Merge branch 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull RCU changes from Ingo Molnar:
 "The main changes in this cycle were:

   - changes permitting use of call_rcu() and friends very early in
     boot, for example, before rcu_init() is invoked.

   - add in-kernel API to enable and disable expediting of normal RCU
     grace periods.

   - improve RCU's handling of (hotplug-) outgoing CPUs.

   - NO_HZ_FULL_SYSIDLE fixes.

   - tiny-RCU updates to make it more tiny.

   - documentation updates.

   - miscellaneous fixes"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (58 commits)
  cpu: Provide smpboot_thread_init() on !CONFIG_SMP kernels as well
  cpu: Defer smpboot kthread unparking until CPU known to scheduler
  rcu: Associate quiescent-state reports with grace period
  rcu: Yet another fix for preemption and CPU hotplug
  rcu: Add diagnostics to grace-period cleanup
  rcutorture: Default to grace-period-initialization delays
  rcu: Handle outgoing CPUs on exit from idle loop
  cpu: Make CPU-offline idle-loop transition point more precise
  rcu: Eliminate ->onoff_mutex from rcu_node structure
  rcu: Process offlining and onlining only at grace-period start
  rcu: Move rcu_report_unblock_qs_rnp() to common code
  rcu: Rework preemptible expedited bitmask handling
  rcu: Remove event tracing from rcu_cpu_notify(), used by offline CPUs
  rcutorture: Enable slow grace-period initializations
  rcu: Provide diagnostic option to slow down grace-period initialization
  rcu: Detect stalls caused by failure to propagate up rcu_node tree
  rcu: Eliminate empty HOTPLUG_CPU ifdef
  rcu: Simplify sync_rcu_preempt_exp_init()
  rcu: Put all orphan-callback-related code under same comment
  rcu: Consolidate offline-CPU callback initialization
  ...

Documentation/atomic_ops.txt

@@ -201,11 +201,11 @@ These routines add 1 and subtract 1, respectively, from the given
 atomic_t and return the new counter value after the operation is
 performed.
 
-Unlike the above routines, it is required that explicit memory
-barriers are performed before and after the operation.  It must be
-done such that all memory operations before and after the atomic
-operation calls are strongly ordered with respect to the atomic
-operation itself.
+Unlike the above routines, it is required that these primitives
+include explicit memory barriers that are performed before and after
+the operation.  It must be done such that all memory operations before
+and after the atomic operation calls are strongly ordered with respect
+to the atomic operation itself.
 
 For example, it should behave as if a smp_mb() call existed both
 before and after the atomic operation.
@@ -233,21 +233,21 @@ These two routines increment and decrement by 1, respectively, the
 given atomic counter.  They return a boolean indicating whether the
 resulting counter value was zero or not.
 
-It requires explicit memory barrier semantics around the operation as
-above.
+Again, these primitives provide explicit memory barrier semantics around
+the atomic operation.
 
 	int atomic_sub_and_test(int i, atomic_t *v);
 
 This is identical to atomic_dec_and_test() except that an explicit
-decrement is given instead of the implicit "1".  It requires explicit
-memory barrier semantics around the operation.
+decrement is given instead of the implicit "1".  This primitive must
+provide explicit memory barrier semantics around the operation.
 
 	int atomic_add_negative(int i, atomic_t *v);
 
-The given increment is added to the given atomic counter value.  A
-boolean is return which indicates whether the resulting counter value
-is negative.  It requires explicit memory barrier semantics around the
-operation.
+The given increment is added to the given atomic counter value.  A boolean
+is return which indicates whether the resulting counter value is negative.
+This primitive must provide explicit memory barrier semantics around
+the operation.
 
 Then:
 
@@ -257,7 +257,7 @@ This performs an atomic exchange operation on the atomic variable v, setting
 the given new value.  It returns the old value that the atomic variable v had
 just before the operation.
 
-atomic_xchg requires explicit memory barriers around the operation.
+atomic_xchg must provide explicit memory barriers around the operation.
 
 	int atomic_cmpxchg(atomic_t *v, int old, int new);
 
@@ -266,7 +266,7 @@ with the given old and new values. Like all atomic_xxx operations,
 atomic_cmpxchg will only satisfy its atomicity semantics as long as all
 other accesses of *v are performed through atomic_xxx operations.
 
-atomic_cmpxchg requires explicit memory barriers around the operation.
+atomic_cmpxchg must provide explicit memory barriers around the operation.
 
 The semantics for atomic_cmpxchg are the same as those defined for 'cas'
 below.
@@ -279,8 +279,8 @@ If the atomic value v is not equal to u, this function adds a to v, and
 returns non zero. If v is equal to u then it returns zero. This is done as
 an atomic operation.
 
-atomic_add_unless requires explicit memory barriers around the operation
-unless it fails (returns 0).
+atomic_add_unless must provide explicit memory barriers around the
+operation unless it fails (returns 0).
 
 atomic_inc_not_zero, equivalent to atomic_add_unless(v, 1, 0)
 
@@ -460,9 +460,9 @@ the return value into an int.  There are other places where things
 like this occur as well.
 
 These routines, like the atomic_t counter operations returning values,
-require explicit memory barrier semantics around their execution.  All
-memory operations before the atomic bit operation call must be made
-visible globally before the atomic bit operation is made visible.
+must provide explicit memory barrier semantics around their execution.
+All memory operations before the atomic bit operation call must be
+made visible globally before the atomic bit operation is made visible.
 Likewise, the atomic bit operation must be visible globally before any
 subsequent memory operation is made visible.  For example:
 
@@ -536,8 +536,9 @@ except that two underscores are prefixed to the interface name.
 These non-atomic variants also do not require any special memory
 barrier semantics.
 
-The routines xchg() and cmpxchg() need the same exact memory barriers
-as the atomic and bit operations returning values.
+The routines xchg() and cmpxchg() must provide the same exact
+memory-barrier semantics as the atomic and bit operations returning
+values.
 
 Spinlocks and rwlocks have memory barrier expectations as well.
 The rule to follow is simple:

Documentation/kernel-parameters.txt

@@ -2969,6 +2969,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Set maximum number of finished RCU callbacks to
 			process in one batch.
 
+	rcutree.gp_init_delay=	[KNL]
+			Set the number of jiffies to delay each step of
+			RCU grace-period initialization.  This only has
+			effect when CONFIG_RCU_TORTURE_TEST_SLOW_INIT is
+			set.
+
 	rcutree.rcu_fanout_leaf= [KNL]
 			Increase the number of CPUs assigned to each
 			leaf rcu_node structure.  Useful for very large
@@ -2992,11 +2998,15 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			value is one, and maximum value is HZ.
 
 	rcutree.kthread_prio= 	 [KNL,BOOT]
-			Set the SCHED_FIFO priority of the RCU
-			per-CPU kthreads (rcuc/N). This value is also
-			used for the priority of the RCU boost threads
-			(rcub/N). Valid values are 1-99 and the default
-			is 1 (the least-favored priority).
+			Set the SCHED_FIFO priority of the RCU per-CPU
+			kthreads (rcuc/N). This value is also used for
+			the priority of the RCU boost threads (rcub/N)
+			and for the RCU grace-period kthreads (rcu_bh,
+			rcu_preempt, and rcu_sched). If RCU_BOOST is
+			set, valid values are 1-99 and the default is 1
+			(the least-favored priority).  Otherwise, when
+			RCU_BOOST is not set, valid values are 0-99 and
+			the default is zero (non-realtime operation).
 
 	rcutree.rcu_nocb_leader_stride= [KNL]
 			Set the number of NOCB kthread groups, which

Documentation/kernel-per-CPU-kthreads.txt

@@ -190,20 +190,24 @@ To reduce its OS jitter, do any of the following:
 		on each CPU, including cs_dbs_timer() and od_dbs_timer().
 		WARNING:  Please check your CPU specifications to
 		make sure that this is safe on your particular system.
-	d.	It is not possible to entirely get rid of OS jitter
-		from vmstat_update() on CONFIG_SMP=y systems, but you
-		can decrease its frequency by writing a large value
-		to /proc/sys/vm/stat_interval.	The default value is
-		HZ, for an interval of one second.  Of course, larger
-		values will make your virtual-memory statistics update
-		more slowly.  Of course, you can also run your workload
-		at a real-time priority, thus preempting vmstat_update(),
+	d.	As of v3.18, Christoph Lameter's on-demand vmstat workers
+		commit prevents OS jitter due to vmstat_update() on
+		CONFIG_SMP=y systems.  Before v3.18, is not possible
+		to entirely get rid of the OS jitter, but you can
+		decrease its frequency by writing a large value to
+		/proc/sys/vm/stat_interval.  The default value is HZ,
+		for an interval of one second.	Of course, larger values
+		will make your virtual-memory statistics update more
+		slowly.  Of course, you can also run your workload at
+		a real-time priority, thus preempting vmstat_update(),
 		but if your workload is CPU-bound, this is a bad idea.
 		However, there is an RFC patch from Christoph Lameter
 		(based on an earlier one from Gilad Ben-Yossef) that
 		reduces or even eliminates vmstat overhead for some
 		workloads at https://lkml.org/lkml/2013/9/4/379.
-	e.	If running on high-end powerpc servers, build with
+	e.	Boot with "elevator=noop" to avoid workqueue use by
+		the block layer.
+	f.	If running on high-end powerpc servers, build with
 		CONFIG_PPC_RTAS_DAEMON=n.  This prevents the RTAS
 		daemon from running on each CPU every second or so.
 		(This will require editing Kconfig files and will defeat
@@ -211,12 +215,12 @@ To reduce its OS jitter, do any of the following:
 		due to the rtas_event_scan() function.
 		WARNING:  Please check your CPU specifications to
 		make sure that this is safe on your particular system.
-	f.	If running on Cell Processor, build your kernel with
+	g.	If running on Cell Processor, build your kernel with
 		CBE_CPUFREQ_SPU_GOVERNOR=n to avoid OS jitter from
 		spu_gov_work().
 		WARNING:  Please check your CPU specifications to
 		make sure that this is safe on your particular system.
-	g.	If running on PowerMAC, build your kernel with
+	h.	If running on PowerMAC, build your kernel with
 		CONFIG_PMAC_RACKMETER=n to disable the CPU-meter,
 		avoiding OS jitter from rackmeter_do_timer().
 
@@ -258,8 +262,12 @@ Purpose: Detect software lockups on each CPU.
 To reduce its OS jitter, do at least one of the following:
 1.	Build with CONFIG_LOCKUP_DETECTOR=n, which will prevent these
 	kthreads from being created in the first place.
-2.	Echo a zero to /proc/sys/kernel/watchdog to disable the
+2.	Boot with "nosoftlockup=0", which will also prevent these kthreads
+	from being created.  Other related watchdog and softlockup boot
+	parameters may be found in Documentation/kernel-parameters.txt
+	and Documentation/watchdog/watchdog-parameters.txt.
+3.	Echo a zero to /proc/sys/kernel/watchdog to disable the
 	watchdog timer.
-3.	Echo a large number of /proc/sys/kernel/watchdog_thresh in
+4.	Echo a large number of /proc/sys/kernel/watchdog_thresh in
 	order to reduce the frequency of OS jitter due to the watchdog
 	timer down to a level that is acceptable for your workload.

Documentation/memory-barriers.txt

@@ -592,9 +592,9 @@ See also the subsection on "Cache Coherency" for a more thorough example.
 CONTROL DEPENDENCIES
 --------------------
 
-A control dependency requires a full read memory barrier, not simply a data
-dependency barrier to make it work correctly.  Consider the following bit of
-code:
+A load-load control dependency requires a full read memory barrier, not
+simply a data dependency barrier to make it work correctly.  Consider the
+following bit of code:
 
 	q = ACCESS_ONCE(a);
 	if (q) {
@@ -615,14 +615,15 @@ case what's actually required is:
 	}
 
 However, stores are not speculated.  This means that ordering -is- provided
-in the following example:
+for load-store control dependencies, as in the following example:
 
 	q = ACCESS_ONCE(a);
 	if (q) {
 		ACCESS_ONCE(b) = p;
 	}
 
-Please note that ACCESS_ONCE() is not optional!  Without the
+Control dependencies pair normally with other types of barriers.
+That said, please note that ACCESS_ONCE() is not optional!  Without the
 ACCESS_ONCE(), might combine the load from 'a' with other loads from
 'a', and the store to 'b' with other stores to 'b', with possible highly
 counterintuitive effects on ordering.
@@ -813,6 +814,8 @@ In summary:
       barrier() can help to preserve your control dependency.  Please
       see the Compiler Barrier section for more information.
 
+  (*) Control dependencies pair normally with other types of barriers.
+
   (*) Control dependencies do -not- provide transitivity.  If you
       need transitivity, use smp_mb().
 
@@ -823,14 +826,14 @@ SMP BARRIER PAIRING
 When dealing with CPU-CPU interactions, certain types of memory barrier should
 always be paired.  A lack of appropriate pairing is almost certainly an error.
 
