Merge branches 'doc.2020.02.27a', 'fixes.2020.03.21a',...

Merge branches 'doc.2020.02.27a', 'fixes.2020.03.21a', 'kfree_rcu.2020.02.20a', 'locktorture.2020.02.20a', 'ovld.2020.02.20a', 'rcu-tasks.2020.02.20a', 'srcu.2020.02.20a' and 'torture.2020.02.20a' into HEAD

doc.2020.02.27a: Documentation updates.
fixes.2020.03.21a: Miscellaneous fixes.
kfree_rcu.2020.02.20a: Updates to kfree_rcu().
locktorture.2020.02.20a: Lock torture-test updates.
ovld.2020.02.20a: Updates to callback-overload handling.
rcu-tasks.2020.02.20a: RCU-tasks updates.
srcu.2020.02.20a: SRCU updates.
torture.2020.02.20a: Torture-test updates.

Documentation/admin-guide/kernel-parameters.txt

@@ -3980,6 +3980,15 @@
 			Set threshold of queued RCU callbacks below which
 			batch limiting is re-enabled.
 
+	rcutree.qovld= [KNL]
+			Set threshold of queued RCU callbacks beyond which
+			RCU's force-quiescent-state scan will aggressively
+			enlist help from cond_resched() and sched IPIs to
+			help CPUs more quickly reach quiescent states.
+			Set to less than zero to make this be set based
+			on rcutree.qhimark at boot time and to zero to
+			disable more aggressive help enlistment.
+
 	rcutree.rcu_idle_gp_delay= [KNL]
 			Set wakeup interval for idle CPUs that have
 			RCU callbacks (RCU_FAST_NO_HZ=y).
@@ -4195,6 +4204,12 @@
 	rcupdate.rcu_cpu_stall_suppress= [KNL]
 			Suppress RCU CPU stall warning messages.
 
+	rcupdate.rcu_cpu_stall_suppress_at_boot= [KNL]
+			Suppress RCU CPU stall warning messages and
+			rcutorture writer stall warnings that occur
+			during early boot, that is, during the time
+			before the init task is spawned.
+
 	rcupdate.rcu_cpu_stall_timeout= [KNL]
 			Set timeout for RCU CPU stall warning messages.
 
@@ -4867,6 +4882,10 @@
 			topology updates sent by the hypervisor to this
 			LPAR.
 
+	torture.disable_onoff_at_boot= [KNL]
+			Prevent the CPU-hotplug component of torturing
+			until after init has spawned.
+
 	tp720=		[HW,PS2]
 
 	tpm_suspend_pcr=[HW,TPM]

fs/nfs/dir.c

@@ -2383,7 +2383,7 @@ static int nfs_access_get_cached_rcu(struct inode *inode, const struct cred *cre
 	rcu_read_lock();
 	if (nfsi->cache_validity & NFS_INO_INVALID_ACCESS)
 		goto out;
-	lh = rcu_dereference(nfsi->access_cache_entry_lru.prev);
+	lh = rcu_dereference(list_tail_rcu(&nfsi->access_cache_entry_lru));
 	cache = list_entry(lh, struct nfs_access_entry, lru);
 	if (lh == &nfsi->access_cache_entry_lru ||
 	    cred_fscmp(cred, cache->cred) != 0)

include/linux/rculist.h

@@ -60,9 +60,9 @@ static inline void INIT_LIST_HEAD_RCU(struct list_head *list)
 #define __list_check_rcu(dummy, cond, extra...)				\
 	({								\
 	check_arg_count_one(extra);					\
-	RCU_LOCKDEP_WARN(!cond && !rcu_read_lock_any_held(),		\
+	RCU_LOCKDEP_WARN(!(cond) && !rcu_read_lock_any_held(),		\
 			 "RCU-list traversed in non-reader section!");	\
-	 })
+	})
 #else
 #define __list_check_rcu(dummy, cond, extra...)				\
 	({ check_arg_count_one(extra); })

include/linux/rcutiny.h

@@ -83,6 +83,7 @@ void rcu_scheduler_starting(void);
 static inline void rcu_scheduler_starting(void) { }
 #endif /* #else #ifndef CONFIG_SRCU */
 static inline void rcu_end_inkernel_boot(void) { }
+static inline bool rcu_inkernel_boot_has_ended(void) { return true; }
 static inline bool rcu_is_watching(void) { return true; }
 static inline void rcu_momentary_dyntick_idle(void) { }
 static inline void kfree_rcu_scheduler_running(void) { }

include/linux/rcutree.h

@@ -54,6 +54,7 @@ void exit_rcu(void);
 void rcu_scheduler_starting(void);
 extern int rcu_scheduler_active __read_mostly;
 void rcu_end_inkernel_boot(void);
+bool rcu_inkernel_boot_has_ended(void);
 bool rcu_is_watching(void);
 #ifndef CONFIG_PREEMPTION
 void rcu_all_qs(void);

include/linux/timer.h

@@ -164,7 +164,7 @@ static inline void destroy_timer_on_stack(struct timer_list *timer) { }
  */
 static inline int timer_pending(const struct timer_list * timer)
 {
-	return timer->entry.pprev != NULL;
+	return !hlist_unhashed_lockless(&timer->entry);
 }
 
 extern void add_timer_on(struct timer_list *timer, int cpu);

include/trace/events/rcu.h

@@ -623,6 +623,34 @@ TRACE_EVENT_RCU(rcu_invoke_kfree_callback,
 		  __entry->rcuname, __entry->rhp, __entry->offset)
 );
 
+/*
+ * Tracepoint for the invocation of a single RCU callback of the special
+ * kfree_bulk() form. The first argument is the RCU flavor, the second
+ * argument is a number of elements in array to free, the third is an
+ * address of the array holding nr_records entries.
+ */
+TRACE_EVENT_RCU(rcu_invoke_kfree_bulk_callback,
+
+	TP_PROTO(const char *rcuname, unsigned long nr_records, void **p),
+
+	TP_ARGS(rcuname, nr_records, p),
+
+	TP_STRUCT__entry(
+		__field(const char *, rcuname)
+		__field(unsigned long, nr_records)
+		__field(void **, p)
+	),
+
+	TP_fast_assign(
+		__entry->rcuname = rcuname;
+		__entry->nr_records = nr_records;
+		__entry->p = p;
+	),
+
+	TP_printk("%s bulk=0x%p nr_records=%lu",
+		__entry->rcuname, __entry->p, __entry->nr_records)
+);
+
 /*
  * Tracepoint for exiting rcu_do_batch after RCU callbacks have been
  * invoked.  The first argument is the name of the RCU flavor,
@@ -712,6 +740,7 @@ TRACE_EVENT_RCU(rcu_torture_read,
  *	"Begin": rcu_barrier() started.
  *	"EarlyExit": rcu_barrier() piggybacked, thus early exit.
  *	"Inc1": rcu_barrier() piggyback check counter incremented.
+ *	"OfflineNoCBQ": rcu_barrier() found offline no-CBs CPU with callbacks.
  *	"OnlineQ": rcu_barrier() found online CPU with callbacks.
  *	"OnlineNQ": rcu_barrier() found online CPU, no callbacks.
  *	"IRQ": An rcu_barrier_callback() callback posted on remote CPU.

kernel/locking/locktorture.c

@@ -618,7 +618,7 @@ static struct lock_torture_ops percpu_rwsem_lock_ops = {
 static int lock_torture_writer(void *arg)
 {
 	struct lock_stress_stats *lwsp = arg;
-	static DEFINE_TORTURE_RANDOM(rand);
+	DEFINE_TORTURE_RANDOM(rand);
 
 	VERBOSE_TOROUT_STRING("lock_torture_writer task started");
 	set_user_nice(current, MAX_NICE);
@@ -655,7 +655,7 @@ static int lock_torture_writer(void *arg)
 static int lock_torture_reader(void *arg)
 {
 	struct lock_stress_stats *lrsp = arg;
-	static DEFINE_TORTURE_RANDOM(rand);
+	DEFINE_TORTURE_RANDOM(rand);
 
 	VERBOSE_TOROUT_STRING("lock_torture_reader task started");
 	set_user_nice(current, MAX_NICE);
@@ -696,15 +696,16 @@ static void __torture_print_stats(char *page,
 		if (statp[i].n_lock_fail)
 			fail = true;
 		sum += statp[i].n_lock_acquired;
-		if (max < statp[i].n_lock_fail)
-			max = statp[i].n_lock_fail;
-		if (min > statp[i].n_lock_fail)
-			min = statp[i].n_lock_fail;
+		if (max < statp[i].n_lock_acquired)
+			max = statp[i].n_lock_acquired;
+		if (min > statp[i].n_lock_acquired)
+			min = statp[i].n_lock_acquired;
 	}
 	page += sprintf(page,
 			"%s:  Total: %lld  Max/Min: %ld/%ld %s  Fail: %d %s\n",
 			write ? "Writes" : "Reads ",
-			sum, max, min, max / 2 > min ? "???" : "",
+			sum, max, min,
+			!onoff_interval && max / 2 > min ? "???" : "",
 			fail, fail ? "!!!" : "");
 	if (fail)
 		atomic_inc(&cxt.n_lock_torture_errors);

kernel/locking/rtmutex.c

@@ -57,7 +57,7 @@ rt_mutex_set_owner(struct rt_mutex *lock, struct task_struct *owner)
 	if (rt_mutex_has_waiters(lock))
 		val |= RT_MUTEX_HAS_WAITERS;
 
-	lock->owner = (struct task_struct *)val;
+	WRITE_ONCE(lock->owner, (struct task_struct *)val);
 }
 
 static inline void clear_rt_mutex_waiters(struct rt_mutex *lock)

kernel/rcu/Makefile

@@ -3,6 +3,10 @@
 # and is generally not a function of system call inputs.
 KCOV_INSTRUMENT := n
 
+ifeq ($(CONFIG_KCSAN),y)
+KBUILD_CFLAGS += -g -fno-omit-frame-pointer
+endif
+
 obj-y += update.o sync.o
 obj-$(CONFIG_TREE_SRCU) += srcutree.o
 obj-$(CONFIG_TINY_SRCU) += srcutiny.o

kernel/rcu/rcu.h

@@ -198,6 +198,13 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head)
 }
 #endif	/* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 
+extern int rcu_cpu_stall_suppress_at_boot;
+
+static inline bool rcu_stall_is_suppressed_at_boot(void)
+{
+	return rcu_cpu_stall_suppress_at_boot && !rcu_inkernel_boot_has_ended();
+}
+
 #ifdef CONFIG_RCU_STALL_COMMON
 
 extern int rcu_cpu_stall_ftrace_dump;
@@ -205,6 +212,11 @@ extern int rcu_cpu_stall_suppress;
 extern int rcu_cpu_stall_timeout;
 int rcu_jiffies_till_stall_check(void);
 
+static inline bool rcu_stall_is_suppressed(void)
+{
+	return rcu_stall_is_suppressed_at_boot() || rcu_cpu_stall_suppress;
+}
+
 #define rcu_ftrace_dump_stall_suppress() \
 do { \
 	if (!rcu_cpu_stall_suppress) \
@@ -218,6 +230,11 @@ do { \
 } while (0)
 
 #else /* #endif #ifdef CONFIG_RCU_STALL_COMMON */
+
+static inline bool rcu_stall_is_suppressed(void)
+{
+	return rcu_stall_is_suppressed_at_boot();
+}
 #define rcu_ftrace_dump_stall_suppress()
 #define rcu_ftrace_dump_stall_unsuppress()
 #endif /* #ifdef CONFIG_RCU_STALL_COMMON */
@@ -325,7 +342,8 @@ 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); \
+	for (WARN_ON_ONCE(!rcu_is_leaf_node(rnp)), \
+	     (cpu) = cpumask_next((rnp)->grplo - 1, cpu_possible_mask); \
 	     (cpu) <= rnp->grphi; \
 	     (cpu) = cpumask_next((cpu), cpu_possible_mask))
 
@@ -335,7 +353,8 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt)
 #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)); \
+	for (WARN_ON_ONCE(!rcu_is_leaf_node(rnp)), \
+	     (cpu) = rcu_find_next_bit((rnp), 0, (mask)); \
 	     (cpu) <= rnp->grphi; \
 	     (cpu) = rcu_find_next_bit((rnp), (cpu) + 1 - (rnp->grplo), (mask)))
 

kernel/rcu/rcu_segcblist.c

@@ -182,7 +182,7 @@ void rcu_segcblist_offload(struct rcu_segcblist *rsclp)
 bool rcu_segcblist_ready_cbs(struct rcu_segcblist *rsclp)
 {
 	return rcu_segcblist_is_enabled(rsclp) &&
-	       &rsclp->head != rsclp->tails[RCU_DONE_TAIL];
+	       &rsclp->head != READ_ONCE(rsclp->tails[RCU_DONE_TAIL]);
 }
 
