x86-32: Rewrite 32-bit atomic64 functions in assembly

This patch replaces atomic64_32.c with two assembly implementations,
one for 386/486 machines using pushf/cli/popf and one for 586+ machines
using cmpxchg8b.

The cmpxchg8b implementation provides the following advantages over the
current one:

1. Implements atomic64_add_unless, atomic64_dec_if_positive and
   atomic64_inc_not_zero

2. Uses the ZF flag changed by cmpxchg8b instead of doing a comparison

3. Uses custom register calling conventions that reduce or eliminate
   register moves to suit cmpxchg8b

4. Reads the initial value instead of using cmpxchg8b to do that.
   Currently we use lock xaddl and movl, which seems the fastest.

5. Does not use the lock prefix for atomic64_set
   64-bit writes are already atomic, so we don't need that.
   We still need it for atomic64_read to avoid restoring a value
   changed in the meantime.

6. Allocates registers as well or better than gcc

The 386 implementation provides support for 386 and 486 machines.
386/486 SMP is not supported (we dropped it), but such support can be
added easily if desired.

A pure assembly implementation is required due to the custom calling
conventions, and desire to use %ebp in atomic64_add_return (we need
7 registers...), as well as the ability to use pushf/popf in the 386
code without an intermediate pop/push.

The parameter names are changed to match the convention in atomic_64.h

Changes in v3 (due to rebasing to tip/x86/asm):
- Patches atomic64_32.h instead of atomic_32.h
- Uses the CALL alternative mechanism from commit
  1b1d9258181bae199dc940f4bd0298126b9a73d9

Changes in v2:
- Merged 386 and cx8 support in the same patch
- 386 support now done in assembly, C code no longer used at all
- cmpxchg64 is used for atomic64_cmpxchg
- stop using macros, use one-line inline functions instead
- miscellanous changes and improvements

Signed-off-by: Luca Barbieri <luca@luca-barbieri.com>
LKML-Reference: <1267005265-27958-5-git-send-email-luca@luca-barbieri.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

1 files changed, 211 insertions, 67 deletions

diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index 03027bf28de..2a934aa19a4 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -14,109 +14,193 @@ typedef struct {
 
 #define ATOMIC64_INIT(val)	{ (val) }
 
-extern u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old_val, u64 new_val);
+#ifdef CONFIG_X86_CMPXCHG64
+#define ATOMIC64_ALTERNATIVE_(f, g) "call atomic64_" #g "_cx8"
+#else
+#define ATOMIC64_ALTERNATIVE_(f, g) ALTERNATIVE("call atomic64_" #f "_386", "call atomic64_" #g "_cx8", X86_FEATURE_CX8)
+#endif
+
+#define ATOMIC64_ALTERNATIVE(f) ATOMIC64_ALTERNATIVE_(f, f)
+
+/**
+ * atomic64_cmpxchg - cmpxchg atomic64 variable
+ * @p: pointer to type atomic64_t
+ * @o: expected value
+ * @n: new value
+ *
+ * Atomically sets @v to @n if it was equal to @o and returns
+ * the old value.
+ */
+
+static inline long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n)
+{
+	return cmpxchg64(&v->counter, o, n);
+}
 
 /**
  * atomic64_xchg - xchg atomic64 variable
- * @ptr:      pointer to type atomic64_t
- * @new_val:  value to assign
+ * @v: pointer to type atomic64_t
+ * @n: value to assign
  *
- * Atomically xchgs the value of @ptr to @new_val and returns
+ * Atomically xchgs the value of @v to @n and returns
  * the old value.
  */
-extern u64 atomic64_xchg(atomic64_t *ptr, u64 new_val);
+static inline long long atomic64_xchg(atomic64_t *v, long long n)
+{
+	long long o;
+	unsigned high = (unsigned)(n >> 32);
+	unsigned low = (unsigned)n;
+	asm volatile(ATOMIC64_ALTERNATIVE(xchg)
+		     : "=A" (o), "+b" (low), "+c" (high)
+		     : "S" (v)
+		     : "memory"
+		     );
+	return o;
+}
 
 /**
  * atomic64_set - set atomic64 variable
- * @ptr:      pointer to type atomic64_t
- * @new_val:  value to assign
+ * @v: pointer to type atomic64_t
+ * @n: value to assign
  *
- * Atomically sets the value of @ptr to @new_val.
+ * Atomically sets the value of @v to @n.
  */
-extern void atomic64_set(atomic64_t *ptr, u64 new_val);
+static inline void atomic64_set(atomic64_t *v, long long i)
+{
+	unsigned high = (unsigned)(i >> 32);
+	unsigned low = (unsigned)i;
+	asm volatile(ATOMIC64_ALTERNATIVE(set)
+		     : "+b" (low), "+c" (high)
+		     : "S" (v)
+		     : "eax", "edx", "memory"
+		     );
+}
 
