Merge branch 'next' (accumulated 3.16 merge window patches) into master

Now that 3.15 is released, this merges the 'next' branch into 'master',
bringing us to the normal situation where my 'master' branch is the
merge window.

* accumulated work in next: (6809 commits)
  ufs: sb mutex merge + mutex_destroy
  powerpc: update comments for generic idle conversion
  cris: update comments for generic idle conversion
  idle: remove cpu_idle() forward declarations
  nbd: zero from and len fields in NBD_CMD_DISCONNECT.
  mm: convert some level-less printks to pr_*
  MAINTAINERS: adi-buildroot-devel is moderated
  MAINTAINERS: add linux-api for review of API/ABI changes
  mm/kmemleak-test.c: use pr_fmt for logging
  fs/dlm/debug_fs.c: replace seq_printf by seq_puts
  fs/dlm/lockspace.c: convert simple_str to kstr
  fs/dlm/config.c: convert simple_str to kstr
  mm: mark remap_file_pages() syscall as deprecated
  mm: memcontrol: remove unnecessary memcg argument from soft limit functions
  mm: memcontrol: clean up memcg zoneinfo lookup
  mm/memblock.c: call kmemleak directly from memblock_(alloc|free)
  mm/mempool.c: update the kmemleak stack trace for mempool allocations
  lib/radix-tree.c: update the kmemleak stack trace for radix tree allocations
  mm: introduce kmemleak_update_trace()
  mm/kmemleak.c: use %u to print ->checksum
  ...

1 files changed, 71 insertions, 1 deletions

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 00a7fd61b3c..5a75d19aa66 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -44,6 +44,7 @@
 #include <linux/debugobjects.h>
 #include <linux/bug.h>
 #include <linux/compiler.h>
+#include <linux/percpu.h>
 #include <asm/barrier.h>
 
 extern int rcu_expedited; /* for sysctl */
@@ -51,7 +52,17 @@ extern int rcu_expedited; /* for sysctl */
 extern int rcutorture_runnable; /* for sysctl */
 #endif /* #ifdef CONFIG_RCU_TORTURE_TEST */
 
+enum rcutorture_type {
+	RCU_FLAVOR,
+	RCU_BH_FLAVOR,
+	RCU_SCHED_FLAVOR,
+	SRCU_FLAVOR,
+	INVALID_RCU_FLAVOR
+};
+
 #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
+void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
+			    unsigned long *gpnum, unsigned long *completed);
 void rcutorture_record_test_transition(void);
 void rcutorture_record_progress(unsigned long vernum);
 void do_trace_rcu_torture_read(const char *rcutorturename,
@@ -60,6 +71,15 @@ void do_trace_rcu_torture_read(const char *rcutorturename,
 			       unsigned long c_old,
 			       unsigned long c);
 #else
+static inline void rcutorture_get_gp_data(enum rcutorture_type test_type,
+					  int *flags,
+					  unsigned long *gpnum,
+					  unsigned long *completed)
+{
+	*flags = 0;
+	*gpnum = 0;
+	*completed = 0;
+}
 static inline void rcutorture_record_test_transition(void)
 {
 }
@@ -228,6 +248,18 @@ void rcu_idle_exit(void);
 void rcu_irq_enter(void);
 void rcu_irq_exit(void);
 
+#ifdef CONFIG_RCU_STALL_COMMON
+void rcu_sysrq_start(void);
+void rcu_sysrq_end(void);
+#else /* #ifdef CONFIG_RCU_STALL_COMMON */
+static inline void rcu_sysrq_start(void)
+{
+}
+static inline void rcu_sysrq_end(void)
+{
+}
+#endif /* #else #ifdef CONFIG_RCU_STALL_COMMON */
+
 #ifdef CONFIG_RCU_USER_QS
 void rcu_user_enter(void);
 void rcu_user_exit(void);
@@ -268,6 +300,41 @@ bool __rcu_is_watching(void);
 #endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP) */
 
 /*
+ * Hooks for cond_resched() and friends to avoid RCU CPU stall warnings.
+ */
+
+#define RCU_COND_RESCHED_LIM 256	/* ms vs. 100s of ms. */
+DECLARE_PER_CPU(int, rcu_cond_resched_count);
+void rcu_resched(void);
+
+/*
+ * Is it time to report RCU quiescent states?
+ *
+ * Note unsynchronized access to rcu_cond_resched_count.  Yes, we might
+ * increment some random CPU's count, and possibly also load the result from
+ * yet another CPU's count.  We might even clobber some other CPU's attempt
+ * to zero its counter.  This is all OK because the goal is not precision,
+ * but rather reasonable amortization of rcu_note_context_switch() overhead
+ * and extremely high probability of avoiding RCU CPU stall warnings.
+ * Note that this function has to be preempted in just the wrong place,
+ * many thousands of times in a row, for anything bad to happen.
+ */
+static inline bool rcu_should_resched(void)
+{
+	return raw_cpu_inc_return(rcu_cond_resched_count) >=
+	       RCU_COND_RESCHED_LIM;
+}
+
+/*
+ * Report quiscent states to RCU if it is time to do so.
+ */
+static inline void rcu_cond_resched(void)
+{
+	if (unlikely(rcu_should_resched()))
+		rcu_resched();
+}
+
+/*
  * Infrastructure to implement the synchronize_() primitives in
  * TREE_RCU and rcu_barrier_() primitives in TINY_RCU.
  */
@@ -328,7 +395,7 @@ extern struct lockdep_map rcu_lock_map;
 extern struct lockdep_map rcu_bh_lock_map;
 extern struct lockdep_map rcu_sched_lock_map;
 extern struct lockdep_map rcu_callback_map;
-extern int debug_lockdep_rcu_enabled(void);
+int debug_lockdep_rcu_enabled(void);
 
 /**
  * rcu_read_lock_held() - might we be in RCU read-side critical section?
@@ -949,6 +1016,9 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
  * pointers, but you must use rcu_assign_pointer() to initialize the
  * external-to-structure pointer -after- you have completely initialized
  * the reader-accessible portions of the linked structure.
+ *
+ * Note that unlike rcu_assign_pointer(), RCU_INIT_POINTER() provides no
+ * ordering guarantees for either the CPU or the compiler.
  */
 #define RCU_INIT_POINTER(p, v) \
 	do { \