1 files changed, 288 insertions, 65 deletions

diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 7d537ced949a..d3561c4a080e 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -1,5 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __LINUX_SPINLOCK_H
 #define __LINUX_SPINLOCK_H
+#define __LINUX_INSIDE_SPINLOCK_H
 
 /*
  * include/linux/spinlock.h - generic spinlock/rwlock declarations
@@ -11,6 +13,8 @@
  *  asm/spinlock_types.h: contains the arch_spinlock_t/arch_rwlock_t and the
  *                        initializers
  *
+ *  linux/spinlock_types_raw:
+ *			  The raw types and initializers
  *  linux/spinlock_types.h:
  *                        defines the generic type and initializers
  *
@@ -30,6 +34,8 @@
  *                        contains the generic, simplified UP spinlock type.
  *                        (which is an empty structure on non-debug builds)
  *
+ *  linux/spinlock_types_raw:
+ *			  The raw RT types and initializers
  *  linux/spinlock_types.h:
  *                        defines the generic type and initializers
  *
@@ -52,10 +58,12 @@
 #include <linux/compiler.h>
 #include <linux/irqflags.h>
 #include <linux/thread_info.h>
-#include <linux/kernel.h>
 #include <linux/stringify.h>
 #include <linux/bottom_half.h>
+#include <linux/lockdep.h>
+#include <linux/cleanup.h>
 #include <asm/barrier.h>
+#include <asm/mmiowb.h>
 
 
 /*
@@ -73,7 +81,7 @@
 #define LOCK_SECTION_END                        \
         ".previous\n\t"
 
-#define __lockfunc __attribute__((section(".spinlock.text")))
+#define __lockfunc __section(".spinlock.text")
 
 /*
  * Pull the arch_spinlock_t and arch_rwlock_t definitions:
@@ -91,12 +99,13 @@
 
 #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
@@ -106,31 +115,69 @@ do {								\
 
 #define raw_spin_is_locked(lock)	arch_spin_is_locked(&(lock)->raw_lock)
 
-#ifdef CONFIG_GENERIC_LOCKBREAK
-#define raw_spin_is_contended(lock) ((lock)->break_lock)
-#else
-
 #ifdef arch_spin_is_contended
 #define raw_spin_is_contended(lock)	arch_spin_is_contended(&(lock)->raw_lock)
 #else
 #define raw_spin_is_contended(lock)	(((void)(lock), 0))
 #endif /*arch_spin_is_contended*/
-#endif
-
-/* The lock does not imply full memory barrier. */
-#ifndef ARCH_HAS_SMP_MB_AFTER_LOCK
-static inline void smp_mb__after_lock(void) { smp_mb(); }
-#endif
 
-/**
- * raw_spin_unlock_wait - wait until the spinlock gets unlocked
- * @lock: the spinlock in question.
+/*
+ * smp_mb__after_spinlock() provides the equivalent of a full memory barrier
+ * between program-order earlier lock acquisitions and program-order later
+ * memory accesses.
+ *
+ * This guarantees that the following two properties hold:
+ *
+ *   1) Given the snippet:
+ *
+ *	  { X = 0;  Y = 0; }
+ *
+ *	  CPU0				CPU1
+ *
+ *	  WRITE_ONCE(X, 1);		WRITE_ONCE(Y, 1);
+ *	  spin_lock(S);			smp_mb();
+ *	  smp_mb__after_spinlock();	r1 = READ_ONCE(X);
+ *	  r0 = READ_ONCE(Y);
+ *	  spin_unlock(S);
+ *
+ *      it is forbidden that CPU0 does not observe CPU1's store to Y (r0 = 0)
+ *      and CPU1 does not observe CPU0's store to X (r1 = 0); see the comments
+ *      preceding the call to smp_mb__after_spinlock() in __schedule() and in
+ *      try_to_wake_up().
+ *
+ *   2) Given the snippet:
+ *
+ *  { X = 0;  Y = 0; }
+ *
+ *  CPU0		CPU1				CPU2
+ *
+ *  spin_lock(S);	spin_lock(S);			r1 = READ_ONCE(Y);
+ *  WRITE_ONCE(X, 1);	smp_mb__after_spinlock();	smp_rmb();
+ *  spin_unlock(S);	r0 = READ_ONCE(X);		r2 = READ_ONCE(X);
+ *			WRITE_ONCE(Y, 1);
+ *			spin_unlock(S);
+ *
+ *      it is forbidden that CPU0's critical section executes before CPU1's
+ *      critical section (r0 = 1), CPU2 observes CPU1's store to Y (r1 = 1)
+ *      and CPU2 does not observe CPU0's store to X (r2 = 0); see the comments
+ *      preceding the calls to smp_rmb() in try_to_wake_up() for similar
+ *      snippets but "projected" onto two CPUs.
+ *
+ * Property (2) upgrades the lock to an RCsc lock.
+ *
+ * Since most load-store architectures implement ACQUIRE with an smp_mb() after
+ * the LL/SC loop, they need no further barriers. Similarly all our TSO
+ * architectures imply an smp_mb() for each atomic instruction and equally don't
+ * need more.
+ *
+ * Architectures that can implement ACQUIRE better need to take care.
  */
-#define raw_spin_unlock_wait(lock)	arch_spin_unlock_wait(&(lock)->raw_lock)
+#ifndef smp_mb__after_spinlock
+#define smp_mb__after_spinlock()	kcsan_mb()
+#endif
 
 #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
@@ -138,22 +185,22 @@ static inline void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock)
 {
 	__acquire(lock);
 	arch_spin_lock(&lock->raw_lock);
-}
-
-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)
 {
-	return arch_spin_trylock(&(lock)->raw_lock);
+	int ret = arch_spin_trylock(&(lock)->raw_lock);
+
+	if (ret)
+		mmiowb_spin_lock();
+
+	return ret;
 }
 
 static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock)
 {
+	mmiowb_spin_unlock();
 	arch_spin_unlock(&lock->raw_lock);
 	__release(lock);
 }
@@ -161,7 +208,7 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock)
 
 /*
  * Define the various spin_lock methods.  Note we define these
- * regardless of whether CONFIG_SMP or CONFIG_PREEMPT are set. The
+ * regardless of whether CONFIG_SMP or CONFIG_PREEMPTION are set. The
  * various methods are defined as nops in the case they are not
  * required.
  */
@@ -179,7 +226,13 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock)
 		 _raw_spin_lock_nest_lock(lock, &(nest_lock)->dep_map);	\
 	 } while (0)
 #else
-# define raw_spin_lock_nested(lock, subclass)		_raw_spin_lock(lock)
+/*
+ * Always evaluate the 'subclass' argument to avoid that the compiler
+ * warns about set-but-not-used variables when building with
+ * CONFIG_DEBUG_LOCK_ALLOC=n and with W=1.
+ */
+# define raw_spin_lock_nested(lock, subclass)		\
+	_raw_spin_lock(((void)(subclass), (lock)))
 # define raw_spin_lock_nest_lock(lock, nest_lock)	_raw_spin_lock(lock)
 #endif
 
@@ -247,14 +300,10 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock)
 	1 : ({ local_irq_restore(flags); 0; }); \
 })
 
-/**
- * raw_spin_can_lock - would raw_spin_trylock() succeed?
- * @lock: the spinlock in question.
- */
-#define raw_spin_can_lock(lock)	(!raw_spin_is_locked(lock))
-
-/* Include rwlock functions */
+#ifndef CONFIG_PREEMPT_RT
+/* Include rwlock functions for !RT */
 #include <linux/rwlock.h>
+#endif
 
 /*
  * Pull the _spin_*()/_read_*()/_write_*() functions/declarations:
@@ -265,32 +314,49 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock)
 # include <linux/spinlock_api_up.h>
 #endif
 
+/* Non PREEMPT_RT kernel, map to raw spinlocks: */
+#ifndef CONFIG_PREEMPT_RT
+
 /*
  * Map the spin_lock functions to the raw variants for PREEMPT_RT=n
  */
 
-static inline raw_spinlock_t *spinlock_check(spinlock_t *lock)
+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)
 
-static inline void spin_lock(spinlock_t *lock)
+#endif
+
+static __always_inline void spin_lock(spinlock_t *lock)
 {
 	raw_spin_lock(&lock->rlock);
 }
 
-static inline void spin_lock_bh(spinlock_t *lock)
+static __always_inline void spin_lock_bh(spinlock_t *lock)
 {
 	raw_spin_lock_bh(&lock->rlock);
 }
 
-static inline int spin_trylock(spinlock_t *lock)
+static __always_inline int spin_trylock(spinlock_t *lock)
 {
 	return raw_spin_trylock(&lock->rlock);
 }
@@ -305,7 +371,7 @@ do {									\
 	raw_spin_lock_nest_lock(spinlock_check(lock), nest_lock);	\
 } while (0)
 
-static inline void spin_lock_irq(spinlock_t *lock)
+static __always_inline void spin_lock_irq(spinlock_t *lock)
 {
 	raw_spin_lock_irq(&lock->rlock);
 }
@@ -320,32 +386,32 @@ do {									\
 	raw_spin_lock_irqsave_nested(spinlock_check(lock), flags, subclass); \
 } while (0)
 
-static inline void spin_unlock(spinlock_t *lock)
+static __always_inline void spin_unlock(spinlock_t *lock)
 {
 	raw_spin_unlock(&lock->rlock);
 }
 
-static inline void spin_unlock_bh(spinlock_t *lock)
+static __always_inline void spin_unlock_bh(spinlock_t *lock)
 {
 	raw_spin_unlock_bh(&lock->rlock);
 }
 
-static inline void spin_unlock_irq(spinlock_t *lock)
+static __always_inline void spin_unlock_irq(spinlock_t *lock)
 {
 	raw_spin_unlock_irq(&lock->rlock);
 }
 
-static inline void spin_unlock_irqrestore(spinlock_t *lock, unsigned long flags)
+static __always_inline void spin_unlock_irqrestore(spinlock_t *lock, unsigned long flags)
 {
 	raw_spin_unlock_irqrestore(&lock->rlock, flags);
 }
 
-static inline int spin_trylock_bh(spinlock_t *lock)
+static __always_inline int spin_trylock_bh(spinlock_t *lock)
 {
 	return raw_spin_trylock_bh(&lock->rlock);
 }
 
-static inline int spin_trylock_irq(spinlock_t *lock)
+static __always_inline int spin_trylock_irq(spinlock_t *lock)
 {
 	return raw_spin_trylock_irq(&lock->rlock);
 }
@@ -355,27 +421,68 @@ static inline int spin_trylock_irq(spinlock_t *lock)
 	raw_spin_trylock_irqsave(spinlock_check(lock), flags); \
 })
 
-static inline void spin_unlock_wait(spinlock_t *lock)
-{
-	raw_spin_unlock_wait(&lock->rlock);
-}
-
-static inline int spin_is_locked(spinlock_t *lock)
+/**
+ * spin_is_locked() - Check whether a spinlock is locked.
+ * @lock: Pointer to the spinlock.
+ *
+ * This function is NOT required to provide any memory ordering
+ * guarantees; it could be used for debugging purposes or, when
+ * additional synchronization is needed, accompanied with other
+ * constructs (memory barriers) enforcing the synchronization.
+ *
+ * Returns: 1 if @lock is locked, 0 otherwise.
+ *
+ * Note that the function only tells you that the spinlock is
+ * seen to be locked, not that it is locked on your CPU.
+ *
+ * Further, on CONFIG_SMP=n builds with CONFIG_DEBUG_SPINLOCK=n,
+ * the return value is always 0 (see include/linux/spinlock_up.h).
+ * Therefore you should not rely heavily on the return value.
+ */
+static __always_inline int spin_is_locked(spinlock_t *lock)
 {
 	return raw_spin_is_locked(&lock->rlock);
 }
 
-static inline int spin_is_contended(spinlock_t *lock)
+static __always_inline int spin_is_contended(spinlock_t *lock)
 {
 	return raw_spin_is_contended(&lock->rlock);
 }
 
-static inline int spin_can_lock(spinlock_t *lock)
+#define assert_spin_locked(lock)	assert_raw_spin_locked(&(lock)->rlock)
+
+#else  /* !CONFIG_PREEMPT_RT */
+# include <linux/spinlock_rt.h>
+#endif /* CONFIG_PREEMPT_RT */
+
+/*
+ * Does a critical section need to be broken due to another
+ * task waiting?: (technically does not depend on CONFIG_PREEMPTION,
+ * but a general need for low latency)
+ */
+static inline int spin_needbreak(spinlock_t *lock)
 {
-	return raw_spin_can_lock(&lock->rlock);
+	if (!preempt_model_preemptible())
+		return 0;
+
+	return spin_is_contended(lock);
 }
 
-#define assert_spin_locked(lock)	assert_raw_spin_locked(&(lock)->rlock)
+/*
+ * Check if a rwlock is contended.
+ * Returns non-zero if there is another task waiting on the rwlock.
+ * Returns zero if the lock is not contended or the system / underlying
+ * rwlock implementation does not support contention detection.
+ * Technically does not depend on CONFIG_PREEMPTION, but a general need
+ * for low latency.
+ */
+static inline int rwlock_needbreak(rwlock_t *lock)
+{
+	if (!preempt_model_preemptible())
+		return 0;
+
+	return rwlock_is_contended(lock);
+}
 
 /*
  * Pull the atomic_t declaration:
@@ -394,4 +501,120 @@ extern int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock);
 #define atomic_dec_and_lock(atomic, lock) \
 		__cond_lock(lock, _atomic_dec_and_lock(atomic, lock))
 
