/* * 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. * * Copyright IBM Corporation, 2008 * * Authors: Dipankar Sarma * Manfred Spraul * Paul E. McKenney Hierarchical version * * Based on the original work by Paul McKenney * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen. * * For detailed explanation of Read-Copy Update mechanism see - * Documentation/RCU */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include "tree.h" #include "rcu.h" #ifdef MODULE_PARAM_PREFIX #undef MODULE_PARAM_PREFIX #endif #define MODULE_PARAM_PREFIX "rcutree." /* Data structures. */ /* * 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__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 #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, \ .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); /* Dump rcu_node combining tree at boot to verify correct setup. */ static bool dump_tree; module_param(dump_tree, bool, 0444); /* Control rcu_node-tree auto-balancing at boot time. */ static bool rcu_fanout_exact; module_param(rcu_fanout_exact, bool, 0444); /* Increase (but not decrease) the RCU_FANOUT_LEAF at boot time. */ static int rcu_fanout_leaf = RCU_FANOUT_LEAF; module_param(rcu_fanout_leaf, int, 0444); 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 * RCU_SCHEDULER_INACTIVE and transitions RCU_SCHEDULER_INIT just before the * first task is spawned. So when this variable is RCU_SCHEDULER_INACTIVE, * RCU can assume that there is but one task, allowing RCU to (for example) * optimize synchronize_rcu() to a simple barrier(). When this variable * is RCU_SCHEDULER_INIT, RCU must actually do all the hard work required * to detect real grace periods. This variable is also used to suppress * boot-time false positives from lockdep-RCU error checking. Finally, it * transitions from RCU_SCHEDULER_INIT to RCU_SCHEDULER_RUNNING after RCU * is fully initialized, including all of its kthreads having been spawned. */ int rcu_scheduler_active __read_mostly; EXPORT_SYMBOL_GPL(rcu_scheduler_active); /* * The rcu_scheduler_fully_active variable transitions from zero to one * during the early_initcall() processing, which is after the scheduler * is capable of creating new tasks. So RCU processing (for example, * creating tasks for RCU priority boosting) must be delayed until after * rcu_scheduler_fully_active transitions from zero to one. We also * currently delay invocation of any RCU callbacks until after this point. * * It might later prove better for people registering RCU callbacks during * early boot to take responsibility for these callbacks, but one step at * a time. */ 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 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); /* rcuc/rcub kthread realtime priority */ static int kthread_prio = IS_ENABLED(CONFIG_RCU_BOOST) ? 1 : 0; module_param(kthread_prio, int, 0644); /* Delay in jiffies for grace-period initialization delays, debug only. */ static int gp_preinit_delay; module_param(gp_preinit_delay, int, 0444); static int gp_init_delay; module_param(gp_init_delay, int, 0444); static int gp_cleanup_delay; module_param(gp_cleanup_delay, int, 0444); /* * Number of grace periods between delays, normalized by the duration of * the delay. The longer the delay, the more the grace periods between * each delay. The reason for this normalization is that it means that, * for non-zero delays, the overall slowdown of grace periods is constant * regardless of the duration of the delay. This arrangement balances * 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); } /* * 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 = 1, .dynticks_nmi_nesting = DYNTICK_IRQ_NONIDLE, .dynticks = ATOMIC_INIT(RCU_DYNTICK_CTRL_CTR), }; /* * Record entry into an extended quiescent state. This is only to be * called when not already in an extended quiescent state. */ static void rcu_dynticks_eqs_enter(void) { struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); int seq; /* * CPUs seeing atomic_add_return() must see prior RCU read-side * critical sections, and we also must force ordering with the * next idle sojourn. */ seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &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)); } /* * Record exit from