Merge tag 'rcu.6.4.april5.2023.3' of git://git.kernel.org/pub/scm/linux/kernel/git/jfern/linux

Pull RCU updates from Joel Fernandes:

 - Updates and additions to MAINTAINERS files, with Boqun being added to
   the RCU entry and Zqiang being added as an RCU reviewer.

   I have also transitioned from reviewer to maintainer; however, Paul
   will be taking over sending RCU pull-requests for the next merge
   window.

 - Resolution of hotplug warning in nohz code, achieved by fixing
   cpu_is_hotpluggable() through interaction with the nohz subsystem.

   Tick dependency modifications by Zqiang, focusing on fixing usage of
   the TICK_DEP_BIT_RCU_EXP bitmask.

 - Avoid needless calls to the rcu-lazy shrinker for CONFIG_RCU_LAZY=n
   kernels, fixed by Zqiang.

 - Improvements to rcu-tasks stall reporting by Neeraj.

 - Initial renaming of k[v]free_rcu() to k[v]free_rcu_mightsleep() for
   increased robustness, affecting several components like mac802154,
   drbd, vmw_vmci, tracing, and more.

   A report by Eric Dumazet showed that the API could be unknowingly
   used in an atomic context, so we'd rather make sure they know what
   they're asking for by being explicit:

      https://lore.kernel.org/all/20221202052847.2623997-1-edumazet@google.com/

 - Documentation updates, including corrections to spelling,
   clarifications in comments, and improvements to the srcu_size_state
   comments.

 - Better srcu_struct cache locality for readers, by adjusting the size
   of srcu_struct in support of SRCU usage by Christoph Hellwig.

 - Teach lockdep to detect deadlocks between srcu_read_lock() vs
   synchronize_srcu() contributed by Boqun.

   Previously lockdep could not detect such deadlocks, now it can.

 - Integration of rcutorture and rcu-related tools, targeted for v6.4
   from Boqun's tree, featuring new SRCU deadlock scenarios, test_nmis
   module parameter, and more

 - Miscellaneous changes, various code cleanups and comment improvements

* tag 'rcu.6.4.april5.2023.3' of git://git.kernel.org/pub/scm/linux/kernel/git/jfern/linux: (71 commits)
  checkpatch: Error out if deprecated RCU API used
  mac802154: Rename kfree_rcu() to kvfree_rcu_mightsleep()
  rcuscale: Rename kfree_rcu() to kfree_rcu_mightsleep()
  ext4/super: Rename kfree_rcu() to kfree_rcu_mightsleep()
  net/mlx5: Rename kfree_rcu() to kfree_rcu_mightsleep()
  net/sysctl: Rename kvfree_rcu() to kvfree_rcu_mightsleep()
  lib/test_vmalloc.c: Rename kvfree_rcu() to kvfree_rcu_mightsleep()
  tracing: Rename kvfree_rcu() to kvfree_rcu_mightsleep()
  misc: vmw_vmci: Rename kvfree_rcu() to kvfree_rcu_mightsleep()
  drbd: Rename kvfree_rcu() to kvfree_rcu_mightsleep()
  rcu: Protect rcu_print_task_exp_stall() ->exp_tasks access
  rcu: Avoid stack overflow due to __rcu_irq_enter_check_tick() being kprobe-ed
  rcu-tasks: Report stalls during synchronize_srcu() in rcu_tasks_postscan()
  rcu: Permit start_poll_synchronize_rcu_expedited() to be invoked early
  rcu: Remove never-set needwake assignment from rcu_report_qs_rdp()
  rcu: Register rcu-lazy shrinker only for CONFIG_RCU_LAZY=y kernels
  rcu: Fix missing TICK_DEP_MASK_RCU_EXP dependency check
  rcu: Fix set/clear TICK_DEP_BIT_RCU_EXP bitmask race
  rcu/trace: use strscpy() to instead of strncpy()
  tick/nohz: Fix cpu_is_hotpluggable() by checking with nohz subsystem
  ...

11 files changed, 573 insertions, 229 deletions

diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig
index ab62074174c32..9071182b1284b 100644
--- a/kernel/rcu/Kconfig
+++ b/kernel/rcu/Kconfig
@@ -53,9 +53,6 @@ config RCU_EXPERT
 
 	  Say N if you are unsure.
 
-config SRCU
-	def_bool y
-
 config TINY_SRCU
 	bool
 	default y if TINY_RCU
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 115616ac3bfa6..4a1b9622598be 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -14,6 +14,43 @@
 
 /*
  * Grace-period counter management.
+ *
+ * The two least significant bits contain the control flags.
+ * The most significant bits contain the grace-period sequence counter.
+ *
+ * When both control flags are zero, no grace period is in progress.
+ * When either bit is non-zero, a grace period has started and is in
+ * progress. When the grace period completes, the control flags are reset
+ * to 0 and the grace-period sequence counter is incremented.
+ *
+ * However some specific RCU usages make use of custom values.
+ *
+ * SRCU special control values:
+ *
+ *	SRCU_SNP_INIT_SEQ	:	Invalid/init value set when SRCU node
+ *					is initialized.
+ *
+ *	SRCU_STATE_IDLE		:	No SRCU gp is in progress
+ *
+ *	SRCU_STATE_SCAN1	:	State set by rcu_seq_start(). Indicates
+ *					we are scanning the readers on the slot
+ *					defined as inactive (there might well
+ *					be pending readers that will use that
+ *					index, but their number is bounded).
+ *
+ *	SRCU_STATE_SCAN2	:	State set manually via rcu_seq_set_state()
+ *					Indicates we are flipping the readers
+ *					index and then scanning the readers on the
+ *					slot newly designated as inactive (again,
+ *					the number of pending readers that will use
+ *					this inactive index is bounded).
+ *
+ * RCU polled GP special control value:
+ *
+ *	RCU_GET_STATE_COMPLETED :	State value indicating an already-completed
+ *					polled GP has completed.  This value covers
+ *					both the state and the counter of the
+ *					grace-period sequence number.
  */
 
 #define RCU_SEQ_CTR_SHIFT	2
@@ -341,11 +378,13 @@ extern void rcu_init_geometry(void);
  * specified state structure (for SRCU) or the only rcu_state structure
  * (for RCU).
  */
-#define srcu_for_each_node_breadth_first(sp, rnp) \
+#define _rcu_for_each_node_breadth_first(sp, rnp) \
 	for ((rnp) = &(sp)->node[0]; \
 	     (rnp) < &(sp)->node[rcu_num_nodes]; (rnp)++)
 #define rcu_for_each_node_breadth_first(rnp) \
-	srcu_for_each_node_breadth_first(&rcu_state, rnp)
+	_rcu_for_each_node_breadth_first(&rcu_state, rnp)
+#define srcu_for_each_node_breadth_first(ssp, rnp) \
+	_rcu_for_each_node_breadth_first(ssp->srcu_sup, rnp)
 
 /*
  * Scan the leaves of the rcu_node hierarchy for the rcu_state structure.
diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c
index 91fb5905a008f..e82ec9f9a5d80 100644
--- a/kernel/rcu/rcuscale.c
+++ b/kernel/rcu/rcuscale.c
@@ -631,8 +631,7 @@ static int compute_real(int n)
 static int
 rcu_scale_shutdown(void *arg)
 {
-	wait_event(shutdown_wq,
-		   atomic_read(&n_rcu_scale_writer_finished) >= nrealwriters);
+	wait_event_idle(shutdown_wq, atomic_read(&n_rcu_scale_writer_finished) >= nrealwriters);
 	smp_mb(); /* Wake before output. */
 	rcu_scale_cleanup();
 	kernel_power_off();
@@ -716,7 +715,7 @@ kfree_scale_thread(void *arg)
 			// is tested.
 			if ((kfree_rcu_test_single && !kfree_rcu_test_double) ||
 					(kfree_rcu_test_both && torture_random(&tr) & 0x800))
-				kfree_rcu(alloc_ptr);
+				kfree_rcu_mightsleep(alloc_ptr);
 			else
 				kfree_rcu(alloc_ptr, rh);
 		}
@@ -771,8 +770,8 @@ kfree_scale_cleanup(void)
 static int
 kfree_scale_shutdown(void *arg)
 {
-	wait_event(shutdown_wq,
-		   atomic_read(&n_kfree_scale_thread_ended) >= kfree_nrealthreads);
+	wait_event_idle(shutdown_wq,
+			atomic_read(&n_kfree_scale_thread_ended) >= kfree_nrealthreads);
 
 	smp_mb(); /* Wake before output. */
 
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 8e6c023212cb3..147551c23baf0 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -119,7 +119,9 @@ torture_param(int, stutter, 5, "Number of seconds to run/halt test");
 torture_param(int, test_boost, 1, "Test RCU prio boost: 0=no, 1=maybe, 2=yes.");
 torture_param(int, test_boost_duration, 4, "Duration of each boost test, seconds.");
 torture_param(int, test_boost_interval, 7, "Interval between boost tests, seconds.");
+torture_param(int, test_nmis, 0, "End-test NMI tests, 0 to disable.");
 torture_param(bool, test_no_idle_hz, true, "Test support for tickless idle CPUs");
+torture_param(int, test_srcu_lockdep, 0, "Test specified SRCU deadlock scenario.");
 torture_param(int, verbose, 1, "Enable verbose debugging printk()s");
 
 static char *torture_type = "rcu";
@@ -179,7 +181,6 @@ static atomic_t n_rcu_torture_mbchk_tries;
 static atomic_t n_rcu_torture_error;
 static long n_rcu_torture_barrier_error;
 static long n_rcu_torture_boost_ktrerror;
-static long n_rcu_torture_boost_rterror;
 static long n_rcu_torture_boost_failure;
 static long n_rcu_torture_boosts;
 static atomic_long_t n_rcu_torture_timers;
@@ -2194,12 +2195,11 @@ rcu_torture_stats_print(void)
 		atomic_read(&n_rcu_torture_alloc),
 		atomic_read(&n_rcu_torture_alloc_fail),
 		atomic_read(&n_rcu_torture_free));
-	pr_cont("rtmbe: %d rtmbkf: %d/%d rtbe: %ld rtbke: %ld rtbre: %ld ",
+	pr_cont("rtmbe: %d rtmbkf: %d/%d rtbe: %ld rtbke: %ld ",
 		atomic_read(&n_rcu_torture_mberror),
 		atomic_read(&n_rcu_torture_mbchk_fail), atomic_read(&n_rcu_torture_mbchk_tries),
 		n_rcu_torture_barrier_error,
-		n_rcu_torture_boost_ktrerror,
-		n_rcu_torture_boost_rterror);
+		n_rcu_torture_boost_ktrerror);
 	pr_cont("rtbf: %ld rtb: %ld nt: %ld ",
 		n_rcu_torture_boost_failure,
 		n_rcu_torture_boosts,
@@ -2217,15 +2217,13 @@ rcu_torture_stats_print(void)
 	if (atomic_read(&n_rcu_torture_mberror) ||
 	    atomic_read(&n_rcu_torture_mbchk_fail) ||
 	    n_rcu_torture_barrier_error || n_rcu_torture_boost_ktrerror ||
-	    n_rcu_torture_boost_rterror || n_rcu_torture_boost_failure ||
-	    i > 1) {
+	    n_rcu_torture_boost_failure || i > 1) {
 		pr_cont("%s", "!!! ");
 		atomic_inc(&n_rcu_torture_error);
 		WARN_ON_ONCE(atomic_read(&n_rcu_torture_mberror));
 		WARN_ON_ONCE(atomic_read(&n_rcu_torture_mbchk_fail));
 		WARN_ON_ONCE(n_rcu_torture_barrier_error);  // rcu_barrier()
 		WARN_ON_ONCE(n_rcu_torture_boost_ktrerror); // no boost kthread
-		WARN_ON_ONCE(n_rcu_torture_boost_rterror); // can't set RT prio
 		WARN_ON_ONCE(n_rcu_torture_boost_failure); // boost failed (TIMER_SOFTIRQ RT prio?)
 		WARN_ON_ONCE(i > 1); // Too-short grace period
 	}
@@ -2358,7 +2356,8 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag)
 		 "n_barrier_cbs=%d "
 		 "onoff_interval=%d onoff_holdoff=%d "
 		 "read_exit_delay=%d read_exit_burst=%d "
-		 "nocbs_nthreads=%d nocbs_toggle=%d\n",
+		 "nocbs_nthreads=%d nocbs_toggle=%d "
+		 "test_nmis=%d\n",
 		 torture_type, tag, nrealreaders, nfakewriters,
 		 stat_interval, verbose, test_no_idle_hz, shuffle_interval,
 		 stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter,
@@ -2369,7 +2368,8 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag)
 		 n_barrier_cbs,
 		 onoff_interval, onoff_holdoff,
 		 read_exit_delay, read_exit_burst,
-		 nocbs_nthreads, nocbs_toggle);
+		 nocbs_nthreads, nocbs_toggle,
+		 test_nmis);
 }
 
