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

Pull locking updates from Ingo Molnar:
 "The main changes in this cycle were:

   - Continued user-access cleanups in the futex code.

   - percpu-rwsem rewrite that uses its own waitqueue and atomic_t
     instead of an embedded rwsem. This addresses a couple of
     weaknesses, but the primary motivation was complications on the -rt
     kernel.

   - Introduce raw lock nesting detection on lockdep
     (CONFIG_PROVE_RAW_LOCK_NESTING=y), document the raw_lock vs. normal
     lock differences. This too originates from -rt.

   - Reuse lockdep zapped chain_hlocks entries, to conserve RAM
     footprint on distro-ish kernels running into the "BUG:
     MAX_LOCKDEP_CHAIN_HLOCKS too low!" depletion of the lockdep
     chain-entries pool.

   - Misc cleanups, smaller fixes and enhancements - see the changelog
     for details"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (55 commits)
  fs/buffer: Make BH_Uptodate_Lock bit_spin_lock a regular spinlock_t
  thermal/x86_pkg_temp: Make pkg_temp_lock a raw_spinlock_t
  Documentation/locking/locktypes: Minor copy editor fixes
  Documentation/locking/locktypes: Further clarifications and wordsmithing
  m68knommu: Remove mm.h include from uaccess_no.h
  x86: get rid of user_atomic_cmpxchg_inatomic()
  generic arch_futex_atomic_op_inuser() doesn't need access_ok()
  x86: don't reload after cmpxchg in unsafe_atomic_op2() loop
  x86: convert arch_futex_atomic_op_inuser() to user_access_begin/user_access_end()
  objtool: whitelist __sanitizer_cov_trace_switch()
  [parisc, s390, sparc64] no need for access_ok() in futex handling
  sh: no need of access_ok() in arch_futex_atomic_op_inuser()
  futex: arch_futex_atomic_op_inuser() calling conventions change
  completion: Use lockdep_assert_RT_in_threaded_ctx() in complete_all()
  lockdep: Add posixtimer context tracing bits
  lockdep: Annotate irq_work
  lockdep: Add hrtimer context tracing bits
  lockdep: Introduce wait-type checks
  completion: Use simple wait queues
  sched/swait: Prepare usage in completions
  ...

17 files changed, 257 insertions, 84 deletions

diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 0c23fd0548d1..a92bea7184a8 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -80,7 +80,7 @@ bool acpi_dev_present(const char *hid, const char *uid, s64 hrv);
 
 #ifdef CONFIG_ACPI
 
-#include <linux/proc_fs.h>
+struct proc_dir_entry;
 
 #define ACPI_BUS_FILE_ROOT	"acpi"
 extern struct proc_dir_entry *acpi_root_dir;
diff --git a/include/asm-generic/bitops.h b/include/asm-generic/bitops.h
index bfc96bf6606e..df9b5bc3d282 100644
--- a/include/asm-generic/bitops.h
+++ b/include/asm-generic/bitops.h
@@ -4,8 +4,9 @@
 
 /*
  * For the benefit of those who are trying to port Linux to another
- * architecture, here are some C-language equivalents.  You should
- * recode these in the native assembly language, if at all possible.
+ * architecture, here are some C-language equivalents.  They should
+ * generate reasonable code, so take a look at what your compiler spits
+ * out before rolling your own buggy implementation in assembly language.
  *
  * C language equivalents written by Theodore Ts'o, 9/26/92
  */
diff --git a/include/asm-generic/futex.h b/include/asm-generic/futex.h
index 02970b11f71f..f4c3470480c7 100644
--- a/include/asm-generic/futex.h
+++ b/include/asm-generic/futex.h
@@ -34,7 +34,6 @@ arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval, u32 __user *uaddr)
 	u32 tmp;
 
 	preempt_disable();
-	pagefault_disable();
 
 	ret = -EFAULT;
 	if (unlikely(get_user(oldval, uaddr) != 0))
@@ -67,7 +66,6 @@ arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval, u32 __user *uaddr)
 		ret = -EFAULT;
 
 out_pagefault_enable:
-	pagefault_enable();
 	preempt_enable();
 
 	if (ret == 0)
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 7b73ef7f902d..e0b020eaf32e 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -22,9 +22,6 @@ enum bh_state_bits {
 	BH_Dirty,	/* Is dirty */
 	BH_Lock,	/* Is locked */
 	BH_Req,		/* Has been submitted for I/O */
-	BH_Uptodate_Lock,/* Used by the first bh in a page, to serialise
-			  * IO completion of other buffers in the page
-			  */
 
 	BH_Mapped,	/* Has a disk mapping */
 	BH_New,		/* Disk mapping was newly created by get_block */
@@ -76,6 +73,9 @@ struct buffer_head {
 	struct address_space *b_assoc_map;	/* mapping this buffer is
 						   associated with */
 	atomic_t b_count;		/* users using this buffer_head */
+	spinlock_t b_uptodate_lock;	/* Used by the first bh in a page, to
+					 * serialise IO completion of other
+					 * buffers in the page */
 };
 
 /*
diff --git a/include/linux/completion.h b/include/linux/completion.h
index 519e94915d18..bf8e77001f18 100644
--- a/include/linux/completion.h
+++ b/include/linux/completion.h
@@ -9,7 +9,7 @@
  * See kernel/sched/completion.c for details.
  */
 
-#include <linux/wait.h>
+#include <linux/swait.h>
 
 /*
  * struct completion - structure used to maintain state for a "completion"
@@ -25,7 +25,7 @@
  */
 struct completion {
 	unsigned int done;
-	wait_queue_head_t wait;
+	struct swait_queue_head wait;
 };
 
 #define init_completion_map(x, m) __init_completion(x)
@@ -34,7 +34,7 @@ static inline void complete_acquire(struct completion *x) {}
 static inline void complete_release(struct completion *x) {}
 
 #define COMPLETION_INITIALIZER(work) \
-	{ 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait) }
+	{ 0, __SWAIT_QUEUE_HEAD_INITIALIZER((work).wait) }
 
 #define COMPLETION_INITIALIZER_ONSTACK_MAP(work, map) \
 	(*({ init_completion_map(&(work), &(map)); &(work); }))
@@ -85,7 +85,7 @@ static inline void complete_release(struct completion *x) {}
 static inline void __init_completion(struct completion *x)
 {
 	x->done = 0;
-	init_waitqueue_head(&x->wait);
+	init_swait_queue_head(&x->wait);
 }
 
 /**
diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h
index 02da997ad12c..3b752e80c017 100644
--- a/include/linux/irq_work.h
+++ b/include/linux/irq_work.h
@@ -18,6 +18,8 @@
 
 /* Doesn't want IPI, wait for tick: */
 #define IRQ_WORK_LAZY		BIT(2)
+/* Run hard IRQ context, even on RT */
+#define IRQ_WORK_HARD_IRQ	BIT(3)
 
 #define IRQ_WORK_CLAIMED	(IRQ_WORK_PENDING | IRQ_WORK_BUSY)
 
diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h
index 21619c92c377..a16adbb58f66 100644
--- a/include/linux/irqflags.h
+++ b/include/linux/irqflags.h
@@ -37,7 +37,12 @@
 # define trace_softirqs_enabled(p)	((p)->softirqs_enabled)
 # define trace_hardirq_enter()			\
 do {						\
-	current->hardirq_context++;		\
+	if (!current->hardirq_context++)	\
+		current->hardirq_threaded = 0;	\
+} while (0)
+# define trace_hardirq_threaded()		\
+do {						\
+	current->hardirq_threaded = 1;		\
 } while (0)
 # define trace_hardirq_exit()			\
 do {						\
@@ -51,6 +56,40 @@ do {						\
 do {						\
 	current->softirq_context--;		\
 } while (0)
+
+# define lockdep_hrtimer_enter(__hrtimer)		\
+	  do {						\
+		  if (!__hrtimer->is_hard)		\
+			current->irq_config = 1;	\
+	  } while (0)
+
+# define lockdep_hrtimer_exit(__hrtimer)		\
+	  do {						\
+		  if (!__hrtimer->is_hard)		\
+			current->irq_config = 0;	\
+	  } while (0)
+
+# define lockdep_posixtimer_enter()				\
+	  do {							\
+		  current->irq_config = 1;			\
+	  } while (0)
+
+# define lockdep_posixtimer_exit()				\
+	  do {							\
+		  current->irq_config = 0;			\
+	  } while (0)
+
+# define lockdep_irq_work_enter(__work)					\
+	  do {								\
+		  if (!(atomic_read(&__work->flags) & IRQ_WORK_HARD_IRQ))\
+			current->irq_config = 1;			\
+	  } while (0)
+# define lockdep_irq_work_exit(__work)					\
+	  do {								\
+		  if (!(atomic_read(&__work->flags) & IRQ_WORK_HARD_IRQ))\
+			current->irq_config = 0;			\
+	  } while (0)
+
 #else
 # define trace_hardirqs_on()		do { } while (0)
 # define trace_hardirqs_off()		do { } while (0)
@@ -59,9 +98,16 @@ do {						\
 # define trace_hardirqs_enabled(p)	0
 # define trace_softirqs_enabled(p)	0
 # define trace_hardirq_enter()		do { } while (0)
+# define trace_hardirq_threaded()	do { } while (0)
 # define trace_hardirq_exit()		do { } while (0)
 # define lockdep_softirq_enter()	do { } while (0)
 # define lockdep_softirq_exit()		do { } while (0)
+# define lockdep_hrtimer_enter(__hrtimer)		do { } while (0)
+# define lockdep_hrtimer_exit(__hrtimer)		do { } while (0)
+# define lockdep_posixtimer_enter()		do { } while (0)
+# define lockdep_posixtimer_exit()		do { } while (0)
+# define lockdep_irq_work_enter(__work)		do { } while (0)
+# define lockdep_irq_work_exit(__work)		do { } while (0)
 #endif
 
 #if defined(CONFIG_IRQSOFF_TRACER) || \
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 664f52c6dd4c..206774ac6946 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -21,6 +21,22 @@ extern int lock_stat;
 
 #include <linux/types.h>
 
+enum lockdep_wait_type {
+	LD_WAIT_INV = 0,	/* not checked, catch all */
+
+	LD_WAIT_FREE,		/* wait free, rcu etc.. */
+	LD_WAIT_SPIN,		/* spin loops, raw_spinlock_t etc.. */
+
+#ifdef CONFIG_PROVE_RAW_LOCK_NESTING
+	LD_WAIT_CONFIG,		/* CONFIG_PREEMPT_LOCK, spinlock_t etc.. */
+#else
+	LD_WAIT_CONFIG = LD_WAIT_SPIN,
+#endif
+	LD_WAIT_SLEEP,		/* sleeping locks, mutex_t etc.. */
+
+	LD_WAIT_MAX,		/* must be last */
+};
+
 #ifdef CONFIG_LOCKDEP
 
 #include <linux/linkage.h>
@@ -111,6 +127,9 @@ struct lock_class {
 	int				name_version;
 	const char			*name;
 
+	short				wait_type_inner;
+	short				wait_type_outer;
+
 #ifdef CONFIG_LOCK_STAT
 	unsigned long			contention_point[LOCKSTAT_POINTS];
 	unsigned long			contending_point[LOCKSTAT_POINTS];
@@ -158,6 +177,8 @@ struct lockdep_map {
 	struct lock_class_key		*key;
 	struct lock_class		*class_cache[NR_LOCKDEP_CACHING_CLASSES];
 	const char			*name;
+	short				wait_type_outer; /* can be taken in this context */
+	short				wait_type_inner; /* presents this context */
 #ifdef CONFIG_LOCK_STAT
 	int				cpu;
 	unsigned long			ip;
@@ -299,8 +320,21 @@ extern void lockdep_unregister_key(struct lock_class_key *key);
  * to lockdep:
  */
 
-extern void lockdep_init_map(struct lockdep_map *lock, const char *name,
-			     struct lock_class_key *key, int subclass);
+extern void lockdep_init_map_waits(struct lockdep_map *lock, const char *name,
+	struct lock_class_key *key, int subclass, short inner, short outer);
+
+static inline void
+lockdep_init_map_wait(struct lockdep_map *lock, const char *name,
+		      struct lock_class_key *key, int subclass, short inner)
+{
+	lockdep_init_map_waits(lock, name, key, subclass, inner, LD_WAIT_INV);
+}
+
+static inline void lockdep_init_map(struct lockdep_map *lock, const char *name,
+			     struct lock_class_key *key, int subclass)
+{
+	lockdep_init_map_wait(lock, name, key, subclass, LD_WAIT_INV);
+}
 
 /*
  * Reinitialize a lock key - for cases where there is special locking or
@@ -308,18 +342,29 @@ extern void lockdep_init_map(struct lockdep_map *lock, const char *name,
  * of dependencies wrong: they are either too broad (they need a class-split)
  * or they are too narrow (they suffer from a false class-split):
  */
-#define lockdep_set_class(lock, key) \
-		lockdep_init_map(&(lock)->dep_map, #key, key, 0)
-#define lockdep_set_class_and_name(lock, key, name) \
-		lockdep_init_map(&(lock)->dep_map, name, key, 0)
-#define lockdep_set_class_and_subclass(lock, key, sub) \
-		lockdep_init_map(&(lock)->dep_map, #key, key, sub)
-#define lockdep_set_subclass(lock, sub)	\
-		lockdep_init_map(&(lock)->dep_map, #lock, \
-				 (lock)->dep_map.key, sub)
+#define lockdep_set_class(lock, key)				\
+	lockdep_init_map_waits(&(lock)->dep_map, #key, key, 0,	\
+			       (lock)->dep_map.wait_type_inner,	\
+			       (lock)->dep_map.wait_type_outer)
+
+#define lockdep_set_class_and_name(lock, key, name)		\
+	lockdep_init_map_waits(&(lock)->dep_map, name, key, 0,	\
+			       (lock)->dep_map.wait_type_inner,	\
+			       (lock)->dep_map.wait_type_outer)
+
+#define lockdep_set_class_and_subclass(lock, key, sub)		\
+	lockdep_init_map_waits(&(lock)->dep_map, #key, key, sub,\
+			       (lock)->dep_map.wait_type_inner,	\
+			       (lock)->dep_map.wait_type_outer)
+
+#define lockdep_set_subclass(lock, sub)					\
+	lockdep_init_map_waits(&(lock)->dep_map, #lock, (lock)->dep_map.key, sub,\
+			       (lock)->dep_map.wait_type_inner,		\
+			       (lock)->dep_map.wait_type_outer)
 
 #define lockdep_set_novalidate_class(lock) \
 	lockdep_set_class_and_name(lock, &__lockdep_no_validate__, #lock)
+
 /*
  * Compare locking classes
  */
@@ -432,6 +477,10 @@ static inline void lockdep_set_selftest_task(struct task_struct *task)
 # define lock_set_class(l, n, k, s, i)		do { } while (0)
 # define lock_set_subclass(l, s, i)		do { } while (0)
 # define lockdep_init()				do { } while (0)
+# define lockdep_init_map_waits(lock, name, key, sub, inner, outer) \
+		do { (void)(name); (void)(key); } while (0)
+# define lockdep_init_map_wait(lock, name, key, sub, inner) \
+		do { (void)(name); (void)(key); } while (0)
 # define lockdep_init_map(lock, name, key, sub) \
 		do { (void)(name); (void)(key); } while (0)
 # define lockdep_set_class(lock, key)		do { (void)(key); } while (0)
@@ -662,6 +711,21 @@ do {									\
 # define lockdep_assert_in_irq() do { } while (0)
 #endif
 
+#ifdef CONFIG_PROVE_RAW_LOCK_NESTING
+
+# define lockdep_assert_RT_in_threaded_ctx() do {			\
+		WARN_ONCE(debug_locks && !current->lockdep_recursion &&	\
+			  current->hardirq_context &&			\
+			  !(current->hardirq_threaded || current->irq_config),	\
+			  "Not in threaded context on PREEMPT_RT as expected\n");	\
+} while (0)
+
+#else
+
+# define lockdep_assert_RT_in_threaded_ctx() do { } while (0)
+
+#endif
+
 #ifdef CONFIG_LOCKDEP
 void lockdep_rcu_suspicious(const char *file, const int line, const char *s);
 #else
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index aca8f36dfac9..ae197cc00cc8 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -109,8 +109,11 @@ do {									\
 } while (0)
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \
-		, .dep_map = { .name = #lockname }
+# define __DEP_MAP_MUTEX_INITIALIZER(lockname)			\
+		, .dep_map = {					\
+			.name = #lockname,			\
+			.wait_type_inner = LD_WAIT_SLEEP,	\
+		}
 #else
 # define __DEP_MAP_MUTEX_INITIALIZER(lockname)
 #endif
diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h
index ad2ca2a89d5b..5e033fe1ff4e 100644
--- a/include/linux/percpu-rwsem.h
+++ b/include/linux/percpu-rwsem.h
@@ -3,41 +3,52 @@
 #define _LINUX_PERCPU_RWSEM_H
 
 #include <linux/atomic.h>
-#include <linux/rwsem.h>
 #include <linux/percpu.h>
 #include <linux/rcuwait.h>
+#include <linux/wait.h>
 #include <linux/rcu_sync.h>
 #include <linux/lockdep.h>
 
 struct percpu_rw_semaphore {
 	struct rcu_sync		rss;
 	unsigned int __percpu	*read_count;
-	struct rw_semaphore	rw_sem; /* slowpath */
-	struct rcuwait          writer; /* blocked writer */
-	int			readers_block;
+	struct rcuwait		writer;
+	wait_queue_head_t	waiters;
+	atomic_t		block;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map	dep_map;
+#endif
 };
 
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+#define __PERCPU_RWSEM_DEP_MAP_INIT(lockname)	.dep_map = { .name = #lockname },
+#else
+#define __PERCPU_RWSEM_DEP_MAP_INIT(lockname)
+#endif
+
 #define __DEFINE_PERCPU_RWSEM(name, is_static)				\
 static DEFINE_PER_CPU(unsigned int, __percpu_rwsem_rc_##name);		\
 is_static struct percpu_rw_semaphore name = {				\
 	.rss = __RCU_SYNC_INITIALIZER(name.rss),			\
 	.read_count = &__percpu_rwsem_rc_##name,			\
-	.rw_sem = __RWSEM_INITIALIZER(name.rw_sem),			\
 	.writer = __RCUWAIT_INITIALIZER(name.writer),			\
+	.waiters = __WAIT_QUEUE_HEAD_INITIALIZER(name.waiters),		\
+	.block = ATOMIC_INIT(0),					\
+	__PERCPU_RWSEM_DEP_MAP_INIT(name)				\
 }
+
 #define DEFINE_PERCPU_RWSEM(name)		\
 	__DEFINE_PERCPU_RWSEM(name, /* not static */)
 #define DEFINE_STATIC_PERCPU_RWSEM(name)	\
 	__DEFINE_PERCPU_RWSEM(name, static)
 
-extern int __percpu_down_read(struct percpu_rw_semaphore *, int);
-extern void __percpu_up_read(struct percpu_rw_semaphore *);
+extern bool __percpu_down_read(struct percpu_rw_semaphore *, bool);
 
 static inline void percpu_down_read(struct percpu_rw_semaphore *sem)
 {
 	might_sleep();
 
-	rwsem_acquire_read(&sem->rw_sem.dep_map, 0, 0, _RET_IP_);
+	rwsem_acquire_read(&sem->dep_map, 0, 0, _RET_IP_);
 
 	preempt_disable();
 	/*
@@ -48,8 +59,9 @@ static inline void percpu_down_read(struct percpu_rw_semaphore *sem)
 	 * and that once the synchronize_rcu() is done, the writer will see
 	 * anything we did within this RCU-sched read-size critical section.
 	 */
-	__this_cpu_inc(*sem->read_count);
-	if (unlikely(!rcu_sync_is_idle(&sem->rss)))
+	if (likely(rcu_sync_is_idle(&sem->rss)))
+		__this_cpu_inc(*sem->read_count);
+	else
 		__percpu_down_read(sem, false); /* Unconditional memory barrier */
 	/*
 	 * The preempt_enable() prevents the compiler from
@@ -58,16 +70,17 @@ static inline void percpu_down_read(struct percpu_rw_semaphore *sem)
 	preempt_enable();
 }
 
