Merge tag 'rcu.2022.03.13a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu

Pull RCU updates from Paul McKenney:

 - Fix idle detection (Neeraj Upadhyay) and missing access marking
   detected by KCSAN.

 - Reduce coupling between rcu_barrier() and CPU-hotplug operations, so
   that rcu_barrier() no longer needs to do cpus_read_lock(). This may
   also someday allow system boot to bring CPUs online concurrently.

 - Enable more aggressive movement to per-CPU queueing when reacting to
   excessive lock contention due to workloads placing heavy update-side
   stress on RCU tasks.

 - Improvements to RCU priority boosting, including changes from Neeraj
   Upadhyay, Zqiang, and Alison Chaiken.

 - Various fixes improving test robustness and debug information.

 - Add tests for SRCU size transitions, further compress torture.sh
   build products, and improve debug output.

 - Miscellaneous fixes.

* tag 'rcu.2022.03.13a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu: (49 commits)
  rcu: Replace cpumask_weight with cpumask_empty where appropriate
  rcu: Remove __read_mostly annotations from rcu_scheduler_active externs
  rcu: Uninline multi-use function: finish_rcuwait()
  rcu: Mark writes to the rcu_segcblist structure's ->flags field
  kasan: Record work creation stack trace with interrupts enabled
  rcu: Inline __call_rcu() into call_rcu()
  rcu: Add mutex for rcu boost kthread spawning and affinity setting
  rcu: Fix description of kvfree_rcu()
  MAINTAINERS:  Add Frederic and Neeraj to their RCU files
  rcutorture: Provide non-power-of-two Tasks RCU scenarios
  rcutorture: Test SRCU size transitions
  torture: Make torture.sh help message match reality
  rcu-tasks: Set ->percpu_enqueue_shift to zero upon contention
  rcu-tasks: Use order_base_2() instead of ilog2()
  rcu: Create and use an rcu_rdp_cpu_online()
  rcu: Make rcu_barrier() no longer block CPU-hotplug operations
  rcu: Rework rcu_barrier() and callback-migration logic
  rcu: Refactor rcu_barrier() empty-list handling
  rcu: Kill rnp->ofl_seq and use only rcu_state.ofl_lock for exclusion
  torture: Change KVM environment variable to RCUTORTURE
  ...

Documentation/admin-guide/kernel-parameters.txt

@@ -4504,6 +4504,8 @@
 			(the least-favored priority).  Otherwise, when
 			RCU_BOOST is not set, valid values are 0-99 and
 			the default is zero (non-realtime operation).
+			When RCU_NOCB_CPU is set, also adjust the
+			priority of NOCB callback kthreads.
 
 	rcutree.rcu_nocb_gp_stride= [KNL]
 			Set the number of NOCB callback kthreads in

MAINTAINERS

@@ -16324,6 +16324,8 @@ F:	tools/testing/selftests/resctrl/
 
 READ-COPY UPDATE (RCU)
 M:	"Paul E. McKenney" <paulmck@kernel.org>
+M:	Frederic Weisbecker <frederic@kernel.org> (kernel/rcu/tree_nocb.h)
+M:	Neeraj Upadhyay <quic_neeraju@quicinc.com> (kernel/rcu/tasks.h)
 M:	Josh Triplett <josh@joshtriplett.org>
 R:	Steven Rostedt <rostedt@goodmis.org>
 R:	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>

include/linux/rcupdate.h

@@ -84,7 +84,7 @@ static inline int rcu_preempt_depth(void)
 
 /* Internal to kernel */
 void rcu_init(void);
-extern int rcu_scheduler_active __read_mostly;
+extern int rcu_scheduler_active;
 void rcu_sched_clock_irq(int user);
 void rcu_report_dead(unsigned int cpu);
 void rcutree_migrate_callbacks(int cpu);
@@ -924,7 +924,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
  *
  *     kvfree_rcu(ptr);
  *
- * where @ptr is a pointer to kvfree().
+ * where @ptr is the pointer to be freed by kvfree().
  *
  * Please note, head-less way of freeing is permitted to
  * use from a context that has to follow might_sleep()

include/linux/rcutree.h

@@ -62,7 +62,7 @@ static inline void rcu_irq_exit_check_preempt(void) { }
 void exit_rcu(void);
 
 void rcu_scheduler_starting(void);
-extern int rcu_scheduler_active __read_mostly;
+extern int rcu_scheduler_active;
 void rcu_end_inkernel_boot(void);
 bool rcu_inkernel_boot_has_ended(void);
 bool rcu_is_watching(void);

include/linux/rcuwait.h

@@ -47,11 +47,7 @@ static inline void prepare_to_rcuwait(struct rcuwait *w)
 	rcu_assign_pointer(w->task, current);
 }
 
-static inline void finish_rcuwait(struct rcuwait *w)
-{
-        rcu_assign_pointer(w->task, NULL);
-	__set_current_state(TASK_RUNNING);
-}
+extern void finish_rcuwait(struct rcuwait *w);
 
 #define rcuwait_wait_event(w, condition, state)				\
 ({									\

include/trace/events/rcu.h

@@ -794,16 +794,15 @@ TRACE_EVENT_RCU(rcu_torture_read,
  * Tracepoint for rcu_barrier() execution.  The string "s" describes
  * the rcu_barrier phase:
  *	"Begin": rcu_barrier() started.
+ *	"CB": An rcu_barrier_callback() invoked a callback, not the last.
  *	"EarlyExit": rcu_barrier() piggybacked, thus early exit.
  *	"Inc1": rcu_barrier() piggyback check counter incremented.
- *	"OfflineNoCBQ": rcu_barrier() found offline no-CBs CPU with callbacks.
- *	"OnlineQ": rcu_barrier() found online CPU with callbacks.
- *	"OnlineNQ": rcu_barrier() found online CPU, no callbacks.
+ *	"Inc2": rcu_barrier() piggyback check counter incremented.
  *	"IRQ": An rcu_barrier_callback() callback posted on remote CPU.
  *	"IRQNQ": An rcu_barrier_callback() callback found no callbacks.
- *	"CB": An rcu_barrier_callback() invoked a callback, not the last.
  *	"LastCB": An rcu_barrier_callback() invoked the last callback.
- *	"Inc2": rcu_barrier() piggyback check counter incremented.
+ *	"NQ": rcu_barrier() found a CPU with no callbacks.
+ *	"OnlineQ": rcu_barrier() found online CPU with callbacks.
  * The "cpu" argument is the CPU or -1 if meaningless, the "cnt" argument
  * is the count of remaining callbacks, and "done" is the piggybacking count.
  */

kernel/rcu/rcu_segcblist.h

@@ -56,13 +56,13 @@ static inline long rcu_segcblist_n_cbs(struct rcu_segcblist *rsclp)
 static inline void rcu_segcblist_set_flags(struct rcu_segcblist *rsclp,
 					   int flags)
 {
-	rsclp->flags |= flags;
+	WRITE_ONCE(rsclp->flags, rsclp->flags | flags);
 }
 
 static inline void rcu_segcblist_clear_flags(struct rcu_segcblist *rsclp,
 					     int flags)
 {
-	rsclp->flags &= ~flags;
+	WRITE_ONCE(rsclp->flags, rsclp->flags & ~flags);
 }
 
 static inline bool rcu_segcblist_test_flags(struct rcu_segcblist *rsclp,

kernel/rcu/rcutorture.c

@@ -284,7 +284,7 @@ static atomic_t barrier_cbs_invoked;	/* Barrier callbacks invoked. */
 static wait_queue_head_t *barrier_cbs_wq; /* Coordinate barrier testing. */
 static DECLARE_WAIT_QUEUE_HEAD(barrier_wq);
 
-static bool rcu_fwd_cb_nodelay;		/* Short rcu_torture_delay() delays. */
+static atomic_t rcu_fwd_cb_nodelay;	/* Short rcu_torture_delay() delays. */
 
 /*
  * Allocate an element from the rcu_tortures pool.
@@ -387,7 +387,7 @@ rcu_read_delay(struct torture_random_state *rrsp, struct rt_read_seg *rtrsp)
 	 * period, and we want a long delay occasionally to trigger
 	 * force_quiescent_state. */
 
-	if (!READ_ONCE(rcu_fwd_cb_nodelay) &&
+	if (!atomic_read(&rcu_fwd_cb_nodelay) &&
 	    !(torture_random(rrsp) % (nrealreaders * 2000 * longdelay_ms))) {
 		started = cur_ops->get_gp_seq();
 		ts = rcu_trace_clock_local();
@@ -674,6 +674,7 @@ static struct rcu_torture_ops srcu_ops = {
 	.call		= srcu_torture_call,
 	.cb_barrier	= srcu_torture_barrier,
 	.stats		= srcu_torture_stats,
+	.cbflood_max	= 50000,
 	.irq_capable	= 1,
 	.no_pi_lock	= IS_ENABLED(CONFIG_TINY_SRCU),
 	.name		= "srcu"
@@ -708,6 +709,7 @@ static struct rcu_torture_ops srcud_ops = {
 	.call		= srcu_torture_call,
 	.cb_barrier	= srcu_torture_barrier,
 	.stats		= srcu_torture_stats,
+	.cbflood_max	= 50000,
 	.irq_capable	= 1,
 	.no_pi_lock	= IS_ENABLED(CONFIG_TINY_SRCU),
 	.name		= "srcud"
@@ -997,7 +999,7 @@ static int rcu_torture_boost(void *arg)
 			goto checkwait;
 
 		/* Wait for the next test interval. */
-		oldstarttime = boost_starttime;
+		oldstarttime = READ_ONCE(boost_starttime);
 		while (time_before(jiffies, oldstarttime)) {
 			schedule_timeout_interruptible(oldstarttime - jiffies);
 			if (stutter_wait("rcu_torture_boost"))
@@ -1041,10 +1043,11 @@ static int rcu_torture_boost(void *arg)
 		 * interval.  Besides, we are running at RT priority,
 		 * so delays should be relatively rare.
 		 */
-		while (oldstarttime == boost_starttime && !kthread_should_stop()) {
+		while (oldstarttime == READ_ONCE(boost_starttime) && !kthread_should_stop()) {
 			if (mutex_trylock(&boost_mutex)) {
 				if (oldstarttime == boost_starttime) {
-					boost_starttime = jiffies + test_boost_interval * HZ;
+					WRITE_ONCE(boost_starttime,
+						   jiffies + test_boost_interval * HZ);
 					n_rcu_torture_boosts++;
 				}
 				mutex_unlock(&boost_mutex);
@@ -1276,7 +1279,7 @@ rcu_torture_writer(void *arg)
 		boot_ended = rcu_inkernel_boot_has_ended();
 		stutter_waited = stutter_wait("rcu_torture_writer");
 		if (stutter_waited &&
-		    !READ_ONCE(rcu_fwd_cb_nodelay) &&
+		    !atomic_read(&rcu_fwd_cb_nodelay) &&
 		    !cur_ops->slow_gps &&
 		    !torture_must_stop() &&
 		    boot_ended)
@@ -2180,7 +2183,6 @@ static void rcu_torture_fwd_cb_hist(struct rcu_fwd *rfp)
 	for (i = ARRAY_SIZE(rfp->n_launders_hist) - 1; i > 0; i--)
 		if (rfp->n_launders_hist[i].n_launders > 0)
 			break;
-	mutex_lock(&rcu_fwd_mutex); // Serialize histograms.
 	pr_alert("%s: Callback-invocation histogram %d (duration %lu jiffies):",
 		 __func__, rfp->rcu_fwd_id, jiffies - rfp->rcu_fwd_startat);
 	gps_old = rfp->rcu_launder_gp_seq_start;
@@ -2193,7 +2195,6 @@ static void rcu_torture_fwd_cb_hist(struct rcu_fwd *rfp)
 		gps_old = gps;
 	}
 	pr_cont("\n");
-	mutex_unlock(&rcu_fwd_mutex);
 }
 
 /* Callback function for continuous-flood RCU callbacks. */
@@ -2281,6 +2282,7 @@ static void rcu_torture_fwd_prog_nr(struct rcu_fwd *rfp,
 	unsigned long stopat;
 	static DEFINE_TORTURE_RANDOM(trs);
 
+	pr_alert("%s: Starting forward-progress test %d\n", __func__, rfp->rcu_fwd_id);
 	if (!cur_ops->sync)
 		return; // Cannot do need_resched() forward progress testing without ->sync.
 	if (cur_ops->call && cur_ops->cb_barrier) {
@@ -2289,7 +2291,7 @@ static void rcu_torture_fwd_prog_nr(struct rcu_fwd *rfp,
 	}
 
