Merge branches 'doc.2013.08.19a', 'fixes.2013.08.20a', 'sysidle.2013.08.31a'...

Merge branches 'doc.2013.08.19a', 'fixes.2013.08.20a', 'sysidle.2013.08.31a' and 'torture.2013.08.20a' into HEAD

doc.2013.08.19a: Documentation updates
fixes.2013.08.20a: Miscellaneous fixes
sysidle.2013.08.31a: Detect system-wide idle state.
torture.2013.08.20a: rcutorture updates.

Documentation/RCU/torture.txt

@@ -42,6 +42,16 @@ fqs_holdoff	Holdoff time (in microseconds) between consecutive calls
 fqs_stutter	Wait time (in seconds) between consecutive bursts
 		of calls to force_quiescent_state().
 
+gp_normal	Make the fake writers use normal synchronous grace-period
+		primitives.
+
+gp_exp		Make the fake writers use expedited synchronous grace-period
+		primitives.  If both gp_normal and gp_exp are set, or
+		if neither gp_normal nor gp_exp are set, then randomly
+		choose the primitive so that about 50% are normal and
+		50% expedited.  By default, neither are set, which
+		gives best overall test coverage.
+
 irqreader	Says to invoke RCU readers from irq level.  This is currently
 		done via timers.  Defaults to "1" for variants of RCU that
 		permit this.  (Or, more accurately, variants of RCU that do

Documentation/timers/NO_HZ.txt

@@ -24,8 +24,8 @@ There are three main ways of managing scheduling-clock interrupts
 	workloads, you will normally -not- want this option.
 
 These three cases are described in the following three sections, followed
-by a third section on RCU-specific considerations and a fourth and final
-section listing known issues.
+by a third section on RCU-specific considerations, a fourth section
+discussing testing, and a fifth and final section listing known issues.
 
 
 NEVER OMIT SCHEDULING-CLOCK TICKS
@@ -121,14 +121,15 @@ boot parameter specifies the adaptive-ticks CPUs.  For example,
 "nohz_full=1,6-8" says that CPUs 1, 6, 7, and 8 are to be adaptive-ticks
 CPUs.  Note that you are prohibited from marking all of the CPUs as
 adaptive-tick CPUs:  At least one non-adaptive-tick CPU must remain
-online to handle timekeeping tasks in order to ensure that system calls
-like gettimeofday() returns accurate values on adaptive-tick CPUs.
-(This is not an issue for CONFIG_NO_HZ_IDLE=y because there are no
-running user processes to observe slight drifts in clock rate.)
-Therefore, the boot CPU is prohibited from entering adaptive-ticks
-mode.  Specifying a "nohz_full=" mask that includes the boot CPU will
-result in a boot-time error message, and the boot CPU will be removed
-from the mask.
+online to handle timekeeping tasks in order to ensure that system
+calls like gettimeofday() returns accurate values on adaptive-tick CPUs.
+(This is not an issue for CONFIG_NO_HZ_IDLE=y because there are no running
+user processes to observe slight drifts in clock rate.)  Therefore, the
+boot CPU is prohibited from entering adaptive-ticks mode.  Specifying a
+"nohz_full=" mask that includes the boot CPU will result in a boot-time
+error message, and the boot CPU will be removed from the mask.  Note that
+this means that your system must have at least two CPUs in order for
+CONFIG_NO_HZ_FULL=y to do anything for you.
 
 Alternatively, the CONFIG_NO_HZ_FULL_ALL=y Kconfig parameter specifies
 that all CPUs other than the boot CPU are adaptive-ticks CPUs.  This
@@ -232,6 +233,29 @@ scheduler will decide where to run them, which might or might not be
 where you want them to run.
 
 
+TESTING
+
+So you enable all the OS-jitter features described in this document,
+but do not see any change in your workload's behavior.  Is this because
+your workload isn't affected that much by OS jitter, or is it because
+something else is in the way?  This section helps answer this question
+by providing a simple OS-jitter test suite, which is available on branch
+master of the following git archive:
+
+git://git.kernel.org/pub/scm/linux/kernel/git/frederic/dynticks-testing.git
+
+Clone this archive and follow the instructions in the README file.
+This test procedure will produce a trace that will allow you to evaluate
+whether or not you have succeeded in removing OS jitter from your system.
+If this trace shows that you have removed OS jitter as much as is
+possible, then you can conclude that your workload is not all that
+sensitive to OS jitter.
+
+Note: this test requires that your system have at least two CPUs.
+We do not currently have a good way to remove OS jitter from single-CPU
+systems.
+
+
 KNOWN ISSUES
 
 o	Dyntick-idle slows transitions to and from idle slightly.

include/linux/debugobjects.h

@@ -63,7 +63,7 @@ struct debug_obj_descr {
 extern void debug_object_init      (void *addr, struct debug_obj_descr *descr);
 extern void
 debug_object_init_on_stack(void *addr, struct debug_obj_descr *descr);
-extern void debug_object_activate  (void *addr, struct debug_obj_descr *descr);
+extern int debug_object_activate  (void *addr, struct debug_obj_descr *descr);
 extern void debug_object_deactivate(void *addr, struct debug_obj_descr *descr);
 extern void debug_object_destroy   (void *addr, struct debug_obj_descr *descr);
 extern void debug_object_free      (void *addr, struct debug_obj_descr *descr);
@@ -85,8 +85,8 @@ static inline void
 debug_object_init      (void *addr, struct debug_obj_descr *descr) { }
 static inline void
 debug_object_init_on_stack(void *addr, struct debug_obj_descr *descr) { }
-static inline void
-debug_object_activate  (void *addr, struct debug_obj_descr *descr) { }
+static inline int
+debug_object_activate  (void *addr, struct debug_obj_descr *descr) { return 0; }
 static inline void
 debug_object_deactivate(void *addr, struct debug_obj_descr *descr) { }
 static inline void

include/linux/jiffies.h

@@ -101,13 +101,13 @@ static inline u64 get_jiffies_64(void)
 #define time_after(a,b)		\
 	(typecheck(unsigned long, a) && \
 	 typecheck(unsigned long, b) && \
-	 ((long)(b) - (long)(a) < 0))
+	 ((long)((b) - (a)) < 0))
 #define time_before(a,b)	time_after(b,a)
 
 #define time_after_eq(a,b)	\
 	(typecheck(unsigned long, a) && \
 	 typecheck(unsigned long, b) && \
-	 ((long)(a) - (long)(b) >= 0))
+	 ((long)((a) - (b)) >= 0))
 #define time_before_eq(a,b)	time_after_eq(b,a)
 
 /*
@@ -130,13 +130,13 @@ static inline u64 get_jiffies_64(void)
 #define time_after64(a,b)	\
 	(typecheck(__u64, a) &&	\
 	 typecheck(__u64, b) && \
-	 ((__s64)(b) - (__s64)(a) < 0))
+	 ((__s64)((b) - (a)) < 0))
 #define time_before64(a,b)	time_after64(b,a)
 
 #define time_after_eq64(a,b)	\
 	(typecheck(__u64, a) && \
 	 typecheck(__u64, b) && \
-	 ((__s64)(a) - (__s64)(b) >= 0))
+	 ((__s64)((a) - (b)) >= 0))
 #define time_before_eq64(a,b)	time_after_eq64(b,a)
 
 #define time_in_range64(a, b, c) \

include/linux/rculist.h

@@ -267,8 +267,9 @@ static inline void list_splice_init_rcu(struct list_head *list,
  */
 #define list_first_or_null_rcu(ptr, type, member) \
 	({struct list_head *__ptr = (ptr); \
-	  struct list_head __rcu *__next = list_next_rcu(__ptr); \
-	  likely(__ptr != __next) ? container_of(__next, type, member) : NULL; \
+	  struct list_head *__next = ACCESS_ONCE(__ptr->next); \
+	  likely(__ptr != __next) ? \
+		list_entry_rcu(__next, type, member) : NULL; \
 	})
 
