locking/atomic: add generic arch_*() bitops

Now that all architectures provide arch_atomic_long_*(), we can
implement the generic bitops atop these rather than atop
atomic_long_*(), and provide arch_*() forms of the bitops that are safe
to use in noinstr code.

Now that all architectures provide arch_atomic_long_*(), we can
build the generic arch_*() bitops atop these, which can be safely used
in noinstr code. The regular bitop wrappers are built atop these.

As the generic non-atomic bitops use plain accesses, these will be
implicitly instrumented unless they are inlined into noinstr functions
(which is similar to arch_atomic*_read() when based on READ_ONCE()).
The wrappers are modified so that where the underlying arch_*() function
uses a plain access, no explicit instrumentation is added, as this is
redundant and could result in confusing reports.

Since function prototypes get excessively long with both an `arch_`
prefix and `__always_inline` attribute, the return type and function
attributes have been split onto a separate line, matching the style of
the generated atomic headers.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210713105253.7615-6-mark.rutland@arm.com

1 files changed, 21 insertions, 18 deletions

diff --git a/include/asm-generic/bitops/lock.h b/include/asm-generic/bitops/lock.h
index 3ae021368f48..630f2f6b9595 100644
--- a/include/asm-generic/bitops/lock.h
+++ b/include/asm-generic/bitops/lock.h
@@ -7,7 +7,7 @@
 #include <asm/barrier.h>
 
 /**
- * test_and_set_bit_lock - Set a bit and return its old value, for lock
+ * arch_test_and_set_bit_lock - Set a bit and return its old value, for lock
  * @nr: Bit to set
  * @addr: Address to count from
  *
@@ -15,8 +15,8 @@
  * the returned value is 0.
  * It can be used to implement bit locks.
  */
-static inline int test_and_set_bit_lock(unsigned int nr,
-					volatile unsigned long *p)
+static __always_inline int
+arch_test_and_set_bit_lock(unsigned int nr, volatile unsigned long *p)
 {
 	long old;
 	unsigned long mask = BIT_MASK(nr);
@@ -25,26 +25,27 @@ static inline int test_and_set_bit_lock(unsigned int nr,
 	if (READ_ONCE(*p) & mask)
 		return 1;
 
-	old = atomic_long_fetch_or_acquire(mask, (atomic_long_t *)p);
+	old = arch_atomic_long_fetch_or_acquire(mask, (atomic_long_t *)p);
 	return !!(old & mask);
 }
 
 
 /**
- * clear_bit_unlock - Clear a bit in memory, for unlock
+ * arch_clear_bit_unlock - Clear a bit in memory, for unlock
  * @nr: the bit to set
  * @addr: the address to start counting from
  *
  * This operation is atomic and provides release barrier semantics.
  */
-static inline void clear_bit_unlock(unsigned int nr, volatile unsigned long *p)
+static __always_inline void
+arch_clear_bit_unlock(unsigned int nr, volatile unsigned long *p)
 {
 	p += BIT_WORD(nr);
-	atomic_long_fetch_andnot_release(BIT_MASK(nr), (atomic_long_t *)p);
+	arch_atomic_long_fetch_andnot_release(BIT_MASK(nr), (atomic_long_t *)p);
 }
 
 /**
- * __clear_bit_unlock - Clear a bit in memory, for unlock
+ * arch___clear_bit_unlock - Clear a bit in memory, for unlock
  * @nr: the bit to set
  * @addr: the address to start counting from
  *
@@ -54,38 +55,40 @@ static inline void clear_bit_unlock(unsigned int nr, volatile unsigned long *p)
  *
  * See for example x86's implementation.
  */
-static inline void __clear_bit_unlock(unsigned int nr,
-				      volatile unsigned long *p)
+static inline void
+arch___clear_bit_unlock(unsigned int nr, volatile unsigned long *p)
 {
 	unsigned long old;
 
 	p += BIT_WORD(nr);
 	old = READ_ONCE(*p);
 	old &= ~BIT_MASK(nr);
-	atomic_long_set_release((atomic_long_t *)p, old);
+	arch_atomic_long_set_release((atomic_long_t *)p, old);
 }
 
 /**
- * clear_bit_unlock_is_negative_byte - Clear a bit in memory and test if bottom
- *                                     byte is negative, for unlock.
+ * arch_clear_bit_unlock_is_negative_byte - Clear a bit in memory and test if bottom
+ *                                          byte is negative, for unlock.
  * @nr: the bit to clear
  * @addr: the address to start counting from
  *
  * This is a bit of a one-trick-pony for the filemap code, which clears
  * PG_locked and tests PG_waiters,
  */
-#ifndef clear_bit_unlock_is_negative_byte
-static inline bool clear_bit_unlock_is_negative_byte(unsigned int nr,
-						     volatile unsigned long *p)
+#ifndef arch_clear_bit_unlock_is_negative_byte
+static inline bool arch_clear_bit_unlock_is_negative_byte(unsigned int nr,
+							  volatile unsigned long *p)
 {
 	long old;
 	unsigned long mask = BIT_MASK(nr);
 
 	p += BIT_WORD(nr);
-	old = atomic_long_fetch_andnot_release(mask, (atomic_long_t *)p);
+	old = arch_atomic_long_fetch_andnot_release(mask, (atomic_long_t *)p);
 	return !!(old & BIT(7));
 }
-#define clear_bit_unlock_is_negative_byte clear_bit_unlock_is_negative_byte
+#define arch_clear_bit_unlock_is_negative_byte arch_clear_bit_unlock_is_negative_byte
 #endif
 
+#include <asm-generic/bitops/instrumented-lock.h>
+
 #endif /* _ASM_GENERIC_BITOPS_LOCK_H_ */