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

Pull RCU changes from Ingo Molnar:

 0. 'idle RCU':

     Adds RCU APIs that allow non-idle tasks to enter RCU idle mode and
     provides x86 code to make use of them, allowing RCU to treat
     user-mode execution as an extended quiescent state when the new
     RCU_USER_QS kernel configuration parameter is specified.  (Work is
     in progress to port this to a few other architectures, but is not
     part of this series.)

 1.  A fix for a latent bug that has been in RCU ever since the addition
     of CPU stall warnings.  This bug results in false-positive stall
     warnings, but thus far only on embedded systems with severely
     cut-down userspace configurations.

 2.  Further reductions in latency spikes for huge systems, along with
     additional boot-time adaptation to the actual hardware.

     This is a large change, as it moves RCU grace-period initialization
     and cleanup, along with quiescent-state forcing, from softirq to a
     kthread.  However, it appears to be in quite good shape (famous
     last words).

 3.  Updates to documentation and rcutorture, the latter category
     including keeping statistics on CPU-hotplug latencies and fixing
     some initialization-time races.

 4.  CPU-hotplug fixes and improvements.

 5.  Idle-loop fixes that were omitted on an earlier submission.

 6.  Miscellaneous fixes and improvements

In certain RCU configurations new kernel threads will show up (rcu_bh,
rcu_sched), showing RCU processing overhead.

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (90 commits)
  rcu: Apply micro-optimization and int/bool fixes to RCU's idle handling
  rcu: Userspace RCU extended QS selftest
  x86: Exit RCU extended QS on notify resume
  x86: Use the new schedule_user API on userspace preemption
  rcu: Exit RCU extended QS on user preemption
  rcu: Exit RCU extended QS on kernel preemption after irq/exception
  x86: Exception hooks for userspace RCU extended QS
  x86: Unspaghettize do_general_protection()
  x86: Syscall hooks for userspace RCU extended QS
  rcu: Switch task's syscall hooks on context switch
  rcu: Ignore userspace extended quiescent state by default
  rcu: Allow rcu_user_enter()/exit() to nest
  rcu: Settle config for userspace extended quiescent state
  rcu: Make RCU_FAST_NO_HZ handle adaptive ticks
  rcu: New rcu_user_enter_after_irq() and rcu_user_exit_after_irq() APIs
  rcu: New rcu_user_enter() and rcu_user_exit() APIs
  ia64: Add missing RCU idle APIs on idle loop
  xtensa: Add missing RCU idle APIs on idle loop
  score: Add missing RCU idle APIs on idle loop
  parisc: Add missing RCU idle APIs on idle loop
  ...

Documentation/RCU/checklist.txt

@@ -310,6 +310,12 @@ over a rather long period of time, but improvements are always welcome!
 	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

Documentation/RCU/stallwarn.txt

@@ -99,7 +99,7 @@ In kernels with CONFIG_RCU_FAST_NO_HZ, even more information is
 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 @@ number between the two "/"s is the value of the nesting, which will
 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

Documentation/RCU/trace.txt

@@ -333,23 +333,23 @@ o	Each element of the form "1/1 0:127 ^0" represents one struct
 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	"gpc" is the number of times that an old grace period had
 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

Documentation/RCU/whatisRCU.txt

@@ -873,7 +873,7 @@ d.	Do you need to treat NMI handlers, hardirq handlers,
 	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 @@ f.	Is your workload too update-intensive for normal use of
 	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.

Documentation/kernel-parameters.txt

@@ -2385,6 +2385,17 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	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.
 

arch/Kconfig

@@ -281,4 +281,14 @@ config SECCOMP_FILTER
 
 	  See Documentation/prctl/seccomp_filter.txt for details.
 
+config HAVE_RCU_USER_QS
+	bool
+	help
+	  Provide kernel entry/exit hooks necessary for userspace
+	  RCU extended quiescent state. Syscalls need to be wrapped inside
+	  rcu_user_exit()-rcu_user_enter() through the slow path using
+	  TIF_NOHZ flag. Exceptions handlers must be wrapped as well. Irqs
+	  are already protected inside rcu_irq_enter/rcu_irq_exit() but
+	  preemption or signal handling on irq exit still need to be protected.
+
 source "kernel/gcov/Kconfig"

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 @@ cpu_idle(void)
 		/* 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();
 	}
 }
 

arch/alpha/kernel/smp.c

@@ -166,6 +166,7 @@ smp_callin(void)
 	DBGS(("smp_callin: commencing CPU %d current %p active_mm %p\n",
 	      cpuid, current, current->active_mm));
 
+	preempt_disable();
 	/* Do nothing.  */
 	cpu_idle();
 }

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 @@ void cpu_idle (void)
 {
 	/* endless idle loop with no priority at all */
 	while (1) {
+		rcu_idle_enter();
 		while (!need_resched()) {
 			void (*idle)(void);
 			/*
@@ -86,6 +88,7 @@ void cpu_idle (void)
 				idle = default_idle;
 			idle();
 		}
+		rcu_idle_exit();
 		schedule_preempt_disabled();
 	}
 }

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 @@ void cpu_idle(void)
 {
 	/* 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();
 	}

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 (*idle)(void) = default_idle;
 void cpu_idle(void)
 {
 	while (1) {
+		rcu_idle_enter();
 		while (!need_resched())
 			idle();
+		rcu_idle_exit();
 		schedule_preempt_disabled();
 	}
 }

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 @@ cpu_idle (void)
 
 	/* 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 @@ cpu_idle (void)
 			normal_xtp();
 #endif
 		}
+		rcu_idle_exit();
 		schedule_preempt_disabled();
 		check_pgt_cache();
 		if (cpu_is_offline(cpu))

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 @@ void cpu_idle (void)
 {
 	/* 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 @@ void cpu_idle (void)
 
 			idle();
 		}
+		rcu_idle_exit();
 		schedule_preempt_disabled();
 	}
 }

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 @@ void cpu_idle(void)
 {
 	/* endless idle loop with no priority at all */
 	while (1) {
+		rcu_idle_enter();
 		while (!need_resched())
 			idle();
+		rcu_idle_exit();
 		schedule_preempt_disabled();
 	}
 }

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 @@ void cpu_idle(void)
 {
 	/* endless idle loop with no priority at all */
 	for (;;) {
+		rcu_idle_enter();
 		while (!need_resched()) {
 			void (*idle)(void);
 
@@ -121,6 +123,7 @@ void cpu_idle(void)
 			}
 			idle();
 		}
+		rcu_idle_exit();
 
 		schedule_preempt_disabled();
 	}

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 @@ void cpu_idle(void)
 
 	/* 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();
 	}

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 @@ void __noreturn cpu_idle(void)
 {
 	/* endless idle loop with no priority at all */
 	while (1) {
+		rcu_idle_enter();
 		while (!need_resched())
 			barrier();
-
+		rcu_idle_exit();
 		schedule_preempt_disabled();
 	}
 }

arch/um/drivers/mconsole_kern.c

@@ -705,6 +705,7 @@ static void stack_proc(void *arg)
 	struct task_struct *from = current, *to = arg;
 
 	to->thread.saved_task = from;
+	rcu_switch(from, to);
 	switch_to(from, to, from);
 }
 

arch/x86/Kconfig

@@ -97,6 +97,7 @@ config X86
 	select KTIME_SCALAR if X86_32
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
+	select HAVE_RCU_USER_QS if X86_64
 
 config INSTRUCTION_DECODER
 	def_bool (KPROBES || PERF_EVENTS || UPROBES)

arch/x86/include/asm/rcu.h

+#ifndef _ASM_X86_RCU_H
+#define _ASM_X86_RCU_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/rcupdate.h>
+#include <asm/ptrace.h>
+
+static inline void exception_enter(struct pt_regs *regs)
+{
+	rcu_user_exit();
+}
+
+static inline void exception_exit(struct pt_regs *regs)
+{
+#ifdef CONFIG_RCU_USER_QS
+	if (user_mode(regs))
+		rcu_user_enter();
+#endif
+}
+
+#else /* __ASSEMBLY__ */
+
+#ifdef CONFIG_RCU_USER_QS
+# define SCHEDULE_USER call schedule_user
+#else
+# define SCHEDULE_USER call schedule
+#endif
+
+#endif /* !__ASSEMBLY__ */
+
+#endif

arch/x86/include/asm/thread_info.h

@@ -89,6 +89,7 @@ struct thread_info {
 #define TIF_NOTSC		16	/* TSC is not accessible in userland */
 #define TIF_IA32		17	/* IA32 compatibility process */
 #define TIF_FORK		18	/* ret_from_fork */
+#define TIF_NOHZ		19	/* in adaptive nohz mode */
 #define TIF_MEMDIE		20	/* is terminating due to OOM killer */
 #define TIF_DEBUG		21	/* uses debug registers */
 #define TIF_IO_BITMAP		22	/* uses I/O bitmap */
@@ -114,6 +115,7 @@ struct thread_info {
 #define _TIF_NOTSC		(1 << TIF_NOTSC)
 #define _TIF_IA32		(1 << TIF_IA32)
 #define _TIF_FORK		(1 << TIF_FORK)
+#define _TIF_NOHZ		(1 << TIF_NOHZ)
 #define _TIF_DEBUG		(1 << TIF_DEBUG)
 #define _TIF_IO_BITMAP		(1 << TIF_IO_BITMAP)
 #define _TIF_FORCED_TF		(1 << TIF_FORCED_TF)
@@ -126,12 +128,13 @@ struct thread_info {
 /* work to do in syscall_trace_enter() */
 #define _TIF_WORK_SYSCALL_ENTRY	\
 	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | _TIF_SYSCALL_AUDIT |	\
-	 _TIF_SECCOMP | _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT)
+	 _TIF_SECCOMP | _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT |	\
+	 _TIF_NOHZ)
 