 /*
@@ -381,8 +381,6 @@ void rcu_segcblist_insert_pend_cbs(struct rcu_segcblist *rsclp,
 		return; /* Nothing to do. */
 	WRITE_ONCE(*rsclp->tails[RCU_NEXT_TAIL], rclp->head);
 	WRITE_ONCE(rsclp->tails[RCU_NEXT_TAIL], rclp->tail);
-	rclp->head = NULL;
-	rclp->tail = &rclp->head;
 }
 
 /*

kernel/rcu/rcuperf.c

@@ -12,6 +12,7 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/kthread.h>
 #include <linux/err.h>
@@ -611,6 +612,7 @@ kfree_perf_thread(void *arg)
 	long me = (long)arg;
 	struct kfree_obj *alloc_ptr;
 	u64 start_time, end_time;
+	long long mem_begin, mem_during = 0;
 
 	VERBOSE_PERFOUT_STRING("kfree_perf_thread task started");
 	set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids));
@@ -626,6 +628,12 @@ kfree_perf_thread(void *arg)
 	}
 
 	do {
+		if (!mem_during) {
+			mem_during = mem_begin = si_mem_available();
+		} else if (loop % (kfree_loops / 4) == 0) {
+			mem_during = (mem_during + si_mem_available()) / 2;
+		}
+
 		for (i = 0; i < kfree_alloc_num; i++) {
 			alloc_ptr = kmalloc(sizeof(struct kfree_obj), GFP_KERNEL);
 			if (!alloc_ptr)
@@ -645,9 +653,11 @@ kfree_perf_thread(void *arg)
 		else
 			b_rcu_gp_test_finished = cur_ops->get_gp_seq();
 
-		pr_alert("Total time taken by all kfree'ers: %llu ns, loops: %d, batches: %ld\n",
+		pr_alert("Total time taken by all kfree'ers: %llu ns, loops: %d, batches: %ld, memory footprint: %lldMB\n",
 		       (unsigned long long)(end_time - start_time), kfree_loops,
-		       rcuperf_seq_diff(b_rcu_gp_test_finished, b_rcu_gp_test_started));
+		       rcuperf_seq_diff(b_rcu_gp_test_finished, b_rcu_gp_test_started),
+		       (mem_begin - mem_during) >> (20 - PAGE_SHIFT));
+
 		if (shutdown) {
 			smp_mb(); /* Assign before wake. */
 			wake_up(&shutdown_wq);

kernel/rcu/rcutorture.c

@@ -339,7 +339,7 @@ rcu_read_delay(struct torture_random_state *rrsp, struct rt_read_seg *rtrsp)
 	 * period, and we want a long delay occasionally to trigger
 	 * force_quiescent_state. */
 
-	if (!rcu_fwd_cb_nodelay &&
+	if (!READ_ONCE(rcu_fwd_cb_nodelay) &&
 	    !(torture_random(rrsp) % (nrealreaders * 2000 * longdelay_ms))) {
 		started = cur_ops->get_gp_seq();
 		ts = rcu_trace_clock_local();
@@ -375,11 +375,12 @@ rcu_torture_pipe_update_one(struct rcu_torture *rp)
 {
 	int i;
 
-	i = rp->rtort_pipe_count;
+	i = READ_ONCE(rp->rtort_pipe_count);
 	if (i > RCU_TORTURE_PIPE_LEN)
 		i = RCU_TORTURE_PIPE_LEN;
 	atomic_inc(&rcu_torture_wcount[i]);
-	if (++rp->rtort_pipe_count >= RCU_TORTURE_PIPE_LEN) {
+	WRITE_ONCE(rp->rtort_pipe_count, i + 1);
+	if (rp->rtort_pipe_count >= RCU_TORTURE_PIPE_LEN) {
 		rp->rtort_mbtest = 0;
 		return true;
 	}
@@ -1015,7 +1016,8 @@ rcu_torture_writer(void *arg)
 			if (i > RCU_TORTURE_PIPE_LEN)
 				i = RCU_TORTURE_PIPE_LEN;
 			atomic_inc(&rcu_torture_wcount[i]);
-			old_rp->rtort_pipe_count++;
+			WRITE_ONCE(old_rp->rtort_pipe_count,
+				   old_rp->rtort_pipe_count + 1);
 			switch (synctype[torture_random(&rand) % nsynctypes]) {
 			case RTWS_DEF_FREE:
 				rcu_torture_writer_state = RTWS_DEF_FREE;
@@ -1067,7 +1069,8 @@ rcu_torture_writer(void *arg)
 		if (stutter_wait("rcu_torture_writer") &&
 		    !READ_ONCE(rcu_fwd_cb_nodelay) &&
 		    !cur_ops->slow_gps &&
-		    !torture_must_stop())
+		    !torture_must_stop() &&
+		    rcu_inkernel_boot_has_ended())
 			for (i = 0; i < ARRAY_SIZE(rcu_tortures); i++)
 				if (list_empty(&rcu_tortures[i].rtort_free) &&
 				    rcu_access_pointer(rcu_torture_current) !=
@@ -1290,7 +1293,7 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp)
 		atomic_inc(&n_rcu_torture_mberror);
 	rtrsp = rcutorture_loop_extend(&readstate, trsp, rtrsp);
 	preempt_disable();
-	pipe_count = p->rtort_pipe_count;
+	pipe_count = READ_ONCE(p->rtort_pipe_count);
 	if (pipe_count > RCU_TORTURE_PIPE_LEN) {
 		/* Should not happen, but... */
 		pipe_count = RCU_TORTURE_PIPE_LEN;
@@ -1404,14 +1407,15 @@ rcu_torture_stats_print(void)
 	int i;
 	long pipesummary[RCU_TORTURE_PIPE_LEN + 1] = { 0 };
 	long batchsummary[RCU_TORTURE_PIPE_LEN + 1] = { 0 };
+	struct rcu_torture *rtcp;
 	static unsigned long rtcv_snap = ULONG_MAX;
 	static bool splatted;
 	struct task_struct *wtp;
 
 	for_each_possible_cpu(cpu) {
 		for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) {
-			pipesummary[i] += per_cpu(rcu_torture_count, cpu)[i];
-			batchsummary[i] += per_cpu(rcu_torture_batch, cpu)[i];
+			pipesummary[i] += READ_ONCE(per_cpu(rcu_torture_count, cpu)[i]);
+			batchsummary[i] += READ_ONCE(per_cpu(rcu_torture_batch, cpu)[i]);
 		}
 	}
 	for (i = RCU_TORTURE_PIPE_LEN - 1; i >= 0; i--) {
@@ -1420,9 +1424,10 @@ rcu_torture_stats_print(void)
 	}
 
 	pr_alert("%s%s ", torture_type, TORTURE_FLAG);
+	rtcp = rcu_access_pointer(rcu_torture_current);
 	pr_cont("rtc: %p %s: %lu tfle: %d rta: %d rtaf: %d rtf: %d ",
-		rcu_torture_current,
-		rcu_torture_current ? "ver" : "VER",
+		rtcp,
+		rtcp && !rcu_stall_is_suppressed_at_boot() ? "ver" : "VER",
 		rcu_torture_current_version,
 		list_empty(&rcu_torture_freelist),
 		atomic_read(&n_rcu_torture_alloc),
@@ -1478,7 +1483,8 @@ rcu_torture_stats_print(void)
 	if (cur_ops->stats)
 		cur_ops->stats();
 	if (rtcv_snap == rcu_torture_current_version &&
-	    rcu_torture_current != NULL) {
+	    rcu_access_pointer(rcu_torture_current) &&
+	    !rcu_stall_is_suppressed()) {
 		int __maybe_unused flags = 0;
 		unsigned long __maybe_unused gp_seq = 0;
 
@@ -1993,8 +1999,11 @@ static int rcu_torture_fwd_prog(void *args)
 		schedule_timeout_interruptible(fwd_progress_holdoff * HZ);
 		WRITE_ONCE(rcu_fwd_emergency_stop, false);
 		register_oom_notifier(&rcutorture_oom_nb);
-		rcu_torture_fwd_prog_nr(rfp, &tested, &tested_tries);
-		rcu_torture_fwd_prog_cr(rfp);
+		if (!IS_ENABLED(CONFIG_TINY_RCU) ||
+		    rcu_inkernel_boot_has_ended())
+			rcu_torture_fwd_prog_nr(rfp, &tested, &tested_tries);
+		if (rcu_inkernel_boot_has_ended())
+			rcu_torture_fwd_prog_cr(rfp);
 		unregister_oom_notifier(&rcutorture_oom_nb);
 
 		/* Avoid slow periods, better to test when busy. */
@@ -2044,6 +2053,14 @@ static void rcu_torture_barrier_cbf(struct rcu_head *rcu)
 	atomic_inc(&barrier_cbs_invoked);
 }
 
+/* IPI handler to get callback posted on desired CPU, if online. */
+static void rcu_torture_barrier1cb(void *rcu_void)
+{
+	struct rcu_head *rhp = rcu_void;
+
+	cur_ops->call(rhp, rcu_torture_barrier_cbf);
+}
+
 /* kthread function to register callbacks used to test RCU barriers. */
 static int rcu_torture_barrier_cbs(void *arg)
 {
@@ -2067,9 +2084,11 @@ static int rcu_torture_barrier_cbs(void *arg)
 		 * The above smp_load_acquire() ensures barrier_phase load
 		 * is ordered before the following ->call().
 		 */
-		local_irq_disable(); /* Just to test no-irq call_rcu(). */
-		cur_ops->call(&rcu, rcu_torture_barrier_cbf);
-		local_irq_enable();
+		if (smp_call_function_single(myid, rcu_torture_barrier1cb,
+					     &rcu, 1)) {
+			// IPI failed, so use direct call from current CPU.
+			cur_ops->call(&rcu, rcu_torture_barrier_cbf);
+		}
 		if (atomic_dec_and_test(&barrier_cbs_count))
 			wake_up(&barrier_wq);
 	} while (!torture_must_stop());
@@ -2105,7 +2124,21 @@ static int rcu_torture_barrier(void *arg)
 			pr_err("barrier_cbs_invoked = %d, n_barrier_cbs = %d\n",
 			       atomic_read(&barrier_cbs_invoked),
 			       n_barrier_cbs);
-			WARN_ON_ONCE(1);
+			WARN_ON(1);
+			// Wait manually for the remaining callbacks
+			i = 0;
+			do {
+				if (WARN_ON(i++ > HZ))
+					i = INT_MIN;
+				schedule_timeout_interruptible(1);
+				cur_ops->cb_barrier();
+			} while (atomic_read(&barrier_cbs_invoked) !=
+				 n_barrier_cbs &&
+				 !torture_must_stop());
+			smp_mb(); // Can't trust ordering if broken.
+			if (!torture_must_stop())
+				pr_err("Recovered: barrier_cbs_invoked = %d\n",
+				       atomic_read(&barrier_cbs_invoked));
 		} else {
 			n_barrier_successes++;
 		}

kernel/rcu/srcutree.c

@@ -5,7 +5,7 @@
  * Copyright (C) IBM Corporation, 2006
  * Copyright (C) Fujitsu, 2012
  *
- * Author: Paul McKenney <paulmck@linux.ibm.com>
+ * Authors: Paul McKenney <paulmck@linux.ibm.com>
  *	   Lai Jiangshan <laijs@cn.fujitsu.com>
  *
  * For detailed explanation of Read-Copy Update mechanism see -
@@ -450,7 +450,7 @@ static void srcu_gp_start(struct srcu_struct *ssp)
 	spin_unlock_rcu_node(sdp);  /* Interrupts remain disabled. */
 	smp_mb(); /* Order prior store to ->srcu_gp_seq_needed vs. GP start. */
 	rcu_seq_start(&ssp->srcu_gp_seq);
-	state = rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq));
+	state = rcu_seq_state(ssp->srcu_gp_seq);
 	WARN_ON_ONCE(state != SRCU_STATE_SCAN1);
 }
 