 /**

include/linux/rcupdate.h

@@ -229,13 +229,9 @@ 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);
 #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) { }
 static inline void rcu_user_hooks_switch(struct task_struct *prev,
 					 struct task_struct *next) { }
 #endif /* CONFIG_RCU_USER_QS */
@@ -1015,4 +1011,22 @@ static inline bool rcu_is_nocb_cpu(int cpu) { return false; }
 #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
 
 
+/* Only for use by adaptive-ticks code. */
+#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
+extern bool rcu_sys_is_idle(void);
+extern void rcu_sysidle_force_exit(void);
+#else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
+
+static inline bool rcu_sys_is_idle(void)
+{
+	return false;
+}
+
+static inline void rcu_sysidle_force_exit(void)
+{
+}
+
+#endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
+
+
 #endif /* __LINUX_RCUPDATE_H */

init/Kconfig

@@ -470,6 +470,7 @@ config TREE_RCU
 config TREE_PREEMPT_RCU
 	bool "Preemptible tree-based hierarchical RCU"
 	depends on PREEMPT
+	select IRQ_WORK
 	help
 	  This option selects the RCU implementation that is
 	  designed for very large SMP systems with hundreds or

kernel/rcu.h

@@ -67,12 +67,15 @@
 
 extern struct debug_obj_descr rcuhead_debug_descr;
 
-static inline void debug_rcu_head_queue(struct rcu_head *head)
+static inline int debug_rcu_head_queue(struct rcu_head *head)
 {
-	debug_object_activate(head, &rcuhead_debug_descr);
+	int r1;
+
+	r1 = debug_object_activate(head, &rcuhead_debug_descr);
 	debug_object_active_state(head, &rcuhead_debug_descr,
 				  STATE_RCU_HEAD_READY,
 				  STATE_RCU_HEAD_QUEUED);
+	return r1;
 }
 
 static inline void debug_rcu_head_unqueue(struct rcu_head *head)
@@ -83,8 +86,9 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head)
 	debug_object_deactivate(head, &rcuhead_debug_descr);
 }
 #else	/* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
-static inline void debug_rcu_head_queue(struct rcu_head *head)
+static inline int debug_rcu_head_queue(struct rcu_head *head)
 {
+	return 0;
 }
 
 static inline void debug_rcu_head_unqueue(struct rcu_head *head)

kernel/rcupdate.c

@@ -211,43 +211,6 @@ static inline void debug_rcu_head_free(struct rcu_head *head)
 	debug_object_free(head, &rcuhead_debug_descr);
 }
 
-/*
- * fixup_init is called when:
- * - an active object is initialized
- */
-static int rcuhead_fixup_init(void *addr, enum debug_obj_state state)
-{
-	struct rcu_head *head = addr;
-
-	switch (state) {
-	case ODEBUG_STATE_ACTIVE:
-		/*
-		 * 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_ONCE(1);
-			return 0;
-		}
-		rcu_barrier();
-		rcu_barrier_sched();
-		rcu_barrier_bh();
-		debug_object_init(head, &rcuhead_debug_descr);
-		return 1;
-	default:
-		return 0;
-	}
-}
-
 /*
  * fixup_activate is called when:
  * - an active object is activated
@@ -268,69 +231,8 @@ static int rcuhead_fixup_activate(void *addr, enum debug_obj_state state)
 		debug_object_init(head, &rcuhead_debug_descr);
 		debug_object_activate(head, &rcuhead_debug_descr);
 		return 0;
-
-	case ODEBUG_STATE_ACTIVE:
-		/*
-		 * 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_ONCE(1);
-			return 0;
-		}
-		rcu_barrier();
-		rcu_barrier_sched();
-		rcu_barrier_bh();
-		debug_object_activate(head, &rcuhead_debug_descr);
-		return 1;
 	default:
-		return 0;
-	}
-}
-
-/*
- * fixup_free is called when:
- * - an active object is freed
- */
-static int rcuhead_fixup_free(void *addr, enum debug_obj_state state)
-{
-	struct rcu_head *head = addr;
-
-	switch (state) {
-	case ODEBUG_STATE_ACTIVE:
-		/*
-		 * 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_ONCE(1);
-			return 0;
-		}
-		rcu_barrier();
-		rcu_barrier_sched();
-		rcu_barrier_bh();
-		debug_object_free(head, &rcuhead_debug_descr);
 		return 1;
-	default:
-		return 0;
 	}
 }
 
