Merge branch 'locking/core' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip into io_uring-futex

Pull in locking/core from the tip tree, to get the futex2 dependencies
from Peter Zijlstra.

* 'locking/core' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (24 commits)
  locking/ww_mutex/test: Make sure we bail out instead of livelock
  locking/ww_mutex/test: Fix potential workqueue corruption
  locking/ww_mutex/test: Use prng instead of rng to avoid hangs at bootup
  futex: Add sys_futex_requeue()
  futex: Add flags2 argument to futex_requeue()
  futex: Propagate flags into get_futex_key()
  futex: Add sys_futex_wait()
  futex: FLAGS_STRICT
  futex: Add sys_futex_wake()
  futex: Validate futex value against futex size
  futex: Flag conversion
  futex: Extend the FUTEX2 flags
  futex: Clarify FUTEX2 flags
  asm-generic: ticket-lock: Optimize arch_spin_value_unlocked()
  futex/pi: Fix recursive rt_mutex waiter state
  locking/rtmutex: Add a lockdep assert to catch potential nested blocking
  locking/rtmutex: Use rt_mutex specific scheduler helpers
  sched: Provide rt_mutex specific scheduler helpers
  sched: Extract __schedule_loop()
  locking/rtmutex: Avoid unconditional slowpath for DEBUG_RT_MUTEXES
  ...

7 files changed, 97 insertions, 14 deletions

diff --git a/include/asm-generic/spinlock.h b/include/asm-generic/spinlock.h
index fdfebcb050f4..90803a826ba0 100644
--- a/include/asm-generic/spinlock.h
+++ b/include/asm-generic/spinlock.h
@@ -68,11 +68,18 @@ static __always_inline void arch_spin_unlock(arch_spinlock_t *lock)
 	smp_store_release(ptr, (u16)val + 1);
 }
 
+static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock)
+{
+	u32 val = lock.counter;
+
+	return ((val >> 16) == (val & 0xffff));
+}
+
 static __always_inline int arch_spin_is_locked(arch_spinlock_t *lock)
 {
-	u32 val = atomic_read(lock);
+	arch_spinlock_t val = READ_ONCE(*lock);
 
-	return ((val >> 16) != (val & 0xffff));
+	return !arch_spin_value_unlocked(val);
 }
 
 static __always_inline int arch_spin_is_contended(arch_spinlock_t *lock)
@@ -82,11 +89,6 @@ static __always_inline int arch_spin_is_contended(arch_spinlock_t *lock)
 	return (s16)((val >> 16) - (val & 0xffff)) > 1;
 }
 
-static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock)
-{
-	return !arch_spin_is_locked(&lock);
-}
-
 #include <asm/qrwlock.h>
 
 #endif /* __ASM_GENERIC_SPINLOCK_H */
diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h
index 53f1a7a932b0..9f1a9c455b68 100644
--- a/include/linux/cleanup.h
+++ b/include/linux/cleanup.h
@@ -7,8 +7,9 @@
 /*
  * DEFINE_FREE(name, type, free):
  *	simple helper macro that defines the required wrapper for a __free()
- *	based cleanup function. @free is an expression using '_T' to access
- *	the variable.
+ *	based cleanup function. @free is an expression using '_T' to access the
+ *	variable. @free should typically include a NULL test before calling a
+ *	function, see the example below.
  *
  * __free(name):
  *	variable attribute to add a scoped based cleanup to the variable.
@@ -17,6 +18,9 @@
  *	like a non-atomic xchg(var, NULL), such that the cleanup function will
  *	be inhibited -- provided it sanely deals with a NULL value.
  *
+ *	NOTE: this has __must_check semantics so that it is harder to accidentally
+ *	leak the resource.
+ *
  * return_ptr(p):
  *	returns p while inhibiting the __free().
  *
@@ -24,6 +28,8 @@
  *
  * DEFINE_FREE(kfree, void *, if (_T) kfree(_T))
  *
+ * void *alloc_obj(...)
+ * {
  *	struct obj *p __free(kfree) = kmalloc(...);
  *	if (!p)
  *		return NULL;
@@ -32,6 +38,24 @@
  *		return NULL;
  *
  *	return_ptr(p);
+ * }
+ *
+ * NOTE: the DEFINE_FREE()'s @free expression includes a NULL test even though
+ * kfree() is fine to be called with a NULL value. This is on purpose. This way
+ * the compiler sees the end of our alloc_obj() function as:
+ *
+ *	tmp = p;
+ *	p = NULL;
+ *	if (p)
+ *		kfree(p);
+ *	return tmp;
+ *
+ * And through the magic of value-propagation and dead-code-elimination, it
+ * eliminates the actual cleanup call and compiles into:
+ *
+ *	return p;
+ *
+ * Without the NULL test it turns into a mess and the compiler can't help us.
  */
 
 #define DEFINE_FREE(_name, _type, _free) \
@@ -39,8 +63,17 @@
 
 #define __free(_name)	__cleanup(__free_##_name)
 
