16 files changed, 79 insertions, 97 deletions

diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h
index 3f49e65169c6..dbb409d77d4f 100644
--- a/include/linux/debug_locks.h
+++ b/include/linux/debug_locks.h
@@ -47,8 +47,6 @@ extern int debug_locks_off(void);
 # define locking_selftest()	do { } while (0)
 #endif
 
-struct task_struct;
-
 #ifdef CONFIG_LOCKDEP
 extern void debug_show_all_locks(void);
 extern void debug_show_held_locks(struct task_struct *task);
diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h
index e1ca2080a1ff..39fefb86780b 100644
--- a/include/linux/dma-resv.h
+++ b/include/linux/dma-resv.h
@@ -173,7 +173,7 @@ static inline int dma_resv_lock_slow_interruptible(struct dma_resv *obj,
  */
 static inline bool __must_check dma_resv_trylock(struct dma_resv *obj)
 {
-	return ww_mutex_trylock(&obj->lock);
+	return ww_mutex_trylock(&obj->lock, NULL);
 }
 
 /**
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 2776423a587e..e8696e4a45aa 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -111,8 +111,8 @@ static __always_inline void might_resched(void)
 #endif /* CONFIG_PREEMPT_* */
 
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
-extern void ___might_sleep(const char *file, int line, int preempt_offset);
-extern void __might_sleep(const char *file, int line, int preempt_offset);
+extern void __might_resched(const char *file, int line, unsigned int offsets);
+extern void __might_sleep(const char *file, int line);
 extern void __cant_sleep(const char *file, int line, int preempt_offset);
 extern void __cant_migrate(const char *file, int line);
 
@@ -129,7 +129,7 @@ extern void __cant_migrate(const char *file, int line);
  * supposed to.
  */
 # define might_sleep() \
-	do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0)
+	do { __might_sleep(__FILE__, __LINE__); might_resched(); } while (0)
 /**
  * cant_sleep - annotation for functions that cannot sleep
  *
@@ -168,10 +168,9 @@ extern void __cant_migrate(const char *file, int line);
  */
 # define non_block_end() WARN_ON(current->non_block_count-- == 0)
 #else
-  static inline void ___might_sleep(const char *file, int line,
-				   int preempt_offset) { }
-  static inline void __might_sleep(const char *file, int line,
-				   int preempt_offset) { }
+  static inline void __might_resched(const char *file, int line,
+				     unsigned int offsets) { }
+static inline void __might_sleep(const char *file, int line) { }
 # define might_sleep() do { might_resched(); } while (0)
 # define cant_sleep() do { } while (0)
 # define cant_migrate()		do { } while (0)
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 9fe165beb0f9..467b94257105 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -481,23 +481,6 @@ do {								\
 
 #endif /* CONFIG_LOCK_STAT */
 
-#ifdef CONFIG_LOCKDEP
-
-/*
- * On lockdep we dont want the hand-coded irq-enable of
- * _raw_*_lock_flags() code, because lockdep assumes
- * that interrupts are not re-enabled during lock-acquire:
- */
-#define LOCK_CONTENDED_FLAGS(_lock, try, lock, lockfl, flags) \
-	LOCK_CONTENDED((_lock), (try), (lock))
-
-#else /* CONFIG_LOCKDEP */
-
-#define LOCK_CONTENDED_FLAGS(_lock, try, lock, lockfl, flags) \
-	lockfl((_lock), (flags))
-
-#endif /* CONFIG_LOCKDEP */
-
 #ifdef CONFIG_PROVE_LOCKING
 extern void print_irqtrace_events(struct task_struct *curr);
 #else
diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h
index 3e726ace5c62..d22430840b53 100644
--- a/include/linux/lockdep_types.h
+++ b/include/linux/lockdep_types.h
@@ -21,7 +21,7 @@ enum lockdep_wait_type {
 	LD_WAIT_SPIN,		/* spin loops, raw_spinlock_t etc.. */
 
 #ifdef CONFIG_PROVE_RAW_LOCK_NESTING
-	LD_WAIT_CONFIG,		/* CONFIG_PREEMPT_LOCK, spinlock_t etc.. */
+	LD_WAIT_CONFIG,		/* preemptible in PREEMPT_RT, spinlock_t etc.. */
 #else
 	LD_WAIT_CONFIG = LD_WAIT_SPIN,
 #endif
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 4d244e295e85..031898b38d06 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -122,9 +122,10 @@
  * The preempt_count offset after spin_lock()
  */
 #if !defined(CONFIG_PREEMPT_RT)
-#define PREEMPT_LOCK_OFFSET	PREEMPT_DISABLE_OFFSET
+#define PREEMPT_LOCK_OFFSET		PREEMPT_DISABLE_OFFSET
 #else
-#define PREEMPT_LOCK_OFFSET	0
+/* Locks on RT do not disable preemption */
+#define PREEMPT_LOCK_OFFSET		0
 #endif
 
