Merge branches 'doc.2013.09.25b' and 'fixes.2013.09.23b' into HEAD

doc.2013.09.25b: Topic branch for documentation updates.
fixes.2013.09.23b: Topic branch for miscellaneous fixes.

7 files changed, 119 insertions, 51 deletions

diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index 4106721c4e5e..45a0a9e81478 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -19,6 +19,21 @@
  */
 
 /*
+ * INIT_LIST_HEAD_RCU - Initialize a list_head visible to RCU readers
+ * @list: list to be initialized
+ *
+ * You should instead use INIT_LIST_HEAD() for normal initialization and
+ * cleanup tasks, when readers have no access to the list being initialized.
+ * However, if the list being initialized is visible to readers, you
+ * need to keep the compiler from being too mischievous.
+ */
+static inline void INIT_LIST_HEAD_RCU(struct list_head *list)
+{
+	ACCESS_ONCE(list->next) = list;
+	ACCESS_ONCE(list->prev) = list;
+}
+
+/*
  * return the ->next pointer of a list_head in an rcu safe
  * way, we must not access it directly
  */
@@ -191,9 +206,13 @@ static inline void list_splice_init_rcu(struct list_head *list,
 	if (list_empty(list))
 		return;
 
-	/* "first" and "last" tracking list, so initialize it. */
+	/*
+	 * "first" and "last" tracking list, so initialize it.  RCU readers
+	 * have access to this list, so we must use INIT_LIST_HEAD_RCU()
+	 * instead of INIT_LIST_HEAD().
+	 */
 
-	INIT_LIST_HEAD(list);
+	INIT_LIST_HEAD_RCU(list);
 
 	/*
 	 * At this point, the list body still points to the source list.
diff --git a/kernel/rcu.h b/kernel/rcu.h
index 77131966c4ad..7859a0a3951e 100644
--- a/kernel/rcu.h
+++ b/kernel/rcu.h
@@ -122,4 +122,11 @@ int rcu_jiffies_till_stall_check(void);
 
 #endif /* #ifdef CONFIG_RCU_STALL_COMMON */
 
+/*
+ * Strings used in tracepoints need to be exported via the
+ * tracing system such that tools like perf and trace-cmd can
+ * translate the string address pointers to actual text.
+ */
+#define TPS(x)  tracepoint_string(x)
+
 #endif /* __LINUX_RCU_H */
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index b02a339836b4..3260a1074b48 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -298,7 +298,7 @@ EXPORT_SYMBOL_GPL(do_trace_rcu_torture_read);
 #endif
 
 int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */
-int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT;
+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);
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index 9ed6075dc562..e99eb5fb10af 100644
--- a/kernel/rcutiny.c
+++ b/kernel/rcutiny.c
@@ -35,6 +35,7 @@
 #include <linux/time.h>
 #include <linux/cpu.h>
 #include <linux/prefetch.h>
+#include <linux/ftrace_event.h>
 
 #ifdef CONFIG_RCU_TRACE
 #include <trace/events/rcu.h>
@@ -58,16 +59,17 @@ static long long rcu_dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
 static void rcu_idle_enter_common(long long newval)
 {
 	if (newval) {
-		RCU_TRACE(trace_rcu_dyntick("--=",
+		RCU_TRACE(trace_rcu_dyntick(TPS("--="),
 					    rcu_dynticks_nesting, newval));
 		rcu_dynticks_nesting = newval;
 		return;
 	}
-	RCU_TRACE(trace_rcu_dyntick("Start", rcu_dynticks_nesting, newval));
+	RCU_TRACE(trace_rcu_dyntick(TPS("Start"),
+				    rcu_dynticks_nesting, newval));
 	if (!is_idle_task(current)) {
 		struct task_struct *idle = idle_task(smp_processor_id());
 
-		RCU_TRACE(trace_rcu_dyntick("Error on entry: not idle task",
+		RCU_TRACE(trace_rcu_dyntick(TPS("Entry error: not idle task"),
 					    rcu_dynticks_nesting, newval));
 		ftrace_dump(DUMP_ALL);
 		WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
@@ -120,15 +122,15 @@ EXPORT_SYMBOL_GPL(rcu_irq_exit);
 static void rcu_idle_exit_common(long long oldval)
 {
 	if (oldval) {
-		RCU_TRACE(trace_rcu_dyntick("++=",
+		RCU_TRACE(trace_rcu_dyntick(TPS("++="),
 					    oldval, rcu_dynticks_nesting));
 		return;
 	}
-	RCU_TRACE(trace_rcu_dyntick("End", oldval, rcu_dynticks_nesting));
+	RCU_TRACE(trace_rcu_dyntick(TPS("End"), oldval, rcu_dynticks_nesting));
 	if (!is_idle_task(current)) {
 		struct task_struct *idle = idle_task(smp_processor_id());
 
-		RCU_TRACE(trace_rcu_dyntick("Error on exit: not idle task",
+		RCU_TRACE(trace_rcu_dyntick(TPS("Exit error: not idle task"),
 			  oldval, rcu_dynticks_nesting));
 		ftrace_dump(DUMP_ALL);
 		WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
@@ -304,7 +306,8 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
 		RCU_TRACE(cb_count++);
 	}
 	RCU_TRACE(rcu_trace_sub_qlen(rcp, cb_count));
-	RCU_TRACE(trace_rcu_batch_end(rcp->name, cb_count, 0, need_resched(),
+	RCU_TRACE(trace_rcu_batch_end(rcp->name,
+				      cb_count, 0, need_resched(),
 				      is_idle_task(current),
 				      false));
 }
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 32618b3fe4e6..62aab5ceefe9 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -61,13 +61,6 @@
 
 #include "rcu.h"
 
-/*
- * Strings used in tracepoints need to be exported via the
- * tracing system such that tools like perf and trace-cmd can
- * translate the string address pointers to actual text.
- */
-#define TPS(x)	tracepoint_string(x)
-
 /* Data structures. */
 
 static struct lock_class_key rcu_node_class[RCU_NUM_LVLS];
@@ -222,7 +215,7 @@ void rcu_note_context_switch(int cpu)
 }
 EXPORT_SYMBOL_GPL(rcu_note_context_switch);
 
-DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
+static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
 	.dynticks_nesting = DYNTICK_TASK_EXIT_IDLE,
 	.dynticks = ATOMIC_INIT(1),
 #ifdef CONFIG_NO_HZ_FULL_SYSIDLE
@@ -371,7 +364,8 @@ static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval,
 {
 	trace_rcu_dyntick(TPS("Start"), oldval, rdtp->dynticks_nesting);
 	if (!user && !is_idle_task(current)) {
-		struct task_struct *idle = idle_task(smp_processor_id());
+		struct task_struct *idle __maybe_unused =
+			idle_task(smp_processor_id());
 
 		trace_rcu_dyntick(TPS("Error on entry: not idle task"), oldval, 0);
 		ftrace_dump(DUMP_ORIG);
@@ -407,7 +401,7 @@ static void rcu_eqs_enter(bool user)
 	long long oldval;
 	struct rcu_dynticks *rdtp;
 
-	rdtp = &__get_cpu_var(rcu_dynticks);
+	rdtp = this_cpu_ptr(&rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
 	WARN_ON_ONCE((oldval & DYNTICK_TASK_NEST_MASK) == 0);
 	if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE)
@@ -435,7 +429,7 @@ void rcu_idle_enter(void)
 
 	local_irq_save(flags);
 	rcu_eqs_enter(false);
-	rcu_sysidle_enter(&__get_cpu_var(rcu_dynticks), 0);
+	rcu_sysidle_enter(this_cpu_ptr(&rcu_dynticks), 0);
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(rcu_idle_enter);
@@ -478,7 +472,7 @@ void rcu_irq_exit(void)
 	struct rcu_dynticks *rdtp;
 
 	local_irq_save(flags);
-	rdtp = &__get_cpu_var(rcu_dynticks);
+	rdtp = this_cpu_ptr(&rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
 	rdtp->dynticks_nesting--;
 	WARN_ON_ONCE(rdtp->dynticks_nesting < 0);
@@ -508,7 +502,8 @@ static void rcu_eqs_exit_common(struct rcu_dynticks *rdtp, long long oldval,
 	rcu_cleanup_after_idle(smp_processor_id());
 	trace_rcu_dyntick(TPS("End"), oldval, rdtp->dynticks_nesting);
 	if (!user && !is_idle_task(current)) {
-		struct task_struct *idle = idle_task(smp_processor_id());
+		struct task_struct *idle __maybe_unused =
+			idle_task(smp_processor_id());
 
 		trace_rcu_dyntick(TPS("Error on exit: not idle task"),
 				  oldval, rdtp->dynticks_nesting);
@@ -528,7 +523,7 @@ static void rcu_eqs_exit(bool user)
 	struct rcu_dynticks *rdtp;
 	long long oldval;
 
-	rdtp = &__get_cpu_var(rcu_dynticks);
+	rdtp = this_cpu_ptr(&rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
 	WARN_ON_ONCE(oldval < 0);
 	if (oldval & DYNTICK_TASK_NEST_MASK)
@@ -555,7 +550,7 @@ void rcu_idle_exit(void)
 
 	local_irq_save(flags);
 	rcu_eqs_exit(false);
-	rcu_sysidle_exit(&__get_cpu_var(rcu_dynticks), 0);
+	rcu_sysidle_exit(this_cpu_ptr(&rcu_dynticks), 0);
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(rcu_idle_exit);
@@ -599,7 +594,7 @@ void rcu_irq_enter(void)
 	long long oldval;
 
 	local_irq_save(flags);
-	rdtp = &__get_cpu_var(rcu_dynticks);
+	rdtp = this_cpu_ptr(&rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
 	rdtp->dynticks_nesting++;
 	WARN_ON_ONCE(rdtp->dynticks_nesting == 0);
@@ -620,7 +615,7 @@ void rcu_irq_enter(void)
  */
 void rcu_nmi_enter(void)
 {
-	struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
+	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
 
 	if (rdtp->dynticks_nmi_nesting == 0 &&
 	    (atomic_read(&rdtp->dynticks) & 0x1))
@@ -642,7 +637,7 @@ void rcu_nmi_enter(void)
  */
 void rcu_nmi_exit(void)
 {
-	struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
+	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
 
 	if (rdtp->dynticks_nmi_nesting == 0 ||
 	    --rdtp->dynticks_nmi_nesting != 0)
@@ -665,7 +660,7 @@ int rcu_is_cpu_idle(void)
 	int ret;
 
 	preempt_disable();
-	ret = (atomic_read(&__get_cpu_var(rcu_dynticks).dynticks) & 0x1) == 0;
+	ret = (atomic_read(this_cpu_ptr(&rcu_dynticks.dynticks)) & 0x1) == 0;
 	preempt_enable();
 	return ret;
 }
@@ -703,7 +698,7 @@ bool rcu_lockdep_current_cpu_online(void)
 	if (in_nmi())
 		return 1;
 	preempt_disable();
-	rdp = &__get_cpu_var(rcu_sched_data);
+	rdp = this_cpu_ptr(&rcu_sched_data);
 	rnp = rdp->mynode;
 	ret = (rdp->grpmask & rnp->qsmaskinit) ||
 	      !rcu_scheduler_fully_active;
@@ -723,7 +718,7 @@ EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online);
  */
 static int rcu_is_cpu_rrupt_from_idle(void)
 {
-	return __get_cpu_var(rcu_dynticks).dynticks_nesting <= 1;
+	return __this_cpu_read(rcu_dynticks.dynticks_nesting) <= 1;
 }
 
 /*
@@ -802,8 +797,11 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
 
 static void record_gp_stall_check_time(struct rcu_state *rsp)
 {
-	rsp->gp_start = jiffies;
-	rsp->jiffies_stall = jiffies + rcu_jiffies_till_stall_check();
+	unsigned long j = ACCESS_ONCE(jiffies);
+
+	rsp->gp_start = j;
+	smp_wmb(); /* Record start time before stall time. */
+	rsp->jiffies_stall = j + rcu_jiffies_till_stall_check();
 }
 
 /*
@@ -932,17 +930,48 @@ static void print_cpu_stall(struct rcu_state *rsp)
 
 static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
 {
+	unsigned long completed;
+	unsigned long gpnum;
+	unsigned long gps;
 	unsigned long j;
 	unsigned long js;
 	struct rcu_node *rnp;
 
-	if (rcu_cpu_stall_suppress)
+	if (rcu_cpu_stall_suppress || !rcu_gp_in_progress(rsp))
 		return;
 	j = ACCESS_ONCE(jiffies);
+
+	/*
+	 * Lots of memory barriers to reject false positives.
+	 *
+	 * The idea is to pick up rsp->gpnum, then rsp->jiffies_stall,
+	 * then rsp->gp_start, and finally rsp->completed.  These values
+	 * are updated in the opposite order with memory barriers (or
+	 * equivalent) during grace-period initialization and cleanup.
+	 * Now, a false positive can occur if we get an new value of
+	 * rsp->gp_start and a old value of rsp->jiffies_stall.  But given
+	 * the memory barriers, the only way that this can happen is if one
+	 * grace period ends and another starts between these two fetches.
+	 * Detect this by comparing rsp->completed with the previous fetch
+	 * from rsp->gpnum.
+	 *
+	 * Given this check, comparisons of jiffies, rsp->jiffies_stall,
+	 * and rsp->gp_start suffice to forestall false positives.
+	 */
+	gpnum = ACCESS_ONCE(rsp->gpnum);
+	smp_rmb(); /* Pick up ->gpnum first... */
 	js = ACCESS_ONCE(rsp->jiffies_stall);
+	smp_rmb(); /* ...then ->jiffies_stall before the rest... */
+	gps = ACCESS_ONCE(rsp->gp_start);
+	smp_rmb(); /* ...and finally ->gp_start before ->completed. */
+	completed = ACCESS_ONCE(rsp->completed);
+	if (ULONG_CMP_GE(completed, gpnum) ||
+	    ULONG_CMP_LT(j, js) ||
+	    ULONG_CMP_GE(gps, js))
+		return; /* No stall or GP completed since entering function. */
 	rnp = rdp->mynode;
 	if (rcu_gp_in_progress(rsp) &&
-	    (ACCESS_ONCE(rnp->qsmask) & rdp->grpmask) && ULONG_CMP_GE(j, js)) {
+	    (ACCESS_ONCE(rnp->qsmask) & rdp->grpmask)) {
 
 		/* We haven't checked in, so go dump stack. */
 		print_cpu_stall(rsp);
@@ -1315,9 +1344,10 @@ static int rcu_gp_init(struct rcu_state *rsp)
 	}
 
 	/* Advance to a new grace period and initialize state. */
+	record_gp_stall_check_time(rsp);
+	smp_wmb(); /* Record GP times before starting GP. */
 	rsp->gpnum++;
 	trace_rcu_grace_period(rsp->name, rsp->gpnum, TPS("start"));
-	record_gp_stall_check_time(rsp);
 	raw_spin_unlock_irq(&rnp->lock);
 
 	/* Exclude any concurrent CPU-hotplug operations. */
@@ -1366,7 +1396,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
 /*
  * Do one round of quiescent-state forcing.
  */
-int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
+static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
 {
 	int fqs_state = fqs_state_in;
 	bool isidle = false;
@@ -1452,7 +1482,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	rdp = this_cpu_ptr(rsp->rda);
 	rcu_advance_cbs(rsp, rnp, rdp);  /* Reduce false positives below. */
 	if (cpu_needs_another_gp(rsp, rdp))
-		rsp->gp_flags = 1;
+		rsp->gp_flags = RCU_GP_FLAG_INIT;
 	raw_spin_unlock_irq(&rnp->lock);
 }
 
@@ -2725,10 +2755,13 @@ static int rcu_cpu_has_callbacks(int cpu, bool *all_lazy)
 
 	for_each_rcu_flavor(rsp) {
 		rdp = per_cpu_ptr(rsp->rda, cpu);
-		if (rdp->qlen != rdp->qlen_lazy)
+		if (!rdp->nxtlist)
+			continue;
+		hc = true;
+		if (rdp->qlen != rdp->qlen_lazy || !all_lazy) {
 			al = false;
-		if (rdp->nxtlist)
-			hc = true;
+			break;
+		}
 	}
 	if (all_lazy)
 		*all_lazy = al;
@@ -3295,8 +3328,8 @@ void __init rcu_init(void)
 
 	rcu_bootup_announce();
 	rcu_init_geometry();
-	rcu_init_one(&rcu_sched_state, &rcu_sched_data);
 	rcu_init_one(&rcu_bh_state, &rcu_bh_data);
+	rcu_init_one(&rcu_sched_state, &rcu_sched_data);
 	__rcu_init_preempt();
 	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
 
