Merge branch 'rcu/next' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu into core/rcu

Pull RCU updates from Paul E. McKenney:

" 1.      Update RCU documentation.  These were posted to LKML at
          https://lkml.org/lkml/2014/4/28/634.

  2.      Miscellaneous fixes.  These were posted to LKML at
          https://lkml.org/lkml/2014/4/28/645.

  3.      Torture-test changes.  These were posted to LKML at
          https://lkml.org/lkml/2014/4/28/667.

  4.      Variable-name renaming cleanup, sent separately due to conflicts.
          This was posted to LKML at https://lkml.org/lkml/2014/5/13/854.

  5.      Patch to suppress RCU stall warnings while sysrq requests are
          being processed.  This patch is the RCU portions of the patch
          that Rik posted to LKML at https://lkml.org/lkml/2014/4/29/457.
          The reason for pushing this patch ahead instead of waiting until
          3.17 is that the NMI-based stack traces are messing up sysrq
          output, and in some cases also messing up the system as well."

Signed-off-by: Ingo Molnar <mingo@kernel.org>

10 files changed, 506 insertions, 266 deletions

diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index f26b1a18e34e..dbafeac18e4d 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -82,14 +82,14 @@ struct lock_writer_stress_stats {
 };
 static struct lock_writer_stress_stats *lwsa;
 
-#if defined(MODULE) || defined(CONFIG_LOCK_TORTURE_TEST_RUNNABLE)
+#if defined(MODULE)
 #define LOCKTORTURE_RUNNABLE_INIT 1
 #else
 #define LOCKTORTURE_RUNNABLE_INIT 0
 #endif
 int locktorture_runnable = LOCKTORTURE_RUNNABLE_INIT;
 module_param(locktorture_runnable, int, 0444);
-MODULE_PARM_DESC(locktorture_runnable, "Start locktorture at boot");
+MODULE_PARM_DESC(locktorture_runnable, "Start locktorture at module init");
 
 /* Forward reference. */
 static void lock_torture_cleanup(void);
@@ -219,7 +219,8 @@ static int lock_torture_writer(void *arg)
 	set_user_nice(current, 19);
 
 	do {
-		schedule_timeout_uninterruptible(1);
+		if ((torture_random(&rand) & 0xfffff) == 0)
+			schedule_timeout_uninterruptible(1);
 		cur_ops->writelock();
 		if (WARN_ON_ONCE(lock_is_write_held))
 			lwsp->n_write_lock_fail++;
@@ -354,7 +355,8 @@ static int __init lock_torture_init(void)
 		&lock_busted_ops, &spin_lock_ops, &spin_lock_irq_ops,
 	};
 
-	torture_init_begin(torture_type, verbose, &locktorture_runnable);
+	if (!torture_init_begin(torture_type, verbose, &locktorture_runnable))
+		return -EBUSY;
 
 	/* Process args and tell the world that the torturer is on the job. */
 	for (i = 0; i < ARRAY_SIZE(torture_ops); i++) {
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index bd30bc61bc05..7fa34f86e5ba 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -58,9 +58,11 @@ torture_param(int, fqs_duration, 0,
 	      "Duration of fqs bursts (us), 0 to disable");
 torture_param(int, fqs_holdoff, 0, "Holdoff time within fqs bursts (us)");
 torture_param(int, fqs_stutter, 3, "Wait time between fqs bursts (s)");
+torture_param(bool, gp_cond, false, "Use conditional/async GP wait primitives");
 torture_param(bool, gp_exp, false, "Use expedited GP wait primitives");
 torture_param(bool, gp_normal, false,
 	     "Use normal (non-expedited) GP wait primitives");
+torture_param(bool, gp_sync, false, "Use synchronous GP wait primitives");
 torture_param(int, irqreader, 1, "Allow RCU readers from irq handlers");
 torture_param(int, n_barrier_cbs, 0,
 	     "# of callbacks/kthreads for barrier testing");
@@ -138,6 +140,18 @@ static long n_barrier_attempts;
 static long n_barrier_successes;
 static struct list_head rcu_torture_removed;
 
+static int rcu_torture_writer_state;
+#define RTWS_FIXED_DELAY	0
+#define RTWS_DELAY		1
+#define RTWS_REPLACE		2
+#define RTWS_DEF_FREE		3
+#define RTWS_EXP_SYNC		4
+#define RTWS_COND_GET		5
+#define RTWS_COND_SYNC		6
+#define RTWS_SYNC		7
+#define RTWS_STUTTER		8
+#define RTWS_STOPPING		9
+
 #if defined(MODULE) || defined(CONFIG_RCU_TORTURE_TEST_RUNNABLE)
 #define RCUTORTURE_RUNNABLE_INIT 1
 #else
@@ -214,6 +228,7 @@ rcu_torture_free(struct rcu_torture *p)
  */
 
 struct rcu_torture_ops {
+	int ttype;
 	void (*init)(void);
 	int (*readlock)(void);
 	void (*read_delay)(struct torture_random_state *rrsp);
@@ -222,6 +237,8 @@ struct rcu_torture_ops {
 	void (*deferred_free)(struct rcu_torture *p);
 	void (*sync)(void);
 	void (*exp_sync)(void);
+	unsigned long (*get_state)(void);
+	void (*cond_sync)(unsigned long oldstate);
 	void (*call)(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
 	void (*cb_barrier)(void);
 	void (*fqs)(void);
@@ -273,10 +290,48 @@ static int rcu_torture_completed(void)
 	return rcu_batches_completed();
 }
 
+/*
+ * Update callback in the pipe.  This should be invoked after a grace period.
+ */
+static bool
+rcu_torture_pipe_update_one(struct rcu_torture *rp)
+{
+	int i;
+
+	i = rp->rtort_pipe_count;
+	if (i > RCU_TORTURE_PIPE_LEN)
+		i = RCU_TORTURE_PIPE_LEN;
+	atomic_inc(&rcu_torture_wcount[i]);
+	if (++rp->rtort_pipe_count >= RCU_TORTURE_PIPE_LEN) {
+		rp->rtort_mbtest = 0;
+		return true;
+	}
+	return false;
+}
+
+/*
+ * Update all callbacks in the pipe.  Suitable for synchronous grace-period
+ * primitives.
+ */
+static void
+rcu_torture_pipe_update(struct rcu_torture *old_rp)
+{
+	struct rcu_torture *rp;
+	struct rcu_torture *rp1;
+
+	if (old_rp)
+		list_add(&old_rp->rtort_free, &rcu_torture_removed);
+	list_for_each_entry_safe(rp, rp1, &rcu_torture_removed, rtort_free) {
+		if (rcu_torture_pipe_update_one(rp)) {
+			list_del(&rp->rtort_free);
+			rcu_torture_free(rp);
+		}
+	}
+}
+
 static void
 rcu_torture_cb(struct rcu_head *p)
 {
-	int i;
 	struct rcu_torture *rp = container_of(p, struct rcu_torture, rtort_rcu);
 
 	if (torture_must_stop_irq()) {
@@ -284,16 +339,10 @@ rcu_torture_cb(struct rcu_head *p)
 		/* The next initialization will pick up the pieces. */
 		return;
 	}
-	i = rp->rtort_pipe_count;
-	if (i > RCU_TORTURE_PIPE_LEN)
-		i = RCU_TORTURE_PIPE_LEN;
-	atomic_inc(&rcu_torture_wcount[i]);
-	if (++rp->rtort_pipe_count >= RCU_TORTURE_PIPE_LEN) {
-		rp->rtort_mbtest = 0;
+	if (rcu_torture_pipe_update_one(rp))
 		rcu_torture_free(rp);
-	} else {
+	else
 		cur_ops->deferred_free(rp);
-	}
 }
 
 static int rcu_no_completed(void)
@@ -312,6 +361,7 @@ static void rcu_sync_torture_init(void)
 }
 
 static struct rcu_torture_ops rcu_ops = {
+	.ttype		= RCU_FLAVOR,
 	.init		= rcu_sync_torture_init,
 	.readlock	= rcu_torture_read_lock,
 	.read_delay	= rcu_read_delay,
@@ -320,6 +370,8 @@ static struct rcu_torture_ops rcu_ops = {
 	.deferred_free	= rcu_torture_deferred_free,
 	.sync		= synchronize_rcu,
 	.exp_sync	= synchronize_rcu_expedited,
+	.get_state	= get_state_synchronize_rcu,
+	.cond_sync	= cond_synchronize_rcu,
 	.call		= call_rcu,
 	.cb_barrier	= rcu_barrier,
 	.fqs		= rcu_force_quiescent_state,
@@ -355,6 +407,7 @@ static void rcu_bh_torture_deferred_free(struct rcu_torture *p)
 }
 
 static struct rcu_torture_ops rcu_bh_ops = {
+	.ttype		= RCU_BH_FLAVOR,
 	.init		= rcu_sync_torture_init,
 	.readlock	= rcu_bh_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
@@ -397,6 +450,7 @@ call_rcu_busted(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
 }
 