-static inline int percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
+static inline bool percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
 {
-	int ret = 1;
+	bool ret = true;
 
 	preempt_disable();
 	/*
 	 * Same as in percpu_down_read().
 	 */
-	__this_cpu_inc(*sem->read_count);
-	if (unlikely(!rcu_sync_is_idle(&sem->rss)))
+	if (likely(rcu_sync_is_idle(&sem->rss)))
+		__this_cpu_inc(*sem->read_count);
+	else
 		ret = __percpu_down_read(sem, true); /* Unconditional memory barrier */
 	preempt_enable();
 	/*
@@ -76,24 +89,36 @@ static inline int percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
 	 */
 
 	if (ret)
-		rwsem_acquire_read(&sem->rw_sem.dep_map, 0, 1, _RET_IP_);
+		rwsem_acquire_read(&sem->dep_map, 0, 1, _RET_IP_);
 
 	return ret;
 }
 
 static inline void percpu_up_read(struct percpu_rw_semaphore *sem)
 {
+	rwsem_release(&sem->dep_map, _RET_IP_);
+
 	preempt_disable();
 	/*
 	 * Same as in percpu_down_read().
 	 */
-	if (likely(rcu_sync_is_idle(&sem->rss)))
+	if (likely(rcu_sync_is_idle(&sem->rss))) {
 		__this_cpu_dec(*sem->read_count);
-	else
-		__percpu_up_read(sem); /* Unconditional memory barrier */
+	} else {
+		/*
+		 * slowpath; reader will only ever wake a single blocked
+		 * writer.
+		 */
+		smp_mb(); /* B matches C */
+		/*
+		 * In other words, if they see our decrement (presumably to
+		 * aggregate zero, as that is the only time it matters) they
+		 * will also see our critical section.
+		 */
+		__this_cpu_dec(*sem->read_count);
+		rcuwait_wake_up(&sem->writer);
+	}
 	preempt_enable();
-
-	rwsem_release(&sem->rw_sem.dep_map, _RET_IP_);
 }
 
 extern void percpu_down_write(struct percpu_rw_semaphore *);
@@ -110,29 +135,19 @@ extern void percpu_free_rwsem(struct percpu_rw_semaphore *);
 	__percpu_init_rwsem(sem, #sem, &rwsem_key);		\
 })
 
-#define percpu_rwsem_is_held(sem) lockdep_is_held(&(sem)->rw_sem)
-
-#define percpu_rwsem_assert_held(sem)				\
-	lockdep_assert_held(&(sem)->rw_sem)
+#define percpu_rwsem_is_held(sem)	lockdep_is_held(sem)
+#define percpu_rwsem_assert_held(sem)	lockdep_assert_held(sem)
 
 static inline void percpu_rwsem_release(struct percpu_rw_semaphore *sem,
 					bool read, unsigned long ip)
 {
-	lock_release(&sem->rw_sem.dep_map, ip);
-#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
-	if (!read)
-		atomic_long_set(&sem->rw_sem.owner, RWSEM_OWNER_UNKNOWN);
-#endif
+	lock_release(&sem->dep_map, ip);
 }
 
 static inline void percpu_rwsem_acquire(struct percpu_rw_semaphore *sem,
 					bool read, unsigned long ip)
 {
-	lock_acquire(&sem->rw_sem.dep_map, 0, 1, read, 1, NULL, ip);
-#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
-	if (!read)
-		atomic_long_set(&sem->rw_sem.owner, (long)current);
-#endif
+	lock_acquire(&sem->dep_map, 0, 1, read, 1, NULL, ip);
 }
 
 #endif
diff --git a/include/linux/rcuwait.h b/include/linux/rcuwait.h
index 75c97e4bbc57..2ffe1ee6d482 100644
--- a/include/linux/rcuwait.h
+++ b/include/linux/rcuwait.h
@@ -3,6 +3,7 @@
 #define _LINUX_RCUWAIT_H_
 
