Merge commit '29ce8310' into next

* commit '29ce8310': (34 commits)
  rcu: provide rcu_virt_note_context_switch() function.
  rcu: get rid of signed overflow in check_cpu_stall()
  rcu: optimize rcutiny
  rcu: prevent call_rcu() from diving into rcu core if irqs disabled
  rcu: further lower priority in rcu_yield()
  rcu: introduce kfree_rcu()
  rcu: fix spelling
  rcu: call __rcu_read_unlock() in exit_rcu for tree RCU
  rcu: Converge TINY_RCU expedited and normal boosting
  rcu: remove useless ->boosted_this_gp field
  rcu: code cleanups in TINY_RCU priority boosting.
  rcu: Switch to this_cpu() primitives
  rcu: Use WARN_ON_ONCE for DEBUG_OBJECTS_RCU_HEAD warnings
  rcu: mark rcutorture boosting callback as being on-stack
  rcu: add DEBUG_OBJECTS_RCU_HEAD check for alignment
  rcu: Enable DEBUG_OBJECTS_RCU_HEAD from !PREEMPT
  rcu: Add forward-progress diagnostic for per-CPU kthreads
  rcu: add grace-period age and more kthread state to tracing
  rcu: fix tracing bug thinko on boost-balk attribution
  rcu: update tracing documentation for new rcutorture and rcuboost
  ...

Pulling in rcu_virt_note_context_switch().
Signed-off-by: Avi Kivity <avi@redhat.com>

* commit '29ce8310': (34 commits)
  rcu: provide rcu_virt_note_context_switch() function.
  rcu: get rid of signed overflow in check_cpu_stall()
  rcu: optimize rcutiny
  rcu: prevent call_rcu() from diving into rcu core if irqs disabled
  rcu: further lower priority in rcu_yield()
  rcu: introduce kfree_rcu()
  rcu: fix spelling
  rcu: call __rcu_read_unlock() in exit_rcu for tree RCU
  rcu: Converge TINY_RCU expedited and normal boosting
  rcu: remove useless ->boosted_this_gp field
  rcu: code cleanups in TINY_RCU priority boosting.
  rcu: Switch to this_cpu() primitives
  rcu: Use WARN_ON_ONCE for DEBUG_OBJECTS_RCU_HEAD warnings
  rcu: mark rcutorture boosting callback as being on-stack
  rcu: add DEBUG_OBJECTS_RCU_HEAD check for alignment
  rcu: Enable DEBUG_OBJECTS_RCU_HEAD from !PREEMPT
  rcu: Add forward-progress diagnostic for per-CPU kthreads
  rcu: add grace-period age and more kthread state to tracing
  rcu: fix tracing bug thinko on boost-balk attribution
  rcu: update tracing documentation for new rcutorture and rcuboost
  ...

Documentation/RCU/00-INDEX

@@ -21,7 +21,7 @@ rcu.txt
 RTFP.txt
 	- List of RCU papers (bibliography) going back to 1980.
 stallwarn.txt
-	- RCU CPU stall warnings (CONFIG_RCU_CPU_STALL_DETECTOR)
+	- RCU CPU stall warnings (module parameter rcu_cpu_stall_suppress)
 torture.txt
 	- RCU Torture Test Operation (CONFIG_RCU_TORTURE_TEST)
 trace.txt

Documentation/RCU/stallwarn.txt

 Using RCU's CPU Stall Detector
 
-The CONFIG_RCU_CPU_STALL_DETECTOR kernel config parameter enables
-RCU's CPU stall detector, which detects conditions that unduly delay
-RCU grace periods.  The stall detector's idea of what constitutes
-"unduly delayed" is controlled by a set of C preprocessor macros:
+The rcu_cpu_stall_suppress module parameter enables RCU's CPU stall
+detector, which detects conditions that unduly delay RCU grace periods.
+This module parameter enables CPU stall detection by default, but
+may be overridden via boot-time parameter or at runtime via sysfs.
+The stall detector's idea of what constitutes "unduly delayed" is
+controlled by a set of kernel configuration variables and cpp macros:
 
-RCU_SECONDS_TILL_STALL_CHECK
+CONFIG_RCU_CPU_STALL_TIMEOUT
 
-	This macro defines the period of time that RCU will wait from
-	the beginning of a grace period until it issues an RCU CPU
-	stall warning.	This time period is normally ten seconds.
+	This kernel configuration parameter defines the period of time
+	that RCU will wait from the beginning of a grace period until it
+	issues an RCU CPU stall warning.  This time period is normally
+	ten seconds.
 
 RCU_SECONDS_TILL_STALL_RECHECK
 
 	This macro defines the period of time that RCU will wait after
 	issuing a stall warning until it issues another stall warning
-	for the same stall.  This time period is normally set to thirty
-	seconds.
+	for the same stall.  This time period is normally set to three
+	times the check interval plus thirty seconds.
 
 RCU_STALL_RAT_DELAY
 

Documentation/filesystems/proc.txt

@@ -836,7 +836,6 @@ Provides counts of softirq handlers serviced since boot time, for each cpu.
  TASKLET:          0          0          0        290
    SCHED:      27035      26983      26971      26746
  HRTIMER:          0          0          0          0
-     RCU:       1678       1769       2178       2250
 
 
 1.3 IDE devices in /proc/ide

include/linux/interrupt.h

@@ -414,7 +414,6 @@ enum
 	TASKLET_SOFTIRQ,
 	SCHED_SOFTIRQ,
 	HRTIMER_SOFTIRQ,
-	RCU_SOFTIRQ,	/* Preferable RCU should always be the last softirq */
 
 	NR_SOFTIRQS
 };

include/linux/rcupdate.h

@@ -47,6 +47,18 @@
 extern int rcutorture_runnable; /* for sysctl */
 #endif /* #ifdef CONFIG_RCU_TORTURE_TEST */
 