 /*
diff --git a/include/linux/rwlock.h b/include/linux/rwlock.h
index 7ce9a51ae5c0..2c0ad417ce3c 100644
--- a/include/linux/rwlock.h
+++ b/include/linux/rwlock.h
@@ -30,31 +30,16 @@ do {								\
 
 #ifdef CONFIG_DEBUG_SPINLOCK
  extern void do_raw_read_lock(rwlock_t *lock) __acquires(lock);
-#define do_raw_read_lock_flags(lock, flags) do_raw_read_lock(lock)
  extern int do_raw_read_trylock(rwlock_t *lock);
  extern void do_raw_read_unlock(rwlock_t *lock) __releases(lock);
  extern void do_raw_write_lock(rwlock_t *lock) __acquires(lock);
-#define do_raw_write_lock_flags(lock, flags) do_raw_write_lock(lock)
  extern int do_raw_write_trylock(rwlock_t *lock);
  extern void do_raw_write_unlock(rwlock_t *lock) __releases(lock);
 #else
-
-#ifndef arch_read_lock_flags
-# define arch_read_lock_flags(lock, flags)	arch_read_lock(lock)
-#endif
-
-#ifndef arch_write_lock_flags
-# define arch_write_lock_flags(lock, flags)	arch_write_lock(lock)
-#endif
-
 # define do_raw_read_lock(rwlock)	do {__acquire(lock); arch_read_lock(&(rwlock)->raw_lock); } while (0)
-# define do_raw_read_lock_flags(lock, flags) \
-		do {__acquire(lock); arch_read_lock_flags(&(lock)->raw_lock, *(flags)); } while (0)
 # define do_raw_read_trylock(rwlock)	arch_read_trylock(&(rwlock)->raw_lock)
 # define do_raw_read_unlock(rwlock)	do {arch_read_unlock(&(rwlock)->raw_lock); __release(lock); } while (0)
 # define do_raw_write_lock(rwlock)	do {__acquire(lock); arch_write_lock(&(rwlock)->raw_lock); } while (0)
-# define do_raw_write_lock_flags(lock, flags) \
-		do {__acquire(lock); arch_write_lock_flags(&(lock)->raw_lock, *(flags)); } while (0)
 # define do_raw_write_trylock(rwlock)	arch_write_trylock(&(rwlock)->raw_lock)
 # define do_raw_write_unlock(rwlock)	do {arch_write_unlock(&(rwlock)->raw_lock); __release(lock); } while (0)
 #endif
diff --git a/include/linux/rwlock_api_smp.h b/include/linux/rwlock_api_smp.h
index abfb53ab11be..f1db6f17c4fb 100644
--- a/include/linux/rwlock_api_smp.h
+++ b/include/linux/rwlock_api_smp.h
@@ -157,8 +157,7 @@ static inline unsigned long __raw_read_lock_irqsave(rwlock_t *lock)
 	local_irq_save(flags);
 	preempt_disable();
 	rwlock_acquire_read(&lock->dep_map, 0, 0, _RET_IP_);
-	LOCK_CONTENDED_FLAGS(lock, do_raw_read_trylock, do_raw_read_lock,
-			     do_raw_read_lock_flags, &flags);
+	LOCK_CONTENDED(lock, do_raw_read_trylock, do_raw_read_lock);
 	return flags;
 }
 
@@ -184,8 +183,7 @@ static inline unsigned long __raw_write_lock_irqsave(rwlock_t *lock)
 	local_irq_save(flags);
 	preempt_disable();
 	rwlock_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	LOCK_CONTENDED_FLAGS(lock, do_raw_write_trylock, do_raw_write_lock,
-			     do_raw_write_lock_flags, &flags);
+	LOCK_CONTENDED(lock, do_raw_write_trylock, do_raw_write_lock);
 	return flags;
 }
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index e0454e60fe8f..caf7071fda87 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2037,7 +2037,7 @@ static inline int _cond_resched(void) { return 0; }
 #endif /* !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC) */
 
 #define cond_resched() ({			\
-	___might_sleep(__FILE__, __LINE__, 0);	\
+	__might_resched(__FILE__, __LINE__, 0);	\
 	_cond_resched();			\
 })
 
@@ -2045,19 +2045,38 @@ extern int __cond_resched_lock(spinlock_t *lock);
 extern int __cond_resched_rwlock_read(rwlock_t *lock);
 extern int __cond_resched_rwlock_write(rwlock_t *lock);
 
