Merge branch 'core/rcu' into core/rcu-for-linus

kernel/pid.c

@@ -30,6 +30,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/init.h>
+#include <linux/rculist.h>
 #include <linux/bootmem.h>
 #include <linux/hash.h>
 #include <linux/pid_namespace.h>

kernel/rcuclassic.c

@@ -387,6 +387,10 @@ static void __rcu_offline_cpu(struct rcu_data *this_rdp,
 	rcu_move_batch(this_rdp, rdp->donelist, rdp->donetail);
 	rcu_move_batch(this_rdp, rdp->curlist, rdp->curtail);
 	rcu_move_batch(this_rdp, rdp->nxtlist, rdp->nxttail);
+
+	local_irq_disable();
+	this_rdp->qlen += rdp->qlen;
+	local_irq_enable();
 }
 
 static void rcu_offline_cpu(int cpu)
@@ -516,10 +520,38 @@ void rcu_check_callbacks(int cpu, int user)
 	if (user ||
 	    (idle_cpu(cpu) && !in_softirq() &&
 				hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
+
+		/*
+		 * Get here if this CPU took its interrupt from user
+		 * mode or from the idle loop, and if this is not a
+		 * nested interrupt.  In this case, the CPU is in
+		 * a quiescent state, so count it.
+		 *
+		 * Also do a memory barrier.  This is needed to handle
+		 * the case where writes from a preempt-disable section
+		 * of code get reordered into schedule() by this CPU's
+		 * write buffer.  The memory barrier makes sure that
+		 * the rcu_qsctr_inc() and rcu_bh_qsctr_inc() are see
+		 * by other CPUs to happen after any such write.
+		 */
+
+		smp_mb();  /* See above block comment. */
 		rcu_qsctr_inc(cpu);
 		rcu_bh_qsctr_inc(cpu);
-	} else if (!in_softirq())
+
+	} else if (!in_softirq()) {
+
+		/*
+		 * Get here if this CPU did not take its interrupt from
+		 * softirq, in other words, if it is not interrupting
+		 * a rcu_bh read-side critical section.  This is an _bh
+		 * critical section, so count it.  The memory barrier
+		 * is needed for the same reason as is the above one.
+		 */
+
+		smp_mb();  /* See above block comment. */
 		rcu_bh_qsctr_inc(cpu);
+	}
 	raise_rcu_softirq();
 }
 

kernel/rcupdate.c

@@ -39,16 +39,16 @@
 #include <linux/sched.h>
 #include <asm/atomic.h>
 #include <linux/bitops.h>
-#include <linux/completion.h>
 #include <linux/percpu.h>
 #include <linux/notifier.h>
 #include <linux/cpu.h>
 #include <linux/mutex.h>
 #include <linux/module.h>
 
-struct rcu_synchronize {
-	struct rcu_head head;
-	struct completion completion;
+enum rcu_barrier {
+	RCU_BARRIER_STD,
+	RCU_BARRIER_BH,
+	RCU_BARRIER_SCHED,
 };
 
 static DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL};
@@ -60,7 +60,7 @@ static struct completion rcu_barrier_completion;
  * Awaken the corresponding synchronize_rcu() instance now that a
  * grace period has elapsed.
  */
-static void wakeme_after_rcu(struct rcu_head  *head)
+void wakeme_after_rcu(struct rcu_head  *head)
 {
 	struct rcu_synchronize *rcu;
 
@@ -77,17 +77,7 @@ static void wakeme_after_rcu(struct rcu_head  *head)
  * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
  * and may be nested.
  */
-void synchronize_rcu(void)
-{
-	struct rcu_synchronize rcu;
-
-	init_completion(&rcu.completion);
-	/* Will wake me after RCU finished */
-	call_rcu(&rcu.head, wakeme_after_rcu);
-
-	/* Wait for it */
-	wait_for_completion(&rcu.completion);
-}
+synchronize_rcu_xxx(synchronize_rcu, call_rcu)
 EXPORT_SYMBOL_GPL(synchronize_rcu);
 
 static void rcu_barrier_callback(struct rcu_head *notused)
@@ -99,19 +89,30 @@ static void rcu_barrier_callback(struct rcu_head *notused)
 /*
  * Called with preemption disabled, and from cross-cpu IRQ context.
  */
-static void rcu_barrier_func(void *notused)
+static void rcu_barrier_func(void *type)
 {
 	int cpu = smp_processor_id();
 	struct rcu_head *head = &per_cpu(rcu_barrier_head, cpu);
 
 	atomic_inc(&rcu_barrier_cpu_count);
-	call_rcu(head, rcu_barrier_callback);
+	switch ((enum rcu_barrier)type) {
+	case RCU_BARRIER_STD:
+		call_rcu(head, rcu_barrier_callback);
+		break;
+	case RCU_BARRIER_BH:
+		call_rcu_bh(head, rcu_barrier_callback);
+		break;
+	case RCU_BARRIER_SCHED:
+		call_rcu_sched(head, rcu_barrier_callback);
+		break;
+	}
 }
 
-/**
- * rcu_barrier - Wait until all the in-flight RCUs are complete.
+/*
+ * Orchestrate the specified type of RCU barrier, waiting for all
+ * RCU callbacks of the specified type to complete.
  */
-void rcu_barrier(void)
+static void _rcu_barrier(enum rcu_barrier type)
 {
 	BUG_ON(in_interrupt());
 	/* Take cpucontrol mutex to protect against CPU hotplug */
@@ -127,13 +128,39 @@ void rcu_barrier(void)
 	 * until all the callbacks are queued.
 	 */
 	rcu_read_lock();
-	on_each_cpu(rcu_barrier_func, NULL, 0, 1);
+	on_each_cpu(rcu_barrier_func, (void *)type, 0, 1);
 	rcu_read_unlock();
 	wait_for_completion(&rcu_barrier_completion);
 	mutex_unlock(&rcu_barrier_mutex);
 }
+
+/**
+ * rcu_barrier - Wait until all in-flight call_rcu() callbacks complete.
+ */
+void rcu_barrier(void)
+{
+	_rcu_barrier(RCU_BARRIER_STD);
+}
 EXPORT_SYMBOL_GPL(rcu_barrier);
 
+/**
+ * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete.
+ */
+void rcu_barrier_bh(void)
+{
+	_rcu_barrier(RCU_BARRIER_BH);
+}
+EXPORT_SYMBOL_GPL(rcu_barrier_bh);
+
+/**
+ * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks.
+ */
+void rcu_barrier_sched(void)
+{
+	_rcu_barrier(RCU_BARRIER_SCHED);
+}
+EXPORT_SYMBOL_GPL(rcu_barrier_sched);
+
 void __init rcu_init(void)
 {
 	__rcu_init();

kernel/rcupreempt_trace.c

@@ -38,7 +38,6 @@
 #include <linux/moduleparam.h>
 #include <linux/percpu.h>
 #include <linux/notifier.h>
-#include <linux/rcupdate.h>
 #include <linux/cpu.h>
 #include <linux/mutex.h>
 #include <linux/rcupreempt_trace.h>

kernel/rcutorture.c

@@ -57,7 +57,9 @@ static int stat_interval;	/* Interval between stats, in seconds. */
 				/*  Defaults to "only at end of test". */
 static int verbose;		/* Print more debug info. */
 static int test_no_idle_hz;	/* Test RCU's support for tickless idle CPUs. */
-static int shuffle_interval = 5; /* Interval between shuffles (in sec)*/
+static int shuffle_interval = 3; /* Interval between shuffles (in sec)*/
+static int stutter = 5;		/* Start/stop testing interval (in sec) */
+static int irqreader = 1;	/* RCU readers from irq (timers). */
 static char *torture_type = "rcu"; /* What RCU implementation to torture. */
 
 module_param(nreaders, int, 0444);
@@ -72,6 +74,10 @@ module_param(test_no_idle_hz, bool, 0444);
 MODULE_PARM_DESC(test_no_idle_hz, "Test support for tickless idle CPUs");
 module_param(shuffle_interval, int, 0444);
 MODULE_PARM_DESC(shuffle_interval, "Number of seconds between shuffles");
+module_param(stutter, int, 0444);
+MODULE_PARM_DESC(stutter, "Number of seconds to run/halt test");
+module_param(irqreader, int, 0444);
+MODULE_PARM_DESC(irqreader, "Allow RCU readers from irq handlers");
 module_param(torture_type, charp, 0444);
 MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, rcu_bh, srcu)");
 