@@ -369,9 +271,7 @@ EXPORT_SYMBOL_GPL(destroy_rcu_head_on_stack);
 
 struct debug_obj_descr rcuhead_debug_descr = {
 	.name = "rcu_head",
-	.fixup_init = rcuhead_fixup_init,
 	.fixup_activate = rcuhead_fixup_activate,
-	.fixup_free = rcuhead_fixup_free,
 };
 EXPORT_SYMBOL_GPL(rcuhead_debug_descr);
 #endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */

kernel/rcutree.h

@@ -88,6 +88,14 @@ struct rcu_dynticks {
 				    /* Process level is worth LLONG_MAX/2. */
 	int dynticks_nmi_nesting;   /* Track NMI nesting level. */
 	atomic_t dynticks;	    /* Even value for idle, else odd. */
+#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
+	long long dynticks_idle_nesting;
+				    /* irq/process nesting level from idle. */
+	atomic_t dynticks_idle;	    /* Even value for idle, else odd. */
+				    /*  "Idle" excludes userspace execution. */
+	unsigned long dynticks_idle_jiffies;
+				    /* End of last non-NMI non-idle period. */
+#endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
 #ifdef CONFIG_RCU_FAST_NO_HZ
 	bool all_lazy;		    /* Are all CPU's CBs lazy? */
 	unsigned long nonlazy_posted;
@@ -545,6 +553,15 @@ static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
 static void rcu_spawn_nocb_kthreads(struct rcu_state *rsp);
 static void rcu_kick_nohz_cpu(int cpu);
 static bool init_nocb_callback_list(struct rcu_data *rdp);
+static void rcu_sysidle_enter(struct rcu_dynticks *rdtp, int irq);
+static void rcu_sysidle_exit(struct rcu_dynticks *rdtp, int irq);
+static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle,
+				  unsigned long *maxj);
+static bool is_sysidle_rcu_state(struct rcu_state *rsp);
+static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle,
+				  unsigned long maxj);
+static void rcu_bind_gp_kthread(void);
+static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp);
 
 #endif /* #ifndef RCU_TREE_NONCORE */
 

kernel/time/Kconfig

@@ -134,6 +134,56 @@ config NO_HZ_FULL_ALL
 	 Note the boot CPU will still be kept outside the range to
 	 handle the timekeeping duty.
 