@@ -534,7 +534,7 @@ static void srcu_gp_end(struct srcu_struct *ssp)
 	rcu_seq_end(&ssp->srcu_gp_seq);
 	gpseq = rcu_seq_current(&ssp->srcu_gp_seq);
 	if (ULONG_CMP_LT(ssp->srcu_gp_seq_needed_exp, gpseq))
-		ssp->srcu_gp_seq_needed_exp = gpseq;
+		WRITE_ONCE(ssp->srcu_gp_seq_needed_exp, gpseq);
 	spin_unlock_irq_rcu_node(ssp);
 	mutex_unlock(&ssp->srcu_gp_mutex);
 	/* A new grace period can start at this point.  But only one. */
@@ -550,7 +550,7 @@ static void srcu_gp_end(struct srcu_struct *ssp)
 		snp->srcu_have_cbs[idx] = gpseq;
 		rcu_seq_set_state(&snp->srcu_have_cbs[idx], 1);
 		if (ULONG_CMP_LT(snp->srcu_gp_seq_needed_exp, gpseq))
-			snp->srcu_gp_seq_needed_exp = gpseq;
+			WRITE_ONCE(snp->srcu_gp_seq_needed_exp, gpseq);
 		mask = snp->srcu_data_have_cbs[idx];
 		snp->srcu_data_have_cbs[idx] = 0;
 		spin_unlock_irq_rcu_node(snp);
@@ -614,7 +614,7 @@ static void srcu_funnel_exp_start(struct srcu_struct *ssp, struct srcu_node *snp
 	}
 	spin_lock_irqsave_rcu_node(ssp, flags);
 	if (ULONG_CMP_LT(ssp->srcu_gp_seq_needed_exp, s))
-		ssp->srcu_gp_seq_needed_exp = s;
+		WRITE_ONCE(ssp->srcu_gp_seq_needed_exp, s);
 	spin_unlock_irqrestore_rcu_node(ssp, flags);
 }
 
@@ -660,7 +660,7 @@ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp,
 		if (snp == sdp->mynode)
 			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;
+			WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s);
 		spin_unlock_irqrestore_rcu_node(snp, flags);
 	}
 
@@ -674,7 +674,7 @@ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp,
 		smp_store_release(&ssp->srcu_gp_seq_needed, s); /*^^^*/
 	}
 	if (!do_norm && ULONG_CMP_LT(ssp->srcu_gp_seq_needed_exp, s))
-		ssp->srcu_gp_seq_needed_exp = s;
+		WRITE_ONCE(ssp->srcu_gp_seq_needed_exp, s);
 
 	/* If grace period not already done and none in progress, start it. */
 	if (!rcu_seq_done(&ssp->srcu_gp_seq, s) &&
@@ -1079,7 +1079,7 @@ EXPORT_SYMBOL_GPL(srcu_barrier);
  */
 unsigned long srcu_batches_completed(struct srcu_struct *ssp)
 {
-	return ssp->srcu_idx;
+	return READ_ONCE(ssp->srcu_idx);
 }
 EXPORT_SYMBOL_GPL(srcu_batches_completed);
 
@@ -1130,7 +1130,9 @@ static void srcu_advance_state(struct srcu_struct *ssp)
 			return; /* readers present, retry later. */
 		}
 		srcu_flip(ssp);
+		spin_lock_irq_rcu_node(ssp);
 		rcu_seq_set_state(&ssp->srcu_gp_seq, SRCU_STATE_SCAN2);
+		spin_unlock_irq_rcu_node(ssp);
 	}
 
 	if (rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)) == SRCU_STATE_SCAN2) {

kernel/rcu/tree.c

 // SPDX-License-Identifier: GPL-2.0+
 /*
- * Read-Copy Update mechanism for mutual exclusion
+ * Read-Copy Update mechanism for mutual exclusion (tree-based version)
  *
  * Copyright IBM Corporation, 2008
  *
  * Authors: Dipankar Sarma <dipankar@in.ibm.com>
  *	    Manfred Spraul <manfred@colorfullife.com>
- *	    Paul E. McKenney <paulmck@linux.ibm.com> Hierarchical version
+ *	    Paul E. McKenney <paulmck@linux.ibm.com>
  *
  * Based on the original work by Paul McKenney <paulmck@linux.ibm.com>
  * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
@@ -150,6 +150,7 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
 static void invoke_rcu_core(void);
 static void rcu_report_exp_rdp(struct rcu_data *rdp);
 static void sync_sched_exp_online_cleanup(int cpu);
+static void check_cb_ovld_locked(struct rcu_data *rdp, struct rcu_node *rnp);
 
 /* rcuc/rcub kthread realtime priority */
 static int kthread_prio = IS_ENABLED(CONFIG_RCU_BOOST) ? 1 : 0;
@@ -342,14 +343,17 @@ bool rcu_eqs_special_set(int cpu)
 {
 	int old;
 	int new;
+	int new_old;
 	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
 
+	new_old = atomic_read(&rdp->dynticks);
 	do {
-		old = atomic_read(&rdp->dynticks);
+		old = new_old;
 		if (old & RCU_DYNTICK_CTRL_CTR)
 			return false;
 		new = old | RCU_DYNTICK_CTRL_MASK;
-	} while (atomic_cmpxchg(&rdp->dynticks, old, new) != old);
+		new_old = atomic_cmpxchg(&rdp->dynticks, old, new);
+	} while (new_old != old);
 	return true;
 }
 
@@ -410,10 +414,15 @@ static long blimit = DEFAULT_RCU_BLIMIT;
 static long qhimark = DEFAULT_RCU_QHIMARK;
 #define DEFAULT_RCU_QLOMARK 100   /* Once only this many pending, use blimit. */
 static long qlowmark = DEFAULT_RCU_QLOMARK;
+#define DEFAULT_RCU_QOVLD_MULT 2
+#define DEFAULT_RCU_QOVLD (DEFAULT_RCU_QOVLD_MULT * DEFAULT_RCU_QHIMARK)
+static long qovld = DEFAULT_RCU_QOVLD; /* If this many pending, hammer QS. */
+static long qovld_calc = -1;	  /* No pre-initialization lock acquisitions! */
 
 module_param(blimit, long, 0444);
 module_param(qhimark, long, 0444);
 module_param(qlowmark, long, 0444);
+module_param(qovld, long, 0444);
 
 static ulong jiffies_till_first_fqs = ULONG_MAX;
 static ulong jiffies_till_next_fqs = ULONG_MAX;
@@ -818,11 +827,12 @@ static __always_inline void rcu_nmi_enter_common(bool irq)
 		incby = 1;
 	} else if (tick_nohz_full_cpu(rdp->cpu) &&
 		   rdp->dynticks_nmi_nesting == DYNTICK_IRQ_NONIDLE &&
-		   READ_ONCE(rdp->rcu_urgent_qs) && !rdp->rcu_forced_tick) {
+		   READ_ONCE(rdp->rcu_urgent_qs) &&
+		   !READ_ONCE(rdp->rcu_forced_tick)) {
 		raw_spin_lock_rcu_node(rdp->mynode);
 		// Recheck under lock.
 		if (rdp->rcu_urgent_qs && !rdp->rcu_forced_tick) {
-			rdp->rcu_forced_tick = true;
+			WRITE_ONCE(rdp->rcu_forced_tick, true);
 			tick_dep_set_cpu(rdp->cpu, TICK_DEP_BIT_RCU);
 		}
 		raw_spin_unlock_rcu_node(rdp->mynode);
@@ -899,7 +909,7 @@ static void rcu_disable_urgency_upon_qs(struct rcu_data *rdp)
 	WRITE_ONCE(rdp->rcu_need_heavy_qs, false);
 	if (tick_nohz_full_cpu(rdp->cpu) && rdp->rcu_forced_tick) {
 		tick_dep_clear_cpu(rdp->cpu, TICK_DEP_BIT_RCU);
-		rdp->rcu_forced_tick = false;
+		WRITE_ONCE(rdp->rcu_forced_tick, false);
 	}
 }
 
@@ -1072,7 +1082,8 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	rnhqp = &per_cpu(rcu_data.rcu_need_heavy_qs, rdp->cpu);
 	if (!READ_ONCE(*rnhqp) &&
 	    (time_after(jiffies, rcu_state.gp_start + jtsq * 2) ||
-	     time_after(jiffies, rcu_state.jiffies_resched))) {
+	     time_after(jiffies, rcu_state.jiffies_resched) ||
+	     rcu_state.cbovld)) {
 		WRITE_ONCE(*rnhqp, true);
 		/* Store rcu_need_heavy_qs before rcu_urgent_qs. */
 		smp_store_release(ruqp, true);
@@ -1089,8 +1100,8 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	 * So hit them over the head with the resched_cpu() hammer!
 	 */
 	if (tick_nohz_full_cpu(rdp->cpu) &&
-		   time_after(jiffies,
-			      READ_ONCE(rdp->last_fqs_resched) + jtsq * 3)) {
+	    (time_after(jiffies, READ_ONCE(rdp->last_fqs_resched) + jtsq * 3) ||
+	     rcu_state.cbovld)) {
 		WRITE_ONCE(*ruqp, true);
 		resched_cpu(rdp->cpu);
 		WRITE_ONCE(rdp->last_fqs_resched, jiffies);
@@ -1126,8 +1137,9 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
 			      unsigned long gp_seq_req, const char *s)
 {
-	trace_rcu_future_grace_period(rcu_state.name, rnp->gp_seq, gp_seq_req,
-				      rnp->level, rnp->grplo, rnp->grphi, s);
+	trace_rcu_future_grace_period(rcu_state.name, READ_ONCE(rnp->gp_seq),
+				      gp_seq_req, rnp->level,
+				      rnp->grplo, rnp->grphi, s);
 }
 
 /*
@@ -1174,7 +1186,7 @@ static bool rcu_start_this_gp(struct rcu_node *rnp_start, struct rcu_data *rdp,
 					  TPS("Prestarted"));
 			goto unlock_out;
 		}
-		rnp->gp_seq_needed = gp_seq_req;
+		WRITE_ONCE(rnp->gp_seq_needed, gp_seq_req);
 		if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq))) {
 			/*
 			 * We just marked the leaf or internal node, and a
@@ -1199,18 +1211,18 @@ static bool rcu_start_this_gp(struct rcu_node *rnp_start, struct rcu_data *rdp,
 	}
 	trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startedroot"));
 	WRITE_ONCE(rcu_state.gp_flags, rcu_state.gp_flags | RCU_GP_FLAG_INIT);
-	rcu_state.gp_req_activity = jiffies;
-	if (!rcu_state.gp_kthread) {
+	WRITE_ONCE(rcu_state.gp_req_activity, jiffies);
+	if (!READ_ONCE(rcu_state.gp_kthread)) {
 		trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("NoGPkthread"));
 		goto unlock_out;
 	}
-	trace_rcu_grace_period(rcu_state.name, READ_ONCE(rcu_state.gp_seq), TPS("newreq"));
+	trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("newreq"));
 	ret = true;  /* Caller must wake GP kthread. */
 unlock_out:
 	/* Push furthest requested GP to leaf node and rcu_data structure. */
 	if (ULONG_CMP_LT(gp_seq_req, rnp->gp_seq_needed)) {
-		rnp_start->gp_seq_needed = rnp->gp_seq_needed;
-		rdp->gp_seq_needed = rnp->gp_seq_needed;
+		WRITE_ONCE(rnp_start->gp_seq_needed, rnp->gp_seq_needed);
+		WRITE_ONCE(rdp->gp_seq_needed, rnp->gp_seq_needed);
 	}
 	if (rnp != rnp_start)
 		raw_spin_unlock_rcu_node(rnp);
@@ -1235,12 +1247,13 @@ static bool rcu_future_gp_cleanup(struct rcu_node *rnp)
 }
 
