_data *rdp = raw_cpu_ptr(rsp->rda); - - lockdep_assert_held(&rsp->orphan_lock); - - /* No-CBs CPUs are handled specially. */ - if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) || - rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags)) - return; - - /* Do the accounting first. */ - rdp->n_cbs_adopted += rsp->orphan_done.len; - if (rsp->orphan_done.len_lazy != rsp->orphan_done.len) - rcu_idle_count_callbacks_posted(); - rcu_segcblist_insert_count(&rdp->cblist, &rsp->orphan_done); - - /* - * We do not need a memory barrier here because the only way we - * can get here if there is an rcu_barrier() in flight is if - * we are the task doing the rcu_barrier(). - */ - - /* First adopt the ready-to-invoke callbacks, then the done ones. */ - rcu_segcblist_insert_done_cbs(&rdp->cblist, &rsp->orphan_done); - WARN_ON_ONCE(rsp->orphan_done.head); - rcu_segcblist_insert_pend_cbs(&rdp->cblist, &rsp->orphan_pend); - WARN_ON_ONCE(rsp->orphan_pend.head); - WARN_ON_ONCE(rcu_segcblist_empty(&rdp->cblist) != - !rcu_segcblist_n_cbs(&rdp->cblist)); + rcu_report_qs_rdp(rdp); } -/* - * Trace the fact that this CPU is going offline. - */ -static void rcu_cleanup_dying_cpu(struct rcu_state *rsp) +/* Return true if callback-invocation time limit exceeded. */ +static bool rcu_do_batch_check_time(long count, long tlimit, + bool jlimit_check, unsigned long jlimit) { - RCU_TRACE(unsigned long mask;) - RCU_TRACE(struct rcu_data *rdp = this_cpu_ptr(rsp->rda);) - RCU_TRACE(struct rcu_node *rnp = rdp->mynode;) - - if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) - return; - - RCU_TRACE(mask = rdp->grpmask;) - trace_rcu_grace_period(rsp->name, - rnp->gpnum + 1 - !!(rnp->qsmask & mask), - TPS("cpuofl")); -} - -/* - * All CPUs for the specified rcu_node structure have gone offline, - * and all tasks that were preempted within an RCU read-side critical - * section while running on one of those CPUs have since exited their RCU - * read-side critical section. Some other CPU is reporting this fact with - * the specified rcu_node structure's ->lock held and interrupts disabled. - * This function therefore goes up the tree of rcu_node structures, - * clearing the corresponding bits in the ->qsmaskinit fields. Note that - * the leaf rcu_node structure's ->qsmaskinit field has already been - * updated - * - * This function does check that the specified rcu_node structure has - * all CPUs offline and no blocked tasks, so it is OK to invoke it - * prematurely. That said, invoking it after the fact will cost you - * a needless lock acquisition. So once it has done its work, don't - * invoke it again. - */ -static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf) -{ - long mask; - struct rcu_node *rnp = rnp_leaf; - - lockdep_assert_held(&rnp->lock); - if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) || - rnp->qsmaskinit || rcu_preempt_has_tasks(rnp)) - return; - for (;;) { - mask = rnp->grpmask; - rnp = rnp->parent; - if (!rnp) - break; - raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ - rnp->qsmaskinit &= ~mask; - rnp->qsmask &= ~mask; - if (rnp->qsmaskinit) { - raw_spin_unlock_rcu_node(rnp); - /* irqs remain disabled. */ - return; - } - raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ - } -} - -/* - * The CPU has been completely removed, and some other CPU is reporting - * this fact from process context. Do the remainder of the cleanup, - * including orphaning the outgoing CPU's RCU callbacks, and also - * adopting them. There can only be one CPU hotplug operation at a time, - * so no other CPU can be attempting to update rcu_cpu_kthread_task. - */ -static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) -{ - unsigned long flags; - struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); - struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */ - - if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) - return; - - /* Adjust any no-longer-needed kthreads. */ - rcu_boost_kthread_setaffinity(rnp, -1); - - /* Orphan the dead CPU's callbacks, and adopt them if appropriate. */ - raw_spin_lock_irqsave(&rsp->orphan_lock, flags); - rcu_send_cbs_to_orphanage(cpu, rsp, rnp, rdp); - rcu_adopt_orphan_cbs(rsp, flags); - raw_spin_unlock_irqrestore(&rsp->orphan_lock, flags); - - WARN_ONCE(rcu_segcblist_n_cbs(&rdp->cblist) != 0 || - !rcu_segcblist_empty(&rdp->cblist), - "rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, 1stCB=%p\n", - cpu, rcu_segcblist_n_cbs(&rdp->cblist), - rcu_segcblist_first_cb(&rdp->cblist)); + // Invoke local_clock() only once per 32 consecutive callbacks. + return unlikely(tlimit) && + (!likely(count & 31) || + (IS_ENABLED(CONFIG_RCU_DOUBLE_CHECK_CB_TIME) && + jlimit_check && time_after(jiffies, jlimit))) && + local_clock() >= tlimit; } /* * 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_state *rsp, struct rcu_data *rdp) +static void rcu_do_batch(struct rcu_data *rdp) { + long bl; + long count = 0; + int div; + bool __maybe_unused empty; unsigned long flags; - struct rcu_head *rhp; + unsigned long jlimit; + bool jlimit_check = false; + long pending; struct rcu_cblist rcl = RCU_CBLIST_INITIALIZER(rcl); - long bl, count; + struct rcu_head *rhp; + long tlimit = 0; /* If no callbacks are ready, just return. */ if (!rcu_segcblist_ready_cbs(&rdp->cblist)) { - trace_rcu_batch_start(rsp->name, - rcu_segcblist_n_lazy_cbs(&rdp->cblist), + trace_rcu_batch_start(rcu_state.name, rcu_segcblist_n_cbs(&rdp->cblist), 0); - trace_rcu_batch_end(rsp->name, 0, + 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. + * + * Callbacks execution is fully ordered against preceding grace period + * completion (materialized by rnp->gp_seq update) thanks to the + * smp_mb__after_unlock_lock() upon node locking required for callbacks + * advancing. In NOCB mode this ordering is then further relayed through + * the nocb locking that protects both callbacks advancing and extraction. */ - local_irq_save(flags); + rcu_nocb_lock_irqsave(rdp, flags); WARN_ON_ONCE(cpu_is_offline(smp_processor_id())); - bl = rdp->blimit; - trace_rcu_batch_start(rsp->name, rcu_segcblist_n_lazy_cbs(&rdp->cblist), + pending = rcu_segcblist_get_seglen(&rdp->cblist, RCU_DONE_TAIL); + 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() || rdp->rcu_cpu_kthread_status == RCU_KTHREAD_RUNNING) && + (IS_ENABLED(CONFIG_RCU_DOUBLE_CHECK_CB_TIME) || unlikely(bl > 100))) { + const long npj = NSEC_PER_SEC / HZ; + 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; + jlimit = jiffies + (rrn + npj + 1) / npj; + jlimit_check = true; + } + trace_rcu_batch_start(rcu_state.name, rcu_segcblist_n_cbs(&rdp->cblist), bl); rcu_segcblist_extract_done_cbs(&rdp->cblist, &rcl); - local_irq_restore(flags); + 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); - if (__rcu_reclaim(rsp->name, rhp)) - rcu_cblist_dequeued_lazy(&rcl); + + rcu_lock_acquire(&rcu_callback_map); + trace_rcu_invoke_callback(rcu_state.name, rhp); + + f = rhp->func; + debug_rcu_head_callback(rhp); + WRITE_ONCE(rhp->func, (rcu_callback_t)0L); + f(rhp); + + rcu_lock_release(&rcu_callback_map); + /* * Stop only if limit reached and CPU has something to do. - * Note: The rcl structure counts down from zero. */ - if (-rcl.len >= bl && - (need_resched() || - (!is_idle_task(current) && !rcu_is_callbacks_kthread()))) - break; + 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 (rcu_do_batch_check_time(count, tlimit, jlimit_check, jlimit)) + break; + } else { + // In rcuc/rcuoc context, so no worries about + // depriving other softirq vectors of CPU cycles. + local_bh_enable(); + lockdep_assert_irqs_enabled(); + cond_resched_tasks_rcu_qs(); + lockdep_assert_irqs_enabled(); + local_bh_disable(); + // But rcuc kthreads can delay quiescent-state + // reporting, so check time limits for them. + if (rdp->rcu_cpu_kthread_status == RCU_KTHREAD_RUNNING && + rcu_do_batch_check_time(count, tlimit, jlimit_check, jlimit)) { + rdp->rcu_cpu_has_work = 1; + break; + } + } } - local_irq_save(flags); - count = -rcl.len; - trace_rcu_batch_end(rsp->name, count, !!rcl.head, need_resched(), - is_idle_task(current), rcu_is_callbacks_kthread()); + 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(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(). */ - rdp->n_cbs_invoked += count; - 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); - if (rdp->blimit == LONG_MAX && count <= qlowmark) + if (rdp->blimit >= DEFAULT_MAX_RCU_BLIMIT && count <= qlowmark) rdp->blimit = blimit; /* 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 = rsp->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; - WARN_ON_ONCE(rcu_segcblist_empty(&rdp->cblist) != (count == 0)); - local_irq_restore(flags); + /* + * The following usually indicates a double call_rcu(). To track + * this down, try building with CONFIG_DEBUG_OBJECTS_RCU_HEAD=y. + */ + empty = rcu_segcblist_empty(&rdp->cblist); + WARN_ON_ONCE(count == 0 && !empty); + WARN_ON_ONCE(!IS_ENABLED(CONFIG_RCU_NOCB_CPU) && + 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); - /* Re-invoke RCU core processing if there are callbacks remaining. */ - if (rcu_segcblist_ready_cbs(&rdp->cblist)) - invoke_rcu_core(); + rcu_nocb_unlock_irqrestore(rdp, flags); + + tick_dep_clear_task(current, TICK_DEP_BIT_RCU); } /* - * Check to see if this CPU is in a non-context-switch quiescent state - * (user mode or idle loop for rcu, non-softirq execution for rcu_bh). - * Also schedule RCU core processing. - * - * This function must be called from hardirq context. It is normally - * invoked from the scheduling-clock interrupt. + * This function is invoked from each scheduling-clock interrupt, + * and checks to see if this CPU is in a non-context-switch quiescent + * 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 the needed quiescent state. */ -void rcu_check_callbacks(int user) +void rcu_sched_clock_irq(int user) { - trace_rcu_utilization(TPS("Start scheduler-tick")); - increment_cpu_stall_ticks(); - if (user || rcu_is_cpu_rrupt_from_idle()) { - - /* - * Get here if this CPU took its interrupt from user - * mode or from the idle loop, and if this is not a - * nested interrupt. In this case, the CPU is in - * a quiescent state, so note it. - * - * No memory barrier is required here because both - * rcu_sched_qs() and rcu_bh_qs() reference only CPU-local - * variables that other CPUs