+#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
+extern void rcutorture_record_test_transition(void);
+extern void rcutorture_record_progress(unsigned long vernum);
+#else
+static inline void rcutorture_record_test_transition(void)
+{
+}
+static inline void rcutorture_record_progress(unsigned long vernum)
+{
+}
+#endif
+
 #define UINT_CMP_GE(a, b)	(UINT_MAX / 2 >= (a) - (b))
 #define UINT_CMP_LT(a, b)	(UINT_MAX / 2 < (a) - (b))
 #define ULONG_CMP_GE(a, b)	(ULONG_MAX / 2 >= (a) - (b))
@@ -68,7 +80,6 @@ extern void call_rcu_sched(struct rcu_head *head,
 extern void synchronize_sched(void);
 extern void rcu_barrier_bh(void);
 extern void rcu_barrier_sched(void);
-extern int sched_expedited_torture_stats(char *page);
 
 static inline void __rcu_read_lock_bh(void)
 {
@@ -774,6 +785,7 @@ extern struct debug_obj_descr rcuhead_debug_descr;
 
 static inline void debug_rcu_head_queue(struct rcu_head *head)
 {
+	WARN_ON_ONCE((unsigned long)head & 0x3);
 	debug_object_activate(head, &rcuhead_debug_descr);
 	debug_object_active_state(head, &rcuhead_debug_descr,
 				  STATE_RCU_HEAD_READY,
@@ -797,4 +809,60 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head)
 }
 #endif	/* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 
+static __always_inline bool __is_kfree_rcu_offset(unsigned long offset)
+{
+	return offset < 4096;
+}
+
+static __always_inline
+void __kfree_rcu(struct rcu_head *head, unsigned long offset)
+{
+	typedef void (*rcu_callback)(struct rcu_head *);
+
+	BUILD_BUG_ON(!__builtin_constant_p(offset));
+
+	/* See the kfree_rcu() header comment. */
+	BUILD_BUG_ON(!__is_kfree_rcu_offset(offset));
+
+	call_rcu(head, (rcu_callback)offset);
+}
+
+extern void kfree(const void *);
+
+static inline void __rcu_reclaim(struct rcu_head *head)
+{
+	unsigned long offset = (unsigned long)head->func;
+
+	if (__is_kfree_rcu_offset(offset))
+		kfree((void *)head - offset);
+	else
+		head->func(head);
+}
+
+/**
+ * kfree_rcu() - kfree an object after a grace period.
+ * @ptr:	pointer to kfree
+ * @rcu_head:	the name of the struct rcu_head within the type of @ptr.
+ *
+ * Many rcu callbacks functions just call kfree() on the base structure.
+ * These functions are trivial, but their size adds up, and furthermore
+ * when they are used in a kernel module, that module must invoke the
+ * high-latency rcu_barrier() function at module-unload time.
+ *
+ * The kfree_rcu() function handles this issue.  Rather than encoding a
+ * function address in the embedded rcu_head structure, kfree_rcu() instead
+ * encodes the offset of the rcu_head structure within the base structure.
+ * Because the functions are not allowed in the low-order 4096 bytes of
+ * kernel virtual memory, offsets up to 4095 bytes can be accommodated.
+ * If the offset is larger than 4095 bytes, a compile-time error will
+ * be generated in __kfree_rcu().  If this error is triggered, you can
+ * either fall back to use of call_rcu() or rearrange the structure to
+ * position the rcu_head structure into the first 4096 bytes.
+ *
+ * Note that the allowable offset might decrease in the future, for example,
+ * to allow something like kmem_cache_free_rcu().
+ */
+#define kfree_rcu(ptr, rcu_head)					\
+	__kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head))
+
 #endif /* __LINUX_RCUPDATE_H */

include/linux/rcutiny.h

@@ -99,6 +99,14 @@ static inline void rcu_note_context_switch(int cpu)
 	rcu_preempt_note_context_switch();
 }
 
+/*
+ * Take advantage of the fact that there is only one CPU, which
+ * allows us to ignore virtualization-based context switches.
+ */
+static inline void rcu_virt_note_context_switch(int cpu)
+{
+}
+
 /*
  * Return the number of grace periods.
  */

include/linux/rcutree.h

@@ -35,6 +35,16 @@ extern void rcu_note_context_switch(int cpu);
 extern int rcu_needs_cpu(int cpu);
 extern void rcu_cpu_stall_reset(void);
 
+/*
+ * Note a virtualization-based context switch.  This is simply a
+ * wrapper around rcu_note_context_switch(), which allows TINY_RCU
+ * to save a few bytes.
+ */
+static inline void rcu_virt_note_context_switch(int cpu)
+{
+	rcu_note_context_switch(cpu);
+}
+
 #ifdef CONFIG_TREE_PREEMPT_RCU
 
 extern void exit_rcu(void);
@@ -58,9 +68,12 @@ static inline void synchronize_rcu_bh_expedited(void)
 
 extern void rcu_barrier(void);
 
+extern unsigned long rcutorture_testseq;
+extern unsigned long rcutorture_vernum;
 extern long rcu_batches_completed(void);
 extern long rcu_batches_completed_bh(void);
 extern long rcu_batches_completed_sched(void);
+
 extern void rcu_force_quiescent_state(void);
 extern void rcu_bh_force_quiescent_state(void);
 extern void rcu_sched_force_quiescent_state(void);

include/trace/events/irq.h

@@ -20,8 +20,7 @@ struct softirq_action;
 			 softirq_name(BLOCK_IOPOLL),	\
 			 softirq_name(TASKLET),		\
 			 softirq_name(SCHED),		\
-			 softirq_name(HRTIMER),		\
-			 softirq_name(RCU))
+			 softirq_name(HRTIMER))
 