-General barriers pair with each other, though they also pair with
-most other types of barriers, albeit without transitivity.  An acquire
-barrier pairs with a release barrier, but both may also pair with other
-barriers, including of course general barriers.  A write barrier pairs
-with a data dependency barrier, an acquire barrier, a release barrier,
-a read barrier, or a general barrier.  Similarly a read barrier or a
-data dependency barrier pairs with a write barrier, an acquire barrier,
-a release barrier, or a general barrier:
+General barriers pair with each other, though they also pair with most
+other types of barriers, albeit without transitivity.  An acquire barrier
+pairs with a release barrier, but both may also pair with other barriers,
+including of course general barriers.  A write barrier pairs with a data
+dependency barrier, a control dependency, an acquire barrier, a release
+barrier, a read barrier, or a general barrier.  Similarly a read barrier,
+control dependency, or a data dependency barrier pairs with a write
+barrier, an acquire barrier, a release barrier, or a general barrier:
 
 	CPU 1		      CPU 2
 	===============	      ===============
@@ -850,6 +853,19 @@ Or:
 			      <data dependency barrier>
 			      y = *x;
 
+Or even:
+
+	CPU 1		      CPU 2
+	===============	      ===============================
+	r1 = ACCESS_ONCE(y);
+	<general barrier>
+	ACCESS_ONCE(y) = 1;   if (r2 = ACCESS_ONCE(x)) {
+			         <implicit control dependency>
+			         ACCESS_ONCE(y) = 1;
+			      }
+
+	assert(r1 == 0 || r2 == 0);
+
 Basically, the read barrier always has to be there, even though it can be of
 the "weaker" type.
 

Documentation/timers/NO_HZ.txt

@@ -158,13 +158,9 @@ not come for free:
 	to the need to inform kernel subsystems (such as RCU) about
 	the change in mode.
 
-3.	POSIX CPU timers on adaptive-tick CPUs may miss their deadlines
-	(perhaps indefinitely) because they currently rely on
-	scheduling-tick interrupts.  This will likely be fixed in
-	one of two ways: (1) Prevent CPUs with POSIX CPU timers from
-	entering adaptive-tick mode, or (2) Use hrtimers or other
-	adaptive-ticks-immune mechanism to cause the POSIX CPU timer to
-	fire properly.
+3.	POSIX CPU timers prevent CPUs from entering adaptive-tick mode.
+	Real-time applications needing to take actions based on CPU time
+	consumption need to use other means of doing so.
 
 4.	If there are more perf events pending than the hardware can
 	accommodate, they are normally round-robined so as to collect

arch/blackfin/mach-common/smp.c

@@ -413,16 +413,14 @@ int __cpu_disable(void)
 	return 0;
 }
 
-static DECLARE_COMPLETION(cpu_killed);
-
 int __cpu_die(unsigned int cpu)
 {
-	return wait_for_completion_timeout(&cpu_killed, 5000);
+	return cpu_wait_death(cpu, 5);
 }
 
 void cpu_die(void)
 {
-	complete(&cpu_killed);
+	(void)cpu_report_death();
 
 	atomic_dec(&init_mm.mm_users);
 	atomic_dec(&init_mm.mm_count);

arch/metag/kernel/smp.c

@@ -261,7 +261,6 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static DECLARE_COMPLETION(cpu_killed);
 
 /*
  * __cpu_disable runs on the processor to be shutdown.
@@ -299,7 +298,7 @@ int __cpu_disable(void)
  */
 void __cpu_die(unsigned int cpu)
 {
-	if (!wait_for_completion_timeout(&cpu_killed, msecs_to_jiffies(1)))
+	if (!cpu_wait_death(cpu, 1))
 		pr_err("CPU%u: unable to kill\n", cpu);
 }
 
@@ -314,7 +313,7 @@ void cpu_die(void)
 	local_irq_disable();
 	idle_task_exit();
 
-	complete(&cpu_killed);
+	(void)cpu_report_death();
 
 	asm ("XOR	TXENABLE, D0Re0,D0Re0\n");
 }

arch/x86/include/asm/cpu.h

@@ -34,8 +34,6 @@ extern int _debug_hotplug_cpu(int cpu, int action);
 #endif
 #endif
 
-DECLARE_PER_CPU(int, cpu_state);
-
 int mwait_usable(const struct cpuinfo_x86 *);
 
 #endif /* _ASM_X86_CPU_H */

arch/x86/include/asm/smp.h

@@ -150,13 +150,13 @@ static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 }
 
 void cpu_disable_common(void);
-void cpu_die_common(unsigned int cpu);
 void native_smp_prepare_boot_cpu(void);
 void native_smp_prepare_cpus(unsigned int max_cpus);
 void native_smp_cpus_done(unsigned int max_cpus);
 void common_cpu_up(unsigned int cpunum, struct task_struct *tidle);
 int native_cpu_up(unsigned int cpunum, struct task_struct *tidle);
 int native_cpu_disable(void);
+int common_cpu_die(unsigned int cpu);
 void native_cpu_die(unsigned int cpu);
 void native_play_dead(void);
 void play_dead_common(void);

arch/x86/kernel/smpboot.c

@@ -77,9 +77,6 @@
 #include <asm/realmode.h>
 #include <asm/misc.h>
 
-/* State of each CPU */
-DEFINE_PER_CPU(int, cpu_state) = { 0 };
-
 /* Number of siblings per CPU package */
 int smp_num_siblings = 1;
 EXPORT_SYMBOL(smp_num_siblings);
@@ -257,7 +254,7 @@ static void notrace start_secondary(void *unused)
 	lock_vector_lock();
 	set_cpu_online(smp_processor_id(), true);
 	unlock_vector_lock();
-	per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
+	cpu_set_state_online(smp_processor_id());
 	x86_platform.nmi_init();
 
 	/* enable local interrupts */
@@ -954,7 +951,10 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
 	 */
 	mtrr_save_state();
 
-	per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
+	/* x86 CPUs take themselves offline, so delayed offline is OK. */
+	err = cpu_check_up_prepare(cpu);
+	if (err && err != -EBUSY)
+		return err;
 
 	/* the FPU context is blank, nobody can own it */
 	__cpu_disable_lazy_restore(cpu);
@@ -1197,7 +1197,7 @@ void __init native_smp_prepare_boot_cpu(void)
 	switch_to_new_gdt(me);
 	/* already set me in cpu_online_mask in boot_cpu_init() */
 	cpumask_set_cpu(me, cpu_callout_mask);
-	per_cpu(cpu_state, me) = CPU_ONLINE;
+	cpu_set_state_online(me);
 }
 
 void __init native_smp_cpus_done(unsigned int max_cpus)
@@ -1324,14 +1324,10 @@ static void __ref remove_cpu_from_maps(int cpu)
 	numa_remove_cpu(cpu);
 }
 
-static DEFINE_PER_CPU(struct completion, die_complete);
-
 void cpu_disable_common(void)
 {
 	int cpu = smp_processor_id();
 
-	init_completion(&per_cpu(die_complete, smp_processor_id()));
-
 	remove_siblinginfo(cpu);
 
 	/* It's now safe to remove this processor from the online map */
@@ -1355,24 +1351,27 @@ int native_cpu_disable(void)
 	return 0;
 }
 
-void cpu_die_common(unsigned int cpu)
+int common_cpu_die(unsigned int cpu)
 {
-	wait_for_completion_timeout(&per_cpu(die_complete, cpu), HZ);
-}
+	int ret = 0;
 
-void native_cpu_die(unsigned int cpu)
-{
 	/* We don't do anything here: idle task is faking death itself. */
 
-	cpu_die_common(cpu);
-
 	/* They ack this in play_dead() by setting CPU_DEAD */
-	if (per_cpu(cpu_state, cpu) == CPU_DEAD) {
+	if (cpu_wait_death(cpu, 5)) {
 		if (system_state == SYSTEM_RUNNING)
 			pr_info("CPU %u is now offline\n", cpu);
 	} else {
 		pr_err("CPU %u didn't die...\n", cpu);
+		ret = -1;
 	}
+
+	return ret;
+}
+
+void native_cpu_die(unsigned int cpu)
+{
+	common_cpu_die(cpu);
 }
 
 void play_dead_common(void)
@@ -1381,10 +1380,8 @@ void play_dead_common(void)
 	reset_lazy_tlbstate();
 	amd_e400_remove_cpu(raw_smp_processor_id());
 
-	mb();
 	/* Ack it */
-	__this_cpu_write(cpu_state, CPU_DEAD);
-	complete(&per_cpu(die_complete, smp_processor_id()));
+	(void)cpu_report_death();
 
 	/*
 	 * With physical CPU hotplug, we should halt the cpu

arch/x86/xen/smp.c

@@ -90,14 +90,10 @@ static void cpu_bringup(void)
 
 	set_cpu_online(cpu, true);
 
-	this_cpu_write(cpu_state, CPU_ONLINE);
-
-	wmb();
+	cpu_set_state_online(cpu);  /* Implies full memory barrier. */
 
 	/* We can take interrupts now: we're officially "up". */
 	local_irq_enable();
-
-	wmb();			/* make sure everything is out */
 }
 
 /*
@@ -451,7 +447,13 @@ static int xen_cpu_up(unsigned int cpu, struct task_struct *idle)
 	xen_setup_timer(cpu);
 	xen_init_lock_cpu(cpu);
 
-	per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
+	/*
+	 * PV VCPUs are always successfully taken down (see 'while' loop
+	 * in xen_cpu_die()), so -EBUSY is an error.
+	 */
+	rc = cpu_check_up_prepare(cpu);
+	if (rc)
+		return rc;
 
 	/* make sure interrupts start blocked */
 	per_cpu(xen_vcpu, cpu)->evtchn_upcall_mask = 1;
@@ -467,10 +469,8 @@ static int xen_cpu_up(unsigned int cpu, struct task_struct *idle)
 	rc = HYPERVISOR_vcpu_op(VCPUOP_up, cpu, NULL);
 	BUG_ON(rc);
 
-	while(per_cpu(cpu_state, cpu) != CPU_ONLINE) {
+	while (cpu_report_state(cpu) != CPU_ONLINE)
 		HYPERVISOR_sched_op(SCHEDOP_yield, NULL);
-		barrier();
-	}
 
 	return 0;
 }
@@ -499,11 +499,11 @@ static void xen_cpu_die(unsigned int cpu)
 		schedule_timeout(HZ/10);
 	}
 
-	cpu_die_common(cpu);
-
-	xen_smp_intr_free(cpu);
-	xen_uninit_lock_cpu(cpu);
-	xen_teardown_timer(cpu);
+	if (common_cpu_die(cpu) == 0) {
+		xen_smp_intr_free(cpu);
+		xen_uninit_lock_cpu(cpu);
+		xen_teardown_timer(cpu);
+	}
 }
 
 static void xen_play_dead(void) /* used only with HOTPLUG_CPU */
@@ -735,6 +735,16 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus)
 static int xen_hvm_cpu_up(unsigned int cpu, struct task_struct *tidle)
 {
 	int rc;
+
+	/*
+	 * This can happen if CPU was offlined earlier and
+	 * offlining timed out in common_cpu_die().
+	 */
+	if (cpu_report_state(cpu) == CPU_DEAD_FROZEN) {
+		xen_smp_intr_free(cpu);
+		xen_uninit_lock_cpu(cpu);
+	}
+
 	/*
 	 * xen_smp_intr_init() needs to run before native_cpu_up()
 	 * so that IPI vectors are set up on the booting CPU before
@@ -756,12 +766,6 @@ static int xen_hvm_cpu_up(unsigned int cpu, struct task_struct *tidle)
 	return rc;
 }
 
-static void xen_hvm_cpu_die(unsigned int cpu)
-{
-	xen_cpu_die(cpu);
-	native_cpu_die(cpu);
-}
-
 void __init xen_hvm_smp_init(void)
 {
 	if (!xen_have_vector_callback)
@@ -769,7 +773,7 @@ void __init xen_hvm_smp_init(void)
 	smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus;
 	smp_ops.smp_send_reschedule = xen_smp_send_reschedule;
 	smp_ops.cpu_up = xen_hvm_cpu_up;
-	smp_ops.cpu_die = xen_hvm_cpu_die;
+	smp_ops.cpu_die = xen_cpu_die;
 	smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi;
 	smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi;
 	smp_ops.smp_prepare_boot_cpu = xen_smp_prepare_boot_cpu;

include/linux/cpu.h

@@ -73,6 +73,7 @@ enum {
 	/* migration should happen before other stuff but after perf */
 	CPU_PRI_PERF		= 20,
 	CPU_PRI_MIGRATION	= 10,
+	CPU_PRI_SMPBOOT		= 9,
 	/* bring up workqueues before normal notifiers and down after */
 	CPU_PRI_WORKQUEUE_UP	= 5,
 	CPU_PRI_WORKQUEUE_DOWN	= -5,
@@ -95,6 +96,10 @@ enum {
 					* Called on the new cpu, just before
 					* enabling interrupts. Must not sleep,
 					* must not fail */
+#define CPU_DYING_IDLE		0x000B /* CPU (unsigned)v dying, reached
+					* idle loop. */
+#define CPU_BROKEN		0x000C /* CPU (unsigned)v did not die properly,
+					* perhaps due to preemption. */
 
 /* Used for CPU hotplug events occurring while tasks are frozen due to a suspend
  * operation in progress
@@ -161,6 +166,7 @@ static inline void __unregister_cpu_notifier(struct notifier_block *nb)
 }
 #endif
 
+void smpboot_thread_init(void);
 int cpu_up(unsigned int cpu);
 void notify_cpu_starting(unsigned int cpu);
 extern void cpu_maps_update_begin(void);
@@ -208,6 +214,10 @@ static inline void cpu_notifier_register_done(void)
 {
 }
 
+static inline void smpboot_thread_init(void)
+{
+}
+
 #endif /* CONFIG_SMP */
 extern struct bus_type cpu_subsys;
 
@@ -271,4 +281,14 @@ void arch_cpu_idle_enter(void);
 void arch_cpu_idle_exit(void);
 void arch_cpu_idle_dead(void);
 
