Merge branch 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull RCU updates from Ingo Molnar:
 "The main RCU changes in this cycle were:

   - Updates to use cond_resched() instead of cond_resched_rcu_qs()
     where feasible (currently everywhere except in kernel/rcu and in
     kernel/torture.c). Also a couple of fixes to avoid sending IPIs to
     offline CPUs.

   - Updates to simplify RCU's dyntick-idle handling.

   - Updates to remove almost all uses of smp_read_barrier_depends() and
     read_barrier_depends().

   - Torture-test updates.

   - Miscellaneous fixes"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (72 commits)
  torture: Save a line in stutter_wait(): while -> for
  torture: Eliminate torture_runnable and perf_runnable
  torture: Make stutter less vulnerable to compilers and races
  locking/locktorture: Fix num reader/writer corner cases
  locking/locktorture: Fix rwsem reader_delay
  torture: Place all torture-test modules in one MAINTAINERS group
  rcutorture/kvm-build.sh: Skip build directory check
  rcutorture: Simplify functions.sh include path
  rcutorture: Simplify logging
  rcutorture/kvm-recheck-*: Improve result directory readability check
  rcutorture/kvm.sh: Support execution from any directory
  rcutorture/kvm.sh: Use consistent help text for --qemu-args
  rcutorture/kvm.sh: Remove unused variable, `alldone`
  rcutorture: Remove unused script, config2frag.sh
  rcutorture/configinit: Fix build directory error message
  rcutorture: Preempt RCU-preempt readers more vigorously
  torture: Reduce #ifdefs for preempt_schedule()
  rcu: Remove have_rcu_nocb_mask from tree_plugin.h
  rcu: Add comment giving debug strategy for double call_rcu()
  tracing, rcu: Hide trace event rcu_nocb_wake when not used
  ...

18 files changed, 311 insertions, 418 deletions

diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 267f6ef91d97..ce6848e46e94 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1167,8 +1167,8 @@ static int xol_add_vma(struct mm_struct *mm, struct xol_area *area)
 	}
 
 	ret = 0;
-	smp_wmb();	/* pairs with get_xol_area() */
-	mm->uprobes_state.xol_area = area;
+	/* pairs with get_xol_area() */
+	smp_store_release(&mm->uprobes_state.xol_area, area); /* ^^^ */
  fail:
 	up_write(&mm->mmap_sem);
 
@@ -1230,8 +1230,8 @@ static struct xol_area *get_xol_area(void)
 	if (!mm->uprobes_state.xol_area)
 		__create_xol_area(0);
 
-	area = mm->uprobes_state.xol_area;
-	smp_read_barrier_depends();	/* pairs with wmb in xol_add_vma() */
+	/* Pairs with xol_add_vma() smp_store_release() */
+	area = READ_ONCE(mm->uprobes_state.xol_area); /* ^^^ */
 	return area;
 }
 
@@ -1528,8 +1528,8 @@ static unsigned long get_trampoline_vaddr(void)
 	struct xol_area *area;
 	unsigned long trampoline_vaddr = -1;
 
-	area = current->mm->uprobes_state.xol_area;
-	smp_read_barrier_depends();
+	/* Pairs with xol_add_vma() smp_store_release() */
+	area = READ_ONCE(current->mm->uprobes_state.xol_area); /* ^^^ */
 	if (area)
 		trampoline_vaddr = area->vaddr;
 
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index f24582d4dad3..6850ffd69125 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -77,10 +77,6 @@ struct lock_stress_stats {
 	long n_lock_acquired;
 };
 
-int torture_runnable = IS_ENABLED(MODULE);
-module_param(torture_runnable, int, 0444);
-MODULE_PARM_DESC(torture_runnable, "Start locktorture at module init");
-
 /* Forward reference. */
 static void lock_torture_cleanup(void);
 
@@ -130,10 +126,8 @@ static void torture_lock_busted_write_delay(struct torture_random_state *trsp)
 	if (!(torture_random(trsp) %
 	      (cxt.nrealwriters_stress * 2000 * longdelay_ms)))
 		mdelay(longdelay_ms);
-#ifdef CONFIG_PREEMPT
 	if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
-		preempt_schedule();  /* Allow test to be preempted. */
-#endif
+		torture_preempt_schedule();  /* Allow test to be preempted. */
 }
 
 static void torture_lock_busted_write_unlock(void)
@@ -179,10 +173,8 @@ static void torture_spin_lock_write_delay(struct torture_random_state *trsp)
 	if (!(torture_random(trsp) %
 	      (cxt.nrealwriters_stress * 2 * shortdelay_us)))
 		udelay(shortdelay_us);
-#ifdef CONFIG_PREEMPT
 	if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
-		preempt_schedule();  /* Allow test to be preempted. */
-#endif
+		torture_preempt_schedule();  /* Allow test to be preempted. */
 }
 
 static void torture_spin_lock_write_unlock(void) __releases(torture_spinlock)
@@ -352,10 +344,8 @@ static void torture_mutex_delay(struct torture_random_state *trsp)
 		mdelay(longdelay_ms * 5);
 	else
 		mdelay(longdelay_ms / 5);
-#ifdef CONFIG_PREEMPT
 	if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
-		preempt_schedule();  /* Allow test to be preempted. */
-#endif
+		torture_preempt_schedule();  /* Allow test to be preempted. */
 }
 