neither access nor modify, - * at least not while the corresponding CPU is online. - */ - - rcu_sched_qs(); - rcu_bh_qs(); - - } else if (!in_softirq()) { - - /* - * Get here if this CPU did not take its interrupt from - * softirq, in other words, if it is not interrupting - * a rcu_bh read-side critical section. This is an _bh - * critical section, so note it. - */ + unsigned long j; - rcu_bh_qs(); + 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))) { + /* Idle and userspace execution already are quiescent states. */ + if (!rcu_is_cpu_rrupt_from_idle() && !user) + set_need_resched_current(); + __this_cpu_write(rcu_data.rcu_urgent_qs, false); } - rcu_preempt_check_callbacks(); - if (rcu_pending()) + rcu_flavor_sched_clock_irq(user); + if (rcu_pending(user)) invoke_rcu_core(); - if (user) + 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")); } /* - * Scan the leaf rcu_node structures, processing dyntick state for any that - * have not yet encountered a quiescent state, using the function specified. - * Also initiate boosting for any threads blocked on the root rcu_node. - * - * The caller must have suppressed start of new grace periods. + * Scan the leaf rcu_node structures. For each structure on which all + * CPUs have reported a quiescent state and on which there are tasks + * blocking the current grace period, initiate RCU priority boosting. + * Otherwise, invoke the specified function to check dyntick state for + * each CPU that has not yet reported a quiescent state. */ -static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp)) +static void force_qs_rnp(int (*f)(struct rcu_data *rdp)) { int cpu; unsigned long flags; - unsigned long mask; struct rcu_node *rnp; - rcu_for_each_leaf_node(rsp, rnp) { - cond_resched_rcu_qs(); - mask = 0; + rcu_state.cbovld = rcu_state.cbovldnext; + rcu_state.cbovldnext = false; + rcu_for_each_leaf_node(rnp) { + unsigned long mask = 0; + unsigned long rsmask = 0; + + cond_resched_tasks_rcu_qs(); raw_spin_lock_irqsave_rcu_node(rnp, flags); + rcu_state.cbovldnext |= !!rnp->cbovldmask; if (rnp->qsmask == 0) { - if (rcu_state_p == &rcu_sched_state || - rsp != rcu_state_p || - 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 @@ -2896,32 +2743,32 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp)) /* rcu_initiate_boost() releases rnp->lock */ continue; } - if (rnp->parent && - (rnp->parent->qsmask & rnp->grpmask)) { - /* - * Race between grace-period - * initialization and task exiting RCU - * read-side critical section: Report. - */ - rcu_report_unblock_qs_rnp(rsp, rnp, flags); - /* rcu_report_unblock_qs_rnp() rlses ->lock */ - continue; - } + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + continue; } - for_each_leaf_node_possible_cpu(rnp, cpu) { - unsigned long bit = leaf_node_cpu_bit(rnp, cpu); - if ((rnp->qsmask & bit) != 0) { - if (f(per_cpu_ptr(rsp->rda, cpu))) - mask |= bit; + for_each_leaf_node_cpu_mask(rnp, cpu, rnp->qsmask) { + struct rcu_data *rdp; + int ret; + + rdp = per_cpu_ptr(&rcu_data, cpu); + ret = f(rdp); + if (ret > 0) { + mask |= rdp->grpmask; + rcu_disable_urgency_upon_qs(rdp); } + if (ret < 0) + rsmask |= rdp->grpmask; } if (mask != 0) { - /* Idle/offline CPUs, report (releases rnp->lock. */ - rcu_report_qs_rnp(mask, rsp, rnp, rnp->gpnum, flags); + /* Idle/offline CPUs, report (releases rnp->lock). */ + rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags); } else { /* Nothing to do here, so just drop the lock. */ raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } + + for_each_leaf_node_cpu_mask(rnp, cpu, rsmask) + resched_cpu(cpu); } } @@ -2929,125 +2776,228 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp)) * Force quiescent states on reluctant CPUs, and also detect which * CPUs are in dyntick-idle mode. */ -static void force_quiescent_state(struct rcu_state *rsp) +void rcu_force_quiescent_state(void) { unsigned long flags; bool ret; struct rcu_node *rnp; struct rcu_node *rnp_old = NULL; + if (!rcu_gp_in_progress()) + return; /* Funnel through hierarchy to reduce memory contention. */ - rnp = __this_cpu_read(rsp->rda->mynode); + rnp = raw_cpu_read(rcu_data.mynode); for (; rnp != NULL; rnp = rnp->parent) { - ret = (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) || - !raw_spin_trylock(&rnp->fqslock); + ret = (READ_ONCE(rcu_state.gp_flags) & RCU_GP_FLAG_FQS) || + !raw_spin_trylock(&rnp->fqslock); if (rnp_old != NULL) raw_spin_unlock(&rnp_old->fqslock); - if (ret) { - rsp->n_force_qs_lh++; + if (ret) return; - } rnp_old = rnp; } - /* rnp_old == rcu_get_root(rsp), rnp == NULL. */ + /* rnp_old == rcu_get_root(), rnp == NULL. */ /* Reached the root of the rcu_node tree, acquire lock. */ raw_spin_lock_irqsave_rcu_node(rnp_old, flags); raw_spin_unlock(&rnp_old->fqslock); - if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) { - rsp->n_force_qs_lh++; + if (READ_ONCE(rcu_state.gp_flags) & RCU_GP_FLAG_FQS) { raw_spin_unlock_irqrestore_rcu_node(rnp_old, flags); return; /* Someone beat us to it. */ } - WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS); + WRITE_ONCE(rcu_state.gp_flags, rcu_state.gp_flags | RCU_GP_FLAG_FQS); raw_spin_unlock_irqrestore_rcu_node(rnp_old, flags); - rcu_gp_kthread_wake(rsp); + rcu_gp_kthread_wake(); +} +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(); } -/* - * This does the RCU core processing work for the specified rcu_state - * and rcu_data structures. This may be called only from the CPU to - * whom the rdp belongs. - */ -static void -__rcu_process_callbacks(struct rcu_state *rsp) +/* Perform RCU core processing work for the current CPU. */ +static __latent_entropy void rcu_core(void) { - unsigned long flags; - bool needwake; - struct rcu_data *rdp = raw_cpu_ptr(rsp->rda); + struct rcu_data *rdp = raw_cpu_ptr(&rcu_data); + struct rcu_node *rnp = rdp->mynode; + if (cpu_is_offline(smp_processor_id())) + return; + trace_rcu_utilization(TPS("Start RCU core")); WARN_ON_ONCE(!rdp->beenonline); - /* Update RCU state based on any recent quiescent states. */ - rcu_check_quiescent_state(rsp, rdp); + /* Report any deferred quiescent states if preemption enabled. */ + if (IS_ENABLED(CONFIG_PREEMPT_COUNT) && (!(preempt_count() & PREEMPT_MASK))) { + rcu_preempt_deferred_qs(current); + } else if (rcu_preempt_need_deferred_qs(current)) { + guard(irqsave)(); + set_need_resched_current(); + } - /* Does this CPU require a not-yet-started grace period? */ - local_irq_save(flags); - if (cpu_needs_another_gp(rsp, rdp)) { - raw_spin_lock_rcu_node(rcu_get_root(rsp)); /* irqs disabled. */ - needwake = rcu_start_gp(rsp); - raw_spin_unlock_irqrestore_rcu_node(rcu_get_root(rsp), flags); - if (needwake) - rcu_gp_kthread_wake(rsp); - } else { - local_irq_restore(flags); + /* Update RCU state based on any recent quiescent states. */ + rcu_check_quiescent_state(rdp); + + /* No grace period and unregistered callbacks? */ + if (!rcu_gp_in_progress() && + rcu_segcblist_is_enabled(&rdp->cblist) && !rcu_rdp_is_offloaded(rdp)) { + guard(irqsave)(); + if (!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) + rcu_accelerate_cbs_unlocked(rnp, rdp); } + rcu_check_gp_start_stall(rnp, rdp, rcu_jiffies_till_stall_check()); + /* If there are callbacks ready, invoke them. */ - if (rcu_segcblist_ready_cbs(&rdp->cblist)) - invoke_rcu_callbacks(rsp, rdp); + if (!rcu_rdp_is_offloaded(rdp) && 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); } -/* - * Do RCU core processing for the current CPU. - */ -static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused) +static void rcu_core_si(void) +{ + rcu_core(); +} + +static void rcu_wake_cond(struct task_struct *t, int status) { - struct rcu_state *rsp; + /* + * If the thread is yielding, only wake it when this + * is invoked from idle + */ + if (t && (status != RCU_KTHREAD_YIELDING || is_idle_task(current))) + wake_up_process(t); +} - if (cpu_is_offline(smp_processor_id())) - return; - trace_rcu_utilization(TPS("Start RCU core")); - for_each_rcu_flavor(rsp) - __rcu_process_callbacks(rsp); - trace_rcu_utilization(TPS("End RCU core")); +static void invoke_rcu_core_kthread(void) +{ + struct task_struct *t; + unsigned long flags; + + local_irq_save(flags); + __this_cpu_write(rcu_data.rcu_cpu_has_work, 1); + t = __this_cpu_read(rcu_data.rcu_cpu_kthread_task); + if (t != NULL && t != current) + rcu_wake_cond(t, __this_cpu_read(rcu_data.rcu_cpu_kthread_status)); + local_irq_restore(flags); } /* - * Schedule RCU callback invocation. If the specified type of RCU - * does not support RCU priority boosting, just do a direct call, - * otherwise wake up the per-CPU kernel kthread. Note that because we - * are running on the current CPU with softirqs disabled, the - * rcu_cpu_kthread_task cannot disappear out from under us. + * Wake up this CPU's rcuc kthread to do RCU core processing. */ -static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) +static void invoke_rcu_core(void) { - if (unlikely(!READ_ONCE(rcu_scheduler_fully_active))) - return; - if (likely(!rsp->boost)) { - rcu_do_batch(rsp, rdp); + if (!cpu_online(smp_processor_id())) return; + if (use_softirq) + raise_softirq(RCU_SOFTIRQ); + else + invoke_rcu_core_kthread(); +} + +static void rcu_cpu_kthread_park(unsigned int cpu) +{ + per_cpu(rcu_data.rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU; +} + +static int rcu_cpu_kthread_should_run(unsigned int cpu) +{ + return __this_cpu_read(rcu_data.rcu_cpu_has_work); +} + +/* + * Per-CPU kernel thread that invokes RCU callbacks. This replaces + * the RCU softirq used in configurations of RCU that do not support RCU + * priority boosting. + */ +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(); + work = *workp; + WRITE_ONCE(*workp, 0); + local_irq_enable(); + if (work) + rcu_core(); + local_bh_enable(); + if (!READ_ONCE(*workp)) { + trace_rcu_utilization(TPS("End CPU kthread@rcu_wait")); + *statusp = RCU_KTHREAD_WAITING; + return; + } } - invoke_rcu_callbacks_kthread(); + *statusp = RCU_KTHREAD_YIELDING; + trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield")); + 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 = { + .store = &rcu_data.rcu_cpu_kthread_task, + .thread_should_run = rcu_cpu_kthread_should_run, + .thread_fn = rcu_cpu_kthread, + .thread_comm = "rcuc/%u", + .setup = rcu_cpu_kthread_setup, + .park = rcu_cpu_kthread_park, +}; + +/* + * Spawn per-CPU RCU core processing kthreads. + */ +static int __init rcu_spawn_core_kthreads(void) +{ + int cpu; + + for_each_possible_cpu(cpu) + per_cpu(rcu_data.rcu_cpu_has_work, cpu) = 0; + 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; } -static void invoke_rcu_core(void) +static void rcutree_enqueue(struct rcu_data *rdp, struct rcu_head *head, rcu_callback_t func) { - if (cpu_online(smp_processor_id())) - raise_softirq(RCU_SOFTIRQ); + rcu_segcblist_enqueue(&rdp->cblist, head); + trace_rcu_callback(rcu_state.name, head, + rcu_segcblist_n_cbs(&rdp->cblist)); + trace_rcu_segcb_stats(&rdp->cblist, TPS("SegCBQueued")); } /* * Handle any core-RCU processing required by a call_rcu() invocation. */ -static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp, - struct rcu_head *head, unsigned long flags) +static void call_rcu_core(struct rcu_data *rdp, struct rcu_head *head, + rcu_callback_t func, unsigned long flags) { - bool needwake; - + rcutree_enqueue(rdp, head, func); /* * If called from an extended quiescent state, invoke the RCU * core in order to force a re-evaluation of RCU's idleness. @@ -3061,33 +3011,27 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp, /* * Force the grace period if too many callbacks or too long waiting. - * Enforce hysteresis, and don't invoke force_quiescent_state() + * Enforce hysteresis, and don't invoke rcu_force_quiescent_state() * if some other CPU has recently done so. Also, don't bother - * invoking force_quiescent_state() if the newly enqueued callback + * invoking rcu_force_quiescent_state() if the newly enqueued callback * is the only one waiting for a grace period to complete. */ if (unlikely(rcu_segcblist_n_cbs(&rdp->cblist) > rdp->qlen_last_fqs_check + qhimark)) { /* Are we ignoring a completed grace period? */ - note_gp_changes(rsp, rdp); + note_gp_changes(rdp); /* Start a new grace period if one not already started. */ - if (!rcu_gp_in_progress(rsp)) { - struct rcu_node *rnp_root = rcu_get_root(rsp); - - raw_spin_lock_rcu_node(rnp_root); - needwake = rcu_start_gp(rsp); - raw_spin_unlock_rcu_node(rnp_root); - if (needwake) - rcu_gp_kthread_wake(rsp); + if (!rcu_gp_in_progress()) { + rcu_accelerate_cbs_unlocked(rdp->mynode, rdp); } else { /* Give the grace period a kick. */ - rdp->blimit = LONG_MAX; - if (rsp->n_force_qs == rdp->n_force_qs_snap && + rdp->blimit = DEFAULT_MAX_RCU_BLIMIT; + if (READ_ONCE(rcu_state.n_force_qs) == rdp->n_force_qs_snap && rcu_segcblist_first_pend_cb(&rdp->cblist) != head) - force_quiescent_state(rsp); - rdp->n_force_qs_snap = rsp->n_force_qs; + rcu_force_quiescent_state(); + rdp->n_force_qs_snap = READ_ONCE(rcu_state.n_force_qs); rdp->qlen_last_fqs_check = rcu_segcblist_n_cbs(&rdp->cblist); } } @@ -3101,536 +3045,800 @@ 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 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); +} + static void -__call_rcu(struct rcu_head *head, rcu_callback_t func, - struct rcu_state *rsp, int cpu, bool lazy) +__call_rcu_common(struct rcu_head *head, rcu_callback_t func, bool lazy_in) { + static atomic_t doublefrees; unsigned long flags; + bool lazy; struct rcu_data *rdp; /* Misaligned rcu_head! */ WARN_ON_ONCE((unsigned long)head & (sizeof(void *) - 1)); + /* Avoid NULL dereference if callback is NULL. */ + if (WARN_ON_ONCE(!func)) + return; + if (debug_rcu_head_queue(head)) { /* * 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->%pF()!!!\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(head); + local_irq_save(flags); - rdp = this_cpu_ptr(rsp->rda); + rdp = this_cpu_ptr(&rcu_data); + RCU_LOCKDEP_WARN(!rcu_rdp_cpu_online(rdp), "Callback enqueued on offline CPU!"); + + lazy = lazy_in && !rcu_async_should_hurry(); /* Add the callback to our list. */ - if (unlikely(!rcu_segcblist_is_enabled(&rdp->cblist)) || cpu != -1) { - int offline; - - if (cpu != -1) - rdp = per_cpu_ptr(rsp->rda, cpu); - if (likely(rdp->mynode)) { - /* Post-boot, so this should be for a no-CBs CPU. */ - offline = !__call_rcu_nocb(rdp, head, lazy, flags); - WARN_ON_ONCE(offline); - /* Offline CPU, _call_rcu() illegal, leak callback. */ - local_irq_restore(flags); - return; - } - /* - * Very early boot, before rcu_init(). Initialize if needed - * and then drop through to queue the callback. - */ - BUG_ON(cpu != -1); + if (unlikely(!rcu_segcblist_is_enabled(&rdp->cblist))) { + // This can trigger due to call_rcu() from offline CPU: + WARN_ON_ONCE(rcu_scheduler_active != RCU_SCHEDULER_INACTIVE); WARN_ON_ONCE(!rcu_is_watching()); + // Very early boot, before rcu_init(). Initialize if needed + // and then drop through to queue the callback. if (rcu_segcblist_empty(&rdp->cblist)) rcu_segcblist_init(&rdp->cblist); } - rcu_segcblist_enqueue(&rdp->cblist, head, lazy); - if (!lazy) - rcu_idle_count_callbacks_posted(); - - if (__is_kfree_rcu_offset((unsigned long)func)) - trace_rcu_kfree_callback(rsp->name, head, (unsigned long)func, - rcu_segcblist_n_lazy_cbs(&rdp->cblist), - rcu_segcblist_n_cbs(&rdp->cblist)); - else - trace_rcu_callback(rsp->name, head, - rcu_segcblist_n_lazy_cbs(&rdp->cblist), - rcu_segcblist_n_cbs(&rdp->cblist)); - /* Go handle any RCU core processing required. */ - __call_rcu_core(rsp, rdp, head, flags); + check_cb_ovld(rdp); + + if (unlikely(rcu_rdp_is_offloaded(rdp))) + call_rcu_nocb(rdp, head, func, flags, lazy); + else + call_rcu_core(rdp, head, func, flags); local_irq_restore(flags); } +#ifdef CONFIG_RCU_LAZY +static bool enable_rcu_lazy __read_mostly = !IS_ENABLED(CONFIG_RCU_LAZY_DEFAULT_OFF); +module_param(enable_rcu_lazy, bool, 0444); + /** - * call_rcu_sched() - Queue an RCU for invocation after sched grace period. + * call_rcu_hurry() - Queue RCU callback for invocation after grace period, and + * flush all lazy callbacks (including the new one) to the main ->cblist while + * doing so. + * * @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 currently executing RCU - * read-side critical sections have completed. call_rcu_sched() assumes - * that the read-side critical sections end on enabling of preemption - * or on voluntary preemption. - * RCU read-side critical sections are delimited by : - * - rcu_read_lock_sched() and rcu_read_unlock_sched(), OR - * - anything that disables preemption. - * - * These may be nested. + * period elapses, in other words after all pre-existing RCU read-side + * critical sections have completed. * - * See the description of call_rcu() for more detailed information on - * memory ordering guarantees. + * Use this API instead of call_rcu() if you don't want the callback to be + * delayed for very long periods of time, which can happen on systems without + * memory pressure and on systems which are lightly loaded or mostly idle. + * This function will cause callbacks to be invoked sooner than later at the + * expense of extra power. Other than that, this function is identical to, and + * reuses call_rcu()'s logic. Refer to call_rcu() for more details about memory + * ordering and other functionality. */ -void call_rcu_sched(struct rcu_head *head, rcu_callback_t func) +void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func) { - __call_rcu(head, func, &rcu_sched_state, -1, 0); + __call_rcu_common(head, func, false); } -EXPORT_SYMBOL_GPL(call_rcu_sched); +EXPORT_SYMBOL_GPL(call_rcu_hurry); +#else +#define enable_rcu_lazy false +#endif /** - * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period. + * call_rcu() - Queue an RCU callback for invocation after a grace period. + * By default the callbacks are 'lazy' and are kept hidden from the main + * ->cblist to prevent starting of grace periods too soon. + * If you desire grace periods to start very soon, use call_rcu_hurry(). + * * @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 currently executing RCU - * read-side critical sections have completed. call_rcu_bh() assumes - * that the read-side critical sections end on completion of a softirq - * handler. This means that read-side critical sections in process - * context must not be interrupted by softirqs. This interface is to be - * used when most of the read-side critical sections are in softirq context. - * RCU read-side critical sections are delimited by : - * - rcu_read_lock() and rcu_read_unlock(), if in interrupt context. - * OR - * - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context. - * These may be nested. + * 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. + * + * It is perfectly legal to repost an RCU callback, potentially with + * a different callback function, from within its callback function. + * The specified function will be invoked after another full grace period + * has elapsed. This use case is similar in form to the common practice + * of reposting a timer from within its own handler. + * + * 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. * - * See the description of call_rcu() for more detailed information on - * memory ordering guarantees. + * 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. + * + * Specific to call_rcu() (as opposed to the other call_rcu*() functions), + * in kernels built with CONFIG_RCU_LAZY=y, call_rcu() might delay for many + * seconds before starting the grace period needed by the corresponding + * callback. This delay can significantly improve energy-efficiency + * on low-utilization battery-powered devices. To avoid this delay, + * in latency-sensitive kernel code, use call_rcu_hurry(). */ -void call_rcu_bh(struct rcu_head *head, rcu_callback_t func) +void call_rcu(struct rcu_head *head, rcu_callback_t func) { - __call_rcu(head, func, &rcu_bh_state, -1, 0); + __call_rcu_common(head, func, enable_rcu_lazy); } -EXPORT_SYMBOL_GPL(call_rcu_bh); +EXPORT_SYMBOL_GPL(call_rcu); /* - * Queue an RCU callback for lazy invocation after a grace period. - * This will likely be later named something like "call_rcu_lazy()", - * but this change will require some way of tagging the lazy RCU - * callbacks in the list of pending callbacks. Until then, this - * function may only be called from __kfree_rcu(). + * During early boot, any blocking grace-period wait automatically + * implies a grace period. + * + * 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. */ -void kfree_call_rcu(struct rcu_head *head, - rcu_callback_t func) +static int rcu_blocking_is_gp(void) { - __call_rcu(head, func, rcu_state_p, -1, 1); + if (rcu_scheduler_active != RCU_SCHEDULER_INACTIVE) { + might_sleep(); + return false; + } + return true; } -EXPORT_SYMBOL_GPL(kfree_call_rcu); /* - * Because a context switch is a grace period for RCU-sched and RCU-bh, - * 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_sched() or synchronize_rcu_bh(). 