 /*
- * Awaken the grace-period kthread.  Don't do a self-awaken (unless in
- * an interrupt or softirq handler), and don't bother awakening when there
- * is nothing for the grace-period kthread to do (as in several CPUs raced
- * to awaken, and we lost), and finally don't try to awaken a kthread that
- * has not yet been created.  If all those checks are passed, track some
- * debug information and awaken.
+ * Awaken the grace-period kthread.  Don't do a self-awaken (unless in an
+ * interrupt or softirq handler, in which case we just might immediately
+ * sleep upon return, resulting in a grace-period hang), and don't bother
+ * awakening when there is nothing for the grace-period kthread to do
+ * (as in several CPUs raced to awaken, we lost), and finally don't try
+ * to awaken a kthread that has not yet been created.  If all those checks
+ * are passed, track some debug information and awaken.
  *
  * So why do the self-wakeup when in an interrupt or softirq handler
  * in the grace-period kthread's context?  Because the kthread might have
@@ -1250,10 +1263,10 @@ static bool rcu_future_gp_cleanup(struct rcu_node *rnp)
  */
 static void rcu_gp_kthread_wake(void)
 {
-	if ((current == rcu_state.gp_kthread &&
-	     !in_irq() && !in_serving_softirq()) ||
-	    !READ_ONCE(rcu_state.gp_flags) ||
-	    !rcu_state.gp_kthread)
+	struct task_struct *t = READ_ONCE(rcu_state.gp_kthread);
+
+	if ((current == t && !in_irq() && !in_serving_softirq()) ||
+	    !READ_ONCE(rcu_state.gp_flags) || !t)
 		return;
 	WRITE_ONCE(rcu_state.gp_wake_time, jiffies);
 	WRITE_ONCE(rcu_state.gp_wake_seq, READ_ONCE(rcu_state.gp_seq));
@@ -1321,7 +1334,7 @@ static void rcu_accelerate_cbs_unlocked(struct rcu_node *rnp,
 
 	rcu_lockdep_assert_cblist_protected(rdp);
 	c = rcu_seq_snap(&rcu_state.gp_seq);
-	if (!rdp->gpwrap && ULONG_CMP_GE(rdp->gp_seq_needed, c)) {
+	if (!READ_ONCE(rdp->gpwrap) && ULONG_CMP_GE(rdp->gp_seq_needed, c)) {
 		/* Old request still live, so mark recent callbacks. */
 		(void)rcu_segcblist_accelerate(&rdp->cblist, c);
 		return;
@@ -1386,7 +1399,7 @@ static void __maybe_unused rcu_advance_cbs_nowake(struct rcu_node *rnp,
 static bool __note_gp_changes(struct rcu_node *rnp, struct rcu_data *rdp)
 {
 	bool ret = false;
-	bool need_gp;
+	bool need_qs;
 	const bool offloaded = IS_ENABLED(CONFIG_RCU_NOCB_CPU) &&
 			       rcu_segcblist_is_offloaded(&rdp->cblist);
 
@@ -1400,10 +1413,13 @@ static bool __note_gp_changes(struct rcu_node *rnp, struct rcu_data *rdp)
 	    unlikely(READ_ONCE(rdp->gpwrap))) {
 		if (!offloaded)
 			ret = rcu_advance_cbs(rnp, rdp); /* Advance CBs. */
+		rdp->core_needs_qs = false;
 		trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("cpuend"));
 	} else {
 		if (!offloaded)
 			ret = rcu_accelerate_cbs(rnp, rdp); /* Recent CBs. */
+		if (rdp->core_needs_qs)
+			rdp->core_needs_qs = !!(rnp->qsmask & rdp->grpmask);
 	}
 
 	/* Now handle the beginnings of any new-to-this-CPU grace periods. */
@@ -1415,14 +1431,14 @@ static bool __note_gp_changes(struct rcu_node *rnp, struct rcu_data *rdp)
 		 * go looking for one.
 		 */
 		trace_rcu_grace_period(rcu_state.name, rnp->gp_seq, TPS("cpustart"));
-		need_gp = !!(rnp->qsmask & rdp->grpmask);
-		rdp->cpu_no_qs.b.norm = need_gp;
-		rdp->core_needs_qs = need_gp;
+		need_qs = !!(rnp->qsmask & rdp->grpmask);
+		rdp->cpu_no_qs.b.norm = need_qs;
+		rdp->core_needs_qs = need_qs;
 		zero_cpu_stall_ticks(rdp);
 	}
 	rdp->gp_seq = rnp->gp_seq;  /* Remember new grace-period state. */
 	if (ULONG_CMP_LT(rdp->gp_seq_needed, rnp->gp_seq_needed) || rdp->gpwrap)
-		rdp->gp_seq_needed = rnp->gp_seq_needed;
+		WRITE_ONCE(rdp->gp_seq_needed, rnp->gp_seq_needed);
 	WRITE_ONCE(rdp->gpwrap, false);
 	rcu_gpnum_ovf(rnp, rdp);
 	return ret;
@@ -1651,8 +1667,7 @@ static void rcu_gp_fqs_loop(void)
 			WRITE_ONCE(rcu_state.jiffies_kick_kthreads,
 				   jiffies + (j ? 3 * j : 2));
 		}
-		trace_rcu_grace_period(rcu_state.name,
-				       READ_ONCE(rcu_state.gp_seq),
+		trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
 				       TPS("fqswait"));
 		rcu_state.gp_state = RCU_GP_WAIT_FQS;
 		ret = swait_event_idle_timeout_exclusive(
@@ -1666,13 +1681,11 @@ static void rcu_gp_fqs_loop(void)
 		/* If time for quiescent-state forcing, do it. */
 		if (ULONG_CMP_GE(jiffies, rcu_state.jiffies_force_qs) ||
 		    (gf & RCU_GP_FLAG_FQS)) {
-			trace_rcu_grace_period(rcu_state.name,
-					       READ_ONCE(rcu_state.gp_seq),
+			trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
 					       TPS("fqsstart"));
 			rcu_gp_fqs(first_gp_fqs);
 			first_gp_fqs = false;
-			trace_rcu_grace_period(rcu_state.name,
-					       READ_ONCE(rcu_state.gp_seq),
+			trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
 					       TPS("fqsend"));
 			cond_resched_tasks_rcu_qs();
 			WRITE_ONCE(rcu_state.gp_activity, jiffies);
@@ -1683,8 +1696,7 @@ static void rcu_gp_fqs_loop(void)
 			cond_resched_tasks_rcu_qs();
 			WRITE_ONCE(rcu_state.gp_activity, jiffies);
 			WARN_ON(signal_pending(current));
-			trace_rcu_grace_period(rcu_state.name,
-					       READ_ONCE(rcu_state.gp_seq),
+			trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
 					       TPS("fqswaitsig"));
 			ret = 1; /* Keep old FQS timing. */
 			j = jiffies;
@@ -1701,8 +1713,9 @@ static void rcu_gp_fqs_loop(void)
  */
 static void rcu_gp_cleanup(void)
 {
-	unsigned long gp_duration;
+	int cpu;
 	bool needgp = false;
+	unsigned long gp_duration;
 	unsigned long new_gp_seq;
 	bool offloaded;
 	struct rcu_data *rdp;
@@ -1748,6 +1761,12 @@ static void rcu_gp_cleanup(void)
 			needgp = __note_gp_changes(rnp, rdp) || needgp;
 		/* smp_mb() provided by prior unlock-lock pair. */
 		needgp = rcu_future_gp_cleanup(rnp) || needgp;
+		// Reset overload indication for CPUs no longer overloaded
+		if (rcu_is_leaf_node(rnp))
+			for_each_leaf_node_cpu_mask(rnp, cpu, rnp->cbovldmask) {
+				rdp = per_cpu_ptr(&rcu_data, cpu);
+				check_cb_ovld_locked(rdp, rnp);
+			}
 		sq = rcu_nocb_gp_get(rnp);
 		raw_spin_unlock_irq_rcu_node(rnp);
 		rcu_nocb_gp_cleanup(sq);
@@ -1774,9 +1793,9 @@ static void rcu_gp_cleanup(void)
 		    rcu_segcblist_is_offloaded(&rdp->cblist);
 	if ((offloaded || !rcu_accelerate_cbs(rnp, rdp)) && needgp) {
 		WRITE_ONCE(rcu_state.gp_flags, RCU_GP_FLAG_INIT);
-		rcu_state.gp_req_activity = jiffies;
+		WRITE_ONCE(rcu_state.gp_req_activity, jiffies);
 		trace_rcu_grace_period(rcu_state.name,
-				       READ_ONCE(rcu_state.gp_seq),
+				       rcu_state.gp_seq,
 				       TPS("newreq"));
 	} else {
 		WRITE_ONCE(rcu_state.gp_flags,
@@ -1795,8 +1814,7 @@ static int __noreturn rcu_gp_kthread(void *unused)
 
 		/* Handle grace-period start. */
 		for (;;) {
-			trace_rcu_grace_period(rcu_state.name,
-					       READ_ONCE(rcu_state.gp_seq),
+			trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
 					       TPS("reqwait"));
 			rcu_state.gp_state = RCU_GP_WAIT_GPS;
 			swait_event_idle_exclusive(rcu_state.gp_wq,
@@ -1809,8 +1827,7 @@ static int __noreturn rcu_gp_kthread(void *unused)
 			cond_resched_tasks_rcu_qs();
 			WRITE_ONCE(rcu_state.gp_activity, jiffies);
 			WARN_ON(signal_pending(current));
-			trace_rcu_grace_period(rcu_state.name,
-					       READ_ONCE(rcu_state.gp_seq),
+			trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
 					       TPS("reqwaitsig"));
 		}
 
@@ -1881,7 +1898,7 @@ static void rcu_report_qs_rnp(unsigned long mask, struct rcu_node *rnp,
 		WARN_ON_ONCE(oldmask); /* Any child must be all zeroed! */
 		WARN_ON_ONCE(!rcu_is_leaf_node(rnp) &&
 			     rcu_preempt_blocked_readers_cgp(rnp));
-		rnp->qsmask &= ~mask;
+		WRITE_ONCE(rnp->qsmask, rnp->qsmask & ~mask);
 		trace_rcu_quiescent_state_report(rcu_state.name, rnp->gp_seq,
 						 mask, rnp->qsmask, rnp->level,
 						 rnp->grplo, rnp->grphi,
@@ -1904,7 +1921,7 @@ static void rcu_report_qs_rnp(unsigned long mask, struct rcu_node *rnp,
 		rnp_c = rnp;
 		rnp = rnp->parent;
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
-		oldmask = rnp_c->qsmask;
+		oldmask = READ_ONCE(rnp_c->qsmask);
 	}
 
 	/*
@@ -1987,6 +2004,8 @@ rcu_report_qs_rdp(int cpu, struct rcu_data *rdp)
 		return;
 	}
 	mask = rdp->grpmask;
+	if (rdp->cpu == smp_processor_id())
+		rdp->core_needs_qs = false;
 	if ((rnp->qsmask & mask) == 0) {
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	} else {
@@ -2052,7 +2071,7 @@ int rcutree_dying_cpu(unsigned int cpu)
 		return 0;
 
 	blkd = !!(rnp->qsmask & rdp->grpmask);
-	trace_rcu_grace_period(rcu_state.name, rnp->gp_seq,
+	trace_rcu_grace_period(rcu_state.name, READ_ONCE(rnp->gp_seq),
 			       blkd ? TPS("cpuofl") : TPS("cpuofl-bgp"));
 	return 0;
 }
@@ -2294,10 +2313,13 @@ static void force_qs_rnp(int (*f)(struct rcu_data *rdp))
 	struct rcu_data *rdp;
 	struct rcu_node *rnp;
 
+	rcu_state.cbovld = rcu_state.cbovldnext;
+	rcu_state.cbovldnext = false;
 	rcu_for_each_leaf_node(rnp) {
 		cond_resched_tasks_rcu_qs();
 		mask = 0;
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
+		rcu_state.cbovldnext |= !!rnp->cbovldmask;
 		if (rnp->qsmask == 0) {
 			if (!IS_ENABLED(CONFIG_PREEMPT_RCU) ||
 			    rcu_preempt_blocked_readers_cgp(rnp)) {
@@ -2579,11 +2601,48 @@ static void rcu_leak_callback(struct rcu_head *rhp)
 }
 