 static void torture_mutex_unlock(void) __releases(torture_mutex)
@@ -507,10 +497,8 @@ static void torture_rtmutex_delay(struct torture_random_state *trsp)
 	if (!(torture_random(trsp) %
 	      (cxt.nrealwriters_stress * 2 * shortdelay_us)))
 		udelay(shortdelay_us);
-#ifdef CONFIG_PREEMPT
 	if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
-		preempt_schedule();  /* Allow test to be preempted. */
-#endif
+		torture_preempt_schedule();  /* Allow test to be preempted. */
 }
 
 static void torture_rtmutex_unlock(void) __releases(torture_rtmutex)
@@ -547,10 +535,8 @@ static void torture_rwsem_write_delay(struct torture_random_state *trsp)
 		mdelay(longdelay_ms * 10);
 	else
 		mdelay(longdelay_ms / 10);
-#ifdef CONFIG_PREEMPT
 	if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
-		preempt_schedule();  /* Allow test to be preempted. */
-#endif
+		torture_preempt_schedule();  /* Allow test to be preempted. */
 }
 
 static void torture_rwsem_up_write(void) __releases(torture_rwsem)
@@ -570,14 +556,12 @@ static void torture_rwsem_read_delay(struct torture_random_state *trsp)
 
 	/* We want a long delay occasionally to force massive contention.  */
 	if (!(torture_random(trsp) %
-	      (cxt.nrealwriters_stress * 2000 * longdelay_ms)))
+	      (cxt.nrealreaders_stress * 2000 * longdelay_ms)))
 		mdelay(longdelay_ms * 2);
 	else
 		mdelay(longdelay_ms / 2);
-#ifdef CONFIG_PREEMPT
 	if (!(torture_random(trsp) % (cxt.nrealreaders_stress * 20000)))
-		preempt_schedule();  /* Allow test to be preempted. */
-#endif
+		torture_preempt_schedule();  /* Allow test to be preempted. */
 }
 
 static void torture_rwsem_up_read(void) __releases(torture_rwsem)
@@ -715,8 +699,7 @@ static void __torture_print_stats(char *page,
 {
 	bool fail = 0;
 	int i, n_stress;
-	long max = 0;
-	long min = statp[0].n_lock_acquired;
+	long max = 0, min = statp ? statp[0].n_lock_acquired : 0;
 	long long sum = 0;
 
 	n_stress = write ? cxt.nrealwriters_stress : cxt.nrealreaders_stress;
@@ -823,7 +806,7 @@ static void lock_torture_cleanup(void)
 	 * such, only perform the underlying torture-specific cleanups,
 	 * and avoid anything related to locktorture.
 	 */
-	if (!cxt.lwsa)
+	if (!cxt.lwsa && !cxt.lrsa)
 		goto end;
 
 	if (writer_tasks) {
@@ -879,7 +862,7 @@ static int __init lock_torture_init(void)
 		&percpu_rwsem_lock_ops,
 	};
 
-	if (!torture_init_begin(torture_type, verbose, &torture_runnable))
+	if (!torture_init_begin(torture_type, verbose))
 		return -EBUSY;
 
 	/* Process args and tell the world that the torturer is on the job. */
@@ -898,6 +881,13 @@ static int __init lock_torture_init(void)
 		firsterr = -EINVAL;
 		goto unwind;
 	}
+
+	if (nwriters_stress == 0 && nreaders_stress == 0) {
+		pr_alert("lock-torture: must run at least one locking thread\n");
+		firsterr = -EINVAL;
+		goto unwind;
+	}
+
 	if (cxt.cur_ops->init)
 		cxt.cur_ops->init();
 
@@ -921,17 +911,19 @@ static int __init lock_torture_init(void)
 #endif
 
 	/* Initialize the statistics so that each run gets its own numbers. */
+	if (nwriters_stress) {
+		lock_is_write_held = 0;
+		cxt.lwsa = kmalloc(sizeof(*cxt.lwsa) * cxt.nrealwriters_stress, GFP_KERNEL);
+		if (cxt.lwsa == NULL) {
+			VERBOSE_TOROUT_STRING("cxt.lwsa: Out of memory");
+			firsterr = -ENOMEM;
+			goto unwind;
+		}
 
-	lock_is_write_held = 0;
-	cxt.lwsa = kmalloc(sizeof(*cxt.lwsa) * cxt.nrealwriters_stress, GFP_KERNEL);
-	if (cxt.lwsa == NULL) {
-		VERBOSE_TOROUT_STRING("cxt.lwsa: Out of memory");
-		firsterr = -ENOMEM;
-		goto unwind;
-	}
-	for (i = 0; i < cxt.nrealwriters_stress; i++) {
-		cxt.lwsa[i].n_lock_fail = 0;
-		cxt.lwsa[i].n_lock_acquired = 0;
+		for (i = 0; i < cxt.nrealwriters_stress; i++) {
+			cxt.lwsa[i].n_lock_fail = 0;
+			cxt.lwsa[i].n_lock_acquired = 0;
+		}
 	}
 
 	if (cxt.cur_ops->readlock) {
@@ -948,19 +940,21 @@ static int __init lock_torture_init(void)
 			cxt.nrealreaders_stress = cxt.nrealwriters_stress;
 		}
 
