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

Pull RCU updates from Ingo Molnar:
 "The main RCU changes in this cycle are:

   - the combination of tree geometry-initialization simplifications and
     OS-jitter-reduction changes to expedited grace periods.  These two
     are stacked due to the large number of conflicts that would
     otherwise result.

   - privatize smp_mb__after_unlock_lock().

     This commit moves the definition of smp_mb__after_unlock_lock() to
     kernel/rcu/tree.h, in recognition of the fact that RCU is the only
     thing using this, that nothing else is likely to use it, and that
     it is likely to go away completely.

   - documentation updates.

   - torture-test updates.

   - misc fixes"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (60 commits)
  rcu,locking: Privatize smp_mb__after_unlock_lock()
  rcu: Silence lockdep false positive for expedited grace periods
  rcu: Don't disable CPU hotplug during OOM notifiers
  scripts: Make checkpatch.pl warn on expedited RCU grace periods
  rcu: Update MAINTAINERS entry
  rcu: Clarify CONFIG_RCU_EQS_DEBUG help text
  rcu: Fix backwards RCU_LOCKDEP_WARN() in synchronize_rcu_tasks()
  rcu: Rename rcu_lockdep_assert() to RCU_LOCKDEP_WARN()
  rcu: Make rcu_is_watching() really notrace
  cpu: Wait for RCU grace periods concurrently
  rcu: Create a synchronize_rcu_mult()
  rcu: Fix obsolete priority-boosting comment
  rcu: Use WRITE_ONCE in RCU_INIT_POINTER
  rcu: Hide RCU_NOCB_CPU behind RCU_EXPERT
  rcu: Add RCU-sched flavors of get-state and cond-sync
  rcu: Add fastpath bypassing funnel locking
  rcu: Rename RCU_GP_DONE_FQS to RCU_GP_DOING_FQS
  rcu: Pull out wait_event*() condition into helper function
  documentation: Describe new expedited stall warnings
  rcu: Add stall warnings to synchronize_sched_expedited()
  ...

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

Documentation/RCU/stallwarn.txt

@@ -26,12 +26,6 @@ CONFIG_RCU_CPU_STALL_TIMEOUT
 	Stall-warning messages may be enabled and disabled completely via
 	/sys/module/rcupdate/parameters/rcu_cpu_stall_suppress.
 
-CONFIG_RCU_CPU_STALL_INFO
-
-	This kernel configuration parameter causes the stall warning to
-	print out additional per-CPU diagnostic information, including
-	information on scheduling-clock ticks and RCU's idle-CPU tracking.
-
 RCU_STALL_DELAY_DELTA
 
 	Although the lockdep facility is extremely useful, it does add
@@ -101,15 +95,13 @@ interact.  Please note that it is not possible to entirely eliminate this
 sort of false positive without resorting to things like stop_machine(),
 which is overkill for this sort of problem.
 
-If the CONFIG_RCU_CPU_STALL_INFO kernel configuration parameter is set,
-more information is printed with the stall-warning message, for example:
+Recent kernels will print a long form of the stall-warning message:
 
 	INFO: rcu_preempt detected stall on CPU
 	0: (63959 ticks this GP) idle=241/3fffffffffffffff/0 softirq=82/543
 	   (t=65000 jiffies)
 
-In kernels with CONFIG_RCU_FAST_NO_HZ, even more information is
-printed:
+In kernels with CONFIG_RCU_FAST_NO_HZ, more information is printed:
 
 	INFO: rcu_preempt detected stall on CPU
 	0: (64628 ticks this GP) idle=dd5/3fffffffffffffff/0 softirq=82/543 last_accelerate: a345/d342 nonlazy_posted: 25 .D
@@ -171,6 +163,23 @@ message will be about three times the interval between the beginning
 of the stall and the first message.
 
 
+Stall Warnings for Expedited Grace Periods
+
+If an expedited grace period detects a stall, it will place a message
+like the following in dmesg:
+
+	INFO: rcu_sched detected expedited stalls on CPUs: { 1 2 6 } 26009 jiffies s: 1043
+
+This indicates that CPUs 1, 2, and 6 have failed to respond to a
+reschedule IPI, that the expedited grace period has been going on for
+26,009 jiffies, and that the expedited grace-period sequence counter is
+1043.  The fact that this last value is odd indicates that an expedited
+grace period is in flight.
+
+It is entirely possible to see stall warnings from normal and from
+expedited grace periods at about the same time from the same run.
+
+
 What Causes RCU CPU Stall Warnings?
 