an extended quiescent state. This is only to be * called from an extended quiescent state. */ static void rcu_dynticks_eqs_exit(void) { struct rcu_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(); } } /* * Reset the current CPU's ->dynticks counter to indicate that the * newly onlined CPU is no longer in an extended quiescent state. * This will either leave the counter unchanged, or increment it * 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, * or when the corresponding CPU is offline. */ static void rcu_dynticks_eqs_online(void) { struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); if (atomic_read(&rdtp->dynticks) & RCU_DYNTICK_CTRL_CTR) return; atomic_add(RCU_DYNTICK_CTRL_CTR, &rdtp->dynticks); } /* * 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() * indicates that RCU is in an extended quiescent state. */ static bool rcu_dynticks_in_eqs(int snap) { return !(snap & RCU_DYNTICK_CTRL_CTR); } /* * 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. */ static bool rcu_dynticks_in_eqs_since(struct rcu_dynticks *rdtp, int snap) { return snap != rcu_dynticks_snap(rdtp); } /* * Do a double-increment of the ->dynticks counter to emulate a * momentary idle-CPU quiescent state. */ static void rcu_dynticks_momentary_idle(void) { struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); int special = atomic_add_return(2 * RCU_DYNTICK_CTRL_CTR, &rdtp->dynticks); /* It is illegal to call this from idle state. */ WARN_ON_ONCE(!(special & RCU_DYNTICK_CTRL_CTR)); } /* * 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; } /* * Let the RCU core know that this CPU has gone through the scheduler, * which is a quiescent state. This is called when the need for a * quiescent state is urgent, so we burn an atomic operation and full * memory barriers to let the RCU core know about it, regardless of what * this CPU might (or might not) do in the near future. * * We inform the RCU core by emulating a zero-duration dyntick-idle period. * * The caller must have disabled interrupts. */ static void rcu_momentary_dyntick_idle(void) { raw_cpu_write(rcu_dynticks.rcu_need_heavy_qs, false); rcu_dynticks_momentary_idle(); } /* * 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); /* * 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. * * 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. * */ void rcu_all_qs(void) { unsigned long flags; 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); } 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(); } EXPORT_SYMBOL_GPL(rcu_all_qs); #define DEFAULT_RCU_BLIMIT 10 /* Maximum callbacks per rcu_do_batch. */ static long blimit = DEFAULT_RCU_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. */ static long qlowmark = DEFAULT_RCU_QLOMARK; module_param(blimit, long, 0444); module_param(qhimark, long, 0444); module_param(qlowmark, long, 0444); static ulong jiffies_till_first_fqs = ULONG_MAX; static ulong jiffies_till_next_fqs = ULONG_MAX; static bool rcu_kick_kthreads; module_param(jiffies_till_first_fqs, ulong, 0644); module_param(jiffies_till_next_fqs, ulong, 0644); module_param(rcu_kick_kthreads, bool, 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 / 10; module_param(jiffies_till_sched_qs, ulong, 0444); 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); /* * Return the number of RCU batches started thus far for debug & stats. */ unsigned long rcu_batches_started(void) { return rcu_state_p->gpnum; } EXPORT_SYMBOL_GPL(rcu_batches_started); /* * 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; } 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) { return rcu_bh_state.gpnum; } EXPORT_SYMBOL_GPL(rcu_batches_started_bh); /* * Return the number of RCU batches completed thus far for debug & stats. */ unsigned long rcu_batches_completed(void) { return rcu_state_p->completed; } 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) { return rcu_sched_state.completed; } EXPORT_SYMBOL_GPL(rcu_batches_completed_sched); /* * Return the number of RCU BH batches completed thus far for debug & stats. */ unsigned long rcu_batches_completed_bh(void) { return rcu_bh_state.completed; } EXPORT_SYMBOL_GPL(rcu_batches_completed_bh); /* * Return the number of RCU expedited batches completed thus far for * debug & stats. Odd