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. + * Helper function for the synchronize_rcu() API. */ -static inline int rcu_blocking_is_gp(void) +static void synchronize_rcu_normal(void) { - int ret; + struct rcu_synchronize rs; - might_sleep(); /* Check for RCU read-side critical section. */ - preempt_disable(); - ret = num_online_cpus() <= 1; - preempt_enable(); - return ret; + trace_rcu_sr_normal(rcu_state.name, &rs.head, TPS("request")); + + if (READ_ONCE(rcu_normal_wake_from_gp) < 1) { + wait_rcu_gp(call_rcu_hurry); + goto trace_complete_out; + } + + init_rcu_head_on_stack(&rs.head); + init_completion(&rs.completion); + + /* + * This code might be preempted, therefore take a GP + * snapshot before adding a request. + */ + if (IS_ENABLED(CONFIG_PROVE_RCU)) + get_state_synchronize_rcu_full(&rs.oldstate); + + rcu_sr_normal_add_req(&rs); + + /* Kick a GP and start waiting. */ + (void) start_poll_synchronize_rcu(); + + /* Now we can wait. */ + wait_for_completion(&rs.completion); + destroy_rcu_head_on_stack(&rs.head); + +trace_complete_out: + trace_rcu_sr_normal(rcu_state.name, &rs.head, TPS("complete")); } /** - * synchronize_sched - wait until an rcu-sched grace period has elapsed. + * synchronize_rcu - wait until a grace period has elapsed. * - * Control will return to the caller some time after a full rcu-sched - * grace period has elapsed, in other words after all currently executing - * rcu-sched read-side critical sections have completed. These read-side - * critical sections are delimited by rcu_read_lock_sched() and - * rcu_read_unlock_sched(), and may be nested. Note that preempt_disable(), - * local_irq_disable(), and so on may be used in place of - * rcu_read_lock_sched(). + * Control will return to the caller some time after a full grace + * period has elapsed, in other words after all currently executing RCU + * 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. * - * This means that all preempt_disable code sequences, including NMI and - * non-threaded hardware-interrupt handlers, in progress on entry will - * have completed before this primitive returns. However, this does not - * guarantee that softirq handlers will have completed, since in some - * kernels, these handlers can run in process context, and can block. + * 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 this guarantee implies further memory-ordering guarantees. - * On systems with more than one CPU, when synchronize_sched() returns, - * each CPU is guaranteed to have executed a full memory barrier since the - * end of its last RCU-sched read-side critical section whose beginning - * preceded the call to synchronize_sched(). In addition, each CPU having + * On systems with more than one CPU, when synchronize_rcu() returns, + * 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 synchronize_rcu(). In addition, each CPU having * an RCU read-side critical section that extends beyond the return from - * synchronize_sched() is guaranteed to have executed a full memory barrier - * after the beginning of synchronize_sched() and before the beginning of + * synchronize_rcu() is guaranteed to have executed a full memory barrier + * after the beginning of synchronize_rcu() and 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 synchronize_sched(), which returned + * Furthermore, if CPU A invoked synchronize_rcu(), which returned * to its caller on CPU B, then both CPU A and CPU B are guaranteed * to have executed a full memory barrier during the execution of - * synchronize_sched() -- even if CPU A and CPU B are the same CPU (but + * 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_sched(void) +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_sched() in RCU-sched read-side critical section"); - if (rcu_blocking_is_gp()) + "Illegal synchronize_rcu() in RCU read-side critical section"); + if (!rcu_blocking_is_gp()) { + if (rcu_gp_is_expedited()) + synchronize_rcu_expedited(); + else + synchronize_rcu_normal(); return; - if (rcu_gp_is_expedited()) - synchronize_sched_expedited(); - else - wait_rcu_gp(call_rcu_sched); + } + + // 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_sched); +EXPORT_SYMBOL_GPL(synchronize_rcu); /** - * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed. + * get_completed_synchronize_rcu_full - Return a full pre-completed polled state cookie + * @rgosp: Place to put state cookie * - * Control will return to the caller some time after a full rcu_bh grace - * period has elapsed, in other words after all currently executing rcu_bh - * read-side critical sections have completed. RCU read-side critical - * sections are delimited by rcu_read_lock_bh() and rcu_read_unlock_bh(), - * and may be nested. - * - * See the description of synchronize_sched() for more detailed information - * on memory ordering guarantees. + * 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 synchronize_rcu_bh(void) +void get_completed_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp) { - 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_bh() in RCU-bh read-side critical section"); - if (rcu_blocking_is_gp()) - return; - if (rcu_gp_is_expedited()) - synchronize_rcu_bh_expedited(); - else - wait_rcu_gp(call_rcu_bh); + rgosp->rgos_norm = RCU_GET_STATE_COMPLETED; + rgosp->rgos_exp = RCU_GET_STATE_COMPLETED; } -EXPORT_SYMBOL_GPL(synchronize_rcu_bh); +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) { /* * Any prior manipulation of RCU-protected data must happen - * before the load from ->gpnum. + * before the load from ->gp_seq. */ smp_mb(); /* ^^^ */ - - /* - * Make sure this load happens before the purportedly - * time-consuming work between get_state_synchronize_rcu() - * and cond_synchronize_rcu(). - */ - return smp_load_acquire(&rcu_state_p->gpnum); + 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. * - * 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. - * - * 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. + * This does not guarantee that the needed grace period will actually + * start. */ -void cond_synchronize_rcu(unsigned long oldstate) +void get_state_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp) { - unsigned long newstate; - /* - * Ensure that this load happens before any RCU-destructive - * actions the caller might carry out after we return. + * Any prior manipulation of RCU-protected data must happen + * before the loads from ->gp_seq and ->expedited_sequence. */ - newstate = smp_load_acquire(&rcu_state_p->completed); - if (ULONG_CMP_GE(oldstate, newstate)) - synchronize_rcu(); + smp_mb(); /* ^^^ */ + + // Yes, rcu_state.gp_seq, not rnp_root->gp_seq, the latter's use + // in poll_state_synchronize_rcu_full() notwithstanding. Use of + // the latter here would result in too-short grace periods due to + // interactions with newly onlined CPUs. + rgosp->rgos_norm = rcu_seq_snap(&rcu_state.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; + + 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(); } -EXPORT_SYMBOL_GPL(cond_synchronize_rcu); /** - * get_state_synchronize_sched - Snapshot current RCU-sched state + * start_poll_synchronize_rcu - Snapshot and start RCU grace period * - * Returns a cookie that is used by a later call to cond_synchronize_sched() - * to determine whether or not a full grace period has elapsed in the - * meantime. + * 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. */ -unsigned long get_state_synchronize_sched(void) +unsigned long start_poll_synchronize_rcu(void) { - /* - * Any prior manipulation of RCU-protected data must happen - * before the load from ->gpnum. - */ - smp_mb(); /* ^^^ */ + unsigned long gp_seq = get_state_synchronize_rcu(); - /* - * Make sure this load happens before the purportedly - * time-consuming work between get_state_synchronize_sched() - * and cond_synchronize_sched(). - */ - return smp_load_acquire(&rcu_sched_state.gpnum); + 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. + */ +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(get_state_synchronize_sched); +EXPORT_SYMBOL_GPL(start_poll_synchronize_rcu_full); /** - * cond_synchronize_sched - Conditionally wait for an RCU-sched grace period + * poll_state_synchronize_rcu - Has the specified RCU grace period completed? + * @oldstate: value from get_state_synchronize_rcu() or start_poll_synchronize_rcu() * - * @oldstate: return value from earlier call to get_state_synchronize_sched() + * 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 either cond_synchronize_rcu() or cond_synchronize_rcu_expedited() + * on the one hand or by directly invoking either synchronize_rcu() or + * synchronize_rcu_expedited() on the other. * - * If a full RCU-sched grace period has elapsed since the earlier call to - * get_state_synchronize_sched(), just return. Otherwise, invoke - * synchronize_sched() 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 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. * - * Yes, this function does not take counter wrap into account. But - * counter wrap is harmless. If the counter wraps, we have waited for + * In addition, because oldstate compresses the grace-period state for + * both normal and expedited grace periods into a single unsigned long, + * it can miss a grace period when synchronize_rcu() runs concurrently + * with synchronize_rcu_expedited(). If this is unacceptable, please + * instead use the _full() variant of these polling APIs. + * + * 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() 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 * 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_sched(unsigned long oldstate) +void cond_synchronize_rcu(unsigned long oldstate) { - unsigned long newstate; + if (!poll_state_synchronize_rcu(oldstate)) + synchronize_rcu(); +} +EXPORT_SYMBOL_GPL(cond_synchronize_rcu); - /* - * Ensure that this load happens before any RCU-destructive - * actions the caller might carry out after we return. - */ - newstate = smp_load_acquire(&rcu_sched_state.completed); - if (ULONG_CMP_GE(oldstate, newstate)) - synchronize_sched(); +/** + * 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_sched); +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, for the specified type of RCU, returning 1 if so. - * The checks are in order of increasing expense: checks that can be - * carried out against CPU-local state are performed first. However, - * we must check for CPU stalls first, else we might not get a chance. + * 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 + * in order of increasing expense: checks that can be carried out against + * CPU-local state are performed first. However, we must check for CPU + * stalls first, else we might not get a chance. */ -static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) +static int rcu_pending(int user) { + bool gp_in_progress; + struct rcu_data *rdp = this_cpu_ptr(&rcu_data); struct rcu_node *rnp = rdp->mynode; - rdp->n_rcu_pending++; + lockdep_assert_irqs_disabled(); /* Check for CPU stalls, if enabled. */ - check_cpu_stall(rsp, rdp); + check_cpu_stall(rdp); - /* Is this CPU a NO_HZ_FULL CPU that should ignore RCU? */ - if (rcu_nohz_full_cpu(rsp)) + /* Does this CPU need a deferred NOCB wakeup? */ + 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.) */ + gp_in_progress = rcu_gp_in_progress(); + if ((user || rcu_is_cpu_rrupt_from_idle() || + (gp_in_progress && + time_before(jiffies, READ_ONCE(rcu_state.gp_start) + + nohz_full_patience_delay_jiffies))) && + rcu_nohz_full_cpu()) return 0; /* Is the RCU core waiting for a quiescent state from this CPU? */ - if (rcu_scheduler_fully_active && - rdp->core_needs_qs && rdp->cpu_no_qs.b.norm && - rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_dynticks.rcu_qs_ctr)) { - rdp->n_rp_core_needs_qs++; - } else if (rdp->core_needs_qs && !rdp->cpu_no_qs.b.norm) { - rdp->n_rp_report_qs++; + if (rdp->core_needs_qs && !rdp->cpu_no_qs.b.norm && gp_in_progress) return 1; - } /* Does this CPU have callbacks ready to invoke? */ - if (rcu_segcblist_ready_cbs(&rdp->cblist)) { - rdp->n_rp_cb_ready++; + 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 (cpu_needs_another_gp(rsp, rdp)) { - rdp->n_rp_cpu_needs_gp++; - return 1; - } - - /* Has another RCU grace period completed? */ - if (READ_ONCE(rnp->completed) != rdp->completed) { /* outside lock */ - rdp->n_rp_gp_completed++; - return 1; - } - - /* Has a new RCU grace period started? */ - if (READ_ONCE(rnp->gpnum) != rdp->gpnum || - unlikely(READ_ONCE(rdp->gpwrap))) { /* outside lock */ - rdp->n_rp_gp_started++; + if (!gp_in_progress && rcu_segcblist_is_enabled(&rdp->cblist) && + !rcu_rdp_is_offloaded(rdp) && + !rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) return 1; - } - /* Does this CPU need a deferred NOCB wakeup? */ - if (rcu_nocb_need_deferred_wakeup(rdp)) { - rdp->n_rp_nocb_defer_wakeup++; + /* Have RCU grace period completed or started? */ + if (rcu_seq_current(&rnp->gp_seq) != rdp->gp_seq || + unlikely(READ_ONCE(rdp->gpwrap))) /* outside lock */ return 1; - } /* nothing to do */ - rdp->n_rp_need_nothing++; return 0; } /* - * Check to see if there is any immediate RCU-related work to be done - * by the current CPU, returning 1 if so. This function is part of the - * RCU implementation; it is -not- an exported member of the RCU API. - */ -static int rcu_pending(void) -{ - struct rcu_state *rsp; - - for_each_rcu_flavor(rsp) - if (__rcu_pending(rsp, this_cpu_ptr(rsp->rda))) - return 1; - return 0; -} - -/* - * Return true if the specified CPU has any callback. If all_lazy is - * non-NULL, store an indication of whether all callbacks are lazy. - * (If there are no callbacks, all of them are deemed to be lazy.) - */ -static bool __maybe_unused rcu_cpu_has_callbacks(bool *all_lazy) -{ - bool al = true; - bool hc = false; - struct rcu_data *rdp; - struct rcu_state *rsp; - - for_each_rcu_flavor(rsp) { - rdp = this_cpu_ptr(rsp->rda); - if (rcu_segcblist_empty(&rdp->cblist)) - continue; - hc = true; - if (rcu_segcblist_n_nonlazy_cbs(&rdp->cblist) || !all_lazy) { - al = false; - break; - } - } - if (all_lazy) - *all_lazy = al; - return hc; -} - -/* - * Helper function for _rcu_barrier() tracing. If tracing is disabled, + * Helper function for rcu_barrier() tracing. If tracing is disabled, * the compiler is expected to optimize this away. */ -static void _rcu_barrier_trace(struct rcu_state *rsp, const char *s, - int cpu, unsigned long done) +static void rcu_barrier_trace(const char *s, int cpu, unsigned long done) { - trace_rcu_barrier(rsp->name, s, cpu, - atomic_read(&rsp->barrier_cpu_count), done); + trace_rcu_barrier(rcu_state.name, s, cpu, + atomic_read(&rcu_state.barrier_cpu_count), done); } /* - * RCU callback function for _rcu_barrier(). If we are last, wake - * up the task executing _rcu_barrier(). + * 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) { - struct rcu_data *rdp = container_of(rhp, struct rcu_data, barrier_head); - struct rcu_state *rsp = rdp->rsp; + unsigned long __maybe_unused s = rcu_state.barrier_sequence; - if (atomic_dec_and_test(&rsp->barrier_cpu_count)) { - _rcu_barrier_trace(rsp, "LastCB", -1, rsp->barrier_sequence); - complete(&rsp->barrier_completion); + rhp->next = rhp; // Mark the callback as having been invoked. + if (atomic_dec_and_test(&rcu_state.barrier_cpu_count)) { + rcu_barrier_trace(TPS("LastCB"), -1, s); + complete(&rcu_state.barrier_completion); } else { - _rcu_barrier_trace(rsp, "CB", -1, rsp->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 *type) +static void rcu_barrier_entrain(struct rcu_data *rdp) { - struct rcu_state *rsp = type; - struct rcu_data *rdp = raw_cpu_ptr(rsp->rda); + unsigned long gseq = READ_ONCE(rcu_state.barrier_sequence); + unsigned long lseq = READ_ONCE(rdp->barrier_seq_snap); + bool wake_nocb = false; + bool was_alldone = false; - _rcu_barrier_trace(rsp, "IRQ", -1, rsp->barrier_sequence); + 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); - if (rcu_segcblist_entrain(&rdp->cblist, &rdp->barrier_head, 0)) { - atomic_inc(&rsp->barrier_cpu_count); + rcu_nocb_lock(rdp); + /* + * Flush bypass and wakeup rcuog if we add callbacks to an empty regular + * queue. This way we don't wait for bypass timer that can reach seconds + * if it's fully lazy. + */ + was_alldone = rcu_rdp_is_offloaded(rdp) && !rcu_segcblist_pend_cbs(&rdp->cblist); + WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies, false)); + wake_nocb = was_alldone && rcu_segcblist_pend_cbs(&rdp->cblist); + if (rcu_segcblist_entrain(&rdp->cblist, &rdp->barrier_head)) { + atomic_inc(&rcu_state.barrier_cpu_count); } else { debug_rcu_head_unqueue(&rdp->barrier_head); - _rcu_barrier_trace(rsp, "IRQNQ", -1, rsp->barrier_sequence); + rcu_barrier_trace(TPS("IRQNQ"), -1, rcu_state.barrier_sequence); } + rcu_nocb_unlock(rdp); + if (wake_nocb) + wake_nocb_gp(rdp, false); + smp_store_release(&rdp->barrier_seq_snap, gseq); } /* - * Orchestrate the specified type of RCU barrier, waiting for all - * RCU callbacks of the specified type to complete. + * Called with preemption disabled, and from cross-cpu IRQ context. */ -static void _rcu_barrier(struct rcu_state *rsp) +static void rcu_barrier_handler(void *cpu_in) { - int cpu; + 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); +} + +/** + * rcu_barrier - Wait until all in-flight call_rcu() callbacks complete. + * + * Note that this primitive does not necessarily wait for an RCU grace period + * to complete. For example, if there are no RCU callbacks queued anywhere + * in the system, then rcu_barrier() is within its rights to return + * immediately, without waiting for anything, much less an RCU grace period. + * In fact, rcu_barrier() will normally not result in any RCU grace periods + * beyond those that were already destined to be executed. + * + * In kernels built with CONFIG_RCU_LAZY=y, this function also hurries all + * pending lazy RCU callbacks. + */ +void rcu_barrier(void) +{ + uintptr_t cpu; + unsigned long flags; + unsigned long gseq; struct rcu_data *rdp; - unsigned long s = rcu_seq_snap(&rsp->barrier_sequence); + unsigned long s = rcu_seq_snap(&rcu_state.barrier_sequence); - _rcu_barrier_trace(rsp, "Begin", -1, s); + rcu_barrier_trace(TPS("Begin"), -1, s); /* Take mutex to serialize concurrent rcu_barrier() requests. */ - mutex_lock(&rsp->barrier_mutex); + mutex_lock(&rcu_state.barrier_mutex); /* Did someone else do our work for us? */ - if (rcu_seq_done(&rsp->barrier_sequence, s)) { - _rcu_barrier_trace(rsp, "EarlyExit", -1, rsp->barrier_sequence); + if (rcu_seq_done(&rcu_state.barrier_sequence, s)) { + rcu_barrier_trace(TPS("EarlyExit"), -1, rcu_state.barrier_sequence); smp_mb(); /* caller's subsequent code after above check. */ - mutex_unlock(&rsp->barrier_mutex); + mutex_unlock(&rcu_state.barrier_mutex); return; } /* Mark the start of the barrier operation. */ - rcu_seq_start(&rsp->barrier_sequence); - _rcu_barrier_trace(rsp, "Inc1", -1, rsp->barrier_sequence); + 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(&rsp->barrier_completion); - atomic_set(&rsp->barrier_cpu_count, 1); - get_online_cpus(); + init_completion(&rcu_state.barrier_completion); + 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. @@ -3638,88 +3846,279 @@ static void _rcu_barrier(struct rcu_state *rsp) * corresponding CPU's preceding callbacks have been invoked. */ for_each_possible_cpu(cpu) { - if (!cpu_online(cpu) && !rcu_is_nocb_cpu(cpu)) + rdp = per_cpu_ptr(&rcu_data, cpu); +retry: + if (smp_load_acquire(&rdp->barrier_seq_snap) == gseq) continue; - rdp = per_cpu_ptr(rsp->rda, cpu); - if (rcu_is_nocb_cpu(cpu)) { - if (!rcu_nocb_cpu_needs_barrier(rsp, cpu)) { - _rcu_barrier_trace(rsp, "OfflineNoCB", cpu, - rsp->barrier_sequence); - } else { - _rcu_barrier_trace(rsp, "OnlineNoCB", cpu, - rsp->barrier_sequence); - smp_mb__before_atomic(); - atomic_inc(&rsp->barrier_cpu_count); - __call_rcu(&rdp->barrier_head, - rcu_barrier_callback, rsp, cpu, 0); - } - } else if (rcu_segcblist_n_cbs(&rdp->cblist)) { - _rcu_barrier_trace(rsp, "OnlineQ", cpu, - rsp->barrier_sequence); - smp_call_function_single(cpu, rcu_barrier_func, rsp, 1); - } else { - _rcu_barrier_trace(rsp, "OnlineNQ", cpu, - rsp->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(&rsp->barrier_cpu_count)) - complete(&rsp->barrier_completion); + 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. */ - wait_for_completion(&rsp->barrier_completion); + wait_for_completion(&rcu_state.barrier_completion); /* Mark the end of the barrier operation. */ - _rcu_barrier_trace(rsp, "Inc2", -1, rsp->barrier_sequence); - rcu_seq_end(&rsp->barrier_sequence); + 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(&rsp->barrier_mutex); + mutex_unlock(&rcu_state.barrier_mutex); } +EXPORT_SYMBOL_GPL(rcu_barrier); + +static unsigned long rcu_barrier_last_throttle; /** - * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete. + * rcu_barrier_throttled - Do rcu_barrier(), but limit to one per second + * + * This can be thought of as guard rails around rcu_barrier() that + * permits unrestricted userspace use, at least assuming the hardware's + * try_cmpxchg() is robust. There will be at most one call per second to + * rcu_barrier() system-wide from use of this function, which means that + * callers might needlessly wait a second or three. + * + * This is intended for use by test suites to avoid OOM by flushing RCU + * callbacks from the previous test before starting the next. See the + * rcutree.do_rcu_barrier module parameter for more information. + * + * Why not simply make rcu_barrier() more scalable? That might be + * the eventual endpoint, but let's keep it simple for the time being. + * Note that the module parameter infrastructure serializes calls to a + * given .set() function, but should concurrent .set() invocation ever be + * possible, we are ready! */ -void rcu_barrier_bh(void) +static void rcu_barrier_throttled(void) { - _rcu_barrier(&rcu_bh_state); + unsigned long j = jiffies; + unsigned long old = READ_ONCE(rcu_barrier_last_throttle); + unsigned long s = rcu_seq_snap(&rcu_state.barrier_sequence); + + while (time_in_range(j, old, old + HZ / 16) || + !try_cmpxchg(&rcu_barrier_last_throttle, &old, j)) { + schedule_timeout_idle(HZ / 16); + if (rcu_seq_done(&rcu_state.barrier_sequence, s)) { + smp_mb(); /* caller's subsequent code after above check. */ + return; + } + j = jiffies; + old = READ_ONCE(rcu_barrier_last_throttle); + } + rcu_barrier(); } -EXPORT_SYMBOL_GPL(rcu_barrier_bh); -/** - * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks. +/* + * Invoke rcu_barrier_throttled() when a rcutree.do_rcu_barrier + * request arrives. We insist on a true value to allow for possible + * future expansion. */ -void rcu_barrier_sched(void) +static int param_set_do_rcu_barrier(const char *val, const struct kernel_param *kp) { - _rcu_barrier(&rcu_sched_state); + bool b; + int ret; + + if (rcu_scheduler_active != RCU_SCHEDULER_RUNNING) + return -EAGAIN; + ret = kstrtobool(val, &b); + if (!ret && b) { + atomic_inc((atomic_t *)kp->arg); + rcu_barrier_throttled(); + atomic_dec((atomic_t *)kp->arg); + } + return ret; +} + +/* + * Output the number of outstanding rcutree.do_rcu_barrier requests. + */ +static int param_get_do_rcu_barrier(char *buffer, const struct kernel_param *kp) +{ + return sprintf(buffer, "%d\n", atomic_read((atomic_t *)kp->arg)); +} + +static const struct kernel_param_ops do_rcu_barrier_ops = { + .set = param_set_do_rcu_barrier, + .get = param_get_do_rcu_barrier, +}; +static atomic_t do_rcu_barrier; +module_param_cb(do_rcu_barrier, &do_rcu_barrier_ops, &do_rcu_barrier, 0644); + +/* + * Compute the mask of online CPUs for the specified rcu_node structure. + * This will not be stable unless the rcu_node structure's ->lock is + * held, but the bit corresponding to the current CPU will be stable + * in most contexts. + */ +static unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp) +{ + return READ_ONCE(rnp->qsmaskinitnext); +} + +/* + * 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)); +} + +bool rcu_cpu_online(int cpu) +{ + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); + + return rcu_rdp_cpu_online(rdp); +} + +#if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) + +/* + * Is the current CPU online as far as RCU is concerned? + * + * Disable preemption to avoid false positives that could otherwise + * happen due to the current CPU number being sampled, this task being + * preempted, its old CPU being taken offline, resuming on some other CPU, + * then determining that its old CPU is now offline. + * + * Disable checking if in an NMI handler because we cannot safely + * report errors from NMI handlers anyway. In addition, it is OK to use + * RCU on an offline processor during initial boot, hence the check for + * rcu_scheduler_fully_active. + */ +bool notrace rcu_lockdep_current_cpu_online(void) +{ + struct rcu_data *rdp; + bool ret = false; + + if (in_nmi() || !rcu_scheduler_fully_active) + return true; + preempt_disable_notrace(); + rdp = this_cpu_ptr(&rcu_data); + /* + * Strictly, we care here about the case where the current CPU is + * in rcutree_report_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_notrace(); + return ret; +} +EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online); + +#endif /* #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) */ + +// 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 !!READ_ONCE(rcu_state.n_online_cpus); +} + +/* + * All CPUs for the specified rcu_node structure have gone offline, + * and all tasks that were preempted within an RCU read-side critical + * section while running on one of those CPUs have since exited their RCU + * read-side critical section. Some other CPU is reporting this fact with + * the specified rcu_node structure's ->lock held and interrupts disabled. + * This function therefore goes up the tree of rcu_node structures, + * clearing the corresponding bits in the ->qsmaskinit fields. Note that + * the leaf rcu_node structure's ->qsmaskinit field has already been + * updated. + * + * This function does check that the specified rcu_node structure has + * all CPUs offline and no blocked tasks, so it is OK to invoke it + * prematurely. That said, invoking it after the fact will cost you + * a needless lock acquisition. So once it has done its work, don't + * invoke it again. + */ +static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf) +{ + long mask; + struct rcu_node *rnp = rnp_leaf; + + raw_lockdep_assert_held_rcu_node(rnp_leaf); + if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) || + WARN_ON_ONCE(rnp_leaf->qsmaskinit) || + WARN_ON_ONCE(rcu_preempt_has_tasks(rnp_leaf))) + return; + for (;;) { + mask = rnp->grpmask; + rnp = rnp->parent; + if (!rnp) + break; + raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ + rnp->qsmaskinit &= ~mask; + /* Between grace periods, so better already be zero! */ + WARN_ON_ONCE(rnp->qsmask); + if (rnp->qsmaskinit) { + raw_spin_unlock_rcu_node(rnp); + /* irqs remain disabled. */ + return; + } + raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ + } } -EXPORT_SYMBOL_GPL(rcu_barrier_sched); /* * 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) { long mask; + long oldmask; struct rcu_node *rnp = rnp_leaf; - lockdep_assert_held(&rnp->lock); + raw_lockdep_assert_held_rcu_node(rnp_leaf); + WARN_ON_ONCE(rnp->wait_blkd_tasks); for (;;) { mask = rnp->grpmask; rnp = rnp->parent; if (rnp == NULL) return; raw_spin_lock_rcu_node(rnp); /* Interrupts already disabled. */ + oldmask = rnp->qsmaskinit; rnp->qsmaskinit |= mask; raw_spin_unlock_rcu_node(rnp); /* Interrupts remain disabled. */ + if (oldmask) + return; } } @@ -3727,93 +4126,161 @@ static void rcu_init_new_rnp(struct rcu_node *rnp_leaf) * Do boot-time initialization of a CPU's per-CPU RCU data. */ static void __init -rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) +rcu_boot_init_percpu_data(int cpu) { - unsigned long flags; - struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); - struct rcu_node *rnp = rcu_get_root(rsp); + 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. */ - raw_spin_lock_irqsave_rcu_node(rnp, flags); rdp->grpmask = leaf_node_cpu_bit(rdp->mynode, cpu); - rdp->dynticks = &per_cpu(rcu_dynticks, cpu); - WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_EXIT_IDLE); - WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp->dynticks))); + INIT_WORK(&rdp->strict_work, strict_work_handler); + WARN_ON_ONCE(ct->nesting != 1); + WARN_ON_ONCE(rcu_watching_snap_in_eqs(ct_rcu_watching_cpu(cpu))); + rdp->barrier_seq_snap = rcu_state.barrier_sequence; + rdp->rcu_ofl_gp_seq = rcu_state.gp_seq; + rdp->rcu_ofl_gp_state = RCU_GP_CLEANED; + rdp->rcu_onl_gp_seq = rcu_state.gp_seq; + rdp->rcu_onl_gp_state = RCU_GP_CLEANED; + rdp->last_sched_clock = jiffies; rdp->cpu = cpu; - rdp->rsp = rsp; rcu_boot_init_nocb_percpu_data(rdp); - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); +} + +static void rcu_thread_affine_rnp(struct task_struct *t, struct rcu_node *rnp) +{ + cpumask_var_t affinity; + int cpu; + + if (!zalloc_cpumask_var(&affinity, GFP_KERNEL)) + return; + + for_each_leaf_node_possible_cpu(rnp, cpu) + cpumask_set_cpu(cpu, affinity); + + kthread_affine_preferred(t, affinity); + + free_cpumask_var(affinity); +} + +struct kthread_worker *rcu_exp_gp_kworker; + +static void rcu_spawn_exp_par_gp_kworker(struct rcu_node *rnp) +{ + struct kthread_worker *kworker; + const char *name = "rcu_exp_par_gp_kthread_worker/%d"; + struct sched_param param = { .sched_priority = kthread_prio }; + int rnp_index = rnp - rcu_get_root(); + + if (rnp->exp_kworker) + return; + + kworker = kthread_create_worker(0, name, rnp_index); + if (IS_ERR_OR_NULL(kworker)) { + pr_err("Failed to create par gp kworker on %d/%d\n", + rnp->grplo, rnp->grphi); + return; + } + WRITE_ONCE(rnp->exp_kworker, kworker); + + if (IS_ENABLED(CONFIG_RCU_EXP_KTHREAD)) + sched_setscheduler_nocheck(kworker->task, SCHED_FIFO, ¶m); + + rcu_thread_affine_rnp(kworker->task, rnp); + wake_up_process(kworker->task); +} + +static void __init rcu_start_exp_gp_kworker(void) +{ + const char *name = "rcu_exp_gp_kthread_worker"; + struct sched_param param = { .sched_priority = kthread_prio }; + + rcu_exp_gp_kworker = kthread_run_worker(0, name); + if (IS_ERR_OR_NULL(rcu_exp_gp_kworker)) { + pr_err("Failed to create %s!