 So your kernel printed an RCU CPU stall warning.  The next question is

Documentation/RCU/trace.txt

@@ -237,42 +237,26 @@ o	"ktl" is the low-order 16 bits (in hexadecimal) of the count of
 
 The output of "cat rcu/rcu_preempt/rcuexp" looks as follows:
 
-s=21872 d=21872 w=0 tf=0 wd1=0 wd2=0 n=0 sc=21872 dt=21872 dl=0 dx=21872
+s=21872 wd0=0 wd1=0 wd2=0 wd3=5 n=0 enq=0 sc=21872
 
 These fields are as follows:
 
-o	"s" is the starting sequence number.
+o	"s" is the sequence number, with an odd number indicating that
+	an expedited grace period is in progress.
 
-o	"d" is the ending sequence number.  When the starting and ending
-	numbers differ, there is an expedited grace period in progress.
-
-o	"w" is the number of times that the sequence numbers have been
-	in danger of wrapping.
-
-o	"tf" is the number of times that contention has resulted in a
-	failure to begin an expedited grace period.
-
-o	"wd1" and "wd2" are the number of times that an attempt to
-	start an expedited grace period found that someone else had
-	completed an expedited grace period that satisfies the
+o	"wd0", "wd1", "wd2", and "wd3" are the number of times that an
+	attempt to start an expedited grace period found that someone
+	else had completed an expedited grace period that satisfies the
 	attempted request.  "Our work is done."
 
-o	"n" is number of times that contention was so great that
-	the request was demoted from an expedited grace period to
-	a normal grace period.
+o	"n" is number of times that a concurrent CPU-hotplug operation
+	forced a fallback to a normal grace period.
+
+o	"enq" is the number of quiescent states still outstanding.
 
 o	"sc" is the number of times that the attempt to start a
 	new expedited grace period succeeded.
 
-o	"dt" is the number of times that we attempted to update
-	the "d" counter.
-
-o	"dl" is the number of times that we failed to update the "d"
-	counter.
-
-o	"dx" is the number of times that we succeeded in updating
-	the "d" counter.
-
 
 The output of "cat rcu/rcu_preempt/rcugp" looks as follows:
 

Documentation/RCU/whatisRCU.txt

@@ -883,7 +883,7 @@ All:  lockdep-checked RCU-protected pointer access
 
 	rcu_access_pointer
 	rcu_dereference_raw
-	rcu_lockdep_assert
+	RCU_LOCKDEP_WARN
 	rcu_sleep_check
 	RCU_NONIDLE
 

Documentation/kernel-parameters.txt

@@ -3137,22 +3137,35 @@ 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.
@@ -3179,9 +3192,6 @@ 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
@@ -3222,6 +3232,9 @@ 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.
 

MAINTAINERS

@@ -8518,7 +8518,7 @@ M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
 M:	Josh Triplett <josh@joshtriplett.org>
 R:	Steven Rostedt <rostedt@goodmis.org>
 R:	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
-R:	Lai Jiangshan <laijs@cn.fujitsu.com>
+R:	Lai Jiangshan <jiangshanlai@gmail.com>
 L:	linux-kernel@vger.kernel.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
@@ -8545,7 +8545,7 @@ M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
 M:	Josh Triplett <josh@joshtriplett.org>
 R:	Steven Rostedt <rostedt@goodmis.org>
 R:	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
-R:	Lai Jiangshan <laijs@cn.fujitsu.com>
+R:	Lai Jiangshan <jiangshanlai@gmail.com>
 L:	linux-kernel@vger.kernel.org
 W:	http://www.rdrop.com/users/paulmck/RCU/
 S:	Supported
@@ -9417,7 +9417,7 @@ F:	include/linux/sl?b*.h
 F:	mm/sl?b*
 
 SLEEPABLE READ-COPY UPDATE (SRCU)
-M:	Lai Jiangshan <laijs@cn.fujitsu.com>
+M:	Lai Jiangshan <jiangshanlai@gmail.com>
 M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
 M:	Josh Triplett <josh@joshtriplett.org>
 R:	Steven Rostedt <rostedt@goodmis.org>

arch/powerpc/include/asm/spinlock.h

@@ -28,8 +28,6 @@
 #include <asm/synch.h>
 #include <asm/ppc-opcode.h>
 
-#define smp_mb__after_unlock_lock()	smp_mb()  /* Full ordering for lock. */
-
 #ifdef CONFIG_PPC64
 /* use 0x800000yy when locked, where yy == CPU number */
 #ifdef __BIG_ENDIAN__

arch/x86/kernel/cpu/mcheck/mce.c

@@ -54,9 +54,9 @@ static DEFINE_MUTEX(mce_chrdev_read_mutex);
 
 #define rcu_dereference_check_mce(p) \
 ({ \
-	rcu_lockdep_assert(rcu_read_lock_sched_held() || \
-			   lockdep_is_held(&mce_chrdev_read_mutex), \
-			   "suspicious rcu_dereference_check_mce() usage"); \
+	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \
+			 !lockdep_is_held(&mce_chrdev_read_mutex), \
+			 "suspicious rcu_dereference_check_mce() usage"); \
 	smp_load_acquire(&(p)); \
 })
 

arch/x86/kernel/traps.c

@@ -136,7 +136,7 @@ enum ctx_state ist_enter(struct pt_regs *regs)
 	preempt_count_add(HARDIRQ_OFFSET);
 
 	/* This code is a bit fragile.  Test it. */
-	rcu_lockdep_assert(rcu_is_watching(), "ist_enter didn't work");
+	RCU_LOCKDEP_WARN(!rcu_is_watching(), "ist_enter didn't work");
 
 	return prev_state;
 }

drivers/base/power/opp.c

@@ -110,8 +110,8 @@ static DEFINE_MUTEX(dev_opp_list_lock);
 
 #define opp_rcu_lockdep_assert()					\
 do {									\
-	rcu_lockdep_assert(rcu_read_lock_held() ||			\
-				lockdep_is_held(&dev_opp_list_lock),	\
+	RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&			\
+				!lockdep_is_held(&dev_opp_list_lock),	\
 			   "Missing rcu_read_lock() or "		\
 			   "dev_opp_list_lock protection");		\
 } while (0)

include/linux/fdtable.h

@@ -86,8 +86,8 @@ static inline struct file *__fcheck_files(struct files_struct *files, unsigned i
 
 static inline struct file *fcheck_files(struct files_struct *files, unsigned int fd)
 {
-	rcu_lockdep_assert(rcu_read_lock_held() ||
-			   lockdep_is_held(&files->file_lock),
+	RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&
+			   !lockdep_is_held(&files->file_lock),
 			   "suspicious rcu_dereference_check() usage");
 	return __fcheck_files(files, fd);
 }

include/linux/rcupdate.h

@@ -226,6 +226,37 @@ struct rcu_synchronize {
 };
 void wakeme_after_rcu(struct rcu_head *head);
 
+void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array,
+		   struct rcu_synchronize *rs_array);
+
+#define _wait_rcu_gp(checktiny, ...) \
+do { \
+	call_rcu_func_t __crcu_array[] = { __VA_ARGS__ }; \
+	const int __n = ARRAY_SIZE(__crcu_array); \
+	struct rcu_synchronize __rs_array[__n]; \
+	\
+	__wait_rcu_gp(checktiny, __n, __crcu_array, __rs_array); \
+} while (0)
+
+#define wait_rcu_gp(...) _wait_rcu_gp(false, __VA_ARGS__)
+
+/**
+ * synchronize_rcu_mult - Wait concurrently for multiple grace periods
+ * @...: List of call_rcu() functions for the flavors to wait on.
+ *
+ * This macro waits concurrently for multiple flavors of RCU grace periods.
+ * For example, synchronize_rcu_mult(call_rcu, call_rcu_bh) would wait
+ * on concurrent RCU and RCU-bh grace periods.  Waiting on a give SRCU
+ * domain requires you to write a wrapper function for that SRCU domain's
+ * call_srcu() function, supplying the corresponding srcu_struct.
+ *
+ * If Tiny RCU, tell _wait_rcu_gp() not to bother waiting for RCU
+ * or RCU-bh, given that anywhere synchronize_rcu_mult() can be called
+ * is automatically a grace period.
+ */
+#define synchronize_rcu_mult(...) \
+	_wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), __VA_ARGS__)
+
 /**
  * call_rcu_tasks() - Queue an RCU for invocation task-based grace period
  * @head: structure to be used for queueing the RCU updates.
@@ -309,7 +340,7 @@ 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 +348,7 @@ 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);
@@ -392,10 +423,6 @@ bool __rcu_is_watching(void);
  * TREE_RCU and rcu_barrier_() primitives in TINY_RCU.
  */
 