numbers mean that a batch is in progress, even * numbers mean idle. The value returned will thus be roughly double * the cumulative batches since boot. */ unsigned long rcu_exp_batches_completed(void) { return rcu_state_p->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. */ void rcu_bh_force_quiescent_state(void) { force_quiescent_state(&rcu_bh_state); } 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) { 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); } 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) { rcutorture_vernum++; } EXPORT_SYMBOL_GPL(rcutorture_record_progress); /* * Return the root node of the specified rcu_state structure. */ static struct rcu_node *rcu_get_root(struct rcu_state *rsp) { return &rsp->node[0]; } /* * Enter an RCU extended quiescent state, which can be either the * idle loop or adaptive-tickless usermode execution. * * We crowbar the ->dynticks_nmi_nesting field to zero to allow for * the possibility of usermode upcalls having messed up our count * of interrupt nesting level during the prior busy period. */ static void rcu_eqs_enter(bool user) { struct rcu_state *rsp; struct rcu_data *rdp; struct rcu_dynticks *rdtp; rdtp = this_cpu_ptr(&rcu_dynticks); WRITE_ONCE(rdtp->dynticks_nmi_nesting, 0); WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && rdtp->dynticks_nesting == 0); if (rdtp->dynticks_nesting != 1) { rdtp->dynticks_nesting--; return; } lockdep_assert_irqs_disabled(); trace_rcu_dyntick(TPS("Start"), rdtp->dynticks_nesting, 0, rdtp->dynticks); WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current)); for_each_rcu_flavor(rsp) { rdp = this_cpu_ptr(rsp->rda); do_nocb_deferred_wakeup(rdp); } rcu_prepare_for_idle(); WRITE_ONCE(rdtp->dynticks_nesting, 0); /* Avoid irq-access tearing. */ rcu_dynticks_eqs_enter(); rcu_dynticks_task_enter(); } /** * rcu_idle_enter - inform RCU that current CPU is entering idle * * Enter idle mode, in other words, -leave- the mode in which RCU * read-side critical sections can occur. (Though RCU read-side * critical sections can occur in irq handlers in idle, a possibility * handled by irq_enter() and irq_exit().) * * If you add or remove a call to rcu_idle_enter(), be sure to test with * CONFIG_RCU_EQS_DEBUG=y. */ void rcu_idle_enter(void) { lockdep_assert_irqs_disabled(); rcu_eqs_enter(false); } #ifdef CONFIG_NO_HZ_FULL /** * rcu_user_enter - inform RCU that we are resuming userspace. * * Enter RCU idle mode right before resuming userspace. No use of RCU * is permitted between this call and rcu_user_exit(). This way the * CPU doesn't need to maintain the tick for RCU maintenance purposes * when the CPU runs in userspace. * * If you add or remove a call to rcu_user_enter(), be sure to test with * CONFIG_RCU_EQS_DEBUG=y. */ void rcu_user_enter(void) { lockdep_assert_irqs_disabled(); rcu_eqs_enter(true); } #endif /* CONFIG_NO_HZ_FULL */ /** * 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. * * If you add or remove a call to rcu_nmi_exit(), be sure to test * with CONFIG_RCU_EQS_DEBUG=y. */ void rcu_nmi_exit(void) { 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) { trace_rcu_dyntick(TPS("--="), rdtp->dynticks_nmi_nesting, rdtp->dynticks_nmi_nesting - 2, rdtp->dynticks); WRITE_ONCE(rdtp->dynticks_nmi_nesting, /* No store tearing. */ rdtp->dynticks_nmi_nesting - 2); return; } /* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */ trace_rcu_dyntick(TPS("Startirq"), rdtp->dynticks_nmi_nesting, 0, rdtp->dynticks); WRITE_ONCE(rdtp->dynticks_nmi_nesting, 0); /* Avoid store tearing. */ rcu_dynticks_eqs_enter(); } /** * rcu_irq_exit - inform RCU that current CPU is exiting irq towards idle * * Exit from an interrupt handler, which might possibly result in entering * idle mode, in other words, leaving the mode in which read-side critical * sections can occur. The caller must have disabled interrupts. * * This code assumes that the idle loop never does anything that might * result in unbalanced calls to irq_enter() and irq_exit(). If your * architecture's idle loop violates this assumption, RCU will give you what * you deserve, good and hard. But very infrequently and irreproducibly. * * Use things like work queues to work around this limitation. * * You have been warned. * * If you add