diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt
index fc103d7..cdb20d4 100644
--- a/Documentation/RCU/checklist.txt
+++ b/Documentation/RCU/checklist.txt
@@ -310,6 +310,12 @@
 	code under the influence of preempt_disable(), you instead
 	need to use synchronize_irq() or synchronize_sched().
 
+	This same limitation also applies to synchronize_rcu_bh()
+	and synchronize_srcu(), as well as to the asynchronous and
+	expedited forms of the three primitives, namely call_rcu(),
+	call_rcu_bh(), call_srcu(), synchronize_rcu_expedited(),
+	synchronize_rcu_bh_expedited(), and synchronize_srcu_expedited().
+
 12.	Any lock acquired by an RCU callback must be acquired elsewhere
 	with softirq disabled, e.g., via spin_lock_irqsave(),
 	spin_lock_bh(), etc.  Failing to disable irq on a given
diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt
index 523364e..1927151 100644
--- a/Documentation/RCU/stallwarn.txt
+++ b/Documentation/RCU/stallwarn.txt
@@ -99,7 +99,7 @@
 printed:
 
 	INFO: rcu_preempt detected stall on CPU
-	0: (64628 ticks this GP) idle=dd5/3fffffffffffffff/0 drain=0 . timer=-1
+	0: (64628 ticks this GP) idle=dd5/3fffffffffffffff/0 drain=0 . timer not pending
 	   (t=65000 jiffies)
 
 The "(64628 ticks this GP)" indicates that this CPU has taken more
@@ -116,13 +116,13 @@
 be a small positive number if in the idle loop and a very large positive
 number (as shown above) otherwise.
 
-For CONFIG_RCU_FAST_NO_HZ kernels, the "drain=0" indicates that the
-CPU is not in the process of trying to force itself into dyntick-idle
-state, the "." indicates that the CPU has not given up forcing RCU
-into dyntick-idle mode (it would be "H" otherwise), and the "timer=-1"
-indicates that the CPU has not recented forced RCU into dyntick-idle
-mode (it would otherwise indicate the number of microseconds remaining
-in this forced state).
+For CONFIG_RCU_FAST_NO_HZ kernels, the "drain=0" indicates that the CPU is
+not in the process of trying to force itself into dyntick-idle state, the
+"." indicates that the CPU has not given up forcing RCU into dyntick-idle
+mode (it would be "H" otherwise), and the "timer not pending" indicates
+that the CPU has not recently forced RCU into dyntick-idle mode (it
+would otherwise indicate the number of microseconds remaining in this
+forced state).
 
 
 Multiple Warnings From One Stall
diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index f6f15ce..672d190 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -333,23 +333,23 @@
 The output of "cat rcu/rcu_pending" looks as follows:
 
 rcu_sched:
-  0 np=255892 qsp=53936 rpq=85 cbr=0 cng=14417 gpc=10033 gps=24320 nf=6445 nn=146741
-  1 np=261224 qsp=54638 rpq=33 cbr=0 cng=25723 gpc=16310 gps=2849 nf=5912 nn=155792
-  2 np=237496 qsp=49664 rpq=23 cbr=0 cng=2762 gpc=45478 gps=1762 nf=1201 nn=136629
-  3 np=236249 qsp=48766 rpq=98 cbr=0 cng=286 gpc=48049 gps=1218 nf=207 nn=137723
-  4 np=221310 qsp=46850 rpq=7 cbr=0 cng=26 gpc=43161 gps=4634 nf=3529 nn=123110
-  5 np=237332 qsp=48449 rpq=9 cbr=0 cng=54 gpc=47920 gps=3252 nf=201 nn=137456
-  6 np=219995 qsp=46718 rpq=12 cbr=0 cng=50 gpc=42098 gps=6093 nf=4202 nn=120834
-  7 np=249893 qsp=49390 rpq=42 cbr=0 cng=72 gpc=38400 gps=17102 nf=41 nn=144888
+  0 np=255892 qsp=53936 rpq=85 cbr=0 cng=14417 gpc=10033 gps=24320 nn=146741
+  1 np=261224 qsp=54638 rpq=33 cbr=0 cng=25723 gpc=16310 gps=2849 nn=155792
+  2 np=237496 qsp=49664 rpq=23 cbr=0 cng=2762 gpc=45478 gps=1762 nn=136629
+  3 np=236249 qsp=48766 rpq=98 cbr=0 cng=286 gpc=48049 gps=1218 nn=137723
+  4 np=221310 qsp=46850 rpq=7 cbr=0 cng=26 gpc=43161 gps=4634 nn=123110
+  5 np=237332 qsp=48449 rpq=9 cbr=0 cng=54 gpc=47920 gps=3252 nn=137456
+  6 np=219995 qsp=46718 rpq=12 cbr=0 cng=50 gpc=42098 gps=6093 nn=120834
+  7 np=249893 qsp=49390 rpq=42 cbr=0 cng=72 gpc=38400 gps=17102 nn=144888
 rcu_bh:
-  0 np=146741 qsp=1419 rpq=6 cbr=0 cng=6 gpc=0 gps=0 nf=2 nn=145314
-  1 np=155792 qsp=12597 rpq=3 cbr=0 cng=0 gpc=4 gps=8 nf=3 nn=143180
-  2 np=136629 qsp=18680 rpq=1 cbr=0 cng=0 gpc=7 gps=6 nf=0 nn=117936
-  3 np=137723 qsp=2843 rpq=0 cbr=0 cng=0 gpc=10 gps=7 nf=0 nn=134863
-  4 np=123110 qsp=12433 rpq=0 cbr=0 cng=0 gpc=4 gps=2 nf=0 nn=110671
-  5 np=137456 qsp=4210 rpq=1 cbr=0 cng=0 gpc=6 gps=5 nf=0 nn=133235
-  6 np=120834 qsp=9902 rpq=2 cbr=0 cng=0 gpc=6 gps=3 nf=2 nn=110921
-  7 np=144888 qsp=26336 rpq=0 cbr=0 cng=0 gpc=8 gps=2 nf=0 nn=118542
+  0 np=146741 qsp=1419 rpq=6 cbr=0 cng=6 gpc=0 gps=0 nn=145314
+  1 np=155792 qsp=12597 rpq=3 cbr=0 cng=0 gpc=4 gps=8 nn=143180
+  2 np=136629 qsp=18680 rpq=1 cbr=0 cng=0 gpc=7 gps=6 nn=117936
+  3 np=137723 qsp=2843 rpq=0 cbr=0 cng=0 gpc=10 gps=7 nn=134863
+  4 np=123110 qsp=12433 rpq=0 cbr=0 cng=0 gpc=4 gps=2 nn=110671
+  5 np=137456 qsp=4210 rpq=1 cbr=0 cng=0 gpc=6 gps=5 nn=133235
+  6 np=120834 qsp=9902 rpq=2 cbr=0 cng=0 gpc=6 gps=3 nn=110921
+  7 np=144888 qsp=26336 rpq=0 cbr=0 cng=0 gpc=8 gps=2 nn=118542
 
 As always, this is once again split into "rcu_sched" and "rcu_bh"
 portions, with CONFIG_TREE_PREEMPT_RCU kernels having an additional
@@ -377,17 +377,6 @@
 o	"gps" is the number of times that a new grace period had started,
 	but this CPU was not yet aware of it.
 
-o	"nf" is the number of times that this CPU suspected that the
-	current grace period had run for too long, and thus needed to
-	be forced.
-
-	Please note that "forcing" consists of sending resched IPIs
-	to holdout CPUs.  If that CPU really still is in an old RCU
-	read-side critical section, then we really do have to wait for it.
-	The assumption behing "forcing" is that the CPU is not still in
-	an old RCU read-side critical section, but has not yet responded
-	for some other reason.
-
 o	"nn" is the number of times that this CPU needed nothing.  Alert
 	readers will note that the rcu "nn" number for a given CPU very
 	closely matches the rcu_bh "np" number for that same CPU.  This
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index 69ee188..bf0f6de 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -873,7 +873,7 @@
 	and code segments with preemption disabled (whether
 	via preempt_disable(), local_irq_save(), local_bh_disable(),
 	or some other mechanism) as if they were explicit RCU readers?
-	If so, you need RCU-sched.
+	If so, RCU-sched is the only choice that will work for you.
 
 e.	Do you need RCU grace periods to complete even in the face
 	of softirq monopolization of one or more of the CPUs?  For
@@ -884,7 +884,12 @@
 	RCU, but inappropriate for other synchronization mechanisms?
 	If so, consider SLAB_DESTROY_BY_RCU.  But please be careful!
 
-g.	Otherwise, use RCU.
+g.	Do you need read-side critical sections that are respected
+	even though they are in the middle of the idle loop, during
+	user-mode execution, or on an offlined CPU?  If so, SRCU is the
+	only choice that will work for you.
+
+h.	Otherwise, use RCU.
 
 Of course, this all assumes that you have determined that RCU is in fact
 the right tool for your job.
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index ad7e2e5..55ada04 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2385,6 +2385,17 @@
 	rcutree.rcu_cpu_stall_timeout= [KNL,BOOT]
 			Set timeout for RCU CPU stall warning messages.
 
+	rcutree.jiffies_till_first_fqs= [KNL,BOOT]
+			Set delay from grace-period initialization to
+			first attempt to force quiescent states.
+			Units are jiffies, minimum value is zero,
+			and maximum value is HZ.
+
+	rcutree.jiffies_till_next_fqs= [KNL,BOOT]
+			Set delay between subsequent attempts to force
+			quiescent states.  Units are jiffies, minimum
+			value is one, and maximum value is HZ.
+
 	rcutorture.fqs_duration= [KNL,BOOT]
 			Set duration of force_quiescent_state bursts.
 
diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c
index d6fde98..83638aa 100644
--- a/arch/alpha/kernel/process.c
+++ b/arch/alpha/kernel/process.c
@@ -28,6 +28,7 @@
 #include <linux/tty.h>
 #include <linux/console.h>
 #include <linux/slab.h>
+#include <linux/rcupdate.h>
 
 #include <asm/reg.h>
 #include <asm/uaccess.h>
@@ -54,9 +55,12 @@
 		/* FIXME -- EV6 and LCA45 know how to power down
 		   the CPU.  */
 
+		rcu_idle_enter();
 		while (!need_resched())
 			cpu_relax();
-		schedule();
+
+		rcu_idle_exit();
+		schedule_preempt_disabled();
 	}
 }
 
diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c
index 35ddc02..a41ad90 100644
--- a/arch/alpha/kernel/smp.c
+++ b/arch/alpha/kernel/smp.c
@@ -166,6 +166,7 @@
 	DBGS(("smp_callin: commencing CPU %d current %p active_mm %p\n",
 	      cpuid, current, current->active_mm));
 
+	preempt_disable();
 	/* Do nothing.  */
 	cpu_idle();
 }
diff --git a/arch/cris/kernel/process.c b/arch/cris/kernel/process.c
index 66fd017..7f65be6 100644
--- a/arch/cris/kernel/process.c
+++ b/arch/cris/kernel/process.c
@@ -25,6 +25,7 @@
 #include <linux/elfcore.h>
 #include <linux/mqueue.h>
 #include <linux/reboot.h>
+#include <linux/rcupdate.h>
 
 //#define DEBUG
 
@@ -74,6 +75,7 @@
 {
 	/* endless idle loop with no priority at all */
 	while (1) {
+		rcu_idle_enter();
 		while (!need_resched()) {
 			void (*idle)(void);
 			/*
@@ -86,6 +88,7 @@
 				idle = default_idle;
 			idle();
 		}
+		rcu_idle_exit();
 		schedule_preempt_disabled();
 	}
 }
diff --git a/arch/frv/kernel/process.c b/arch/frv/kernel/process.c
index ff95f50..2eb7fa5 100644
--- a/arch/frv/kernel/process.c
+++ b/arch/frv/kernel/process.c
@@ -25,6 +25,7 @@
 #include <linux/reboot.h>
 #include <linux/interrupt.h>
 #include <linux/pagemap.h>
+#include <linux/rcupdate.h>
 