-		lock_is_read_held = 0;
-		cxt.lrsa = kmalloc(sizeof(*cxt.lrsa) * cxt.nrealreaders_stress, GFP_KERNEL);
-		if (cxt.lrsa == NULL) {
-			VERBOSE_TOROUT_STRING("cxt.lrsa: Out of memory");
-			firsterr = -ENOMEM;
-			kfree(cxt.lwsa);
-			cxt.lwsa = NULL;
-			goto unwind;
-		}
-
-		for (i = 0; i < cxt.nrealreaders_stress; i++) {
-			cxt.lrsa[i].n_lock_fail = 0;
-			cxt.lrsa[i].n_lock_acquired = 0;
+		if (nreaders_stress) {
+			lock_is_read_held = 0;
+			cxt.lrsa = kmalloc(sizeof(*cxt.lrsa) * cxt.nrealreaders_stress, GFP_KERNEL);
+			if (cxt.lrsa == NULL) {
+				VERBOSE_TOROUT_STRING("cxt.lrsa: Out of memory");
+				firsterr = -ENOMEM;
+				kfree(cxt.lwsa);
+				cxt.lwsa = NULL;
+				goto unwind;
+			}
+
+			for (i = 0; i < cxt.nrealreaders_stress; i++) {
+				cxt.lrsa[i].n_lock_fail = 0;
+				cxt.lrsa[i].n_lock_acquired = 0;
+			}
 		}
 	}
 
@@ -990,12 +984,14 @@ static int __init lock_torture_init(void)
 			goto unwind;
 	}
 
-	writer_tasks = kzalloc(cxt.nrealwriters_stress * sizeof(writer_tasks[0]),
-			       GFP_KERNEL);
-	if (writer_tasks == NULL) {
-		VERBOSE_TOROUT_ERRSTRING("writer_tasks: Out of memory");
-		firsterr = -ENOMEM;
-		goto unwind;
+	if (nwriters_stress) {
+		writer_tasks = kzalloc(cxt.nrealwriters_stress * sizeof(writer_tasks[0]),
+				       GFP_KERNEL);
+		if (writer_tasks == NULL) {
+			VERBOSE_TOROUT_ERRSTRING("writer_tasks: Out of memory");
+			firsterr = -ENOMEM;
+			goto unwind;
+		}
 	}
 
 	if (cxt.cur_ops->readlock) {
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index 294294c71ba4..38ece035039e 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -170,7 +170,7 @@ static __always_inline void clear_pending_set_locked(struct qspinlock *lock)
  * @tail : The new queue tail code word
  * Return: The previous queue tail code word
  *
- * xchg(lock, tail)
+ * xchg(lock, tail), which heads an address dependency
  *
  * p,*,* -> n,*,* ; prev = xchg(lock, node)
  */
@@ -409,13 +409,11 @@ queue:
 	if (old & _Q_TAIL_MASK) {
 		prev = decode_tail(old);
 		/*
-		 * The above xchg_tail() is also a load of @lock which generates,
-		 * through decode_tail(), a pointer.
-		 *
-		 * The address dependency matches the RELEASE of xchg_tail()
-		 * such that the access to @prev must happen after.
+		 * The above xchg_tail() is also a load of @lock which
+		 * generates, through decode_tail(), a pointer.  The address
+		 * dependency matches the RELEASE of xchg_tail() such that
+		 * the subsequent access to @prev happens after.
 		 */
-		smp_read_barrier_depends();
 
 		WRITE_ONCE(prev->next, node);
 
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 59c471de342a..6334f2c1abd0 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -30,31 +30,8 @@
 #define RCU_TRACE(stmt)
 #endif /* #else #ifdef CONFIG_RCU_TRACE */
 
-/*
- * Process-level increment to ->dynticks_nesting field.  This allows for
- * architectures that use half-interrupts and half-exceptions from
- * process context.
- *
- * DYNTICK_TASK_NEST_MASK defines a field of width DYNTICK_TASK_NEST_WIDTH
- * that counts the number of process-based reasons why RCU cannot
- * consider the corresponding CPU to be idle, and DYNTICK_TASK_NEST_VALUE
- * is the value used to increment or decrement this field.
- *
- * The rest of the bits could in principle be used to count interrupts,
- * but this would mean that a negative-one value in the interrupt
- * field could incorrectly zero out the DYNTICK_TASK_NEST_MASK field.
- * We therefore provide a two-bit guard field defined by DYNTICK_TASK_MASK
- * that is set to DYNTICK_TASK_FLAG upon initial exit from idle.
- * The DYNTICK_TASK_EXIT_IDLE value is thus the combined value used upon
- * initial exit from idle.
- */
-#define DYNTICK_TASK_NEST_WIDTH 7
-#define DYNTICK_TASK_NEST_VALUE ((LLONG_MAX >> DYNTICK_TASK_NEST_WIDTH) + 1)
-#define DYNTICK_TASK_NEST_MASK  (LLONG_MAX - DYNTICK_TASK_NEST_VALUE + 1)
-#define DYNTICK_TASK_FLAG	   ((DYNTICK_TASK_NEST_VALUE / 8) * 2)
-#define DYNTICK_TASK_MASK	   ((DYNTICK_TASK_NEST_VALUE / 8) * 3)
-#define DYNTICK_TASK_EXIT_IDLE	   (DYNTICK_TASK_NEST_VALUE + \
-				    DYNTICK_TASK_FLAG)
+/* Offset to allow for unmatched rcu_irq_{enter,exit}(). */
+#define DYNTICK_IRQ_NONIDLE	((LONG_MAX / 2) + 1)
 
