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

…ux/kernel/git/tip/tip

Pull RCU changes from Ingo Molnar:
 "SRCU changes:

   - These include debugging aids, updates that move towards the goal of
     permitting srcu_read_lock() and srcu_read_unlock() to be used from
     idle and offline CPUs, and a few small fixes.

  Changes to rcutorture and to RCU documentation:

   - Posted to LKML at https://lkml.org/lkml/2013/1/26/188

  Enhancements to uniprocessor handling in tiny RCU:

   - Posted to LKML at https://lkml.org/lkml/2013/1/27/2

  Tag RCU callbacks with grace-period number to simplify callback
  advancement:

   - Posted to LKML at https://lkml.org/lkml/2013/1/26/203

  Miscellaneous fixes:

   - Posted to LKML at https://lkml.org/lkml/2013/1/26/204"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (27 commits)
  srcu: use ACCESS_ONCE() to access sp->completed in srcu_read_lock()
  srcu: Update synchronize_srcu_expedited()'s comments
  srcu: Update synchronize_srcu()'s comments
  srcu: Remove checks preventing idle CPUs from calling srcu_read_lock()
  srcu: Remove checks preventing offline CPUs from calling srcu_read_lock()
  srcu: Simple cleanup for cleanup_srcu_struct()
  srcu: Add might_sleep() annotation to synchronize_srcu()
  srcu: Simplify __srcu_read_unlock() via this_cpu_dec()
  rcu: Allow rcutorture to be built at low optimization levels
  rcu: Make rcutorture's shuffler task shuffle recently added tasks
  rcu: Allow TREE_PREEMPT_RCU on UP systems
  rcu: Provide RCU CPU stall warnings for tiny RCU
  context_tracking: Add comments on interface and internals
  rcu: Remove obsolete Kconfig option from comment
  rcu: Remove unused code originally used for context tracking
  rcu: Consolidate debugging Kconfig options
  rcu: Correct 'optimized' to 'optimize' in header comment
  rcu: Trace callback acceleration
  rcu: Tag callback lists with corresponding grace-period number
  rcutorture: Don't compare ptr with 0
  ...

Documentation/atomic_ops.txt

@@ -253,6 +253,8 @@ This performs an atomic exchange operation on the atomic variable v, setting
 the given new value.  It returns the old value that the atomic variable v had
 just before the operation.
 
+atomic_xchg requires explicit memory barriers around the operation.
+
 	int atomic_cmpxchg(atomic_t *v, int old, int new);
 
 This performs an atomic compare exchange operation on the atomic value v,

Documentation/memory-barriers.txt

@@ -1685,6 +1685,7 @@ explicit lock operations, described later).  These include:
 
 	xchg();
 	cmpxchg();
+	atomic_xchg();
 	atomic_cmpxchg();
 	atomic_inc_return();
 	atomic_dec_return();

include/linux/rcupdate.h

@@ -53,7 +53,10 @@ extern int rcutorture_runnable; /* for sysctl */
 extern void rcutorture_record_test_transition(void);
 extern void rcutorture_record_progress(unsigned long vernum);
 extern void do_trace_rcu_torture_read(char *rcutorturename,
-				      struct rcu_head *rhp);
+				      struct rcu_head *rhp,
+				      unsigned long secs,
+				      unsigned long c_old,
+				      unsigned long c);
 #else
 static inline void rcutorture_record_test_transition(void)
 {
@@ -63,9 +66,13 @@ static inline void rcutorture_record_progress(unsigned long vernum)
 }
 #ifdef CONFIG_RCU_TRACE
 extern void do_trace_rcu_torture_read(char *rcutorturename,
-				      struct rcu_head *rhp);
+				      struct rcu_head *rhp,
+				      unsigned long secs,
+				      unsigned long c_old,
+				      unsigned long c);
 #else
-#define do_trace_rcu_torture_read(rcutorturename, rhp) do { } while (0)
+#define do_trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \
+	do { } while (0)
 #endif
 #endif
 