-typedef void call_rcu_func_t(struct rcu_head *head,
-			     void (*func)(struct rcu_head *head));
-void wait_rcu_gp(call_rcu_func_t crf);
-
 #if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU)
 #include <linux/rcutree.h>
 #elif defined(CONFIG_TINY_RCU)
@@ -469,46 +496,10 @@ 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)
 {
@@ -545,6 +536,11 @@ static inline int rcu_read_lock_sched_held(void)
 
 #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
+/* Deprecate rcu_lockdep_assert():  Use RCU_LOCKDEP_WARN() instead. */
+static inline void __attribute((deprecated)) deprecate_rcu_lockdep_assert(void)
+{
+}
+
 #ifdef CONFIG_PROVE_RCU
 
 /**
@@ -555,17 +551,32 @@ static inline int rcu_read_lock_sched_held(void)
 #define rcu_lockdep_assert(c, s)					\
 	do {								\
 		static bool __section(.data.unlikely) __warned;		\
+		deprecate_rcu_lockdep_assert();				\
 		if (debug_lockdep_rcu_enabled() && !__warned && !(c)) {	\
 			__warned = true;				\
 			lockdep_rcu_suspicious(__FILE__, __LINE__, s);	\
 		}							\
 	} while (0)
 
+/**
+ * RCU_LOCKDEP_WARN - emit lockdep splat if specified condition is met
+ * @c: condition to check
+ * @s: informative message
+ */
+#define RCU_LOCKDEP_WARN(c, s)						\
+	do {								\
+		static bool __section(.data.unlikely) __warned;		\
+		if (debug_lockdep_rcu_enabled() && !__warned && (c)) {	\
+			__warned = true;				\
+			lockdep_rcu_suspicious(__FILE__, __LINE__, s);	\
+		}							\
+	} while (0)
+
 #if defined(CONFIG_PROVE_RCU) && !defined(CONFIG_PREEMPT_RCU)
 static inline void rcu_preempt_sleep_check(void)
 {
-	rcu_lockdep_assert(!lock_is_held(&rcu_lock_map),
-			   "Illegal context switch in RCU read-side critical section");
+	RCU_LOCKDEP_WARN(lock_is_held(&rcu_lock_map),
+			 "Illegal context switch in RCU read-side critical section");
 }
 #else /* #ifdef CONFIG_PROVE_RCU */
 static inline void rcu_preempt_sleep_check(void)
@@ -576,15 +587,16 @@ static inline void rcu_preempt_sleep_check(void)
 #define rcu_sleep_check()						\
 	do {								\
 		rcu_preempt_sleep_check();				\
-		rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map),	\
-				   "Illegal context switch in RCU-bh read-side critical section"); \
-		rcu_lockdep_assert(!lock_is_held(&rcu_sched_lock_map),	\
-				   "Illegal context switch in RCU-sched read-side critical section"); \
+		RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map),	\
+				 "Illegal context switch in RCU-bh read-side critical section"); \
+		RCU_LOCKDEP_WARN(lock_is_held(&rcu_sched_lock_map),	\
+				 "Illegal context switch in RCU-sched read-side critical section"); \
 	} while (0)
 
 #else /* #ifdef CONFIG_PROVE_RCU */
 
-#define rcu_lockdep_assert(c, s) do { } while (0)
+#define rcu_lockdep_assert(c, s) deprecate_rcu_lockdep_assert()
+#define RCU_LOCKDEP_WARN(c, s) do { } while (0)
 #define rcu_sleep_check() do { } while (0)
 
 #endif /* #else #ifdef CONFIG_PROVE_RCU */
@@ -615,13 +627,13 @@ static inline void rcu_preempt_sleep_check(void)
 ({ \
 	/* Dependency order vs. p above. */ \
 	typeof(*p) *________p1 = (typeof(*p) *__force)lockless_dereference(p); \
-	rcu_lockdep_assert(c, "suspicious rcu_dereference_check() usage"); \
+	RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_check() usage"); \
 	rcu_dereference_sparse(p, space); \
 	((typeof(*p) __force __kernel *)(________p1)); \
 })
 #define __rcu_dereference_protected(p, c, space) \
 ({ \
-	rcu_lockdep_assert(c, "suspicious rcu_dereference_protected() usage"); \
+	RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_protected() usage"); \
 	rcu_dereference_sparse(p, space); \
 	((typeof(*p) __force __kernel *)(p)); \
 })
@@ -845,8 +857,8 @@ static inline void rcu_read_lock(void)
 	__rcu_read_lock();
 	__acquire(RCU);
 	rcu_lock_acquire(&rcu_lock_map);
-	rcu_lockdep_assert(rcu_is_watching(),
-			   "rcu_read_lock() used illegally while idle");
+	RCU_LOCKDEP_WARN(!rcu_is_watching(),
+			 "rcu_read_lock() used illegally while idle");
 }
 
 /*
@@ -896,8 +908,8 @@ static inline void rcu_read_lock(void)
  */
 static inline void rcu_read_unlock(void)
 {
-	rcu_lockdep_assert(rcu_is_watching(),
-			   "rcu_read_unlock() used illegally while idle");
+	RCU_LOCKDEP_WARN(!rcu_is_watching(),
+			 "rcu_read_unlock() used illegally while idle");
 	__release(RCU);
 	__rcu_read_unlock();
 	rcu_lock_release(&rcu_lock_map); /* Keep acq info for rls diags. */
@@ -925,8 +937,8 @@ static inline void rcu_read_lock_bh(void)
 	local_bh_disable();
 	__acquire(RCU_BH);
 	rcu_lock_acquire(&rcu_bh_lock_map);
-	rcu_lockdep_assert(rcu_is_watching(),
-			   "rcu_read_lock_bh() used illegally while idle");
+	RCU_LOCKDEP_WARN(!rcu_is_watching(),
+			 "rcu_read_lock_bh() used illegally while idle");
 }
 
 /*
@@ -936,8 +948,8 @@ static inline void rcu_read_lock_bh(void)
  */
 static inline void rcu_read_unlock_bh(void)
 {
-	rcu_lockdep_assert(rcu_is_watching(),
-			   "rcu_read_unlock_bh() used illegally while idle");
+	RCU_LOCKDEP_WARN(!rcu_is_watching(),
+			 "rcu_read_unlock_bh() used illegally while idle");
 	rcu_lock_release(&rcu_bh_lock_map);
 	__release(RCU_BH);
 	local_bh_enable();
@@ -961,8 +973,8 @@ static inline void rcu_read_lock_sched(void)
 	preempt_disable();
 	__acquire(RCU_SCHED);
 	rcu_lock_acquire(&rcu_sched_lock_map);
-	rcu_lockdep_assert(rcu_is_watching(),
-			   "rcu_read_lock_sched() used illegally while idle");
+	RCU_LOCKDEP_WARN(!rcu_is_watching(),
+			 "rcu_read_lock_sched() used illegally while idle");
 }
 
 /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */
@@ -979,8 +991,8 @@ static inline notrace void rcu_read_lock_sched_notrace(void)
  */
 static inline void rcu_read_unlock_sched(void)
 {
-	rcu_lockdep_assert(rcu_is_watching(),
-			   "rcu_read_unlock_sched() used illegally while idle");
+	RCU_LOCKDEP_WARN(!rcu_is_watching(),
+			 "rcu_read_unlock_sched() used illegally while idle");
 	rcu_lock_release(&rcu_sched_lock_map);
 	__release(RCU_SCHED);
 	preempt_enable();
@@ -1031,7 +1043,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
 #define RCU_INIT_POINTER(p, v) \
 	do { \
 		rcu_dereference_sparse(p, __rcu); \
-		p = RCU_INITIALIZER(v); \
+		WRITE_ONCE(p, RCU_INITIALIZER(v)); \
 	} while (0)
 