 static struct rcu_torture_ops rcu_busted_ops = {
+	.ttype		= INVALID_RCU_FLAVOR,
 	.init		= rcu_sync_torture_init,
 	.readlock	= rcu_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
@@ -479,9 +533,11 @@ static void srcu_torture_stats(char *page)
 	page += sprintf(page, "%s%s per-CPU(idx=%d):",
 		       torture_type, TORTURE_FLAG, idx);
 	for_each_possible_cpu(cpu) {
-		page += sprintf(page, " %d(%lu,%lu)", cpu,
-			       per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[!idx],
-			       per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[idx]);
+		long c0, c1;
+
+		c0 = (long)per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[!idx];
+		c1 = (long)per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[idx];
+		page += sprintf(page, " %d(%ld,%ld)", cpu, c0, c1);
 	}
 	sprintf(page, "\n");
 }
@@ -492,6 +548,7 @@ static void srcu_torture_synchronize_expedited(void)
 }
 
 static struct rcu_torture_ops srcu_ops = {
+	.ttype		= SRCU_FLAVOR,
 	.init		= rcu_sync_torture_init,
 	.readlock	= srcu_torture_read_lock,
 	.read_delay	= srcu_read_delay,
@@ -527,6 +584,7 @@ static void rcu_sched_torture_deferred_free(struct rcu_torture *p)
 }
 
 static struct rcu_torture_ops sched_ops = {
+	.ttype		= RCU_SCHED_FLAVOR,
 	.init		= rcu_sync_torture_init,
 	.readlock	= sched_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
@@ -688,23 +746,59 @@ rcu_torture_fqs(void *arg)
 static int
 rcu_torture_writer(void *arg)
 {
-	bool exp;
+	unsigned long gp_snap;
+	bool gp_cond1 = gp_cond, gp_exp1 = gp_exp, gp_normal1 = gp_normal;
+	bool gp_sync1 = gp_sync;
 	int i;
 	struct rcu_torture *rp;
-	struct rcu_torture *rp1;
 	struct rcu_torture *old_rp;
 	static DEFINE_TORTURE_RANDOM(rand);
+	int synctype[] = { RTWS_DEF_FREE, RTWS_EXP_SYNC,
+			   RTWS_COND_GET, RTWS_SYNC };
+	int nsynctypes = 0;
 
 	VERBOSE_TOROUT_STRING("rcu_torture_writer task started");
-	set_user_nice(current, MAX_NICE);
+
+	/* Initialize synctype[] array.  If none set, take default. */
+	if (!gp_cond1 && !gp_exp1 && !gp_normal1 && !gp_sync)
+		gp_cond1 = gp_exp1 = gp_normal1 = gp_sync1 = true;
+	if (gp_cond1 && cur_ops->get_state && cur_ops->cond_sync)
+		synctype[nsynctypes++] = RTWS_COND_GET;
+	else if (gp_cond && (!cur_ops->get_state || !cur_ops->cond_sync))
+		pr_alert("rcu_torture_writer: gp_cond without primitives.\n");
+	if (gp_exp1 && cur_ops->exp_sync)
+		synctype[nsynctypes++] = RTWS_EXP_SYNC;
+	else if (gp_exp && !cur_ops->exp_sync)
+		pr_alert("rcu_torture_writer: gp_exp without primitives.\n");
+	if (gp_normal1 && cur_ops->deferred_free)
+		synctype[nsynctypes++] = RTWS_DEF_FREE;
+	else if (gp_normal && !cur_ops->deferred_free)
+		pr_alert("rcu_torture_writer: gp_normal without primitives.\n");
+	if (gp_sync1 && cur_ops->sync)
+		synctype[nsynctypes++] = RTWS_SYNC;
+	else if (gp_sync && !cur_ops->sync)
+		pr_alert("rcu_torture_writer: gp_sync without primitives.\n");
+	if (WARN_ONCE(nsynctypes == 0,
+		      "rcu_torture_writer: No update-side primitives.\n")) {
+		/*
+		 * No updates primitives, so don't try updating.
+		 * The resulting test won't be testing much, hence the
+		 * above WARN_ONCE().
+		 */
+		rcu_torture_writer_state = RTWS_STOPPING;
+		torture_kthread_stopping("rcu_torture_writer");
+	}
 
 	do {
+		rcu_torture_writer_state = RTWS_FIXED_DELAY;
 		schedule_timeout_uninterruptible(1);
 		rp = rcu_torture_alloc();
 		if (rp == NULL)
 			continue;
 		rp->rtort_pipe_count = 0;
+		rcu_torture_writer_state = RTWS_DELAY;
 		udelay(torture_random(&rand) & 0x3ff);
+		rcu_torture_writer_state = RTWS_REPLACE;
 		old_rp = rcu_dereference_check(rcu_torture_current,
 					       current == writer_task);
 		rp->rtort_mbtest = 1;
@@ -716,35 +810,42 @@ rcu_torture_writer(void *arg)
 				i = RCU_TORTURE_PIPE_LEN;
 			atomic_inc(&rcu_torture_wcount[i]);
 			old_rp->rtort_pipe_count++;
-			if (gp_normal == gp_exp)
-				exp = !!(torture_random(&rand) & 0x80);
-			else
-				exp = gp_exp;
-			if (!exp) {
+			switch (synctype[torture_random(&rand) % nsynctypes]) {
+			case RTWS_DEF_FREE:
+				rcu_torture_writer_state = RTWS_DEF_FREE;
 				cur_ops->deferred_free(old_rp);
-			} else {
+				break;
+			case RTWS_EXP_SYNC:
+				rcu_torture_writer_state = RTWS_EXP_SYNC;
 				cur_ops->exp_sync();
-				list_add(&old_rp->rtort_free,
-					 &rcu_torture_removed);
-				list_for_each_entry_safe(rp, rp1,
-							 &rcu_torture_removed,
-							 rtort_free) {
-					i = rp->rtort_pipe_count;
-					if (i > RCU_TORTURE_PIPE_LEN)
-						i = RCU_TORTURE_PIPE_LEN;
-					atomic_inc(&rcu_torture_wcount[i]);
-					if (++rp->rtort_pipe_count >=
-					    RCU_TORTURE_PIPE_LEN) {
-						rp->rtort_mbtest = 0;
-						list_del(&rp->rtort_free);
-						rcu_torture_free(rp);
-					}
-				 }
+				rcu_torture_pipe_update(old_rp);
+				break;
+			case RTWS_COND_GET:
+				rcu_torture_writer_state = RTWS_COND_GET;
+				gp_snap = cur_ops->get_state();
+				i = torture_random(&rand) % 16;
+				if (i != 0)
+					schedule_timeout_interruptible(i);
+				udelay(torture_random(&rand) % 1000);
+				rcu_torture_writer_state = RTWS_COND_SYNC;
+				cur_ops->cond_sync(gp_snap);
+				rcu_torture_pipe_update(old_rp);
+				break;
+			case RTWS_SYNC:
+				rcu_torture_writer_state = RTWS_SYNC;
+				cur_ops->sync();
+				rcu_torture_pipe_update(old_rp);
+				break;
+			default:
+				WARN_ON_ONCE(1);
+				break;
 			}
 		}
 		rcutorture_record_progress(++rcu_torture_current_version);
+		rcu_torture_writer_state = RTWS_STUTTER;
 		stutter_wait("rcu_torture_writer");
 	} while (!torture_must_stop());
+	rcu_torture_writer_state = RTWS_STOPPING;
 	torture_kthread_stopping("rcu_torture_writer");
 	return 0;
 }
@@ -784,7 +885,7 @@ rcu_torture_fakewriter(void *arg)
 	return 0;
 }
 
-void rcutorture_trace_dump(void)
+static void rcutorture_trace_dump(void)
 {
 	static atomic_t beenhere = ATOMIC_INIT(0);
 
@@ -918,11 +1019,13 @@ rcu_torture_reader(void *arg)
 		__this_cpu_inc(rcu_torture_batch[completed]);
 		preempt_enable();
 		cur_ops->readunlock(idx);
-		schedule();
+		cond_resched();
 		stutter_wait("rcu_torture_reader");
 	} while (!torture_must_stop());
-	if (irqreader && cur_ops->irq_capable)
+	if (irqreader && cur_ops->irq_capable) {
 		del_timer_sync(&t);
+		destroy_timer_on_stack(&t);
+	}
 	torture_kthread_stopping("rcu_torture_reader");
 	return 0;
 }
@@ -937,6 +1040,7 @@ rcu_torture_printk(char *page)
 	int i;
 	long pipesummary[RCU_TORTURE_PIPE_LEN + 1] = { 0 };
 	long batchsummary[RCU_TORTURE_PIPE_LEN + 1] = { 0 };
+	static unsigned long rtcv_snap = ULONG_MAX;
 
 	for_each_possible_cpu(cpu) {
 		for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) {
@@ -997,6 +1101,22 @@ rcu_torture_printk(char *page)
 	page += sprintf(page, "\n");
 	if (cur_ops->stats)
 		cur_ops->stats(page);
+	if (rtcv_snap == rcu_torture_current_version &&
+	    rcu_torture_current != NULL) {
+		int __maybe_unused flags;
+		unsigned long __maybe_unused gpnum;
+		unsigned long __maybe_unused completed;
+
+		rcutorture_get_gp_data(cur_ops->ttype,
+				       &flags, &gpnum, &completed);
+		page += sprintf(page,
+				"??? Writer stall state %d g%lu c%lu f%#x\n",
+				rcu_torture_writer_state,
+				gpnum, completed, flags);
+		show_rcu_gp_kthreads();
+		rcutorture_trace_dump();
+	}
+	rtcv_snap = rcu_torture_current_version;
 }
 