 /**
  * irq_handler_entry - called immediately before the irq action handler

init/Kconfig

@@ -485,7 +485,7 @@ config TREE_RCU_TRACE
 
 config RCU_BOOST
 	bool "Enable RCU priority boosting"
-	depends on RT_MUTEXES && TINY_PREEMPT_RCU
+	depends on RT_MUTEXES && PREEMPT_RCU
 	default n
 	help
 	  This option boosts the priority of preempted RCU readers that

kernel/rcupdate.c

@@ -142,10 +142,17 @@ static int rcuhead_fixup_init(void *addr, enum debug_obj_state state)
 		 * Ensure that queued callbacks are all executed.
 		 * If we detect that we are nested in a RCU read-side critical
 		 * section, we should simply fail, otherwise we would deadlock.
+		 * In !PREEMPT configurations, there is no way to tell if we are
+		 * in a RCU read-side critical section or not, so we never
+		 * attempt any fixup and just print a warning.
 		 */
+#ifndef CONFIG_PREEMPT
+		WARN_ON_ONCE(1);
+		return 0;
+#endif
 		if (rcu_preempt_depth() != 0 || preempt_count() != 0 ||
 		    irqs_disabled()) {
-			WARN_ON(1);
+			WARN_ON_ONCE(1);
 			return 0;
 		}
 		rcu_barrier();
@@ -184,10 +191,17 @@ static int rcuhead_fixup_activate(void *addr, enum debug_obj_state state)
 		 * Ensure that queued callbacks are all executed.
 		 * If we detect that we are nested in a RCU read-side critical
 		 * section, we should simply fail, otherwise we would deadlock.
+		 * In !PREEMPT configurations, there is no way to tell if we are
+		 * in a RCU read-side critical section or not, so we never
+		 * attempt any fixup and just print a warning.
 		 */
+#ifndef CONFIG_PREEMPT
+		WARN_ON_ONCE(1);
+		return 0;
+#endif
 		if (rcu_preempt_depth() != 0 || preempt_count() != 0 ||
 		    irqs_disabled()) {
-			WARN_ON(1);
+			WARN_ON_ONCE(1);
 			return 0;
 		}
 		rcu_barrier();
@@ -214,15 +228,17 @@ static int rcuhead_fixup_free(void *addr, enum debug_obj_state state)
 		 * Ensure that queued callbacks are all executed.
 		 * If we detect that we are nested in a RCU read-side critical
 		 * section, we should simply fail, otherwise we would deadlock.
-		 * Note that the machinery to reliably determine whether
-		 * or not we are in an RCU read-side critical section
-		 * exists only in the preemptible RCU implementations
-		 * (TINY_PREEMPT_RCU and TREE_PREEMPT_RCU), which is why
-		 * DEBUG_OBJECTS_RCU_HEAD is disallowed if !PREEMPT.
+		 * In !PREEMPT configurations, there is no way to tell if we are
+		 * in a RCU read-side critical section or not, so we never
+		 * attempt any fixup and just print a warning.
 		 */
+#ifndef CONFIG_PREEMPT
+		WARN_ON_ONCE(1);
+		return 0;
+#endif
 		if (rcu_preempt_depth() != 0 || preempt_count() != 0 ||
 		    irqs_disabled()) {
-			WARN_ON(1);
+			WARN_ON_ONCE(1);
 			return 0;
 		}
 		rcu_barrier();

kernel/rcutiny.c

@@ -40,10 +40,10 @@
 static struct task_struct *rcu_kthread_task;
 static DECLARE_WAIT_QUEUE_HEAD(rcu_kthread_wq);
 static unsigned long have_rcu_kthread_work;
-static void invoke_rcu_kthread(void);
 
 /* Forward declarations for rcutiny_plugin.h. */
 struct rcu_ctrlblk;
+static void invoke_rcu_kthread(void);
 static void rcu_process_callbacks(struct rcu_ctrlblk *rcp);
 static int rcu_kthread(void *arg);
 static void __call_rcu(struct rcu_head *head,
@@ -79,26 +79,31 @@ void rcu_exit_nohz(void)
 #endif /* #ifdef CONFIG_NO_HZ */
 
 /*
- * Helper function for rcu_qsctr_inc() and rcu_bh_qsctr_inc().
- * Also disable irqs to avoid confusion due to interrupt handlers
+ * Helper function for rcu_sched_qs() and rcu_bh_qs().
+ * Also irqs are disabled to avoid confusion due to interrupt handlers
  * invoking call_rcu().
  */
 static int rcu_qsctr_help(struct rcu_ctrlblk *rcp)
 {
-	unsigned long flags;
-
-	local_irq_save(flags);
 	if (rcp->rcucblist != NULL &&
 	    rcp->donetail != rcp->curtail) {
 		rcp->donetail = rcp->curtail;
-		local_irq_restore(flags);
 		return 1;
 	}
-	local_irq_restore(flags);
 
 	return 0;
 }
 
+/*
+ * Wake up rcu_kthread() to process callbacks now eligible for invocation
+ * or to boost readers.
+ */
+static void invoke_rcu_kthread(void)
+{
+	have_rcu_kthread_work = 1;
+	wake_up(&rcu_kthread_wq);
+}
+
 /*
  * Record an rcu quiescent state.  And an rcu_bh quiescent state while we
  * are at it, given that any rcu quiescent state is also an rcu_bh
@@ -106,9 +111,13 @@ static int rcu_qsctr_help(struct rcu_ctrlblk *rcp)
  */
 void rcu_sched_qs(int cpu)
 {
+	unsigned long flags;
+
+	local_irq_save(flags);
 	if (rcu_qsctr_help(&rcu_sched_ctrlblk) +
 	    rcu_qsctr_help(&rcu_bh_ctrlblk))
 		invoke_rcu_kthread();
+	local_irq_restore(flags);
 }
 
 /*
@@ -116,8 +125,12 @@ void rcu_sched_qs(int cpu)
  */
 void rcu_bh_qs(int cpu)
 {
+	unsigned long flags;
+
+	local_irq_save(flags);
 	if (rcu_qsctr_help(&rcu_bh_ctrlblk))
 		invoke_rcu_kthread();
+	local_irq_restore(flags);
 }
 
 /*
@@ -167,7 +180,7 @@ static void rcu_process_callbacks(struct rcu_ctrlblk *rcp)
 		prefetch(next);
 		debug_rcu_head_unqueue(list);
 		local_bh_disable();
-		list->func(list);
+		__rcu_reclaim(list);
 		local_bh_enable();
 		list = next;
 		RCU_TRACE(cb_count++);
@@ -207,20 +220,6 @@ static int rcu_kthread(void *arg)
 	return 0;  /* Not reached, but needed to shut gcc up. */
 }
 
-/*
- * Wake up rcu_kthread() to process callbacks now eligible for invocation
- * or to boost readers.
- */
-static void invoke_rcu_kthread(void)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	have_rcu_kthread_work = 1;
-	wake_up(&rcu_kthread_wq);
-	local_irq_restore(flags);
-}
-
 /*
  * Wait for a grace period to elapse.  But it is illegal to invoke
  * synchronize_sched() from within an RCU read-side critical section.

kernel/rcutorture.c

@@ -131,7 +131,7 @@ struct rcu_torture {
 
 static LIST_HEAD(rcu_torture_freelist);
 static struct rcu_torture __rcu *rcu_torture_current;
-static long rcu_torture_current_version;
+static unsigned long rcu_torture_current_version;
 static struct rcu_torture rcu_tortures[10 * RCU_TORTURE_PIPE_LEN];
 static DEFINE_SPINLOCK(rcu_torture_lock);
 static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], rcu_torture_count) =
@@ -146,8 +146,6 @@ static atomic_t n_rcu_torture_mberror;
 static atomic_t n_rcu_torture_error;
 static long n_rcu_torture_boost_ktrerror;
 static long n_rcu_torture_boost_rterror;
-static long n_rcu_torture_boost_allocerror;
-static long n_rcu_torture_boost_afferror;
 static long n_rcu_torture_boost_failure;
 static long n_rcu_torture_boosts;
 static long n_rcu_torture_timers;
@@ -163,11 +161,11 @@ static int stutter_pause_test;
 #endif
 int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT;
 
-#ifdef CONFIG_RCU_BOOST
+#if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU)
 #define rcu_can_boost() 1
-#else /* #ifdef CONFIG_RCU_BOOST */
+#else /* #if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU) */
 #define rcu_can_boost() 0
-#endif /* #else #ifdef CONFIG_RCU_BOOST */
+#endif /* #else #if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU) */
 
 static unsigned long boost_starttime;	/* jiffies of next boost test start. */
 DEFINE_MUTEX(boost_mutex);		/* protect setting boost_starttime */
@@ -751,6 +749,7 @@ static int rcu_torture_boost(void *arg)
 		n_rcu_torture_boost_rterror++;
 	}
 
+	init_rcu_head_on_stack(&rbi.rcu);
 	/* Each pass through the following loop does one boost-test cycle. */
 	do {
 		/* Wait for the next test interval. */
@@ -810,6 +809,7 @@ checkwait:	rcu_stutter_wait("rcu_torture_boost");
 
 	/* Clean up and exit. */
 	VERBOSE_PRINTK_STRING("rcu_torture_boost task stopping");
+	destroy_rcu_head_on_stack(&rbi.rcu);
 	rcutorture_shutdown_absorb("rcu_torture_boost");
 	while (!kthread_should_stop() || rbi.inflight)
 		schedule_timeout_uninterruptible(1);
@@ -886,7 +886,7 @@ rcu_torture_writer(void *arg)
 			old_rp->rtort_pipe_count++;
 			cur_ops->deferred_free(old_rp);
 		}
-		rcu_torture_current_version++;
+		rcutorture_record_progress(++rcu_torture_current_version);
 		oldbatch = cur_ops->completed();
 		rcu_stutter_wait("rcu_torture_writer");
 	} while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
@@ -1066,8 +1066,8 @@ rcu_torture_printk(char *page)
 	}
 	cnt += sprintf(&page[cnt], "%s%s ", torture_type, TORTURE_FLAG);
 	cnt += sprintf(&page[cnt],
-		       "rtc: %p ver: %ld tfle: %d rta: %d rtaf: %d rtf: %d "
-		       "rtmbe: %d rtbke: %ld rtbre: %ld rtbae: %ld rtbafe: %ld "
+		       "rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d "
+		       "rtmbe: %d rtbke: %ld rtbre: %ld "
 		       "rtbf: %ld rtb: %ld nt: %ld",
 		       rcu_torture_current,
 		       rcu_torture_current_version,
@@ -1078,16 +1078,12 @@ rcu_torture_printk(char *page)
 		       atomic_read(&n_rcu_torture_mberror),
 		       n_rcu_torture_boost_ktrerror,
 		       n_rcu_torture_boost_rterror,
-		       n_rcu_torture_boost_allocerror,
-		       n_rcu_torture_boost_afferror,
 		       n_rcu_torture_boost_failure,
 		       n_rcu_torture_boosts,
 		       n_rcu_torture_timers);
 	if (atomic_read(&n_rcu_torture_mberror) != 0 ||
 	    n_rcu_torture_boost_ktrerror != 0 ||
 	    n_rcu_torture_boost_rterror != 0 ||
-	    n_rcu_torture_boost_allocerror != 0 ||
-	    n_rcu_torture_boost_afferror != 0 ||
 	    n_rcu_torture_boost_failure != 0)
 		cnt += sprintf(&page[cnt], " !!!");
 	cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG);
@@ -1331,6 +1327,7 @@ rcu_torture_cleanup(void)
 	int i;
 
 	mutex_lock(&fullstop_mutex);
+	rcutorture_record_test_transition();
 	if (fullstop == FULLSTOP_SHUTDOWN) {
 		printk(KERN_WARNING /* but going down anyway, so... */
 		       "Concurrent 'rmmod rcutorture' and shutdown illegal!\n");
@@ -1486,8 +1483,6 @@ rcu_torture_init(void)
 	atomic_set(&n_rcu_torture_error, 0);
 	n_rcu_torture_boost_ktrerror = 0;
 	n_rcu_torture_boost_rterror = 0;
-	n_rcu_torture_boost_allocerror = 0;
-	n_rcu_torture_boost_afferror = 0;
 	n_rcu_torture_boost_failure = 0;
 	n_rcu_torture_boosts = 0;
 	for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
@@ -1624,6 +1619,7 @@ rcu_torture_init(void)
 		}
 	}
 	register_reboot_notifier(&rcutorture_shutdown_nb);
+	rcutorture_record_test_transition();
 	mutex_unlock(&fullstop_mutex);
 	return 0;
 

kernel/rcutree.h

@@ -84,13 +84,19 @@
  * Dynticks per-CPU state.
  */
 struct rcu_dynticks {
-	int dynticks_nesting;	/* Track nesting level, sort of. */
-	int dynticks;		/* Even value for dynticks-idle, else odd. */
-	int dynticks_nmi;	/* Even value for either dynticks-idle or */
-				/*  not in nmi handler, else odd.  So this */
-				/*  remains even for nmi from irq handler. */
+	int dynticks_nesting;	/* Track irq/process nesting level. */
+	int dynticks_nmi_nesting; /* Track NMI nesting level. */
+	atomic_t dynticks;	/* Even value for dynticks-idle, else odd. */
 };
 