 	/* Tight loop containing cond_resched(). */
-	WRITE_ONCE(rcu_fwd_cb_nodelay, true);
+	atomic_inc(&rcu_fwd_cb_nodelay);
 	cur_ops->sync(); /* Later readers see above write. */
 	if  (selfpropcb) {
 		WRITE_ONCE(fcs.stop, 0);
@@ -2325,6 +2327,7 @@ static void rcu_torture_fwd_prog_nr(struct rcu_fwd *rfp,
 	if (selfpropcb) {
 		WRITE_ONCE(fcs.stop, 1);
 		cur_ops->sync(); /* Wait for running CB to complete. */
+		pr_alert("%s: Waiting for CBs: %pS() %d\n", __func__, cur_ops->cb_barrier, rfp->rcu_fwd_id);
 		cur_ops->cb_barrier(); /* Wait for queued callbacks. */
 	}
 
@@ -2333,7 +2336,7 @@ static void rcu_torture_fwd_prog_nr(struct rcu_fwd *rfp,
 		destroy_rcu_head_on_stack(&fcs.rh);
 	}
 	schedule_timeout_uninterruptible(HZ / 10); /* Let kthreads recover. */
-	WRITE_ONCE(rcu_fwd_cb_nodelay, false);
+	atomic_dec(&rcu_fwd_cb_nodelay);
 }
 
 /* Carry out call_rcu() forward-progress testing. */
@@ -2353,13 +2356,14 @@ static void rcu_torture_fwd_prog_cr(struct rcu_fwd *rfp)
 	unsigned long stopat;
 	unsigned long stoppedat;
 
+	pr_alert("%s: Starting forward-progress test %d\n", __func__, rfp->rcu_fwd_id);
 	if (READ_ONCE(rcu_fwd_emergency_stop))
 		return; /* Get out of the way quickly, no GP wait! */
 	if (!cur_ops->call)
 		return; /* Can't do call_rcu() fwd prog without ->call. */
 
 	/* Loop continuously posting RCU callbacks. */
-	WRITE_ONCE(rcu_fwd_cb_nodelay, true);
+	atomic_inc(&rcu_fwd_cb_nodelay);
 	cur_ops->sync(); /* Later readers see above write. */
 	WRITE_ONCE(rfp->rcu_fwd_startat, jiffies);
 	stopat = rfp->rcu_fwd_startat + MAX_FWD_CB_JIFFIES;
@@ -2414,6 +2418,7 @@ static void rcu_torture_fwd_prog_cr(struct rcu_fwd *rfp)
 	n_launders_cb_snap = READ_ONCE(rfp->n_launders_cb);
 	cver = READ_ONCE(rcu_torture_current_version) - cver;
 	gps = rcutorture_seq_diff(cur_ops->get_gp_seq(), gps);
+	pr_alert("%s: Waiting for CBs: %pS() %d\n", __func__, cur_ops->cb_barrier, rfp->rcu_fwd_id);
 	cur_ops->cb_barrier(); /* Wait for callbacks to be invoked. */
 	(void)rcu_torture_fwd_prog_cbfree(rfp);
 
@@ -2427,11 +2432,13 @@ static void rcu_torture_fwd_prog_cr(struct rcu_fwd *rfp)
 			 n_launders, n_launders_sa,
 			 n_max_gps, n_max_cbs, cver, gps);
 		atomic_long_add(n_max_cbs, &rcu_fwd_max_cbs);
+		mutex_lock(&rcu_fwd_mutex); // Serialize histograms.
 		rcu_torture_fwd_cb_hist(rfp);
+		mutex_unlock(&rcu_fwd_mutex);
 	}
 	schedule_timeout_uninterruptible(HZ); /* Let CBs drain. */
 	tick_dep_clear_task(current, TICK_DEP_BIT_RCU);
-	WRITE_ONCE(rcu_fwd_cb_nodelay, false);
+	atomic_dec(&rcu_fwd_cb_nodelay);
 }
 
 
@@ -2511,7 +2518,7 @@ static int rcu_torture_fwd_prog(void *args)
 			firsttime = false;
 			WRITE_ONCE(rcu_fwd_seq, rcu_fwd_seq + 1);
 		} else {
-			while (READ_ONCE(rcu_fwd_seq) == oldseq)
+			while (READ_ONCE(rcu_fwd_seq) == oldseq && !torture_must_stop())
 				schedule_timeout_interruptible(1);
 			oldseq = READ_ONCE(rcu_fwd_seq);
 		}
@@ -2905,8 +2912,10 @@ rcu_torture_cleanup(void)
 	int i;
 
 	if (torture_cleanup_begin()) {
-		if (cur_ops->cb_barrier != NULL)
+		if (cur_ops->cb_barrier != NULL) {
+			pr_info("%s: Invoking %pS().\n", __func__, cur_ops->cb_barrier);
 			cur_ops->cb_barrier();
+		}
 		return;
 	}
 	if (!cur_ops) {
@@ -2961,8 +2970,10 @@ rcu_torture_cleanup(void)
 	 * Wait for all RCU callbacks to fire, then do torture-type-specific
 	 * cleanup operations.
 	 */
-	if (cur_ops->cb_barrier != NULL)
+	if (cur_ops->cb_barrier != NULL) {
+		pr_info("%s: Invoking %pS().\n", __func__, cur_ops->cb_barrier);
 		cur_ops->cb_barrier();
+	}
 	if (cur_ops->cleanup != NULL)
 		cur_ops->cleanup();
 

kernel/rcu/tasks.h

@@ -123,7 +123,7 @@ static struct rcu_tasks rt_name =							\
 	.call_func = call,								\
 	.rtpcpu = &rt_name ## __percpu,							\
 	.name = n,									\
-	.percpu_enqueue_shift = ilog2(CONFIG_NR_CPUS) + 1,				\
+	.percpu_enqueue_shift = order_base_2(CONFIG_NR_CPUS),				\
 	.percpu_enqueue_lim = 1,							\
 	.percpu_dequeue_lim = 1,							\
 	.barrier_q_mutex = __MUTEX_INITIALIZER(rt_name.barrier_q_mutex),		\
@@ -302,7 +302,7 @@ static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func,
 	if (unlikely(needadjust)) {
 		raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags);
 		if (rtp->percpu_enqueue_lim != nr_cpu_ids) {
-			WRITE_ONCE(rtp->percpu_enqueue_shift, ilog2(nr_cpu_ids) + 1);
+			WRITE_ONCE(rtp->percpu_enqueue_shift, 0);
 			WRITE_ONCE(rtp->percpu_dequeue_lim, nr_cpu_ids);
 			smp_store_release(&rtp->percpu_enqueue_lim, nr_cpu_ids);
 			pr_info("Switching %s to per-CPU callback queuing.\n", rtp->name);
@@ -417,7 +417,7 @@ static int rcu_tasks_need_gpcb(struct rcu_tasks *rtp)
 	if (rcu_task_cb_adjust && ncbs <= rcu_task_collapse_lim) {
 		raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags);
 		if (rtp->percpu_enqueue_lim > 1) {
-			WRITE_ONCE(rtp->percpu_enqueue_shift, ilog2(nr_cpu_ids) + 1);
+			WRITE_ONCE(rtp->percpu_enqueue_shift, order_base_2(nr_cpu_ids));
 			smp_store_release(&rtp->percpu_enqueue_lim, 1);
 			rtp->percpu_dequeue_gpseq = get_state_synchronize_rcu();
 			pr_info("Starting switch %s to CPU-0 callback queuing.\n", rtp->name);

kernel/rcu/tree.h

@@ -56,8 +56,6 @@ struct rcu_node {
 				/*  Initialized from ->qsmaskinitnext at the */
 				/*  beginning of each grace period. */
 	unsigned long qsmaskinitnext;
-	unsigned long ofl_seq;	/* CPU-hotplug operation sequence count. */
-				/* Online CPUs for next grace period. */
 	unsigned long expmask;	/* CPUs or groups that need to check in */
 				/*  to allow the current expedited GP */
 				/*  to complete. */
@@ -110,6 +108,9 @@ struct rcu_node {
 				/*  side effect, not as a lock. */
 	unsigned long boost_time;
 				/* When to start boosting (jiffies). */
+	struct mutex boost_kthread_mutex;
+				/* Exclusion for thread spawning and affinity */
+				/*  manipulation. */
 	struct task_struct *boost_kthread_task;
 				/* kthread that takes care of priority */
 				/*  boosting for this rcu_node structure. */
@@ -190,6 +191,7 @@ struct rcu_data {
 	bool rcu_forced_tick_exp;	/*   ... provide QS to expedited GP. */
 
 	/* 4) rcu_barrier(), OOM callbacks, and expediting. */
+	unsigned long barrier_seq_snap;	/* Snap of rcu_state.barrier_sequence. */
 	struct rcu_head barrier_head;
 	int exp_dynticks_snap;		/* Double-check need for IPI. */
 
@@ -203,6 +205,8 @@ struct rcu_data {
 	int nocb_defer_wakeup;		/* Defer wakeup of nocb_kthread. */
 	struct timer_list nocb_timer;	/* Enforce finite deferral. */
 	unsigned long nocb_gp_adv_time;	/* Last call_rcu() CB adv (jiffies). */
+	struct mutex nocb_gp_kthread_mutex; /* Exclusion for nocb gp kthread */
+					    /* spawning */
 
 	/* The following fields are used by call_rcu, hence own cacheline. */
 	raw_spinlock_t nocb_bypass_lock ____cacheline_internodealigned_in_smp;
@@ -237,6 +241,7 @@ struct rcu_data {
 					/* rcuc per-CPU kthread or NULL. */
 	unsigned int rcu_cpu_kthread_status;
 	char rcu_cpu_has_work;
+	unsigned long rcuc_activity;
 
 	/* 7) Diagnostic data, including RCU CPU stall warnings. */
 	unsigned int softirq_snap;	/* Snapshot of softirq activity. */
@@ -302,9 +307,8 @@ struct rcu_state {
 
 	/* The following fields are guarded by the root rcu_node's lock. */
 
-	u8	boost ____cacheline_internodealigned_in_smp;
-						/* Subject to priority boost. */
-	unsigned long gp_seq;			/* Grace-period sequence #. */
+	unsigned long gp_seq ____cacheline_internodealigned_in_smp;
+						/* Grace-period sequence #. */
 	unsigned long gp_max;			/* Maximum GP duration in */
 						/*  jiffies. */
 	struct task_struct *gp_kthread;		/* Task for grace periods. */
@@ -323,6 +327,8 @@ struct rcu_state {
 						/*  rcu_barrier(). */
 	/* End of fields guarded by barrier_mutex. */
 
+	raw_spinlock_t barrier_lock;		/* Protects ->barrier_seq_snap. */
+
 	struct mutex exp_mutex;			/* Serialize expedited GP. */
 	struct mutex exp_wake_mutex;		/* Serialize wakeup. */
 	unsigned long expedited_sequence;	/* Take a ticket. */
@@ -355,7 +361,7 @@ struct rcu_state {
 	const char *name;			/* Name of structure. */
 	char abbr;				/* Abbreviated name. */
 
-	raw_spinlock_t ofl_lock ____cacheline_internodealigned_in_smp;
+	arch_spinlock_t ofl_lock ____cacheline_internodealigned_in_smp;
 						/* Synchronize offline with */
 						/*  GP pre-initialization. */
 };

kernel/rcu/tree_exp.h

@@ -502,7 +502,8 @@ static void synchronize_rcu_expedited_wait(void)
 		if (synchronize_rcu_expedited_wait_once(1))
 			return;
 		rcu_for_each_leaf_node(rnp) {
-			for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) {
+			mask = READ_ONCE(rnp->expmask);
+			for_each_leaf_node_cpu_mask(rnp, cpu, mask) {
 				rdp = per_cpu_ptr(&rcu_data, cpu);
 				if (rdp->rcu_forced_tick_exp)
 					continue;
@@ -656,7 +657,7 @@ static void rcu_exp_handler(void *unused)
 	 */
 	if (!depth) {
 		if (!(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK)) ||
-		    rcu_dynticks_curr_cpu_in_eqs()) {
+		    rcu_is_cpu_rrupt_from_idle()) {
 			rcu_report_exp_rdp(rdp);
 		} else {
 			WRITE_ONCE(rdp->cpu_no_qs.b.exp, true);

kernel/rcu/tree_nocb.h

@@ -1169,7 +1169,7 @@ void __init rcu_init_nohz(void)
 	struct rcu_data *rdp;
 
 #if defined(CONFIG_NO_HZ_FULL)
-	if (tick_nohz_full_running && cpumask_weight(tick_nohz_full_mask))
+	if (tick_nohz_full_running && !cpumask_empty(tick_nohz_full_mask))
 		need_rcu_nocb_mask = true;
 #endif /* #if defined(CONFIG_NO_HZ_FULL) */
 
@@ -1226,6 +1226,7 @@ static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
 	raw_spin_lock_init(&rdp->nocb_gp_lock);
 	timer_setup(&rdp->nocb_timer, do_nocb_deferred_wakeup_timer, 0);
 	rcu_cblist_init(&rdp->nocb_bypass);
+	mutex_init(&rdp->nocb_gp_kthread_mutex);
 }
 