 /*
@@ -1146,7 +1266,7 @@ static int __init rcu_torture_stall_init(void)
 }
 
 /* Callback function for RCU barrier testing. */
-void rcu_torture_barrier_cbf(struct rcu_head *rcu)
+static void rcu_torture_barrier_cbf(struct rcu_head *rcu)
 {
 	atomic_inc(&barrier_cbs_invoked);
 }
@@ -1416,7 +1536,8 @@ rcu_torture_init(void)
 		&rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &sched_ops,
 	};
 
-	torture_init_begin(torture_type, verbose, &rcutorture_runnable);
+	if (!torture_init_begin(torture_type, verbose, &rcutorture_runnable))
+		return -EBUSY;
 
 	/* Process args and tell the world that the torturer is on the job. */
 	for (i = 0; i < ARRAY_SIZE(torture_ops); i++) {
@@ -1441,10 +1562,13 @@ rcu_torture_init(void)
 	if (cur_ops->init)
 		cur_ops->init(); /* no "goto unwind" prior to this point!!! */
 
-	if (nreaders >= 0)
+	if (nreaders >= 0) {
 		nrealreaders = nreaders;
-	else
-		nrealreaders = 2 * num_online_cpus();
+	} else {
+		nrealreaders = num_online_cpus() - 1;
+		if (nrealreaders <= 0)
+			nrealreaders = 1;
+	}
 	rcu_torture_print_module_parms(cur_ops, "Start of test");
 
 	/* Set up the freelist. */
@@ -1533,7 +1657,8 @@ rcu_torture_init(void)
 		fqs_duration = 0;
 	if (fqs_duration) {
 		/* Create the fqs thread */
-		torture_create_kthread(rcu_torture_fqs, NULL, fqs_task);
+		firsterr = torture_create_kthread(rcu_torture_fqs, NULL,
+						  fqs_task);
 		if (firsterr)
 			goto unwind;
 	}
diff --git a/kernel/rcu/tiny_plugin.h b/kernel/rcu/tiny_plugin.h
index 431528520562..858c56569127 100644
--- a/kernel/rcu/tiny_plugin.h
+++ b/kernel/rcu/tiny_plugin.h
@@ -144,7 +144,7 @@ static void check_cpu_stall(struct rcu_ctrlblk *rcp)
 		return;
 	rcp->ticks_this_gp++;
 	j = jiffies;
-	js = rcp->jiffies_stall;
+	js = ACCESS_ONCE(rcp->jiffies_stall);
 	if (*rcp->curtail && ULONG_CMP_GE(j, js)) {
 		pr_err("INFO: %s stall on CPU (%lu ticks this GP) idle=%llx (t=%lu jiffies q=%ld)\n",
 		       rcp->name, rcp->ticks_this_gp, rcu_dynticks_nesting,
@@ -152,17 +152,17 @@ static void check_cpu_stall(struct rcu_ctrlblk *rcp)
 		dump_stack();
 	}
 	if (*rcp->curtail && ULONG_CMP_GE(j, js))
-		rcp->jiffies_stall = jiffies +
+		ACCESS_ONCE(rcp->jiffies_stall) = jiffies +
 			3 * rcu_jiffies_till_stall_check() + 3;
 	else if (ULONG_CMP_GE(j, js))
-		rcp->jiffies_stall = jiffies + rcu_jiffies_till_stall_check();
+		ACCESS_ONCE(rcp->jiffies_stall) = jiffies + rcu_jiffies_till_stall_check();
 }
 
 static void reset_cpu_stall_ticks(struct rcu_ctrlblk *rcp)
 {
 	rcp->ticks_this_gp = 0;
 	rcp->gp_start = jiffies;
-	rcp->jiffies_stall = jiffies + rcu_jiffies_till_stall_check();
+	ACCESS_ONCE(rcp->jiffies_stall) = jiffies + rcu_jiffies_till_stall_check();
 }
 
 static void check_cpu_stalls(void)
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 0c47e300210a..3e3f13e8b429 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -101,7 +101,7 @@ DEFINE_PER_CPU(struct rcu_data, sname##_data)
 RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched);
 RCU_STATE_INITIALIZER(rcu_bh, 'b', call_rcu_bh);
 
-static struct rcu_state *rcu_state;
+static struct rcu_state *rcu_state_p;
 LIST_HEAD(rcu_struct_flavors);
 
 /* Increase (but not decrease) the CONFIG_RCU_FANOUT_LEAF at boot time. */
@@ -243,7 +243,7 @@ static ulong jiffies_till_next_fqs = ULONG_MAX;
 module_param(jiffies_till_first_fqs, ulong, 0644);
 module_param(jiffies_till_next_fqs, ulong, 0644);
 
-static void rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
+static bool rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
 				  struct rcu_data *rdp);
 static void force_qs_rnp(struct rcu_state *rsp,
 			 int (*f)(struct rcu_data *rsp, bool *isidle,
@@ -271,6 +271,15 @@ long rcu_batches_completed_bh(void)
 EXPORT_SYMBOL_GPL(rcu_batches_completed_bh);
 
 /*
+ * Force a quiescent state.
+ */
+void rcu_force_quiescent_state(void)
+{
+	force_quiescent_state(rcu_state_p);
+}
+EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
+
+/*
  * Force a quiescent state for RCU BH.
  */
 void rcu_bh_force_quiescent_state(void)
@@ -280,6 +289,21 @@ void rcu_bh_force_quiescent_state(void)
 EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state);
 
 /*
+ * Show the state of the grace-period kthreads.
+ */
+void show_rcu_gp_kthreads(void)
+{
+	struct rcu_state *rsp;
+
+	for_each_rcu_flavor(rsp) {
+		pr_info("%s: wait state: %d ->state: %#lx\n",
+			rsp->name, rsp->gp_state, rsp->gp_kthread->state);
+		/* sched_show_task(rsp->gp_kthread); */
+	}
+}
+EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads);
+
+/*
  * Record the number of times rcutorture tests have been initiated and
  * terminated.  This information allows the debugfs tracing stats to be
  * correlated to the rcutorture messages, even when the rcutorture module
@@ -294,6 +318,39 @@ void rcutorture_record_test_transition(void)
 EXPORT_SYMBOL_GPL(rcutorture_record_test_transition);
 
 /*
+ * Send along grace-period-related data for rcutorture diagnostics.
+ */
+void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
+			    unsigned long *gpnum, unsigned long *completed)
+{
+	struct rcu_state *rsp = NULL;
+
+	switch (test_type) {
+	case RCU_FLAVOR:
+		rsp = rcu_state_p;
+		break;
+	case RCU_BH_FLAVOR:
+		rsp = &rcu_bh_state;
+		break;
+	case RCU_SCHED_FLAVOR:
+		rsp = &rcu_sched_state;
+		break;
+	default:
+		break;
+	}
+	if (rsp != NULL) {
+		*flags = ACCESS_ONCE(rsp->gp_flags);
+		*gpnum = ACCESS_ONCE(rsp->gpnum);
+		*completed = ACCESS_ONCE(rsp->completed);
+		return;
+	}
+	*flags = 0;
+	*gpnum = 0;
+	*completed = 0;
+}
+EXPORT_SYMBOL_GPL(rcutorture_get_gp_data);
+
+/*
  * Record the number of writer passes through the current rcutorture test.
  * This is also used to correlate debugfs tracing stats with the rcutorture
  * messages.
@@ -324,6 +381,28 @@ cpu_has_callbacks_ready_to_invoke(struct rcu_data *rdp)
 }
 
 /*
+ * Return the root node of the specified rcu_state structure.
+ */
+static struct rcu_node *rcu_get_root(struct rcu_state *rsp)
+{
+	return &rsp->node[0];
+}
+
+/*
+ * Is there any need for future grace periods?
+ * Interrupts must be disabled.  If the caller does not hold the root
+ * rnp_node structure's ->lock, the results are advisory only.
+ */
+static int rcu_future_needs_gp(struct rcu_state *rsp)
+{
+	struct rcu_node *rnp = rcu_get_root(rsp);
+	int idx = (ACCESS_ONCE(rnp->completed) + 1) & 0x1;
+	int *fp = &rnp->need_future_gp[idx];
+
+	return ACCESS_ONCE(*fp);
+}
+
+/*
  * Does the current CPU require a not-yet-started grace period?
  * The caller must have disabled interrupts to prevent races with
  * normal callback registry.
@@ -335,7 +414,7 @@ cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
 
 	if (rcu_gp_in_progress(rsp))
 		return 0;  /* No, a grace period is already in progress. */
-	if (rcu_nocb_needs_gp(rsp))
+	if (rcu_future_needs_gp(rsp))
 		return 1;  /* Yes, a no-CBs CPU needs one. */
 	if (!rdp->nxttail[RCU_NEXT_TAIL])
 		return 0;  /* No, this is a no-CBs (or offline) CPU. */
@@ -350,14 +429,6 @@ cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
 }
 
 /*
- * Return the root node of the specified rcu_state structure.
- */
-static struct rcu_node *rcu_get_root(struct rcu_state *rsp)
-{
-	return &rsp->node[0];
-}
-
-/*
  * rcu_eqs_enter_common - current CPU is moving towards extended quiescent state
  *
  * If the new value of the ->dynticks_nesting counter now is zero,
@@ -758,7 +829,12 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp,
 {
 	rdp->dynticks_snap = atomic_add_return(0, &rdp->dynticks->dynticks);
 	rcu_sysidle_check_cpu(rdp, isidle, maxj);
-	return (rdp->dynticks_snap & 0x1) == 0;
+	if ((rdp->dynticks_snap & 0x1) == 0) {
+		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti"));
+		return 1;
+	} else {
+		return 0;
+	}
 }
 
