/* * 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, write to the Free Software * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. * * 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 <linux/tick.h> #define RCU_KTHREAD_PRIO 1 #ifdef CONFIG_RCU_BOOST#define RCU_BOOST_PRIO CONFIG_RCU_BOOST_PRIO#else#define RCU_BOOST_PRIO RCU_KTHREAD_PRIO#endif #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. */static char __initdata nocb_buf[NR_CPUS * 5];#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){#ifdef CONFIG_RCU_TRACE	printk(KERN_INFO "\tRCU debugfs-based tracing is enabled.\n");#endif#if (defined(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 64) || (!defined(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 32)	printk(KERN_INFO "\tCONFIG_RCU_FANOUT set to non-default value of %d\n",	       CONFIG_RCU_FANOUT);#endif#ifdef CONFIG_RCU_FANOUT_EXACT	printk(KERN_INFO "\tHierarchical RCU autobalancing is disabled.\n");#endif#ifdef CONFIG_RCU_FAST_NO_HZ	printk(KERN_INFO	       "\tRCU dyntick-idle grace-period acceleration is enabled.\n");#endif#ifdef CONFIG_PROVE_RCU	printk(KERN_INFO "\tRCU lockdep checking is enabled.\n");#endif#ifdef CONFIG_RCU_TORTURE_TEST_RUNNABLE	printk(KERN_INFO "\tRCU torture testing starts during boot.\n");#endif#if defined(CONFIG_TREE_PREEMPT_RCU) && !defined(CONFIG_RCU_CPU_STALL_VERBOSE)	printk(KERN_INFO "\tDump stacks of tasks blocking RCU-preempt GP.\n");#endif#if defined(CONFIG_RCU_CPU_STALL_INFO)	printk(KERN_INFO "\tAdditional per-CPU info printed with stalls.\n");#endif#if NUM_RCU_LVL_4 != 0	printk(KERN_INFO "\tFour-level hierarchy is enabled.\n");#endif	if (rcu_fanout_leaf != CONFIG_RCU_FANOUT_LEAF)		printk(KERN_INFO "\tExperimental boot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf);	if (nr_cpu_ids != NR_CPUS)		printk(KERN_INFO "\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids);#ifdef CONFIG_RCU_NOCB_CPU#ifndef CONFIG_RCU_NOCB_CPU_NONE	if (!have_rcu_nocb_mask) {		zalloc_cpumask_var(&rcu_nocb_mask, GFP_KERNEL);		have_rcu_nocb_mask = true;	}#ifdef CONFIG_RCU_NOCB_CPU_ZERO	pr_info("\tExperimental no-CBs CPU 0\n");	cpumask_set_cpu(0, rcu_nocb_mask);#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ZERO */#ifdef CONFIG_RCU_NOCB_CPU_ALL	pr_info("\tExperimental no-CBs for all CPUs\n");	cpumask_setall(rcu_nocb_mask);#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ALL */#endif /* #ifndef CONFIG_RCU_NOCB_CPU_NONE */	if (have_rcu_nocb_mask) {		cpulist_scnprintf(nocb_buf, sizeof(nocb_buf), rcu_nocb_mask);		pr_info("\tExperimental no-CBs CPUs: %s.\n", nocb_buf);		if (rcu_nocb_poll)			pr_info("\tExperimental polled no-CBs CPUs.\n");	}#endif /* #ifdef CONFIG_RCU_NOCB_CPU */} #ifdef CONFIG_TREE_PREEMPT_RCU struct rcu_state rcu_preempt_state =	RCU_STATE_INITIALIZER(rcu_preempt, 'p', call_rcu);DEFINE_PER_CPU(struct rcu_data, rcu_preempt_data);static struct rcu_state *rcu_state = &rcu_preempt_state; static int rcu_preempted_readers_exp(struct rcu_node *rnp); /* * Tell them what RCU they are running. */static void __init rcu_bootup_announce(void){	printk(KERN_INFO "Preemptible hierarchical RCU implementation.\n");	rcu_bootup_announce_oddness();} /* * Return the number of RCU-preempt batches processed thus far * for debug and statistics. */long rcu_batches_completed_preempt(void){	return rcu_preempt_state.completed;}EXPORT_SYMBOL_GPL(rcu_batches_completed_preempt); /* * Return the number of RCU batches processed thus far for debug & stats. */long rcu_batches_completed(void){	return rcu_batches_completed_preempt();}EXPORT_SYMBOL_GPL(rcu_batches_completed); /* * Force a quiescent state for preemptible RCU. */void rcu_force_quiescent_state(void){	