 
 /*
diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index 1f87a02c3399..d1ebdf9868bb 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuperf.c
@@ -106,10 +106,6 @@ static int rcu_perf_writer_state;
 #define MAX_MEAS 10000
 #define MIN_MEAS 100
 
-static int perf_runnable = IS_ENABLED(MODULE);
-module_param(perf_runnable, int, 0444);
-MODULE_PARM_DESC(perf_runnable, "Start rcuperf at boot");
-
 /*
  * Operations vector for selecting different types of tests.
  */
@@ -646,7 +642,7 @@ rcu_perf_init(void)
 		&tasks_ops,
 	};
 
-	if (!torture_init_begin(perf_type, verbose, &perf_runnable))
+	if (!torture_init_begin(perf_type, verbose))
 		return -EBUSY;
 
 	/* Process args and tell the world that the perf'er is on the job. */
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 74f6b0146b98..308e6fdbced8 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -187,10 +187,6 @@ static const char *rcu_torture_writer_state_getname(void)
 	return rcu_torture_writer_state_names[i];
 }
 
-static int torture_runnable = IS_ENABLED(MODULE);
-module_param(torture_runnable, int, 0444);
-MODULE_PARM_DESC(torture_runnable, "Start rcutorture at boot");
-
 #if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU)
 #define rcu_can_boost() 1
 #else /* #if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU) */
@@ -315,11 +311,9 @@ static void rcu_read_delay(struct torture_random_state *rrsp)
 	}
 	if (!(torture_random(rrsp) % (nrealreaders * 2 * shortdelay_us)))
 		udelay(shortdelay_us);
-#ifdef CONFIG_PREEMPT
 	if (!preempt_count() &&
-	    !(torture_random(rrsp) % (nrealreaders * 20000)))
-		preempt_schedule();  /* No QS if preempt_disable() in effect */
-#endif
+	    !(torture_random(rrsp) % (nrealreaders * 500)))
+		torture_preempt_schedule();  /* QS only if preemptible. */
 }
 
 static void rcu_torture_read_unlock(int idx) __releases(RCU)
@@ -1731,7 +1725,7 @@ rcu_torture_init(void)
 		&sched_ops, &tasks_ops,
 	};
 
-	if (!torture_init_begin(torture_type, verbose, &torture_runnable))
+	if (!torture_init_begin(torture_type, verbose))
 		return -EBUSY;
 
 	/* Process args and tell the world that the torturer is on the job. */
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 6d5880089ff6..d5cea81378cc 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -53,6 +53,33 @@ static void srcu_invoke_callbacks(struct work_struct *work);
 static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay);
 static void process_srcu(struct work_struct *work);
 
+/* Wrappers for lock acquisition and release, see raw_spin_lock_rcu_node(). */
+#define spin_lock_rcu_node(p)					\
+do {									\
+	spin_lock(&ACCESS_PRIVATE(p, lock));			\
+	smp_mb__after_unlock_lock();					\
+} while (0)
+
+#define spin_unlock_rcu_node(p) spin_unlock(&ACCESS_PRIVATE(p, lock))
+
+#define spin_lock_irq_rcu_node(p)					\
+do {									\
+	spin_lock_irq(&ACCESS_PRIVATE(p, lock));			\
+	smp_mb__after_unlock_lock();					\
+} while (0)
+
+#define spin_unlock_irq_rcu_node(p)					\
+	spin_unlock_irq(&ACCESS_PRIVATE(p, lock))
+
+#define spin_lock_irqsave_rcu_node(p, flags)			\
+do {									\
+	spin_lock_irqsave(&ACCESS_PRIVATE(p, lock), flags);	\
+	smp_mb__after_unlock_lock();					\
+} while (0)
+
+#define spin_unlock_irqrestore_rcu_node(p, flags)			\
+	spin_unlock_irqrestore(&ACCESS_PRIVATE(p, lock), flags)	\
+
 /*
  * Initialize SRCU combining tree.  Note that statically allocated
  * srcu_struct structures might already have srcu_read_lock() and
@@ -77,7 +104,7 @@ static void init_srcu_struct_nodes(struct srcu_struct *sp, bool is_static)
 
 	/* Each pass through this loop initializes one srcu_node structure. */
 	rcu_for_each_node_breadth_first(sp, snp) {
-		raw_spin_lock_init(&ACCESS_PRIVATE(snp, lock));
+		spin_lock_init(&ACCESS_PRIVATE(snp, lock));
 		WARN_ON_ONCE(ARRAY_SIZE(snp->srcu_have_cbs) !=
 			     ARRAY_SIZE(snp->srcu_data_have_cbs));
 		for (i = 0; i < ARRAY_SIZE(snp->srcu_have_cbs); i++) {
@@ -111,7 +138,7 @@ static void init_srcu_struct_nodes(struct srcu_struct *sp, bool is_static)
 	snp_first = sp->level[level];
 	for_each_possible_cpu(cpu) {
 		sdp = per_cpu_ptr(sp->sda, cpu);
-		raw_spin_lock_init(&ACCESS_PRIVATE(sdp, lock));
+		spin_lock_init(&ACCESS_PRIVATE(sdp, lock));
 		rcu_segcblist_init(&sdp->srcu_cblist);
 		sdp->srcu_cblist_invoking = false;
 		sdp->srcu_gp_seq_needed = sp->srcu_gp_seq;
@@ -170,7 +197,7 @@ int __init_srcu_struct(struct srcu_struct *sp, const char *name,
 	/* Don't re-initialize a lock while it is held. */
 	debug_check_no_locks_freed((void *)sp, sizeof(*sp));
 	lockdep_init_map(&sp->dep_map, name, key, 0);
-	raw_spin_lock_init(&ACCESS_PRIVATE(sp, lock));
+	spin_lock_init(&ACCESS_PRIVATE(sp, lock));
 	return init_srcu_struct_fields(sp, false);
 }
 EXPORT_SYMBOL_GPL(__init_srcu_struct);
@@ -187,7 +214,7 @@ EXPORT_SYMBOL_GPL(__init_srcu_struct);
  */
 int init_srcu_struct(struct srcu_struct *sp)
 {
-	raw_spin_lock_init(&ACCESS_PRIVATE(sp, lock));
+	spin_lock_init(&ACCESS_PRIVATE(sp, lock));
 	return init_srcu_struct_fields(sp, false);
 }
 EXPORT_SYMBOL_GPL(init_srcu_struct);
@@ -210,13 +237,13 @@ static void check_init_srcu_struct(struct srcu_struct *sp)
 	/* The smp_load_acquire() pairs with the smp_store_release(). */
 	if (!rcu_seq_state(smp_load_acquire(&sp->srcu_gp_seq_needed))) /*^^^*/
 		return; /* Already initialized. */
-	raw_spin_lock_irqsave_rcu_node(sp, flags);
+	spin_lock_irqsave_rcu_node(sp, flags);
 	if (!rcu_seq_state(sp->srcu_gp_seq_needed)) {
-		raw_spin_unlock_irqrestore_rcu_node(sp, flags);
+		spin_unlock_irqrestore_rcu_node(sp, flags);
 		return;
 	}
 	init_srcu_struct_fields(sp, true);
-	raw_spin_unlock_irqrestore_rcu_node(sp, flags);
+	spin_unlock_irqrestore_rcu_node(sp, flags);
 }
 
 /*
@@ -513,7 +540,7 @@ static void srcu_gp_end(struct srcu_struct *sp)
 	mutex_lock(&sp->srcu_cb_mutex);
 
 	/* End the current grace period. */
-	raw_spin_lock_irq_rcu_node(sp);
+	spin_lock_irq_rcu_node(sp);
 	idx = rcu_seq_state(sp->srcu_gp_seq);
 	WARN_ON_ONCE(idx != SRCU_STATE_SCAN2);
 	cbdelay = srcu_get_delay(sp);
@@ -522,7 +549,7 @@ static void srcu_gp_end(struct srcu_struct *sp)
 	gpseq = rcu_seq_current(&sp->srcu_gp_seq);
 	if (ULONG_CMP_LT(sp->srcu_gp_seq_needed_exp, gpseq))
 		sp->srcu_gp_seq_needed_exp = gpseq;
-	raw_spin_unlock_irq_rcu_node(sp);
+	spin_unlock_irq_rcu_node(sp);
 	mutex_unlock(&sp->srcu_gp_mutex);
 	/* A new grace period can start at this point.  But only one. */
 
@@ -530,7 +557,7 @@ static void srcu_gp_end(struct srcu_struct *sp)
 	idx = rcu_seq_ctr(gpseq) % ARRAY_SIZE(snp->srcu_have_cbs);
 	idxnext = (idx + 1) % ARRAY_SIZE(snp->srcu_have_cbs);
 	rcu_for_each_node_breadth_first(sp, snp) {
-		raw_spin_lock_irq_rcu_node(snp);
+		spin_lock_irq_rcu_node(snp);
 		cbs = false;
 		if (snp >= sp->level[rcu_num_lvls - 1])
 			cbs = snp->srcu_have_cbs[idx] == gpseq;
@@ -540,7 +567,7 @@ static void srcu_gp_end(struct srcu_struct *sp)
 			snp->srcu_gp_seq_needed_exp = gpseq;
 		mask = snp->srcu_data_have_cbs[idx];
 		snp->srcu_data_have_cbs[idx] = 0;
-		raw_spin_unlock_irq_rcu_node(snp);
+		spin_unlock_irq_rcu_node(snp);
 		if (cbs)
 			srcu_schedule_cbs_snp(sp, snp, mask, cbdelay);
 
@@ -548,11 +575,11 @@ static void srcu_gp_end(struct srcu_struct *sp)
 		if (!(gpseq & counter_wrap_check))
 			for (cpu = snp->grplo; cpu <= snp->grphi; cpu++) {
 				sdp = per_cpu_ptr(sp->sda, cpu);
-				raw_spin_lock_irqsave_rcu_node(sdp, flags);
+				spin_lock_irqsave_rcu_node(sdp, flags);
 				if (ULONG_CMP_GE(gpseq,
 						 sdp->srcu_gp_seq_needed + 100))
 					sdp->srcu_gp_seq_needed = gpseq;
-				raw_spin_unlock_irqrestore_rcu_node(sdp, flags);
+				spin_unlock_irqrestore_rcu_node(sdp, flags);
 			}
 	}
 
@@ -560,17 +587,17 @@ static void srcu_gp_end(struct srcu_struct *sp)
 	mutex_unlock(&sp->srcu_cb_mutex);
 
 	/* Start a new grace period if needed. */
-	raw_spin_lock_irq_rcu_node(sp);
+	spin_lock_irq_rcu_node(sp);
 	gpseq = rcu_seq_current(&sp->srcu_gp_seq);
 	if (!rcu_seq_state(gpseq) &&
 	    ULONG_CMP_LT(gpseq, sp->srcu_gp_seq_needed)) {
 		srcu_gp_start(sp);
-		raw_spin_unlock_irq_rcu_node(sp);
+		spin_unlock_irq_rcu_node(sp);
 		/* Throttle expedited grace periods: Should be rare! */
 		srcu_reschedule(sp, rcu_seq_ctr(gpseq) & 0x3ff
 				    ? 0 : SRCU_INTERVAL);
 	} else {
-		raw_spin_unlock_irq_rcu_node(sp);
+		spin_unlock_irq_rcu_node(sp);
 	}
 }
 
@@ -590,18 +617,18 @@ static void srcu_funnel_exp_start(struct srcu_struct *sp, struct srcu_node *snp,
 		if (rcu_seq_done(&sp->srcu_gp_seq, s) ||
 		    ULONG_CMP_GE(READ_ONCE(snp->srcu_gp_seq_needed_exp), s))
 			return;
-		raw_spin_lock_irqsave_rcu_node(snp, flags);
+		spin_lock_irqsave_rcu_node(snp, flags);
 		if (ULONG_CMP_GE(snp->srcu_gp_seq_needed_exp, s)) {
-			raw_spin_unlock_irqrestore_rcu_node(snp, flags);
+			spin_unlock_irqrestore_rcu_node(snp, flags);
 			return;
 		}
 		WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s);
-		raw_spin_unlock_irqrestore_rcu_node(snp, flags);
+		spin_unlock_irqrestore_rcu_node(snp, flags);
 	}
-	raw_spin_lock_irqsave_rcu_node(sp, flags);
+	spin_lock_irqsave_rcu_node(sp, flags);
 	if (!ULONG_CMP_LT(sp->srcu_gp_seq_needed_exp, s))
 		sp->srcu_gp_seq_needed_exp = s;
-	raw_spin_unlock_irqrestore_rcu_node(sp, flags);
+	spin_unlock_irqrestore_rcu_node(sp, flags);
 }
 
 /*
@@ -623,12 +650,12 @@ static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp,
 	for (; snp != NULL; snp = snp->srcu_parent) {
 		if (rcu_seq_done(&sp->srcu_gp_seq, s) && snp != sdp->mynode)
 			return; /* GP already done and CBs recorded. */
-		raw_spin_lock_irqsave_rcu_node(snp, flags);
+		spin_lock_irqsave_rcu_node(snp, flags);
 		if (ULONG_CMP_GE(snp->srcu_have_cbs[idx], s)) {
 			snp_seq = snp->srcu_have_cbs[idx];
 			if (snp == sdp->mynode && snp_seq == s)
 				snp->srcu_data_have_cbs[idx] |= sdp->grpmask;
-			raw_spin_unlock_irqrestore_rcu_node(snp, flags);
+			spin_unlock_irqrestore_rcu_node(snp, flags);
 			if (snp == sdp->mynode && snp_seq != s) {
 				srcu_schedule_cbs_sdp(sdp, do_norm
 							   ? SRCU_INTERVAL
@@ -644,11 +671,11 @@ static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp,
 			snp->srcu_data_have_cbs[idx] |= sdp->grpmask;
 		if (!do_norm && ULONG_CMP_LT(snp->srcu_gp_seq_needed_exp, s))
 			snp->srcu_gp_seq_needed_exp = s;
-		raw_spin_unlock_irqrestore_rcu_node(snp, flags);
+		spin_unlock_irqrestore_rcu_node(snp, flags);
 	}
 
 	/* Top of tree, must ensure the grace period will be started. */
-	raw_spin_lock_irqsave_rcu_node(sp, flags);
+	spin_lock_irqsave_rcu_node(sp, flags);
 	if (ULONG_CMP_LT(sp->srcu_gp_seq_needed, s)) {
 		/*
 		 * Record need for grace period s.  Pair with load
@@ -667,7 +694,7 @@ static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp,
 		queue_delayed_work(system_power_efficient_wq, &sp->work,
 				   srcu_get_delay(sp));
 	}
-	raw_spin_unlock_irqrestore_rcu_node(sp, flags);
+	spin_unlock_irqrestore_rcu_node(sp, flags);
 }
 
 /*
@@ -830,7 +857,7 @@ void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
 	rhp->func = func;
 	local_irq_save(flags);
 	sdp = this_cpu_ptr(sp->sda);
-	raw_spin_lock_rcu_node(sdp);
+	spin_lock_rcu_node(sdp);
 	rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp, false);
 	rcu_segcblist_advance(&sdp->srcu_cblist,
 			      rcu_seq_current(&sp->srcu_gp_seq));
@@ -844,7 +871,7 @@ void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
 		sdp->srcu_gp_seq_needed_exp = s;
 		needexp = true;
 	}
-	raw_spin_unlock_irqrestore_rcu_node(sdp, flags);
+	spin_unlock_irqrestore_rcu_node(sdp, flags);
 	if (needgp)
 		srcu_funnel_gp_start(sp, sdp, s, do_norm);
 	else if (needexp)
@@ -900,7 +927,7 @@ static void __synchronize_srcu(struct srcu_struct *sp, bool do_norm)
 
 	/*
 	 * Make sure that later code is ordered after the SRCU grace
-	 * period.  This pairs with the raw_spin_lock_irq_rcu_node()
+	 * period.  This pairs with the spin_lock_irq_rcu_node()
 	 * in srcu_invoke_callbacks().  Unlike Tree RCU, this is needed
 	 * because the current CPU might have been totally uninvolved with
 	 * (and thus unordered against) that grace period.
@@ -1024,7 +1051,7 @@ void srcu_barrier(struct srcu_struct *sp)
 	 */
 	for_each_possible_cpu(cpu) {
 		sdp = per_cpu_ptr(sp->sda, cpu);
-		raw_spin_lock_irq_rcu_node(sdp);
+		spin_lock_irq_rcu_node(sdp);
 		atomic_inc(&sp->srcu_barrier_cpu_cnt);
 		sdp->srcu_barrier_head.func = srcu_barrier_cb;
 		debug_rcu_head_queue(&sdp->srcu_barrier_head);
@@ -1033,7 +1060,7 @@ void srcu_barrier(struct srcu_struct *sp)
 			debug_rcu_head_unqueue(&sdp->srcu_barrier_head);
 			atomic_dec(&sp->srcu_barrier_cpu_cnt);
 		}
-		raw_spin_unlock_irq_rcu_node(sdp);
+		spin_unlock_irq_rcu_node(sdp);
 	}
 
 	/* Remove the initial count, at which point reaching zero can happen. */
@@ -1082,17 +1109,17 @@ static void srcu_advance_state(struct srcu_struct *sp)
 	 */
 	idx = rcu_seq_state(smp_load_acquire(&sp->srcu_gp_seq)); /* ^^^ */
 	if (idx == SRCU_STATE_IDLE) {
-		raw_spin_lock_irq_rcu_node(sp);
+		spin_lock_irq_rcu_node(sp);
 		if (ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed)) {
 			WARN_ON_ONCE(rcu_seq_state(sp->srcu_gp_seq));
-			raw_spin_unlock_irq_rcu_node(sp);
+			spin_unlock_irq_rcu_node(sp);
 			mutex_unlock(&sp->srcu_gp_mutex);
 			return;
 		}
 		idx = rcu_seq_state(READ_ONCE(sp->srcu_gp_seq));
 		if (idx == SRCU_STATE_IDLE)
 			srcu_gp_start(sp);
-		raw_spin_unlock_irq_rcu_node(sp);
+		spin_unlock_irq_rcu_node(sp);
 		if (idx != SRCU_STATE_IDLE) {
 			mutex_unlock(&sp->srcu_gp_mutex);
 			return; /* Someone else started the grace period. */
@@ -1141,19 +1168,19 @@ static void srcu_invoke_callbacks(struct work_struct *work)
 	sdp = container_of(work, struct srcu_data, work.work);
 	sp = sdp->sp;
 	rcu_cblist_init(&ready_cbs);
-	raw_spin_lock_irq_rcu_node(sdp);
+	spin_lock_irq_rcu_node(sdp);
 	rcu_segcblist_advance(&sdp->srcu_cblist,
 			      rcu_seq_current(&sp->srcu_gp_seq));
 	if (sdp->srcu_cblist_invoking ||
 	    !rcu_segcblist_ready_cbs(&sdp->srcu_cblist)) {
-		raw_spin_unlock_irq_rcu_node(sdp);
+		spin_unlock_irq_rcu_node(sdp);
 		return;  /* Someone else on the job or nothing to do. */
 	}
 