 static int rcutorture_booster_cleanup(unsigned int cpu)
@@ -3273,6 +3273,29 @@ static void rcu_torture_read_exit_cleanup(void)
 	torture_stop_kthread(rcutorture_read_exit, read_exit_task);
 }
 
+static void rcutorture_test_nmis(int n)
+{
+#if IS_BUILTIN(CONFIG_RCU_TORTURE_TEST)
+	int cpu;
+	int dumpcpu;
+	int i;
+
+	for (i = 0; i < n; i++) {
+		preempt_disable();
+		cpu = smp_processor_id();
+		dumpcpu = cpu + 1;
+		if (dumpcpu >= nr_cpu_ids)
+			dumpcpu = 0;
+		pr_alert("%s: CPU %d invoking dump_cpu_task(%d)\n", __func__, cpu, dumpcpu);
+		dump_cpu_task(dumpcpu);
+		preempt_enable();
+		schedule_timeout_uninterruptible(15 * HZ);
+	}
+#else // #if IS_BUILTIN(CONFIG_RCU_TORTURE_TEST)
+	WARN_ONCE(n, "Non-zero rcutorture.test_nmis=%d permitted only when rcutorture is built in.\n", test_nmis);
+#endif // #else // #if IS_BUILTIN(CONFIG_RCU_TORTURE_TEST)
+}
+
 static enum cpuhp_state rcutor_hp;
 
 static void
@@ -3297,6 +3320,8 @@ rcu_torture_cleanup(void)
 		return;
 	}
 
+	rcutorture_test_nmis(test_nmis);
+
 	if (cur_ops->gp_kthread_dbg)
 		cur_ops->gp_kthread_dbg();
 	rcu_torture_read_exit_cleanup();
@@ -3463,6 +3488,188 @@ static void rcutorture_sync(void)
 		cur_ops->sync();
 }
 
+static DEFINE_MUTEX(mut0);
+static DEFINE_MUTEX(mut1);
+static DEFINE_MUTEX(mut2);
+static DEFINE_MUTEX(mut3);
+static DEFINE_MUTEX(mut4);
+static DEFINE_MUTEX(mut5);
+static DEFINE_MUTEX(mut6);
+static DEFINE_MUTEX(mut7);
+static DEFINE_MUTEX(mut8);
+static DEFINE_MUTEX(mut9);
+
+static DECLARE_RWSEM(rwsem0);
+static DECLARE_RWSEM(rwsem1);
+static DECLARE_RWSEM(rwsem2);
+static DECLARE_RWSEM(rwsem3);
+static DECLARE_RWSEM(rwsem4);
+static DECLARE_RWSEM(rwsem5);
+static DECLARE_RWSEM(rwsem6);
+static DECLARE_RWSEM(rwsem7);
+static DECLARE_RWSEM(rwsem8);
+static DECLARE_RWSEM(rwsem9);
+
+DEFINE_STATIC_SRCU(srcu0);
+DEFINE_STATIC_SRCU(srcu1);
+DEFINE_STATIC_SRCU(srcu2);
+DEFINE_STATIC_SRCU(srcu3);
+DEFINE_STATIC_SRCU(srcu4);
+DEFINE_STATIC_SRCU(srcu5);
+DEFINE_STATIC_SRCU(srcu6);
+DEFINE_STATIC_SRCU(srcu7);
+DEFINE_STATIC_SRCU(srcu8);
+DEFINE_STATIC_SRCU(srcu9);
+
+static int srcu_lockdep_next(const char *f, const char *fl, const char *fs, const char *fu, int i,
+			     int cyclelen, int deadlock)
+{
+	int j = i + 1;
+
+	if (j >= cyclelen)
+		j = deadlock ? 0 : -1;
+	if (j >= 0)
+		pr_info("%s: %s(%d), %s(%d), %s(%d)\n", f, fl, i, fs, j, fu, i);
+	else
+		pr_info("%s: %s(%d), %s(%d)\n", f, fl, i, fu, i);
+	return j;
+}
+
+// Test lockdep on SRCU-based deadlock scenarios.
+static void rcu_torture_init_srcu_lockdep(void)
+{
+	int cyclelen;
+	int deadlock;
+	bool err = false;
+	int i;
+	int j;
+	int idx;
+	struct mutex *muts[] = { &mut0, &mut1, &mut2, &mut3, &mut4,
+				 &mut5, &mut6, &mut7, &mut8, &mut9 };
+	struct rw_semaphore *rwsems[] = { &rwsem0, &rwsem1, &rwsem2, &rwsem3, &rwsem4,
+					  &rwsem5, &rwsem6, &rwsem7, &rwsem8, &rwsem9 };
+	struct srcu_struct *srcus[] = { &srcu0, &srcu1, &srcu2, &srcu3, &srcu4,
+					&srcu5, &srcu6, &srcu7, &srcu8, &srcu9 };
+	int testtype;
+
+	if (!test_srcu_lockdep)
+		return;
+
+	deadlock = test_srcu_lockdep / 1000;
+	testtype = (test_srcu_lockdep / 10) % 100;
+	cyclelen = test_srcu_lockdep % 10;
+	WARN_ON_ONCE(ARRAY_SIZE(muts) != ARRAY_SIZE(srcus));
+	if (WARN_ONCE(deadlock != !!deadlock,
+		      "%s: test_srcu_lockdep=%d and deadlock digit %d must be zero or one.\n",
+		      __func__, test_srcu_lockdep, deadlock))
+		err = true;
+	if (WARN_ONCE(cyclelen <= 0,
+		      "%s: test_srcu_lockdep=%d and cycle-length digit %d must be greater than zero.\n",
+		      __func__, test_srcu_lockdep, cyclelen))
+		err = true;
+	if (err)
+		goto err_out;
+
+	if (testtype == 0) {
+		pr_info("%s: test_srcu_lockdep = %05d: SRCU %d-way %sdeadlock.\n",
+			__func__, test_srcu_lockdep, cyclelen, deadlock ? "" : "non-");
+		if (deadlock && cyclelen == 1)
+			pr_info("%s: Expect hang.\n", __func__);
+		for (i = 0; i < cyclelen; i++) {
+			j = srcu_lockdep_next(__func__, "srcu_read_lock", "synchronize_srcu",
+					      "srcu_read_unlock", i, cyclelen, deadlock);
+			idx = srcu_read_lock(srcus[i]);
+			if (j >= 0)
+				synchronize_srcu(srcus[j]);
+			srcu_read_unlock(srcus[i], idx);
+		}
+		return;
+	}
+
+	if (testtype == 1) {
+		pr_info("%s: test_srcu_lockdep = %05d: SRCU/mutex %d-way %sdeadlock.\n",
+			__func__, test_srcu_lockdep, cyclelen, deadlock ? "" : "non-");
+		for (i = 0; i < cyclelen; i++) {
+			pr_info("%s: srcu_read_lock(%d), mutex_lock(%d), mutex_unlock(%d), srcu_read_unlock(%d)\n",
+				__func__, i, i, i, i);
+			idx = srcu_read_lock(srcus[i]);
+			mutex_lock(muts[i]);
+			mutex_unlock(muts[i]);
+			srcu_read_unlock(srcus[i], idx);
+
+			j = srcu_lockdep_next(__func__, "mutex_lock", "synchronize_srcu",
+					      "mutex_unlock", i, cyclelen, deadlock);
+			mutex_lock(muts[i]);
+			if (j >= 0)
+				synchronize_srcu(srcus[j]);
+			mutex_unlock(muts[i]);
+		}
+		return;
+	}
+
+	if (testtype == 2) {
+		pr_info("%s: test_srcu_lockdep = %05d: SRCU/rwsem %d-way %sdeadlock.\n",
+			__func__, test_srcu_lockdep, cyclelen, deadlock ? "" : "non-");
+		for (i = 0; i < cyclelen; i++) {
+			pr_info("%s: srcu_read_lock(%d), down_read(%d), up_read(%d), srcu_read_unlock(%d)\n",
+				__func__, i, i, i, i);
+			idx = srcu_read_lock(srcus[i]);
+			down_read(rwsems[i]);
+			up_read(rwsems[i]);
+			srcu_read_unlock(srcus[i], idx);
+
+			j = srcu_lockdep_next(__func__, "down_write", "synchronize_srcu",
+					      "up_write", i, cyclelen, deadlock);
+			down_write(rwsems[i]);
+			if (j >= 0)
+				synchronize_srcu(srcus[j]);
+			up_write(rwsems[i]);
+		}
+		return;
+	}
+
+#ifdef CONFIG_TASKS_TRACE_RCU
+	if (testtype == 3) {
+		pr_info("%s: test_srcu_lockdep = %05d: SRCU and Tasks Trace RCU %d-way %sdeadlock.\n",
+			__func__, test_srcu_lockdep, cyclelen, deadlock ? "" : "non-");
+		if (deadlock && cyclelen == 1)
+			pr_info("%s: Expect hang.\n", __func__);
+		for (i = 0; i < cyclelen; i++) {
+			char *fl = i == 0 ? "rcu_read_lock_trace" : "srcu_read_lock";
+			char *fs = i == cyclelen - 1 ? "synchronize_rcu_tasks_trace"
+						     : "synchronize_srcu";
+			char *fu = i == 0 ? "rcu_read_unlock_trace" : "srcu_read_unlock";
+
+			j = srcu_lockdep_next(__func__, fl, fs, fu, i, cyclelen, deadlock);
+			if (i == 0)
+				rcu_read_lock_trace();
+			else
+				idx = srcu_read_lock(srcus[i]);
+			if (j >= 0) {
+				if (i == cyclelen - 1)
+					synchronize_rcu_tasks_trace();
+				else
+					synchronize_srcu(srcus[j]);
+			}
+			if (i == 0)
+				rcu_read_unlock_trace();
+			else
+				srcu_read_unlock(srcus[i], idx);
+		}
+		return;
+	}
+#endif // #ifdef CONFIG_TASKS_TRACE_RCU
+
+err_out:
+	pr_info("%s: test_srcu_lockdep = %05d does nothing.\n", __func__, test_srcu_lockdep);
+	pr_info("%s: test_srcu_lockdep = DNNL.\n", __func__);
+	pr_info("%s: D: Deadlock if nonzero.\n", __func__);
+	pr_info("%s: NN: Test number, 0=SRCU, 1=SRCU/mutex, 2=SRCU/rwsem, 3=SRCU/Tasks Trace RCU.\n", __func__);
+	pr_info("%s: L: Cycle length.\n", __func__);
+	if (!IS_ENABLED(CONFIG_TASKS_TRACE_RCU))
+		pr_info("%s: NN=3 disallowed because kernel is built with CONFIG_TASKS_TRACE_RCU=n\n", __func__);
+}
+
 static int __init
 rcu_torture_init(void)
 {
@@ -3501,9 +3708,17 @@ rcu_torture_init(void)
 		pr_alert("rcu-torture: ->fqs NULL and non-zero fqs_duration, fqs disabled.\n");
 		fqs_duration = 0;
 	}
+	if (nocbs_nthreads != 0 && (cur_ops != &rcu_ops ||
+				    !IS_ENABLED(CONFIG_RCU_NOCB_CPU))) {
+		pr_alert("rcu-torture types: %s and CONFIG_RCU_NOCB_CPU=%d, nocb toggle disabled.\n",
+			 cur_ops->name, IS_ENABLED(CONFIG_RCU_NOCB_CPU));
+		nocbs_nthreads = 0;
+	}
 	if (cur_ops->init)
 		cur_ops->init();
 