 /*
@@ -834,7 +910,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
 	 * we will beat on the first one until it gets unstuck, then move
 	 * to the next.  Only do this for the primary flavor of RCU.
 	 */
-	if (rdp->rsp == rcu_state &&
+	if (rdp->rsp == rcu_state_p &&
 	    ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) {
 		rdp->rsp->jiffies_resched += 5;
 		resched_cpu(rdp->cpu);
@@ -851,7 +927,7 @@ static void record_gp_stall_check_time(struct rcu_state *rsp)
 	rsp->gp_start = j;
 	smp_wmb(); /* Record start time before stall time. */
 	j1 = rcu_jiffies_till_stall_check();
-	rsp->jiffies_stall = j + j1;
+	ACCESS_ONCE(rsp->jiffies_stall) = j + j1;
 	rsp->jiffies_resched = j + j1 / 2;
 }
 
@@ -890,12 +966,12 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
 	/* Only let one CPU complain about others per time interval. */
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
-	delta = jiffies - rsp->jiffies_stall;
+	delta = jiffies - ACCESS_ONCE(rsp->jiffies_stall);
 	if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) {
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		return;
 	}
-	rsp->jiffies_stall = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
+	ACCESS_ONCE(rsp->jiffies_stall) = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 
 	/*
@@ -932,9 +1008,9 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
 	print_cpu_stall_info_end();
 	for_each_possible_cpu(cpu)
 		totqlen += per_cpu_ptr(rsp->rda, cpu)->qlen;
-	pr_cont("(detected by %d, t=%ld jiffies, g=%lu, c=%lu, q=%lu)\n",
+	pr_cont("(detected by %d, t=%ld jiffies, g=%ld, c=%ld, q=%lu)\n",
 	       smp_processor_id(), (long)(jiffies - rsp->gp_start),
-	       rsp->gpnum, rsp->completed, totqlen);
+	       (long)rsp->gpnum, (long)rsp->completed, totqlen);
 	if (ndetected == 0)
 		pr_err("INFO: Stall ended before state dump start\n");
 	else if (!trigger_all_cpu_backtrace())
@@ -947,12 +1023,6 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
 	force_quiescent_state(rsp);  /* Kick them all. */
 }
 
-/*
- * This function really isn't for public consumption, but RCU is special in
- * that context switches can allow the state machine to make progress.
- */
-extern void resched_cpu(int cpu);
-
 static void print_cpu_stall(struct rcu_state *rsp)
 {
 	int cpu;
@@ -971,14 +1041,15 @@ static void print_cpu_stall(struct rcu_state *rsp)
 	print_cpu_stall_info_end();
 	for_each_possible_cpu(cpu)
 		totqlen += per_cpu_ptr(rsp->rda, cpu)->qlen;
-	pr_cont(" (t=%lu jiffies g=%lu c=%lu q=%lu)\n",
-		jiffies - rsp->gp_start, rsp->gpnum, rsp->completed, totqlen);
+	pr_cont(" (t=%lu jiffies g=%ld c=%ld q=%lu)\n",
+		jiffies - rsp->gp_start,
+		(long)rsp->gpnum, (long)rsp->completed, totqlen);
 	if (!trigger_all_cpu_backtrace())
 		dump_stack();
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
-	if (ULONG_CMP_GE(jiffies, rsp->jiffies_stall))
-		rsp->jiffies_stall = jiffies +
+	if (ULONG_CMP_GE(jiffies, ACCESS_ONCE(rsp->jiffies_stall)))
+		ACCESS_ONCE(rsp->jiffies_stall) = jiffies +
 				     3 * rcu_jiffies_till_stall_check() + 3;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 
@@ -1062,7 +1133,7 @@ void rcu_cpu_stall_reset(void)
 	struct rcu_state *rsp;
 
 	for_each_rcu_flavor(rsp)
-		rsp->jiffies_stall = jiffies + ULONG_MAX / 2;
+		ACCESS_ONCE(rsp->jiffies_stall) = jiffies + ULONG_MAX / 2;
 }
 
 /*
@@ -1123,15 +1194,18 @@ static void trace_rcu_future_gp(struct rcu_node *rnp, struct rcu_data *rdp,
 /*
  * Start some future grace period, as needed to handle newly arrived
  * callbacks.  The required future grace periods are recorded in each
- * rcu_node structure's ->need_future_gp field.
+ * rcu_node structure's ->need_future_gp field.  Returns true if there
+ * is reason to awaken the grace-period kthread.
  *
  * The caller must hold the specified rcu_node structure's ->lock.
  */
-static unsigned long __maybe_unused
-rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp)
+static bool __maybe_unused
+rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp,
+		    unsigned long *c_out)
 {
 	unsigned long c;
 	int i;
+	bool ret = false;
 	struct rcu_node *rnp_root = rcu_get_root(rdp->rsp);
 
 	/*
@@ -1142,7 +1216,7 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp)
 	trace_rcu_future_gp(rnp, rdp, c, TPS("Startleaf"));
 	if (rnp->need_future_gp[c & 0x1]) {
 		trace_rcu_future_gp(rnp, rdp, c, TPS("Prestartleaf"));
-		return c;
+		goto out;
 	}
 
 	/*
@@ -1156,7 +1230,7 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp)
 	    ACCESS_ONCE(rnp->gpnum) != ACCESS_ONCE(rnp->completed)) {
 		rnp->need_future_gp[c & 0x1]++;
 		trace_rcu_future_gp(rnp, rdp, c, TPS("Startedleaf"));
-		return c;
+		goto out;
 	}
 
 	/*
@@ -1197,12 +1271,15 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp)
 		trace_rcu_future_gp(rnp, rdp, c, TPS("Startedleafroot"));
 	} else {
 		trace_rcu_future_gp(rnp, rdp, c, TPS("Startedroot"));
-		rcu_start_gp_advanced(rdp->rsp, rnp_root, rdp);
+		ret = rcu_start_gp_advanced(rdp->rsp, rnp_root, rdp);
 	}
 unlock_out:
 	if (rnp != rnp_root)
 		raw_spin_unlock(&rnp_root->lock);
-	return c;
+out:
+	if (c_out != NULL)
+		*c_out = c;
+	return ret;
 }
 
 /*
@@ -1226,25 +1303,43 @@ static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
 }
 
 /*
+ * Awaken the grace-period kthread for the specified flavor of RCU.
+ * Don't do a self-awaken, and don't bother awakening when there is
+ * nothing for the grace-period kthread to do (as in several CPUs
+ * raced to awaken, and we lost), and finally don't try to awaken
+ * a kthread that has not yet been created.
+ */
+static void rcu_gp_kthread_wake(struct rcu_state *rsp)
+{
+	if (current == rsp->gp_kthread ||
+	    !ACCESS_ONCE(rsp->gp_flags) ||
+	    !rsp->gp_kthread)
+		return;
+	wake_up(&rsp->gp_wq);
+}
+
+/*
  * If there is room, assign a ->completed number to any callbacks on
  * this CPU that have not already been assigned.  Also accelerate any
  * callbacks that were previously assigned a ->completed number that has
  * since proven to be too conservative, which can happen if callbacks get
  * assigned a ->completed number while RCU is idle, but with reference to
  * a non-root rcu_node structure.  This function is idempotent, so it does
- * not hurt to call it repeatedly.
+ * not hurt to call it repeatedly.  Returns an flag saying that we should
+ * awaken the RCU grace-period kthread.
  *
  * The caller must hold rnp->lock with interrupts disabled.
  */
-static void rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
+static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
 			       struct rcu_data *rdp)
 {
 	unsigned long c;
 	int i;
+	bool ret;
 
 	/* If the CPU has no callbacks, nothing to do. */
 	if (!rdp->nxttail[RCU_NEXT_TAIL] || !*rdp->nxttail[RCU_DONE_TAIL])
-		return;
+		return false;
 
 	/*
 	 * Starting from the sublist containing the callbacks most
@@ -1273,7 +1368,7 @@ static void rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
 	 * be grouped into.
 	 */
 	if (++i >= RCU_NEXT_TAIL)
-		return;
+		return false;
 
 	/*
 	 * Assign all subsequent callbacks' ->completed number to the next
@@ -1285,13 +1380,14 @@ static void rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
 		rdp->nxtcompleted[i] = c;
 	}
 	/* Record any needed additional grace periods. */
-	rcu_start_future_gp(rnp, rdp);
+	ret = rcu_start_future_gp(rnp, rdp, NULL);
 
 	/* Trace depending on how much we were able to accelerate. */
 	if (!*rdp->nxttail[RCU_WAIT_TAIL])
 		trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccWaitCB"));
 	else
 		trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccReadyCB"));
+	return ret;
 }
 
 /*
@@ -1300,17 +1396,18 @@ static void rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
  * assign ->completed numbers to any callbacks in the RCU_NEXT_TAIL
  * sublist.  This function is idempotent, so it does not hurt to
  * invoke it repeatedly.  As long as it is not invoked -too- often...
+ * Returns true if the RCU grace-period kthread needs to be awakened.
  *
  * The caller must hold rnp->lock with interrupts disabled.
  */
-static void rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
+static bool rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
 			    struct rcu_data *rdp)
 {
 	int i, j;
 
 	/* If the CPU has no callbacks, nothing to do. */
 	if (!rdp->nxttail[RCU_NEXT_TAIL] || !*rdp->nxttail[RCU_DONE_TAIL])
-		return;
+		return false;
 
 	/*
 	 * Find all callbacks whose ->completed numbers indicate that they
@@ -1334,26 +1431,30 @@ static void rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
 	}
 
 	/* Classify any remaining callbacks. */
-	rcu_accelerate_cbs(rsp, rnp, rdp);
+	return rcu_accelerate_cbs(rsp, rnp, rdp);
 }
 
 /*
  * Update CPU-local rcu_data state to record the beginnings and ends of
  * grace periods.  The caller must hold the ->lock of the leaf rcu_node
  * structure corresponding to the current CPU, and must have irqs disabled.
+ * Returns true if the grace-period kthread needs to be awakened.
  */
-static void __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
+static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp,
+			      struct rcu_data *rdp)
 {
+	bool ret;
+
 	/* Handle the ends of any preceding grace periods first. */
 	if (rdp->completed == rnp->completed) {
 
 		/* No grace period end, so just accelerate recent callbacks. */
-		rcu_accelerate_cbs(rsp, rnp, rdp);
+		ret = rcu_accelerate_cbs(rsp, rnp, rdp);
 
 	} else {
 
 		/* Advance callbacks. */
-		rcu_advance_cbs(rsp, rnp, rdp);
+		ret = rcu_advance_cbs(rsp, rnp, rdp);
 
 		/* Remember that we saw this grace-period completion. */
 		rdp->completed = rnp->completed;
@@ -1372,11 +1473,13 @@ static void __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, struc
 		rdp->qs_pending = !!(rnp->qsmask & rdp->grpmask);
 		zero_cpu_stall_ticks(rdp);
 	}
+	return ret;
 }
 
 static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
 {
 	unsigned long flags;
+	bool needwake;
 	struct rcu_node *rnp;
 
 	local_irq_save(flags);
@@ -1388,8 +1491,10 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
 		return;
 	}
 	smp_mb__after_unlock_lock();
-	__note_gp_changes(rsp, rnp, rdp);
+	needwake = __note_gp_changes(rsp, rnp, rdp);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	if (needwake)
+		rcu_gp_kthread_wake(rsp);
 }
 
 /*
@@ -1403,12 +1508,12 @@ static int rcu_gp_init(struct rcu_state *rsp)
 	rcu_bind_gp_kthread();
 	raw_spin_lock_irq(&rnp->lock);
 	smp_mb__after_unlock_lock();
-	if (rsp->gp_flags == 0) {
+	if (!ACCESS_ONCE(rsp->gp_flags)) {
 		/* Spurious wakeup, tell caller to go back to sleep.  */
 		raw_spin_unlock_irq(&rnp->lock);
 		return 0;
 	}
-	rsp->gp_flags = 0; /* Clear all flags: New grace period. */
+	ACCESS_ONCE(rsp->gp_flags) = 0; /* Clear all flags: New grace period. */
 
 	if (WARN_ON_ONCE(rcu_gp_in_progress(rsp))) {
 		/*
@@ -1453,7 +1558,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
 		WARN_ON_ONCE(rnp->completed != rsp->completed);
 		ACCESS_ONCE(rnp->completed) = rsp->completed;
 		if (rnp == rdp->mynode)
-			__note_gp_changes(rsp, rnp, rdp);
+			(void)__note_gp_changes(rsp, rnp, rdp);
 		rcu_preempt_boost_start_gp(rnp);
 		trace_rcu_grace_period_init(rsp->name, rnp->gpnum,
 					    rnp->level, rnp->grplo,
@@ -1501,7 +1606,7 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
 	if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
 		raw_spin_lock_irq(&rnp->lock);
 		smp_mb__after_unlock_lock();
-		rsp->gp_flags &= ~RCU_GP_FLAG_FQS;
+		ACCESS_ONCE(rsp->gp_flags) &= ~RCU_GP_FLAG_FQS;
 		raw_spin_unlock_irq(&rnp->lock);
 	}
 	return fqs_state;
@@ -1513,6 +1618,7 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
 static void rcu_gp_cleanup(struct rcu_state *rsp)
 {
 	unsigned long gp_duration;
+	bool needgp = false;
 	int nocb = 0;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp = rcu_get_root(rsp);
@@ -1548,7 +1654,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 		ACCESS_ONCE(rnp->completed) = rsp->gpnum;
 		rdp = this_cpu_ptr(rsp->rda);
 		if (rnp == rdp->mynode)
-			__note_gp_changes(rsp, rnp, rdp);
+			needgp = __note_gp_changes(rsp, rnp, rdp) || needgp;
 		/* smp_mb() provided by prior unlock-lock pair. */
 		nocb += rcu_future_gp_cleanup(rsp, rnp);
 		raw_spin_unlock_irq(&rnp->lock);
@@ -1564,9 +1670,10 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	trace_rcu_grace_period(rsp->name, rsp->completed, TPS("end"));
 	rsp->fqs_state = RCU_GP_IDLE;
 	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 = RCU_GP_FLAG_INIT;
+	/* Advance CBs to reduce false positives below. */
+	needgp = rcu_advance_cbs(rsp, rnp, rdp) || needgp;
+	if (needgp || cpu_needs_another_gp(rsp, rdp)) {
+		ACCESS_ONCE(rsp->gp_flags) = RCU_GP_FLAG_INIT;
 		trace_rcu_grace_period(rsp->name,
 				       ACCESS_ONCE(rsp->gpnum),
 				       TPS("newreq"));
@@ -1593,6 +1700,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
 			trace_rcu_grace_period(rsp->name,
 					       ACCESS_ONCE(rsp->gpnum),
 					       TPS("reqwait"));
+			rsp->gp_state = RCU_GP_WAIT_GPS;
 			wait_event_interruptible(rsp->gp_wq,
 						 ACCESS_ONCE(rsp->gp_flags) &
 						 RCU_GP_FLAG_INIT);
@@ -1620,6 +1728,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
 			trace_rcu_grace_period(rsp->name,
 					       ACCESS_ONCE(rsp->gpnum),
 					       TPS("fqswait"));
+			rsp->gp_state = RCU_GP_WAIT_FQS;
 			ret = wait_event_interruptible_timeout(rsp->gp_wq,
 					((gf = ACCESS_ONCE(rsp->gp_flags)) &
 					 RCU_GP_FLAG_FQS) ||
@@ -1665,14 +1774,6 @@ static int __noreturn rcu_gp_kthread(void *arg)
 	}
 }
 
-static void rsp_wakeup(struct irq_work *work)
-{
-	struct rcu_state *rsp = container_of(work, struct rcu_state, wakeup_work);
-
-	/* Wake up rcu_gp_kthread() to start the grace period. */
-	wake_up(&rsp->gp_wq);
-}
-
 /*
  * Start a new RCU grace period if warranted, re-initializing the hierarchy
  * in preparation for detecting the next grace period.  The caller must hold
@@ -1681,8 +1782,10 @@ static void rsp_wakeup(struct irq_work *work)
  * Note that it is legal for a dying CPU (which is marked as offline) to
  * invoke this function.  This can happen when the dying CPU reports its
  * quiescent state.
+ *
+ * Returns true if the grace-period kthread must be awakened.
  */
-static void
+static bool
 rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
 		      struct rcu_data *rdp)
 {
@@ -1693,20 +1796,18 @@ rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
 		 * or a grace period is already in progress.
 		 * Either way, don't start a new grace period.
 		 */
-		return;
+		return false;
 	}
-	rsp->gp_flags = RCU_GP_FLAG_INIT;
+	ACCESS_ONCE(rsp->gp_flags) = RCU_GP_FLAG_INIT;
 	trace_rcu_grace_period(rsp->name, ACCESS_ONCE(rsp->gpnum),
 			       TPS("newreq"));
 
 	/*
 	 * We can't do wakeups while holding the rnp->lock, as that
 	 * could cause possible deadlocks with the rq->lock. Defer
-	 * the wakeup to interrupt context.  And don't bother waking
-	 * up the running kthread.
+	 * the wakeup to our caller.
 	 */
-	if (current != rsp->gp_kthread)
-		irq_work_queue(&rsp->wakeup_work);
+	return true;
 }
 
 /*
@@ -1715,12 +1816,14 @@ rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
  * is invoked indirectly from rcu_advance_cbs(), which would result in
  * endless recursion -- or would do so if it wasn't for the self-deadlock
  * that is encountered beforehand.
+ *
+ * Returns true if the grace-period kthread needs to be awakened.
  */
-static void
-rcu_start_gp(struct rcu_state *rsp)
+static bool rcu_start_gp(struct rcu_state *rsp)
 {
 	struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
 	struct rcu_node *rnp = rcu_get_root(rsp);
+	bool ret = false;
 
 	/*
 	 * If there is no grace period in progress right now, any
@@ -1730,8 +1833,9 @@ rcu_start_gp(struct rcu_state *rsp)
 	 * resulting in pointless grace periods.  So, advance callbacks
 	 * then start the grace period!
 	 */
-	rcu_advance_cbs(rsp, rnp, rdp);
-	rcu_start_gp_advanced(rsp, rnp, rdp);
+	ret = rcu_advance_cbs(rsp, rnp, rdp) || ret;
+	ret = rcu_start_gp_advanced(rsp, rnp, rdp) || ret;
+	return ret;
 }
 