+DECLARE_PER_CPU(bool, cpu_dead_idle);
+
+int cpu_report_state(int cpu);
+int cpu_check_up_prepare(int cpu);
+void cpu_set_state_online(int cpu);
+#ifdef CONFIG_HOTPLUG_CPU
+bool cpu_wait_death(unsigned int cpu, int seconds);
+bool cpu_report_death(void);
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+
 #endif /* _LINUX_CPU_H_ */

include/linux/lockdep.h

@@ -531,8 +531,13 @@ do {									\
 # define might_lock_read(lock) do { } while (0)
 #endif
 
-#ifdef CONFIG_PROVE_RCU
+#ifdef CONFIG_LOCKDEP
 void lockdep_rcu_suspicious(const char *file, const int line, const char *s);
+#else
+static inline void
+lockdep_rcu_suspicious(const char *file, const int line, const char *s)
+{
+}
 #endif
 
 #endif /* __LINUX_LOCKDEP_H */

include/linux/rcupdate.h

@@ -48,6 +48,26 @@
 
 extern int rcu_expedited; /* for sysctl */
 
+#ifdef CONFIG_TINY_RCU
+/* Tiny RCU doesn't expedite, as its purpose in life is instead to be tiny. */
+static inline bool rcu_gp_is_expedited(void)  /* Internal RCU use. */
+{
+	return false;
+}
+
+static inline void rcu_expedite_gp(void)
+{
+}
+
+static inline void rcu_unexpedite_gp(void)
+{
+}
+#else /* #ifdef CONFIG_TINY_RCU */
+bool rcu_gp_is_expedited(void);  /* Internal RCU use. */
+void rcu_expedite_gp(void);
+void rcu_unexpedite_gp(void);
+#endif /* #else #ifdef CONFIG_TINY_RCU */
+
 enum rcutorture_type {
 	RCU_FLAVOR,
 	RCU_BH_FLAVOR,
@@ -195,6 +215,15 @@ void call_rcu_sched(struct rcu_head *head,
 
 void synchronize_sched(void);
 
+/*
+ * Structure allowing asynchronous waiting on RCU.
+ */
+struct rcu_synchronize {
+	struct rcu_head head;
+	struct completion completion;
+};
+void wakeme_after_rcu(struct rcu_head *head);
+
 /**
  * call_rcu_tasks() - Queue an RCU for invocation task-based grace period
  * @head: structure to be used for queueing the RCU updates.
@@ -258,6 +287,7 @@ static inline int rcu_preempt_depth(void)
 
 /* Internal to kernel */
 void rcu_init(void);
+void rcu_end_inkernel_boot(void);
 void rcu_sched_qs(void);
 void rcu_bh_qs(void);
 void rcu_check_callbacks(int user);
@@ -266,6 +296,8 @@ void rcu_idle_enter(void);
 void rcu_idle_exit(void);
 void rcu_irq_enter(void);
 void rcu_irq_exit(void);
+int rcu_cpu_notify(struct notifier_block *self,
+		   unsigned long action, void *hcpu);
 
 #ifdef CONFIG_RCU_STALL_COMMON
 void rcu_sysrq_start(void);
@@ -720,7 +752,7 @@ static inline void rcu_preempt_sleep_check(void)
  * annotated as __rcu.
  */
 #define rcu_dereference_check(p, c) \
-	__rcu_dereference_check((p), rcu_read_lock_held() || (c), __rcu)
+	__rcu_dereference_check((p), (c) || rcu_read_lock_held(), __rcu)
 
 /**
  * rcu_dereference_bh_check() - rcu_dereference_bh with debug checking
@@ -730,7 +762,7 @@ static inline void rcu_preempt_sleep_check(void)
  * This is the RCU-bh counterpart to rcu_dereference_check().
  */
 #define rcu_dereference_bh_check(p, c) \
-	__rcu_dereference_check((p), rcu_read_lock_bh_held() || (c), __rcu)
+	__rcu_dereference_check((p), (c) || rcu_read_lock_bh_held(), __rcu)
 
 /**
  * rcu_dereference_sched_check() - rcu_dereference_sched with debug checking
@@ -740,7 +772,7 @@ static inline void rcu_preempt_sleep_check(void)
  * This is the RCU-sched counterpart to rcu_dereference_check().
  */
 #define rcu_dereference_sched_check(p, c) \
-	__rcu_dereference_check((p), rcu_read_lock_sched_held() || (c), \
+	__rcu_dereference_check((p), (c) || rcu_read_lock_sched_held(), \
 				__rcu)
 
 #define rcu_dereference_raw(p) rcu_dereference_check(p, 1) /*@@@ needed? @@@*/
@@ -933,9 +965,9 @@ static inline void rcu_read_unlock(void)
 {
 	rcu_lockdep_assert(rcu_is_watching(),
 			   "rcu_read_unlock() used illegally while idle");
-	rcu_lock_release(&rcu_lock_map);
 	__release(RCU);
 	__rcu_read_unlock();
+	rcu_lock_release(&rcu_lock_map); /* Keep acq info for rls diags. */
 }
 
 /**

include/linux/srcu.h

@@ -182,7 +182,7 @@ static inline int srcu_read_lock_held(struct srcu_struct *sp)
  * lockdep_is_held() calls.
  */
 #define srcu_dereference_check(p, sp, c) \
-	__rcu_dereference_check((p), srcu_read_lock_held(sp) || (c), __rcu)
+	__rcu_dereference_check((p), (c) || srcu_read_lock_held(sp), __rcu)
 
 /**
  * srcu_dereference - fetch SRCU-protected pointer for later dereferencing

init/Kconfig

@@ -791,6 +791,19 @@ config RCU_NOCB_CPU_ALL
 
 endchoice
 
+config RCU_EXPEDITE_BOOT
+	bool
+	default n
+	help
+	  This option enables expedited grace periods at boot time,
+	  as if rcu_expedite_gp() had been invoked early in boot.
+	  The corresponding rcu_unexpedite_gp() is invoked from
+	  rcu_end_inkernel_boot(), which is intended to be invoked
+	  at the end of the kernel-only boot sequence, just before
+	  init is exec'ed.
+
+	  Accept the default if unsure.
+
 endmenu # "RCU Subsystem"
 
 config BUILD_BIN2C

init/main.c

@@ -384,6 +384,7 @@ static noinline void __init_refok rest_init(void)
 	int pid;
 
 	rcu_scheduler_starting();
+	smpboot_thread_init();
 	/*
 	 * We need to spawn init first so that it obtains pid 1, however
 	 * the init task will end up wanting to create kthreads, which, if

kernel/cpu.c

@@ -411,8 +411,10 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 	 *
 	 * Wait for the stop thread to go away.
 	 */
-	while (!idle_cpu(cpu))
+	while (!per_cpu(cpu_dead_idle, cpu))
 		cpu_relax();
+	smp_mb(); /* Read from cpu_dead_idle before __cpu_die(). */
+	per_cpu(cpu_dead_idle, cpu) = false;
 
 	hotplug_cpu__broadcast_tick_pull(cpu);
 	/* This actually kills the CPU. */
@@ -451,6 +453,37 @@ out:
 EXPORT_SYMBOL(cpu_down);
 #endif /*CONFIG_HOTPLUG_CPU*/
 
+/*
+ * Unpark per-CPU smpboot kthreads at CPU-online time.
+ */
+static int smpboot_thread_call(struct notifier_block *nfb,
+			       unsigned long action, void *hcpu)
+{
+	int cpu = (long)hcpu;
+
+	switch (action & ~CPU_TASKS_FROZEN) {
+
+	case CPU_ONLINE:
+		smpboot_unpark_threads(cpu);
+		break;
+
+	default:
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block smpboot_thread_notifier = {
+	.notifier_call = smpboot_thread_call,
+	.priority = CPU_PRI_SMPBOOT,
+};
+
+void __cpuinit smpboot_thread_init(void)
+{
+	register_cpu_notifier(&smpboot_thread_notifier);
+}
+
 /* Requires cpu_add_remove_lock to be held */
 static int _cpu_up(unsigned int cpu, int tasks_frozen)
 {
@@ -490,9 +523,6 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen)
 		goto out_notify;
 	BUG_ON(!cpu_online(cpu));
 
-	/* Wake the per cpu threads */
-	smpboot_unpark_threads(cpu);
-
 	/* Now call notifier in preparation. */
 	cpu_notify(CPU_ONLINE | mod, hcpu);
 

kernel/rcu/rcutorture.c

@@ -853,6 +853,8 @@ rcu_torture_fqs(void *arg)
 static int
 rcu_torture_writer(void *arg)
 {
+	bool can_expedite = !rcu_gp_is_expedited();
+	int expediting = 0;
 	unsigned long gp_snap;
 	bool gp_cond1 = gp_cond, gp_exp1 = gp_exp, gp_normal1 = gp_normal;
 	bool gp_sync1 = gp_sync;
@@ -865,9 +867,15 @@ rcu_torture_writer(void *arg)
 	int nsynctypes = 0;
 
 	VERBOSE_TOROUT_STRING("rcu_torture_writer task started");
+	pr_alert("%s" TORTURE_FLAG
+		 " Grace periods expedited from boot/sysfs for %s,\n",
+		 torture_type, cur_ops->name);
+	pr_alert("%s" TORTURE_FLAG
+		 " Testing of dynamic grace-period expediting diabled.\n",
+		 torture_type);
 
 	/* Initialize synctype[] array.  If none set, take default. */
-	if (!gp_cond1 && !gp_exp1 && !gp_normal1 && !gp_sync)
+	if (!gp_cond1 && !gp_exp1 && !gp_normal1 && !gp_sync1)
 		gp_cond1 = gp_exp1 = gp_normal1 = gp_sync1 = true;
 	if (gp_cond1 && cur_ops->get_state && cur_ops->cond_sync)
 		synctype[nsynctypes++] = RTWS_COND_GET;
@@ -949,9 +957,26 @@ rcu_torture_writer(void *arg)
 			}
 		}
 		rcutorture_record_progress(++rcu_torture_current_version);
+		/* Cycle through nesting levels of rcu_expedite_gp() calls. */
+		if (can_expedite &&
+		    !(torture_random(&rand) & 0xff & (!!expediting - 1))) {
+			WARN_ON_ONCE(expediting == 0 && rcu_gp_is_expedited());
+			if (expediting >= 0)
+				rcu_expedite_gp();
+			else
+				rcu_unexpedite_gp();
+			if (++expediting > 3)
+				expediting = -expediting;
+		}
 		rcu_torture_writer_state = RTWS_STUTTER;
 		stutter_wait("rcu_torture_writer");
 	} while (!torture_must_stop());
+	/* Reset expediting back to unexpedited. */
+	if (expediting > 0)
+		expediting = -expediting;
+	while (can_expedite && expediting++ < 0)
+		rcu_unexpedite_gp();
+	WARN_ON_ONCE(can_expedite && rcu_gp_is_expedited());
 	rcu_torture_writer_state = RTWS_STOPPING;
 	torture_kthread_stopping("rcu_torture_writer");
 	return 0;

kernel/rcu/srcu.c

@@ -402,23 +402,6 @@ void call_srcu(struct srcu_struct *sp, struct rcu_head *head,
 }
 EXPORT_SYMBOL_GPL(call_srcu);
 
-struct rcu_synchronize {
-	struct rcu_head head;
-	struct completion completion;
-};
-
-/*
- * Awaken the corresponding synchronize_srcu() instance now that a
- * grace period has elapsed.
- */
-static void wakeme_after_rcu(struct rcu_head *head)
-{
-	struct rcu_synchronize *rcu;
-
-	rcu = container_of(head, struct rcu_synchronize, head);
-	complete(&rcu->completion);
-}
-
 static void srcu_advance_batches(struct srcu_struct *sp, int trycount);
 static void srcu_reschedule(struct srcu_struct *sp);
 
@@ -507,7 +490,7 @@ static void __synchronize_srcu(struct srcu_struct *sp, int trycount)
  */
 void synchronize_srcu(struct srcu_struct *sp)
 {
-	__synchronize_srcu(sp, rcu_expedited
+	__synchronize_srcu(sp, rcu_gp_is_expedited()
 			   ? SYNCHRONIZE_SRCU_EXP_TRYCOUNT
 			   : SYNCHRONIZE_SRCU_TRYCOUNT);
 }

kernel/rcu/tiny.c

@@ -103,8 +103,7 @@ EXPORT_SYMBOL(__rcu_is_watching);
 static int rcu_qsctr_help(struct rcu_ctrlblk *rcp)
 {
 	RCU_TRACE(reset_cpu_stall_ticks(rcp));
-	if (rcp->rcucblist != NULL &&
-	    rcp->donetail != rcp->curtail) {
+	if (rcp->donetail != rcp->curtail) {
 		rcp->donetail = rcp->curtail;
 		return 1;
 	}
@@ -169,17 +168,6 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
 	unsigned long flags;
 	RCU_TRACE(int cb_count = 0);
 
-	/* If no RCU callbacks ready to invoke, just return. */
-	if (&rcp->rcucblist == rcp->donetail) {
-		RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, 0, -1));
-		RCU_TRACE(trace_rcu_batch_end(rcp->name, 0,
-					      !!ACCESS_ONCE(rcp->rcucblist),
-					      need_resched(),
-					      is_idle_task(current),
-					      false));
-		return;
-	}
-
 	/* Move the ready-to-invoke callbacks to a local list. */
 	local_irq_save(flags);
 	RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, rcp->qlen, -1));

kernel/rcu/tree.c

@@ -91,8 +91,10 @@ static const char *tp_##sname##_varname __used __tracepoint_string = sname##_var
 
