 61f38db3e3
			
		
	
	
	61f38db3e3
	
	
	
		
			
			Some sysrq handlers can run for a long time, because they dump a lot of data onto a serial console. Having RCU stall warnings pop up in the middle of them only makes the problem worse. This commit provides rcu_sysrq_start() and rcu_sysrq_end() APIs to temporarily suppress RCU CPU stall warnings while a sysrq request is handled. Signed-off-by: Rik van Riel <riel@redhat.com> [ paulmck: Fix TINY_RCU build error. ] Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
		
			
				
	
	
		
			370 lines
		
	
	
	
		
			11 KiB
			
		
	
	
	
		
			C
		
	
	
	
	
	
			
		
		
	
	
			370 lines
		
	
	
	
		
			11 KiB
			
		
	
	
	
		
			C
		
	
	
	
	
	
| /*
 | |
|  * 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, 2001
 | |
|  *
 | |
|  * Authors: Dipankar Sarma <dipankar@in.ibm.com>
 | |
|  *	    Manfred Spraul <manfred@colorfullife.com>
 | |
|  *
 | |
|  * Based on the original work by Paul McKenney <paulmck@us.ibm.com>
 | |
|  * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
 | |
|  * Papers:
 | |
|  * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf
 | |
|  * http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001)
 | |
|  *
 | |
|  * For detailed explanation of Read-Copy Update mechanism see -
 | |
|  *		http://lse.sourceforge.net/locking/rcupdate.html
 | |
|  *
 | |
|  */
 | |
| #include <linux/types.h>
 | |
| #include <linux/kernel.h>
 | |
| #include <linux/init.h>
 | |
| #include <linux/spinlock.h>
 | |
| #include <linux/smp.h>
 | |
| #include <linux/interrupt.h>
 | |
| #include <linux/sched.h>
 | |
| #include <linux/atomic.h>
 | |
| #include <linux/bitops.h>
 | |
| #include <linux/percpu.h>
 | |
| #include <linux/notifier.h>
 | |
| #include <linux/cpu.h>
 | |
| #include <linux/mutex.h>
 | |
| #include <linux/export.h>
 | |
| #include <linux/hardirq.h>
 | |
| #include <linux/delay.h>
 | |
| #include <linux/module.h>
 | |
| 
 | |
| #define CREATE_TRACE_POINTS
 | |
| 
 | |
| #include "rcu.h"
 | |
| 
 | |
| MODULE_ALIAS("rcupdate");
 | |
| #ifdef MODULE_PARAM_PREFIX
 | |
| #undef MODULE_PARAM_PREFIX
 | |
| #endif
 | |
| #define MODULE_PARAM_PREFIX "rcupdate."
 | |
| 
 | |
| module_param(rcu_expedited, int, 0);
 | |
| 
 | |
| #ifdef CONFIG_PREEMPT_RCU
 | |
| 
 | |
| /*
 | |
|  * Preemptible RCU implementation for rcu_read_lock().
 | |
|  * Just increment ->rcu_read_lock_nesting, shared state will be updated
 | |
|  * if we block.
 | |
|  */
 | |
| void __rcu_read_lock(void)
 | |
| {
 | |
| 	current->rcu_read_lock_nesting++;
 | |
| 	barrier();  /* critical section after entry code. */
 | |
| }
 | |
| EXPORT_SYMBOL_GPL(__rcu_read_lock);
 | |
| 
 | |
| /*
 | |
|  * Preemptible RCU implementation for rcu_read_unlock().
 | |
|  * Decrement ->rcu_read_lock_nesting.  If the result is zero (outermost
 | |
|  * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then
 | |
|  * invoke rcu_read_unlock_special() to clean up after a context switch
 | |
|  * in an RCU read-side critical section and other special cases.
 | |
|  */
 | |
| void __rcu_read_unlock(void)
 | |
| {
 | |
| 	struct task_struct *t = current;
 | |
| 
 | |
| 	if (t->rcu_read_lock_nesting != 1) {
 | |
| 		--t->rcu_read_lock_nesting;
 | |
| 	} else {
 | |
| 		barrier();  /* critical section before exit code. */
 | |
| 		t->rcu_read_lock_nesting = INT_MIN;
 | |
| #ifdef CONFIG_PROVE_RCU_DELAY