or remove a call to rcu_irq_exit(), be sure to test with * CONFIG_RCU_EQS_DEBUG=y. */ void rcu_irq_exit(void) { struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); lockdep_assert_irqs_disabled(); if (rdtp->dynticks_nmi_nesting == 1) rcu_prepare_for_idle(); rcu_nmi_exit(); if (rdtp->dynticks_nmi_nesting == 0) rcu_dynticks_task_enter(); } /* * Wrapper for rcu_irq_exit() where interrupts are enabled. * * If you add or remove a call to rcu_irq_exit_irqson(), be sure to test * with CONFIG_RCU_EQS_DEBUG=y. */ void rcu_irq_exit_irqson(void) { unsigned long flags; local_irq_save(flags); rcu_irq_exit(); local_irq_restore(flags); } /* * Exit an RCU extended quiescent state, which can be either the * idle loop or adaptive-tickless usermode execution. * * We crowbar the ->dynticks_nmi_nesting field to DYNTICK_IRQ_NONIDLE to * allow for the possibility of usermode upcalls messing up our count of * interrupt nesting level during the busy period that is just now starting. */ static void rcu_eqs_exit(bool user) { struct rcu_dynticks *rdtp; long oldval; lockdep_assert_irqs_disabled(); rdtp = this_cpu_ptr(&rcu_dynticks); oldval = rdtp->dynticks_nesting; WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && oldval < 0); if (oldval) { rdtp->dynticks_nesting++; return; } rcu_dynticks_task_exit(); rcu_dynticks_eqs_exit(); rcu_cleanup_after_idle(); trace_rcu_dyntick(TPS("End"), rdtp->dynticks_nesting, 1, rdtp->dynticks); WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current)); WRITE_ONCE(rdtp->dynticks_nesting, 1); WRITE_ONCE(rdtp->dynticks_nmi_nesting, DYNTICK_IRQ_NONIDLE); } /** * rcu_idle_exit - inform RCU that current CPU is leaving idle * * Exit idle mode, in other words, -enter- the mode in which RCU * read-side critical sections can occur. * * If you add or remove a call to rcu_idle_exit(), be sure to test with * CONFIG_RCU_EQS_DEBUG=y. */ void rcu_idle_exit(void) { unsigned long flags; local_irq_save(flags); rcu_eqs_exit(false); local_irq_restore(flags); } #ifdef CONFIG_NO_HZ_FULL /** * rcu_user_exit - inform RCU that we are exiting userspace. * * Exit RCU idle mode while entering the kernel because it can * run a RCU read side critical section anytime. * * If you add or remove a call to rcu_user_exit(), be sure to test with * CONFIG_RCU_EQS_DEBUG=y. */ void rcu_user_exit(void) { rcu_eqs_exit(1); } #endif /* CONFIG_NO_HZ_FULL */ /** * rcu_nmi_enter - inform RCU of entry to NMI context * * If the CPU was idle from RCU's viewpoint, update 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.) * * If you add or remove a call to rcu_nmi_enter(), be sure to test * with CONFIG_RCU_EQS_DEBUG=y. */ void rcu_nmi_enter(void) { struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); long 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; } trace_rcu_dyntick(incby == 1 ? TPS("Endirq") : TPS("++="), rdtp->dynticks_nmi_nesting, rdtp->dynticks_nmi_nesting + incby, rdtp->dynticks); WRITE_ONCE(rdtp->dynticks_nmi_nesting, /* Prevent store tearing. */ rdtp->dynticks_nmi_nesting + incby); barrier(); } /** * rcu_irq_enter - inform RCU that current CPU is entering irq away from idle * * Enter an interrupt handler, which might possibly result in exiting * idle mode, in other words, entering the mode in which read-side critical * sections can occur. The caller must have disabled interrupts. * * Note that the Linux kernel is fully capable of entering an interrupt * handler that it never exits, for example when doing upcalls to user mode! * This code assumes that the idle loop never does upcalls to user mode. * If your architecture's idle loop does do upcalls to user mode (or does * anything else that results in unbalanced calls to the irq_enter() and * irq_exit() functions), RCU will give you what you deserve, good and hard. * But very infrequently and irreproducibly. * * Use things like work queues to work around this limitation. * * You have been warned. * * If you add or remove a call to rcu_irq_enter(), be sure to test with * CONFIG_RCU_EQS_DEBUG=y. */ void rcu_irq_enter(void) { struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); lockdep_assert_irqs_disabled(); if (rdtp->dynticks_nmi_nesting == 0) rcu_dynticks_task_exit(); rcu_nmi_enter(); if (rdtp->dynticks_nmi_nesting == 