 /*
@@ -1820,6 +1924,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
 {
 	unsigned long flags;
 	unsigned long mask;
+	bool needwake;
 	struct rcu_node *rnp;
 
 	rnp = rdp->mynode;
@@ -1848,9 +1953,11 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
 		 * This GP can't end until cpu checks in, so all of our
 		 * callbacks can be processed during the next GP.
 		 */
-		rcu_accelerate_cbs(rsp, rnp, rdp);
+		needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
 
 		rcu_report_qs_rnp(mask, rsp, rnp, flags); /* rlses rnp->lock */
+		if (needwake)
+			rcu_gp_kthread_wake(rsp);
 	}
 }
 
@@ -1951,7 +2058,7 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp,
 static void rcu_adopt_orphan_cbs(struct rcu_state *rsp, unsigned long flags)
 {
 	int i;
-	struct rcu_data *rdp = __this_cpu_ptr(rsp->rda);
+	struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
 
 	/* No-CBs CPUs are handled specially. */
 	if (rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags))
@@ -2320,7 +2427,7 @@ static void force_quiescent_state(struct rcu_state *rsp)
 		raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
 		return;  /* Someone beat us to it. */
 	}
-	rsp->gp_flags |= RCU_GP_FLAG_FQS;
+	ACCESS_ONCE(rsp->gp_flags) |= RCU_GP_FLAG_FQS;
 	raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
 	wake_up(&rsp->gp_wq);  /* Memory barrier implied by wake_up() path. */
 }
@@ -2334,7 +2441,8 @@ static void
 __rcu_process_callbacks(struct rcu_state *rsp)
 {
 	unsigned long flags;
-	struct rcu_data *rdp = __this_cpu_ptr(rsp->rda);
+	bool needwake;
+	struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
 
 	WARN_ON_ONCE(rdp->beenonline == 0);
 
@@ -2345,8 +2453,10 @@ __rcu_process_callbacks(struct rcu_state *rsp)
 	local_irq_save(flags);
 	if (cpu_needs_another_gp(rsp, rdp)) {
 		raw_spin_lock(&rcu_get_root(rsp)->lock); /* irqs disabled. */
-		rcu_start_gp(rsp);
+		needwake = rcu_start_gp(rsp);
 		raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags);
+		if (needwake)
+			rcu_gp_kthread_wake(rsp);
 	} else {
 		local_irq_restore(flags);
 	}
@@ -2404,6 +2514,8 @@ static void invoke_rcu_core(void)
 static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
 			    struct rcu_head *head, unsigned long flags)
 {
+	bool needwake;
+
 	/*
 	 * If called from an extended quiescent state, invoke the RCU
 	 * core in order to force a re-evaluation of RCU's idleness.
@@ -2433,8 +2545,10 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
 
 			raw_spin_lock(&rnp_root->lock);
 			smp_mb__after_unlock_lock();
-			rcu_start_gp(rsp);
+			needwake = rcu_start_gp(rsp);
 			raw_spin_unlock(&rnp_root->lock);
+			if (needwake)
+				rcu_gp_kthread_wake(rsp);
 		} else {
 			/* Give the grace period a kick. */
 			rdp->blimit = LONG_MAX;
@@ -2537,6 +2651,20 @@ void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
 EXPORT_SYMBOL_GPL(call_rcu_bh);
 
 /*
+ * Queue an RCU callback for lazy invocation after a grace period.
+ * This will likely be later named something like "call_rcu_lazy()",
+ * but this change will require some way of tagging the lazy RCU
+ * callbacks in the list of pending callbacks. Until then, this
+ * function may only be called from __kfree_rcu().
+ */
+void kfree_call_rcu(struct rcu_head *head,
+		    void (*func)(struct rcu_head *rcu))
+{
+	__call_rcu(head, func, rcu_state_p, -1, 1);
+}
+EXPORT_SYMBOL_GPL(kfree_call_rcu);
+
+/*
  * Because a context switch is a grace period for RCU-sched and RCU-bh,
  * any blocking grace-period wait automatically implies a grace period
  * if there is only one CPU online at any point time during execution
@@ -2659,7 +2787,7 @@ unsigned long get_state_synchronize_rcu(void)
 	 * time-consuming work between get_state_synchronize_rcu()
 	 * and cond_synchronize_rcu().
 	 */
-	return smp_load_acquire(&rcu_state->gpnum);
+	return smp_load_acquire(&rcu_state_p->gpnum);
 }
 EXPORT_SYMBOL_GPL(get_state_synchronize_rcu);
 
@@ -2685,7 +2813,7 @@ void cond_synchronize_rcu(unsigned long oldstate)
 	 * Ensure that this load happens before any RCU-destructive
 	 * actions the caller might carry out after we return.
 	 */
-	newstate = smp_load_acquire(&rcu_state->completed);
+	newstate = smp_load_acquire(&rcu_state_p->completed);
 	if (ULONG_CMP_GE(oldstate, newstate))
 		synchronize_rcu();
 }
@@ -2988,7 +3116,7 @@ static void rcu_barrier_callback(struct rcu_head *rhp)
 static void rcu_barrier_func(void *type)
 {
 	struct rcu_state *rsp = type;
-	struct rcu_data *rdp = __this_cpu_ptr(rsp->rda);
+	struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
 
 	_rcu_barrier_trace(rsp, "IRQ", -1, rsp->n_barrier_done);
 	atomic_inc(&rsp->barrier_cpu_count);
@@ -3160,7 +3288,7 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
  * that this CPU cannot possibly have any RCU callbacks in flight yet.
  */
 static void
-rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible)
+rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 {
 	unsigned long flags;
 	unsigned long mask;
@@ -3173,7 +3301,6 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible)
 	/* Set up local state, ensuring consistent view of global state. */
 	raw_spin_lock_irqsave(&rnp->lock, flags);
 	rdp->beenonline = 1;	 /* We have now been online. */
-	rdp->preemptible = preemptible;
 	rdp->qlen_last_fqs_check = 0;
 	rdp->n_force_qs_snap = rsp->n_force_qs;
 	rdp->blimit = blimit;
@@ -3217,8 +3344,7 @@ static void rcu_prepare_cpu(int cpu)
 	struct rcu_state *rsp;
 
 	for_each_rcu_flavor(rsp)
-		rcu_init_percpu_data(cpu, rsp,
-				     strcmp(rsp->name, "rcu_preempt") == 0);
+		rcu_init_percpu_data(cpu, rsp);
 }
 
 /*
@@ -3228,7 +3354,7 @@ static int rcu_cpu_notify(struct notifier_block *self,
 				    unsigned long action, void *hcpu)
 {
 	long cpu = (long)hcpu;
-	struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu);
+	struct rcu_data *rdp = per_cpu_ptr(rcu_state_p->rda, cpu);
 	struct rcu_node *rnp = rdp->mynode;
 	struct rcu_state *rsp;
 
@@ -3402,8 +3528,8 @@ static void __init rcu_init_one(struct rcu_state *rsp,
 			rnp->qsmaskinit = 0;
 			rnp->grplo = j * cpustride;
 			rnp->grphi = (j + 1) * cpustride - 1;
-			if (rnp->grphi >= NR_CPUS)
-				rnp->grphi = NR_CPUS - 1;
+			if (rnp->grphi >= nr_cpu_ids)
+				rnp->grphi = nr_cpu_ids - 1;
 			if (i == 0) {
 				rnp->grpnum = 0;
 				rnp->grpmask = 0;
@@ -3422,7 +3548,6 @@ static void __init rcu_init_one(struct rcu_state *rsp,
 
 	rsp->rda = rda;
 	init_waitqueue_head(&rsp->gp_wq);
-	init_irq_work(&rsp->wakeup_work, rsp_wakeup);
 	rnp = rsp->level[rcu_num_lvls - 1];
 	for_each_possible_cpu(i) {
 		while (i > rnp->grphi)
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 75dc3c39a02a..bf2c1e669691 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -252,7 +252,6 @@ struct rcu_data {
 	bool		passed_quiesce;	/* User-mode/idle loop etc. */
 	bool		qs_pending;	/* Core waits for quiesc state. */
 	bool		beenonline;	/* CPU online at least once. */
-	bool		preemptible;	/* Preemptible RCU? */
 	struct rcu_node *mynode;	/* This CPU's leaf of hierarchy */
 	unsigned long grpmask;		/* Mask to apply to leaf qsmask. */
 #ifdef CONFIG_RCU_CPU_STALL_INFO
@@ -406,7 +405,8 @@ struct rcu_state {
 	unsigned long completed;		/* # of last completed gp. */
 	struct task_struct *gp_kthread;		/* Task for grace periods. */
 	wait_queue_head_t gp_wq;		/* Where GP task waits. */
-	int gp_flags;				/* Commands for GP task. */
+	short gp_flags;				/* Commands for GP task. */
+	short gp_state;				/* GP kthread sleep state. */
 
 	/* End of fields guarded by root rcu_node's lock. */
 
@@ -462,13 +462,17 @@ struct rcu_state {
 	const char *name;			/* Name of structure. */
 	char abbr;				/* Abbreviated name. */
 	struct list_head flavors;		/* List of RCU flavors. */
-	struct irq_work wakeup_work;		/* Postponed wakeups */
 };
 