@@ -749,7 +756,7 @@ static inline void rcu_preempt_sleep_check(void)
  * preemptible RCU implementations (TREE_PREEMPT_RCU and TINY_PREEMPT_RCU)
  * in CONFIG_PREEMPT kernel builds, RCU read-side critical sections may
  * be preempted, but explicit blocking is illegal.  Finally, in preemptible
- * RCU implementations in real-time (CONFIG_PREEMPT_RT) kernel builds,
+ * RCU implementations in real-time (with -rt patchset) kernel builds,
  * RCU read-side critical sections may be preempted and they may also
  * block, but only when acquiring spinlocks that are subject to priority
  * inheritance.

include/linux/srcu.h

@@ -151,30 +151,14 @@ void srcu_barrier(struct srcu_struct *sp);
  * Checks 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 srcu_read_lock_held() returns false even if
- * the CPU did an srcu_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.
+ * Note that SRCU is based on its own statemachine and it doesn't
+ * relies on normal RCU, it can be called from the CPU which
+ * is in the idle loop from an RCU point of view or offline.
  */
 static inline int srcu_read_lock_held(struct srcu_struct *sp)
 {
 	if (!debug_lockdep_rcu_enabled())
 		return 1;
-	if (rcu_is_cpu_idle())
-		return 0;
-	if (!rcu_lockdep_current_cpu_online())
-		return 0;
 	return lock_is_held(&sp->dep_map);
 }
 
@@ -236,8 +220,6 @@ static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp)
 	int retval = __srcu_read_lock(sp);
 
 	rcu_lock_acquire(&(sp)->dep_map);
-	rcu_lockdep_assert(!rcu_is_cpu_idle(),
-			   "srcu_read_lock() used illegally while idle");
 	return retval;
 }
 
@@ -251,8 +233,6 @@ static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp)
 static inline void srcu_read_unlock(struct srcu_struct *sp, int idx)
 	__releases(sp)
 {
-	rcu_lockdep_assert(!rcu_is_cpu_idle(),
-			   "srcu_read_unlock() used illegally while idle");
 	rcu_lock_release(&(sp)->dep_map);
 	__srcu_read_unlock(sp, idx);
 }

include/trace/events/rcu.h

@@ -44,8 +44,10 @@ TRACE_EVENT(rcu_utilization,
  * of a new grace period or the end of an old grace period ("cpustart"
  * and "cpuend", respectively), a CPU passing through a quiescent
  * state ("cpuqs"), a CPU coming online or going offline ("cpuonl"
- * and "cpuofl", respectively), and a CPU being kicked for being too
- * long in dyntick-idle mode ("kick").
+ * and "cpuofl", respectively), a CPU being kicked for being too
+ * long in dyntick-idle mode ("kick"), a CPU accelerating its new
+ * callbacks to RCU_NEXT_READY_TAIL ("AccReadyCB"), and a CPU
+ * accelerating its new callbacks to RCU_WAIT_TAIL ("AccWaitCB").
  */
 TRACE_EVENT(rcu_grace_period,
 
@@ -393,15 +395,15 @@ TRACE_EVENT(rcu_kfree_callback,
  */
 TRACE_EVENT(rcu_batch_start,
 
-	TP_PROTO(char *rcuname, long qlen_lazy, long qlen, int blimit),
+	TP_PROTO(char *rcuname, long qlen_lazy, long qlen, long blimit),
 
 	TP_ARGS(rcuname, qlen_lazy, qlen, blimit),
 
 	TP_STRUCT__entry(
 		__field(char *, rcuname)
 		__field(long, qlen_lazy)
 		__field(long, qlen)
-		__field(int, blimit)
+		__field(long, blimit)
 	),
 
 	TP_fast_assign(
@@ -411,7 +413,7 @@ TRACE_EVENT(rcu_batch_start,
 		__entry->blimit = blimit;
 	),
 
-	TP_printk("%s CBs=%ld/%ld bl=%d",
+	TP_printk("%s CBs=%ld/%ld bl=%ld",
 		  __entry->rcuname, __entry->qlen_lazy, __entry->qlen,
 		  __entry->blimit)
 );
@@ -523,22 +525,30 @@ TRACE_EVENT(rcu_batch_end,
  */
 TRACE_EVENT(rcu_torture_read,
 
