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, 28 insertions, 13 deletions

diff --git a/include/asm-generic/bitops/non-atomic.h b/include/asm-generic/bitops/non-atomic.h
index 7e10c4b50c5d..c8149cd52730 100644
--- a/include/asm-generic/bitops/non-atomic.h
+++ b/include/asm-generic/bitops/non-atomic.h
@@ -5,7 +5,7 @@
 #include <asm/types.h>
 
 /**
- * __set_bit - Set a bit in memory
+ * arch___set_bit - Set a bit in memory
  * @nr: the bit to set
  * @addr: the address to start counting from
  *
@@ -13,24 +13,28 @@
  * If it's called on the same region of memory simultaneously, the effect
  * may be that only one operation succeeds.
  */
-static inline void __set_bit(int nr, volatile unsigned long *addr)
+static __always_inline void
+arch___set_bit(int nr, volatile unsigned long *addr)
 {
 	unsigned long mask = BIT_MASK(nr);
 	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
 
 	*p  |= mask;
 }
+#define arch___set_bit_uses_plain_access
 
-static inline void __clear_bit(int nr, volatile unsigned long *addr)
+static __always_inline void
+arch___clear_bit(int nr, volatile unsigned long *addr)
 {
 	unsigned long mask = BIT_MASK(nr);
 	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
 
 	*p &= ~mask;
 }
+#define arch___clear_bit_uses_plain_access
 
 /**
- * __change_bit - Toggle a bit in memory
+ * arch___change_bit - Toggle a bit in memory
  * @nr: the bit to change
  * @addr: the address to start counting from
  *
@@ -38,16 +42,18 @@ static inline void __clear_bit(int nr, volatile unsigned long *addr)
  * If it's called on the same region of memory simultaneously, the effect
  * may be that only one operation succeeds.
  */
-static inline void __change_bit(int nr, volatile unsigned long *addr)
+static __always_inline
+void arch___change_bit(int nr, volatile unsigned long *addr)
 {
 	unsigned long mask = BIT_MASK(nr);
 	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
 
 	*p ^= mask;
 }
+#define arch___change_bit_uses_plain_access
 
 /**
- * __test_and_set_bit - Set a bit and return its old value
+ * arch___test_and_set_bit - Set a bit and return its old value
  * @nr: Bit to set
  * @addr: Address to count from
  *
@@ -55,7 +61,8 @@ static inline void __change_bit(int nr, volatile unsigned long *addr)
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
  */
-static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
+static __always_inline int
+arch___test_and_set_bit(int nr, volatile unsigned long *addr)
 {
 	unsigned long mask = BIT_MASK(nr);
 	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
@@ -64,9 +71,10 @@ static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
 	*p = old | mask;
 	return (old & mask) != 0;
 }
+#define arch___test_and_set_bit_uses_plain_access
 
 /**
- * __test_and_clear_bit - Clear a bit and return its old value
+ * arch___test_and_clear_bit - Clear a bit and return its old value
  * @nr: Bit to clear
  * @addr: Address to count from
  *
@@ -74,7 +82,8 @@ static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
  */
-static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
+static __always_inline int
+arch___test_and_clear_bit(int nr, volatile unsigned long *addr)
 {
 	unsigned long mask = BIT_MASK(nr);
 	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
@@ -83,10 +92,11 @@ static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
 	*p = old & ~mask;
 	return (old & mask) != 0;
 }
+#define arch___test_and_clear_bit_uses_plain_access
 
 /* WARNING: non atomic and it can be reordered! */
-static inline int __test_and_change_bit(int nr,
-					    volatile unsigned long *addr)
+static __always_inline int
+arch___test_and_change_bit(int nr, volatile unsigned long *addr)
 {
 	unsigned long mask = BIT_MASK(nr);
 	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
@@ -95,15 +105,20 @@ static inline int __test_and_change_bit(int nr,
 	*p = old ^ mask;
 	return (old & mask) != 0;
 }
+#define arch___test_and_change_bit_uses_plain_access
 
 /**
- * test_bit - Determine whether a bit is set
+ * arch_test_bit - Determine whether a bit is set
  * @nr: bit number to test
  * @addr: Address to start counting from
  */
-static inline int test_bit(int nr, const volatile unsigned long *addr)
+static __always_inline int
+arch_test_bit(int nr, const volatile unsigned long *addr)
 {
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
+#define arch_test_bit_uses_plain_access
+
+#include <asm-generic/bitops/instrumented-non-atomic.h>
 
 #endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */