Merge commit '29ce831000081dd757d3116bf774aafffc4b6b20' into next

* commit '29ce831000081dd757d3116bf774aafffc4b6b20': (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 '29ce831000081dd757d3116bf774aafffc4b6b20': (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
  ...

4 files changed, 90 insertions, 2 deletions

diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index bea0ac750712..6c12989839d9 100644
--- a/include/linux/interrupt.h
+++ b/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
 };
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index ff422d2b7f90..99f9aa7c2804 100644
--- a/include/linux/rcupdate.h
+++ b/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 */
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 30ebd7c8d874..52b3e0281fd0 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -100,6 +100,14 @@ static inline void rcu_note_context_switch(int cpu)
 }
 
 /*
+ * 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.
  */
 static inline long rcu_batches_completed(void)
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 3a933482734a..e65d06634dd8 100644
--- a/include/linux/rcutree.h
+++ b/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);