 	/* We are on the job!  Extract and invoke ready callbacks. */
 	sdp->srcu_cblist_invoking = true;
 	rcu_segcblist_extract_done_cbs(&sdp->srcu_cblist, &ready_cbs);
-	raw_spin_unlock_irq_rcu_node(sdp);
+	spin_unlock_irq_rcu_node(sdp);
 	rhp = rcu_cblist_dequeue(&ready_cbs);
 	for (; rhp != NULL; rhp = rcu_cblist_dequeue(&ready_cbs)) {
 		debug_rcu_head_unqueue(rhp);
@@ -1166,13 +1193,13 @@ static void srcu_invoke_callbacks(struct work_struct *work)
 	 * Update counts, accelerate new callbacks, and if needed,
 	 * schedule another round of callback invocation.
 	 */
-	raw_spin_lock_irq_rcu_node(sdp);
+	spin_lock_irq_rcu_node(sdp);
 	rcu_segcblist_insert_count(&sdp->srcu_cblist, &ready_cbs);
 	(void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
 				       rcu_seq_snap(&sp->srcu_gp_seq));
 	sdp->srcu_cblist_invoking = false;
 	more = rcu_segcblist_ready_cbs(&sdp->srcu_cblist);
-	raw_spin_unlock_irq_rcu_node(sdp);
+	spin_unlock_irq_rcu_node(sdp);
 	if (more)
 		srcu_schedule_cbs_sdp(sdp, 0);
 }
@@ -1185,7 +1212,7 @@ static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay)
 {
 	bool pushgp = true;
 
-	raw_spin_lock_irq_rcu_node(sp);
+	spin_lock_irq_rcu_node(sp);
 	if (ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed)) {
 		if (!WARN_ON_ONCE(rcu_seq_state(sp->srcu_gp_seq))) {
 			/* All requests fulfilled, time to go idle. */
@@ -1195,7 +1222,7 @@ static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay)
 		/* Outstanding request and no GP.  Start one. */
 		srcu_gp_start(sp);
 	}
-	raw_spin_unlock_irq_rcu_node(sp);
+	spin_unlock_irq_rcu_node(sp);
 
 	if (pushgp)
 		queue_delayed_work(system_power_efficient_wq, &sp->work, delay);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index f9c0ca2ccf0c..491bdf39f276 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -265,25 +265,12 @@ void rcu_bh_qs(void)
 #endif
 
 static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
-	.dynticks_nesting = DYNTICK_TASK_EXIT_IDLE,
+	.dynticks_nesting = 1,
+	.dynticks_nmi_nesting = DYNTICK_IRQ_NONIDLE,
 	.dynticks = ATOMIC_INIT(RCU_DYNTICK_CTRL_CTR),
 };
 
 /*
- * There's a few places, currently just in the tracing infrastructure,
- * that uses rcu_irq_enter() to make sure RCU is watching. But there's
- * a small location where that will not even work. In those cases
- * rcu_irq_enter_disabled() needs to be checked to make sure rcu_irq_enter()
- * can be called.
- */
-static DEFINE_PER_CPU(bool, disable_rcu_irq_enter);
-
-bool rcu_irq_enter_disabled(void)
-{
-	return this_cpu_read(disable_rcu_irq_enter);
-}
-
-/*
  * Record entry into an extended quiescent state.  This is only to be
  * called when not already in an extended quiescent state.
  */
@@ -762,68 +749,39 @@ cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
 }
 
 /*
- * rcu_eqs_enter_common - current CPU is entering an extended quiescent state
+ * Enter an RCU extended quiescent state, which can be either the
+ * idle loop or adaptive-tickless usermode execution.
  *
- * Enter idle, doing appropriate accounting.  The caller must have
- * disabled interrupts.
+ * We crowbar the ->dynticks_nmi_nesting field to zero to allow for
+ * the possibility of usermode upcalls having messed up our count
+ * of interrupt nesting level during the prior busy period.
  */
-static void rcu_eqs_enter_common(bool user)
+static void rcu_eqs_enter(bool user)
 {
 	struct rcu_state *rsp;
 	struct rcu_data *rdp;
-	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+	struct rcu_dynticks *rdtp;
 
-	lockdep_assert_irqs_disabled();
-	trace_rcu_dyntick(TPS("Start"), rdtp->dynticks_nesting, 0);
-	if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
-	    !user && !is_idle_task(current)) {
-		struct task_struct *idle __maybe_unused =
-			idle_task(smp_processor_id());
-
-		trace_rcu_dyntick(TPS("Error on entry: not idle task"), rdtp->dynticks_nesting, 0);
-		rcu_ftrace_dump(DUMP_ORIG);
-		WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
-			  current->pid, current->comm,
-			  idle->pid, idle->comm); /* must be idle task! */
+	rdtp = this_cpu_ptr(&rcu_dynticks);
+	WRITE_ONCE(rdtp->dynticks_nmi_nesting, 0);
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+		     rdtp->dynticks_nesting == 0);
+	i