Merge tag 'rcu.release.v6.13' of git://git.kernel.org/pub/scm/linux/kernel/git/rcu/linux

Pull RCU updates from Frederic Weisbecker:
 "SRCU:

   - Introduction of the new SRCU-lite flavour with a new pair of
     srcu_read_[un]lock_lite() APIs. In practice the read side using
     this flavour becomes lighter by removing a full memory barrier on
     LOCK and a full memory barrier on UNLOCK. This comes at the expense
     of a higher latency write side with two (in the best case of a
     snaphot of unused read-sides) or more RCU grace periods on the
     update side which now assumes by itself the whole full ordering
     guarantee against the LOCK/UNLOCK counters on both indexes, along
     with the accesses performed inside.

     Uretprobes is a known potential user.

     Note this doesn't replace the default normal flavour of SRCU which
     still behaves the same as usual.

   - Add testing of SRCU-lite through rcutorture and rcuscale

   - Various cleanups on the way.

  Fixes:

   - Allow short-circuiting RCU-TASKS-RUDE grace periods on
     architectures that have sane noinstr boundaries forbidding tracing
     on low-level idle and kernel entry code. RCU-TASKS is enough on
     such configurations because it involves an RCU grace period that
     waits for all idle tasks to either schedule out voluntarily or
     enter into RCU unwatched noinstr code.

   - Allow and test start_poll_synchronize_rcu() with IRQs disabled.

   - Mention rcuog kthreads in relevant documentation and Kconfig help

   - Various fixes and consolidations

  rcutorture:

   - Add --no-affinity on tools to leave the affinity setting of guests
     up to the user.

   - Add guest_os_delay parameter to rcuscale for better warm-up
     control.

   - Fix and improve some rcuscale error handling.

   - Various cleanups and fixes

  stall:

   - Remove dead code

   - Stop dumping tasks if a stalled grace period eventually ended
     midway as that only produces confusing output.

   - Optimize detection of stalling CPUs and avoid useless node locking
     otherwise.

  NOCB:

   - Fix rcu_barrier() hang due to a race against callbacks
     deoffloading. This is not yet used, except by rcutorture, and waits
     for its promised cpusets interface.

   - Remove leftover function declaration"

* tag 'rcu.release.v6.13' of git://git.kernel.org/pub/scm/linux/kernel/git/rcu/linux: (42 commits)
  rcuscale: Remove redundant WARN_ON_ONCE() splat
  rcuscale: Do a proper cleanup if kfree_scale_init() fails
  srcu: Unconditionally record srcu_read_lock_lite() in ->srcu_reader_flavor
  srcu: Check for srcu_read_lock_lite() across all CPUs
  srcu: Remove smp_mb() from srcu_read_unlock_lite()
  rcutorture: Avoid printing cpu=-1 for no-fault RCU boost failure
  rcuscale: Add guest_os_delay module parameter
  refscale: Correct affinity check
  torture: Add --no-affinity parameter to kvm.sh
  rcu/nocb: Fix missed RCU barrier on deoffloading
  rcu/kvfree: Fix data-race in __mod_timer / kvfree_call_rcu
  rcu/srcutiny: don't return before reenabling preemption
  rcu-tasks: Remove open-coded one-byte cmpxchg() emulation
  doc: Remove kernel-parameters.txt entry for rcutorture.read_exit
  rcutorture: Test start-poll primitives with interrupts disabled
  rcu: Permit start_poll_synchronize_rcu*() with interrupts disabled
  rcu: Allow short-circuiting of synchronize_rcu_tasks_rude()
  doc: Add rcuog kthreads to kernel-per-CPU-kthreads.rst
  rcu: Add rcuog kthreads to RCU_NOCB_CPU help text
  rcu: Use the BITS_PER_LONG macro
  ...

12 files changed, 275 insertions, 173 deletions

diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig
index 3e079de0f5b4..b9b6bc55185d 100644
--- a/kernel/rcu/Kconfig
+++ b/kernel/rcu/Kconfig
@@ -249,16 +249,24 @@ config RCU_NOCB_CPU
 	  workloads will incur significant increases in context-switch
 	  rates.
 
-	  This option offloads callback invocation from the set of CPUs
-	  specified at boot time by the rcu_nocbs parameter.  For each
-	  such CPU, a kthread ("rcuox/N") will be created to invoke
-	  callbacks, where the "N" is the CPU being offloaded, and where
-	  the "x" is "p" for RCU-preempt (PREEMPTION kernels) and "s" for
-	  RCU-sched (!PREEMPTION kernels).  Nothing prevents this kthread
-	  from running on the specified CPUs, but (1) the kthreads may be
-	  preempted between each callback, and (2) affinity or cgroups can
-	  be used to force the kthreads to run on whatever set of CPUs is
-	  desired.
+	  This option offloads callback invocation from the set of
+	  CPUs specified at boot time by the rcu_nocbs parameter.
+	  For each such CPU, a kthread ("rcuox/N") will be created to
+	  invoke callbacks, where the "N" is the CPU being offloaded,
+	  and where the "x" is "p" for RCU-preempt (PREEMPTION kernels)
+	  and "s" for RCU-sched (!PREEMPTION kernels).	This option
+	  also creates another kthread for each sqrt(nr_cpu_ids) CPUs
+	  ("rcuog/N", where N is the first CPU in that group to come
+	  online), which handles grace periods for its group.  Nothing
+	  prevents these kthreads from running on the specified CPUs,
+	  but (1) the kthreads may be preempted between each callback,
+	  and (2) affinity or cgroups can be used to force the kthreads
+	  to run on whatever set of CPUs is desired.
+
+	  The sqrt(nr_cpu_ids) grouping may be overridden using the
+	  rcutree.rcu_nocb_gp_stride kernel boot parameter.  This can
+	  be especially helpful for smaller numbers of CPUs, where
+	  sqrt(nr_cpu_ids) can be a bit of a blunt instrument.
 
 	  Say Y here if you need reduced OS jitter, despite added overhead.
 	  Say N here if you are unsure.
diff --git a/kernel/rcu/rcu_segcblist.h b/kernel/rcu/rcu_segcblist.h
index 259904075636..fadc08ad4b7b 100644
--- a/kernel/rcu/rcu_segcblist.h
+++ b/kernel/rcu/rcu_segcblist.h
@@ -120,7 +120,6 @@ void rcu_segcblist_inc_len(struct rcu_segcblist *rsclp);
 void rcu_segcblist_add_len(struct rcu_segcblist *rsclp, long v);
 void rcu_segcblist_init(struct rcu_segcblist *rsclp);
 void rcu_segcblist_disable(struct rcu_segcblist *rsclp);
-void rcu_segcblist_offload(struct rcu_segcblist *rsclp, bool offload);
 bool rcu_segcblist_ready_cbs(struct rcu_segcblist *rsclp);
 bool rcu_segcblist_pend_cbs(struct rcu_segcblist *rsclp);
 struct rcu_head *rcu_segcblist_first_cb(struct rcu_segcblist *rsclp);
diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c
index 6d37596deb1f..0f3059b1b80d 100644
--- a/kernel/rcu/rcuscale.c
+++ b/kernel/rcu/rcuscale.c
@@ -889,14 +889,14 @@ kfree_scale_init(void)
 
 		if (WARN_ON_ONCE(jiffies_at_lazy_cb - jif_start < 2 * HZ)) {
 			pr_alert("ERROR: call_rcu() CBs are not being lazy as expected!\n");
-			WARN_ON_ONCE(1);
-			return -1;
+			firsterr = -1;
+			goto unwind;
 		}
 
 		if (WARN_ON_ONCE(jiffies_at_lazy_cb - jif_start > 3 * HZ)) {
 			pr_alert("ERROR: call_rcu() CBs are being too lazy!\n");
-			WARN_ON_ONCE(1);
-			return -1;
+			firsterr = -1;
+			goto unwind;
 		}
 	}
 