1) rcu_cleanup_after_idle(); } /* * Wrapper for rcu_irq_enter() where interrupts are enabled. * * If you add or remove a call to rcu_irq_enter_irqson(), be sure to test * with CONFIG_RCU_EQS_DEBUG=y. */ void rcu_irq_enter_irqson(void) { unsigned long flags; local_irq_save(flags); rcu_irq_enter(); local_irq_restore(flags); } /** * rcu_is_watching - see if RCU thinks that the current CPU is idle * * 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. */ bool notrace rcu_is_watching(void) { bool ret; preempt_disable_notrace(); ret = !rcu_dynticks_curr_cpu_in_eqs(); preempt_enable_notrace(); return ret; } EXPORT_SYMBOL_GPL(rcu_is_watching); /* * If a holdout task is actually running, request an urgent quiescent * state from its CPU. This is unsynchronized, so migrations can cause * the request to go to the wrong CPU. Which is OK, all that will happen * is that the CPU's next context switch will be a bit slower and next * time around this task will generate another request. */ void rcu_request_urgent_qs_task(struct task_struct *t) { int cpu; barrier(); 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); } #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) /* * 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. */ bool rcu_lockdep_current_cpu_online(void) { struct rcu_data *rdp; struct rcu_node *rnp; bool ret; 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; } EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online); #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) <= 0 && __this_cpu_read(rcu_dynticks.dynticks_nmi_nesting) <= 1; } /* * We are reporting a quiescent state on behalf of some other CPU, so * it is our responsibility to check for and handle potential overflow * of the rcu_node ->gpnum 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(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4, rnp->gpnum)) WRITE_ONCE(rdp->gpwrap, true); if (ULONG_CMP_LT(rdp->rcu_iw_gpnum + ULONG_MAX / 4, rnp->gpnum)) rdp->rcu_iw_gpnum = rnp->gpnum + ULONG_MAX / 4; } /* * Snapshot the specified CPU's dynticks 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")); rcu_gpnum_ovf(rdp->mynode, rdp); return 1; } return 0; } /* * Handler for the irq_work request posted when a grace period has * gone on for too long, but not yet long enough for an RCU CPU * stall warning. Set state appropriately, but just complain if * there is unexpected state on entry. */ static void rcu_iw_handler(struct irq_work *iwp) { struct rcu_data *rdp; struct rcu_node *rnp; rdp = container_of(iwp, struct rcu_data, rcu_iw); rnp = rdp->mynode; raw_spin_lock_rcu_node(rnp); if (!WARN_ON_ONCE(!rdp->rcu_iw_pending)) { rdp->rcu_iw_gpnum = rnp->gpnum; rdp->rcu_iw_pending = false; } raw_spin_unlock_rcu_node(rnp); } /* * 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. */ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) { unsigned long jtsq; bool *rnhqp; bool *ruqp; struct rcu_node *rnp = rdp->mynode; /* * If the CPU passed through or entered a dynticks idle phase with * no active irq/NMI handlers, then we can safely pretend that the CPU * already acknowledged the request to pass through a quiescent * state. Either way, that CPU cannot possibly be in an RCU * 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++; rcu_gpnum_ovf(rnp, rdp); return 1; } /* * Has this CPU encountered a cond_resched() 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. */ jtsq = jiffies_till_sched_qs; 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")); rcu_gpnum_ovf(rnp, rdp); return 1; } else if (time_after(jiffies, rdp->rsp->gp_start + jtsq)) { /* 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++; rcu_gpnum_ovf(rnp, rdp); return 1; } /* * 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. */ 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); /* Store rcu_need_heavy_qs before rcu_urgent_qs. */ smp_store_release(ruqp, true); rdp->rsp->jiffies_resched += jtsq; /* Re-enable beating. */ } /* * If more than halfway to RCU CPU stall-warning time, do a * resched_cpu() 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. */ if (jiffies - rdp->rsp->gp_start > rcu_jiffies_till_stall_check() / 2) { resched_cpu(rdp->cpu); if (IS_ENABLED(CONFIG_IRQ_WORK) && !rdp->rcu_iw_pending && rdp->rcu_iw_gpnum != rnp->gpnum && (rnp->ffmask & rdp->grpmask)) { init_irq_work(&rdp->rcu_iw, rcu_iw_handler); rdp->rcu_iw_pending = true; rdp->rcu_iw_gpnum = rnp->gpnum; irq_work_queue_on(&rdp->rcu_iw, 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 ->cpu=%d\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, rsp->gp_kthread ? task_cpu(rsp->gp_kthread) : -1); if (rsp->gp_kthread) { pr_err("RCU grace-period kthread stack dump:\n"); 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 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. */ 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++; } } 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); } } 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_data *rdp = this_cpu_ptr(rsp->rda); 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(); raw_spin_lock_irqsave_rcu_node(rdp->mynode, flags); print_cpu_stall_info(rsp, smp_processor_id()); raw_spin_unlock_irqrestore_rcu_node(rdp->mynode, 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(" (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); } } /** * 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) { raw_lockdep_assert_held_rcu_node(rnp); /* * 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; /* * If the current rcu_node structure believes that RCU is * idle, and if the rcu_state structure does not yet reflect * the start of a new grace period, then the next grace period * will suffice. The memory barrier is needed to accurately * sample the rsp->gpnum, and pairs with the second lock * acquisition in rcu_gp_init(), which is augmented with * smp_mb__after_unlock_lock() for this purpose. */ if (rnp->gpnum == rnp->completed) { smp_mb(); /* See above block comment. */ if (READ_ONCE(rsp->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; } /* 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 c, const char *s) { trace_rcu_future_grace_period(rdp->rsp->name, rnp->gpnum, rnp->completed, c, rnp->level, rnp->grplo, rnp->grphi, s); } /* * 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 * is reason to awaken the grace-period kthread. * * The caller must hold the specified rcu_node structure's ->lock, which * is why the caller is responsible for waking the grace-period kthread. */ static bool rcu_start_this_gp(struct rcu_node *rnp, struct rcu_data *rdp, unsigned long c) { bool ret = false; struct rcu_state *rsp = rdp->rsp; struct rcu_node *rnp_root; /* * 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 has 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->lock must * not be released. */ raw_lockdep_assert_held_rcu_node(rnp); trace_rcu_this_gp(rnp, rdp, c, TPS("Startleaf")); for (rnp_root = rnp; 1; rnp_root = rnp_root->parent) { if (rnp_root != rnp) raw_spin_lock_rcu_node(rnp_root); WARN_ON_ONCE(ULONG_CMP_LT(rnp_root->gpnum + need_future_gp_mask(), c)); if (need_future_gp_element(rnp_root, c) || ULONG_CMP_GE(rnp_root->gpnum, c) || (rnp != rnp_root && rnp_root->gpnum != rnp_root->completed)) { trace_rcu_this_gp(rnp_root, rdp, c, TPS("Prestarted")); goto unlock_out; } need_future_gp_element(rnp_root, c) = true; if (rnp_root != rnp && rnp_root->parent != NULL) raw_spin_unlock_rcu_node(rnp_root); if (!rnp_root->parent) break; /* At root, and perhaps also leaf. */ } /* If GP already in progress, just leave, otherwise start one. */ if (rnp_root->gpnum != rnp_root->completed) { trace_rcu_this_gp(rnp_root, rdp, c, TPS("Startedleafroot")); goto unlock_out; } trace_rcu_this_gp(rnp_root, rdp, c, TPS("Startedroot")); WRITE_ONCE(rsp->gp_flags, rsp->gp_flags | RCU_GP_FLAG_INIT); if (!rsp->gp_kthread) { trace_rcu_this_gp(rnp_root, rdp, c, TPS("NoGPkthread")); goto unlock_out; } trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum), TPS("newreq")); ret = true; /* Caller must wake GP kthread. */ unlock_out: if (rnp != rnp_root) raw_spin_unlock_rcu_node(rnp_root); return ret; } /* * Clean up any old requests for the just-ended grace period. Also return * whether any additional grace periods have been requested. */ static bool rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) { unsigned long c = rnp->completed; bool needmore; struct rcu_data *rdp = this_cpu_ptr(rsp->rda); need_future_gp_element(rnp, c) = false; needmore = need_any_future_gp(rnp); trace_rcu_this_gp(rnp, rdp, c, 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. */ static void rcu_gp_kthread_wake(struct rcu_state *rsp) { if (current == rsp->gp_kthread || !READ_ONCE(rsp->gp_flags) || !rsp->gp_kthread) return; swake_up(&rsp->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. * * 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) { unsigned long c; bool ret = false; 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; /* * Callbacks are often registered with incomplete grace-period * information. Something about the fact that getting exact * information requires acquiring a global lock... RCU therefore * makes a conservative estimate of the grace period number at which * a given callback will become ready to invoke. The following * code checks this estimate and improves it when possible, thus * accelerating callback invocation to an earlier grace-period * number. */ c = rcu_cbs_completed(rsp, rnp); if (rcu_segcblist_accelerate(&rdp->cblist, c)) ret = rcu_start_this_gp(rnp, rdp, c); /* 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")); else trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccReadyCB")); return ret; } /* * 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 * 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) { 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 * are ready to invoke, and put them into the RCU_DONE_TAIL sublist. */ rcu_segcblist_advance(&rdp->cblist, rnp->completed); /* Classify any remaining callbacks. */ return rcu_accelerate_cbs(rsp, rnp, rdp); } /* * Update CPU-local rcu_data state to record the beginnings and ends of * grace periods. The caller must hold the ->lock of the leaf rcu_node * structure corresponding to the current CPU, and must have irqs disabled. * 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) { bool ret; bool need_gp; 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); } 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 (rdp->gpnum != rnp->gpnum || unlikely(READ_ONCE(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; zero_cpu_stall_ticks(rdp); 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) { unsigned long flags; bool needwake; struct rcu_node *rnp; local_irq_save(flags); rnp = rdp->mynode; if ((rdp->gpnum == READ_ONCE(rnp->gpnum) && rdp->completed == READ_ONCE(rnp->completed) && !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); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); if (needwake) rcu_gp_kthread_wake(rsp); } static void rcu_gp_slow(struct rcu_state *rsp, int delay) { if (delay > 0 && !(rsp->gpnum % (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay))) schedule_timeout_uninterruptible(delay); } /* * Initialize a new grace period. Return false if no grace period required. */ static bool rcu_gp_init(struct rcu_state *rsp) { unsigned long oldmask; struct rcu_data *rdp; struct rcu_node *rnp = rcu_get_root(rsp); WRITE_ONCE(rsp->gp_activity, jiffies); raw_spin_lock_irq_rcu_node(rnp); if (!READ_ONCE(rsp->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. */ if (WARN_ON_ONCE(rcu_gp_in_progress(rsp))) { /* * Grace period already in progress, don't start another. * Not supposed to be able to happen. */ raw_spin_unlock_irq_rcu_node(rnp); return false; } /* 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")); 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. */ rcu_for_each_leaf_node(rsp, rnp) { rcu_gp_slow(rsp, gp_preinit_delay); raw_spin_lock_irq_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); continue; } /* Record old state, apply changes to ->qsmaskinit field. */ oldmask = rnp->qsmaskinit; rnp->qsmaskinit = rnp->qsmaskinitnext; /* 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. */ rcu_cleanup_dead_rnp(rnp); } /* * If all waited-on tasks from prior grace period are * done, and if all this rcu_node structure's CPUs are * 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). */ if (rnp->wait_blkd_tasks && (!rcu_preempt_has_tasks(rnp) || rnp->qsmaskinit)) { rnp->wait_blkd_tasks = false; rcu_cleanup_dead_rnp(rnp); } raw_spin_unlock_irq_rcu_node(rnp); } /* * 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. * * 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); 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); if (r