Merge branches 'doc.2021.07.20c', 'fixes.2021.08.06a', 'nocb.2021.07.20c',...

Merge branches 'doc.2021.07.20c', 'fixes.2021.08.06a', 'nocb.2021.07.20c', 'nolibc.2021.07.20c', 'tasks.2021.07.20c', 'torture.2021.07.27a' and 'torturescript.2021.07.27a' into HEAD

doc.2021.07.20c: Documentation updates.
fixes.2021.08.06a: Miscellaneous fixes.
nocb.2021.07.20c: Callback-offloading (NOCB CPU) updates.
nolibc.2021.07.20c: Tiny userspace library updates.
tasks.2021.07.20c: Tasks RCU updates.
torture.2021.07.27a: In-kernel torture-test updates.
torturescript.2021.07.27a: Torture-test scripting updates.

include/linux/rculist.h

@@ -10,15 +10,6 @@
 #include <linux/list.h>
 #include <linux/rcupdate.h>
 
-/*
- * Why is there no list_empty_rcu()?  Because list_empty() serves this
- * purpose.  The list_empty() function fetches the RCU-protected pointer
- * and compares it to the address of the list head, but neither dereferences
- * this pointer itself nor provides this pointer to the caller.  Therefore,
- * it is not necessary to use rcu_dereference(), so that list_empty() can
- * be used anywhere you would want to use a list_empty_rcu().
- */
-
 /*
  * INIT_LIST_HEAD_RCU - Initialize a list_head visible to RCU readers
  * @list: list to be initialized
@@ -318,21 +309,29 @@ static inline void list_splice_tail_init_rcu(struct list_head *list,
 /*
  * Where are list_empty_rcu() and list_first_entry_rcu()?
  *
- * Implementing those functions following their counterparts list_empty() and
- * list_first_entry() is not advisable because they lead to subtle race
- * conditions as the following snippet shows:
+ * They do not exist because they would lead to subtle race conditions:
  *
  * if (!list_empty_rcu(mylist)) {
  *	struct foo *bar = list_first_entry_rcu(mylist, struct foo, list_member);
  *	do_something(bar);
  * }
  *
- * The list may not be empty when list_empty_rcu checks it, but it may be when
- * list_first_entry_rcu rereads the ->next pointer.
- *
- * Rereading the ->next pointer is not a problem for list_empty() and
- * list_first_entry() because they would be protected by a lock that blocks
- * writers.
+ * The list might be non-empty when list_empty_rcu() checks it, but it
+ * might have become empty by the time that list_first_entry_rcu() rereads
+ * the ->next pointer, which would result in a SEGV.
+ *
+ * When not using RCU, it is OK for list_first_entry() to re-read that
+ * pointer because both functions should be protected by some lock that
+ * blocks writers.
+ *
+ * When using RCU, list_empty() uses READ_ONCE() to fetch the
+ * RCU-protected ->next pointer and then compares it to the address of the
+ * list head.  However, it neither dereferences this pointer nor provides
+ * this pointer to its caller.  Thus, READ_ONCE() suffices (that is,
+ * rcu_dereference() is not needed), which means that list_empty() can be
+ * used anywhere you would want to use list_empty_rcu().  Just don't
+ * expect anything useful to happen if you do a subsequent lockless
+ * call to list_first_entry_rcu()!!!
  *
  * See list_first_or_null_rcu for an alternative.
  */

include/linux/rcupdate.h

@@ -53,7 +53,7 @@ void __rcu_read_unlock(void);
  * nesting depth, but makes sense only if CONFIG_PREEMPT_RCU -- in other
  * types of kernel builds, the rcu_read_lock() nesting depth is unknowable.
  */
-#define rcu_preempt_depth() (current->rcu_read_lock_nesting)
+#define rcu_preempt_depth() READ_ONCE(current->rcu_read_lock_nesting)
 
 #else /* #ifdef CONFIG_PREEMPT_RCU */
 
@@ -167,7 +167,7 @@ void synchronize_rcu_tasks(void);
 # define synchronize_rcu_tasks synchronize_rcu
 # endif
 
-# ifdef CONFIG_TASKS_RCU_TRACE
+# ifdef CONFIG_TASKS_TRACE_RCU
 # define rcu_tasks_trace_qs(t)						\
 	do {								\
 		if (!likely(READ_ONCE((t)->trc_reader_checked)) &&	\

include/linux/rcutiny.h

@@ -14,9 +14,6 @@
 
 #include <asm/param.h> /* for HZ */
 
-/* Never flag non-existent other CPUs! */
-static inline bool rcu_eqs_special_set(int cpu) { return false; }
-
 unsigned long get_state_synchronize_rcu(void);
 unsigned long start_poll_synchronize_rcu(void);
 bool poll_state_synchronize_rcu(unsigned long oldstate);

include/linux/srcutiny.h

@@ -61,7 +61,7 @@ static inline int __srcu_read_lock(struct srcu_struct *ssp)
 	int idx;
 
 	idx = ((READ_ONCE(ssp->srcu_idx) + 1) & 0x2) >> 1;
-	WRITE_ONCE(ssp->srcu_lock_nesting[idx], ssp->srcu_lock_nesting[idx] + 1);
+	WRITE_ONCE(ssp->srcu_lock_nesting[idx], READ_ONCE(ssp->srcu_lock_nesting[idx]) + 1);
 	return idx;
 }
 
@@ -81,11 +81,11 @@ static inline void srcu_torture_stats_print(struct srcu_struct *ssp,
 {
 	int idx;
 
-	idx = ((READ_ONCE(ssp->srcu_idx) + 1) & 0x2) >> 1;
+	idx = ((data_race(READ_ONCE(ssp->srcu_idx)) + 1) & 0x2) >> 1;
 	pr_alert("%s%s Tiny SRCU per-CPU(idx=%d): (%hd,%hd)\n",
 		 tt, tf, idx,
-		 READ_ONCE(ssp->srcu_lock_nesting[!idx]),
-		 READ_ONCE(ssp->srcu_lock_nesting[idx]));
+		 data_race(READ_ONCE(ssp->srcu_lock_nesting[!idx])),
+		 data_race(READ_ONCE(ssp->srcu_lock_nesting[idx])));
 }
 
 #endif

kernel/locking/locktorture.c

@@ -59,7 +59,7 @@ static struct task_struct **writer_tasks;
 static struct task_struct **reader_tasks;
 
 static bool lock_is_write_held;
-static bool lock_is_read_held;
+static atomic_t lock_is_read_held;
 static unsigned long last_lock_release;
 
 struct lock_stress_stats {
@@ -682,7 +682,7 @@ static int lock_torture_writer(void *arg)
 		if (WARN_ON_ONCE(lock_is_write_held))
 			lwsp->n_lock_fail++;
 		lock_is_write_held = true;
-		if (WARN_ON_ONCE(lock_is_read_held))
+		if (WARN_ON_ONCE(atomic_read(&lock_is_read_held)))
 			lwsp->n_lock_fail++; /* rare, but... */
 
 		lwsp->n_lock_acquired++;
@@ -717,13 +717,13 @@ static int lock_torture_reader(void *arg)
 			schedule_timeout_uninterruptible(1);
 
 		cxt.cur_ops->readlock(tid);
-		lock_is_read_held = true;
+		atomic_inc(&lock_is_read_held);
 		if (WARN_ON_ONCE(lock_is_write_held))
 			lrsp->n_lock_fail++; /* rare, but... */
 
 		lrsp->n_lock_acquired++;
 		cxt.cur_ops->read_delay(&rand);
-		lock_is_read_held = false;
+		atomic_dec(&lock_is_read_held);
 		cxt.cur_ops->readunlock(tid);
 
 		stutter_wait("lock_torture_reader");
@@ -738,20 +738,22 @@ static int lock_torture_reader(void *arg)
 static void __torture_print_stats(char *page,
 				  struct lock_stress_stats *statp, bool write)
 {
+	long cur;
 	bool fail = false;
 	int i, n_stress;
-	long max = 0, min = statp ? statp[0].n_lock_acquired : 0;
+	long max = 0, min = statp ? data_race(statp[0].n_lock_acquired) : 0;
 	long long sum = 0;
 
 	n_stress = write ? cxt.nrealwriters_stress : cxt.nrealreaders_stress;
 	for (i = 0; i < n_stress; i++) {
-		if (statp[i].n_lock_fail)
+		if (data_race(statp[i].n_lock_fail))
 			fail = true;
-		sum += statp[i].n_lock_acquired;
-		if (max < statp[i].n_lock_acquired)
-			max = statp[i].n_lock_acquired;
-		if (min > statp[i].n_lock_acquired)
-			min = statp[i].n_lock_acquired;
+		cur = data_race(statp[i].n_lock_acquired);
+		sum += cur;
+		if (max < cur)
+			max = cur;
+		if (min > cur)
+			min = cur;
 	}
 	page += sprintf(page,
 			"%s:  Total: %lld  Max/Min: %ld/%ld %s  Fail: %d %s\n",
@@ -996,7 +998,6 @@ static int __init lock_torture_init(void)
 		}
 
 		if (nreaders_stress) {
-			lock_is_read_held = false;
 			cxt.lrsa = kmalloc_array(cxt.nrealreaders_stress,
 						 sizeof(*cxt.lrsa),
 						 GFP_KERNEL);

kernel/rcu/rcuscale.c

@@ -487,7 +487,7 @@ rcu_scale_writer(void *arg)
 	if (gp_async) {
 		cur_ops->gp_barrier();
 	}
-	writer_n_durations[me] = i_max;
+	writer_n_durations[me] = i_max + 1;
 	torture_kthread_stopping("rcu_scale_writer");
 	return 0;
 }
@@ -561,7 +561,7 @@ rcu_scale_cleanup(void)
 			wdpp = writer_durations[i];
 			if (!wdpp)
 				continue;
-			for (j = 0; j <= writer_n_durations[i]; j++) {
+			for (j = 0; j < writer_n_durations[i]; j++) {
 				wdp = &wdpp[j];
 				pr_alert("%s%s %4d writer-duration: %5d %llu\n",
 					scale_type, SCALE_FLAG,

kernel/rcu/rcutorture.c

@@ -2022,8 +2022,13 @@ static int rcu_torture_stall(void *args)
 			  __func__, raw_smp_processor_id());
 		while (ULONG_CMP_LT((unsigned long)ktime_get_seconds(),
 				    stop_at))
-			if (stall_cpu_block)
+			if (stall_cpu_block) {
+#ifdef CONFIG_PREEMPTION
+				preempt_schedule();
+#else
 				schedule_timeout_uninterruptible(HZ);
+#endif
+			}
 		if (stall_cpu_irqsoff)
 			local_irq_enable();
 		else if (!stall_cpu_block)

kernel/rcu/refscale.c

@@ -467,6 +467,40 @@ static struct ref_scale_ops acqrel_ops = {
 	.name		= "acqrel"
 };
 
+static volatile u64 stopopts;
+
+static void ref_clock_section(const int nloops)
+{
+	u64 x = 0;
+	int i;
+
+	preempt_disable();
+	for (i = nloops; i >= 0; i--)
+		x += ktime_get_real_fast_ns();
+	preempt_enable();
+	stopopts = x;
+}
+
+static void ref_clock_delay_section(const int nloops, const int udl, const int ndl)
+{
+	u64 x = 0;
+	int i;
+
+	preempt_disable();
+	for (i = nloops; i >= 0; i--) {
+		x += ktime_get_real_fast_ns();
+		un_delay(udl, ndl);
+	}
+	preempt_enable();
+	stopopts = x;
+}
+
+static struct ref_scale_ops clock_ops = {
+	.readsection	= ref_clock_section,
+	.delaysection	= ref_clock_delay_section,
+	.name		= "clock"
+};
+
 static void rcu_scale_one_reader(void)
 {
 	if (readdelay <= 0)
@@ -759,7 +793,7 @@ ref_scale_init(void)
 	int firsterr = 0;
 	static struct ref_scale_ops *scale_ops[] = {
 		&rcu_ops, &srcu_ops, &rcu_trace_ops, &rcu_tasks_ops, &refcnt_ops, &rwlock_ops,
-		&rwsem_ops, &lock_ops, &lock_irq_ops, &acqrel_ops,
+		&rwsem_ops, &lock_ops, &lock_irq_ops, &acqrel_ops, &clock_ops,
 	};
 
 	if (!torture_init_begin(scale_type, verbose))

kernel/rcu/srcutiny.c

@@ -96,7 +96,7 @@ EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
  */
 void __srcu_read_unlock(struct srcu_struct *ssp, int idx)
 {
-	int newval = ssp->srcu_lock_nesting[idx] - 1;
+	int newval = READ_ONCE(ssp->srcu_lock_nesting[idx]) - 1;
 
 	WRITE_ONCE(ssp->srcu_lock_nesting[idx], newval);
 	if (!newval && READ_ONCE(ssp->srcu_gp_waiting))

kernel/rcu/tasks.h

@@ -643,8 +643,8 @@ void exit_tasks_rcu_finish(void) { exit_tasks_rcu_finish_trace(current); }
 //
 // "Rude" variant of Tasks RCU, inspired by Steve Rostedt's trick of
 // passing an empty function to schedule_on_each_cpu().  This approach
-// provides an asynchronous call_rcu_tasks_rude() API and batching
-// of concurrent calls to the synchronous synchronize_rcu_rude() API.
+// provides an asynchronous call_rcu_tasks_rude() API and batching of
+// concurrent calls to the synchronous synchronize_rcu_tasks_rude() API.
 // This invokes schedule_on_each_cpu() in order to send IPIs far and wide
 // and induces otherwise unnecessary context switches on all online CPUs,
 // whether idle or not.
@@ -785,7 +785,10 @@ EXPORT_SYMBOL_GPL(show_rcu_tasks_rude_gp_kthread);
 //	set that task's .need_qs flag so that task's next outermost
 //	rcu_read_unlock_trace() will report the quiescent state (in which
 //	case the count of readers is incremented).  If both attempts fail,
-//	the task is added to a "holdout" list.
+//	the task is added to a "holdout" list.  Note that IPIs are used
+//	to invoke trc_read_check_handler() in the context of running tasks
+//	in order to avoid ordering overhead on common-case shared-variable
+//	accessses.
 // rcu_tasks_trace_postscan():
 //	Initialize state and attempt to identify an immediate quiescent
 //	state as above (but only for idle tasks), unblock CPU-hotplug
@@ -847,7 +850,7 @@ static DEFINE_IRQ_WORK(rcu_tasks_trace_iw, rcu_read_unlock_iw);
 /* If we are the last reader, wake up the grace-period kthread. */
 void rcu_read_unlock_trace_special(struct task_struct *t, int nesting)
 {
-	int nq = t->trc_reader_special.b.need_qs;
+	int nq = READ_ONCE(t->trc_reader_special.b.need_qs);
 
 	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) &&
 	    t->trc_reader_special.b.need_mb)
@@ -894,7 +897,7 @@ static void trc_read_check_handler(void *t_in)
 
 	// If the task is not in a read-side critical section, and
 	// if this is the last reader, awaken the grace-period kthread.
-	if (likely(!t->trc_reader_nesting)) {
+	if (likely(!READ_ONCE(t->trc_reader_nesting))) {
 		if (WARN_ON_ONCE(atomic_dec_and_test(&trc_n_readers_need_end)))
 			wake_up(&trc_wait);
 		// Mark as checked after decrement to avoid false
@@ -903,7 +906,7 @@ static void trc_read_check_handler(void *t_in)
 		goto reset_ipi;
 	}
 	// If we are racing with an rcu_read_unlock_trace(), try again later.
-	if (unlikely(t->trc_reader_nesting < 0)) {
+	if (unlikely(READ_ONCE(t->trc_reader_nesting) < 0)) {
 		if (WARN_ON_ONCE(atomic_dec_and_test(&trc_n_readers_need_end)))
 			wake_up(&trc_wait);
 		goto reset_ipi;
@@ -913,14 +916,14 @@ static void trc_read_check_handler(void *t_in)
 	// Get here if the task is in a read-side critical section.  Set
 	// its state so that it will awaken the grace-period kthread upon
 	// exit from that critical section.
-	WARN_ON_ONCE(t->trc_reader_special.b.need_qs);
+	WARN_ON_ONCE(READ_ONCE(t->trc_reader_special.b.need_qs));
 	WRITE_ONCE(t->trc_reader_special.b.need_qs, true);
 
 reset_ipi:
 	// Allow future IPIs to be sent on CPU and for task.
 	// Also order this IPI handler against any later manipulations of
 	// the intended task.
-	smp_store_release(&per_cpu(trc_ipi_to_cpu, smp_processor_id()), false); // ^^^
+	smp_store_release(per_cpu_ptr(&trc_ipi_to_cpu, smp_processor_id()), false); // ^^^
 	smp_store_release(&texp->trc_ipi_to_cpu, -1); // ^^^
 }
 
@@ -950,6 +953,7 @@ static bool trc_inspect_reader(struct task_struct *t, void *arg)
 			n_heavy_reader_ofl_updates++;
 		in_qs = true;
 	} else {
+		// The task is not running, so C-language access is safe.
 		in_qs = likely(!t->trc_reader_nesting);
 	}
 
@@ -964,7 +968,7 @@ static bool trc_inspect_reader(struct task_struct *t, void *arg)
 	// state so that it will awaken the grace-period kthread upon exit
 	// from that critical section.
 	atomic_inc(&trc_n_readers_need_end); // One more to wait on.
-	WARN_ON_ONCE(t->trc_reader_special.b.need_qs);
+	WARN_ON_ONCE(READ_ONCE(t->trc_reader_special.b.need_qs));
 	WRITE_ONCE(t->trc_reader_special.b.need_qs, true);
 	return true;
 }
@@ -982,7 +986,7 @@ static void trc_wait_for_one_reader(struct task_struct *t,
 	// The current task had better be in a quiescent state.
 	if (t == current) {
 		t->trc_reader_checked = true;
-		WARN_ON_ONCE(t->trc_reader_nesting);
+		WARN_ON_ONCE(READ_ONCE(t->trc_reader_nesting));
 		return;
 	}
 
@@ -994,6 +998,12 @@ static void trc_wait_for_one_reader(struct task_struct *t,
 	}
 	put_task_struct(t);
 
+	// If this task is not yet on the holdout list, then we are in
+	// an RCU read-side critical section.  Otherwise, the invocation of
+	// rcu_add_holdout() that added it to the list did the necessary
+	// get_task_struct().  Either way, the task cannot be freed out
+	// from under this code.
+
 	// If currently running, send an IPI, either way, add to list.
 	trc_add_holdout(t, bhp);
 	if (task_curr(t) &&
@@ -1092,8 +1102,8 @@ static void show_stalled_task_trace(struct task_struct *t, bool *firstreport)
 		 ".I"[READ_ONCE(t->trc_ipi_to_cpu) > 0],
 		 ".i"[is_idle_task(t)],
 		 ".N"[cpu > 0 && tick_nohz_full_cpu(cpu)],
-		 t->trc_reader_nesting,
-		 " N"[!!t->trc_reader_special.b.need_qs],
+		 READ_ONCE(t->trc_reader_nesting),
+		 " N"[!!READ_ONCE(t->trc_reader_special.b.need_qs)],
 		 cpu);
 	sched_show_task(t);
 }
@@ -1187,7 +1197,7 @@ static void rcu_tasks_trace_postgp(struct rcu_tasks *rtp)
 static void exit_tasks_rcu_finish_trace(struct task_struct *t)
 {
 	WRITE_ONCE(t->trc_reader_checked, true);
-	WARN_ON_ONCE(t->trc_reader_nesting);
+	WARN_ON_ONCE(READ_ONCE(t->trc_reader_nesting));
 	WRITE_ONCE(t->trc_reader_nesting, 0);
 	if (WARN_ON_ONCE(READ_ONCE(t->trc_reader_special.b.need_qs)))
 		rcu_read_unlock_trace_special(t, 0);

kernel/rcu/tree.c

@@ -74,17 +74,10 @@
 
 /* Data structures. */
 
-/*
- * Steal a bit from the bottom of ->dynticks for idle entry/exit
- * control.  Initially this is for TLB flushing.
- */
-#define RCU_DYNTICK_CTRL_MASK 0x1
-#define RCU_DYNTICK_CTRL_CTR  (RCU_DYNTICK_CTRL_MASK + 1)
-
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, rcu_data) = {
 	.dynticks_nesting = 1,
 	.dynticks_nmi_nesting = DYNTICK_IRQ_NONIDLE,
-	.dynticks = ATOMIC_INIT(RCU_DYNTICK_CTRL_CTR),
+	.dynticks = ATOMIC_INIT(1),
 #ifdef CONFIG_RCU_NOCB_CPU
 	.cblist.flags = SEGCBLIST_SOFTIRQ_ONLY,
 #endif
@@ -258,6 +251,15 @@ void rcu_softirq_qs(void)
 	rcu_tasks_qs(current, false);
 }
 
+/*
+ * Increment the current CPU's rcu_data structure's ->dynticks field
+ * with ordering.  Return the new value.
+ */
+static noinline noinstr unsigned long rcu_dynticks_inc(int incby)
+{
+	return arch_atomic_add_return(incby, this_cpu_ptr(&rcu_data.dynticks));
+}
+
 /*
  * Record entry into an extended quiescent state.  This is only to be
  * called when not already in an extended quiescent state, that is,
@@ -266,7 +268,6 @@ void rcu_softirq_qs(void)
  */
 static noinstr void rcu_dynticks_eqs_enter(void)
 {
-	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 	int seq;
 
 	/*
@@ -275,13 +276,9 @@ static noinstr void rcu_dynticks_eqs_enter(void)
 	 * next idle sojourn.
 	 */
 	rcu_dynticks_task_trace_enter();  // Before ->dynticks update!
-	seq = arch_atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
+	seq = rcu_dynticks_inc(1);
 	// RCU is no longer watching.  Better be in extended quiescent state!
-	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
-		     (seq & RCU_DYNTICK_CTRL_CTR));
-	/* Better not have special action (TLB flush) pending! */
-	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
-		     (seq & RCU_DYNTICK_CTRL_MASK));
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && (seq & 0x1));
 }
 
 /*
@@ -291,7 +288,6 @@ static noinstr void rcu_dynticks_eqs_enter(void)
  */
 static noinstr void rcu_dynticks_eqs_exit(void)
 {
-	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 	int seq;
 
 	/*
@@ -299,15 +295,10 @@ static noinstr void rcu_dynticks_eqs_exit(void)
 	 * and we also must force ordering with the next RCU read-side
 	 * critical section.
 	 */
-	seq = arch_atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
+	seq = rcu_dynticks_inc(1);
 	// RCU is now watching.  Better not be in an extended quiescent state!
 	rcu_dynticks_task_trace_exit();  // After ->dynticks update!
-	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
-		     !(seq & RCU_DYNTICK_CTRL_CTR));
-	if (seq & RCU_DYNTICK_CTRL_MASK) {
-		arch_atomic_andnot(RCU_DYNTICK_CTRL_MASK, &rdp->dynticks);
-		smp_mb__after_atomic(); /* _exit after clearing mask. */
-	}
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !(seq & 0x1));
 }
 
 /*
@@ -324,9 +315,9 @@ static void rcu_dynticks_eqs_online(void)
 {
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 
-	if (atomic_read(&rdp->dynticks) & RCU_DYNTICK_CTRL_CTR)
+	if (atomic_read(&rdp->dynticks) & 0x1)
 		return;
-	atomic_add(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
+	rcu_dynticks_inc(1);
 }
 
 /*
@@ -336,9 +327,7 @@ static void rcu_dynticks_eqs_online(void)
  */
 static __always_inline bool rcu_dynticks_curr_cpu_in_eqs(void)
 {
-	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
-
-	return !(arch_atomic_read(&rdp->dynticks) & RCU_DYNTICK_CTRL_CTR);
+	return !(atomic_read(this_cpu_ptr(&rcu_data.dynticks)) & 0x1);
 }
 
 /*
@@ -347,9 +336,8 @@ static __always_inline bool rcu_dynticks_curr_cpu_in_eqs(void)
  */
 static int rcu_dynticks_snap(struct rcu_data *rdp)
 {
-	int snap = atomic_add_return(0, &rdp->dynticks);
-
-	return snap & ~RCU_DYNTICK_CTRL_MASK;
+	smp_mb();  // Fundamental RCU ordering guarantee.
+	return atomic_read_acquire(&rdp->dynticks);
 }
 
 /*
@@ -358,7 +346,7 @@ static int rcu_dynticks_snap(struct rcu_data *rdp)
  */
 static bool rcu_dynticks_in_eqs(int snap)
 {
-	return !(snap & RCU_DYNTICK_CTRL_CTR);
+	return !(snap & 0x1);
 }
 
 /* Return true if the specified CPU is currently idle from an RCU viewpoint.  */
@@ -389,8 +377,7 @@ bool rcu_dynticks_zero_in_eqs(int cpu, int *vp)
 	int snap;
 
 	// If not quiescent, force back to earlier extended quiescent state.
-	snap = atomic_read(&rdp->dynticks) & ~(RCU_DYNTICK_CTRL_MASK |
-					       RCU_DYNTICK_CTRL_CTR);
+	snap = atomic_read(&rdp->dynticks) & ~0x1;
 
 	smp_rmb(); // Order ->dynticks and *vp reads.
 	if (READ_ONCE(*vp))
@@ -398,32 +385,7 @@ bool rcu_dynticks_zero_in_eqs(int cpu, int *vp)
 	smp_rmb(); // Order *vp read and ->dynticks re-read.
 
 	// If still in the same extended quiescent state, we are good!
-	return snap == (atomic_read(&rdp->dynticks) & ~RCU_DYNTICK_CTRL_MASK);
-}
-
-/*
- * Set the special (bottom) bit of the specified CPU so that it
- * will take special action (such as flushing its TLB) on the
- * next exit from an extended quiescent state.  Returns true if
- * the bit was successfully set, or false if the CPU was not in
- * an extended quiescent state.
- */
-bool rcu_eqs_special_set(int cpu)
-{
-	int old;
-	int new;
-	int new_old;
-	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
-
-	new_old = atomic_read(&rdp->dynticks);
-	do {
-		old = new_old;
-		if (old & RCU_DYNTICK_CTRL_CTR)
-			return false;
-		new = old | RCU_DYNTICK_CTRL_MASK;
-		new_old = atomic_cmpxchg(&rdp->dynticks, old, new);
-	} while (new_old != old);
-	return true;
+	return snap == atomic_read(&rdp->dynticks);
 }
 
 /*
@@ -439,13 +401,12 @@ bool rcu_eqs_special_set(int cpu)
  */
 notrace void rcu_momentary_dyntick_idle(void)
 {
-	int special;
+	int seq;
 
 	raw_cpu_write(rcu_data.rcu_need_heavy_qs, false);
-	special = atomic_add_return(2 * RCU_DYNTICK_CTRL_CTR,
-				    &this_cpu_ptr(&rcu_data)->dynticks);
+	seq = rcu_dynticks_inc(2);
 	/* It is illegal to call this from idle state. */
-	WARN_ON_ONCE(!(special & RCU_DYNTICK_CTRL_CTR));
+	WARN_ON_ONCE(!(seq & 0x1));
 	rcu_preempt_deferred_qs(current);
 }
 EXPORT_SYMBOL_GPL(rcu_momentary_dyntick_idle);
@@ -1325,7 +1286,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	 */
 	jtsq = READ_ONCE(jiffies_to_sched_qs);
 	ruqp = per_cpu_ptr(&rcu_data.rcu_urgent_qs, rdp->cpu);
-	rnhqp = &per_cpu(rcu_data.rcu_need_heavy_qs, rdp->cpu);
+	rnhqp = per_cpu_ptr(&rcu_data.rcu_need_heavy_qs, rdp->cpu);
 	if (!READ_ONCE(*rnhqp) &&
 	    (time_after(jiffies, rcu_state.gp_start + jtsq * 2) ||
 	     time_after(jiffies, rcu_state.jiffies_resched) ||
@@ -1772,7 +1733,7 @@ static void rcu_strict_gp_boundary(void *unused)
 /*
  * Initialize a new grace period.  Return false if no grace period required.
  */
-static bool rcu_gp_init(void)
+static noinline_for_stack bool rcu_gp_init(void)
 {
 	unsigned long firstseq;
 	unsigned long flags;
@@ -1966,7 +1927,7 @@ static void rcu_gp_fqs(bool first_time)
 /*
  * Loop doing repeated quiescent-state forcing until the grace period ends.
  */
-static void rcu_gp_fqs_loop(void)
+static noinline_for_stack void rcu_gp_fqs_loop(void)
 {
 	bool first_gp_fqs;
 	int gf = 0;
@@ -1993,8 +1954,8 @@ static void rcu_gp_fqs_loop(void)
 		trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
 				       TPS("fqswait"));
 		WRITE_ONCE(rcu_state.gp_state, RCU_GP_WAIT_FQS);
-		ret = swait_event_idle_timeout_exclusive(
-				rcu_state.gp_wq, rcu_gp_fqs_check_wake(&gf), j);
+		(void)swait_event_idle_timeout_exclusive(rcu_state.gp_wq,
+				 rcu_gp_fqs_check_wake(&gf), j);
 		rcu_gp_torture_wait();
 		WRITE_ONCE(rcu_state.gp_state, RCU_GP_DOING_FQS);
 		/* Locking provides needed memory barriers. */
@@ -2471,9 +2432,6 @@ int rcutree_dead_cpu(unsigned int cpu)
 	WRITE_ONCE(rcu_state.n_online_cpus, rcu_state.n_online_cpus - 1);
 	/* Adjust any no-longer-needed kthreads. */
 	rcu_boost_kthread_setaffinity(rnp, -1);
-	/* Do any needed no-CB deferred wakeups from this CPU. */
-	do_nocb_deferred_wakeup(per_cpu_ptr(&rcu_data, cpu));
-
 	// Stop-machine done, so allow nohz_full to disable tick.
 	tick_dep_clear(TICK_DEP_BIT_RCU);
 	return 0;
@@ -4050,7 +4008,7 @@ void rcu_barrier(void)
 	 */
 	init_completion(&rcu_state.barrier_completion);
 	atomic_set(&rcu_state.barrier_cpu_count, 2);
-	get_online_cpus();
+	cpus_read_lock();
 
 	/*
 	 * Force each CPU with callbacks to register a new callback.
@@ -4081,7 +4039,7 @@ void rcu_barrier(void)
 					  rcu_state.barrier_sequence);
 		}
 	}
-	put_online_cpus();
+	cpus_read_unlock();
 
 	/*
 	 * Now that we have an rcu_barrier_callback() callback on each
@@ -4784,4 +4742,5 @@ void __init rcu_init(void)
 
 #include "tree_stall.h"
 #include "tree_exp.h"
+#include "tree_nocb.h"
 #include "tree_plugin.h"

kernel/rcu/tree_stall.h

@@ -7,6 +7,8 @@
  * Author: Paul E. McKenney <paulmck@linux.ibm.com>
  */
 
+#include <linux/kvm_para.h>
+
 //////////////////////////////////////////////////////////////////////////////
 //
 // Controlling CPU stall warnings, including delay calculation.
@@ -117,17 +119,14 @@ static void panic_on_rcu_stall(void)
 }
 
 /**
- * rcu_cpu_stall_reset - prevent further stall warnings in current grace period
- *
- * Set the stall-warning timeout way off into the future, thus preventing
- * any RCU CPU stall-warning messages from appearing in the current set of
- * RCU grace periods.
+ * rcu_cpu_stall_reset - restart stall-warning timeout for current grace period
  *
  * The caller must disable hard irqs.
  */
 void rcu_cpu_stall_reset(void)
 {
-	WRITE_ONCE(rcu_state.jiffies_stall, jiffies + ULONG_MAX / 2);
+	WRITE_ONCE(rcu_state.jiffies_stall,
+		   jiffies + rcu_jiffies_till_stall_check());
 }
 