@@ -91,6 +97,7 @@ static struct task_struct **fakewriter_tasks;
 static struct task_struct **reader_tasks;
 static struct task_struct *stats_task;
 static struct task_struct *shuffler_task;
+static struct task_struct *stutter_task;
 
 #define RCU_TORTURE_PIPE_LEN 10
 
@@ -117,8 +124,18 @@ static atomic_t n_rcu_torture_alloc_fail;
 static atomic_t n_rcu_torture_free;
 static atomic_t n_rcu_torture_mberror;
 static atomic_t n_rcu_torture_error;
+static long n_rcu_torture_timers = 0;
 static struct list_head rcu_torture_removed;
 
+static int stutter_pause_test = 0;
+
+#if defined(MODULE) || defined(CONFIG_RCU_TORTURE_TEST_RUNNABLE)
+#define RCUTORTURE_RUNNABLE_INIT 1
+#else
+#define RCUTORTURE_RUNNABLE_INIT 0
+#endif
+int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT;
+
 /*
  * Allocate an element from the rcu_tortures pool.
  */
@@ -179,6 +196,16 @@ rcu_random(struct rcu_random_state *rrsp)
 	return swahw32(rrsp->rrs_state);
 }
 
+static void
+rcu_stutter_wait(void)
+{
+	while (stutter_pause_test || !rcutorture_runnable)
+		if (rcutorture_runnable)
+			schedule_timeout_interruptible(1);
+		else
+			schedule_timeout_interruptible(round_jiffies_relative(HZ));
+}
+
 /*
  * Operations vector for selecting different types of tests.
  */
@@ -192,7 +219,9 @@ struct rcu_torture_ops {
 	int (*completed)(void);
 	void (*deferredfree)(struct rcu_torture *p);
 	void (*sync)(void);
+	void (*cb_barrier)(void);
 	int (*stats)(char *page);
+	int irqcapable;
 	char *name;
 };
 static struct rcu_torture_ops *cur_ops = NULL;
@@ -265,7 +294,9 @@ static struct rcu_torture_ops rcu_ops = {
 	.completed = rcu_torture_completed,
 	.deferredfree = rcu_torture_deferred_free,
 	.sync = synchronize_rcu,
+	.cb_barrier = rcu_barrier,
 	.stats = NULL,
+	.irqcapable = 1,
 	.name = "rcu"
 };
 
@@ -304,7 +335,9 @@ static struct rcu_torture_ops rcu_sync_ops = {
 	.completed = rcu_torture_completed,
 	.deferredfree = rcu_sync_torture_deferred_free,
 	.sync = synchronize_rcu,
+	.cb_barrier = NULL,
 	.stats = NULL,
+	.irqcapable = 1,
 	.name = "rcu_sync"
 };
 
@@ -364,7 +397,9 @@ static struct rcu_torture_ops rcu_bh_ops = {
 	.completed = rcu_bh_torture_completed,
 	.deferredfree = rcu_bh_torture_deferred_free,
 	.sync = rcu_bh_torture_synchronize,
+	.cb_barrier = rcu_barrier_bh,
 	.stats = NULL,
+	.irqcapable = 1,
 	.name = "rcu_bh"
 };
 
@@ -377,7 +412,9 @@ static struct rcu_torture_ops rcu_bh_sync_ops = {
 	.completed = rcu_bh_torture_completed,
 	.deferredfree = rcu_sync_torture_deferred_free,
 	.sync = rcu_bh_torture_synchronize,
+	.cb_barrier = NULL,
 	.stats = NULL,
+	.irqcapable = 1,
 	.name = "rcu_bh_sync"
 };
 