 /* work to do in syscall_trace_leave() */
 #define _TIF_WORK_SYSCALL_EXIT	\
 	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP |	\
-	 _TIF_SYSCALL_TRACEPOINT)
+	 _TIF_SYSCALL_TRACEPOINT | _TIF_NOHZ)
 
 /* work to do on interrupt/exception return */
 #define _TIF_WORK_MASK							\
@@ -141,7 +144,8 @@ struct thread_info {
 
 /* work to do on any return to user space */
 #define _TIF_ALLWORK_MASK						\
-	((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_TRACEPOINT)
+	((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_TRACEPOINT |	\
+	_TIF_NOHZ)
 
 /* Only used for 64 bit */
 #define _TIF_DO_NOTIFY_MASK						\

arch/x86/kernel/cpuid.c

@@ -199,12 +199,14 @@ static int __init cpuid_init(void)
 		goto out_chrdev;
 	}
 	cpuid_class->devnode = cpuid_devnode;
+	get_online_cpus();
 	for_each_online_cpu(i) {
 		err = cpuid_device_create(i);
 		if (err != 0)
 			goto out_class;
 	}
 	register_hotcpu_notifier(&cpuid_class_cpu_notifier);
+	put_online_cpus();
 
 	err = 0;
 	goto out;
@@ -214,6 +216,7 @@ static int __init cpuid_init(void)
 	for_each_online_cpu(i) {
 		cpuid_device_destroy(i);
 	}
+	put_online_cpus();
 	class_destroy(cpuid_class);
 out_chrdev:
 	__unregister_chrdev(CPUID_MAJOR, 0, NR_CPUS, "cpu/cpuid");
@@ -225,11 +228,13 @@ static void __exit cpuid_exit(void)
 {
 	int cpu = 0;
 
+	get_online_cpus();
 	for_each_online_cpu(cpu)
 		cpuid_device_destroy(cpu);
 	class_destroy(cpuid_class);
 	__unregister_chrdev(CPUID_MAJOR, 0, NR_CPUS, "cpu/cpuid");
 	unregister_hotcpu_notifier(&cpuid_class_cpu_notifier);
+	put_online_cpus();
 }
 
 module_init(cpuid_init);

arch/x86/kernel/entry_64.S

@@ -56,6 +56,7 @@
 #include <asm/ftrace.h>
 #include <asm/percpu.h>
 #include <asm/asm.h>
+#include <asm/rcu.h>
 #include <linux/err.h>
 
 /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
@@ -565,7 +566,7 @@ sysret_careful:
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
 	pushq_cfi %rdi
-	call schedule
+	SCHEDULE_USER
 	popq_cfi %rdi
 	jmp sysret_check
 
@@ -678,7 +679,7 @@ int_careful:
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
 	pushq_cfi %rdi
-	call schedule
+	SCHEDULE_USER
 	popq_cfi %rdi
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
@@ -974,7 +975,7 @@ retint_careful:
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
 	pushq_cfi %rdi
-	call  schedule
+	SCHEDULE_USER
 	popq_cfi %rdi
 	GET_THREAD_INFO(%rcx)
 	DISABLE_INTERRUPTS(CLBR_NONE)
@@ -1449,7 +1450,7 @@ paranoid_userspace:
 paranoid_schedule:
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_ANY)
-	call schedule
+	SCHEDULE_USER
 	DISABLE_INTERRUPTS(CLBR_ANY)
 	TRACE_IRQS_OFF
 	jmp paranoid_userspace

arch/x86/kernel/msr.c

@@ -257,12 +257,14 @@ static int __init msr_init(void)
 		goto out_chrdev;
 	}
 	msr_class->devnode = msr_devnode;
+	get_online_cpus();
 	for_each_online_cpu(i) {
 		err = msr_device_create(i);
 		if (err != 0)
 			goto out_class;
 	}
 	register_hotcpu_notifier(&msr_class_cpu_notifier);
+	put_online_cpus();
 
 	err = 0;
 	goto out;
@@ -271,6 +273,7 @@ static int __init msr_init(void)
 	i = 0;
 	for_each_online_cpu(i)
 		msr_device_destroy(i);
+	put_online_cpus();
 	class_destroy(msr_class);
 out_chrdev:
 	__unregister_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr");
@@ -281,11 +284,13 @@ static int __init msr_init(void)
 static void __exit msr_exit(void)
 {
 	int cpu = 0;
+	get_online_cpus();
 	for_each_online_cpu(cpu)
 		msr_device_destroy(cpu);
 	class_destroy(msr_class);
 	__unregister_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr");
 	unregister_hotcpu_notifier(&msr_class_cpu_notifier);
+	put_online_cpus();
 }
 
 module_init(msr_init);

arch/x86/kernel/ptrace.c

@@ -21,6 +21,7 @@
 #include <linux/signal.h>
 #include <linux/perf_event.h>
 #include <linux/hw_breakpoint.h>
+#include <linux/rcupdate.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -1463,6 +1464,8 @@ long syscall_trace_enter(struct pt_regs *regs)
 {
 	long ret = 0;
 
+	rcu_user_exit();
+
 	/*
 	 * If we stepped into a sysenter/syscall insn, it trapped in
 	 * kernel mode; do_debug() cleared TF and set TIF_SINGLESTEP.
@@ -1526,4 +1529,6 @@ void syscall_trace_leave(struct pt_regs *regs)
 			!test_thread_flag(TIF_SYSCALL_EMU);
 	if (step || test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall_exit(regs, step);
+
+	rcu_user_enter();
 }

arch/x86/kernel/signal.c

@@ -779,6 +779,8 @@ static void do_signal(struct pt_regs *regs)
 void
 do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
 {
+	rcu_user_exit();
+
 #ifdef CONFIG_X86_MCE
 	/* notify userspace of pending MCEs */
 	if (thread_info_flags & _TIF_MCE_NOTIFY)
@@ -804,6 +806,8 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
 #ifdef CONFIG_X86_32
 	clear_thread_flag(TIF_IRET);
 #endif /* CONFIG_X86_32 */
+
+	rcu_user_enter();
 }
 
 void signal_fault(struct pt_regs *regs, void __user *frame, char *where)

arch/x86/kernel/traps.c

@@ -55,6 +55,7 @@
 #include <asm/i387.h>
 #include <asm/fpu-internal.h>
 #include <asm/mce.h>
+#include <asm/rcu.h>
 
 #include <asm/mach_traps.h>
 
@@ -180,11 +181,15 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
 #define DO_ERROR(trapnr, signr, str, name)				\
 dotraplinkage void do_##name(struct pt_regs *regs, long error_code)	\
 {									\
-	if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr)	\
-							== NOTIFY_STOP)	\
+	exception_enter(regs);						\
+	if (notify_die(DIE_TRAP, str, regs, error_code,			\
+			trapnr, signr) == NOTIFY_STOP) {		\
+		exception_exit(regs);					\
 		return;							\
+	}								\
 	conditional_sti(regs);						\
 	do_trap(trapnr, signr, str, regs, error_code, NULL);		\
+	exception_exit(regs);						\
 }
 
 #define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr)		\
@@ -195,11 +200,15 @@ dotraplinkage void do_##name(struct pt_regs *regs, long error_code)	\
 	info.si_errno = 0;						\
 	info.si_code = sicode;						\
 	info.si_addr = (void __user *)siaddr;				\
-	if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr)	\
-							== NOTIFY_STOP)	\
+	exception_enter(regs);						\
+	if (notify_die(DIE_TRAP, str, regs, error_code,			\
+			trapnr, signr) == NOTIFY_STOP) {		\
+		exception_exit(regs);					\
 		return;							\
+	}								\
 	conditional_sti(regs);						\
 	do_trap(trapnr, signr, str, regs, error_code, &info);		\
+	exception_exit(regs);						\
 }
 
 DO_ERROR_INFO(X86_TRAP_DE, SIGFPE, "divide error", divide_error, FPE_INTDIV,
@@ -222,12 +231,14 @@ DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check,
 /* Runs on IST stack */
 dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code)
 {
+	exception_enter(regs);
 	if (notify_die(DIE_TRAP, "stack segment", regs, error_code,
-			X86_TRAP_SS, SIGBUS) == NOTIFY_STOP)
-		return;
-	preempt_conditional_sti(regs);
-	do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL);
-	preempt_conditional_cli(regs);
+		       X86_TRAP_SS, SIGBUS) != NOTIFY_STOP) {
+		preempt_conditional_sti(regs);
+		do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL);
+		preempt_conditional_cli(regs);
+	}
+	exception_exit(regs);
 }
 
 dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
@@ -235,6 +246,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 	static const char str[] = "double fault";
 	struct task_struct *tsk = current;
 
