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 subsystem changes in this cycle were:

  - Miscellaneous fixes, perhaps most notably removing obsolete code
    whose only purpose in life was to gather information for the
    now-removed RCU debugfs facility. Other notable changes include
    removing NO_HZ_FULL_ALL in favor of the nohz_full kernel boot
    parameter, minor optimizations for expedited grace periods, some
    added tracing, creating an RCU-specific workqueue using Tejun's new
    WQ_MEM_RECLAIM flag, and several cleanups to code and comments.

  - SRCU cleanups and optimizations.

  - Torture-test updates, perhaps most notably the adding of ARMv8
    support, but also including numerous cleanups and usability fixes"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (37 commits)
  rcu: Create RCU-specific workqueues with rescuers
  torture: Provide more sensible nreader/nwriter defaults for rcuperf
  torture: Grace periods do not piggyback off of themselves
  torture: Adjust rcuperf trace processing to allow for workqueues
  torture: Default jitter off when running rcuperf
  torture: Specify qemu memory size with --memory argument
  rcutorture: Add basic ARM64 support to run scripts
  rcutorture: Update kvm.sh header comment
  rcutorture: Record which grace-period primitives are tested
  rcutorture: Re-enable testing of dynamic expediting
  rcutorture: Avoid fake-writer use of undefined primitives
  rcutorture: Abstract function and module names
  rcutorture: Replace multi-instance kzalloc() with kcalloc()
  rcu: Remove SRCU throttling
  srcu: Remove dead code in srcu_gp_end()
  srcu: Reduce scans of srcu_data in counter wrap check
  srcu: Prevent sdp->srcu_gp_seq_needed_exp counter wrap
  srcu: Abstract function name
  rcu: Make expedited RCU CPU selection avoid unnecessary stores
  rcu: Trace expedited GP delays due to transitioning CPUs
  ...

Documentation/timers/NO_HZ.txt

@@ -131,13 +131,6 @@ error message, and the boot CPU will be removed from the mask.  Note that
 this means that your system must have at least two CPUs in order for
 CONFIG_NO_HZ_FULL=y to do anything for you.
 
-Alternatively, the CONFIG_NO_HZ_FULL_ALL=y Kconfig parameter specifies
-that all CPUs other than the boot CPU are adaptive-ticks CPUs.  This
-Kconfig parameter will be overridden by the "nohz_full=" boot parameter,
-so that if both the CONFIG_NO_HZ_FULL_ALL=y Kconfig parameter and
-the "nohz_full=1" boot parameter is specified, the boot parameter will
-prevail so that only CPU 1 will be an adaptive-ticks CPU.
-
 Finally, adaptive-ticks CPUs must have their RCU callbacks offloaded.
 This is covered in the "RCU IMPLICATIONS" section below.
 

include/linux/rcupdate.h

@@ -214,10 +214,12 @@ do { \
 #endif
 
 /*
- * init_rcu_head_on_stack()/destroy_rcu_head_on_stack() are needed for dynamic
- * initialization and destruction of rcu_head on the stack. rcu_head structures
- * allocated dynamically in the heap or defined statically don't need any
- * initialization.
+ * The init_rcu_head_on_stack() and destroy_rcu_head_on_stack() calls
+ * are needed for dynamic initialization and destruction of rcu_head
+ * on the stack, and init_rcu_head()/destroy_rcu_head() are needed for
+ * dynamic initialization and destruction of statically allocated rcu_head
+ * structures.  However, rcu_head structures allocated dynamically in the
+ * heap don't need any initialization.
  */
 #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
 void init_rcu_head(struct rcu_head *head);

include/linux/types.h

@@ -217,7 +217,7 @@ struct ustat {
  *
  * This guarantee is important for few reasons:
  *  - future call_rcu_lazy() will make use of lower bits in the pointer;
- *  - the structure shares storage spacer in struct page with @compound_head,
+ *  - the structure shares storage space in struct page with @compound_head,
  *    which encode PageTail() in bit 0. The guarantee is needed to avoid
  *    false-positive PageTail().
  */

include/trace/events/rcu.h

@@ -179,6 +179,10 @@ TRACE_EVENT(rcu_grace_period_init,
  *
  *	"snap": Captured snapshot of expedited grace period sequence number.
  *	"start": Started a real expedited grace period.
+ *	"reset": Started resetting the tree
+ *	"select": Started selecting the CPUs to wait on.
+ *	"selectofl": Selected CPU partially offline.
+ *	"startwait": Started waiting on selected CPUs.
  *	"end": Ended a real expedited grace period.
  *	"endwake": Woke piggybackers up.
  *	"done": Someone else did the expedited grace period for us.

kernel/rcu/rcu.h

@@ -77,12 +77,18 @@ static inline void rcu_seq_start(unsigned long *sp)
 	WARN_ON_ONCE(rcu_seq_state(*sp) != 1);
 }
 
+/* Compute the end-of-grace-period value for the specified sequence number. */
+static inline unsigned long rcu_seq_endval(unsigned long *sp)
+{
+	return (*sp | RCU_SEQ_STATE_MASK) + 1;
+}
+
 /* Adjust sequence number for end of update-side operation. */
 static inline void rcu_seq_end(unsigned long *sp)
 {
 	smp_mb(); /* Ensure update-side operation before counter increment. */
 	WARN_ON_ONCE(!rcu_seq_state(*sp));
-	WRITE_ONCE(*sp, (*sp | RCU_SEQ_STATE_MASK) + 1);
+	WRITE_ONCE(*sp, rcu_seq_endval(sp));
 }
 
 /* Take a snapshot of the update side's sequence number. */
@@ -295,9 +301,19 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt)
  * Iterate over all possible CPUs in a leaf RCU node.
  */
 #define for_each_leaf_node_possible_cpu(rnp, cpu) \
-	for ((cpu) = cpumask_next(rnp->grplo - 1, cpu_possible_mask); \
-	     cpu <= rnp->grphi; \
-	     cpu = cpumask_next((cpu), cpu_possible_mask))
+	for ((cpu) = cpumask_next((rnp)->grplo - 1, cpu_possible_mask); \
+	     (cpu) <= rnp->grphi; \
+	     (cpu) = cpumask_next((cpu), cpu_possible_mask))
+
+/*
+ * Iterate over all CPUs in a leaf RCU node's specified mask.
+ */
+#define rcu_find_next_bit(rnp, cpu, mask) \
+	((rnp)->grplo + find_next_bit(&(mask), BITS_PER_LONG, (cpu)))
+#define for_each_leaf_node_cpu_mask(rnp, cpu, mask) \
+	for ((cpu) = rcu_find_next_bit((rnp), 0, (mask)); \
+	     (cpu) <= rnp->grphi; \
+	     (cpu) = rcu_find_next_bit((rnp), (cpu) + 1 - (rnp->grplo), (mask)))
 
 /*
  * Wrappers for the rcu_node::lock acquire and release.
@@ -337,7 +353,7 @@ do {									\
 } while (0)
 
 #define raw_spin_unlock_irqrestore_rcu_node(p, flags)			\
-	raw_spin_unlock_irqrestore(&ACCESS_PRIVATE(p, lock), flags)	\
+	raw_spin_unlock_irqrestore(&ACCESS_PRIVATE(p, lock), flags)
 
 #define raw_spin_trylock_rcu_node(p)					\
 ({									\
@@ -348,6 +364,9 @@ do {									\
 	___locked;							\
 })
 
+#define raw_lockdep_assert_held_rcu_node(p)				\
+	lockdep_assert_held(&ACCESS_PRIVATE(p, lock))
+
 #endif /* #if defined(SRCU) || !defined(TINY_RCU) */
 
 #ifdef CONFIG_TINY_RCU
@@ -356,24 +375,20 @@ static inline bool rcu_gp_is_normal(void) { return true; }
 static inline bool rcu_gp_is_expedited(void) { return false; }
 static inline void rcu_expedite_gp(void) { }
 static inline void rcu_unexpedite_gp(void) { }
+static inline void rcu_request_urgent_qs_task(struct task_struct *t) { }
 #else /* #ifdef CONFIG_TINY_RCU */
 bool rcu_gp_is_normal(void);     /* Internal RCU use. */
 bool rcu_gp_is_expedited(void);  /* Internal RCU use. */
 void rcu_expedite_gp(void);
 void rcu_unexpedite_gp(void);
 void rcupdate_announce_bootup_oddness(void);
+void rcu_request_urgent_qs_task(struct task_struct *t);
 #endif /* #else #ifdef CONFIG_TINY_RCU */
 
 #define RCU_SCHEDULER_INACTIVE	0
 #define RCU_SCHEDULER_INIT	1
 #define RCU_SCHEDULER_RUNNING	2
 
-#ifdef CONFIG_TINY_RCU
-static inline void rcu_request_urgent_qs_task(struct task_struct *t) { }
-#else /* #ifdef CONFIG_TINY_RCU */
-void rcu_request_urgent_qs_task(struct task_struct *t);
-#endif /* #else #ifdef CONFIG_TINY_RCU */
-
 enum rcutorture_type {
 	RCU_FLAVOR,
 	RCU_BH_FLAVOR,
@@ -470,6 +485,7 @@ void show_rcu_gp_kthreads(void);
 void rcu_force_quiescent_state(void);
 void rcu_bh_force_quiescent_state(void);
 void rcu_sched_force_quiescent_state(void);
+extern struct workqueue_struct *rcu_gp_wq;
 #endif /* #else #ifdef CONFIG_TINY_RCU */
 
 #ifdef CONFIG_RCU_NOCB_CPU

kernel/rcu/rcuperf.c

@@ -61,11 +61,30 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.vnet.ibm.com>");
 #define VERBOSE_PERFOUT_ERRSTRING(s) \
 	do { if (verbose) pr_alert("%s" PERF_FLAG "!!! %s\n", perf_type, s); } while (0)
 
+/*
+ * The intended use cases for the nreaders and nwriters module parameters
+ * are as follows:
+ *
+ * 1.	Specify only the nr_cpus kernel boot parameter.  This will
+ *	set both nreaders and nwriters to the value specified by
+ *	nr_cpus for a mixed reader/writer test.
+ *
+ * 2.	Specify the nr_cpus kernel boot parameter, but set
+ *	rcuperf.nreaders to zero.  This will set nwriters to the
+ *	value specified by nr_cpus for an update-only test.
+ *
+ * 3.	Specify the nr_cpus kernel boot parameter, but set
+ *	rcuperf.nwriters to zero.  This will set nreaders to the
+ *	value specified by nr_cpus for a read-only test.
+ *
+ * Various other use cases may of course be specified.
+ */
+
 torture_param(bool, gp_async, false, "Use asynchronous GP wait primitives");
 torture_param(int, gp_async_max, 1000, "Max # outstanding waits per reader");
 torture_param(bool, gp_exp, false, "Use expedited GP wait primitives");
 torture_param(int, holdoff, 10, "Holdoff time before test start (s)");
-torture_param(int, nreaders, 0, "Number of RCU reader threads");
+torture_param(int, nreaders, -1, "Number of RCU reader threads");
 torture_param(int, nwriters, -1, "Number of RCU updater threads");
 torture_param(bool, shutdown, !IS_ENABLED(MODULE),
 	      "Shutdown at end of performance tests.");

kernel/rcu/rcutorture.c

@@ -909,34 +909,38 @@ rcu_torture_writer(void *arg)
 	int nsynctypes = 0;
 
 	VERBOSE_TOROUT_STRING("rcu_torture_writer task started");
-	if (!can_expedite) {
+	if (!can_expedite)
 		pr_alert("%s" TORTURE_FLAG
-			 " GP expediting controlled from boot/sysfs for %s,\n",
+			 " GP expediting controlled from boot/sysfs for %s.\n",
 			 torture_type, cur_ops->name);
-		pr_alert("%s" TORTURE_FLAG
-			 " Disabled dynamic grace-period expediting.\n",
-			 torture_type);
-	}
 
 	/* Initialize synctype[] array.  If none set, take default. */
 	if (!gp_cond1 && !gp_exp1 && !gp_normal1 && !gp_sync1)
 		gp_cond1 = gp_exp1 = gp_normal1 = gp_sync1 = true;
-	if (gp_cond1 && cur_ops->get_state && cur_ops->cond_sync)
+	if (gp_cond1 && cur_ops->get_state && cur_ops->cond_sync) {
 		synctype[nsynctypes++] = RTWS_COND_GET;
-	else if (gp_cond && (!cur_ops->get_state || !cur_ops->cond_sync))
-		pr_alert("rcu_torture_writer: gp_cond without primitives.\n");
-	if (gp_exp1 && cur_ops->exp_sync)
+		pr_info("%s: Testing conditional GPs.\n", __func__);
+	} else if (gp_cond && (!cur_ops->get_state || !cur_ops->cond_sync)) {
+		pr_alert("%s: gp_cond without primitives.\n", __func__);
+	}
+	if (gp_exp1 && cur_ops->exp_sync) {
 		synctype[nsynctypes++] = RTWS_EXP_SYNC;
-	else if (gp_exp && !cur_ops->exp_sync)
-		pr_alert("rcu_torture_writer: gp_exp without primitives.\n");
-	if (gp_normal1 && cur_ops->deferred_free)
+		pr_info("%s: Testing expedited GPs.\n", __func__);
+	} else if (gp_exp && !cur_ops->exp_sync) {
+		pr_alert("%s: gp_exp without primitives.\n", __func__);
+	}
+	if (gp_normal1 && cur_ops->deferred_free) {
 		synctype[nsynctypes++] = RTWS_DEF_FREE;
-	else if (gp_normal && !cur_ops->deferred_free)
-		pr_alert("rcu_torture_writer: gp_normal without primitives.\n");
-	if (gp_sync1 && cur_ops->sync)
+		pr_info("%s: Testing asynchronous GPs.\n", __func__);
+	} else if (gp_normal && !cur_ops->deferred_free) {
+		pr_alert("%s: gp_normal without primitives.\n", __func__);
+	}
+	if (gp_sync1 && cur_ops->sync) {
 		synctype[nsynctypes++] = RTWS_SYNC;
-	else if (gp_sync && !cur_ops->sync)
-		pr_alert("rcu_torture_writer: gp_sync without primitives.\n");
+		pr_info("%s: Testing normal GPs.\n", __func__);
+	} else if (gp_sync && !cur_ops->sync) {
+		pr_alert("%s: gp_sync without primitives.\n", __func__);
+	}
 	if (WARN_ONCE(nsynctypes == 0,
 		      "rcu_torture_writer: No update-side primitives.\n")) {
 		/*
@@ -1011,6 +1015,9 @@ rcu_torture_writer(void *arg)
 				rcu_unexpedite_gp();
 			if (++expediting > 3)
 				expediting = -expediting;
+		} else if (!can_expedite) { /* Disabled during boot, recheck. */
+			can_expedite = !rcu_gp_is_expedited() &&
+				       !rcu_gp_is_normal();
 		}
 		rcu_torture_writer_state = RTWS_STUTTER;
 		stutter_wait("rcu_torture_writer");
@@ -1021,6 +1028,10 @@ rcu_torture_writer(void *arg)
 	while (can_expedite && expediting++ < 0)
 		rcu_unexpedite_gp();
 	WARN_ON_ONCE(can_expedite && rcu_gp_is_expedited());
+	if (!can_expedite)
+		pr_alert("%s" TORTURE_FLAG
+			 " Dynamic grace-period expediting was disabled.\n",
+			 torture_type);
 	rcu_torture_writer_state = RTWS_STOPPING;
 	torture_kthread_stopping("rcu_torture_writer");
 	return 0;
@@ -1045,13 +1056,13 @@ rcu_torture_fakewriter(void *arg)
 		    torture_random(&rand) % (nfakewriters * 8) == 0) {
 			cur_ops->cb_barrier();
 		} else if (gp_normal == gp_exp) {
-			if (torture_random(&rand) & 0x80)
+			if (cur_ops->sync && torture_random(&rand) & 0x80)
 				cur_ops->sync();
-			else
+			else if (cur_ops->exp_sync)
 				cur_ops->exp_sync();
-		} else if (gp_normal) {
+		} else if (gp_normal && cur_ops->sync) {
 			cur_ops->sync();
-		} else {
+		} else if (cur_ops->exp_sync) {
 			cur_ops->exp_sync();
 		}
 		stutter_wait("rcu_torture_fakewriter");
@@ -1557,11 +1568,10 @@ static int rcu_torture_barrier_init(void)
 	atomic_set(&barrier_cbs_count, 0);
 	atomic_set(&barrier_cbs_invoked, 0);
 	barrier_cbs_tasks =
-		kzalloc(n_barrier_cbs * sizeof(barrier_cbs_tasks[0]),
+		kcalloc(n_barrier_cbs, sizeof(barrier_cbs_tasks[0]),
 			GFP_KERNEL);
 	barrier_cbs_wq =
-		kzalloc(n_barrier_cbs * sizeof(barrier_cbs_wq[0]),
-			GFP_KERNEL);
+		kcalloc(n_barrier_cbs, sizeof(barrier_cbs_wq[0]), GFP_KERNEL);
 	if (barrier_cbs_tasks == NULL || !barrier_cbs_wq)
 		return -ENOMEM;
 	for (i = 0; i < n_barrier_cbs; i++) {
@@ -1674,7 +1684,7 @@ static void rcu_torture_err_cb(struct rcu_head *rhp)
 	 * next grace period.  Unlikely, but can happen.  If it
 	 * does happen, the debug-objects subsystem won't have splatted.
 	 */
-	pr_alert("rcutorture: duplicated callback was invoked.\n");
+	pr_alert("%s: duplicated callback was invoked.\n", KBUILD_MODNAME);
 }
 #endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 
@@ -1691,7 +1701,7 @@ static void rcu_test_debug_objects(void)
 
 	init_rcu_head_on_stack(&rh1);
 	init_rcu_head_on_stack(&rh2);
-	pr_alert("rcutorture: WARN: Duplicate call_rcu() test starting.\n");
+	pr_alert("%s: WARN: Duplicate call_rcu() test starting.\n", KBUILD_MODNAME);
 
 	/* Try to queue the rh2 pair of callbacks for the same grace period. */
 	preempt_disable(); /* Prevent preemption from interrupting test. */
@@ -1706,11 +1716,11 @@ static void rcu_test_debug_objects(void)
 
 	/* Wait for them all to get done so we can safely return. */
 	rcu_barrier();
-	pr_alert("rcutorture: WARN: Duplicate call_rcu() test complete.\n");
+	pr_alert("%s: WARN: Duplicate call_rcu() test complete.\n", KBUILD_MODNAME);
 	destroy_rcu_head_on_stack(&rh1);
 	destroy_rcu_head_on_stack(&rh2);
 #else /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
-	pr_alert("rcutorture: !CONFIG_DEBUG_OBJECTS_RCU_HEAD, not testing duplicate call_rcu()\n");
+	pr_alert("%s: !CONFIG_DEBUG_OBJECTS_RCU_HEAD, not testing duplicate call_rcu()\n", KBUILD_MODNAME);
 #endif /* #else #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 }
 
@@ -1799,7 +1809,7 @@ rcu_torture_init(void)
 	if (firsterr)
 		goto unwind;
 	if (nfakewriters > 0) {
-		fakewriter_tasks = kzalloc(nfakewriters *
+		fakewriter_tasks = kcalloc(nfakewriters,
 					   sizeof(fakewriter_tasks[0]),
 					   GFP_KERNEL);
 		if (fakewriter_tasks == NULL) {
@@ -1814,7 +1824,7 @@ rcu_torture_init(void)
 		if (firsterr)
 			goto unwind;
 	}
-	reader_tasks = kzalloc(nrealreaders * sizeof(reader_tasks[0]),
+	reader_tasks = kcalloc(nrealreaders, sizeof(reader_tasks[0]),
 			       GFP_KERNEL);
 	if (reader_tasks == NULL) {
 		VERBOSE_TOROUT_ERRSTRING("out of memory");

kernel/rcu/srcutree.c

@@ -386,7 +386,7 @@ void cleanup_srcu_struct(struct srcu_struct *sp)
 		flush_delayed_work(&per_cpu_ptr(sp->sda, cpu)->work);
 	if (WARN_ON(rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) != SRCU_STATE_IDLE) ||
 	    WARN_ON(srcu_readers_active(sp))) {
-		pr_info("cleanup_srcu_struct: Active srcu_struct %p state: %d\n", sp, rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)));
+		pr_info("%s: Active srcu_struct %p state: %d\n", __func__, sp, rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)));
 		return; /* Caller forgot to stop doing call_srcu()? */
 	}
 	free_percpu(sp->sda);
@@ -439,7 +439,7 @@ static void srcu_gp_start(struct srcu_struct *sp)
 	struct srcu_data *sdp = this_cpu_ptr(sp->sda);
 	int state;
 
-	lockdep_assert_held(&sp->lock);
+	lockdep_assert_held(&ACCESS_PRIVATE(sp, lock));
 	WARN_ON_ONCE(ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed));
 	rcu_segcblist_advance(&sdp->srcu_cblist,
 			      rcu_seq_current(&sp->srcu_gp_seq));
@@ -492,8 +492,7 @@ static bool srcu_queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
  */
 static void srcu_schedule_cbs_sdp(struct srcu_data *sdp, unsigned long delay)
 {
-	srcu_queue_delayed_work_on(sdp->cpu, system_power_efficient_wq,
-				   &sdp->work, delay);
+	srcu_queue_delayed_work_on(sdp->cpu, rcu_gp_wq, &sdp->work, delay);
 }
 
 /*
@@ -527,11 +526,11 @@ static void srcu_gp_end(struct srcu_struct *sp)
 {
 	unsigned long cbdelay;
 	bool cbs;
+	bool last_lvl;
 	int cpu;
 	unsigned long flags;
 	unsigned long gpseq;
 	int idx;
-	int idxnext;
 	unsigned long mask;
 	struct srcu_data *sdp;
 	struct srcu_node *snp;
@@ -555,11 +554,11 @@ static void srcu_gp_end(struct srcu_struct *sp)
 
 	/* Initiate callback invocation as needed. */
 	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) {
 		spin_lock_irq_rcu_node(snp);
 		cbs = false;
-		if (snp >= sp->level[rcu_num_lvls - 1])
+		last_lvl = snp >= sp->level[rcu_num_lvls - 1];
+		if (last_lvl)
 			cbs = snp->srcu_have_cbs[idx] == gpseq;
 		snp->srcu_have_cbs[idx] = gpseq;
 		rcu_seq_set_state(&snp->srcu_have_cbs[idx], 1);
@@ -572,13 +571,16 @@ static void srcu_gp_end(struct srcu_struct *sp)
 			srcu_schedule_cbs_snp(sp, snp, mask, cbdelay);
 
 		/* Occasionally prevent srcu_data counter wrap. */
-		if (!(gpseq & counter_wrap_check))
+		if (!(gpseq & counter_wrap_check) && last_lvl)
 			for (cpu = snp->grplo; cpu <= snp->grphi; cpu++) {
 				sdp = per_cpu_ptr(sp->sda, cpu);
 				spin_lock_irqsave_rcu_node(sdp, flags);
 				if (ULONG_CMP_GE(gpseq,
 						 sdp->srcu_gp_seq_needed + 100))
 					sdp->srcu_gp_seq_needed = gpseq;
+				if (ULONG_CMP_GE(gpseq,
+						 sdp->srcu_gp_seq_needed_exp + 100))
+					sdp->srcu_gp_seq_needed_exp = gpseq;
 				spin_unlock_irqrestore_rcu_node(sdp, flags);
 			}
 	}
@@ -593,9 +595,7 @@ static void srcu_gp_end(struct srcu_struct *sp)
 	    ULONG_CMP_LT(gpseq, sp->srcu_gp_seq_needed)) {
 		srcu_gp_start(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);
+		srcu_reschedule(sp, 0);
 	} else {
 		spin_unlock_irq_rcu_node(sp);
 	}
@@ -626,7 +626,7 @@ static void srcu_funnel_exp_start(struct srcu_struct *sp, struct srcu_node *snp,
 		spin_unlock_irqrestore_rcu_node(snp, flags);
 	}
 	spin_lock_irqsave_rcu_node(sp, flags);
-	if (!ULONG_CMP_LT(sp->srcu_gp_seq_needed_exp, s))
+	if (ULONG_CMP_LT(sp->srcu_gp_seq_needed_exp, s))
 		sp->srcu_gp_seq_needed_exp = s;
 	spin_unlock_irqrestore_rcu_node(sp, flags);
 }
@@ -691,8 +691,7 @@ static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp,
 	    rcu_seq_state(sp->srcu_gp_seq) == SRCU_STATE_IDLE) {
 		WARN_ON_ONCE(ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed));
 		srcu_gp_start(sp);
-		queue_delayed_work(system_power_efficient_wq, &sp->work,
-				   srcu_get_delay(sp));
+		queue_delayed_work(rcu_gp_wq, &sp->work, srcu_get_delay(sp));
 	}
 	spin_unlock_irqrestore_rcu_node(sp, flags);
 }
@@ -1225,7 +1224,7 @@ static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay)
 	spin_unlock_irq_rcu_node(sp);
 
 	if (pushgp)
-		queue_delayed_work(system_power_efficient_wq, &sp->work, delay);
+		queue_delayed_work(rcu_gp_wq, &sp->work, delay);
 }
 
 /*

kernel/rcu/tree.c

@@ -1161,7 +1161,7 @@ static int rcu_is_cpu_rrupt_from_idle(void)
  */
 static void rcu_gpnum_ovf(struct rcu_node *rnp, struct rcu_data *rdp)
 {
-	lockdep_assert_held(&rnp->lock);
+	raw_lockdep_assert_held_rcu_node(rnp);
 	if (ULONG_CMP_LT(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4, rnp->gpnum))
 		WRITE_ONCE(rdp->gpwrap, true);
 	if (ULONG_CMP_LT(rdp->rcu_iw_gpnum + ULONG_MAX / 4, rnp->gpnum))
@@ -1350,6 +1350,7 @@ static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp)
 		       rsp->gp_kthread ? rsp->gp_kthread->state : ~0,
 		       rsp->gp_kthread ? task_cpu(rsp->gp_kthread) : -1);
 		if (rsp->gp_kthread) {
+			pr_err("RCU grace-period kthread stack dump:\n");
 			sched_show_task(rsp->gp_kthread);
 			wake_up_process(rsp->gp_kthread);
 		}
@@ -1628,7 +1629,7 @@ void rcu_cpu_stall_reset(void)
 static unsigned long rcu_cbs_completed(struct rcu_state *rsp,
 				       struct rcu_node *rnp)
 {
-	lockdep_assert_held(&rnp->lock);
+	raw_lockdep_assert_held_rcu_node(rnp);
 
 	/*
 	 * If RCU is idle, we just wait for the next grace period.
@@ -1675,7 +1676,7 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp,
 	bool ret = false;
 	struct rcu_node *rnp_root = rcu_get_root(rdp->rsp);
 
-	lockdep_assert_held(&rnp->lock);
+	raw_lockdep_assert_held_rcu_node(rnp);
 
 	/*
 	 * Pick up grace-period number for new callbacks.  If this
@@ -1803,7 +1804,7 @@ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
 {
 	bool ret = false;
 
-	lockdep_assert_held(&rnp->lock);
+	raw_lockdep_assert_held_rcu_node(rnp);
 
 	/* If no pending (not yet ready to invoke) callbacks, nothing to do. */
 	if (!rcu_segcblist_pend_cbs(&rdp->cblist))
@@ -1843,7 +1844,7 @@ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
 static bool rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
 			    struct rcu_data *rdp)
 {
-	lockdep_assert_held(&rnp->lock);
+	raw_lockdep_assert_held_rcu_node(rnp);
 
 	/* If no pending (not yet ready to invoke) callbacks, nothing to do. */
 	if (!rcu_segcblist_pend_cbs(&rdp->cblist))
@@ -1871,7 +1872,7 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp,
 	bool ret;
 	bool need_gp;
 
-	lockdep_assert_held(&rnp->lock);
+	raw_lockdep_assert_held_rcu_node(rnp);
 
 	/* Handle the ends of any preceding grace periods first. */
 	if (rdp->completed == rnp->completed &&
@@ -2296,7 +2297,7 @@ static bool
 rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
 		      struct rcu_data *rdp)
 {
-	lockdep_assert_held(&rnp->lock);
+	raw_lockdep_assert_held_rcu_node(rnp);
 	if (!rsp->gp_kthread || !cpu_needs_another_gp(rsp, rdp)) {
 		/*
 		 * Either we have not yet spawned the grace-period
@@ -2358,7 +2359,7 @@ static bool rcu_start_gp(struct rcu_state *rsp)
 static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
 	__releases(rcu_get_root(rsp)->lock)
 {
-	lockdep_assert_held(&rcu_get_root(rsp)->lock);
+	raw_lockdep_assert_held_rcu_node(rcu_get_root(rsp));
 	WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
 	WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS);
 	raw_spin_unlock_irqrestore_rcu_node(rcu_get_root(rsp), flags);
@@ -2383,7 +2384,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 	unsigned long oldmask = 0;
 	struct rcu_node *rnp_c;
 
-	lockdep_assert_held(&rnp->lock);
+	raw_lockdep_assert_held_rcu_node(rnp);
 
 	/* Walk up the rcu_node hierarchy. */
 	for (;;) {
@@ -2447,7 +2448,7 @@ static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp,
 	unsigned long mask;
 	struct rcu_node *rnp_p;
 