\n", name); + rcu_exp_gp_kworker = NULL; + return; + } + + if (IS_ENABLED(CONFIG_RCU_EXP_KTHREAD)) + sched_setscheduler_nocheck(rcu_exp_gp_kworker->task, SCHED_FIFO, ¶m); +} + +static void rcu_spawn_rnp_kthreads(struct rcu_node *rnp) +{ + if (rcu_scheduler_fully_active) { + mutex_lock(&rnp->kthread_mutex); + rcu_spawn_one_boost_kthread(rnp); + rcu_spawn_exp_par_gp_kworker(rnp); + mutex_unlock(&rnp->kthread_mutex); + } } /* - * Initialize a CPU's per-CPU RCU data. Note that only one online or - * offline event can be happening at a given time. Note also that we - * can accept some slop in the rsp->completed access due to the fact - * that this CPU cannot possibly have any RCU callbacks in flight yet. + * Invoked early in the CPU-online process, when pretty much all services + * are available. The incoming CPU is not present. + * + * Initializes a CPU's per-CPU RCU data. Note that only one online or + * offline event can be happening at a given time. Note also that we can + * accept some slop in the rsp->gp_seq access due to the fact that this + * CPU cannot possibly have any non-offloaded RCU callbacks in flight yet. + * And any offloaded callbacks are being numbered elsewhere. */ -static void -rcu_init_percpu_data(int cpu, struct rcu_state *rsp) +int rcutree_prepare_cpu(unsigned int cpu) { unsigned long flags; - struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); - struct rcu_node *rnp = rcu_get_root(rsp); + 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 = rsp->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? */ - !init_nocb_callback_list(rdp)) - rcu_segcblist_init(&rdp->cblist); /* Re-enable callbacks. */ - rdp->dynticks->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; - rcu_dynticks_eqs_online(); + ct->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. */ rnp = rdp->mynode; raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ - if (!rdp->beenonline) - WRITE_ONCE(rsp->ncpus, READ_ONCE(rsp->ncpus) + 1); - rdp->beenonline = true; /* We have now been online. */ - rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */ - rdp->completed = rnp->completed; + rdp->gp_seq = READ_ONCE(rnp->gp_seq); + rdp->gp_seq_needed = rdp->gp_seq; rdp->cpu_no_qs.b.norm = true; - rdp->rcu_qs_ctr_snap = per_cpu(rcu_dynticks.rcu_qs_ctr, cpu); rdp->core_needs_qs = false; - trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl")); + rdp->rcu_iw_pending = false; + 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); -} - -/* - * Invoked early in the CPU-online process, when pretty much all - * services are available. The incoming CPU is not present. - */ -int rcutree_prepare_cpu(unsigned int cpu) -{ - struct rcu_state *rsp; - - for_each_rcu_flavor(rsp) - rcu_init_percpu_data(cpu, rsp); - rcu_prepare_kthreads(cpu); - rcu_spawn_all_nocb_kthreads(cpu); + rcu_preempt_deferred_qs_init(rdp); + rcu_spawn_rnp_kthreads(rnp); + rcu_spawn_cpu_nocb_kthread(cpu); + ASSERT_EXCLUSIVE_WRITER(rcu_state.n_online_cpus); + WRITE_ONCE(rcu_state.n_online_cpus, rcu_state.n_online_cpus + 1); return 0; } /* - * Update RCU priority boot kthread affinity for CPU-hotplug changes. + * Has the specified (known valid) CPU ever been fully online? */ -static void rcutree_affinity_setting(unsigned int cpu, int outgoing) +bool rcu_cpu_beenfullyonline(int cpu) { - struct rcu_data *rdp = per_cpu_ptr(rcu_state_p->rda, cpu); + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); - rcu_boost_kthread_setaffinity(rdp->mynode, outgoing); + return smp_load_acquire(&rdp->beenonline); } /* @@ -3822,48 +4289,20 @@ static void rcutree_affinity_setting(unsigned int cpu, int outgoing) */ int rcutree_online_cpu(unsigned int cpu) { - sync_sched_exp_online_cleanup(cpu); - rcutree_affinity_setting(cpu, -1); - if (IS_ENABLED(CONFIG_TREE_SRCU)) - srcu_online_cpu(cpu); - return 0; -} - -/* - * Near the beginning of the process. The CPU is still very much alive - * with pretty much all services enabled. - */ -int rcutree_offline_cpu(unsigned int cpu) -{ - rcutree_affinity_setting(cpu, cpu); - if (IS_ENABLED(CONFIG_TREE_SRCU)) - srcu_offline_cpu(cpu); - return 0; -} - -/* - * Near the end of the offline process. We do only tracing here. - */ -int rcutree_dying_cpu(unsigned int cpu) -{ - struct rcu_state *rsp; - - for_each_rcu_flavor(rsp) - rcu_cleanup_dying_cpu(rsp); - return 0; -} + unsigned long flags; + struct rcu_data *rdp; + struct rcu_node *rnp; -/* - * The outgoing CPU is gone and we are running elsewhere. - */ -int rcutree_dead_cpu(unsigned int cpu) -{ - struct rcu_state *rsp; + rdp = per_cpu_ptr(&rcu_data, cpu); + rnp = rdp->mynode; + raw_spin_lock_irqsave_rcu_node(rnp, flags); + rnp->ffmask |= rdp->grpmask; + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE) + return 0; /* Too early in boot for scheduler work. */ - for_each_rcu_flavor(rsp) { - rcu_cleanup_dead_cpu(cpu, rsp); - do_nocb_deferred_wakeup(per_cpu_ptr(rsp->rda, cpu)); - } + // Stop-machine done, so allow nohz_full to disable tick. + tick_dep_clear(TICK_DEP_BIT_RCU); return 0; } @@ -3877,67 +4316,225 @@ int rcutree_dead_cpu(unsigned int cpu) * Note that this function is special in that it is invoked directly * from the incoming CPU rather than from the cpuhp_step mechanism. * This is because this function must be invoked at a precise location. + * This incoming CPU must not have enabled interrupts yet. + * + * This mirrors the effects of rcutree_report_cpu_dead(). */ -void rcu_cpu_starting(unsigned int cpu) +void rcutree_report_cpu_starting(unsigned int cpu) { - unsigned long flags; unsigned long mask; struct rcu_data *rdp; struct rcu_node *rnp; - struct rcu_state *rsp; + bool newcpu; - for_each_rcu_flavor(rsp) { - rdp = per_cpu_ptr(rsp->rda, cpu); - rnp = rdp->mynode; - mask = rdp->grpmask; - raw_spin_lock_irqsave_rcu_node(rnp, flags); - rnp->qsmaskinitnext |= mask; - rnp->expmaskinitnext |= mask; - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + lockdep_assert_irqs_disabled(); + rdp = per_cpu_ptr(&rcu_data, cpu); + if (rdp->cpu_started) + return; + rdp->cpu_started = true; + + rnp = rdp->mynode; + mask = rdp->grpmask; + arch_spin_lock(&rcu_state.ofl_lock); + rcu_watching_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; + /* Allow lockless access for expedited grace periods. */ + 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_state = READ_ONCE(rcu_state.gp_state); + + /* 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 flags; + + local_irq_save(flags); + rcu_disable_urgency_upon_qs(rdp); + /* Report QS -after- changing ->qsmaskinitnext! */ + rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags); + } else { + raw_spin_unlock_rcu_node(rnp); } + arch_spin_unlock(&rcu_state.ofl_lock); + smp_store_release(&rdp->beenonline, true); + smp_mb(); /* Ensure RCU read-side usage follows above initialization. */ } -#ifdef CONFIG_HOTPLUG_CPU /* - * The CPU is exiting the idle loop into the arch_cpu_idle_dead() - * function. We now remove it from the rcu_node tree's ->qsmaskinit - * bit masks. + * The outgoing function has no further need of RCU, so remove it from + * the rcu_node tree's ->qsmaskinitnext bit masks. + * + * Note that this function is special in that it is invoked directly + * from the outgoing CPU rather than from the cpuhp_step mechanism. + * This is because this function must be invoked at a precise location. + * + * This mirrors the effect of rcutree_report_cpu_starting(). */ -static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp) +void rcutree_report_cpu_dead(void) { unsigned long flags; unsigned long mask; - struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); + struct rcu_data *rdp = this_cpu_ptr(&rcu_data); struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */ + /* + * IRQS must be disabled from now on and until the CPU dies, or an interrupt + * may introduce a new READ-side while it is actually off the QS masks. + */ + lockdep_assert_irqs_disabled(); + /* + * CPUHP_AP_SMPCFD_DYING was the last call for rcu_exp_handler() execution. + * The requested QS must have been reported on the last context switch + * from stop machine to idle. + */ + WARN_ON_ONCE(rdp->cpu_no_qs.b.exp); + // Do any dangling deferred wakeups. + do_nocb_deferred_wakeup(rdp); + + rcu_preempt_deferred_qs(current); + /* Remove outgoing CPU from mask in the leaf rcu_node structure. */ mask = rdp->grpmask; + + /* + * Hold the ofl_lock and rnp lock to avoid races between CPU going + * offline and doing a QS report (as below), versus rcu_gp_init(). + * See Requirements.rst > Hotplug CPU > Concurrent QS Reporting section + * for more details. + */ + arch_spin_lock(&rcu_state.ofl_lock); raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */ - rnp->qsmaskinitnext &= ~mask; + rdp->rcu_ofl_gp_seq = READ_ONCE(rcu_state.gp_seq); + rdp->rcu_ofl_gp_state = READ_ONCE(rcu_state.gp_state); + 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); + } + /* Clear from ->qsmaskinitnext to mark offline. */ + WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext & ~mask); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + arch_spin_unlock(&rcu_state.ofl_lock); + rdp->cpu_started = false; } +#ifdef CONFIG_HOTPLUG_CPU /* - * The outgoing function has no further need of RCU, so remove it from - * the list of CPUs that RCU must track. - * - * Note that this function is special in that it is invoked directly - * from the outgoing CPU rather than from the cpuhp_step mechanism. - * This is because this function must be invoked at a precise location. + * 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 + * operation. Migrate the outgoing CPU's callbacks to the current CPU. + */ +void rcutree_migrate_callbacks(int cpu) +{ + unsigned long flags; + struct rcu_data *my_rdp; + struct rcu_node *my_rnp; + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); + bool needwake; + + if (rcu_rdp_is_offloaded(rdp)) + return; + + raw_spin_lock_irqsave(&rcu_state.barrier_lock, flags); + if (rcu_segcblist_empty(&rdp->cblist)) { + raw_spin_unlock_irqrestore(&rcu_state.barrier_lock, flags); + return; /* No callbacks to migrate. */ + } + + 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. */ + WARN_ON_ONCE(!rcu_nocb_flush_bypass(my_rdp, NULL, jiffies, false)); + raw_spin_lock_rcu_node(my_rnp); /* irqs already disabled. */ + /* Leverage recent GPs and set GP for new callbacks. */ + 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)); + 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 { + rcu_nocb_unlock(my_rdp); /* irqs remain disabled. */ + raw_spin_unlock_rcu_node(my_rnp); /* irqs remain disabled. */ + } + local_irq_restore(flags); + if (needwake) + rcu_gp_kthread_wake(); + lockdep_assert_irqs_enabled(); + WARN_ONCE(rcu_segcblist_n_cbs(&rdp->cblist) != 0 || + !rcu_segcblist_empty(&rdp->cblist), + "rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, 1stCB=%p\n", + cpu, rcu_segcblist_n_cbs(&rdp->cblist), + rcu_segcblist_first_cb(&rdp->cblist)); +} + +/* + * The CPU has been completely removed, and some other CPU is reporting + * this fact from process context. Do the remainder of the cleanup. + * There can only be one CPU hotplug operation at a time, so no need for + * explicit locking. + */ +int rcutree_dead_cpu(unsigned int cpu) +{ + ASSERT_EXCLUSIVE_WRITER(rcu_state.n_online_cpus); + WRITE_ONCE(rcu_state.n_online_cpus, rcu_state.n_online_cpus - 1); + // Stop-machine done, so allow nohz_full to disable tick. + tick_dep_clear(TICK_DEP_BIT_RCU); + return 0; +} + +/* + * Near the end of the offline process. Trace the fact that this CPU + * is going offline. */ -void rcu_report_dead(unsigned int cpu) +int rcutree_dying_cpu(unsigned int cpu) { - struct rcu_state *rsp; + bool blkd; + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); + struct rcu_node *rnp = rdp->mynode; - /* QS for any half-done expedited RCU-sched GP. */ - preempt_disable(); - rcu_report_exp_rdp(&rcu_sched_state, - this_cpu_ptr(rcu_sched_state.rda), true); - preempt_enable(); - for_each_rcu_flavor(rsp) - rcu_cleanup_dying_idle_cpu(cpu, rsp); + blkd = !!