+extern int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock,
+					unsigned long *flags);
+#define atomic_dec_and_lock_irqsave(atomic, lock, flags) \
+		__cond_lock(lock, _atomic_dec_and_lock_irqsave(atomic, lock, &(flags)))
+
+extern int _atomic_dec_and_raw_lock(atomic_t *atomic, raw_spinlock_t *lock);
+#define atomic_dec_and_raw_lock(atomic, lock) \
+		__cond_lock(lock, _atomic_dec_and_raw_lock(atomic, lock))
+
+extern int _atomic_dec_and_raw_lock_irqsave(atomic_t *atomic, raw_spinlock_t *lock,
+					unsigned long *flags);
+#define atomic_dec_and_raw_lock_irqsave(atomic, lock, flags) \
+		__cond_lock(lock, _atomic_dec_and_raw_lock_irqsave(atomic, lock, &(flags)))
+
+int __alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *lock_mask,
+			     size_t max_size, unsigned int cpu_mult,
+			     gfp_t gfp, const char *name,
+			     struct lock_class_key *key);
+
+#define alloc_bucket_spinlocks(locks, lock_mask, max_size, cpu_mult, gfp)    \
+	({								     \
+		static struct lock_class_key key;			     \
+		int ret;						     \
+									     \
+		ret = __alloc_bucket_spinlocks(locks, lock_mask, max_size,   \
+					       cpu_mult, gfp, #locks, &key); \
+		ret;							     \
+	})
+
+void free_bucket_spinlocks(spinlock_t *locks);
+
+DEFINE_LOCK_GUARD_1(raw_spinlock, raw_spinlock_t,
+		    raw_spin_lock(_T->lock),
+		    raw_spin_unlock(_T->lock))
+
+DEFINE_LOCK_GUARD_1_COND(raw_spinlock, _try, raw_spin_trylock(_T->lock))
+
+DEFINE_LOCK_GUARD_1(raw_spinlock_nested, raw_spinlock_t,
+		    raw_spin_lock_nested(_T->lock, SINGLE_DEPTH_NESTING),
+		    raw_spin_unlock(_T->lock))
+
+DEFINE_LOCK_GUARD_1(raw_spinlock_irq, raw_spinlock_t,
+		    raw_spin_lock_irq(_T->lock),
+		    raw_spin_unlock_irq(_T->lock))
+
+DEFINE_LOCK_GUARD_1_COND(raw_spinlock_irq, _try, raw_spin_trylock_irq(_T->lock))
+
+DEFINE_LOCK_GUARD_1(raw_spinlock_bh, raw_spinlock_t,
+		    raw_spin_lock_bh(_T->lock),
+		    raw_spin_unlock_bh(_T->lock))
+
+DEFINE_LOCK_GUARD_1_COND(raw_spinlock_bh, _try, raw_spin_trylock_bh(_T->lock))
+
+DEFINE_LOCK_GUARD_1(raw_spinlock_irqsave, raw_spinlock_t,
+		    raw_spin_lock_irqsave(_T->lock, _T->flags),
+		    raw_spin_unlock_irqrestore(_T->lock, _T->flags),
+		    unsigned long flags)
+
+DEFINE_LOCK_GUARD_1_COND(raw_spinlock_irqsave, _try,
+			 raw_spin_trylock_irqsave(_T->lock, _T->flags))
+
+DEFINE_LOCK_GUARD_1(spinlock, spinlock_t,
+		    spin_lock(_T->lock),
+		    spin_unlock(_T->lock))
+
+DEFINE_LOCK_GUARD_1_COND(spinlock, _try, spin_trylock(_T->lock))
+
+DEFINE_LOCK_GUARD_1(spinlock_irq, spinlock_t,
+		    spin_lock_irq(_T->lock),
+		    spin_unlock_irq(_T->lock))
+
+DEFINE_LOCK_GUARD_1_COND(spinlock_irq, _try,
+			 spin_trylock_irq(_T->lock))
+
+DEFINE_LOCK_GUARD_1(spinlock_bh, spinlock_t,
+		    spin_lock_bh(_T->lock),
+		    spin_unlock_bh(_T->lock))
+
+DEFINE_LOCK_GUARD_1_COND(spinlock_bh, _try,
+			 spin_trylock_bh(_T->lock))
+
+DEFINE_LOCK_GUARD_1(spinlock_irqsave, spinlock_t,
+		    spin_lock_irqsave(_T->lock, _T->flags),
+		    spin_unlock_irqrestore(_T->lock, _T->flags),
+		    unsigned long flags)
+
+DEFINE_LOCK_GUARD_1_COND(spinlock_irqsave, _try,
+			 spin_trylock_irqsave(_T->lock, _T->flags))
+
+DEFINE_LOCK_GUARD_1(read_lock, rwlock_t,
+		    read_lock(_T->lock),
+		    read_unlock(_T->lock))
+
+DEFINE_LOCK_GUARD_1(read_lock_irq, rwlock_t,
+		    read_lock_irq(_T->lock),
+		    read_unlock_irq(_T->lock))
+
+DEFINE_LOCK_GUARD_1(read_lock_irqsave, rwlock_t,
+		    read_lock_irqsave(_T->lock, _T->flags),
+		    read_unlock_irqrestore(_T->lock, _T->flags),
+		    unsigned long flags)
+
+DEFINE_LOCK_GUARD_1(write_lock, rwlock_t,
+		    write_lock(_T->lock),
+		    write_unlock(_T->lock))
+
+DEFINE_LOCK_GUARD_1(write_lock_irq, rwlock_t,
+		    write_lock_irq(_T->lock),
+		    write_unlock_irq(_T->lock))
+
+DEFINE_LOCK_GUARD_1(write_lock_irqsave, rwlock_t,
+		    write_lock_irqsave(_T->lock, _T->flags),
+		    write_unlock_irqrestore(_T->lock, _T->flags),
+		    unsigned long flags)
+
+#undef __LINUX_INSIDE_SPINLOCK_H
 #endif /* __LINUX_SPINLOCK_H */