Merge remote-tracking branch 'rcu/rcu/next'

11 files changed, 109 insertions, 83 deletions

diff --git a/Documentation/RCU/rcu_dereference.txt b/Documentation/RCU/rcu_dereference.txt
index 1e6c0da994f544..c0bf2441a2baf5 100644
--- a/Documentation/RCU/rcu_dereference.txt
+++ b/Documentation/RCU/rcu_dereference.txt
@@ -28,7 +28,7 @@ o	You must use one of the rcu_dereference() family of primitives
 o	Avoid cancellation when using the "+" and "-" infix arithmetic
 	operators.  For example, for a given variable "x", avoid
 	"(x-x)".  There are similar arithmetic pitfalls from other
-	arithmetic operatiors, such as "(x*0)", "(x/(x+1))" or "(x%1)".
+	arithmetic operators, such as "(x*0)", "(x/(x+1))" or "(x%1)".
 	The compiler is within its rights to substitute zero for all of
 	these expressions, so that subsequent accesses no longer depend
 	on the rcu_dereference(), again possibly resulting in bugs due
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 136e6223a6c124..67709a5f1af48f 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -3106,22 +3106,35 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			in a given burst of a callback-flood test.
 
 	rcutorture.fqs_duration= [KNL]
-			Set duration of force_quiescent_state bursts.
+			Set duration of force_quiescent_state bursts
+			in microseconds.
 
 	rcutorture.fqs_holdoff= [KNL]
-			Set holdoff time within force_quiescent_state bursts.
+			Set holdoff time within force_quiescent_state bursts
+			in microseconds.
 
 	rcutorture.fqs_stutter= [KNL]
-			Set wait time between force_quiescent_state bursts.
+			Set wait time between force_quiescent_state bursts
+			in seconds.
+
+	rcutorture.gp_cond= [KNL]
+			Use conditional/asynchronous update-side
+			primitives, if available.
 
 	rcutorture.gp_exp= [KNL]
-			Use expedited update-side primitives.
+			Use expedited update-side primitives, if available.
 
 	rcutorture.gp_normal= [KNL]
-			Use normal (non-expedited) update-side primitives.
-			If both gp_exp and gp_normal are set, do both.
-			If neither gp_exp nor gp_normal are set, still
-			do both.
+			Use normal (non-expedited) asynchronous
+			update-side primitives, if available.
+
+	rcutorture.gp_sync= [KNL]
+			Use normal (non-expedited) synchronous
+			update-side primitives, if available.  If all
+			of rcutorture.gp_cond=, rcutorture.gp_exp=,
+			rcutorture.gp_normal=, and rcutorture.gp_sync=
+			are zero, rcutorture acts as if is interpreted
+			they are all non-zero.
 
 	rcutorture.n_barrier_cbs= [KNL]
 			Set callbacks/threads for rcu_barrier() testing.
@@ -3148,9 +3161,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Set time (s) between CPU-hotplug operations, or
 			zero to disable CPU-hotplug testing.
 
-	rcutorture.torture_runnable= [BOOT]
-			Start rcutorture running at boot time.
-
 	rcutorture.shuffle_interval= [KNL]
 			Set task-shuffle interval (s).  Shuffling tasks
 			allows some CPUs to go into dyntick-idle mode
@@ -3191,6 +3201,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Test RCU's dyntick-idle handling.  See also the
 			rcutorture.shuffle_interval parameter.
 
+	rcutorture.torture_runnable= [BOOT]
+			Start rcutorture running at boot time.
+
 	rcutorture.torture_type= [KNL]
 			Specify the RCU implementation to test.
 
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index 13feb697271f0a..3d06f98b2ff2c3 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -746,7 +746,7 @@ You must also be careful not to rely too much on boolean short-circuit
 evaluation.  Consider this example:
 
 	q = READ_ONCE_CTRL(a);
-	if (a || 1 > 0)
+	if (q || 1 > 0)
 		ACCESS_ONCE(b) = 1;
 
 Because the first condition cannot fault and the second condition is
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 90dfbedfbfb852..f4e0e14e700ae4 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -220,15 +220,13 @@ int __cpu_disable(void)
 	return 0;
 }
 