@@ -458,6 +495,7 @@ static struct rcu_torture_ops srcu_ops = {
 	.completed = srcu_torture_completed,
 	.deferredfree = rcu_sync_torture_deferred_free,
 	.sync = srcu_torture_synchronize,
+	.cb_barrier = NULL,
 	.stats = srcu_torture_stats,
 	.name = "srcu"
 };
@@ -482,12 +520,32 @@ static int sched_torture_completed(void)
 	return 0;
 }
 
+static void rcu_sched_torture_deferred_free(struct rcu_torture *p)
+{
+	call_rcu_sched(&p->rtort_rcu, rcu_torture_cb);
+}
+
 static void sched_torture_synchronize(void)
 {
 	synchronize_sched();
 }
 
 static struct rcu_torture_ops sched_ops = {
+	.init = rcu_sync_torture_init,
+	.cleanup = NULL,
+	.readlock = sched_torture_read_lock,
+	.readdelay = rcu_read_delay,  /* just reuse rcu's version. */
+	.readunlock = sched_torture_read_unlock,
+	.completed = sched_torture_completed,
+	.deferredfree = rcu_sched_torture_deferred_free,
+	.sync = sched_torture_synchronize,
+	.cb_barrier = rcu_barrier_sched,
+	.stats = NULL,
+	.irqcapable = 1,
+	.name = "sched"
+};
+
+static struct rcu_torture_ops sched_ops_sync = {
 	.init = rcu_sync_torture_init,
 	.cleanup = NULL,
 	.readlock = sched_torture_read_lock,
@@ -496,8 +554,9 @@ static struct rcu_torture_ops sched_ops = {
 	.completed = sched_torture_completed,
 	.deferredfree = rcu_sync_torture_deferred_free,
 	.sync = sched_torture_synchronize,
+	.cb_barrier = NULL,
 	.stats = NULL,
-	.name = "sched"
+	.name = "sched_sync"
 };
 
 /*
@@ -537,6 +596,7 @@ rcu_torture_writer(void *arg)
 		}
 		rcu_torture_current_version++;
 		oldbatch = cur_ops->completed();
+		rcu_stutter_wait();
 	} while (!kthread_should_stop() && !fullstop);
 	VERBOSE_PRINTK_STRING("rcu_torture_writer task stopping");
 	while (!kthread_should_stop())
@@ -560,6 +620,7 @@ rcu_torture_fakewriter(void *arg)
 		schedule_timeout_uninterruptible(1 + rcu_random(&rand)%10);
 		udelay(rcu_random(&rand) & 0x3ff);
 		cur_ops->sync();
+		rcu_stutter_wait();
 	} while (!kthread_should_stop() && !fullstop);
 
 	VERBOSE_PRINTK_STRING("rcu_torture_fakewriter task stopping");
@@ -568,6 +629,52 @@ rcu_torture_fakewriter(void *arg)
 	return 0;
 }
 
+/*
+ * RCU torture reader from timer handler.  Dereferences rcu_torture_current,
+ * incrementing the corresponding element of the pipeline array.  The
+ * counter in the element should never be greater than 1, otherwise, the
+ * RCU implementation is broken.
+ */
+static void rcu_torture_timer(unsigned long unused)
+{
+	int idx;
+	int completed;
+	static DEFINE_RCU_RANDOM(rand);
+	static DEFINE_SPINLOCK(rand_lock);
+	struct rcu_torture *p;
+	int pipe_count;
+
+	idx = cur_ops->readlock();
+	completed = cur_ops->completed();
+	p = rcu_dereference(rcu_torture_current);
+	if (p == NULL) {
+		/* Leave because rcu_torture_writer is not yet underway */
+		cur_ops->readunlock(idx);
+		return;
+	}
+	if (p->rtort_mbtest == 0)
+		atomic_inc(&n_rcu_torture_mberror);
+	spin_lock(&rand_lock);
+	cur_ops->readdelay(&rand);
+	n_rcu_torture_timers++;
+	spin_unlock(&rand_lock);
+	preempt_disable();
+	pipe_count = p->rtort_pipe_count;
+	if (pipe_count > RCU_TORTURE_PIPE_LEN) {
+		/* Should not happen, but... */
+		pipe_count = RCU_TORTURE_PIPE_LEN;
+	}
+	++__get_cpu_var(rcu_torture_count)[pipe_count];
+	completed = cur_ops->completed() - completed;
+	if (completed > RCU_TORTURE_PIPE_LEN) {
+		/* Should not happen, but... */
+		completed = RCU_TORTURE_PIPE_LEN;
+	}
+	++__get_cpu_var(rcu_torture_batch)[completed];
+	preempt_enable();
+	cur_ops->readunlock(idx);
+}
+
 /*
  * RCU torture reader kthread.  Repeatedly dereferences rcu_torture_current,
  * incrementing the corresponding element of the pipeline array.  The
@@ -582,11 +689,18 @@ rcu_torture_reader(void *arg)
 	DEFINE_RCU_RANDOM(rand);
 	struct rcu_torture *p;
 	int pipe_count;
+	struct timer_list t;
 
 	VERBOSE_PRINTK_STRING("rcu_torture_reader task started");
 	set_user_nice(current, 19);
+	if (irqreader && cur_ops->irqcapable)
+		setup_timer_on_stack(&t, rcu_torture_timer, 0);
 
 	do {
+		if (irqreader && cur_ops->irqcapable) {
+			if (!timer_pending(&t))
+				mod_timer(&t, 1);
+		}
 		idx = cur_ops->readlock();
 		completed = cur_ops->completed();
 		p = rcu_dereference(rcu_torture_current);
@@ -615,8 +729,11 @@ rcu_torture_reader(void *arg)
 		preempt_enable();
 		cur_ops->readunlock(idx);
 		schedule();
+		rcu_stutter_wait();
 	} while (!kthread_should_stop() && !fullstop);
 	VERBOSE_PRINTK_STRING("rcu_torture_reader task stopping");
+	if (irqreader && cur_ops->irqcapable)
+		del_timer_sync(&t);
 	while (!kthread_should_stop())
 		schedule_timeout_uninterruptible(1);
 	return 0;
@@ -647,20 +764,22 @@ rcu_torture_printk(char *page)
 	cnt += sprintf(&page[cnt], "%s%s ", torture_type, TORTURE_FLAG);
 	cnt += sprintf(&page[cnt],
 		       "rtc: %p ver: %ld tfle: %d rta: %d rtaf: %d rtf: %d "
-		       "rtmbe: %d",
+		       "rtmbe: %d nt: %ld",
 		       rcu_torture_current,
 		       rcu_torture_current_version,
 		       list_empty(&rcu_torture_freelist),
 		       atomic_read(&n_rcu_torture_alloc),
 		       atomic_read(&n_rcu_torture_alloc_fail),
 		       atomic_read(&n_rcu_torture_free),
-		       atomic_read(&n_rcu_torture_mberror));
+		       atomic_read(&n_rcu_torture_mberror),
+		       n_rcu_torture_timers);
 	if (atomic_read(&n_rcu_torture_mberror) != 0)
 		cnt += sprintf(&page[cnt], " !!!");
 	cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG);
 	if (i > 1) {
 		cnt += sprintf(&page[cnt], "!!! ");
 		atomic_inc(&n_rcu_torture_error);
+		WARN_ON_ONCE(1);
 	}
 	cnt += sprintf(&page[cnt], "Reader Pipe: ");
 	for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
@@ -785,15 +904,34 @@ rcu_torture_shuffle(void *arg)
 	return 0;
 }
 
+/* Cause the rcutorture test to "stutter", starting and stopping all
+ * threads periodically.
+ */
+static int
+rcu_torture_stutter(void *arg)
+{
+	VERBOSE_PRINTK_STRING("rcu_torture_stutter task started");
+	do {
+		schedule_timeout_interruptible(stutter * HZ);
+		stutter_pause_test = 1;
+		if (!kthread_should_stop())
+			schedule_timeout_interruptible(stutter * HZ);
+		stutter_pause_test = 0;
+	} while (!kthread_should_stop());
+	VERBOSE_PRINTK_STRING("rcu_torture_stutter task stopping");
+	return 0;
+}
+
 static inline void
 rcu_torture_print_module_parms(char *tag)
 {
 	printk(KERN_ALERT "%s" TORTURE_FLAG
 		"--- %s: nreaders=%d nfakewriters=%d "
 		"stat_interval=%d verbose=%d test_no_idle_hz=%d "
-		"shuffle_interval = %d\n",
+		"shuffle_interval=%d stutter=%d irqreader=%d\n",
 		torture_type, tag, nrealreaders, nfakewriters,
-		stat_interval, verbose, test_no_idle_hz, shuffle_interval);
+		stat_interval, verbose, test_no_idle_hz, shuffle_interval,
+		stutter, irqreader);
 }
 
 static void
@@ -802,6 +940,11 @@ rcu_torture_cleanup(void)
 	int i;
 
 	fullstop = 1;
+	if (stutter_task) {
+		VERBOSE_PRINTK_STRING("Stopping rcu_torture_stutter task");
+		kthread_stop(stutter_task);
+	}
+	stutter_task = NULL;
 	if (shuffler_task) {
 		VERBOSE_PRINTK_STRING("Stopping rcu_torture_shuffle task");
 		kthread_stop(shuffler_task);
@@ -848,7 +991,9 @@ rcu_torture_cleanup(void)
 	stats_task = NULL;
 
 	/* Wait for all RCU callbacks to fire.  */
-	rcu_barrier();
+
+	if (cur_ops->cb_barrier != NULL)
+		cur_ops->cb_barrier();
 
 	rcu_torture_stats_print();  /* -After- the stats thread is stopped! */
 
@@ -868,7 +1013,7 @@ rcu_torture_init(void)
 	int firsterr = 0;
 	static struct rcu_torture_ops *torture_ops[] =
 		{ &rcu_ops, &rcu_sync_ops, &rcu_bh_ops, &rcu_bh_sync_ops,
-		  &srcu_ops, &sched_ops, };
+		  &srcu_ops, &sched_ops, &sched_ops_sync, };
 
 	/* Process args and tell the world that the torturer is on the job. */
 	for (i = 0; i < ARRAY_SIZE(torture_ops); i++) {
@@ -988,6 +1133,19 @@ rcu_torture_init(void)
 			goto unwind;
 		}
 	}
+	if (stutter < 0)
+		stutter = 0;
+	if (stutter) {
+		/* Create the stutter thread */
+		stutter_task = kthread_run(rcu_torture_stutter, NULL,
+					  "rcu_torture_stutter");
+		if (IS_ERR(stutter_task)) {
+			firsterr = PTR_ERR(stutter_task);
+			VERBOSE_PRINTK_ERRSTRING("Failed to create stutter");
+			stutter_task = NULL;
+			goto unwind;
+		}
+	}
 	return 0;
 
 unwind:

kernel/sysctl.c

@@ -83,6 +83,9 @@ extern int maps_protect;
 extern int sysctl_stat_interval;
 extern int latencytop_enabled;
 extern int sysctl_nr_open_min, sysctl_nr_open_max;
+#ifdef CONFIG_RCU_TORTURE_TEST
+extern int rcutorture_runnable;
+#endif /* #ifdef CONFIG_RCU_TORTURE_TEST */
 
 /* Constants used for minimum and  maximum */
 #if defined(CONFIG_DETECT_SOFTLOCKUP) || defined(CONFIG_HIGHMEM)
@@ -820,6 +823,16 @@ static struct ctl_table kern_table[] = {
 		.child		= key_sysctls,
 	},
 #endif
+#ifdef CONFIG_RCU_TORTURE_TEST
+	{
+		.ctl_name       = CTL_UNNUMBERED,
+		.procname       = "rcutorture_runnable",
+		.data           = &rcutorture_runnable,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = &proc_dointvec,
+	},
+#endif
 /*
  * NOTE: do not add new entries to this table unless you have read
  * Documentation/sysctl/ctl_unnumbered.txt