 #include <asm/asm-offsets.h>
 #include <asm/uaccess.h>
@@ -69,12 +70,14 @@
 {
 	/* endless idle loop with no priority at all */
 	while (1) {
+		rcu_idle_enter();
 		while (!need_resched()) {
 			check_pgt_cache();
 
 			if (!frv_dma_inprogress && idle)
 				idle();
 		}
+		rcu_idle_exit();
 
 		schedule_preempt_disabled();
 	}
diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c
index 0e9c315..f153ed1 100644
--- a/arch/h8300/kernel/process.c
+++ b/arch/h8300/kernel/process.c
@@ -36,6 +36,7 @@
 #include <linux/reboot.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
+#include <linux/rcupdate.h>
 
 #include <asm/uaccess.h>
 #include <asm/traps.h>
@@ -78,8 +79,10 @@
 void cpu_idle(void)
 {
 	while (1) {
+		rcu_idle_enter();
 		while (!need_resched())
 			idle();
+		rcu_idle_exit();
 		schedule_preempt_disabled();
 	}
 }
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index dd6fc14..3e316ec 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -29,6 +29,7 @@
 #include <linux/kdebug.h>
 #include <linux/utsname.h>
 #include <linux/tracehook.h>
+#include <linux/rcupdate.h>
 
 #include <asm/cpu.h>
 #include <asm/delay.h>
@@ -279,6 +280,7 @@
 
 	/* endless idle loop with no priority at all */
 	while (1) {
+		rcu_idle_enter();
 		if (can_do_pal_halt) {
 			current_thread_info()->status &= ~TS_POLLING;
 			/*
@@ -309,6 +311,7 @@
 			normal_xtp();
 #endif
 		}
+		rcu_idle_exit();
 		schedule_preempt_disabled();
 		check_pgt_cache();
 		if (cpu_is_offline(cpu))
diff --git a/arch/m32r/kernel/process.c b/arch/m32r/kernel/process.c
index 3a4a32b..384e63f 100644
--- a/arch/m32r/kernel/process.c
+++ b/arch/m32r/kernel/process.c
@@ -26,6 +26,7 @@
 #include <linux/ptrace.h>
 #include <linux/unistd.h>
 #include <linux/hardirq.h>
+#include <linux/rcupdate.h>
 
 #include <asm/io.h>
 #include <asm/uaccess.h>
@@ -82,6 +83,7 @@
 {
 	/* endless idle loop with no priority at all */
 	while (1) {
+		rcu_idle_enter();
 		while (!need_resched()) {
 			void (*idle)(void) = pm_idle;
 
@@ -90,6 +92,7 @@
 
 			idle();
 		}
+		rcu_idle_exit();
 		schedule_preempt_disabled();
 	}
 }
diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c
index c488e3c..ac2892e 100644
--- a/arch/m68k/kernel/process.c
+++ b/arch/m68k/kernel/process.c
@@ -25,6 +25,7 @@
 #include <linux/reboot.h>
 #include <linux/init_task.h>
 #include <linux/mqueue.h>
+#include <linux/rcupdate.h>
 
 #include <asm/uaccess.h>
 #include <asm/traps.h>
@@ -75,8 +76,10 @@
 {
 	/* endless idle loop with no priority at all */
 	while (1) {
+		rcu_idle_enter();
 		while (!need_resched())
 			idle();
+		rcu_idle_exit();
 		schedule_preempt_disabled();
 	}
 }
diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c
index 7dab0cd..e9cceba 100644
--- a/arch/mn10300/kernel/process.c
+++ b/arch/mn10300/kernel/process.c
@@ -25,6 +25,7 @@
 #include <linux/err.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
+#include <linux/rcupdate.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/io.h>
@@ -107,6 +108,7 @@
 {
 	/* endless idle loop with no priority at all */
 	for (;;) {
+		rcu_idle_enter();
 		while (!need_resched()) {
 			void (*idle)(void);
 
@@ -121,6 +123,7 @@
 			}
 			idle();
 		}
+		rcu_idle_exit();
 
 		schedule_preempt_disabled();
 	}
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index 2c05a929..8c6b6b6 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -48,6 +48,7 @@
 #include <linux/unistd.h>
 #include <linux/kallsyms.h>
 #include <linux/uaccess.h>
+#include <linux/rcupdate.h>
 
 #include <asm/io.h>
 #include <asm/asm-offsets.h>
@@ -69,8 +70,10 @@
 
 	/* endless idle loop with no priority at all */
 	while (1) {
+		rcu_idle_enter();
 		while (!need_resched())
 			barrier();
+		rcu_idle_exit();
 		schedule_preempt_disabled();
 		check_pgt_cache();
 	}
diff --git a/arch/score/kernel/process.c b/arch/score/kernel/process.c
index 2707023..637970c 100644
--- a/arch/score/kernel/process.c
+++ b/arch/score/kernel/process.c
@@ -27,6 +27,7 @@
 #include <linux/reboot.h>
 #include <linux/elfcore.h>
 #include <linux/pm.h>
+#include <linux/rcupdate.h>
 
 void (*pm_power_off)(void);
 EXPORT_SYMBOL(pm_power_off);
@@ -50,9 +51,10 @@
 {
 	/* endless idle loop with no priority at all */
 	while (1) {
+		rcu_idle_enter();
 		while (!need_resched())
 			barrier();
-
+		rcu_idle_exit();
 		schedule_preempt_disabled();
 	}
 }
diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c
index 2c8d6a3..bc44311 100644
--- a/arch/xtensa/kernel/process.c
+++ b/arch/xtensa/kernel/process.c
@@ -31,6 +31,7 @@
 #include <linux/mqueue.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
+#include <linux/rcupdate.h>
 
 #include <asm/pgtable.h>
 #include <asm/uaccess.h>
@@ -110,8 +111,10 @@
 
 	/* endless idle loop with no priority at all */
 	while (1) {
+		rcu_idle_enter();
 		while (!need_resched())
 			platform_idle();
+		rcu_idle_exit();
 		schedule_preempt_disabled();
 	}
 }
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index c5f856a..5e4e617 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -430,6 +430,8 @@
 	NR_SOFTIRQS
 };
 
+#define SOFTIRQ_STOP_IDLE_MASK (~(1 << RCU_SOFTIRQ))
+
 /* map softirq index to softirq name. update 'softirq_to_name' in
  * kernel/softirq.c when adding a new softirq.
  */
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 115ead2..0fbbd52 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -210,14 +210,12 @@
  * to nest RCU_NONIDLE() wrappers, but the nesting level is currently
  * quite limited.  If deeper nesting is required, it will be necessary
  * to adjust DYNTICK_TASK_NESTING_VALUE accordingly.
- *
- * This macro may be used from process-level code only.
  */
 #define RCU_NONIDLE(a) \
 	do { \
-		rcu_idle_exit(); \
+		rcu_irq_enter(); \
 		do { a; } while (0); \
-		rcu_idle_enter(); \
+		rcu_irq_exit(); \
 	} while (0)
 
 /*
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index 4e6a61b..29ca1c6 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -45,6 +45,7 @@
 #include <linux/mutex.h>
 #include <linux/export.h>
 #include <linux/hardirq.h>
+#include <linux/delay.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/rcu.h>
@@ -81,6 +82,9 @@
 	} else {
 		barrier();  /* critical section before exit code. */
 		t->rcu_read_lock_nesting = INT_MIN;
+#ifdef CONFIG_PROVE_RCU_DELAY
+		udelay(10); /* Make preemption more probable. */
+#endif /* #ifdef CONFIG_PROVE_RCU_DELAY */
 		barrier();  /* assign before ->rcu_read_unlock_special load */
 		if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
 			rcu_read_unlock_special(t);
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index 547b1fe..e4c6a59 100644
--- a/kernel/rcutiny.c
+++ b/kernel/rcutiny.c
@@ -56,25 +56,28 @@
 static long long rcu_dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
 
 /* Common code for rcu_idle_enter() and rcu_irq_exit(), see kernel/rcutree.c. */
-static void rcu_idle_enter_common(long long oldval)
+static void rcu_idle_enter_common(long long newval)
 {
-	if (rcu_dynticks_nesting) {
+	if (newval) {
 		RCU_TRACE(trace_rcu_dyntick("--=",
-					    oldval, rcu_dynticks_nesting));
+					    rcu_dynticks_nesting, newval));
+		rcu_dynticks_nesting = newval;
 		return;
 	}
-	RCU_TRACE(trace_rcu_dyntick("Start", oldval, rcu_dynticks_nesting));
+	RCU_TRACE(trace_rcu_dyntick("Start", rcu_dynticks_nesting, newval));
 	if (!is_idle_task(current)) {
 		struct task_struct *idle = idle_task(smp_processor_id());
 
 		RCU_TRACE(trace_rcu_dyntick("Error on entry: not idle task",
-					    oldval, rcu_dynticks_nesting));
+					    rcu_dynticks_nesting, newval));
 		ftrace_dump(DUMP_ALL);
 		WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
 			  current->pid, current->comm,
 			  idle->pid, idle->comm); /* must be idle task! */
 	}
 	rcu_sched_qs(0); /* implies rcu_bh_qsctr_inc(0) */
+	barrier();
+	rcu_dynticks_nesting = newval;
 }
 
 /*
@@ -84,17 +87,16 @@
 void rcu_idle_enter(void)
 {
 	unsigned long flags;
-	long long oldval;
+	long long newval;
 
 	local_irq_save(flags);
-	oldval = rcu_dynticks_nesting;
 	WARN_ON_ONCE((rcu_dynticks_nesting & DYNTICK_TASK_NEST_MASK) == 0);
 	if ((rcu_dynticks_nesting & DYNTICK_TASK_NEST_MASK) ==
 	    DYNTICK_TASK_NEST_VALUE)
-		rcu_dynticks_nesting = 0;
+		newval = 0;
 	else
-		rcu_dynticks_nesting  -= DYNTICK_TASK_NEST_VALUE;
-	rcu_idle_enter_common(oldval);
+		newval = rcu_dynticks_nesting - DYNTICK_TASK_NEST_VALUE;
+	rcu_idle_enter_common(newval);
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(rcu_idle_enter);
@@ -105,15 +107,15 @@
 void rcu_irq_exit(void)
 {
 	unsigned long flags;
-	long long oldval;
+	long long newval;
 
 	local_irq_save(flags);
-	oldval = rcu_dynticks_nesting;
-	rcu_dynticks_nesting--;
-	WARN_ON_ONCE(rcu_dynticks_nesting < 0);
-	rcu_idle_enter_common(oldval);
+	newval = rcu_dynticks_nesting - 1;
+	WARN_ON_ONCE(newval < 0);
+	rcu_idle_enter_common(newval);
 	local_irq_restore(flags);
 }
+EXPORT_SYMBOL_GPL(rcu_irq_exit);
 
 /* Common code for rcu_idle_exit() and rcu_irq_enter(), see kernel/rcutree.c. */
 static void rcu_idle_exit_common(long long oldval)
@@ -171,6 +173,7 @@
 	rcu_idle_exit_common(oldval);
 	local_irq_restore(flags);
 }
+EXPORT_SYMBOL_GPL(rcu_irq_enter);
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 
diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h
index 918fd1e..3d01902 100644
--- a/kernel/rcutiny_plugin.h
+++ b/kernel/rcutiny_plugin.h
@@ -278,7 +278,7 @@
 	    rcu_preempt_ctrlblk.exp_tasks == NULL)
 		return 0;  /* Nothing to boost. */
 
-	raw_local_irq_save(flags);
+	local_irq_save(flags);
 
 	/*
 	 * Recheck with irqs disabled: all tasks in need of boosting
@@ -287,7 +287,7 @@
 	 */
 	if (rcu_preempt_ctrlblk.boost_tasks == NULL &&
 	    rcu_preempt_ctrlblk.exp_tasks == NULL) {
-		raw_local_irq_restore(flags);
+		local_irq_restore(flags);
 		return 0;
 	}
 
@@ -317,7 +317,7 @@
 	t = container_of(tb, struct task_struct, rcu_node_entry);
 	rt_mutex_init_proxy_locked(&mtx, t);
 	t->rcu_boost_mutex = &mtx;
-	raw_local_irq_restore(flags);
+	local_irq_restore(flags);
 	rt_mutex_lock(&mtx);
 	rt_mutex_unlock(&mtx);  /* Keep lockdep happy. */
 
@@ -991,9 +991,9 @@
 {
 	unsigned long flags;
 
-	raw_local_irq_save(flags);
+	local_irq_save(flags);
 	rcp->qlen -= n;
-	raw_local_irq_restore(flags);
+	local_irq_restore(flags);
 }
 
 /*
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 25b1503..aaa7b9f 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -53,10 +53,11 @@
 
 static int nreaders = -1;	/* # reader threads, defaults to 2*ncpus */
 static int nfakewriters = 4;	/* # fake writer threads */
-static int stat_interval;	/* Interval between stats, in seconds. */
-				/*  Defaults to "only at end of test". */
+static int stat_interval = 60;	/* Interval between stats, in seconds. */
+				/*  Zero means "only at end of test". */
 static bool verbose;		/* Print more debug info. */
-static bool test_no_idle_hz;	/* Test RCU's support for tickless idle CPUs. */
+static bool test_no_idle_hz = true;
+				/* Test RCU support for tickless idle CPUs. */
 static int shuffle_interval = 3; /* Interval between shuffles (in sec)*/
 static int stutter = 5;		/* Start/stop testing interval (in sec) */
 static int irqreader = 1;	/* RCU readers from irq (timers). */
@@ -119,11 +120,11 @@
 
 #define TORTURE_FLAG "-torture:"
 #define PRINTK_STRING(s) \
-	do { printk(KERN_ALERT "%s" TORTURE_FLAG s "\n", torture_type); } while (0)
+	do { pr_alert("%s" TORTURE_FLAG s "\n", torture_type); } while (0)
 #define VERBOSE_PRINTK_STRING(s) \
-	do { if (verbose) printk(KERN_ALERT "%s" TORTURE_FLAG s "\n", torture_type); } while (0)
+	do { if (verbose) pr_alert("%s" TORTURE_FLAG s "\n", torture_type); } while (0)
 #define VERBOSE_PRINTK_ERRSTRING(s) \
-	do { if (verbose) printk(KERN_ALERT "%s" TORTURE_FLAG "!!! " s "\n", torture_type); } while (0)
+	do { if (verbose) pr_alert("%s" TORTURE_FLAG "!!! " s "\n", torture_type); } while (0)
 
 static char printk_buf[4096];
 
@@ -176,8 +177,14 @@
 static long n_rcu_torture_timers;
 static long n_offline_attempts;
 static long n_offline_successes;
+static unsigned long sum_offline;
+static int min_offline = -1;
+static int max_offline;
 static long n_online_attempts;
 static long n_online_successes;
+static unsigned long sum_online;
+static int min_online = -1;
+static int max_online;
 static long n_barrier_attempts;
 static long n_barrier_successes;
 static struct list_head rcu_torture_removed;
@@ -235,7 +242,7 @@
 	if (fullstop == FULLSTOP_DONTSTOP)
 		fullstop = FULLSTOP_SHUTDOWN;
 	else
-		printk(KERN_WARNING /* but going down anyway, so... */
+		pr_warn(/* but going down anyway, so... */
 		       "Concurrent 'rmmod rcutorture' and shutdown illegal!\n");
 	mutex_unlock(&fullstop_mutex);
 	return NOTIFY_DONE;
@@ -248,7 +255,7 @@
 static void rcutorture_shutdown_absorb(char *title)
 {
 	if (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) {
-		printk(KERN_NOTICE
+		pr_notice(
 		       "rcutorture thread %s parking due to system shutdown\n",
 		       title);
 		schedule_timeout_uninterruptible(MAX_SCHEDULE_TIMEOUT);
@@ -1214,11 +1221,13 @@
 		       n_rcu_torture_boost_failure,
 		       n_rcu_torture_boosts,
 		       n_rcu_torture_timers);
-	cnt += sprintf(&page[cnt], "onoff: %ld/%ld:%ld/%ld ",
-		       n_online_successes,
-		       n_online_attempts,
-		       n_offline_successes,
-		       n_offline_attempts);
+	cnt += sprintf(&page[cnt],
+		       "onoff: %ld/%ld:%ld/%ld %d,%d:%d,%d %lu:%lu (HZ=%d) ",
+		       n_online_successes, n_online_attempts,
+		       n_offline_successes, n_offline_attempts,
+		       min_online, max_online,
+		       min_offline, max_offline,
+		       sum_online, sum_offline, HZ);
 	cnt += sprintf(&page[cnt], "barrier: %ld/%ld:%ld",
 		       n_barrier_successes,
 		       n_barrier_attempts,
@@ -1267,7 +1276,7 @@
 	int cnt;
 
 	cnt = rcu_torture_printk(printk_buf);
-	printk(KERN_ALERT "%s", printk_buf);
+	pr_alert("%s", printk_buf);
 }
 
 /*
@@ -1380,20 +1389,20 @@
 static inline void
 rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, char *tag)
 {
-	printk(KERN_ALERT "%s" TORTURE_FLAG
-		"--- %s: nreaders=%d nfakewriters=%d "
-		"stat_interval=%d verbose=%d test_no_idle_hz=%d "
-		"shuffle_interval=%d stutter=%d irqreader=%d "
-		"fqs_duration=%d fqs_holdoff=%d fqs_stutter=%d "
-		"test_boost=%d/%d test_boost_interval=%d "
-		"test_boost_duration=%d shutdown_secs=%d "
-		"onoff_interval=%d onoff_holdoff=%d\n",
-		torture_type, tag, nrealreaders, nfakewriters,
-		stat_interval, verbose, test_no_idle_hz, shuffle_interval,
-		stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter,
-		test_boost, cur_ops->can_boost,
-		test_boost_interval, test_boost_duration, shutdown_secs,
-		onoff_interval, onoff_holdoff);
+	pr_alert("%s" TORTURE_FLAG
+		 "--- %s: nreaders=%d nfakewriters=%d "
+		 "stat_interval=%d verbose=%d test_no_idle_hz=%d "
+		 "shuffle_interval=%d stutter=%d irqreader=%d "
+		 "fqs_duration=%d fqs_holdoff=%d fqs_stutter=%d "
+		 "test_boost=%d/%d test_boost_interval=%d "
+		 "test_boost_duration=%d shutdown_secs=%d "
+		 "onoff_interval=%d onoff_holdoff=%d\n",
+		 torture_type, tag, nrealreaders, nfakewriters,
+		 stat_interval, verbose, test_no_idle_hz, shuffle_interval,
+		 stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter,
+		 test_boost, cur_ops->can_boost,
+		 test_boost_interval, test_boost_duration, shutdown_secs,
+		 onoff_interval, onoff_holdoff);
 }
 
 static struct notifier_block rcutorture_shutdown_nb = {
@@ -1460,9 +1469,9 @@
 	       !kthread_should_stop()) {
 		delta = shutdown_time - jiffies_snap;
 		if (verbose)
-			printk(KERN_ALERT "%s" TORTURE_FLAG
-			       "rcu_torture_shutdown task: %lu jiffies remaining\n",
-			       torture_type, delta);
+			pr_alert("%s" TORTURE_FLAG
+				 "rcu_torture_shutdown task: %lu jiffies remaining\n",
+				 torture_type, delta);
 		schedule_timeout_interruptible(delta);
 		jiffies_snap = ACCESS_ONCE(jiffies);
 	}
@@ -1490,8 +1499,10 @@
 rcu_torture_onoff(void *arg)
 {
 	int cpu;
+	unsigned long delta;
 	int maxcpu = -1;
 	DEFINE_RCU_RANDOM(rand);
+	unsigned long starttime;
 
 	VERBOSE_PRINTK_STRING("rcu_torture_onoff task started");
 	for_each_online_cpu(cpu)
@@ -1506,29 +1517,51 @@
 		cpu = (rcu_random(&rand) >> 4) % (maxcpu + 1);
 		if (cpu_online(cpu) && cpu_is_hotpluggable(cpu)) {
 			if (verbose)
-				printk(KERN_ALERT "%s" TORTURE_FLAG
-				       "rcu_torture_onoff task: offlining %d\n",
-				       torture_type, cpu);
+				pr_alert("%s" TORTURE_FLAG
+					 "rcu_torture_onoff task: offlining %d\n",
+					 torture_type, cpu);
+			starttime = jiffies;
 			n_offline_attempts++;
 			if (cpu_down(cpu) == 0) {
 				if (verbose)
-					printk(KERN_ALERT "%s" TORTURE_FLAG
-					       "rcu_torture_onoff task: offlined %d\n",
-					       torture_type, cpu);
+					pr_alert("%s" TORTURE_FLAG
+						 "rcu_torture_onoff task: offlined %d\n",
+						 torture_type, cpu);
 				n_offline_successes++;
+				delta = jiffies - starttime;
+				sum_offline += delta;
+				if (min_offline < 0) {
+					min_offline = delta;
+					max_offline = delta;
+				}
+				if (min_offline > delta)
+					min_offline = delta;
+				if (max_offline < delta)
+					max_offline = delta;
 			}
 		} else if (cpu_is_hotpluggable(cpu)) {
 			if (verbose)
-				printk(KERN_ALERT "%s" TORTURE_FLAG
-				       "rcu_torture_onoff task: onlining %d\n",
-				       torture_type, cpu);
+				pr_alert("%s" TORTURE_FLAG
+					 "rcu_torture_onoff task: onlining %d\n",
+					 torture_type, cpu);
+			starttime = jiffies;
 			n_online_attempts++;
 			if (cpu_up(cpu) == 0) {
 				if (verbose)
-					printk(KERN_ALERT "%s" TORTURE_FLAG
-					       "rcu_torture_onoff task: onlined %d\n",
-					       torture_type, cpu);
+					pr_alert("%s" TORTURE_FLAG
+						 "rcu_torture_onoff task: onlined %d\n",
+						 torture_type, cpu);
 				n_online_successes++;
+				delta = jiffies - starttime;
+				sum_online += delta;
+				if (min_online < 0) {
+					min_online = delta;
+					max_online = delta;
+				}
+				if (min_online > delta)
+					min_online = delta;
+				if (max_online < delta)
+					max_online = delta;
 			}
 		}
 		schedule_timeout_interruptible(onoff_interval * HZ);
@@ -1593,14 +1626,14 @@
 	if (!kthread_should_stop()) {
 		stop_at = get_seconds() + stall_cpu;
 		/* RCU CPU stall is expected behavior in following code. */
-		printk(KERN_ALERT "rcu_torture_stall start.\n");
+		pr_alert("rcu_torture_stall start.\n");
 		rcu_read_lock();
 		preempt_disable();
 		while (ULONG_CMP_LT(get_seconds(), stop_at))
 			continue;  /* Induce RCU CPU stall warning. */
 		preempt_enable();
 		rcu_read_unlock();
-		printk(KERN_ALERT "rcu_torture_stall end.\n");
+		pr_alert("rcu_torture_stall end.\n");
 	}
 	rcutorture_shutdown_absorb("rcu_torture_stall");
 	while (!kthread_should_stop())
@@ -1716,12 +1749,12 @@
 	if (n_barrier_cbs == 0)
 		return 0;
 	if (cur_ops->call == NULL || cur_ops->cb_barrier == NULL) {
-		printk(KERN_ALERT "%s" TORTURE_FLAG
-		       " Call or barrier ops missing for %s,\n",
-		       torture_type, cur_ops->name);
-		printk(KERN_ALERT "%s" TORTURE_FLAG
-		       " RCU barrier testing omitted from run.\n",
-		       torture_type);
+		pr_alert("%s" TORTURE_FLAG
+			 " Call or barrier ops missing for %s,\n",
+			 torture_type, cur_ops->name);
+		pr_alert("%s" TORTURE_FLAG
+			 " RCU barrier testing omitted from run.\n",
+			 torture_type);
 		return 0;
 	}
 	atomic_set(&barrier_cbs_count, 0);
@@ -1814,7 +1847,7 @@
 	mutex_lock(&fullstop_mutex);
 	rcutorture_record_test_transition();
 	if (fullstop == FULLSTOP_SHUTDOWN) {
-		printk(KERN_WARNING /* but going down anyway, so... */
+		pr_warn(/* but going down anyway, so... */
 		       "Concurrent 'rmmod rcutorture' and shutdown illegal!\n");
 		mutex_unlock(&fullstop_mutex);
 		schedule_timeout_uninterruptible(10);
@@ -1938,17 +1971,17 @@
 			break;
 	}
 	if (i == ARRAY_SIZE(torture_ops)) {
-		printk(KERN_ALERT "rcu-torture: invalid torture type: \"%s\"\n",
-		       torture_type);
-		printk(KERN_ALERT "rcu-torture types:");
+		pr_alert("rcu-torture: invalid torture type: \"%s\"\n",
+			 torture_type);
+		pr_alert("rcu-torture types:");
 		for (i = 0; i < ARRAY_SIZE(torture_ops); i++)
-			printk(KERN_ALERT " %s", torture_ops[i]->name);
-		printk(KERN_ALERT "\n");
+			pr_alert(" %s", torture_ops[i]->name);
+		pr_alert("\n");
 		mutex_unlock(&fullstop_mutex);
 		return -EINVAL;
 	}
 	if (cur_ops->fqs == NULL && fqs_duration != 0) {
-		printk(KERN_ALERT "rcu-torture: ->fqs NULL and non-zero fqs_duration, fqs disabled.\n");
+		pr_alert("rcu-torture: ->fqs NULL and non-zero fqs_duration, fqs disabled.\n");
 		fqs_duration = 0;
 	}
 	if (cur_ops->init)
@@ -1996,14 +2029,15 @@
 	/* Start up the kthreads. */
 
 	VERBOSE_PRINTK_STRING("Creating rcu_torture_writer task");
-	writer_task = kthread_run(rcu_torture_writer, NULL,
-				  "rcu_torture_writer");
+	writer_task = kthread_create(rcu_torture_writer, NULL,
+				     "rcu_torture_writer");
 	if (IS_ERR(writer_task)) {
 		firsterr = PTR_ERR(writer_task);
 		VERBOSE_PRINTK_ERRSTRING("Failed to create writer");
 		writer_task = NULL;
 		goto unwind;
 	}
+	wake_up_process(writer_task);
 	fakewriter_tasks = kzalloc(nfakewriters * sizeof(fakewriter_tasks[0]),
 				   GFP_KERNEL);
 	if (fakewriter_tasks == NULL) {
@@ -2118,14 +2152,15 @@
 	}
 	if (shutdown_secs > 0) {
 		shutdown_time = jiffies + shutdown_secs * HZ;
-		shutdown_task = kthread_run(rcu_torture_shutdown, NULL,
-					    "rcu_torture_shutdown");
+		shutdown_task = kthread_create(rcu_torture_shutdown, NULL,
+					       "rcu_torture_shutdown");
 		if (IS_ERR(shutdown_task)) {
 			firsterr = PTR_ERR(shutdown_task);
 			VERBOSE_PRINTK_ERRSTRING("Failed to create shutdown");
 			shutdown_task = NULL;
 			goto unwind;
 		}
+		wake_up_process(shutdown_task);
 	}
 	i = rcu_torture_onoff_init();
 	if (i != 0) {
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index be76c80..80fd02e 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -52,6 +52,7 @@
 #include <linux/prefetch.h>
 #include <linux/delay.h>
 #include <linux/stop_machine.h>
+#include <linux/random.h>
 
 #include "rcutree.h"
 #include <trace/events/rcu.h>
@@ -61,6 +62,7 @@
 /* Data structures. */
 
 static struct lock_class_key rcu_node_class[RCU_NUM_LVLS];
+static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS];
 
 #define RCU_STATE_INITIALIZER(sname, cr) { \
 	.level = { &sname##_state.node[0] }, \
@@ -72,7 +74,6 @@
 	.orphan_nxttail = &sname##_state.orphan_nxtlist, \
 	.orphan_donetail = &sname##_state.orphan_donelist, \
 	.barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \
-	.fqslock = __RAW_SPIN_LOCK_UNLOCKED(&sname##_state.fqslock), \
 	.name = #sname, \
 }
 
@@ -88,7 +89,7 @@
 
 /* Increase (but not decrease) the CONFIG_RCU_FANOUT_LEAF at boot time. */
 static int rcu_fanout_leaf = CONFIG_RCU_FANOUT_LEAF;
-module_param(rcu_fanout_leaf, int, 0);
+module_param(rcu_fanout_leaf, int, 0444);
 int rcu_num_lvls __read_mostly = RCU_NUM_LVLS;
 static int num_rcu_lvl[] = {  /* Number of rcu_nodes at specified level. */
 	NUM_RCU_LVL_0,
@@ -175,8 +176,6 @@
 {
 	struct rcu_data *rdp = &per_cpu(rcu_sched_data, cpu);
 
-	rdp->passed_quiesce_gpnum = rdp->gpnum;
-	barrier();
 	if (rdp->passed_quiesce == 0)
 		trace_rcu_grace_period("rcu_sched", rdp->gpnum, "cpuqs");
 	rdp->passed_quiesce = 1;
@@ -186,8 +185,6 @@
 {
 	struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu);
 
-	rdp->passed_quiesce_gpnum = rdp->gpnum;
-	barrier();
 	if (rdp->passed_quiesce == 0)
 		trace_rcu_grace_period("rcu_bh", rdp->gpnum, "cpuqs");
 	rdp->passed_quiesce = 1;
@@ -216,9 +213,9 @@
 static int qhimark = 10000;	/* If this many pending, ignore blimit. */
 static int qlowmark = 100;	/* Once only this many pending, use blimit. */
 
-module_param(blimit, int, 0);
-module_param(qhimark, int, 0);
-module_param(qlowmark, int, 0);
+module_param(blimit, int, 0444);
+module_param(qhimark, int, 0444);
+module_param(qlowmark, int, 0444);
 
 int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */
 int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT;
@@ -226,7 +223,14 @@
 module_param(rcu_cpu_stall_suppress, int, 0644);
 module_param(rcu_cpu_stall_timeout, int, 0644);
 
-static void force_quiescent_state(struct rcu_state *rsp, int relaxed);
+static ulong jiffies_till_first_fqs = RCU_JIFFIES_TILL_FORCE_QS;
+static ulong jiffies_till_next_fqs = RCU_JIFFIES_TILL_FORCE_QS;
+
+module_param(jiffies_till_first_fqs, ulong, 0644);
+module_param(jiffies_till_next_fqs, ulong, 0644);
+
+static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *));
+static void force_quiescent_state(struct rcu_state *rsp);
 static int rcu_pending(int cpu);
 
 /*
@@ -252,7 +256,7 @@
  */
 void rcu_bh_force_quiescent_state(void)
 {
-	force_quiescent_state(&rcu_bh_state, 0);
+	force_quiescent_state(&rcu_bh_state);
 }
 EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state);
 
@@ -286,7 +290,7 @@
  */
 void rcu_sched_force_quiescent_state(void)
 {
-	force_quiescent_state(&rcu_sched_state, 0);
+	force_quiescent_state(&rcu_sched_state);
 }
 EXPORT_SYMBOL_GPL(rcu_sched_force_quiescent_state);
 
@@ -319,35 +323,6 @@
 }
 
 /*
- * If the specified CPU is offline, tell the caller that it is in
- * a quiescent state.  Otherwise, whack it with a reschedule IPI.
- * Grace periods can end up waiting on an offline CPU when that
- * CPU is in the process of coming online -- it will be added to the
- * rcu_node bitmasks before it actually makes it online.  The same thing
- * can happen while a CPU is in the process of coming online.  Because this
- * race is quite rare, we check for it after detecting that the grace
- * period has been delayed rather than checking each and every CPU
- * each and every time we start a new grace period.
- */
-static int rcu_implicit_offline_qs(struct rcu_data *rdp)
-{
-	/*
-	 * If the CPU is offline for more than a jiffy, it is in a quiescent
-	 * state.  We can trust its state not to change because interrupts
-	 * are disabled.  The reason for the jiffy's worth of slack is to
-	 * handle CPUs initializing on the way up and finding their way
-	 * to the idle loop on the way down.
-	 */
-	if (cpu_is_offline(rdp->cpu) &&
-	    ULONG_CMP_LT(rdp->rsp->gp_start + 2, jiffies)) {
-		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, "ofl");
-		rdp->offline_fqs++;
-		return 1;
-	}
-	return 0;
-}
-
-/*
  * rcu_idle_enter_common - inform RCU that current CPU is moving towards idle
  *
  * If the new value of the ->dynticks_nesting counter now is zero,
@@ -675,7 +650,7 @@
  * Return true if the specified CPU has passed through a quiescent
  * state by virtue of being in or having passed through an dynticks
  * idle state since the last call to dyntick_save_progress_counter()
- * for this same CPU.
+ * for this same CPU, or by virtue of having been offline.
  */
 static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 {
@@ -699,8 +674,26 @@
 		return 1;
 	}
 
-	/* Go check for the CPU being offline. */
-	return rcu_implicit_offline_qs(rdp);
+	/*
+	 * Check for the CPU being offline, but only if the grace period
+	 * is old enough.  We don't need to worry about the CPU changing
+	 * state: If we see it offline even once, it has been through a
+	 * quiescent state.
+	 *
+	 * The reason for insisting that the grace period be at least
+	 * one jiffy old is that CPUs that are not quite online and that
+	 * have just gone offline can still execute RCU read-side critical
+	 * sections.
+	 */
+	if (ULONG_CMP_GE(rdp->rsp->gp_start + 2, jiffies))
+		return 0;  /* Grace period is not old enough. */
+	barrier();
+	if (cpu_is_offline(rdp->cpu)) {
+		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, "ofl");
+		rdp->offline_fqs++;
+		return 1;
+	}
+	return 0;
 }
 
 static int jiffies_till_stall_check(void)
@@ -757,14 +750,15 @@
 	rcu_for_each_leaf_node(rsp, rnp) {
 		raw_spin_lock_irqsave(&rnp->lock, flags);
 		ndetected += rcu_print_task_stall(rnp);
+		if (rnp->qsmask != 0) {
+			for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++)
+				if (rnp->qsmask & (1UL << cpu)) {
+					print_cpu_stall_info(rsp,
+							     rnp->grplo + cpu);
+					ndetected++;
+				}
+		}
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
-		if (rnp->qsmask == 0)
-			continue;
-		for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++)
-			if (rnp->qsmask & (1UL << cpu)) {
-				print_cpu_stall_info(rsp, rnp->grplo + cpu);
-				ndetected++;
-			}
 	}
 
 	/*
@@ -784,11 +778,11 @@
 	else if (!trigger_all_cpu_backtrace())
 		dump_stack();
 
-	/* If so configured, complain about tasks blocking the grace period. */
+	/* Complain about tasks blocking the grace period. */
 
 	rcu_print_detail_task_stall(rsp);
 
-	force_quiescent_state(rsp, 0);  /* Kick them all. */
+	force_quiescent_state(rsp);  /* Kick them all. */
 }
 
 static void print_cpu_stall(struct rcu_state *rsp)
@@ -829,7 +823,8 @@
 	j = ACCESS_ONCE(jiffies);
 	js = ACCESS_ONCE(rsp->jiffies_stall);
 	rnp = rdp->mynode;
-	if ((ACCESS_ONCE(rnp->qsmask) & rdp->grpmask) && ULONG_CMP_GE(j, js)) {
+	if (rcu_gp_in_progress(rsp) &&
+	    (ACCESS_ONCE(rnp->qsmask) & rdp->grpmask) && ULONG_CMP_GE(j, js)) {
 
 		/* We haven't checked in, so go dump stack. */
 		print_cpu_stall(rsp);
@@ -891,12 +886,8 @@
 		 */
 		rdp->gpnum = rnp->gpnum;
 		trace_rcu_grace_period(rsp->name, rdp->gpnum, "cpustart");
-		if (rnp->qsmask & rdp->grpmask) {
-			rdp->qs_pending = 1;
-			rdp->passed_quiesce = 0;
-		} else {
-			rdp->qs_pending = 0;
-		}
+		rdp->passed_quiesce = 0;
+		rdp->qs_pending = !!(rnp->qsmask & rdp->grpmask);
 		zero_cpu_stall_ticks(rdp);
 	}
 }
@@ -976,10 +967,13 @@
 		 * our behalf. Catch up with this state to avoid noting
 		 * spurious new grace periods.  If another grace period
 		 * has started, then rnp->gpnum will have advanced, so
-		 * we will detect this later on.
+		 * we will detect this later on.  Of course, any quiescent
+		 * states we found for the old GP are now invalid.
 		 */
-		if (ULONG_CMP_LT(rdp->gpnum, rdp->completed))
+		if (ULONG_CMP_LT(rdp->gpnum, rdp->completed)) {
 			rdp->gpnum = rdp->completed;
+			rdp->passed_quiesce = 0;
+		}
 
 		/*
 		 * If RCU does not need a quiescent state from this CPU,
@@ -1023,25 +1017,220 @@
 	/* Prior grace period ended, so advance callbacks for current CPU. */
 	__rcu_process_gp_end(rsp, rnp, rdp);
 
-	/*
-	 * Because this CPU just now started the new grace period, we know
-	 * that all of its callbacks will be covered by this upcoming grace
-	 * period, even the ones that were registered arbitrarily recently.
-	 * Therefore, advance all outstanding callbacks to RCU_WAIT_TAIL.
-	 *
-	 * Other CPUs cannot be sure exactly when the grace period started.
-	 * Therefore, their recently registered callbacks must pass through
-	 * an additional RCU_NEXT_READY stage, so that they will be handled
-	 * by the next RCU grace period.
-	 */
-	rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
-	rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
-
 	/* Set state so that this CPU will detect the next quiescent state. */
 	__note_new_gpnum(rsp, rnp, rdp);
 }
 
 /*
+ * Initialize a new grace period.
+ */
+static int rcu_gp_init(struct rcu_state *rsp)
+{
+	struct rcu_data *rdp;
+	struct rcu_node *rnp = rcu_get_root(rsp);
+
+	raw_spin_lock_irq(&rnp->lock);
+	rsp->gp_flags = 0; /* Clear all flags: New grace period. */
+
+	if (rcu_gp_in_progress(rsp)) {
+		/* Grace period already in progress, don't start another.  */
+		raw_spin_unlock_irq(&rnp->lock);
+		return 0;
+	}
+
+	/* Advance to a new grace period and initialize state. */
+	rsp->gpnum++;
+	trace_rcu_grace_period(rsp->name, rsp->gpnum, "start");
+	record_gp_stall_check_time(rsp);
+	raw_spin_unlock_irq(&rnp->lock);
+
+	/* Exclude any concurrent CPU-hotplug operations. */
+	get_online_cpus();
+
+	/*
+	 * Set the quiescent-state-needed bits in all the rcu_node
+	 * structures for all currently online CPUs in breadth-first order,
+	 * starting from the root rcu_node structure, relying on the layout
+	 * of the tree within the rsp->node[] array.  Note that other CPUs
+	 * will access only the leaves of the hierarchy, thus seeing that no
+	 * grace period is in progress, at least until the corresponding
+	 * leaf node has been initialized.  In addition, we have excluded
+	 * CPU-hotplug operations.
+	 *
+	 * The grace period cannot complete until the initialization
+	 * process finishes, because this kthread handles both.
+	 */
+	rcu_for_each_node_breadth_first(rsp, rnp) {
+		raw_spin_lock_irq(&rnp->lock);
+		rdp = this_cpu_ptr(rsp->rda);
+		rcu_preempt_check_blocked_tasks(rnp);
+		rnp->qsmask = rnp->qsmaskinit;
+		rnp->gpnum = rsp->gpnum;
+		WARN_ON_ONCE(rnp->completed != rsp->completed);
+		rnp->completed = rsp->completed;
+		if (rnp == rdp->mynode)
+			rcu_start_gp_per_cpu(rsp, rnp, rdp);
+		rcu_preempt_boost_start_gp(rnp);
+		trace_rcu_grace_period_init(rsp->name, rnp->gpnum,
+					    rnp->level, rnp->grplo,
+					    rnp->grphi, rnp->qsmask);
+		raw_spin_unlock_irq(&rnp->lock);
+#ifdef CONFIG_PROVE_RCU_DELAY
+		if ((random32() % (rcu_num_nodes * 8)) == 0)
+			schedule_timeout_uninterruptible(2);
+#endif /* #ifdef CONFIG_PROVE_RCU_DELAY */
+		cond_resched();
+	}
+
+	put_online_cpus();
+	return 1;
+}
+
+/*
+ * Do one round of quiescent-state forcing.
+ */
+int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
+{
+	int fqs_state = fqs_state_in;
+	struct rcu_node *rnp = rcu_get_root(rsp);
+
+	rsp->n_force_qs++;
+	if (fqs_state == RCU_SAVE_DYNTICK) {
+		/* Collect dyntick-idle snapshots. */
+		force_qs_rnp(rsp, dyntick_save_progress_counter);
+		fqs_state = RCU_FORCE_QS;
+	} else {
+		/* Handle dyntick-idle and offline CPUs. */
+		force_qs_rnp(rsp, rcu_implicit_dynticks_qs);
+	}
+	/* Clear flag to prevent immediate re-entry. */
+	if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
+		raw_spin_lock_irq(&rnp->lock);
+		rsp->gp_flags &= ~RCU_GP_FLAG_FQS;
+		raw_spin_unlock_irq(&rnp->lock);
+	}
+	return fqs_state;
+}
+
+/*
+ * Clean up after the old grace period.
+ */
+static void rcu_gp_cleanup(struct rcu_state *rsp)
+{
+	unsigned long gp_duration;
+	struct rcu_data *rdp;
+	struct rcu_node *rnp = rcu_get_root(rsp);
+
+	raw_spin_lock_irq(&rnp->lock);
+	gp_duration = jiffies - rsp->gp_start;
+	if (gp_duration > rsp->gp_max)
+		rsp->gp_max = gp_duration;
+
+	/*
+	 * We know the grace period is complete, but to everyone else
+	 * it appears to still be ongoing.  But it is also the case
+	 * that to everyone else it looks like there is nothing that
+	 * they can do to advance the grace period.  It is therefore
+	 * safe for us to drop the lock in order to mark the grace
+	 * period as completed in all of the rcu_node structures.
+	 */
+	raw_spin_unlock_irq(&rnp->lock);
+
+	/*
+	 * Propagate new ->completed value to rcu_node structures so
+	 * that other CPUs don't have to wait until the start of the next
+	 * grace period to process their callbacks.  This also avoids
+	 * some nasty RCU grace-period initialization races by forcing
+	 * the end of the current grace period to be completely recorded in
+	 * all of the rcu_node structures before the beginning of the next
+	 * grace period is recorded in any of the rcu_node structures.
+	 */
+	rcu_for_each_node_breadth_first(rsp, rnp) {
+		raw_spin_lock_irq(&rnp->lock);
+		rnp->completed = rsp->gpnum;
+		raw_spin_unlock_irq(&rnp->lock);
+		cond_resched();
+	}
+	rnp = rcu_get_root(rsp);
+	raw_spin_lock_irq(&rnp->lock);
+
+	rsp->completed = rsp->gpnum; /* Declare grace period done. */
+	trace_rcu_grace_period(rsp->name, rsp->completed, "end");
+	rsp->fqs_state = RCU_GP_IDLE;
+	rdp = this_cpu_ptr(rsp->rda);
+	if (cpu_needs_another_gp(rsp, rdp))
+		rsp->gp_flags = 1;
+	raw_spin_unlock_irq(&rnp->lock);
+}
+
+/*
+ * Body of kthread that handles grace periods.
+ */
+static int __noreturn rcu_gp_kthread(void *arg)
+{
+	int fqs_state;
+	unsigned long j;
+	int ret;
+	struct rcu_state *rsp = arg;
+	struct rcu_node *rnp = rcu_get_root(rsp);
+
+	for (;;) {
+
+		/* Handle grace-period start. */
+		for (;;) {
+			wait_event_interruptible(rsp->gp_wq,
+						 rsp->gp_flags &
+						 RCU_GP_FLAG_INIT);
+			if ((rsp->gp_flags & RCU_GP_FLAG_INIT) &&
+			    rcu_gp_init(rsp))
+				break;
+			cond_resched();
+			flush_signals(current);
+		}
+
+		/* Handle quiescent-state forcing. */
+		fqs_state = RCU_SAVE_DYNTICK;
+		j = jiffies_till_first_fqs;
+		if (j > HZ) {
+			j = HZ;
+			jiffies_till_first_fqs = HZ;
+		}
+		for (;;) {
+			rsp->jiffies_force_qs = jiffies + j;
+			ret = wait_event_interruptible_timeout(rsp->gp_wq,
+					(rsp->gp_flags & RCU_GP_FLAG_FQS) ||
+					(!ACCESS_ONCE(rnp->qsmask) &&
+					 !rcu_preempt_blocked_readers_cgp(rnp)),
+					j);
+			/* If grace period done, leave loop. */
+			if (!ACCESS_ONCE(rnp->qsmask) &&
+			    !rcu_preempt_blocked_readers_cgp(rnp))
+				break;
+			/* If time for quiescent-state forcing, do it. */
+			if (ret == 0 || (rsp->gp_flags & RCU_GP_FLAG_FQS)) {
+				fqs_state = rcu_gp_fqs(rsp, fqs_state);
+				cond_resched();
+			} else {
+				/* Deal with stray signal. */
+				cond_resched();
+				flush_signals(current);
+			}
+			j = jiffies_till_next_fqs;
+			if (j > HZ) {
+				j = HZ;
+				jiffies_till_next_fqs = HZ;
+			} else if (j < 1) {
+				j = 1;
+				jiffies_till_next_fqs = 1;
+			}
+		}
+
+		/* Handle grace-period end. */
+		rcu_gp_cleanup(rsp);
+	}
+}
+
+/*
  * Start a new RCU grace period if warranted, re-initializing the hierarchy
  * in preparation for detecting the next grace period.  The caller must hold
  * the root node's ->lock, which is released before return.  Hard irqs must
@@ -1058,77 +1247,20 @@
 	struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
-	if (!rcu_scheduler_fully_active ||
+	if (!rsp->gp_kthread ||
 	    !cpu_needs_another_gp(rsp, rdp)) {
 		/*
-		 * Either the scheduler hasn't yet spawned the first
-		 * non-idle task or this CPU does not need another
-		 * grace period.  Either way, don't start a new grace
-		 * period.
+		 * Either we have not yet spawned the grace-period
+		 * task or this CPU does not need another grace period.
+		 * Either way, don't start a new grace period.
 		 */
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		return;
 	}
 
-	if (rsp->fqs_active) {
-		/*
-		 * This CPU needs a grace period, but force_quiescent_state()
-		 * is running.  Tell it to start one on this CPU's behalf.
-		 */
-		rsp->fqs_need_gp = 1;
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
-		return;
-	}
-
-	/* Advance to a new grace period and initialize state. */
-	rsp->gpnum++;
-	trace_rcu_grace_period(rsp->name, rsp->gpnum, "start");
-	WARN_ON_ONCE(rsp->fqs_state == RCU_GP_INIT);
-	rsp->fqs_state = RCU_GP_INIT; /* Hold off force_quiescent_state. */
-	rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS;
-	record_gp_stall_check_time(rsp);
-	raw_spin_unlock(&rnp->lock);  /* leave irqs disabled. */
-
-	/* Exclude any concurrent CPU-hotplug operations. */
-	raw_spin_lock(&rsp->onofflock);  /* irqs already disabled. */
-
-	/*
-	 * Set the quiescent-state-needed bits in all the rcu_node
-	 * structures for all currently online CPUs in breadth-first
-	 * order, starting from the root rcu_node structure.  This
-	 * operation relies on the layout of the hierarchy within the
-	 * rsp->node[] array.  Note that other CPUs will access only
-	 * the leaves of the hierarchy, which still indicate that no
-	 * grace period is in progress, at least until the corresponding
-	 * leaf node has been initialized.  In addition, we have excluded
-	 * CPU-hotplug operations.
-	 *
-	 * Note that the grace period cannot complete until we finish
-	 * the initialization process, as there will be at least one
-	 * qsmask bit set in the root node until that time, namely the
-	 * one corresponding to this CPU, due to the fact that we have
-	 * irqs disabled.
-	 */
-	rcu_for_each_node_breadth_first(rsp, rnp) {
-		raw_spin_lock(&rnp->lock);	/* irqs already disabled. */
-		rcu_preempt_check_blocked_tasks(rnp);
-		rnp->qsmask = rnp->qsmaskinit;
-		rnp->gpnum = rsp->gpnum;
-		rnp->completed = rsp->completed;
-		if (rnp == rdp->mynode)
-			rcu_start_gp_per_cpu(rsp, rnp, rdp);
-		rcu_preempt_boost_start_gp(rnp);
-		trace_rcu_grace_period_init(rsp->name, rnp->gpnum,
-					    rnp->level, rnp->grplo,
-					    rnp->grphi, rnp->qsmask);
-		raw_spin_unlock(&rnp->lock);	/* irqs remain disabled. */
-	}
-
-	rnp = rcu_get_root(rsp);
-	raw_spin_lock(&rnp->lock);		/* irqs already disabled. */
-	rsp->fqs_state = RCU_SIGNAL_INIT; /* force_quiescent_state now OK. */
-	raw_spin_unlock(&rnp->lock);		/* irqs remain disabled. */
-	raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
+	rsp->gp_flags = RCU_GP_FLAG_INIT;
+	raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	wake_up(&rsp->gp_wq);
 }
 
 /*
@@ -1141,57 +1273,9 @@
 static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
 	__releases(rcu_get_root(rsp)->lock)
 {
-	unsigned long gp_duration;
-	struct rcu_node *rnp = rcu_get_root(rsp);
-	struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
-
 	WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
-
-	/*
-	 * Ensure that all grace-period and pre-grace-period activity
-	 * is seen before the assignment to rsp->completed.
-	 */
-	smp_mb(); /* See above block comment. */
-	gp_duration = jiffies - rsp->gp_start;
-	if (gp_duration > rsp->gp_max)
-		rsp->gp_max = gp_duration;
-
-	/*
-	 * We know the grace period is complete, but to everyone else
-	 * it appears to still be ongoing.  But it is also the case
-	 * that to everyone else it looks like there is nothing that
-	 * they can do to advance the grace period.  It is therefore
-	 * safe for us to drop the lock in order to mark the grace
-	 * period as completed in all of the rcu_node structures.
-	 *
-	 * But if this CPU needs another grace period, it will take
-	 * care of this while initializing the next grace period.
-	 * We use RCU_WAIT_TAIL instead of the usual RCU_DONE_TAIL
-	 * because the callbacks have not yet been advanced: Those
-	 * callbacks are waiting on the grace period that just now
-	 * completed.
-	 */
-	if (*rdp->nxttail[RCU_WAIT_TAIL] == NULL) {
-		raw_spin_unlock(&rnp->lock);	 /* irqs remain disabled. */
-
-		/*
-		 * Propagate new ->completed value to rcu_node structures
-		 * so that other CPUs don't have to wait until the start
-		 * of the next grace period to process their callbacks.
-		 */
-		rcu_for_each_node_breadth_first(rsp, rnp) {
-			raw_spin_lock(&rnp->lock); /* irqs already disabled. */
-			rnp->completed = rsp->gpnum;
-			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
-		}
-		rnp = rcu_get_root(rsp);
-		raw_spin_lock(&rnp->lock); /* irqs already disabled. */
-	}
-
-	rsp->completed = rsp->gpnum;  /* Declare the grace period complete. */
-	trace_rcu_grace_period(rsp->name, rsp->completed, "end");
-	rsp->fqs_state = RCU_GP_IDLE;
-	rcu_start_gp(rsp, flags);  /* releases root node's rnp->lock. */
+	raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags);
+	wake_up(&rsp->gp_wq);  /* Memory barrier implied by wake_up() path. */
 }
 
 /*
@@ -1260,7 +1344,7 @@
  * based on quiescent states detected in an earlier grace period!
  */
 static void
-rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long lastgp)
+rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
 {
 	unsigned long flags;
 	unsigned long mask;
@@ -1268,7 +1352,8 @@
 
 	rnp = rdp->mynode;
 	raw_spin_lock_irqsave(&rnp->lock, flags);
-	if (lastgp != rnp->gpnum || rnp->completed == rnp->gpnum) {
+	if (rdp->passed_quiesce == 0 || rdp->gpnum != rnp->gpnum ||
+	    rnp->completed == rnp->gpnum) {
 
 		/*
 		 * The grace period in which this quiescent state was
@@ -1327,7 +1412,7 @@
 	 * Tell RCU we are done (but rcu_report_qs_rdp() will be the
 	 * judge of that).
 	 */
-	rcu_report_qs_rdp(rdp->cpu, rsp, rdp, rdp->passed_quiesce_gpnum);
+	rcu_report_qs_rdp(rdp->cpu, rsp, rdp);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -1676,6 +1761,7 @@
 	struct rcu_node *rnp;
 
 	rcu_for_each_leaf_node(rsp, rnp) {
+		cond_resched();
 		mask = 0;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
 		if (!rcu_gp_in_progress(rsp)) {
@@ -1712,72 +1798,39 @@
  * Force quiescent states on reluctant CPUs, and also detect which
  * CPUs are in dyntick-idle mode.
  */
-static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
+static void force_quiescent_state(struct rcu_state *rsp)
 {
 	unsigned long flags;
-	struct rcu_node *rnp = rcu_get_root(rsp);
+	bool ret;
+	struct rcu_node *rnp;
+	struct rcu_node *rnp_old = NULL;
 
-	trace_rcu_utilization("Start fqs");
-	if (!rcu_gp_in_progress(rsp)) {
-		trace_rcu_utilization("End fqs");
-		return;  /* No grace period in progress, nothing to force. */
+	/* Funnel through hierarchy to reduce memory contention. */
+	rnp = per_cpu_ptr(rsp->rda, raw_smp_processor_id())->mynode;
+	for (; rnp != NULL; rnp = rnp->parent) {
+		ret = (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) ||
+		      !raw_spin_trylock(&rnp->fqslock);
+		if (rnp_old != NULL)
+			raw_spin_unlock(&rnp_old->fqslock);
+		if (ret) {
+			rsp->n_force_qs_lh++;
+			return;
+		}
+		rnp_old = rnp;
 	}
-	if (!raw_spin_trylock_irqsave(&rsp->fqslock, flags)) {
-		rsp->n_force_qs_lh++; /* Inexact, can lose counts.  Tough! */
-		trace_rcu_utilization("End fqs");
-		return;	/* Someone else is already on the job. */
+	/* rnp_old == rcu_get_root(rsp), rnp == NULL. */
+
+	/* Reached the root of the rcu_node tree, acquire lock. */
+	raw_spin_lock_irqsave(&rnp_old->lock, flags);
+	raw_spin_unlock(&rnp_old->fqslock);
+	if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
+		rsp->n_force_qs_lh++;
+		raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
+		return;  /* Someone beat us to it. */
 	}
-	if (relaxed && ULONG_CMP_GE(rsp->jiffies_force_qs, jiffies))
-		goto unlock_fqs_ret; /* no emergency and done recently. */
-	rsp->n_force_qs++;
-	raw_spin_lock(&rnp->lock);  /* irqs already disabled */
-	rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS;
-	if(!rcu_gp_in_progress(rsp)) {
-		rsp->n_force_qs_ngp++;
-		raw_spin_unlock(&rnp->lock);  /* irqs remain disabled */
-		goto unlock_fqs_ret;  /* no GP in progress, time updated. */
-	}
-	rsp->fqs_active = 1;
-	switch (rsp->fqs_state) {
-	case RCU_GP_IDLE:
-	case RCU_GP_INIT:
-
-		break; /* grace period idle or initializing, ignore. */
-
-	case RCU_SAVE_DYNTICK:
-
-		raw_spin_unlock(&rnp->lock);  /* irqs remain disabled */
-
-		/* Record dyntick-idle state. */
-		force_qs_rnp(rsp, dyntick_save_progress_counter);
-		raw_spin_lock(&rnp->lock);  /* irqs already disabled */
-		if (rcu_gp_in_progress(rsp))
-			rsp->fqs_state = RCU_FORCE_QS;
-		break;
-
-	case RCU_FORCE_QS:
-
-		/* Check dyntick-idle state, send IPI to laggarts. */
-		raw_spin_unlock(&rnp->lock);  /* irqs remain disabled */
-		force_qs_rnp(rsp, rcu_implicit_dynticks_qs);
-
-		/* Leave state in case more forcing is required. */
-
-		raw_spin_lock(&rnp->lock);  /* irqs already disabled */
-		break;
-	}
-	rsp->fqs_active = 0;
-	if (rsp->fqs_need_gp) {
-		raw_spin_unlock(&rsp->fqslock); /* irqs remain disabled */
-		rsp->fqs_need_gp = 0;
-		rcu_start_gp(rsp, flags); /* releases rnp->lock */
-		trace_rcu_utilization("End fqs");
-		return;
-	}
-	raw_spin_unlock(&rnp->lock);  /* irqs remain disabled */
-unlock_fqs_ret:
-	raw_spin_unlock_irqrestore(&rsp->fqslock, flags);
-	trace_rcu_utilization("End fqs");
+	rsp->gp_flags |= RCU_GP_FLAG_FQS;
+	raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
+	wake_up(&rsp->gp_wq);  /* Memory barrier implied by wake_up() path. */
 }
 
 /*
@@ -1794,13 +1847,6 @@
 	WARN_ON_ONCE(rdp->beenonline == 0);
 
 	/*
-	 * If an RCU GP has gone long enough, go check for dyntick
-	 * idle CPUs and, if needed, send resched IPIs.
-	 */
-	if (ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs), jiffies))
-		force_quiescent_state(rsp, 1);
-
-	/*
 	 * Advance callbacks in response to end of earlier grace
 	 * period that some other CPU ended.
 	 */
@@ -1827,6 +1873,8 @@
 {
 	struct rcu_state *rsp;
 
+	if (cpu_is_offline(smp_processor_id()))
+		return;
 	trace_rcu_utilization("Start RCU core");
 	for_each_rcu_flavor(rsp)
 		__rcu_process_callbacks(rsp);
@@ -1898,12 +1946,11 @@
 			rdp->blimit = LONG_MAX;
 			if (rsp->n_force_qs == rdp->n_force_qs_snap &&
 			    *rdp->nxttail[RCU_DONE_TAIL] != head)
-				force_quiescent_state(rsp, 0);
+				force_quiescent_state(rsp);
 			rdp->n_force_qs_snap = rsp->n_force_qs;
 			rdp->qlen_last_fqs_check = rdp->qlen;
 		}
-	} else if (ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs), jiffies))
-		force_quiescent_state(rsp, 1);
+	}
 }
 
 static void
@@ -1918,8 +1965,6 @@
 	head->func = func;
 	head->next = NULL;
 
-	smp_mb(); /* Ensure RCU update seen before callback registry. */
-
 	/*
 	 * Opportunistically note grace-period endings and beginnings.
 	 * Note that we might see a beginning right after we see an
@@ -2190,17 +2235,7 @@
 	/* Is the RCU core waiting for a quiescent state from this CPU? */
 	if (rcu_scheduler_fully_active &&
 	    rdp->qs_pending && !rdp->passed_quiesce) {
-
-		/*
-		 * If force_quiescent_state() coming soon and this CPU
-		 * needs a quiescent state, and this is either RCU-sched
-		 * or RCU-bh, force a local reschedule.
-		 */
 		rdp->n_rp_qs_pending++;
-		if (!rdp->preemptible &&
-		    ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs) - 1,
-				 jiffies))
-			set_need_resched();
 	} else if (rdp->qs_pending && rdp->passed_quiesce) {
 		rdp->n_rp_report_qs++;
 		return 1;
@@ -2230,13 +2265,6 @@
 		return 1;
 	}
 
-	/* Has an RCU GP gone long enough to send resched IPIs &c? */
-	if (rcu_gp_in_progress(rsp) &&
-	    ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs), jiffies)) {
-		rdp->n_rp_need_fqs++;
-		return 1;
-	}
-
 	/* nothing to do */
 	rdp->n_rp_need_nothing++;
 	return 0;
@@ -2506,7 +2534,6 @@
 			rdp->completed = rnp->completed;
 			rdp->passed_quiesce = 0;
 			rdp->qs_pending = 0;
-			rdp->passed_quiesce_gpnum = rnp->gpnum - 1;
 			trace_rcu_grace_period(rsp->name, rdp->gpnum, "cpuonl");
 		}
 		raw_spin_unlock(&rnp->lock); /* irqs already disabled. */
@@ -2578,6 +2605,28 @@
 }
 
 /*
+ * Spawn the kthread that handles this RCU flavor's grace periods.
+ */
+static int __init rcu_spawn_gp_kthread(void)
+{
+	unsigned long flags;
+	struct rcu_node *rnp;
+	struct rcu_state *rsp;
+	struct task_struct *t;
+
+	for_each_rcu_flavor(rsp) {
+		t = kthread_run(rcu_gp_kthread, rsp, rsp->name);
+		BUG_ON(IS_ERR(t));
+		rnp = rcu_get_root(rsp);
+		raw_spin_lock_irqsave(&rnp->lock, flags);
+		rsp->gp_kthread = t;
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	}
+	return 0;
+}
+early_initcall(rcu_spawn_gp_kthread);
+
+/*
  * This function is invoked towards the end of the scheduler's initialization
  * process.  Before this is called, the idle task might contain
  * RCU read-side critical sections (during which time, this idle
@@ -2612,7 +2661,7 @@
 	int cprv;
 	int i;
 
-	cprv = NR_CPUS;
+	cprv = nr_cpu_ids;
 	for (i = rcu_num_lvls - 1; i >= 0; i--) {
 		ccur = rsp->levelcnt[i];
 		rsp->levelspread[i] = (cprv + ccur - 1) / ccur;
@@ -2627,10 +2676,14 @@
 static void __init rcu_init_one(struct rcu_state *rsp,
 		struct rcu_data __percpu *rda)
 {
-	static char *buf[] = { "rcu_node_level_0",
-			       "rcu_node_level_1",
-			       "rcu_node_level_2",
-			       "rcu_node_level_3" };  /* Match MAX_RCU_LVLS */
+	static char *buf[] = { "rcu_node_0",
+			       "rcu_node_1",
+			       "rcu_node_2",
+			       "rcu_node_3" };  /* Match MAX_RCU_LVLS */
+	static char *fqs[] = { "rcu_node_fqs_0",
+			       "rcu_node_fqs_1",
+			       "rcu_node_fqs_2",
+			       "rcu_node_fqs_3" };  /* Match MAX_RCU_LVLS */
 	int cpustride = 1;
 	int i;
 	int j;
@@ -2655,7 +2708,11 @@
 			raw_spin_lock_init(&rnp->lock);
 			lockdep_set_class_and_name(&rnp->lock,
 						   &rcu_node_class[i], buf[i]);
-			rnp->gpnum = 0;
+			raw_spin_lock_init(&rnp->fqslock);
+			lockdep_set_class_and_name(&rnp->fqslock,
+						   &rcu_fqs_class[i], fqs[i]);
+			rnp->gpnum = rsp->gpnum;
+			rnp->completed = rsp->completed;
 			rnp->qsmask = 0;
 			rnp->qsmaskinit = 0;
 			rnp->grplo = j * cpustride;
@@ -2678,6 +2735,7 @@
 	}
 
 	rsp->rda = rda;
+	init_waitqueue_head(&rsp->gp_wq);
 	rnp = rsp->level[rcu_num_lvls - 1];
 	for_each_possible_cpu(i) {
 		while (i > rnp->grphi)
@@ -2701,7 +2759,8 @@
 	int rcu_capacity[MAX_RCU_LVLS + 1];
 
 	/* If the compile-time values are accurate, just leave. */
-	if (rcu_fanout_leaf == CONFIG_RCU_FANOUT_LEAF)
+	if (rcu_fanout_leaf == CONFIG_RCU_FANOUT_LEAF &&
+	    nr_cpu_ids == NR_CPUS)
 		return;
 
 	/*
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 94dfdf1..3cf71ce 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -202,6 +202,7 @@
 				/*  per-CPU kthreads as needed. */
 	unsigned int node_kthread_status;
 				/* State of node_kthread_task for tracing. */
+	raw_spinlock_t fqslock ____cacheline_internodealigned_in_smp;
 } ____cacheline_internodealigned_in_smp;
 
 /*
@@ -245,8 +246,6 @@
 					/*  in order to detect GP end. */
 	unsigned long	gpnum;		/* Highest gp number that this CPU */
 					/*  is aware of having started. */
-	unsigned long	passed_quiesce_gpnum;
-					/* gpnum at time of quiescent state. */
 	bool		passed_quiesce;	/* User-mode/idle loop etc. */
 	bool		qs_pending;	/* Core waits for quiesc state. */
 	bool		beenonline;	/* CPU online at least once. */
@@ -312,11 +311,13 @@
 	unsigned long n_rp_cpu_needs_gp;
 	unsigned long n_rp_gp_completed;
 	unsigned long n_rp_gp_started;
-	unsigned long n_rp_need_fqs;
 	unsigned long n_rp_need_nothing;
 
-	/* 6) _rcu_barrier() callback. */
+	/* 6) _rcu_barrier() and OOM callbacks. */
 	struct rcu_head barrier_head;
+#ifdef CONFIG_RCU_FAST_NO_HZ
+	struct rcu_head oom_head;
+#endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
 
 	int cpu;
 	struct rcu_state *rsp;
@@ -375,20 +376,17 @@
 
 	u8	fqs_state ____cacheline_internodealigned_in_smp;
 						/* Force QS state. */
-	u8	fqs_active;			/* force_quiescent_state() */
-						/*  is running. */
-	u8	fqs_need_gp;			/* A CPU was prevented from */
-						/*  starting a new grace */
-						/*  period because */
-						/*  force_quiescent_state() */
-						/*  was running. */
 	u8	boost;				/* Subject to priority boost. */
 	unsigned long gpnum;			/* Current gp number. */
 	unsigned long completed;		/* # of last completed gp. */
+	struct task_struct *gp_kthread;		/* Task for grace periods. */
+	wait_queue_head_t gp_wq;		/* Where GP task waits. */
+	int gp_flags;				/* Commands for GP task. */
 
 	/* End of fields guarded by root rcu_node's lock. */
 
-	raw_spinlock_t onofflock;		/* exclude on/offline and */
+	raw_spinlock_t onofflock ____cacheline_internodealigned_in_smp;
+						/* exclude on/offline and */
 						/*  starting new GP. */
 	struct rcu_head *orphan_nxtlist;	/* Orphaned callbacks that */
 						/*  need a grace period. */
@@ -403,8 +401,6 @@
 	struct completion barrier_completion;	/* Wake at barrier end. */
 	unsigned long n_barrier_done;		/* ++ at start and end of */
 						/*  _rcu_barrier(). */
-	raw_spinlock_t fqslock;			/* Only one task forcing */
-						/*  quiescent states. */
 	unsigned long jiffies_force_qs;		/* Time at which to invoke */
 						/*  force_quiescent_state(). */
 	unsigned long n_force_qs;		/* Number of calls to */
@@ -423,6 +419,10 @@
 	struct list_head flavors;		/* List of RCU flavors. */
 };
 
+/* Values for rcu_state structure's gp_flags field. */
+#define RCU_GP_FLAG_INIT 0x1	/* Need grace-period initialization. */
+#define RCU_GP_FLAG_FQS  0x2	/* Need grace-period quiescent-state forcing. */
+
 extern struct list_head rcu_struct_flavors;
 #define for_each_rcu_flavor(rsp) \
 	list_for_each_entry((rsp), &rcu_struct_flavors, flavors)
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 7f3244c..46d7d6c 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -25,6 +25,7 @@
  */
 
 #include <linux/delay.h>
+#include <linux/oom.h>
 
 #define RCU_KTHREAD_PRIO 1
 
@@ -118,7 +119,7 @@
  */
 void rcu_force_quiescent_state(void)
 {
-	force_quiescent_state(&rcu_preempt_state, 0);
+	force_quiescent_state(&rcu_preempt_state);
 }
 EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
 
@@ -136,8 +137,6 @@
 {
 	struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu);
 
-	rdp->passed_quiesce_gpnum = rdp->gpnum;
-	barrier();
 	if (rdp->passed_quiesce == 0)
 		trace_rcu_grace_period("rcu_preempt", rdp->gpnum, "cpuqs");
 	rdp->passed_quiesce = 1;
@@ -422,9 +421,11 @@
 	unsigned long flags;
 	struct task_struct *t;
 
-	if (!rcu_preempt_blocked_readers_cgp(rnp))
-		return;
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	if (!rcu_preempt_blocked_readers_cgp(rnp)) {
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		return;
+	}
 	t = list_entry(rnp->gp_tasks,
 		       struct task_struct, rcu_node_entry);
 	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry)
@@ -584,17 +585,23 @@
 		raw_spin_unlock(&rnp_root->lock); /* irqs still disabled */
 	}
 
+	rnp->gp_tasks = NULL;
+	rnp->exp_tasks = NULL;
 #ifdef CONFIG_RCU_BOOST
-	/* In case root is being boosted and leaf is not. */
+	rnp->boost_tasks = NULL;
+	/*
+	 * In case root is being boosted and leaf was not.  Make sure
+	 * that we boost the tasks blocking the current grace period
+	 * in this case.
+	 */
 	raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
 	if (rnp_root->boost_tasks != NULL &&
-	    rnp_root->boost_tasks != rnp_root->gp_tasks)
+	    rnp_root->boost_tasks != rnp_root->gp_tasks &&
+	    rnp_root->boost_tasks != rnp_root->exp_tasks)
 		rnp_root->boost_tasks = rnp_root->gp_tasks;
 	raw_spin_unlock(&rnp_root->lock); /* irqs still disabled */
 #endif /* #ifdef CONFIG_RCU_BOOST */
 
-	rnp->gp_tasks = NULL;
-	rnp->exp_tasks = NULL;
 	return retval;
 }
 
@@ -676,7 +683,7 @@
 EXPORT_SYMBOL_GPL(synchronize_rcu);
 
 static DECLARE_WAIT_QUEUE_HEAD(sync_rcu_preempt_exp_wq);
-static long sync_rcu_preempt_exp_count;
+static unsigned long sync_rcu_preempt_exp_count;
 static DEFINE_MUTEX(sync_rcu_preempt_exp_mutex);
 
 /*
@@ -791,7 +798,7 @@
 	unsigned long flags;
 	struct rcu_node *rnp;
 	struct rcu_state *rsp = &rcu_preempt_state;
-	long snap;
+	unsigned long snap;
 	int trycount = 0;
 
 	smp_mb(); /* Caller's modifications seen first by other CPUs. */
@@ -799,33 +806,47 @@
 	smp_mb(); /* Above access cannot bleed into critical section. */
 
 	/*
+	 * Block CPU-hotplug operations.  This means that any CPU-hotplug
+	 * operation that finds an rcu_node structure with tasks in the
+	 * process of being boosted will know that all tasks blocking
+	 * this expedited grace period will already be in the process of
+	 * being boosted.  This simplifies the process of moving tasks
+	 * from leaf to root rcu_node structures.
+	 */
+	get_online_cpus();
+
+	/*
 	 * Acquire lock, falling back to synchronize_rcu() if too many
 	 * lock-acquisition failures.  Of course, if someone does the
 	 * expedited grace period for us, just leave.
 	 */
 	while (!mutex_trylock(&sync_rcu_preempt_exp_mutex)) {
+		if (ULONG_CMP_LT(snap,
+		    ACCESS_ONCE(sync_rcu_preempt_exp_count))) {
+			put_online_cpus();
+			goto mb_ret; /* Others did our work for us. */
+		}
 		if (trycount++ < 10) {
 			udelay(trycount * num_online_cpus());
 		} else {
+			put_online_cpus();
 			synchronize_rcu();
 			return;
 		}
-		if ((ACCESS_ONCE(sync_rcu_preempt_exp_count) - snap) > 0)
-			goto mb_ret; /* Others did our work for us. */
 	}
-	if ((ACCESS_ONCE(sync_rcu_preempt_exp_count) - snap) > 0)
+	if (ULONG_CMP_LT(snap, ACCESS_ONCE(sync_rcu_preempt_exp_count))) {
+		put_online_cpus();
 		goto unlock_mb_ret; /* Others did our work for us. */
+	}
 
 	/* force all RCU readers onto ->blkd_tasks lists. */
 	synchronize_sched_expedited();
 
-	raw_spin_lock_irqsave(&rsp->onofflock, flags);
-
 	/* Initialize ->expmask for all non-leaf rcu_node structures. */
 	rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) {
-		raw_spin_lock(&rnp->lock); /* irqs already disabled. */
+		raw_spin_lock_irqsave(&rnp->lock, flags);
 		rnp->expmask = rnp->qsmaskinit;
-		raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	}
 
 	/* Snapshot current state of ->blkd_tasks lists. */
@@ -834,7 +855,7 @@
 	if (NUM_RCU_NODES > 1)
 		sync_rcu_preempt_exp_init(rsp, rcu_get_root(rsp));
 
-	raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
+	put_online_cpus();
 
 	/* Wait for snapshotted ->blkd_tasks lists to drain. */
 	rnp = rcu_get_root(rsp);
@@ -1191,9 +1212,9 @@
  * kthread to start boosting them.  If there is an expedited grace
  * period in progress, it is always time to boost.
  *
- * The caller must hold rnp->lock, which this function releases,
- * but irqs remain disabled.  The ->boost_kthread_task is immortal,
- * so we don't need to worry about it going away.
+ * The caller must hold rnp->lock, which this function releases.
+ * The ->boost_kthread_task is immortal, so we don't need to worry
+ * about it going away.
  */
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
 {
@@ -2075,16 +2096,16 @@
 #ifdef CONFIG_TREE_PREEMPT_RCU
 	if (per_cpu(rcu_preempt_data, cpu).nxtlist) {
 		rcu_preempt_qs(cpu);
-		force_quiescent_state(&rcu_preempt_state, 0);
+		force_quiescent_state(&rcu_preempt_state);
 	}
 #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
 	if (per_cpu(rcu_sched_data, cpu).nxtlist) {
 		rcu_sched_qs(cpu);
-		force_quiescent_state(&rcu_sched_state, 0);
+		force_quiescent_state(&rcu_sched_state);
 	}
 	if (per_cpu(rcu_bh_data, cpu).nxtlist) {
 		rcu_bh_qs(cpu);
-		force_quiescent_state(&rcu_bh_state, 0);
+		force_quiescent_state(&rcu_bh_state);
 	}
 
 	/*
@@ -2112,6 +2133,88 @@
 	__this_cpu_add(rcu_dynticks.nonlazy_posted, 1);
 }
 
+/*
+ * Data for flushing lazy RCU callbacks at OOM time.
+ */
+static atomic_t oom_callback_count;
+static DECLARE_WAIT_QUEUE_HEAD(oom_callback_wq);
+
+/*
+ * RCU OOM callback -- decrement the outstanding count and deliver the
+ * wake-up if we are the last one.
+ */
+static void rcu_oom_callback(struct rcu_head *rhp)
+{
+	if (atomic_dec_and_test(&oom_callback_count))
+		wake_up(&oom_callback_wq);
+}
+
+/*
+ * Post an rcu_oom_notify callback on the current CPU if it has at
+ * least one lazy callback.  This will unnecessarily post callbacks
+ * to CPUs that already have a non-lazy callback at the end of their
+ * callback list, but this is an infrequent operation, so accept some
+ * extra overhead to keep things simple.
+ */
+static void rcu_oom_notify_cpu(void *unused)
+{
+	struct rcu_state *rsp;
+	struct rcu_data *rdp;
+
+	for_each_rcu_flavor(rsp) {
+		rdp = __this_cpu_ptr(rsp->rda);
+		if (rdp->qlen_lazy != 0) {
+			atomic_inc(&oom_callback_count);
+			rsp->call(&rdp->oom_head, rcu_oom_callback);
+		}
+	}
+}
+
+/*
+ * If low on memory, ensure that each CPU has a non-lazy callback.
+ * This will wake up CPUs that have only lazy callbacks, in turn
+ * ensuring that they free up the corresponding memory in a timely manner.
+ * Because an uncertain amount of memory will be freed in some uncertain
+ * timeframe, we do not claim to have freed anything.
+ */
+static int rcu_oom_notify(struct notifier_block *self,
+			  unsigned long notused, void *nfreed)
+{
+	int cpu;
+
+	/* Wait for callbacks from earlier instance to complete. */
+	wait_event(oom_callback_wq, atomic_read(&oom_callback_count) == 0);
+
+	/*
+	 * Prevent premature wakeup: ensure that all increments happen
+	 * before there is a chance of the counter reaching zero.
+	 */
+	atomic_set(&oom_callback_count, 1);
+
+	get_online_cpus();
+	for_each_online_cpu(cpu) {
+		smp_call_function_single(cpu, rcu_oom_notify_cpu, NULL, 1);
+		cond_resched();
+	}
+	put_online_cpus();
+
+	/* Unconditionally decrement: no need to wake ourselves up. */
+	atomic_dec(&oom_callback_count);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block rcu_oom_nb = {
+	.notifier_call = rcu_oom_notify
+};
+
+static int __init rcu_register_oom_notifier(void)
+{
+	register_oom_notifier(&rcu_oom_nb);
+	return 0;
+}
+early_initcall(rcu_register_oom_notifier);
+
 #endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */
 
 #ifdef CONFIG_RCU_CPU_STALL_INFO
@@ -2122,11 +2225,15 @@
 {
 	struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
 	struct timer_list *tltp = &rdtp->idle_gp_timer;
+	char c;
 
-	sprintf(cp, "drain=%d %c timer=%lu",
-		rdtp->dyntick_drain,
-		rdtp->dyntick_holdoff == jiffies ? 'H' : '.',
-		timer_pending(tltp) ? tltp->expires - jiffies : -1);
+	c = rdtp->dyntick_holdoff == jiffies ? 'H' : '.';
+	if (timer_pending(tltp))
+		sprintf(cp, "drain=%d %c timer=%lu",
+			rdtp->dyntick_drain, c, tltp->expires - jiffies);
+	else
+		sprintf(cp, "drain=%d %c timer not pending",
+			rdtp->dyntick_drain, c);
 }
 
 #else /* #ifdef CONFIG_RCU_FAST_NO_HZ */
@@ -2194,11 +2301,10 @@
 /* Increment ->ticks_this_gp for all flavors of RCU. */
 static void increment_cpu_stall_ticks(void)
 {
-	__get_cpu_var(rcu_sched_data).ticks_this_gp++;
-	__get_cpu_var(rcu_bh_data).ticks_this_gp++;
-#ifdef CONFIG_TREE_PREEMPT_RCU
-	__get_cpu_var(rcu_preempt_data).ticks_this_gp++;
-#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
+	struct rcu_state *rsp;
+
+	for_each_rcu_flavor(rsp)
+		__this_cpu_ptr(rsp->rda)->ticks_this_gp++;
 }
 
 #else /* #ifdef CONFIG_RCU_CPU_STALL_INFO */
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index 6a2e52a..7340efd 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -86,12 +86,11 @@
 {
 	if (!rdp->beenonline)
 		return;
-	seq_printf(m, "%3d%cc=%lu g=%lu pq=%d pgp=%lu qp=%d",
+	seq_printf(m, "%3d%cc=%lu g=%lu pq=%d qp=%d",
 		   rdp->cpu,
 		   cpu_is_offline(rdp->cpu) ? '!' : ' ',
 		   rdp->completed, rdp->gpnum,
-		   rdp->passed_quiesce, rdp->passed_quiesce_gpnum,
-		   rdp->qs_pending);
+		   rdp->passed_quiesce, rdp->qs_pending);
 	seq_printf(m, " dt=%d/%llx/%d df=%lu",
 		   atomic_read(&rdp->dynticks->dynticks),
 		   rdp->dynticks->dynticks_nesting,
@@ -150,12 +149,11 @@
 {
 	if (!rdp->beenonline)
 		return;
-	seq_printf(m, "%d,%s,%lu,%lu,%d,%lu,%d",
+	seq_printf(m, "%d,%s,%lu,%lu,%d,%d",
 		   rdp->cpu,
 		   cpu_is_offline(rdp->cpu) ? "\"N\"" : "\"Y\"",
 		   rdp->completed, rdp->gpnum,
-		   rdp->passed_quiesce, rdp->passed_quiesce_gpnum,
-		   rdp->qs_pending);
+		   rdp->passed_quiesce, rdp->qs_pending);
 	seq_printf(m, ",%d,%llx,%d,%lu",
 		   atomic_read(&rdp->dynticks->dynticks),
 		   rdp->dynticks->dynticks_nesting,
@@ -186,7 +184,7 @@
 	int cpu;
 	struct rcu_state *rsp;
 
-	seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pgp\",\"pq\",");
+	seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pq\",");
 	seq_puts(m, "\"dt\",\"dt nesting\",\"dt NMI nesting\",\"df\",");
 	seq_puts(m, "\"of\",\"qll\",\"ql\",\"qs\"");
 #ifdef CONFIG_RCU_BOOST
@@ -386,10 +384,9 @@
 		   rdp->n_rp_report_qs,
 		   rdp->n_rp_cb_ready,
 		   rdp->n_rp_cpu_needs_gp);
-	seq_printf(m, "gpc=%ld gps=%ld nf=%ld nn=%ld\n",
+	seq_printf(m, "gpc=%ld gps=%ld nn=%ld\n",
 		   rdp->n_rp_gp_completed,
 		   rdp->n_rp_gp_started,
-		   rdp->n_rp_need_fqs,
 		   rdp->n_rp_need_nothing);
 }
 
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 024540f..4b1785a 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -436,7 +436,8 @@
 	if (unlikely(local_softirq_pending() && cpu_online(cpu))) {
 		static int ratelimit;
 
-		if (ratelimit < 10) {
+		if (ratelimit < 10 &&
+		    (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) {
 			printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
 			       (unsigned int) local_softirq_pending());
 			ratelimit++;
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 2403a63..dacbbe4 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -629,6 +629,20 @@
 
 	 Say N if you are unsure.
 
+config PROVE_RCU_DELAY
+	bool "RCU debugging: preemptible RCU race provocation"
+	depends on DEBUG_KERNEL && PREEMPT_RCU
+	default n
+	help
+	 There is a class of races that involve an unlikely preemption
+	 of __rcu_read_unlock() just after ->rcu_read_lock_nesting has
+	 been set to INT_MIN.  This feature inserts a delay at that
+	 point to increase the probability of these races.
+
+	 Say Y to increase probability of preemption of __rcu_read_unlock().
+
+	 Say N if you are unsure.
+
 config SPARSE_RCU_POINTER
 	bool "RCU debugging: sparse-based checks for pointer usage"
 	default n
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 45eb621..0de83b4 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1483,13 +1483,11 @@
 {
 	struct kmemleak_object *prev_obj = v;
 	struct kmemleak_object *next_obj = NULL;
-	struct list_head *n = &prev_obj->object_list;
+	struct kmemleak_object *obj = prev_obj;
 
 	++(*pos);
 
-	list_for_each_continue_rcu(n, &object_list) {
-		struct kmemleak_object *obj =
-			list_entry(n, struct kmemleak_object, object_list);
+	list_for_each_entry_continue_rcu(obj, &object_list, object_list) {
 		if (get_object(obj)) {
 			next_obj = obj;
 			break;