-static DECLARE_COMPLETION(cpu_died);
-
 /*
  * called on the thread which is asking for a CPU to be shutdown -
  * waits until shutdown has completed, or it is timed out.
  */
 void __cpu_die(unsigned int cpu)
 {
-	if (!wait_for_completion_timeout(&cpu_died, msecs_to_jiffies(5000))) {
+	if (!cpu_wait_death(cpu, 5)) {
 		pr_err("CPU%u: cpu didn't die\n", cpu);
 		return;
 	}
@@ -274,7 +272,7 @@ void __ref cpu_die(void)
 	 * this returns, power and/or clocks can be removed at any point
 	 * from this CPU and its cache by platform_cpu_kill().
 	 */
-	complete(&cpu_died);
+	(void)cpu_report_death();
 
 	/*
 	 * Ensure that the cache lines associated with that completion are
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 4cf5f51b4c9c43..def6d45ad61c02 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -309,7 +309,7 @@ static inline void rcu_sysrq_end(void)
 }
 #endif /* #else #ifdef CONFIG_RCU_STALL_COMMON */
 
-#ifdef CONFIG_RCU_USER_QS
+#ifdef CONFIG_NO_HZ_FULL
 void rcu_user_enter(void);
 void rcu_user_exit(void);
 #else
@@ -317,7 +317,7 @@ static inline void rcu_user_enter(void) { }
 static inline void rcu_user_exit(void) { }
 static inline void rcu_user_hooks_switch(struct task_struct *prev,
 					 struct task_struct *next) { }
-#endif /* CONFIG_RCU_USER_QS */
+#endif /* CONFIG_NO_HZ_FULL */
 
 #ifdef CONFIG_RCU_NOCB_CPU
 void rcu_init_nohz(void);
@@ -469,46 +469,10 @@ int rcu_read_lock_bh_held(void);
  * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an
  * RCU-sched read-side critical section.  In absence of
  * CONFIG_DEBUG_LOCK_ALLOC, this assumes we are in an RCU-sched read-side
- * critical section unless it can prove otherwise.  Note that disabling
- * of preemption (including disabling irqs) counts as an RCU-sched
- * read-side critical section.  This is useful for debug checks in functions
- * that required that they be called within an RCU-sched read-side
- * critical section.
- *
- * Check debug_lockdep_rcu_enabled() to prevent false positives during boot
- * and while lockdep is disabled.
- *
- * Note that if the CPU is in the idle loop from an RCU point of
- * view (ie: that we are in the section between rcu_idle_enter() and
- * rcu_idle_exit()) then rcu_read_lock_held() returns false even if the CPU
- * did an rcu_read_lock().  The reason for this is that RCU ignores CPUs
- * that are in such a section, considering these as in extended quiescent
- * state, so such a CPU is effectively never in an RCU read-side critical
- * section regardless of what RCU primitives it invokes.  This state of
- * affairs is required --- we need to keep an RCU-free window in idle
- * where the CPU may possibly enter into low power mode. This way we can
- * notice an extended quiescent state to other CPUs that started a grace
- * period. Otherwise we would delay any grace period as long as we run in
- * the idle task.
- *
- * Similarly, we avoid claiming an SRCU read lock held if the current
- * CPU is offline.
+ * critical section unless it can prove otherwise.
  */
 #ifdef CONFIG_PREEMPT_COUNT
-static inline int rcu_read_lock_sched_held(void)
-{
-	int lockdep_opinion = 0;
-
-	if (!debug_lockdep_rcu_enabled())
-		return 1;
-	if (!rcu_is_watching())
-		return 0;
-	if (!rcu_lockdep_current_cpu_online())
-		return 0;
-	if (debug_locks)
-		lockdep_opinion = lock_is_held(&rcu_sched_lock_map);
-	return lockdep_opinion || preempt_count() != 0 || irqs_disabled();
-}
+int rcu_read_lock_sched_held(void);
 #else /* #ifdef CONFIG_PREEMPT_COUNT */
 static inline int rcu_read_lock_sched_held(void)
 {
diff --git a/init/Kconfig b/init/Kconfig
index 194bc7c1df93ca..9fbf6668a14b19 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -537,15 +537,6 @@ config RCU_STALL_COMMON
 config CONTEXT_TRACKING
        bool
 
-config RCU_USER_QS
-	bool
-	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
-	  try to keep the timer tick on for RCU.
-
 config CONTEXT_TRACKING_FORCE
 	bool "Force context tracking"
 	depends on CONTEXT_TRACKING
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 59e32684c23b58..1cead7806ca607 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -1507,7 +1507,7 @@ static int rcu_torture_barrier_init(void)
 	int i;
 	int ret;
 
-	if (n_barrier_cbs == 0)
+	if (n_barrier_cbs <= 0)
 		return 0;
 	if (cur_ops->call == NULL || cur_ops->cb_barrier == NULL) {
 		pr_alert("%s" TORTURE_FLAG
@@ -1786,12 +1786,15 @@ rcu_torture_init(void)
 					  writer_task);
 	if (firsterr)
 		goto unwind;
-	fakewriter_tasks = kzalloc(nfakewriters * sizeof(fakewriter_tasks[0]),
-				   GFP_KERNEL);
-	if (fakewriter_tasks == NULL) {
-		VERBOSE_TOROUT_ERRSTRING("out of memory");
-		firsterr = -ENOMEM;
-		goto unwind;
+	if (nfakewriters > 0) {
+		fakewriter_tasks = kzalloc(nfakewriters *
+					   sizeof(fakewriter_tasks[0]),
+					   GFP_KERNEL);
+		if (fakewriter_tasks == NULL) {
+			VERBOSE_TOROUT_ERRSTRING("out of memory");
+			firsterr = -ENOMEM;
+			goto unwind;
+		}
 	}
 	for (i = 0; i < nfakewriters; i++) {
 		firsterr = torture_create_kthread(rcu_torture_fakewriter,
@@ -1818,7 +1821,7 @@ rcu_torture_init(void)
 		if (firsterr)
 			goto unwind;
 	}
-	if (test_no_idle_hz) {
+	if (test_no_idle_hz && shuffle_interval > 0) {
 		firsterr = torture_shuffle_init(shuffle_interval * HZ);
 		if (firsterr)
 			goto unwind;
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 65137bc28b2b36..cdb66d4ccc008e 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -701,7 +701,7 @@ void rcu_idle_enter(void)
 }
 EXPORT_SYMBOL_GPL(rcu_idle_enter);
 
-#ifdef CONFIG_RCU_USER_QS
+#ifdef CONFIG_NO_HZ_FULL
 /**
  * rcu_user_enter - inform RCU that we are resuming userspace.
  *
@@ -714,7 +714,7 @@ void rcu_user_enter(void)
 {
 	rcu_eqs_enter(1);
 }
-#endif /* CONFIG_RCU_USER_QS */
+#endif /* CONFIG_NO_HZ_FULL */
 
 /**
  * rcu_irq_exit - inform RCU that current CPU is exiting irq towards idle
@@ -828,7 +828,7 @@ void rcu_idle_exit(void)
 }
 EXPORT_SYMBOL_GPL(rcu_idle_exit);
 
-#ifdef CONFIG_RCU_USER_QS
+#ifdef CONFIG_NO_HZ_FULL
 /**
  * rcu_user_exit - inform RCU that we are exiting userspace.
  *
@@ -839,7 +839,7 @@ void rcu_user_exit(void)
 {
 	rcu_eqs_exit(1);
 }
-#endif /* CONFIG_RCU_USER_QS */
+#endif /* CONFIG_NO_HZ_FULL */
 
 /**
  * rcu_irq_enter - inform RCU that current CPU is entering irq away from idle
@@ -1178,9 +1178,11 @@ static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp)
 	j = jiffies;
 	gpa = READ_ONCE(rsp->gp_activity);
 	if (j - gpa > 2 * HZ)
-		pr_err("%s kthread starved for %ld jiffies! g%lu c%lu f%#x\n",
+		pr_err("%s kthread starved for %ld jiffies! g%lu c%lu f%#x s%d ->state=%#lx\n",
 		       rsp->name, j - gpa,
-		       rsp->gpnum, rsp->completed, rsp->gp_flags);
+		       rsp->gpnum, rsp->completed,
+		       rsp->gp_flags, rsp->gp_state,
+		       rsp->gp_kthread ? rsp->gp_kthread->state : 0);
 }
 
 /*
@@ -2041,6 +2043,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
 			wait_event_interruptible(rsp->gp_wq,
 						 READ_ONCE(rsp->gp_flags) &
 						 RCU_GP_FLAG_INIT);
+			rsp->gp_state = RCU_GP_DONE_GPS;
 			/* Locking provides needed memory barrier. */
 			if (rcu_gp_init(rsp))
 				break;
@@ -2073,6 +2076,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
 					(!READ_ONCE(rnp->qsmask) &&
 					 !rcu_preempt_blocked_readers_cgp(rnp)),
 					j);
+			rsp->gp_state = RCU_GP_DONE_FQS;
 			/* Locking provides needed memory barriers. */
 			/* If grace period done, leave loop. */
 			if (!READ_ONCE(rnp->qsmask) &&
@@ -2110,7 +2114,9 @@ static int __noreturn rcu_gp_kthread(void *arg)
 		}
 