 #include <linux/rcupdate.h>
+#include <linux/sched/signal.h>
 
 /*
  * rcuwait provides a way of blocking and waking up a single
@@ -30,23 +31,30 @@ extern void rcuwait_wake_up(struct rcuwait *w);
  * The caller is responsible for locking around rcuwait_wait_event(),
  * such that writes to @task are properly serialized.
  */
-#define rcuwait_wait_event(w, condition)				\
+#define rcuwait_wait_event(w, condition, state)				\
 ({									\
+	int __ret = 0;							\
 	rcu_assign_pointer((w)->task, current);				\
 	for (;;) {							\
 		/*							\
 		 * Implicit barrier (A) pairs with (B) in		\
 		 * rcuwait_wake_up().					\
 		 */							\
-		set_current_state(TASK_UNINTERRUPTIBLE);		\
+		set_current_state(state);				\
 		if (condition)						\
 			break;						\
 									\
+		if (signal_pending_state(state, current)) {		\
+			__ret = -EINTR;					\
+			break;						\
+		}							\
+									\
 		schedule();						\
 	}								\
 									\
 	WRITE_ONCE((w)->task, NULL);					\
 	__set_current_state(TASK_RUNNING);				\
+	__ret;								\
 })
 
 #endif /* _LINUX_RCUWAIT_H_ */
diff --git a/include/linux/rwlock_types.h b/include/linux/rwlock_types.h
index 857a72ceb794..3bd03e18061c 100644
--- a/include/linux/rwlock_types.h
+++ b/include/linux/rwlock_types.h
@@ -22,7 +22,11 @@ typedef struct {
 #define RWLOCK_MAGIC		0xdeaf1eed
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define RW_DEP_MAP_INIT(lockname)	.dep_map = { .name = #lockname }
+# define RW_DEP_MAP_INIT(lockname)					\
+	.dep_map = {							\
+		.name = #lockname,					\
+		.wait_type_inner = LD_WAIT_CONFIG,			\
+	}
 #else
 # define RW_DEP_MAP_INIT(lockname)
 #endif
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 00d6054687dd..7e5b2a4eb560 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -53,12 +53,6 @@ struct rw_semaphore {
 #endif
 };
 
-/*
- * Setting all bits of the owner field except bit 0 will indicate
- * that the rwsem is writer-owned with an unknown owner.
- */
-#define RWSEM_OWNER_UNKNOWN	(-2L)
-
 /* In all implementations count != 0 means locked */
 static inline int rwsem_is_locked(struct rw_semaphore *sem)
 {
@@ -71,7 +65,11 @@ static inline int rwsem_is_locked(struct rw_semaphore *sem)
 /* Common initializer macros and functions */
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
+# define __RWSEM_DEP_MAP_INIT(lockname)			\
+	, .dep_map = {					\
+		.name = #lockname,			\
+		.wait_type_inner = LD_WAIT_SLEEP,	\
+	}
 #else
 # define __RWSEM_DEP_MAP_INIT(lockname)
 #endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 04278493bf15..933914cdf219 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -970,6 +970,7 @@ struct task_struct {
 
 #ifdef CONFIG_TRACE_IRQFLAGS
 	unsigned int			irq_events;
+	unsigned int			hardirq_threaded;
 	unsigned long			hardirq_enable_ip;
 	unsigned long			hardirq_disable_ip;
 	unsigned int			hardirq_enable_event;
@@ -982,6 +983,7 @@ struct task_struct {
 	unsigned int			softirq_enable_event;
 	int				softirqs_enabled;
 	int				softirq_context;
+	int				irq_config;
 #endif
 
 #ifdef CONFIG_LOCKDEP
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 031ce8617df8..d3770b3f9d9a 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -93,12 +93,13 @@
 
 #ifdef CONFIG_DEBUG_SPINLOCK
   extern void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name,
-				   struct lock_class_key *key);
-# define raw_spin_lock_init(lock)				\
-do {								\
-	static struct lock_class_key __key;			\
-								\
-	__raw_spin_lock_init((lock), #lock, &__key);		\
+				   struct lock_class_key *key, short inner);
+
+# define raw_spin_lock_init(lock)					\
+do {									\
+	static struct lock_class_key __key;				\
+									\
+	__raw_spin_lock_init((lock), #lock, &__key, LD_WAIT_SPIN);	\
 } while (0)
 
 #else
@@ -327,12 +328,26 @@ static __always_inline raw_spinlock_t *spinlock_check(spinlock_t *lock)
 	return &lock->rlock;
 }
 
-#define spin_lock_init(_lock)				\
-do {							\
-	spinlock_check(_lock);				\
-	raw_spin_lock_init(&(_lock)->rlock);		\
+#ifdef CONFIG_DEBUG_SPINLOCK
+
+# define spin_lock_init(lock)					\
+do {								\
+	static struct lock_class_key __key;			\
+								\
+	__raw_spin_lock_init(spinlock_check(lock),		\
+			     #lock, &__key, LD_WAIT_CONFIG);	\
+} while (0)
+
+#else
+
+# define spin_lock_init(_lock)			\
+do {						\
+	spinlock_check(_lock);			\
+	*(_lock) = __SPIN_LOCK_UNLOCKED(_lock);	\
 } while (0)
 
+#endif
+
 static __always_inline void spin_lock(spinlock_t *lock)
 {
 	raw_spin_lock(&lock->rlock);
diff --git a/include/linux/spinlock_types.h b/include/linux/spinlock_types.h
index 24b4e6f2c1a2..6102e6bff3ae 100644
--- a/include/linux/spinlock_types.h
+++ b/include/linux/spinlock_types.h
@@ -33,8 +33,18 @@ typedef struct raw_spinlock {
 #define SPINLOCK_OWNER_INIT	((void *)-1L)
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define SPIN_DEP_MAP_INIT(lockname)	.dep_map = { .name = #lockname }
+# define RAW_SPIN_DEP_MAP_INIT(lockname)		\
+	.dep_map = {					\
+		.name = #lockname,			\
+		.wait_type_inner = LD_WAIT_SPIN,	\
+	}
+# define SPIN_DEP_MAP_INIT(lockname)			\
+	.dep_map = {					\
+		.name = #lockname,			\
+		.wait_type_inner = LD_WAIT_CONFIG,	\
+	}
 #else
+# define RAW_SPIN_DEP_MAP_INIT(lockname)
 # define SPIN_DEP_MAP_INIT(lockname)
 #endif
 
@@ -51,7 +61,7 @@ typedef struct raw_spinlock {
 	{					\
 	.raw_lock = __ARCH_SPIN_LOCK_UNLOCKED,	\
 	SPIN_DEBUG_INIT(lockname)		\
-	SPIN_DEP_MAP_INIT(lockname) }
+	RAW_SPIN_DEP_MAP_INIT(lockname) }
 
 #define __RAW_SPIN_LOCK_UNLOCKED(lockname)	\
 	(raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname)
@@ -72,11 +82,17 @@ typedef struct spinlock {
 	};
 } spinlock_t;
 
+#define ___SPIN_LOCK_INITIALIZER(lockname)	\
+	{					\
+	.raw_lock = __ARCH_SPIN_LOCK_UNLOCKED,	\
+	SPIN_DEBUG_INIT(lockname)		\
+	SPIN_DEP_MAP_INIT(lockname) }
+
 #define __SPIN_LOCK_INITIALIZER(lockname) \
-	{ { .rlock = __RAW_SPIN_LOCK_INITIALIZER(lockname) } }
+	{ { .rlock = ___SPIN_LOCK_INITIALIZER(lockname) } }
 
 #define __SPIN_LOCK_UNLOCKED(lockname) \
-	(spinlock_t ) __SPIN_LOCK_INITIALIZER(lockname)
+	(spinlock_t) __SPIN_LOCK_INITIALIZER(lockname)
 
 #define DEFINE_SPINLOCK(x)	spinlock_t x = __SPIN_LOCK_UNLOCKED(x)
 
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 3283c8d02137..feeb6be5cad6 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -20,6 +20,7 @@ int default_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int
 #define WQ_FLAG_EXCLUSIVE	0x01
 #define WQ_FLAG_WOKEN		0x02
 #define WQ_FLAG_BOOKMARK	0x04
+#define WQ_FLAG_CUSTOM		0x08
 
 /*
  * A single wait-queue entry structure: