Merge tag 'rcu.2021.11.01a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu

Pull RCU updates from Paul McKenney:

 - Miscellaneous fixes

 - Torture-test updates for smp_call_function(), most notably improved
   checking of module parameters.

 - Tasks-trace RCU updates that fix a number of rare but important
   race-condition bugs.

 - Other torture-test updates, most notably better checking of module
   parameters. In addition, rcutorture may once again be run on
   CONFIG_PREEMPT_RT kernels.

 - Torture-test scripting updates, most notably specifying the new
   CONFIG_KCSAN_STRICT kconfig option rather than maintaining an
   ever-changing list of individual KCSAN kconfig options.

* tag 'rcu.2021.11.01a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu: (46 commits)
  rcu: Fix rcu_dynticks_curr_cpu_in_eqs() vs noinstr
  rcu: Always inline rcu_dynticks_task*_{enter,exit}()
  torture: Make kvm-remote.sh print size of downloaded tarball
  torture: Allot 1G of memory for scftorture runs
  tools/rcu: Add an extract-stall script
  scftorture: Warn on individual scf_torture_init() error conditions
  scftorture: Count reschedule IPIs
  scftorture: Account for weight_resched when checking for all zeroes
  scftorture: Shut down if nonsensical arguments given
  scftorture: Allow zero weight to exclude an smp_call_function*() category
  rcu: Avoid unneeded function call in rcu_read_unlock()
  rcu-tasks: Update comments to cond_resched_tasks_rcu_qs()
  rcu-tasks: Fix IPI failure handling in trc_wait_for_one_reader
  rcu-tasks: Fix read-side primitives comment for call_rcu_tasks_trace
  rcu-tasks: Clarify read side section info for rcu_tasks_rude GP primitives
  rcu-tasks: Correct comparisons for CPU numbers in show_stalled_task_trace
  rcu-tasks: Correct firstreport usage in check_all_holdout_tasks_trace
  rcu-tasks: Fix s/rcu_add_holdout/trc_add_holdout/ typo in comment
  rcu-tasks: Move RTGS_WAIT_CBS to beginning of rcu_tasks_kthread() loop
  rcu-tasks: Fix s/instruction/instructions/ typo in comment
  ...

9 files changed, 143 insertions, 128 deletions

diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c
index 2cc34a22a506..228f143bf935 100644
--- a/kernel/rcu/rcuscale.c
+++ b/kernel/rcu/rcuscale.c
@@ -758,7 +758,7 @@ kfree_scale_init(void)
 		init_waitqueue_head(&shutdown_wq);
 		firsterr = torture_create_kthread(kfree_scale_shutdown, NULL,
 						  shutdown_task);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 		schedule_timeout_uninterruptible(1);
 	}
@@ -775,7 +775,7 @@ kfree_scale_init(void)
 	for (i = 0; i < kfree_nrealthreads; i++) {
 		firsterr = torture_create_kthread(kfree_scale_thread, (void *)i,
 						  kfree_reader_tasks[i]);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 
@@ -838,7 +838,7 @@ rcu_scale_init(void)
 		init_waitqueue_head(&shutdown_wq);
 		firsterr = torture_create_kthread(rcu_scale_shutdown, NULL,
 						  shutdown_task);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 		schedule_timeout_uninterruptible(1);
 	}
@@ -852,7 +852,7 @@ rcu_scale_init(void)
 	for (i = 0; i < nrealreaders; i++) {
 		firsterr = torture_create_kthread(rcu_scale_reader, (void *)i,
 						  reader_tasks[i]);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	while (atomic_read(&n_rcu_scale_reader_started) < nrealreaders)
@@ -879,7 +879,7 @@ rcu_scale_init(void)
 		}
 		firsterr = torture_create_kthread(rcu_scale_writer, (void *)i,
 						  writer_tasks[i]);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	torture_init_end();
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index ab4215266ebe..8b410d982990 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -1432,28 +1432,34 @@ static void rcutorture_one_extend(int *readstate, int newstate,
 	/* First, put new protection in place to avoid critical-section gap. */
 	if (statesnew & RCUTORTURE_RDR_BH)
 		local_bh_disable();
+	if (statesnew & RCUTORTURE_RDR_RBH)
+		rcu_read_lock_bh();
 	if (statesnew & RCUTORTURE_RDR_IRQ)
 		local_irq_disable();
 	if (statesnew & RCUTORTURE_RDR_PREEMPT)
 		preempt_disable();
-	if (statesnew & RCUTORTURE_RDR_RBH)
-		rcu_read_lock_bh();
 	if (statesnew & RCUTORTURE_RDR_SCHED)
 		rcu_read_lock_sched();
 	if (statesnew & RCUTORTURE_RDR_RCU)
 		idxnew = cur_ops->readlock() << RCUTORTURE_RDR_SHIFT;
 
-	/* Next, remove old protection, irq first due to bh conflict. */
+	/*
+	 * Next, remove old protection, in decreasing order of strength
+	 * to avoid unlock paths that aren't safe in the stronger
+	 * context. Namely: BH can not be enabled with disabled interrupts.
+	 * Additionally PREEMPT_RT requires that BH is enabled in preemptible
+	 * context.
+	 */
 	if (statesold & RCUTORTURE_RDR_IRQ)
 		local_irq_enable();
-	if (statesold & RCUTORTURE_RDR_BH)
-		local_bh_enable();
 	if (statesold & RCUTORTURE_RDR_PREEMPT)
 		preempt_enable();
-	if (statesold & RCUTORTURE_RDR_RBH)
-		rcu_read_unlock_bh();
 	if (statesold & RCUTORTURE_RDR_SCHED)
 		rcu_read_unlock_sched();
+	if (statesold & RCUTORTURE_RDR_BH)
+		local_bh_enable();
+	if (statesold & RCUTORTURE_RDR_RBH)
+		rcu_read_unlock_bh();
 	if (statesold & RCUTORTURE_RDR_RCU) {
 		bool lockit = !statesnew && !(torture_random(trsp) & 0xffff);
 
@@ -1496,6 +1502,9 @@ rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp)
 	int mask = rcutorture_extend_mask_max();
 	unsigned long randmask1 = torture_random(trsp) >> 8;
 	unsigned long randmask2 = randmask1 >> 3;
+	unsigned long preempts = RCUTORTURE_RDR_PREEMPT | RCUTORTURE_RDR_SCHED;
+	unsigned long preempts_irq = preempts | RCUTORTURE_RDR_IRQ;
+	unsigned long bhs = RCUTORTURE_RDR_BH | RCUTORTURE_RDR_RBH;
 
 	WARN_ON_ONCE(mask >> RCUTORTURE_RDR_SHIFT);
 	/* Mostly only one bit (need preemption!), sometimes lots of bits. */
@@ -1503,11 +1512,26 @@ rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp)
 		mask = mask & randmask2;
 	else
 		mask = mask & (1 << (randmask2 % RCUTORTURE_RDR_NBITS));
-	/* Can't enable bh w/irq disabled. */
-	if ((mask & RCUTORTURE_RDR_IRQ) &&
-	    ((!(mask & RCUTORTURE_RDR_BH) && (oldmask & RCUTORTURE_RDR_BH)) ||
-	     (!(mask & RCUTORTURE_RDR_RBH) && (oldmask & RCUTORTURE_RDR_RBH))))
-		mask |= RCUTORTURE_RDR_BH | RCUTORTURE_RDR_RBH;
+
+	/*
+	 * Can't enable bh w/irq disabled.
+	 */
+	if (mask & RCUTORTURE_RDR_IRQ)
+		mask |= oldmask & bhs;
+
+	/*
+	 * Ideally these sequences would be detected in debug builds
+	 * (regardless of RT), but until then don't stop testing
+	 * them on non-RT.
+	 */
+	if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
+		/* Can't modify BH in atomic context */
+		if (oldmask & preempts_irq)
+			mask &= ~bhs;
+		if ((oldmask | mask) & preempts_irq)
+			mask |= oldmask & bhs;
+	}
+
 	return mask ?: RCUTORTURE_RDR_RCU;
 }
 
@@ -2449,7 +2473,7 @@ static int __init rcu_torture_fwd_prog_init(void)
 	}
 	if (stall_cpu > 0) {
 		VERBOSE_TOROUT_STRING("rcu_torture_fwd_prog_init: Disabled, conflicts with CPU-stall testing");
-		if (IS_MODULE(CONFIG_RCU_TORTURE_TESTS))
+		if (IS_MODULE(CONFIG_RCU_TORTURE_TEST))
 			return -EINVAL; /* In module, can fail back to user. */
 		WARN_ON(1); /* Make sure rcutorture notices conflict. */
 		return 0;
@@ -2741,7 +2765,7 @@ static int rcu_torture_read_exit(void *unused)
 static int rcu_torture_read_exit_init(void)
 {
 	if (read_exit_burst <= 0)
-		return -EINVAL;
+		return 0;
 	init_waitqueue_head(&read_exit_wq);
 	read_exit_child_stop = false;
 	read_exit_child_stopped = false;
@@ -2819,7 +2843,7 @@ rcu_torture_cleanup(void)
 		 rcutorture_seq_diff(gp_seq, start_gp_seq));
 	torture_stop_kthread(rcu_torture_stats, stats_task);
 	torture_stop_kthread(rcu_torture_fqs, fqs_task);
-	if (rcu_torture_can_boost())
+	if (rcu_torture_can_boost() && rcutor_hp >= 0)
 		cpuhp_remove_state(rcutor_hp);
 
 	/*
@@ -3037,7 +3061,7 @@ rcu_torture_init(void)
 	rcu_torture_write_types();
 	firsterr = torture_create_kthread(rcu_torture_writer, NULL,
 					  writer_task);
-	if (firsterr)
+	if (torture_init_error(firsterr))
 		goto unwind;
 	if (nfakewriters > 0) {
 		fakewriter_tasks = kcalloc(nfakewriters,
@@ -3052,7 +3076,7 @@ rcu_torture_init(void)
 	for (i = 0; i < nfakewriters; i++) {
 		firsterr = torture_create_kthread(rcu_torture_fakewriter,
 						  NULL, fakewriter_tasks[i]);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	reader_tasks = kcalloc(nrealreaders, sizeof(reader_tasks[0]),
@@ -3068,7 +3092,7 @@ rcu_torture_init(void)
 		rcu_torture_reader_mbchk[i].rtc_chkrdr = -1;
 		firsterr = torture_create_kthread(rcu_torture_reader, (void *)i,
 						  reader_tasks[i]);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	nrealnocbers = nocbs_nthreads;
@@ -3088,18 +3112,18 @@ rcu_torture_init(void)
 	}
 	for (i = 0; i < nrealnocbers; i++) {
 		firsterr = torture_create_kthread(rcu_nocb_toggle, NULL, nocb_tasks[i]);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	if (stat_interval > 0) {
 		firsterr = torture_create_kthread(rcu_torture_stats, NULL,
 						  stats_task);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	if (test_no_idle_hz && shuffle_interval > 0) {
 		firsterr = torture_shuffle_init(shuffle_interval * HZ);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	if (stutter < 0)
@@ -3109,7 +3133,7 @@ rcu_torture_init(void)
 
 		t = cur_ops->stall_dur ? cur_ops->stall_dur() : stutter * HZ;
 		firsterr = torture_stutter_init(stutter * HZ, t);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	if (fqs_duration < 0)
@@ -3118,7 +3142,7 @@ rcu_torture_init(void)
 		/* Create the fqs thread */
 		firsterr = torture_create_kthread(rcu_torture_fqs, NULL,
 						  fqs_task);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	if (test_boost_interval < 1)
@@ -3132,9 +3156,9 @@ rcu_torture_init(void)
 		firsterr = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "RCU_TORTURE",
 					     rcutorture_booster_init,
 					     rcutorture_booster_cleanup);
-		if (firsterr < 0)
-			goto unwind;
 		rcutor_hp = firsterr;
+		if (torture_init_error(firsterr))
+			goto unwind;
 
 		// Testing RCU priority boosting requires rcutorture do
 		// some serious abuse.  Counter this by running ksoftirqd
@@ -3153,23 +3177,23 @@ rcu_torture_init(void)
 	}
 	shutdown_jiffies = jiffies + shutdown_secs * HZ;
 	firsterr = torture_shutdown_init(shutdown_secs, rcu_torture_cleanup);
-	if (firsterr)
+	if (torture_init_error(firsterr))
 		goto unwind;
 	firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval,
 				      rcutorture_sync);
-	if (firsterr)
+	if (torture_init_error(firsterr))
 		goto unwind;
 	firsterr = rcu_torture_stall_init();
-	if (firsterr)
+	if (torture_init_error(firsterr))
 		goto unwind;
 	firsterr = rcu_torture_fwd_prog_init();
-	if (firsterr)
+	if (torture_init_error(firsterr))
 		goto unwind;
 	firsterr = rcu_torture_barrier_init();
-	if (firsterr)
+	if (torture_init_error(firsterr))
 		goto unwind;
 	firsterr = rcu_torture_read_exit_init();
-	if (firsterr)
+	if (torture_init_error(firsterr))
 		goto unwind;
 	if (object_debug)
 		rcu_test_debug_objects();
diff --git a/kernel/rcu/refscale.c b/kernel/rcu/refscale.c
index 66dc14cf5687..1631ef8a138d 100644
--- a/kernel/rcu/refscale.c
+++ b/kernel/rcu/refscale.c
@@ -824,7 +824,7 @@ ref_scale_init(void)
 		init_waitqueue_head(&shutdown_wq);
 		firsterr = torture_create_kthread(ref_scale_shutdown, NULL,
 						  shutdown_task);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 		schedule_timeout_uninterruptible(1);
 	}
@@ -851,7 +851,7 @@ ref_scale_init(void)
 	for (i = 0; i < nreaders; i++) {
 		firsterr = torture_create_kthread(ref_scale_reader, (void *)i,
 						  reader_tasks[i].task);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 
 		init_waitqueue_head(&(reader_tasks[i].wq));
@@ -860,7 +860,7 @@ ref_scale_init(void)
 	// Main Task
 	init_waitqueue_head(&main_wq);
 	firsterr = torture_create_kthread(main_func, NULL, main_task);
-	if (firsterr)
+	if (torture_init_error(firsterr))
 		goto unwind;
 
 	torture_init_end();
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 171bc848e8e3..7da3c81c3f59 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -197,6 +197,7 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 	 * This loop is terminated by the system going down.  ;-)
 	 */
 	for (;;) {
+		set_tasks_gp_state(rtp, RTGS_WAIT_CBS);
 
 		/* Pick up any new callbacks. */
 		raw_spin_lock_irqsave(&rtp->cbs_lock, flags);
@@ -236,8 +237,6 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 		}
 		/* Paranoid sleep to keep this from entering a tight loop */
 		schedule_timeout_idle(rtp->gp_sleep);
-
-		set_tasks_gp_state(rtp, RTGS_WAIT_CBS);
 	}
 }
 
@@ -369,7 +368,7 @@ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp)
 ////////////////////////////////////////////////////////////////////////
 //
 // Simple variant of RCU whose quiescent states are voluntary context
-// switch, cond_resched_rcu_qs(), user-space execution, and idle.
+// switch, cond_resched_tasks_rcu_qs(), user-space execution, and idle.
 // As such, grace periods can take one good long time.  There are no
 // read-side primitives similar to rcu_read_lock() and rcu_read_unlock()
 // because this implementation is intended to get the system into a safe
@@ -540,7 +539,7 @@ DEFINE_RCU_TASKS(rcu_tasks, rcu_tasks_wait_gp, call_rcu_tasks, "RCU Tasks");
  * period elapses, in other words after all currently executing RCU
  * read-side critical sections have completed. call_rcu_tasks() assumes
  * that the read-side critical sections end at a voluntary context
- * switch (not a preemption!), cond_resched_rcu_qs(), entry into idle,
+ * switch (not a preemption!), cond_resched_tasks_rcu_qs(), entry into idle,
  * or transition to usermode execution.  As such, there are no read-side
  * primitives analogous to rcu_read_lock() and rcu_read_unlock() because
  * this primitive is intended to determine that all tasks have passed
@@ -678,11 +677,11 @@ DEFINE_RCU_TASKS(rcu_tasks_rude, rcu_tasks_rude_wait_gp, call_rcu_tasks_rude,
  * period elapses, in other words after all currently executing RCU
  * read-side critical sections have completed. call_rcu_tasks_rude()
  * assumes that the read-side critical sections end at context switch,
- * cond_resched_rcu_qs(), or transition to usermode execution.  As such,
- * there are no read-side primitives analogous to rcu_read_lock() and
- * rcu_read_unlock() because this primitive is intended to determine
- * that all tasks have passed through a safe state, not so much for
- * data-structure synchronization.
+ * cond_resched_tasks_rcu_qs(), or transition to usermode execution (as
+ * usermode execution is schedulable). As such, there are no read-side
+ * primitives analogous to rcu_read_lock() and rcu_read_unlock() because
+ * this primitive is intended to determine that all tasks have passed
+ * through a safe state, not so much for data-structure synchronization.
  *
  * See the description of call_rcu() for more detailed information on
  * memory ordering guarantees.
@@ -700,8 +699,8 @@ EXPORT_SYMBOL_GPL(call_rcu_tasks_rude);
  * grace period has elapsed, in other words after all currently
  * executing rcu-tasks read-side critical sections have elapsed.  These
  * read-side critical sections are delimited by calls to schedule(),
- * cond_resched_tasks_rcu_qs(), userspace execution, and (in theory,
- * anyway) cond_resched().
+ * cond_resched_tasks_rcu_qs(), userspace execution (which is a schedulable
+ * context), and (in theory, anyway) cond_resched().
  *
  * This is a very specialized primitive, intended only for a few uses in
  * tracing and other situations requiring manipulation of function preambles
@@ -758,7 +757,7 @@ EXPORT_SYMBOL_GPL(show_rcu_tasks_rude_gp_kthread);
 // 2.	Protects code in the idle loop, exception entry/exit, and
 //	CPU-hotplug code paths, similar to the capabilities of SRCU.
 //
-// 3.	Avoids expensive read-side instruction, having overhead similar
+// 3.	Avoids expensive read-side instructions, having overhead similar
 //	to that of Preemptible RCU.
 //
 // There are of course downsides.  The grace-period code can send IPIs to
@@ -848,7 +847,7 @@ static void rcu_read_unlock_iw(struct irq_work *iwp)
 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)
+void rcu_read_unlock_trace_special(struct task_struct *t)
 {
 	int nq = READ_ONCE(t->trc_reader_special.b.need_qs);
 
@@ -858,7 +857,7 @@ void rcu_read_unlock_trace_special(struct task_struct *t, int nesting)
 	// Update .need_qs before ->trc_reader_nesting for irq/NMI handlers.
 	if (nq)
 		WRITE_ONCE(t->trc_reader_special.b.need_qs, false);
-	WRITE_ONCE(t->trc_reader_nesting, nesting);
+	WRITE_ONCE(t->trc_reader_nesting, 0);
 	if (nq && atomic_dec_and_test(&trc_n_readers_need_end))
 		irq_work_queue(&rcu_tasks_trace_iw);
 }
@@ -890,32 +889,24 @@ static void trc_read_check_handler(void *t_in)
 
 	// If the task is no longer running on this CPU, leave.
 	if (unlikely(texp != t)) {
-		if (WARN_ON_ONCE(atomic_dec_and_test(&trc_n_readers_need_end)))
-			wake_up(&trc_wait);
 		goto reset_ipi; // Already on holdout list, so will check later.
 	}
 
 	// 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(!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
-		// positives on the above WARN_ON_ONCE().
 		WRITE_ONCE(t->trc_reader_checked, true);
 		goto reset_ipi;
 	}
 	// If we are racing with an rcu_read_unlock_trace(), try again later.
-	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);
+	if (unlikely(READ_ONCE(t->trc_reader_nesting) < 0))
 		goto reset_ipi;
-	}
 	WRITE_ONCE(t->trc_reader_checked, true);
 
 	// 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.
+	atomic_inc(&trc_n_readers_need_end); // One more to wait on.
 	WARN_ON_ONCE(READ_ONCE(t->trc_reader_special.b.need_qs));
 	WRITE_ONCE(t->trc_reader_special.b.need_qs, true);
 
@@ -931,7 +922,7 @@ reset_ipi:
 static int trc_inspect_reader(struct task_struct *t, void *arg)
 {
 	int cpu = task_cpu(t);
-	bool in_qs = false;
+	int nesting;
 	bool ofl = cpu_is_offline(cpu);
 
 	if (task_curr(t)) {
@@ -951,18 +942,18 @@ static int trc_inspect_reader(struct task_struct *t, void *arg)
 		n_heavy_reader_updates++;
 		if (ofl)
 			n_heavy_reader_ofl_updates++;
-		in_qs = true;
+		nesting = 0;
 	} else {
 		// The task is not running, so C-language access is safe.
-		in_qs = likely(!t->trc_reader_nesting);
+		nesting = t->trc_reader_nesting;
 	}
 
-	// Mark as checked so that the grace-period kthread will
-	// remove it from the holdout list.
-	t->trc_reader_checked = true;
-
-	if (in_qs)
-		return 0;  // Already in quiescent state, done!!!
+	// If not exiting a read-side critical section, mark as checked
+	// so that the grace-period kthread will remove it from the
+	// holdout list.
+	t->trc_reader_checked = nesting >= 0;
+	if (nesting <= 0)
+		return nesting ? -EINVAL : 0;  // If in QS, done, otherwise try again later.
 
 	// The task is in a read-side critical section, so set up its
 	// state so that it will awaken the grace-period kthread upon exit
@@ -1000,7 +991,7 @@ static void trc_wait_for_one_reader(struct 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
+	// trc_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.
 
@@ -1015,21 +1006,17 @@ static void trc_wait_for_one_reader(struct task_struct *t,
 		if (per_cpu(trc_ipi_to_cpu, cpu) || t->trc_ipi_to_cpu >= 0)
 			return;
 
-		atomic_inc(&trc_n_readers_need_end);
 		per_cpu(trc_ipi_to_cpu, cpu) = true;
 		t->trc_ipi_to_cpu = cpu;
 		rcu_tasks_trace.n_ipis++;
-		if (smp_call_function_single(cpu,
-					     trc_read_check_handler, t, 0)) {
+		if (smp_call_function_single(cpu, trc_read_check_handler, t, 0)) {
 			// Just in case there is some other reason for
 			// failure than the target CPU being offline.
+			WARN_ONCE(1, "%s():  smp_call_function_single() failed for CPU: %d\n",
+				  __func__, cpu);
 			rcu_tasks_trace.n_ipis_fails++;
 			per_cpu(trc_ipi_to_cpu, cpu) = false;
-			t->trc_ipi_to_cpu = cpu;
-			if (atomic_dec_and_test(&trc_n_readers_need_end)) {
-				WARN_ON_ONCE(1);
-				wake_up(&trc_wait);
-			}
+			t->trc_ipi_to_cpu = -1;
 		}
 	}
 }
@@ -1099,9 +1086,9 @@ static void show_stalled_task_trace(struct task_struct *t, bool *firstreport)
 	cpu = task_cpu(t);
 	pr_alert("P%d: %c%c%c nesting: %d%c cpu: %d\n",
 		 t->pid,
-		 ".I"[READ_ONCE(t->trc_ipi_to_cpu) > 0],
+		 ".I"[READ_ONCE(t->trc_ipi_to_cpu) >= 0],
 		 ".i"[is_idle_task(t)],
-		 ".N"[cpu > 0 && tick_nohz_full_cpu(cpu)],
+		 ".N"[cpu >= 0 && tick_nohz_full_cpu(cpu)],
 		 READ_ONCE(t->trc_reader_nesting),
 		 " N"[!!READ_ONCE(t->trc_reader_special.b.need_qs)],
 		 cpu);
@@ -1144,20 +1131,34 @@ static void check_all_holdout_tasks_trace(struct list_head *hop,
 	cpus_read_unlock();
 
 	if (needreport) {
-		if (firstreport)
+		if (*firstreport)
 			pr_err("INFO: rcu_tasks_trace detected stalls? (Late IPI?)\n");
 		show_stalled_ipi_trace();
 	}
 }
 
+static void rcu_tasks_trace_empty_fn(void *unused)
+{
+}
+
 /* Wait for grace period to complete and provide ordering. */
 static void rcu_tasks_trace_postgp(struct rcu_tasks *rtp)
 {
+	int cpu;
 	bool firstreport;
 	struct task_struct *g, *t;
 	LIST_HEAD(holdouts);
 	long ret;
 
+	// Wait for any lingering IPI handlers to complete.  Note that
+	// if a CPU has gone offline or transitioned to userspace in the
+	// meantime, all IPI handlers should have been drained beforehand.
+	// Yes, this assumes that CPUs process IPIs in order.  If that ever
+	// changes, there will need to be a recheck and/or timed wait.
+	for_each_online_cpu(cpu)
+		if (smp_load_acquire(per_cpu_ptr(&trc_ipi_to_cpu, cpu)))
+			smp_call_function_single(cpu, rcu_tasks_trace_empty_fn, NULL, 1);
+
 	// Remove the safety count.
 	smp_mb__before_atomic();  // Order vs. earlier atomics
 	atomic_dec(&trc_n_readers_need_end);
@@ -1200,7 +1201,7 @@ static void exit_tasks_rcu_finish_trace(struct task_struct *t)
 	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);
+		rcu_read_unlock_trace_special(t);
 }
 
 /**
@@ -1208,15 +1209,11 @@ static void exit_tasks_rcu_finish_trace(struct task_struct *t)
  * @rhp: structure to be used for queueing the RCU updates.
  * @func: actual callback function to be invoked after the grace period
  *
- * The callback function will be invoked some time after a full grace
- * period elapses, in other words after all currently executing RCU
- * read-side critical sections have completed. call_rcu_tasks_trace()
- * assumes that the read-side critical sections end at context switch,
- * cond_resched_rcu_qs(), or transition to usermode execution.  As such,
- * there are no read-side primitives analogous to rcu_read_lock() and
- * rcu_read_unlock() because this primitive is intended to determine
- * that all tasks have passed through a safe state, not so much for
- * data-structure synchronization.
+ * The callback function will be invoked some time after a trace rcu-tasks
+ * grace period elapses, in other words after all currently executing
+ * trace rcu-tasks read-side critical sections have completed. These
+ * read-side critical sections are delimited by calls to rcu_read_lock_trace()
+ * and rcu_read_unlock_trace().
  *
  * See the description of call_rcu() for more detailed information on
  * memory ordering guarantees.
@@ -1232,7 +1229,7 @@ EXPORT_SYMBOL_GPL(call_rcu_tasks_trace);
  *
  * Control will return to the caller some time after a trace rcu-tasks
  * grace period has elapsed, in other words after all currently executing
- * rcu-tasks read-side critical sections have elapsed.  These read-side
+ * trace rcu-tasks read-side critical sections have elapsed. These read-side
  * critical sections are delimited by calls to rcu_read_lock_trace()
  * and rcu_read_unlock_trace().
  *
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index bce848e50512..ef8d36f580fc 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -327,7 +327,7 @@ static void rcu_dynticks_eqs_online(void)
  */
 static __always_inline bool rcu_dynticks_curr_cpu_in_eqs(void)
 {
-	return !(atomic_read(this_cpu_ptr(&rcu_data.dynticks)) & 0x1);
+	return !(arch_atomic_read(this_cpu_ptr(&rcu_data.dynticks)) & 0x1);
 }
 
 /*
@@ -1219,8 +1219,6 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp)
 static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 {
 	unsigned long jtsq;
-	bool *rnhqp;
-	bool *ruqp;
 	struct rcu_node *rnp = rdp->mynode;
 
 	/*
@@ -1285,17 +1283,15 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	 * is set way high.
 	 */
 	jtsq = READ_ONCE(jiffies_to_sched_qs);
-	ruqp = per_cpu_ptr(&rcu_data.rcu_urgent_qs, rdp->cpu);
-	rnhqp = per_cpu_ptr(&rcu_data.rcu_need_heavy_qs, rdp->cpu);
-	if (!READ_ONCE(*rnhqp) &&
+	if (!READ_ONCE(rdp->rcu_need_heavy_qs) &&
 	    (time_after(jiffies, rcu_state.gp_start + jtsq * 2) ||
 	     time_after(jiffies, rcu_state.jiffies_resched) ||
 	     rcu_state.cbovld)) {
-		WRITE_ONCE(*rnhqp, true);
+		WRITE_ONCE(rdp->rcu_need_heavy_qs, true);
 		/* Store rcu_need_heavy_qs before rcu_urgent_qs. */
-		smp_store_release(ruqp, true);
+		smp_store_release(&rdp->rcu_urgent_qs, true);
 	} else if (time_after(jiffies, rcu_state.gp_start + jtsq)) {
-		WRITE_ONCE(*ruqp, true);
+		WRITE_ONCE(rdp->rcu_urgent_qs, true);
 	}
 
 	/*
@@ -1309,7 +1305,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	if (tick_nohz_full_cpu(rdp->cpu) &&
 	    (time_after(jiffies, READ_ONCE(rdp->last_fqs_resched) + jtsq * 3) ||
 	     rcu_state.cbovld)) {
-		WRITE_ONCE(*ruqp, true);
+		WRITE_ONCE(rdp->rcu_urgent_qs, true);
 		resched_cpu(rdp->cpu);
 		WRITE_ONCE(rdp->last_fqs_resched, jiffies);
 	}
@@ -1779,6 +1775,8 @@ static noinline_for_stack bool rcu_gp_init(void)
 	 */
 	WRITE_ONCE(rcu_state.gp_state, RCU_GP_ONOFF);
 	rcu_for_each_leaf_node(rnp) {
+		// Wait for CPU-hotplug operations that might have
+		// started before this grace period did.
 		smp_mb(); // Pair with barriers used when updating ->ofl_seq to odd values.
 		firstseq = READ_ONCE(rnp->ofl_seq);
 		if (firstseq & 0x1)
@@ -1907,7 +1905,7 @@ static void rcu_gp_fqs(bool first_time)
 	struct rcu_node *rnp = rcu_get_root();
 
 	WRITE_ONCE(rcu_state.gp_activity, jiffies);
-	rcu_state.n_force_qs++;
+	WRITE_ONCE(rcu_state.n_force_qs, rcu_state.n_force_qs + 1);
 	if (first_time) {
 		/* Collect dyntick-idle snapshots. */
 		force_qs_rnp(dyntick_save_progress_counter);
@@ -2358,7 +2356,7 @@ rcu_check_quiescent_state(struct rcu_data *rdp)
 int rcutree_dying_cpu(unsigned int cpu)
 {
 	bool blkd;
-	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
+	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
 	struct rcu_node *rnp = rdp->mynode;
 
 	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
@@ -2550,7 +2548,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
 	/* Reset ->qlen_last_fqs_check trigger if enough CBs have drained. */
 	if (count == 0 && rdp->qlen_last_fqs_check != 0) {
 		rdp->qlen_last_fqs_check = 0;
-		rdp->n_force_qs_snap = rcu_state.n_force_qs;
+		rdp->n_force_qs_snap = READ_ONCE(rcu_state.n_force_qs);
 	} else if (count < rdp->qlen_last_fqs_check - qhimark)
 		rdp->qlen_last_fqs_check = count;
 
@@ -2898,10 +2896,10 @@ static void __call_rcu_core(struct rcu_data *rdp, struct rcu_head *head,
 		} else {
 			/* Give the grace period a kick. */
 			rdp->blimit = DEFAULT_MAX_RCU_BLIMIT;
-			if (rcu_state.n_force_qs == rdp->n_force_qs_snap &&
+			if (READ_ONCE(rcu_state.n_force_qs) == rdp->n_force_qs_snap &&
 			    rcu_segcblist_first_pend_cb(&rdp->cblist) != head)
 				rcu_force_quiescent_state();
-			rdp->n_force_qs_snap = rcu_state.n_force_qs;
+			rdp->n_force_qs_snap = READ_ONCE(rcu_state.n_force_qs);
 			rdp->qlen_last_fqs_check = rcu_segcblist_n_cbs(&rdp->cblist);
 		}
 	}
@@ -4128,10 +4126,9 @@ int rcutree_prepare_cpu(unsigned int cpu)
 	/* Set up local state, ensuring consistent view of global state. */
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	rdp->qlen_last_fqs_check = 0;
-	rdp->n_force_qs_snap = rcu_state.n_force_qs;
+	rdp->n_force_qs_snap = READ_ONCE(rcu_state.n_force_qs);
 	rdp->blimit = blimit;
 	rdp->dynticks_nesting = 1;	/* CPU not up, no tearing. */
-	rcu_dynticks_eqs_online();
 	raw_spin_unlock_rcu_node(rnp);		/* irqs remain disabled. */
 
 	/*
@@ -4251,6 +4248,7 @@ void rcu_cpu_starting(unsigned int cpu)
 	mask = rdp->grpmask;
 	WRITE_ONCE(rnp->ofl_seq, rnp->ofl_seq + 1);
 	WARN_ON_ONCE(!(rnp->ofl_seq & 0x1));
+	rcu_dynticks_eqs_online();
 	smp_mb(); // Pair with rcu_gp_cleanup()'s ->ofl_seq barrier().
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext | mask);
@@ -4296,9 +4294,7 @@ void rcu_report_dead(unsigned int cpu)
 	do_nocb_deferred_wakeup(rdp);
 
 	/* QS for any half-done expedited grace period. */
-	preempt_disable();
-	rcu_report_exp_rdp(this_cpu_ptr(&rcu_data));
-	preempt_enable();
+	rcu_report_exp_rdp(rdp);
 	rcu_preempt_deferred_qs(current);
 
 	/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 2796084ef85a..f3947c49eee7 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -512,7 +512,6 @@ static void synchronize_rcu_expedited_wait(void)
 		j = READ_ONCE(jiffies_till_first_fqs);
 		if (synchronize_rcu_expedited_wait_once(j + HZ))
 			return;
-		WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_RT));
 	}
 
 	for (;;) {
@@ -760,7 +759,7 @@ static void sync_sched_exp_online_cleanup(int cpu)
 	my_cpu = get_cpu();
 	/* Quiescent state either not needed or already requested, leave. */
 	if (!(READ_ONCE(rnp->expmask) & rdp->grpmask) ||
-	    __this_cpu_read(rcu_data.cpu_no_qs.b.exp)) {
+	    rdp->cpu_no_qs.b.exp) {
 		put_cpu();
 		return;
 	}
diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
index 8fdf44f8523f..368ef7b9af4f 100644
--- a/kernel/rcu/tree_nocb.h
+++ b/kernel/rcu/tree_nocb.h
@@ -549,7 +549,6 @@ static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone,
 		rcu_nocb_unlock_irqrestore(rdp, flags);
 		trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WakeNot"));
 	}
-	return;
 }
 
 /*
@@ -767,6 +766,7 @@ static int rcu_nocb_gp_kthread(void *arg)
 static inline bool nocb_cb_can_run(struct rcu_data *rdp)
 {
 	u8 flags = SEGCBLIST_OFFLOADED | SEGCBLIST_KTHREAD_CB;
+
 	return rcu_segcblist_test_flags(&rdp->cblist, flags);
 }
 
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index d070059163d7..5199559fbbf0 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -814,8 +814,7 @@ void rcu_read_unlock_strict(void)
 {
 	struct rcu_data *rdp;
 
-	if (!IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) ||
-	   irqs_disabled() || preempt_count() || !rcu_state.gp_kthread)
+	if (irqs_disabled() || preempt_count() || !rcu_state.gp_kthread)
 		return;
 	rdp = this_cpu_ptr(&rcu_data);
 	rcu_report_qs_rdp(rdp);
@@ -1480,7 +1479,7 @@ static void rcu_bind_gp_kthread(void)
 }
 
 /* Record the current task on dyntick-idle entry. */
-static void noinstr rcu_dynticks_task_enter(void)
+static __always_inline void rcu_dynticks_task_enter(void)
 {
 #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL)
 	WRITE_ONCE(current->rcu_tasks_idle_cpu, smp_processor_id());
@@ -1488,7 +1487,7 @@ static void noinstr rcu_dynticks_task_enter(void)
 }
 
 /* Record no current task on dyntick-idle exit. */
-static void noinstr rcu_dynticks_task_exit(void)
+static __always_inline void rcu_dynticks_task_exit(void)
 {
 #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL)
 	WRITE_ONCE(current->rcu_tasks_idle_cpu, -1);
@@ -1496,7 +1495,7 @@ static void noinstr rcu_dynticks_task_exit(void)
 }
 
 /* Turn on heavyweight RCU tasks trace readers on idle/user entry. */
-static void rcu_dynticks_task_trace_enter(void)
+static __always_inline void rcu_dynticks_task_trace_enter(void)
 {
 #ifdef CONFIG_TASKS_TRACE_RCU
 	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB))
@@ -1505,7 +1504,7 @@ static void rcu_dynticks_task_trace_enter(void)
 }
 
 /* Turn off heavyweight RCU tasks trace readers on idle/user exit. */
-static void rcu_dynticks_task_trace_exit(void)
+static __always_inline void rcu_dynticks_task_trace_exit(void)
 {
 #ifdef CONFIG_TASKS_TRACE_RCU
 	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB))
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 690b0cec7459..156892c22bb5 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -54,11 +54,11 @@
 #define MODULE_PARAM_PREFIX "rcupdate."
 
 #ifndef CONFIG_TINY_RCU
-module_param(rcu_expedited, int, 0);
-module_param(rcu_normal, int, 0);
+module_param(rcu_expedited, int, 0444);
+module_param(rcu_normal, int, 0444);
 static int rcu_normal_after_boot = IS_ENABLED(CONFIG_PREEMPT_RT);
-#ifndef CONFIG_PREEMPT_RT
-module_param(rcu_normal_after_boot, int, 0);
+#if !defined(CONFIG_PREEMPT_RT) || defined(CONFIG_NO_HZ_FULL)
+module_param(rcu_normal_after_boot, int, 0444);
 #endif
 #endif /* #ifndef CONFIG_TINY_RCU */