 #define RCU_STATE_INITIALIZER(sname, sabbr, cr) \
 DEFINE_RCU_TPS(sname) \
+DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, sname##_data); \
 struct rcu_state sname##_state = { \
 	.level = { &sname##_state.node[0] }, \
+	.rda = &sname##_data, \
 	.call = cr, \
 	.fqs_state = RCU_GP_IDLE, \
 	.gpnum = 0UL - 300UL, \
@@ -101,11 +103,9 @@ struct rcu_state sname##_state = { \
 	.orphan_nxttail = &sname##_state.orphan_nxtlist, \
 	.orphan_donetail = &sname##_state.orphan_donelist, \
 	.barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \
-	.onoff_mutex = __MUTEX_INITIALIZER(sname##_state.onoff_mutex), \
 	.name = RCU_STATE_NAME(sname), \
 	.abbr = sabbr, \
-}; \
-DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, sname##_data)
+}
 
 RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched);
 RCU_STATE_INITIALIZER(rcu_bh, 'b', call_rcu_bh);
@@ -152,6 +152,8 @@ EXPORT_SYMBOL_GPL(rcu_scheduler_active);
  */
 static int rcu_scheduler_fully_active __read_mostly;
 
+static void rcu_init_new_rnp(struct rcu_node *rnp_leaf);
+static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf);
 static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu);
 static void invoke_rcu_core(void);
 static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp);
@@ -160,6 +162,12 @@ static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp);
 static int kthread_prio = CONFIG_RCU_KTHREAD_PRIO;
 module_param(kthread_prio, int, 0644);
 
+/* Delay in jiffies for grace-period initialization delays. */
+static int gp_init_delay = IS_ENABLED(CONFIG_RCU_TORTURE_TEST_SLOW_INIT)
+				? CONFIG_RCU_TORTURE_TEST_SLOW_INIT_DELAY
+				: 0;
+module_param(gp_init_delay, int, 0644);
+
 /*
  * Track the rcutorture test sequence number and the update version
  * number within a given test.  The rcutorture_testseq is incremented
@@ -172,6 +180,17 @@ module_param(kthread_prio, int, 0644);
 unsigned long rcutorture_testseq;
 unsigned long rcutorture_vernum;
 
+/*
+ * Compute the mask of online CPUs for the specified rcu_node structure.
+ * This will not be stable unless the rcu_node structure's ->lock is
+ * held, but the bit corresponding to the current CPU will be stable
+ * in most contexts.
+ */
+unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp)
+{
+	return ACCESS_ONCE(rnp->qsmaskinitnext);
+}
+
 /*
  * Return true if an RCU grace period is in progress.  The ACCESS_ONCE()s
  * permit this function to be invoked without holding the root rcu_node
@@ -292,10 +311,10 @@ void rcu_note_context_switch(void)
 EXPORT_SYMBOL_GPL(rcu_note_context_switch);
 
 /*
- * Register a quiesecent state for all RCU flavors.  If there is an
+ * Register a quiescent state for all RCU flavors.  If there is an
  * emergency, invoke rcu_momentary_dyntick_idle() to do a heavy-weight
  * dyntick-idle quiescent state visible to other CPUs (but only for those
- * RCU flavors in desparate need of a quiescent state, which will normally
+ * RCU flavors in desperate need of a quiescent state, which will normally
  * be none of them).  Either way, do a lightweight quiescent state for
  * all RCU flavors.
  */
@@ -409,6 +428,15 @@ void rcu_bh_force_quiescent_state(void)
 }
 EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state);
 
+/*
+ * Force a quiescent state for RCU-sched.
+ */
+void rcu_sched_force_quiescent_state(void)
+{
+	force_quiescent_state(&rcu_sched_state);
+}
+EXPORT_SYMBOL_GPL(rcu_sched_force_quiescent_state);
+
 /*
  * Show the state of the grace-period kthreads.
  */
@@ -482,15 +510,6 @@ void rcutorture_record_progress(unsigned long vernum)
 }
 EXPORT_SYMBOL_GPL(rcutorture_record_progress);
 
-/*
- * Force a quiescent state for RCU-sched.
- */
-void rcu_sched_force_quiescent_state(void)
-{
-	force_quiescent_state(&rcu_sched_state);
-}
-EXPORT_SYMBOL_GPL(rcu_sched_force_quiescent_state);
-
 /*
  * Does the CPU have callbacks ready to be invoked?
  */
@@ -954,7 +973,7 @@ bool rcu_lockdep_current_cpu_online(void)
 	preempt_disable();
 	rdp = this_cpu_ptr(&rcu_sched_data);
 	rnp = rdp->mynode;
-	ret = (rdp->grpmask & rnp->qsmaskinit) ||
+	ret = (rdp->grpmask & rcu_rnp_online_cpus(rnp)) ||
 	      !rcu_scheduler_fully_active;
 	preempt_enable();
 	return ret;
@@ -1196,9 +1215,10 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
 		} else {
 			j = jiffies;
 			gpa = ACCESS_ONCE(rsp->gp_activity);
-			pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld\n",
+			pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld, root ->qsmask %#lx\n",
 			       rsp->name, j - gpa, j, gpa,
-			       jiffies_till_next_fqs);
+			       jiffies_till_next_fqs,
+			       rcu_get_root(rsp)->qsmask);
 			/* In this case, the current CPU might be at fault. */
 			sched_show_task(current);
 		}
@@ -1328,19 +1348,29 @@ void rcu_cpu_stall_reset(void)
 }
 
 /*
- * Initialize the specified rcu_data structure's callback list to empty.
+ * Initialize the specified rcu_data structure's default callback list
+ * to empty.  The default callback list is the one that is not used by
+ * no-callbacks CPUs.
  */
-static void init_callback_list(struct rcu_data *rdp)
+static void init_default_callback_list(struct rcu_data *rdp)
 {
 	int i;
 
-	if (init_nocb_callback_list(rdp))
-		return;
 	rdp->nxtlist = NULL;
 	for (i = 0; i < RCU_NEXT_SIZE; i++)
 		rdp->nxttail[i] = &rdp->nxtlist;
 }
 
+/*
+ * Initialize the specified rcu_data structure's callback list to empty.
+ */
+static void init_callback_list(struct rcu_data *rdp)
+{
+	if (init_nocb_callback_list(rdp))
+		return;
+	init_default_callback_list(rdp);
+}
+
 /*
  * Determine the value that ->completed will have at the end of the
  * next subsequent grace period.  This is used to tag callbacks so that
@@ -1703,11 +1733,11 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
  */
 static int rcu_gp_init(struct rcu_state *rsp)
 {
+	unsigned long oldmask;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
 	ACCESS_ONCE(rsp->gp_activity) = jiffies;
-	rcu_bind_gp_kthread();
 	raw_spin_lock_irq(&rnp->lock);
 	smp_mb__after_unlock_lock();
 	if (!ACCESS_ONCE(rsp->gp_flags)) {
@@ -1733,9 +1763,54 @@ static int rcu_gp_init(struct rcu_state *rsp)
 	trace_rcu_grace_period(rsp->name, rsp->gpnum, TPS("start"));
 	raw_spin_unlock_irq(&rnp->lock);
 
-	/* Exclude any concurrent CPU-hotplug operations. */
-	mutex_lock(&rsp->onoff_mutex);
-	smp_mb__after_unlock_lock(); /* ->gpnum increment before GP! */
+	/*
+	 * Apply per-leaf buffered online and offline operations to the
+	 * rcu_node tree.  Note that this new grace period need not wait
+	 * for subsequent online CPUs, and that quiescent-state forcing
+	 * will handle subsequent offline CPUs.
+	 */
+	rcu_for_each_leaf_node(rsp, rnp) {
+		raw_spin_lock_irq(&rnp->lock);
+		smp_mb__after_unlock_lock();
+		if (rnp->qsmaskinit == rnp->qsmaskinitnext &&
+		    !rnp->wait_blkd_tasks) {
+			/* Nothing to do on this leaf rcu_node structure. */
+			raw_spin_unlock_irq(&rnp->lock);
+			continue;
+		}
+
+		/* Record old state, apply changes to ->qsmaskinit field. */
+		oldmask = rnp->qsmaskinit;
+		rnp->qsmaskinit = rnp->qsmaskinitnext;
+
+		/* If zero-ness of ->qsmaskinit changed, propagate up tree. */
+		if (!oldmask != !rnp->qsmaskinit) {
+			if (!oldmask) /* First online CPU for this rcu_node. */
+				rcu_init_new_rnp(rnp);
+			else if (rcu_preempt_has_tasks(rnp)) /* blocked tasks */
+				rnp->wait_blkd_tasks = true;
+			else /* Last offline CPU and can propagate. */
+				rcu_cleanup_dead_rnp(rnp);
+		}
+
+		/*
+		 * If all waited-on tasks from prior grace period are
+		 * done, and if all this rcu_node structure's CPUs are
+		 * still offline, propagate up the rcu_node tree and
+		 * clear ->wait_blkd_tasks.  Otherwise, if one of this
+		 * rcu_node structure's CPUs has since come back online,
+		 * simply clear ->wait_blkd_tasks (but rcu_cleanup_dead_rnp()
+		 * checks for this, so just call it unconditionally).
+		 */
+		if (rnp->wait_blkd_tasks &&
+		    (!rcu_preempt_has_tasks(rnp) ||
+		     rnp->qsmaskinit)) {
+			rnp->wait_blkd_tasks = false;
+			rcu_cleanup_dead_rnp(rnp);
+		}
+
+		raw_spin_unlock_irq(&rnp->lock);
+	}
 
 	/*
 	 * Set the quiescent-state-needed bits in all the rcu_node
@@ -1757,8 +1832,8 @@ static int rcu_gp_init(struct rcu_state *rsp)
 		rcu_preempt_check_blocked_tasks(rnp);
 		rnp->qsmask = rnp->qsmaskinit;
 		ACCESS_ONCE(rnp->gpnum) = rsp->gpnum;
-		WARN_ON_ONCE(rnp->completed != rsp->completed);
-		ACCESS_ONCE(rnp->completed) = rsp->completed;
+		if (WARN_ON_ONCE(rnp->completed != rsp->completed))
+			ACCESS_ONCE(rnp->completed) = rsp->completed;
 		if (rnp == rdp->mynode)
 			(void)__note_gp_changes(rsp, rnp, rdp);
 		rcu_preempt_boost_start_gp(rnp);
@@ -1768,9 +1843,12 @@ static int rcu_gp_init(struct rcu_state *rsp)
 		raw_spin_unlock_irq(&rnp->lock);
 		cond_resched_rcu_qs();
 		ACCESS_ONCE(rsp->gp_activity) = jiffies;
+		if (IS_ENABLED(CONFIG_RCU_TORTURE_TEST_SLOW_INIT) &&
+		    gp_init_delay > 0 &&
+		    !(rsp->gpnum % (rcu_num_nodes * 10)))
+			schedule_timeout_uninterruptible(gp_init_delay);
 	}
 
-	mutex_unlock(&rsp->onoff_mutex);
 	return 1;
 }
 
@@ -1798,7 +1876,7 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
 		fqs_state = RCU_FORCE_QS;
 	} else {
 		/* Handle dyntick-idle and offline CPUs. */
-		isidle = false;
+		isidle = true;
 		force_qs_rnp(rsp, rcu_implicit_dynticks_qs, &isidle, &maxj);
 	}
 	/* Clear flag to prevent immediate re-entry. */
@@ -1852,6 +1930,8 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	rcu_for_each_node_breadth_first(rsp, rnp) {
 		raw_spin_lock_irq(&rnp->lock);
 		smp_mb__after_unlock_lock();
+		WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp));
+		WARN_ON_ONCE(rnp->qsmask);
 		ACCESS_ONCE(rnp->completed) = rsp->gpnum;
 		rdp = this_cpu_ptr(rsp->rda);
 		if (rnp == rdp->mynode)
@@ -1895,6 +1975,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
 	struct rcu_state *rsp = arg;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
+	rcu_bind_gp_kthread();
 	for (;;) {
 
 		/* Handle grace-period start. */
@@ -2062,25 +2143,32 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
  * Similar to rcu_report_qs_rdp(), for which it is a helper function.
  * Allows quiescent states for a group of CPUs to be reported at one go
  * to the specified rcu_node structure, though all the CPUs in the group
- * must be represented by the same rcu_node structure (which need not be
- * a leaf rcu_node structure, though it often will be).  That structure's
- * lock must be held upon entry, and it is released before return.
+ * must be represented by the same rcu_node structure (which need not be a
+ * leaf rcu_node structure, though it often will be).  The gps parameter
+ * is the grace-period snapshot, which means that the quiescent states
+ * are valid only if rnp->gpnum is equal to gps.  That structure's lock
+ * must be held upon entry, and it is released before return.
  */
 static void
 rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
-		  struct rcu_node *rnp, unsigned long flags)
+		  struct rcu_node *rnp, unsigned long gps, unsigned long flags)
 	__releases(rnp->lock)
 {
+	unsigned long oldmask = 0;
 	struct rcu_node *rnp_c;
 
 	/* Walk up the rcu_node hierarchy. */
 	for (;;) {
-		if (!(rnp->qsmask & mask)) {
+		if (!(rnp->qsmask & mask) || rnp->gpnum != gps) {
 