+	exception_enter(regs);
 	/* Return not checked because double check cannot be ignored */
 	notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);
 
@@ -255,16 +267,29 @@ do_general_protection(struct pt_regs *regs, long error_code)
 {
 	struct task_struct *tsk;
 
+	exception_enter(regs);
 	conditional_sti(regs);
 
 #ifdef CONFIG_X86_32
-	if (regs->flags & X86_VM_MASK)
-		goto gp_in_vm86;
+	if (regs->flags & X86_VM_MASK) {
+		local_irq_enable();
+		handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code);
+		goto exit;
+	}
 #endif
 
 	tsk = current;
-	if (!user_mode(regs))
-		goto gp_in_kernel;
+	if (!user_mode(regs)) {
+		if (fixup_exception(regs))
+			goto exit;
+
+		tsk->thread.error_code = error_code;
+		tsk->thread.trap_nr = X86_TRAP_GP;
+		if (notify_die(DIE_GPF, "general protection fault", regs, error_code,
+			       X86_TRAP_GP, SIGSEGV) != NOTIFY_STOP)
+			die("general protection fault", regs, error_code);
+		goto exit;
+	}
 
 	tsk->thread.error_code = error_code;
 	tsk->thread.trap_nr = X86_TRAP_GP;
@@ -279,25 +304,8 @@ do_general_protection(struct pt_regs *regs, long error_code)
 	}
 
 	force_sig(SIGSEGV, tsk);
-	return;
-
-#ifdef CONFIG_X86_32
-gp_in_vm86:
-	local_irq_enable();
-	handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code);
-	return;
-#endif
-
-gp_in_kernel:
-	if (fixup_exception(regs))
-		return;
-
-	tsk->thread.error_code = error_code;
-	tsk->thread.trap_nr = X86_TRAP_GP;
-	if (notify_die(DIE_GPF, "general protection fault", regs, error_code,
-			X86_TRAP_GP, SIGSEGV) == NOTIFY_STOP)
-		return;
-	die("general protection fault", regs, error_code);
+exit:
+	exception_exit(regs);
 }
 
 /* May run on IST stack. */
@@ -312,15 +320,16 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co
 	    ftrace_int3_handler(regs))
 		return;
 #endif
+	exception_enter(regs);
 #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
 	if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
 				SIGTRAP) == NOTIFY_STOP)
-		return;
+		goto exit;
 #endif /* CONFIG_KGDB_LOW_LEVEL_TRAP */
 
 	if (notify_die(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
 			SIGTRAP) == NOTIFY_STOP)
-		return;
+		goto exit;
 
 	/*
 	 * Let others (NMI) know that the debug stack is in use
@@ -331,6 +340,8 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co
 	do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL);
 	preempt_conditional_cli(regs);
 	debug_stack_usage_dec();
+exit:
+	exception_exit(regs);
 }
 
 #ifdef CONFIG_X86_64
@@ -391,6 +402,8 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
 	unsigned long dr6;
 	int si_code;
 
+	exception_enter(regs);
+
 	get_debugreg(dr6, 6);
 
 	/* Filter out all the reserved bits which are preset to 1 */
@@ -406,7 +419,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
 
 	/* Catch kmemcheck conditions first of all! */
 	if ((dr6 & DR_STEP) && kmemcheck_trap(regs))
-		return;
+		goto exit;
 
 	/* DR6 may or may not be cleared by the CPU */
 	set_debugreg(0, 6);
@@ -421,7 +434,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
 
 	if (notify_die(DIE_DEBUG, "debug", regs, PTR_ERR(&dr6), error_code,
 							SIGTRAP) == NOTIFY_STOP)
-		return;
+		goto exit;
 
 	/*
 	 * Let others (NMI) know that the debug stack is in use
@@ -437,7 +450,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
 					X86_TRAP_DB);
 		preempt_conditional_cli(regs);
 		debug_stack_usage_dec();
-		return;
+		goto exit;
 	}
 
 	/*
@@ -458,7 +471,8 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
 	preempt_conditional_cli(regs);
 	debug_stack_usage_dec();
 
-	return;
+exit:
+	exception_exit(regs);
 }
 
 /*
@@ -555,14 +569,17 @@ dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code)
 #ifdef CONFIG_X86_32
 	ignore_fpu_irq = 1;
 #endif
-
+	exception_enter(regs);
 	math_error(regs, error_code, X86_TRAP_MF);
+	exception_exit(regs);
 }
 
 dotraplinkage void
 do_simd_coprocessor_error(struct pt_regs *regs, long error_code)
 {
+	exception_enter(regs);
 	math_error(regs, error_code, X86_TRAP_XF);
+	exception_exit(regs);
 }
 
 dotraplinkage void
@@ -629,6 +646,7 @@ EXPORT_SYMBOL_GPL(math_state_restore);
 dotraplinkage void __kprobes
 do_device_not_available(struct pt_regs *regs, long error_code)
 {
+	exception_enter(regs);
 #ifdef CONFIG_MATH_EMULATION
 	if (read_cr0() & X86_CR0_EM) {
 		struct math_emu_info info = { };
@@ -637,6 +655,7 @@ do_device_not_available(struct pt_regs *regs, long error_code)
 
 		info.regs = regs;
 		math_emulate(&info);
+		exception_exit(regs);
 		return;
 	}
 #endif
@@ -644,12 +663,15 @@ do_device_not_available(struct pt_regs *regs, long error_code)
 #ifdef CONFIG_X86_32
 	conditional_sti(regs);
 #endif
+	exception_exit(regs);
 }
 
 #ifdef CONFIG_X86_32
 dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
 {
 	siginfo_t info;
+
+	exception_enter(regs);
 	local_irq_enable();
 
 	info.si_signo = SIGILL;
@@ -657,10 +679,11 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
 	info.si_code = ILL_BADSTK;
 	info.si_addr = NULL;
 	if (notify_die(DIE_TRAP, "iret exception", regs, error_code,
-			X86_TRAP_IRET, SIGILL) == NOTIFY_STOP)
-		return;
-	do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code,
-		&info);
+			X86_TRAP_IRET, SIGILL) != NOTIFY_STOP) {
+		do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code,
+			&info);
+	}
+	exception_exit(regs);
 }
 #endif
 

arch/x86/mm/fault.c

@@ -18,6 +18,7 @@
 #include <asm/pgalloc.h>		/* pgd_*(), ...			*/
 #include <asm/kmemcheck.h>		/* kmemcheck_*(), ...		*/
 #include <asm/fixmap.h>			/* VSYSCALL_START		*/
+#include <asm/rcu.h>			/* exception_enter(), ...	*/
 
 /*
  * Page fault error code bits:
@@ -1000,8 +1001,8 @@ static int fault_in_kernel_space(unsigned long address)
  * and the problem, and then passes it off to one of the appropriate
  * routines.
  */
-dotraplinkage void __kprobes
-do_page_fault(struct pt_regs *regs, unsigned long error_code)
+static void __kprobes
+__do_page_fault(struct pt_regs *regs, unsigned long error_code)
 {
 	struct vm_area_struct *vma;
 	struct task_struct *tsk;
@@ -1209,3 +1210,11 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code)
 
 	up_read(&mm->mmap_sem);
 }
+
+dotraplinkage void __kprobes
+do_page_fault(struct pt_regs *regs, unsigned long error_code)
+{
+	exception_enter(regs);
+	__do_page_fault(regs, error_code);
+	exception_exit(regs);
+}

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 @@ void cpu_idle(void)
 
 	/* endless idle loop with no priority at all */
 	while (1) {
+		rcu_idle_enter();
 		while (!need_resched())
 			platform_idle();
+		rcu_idle_exit();
 		schedule_preempt_disabled();
 	}
 }

drivers/infiniband/hw/ehca/ehca_irq.c

@@ -42,6 +42,7 @@
  */
 
 #include <linux/slab.h>
+#include <linux/smpboot.h>
 
 #include "ehca_classes.h"
 #include "ehca_irq.h"
@@ -652,7 +653,7 @@ void ehca_tasklet_eq(unsigned long data)
 	ehca_process_eq((struct ehca_shca*)data, 1);
 }
 
-static inline int find_next_online_cpu(struct ehca_comp_pool *pool)
+static int find_next_online_cpu(struct ehca_comp_pool *pool)
 {
 	int cpu;
 	unsigned long flags;
@@ -662,17 +663,20 @@ static inline int find_next_online_cpu(struct ehca_comp_pool *pool)
 		ehca_dmp(cpu_online_mask, cpumask_size(), "");
 
 	spin_lock_irqsave(&pool->last_cpu_lock, flags);
-	cpu = cpumask_next(pool->last_cpu, cpu_online_mask);
-	if (cpu >= nr_cpu_ids)
-		cpu = cpumask_first(cpu_online_mask);
-	pool->last_cpu = cpu;
+	do {
+		cpu = cpumask_next(pool->last_cpu, cpu_online_mask);
+		if (cpu >= nr_cpu_ids)
+			cpu = cpumask_first(cpu_online_mask);
+		pool->last_cpu = cpu;
+	} while (!per_cpu_ptr(pool->cpu_comp_tasks, cpu)->active);
 	spin_unlock_irqrestore(&pool->last_cpu_lock, flags);
 
 	return cpu;
 }
 
 static void __queue_comp_task(struct ehca_cq *__cq,
-			      struct ehca_cpu_comp_task *cct)
+			      struct ehca_cpu_comp_task *cct,
+			      struct task_struct *thread)
 {
 	unsigned long flags;
 
