/* * Read-Copy Update mechanism for mutual exclusion (tree-based version) * Internal non-public definitions that provide either classic * or preemptible semantics. * * 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 Red Hat, 2009 * Copyright IBM Corporation, 2009 * * Author: Ingo Molnar <mingo@elte.hu> * Paul E. McKenney <paulmck@linux.vnet.ibm.com> */ #include <linux/delay.h>#include <linux/gfp.h>#include <linux/oom.h>#include <linux/smpboot.h>#include "../time/tick-internal.h" #ifdef CONFIG_RCU_BOOST #include "../locking/rtmutex_common.h" /* * Control variables for per-CPU and per-rcu_node kthreads. These * handle all flavors of RCU. */static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task);DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status);DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);DEFINE_PER_CPU(char, rcu_cpu_has_work); #else /* #ifdef CONFIG_RCU_BOOST */ /* * Some architectures do not define rt_mutexes, but if !CONFIG_RCU_BOOST, * all uses are in dead code. Provide a definition to keep the compiler * happy, but add WARN_ON_ONCE() to complain if used in the wrong place. * This probably needs to be excluded from -rt builds. */#define rt_mutex_owner(a) ({ WARN_ON_ONCE(1); NULL; }) #endif /* #else #ifdef CONFIG_RCU_BOOST */ #ifdef CONFIG_RCU_NOCB_CPUstatic cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */static bool have_rcu_nocb_mask; /* Was rcu_nocb_mask allocated? */static bool __read_mostly rcu_nocb_poll; /* Offload kthread are to poll. */#endif /* #ifdef CONFIG_RCU_NOCB_CPU */ /* * Check the RCU kernel configuration parameters and print informative * messages about anything out of the ordinary. If you like #ifdef, you * will love this function. */static void __init rcu_bootup_announce_oddness(void){ if (IS_ENABLED(CONFIG_RCU_TRACE)) pr_info("\tRCU debugfs-based tracing is enabled.\n"); if ((IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 64) || (!IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 32)) pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d\n", RCU_FANOUT); if (rcu_fanout_exact) pr_info("\tHierarchical RCU autobalancing is disabled.\n"); if (IS_ENABLED(CONFIG_RCU_FAST_NO_HZ)) pr_info("\tRCU dyntick-idle grace-period acceleration is enabled.\n"); if (IS_ENABLED(CONFIG_PROVE_RCU)) pr_info("\tRCU lockdep checking is enabled.\n"); if (IS_ENABLED(CONFIG_RCU_TORTURE_TEST_RUNNABLE)) pr_info("\tRCU torture testing starts during boot.\n"); if (RCU_NUM_LVLS >= 4) pr_info("\tFour(or more)-level hierarchy is enabled.\n"); if (RCU_FANOUT_LEAF != 16) pr_info("\tBuild-time adjustment of leaf fanout to %d.\n", RCU_FANOUT_LEAF); if (rcu_fanout_leaf != RCU_FANOUT_LEAF) pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf); if (nr_cpu_ids != NR_CPUS) pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids); if (IS_ENABLED(CONFIG_RCU_BOOST)) pr_info("\tRCU kthread priority: %d.\n", kthread_prio);} #ifdef CONFIG_PREEMPT_RCU RCU_STATE_INITIALIZER(rcu_preempt, 'p', call_rcu);static struct rcu_state *const rcu_state_p = &rcu_preempt_state;static struct rcu_data __percpu *const rcu_data_p = &rcu_preempt_data; static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, bool wake); /* * Tell them what RCU they are running. */static void __init rcu_bootup_announce(void){ pr_info("Preemptible hierarchical RCU implementation.\n"); rcu_bootup_announce_oddness();} /* Flags for rcu_preempt_ctxt_queue() decision table. */#define RCU_GP_TASKS 0x8#define RCU_EXP_TASKS 0x4#define RCU_GP_BLKD 0x2#define RCU_EXP_BLKD 0x1 /* * Queues a task preempted within an RCU-preempt read-side critical * section into the appropriate location within the ->blkd_tasks list, * depending on the states of any ongoing normal and expedited grace * periods. The ->gp_tasks pointer indicates which element the normal * grace period is waiting on (NULL if none), and the ->exp_tasks pointer * indicates which element the expedited grace period is waiting on (again, * NULL if none). If a grace period is waiting on a given element in the * ->blkd_tasks list, it also waits on all subsequent elements. Thus, * adding a task to the tail of the list blocks any grace period that is * already waiting on one of the elements. In contrast, adding a task * to the head of the list won't block any grace period that is already * waiting on one of the elements. * * This queuing is imprecise, and can sometimes make an ongoing grace * period wait for a task that is not strictly speaking blocking it. * Given the choice, we needlessly block a normal grace period rather than * blocking an expedited grace period. * * Note that an endless sequence of expedited grace periods still cannot * indefinitely postpone a normal grace period. Eventually, all of the * fixed number of preempted tasks blocking the normal grace period that are * not also blocking the expedited grace period will resume and complete * their RCU read-side critical sections. At that point, the ->gp_tasks * pointer will equal the ->exp_tasks pointer, at which point the end of * the corresponding expedited grace period will also be the end of the * normal grace period. */static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp, unsigned long flags) __releases(rnp->lock){ int blkd_state = (rnp->gp_tasks ? RCU_GP_TASKS : 0) + (rnp->exp_tasks ? RCU_EXP_TASKS : 0) + (rnp->qsmask & rdp->grpmask ? RCU_GP_BLKD : 0) + (rnp->expmask & rdp->grpmask ? RCU_EXP_BLKD : 0); struct task_struct *t = current; /* * Decide where to queue the newly blocked task. In theory, * this could be an if-statement. In practice, when I tried * that, it was quite messy. */ switch (blkd_state) { case 0: case RCU_EXP_TASKS: case RCU_EXP_TASKS + RCU_GP_BLKD: case RCU_GP_TASKS: case RCU_GP_TASKS + RCU_EXP_TASKS: /* * Blocking neither GP, or first task blocking the normal * GP but not blocking the already-waiting expedited GP. * Queue at the head of the list to avoid unnecessarily * blocking the already-waiting GPs. */ list_add(&t->rcu_node_entry, &rnp->blkd_tasks); break; case RCU_EXP_BLKD: case RCU_GP_BLKD: case RCU_GP_BLKD + RCU_EXP_BLKD: case RCU_GP_TASKS + RCU_EXP_BLKD: case RCU_GP_TASKS + RCU_GP_BLKD + RCU_EXP_BLKD: case RCU_GP_TASKS + RCU_EXP_TASKS + RCU_GP_BLKD + RCU_EXP_BLKD: /* * First task arriving that blocks either GP, or first task * arriving that blocks the expedited GP (with the normal * GP already waiting), or a task arriving that blocks * both GPs with both GPs already waiting. Queue at the * tail of the list to avoid any GP waiting on any of the * already queued tasks that are not blocking it. */ list_add_tail(&t->rcu_node_entry, &rnp->blkd_tasks); break; case RCU_EXP_TASKS + RCU_EXP_BLKD: case RCU_EXP_TASKS + RCU_GP_BLKD + RCU_EXP_BLKD: case RCU_GP_TASKS + RCU_EXP_TASKS + RCU_EXP_BLKD: /* * Second or subsequent task blocking the expedited GP. * The task either does not block the normal GP, or is the * first task blocking the normal GP. Queue just after * the first task blocking the expedited GP. */ list_add(&t->rcu_node_entry, rnp->exp_tasks); break; case RCU_GP_TASKS + RCU_GP_BLKD: case RCU_GP_TASKS + RCU_EXP_TASKS + RCU_GP_BLKD: /* * Second or subsequent task blocking the normal GP. * The task does not block the expedited GP. Queue just * after the first task blocking the normal GP. */ list_add(&t->rcu_node_entry, rnp->gp_tasks); break; default: /* Yet another exercise in excessive paranoia. */ WARN_ON_ONCE(1); break; } /* * We have now queued the task. If it was the first one to * block either grace period, update the ->gp_tasks and/or * ->exp_tasks pointers, respectively, to reference the newly * blocked tasks. */ if (!rnp->gp_tasks && (blkd_state & RCU_GP_BLKD)) rnp->gp_tasks = &t->rcu_node_entry; if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD)) rnp->exp_tasks = &t->rcu_node_entry; raw_spin_unlock(&rnp->lock); /* * Report the quiescent state for the expedited GP. This expedited * GP should not be able to end until we report, so there should be * no need to check for a subsequent expedited GP. (Though we are * still in a quiescent state in any case.) */ if (blkd_state & RCU_EXP_BLKD && t->rcu_read_unlock_special.b.exp_need_qs) { t->rcu_read_unlock_special.b.exp_need_qs = false; rcu_report_exp_rdp(rdp->rsp, rdp, true); } else { WARN_ON_ONCE(t->rcu_read_unlock_special.b.exp_need_qs); } local_irq_restore(flags);} /* * Record a preemptible-RCU quiescent state for the specified CPU. Note * that this just means that the task currently running on the CPU is * not in a quiescent state. There might be any number of tasks blocked * while in an RCU read-side critical section. * * As with the other rcu_*_qs() functions, callers to this function * must disable preemption. */static void rcu_preempt_qs(void){ if (__this_cpu_read(rcu_data_p->cpu_no_qs.s)) { trace_rcu_grace_period(TPS("rcu_preempt"), __this_cpu_read(rcu_data_p->gpnum), TPS("cpuqs")); __this_cpu_write(rcu_data_p->cpu_no_qs.b.norm, false); barrier(); /* Coordinate with rcu_preempt_check_callbacks(). */ current->rcu_read_unlock_special.b.need_qs = false; }} /* * We have entered the scheduler, and the current task might soon be * context-switched away from. If this task is in an RCU read-side * critical section, we will no longer be able to rely on the CPU to * record that fact, so we enqueue the task on the blkd_tasks list. * The task will dequeue itself when it exits the outermost enclosing * RCU read-side critical section. Therefore, the current grace period * cannot be permitted to complete until the blkd_tasks list entries * predating the current grace period drain, in other words, until * rnp->gp_tasks becomes NULL. * * Caller must disable preemption. */static void rcu_preempt_note_context_switch(void){ struct task_struct *t = current; unsigned long flags; struct rcu_data *rdp; struct rcu_node *rnp; if (t->rcu_read_lock_nesting > 0 && !t->rcu_read_unlock_special.b.blocked) { /* Possibly blocking in an RCU read-side critical section. */ rdp = this_cpu_ptr(rcu_state_p->rda); rnp = rdp->mynode; raw_spin_lock_irqsave(&rnp->lock, flags); smp_mb__after_unlock_lock(); t->rcu_read_unlock_special.b.blocked = true; t->rcu_blocked_node = rnp; /* * Verify the CPU's sanity, trace the preemption, and * then queue the task as required based on the states * of any ongoing and expedited grace periods. */ WARN_ON_ONCE((rdp->grpmask & rcu_rnp_online_cpus(rnp)) == 0); WARN_ON_ONCE(!list_empty(&t->rcu_node_entry)); trace_rcu_preempt_task(rdp->rsp->name, t->pid, (rnp->qsmask & rdp->grpmask) ? rnp->gpnum : rnp->gpnum + 1); rcu_preempt_ctxt_queue(rnp, rdp, flags); } else if (t->rcu_read_lock_nesting < 0 && t->rcu_read_unlock_special.s) { /* * Complete exit from RCU read-side critical section on * behalf of preempted instance of __rcu_read_unlock(). */ rcu_read_unlock_special(t); } /* * Either we were not in an RCU read-side critical section to * begin with, or we have now recorded that critical section * globally. Either way, we can now note a quiescent state * for this CPU. Again, if we were in an RCU read-side critical * section, and if that critical section was blocking the current * grace period, then the fact that the task has been enqueued * means that we continue to block the current grace period. */ rcu_preempt_qs();} /* * Check for preempted RCU readers blocking the current grace period * for the specified rcu_node structure. If the caller needs a reliable * answer, it must hold the rcu_node's ->lock. */static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp){ return rnp->gp_tasks != NULL;} /* * Advance a ->blkd_tasks-list pointer to the next entry, instead * returning NULL if at the end of the list. */static struct list_head *rcu_next_node_entry(struct task_struct *t, struct rcu_node *rnp){ struct list_head *np; np = t->rcu_node_entry.next; if (np == &rnp->blkd_tasks) np = NULL; return np;} /* * Return true if the specified rcu_node structure has tasks that were * preempted within an