+#define __get_and_null_ptr(p) \
+	({ __auto_type __ptr = &(p); \
+	   __auto_type __val = *__ptr; \
+	   *__ptr = NULL;  __val; })
+
+static inline __must_check
+const volatile void * __must_check_fn(const volatile void *val)
+{ return val; }
+
 #define no_free_ptr(p) \
-	({ __auto_type __ptr = (p); (p) = NULL; __ptr; })
+	((typeof(p)) __must_check_fn(__get_and_null_ptr(p)))
 
 #define return_ptr(p)	return no_free_ptr(p)
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 77f01ac385f7..67623ffd4a8e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -911,6 +911,9 @@ struct task_struct {
 	 * ->sched_remote_wakeup gets used, so it can be in this word.
 	 */
 	unsigned			sched_remote_wakeup:1;
+#ifdef CONFIG_RT_MUTEXES
+	unsigned			sched_rt_mutex:1;
+#endif
 
 	/* Bit to tell LSMs we're in execve(): */
 	unsigned			in_execve:1;
diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h
index 994c25640e15..b2b9e6eb9683 100644
--- a/include/linux/sched/rt.h
+++ b/include/linux/sched/rt.h
@@ -30,6 +30,10 @@ static inline bool task_is_realtime(struct task_struct *tsk)
 }
 
 #ifdef CONFIG_RT_MUTEXES
+extern void rt_mutex_pre_schedule(void);
+extern void rt_mutex_schedule(void);
+extern void rt_mutex_post_schedule(void);
+
 /*
  * Must hold either p->pi_lock or task_rq(p)->lock.
  */
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 22bc6bc147f8..0901af60d971 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -549,6 +549,16 @@ asmlinkage long sys_set_robust_list(struct robust_list_head __user *head,
 asmlinkage long sys_futex_waitv(struct futex_waitv *waiters,
 				unsigned int nr_futexes, unsigned int flags,
 				struct __kernel_timespec __user *timeout, clockid_t clockid);
+
+asmlinkage long sys_futex_wake(void __user *uaddr, unsigned long mask, int nr, unsigned int flags);
+
+asmlinkage long sys_futex_wait(void __user *uaddr, unsigned long val, unsigned long mask,
+			       unsigned int flags, struct __kernel_timespec __user *timespec,
+			       clockid_t clockid);
+
+asmlinkage long sys_futex_requeue(struct futex_waitv __user *waiters,
+				  unsigned int flags, int nr_wake, int nr_requeue);
+
 asmlinkage long sys_nanosleep(struct __kernel_timespec __user *rqtp,
 			      struct __kernel_timespec __user *rmtp);
 asmlinkage long sys_nanosleep_time32(struct old_timespec32 __user *rqtp,
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index abe087c53b4b..d9e9cd13e577 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -822,9 +822,15 @@ __SYSCALL(__NR_cachestat, sys_cachestat)
 
 #define __NR_fchmodat2 452
 __SYSCALL(__NR_fchmodat2, sys_fchmodat2)
+#define __NR_futex_wake 454
+__SYSCALL(__NR_futex_wake, sys_futex_wake)
+#define __NR_futex_wait 455
+__SYSCALL(__NR_futex_wait, sys_futex_wait)
+#define __NR_futex_requeue 456
+__SYSCALL(__NR_futex_requeue, sys_futex_requeue)
 
 #undef __NR_syscalls
-#define __NR_syscalls 453
+#define __NR_syscalls 457
 
 /*
  * 32 bit systems traditionally used different
diff --git a/include/uapi/linux/futex.h b/include/uapi/linux/futex.h
index 71a5df8d2689..d2ee625ea189 100644
--- a/include/uapi/linux/futex.h
+++ b/include/uapi/linux/futex.h
@@ -44,10 +44,35 @@
 					 FUTEX_PRIVATE_FLAG)
 
 /*
- * Flags to specify the bit length of the futex word for futex2 syscalls.
- * Currently, only 32 is supported.
+ * Flags for futex2 syscalls.
+ *
+ * NOTE: these are not pure flags, they can also be seen as:
+ *
+ *   union {
+ *     u32  flags;
+ *     struct {
+ *       u32 size    : 2,
+ *           numa    : 1,
+ *                   : 4,
+ *           private : 1;
+ *     };
+ *   };
  */
-#define FUTEX_32		2
+#define FUTEX2_SIZE_U8		0x00
+#define FUTEX2_SIZE_U16		0x01
+#define FUTEX2_SIZE_U32		0x02
+#define FUTEX2_SIZE_U64		0x03
+#define FUTEX2_NUMA		0x04
+			/*	0x08 */
+			/*	0x10 */
+			/*	0x20 */
+			/*	0x40 */
+#define FUTEX2_PRIVATE		FUTEX_PRIVATE_FLAG
+
+#define FUTEX2_SIZE_MASK	0x03
+
+/* do not use */
+#define FUTEX_32		FUTEX2_SIZE_U32 /* historical accident :-( */
 
 /*
  * Max numbers of elements in a futex_waitv array