 /**

include/linux/rcutiny.h

@@ -37,6 +37,16 @@ static inline void cond_synchronize_rcu(unsigned long oldstate)
 	might_sleep();
 }
 
+static inline unsigned long get_state_synchronize_sched(void)
+{
+	return 0;
+}
+
+static inline void cond_synchronize_sched(unsigned long oldstate)
+{
+	might_sleep();
+}
+
 static inline void rcu_barrier_bh(void)
 {
 	wait_rcu_gp(call_rcu_bh);

include/linux/rcutree.h

@@ -76,6 +76,8 @@ void rcu_barrier_bh(void);
 void rcu_barrier_sched(void);
 unsigned long get_state_synchronize_rcu(void);
 void cond_synchronize_rcu(unsigned long oldstate);
+unsigned long get_state_synchronize_sched(void);
+void cond_synchronize_sched(unsigned long oldstate);
 
 extern unsigned long rcutorture_testseq;
 extern unsigned long rcutorture_vernum;

include/linux/spinlock.h

@@ -130,16 +130,6 @@ do {								\
 #define smp_mb__before_spinlock()	smp_wmb()
 #endif
 
-/*
- * Place this after a lock-acquisition primitive to guarantee that
- * an UNLOCK+LOCK pair act as a full barrier.  This guarantee applies
- * if the UNLOCK and LOCK are executed by the same CPU or if the
- * UNLOCK and LOCK operate on the same lock variable.
- */
-#ifndef smp_mb__after_unlock_lock
-#define smp_mb__after_unlock_lock()	do { } while (0)
-#endif
-
 /**
  * raw_spin_unlock_wait - wait until the spinlock gets unlocked
  * @lock: the spinlock in question.

include/linux/types.h

@@ -212,6 +212,9 @@ struct callback_head {
 };
 #define rcu_head callback_head
 
+typedef void (*rcu_callback_t)(struct rcu_head *head);
+typedef void (*call_rcu_func_t)(struct rcu_head *head, rcu_callback_t func);
+
 /* clocksource cycle base type */
 typedef u64 cycle_t;
 

include/trace/events/rcu.h

@@ -661,7 +661,6 @@ TRACE_EVENT(rcu_torture_read,
  * Tracepoint for _rcu_barrier() execution.  The string "s" describes
  * the _rcu_barrier phase:
  *	"Begin": _rcu_barrier() started.
- *	"Check": _rcu_barrier() checking for piggybacking.
  *	"EarlyExit": _rcu_barrier() piggybacked, thus early exit.
  *	"Inc1": _rcu_barrier() piggyback check counter incremented.
  *	"OfflineNoCB": _rcu_barrier() found callback on never-online CPU

init/Kconfig

@@ -538,15 +538,6 @@ 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
@@ -707,6 +698,7 @@ config RCU_BOOST_DELAY
 config RCU_NOCB_CPU
 	bool "Offload RCU callback processing from boot-selected CPUs"
 	depends on TREE_RCU || PREEMPT_RCU
+	depends on RCU_EXPERT || NO_HZ_FULL
 	default n
 	help
 	  Use this option to reduce OS jitter for aggressive HPC or

kernel/cgroup.c

@@ -107,8 +107,8 @@ static DEFINE_SPINLOCK(release_agent_path_lock);
 struct percpu_rw_semaphore cgroup_threadgroup_rwsem;
 
 #define cgroup_assert_mutex_or_rcu_locked()				\
-	rcu_lockdep_assert(rcu_read_lock_held() ||			\
-			   lockdep_is_held(&cgroup_mutex),		\
+	RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&			\
+			   !lockdep_is_held(&cgroup_mutex),		\
 			   "cgroup_mutex or RCU read lock required");
 
 /*