 /*
- * Helper function for call_rcu() and friends.  The cpu argument will
- * normally be -1, indicating "currently running CPU".  It may specify
- * a CPU only if that CPU is a no-CBs CPU.  Currently, only rcu_barrier()
- * is expected to specify a CPU.
+ * Check and if necessary update the leaf rcu_node structure's
+ * ->cbovldmask bit corresponding to the current CPU based on that CPU's
+ * number of queued RCU callbacks.  The caller must hold the leaf rcu_node
+ * structure's ->lock.
  */
+static void check_cb_ovld_locked(struct rcu_data *rdp, struct rcu_node *rnp)
+{
+	raw_lockdep_assert_held_rcu_node(rnp);
+	if (qovld_calc <= 0)
+		return; // Early boot and wildcard value set.
+	if (rcu_segcblist_n_cbs(&rdp->cblist) >= qovld_calc)
+		WRITE_ONCE(rnp->cbovldmask, rnp->cbovldmask | rdp->grpmask);
+	else
+		WRITE_ONCE(rnp->cbovldmask, rnp->cbovldmask & ~rdp->grpmask);
+}
+
+/*
+ * Check and if necessary update the leaf rcu_node structure's
+ * ->cbovldmask bit corresponding to the current CPU based on that CPU's
+ * number of queued RCU callbacks.  No locks need be held, but the
+ * caller must have disabled interrupts.
+ *
+ * Note that this function ignores the possibility that there are a lot
+ * of callbacks all of which have already seen the end of their respective
+ * grace periods.  This omission is due to the need for no-CBs CPUs to
+ * be holding ->nocb_lock to do this check, which is too heavy for a
+ * common-case operation.
+ */
+static void check_cb_ovld(struct rcu_data *rdp)
+{
+	struct rcu_node *const rnp = rdp->mynode;
+
+	if (qovld_calc <= 0 ||
+	    ((rcu_segcblist_n_cbs(&rdp->cblist) >= qovld_calc) ==
+	     !!(READ_ONCE(rnp->cbovldmask) & rdp->grpmask)))
+		return; // Early boot wildcard value or already set correctly.
+	raw_spin_lock_rcu_node(rnp);
+	check_cb_ovld_locked(rdp, rnp);
+	raw_spin_unlock_rcu_node(rnp);
+}
+
+/* Helper function for call_rcu() and friends.  */
 static void
 __call_rcu(struct rcu_head *head, rcu_callback_t func)
 {
@@ -2621,9 +2680,10 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func)
 			rcu_segcblist_init(&rdp->cblist);
 	}
 
+	check_cb_ovld(rdp);
 	if (rcu_nocb_try_bypass(rdp, head, &was_alldone, flags))
 		return; // Enqueued onto ->nocb_bypass, so just leave.
-	/* If we get here, rcu_nocb_try_bypass() acquired ->nocb_lock. */
+	// If no-CBs CPU gets here, rcu_nocb_try_bypass() acquired ->nocb_lock.
 	rcu_segcblist_enqueue(&rdp->cblist, head);
 	if (__is_kfree_rcu_offset((unsigned long)func))
 		trace_rcu_kfree_callback(rcu_state.name, head,
@@ -2689,22 +2749,47 @@ EXPORT_SYMBOL_GPL(call_rcu);
 #define KFREE_DRAIN_JIFFIES (HZ / 50)
 #define KFREE_N_BATCHES 2
 
+/*
+ * This macro defines how many entries the "records" array
+ * will contain. It is based on the fact that the size of
+ * kfree_rcu_bulk_data structure becomes exactly one page.
+ */
+#define KFREE_BULK_MAX_ENTR ((PAGE_SIZE / sizeof(void *)) - 3)
+
+/**
+ * struct kfree_rcu_bulk_data - single block to store kfree_rcu() pointers
+ * @nr_records: Number of active pointers in the array
+ * @records: Array of the kfree_rcu() pointers
+ * @next: Next bulk object in the block chain
+ * @head_free_debug: For debug, when CONFIG_DEBUG_OBJECTS_RCU_HEAD is set
+ */
+struct kfree_rcu_bulk_data {
+	unsigned long nr_records;
+	void *records[KFREE_BULK_MAX_ENTR];
+	struct kfree_rcu_bulk_data *next;
+	struct rcu_head *head_free_debug;
+};
+
 /**
  * struct kfree_rcu_cpu_work - single batch of kfree_rcu() requests
  * @rcu_work: Let queue_rcu_work() invoke workqueue handler after grace period
  * @head_free: List of kfree_rcu() objects waiting for a grace period
+ * @bhead_free: Bulk-List of kfree_rcu() objects waiting for a grace period
  * @krcp: Pointer to @kfree_rcu_cpu structure
  */
 
 struct kfree_rcu_cpu_work {
 	struct rcu_work rcu_work;
 	struct rcu_head *head_free;
+	struct kfree_rcu_bulk_data *bhead_free;
 	struct kfree_rcu_cpu *krcp;
 };
 
 /**
  * struct kfree_rcu_cpu - batch up kfree_rcu() requests for RCU grace period
  * @head: List of kfree_rcu() objects not yet waiting for a grace period
+ * @bhead: Bulk-List of kfree_rcu() objects not yet waiting for a grace period
+ * @bcached: Keeps at most one object for later reuse when build chain blocks
  * @krw_arr: Array of batches of kfree_rcu() objects waiting for a grace period
  * @lock: Synchronize access to this structure
  * @monitor_work: Promote @head to @head_free after KFREE_DRAIN_JIFFIES
@@ -2718,6 +2803,8 @@ struct kfree_rcu_cpu_work {
  */
 struct kfree_rcu_cpu {
 	struct rcu_head *head;
+	struct kfree_rcu_bulk_data *bhead;
+	struct kfree_rcu_bulk_data *bcached;
 	struct kfree_rcu_cpu_work krw_arr[KFREE_N_BATCHES];
 	spinlock_t lock;
 	struct delayed_work monitor_work;
@@ -2727,14 +2814,24 @@ struct kfree_rcu_cpu {
 
 static DEFINE_PER_CPU(struct kfree_rcu_cpu, krc);
 
+static __always_inline void
+debug_rcu_head_unqueue_bulk(struct rcu_head *head)
+{
+#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
+	for (; head; head = head->next)
+		debug_rcu_head_unqueue(head);
+#endif
+}
+
 /*
  * This function is invoked in workqueue context after a grace period.
- * It frees all the objects queued on ->head_free.
+ * It frees all the objects queued on ->bhead_free or ->head_free.
  */
 static void kfree_rcu_work(struct work_struct *work)
 {
 	unsigned long flags;
 	struct rcu_head *head, *next;
+	struct kfree_rcu_bulk_data *bhead, *bnext;
 	struct kfree_rcu_cpu *krcp;
 	struct kfree_rcu_cpu_work *krwp;
 
@@ -2744,22 +2841,44 @@ static void kfree_rcu_work(struct work_struct *work)
 	spin_lock_irqsave(&krcp->lock, flags);
 	head = krwp->head_free;
 	krwp->head_free = NULL;
+	bhead = krwp->bhead_free;
+	krwp->bhead_free = NULL;
 	spin_unlock_irqrestore(&krcp->lock, flags);
 
-	// List "head" is now private, so traverse locklessly.
+	/* "bhead" is now private, so traverse locklessly. */
+	for (; bhead; bhead = bnext) {
+		bnext = bhead->next;
+
+		debug_rcu_head_unqueue_bulk(bhead->head_free_debug);
+
+		rcu_lock_acquire(&rcu_callback_map);
+		trace_rcu_invoke_kfree_bulk_callback(rcu_state.name,
+			bhead->nr_records, bhead->records);
+
+		kfree_bulk(bhead->nr_records, bhead->records);
+		rcu_lock_release(&rcu_callback_map);
+
+		if (cmpxchg(&krcp->bcached, NULL, bhead))
+			free_page((unsigned long) bhead);
+
+		cond_resched_tasks_rcu_qs();
+	}
+
+	/*
+	 * Emergency case only. It can happen under low memory
+	 * condition when an allocation gets failed, so the "bulk"
+	 * path can not be temporary maintained.
+	 */
 	for (; head; head = next) {
 		unsigned long offset = (unsigned long)head->func;
 
 		next = head->next;
-		// Potentially optimize with kfree_bulk in future.
 		debug_rcu_head_unqueue(head);
 		rcu_lock_acquire(&rcu_callback_map);
 		trace_rcu_invoke_kfree_callback(rcu_state.name, head, offset);
 
-		if (!WARN_ON_ONCE(!__is_kfree_rcu_offset(offset))) {
-			/* Could be optimized with kfree_bulk() in future. */
+		if (!WARN_ON_ONCE(!__is_kfree_rcu_offset(offset)))
 			kfree((void *)head - offset);
-		}
 
 		rcu_lock_release(&rcu_callback_map);
 		cond_resched_tasks_rcu_qs();
@@ -2774,26 +2893,48 @@ static void kfree_rcu_work(struct work_struct *work)
  */
 static inline bool queue_kfree_rcu_work(struct kfree_rcu_cpu *krcp)
 {
+	struct kfree_rcu_cpu_work *krwp;
+	bool queued = false;
 	int i;
-	struct kfree_rcu_cpu_work *krwp = NULL;
 
 	lockdep_assert_held(&krcp->lock);
-	for (i = 0; i < KFREE_N_BATCHES; i++)
-		if (!krcp->krw_arr[i].head_free) {
-			krwp = &(krcp->krw_arr[i]);
-			break;
-		}
 
-	// If a previous RCU batch is in progress, we cannot immediately
-	// queue another one, so return false to tell caller to retry.
-	if (!krwp)
-		return false;
+	for (i = 0; i < KFREE_N_BATCHES; i++) {
+		krwp = &(krcp->krw_arr[i]);
 
-	krwp->head_free = krcp->head;
-	krcp->head = NULL;
-	INIT_RCU_WORK(&krwp->rcu_work, kfree_rcu_work);
-	queue_rcu_work(system_wq, &krwp->rcu_work);
-	return true;
+		/*
+		 * Try to detach bhead or head and attach it over any
+		 * available corresponding free channel. It can be that
+		 * a previous RCU batch is in progress, it means that
+		 * immediately to queue another one is not possible so
+		 * return false to tell caller to retry.
+		 */
+		if ((krcp->bhead && !krwp->bhead_free) ||
+				(krcp->head && !krwp->head_free)) {
+			/* Channel 1. */
+			if (!krwp->bhead_free) {
+				krwp->bhead_free = krcp->bhead;
+				krcp->bhead = NULL;
+			}
+
+			/* Channel 2. */
+			if (!krwp->head_free) {
+				krwp->head_free = krcp->head;
+				krcp->head = NULL;
+			}
+
+			/*
+			 * One work is per one batch, so there are two "free channels",
+			 * "bhead_free" and "head_free" the batch can handle. It can be
+			 * that the work is in the pending state when two channels have
+			 * been detached following each other, one by one.
+			 */
+			queue_rcu_work(system_wq, &krwp->rcu_work);
+			queued = true;
+		}
+	}
+
+	return queued;
 }
 
 static inline void kfree_rcu_drain_unlock(struct kfree_rcu_cpu *krcp,
@@ -2830,19 +2971,65 @@ static void kfree_rcu_monitor(struct work_struct *work)
 		spin_unlock_irqrestore(&krcp->lock, flags);
 }
 
+static inline bool
+kfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp,
+	struct rcu_head *head, rcu_callback_t func)
+{
+	struct kfree_rcu_bulk_data *bnode;
+
+	if (unlikely(!krcp->initialized))
+		return false;
+
+	lockdep_assert_held(&krcp->lock);
+
+	/* Check if a new block is required. */
+	if (!krcp->bhead ||
+			krcp->bhead->nr_records == KFREE_BULK_MAX_ENTR) {
+		bnode = xchg(&krcp->bcached, NULL);
+		if (!bnode) {
+			WARN_ON_ONCE(sizeof(struct kfree_rcu_bulk_data) > PAGE_SIZE);
+
+			bnode = (struct kfree_rcu_bulk_data *)
+				__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
+		}
+
+		/* Switch to emergency path. */
+		if (unlikely(!bnode))
+			return false;
+
+		/* Initialize the new block. */
+		bnode->nr_records = 0;
+		bnode->next = krcp->bhead;
+		bnode->head_free_debug = NULL;
+
+		/* Attach it to the head. */
+		krcp->bhead = bnode;
+	}
+
+#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
+	head->func = func;
+	head->next = krcp->bhead->head_free_debug;
+	krcp->bhead->head_free_debug = head;
+#endif
+
+	/* Finally insert. */
+	krcp->bhead->records[krcp->bhead->nr_records++] =
+		(void *) head - (unsigned long) func;
+
+	return true;
+}
+
 /*
- * Queue a request for lazy invocation of kfree() after a grace period.
+ * Queue a request for lazy invocation of kfree_bulk()/kfree() after a grace
+ * period. Please note there are two paths are maintained, one is the main one
+ * that uses kfree_bulk() interface and second one is emergency one, that is
+ * used only when the main path can not be maintained temporary, due to memory
+ * pressure.
  *
  * Each kfree_call_rcu() request is added to a batch. The batch will be drained
- * every KFREE_DRAIN_JIFFIES number of jiffies. All the objects in the batch
- * will be kfree'd in workqueue context. This allows us to:
- *
- * 1.	Batch requests together to reduce the number of grace periods during
- *	heavy kfree_rcu() load.
- *
- * 2.	It makes it possible to use kfree_bulk() on a large number of
- *	kfree_rcu() requests thus reducing cache misses and the per-object
- *	overhead of kfree().
+ * every KFREE_DRAIN_JIFFIES number of jiffies. All the objects in the batch will
+ * be free'd in workqueue context. This allows us to: batch requests together to
+ * reduce the number of grace periods during heavy kfree_rcu() load.
  */
 void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 {
@@ -2861,9 +3048,16 @@ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 			  __func__, head);
 		goto unlock_return;
 	}
-	head->func = func;
-	head->next = krcp->head;
-	krcp->head = head;
+
+	/*
+	 * Under high memory pressure GFP_NOWAIT can fail,
+	 * in that case the emergency path is maintained.
+	 */
+	if (unlikely(!kfree_call_rcu_add_ptr_to_bulk(krcp, head, func))) {
+		head->func = func;
+		head->next = krcp->head;
+		krcp->head = head;
+	}
 