(READ_ONCE(rnp->qsmask) & rdp->grpmask); + trace_rcu_grace_period(rcu_state.name, READ_ONCE(rnp->gp_seq), + blkd ? TPS("cpuofl-bgp") : TPS("cpuofl")); + return 0; } -#endif + +/* + * Near the beginning of the process. The CPU is still very much alive + * with pretty much all services enabled. + */ +int rcutree_offline_cpu(unsigned int cpu) +{ + unsigned long flags; + struct rcu_data *rdp; + struct rcu_node *rnp; + + rdp = per_cpu_ptr(&rcu_data, cpu); + rnp = rdp->mynode; + raw_spin_lock_irqsave_rcu_node(rnp, flags); + rnp->ffmask &= ~rdp->grpmask; + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + + // nohz_full CPUs need the tick for stop-machine to work quickly + tick_dep_set(TICK_DEP_BIT_RCU); + return 0; +} +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ /* * On non-huge systems, use expedited RCU grace periods to make suspend @@ -3949,13 +4546,13 @@ static int rcu_pm_notify(struct notifier_block *self, switch (action) { case PM_HIBERNATION_PREPARE: case PM_SUSPEND_PREPARE: - if (nr_cpu_ids <= 256) /* Expediting bad for large systems. */ - rcu_expedite_gp(); + rcu_async_hurry(); + rcu_expedite_gp(); break; case PM_POST_HIBERNATION: case PM_POST_SUSPEND: - if (nr_cpu_ids <= 256) /* Expediting bad for large systems. */ - rcu_unexpedite_gp(); + rcu_unexpedite_gp(); + rcu_async_relax(); break; default: break; @@ -3964,44 +4561,43 @@ static int rcu_pm_notify(struct notifier_block *self, } /* - * Spawn the kthreads that handle each RCU flavor's grace periods. + * 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 rcu_state *rsp; struct sched_param sp; struct task_struct *t; - - /* Force priority into range. */ - 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; - for_each_rcu_flavor(rsp) { - t = kthread_create(rcu_gp_kthread, rsp, "%s", rsp->name); - BUG_ON(IS_ERR(t)); - rnp = rcu_get_root(rsp); - raw_spin_lock_irqsave_rcu_node(rnp, flags); - rsp->gp_kthread = t; - if (kthread_prio) { - sp.sched_priority = kthread_prio; - sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); - } - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - wake_up_process(t); + t = kthread_create(rcu_gp_kthread, NULL, "%s", rcu_state.name); + if (WARN_ONCE(IS_ERR(t), "%s: Could not start grace-period kthread, OOM is now expected behavior\n", __func__)) + return 0; + if (kthread_prio) { + sp.sched_priority = kthread_prio; + sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); } - rcu_spawn_nocb_kthreads(); - rcu_spawn_boost_kthreads(); + rnp = rcu_get_root(); + raw_spin_lock_irqsave_rcu_node(rnp, flags); + 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); + /* 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_rnp_kthreads(rdp->mynode); + rcu_spawn_core_kthreads(); + /* Create kthread worker for expedited GPs */ + rcu_start_exp_gp_kworker(); return 0; } early_initcall(rcu_spawn_gp_kthread); @@ -4018,17 +4614,28 @@ 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(); } /* - * Helper function for rcu_init() that initializes one rcu_state structure. + * Helper function for rcu_init() that initializes the rcu_state structure. */ -static void __init rcu_init_one(struct rcu_state *rsp) +static void __init rcu_init_one(void) { static const char * const buf[] = RCU_NODE_NAME_INIT; static const char * const fqs[] = RCU_FQS_NAME_INIT; @@ -4050,14 +4657,15 @@ static void __init rcu_init_one(struct rcu_state *rsp) /* Initialize the level-tracking arrays. */ for (i = 1; i < rcu_num_lvls; i++) - rsp->level[i] = rsp->level[i - 1] + num_rcu_lvl[i - 1]; + rcu_state.level[i] = + rcu_state.level[i - 1] + num_rcu_lvl[i - 1]; rcu_init_levelspread(levelspread, num_rcu_lvl); /* Initialize the elements themselves, starting from the leaves. */ for (i = rcu_num_lvls - 1; i >= 0; i--) { cpustride *= levelspread[i]; - rnp = rsp->level[i]; + rnp = rcu_state.level[i]; for (j = 0; j < num_rcu_lvl[i]; j++, rnp++) { raw_spin_lock_init(&ACCESS_PRIVATE(rnp, lock)); lockdep_set_class_and_name(&ACCESS_PRIVATE(rnp, lock), @@ -4065,8 +4673,9 @@ static void __init rcu_init_one(struct rcu_state *rsp) raw_spin_lock_init(&rnp->fqslock); lockdep_set_class_and_name(&rnp->fqslock, &rcu_fqs_class[i], fqs[i]); - rnp->gpnum = rsp->gpnum; - rnp->completed = rsp->completed; + rnp->gp_seq = rcu_state.gp_seq; + rnp->gp_seq_needed = rcu_state.gp_seq; + rnp->completedqs = rcu_state.gp_seq; rnp->qsmask = 0; rnp->qsmaskinit = 0; rnp->grplo = j * cpustride; @@ -4079,8 +4688,8 @@ static void __init rcu_init_one(struct rcu_state *rsp) rnp->parent = NULL; } else { rnp->grpnum = j % levelspread[i - 1]; - rnp->grpmask = 1UL << rnp->grpnum; - rnp->parent = rsp->level[i - 1] + + rnp->grpmask = BIT(rnp->grpnum); + rnp->parent = rcu_state.level[i - 1] + j / levelspread[i - 1]; } rnp->level = i; @@ -4091,19 +4700,46 @@ static void __init rcu_init_one(struct rcu_state *rsp) init_waitqueue_head(&rnp->exp_wq[2]); init_waitqueue_head(&rnp->exp_wq[3]); spin_lock_init(&rnp->exp_lock); + mutex_init(&rnp->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); } } - init_swait_queue_head(&rsp->gp_wq); - init_swait_queue_head(&rsp->expedited_wq); - rnp = rsp->level[rcu_num_lvls - 1]; + init_swait_queue_head(&rcu_state.gp_wq); + init_swait_queue_head(&rcu_state.expedited_wq); + rnp = rcu_first_leaf_node(); for_each_possible_cpu(i) { while (i > rnp->grphi) rnp++; - per_cpu_ptr(rsp->rda, i)->mynode = rnp; - rcu_boot_init_percpu_data(i, rsp); + per_cpu_ptr(&rcu_data, i)->mynode = rnp; + per_cpu_ptr(&rcu_data, i)->barrier_head.next = + &per_cpu_ptr(&rcu_data, i)->barrier_head; + rcu_boot_init_percpu_data(i); } - list_add(&rsp->flavors, &rcu_struct_flavors); +} + +/* + * 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); } /* @@ -4111,11 +4747,25 @@ static void __init rcu_init_one(struct rcu_state *rsp) * 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. @@ -4129,12 +4779,13 @@ static void __init rcu_init_geometry(void) jiffies_till_first_fqs = d; if (jiffies_till_next_fqs == ULONG_MAX) jiffies_till_next_fqs = d; + adjust_jiffies_till_sched_qs(); /* If the compile-time values are accurate, just leave. */ if (rcu_fanout_leaf == RCU_FANOUT_LEAF && nr_cpu_ids == NR_CPUS) return; - pr_info("RCU: Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%d\n", + pr_info("Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%u\n", rcu_fanout_leaf, nr_cpu_ids); /* @@ -4143,8 +4794,7 @@ static void __init rcu_init_geometry(void) * Complain and fall back to the compile-time values if this * limit is exceeded. */ - if (rcu_fanout_leaf < 2 || - rcu_fanout_leaf > sizeof(unsigned long) * 8) { + if (rcu_fanout_leaf < 2 || rcu_fanout_leaf > BITS_PER_LONG) { rcu_fanout_leaf = RCU_FANOUT_LEAF; WARN_ON(1); return; @@ -4187,16 +4837,16 @@ static void __init rcu_init_geometry(void) /* * Dump out the structure of the rcu_node combining tree associated - * with the rcu_state structure referenced by rsp. + * with the rcu_state structure. */ -static void __init rcu_dump_rcu_node_tree(struct rcu_state *rsp) +static void __init rcu_dump_rcu_node_tree(void) { int level = 0; struct rcu_node *rnp; pr_info("rcu_node tree layout dump\n"); pr_info(" "); - rcu_for_each_node_breadth_first(rsp, rnp) { + rcu_for_each_node_breadth_first(rnp) { if (rnp->level != level) { pr_cont("\n"); pr_info(" "); @@ -4207,20 +4857,22 @@ static void __init rcu_dump_rcu_node_tree(struct rcu_state *rsp) pr_cont("\n"); } +struct workqueue_struct *rcu_gp_wq; + void __init rcu_init(void) { - int cpu; + int cpu = smp_processor_id(); rcu_early_boot_tests(); rcu_bootup_announce(); + sanitize_kthread_prio(); rcu_init_geometry(); - rcu_init_one(&rcu_bh_state); - rcu_init_one(&rcu_sched_state); + rcu_init_one(); if (dump_tree) - rcu_dump_rcu_node_tree(&rcu_sched_state); - __rcu_init_preempt(); - open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); + rcu_dump_rcu_node_tree(); + if (use_softirq) + open_softirq(RCU_SOFTIRQ, rcu_core_si); /* * We don't need protection against CPU-hotplug here because @@ -4228,13 +4880,40 @@ 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); - if (IS_ENABLED(CONFIG_TREE_SRCU)) - srcu_online_cpu(cpu); + WARN_ON(num_online_cpus() > 1); // Only one CPU this early in boot. + rcutree_prepare_cpu(cpu); + rcutree_report_cpu_starting(cpu); + rcutree_online_cpu(cpu); + + /* Create workqueue for Tree SRCU and for expedited GPs. */ + rcu_gp_wq = alloc_workqueue("rcu_gp", WQ_MEM_RECLAIM | WQ_PERCPU, 0); + WARN_ON(!rcu_gp_wq); + + sync_wq = alloc_workqueue("sync_wq", WQ_MEM_RECLAIM | WQ_UNBOUND, 0); + WARN_ON(!sync_wq); + + /* Respect if explicitly disabled via a boot parameter. */ + if (rcu_normal_wake_from_gp < 0) { + if (num_possible_cpus() <= WAKE_FROM_GP_CPU_THRESHOLD) + rcu_normal_wake_from_gp = 1; } + + /* 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 in case any polled grace periods started early. + (void)start_poll_synchronize_rcu_expedited(); + + rcu_test_sync_prims(); + + tasks_cblist_init_generic(); } +#include "tree_stall.h" #include "tree_exp.h" +#include "tree_nocb.h" #include "tree_plugin.h" |