+	rcu_torture_init_srcu_lockdep();
+
 	if (nreaders >= 0) {
 		nrealreaders = nreaders;
 	} else {
@@ -3540,7 +3755,6 @@ rcu_torture_init(void)
 	atomic_set(&n_rcu_torture_error, 0);
 	n_rcu_torture_barrier_error = 0;
 	n_rcu_torture_boost_ktrerror = 0;
-	n_rcu_torture_boost_rterror = 0;
 	n_rcu_torture_boost_failure = 0;
 	n_rcu_torture_boosts = 0;
 	for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
diff --git a/kernel/rcu/refscale.c b/kernel/rcu/refscale.c
index afa3e1a2f6902..1970ce5f22d40 100644
--- a/kernel/rcu/refscale.c
+++ b/kernel/rcu/refscale.c
@@ -1031,7 +1031,7 @@ ref_scale_cleanup(void)
 static int
 ref_scale_shutdown(void *arg)
 {
-	wait_event(shutdown_wq, shutdown_start);
+	wait_event_idle(shutdown_wq, shutdown_start);
 
 	smp_mb(); // Wake before output.
 	ref_scale_cleanup();
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index b12fb0cec44d6..336af24e0fe35 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -197,6 +197,8 @@ void synchronize_srcu(struct srcu_struct *ssp)
 {
 	struct rcu_synchronize rs;
 
+	srcu_lock_sync(&ssp->dep_map);
+
 	RCU_LOCKDEP_WARN(lockdep_is_held(ssp) ||
 			lock_is_held(&rcu_bh_lock_map) ||
 			lock_is_held(&rcu_lock_map) ||
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index ab4ee58af84bf..20d7a238d675a 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -103,7 +103,7 @@ do {										\
 
 #define spin_trylock_irqsave_rcu_node(p, flags)					\
 ({										\
-	bool ___locked = spin_trylock_irqsave(&ACCESS_PRIVATE(p, lock), flags);	\
+	bool ___locked = spin_trylock_irqsave(&ACCESS_PRIVATE(p, lock), flags); \
 										\
 	if (___locked)								\
 		smp_mb__after_unlock_lock();					\
@@ -135,8 +135,8 @@ static void init_srcu_struct_data(struct srcu_struct *ssp)
 		spin_lock_init(&ACCESS_PRIVATE(sdp, lock));
 		rcu_segcblist_init(&sdp->srcu_cblist);
 		sdp->srcu_cblist_invoking = false;
-		sdp->srcu_gp_seq_needed = ssp->srcu_gp_seq;
-		sdp->srcu_gp_seq_needed_exp = ssp->srcu_gp_seq;
+		sdp->srcu_gp_seq_needed = ssp->srcu_sup->srcu_gp_seq;
+		sdp->srcu_gp_seq_needed_exp = ssp->srcu_sup->srcu_gp_seq;
 		sdp->mynode = NULL;
 		sdp->cpu = cpu;
 		INIT_WORK(&sdp->work, srcu_invoke_callbacks);
@@ -173,14 +173,14 @@ static bool init_srcu_struct_nodes(struct srcu_struct *ssp, gfp_t gfp_flags)
 
 	/* Initialize geometry if it has not already been initialized. */
 	rcu_init_geometry();
-	ssp->node = kcalloc(rcu_num_nodes, sizeof(*ssp->node), gfp_flags);
-	if (!ssp->node)
+	ssp->srcu_sup->node = kcalloc(rcu_num_nodes, sizeof(*ssp->srcu_sup->node), gfp_flags);
+	if (!ssp->srcu_sup->node)
 		return false;
 
 	/* Work out the overall tree geometry. */
-	ssp->level[0] = &ssp->node[0];
+	ssp->srcu_sup->level[0] = &ssp->srcu_sup->node[0];
 	for (i = 1; i < rcu_num_lvls; i++)
-		ssp->level[i] = ssp->level[i - 1] + num_rcu_lvl[i - 1];
+		ssp->srcu_sup->level[i] = ssp->srcu_sup->level[i - 1] + num_rcu_lvl[i - 1];
 	rcu_init_levelspread(levelspread, num_rcu_lvl);
 
 	/* Each pass through this loop initializes one srcu_node structure. */
@@ -195,17 +195,17 @@ static bool init_srcu_struct_nodes(struct srcu_struct *ssp, gfp_t gfp_flags)
 		snp->srcu_gp_seq_needed_exp = SRCU_SNP_INIT_SEQ;
 		snp->grplo = -1;
 		snp->grphi = -1;
-		if (snp == &ssp->node[0]) {
+		if (snp == &ssp->srcu_sup->node[0]) {
 			/* Root node, special case. */
 			snp->srcu_parent = NULL;
 			continue;
 		}
 
 		/* Non-root node. */
-		if (snp == ssp->level[level + 1])
+		if (snp == ssp->srcu_sup->level[level + 1])
 			level++;
-		snp->srcu_parent = ssp->level[level - 1] +
-				   (snp - ssp->level[level]) /
+		snp->srcu_parent = ssp->srcu_sup->level[level - 1] +
+				   (snp - ssp->srcu_sup->level[level]) /
 				   levelspread[level - 1];
 	}
 
@@ -214,7 +214,7 @@ static bool init_srcu_struct_nodes(struct srcu_struct *ssp, gfp_t gfp_flags)
 	 * leaves of the srcu_node tree.
 	 */
 	level = rcu_num_lvls - 1;
-	snp_first = ssp->level[level];
+	snp_first = ssp->srcu_sup->level[level];
 	for_each_possible_cpu(cpu) {
 		sdp = per_cpu_ptr(ssp->sda, cpu);
 		sdp->mynode = &snp_first[cpu / levelspread[level]];
@@ -225,7 +225,7 @@ static bool init_srcu_struct_nodes(struct srcu_struct *ssp, gfp_t gfp_flags)
 		}
 		sdp->grpmask = 1 << (cpu - sdp->mynode->grplo);
 	}
-	smp_store_release(&ssp->srcu_size_state, SRCU_SIZE_WAIT_BARRIER);
+	smp_store_release(&ssp->srcu_sup->srcu_size_state, SRCU_SIZE_WAIT_BARRIER);
 	return true;
 }
 
@@ -236,36 +236,47 @@ static bool init_srcu_struct_nodes(struct srcu_struct *ssp, gfp_t gfp_flags)
  */
 static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static)
 {
-	ssp->srcu_size_state = SRCU_SIZE_SMALL;
-	ssp->node = NULL;
-	mutex_init(&ssp->srcu_cb_mutex);
-	mutex_init(&ssp->srcu_gp_mutex);
+	if (!is_static)
+		ssp->srcu_sup = kzalloc(sizeof(*ssp->srcu_sup), GFP_KERNEL);
+	if (!ssp->srcu_sup)
+		return -ENOMEM;
+	if (!is_static)
+		spin_lock_init(&ACCESS_PRIVATE(ssp->srcu_sup, lock));
+	ssp->srcu_sup->srcu_size_state = SRCU_SIZE_SMALL;
+	ssp->srcu_sup->node = NULL;
+	mutex_init(&ssp->srcu_sup->srcu_cb_mutex);
+	mutex_init(&ssp->srcu_sup->srcu_gp_mutex);
 	ssp->srcu_idx = 0;
-	ssp->srcu_gp_seq = 0;
-	ssp->srcu_barrier_seq = 0;
-	mutex_init(&ssp->srcu_barrier_mutex);
-	atomic_set(&ssp->srcu_barrier_cpu_cnt, 0);
-	INIT_DELAYED_WORK(&ssp->work, process_srcu);
-	ssp->sda_is_static = is_static;
+	ssp->srcu_sup->srcu_gp_seq = 0;
+	ssp->srcu_sup->srcu_barrier_seq = 0;
+	mutex_init(&ssp->srcu_sup->srcu_barrier_mutex);
+	atomic_set(&ssp->srcu_sup->srcu_barrier_cpu_cnt, 0);
+	INIT_DELAYED_WORK(&ssp->srcu_sup->work, process_srcu);
+	ssp->srcu_sup->sda_is_static = is_static;
 	if (!is_static)
 		ssp->sda = alloc_percpu(struct srcu_data);
-	if (!ssp->sda)
+	if (!ssp->sda) {
+		if (!is_static)
+			kfree(ssp->srcu_sup);
 		return -ENOMEM;
+	}
 	init_srcu_struct_data(ssp);
-	ssp->srcu_gp_seq_needed_exp = 0;
-	ssp->srcu_last_gp_end = ktime_get_mono_fast_ns();
-	if (READ_ONCE(ssp->srcu_size_state) == SRCU_SIZE_SMALL && SRCU_SIZING_IS_INIT()) {
+	ssp->srcu_sup->srcu_gp_seq_needed_exp = 0;
+	ssp->srcu_sup->srcu_last_gp_end = ktime_get_mono_fast_ns();
+	if (READ_ONCE(ssp->srcu_sup->srcu_size_state) == SRCU_SIZE_SMALL && SRCU_SIZING_IS_INIT()) {
 		if (!init_srcu_struct_nodes(ssp, GFP_ATOMIC)) {
-			if (!ssp->sda_is_static) {
+			if (!ssp->srcu_sup->sda_is_static) {
 				free_percpu(ssp->sda);
 				ssp->sda = NULL;
+				kfree(ssp->srcu_sup);
 				return -ENOMEM;
 			}
 		} else {
-			WRITE_ONCE(ssp->srcu_size_state, SRCU_SIZE_BIG);
+			WRITE_ONCE(ssp->srcu_sup->srcu_size_state, SRCU_SIZE_BIG);
 		}
 	}
-	smp_store_release(&ssp->srcu_gp_seq_needed, 0); /* Init done. */
+	ssp->srcu_sup->srcu_ssp = ssp;
+	smp_store_release(&ssp->srcu_sup->srcu_gp_seq_needed, 0); /* Init done. */
 	return 0;
 }
 
@@ -277,7 +288,6 @@ int __init_srcu_struct(struct srcu_struct *ssp, const char *name,
 	/* Don't re-initialize a lock while it is held. */
 	debug_check_no_locks_freed((void *)ssp, sizeof(*ssp));
 	lockdep_init_map(&ssp->dep_map, name, key, 0);
-	spin_lock_init(&ACCESS_PRIVATE(ssp, lock));
 	return init_srcu_struct_fields(ssp, false);
 }
 EXPORT_SYMBOL_GPL(__init_srcu_struct);
@@ -294,7 +304,6 @@ EXPORT_SYMBOL_GPL(__init_srcu_struct);
  */
 int init_srcu_struct(struct srcu_struct *ssp)
 {
-	spin_lock_init(&ACCESS_PRIVATE(ssp, lock));
 	return init_srcu_struct_fields(ssp, false);
 }
 EXPORT_SYMBOL_GPL(init_srcu_struct);
@@ -306,8 +315,8 @@ EXPORT_SYMBOL_GPL(init_srcu_struct);
  */
 static void __srcu_transition_to_big(struct srcu_struct *ssp)
 {
-	lockdep_assert_held(&ACCESS_PRIVATE(ssp, lock));
-	smp_store_release(&ssp->srcu_size_state, SRCU_SIZE_ALLOC);
+	lockdep_assert_held(&ACCESS_PRIVATE(ssp->srcu_sup, lock));
+	smp_store_release(&ssp->srcu_sup->srcu_size_state, SRCU_SIZE_ALLOC);
 }
 
 /*
@@ -318,15 +327,15 @@ static void srcu_transition_to_big(struct srcu_struct *ssp)
 	unsigned long flags;
 
 	/* Double-checked locking on ->srcu_size-state. */
-	if (smp_load_acquire(&ssp->srcu_size_state) != SRCU_SIZE_SMALL)
+	if (smp_load_acquire(&ssp->srcu_sup->srcu_size_state) != SRCU_SIZE_SMALL)
 		return;
-	spin_lock_irqsave_rcu_node(ssp, flags);
-	if (smp_load_acquire(&ssp->srcu_size_state) != SRCU_SIZE_SMALL) {
-		spin_unlock_irqrestore_rcu_node(ssp, flags);
+	spin_lock_irqsave_rcu_node(ssp->srcu_sup, flags);
+	if (smp_load_acquire(&ssp->srcu_sup->srcu_size_state) != SRCU_SIZE_SMALL) {
+		spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, flags);
 		return;
 	}
 	__srcu_transition_to_big(ssp);
-	spin_unlock_irqrestore_rcu_node(ssp, flags);
+	spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, flags);
 }
 
 /*
@@ -337,14 +346,14 @@ static void spin_lock_irqsave_check_contention(struct srcu_struct *ssp)
 {
 	unsigned long j;
 
-	if (!SRCU_SIZING_IS_CONTEND() || ssp->srcu_size_state)
+	if (!SRCU_SIZING_IS_CONTEND() || ssp->srcu_sup->srcu_size_state)
 		return;
 	j = jiffies;
-	if (ssp->srcu_size_jiffies != j) {
-		ssp->srcu_size_jiffies = j;
-		ssp->srcu_n_lock_retries = 0;
+	if (ssp->srcu_sup->srcu_size_jiffies != j) {
+		ssp->srcu_sup->srcu_size_jiffies = j;
+		ssp->srcu_sup->srcu_n_lock_retries = 0;
 	}
-	if (++ssp->srcu_n_lock_retries <= small_contention_lim)
+	if (++ssp->srcu_sup->srcu_n_lock_retries <= small_contention_lim)
 		return;
 	__srcu_transition_to_big(ssp);
 }
@@ -361,9 +370,9 @@ static void spin_lock_irqsave_sdp_contention(struct srcu_data *sdp, unsigned lon
 
 	if (spin_trylock_irqsave_rcu_node(sdp, *flags))
 		return;
-	spin_lock_irqsave_rcu_node(ssp, *flags);
+	spin_lock_irqsave_rcu_node(ssp->srcu_sup, *flags);
 	spin_lock_irqsave_check_contention(ssp);
-	spin_unlock_irqrestore_rcu_node(ssp, *flags);
+	spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, *flags);
 	spin_lock_irqsave_rcu_node(sdp, *flags);
 }
 
@@ -375,9 +384,9 @@ static void spin_lock_irqsave_sdp_contention(struct srcu_data *sdp, unsigned lon
  */
 static void spin_lock_irqsave_ssp_contention(struct srcu_struct *ssp, unsigned long *flags)
 {
-	if (spin_trylock_irqsave_rcu_node(ssp, *flags))
+	if (spin_trylock_irqsave_rcu_node(ssp->srcu_sup, *flags))
 		return;
-	spin_lock_irqsave_rcu_node(ssp, *flags);
+	spin_lock_irqsave_rcu_node(ssp->srcu_sup, *flags);
 	spin_lock_irqsave_check_contention(ssp);
 }
 
@@ -394,15 +403,15 @@ static void check_init_srcu_struct(struct srcu_struct *ssp)
 	unsigned long flags;
 
 	/* The smp_load_acquire() pairs with the smp_store_release(). */
-	if (!rcu_seq_state(smp_load_acquire(&ssp->srcu_gp_seq_needed))) /*^^^*/
+	if (!rcu_seq_state(smp_load_acquire(&ssp->srcu_sup->srcu_gp_seq_needed))) /*^^^*/
 		return; /* Already initialized. */
-	spin_lock_irqsave_rcu_node(ssp, flags);
-	if (!rcu_seq_state(ssp->srcu_gp_seq_needed)) {
-		spin_unlock_irqrestore_rcu_node(ssp, flags);
+	spin_lock_irqsave_rcu_node(ssp->srcu_sup, flags);
+	if (!rcu_seq_state(ssp->srcu_sup->srcu_gp_seq_needed)) {
+		spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, flags);
 		return;
 	}
 	init_srcu_struct_fields(ssp, true);
-	spin_unlock_irqrestore_rcu_node(ssp, flags);
+	spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, flags);
 }
 
 /*
@@ -607,17 +616,18 @@ static unsigned long srcu_get_delay(struct srcu_struct *ssp)
 	unsigned long gpstart;
 	unsigned long j;
 	unsigned long jbase = SRCU_INTERVAL;
+	struct srcu_usage *sup = ssp->srcu_sup;
 
-	if (ULONG_CMP_LT(READ_ONCE(ssp->srcu_gp_seq), READ_ONCE(ssp->srcu_gp_seq_needed_exp)))
+	if (ULONG_CMP_LT(READ_ONCE(sup->srcu_gp_seq), READ_ONCE(sup->srcu_gp_seq_needed_exp)))
 		jbase = 0;
-	if (rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq))) {
+	if (rcu_seq_state(READ_ONCE(sup->srcu_gp_seq))) {
 		j = jiffies - 1;
-		gpstart = READ_ONCE(ssp->srcu_gp_start);
+		gpstart = READ_ONCE(sup->srcu_gp_start);
 		if (time_after(j, gpstart))
 			jbase += j - gpstart;
 		if (!jbase) {
-			WRITE_ONCE(ssp->srcu_n_exp_nodelay, READ_ONCE(ssp->srcu_n_exp_nodelay) + 1);
-			if (READ_ONCE(ssp->srcu_n_exp_nodelay) > srcu_max_nodelay_phase)
+			WRITE_ONCE(sup->srcu_n_exp_nodelay, READ_ONCE(sup->srcu_n_exp_nodelay) + 1);
+			if (READ_ONCE(sup->srcu_n_exp_nodelay) > srcu_max_nodelay_phase)
 				jbase = 1;
 		}
 	}
@@ -634,12 +644,13 @@ static unsigned long srcu_get_delay(struct srcu_struct *ssp)
 void cleanup_srcu_struct(struct srcu_struct *ssp)
 {
 	int cpu;
+	struct srcu_usage *sup = ssp->srcu_sup;
 
 	if (WARN_ON(!srcu_get_delay(ssp)))
 		return; /* Just leak it! */
 	if (WARN_ON(srcu_readers_active(ssp)))
 		return; /* Just leak it! */
-	flush_delayed_work(&ssp->work);
+	flush_delayed_work(&sup->work);
 	for_each_possible_cpu(cpu) {
 		struct srcu_data *sdp = per_cpu_ptr(ssp->sda, cpu);
 
@@ -648,21 +659,23 @@ void cleanup_srcu_struct(struct srcu_struct *ssp)
 		if (WARN_ON(rcu_segcblist_n_cbs(&sdp->srcu_cblist)))
 			return; /* Forgot srcu_barrier(), so just leak it! */
 	}
-	if (WARN_ON(rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)) != SRCU_STATE_IDLE) ||
-	    WARN_ON(rcu_seq_current(&ssp->srcu_gp_seq) != ssp->srcu_gp_seq_needed) ||
+	if (WARN_ON(rcu_seq_state(READ_ONCE(sup->srcu_gp_seq)) != SRCU_STATE_IDLE) ||
+	    WARN_ON(rcu_seq_current(&sup->srcu_gp_seq) != sup->srcu_gp_seq_needed) ||
 	    WARN_ON(srcu_readers_active(ssp))) {
 		pr_info("%s: Active srcu_struct %p read state: %d gp state: %lu/%lu\n",
-			__func__, ssp, rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)),
-			rcu_seq_current(&ssp->srcu_gp_seq), ssp->srcu_gp_seq_needed);
+			__func__, ssp, rcu_seq_state(READ_ONCE(sup->srcu_gp_seq)),
+			rcu_seq_current(&sup->srcu_gp_seq), sup->srcu_gp_seq_needed);
 		return; /* Caller forgot to stop doing call_srcu()? */
 	}
-	if (!ssp->sda_is_static) {
+	kfree(sup->node);
+	sup->node = NULL;
+	sup->srcu_size_state = SRCU_SIZE_SMALL;
+	if (!sup->sda_is_static) {
 		free_percpu(ssp->sda);
 		ssp->sda = NULL;
+		kfree(sup);
+		ssp->srcu_sup = NULL;
 	}
-	kfree(ssp->node);
-	ssp->node = NULL;
-	ssp->srcu_size_state = SRCU_SIZE_SMALL;
 }
 EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
 
@@ -760,23 +773,23 @@ static void srcu_gp_start(struct srcu_struct *ssp)
 	struct srcu_data *sdp;
 	int state;
 
-	if (smp_load_acquire(&ssp->srcu_size_state) < SRCU_SIZE_WAIT_BARRIER)
+	if (smp_load_acquire(&ssp->srcu_sup->srcu_size_state) < SRCU_SIZE_WAIT_BARRIER)
 		sdp = per_cpu_ptr(ssp->sda, get_boot_cpu_id());
 	else
 		sdp = this_cpu_ptr(ssp->sda);
-	lockdep_assert_held(&ACCESS_PRIVATE(ssp, lock));
-	WARN_ON_ONCE(ULONG_CMP_GE(ssp->srcu_gp_seq, ssp->srcu_gp_seq_needed));
+	lockdep_assert_held(&ACCESS_PRIVATE(ssp->srcu_sup, lock));
+	WARN_ON_ONCE(ULONG_CMP_GE(ssp->srcu_sup->srcu_gp_seq, ssp->srcu_sup->srcu_gp_seq_needed));
 	spin_lock_rcu_node(sdp);  /* Interrupts already disabled. */
 	rcu_segcblist_advance(&sdp->srcu_cblist,
-			      rcu_seq_current(&ssp->srcu_gp_seq));
+			      rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq));
 	(void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
-				       rcu_seq_snap(&ssp->srcu_gp_seq));
+				       rcu_seq_snap(&ssp->srcu_sup->srcu_gp_seq));
 	spin_unlock_rcu_node(sdp);  /* Interrupts remain disabled. */
-	WRITE_ONCE(ssp->srcu_gp_start, jiffies);
-	WRITE_ONCE(ssp->srcu_n_exp_nodelay, 0);
+	WRITE_ONCE(ssp->srcu_sup->srcu_gp_start, jiffies);
+	WRITE_ONCE(ssp->srcu_sup->srcu_n_exp_nodelay, 0);
 	smp_mb(); /* Order prior store to ->srcu_gp_seq_needed vs. GP start. */
-	rcu_seq_start(&ssp->srcu_gp_seq);
-	state = rcu_seq_state(ssp->srcu_gp_seq);
+	rcu_seq_start(&ssp->srcu_sup->srcu_gp_seq);
+	state = rcu_seq_state(ssp->srcu_sup->srcu_gp_seq);
 	WARN_ON_ONCE(state != SRCU_STATE_SCAN1);
 }
 
@@ -849,28 +862,29 @@ static void srcu_gp_end(struct srcu_struct *ssp)
 	unsigned long sgsne;
 	struct srcu_node *snp;
 	int ss_state;
+	struct srcu_usage *sup = ssp->srcu_sup;
 
 	/* Prevent more than one additional grace period. */
-	mutex_lock(&ssp->srcu_cb_mutex);
+	mutex_lock(&sup->srcu_cb_mutex);
 
 	/* End the current grace period. */
-	spin_lock_irq_rcu_node(ssp);
-	idx = rcu_seq_state(ssp->srcu_gp_seq);
+	spin_lock_irq_rcu_node(sup);
+	idx = rcu_seq_state(sup->srcu_gp_seq);
 	WARN_ON_ONCE(idx != SRCU_STATE_SCAN2);
-	if (ULONG_CMP_LT(READ_ONCE(ssp->srcu_gp_seq), READ_ONCE(ssp->srcu_gp_seq_needed_exp)))
+	if (ULONG_CMP_LT(READ_ONCE(sup->srcu_gp_seq), READ_ONCE(sup->srcu_gp_seq_needed_exp)))
 		cbdelay = 0;
 
-	WRITE_ONCE(ssp->srcu_last_gp_end, ktime_get_mono_fast_ns());
-	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))
-		WRITE_ONCE(ssp->srcu_gp_seq_needed_exp, gpseq);
-	spin_unlock_irq_rcu_node(ssp);
-	mutex_unlock(&ssp->srcu_gp_mutex);
+	WRITE_ONCE(sup->srcu_last_gp_end, ktime_get_mono_fast_ns());
+	rcu_seq_end(&sup->srcu_gp_seq);
+	gpseq = rcu_seq_current(&sup->srcu_gp_seq);
+	if (ULONG_CMP_LT(sup->srcu_gp_seq_needed_exp, gpseq))
+		WRITE_ONCE(sup->srcu_gp_seq_needed_exp, gpseq);
+	spin_unlock_irq_rcu_node(sup);
+	mutex_unlock(&sup->srcu_gp_mutex);
 	/* A new grace period can start at this point.  But only one. */
 
 	/* Initiate callback invocation as needed. */
-	ss_state = smp_load_acquire(&ssp->srcu_size_state);
+	ss_state = smp_load_acquire(&sup->srcu_size_state);
 	if (ss_state < SRCU_SIZE_WAIT_BARRIER) {
 		srcu_schedule_cbs_sdp(per_cpu_ptr(ssp->sda, get_boot_cpu_id()),
 					cbdelay);
@@ -879,7 +893,7 @@ static void srcu_gp_end(struct srcu_struct *ssp)
 		srcu_for_each_node_breadth_first(ssp, snp) {
 			spin_lock_irq_rcu_node(snp);
 			cbs = false;
-			last_lvl = snp >= ssp->level[rcu_num_lvls - 1];
+			last_lvl = snp >= sup->level[rcu_num_lvls - 1];
 			if (last_lvl)
 				cbs = ss_state < SRCU_SIZE_BIG || snp->srcu_have_cbs[idx] == gpseq;
 			snp->srcu_have_cbs[idx] = gpseq;
@@ -911,18 +925,18 @@ static void srcu_gp_end(struct srcu_struct *ssp)
 		}
 
 	/* Callback initiation done, allow grace periods after next. */
-	mutex_unlock(&ssp->srcu_cb_mutex);
+	mutex_unlock(&sup->srcu_cb_mutex);
 
 	/* Start a new grace period if needed. */
-	spin_lock_irq_rcu_node(ssp);
-	gpseq = rcu_seq_current(&ssp->srcu_gp_seq);
+	spin_lock_irq_rcu_node(sup);
+	gpseq = rcu_seq_current(&sup->srcu_gp_seq);
 	if (!rcu_seq_state(gpseq) &&
-	    ULONG_CMP_LT(gpseq, ssp->srcu_gp_seq_needed)) {
+	    ULONG_CMP_LT(gpseq, sup->srcu_gp_seq_needed)) {
 		srcu_gp_start(ssp);
-		spin_unlock_irq_rcu_node(ssp);
+		spin_unlock_irq_rcu_node(sup);
 		srcu_reschedule(ssp, 0);
 	} else {
-		spin_unlock_irq_rcu_node(ssp);
+		spin_unlock_irq_rcu_node(sup);
 	}
 
 	/* Transition to big if needed. */
@@ -930,7 +944,7 @@ static void srcu_gp_end(struct srcu_struct *ssp)
 		if (ss_state == SRCU_SIZE_ALLOC)
 			init_srcu_struct_nodes(ssp, GFP_KERNEL);
 		else
-			smp_store_release(&ssp->srcu_size_state, ss_state + 1);
+			smp_store_release(&sup->srcu_size_state, ss_state + 1);
 	}
 }
 
@@ -950,7 +964,7 @@ static void srcu_funnel_exp_start(struct srcu_struct *ssp, struct srcu_node *snp
 	if (snp)
 		for (; snp != NULL; snp = snp->srcu_parent) {
 			sgsne = READ_ONCE(snp->srcu_gp_seq_needed_exp);
-			if (WARN_ON_ONCE(rcu_seq_done(&ssp->srcu_gp_seq, s)) ||
+			if (WARN_ON_ONCE(rcu_seq_done(&ssp->srcu_sup->srcu_gp_seq, s)) ||
 			    (!srcu_invl_snp_seq(sgsne) && ULONG_CMP_GE(sgsne, s)))
 				return;
 			spin_lock_irqsave_rcu_node(snp, flags);
@@ -963,9 +977,9 @@ static void srcu_funnel_exp_start(struct srcu_struct *ssp, struct srcu_node *snp
 			spin_unlock_irqrestore_rcu_node(snp, flags);
 		}
 	spin_lock_irqsave_ssp_contention(ssp, &flags);
-	if (ULONG_CMP_LT(ssp->srcu_gp_seq_needed_exp, s))
-		WRITE_ONCE(ssp->srcu_gp_seq_needed_exp, s);
-	spin_unlock_irqrestore_rcu_node(ssp, flags);
+	if (ULONG_CMP_LT(ssp->srcu_sup->srcu_gp_seq_needed_exp, s))
+		WRITE_ONCE(ssp->srcu_sup->srcu_gp_seq_needed_exp, s);
+	spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, flags);
 }
 
 /*
@@ -990,9 +1004,10 @@ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp,
 	struct srcu_node *snp;
 	struct srcu_node *snp_leaf;
 	unsigned long snp_seq;
+	struct srcu_usage *sup = ssp->srcu_sup;
 
 	/* Ensure that snp node tree is fully initialized before traversing it */
-	if (smp_load_acquire(&ssp->srcu_size_state) < SRCU_SIZE_WAIT_BARRIER)
+	if (smp_load_acquire(&sup->srcu_size_state) < SRCU_SIZE_WAIT_BARRIER)
 		snp_leaf = NULL;
 	else
 		snp_leaf = sdp->mynode;
@@ -1000,7 +1015,7 @@ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp,
 	if (snp_leaf)
 		/* Each pass through the loop does one level of the srcu_node tree. */
 		for (snp = snp_leaf; snp != NULL; snp = snp->srcu_parent) {
-			if (WARN_ON_ONCE(rcu_seq_done(&ssp->srcu_gp_seq, s)) && snp != snp_leaf)
+			if (WARN_ON_ONCE(rcu_seq_done(&sup->srcu_gp_seq, s)) && snp != snp_leaf)
 				return; /* GP already done and CBs recorded. */
 			spin_lock_irqsave_rcu_node(snp, flags);
 			snp_seq = snp->srcu_have_cbs[idx];
@@ -1027,20 +1042,20 @@ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp,
 
 	/* Top of tree, must ensure the grace period will be started. */
 	spin_lock_irqsave_ssp_contention(ssp, &flags);
-	if (ULONG_CMP_LT(ssp->srcu_gp_seq_needed, s)) {
+	if (ULONG_CMP_LT(sup->srcu_gp_seq_needed, s)) {
 		/*
 		 * Record need for grace period s.  Pair with load
 		 * acquire setting up for initialization.
 		 */
-		smp_store_release(&ssp->srcu_gp_seq_needed, s); /*^^^*/
+		smp_store_release(&sup->srcu_gp_seq_needed, s); /*^^^*/
 	}
-	if (!do_norm && ULONG_CMP_LT(ssp->srcu_gp_seq_needed_exp, s))
-		WRITE_ONCE(ssp->srcu_gp_seq_needed_exp, s);
+	if (!do_norm && ULONG_CMP_LT(sup->srcu_gp_seq_needed_exp, s))
+		WRITE_ONCE(sup->srcu_gp_seq_needed_exp, s);
 
 	/* If grace period not already in progress, start it. */
-	if (!WARN_ON_ONCE(rcu_seq_done(&ssp->srcu_gp_seq, s)) &&
-	    rcu_seq_state(ssp->srcu_gp_seq) == SRCU_STATE_IDLE) {
-		WARN_ON_ONCE(ULONG_CMP_GE(ssp->srcu_gp_seq, ssp->srcu_gp_seq_needed));
+	if (!WARN_ON_ONCE(rcu_seq_done(&sup->srcu_gp_seq, s)) &&
+	    rcu_seq_state(sup->srcu_gp_seq) == SRCU_STATE_IDLE) {
+		WARN_ON_ONCE(ULONG_CMP_GE(sup->srcu_gp_seq, sup->srcu_gp_seq_needed));
 		srcu_gp_start(ssp);
 
 		// And how can that list_add() in the "else" clause
@@ -1049,12 +1064,12 @@ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp,
 		// can only be executed during early boot when there is only
 		// the one boot CPU running with interrupts still disabled.
 		if (likely(srcu_init_done))
-			queue_delayed_work(rcu_gp_wq, &ssp->work,
+			queue_delayed_work(rcu_gp_wq, &sup->work,
 					   !!srcu_get_delay(ssp));
-		else if (list_empty(&ssp->work.work.entry))
-			list_add(&ssp->work.work.entry, &srcu_boot_list);
+		else if (list_empty(&sup->work.work.entry))
+			list_add(&sup->work.work.entry, &srcu_boot_list);
 	}
-	spin_unlock_irqrestore_rcu_node(ssp, flags);
+	spin_unlock_irqrestore_rcu_node(sup, flags);
 }
 
 /*
@@ -1085,16 +1100,36 @@ static bool try_check_zero(struct srcu_struct *ssp, int idx, int trycount)
 static void srcu_flip(struct srcu_struct *ssp)
 {
 	/*
-	 * Ensure that if this updater saw a given reader's increment
-	 * from __srcu_read_lock(), that reader was using an old value
-	 * of ->srcu_idx.  Also ensure that if a given reader sees the
-	 * new value of ->srcu_idx, this updater's earlier scans cannot
-	 * have seen that reader's increments (which is OK, because this
-	 * grace period need not wait on that reader).
+	 * Because the flip of ->srcu_idx is executed only if the
+	 * preceding call to srcu_readers_active_idx_check() found that
+	 * the ->srcu_unlock_count[] and ->srcu_lock_count[] sums matched
+	 * and because that summing uses atomic_long_read(), there is
+	 * ordering due to a control dependency between that summing and
+	 * the WRITE_ONCE() in this call to srcu_flip().  This ordering
+	 * ensures that if this updater saw a given reader's increment from
+	 * __srcu_read_lock(), that reader was using a value of ->srcu_idx
+	 * from before the previous call to srcu_flip(), which should be
+	 * quite rare.  This ordering thus helps forward progress because
+	 * the grace period could otherwise be delayed by additional
+	 * calls to __srcu_read_lock() using that old (soon to be new)
+	 * value of ->srcu_idx.
+	 *
+	 * This sum-equality check and ordering also ensures that if
+	 * a given call to __srcu_read_lock() uses the new value of
+	 * ->srcu_idx, this updater's earlier scans cannot have seen
+	 * that reader's increments, which is all to the good, because
+	 * this grace period need not wait on that reader.  After all,
+	 * if those earlier scans had seen that reader, there would have
+	 * been a sum mismatch and this code would not be reached.
+	 *
+	 * This means that the following smp_mb() is redundant, but
+	 * it stays until either (1) Compilers learn about this sort of
+	 * control dependency or (2) Some production workload running on
+	 * a production system is unduly delayed by this slowpath smp_mb().
 	 */
 	smp_mb(); /* E */  /* Pairs with B and C. */
 
-	WRITE_ONCE(ssp->srcu_idx, ssp->srcu_idx + 1);
+	WRITE_ONCE(ssp->srcu_idx, ssp->srcu_idx + 1); // Flip the counter.
 
 	/*
 	 * Ensure that if the updater misses an __srcu_read_unlock()
@@ -1154,18 +1189,18 @@ static bool srcu_might_be_idle(struct srcu_struct *ssp)
 
 	/* First, see if enough time has passed since the last GP. */
 	t = ktime_get_mono_fast_ns();
-	tlast = READ_ONCE(ssp->srcu_last_gp_end);
+	tlast = READ_ONCE(ssp->srcu_sup->srcu_last_gp_end);
 	if (exp_holdoff == 0 ||
 	    time_in_range_open(t, tlast, tlast + exp_holdoff))
 		return false; /* Too soon after last GP. */
 
 	/* Next, check for probable idleness. */
-	curseq = rcu_seq_current(&ssp->srcu_gp_seq);
+	curseq = rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq);
 	smp_mb(); /* Order ->srcu_gp_seq with ->srcu_gp_seq_needed. */
-	if (ULONG_CMP_LT(curseq, READ_ONCE(ssp->srcu_gp_seq_needed)))
+	if (ULONG_CMP_LT(curseq, READ_ONCE(ssp->srcu_sup->srcu_gp_seq_needed)))
 		return false; /* Grace period in progress, so not idle. */
 	smp_mb(); /* Order ->srcu_gp_seq with prior access. */
-	if (curseq != rcu_seq_current(&ssp->srcu_gp_seq))
+	if (curseq != rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq))
 		return false; /* GP # changed, so not idle. */
 	return true; /* With reasonable probability, idle! */
 }
@@ -1199,7 +1234,7 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp,
 	 * sequence number cannot wrap around in the meantime.
 	 */
 	idx = __srcu_read_lock_nmisafe(ssp);
-	ss_state = smp_load_acquire(&ssp->srcu_size_state);
+	ss_state = smp_load_acquire(&ssp->srcu_sup->srcu_size_state);
 	if (ss_state < SRCU_SIZE_WAIT_CALL)
 		sdp = per_cpu_ptr(ssp->sda, get_boot_cpu_id());
 	else
@@ -1208,8 +1243,8 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp,
 	if (rhp)
 		rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp);
 	rcu_segcblist_advance(&sdp->srcu_cblist,
-			      rcu_seq_current(&ssp->srcu_gp_seq));
-	s = rcu_seq_snap(&ssp->srcu_gp_seq);
+			      rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq));
+	s = rcu_seq_snap(&ssp->srcu_sup->srcu_gp_seq);
 	(void)rcu_segcblist_accelerate(&sdp->srcu_cblist, s);
 	if (ULONG_CMP_LT(sdp->srcu_gp_seq_needed, s)) {
 		sdp->srcu_gp_seq_needed = s;
@@ -1307,6 +1342,8 @@ static void __synchronize_srcu(struct srcu_struct *ssp, bool do_norm)
 {
 	struct rcu_synchronize rcu;
 
+	srcu_lock_sync(&ssp->dep_map);
+
 	RCU_LOCKDEP_WARN(lockdep_is_held(ssp) ||
 			 lock_is_held(&rcu_bh_lock_map) ||
 			 lock_is_held(&rcu_lock_map) ||
@@ -1420,7 +1457,7 @@ unsigned long get_state_synchronize_srcu(struct srcu_struct *ssp)
 	// Any prior manipulation of SRCU-protected data must happen
 	// before the load from ->srcu_gp_seq.
 	smp_mb();
-	return rcu_seq_snap(&ssp->srcu_gp_seq);
+	return rcu_seq_snap(&ssp->srcu_sup->srcu_gp_seq);
 }
 EXPORT_SYMBOL_GPL(get_state_synchronize_srcu);
 
@@ -1467,7 +1504,7 @@ EXPORT_SYMBOL_GPL(start_poll_synchronize_srcu);
  */
 bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie)
 {
-	if (!rcu_seq_done(&ssp->srcu_gp_seq, cookie))
+	if (!rcu_seq_done(&ssp->srcu_sup->srcu_gp_seq, cookie))
 		return false;
 	// Ensure that the end of the SRCU grace period happens before
 	// any subsequent code that the caller might execute.
@@ -1486,8 +1523,8 @@ static void srcu_barrier_cb(struct rcu_head *rhp)
 
 	sdp = container_of(rhp, struct srcu_data, srcu_barrier_head);
 	ssp = sdp->ssp;
-	if (atomic_dec_and_test(&ssp->srcu_barrier_cpu_cnt))
-		complete(&ssp->srcu_barrier_completion);
+	if (atomic_dec_and_test(&ssp->srcu_sup->srcu_barrier_cpu_cnt))
+		complete(&ssp->srcu_sup->srcu_barrier_completion);
 }
 
 /*
@@ -1501,13 +1538,13 @@ static void srcu_barrier_cb(struct rcu_head *rhp)
 static void srcu_barrier_one_cpu(struct srcu_struct *ssp, struct srcu_data *sdp)
 {
 	spin_lock_irq_rcu_node(sdp);
-	atomic_inc(&ssp->srcu_barrier_cpu_cnt);
+	atomic_inc(&ssp->srcu_sup->srcu_barrier_cpu_cnt);
 	sdp->srcu_barrier_head.func = srcu_barrier_cb;
 	debug_rcu_head_queue(&sdp->srcu_barrier_head);
 	if (!rcu_segcblist_entrain(&sdp->srcu_cblist,
 				   &sdp->srcu_barrier_head)) {
 		debug_rcu_head_unqueue(&sdp->srcu_barrier_head);
-		atomic_dec(&ssp->srcu_barrier_cpu_cnt);
+		atomic_dec(&ssp->srcu_sup->srcu_barrier_cpu_cnt);
 	}
 	spin_unlock_irq_rcu_node(sdp);
 }
@@ -1520,23 +1557,23 @@ void srcu_barrier(struct srcu_struct *ssp)
 {
 	int cpu;
 	int idx;
-	unsigned long s = rcu_seq_snap(&ssp->srcu_barrier_seq);
+	unsigned long s = rcu_seq_snap(&ssp->srcu_sup->srcu_barrier_seq);
 
 	check_init_srcu_struct(ssp);
-	mutex_lock(&ssp->srcu_barrier_mutex);
-	if (rcu_seq_done(&ssp->srcu_barrier_seq, s)) {
+	mutex_lock(&ssp->srcu_sup->srcu_barrier_mutex);
+	if (rcu_seq_done(&ssp->srcu_sup->srcu_barrier_seq, s)) {
 		smp_mb(); /* Force ordering following return. */
-		mutex_unlock(&ssp->srcu_barrier_mutex);
+		mutex_unlock(&ssp->srcu_sup->srcu_barrier_mutex);
 		return; /* Someone else did our work for us. */
 	}
-	rcu_seq_start(&ssp->srcu_barrier_seq);
-	init_completion(&ssp->srcu_barrier_completion);
+	rcu_seq_start(&ssp->srcu_sup->srcu_barrier_seq);
+	init_completion(&ssp->srcu_sup->srcu_barrier_completion);
 
 	/* Initial count prevents reaching zero until all CBs are posted. */
-	atomic_set(&ssp->srcu_barrier_cpu_cnt, 1);
+	atomic_set(&ssp->srcu_sup->srcu_barrier_cpu_cnt, 1);
 
 	idx = __srcu_read_lock_nmisafe(ssp);
-	if (smp_load_acquire(&ssp->srcu_size_state) < SRCU_SIZE_WAIT_BARRIER)
+	if (smp_load_acquire(&ssp->srcu_sup->srcu_size_state) < SRCU_SIZE_WAIT_BARRIER)
 		srcu_barrier_one_cpu(ssp, per_cpu_ptr(ssp->sda,	get_boot_cpu_id()));
 	else
 		for_each_possible_cpu(cpu)
@@ -1544,12 +1581,12 @@ void srcu_barrier(struct srcu_struct *ssp)
 	__srcu_read_unlock_nmisafe(ssp, idx);
 
 	/* Remove the initial count, at which point reaching zero can happen. */
-	if (atomic_dec_and_test(&ssp->srcu_barrier_cpu_cnt))
-		complete(&ssp->srcu_barrier_completion);
-	wait_for_completion(&ssp->srcu_barrier_completion);
+	if (atomic_dec_and_test(&ssp->srcu_sup->srcu_barrier_cpu_cnt))
+		complete(&ssp->srcu_sup->srcu_barrier_completion);
+	wait_for_completion(&ssp->srcu_sup->srcu_barrier_completion);
 
-	rcu_seq_end(&ssp->srcu_barrier_seq);
-	mutex_unlock(&ssp->srcu_barrier_mutex);
+	rcu_seq_end(&ssp->srcu_sup->srcu_barrier_seq);
+	mutex_unlock(&ssp->srcu_sup->srcu_barrier_mutex);
 }
 EXPORT_SYMBOL_GPL(srcu_barrier);
 
@@ -1575,7 +1612,7 @@ static void srcu_advance_state(struct srcu_struct *ssp)
 {
 	int idx;
 
-	mutex_lock(&ssp->srcu_gp_mutex);
+	mutex_lock(&ssp->srcu_sup->srcu_gp_mutex);
 
 	/*
 	 * Because readers might be delayed for an extended period after
@@ -1587,39 +1624,39 @@ static void srcu_advance_state(struct srcu_struct *ssp)
 	 * The load-acquire ensures that we see the accesses performed
 	 * by the prior grace period.
 	 */
-	idx = rcu_seq_state(smp_load_acquire(&ssp->srcu_gp_seq)); /* ^^^ */
+	idx = rcu_seq_state(smp_load_acquire(&ssp->srcu_sup->srcu_gp_seq)); /* ^^^ */
 	if (idx == SRCU_STATE_IDLE) {
-		spin_lock_irq_rcu_node(ssp);
-		if (ULONG_CMP_GE(ssp->srcu_gp_seq, ssp->srcu_gp_seq_needed)) {
-			WARN_ON_ONCE(rcu_seq_state(ssp->srcu_gp_seq));
-			spin_unlock_irq_rcu_node(ssp);
-			mutex_unlock(&ssp->srcu_gp_mutex);
+		spin_lock_irq_rcu_node(ssp->srcu_sup);
+		if (ULONG_CMP_GE(ssp->srcu_sup->srcu_gp_seq, ssp->srcu_sup->srcu_gp_seq_needed)) {
+			WARN_ON_ONCE(rcu_seq_state(ssp->srcu_sup->srcu_gp_seq));
+			spin_unlock_irq_rcu_node(ssp->srcu_sup);
+			mutex_unlock(&ssp->srcu_sup->srcu_gp_mutex);
 			return;
 		}
-		idx = rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq));
+		idx = rcu_seq_state(READ_ONCE(ssp->srcu_sup->srcu_gp_seq));
 		if (idx == SRCU_STATE_IDLE)
 			srcu_gp_start(ssp);
-		spin_unlock_irq_rcu_node(ssp);
+		spin_unlock_irq_rcu_node(ssp->srcu_sup);
 		if (idx != SRCU_STATE_IDLE) {
-			mutex_unlock(&ssp->srcu_gp_mutex);
+			mutex_unlock(&ssp->srcu_sup->srcu_gp_mutex);
 			return; /* Someone else started the grace period. */
 		}
 	}
 
-	if (rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)) == SRCU_STATE_SCAN1) {
+	if (rcu_seq_state(READ_ONCE(ssp->srcu_sup->srcu_gp_seq)) == SRCU_STATE_SCAN1) {
 		idx = 1 ^ (ssp->srcu_idx & 1);
 		if (!try_check_zero(ssp, idx, 1)) {
-			mutex_unlock(&ssp->srcu_gp_mutex);
+			mutex_unlock(&ssp->srcu_sup->srcu_gp_mutex);
 			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);
-		ssp->srcu_n_exp_nodelay = 0;
-		spin_unlock_irq_rcu_node(ssp);
+		spin_lock_irq_rcu_node(ssp->srcu_sup);
+		rcu_seq_set_state(&ssp->srcu_sup->srcu_gp_seq, SRCU_STATE_SCAN2);
+		ssp->srcu_sup->srcu_n_exp_nodelay = 0;
+		spin_unlock_irq_rcu_node(ssp->srcu_sup);
 	}
 
-	if (rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)) == SRCU_STATE_SCAN2) {
+	if (rcu_seq_state(READ_ONCE(ssp->srcu_sup->srcu_gp_seq)) == SRCU_STATE_SCAN2) {
 
 		/*
 		 * SRCU read-side critical sections are normally short,
@@ -1627,10 +1664,10 @@ static void srcu_advance_state(struct srcu_struct *ssp)
 		 */
 		idx = 1 ^ (ssp->srcu_idx & 1);
 		if (!try_check_zero(ssp, idx, 2)) {
-			mutex_unlock(&ssp->srcu_gp_mutex);
+			mutex_unlock(&ssp->srcu_sup->srcu_gp_mutex);
 			return; /* readers present, retry later. */
 		}
-		ssp->srcu_n_exp_nodelay = 0;
+		ssp->srcu_sup->srcu_n_exp_nodelay = 0;
 		srcu_gp_end(ssp);  /* Releases ->srcu_gp_mutex. */
 	}
 }
@@ -1656,7 +1693,7 @@ static void srcu_invoke_callbacks(struct work_struct *work)
 	rcu_cblist_init(&ready_cbs);
 	spin_lock_irq_rcu_node(sdp);
 	rcu_segcblist_advance(&sdp->srcu_cblist,
-			      rcu_seq_current(&ssp->srcu_gp_seq));
+			      rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq));
 	if (sdp->srcu_cblist_invoking ||
 	    !rcu_segcblist_ready_cbs(&sdp->srcu_cblist)) {
 		spin_unlock_irq_rcu_node(sdp);
@@ -1684,7 +1721,7 @@ static void srcu_invoke_callbacks(struct work_struct *work)
 	spin_lock_irq_rcu_node(sdp);
 	rcu_segcblist_add_len(&sdp->srcu_cblist, -len);
 	(void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
-				       rcu_seq_snap(&ssp->srcu_gp_seq));
+				       rcu_seq_snap(&ssp->srcu_sup->srcu_gp_seq));
 	sdp->srcu_cblist_invoking = false;
 	more = rcu_segcblist_ready_cbs(&sdp->srcu_cblist);
 	spin_unlock_irq_rcu_node(sdp);
@@ -1700,20 +1737,20 @@ static void srcu_reschedule(struct srcu_struct *ssp, unsigned long delay)
 {
 	bool pushgp = true;
 
-	spin_lock_irq_rcu_node(ssp);
-	if (ULONG_CMP_GE(ssp->srcu_gp_seq, ssp->srcu_gp_seq_needed)) {
-		if (!WARN_ON_ONCE(rcu_seq_state(ssp->srcu_gp_seq))) {
+	spin_lock_irq_rcu_node(ssp->srcu_sup);
+	if (ULONG_CMP_GE(ssp->srcu_sup->srcu_gp_seq, ssp->srcu_sup->srcu_gp_seq_needed)) {
+		if (!WARN_ON_ONCE(rcu_seq_state(ssp->srcu_sup->srcu_gp_seq))) {
 			/* All requests fulfilled, time to go idle. */
 			pushgp = false;
 		}
-	} else if (!rcu_seq_state(ssp->srcu_gp_seq)) {
+	} else if (!rcu_seq_state(ssp->srcu_sup->srcu_gp_seq)) {
 		/* Outstanding request and no GP.  Start one. */
 		srcu_gp_start(ssp);
 	}
-	spin_unlock_irq_rcu_node(ssp);
+	spin_unlock_irq_rcu_node(ssp->srcu_sup);
 
 	if (pushgp)
-		queue_delayed_work(rcu_gp_wq, &ssp->work, delay);
+		queue_delayed_work(rcu_gp_wq, &ssp->srcu_sup->work, delay);
 }
 
 /*
@@ -1724,22 +1761,24 @@ static void process_srcu(struct work_struct *work)
 	unsigned long curdelay;
 	unsigned long j;
 	struct srcu_struct *ssp;
+	struct srcu_usage *sup;
 
-	ssp = container_of(work, struct srcu_struct, work.work);
+	sup = container_of(work, struct srcu_usage, work.work);
+	ssp = sup->srcu_ssp;
 
 	srcu_advance_state(ssp);
 	curdelay = srcu_get_delay(ssp);
 	if (curdelay) {
-		WRITE_ONCE(ssp->reschedule_count, 0);
+		WRITE_ONCE(sup->reschedule_count, 0);
 	} else {
 		j = jiffies;
-		if (READ_ONCE(ssp->reschedule_jiffies) == j) {
-			WRITE_ONCE(ssp->reschedule_count, READ_ONCE(ssp->reschedule_count) + 1);
-			if (READ_ONCE(ssp->reschedule_count) > srcu_max_nodelay)
+		if (READ_ONCE(sup->reschedule_jiffies) == j) {
+			WRITE_ONCE(sup->reschedule_count, READ_ONCE(sup->reschedule_count) + 1);
+			if (READ_ONCE(sup->reschedule_count) > srcu_max_nodelay)
 				curdelay = 1;
 		} else {
-			WRITE_ONCE(ssp->reschedule_count, 1);
-			WRITE_ONCE(ssp->reschedule_jiffies, j);
+			WRITE_ONCE(sup->reschedule_count, 1);
+			WRITE_ONCE(sup->reschedule_jiffies, j);
 		}
 	}
 	srcu_reschedule(ssp, curdelay);
@@ -1752,7 +1791,7 @@ void srcutorture_get_gp_data(enum rcutorture_type test_type,
 	if (test_type != SRCU_FLAVOR)
 		return;
 	*flags = 0;
-	*gp_seq = rcu_seq_current(&ssp->srcu_gp_seq);
+	*gp_seq = rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq);
 }
 EXPORT_SYMBOL_GPL(srcutorture_get_gp_data);
 
@@ -1774,14 +1813,14 @@ void srcu_torture_stats_print(struct srcu_struct *ssp, char *tt, char *tf)
 	int cpu;
 	int idx;
 	unsigned long s0 = 0, s1 = 0;
-	int ss_state = READ_ONCE(ssp->srcu_size_state);
+	int ss_state = READ_ONCE(ssp->srcu_sup->srcu_size_state);
 	int ss_state_idx = ss_state;
 
 	idx = ssp->srcu_idx & 0x1;
 	if (ss_state < 0 || ss_state >= ARRAY_SIZE(srcu_size_state_name))
 		ss_state_idx = ARRAY_SIZE(srcu_size_state_name) - 1;
 	pr_alert("%s%s Tree SRCU g%ld state %d (%s)",
-		 tt, tf, rcu_seq_current(&ssp->srcu_gp_seq), ss_state,
+		 tt, tf, rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq), ss_state,
 		 srcu_size_state_name[ss_state_idx]);
 	if (!ssp->sda) {
 		// Called after cleanup_srcu_struct(), perhaps.
@@ -1838,7 +1877,7 @@ early_initcall(srcu_bootup_announce);
 
 void __init srcu_init(void)
 {
-	struct srcu_struct *ssp;
+	struct srcu_usage *sup;
 
 	/* Decide on srcu_struct-size strategy. */
 	if (SRCU_SIZING_IS(SRCU_SIZING_AUTO)) {
@@ -1858,12 +1897,13 @@ void __init srcu_init(void)
 	 */
 	srcu_init_done = true;
 	while (!list_empty(&srcu_boot_list)) {
-		ssp = list_first_entry(&srcu_boot_list, struct srcu_struct,
+		sup = list_first_entry(&srcu_boot_list, struct srcu_usage,
 				      work.work.entry);
-		list_del_init(&ssp->work.work.entry);
-		if (SRCU_SIZING_IS(SRCU_SIZING_INIT) && ssp->srcu_size_state == SRCU_SIZE_SMALL)
-			ssp->srcu_size_state = SRCU_SIZE_ALLOC;
-		queue_work(rcu_gp_wq, &ssp->work.work);
+		list_del_init(&sup->work.work.entry);
+		if (SRCU_SIZING_IS(SRCU_SIZING_INIT) &&
+		    sup->srcu_size_state == SRCU_SIZE_SMALL)
+			sup->srcu_size_state = SRCU_SIZE_ALLOC;
+		queue_work(rcu_gp_wq, &sup->work.work);
 	}
 }
 
@@ -1873,13 +1913,14 @@ void __init srcu_init(void)
 static int srcu_module_coming(struct module *mod)
 {
 	int i;
+	struct srcu_struct *ssp;
 	struct srcu_struct **sspp = mod->srcu_struct_ptrs;
-	int ret;
 
 	for (i = 0; i < mod->num_srcu_structs; i++) {
-		ret = init_srcu_struct(*(sspp++));
-		if (WARN_ON_ONCE(ret))
-			return ret;
+		ssp = *(sspp++);
+		ssp->sda = alloc_percpu(struct srcu_data);
+		if (WARN_ON_ONCE(!ssp->sda))
+			return -ENOMEM;
 	}
 	return 0;
 }
@@ -1888,10 +1929,17 @@ static int srcu_module_coming(struct module *mod)
 static void srcu_module_going(struct module *mod)
 {
 	int i;
+	struct srcu_struct *ssp;
 	struct srcu_struct **sspp = mod->srcu_struct_ptrs;
 
-	for (i = 0; i < mod->num_srcu_structs; i++)
-		cleanup_srcu_struct(*(sspp++));
+	for (i = 0; i < mod->num_srcu_structs; i++) {
+		ssp = *(sspp++);
+		if (!rcu_seq_state(smp_load_acquire(&ssp->srcu_sup->srcu_gp_seq_needed)) &&
+		    !WARN_ON_ONCE(!ssp->srcu_sup->sda_is_static))
+			cleanup_srcu_struct(ssp);
+		if (!WARN_ON(srcu_readers_active(ssp)))
+			free_percpu(ssp->sda);
+	}
 }
 
 /* Handle one module, either coming or going. */
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index bfb5e1549f2b2..5f4fc8184dd0b 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -136,8 +136,16 @@ static struct rcu_tasks rt_name =							\
 	.kname = #rt_name,								\
 }
 
+#ifdef CONFIG_TASKS_RCU
 /* Track exiting tasks in order to allow them to be waited for. */
 DEFINE_STATIC_SRCU(tasks_rcu_exit_srcu);
+#endif
+
+#ifdef CONFIG_TASKS_RCU
+/* Report delay in synchronize_srcu() completion in rcu_tasks_postscan(). */
+static void tasks_rcu_exit_srcu_stall(struct timer_list *unused);
+static DEFINE_TIMER(tasks_rcu_exit_srcu_stall_timer, tasks_rcu_exit_srcu_stall);
+#endif
 
 /* Avoid IPIing CPUs early in the grace period. */
 #define RCU_TASK_IPI_DELAY (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) ? HZ / 2 : 0)
@@ -830,6 +838,13 @@ static void rcu_tasks_pertask(struct task_struct *t, struct list_head *hop)
 /* Processing between scanning taskslist and draining the holdout list. */
 static void rcu_tasks_postscan(struct list_head *hop)
 {
+	int rtsi = READ_ONCE(rcu_task_stall_info);
+
+	if (!IS_ENABLED(CONFIG_TINY_RCU)) {
+		tasks_rcu_exit_srcu_stall_timer.expires = jiffies + rtsi;
+		add_timer(&tasks_rcu_exit_srcu_stall_timer);
+	}
+
 	/*
 	 * Exiting tasks may escape the tasklist scan. Those are vulnerable
 	 * until their final schedule() with TASK_DEAD state. To cope with
@@ -848,6 +863,9 @@ static void rcu_tasks_postscan(struct list_head *hop)
 	 * call to synchronize_rcu().
 	 */
 	synchronize_srcu(&tasks_rcu_exit_srcu);
+
+	if (!IS_ENABLED(CONFIG_TINY_RCU))
+		del_timer_sync(&tasks_rcu_exit_srcu_stall_timer);
 }
 
 /* See if tasks are still holding out, complain if so. */
@@ -923,6 +941,21 @@ static void rcu_tasks_postgp(struct rcu_tasks *rtp)
 void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func);
 DEFINE_RCU_TASKS(rcu_tasks, rcu_tasks_wait_gp, call_rcu_tasks, "RCU Tasks");
 
+static void tasks_rcu_exit_srcu_stall(struct timer_list *unused)
+{
+#ifndef CONFIG_TINY_RCU
+	int rtsi;
+
+	rtsi = READ_ONCE(rcu_task_stall_info);
+	pr_info("%s: %s grace period number %lu (since boot) gp_state: %s is %lu jiffies old.\n",
+		__func__, rcu_tasks.kname, rcu_tasks.tasks_gp_seq,
+		tasks_gp_state_getname(&rcu_tasks), jiffies - rcu_tasks.gp_jiffies);
+	pr_info("Please check any exiting tasks stuck between calls to exit_tasks_rcu_start() and exit_tasks_rcu_finish()\n");
+	tasks_rcu_exit_srcu_stall_timer.expires = jiffies + rtsi;
+	add_timer(&tasks_rcu_exit_srcu_stall_timer);
+#endif // #ifndef CONFIG_TINY_RCU
+}
+
 /**
  * call_rcu_tasks() - Queue an RCU for invocation task-based grace period
  * @rhp: structure to be used for queueing the RCU updates.
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 7b95ee98a1a53..f52ff72410416 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -640,6 +640,7 @@ void __rcu_irq_enter_check_tick(void)
 	}
 	raw_spin_unlock_rcu_node(rdp->mynode);
 }
+NOKPROBE_SYMBOL(__rcu_irq_enter_check_tick);
 #endif /* CONFIG_NO_HZ_FULL */
 
 /*
@@ -1955,7 +1956,6 @@ rcu_report_qs_rdp(struct rcu_data *rdp)
 {
 	unsigned long flags;
 	unsigned long mask;
-	bool needwake = false;
 	bool needacc = false;
 	struct rcu_node *rnp;
 
@@ -1987,7 +1987,12 @@ rcu_report_qs_rdp(struct rcu_data *rdp)
 		 * NOCB kthreads have their own way to deal with that...
 		 */
 		if (!rcu_rdp_is_offloaded(rdp)) {
-			needwake = rcu_accelerate_cbs(rnp, rdp);
+			/*
+			 * The current GP has not yet ended, so it
+			 * should not be possible for rcu_accelerate_cbs()
+			 * to return true.  So complain, but don't awaken.
+			 */
+			WARN_ON_ONCE(rcu_accelerate_cbs(rnp, rdp));
 		} else if (!rcu_segcblist_completely_offloaded(&rdp->cblist)) {
 			/*
 			 * ...but NOCB kthreads may miss or delay callbacks acceleration
@@ -1999,8 +2004,6 @@ rcu_report_qs_rdp(struct rcu_data *rdp)
 		rcu_disable_urgency_upon_qs(rdp);
 		rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
 		/* ^^^ Released rnp->lock */
-		if (needwake)
-			rcu_gp_kthread_wake();
 
 		if (needacc) {
 			rcu_nocb_lock_irqsave(rdp, flags);
@@ -2131,6 +2134,8 @@ static void rcu_do_batch(struct rcu_data *rdp)
 				break;
 			}
 		} else {
+			// In rcuoc context, so no worries about depriving
+			// other softirq vectors of CPU cycles.
 			local_bh_enable();
 			lockdep_assert_irqs_enabled();
 			cond_resched_tasks_rcu_qs();
@@ -4951,9 +4956,8 @@ void __init rcu_init(void)
 	else
 		qovld_calc = qovld;
 
-	// Kick-start any polled grace periods that started early.
-	if (!(per_cpu_ptr(&rcu_data, cpu)->mynode->exp_seq_poll_rq & 0x1))
-		(void)start_poll_synchronize_rcu_expedited();
+	// Kick-start in case any polled grace periods started early.
+	(void)start_poll_synchronize_rcu_expedited();
 
 	rcu_test_sync_prims();
 }
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 249c2967d9e6c..3b7abb58157df 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -594,6 +594,7 @@ static void synchronize_rcu_expedited_wait(void)
 	struct rcu_data *rdp;
 	struct rcu_node *rnp;
 	struct rcu_node *rnp_root = rcu_get_root();
+	unsigned long flags;
 
 	trace_rcu_exp_grace_period(rcu_state.name, rcu_exp_gp_seq_endval(), TPS("startwait"));
 	jiffies_stall = rcu_exp_jiffies_till_stall_check();
@@ -602,17 +603,17 @@ static void synchronize_rcu_expedited_wait(void)
 		if (synchronize_rcu_expedited_wait_once(1))
 			return;
 		rcu_for_each_leaf_node(rnp) {
+			raw_spin_lock_irqsave_rcu_node(rnp, flags);
 			mask = READ_ONCE(rnp->expmask);
 			for_each_leaf_node_cpu_mask(rnp, cpu, mask) {
 				rdp = per_cpu_ptr(&rcu_data, cpu);
 				if (rdp->rcu_forced_tick_exp)
 					continue;
 				rdp->rcu_forced_tick_exp = true;
-				preempt_disable();
 				if (cpu_online(cpu))
 					tick_dep_set_cpu(cpu, TICK_DEP_BIT_RCU_EXP);
-				preempt_enable();
 			}
+			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		}
 		j = READ_ONCE(jiffies_till_first_fqs);
 		if (synchronize_rcu_expedited_wait_once(j + HZ))
@@ -802,9 +803,11 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp)
 	int ndetected = 0;
 	struct task_struct *t;
 
-	if (!READ_ONCE(rnp->exp_tasks))
-		return 0;
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
+	if (!rnp->exp_tasks) {
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+		return 0;
+	}
 	t = list_entry(rnp->exp_tasks->prev,
 		       struct task_struct, rcu_node_entry);
 	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
@@ -1065,9 +1068,10 @@ unsigned long start_poll_synchronize_rcu_expedited(void)
 	if (rcu_init_invoked())
 		raw_spin_lock_irqsave(&rnp->exp_poll_lock, flags);
 	if (!poll_state_synchronize_rcu(s)) {
-		rnp->exp_seq_poll_rq = s;
-		if (rcu_init_invoked())
+		if (rcu_init_invoked()) {
+			rnp->exp_seq_poll_rq = s;
 			queue_work(rcu_gp_wq, &rnp->exp_poll_wq);
+		}
 	}
 	if (rcu_init_invoked())
 		raw_spin_unlock_irqrestore(&rnp->exp_poll_lock, flags);
diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
index 9e1c8caec5ceb..f2280616f9d51 100644
--- a/kernel/rcu/tree_nocb.h
+++ b/kernel/rcu/tree_nocb.h
@@ -1312,6 +1312,7 @@ int rcu_nocb_cpu_offload(int cpu)
 }
 EXPORT_SYMBOL_GPL(rcu_nocb_cpu_offload);
 
+#ifdef CONFIG_RCU_LAZY
 static unsigned long
 lazy_rcu_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
 {
@@ -1360,6 +1361,7 @@ static struct shrinker lazy_rcu_shrinker = {
 	.batch = 0,
 	.seeks = DEFAULT_SEEKS,
 };
+#endif // #ifdef CONFIG_RCU_LAZY
 
 void __init rcu_init_nohz(void)
 {
@@ -1391,8 +1393,10 @@ void __init rcu_init_nohz(void)
 	if (!rcu_state.nocb_is_setup)
 		return;
 
+#ifdef CONFIG_RCU_LAZY
 	if (register_shrinker(&lazy_rcu_shrinker, "rcu-lazy"))
 		pr_err("Failed to register lazy_rcu shrinker!\n");
+#endif // #ifdef CONFIG_RCU_LAZY
 
 	if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) {
 		pr_info("\tNote: kernel parameter 'rcu_nocbs=', 'nohz_full', or 'isolcpus=' contains nonexistent CPUs.\n");