 	// Set timer to drain after KFREE_DRAIN_JIFFIES.
 	if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING &&
@@ -3075,24 +3269,32 @@ static void rcu_barrier_trace(const char *s, int cpu, unsigned long done)
 /*
  * RCU callback function for rcu_barrier().  If we are last, wake
  * up the task executing rcu_barrier().
+ *
+ * Note that the value of rcu_state.barrier_sequence must be captured
+ * before the atomic_dec_and_test().  Otherwise, if this CPU is not last,
+ * other CPUs might count the value down to zero before this CPU gets
+ * around to invoking rcu_barrier_trace(), which might result in bogus
+ * data from the next instance of rcu_barrier().
  */
 static void rcu_barrier_callback(struct rcu_head *rhp)
 {
+	unsigned long __maybe_unused s = rcu_state.barrier_sequence;
+
 	if (atomic_dec_and_test(&rcu_state.barrier_cpu_count)) {
-		rcu_barrier_trace(TPS("LastCB"), -1,
-				  rcu_state.barrier_sequence);
+		rcu_barrier_trace(TPS("LastCB"), -1, s);
 		complete(&rcu_state.barrier_completion);
 	} else {
-		rcu_barrier_trace(TPS("CB"), -1, rcu_state.barrier_sequence);
+		rcu_barrier_trace(TPS("CB"), -1, s);
 	}
 }
 
 /*
  * Called with preemption disabled, and from cross-cpu IRQ context.
  */
-static void rcu_barrier_func(void *unused)
+static void rcu_barrier_func(void *cpu_in)
 {
-	struct rcu_data *rdp = raw_cpu_ptr(&rcu_data);
+	uintptr_t cpu = (uintptr_t)cpu_in;
+	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
 
 	rcu_barrier_trace(TPS("IRQ"), -1, rcu_state.barrier_sequence);
 	rdp->barrier_head.func = rcu_barrier_callback;
@@ -3119,7 +3321,7 @@ static void rcu_barrier_func(void *unused)
  */
 void rcu_barrier(void)
 {
-	int cpu;
+	uintptr_t cpu;
 	struct rcu_data *rdp;
 	unsigned long s = rcu_seq_snap(&rcu_state.barrier_sequence);
 
@@ -3142,13 +3344,14 @@ void rcu_barrier(void)
 	rcu_barrier_trace(TPS("Inc1"), -1, rcu_state.barrier_sequence);
 
 	/*
-	 * Initialize the count to one rather than to zero in order to
-	 * avoid a too-soon return to zero in case of a short grace period
-	 * (or preemption of this task).  Exclude CPU-hotplug operations
-	 * to ensure that no offline CPU has callbacks queued.
+	 * Initialize the count to two rather than to zero in order
+	 * to avoid a too-soon return to zero in case of an immediate
+	 * invocation of the just-enqueued callback (or preemption of
+	 * this task).  Exclude CPU-hotplug operations to ensure that no
+	 * offline non-offloaded CPU has callbacks queued.
 	 */
 	init_completion(&rcu_state.barrier_completion);
-	atomic_set(&rcu_state.barrier_cpu_count, 1);
+	atomic_set(&rcu_state.barrier_cpu_count, 2);
 	get_online_cpus();
 
 	/*
@@ -3158,13 +3361,23 @@ void rcu_barrier(void)
 	 */
 	for_each_possible_cpu(cpu) {
 		rdp = per_cpu_ptr(&rcu_data, cpu);
-		if (!cpu_online(cpu) &&
+		if (cpu_is_offline(cpu) &&
 		    !rcu_segcblist_is_offloaded(&rdp->cblist))
 			continue;
-		if (rcu_segcblist_n_cbs(&rdp->cblist)) {
+		if (rcu_segcblist_n_cbs(&rdp->cblist) && cpu_online(cpu)) {
 			rcu_barrier_trace(TPS("OnlineQ"), cpu,
 					  rcu_state.barrier_sequence);
-			smp_call_function_single(cpu, rcu_barrier_func, NULL, 1);
+			smp_call_function_single(cpu, rcu_barrier_func, (void *)cpu, 1);
+		} else if (rcu_segcblist_n_cbs(&rdp->cblist) &&
+			   cpu_is_offline(cpu)) {
+			rcu_barrier_trace(TPS("OfflineNoCBQ"), cpu,
+					  rcu_state.barrier_sequence);
+			local_irq_disable();
+			rcu_barrier_func((void *)cpu);
+			local_irq_enable();
+		} else if (cpu_is_offline(cpu)) {
+			rcu_barrier_trace(TPS("OfflineNoCBNoQ"), cpu,
+					  rcu_state.barrier_sequence);
 		} else {
 			rcu_barrier_trace(TPS("OnlineNQ"), cpu,
 					  rcu_state.barrier_sequence);
@@ -3176,7 +3389,7 @@ void rcu_barrier(void)
 	 * Now that we have an rcu_barrier_callback() callback on each
 	 * CPU, and thus each counted, remove the initial count.
 	 */
-	if (atomic_dec_and_test(&rcu_state.barrier_cpu_count))
+	if (atomic_sub_and_test(2, &rcu_state.barrier_cpu_count))
 		complete(&rcu_state.barrier_completion);
 
 	/* Wait for all rcu_barrier_callback() callbacks to be invoked. */
@@ -3275,12 +3488,12 @@ int rcutree_prepare_cpu(unsigned int cpu)
 	rnp = rdp->mynode;
 	raw_spin_lock_rcu_node(rnp);		/* irqs already disabled. */
 	rdp->beenonline = true;	 /* We have now been online. */
-	rdp->gp_seq = rnp->gp_seq;
-	rdp->gp_seq_needed = rnp->gp_seq;
+	rdp->gp_seq = READ_ONCE(rnp->gp_seq);
+	rdp->gp_seq_needed = rdp->gp_seq;
 	rdp->cpu_no_qs.b.norm = true;
 	rdp->core_needs_qs = false;
 	rdp->rcu_iw_pending = false;
-	rdp->rcu_iw_gp_seq = rnp->gp_seq - 1;
+	rdp->rcu_iw_gp_seq = rdp->gp_seq - 1;
 	trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("cpuonl"));
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	rcu_prepare_kthreads(cpu);
@@ -3378,7 +3591,7 @@ void rcu_cpu_starting(unsigned int cpu)
 	rnp = rdp->mynode;
 	mask = rdp->grpmask;
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
-	rnp->qsmaskinitnext |= mask;
+	WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext | mask);
 	oldmask = rnp->expmaskinitnext;
 	rnp->expmaskinitnext |= mask;
 	oldmask ^= rnp->expmaskinitnext;
@@ -3431,7 +3644,7 @@ void rcu_report_dead(unsigned int cpu)
 		rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	}
-	rnp->qsmaskinitnext &= ~mask;
+	WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext & ~mask);
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	raw_spin_unlock(&rcu_state.ofl_lock);
 
@@ -3545,7 +3758,10 @@ static int __init rcu_spawn_gp_kthread(void)
 	}
 	rnp = rcu_get_root();
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
-	rcu_state.gp_kthread = t;
+	WRITE_ONCE(rcu_state.gp_activity, jiffies);
+	WRITE_ONCE(rcu_state.gp_req_activity, jiffies);
+	// Reset .gp_activity and .gp_req_activity before setting .gp_kthread.
+	smp_store_release(&rcu_state.gp_kthread, t);  /* ^^^ */
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	wake_up_process(t);
 	rcu_spawn_nocb_kthreads();
@@ -3769,8 +3985,11 @@ static void __init kfree_rcu_batch_init(void)
 		struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
 
 		spin_lock_init(&krcp->lock);
-		for (i = 0; i < KFREE_N_BATCHES; i++)
+		for (i = 0; i < KFREE_N_BATCHES; i++) {
+			INIT_RCU_WORK(&krcp->krw_arr[i].rcu_work, kfree_rcu_work);
 			krcp->krw_arr[i].krcp = krcp;
+		}
+
 		INIT_DELAYED_WORK(&krcp->monitor_work, kfree_rcu_monitor);
 		krcp->initialized = true;
 	}
@@ -3809,6 +4028,13 @@ void __init rcu_init(void)
 	rcu_par_gp_wq = alloc_workqueue("rcu_par_gp", WQ_MEM_RECLAIM, 0);
 	WARN_ON(!rcu_par_gp_wq);
 	srcu_init();
+
+	/* Fill in default value for rcutree.qovld boot parameter. */
+	/* -After- the rcu_node ->lock fields are initialized! */
+	if (qovld < 0)
+		qovld_calc = DEFAULT_RCU_QOVLD_MULT * qhimark;
+	else
+		qovld_calc = qovld;
 }
 
 #include "tree_stall.h"

kernel/rcu/tree.h

@@ -68,6 +68,8 @@ struct rcu_node {
 				/* Online CPUs for next expedited GP. */
 				/*  Any CPU that has ever been online will */
 				/*  have its bit set. */
+	unsigned long cbovldmask;
+				/* CPUs experiencing callback overload. */
 	unsigned long ffmask;	/* Fully functional CPUs. */
 	unsigned long grpmask;	/* Mask to apply to parent qsmask. */
 				/*  Only one bit will be set in this mask. */
@@ -321,6 +323,8 @@ struct rcu_state {
 	atomic_t expedited_need_qs;		/* # CPUs left to check in. */
 	struct swait_queue_head expedited_wq;	/* Wait for check-ins. */
 	int ncpus_snap;				/* # CPUs seen last time. */
+	u8 cbovld;				/* Callback overload now? */
+	u8 cbovldnext;				/* ^        ^  next time? */
 
 	unsigned long jiffies_force_qs;		/* Time at which to invoke */
 						/*  force_quiescent_state(). */

kernel/rcu/tree_exp.h

@@ -314,7 +314,7 @@ static bool exp_funnel_lock(unsigned long s)
 				   sync_exp_work_done(s));
 			return true;
 		}
-		rnp->exp_seq_rq = s; /* Followers can wait on us. */
+		WRITE_ONCE(rnp->exp_seq_rq, s); /* Followers can wait on us. */
 		spin_unlock(&rnp->exp_lock);
 		trace_rcu_exp_funnel_lock(rcu_state.name, rnp->level,
 					  rnp->grplo, rnp->grphi, TPS("nxtlvl"));
@@ -485,6 +485,7 @@ static bool synchronize_rcu_expedited_wait_once(long tlimit)
 static void synchronize_rcu_expedited_wait(void)
 {
 	int cpu;
+	unsigned long j;
 	unsigned long jiffies_stall;
 	unsigned long jiffies_start;
 	unsigned long mask;
@@ -496,7 +497,7 @@ static void synchronize_rcu_expedited_wait(void)
 	trace_rcu_exp_grace_period(rcu_state.name, rcu_exp_gp_seq_endval(), TPS("startwait"));
 	jiffies_stall = rcu_jiffies_till_stall_check();
 	jiffies_start = jiffies;
-	if (IS_ENABLED(CONFIG_NO_HZ_FULL)) {
+	if (tick_nohz_full_enabled() && rcu_inkernel_boot_has_ended()) {
 		if (synchronize_rcu_expedited_wait_once(1))
 			return;
 		rcu_for_each_leaf_node(rnp) {
@@ -508,12 +509,16 @@ static void synchronize_rcu_expedited_wait(void)
 				tick_dep_set_cpu(cpu, TICK_DEP_BIT_RCU_EXP);
 			}
 		}
+		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 (;;) {
 		if (synchronize_rcu_expedited_wait_once(jiffies_stall))
 			return;
-		if (rcu_cpu_stall_suppress)
+		if (rcu_stall_is_suppressed())
 			continue;
 		panic_on_rcu_stall();
 		pr_err("INFO: %s detected expedited stalls on CPUs/tasks: {",
@@ -589,7 +594,7 @@ static void rcu_exp_wait_wake(unsigned long s)
 			spin_lock(&rnp->exp_lock);
 			/* Recheck, avoid hang in case someone just arrived. */
 			if (ULONG_CMP_LT(rnp->exp_seq_rq, s))
-				rnp->exp_seq_rq = s;
+				WRITE_ONCE(rnp->exp_seq_rq, s);
 			spin_unlock(&rnp->exp_lock);
 		}
 		smp_mb(); /* All above changes before wakeup. */

kernel/rcu/tree_plugin.h

@@ -56,6 +56,8 @@ static void __init rcu_bootup_announce_oddness(void)
 		pr_info("\tBoot-time adjustment of callback high-water mark to %ld.\n", qhimark);
 	if (qlowmark != DEFAULT_RCU_QLOMARK)
 		pr_info("\tBoot-time adjustment of callback low-water mark to %ld.\n", qlowmark);
+	if (qovld != DEFAULT_RCU_QOVLD)
+		pr_info("\tBoot-time adjustment of callback overload level to %ld.\n", qovld);
 	if (jiffies_till_first_fqs != ULONG_MAX)
 		pr_info("\tBoot-time adjustment of first FQS scan delay to %ld jiffies.\n", jiffies_till_first_fqs);
 	if (jiffies_till_next_fqs != ULONG_MAX)
@@ -753,7 +755,7 @@ dump_blkd_tasks(struct rcu_node *rnp, int ncheck)
 	raw_lockdep_assert_held_rcu_node(rnp);
 	pr_info("%s: grp: %d-%d level: %d ->gp_seq %ld ->completedqs %ld\n",
 		__func__, rnp->grplo, rnp->grphi, rnp->level,
-		(long)rnp->gp_seq, (long)rnp->completedqs);
+		(long)READ_ONCE(rnp->gp_seq), (long)rnp->completedqs);
 	for (rnp1 = rnp; rnp1; rnp1 = rnp1->parent)
 		pr_info("%s: %d:%d ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx\n",
 			__func__, rnp1->grplo, rnp1->grphi, rnp1->qsmask, rnp1->qsmaskinit, rnp1->qsmaskinitnext);
@@ -1032,18 +1034,18 @@ static int rcu_boost_kthread(void *arg)
 
 	trace_rcu_utilization(TPS("Start boost kthread@init"));
 	for (;;) {
-		rnp->boost_kthread_status = RCU_KTHREAD_WAITING;
+		WRITE_ONCE(rnp->boost_kthread_status, RCU_KTHREAD_WAITING);
 		trace_rcu_utilization(TPS("End boost kthread@rcu_wait"));
 		rcu_wait(rnp->boost_tasks || rnp->exp_tasks);
 		trace_rcu_utilization(TPS("Start boost kthread@rcu_wait"));
-		rnp->boost_kthread_status = RCU_KTHREAD_RUNNING;
+		WRITE_ONCE(rnp->boost_kthread_status, RCU_KTHREAD_RUNNING);
 		more2boost = rcu_boost(rnp);
 		if (more2boost)
 			spincnt++;
 		else
 			spincnt = 0;
 		if (spincnt > 10) {
-			rnp->boost_kthread_status = RCU_KTHREAD_YIELDING;
+			WRITE_ONCE(rnp->boost_kthread_status, RCU_KTHREAD_YIELDING);
 			trace_rcu_utilization(TPS("End boost kthread@rcu_yield"));
 			schedule_timeout_interruptible(2);
 			trace_rcu_utilization(TPS("Start boost kthread@rcu_yield"));
@@ -1077,12 +1079,12 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
 	    (rnp->gp_tasks != NULL &&
 	     rnp->boost_tasks == NULL &&
 	     rnp->qsmask == 0 &&
-	     ULONG_CMP_GE(jiffies, rnp->boost_time))) {
+	     (ULONG_CMP_GE(jiffies, rnp->boost_time) || rcu_state.cbovld))) {
 		if (rnp->exp_tasks == NULL)
 			rnp->boost_tasks = rnp->gp_tasks;
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		rcu_wake_cond(rnp->boost_kthread_task,
-			      rnp->boost_kthread_status);
+			      READ_ONCE(rnp->boost_kthread_status));
 	} else {
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	}
@@ -1486,6 +1488,7 @@ module_param(nocb_nobypass_lim_per_jiffy, int, 0);
  * flag the contention.
  */
 static void rcu_nocb_bypass_lock(struct rcu_data *rdp)
+	__acquires(&rdp->nocb_bypass_lock)
 {
 	lockdep_assert_irqs_disabled();
 	if (raw_spin_trylock(&rdp->nocb_bypass_lock))
@@ -1529,6 +1532,7 @@ static bool rcu_nocb_bypass_trylock(struct rcu_data *rdp)
  * Release the specified rcu_data structure's ->nocb_bypass_lock.
  */
 static void rcu_nocb_bypass_unlock(struct rcu_data *rdp)
+	__releases(&rdp->nocb_bypass_lock)
 {
 	lockdep_assert_irqs_disabled();
 	raw_spin_unlock(&rdp->nocb_bypass_lock);
@@ -1577,8 +1581,7 @@ static void rcu_nocb_unlock_irqrestore(struct rcu_data *rdp,
 static void rcu_lockdep_assert_cblist_protected(struct rcu_data *rdp)
 {
 	lockdep_assert_irqs_disabled();
-	if (rcu_segcblist_is_offloaded(&rdp->cblist) &&
-	    cpu_online(rdp->cpu))
+	if (rcu_segcblist_is_offloaded(&rdp->cblist))
 		lockdep_assert_held(&rdp->nocb_lock);
 }
 
@@ -1930,6 +1933,7 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
 	struct rcu_data *rdp;
 	struct rcu_node *rnp;
 	unsigned long wait_gp_seq = 0; // Suppress "use uninitialized" warning.
+	bool wasempty = false;
 
 	/*
 	 * Each pass through the following loop checks for CBs and for the
@@ -1969,10 +1973,13 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
 		     rcu_seq_done(&rnp->gp_seq, cur_gp_seq))) {
 			raw_spin_lock_rcu_node(rnp); /* irqs disabled. */
 			needwake_gp = rcu_advance_cbs(rnp, rdp);
+			wasempty = rcu_segcblist_restempty(&rdp->cblist,
+							   RCU_NEXT_READY_TAIL);
 			raw_spin_unlock_rcu_node(rnp); /* irqs disabled. */
 		}
 		// Need to wait on some grace period?
-		WARN_ON_ONCE(!rcu_segcblist_restempty(&rdp->cblist,
+		WARN_ON_ONCE(wasempty &&
+			     !rcu_segcblist_restempty(&rdp->cblist,
 						      RCU_NEXT_READY_TAIL));
 		if (rcu_segcblist_nextgp(&rdp->cblist, &cur_gp_seq)) {
 			if (!needwait_gp ||

kernel/rcu/tree_stall.h

@@ -102,7 +102,7 @@ static void record_gp_stall_check_time(void)
 	unsigned long j = jiffies;
 	unsigned long j1;
 
-	rcu_state.gp_start = j;
+	WRITE_ONCE(rcu_state.gp_start, j);
 	j1 = rcu_jiffies_till_stall_check();
 	/* Record ->gp_start before ->jiffies_stall. */
 	smp_store_release(&rcu_state.jiffies_stall, j + j1); /* ^^^ */
@@ -383,7 +383,7 @@ static void print_other_cpu_stall(unsigned long gp_seq)
 
 	/* Kick and suppress, if so configured. */
 	rcu_stall_kick_kthreads();
-	if (rcu_cpu_stall_suppress)
+	if (rcu_stall_is_suppressed())
 		return;
 
 	/*
@@ -452,7 +452,7 @@ static void print_cpu_stall(void)
 
 	/* Kick and suppress, if so configured. */
 	rcu_stall_kick_kthreads();
-	if (rcu_cpu_stall_suppress)
+	if (rcu_stall_is_suppressed())
 		return;
 
 	/*
@@ -504,7 +504,7 @@ static void check_cpu_stall(struct rcu_data *rdp)
 	unsigned long js;
 	struct rcu_node *rnp;
 
-	if ((rcu_cpu_stall_suppress && !rcu_kick_kthreads) ||
+	if ((rcu_stall_is_suppressed() && !rcu_kick_kthreads) ||
 	    !rcu_gp_in_progress())
 		return;
 	rcu_stall_kick_kthreads();
@@ -578,6 +578,7 @@ void show_rcu_gp_kthreads(void)
 	unsigned long jw;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp;
+	struct task_struct *t = READ_ONCE(rcu_state.gp_kthread);
 
 	j = jiffies;
 	ja = j - READ_ONCE(rcu_state.gp_activity);
@@ -585,28 +586,28 @@ void show_rcu_gp_kthreads(void)
 	jw = j - READ_ONCE(rcu_state.gp_wake_time);
 	pr_info("%s: wait state: %s(%d) ->state: %#lx delta ->gp_activity %lu ->gp_req_activity %lu ->gp_wake_time %lu ->gp_wake_seq %ld ->gp_seq %ld ->gp_seq_needed %ld ->gp_flags %#x\n",
 		rcu_state.name, gp_state_getname(rcu_state.gp_state),
-		rcu_state.gp_state,
-		rcu_state.gp_kthread ? rcu_state.gp_kthread->state : 0x1ffffL,
+		rcu_state.gp_state, t ? t->state : 0x1ffffL,
 		ja, jr, jw, (long)READ_ONCE(rcu_state.gp_wake_seq),
 		(long)READ_ONCE(rcu_state.gp_seq),
 		(long)READ_ONCE(rcu_get_root()->gp_seq_needed),
 		READ_ONCE(rcu_state.gp_flags));
 	rcu_for_each_node_breadth_first(rnp) {
-		if (ULONG_CMP_GE(rcu_state.gp_seq, rnp->gp_seq_needed))
+		if (ULONG_CMP_GE(READ_ONCE(rcu_state.gp_seq),
+				 READ_ONCE(rnp->gp_seq_needed)))
 			continue;
 		pr_info("\trcu_node %d:%d ->gp_seq %ld ->gp_seq_needed %ld\n",
-			rnp->grplo, rnp->grphi, (long)rnp->gp_seq,
-			(long)rnp->gp_seq_needed);
+			rnp->grplo, rnp->grphi, (long)READ_ONCE(rnp->gp_seq),
+			(long)READ_ONCE(rnp->gp_seq_needed));
 		if (!rcu_is_leaf_node(rnp))
 			continue;
 		for_each_leaf_node_possible_cpu(rnp, cpu) {
 			rdp = per_cpu_ptr(&rcu_data, cpu);
-			if (rdp->gpwrap ||
-			    ULONG_CMP_GE(rcu_state.gp_seq,
-					 rdp->gp_seq_needed))
+			if (READ_ONCE(rdp->gpwrap) ||
+			    ULONG_CMP_GE(READ_ONCE(rcu_state.gp_seq),
+					 READ_ONCE(rdp->gp_seq_needed)))
 				continue;
 			pr_info("\tcpu %d ->gp_seq_needed %ld\n",
-				cpu, (long)rdp->gp_seq_needed);
+				cpu, (long)READ_ONCE(rdp->gp_seq_needed));
 		}
 	}
 	for_each_possible_cpu(cpu) {
@@ -631,7 +632,9 @@ static void rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp,
 	static atomic_t warned = ATOMIC_INIT(0);
 
 	if (!IS_ENABLED(CONFIG_PROVE_RCU) || rcu_gp_in_progress() ||
-	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed))
+	    ULONG_CMP_GE(READ_ONCE(rnp_root->gp_seq),
+			 READ_ONCE(rnp_root->gp_seq_needed)) ||
+	    !smp_load_acquire(&rcu_state.gp_kthread)) // Get stable kthread.
 		return;
 	j = jiffies; /* Expensive access, and in common case don't get here. */
 	if (time_before(j, READ_ONCE(rcu_state.gp_req_activity) + gpssdelay) ||
@@ -642,7 +645,8 @@ static void rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp,
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	j = jiffies;
 	if (rcu_gp_in_progress() ||
-	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
+	    ULONG_CMP_GE(READ_ONCE(rnp_root->gp_seq),
+			 READ_ONCE(rnp_root->gp_seq_needed)) ||
 	    time_before(j, READ_ONCE(rcu_state.gp_req_activity) + gpssdelay) ||
 	    time_before(j, READ_ONCE(rcu_state.gp_activity) + gpssdelay) ||
 	    atomic_read(&warned)) {
@@ -655,9 +659,10 @@ static void rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp,
 		raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */
 	j = jiffies;
 	if (rcu_gp_in_progress() ||
-	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
-	    time_before(j, rcu_state.gp_req_activity + gpssdelay) ||
-	    time_before(j, rcu_state.gp_activity + gpssdelay) ||
+	    ULONG_CMP_GE(READ_ONCE(rnp_root->gp_seq),
+			 READ_ONCE(rnp_root->gp_seq_needed)) ||
+	    time_before(j, READ_ONCE(rcu_state.gp_req_activity) + gpssdelay) ||
+	    time_before(j, READ_ONCE(rcu_state.gp_activity) + gpssdelay) ||
 	    atomic_xchg(&warned, 1)) {
 		if (rnp_root != rnp)
 			/* irqs remain disabled. */

kernel/rcu/update.c

@@ -183,6 +183,8 @@ void rcu_unexpedite_gp(void)
 }
 EXPORT_SYMBOL_GPL(rcu_unexpedite_gp);
 