 | |
| 		udelay(10); /* Make preemption more probable. */
 | |
| #endif /* #ifdef CONFIG_PROVE_RCU_DELAY */
 | |
| 		barrier();  /* assign before ->rcu_read_unlock_special load */
 | |
| 		if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
 | |
| 			rcu_read_unlock_special(t);
 | |
| 		barrier();  /* ->rcu_read_unlock_special load before assign */
 | |
| 		t->rcu_read_lock_nesting = 0;
 | |
| 	}
 | |
| #ifdef CONFIG_PROVE_LOCKING
 | |
| 	{
 | |
| 		int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting);
 | |
| 
 | |
| 		WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2);
 | |
| 	}
 | |
| #endif /* #ifdef CONFIG_PROVE_LOCKING */
 | |
| }
 | |
| EXPORT_SYMBOL_GPL(__rcu_read_unlock);
 | |
| 
 | |
| #endif /* #ifdef CONFIG_PREEMPT_RCU */
 | |
| 
 | |
| #ifdef CONFIG_DEBUG_LOCK_ALLOC
 | |
| static struct lock_class_key rcu_lock_key;
 | |
| struct lockdep_map rcu_lock_map =
 | |
| 	STATIC_LOCKDEP_MAP_INIT("rcu_read_lock", &rcu_lock_key);
 | |
| EXPORT_SYMBOL_GPL(rcu_lock_map);
 | |
| 
 | |
| static struct lock_class_key rcu_bh_lock_key;
 | |
| struct lockdep_map rcu_bh_lock_map =
 | |
| 	STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_bh", &rcu_bh_lock_key);
 | |
| EXPORT_SYMBOL_GPL(rcu_bh_lock_map);
 | |
| 
 | |
| static struct lock_class_key rcu_sched_lock_key;
 | |
| struct lockdep_map rcu_sched_lock_map =
 | |
| 	STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_sched", &rcu_sched_lock_key);
 | |
| EXPORT_SYMBOL_GPL(rcu_sched_lock_map);
 | |
| 
 | |
| static struct lock_class_key rcu_callback_key;
 | |
| struct lockdep_map rcu_callback_map =
 | |
| 	STATIC_LOCKDEP_MAP_INIT("rcu_callback", &rcu_callback_key);
 | |
| EXPORT_SYMBOL_GPL(rcu_callback_map);
 | |
| 
 | |
| int notrace debug_lockdep_rcu_enabled(void)
 | |
| {
 | |
| 	return rcu_scheduler_active && debug_locks &&
 | |
| 	       current->lockdep_recursion == 0;
 | |
| }
 | |
| EXPORT_SYMBOL_GPL(debug_lockdep_rcu_enabled);
 | |
| 
 | |
| /**
 | |
|  * rcu_read_lock_bh_held() - might we be in RCU-bh read-side critical section?
 | |
|  *
 | |
|  * Check for bottom half being disabled, which covers both the
 | |
|  * CONFIG_PROVE_RCU and not cases.  Note that if someone uses
 | |
|  * rcu_read_lock_bh(), but then later enables BH, lockdep (if enabled)
 | |
|  * will show the situation.  This is useful for debug checks in functions
 | |
|  * that require that they be called within an RCU read-side critical
 | |
|  * section.
 | |
|  *
 | |
|  * Check debug_lockdep_rcu_enabled() to prevent false positives during boot.
 | |
|  *
 | |
|  * Note that rcu_read_lock() is disallowed if the CPU is either idle or
 | |
|  * offline from an RCU perspective, so check for those as well.
 | |
|  */
 | |
| int rcu_read_lock_bh_held(void)
 | |
| {
 | |
| 	if (!debug_lockdep_rcu_enabled())
 | |
| 		return 1;
 | |
| 	if (!rcu_is_watching())
 | |
| 		return 0;
 | |
| 	if (!rcu_lockdep_current_cpu_online())
 | |
| 		return 0;
 | |
| 	return in_softirq() || irqs_disabled();
 | |
| }
 | |
| EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held);
 | |
| 
 | |
| #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 | |
| 
 | |
| struct rcu_synchronize {
 | |
| 	struct rcu_head head;
 | |
| 	struct completion completion;
 | |
| };
 | |
| 
 | |
| /*
 | |
|  * Awaken the corresponding synchronize_rcu() instance now that a
 | |
|  * grace period has elapsed.
 | |
|  */
 | |
| static void wakeme_after_rcu(struct rcu_head  *head)
 | |
| {
 | |
| 	struct rcu_synchronize *rcu;
 | |
| 
 | |
| 	rcu = container_of(head, struct rcu_synchronize, head);
 | |
| 	complete(&rcu->completion);
 | |
| }
 | |
| 
 | |
| void wait_rcu_gp(call_rcu_func_t crf)
 | |
| {
 | |
| 	struct rcu_synchronize rcu;
 | |
| 
 | |
| 	init_rcu_head_on_stack(&rcu.head);
 | |
| 	init_completion(&rcu.completion);
 | |
| 	/* Will wake me after RCU finished. */
 | |
| 	crf(&rcu.head, wakeme_after_rcu);
 | |
| 	/* Wait for it. */
 | |
| 	wait_for_completion(&rcu.completion);
 | |
| 	destroy_rcu_head_on_stack(&rcu.head);
 | |
| }
 | |
| EXPORT_SYMBOL_GPL(wait_rcu_gp);
 | |
| 
 | |
| #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
 | |
| static inline void debug_init_rcu_head(struct rcu_head *head)
 | |
| {
 | |
| 	debug_object_init(head, &rcuhead_debug_descr);
 | |
| }
 | |
| 
 | |
| static inline void debug_rcu_head_free(struct rcu_head *head)
 | |
| {
 | |
| 	debug_object_free(head, &rcuhead_debug_descr);
 | |
| }
 | |
| 
 | |
| /*
 | |
|  * fixup_activate is called when:
 | |
|  * - an active object is activated
 | |
|  * - an unknown object is activated (might be a statically initialized object)
 | |
|  * Activation is performed internally by call_rcu().
 | |
|  */
 | |
| static int rcuhead_fixup_activate(void *addr, enum debug_obj_state state)
 | |
| {
 | |
| 	struct rcu_head *head = addr;
 | |
| 
 | |
| 	switch (state) {
 | |
| 
 | |
| 	case ODEBUG_STATE_NOTAVAILABLE:
 | |
| 		/*
 | |
| 		 * This is not really a fixup. We just make sure that it is
 | |
| 		 * tracked in the object tracker.
 | |
| 		 */
 | |
| 		debug_object_init(head, &rcuhead_debug_descr);
 | |
| 		debug_object_activate(head, &rcuhead_debug_descr);
 | |
| 		return 0;
 | |
| 	default:
 | |
| 		return 1;
 | |
| 	}
 | |
| }
 | |
| 
 | |
| /**
 | |
|  * init_rcu_head_on_stack() - initialize on-stack rcu_head for debugobjects
 | |
|  * @head: pointer to rcu_head structure to be initialized
 | |
|  *
 | |
|  * This function informs debugobjects of a new rcu_head structure that
 | |
|  * has been allocated as an auto variable on the stack.  This function
 | |
|  * is not required for rcu_head structures that are statically defined or
 | |
|  * that are dynamically allocated on the heap.  This function has no
 | |
|  * effect for !CONFIG_DEBUG_OBJECTS_RCU_HEAD kernel builds.
 | |
|  */
 | |
| void init_rcu_head_on_stack(struct rcu_head *head)
 | |
| {
 | |
| 	debug_object_init_on_stack(head, &rcuhead_debug_descr);
 | |
| }
 | |
| EXPORT_SYMBOL_GPL(init_rcu_head_on_stack);
 | |
| 
 | |
| /**
 | |
|  * destroy_rcu_head_on_stack() - destroy on-stack rcu_head for debugobjects
 | |
|  * @head: pointer to rcu_head structure to be initialized
 | |
|  *
 | |
|  * This function informs debugobjects that an on-stack rcu_head structure
 | |
|  * is about to go out of scope.  As with init_rcu_head_on_stack(), this
 | |
|  * function is not required for rcu_head structures that are statically
 | |
|  * defined or that are dynamically allocated on the heap.  Also as with
 | |
|  * init_rcu_head_on_stack(), this function has no effect for
 | |
|  * !CONFIG_DEBUG_OBJECTS_RCU_HEAD kernel builds.
 | |
|  */
 | |
| void destroy_rcu_head_on_stack(struct rcu_head *head)
 | |
| {
 | |
| 	debug_object_free(head, &rcuhead_debug_descr);
 | |
| }
 | |
| EXPORT_SYMBOL_GPL(destroy_rcu_head_on_stack);
 | |
| 
 | |
| struct debug_obj_descr rcuhead_debug_descr = {
 | |
| 	.name = "rcu_head",
 | |
| 	.fixup_activate = rcuhead_fixup_activate,
 | |
| };
 | |
| EXPORT_SYMBOL_GPL(rcuhead_debug_descr);
 | |
| #endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 | |
| 
 | |
| #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU) || defined(CONFIG_RCU_TRACE)
 | |
| void do_trace_rcu_torture_read(const char *rcutorturename, struct rcu_head *rhp,
 | |
| 			       unsigned long secs,
 | |
| 			       unsigned long c_old, unsigned long c)
 | |
| {
 | |
| 	trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c);
 | |
| }
 | |
| EXPORT_SYMBOL_GPL(do_trace_rcu_torture_read);
 | |
| #else
 | |
| #define do_trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \
 | |
| 	do { } while (0)
 | |
| #endif
 | |
| 
 | |
| #ifdef CONFIG_RCU_STALL_COMMON
 | |
| 
 | |
| #ifdef CONFIG_PROVE_RCU
 | |
| #define RCU_STALL_DELAY_DELTA	       (5 * HZ)
 | |
| #else
 | |
| #define RCU_STALL_DELAY_DELTA	       0
 | |
| #endif
 | |
| 
 | |
| int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */
 | |
| static int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT;
 | |
| 
 | |
| module_param(rcu_cpu_stall_suppress, int, 0644);
 | |
| module_param(rcu_cpu_stall_timeout, int, 0644);
 | |
| 
 | |
| int rcu_jiffies_till_stall_check(void)
 | |
| {
 | |
| 	int till_stall_check = ACCESS_ONCE(rcu_cpu_stall_timeout);
 | |
| 
 | |
| 	/*
 | |
| 	 * Limit check must be consistent with the Kconfig limits
 | |
| 	 * for CONFIG_RCU_CPU_STALL_TIMEOUT.
 | |
| 	 */
 | |
| 	if (till_stall_check < 3) {
 | |
| 		ACCESS_ONCE(rcu_cpu_stall_timeout) = 3;
 | |
| 		till_stall_check = 3;
 | |
| 	} else if (till_stall_check > 300) {
 | |
| 		ACCESS_ONCE(rcu_cpu_stall_timeout) = 300;
 | |
| 		till_stall_check = 300;
 | |
| 	}
 | |
| 	return till_stall_check * HZ + RCU_STALL_DELAY_DELTA;
 | |
| }
 | |
| 
 | |
| void rcu_sysrq_start(void)
 | |
| {
 | |
| 	if (!rcu_cpu_stall_suppress)
 | |
| 		rcu_cpu_stall_suppress = 2;
 | |
| }
 | |
| 
 | |
| void rcu_sysrq_end(void)
 | |
| {
 | |
| 	if (rcu_cpu_stall_suppress == 2)
 | |
| 		rcu_cpu_stall_suppress = 0;
 | |
| }
 | |
| 
 | |
| static int rcu_panic(struct notifier_block *this, unsigned long ev, void *ptr)
 | |
| {
 | |
| 	rcu_cpu_stall_suppress = 1;
 | |
| 	return NOTIFY_DONE;
 | |
| }
 | |
| 
 | |
| static struct notifier_block rcu_panic_block = {
 | |
| 	.notifier_call = rcu_panic,
 | |
| };
 | |
| 
 | |
| static int __init check_cpu_stall_init(void)
 | |
| {
 | |
| 	atomic_notifier_chain_register(&panic_notifier_list, &rcu_panic_block);
 | |
| 	return 0;
 | |
| }
 | |
| early_initcall(check_cpu_stall_init);
 | |
| 
 | |
| #endif /* #ifdef CONFIG_RCU_STALL_COMMON */
 | |
| 
 | |
| /*
 | |
|  * Hooks for cond_resched() and friends to avoid RCU CPU stall warnings.
 | |
|  */
 | |
| 
 | |
| DEFINE_PER_CPU(int, rcu_cond_resched_count);
 | |
| 
 | |
| /*
 | |
|  * Report a set of RCU quiescent states, for use by cond_resched()
 | |
|  * and friends.  Out of line due to being called infrequently.
 | |
|  */
 | |
| void rcu_resched(void)
 | |
| {
 | |
| 	preempt_disable();
 | |
| 	__this_cpu_write(rcu_cond_resched_count, 0);
 | |
| 	rcu_note_context_switch(smp_processor_id());
 | |
| 	preempt_enable();
 | |
| }
 |