-#define cond_resched_lock(lock) ({				\
-	___might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);\
-	__cond_resched_lock(lock);				\
+#define MIGHT_RESCHED_RCU_SHIFT		8
+#define MIGHT_RESCHED_PREEMPT_MASK	((1U << MIGHT_RESCHED_RCU_SHIFT) - 1)
+
+#ifndef CONFIG_PREEMPT_RT
+/*
+ * Non RT kernels have an elevated preempt count due to the held lock,
+ * but are not allowed to be inside a RCU read side critical section
+ */
+# define PREEMPT_LOCK_RESCHED_OFFSETS	PREEMPT_LOCK_OFFSET
+#else
+/*
+ * spin/rw_lock() on RT implies rcu_read_lock(). The might_sleep() check in
+ * cond_resched*lock() has to take that into account because it checks for
+ * preempt_count() and rcu_preempt_depth().
+ */
+# define PREEMPT_LOCK_RESCHED_OFFSETS	\
+	(PREEMPT_LOCK_OFFSET + (1U << MIGHT_RESCHED_RCU_SHIFT))
+#endif
+
+#define cond_resched_lock(lock) ({						\
+	__might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS);	\
+	__cond_resched_lock(lock);						\
 })
 
-#define cond_resched_rwlock_read(lock) ({			\
-	__might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);	\
-	__cond_resched_rwlock_read(lock);			\
+#define cond_resched_rwlock_read(lock) ({					\
+	__might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS);	\
+	__cond_resched_rwlock_read(lock);					\
 })
 
-#define cond_resched_rwlock_write(lock) ({			\
-	__might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);	\
-	__cond_resched_rwlock_write(lock);			\
+#define cond_resched_rwlock_write(lock) ({					\
+	__might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS);	\
+	__cond_resched_rwlock_write(lock);					\
 })
 
 static inline void cond_resched_rcu(void)
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 45310ea1b1d7..f0447062eecd 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -177,7 +177,6 @@ do {									\
 
 #ifdef CONFIG_DEBUG_SPINLOCK
  extern void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock);
-#define do_raw_spin_lock_flags(lock, flags) do_raw_spin_lock(lock)
  extern int do_raw_spin_trylock(raw_spinlock_t *lock);
  extern void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock);
 #else
@@ -188,18 +187,6 @@ static inline void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock)
 	mmiowb_spin_lock();
 }
 
-#ifndef arch_spin_lock_flags
-#define arch_spin_lock_flags(lock, flags)	arch_spin_lock(lock)
-#endif
-
-static inline void
-do_raw_spin_lock_flags(raw_spinlock_t *lock, unsigned long *flags) __acquires(lock)
-{
-	__acquire(lock);
-	arch_spin_lock_flags(&lock->raw_lock, *flags);
-	mmiowb_spin_lock();
-}
-
 static inline int do_raw_spin_trylock(raw_spinlock_t *lock)
 {
 	int ret = arch_spin_trylock(&(lock)->raw_lock);
diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h
index 6b8e1a0b137b..51fa0dab68c4 100644
--- a/include/linux/spinlock_api_smp.h
+++ b/include/linux/spinlock_api_smp.h
@@ -108,16 +108,7 @@ static inline unsigned long __raw_spin_lock_irqsave(raw_spinlock_t *lock)
 	local_irq_save(flags);
 	preempt_disable();
 	spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	/*
-	 * On lockdep we dont want the hand-coded irq-enable of
-	 * do_raw_spin_lock_flags() code, because lockdep assumes
-	 * that interrupts are not re-enabled during lock-acquire:
-	 */
-#ifdef CONFIG_LOCKDEP
 	LOCK_CONTENDED(lock, do_raw_spin_trylock, do_raw_spin_lock);
-#else
-	do_raw_spin_lock_flags(lock, &flags);
-#endif
 	return flags;
 }
 
diff --git a/include/linux/spinlock_up.h b/include/linux/spinlock_up.h
index 0ac9112c1bbe..16521074b6f7 100644
--- a/include/linux/spinlock_up.h
+++ b/include/linux/spinlock_up.h
@@ -62,7 +62,6 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 #define arch_spin_is_locked(lock)	((void)(lock), 0)
 /* for sched/core.c and kernel_lock.c: */
 # define arch_spin_lock(lock)		do { barrier(); (void)(lock); } while (0)
-# define arch_spin_lock_flags(lock, flags)	do { barrier(); (void)(lock); } while (0)
 # define arch_spin_unlock(lock)	do { barrier(); (void)(lock); } while (0)
 # define arch_spin_trylock(lock)	({ barrier(); (void)(lock); 1; })
 #endif /* DEBUG_SPINLOCK */
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 252243c7783d..528a478dbda8 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -58,6 +58,7 @@ struct mq_attr;
 struct compat_stat;
 struct old_timeval32;
 struct robust_list_head;
+struct futex_waitv;
 struct getcpu_cache;
 struct old_linux_dirent;
 struct perf_event_attr;
@@ -610,7 +611,7 @@ asmlinkage long sys_waitid(int which, pid_t pid,
 asmlinkage long sys_set_tid_address(int __user *tidptr);
 asmlinkage long sys_unshare(unsigned long unshare_flags);
 
