/* * Read-Copy Update mechanism for mutual exclusion, the Bloatwatch edition * 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, write to the Free Software * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. * * Copyright (c) 2010 Linaro * * Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com> */ #include <linux/kthread.h>#include <linux/module.h>#include <linux/debugfs.h>#include <linux/seq_file.h> /* Global control variables for rcupdate callback mechanism. */struct rcu_ctrlblk { struct rcu_head *rcucblist; /* List of pending callbacks (CBs). */ struct rcu_head **donetail; /* ->next pointer of last "done" CB. */ struct rcu_head **curtail; /* ->next pointer of last CB. */ RCU_TRACE(long qlen); /* Number of pending CBs. */ RCU_TRACE(char *name); /* Name of RCU type. */}; /* Definition for rcupdate control block. */static struct rcu_ctrlblk rcu_sched_ctrlblk = { .donetail = &rcu_sched_ctrlblk.rcucblist, .curtail = &rcu_sched_ctrlblk.rcucblist, RCU_TRACE(.name = "rcu_sched")}; static struct rcu_ctrlblk rcu_bh_ctrlblk = { .donetail = &rcu_bh_ctrlblk.rcucblist, .curtail = &rcu_bh_ctrlblk.rcucblist, RCU_TRACE(.name = "rcu_bh")}; #ifdef CONFIG_DEBUG_LOCK_ALLOCint rcu_scheduler_active __read_mostly;EXPORT_SYMBOL_GPL(rcu_scheduler_active);#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #ifdef CONFIG_TINY_PREEMPT_RCU #include <linux/delay.h> /* Global control variables for preemptible RCU. */struct rcu_preempt_ctrlblk { struct rcu_ctrlblk rcb; /* curtail: ->next ptr of last CB for GP. */ struct rcu_head **nexttail; /* Tasks blocked in a preemptible RCU */ /* read-side critical section while an */ /* preemptible-RCU grace period is in */ /* progress must wait for a later grace */ /* period. This pointer points to the */ /* ->next pointer of the last task that */ /* must wait for a later grace period, or */ /* to &->rcb.rcucblist if there is no */ /* such task. */ struct list_head blkd_tasks; /* Tasks blocked in RCU read-side critical */ /* section. Tasks are placed at the head */ /* of this list and age towards the tail. */ struct list_head *gp_tasks; /* Pointer to the first task blocking the */ /* current grace period, or NULL if there */ /* is no such task. */ struct list_head *exp_tasks; /* Pointer to first task blocking the */ /* current expedited grace period, or NULL */ /* if there is no such task. If there */ /* is no current expedited grace period, */ /* then there cannot be any such task. */#ifdef CONFIG_RCU_BOOST struct list_head *boost_tasks; /* Pointer to first task that needs to be */ /* priority-boosted, or NULL if no priority */ /* boosting is needed. If there is no */ /* current or expedited grace period, there */ /* can be no such task. */#endif /* #ifdef CONFIG_RCU_BOOST */ u8 gpnum; /* Current grace period. */ u8 gpcpu; /* Last grace period blocked by the CPU. */ u8 completed; /* Last grace period completed. */ /* If all three are equal, RCU is idle. */#ifdef CONFIG_RCU_BOOST unsigned long boost_time; /* When to start boosting (jiffies) */#endif /* #ifdef CONFIG_RCU_BOOST */#ifdef CONFIG_RCU_TRACE unsigned long n_grace_periods;#ifdef CONFIG_RCU_BOOST unsigned long n_tasks_boosted; /* Total number of tasks boosted. */ unsigned long n_exp_boosts; /* Number of tasks boosted for expedited GP. */ unsigned long n_normal_boosts; /* Number of tasks boosted for normal GP. */ unsigned long n_balk_blkd_tasks; /* Refused to boost: no blocked tasks. */ unsigned long n_balk_exp_gp_tasks; /* Refused to boost: nothing blocking GP. */ unsigned long n_balk_boost_tasks; /* Refused to boost: already boosting. */ unsigned long n_balk_notyet; /* Refused to boost: not yet time. */ unsigned long n_balk_nos; /* Refused to boost: not sure why, though. */ /* This can happen due to race conditions. */#endif /* #ifdef CONFIG_RCU_BOOST */#endif /* #ifdef CONFIG_RCU_TRACE */}; static struct rcu_preempt_ctrlblk rcu_preempt_ctrlblk = { .rcb.donetail = &rcu_preempt_ctrlblk.rcb.rcucblist, .rcb.curtail = &rcu_preempt_ctrlblk.rcb.rcucblist, .nexttail = &rcu_preempt_ctrlblk.rcb.rcucblist, .blkd_tasks = LIST_HEAD_INIT(rcu_preempt_ctrlblk.blkd_tasks), RCU_TRACE(.rcb.name = "rcu_preempt")}; static int rcu_preempted_readers_exp(void);static void rcu_report_exp_done(void); /* * Return true if the CPU has not yet responded to the current grace period. */static int rcu_cpu_blocking_cur_gp(void){ return rcu_preempt_ctrlblk.gpcpu != rcu_preempt_ctrlblk.gpnum;} /* * Check for a running RCU reader. Because there is only one CPU, * there can be but one running RCU reader at a time. ;-) */static int rcu_preempt_running_reader(void){ return current->rcu_read_lock_nesting;} /* * Check for preempted RCU readers blocking any grace period. * If the caller needs a reliable answer, it must disable hard irqs. */static int rcu_preempt_blocked_readers_any(void){ return !list_empty(&rcu_preempt_ctrlblk.blkd_tasks);} /* * Check for preempted RCU readers blocking the current grace period. * If the caller needs a reliable answer, it must disable hard irqs. */static int rcu_preempt_blocked_readers_cgp(void){ return rcu_preempt_ctrlblk.gp_tasks != NULL;} /* * Return true if another preemptible-RCU grace period is needed. */static int rcu_preempt_needs_another_gp(void){ return *rcu_preempt_ctrlblk.rcb.curtail != NULL;} /* * Return true if a preemptible-RCU grace period is in progress. * The caller must disable hardirqs. */static int rcu_preempt_gp_in_progress(void){ return rcu_preempt_ctrlblk.completed != rcu_preempt_ctrlblk.gpnum;} /* * 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 list_head *np; np = t->rcu_node_entry.next; if (np == &rcu_preempt_ctrlblk.blkd_tasks) np = NULL; return np;} #ifdef CONFIG_RCU_TRACE #ifdef CONFIG_RCU_BOOSTstatic void rcu_initiate_boost_trace(void);#endif /* #ifdef CONFIG_RCU_BOOST */ /* * Dump additional statistice for TINY_PREEMPT_RCU. */static void show_tiny_preempt_stats(struct seq_file *m){ seq_printf(m, "rcu_preempt: qlen=%ld gp=%lu g%u/p%u/c%u tasks=%c%c%c\n", rcu_preempt_ctrlblk.rcb.qlen, rcu_preempt_ctrlblk.n_grace_periods, rcu_preempt_ctrlblk.gpnum, rcu_preempt_ctrlblk.gpcpu, rcu_preempt_ctrlblk.completed, "T."[list_empty(&rcu_preempt_ctrlblk.blkd_tasks)], "N."[!rcu_preempt_ctrlblk.gp_tasks], "E."[!rcu_preempt_ctrlblk.exp_tasks]);#ifdef CONFIG_RCU_BOOST seq_printf(m, "%sttb=%c ntb=%lu neb=%lu nnb=%lu j=%04x bt=%04x\n", " ", "B."[!rcu_preempt_ctrlblk.boost_tasks], rcu_preempt_ctrlblk.n_tasks_boosted, rcu_preempt_ctrlblk.n_exp_boosts, rcu_preempt_ctrlblk.n_normal_boosts, (int)(jiffies & 0xffff), (int)(rcu_preempt_ctrlblk.boost_time & 0xffff)); seq_printf(m, "%s: nt=%lu egt=%lu bt=%lu ny=%lu nos=%lu\n", " balk", rcu_preempt_ctrlblk.n_balk_blkd_tasks, rcu_preempt_ctrlblk.n_balk_exp_gp_tasks, rcu_preempt_ctrlblk.n_balk_boost_tasks, rcu_preempt_ctrlblk.n_balk_notyet, rcu_preempt_ctrlblk.n_balk_nos);#endif /* #ifdef CONFIG_RCU_BOOST */} #endif /* #ifdef CONFIG_RCU_TRACE */ #ifdef CONFIG_RCU_BOOST #include "rtmutex_common.h" #define RCU_BOOST_PRIO CONFIG_RCU_BOOST_PRIO /* Controls for rcu_kthread() kthread. */static struct task_struct *rcu_kthread_task;static DECLARE_WAIT_QUEUE_HEAD(rcu_kthread_wq);static unsigned long have_rcu_kthread_work; /* * Carry out RCU priority boosting on the task indicated by ->boost_tasks, * and advance ->boost_tasks to the next task in the ->blkd_tasks list. */static int rcu_boost(void){ unsigned long flags; struct rt_mutex mtx; struct task_struct *t; struct list_head *tb; if (rcu_preempt_ctrlblk.boost_tasks == NULL && rcu_preempt_ctrlblk.exp_tasks == NULL) return 0; /* Nothing to boost. */ raw_local_irq_save(flags); /* * Recheck with irqs disabled: all tasks in need of boosting * might exit their RCU read-side critical sections on their own * if we are preempted just before disabling irqs. */ if (rcu_preempt_ctrlblk.boost_tasks == NULL && rcu_preempt_ctrlblk.exp_tasks == NULL) { raw_local_irq_restore(flags); return 0; } /* * Preferentially boost tasks blocking expedited grace periods. * This cannot starve the normal grace periods because a second * expedited grace period must boost all blocked tasks, including * those blocking the pre-existing normal grace period. */ if (rcu_preempt_ctrlblk.exp_tasks != NULL) { tb = rcu_preempt_ctrlblk.exp_tasks; RCU_TRACE(rcu_preempt_ctrlblk.n_exp_boosts++); } else { tb = rcu_preempt_ctrlblk.boost_tasks; RCU_TRACE(rcu_preempt_ctrlblk.n_normal_boosts++); } RCU_TRACE(rcu_preempt_ctrlblk.n_tasks_boosted++); /* * We boost task t by manufacturing an rt_mutex that appears to * be held by task t. We leave a pointer to that rt_mutex where * task t can find it, and task t will release the mutex when it * exits its outermost RCU read-side critical section. Then * simply acquiring this artificial rt_mutex will boost task * t's priority. (Thanks to tglx for suggesting this approach!) */ t = container_of(tb, struct task_struct, rcu_node_entry); rt_mutex_init_proxy_locked(&mtx, t); t->rcu_boost_mutex = &mtx; t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BOOSTED; raw_local_irq_restore(flags); rt_mutex_lock(&mtx); rt_mutex_unlock(&mtx); /* Keep lockdep happy. */ return ACCESS_ONCE(rcu_preempt_ctrlblk.boost_tasks) != NULL || ACCESS_ONCE(rcu_preempt_ctrlblk.exp_tasks) != NULL;} /* * Check to see if it is now time to start boosting RCU readers blocking * the current grace period, and, if so, tell the rcu_kthread_task to * start boosting them. If there is an expedited boost in progress, * we wait for it to complete. * * If there are no blocked readers blocking the current grace period, * return 0 to let the caller know, otherwise return 1. Note that this * return value is independent of whether or not boosting was done. */static int rcu_initiate_boost(void){ if (!rcu_preempt_blocked_readers_cgp() && rcu_preempt_ctrlblk.exp_tasks == NULL) { RCU_TRACE(rcu_preempt_ctrlblk.n_balk_exp_gp_tasks++); return 0; } if (rcu_preempt_ctrlblk.exp_tasks != NULL || (rcu_preempt_ctrlblk.gp_tasks != NULL && rcu_preempt_ctrlblk.boost_tasks == NULL && ULONG_CMP_GE(jiffies, rcu_preempt_ctrlblk.boost_time))) { if (rcu_preempt_ctrlblk.exp_tasks == NULL) rcu_preempt_ctrlblk.boost_tasks = rcu_preempt_ctrlblk.gp_tasks; invoke_rcu_callbacks(); } else RCU_TRACE(rcu_initiate_boost_trace()); return 1;} #define RCU_BOOST_DELAY_JIFFIES DIV_ROUND_UP(CONFIG_RCU_BOOST_DELAY * HZ, 1000) /* * Do priority-boost accounting for the start of a new grace period. */static void rcu_preempt_boost_start_gp(void){ rcu_preempt_ctrlblk.boost_time = jiffies + RCU_BOOST_DELAY_JIFFIES;} #else /* #ifdef CONFIG_RCU_BOOST */ /* * If there is no RCU priority boosting, we don't initiate boosting, * but we do indicate whether there are blocked readers blocking the * current grace period. */static int rcu_initiate_boost(void){ return rcu_preempt_blocked_readers_cgp();} /* * If there is no RCU priority boosting, nothing to do at grace-period start. */static void rcu_preempt_boost_start_gp(void){} #endif /* else #ifdef CONFIG_RCU_BOOST */ /* * Record a preemptible-RCU quiescent state for the specified CPU. Note * that this just means that the task currently running on the CPU is * in a quiescent state. There might be any number of tasks blocked * while in an RCU read-side critical section. * * Unlike the other rcu_*_qs() functions, callers to this function * must disable irqs in order to protect the assignment to * ->rcu_read_unlock_special. * * Because this is a single-CPU implementation, the only way a grace * period can end is if the CPU is in a quiescent state. The reason is * that a blocked preemptible-RCU reader can exit its critical section * only if the CPU is running it at the time. Therefore, when the * last task blocking the current grace period exits its RCU read-side * critical section, neither the CPU nor blocked tasks will be stopping * the current grace period. (In contrast, SMP implementations * might have CPUs running in RCU read-side critical sections that * block later grace periods -- but this is not possible given only * one CPU.) */static void rcu_preempt_cpu_qs(void){ /* Record both CPU and task as having responded to current GP. */ rcu_preempt_ctrlblk.gpcpu = rcu_preempt_ctrlblk.gpnum; current->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS; /* If there is no GP then there is nothing more to do. */ if (!rcu_preempt_gp_in_progress()) return; /* * Check up on boosting. If there are readers blocking the * current grace period, leave. */ if (rcu_initiate_boost()) return; /* Advance callbacks. */ rcu_preempt_ctrlblk.completed = rcu_preempt_ctrlblk.gpnum; rcu_preempt_ctrlblk.rcb.donetail = rcu_preempt_ctrlblk.rcb.curtail; rcu_preempt_ctrlblk.rcb.curtail = rcu_preempt_ctrlblk.nexttail; /* If there are no blocked readers, next GP is done instantly. */ if (!rcu_preempt_blocked_readers_any()) rcu_preempt_ctrlblk.rcb.donetail = rcu_preempt_ctrlblk.nexttail; /* If there are done callbacks, cause them to be invoked. */ if (*rcu_preempt_ctrlblk.rcb.donetail != NULL) invoke_rcu_callbacks();} /* * Start a new RCU grace period if warranted. Hard irqs must be disabled. */static void rcu_preempt_start_gp(void){ if (!rcu_preempt_gp_in_progress() && rcu_preempt_needs_another_gp()) { /* Official start of GP. */ rcu_preempt_ctrlblk.gpnum++; RCU_TRACE(rcu_preempt_ctrlblk.n_grace_periods++); /* Any blocked RCU readers block new GP. */ if (rcu_preempt_blocked_readers_any()) rcu_preempt_ctrlblk.gp_tasks = rcu_preempt_ctrlblk.blkd_tasks.next; /* Set up for RCU priority boosting. */ rcu_preempt_boost_start_gp(); /* If there is no running reader, CPU is done with GP. */ if (!rcu_preempt_running_reader()) rcu_preempt_cpu_qs(); }} /* * 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. * If the task started after the current grace period began, as recorded * by ->gpcpu, we enqueue at the beginning of the list. Otherwise * before the element referenced by ->gp_tasks (or at the tail if * ->gp_tasks is NULL) and point ->gp_tasks at the newly added element. * 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 ->gp_tasks pointer becomes * NULL. * * Caller must disable preemption. */void rcu_preempt_note_context_switch(void){ struct task_struct *t = current; unsigned long flags; local_irq_save(flags); /* must exclude scheduler_tick(). */ if (rcu_preempt_running_reader() && (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) { /* Possibly blocking in an RCU read-side critical section. */ t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED; /* * If this CPU has already checked in, then this task * will hold up the next grace period rather than the * current grace period. Queue the task accordingly. * If the task is queued for the current grace period * (i.e., this CPU has not yet passed through a quiescent * state for the current grace period), then as long * as that task remains queued, the current grace period * cannot end. */ list_add(&t->rcu_node_entry, &rcu_preempt_ctrlblk.blkd_tasks); if (rcu_cpu_blocking_cur_gp()) rcu_preempt_ctrlblk.gp_tasks = &t->rcu_node_entry; } /* * Either we were not in an RCU read-side critical section toLines 1–500 of 1073. Load more
/* * Read-Copy Update mechanism for mutual exclusion, the Bloatwatch edition * 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, write to the Free Software * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. * * Copyright (c) 2010 Linaro * * Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com> */ #include <linux/kthread.h> #include <linux/module.h> #include <linux/debugfs.h> #include <linux/seq_file.h> /* Global control variables for rcupdate callback mechanism. */ struct rcu_ctrlblk { struct rcu_head *rcucblist; /* List of pending callbacks (CBs). */ struct rcu_head **donetail; /* ->next pointer of last "done" CB. */ struct rcu_head **curtail; /* ->next pointer of last CB. */ RCU_TRACE(long qlen); /* Number of pending CBs. */ RCU_TRACE(char *name); /* Name of RCU type. */ }; /* Definition for rcupdate control block. */ static struct rcu_ctrlblk rcu_sched_ctrlblk = { .donetail = &rcu_sched_ctrlblk.rcucblist, .curtail = &rcu_sched_ctrlblk.rcucblist, RCU_TRACE(.name = "rcu_sched") }; static struct rcu_ctrlblk rcu_bh_ctrlblk = { .donetail = &rcu_bh_ctrlblk.rcucblist, .curtail = &rcu_bh_ctrlblk.rcucblist, RCU_TRACE(.name = "rcu_bh") }; #ifdef CONFIG_DEBUG_LOCK_ALLOC int rcu_scheduler_active __read_mostly; EXPORT_SYMBOL_GPL(rcu_scheduler_active); #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #ifdef CONFIG_TINY_PREEMPT_RCU #include <linux/delay.h> /* Global control variables for preemptible RCU. */ struct rcu_preempt_ctrlblk { struct rcu_ctrlblk rcb; /* curtail: ->next ptr of last CB for GP. */ struct rcu_head **nexttail; /* Tasks blocked in a preemptible RCU */ /* read-side critical section while an */ /* preemptible-RCU grace period is in */ /* progress must wait for a later grace */ /* period. This pointer points to the */ /* ->next pointer of the last task that */ /* must wait for a later grace period, or */ /* to &->rcb.rcucblist if there is no */ /* such task. */ struct list_head blkd_tasks; /* Tasks blocked in RCU read-side critical */ /* section. Tasks are placed at the head */ /* of this list and age towards the tail. */ struct list_head *gp_tasks; /* Pointer to the first task blocking the */ /* current grace period, or NULL if there */ /* is no such task. */ struct list_head *exp_tasks; /* Pointer to first task blocking the */ /* current expedited grace period, or NULL */ /* if there is no such task. If there */ /* is no current expedited grace period, */ /* then there cannot be any such task. */ #ifdef CONFIG_RCU_BOOST struct list_head *boost_tasks; /* Pointer to first task that needs to be */ /* priority-boosted, or NULL if no priority */ /* boosting is needed. If there is no */ /* current or expedited grace period, there */ /* can be no such task. */ #endif /* #ifdef CONFIG_RCU_BOOST */ u8 gpnum; /* Current grace period. */ u8 gpcpu; /* Last grace period blocked by the CPU. */ u8 completed; /* Last grace period completed. */ /* If all three are equal, RCU is idle. */ #ifdef CONFIG_RCU_BOOST unsigned long boost_time; /* When to start boosting (jiffies) */ #endif /* #ifdef CONFIG_RCU_BOOST */ #ifdef CONFIG_RCU_TRACE unsigned long n_grace_periods; #ifdef CONFIG_RCU_BOOST unsigned long n_tasks_boosted; /* Total number of tasks boosted. */ unsigned long n_exp_boosts; /* Number of tasks boosted for expedited GP. */ unsigned long n_normal_boosts; /* Number of tasks boosted for normal GP. */ unsigned long n_balk_blkd_tasks; /* Refused to boost: no blocked tasks. */ unsigned long n_balk_exp_gp_tasks; /* Refused to boost: nothing blocking GP. */ unsigned long n_balk_boost_tasks; /* Refused to boost: already boosting. */ unsigned long n_balk_notyet; /* Refused to boost: not yet time. */ unsigned long n_balk_nos; /* Refused to boost: not sure why, though. */ /* This can happen due to race conditions. */ #endif /* #ifdef CONFIG_RCU_BOOST */ #endif /* #ifdef CONFIG_RCU_TRACE */ }; static struct rcu_preempt_ctrlblk rcu_preempt_ctrlblk = { .rcb.donetail = &rcu_preempt_ctrlblk.rcb.rcucblist, .rcb.curtail = &rcu_preempt_ctrlblk.rcb.rcucblist, .nexttail = &rcu_preempt_ctrlblk.rcb.rcucblist, .blkd_tasks = LIST_HEAD_INIT(rcu_preempt_ctrlblk.blkd_tasks), RCU_TRACE(.rcb.name = "rcu_preempt") }; static int rcu_preempted_readers_exp(void); static void rcu_report_exp_done(void); /* * Return true if the CPU has not yet responded to the current grace period. */ static int rcu_cpu_blocking_cur_gp(void) { return rcu_preempt_ctrlblk.gpcpu != rcu_preempt_ctrlblk.gpnum; } /* * Check for a running RCU reader. Because there is only one CPU, * there can be but one running RCU reader at a time. ;-) */ static int rcu_preempt_running_reader(void) { return current->rcu_read_lock_nesting; } /* * Check for preempted RCU readers blocking any grace period. * If the caller needs a reliable answer, it must disable hard irqs. */ static int rcu_preempt_blocked_readers_any(void) { return !list_empty(&rcu_preempt_ctrlblk.blkd_tasks); } /* * Check for preempted RCU readers blocking the current grace period. * If the caller needs a reliable answer, it must disable hard irqs. */ static int rcu_preempt_blocked_readers_cgp(void) { return rcu_preempt_ctrlblk.gp_tasks != NULL; } /* * Return true if another preemptible-RCU grace period is needed. */ static int rcu_preempt_needs_another_gp(void) { return *rcu_preempt_ctrlblk.rcb.curtail != NULL; } /* * Return true if a preemptible-RCU grace period is in progress. * The caller must disable hardirqs. */ static int rcu_preempt_gp_in_progress(void) { return rcu_preempt_ctrlblk.completed != rcu_preempt_ctrlblk.gpnum; } /* * 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 list_head *np; np = t->rcu_node_entry.next; if (np == &rcu_preempt_ctrlblk.blkd_tasks) np = NULL; return np; } #ifdef CONFIG_RCU_TRACE #ifdef CONFIG_RCU_BOOST static void rcu_initiate_boost_trace(void); #endif /* #ifdef CONFIG_RCU_BOOST */ /* * Dump additional statistice for TINY_PREEMPT_RCU. */ static void show_tiny_preempt_stats(struct seq_file *m) { seq_printf(m, "rcu_preempt: qlen=%ld gp=%lu g%u/p%u/c%u tasks=%c%c%c\n", rcu_preempt_ctrlblk.rcb.qlen, rcu_preempt_ctrlblk.n_grace_periods, rcu_preempt_ctrlblk.gpnum, rcu_preempt_ctrlblk.gpcpu, rcu_preempt_ctrlblk.completed, "T."[list_empty(&rcu_preempt_ctrlblk.blkd_tasks)], "N."[!rcu_preempt_ctrlblk.gp_tasks], "E."[!rcu_preempt_ctrlblk.exp_tasks]); #ifdef CONFIG_RCU_BOOST seq_printf(m, "%sttb=%c ntb=%lu neb=%lu nnb=%lu j=%04x bt=%04x\n", " ", "B."[!rcu_preempt_ctrlblk.boost_tasks], rcu_preempt_ctrlblk.n_tasks_boosted, rcu_preempt_ctrlblk.n_exp_boosts, rcu_preempt_ctrlblk.n_normal_boosts, (int)(jiffies & 0xffff), (int)(rcu_preempt_ctrlblk.boost_time & 0xffff)); seq_printf(m, "%s: nt=%lu egt=%lu bt=%lu ny=%lu nos=%lu\n", " balk", rcu_preempt_ctrlblk.n_balk_blkd_tasks, rcu_preempt_ctrlblk.n_balk_exp_gp_tasks, rcu_preempt_ctrlblk.n_balk_boost_tasks, rcu_preempt_ctrlblk.n_balk_notyet, rcu_preempt_ctrlblk.n_balk_nos); #endif /* #ifdef CONFIG_RCU_BOOST */ } #endif /* #ifdef CONFIG_RCU_TRACE */ #ifdef CONFIG_RCU_BOOST #include "rtmutex_common.h" #define RCU_BOOST_PRIO CONFIG_RCU_BOOST_PRIO /* Controls for rcu_kthread() kthread. */ static struct task_struct *rcu_kthread_task; static DECLARE_WAIT_QUEUE_HEAD(rcu_kthread_wq); static unsigned long have_rcu_kthread_work; /* * Carry out RCU priority boosting on the task indicated by ->boost_tasks, * and advance ->boost_tasks to the next task in the ->blkd_tasks list. */ static int rcu_boost(void) { unsigned long flags; struct rt_mutex mtx; struct task_struct *t; struct list_head *tb; if (rcu_preempt_ctrlblk.boost_tasks == NULL && rcu_preempt_ctrlblk.exp_tasks == NULL) return 0; /* Nothing to boost. */ raw_local_irq_save(flags); /* * Recheck with irqs disabled: all tasks in need of boosting * might exit their RCU read-side critical sections on their own * if we are preempted just before disabling irqs. */ if (rcu_preempt_ctrlblk.boost_tasks == NULL && rcu_preempt_ctrlblk.exp_tasks == NULL) { raw_local_irq_restore(flags); return 0; } /* * Preferentially boost tasks blocking expedited grace periods. * This cannot starve the normal grace periods because a second * expedited grace period must boost all blocked tasks, including * those blocking the pre-existing normal grace period. */ if (rcu_preempt_ctrlblk.exp_tasks != NULL) { tb = rcu_preempt_ctrlblk.exp_tasks; RCU_TRACE(rcu_preempt_ctrlblk.n_exp_boosts++); } else { tb = rcu_preempt_ctrlblk.boost_tasks; RCU_TRACE(rcu_preempt_ctrlblk.n_normal_boosts++); } RCU_TRACE(rcu_preempt_ctrlblk.n_tasks_boosted++); /* * We boost task t by manufacturing an rt_mutex that appears to * be held by task t. We leave a pointer to that rt_mutex where * task t can find it, and task t will release the mutex when it * exits its outermost RCU read-side critical section. Then * simply acquiring this artificial rt_mutex will boost task * t's priority. (Thanks to tglx for suggesting this approach!) */ t = container_of(tb, struct task_struct, rcu_node_entry); rt_mutex_init_proxy_locked(&mtx, t); t->rcu_boost_mutex = &mtx; t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BOOSTED; raw_local_irq_restore(flags); rt_mutex_lock(&mtx); rt_mutex_unlock(&mtx); /* Keep lockdep happy. */ return ACCESS_ONCE(rcu_preempt_ctrlblk.boost_tasks) != NULL || ACCESS_ONCE(rcu_preempt_ctrlblk.exp_tasks) != NULL; } /* * Check to see if it is now time to start boosting RCU readers blocking * the current grace period, and, if so, tell the rcu_kthread_task to * start boosting them. If there is an expedited boost in progress, * we wait for it to complete. * * If there are no blocked readers blocking the current grace period, * return 0 to let the caller know, otherwise return 1. Note that this * return value is independent of whether or not boosting was done. */ static int rcu_initiate_boost(void) { if (!rcu_preempt_blocked_readers_cgp() && rcu_preempt_ctrlblk.exp_tasks == NULL) { RCU_TRACE(rcu_preempt_ctrlblk.n_balk_exp_gp_tasks++); return 0; } if (rcu_preempt_ctrlblk.exp_tasks != NULL || (rcu_preempt_ctrlblk.gp_tasks != NULL && rcu_preempt_ctrlblk.boost_tasks == NULL && ULONG_CMP_GE(jiffies, rcu_preempt_ctrlblk.boost_time))) { if (rcu_preempt_ctrlblk.exp_tasks == NULL) rcu_preempt_ctrlblk.boost_tasks = rcu_preempt_ctrlblk.gp_tasks; invoke_rcu_callbacks(); } else RCU_TRACE(rcu_initiate_boost_trace()); return 1; } #define RCU_BOOST_DELAY_JIFFIES DIV_ROUND_UP(CONFIG_RCU_BOOST_DELAY * HZ, 1000) /* * Do priority-boost accounting for the start of a new grace period. */ static void rcu_preempt_boost_start_gp(void) { rcu_preempt_ctrlblk.boost_time = jiffies + RCU_BOOST_DELAY_JIFFIES; } #else /* #ifdef CONFIG_RCU_BOOST */ /* * If there is no RCU priority boosting, we don't initiate boosting, * but we do indicate whether there are blocked readers blocking the * current grace period. */ static int rcu_initiate_boost(void) { return rcu_preempt_blocked_readers_cgp(); } /* * If there is no RCU priority boosting, nothing to do at grace-period start. */ static void rcu_preempt_boost_start_gp(void) { } #endif /* else #ifdef CONFIG_RCU_BOOST */ /* * Record a preemptible-RCU quiescent state for the specified CPU. Note * that this just means that the task currently running on the CPU is * in a quiescent state. There might be any number of tasks blocked * while in an RCU read-side critical section. * * Unlike the other rcu_*_qs() functions, callers to this function * must disable irqs in order to protect the assignment to * ->rcu_read_unlock_special. * * Because this is a single-CPU implementation, the only way a grace * period can end is if the CPU is in a quiescent state. The reason is * that a blocked preemptible-RCU reader can exit its critical section * only if the CPU is running it at the time. Therefore, when the * last task blocking the current grace period exits its RCU read-side * critical section, neither the CPU nor blocked tasks will be stopping * the current grace period. (In contrast, SMP implementations * might have CPUs running in RCU read-side critical sections that * block later grace periods -- but this is not possible given only * one CPU.) */ static void rcu_preempt_cpu_qs(void) { /* Record both CPU and task as having responded to current GP. */ rcu_preempt_ctrlblk.gpcpu = rcu_preempt_ctrlblk.gpnum; current->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS; /* If there is no GP then there is nothing more to do. */ if (!rcu_preempt_gp_in_progress()) return; /* * Check up on boosting. If there are readers blocking the * current grace period, leave. */ if (rcu_initiate_boost()) return; /* Advance callbacks. */ rcu_preempt_ctrlblk.completed = rcu_preempt_ctrlblk.gpnum; rcu_preempt_ctrlblk.rcb.donetail = rcu_preempt_ctrlblk.rcb.curtail; rcu_preempt_ctrlblk.rcb.curtail = rcu_preempt_ctrlblk.nexttail; /* If there are no blocked readers, next GP is done instantly. */ if (!rcu_preempt_blocked_readers_any()) rcu_preempt_ctrlblk.rcb.donetail = rcu_preempt_ctrlblk.nexttail; /* If there are done callbacks, cause them to be invoked. */ if (*rcu_preempt_ctrlblk.rcb.donetail != NULL) invoke_rcu_callbacks(); } /* * Start a new RCU grace period if warranted. Hard irqs must be disabled. */ static void rcu_preempt_start_gp(void) { if (!rcu_preempt_gp_in_progress() && rcu_preempt_needs_another_gp()) { /* Official start of GP. */ rcu_preempt_ctrlblk.gpnum++; RCU_TRACE(rcu_preempt_ctrlblk.n_grace_periods++); /* Any blocked RCU readers block new GP. */ if (rcu_preempt_blocked_readers_any()) rcu_preempt_ctrlblk.gp_tasks = rcu_preempt_ctrlblk.blkd_tasks.next; /* Set up for RCU priority boosting. */ rcu_preempt_boost_start_gp(); /* If there is no running reader, CPU is done with GP. */ if (!rcu_preempt_running_reader()) rcu_preempt_cpu_qs(); } } /* * 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. * If the task started after the current grace period began, as recorded * by ->gpcpu, we enqueue at the beginning of the list. Otherwise * before the element referenced by ->gp_tasks (or at the tail if * ->gp_tasks is NULL) and point ->gp_tasks at the newly added element. * 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 ->gp_tasks pointer becomes * NULL. * * Caller must disable preemption. */ void rcu_preempt_note_context_switch(void) { struct task_struct *t = current; unsigned long flags; local_irq_save(flags); /* must exclude scheduler_tick(). */ if (rcu_preempt_running_reader() && (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) { /* Possibly blocking in an RCU read-side critical section. */ t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED; /* * If this CPU has already checked in, then this task * will hold up the next grace period rather than the * current grace period. Queue the task accordingly. * If the task is queued for the current grace period * (i.e., this CPU has not yet passed through a quiescent * state for the current grace period), then as long * as that task remains queued, the current grace period * cannot end. */ list_add(&t->rcu_node_entry, &rcu_preempt_ctrlblk.blkd_tasks); if (rcu_cpu_blocking_cur_gp()) rcu_preempt_ctrlblk.gp_tasks = &t->rcu_node_entry; } /* * Either we were not in an RCU read-side critical section to