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 130c97b027f2..1855d66bf705 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -96,10 +96,15 @@ static void __init rcu_bootup_announce_oddness(void)
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU_ZERO */
 #ifdef CONFIG_RCU_NOCB_CPU_ALL
 	pr_info("\tOffload RCU callbacks from all CPUs\n");
-	cpumask_setall(rcu_nocb_mask);
+	cpumask_copy(rcu_nocb_mask, cpu_possible_mask);
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU_ALL */
 #endif /* #ifndef CONFIG_RCU_NOCB_CPU_NONE */
 	if (have_rcu_nocb_mask) {
+		if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) {
+			pr_info("\tNote: kernel parameter 'rcu_nocbs=' contains nonexistent CPUs.\n");
+			cpumask_and(rcu_nocb_mask, cpu_possible_mask,
+				    rcu_nocb_mask);
+		}
 		cpulist_scnprintf(nocb_buf, sizeof(nocb_buf), rcu_nocb_mask);
 		pr_info("\tOffload RCU callbacks from CPUs: %s.\n", nocb_buf);
 		if (rcu_nocb_poll)
@@ -660,7 +665,7 @@ static void rcu_preempt_check_callbacks(int cpu)
 
 static void rcu_preempt_do_callbacks(void)
 {
-	rcu_do_batch(&rcu_preempt_state, &__get_cpu_var(rcu_preempt_data));
+	rcu_do_batch(&rcu_preempt_state, this_cpu_ptr(&rcu_preempt_data));
 }
 
 #endif /* #ifdef CONFIG_RCU_BOOST */
@@ -1332,7 +1337,7 @@ static void invoke_rcu_callbacks_kthread(void)
  */
 static bool rcu_is_callbacks_kthread(void)
 {
-	return __get_cpu_var(rcu_cpu_kthread_task) == current;
+	return __this_cpu_read(rcu_cpu_kthread_task) == current;
 }
 
 #define RCU_BOOST_DELAY_JIFFIES DIV_ROUND_UP(CONFIG_RCU_BOOST_DELAY * HZ, 1000)
@@ -1382,8 +1387,8 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 
 static void rcu_kthread_do_work(void)
 {
-	rcu_do_batch(&rcu_sched_state, &__get_cpu_var(rcu_sched_data));
-	rcu_do_batch(&rcu_bh_state, &__get_cpu_var(rcu_bh_data));
+	rcu_do_batch(&rcu_sched_state, this_cpu_ptr(&rcu_sched_data));
+	rcu_do_batch(&rcu_bh_state, this_cpu_ptr(&rcu_bh_data));
 	rcu_preempt_do_callbacks();
 }
 
@@ -1402,7 +1407,7 @@ static void rcu_cpu_kthread_park(unsigned int cpu)
 
 static int rcu_cpu_kthread_should_run(unsigned int cpu)
 {
-	return __get_cpu_var(rcu_cpu_has_work);
+	return __this_cpu_read(rcu_cpu_has_work);
 }
 
 /*
@@ -1412,8 +1417,8 @@ static int rcu_cpu_kthread_should_run(unsigned int cpu)
  */
 static void rcu_cpu_kthread(unsigned int cpu)
 {
-	unsigned int *statusp = &__get_cpu_var(rcu_cpu_kthread_status);
-	char work, *workp = &__get_cpu_var(rcu_cpu_has_work);
+	unsigned int *statusp = this_cpu_ptr(&rcu_cpu_kthread_status);
+	char work, *workp = this_cpu_ptr(&rcu_cpu_has_work);
 	int spincnt;
 
 	for (spincnt = 0; spincnt < 10; spincnt++) {
@@ -2108,7 +2113,7 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
 
 	/* If we are not being polled and there is a kthread, awaken it ... */
 	t = ACCESS_ONCE(rdp->nocb_kthread);
-	if (rcu_nocb_poll | !t)
+	if (rcu_nocb_poll || !t)
 		return;
 	len = atomic_long_read(&rdp->nocb_q_count);
 	if (old_rhpp == &rdp->nocb_head) {
diff --git a/mm/mlock.c b/mm/mlock.c
index d63802663242..67ba6da7d0e3 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -736,6 +736,7 @@ static int do_mlockall(int flags)
 
 		/* Ignore errors */
 		mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags);
+		cond_resched();
 	}
 out:
 	return 0;