@@ -683,7 +687,7 @@ static void __queue_comp_task(struct ehca_cq *__cq,
 		__cq->nr_callbacks++;
 		list_add_tail(&__cq->entry, &cct->cq_list);
 		cct->cq_jobs++;
-		wake_up(&cct->wait_queue);
+		wake_up_process(thread);
 	} else
 		__cq->nr_callbacks++;
 
@@ -695,6 +699,7 @@ static void queue_comp_task(struct ehca_cq *__cq)
 {
 	int cpu_id;
 	struct ehca_cpu_comp_task *cct;
+	struct task_struct *thread;
 	int cq_jobs;
 	unsigned long flags;
 
@@ -702,7 +707,8 @@ static void queue_comp_task(struct ehca_cq *__cq)
 	BUG_ON(!cpu_online(cpu_id));
 
 	cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu_id);
-	BUG_ON(!cct);
+	thread = *per_cpu_ptr(pool->cpu_comp_threads, cpu_id);
+	BUG_ON(!cct || !thread);
 
 	spin_lock_irqsave(&cct->task_lock, flags);
 	cq_jobs = cct->cq_jobs;
@@ -710,28 +716,25 @@ static void queue_comp_task(struct ehca_cq *__cq)
 	if (cq_jobs > 0) {
 		cpu_id = find_next_online_cpu(pool);
 		cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu_id);
-		BUG_ON(!cct);
+		thread = *per_cpu_ptr(pool->cpu_comp_threads, cpu_id);
+		BUG_ON(!cct || !thread);
 	}
-
-	__queue_comp_task(__cq, cct);
+	__queue_comp_task(__cq, cct, thread);
 }
 
 static void run_comp_task(struct ehca_cpu_comp_task *cct)
 {
 	struct ehca_cq *cq;
-	unsigned long flags;
-
-	spin_lock_irqsave(&cct->task_lock, flags);
 
 	while (!list_empty(&cct->cq_list)) {
 		cq = list_entry(cct->cq_list.next, struct ehca_cq, entry);
-		spin_unlock_irqrestore(&cct->task_lock, flags);
+		spin_unlock_irq(&cct->task_lock);
 
 		comp_event_callback(cq);
 		if (atomic_dec_and_test(&cq->nr_events))
 			wake_up(&cq->wait_completion);
 
-		spin_lock_irqsave(&cct->task_lock, flags);
+		spin_lock_irq(&cct->task_lock);
 		spin_lock(&cq->task_lock);
 		cq->nr_callbacks--;
 		if (!cq->nr_callbacks) {
@@ -740,159 +743,76 @@ static void run_comp_task(struct ehca_cpu_comp_task *cct)
 		}
 		spin_unlock(&cq->task_lock);
 	}
-
-	spin_unlock_irqrestore(&cct->task_lock, flags);
 }
 
-static int comp_task(void *__cct)
+static void comp_task_park(unsigned int cpu)
 {
-	struct ehca_cpu_comp_task *cct = __cct;
-	int cql_empty;
-	DECLARE_WAITQUEUE(wait, current);
-
-	set_current_state(TASK_INTERRUPTIBLE);
-	while (!kthread_should_stop()) {
-		add_wait_queue(&cct->wait_queue, &wait);
-
-		spin_lock_irq(&cct->task_lock);
-		cql_empty = list_empty(&cct->cq_list);
-		spin_unlock_irq(&cct->task_lock);
-		if (cql_empty)
-			schedule();
-		else
-			__set_current_state(TASK_RUNNING);
-
-		remove_wait_queue(&cct->wait_queue, &wait);
+	struct ehca_cpu_comp_task *cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
+	struct ehca_cpu_comp_task *target;
+	struct task_struct *thread;
+	struct ehca_cq *cq, *tmp;
+	LIST_HEAD(list);
 
-		spin_lock_irq(&cct->task_lock);
-		cql_empty = list_empty(&cct->cq_list);
-		spin_unlock_irq(&cct->task_lock);
-		if (!cql_empty)
-			run_comp_task(__cct);
+	spin_lock_irq(&cct->task_lock);
+	cct->cq_jobs = 0;
+	cct->active = 0;
+	list_splice_init(&cct->cq_list, &list);
+	spin_unlock_irq(&cct->task_lock);
 
-		set_current_state(TASK_INTERRUPTIBLE);
+	cpu = find_next_online_cpu(pool);
+	target = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
+	thread = *per_cpu_ptr(pool->cpu_comp_threads, cpu);
+	spin_lock_irq(&target->task_lock);
+	list_for_each_entry_safe(cq, tmp, &list, entry) {
+		list_del(&cq->entry);
+		__queue_comp_task(cq, target, thread);
 	}
-	__set_current_state(TASK_RUNNING);
-
-	return 0;
-}
-
-static struct task_struct *create_comp_task(struct ehca_comp_pool *pool,
-					    int cpu)
-{
-	struct ehca_cpu_comp_task *cct;
-
-	cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
-	spin_lock_init(&cct->task_lock);
-	INIT_LIST_HEAD(&cct->cq_list);
-	init_waitqueue_head(&cct->wait_queue);
-	cct->task = kthread_create_on_node(comp_task, cct, cpu_to_node(cpu),
-					   "ehca_comp/%d", cpu);
-
-	return cct->task;
+	spin_unlock_irq(&target->task_lock);
 }
 
-static void destroy_comp_task(struct ehca_comp_pool *pool,
-			      int cpu)
+static void comp_task_stop(unsigned int cpu, bool online)
 {
-	struct ehca_cpu_comp_task *cct;
-	struct task_struct *task;
-	unsigned long flags_cct;
-
-	cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
-
-	spin_lock_irqsave(&cct->task_lock, flags_cct);
+	struct ehca_cpu_comp_task *cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
 
-	task = cct->task;
-	cct->task = NULL;
+	spin_lock_irq(&cct->task_lock);
 	cct->cq_jobs = 0;
-
-	spin_unlock_irqrestore(&cct->task_lock, flags_cct);
-
-	if (task)
-		kthread_stop(task);
+	cct->active = 0;
+	WARN_ON(!list_empty(&cct->cq_list));
+	spin_unlock_irq(&cct->task_lock);
 }
 
-static void __cpuinit take_over_work(struct ehca_comp_pool *pool, int cpu)
+static int comp_task_should_run(unsigned int cpu)
 {
 	struct ehca_cpu_comp_task *cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
-	LIST_HEAD(list);
-	struct ehca_cq *cq;
-	unsigned long flags_cct;
-
-	spin_lock_irqsave(&cct->task_lock, flags_cct);
-
-	list_splice_init(&cct->cq_list, &list);
-
-	while (!list_empty(&list)) {
-		cq = list_entry(cct->cq_list.next, struct ehca_cq, entry);
-
-		list_del(&cq->entry);
-		__queue_comp_task(cq, this_cpu_ptr(pool->cpu_comp_tasks));
-	}
-
-	spin_unlock_irqrestore(&cct->task_lock, flags_cct);
 
+	return cct->cq_jobs;
 }
 
-static int __cpuinit comp_pool_callback(struct notifier_block *nfb,
-					unsigned long action,
-					void *hcpu)
+static void comp_task(unsigned int cpu)
 {
-	unsigned int cpu = (unsigned long)hcpu;
-	struct ehca_cpu_comp_task *cct;
+	struct ehca_cpu_comp_task *cct = this_cpu_ptr(pool->cpu_comp_tasks);
+	int cql_empty;
 
-	switch (action) {
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
-		ehca_gen_dbg("CPU: %x (CPU_PREPARE)", cpu);
-		if (!create_comp_task(pool, cpu)) {
-			ehca_gen_err("Can't create comp_task for cpu: %x", cpu);
-			return notifier_from_errno(-ENOMEM);
-		}
-		break;
-	case CPU_UP_CANCELED:
-	case CPU_UP_CANCELED_FROZEN:
-		ehca_gen_dbg("CPU: %x (CPU_CANCELED)", cpu);
-		cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
-		kthread_bind(cct->task, cpumask_any(cpu_online_mask));
-		destroy_comp_task(pool, cpu);
-		break;
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		ehca_gen_dbg("CPU: %x (CPU_ONLINE)", cpu);
-		cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
-		kthread_bind(cct->task, cpu);
-		wake_up_process(cct->task);
-		break;
-	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
-		ehca_gen_dbg("CPU: %x (CPU_DOWN_PREPARE)", cpu);
-		break;
-	case CPU_DOWN_FAILED:
-	case CPU_DOWN_FAILED_FROZEN:
-		ehca_gen_dbg("CPU: %x (CPU_DOWN_FAILED)", cpu);
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		ehca_gen_dbg("CPU: %x (CPU_DEAD)", cpu);
-		destroy_comp_task(pool, cpu);
-		take_over_work(pool, cpu);
-		break;
+	spin_lock_irq(&cct->task_lock);
+	cql_empty = list_empty(&cct->cq_list);
+	if (!cql_empty) {
+		__set_current_state(TASK_RUNNING);
+		run_comp_task(cct);
 	}
-
-	return NOTIFY_OK;
+	spin_unlock_irq(&cct->task_lock);
 }
 