 //////////////////////////////////////////////////////////////////////////////
@@ -267,8 +266,10 @@ static int rcu_print_task_stall(struct rcu_node *rnp, unsigned long flags)
 	struct task_struct *ts[8];
 
 	lockdep_assert_irqs_disabled();
-	if (!rcu_preempt_blocked_readers_cgp(rnp))
+	if (!rcu_preempt_blocked_readers_cgp(rnp)) {
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		return 0;
+	}
 	pr_err("\tTasks blocked on level-%d rcu_node (CPUs %d-%d):",
 	       rnp->level, rnp->grplo, rnp->grphi);
 	t = list_entry(rnp->gp_tasks->prev,
@@ -280,8 +281,8 @@ static int rcu_print_task_stall(struct rcu_node *rnp, unsigned long flags)
 			break;
 	}
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-	for (i--; i; i--) {
-		t = ts[i];
+	while (i) {
+		t = ts[--i];
 		if (!try_invoke_on_locked_down_task(t, check_slow_task, &rscr))
 			pr_cont(" P%d", t->pid);
 		else
@@ -350,7 +351,7 @@ static void rcu_dump_cpu_stacks(void)
 
 static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
 {
-	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
+	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
 
 	sprintf(cp, "last_accelerate: %04lx/%04lx dyntick_enabled: %d",
 		rdp->last_accelerate & 0xffff, jiffies & 0xffff,
@@ -464,9 +465,10 @@ static void rcu_check_gp_kthread_starvation(void)
 		pr_err("%s kthread starved for %ld jiffies! g%ld f%#x %s(%d) ->state=%#x ->cpu=%d\n",
 		       rcu_state.name, j,
 		       (long)rcu_seq_current(&rcu_state.gp_seq),
-		       data_race(rcu_state.gp_flags),
-		       gp_state_getname(rcu_state.gp_state), rcu_state.gp_state,
-		       gpk ? gpk->__state : ~0, cpu);
+		       data_race(READ_ONCE(rcu_state.gp_flags)),
+		       gp_state_getname(rcu_state.gp_state),
+		       data_race(READ_ONCE(rcu_state.gp_state)),
+		       gpk ? data_race(READ_ONCE(gpk->__state)) : ~0, cpu);
 		if (gpk) {
 			pr_err("\tUnless %s kthread gets sufficient CPU time, OOM is now expected behavior.\n", rcu_state.name);
 			pr_err("RCU grace-period kthread stack dump:\n");
@@ -509,7 +511,7 @@ static void rcu_check_gp_kthread_expired_fqs_timer(void)
 		       (long)rcu_seq_current(&rcu_state.gp_seq),
 		       data_race(rcu_state.gp_flags),
 		       gp_state_getname(RCU_GP_WAIT_FQS), RCU_GP_WAIT_FQS,
-		       gpk->__state);
+		       data_race(READ_ONCE(gpk->__state)));
 		pr_err("\tPossible timer handling issue on cpu=%d timer-softirq=%u\n",
 		       cpu, kstat_softirqs_cpu(TIMER_SOFTIRQ, cpu));
 	}
@@ -568,11 +570,11 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps)
 			pr_err("INFO: Stall ended before state dump start\n");
 		} else {
 			j = jiffies;
-			gpa = data_race(rcu_state.gp_activity);
+			gpa = data_race(READ_ONCE(rcu_state.gp_activity));
 			pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld, root ->qsmask %#lx\n",
 			       rcu_state.name, j - gpa, j, gpa,
-			       data_race(jiffies_till_next_fqs),
-			       rcu_get_root()->qsmask);
+			       data_race(READ_ONCE(jiffies_till_next_fqs)),
+			       data_race(READ_ONCE(rcu_get_root()->qsmask)));
 		}
 	}
 	/* Rewrite if needed in case of slow consoles. */
@@ -646,6 +648,7 @@ static void print_cpu_stall(unsigned long gps)
 
 static void check_cpu_stall(struct rcu_data *rdp)
 {
+	bool didstall = false;
 	unsigned long gs1;
 	unsigned long gs2;
 	unsigned long gps;
@@ -691,24 +694,46 @@ static void check_cpu_stall(struct rcu_data *rdp)
 	    ULONG_CMP_GE(gps, js))
 		return; /* No stall or GP completed since entering function. */
 	rnp = rdp->mynode;
-	jn = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
+	jn = jiffies + ULONG_MAX / 2;
 	if (rcu_gp_in_progress() &&
 	    (READ_ONCE(rnp->qsmask) & rdp->grpmask) &&
 	    cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) {
 
+		/*
+		 * If a virtual machine is stopped by the host it can look to
+		 * the watchdog like an RCU stall. Check to see if the host
+		 * stopped the vm.
+		 */
+		if (kvm_check_and_clear_guest_paused())
+			return;
+
 		/* We haven't checked in, so go dump stack. */
 		print_cpu_stall(gps);
 		if (READ_ONCE(rcu_cpu_stall_ftrace_dump))
 			rcu_ftrace_dump(DUMP_ALL);
+		didstall = true;
 
 	} else if (rcu_gp_in_progress() &&
 		   ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY) &&
 		   cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) {
 
+		/*
+		 * If a virtual machine is stopped by the host it can look to
+		 * the watchdog like an RCU stall. Check to see if the host
+		 * stopped the vm.
+		 */
+		if (kvm_check_and_clear_guest_paused())
+			return;
+
 		/* They had a few time units to dump stack, so complain. */
 		print_other_cpu_stall(gs2, gps);
 		if (READ_ONCE(rcu_cpu_stall_ftrace_dump))
 			rcu_ftrace_dump(DUMP_ALL);
+		didstall = true;
+	}
+	if (didstall && READ_ONCE(rcu_state.jiffies_stall) == jn) {
+		jn = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
+		WRITE_ONCE(rcu_state.jiffies_stall, jn);
 	}
 }
 
@@ -742,7 +767,7 @@ bool rcu_check_boost_fail(unsigned long gp_state, int *cpup)
 
 	rcu_for_each_leaf_node(rnp) {
 		if (!cpup) {
-			if (READ_ONCE(rnp->qsmask)) {
+			if (data_race(READ_ONCE(rnp->qsmask))) {
 				return false;
 			} else {
 				if (READ_ONCE(rnp->gp_tasks))
@@ -791,32 +816,34 @@ void show_rcu_gp_kthreads(void)
 	struct task_struct *t = READ_ONCE(rcu_state.gp_kthread);
 
 	j = jiffies;
-	ja = j - data_race(rcu_state.gp_activity);
-	jr = j - data_race(rcu_state.gp_req_activity);
-	js = j - data_race(rcu_state.gp_start);
-	jw = j - data_race(rcu_state.gp_wake_time);
+	ja = j - data_race(READ_ONCE(rcu_state.gp_activity));
+	jr = j - data_race(READ_ONCE(rcu_state.gp_req_activity));
+	js = j - data_race(READ_ONCE(rcu_state.gp_start));
+	jw = j - data_race(READ_ONCE(rcu_state.gp_wake_time));
 	pr_info("%s: wait state: %s(%d) ->state: %#x ->rt_priority %u delta ->gp_start %lu ->gp_activity %lu ->gp_req_activity %lu ->gp_wake_time %lu ->gp_wake_seq %ld ->gp_seq %ld ->gp_seq_needed %ld ->gp_max %lu ->gp_flags %#x\n",
 		rcu_state.name, gp_state_getname(rcu_state.gp_state),
-		rcu_state.gp_state, t ? t->__state : 0x1ffff, t ? t->rt_priority : 0xffU,
-		js, ja, jr, jw, (long)data_race(rcu_state.gp_wake_seq),
-		(long)data_race(rcu_state.gp_seq),
-		(long)data_race(rcu_get_root()->gp_seq_needed),
-		data_race(rcu_state.gp_max),
-		data_race(rcu_state.gp_flags));
+		data_race(READ_ONCE(rcu_state.gp_state)),
+		t ? data_race(READ_ONCE(t->__state)) : 0x1ffff, t ? t->rt_priority : 0xffU,
+		js, ja, jr, jw, (long)data_race(READ_ONCE(rcu_state.gp_wake_seq)),
+		(long)data_race(READ_ONCE(rcu_state.gp_seq)),
+		(long)data_race(READ_ONCE(rcu_get_root()->gp_seq_needed)),
+		data_race(READ_ONCE(rcu_state.gp_max)),
+		data_race(READ_ONCE(rcu_state.gp_flags)));
 	rcu_for_each_node_breadth_first(rnp) {
 		if (ULONG_CMP_GE(READ_ONCE(rcu_state.gp_seq), READ_ONCE(rnp->gp_seq_needed)) &&
-		    !data_race(rnp->qsmask) && !data_race(rnp->boost_tasks) &&
-		    !data_race(rnp->exp_tasks) && !data_race(rnp->gp_tasks))
+		    !data_race(READ_ONCE(rnp->qsmask)) && !data_race(READ_ONCE(rnp->boost_tasks)) &&
+		    !data_race(READ_ONCE(rnp->exp_tasks)) && !data_race(READ_ONCE(rnp->gp_tasks)))
 			continue;
 		pr_info("\trcu_node %d:%d ->gp_seq %ld ->gp_seq_needed %ld ->qsmask %#lx %c%c%c%c ->n_boosts %ld\n",
 			rnp->grplo, rnp->grphi,
-			(long)data_race(rnp->gp_seq), (long)data_race(rnp->gp_seq_needed),
-			data_race(rnp->qsmask),
-			".b"[!!data_race(rnp->boost_kthread_task)],
-			".B"[!!data_race(rnp->boost_tasks)],
-			".E"[!!data_race(rnp->exp_tasks)],
-			".G"[!!data_race(rnp->gp_tasks)],
-			data_race(rnp->n_boosts));
+			(long)data_race(READ_ONCE(rnp->gp_seq)),
+			(long)data_race(READ_ONCE(rnp->gp_seq_needed)),
+			data_race(READ_ONCE(rnp->qsmask)),
+			".b"[!!data_race(READ_ONCE(rnp->boost_kthread_task))],
+			".B"[!!data_race(READ_ONCE(rnp->boost_tasks))],
+			".E"[!!data_race(READ_ONCE(rnp->exp_tasks))],
+			".G"[!!data_race(READ_ONCE(rnp->gp_tasks))],
+			data_race(READ_ONCE(rnp->n_boosts)));
 		if (!rcu_is_leaf_node(rnp))
 			continue;
 		for_each_leaf_node_possible_cpu(rnp, cpu) {
@@ -826,12 +853,12 @@ void show_rcu_gp_kthreads(void)
 					 READ_ONCE(rdp->gp_seq_needed)))
 				continue;
 			pr_info("\tcpu %d ->gp_seq_needed %ld\n",
-				cpu, (long)data_race(rdp->gp_seq_needed));
+				cpu, (long)data_race(READ_ONCE(rdp->gp_seq_needed)));
 		}
 	}
 	for_each_possible_cpu(cpu) {
 		rdp = per_cpu_ptr(&rcu_data, cpu);
-		cbs += data_race(rdp->n_cbs_invoked);
+		cbs += data_race(READ_ONCE(rdp->n_cbs_invoked));
 		if (rcu_segcblist_is_offloaded(&rdp->cblist))
 			show_rcu_nocb_state(rdp);
 	}
@@ -913,11 +940,11 @@ void rcu_fwd_progress_check(unsigned long j)
 
 	if (rcu_gp_in_progress()) {
 		pr_info("%s: GP age %lu jiffies\n",
-			__func__, jiffies - rcu_state.gp_start);
+			__func__, jiffies - data_race(READ_ONCE(rcu_state.gp_start)));
 		show_rcu_gp_kthreads();
 	} else {
 		pr_info("%s: Last GP end %lu jiffies ago\n",
-			__func__, jiffies - rcu_state.gp_end);
+			__func__, jiffies - data_race(READ_ONCE(rcu_state.gp_end)));
 		preempt_disable();
 		rdp = this_cpu_ptr(&rcu_data);
 		rcu_check_gp_start_stall(rdp->mynode, rdp, j);

kernel/scftorture.c

@@ -64,6 +64,7 @@ torture_param(bool, use_cpus_read_lock, 0, "Use cpus_read_lock() to exclude CPU
 torture_param(int, verbose, 0, "Enable verbose debugging printk()s");
 torture_param(int, weight_resched, -1, "Testing weight for resched_cpu() operations.");
 torture_param(int, weight_single, -1, "Testing weight for single-CPU no-wait operations.");
+torture_param(int, weight_single_rpc, -1, "Testing weight for single-CPU RPC operations.");
 torture_param(int, weight_single_wait, -1, "Testing weight for single-CPU operations.");
 torture_param(int, weight_many, -1, "Testing weight for multi-CPU no-wait operations.");
 torture_param(int, weight_many_wait, -1, "Testing weight for multi-CPU operations.");
@@ -86,6 +87,8 @@ struct scf_statistics {
 	long long n_resched;
 	long long n_single;
 	long long n_single_ofl;
+	long long n_single_rpc;
+	long long n_single_rpc_ofl;
 	long long n_single_wait;
 	long long n_single_wait_ofl;
 	long long n_many;
@@ -101,14 +104,17 @@ static DEFINE_PER_CPU(long long, scf_invoked_count);
 // Data for random primitive selection
 #define SCF_PRIM_RESCHED	0
 #define SCF_PRIM_SINGLE		1
-#define SCF_PRIM_MANY		2
-#define SCF_PRIM_ALL		3
-#define SCF_NPRIMS		7 // Need wait and no-wait versions of each,
-				  //  except for SCF_PRIM_RESCHED.
+#define SCF_PRIM_SINGLE_RPC	2
+#define SCF_PRIM_MANY		3
+#define SCF_PRIM_ALL		4
+#define SCF_NPRIMS		8 // Need wait and no-wait versions of each,
+				  //  except for SCF_PRIM_RESCHED and
+				  //  SCF_PRIM_SINGLE_RPC.
 
 static char *scf_prim_name[] = {
 	"resched_cpu",
 	"smp_call_function_single",
+	"smp_call_function_single_rpc",
 	"smp_call_function_many",
 	"smp_call_function",
 };
@@ -128,6 +134,8 @@ struct scf_check {
 	bool scfc_out;
 	int scfc_cpu; // -1 for not _single().
 	bool scfc_wait;
+	bool scfc_rpc;
+	struct completion scfc_completion;
 };
 
 // Use to wait for all threads to start.
@@ -158,6 +166,7 @@ static void scf_torture_stats_print(void)
 		scfs.n_resched += scf_stats_p[i].n_resched;
 		scfs.n_single += scf_stats_p[i].n_single;
 		scfs.n_single_ofl += scf_stats_p[i].n_single_ofl;
+		scfs.n_single_rpc += scf_stats_p[i].n_single_rpc;
 		scfs.n_single_wait += scf_stats_p[i].n_single_wait;
 		scfs.n_single_wait_ofl += scf_stats_p[i].n_single_wait_ofl;
 		scfs.n_many += scf_stats_p[i].n_many;
@@ -168,9 +177,10 @@ static void scf_torture_stats_print(void)
 	if (atomic_read(&n_errs) || atomic_read(&n_mb_in_errs) ||
 	    atomic_read(&n_mb_out_errs) || atomic_read(&n_alloc_errs))
 		bangstr = "!!! ";
-	pr_alert("%s %sscf_invoked_count %s: %lld resched: %lld single: %lld/%lld single_ofl: %lld/%lld many: %lld/%lld all: %lld/%lld ",
+	pr_alert("%s %sscf_invoked_count %s: %lld resched: %lld single: %lld/%lld single_ofl: %lld/%lld single_rpc: %lld single_rpc_ofl: %lld many: %lld/%lld all: %lld/%lld ",
 		 SCFTORT_FLAG, bangstr, isdone ? "VER" : "ver", invoked_count, scfs.n_resched,
 		 scfs.n_single, scfs.n_single_wait, scfs.n_single_ofl, scfs.n_single_wait_ofl,
+		 scfs.n_single_rpc, scfs.n_single_rpc_ofl,
 		 scfs.n_many, scfs.n_many_wait, scfs.n_all, scfs.n_all_wait);
 	torture_onoff_stats();
 	pr_cont("ste: %d stnmie: %d stnmoe: %d staf: %d\n", atomic_read(&n_errs),
@@ -282,10 +292,13 @@ static void scf_handler(void *scfc_in)
 out:
 	if (unlikely(!scfcp))
 		return;
-	if (scfcp->scfc_wait)
+	if (scfcp->scfc_wait) {
 		WRITE_ONCE(scfcp->scfc_out, true);
-	else
+		if (scfcp->scfc_rpc)
+			complete(&scfcp->scfc_completion);
+	} else {
 		kfree(scfcp);
+	}
 }
 
 // As above, but check for correct CPU.
@@ -319,6 +332,7 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra
 			scfcp->scfc_cpu = -1;
 			scfcp->scfc_wait = scfsp->scfs_wait;
 			scfcp->scfc_out = false;
+			scfcp->scfc_rpc = false;
 		}
 	}
 	switch (scfsp->scfs_prim) {
@@ -350,6 +364,34 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra
 			scfcp = NULL;
 		}
 		break;
+	case SCF_PRIM_SINGLE_RPC:
+		if (!scfcp)
+			break;
+		cpu = torture_random(trsp) % nr_cpu_ids;
+		scfp->n_single_rpc++;
+		scfcp->scfc_cpu = cpu;
+		scfcp->scfc_wait = true;
+		init_completion(&scfcp->scfc_completion);
+		scfcp->scfc_rpc = true;
+		barrier(); // Prevent race-reduction compiler optimizations.
+		scfcp->scfc_in = true;
+		ret = smp_call_function_single(cpu, scf_handler_1, (void *)scfcp, 0);
+		if (!ret) {
+			if (use_cpus_read_lock)
+				cpus_read_unlock();
+			else
+				preempt_enable();
+			wait_for_completion(&scfcp->scfc_completion);
+			if (use_cpus_read_lock)
+				cpus_read_lock();
+			else
+				preempt_disable();
+		} else {
+			scfp->n_single_rpc_ofl++;
+			kfree(scfcp);
+			scfcp = NULL;
+		}
+		break;
 	case SCF_PRIM_MANY:
 		if (scfsp->scfs_wait)
 			scfp->n_many_wait++;
@@ -379,10 +421,12 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra
 	}
 	if (scfcp && scfsp->scfs_wait) {
 		if (WARN_ON_ONCE((num_online_cpus() > 1 || scfsp->scfs_prim == SCF_PRIM_SINGLE) &&
-				 !scfcp->scfc_out))
+				 !scfcp->scfc_out)) {
+			pr_warn("%s: Memory-ordering failure, scfs_prim: %d.\n", __func__, scfsp->scfs_prim);
 			atomic_inc(&n_mb_out_errs); // Leak rather than trash!
-		else
+		} else {
 			kfree(scfcp);
+		}
 		barrier(); // Prevent race-reduction compiler optimizations.
 	}
 	if (use_cpus_read_lock)
@@ -453,8 +497,8 @@ static void
 scftorture_print_module_parms(const char *tag)
 {
 	pr_alert(SCFTORT_FLAG
-		 "--- %s:  verbose=%d holdoff=%d longwait=%d nthreads=%d onoff_holdoff=%d onoff_interval=%d shutdown_secs=%d stat_interval=%d stutter=%d use_cpus_read_lock=%d, weight_resched=%d, weight_single=%d, weight_single_wait=%d, weight_many=%d, weight_many_wait=%d, weight_all=%d, weight_all_wait=%d\n", tag,
-		 verbose, holdoff, longwait, nthreads, onoff_holdoff, onoff_interval, shutdown, stat_interval, stutter, use_cpus_read_lock, weight_resched, weight_single, weight_single_wait, weight_many, weight_many_wait, weight_all, weight_all_wait);
+		 "--- %s:  verbose=%d holdoff=%d longwait=%d nthreads=%d onoff_holdoff=%d onoff_interval=%d shutdown_secs=%d stat_interval=%d stutter=%d use_cpus_read_lock=%d, weight_resched=%d, weight_single=%d, weight_single_rpc=%d, weight_single_wait=%d, weight_many=%d, weight_many_wait=%d, weight_all=%d, weight_all_wait=%d\n", tag,
+		 verbose, holdoff, longwait, nthreads, onoff_holdoff, onoff_interval, shutdown, stat_interval, stutter, use_cpus_read_lock, weight_resched, weight_single, weight_single_rpc, weight_single_wait, weight_many, weight_many_wait, weight_all, weight_all_wait);
 }
 
 static void scf_cleanup_handler(void *unused)
@@ -469,7 +513,7 @@ static void scf_torture_cleanup(void)
 		return;
 
 	WRITE_ONCE(scfdone, true);
-	if (nthreads)
+	if (nthreads && scf_stats_p)
 		for (i = 0; i < nthreads; i++)
 			torture_stop_kthread("scftorture_invoker", scf_stats_p[i].task);
 	else
@@ -497,6 +541,7 @@ static int __init scf_torture_init(void)
 	int firsterr = 0;
 	unsigned long weight_resched1 = weight_resched;
 	unsigned long weight_single1 = weight_single;
+	unsigned long weight_single_rpc1 = weight_single_rpc;
 	unsigned long weight_single_wait1 = weight_single_wait;
 	unsigned long weight_many1 = weight_many;
 	unsigned long weight_many_wait1 = weight_many_wait;
@@ -508,11 +553,13 @@ static int __init scf_torture_init(void)
 
 	scftorture_print_module_parms("Start of test");
 
-	if (weight_resched == -1 && weight_single == -1 && weight_single_wait == -1 &&
+	if (weight_resched == -1 &&
+	    weight_single == -1 && weight_single_rpc == -1 && weight_single_wait == -1 &&
 	    weight_many == -1 && weight_many_wait == -1 &&
 	    weight_all == -1 && weight_all_wait == -1) {
 		weight_resched1 = 2 * nr_cpu_ids;
 		weight_single1 = 2 * nr_cpu_ids;
+		weight_single_rpc1 = 2 * nr_cpu_ids;
 		weight_single_wait1 = 2 * nr_cpu_ids;
 		weight_many1 = 2;
 		weight_many_wait1 = 2;
@@ -523,6 +570,8 @@ static int __init scf_torture_init(void)
 			weight_resched1 = 0;
 		if (weight_single == -1)
 			weight_single1 = 0;
+		if (weight_single_rpc == -1)
+			weight_single_rpc1 = 0;
 		if (weight_single_wait == -1)
 			weight_single_wait1 = 0;
 		if (weight_many == -1)
@@ -534,7 +583,7 @@ static int __init scf_torture_init(void)
 		if (weight_all_wait == -1)
 			weight_all_wait1 = 0;
 	}
-	if (weight_single1 == 0 && weight_single_wait1 == 0 &&
+	if (weight_single1 == 0 && weight_single_rpc1 == 0 && weight_single_wait1 == 0 &&
 	    weight_many1 == 0 && weight_many_wait1 == 0 &&
 	    weight_all1 == 0 && weight_all_wait1 == 0) {
 		VERBOSE_SCFTORTOUT_ERRSTRING("all zero weights makes no sense");
@@ -546,6 +595,7 @@ static int __init scf_torture_init(void)
 	else if (weight_resched1)
 		VERBOSE_SCFTORTOUT_ERRSTRING("built as module, weight_resched ignored");
 	scf_sel_add(weight_single1, SCF_PRIM_SINGLE, false);
+	scf_sel_add(weight_single_rpc1, SCF_PRIM_SINGLE_RPC, true);
 	scf_sel_add(weight_single_wait1, SCF_PRIM_SINGLE, true);
 	scf_sel_add(weight_many1, SCF_PRIM_MANY, false);
 	scf_sel_add(weight_many_wait1, SCF_PRIM_MANY, true);

kernel/sched/core.c

@@ -7781,6 +7781,17 @@ int __sched __cond_resched(void)
 		preempt_schedule_common();
 		return 1;
 	}
+	/*
+	 * In preemptible kernels, ->rcu_read_lock_nesting tells the tick
+	 * whether the current CPU is in an RCU read-side critical section,
+	 * so the tick can report quiescent states even for CPUs looping
+	 * in kernel context.  In contrast, in non-preemptible kernels,
+	 * RCU readers leave no in-memory hints, which means that CPU-bound
+	 * processes executing in kernel context might never report an
+	 * RCU quiescent state.  Therefore, the following code causes
+	 * cond_resched() to report a quiescent state, but only when RCU
+	 * is in urgent need of one.
+	 */
 #ifndef CONFIG_PREEMPT_RCU
 	rcu_all_qs();
 #endif

kernel/torture.c

@@ -521,11 +521,11 @@ static void torture_shuffle_tasks(void)
 	struct shuffle_task *stp;
 
 	cpumask_setall(shuffle_tmp_mask);
-	get_online_cpus();
+	cpus_read_lock();
 