 		/* Handle grace-period end. */
+		rsp->gp_state = RCU_GP_CLEANUP;
 		rcu_gp_cleanup(rsp);
+		rsp->gp_state = RCU_GP_CLEANED;
 	}
 }
 
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 4adb7ca0bf47a2..f1f4784f91074d 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -527,7 +527,11 @@ struct rcu_state {
 /* Values for rcu_state structure's gp_flags field. */
 #define RCU_GP_WAIT_INIT 0	/* Initial state. */
 #define RCU_GP_WAIT_GPS  1	/* Wait for grace-period start. */
-#define RCU_GP_WAIT_FQS  2	/* Wait for force-quiescent-state time. */
+#define RCU_GP_DONE_GPS  2	/* Wait done for grace-period start. */
+#define RCU_GP_WAIT_FQS  3	/* Wait for force-quiescent-state time. */
+#define RCU_GP_DONE_FQS  4	/* Wait done for force-quiescent-state time. */
+#define RCU_GP_CLEANUP   5	/* Grace-period cleanup started. */
+#define RCU_GP_CLEANED   6	/* Grace-period cleanup complete. */
 
 extern struct list_head rcu_struct_flavors;
 
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index afaecb7a799af2..fec5f48b8860e9 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -62,6 +62,55 @@ MODULE_ALIAS("rcupdate");
 
 module_param(rcu_expedited, int, 0);
 
+#if defined(CONFIG_DEBUG_LOCK_ALLOC) && defined(CONFIG_PREEMPT_COUNT)
+/**
+ * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section?
+ *
+ * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an
+ * RCU-sched read-side critical section.  In absence of
+ * CONFIG_DEBUG_LOCK_ALLOC, this assumes we are in an RCU-sched read-side
+ * critical section unless it can prove otherwise.  Note that disabling
+ * of preemption (including disabling irqs) counts as an RCU-sched
+ * read-side critical section.  This is useful for debug checks in functions
+ * that required that they be called within an RCU-sched read-side
+ * critical section.
+ *
+ * Check debug_lockdep_rcu_enabled() to prevent false positives during boot
+ * and while lockdep is disabled.
+ *
+ * Note that if the CPU is in the idle loop from an RCU point of
+ * view (ie: that we are in the section between rcu_idle_enter() and
+ * rcu_idle_exit()) then rcu_read_lock_held() returns false even if the CPU
+ * did an rcu_read_lock().  The reason for this is that RCU ignores CPUs
+ * that are in such a section, considering these as in extended quiescent
+ * state, so such a CPU is effectively never in an RCU read-side critical
+ * section regardless of what RCU primitives it invokes.  This state of
+ * affairs is required --- we need to keep an RCU-free window in idle
+ * where the CPU may possibly enter into low power mode. This way we can
+ * notice an extended quiescent state to other CPUs that started a grace
+ * period. Otherwise we would delay any grace period as long as we run in
+ * the idle task.
+ *
+ * Similarly, we avoid claiming an SRCU read lock held if the current
+ * CPU is offline.
+ */
+int rcu_read_lock_sched_held(void)
+{
+	int lockdep_opinion = 0;
+
+	if (!debug_lockdep_rcu_enabled())
+		return 1;
+	if (!rcu_is_watching())
+		return 0;
+	if (!rcu_lockdep_current_cpu_online())
+		return 0;
+	if (debug_locks)
+		lockdep_opinion = lock_is_held(&rcu_sched_lock_map);
+	return lockdep_opinion || preempt_count() != 0 || irqs_disabled();
+}
+EXPORT_SYMBOL(rcu_read_lock_sched_held);
+#endif
+
 #ifndef CONFIG_TINY_RCU
 
 static atomic_t rcu_expedited_nesting =
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index 579ce1b929afde..4008d9f95dd724 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -92,12 +92,10 @@ config NO_HZ_FULL
 	depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS
 	# We need at least one periodic CPU for timekeeping
 	depends on SMP
-	# RCU_USER_QS dependency
 	depends on HAVE_CONTEXT_TRACKING
 	# VIRT_CPU_ACCOUNTING_GEN dependency
 	depends on HAVE_VIRT_CPU_ACCOUNTING_GEN
 	select NO_HZ_COMMON
-	select RCU_USER_QS
 	select RCU_NOCB_CPU
 	select VIRT_CPU_ACCOUNTING_GEN
 	select IRQ_WORK