-/* kernel/futex.c */
+/* kernel/futex/syscalls.c */
 asmlinkage long sys_futex(u32 __user *uaddr, int op, u32 val,
 			  const struct __kernel_timespec __user *utime,
 			  u32 __user *uaddr2, u32 val3);
@@ -623,6 +624,10 @@ asmlinkage long sys_get_robust_list(int pid,
 asmlinkage long sys_set_robust_list(struct robust_list_head __user *head,
 				    size_t len);
 
+asmlinkage long sys_futex_waitv(struct futex_waitv *waiters,
+				unsigned int nr_futexes, unsigned int flags,
+				struct __kernel_timespec __user *timeout, clockid_t clockid);
+
 /* kernel/hrtimer.c */
 asmlinkage long sys_nanosleep(struct __kernel_timespec __user *rqtp,
 			      struct __kernel_timespec __user *rmtp);
diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h
index 29db736af86d..bb763085479a 100644
--- a/include/linux/ww_mutex.h
+++ b/include/linux/ww_mutex.h
@@ -28,12 +28,10 @@
 #ifndef CONFIG_PREEMPT_RT
 #define WW_MUTEX_BASE			mutex
 #define ww_mutex_base_init(l,n,k)	__mutex_init(l,n,k)
-#define ww_mutex_base_trylock(l)	mutex_trylock(l)
 #define ww_mutex_base_is_locked(b)	mutex_is_locked((b))
 #else
 #define WW_MUTEX_BASE			rt_mutex
 #define ww_mutex_base_init(l,n,k)	__rt_mutex_init(l,n,k)
-#define ww_mutex_base_trylock(l)	rt_mutex_trylock(l)
 #define ww_mutex_base_is_locked(b)	rt_mutex_base_is_locked(&(b)->rtmutex)
 #endif
 
@@ -339,17 +337,8 @@ ww_mutex_lock_slow_interruptible(struct ww_mutex *lock,
 
 extern void ww_mutex_unlock(struct ww_mutex *lock);
 
-/**
- * ww_mutex_trylock - tries to acquire the w/w mutex without acquire context
- * @lock: mutex to lock
- *
- * Trylocks a mutex without acquire context, so no deadlock detection is
- * possible. Returns 1 if the mutex has been acquired successfully, 0 otherwise.
- */
-static inline int __must_check ww_mutex_trylock(struct ww_mutex *lock)
-{
-	return ww_mutex_base_trylock(&lock->base);
-}
+extern int __must_check ww_mutex_trylock(struct ww_mutex *lock,
+					 struct ww_acquire_ctx *ctx);
 
 /***
  * ww_mutex_destroy - mark a w/w mutex unusable
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 1c5fb86d455a..4557a8b6086f 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -880,8 +880,11 @@ __SYSCALL(__NR_memfd_secret, sys_memfd_secret)
 #define __NR_process_mrelease 448
 __SYSCALL(__NR_process_mrelease, sys_process_mrelease)
 
+#define __NR_futex_waitv 449
+__SYSCALL(__NR_futex_waitv, sys_futex_waitv)
+
 #undef __NR_syscalls
-#define __NR_syscalls 449
+#define __NR_syscalls 450
 
 /*
  * 32 bit systems traditionally used different
diff --git a/include/uapi/linux/futex.h b/include/uapi/linux/futex.h
index 235e5b2facaa..71a5df8d2689 100644
--- a/include/uapi/linux/futex.h
+++ b/include/uapi/linux/futex.h
@@ -44,6 +44,31 @@
 					 FUTEX_PRIVATE_FLAG)
 
 /*
+ * Flags to specify the bit length of the futex word for futex2 syscalls.
+ * Currently, only 32 is supported.
+ */
+#define FUTEX_32		2
+
+/*
+ * Max numbers of elements in a futex_waitv array
+ */
+#define FUTEX_WAITV_MAX		128
+
+/**
+ * struct futex_waitv - A waiter for vectorized wait
+ * @val:	Expected value at uaddr
+ * @uaddr:	User address to wait on
+ * @flags:	Flags for this waiter
+ * @__reserved:	Reserved member to preserve data alignment. Should be 0.
+ */
+struct futex_waitv {
+	__u64 val;
+	__u64 uaddr;
+	__u32 flags;
+	__u32 __reserved;
+};
+
+/*
  * Support for robust futexes: the kernel cleans up held futexes at
  * thread exit time.
  */