Merge branch 'rcu/next' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git

78 files changed, 1569 insertions, 787 deletions

diff --git a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst
index eeb351296df11..7fdf151a8680a 100644
--- a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst
+++ b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst
@@ -202,49 +202,44 @@ newly arrived RCU callbacks against future grace periods:
     1 static void rcu_prepare_for_idle(void)
     2 {
     3   bool needwake;
-    4   struct rcu_data *rdp;
-    5   struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
-    6   struct rcu_node *rnp;
-    7   struct rcu_state *rsp;
-    8   int tne;
-    9
-   10   if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL) ||
-   11       rcu_is_nocb_cpu(smp_processor_id()))
-   12     return;
+    4   struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
+    5   struct rcu_node *rnp;
+    6   int tne;
+    7
+    8   lockdep_assert_irqs_disabled();
+    9   if (rcu_rdp_is_offloaded(rdp))
+   10     return;
+   11
+   12   /* Handle nohz enablement switches conservatively. */
    13   tne = READ_ONCE(tick_nohz_active);
-   14   if (tne != rdtp->tick_nohz_enabled_snap) {
-   15     if (rcu_cpu_has_callbacks(NULL))
-   16       invoke_rcu_core();
-   17     rdtp->tick_nohz_enabled_snap = tne;
+   14   if (tne != rdp->tick_nohz_enabled_snap) {
+   15     if (!rcu_segcblist_empty(&rdp->cblist))
+   16       invoke_rcu_core(); /* force nohz to see update. */
+   17     rdp->tick_nohz_enabled_snap = tne;
    18     return;
-   19   }
+   19	}
    20   if (!tne)
    21     return;
-   22   if (rdtp->all_lazy &&
-   23       rdtp->nonlazy_posted != rdtp->nonlazy_posted_snap) {
-   24     rdtp->all_lazy = false;
-   25     rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted;
-   26     invoke_rcu_core();
-   27     return;
-   28   }
-   29   if (rdtp->last_accelerate == jiffies)
-   30     return;
-   31   rdtp->last_accelerate = jiffies;
-   32   for_each_rcu_flavor(rsp) {
-   33     rdp = this_cpu_ptr(rsp->rda);
-   34     if (rcu_segcblist_pend_cbs(&rdp->cblist))
-   35       continue;
-   36     rnp = rdp->mynode;
-   37     raw_spin_lock_rcu_node(rnp);
-   38     needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
-   39     raw_spin_unlock_rcu_node(rnp);
-   40     if (needwake)
-   41       rcu_gp_kthread_wake(rsp);
-   42   }
-   43 }
+   22
+   23   /*
+   24    * If we have not yet accelerated this jiffy, accelerate all
+   25    * callbacks on this CPU.
+   26   */
+   27   if (rdp->last_accelerate == jiffies)
+   28     return;
+   29   rdp->last_accelerate = jiffies;
+   30   if (rcu_segcblist_pend_cbs(&rdp->cblist)) {
+   31     rnp = rdp->mynode;
+   32     raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
+   33     needwake = rcu_accelerate_cbs(rnp, rdp);
+   34     raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */
+   35     if (needwake)
+   36       rcu_gp_kthread_wake();
+   37   }
+   38 }
 
 But the only part of ``rcu_prepare_for_idle()`` that really matters for
-this discussion are lines 37–39. We will therefore abbreviate this
+this discussion are lines 32–34. We will therefore abbreviate this
 function as follows:
 
 .. kernel-figure:: rcu_node-lock.svg
diff --git a/Documentation/RCU/stallwarn.rst b/Documentation/RCU/stallwarn.rst
index 5036df24ae61c..78404625bad26 100644
--- a/Documentation/RCU/stallwarn.rst
+++ b/Documentation/RCU/stallwarn.rst
@@ -96,6 +96,16 @@ warnings:
 	the ``rcu_.*timer wakeup didn't happen for`` console-log message,
 	which will include additional debugging information.
 
+-	A low-level kernel issue that either fails to invoke one of the
+	variants of rcu_user_enter(), rcu_user_exit(), rcu_idle_enter(),
+	rcu_idle_exit(), rcu_irq_enter(), or rcu_irq_exit() on the one
+	hand, or that invokes one of them too many times on the other.
+	Historically, the most frequent issue has been an omission
+	of either irq_enter() or irq_exit(), which in turn invoke
+	rcu_irq_enter() or rcu_irq_exit(), respectively.  Building your
+	kernel with CONFIG_RCU_EQS_DEBUG=y can help track down these types
+	of issues, which sometimes arise in architecture-specific code.
+
 -	A bug in the RCU implementation.
 
 -	A hardware failure.  This is quite unlikely, but has occurred
@@ -244,17 +254,6 @@ period (in this case 2603), the grace-period sequence number (7075), and
 an estimate of the total number of RCU callbacks queued across all CPUs
 (625 in this case).
 
-In kernels with CONFIG_RCU_FAST_NO_HZ, more information is printed
-for each CPU::
-
-	0: (64628 ticks this GP) idle=dd5/3fffffffffffffff/0 softirq=82/543 last_accelerate: a345/d342 dyntick_enabled: 1
-
-The "last_accelerate:" prints the low-order 16 bits (in hex) of the
-jiffies counter when this CPU last invoked rcu_try_advance_all_cbs()
-from rcu_needs_cpu() or last invoked rcu_accelerate_cbs() from
-rcu_prepare_for_idle(). "dyntick_enabled: 1" indicates that dyntick-idle
-processing is enabled.
-
 If the grace period ends just as the stall warning starts printing,
 there will be a spurious stall-warning message, which will include
 the following::
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 91ba391f9b328..316027c3aadce 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -4465,10 +4465,6 @@
 			on rcutree.qhimark at boot time and to zero to
 			disable more aggressive help enlistment.
 
-	rcutree.rcu_idle_gp_delay= [KNL]
-			Set wakeup interval for idle CPUs that have
-			RCU callbacks (RCU_FAST_NO_HZ=y).
-
 	rcutree.rcu_kick_kthreads= [KNL]
 			Cause the grace-period kthread to get an extra
 			wake_up() if it sleeps three times longer than
diff --git a/Documentation/admin-guide/kernel-per-CPU-kthreads.rst b/Documentation/admin-guide/kernel-per-CPU-kthreads.rst
index 5e51ee5b03589..e4a5fc26f1a9d 100644
--- a/Documentation/admin-guide/kernel-per-CPU-kthreads.rst
+++ b/Documentation/admin-guide/kernel-per-CPU-kthreads.rst
@@ -208,7 +208,7 @@ Do at least one of the following:
 2.	Enable RCU to do its processing remotely via dyntick-idle by
 	doing all of the following:
 
-	a.	Build with CONFIG_NO_HZ=y and CONFIG_RCU_FAST_NO_HZ=y.
+	a.	Build with CONFIG_NO_HZ=y.
 	b.	Ensure that the CPU goes idle frequently, allowing other
 		CPUs to detect that it has passed through an RCU quiescent
 		state.	If the kernel is built with CONFIG_NO_HZ_FULL=y,
diff --git a/Documentation/litmus-tests/locking/DCL-broken.litmus b/Documentation/litmus-tests/locking/DCL-broken.litmus
new file mode 100644
index 0000000000000..cfaa25ff82b1e
--- /dev/null
+++ b/Documentation/litmus-tests/locking/DCL-broken.litmus
@@ -0,0 +1,55 @@
+C DCL-broken
+
+(*
+ * Result: Sometimes
+ *
+ * This litmus test demonstrates more than just locking is required to
+ * correctly implement double-checked locking.
+ *)
+
+{
+	int flag;
+	int data;
+	int lck;
+}
+
+P0(int *flag, int *data, int *lck)
+{
+	int r0;
+	int r1;
+	int r2;
+
+	r0 = READ_ONCE(*flag);
+	if (r0 == 0) {
+		spin_lock(lck);
+		r1 = READ_ONCE(*flag);
+		if (r1 == 0) {
+			WRITE_ONCE(*data, 1);
+			WRITE_ONCE(*flag, 1);
+		}
+		spin_unlock(lck);
+	}
+	r2 = READ_ONCE(*data);
+}
+
+P1(int *flag, int *data, int *lck)
+{
+	int r0;
+	int r1;
+	int r2;
+
+	r0 = READ_ONCE(*flag);
+	if (r0 == 0) {
+		spin_lock(lck);
+		r1 = READ_ONCE(*flag);
+		if (r1 == 0) {
+			WRITE_ONCE(*data, 1);
+			WRITE_ONCE(*flag, 1);
+		}
+		spin_unlock(lck);
+	}
+	r2 = READ_ONCE(*data);
+}
+
+locations [flag;data;lck;0:r0;0:r1;1:r0;1:r1]
+exists (0:r2=0 \/ 1:r2=0)
diff --git a/Documentation/litmus-tests/locking/DCL-fixed.litmus b/Documentation/litmus-tests/locking/DCL-fixed.litmus
new file mode 100644
index 0000000000000..579d6c246f167
--- /dev/null
+++ b/Documentation/litmus-tests/locking/DCL-fixed.litmus
@@ -0,0 +1,56 @@
+C DCL-fixed
+
+(*
+ * Result: Never
+ *
+ * This litmus test demonstrates that double-checked locking can be
+ * reliable given proper use of smp_load_acquire() and smp_store_release()
+ * in addition to the locking.
+ *)
+
+{
+	int flag;
+	int data;
+	int lck;
+}
+
+P0(int *flag, int *data, int *lck)
+{
+	int r0;
+	int r1;
+	int r2;
+
+	r0 = smp_load_acquire(flag);
+	if (r0 == 0) {
+		spin_lock(lck);
+		r1 = READ_ONCE(*flag);
+		if (r1 == 0) {
+			WRITE_ONCE(*data, 1);
+			smp_store_release(flag, 1);
+		}
+		spin_unlock(lck);
+	}
+	r2 = READ_ONCE(*data);
+}
+
+P1(int *flag, int *data, int *lck)
+{
+	int r0;
+	int r1;
+	int r2;
+
+	r0 = smp_load_acquire(flag);
+	if (r0 == 0) {
+		spin_lock(lck);
+		r1 = READ_ONCE(*flag);
+		if (r1 == 0) {
+			WRITE_ONCE(*data, 1);
+			smp_store_release(flag, 1);
+		}
+		spin_unlock(lck);
+	}
+	r2 = READ_ONCE(*data);
+}
+
+locations [flag;data;lck;0:r0;0:r1;1:r0;1:r1]
+exists (0:r2=0 \/ 1:r2=0)
diff --git a/Documentation/litmus-tests/locking/RM-broken.litmus b/Documentation/litmus-tests/locking/RM-broken.litmus
new file mode 100644
index 0000000000000..c586ae4b547de
--- /dev/null
+++ b/Documentation/litmus-tests/locking/RM-broken.litmus
@@ -0,0 +1,42 @@
+C RM-broken
+
+(*
+ * Result: DEADLOCK
+ *
+ * This litmus test demonstrates that the old "roach motel" approach
+ * to locking, where code can be freely moved into critical sections,
+ * cannot be used in the Linux kernel.
+ *)
+
+{
+	int lck;
+	int x;
+	int y;
+}
+
+P0(int *x, int *y, int *lck)
+{
+	int r2;
+
+	spin_lock(lck);
+	r2 = atomic_inc_return(y);
+	WRITE_ONCE(*x, 1);
+	spin_unlock(lck);
+}
+
+P1(int *x, int *y, int *lck)
+{
+	int r0;
+	int r1;
+	int r2;
+
+	spin_lock(lck);
+	r0 = READ_ONCE(*x);
+	r1 = READ_ONCE(*x);
+	r2 = atomic_inc_return(y);
+	spin_unlock(lck);
+}
+
+locations [x;lck;0:r2;1:r0;1:r1;1:r2]
+filter (y=2 /\ 1:r0=0 /\ 1:r1=1)
+exists (1:r2=1)
diff --git a/Documentation/litmus-tests/locking/RM-fixed.litmus b/Documentation/litmus-tests/locking/RM-fixed.litmus
new file mode 100644
index 0000000000000..672856736b42e
--- /dev/null
+++ b/Documentation/litmus-tests/locking/RM-fixed.litmus
@@ -0,0 +1,42 @@
+C RM-fixed
+
+(*
+ * Result: Never
+ *
+ * This litmus test demonstrates that the old "roach motel" approach
+ * to locking, where code can be freely moved into critical sections,
+ * cannot be used in the Linux kernel.
+ *)
+
+{
+	int lck;
+	int x;
+	int y;
+}
+
+P0(int *x, int *y, int *lck)
+{
+	int r2;
+
+	spin_lock(lck);
+	r2 = atomic_inc_return(y);
+	WRITE_ONCE(*x, 1);
+	spin_unlock(lck);
+}
+
+P1(int *x, int *y, int *lck)
+{
+	int r0;
+	int r1;
+	int r2;
+
+	r0 = READ_ONCE(*x);
+	r1 = READ_ONCE(*x);
+	spin_lock(lck);
+	r2 = atomic_inc_return(y);
+	spin_unlock(lck);
+}
+
+locations [x;lck;0:r2;1:r0;1:r1;1:r2]
+filter (y=2 /\ 1:r0=0 /\ 1:r1=1)
+exists (1:r2=1)
diff --git a/Documentation/timers/no_hz.rst b/Documentation/timers/no_hz.rst
index 20ad23a6c618e..f8786be15183c 100644
--- a/Documentation/timers/no_hz.rst
+++ b/Documentation/timers/no_hz.rst
@@ -184,16 +184,12 @@ There are situations in which idle CPUs cannot be permitted to
 enter either dyntick-idle mode or adaptive-tick mode, the most
 common being when that CPU has RCU callbacks pending.
 
-The CONFIG_RCU_FAST_NO_HZ=y Kconfig option may be used to cause such CPUs
-to enter dyntick-idle mode or adaptive-tick mode anyway.  In this case,
-a timer will awaken these CPUs every four jiffies in order to ensure
-that the RCU callbacks are processed in a timely fashion.
-
-Another approach is to offload RCU callback processing to "rcuo" kthreads
+Avoid this by offloading RCU callback processing to "rcuo" kthreads
 using the CONFIG_RCU_NOCB_CPU=y Kconfig option.  The specific CPUs to
 offload may be selected using The "rcu_nocbs=" kernel boot parameter,
 which takes a comma-separated list of CPUs and CPU ranges, for example,
-"1,3-5" selects CPUs 1, 3, 4, and 5.
+"1,3-5" selects CPUs 1, 3, 4, and 5.  Note that CPUs specified by
+the "nohz_full" kernel boot parameter are also offloaded.
 
 The offloaded CPUs will never queue RCU callbacks, and therefore RCU
 never prevents offloaded CPUs from entering either dyntick-idle mode
diff --git a/arch/sh/configs/sdk7786_defconfig b/arch/sh/configs/sdk7786_defconfig
index f776a1d0d2776..a8662b6927ec7 100644
--- a/arch/sh/configs/sdk7786_defconfig
+++ b/arch/sh/configs/sdk7786_defconfig
@@ -5,7 +5,6 @@ CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_BSD_PROCESS_ACCT_V3=y
 CONFIG_AUDIT=y
 CONFIG_AUDITSYSCALL=y
-CONFIG_TREE_PREEMPT_RCU=y
 CONFIG_RCU_TRACE=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
diff --git a/arch/xtensa/configs/nommu_kc705_defconfig b/arch/xtensa/configs/nommu_kc705_defconfig
index 88b2e222d4bff..fcb620ef37997 100644
--- a/arch/xtensa/configs/nommu_kc705_defconfig
+++ b/arch/xtensa/configs/nommu_kc705_defconfig
@@ -119,7 +119,6 @@ CONFIG_DEBUG_SPINLOCK=y
 CONFIG_DEBUG_MUTEXES=y
 CONFIG_DEBUG_ATOMIC_SLEEP=y
 CONFIG_STACKTRACE=y
-# CONFIG_RCU_CPU_STALL_INFO is not set
 CONFIG_RCU_TRACE=y
 # CONFIG_FTRACE is not set
 # CONFIG_LD_NO_RELAX is not set
diff --git a/include/linux/kcsan-checks.h b/include/linux/kcsan-checks.h
index 9fd0ad80fef6c..5f5965246877a 100644
--- a/include/linux/kcsan-checks.h
+++ b/include/linux/kcsan-checks.h
@@ -100,9 +100,12 @@ void kcsan_set_access_mask(unsigned long mask);
 /* Scoped access information. */
 struct kcsan_scoped_access {
 	struct list_head list;
+	/* Access information. */
 	const volatile void *ptr;
 	size_t size;
 	int type;
+	/* Location where scoped access was set up. */
+	unsigned long ip;
 };
 /*
  * Automatically call kcsan_end_scoped_access() when kcsan_scoped_access goes
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 434d12fe2d4f5..88b42eb464068 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -71,7 +71,8 @@ static inline void __rcu_read_lock(void)
 static inline void __rcu_read_unlock(void)
 {
 	preempt_enable();
-	rcu_read_unlock_strict();
+	if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD))
+		rcu_read_unlock_strict();
 }
 
 static inline int rcu_preempt_depth(void)
@@ -363,6 +364,12 @@ static inline void rcu_preempt_sleep_check(void) { }
 #define rcu_check_sparse(p, space)
 #endif /* #else #ifdef __CHECKER__ */
 
+#define __unrcu_pointer(p, local)					\
+({									\
+	typeof(*p) *local = (typeof(*p) *__force)(p);			\
+	rcu_check_sparse(p, __rcu);					\
+	((typeof(*p) __force __kernel *)(local)); 			\
+})
 /**
  * unrcu_pointer - mark a pointer as not being RCU protected
  * @p: pointer needing to lose its __rcu property
@@ -370,39 +377,35 @@ static inline void rcu_preempt_sleep_check(void) { }
  * Converts @p from an __rcu pointer to a __kernel pointer.
  * This allows an __rcu pointer to be used with xchg() and friends.
  */
-#define unrcu_pointer(p)						\
-({									\
-	typeof(*p) *_________p1 = (typeof(*p) *__force)(p);		\
-	rcu_check_sparse(p, __rcu);					\
-	((typeof(*p) __force __kernel *)(_________p1)); 		\
-})
+#define unrcu_pointer(p) __unrcu_pointer(p, __UNIQUE_ID(rcu))
 
-#define __rcu_access_pointer(p, space) \
+#define __rcu_access_pointer(p, local, space) \
 ({ \
-	typeof(*p) *_________p1 = (typeof(*p) *__force)READ_ONCE(p); \
+	typeof(*p) *local = (typeof(*p) *__force)READ_ONCE(p); \
 	rcu_check_sparse(p, space); \
-	((typeof(*p) __force __kernel *)(_________p1)); \
+	((typeof(*p) __force __kernel *)(local)); \
 })
-#define __rcu_dereference_check(p, c, space) \
+#define __rcu_dereference_check(p, local, c, space) \
 ({ \
 	/* Dependency order vs. p above. */ \
-	typeof(*p) *________p1 = (typeof(*p) *__force)READ_ONCE(p); \
+	typeof(*p) *local = (typeof(*p) *__force)READ_ONCE(p); \
 	RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_check() usage"); \
 	rcu_check_sparse(p, space); \
-	((typeof(*p) __force __kernel *)(________p1)); \
+	((typeof(*p) __force __kernel *)(local)); \
 })
-#define __rcu_dereference_protected(p, c, space) \
+#define __rcu_dereference_protected(p, local, c, space) \
 ({ \
 	RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_protected() usage"); \
 	rcu_check_sparse(p, space); \
 	((typeof(*p) __force __kernel *)(p)); \
 })
-#define rcu_dereference_raw(p) \
+#define __rcu_dereference_raw(p, local) \
 ({ \
 	/* Dependency order vs. p above. */ \
-	typeof(p) ________p1 = READ_ONCE(p); \
-	((typeof(*p) __force __kernel *)(________p1)); \
+	typeof(p) local = READ_ONCE(p); \
+	((typeof(*p) __force __kernel *)(local)); \
 })
+#define rcu_dereference_raw(p) __rcu_dereference_raw(p, __UNIQUE_ID(rcu))
 
 /**
  * RCU_INITIALIZER() - statically initialize an RCU-protected global variable
@@ -489,7 +492,7 @@ do {									      \
  * when tearing down multi-linked structures after a grace period
  * has elapsed.
  */
-#define rcu_access_pointer(p) __rcu_access_pointer((p), __rcu)
+#define rcu_access_pointer(p) __rcu_access_pointer((p), __UNIQUE_ID(rcu), __rcu)
 
 /**
  * rcu_dereference_check() - rcu_dereference with debug checking
@@ -525,7 +528,8 @@ do {									      \
  * annotated as __rcu.
  */
 #define rcu_dereference_check(p, c) \
-	__rcu_dereference_check((p), (c) || rcu_read_lock_held(), __rcu)
+	__rcu_dereference_check((p), __UNIQUE_ID(rcu), \
+				(c) || rcu_read_lock_held(), __rcu)
 
 /**
  * rcu_dereference_bh_check() - rcu_dereference_bh with debug checking
@@ -540,7 +544,8 @@ do {									      \
  * rcu_read_lock() but also rcu_read_lock_bh() into account.
  */
 #define rcu_dereference_bh_check(p, c) \
-	__rcu_dereference_check((p), (c) || rcu_read_lock_bh_held(), __rcu)
+	__rcu_dereference_check((p), __UNIQUE_ID(rcu), \
+				(c) || rcu_read_lock_bh_held(), __rcu)
 
 /**
  * rcu_dereference_sched_check() - rcu_dereference_sched with debug checking
@@ -555,7 +560,8 @@ do {									      \
  * only rcu_read_lock() but also rcu_read_lock_sched() into account.
  */
 #define rcu_dereference_sched_check(p, c) \
-	__rcu_dereference_check((p), (c) || rcu_read_lock_sched_held(), \
+	__rcu_dereference_check((p), __UNIQUE_ID(rcu), \
+				(c) || rcu_read_lock_sched_held(), \
 				__rcu)
 
 /*
@@ -565,7 +571,8 @@ do {									      \
  * The no-tracing version of rcu_dereference_raw() must not call
  * rcu_read_lock_held().
  */
-#define rcu_dereference_raw_check(p) __rcu_dereference_check((p), 1, __rcu)
+#define rcu_dereference_raw_check(p) \
+	__rcu_dereference_check((p), __UNIQUE_ID(rcu), 1, __rcu)
 
 /**
  * rcu_dereference_protected() - fetch RCU pointer when updates prevented
@@ -584,7 +591,7 @@ do {									      \
  * but very ugly failures.
  */
 #define rcu_dereference_protected(p, c) \
-	__rcu_dereference_protected((p), (c), __rcu)
+	__rcu_dereference_protected((p), __UNIQUE_ID(rcu), (c), __rcu)
 
 
 /**
diff --git a/include/linux/rcupdate_trace.h b/include/linux/rcupdate_trace.h
index 86c8f6c98412b..6f9c358173989 100644
--- a/include/linux/rcupdate_trace.h
+++ b/include/linux/rcupdate_trace.h
@@ -31,7 +31,7 @@ static inline int rcu_read_lock_trace_held(void)
 
 #ifdef CONFIG_TASKS_TRACE_RCU
 
-void rcu_read_unlock_trace_special(struct task_struct *t, int nesting);
+void rcu_read_unlock_trace_special(struct task_struct *t);
 
 /**
  * rcu_read_lock_trace - mark beginning of RCU-trace read-side critical section
@@ -80,7 +80,8 @@ static inline void rcu_read_unlock_trace(void)
 		WRITE_ONCE(t->trc_reader_nesting, nesting);
 		return;  // We assume shallow reader nesting.
 	}
-	rcu_read_unlock_trace_special(t, nesting);
+	WARN_ON_ONCE(nesting != 0);
+	rcu_read_unlock_trace_special(t);
 }
 
 void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func);
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 9be015305f9f9..858f4d429946d 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -85,7 +85,7 @@ static inline void rcu_irq_enter_irqson(void) { }
 static inline void rcu_irq_exit(void) { }
 static inline void rcu_irq_exit_check_preempt(void) { }
 #define rcu_is_idle_cpu(cpu) \
-	(is_idle_task(current) && !in_nmi() && !in_irq() && !in_serving_softirq())
+	(is_idle_task(current) && !in_nmi() && !in_hardirq() && !in_serving_softirq())
 static inline void exit_rcu(void) { }
 static inline bool rcu_preempt_need_deferred_qs(struct task_struct *t)
 {
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index e6011a9975af2..01226e4d960a0 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -117,7 +117,8 @@ static inline int srcu_read_lock_held(const struct srcu_struct *ssp)
  * lockdep_is_held() calls.
  */
 #define srcu_dereference_check(p, ssp, c) \
-	__rcu_dereference_check((p), (c) || srcu_read_lock_held(ssp), __rcu)
+	__rcu_dereference_check((p), __UNIQUE_ID(rcu), \
+				(c) || srcu_read_lock_held(ssp), __rcu)
 
 /**
  * srcu_dereference - fetch SRCU-protected pointer for later dereferencing
diff --git a/include/linux/torture.h b/include/linux/torture.h
index 0910c5803f35a..24f58e50a94b8 100644
--- a/include/linux/torture.h
+++ b/include/linux/torture.h
@@ -47,6 +47,14 @@ do {										\
 } while (0)
 void verbose_torout_sleep(void);
 
+#define torture_init_error(firsterr)						\
+({										\
+	int ___firsterr = (firsterr);						\
+										\
+	WARN_ONCE(!IS_MODULE(CONFIG_RCU_TORTURE_TEST) && ___firsterr < 0, "Torture-test initialization failed with error code %d\n", ___firsterr); \
+	___firsterr < 0;								\
+})
+
 /* Definitions for online/offline exerciser. */
 #ifdef CONFIG_HOTPLUG_CPU
 int torture_num_online_cpus(void);
diff --git a/kernel/kcsan/core.c b/kernel/kcsan/core.c
index 76e67d1e02d48..4b84c8e7884b4 100644
--- a/kernel/kcsan/core.c
+++ b/kernel/kcsan/core.c
@@ -202,6 +202,9 @@ static __always_inline struct kcsan_ctx *get_ctx(void)
 	return in_task() ? &current->kcsan_ctx : raw_cpu_ptr(&kcsan_cpu_ctx);
 }
 
+static __always_inline void
+check_access(const volatile void *ptr, size_t size, int type, unsigned long ip);
+
 /* Check scoped accesses; never inline because this is a slow-path! */
 static noinline void kcsan_check_scoped_accesses(void)
 {
@@ -210,14 +213,16 @@ static noinline void kcsan_check_scoped_accesses(void)
 	struct kcsan_scoped_access *scoped_access;
 
 	ctx->scoped_accesses.prev = NULL;  /* Avoid recursion. */
-	list_for_each_entry(scoped_access, &ctx->scoped_accesses, list)
-		__kcsan_check_access(scoped_access->ptr, scoped_access->size, scoped_access->type);
+	list_for_each_entry(scoped_access, &ctx->scoped_accesses, list) {
+		check_access(scoped_access->ptr, scoped_access->size,
+			     scoped_access->type, scoped_access->ip);
+	}
 	ctx->scoped_accesses.prev = prev_save;
 }
 
 /* Rules for generic atomic accesses. Called from fast-path. */
 static __always_inline bool
-is_atomic(const volatile void *ptr, size_t size, int type, struct kcsan_ctx *ctx)
+is_atomic(struct kcsan_ctx *ctx, const volatile void *ptr, size_t size, int type)
 {
 	if (type & KCSAN_ACCESS_ATOMIC)
 		return true;
@@ -254,7 +259,7 @@ is_atomic(const volatile void *ptr, size_t size, int type, struct kcsan_ctx *ctx
 }
 
 static __always_inline bool
-should_watch(const volatile void *ptr, size_t size, int type, struct kcsan_ctx *ctx)
+should_watch(struct kcsan_ctx *ctx, const volatile void *ptr, size_t size, int type)
 {
 	/*
 	 * Never set up watchpoints when memory operations are atomic.
@@ -263,7 +268,7 @@ should_watch(const volatile void *ptr, size_t size, int type, struct kcsan_ctx *
 	 * should not count towards skipped instructions, and (2) to actually
 	 * decrement kcsan_atomic_next for consecutive instruction stream.
 	 */
-	if (is_atomic(ptr, size, type, ctx))
+	if (is_atomic(ctx, ptr, size, type))
 		return false;
 
 	if (this_cpu_dec_return(kcsan_skip) >= 0)
@@ -350,6 +355,7 @@ void kcsan_restore_irqtrace(struct task_struct *task)
 static noinline void kcsan_found_watchpoint(const volatile void *ptr,
 					    size_t size,
 					    int type,
+					    unsigned long ip,
 					    atomic_long_t *watchpoint,
 					    long encoded_watchpoint)
 {
@@ -396,7 +402,7 @@ static noinline void kcsan_found_watchpoint(const volatile void *ptr,
 
 	if (consumed) {
 		kcsan_save_irqtrace(current);
-		kcsan_report_set_info(ptr, size, type, watchpoint - watchpoints);
+		kcsan_report_set_info(ptr, size, type, ip, watchpoint - watchpoints);
 		kcsan_restore_irqtrace(current);
 	} else {
 		/*
@@ -416,7 +422,7 @@ static noinline void kcsan_found_watchpoint(const volatile void *ptr,
 }
 
 static noinline void
-kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type)
+kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type, unsigned long ip)
 {
 	const bool is_write = (type & KCSAN_ACCESS_WRITE) != 0;
 	const bool is_assert = (type & KCSAN_ACCESS_ASSERT) != 0;
@@ -568,8 +574,8 @@ kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type)
 		if (is_assert && value_change == KCSAN_VALUE_CHANGE_TRUE)
 			atomic_long_inc(&kcsan_counters[KCSAN_COUNTER_ASSERT_FAILURES]);
 
-		kcsan_report_known_origin(ptr, size, type, value_change,
-					  watchpoint - watchpoints,
+		kcsan_report_known_origin(ptr, size, type, ip,
+					  value_change, watchpoint - watchpoints,
 					  old, new, access_mask);
 	} else if (value_change == KCSAN_VALUE_CHANGE_TRUE) {
 		/* Inferring a race, since the value should not have changed. */
@@ -578,8 +584,10 @@ kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type)
 		if (is_assert)
 			atomic_long_inc(&kcsan_counters[KCSAN_COUNTER_ASSERT_FAILURES]);
 
-		if (IS_ENABLED(CONFIG_KCSAN_REPORT_RACE_UNKNOWN_ORIGIN) || is_assert)
-			kcsan_report_unknown_origin(ptr, size, type, old, new, access_mask);
+		if (IS_ENABLED(CONFIG_KCSAN_REPORT_RACE_UNKNOWN_ORIGIN) || is_assert) {
+			kcsan_report_unknown_origin(ptr, size, type, ip,
+						    old, new, access_mask);
+		}
 	}
 
 	/*
@@ -596,8 +604,8 @@ out:
 	user_access_restore(ua_flags);
 }
 
-static __always_inline void check_access(const volatile void *ptr, size_t size,
-					 int type)
+static __always_inline void
+check_access(const volatile void *ptr, size_t size, int type, unsigned long ip)
 {
 	const bool is_write = (type & KCSAN_ACCESS_WRITE) != 0;
 	atomic_long_t *watchpoint;
@@ -625,13 +633,12 @@ static __always_inline void check_access(const volatile void *ptr, size_t size,
 	 */
 
 	if (unlikely(watchpoint != NULL))
-		kcsan_found_watchpoint(ptr, size, type, watchpoint,
-				       encoded_watchpoint);
+		kcsan_found_watchpoint(ptr, size, type, ip, watchpoint, encoded_watchpoint);
 	else {
 		struct kcsan_ctx *ctx = get_ctx(); /* Call only once in fast-path. */
 
-		if (unlikely(should_watch(ptr, size, type, ctx)))
-			kcsan_setup_watchpoint(ptr, size, type);
+		if (unlikely(should_watch(ctx, ptr, size, type)))
+			kcsan_setup_watchpoint(ptr, size, type, ip);
 		else if (unlikely(ctx->scoped_accesses.prev))
 			kcsan_check_scoped_accesses();
 	}
@@ -757,7 +764,7 @@ kcsan_begin_scoped_access(const volatile void *ptr, size_t size, int type,
 {
 	struct kcsan_ctx *ctx = get_ctx();
 
-	__kcsan_check_access(ptr, size, type);
+	check_access(ptr, size, type, _RET_IP_);
 
 	ctx->disable_count++; /* Disable KCSAN, in case list debugging is on. */
 
@@ -765,6 +772,7 @@ kcsan_begin_scoped_access(const volatile void *ptr, size_t size, int type,
 	sa->ptr = ptr;
 	sa->size = size;
 	sa->type = type;
+	sa->ip = _RET_IP_;
 
 	if (!ctx->scoped_accesses.prev) /* Lazy initialize list head. */
 		INIT_LIST_HEAD(&ctx->scoped_accesses);
@@ -796,13 +804,13 @@ void kcsan_end_scoped_access(struct kcsan_scoped_access *sa)
 
 	ctx->disable_count--;
 
-	__kcsan_check_access(sa->ptr, sa->size, sa->type);
+	check_access(sa->ptr, sa->size, sa->type, sa->ip);
 }
 EXPORT_SYMBOL(kcsan_end_scoped_access);
 
 void __kcsan_check_access(const volatile void *ptr, size_t size, int type)
 {
-	check_access(ptr, size, type);
+	check_access(ptr, size, type, _RET_IP_);
 }
 EXPORT_SYMBOL(__kcsan_check_access);
 
@@ -823,7 +831,7 @@ EXPORT_SYMBOL(__kcsan_check_access);
 	void __tsan_read##size(void *ptr);                                     \
 	void __tsan_read##size(void *ptr)                                      \
 	{                                                                      \
-		check_access(ptr, size, 0);                                    \
+		check_access(ptr, size, 0, _RET_IP_);                          \
 	}                                                                      \
 	EXPORT_SYMBOL(__tsan_read##size);                                      \
 	void __tsan_unaligned_read##size(void *ptr)                            \
@@ -832,7 +840,7 @@ EXPORT_SYMBOL(__kcsan_check_access);
 	void __tsan_write##size(void *ptr);                                    \
 	void __tsan_write##size(void *ptr)                                     \
 	{                                                                      \
-		check_access(ptr, size, KCSAN_ACCESS_WRITE);                   \
+		check_access(ptr, size, KCSAN_ACCESS_WRITE, _RET_IP_);         \
 	}                                                                      \
 	EXPORT_SYMBOL(__tsan_write##size);                                     \
 	void __tsan_unaligned_write##size(void *ptr)                           \
@@ -842,7 +850,8 @@ EXPORT_SYMBOL(__kcsan_check_access);
 	void __tsan_read_write##size(void *ptr)                                \
 	{                                                                      \
 		check_access(ptr, size,                                        \
-			     KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE);      \
+			     KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE,       \
+			     _RET_IP_);                                        \
 	}                                                                      \
 	EXPORT_SYMBOL(__tsan_read_write##size);                                \
 	void __tsan_unaligned_read_write##size(void *ptr)                      \
@@ -858,14 +867,14 @@ DEFINE_TSAN_READ_WRITE(16);
 void __tsan_read_range(void *ptr, size_t size);
 void __tsan_read_range(void *ptr, size_t size)
 {
-	check_access(ptr, size, 0);
+	check_access(ptr, size, 0, _RET_IP_);
 }
 EXPORT_SYMBOL(__tsan_read_range);
 
 void __tsan_write_range(void *ptr, size_t size);
 void __tsan_write_range(void *ptr, size_t size)
 {
-	check_access(ptr, size, KCSAN_ACCESS_WRITE);
+	check_access(ptr, size, KCSAN_ACCESS_WRITE, _RET_IP_);
 }
 EXPORT_SYMBOL(__tsan_write_range);
 
@@ -886,7 +895,8 @@ EXPORT_SYMBOL(__tsan_write_range);
 				       IS_ALIGNED((unsigned long)ptr, size);   \
 		if (IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS) && is_atomic)      \
 			return;                                                \
-		check_access(ptr, size, is_atomic ? KCSAN_ACCESS_ATOMIC : 0);  \
+		check_access(ptr, size, is_atomic ? KCSAN_ACCESS_ATOMIC : 0,   \
+			     _RET_IP_);                                        \
 	}                                                                      \
 	EXPORT_SYMBOL(__tsan_volatile_read##size);                             \
 	void __tsan_unaligned_volatile_read##size(void *ptr)                   \
@@ -901,7 +911,8 @@ EXPORT_SYMBOL(__tsan_write_range);
 			return;                                                \
 		check_access(ptr, size,                                        \
 			     KCSAN_ACCESS_WRITE |                              \
-				     (is_atomic ? KCSAN_ACCESS_ATOMIC : 0));   \
+				     (is_atomic ? KCSAN_ACCESS_ATOMIC : 0),    \
+			     _RET_IP_);                                        \
 	}                                                                      \
 	EXPORT_SYMBOL(__tsan_volatile_write##size);                            \
 	void __tsan_unaligned_volatile_write##size(void *ptr)                  \
@@ -955,7 +966,7 @@ EXPORT_SYMBOL(__tsan_init);
 	u##bits __tsan_atomic##bits##_load(const u##bits *ptr, int memorder)                       \
 	{                                                                                          \
 		if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) {                                    \
-			check_access(ptr, bits / BITS_PER_BYTE, KCSAN_ACCESS_ATOMIC);              \
+			check_access(ptr, bits / BITS_PER_BYTE, KCSAN_ACCESS_ATOMIC, _RET_IP_);    \
 		}                                                                                  \
 		return __atomic_load_n(ptr, memorder);                                             \
 	}                                                                                          \
@@ -965,7 +976,7 @@ EXPORT_SYMBOL(__tsan_init);
 	{                                                                                          \
 		if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) {                                    \
 			check_access(ptr, bits / BITS_PER_BYTE,                                    \
-				     KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC);                    \
+				     KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC, _RET_IP_);          \
 		}                                                                                  \
 		__atomic_store_n(ptr, v, memorder);                                                \
 	}                                                                                          \
@@ -978,7 +989,7 @@ EXPORT_SYMBOL(__tsan_init);
 		if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) {                                    \
 			check_access(ptr, bits / BITS_PER_BYTE,                                    \
 				     KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE |                  \
-					     KCSAN_ACCESS_ATOMIC);                                 \
+					     KCSAN_ACCESS_ATOMIC, _RET_IP_);                       \
 		}                                                                                  \
 		return __atomic_##op##suffix(ptr, v, memorder);                                    \
 	}                                                                                          \
@@ -1010,7 +1021,7 @@ EXPORT_SYMBOL(__tsan_init);
 		if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) {                                    \
 			check_access(ptr, bits / BITS_PER_BYTE,                                    \
 				     KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE |                  \
-					     KCSAN_ACCESS_ATOMIC);                                 \
+					     KCSAN_ACCESS_ATOMIC, _RET_IP_);                       \
 		}                                                                                  \
 		return __atomic_compare_exchange_n(ptr, exp, val, weak, mo, fail_mo);              \
 	}                                                                                          \
@@ -1025,7 +1036,7 @@ EXPORT_SYMBOL(__tsan_init);
 		if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) {                                    \
 			check_access(ptr, bits / BITS_PER_BYTE,                                    \
 				     KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE |                  \
-					     KCSAN_ACCESS_ATOMIC);                                 \
+					     KCSAN_ACCESS_ATOMIC, _RET_IP_);                       \
 		}                                                                                  \
 		__atomic_compare_exchange_n(ptr, &exp, val, 0, mo, fail_mo);                       \
 		return exp;                                                                        \
diff --git a/kernel/kcsan/kcsan.h b/kernel/kcsan/kcsan.h
index f36e25c497ed8..ae33c2a7f07e3 100644
--- a/kernel/kcsan/kcsan.h
+++ b/kernel/kcsan/kcsan.h
@@ -121,7 +121,7 @@ enum kcsan_value_change {
  * to be consumed by the reporting thread. No report is printed yet.
  */
 void kcsan_report_set_info(const volatile void *ptr, size_t size, int access_type,
-			   int watchpoint_idx);
+			   unsigned long ip, int watchpoint_idx);
 
 /*
  * The calling thread observed that the watchpoint it set up was hit and
@@ -129,14 +129,14 @@ void kcsan_report_set_info(const volatile void *ptr, size_t size, int access_typ
  * thread.
  */
 void kcsan_report_known_origin(const volatile void *ptr, size_t size, int access_type,
-			       enum kcsan_value_change value_change, int watchpoint_idx,
-			       u64 old, u64 new, u64 mask);
+			       unsigned long ip, enum kcsan_value_change value_change,
+			       int watchpoint_idx, u64 old, u64 new, u64 mask);
 
 /*
  * No other thread was observed to race with the access, but the data value
  * before and after the stall differs. Reports a race of "unknown origin".
  */
 void kcsan_report_unknown_origin(const volatile void *ptr, size_t size, int access_type,
-				 u64 old, u64 new, u64 mask);
+				 unsigned long ip, u64 old, u64 new, u64 mask);
 
 #endif /* _KERNEL_KCSAN_KCSAN_H */
diff --git a/kernel/kcsan/kcsan_test.c b/kernel/kcsan/kcsan_test.c
index dc55fd5a36fcc..6607292385880 100644
--- a/kernel/kcsan/kcsan_test.c
+++ b/kernel/kcsan/kcsan_test.c
@@ -29,6 +29,11 @@
 #include <linux/types.h>
 #include <trace/events/printk.h>
 
+#define KCSAN_TEST_REQUIRES(test, cond) do {			\
+	if (!(cond))						\
+		kunit_skip((test), "Test requires: " #cond);	\
+} while (0)
+
 #ifdef CONFIG_CC_HAS_TSAN_COMPOUND_READ_BEFORE_WRITE
 #define __KCSAN_ACCESS_RW(alt) (KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE)
 #else
@@ -205,10 +210,12 @@ static bool report_matches(const struct expect_report *r)
 							"read-write" :
 							"write") :
 					       "read");
+		const bool is_atomic = (ty & KCSAN_ACCESS_ATOMIC);
+		const bool is_scoped = (ty & KCSAN_ACCESS_SCOPED);
 		const char *const access_type_aux =
-			(ty & KCSAN_ACCESS_ATOMIC) ?
-				      " (marked)" :
-				      ((ty & KCSAN_ACCESS_SCOPED) ? " (scoped)" : "");
+				(is_atomic && is_scoped)	? " (marked, scoped)"
+				: (is_atomic			? " (marked)"
+				   : (is_scoped			? " (scoped)" : ""));
 
 		if (i == 1) {
 			/* Access 2 */
@@ -333,7 +340,10 @@ static noinline void test_kernel_assert_bits_nochange(void)
 	ASSERT_EXCLUSIVE_BITS(test_var, ~TEST_CHANGE_BITS);
 }
 
-/* To check that scoped assertions do trigger anywhere in scope. */
+/*
+ * Scoped assertions do trigger anywhere in scope. However, the report should
+ * still only point at the start of the scope.
+ */
 static noinline void test_enter_scope(void)
 {
 	int x = 0;
@@ -488,17 +498,24 @@ static void test_concurrent_races(struct kunit *test)
 __no_kcsan
 static void test_novalue_change(struct kunit *test)
 {
-	const struct expect_report expect = {
+	const struct expect_report expect_rw = {
 		.access = {
 			{ test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE },
 			{ test_kernel_read, &test_var, sizeof(test_var), 0 },
 		},
 	};
+	const struct expect_report expect_ww = {
+		.access = {
+			{ test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE },
+			{ test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE },
+		},
+	};
 	bool match_expect = false;
 
+	test_kernel_write_nochange(); /* Reset value. */
 	begin_test_checks(test_kernel_write_nochange, test_kernel_read);
 	do {
-		match_expect = report_matches(&expect);
+		match_expect = report_matches(&expect_rw) || report_matches(&expect_ww);
 	} while (!end_test_checks(match_expect));
 	if (IS_ENABLED(CONFIG_KCSAN_REPORT_VALUE_CHANGE_ONLY))
 		KUNIT_EXPECT_FALSE(test, match_expect);
@@ -513,17 +530,24 @@ static void test_novalue_change(struct kunit *test)
 __no_kcsan
 static void test_novalue_change_exception(struct kunit *test)
 {
-	const struct expect_report expect = {
+	const struct expect_report expect_rw = {
 		.access = {
 			{ test_kernel_write_nochange_rcu, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE },
 			{ test_kernel_read, &test_var, sizeof(test_var), 0 },
 		},
 	};
+	const struct expect_report expect_ww = {
+		.access = {
+			{ test_kernel_write_nochange_rcu, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE },
+			{ test_kernel_write_nochange_rcu, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE },
+		},
+	};
 	bool match_expect = false;
 
+	test_kernel_write_nochange_rcu(); /* Reset value. */
 	begin_test_checks(test_kernel_write_nochange_rcu, test_kernel_read);
 	do {
-		match_expect = report_matches(&expect);
+		match_expect = report_matches(&expect_rw) || report_matches(&expect_ww);
 	} while (!end_test_checks(match_expect));
 	KUNIT_EXPECT_TRUE(test, match_expect);
 }
@@ -642,8 +666,7 @@ static void test_read_plain_atomic_write(struct kunit *test)
 	};
 	bool match_expect = false;
 
-	if (IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS))
-		return;
+	KCSAN_TEST_REQUIRES(test, !IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS));
 
 	begin_test_checks(test_kernel_read, test_kernel_write_atomic);
 	do {
@@ -665,8 +688,7 @@ static void test_read_plain_atomic_rmw(struct kunit *test)
 	};
 	bool match_expect = false;
 
-	if (IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS))
-		return;
+	KCSAN_TEST_REQUIRES(test, !IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS));
 
 	begin_test_checks(test_kernel_read, test_kernel_atomic_rmw);
 	do {
@@ -828,22 +850,22 @@ static void test_assert_exclusive_writer_scoped(struct kunit *test)
 			{ test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE },
 		},
 	};
-	const struct expect_report expect_anywhere = {
+	const struct expect_report expect_inscope = {
 		.access = {
 			{ test_enter_scope, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_SCOPED },
 			{ test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE },
 		},
 	};
 	bool match_expect_start = false;
-	bool match_expect_anywhere = false;
+	bool match_expect_inscope = false;
 
 	begin_test_checks(test_kernel_assert_writer_scoped, test_kernel_write_nochange);
 	do {
 		match_expect_start |= report_matches(&expect_start);
-		match_expect_anywhere |= report_matches(&expect_anywhere);
-	} while (!end_test_checks(match_expect_start && match_expect_anywhere));
+		match_expect_inscope |= report_matches(&expect_inscope);
+	} while (!end_test_checks(match_expect_inscope));
 	KUNIT_EXPECT_TRUE(test, match_expect_start);
-	KUNIT_EXPECT_TRUE(test, match_expect_anywhere);
+	KUNIT_EXPECT_FALSE(test, match_expect_inscope);
 }
 
 __no_kcsan
@@ -872,9 +894,9 @@ static void test_assert_exclusive_access_scoped(struct kunit *test)
 	do {
 		match_expect_start |= report_matches(&expect_start1) || report_matches(&expect_start2);
 		match_expect_inscope |= report_matches(&expect_inscope);
-	} while (!end_test_checks(match_expect_start && match_expect_inscope));
+	} while (!end_test_checks(match_expect_inscope));
 	KUNIT_EXPECT_TRUE(test, match_expect_start);
-	KUNIT_EXPECT_TRUE(test, match_expect_inscope);
+	KUNIT_EXPECT_FALSE(test, match_expect_inscope);
 }
 
 /*
@@ -1224,7 +1246,7 @@ static void kcsan_test_exit(void)
 	tracepoint_synchronize_unregister();
 }
 
-late_initcall(kcsan_test_init);
+late_initcall_sync(kcsan_test_init);
 module_exit(kcsan_test_exit);
 
 MODULE_LICENSE("GPL v2");
diff --git a/kernel/kcsan/report.c b/kernel/kcsan/report.c
index 21137929d4283..fc15077991c47 100644
--- a/kernel/kcsan/report.c
+++ b/kernel/kcsan/report.c
@@ -8,6 +8,7 @@
 #include <linux/debug_locks.h>
 #include <linux/delay.h>
 #include <linux/jiffies.h>
+#include <linux/kallsyms.h>
 #include <linux/kernel.h>
 #include <linux/lockdep.h>
 #include <linux/preempt.h>
@@ -31,6 +32,7 @@ struct access_info {
 	int			access_type;
 	int			task_pid;
 	int			cpu_id;
+	unsigned long		ip;
 };
 
 /*
@@ -245,6 +247,10 @@ static const char *get_access_type(int type)
 		return "write (scoped)";
 	case KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC:
 		return "write (marked, scoped)";
+	case KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE:
+		return "read-write (scoped)";
+	case KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC:
+		return "read-write (marked, scoped)";
 	default:
 		BUG();
 	}
@@ -300,6 +306,48 @@ static int get_stack_skipnr(const unsigned long stack_entries[], int num_entries
 	return skip;
 }
 
+/*
+ * Skips to the first entry that matches the function of @ip, and then replaces
+ * that entry with @ip, returning the entries to skip.
+ */
+static int
+replace_stack_entry(unsigned long stack_entries[], int num_entries, unsigned long ip)
+{
+	unsigned long symbolsize, offset;
+	unsigned long target_func;
+	int skip;
+
+	if (kallsyms_lookup_size_offset(ip, &symbolsize, &offset))
+		target_func = ip - offset;
+	else
+		goto fallback;
+
+	for (skip = 0; skip < num_entries; ++skip) {
+		unsigned long func = stack_entries[skip];
+
+		if (!kallsyms_lookup_size_offset(func, &symbolsize, &offset))
+			goto fallback;
+		func -= offset;
+
+		if (func == target_func) {
+			stack_entries[skip] = ip;
+			return skip;
+		}
+	}
+
+fallback:
+	/* Should not happen; the resulting stack trace is likely misleading. */
+	WARN_ONCE(1, "Cannot find frame for %pS in stack trace", (void *)ip);
+	return get_stack_skipnr(stack_entries, num_entries);
+}
+
+static int
+sanitize_stack_entries(unsigned long stack_entries[], int num_entries, unsigned long ip)
+{
+	return ip ? replace_stack_entry(stack_entries, num_entries, ip) :
+			  get_stack_skipnr(stack_entries, num_entries);
+}
+
 /* Compares symbolized strings of addr1 and addr2. */
 static int sym_strcmp(void *addr1, void *addr2)
 {
@@ -327,12 +375,12 @@ static void print_verbose_info(struct task_struct *task)
 
 static void print_report(enum kcsan_value_change value_change,
 			 const struct access_info *ai,
-			 const struct other_info *other_info,
+			 struct other_info *other_info,
 			 u64 old, u64 new, u64 mask)
 {
 	unsigned long stack_entries[NUM_STACK_ENTRIES] = { 0 };
 	int num_stack_entries = stack_trace_save(stack_entries, NUM_STACK_ENTRIES, 1);
-	int skipnr = get_stack_skipnr(stack_entries, num_stack_entries);
+	int skipnr = sanitize_stack_entries(stack_entries, num_stack_entries, ai->ip);
 	unsigned long this_frame = stack_entries[skipnr];
 	unsigned long other_frame = 0;
 	int other_skipnr = 0; /* silence uninit warnings */
@@ -344,8 +392,9 @@ static void print_report(enum kcsan_value_change value_change,
 		return;
 
 	if (other_info) {
-		other_skipnr = get_stack_skipnr(other_info->stack_entries,
-						other_info->num_stack_entries);
+		other_skipnr = sanitize_stack_entries(other_info->stack_entries,
+						      other_info->num_stack_entries,
+						      other_info->ai.ip);
 		other_frame = other_info->stack_entries[other_skipnr];
 
 		/* @value_change is only known for the other thread */
@@ -576,21 +625,23 @@ discard:
 }
 
 static struct access_info prepare_access_info(const volatile void *ptr, size_t size,
-					      int access_type)
+					      int access_type, unsigned long ip)
 {
 	return (struct access_info) {
 		.ptr		= ptr,
 		.size		= size,
 		.access_type	= access_type,
 		.task_pid	= in_task() ? task_pid_nr(current) : -1,
-		.cpu_id		= raw_smp_processor_id()
+		.cpu_id		= raw_smp_processor_id(),
+		/* Only replace stack entry with @ip if scoped access. */
+		.ip		= (access_type & KCSAN_ACCESS_SCOPED) ? ip : 0,
 	};
 }
 
 void kcsan_report_set_info(const volatile void *ptr, size_t size, int access_type,
-			   int watchpoint_idx)
+			   unsigned long ip, int watchpoint_idx)
 {
-	const struct access_info ai = prepare_access_info(ptr, size, access_type);
+	const struct access_info ai = prepare_access_info(ptr, size, access_type, ip);
 	unsigned long flags;
 
 	kcsan_disable_current();
@@ -603,10 +654,10 @@ void kcsan_report_set_info(const volatile void *ptr, size_t size, int access_typ
 }
 
 void kcsan_report_known_origin(const volatile void *ptr, size_t size, int access_type,
-			       enum kcsan_value_change value_change, int watchpoint_idx,
-			       u64 old, u64 new, u64 mask)
+			       unsigned long ip, enum kcsan_value_change value_change,
+			       int watchpoint_idx, u64 old, u64 new, u64 mask)
 {
-	const struct access_info ai = prepare_access_info(ptr, size, access_type);
+	const struct access_info ai = prepare_access_info(ptr, size, access_type, ip);
 	struct other_info *other_info = &other_infos[watchpoint_idx];
 	unsigned long flags = 0;
 
@@ -637,9 +688,9 @@ out:
 }
 
 void kcsan_report_unknown_origin(const volatile void *ptr, size_t size, int access_type,
-				 u64 old, u64 new, u64 mask)
+				 unsigned long ip, u64 old, u64 new, u64 mask)
 {
-	const struct access_info ai = prepare_access_info(ptr, size, access_type);
+	const struct access_info ai = prepare_access_info(ptr, size, access_type, ip);
 	unsigned long flags;
 
 	kcsan_disable_current();
diff --git a/kernel/kcsan/selftest.c b/kernel/kcsan/selftest.c
index 7f29cb0f5e634..b4295a3892b7c 100644
--- a/kernel/kcsan/selftest.c
+++ b/kernel/kcsan/selftest.c
@@ -18,7 +18,7 @@
 #define ITERS_PER_TEST 2000
 
 /* Test requirements. */
-static bool test_requires(void)
+static bool __init test_requires(void)
 {
 	/* random should be initialized for the below tests */
 	return prandom_u32() + prandom_u32() != 0;
@@ -28,14 +28,18 @@ static bool test_requires(void)
  * Test watchpoint encode and decode: check that encoding some access's info,
  * and then subsequent decode preserves the access's info.
  */
-static bool test_encode_decode(void)
+static bool __init test_encode_decode(void)
 {
 	int i;
 
 	for (i = 0; i < ITERS_PER_TEST; ++i) {
 		size_t size = prandom_u32_max(MAX_ENCODABLE_SIZE) + 1;
 		bool is_write = !!prandom_u32_max(2);
+		unsigned long verif_masked_addr;
+		long encoded_watchpoint;
+		bool verif_is_write;
 		unsigned long addr;
+		size_t verif_size;
 
 		prandom_bytes(&addr, sizeof(addr));
 		if (addr < PAGE_SIZE)
@@ -44,53 +48,37 @@ static bool test_encode_decode(void)
 		if (WARN_ON(!check_encodable(addr, size)))
 			return false;
 
-		/* Encode and decode */
-		{
-			const long encoded_watchpoint =
-				encode_watchpoint(addr, size, is_write);
-			unsigned long verif_masked_addr;
-			size_t verif_size;
-			bool verif_is_write;
-
-			/* Check special watchpoints */
-			if (WARN_ON(decode_watchpoint(
-				    INVALID_WATCHPOINT, &verif_masked_addr,
-				    &verif_size, &verif_is_write)))
-				return false;
-			if (WARN_ON(decode_watchpoint(
-				    CONSUMED_WATCHPOINT, &verif_masked_addr,
-				    &verif_size, &verif_is_write)))
-				return false;
-
-			/* Check decoding watchpoint returns same data */
-			if (WARN_ON(!decode_watchpoint(
-				    encoded_watchpoint, &verif_masked_addr,
-				    &verif_size, &verif_is_write)))
-				return false;
-			if (WARN_ON(verif_masked_addr !=
-				    (addr & WATCHPOINT_ADDR_MASK)))
-				goto fail;
-			if (WARN_ON(verif_size != size))
-				goto fail;
-			if (WARN_ON(is_write != verif_is_write))
-				goto fail;
-
-			continue;
-fail:
-			pr_err("%s fail: %s %zu bytes @ %lx -> encoded: %lx -> %s %zu bytes @ %lx\n",
-			       __func__, is_write ? "write" : "read", size,
-			       addr, encoded_watchpoint,
-			       verif_is_write ? "write" : "read", verif_size,
-			       verif_masked_addr);
+		encoded_watchpoint = encode_watchpoint(addr, size, is_write);
+
+		/* Check special watchpoints */
+		if (WARN_ON(decode_watchpoint(INVALID_WATCHPOINT, &verif_masked_addr, &verif_size, &verif_is_write)))
 			return false;
-		}
+		if (WARN_ON(decode_watchpoint(CONSUMED_WATCHPOINT, &verif_masked_addr, &verif_size, &verif_is_write)))
+			return false;
+
+		/* Check decoding watchpoint returns same data */
+		if (WARN_ON(!decode_watchpoint(encoded_watchpoint, &verif_masked_addr, &verif_size, &verif_is_write)))
+			return false;
+		if (WARN_ON(verif_masked_addr != (addr & WATCHPOINT_ADDR_MASK)))
+			goto fail;
+		if (WARN_ON(verif_size != size))
+			goto fail;
+		if (WARN_ON(is_write != verif_is_write))
+			goto fail;
+
+		continue;
+fail:
+		pr_err("%s fail: %s %zu bytes @ %lx -> encoded: %lx -> %s %zu bytes @ %lx\n",
+		       __func__, is_write ? "write" : "read", size, addr, encoded_watchpoint,
+		       verif_is_write ? "write" : "read", verif_size, verif_masked_addr);
+		return false;
 	}
 
 	return true;
 }
 
 /* Test access matching function. */
-static bool test_matching_access(void)
+static bool __init test_matching_access(void)
 {
 	if (WARN_ON(!matching_access(10, 1, 10, 1)))
 		return false;
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index 7c5a4a087cc73..397ac13d2ef75 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -1022,23 +1022,23 @@ static int __init lock_torture_init(void)
 	if (onoff_interval > 0) {
 		firsterr = torture_onoff_init(onoff_holdoff * HZ,
 					      onoff_interval * HZ, NULL);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	if (shuffle_interval > 0) {
 		firsterr = torture_shuffle_init(shuffle_interval);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	if (shutdown_secs > 0) {
 		firsterr = torture_shutdown_init(shutdown_secs,
 						 lock_torture_cleanup);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	if (stutter > 0) {
 		firsterr = torture_stutter_init(stutter, stutter);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 
@@ -1082,7 +1082,7 @@ static int __init lock_torture_init(void)
 		/* Create writer. */
 		firsterr = torture_create_kthread(lock_torture_writer, &cxt.lwsa[i],
 						  writer_tasks[i]);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 
 	create_reader:
@@ -1091,13 +1091,13 @@ static int __init lock_torture_init(void)
 		/* Create reader. */
 		firsterr = torture_create_kthread(lock_torture_reader, &cxt.lrsa[j],
 						  reader_tasks[j]);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	if (stat_interval > 0) {
 		firsterr = torture_create_kthread(lock_torture_stats, NULL,
 						  stats_task);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	torture_init_end();
diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig
index 3128b7cf8e1fd..4005f2728f1a6 100644
--- a/kernel/rcu/Kconfig
+++ b/kernel/rcu/Kconfig
@@ -169,24 +169,6 @@ config RCU_FANOUT_LEAF
 
 	  Take the default if unsure.
 
-config RCU_FAST_NO_HZ
-	bool "Accelerate last non-dyntick-idle CPU's grace periods"
-	depends on NO_HZ_COMMON && SMP && RCU_EXPERT
-	default n
-	help
-	  This option permits CPUs to enter dynticks-idle state even if
-	  they have RCU callbacks queued, and prevents RCU from waking
-	  these CPUs up more than roughly once every four jiffies (by
-	  default, you can adjust this using the rcutree.rcu_idle_gp_delay
-	  parameter), thus improving energy efficiency.  On the other
-	  hand, this option increases the duration of RCU grace periods,
-	  for example, slowing down synchronize_rcu().
-
-	  Say Y if energy efficiency is critically important, and you
-	  	don't care about increased grace-period durations.
-
-	  Say N if you are unsure.
-
 config RCU_BOOST
 	bool "Enable RCU priority boosting"
 	depends on (RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT) || PREEMPT_RT
diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c
index 2cc34a22a5060..228f143bf935d 100644
--- a/kernel/rcu/rcuscale.c
+++ b/kernel/rcu/rcuscale.c
@@ -758,7 +758,7 @@ kfree_scale_init(void)
 		init_waitqueue_head(&shutdown_wq);
 		firsterr = torture_create_kthread(kfree_scale_shutdown, NULL,
 						  shutdown_task);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 		schedule_timeout_uninterruptible(1);
 	}
@@ -775,7 +775,7 @@ kfree_scale_init(void)
 	for (i = 0; i < kfree_nrealthreads; i++) {
 		firsterr = torture_create_kthread(kfree_scale_thread, (void *)i,
 						  kfree_reader_tasks[i]);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 
@@ -838,7 +838,7 @@ rcu_scale_init(void)
 		init_waitqueue_head(&shutdown_wq);
 		firsterr = torture_create_kthread(rcu_scale_shutdown, NULL,
 						  shutdown_task);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 		schedule_timeout_uninterruptible(1);
 	}
@@ -852,7 +852,7 @@ rcu_scale_init(void)
 	for (i = 0; i < nrealreaders; i++) {
 		firsterr = torture_create_kthread(rcu_scale_reader, (void *)i,
 						  reader_tasks[i]);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	while (atomic_read(&n_rcu_scale_reader_started) < nrealreaders)
@@ -879,7 +879,7 @@ rcu_scale_init(void)
 		}
 		firsterr = torture_create_kthread(rcu_scale_writer, (void *)i,
 						  writer_tasks[i]);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	torture_init_end();
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index ab4215266ebee..503e14e62e8f2 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -53,15 +53,18 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com> and Josh Triplett <josh@joshtriplett.org>");
 
 /* Bits for ->extendables field, extendables param, and related definitions. */
-#define RCUTORTURE_RDR_SHIFT	 8	/* Put SRCU index in upper bits. */
-#define RCUTORTURE_RDR_MASK	 ((1 << RCUTORTURE_RDR_SHIFT) - 1)
+#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_BH	 0x01	/* Extend readers by disabling bh. */
 #define RCUTORTURE_RDR_IRQ	 0x02	/*  ... disabling interrupts. */
 #define RCUTORTURE_RDR_PREEMPT	 0x04	/*  ... disabling preemption. */
 #define RCUTORTURE_RDR_RBH	 0x08	/*  ... rcu_read_lock_bh(). */
 #define RCUTORTURE_RDR_SCHED	 0x10	/*  ... rcu_read_lock_sched(). */
-#define RCUTORTURE_RDR_RCU	 0x20	/*  ... entering another RCU reader. */
-#define RCUTORTURE_RDR_NBITS	 6	/* Number of bits defined above. */
+#define RCUTORTURE_RDR_RCU_1	 0x20	/*  ... entering another RCU reader. */
+#define RCUTORTURE_RDR_RCU_2	 0x40	/*  ... entering another RCU reader. */
+#define RCUTORTURE_RDR_NBITS	 7	/* Number of bits defined above. */
 #define RCUTORTURE_MAX_EXTEND	 \
 	(RCUTORTURE_RDR_BH | RCUTORTURE_RDR_IRQ | RCUTORTURE_RDR_PREEMPT | \
 	 RCUTORTURE_RDR_RBH | RCUTORTURE_RDR_SCHED)
@@ -346,6 +349,7 @@ struct rcu_torture_ops {
 	int can_boost;
 	int extendables;
 	int slow_gps;
+	int no_pi_lock;
 	const char *name;
 };
 
@@ -667,6 +671,7 @@ static struct rcu_torture_ops srcu_ops = {
 	.cb_barrier	= srcu_torture_barrier,
 	.stats		= srcu_torture_stats,
 	.irq_capable	= 1,
+	.no_pi_lock	= IS_ENABLED(CONFIG_TINY_SRCU),
 	.name		= "srcu"
 };
 
@@ -700,6 +705,7 @@ static struct rcu_torture_ops srcud_ops = {
 	.cb_barrier	= srcu_torture_barrier,
 	.stats		= srcu_torture_stats,
 	.irq_capable	= 1,
+	.no_pi_lock	= IS_ENABLED(CONFIG_TINY_SRCU),
 	.name		= "srcud"
 };
 
@@ -720,6 +726,7 @@ static struct rcu_torture_ops busted_srcud_ops = {
 	.cb_barrier	= srcu_torture_barrier,
 	.stats		= srcu_torture_stats,
 	.irq_capable	= 1,
+	.no_pi_lock	= IS_ENABLED(CONFIG_TINY_SRCU),
 	.extendables	= RCUTORTURE_MAX_EXTEND,
 	.name		= "busted_srcud"
 };
@@ -1420,46 +1427,64 @@ static void rcutorture_one_extend(int *readstate, int newstate,
 				  struct rt_read_seg *rtrsp)
 {
 	unsigned long flags;
-	int idxnew = -1;
-	int idxold = *readstate;
+	int idxnew1 = -1;
+	int idxnew2 = -1;
+	int idxold1 = *readstate;
+	int idxold2 = idxold1;
 	int statesnew = ~*readstate & newstate;
 	int statesold = *readstate & ~newstate;
 
-	WARN_ON_ONCE(idxold < 0);
-	WARN_ON_ONCE((idxold >> RCUTORTURE_RDR_SHIFT) > 1);
+	WARN_ON_ONCE(idxold2 < 0);
+	WARN_ON_ONCE((idxold2 >> RCUTORTURE_RDR_SHIFT_2) > 1);
 	rtrsp->rt_readstate = newstate;
 
 	/* First, put new protection in place to avoid critical-section gap. */
 	if (statesnew & RCUTORTURE_RDR_BH)
 		local_bh_disable();
+	if (statesnew & RCUTORTURE_RDR_RBH)
+		rcu_read_lock_bh();
 	if (statesnew & RCUTORTURE_RDR_IRQ)
 		local_irq_disable();
 	if (statesnew & RCUTORTURE_RDR_PREEMPT)
 		preempt_disable();
-	if (statesnew & RCUTORTURE_RDR_RBH)
-		rcu_read_lock_bh();
 	if (statesnew & RCUTORTURE_RDR_SCHED)
 		rcu_read_lock_sched();
-	if (statesnew & RCUTORTURE_RDR_RCU)
-		idxnew = cur_ops->readlock() << RCUTORTURE_RDR_SHIFT;
+	if (statesnew & RCUTORTURE_RDR_RCU_1)
+		idxnew1 = (cur_ops->readlock() & 0x1) << RCUTORTURE_RDR_SHIFT_1;
+	if (statesnew & RCUTORTURE_RDR_RCU_2)
+		idxnew2 = (cur_ops->readlock() & 0x1) << RCUTORTURE_RDR_SHIFT_2;
 
-	/* Next, remove old protection, irq first due to bh conflict. */
+	/*
+	 * Next, remove old protection, in decreasing order of strength
+	 * to avoid unlock paths that aren't safe in the stronger
+	 * context. Namely: BH can not be enabled with disabled interrupts.
+	 * Additionally PREEMPT_RT requires that BH is enabled in preemptible
+	 * context.
+	 */
 	if (statesold & RCUTORTURE_RDR_IRQ)
 		local_irq_enable();
-	if (statesold & RCUTORTURE_RDR_BH)
-		local_bh_enable();
 	if (statesold & RCUTORTURE_RDR_PREEMPT)
 		preempt_enable();
-	if (statesold & RCUTORTURE_RDR_RBH)
-		rcu_read_unlock_bh();
 	if (statesold & RCUTORTURE_RDR_SCHED)
 		rcu_read_unlock_sched();
-	if (statesold & RCUTORTURE_RDR_RCU) {
-		bool lockit = !statesnew && !(torture_random(trsp) & 0xffff);
+	if (statesold & RCUTORTURE_RDR_BH)
+		local_bh_enable();
+	if (statesold & RCUTORTURE_RDR_RBH)
+		rcu_read_unlock_bh();
+	if (statesold & RCUTORTURE_RDR_RCU_2) {
+		cur_ops->readunlock((idxold2 >> RCUTORTURE_RDR_SHIFT_2) & 0x1);
+		WARN_ON_ONCE(idxnew2 != -1);
+		idxold2 = 0;
+	}
+	if (statesold & RCUTORTURE_RDR_RCU_1) {
+		bool lockit;
 
+		lockit = !cur_ops->no_pi_lock && !statesnew && !(torture_random(trsp) & 0xffff);
 		if (lockit)
 			raw_spin_lock_irqsave(&current->pi_lock, flags);
-		cur_ops->readunlock(idxold >> RCUTORTURE_RDR_SHIFT);
+		cur_ops->readunlock((idxold1 >> RCUTORTURE_RDR_SHIFT_1) & 0x1);
+		WARN_ON_ONCE(idxnew1 != -1);
+		idxold1 = 0;
 		if (lockit)
 			raw_spin_unlock_irqrestore(&current->pi_lock, flags);
 	}
@@ -1469,13 +1494,19 @@ static void rcutorture_one_extend(int *readstate, int newstate,
 		cur_ops->read_delay(trsp, rtrsp);
 
 	/* Update the reader state. */
-	if (idxnew == -1)
-		idxnew = idxold & ~RCUTORTURE_RDR_MASK;
-	WARN_ON_ONCE(idxnew < 0);
-	WARN_ON_ONCE((idxnew >> RCUTORTURE_RDR_SHIFT) > 1);
-	*readstate = idxnew | newstate;
-	WARN_ON_ONCE((*readstate >> RCUTORTURE_RDR_SHIFT) < 0);
-	WARN_ON_ONCE((*readstate >> RCUTORTURE_RDR_SHIFT) > 1);
+	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);
 }
 
 /* Return the biggest extendables mask given current RCU and boot parameters. */
@@ -1485,7 +1516,7 @@ static int rcutorture_extend_mask_max(void)
 
 	WARN_ON_ONCE(extendables & ~RCUTORTURE_MAX_EXTEND);
 	mask = extendables & RCUTORTURE_MAX_EXTEND & cur_ops->extendables;
-	mask = mask | RCUTORTURE_RDR_RCU;
+	mask = mask | RCUTORTURE_RDR_RCU_1 | RCUTORTURE_RDR_RCU_2;
 	return mask;
 }
 
@@ -1496,19 +1527,45 @@ rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp)
 	int mask = rcutorture_extend_mask_max();
 	unsigned long randmask1 = torture_random(trsp) >> 8;
 	unsigned long randmask2 = randmask1 >> 3;
+	unsigned long preempts = RCUTORTURE_RDR_PREEMPT | RCUTORTURE_RDR_SCHED;
+	unsigned long preempts_irq = preempts | RCUTORTURE_RDR_IRQ;
+	unsigned long bhs = RCUTORTURE_RDR_BH | RCUTORTURE_RDR_RBH;
 
-	WARN_ON_ONCE(mask >> RCUTORTURE_RDR_SHIFT);
+	WARN_ON_ONCE(mask >> RCUTORTURE_RDR_SHIFT_1);
 	/* Mostly only one bit (need preemption!), sometimes lots of bits. */
 	if (!(randmask1 & 0x7))
 		mask = mask & randmask2;
 	else
 		mask = mask & (1 << (randmask2 % RCUTORTURE_RDR_NBITS));
-	/* Can't enable bh w/irq disabled. */
-	if ((mask & RCUTORTURE_RDR_IRQ) &&
-	    ((!(mask & RCUTORTURE_RDR_BH) && (oldmask & RCUTORTURE_RDR_BH)) ||
-	     (!(mask & RCUTORTURE_RDR_RBH) && (oldmask & RCUTORTURE_RDR_RBH))))
-		mask |= RCUTORTURE_RDR_BH | RCUTORTURE_RDR_RBH;
-	return mask ?: RCUTORTURE_RDR_RCU;
+
+	// Can't have nested RCU reader without outer RCU reader.
+	if (!(mask & RCUTORTURE_RDR_RCU_1) && (mask & RCUTORTURE_RDR_RCU_2)) {
+		if (oldmask & RCUTORTURE_RDR_RCU_1)
+			mask &= ~RCUTORTURE_RDR_RCU_2;
+		else
+			mask |= RCUTORTURE_RDR_RCU_1;
+	}
+
+	/*
+	 * Can't enable bh w/irq disabled.
+	 */
+	if (mask & RCUTORTURE_RDR_IRQ)
+		mask |= oldmask & bhs;
+
+	/*
+	 * Ideally these sequences would be detected in debug builds
+	 * (regardless of RT), but until then don't stop testing
+	 * them on non-RT.
+	 */
+	if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
+		/* Can't modify BH in atomic context */
+		if (oldmask & preempts_irq)
+			mask &= ~bhs;
+		if ((oldmask | mask) & preempts_irq)
+			mask |= oldmask & bhs;
+	}
+
+	return mask ?: RCUTORTURE_RDR_RCU_1;
 }
 
 /*
@@ -1602,7 +1659,7 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp, long myid)
 			  rcu_torture_writer_state,
 			  cookie, cur_ops->get_gp_state());
 	rcutorture_one_extend(&readstate, 0, trsp, rtrsp);
-	WARN_ON_ONCE(readstate & RCUTORTURE_RDR_MASK);
+	WARN_ON_ONCE(readstate);
 	// This next splat is expected behavior if leakpointer, especially
 	// for CONFIG_RCU_STRICT_GRACE_PERIOD=y kernels.
 	WARN_ON_ONCE(leakpointer && READ_ONCE(p->rtort_pipe_count) > 1);
@@ -2449,7 +2506,7 @@ static int __init rcu_torture_fwd_prog_init(void)
 	}
 	if (stall_cpu > 0) {
 		VERBOSE_TOROUT_STRING("rcu_torture_fwd_prog_init: Disabled, conflicts with CPU-stall testing");
-		if (IS_MODULE(CONFIG_RCU_TORTURE_TESTS))
+		if (IS_MODULE(CONFIG_RCU_TORTURE_TEST))
 			return -EINVAL; /* In module, can fail back to user. */
 		WARN_ON(1); /* Make sure rcutorture notices conflict. */
 		return 0;
@@ -2741,7 +2798,7 @@ static int rcu_torture_read_exit(void *unused)
 static int rcu_torture_read_exit_init(void)
 {
 	if (read_exit_burst <= 0)
-		return -EINVAL;
+		return 0;
 	init_waitqueue_head(&read_exit_wq);
 	read_exit_child_stop = false;
 	read_exit_child_stopped = false;
@@ -2819,7 +2876,7 @@ rcu_torture_cleanup(void)
 		 rcutorture_seq_diff(gp_seq, start_gp_seq));
 	torture_stop_kthread(rcu_torture_stats, stats_task);
 	torture_stop_kthread(rcu_torture_fqs, fqs_task);
-	if (rcu_torture_can_boost())
+	if (rcu_torture_can_boost() && rcutor_hp >= 0)
 		cpuhp_remove_state(rcutor_hp);
 
 	/*
@@ -3037,7 +3094,7 @@ rcu_torture_init(void)
 	rcu_torture_write_types();
 	firsterr = torture_create_kthread(rcu_torture_writer, NULL,
 					  writer_task);
-	if (firsterr)
+	if (torture_init_error(firsterr))
 		goto unwind;
 	if (nfakewriters > 0) {
 		fakewriter_tasks = kcalloc(nfakewriters,
@@ -3052,7 +3109,7 @@ rcu_torture_init(void)
 	for (i = 0; i < nfakewriters; i++) {
 		firsterr = torture_create_kthread(rcu_torture_fakewriter,
 						  NULL, fakewriter_tasks[i]);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	reader_tasks = kcalloc(nrealreaders, sizeof(reader_tasks[0]),
@@ -3068,7 +3125,7 @@ rcu_torture_init(void)
 		rcu_torture_reader_mbchk[i].rtc_chkrdr = -1;
 		firsterr = torture_create_kthread(rcu_torture_reader, (void *)i,
 						  reader_tasks[i]);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	nrealnocbers = nocbs_nthreads;
@@ -3088,18 +3145,18 @@ rcu_torture_init(void)
 	}
 	for (i = 0; i < nrealnocbers; i++) {
 		firsterr = torture_create_kthread(rcu_nocb_toggle, NULL, nocb_tasks[i]);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	if (stat_interval > 0) {
 		firsterr = torture_create_kthread(rcu_torture_stats, NULL,
 						  stats_task);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	if (test_no_idle_hz && shuffle_interval > 0) {
 		firsterr = torture_shuffle_init(shuffle_interval * HZ);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	if (stutter < 0)
@@ -3109,7 +3166,7 @@ rcu_torture_init(void)
 
 		t = cur_ops->stall_dur ? cur_ops->stall_dur() : stutter * HZ;
 		firsterr = torture_stutter_init(stutter * HZ, t);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	if (fqs_duration < 0)
@@ -3118,7 +3175,7 @@ rcu_torture_init(void)
 		/* Create the fqs thread */
 		firsterr = torture_create_kthread(rcu_torture_fqs, NULL,
 						  fqs_task);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	if (test_boost_interval < 1)
@@ -3132,9 +3189,9 @@ rcu_torture_init(void)
 		firsterr = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "RCU_TORTURE",
 					     rcutorture_booster_init,
 					     rcutorture_booster_cleanup);
-		if (firsterr < 0)
-			goto unwind;
 		rcutor_hp = firsterr;
+		if (torture_init_error(firsterr))
+			goto unwind;
 
 		// Testing RCU priority boosting requires rcutorture do
 		// some serious abuse.  Counter this by running ksoftirqd
@@ -3153,23 +3210,23 @@ rcu_torture_init(void)
 	}
 	shutdown_jiffies = jiffies + shutdown_secs * HZ;
 	firsterr = torture_shutdown_init(shutdown_secs, rcu_torture_cleanup);
-	if (firsterr)
+	if (torture_init_error(firsterr))
 		goto unwind;
 	firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval,
 				      rcutorture_sync);
-	if (firsterr)
+	if (torture_init_error(firsterr))
 		goto unwind;
 	firsterr = rcu_torture_stall_init();
-	if (firsterr)
+	if (torture_init_error(firsterr))
 		goto unwind;
 	firsterr = rcu_torture_fwd_prog_init();
-	if (firsterr)
+	if (torture_init_error(firsterr))
 		goto unwind;
 	firsterr = rcu_torture_barrier_init();
-	if (firsterr)
+	if (torture_init_error(firsterr))
 		goto unwind;
 	firsterr = rcu_torture_read_exit_init();
-	if (firsterr)
+	if (torture_init_error(firsterr))
 		goto unwind;
 	if (object_debug)
 		rcu_test_debug_objects();
diff --git a/kernel/rcu/refscale.c b/kernel/rcu/refscale.c
index 66dc14cf5687e..1631ef8a138db 100644
--- a/kernel/rcu/refscale.c
+++ b/kernel/rcu/refscale.c
@@ -824,7 +824,7 @@ ref_scale_init(void)
 		init_waitqueue_head(&shutdown_wq);
 		firsterr = torture_create_kthread(ref_scale_shutdown, NULL,
 						  shutdown_task);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 		schedule_timeout_uninterruptible(1);
 	}
@@ -851,7 +851,7 @@ ref_scale_init(void)
 	for (i = 0; i < nreaders; i++) {
 		firsterr = torture_create_kthread(ref_scale_reader, (void *)i,
 						  reader_tasks[i].task);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 
 		init_waitqueue_head(&(reader_tasks[i].wq));
@@ -860,7 +860,7 @@ ref_scale_init(void)
 	// Main Task
 	init_waitqueue_head(&main_wq);
 	firsterr = torture_create_kthread(main_func, NULL, main_task);
-	if (firsterr)
+	if (torture_init_error(firsterr))
 		goto unwind;
 
 	torture_init_end();
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index a0ba2ed49bc61..92c002d654828 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -99,7 +99,7 @@ void __srcu_read_unlock(struct srcu_struct *ssp, int idx)
 	int newval = READ_ONCE(ssp->srcu_lock_nesting[idx]) - 1;
 
 	WRITE_ONCE(ssp->srcu_lock_nesting[idx], newval);
-	if (!newval && READ_ONCE(ssp->srcu_gp_waiting))
+	if (!newval && READ_ONCE(ssp->srcu_gp_waiting) && in_task())
 		swake_up_one(&ssp->srcu_wq);
 }
 EXPORT_SYMBOL_GPL(__srcu_read_unlock);
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 806160c44b172..e4a32db9f7122 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -197,6 +197,7 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 	 * This loop is terminated by the system going down.  ;-)
 	 */
 	for (;;) {
+		set_tasks_gp_state(rtp, RTGS_WAIT_CBS);
 
 		/* Pick up any new callbacks. */
 		raw_spin_lock_irqsave(&rtp->cbs_lock, flags);
@@ -236,8 +237,6 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 		}
 		/* Paranoid sleep to keep this from entering a tight loop */
 		schedule_timeout_idle(rtp->gp_sleep);
-
-		set_tasks_gp_state(rtp, RTGS_WAIT_CBS);
 	}
 }
 
@@ -369,7 +368,7 @@ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp)
 ////////////////////////////////////////////////////////////////////////
 //
 // Simple variant of RCU whose quiescent states are voluntary context
-// switch, cond_resched_rcu_qs(), user-space execution, and idle.
+// switch, cond_resched_tasks_rcu_qs(), user-space execution, and idle.
 // As such, grace periods can take one good long time.  There are no
 // read-side primitives similar to rcu_read_lock() and rcu_read_unlock()
 // because this implementation is intended to get the system into a safe
@@ -540,7 +539,7 @@ DEFINE_RCU_TASKS(rcu_tasks, rcu_tasks_wait_gp, call_rcu_tasks, "RCU Tasks");
  * period elapses, in other words after all currently executing RCU
  * read-side critical sections have completed. call_rcu_tasks() assumes
  * that the read-side critical sections end at a voluntary context
- * switch (not a preemption!), cond_resched_rcu_qs(), entry into idle,
+ * switch (not a preemption!), cond_resched_tasks_rcu_qs(), entry into idle,
  * or transition to usermode execution.  As such, there are no read-side
  * primitives analogous to rcu_read_lock() and rcu_read_unlock() because
  * this primitive is intended to determine that all tasks have passed
@@ -678,11 +677,11 @@ DEFINE_RCU_TASKS(rcu_tasks_rude, rcu_tasks_rude_wait_gp, call_rcu_tasks_rude,
  * period elapses, in other words after all currently executing RCU
  * read-side critical sections have completed. call_rcu_tasks_rude()
  * assumes that the read-side critical sections end at context switch,
- * cond_resched_rcu_qs(), or transition to usermode execution.  As such,
- * there are no read-side primitives analogous to rcu_read_lock() and
- * rcu_read_unlock() because this primitive is intended to determine
- * that all tasks have passed through a safe state, not so much for
- * data-structure synchronization.
+ * cond_resched_tasks_rcu_qs(), or transition to usermode execution (as
+ * usermode execution is schedulable). As such, there are no read-side
+ * primitives analogous to rcu_read_lock() and rcu_read_unlock() because
+ * this primitive is intended to determine that all tasks have passed
+ * through a safe state, not so much for data-structure synchronization.
  *
  * See the description of call_rcu() for more detailed information on
  * memory ordering guarantees.
@@ -700,8 +699,8 @@ EXPORT_SYMBOL_GPL(call_rcu_tasks_rude);
  * grace period has elapsed, in other words after all currently
  * executing rcu-tasks read-side critical sections have elapsed.  These
  * read-side critical sections are delimited by calls to schedule(),
- * cond_resched_tasks_rcu_qs(), userspace execution, and (in theory,
- * anyway) cond_resched().
+ * cond_resched_tasks_rcu_qs(), userspace execution (which is a schedulable
+ * context), and (in theory, anyway) cond_resched().
  *
  * This is a very specialized primitive, intended only for a few uses in
  * tracing and other situations requiring manipulation of function preambles
@@ -758,7 +757,7 @@ EXPORT_SYMBOL_GPL(show_rcu_tasks_rude_gp_kthread);
 // 2.	Protects code in the idle loop, exception entry/exit, and
 //	CPU-hotplug code paths, similar to the capabilities of SRCU.
 //
-// 3.	Avoids expensive read-side instruction, having overhead similar
+// 3.	Avoids expensive read-side instructions, having overhead similar
 //	to that of Preemptible RCU.
 //
 // There are of course downsides.  The grace-period code can send IPIs to
@@ -848,7 +847,7 @@ static void rcu_read_unlock_iw(struct irq_work *iwp)
 static DEFINE_IRQ_WORK(rcu_tasks_trace_iw, rcu_read_unlock_iw);
 
 /* If we are the last reader, wake up the grace-period kthread. */
-void rcu_read_unlock_trace_special(struct task_struct *t, int nesting)
+void rcu_read_unlock_trace_special(struct task_struct *t)
 {
 	int nq = READ_ONCE(t->trc_reader_special.b.need_qs);
 
@@ -858,7 +857,7 @@ void rcu_read_unlock_trace_special(struct task_struct *t, int nesting)
 	// Update .need_qs before ->trc_reader_nesting for irq/NMI handlers.
 	if (nq)
 		WRITE_ONCE(t->trc_reader_special.b.need_qs, false);
-	WRITE_ONCE(t->trc_reader_nesting, nesting);
+	WRITE_ONCE(t->trc_reader_nesting, 0);
 	if (nq && atomic_dec_and_test(&trc_n_readers_need_end))
 		irq_work_queue(&rcu_tasks_trace_iw);
 }
@@ -890,32 +889,24 @@ static void trc_read_check_handler(void *t_in)
 
 	// If the task is no longer running on this CPU, leave.
 	if (unlikely(texp != t)) {
-		if (WARN_ON_ONCE(atomic_dec_and_test(&trc_n_readers_need_end)))
-			wake_up(&trc_wait);
 		goto reset_ipi; // Already on holdout list, so will check later.
 	}
 
 	// If the task is not in a read-side critical section, and
 	// if this is the last reader, awaken the grace-period kthread.
 	if (likely(!READ_ONCE(t->trc_reader_nesting))) {
-		if (WARN_ON_ONCE(atomic_dec_and_test(&trc_n_readers_need_end)))
-			wake_up(&trc_wait);
-		// Mark as checked after decrement to avoid false
-		// positives on the above WARN_ON_ONCE().
 		WRITE_ONCE(t->trc_reader_checked, true);
 		goto reset_ipi;
 	}
 	// If we are racing with an rcu_read_unlock_trace(), try again later.
-	if (unlikely(READ_ONCE(t->trc_reader_nesting) < 0)) {
-		if (WARN_ON_ONCE(atomic_dec_and_test(&trc_n_readers_need_end)))
-			wake_up(&trc_wait);
+	if (unlikely(READ_ONCE(t->trc_reader_nesting) < 0))
 		goto reset_ipi;
-	}
 	WRITE_ONCE(t->trc_reader_checked, true);
 
 	// Get here if the task is in a read-side critical section.  Set
 	// its state so that it will awaken the grace-period kthread upon
 	// exit from that critical section.
+	atomic_inc(&trc_n_readers_need_end); // One more to wait on.
 	WARN_ON_ONCE(READ_ONCE(t->trc_reader_special.b.need_qs));
 	WRITE_ONCE(t->trc_reader_special.b.need_qs, true);
 
@@ -931,7 +922,7 @@ reset_ipi:
 static bool trc_inspect_reader(struct task_struct *t, void *arg)
 {
 	int cpu = task_cpu(t);
-	bool in_qs = false;
+	int nesting;
 	bool ofl = cpu_is_offline(cpu);
 
 	if (task_curr(t)) {
@@ -951,18 +942,18 @@ static bool trc_inspect_reader(struct task_struct *t, void *arg)
 		n_heavy_reader_updates++;
 		if (ofl)
 			n_heavy_reader_ofl_updates++;
-		in_qs = true;
+		nesting = 0;
 	} else {
 		// The task is not running, so C-language access is safe.
-		in_qs = likely(!t->trc_reader_nesting);
+		nesting = t->trc_reader_nesting;
 	}
 
-	// Mark as checked so that the grace-period kthread will
-	// remove it from the holdout list.
-	t->trc_reader_checked = true;
-
-	if (in_qs)
-		return true;  // Already in quiescent state, done!!!
+	// If not exiting a read-side critical section, mark as checked
+	// so that the grace-period kthread will remove it from the
+	// holdout list.
+	t->trc_reader_checked = nesting >= 0;
+	if (nesting <= 0)
+		return !nesting;  // If in QS, done, otherwise try again later.
 
 	// The task is in a read-side critical section, so set up its
 	// state so that it will awaken the grace-period kthread upon exit
@@ -1000,7 +991,7 @@ static void trc_wait_for_one_reader(struct task_struct *t,
 
 	// If this task is not yet on the holdout list, then we are in
 	// an RCU read-side critical section.  Otherwise, the invocation of
-	// rcu_add_holdout() that added it to the list did the necessary
+	// trc_add_holdout() that added it to the list did the necessary
 	// get_task_struct().  Either way, the task cannot be freed out
 	// from under this code.
 
@@ -1015,21 +1006,17 @@ static void trc_wait_for_one_reader(struct task_struct *t,
 		if (per_cpu(trc_ipi_to_cpu, cpu) || t->trc_ipi_to_cpu >= 0)
 			return;
 
-		atomic_inc(&trc_n_readers_need_end);
 		per_cpu(trc_ipi_to_cpu, cpu) = true;
 		t->trc_ipi_to_cpu = cpu;
 		rcu_tasks_trace.n_ipis++;
-		if (smp_call_function_single(cpu,
-					     trc_read_check_handler, t, 0)) {
+		if (smp_call_function_single(cpu, trc_read_check_handler, t, 0)) {
 			// Just in case there is some other reason for
 			// failure than the target CPU being offline.
+			WARN_ONCE(1, "%s():  smp_call_function_single() failed for CPU: %d\n",
+				  __func__, cpu);
 			rcu_tasks_trace.n_ipis_fails++;
 			per_cpu(trc_ipi_to_cpu, cpu) = false;
-			t->trc_ipi_to_cpu = cpu;
-			if (atomic_dec_and_test(&trc_n_readers_need_end)) {
-				WARN_ON_ONCE(1);
-				wake_up(&trc_wait);
-			}
+			t->trc_ipi_to_cpu = -1;
 		}
 	}
 }
@@ -1099,9 +1086,9 @@ static void show_stalled_task_trace(struct task_struct *t, bool *firstreport)
 	cpu = task_cpu(t);
 	pr_alert("P%d: %c%c%c nesting: %d%c cpu: %d\n",
 		 t->pid,
-		 ".I"[READ_ONCE(t->trc_ipi_to_cpu) > 0],
+		 ".I"[READ_ONCE(t->trc_ipi_to_cpu) >= 0],
 		 ".i"[is_idle_task(t)],
-		 ".N"[cpu > 0 && tick_nohz_full_cpu(cpu)],
+		 ".N"[cpu >= 0 && tick_nohz_full_cpu(cpu)],
 		 READ_ONCE(t->trc_reader_nesting),
 		 " N"[!!READ_ONCE(t->trc_reader_special.b.need_qs)],
 		 cpu);
@@ -1134,7 +1121,8 @@ static void check_all_holdout_tasks_trace(struct list_head *hop,
 			trc_wait_for_one_reader(t, hop);
 
 		// If check succeeded, remove this task from the list.
-		if (READ_ONCE(t->trc_reader_checked))
+		if (smp_load_acquire(&t->trc_ipi_to_cpu) == -1 &&
+		    READ_ONCE(t->trc_reader_checked))
 			trc_del_holdout(t);
 		else if (needreport)
 			show_stalled_task_trace(t, firstreport);
@@ -1144,20 +1132,34 @@ static void check_all_holdout_tasks_trace(struct list_head *hop,
 	cpus_read_unlock();
 
 	if (needreport) {
-		if (firstreport)
+		if (*firstreport)
 			pr_err("INFO: rcu_tasks_trace detected stalls? (Late IPI?)\n");
 		show_stalled_ipi_trace();
 	}
 }
 
+static void rcu_tasks_trace_empty_fn(void *unused)
+{
+}
+
 /* Wait for grace period to complete and provide ordering. */
 static void rcu_tasks_trace_postgp(struct rcu_tasks *rtp)
 {
+	int cpu;
 	bool firstreport;
 	struct task_struct *g, *t;
 	LIST_HEAD(holdouts);
 	long ret;
 
+	// Wait for any lingering IPI handlers to complete.  Note that
+	// if a CPU has gone offline or transitioned to userspace in the
+	// meantime, all IPI handlers should have been drained beforehand.
+	// Yes, this assumes that CPUs process IPIs in order.  If that ever
+	// changes, there will need to be a recheck and/or timed wait.
+	for_each_online_cpu(cpu)
+		if (WARN_ON_ONCE(smp_load_acquire(per_cpu_ptr(&trc_ipi_to_cpu, cpu))))
+			smp_call_function_single(cpu, rcu_tasks_trace_empty_fn, NULL, 1);
+
 	// Remove the safety count.
 	smp_mb__before_atomic();  // Order vs. earlier atomics
 	atomic_dec(&trc_n_readers_need_end);
@@ -1200,7 +1202,7 @@ static void exit_tasks_rcu_finish_trace(struct task_struct *t)
 	WARN_ON_ONCE(READ_ONCE(t->trc_reader_nesting));
 	WRITE_ONCE(t->trc_reader_nesting, 0);
 	if (WARN_ON_ONCE(READ_ONCE(t->trc_reader_special.b.need_qs)))
-		rcu_read_unlock_trace_special(t, 0);
+		rcu_read_unlock_trace_special(t);
 }
 
 /**
@@ -1208,15 +1210,11 @@ static void exit_tasks_rcu_finish_trace(struct task_struct *t)
  * @rhp: structure to be used for queueing the RCU updates.
  * @func: actual callback function to be invoked after the grace period
  *
- * The callback function will be invoked some time after a full grace
- * period elapses, in other words after all currently executing RCU
- * read-side critical sections have completed. call_rcu_tasks_trace()
- * assumes that the read-side critical sections end at context switch,
- * cond_resched_rcu_qs(), or transition to usermode execution.  As such,
- * there are no read-side primitives analogous to rcu_read_lock() and
- * rcu_read_unlock() because this primitive is intended to determine
- * that all tasks have passed through a safe state, not so much for
- * data-structure synchronization.
+ * The callback function will be invoked some time after a trace rcu-tasks
+ * grace period elapses, in other words after all currently executing
+ * trace rcu-tasks read-side critical sections have completed. These
+ * read-side critical sections are delimited by calls to rcu_read_lock_trace()
+ * and rcu_read_unlock_trace().
  *
  * See the description of call_rcu() for more detailed information on
  * memory ordering guarantees.
@@ -1232,7 +1230,7 @@ EXPORT_SYMBOL_GPL(call_rcu_tasks_trace);
  *
  * Control will return to the caller some time after a trace rcu-tasks
  * grace period has elapsed, in other words after all currently executing
- * rcu-tasks read-side critical sections have elapsed.  These read-side
+ * trace rcu-tasks read-side critical sections have elapsed. These read-side
  * critical sections are delimited by calls to rcu_read_lock_trace()
  * and rcu_read_unlock_trace().
  *
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index bce848e50512e..e8247861ca938 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -327,7 +327,7 @@ static void rcu_dynticks_eqs_online(void)
  */
 static __always_inline bool rcu_dynticks_curr_cpu_in_eqs(void)
 {
-	return !(atomic_read(this_cpu_ptr(&rcu_data.dynticks)) & 0x1);
+	return !(arch_atomic_read(this_cpu_ptr(&rcu_data.dynticks)) & 0x1);
 }
 
 /*
@@ -624,7 +624,6 @@ static noinstr void rcu_eqs_enter(bool user)
 	instrumentation_begin();
 	trace_rcu_dyntick(TPS("Start"), rdp->dynticks_nesting, 0, atomic_read(&rdp->dynticks));
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
-	rcu_prepare_for_idle();
 	rcu_preempt_deferred_qs(current);
 
 	// instrumentation for the noinstr rcu_dynticks_eqs_enter()
@@ -768,9 +767,6 @@ noinstr void rcu_nmi_exit(void)
 	trace_rcu_dyntick(TPS("Startirq"), rdp->dynticks_nmi_nesting, 0, atomic_read(&rdp->dynticks));
 	WRITE_ONCE(rdp->dynticks_nmi_nesting, 0); /* Avoid store tearing. */
 
-	if (!in_nmi())
-		rcu_prepare_for_idle();
-
 	// instrumentation for the noinstr rcu_dynticks_eqs_enter()
 	instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
 	instrumentation_end();
@@ -872,7 +868,6 @@ static void noinstr rcu_eqs_exit(bool user)
 	// instrumentation for the noinstr rcu_dynticks_eqs_exit()
 	instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
 
-	rcu_cleanup_after_idle();
 	trace_rcu_dyntick(TPS("End"), rdp->dynticks_nesting, 1, atomic_read(&rdp->dynticks));
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
 	WRITE_ONCE(rdp->dynticks_nesting, 1);
@@ -1014,12 +1009,6 @@ noinstr void rcu_nmi_enter(void)
 		rcu_dynticks_eqs_exit();
 		// ... but is watching here.
 
-		if (!in_nmi()) {
-			instrumentation_begin();
-			rcu_cleanup_after_idle();
-			instrumentation_end();
-		}
-
 		instrumentation_begin();
 		// instrumentation for the noinstr rcu_dynticks_curr_cpu_in_eqs()
 		instrument_atomic_read(&rdp->dynticks, sizeof(rdp->dynticks));
@@ -1087,6 +1076,24 @@ void rcu_irq_enter_irqson(void)
 }
 
 /*
+ * Check to see if any future non-offloaded RCU-related work will need
+ * to be done by the current CPU, even if none need be done immediately,
+ * returning 1 if so.  This function is part of the RCU implementation;
+ * it is -not- an exported member of the RCU API.  This is used by
+ * the idle-entry code to figure out whether it is safe to disable the
+ * scheduler-clock interrupt.
+ *
+ * Just check whether or not this CPU has non-offloaded RCU callbacks
+ * queued.
+ */
+int rcu_needs_cpu(u64 basemono, u64 *nextevt)
+{
+	*nextevt = KTIME_MAX;
+	return !rcu_segcblist_empty(&this_cpu_ptr(&rcu_data)->cblist) &&
+		!rcu_rdp_is_offloaded(this_cpu_ptr(&rcu_data));
+}
+
+/*
  * If any sort of urgency was applied to the current CPU (for example,
  * the scheduler-clock interrupt was enabled on a nohz_full CPU) in order
  * to get to a quiescent state, disable it.
@@ -1219,8 +1226,6 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp)
 static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 {
 	unsigned long jtsq;
-	bool *rnhqp;
-	bool *ruqp;
 	struct rcu_node *rnp = rdp->mynode;
 
 	/*
@@ -1285,17 +1290,15 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	 * is set way high.
 	 */
 	jtsq = READ_ONCE(jiffies_to_sched_qs);
-	ruqp = per_cpu_ptr(&rcu_data.rcu_urgent_qs, rdp->cpu);
-	rnhqp = per_cpu_ptr(&rcu_data.rcu_need_heavy_qs, rdp->cpu);
-	if (!READ_ONCE(*rnhqp) &&
+	if (!READ_ONCE(rdp->rcu_need_heavy_qs) &&
 	    (time_after(jiffies, rcu_state.gp_start + jtsq * 2) ||
 	     time_after(jiffies, rcu_state.jiffies_resched) ||
 	     rcu_state.cbovld)) {
-		WRITE_ONCE(*rnhqp, true);
+		WRITE_ONCE(rdp->rcu_need_heavy_qs, true);
 		/* Store rcu_need_heavy_qs before rcu_urgent_qs. */
-		smp_store_release(ruqp, true);
+		smp_store_release(&rdp->rcu_urgent_qs, true);
 	} else if (time_after(jiffies, rcu_state.gp_start + jtsq)) {
-		WRITE_ONCE(*ruqp, true);
+		WRITE_ONCE(rdp->rcu_urgent_qs, true);
 	}
 
 	/*
@@ -1309,7 +1312,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	if (tick_nohz_full_cpu(rdp->cpu) &&
 	    (time_after(jiffies, READ_ONCE(rdp->last_fqs_resched) + jtsq * 3) ||
 	     rcu_state.cbovld)) {
-		WRITE_ONCE(*ruqp, true);
+		WRITE_ONCE(rdp->rcu_urgent_qs, true);
 		resched_cpu(rdp->cpu);
 		WRITE_ONCE(rdp->last_fqs_resched, jiffies);
 	}
@@ -1471,7 +1474,7 @@ static void rcu_gp_kthread_wake(void)
 {
 	struct task_struct *t = READ_ONCE(rcu_state.gp_kthread);
 
-	if ((current == t && !in_irq() && !in_serving_softirq()) ||
+	if ((current == t && !in_hardirq() && !in_serving_softirq()) ||
 	    !READ_ONCE(rcu_state.gp_flags) || !t)
 		return;
 	WRITE_ONCE(rcu_state.gp_wake_time, jiffies);
@@ -1594,10 +1597,14 @@ static void __maybe_unused rcu_advance_cbs_nowake(struct rcu_node *rnp,
 						  struct rcu_data *rdp)
 {
 	rcu_lockdep_assert_cblist_protected(rdp);
-	if (!rcu_seq_state(rcu_seq_current(&rnp->gp_seq)) ||
+	// Don't do anything unless the current grace period is guaranteed
+	// not to end.  This means a grace period in progress and at least
+	// one holdout CPU.
+	if (!rcu_seq_state(rcu_seq_current(&rnp->gp_seq)) || !READ_ONCE(rnp->qsmask) ||
 	    !raw_spin_trylock_rcu_node(rnp))
 		return;
-	WARN_ON_ONCE(rcu_advance_cbs(rnp, rdp));
+	if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq)) && READ_ONCE(rnp->qsmask))
+		WARN_ON_ONCE(rcu_advance_cbs(rnp, rdp));
 	raw_spin_unlock_rcu_node(rnp);
 }
 
@@ -1779,6 +1786,8 @@ static noinline_for_stack bool rcu_gp_init(void)
 	 */
 	WRITE_ONCE(rcu_state.gp_state, RCU_GP_ONOFF);
 	rcu_for_each_leaf_node(rnp) {
+		// Wait for CPU-hotplug operations that might have
+		// started before this grace period did.
 		smp_mb(); // Pair with barriers used when updating ->ofl_seq to odd values.
 		firstseq = READ_ONCE(rnp->ofl_seq);
 		if (firstseq & 0x1)
@@ -1907,7 +1916,7 @@ static void rcu_gp_fqs(bool first_time)
 	struct rcu_node *rnp = rcu_get_root();
 
 	WRITE_ONCE(rcu_state.gp_activity, jiffies);
-	rcu_state.n_force_qs++;
+	WRITE_ONCE(rcu_state.n_force_qs, rcu_state.n_force_qs + 1);
 	if (first_time) {
 		/* Collect dyntick-idle snapshots. */
 		force_qs_rnp(dyntick_save_progress_counter);
@@ -2358,7 +2367,7 @@ rcu_check_quiescent_state(struct rcu_data *rdp)
 int rcutree_dying_cpu(unsigned int cpu)
 {
 	bool blkd;
-	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
+	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
 	struct rcu_node *rnp = rdp->mynode;
 
 	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
@@ -2550,7 +2559,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
 	/* Reset ->qlen_last_fqs_check trigger if enough CBs have drained. */
 	if (count == 0 && rdp->qlen_last_fqs_check != 0) {
 		rdp->qlen_last_fqs_check = 0;
-		rdp->n_force_qs_snap = rcu_state.n_force_qs;
+		rdp->n_force_qs_snap = READ_ONCE(rcu_state.n_force_qs);
 	} else if (count < rdp->qlen_last_fqs_check - qhimark)
 		rdp->qlen_last_fqs_check = count;
 
@@ -2716,7 +2725,7 @@ static __latent_entropy void rcu_core(void)
 	WARN_ON_ONCE(!rdp->beenonline);
 
 	/* Report any deferred quiescent states if preemption enabled. */
-	if (!(preempt_count() & PREEMPT_MASK)) {
+	if (IS_ENABLED(CONFIG_PREEMPT_COUNT) && (!(preempt_count() & PREEMPT_MASK))) {
 		rcu_preempt_deferred_qs(current);
 	} else if (rcu_preempt_need_deferred_qs(current)) {
 		set_tsk_need_resched(current);
@@ -2898,10 +2907,10 @@ static void __call_rcu_core(struct rcu_data *rdp, struct rcu_head *head,
 		} else {
 			/* Give the grace period a kick. */
 			rdp->blimit = DEFAULT_MAX_RCU_BLIMIT;
-			if (rcu_state.n_force_qs == rdp->n_force_qs_snap &&
+			if (READ_ONCE(rcu_state.n_force_qs) == rdp->n_force_qs_snap &&
 			    rcu_segcblist_first_pend_cb(&rdp->cblist) != head)
 				rcu_force_quiescent_state();
-			rdp->n_force_qs_snap = rcu_state.n_force_qs;
+			rdp->n_force_qs_snap = READ_ONCE(rcu_state.n_force_qs);
 			rdp->qlen_last_fqs_check = rcu_segcblist_n_cbs(&rdp->cblist);
 		}
 	}
@@ -4128,10 +4137,9 @@ int rcutree_prepare_cpu(unsigned int cpu)
 	/* Set up local state, ensuring consistent view of global state. */
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	rdp->qlen_last_fqs_check = 0;
-	rdp->n_force_qs_snap = rcu_state.n_force_qs;
+	rdp->n_force_qs_snap = READ_ONCE(rcu_state.n_force_qs);
 	rdp->blimit = blimit;
 	rdp->dynticks_nesting = 1;	/* CPU not up, no tearing. */
-	rcu_dynticks_eqs_online();
 	raw_spin_unlock_rcu_node(rnp);		/* irqs remain disabled. */
 
 	/*
@@ -4251,6 +4259,7 @@ void rcu_cpu_starting(unsigned int cpu)
 	mask = rdp->grpmask;
 	WRITE_ONCE(rnp->ofl_seq, rnp->ofl_seq + 1);
 	WARN_ON_ONCE(!(rnp->ofl_seq & 0x1));
+	rcu_dynticks_eqs_online();
 	smp_mb(); // Pair with rcu_gp_cleanup()'s ->ofl_seq barrier().
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext | mask);
@@ -4296,9 +4305,7 @@ void rcu_report_dead(unsigned int cpu)
 	do_nocb_deferred_wakeup(rdp);
 
 	/* QS for any half-done expedited grace period. */
-	preempt_disable();
-	rcu_report_exp_rdp(this_cpu_ptr(&rcu_data));
-	preempt_enable();
+	rcu_report_exp_rdp(rdp);
 	rcu_preempt_deferred_qs(current);
 
 	/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 305cf6aeb4086..70188cb424731 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -157,7 +157,6 @@ struct rcu_data {
 	bool		core_needs_qs;	/* Core waits for quiescent state. */
 	bool		beenonline;	/* CPU online at least once. */
 	bool		gpwrap;		/* Possible ->gp_seq wrap. */
-	bool		exp_deferred_qs; /* This CPU awaiting a deferred QS? */
 	bool		cpu_started;	/* RCU watching this onlining CPU. */
 	struct rcu_node *mynode;	/* This CPU's leaf of hierarchy */
 	unsigned long grpmask;		/* Mask to apply to leaf qsmask. */
@@ -189,11 +188,6 @@ struct rcu_data {
 	bool rcu_urgent_qs;		/* GP old need light quiescent state. */
 	bool rcu_forced_tick;		/* Forced tick to provide QS. */
 	bool rcu_forced_tick_exp;	/*   ... provide QS to expedited GP. */
-#ifdef CONFIG_RCU_FAST_NO_HZ
-	unsigned long last_accelerate;	/* Last jiffy CBs were accelerated. */
-	unsigned long last_advance_all;	/* Last jiffy CBs were all advanced. */
-	int tick_nohz_enabled_snap;	/* Previously seen value from sysfs. */
-#endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
 
 	/* 4) rcu_barrier(), OOM callbacks, and expediting. */
 	struct rcu_head barrier_head;
@@ -419,8 +413,6 @@ static bool rcu_is_callbacks_kthread(void);
 static void rcu_cpu_kthread_setup(unsigned int cpu);
 static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp);
 static void __init rcu_spawn_boost_kthreads(void);
-static void rcu_cleanup_after_idle(void);
-static void rcu_prepare_for_idle(void);
 static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
 static bool rcu_preempt_need_deferred_qs(struct task_struct *t);
 static void rcu_preempt_deferred_qs(struct task_struct *t);
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 2796084ef85a5..a96d17206d87a 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -255,7 +255,7 @@ static void rcu_report_exp_cpu_mult(struct rcu_node *rnp,
  */
 static void rcu_report_exp_rdp(struct rcu_data *rdp)
 {
-	WRITE_ONCE(rdp->exp_deferred_qs, false);
+	WRITE_ONCE(rdp->cpu_no_qs.b.exp, false);
 	rcu_report_exp_cpu_mult(rdp->mynode, rdp->grpmask, true);
 }
 
@@ -506,13 +506,15 @@ static void synchronize_rcu_expedited_wait(void)
 				if (rdp->rcu_forced_tick_exp)
 					continue;
 				rdp->rcu_forced_tick_exp = true;
-				tick_dep_set_cpu(cpu, TICK_DEP_BIT_RCU_EXP);
+				preempt_disable();
+				if (cpu_online(cpu))
+					tick_dep_set_cpu(cpu, TICK_DEP_BIT_RCU_EXP);
+				preempt_enable();
 			}
 		}
 		j = READ_ONCE(jiffies_till_first_fqs);
 		if (synchronize_rcu_expedited_wait_once(j + HZ))
 			return;
-		WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_RT));
 	}
 
 	for (;;) {
@@ -656,7 +658,7 @@ static void rcu_exp_handler(void *unused)
 		    rcu_dynticks_curr_cpu_in_eqs()) {
 			rcu_report_exp_rdp(rdp);
 		} else {
-			rdp->exp_deferred_qs = true;
+			WRITE_ONCE(rdp->cpu_no_qs.b.exp, true);
 			set_tsk_need_resched(t);
 			set_preempt_need_resched();
 		}
@@ -678,7 +680,7 @@ static void rcu_exp_handler(void *unused)
 	if (depth > 0) {
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		if (rnp->expmask & rdp->grpmask) {
-			rdp->exp_deferred_qs = true;
+			WRITE_ONCE(rdp->cpu_no_qs.b.exp, true);
 			t->rcu_read_unlock_special.b.exp_hint = true;
 		}
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
@@ -760,7 +762,7 @@ static void sync_sched_exp_online_cleanup(int cpu)
 	my_cpu = get_cpu();
 	/* Quiescent state either not needed or already requested, leave. */
 	if (!(READ_ONCE(rnp->expmask) & rdp->grpmask) ||
-	    __this_cpu_read(rcu_data.cpu_no_qs.b.exp)) {
+	    READ_ONCE(rdp->cpu_no_qs.b.exp)) {
 		put_cpu();
 		return;
 	}
diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
index 8fdf44f8523f2..368ef7b9af4fe 100644
--- a/kernel/rcu/tree_nocb.h
+++ b/kernel/rcu/tree_nocb.h
@@ -549,7 +549,6 @@ static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone,
 		rcu_nocb_unlock_irqrestore(rdp, flags);
 		trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WakeNot"));
 	}
-	return;
 }
 
 /*
@@ -767,6 +766,7 @@ static int rcu_nocb_gp_kthread(void *arg)
 static inline bool nocb_cb_can_run(struct rcu_data *rdp)
 {
 	u8 flags = SEGCBLIST_OFFLOADED | SEGCBLIST_KTHREAD_CB;
+
 	return rcu_segcblist_test_flags(&rdp->cblist, flags);
 }
 
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index d070059163d70..e25c8ab292598 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -51,8 +51,6 @@ static void __init rcu_bootup_announce_oddness(void)
 			RCU_FANOUT);
 	if (rcu_fanout_exact)
 		pr_info("\tHierarchical RCU autobalancing is disabled.\n");
-	if (IS_ENABLED(CONFIG_RCU_FAST_NO_HZ))
-		pr_info("\tRCU dyntick-idle grace-period acceleration is enabled.\n");
 	if (IS_ENABLED(CONFIG_PROVE_RCU))
 		pr_info("\tRCU lockdep checking is enabled.\n");
 	if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD))
@@ -260,10 +258,10 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
 	 * no need to check for a subsequent expedited GP.  (Though we are
 	 * still in a quiescent state in any case.)
 	 */
-	if (blkd_state & RCU_EXP_BLKD && rdp->exp_deferred_qs)
+	if (blkd_state & RCU_EXP_BLKD && rdp->cpu_no_qs.b.exp)
 		rcu_report_exp_rdp(rdp);
 	else
-		WARN_ON_ONCE(rdp->exp_deferred_qs);
+		WARN_ON_ONCE(rdp->cpu_no_qs.b.exp);
 }
 
 /*
@@ -277,12 +275,16 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
  * current task, there might be any number of other tasks blocked while
  * in an RCU read-side critical section.
  *
+ * Unlike non-preemptible-RCU, quiescent state reports for expedited
+ * grace periods are handled seperately via deferred quiescent states
+ * and context switch events.
+ *
  * Callers to this function must disable preemption.
  */
 static void rcu_qs(void)
 {
 	RCU_LOCKDEP_WARN(preemptible(), "rcu_qs() invoked with preemption enabled!!!\n");
-	if (__this_cpu_read(rcu_data.cpu_no_qs.s)) {
+	if (__this_cpu_read(rcu_data.cpu_no_qs.b.norm)) {
 		trace_rcu_grace_period(TPS("rcu_preempt"),
 				       __this_cpu_read(rcu_data.gp_seq),
 				       TPS("cpuqs"));
@@ -350,7 +352,7 @@ void rcu_note_context_switch(bool preempt)
 	 * means that we continue to block the current grace period.
 	 */
 	rcu_qs();
-	if (rdp->exp_deferred_qs)
+	if (rdp->cpu_no_qs.b.exp)
 		rcu_report_exp_rdp(rdp);
 	rcu_tasks_qs(current, preempt);
 	trace_rcu_utilization(TPS("End context switch"));
@@ -477,7 +479,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
 	 */
 	special = t->rcu_read_unlock_special;
 	rdp = this_cpu_ptr(&rcu_data);
-	if (!special.s && !rdp->exp_deferred_qs) {
+	if (!special.s && !rdp->cpu_no_qs.b.exp) {
 		local_irq_restore(flags);
 		return;
 	}
@@ -497,7 +499,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
 	 * tasks are handled when removing the task from the
 	 * blocked-tasks list below.
 	 */
-	if (rdp->exp_deferred_qs)
+	if (rdp->cpu_no_qs.b.exp)
 		rcu_report_exp_rdp(rdp);
 
 	/* Clean up if blocked during RCU read-side critical section. */
@@ -580,7 +582,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
  */
 static bool rcu_preempt_need_deferred_qs(struct task_struct *t)
 {
-	return (__this_cpu_read(rcu_data.exp_deferred_qs) ||
+	return (__this_cpu_read(rcu_data.cpu_no_qs.b.exp) ||
 		READ_ONCE(t->rcu_read_unlock_special.s)) &&
 	       rcu_preempt_depth() == 0;
 }
@@ -642,7 +644,7 @@ static void rcu_read_unlock_special(struct task_struct *t)
 			   (IS_ENABLED(CONFIG_RCU_BOOST) && irqs_were_disabled &&
 			    t->rcu_blocked_node);
 		// Need to defer quiescent state until everything is enabled.
-		if (use_softirq && (in_irq() || (expboost && !irqs_were_disabled))) {
+		if (use_softirq && (in_hardirq() || (expboost && !irqs_were_disabled))) {
 			// Using softirq, safe to awaken, and either the
 			// wakeup is free or there is either an expedited
 			// GP in flight or a potential need to deboost.
@@ -814,8 +816,7 @@ void rcu_read_unlock_strict(void)
 {
 	struct rcu_data *rdp;
 
-	if (!IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) ||
-	   irqs_disabled() || preempt_count() || !rcu_state.gp_kthread)
+	if (irqs_disabled() || preempt_count() || !rcu_state.gp_kthread)
 		return;
 	rdp = this_cpu_ptr(&rcu_data);
 	rcu_report_qs_rdp(rdp);
@@ -846,10 +847,8 @@ static void rcu_qs(void)
 	trace_rcu_grace_period(TPS("rcu_sched"),
 			       __this_cpu_read(rcu_data.gp_seq), TPS("cpuqs"));
 	__this_cpu_write(rcu_data.cpu_no_qs.b.norm, false);
-	if (!__this_cpu_read(rcu_data.cpu_no_qs.b.exp))
-		return;
-	__this_cpu_write(rcu_data.cpu_no_qs.b.exp, false);
-	rcu_report_exp_rdp(this_cpu_ptr(&rcu_data));
+	if (__this_cpu_read(rcu_data.cpu_no_qs.b.exp))
+		rcu_report_exp_rdp(this_cpu_ptr(&rcu_data));
 }
 
 /*
@@ -926,7 +925,18 @@ static bool rcu_preempt_need_deferred_qs(struct task_struct *t)
 {
 	return false;
 }
-static void rcu_preempt_deferred_qs(struct task_struct *t) { }
+
+// Except that we do need to respond to a request by an expedited grace
+// period for a quiescent state from this CPU.  Note that requests from
+// tasks are handled when removing the task from the blocked-tasks list
+// below.
+static void rcu_preempt_deferred_qs(struct task_struct *t)
+{
+	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
+
+	if (rdp->cpu_no_qs.b.exp)
+		rcu_report_exp_rdp(rdp);
+}
 
 /*
  * Because there is no preemptible RCU, there can be no readers blocked,
@@ -1254,201 +1264,6 @@ static void __init rcu_spawn_boost_kthreads(void)
 
 #endif /* #else #ifdef CONFIG_RCU_BOOST */
 
-#if !defined(CONFIG_RCU_FAST_NO_HZ)
-
-/*
- * Check to see if any future non-offloaded RCU-related work will need
- * to be done by the current CPU, even if none need be done immediately,
- * returning 1 if so.  This function is part of the RCU implementation;
- * it is -not- an exported member of the RCU API.
- *
- * Because we not have RCU_FAST_NO_HZ, just check whether or not this
- * CPU has RCU callbacks queued.
- */
-int rcu_needs_cpu(u64 basemono, u64 *nextevt)
-{
-	*nextevt = KTIME_MAX;
-	return !rcu_segcblist_empty(&this_cpu_ptr(&rcu_data)->cblist) &&
-		!rcu_rdp_is_offloaded(this_cpu_ptr(&rcu_data));
-}
-
-/*
- * Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up
- * after it.
- */
-static void rcu_cleanup_after_idle(void)
-{
-}
-
-/*
- * Do the idle-entry grace-period work, which, because CONFIG_RCU_FAST_NO_HZ=n,
- * is nothing.
- */
-static void rcu_prepare_for_idle(void)
-{
-}
-
-#else /* #if !defined(CONFIG_RCU_FAST_NO_HZ) */
-
-/*
- * This code is invoked when a CPU goes idle, at which point we want
- * to have the CPU do everything required for RCU so that it can enter
- * the energy-efficient dyntick-idle mode.
- *
- * The following preprocessor symbol controls this:
- *
- * RCU_IDLE_GP_DELAY gives the number of jiffies that a CPU is permitted
- *	to sleep in dyntick-idle mode with RCU callbacks pending.  This
- *	is sized to be roughly one RCU grace period.  Those energy-efficiency
- *	benchmarkers who might otherwise be tempted to set this to a large
- *	number, be warned: Setting RCU_IDLE_GP_DELAY too high can hang your
- *	system.  And if you are -that- concerned about energy efficiency,
- *	just power the system down and be done with it!
- *
- * The value below works well in practice.  If future workloads require
- * adjustment, they can be converted into kernel config parameters, though
- * making the state machine smarter might be a better option.
- */
-#define RCU_IDLE_GP_DELAY 4		/* Roughly one grace period. */
-
-static int rcu_idle_gp_delay = RCU_IDLE_GP_DELAY;
-module_param(rcu_idle_gp_delay, int, 0644);
-
-/*
- * Try to advance callbacks on the current CPU, but only if it has been
- * awhile since the last time we did so.  Afterwards, if there are any
- * callbacks ready for immediate invocation, return true.
- */
-static bool __maybe_unused rcu_try_advance_all_cbs(void)
-{
-	bool cbs_ready = false;
-	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
-	struct rcu_node *rnp;
-
-	/* Exit early if we advanced recently. */
-	if (jiffies == rdp->last_advance_all)
-		return false;
-	rdp->last_advance_all = jiffies;
-
-	rnp = rdp->mynode;
-
-	/*
-	 * Don't bother checking unless a grace period has
-	 * completed since we last checked and there are
-	 * callbacks not yet ready to invoke.
-	 */
-	if ((rcu_seq_completed_gp(rdp->gp_seq,
-				  rcu_seq_current(&rnp->gp_seq)) ||
-	     unlikely(READ_ONCE(rdp->gpwrap))) &&
-	    rcu_segcblist_pend_cbs(&rdp->cblist))
-		note_gp_changes(rdp);
-
-	if (rcu_segcblist_ready_cbs(&rdp->cblist))
-		cbs_ready = true;
-	return cbs_ready;
-}
-
-/*
- * Allow the CPU to enter dyntick-idle mode unless it has callbacks ready
- * to invoke.  If the CPU has callbacks, try to advance them.  Tell the
- * caller about what to set the timeout.
- *
- * The caller must have disabled interrupts.
- */
-int rcu_needs_cpu(u64 basemono, u64 *nextevt)
-{
-	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
-	unsigned long dj;
-
-	lockdep_assert_irqs_disabled();
-
-	/* If no non-offloaded callbacks, RCU doesn't need the CPU. */
-	if (rcu_segcblist_empty(&rdp->cblist) ||
-	    rcu_rdp_is_offloaded(rdp)) {
-		*nextevt = KTIME_MAX;
-		return 0;
-	}
-
-	/* Attempt to advance callbacks. */
-	if (rcu_try_advance_all_cbs()) {
-		/* Some ready to invoke, so initiate later invocation. */
-		invoke_rcu_core();
-		return 1;
-	}
-	rdp->last_accelerate = jiffies;
-
-	/* Request timer and round. */
-	dj = round_up(rcu_idle_gp_delay + jiffies, rcu_idle_gp_delay) - jiffies;
-
-	*nextevt = basemono + dj * TICK_NSEC;
-	return 0;
-}
-
-/*
- * Prepare a CPU for idle from an RCU perspective.  The first major task is to
- * sense whether nohz mode has been enabled or disabled via sysfs.  The second
- * major task is to accelerate (that is, assign grace-period numbers to) any
- * recently arrived callbacks.
- *
- * The caller must have disabled interrupts.
- */
-static void rcu_prepare_for_idle(void)
-{
-	bool needwake;
-	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
-	struct rcu_node *rnp;
-	int tne;
-
-	lockdep_assert_irqs_disabled();
-	if (rcu_rdp_is_offloaded(rdp))
-		return;
-
-	/* Handle nohz enablement switches conservatively. */
-	tne = READ_ONCE(tick_nohz_active);
-	if (tne != rdp->tick_nohz_enabled_snap) {
-		if (!rcu_segcblist_empty(&rdp->cblist))
-			invoke_rcu_core(); /* force nohz to see update. */
-		rdp->tick_nohz_enabled_snap = tne;
-		return;
-	}
-	if (!tne)
-		return;
-
-	/*
-	 * If we have not yet accelerated this jiffy, accelerate all
-	 * callbacks on this CPU.
-	 */
-	if (rdp->last_accelerate == jiffies)
-		return;
-	rdp->last_accelerate = jiffies;
-	if (rcu_segcblist_pend_cbs(&rdp->cblist)) {
-		rnp = rdp->mynode;
-		raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
-		needwake = rcu_accelerate_cbs(rnp, rdp);
-		raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */
-		if (needwake)
-			rcu_gp_kthread_wake();
-	}
-}
-
-/*
- * Clean up for exit from idle.  Attempt to advance callbacks based on
- * any grace periods that elapsed while the CPU was idle, and if any
- * callbacks are now ready to invoke, initiate invocation.
- */
-static void rcu_cleanup_after_idle(void)
-{
-	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
-
-	lockdep_assert_irqs_disabled();
-	if (rcu_rdp_is_offloaded(rdp))
-		return;
-	if (rcu_try_advance_all_cbs())
-		invoke_rcu_core();
-}
-
-#endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */
-
 /*
  * Is this CPU a NO_HZ_FULL CPU that should ignore RCU so that the
  * grace-period kthread will do force_quiescent_state() processing?
@@ -1480,7 +1295,7 @@ static void rcu_bind_gp_kthread(void)
 }
 
 /* Record the current task on dyntick-idle entry. */
-static void noinstr rcu_dynticks_task_enter(void)
+static __always_inline void rcu_dynticks_task_enter(void)
 {
 #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL)
 	WRITE_ONCE(current->rcu_tasks_idle_cpu, smp_processor_id());
@@ -1488,7 +1303,7 @@ static void noinstr rcu_dynticks_task_enter(void)
 }
 
 /* Record no current task on dyntick-idle exit. */
-static void noinstr rcu_dynticks_task_exit(void)
+static __always_inline void rcu_dynticks_task_exit(void)
 {
 #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL)
 	WRITE_ONCE(current->rcu_tasks_idle_cpu, -1);
@@ -1496,7 +1311,7 @@ static void noinstr rcu_dynticks_task_exit(void)
 }
 
 /* Turn on heavyweight RCU tasks trace readers on idle/user entry. */
-static void rcu_dynticks_task_trace_enter(void)
+static __always_inline void rcu_dynticks_task_trace_enter(void)
 {
 #ifdef CONFIG_TASKS_TRACE_RCU
 	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB))
@@ -1505,7 +1320,7 @@ static void rcu_dynticks_task_trace_enter(void)
 }
 
 /* Turn off heavyweight RCU tasks trace readers on idle/user exit. */
-static void rcu_dynticks_task_trace_exit(void)
+static __always_inline void rcu_dynticks_task_trace_exit(void)
 {
 #ifdef CONFIG_TASKS_TRACE_RCU
 	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB))
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index 677ee3d8671bf..dc30e77eaf053 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -347,26 +347,6 @@ static void rcu_dump_cpu_stacks(void)
 	}
 }
 
-#ifdef CONFIG_RCU_FAST_NO_HZ
-
-static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
-{
-	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
-
-	sprintf(cp, "last_accelerate: %04lx/%04lx dyntick_enabled: %d",
-		rdp->last_accelerate & 0xffff, jiffies & 0xffff,
-		!!rdp->tick_nohz_enabled_snap);
-}
-
-#else /* #ifdef CONFIG_RCU_FAST_NO_HZ */
-
-static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
-{
-	*cp = '\0';
-}
-
-#endif /* #else #ifdef CONFIG_RCU_FAST_NO_HZ */
-
 static const char * const gp_state_names[] = {
 	[RCU_GP_IDLE] = "RCU_GP_IDLE",
 	[RCU_GP_WAIT_GPS] = "RCU_GP_WAIT_GPS",
@@ -408,13 +388,12 @@ static bool rcu_is_gp_kthread_starving(unsigned long *jp)
  * of RCU grace periods that this CPU is ignorant of, for example, "1"
  * if the CPU was aware of the previous grace period.
  *
- * Also print out idle and (if CONFIG_RCU_FAST_NO_HZ) idle-entry info.
+ * Also print out idle info.
  */
 static void print_cpu_stall_info(int cpu)
 {
 	unsigned long delta;
 	bool falsepositive;
-	char fast_no_hz[72];
 	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
 	char *ticks_title;
 	unsigned long ticks_value;
@@ -432,11 +411,10 @@ static void print_cpu_stall_info(int cpu)
 		ticks_title = "ticks this GP";
 		ticks_value = rdp->ticks_this_gp;
 	}
-	print_cpu_stall_fast_no_hz(fast_no_hz, cpu);
 	delta = rcu_seq_ctr(rdp->mynode->gp_seq - rdp->rcu_iw_gp_seq);
 	falsepositive = rcu_is_gp_kthread_starving(NULL) &&
 			rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp));
-	pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s%s\n",
+	pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s\n",
 	       cpu,
 	       "O."[!!cpu_online(cpu)],
 	       "o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)],
@@ -449,7 +427,6 @@ static void print_cpu_stall_info(int cpu)
 	       rdp->dynticks_nesting, rdp->dynticks_nmi_nesting,
 	       rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu),
 	       data_race(rcu_state.n_force_qs) - rcu_state.n_force_qs_gpstart,
-	       fast_no_hz,
 	       falsepositive ? " (false positive?)" : "");
 }
 
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 690b0cec74598..156892c22bb56 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -54,11 +54,11 @@
 #define MODULE_PARAM_PREFIX "rcupdate."
 
 #ifndef CONFIG_TINY_RCU
-module_param(rcu_expedited, int, 0);
-module_param(rcu_normal, int, 0);
+module_param(rcu_expedited, int, 0444);
+module_param(rcu_normal, int, 0444);
 static int rcu_normal_after_boot = IS_ENABLED(CONFIG_PREEMPT_RT);
-#ifndef CONFIG_PREEMPT_RT
-module_param(rcu_normal_after_boot, int, 0);
+#if !defined(CONFIG_PREEMPT_RT) || defined(CONFIG_NO_HZ_FULL)
+module_param(rcu_normal_after_boot, int, 0444);
 #endif
 #endif /* #ifndef CONFIG_TINY_RCU */
 
diff --git a/kernel/scftorture.c b/kernel/scftorture.c
index 64a08288b1a6d..5d42f44e3e1a1 100644
--- a/kernel/scftorture.c
+++ b/kernel/scftorture.c
@@ -341,6 +341,7 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra
 			cpu = torture_random(trsp) % nr_cpu_ids;
 			scfp->n_resched++;
 			resched_cpu(cpu);
+			this_cpu_inc(scf_invoked_count);
 		}
 		break;
 	case SCF_PRIM_SINGLE:
@@ -553,18 +554,18 @@ static int __init scf_torture_init(void)
 
 	scftorture_print_module_parms("Start of test");
 
-	if (weight_resched == -1 &&
-	    weight_single == -1 && weight_single_rpc == -1 && weight_single_wait == -1 &&
-	    weight_many == -1 && weight_many_wait == -1 &&
-	    weight_all == -1 && weight_all_wait == -1) {
-		weight_resched1 = 2 * nr_cpu_ids;
-		weight_single1 = 2 * nr_cpu_ids;
-		weight_single_rpc1 = 2 * nr_cpu_ids;
-		weight_single_wait1 = 2 * nr_cpu_ids;
-		weight_many1 = 2;
-		weight_many_wait1 = 2;
-		weight_all1 = 1;
-		weight_all_wait1 = 1;
+	if (weight_resched <= 0 &&
+	    weight_single <= 0 && weight_single_rpc <= 0 && weight_single_wait <= 0 &&
+	    weight_many <= 0 && weight_many_wait <= 0 &&
+	    weight_all <= 0 && weight_all_wait <= 0) {
+		weight_resched1 = weight_resched == 0 ? 0 : 2 * nr_cpu_ids;
+		weight_single1 = weight_single == 0 ? 0 : 2 * nr_cpu_ids;
+		weight_single_rpc1 = weight_single_rpc == 0 ? 0 : 2 * nr_cpu_ids;
+		weight_single_wait1 = weight_single_wait == 0 ? 0 : 2 * nr_cpu_ids;
+		weight_many1 = weight_many == 0 ? 0 : 2;
+		weight_many_wait1 = weight_many_wait == 0 ? 0 : 2;
+		weight_all1 = weight_all == 0 ? 0 : 1;
+		weight_all_wait1 = weight_all_wait == 0 ? 0 : 1;
 	} else {
 		if (weight_resched == -1)
 			weight_resched1 = 0;
@@ -583,8 +584,8 @@ static int __init scf_torture_init(void)
 		if (weight_all_wait == -1)
 			weight_all_wait1 = 0;
 	}
-	if (weight_single1 == 0 && weight_single_rpc1 == 0 && weight_single_wait1 == 0 &&
-	    weight_many1 == 0 && weight_many_wait1 == 0 &&
+	if (weight_resched1 == 0 && weight_single1 == 0 && weight_single_rpc1 == 0 &&
+	    weight_single_wait1 == 0 && weight_many1 == 0 && weight_many_wait1 == 0 &&
 	    weight_all1 == 0 && weight_all_wait1 == 0) {
 		VERBOSE_SCFTORTOUT_ERRSTRING("all zero weights makes no sense");
 		firsterr = -EINVAL;
@@ -605,17 +606,17 @@ static int __init scf_torture_init(void)
 
 	if (onoff_interval > 0) {
 		firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval, NULL);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	if (shutdown_secs > 0) {
 		firsterr = torture_shutdown_init(shutdown_secs, scf_torture_cleanup);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	if (stutter > 0) {
 		firsterr = torture_stutter_init(stutter, stutter);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 
@@ -636,12 +637,12 @@ static int __init scf_torture_init(void)
 		scf_stats_p[i].cpu = i;
 		firsterr = torture_create_kthread(scftorture_invoker, (void *)&scf_stats_p[i],
 						  scf_stats_p[i].task);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 	if (stat_interval > 0) {
 		firsterr = torture_create_kthread(scf_torture_stats, NULL, scf_torture_stats_task);
-		if (firsterr)
+		if (torture_init_error(firsterr))
 			goto unwind;
 	}
 
@@ -651,6 +652,10 @@ static int __init scf_torture_init(void)
 unwind:
 	torture_init_end();
 	scf_torture_cleanup();
+	if (shutdown_secs) {
+		WARN_ON(!IS_MODULE(CONFIG_SCF_TORTURE_TEST));
+		kernel_power_off();
+	}
 	return firsterr;
 }
 
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 322b65d456767..41f470929e991 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -595,7 +595,8 @@ void irq_enter_rcu(void)
 {
 	__irq_enter_raw();
 
-	if (is_idle_task(current) && (irq_count() == HARDIRQ_OFFSET))
+	if (tick_nohz_full_cpu(smp_processor_id()) ||
+	    (is_idle_task(current) && (irq_count() == HARDIRQ_OFFSET)))
 		tick_irq_enter();
 
 	account_hardirq_enter(current);
diff --git a/kernel/time/clocksource-wdtest.c b/kernel/time/clocksource-wdtest.c
index df922f49d171b..7e82500c400b9 100644
--- a/kernel/time/clocksource-wdtest.c
+++ b/kernel/time/clocksource-wdtest.c
@@ -145,13 +145,12 @@ static int wdtest_func(void *arg)
 		else if (i <= max_cswd_read_retries)
 			s = ", expect message";
 		else
-			s = ", expect clock skew";
+			s = ", expect coarse-grained clock skew check and re-initialization";
 		pr_info("--- Watchdog with %dx error injection, %lu retries%s.\n", i, max_cswd_read_retries, s);
 		WRITE_ONCE(wdtest_ktime_read_ndelays, i);
 		schedule_timeout_uninterruptible(2 * HZ);
 		WARN_ON_ONCE(READ_ONCE(wdtest_ktime_read_ndelays));
-		WARN_ON_ONCE((i <= max_cswd_read_retries) !=
-			     !(clocksource_wdtest_ktime.flags & CLOCK_SOURCE_UNSTABLE));
+		WARN_ON_ONCE(clocksource_wdtest_ktime.flags & CLOCK_SOURCE_UNSTABLE);
 		wdtest_ktime_clocksource_reset();
 	}
 
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index b8a14d2fb5ba6..b038b81f8d32c 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -226,13 +226,18 @@ static bool cs_watchdog_read(struct clocksource *cs, u64 *csnow, u64 *wdnow)
 				pr_warn("timekeeping watchdog on CPU%d: %s retried %d times before success\n",
 					smp_processor_id(), watchdog->name, nretries);
 			}
-			return true;
+			return false;
 		}
 	}
 
-	pr_warn("timekeeping watchdog on CPU%d: %s read-back delay of %lldns, attempt %d, marking unstable\n",
-		smp_processor_id(), watchdog->name, wd_delay, nretries);
-	return false;
+	if ((cs->flags & CLOCK_SOURCE_WATCHDOG) && !atomic_read(&watchdog_reset_pending)) {
+		pr_warn("timekeeping watchdog on CPU%d: %s read-back delay of %lldns, attempt %d, coarse-grained skew check followed by re-initialization\n",
+			smp_processor_id(), watchdog->name, wd_delay, nretries);
+	} else {
+		pr_warn("timekeeping watchdog on CPU%d: %s read-back delay of %lldns, attempt %d, awaiting re-initialization\n",
+			smp_processor_id(), watchdog->name, wd_delay, nretries);
+	}
+	return true;
 }
 
 static u64 csnow_mid;
@@ -356,6 +361,7 @@ static void clocksource_watchdog(struct timer_list *unused)
 	int next_cpu, reset_pending;
 	int64_t wd_nsec, cs_nsec;
 	struct clocksource *cs;
+	bool coarse;
 	u32 md;
 
 	spin_lock(&watchdog_lock);
@@ -373,16 +379,13 @@ static void clocksource_watchdog(struct timer_list *unused)
 			continue;
 		}
 
-		if (!cs_watchdog_read(cs, &csnow, &wdnow)) {
-			/* Clock readout unreliable, so give it up. */
-			__clocksource_unstable(cs);
-			continue;
-		}
+		coarse = cs_watchdog_read(cs, &csnow, &wdnow);
 
 		/* Clocksource initialized ? */
 		if (!(cs->flags & CLOCK_SOURCE_WATCHDOG) ||
 		    atomic_read(&watchdog_reset_pending)) {
-			cs->flags |= CLOCK_SOURCE_WATCHDOG;
+			if (!coarse)
+				cs->flags |= CLOCK_SOURCE_WATCHDOG;
 			cs->wd_last = wdnow;
 			cs->cs_last = csnow;
 			continue;
@@ -403,7 +406,13 @@ static void clocksource_watchdog(struct timer_list *unused)
 			continue;
 
 		/* Check the deviation from the watchdog clocksource. */
-		md = cs->uncertainty_margin + watchdog->uncertainty_margin;
+		if (coarse) {
+			md = 62500 * NSEC_PER_USEC;
+			cs->flags &= ~CLOCK_SOURCE_WATCHDOG;
+			pr_warn("timekeeping watchdog on CPU%d: %s coarse-grained %lu.%03lu ms clock-skew check followed by re-initialization\n", smp_processor_id(), watchdog->name, md / NSEC_PER_MSEC, md % NSEC_PER_MSEC / NSEC_PER_USEC);
+		} else {
+			md = cs->uncertainty_margin + watchdog->uncertainty_margin;
+		}
 		if (abs(cs_nsec - wd_nsec) > md) {
 			pr_warn("timekeeping watchdog on CPU%d: Marking clocksource '%s' as unstable because the skew is too large:\n",
 				smp_processor_id(), cs->name);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 6bffe5af8cb11..17a283ce2b20f 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -1375,6 +1375,13 @@ static inline void tick_nohz_irq_enter(void)
 	now = ktime_get();
 	if (ts->idle_active)
 		tick_nohz_stop_idle(ts, now);
+	/*
+	 * If all CPUs are idle. We may need to update a stale jiffies value.
+	 * Note nohz_full is a special case: a timekeeper is guaranteed to stay
+	 * alive but it might be busy looping with interrupts disabled in some
+	 * rare case (typically stop machine). So we must make sure we have a
+	 * last resort.
+	 */
 	if (ts->tick_stopped)
 		tick_nohz_update_jiffies(now);
 }
diff --git a/tools/memory-model/Documentation/locking.txt b/tools/memory-model/Documentation/locking.txt
new file mode 100644
index 0000000000000..4e05c6d53ab72
--- /dev/null
+++ b/tools/memory-model/Documentation/locking.txt
@@ -0,0 +1,320 @@
+Locking
+=======
+
+Locking is well-known and the common use cases are straightforward: Any
+CPU holding a given lock sees any changes previously seen or made by any
+CPU before it previously released that same lock.  This last sentence
+is the only part of this document that most developers will need to read.
+
+However, developers who would like to also access lock-protected shared
+variables outside of their corresponding locks should continue reading.
+
+
+Locking and Prior Accesses
+--------------------------
+
+The basic rule of locking is worth repeating:
+
+	Any CPU holding a given lock sees any changes previously seen
+	or made by any CPU before it previously released that same lock.
+
+Note that this statement is a bit stronger than "Any CPU holding a
+given lock sees all changes made by any CPU during the time that CPU was
+previously holding this same lock".  For example, consider the following
+pair of code fragments:
+
+	/* See MP+polocks.litmus. */
+	void CPU0(void)
+	{
+		WRITE_ONCE(x, 1);
+		spin_lock(&mylock);
+		WRITE_ONCE(y, 1);
+		spin_unlock(&mylock);
+	}
+
+	void CPU1(void)
+	{
+		spin_lock(&mylock);
+		r0 = READ_ONCE(y);
+		spin_unlock(&mylock);
+		r1 = READ_ONCE(x);
+	}
+
+The basic rule guarantees that if CPU0() acquires mylock before CPU1(),
+then both r0 and r1 must be set to the value 1.  This also has the
+consequence that if the final value of r0 is equal to 1, then the final
+value of r1 must also be equal to 1.  In contrast, the weaker rule would
+say nothing about the final value of r1.
+
+
+Locking and Subsequent Accesses
+-------------------------------
+
+The converse to the basic rule also holds:  Any CPU holding a given
+lock will not see any changes that will be made by any CPU after it
+subsequently acquires this same lock.  This converse statement is
+illustrated by the following litmus test:
+
+	/* See MP+porevlocks.litmus. */
+	void CPU0(void)
+	{
+		r0 = READ_ONCE(y);
+		spin_lock(&mylock);
+		r1 = READ_ONCE(x);
+		spin_unlock(&mylock);
+	}
+
+	void CPU1(void)
+	{
+		spin_lock(&mylock);
+		WRITE_ONCE(x, 1);
+		spin_unlock(&mylock);
+		WRITE_ONCE(y, 1);
+	}
+
+This converse to the basic rule guarantees that if CPU0() acquires
+mylock before CPU1(), then both r0 and r1 must be set to the value 0.
+This also has the consequence that if the final value of r1 is equal
+to 0, then the final value of r0 must also be equal to 0.  In contrast,
+the weaker rule would say nothing about the final value of r0.
+
+These examples show only a single pair of CPUs, but the effects of the
+locking basic rule extend across multiple acquisitions of a given lock
+across multiple CPUs.
+
+
+Double-Checked Locking
+----------------------
+
+It is well known that more than just a lock is required to make
+double-checked locking work correctly,  This litmus test illustrates
+one incorrect approach:
+
+	/* See Documentation/litmus-tests/locking/DCL-broken.litmus. */
+	P0(int *flag, int *data, int *lck)
+	{
+		int r0;
+		int r1;
+		int r2;
+
+		r0 = READ_ONCE(*flag);
+		if (r0 == 0) {
+			spin_lock(lck);
+			r1 = READ_ONCE(*flag);
+			if (r1 == 0) {
+				WRITE_ONCE(*data, 1);
+				WRITE_ONCE(*flag, 1);
+			}
+			spin_unlock(lck);
+		}
+		r2 = READ_ONCE(*data);
+	}
+	/* P1() is the exactly the same as P0(). */
+
+There are two problems.  First, there is no ordering between the first
+READ_ONCE() of "flag" and the READ_ONCE() of "data".  Second, there is
+no ordering between the two WRITE_ONCE() calls.  It should therefore be
+no surprise that "r2" can be zero, and a quick herd7 run confirms this.
+
+One way to fix this is to use smp_load_acquire() and smp_store_release()
+as shown in this corrected version:
+
+	/* See Documentation/litmus-tests/locking/DCL-fixed.litmus. */
+	P0(int *flag, int *data, int *lck)
+	{
+		int r0;
+		int r1;
+		int r2;
+
+		r0 = smp_load_acquire(flag);
+		if (r0 == 0) {
+			spin_lock(lck);
+			r1 = READ_ONCE(*flag);
+			if (r1 == 0) {
+				WRITE_ONCE(*data, 1);
+				smp_store_release(flag, 1);
+			}
+			spin_unlock(lck);
+		}
+		r2 = READ_ONCE(*data);
+	}
+	/* P1() is the exactly the same as P0(). */
+
+The smp_load_acquire() guarantees that its load from "flags" will
+be ordered before the READ_ONCE() from data, thus solving the first
+problem.  The smp_store_release() guarantees that its store will be
+ordered after the WRITE_ONCE() to "data", solving the second problem.
+The smp_store_release() pairs with the smp_load_acquire(), thus ensuring
+that the ordering provided by each actually takes effect.  Again, a
+quick herd7 run confirms this.
+
+In short, if you access a lock-protected variable without holding the
+corresponding lock, you will need to provide additional ordering, in
+this case, via the smp_load_acquire() and the smp_store_release().
+
+
+Ordering Provided by a Lock to CPUs Not Holding That Lock
+---------------------------------------------------------
+
+It is not necessarily the case that accesses ordered by locking will be
+seen as ordered by CPUs not holding that lock.  Consider this example:
+
+	/* See Z6.0+pooncelock+pooncelock+pombonce.litmus. */
+	void CPU0(void)
+	{
+		spin_lock(&mylock);
+		WRITE_ONCE(x, 1);
+		WRITE_ONCE(y, 1);
+		spin_unlock(&mylock);
+	}
+
+	void CPU1(void)
+	{
+		spin_lock(&mylock);
+		r0 = READ_ONCE(y);
+		WRITE_ONCE(z, 1);
+		spin_unlock(&mylock);
+	}
+
+	void CPU2(void)
+	{
+		WRITE_ONCE(z, 2);
+		smp_mb();
+		r1 = READ_ONCE(x);
+	}
+
+Counter-intuitive though it might be, it is quite possible to have
+the final value of r0 be 1, the final value of z be 2, and the final
+value of r1 be 0.  The reason for this surprising outcome is that CPU2()
+never acquired the lock, and thus did not fully benefit from the lock's
+ordering properties.
+
+Ordering can be extended to CPUs not holding the lock by careful use
+of smp_mb__after_spinlock():
+
+	/* See Z6.0+pooncelock+poonceLock+pombonce.litmus. */
+	void CPU0(void)
+	{
+		spin_lock(&mylock);
+		WRITE_ONCE(x, 1);
+		WRITE_ONCE(y, 1);
+		spin_unlock(&mylock);
+	}
+
+	void CPU1(void)
+	{
+		spin_lock(&mylock);
+		smp_mb__after_spinlock();
+		r0 = READ_ONCE(y);
+		WRITE_ONCE(z, 1);
+		spin_unlock(&mylock);
+	}
+
+	void CPU2(void)
+	{
+		WRITE_ONCE(z, 2);
+		smp_mb();
+		r1 = READ_ONCE(x);
+	}
+
+This addition of smp_mb__after_spinlock() strengthens the lock
+acquisition sufficiently to rule out the counter-intuitive outcome.
+In other words, the addition of the smp_mb__after_spinlock() prohibits
+the counter-intuitive result where the final value of r0 is 1, the final
+value of z is 2, and the final value of r1 is 0.
+
+
+No Roach-Motel Locking!
+-----------------------
+
+This example requires familiarity with the herd7 "filter" clause, so
+please read up on that topic in litmus-tests.txt.
+
+It is tempting to allow memory-reference instructions to be pulled
+into a critical section, but this cannot be allowed in the general case.
+For example, consider a spin loop preceding a lock-based critical section.
+Now, herd7 does not model spin loops, but we can emulate one with two
+loads, with a "filter" clause to constrain the first to return the
+initial value and the second to return the updated value, as shown below:
+
+	/* See Documentation/litmus-tests/locking/RM-fixed.litmus. */
+	P0(int *x, int *y, int *lck)
+	{
+		int r2;
+
+		spin_lock(lck);
+		r2 = atomic_inc_return(y);
+		WRITE_ONCE(*x, 1);
+		spin_unlock(lck);
+	}
+
+	P1(int *x, int *y, int *lck)
+	{
+		int r0;
+		int r1;
+		int r2;
+
+		r0 = READ_ONCE(*x);
+		r1 = READ_ONCE(*x);
+		spin_lock(lck);
+		r2 = atomic_inc_return(y);
+		spin_unlock(lck);
+	}
+
+	filter (y=2 /\ 1:r0=0 /\ 1:r1=1)
+	exists (1:r2=1)
+
+The variable "x" is the control variable for the emulated spin loop.
+P0() sets it to "1" while holding the lock, and P1() emulates the
+spin loop by reading it twice, first into "1:r0" (which should get the
+initial value "0") and then into "1:r1" (which should get the updated
+value "1").
+
+The purpose of the variable "y" is to reject deadlocked executions.
+Only those executions where the final value of "y" have avoided deadlock.
+
+The "filter" clause takes all this into account, constraining "y" to
+equal "2", "1:r0" to equal "0", and "1:r1" to equal 1.
+
+Then the "exists" clause checks to see if P1() acquired its lock first,
+which should not happen given the filter clause because P0() updates
+"x" while holding the lock.  And herd7 confirms this.
+
+But suppose that the compiler was permitted to reorder the spin loop
+into P1()'s critical section, like this:
+
+	/* See Documentation/litmus-tests/locking/RM-broken.litmus. */
+	P0(int *x, int *y, int *lck)
+	{
+		int r2;
+
+		spin_lock(lck);
+		r2 = atomic_inc_return(y);
+		WRITE_ONCE(*x, 1);
+		spin_unlock(lck);
+	}
+
+	P1(int *x, int *y, int *lck)
+	{
+		int r0;
+		int r1;
+		int r2;
+
+		spin_lock(lck);
+		r0 = READ_ONCE(*x);
+		r1 = READ_ONCE(*x);
+		r2 = atomic_inc_return(y);
+		spin_unlock(lck);
+	}
+
+	locations [x;lck;0:r2;1:r0;1:r1;1:r2]
+	filter (y=2 /\ 1:r0=0 /\ 1:r1=1)
+	exists (1:r2=1)
+
+If "1:r0" is equal to "0", "1:r1" can never equal "1" because P0()
+cannot update "x" while P1() holds the lock.  And herd7 confirms this,
+showing zero executions matching the "filter" criteria.
+
+And this is why Linux-kernel lock and unlock primitives must prevent
+code from entering critical sections.  It is not sufficient to only
+prevent code from leaving them.
diff --git a/tools/memory-model/litmus-tests/.gitignore b/tools/memory-model/litmus-tests/.gitignore
index c492a1ddad91d..19c379cf069d2 100644
--- a/tools/memory-model/litmus-tests/.gitignore
+++ b/tools/memory-model/litmus-tests/.gitignore
@@ -1,2 +1,2 @@
 # SPDX-License-Identifier: GPL-2.0-only
-*.litmus.out
+*.litmus.*
diff --git a/tools/memory-model/scripts/README b/tools/memory-model/scripts/README
index 095c7eb36f9f9..cc2c4e5be9ec1 100644
--- a/tools/memory-model/scripts/README
+++ b/tools/memory-model/scripts/README
@@ -27,6 +27,14 @@ checklitmushist.sh
 checklitmus.sh
 
 	Check a single litmus test against its "Result:" expected result.
+	Not intended to for manual use.
+
+checktheselitmus.sh
+
+	Check the specified list of litmus tests against their "Result:"
+	expected results.  This takes optional parseargs.sh arguments,
+	followed by "--" followed by pathnames starting from the current
+	directory.
 
 cmplitmushist.sh
 
@@ -43,10 +51,10 @@ initlitmushist.sh
 
 judgelitmus.sh
 
-	Given a .litmus file and its .litmus.out herd7 output, check the
-	.litmus.out file against the .litmus file's "Result:" comment to
-	judge whether the test ran correctly.  Not normally run manually,
-	provided instead for use by other scripts.
+	Given a .litmus file and its herd7 output, check the output file
+	against the .litmus file's "Result:" comment to judge whether
+	the test ran correctly.  Not normally run manually, provided
+	instead for use by other scripts.
 
 newlitmushist.sh
 
diff --git a/tools/memory-model/scripts/checkalllitmus.sh b/tools/memory-model/scripts/checkalllitmus.sh
index 3c0c7fbbd223b..2d3ee850a8399 100755
--- a/tools/memory-model/scripts/checkalllitmus.sh
+++ b/tools/memory-model/scripts/checkalllitmus.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 # SPDX-License-Identifier: GPL-2.0+
 #
 # Run herd7 tests on all .litmus files in the litmus-tests directory
@@ -8,6 +8,11 @@
 # "^^^".  It also outputs verification results to a file whose name is
 # that of the specified litmus test, but with ".out" appended.
 #
+# If the --hw argument is specified, this script translates the .litmus
+# C-language file to the specified type of assembly and verifies that.
+# But in this case, litmus tests using complex synchronization (such as
+# locking, RCU, and SRCU) are cheerfully ignored.
+#
 # Usage:
 #	checkalllitmus.sh
 #
@@ -17,7 +22,7 @@
 #
 # Copyright IBM Corporation, 2018
 #
-# Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Author: Paul E. McKenney <paulmck@linux.ibm.com>
 
 . scripts/parseargs.sh
 
@@ -30,29 +35,23 @@ else
 	exit 255
 fi
 
-# Create any new directories that have appeared in the github litmus
-# repo since the last run.
+# Create any new directories that have appeared in the litmus-tests
+# directory since the last run.
 if test "$LKMM_DESTDIR" != "."
 then
 	find $litmusdir -type d -print |
 	( cd "$LKMM_DESTDIR"; sed -e 's/^/mkdir -p /' | sh )
 fi
 
-# Find the checklitmus script.  If it is not where we expect it, then
-# assume that the caller has the PATH environment variable set
-# appropriately.
-if test -x scripts/checklitmus.sh
-then
-	clscript=scripts/checklitmus.sh
-else
-	clscript=checklitmus.sh
-fi
-
 # Run the script on all the litmus tests in the specified directory
 ret=0
 for i in $litmusdir/*.litmus
 do
-	if ! $clscript $i
+	if test -n "$LKMM_HW_MAP_FILE" && ! scripts/simpletest.sh $i
+	then
+		continue
+	fi
+	if ! scripts/checklitmus.sh $i
 	then
 		ret=1
 	fi
diff --git a/tools/memory-model/scripts/checkghlitmus.sh b/tools/memory-model/scripts/checkghlitmus.sh
index 6589fbb6f6538..cedd0290b73f8 100755
--- a/tools/memory-model/scripts/checkghlitmus.sh
+++ b/tools/memory-model/scripts/checkghlitmus.sh
@@ -10,6 +10,7 @@
 # parseargs.sh scripts for arguments.
 
 . scripts/parseargs.sh
+. scripts/hwfnseg.sh
 
 T=/tmp/checkghlitmus.sh.$$
 trap 'rm -rf $T' 0
@@ -32,19 +33,19 @@ then
 	( cd "$LKMM_DESTDIR"; sed -e 's/^/mkdir -p /' | sh )
 fi
 
-# Create a list of the C-language litmus tests previously run.
-( cd $LKMM_DESTDIR; find litmus -name '*.litmus.out' -print ) |
-	sed -e 's/\.out$//' |
+# Create a list of the specified litmus tests previously run.
+( cd $LKMM_DESTDIR; find litmus -name "*.litmus${hwfnseg}.out" -print ) |
+	sed -e "s/${hwfnseg}"'\.out$//' |
 	xargs -r egrep -l '^ \* Result: (Never|Sometimes|Always|DEADLOCK)' |
 	xargs -r grep -L "^P${LKMM_PROCS}"> $T/list-C-already
 
 # Create a list of C-language litmus tests with "Result:" commands and
 # no more than the specified number of processes.
-find litmus -name '*.litmus' -exec grep -l -m 1 "^C " {} \; > $T/list-C
+find litmus -name '*.litmus' -print | mselect7 -arch C > $T/list-C
 xargs < $T/list-C -r egrep -l '^ \* Result: (Never|Sometimes|Always|DEADLOCK)' > $T/list-C-result
 xargs < $T/list-C-result -r grep -L "^P${LKMM_PROCS}" > $T/list-C-result-short
 
-# Form list of tests without corresponding .litmus.out files
+# Form list of tests without corresponding .out files
 sort $T/list-C-already $T/list-C-result-short | uniq -u > $T/list-C-needed
 
 # Run any needed tests.
diff --git a/tools/memory-model/scripts/checklitmus.sh b/tools/memory-model/scripts/checklitmus.sh
index 11461ed40b5e4..4c1d0cf0ddadc 100755
--- a/tools/memory-model/scripts/checklitmus.sh
+++ b/tools/memory-model/scripts/checklitmus.sh
@@ -1,10 +1,8 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0+
 #
-# Run a herd7 test and invokes judgelitmus.sh to check the result against
-# a "Result:" comment within the litmus test.  It also outputs verification
-# results to a file whose name is that of the specified litmus test, but
-# with ".out" appended.
+# Invokes runlitmus.sh and judgelitmus.sh on its arguments to run the
+# specified litmus test and pass judgment on the results.
 #
 # Usage:
 #	checklitmus.sh file.litmus
@@ -15,20 +13,7 @@
 #
 # Copyright IBM Corporation, 2018
 #
-# Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Author: Paul E. McKenney <paulmck@linux.ibm.com>
 
-litmus=$1
-herdoptions=${LKMM_HERD_OPTIONS--conf linux-kernel.cfg}
-
-if test -f "$litmus" -a -r "$litmus"
-then
-	:
-else
-	echo ' --- ' error: \"$litmus\" is not a readable file
-	exit 255
-fi
-
-echo Herd options: $herdoptions > $LKMM_DESTDIR/$litmus.out
-/usr/bin/time $LKMM_TIMEOUT_CMD herd7 $herdoptions $litmus >> $LKMM_DESTDIR/$litmus.out 2>&1
-
-scripts/judgelitmus.sh $litmus
+scripts/runlitmus.sh $1
+scripts/judgelitmus.sh $1
diff --git a/tools/memory-model/scripts/checklitmushist.sh b/tools/memory-model/scripts/checklitmushist.sh
index 1d210ffb7c8af..406ecfc0aee4c 100755
--- a/tools/memory-model/scripts/checklitmushist.sh
+++ b/tools/memory-model/scripts/checklitmushist.sh
@@ -12,7 +12,7 @@
 #
 # Copyright IBM Corporation, 2018
 #
-# Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Author: Paul E. McKenney <paulmck@linux.ibm.com>
 
 . scripts/parseargs.sh
 
diff --git a/tools/memory-model/scripts/checktheselitmus.sh b/tools/memory-model/scripts/checktheselitmus.sh
new file mode 100755
index 0000000000000..10eeb5ecea6de
--- /dev/null
+++ b/tools/memory-model/scripts/checktheselitmus.sh
@@ -0,0 +1,43 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Invokes checklitmus.sh on its arguments to run the specified litmus
+# test and pass judgment on the results.
+#
+# Usage:
+#	checktheselitmus.sh -- [ file1.litmus [ file2.litmus ... ] ]
+#
+# Run this in the directory containing the memory model, specifying the
+# pathname of the litmus test to check.  The usual parseargs.sh arguments
+# can be specified prior to the "--".
+#
+# This script is intended for use with pathnames that start from the
+# tools/memory-model directory.  If some of the pathnames instead start at
+# the root directory, they all must do so and the "--destdir /" parseargs.sh
+# argument must be specified prior to the "--".  Alternatively, some other
+# "--destdir" argument can be supplied as long as the needed subdirectories
+# are populated.
+#
+# Copyright IBM Corporation, 2018
+#
+# Author: Paul E. McKenney <paulmck@linux.ibm.com>
+
+. scripts/parseargs.sh
+
+ret=0
+for i in "$@"
+do
+	if scripts/checklitmus.sh $i
+	then
+		:
+	else
+		ret=1
+	fi
+done
+if test "$ret" -ne 0
+then
+	echo " ^^^ VERIFICATION MISMATCHES" 1>&2
+else
+	echo All litmus tests verified as was expected. 1>&2
+fi
+exit $ret
diff --git a/tools/memory-model/scripts/cmplitmushist.sh b/tools/memory-model/scripts/cmplitmushist.sh
index 0f498aeeccf5e..ca1ac8b646144 100755
--- a/tools/memory-model/scripts/cmplitmushist.sh
+++ b/tools/memory-model/scripts/cmplitmushist.sh
@@ -12,12 +12,49 @@ trap 'rm -rf $T' 0
 mkdir $T
 
 # comparetest oldpath newpath
+badmacnam=0
+timedout=0
 perfect=0
 obsline=0
 noobsline=0
 obsresult=0
 badcompare=0
 comparetest () {
+	if grep -q ': Unknown macro ' $1 || grep -q ': Unknown macro ' $2
+	then
+		if grep -q ': Unknown macro ' $1
+		then
+			badname=`grep ': Unknown macro ' $1 |
+				sed -e 's/^.*: Unknown macro //' |
+				sed -e 's/ (User error).*$//'`
+			echo 'Current LKMM version does not know "'$badname'"' $1
+		fi
+		if grep -q ': Unknown macro ' $2
+		then
+			badname=`grep ': Unknown macro ' $2 |
+				sed -e 's/^.*: Unknown macro //' |
+				sed -e 's/ (User error).*$//'`
+			echo 'Current LKMM version does not know "'$badname'"' $2
+		fi
+		badmacnam=`expr "$badmacnam" + 1`
+		return 0
+	elif grep -q '^Command exited with non-zero status 124' $1 ||
+	     grep -q '^Command exited with non-zero status 124' $2
+	then
+		if grep -q '^Command exited with non-zero status 124' $1 &&
+		   grep -q '^Command exited with non-zero status 124' $2
+		then
+			echo Both runs timed out: $2
+		elif grep -q '^Command exited with non-zero status 124' $1
+		then
+			echo Old run timed out: $2
+		elif grep -q '^Command exited with non-zero status 124' $2
+		then
+			echo New run timed out: $2
+		fi
+		timedout=`expr "$timedout" + 1`
+		return 0
+	fi
 	grep -v 'maxresident)k\|minor)pagefaults\|^Time' $1 > $T/oldout
 	grep -v 'maxresident)k\|minor)pagefaults\|^Time' $2 > $T/newout
 	if cmp -s $T/oldout $T/newout && grep -q '^Observation' $1
@@ -38,7 +75,7 @@ comparetest () {
 			return 0
 		fi
 	else
-		echo Missing Observation line "(e.g., herd7 timeout)": $2
+		echo Missing Observation line "(e.g., syntax error)": $2
 		noobsline=`expr "$noobsline" + 1`
 		return 0
 	fi
@@ -72,12 +109,20 @@ then
 fi
 if test "$noobsline" -ne 0
 then
-	echo Missing Observation line "(e.g., herd7 timeout)": $noobsline 1>&2
+	echo Missing Observation line "(e.g., syntax error)": $noobsline 1>&2
 fi
 if test "$obsresult" -ne 0
 then
 	echo Matching Observation Always/Sometimes/Never result: $obsresult 1>&2
 fi
+if test "$timedout" -ne 0
+then
+	echo "!!!" Timed out: $timedout 1>&2
+fi
+if test "$badmacnam" -ne 0
+then
+	echo "!!!" Unknown primitive: $badmacnam 1>&2
+fi
 if test "$badcompare" -ne 0
 then
 	echo "!!!" Result changed: $badcompare 1>&2
diff --git a/tools/memory-model/scripts/hwfnseg.sh b/tools/memory-model/scripts/hwfnseg.sh
new file mode 100755
index 0000000000000..580c3281181c5
--- /dev/null
+++ b/tools/memory-model/scripts/hwfnseg.sh
@@ -0,0 +1,20 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Generate the hardware extension to the litmus-test filename, or the
+# empty string if this is an LKMM run.  The extension is placed in
+# the shell variable hwfnseg.
+#
+# Usage:
+#	. hwfnseg.sh
+#
+# Copyright IBM Corporation, 2019
+#
+# Author: Paul E. McKenney <paulmck@linux.ibm.com>
+
+if test -z "$LKMM_HW_MAP_FILE"
+then
+	hwfnseg=
+else
+	hwfnseg=".$LKMM_HW_MAP_FILE"
+fi
diff --git a/tools/memory-model/scripts/initlitmushist.sh b/tools/memory-model/scripts/initlitmushist.sh
index 956b6957484d8..31ea782955d3f 100755
--- a/tools/memory-model/scripts/initlitmushist.sh
+++ b/tools/memory-model/scripts/initlitmushist.sh
@@ -60,7 +60,7 @@ fi
 
 # Create a list of the C-language litmus tests with no more than the
 # specified number of processes (per the --procs argument).
-find litmus -name '*.litmus' -exec grep -l -m 1 "^C " {} \; > $T/list-C
+find litmus -name '*.litmus' -print | mselect7 -arch C > $T/list-C
 xargs < $T/list-C -r grep -L "^P${LKMM_PROCS}" > $T/list-C-short
 
 scripts/runlitmushist.sh < $T/list-C-short
diff --git a/tools/memory-model/scripts/judgelitmus.sh b/tools/memory-model/scripts/judgelitmus.sh
index 0cc63875e395d..1ec5d89fcfbb2 100755
--- a/tools/memory-model/scripts/judgelitmus.sh
+++ b/tools/memory-model/scripts/judgelitmus.sh
@@ -1,9 +1,22 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0+
 #
-# Given a .litmus test and the corresponding .litmus.out file, check
-# the .litmus.out file against the "Result:" comment to judge whether
-# the test ran correctly.
+# Given a .litmus test and the corresponding litmus output file, check
+# the .litmus.out file against the "Result:" comment to judge whether the
+# test ran correctly.  If the --hw argument is omitted, check against the
+# LKMM output, which is assumed to be in file.litmus.out. If either a
+# "DATARACE" marker in the "Result:" comment or a "Flag data-race" marker
+# in the LKMM output is present, the other must also be as well, at least
+# for litmus tests having a "Result:" comment. In this case, a failure of
+# the Always/Sometimes/Never portion of the "Result:" prediction will be
+# noted, but forgiven.
+#
+# If the --hw argument is provided, this is assumed to be a hardware
+# test, and the output is assumed to be in file.litmus.HW.out, where
+# "HW" is the --hw argument. In addition, non-Sometimes verification
+# results will be noted, but forgiven.  Furthermore, if there is no
+# "Result:" comment but there is an LKMM .litmus.out file, the observation
+# in that file will be used to judge the assembly-language verification.
 #
 # Usage:
 #	judgelitmus.sh file.litmus
@@ -13,7 +26,7 @@
 #
 # Copyright IBM Corporation, 2018
 #
-# Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Author: Paul E. McKenney <paulmck@linux.ibm.com>
 
 litmus=$1
 
@@ -24,55 +37,120 @@ else
 	echo ' --- ' error: \"$litmus\" is not a readable file
 	exit 255
 fi
-if test -f "$LKMM_DESTDIR/$litmus".out -a -r "$LKMM_DESTDIR/$litmus".out
+if test -z "$LKMM_HW_MAP_FILE"
+then
+	litmusout=$litmus.out
+	lkmmout=
+else
+	litmusout="`echo $litmus |
+		sed -e 's/\.litmus$/.litmus.'${LKMM_HW_MAP_FILE}'/'`.out"
+	lkmmout=$litmus.out
+fi
+if test -f "$LKMM_DESTDIR/$litmusout" -a -r "$LKMM_DESTDIR/$litmusout"
 then
 	:
 else
-	echo ' --- ' error: \"$LKMM_DESTDIR/$litmus\".out is not a readable file
+	echo ' --- ' error: \"$LKMM_DESTDIR/$litmusout is not a readable file
 	exit 255
 fi
-if grep -q '^ \* Result: ' $litmus
+if grep -q '^Flag data-race$' "$LKMM_DESTDIR/$litmusout"
+then
+	datarace_modeled=1
+fi
+if grep -q '^[( ]\* Result: ' $litmus
+then
+	outcome=`grep -m 1 '^[( ]\* Result: ' $litmus | awk '{ print $3 }'`
+	if grep -m1 '^[( ]\* Result: .* DATARACE' $litmus
+	then
+		datarace_predicted=1
+	fi
+	if test -n "$datarace_predicted" -a -z "$datarace_modeled" -a -z "$LKMM_HW_MAP_FILE"
+	then
+		echo '!!! Predicted data race not modeled' $litmus
+		exit 252
+	elif test -z "$datarace_predicted" -a -n "$datarace_modeled"
+	then
+		# Note that hardware models currently don't model data races
+		echo '!!! Unexpected data race modeled' $litmus
+		exit 253
+	fi
+elif test -n "$LKMM_HW_MAP_FILE" && grep -q '^Observation' $LKMM_DESTDIR/$lkmmout > /dev/null 2>&1
 then
-	outcome=`grep -m 1 '^ \* Result: ' $litmus | awk '{ print $3 }'`
+	outcome=`grep -m 1 '^Observation ' $LKMM_DESTDIR/$lkmmout | awk '{ print $3 }'`
 else
 	outcome=specified
 fi
 
-grep '^Observation' $LKMM_DESTDIR/$litmus.out
-if grep -q '^Observation' $LKMM_DESTDIR/$litmus.out
+grep '^Observation' $LKMM_DESTDIR/$litmusout
+if grep -q '^Observation' $LKMM_DESTDIR/$litmusout
 then
 	:
+elif grep ': Unknown macro ' $LKMM_DESTDIR/$litmusout
+then
+	badname=`grep ': Unknown macro ' $LKMM_DESTDIR/$litmusout |
+		sed -e 's/^.*: Unknown macro //' |
+		sed -e 's/ (User error).*$//'`
+	badmsg=' !!! Current LKMM version does not know "'$badname'"'" $litmus"
+	echo $badmsg
+	if ! grep -q '!!!' $LKMM_DESTDIR/$litmusout
+	then
+		echo ' !!! '$badmsg >> $LKMM_DESTDIR/$litmusout 2>&1
+	fi
+	exit 254
+elif grep '^Command exited with non-zero status 124' $LKMM_DESTDIR/$litmusout
+then
+	echo ' !!! Timeout' $litmus
+	if ! grep -q '!!!' $LKMM_DESTDIR/$litmusout
+	then
+		echo ' !!! Timeout' >> $LKMM_DESTDIR/$litmusout 2>&1
+	fi
+	exit 124
 else
 	echo ' !!! Verification error' $litmus
-	if ! grep -q '!!!' $LKMM_DESTDIR/$litmus.out
+	if ! grep -q '!!!' $LKMM_DESTDIR/$litmusout
 	then
-		echo ' !!! Verification error' >> $LKMM_DESTDIR/$litmus.out 2>&1
+		echo ' !!! Verification error' >> $LKMM_DESTDIR/$litmusout 2>&1
 	fi
 	exit 255
 fi
 if test "$outcome" = DEADLOCK
 then
-	if grep '^Observation' $LKMM_DESTDIR/$litmus.out | grep -q 'Never 0 0$'
+	if grep '^Observation' $LKMM_DESTDIR/$litmusout | grep -q 'Never 0 0$'
 	then
 		ret=0
 	else
 		echo " !!! Unexpected non-$outcome verification" $litmus
-		if ! grep -q '!!!' $LKMM_DESTDIR/$litmus.out
+		if ! grep -q '!!!' $LKMM_DESTDIR/$litmusout
 		then
-			echo " !!! Unexpected non-$outcome verification" >> $LKMM_DESTDIR/$litmus.out 2>&1
+			echo " !!! Unexpected non-$outcome verification" >> $LKMM_DESTDIR/$litmusout 2>&1
 		fi
 		ret=1
 	fi
-elif grep '^Observation' $LKMM_DESTDIR/$litmus.out | grep -q $outcome || test "$outcome" = Maybe
+elif grep '^Observation' $LKMM_DESTDIR/$litmusout | grep -q 'Never 0 0$'
+then
+	echo " !!! Unexpected non-$outcome deadlock" $litmus
+	if ! grep -q '!!!' $LKMM_DESTDIR/$litmusout
+	then
+		echo " !!! Unexpected non-$outcome deadlock" $litmus >> $LKMM_DESTDIR/$litmusout 2>&1
+	fi
+	ret=1
+elif grep '^Observation' $LKMM_DESTDIR/$litmusout | grep -q $outcome || test "$outcome" = Maybe
 then
 	ret=0
 else
-	echo " !!! Unexpected non-$outcome verification" $litmus
-	if ! grep -q '!!!' $LKMM_DESTDIR/$litmus.out
+	if test \( -n "$LKMM_HW_MAP_FILE" -a "$outcome" = Sometimes \) -o -n "$datarace_modeled"
 	then
-		echo " !!! Unexpected non-$outcome verification" >> $LKMM_DESTDIR/$litmus.out 2>&1
+		flag="--- Forgiven"
+		ret=0
+	else
+		flag="!!! Unexpected"
+		ret=1
+	fi
+	echo " $flag non-$outcome verification" $litmus
+	if ! grep -qe "$flag" $LKMM_DESTDIR/$litmusout
+	then
+		echo " $flag non-$outcome verification" >> $LKMM_DESTDIR/$litmusout 2>&1
 	fi
-	ret=1
 fi
-tail -2 $LKMM_DESTDIR/$litmus.out | head -1
+tail -2 $LKMM_DESTDIR/$litmusout | head -1
 exit $ret
diff --git a/tools/memory-model/scripts/newlitmushist.sh b/tools/memory-model/scripts/newlitmushist.sh
index 991f8f8148817..25235e2049cf0 100755
--- a/tools/memory-model/scripts/newlitmushist.sh
+++ b/tools/memory-model/scripts/newlitmushist.sh
@@ -12,7 +12,7 @@
 #
 # Copyright IBM Corporation, 2018
 #
-# Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Author: Paul E. McKenney <paulmck@linux.ibm.com>
 
 . scripts/parseargs.sh
 
@@ -43,7 +43,7 @@ fi
 
 # Form full list of litmus tests with no more than the specified
 # number of processes (per the --procs argument).
-find litmus -name '*.litmus' -exec grep -l -m 1 "^C " {} \; > $T/list-C-all
+find litmus -name '*.litmus' -print | mselect7 -arch C > $T/list-C-all
 xargs < $T/list-C-all -r grep -L "^P${LKMM_PROCS}" > $T/list-C-short
 
 # Form list of new tests.  Note: This does not handle litmus-test deletion!
diff --git a/tools/memory-model/scripts/parseargs.sh b/tools/memory-model/scripts/parseargs.sh
index 40f52080fdbd6..08ded59098607 100755
--- a/tools/memory-model/scripts/parseargs.sh
+++ b/tools/memory-model/scripts/parseargs.sh
@@ -1,7 +1,7 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0+
 #
-# the corresponding .litmus.out file, and does not judge the result.
+# Parse arguments common to the various scripts.
 #
 # . scripts/parseargs.sh
 #
@@ -9,7 +9,7 @@
 #
 # Copyright IBM Corporation, 2018
 #
-# Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Author: Paul E. McKenney <paulmck@linux.ibm.com>
 
 T=/tmp/parseargs.sh.$$
 mkdir $T
@@ -27,6 +27,7 @@ initparam () {
 
 initparam LKMM_DESTDIR "."
 initparam LKMM_HERD_OPTIONS "-conf linux-kernel.cfg"
+initparam LKMM_HW_MAP_FILE ""
 initparam LKMM_JOBS `getconf _NPROCESSORS_ONLN`
 initparam LKMM_PROCS "3"
 initparam LKMM_TIMEOUT "1m"
@@ -37,10 +38,11 @@ usagehelp () {
 	echo "Usage $scriptname [ arguments ]"
 	echo "      --destdir path (place for .litmus.out, default by .litmus)"
 	echo "      --herdopts -conf linux-kernel.cfg ..."
+	echo "      --hw AArch64"
 	echo "      --jobs N (number of jobs, default one per CPU)"
 	echo "      --procs N (litmus tests with at most this many processes)"
 	echo "      --timeout N (herd7 timeout (e.g., 10s, 1m, 2hr, 1d, '')"
-	echo "Defaults: --destdir '$LKMM_DESTDIR_DEF' --herdopts '$LKMM_HERD_OPTIONS_DEF' --jobs '$LKMM_JOBS_DEF' --procs '$LKMM_PROCS_DEF' --timeout '$LKMM_TIMEOUT_DEF'"
+	echo "Defaults: --destdir '$LKMM_DESTDIR_DEF' --herdopts '$LKMM_HERD_OPTIONS_DEF' --hw '$LKMM_HW_MAP_FILE' --jobs '$LKMM_JOBS_DEF' --procs '$LKMM_PROCS_DEF' --timeout '$LKMM_TIMEOUT_DEF'"
 	exit 1
 }
 
@@ -81,7 +83,7 @@ do
 			echo "Cannot create directory --destdir '$LKMM_DESTDIR'"
 			usage
 		fi
-		if test -d "$LKMM_DESTDIR" -a -w "$LKMM_DESTDIR" -a -x "$LKMM_DESTDIR"
+		if test -d "$LKMM_DESTDIR" -a -x "$LKMM_DESTDIR"
 		then
 			:
 		else
@@ -95,6 +97,11 @@ do
 		LKMM_HERD_OPTIONS="$2"
 		shift
 		;;
+	--hw)
+		checkarg --hw "(.map file architecture name)" "$#" "$2" '^[A-Za-z0-9_-]\+' '^--'
+		LKMM_HW_MAP_FILE="$2"
+		shift
+		;;
 	-j[1-9]*)
 		njobs="`echo $1 | sed -e 's/^-j//'`"
 		trailchars="`echo $njobs | sed -e 's/[0-9]\+\(.*\)$/\1/'`"
@@ -106,7 +113,7 @@ do
 		LKMM_JOBS="`echo $njobs | sed -e 's/^\([0-9]\+\).*$/\1/'`"
 		;;
 	--jobs|--job|-j)
-		checkarg --jobs "(number)" "$#" "$2" '^[1-9][0-9]\+$' '^--'
+		checkarg --jobs "(number)" "$#" "$2" '^[1-9][0-9]*$' '^--'
 		LKMM_JOBS="$2"
 		shift
 		;;
@@ -120,6 +127,10 @@ do
 		LKMM_TIMEOUT="$2"
 		shift
 		;;
+	--)
+		shift
+		break
+		;;
 	*)
 		echo Unknown argument $1
 		usage
diff --git a/tools/memory-model/scripts/runlitmus.sh b/tools/memory-model/scripts/runlitmus.sh
new file mode 100755
index 0000000000000..94608d4b6502e
--- /dev/null
+++ b/tools/memory-model/scripts/runlitmus.sh
@@ -0,0 +1,80 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Without the -hw argument, runs a herd7 test and outputs verification
+# results to a file whose name is that of the specified litmus test,
+# but with ".out" appended.
+#
+# If the --hw argument is specified, this script translates the .litmus
+# C-language file to the specified type of assembly and verifies that.
+# But in this case, litmus tests using complex synchronization (such as
+# locking, RCU, and SRCU) are cheerfully ignored.
+#
+# Either way, return the status of the herd7 command.
+#
+# Usage:
+#	runlitmus.sh file.litmus
+#
+# Run this in the directory containing the memory model, specifying the
+# pathname of the litmus test to check.  The caller is expected to have
+# properly set up the LKMM environment variables.
+#
+# Copyright IBM Corporation, 2019
+#
+# Author: Paul E. McKenney <paulmck@linux.ibm.com>
+
+litmus=$1
+if test -f "$litmus" -a -r "$litmus"
+then
+	:
+else
+	echo ' !!! ' error: \"$litmus\" is not a readable file
+	exit 255
+fi
+
+if test -z "$LKMM_HW_MAP_FILE" -o ! -e $LKMM_DESTDIR/$litmus.out
+then
+	# LKMM run
+	herdoptions=${LKMM_HERD_OPTIONS--conf linux-kernel.cfg}
+	echo Herd options: $herdoptions > $LKMM_DESTDIR/$litmus.out
+	/usr/bin/time $LKMM_TIMEOUT_CMD herd7 $herdoptions $litmus >> $LKMM_DESTDIR/$litmus.out 2>&1
+	ret=$?
+	if test -z "$LKMM_HW_MAP_FILE"
+	then
+		exit $ret
+	fi
+	echo " --- " Automatically generated LKMM output for '"'--hw $LKMM_HW_MAP_FILE'"' run
+fi
+
+# Hardware run
+
+T=/tmp/checklitmushw.sh.$$
+trap 'rm -rf $T' 0 2
+mkdir $T
+
+# Generate filenames
+mapfile="Linux2${LKMM_HW_MAP_FILE}.map"
+themefile="$T/${LKMM_HW_MAP_FILE}.theme"
+herdoptions="-model $LKMM_HW_CAT_FILE"
+hwlitmus=`echo $litmus | sed -e 's/\.litmus$/.litmus.'${LKMM_HW_MAP_FILE}'/'`
+hwlitmusfile=`echo $hwlitmus | sed -e 's,^.*/,,'`
+
+# Don't run on litmus tests with complex synchronization
+if ! scripts/simpletest.sh $litmus
+then
+	echo ' --- ' error: \"$litmus\" contains locking, RCU, or SRCU
+	exit 254
+fi
+
+# Generate the assembly code and run herd7 on it.
+gen_theme7 -n 10 -map $mapfile -call Linux.call > $themefile
+jingle7 -v -theme $themefile $litmus > $LKMM_DESTDIR/$hwlitmus 2> $T/$hwlitmusfile.jingle7.out
+if grep -q "Generated 0 tests" $T/$hwlitmusfile.jingle7.out
+then
+	echo ' !!! ' jingle7 failed, errors in $hwlitmus.err
+	cp $T/$hwlitmusfile.jingle7.out $LKMM_DESTDIR/$hwlitmus.err
+	exit 253
+fi
+/usr/bin/time $LKMM_TIMEOUT_CMD herd7 -unroll 0 $LKMM_DESTDIR/$hwlitmus > $LKMM_DESTDIR/$hwlitmus.out 2>&1
+
+exit $?
diff --git a/tools/memory-model/scripts/runlitmushist.sh b/tools/memory-model/scripts/runlitmushist.sh
index 6ed376f495bb4..c6c2bdc67a502 100755
--- a/tools/memory-model/scripts/runlitmushist.sh
+++ b/tools/memory-model/scripts/runlitmushist.sh
@@ -13,7 +13,9 @@
 #
 # Copyright IBM Corporation, 2018
 #
-# Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Author: Paul E. McKenney <paulmck@linux.ibm.com>
+
+. scripts/hwfnseg.sh
 
 T=/tmp/runlitmushist.sh.$$
 trap 'rm -rf $T' 0
@@ -30,15 +32,12 @@ fi
 # Prefixes for per-CPU scripts
 for ((i=0;i<$LKMM_JOBS;i++))
 do
-	echo dir="$LKMM_DESTDIR" > $T/$i.sh
 	echo T=$T >> $T/$i.sh
-	echo herdoptions=\"$LKMM_HERD_OPTIONS\" >> $T/$i.sh
 	cat << '___EOF___' >> $T/$i.sh
 	runtest () {
-		echo ' ... ' /usr/bin/time $LKMM_TIMEOUT_CMD herd7 $herdoptions $1 '>' $dir/$1.out '2>&1'
-		if /usr/bin/time $LKMM_TIMEOUT_CMD herd7 $herdoptions $1 > $dir/$1.out 2>&1
+		if scripts/runlitmus.sh $1
 		then
-			if ! grep -q '^Observation ' $dir/$1.out
+			if ! grep -q '^Observation ' $LKMM_DESTDIR/$1$2.out
 			then
 				echo ' !!! Herd failed, no Observation:' $1
 			fi
@@ -47,10 +46,16 @@ do
 			if test "$exitcode" -eq 124
 			then
 				exitmsg="timed out"
+			elif test "$exitcode" -eq 253
+			then
+				exitmsg=
 			else
 				exitmsg="failed, exit code $exitcode"
 			fi
-			echo ' !!! Herd' ${exitmsg}: $1
+			if test -n "$exitmsg"
+			then
+				echo ' !!! Herd' ${exitmsg}: $1
+			fi
 		fi
 	}
 ___EOF___
@@ -59,11 +64,13 @@ done
 awk -v q="'" -v b='\\' '
 {
 	print "echo `grep " q "^P[0-9]" b "+(" q " " $0 " | tail -1 | sed -e " q "s/^P" b "([0-9]" b "+" b ")(.*$/" b "1/" q "` " $0
-}' | bash |
-sort -k1n |
-awk -v ncpu=$LKMM_JOBS -v t=$T '
+}' | sh | sort -k1n |
+awk -v dq='"' -v hwfnseg="$hwfnseg" -v ncpu="$LKMM_JOBS" -v t="$T" '
 {
-	print "runtest " $2 >> t "/" NR % ncpu ".sh";
+	print "if test -z " dq hwfnseg dq " || scripts/simpletest.sh " dq $2 dq
+	print "then"
+	print "\techo runtest " dq $2 dq " " hwfnseg " >> " t "/" NR % ncpu ".sh";
+	print "fi"
 }
 
 END {
diff --git a/tools/memory-model/scripts/simpletest.sh b/tools/memory-model/scripts/simpletest.sh
new file mode 100755
index 0000000000000..7edc5d3616657
--- /dev/null
+++ b/tools/memory-model/scripts/simpletest.sh
@@ -0,0 +1,35 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Give zero status if this is a simple test and non-zero otherwise.
+# Simple tests do not contain locking, RCU, or SRCU.
+#
+# Usage:
+#	simpletest.sh file.litmus
+#
+# Copyright IBM Corporation, 2019
+#
+# Author: Paul E. McKenney <paulmck@linux.ibm.com>
+
+
+litmus=$1
+
+if test -f "$litmus" -a -r "$litmus"
+then
+	:
+else
+	echo ' --- ' error: \"$litmus\" is not a readable file
+	exit 255
+fi
+exclude="^[[:space:]]*\("
+exclude="${exclude}spin_lock(\|spin_unlock(\|spin_trylock(\|spin_is_locked("
+exclude="${exclude}\|rcu_read_lock(\|rcu_read_unlock("
+exclude="${exclude}\|synchronize_rcu(\|synchronize_rcu_expedited("
+exclude="${exclude}\|srcu_read_lock(\|srcu_read_unlock("
+exclude="${exclude}\|synchronize_srcu(\|synchronize_srcu_expedited("
+exclude="${exclude}\)"
+if grep -q $exclude $litmus
+then
+	exit 255
+fi
+exit 0
diff --git a/tools/rcu/extract-stall.sh b/tools/rcu/extract-stall.sh
new file mode 100644
index 0000000000000..e565697c9f90e
--- /dev/null
+++ b/tools/rcu/extract-stall.sh
@@ -0,0 +1,34 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Extract any RCU CPU stall warnings present in specified file.
+# Filter out clocksource lines.  Note that preceding-lines excludes the
+# initial line of the stall warning but trailing-lines includes it.
+#
+# Usage: extract-stall.sh dmesg-file [ preceding-lines [ trailing-lines ] ]
+
+echo $1
+preceding_lines="${2-3}"
+trailing_lines="${3-10}"
+
+awk -v preceding_lines="$preceding_lines" -v trailing_lines="$trailing_lines" '
+suffix <= 0 {
+	for (i = preceding_lines; i > 0; i--)
+		last[i] = last[i - 1];
+	last[0] = $0;
+}
+
+suffix > 0 {
+	print $0;
+	suffix--;
+	if (suffix <= 0)
+		print "";
+}
+
+suffix <= 0 && /detected stall/ {
+	for (i = preceding_lines; i >= 0; i--)
+		if (last[i] != "")
+			print last[i];
+	suffix = trailing_lines;
+}' < "$1" | tr -d '\015' | grep -v clocksource
+
diff --git a/tools/testing/selftests/bpf/prog_tests/atomics.c b/tools/testing/selftests/bpf/prog_tests/atomics.c
index ba0e1efe5a45f..ca431c2917e9d 100644
--- a/tools/testing/selftests/bpf/prog_tests/atomics.c
+++ b/tools/testing/selftests/bpf/prog_tests/atomics.c
@@ -167,7 +167,7 @@ static void test_cmpxchg(struct atomics *skel)
 	prog_fd = skel->progs.cmpxchg.prog_fd;
 	err = bpf_prog_test_run(prog_fd, 1, NULL, 0,
 				NULL, NULL, &retval, &duration);
-	if (CHECK(err || retval, "test_run add",
+	if (CHECK(err || retval, "test_run cmpxchg",
 		  "err %d errno %d retval %d duration %d\n", err, errno, retval, duration))
 		goto cleanup;
 
@@ -196,7 +196,7 @@ static void test_xchg(struct atomics *skel)
 	prog_fd = skel->progs.xchg.prog_fd;
 	err = bpf_prog_test_run(prog_fd, 1, NULL, 0,
 				NULL, NULL, &retval, &duration);
-	if (CHECK(err || retval, "test_run add",
+	if (CHECK(err || retval, "test_run xchg",
 		  "err %d errno %d retval %d duration %d\n", err, errno, retval, duration))
 		goto cleanup;
 
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-remote.sh b/tools/testing/selftests/rcutorture/bin/kvm-remote.sh
index 03126eb6ec5ae..c7d42ef80c534 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-remote.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-remote.sh
@@ -149,6 +149,7 @@ do
 done
 
 # Download and expand the tarball on all systems.
+echo Build-products tarball: `du -h $T/binres.tgz` | tee -a "$oldrun/remote-log"
 for i in $systems
 do
 	echo Downloading tarball to $i `date` | tee -a "$oldrun/remote-log"
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index f442d84fb2a3e..6de0c183db5b9 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -74,7 +74,9 @@ usage () {
 	echo "       --help"
 	echo "       --interactive"
 	echo "       --jitter N [ maxsleep (us) [ maxspin (us) ] ]"
+	echo "       --kasan"
 	echo "       --kconfig Kconfig-options"
+	echo "       --kcsan"
 	echo "       --kmake-arg kernel-make-arguments"
 	echo "       --mac nn:nn:nn:nn:nn:nn"
 	echo "       --memory megabytes|nnnG"
@@ -83,6 +85,7 @@ usage () {
 	echo "       --qemu-cmd qemu-system-..."
 	echo "       --remote"
 	echo "       --results absolute-pathname"
+	echo "       --shutdown-grace seconds"
 	echo "       --torture lock|rcu|rcuscale|refscale|scf"
 	echo "       --trust-make"
 	exit 1
@@ -175,16 +178,16 @@ do
 		jitter="$2"
 		shift
 		;;
+	--kasan)
+		TORTURE_KCONFIG_KASAN_ARG="CONFIG_DEBUG_INFO=y CONFIG_KASAN=y"; export TORTURE_KCONFIG_KASAN_ARG
+		;;
 	--kconfig|--kconfigs)
 		checkarg --kconfig "(Kconfig options)" $# "$2" '^CONFIG_[A-Z0-9_]\+=\([ynm]\|[0-9]\+\)\( CONFIG_[A-Z0-9_]\+=\([ynm]\|[0-9]\+\)\)*$' '^error$'
 		TORTURE_KCONFIG_ARG="`echo "$TORTURE_KCONFIG_ARG $2" | sed -e 's/^ *//' -e 's/ *$//'`"
 		shift
 		;;
-	--kasan)
-		TORTURE_KCONFIG_KASAN_ARG="CONFIG_DEBUG_INFO=y CONFIG_KASAN=y"; export TORTURE_KCONFIG_KASAN_ARG
-		;;
 	--kcsan)
-		TORTURE_KCONFIG_KCSAN_ARG="CONFIG_DEBUG_INFO=y CONFIG_KCSAN=y CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC=n CONFIG_KCSAN_REPORT_VALUE_CHANGE_ONLY=n CONFIG_KCSAN_REPORT_ONCE_IN_MS=100000 CONFIG_KCSAN_INTERRUPT_WATCHER=y CONFIG_KCSAN_VERBOSE=y CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y"; export TORTURE_KCONFIG_KCSAN_ARG
+		TORTURE_KCONFIG_KCSAN_ARG="CONFIG_DEBUG_INFO=y CONFIG_KCSAN=y CONFIG_KCSAN_STRICT=y CONFIG_KCSAN_REPORT_ONCE_IN_MS=100000 CONFIG_KCSAN_VERBOSE=y CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y"; export TORTURE_KCONFIG_KCSAN_ARG
 		;;
 	--kmake-arg|--kmake-args)
 		checkarg --kmake-arg "(kernel make arguments)" $# "$2" '.*' '^error$'
diff --git a/tools/testing/selftests/rcutorture/bin/torture.sh b/tools/testing/selftests/rcutorture/bin/torture.sh
index 363f56081eff3..eae88aacca2aa 100755
--- a/tools/testing/selftests/rcutorture/bin/torture.sh
+++ b/tools/testing/selftests/rcutorture/bin/torture.sh
@@ -351,7 +351,7 @@ fi
 if test "$do_scftorture" = "yes"
 then
 	torture_bootargs="scftorture.nthreads=$HALF_ALLOTED_CPUS torture.disable_onoff_at_boot"
-	torture_set "scftorture" tools/testing/selftests/rcutorture/bin/kvm.sh --torture scf --allcpus --duration "$duration_scftorture" --configs "$configs_scftorture" --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --trust-make
+	torture_set "scftorture" tools/testing/selftests/rcutorture/bin/kvm.sh --torture scf --allcpus --duration "$duration_scftorture" --configs "$configs_scftorture" --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --memory 1G --trust-make
 fi
 
 if test "$do_refscale" = yes
@@ -434,7 +434,12 @@ then
 	batchno=1
 	if test -s $T/xz-todo
 	then
-		echo Size before compressing: `du -sh $tdir | awk '{ print $1 }'` `date` 2>&1 | tee -a "$tdir/log-xz" | tee -a $T/log
+		for i in `cat $T/xz-todo`
+		do
+			find $i -name 'vmlinux*' -print
+		done | wc -l | awk '{ print $1 }' > $T/xz-todo-count
+		n2compress="`cat $T/xz-todo-count`"
+		echo Size before compressing $n2compress files: `du -sh $tdir | awk '{ print $1 }'` `date` 2>&1 | tee -a "$tdir/log-xz" | tee -a $T/log
 		for i in `cat $T/xz-todo`
 		do
 			echo Compressing vmlinux files in ${i}: `date` >> "$tdir/log-xz" 2>&1
@@ -456,7 +461,7 @@ then
 			echo Waiting for final batch $batchno of $ncompresses compressions `date` | tee -a "$tdir/log-xz" | tee -a $T/log
 		fi
 		wait
-		echo Size after compressing: `du -sh $tdir | awk '{ print $1 }'` `date` 2>&1 | tee -a "$tdir/log-xz" | tee -a $T/log
+		echo Size after compressing $n2compress files: `du -sh $tdir | awk '{ print $1 }'` `date` 2>&1 | tee -a "$tdir/log-xz" | tee -a $T/log
 		echo Total duration `get_starttime_duration $starttime`. | tee -a $T/log
 	else
 		echo No compression needed: `date` >> "$tdir/log-xz" 2>&1
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 b/tools/testing/selftests/rcutorture/configs/rcu/TREE01
index b5b53973c01e4..8ae41d5f81a3e 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01
@@ -6,7 +6,6 @@ CONFIG_PREEMPT=y
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
-CONFIG_RCU_FAST_NO_HZ=y
 CONFIG_RCU_TRACE=y
 CONFIG_HOTPLUG_CPU=y
 CONFIG_MAXSMP=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02 b/tools/testing/selftests/rcutorture/configs/rcu/TREE02
index 65daee4fbf5a3..2871ee599891d 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE02
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02
@@ -7,7 +7,6 @@ CONFIG_PREEMPT=y
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
-CONFIG_RCU_FAST_NO_HZ=n
 CONFIG_RCU_TRACE=n
 CONFIG_RCU_FANOUT=3
 CONFIG_RCU_FANOUT_LEAF=3
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 b/tools/testing/selftests/rcutorture/configs/rcu/TREE04
index f6d6a40c05768..22ad0261728d0 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04
@@ -7,7 +7,6 @@ CONFIG_PREEMPT=n
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=n
 CONFIG_NO_HZ_FULL=y
-CONFIG_RCU_FAST_NO_HZ=y
 CONFIG_RCU_TRACE=y
 CONFIG_RCU_FANOUT=4
 CONFIG_RCU_FANOUT_LEAF=3
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE05 b/tools/testing/selftests/rcutorture/configs/rcu/TREE05
index 4f95f8544f3f0..9f48c73709ec3 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE05
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05
@@ -7,7 +7,6 @@ CONFIG_PREEMPT=n
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
-CONFIG_RCU_FAST_NO_HZ=n
 CONFIG_RCU_TRACE=n
 CONFIG_HOTPLUG_CPU=y
 CONFIG_RCU_FANOUT=6
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 b/tools/testing/selftests/rcutorture/configs/rcu/TREE06
index bf4980d606b50..db27651de04b8 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE06
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06
@@ -7,7 +7,6 @@ CONFIG_PREEMPT=n
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
-CONFIG_RCU_FAST_NO_HZ=n
 CONFIG_RCU_TRACE=n
 CONFIG_RCU_FANOUT=6
 CONFIG_RCU_FANOUT_LEAF=6
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 b/tools/testing/selftests/rcutorture/configs/rcu/TREE07
index d7afb271a586d..2789b47e4ecd7 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE07
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07
@@ -7,7 +7,6 @@ CONFIG_PREEMPT=n
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=n
 CONFIG_NO_HZ_FULL=y
-CONFIG_RCU_FAST_NO_HZ=n
 CONFIG_RCU_TRACE=y
 CONFIG_HOTPLUG_CPU=y
 CONFIG_RCU_FANOUT=2
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08 b/tools/testing/selftests/rcutorture/configs/rcu/TREE08
index c810c5276a89f..8b561355b9ef2 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08
@@ -7,7 +7,6 @@ CONFIG_PREEMPT=y
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
-CONFIG_RCU_FAST_NO_HZ=n
 CONFIG_RCU_TRACE=n
 CONFIG_RCU_FANOUT=3
 CONFIG_RCU_FANOUT_LEAF=2
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE10 b/tools/testing/selftests/rcutorture/configs/rcu/TREE10
index 7311f84a58765..4a00539bfdd71 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE10
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE10
@@ -7,7 +7,6 @@ CONFIG_PREEMPT=n
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
-CONFIG_RCU_FAST_NO_HZ=n
 CONFIG_RCU_TRACE=n
 CONFIG_RCU_NOCB_CPU=n
 CONFIG_DEBUG_LOCK_ALLOC=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcuscale/TINY b/tools/testing/selftests/rcutorture/configs/rcuscale/TINY
index fb05ef5279b43..7a7bf776a448b 100644
--- a/tools/testing/selftests/rcutorture/configs/rcuscale/TINY
+++ b/tools/testing/selftests/rcutorture/configs/rcuscale/TINY
@@ -6,7 +6,6 @@ CONFIG_PREEMPT=n
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
-CONFIG_RCU_FAST_NO_HZ=n
 CONFIG_RCU_NOCB_CPU=n
 CONFIG_DEBUG_LOCK_ALLOC=n
 CONFIG_PROVE_LOCKING=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01 b/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01
index e6baa2fbaeb33..227aba7783aff 100644
--- a/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01
+++ b/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01
@@ -5,7 +5,6 @@ CONFIG_PREEMPT=n
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
-CONFIG_RCU_FAST_NO_HZ=n
 CONFIG_RCU_NOCB_CPU=n
 CONFIG_DEBUG_LOCK_ALLOC=n
 CONFIG_PROVE_LOCKING=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcuscale/TREE b/tools/testing/selftests/rcutorture/configs/rcuscale/TREE
index 4cc1cc5813214..f110d9ffbe4cb 100644
--- a/tools/testing/selftests/rcutorture/configs/rcuscale/TREE
+++ b/tools/testing/selftests/rcutorture/configs/rcuscale/TREE
@@ -6,7 +6,6 @@ CONFIG_PREEMPT=y
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
-CONFIG_RCU_FAST_NO_HZ=n
 CONFIG_HOTPLUG_CPU=y
 CONFIG_SUSPEND=n
 CONFIG_HIBERNATION=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcuscale/TREE54 b/tools/testing/selftests/rcutorture/configs/rcuscale/TREE54
index f5952061fde7b..9f83e53727969 100644
--- a/tools/testing/selftests/rcutorture/configs/rcuscale/TREE54
+++ b/tools/testing/selftests/rcutorture/configs/rcuscale/TREE54
@@ -7,7 +7,6 @@ CONFIG_PREEMPT=y
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
-CONFIG_RCU_FAST_NO_HZ=n
 CONFIG_HOTPLUG_CPU=y
 CONFIG_SUSPEND=n
 CONFIG_HIBERNATION=n
diff --git a/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT
index ad505a887bec4..7f06838a91e61 100644
--- a/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT
+++ b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT
@@ -6,7 +6,6 @@ CONFIG_PREEMPT=n
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
-CONFIG_RCU_FAST_NO_HZ=n
 CONFIG_HOTPLUG_CPU=y
 CONFIG_SUSPEND=n
 CONFIG_HIBERNATION=n
diff --git a/tools/testing/selftests/rcutorture/configs/refscale/PREEMPT b/tools/testing/selftests/rcutorture/configs/refscale/PREEMPT
index 4f08e641bb6b8..52e3ef6740567 100644
--- a/tools/testing/selftests/rcutorture/configs/refscale/PREEMPT
+++ b/tools/testing/selftests/rcutorture/configs/refscale/PREEMPT
@@ -6,7 +6,6 @@ CONFIG_PREEMPT=y
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
-CONFIG_RCU_FAST_NO_HZ=n
 CONFIG_HOTPLUG_CPU=y
 CONFIG_SUSPEND=n
 CONFIG_HIBERNATION=n
diff --git a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
index 1b96d68473b8f..42acb1a64ce10 100644
--- a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
+++ b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
@@ -15,7 +15,6 @@ CONFIG_PROVE_RCU -- Hardwired to CONFIG_PROVE_LOCKING.
 CONFIG_RCU_BOOST -- one of PREEMPT_RCU.
 CONFIG_RCU_FANOUT -- Cover hierarchy, but overlap with others.
 CONFIG_RCU_FANOUT_LEAF -- Do one non-default.
-CONFIG_RCU_FAST_NO_HZ -- Do one, but not with all nohz_full CPUs.
 CONFIG_RCU_NOCB_CPU -- Do three, one with no rcu_nocbs CPUs, one with
 	rcu_nocbs=0, and one with all rcu_nocbs CPUs.
 CONFIG_RCU_TRACE -- Do half.