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index bb75dbf5c800..2ae8a5e5e99a 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -57,9 +57,9 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com> and Josh Triplett <josh@
 
 /* Bits for ->extendables field, extendables param, and related definitions. */
 #define RCUTORTURE_RDR_SHIFT_1	 8	/* Put SRCU index in upper bits. */
-#define RCUTORTURE_RDR_MASK_1	 (1 << RCUTORTURE_RDR_SHIFT_1)
-#define RCUTORTURE_RDR_SHIFT_2	 9	/* Put SRCU index in upper bits. */
-#define RCUTORTURE_RDR_MASK_2	 (1 << RCUTORTURE_RDR_SHIFT_2)
+#define RCUTORTURE_RDR_MASK_1	 (0xff << RCUTORTURE_RDR_SHIFT_1)
+#define RCUTORTURE_RDR_SHIFT_2	 16	/* Put SRCU index in upper bits. */
+#define RCUTORTURE_RDR_MASK_2	 (0xff << RCUTORTURE_RDR_SHIFT_2)
 #define RCUTORTURE_RDR_BH	 0x01	/* Extend readers by disabling bh. */
 #define RCUTORTURE_RDR_IRQ	 0x02	/*  ... disabling interrupts. */
 #define RCUTORTURE_RDR_PREEMPT	 0x04	/*  ... disabling preemption. */
@@ -71,6 +71,9 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com> and Josh Triplett <josh@
 #define RCUTORTURE_MAX_EXTEND	 \
 	(RCUTORTURE_RDR_BH | RCUTORTURE_RDR_IRQ | RCUTORTURE_RDR_PREEMPT | \
 	 RCUTORTURE_RDR_RBH | RCUTORTURE_RDR_SCHED)
+#define RCUTORTURE_RDR_ALLBITS	\
+	(RCUTORTURE_MAX_EXTEND | RCUTORTURE_RDR_RCU_1 | RCUTORTURE_RDR_RCU_2 | \
+	 RCUTORTURE_RDR_MASK_1 | RCUTORTURE_RDR_MASK_2)
 #define RCUTORTURE_RDR_MAX_LOOPS 0x7	/* Maximum reader extensions. */
 					/* Must be power of two minus one. */
 #define RCUTORTURE_RDR_MAX_SEGS (RCUTORTURE_RDR_MAX_LOOPS + 3)
@@ -108,6 +111,7 @@ torture_param(int, nocbs_nthreads, 0, "Number of NOCB toggle threads, 0 to disab
 torture_param(int, nocbs_toggle, 1000, "Time between toggling nocb state (ms)");
 torture_param(int, read_exit_delay, 13, "Delay between read-then-exit episodes (s)");
 torture_param(int, read_exit_burst, 16, "# of read-then-exit bursts per episode, zero to disable");
+torture_param(int, reader_flavor, 0x1, "Reader flavors to use, one per bit.");
 torture_param(int, shuffle_interval, 3, "Number of seconds between shuffles");
 torture_param(int, shutdown_secs, 0, "Shutdown time (s), <= zero to disable.");
 torture_param(int, stall_cpu, 0, "Stall duration (s), zero to disable.");
@@ -393,6 +397,7 @@ struct rcu_torture_ops {
 	int slow_gps;
 	int no_pi_lock;
 	int debug_objects;
+	int start_poll_irqsoff;
 	const char *name;
 };
 
@@ -581,6 +586,7 @@ static struct rcu_torture_ops rcu_ops = {
 	.can_boost		= IS_ENABLED(CONFIG_RCU_BOOST),
 	.extendables		= RCUTORTURE_MAX_EXTEND,
 	.debug_objects		= 1,
+	.start_poll_irqsoff	= 1,
 	.name			= "rcu"
 };
 
@@ -641,10 +647,25 @@ static void srcu_get_gp_data(int *flags, unsigned long *gp_seq)
 
 static int srcu_torture_read_lock(void)
 {
-	if (cur_ops == &srcud_ops)
-		return srcu_read_lock_nmisafe(srcu_ctlp);
-	else
-		return srcu_read_lock(srcu_ctlp);
+	int idx;
+	int ret = 0;
+
+	if ((reader_flavor & 0x1) || !(reader_flavor & 0x7)) {
+		idx = srcu_read_lock(srcu_ctlp);
+		WARN_ON_ONCE(idx & ~0x1);
+		ret += idx;
+	}
+	if (reader_flavor & 0x2) {
+		idx = srcu_read_lock_nmisafe(srcu_ctlp);
+		WARN_ON_ONCE(idx & ~0x1);
+		ret += idx << 1;
+	}
+	if (reader_flavor & 0x4) {
+		idx = srcu_read_lock_lite(srcu_ctlp);
+		WARN_ON_ONCE(idx & ~0x1);
+		ret += idx << 2;
+	}
+	return ret;
 }
 
 static void
@@ -668,10 +689,13 @@ srcu_read_delay(struct torture_random_state *rrsp, struct rt_read_seg *rtrsp)
 
 static void srcu_torture_read_unlock(int idx)
 {
-	if (cur_ops == &srcud_ops)
-		srcu_read_unlock_nmisafe(srcu_ctlp, idx);
-	else
-		srcu_read_unlock(srcu_ctlp, idx);
+	WARN_ON_ONCE((reader_flavor && (idx & ~reader_flavor)) || (!reader_flavor && (idx & ~0x1)));
+	if (reader_flavor & 0x4)
+		srcu_read_unlock_lite(srcu_ctlp, (idx & 0x4) >> 2);
+	if (reader_flavor & 0x2)
+		srcu_read_unlock_nmisafe(srcu_ctlp, (idx & 0x2) >> 1);
+	if ((reader_flavor & 0x1) || !(reader_flavor & 0x7))
+		srcu_read_unlock(srcu_ctlp, idx & 0x1);
 }
 