+/* RCU's kthread states for tracing. */
+#define RCU_KTHREAD_STOPPED  0
+#define RCU_KTHREAD_RUNNING  1
+#define RCU_KTHREAD_WAITING  2
+#define RCU_KTHREAD_OFFCPU   3
+#define RCU_KTHREAD_YIELDING 4
+#define RCU_KTHREAD_MAX      4
+
 /*
  * Definition for node within the RCU grace-period-detection hierarchy.
  */
@@ -109,10 +115,11 @@ struct rcu_node {
 				/*  an rcu_data structure, otherwise, each */
 				/*  bit corresponds to a child rcu_node */
 				/*  structure. */
-	unsigned long expmask;	/* Groups that have ->blocked_tasks[] */
+	unsigned long expmask;	/* Groups that have ->blkd_tasks */
 				/*  elements that need to drain to allow the */
 				/*  current expedited grace period to */
 				/*  complete (only for TREE_PREEMPT_RCU). */
+	unsigned long wakemask; /* CPUs whose kthread needs to be awakened. */
 	unsigned long qsmaskinit;
 				/* Per-GP initial value for qsmask & expmask. */
 	unsigned long grpmask;	/* Mask to apply to parent qsmask. */
@@ -122,11 +129,68 @@ struct rcu_node {
 	u8	grpnum;		/* CPU/group number for next level up. */
 	u8	level;		/* root is at level 0. */
 	struct rcu_node *parent;
-	struct list_head blocked_tasks[4];
-				/* Tasks blocked in RCU read-side critsect. */
-				/*  Grace period number (->gpnum) x blocked */
-				/*  by tasks on the (x & 0x1) element of the */
-				/*  blocked_tasks[] array. */
+	struct list_head blkd_tasks;
+				/* Tasks blocked in RCU read-side critical */
+				/*  section.  Tasks are placed at the head */
+				/*  of this list and age towards the tail. */
+	struct list_head *gp_tasks;
+				/* Pointer to the first task blocking the */
+				/*  current grace period, or NULL if there */
+				/*  is no such task. */
+	struct list_head *exp_tasks;
+				/* Pointer to the first task blocking the */
+				/*  current expedited grace period, or NULL */
+				/*  if there is no such task.  If there */
+				/*  is no current expedited grace period, */
+				/*  then there can cannot be any such task. */
+#ifdef CONFIG_RCU_BOOST
+	struct list_head *boost_tasks;
+				/* Pointer to first task that needs to be */
+				/*  priority boosted, or NULL if no priority */
+				/*  boosting is needed for this rcu_node */
+				/*  structure.  If there are no tasks */
+				/*  queued on this rcu_node structure that */
+				/*  are blocking the current grace period, */
+				/*  there can be no such task. */
+	unsigned long boost_time;
+				/* When to start boosting (jiffies). */
+	struct task_struct *boost_kthread_task;
+				/* kthread that takes care of priority */
+				/*  boosting for this rcu_node structure. */
+	wait_queue_head_t boost_wq;
+				/* Wait queue on which to park the boost */
+				/*  kthread. */
+	unsigned int boost_kthread_status;
+				/* State of boost_kthread_task for tracing. */
+	unsigned long n_tasks_boosted;
+				/* Total number of tasks boosted. */
+	unsigned long n_exp_boosts;
+				/* Number of tasks boosted for expedited GP. */
+	unsigned long n_normal_boosts;
+				/* Number of tasks boosted for normal GP. */
+	unsigned long n_balk_blkd_tasks;
+				/* Refused to boost: no blocked tasks. */
+	unsigned long n_balk_exp_gp_tasks;
+				/* Refused to boost: nothing blocking GP. */
+	unsigned long n_balk_boost_tasks;
+				/* Refused to boost: already boosting. */
+	unsigned long n_balk_notblocked;
+				/* Refused to boost: RCU RS CS still running. */
+	unsigned long n_balk_notyet;
+				/* Refused to boost: not yet time. */
+	unsigned long n_balk_nos;
+				/* 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. */
+	wait_queue_head_t node_wq;
+				/* Wait queue on which to park the per-node */
+				/*  kthread. */
+	unsigned int node_kthread_status;
+				/* State of node_kthread_task for tracing. */
 } ____cacheline_internodealigned_in_smp;
 
 /*
@@ -175,7 +239,7 @@ struct rcu_data {
 	bool		passed_quiesc;	/* User-mode/idle loop etc. */
 	bool		qs_pending;	/* Core waits for quiesc state. */
 	bool		beenonline;	/* CPU online at least once. */
-	bool		preemptable;	/* Preemptable RCU? */
+	bool		preemptible;	/* Preemptible RCU? */
 	struct rcu_node *mynode;	/* This CPU's leaf of hierarchy */
 	unsigned long grpmask;		/* Mask to apply to leaf qsmask. */
 
@@ -218,7 +282,6 @@ struct rcu_data {
 	/* 3) dynticks interface. */
 	struct rcu_dynticks *dynticks;	/* Shared per-CPU dynticks state. */
 	int dynticks_snap;		/* Per-GP tracking for dynticks. */
-	int dynticks_nmi_snap;		/* Per-GP tracking for dynticks_nmi. */
 #endif /* #ifdef CONFIG_NO_HZ */
 
 	/* 4) reasons this CPU needed to be kicked by force_quiescent_state */
@@ -254,7 +317,6 @@ struct rcu_data {
 #endif /* #else #ifdef CONFIG_NO_HZ */
 
 #define RCU_JIFFIES_TILL_FORCE_QS	 3	/* for rsp->jiffies_force_qs */
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
 
 #ifdef CONFIG_PROVE_RCU
 #define RCU_STALL_DELAY_DELTA	       (5 * HZ)
@@ -272,13 +334,6 @@ struct rcu_data {
 						/*  scheduling clock irq */
 						/*  before ratting on them. */
 
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR_RUNNABLE
-#define RCU_CPU_STALL_SUPPRESS_INIT 0
-#else
-#define RCU_CPU_STALL_SUPPRESS_INIT 1
-#endif
-
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 
 /*
  * RCU global state, including node hierarchy.  This hierarchy is
@@ -325,12 +380,12 @@ struct rcu_state {
 						/*  due to lock unavailable. */
 	unsigned long n_force_qs_ngp;		/* Number of calls leaving */
 						/*  due to no GP active. */
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
 	unsigned long gp_start;			/* Time at which GP started, */
 						/*  but in jiffies. */
 	unsigned long jiffies_stall;		/* Time at which to check */
 						/*  for CPU stalls. */
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+	unsigned long gp_max;			/* Maximum GP duration in */
+						/*  jiffies. */
 	char *name;				/* Name of structure. */
 };
 
@@ -361,16 +416,14 @@ DECLARE_PER_CPU(struct rcu_data, rcu_preempt_data);
 static void rcu_bootup_announce(void);
 long rcu_batches_completed(void);
 static void rcu_preempt_note_context_switch(int cpu);
-static int rcu_preempted_readers(struct rcu_node *rnp);
+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);
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
 static void rcu_print_detail_task_stall(struct rcu_state *rsp);
 static void rcu_print_task_stall(struct rcu_node *rnp);
 static void rcu_preempt_stall_reset(void);
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
 #ifdef CONFIG_HOTPLUG_CPU
 static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
@@ -390,5 +443,16 @@ static void __cpuinit rcu_preempt_init_percpu_data(int cpu);
 static void rcu_preempt_send_cbs_to_online(void);
 static void __init __rcu_init_preempt(void);
 static void rcu_needs_cpu_flush(void);
+static void __init rcu_init_boost_waitqueue(struct rcu_node *rnp);
+static void rcu_initiate_boost(struct rcu_node *rnp);
+static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp,
+					  cpumask_var_t cm);
+static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
+static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
+						 struct rcu_node *rnp,
+						 int rnp_index);
+#ifdef CONFIG_HOTPLUG_CPU
+static void rcu_stop_boost_kthread(struct rcu_node *rnp);
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
 
 #endif /* #ifndef RCU_TREE_NONCORE */

kernel/rcutree_trace.c

@@ -46,6 +46,18 @@
 #define RCU_TREE_NONCORE
 #include "rcutree.h"
 
+DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
+DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_cpu);
+DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
+DECLARE_PER_CPU(char, rcu_cpu_has_work);
+
+static char convert_kthread_status(unsigned int kthread_status)
+{
+	if (kthread_status > RCU_KTHREAD_MAX)
+		return '?';
+	return "SRWOY"[kthread_status];
+}
+
 static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
 {
 	if (!rdp->beenonline)
@@ -57,14 +69,28 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
 		   rdp->passed_quiesc, rdp->passed_quiesc_completed,
 		   rdp->qs_pending);
 #ifdef CONFIG_NO_HZ
-	seq_printf(m, " dt=%d/%d dn=%d df=%lu",
-		   rdp->dynticks->dynticks,
+	seq_printf(m, " dt=%d/%d/%d df=%lu",
+		   atomic_read(&rdp->dynticks->dynticks),
 		   rdp->dynticks->dynticks_nesting,
-		   rdp->dynticks->dynticks_nmi,
+		   rdp->dynticks->dynticks_nmi_nesting,
 		   rdp->dynticks_fqs);
 #endif /* #ifdef CONFIG_NO_HZ */
 	seq_printf(m, " of=%lu ri=%lu", rdp->offline_fqs, rdp->resched_ipi);
-	seq_printf(m, " ql=%ld b=%ld", rdp->qlen, rdp->blimit);
+	seq_printf(m, " ql=%ld qs=%c%c%c%c kt=%d/%c/%d ktl=%x b=%ld",
+		   rdp->qlen,
+		   ".N"[rdp->nxttail[RCU_NEXT_READY_TAIL] !=
+			rdp->nxttail[RCU_NEXT_TAIL]],
+		   ".R"[rdp->nxttail[RCU_WAIT_TAIL] !=
+			rdp->nxttail[RCU_NEXT_READY_TAIL]],
+		   ".W"[rdp->nxttail[RCU_DONE_TAIL] !=
+			rdp->nxttail[RCU_WAIT_TAIL]],
+		   ".D"[&rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL]],
+		   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,
+		   rdp->blimit);
 	seq_printf(m, " ci=%lu co=%lu ca=%lu\n",
 		   rdp->n_cbs_invoked, rdp->n_cbs_orphaned, rdp->n_cbs_adopted);
 }
@@ -115,13 +141,24 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp)
 		   rdp->qs_pending);
 #ifdef CONFIG_NO_HZ
 	seq_printf(m, ",%d,%d,%d,%lu",
-		   rdp->dynticks->dynticks,
+		   atomic_read(&rdp->dynticks->dynticks),
 		   rdp->dynticks->dynticks_nesting,
-		   rdp->dynticks->dynticks_nmi,
+		   rdp->dynticks->dynticks_nmi_nesting,
 		   rdp->dynticks_fqs);
 #endif /* #ifdef CONFIG_NO_HZ */
 	seq_printf(m, ",%lu,%lu", rdp->offline_fqs, rdp->resched_ipi);
-	seq_printf(m, ",%ld,%ld", rdp->qlen, rdp->blimit);
+	seq_printf(m, ",%ld,\"%c%c%c%c\",%d,\"%c\",%ld", rdp->qlen,
+		   ".N"[rdp->nxttail[RCU_NEXT_READY_TAIL] !=
+			rdp->nxttail[RCU_NEXT_TAIL]],
+		   ".R"[rdp->nxttail[RCU_WAIT_TAIL] !=
+			rdp->nxttail[RCU_NEXT_READY_TAIL]],
+		   ".W"[rdp->nxttail[RCU_DONE_TAIL] !=
+			rdp->nxttail[RCU_WAIT_TAIL]],
+		   ".D"[&rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL]],
+		   per_cpu(rcu_cpu_has_work, rdp->cpu),
+		   convert_kthread_status(per_cpu(rcu_cpu_kthread_status,
+					  rdp->cpu)),
+		   rdp->blimit);
 	seq_printf(m, ",%lu,%lu,%lu\n",
 		   rdp->n_cbs_invoked, rdp->n_cbs_orphaned, rdp->n_cbs_adopted);
 }
@@ -130,7 +167,7 @@ static int show_rcudata_csv(struct seq_file *m, void *unused)
 {
 	seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pqc\",\"pq\",");
 #ifdef CONFIG_NO_HZ
-	seq_puts(m, "\"dt\",\"dt nesting\",\"dn\",\"df\",");
+	seq_puts(m, "\"dt\",\"dt nesting\",\"dt NMI nesting\",\"df\",");
 #endif /* #ifdef CONFIG_NO_HZ */
 	seq_puts(m, "\"of\",\"ri\",\"ql\",\"b\",\"ci\",\"co\",\"ca\"\n");
 #ifdef CONFIG_TREE_PREEMPT_RCU
@@ -157,11 +194,76 @@ static const struct file_operations rcudata_csv_fops = {
 	.release = single_release,
 };
 
+#ifdef CONFIG_RCU_BOOST
+
+static void print_one_rcu_node_boost(struct seq_file *m, struct rcu_node *rnp)
+{
+	seq_printf(m,  "%d:%d tasks=%c%c%c%c kt=%c ntb=%lu neb=%lu nnb=%lu "
+		   "j=%04x bt=%04x\n",
+		   rnp->grplo, rnp->grphi,
+		   "T."[list_empty(&rnp->blkd_tasks)],
+		   "N."[!rnp->gp_tasks],
+		   "E."[!rnp->exp_tasks],
+		   "B."[!rnp->boost_tasks],
+		   convert_kthread_status(rnp->boost_kthread_status),
+		   rnp->n_tasks_boosted, rnp->n_exp_boosts,
+		   rnp->n_normal_boosts,
+		   (int)(jiffies & 0xffff),
+		   (int)(rnp->boost_time & 0xffff));
+	seq_printf(m, "%s: nt=%lu egt=%lu bt=%lu nb=%lu ny=%lu nos=%lu\n",
+		   "     balk",
+		   rnp->n_balk_blkd_tasks,
+		   rnp->n_balk_exp_gp_tasks,
+		   rnp->n_balk_boost_tasks,
+		   rnp->n_balk_notblocked,
+		   rnp->n_balk_notyet,
+		   rnp->n_balk_nos);
+}
+
+static int show_rcu_node_boost(struct seq_file *m, void *unused)
+{
+	struct rcu_node *rnp;
+
+	rcu_for_each_leaf_node(&rcu_preempt_state, rnp)
+		print_one_rcu_node_boost(m, rnp);
+	return 0;
+}
+
+static int rcu_node_boost_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, show_rcu_node_boost, NULL);
+}
+
+static const struct file_operations rcu_node_boost_fops = {
+	.owner = THIS_MODULE,
+	.open = rcu_node_boost_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+/*
+ * Create the rcuboost debugfs entry.  Standard error return.
+ */
+static int rcu_boost_trace_create_file(struct dentry *rcudir)
+{
+	return !debugfs_create_file("rcuboost", 0444, rcudir, NULL,
+				    &rcu_node_boost_fops);
+}
+
+#else /* #ifdef CONFIG_RCU_BOOST */
+
+static int rcu_boost_trace_create_file(struct dentry *rcudir)
+{
+	return 0;  /* There cannot be an error if we didn't create it! */
+}
+
+#endif /* #else #ifdef CONFIG_RCU_BOOST */
+
 static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
 {
 	unsigned long gpnum;
 	int level = 0;
-	int phase;
 	struct rcu_node *rnp;
 
 	gpnum = rsp->gpnum;
@@ -178,13 +280,11 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
 			seq_puts(m, "\n");
 			level = rnp->level;
 		}
-		phase = gpnum & 0x1;
-		seq_printf(m, "%lx/%lx %c%c>%c%c %d:%d ^%d    ",
+		seq_printf(m, "%lx/%lx %c%c>%c %d:%d ^%d    ",
 			   rnp->qsmask, rnp->qsmaskinit,
-			   "T."[list_empty(&rnp->blocked_tasks[phase])],
-			   "E."[list_empty(&rnp->blocked_tasks[phase + 2])],
-			   "T."[list_empty(&rnp->blocked_tasks[!phase])],
-			   "E."[list_empty(&rnp->blocked_tasks[!phase + 2])],
+			   ".G"[rnp->gp_tasks != NULL],
+			   ".E"[rnp->exp_tasks != NULL],
+			   ".T"[!list_empty(&rnp->blkd_tasks)],
 			   rnp->grplo, rnp->grphi, rnp->grpnum);
 	}
 	seq_puts(m, "\n");
@@ -216,16 +316,35 @@ static const struct file_operations rcuhier_fops = {
 	.release = single_release,
 };
 