 /* Values for rcu_state structure's gp_flags field. */
 #define RCU_GP_FLAG_INIT 0x1	/* Need grace-period initialization. */
 #define RCU_GP_FLAG_FQS  0x2	/* Need grace-period quiescent-state forcing. */
 
+/* Values for rcu_state structure's gp_flags field. */
+#define RCU_GP_WAIT_INIT 0	/* Initial state. */
+#define RCU_GP_WAIT_GPS  1	/* Wait for grace-period start. */
+#define RCU_GP_WAIT_FQS  2	/* Wait for force-quiescent-state time. */
+
 extern struct list_head rcu_struct_flavors;
 
 /* Sequence through rcu_state structures for each RCU flavor. */
@@ -547,7 +551,6 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu);
 static void print_cpu_stall_info_end(void);
 static void zero_cpu_stall_ticks(struct rcu_data *rdp);
 static void increment_cpu_stall_ticks(void);
-static int rcu_nocb_needs_gp(struct rcu_state *rsp);
 static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq);
 static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp);
 static void rcu_init_one_nocb(struct rcu_node *rnp);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 962d1d589929..29977ae84e7e 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -116,7 +116,7 @@ static void __init rcu_bootup_announce_oddness(void)
 #ifdef CONFIG_TREE_PREEMPT_RCU
 
 RCU_STATE_INITIALIZER(rcu_preempt, 'p', call_rcu);
-static struct rcu_state *rcu_state = &rcu_preempt_state;
+static struct rcu_state *rcu_state_p = &rcu_preempt_state;
 
 static int rcu_preempted_readers_exp(struct rcu_node *rnp);
 
@@ -149,15 +149,6 @@ long rcu_batches_completed(void)
 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
@@ -688,20 +679,6 @@ void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
 }
 EXPORT_SYMBOL_GPL(call_rcu);
 
-/*
- * Queue an RCU callback for lazy invocation after a grace period.
- * This will likely be later named something like "call_rcu_lazy()",
- * but this change will require some way of tagging the lazy RCU
- * callbacks in the list of pending callbacks.  Until then, this
- * function may only be called from __kfree_rcu().
- */
-void kfree_call_rcu(struct rcu_head *head,
-		    void (*func)(struct rcu_head *rcu))
-{
-	__call_rcu(head, func, &rcu_preempt_state, -1, 1);
-}
-EXPORT_SYMBOL_GPL(kfree_call_rcu);
-
 /**
  * synchronize_rcu - wait until a grace period has elapsed.
  *
@@ -970,7 +947,7 @@ void exit_rcu(void)
 
 #else /* #ifdef CONFIG_TREE_PREEMPT_RCU */
 
-static struct rcu_state *rcu_state = &rcu_sched_state;
+static struct rcu_state *rcu_state_p = &rcu_sched_state;
 
 /*
  * Tell them what RCU they are running.
@@ -991,16 +968,6 @@ long rcu_batches_completed(void)
 EXPORT_SYMBOL_GPL(rcu_batches_completed);
 
 /*
- * Force a quiescent state for RCU, which, because there is no preemptible
- * RCU, becomes the same as rcu-sched.
- */
-void rcu_force_quiescent_state(void)
-{
-	rcu_sched_force_quiescent_state();
-}
-EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
-
-/*
  * Because preemptible RCU does not exist, we never have to check for
  * CPUs being in quiescent states.
  */
@@ -1080,22 +1047,6 @@ static void rcu_preempt_check_callbacks(int cpu)
 }
 
 /*
- * Queue an RCU callback for lazy invocation after a grace period.
- * This will likely be later named something like "call_rcu_lazy()",
- * but this change will require some way of tagging the lazy RCU
- * callbacks in the list of pending callbacks.  Until then, this
- * function may only be called from __kfree_rcu().
- *
- * Because there is no preemptible RCU, we use RCU-sched instead.
- */
-void kfree_call_rcu(struct rcu_head *head,
-		    void (*func)(struct rcu_head *rcu))
-{
-	__call_rcu(head, func, &rcu_sched_state, -1, 1);
-}
-EXPORT_SYMBOL_GPL(kfree_call_rcu);
-
-/*
  * Wait for an rcu-preempt grace period, but make it happen quickly.
  * But because preemptible RCU does not exist, map to rcu-sched.
  */
@@ -1517,11 +1468,11 @@ static int __init rcu_spawn_kthreads(void)
 	for_each_possible_cpu(cpu)
 		per_cpu(rcu_cpu_has_work, cpu) = 0;
 	BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec));
-	rnp = rcu_get_root(rcu_state);
-	(void)rcu_spawn_one_boost_kthread(rcu_state, rnp);
+	rnp = rcu_get_root(rcu_state_p);
+	(void)rcu_spawn_one_boost_kthread(rcu_state_p, rnp);
 	if (NUM_RCU_NODES > 1) {
-		rcu_for_each_leaf_node(rcu_state, rnp)
-			(void)rcu_spawn_one_boost_kthread(rcu_state, rnp);
+		rcu_for_each_leaf_node(rcu_state_p, rnp)
+			(void)rcu_spawn_one_boost_kthread(rcu_state_p, rnp);
 	}
 	return 0;
 }
@@ -1529,12 +1480,12 @@ early_initcall(rcu_spawn_kthreads);
 
 static void rcu_prepare_kthreads(int cpu)
 {
-	struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu);
+	struct rcu_data *rdp = per_cpu_ptr(rcu_state_p->rda, cpu);
 	struct rcu_node *rnp = rdp->mynode;
 
 	/* Fire up the incoming CPU's kthread and leaf rcu_node kthread. */
 	if (rcu_scheduler_fully_active)
-		(void)rcu_spawn_one_boost_kthread(rcu_state, rnp);
+		(void)rcu_spawn_one_boost_kthread(rcu_state_p, rnp);
 }
 
 #else /* #ifdef CONFIG_RCU_BOOST */
@@ -1744,6 +1695,7 @@ int rcu_needs_cpu(int cpu, unsigned long *dj)
 static void rcu_prepare_for_idle(int cpu)
 {
 #ifndef CONFIG_RCU_NOCB_CPU_ALL
+	bool needwake;
 	struct rcu_data *rdp;
 	struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
 	struct rcu_node *rnp;
@@ -1792,8 +1744,10 @@ static void rcu_prepare_for_idle(int cpu)
 		rnp = rdp->mynode;
 		raw_spin_lock(&rnp->lock); /* irqs already disabled. */
 		smp_mb__after_unlock_lock();
-		rcu_accelerate_cbs(rsp, rnp, rdp);
+		needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
 		raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
+		if (needwake)
+			rcu_gp_kthread_wake(rsp);
 	}
 #endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
 }
@@ -1855,7 +1809,7 @@ static void rcu_oom_notify_cpu(void *unused)
 	struct rcu_data *rdp;
 
 	for_each_rcu_flavor(rsp) {
-		rdp = __this_cpu_ptr(rsp->rda);
+		rdp = raw_cpu_ptr(rsp->rda);
 		if (rdp->qlen_lazy != 0) {
 			atomic_inc(&oom_callback_count);
 			rsp->call(&rdp->oom_head, rcu_oom_callback);
@@ -1997,7 +1951,7 @@ static void increment_cpu_stall_ticks(void)
 	struct rcu_state *rsp;
 
 	for_each_rcu_flavor(rsp)
-		__this_cpu_ptr(rsp->rda)->ticks_this_gp++;
+		raw_cpu_inc(rsp->rda->ticks_this_gp);
 }
 
 #else /* #ifdef CONFIG_RCU_CPU_STALL_INFO */
@@ -2068,19 +2022,6 @@ static int __init parse_rcu_nocb_poll(char *arg)
 early_param("rcu_nocb_poll", parse_rcu_nocb_poll);
 
 /*
- * Do any no-CBs CPUs need another grace period?
- *
- * Interrupts must be disabled.  If the caller does not hold the root
- * rnp_node structure's ->lock, the results are advisory only.
- */
-static int rcu_nocb_needs_gp(struct rcu_state *rsp)
-{
-	struct rcu_node *rnp = rcu_get_root(rsp);
-
-	return rnp->need_future_gp[(ACCESS_ONCE(rnp->completed) + 1) & 0x1];
-}
-
-/*
  * Wake up any no-CBs CPUs' kthreads that were waiting on the just-ended
  * grace period.
  */
@@ -2109,7 +2050,7 @@ static void rcu_init_one_nocb(struct rcu_node *rnp)
 }
 
 #ifndef CONFIG_RCU_NOCB_CPU_ALL
-/* Is the specified CPU a no-CPUs CPU? */
+/* Is the specified CPU a no-CBs CPU? */
 bool rcu_is_nocb_cpu(int cpu)
 {
 	if (have_rcu_nocb_mask)
@@ -2243,12 +2184,15 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
 	unsigned long c;
 	bool d;
 	unsigned long flags;
+	bool needwake;
 	struct rcu_node *rnp = rdp->mynode;
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
 	smp_mb__after_unlock_lock();
-	c = rcu_start_future_gp(rnp, rdp);
+	needwake = rcu_start_future_gp(rnp, rdp, &c);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	if (needwake)
+		rcu_gp_kthread_wake(rdp->rsp);
 
 	/*
 	 * Wait for the grace period.  Do so interruptibly to avoid messing
@@ -2402,11 +2346,6 @@ static bool init_nocb_callback_list(struct rcu_data *rdp)
 
 #else /* #ifdef CONFIG_RCU_NOCB_CPU */
 
-static int rcu_nocb_needs_gp(struct rcu_state *rsp)
-{
-	return 0;
-}
-
 static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
 {
 }
@@ -2657,20 +2596,6 @@ static bool is_sysidle_rcu_state(struct rcu_state *rsp)
 }
 
 /*
- * Bind the grace-period kthread for the sysidle flavor of RCU to the
- * timekeeping CPU.
- */
-static void rcu_bind_gp_kthread(void)
-{
-	int cpu = ACCESS_ONCE(tick_do_timer_cpu);
-
-	if (cpu < 0 || cpu >= nr_cpu_ids)
-		return;
-	if (raw_smp_processor_id() != cpu)
-		set_cpus_allowed_ptr(current, cpumask_of(cpu));
-}
-
-/*
  * Return a delay in jiffies based on the number of CPUs, rcu_node
  * leaf fanout, and jiffies tick rate.  The idea is to allow larger
  * systems more time to transition to full-idle state in order to
@@ -2734,7 +2659,8 @@ static void rcu_sysidle(unsigned long j)
 static void rcu_sysidle_cancel(void)
 {
 	smp_mb();
-	ACCESS_ONCE(full_sysidle_state) = RCU_SYSIDLE_NOT;
+	if (full_sysidle_state > RCU_SYSIDLE_SHORT)
+		ACCESS_ONCE(full_sysidle_state) = RCU_SYSIDLE_NOT;
 }
 
 /*
@@ -2880,10 +2806,6 @@ static bool is_sysidle_rcu_state(struct rcu_state *rsp)
 	return false;
 }
 
-static void rcu_bind_gp_kthread(void)
-{
-}
-
 static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle,
 				  unsigned long maxj)
 {
@@ -2914,3 +2836,19 @@ static bool rcu_nohz_full_cpu(struct rcu_state *rsp)
 #endif /* #ifdef CONFIG_NO_HZ_FULL */
 	return 0;
 }
+
+/*
+ * Bind the grace-period kthread for the sysidle flavor of RCU to the
+ * timekeeping CPU.
+ */
+static void rcu_bind_gp_kthread(void)
+{
+#ifdef CONFIG_NO_HZ_FULL
+	int cpu = ACCESS_ONCE(tick_do_timer_cpu);
+
+	if (cpu < 0 || cpu >= nr_cpu_ids)
+		return;
+	if (raw_smp_processor_id() != cpu)
+		set_cpus_allowed_ptr(current, cpumask_of(cpu));
+#endif /* #ifdef CONFIG_NO_HZ_FULL */
+}
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 4c0a9b0af469..a2aeb4df0f60 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -320,6 +320,18 @@ int rcu_jiffies_till_stall_check(void)
 	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;
@@ -338,3 +350,21 @@ static int __init check_cpu_stall_init(void)
 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();
+}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d9d8ece46a15..64f71f183aad 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4051,6 +4051,7 @@ static void __cond_resched(void)
 
 int __sched _cond_resched(void)
 {
+	rcu_cond_resched();
 	if (should_resched()) {
 		__cond_resched();
 		return 1;
@@ -4069,15 +4070,18 @@ EXPORT_SYMBOL(_cond_resched);
  */
 int __cond_resched_lock(spinlock_t *lock)
 {
+	bool need_rcu_resched = rcu_should_resched();
 	int resched = should_resched();
 	int ret = 0;
 
 	lockdep_assert_held(lock);
 
-	if (spin_needbreak(lock) || resched) {
+	if (spin_needbreak(lock) || resched || need_rcu_resched) {
 		spin_unlock(lock);
 		if (resched)
 			__cond_resched();
+		else if (unlikely(need_rcu_resched))
+			rcu_resched();
 		else
 			cpu_relax();
 		ret = 1;
@@ -4091,6 +4095,7 @@ int __sched __cond_resched_softirq(void)
 {
 	BUG_ON(!in_softirq());
 
+	rcu_cond_resched();  /* BH disabled OK, just recording QSes. */
 	if (should_resched()) {
 		local_bh_enable();
 		__cond_resched();
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 92f24f5e8d52..5918d227730f 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -232,7 +232,6 @@ asmlinkage __visible void __do_softirq(void)
 	bool in_hardirq;
 	__u32 pending;
 	int softirq_bit;
-	int cpu;
 
 	/*
 	 * Mask out PF_MEMALLOC s current task context is borrowed for the
@@ -247,7 +246,6 @@ asmlinkage __visible void __do_softirq(void)
 	__local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
 	in_hardirq = lockdep_softirq_start();
 
-	cpu = smp_processor_id();
 restart:
 	/* Reset the pending bitmask before enabling irqs */
 	set_softirq_pending(0);
@@ -276,11 +274,11 @@ restart:
 			       prev_count, preempt_count());
 			preempt_count_set(prev_count);
 		}
-		rcu_bh_qs(cpu);
 		h++;
 		pending >>= softirq_bit;
 	}
 
+	rcu_bh_qs(smp_processor_id());
 	local_irq_disable();
 
 	pending = local_softirq_pending();
diff --git a/kernel/torture.c b/kernel/torture.c
index acc9afc2f26e..40bb511cca48 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -335,13 +335,8 @@ static void torture_shuffle_tasks(void)
 	shuffle_idle_cpu = cpumask_next(shuffle_idle_cpu, shuffle_tmp_mask);
 	if (shuffle_idle_cpu >= nr_cpu_ids)
 		shuffle_idle_cpu = -1;
-	if (shuffle_idle_cpu != -1) {
+	else
 		cpumask_clear_cpu(shuffle_idle_cpu, shuffle_tmp_mask);
-		if (cpumask_empty(shuffle_tmp_mask)) {
-			put_online_cpus();
-			return;
-		}
-	}
 
 	mutex_lock(&shuffle_task_mutex);
 	list_for_each_entry(stp, &shuffle_task_list, st_l)
@@ -533,7 +528,11 @@ void stutter_wait(const char *title)
 	while (ACCESS_ONCE(stutter_pause_test) ||
 	       (torture_runnable && !ACCESS_ONCE(*torture_runnable))) {
 		if (stutter_pause_test)
-			schedule_timeout_interruptible(1);
+			if (ACCESS_ONCE(stutter_pause_test) == 1)
+				schedule_timeout_interruptible(1);
+			else
+				while (ACCESS_ONCE(stutter_pause_test))
+					cond_resched();
 		else
 			schedule_timeout_interruptible(round_jiffies_relative(HZ));
 		torture_shutdown_absorb(title);
@@ -550,7 +549,11 @@ static int torture_stutter(void *arg)
 	VERBOSE_TOROUT_STRING("torture_stutter task started");
 	do {
 		if (!torture_must_stop()) {
-			schedule_timeout_interruptible(stutter);
+			if (stutter > 1) {
+				schedule_timeout_interruptible(stutter - 1);
+				ACCESS_ONCE(stutter_pause_test) = 2;
+			}
+			schedule_timeout_interruptible(1);
 			ACCESS_ONCE(stutter_pause_test) = 1;
 		}
 		if (!torture_must_stop())
@@ -596,21 +599,27 @@ static void torture_stutter_cleanup(void)
  * The runnable parameter points to a flag that controls whether or not
  * the test is currently runnable.  If there is no such flag, pass in NULL.
  */
-void __init torture_init_begin(char *ttype, bool v, int *runnable)
+bool torture_init_begin(char *ttype, bool v, int *runnable)
 {
 	mutex_lock(&fullstop_mutex);
+	if (torture_type != NULL) {
+		pr_alert("torture_init_begin: refusing %s init: %s running",
+			 ttype, torture_type);
+		mutex_unlock(&fullstop_mutex);
+		return false;
+	}
 	torture_type = ttype;
 	verbose = v;
 	torture_runnable = runnable;
 	fullstop = FULLSTOP_DONTSTOP;
-
+	return true;
 }
 EXPORT_SYMBOL_GPL(torture_init_begin);
 
 /*
  * Tell the torture module that initialization is complete.
  */
-void __init torture_init_end(void)
+void torture_init_end(void)
 {
 	mutex_unlock(&fullstop_mutex);
 	register_reboot_notifier(&torture_shutdown_nb);
@@ -642,6 +651,9 @@ bool torture_cleanup(void)
 	torture_shuffle_cleanup();
 	torture_stutter_cleanup();
 	torture_onoff_cleanup();
+	mutex_lock(&fullstop_mutex);
+	torture_type = NULL;
+	mutex_unlock(&fullstop_mutex);
 	return false;
 }
 EXPORT_SYMBOL_GPL(torture_cleanup);
@@ -674,8 +686,10 @@ EXPORT_SYMBOL_GPL(torture_must_stop_irq);
  */
 void torture_kthread_stopping(char *title)
 {
-	if (verbose)
-		VERBOSE_TOROUT_STRING(title);
+	char buf[128];
+
+	snprintf(buf, sizeof(buf), "Stopping %s", title);
+	VERBOSE_TOROUT_STRING(buf);
 	while (!kthread_should_stop()) {
 		torture_shutdown_absorb(title);
 		schedule_timeout_uninterruptible(1);