 /*
@@ -1238,6 +1239,7 @@ static void rcu_spawn_cpu_nocb_kthread(int cpu)
 	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
 	struct rcu_data *rdp_gp;
 	struct task_struct *t;
+	struct sched_param sp;
 
 	if (!rcu_scheduler_fully_active || !rcu_nocb_is_setup)
 		return;
@@ -1247,20 +1249,30 @@ static void rcu_spawn_cpu_nocb_kthread(int cpu)
 		return;
 
 	/* If we didn't spawn the GP kthread first, reorganize! */
+	sp.sched_priority = kthread_prio;
 	rdp_gp = rdp->nocb_gp_rdp;
+	mutex_lock(&rdp_gp->nocb_gp_kthread_mutex);
 	if (!rdp_gp->nocb_gp_kthread) {
 		t = kthread_run(rcu_nocb_gp_kthread, rdp_gp,
 				"rcuog/%d", rdp_gp->cpu);
-		if (WARN_ONCE(IS_ERR(t), "%s: Could not start rcuo GP kthread, OOM is now expected behavior\n", __func__))
+		if (WARN_ONCE(IS_ERR(t), "%s: Could not start rcuo GP kthread, OOM is now expected behavior\n", __func__)) {
+			mutex_unlock(&rdp_gp->nocb_gp_kthread_mutex);
 			return;
+		}
 		WRITE_ONCE(rdp_gp->nocb_gp_kthread, t);
+		if (kthread_prio)
+			sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
 	}
+	mutex_unlock(&rdp_gp->nocb_gp_kthread_mutex);
 
 	/* Spawn the kthread for this CPU. */
 	t = kthread_run(rcu_nocb_cb_kthread, rdp,
 			"rcuo%c/%d", rcu_state.abbr, cpu);
 	if (WARN_ONCE(IS_ERR(t), "%s: Could not start rcuo CB kthread, OOM is now expected behavior\n", __func__))
 		return;
+
+	if (kthread_prio)
+		sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
 	WRITE_ONCE(rdp->nocb_cb_kthread, t);
 	WRITE_ONCE(rdp->nocb_gp_kthread, rdp_gp->nocb_gp_kthread);
 }
@@ -1348,7 +1360,7 @@ static void __init rcu_organize_nocb_kthreads(void)
  */
 void rcu_bind_current_to_nocb(void)
 {
-	if (cpumask_available(rcu_nocb_mask) && cpumask_weight(rcu_nocb_mask))
+	if (cpumask_available(rcu_nocb_mask) && !cpumask_empty(rcu_nocb_mask))
 		WARN_ON(sched_setaffinity(current->pid, rcu_nocb_mask));
 }
 EXPORT_SYMBOL_GPL(rcu_bind_current_to_nocb);

kernel/rcu/tree_plugin.h

@@ -330,7 +330,7 @@ void rcu_note_context_switch(bool preempt)
 		 * then queue the task as required based on the states
 		 * of any ongoing and expedited grace periods.
 		 */
-		WARN_ON_ONCE((rdp->grpmask & rcu_rnp_online_cpus(rnp)) == 0);
+		WARN_ON_ONCE(!rcu_rdp_cpu_online(rdp));
 		WARN_ON_ONCE(!list_empty(&t->rcu_node_entry));
 		trace_rcu_preempt_task(rcu_state.name,
 				       t->pid,
@@ -556,16 +556,16 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
 			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		}
 
-		/* Unboost if we were boosted. */
-		if (IS_ENABLED(CONFIG_RCU_BOOST) && drop_boost_mutex)
-			rt_mutex_futex_unlock(&rnp->boost_mtx.rtmutex);
-
 		/*
 		 * If this was the last task on the expedited lists,
 		 * then we need to report up the rcu_node hierarchy.
 		 */
 		if (!empty_exp && empty_exp_now)
 			rcu_report_exp_rnp(rnp, true);
+
+		/* Unboost if we were boosted. */
+		if (IS_ENABLED(CONFIG_RCU_BOOST) && drop_boost_mutex)
+			rt_mutex_futex_unlock(&rnp->boost_mtx.rtmutex);
 	} else {
 		local_irq_restore(flags);
 	}
@@ -773,7 +773,6 @@ dump_blkd_tasks(struct rcu_node *rnp, int ncheck)
 	int cpu;
 	int i;
 	struct list_head *lhp;
-	bool onl;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp1;
 
@@ -797,9 +796,8 @@ dump_blkd_tasks(struct rcu_node *rnp, int ncheck)
 	pr_cont("\n");
 	for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++) {
 		rdp = per_cpu_ptr(&rcu_data, cpu);
-		onl = !!(rdp->grpmask & rcu_rnp_online_cpus(rnp));
 		pr_info("\t%d: %c online: %ld(%d) offline: %ld(%d)\n",
-			cpu, ".o"[onl],
+			cpu, ".o"[rcu_rdp_cpu_online(rdp)],
 			(long)rdp->rcu_onl_gp_seq, rdp->rcu_onl_gp_flags,
 			(long)rdp->rcu_ofl_gp_seq, rdp->rcu_ofl_gp_flags);
 	}
@@ -996,12 +994,15 @@ dump_blkd_tasks(struct rcu_node *rnp, int ncheck)
  */
 static void rcu_cpu_kthread_setup(unsigned int cpu)
 {
+	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
 #ifdef CONFIG_RCU_BOOST
 	struct sched_param sp;
 
 	sp.sched_priority = kthread_prio;
 	sched_setscheduler_nocheck(current, SCHED_FIFO, &sp);
 #endif /* #ifdef CONFIG_RCU_BOOST */
+
+	WRITE_ONCE(rdp->rcuc_activity, jiffies);
 }
 
 #ifdef CONFIG_RCU_BOOST
@@ -1172,15 +1173,14 @@ static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp)
 	struct sched_param sp;
 	struct task_struct *t;
 
+	mutex_lock(&rnp->boost_kthread_mutex);
 	if (rnp->boost_kthread_task || !rcu_scheduler_fully_active)
-		return;
-
-	rcu_state.boost = 1;
+		goto out;
 
 	t = kthread_create(rcu_boost_kthread, (void *)rnp,
 			   "rcub/%d", rnp_index);
 	if (WARN_ON_ONCE(IS_ERR(t)))
-		return;
+		goto out;
 
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	rnp->boost_kthread_task = t;
@@ -1188,6 +1188,9 @@ static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp)
 	sp.sched_priority = kthread_prio;
 	sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
 	wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */
+
+ out:
+	mutex_unlock(&rnp->boost_kthread_mutex);
 }
 