+static void show_one_rcugp(struct seq_file *m, struct rcu_state *rsp)
+{
+	unsigned long flags;
+	unsigned long completed;
+	unsigned long gpnum;
+	unsigned long gpage;
+	unsigned long gpmax;
+	struct rcu_node *rnp = &rsp->node[0];
+
+	raw_spin_lock_irqsave(&rnp->lock, flags);
+	completed = rsp->completed;
+	gpnum = rsp->gpnum;
+	if (rsp->completed == rsp->gpnum)
+		gpage = 0;
+	else
+		gpage = jiffies - rsp->gp_start;
+	gpmax = rsp->gp_max;
+	raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	seq_printf(m, "%s: completed=%ld  gpnum=%lu  age=%ld  max=%ld\n",
+		   rsp->name, completed, gpnum, gpage, gpmax);
+}
+
 static int show_rcugp(struct seq_file *m, void *unused)
 {
 #ifdef CONFIG_TREE_PREEMPT_RCU
-	seq_printf(m, "rcu_preempt: completed=%ld  gpnum=%lu\n",
-		   rcu_preempt_state.completed, rcu_preempt_state.gpnum);
+	show_one_rcugp(m, &rcu_preempt_state);
 #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
-	seq_printf(m, "rcu_sched: completed=%ld  gpnum=%lu\n",
-		   rcu_sched_state.completed, rcu_sched_state.gpnum);
-	seq_printf(m, "rcu_bh: completed=%ld  gpnum=%lu\n",
-		   rcu_bh_state.completed, rcu_bh_state.gpnum);
+	show_one_rcugp(m, &rcu_sched_state);
+	show_one_rcugp(m, &rcu_bh_state);
 	return 0;
 }
 
@@ -298,6 +417,29 @@ static const struct file_operations rcu_pending_fops = {
 	.release = single_release,
 };
 
+static int show_rcutorture(struct seq_file *m, void *unused)
+{
+	seq_printf(m, "rcutorture test sequence: %lu %s\n",
+		   rcutorture_testseq >> 1,
+		   (rcutorture_testseq & 0x1) ? "(test in progress)" : "");
+	seq_printf(m, "rcutorture update version number: %lu\n",
+		   rcutorture_vernum);
+	return 0;
+}
+
+static int rcutorture_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, show_rcutorture, NULL);
+}
+
+static const struct file_operations rcutorture_fops = {
+	.owner = THIS_MODULE,
+	.open = rcutorture_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
 static struct dentry *rcudir;
 
 static int __init rcutree_trace_init(void)
@@ -318,6 +460,9 @@ static int __init rcutree_trace_init(void)
 	if (!retval)
 		goto free_out;
 
+	if (rcu_boost_trace_create_file(rcudir))
+		goto free_out;
+
 	retval = debugfs_create_file("rcugp", 0444, rcudir, NULL, &rcugp_fops);
 	if (!retval)
 		goto free_out;
@@ -331,6 +476,11 @@ static int __init rcutree_trace_init(void)
 						NULL, &rcu_pending_fops);
 	if (!retval)
 		goto free_out;
+
+	retval = debugfs_create_file("rcutorture", 0444, rcudir,
+						NULL, &rcutorture_fops);
+	if (!retval)
+		goto free_out;
 	return 0;
 free_out:
 	debugfs_remove_recursive(rcudir);

kernel/softirq.c

@@ -58,7 +58,7 @@ DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
 
 char *softirq_to_name[NR_SOFTIRQS] = {
 	"HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "BLOCK_IOPOLL",
-	"TASKLET", "SCHED", "HRTIMER",	"RCU"
+	"TASKLET", "SCHED", "HRTIMER"
 };
 
 /*

lib/Kconfig.debug

@@ -337,7 +337,7 @@ config DEBUG_OBJECTS_WORK
 
 config DEBUG_OBJECTS_RCU_HEAD
 	bool "Debug RCU callbacks objects"
-	depends on DEBUG_OBJECTS && PREEMPT
+	depends on DEBUG_OBJECTS
 	help
 	  Enable this to turn on debugging of RCU list heads (call_rcu() usage).
 
@@ -875,22 +875,9 @@ config RCU_TORTURE_TEST_RUNNABLE
 	  Say N here if you want the RCU torture tests to start only
 	  after being manually enabled via /proc.
 
-config RCU_CPU_STALL_DETECTOR
-	bool "Check for stalled CPUs delaying RCU grace periods"
-	depends on TREE_RCU || TREE_PREEMPT_RCU
-	default y
-	help
-	  This option causes RCU to printk information on which
-	  CPUs are delaying the current grace period, but only when
-	  the grace period extends for excessive time periods.
-
-	  Say N if you want to disable such checks.
-
-	  Say Y if you are unsure.
-
 config RCU_CPU_STALL_TIMEOUT
 	int "RCU CPU stall timeout in seconds"
-	depends on RCU_CPU_STALL_DETECTOR
+	depends on TREE_RCU || TREE_PREEMPT_RCU
 	range 3 300
 	default 60
 	help
@@ -899,22 +886,9 @@ config RCU_CPU_STALL_TIMEOUT
 	  RCU grace period persists, additional CPU stall warnings are
 	  printed at more widely spaced intervals.
 
-config RCU_CPU_STALL_DETECTOR_RUNNABLE
-	bool "RCU CPU stall checking starts automatically at boot"
-	depends on RCU_CPU_STALL_DETECTOR
-	default y
-	help
-	  If set, start checking for RCU CPU stalls immediately on
-	  boot.  Otherwise, RCU CPU stall checking must be manually
-	  enabled.
-
-	  Say Y if you are unsure.
-
-	  Say N if you wish to suppress RCU CPU stall checking during boot.
-
 config RCU_CPU_STALL_VERBOSE
 	bool "Print additional per-task information for RCU_CPU_STALL_DETECTOR"
-	depends on RCU_CPU_STALL_DETECTOR && TREE_PREEMPT_RCU
+	depends on TREE_PREEMPT_RCU
 	default y
 	help
 	  This option causes RCU to printk detailed per-task information

tools/perf/util/trace-event-parse.c

@@ -2187,7 +2187,6 @@ static const struct flag flags[] = {
 	{ "TASKLET_SOFTIRQ", 6 },
 	{ "SCHED_SOFTIRQ", 7 },
 	{ "HRTIMER_SOFTIRQ", 8 },
-	{ "RCU_SOFTIRQ", 9 },
 
 	{ "HRTIMER_NORESTART", 0 },
 	{ "HRTIMER_RESTART", 1 },