-	TP_PROTO(char *rcutorturename, struct rcu_head *rhp),
+	TP_PROTO(char *rcutorturename, struct rcu_head *rhp,
+		 unsigned long secs, unsigned long c_old, unsigned long c),
 
-	TP_ARGS(rcutorturename, rhp),
+	TP_ARGS(rcutorturename, rhp, secs, c_old, c),
 
 	TP_STRUCT__entry(
 		__field(char *, rcutorturename)
 		__field(struct rcu_head *, rhp)
+		__field(unsigned long, secs)
+		__field(unsigned long, c_old)
+		__field(unsigned long, c)
 	),
 
 	TP_fast_assign(
 		__entry->rcutorturename = rcutorturename;
 		__entry->rhp = rhp;
+		__entry->secs = secs;
+		__entry->c_old = c_old;
+		__entry->c = c;
 	),
 
-	TP_printk("%s torture read %p",
-		  __entry->rcutorturename, __entry->rhp)
+	TP_printk("%s torture read %p %luus c: %lu %lu",
+		  __entry->rcutorturename, __entry->rhp,
+		  __entry->secs, __entry->c_old, __entry->c)
 );
 
 /*
@@ -608,7 +618,8 @@ TRACE_EVENT(rcu_barrier,
 #define trace_rcu_invoke_kfree_callback(rcuname, rhp, offset) do { } while (0)
 #define trace_rcu_batch_end(rcuname, callbacks_invoked, cb, nr, iit, risk) \
 	do { } while (0)
-#define trace_rcu_torture_read(rcutorturename, rhp) do { } while (0)
+#define trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \
+	do { } while (0)
 #define trace_rcu_barrier(name, s, cpu, cnt, done) do { } while (0)
 
 #endif /* #else #ifdef CONFIG_RCU_TRACE */

init/Kconfig

@@ -453,14 +453,16 @@ config TREE_RCU
 
 config TREE_PREEMPT_RCU
 	bool "Preemptible tree-based hierarchical RCU"
-	depends on PREEMPT && SMP
+	depends on PREEMPT
 	help
 	  This option selects the RCU implementation that is
 	  designed for very large SMP systems with hundreds or
 	  thousands of CPUs, but for which real-time response
 	  is also required.  It also scales down nicely to
 	  smaller systems.
 
+	  Select this option if you are unsure.
+
 config TINY_RCU
 	bool "UP-only small-memory-footprint RCU"
 	depends on !PREEMPT && !SMP
@@ -486,6 +488,14 @@ config PREEMPT_RCU
 	  This option enables preemptible-RCU code that is common between
 	  the TREE_PREEMPT_RCU and TINY_PREEMPT_RCU implementations.
 
+config RCU_STALL_COMMON
+	def_bool ( TREE_RCU || TREE_PREEMPT_RCU || RCU_TRACE )
+	help
+	  This option enables RCU CPU stall code that is common between
+	  the TINY and TREE variants of RCU.  The purpose is to allow
+	  the tiny variants to disable RCU CPU stall warnings, while
+	  making these warnings mandatory for the tree variants.
+
 config CONTEXT_TRACKING
        bool
 

kernel/context_tracking.c

@@ -1,3 +1,19 @@
+/*
+ * Context tracking: Probe on high level context boundaries such as kernel
+ * and userspace. This includes syscalls and exceptions entry/exit.
+ *
+ * This is used by RCU to remove its dependency on the timer tick while a CPU
+ * runs in userspace.
+ *
+ *  Started by Frederic Weisbecker:
+ *
+ * Copyright (C) 2012 Red Hat, Inc., Frederic Weisbecker <fweisbec@redhat.com>
+ *
+ * Many thanks to Gilad Ben-Yossef, Paul McKenney, Ingo Molnar, Andrew Morton,
+ * Steven Rostedt, Peter Zijlstra for suggestions and improvements.
+ *
+ */
+
 #include <linux/context_tracking.h>
 #include <linux/rcupdate.h>
 #include <linux/sched.h>
@@ -6,8 +22,8 @@
 
 struct context_tracking {
 	/*
-	 * When active is false, hooks are not set to
-	 * minimize overhead: TIF flags are cleared
+	 * When active is false, probes are unset in order
+	 * to minimize overhead: TIF flags are cleared
 	 * and calls to user_enter/exit are ignored. This
 	 * may be further optimized using static keys.
 	 */
@@ -24,6 +40,15 @@ static DEFINE_PER_CPU(struct context_tracking, context_tracking) = {
 #endif
 };
 