-			/* Our bit has already been cleared, so done. */
+			/*
+			 * Our bit has already been cleared, or the
+			 * relevant grace period is already over, so done.
+			 */
 			raw_spin_unlock_irqrestore(&rnp->lock, flags);
 			return;
 		}
+		WARN_ON_ONCE(oldmask); /* Any child must be all zeroed! */
 		rnp->qsmask &= ~mask;
 		trace_rcu_quiescent_state_report(rsp->name, rnp->gpnum,
 						 mask, rnp->qsmask, rnp->level,
@@ -2104,7 +2192,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 		rnp = rnp->parent;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
 		smp_mb__after_unlock_lock();
-		WARN_ON_ONCE(rnp_c->qsmask);
+		oldmask = rnp_c->qsmask;
 	}
 
 	/*
@@ -2115,6 +2203,46 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 	rcu_report_qs_rsp(rsp, flags); /* releases rnp->lock. */
 }
 
+/*
+ * Record a quiescent state for all tasks that were previously queued
+ * on the specified rcu_node structure and that were blocking the current
+ * RCU grace period.  The caller must hold the specified rnp->lock with
+ * irqs disabled, and this lock is released upon return, but irqs remain
+ * disabled.
+ */
+static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp,
+				      struct rcu_node *rnp, unsigned long flags)
+	__releases(rnp->lock)
+{
+	unsigned long gps;
+	unsigned long mask;
+	struct rcu_node *rnp_p;
+
+	if (rcu_state_p == &rcu_sched_state || rsp != rcu_state_p ||
+	    rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) {
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		return;  /* Still need more quiescent states! */
+	}
+
+	rnp_p = rnp->parent;
+	if (rnp_p == NULL) {
+		/*
+		 * Only one rcu_node structure in the tree, so don't
+		 * try to report up to its nonexistent parent!
+		 */
+		rcu_report_qs_rsp(rsp, flags);
+		return;
+	}
+
+	/* Report up the rest of the hierarchy, tracking current ->gpnum. */
+	gps = rnp->gpnum;
+	mask = rnp->grpmask;
+	raw_spin_unlock(&rnp->lock);	/* irqs remain disabled. */
+	raw_spin_lock(&rnp_p->lock);	/* irqs already disabled. */
+	smp_mb__after_unlock_lock();
+	rcu_report_qs_rnp(mask, rsp, rnp_p, gps, flags);
+}
+
 /*
  * Record a quiescent state for the specified CPU to that CPU's rcu_data
  * structure.  This must be either called from the specified CPU, or
@@ -2163,7 +2291,8 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
 		 */
 		needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
 
-		rcu_report_qs_rnp(mask, rsp, rnp, flags); /* rlses rnp->lock */
+		rcu_report_qs_rnp(mask, rsp, rnp, rnp->gpnum, flags);
+		/* ^^^ Released rnp->lock */
 		if (needwake)
 			rcu_gp_kthread_wake(rsp);
 	}
@@ -2256,8 +2385,12 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp,
 		rsp->orphan_donetail = rdp->nxttail[RCU_DONE_TAIL];
 	}
 
-	/* Finally, initialize the rcu_data structure's list to empty.  */
+	/*
+	 * Finally, initialize the rcu_data structure's list to empty and
+	 * disallow further callbacks on this CPU.
+	 */
 	init_callback_list(rdp);
+	rdp->nxttail[RCU_NEXT_TAIL] = NULL;
 }
 
 /*
@@ -2355,6 +2488,7 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
 		raw_spin_lock(&rnp->lock); /* irqs already disabled. */
 		smp_mb__after_unlock_lock(); /* GP memory ordering. */
 		rnp->qsmaskinit &= ~mask;
+		rnp->qsmask &= ~mask;
 		if (rnp->qsmaskinit) {
 			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
 			return;
@@ -2363,6 +2497,26 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
 	}
 }
 
+/*
+ * The CPU is exiting the idle loop into the arch_cpu_idle_dead()
+ * function.  We now remove it from the rcu_node tree's ->qsmaskinit
+ * bit masks.
+ */
+static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
+{
+	unsigned long flags;
+	unsigned long mask;
+	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
+	struct rcu_node *rnp = rdp->mynode;  /* Outgoing CPU's rdp & rnp. */
+
+	/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
+	mask = rdp->grpmask;
+	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();	/* Enforce GP memory-order guarantee. */
+	rnp->qsmaskinitnext &= ~mask;
+	raw_spin_unlock_irqrestore(&rnp->lock, flags);
+}
+
 /*
  * The CPU has been completely removed, and some other CPU is reporting
  * this fact from process context.  Do the remainder of the cleanup,
@@ -2379,29 +2533,15 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
 	/* Adjust any no-longer-needed kthreads. */
 	rcu_boost_kthread_setaffinity(rnp, -1);
 
-	/* Exclude any attempts to start a new grace period. */
-	mutex_lock(&rsp->onoff_mutex);
-	raw_spin_lock_irqsave(&rsp->orphan_lock, flags);
-
 	/* Orphan the dead CPU's callbacks, and adopt them if appropriate. */
+	raw_spin_lock_irqsave(&rsp->orphan_lock, flags);
 	rcu_send_cbs_to_orphanage(cpu, rsp, rnp, rdp);
 	rcu_adopt_orphan_cbs(rsp, flags);
 	raw_spin_unlock_irqrestore(&rsp->orphan_lock, flags);
 
-	/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	smp_mb__after_unlock_lock();	/* Enforce GP memory-order guarantee. */
-	rnp->qsmaskinit &= ~rdp->grpmask;
-	if (rnp->qsmaskinit == 0 && !rcu_preempt_has_tasks(rnp))
-		rcu_cleanup_dead_rnp(rnp);
-	rcu_report_qs_rnp(rdp->grpmask, rsp, rnp, flags); /* Rlses rnp->lock. */
 	WARN_ONCE(rdp->qlen != 0 || rdp->nxtlist != NULL,
 		  "rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, nxtlist=%p\n",
 		  cpu, rdp->qlen, rdp->nxtlist);
-	init_callback_list(rdp);
-	/* Disallow further callbacks on this CPU. */
-	rdp->nxttail[RCU_NEXT_TAIL] = NULL;
-	mutex_unlock(&rsp->onoff_mutex);
 }
 
 #else /* #ifdef CONFIG_HOTPLUG_CPU */
@@ -2414,6 +2554,10 @@ static void __maybe_unused rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
 {
 }
 
+static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
+{
+}
+
 static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
 {
 }
@@ -2589,26 +2733,47 @@ static void force_qs_rnp(struct rcu_state *rsp,
 			return;
 		}
 		if (rnp->qsmask == 0) {
-			rcu_initiate_boost(rnp, flags); /* releases rnp->lock */
-			continue;
+			if (rcu_state_p == &rcu_sched_state ||
+			    rsp != rcu_state_p ||
+			    rcu_preempt_blocked_readers_cgp(rnp)) {
+				/*
+				 * No point in scanning bits because they
+				 * are all zero.  But we might need to
+				 * priority-boost blocked readers.
+				 */
+				rcu_initiate_boost(rnp, flags);
+				/* rcu_initiate_boost() releases rnp->lock */
+				continue;
+			}
+			if (rnp->parent &&
+			    (rnp->parent->qsmask & rnp->grpmask)) {
+				/*
+				 * Race between grace-period
+				 * initialization and task exiting RCU
+				 * read-side critical section: Report.
+				 */
+				rcu_report_unblock_qs_rnp(rsp, rnp, flags);
+				/* rcu_report_unblock_qs_rnp() rlses ->lock */
+				continue;
+			}
 		}
 		cpu = rnp->grplo;
 		bit = 1;
 		for (; cpu <= rnp->grphi; cpu++, bit <<= 1) {
 			if ((rnp->qsmask & bit) != 0) {
-				if ((rnp->qsmaskinit & bit) != 0)
-					*isidle = false;
+				if ((rnp->qsmaskinit & bit) == 0)
+					*isidle = false; /* Pending hotplug. */
 				if (f(per_cpu_ptr(rsp->rda, cpu), isidle, maxj))
 					mask |= bit;
 			}
 		}
 		if (mask != 0) {
-
-			/* rcu_report_qs_rnp() releases rnp->lock. */
-			rcu_report_qs_rnp(mask, rsp, rnp, flags);
-			continue;
+			/* Idle/offline CPUs, report (releases rnp->lock. */
+			rcu_report_qs_rnp(mask, rsp, rnp, rnp->gpnum, flags);
+		} else {
+			/* Nothing to do here, so just drop the lock. */
+			raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		}
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	}
 }
 
@@ -2741,7 +2906,7 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
 	 * If called from an extended quiescent state, invoke the RCU
 	 * core in order to force a re-evaluation of RCU's idleness.
 	 */
-	if (!rcu_is_watching() && cpu_online(smp_processor_id()))
+	if (!rcu_is_watching())
 		invoke_rcu_core();
 
 	/* If interrupts were disabled or CPU offline, don't invoke RCU core. */
@@ -2827,11 +2992,22 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 
 		if (cpu != -1)
 			rdp = per_cpu_ptr(rsp->rda, cpu);
-		offline = !__call_rcu_nocb(rdp, head, lazy, flags);
-		WARN_ON_ONCE(offline);
-		/* _call_rcu() is illegal on offline CPU; leak the callback. */
-		local_irq_restore(flags);
-		return;
+		if (likely(rdp->mynode)) {
+			/* Post-boot, so this should be for a no-CBs CPU. */
+			offline = !__call_rcu_nocb(rdp, head, lazy, flags);
+			WARN_ON_ONCE(offline);
+			/* Offline CPU, _call_rcu() illegal, leak callback.  */
+			local_irq_restore(flags);
+			return;
+		}
+		/*
+		 * Very early boot, before rcu_init().  Initialize if needed
+		 * and then drop through to queue the callback.
+		 */
+		BUG_ON(cpu != -1);
+		WARN_ON_ONCE(!rcu_is_watching());
+		if (!likely(rdp->nxtlist))
+			init_default_callback_list(rdp);
 	}
 	ACCESS_ONCE(rdp->qlen) = rdp->qlen + 1;
 	if (lazy)
@@ -2954,7 +3130,7 @@ void synchronize_sched(void)
 			   "Illegal synchronize_sched() in RCU-sched read-side critical section");
 	if (rcu_blocking_is_gp())
 		return;
-	if (rcu_expedited)
+	if (rcu_gp_is_expedited())
 		synchronize_sched_expedited();
 	else
 		wait_rcu_gp(call_rcu_sched);
@@ -2981,7 +3157,7 @@ void synchronize_rcu_bh(void)
 			   "Illegal synchronize_rcu_bh() in RCU-bh read-side critical section");
 	if (rcu_blocking_is_gp())
 		return;
-	if (rcu_expedited)
+	if (rcu_gp_is_expedited())
 		synchronize_rcu_bh_expedited();
 	else
 		wait_rcu_gp(call_rcu_bh);
@@ -3517,6 +3693,28 @@ void rcu_barrier_sched(void)
 }
 EXPORT_SYMBOL_GPL(rcu_barrier_sched);
 
+/*
+ * Propagate ->qsinitmask bits up the rcu_node tree to account for the
+ * first CPU in a given leaf rcu_node structure coming online.  The caller
+ * must hold the corresponding leaf rcu_node ->lock with interrrupts
+ * disabled.
+ */
+static void rcu_init_new_rnp(struct rcu_node *rnp_leaf)
+{
+	long mask;
+	struct rcu_node *rnp = rnp_leaf;
+
+	for (;;) {
+		mask = rnp->grpmask;
+		rnp = rnp->parent;
+		if (rnp == NULL)
+			return;
+		raw_spin_lock(&rnp->lock); /* Interrupts already disabled. */
+		rnp->qsmaskinit |= mask;
+		raw_spin_unlock(&rnp->lock); /* Interrupts remain disabled. */
+	}
+}
+
 /*
  * Do boot-time initialization of a CPU's per-CPU RCU data.
  */
@@ -3553,49 +3751,37 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
-	/* Exclude new grace periods. */
-	mutex_lock(&rsp->onoff_mutex);
-
 	/* Set up local state, ensuring consistent view of global state. */
 	raw_spin_lock_irqsave(&rnp->lock, flags);
 	rdp->beenonline = 1;	 /* We have now been online. */
 	rdp->qlen_last_fqs_check = 0;
 	rdp->n_force_qs_snap = rsp->n_force_qs;
 	rdp->blimit = blimit;
-	init_callback_list(rdp);  /* Re-enable callbacks on this CPU. */
+	if (!rdp->nxtlist)
+		init_callback_list(rdp);  /* Re-enable callbacks on this CPU. */
 	rdp->dynticks->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
 	rcu_sysidle_init_percpu_data(rdp->dynticks);
 	atomic_set(&rdp->dynticks->dynticks,
 		   (atomic_read(&rdp->dynticks->dynticks) & ~0x1) + 1);
 	raw_spin_unlock(&rnp->lock);		/* irqs remain disabled. */
 
-	/* Add CPU to rcu_node bitmasks. */
+	/*
+	 * Add CPU to leaf rcu_node pending-online bitmask.  Any needed
+	 * propagation up the rcu_node tree will happen at the beginning
+	 * of the next grace period.
+	 */
 	rnp = rdp->mynode;
 	mask = rdp->grpmask;
-	do {
-		/* Exclude any attempts to start a new GP on small systems. */
-		raw_spin_lock(&rnp->lock);	/* irqs already disabled. */
-		rnp->qsmaskinit |= mask;
-		mask = rnp->grpmask;
-		if (rnp == rdp->mynode) {
-			/*
-			 * If there is a grace period in progress, we will
-			 * set up to wait for it next time we run the
-			 * RCU core code.
-			 */
-			rdp->gpnum = rnp->completed;
-			rdp->completed = rnp->completed;
-			rdp->passed_quiesce = 0;
-			rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
-			rdp->qs_pending = 0;
-			trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl"));
-		}
-		raw_spin_unlock(&rnp->lock); /* irqs already disabled. */
-		rnp = rnp->parent;
-	} while (rnp != NULL && !(rnp->qsmaskinit & mask));
-	local_irq_restore(flags);
-
-	mutex_unlock(&rsp->onoff_mutex);
+	raw_spin_lock(&rnp->lock);		/* irqs already disabled. */
+	smp_mb__after_unlock_lock();
+	rnp->qsmaskinitnext |= mask;
+	rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */
+	rdp->completed = rnp->completed;
+	rdp->passed_quiesce = false;
+	rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
+	rdp->qs_pending = false;
+	trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl"));
+	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 }
 
 static void rcu_prepare_cpu(int cpu)
@@ -3609,15 +3795,14 @@ static void rcu_prepare_cpu(int cpu)
 /*
  * Handle CPU online/offline notification events.
  */
-static int rcu_cpu_notify(struct notifier_block *self,
-				    unsigned long action, void *hcpu)
+int rcu_cpu_notify(struct notifier_block *self,
+		   unsigned long action, void *hcpu)
 {
 	long cpu = (long)hcpu;
 	struct rcu_data *rdp = per_cpu_ptr(rcu_state_p->rda, cpu);
 	struct rcu_node *rnp = rdp->mynode;
 	struct rcu_state *rsp;
 
-	trace_rcu_utilization(TPS("Start CPU hotplug"));
 	switch (action) {
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
@@ -3637,6 +3822,11 @@ static int rcu_cpu_notify(struct notifier_block *self,
 		for_each_rcu_flavor(rsp)
 			rcu_cleanup_dying_cpu(rsp);
 		break;
+	case CPU_DYING_IDLE:
+		for_each_rcu_flavor(rsp) {
+			rcu_cleanup_dying_idle_cpu(cpu, rsp);
+		}
+		break;
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
 	case CPU_UP_CANCELED:
@@ -3649,7 +3839,6 @@ static int rcu_cpu_notify(struct notifier_block *self,
 	default:
 		break;
 	}
-	trace_rcu_utilization(TPS("End CPU hotplug"));
 	return NOTIFY_OK;
 }
 
@@ -3660,11 +3849,12 @@ static int rcu_pm_notify(struct notifier_block *self,
 	case PM_HIBERNATION_PREPARE:
 	case PM_SUSPEND_PREPARE:
 		if (nr_cpu_ids <= 256) /* Expediting bad for large systems. */
-			rcu_expedited = 1;
+			rcu_expedite_gp();
 		break;
 	case PM_POST_HIBERNATION:
 	case PM_POST_SUSPEND:
-		rcu_expedited = 0;
+		if (nr_cpu_ids <= 256) /* Expediting bad for large systems. */
+			rcu_unexpedite_gp();
 		break;
 	default:
 		break;
@@ -3734,30 +3924,26 @@ void rcu_scheduler_starting(void)
  * Compute the per-level fanout, either using the exact fanout specified
  * or balancing the tree, depending on CONFIG_RCU_FANOUT_EXACT.
  */
-#ifdef CONFIG_RCU_FANOUT_EXACT
-static void __init rcu_init_levelspread(struct rcu_state *rsp)
-{
-	int i;
-
-	rsp->levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf;
-	for (i = rcu_num_lvls - 2; i >= 0; i--)
-		rsp->levelspread[i] = CONFIG_RCU_FANOUT;
-}
-#else /* #ifdef CONFIG_RCU_FANOUT_EXACT */
 static void __init rcu_init_levelspread(struct rcu_state *rsp)
 {
-	int ccur;
-	int cprv;
 	int i;
 
-	cprv = nr_cpu_ids;
-	for (i = rcu_num_lvls - 1; i >= 0; i--) {
-		ccur = rsp->levelcnt[i];
-		rsp->levelspread[i] = (cprv + ccur - 1) / ccur;
-		cprv = ccur;
+	if (IS_ENABLED(CONFIG_RCU_FANOUT_EXACT)) {
+		rsp->levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf;
+		for (i = rcu_num_lvls - 2; i >= 0; i--)
+			rsp->levelspread[i] = CONFIG_RCU_FANOUT;
+	} else {
+		int ccur;
+		int cprv;
+
+		cprv = nr_cpu_ids;
+		for (i = rcu_num_lvls - 1; i >= 0; i--) {
+			ccur = rsp->levelcnt[i];
+			rsp->levelspread[i] = (cprv + ccur - 1) / ccur;
+			cprv = ccur;
+		}
 	}
 }
-#endif /* #else #ifdef CONFIG_RCU_FANOUT_EXACT */
 
 /*
  * Helper function for rcu_init() that initializes one rcu_state structure.
@@ -3833,7 +4019,6 @@ static void __init rcu_init_one(struct rcu_state *rsp,
 		}
 	}
 
-	rsp->rda = rda;
 	init_waitqueue_head(&rsp->gp_wq);
 	rnp = rsp->level[rcu_num_lvls - 1];
 	for_each_possible_cpu(i) {
@@ -3926,6 +4111,8 @@ void __init rcu_init(void)
 {
 	int cpu;
 
+	rcu_early_boot_tests();
+
 	rcu_bootup_announce();
 	rcu_init_geometry();
 	rcu_init_one(&rcu_bh_state, &rcu_bh_data);
@@ -3942,8 +4129,6 @@ void __init rcu_init(void)
 	pm_notifier(rcu_pm_notify, 0);
 	for_each_online_cpu(cpu)
 		rcu_cpu_notify(NULL, CPU_UP_PREPARE, (void *)(long)cpu);
-
-	rcu_early_boot_tests();
 }
 
 #include "tree_plugin.h"

kernel/rcu/tree.h

@@ -141,12 +141,20 @@ struct rcu_node {
 				/*  complete (only for PREEMPT_RCU). */
 	unsigned long qsmaskinit;
 				/* Per-GP initial value for qsmask & expmask. */
+				/*  Initialized from ->qsmaskinitnext at the */
+				/*  beginning of each grace period. */
+	unsigned long qsmaskinitnext;
+				/* Online CPUs for next grace period. */
 	unsigned long grpmask;	/* Mask to apply to parent qsmask. */
 				/*  Only one bit will be set in this mask. */
 	int	grplo;		/* lowest-numbered CPU or group here. */
 	int	grphi;		/* highest-numbered CPU or group here. */
 	u8	grpnum;		/* CPU/group number for next level up. */
 	u8	level;		/* root is at level 0. */
+	bool	wait_blkd_tasks;/* Necessary to wait for blocked tasks to */
+				/*  exit RCU read-side critical sections */
+				/*  before propagating offline up the */
+				/*  rcu_node tree? */
 	struct rcu_node *parent;
 	struct list_head blkd_tasks;
 				/* Tasks blocked in RCU read-side critical */
@@ -448,8 +456,6 @@ struct rcu_state {
 	long qlen;				/* Total number of callbacks. */
 	/* End of fields guarded by orphan_lock. */
 
-	struct mutex onoff_mutex;		/* Coordinate hotplug & GPs. */
-
 	struct mutex barrier_mutex;		/* Guards barrier fields. */
 	atomic_t barrier_cpu_count;		/* # CPUs waiting on. */
 	struct completion barrier_completion;	/* Wake at barrier end. */
@@ -559,6 +565,7 @@ static void rcu_prepare_kthreads(int cpu);
 static void rcu_cleanup_after_idle(void);
 static void rcu_prepare_for_idle(void);
 static void rcu_idle_count_callbacks_posted(void);
+static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
 static void print_cpu_stall_info_begin(void);
 static void print_cpu_stall_info(struct rcu_state *rsp, int cpu);
 static void print_cpu_stall_info_end(void);

kernel/rcu/tree_plugin.h

@@ -58,38 +58,33 @@ static bool __read_mostly rcu_nocb_poll;    /* Offload kthread are to poll. */
  */
 static void __init rcu_bootup_announce_oddness(void)
 {
-#ifdef CONFIG_RCU_TRACE
-	pr_info("\tRCU debugfs-based tracing is enabled.\n");
-#endif
-#if (defined(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 64) || (!defined(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 32)
-	pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d\n",
-	       CONFIG_RCU_FANOUT);
-#endif
-#ifdef CONFIG_RCU_FANOUT_EXACT
-	pr_info("\tHierarchical RCU autobalancing is disabled.\n");
-#endif
-#ifdef CONFIG_RCU_FAST_NO_HZ
-	pr_info("\tRCU dyntick-idle grace-period acceleration is enabled.\n");
-#endif
-#ifdef CONFIG_PROVE_RCU
-	pr_info("\tRCU lockdep checking is enabled.\n");
-#endif
-#ifdef CONFIG_RCU_TORTURE_TEST_RUNNABLE
-	pr_info("\tRCU torture testing starts during boot.\n");
-#endif
-#if defined(CONFIG_RCU_CPU_STALL_INFO)
-	pr_info("\tAdditional per-CPU info printed with stalls.\n");
-#endif
-#if NUM_RCU_LVL_4 != 0
-	pr_info("\tFour-level hierarchy is enabled.\n");
-#endif
+	if (IS_ENABLED(CONFIG_RCU_TRACE))
+		pr_info("\tRCU debugfs-based tracing is enabled.\n");
+	if ((IS_ENABLED(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 64) ||
+	    (!IS_ENABLED(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 32))
+		pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d\n",
+		       CONFIG_RCU_FANOUT);
+	if (IS_ENABLED(CONFIG_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_TORTURE_TEST_RUNNABLE))
+		pr_info("\tRCU torture testing starts during boot.\n");
+	if (IS_ENABLED(CONFIG_RCU_CPU_STALL_INFO))
+		pr_info("\tAdditional per-CPU info printed with stalls.\n");
+	if (NUM_RCU_LVL_4 != 0)
+		pr_info("\tFour-level hierarchy is enabled.\n");
+	if (CONFIG_RCU_FANOUT_LEAF != 16)
+		pr_info("\tBuild-time adjustment of leaf fanout to %d.\n",
+			CONFIG_RCU_FANOUT_LEAF);
 	if (rcu_fanout_leaf != CONFIG_RCU_FANOUT_LEAF)
 		pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf);
 	if (nr_cpu_ids != NR_CPUS)
 		pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids);
-#ifdef CONFIG_RCU_BOOST
-	pr_info("\tRCU kthread priority: %d.\n", kthread_prio);
-#endif
+	if (IS_ENABLED(CONFIG_RCU_BOOST))
+		pr_info("\tRCU kthread priority: %d.\n", kthread_prio);
 }
 
 #ifdef CONFIG_PREEMPT_RCU
@@ -180,7 +175,7 @@ static void rcu_preempt_note_context_switch(void)
 		 * But first, note that the current CPU must still be
 		 * on line!
 		 */
-		WARN_ON_ONCE((rdp->grpmask & rnp->qsmaskinit) == 0);
+		WARN_ON_ONCE((rdp->grpmask & rcu_rnp_online_cpus(rnp)) == 0);
 		WARN_ON_ONCE(!list_empty(&t->rcu_node_entry));
 		if ((rnp->qsmask & rdp->grpmask) && rnp->gp_tasks != NULL) {
 			list_add(&t->rcu_node_entry, rnp->gp_tasks->prev);
@@ -232,43 +227,6 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp)
 	return rnp->gp_tasks != NULL;
 }
 
-/*
- * Record a quiescent state for all tasks that were previously queued
- * on the specified rcu_node structure and that were blocking the current
- * RCU grace period.  The caller must hold the specified rnp->lock with
- * irqs disabled, and this lock is released upon return, but irqs remain
- * disabled.
- */
-static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
-	__releases(rnp->lock)
-{
-	unsigned long mask;
-	struct rcu_node *rnp_p;
-
-	if (rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) {
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
-		return;  /* Still need more quiescent states! */
-	}
-
-	rnp_p = rnp->parent;
-	if (rnp_p == NULL) {
-		/*
-		 * Either there is only one rcu_node in the tree,
-		 * or tasks were kicked up to root rcu_node due to
-		 * CPUs going offline.
-		 */
-		rcu_report_qs_rsp(&rcu_preempt_state, flags);
-		return;
-	}
-
-	/* Report up the rest of the hierarchy. */
-	mask = rnp->grpmask;
-	raw_spin_unlock(&rnp->lock);	/* irqs remain disabled. */
-	raw_spin_lock(&rnp_p->lock);	/* irqs already disabled. */
-	smp_mb__after_unlock_lock();
-	rcu_report_qs_rnp(mask, &rcu_preempt_state, rnp_p, flags);
-}
-
 /*
  * Advance a ->blkd_tasks-list pointer to the next entry, instead
  * returning NULL if at the end of the list.
@@ -300,7 +258,6 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp)
  */
 void rcu_read_unlock_special(struct task_struct *t)
 {
-	bool empty;
 	bool empty_exp;
 	bool empty_norm;
 	bool empty_exp_now;
@@ -334,7 +291,13 @@ void rcu_read_unlock_special(struct task_struct *t)
 	}
 
 	/* Hardware IRQ handlers cannot block, complain if they get here. */
-	if (WARN_ON_ONCE(in_irq() || in_serving_softirq())) {
+	if (in_irq() || in_serving_softirq()) {
+		lockdep_rcu_suspicious(__FILE__, __LINE__,
+				       "rcu_read_unlock() from irq or softirq with blocking in critical section!!!\n");
+		pr_alert("->rcu_read_unlock_special: %#x (b: %d, nq: %d)\n",
+			 t->rcu_read_unlock_special.s,
+			 t->rcu_read_unlock_special.b.blocked,
+			 t->rcu_read_unlock_special.b.need_qs);
 		local_irq_restore(flags);
 		return;
 	}
@@ -356,7 +319,6 @@ void rcu_read_unlock_special(struct task_struct *t)
 				break;
 			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
 		}
-		empty = !rcu_preempt_has_tasks(rnp);
 		empty_norm = !rcu_preempt_blocked_readers_cgp(rnp);
 		empty_exp = !rcu_preempted_readers_exp(rnp);
 		smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
@@ -376,14 +338,6 @@ void rcu_read_unlock_special(struct task_struct *t)
 		drop_boost_mutex = rt_mutex_owner(&rnp->boost_mtx) == t;
 #endif /* #ifdef CONFIG_RCU_BOOST */
 
-		/*
-		 * If this was the last task on the list, go see if we
-		 * need to propagate ->qsmaskinit bit clearing up the
-		 * rcu_node tree.
-		 */
-		if (!empty && !rcu_preempt_has_tasks(rnp))
-			rcu_cleanup_dead_rnp(rnp);
-
 		/*
 		 * If this was the last task on the current list, and if
 		 * we aren't waiting on any CPUs, report the quiescent state.
@@ -399,7 +353,8 @@ void rcu_read_unlock_special(struct task_struct *t)
 							 rnp->grplo,
 							 rnp->grphi,
 							 !!rnp->gp_tasks);
-			rcu_report_unblock_qs_rnp(rnp, flags);
+			rcu_report_unblock_qs_rnp(&rcu_preempt_state,
+						  rnp, flags);
 		} else {
 			raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		}
@@ -520,10 +475,6 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
 	WARN_ON_ONCE(rnp->qsmask);
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
-
-#endif /* #ifdef CONFIG_HOTPLUG_CPU */
-
 /*
  * Check for a quiescent state from the current CPU.  When a task blocks,
  * the task is recorded in the corresponding CPU's rcu_node structure,
@@ -585,7 +536,7 @@ void synchronize_rcu(void)
 			   "Illegal synchronize_rcu() in RCU read-side critical section");
 	if (!rcu_scheduler_active)
 		return;
-	if (rcu_expedited)
+	if (rcu_gp_is_expedited())
 		synchronize_rcu_expedited();
 	else
 		wait_rcu_gp(call_rcu);
@@ -630,9 +581,6 @@ static int sync_rcu_preempt_exp_done(struct rcu_node *rnp)
  * recursively up the tree.  (Calm down, calm down, we do the recursion
  * iteratively!)
  *
- * Most callers will set the "wake" flag, but the task initiating the
- * expedited grace period need not wake itself.
- *
  * Caller must hold sync_rcu_preempt_exp_mutex.
  */
 static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
@@ -667,29 +615,85 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
 
 /*
  * Snapshot the tasks blocking the newly started preemptible-RCU expedited
- * grace period for the specified rcu_node structure.  If there are no such
- * tasks, report it up the rcu_node hierarchy.
+ * grace period for the specified rcu_node structure, phase 1.  If there
+ * are such tasks, set the ->expmask bits up the rcu_node tree and also
+ * set the ->expmask bits on the leaf rcu_node structures to tell phase 2
+ * that work is needed here.
  *
- * Caller must hold sync_rcu_preempt_exp_mutex and must exclude
- * CPU hotplug operations.
+ * Caller must hold sync_rcu_preempt_exp_mutex.
  */
 static void
-sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp)
+sync_rcu_preempt_exp_init1(struct rcu_state *rsp, struct rcu_node *rnp)
 {
 	unsigned long flags;
-	int must_wait = 0;
+	unsigned long mask;
+	struct rcu_node *rnp_up;
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
 	smp_mb__after_unlock_lock();
+	WARN_ON_ONCE(rnp->expmask);
+	WARN_ON_ONCE(rnp->exp_tasks);
 	if (!rcu_preempt_has_tasks(rnp)) {
+		/* No blocked tasks, nothing to do. */
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
-	} else {
+		return;
+	}
+	/* Call for Phase 2 and propagate ->expmask bits up the tree. */
+	rnp->expmask = 1;
+	rnp_up = rnp;
+	while (rnp_up->parent) {
+		mask = rnp_up->grpmask;
+		rnp_up = rnp_up->parent;
+		if (rnp_up->expmask & mask)
+			break;
+		raw_spin_lock(&rnp_up->lock); /* irqs already off */
+		smp_mb__after_unlock_lock();
+		rnp_up->expmask |= mask;
+		raw_spin_unlock(&rnp_up->lock); /* irqs still off */
+	}
+	raw_spin_unlock_irqrestore(&rnp->lock, flags);
+}
+
+/*
+ * Snapshot the tasks blocking the newly started preemptible-RCU expedited
+ * grace period for the specified rcu_node structure, phase 2.  If the
+ * leaf rcu_node structure has its ->expmask field set, check for tasks.
+ * If there are some, clear ->expmask and set ->exp_tasks accordingly,
+ * then initiate RCU priority boosting.  Otherwise, clear ->expmask and
+ * invoke rcu_report_exp_rnp() to clear out the upper-level ->expmask bits,
+ * enabling rcu_read_unlock_special() to do the bit-clearing.
+ *
+ * Caller must hold sync_rcu_preempt_exp_mutex.
+ */
+static void
+sync_rcu_preempt_exp_init2(struct rcu_state *rsp, struct rcu_node *rnp)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
+	if (!rnp->expmask) {
+		/* Phase 1 didn't do anything, so Phase 2 doesn't either. */
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		return;
+	}
+
+	/* Phase 1 is over. */
+	rnp->expmask = 0;
+
+	/*
+	 * If there are still blocked tasks, set up ->exp_tasks so that
+	 * rcu_read_unlock_special() will wake us and then boost them.
+	 */
+	if (rcu_preempt_has_tasks(rnp)) {
 		rnp->exp_tasks = rnp->blkd_tasks.next;
 		rcu_initiate_boost(rnp, flags);  /* releases rnp->lock */
-		must_wait = 1;
+		return;
 	}
-	if (!must_wait)
-		rcu_report_exp_rnp(rsp, rnp, false); /* Don't wake self. */
+
+	/* No longer any blocked tasks, so undo bit setting. */
+	raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	rcu_report_exp_rnp(rsp, rnp, false);
 }
 
 /**
@@ -706,7 +710,6 @@ sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp)
  */
 void synchronize_rcu_expedited(void)
 {
-	unsigned long flags;
 	struct rcu_node *rnp;
 	struct rcu_state *rsp = &rcu_preempt_state;
 	unsigned long snap;
@@ -757,19 +760,16 @@ void synchronize_rcu_expedited(void)
 	/* force all RCU readers onto ->blkd_tasks lists. */
 	synchronize_sched_expedited();
 
-	/* Initialize ->expmask for all non-leaf rcu_node structures. */
-	rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) {
-		raw_spin_lock_irqsave(&rnp->lock, flags);
-		smp_mb__after_unlock_lock();
-		rnp->expmask = rnp->qsmaskinit;
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
-	}
-
-	/* Snapshot current state of ->blkd_tasks lists. */
+	/*
+	 * Snapshot current state of ->blkd_tasks lists into ->expmask.
+	 * Phase 1 sets bits and phase 2 permits rcu_read_unlock_special()
+	 * to start clearing them.  Doing this in one phase leads to
+	 * strange races between setting and clearing bits, so just say "no"!
+	 */
+	rcu_for_each_leaf_node(rsp, rnp)
+		sync_rcu_preempt_exp_init1(rsp, rnp);
 	rcu_for_each_leaf_node(rsp, rnp)
-		sync_rcu_preempt_exp_init(rsp, rnp);
-	if (NUM_RCU_NODES > 1)
-		sync_rcu_preempt_exp_init(rsp, rcu_get_root(rsp));
+		sync_rcu_preempt_exp_init2(rsp, rnp);
 
 	put_online_cpus();
 
@@ -859,8 +859,6 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp)
 	return 0;
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
-
 /*
  * Because there is no preemptible RCU, there can be no readers blocked.
  */
@@ -869,8 +867,6 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp)
 	return false;
 }
 
-#endif /* #ifdef CONFIG_HOTPLUG_CPU */
-
 /*
  * Because preemptible RCU does not exist, we never have to check for
  * tasks blocked within RCU read-side critical sections.
@@ -1170,7 +1166,7 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp)
  * Returns zero if all is well, a negated errno otherwise.
  */
 static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
-						 struct rcu_node *rnp)
+				       struct rcu_node *rnp)
 {
 	int rnp_index = rnp - &rsp->node[0];
 	unsigned long flags;
@@ -1180,7 +1176,7 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 	if (&rcu_preempt_state != rsp)
 		return 0;
 
-	if (!rcu_scheduler_fully_active || rnp->qsmaskinit == 0)
+	if (!rcu_scheduler_fully_active || rcu_rnp_online_cpus(rnp) == 0)
 		return 0;
 
 	rsp->boost = 1;
@@ -1273,7 +1269,7 @@ static void rcu_cpu_kthread(unsigned int cpu)
 static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
 {
 	struct task_struct *t = rnp->boost_kthread_task;
-	unsigned long mask = rnp->qsmaskinit;
+	unsigned long mask = rcu_rnp_online_cpus(rnp);
 	cpumask_var_t cm;
 	int cpu;
 
@@ -1945,7 +1941,8 @@ static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu)
 		rhp = ACCESS_ONCE(rdp->nocb_follower_head);
 
 	/* Having no rcuo kthread but CBs after scheduler starts is bad! */
-	if (!ACCESS_ONCE(rdp->nocb_kthread) && rhp) {
+	if (!ACCESS_ONCE(rdp->nocb_kthread) && rhp &&
+	    rcu_scheduler_fully_active) {
 		/* RCU callback enqueued before CPU first came online??? */
 		pr_err("RCU: Never-onlined no-CBs CPU %d has CB %p\n",
 		       cpu, rhp->func);
@@ -2392,18 +2389,8 @@ void __init rcu_init_nohz(void)
 		pr_info("\tPoll for callbacks from no-CBs CPUs.\n");
 
 	for_each_rcu_flavor(rsp) {
-		for_each_cpu(cpu, rcu_nocb_mask) {
-			struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
-
-			/*
-			 * If there are early callbacks, they will need
-			 * to be moved to the nocb lists.
-			 */
-			WARN_ON_ONCE(rdp->nxttail[RCU_NEXT_TAIL] !=
-				     &rdp->nxtlist &&
-				     rdp->nxttail[RCU_NEXT_TAIL] != NULL);
-			init_nocb_callback_list(rdp);
-		}
+		for_each_cpu(cpu, rcu_nocb_mask)
+			init_nocb_callback_list(per_cpu_ptr(rsp->rda, cpu));
 		rcu_organize_nocb_kthreads(rsp);
 	}
 }
@@ -2540,6 +2527,16 @@ static bool init_nocb_callback_list(struct rcu_data *rdp)
 	if (!rcu_is_nocb_cpu(rdp->cpu))
 		return false;
 
+	/* If there are early-boot callbacks, move them to nocb lists. */
+	if (rdp->nxtlist) {
+		rdp->nocb_head = rdp->nxtlist;
+		rdp->nocb_tail = rdp->nxttail[RCU_NEXT_TAIL];
+		atomic_long_set(&rdp->nocb_q_count, rdp->qlen);
+		atomic_long_set(&rdp->nocb_q_count_lazy, rdp->qlen_lazy);
+		rdp->nxtlist = NULL;
+		rdp->qlen = 0;
+		rdp->qlen_lazy = 0;
+	}
 	rdp->nxttail[RCU_NEXT_TAIL] = NULL;
 	return true;
 }
@@ -2763,7 +2760,8 @@ static void rcu_sysidle_exit(int irq)
 
 /*
  * Check to see if the current CPU is idle.  Note that usermode execution
- * does not count as idle.  The caller must have disabled interrupts.
+ * does not count as idle.  The caller must have disabled interrupts,
+ * and must be running on tick_do_timer_cpu.
  */
 static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle,
 				  unsigned long *maxj)
@@ -2784,8 +2782,8 @@ static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle,
 	if (!*isidle || rdp->rsp != rcu_state_p ||
 	    cpu_is_offline(rdp->cpu) || rdp->cpu == tick_do_timer_cpu)
 		return;
-	if (rcu_gp_in_progress(rdp->rsp))
-		WARN_ON_ONCE(smp_processor_id() != tick_do_timer_cpu);
+	/* Verify affinity of current kthread. */
+	WARN_ON_ONCE(smp_processor_id() != tick_do_timer_cpu);
 
 	/* Pick up current idle and NMI-nesting counter and check. */
 	cur = atomic_read(&rdtp->dynticks_idle);
@@ -3068,11 +3066,10 @@ static void rcu_bind_gp_kthread(void)
 		return;
 #ifdef CONFIG_NO_HZ_FULL_SYSIDLE
 	cpu = tick_do_timer_cpu;
-	if (cpu >= 0 && cpu < nr_cpu_ids && raw_smp_processor_id() != cpu)
+	if (cpu >= 0 && cpu < nr_cpu_ids)
 		set_cpus_allowed_ptr(current, cpumask_of(cpu));
 #else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
-	if (!is_housekeeping_cpu(raw_smp_processor_id()))
-		housekeeping_affine(current);
+	housekeeping_affine(current);
 #endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
 }
 

kernel/rcu/tree_trace.c

@@ -283,8 +283,8 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
 			seq_puts(m, "\n");
 			level = rnp->level;
 		}
-		seq_printf(m, "%lx/%lx %c%c>%c %d:%d ^%d    ",
-			   rnp->qsmask, rnp->qsmaskinit,
+		seq_printf(m, "%lx/%lx->%lx %c%c>%c %d:%d ^%d    ",
+			   rnp->qsmask, rnp->qsmaskinit, rnp->qsmaskinitnext,
 			   ".G"[rnp->gp_tasks != NULL],
 			   ".E"[rnp->exp_tasks != NULL],
 			   ".T"[!list_empty(&rnp->blkd_tasks)],

kernel/rcu/update.c

@@ -62,6 +62,63 @@ MODULE_ALIAS("rcupdate");
 
 module_param(rcu_expedited, int, 0);
 
+#ifndef CONFIG_TINY_RCU
+
+static atomic_t rcu_expedited_nesting =
+	ATOMIC_INIT(IS_ENABLED(CONFIG_RCU_EXPEDITE_BOOT) ? 1 : 0);
+
+/*
+ * Should normal grace-period primitives be expedited?  Intended for
+ * use within RCU.  Note that this function takes the rcu_expedited
+ * sysfs/boot variable into account as well as the rcu_expedite_gp()
+ * nesting.  So looping on rcu_unexpedite_gp() until rcu_gp_is_expedited()
+ * returns false is a -really- bad idea.
+ */
+bool rcu_gp_is_expedited(void)
+{
+	return rcu_expedited || atomic_read(&rcu_expedited_nesting);
+}
+EXPORT_SYMBOL_GPL(rcu_gp_is_expedited);
+
+/**
+ * rcu_expedite_gp - Expedite future RCU grace periods
+ *
+ * After a call to this function, future calls to synchronize_rcu() and
+ * friends act as the corresponding synchronize_rcu_expedited() function
+ * had instead been called.
+ */
+void rcu_expedite_gp(void)
+{
+	atomic_inc(&rcu_expedited_nesting);
+}
+EXPORT_SYMBOL_GPL(rcu_expedite_gp);
+
+/**
+ * rcu_unexpedite_gp - Cancel prior rcu_expedite_gp() invocation
+ *
+ * Undo a prior call to rcu_expedite_gp().  If all prior calls to
+ * rcu_expedite_gp() are undone by a subsequent call to rcu_unexpedite_gp(),
+ * and if the rcu_expedited sysfs/boot parameter is not set, then all
+ * subsequent calls to synchronize_rcu() and friends will return to
+ * their normal non-expedited behavior.
+ */
+void rcu_unexpedite_gp(void)
+{
+	atomic_dec(&rcu_expedited_nesting);
+}
+EXPORT_SYMBOL_GPL(rcu_unexpedite_gp);
+
+#endif /* #ifndef CONFIG_TINY_RCU */
+
+/*
+ * Inform RCU of the end of the in-kernel boot sequence.
+ */
+void rcu_end_inkernel_boot(void)
+{
+	if (IS_ENABLED(CONFIG_RCU_EXPEDITE_BOOT))
+		rcu_unexpedite_gp();
+}
+
 #ifdef CONFIG_PREEMPT_RCU
 
 /*
@@ -199,16 +256,13 @@ EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held);
 
 #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
-struct rcu_synchronize {
-	struct rcu_head head;
-	struct completion completion;
-};
-
-/*
- * Awaken the corresponding synchronize_rcu() instance now that a
- * grace period has elapsed.
+/**
+ * wakeme_after_rcu() - Callback function to awaken a task after grace period
+ * @head: Pointer to rcu_head member within rcu_synchronize structure
+ *
+ * Awaken the corresponding task now that a grace period has elapsed.
  */
-static void wakeme_after_rcu(struct rcu_head  *head)
+void wakeme_after_rcu(struct rcu_head *head)
 {
 	struct rcu_synchronize *rcu;
 

kernel/sched/idle.c

@@ -209,6 +209,8 @@ use_default:
 	goto exit_idle;
 }
 
+DEFINE_PER_CPU(bool, cpu_dead_idle);
+
 /*
  * Generic idle loop implementation
  *
@@ -233,8 +235,13 @@ static void cpu_idle_loop(void)
 			check_pgt_cache();
 			rmb();
 
-			if (cpu_is_offline(smp_processor_id()))
+			if (cpu_is_offline(smp_processor_id())) {
+				rcu_cpu_notify(NULL, CPU_DYING_IDLE,
+					       (void *)(long)smp_processor_id());
+				smp_mb(); /* all activity before dead. */
+				this_cpu_write(cpu_dead_idle, true);
 				arch_cpu_idle_dead();
+			}
 
 			local_irq_disable();
 			arch_cpu_idle_enter();

kernel/smpboot.c

@@ -4,6 +4,7 @@
 #include <linux/cpu.h>
 #include <linux/err.h>
 #include <linux/smp.h>
+#include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/list.h>
 #include <linux/slab.h>
@@ -314,3 +315,158 @@ void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread)
 	put_online_cpus();
 }
 EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread);
+
+static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD);
+
+/*
+ * Called to poll specified CPU's state, for example, when waiting for
+ * a CPU to come online.
+ */
+int cpu_report_state(int cpu)
+{
+	return atomic_read(&per_cpu(cpu_hotplug_state, cpu));
+}
+
+/*
+ * If CPU has died properly, set its state to CPU_UP_PREPARE and
+ * return success.  Otherwise, return -EBUSY if the CPU died after
+ * cpu_wait_death() timed out.  And yet otherwise again, return -EAGAIN
+ * if cpu_wait_death() timed out and the CPU still hasn't gotten around
+ * to dying.  In the latter two cases, the CPU might not be set up
+ * properly, but it is up to the arch-specific code to decide.
+ * Finally, -EIO indicates an unanticipated problem.
+ *
+ * Note that it is permissible to omit this call entirely, as is
+ * done in architectures that do no CPU-hotplug error checking.
+ */
+int cpu_check_up_prepare(int cpu)
+{
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) {
+		atomic_set(&per_cpu(cpu_hotplug_state, cpu), CPU_UP_PREPARE);
+		return 0;
+	}
+
+	switch (atomic_read(&per_cpu(cpu_hotplug_state, cpu))) {
+
+	case CPU_POST_DEAD:
+
+		/* The CPU died properly, so just start it up again. */
+		atomic_set(&per_cpu(cpu_hotplug_state, cpu), CPU_UP_PREPARE);
+		return 0;
+
+	case CPU_DEAD_FROZEN:
+
+		/*
+		 * Timeout during CPU death, so let caller know.
+		 * The outgoing CPU completed its processing, but after
+		 * cpu_wait_death() timed out and reported the error. The
+		 * caller is free to proceed, in which case the state
+		 * will be reset properly by cpu_set_state_online().
+		 * Proceeding despite this -EBUSY return makes sense
+		 * for systems where the outgoing CPUs take themselves
+		 * offline, with no post-death manipulation required from
+		 * a surviving CPU.
+		 */
+		return -EBUSY;
+
+	case CPU_BROKEN:
+
+		/*
+		 * The most likely reason we got here is that there was
+		 * a timeout during CPU death, and the outgoing CPU never
+		 * did complete its processing.  This could happen on
+		 * a virtualized system if the outgoing VCPU gets preempted
+		 * for more than five seconds, and the user attempts to
+		 * immediately online that same CPU.  Trying again later
+		 * might return -EBUSY above, hence -EAGAIN.
+		 */
+		return -EAGAIN;
+
+	default:
+
+		/* Should not happen.  Famous last words. */
+		return -EIO;
+	}
+}
+
+/*
+ * Mark the specified CPU online.
+ *
+ * Note that it is permissible to omit this call entirely, as is
+ * done in architectures that do no CPU-hotplug error checking.
+ */
+void cpu_set_state_online(int cpu)
+{
+	(void)atomic_xchg(&per_cpu(cpu_hotplug_state, cpu), CPU_ONLINE);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+/*
+ * Wait for the specified CPU to exit the idle loop and die.
+ */
+bool cpu_wait_death(unsigned int cpu, int seconds)
+{
+	int jf_left = seconds * HZ;
+	int oldstate;
+	bool ret = true;
+	int sleep_jf = 1;
+
+	might_sleep();
+
+	/* The outgoing CPU will normally get done quite quickly. */
+	if (atomic_read(&per_cpu(cpu_hotplug_state, cpu)) == CPU_DEAD)
+		goto update_state;
+	udelay(5);
+
+	/* But if the outgoing CPU dawdles, wait increasingly long times. */
+	while (atomic_read(&per_cpu(cpu_hotplug_state, cpu)) != CPU_DEAD) {
+		schedule_timeout_uninterruptible(sleep_jf);
+		jf_left -= sleep_jf;
+		if (jf_left <= 0)
+			break;
+		sleep_jf = DIV_ROUND_UP(sleep_jf * 11, 10);
+	}
+update_state:
+	oldstate = atomic_read(&per_cpu(cpu_hotplug_state, cpu));
+	if (oldstate == CPU_DEAD) {
+		/* Outgoing CPU died normally, update state. */
+		smp_mb(); /* atomic_read() before update. */
+		atomic_set(&per_cpu(cpu_hotplug_state, cpu), CPU_POST_DEAD);
+	} else {
+		/* Outgoing CPU still hasn't died, set state accordingly. */
+		if (atomic_cmpxchg(&per_cpu(cpu_hotplug_state, cpu),
+				   oldstate, CPU_BROKEN) != oldstate)
+			goto update_state;
+		ret = false;
+	}
+	return ret;
+}
+
+/*
+ * Called by the outgoing CPU to report its successful death.  Return
+ * false if this report follows the surviving CPU's timing out.
+ *
+ * A separate "CPU_DEAD_FROZEN" is used when the surviving CPU
+ * timed out.  This approach allows architectures to omit calls to
+ * cpu_check_up_prepare() and cpu_set_state_online() without defeating
+ * the next cpu_wait_death()'s polling loop.
+ */
+bool cpu_report_death(void)
+{
+	int oldstate;
+	int newstate;
+	int cpu = smp_processor_id();
+
+	do {
+		oldstate = atomic_read(&per_cpu(cpu_hotplug_state, cpu));
+		if (oldstate != CPU_BROKEN)
+			newstate = CPU_DEAD;
+		else
+			newstate = CPU_DEAD_FROZEN;
+	} while (atomic_cmpxchg(&per_cpu(cpu_hotplug_state, cpu),
+				oldstate, newstate) != oldstate);
+	return newstate == CPU_DEAD;
+}
+
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */

lib/Kconfig.debug

@@ -1193,16 +1193,7 @@ config DEBUG_CREDENTIALS
 menu "RCU Debugging"
 
 config PROVE_RCU
-	bool "RCU debugging: prove RCU correctness"
-	depends on PROVE_LOCKING
-	default n
-	help
-	 This feature enables lockdep extensions that check for correct
-	 use of RCU APIs.  This is currently under development.  Say Y
-	 if you want to debug RCU usage or help work on the PROVE_RCU
-	 feature.
-
-	 Say N if you are unsure.
+	def_bool PROVE_LOCKING
 
 config PROVE_RCU_REPEATEDLY
 	bool "RCU debugging: don't disable PROVE_RCU on first splat"
@@ -1270,6 +1261,30 @@ config RCU_TORTURE_TEST_RUNNABLE
 	  Say N here if you want the RCU torture tests to start only
 	  after being manually enabled via /proc.
 
+config RCU_TORTURE_TEST_SLOW_INIT
+	bool "Slow down RCU grace-period initialization to expose races"
+	depends on RCU_TORTURE_TEST
+	help
+	  This option makes grace-period initialization block for a
+	  few jiffies between initializing each pair of consecutive
+	  rcu_node structures.	This helps to expose races involving
+	  grace-period initialization, in other words, it makes your
+	  kernel less stable.  It can also greatly increase grace-period
+	  latency, especially on systems with large numbers of CPUs.
+	  This is useful when torture-testing RCU, but in almost no
+	  other circumstance.
+
+	  Say Y here if you want your system to crash and hang more often.
+	  Say N if you want a sane system.
+
+config RCU_TORTURE_TEST_SLOW_INIT_DELAY
+	int "How much to slow down RCU grace-period initialization"
+	range 0 5
+	default 3
+	help
+	  This option specifies the number of jiffies to wait between
+	  each rcu_node structure initialization.
+
 config RCU_CPU_STALL_TIMEOUT
 	int "RCU CPU stall timeout in seconds"
 	depends on RCU_STALL_COMMON

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

@@ -310,7 +310,7 @@ function dump(first, pastlast)
 			cfr[jn] = cf[j] "." cfrep[cf[j]];
 		}
 		if (cpusr[jn] > ncpus && ncpus != 0)
-			ovf = "(!)";
+			ovf = "-ovf";
 		else
 			ovf = "";
 		print "echo ", cfr[jn], cpusr[jn] ovf ": Starting build. `date`";

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

@@ -1,2 +1,3 @@
 CONFIG_RCU_TORTURE_TEST=y
 CONFIG_PRINTK_TIME=y
+CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y