 	/* No point in shuffling if there is only one online CPU (ex: UP) */
 	if (num_online_cpus() == 1) {
-		put_online_cpus();
+		cpus_read_unlock();
 		return;
 	}
 
@@ -541,7 +541,7 @@ static void torture_shuffle_tasks(void)
 		set_cpus_allowed_ptr(stp->st_t, shuffle_tmp_mask);
 	mutex_unlock(&shuffle_task_mutex);
 
-	put_online_cpus();
+	cpus_read_unlock();
 }
 
 /* Shuffle tasks across CPUs, with the intent of allowing each CPU in the

tools/include/nolibc/nolibc.h

@@ -1031,7 +1031,7 @@ struct sys_stat_struct {
  *     scall32-o32.S in the kernel sources.
  *   - the system call is performed by calling "syscall"
  *   - syscall return comes in v0, and register a3 needs to be checked to know
- *     if an error occured, in which case errno is in v0.
+ *     if an error occurred, in which case errno is in v0.
  *   - the arguments are cast to long and assigned into the target registers
  *     which are then simply passed as registers to the asm code, so that we
  *     don't have to experience issues with register constraints.
@@ -2243,6 +2243,19 @@ unsigned int sleep(unsigned int seconds)
 		return 0;
 }
 
+static __attribute__((unused))
+int msleep(unsigned int msecs)
+{
+	struct timeval my_timeval = { msecs / 1000, (msecs % 1000) * 1000 };
+
+	if (sys_select(0, 0, 0, 0, &my_timeval) < 0)
+		return (my_timeval.tv_sec * 1000) +
+			(my_timeval.tv_usec / 1000) +
+			!!(my_timeval.tv_usec % 1000);
+	else
+		return 0;
+}
+
 static __attribute__((unused))
 int stat(const char *path, struct stat *buf)
 {

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

@@ -68,16 +68,12 @@ do
 	cpumask=`awk -v cpus="$cpus" -v me=$me -v n=$n 'BEGIN {
 		srand(n + me + systime());
 		ncpus = split(cpus, ca);
-		curcpu = ca[int(rand() * ncpus + 1)];
-		z = "";
-		for (i = 1; 4 * i <= curcpu; i++)
-			z = z "0";
-		print "0x" 2 ^ (curcpu % 4) z;
+		print ca[int(rand() * ncpus + 1)];
 	}' < /dev/null`
 	n=$(($n+1))
-	if ! taskset -p $cpumask $$ > /dev/null 2>&1
+	if ! taskset -c -p $cpumask $$ > /dev/null 2>&1
 	then
-		echo taskset failure: '"taskset -p ' $cpumask $$ '"'
+		echo taskset failure: '"taskset -c -p ' $cpumask $$ '"'
 		exit 1
 	fi
 

tools/testing/selftests/rcutorture/bin/kcsan-collapse.sh

@@ -14,7 +14,7 @@ if test -z "$TORTURE_KCONFIG_KCSAN_ARG"
 then
 	exit 0
 fi
-cat $1/*/console.log |
+find $1 -name console.log -exec cat {} \; |
 	grep "BUG: KCSAN: " |
 	sed -e 's/^\[[^]]*] //' |
 	sort |

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

@@ -142,7 +142,7 @@ then
 	echo "Cannot copy from $oldrun to $rundir."
 	usage
 fi
-rm -f "$rundir"/*/{console.log,console.log.diags,qemu_pid,qemu-retval,Warnings,kvm-test-1-run.sh.out,kvm-test-1-run-qemu.sh.out,vmlinux} "$rundir"/log
+rm -f "$rundir"/*/{console.log,console.log.diags,qemu_pid,qemu-pid,qemu-retval,Warnings,kvm-test-1-run.sh.out,kvm-test-1-run-qemu.sh.out,vmlinux} "$rundir"/log
 touch "$rundir/log"
 echo $scriptname $args | tee -a "$rundir/log"
 echo $oldrun > "$rundir/re-run"
@@ -179,6 +179,6 @@ if test -n "$dryrun"
 then
 	echo ---- Dryrun complete, directory: $rundir | tee -a "$rundir/log"
 else
-	( cd "$rundir"; sh $T/runbatches.sh )
+	( cd "$rundir"; sh $T/runbatches.sh ) | tee -a "$rundir/log"
 	kvm-end-run-stats.sh "$rundir" "$starttime"
 fi

tools/testing/selftests/rcutorture/bin/kvm-assign-cpus.sh

+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Produce awk statements roughly depicting the system's CPU and cache
+# layout.  If the required information is not available, produce
+# error messages as awk comments.  Successful exit regardless.
+#
+# Usage: kvm-assign-cpus.sh /path/to/sysfs
+
+T=/tmp/kvm-assign-cpus.sh.$$
+trap 'rm -rf $T' 0 2
+mkdir $T
+
+sysfsdir=${1-/sys/devices/system/node}
+if ! cd "$sysfsdir" > $T/msg 2>&1
+then
+	sed -e 's/^/# /' < $T/msg
+	exit 0
+fi
+nodelist="`ls -d node*`"
+for i in node*
+do
+	if ! test -d $i/
+	then
+		echo "# Not a directory: $sysfsdir/node*"
+		exit 0
+	fi
+	for j in $i/cpu*/cache/index*
+	do
+		if ! test -d $j/
+		then
+			echo "# Not a directory: $sysfsdir/$j"
+			exit 0
+		else
+			break
+		fi
+	done
+	indexlist="`ls -d $i/cpu* | grep 'cpu[0-9][0-9]*' | head -1 | sed -e 's,^.*$,ls -d &/cache/index*,' | sh | sed -e 's,^.*/,,'`"
+	break
+done
+for i in node*/cpu*/cache/index*/shared_cpu_list
+do
+	if ! test -f $i
+	then
+		echo "# Not a file: $sysfsdir/$i"
+		exit 0
+	else
+		break
+	fi
+done
+firstshared=
+for i in $indexlist
+do
+	rm -f $T/cpulist
+	for n in node*
+	do
+		f="$n/cpu*/cache/$i/shared_cpu_list"
+		if ! cat $f > $T/msg 2>&1
+		then
+			sed -e 's/^/# /' < $T/msg
+			exit 0
+		fi
+		cat $f >> $T/cpulist
+	done
+	if grep -q '[-,]' $T/cpulist
+	then
+		if test -z "$firstshared"
+		then
+			firstshared="$i"
+		fi
+	fi
+done
+if test -z "$firstshared"
+then
+	splitindex="`echo $indexlist | sed -e 's/ .*$//'`"
+else
+	splitindex="$firstshared"
+fi
+nodenum=0
+for n in node*
+do
+	cat $n/cpu*/cache/$splitindex/shared_cpu_list | sort -u -k1n |
+	awk -v nodenum="$nodenum" '
+	BEGIN {
+		idx = 0;
+	}
+
+	{
+		nlists = split($0, cpulists, ",");
+		for (i = 1; i <= nlists; i++) {
+			listsize = split(cpulists[i], cpus, "-");
+			if (listsize == 1)
+				cpus[2] = cpus[1];
+			for (j = cpus[1]; j <= cpus[2]; j++) {
+				print "cpu[" nodenum "][" idx "] = " j ";";
+				idx++;
+			}
+		}
+	}
+
+	END {
+		print "nodecpus[" nodenum "] = " idx ";";
+	}'
+	nodenum=`expr $nodenum + 1`
+done
+echo "numnodes = $nodenum;"

tools/testing/selftests/rcutorture/bin/kvm-get-cpus-script.sh

+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Create an awk script that takes as input numbers of CPUs and outputs
+# lists of CPUs, one per line in both cases.
+#
+# Usage: kvm-get-cpus-script.sh /path/to/cpu/arrays /path/to/put/script [ /path/to/state ]
+#
+# The CPU arrays are output by kvm-assign-cpus.sh, and are valid awk
+# statements initializing the variables describing the system's topology.
+#
+# The optional state is input by this script (if the file exists and is
+# non-empty), and can also be output by this script.
+
+cpuarrays="${1-/sys/devices/system/node}"
+scriptfile="${2}"
+statefile="${3}"
+
+if ! test -f "$cpuarrays"
+then
+	echo "File not found: $cpuarrays" 1>&2
+	exit 1
+fi
+scriptdir="`dirname "$scriptfile"`"
+if ! test -d "$scriptdir" || ! test -x "$scriptdir" || ! test -w "$scriptdir"
+then
+	echo "Directory not usable for script output: $scriptdir"
+	exit 1
+fi
+
+cat << '___EOF___' > "$scriptfile"
+BEGIN {
+___EOF___
+cat "$cpuarrays" >> "$scriptfile"
+if test -r "$statefile"
+then
+	cat "$statefile" >> "$scriptfile"
+fi
+cat << '___EOF___' >> "$scriptfile"
+}
+
+# Do we have the system architecture to guide CPU affinity?
+function gotcpus()
+{
+	return numnodes != "";
+}
+
+# Return a comma-separated list of the next n CPUs.
+function nextcpus(n,  i, s)
+{
+	for (i = 0; i < n; i++) {
+		if (nodecpus[curnode] == "")
+			curnode = 0;
+		if (cpu[curnode][curcpu[curnode]] == "")
+			curcpu[curnode] = 0;
+		if (s != "")
+			s = s ",";
+		s = s cpu[curnode][curcpu[curnode]];
+		curcpu[curnode]++;
+		curnode++
+	}
+	return s;
+}
+
+# Dump out the current node/CPU state so that a later invocation of this
+# script can continue where this one left off.  Of course, this only works
+# when a state file was specified and where there was valid sysfs state.
+# Returns 1 if the state was dumped, 0 otherwise.
+#
+# Dumping the state for one system configuration and loading it into
+# another isn't likely to do what you want, whatever that might be.
+function dumpcpustate(  i, fn)
+{
+___EOF___
+echo '	fn = "'"$statefile"'";' >> $scriptfile
+cat << '___EOF___' >> "$scriptfile"
+	if (fn != "" && gotcpus()) {
+		print "curnode = " curnode ";" > fn;
+		for (i = 0; i < numnodes; i++)
+			if (curcpu[i] != "")
+				print "curcpu[" i "] = " curcpu[i] ";" >> fn;
+		return 1;
+	}
+	if (fn != "")
+		print "# No CPU state to dump." > fn;
+	return 0;
+}
+___EOF___

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

@@ -25,7 +25,7 @@ then
 	echo "$configfile -------"
 else
 	title="$configfile ------- $ncs acquisitions/releases"
-	dur=`sed -e 's/^.* locktorture.shutdown_secs=//' -e 's/ .*$//' < $i/qemu-cmd 2> /dev/null`
+	dur=`grep -v '^#' $i/qemu-cmd | sed -e 's/^.* locktorture.shutdown_secs=//' -e 's/ .*$//' 2> /dev/null`
 	if test -z "$dur"
 	then
 		:

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

@@ -25,7 +25,7 @@ if test -z "$nscfs"
 then
 	echo "$configfile ------- "
 else
-	dur="`sed -e 's/^.* scftorture.shutdown_secs=//' -e 's/ .*$//' < $i/qemu-cmd 2> /dev/null`"
+	dur="`grep -v '^#' $i/qemu-cmd | sed -e 's/^.* scftorture.shutdown_secs=//' -e 's/ .*$//' 2> /dev/null`"
 	if test -z "$dur"
 	then
 		rate=""

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

@@ -74,7 +74,10 @@ do
 	done
 	if test -f "$rd/kcsan.sum"
 	then
-		if grep -q CONFIG_KCSAN=y $T
+		if ! test -f $T
+		then
+			:
+		elif grep -q CONFIG_KCSAN=y $T
 		then
 			echo "Compiler or architecture does not support KCSAN!"
 			echo Did you forget to switch your compiler with '--kmake-arg CC=<cc-that-supports-kcsan>'?

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

+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Periodically scan a directory tree to prevent files from being reaped
+# by systemd and friends on long runs.
+#
+# Usage: kvm-remote-noreap.sh pathname
+#
+# Copyright (C) 2021 Facebook, Inc.
+#
+# Authors: Paul E. McKenney <paulmck@kernel.org>
+
+pathname="$1"
+if test "$pathname" = ""
+then
+	echo Usage: kvm-remote-noreap.sh pathname
+	exit 1
+fi
+if ! test -d "$pathname"
+then
+	echo  Usage: kvm-remote-noreap.sh pathname
+	echo "       pathname must be a directory."
+	exit 2
+fi
+
+while test -d "$pathname"
+do
+	find "$pathname" -type f -exec touch -c {} \; > /dev/null 2>&1
+	sleep 30
+done

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

@@ -124,10 +124,12 @@ awk < "$rundir"/scenarios -v dest="$T/bin" -v rundir="$rundir" '
 	n = $1;
 	sub(/\./, "", n);
 	fn = dest "/kvm-remote-" n ".sh"
+	print "kvm-remote-noreap.sh " rundir " &" > fn;
 	scenarios = "";
 	for (i = 2; i <= NF; i++)
 		scenarios = scenarios " " $i;
-	print "kvm-test-1-run-batch.sh" scenarios > fn;
+	print "kvm-test-1-run-batch.sh" scenarios >> fn;
+	print "sync" >> fn;
 	print "rm " rundir "/remote.run" >> fn;
 }'
 chmod +x $T/bin/kvm-remote-*.sh
@@ -172,11 +174,20 @@ checkremotefile () {
 	do
 		ssh $1 "test -f \"$2\""
 		ret=$?
-		if test "$ret" -ne 255
+		if test "$ret" -eq 255
 		then
+			echo " ---" ssh failure to $1 checking for file $2, retry after $sleeptime seconds. `date`
+		elif test "$ret" -eq 0
+		then
+			return 0
+		elif test "$ret" -eq 1
+		then
+			echo " ---" File \"$2\" not found: ssh $1 test -f \"$2\"
+			return 1
+		else
+			echo " ---" Exit code $ret: ssh $1 test -f \"$2\", retry after $sleeptime seconds. `date`
 			return $ret
 		fi
-		echo " ---" ssh failure to $1 checking for file $2, retry after $sleeptime seconds. `date`
 		sleep $sleeptime
 	done
 }
@@ -242,7 +253,8 @@ do
 	do
 		sleep 30
 	done
-	( cd "$oldrun"; ssh $i "cd $rundir; tar -czf - kvm-remote-*.sh.out */console.log */kvm-test-1-run*.sh.out */qemu_pid */qemu-retval; rm -rf $T > /dev/null 2>&1" | tar -xzf - )
+	echo " ---" Collecting results from $i `date`
+	( cd "$oldrun"; ssh $i "cd $rundir; tar -czf - kvm-remote-*.sh.out */console.log */kvm-test-1-run*.sh.out */qemu[_-]pid */qemu-retval */qemu-affinity; rm -rf $T > /dev/null 2>&1" | tar -xzf - )
 done
 
 ( kvm-end-run-stats.sh "$oldrun" "$starttime"; echo $? > $T/exitcode ) | tee -a "$oldrun/remote-log"

tools/testing/selftests/rcutorture/bin/kvm-test-1-run-batch.sh

@@ -50,10 +50,34 @@ grep '^#' $1/qemu-cmd | sed -e 's/^# //' > $T/qemu-cmd-settings
 echo ---- System running test: `uname -a`
 echo ---- Starting kernels. `date` | tee -a log
 $TORTURE_JITTER_START
+kvm-assign-cpus.sh /sys/devices/system/node > $T/cpuarray.awk
 for i in "$@"
 do
 	echo ---- System running test: `uname -a` > $i/kvm-test-1-run-qemu.sh.out
 	echo > $i/kvm-test-1-run-qemu.sh.out
+	export TORTURE_AFFINITY=
+	kvm-get-cpus-script.sh $T/cpuarray.awk $T/cpubatches.awk $T/cpustate
+	cat << '	___EOF___' >> $T/cpubatches.awk
+	END {
+		affinitylist = "";
+		if (!gotcpus()) {
+			print "echo No CPU-affinity information, so no taskset command.";
+		} else if (cpu_count !~ /^[0-9][0-9]*$/) {
+			print "echo " scenario ": Bogus number of CPUs (old qemu-cmd?), so no taskset command.";
+		} else {
+			affinitylist = nextcpus(cpu_count);
+			if (!(affinitylist ~ /^[0-9,-][0-9,-]*$/))
+				print "echo " scenario ": Bogus CPU-affinity information, so no taskset command.";
+			else if (!dumpcpustate())
+				print "echo " scenario ": Could not dump state, so no taskset command.";
+			else
+				print "export TORTURE_AFFINITY=" affinitylist;
+		}
+	}
+	___EOF___
+	cpu_count="`grep '# TORTURE_CPU_COUNT=' $i/qemu-cmd | sed -e 's/^.*=//'`"
+	affinity_export="`awk -f $T/cpubatches.awk -v cpu_count="$cpu_count" -v scenario=$i < /dev/null`"
+	$affinity_export
 	kvm-test-1-run-qemu.sh $i >> $i/kvm-test-1-run-qemu.sh.out 2>&1 &
 done
 for i in $runfiles

tools/testing/selftests/rcutorture/bin/kvm-test-1-run-qemu.sh

@@ -39,27 +39,34 @@ echo ' ---' `date`: Starting kernel, PID $$
 grep '^#' $resdir/qemu-cmd | sed -e 's/^# //' > $T/qemu-cmd-settings
 . $T/qemu-cmd-settings
 
-# Decorate qemu-cmd with redirection, backgrounding, and PID capture
-sed -e 's/$/ 2>\&1 \&/' < $resdir/qemu-cmd > $T/qemu-cmd
-echo 'echo $! > $resdir/qemu_pid' >> $T/qemu-cmd
+# Decorate qemu-cmd with affinity, redirection, backgrounding, and PID capture
+taskset_command=
+if test -n "$TORTURE_AFFINITY"
+then
+	taskset_command="taskset -c $TORTURE_AFFINITY "
+fi
+sed -e 's/^[^#].*$/'"$taskset_command"'& 2>\&1 \&/' < $resdir/qemu-cmd > $T/qemu-cmd
+echo 'qemu_pid=$!' >> $T/qemu-cmd
+echo 'echo $qemu_pid > $resdir/qemu-pid' >> $T/qemu-cmd
+echo 'taskset -c -p $qemu_pid > $resdir/qemu-affinity' >> $T/qemu-cmd
 
 # In case qemu refuses to run...
 echo "NOTE: $QEMU either did not run or was interactive" > $resdir/console.log
 
 # Attempt to run qemu
 kstarttime=`gawk 'BEGIN { print systime() }' < /dev/null`
-( . $T/qemu-cmd; wait `cat  $resdir/qemu_pid`; echo $? > $resdir/qemu-retval ) &
+( . $T/qemu-cmd; wait `cat  $resdir/qemu-pid`; echo $? > $resdir/qemu-retval ) &
 commandcompleted=0
 if test -z "$TORTURE_KCONFIG_GDB_ARG"
 then
 	sleep 10 # Give qemu's pid a chance to reach the file
-	if test -s "$resdir/qemu_pid"
+	if test -s "$resdir/qemu-pid"
 	then
-		qemu_pid=`cat "$resdir/qemu_pid"`
-		echo Monitoring qemu job at pid $qemu_pid
+		qemu_pid=`cat "$resdir/qemu-pid"`
+		echo Monitoring qemu job at pid $qemu_pid `date`
 	else
 		qemu_pid=""
-		echo Monitoring qemu job at yet-as-unknown pid
+		echo Monitoring qemu job at yet-as-unknown pid `date`
 	fi
 fi
 if test -n "$TORTURE_KCONFIG_GDB_ARG"
@@ -82,9 +89,9 @@ then
 fi
 while :
 do
-	if test -z "$qemu_pid" -a -s "$resdir/qemu_pid"
+	if test -z "$qemu_pid" && test -s "$resdir/qemu-pid"
 	then
-		qemu_pid=`cat "$resdir/qemu_pid"`
+		qemu_pid=`cat "$resdir/qemu-pid"`
 	fi
 	kruntime=`gawk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null`
 	if test -z "$qemu_pid" || kill -0 "$qemu_pid" > /dev/null 2>&1
@@ -115,22 +122,22 @@ do
 		break
 	fi
 done
-if test -z "$qemu_pid" -a -s "$resdir/qemu_pid"
+if test -z "$qemu_pid" && test -s "$resdir/qemu-pid"
 then
-	qemu_pid=`cat "$resdir/qemu_pid"`
+	qemu_pid=`cat "$resdir/qemu-pid"`
 fi
-if test $commandcompleted -eq 0 -a -n "$qemu_pid"
+if test $commandcompleted -eq 0 && test -n "$qemu_pid"
 then
 	if ! test -f "$resdir/../STOP.1"
 	then
-		echo Grace period for qemu job at pid $qemu_pid
+		echo Grace period for qemu job at pid $qemu_pid `date`
 	fi
 	oldline="`tail $resdir/console.log`"
 	while :
 	do
 		if test -f "$resdir/../STOP.1"
 		then
-			echo "PID $qemu_pid killed due to run STOP.1 request" >> $resdir/Warnings 2>&1
+			echo "PID $qemu_pid killed due to run STOP.1 request `date`" >> $resdir/Warnings 2>&1
 			kill -KILL $qemu_pid
 			break
 		fi
@@ -152,13 +159,17 @@ then
 		then
 			last_ts=0
 		fi
-		if test "$newline" != "$oldline" -a "$last_ts" -lt $((seconds + $TORTURE_SHUTDOWN_GRACE))
+		if test "$newline" != "$oldline" && test "$last_ts" -lt $((seconds + $TORTURE_SHUTDOWN_GRACE)) && test "$last_ts" -gt "$TORTURE_SHUTDOWN_GRACE"
 		then
 			must_continue=yes
+			if test $kruntime -ge $((seconds + $TORTURE_SHUTDOWN_GRACE))
+			then
+				echo Continuing at console.log time $last_ts \"`tail -n 1 $resdir/console.log`\" `date`
 			fi
-		if test $must_continue = no -a $kruntime -ge $((seconds + $TORTURE_SHUTDOWN_GRACE))
+		fi
+		if test $must_continue = no && test $kruntime -ge $((seconds + $TORTURE_SHUTDOWN_GRACE))
 		then
-			echo "!!! PID $qemu_pid hung at $kruntime vs. $seconds seconds" >> $resdir/Warnings 2>&1
+			echo "!!! PID $qemu_pid hung at $kruntime vs. $seconds seconds `date`" >> $resdir/Warnings 2>&1
 			kill -KILL $qemu_pid
 			break
 		fi
@@ -172,5 +183,3 @@ fi
 
 # Tell the script that this run is done.
 rm -f $resdir/build.run
-
-parse-console.sh $resdir/console.log $title

tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh

@@ -205,6 +205,7 @@ echo "# TORTURE_KCONFIG_GDB_ARG=\"$TORTURE_KCONFIG_GDB_ARG\"" >> $resdir/qemu-cm
 echo "# TORTURE_JITTER_START=\"$TORTURE_JITTER_START\"" >> $resdir/qemu-cmd
 echo "# TORTURE_JITTER_STOP=\"$TORTURE_JITTER_STOP\"" >> $resdir/qemu-cmd
 echo "# TORTURE_TRUST_MAKE=\"$TORTURE_TRUST_MAKE\"; export TORTURE_TRUST_MAKE" >> $resdir/qemu-cmd
+echo "# TORTURE_CPU_COUNT=$cpu_count" >> $resdir/qemu-cmd
 
 if test -n "$TORTURE_BUILDONLY"
 then
@@ -214,3 +215,4 @@ then
 fi
 
 kvm-test-1-run-qemu.sh $resdir
+parse-console.sh $resdir/console.log $title

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

@@ -430,17 +430,10 @@ then
 	git diff HEAD >> $resdir/$ds/testid.txt
 fi
 ___EOF___
-awk < $T/cfgcpu.pack \
-	-v TORTURE_BUILDONLY="$TORTURE_BUILDONLY" \
-	-v CONFIGDIR="$CONFIGFRAG/" \
-	-v KVM="$KVM" \
-	-v ncpus=$cpus \
-	-v jitter="$jitter" \
-	-v rd=$resdir/$ds/ \
-	-v dur=$dur \
-	-v TORTURE_QEMU_ARG="$TORTURE_QEMU_ARG" \
-	-v TORTURE_BOOTARGS="$TORTURE_BOOTARGS" \
-'BEGIN {
+kvm-assign-cpus.sh /sys/devices/system/node > $T/cpuarray.awk
+kvm-get-cpus-script.sh $T/cpuarray.awk $T/dumpbatches.awk
+cat << '___EOF___' >> $T/dumpbatches.awk
+BEGIN {
 	i = 0;
 }
 
@@ -451,7 +444,7 @@ awk < $T/cfgcpu.pack \
 }
 
 # Dump out the scripting required to run one test batch.
-function dump(first, pastlast, batchnum)
+function dump(first, pastlast, batchnum,  affinitylist)
 {
 	print "echo ----Start batch " batchnum ": `date` | tee -a " rd "log";
 	print "needqemurun="
@@ -483,6 +476,14 @@ function dump(first, pastlast, batchnum)
 		print "echo ", cfr[jn], cpusr[jn] ovf ": Starting build. `date` | tee -a " rd "log";
 		print "mkdir " rd cfr[jn] " || :";
 		print "touch " builddir ".wait";
+		affinitylist = "";
+		if (gotcpus()) {
+			affinitylist = nextcpus(cpusr[jn]);
+		}
+		if (affinitylist ~ /^[0-9,-][0-9,-]*$/)
+			print "export TORTURE_AFFINITY=" affinitylist;
+		else
+			print "export TORTURE_AFFINITY=";
 		print "kvm-test-1-run.sh " CONFIGDIR cf[j], rd cfr[jn], dur " \"" TORTURE_QEMU_ARG "\" \"" TORTURE_BOOTARGS "\" > " rd cfr[jn]  "/kvm-test-1-run.sh.out 2>&1 &"
 		print "echo ", cfr[jn], cpusr[jn] ovf ": Waiting for build to complete. `date` | tee -a " rd "log";
 		print "while test -f " builddir ".wait"
@@ -560,7 +561,19 @@ END {
 	# Dump the last batch.
 	if (ncpus != 0)
 		dump(first, i, batchnum);
-}' >> $T/script
+}
+___EOF___
+awk < $T/cfgcpu.pack \
+	-v TORTURE_BUILDONLY="$TORTURE_BUILDONLY" \
+	-v CONFIGDIR="$CONFIGFRAG/" \
+	-v KVM="$KVM" \
+	-v ncpus=$cpus \
+	-v jitter="$jitter" \
+	-v rd=$resdir/$ds/ \
+	-v dur=$dur \
+	-v TORTURE_QEMU_ARG="$TORTURE_QEMU_ARG" \
+	-v TORTURE_BOOTARGS="$TORTURE_BOOTARGS" \
+	-f $T/dumpbatches.awk >> $T/script
 echo kvm-end-run-stats.sh "$resdir/$ds" "$starttime" >> $T/script
 
 # Extract the tests and their batches from the script.

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

@@ -53,6 +53,7 @@ do_refscale=yes
 do_kvfree=yes
 do_kasan=yes
 do_kcsan=no
+do_clocksourcewd=yes
 
 # doyesno - Helper function for yes/no arguments
 function doyesno () {
@@ -72,6 +73,7 @@ usage () {
 	echo "       --configs-scftorture \"config-file list w/ repeat factor (2*CFLIST)\""
 	echo "       --doall"
 	echo "       --doallmodconfig / --do-no-allmodconfig"
+	echo "       --do-clocksourcewd / --do-no-clocksourcewd"
 	echo "       --do-kasan / --do-no-kasan"
 	echo "       --do-kcsan / --do-no-kcsan"
 	echo "       --do-kvfree / --do-no-kvfree"
@@ -109,7 +111,7 @@ do
 		configs_scftorture="$configs_scftorture $2"
 		shift
 		;;
-	--doall)
+	--do-all|--doall)
 		do_allmodconfig=yes
 		do_rcutorture=yes
 		do_locktorture=yes
@@ -119,10 +121,14 @@ do
 		do_kvfree=yes
 		do_kasan=yes
 		do_kcsan=yes
+		do_clocksourcewd=yes
 		;;
 	--do-allmodconfig|--do-no-allmodconfig)
 		do_allmodconfig=`doyesno "$1" --do-allmodconfig`
 		;;
+	--do-clocksourcewd|--do-no-clocksourcewd)
+		do_clocksourcewd=`doyesno "$1" --do-clocksourcewd`
+		;;
 	--do-kasan|--do-no-kasan)
 		do_kasan=`doyesno "$1" --do-kasan`
 		;;
@@ -135,7 +141,7 @@ do
 	--do-locktorture|--do-no-locktorture)
 		do_locktorture=`doyesno "$1" --do-locktorture`
 		;;
-	--do-none)
+	--do-none|--donone)
 		do_allmodconfig=no
 		do_rcutorture=no
 		do_locktorture=no
@@ -145,6 +151,7 @@ do
 		do_kvfree=no
 		do_kasan=no
 		do_kcsan=no
+		do_clocksourcewd=no
 		;;
 	--do-rcuscale|--do-no-rcuscale)
 		do_rcuscale=`doyesno "$1" --do-rcuscale`
@@ -279,9 +286,9 @@ function torture_one {
 #	torture_bootargs="[ kernel boot arguments ]"
 #	torture_set flavor [ kvm.sh arguments ]
 #
-# Note that "flavor" is an arbitrary string.  Supply --torture if needed.
-# Note that quoting is problematic.  So on the command line, pass multiple
-# values with multiple kvm.sh argument instances.
+# Note that "flavor" is an arbitrary string that does not affect kvm.sh
+# in any way.  So also supply --torture if you need something other than
+# the default.
 function torture_set {
 	local cur_kcsan_kmake_args=
 	local kcsan_kmake_tag=
@@ -377,6 +384,22 @@ then
 	torture_set "rcuscale-kvfree" tools/testing/selftests/rcutorture/bin/kvm.sh --torture rcuscale --allcpus --duration 10 --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --memory 1G --trust-make
 fi
 
+if test "$do_clocksourcewd" = "yes"
+then
+	torture_bootargs="rcupdate.rcu_cpu_stall_suppress_at_boot=1 torture.disable_onoff_at_boot rcupdate.rcu_task_stall_timeout=30000"
+	torture_set "clocksourcewd-1" tools/testing/selftests/rcutorture/bin/kvm.sh --allcpus --duration 45s --configs TREE03 --kconfig "CONFIG_TEST_CLOCKSOURCE_WATCHDOG=y" --trust-make
+
+	torture_bootargs="rcupdate.rcu_cpu_stall_suppress_at_boot=1 torture.disable_onoff_at_boot rcupdate.rcu_task_stall_timeout=30000 clocksource.max_cswd_read_retries=1"
+	torture_set "clocksourcewd-2" tools/testing/selftests/rcutorture/bin/kvm.sh --allcpus --duration 45s --configs TREE03 --kconfig "CONFIG_TEST_CLOCKSOURCE_WATCHDOG=y" --trust-make
+
+	# In case our work is already done...
+	if test "$do_rcutorture" != "yes"
+	then
+		torture_bootargs="rcupdate.rcu_cpu_stall_suppress_at_boot=1 torture.disable_onoff_at_boot rcupdate.rcu_task_stall_timeout=30000"
+		torture_set "clocksourcewd-3" tools/testing/selftests/rcutorture/bin/kvm.sh --allcpus --duration 45s --configs TREE03 --trust-make
+	fi
+fi
+
 echo " --- " $scriptname $args
 echo " --- " Done `date` | tee -a $T/log
 ret=0
@@ -395,6 +418,10 @@ then
 	nfailures="`wc -l "$T/failures" | awk '{ print $1 }'`"
 	ret=2
 fi
+if test "$do_kcsan" = "yes"
+then
+	TORTURE_KCONFIG_KCSAN_ARG=1 tools/testing/selftests/rcutorture/bin/kcsan-collapse.sh tools/testing/selftests/rcutorture/res/$ds > tools/testing/selftests/rcutorture/res/$ds/kcsan.sum
+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
 tdir="`cat $T/successes $T/failures | head -1 | awk '{ print $NF }' | sed -e 's,/[^/]\+/*$,,'`"

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

 CONFIG_SMP=y
-CONFIG_NR_CPUS=2
+CONFIG_NR_CPUS=4
 CONFIG_HOTPLUG_CPU=y
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n

tools/testing/selftests/rcutorture/configs/rcu/TASKS01

 CONFIG_SMP=y
-CONFIG_NR_CPUS=2
+CONFIG_NR_CPUS=4
 CONFIG_HOTPLUG_CPU=y
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n

tools/testing/selftests/rcutorture/configs/rcu/TASKS03

 CONFIG_SMP=y
-CONFIG_NR_CPUS=2
+CONFIG_NR_CPUS=4
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y