+config NO_HZ_FULL_SYSIDLE
+	bool "Detect full-system idle state for full dynticks system"
+	depends on NO_HZ_FULL
+	default n
+	help
+	 At least one CPU must keep the scheduling-clock tick running for
+	 timekeeping purposes whenever there is a non-idle CPU, where
+	 "non-idle" also includes dynticks CPUs as long as they are
+	 running non-idle tasks.  Because the underlying adaptive-tick
+	 support cannot distinguish between all CPUs being idle and
+	 all CPUs each running a single task in dynticks mode, the
+	 underlying support simply ensures that there is always a CPU
+	 handling the scheduling-clock tick, whether or not all CPUs
+	 are idle.  This Kconfig option enables scalable detection of
+	 the all-CPUs-idle state, thus allowing the scheduling-clock
+	 tick to be disabled when all CPUs are idle.  Note that scalable
+	 detection of the all-CPUs-idle state means that larger systems
+	 will be slower to declare the all-CPUs-idle state.
+
+	 Say Y if you would like to help debug all-CPUs-idle detection.
+
+	 Say N if you are unsure.
+
+config NO_HZ_FULL_SYSIDLE_SMALL
+	int "Number of CPUs above which large-system approach is used"
+	depends on NO_HZ_FULL_SYSIDLE
+	range 1 NR_CPUS
+	default 8
+	help
+	 The full-system idle detection mechanism takes a lazy approach
+	 on large systems, as is required to attain decent scalability.
+	 However, on smaller systems, scalability is not anywhere near as
+	 large a concern as is energy efficiency.  The sysidle subsystem
+	 therefore uses a fast but non-scalable algorithm for small
+	 systems and a lazier but scalable algorithm for large systems.
+	 This Kconfig parameter defines the number of CPUs in the largest
+	 system that will be considered to be "small".
+
+	 The default value will be fine in most cases.	Battery-powered
+	 systems that (1) enable NO_HZ_FULL_SYSIDLE, (2) have larger
+	 numbers of CPUs, and (3) are suffering from battery-lifetime
+	 problems due to long sysidle latencies might wish to experiment
+	 with larger values for this Kconfig parameter.  On the other
+	 hand, they might be even better served by disabling NO_HZ_FULL
+	 entirely, given that NO_HZ_FULL is intended for HPC and
+	 real-time workloads that at present do not tend to be run on
+	 battery-powered systems.
+
+	 Take the default if you are unsure.
+
 config NO_HZ
 	bool "Old Idle dynticks config"
 	depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS

lib/debugobjects.c

@@ -381,19 +381,21 @@ void debug_object_init_on_stack(void *addr, struct debug_obj_descr *descr)
  * debug_object_activate - debug checks when an object is activated
  * @addr:	address of the object
  * @descr:	pointer to an object specific debug description structure
+ * Returns 0 for success, -EINVAL for check failed.
  */
-void debug_object_activate(void *addr, struct debug_obj_descr *descr)
+int debug_object_activate(void *addr, struct debug_obj_descr *descr)
 {
 	enum debug_obj_state state;
 	struct debug_bucket *db;
 	struct debug_obj *obj;
 	unsigned long flags;
+	int ret;
 	struct debug_obj o = { .object = addr,
 			       .state = ODEBUG_STATE_NOTAVAILABLE,
 			       .descr = descr };
 
 	if (!debug_objects_enabled)
-		return;
+		return 0;
 
 	db = get_bucket((unsigned long) addr);
 
@@ -405,23 +407,26 @@ void debug_object_activate(void *addr, struct debug_obj_descr *descr)
 		case ODEBUG_STATE_INIT:
 		case ODEBUG_STATE_INACTIVE:
 			obj->state = ODEBUG_STATE_ACTIVE;
+			ret = 0;
 			break;
 
 		case ODEBUG_STATE_ACTIVE:
 			debug_print_object(obj, "activate");
 			state = obj->state;
 			raw_spin_unlock_irqrestore(&db->lock, flags);
-			debug_object_fixup(descr->fixup_activate, addr, state);
-			return;
+			ret = debug_object_fixup(descr->fixup_activate, addr, state);
+			return ret ? -EINVAL : 0;
 
 		case ODEBUG_STATE_DESTROYED:
 			debug_print_object(obj, "activate");
+			ret = -EINVAL;
 			break;
 		default:
+			ret = 0;
 			break;
 		}
 		raw_spin_unlock_irqrestore(&db->lock, flags);
-		return;
+		return ret;
 	}
 
 	raw_spin_unlock_irqrestore(&db->lock, flags);
@@ -431,8 +436,11 @@ void debug_object_activate(void *addr, struct debug_obj_descr *descr)
 	 * true or not.
 	 */
 	if (debug_object_fixup(descr->fixup_activate, addr,
-			   ODEBUG_STATE_NOTAVAILABLE))
+			   ODEBUG_STATE_NOTAVAILABLE)) {
 		debug_print_object(&o, "activate");
+		return -EINVAL;
+	}
+	return 0;
 }
 
 /**