-	lockdep_assert_held(&rnp->lock);
+	raw_lockdep_assert_held_rcu_node(rnp);
 	if (rcu_state_p == &rcu_sched_state || rsp != rcu_state_p ||
 	    rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) {
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
@@ -2592,7 +2593,7 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
 	long mask;
 	struct rcu_node *rnp = rnp_leaf;
 
-	lockdep_assert_held(&rnp->lock);
+	raw_lockdep_assert_held_rcu_node(rnp);
 	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) ||
 	    rnp->qsmaskinit || rcu_preempt_has_tasks(rnp))
 		return;
@@ -2691,7 +2692,6 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
 	/* Update counts and requeue any remaining callbacks. */
 	rcu_segcblist_insert_done_cbs(&rdp->cblist, &rcl);
 	smp_mb(); /* List handling before counting for rcu_barrier(). */
-	rdp->n_cbs_invoked += count;
 	rcu_segcblist_insert_count(&rdp->cblist, &rcl);
 
 	/* Reinstate batch limit if we have worked down the excess. */
@@ -2845,10 +2845,8 @@ static void force_quiescent_state(struct rcu_state *rsp)
 		      !raw_spin_trylock(&rnp->fqslock);
 		if (rnp_old != NULL)
 			raw_spin_unlock(&rnp_old->fqslock);
-		if (ret) {
-			rsp->n_force_qs_lh++;
+		if (ret)
 			return;
-		}
 		rnp_old = rnp;
 	}
 	/* rnp_old == rcu_get_root(rsp), rnp == NULL. */
@@ -2857,7 +2855,6 @@ static void force_quiescent_state(struct rcu_state *rsp)
 	raw_spin_lock_irqsave_rcu_node(rnp_old, flags);
 	raw_spin_unlock(&rnp_old->fqslock);
 	if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
-		rsp->n_force_qs_lh++;
 		raw_spin_unlock_irqrestore_rcu_node(rnp_old, flags);
 		return;  /* Someone beat us to it. */
 	}
@@ -3355,8 +3352,6 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
 {
 	struct rcu_node *rnp = rdp->mynode;
 
-	rdp->n_rcu_pending++;
-
 	/* Check for CPU stalls, if enabled. */
 	check_cpu_stall(rsp, rdp);
 
@@ -3365,48 +3360,31 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
 		return 0;
 
 	/* Is the RCU core waiting for a quiescent state from this CPU? */
-	if (rcu_scheduler_fully_active &&
-	    rdp->core_needs_qs && rdp->cpu_no_qs.b.norm &&
-	    rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_dynticks.rcu_qs_ctr)) {
-		rdp->n_rp_core_needs_qs++;
-	} else if (rdp->core_needs_qs && !rdp->cpu_no_qs.b.norm) {
-		rdp->n_rp_report_qs++;
+	if (rdp->core_needs_qs && !rdp->cpu_no_qs.b.norm)
 		return 1;
-	}
 
 	/* Does this CPU have callbacks ready to invoke? */
-	if (rcu_segcblist_ready_cbs(&rdp->cblist)) {
-		rdp->n_rp_cb_ready++;
+	if (rcu_segcblist_ready_cbs(&rdp->cblist))
 		return 1;
-	}
 
 	/* Has RCU gone idle with this CPU needing another grace period? */
-	if (cpu_needs_another_gp(rsp, rdp)) {
-		rdp->n_rp_cpu_needs_gp++;
+	if (cpu_needs_another_gp(rsp, rdp))
 		return 1;
-	}
 
 	/* Has another RCU grace period completed?  */
-	if (READ_ONCE(rnp->completed) != rdp->completed) { /* outside lock */
-		rdp->n_rp_gp_completed++;
+	if (READ_ONCE(rnp->completed) != rdp->completed) /* outside lock */
 		return 1;
-	}
 
 	/* Has a new RCU grace period started? */
 	if (READ_ONCE(rnp->gpnum) != rdp->gpnum ||
-	    unlikely(READ_ONCE(rdp->gpwrap))) { /* outside lock */
-		rdp->n_rp_gp_started++;
+	    unlikely(READ_ONCE(rdp->gpwrap))) /* outside lock */
 		return 1;
-	}
 
 	/* Does this CPU need a deferred NOCB wakeup? */
-	if (rcu_nocb_need_deferred_wakeup(rdp)) {
-		rdp->n_rp_nocb_defer_wakeup++;
+	if (rcu_nocb_need_deferred_wakeup(rdp))
 		return 1;
-	}
 
 	/* nothing to do */
-	rdp->n_rp_need_nothing++;
 	return 0;
 }
 
@@ -3618,7 +3596,7 @@ static void rcu_init_new_rnp(struct rcu_node *rnp_leaf)
 	long mask;
 	struct rcu_node *rnp = rnp_leaf;
 
-	lockdep_assert_held(&rnp->lock);
+	raw_lockdep_assert_held_rcu_node(rnp);
 	for (;;) {
 		mask = rnp->grpmask;
 		rnp = rnp->parent;
@@ -3636,12 +3614,9 @@ static void rcu_init_new_rnp(struct rcu_node *rnp_leaf)
 static void __init
 rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
 {
-	unsigned long flags;
 	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
-	struct rcu_node *rnp = rcu_get_root(rsp);
 
 	/* Set up local state, ensuring consistent view of global state. */
-	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	rdp->grpmask = leaf_node_cpu_bit(rdp->mynode, cpu);
 	rdp->dynticks = &per_cpu(rcu_dynticks, cpu);
 	WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != 1);
@@ -3649,7 +3624,6 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
 	rdp->cpu = cpu;
 	rdp->rsp = rsp;
 	rcu_boot_init_nocb_percpu_data(rdp);
-	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 }
 
 /*
@@ -4193,6 +4167,8 @@ static void __init rcu_dump_rcu_node_tree(struct rcu_state *rsp)
 	pr_cont("\n");
 }
 
+struct workqueue_struct *rcu_gp_wq;
+
 void __init rcu_init(void)
 {
 	int cpu;
@@ -4219,6 +4195,10 @@ void __init rcu_init(void)
 		rcu_cpu_starting(cpu);
 		rcutree_online_cpu(cpu);
 	}
+
+	/* Create workqueue for expedited GPs and for Tree SRCU. */
+	rcu_gp_wq = alloc_workqueue("rcu_gp", WQ_MEM_RECLAIM, 0);
+	WARN_ON(!rcu_gp_wq);
 }
 
 #include "tree_exp.h"

kernel/rcu/tree.h

@@ -146,12 +146,6 @@ struct rcu_node {
 				/*  boosting for this rcu_node structure. */
 	unsigned int boost_kthread_status;
 				/* State of boost_kthread_task for tracing. */
-	unsigned long n_tasks_boosted;
-				/* Total number of tasks boosted. */
-	unsigned long n_exp_boosts;
-				/* Number of tasks boosted for expedited GP. */
-	unsigned long n_normal_boosts;
-				/* Number of tasks boosted for normal GP. */
 #ifdef CONFIG_RCU_NOCB_CPU
 	struct swait_queue_head nocb_gp_wq[2];
 				/* Place for rcu_nocb_kthread() to wait GP. */
@@ -184,13 +178,6 @@ union rcu_noqs {
 	u16 s; /* Set of bits, aggregate OR here. */
 };
 
-/* Index values for nxttail array in struct rcu_data. */
-#define RCU_DONE_TAIL		0	/* Also RCU_WAIT head. */
-#define RCU_WAIT_TAIL		1	/* Also RCU_NEXT_READY head. */
-#define RCU_NEXT_READY_TAIL	2	/* Also RCU_NEXT head. */
-#define RCU_NEXT_TAIL		3
-#define RCU_NEXT_SIZE		4
-
 /* Per-CPU data for read-copy update. */
 struct rcu_data {
 	/* 1) quiescent-state and grace-period handling : */
@@ -217,8 +204,6 @@ struct rcu_data {
 					/* different grace periods. */
 	long		qlen_last_fqs_check;
 					/* qlen at last check for QS forcing */
-	unsigned long	n_cbs_invoked;	/* count of RCU cbs invoked. */
-	unsigned long	n_nocbs_invoked; /* count of no-CBs RCU cbs invoked. */
 	unsigned long	n_force_qs_snap;
 					/* did other CPU force QS recently? */
 	long		blimit;		/* Upper limit on a processed batch */
@@ -234,18 +219,7 @@ struct rcu_data {
 					/* Grace period that needs help */
 					/*  from cond_resched(). */
 
-	/* 5) __rcu_pending() statistics. */
-	unsigned long n_rcu_pending;	/* rcu_pending() calls since boot. */
-	unsigned long n_rp_core_needs_qs;
-	unsigned long n_rp_report_qs;
-	unsigned long n_rp_cb_ready;
-	unsigned long n_rp_cpu_needs_gp;
-	unsigned long n_rp_gp_completed;
-	unsigned long n_rp_gp_started;
-	unsigned long n_rp_nocb_defer_wakeup;
-	unsigned long n_rp_need_nothing;
-
-	/* 6) _rcu_barrier(), OOM callbacks, and expediting. */
+	/* 5) _rcu_barrier(), OOM callbacks, and expediting. */
 	struct rcu_head barrier_head;
 #ifdef CONFIG_RCU_FAST_NO_HZ
 	struct rcu_head oom_head;
@@ -256,7 +230,7 @@ struct rcu_data {
 	atomic_long_t exp_workdone3;	/* # done by others #3. */
 	int exp_dynticks_snap;		/* Double-check need for IPI. */
 
-	/* 7) Callback offloading. */
+	/* 6) Callback offloading. */
 #ifdef CONFIG_RCU_NOCB_CPU
 	struct rcu_head *nocb_head;	/* CBs waiting for kthread. */
 	struct rcu_head **nocb_tail;
@@ -283,7 +257,7 @@ struct rcu_data {
 					/* Leader CPU takes GP-end wakeups. */
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU */
 
-	/* 8) RCU CPU stall data. */
+	/* 7) RCU CPU stall data. */
 	unsigned int softirq_snap;	/* Snapshot of softirq activity. */
 	/* ->rcu_iw* fields protected by leaf rcu_node ->lock. */
 	struct irq_work rcu_iw;		/* Check for non-irq activity. */
@@ -374,10 +348,6 @@ struct rcu_state {
 						/*  kthreads, if configured. */
 	unsigned long n_force_qs;		/* Number of calls to */
 						/*  force_quiescent_state(). */
-	unsigned long n_force_qs_lh;		/* ~Number of calls leaving */
-						/*  due to lock unavailable. */
-	unsigned long n_force_qs_ngp;		/* Number of calls leaving */
-						/*  due to no GP active. */
 	unsigned long gp_start;			/* Time at which GP started, */
 						/*  but in jiffies. */
 	unsigned long gp_activity;		/* Time of last GP kthread */

kernel/rcu/tree_exp.h

@@ -28,6 +28,15 @@ static void rcu_exp_gp_seq_start(struct rcu_state *rsp)
 	rcu_seq_start(&rsp->expedited_sequence);
 }
 
+/*
+ * Return then value that expedited-grace-period counter will have
+ * at the end of the current grace period.
+ */
+static __maybe_unused unsigned long rcu_exp_gp_seq_endval(struct rcu_state *rsp)
+{
+	return rcu_seq_endval(&rsp->expedited_sequence);
+}
+
 /*
  * Record the end of an expedited grace period.
  */
@@ -366,21 +375,30 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
 	int ret;
 	struct rcu_node *rnp;
 
+	trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("reset"));
 	sync_exp_reset_tree(rsp);
+	trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("select"));
 	rcu_for_each_leaf_node(rsp, rnp) {
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 
 		/* Each pass checks a CPU for identity, offline, and idle. */
 		mask_ofl_test = 0;
-		for_each_leaf_node_possible_cpu(rnp, cpu) {
+		for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) {
+			unsigned long mask = leaf_node_cpu_bit(rnp, cpu);
 			struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
+			struct rcu_dynticks *rdtp = per_cpu_ptr(&rcu_dynticks, cpu);
+			int snap;
 
-			rdp->exp_dynticks_snap =
-				rcu_dynticks_snap(rdp->dynticks);
 			if (raw_smp_processor_id() == cpu ||
-			    rcu_dynticks_in_eqs(rdp->exp_dynticks_snap) ||
-			    !(rnp->qsmaskinitnext & rdp->grpmask))
-				mask_ofl_test |= rdp->grpmask;
+			    !(rnp->qsmaskinitnext & mask)) {
+				mask_ofl_test |= mask;
+			} else {
+				snap = rcu_dynticks_snap(rdtp);
+				if (rcu_dynticks_in_eqs(snap))
+					mask_ofl_test |= mask;
+				else
+					rdp->exp_dynticks_snap = snap;
+			}
 		}
 		mask_ofl_ipi = rnp->expmask & ~mask_ofl_test;
 
@@ -394,7 +412,7 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 
 		/* IPI the remaining CPUs for expedited quiescent state. */
-		for_each_leaf_node_possible_cpu(rnp, cpu) {
+		for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) {
 			unsigned long mask = leaf_node_cpu_bit(rnp, cpu);
 			struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
 
@@ -417,6 +435,7 @@ retry_ipi:
 			    (rnp->expmask & mask)) {
 				/* Online, so delay for a bit and try again. */
 				raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+				trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("selectofl"));
 				schedule_timeout_uninterruptible(1);
 				goto retry_ipi;
 			}
@@ -443,6 +462,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
 	struct rcu_node *rnp_root = rcu_get_root(rsp);
 	int ret;
 
+	trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("startwait"));
 	jiffies_stall = rcu_jiffies_till_stall_check();
 	jiffies_start = jiffies;
 
@@ -606,7 +626,7 @@ static void _synchronize_rcu_expedited(struct rcu_state *rsp,
 		rew.rew_rsp = rsp;
 		rew.rew_s = s;
 		INIT_WORK_ONSTACK(&rew.rew_work, wait_rcu_exp_gp);
-		schedule_work(&rew.rew_work);
+		queue_work(rcu_gp_wq, &rew.rew_work);
 	}
 
 	/* Wait for expedited grace period to complete. */

kernel/rcu/tree_plugin.h

@@ -180,7 +180,7 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
 			 (rnp->expmask & rdp->grpmask ? RCU_EXP_BLKD : 0);
 	struct task_struct *t = current;
 
-	lockdep_assert_held(&rnp->lock);
+	raw_lockdep_assert_held_rcu_node(rnp);
 	WARN_ON_ONCE(rdp->mynode != rnp);
 	WARN_ON_ONCE(rnp->level != rcu_num_lvls - 1);
 
@@ -560,8 +560,14 @@ static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp)
 	}
 	t = list_entry(rnp->gp_tasks->prev,
 		       struct task_struct, rcu_node_entry);
-	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry)
+	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
+		/*
+		 * We could be printing a lot while holding a spinlock.
+		 * Avoid triggering hard lockup.
+		 */
+		touch_nmi_watchdog();
 		sched_show_task(t);
+	}
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 }
 
@@ -957,14 +963,10 @@ static int rcu_boost(struct rcu_node *rnp)
 	 * expedited grace period must boost all blocked tasks, including
 	 * those blocking the pre-existing normal grace period.
 	 */
-	if (rnp->exp_tasks != NULL) {
+	if (rnp->exp_tasks != NULL)
 		tb = rnp->exp_tasks;
-		rnp->n_exp_boosts++;
-	} else {
+	else
 		tb = rnp->boost_tasks;
-		rnp->n_normal_boosts++;
-	}
-	rnp->n_tasks_boosted++;
 
 	/*
 	 * We boost task t by manufacturing an rt_mutex that appears to
@@ -1042,7 +1044,7 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
 {
 	struct task_struct *t;
 
-	lockdep_assert_held(&rnp->lock);
+	raw_lockdep_assert_held_rcu_node(rnp);
 	if (!rcu_preempt_blocked_readers_cgp(rnp) && rnp->exp_tasks == NULL) {
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		return;
@@ -1677,6 +1679,12 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu)
 	char *ticks_title;
 	unsigned long ticks_value;
 
+	/*
+	 * We could be printing a lot while holding a spinlock.  Avoid
+	 * triggering hard lockup.
+	 */
+	touch_nmi_watchdog();
+
 	if (rsp->gpnum == rdp->gpnum) {
 		ticks_title = "ticks this GP";
 		ticks_value = rdp->ticks_this_gp;
@@ -2235,7 +2243,6 @@ static int rcu_nocb_kthread(void *arg)
 		smp_mb__before_atomic();  /* _add after CB invocation. */
 		atomic_long_add(-c, &rdp->nocb_q_count);
 		atomic_long_add(-cl, &rdp->nocb_q_count_lazy);
-		rdp->n_nocbs_invoked += c;
 	}
 	return 0;
 }
@@ -2312,8 +2319,11 @@ void __init rcu_init_nohz(void)
 		cpumask_and(rcu_nocb_mask, cpu_possible_mask,
 			    rcu_nocb_mask);
 	}
-	pr_info("\tOffload RCU callbacks from CPUs: %*pbl.\n",
-		cpumask_pr_args(rcu_nocb_mask));
+	if (cpumask_empty(rcu_nocb_mask))
+		pr_info("\tOffload RCU callbacks from CPUs: (none).\n");
+	else
+		pr_info("\tOffload RCU callbacks from CPUs: %*pbl.\n",
+			cpumask_pr_args(rcu_nocb_mask));
 	if (rcu_nocb_poll)
 		pr_info("\tPoll for callbacks from no-CBs CPUs.\n");
 

kernel/time/Kconfig

@@ -113,16 +113,6 @@ config NO_HZ_FULL
 
 endchoice
 
-config NO_HZ_FULL_ALL
-       bool "Full dynticks system on all CPUs by default (except CPU 0)"
-       depends on NO_HZ_FULL
-       help
-         If the user doesn't pass the nohz_full boot option to
-	 define the range of full dynticks CPUs, consider that all
-	 CPUs in the system are full dynticks by default.
-	 Note the boot CPU will still be kept outside the range to
-	 handle the timekeeping duty.
-
 config NO_HZ
 	bool "Old Idle dynticks config"
 	depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS

kernel/time/tick-sched.c

@@ -405,30 +405,12 @@ static int tick_nohz_cpu_down(unsigned int cpu)
 	return 0;
 }
 
-static int tick_nohz_init_all(void)
-{
-	int err = -1;
-
-#ifdef CONFIG_NO_HZ_FULL_ALL
-	if (!alloc_cpumask_var(&tick_nohz_full_mask, GFP_KERNEL)) {
-		WARN(1, "NO_HZ: Can't allocate full dynticks cpumask\n");
-		return err;
-	}
-	err = 0;
-	cpumask_setall(tick_nohz_full_mask);
-	tick_nohz_full_running = true;
-#endif
-	return err;
-}
-
 void __init tick_nohz_init(void)
 {
 	int cpu, ret;
 
-	if (!tick_nohz_full_running) {
-		if (tick_nohz_init_all() < 0)
-			return;
-	}
+	if (!tick_nohz_full_running)
+		return;
 
 	/*
 	 * Full dynticks uses irq work to drive the tick rescheduling on safe

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

@@ -136,6 +136,9 @@ identify_boot_image () {
 		qemu-system-x86_64|qemu-system-i386)
 			echo arch/x86/boot/bzImage
 			;;
+		qemu-system-aarch64)
+			echo arch/arm64/boot/Image
+			;;
 		*)
 			echo vmlinux
 			;;
@@ -158,6 +161,9 @@ identify_qemu () {
 	elif echo $u | grep -q "Intel 80386"
 	then
 		echo qemu-system-i386
+	elif echo $u | grep -q aarch64
+	then
+		echo qemu-system-aarch64
 	elif uname -a | grep -q ppc64
 	then
 		echo qemu-system-ppc64
@@ -176,16 +182,20 @@ identify_qemu () {
 # Output arguments for the qemu "-append" string based on CPU type
 # and the TORTURE_QEMU_INTERACTIVE environment variable.
 identify_qemu_append () {
+	local console=ttyS0
 	case "$1" in
 	qemu-system-x86_64|qemu-system-i386)
 		echo noapic selinux=0 initcall_debug debug
 		;;
+	qemu-system-aarch64)
+		console=ttyAMA0
+		;;
 	esac
 	if test -n "$TORTURE_QEMU_INTERACTIVE"
 	then
 		echo root=/dev/sda
 	else
-		echo console=ttyS0
+		echo console=$console
 	fi
 }
 
@@ -197,6 +207,9 @@ identify_qemu_args () {
 	case "$1" in
 	qemu-system-x86_64|qemu-system-i386)
 		;;
+	qemu-system-aarch64)
+		echo -machine virt,gic-version=host -cpu host
+		;;
 	qemu-system-ppc64)
 		echo -enable-kvm -M pseries -nodefaults
 		echo -device spapr-vscsi
@@ -254,7 +267,7 @@ specify_qemu_cpus () {
 		echo $2
 	else
 		case "$1" in
-		qemu-system-x86_64|qemu-system-i386)
+		qemu-system-x86_64|qemu-system-i386|qemu-system-aarch64)
 			echo $2 -smp $3
 			;;
 		qemu-system-ppc64)

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

@@ -39,30 +39,31 @@ sed -e 's/us : / : /' |
 tr -d '\015' |
 awk '
 $8 == "start" {
-	if (starttask != "")
+	if (startseq != "")
 		nlost++;
 	starttask = $1;
 	starttime = $3;
 	startseq = $7;
+	seqtask[startseq] = starttask;
 }
 
 $8 == "end" {
-	if (starttask == $1 && startseq == $7) {
+	if (startseq == $7) {
 		curgpdur = $3 - starttime;
 		gptimes[++n] = curgpdur;
 		gptaskcnt[starttask]++;
 		sum += curgpdur;
 		if (curgpdur > 1000)
 			print "Long GP " starttime "us to " $3 "us (" curgpdur "us)";
-		starttask = "";
+		startseq = "";
 	} else {
 		# Lost a message or some such, reset.
-		starttask = "";
+		startseq = "";
 		nlost++;
 	}
 }
 
-$8 == "done" {
+$8 == "done" && seqtask[$7] != $1 {
 	piggybackcnt[$1]++;
 }
 

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

@@ -177,8 +177,8 @@ then
 	exit 0
 fi
 echo "NOTE: $QEMU either did not run or was interactive" > $resdir/console.log
-echo $QEMU $qemu_args -m 512 -kernel $KERNEL -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd
-( $QEMU $qemu_args -m 512 -kernel $KERNEL -append "$qemu_append $boot_args"& echo $! > $resdir/qemu_pid; wait `cat  $resdir/qemu_pid`; echo $? > $resdir/qemu-retval ) &
+echo $QEMU $qemu_args -m $TORTURE_QEMU_MEM -kernel $KERNEL -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd
+( $QEMU $qemu_args -m $TORTURE_QEMU_MEM -kernel $KERNEL -append "$qemu_append $boot_args"& echo $! > $resdir/qemu_pid; wait `cat  $resdir/qemu_pid`; echo $? > $resdir/qemu-retval ) &
 commandcompleted=0
 sleep 10 # Give qemu's pid a chance to reach the file
 if test -s "$resdir/qemu_pid"

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

@@ -1,10 +1,8 @@
 #!/bin/bash
 #
-# Run a series of 14 tests under KVM.  These are not particularly
-# well-selected or well-tuned, but are the current set.
-#
-# Edit the definitions below to set the locations of the various directories,
-# as well as the test duration.
+# Run a series of tests under KVM.  By default, this series is specified
+# by the relevant CFLIST file, but can be overridden by the --configs
+# command-line argument.
 #
 # Usage: kvm.sh [ options ]
 #
@@ -44,6 +42,7 @@ TORTURE_BOOT_IMAGE=""
 TORTURE_INITRD="$KVM/initrd"; export TORTURE_INITRD
 TORTURE_KCONFIG_ARG=""
 TORTURE_KMAKE_ARG=""
+TORTURE_QEMU_MEM=512
 TORTURE_SHUTDOWN_GRACE=180
 TORTURE_SUITE=rcu
 resdir=""
@@ -70,6 +69,7 @@ usage () {
 	echo "       --kconfig Kconfig-options"
 	echo "       --kmake-arg kernel-make-arguments"
 	echo "       --mac nn:nn:nn:nn:nn:nn"
+	echo "       --memory megabytes | nnnG"
 	echo "       --no-initrd"
 	echo "       --qemu-args qemu-arguments"
 	echo "       --qemu-cmd qemu-system-..."
@@ -147,6 +147,11 @@ do
 		TORTURE_QEMU_MAC=$2
 		shift
 		;;
+	--memory)
+		checkarg --memory "(memory size)" $# "$2" '^[0-9]\+[MG]\?$' error
+		TORTURE_QEMU_MEM=$2
+		shift
+		;;
 	--no-initrd)
 		TORTURE_INITRD=""; export TORTURE_INITRD
 		;;
@@ -174,6 +179,12 @@ do
 		checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\|rcuperf\)$' '^--'
 		TORTURE_SUITE=$2
 		shift
+		if test "$TORTURE_SUITE" = rcuperf
+		then
+			# If you really want jitter for rcuperf, specify
+			# it after specifying rcuperf.  (But why?)
+			jitter=0
+		fi
 		;;
 	*)
 		echo Unknown argument $1
@@ -288,6 +299,7 @@ TORTURE_KMAKE_ARG="$TORTURE_KMAKE_ARG"; export TORTURE_KMAKE_ARG
 TORTURE_QEMU_CMD="$TORTURE_QEMU_CMD"; export TORTURE_QEMU_CMD
 TORTURE_QEMU_INTERACTIVE="$TORTURE_QEMU_INTERACTIVE"; export TORTURE_QEMU_INTERACTIVE
 TORTURE_QEMU_MAC="$TORTURE_QEMU_MAC"; export TORTURE_QEMU_MAC
+TORTURE_QEMU_MEM="$TORTURE_QEMU_MEM"; export TORTURE_QEMU_MEM
 TORTURE_SHUTDOWN_GRACE="$TORTURE_SHUTDOWN_GRACE"; export TORTURE_SHUTDOWN_GRACE
 TORTURE_SUITE="$TORTURE_SUITE"; export TORTURE_SUITE
 if ! test -e $resdir

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

@@ -9,5 +9,4 @@ CONFIG_PREEMPT=y
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=n
 CONFIG_NO_HZ_FULL=y
-CONFIG_NO_HZ_FULL_ALL=y
 #CHECK#CONFIG_RCU_EXPERT=n

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

@@ -1 +1 @@
-rcutorture.torture_type=tasks
+rcutorture.torture_type=tasks nohz_full=1

tools/testing/selftests/rcutorture/configs/rcu/TREE04

@@ -7,7 +7,6 @@ CONFIG_PREEMPT=n
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=n
 CONFIG_NO_HZ_FULL=y
-CONFIG_NO_HZ_FULL_ALL=y
 CONFIG_RCU_FAST_NO_HZ=y
 CONFIG_RCU_TRACE=y
 CONFIG_HOTPLUG_CPU=n

tools/testing/selftests/rcutorture/configs/rcu/TREE04.boot

@@ -1 +1 @@
-rcutorture.torture_type=rcu_bh rcutree.rcu_fanout_leaf=4
+rcutorture.torture_type=rcu_bh rcutree.rcu_fanout_leaf=4 nohz_full=1-7

tools/testing/selftests/rcutorture/configs/rcu/TREE07

@@ -7,7 +7,6 @@ CONFIG_PREEMPT=n
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=n
 CONFIG_NO_HZ_FULL=y
-CONFIG_NO_HZ_FULL_ALL=n
 CONFIG_RCU_FAST_NO_HZ=n
 CONFIG_RCU_TRACE=y
 CONFIG_HOTPLUG_CPU=y

tools/testing/selftests/rcutorture/configs/rcuperf/ver_functions.sh

@@ -20,32 +20,10 @@
 #
 # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 
-# rcuperf_param_nreaders bootparam-string
-#
-# Adds nreaders rcuperf module parameter if not already specified.
-rcuperf_param_nreaders () {
-	if ! echo "$1" | grep -q "rcuperf.nreaders"
-	then
-		echo rcuperf.nreaders=-1
-	fi
-}
-
-# rcuperf_param_nwriters bootparam-string
-#
-# Adds nwriters rcuperf module parameter if not already specified.
-rcuperf_param_nwriters () {
-	if ! echo "$1" | grep -q "rcuperf.nwriters"
-	then
-		echo rcuperf.nwriters=-1
-	fi
-}
-
 # per_version_boot_params bootparam-string config-file seconds
 #
 # Adds per-version torture-module parameters to kernels supporting them.
 per_version_boot_params () {
-	echo $1 `rcuperf_param_nreaders "$1"` \
-		`rcuperf_param_nwriters "$1"` \
-		rcuperf.shutdown=1 \
+	echo $1 rcuperf.shutdown=1 \
 		rcuperf.verbose=1
 }

tools/testing/selftests/rcutorture/doc/rcu-test-image.txt

@@ -1,4 +1,4 @@
-This document describes one way to created the rcu-test-image file
+This document describes one way to create the rcu-test-image file
 that contains the filesystem used by the guest-OS kernel.  There are
 probably much better ways of doing this, and this filesystem could no
 doubt be smaller.  It is probably also possible to simply download