 static int torture_srcu_read_lock_held(void)
@@ -1059,8 +1083,13 @@ static bool rcu_torture_boost_failed(unsigned long gp_state, unsigned long *star
 			// At most one persisted message per boost test.
 			j = jiffies;
 			lp = READ_ONCE(last_persist);
-			if (time_after(j, lp + mininterval) && cmpxchg(&last_persist, lp, j) == lp)
-				pr_info("Boost inversion persisted: No QS from CPU %d\n", cpu);
+			if (time_after(j, lp + mininterval) &&
+			    cmpxchg(&last_persist, lp, j) == lp) {
+				if (cpu < 0)
+					pr_info("Boost inversion persisted: QS from all CPUs\n");
+				else
+					pr_info("Boost inversion persisted: No QS from CPU %d\n", cpu);
+			}
 			return false; // passed on a technicality
 		}
 		VERBOSE_TOROUT_STRING("rcu_torture_boost boosting failed");
@@ -1695,14 +1724,22 @@ rcu_torture_fakewriter(void *arg)
 				cur_ops->cond_sync_exp_full(&gp_snap_full);
 				break;
 			case RTWS_POLL_GET:
+				if (cur_ops->start_poll_irqsoff)
+					local_irq_disable();
 				gp_snap = cur_ops->start_gp_poll();
+				if (cur_ops->start_poll_irqsoff)
+					local_irq_enable();
 				while (!cur_ops->poll_gp_state(gp_snap)) {
 					torture_hrtimeout_jiffies(torture_random(&rand) % 16,
 								  &rand);
 				}
 				break;
 			case RTWS_POLL_GET_FULL:
+				if (cur_ops->start_poll_irqsoff)
+					local_irq_disable();
 				cur_ops->start_gp_poll_full(&gp_snap_full);
+				if (cur_ops->start_poll_irqsoff)
+					local_irq_enable();
 				while (!cur_ops->poll_gp_state_full(&gp_snap_full)) {
 					torture_hrtimeout_jiffies(torture_random(&rand) % 16,
 								  &rand);
@@ -1820,7 +1857,7 @@ static void rcutorture_one_extend(int *readstate, int newstate,
 	int statesold = *readstate & ~newstate;
 
 	WARN_ON_ONCE(idxold2 < 0);
-	WARN_ON_ONCE((idxold2 >> RCUTORTURE_RDR_SHIFT_2) > 1);
+	WARN_ON_ONCE(idxold2 & ~RCUTORTURE_RDR_ALLBITS);
 	rtrsp->rt_readstate = newstate;
 
 	/* First, put new protection in place to avoid critical-section gap. */
@@ -1835,9 +1872,9 @@ static void rcutorture_one_extend(int *readstate, int newstate,
 	if (statesnew & RCUTORTURE_RDR_SCHED)
 		rcu_read_lock_sched();
 	if (statesnew & RCUTORTURE_RDR_RCU_1)
-		idxnew1 = (cur_ops->readlock() & 0x1) << RCUTORTURE_RDR_SHIFT_1;
+		idxnew1 = (cur_ops->readlock() << RCUTORTURE_RDR_SHIFT_1) & RCUTORTURE_RDR_MASK_1;
 	if (statesnew & RCUTORTURE_RDR_RCU_2)
-		idxnew2 = (cur_ops->readlock() & 0x1) << RCUTORTURE_RDR_SHIFT_2;
+		idxnew2 = (cur_ops->readlock() << RCUTORTURE_RDR_SHIFT_2) & RCUTORTURE_RDR_MASK_2;
 
 	/*
 	 * Next, remove old protection, in decreasing order of strength
@@ -1857,7 +1894,7 @@ static void rcutorture_one_extend(int *readstate, int newstate,
 	if (statesold & RCUTORTURE_RDR_RBH)
 		rcu_read_unlock_bh();
 	if (statesold & RCUTORTURE_RDR_RCU_2) {
-		cur_ops->readunlock((idxold2 >> RCUTORTURE_RDR_SHIFT_2) & 0x1);
+		cur_ops->readunlock((idxold2 & RCUTORTURE_RDR_MASK_2) >> RCUTORTURE_RDR_SHIFT_2);
 		WARN_ON_ONCE(idxnew2 != -1);
 		idxold2 = 0;
 	}
@@ -1867,7 +1904,7 @@ static void rcutorture_one_extend(int *readstate, int newstate,
 		lockit = !cur_ops->no_pi_lock && !statesnew && !(torture_random(trsp) & 0xffff);
 		if (lockit)
 			raw_spin_lock_irqsave(&current->pi_lock, flags);
-		cur_ops->readunlock((idxold1 >> RCUTORTURE_RDR_SHIFT_1) & 0x1);
+		cur_ops->readunlock((idxold1 & RCUTORTURE_RDR_MASK_1) >> RCUTORTURE_RDR_SHIFT_1);
 		WARN_ON_ONCE(idxnew1 != -1);
 		idxold1 = 0;
 		if (lockit)
@@ -1882,16 +1919,13 @@ static void rcutorture_one_extend(int *readstate, int newstate,
 	if (idxnew1 == -1)
 		idxnew1 = idxold1 & RCUTORTURE_RDR_MASK_1;
 	WARN_ON_ONCE(idxnew1 < 0);
-	if (WARN_ON_ONCE((idxnew1 >> RCUTORTURE_RDR_SHIFT_1) > 1))
-		pr_info("Unexpected idxnew1 value of %#x\n", idxnew1);
 	if (idxnew2 == -1)
 		idxnew2 = idxold2 & RCUTORTURE_RDR_MASK_2;
 	WARN_ON_ONCE(idxnew2 < 0);
-	WARN_ON_ONCE((idxnew2 >> RCUTORTURE_RDR_SHIFT_2) > 1);
 	*readstate = idxnew1 | idxnew2 | newstate;
 	WARN_ON_ONCE(*readstate < 0);
-	if (WARN_ON_ONCE((*readstate >> RCUTORTURE_RDR_SHIFT_2) > 1))
-		pr_info("Unexpected idxnew2 value of %#x\n", idxnew2);
+	if (WARN_ON_ONCE(*readstate & ~RCUTORTURE_RDR_ALLBITS))
+		pr_info("Unexpected readstate value of %#x\n", *readstate);
 }
 
 /* Return the biggest extendables mask given current RCU and boot parameters. */
@@ -1916,7 +1950,7 @@ rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp)
 	unsigned long preempts_irq = preempts | RCUTORTURE_RDR_IRQ;
 	unsigned long bhs = RCUTORTURE_RDR_BH | RCUTORTURE_RDR_RBH;
 
-	WARN_ON_ONCE(mask >> RCUTORTURE_RDR_SHIFT_1);
+	WARN_ON_ONCE(mask >> RCUTORTURE_RDR_SHIFT_1);  // Can't have reader idx bits.
 	/* Mostly only one bit (need preemption!), sometimes lots of bits. */
 	if (!(randmask1 & 0x7))
 		mask = mask & randmask2;
@@ -2389,6 +2423,7 @@ 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 "
+		 "reader_flavor=%x "
 		 "nocbs_nthreads=%d nocbs_toggle=%d "
 		 "test_nmis=%d\n",
 		 torture_type, tag, nrealreaders, nfakewriters,
@@ -2401,6 +2436,7 @@ 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,
+		 reader_flavor,
 		 nocbs_nthreads, nocbs_toggle,
 		 test_nmis);
 }
diff --git a/kernel/rcu/refscale.c b/kernel/rcu/refscale.c
index 0db9db73f57f..aacfcc9838b3 100644
--- a/kernel/rcu/refscale.c
+++ b/kernel/rcu/refscale.c
@@ -75,6 +75,9 @@ MODULE_PARM_DESC(scale_type, "Type of test (rcu, srcu, refcnt, rwsem, rwlock.");
 torture_param(int, verbose, 0, "Enable verbose debugging printk()s");
 torture_param(int, verbose_batched, 0, "Batch verbose debugging printk()s");
 
+// Number of seconds to extend warm-up and cool-down for multiple guest OSes
+torture_param(long, guest_os_delay, 0,
+	      "Number of seconds to extend warm-up/cool-down for multiple guest OSes.");
 // Wait until there are multiple CPUs before starting test.
 torture_param(int, holdoff, IS_BUILTIN(CONFIG_RCU_REF_SCALE_TEST) ? 10 : 0,
 	      "Holdoff time before test start (s)");
@@ -212,6 +215,36 @@ static const struct ref_scale_ops srcu_ops = {
 	.name		= "srcu"
 };
 
+static void srcu_lite_ref_scale_read_section(const int nloops)
+{
+	int i;
+	int idx;
+
+	for (i = nloops; i >= 0; i--) {
+		idx = srcu_read_lock_lite(srcu_ctlp);
+		srcu_read_unlock_lite(srcu_ctlp, idx);
+	}
+}
+
+static void srcu_lite_ref_scale_delay_section(const int nloops, const int udl, const int ndl)
+{
+	int i;
+	int idx;
+
+	for (i = nloops; i >= 0; i--) {
+		idx = srcu_read_lock_lite(srcu_ctlp);
+		un_delay(udl, ndl);
+		srcu_read_unlock_lite(srcu_ctlp, idx);
+	}
+}
+
+static const struct ref_scale_ops srcu_lite_ops = {
+	.init		= rcu_sync_scale_init,
+	.readsection	= srcu_lite_ref_scale_read_section,
+	.delaysection	= srcu_lite_ref_scale_delay_section,
+	.name		= "srcu-lite"
+};
+
 #ifdef CONFIG_TASKS_RCU
 
 // Definitions for RCU Tasks ref scale testing: Empty read markers.
@@ -801,6 +834,18 @@ static void rcu_scale_one_reader(void)
 		cur_ops->delaysection(loops, readdelay / 1000, readdelay % 1000);
 }
 
+// Warm up cache, or, if needed run a series of rcu_scale_one_reader()
+// to allow multiple rcuscale guest OSes to collect mutually valid data.
+static void rcu_scale_warm_cool(void)
+{
+	unsigned long jdone = jiffies + (guest_os_delay > 0 ? guest_os_delay * HZ : -1);
+
+	do {
+		rcu_scale_one_reader();
+		cond_resched();
+	} while (time_before(jiffies, jdone));
+}
+
 // Reader kthread.  Repeatedly does empty RCU read-side
 // critical section, minimizing update-side interference.
 static int
@@ -829,7 +874,7 @@ repeat:
 		goto end;
 
 	// Make sure that the CPU is affinitized appropriately during testing.
-	WARN_ON_ONCE(raw_smp_processor_id() != me);
+	WARN_ON_ONCE(raw_smp_processor_id() != me % nr_cpu_ids);
 
 	WRITE_ONCE(rt->start_reader, 0);
 	if (!atomic_dec_return(&n_started))
@@ -957,6 +1002,7 @@ static int main_func(void *arg)
 		schedule_timeout_uninterruptible(1);
 
 	// Start exp readers up per experiment
+	rcu_scale_warm_cool();
 	for (exp = 0; exp < nruns && !torture_must_stop(); exp++) {
 		if (torture_must_stop())
 			goto end;
@@ -987,6 +1033,7 @@ static int main_func(void *arg)
 
 		result_avg[exp] = div_u64(1000 * process_durations(nreaders), nreaders * loops);
 	}
+	rcu_scale_warm_cool();
 
 	// Print the average of all experiments
 	SCALEOUT("END OF TEST. Calculating average duration per loop (nanoseconds)...\n");
@@ -1082,9 +1129,10 @@ ref_scale_init(void)
 	long i;
 	int firsterr = 0;
 	static const struct ref_scale_ops *scale_ops[] = {
-		&rcu_ops, &srcu_ops, RCU_TRACE_OPS RCU_TASKS_OPS &refcnt_ops, &rwlock_ops,
-		&rwsem_ops, &lock_ops, &lock_irq_ops, &acqrel_ops, &clock_ops, &jiffies_ops,
-		&typesafe_ref_ops, &typesafe_lock_ops, &typesafe_seqlock_ops,
+		&rcu_ops, &srcu_ops, &srcu_lite_ops, RCU_TRACE_OPS RCU_TASKS_OPS
+		&refcnt_ops, &rwlock_ops, &rwsem_ops, &lock_ops, &lock_irq_ops, &acqrel_ops,
+		&clock_ops, &jiffies_ops, &typesafe_ref_ops, &typesafe_lock_ops,
+		&typesafe_seqlock_ops,
 	};
 
 	if (!torture_init_begin(scale_type, verbose))
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index 549c03336ee9..4dcbf8aa80ff 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -122,8 +122,8 @@ void srcu_drive_gp(struct work_struct *wp)
 	ssp = container_of(wp, struct srcu_struct, srcu_work);
 	preempt_disable();  // Needed for PREEMPT_AUTO
 	if (ssp->srcu_gp_running || ULONG_CMP_GE(ssp->srcu_idx, READ_ONCE(ssp->srcu_idx_max))) {
-		return; /* Already running or nothing to do. */
 		preempt_enable();
+		return; /* Already running or nothing to do. */
 	}
 
 	/* Remove recently arrived callbacks and wait for readers. */
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 31706e3293bc..5e2e53464794 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -128,7 +128,7 @@ static void init_srcu_struct_data(struct srcu_struct *ssp)
 	 * Initialize the per-CPU srcu_data array, which feeds into the
 	 * leaves of the srcu_node tree.
 	 */
-	WARN_ON_ONCE(ARRAY_SIZE(sdp->srcu_lock_count) !=
+	BUILD_BUG_ON(ARRAY_SIZE(sdp->srcu_lock_count) !=
 		     ARRAY_SIZE(sdp->srcu_unlock_count));
 	for_each_possible_cpu(cpu) {
 		sdp = per_cpu_ptr(ssp->sda, cpu);
@@ -187,7 +187,7 @@ static bool init_srcu_struct_nodes(struct srcu_struct *ssp, gfp_t gfp_flags)
 	/* Each pass through this loop initializes one srcu_node structure. */
 	srcu_for_each_node_breadth_first(ssp, snp) {
 		spin_lock_init(&ACCESS_PRIVATE(snp, lock));
-		WARN_ON_ONCE(ARRAY_SIZE(snp->srcu_have_cbs) !=
+		BUILD_BUG_ON(ARRAY_SIZE(snp->srcu_have_cbs) !=
 			     ARRAY_SIZE(snp->srcu_data_have_cbs));
 		for (i = 0; i < ARRAY_SIZE(snp->srcu_have_cbs); i++) {
 			snp->srcu_have_cbs[i] = SRCU_SNP_INIT_SEQ;
@@ -419,41 +419,60 @@ static void check_init_srcu_struct(struct srcu_struct *ssp)
 }
 
 /*
- * Returns approximate total of the readers' ->srcu_lock_count[] values
- * for the rank of per-CPU counters specified by idx.
+ * Is the current or any upcoming grace period to be expedited?
  */
-static unsigned long srcu_readers_lock_idx(struct srcu_struct *ssp, int idx)
+static bool srcu_gp_is_expedited(struct srcu_struct *ssp)
+{
+	struct srcu_usage *sup = ssp->srcu_sup;
+
+	return ULONG_CMP_LT(READ_ONCE(sup->srcu_gp_seq), READ_ONCE(sup->srcu_gp_seq_needed_exp));
+}
+
+/*
+ * Computes approximate total of the readers' ->srcu_lock_count[] values
+ * for the rank of per-CPU counters specified by idx, and returns true if
+ * the caller did the proper barrier (gp), and if the count of the locks
+ * matches that of the unlocks passed in.
+ */
+static bool srcu_readers_lock_idx(struct srcu_struct *ssp, int idx, bool gp, unsigned long unlocks)
 {
 	int cpu;
+	unsigned long mask = 0;
 	unsigned long sum = 0;
 
 	for_each_possible_cpu(cpu) {
-		struct srcu_data *cpuc = per_cpu_ptr(ssp->sda, cpu);
+		struct srcu_data *sdp = per_cpu_ptr(ssp->sda, cpu);
 
-		sum += atomic_long_read(&cpuc->srcu_lock_count[idx]);
+		sum += atomic_long_read(&sdp->srcu_lock_count[idx]);
+		if (IS_ENABLED(CONFIG_PROVE_RCU))
+			mask = mask | READ_ONCE(sdp->srcu_reader_flavor);
 	}
-	return sum;
+	WARN_ONCE(IS_ENABLED(CONFIG_PROVE_RCU) && (mask & (mask - 1)),
+		  "Mixed reader flavors for srcu_struct at %ps.\n", ssp);
+	if (mask & SRCU_READ_FLAVOR_LITE && !gp)
+		return false;
+	return sum == unlocks;
 }
 
 /*
  * Returns approximate total of the readers' ->srcu_unlock_count[] values
  * for the rank of per-CPU counters specified by idx.
  */
-static unsigned long srcu_readers_unlock_idx(struct srcu_struct *ssp, int idx)
+static unsigned long srcu_readers_unlock_idx(struct srcu_struct *ssp, int idx, unsigned long *rdm)
 {
 	int cpu;
 	unsigned long mask = 0;
 	unsigned long sum = 0;
 
 	for_each_possible_cpu(cpu) {
-		struct srcu_data *cpuc = per_cpu_ptr(ssp->sda, cpu);
+		struct srcu_data *sdp = per_cpu_ptr(ssp->sda, cpu);
 
-		sum += atomic_long_read(&cpuc->srcu_unlock_count[idx]);
-		if (IS_ENABLED(CONFIG_PROVE_RCU))
-			mask = mask | READ_ONCE(cpuc->srcu_nmi_safety);
+		sum += atomic_long_read(&sdp->srcu_unlock_count[idx]);
+		mask = mask | READ_ONCE(sdp->srcu_reader_flavor);
 	}
-	WARN_ONCE(IS_ENABLED(CONFIG_PROVE_RCU) && (mask & (mask >> 1)),
-		  "Mixed NMI-safe readers for srcu_struct at %ps.\n", ssp);
+	WARN_ONCE(IS_ENABLED(CONFIG_PROVE_RCU) && (mask & (mask - 1)),
+		  "Mixed reader flavors for srcu_struct at %ps.\n", ssp);
+	*rdm = mask;
 	return sum;
 }
 
@@ -463,22 +482,28 @@ static unsigned long srcu_readers_unlock_idx(struct srcu_struct *ssp, int idx)
  */
 static bool srcu_readers_active_idx_check(struct srcu_struct *ssp, int idx)
 {
+	bool did_gp;
+	unsigned long rdm;
 	unsigned long unlocks;
 
-	unlocks = srcu_readers_unlock_idx(ssp, idx);
+	unlocks = srcu_readers_unlock_idx(ssp, idx, &rdm);
+	did_gp = !!(rdm & SRCU_READ_FLAVOR_LITE);
 
 	/*
 	 * Make sure that a lock is always counted if the corresponding
 	 * unlock is counted. Needs to be a smp_mb() as the read side may
 	 * contain a read from a variable that is written to before the
 	 * synchronize_srcu() in the write side. In this case smp_mb()s
-	 * A and B act like the store buffering pattern.
+	 * A and B (or X and Y) act like the store buffering pattern.
 	 *
-	 * This smp_mb() also pairs with smp_mb() C to prevent accesses
-	 * after the synchronize_srcu() from being executed before the
-	 * grace period ends.
+	 * This smp_mb() also pairs with smp_mb() C (or, in the case of X,
+	 * Z) to prevent accesses after the synchronize_srcu() from being
+	 * executed before the grace period ends.
 	 */
-	smp_mb(); /* A */
+	if (!did_gp)
+		smp_mb(); /* A */
+	else
+		synchronize_rcu(); /* X */
 
 	/*
 	 * If the locks are the same as the unlocks, then there must have
@@ -536,7 +561,7 @@ static bool srcu_readers_active_idx_check(struct srcu_struct *ssp, int idx)
 	 * which are unlikely to be configured with an address space fully
 	 * populated with memory, at least not anytime soon.
 	 */
-	return srcu_readers_lock_idx(ssp, idx) == unlocks;
+	return srcu_readers_lock_idx(ssp, idx, did_gp, unlocks);
 }
 
 /**
@@ -554,12 +579,12 @@ static bool srcu_readers_active(struct srcu_struct *ssp)
 	unsigned long sum = 0;
 
 	for_each_possible_cpu(cpu) {
-		struct srcu_data *cpuc = per_cpu_ptr(ssp->sda, cpu);
+		struct srcu_data *sdp = per_cpu_ptr(ssp->sda, cpu);
 
-		sum += atomic_long_read(&cpuc->srcu_lock_count[0]);
-		sum += atomic_long_read(&cpuc->srcu_lock_count[1]);
-		sum -= atomic_long_read(&cpuc->srcu_unlock_count[0]);
-		sum -= atomic_long_read(&cpuc->srcu_unlock_count[1]);
+		sum += atomic_long_read(&sdp->srcu_lock_count[0]);
+		sum += atomic_long_read(&sdp->srcu_lock_count[1]);
+		sum -= atomic_long_read(&sdp->srcu_unlock_count[0]);
+		sum -= atomic_long_read(&sdp->srcu_unlock_count[1]);
 	}
 	return sum;
 }
@@ -622,7 +647,7 @@ static unsigned long srcu_get_delay(struct srcu_struct *ssp)
 	unsigned long jbase = SRCU_INTERVAL;
 	struct srcu_usage *sup = ssp->srcu_sup;
 
-	if (ULONG_CMP_LT(READ_ONCE(sup->srcu_gp_seq), READ_ONCE(sup->srcu_gp_seq_needed_exp)))
+	if (srcu_gp_is_expedited(ssp))
 		jbase = 0;
 	if (rcu_seq_state(READ_ONCE(sup->srcu_gp_seq))) {
 		j = jiffies - 1;
@@ -687,28 +712,28 @@ void cleanup_srcu_struct(struct srcu_struct *ssp)
 }
 EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
 
-#ifdef CONFIG_PROVE_RCU
 /*
- * Check for consistent NMI safety.
+ * Check for consistent reader flavor.
  */
-void srcu_check_nmi_safety(struct srcu_struct *ssp, bool nmi_safe)
+void __srcu_check_read_flavor(struct srcu_struct *ssp, int read_flavor)
 {
-	int nmi_safe_mask = 1 << nmi_safe;
-	int old_nmi_safe_mask;
+	int old_read_flavor;
 	struct srcu_data *sdp;
 
-	/* NMI-unsafe use in NMI is a bad sign */
-	WARN_ON_ONCE(!nmi_safe && in_nmi());
+	/* NMI-unsafe use in NMI is a bad sign, as is multi-bit read_flavor values. */
+	WARN_ON_ONCE((read_flavor != SRCU_READ_FLAVOR_NMI) && in_nmi());
+	WARN_ON_ONCE(read_flavor & (read_flavor - 1));
+
 	sdp = raw_cpu_ptr(ssp->sda);
-	old_nmi_safe_mask = READ_ONCE(sdp->srcu_nmi_safety);
-	if (!old_nmi_safe_mask) {
-		WRITE_ONCE(sdp->srcu_nmi_safety, nmi_safe_mask);
-		return;
+	old_read_flavor = READ_ONCE(sdp->srcu_reader_flavor);
+	if (!old_read_flavor) {
+		old_read_flavor = cmpxchg(&sdp->srcu_reader_flavor, 0, read_flavor);
+		if (!old_read_flavor)
+			return;
 	}
-	WARN_ONCE(old_nmi_safe_mask != nmi_safe_mask, "CPU %d old state %d new state %d\n", sdp->cpu, old_nmi_safe_mask, nmi_safe_mask);
+	WARN_ONCE(old_read_flavor != read_flavor, "CPU %d old state %d new state %d\n", sdp->cpu, old_read_flavor, read_flavor);
 }
-EXPORT_SYMBOL_GPL(srcu_check_nmi_safety);
-#endif /* CONFIG_PROVE_RCU */
+EXPORT_SYMBOL_GPL(__srcu_check_read_flavor);
 
 /*
  * Counts the new reader in the appropriate per-CPU element of the
@@ -867,7 +892,7 @@ static void srcu_gp_end(struct srcu_struct *ssp)
 	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(sup->srcu_gp_seq), READ_ONCE(sup->srcu_gp_seq_needed_exp)))
+	if (srcu_gp_is_expedited(ssp))
 		cbdelay = 0;
 
 	WRITE_ONCE(sup->srcu_last_gp_end, ktime_get_mono_fast_ns());
@@ -1122,6 +1147,8 @@ static void srcu_flip(struct srcu_struct *ssp)
 	 * 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().
+	 * Except for _lite() readers, where it is inoperative, which
+	 * means that it is a good thing that it is redundant.
 	 */
 	smp_mb(); /* E */  /* Pairs with B and C. */
 
@@ -1139,7 +1166,9 @@ static void srcu_flip(struct srcu_struct *ssp)
 }
 
 /*
- * If SRCU is likely idle, return true, otherwise return false.
+ * If SRCU is likely idle, in other words, the next SRCU grace period
+ * should be expedited, return true, otherwise return false.  Except that
+ * in the presence of _lite() readers, always return false.
  *
  * Note that it is OK for several current from-idle requests for a new
  * grace period from idle to specify expediting because they will all end
@@ -1159,7 +1188,7 @@ static void srcu_flip(struct srcu_struct *ssp)
  * negligible when amortized over that time period, and the extra latency
  * of a needlessly non-expedited grace period is similarly negligible.
  */
-static bool srcu_might_be_idle(struct srcu_struct *ssp)
+static bool srcu_should_expedite(struct srcu_struct *ssp)
 {
 	unsigned long curseq;
 	unsigned long flags;
@@ -1168,6 +1197,9 @@ static bool srcu_might_be_idle(struct srcu_struct *ssp)
 	unsigned long tlast;
 
 	check_init_srcu_struct(ssp);
+	/* If _lite() readers, don't do unsolicited expediting. */
+	if (this_cpu_read(ssp->sda->srcu_reader_flavor) & SRCU_READ_FLAVOR_LITE)
+		return false;
 	/* If the local srcu_data structure has callbacks, not idle.  */
 	sdp = raw_cpu_ptr(ssp->sda);
 	spin_lock_irqsave_rcu_node(sdp, flags);
@@ -1469,14 +1501,15 @@ EXPORT_SYMBOL_GPL(synchronize_srcu_expedited);
  * Implementation of these memory-ordering guarantees is similar to
  * that of synchronize_rcu().
  *
- * If SRCU is likely idle, expedite the first request.  This semantic
- * was provided by Classic SRCU, and is relied upon by its users, so TREE
- * SRCU must also provide it.  Note that detecting idleness is heuristic
- * and subject to both false positives and negatives.
+ * If SRCU is likely idle as determined by srcu_should_expedite(),
+ * expedite the first request.  This semantic was provided by Classic SRCU,
+ * and is relied upon by its users, so TREE SRCU must also provide it.
+ * Note that detecting idleness is heuristic and subject to both false
+ * positives and negatives.
  */
 void synchronize_srcu(struct srcu_struct *ssp)
 {
-	if (srcu_might_be_idle(ssp) || rcu_gp_is_expedited())
+	if (srcu_should_expedite(ssp) || rcu_gp_is_expedited())
 		synchronize_srcu_expedited(ssp);
 	else
 		__synchronize_srcu(ssp, true);
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 4d7ee95df06e..59314da5eb60 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -1407,7 +1407,8 @@ static void call_rcu_tasks_rude(struct rcu_head *rhp, rcu_callback_t func)
  */
 void synchronize_rcu_tasks_rude(void)
 {
-	synchronize_rcu_tasks_generic(&rcu_tasks_rude);
+	if (!IS_ENABLED(CONFIG_ARCH_WANTS_NO_INSTR) || IS_ENABLED(CONFIG_FORCE_TASKS_RUDE_RCU))
+		synchronize_rcu_tasks_generic(&rcu_tasks_rude);
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu_tasks_rude);
 
@@ -1549,22 +1550,7 @@ static void rcu_st_need_qs(struct task_struct *t, u8 v)
  */
 u8 rcu_trc_cmpxchg_need_qs(struct task_struct *t, u8 old, u8 new)
 {
-	union rcu_special ret;
-	union rcu_special trs_old = READ_ONCE(t->trc_reader_special);
-	union rcu_special trs_new = trs_old;
-
-	if (trs_old.b.need_qs != old)
-		return trs_old.b.need_qs;
-	trs_new.b.need_qs = new;
-
-	// Although cmpxchg() appears to KCSAN to update all four bytes,
-	// only the .b.need_qs byte actually changes.
-	instrument_atomic_read_write(&t->trc_reader_special.b.need_qs,
-				     sizeof(t->trc_reader_special.b.need_qs));
-	// Avoid false-positive KCSAN failures.
-	ret.s = data_race(cmpxchg(&t->trc_reader_special.s, trs_old.s, trs_new.s));
-
-	return ret.b.need_qs;
+	return cmpxchg(&t->trc_reader_special.b.need_qs, old, new);
 }
 EXPORT_SYMBOL_GPL(rcu_trc_cmpxchg_need_qs);
 
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index b1f883fcd918..ff98233d4aa5 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3511,7 +3511,7 @@ static int krc_count(struct kfree_rcu_cpu *krcp)
 }
 
 static void
-schedule_delayed_monitor_work(struct kfree_rcu_cpu *krcp)
+__schedule_delayed_monitor_work(struct kfree_rcu_cpu *krcp)
 {
 	long delay, delay_left;
 
@@ -3526,6 +3526,16 @@ schedule_delayed_monitor_work(struct kfree_rcu_cpu *krcp)
 }
 
 static void
+schedule_delayed_monitor_work(struct kfree_rcu_cpu *krcp)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&krcp->lock, flags);
+	__schedule_delayed_monitor_work(krcp);
+	raw_spin_unlock_irqrestore(&krcp->lock, flags);
+}
+
+static void
 kvfree_rcu_drain_ready(struct kfree_rcu_cpu *krcp)
 {
 	struct list_head bulk_ready[FREE_N_CHANNELS];
@@ -3836,7 +3846,7 @@ void kvfree_call_rcu(struct rcu_head *head, void *ptr)
 
 	// Set timer to drain after KFREE_DRAIN_JIFFIES.
 	if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING)
-		schedule_delayed_monitor_work(krcp);
+		__schedule_delayed_monitor_work(krcp);
 
 unlock_return:
 	krc_this_cpu_unlock(krcp, flags);
@@ -4194,7 +4204,6 @@ static void start_poll_synchronize_rcu_common(void)
 	struct rcu_data *rdp;
 	struct rcu_node *rnp;
 
-	lockdep_assert_irqs_enabled();
 	local_irq_save(flags);
 	rdp = this_cpu_ptr(&rcu_data);
 	rnp = rdp->mynode;
@@ -4219,9 +4228,6 @@ static void start_poll_synchronize_rcu_common(void)
  * grace period has elapsed in the meantime.  If the needed grace period
  * is not already slated to start, notifies RCU core of the need for that
  * grace period.
- *
- * Interrupts must be enabled for the case where it is necessary to awaken
- * the grace-period kthread.
  */
 unsigned long start_poll_synchronize_rcu(void)
 {
@@ -4242,9 +4248,6 @@ EXPORT_SYMBOL_GPL(start_poll_synchronize_rcu);
  * grace period (whether normal or expedited) has elapsed in the meantime.
  * If the needed grace period is not already slated to start, notifies
  * RCU core of the need for that grace period.
- *
- * Interrupts must be enabled for the case where it is necessary to awaken
- * the grace-period kthread.
  */
 void start_poll_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp)
 {
@@ -5580,8 +5583,7 @@ void rcu_init_geometry(void)
 	 * Complain and fall back to the compile-time values if this
 	 * limit is exceeded.
 	 */
-	if (rcu_fanout_leaf < 2 ||
-	    rcu_fanout_leaf > sizeof(unsigned long) * 8) {
+	if (rcu_fanout_leaf < 2 || rcu_fanout_leaf > BITS_PER_LONG) {
 		rcu_fanout_leaf = RCU_FANOUT_LEAF;
 		WARN_ON(1);
 		return;
diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
index 16865475120b..2605dd234a13 100644
--- a/kernel/rcu/tree_nocb.h
+++ b/kernel/rcu/tree_nocb.h
@@ -891,7 +891,18 @@ static void nocb_cb_wait(struct rcu_data *rdp)
 	swait_event_interruptible_exclusive(rdp->nocb_cb_wq,
 					    nocb_cb_wait_cond(rdp));
 	if (kthread_should_park()) {
-		kthread_parkme();
+		/*
+		 * kthread_park() must be preceded by an rcu_barrier().
+		 * But yet another rcu_barrier() might have sneaked in between
+		 * the barrier callback execution and the callbacks counter
+		 * decrement.
+		 */
+		if (rdp->nocb_cb_sleep) {
+			rcu_nocb_lock_irqsave(rdp, flags);
+			WARN_ON_ONCE(rcu_segcblist_n_cbs(&rdp->cblist));
+			rcu_nocb_unlock_irqrestore(rdp, flags);
+			kthread_parkme();
+		}
 	} else if (READ_ONCE(rdp->nocb_cb_sleep)) {
 		WARN_ON(signal_pending(current));
 		trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WokeEmpty"));
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 1c7cbd145d5e..3927ea5f7955 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -183,9 +183,9 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
 	switch (blkd_state) {
 	case 0:
 	case                RCU_EXP_TASKS:
-	case                RCU_EXP_TASKS + RCU_GP_BLKD:
+	case                RCU_EXP_TASKS | RCU_GP_BLKD:
 	case RCU_GP_TASKS:
-	case RCU_GP_TASKS + RCU_EXP_TASKS:
+	case RCU_GP_TASKS | RCU_EXP_TASKS:
 
 		/*
 		 * Blocking neither GP, or first task blocking the normal
@@ -198,10 +198,10 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
 
 	case                                              RCU_EXP_BLKD:
 	case                                RCU_GP_BLKD:
-	case                                RCU_GP_BLKD + RCU_EXP_BLKD:
-	case RCU_GP_TASKS +                               RCU_EXP_BLKD:
-	case RCU_GP_TASKS +                 RCU_GP_BLKD + RCU_EXP_BLKD:
-	case RCU_GP_TASKS + RCU_EXP_TASKS + RCU_GP_BLKD + RCU_EXP_BLKD:
+	case                                RCU_GP_BLKD | RCU_EXP_BLKD:
+	case RCU_GP_TASKS |                               RCU_EXP_BLKD:
+	case RCU_GP_TASKS |                 RCU_GP_BLKD | RCU_EXP_BLKD:
+	case RCU_GP_TASKS | RCU_EXP_TASKS | RCU_GP_BLKD | RCU_EXP_BLKD:
 
 		/*
 		 * First task arriving that blocks either GP, or first task
@@ -214,9 +214,9 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
 		list_add_tail(&t->rcu_node_entry, &rnp->blkd_tasks);
 		break;
 
-	case                RCU_EXP_TASKS +               RCU_EXP_BLKD:
-	case                RCU_EXP_TASKS + RCU_GP_BLKD + RCU_EXP_BLKD:
-	case RCU_GP_TASKS + RCU_EXP_TASKS +               RCU_EXP_BLKD:
+	case                RCU_EXP_TASKS |               RCU_EXP_BLKD:
+	case                RCU_EXP_TASKS | RCU_GP_BLKD | RCU_EXP_BLKD:
+	case RCU_GP_TASKS | RCU_EXP_TASKS |               RCU_EXP_BLKD:
 
 		/*
 		 * Second or subsequent task blocking the expedited GP.
@@ -227,8 +227,8 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
 		list_add(&t->rcu_node_entry, rnp->exp_tasks);
 		break;
 
-	case RCU_GP_TASKS +                 RCU_GP_BLKD:
-	case RCU_GP_TASKS + RCU_EXP_TASKS + RCU_GP_BLKD:
+	case RCU_GP_TASKS |                 RCU_GP_BLKD:
+	case RCU_GP_TASKS | RCU_EXP_TASKS | RCU_GP_BLKD:
 
 		/*
 		 * Second or subsequent task blocking the normal GP.
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index 4432db6d0b99..925fcdad5dea 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -76,36 +76,6 @@ int rcu_jiffies_till_stall_check(void)
 }
 EXPORT_SYMBOL_GPL(rcu_jiffies_till_stall_check);
 
-/**
- * rcu_gp_might_be_stalled - Is it likely that the grace period is stalled?
- *
- * Returns @true if the current grace period is sufficiently old that
- * it is reasonable to assume that it might be stalled.  This can be
- * useful when deciding whether to allocate memory to enable RCU-mediated
- * freeing on the one hand or just invoking synchronize_rcu() on the other.
- * The latter is preferable when the grace period is stalled.
- *
- * Note that sampling of the .gp_start and .gp_seq fields must be done
- * carefully to avoid false positives at the beginnings and ends of
- * grace periods.
- */
-bool rcu_gp_might_be_stalled(void)
-{
-	unsigned long d = rcu_jiffies_till_stall_check() / RCU_STALL_MIGHT_DIV;
-	unsigned long j = jiffies;
-
-	if (d < RCU_STALL_MIGHT_MIN)
-		d = RCU_STALL_MIGHT_MIN;
-	smp_mb(); // jiffies before .gp_seq to avoid false positives.
-	if (!rcu_gp_in_progress())
-		return false;
-	// Long delays at this point avoids false positive, but a delay
-	// of ULONG_MAX/4 jiffies voids your no-false-positive warranty.
-	smp_mb(); // .gp_seq before second .gp_start
-	// And ditto here.
-	return !time_before(j, READ_ONCE(rcu_state.gp_start) + d);
-}
-
 /* Don't do RCU CPU stall warnings during long sysrq printouts. */
 void rcu_sysrq_start(void)
 {
@@ -365,7 +335,7 @@ static int rcu_print_task_stall(struct rcu_node *rnp, unsigned long flags)
  * that don't support NMI-based stack dumps.  The NMI-triggered stack
  * traces are more accurate because they are printed by the target CPU.
  */
-static void rcu_dump_cpu_stacks(void)
+static void rcu_dump_cpu_stacks(unsigned long gp_seq)
 {
 	int cpu;
 	unsigned long flags;
@@ -373,15 +343,23 @@ static void rcu_dump_cpu_stacks(void)
 
 	rcu_for_each_leaf_node(rnp) {
 		printk_deferred_enter();
-		raw_spin_lock_irqsave_rcu_node(rnp, flags);
-		for_each_leaf_node_possible_cpu(rnp, cpu)
+		for_each_leaf_node_possible_cpu(rnp, cpu) {
+			if (gp_seq != data_race(rcu_state.gp_seq)) {
+				printk_deferred_exit();
+				pr_err("INFO: Stall ended during stack backtracing.\n");
+				return;
+			}
+			if (!(data_race(rnp->qsmask) & leaf_node_cpu_bit(rnp, cpu)))
+				continue;
+			raw_spin_lock_irqsave_rcu_node(rnp, flags);
 			if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) {
 				if (cpu_is_offline(cpu))
 					pr_err("Offline CPU %d blocking current GP.\n", cpu);
 				else
 					dump_cpu_task(cpu);
 			}
-		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+		}
 		printk_deferred_exit();
 	}
 }
@@ -638,7 +616,7 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps)
 	       (long)rcu_seq_current(&rcu_state.gp_seq), totqlen,
 	       data_race(rcu_state.n_online_cpus)); // Diagnostic read
 	if (ndetected) {
-		rcu_dump_cpu_stacks();
+		rcu_dump_cpu_stacks(gp_seq);
 
 		/* Complain about tasks blocking the grace period. */
 		rcu_for_each_leaf_node(rnp)
@@ -670,7 +648,7 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps)
 	rcu_force_quiescent_state();  /* Kick them all. */
 }
 
-static void print_cpu_stall(unsigned long gps)
+static void print_cpu_stall(unsigned long gp_seq, unsigned long gps)
 {
 	int cpu;
 	unsigned long flags;
@@ -707,7 +685,7 @@ static void print_cpu_stall(unsigned long gps)
 	rcu_check_gp_kthread_expired_fqs_timer();
 	rcu_check_gp_kthread_starvation();
 
-	rcu_dump_cpu_stacks();
+	rcu_dump_cpu_stacks(gp_seq);
 
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	/* Rewrite if needed in case of slow consoles. */
@@ -789,7 +767,8 @@ static void check_cpu_stall(struct rcu_data *rdp)
 	gs2 = READ_ONCE(rcu_state.gp_seq);
 	if (gs1 != gs2 ||
 	    ULONG_CMP_LT(j, js) ||
-	    ULONG_CMP_GE(gps, js))
+	    ULONG_CMP_GE(gps, js) ||
+	    !rcu_seq_state(gs2))
 		return; /* No stall or GP completed since entering function. */
 	rnp = rdp->mynode;
 	jn = jiffies + ULONG_MAX / 2;
@@ -810,7 +789,7 @@ static void check_cpu_stall(struct rcu_data *rdp)
 			pr_err("INFO: %s detected stall, but suppressed full report due to a stuck CSD-lock.\n", rcu_state.name);
 		} else if (self_detected) {
 			/* We haven't checked in, so go dump stack. */
-			print_cpu_stall(gps);
+			print_cpu_stall(gs2, gps);
 		} else {
 			/* They had a few time units to dump stack, so complain. */
 			print_other_cpu_stall(gs2, gps);