-static struct notifier_block comp_pool_callback_nb __cpuinitdata = {
-	.notifier_call	= comp_pool_callback,
-	.priority	= 0,
+static struct smp_hotplug_thread comp_pool_threads = {
+	.thread_should_run	= comp_task_should_run,
+	.thread_fn		= comp_task,
+	.thread_comm		= "ehca_comp/%u",
+	.cleanup		= comp_task_stop,
+	.park			= comp_task_park,
 };
 
 int ehca_create_comp_pool(void)
 {
-	int cpu;
-	struct task_struct *task;
+	int cpu, ret = -ENOMEM;
 
 	if (!ehca_scaling_code)
 		return 0;
@@ -905,38 +825,46 @@ int ehca_create_comp_pool(void)
 	pool->last_cpu = cpumask_any(cpu_online_mask);
 
 	pool->cpu_comp_tasks = alloc_percpu(struct ehca_cpu_comp_task);
-	if (pool->cpu_comp_tasks == NULL) {
-		kfree(pool);
-		return -EINVAL;
-	}
+	if (!pool->cpu_comp_tasks)
+		goto out_pool;
 
-	for_each_online_cpu(cpu) {
-		task = create_comp_task(pool, cpu);
-		if (task) {
-			kthread_bind(task, cpu);
-			wake_up_process(task);
-		}
+	pool->cpu_comp_threads = alloc_percpu(struct task_struct *);
+	if (!pool->cpu_comp_threads)
+		goto out_tasks;
+
+	for_each_present_cpu(cpu) {
+		struct ehca_cpu_comp_task *cct;
+
+		cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
+		spin_lock_init(&cct->task_lock);
+		INIT_LIST_HEAD(&cct->cq_list);
 	}
 
-	register_hotcpu_notifier(&comp_pool_callback_nb);
+	comp_pool_threads.store = pool->cpu_comp_threads;
+	ret = smpboot_register_percpu_thread(&comp_pool_threads);
+	if (ret)
+		goto out_threads;
 
-	printk(KERN_INFO "eHCA scaling code enabled\n");
+	pr_info("eHCA scaling code enabled\n");
+	return ret;
 
-	return 0;
+out_threads:
+	free_percpu(pool->cpu_comp_threads);
+out_tasks:
+	free_percpu(pool->cpu_comp_tasks);
+out_pool:
+	kfree(pool);
+	return ret;
 }
 
 void ehca_destroy_comp_pool(void)
 {
-	int i;
-
 	if (!ehca_scaling_code)
 		return;
 
-	unregister_hotcpu_notifier(&comp_pool_callback_nb);
-
-	for_each_online_cpu(i)
-		destroy_comp_task(pool, i);
+	smpboot_unregister_percpu_thread(&comp_pool_threads);
 
+	free_percpu(pool->cpu_comp_threads);
 	free_percpu(pool->cpu_comp_tasks);
 	kfree(pool);
 }

drivers/infiniband/hw/ehca/ehca_irq.h

@@ -58,15 +58,15 @@ void ehca_tasklet_eq(unsigned long data);
 void ehca_process_eq(struct ehca_shca *shca, int is_irq);
 
 struct ehca_cpu_comp_task {
-	wait_queue_head_t wait_queue;
 	struct list_head cq_list;
-	struct task_struct *task;
 	spinlock_t task_lock;
 	int cq_jobs;
+	int active;
 };
 
 struct ehca_comp_pool {
-	struct ehca_cpu_comp_task *cpu_comp_tasks;
+	struct ehca_cpu_comp_task __percpu *cpu_comp_tasks;
+	struct task_struct * __percpu *cpu_comp_threads;
 	int last_cpu;
 	spinlock_t last_cpu_lock;
 };

include/linux/interrupt.h

@@ -430,6 +430,8 @@ enum
 	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.
  */

include/linux/kthread.h

@@ -14,6 +14,11 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
 	kthread_create_on_node(threadfn, data, -1, namefmt, ##arg)
 
 
+struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data),
+					  void *data,
+					  unsigned int cpu,
+					  const char *namefmt);
+
 /**
  * kthread_run - create and wake a thread.
  * @threadfn: the function to run until signal_pending(current).
@@ -34,9 +39,13 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
 
 void kthread_bind(struct task_struct *k, unsigned int cpu);
 int kthread_stop(struct task_struct *k);
-int kthread_should_stop(void);
+bool kthread_should_stop(void);
+bool kthread_should_park(void);
 bool kthread_freezable_should_stop(bool *was_frozen);
 void *kthread_data(struct task_struct *k);
+int kthread_park(struct task_struct *k);
+void kthread_unpark(struct task_struct *k);
+void kthread_parkme(void);
 
 int kthreadd(void *unused);
 extern struct task_struct *kthreadd_task;

include/linux/rcupdate.h

@@ -191,6 +191,21 @@ extern void rcu_idle_enter(void);
 extern void rcu_idle_exit(void);
 extern void rcu_irq_enter(void);
 extern void rcu_irq_exit(void);
+
+#ifdef CONFIG_RCU_USER_QS
+extern void rcu_user_enter(void);
+extern void rcu_user_exit(void);
+extern void rcu_user_enter_after_irq(void);
+extern void rcu_user_exit_after_irq(void);
+extern void rcu_user_hooks_switch(struct task_struct *prev,
+				  struct task_struct *next);
+#else
+static inline void rcu_user_enter(void) { }
+static inline void rcu_user_exit(void) { }
+static inline void rcu_user_enter_after_irq(void) { }
+static inline void rcu_user_exit_after_irq(void) { }
+#endif /* CONFIG_RCU_USER_QS */
+
 extern void exit_rcu(void);
 
 /**
@@ -210,14 +225,12 @@ extern void exit_rcu(void);
  * 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)
 
 /*

include/linux/sched.h

@@ -1885,6 +1885,14 @@ static inline void rcu_copy_process(struct task_struct *p)
 
 #endif
 
+static inline void rcu_switch(struct task_struct *prev,
+			      struct task_struct *next)
+{
+#ifdef CONFIG_RCU_USER_QS
+	rcu_user_hooks_switch(prev, next);
+#endif
+}
+
 static inline void tsk_restore_flags(struct task_struct *task,
 				unsigned long orig_flags, unsigned long flags)
 {

include/linux/smpboot.h

+#ifndef _LINUX_SMPBOOT_H
+#define _LINUX_SMPBOOT_H
+
+#include <linux/types.h>
+
+struct task_struct;
+/* Cookie handed to the thread_fn*/
+struct smpboot_thread_data;
+
+/**
+ * struct smp_hotplug_thread - CPU hotplug related thread descriptor
+ * @store:		Pointer to per cpu storage for the task pointers
+ * @list:		List head for core management
+ * @thread_should_run:	Check whether the thread should run or not. Called with
+ *			preemption disabled.
+ * @thread_fn:		The associated thread function
+ * @setup:		Optional setup function, called when the thread gets
+ *			operational the first time
+ * @cleanup:		Optional cleanup function, called when the thread
+ *			should stop (module exit)
+ * @park:		Optional park function, called when the thread is
+ *			parked (cpu offline)
+ * @unpark:		Optional unpark function, called when the thread is
+ *			unparked (cpu online)
+ * @thread_comm:	The base name of the thread
+ */
+struct smp_hotplug_thread {
+	struct task_struct __percpu	**store;
+	struct list_head		list;
+	int				(*thread_should_run)(unsigned int cpu);
+	void				(*thread_fn)(unsigned int cpu);
+	void				(*setup)(unsigned int cpu);
+	void				(*cleanup)(unsigned int cpu, bool online);
+	void				(*park)(unsigned int cpu);
+	void				(*unpark)(unsigned int cpu);
+	const char			*thread_comm;
+};
+
+int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread);
+void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread);
+int smpboot_thread_schedule(void);
+
+#endif

include/linux/tracepoint.h

@@ -136,6 +136,22 @@ static inline void tracepoint_synchronize_unregister(void)
 		postrcu;						\
 	} while (0)
 
+#ifndef MODULE
+#define __DECLARE_TRACE_RCU(name, proto, args, cond, data_proto, data_args)	\
+	static inline void trace_##name##_rcuidle(proto)		\
+	{								\
+		if (static_key_false(&__tracepoint_##name.key))		\
+			__DO_TRACE(&__tracepoint_##name,		\
+				TP_PROTO(data_proto),			\
+				TP_ARGS(data_args),			\
+				TP_CONDITION(cond),			\
+				rcu_idle_exit(),			\
+				rcu_idle_enter());			\
+	}
+#else
+#define __DECLARE_TRACE_RCU(name, proto, args, cond, data_proto, data_args)
+#endif
+
 /*
  * Make sure the alignment of the structure in the __tracepoints section will
  * not add unwanted padding between the beginning of the section and the
@@ -151,16 +167,8 @@ static inline void tracepoint_synchronize_unregister(void)
 				TP_ARGS(data_args),			\
 				TP_CONDITION(cond),,);			\
 	}								\
-	static inline void trace_##name##_rcuidle(proto)		\
-	{								\
-		if (static_key_false(&__tracepoint_##name.key))		\
-			__DO_TRACE(&__tracepoint_##name,		\
-				TP_PROTO(data_proto),			\
-				TP_ARGS(data_args),			\
-				TP_CONDITION(cond),			\
-				rcu_idle_exit(),			\
-				rcu_idle_enter());			\
-	}								\
+	__DECLARE_TRACE_RCU(name, PARAMS(proto), PARAMS(args),		\
+		PARAMS(cond), PARAMS(data_proto), PARAMS(data_args))	\
 	static inline int						\
 	register_trace_##name(void (*probe)(data_proto), void *data)	\
 	{								\

init/Kconfig

@@ -441,6 +441,24 @@ config PREEMPT_RCU
 	  This option enables preemptible-RCU code that is common between
 	  the TREE_PREEMPT_RCU and TINY_PREEMPT_RCU implementations.
 