+/**
+ * user_enter - Inform the context tracking that the CPU is going to
+ *              enter userspace mode.
+ *
+ * This function must be called right before we switch from the kernel
+ * to userspace, when it's guaranteed the remaining kernel instructions
+ * to execute won't use any RCU read side critical section because this
+ * function sets RCU in extended quiescent state.
+ */
 void user_enter(void)
 {
 	unsigned long flags;
@@ -39,40 +64,70 @@ void user_enter(void)
 	if (in_interrupt())
 		return;
 
+	/* Kernel threads aren't supposed to go to userspace */
 	WARN_ON_ONCE(!current->mm);
 
 	local_irq_save(flags);
 	if (__this_cpu_read(context_tracking.active) &&
 	    __this_cpu_read(context_tracking.state) != IN_USER) {
 		__this_cpu_write(context_tracking.state, IN_USER);
+		/*
+		 * At this stage, only low level arch entry code remains and
+		 * then we'll run in userspace. We can assume there won't be
+		 * any RCU read-side critical section until the next call to
+		 * user_exit() or rcu_irq_enter(). Let's remove RCU's dependency
+		 * on the tick.
+		 */
 		rcu_user_enter();
 	}
 	local_irq_restore(flags);
 }
 
+
+/**
+ * user_exit - Inform the context tracking that the CPU is
+ *             exiting userspace mode and entering the kernel.
+ *
+ * This function must be called after we entered the kernel from userspace
+ * before any use of RCU read side critical section. This potentially include
+ * any high level kernel code like syscalls, exceptions, signal handling, etc...
+ *
+ * This call supports re-entrancy. This way it can be called from any exception
+ * handler without needing to know if we came from userspace or not.
+ */
 void user_exit(void)
 {
 	unsigned long flags;
 
-	/*
-	 * Some contexts may involve an exception occuring in an irq,
-	 * leading to that nesting:
-	 * rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit()
-	 * This would mess up the dyntick_nesting count though. And rcu_irq_*()
-	 * helpers are enough to protect RCU uses inside the exception. So
-	 * just return immediately if we detect we are in an IRQ.
-	 */
 	if (in_interrupt())
 		return;
 
 	local_irq_save(flags);
 	if (__this_cpu_read(context_tracking.state) == IN_USER) {
 		__this_cpu_write(context_tracking.state, IN_KERNEL);
+		/*
+		 * We are going to run code that may use RCU. Inform
+		 * RCU core about that (ie: we may need the tick again).
+		 */
 		rcu_user_exit();
 	}
 	local_irq_restore(flags);
 }
 
+
+/**
+ * context_tracking_task_switch - context switch the syscall callbacks
+ * @prev: the task that is being switched out
+ * @next: the task that is being switched in
+ *
+ * The context tracking uses the syscall slow path to implement its user-kernel
+ * boundaries probes on syscalls. This way it doesn't impact the syscall fast
+ * path on CPUs that don't do context tracking.
+ *
+ * But we need to clear the flag on the previous task because it may later
+ * migrate to some CPU that doesn't do the context tracking. As such the TIF
+ * flag may not be desired there.
+ */
 void context_tracking_task_switch(struct task_struct *prev,
 			     struct task_struct *next)
 {

kernel/rcu.h

@@ -111,4 +111,11 @@ static inline bool __rcu_reclaim(char *rn, struct rcu_head *head)
 
 extern int rcu_expedited;
 
+#ifdef CONFIG_RCU_STALL_COMMON
+
+extern int rcu_cpu_stall_suppress;
+int rcu_jiffies_till_stall_check(void);
+
+#endif /* #ifdef CONFIG_RCU_STALL_COMMON */
+
 #endif /* __LINUX_RCU_H */