force_quiescent_state(&rcu_preempt_state);}EXPORT_SYMBOL_GPL(rcu_force_quiescent_state); /* * 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. * * Unlike the other rcu_*_qs() functions, callers to this function * must disable irqs in order to protect the assignment to * ->rcu_read_unlock_special. */static void rcu_preempt_qs(int cpu){	struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu); 	if (rdp->passed_quiesce == 0)		trace_rcu_grace_period("rcu_preempt", rdp->gpnum, "cpuqs");	rdp->passed_quiesce = 1;	current->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_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. * 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(int cpu){	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 & RCU_READ_UNLOCK_BLOCKED) == 0) { 		/* Possibly blocking in an RCU read-side critical section. */		rdp = per_cpu_ptr(rcu_preempt_state.rda, cpu);		rnp = rdp->mynode;		raw_spin_lock_irqsave(&rnp->lock, flags);		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;		t->rcu_blocked_node = rnp; 		/*		 * 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.  Note that there is some uncertainty as		 * to exactly when the current grace period started.		 * We take a conservative approach, which can result		 * in unnecessarily waiting on tasks that started very		 * slightly after the current grace period began.  C'est		 * la vie!!!		 *		 * But first, note that the current CPU must still be		 * on line!		 */		WARN_ON_ONCE((rdp->grpmask & rnp->qsmaskinit) == 0);		WARN_ON_ONCE(!list_empty(&t->rcu_node_entry));		if ((rnp->qsmask & rdp->grpmask) && rnp->gp_tasks != NULL) {			list_add(&t->rcu_node_entry, rnp->gp_tasks->prev);			rnp->gp_tasks = &t->rcu_node_entry;#ifdef CONFIG_RCU_BOOST			if (rnp->boost_tasks != NULL)				rnp->boost_tasks = rnp->gp_tasks;#endif /* #ifdef CONFIG_RCU_BOOST */		} else {			list_add(&t->rcu_node_entry, &rnp->blkd_tasks);			if (rnp->qsmask & rdp->grpmask)				rnp->gp_tasks = &t->rcu_node_entry;		}		trace_rcu_preempt_task(rdp->rsp->name,				       t->pid,				       (rnp->qsmask & rdp->grpmask)				       ? rnp->gpnum				       : rnp->gpnum + 1);		raw_spin_unlock_irqrestore(&rnp->lock, flags);	} else if (t->rcu_read_lock_nesting < 0 &&		   t->rcu_read_unlock_special) { 		/*		 * 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.	 */	local_irq_save(flags);	rcu_preempt_qs(cpu);	local_irq_restore(flags);} /* * 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;} /* * Record a quiescent state for all tasks that were previously queued * on the specified rcu_node structure and that were blocking the current * RCU grace period.  The caller must hold the specified rnp->lock with * irqs disabled, and this lock is released upon return, but irqs remain * disabled. */static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)	__releases(rnp->lock){	unsigned long mask;	struct rcu_node *rnp_p; 	if (rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) {		raw_spin_unlock_irqrestore(&rnp->lock, flags);		return;  /* Still need more quiescent states! */	} 	rnp_p = rnp->parent;	if (rnp_p == NULL) {		/*		 * Either there is only one rcu_node in the tree,		 * or tasks were kicked up to root rcu_node due to		 * CPUs going offline.		 */		rcu_report_qs_rsp(&rcu_preempt_state, flags);		return;	} 	/* Report up the rest of the hierarchy. */	mask = rnp->grpmask;	raw_spin_unlock(&rnp->lock);	/* irqs remain disabled. */	raw_spin_lock(&rnp_p->lock);	/* irqs already disabled. */	rcu_report_qs_rnp(mask, &rcu_preempt_state, rnp_p, flags);} /* * 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;} /* * 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){	int empty;	int empty_exp;	int empty_exp_now;	unsigned long flags;	struct list_head *np;#ifdef CONFIG_RCU_BOOST	struct rt_mutex *rbmp = NULL;#endif /* #ifdef CONFIG_RCU_BOOST */	struct rcu_node *rnp;	int 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 critical section,	 * let it know that we have done so.	 */	special = t->rcu_read_unlock_special;	if (special & RCU_READ_UNLOCK_NEED_QS) {		rcu_preempt_qs(smp_processor_id());	} 	/* Hardware IRQ handlers cannot block. */	if (in_irq() || in_serving_softirq()) {		local_irq_restore(flags);		return;	} 	/* Clean up if blocked during RCU read-side critical section. */	if (special & RCU_READ_UNLOCK_BLOCKED) {		t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_BLOCKED; 		/*		 * Remove this task from the list it blocked on.  The		 * task can migrate while we acquire the lock, but at		 * most one time.  So at most two passes through loop.		 */		for (;;) {			rnp = t->rcu_blocked_node;			raw_spin_lock(&rnp->lock);  /* irqs already disabled. */			if (rnp == t->rcu_blocked_node)				break;			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */		}		empty = !rcu_preempt_blocked_readers_cgp(rnp);		empty_exp = !rcu_preempted_readers_exp(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("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;#ifdef CONFIG_RCU_BOOST		if (&t->rcu_node_entry == rnp->boost_tasks)			rnp->boost_tasks = np;		/* Snapshot/clear ->rcu_boost_mutex with rcu_node lock held. */		if (t->rcu_boost_mutex) {			rbmp = t->rcu_boost_mutex;			t->rcu_boost_mutex = NULL;		}#endif /* #ifdef CONFIG_RCU_BOOST */ 		/*		 * 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 = !rcu_preempted_readers_exp(rnp);		if (!empty && !rcu_preempt_blocked_readers_cgp(rnp)) {			trace_rcu_quiescent_state_report("preempt_rcu",							 rnp->gpnum,							 0, rnp->qsmask,							 rnp->level,							 rnp->grplo,							 rnp->grphi,							 !!rnp->gp_tasks);			rcu_report_unblock_qs_rnp(rnp, flags);		} else {			raw_spin_unlock_irqrestore(&rnp->lock, flags);		} #ifdef CONFIG_RCU_BOOST		/* Unboost if we were boosted. */		if (rbmp)			rt_mutex_unlock(rbmp);#endif /* #ifdef CONFIG_RCU_BOOST */ 		/*		 * If this was the last task on the expedited lists,		 * then we need to report up the rcu_node hierarchy.		 */		if (!empty_exp && empty_exp_now)			rcu_report_exp_rnp(&rcu_preempt_state, rnp, true);	} else {		local_irq_restore(flags);	}} #ifdef CONFIG_RCU_CPU_STALL_VERBOSE /* * Dump detailed information for all tasks blocking the current RCU * grace period on the specified rcu_node structure. */static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp){	unsigned long flags;	struct task_struct *t; 	raw_spin_lock_irqsave(&rnp->lock, flags);	if (!rcu_preempt_blocked_readers_cgp(rnp)) {		raw_spin_unlock_irqrestore(&rnp->lock, flags);		return;	}	t = list_entry(rnp->gp_tasks,		       struct task_struct, rcu_node_entry);	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry)		sched_show_task(t);	raw_spin_unlock_irqrestore(&rnp->lock, flags);} /* * Dump detailed information for all tasks blocking the current RCU * grace period. */static void rcu_print_detail_task_stall(struct rcu_state *rsp){	struct rcu_node *rnp = rcu_get_root(rsp); 	rcu_print_detail_task_stall_rnp(rnp);	rcu_for_each_leaf_node(rsp, rnp)		rcu_print_detail_task_stall_rnp(rnp);} #else /* #ifdef CONFIG_RCU_CPU_STALL_VERBOSE */ static void rcu_print_detail_task_stall(struct rcu_state *rsp){} #endif /* #else #ifdef CONFIG_RCU_CPU_STALL_VERBOSE */ #ifdef CONFIG_RCU_CPU_STALL_INFO static void rcu_print_task_stall_begin(struct rcu_node *rnp){	printk(KERN_ERR "\tTasks blocked on level-%d rcu_node (CPUs %d-%d):",	       rnp->level, rnp->grplo, rnp->grphi);} static void rcu_print_task_stall_end(void){	printk(KERN_CONT "\n");}

Lines 1–500 of 2352. Load more