 /*
@@ -1210,14 +1213,16 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
 		return;
 	if (!zalloc_cpumask_var(&cm, GFP_KERNEL))
 		return;
+	mutex_lock(&rnp->boost_kthread_mutex);
 	for_each_leaf_node_possible_cpu(rnp, cpu)
 		if ((mask & leaf_node_cpu_bit(rnp, cpu)) &&
 		    cpu != outgoingcpu)
 			cpumask_set_cpu(cpu, cm);
 	cpumask_and(cm, cm, housekeeping_cpumask(HK_FLAG_RCU));
-	if (cpumask_weight(cm) == 0)
+	if (cpumask_empty(cm))
 		cpumask_copy(cm, housekeeping_cpumask(HK_FLAG_RCU));
 	set_cpus_allowed_ptr(t, cm);
+	mutex_unlock(&rnp->boost_kthread_mutex);
 	free_cpumask_var(cm);
 }
 

kernel/rcu/tree_stall.h

@@ -379,6 +379,15 @@ static bool rcu_is_gp_kthread_starving(unsigned long *jp)
 	return j > 2 * HZ;
 }
 
+static bool rcu_is_rcuc_kthread_starving(struct rcu_data *rdp, unsigned long *jp)
+{
+	unsigned long j = jiffies - READ_ONCE(rdp->rcuc_activity);
+
+	if (jp)
+		*jp = j;
+	return j > 2 * HZ;
+}
+
 /*
  * Print out diagnostic information for the specified stalled CPU.
  *
@@ -430,6 +439,29 @@ static void print_cpu_stall_info(int cpu)
 	       falsepositive ? " (false positive?)" : "");
 }
 
+static void rcuc_kthread_dump(struct rcu_data *rdp)
+{
+	int cpu;
+	unsigned long j;
+	struct task_struct *rcuc;
+
+	rcuc = rdp->rcu_cpu_kthread_task;
+	if (!rcuc)
+		return;
+
+	cpu = task_cpu(rcuc);
+	if (cpu_is_offline(cpu) || idle_cpu(cpu))
+		return;
+
+	if (!rcu_is_rcuc_kthread_starving(rdp, &j))
+		return;
+
+	pr_err("%s kthread starved for %ld jiffies\n", rcuc->comm, j);
+	sched_show_task(rcuc);
+	if (!trigger_single_cpu_backtrace(cpu))
+		dump_cpu_task(cpu);
+}
+
 /* Complain about starvation of grace-period kthread.  */
 static void rcu_check_gp_kthread_starvation(void)
 {
@@ -601,6 +633,9 @@ static void print_cpu_stall(unsigned long gps)
 	rcu_check_gp_kthread_expired_fqs_timer();
 	rcu_check_gp_kthread_starvation();
 
+	if (!use_softirq)
+		rcuc_kthread_dump(rdp);
+
 	rcu_dump_cpu_stacks();
 
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);

kernel/rcu/update.c

@@ -407,6 +407,13 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array,
 }
 EXPORT_SYMBOL_GPL(__wait_rcu_gp);
 
+void finish_rcuwait(struct rcuwait *w)
+{
+	rcu_assign_pointer(w->task, NULL);
+	__set_current_state(TASK_RUNNING);
+}
+EXPORT_SYMBOL_GPL(finish_rcuwait);
+
 #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
 void init_rcu_head(struct rcu_head *head)
 {

kernel/torture.c

@@ -911,7 +911,7 @@ void torture_kthread_stopping(char *title)
 {
 	char buf[128];
 
-	snprintf(buf, sizeof(buf), "Stopping %s", title);
+	snprintf(buf, sizeof(buf), "%s is stopping", title);
 	VERBOSE_TOROUT_STRING(buf);
 	while (!kthread_should_stop()) {
 		torture_shutdown_absorb(title);
@@ -931,12 +931,14 @@ int _torture_create_kthread(int (*fn)(void *arg), void *arg, char *s, char *m,
 	int ret = 0;
 
 	VERBOSE_TOROUT_STRING(m);
-	*tp = kthread_run(fn, arg, "%s", s);
+	*tp = kthread_create(fn, arg, "%s", s);
 	if (IS_ERR(*tp)) {
 		ret = PTR_ERR(*tp);
 		TOROUT_ERRSTRING(f);
 		*tp = NULL;
+		return ret;
 	}
+	wake_up_process(*tp);  // Process is sleeping, so ordering provided.
 	torture_shuffle_task_register(*tp);
 	return ret;
 }

tools/testing/selftests/rcutorture/bin/console-badness.sh

@@ -10,7 +10,7 @@
 #
 # Authors: Paul E. McKenney <paulmck@kernel.org>
 
-egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for|!!!' |
+egrep 'Badness|WARNING:|Warn|BUG|===========|BUG: KCSAN:|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for|!!!' |
 grep -v 'ODEBUG: ' |
 grep -v 'This means that this is a DEBUG kernel and it is' |
 grep -v 'Warning: unable to open an initial console' |

tools/testing/selftests/rcutorture/bin/kvm-again.sh

@@ -47,8 +47,8 @@ else
 	exit 1
 fi
 
-KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM
-PATH=${KVM}/bin:$PATH; export PATH
+RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE
+PATH=${RCUTORTURE}/bin:$PATH; export PATH
 . functions.sh
 
 dryrun=

tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh

@@ -49,8 +49,8 @@ fi
 mkdir $resdir/$ds
 echo Results directory: $resdir/$ds
 
-KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM
-PATH=${KVM}/bin:$PATH; export PATH
+RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE
+PATH=${RCUTORTURE}/bin:$PATH; export PATH
 . functions.sh
 echo Using all `identify_qemu_vcpus` CPUs.
 

tools/testing/selftests/rcutorture/bin/kvm-end-run-stats.sh

@@ -22,8 +22,8 @@ T=${TMPDIR-/tmp}/kvm-end-run-stats.sh.$$
 trap 'rm -rf $T' 0
 mkdir $T
 
-KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM
-PATH=${KVM}/bin:$PATH; export PATH
+RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE
+PATH=${RCUTORTURE}/bin:$PATH; export PATH
 . functions.sh
 default_starttime="`get_starttime`"
 starttime="${2-default_starttime}"

tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh

@@ -30,10 +30,16 @@ editor=${EDITOR-vi}
 files=
 for i in ${rundir}/*/Make.out
 do
+	scenariodir="`dirname $i`"
+	scenariobasedir="`echo ${scenariodir} | sed -e 's/\.[0-9]*$//'`"
 	if egrep -q "error:|warning:|^ld: .*undefined reference to" < $i
 	then
 		egrep "error:|warning:|^ld: .*undefined reference to" < $i > $i.diags
 		files="$files $i.diags $i"
+	elif ! test -f ${scenariobasedir}/vmlinux
+	then
+		echo No ${scenariobasedir}/vmlinux file > $i.diags
+		files="$files $i.diags $i"
 	fi
 done
 if test -n "$files"

tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh

@@ -25,7 +25,7 @@ stopstate="`grep 'End-test grace-period state: g' $i/console.log 2> /dev/null |
 	    tail -1 | sed -e 's/^\[[ 0-9.]*] //' |
 	    awk '{ print \"[\" $1 \" \" $5 \" \" $6 \" \" $7 \"]\"; }' |
 	    tr -d '\012\015'`"
-fwdprog="`grep 'rcu_torture_fwd_prog n_max_cbs: ' $i/console.log 2> /dev/null | sed -e 's/^\[[^]]*] //' | sort -k3nr | head -1 | awk '{ print $2 " " $3 }'`"
+fwdprog="`grep 'rcu_torture_fwd_prog n_max_cbs: ' $i/console.log 2> /dev/null | sed -e 's/^\[[^]]*] //' | sort -k3nr | head -1 | awk '{ print $2 " " $3 }' | tr -d '\015'`"
 if test -z "$ngps"
 then
 	echo "$configfile ------- " $stopstate

tools/testing/selftests/rcutorture/bin/kvm-remote.sh

@@ -19,8 +19,8 @@ then
 	exit 1
 fi
 
-KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM
-PATH=${KVM}/bin:$PATH; export PATH
+RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE
+PATH=${RCUTORTURE}/bin:$PATH; export PATH
 . functions.sh
 
 starttime="`get_starttime`"
@@ -108,8 +108,8 @@ else
 		cat $T/kvm-again.sh.out | tee -a "$oldrun/remote-log"
 		exit 2
 	fi
-	cp -a "$rundir" "$KVM/res/"
-	oldrun="$KVM/res/$ds"
+	cp -a "$rundir" "$RCUTORTURE/res/"
+	oldrun="$RCUTORTURE/res/$ds"
 fi
 echo | tee -a "$oldrun/remote-log"
 echo " ----" kvm-again.sh output: "(`date`)" | tee -a "$oldrun/remote-log"
@@ -155,18 +155,23 @@ do
 	echo Downloading tarball to $i `date` | tee -a "$oldrun/remote-log"
 	cat $T/binres.tgz | ssh $i "cd /tmp; tar -xzf -"
 	ret=$?
-	if test "$ret" -ne 0
-	then
-		echo Unable to download $T/binres.tgz to system $i, waiting and then retrying. | tee -a "$oldrun/remote-log"
+	tries=0
+	while test "$ret" -ne 0
+	do
+		echo Unable to download $T/binres.tgz to system $i, waiting and then retrying.  $tries prior retries. | tee -a "$oldrun/remote-log"
 		sleep 60
 		cat $T/binres.tgz | ssh $i "cd /tmp; tar -xzf -"
 		ret=$?
 		if test "$ret" -ne 0
+		then
+			if test "$tries" > 5
 			then
 				echo Unable to download $T/binres.tgz to system $i, giving up. | tee -a "$oldrun/remote-log"
 				exit 10
 			fi
 		fi
+		tries=$((tries+1))
+	done
 done
 
 # Function to check for presence of a file on the specified system.

tools/testing/selftests/rcutorture/bin/kvm.sh

@@ -25,15 +25,15 @@ LANG=en_US.UTF-8; export LANG
 
 dur=$((30*60))
 dryrun=""
-KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM
-PATH=${KVM}/bin:$PATH; export PATH
+RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE
+PATH=${RCUTORTURE}/bin:$PATH; export PATH
 . functions.sh
 
 TORTURE_ALLOTED_CPUS="`identify_qemu_vcpus`"
 TORTURE_DEFCONFIG=defconfig
 TORTURE_BOOT_IMAGE=""
 TORTURE_BUILDONLY=
-TORTURE_INITRD="$KVM/initrd"; export TORTURE_INITRD
+TORTURE_INITRD="$RCUTORTURE/initrd"; export TORTURE_INITRD
 TORTURE_KCONFIG_ARG=""
 TORTURE_KCONFIG_GDB_ARG=""
 TORTURE_BOOT_GDB_ARG=""
@@ -262,7 +262,7 @@ else
 	exit 1
 fi
 
-CONFIGFRAG=${KVM}/configs/${TORTURE_SUITE}; export CONFIGFRAG
+CONFIGFRAG=${RCUTORTURE}/configs/${TORTURE_SUITE}; export CONFIGFRAG
 
 defaultconfigs="`tr '\012' ' ' < $CONFIGFRAG/CFLIST`"
 if test -z "$configs"
@@ -272,7 +272,7 @@ fi
 
 if test -z "$resdir"
 then
-	resdir=$KVM/res
+	resdir=$RCUTORTURE/res
 fi
 
 # Create a file of test-name/#cpus pairs, sorted by decreasing #cpus.
@@ -280,7 +280,7 @@ configs_derep=
 for CF in $configs
 do
 	case $CF in
-	[0-9]\**|[0-9][0-9]\**|[0-9][0-9][0-9]\**)
+	[0-9]\**|[0-9][0-9]\**|[0-9][0-9][0-9]\**|[0-9][0-9][0-9][0-9]\**)
 		config_reps=`echo $CF | sed -e 's/\*.*$//'`
 		CF1=`echo $CF | sed -e 's/^[^*]*\*//'`
 		;;
@@ -386,7 +386,7 @@ END {
 # Generate a script to execute the tests in appropriate batches.
 cat << ___EOF___ > $T/script
 CONFIGFRAG="$CONFIGFRAG"; export CONFIGFRAG
-KVM="$KVM"; export KVM
+RCUTORTURE="$RCUTORTURE"; export RCUTORTURE
 PATH="$PATH"; export PATH
 TORTURE_ALLOTED_CPUS="$TORTURE_ALLOTED_CPUS"; export TORTURE_ALLOTED_CPUS
 TORTURE_BOOT_IMAGE="$TORTURE_BOOT_IMAGE"; export TORTURE_BOOT_IMAGE
@@ -569,7 +569,7 @@ ___EOF___
 awk < $T/cfgcpu.pack \
 	-v TORTURE_BUILDONLY="$TORTURE_BUILDONLY" \
 	-v CONFIGDIR="$CONFIGFRAG/" \
-	-v KVM="$KVM" \
+	-v RCUTORTURE="$RCUTORTURE" \
 	-v ncpus=$cpus \
 	-v jitter="$jitter" \
 	-v rd=$resdir/$ds/ \

tools/testing/selftests/rcutorture/bin/parse-console.sh

@@ -138,6 +138,16 @@ then
 	then
 		summary="$summary  Bugs: $n_bugs"
 	fi
+	n_kcsan=`egrep -c 'BUG: KCSAN: ' $file`
+	if test "$n_kcsan" -ne 0
+	then
+		if test "$n_bugs" = "$n_kcsan"
+		then
+			summary="$summary (all bugs kcsan)"
+		else
+			summary="$summary  KCSAN: $n_kcsan"
+		fi
+	fi
 	n_calltrace=`grep -c 'Call Trace:' $file`
 	if test "$n_calltrace" -ne 0
 	then

tools/testing/selftests/rcutorture/bin/torture.sh

@@ -13,8 +13,8 @@
 scriptname=$0
 args="$*"
 
-KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM
-PATH=${KVM}/bin:$PATH; export PATH
+RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE
+PATH=${RCUTORTURE}/bin:$PATH; export PATH
 . functions.sh
 
 TORTURE_ALLOTED_CPUS="`identify_qemu_vcpus`"
@@ -37,7 +37,7 @@ configs_scftorture=
 kcsan_kmake_args=
 
 # Default compression, duration, and apportionment.
-compress_kasan_vmlinux="`identify_qemu_vcpus`"
+compress_concurrency="`identify_qemu_vcpus`"
 duration_base=10
 duration_rcutorture_frac=7
 duration_locktorture_frac=1
@@ -67,12 +67,12 @@ function doyesno () {
 
 usage () {
 	echo "Usage: $scriptname optional arguments:"
-	echo "       --compress-kasan-vmlinux concurrency"
+	echo "       --compress-concurrency concurrency"
 	echo "       --configs-rcutorture \"config-file list w/ repeat factor (3*TINY01)\""
 	echo "       --configs-locktorture \"config-file list w/ repeat factor (10*LOCK01)\""
 	echo "       --configs-scftorture \"config-file list w/ repeat factor (2*CFLIST)\""
-	echo "       --doall"
-	echo "       --doallmodconfig / --do-no-allmodconfig"
+	echo "       --do-all"
+	echo "       --do-allmodconfig / --do-no-allmodconfig"
 	echo "       --do-clocksourcewd / --do-no-clocksourcewd"
 	echo "       --do-kasan / --do-no-kasan"
 	echo "       --do-kcsan / --do-no-kcsan"
@@ -91,9 +91,9 @@ usage () {
 while test $# -gt 0
 do
 	case "$1" in
-	--compress-kasan-vmlinux)
-		checkarg --compress-kasan-vmlinux "(concurrency level)" $# "$2" '^[0-9][0-9]*$' '^error'
-		compress_kasan_vmlinux=$2
+	--compress-concurrency)
+		checkarg --compress-concurrency "(concurrency level)" $# "$2" '^[0-9][0-9]*$' '^error'
+		compress_concurrency=$2
 		shift
 		;;
 	--config-rcutorture|--configs-rcutorture)
@@ -414,8 +414,14 @@ nfailures=0
 echo FAILURES: | tee -a $T/log
 if test -s "$T/failures"
 then
-	cat "$T/failures" | tee -a $T/log
+	awk < "$T/failures" -v sq="'" '{ print "echo " sq $0 sq; print "sed -e " sq "1,/^ --- .* Test summary:$/d" sq " " $2 "/log | grep Summary: | sed -e " sq "s/^[^S]*/  /" sq; }' | sh | tee -a $T/log | tee "$T/failuresum"
 	nfailures="`wc -l "$T/failures" | awk '{ print $1 }'`"
+	grep "^  Summary: " "$T/failuresum" |
+		grep -v '^  Summary: Bugs: [0-9]* (all bugs kcsan)$' > "$T/nonkcsan"
+	if test -s "$T/nonkcsan"
+	then
+		nonkcsanbug="yes"
+	fi
 	ret=2
 fi
 if test "$do_kcsan" = "yes"
@@ -424,12 +430,16 @@ then
 fi
 echo Started at $startdate, ended at `date`, duration `get_starttime_duration $starttime`. | tee -a $T/log
 echo Summary: Successes: $nsuccesses Failures: $nfailures. | tee -a $T/log
+if test -z "$nonkcsanbug" && test -s "$T/failuresum"
+then
+	echo "  All bugs were KCSAN failures."
+fi
 tdir="`cat $T/successes $T/failures | head -1 | awk '{ print $NF }' | sed -e 's,/[^/]\+/*$,,'`"
-if test -n "$tdir" && test $compress_kasan_vmlinux -gt 0
+if test -n "$tdir" && test $compress_concurrency -gt 0
 then
 	# KASAN vmlinux files can approach 1GB in size, so compress them.
-	echo Looking for KASAN files to compress: `date` > "$tdir/log-xz" 2>&1
-	find "$tdir" -type d -name '*-kasan' -print > $T/xz-todo
+	echo Looking for K[AC]SAN files to compress: `date` > "$tdir/log-xz" 2>&1
+	find "$tdir" -type d -name '*-k[ac]san' -print > $T/xz-todo
 	ncompresses=0
 	batchno=1
 	if test -s $T/xz-todo
@@ -447,7 +457,7 @@ then
 			do
 				xz "$j" >> "$tdir/log-xz" 2>&1 &
 				ncompresses=$((ncompresses+1))
-				if test $ncompresses -ge $compress_kasan_vmlinux
+				if test $ncompresses -ge $compress_concurrency
 				then
 					echo Waiting for batch $batchno of $ncompresses compressions `date` | tee -a "$tdir/log-xz" | tee -a $T/log
 					wait

tools/testing/selftests/rcutorture/configs/rcu/RUDE01

 CONFIG_SMP=y
-CONFIG_NR_CPUS=4
+CONFIG_NR_CPUS=3
 CONFIG_HOTPLUG_CPU=y
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n

tools/testing/selftests/rcutorture/configs/rcu/SRCU-N.boot

 rcutorture.torture_type=srcu
+rcutorture.fwd_progress=3

tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot

 rcutorture.torture_type=srcud
 rcupdate.rcu_self_test=1
+rcutorture.fwd_progress=3
+srcutree.big_cpu_lim=5

tools/testing/selftests/rcutorture/configs/rcu/TRACE01

 CONFIG_SMP=y
-CONFIG_NR_CPUS=4
+CONFIG_NR_CPUS=5
 CONFIG_HOTPLUG_CPU=y
 CONFIG_PREEMPT_NONE=y
 CONFIG_PREEMPT_VOLUNTARY=n