RCU read-side critical section. */static bool rcu_preempt_has_tasks(struct rcu_node *rnp){ return !list_empty(&rnp->blkd_tasks);} /* * Handle special cases during rcu_read_unlock(), such as needing to * notify RCU core processing or task having blocked during the RCU * read-side critical section. */void rcu_read_unlock_special(struct task_struct *t){ bool empty_exp; bool empty_norm; bool empty_exp_now; unsigned long flags; struct list_head *np; bool drop_boost_mutex = false; struct rcu_data *rdp; struct rcu_node *rnp; union rcu_special special; /* NMI handlers cannot block and cannot safely manipulate state. */ if (in_nmi()) return; local_irq_save(flags); /* * If RCU core is waiting for this CPU to exit its critical section, * report the fact that it has exited. Because irqs are disabled, * t->rcu_read_unlock_special cannot change. */ special = t->rcu_read_unlock_special; if (special.b.need_qs) { rcu_preempt_qs(); t->rcu_read_unlock_special.b.need_qs = false; if (!t->rcu_read_unlock_special.s) { local_irq_restore(flags); return; } } /* * Respond to a request for an expedited grace period, but only if * we were not preempted, meaning that we were running on the same * CPU throughout. If we were preempted, the exp_need_qs flag * would have been cleared at the time of the first preemption, * and the quiescent state would be reported when we were dequeued. */ if (special.b.exp_need_qs) { WARN_ON_ONCE(special.b.blocked); t->rcu_read_unlock_special.b.exp_need_qs = false; rdp = this_cpu_ptr(rcu_state_p->rda); rcu_report_exp_rdp(rcu_state_p, rdp, true); if (!t->rcu_read_unlock_special.s) { local_irq_restore(flags); return; } } /* Hardware IRQ handlers cannot block, complain if they get here. */ if (in_irq() || in_serving_softirq()) { lockdep_rcu_suspicious(__FILE__, __LINE__, "rcu_read_unlock() from irq or softirq with blocking in critical section!!!\n"); pr_alert("->rcu_read_unlock_special: %#x (b: %d, enq: %d nq: %d)\n", t->rcu_read_unlock_special.s, t->rcu_read_unlock_special.b.blocked, t->rcu_read_unlock_special.b.exp_need_qs, t->rcu_read_unlock_special.b.need_qs); local_irq_restore(flags); return; } /* Clean up if blocked during RCU read-side critical section. */ if (special.b.blocked) { t->rcu_read_unlock_special.b.blocked = false; /* * Remove this task from the list it blocked on. The task * now remains queued on the rcu_node corresponding to * the CPU it first blocked on, so the first attempt to * acquire the task's rcu_node's ->lock will succeed. * Keep the loop and add a WARN_ON() out of sheer paranoia. */ for (;;) { rnp = t->rcu_blocked_node; raw_spin_lock(&rnp->lock); /* irqs already disabled. */ smp_mb__after_unlock_lock(); if (rnp == t->rcu_blocked_node) break; WARN_ON_ONCE(1); raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ } empty_norm = !rcu_preempt_blocked_readers_cgp(rnp); empty_exp = sync_rcu_preempt_exp_done(rnp); smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */ np = rcu_next_node_entry(t, rnp); list_del_init(&t->rcu_node_entry); t->rcu_blocked_node = NULL; trace_rcu_unlock_preempted_task(TPS("rcu_preempt"), rnp->gpnum, t->pid); if (&t->rcu_node_entry == rnp->gp_tasks) rnp->gp_tasks = np; if (&t->rcu_node_entry == rnp->exp_tasks) rnp->exp_tasks = np; if (IS_ENABLED(CONFIG_RCU_BOOST)) { if (&t->rcu_node_entry == rnp->boost_tasks) rnp->boost_tasks = np; /* Snapshot ->boost_mtx ownership w/rnp->lock held. */ drop_boost_mutex = rt_mutex_owner(&rnp->boost_mtx) == t; } /* * If this was the last task on the current list, and if * we aren't waiting on any CPUs, report the quiescent state. * Note that rcu_report_unblock_qs_rnp() releases rnp->lock, * so we must take a snapshot of the expedited state. */ empty_exp_now = sync_rcu_preempt_exp_done(rnp); if (!empty_norm && !rcu_preempt_blocked_readers_cgp(rnp)) { trace_rcu_quiescent_state_report(TPS("preempt_rcu"), rnp->gpnum, 0, rnp->qsmask, rnp->level, rnp->grplo, rnp->grphi, !!rnp->gp_tasks);Lines 1–500 of 3055. Load more
/* * Read-Copy Update mechanism for mutual exclusion (tree-based version) * Internal non-public definitions that provide either classic * or preemptible semantics. * * 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 Red Hat, 2009 * Copyright IBM Corporation, 2009 * * Author: Ingo Molnar <mingo@elte.hu> * Paul E. McKenney <paulmck@linux.vnet.ibm.com> */ #include <linux/delay.h> #include <linux/gfp.h> #include <linux/oom.h> #include <linux/smpboot.h> #include "../time/tick-internal.h" #ifdef CONFIG_RCU_BOOST #include "../locking/rtmutex_common.h" /* * Control variables for per-CPU and per-rcu_node kthreads. These * handle all flavors of RCU. */ static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task); DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status); DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); DEFINE_PER_CPU(char, rcu_cpu_has_work); #else /* #ifdef CONFIG_RCU_BOOST */ /* * Some architectures do not define rt_mutexes, but if !CONFIG_RCU_BOOST, * all uses are in dead code. Provide a definition to keep the compiler * happy, but add WARN_ON_ONCE() to complain if used in the wrong place. * This probably needs to be excluded from -rt builds. */ #define rt_mutex_owner(a) ({ WARN_ON_ONCE(1); NULL; }) #endif /* #else #ifdef CONFIG_RCU_BOOST */ #ifdef CONFIG_RCU_NOCB_CPU static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */ static bool have_rcu_nocb_mask; /* Was rcu_nocb_mask allocated? */ static bool __read_mostly rcu_nocb_poll; /* Offload kthread are to poll. */ #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ /* * Check the RCU kernel configuration parameters and print informative * messages about anything out of the ordinary. If you like #ifdef, you * will love this function. */ static void __init rcu_bootup_announce_oddness(void) { if (IS_ENABLED(CONFIG_RCU_TRACE)) pr_info("\tRCU debugfs-based tracing is enabled.\n"); if ((IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 64) || (!IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 32)) pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d\n", RCU_FANOUT); if (rcu_fanout_exact) pr_info("\tHierarchical RCU autobalancing is disabled.\n"); if (IS_ENABLED(CONFIG_RCU_FAST_NO_HZ)) pr_info("\tRCU dyntick-idle grace-period acceleration is enabled.\n"); if (IS_ENABLED(CONFIG_PROVE_RCU)) pr_info("\tRCU lockdep checking is enabled.\n"); if (IS_ENABLED(CONFIG_RCU_TORTURE_TEST_RUNNABLE)) pr_info("\tRCU torture testing starts during boot.\n"); if (RCU_NUM_LVLS >= 4) pr_info("\tFour(or more)-level hierarchy is enabled.\n"); if (RCU_FANOUT_LEAF != 16) pr_info("\tBuild-time adjustment of leaf fanout to %d.\n", RCU_FANOUT_LEAF); if (rcu_fanout_leaf != RCU_FANOUT_LEAF) pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf); if (nr_cpu_ids != NR_CPUS) pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids); if (IS_ENABLED(CONFIG_RCU_BOOST)) pr_info("\tRCU kthread priority: %d.\n", kthread_prio); } #ifdef CONFIG_PREEMPT_RCU RCU_STATE_INITIALIZER(rcu_preempt, 'p', call_rcu); static struct rcu_state *const rcu_state_p = &rcu_preempt_state; static struct rcu_data __percpu *const rcu_data_p = &rcu_preempt_data; static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, bool wake); /* * Tell them what RCU they are running. */ static void __init rcu_bootup_announce(void) { pr_info("Preemptible hierarchical RCU implementation.\n"); rcu_bootup_announce_oddness(); } /* Flags for rcu_preempt_ctxt_queue() decision table. */ #define RCU_GP_TASKS 0x8 #define RCU_EXP_TASKS 0x4 #define RCU_GP_BLKD 0x2 #define RCU_EXP_BLKD 0x1 /* * Queues a task preempted within an RCU-preempt read-side critical * section into the appropriate location within the ->blkd_tasks list, * depending on the states of any ongoing normal and expedited grace * periods. The ->gp_tasks pointer indicates which element the normal * grace period is waiting on (NULL if none), and the ->exp_tasks pointer * indicates which element the expedited grace period is waiting on (again, * NULL if none). If a grace period is waiting on a given element in the * ->blkd_tasks list, it also waits on all subsequent elements. Thus, * adding a task to the tail of the list blocks any grace period that is * already waiting on one of the elements. In contrast, adding a task * to the head of the list won't block any grace period that is already * waiting on one of the elements. * * This queuing is imprecise, and can sometimes make an ongoing grace * period wait for a task that is not strictly speaking blocking it. * Given the choice, we needlessly block a normal grace period rather than * blocking an expedited grace period. * * Note that an endless sequence of expedited grace periods still cannot * indefinitely postpone a normal grace period. Eventually, all of the * fixed number of preempted tasks blocking the normal grace period that are * not also blocking the expedited grace period will resume and complete * their RCU read-side critical sections. At that point, the ->gp_tasks * pointer will equal the ->exp_tasks pointer, at which point the end of * the corresponding expedited grace period will also be the end of the * normal grace period. */ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp, unsigned long flags) __releases(rnp->lock) { int blkd_state = (rnp->gp_tasks ? RCU_GP_TASKS : 0) + (rnp->exp_tasks ? RCU_EXP_TASKS : 0) + (rnp->qsmask & rdp->grpmask ? RCU_GP_BLKD : 0) + (rnp->expmask & rdp->grpmask ? RCU_EXP_BLKD : 0); struct task_struct *t = current; /* * Decide where to queue the newly blocked task. In theory, * this could be an if-statement. In practice, when I tried * that, it was quite messy. */ switch (blkd_state) { case 0: case RCU_EXP_TASKS: case RCU_EXP_TASKS + RCU_GP_BLKD: case RCU_GP_TASKS: case RCU_GP_TASKS + RCU_EXP_TASKS: /* * Blocking neither GP, or first task blocking the normal * GP but not blocking the already-waiting expedited GP. * Queue at the head of the list to avoid unnecessarily * blocking the already-waiting GPs. */ list_add(&t->rcu_node_entry, &rnp->blkd_tasks); break; case RCU_EXP_BLKD: case RCU_GP_BLKD: case RCU_GP_BLKD + RCU_EXP_BLKD: case RCU_GP_TASKS + RCU_EXP_BLKD: case RCU_GP_TASKS + RCU_GP_BLKD + RCU_EXP_BLKD: case RCU_GP_TASKS + RCU_EXP_TASKS + RCU_GP_BLKD + RCU_EXP_BLKD: /* * First task arriving that blocks either GP, or first task * arriving that blocks the expedited GP (with the normal * GP already waiting), or a task arriving that blocks * both GPs with both GPs already waiting. Queue at the * tail of the list to avoid any GP waiting on any of the * already queued tasks that are not blocking it. */ list_add_tail(&t->rcu_node_entry, &rnp->blkd_tasks); break; case RCU_EXP_TASKS + RCU_EXP_BLKD: case RCU_EXP_TASKS + RCU_GP_BLKD + RCU_EXP_BLKD: case RCU_GP_TASKS + RCU_EXP_TASKS + RCU_EXP_BLKD: /* * Second or subsequent task blocking the expedited GP. * The task either does not block the normal GP, or is the * first task blocking the normal GP. Queue just after * the first task blocking the expedited GP. */ list_add(&t->rcu_node_entry, rnp->exp_tasks); break; case RCU_GP_TASKS + RCU_GP_BLKD: case RCU_GP_TASKS + RCU_EXP_TASKS + RCU_GP_BLKD: /* * Second or subsequent task blocking the normal GP. * The task does not block the expedited GP. Queue just * after the first task blocking the normal GP. */ list_add(&t->rcu_node_entry, rnp->gp_tasks); break; default: /* Yet another exercise in excessive paranoia. */ WARN_ON_ONCE(1); break; } /* * We have now queued the task. If it was the first one to * block either grace period, update the ->gp_tasks and/or * ->exp_tasks pointers, respectively, to reference the newly * blocked tasks. */ if (!rnp->gp_tasks && (blkd_state & RCU_GP_BLKD)) rnp->gp_tasks = &t->rcu_node_entry; if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD)) rnp->exp_tasks = &t->rcu_node_entry; raw_spin_unlock(&rnp->lock); /* * Report the quiescent state for the expedited GP. This expedited * GP should not be able to end until we report, so there should be * no need to check for a subsequent expedited GP. (Though we are * still in a quiescent state in any case.) */ if (blkd_state & RCU_EXP_BLKD && t->rcu_read_unlock_special.b.exp_need_qs) { t->rcu_read_unlock_special.b.exp_need_qs = false; rcu_report_exp_rdp(rdp->rsp, rdp, true); } else { WARN_ON_ONCE(t->rcu_read_unlock_special.b.exp_need_qs); } local_irq_restore(flags); } /* * Record a preemptible-RCU quiescent state for the specified CPU. Note * that this just means that the task currently running on the CPU is * not in a quiescent state. There might be any number of tasks blocked * while in an RCU read-side critical section. * * As with the other rcu_*_qs() functions, callers to this function * must disable preemption. */ static void rcu_preempt_qs(void) { if (__this_cpu_read(rcu_data_p->cpu_no_qs.s)) { trace_rcu_grace_period(TPS("rcu_preempt"), __this_cpu_read(rcu_data_p->gpnum), TPS("cpuqs")); __this_cpu_write(rcu_data_p->cpu_no_qs.b.norm, false); barrier(); /* Coordinate with rcu_preempt_check_callbacks(). */ current->rcu_read_unlock_special.b.need_qs = false; } } /* * We have entered the scheduler, and the current task might soon be * context-switched away from. If this task is in an RCU read-side * critical section, we will no longer be able to rely on the CPU to * record that fact, so we enqueue the task on the blkd_tasks list. * The task will dequeue itself when it exits the outermost enclosing * RCU read-side critical section. Therefore, the current grace period * cannot be permitted to complete until the blkd_tasks list entries * predating the current grace period drain, in other words, until * rnp->gp_tasks becomes NULL. * * Caller must disable preemption. */ static void rcu_preempt_note_context_switch(void) { struct task_struct *t = current; unsigned long flags; struct rcu_data *rdp; struct rcu_node *rnp; if (t->rcu_read_lock_nesting > 0 && !t->rcu_read_unlock_special.b.blocked) { /* Possibly blocking in an RCU read-side critical section. */ rdp = this_cpu_ptr(rcu_state_p->rda); rnp = rdp->mynode; raw_spin_lock_irqsave(&rnp->lock, flags); smp_mb__after_unlock_lock(); t->rcu_read_unlock_special.b.blocked = true; t->rcu_blocked_node = rnp; /* * Verify the CPU's sanity, trace the preemption, and * then queue the task as required based on the states * of any ongoing and expedited grace periods. */ WARN_ON_ONCE((rdp->grpmask & rcu_rnp_online_cpus(rnp)) == 0); WARN_ON_ONCE(!list_empty(&t->rcu_node_entry)); trace_rcu_preempt_task(rdp->rsp->name, t->pid, (rnp->qsmask & rdp->grpmask) ? rnp->gpnum : rnp->gpnum + 1); rcu_preempt_ctxt_queue(rnp, rdp, flags); } else if (t->rcu_read_lock_nesting < 0 && t->rcu_read_unlock_special.s) { /* * Complete exit from RCU read-side critical section on * behalf of preempted instance of __rcu_read_unlock(). */ rcu_read_unlock_special(t); } /* * Either we were not in an RCU read-side critical section to * begin with, or we have now recorded that critical section * globally. Either way, we can now note a quiescent state * for this CPU. Again, if we were in an RCU read-side critical * section, and if that critical section was blocking the current * grace period, then the fact that the task has been enqueued * means that we continue to block the current grace period. */ rcu_preempt_qs(); } /* * Check for preempted RCU readers blocking the current grace period * for the specified rcu_node structure. If the caller needs a reliable * answer, it must hold the rcu_node's ->lock. */ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp) { return rnp->gp_tasks != NULL; } /* * Advance a ->blkd_tasks-list pointer to the next entry, instead * returning NULL if at the end of the list. */ static struct list_head *rcu_next_node_entry(struct task_struct *t, struct rcu_node *rnp) { struct list_head *np; np = t->rcu_node_entry.next; if (np == &rnp->blkd_tasks) np = NULL; return np; } /* * Return true if the specified rcu_node structure has tasks that were * preempted within an RCU read-side critical section. */ static bool rcu_preempt_has_tasks(struct rcu_node *rnp) { return !list_empty(&rnp->blkd_tasks); } /* * Handle special cases during rcu_read_unlock(), such as needing to * notify RCU core processing or task having blocked during the RCU * read-side critical section. */ void rcu_read_unlock_special(struct task_struct *t) { bool empty_exp; bool empty_norm; bool empty_exp_now; unsigned long flags; struct list_head *np; bool drop_boost_mutex = false; struct rcu_data *rdp; struct rcu_node *rnp; union rcu_special special; /* NMI handlers cannot block and cannot safely manipulate state. */ if (in_nmi()) return; local_irq_save(flags); /* * If RCU core is waiting for this CPU to exit its critical section, * report the fact that it has exited. Because irqs are disabled, * t->rcu_read_unlock_special cannot change. */ special = t->rcu_read_unlock_special; if (special.b.need_qs) { rcu_preempt_qs(); t->rcu_read_unlock_special.b.need_qs = false; if (!t->rcu_read_unlock_special.s) { local_irq_restore(flags); return; } } /* * Respond to a request for an expedited grace period, but only if * we were not preempted, meaning that we were running on the same * CPU throughout. If we were preempted, the exp_need_qs flag * would have been cleared at the time of the first preemption, * and the quiescent state would be reported when we were dequeued. */ if (special.b.exp_need_qs) { WARN_ON_ONCE(special.b.blocked); t->rcu_read_unlock_special.b.exp_need_qs = false; rdp = this_cpu_ptr(rcu_state_p->rda); rcu_report_exp_rdp(rcu_state_p, rdp, true); if (!t->rcu_read_unlock_special.s) { local_irq_restore(flags); return; } } /* Hardware IRQ handlers cannot block, complain if they get here. */ if (in_irq() || in_serving_softirq()) { lockdep_rcu_suspicious(__FILE__, __LINE__, "rcu_read_unlock() from irq or softirq with blocking in critical section!!!\n"); pr_alert("->rcu_read_unlock_special: %#x (b: %d, enq: %d nq: %d)\n", t->rcu_read_unlock_special.s, t->rcu_read_unlock_special.b.blocked, t->rcu_read_unlock_special.b.exp_need_qs, t->rcu_read_unlock_special.b.need_qs); local_irq_restore(flags); return; } /* Clean up if blocked during RCU read-side critical section. */ if (special.b.blocked) { t->rcu_read_unlock_special.b.blocked = false; /* * Remove this task from the list it blocked on. The task * now remains queued on the rcu_node corresponding to * the CPU it first blocked on, so the first attempt to * acquire the task's rcu_node's ->lock will succeed. * Keep the loop and add a WARN_ON() out of sheer paranoia. */ for (;;) { rnp = t->rcu_blocked_node; raw_spin_lock(&rnp->lock); /* irqs already disabled. */ smp_mb__after_unlock_lock(); if (rnp == t->rcu_blocked_node) break; WARN_ON_ONCE(1); raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ } empty_norm = !rcu_preempt_blocked_readers_cgp(rnp); empty_exp = sync_rcu_preempt_exp_done(rnp); smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */ np = rcu_next_node_entry(t, rnp); list_del_init(&t->rcu_node_entry); t->rcu_blocked_node = NULL; trace_rcu_unlock_preempted_task(TPS("rcu_preempt"), rnp->gpnum, t->pid); if (&t->rcu_node_entry == rnp->gp_tasks) rnp->gp_tasks = np; if (&t->rcu_node_entry == rnp->exp_tasks) rnp->exp_tasks = np; if (IS_ENABLED(CONFIG_RCU_BOOST)) { if (&t->rcu_node_entry == rnp->boost_tasks) rnp->boost_tasks = np; /* Snapshot ->boost_mtx ownership w/rnp->lock held. */ drop_boost_mutex = rt_mutex_owner(&rnp->boost_mtx) == t; } /* * If this was the last task on the current list, and if * we aren't waiting on any CPUs, report the quiescent state. * Note that rcu_report_unblock_qs_rnp() releases rnp->lock, * so we must take a snapshot of the expedited state. */ empty_exp_now = sync_rcu_preempt_exp_done(rnp); if (!empty_norm && !rcu_preempt_blocked_readers_cgp(rnp)) { trace_rcu_quiescent_state_report(TPS("preempt_rcu"), rnp->gpnum, 0, rnp->qsmask, rnp->level, rnp->grplo, rnp->grphi, !!rnp->gp_tasks);