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 changes in this cycle were:

   - Make kfree_rcu() use kfree_bulk() for added performance

   - RCU updates

   - Callback-overload handling updates

   - Tasks-RCU KCSAN and sparse updates

   - Locking torture test and RCU torture test updates

   - Documentation updates

   - Miscellaneous fixes"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (74 commits)
  rcu: Make rcu_barrier() account for offline no-CBs CPUs
  rcu: Mark rcu_state.gp_seq to detect concurrent writes
  Documentation/memory-barriers: Fix typos
  doc: Add rcutorture scripting to torture.txt
  doc/RCU/rcu: Use https instead of http if possible
  doc/RCU/rcu: Use absolute paths for non-rst files
  doc/RCU/rcu: Use ':ref:' for links to other docs
  doc/RCU/listRCU: Update example function name
  doc/RCU/listRCU: Fix typos in a example code snippets
  doc/RCU/Design: Remove remaining HTML tags in ReST files
  doc: Add some more RCU list patterns in the kernel
  rcutorture: Set KCSAN Kconfig options to detect more data races
  rcutorture: Manually clean up after rcu_barrier() failure
  rcutorture: Make rcu_torture_barrier_cbs() post from corresponding CPU
  rcuperf: Measure memory footprint during kfree_rcu() test
  rcutorture: Annotation lockless accesses to rcu_torture_current
  rcutorture: Add READ_ONCE() to rcu_torture_count and rcu_torture_batch
  rcutorture: Fix stray access to rcu_fwd_cb_nodelay
  rcutorture: Fix rcu_torture_one_read()/rcu_torture_writer() data race
  rcutorture: Make kvm-find-errors.sh abort on bad directory
  ...

16 files changed, 550 insertions, 196 deletions

diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index 99475a66c94f..5efbfc68ce99 100644
--- a/kernel/locking/locktorture.c
+++ b/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);
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 851bbb10819d..c9f090d64f00 100644
--- a/kernel/locking/rtmutex.c
+++ b/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)
diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile
index 82d5fba48b2f..f91f2c2cf138 100644
--- a/kernel/rcu/Makefile
+++ b/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
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 05f936ed167a..00ddc92c5774 100644
--- a/kernel/rcu/rcu.h
+++ b/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)))
 
diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c
index 5f4fd3b8777c..9a0f66133b4b 100644
--- a/kernel/rcu/rcu_segcblist.c
+++ b/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;
 }
 
 /*
diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index da94b89cd531..a4a8d097d84d 100644
--- a/kernel/rcu/rcuperf.c
+++ b/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);
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 1aeecc165b21..5453bd557f43 100644
--- a/kernel/rcu/rcutorture.c
+++ b/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++;
 		}
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 657e6a7d1c03..0c71505f0e19 100644
--- a/kernel/rcu/srcutree.c
+++ b/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) {
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index d91c9156fab2..550193a9ce76 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1,12 +1,12 @@
 // 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)