+config RCU_USER_QS
+	bool "Consider userspace as in RCU extended quiescent state"
+	depends on HAVE_RCU_USER_QS && SMP
+	help
+	  This option sets hooks on kernel / userspace boundaries and
+	  puts RCU in extended quiescent state when the CPU runs in
+	  userspace. It means that when a CPU runs in userspace, it is
+	  excluded from the global RCU state machine and thus doesn't
+	  to keep the timer tick on for RCU.
+
+config RCU_USER_QS_FORCE
+	bool "Force userspace extended QS by default"
+	depends on RCU_USER_QS
+	help
+	  Set the hooks in user/kernel boundaries by default in order to
+	  test this feature that treats userspace as an extended quiescent
+	  state until we have a real user like a full adaptive nohz option.
+
 config RCU_FANOUT
 	int "Tree-based hierarchical RCU fanout value"
 	range 2 64 if 64BIT

kernel/Makefile

@@ -10,7 +10,7 @@ obj-y     = fork.o exec_domain.o panic.o printk.o \
 	    kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
 	    hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
 	    notifier.o ksysfs.o cred.o \
-	    async.o range.o groups.o lglock.o
+	    async.o range.o groups.o lglock.o smpboot.o
 
 ifdef CONFIG_FUNCTION_TRACER
 # Do not trace debug files and internal ftrace files
@@ -46,7 +46,6 @@ obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
 obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o
 obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o
 obj-$(CONFIG_SMP) += smp.o
-obj-$(CONFIG_SMP) += smpboot.o
 ifneq ($(CONFIG_SMP),y)
 obj-y += up.o
 endif

kernel/cpu.c

@@ -280,12 +280,13 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 				__func__, cpu);
 		goto out_release;
 	}
+	smpboot_park_threads(cpu);
 
 	err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
 	if (err) {
 		/* CPU didn't die: tell everyone.  Can't complain. */
+		smpboot_unpark_threads(cpu);
 		cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu);
-
 		goto out_release;
 	}
 	BUG_ON(cpu_online(cpu));
@@ -354,6 +355,10 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen)
 		goto out;
 	}
 
+	ret = smpboot_create_threads(cpu);
+	if (ret)
+		goto out;
+
 	ret = __cpu_notify(CPU_UP_PREPARE | mod, hcpu, -1, &nr_calls);
 	if (ret) {
 		nr_calls--;
@@ -368,6 +373,9 @@ static int __cpuinit _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/kthread.c

@@ -37,11 +37,20 @@ struct kthread_create_info
 };
 
 struct kthread {
-	int should_stop;
+	unsigned long flags;
+	unsigned int cpu;
 	void *data;
+	struct completion parked;
 	struct completion exited;
 };
 
+enum KTHREAD_BITS {
+	KTHREAD_IS_PER_CPU = 0,
+	KTHREAD_SHOULD_STOP,
+	KTHREAD_SHOULD_PARK,
+	KTHREAD_IS_PARKED,
+};
+
 #define to_kthread(tsk)	\
 	container_of((tsk)->vfork_done, struct kthread, exited)
 
@@ -52,12 +61,28 @@ struct kthread {
  * and this will return true.  You should then return, and your return
  * value will be passed through to kthread_stop().
  */
-int kthread_should_stop(void)
+bool kthread_should_stop(void)
 {
-	return to_kthread(current)->should_stop;
+	return test_bit(KTHREAD_SHOULD_STOP, &to_kthread(current)->flags);
 }
 EXPORT_SYMBOL(kthread_should_stop);
 
+/**
+ * kthread_should_park - should this kthread park now?
+ *
+ * When someone calls kthread_park() on your kthread, it will be woken
+ * and this will return true.  You should then do the necessary
+ * cleanup and call kthread_parkme()
+ *
+ * Similar to kthread_should_stop(), but this keeps the thread alive
+ * and in a park position. kthread_unpark() "restarts" the thread and
+ * calls the thread function again.
+ */
+bool kthread_should_park(void)
+{
+	return test_bit(KTHREAD_SHOULD_PARK, &to_kthread(current)->flags);
+}
+
 /**
  * kthread_freezable_should_stop - should this freezable kthread return now?
  * @was_frozen: optional out parameter, indicates whether %current was frozen
@@ -96,6 +121,24 @@ void *kthread_data(struct task_struct *task)
 	return to_kthread(task)->data;
 }
 
+static void __kthread_parkme(struct kthread *self)
+{
+	__set_current_state(TASK_INTERRUPTIBLE);
+	while (test_bit(KTHREAD_SHOULD_PARK, &self->flags)) {
+		if (!test_and_set_bit(KTHREAD_IS_PARKED, &self->flags))
+			complete(&self->parked);
+		schedule();
+		__set_current_state(TASK_INTERRUPTIBLE);
+	}
+	clear_bit(KTHREAD_IS_PARKED, &self->flags);
+	__set_current_state(TASK_RUNNING);
+}
+
+void kthread_parkme(void)
+{
+	__kthread_parkme(to_kthread(current));
+}
+
 static int kthread(void *_create)
 {
 	/* Copy data: it's on kthread's stack */
@@ -105,9 +148,10 @@ static int kthread(void *_create)
 	struct kthread self;
 	int ret;
 
-	self.should_stop = 0;
+	self.flags = 0;
 	self.data = data;
 	init_completion(&self.exited);
+	init_completion(&self.parked);
 	current->vfork_done = &self.exited;
 
 	/* OK, tell user we're spawned, wait for stop or wakeup */
@@ -117,9 +161,11 @@ static int kthread(void *_create)
 	schedule();
 
 	ret = -EINTR;
-	if (!self.should_stop)
-		ret = threadfn(data);
 
+	if (!test_bit(KTHREAD_SHOULD_STOP, &self.flags)) {
+		__kthread_parkme(&self);
+		ret = threadfn(data);
+	}
 	/* we can't just return, we must preserve "self" on stack */
 	do_exit(ret);
 }
@@ -172,8 +218,7 @@ static void create_kthread(struct kthread_create_info *create)
  * Returns a task_struct or ERR_PTR(-ENOMEM).
  */
 struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
-					   void *data,
-					   int node,
+					   void *data, int node,
 					   const char namefmt[],
 					   ...)
 {
@@ -210,6 +255,13 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
 }
 EXPORT_SYMBOL(kthread_create_on_node);
 
+static void __kthread_bind(struct task_struct *p, unsigned int cpu)
+{
+	/* It's safe because the task is inactive. */
+	do_set_cpus_allowed(p, cpumask_of(cpu));
+	p->flags |= PF_THREAD_BOUND;
+}
+
 /**
  * kthread_bind - bind a just-created kthread to a cpu.
  * @p: thread created by kthread_create().
@@ -226,13 +278,111 @@ void kthread_bind(struct task_struct *p, unsigned int cpu)
 		WARN_ON(1);
 		return;
 	}
-
-	/* It's safe because the task is inactive. */
-	do_set_cpus_allowed(p, cpumask_of(cpu));
-	p->flags |= PF_THREAD_BOUND;
+	__kthread_bind(p, cpu);
 }
 EXPORT_SYMBOL(kthread_bind);
 
+/**
+ * kthread_create_on_cpu - Create a cpu bound kthread
+ * @threadfn: the function to run until signal_pending(current).
+ * @data: data ptr for @threadfn.
+ * @cpu: The cpu on which the thread should be bound,
+ * @namefmt: printf-style name for the thread. Format is restricted
+ *	     to "name.*%u". Code fills in cpu number.
+ *
+ * Description: This helper function creates and names a kernel thread
+ * The thread will be woken and put into park mode.
+ */
+struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data),
+					  void *data, unsigned int cpu,
+					  const char *namefmt)
+{
+	struct task_struct *p;
+
+	p = kthread_create_on_node(threadfn, data, cpu_to_node(cpu), namefmt,
+				   cpu);
+	if (IS_ERR(p))
+		return p;
+	set_bit(KTHREAD_IS_PER_CPU, &to_kthread(p)->flags);
+	to_kthread(p)->cpu = cpu;
+	/* Park the thread to get it out of TASK_UNINTERRUPTIBLE state */
+	kthread_park(p);
+	return p;
+}
+
+static struct kthread *task_get_live_kthread(struct task_struct *k)
+{
+	struct kthread *kthread;
+
+	get_task_struct(k);
+	kthread = to_kthread(k);
+	/* It might have exited */
+	barrier();
+	if (k->vfork_done != NULL)
+		return kthread;
+	return NULL;
+}
+
+/**
+ * kthread_unpark - unpark a thread created by kthread_create().
+ * @k:		thread created by kthread_create().
+ *
+ * Sets kthread_should_park() for @k to return false, wakes it, and
+ * waits for it to return. If the thread is marked percpu then its
+ * bound to the cpu again.
+ */
+void kthread_unpark(struct task_struct *k)
+{
+	struct kthread *kthread = task_get_live_kthread(k);
+
+	if (kthread) {
+		clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
+		/*
+		 * We clear the IS_PARKED bit here as we don't wait
+		 * until the task has left the park code. So if we'd
+		 * park before that happens we'd see the IS_PARKED bit
+		 * which might be about to be cleared.
+		 */
+		if (test_and_clear_bit(KTHREAD_IS_PARKED, &kthread->flags)) {
+			if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags))
+				__kthread_bind(k, kthread->cpu);
+			wake_up_process(k);
+		}
+	}
+	put_task_struct(k);
+}
+
+/**
+ * kthread_park - park a thread created by kthread_create().
+ * @k: thread created by kthread_create().
+ *
+ * Sets kthread_should_park() for @k to return true, wakes it, and
+ * waits for it to return. This can also be called after kthread_create()
+ * instead of calling wake_up_process(): the thread will park without
+ * calling threadfn().
+ *
+ * Returns 0 if the thread is parked, -ENOSYS if the thread exited.
+ * If called by the kthread itself just the park bit is set.
+ */
+int kthread_park(struct task_struct *k)
+{
+	struct kthread *kthread = task_get_live_kthread(k);
+	int ret = -ENOSYS;
+
+	if (kthread) {
+		if (!test_bit(KTHREAD_IS_PARKED, &kthread->flags)) {
+			set_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
+			if (k != current) {
+				wake_up_process(k);
+				wait_for_completion(&kthread->parked);
+			}
+		}
+		ret = 0;
+	}
+	put_task_struct(k);
+	return ret;
+}
+
 /**
  * kthread_stop - stop a thread created by kthread_create().
  * @k: thread created by kthread_create().
@@ -250,16 +400,13 @@ EXPORT_SYMBOL(kthread_bind);
  */
 int kthread_stop(struct task_struct *k)
 {
-	struct kthread *kthread;
+	struct kthread *kthread = task_get_live_kthread(k);
 	int ret;
 
 	trace_sched_kthread_stop(k);
-	get_task_struct(k);
-
-	kthread = to_kthread(k);
-	barrier(); /* it might have exited */
-	if (k->vfork_done != NULL) {
-		kthread->should_stop = 1;
+	if (kthread) {
+		set_bit(KTHREAD_SHOULD_STOP, &kthread->flags);
+		clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
 		wake_up_process(k);
 		wait_for_completion(&kthread->exited);
 	}

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 @@ void __rcu_read_unlock(void)
 	} 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);

kernel/rcutiny.c

@@ -56,25 +56,28 @@ static void __call_rcu(struct rcu_head *head,
 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 @@ static void rcu_idle_enter_common(long long oldval)
 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 @@ EXPORT_SYMBOL_GPL(rcu_idle_enter);
 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 @@ void rcu_irq_enter(void)
 	rcu_idle_exit_common(oldval);
 	local_irq_restore(flags);
 }
+EXPORT_SYMBOL_GPL(rcu_irq_enter);
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 

kernel/rcutiny_plugin.h

@@ -278,7 +278,7 @@ static int rcu_boost(void)
 	    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 @@ static int rcu_boost(void)
 	 */
 	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 @@ static int rcu_boost(void)
 	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 @@ static void rcu_trace_sub_qlen(struct rcu_ctrlblk *rcp, int n)
 {
 	unsigned long flags;
 
-	raw_local_irq_save(flags);
+	local_irq_save(flags);
 	rcp->qlen -= n;
-	raw_local_irq_restore(flags);
+	local_irq_restore(flags);
 }
 
 /*

kernel/rcutree.h

@@ -102,6 +102,10 @@ struct rcu_dynticks {
 				    /* idle-period nonlazy_posted snapshot. */
 	int tick_nohz_enabled_snap; /* Previously seen value from sysfs. */
 #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
+#ifdef CONFIG_RCU_USER_QS
+	bool ignore_user_qs;	    /* Treat userspace as extended QS or not */
+	bool in_user;		    /* Is the CPU in userland from RCU POV? */
+#endif
 };
 
 /* RCU's kthread states for tracing. */
@@ -196,12 +200,7 @@ struct rcu_node {
 				/* Refused to boost: not sure why, though. */
 				/*  This can happen due to race conditions. */
 #endif /* #ifdef CONFIG_RCU_BOOST */
-	struct task_struct *node_kthread_task;
-				/* kthread that takes care of this rcu_node */
-				/*  structure, for example, awakening the */
-				/*  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 +244,6 @@ struct rcu_data {
 					/*  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 +309,13 @@ struct rcu_data {
 	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 +374,17 @@ struct rcu_state {
 
 	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. */
@@ -398,16 +394,11 @@ struct rcu_state {
 	struct rcu_head **orphan_donetail;	/* Tail of above. */
 	long qlen_lazy;				/* Number of lazy callbacks. */
 	long qlen;				/* Total number of callbacks. */
-	struct task_struct *rcu_barrier_in_progress;
-						/* Task doing rcu_barrier(), */
-						/*  or NULL if no barrier. */
 	struct mutex barrier_mutex;		/* Guards barrier fields. */
 	atomic_t barrier_cpu_count;		/* # CPUs waiting on. */
 	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 */
@@ -426,6 +417,10 @@ struct rcu_state {
 	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)
@@ -468,7 +463,6 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp);
 #ifdef CONFIG_HOTPLUG_CPU
 static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp,
 				      unsigned long flags);
-static void rcu_stop_cpu_kthread(int cpu);
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
 static void rcu_print_detail_task_stall(struct rcu_state *rsp);
 static int rcu_print_task_stall(struct rcu_node *rnp);
@@ -491,15 +485,9 @@ static void invoke_rcu_callbacks_kthread(void);
 static bool rcu_is_callbacks_kthread(void);
 #ifdef CONFIG_RCU_BOOST
 static void rcu_preempt_do_callbacks(void);
-static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp,
-					  cpumask_var_t cm);
 static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
-						 struct rcu_node *rnp,
-						 int rnp_index);
-static void invoke_rcu_node_kthread(struct rcu_node *rnp);
-static void rcu_yield(void (*f)(unsigned long), unsigned long arg);
+						 struct rcu_node *rnp);
 #endif /* #ifdef CONFIG_RCU_BOOST */
-static void rcu_cpu_kthread_setrt(int cpu, int to_rt);
 static void __cpuinit rcu_prepare_kthreads(int cpu);
 static void rcu_prepare_for_idle_init(int cpu);
 static void rcu_cleanup_after_idle(int cpu);

kernel/rcutree_trace.c

@@ -51,8 +51,8 @@ static int show_rcubarrier(struct seq_file *m, void *unused)
 	struct rcu_state *rsp;
 
 	for_each_rcu_flavor(rsp)
-		seq_printf(m, "%s: %c bcc: %d nbd: %lu\n",
-			   rsp->name, rsp->rcu_barrier_in_progress ? 'B' : '.',
+		seq_printf(m, "%s: bcc: %d nbd: %lu\n",
+			   rsp->name,
 			   atomic_read(&rsp->barrier_cpu_count),
 			   rsp->n_barrier_done);
 	return 0;
@@ -86,12 +86,11 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
 {
 	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,
@@ -108,11 +107,10 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
 			rdp->nxttail[RCU_WAIT_TAIL]],
 		   ".D"[&rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL]]);
 #ifdef CONFIG_RCU_BOOST
-	seq_printf(m, " kt=%d/%c/%d ktl=%x",
+	seq_printf(m, " kt=%d/%c ktl=%x",
 		   per_cpu(rcu_cpu_has_work, rdp->cpu),
 		   convert_kthread_status(per_cpu(rcu_cpu_kthread_status,
 					  rdp->cpu)),
-		   per_cpu(rcu_cpu_kthread_cpu, rdp->cpu),
 		   per_cpu(rcu_cpu_kthread_loops, rdp->cpu) & 0xffff);
 #endif /* #ifdef CONFIG_RCU_BOOST */
 	seq_printf(m, " b=%ld", rdp->blimit);
@@ -150,12 +148,11 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp)
 {
 	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 +183,7 @@ static int show_rcudata_csv(struct seq_file *m, void *unused)
 	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 +383,9 @@ static void print_one_rcu_pending(struct seq_file *m, struct rcu_data *rdp)
 		   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);
 }
 

kernel/sched/core.c

@@ -2081,6 +2081,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
 #endif
 
 	/* Here we just switch the register state and the stack. */
+	rcu_switch(prev, next);
 	switch_to(prev, next, prev);
 
 	barrier();
@@ -3468,6 +3469,21 @@ asmlinkage void __sched schedule(void)
 }
 EXPORT_SYMBOL(schedule);
 
+#ifdef CONFIG_RCU_USER_QS
+asmlinkage void __sched schedule_user(void)
+{
+	/*
+	 * If we come here after a random call to set_need_resched(),
+	 * or we have been woken up remotely but the IPI has not yet arrived,
+	 * we haven't yet exited the RCU idle mode. Do it here manually until
+	 * we find a better solution.
+	 */
+	rcu_user_exit();
+	schedule();
+	rcu_user_enter();
+}
+#endif
+
 /**
  * schedule_preempt_disabled - called with preemption disabled
  *
@@ -3569,6 +3585,7 @@ asmlinkage void __sched preempt_schedule_irq(void)
 	/* Catch callers which need to be fixed */
 	BUG_ON(ti->preempt_count || !irqs_disabled());
 
+	rcu_user_exit();
 	do {
 		add_preempt_count(PREEMPT_ACTIVE);
 		local_irq_enable();
@@ -5604,7 +5621,9 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		migrate_tasks(cpu);
 		BUG_ON(rq->nr_running != 1); /* the migration thread */
 		raw_spin_unlock_irqrestore(&rq->lock, flags);
+		break;
 
+	case CPU_DEAD:
 		calc_load_migrate(rq);
 		break;
 #endif

kernel/smpboot.c

 /*
  * Common SMP CPU bringup/teardown functions
  */
+#include <linux/cpu.h>
 #include <linux/err.h>
 #include <linux/smp.h>
 #include <linux/init.h>
+#include <linux/list.h>
+#include <linux/slab.h>
 #include <linux/sched.h>
+#include <linux/export.h>
 #include <linux/percpu.h>
+#include <linux/kthread.h>
+#include <linux/smpboot.h>
 
 #include "smpboot.h"
 
+#ifdef CONFIG_SMP
+
 #ifdef CONFIG_GENERIC_SMP_IDLE_THREAD
 /*
  * For the hotplug case we keep the task structs around and reuse
@@ -65,3 +73,228 @@ void __init idle_threads_init(void)
 	}
 }
 #endif
+
+#endif /* #ifdef CONFIG_SMP */
+
+static LIST_HEAD(hotplug_threads);
+static DEFINE_MUTEX(smpboot_threads_lock);
+
+struct smpboot_thread_data {
+	unsigned int			cpu;
+	unsigned int			status;
+	struct smp_hotplug_thread	*ht;
+};
+
+enum {
+	HP_THREAD_NONE = 0,
+	HP_THREAD_ACTIVE,
+	HP_THREAD_PARKED,
+};
+
+/**
+ * smpboot_thread_fn - percpu hotplug thread loop function
+ * @data:	thread data pointer
+ *
+ * Checks for thread stop and park conditions. Calls the necessary
+ * setup, cleanup, park and unpark functions for the registered
+ * thread.
+ *
+ * Returns 1 when the thread should exit, 0 otherwise.
+ */
+static int smpboot_thread_fn(void *data)
+{
+	struct smpboot_thread_data *td = data;
+	struct smp_hotplug_thread *ht = td->ht;
+
+	while (1) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		preempt_disable();
+		if (kthread_should_stop()) {
+			set_current_state(TASK_RUNNING);
+			preempt_enable();
+			if (ht->cleanup)
+				ht->cleanup(td->cpu, cpu_online(td->cpu));
+			kfree(td);
+			return 0;
+		}
+
+		if (kthread_should_park()) {
+			__set_current_state(TASK_RUNNING);
+			preempt_enable();
+			if (ht->park && td->status == HP_THREAD_ACTIVE) {
+				BUG_ON(td->cpu != smp_processor_id());
+				ht->park(td->cpu);
+				td->status = HP_THREAD_PARKED;
+			}
+			kthread_parkme();
+			/* We might have been woken for stop */
+			continue;
+		}
+
+		BUG_ON(td->cpu != smp_processor_id());
+
+		/* Check for state change setup */
+		switch (td->status) {
+		case HP_THREAD_NONE:
+			preempt_enable();
+			if (ht->setup)
+				ht->setup(td->cpu);
+			td->status = HP_THREAD_ACTIVE;
+			preempt_disable();
+			break;
+		case HP_THREAD_PARKED:
+			preempt_enable();
+			if (ht->unpark)
+				ht->unpark(td->cpu);
+			td->status = HP_THREAD_ACTIVE;
+			preempt_disable();
+			break;
+		}
+
+		if (!ht->thread_should_run(td->cpu)) {
+			preempt_enable();
+			schedule();
+		} else {
+			set_current_state(TASK_RUNNING);
+			preempt_enable();
+			ht->thread_fn(td->cpu);
+		}
+	}
+}
+
+static int
+__smpboot_create_thread(struct smp_hotplug_thread *ht, unsigned int cpu)
+{
+	struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu);
+	struct smpboot_thread_data *td;
+
+	if (tsk)
+		return 0;
+
+	td = kzalloc_node(sizeof(*td), GFP_KERNEL, cpu_to_node(cpu));
+	if (!td)
+		return -ENOMEM;
+	td->cpu = cpu;
+	td->ht = ht;
+
+	tsk = kthread_create_on_cpu(smpboot_thread_fn, td, cpu,
+				    ht->thread_comm);
+	if (IS_ERR(tsk)) {
+		kfree(td);
+		return PTR_ERR(tsk);
+	}
+
+	get_task_struct(tsk);
+	*per_cpu_ptr(ht->store, cpu) = tsk;
+	return 0;
+}
+
+int smpboot_create_threads(unsigned int cpu)
+{
+	struct smp_hotplug_thread *cur;
+	int ret = 0;
+
+	mutex_lock(&smpboot_threads_lock);
+	list_for_each_entry(cur, &hotplug_threads, list) {
+		ret = __smpboot_create_thread(cur, cpu);
+		if (ret)
+			break;
+	}
+	mutex_unlock(&smpboot_threads_lock);
+	return ret;
+}
+
+static void smpboot_unpark_thread(struct smp_hotplug_thread *ht, unsigned int cpu)
+{
+	struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu);
+
+	kthread_unpark(tsk);
+}
+
+void smpboot_unpark_threads(unsigned int cpu)
+{
+	struct smp_hotplug_thread *cur;
+
+	mutex_lock(&smpboot_threads_lock);
+	list_for_each_entry(cur, &hotplug_threads, list)
+		smpboot_unpark_thread(cur, cpu);
+	mutex_unlock(&smpboot_threads_lock);
+}
+
+static void smpboot_park_thread(struct smp_hotplug_thread *ht, unsigned int cpu)
+{
+	struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu);
+
+	if (tsk)
+		kthread_park(tsk);
+}
+
+void smpboot_park_threads(unsigned int cpu)
+{
+	struct smp_hotplug_thread *cur;
+
+	mutex_lock(&smpboot_threads_lock);
+	list_for_each_entry_reverse(cur, &hotplug_threads, list)
+		smpboot_park_thread(cur, cpu);
+	mutex_unlock(&smpboot_threads_lock);
+}
+
+static void smpboot_destroy_threads(struct smp_hotplug_thread *ht)
+{
+	unsigned int cpu;
+
+	/* We need to destroy also the parked threads of offline cpus */
+	for_each_possible_cpu(cpu) {
+		struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu);
+
+		if (tsk) {
+			kthread_stop(tsk);
+			put_task_struct(tsk);
+			*per_cpu_ptr(ht->store, cpu) = NULL;
+		}
+	}
+}
+
+/**
+ * smpboot_register_percpu_thread - Register a per_cpu thread related to hotplug
+ * @plug_thread:	Hotplug thread descriptor
+ *
+ * Creates and starts the threads on all online cpus.
+ */
+int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread)
+{
+	unsigned int cpu;
+	int ret = 0;
+
+	mutex_lock(&smpboot_threads_lock);
+	for_each_online_cpu(cpu) {
+		ret = __smpboot_create_thread(plug_thread, cpu);
+		if (ret) {
+			smpboot_destroy_threads(plug_thread);
+			goto out;
+		}
+		smpboot_unpark_thread(plug_thread, cpu);
+	}
+	list_add(&plug_thread->list, &hotplug_threads);
+out:
+	mutex_unlock(&smpboot_threads_lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread);
+
+/**
+ * smpboot_unregister_percpu_thread - Unregister a per_cpu thread related to hotplug
+ * @plug_thread:	Hotplug thread descriptor
+ *
+ * Stops all threads on all possible cpus.
+ */
+void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread)
+{
+	get_online_cpus();
+	mutex_lock(&smpboot_threads_lock);
+	list_del(&plug_thread->list);
+	smpboot_destroy_threads(plug_thread);
+	mutex_unlock(&smpboot_threads_lock);
+	put_online_cpus();
+}
+EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread);

kernel/smpboot.h

@@ -13,4 +13,8 @@ static inline void idle_thread_set_boot_cpu(void) { }
 static inline void idle_threads_init(void) { }
 #endif
 
+int smpboot_create_threads(unsigned int cpu);
+void smpboot_park_threads(unsigned int cpu);
+void smpboot_unpark_threads(unsigned int cpu);
+
 #endif

kernel/time/tick-sched.c

@@ -436,7 +436,8 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
 	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++;

lib/Kconfig.debug

@@ -629,6 +629,20 @@ config PROVE_RCU_REPEATEDLY
 
 	 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

mm/kmemleak.c

@@ -1483,13 +1483,11 @@ static void *kmemleak_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	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;