+static bool rcu_boot_ended __read_mostly;
+
 /*
  * Inform RCU of the end of the in-kernel boot sequence.
  */
@@ -191,8 +193,18 @@ void rcu_end_inkernel_boot(void)
 	rcu_unexpedite_gp();
 	if (rcu_normal_after_boot)
 		WRITE_ONCE(rcu_normal, 1);
+	rcu_boot_ended = 1;
 }
 
+/*
+ * Let rcutorture know when it is OK to turn it up to eleven.
+ */
+bool rcu_inkernel_boot_has_ended(void)
+{
+	return rcu_boot_ended;
+}
+EXPORT_SYMBOL_GPL(rcu_inkernel_boot_has_ended);
+
 #endif /* #ifndef CONFIG_TINY_RCU */
 
 /*
@@ -464,13 +476,19 @@ EXPORT_SYMBOL_GPL(rcutorture_sched_setaffinity);
 #ifdef CONFIG_RCU_STALL_COMMON
 int rcu_cpu_stall_ftrace_dump __read_mostly;
 module_param(rcu_cpu_stall_ftrace_dump, int, 0644);
-int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */
+int rcu_cpu_stall_suppress __read_mostly; // !0 = suppress stall warnings.
 EXPORT_SYMBOL_GPL(rcu_cpu_stall_suppress);
 module_param(rcu_cpu_stall_suppress, int, 0644);
 int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT;
 module_param(rcu_cpu_stall_timeout, int, 0644);
 #endif /* #ifdef CONFIG_RCU_STALL_COMMON */
 
+// Suppress boot-time RCU CPU stall warnings and rcutorture writer stall
+// warnings.  Also used by rcutorture even if stall warnings are excluded.
+int rcu_cpu_stall_suppress_at_boot __read_mostly; // !0 = suppress boot stalls.
+EXPORT_SYMBOL_GPL(rcu_cpu_stall_suppress_at_boot);
+module_param(rcu_cpu_stall_suppress_at_boot, int, 0444);
+
 #ifdef CONFIG_TASKS_RCU
 
 /*
@@ -528,7 +546,7 @@ void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func)
 	rhp->func = func;
 	raw_spin_lock_irqsave(&rcu_tasks_cbs_lock, flags);
 	needwake = !rcu_tasks_cbs_head;
-	*rcu_tasks_cbs_tail = rhp;
+	WRITE_ONCE(*rcu_tasks_cbs_tail, rhp);
 	rcu_tasks_cbs_tail = &rhp->next;
 	raw_spin_unlock_irqrestore(&rcu_tasks_cbs_lock, flags);
 	/* We can't create the thread unless interrupts are enabled. */
@@ -658,7 +676,7 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 		/* If there were none, wait a bit and start over. */
 		if (!list) {
 			wait_event_interruptible(rcu_tasks_cbs_wq,
-						 rcu_tasks_cbs_head);
+						 READ_ONCE(rcu_tasks_cbs_head));
 			if (!rcu_tasks_cbs_head) {
 				WARN_ON(signal_pending(current));
 				schedule_timeout_interruptible(HZ/10);
@@ -801,7 +819,7 @@ static int __init rcu_spawn_tasks_kthread(void)
 core_initcall(rcu_spawn_tasks_kthread);
 
 /* Do the srcu_read_lock() for the above synchronize_srcu().  */
-void exit_tasks_rcu_start(void)
+void exit_tasks_rcu_start(void) __acquires(&tasks_rcu_exit_srcu)
 {
 	preempt_disable();
 	current->rcu_tasks_idx = __srcu_read_lock(&tasks_rcu_exit_srcu);
@@ -809,7 +827,7 @@ void exit_tasks_rcu_start(void)
 }
 
 /* Do the srcu_read_unlock() for the above synchronize_srcu().  */
-void exit_tasks_rcu_finish(void)
+void exit_tasks_rcu_finish(void) __releases(&tasks_rcu_exit_srcu)
 {
 	preempt_disable();
 	__srcu_read_unlock(&tasks_rcu_exit_srcu, current->rcu_tasks_idx);

kernel/time/timer.c

@@ -944,6 +944,7 @@ static struct timer_base *lock_timer_base(struct timer_list *timer,
 
 #define MOD_TIMER_PENDING_ONLY		0x01
 #define MOD_TIMER_REDUCE		0x02
+#define MOD_TIMER_NOTPENDING		0x04
 
 static inline int
 __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int options)
@@ -960,7 +961,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option
 	 * the timer is re-modified to have the same timeout or ends up in the
 	 * same array bucket then just return:
 	 */
-	if (timer_pending(timer)) {
+	if (!(options & MOD_TIMER_NOTPENDING) && timer_pending(timer)) {
 		/*
 		 * The downside of this optimization is that it can result in
 		 * larger granularity than you would get from adding a new
@@ -1133,7 +1134,7 @@ EXPORT_SYMBOL(timer_reduce);
 void add_timer(struct timer_list *timer)
 {
 	BUG_ON(timer_pending(timer));
-	mod_timer(timer, timer->expires);
+	__mod_timer(timer, timer->expires, MOD_TIMER_NOTPENDING);
 }
 EXPORT_SYMBOL(add_timer);
 
@@ -1891,7 +1892,7 @@ signed long __sched schedule_timeout(signed long timeout)
 
 	timer.task = current;
 	timer_setup_on_stack(&timer.timer, process_timeout, 0);
-	__mod_timer(&timer.timer, expire, 0);
+	__mod_timer(&timer.timer, expire, MOD_TIMER_NOTPENDING);
 	schedule();
 	del_singleshot_timer_sync(&timer.timer);
 

kernel/torture.c

@@ -42,6 +42,9 @@
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com>");
 
+static bool disable_onoff_at_boot;
+module_param(disable_onoff_at_boot, bool, 0444);
+
 static char *torture_type;
 static int verbose;
 
@@ -84,6 +87,7 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes,
 {
 	unsigned long delta;
 	int ret;
+	char *s;
 	unsigned long starttime;
 
 	if (!cpu_online(cpu) || !cpu_is_hotpluggable(cpu))
@@ -99,10 +103,16 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes,
 	(*n_offl_attempts)++;
 	ret = cpu_down(cpu);
 	if (ret) {
+		s = "";
+		if (!rcu_inkernel_boot_has_ended() && ret == -EBUSY) {
+			// PCI probe frequently disables hotplug during boot.
+			(*n_offl_attempts)--;
+			s = " (-EBUSY forgiven during boot)";
+		}
 		if (verbose)
 			pr_alert("%s" TORTURE_FLAG
-				 "torture_onoff task: offline %d failed: errno %d\n",
-				 torture_type, cpu, ret);
+				 "torture_onoff task: offline %d failed%s: errno %d\n",
+				 torture_type, cpu, s, ret);
 	} else {
 		if (verbose > 1)
 			pr_alert("%s" TORTURE_FLAG
@@ -137,6 +147,7 @@ bool torture_online(int cpu, long *n_onl_attempts, long *n_onl_successes,
 {
 	unsigned long delta;
 	int ret;
+	char *s;
 	unsigned long starttime;
 
 	if (cpu_online(cpu) || !cpu_is_hotpluggable(cpu))
@@ -150,10 +161,16 @@ bool torture_online(int cpu, long *n_onl_attempts, long *n_onl_successes,
 	(*n_onl_attempts)++;
 	ret = cpu_up(cpu);
 	if (ret) {
+		s = "";
+		if (!rcu_inkernel_boot_has_ended() && ret == -EBUSY) {
+			// PCI probe frequently disables hotplug during boot.
+			(*n_onl_attempts)--;
+			s = " (-EBUSY forgiven during boot)";
+		}
 		if (verbose)
 			pr_alert("%s" TORTURE_FLAG
-				 "torture_onoff task: online %d failed: errno %d\n",
-				 torture_type, cpu, ret);
+				 "torture_onoff task: online %d failed%s: errno %d\n",
+				 torture_type, cpu, s, ret);
 	} else {
 		if (verbose > 1)
 			pr_alert("%s" TORTURE_FLAG
@@ -215,6 +232,10 @@ torture_onoff(void *arg)
 		VERBOSE_TOROUT_STRING("torture_onoff end holdoff");
 	}
 	while (!torture_must_stop()) {
+		if (disable_onoff_at_boot && !rcu_inkernel_boot_has_ended()) {
+			schedule_timeout_interruptible(HZ / 10);
+			continue;
+		}
 		cpu = (torture_random(&rand) >> 4) % (maxcpu + 1);
 		if (!torture_offline(cpu,
 				     &n_offline_attempts, &n_offline_successes,

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

@@ -12,7 +12,7 @@
 # Returns 1 if the specified boot-parameter string tells rcutorture to
 # test CPU-hotplug operations.
 bootparam_hotplug_cpu () {
-	echo "$1" | grep -q "rcutorture\.onoff_"
+	echo "$1" | grep -q "torture\.onoff_"
 }
 
 # checkarg --argname argtype $# arg mustmatch cannotmatch

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

@@ -20,7 +20,9 @@
 rundir="${1}"
 if test -z "$rundir" -o ! -d "$rundir"
 then
+	echo Directory "$rundir" not found.
 	echo Usage: $0 directory
+	exit 1
 fi
 editor=${EDITOR-vi}
 

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

@@ -13,6 +13,9 @@
 #
 # Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
+T=/tmp/kvm-recheck.sh.$$
+trap 'rm -f $T' 0 2
+
 PATH=`pwd`/tools/testing/selftests/rcutorture/bin:$PATH; export PATH
 . functions.sh
 for rd in "$@"
@@ -68,4 +71,16 @@ do
 		fi
 	done
 done
-EDITOR=echo kvm-find-errors.sh "${@: -1}" > /dev/null 2>&1
+EDITOR=echo kvm-find-errors.sh "${@: -1}" > $T 2>&1
+ret=$?
+builderrors="`tr ' ' '\012' < $T | grep -c '/Make.out.diags'`"
+if test "$builderrors" -gt 0
+then
+	echo $builderrors runs with build errors.
+fi
+runerrors="`tr ' ' '\012' < $T | grep -c '/console.log.diags'`"
+if test "$runerrors" -gt 0
+then
+	echo $runerrors runs with runtime errors.
+fi
+exit $ret

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

@@ -39,7 +39,7 @@ TORTURE_TRUST_MAKE=""
 resdir=""
 configs=""
 cpus=0
-ds=`date +%Y.%m.%d-%H:%M:%S`
+ds=`date +%Y.%m.%d-%H.%M.%S`
 jitter="-1"
 
 usage () {

tools/testing/selftests/rcutorture/configs/rcu/CFcommon

@@ -3,3 +3,5 @@ CONFIG_PRINTK_TIME=y
 CONFIG_HYPERVISOR_GUEST=y
 CONFIG_PARAVIRT=y
 CONFIG_KVM_GUEST=y
+CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC=n
+CONFIG_KCSAN_REPORT_VALUE_CHANGE_ONLY=n

tools/testing/selftests/rcutorture/configs/rcu/TREE10

+CONFIG_SMP=y
+CONFIG_NR_CPUS=100
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_HZ_PERIODIC=n
+CONFIG_NO_HZ_IDLE=y
+CONFIG_NO_HZ_FULL=n
+CONFIG_RCU_FAST_NO_HZ=n
+CONFIG_RCU_TRACE=n
+CONFIG_RCU_NOCB_CPU=n
+CONFIG_DEBUG_LOCK_ALLOC=n
+CONFIG_PROVE_LOCKING=n
+#CHECK#CONFIG_PROVE_RCU=n
+CONFIG_DEBUG_OBJECTS=n
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_RCU_EXPERT=n