 /**
  * atomic64_read - read atomic64 variable
- * @ptr:      pointer to type atomic64_t
+ * @v: pointer to type atomic64_t
  *
- * Atomically reads the value of @ptr and returns it.
+ * Atomically reads the value of @v and returns it.
  */
-static inline u64 atomic64_read(atomic64_t *ptr)
+static inline long long atomic64_read(atomic64_t *v)
 {
-	u64 res;
-
-	/*
-	 * Note, we inline this atomic64_t primitive because
-	 * it only clobbers EAX/EDX and leaves the others
-	 * untouched. We also (somewhat subtly) rely on the
-	 * fact that cmpxchg8b returns the current 64-bit value
-	 * of the memory location we are touching:
-	 */
-	asm volatile(
-		"mov %%ebx, %%eax\n\t"
-		"mov %%ecx, %%edx\n\t"
-		LOCK_PREFIX "cmpxchg8b %1\n"
-			: "=&A" (res)
-			: "m" (*ptr)
-		);
-
-	return res;
-}
-
-extern u64 atomic64_read(atomic64_t *ptr);
+	long long r;
+	asm volatile(ATOMIC64_ALTERNATIVE(read)
+		     : "=A" (r), "+c" (v)
+		     : : "memory"
+		     );
+	return r;
+ }
 
 /**
  * atomic64_add_return - add and return
- * @delta: integer value to add
- * @ptr:   pointer to type atomic64_t
+ * @i: integer value to add
+ * @v: pointer to type atomic64_t
  *
- * Atomically adds @delta to @ptr and returns @delta + *@ptr
+ * Atomically adds @i to @v and returns @i + *@v
  */
-extern u64 atomic64_add_return(u64 delta, atomic64_t *ptr);
+static inline long long atomic64_add_return(long long i, atomic64_t *v)
+{
+	asm volatile(ATOMIC64_ALTERNATIVE(add_return)
+		     : "+A" (i), "+c" (v)
+		     : : "memory"
+		     );
+	return i;
+}
 
 /*
  * Other variants with different arithmetic operators:
  */
-extern u64 atomic64_sub_return(u64 delta, atomic64_t *ptr);
-extern u64 atomic64_inc_return(atomic64_t *ptr);
-extern u64 atomic64_dec_return(atomic64_t *ptr);
+static inline long long atomic64_sub_return(long long i, atomic64_t *v)
+{
+	asm volatile(ATOMIC64_ALTERNATIVE(sub_return)
+		     : "+A" (i), "+c" (v)
+		     : : "memory"
+		     );
+	return i;
+}
+
+static inline long long atomic64_inc_return(atomic64_t *v)
+{
+	long long a;
+	asm volatile(ATOMIC64_ALTERNATIVE(inc_return)
+		     : "=A" (a)
+		     : "S" (v)
+		     : "memory", "ecx"
+		     );
+	return a;
+}
+
+static inline long long atomic64_dec_return(atomic64_t *v)
+{
+	long long a;
+	asm volatile(ATOMIC64_ALTERNATIVE(dec_return)
+		     : "=A" (a)
+		     : "S" (v)
+		     : "memory", "ecx"
+		     );
+	return a;
+}
 
 /**
  * atomic64_add - add integer to atomic64 variable
- * @delta: integer value to add
- * @ptr:   pointer to type atomic64_t
+ * @i: integer value to add
+ * @v: pointer to type atomic64_t
  *
- * Atomically adds @delta to @ptr.
+ * Atomically adds @i to @v.
  */
-extern void atomic64_add(u64 delta, atomic64_t *ptr);
+static inline long long atomic64_add(long long i, atomic64_t *v)
+{
+	asm volatile(ATOMIC64_ALTERNATIVE_(add, add_return)
+		     : "+A" (i), "+c" (v)
+		     : : "memory"
+		     );
+	return i;
+}
 
 /**
  * atomic64_sub - subtract the atomic64 variable
- * @delta: integer value to subtract
- * @ptr:   pointer to type atomic64_t
+ * @i: integer value to subtract
+ * @v: pointer to type atomic64_t
  *
- * Atomically subtracts @delta from @ptr.
+ * Atomically subtracts @i from @v.
  */
-extern void atomic64_sub(u64 delta, atomic64_t *ptr);
+static inline long long atomic64_sub(long long i, atomic64_t *v)
+{
+	asm volatile(ATOMIC64_ALTERNATIVE_(sub, sub_return)
+		     : "+A" (i), "+c" (v)
+		     : : "memory"
+		     );
+	return i;
+}
 
 /**
  * atomic64_sub_and_test - subtract value from variable and test result
- * @delta: integer value to subtract
- * @ptr:   pointer to type atomic64_t
- *
- * Atomically subtracts @delta from @ptr and returns
+ * @i: integer value to subtract
+ * @v: pointer to type atomic64_t
+  *
+ * Atomically subtracts @i from @v and returns
  * true if the result is zero, or false for all
  * other cases.
  */
-extern int atomic64_sub_and_test(u64 delta, atomic64_t *ptr);
+static inline int atomic64_sub_and_test(long long i, atomic64_t *v)
+{
+	return atomic64_sub_return(i, v) == 0;
+}
 
 /**
  * atomic64_inc - increment atomic64 variable
- * @ptr: pointer to type atomic64_t
+ * @v: pointer to type atomic64_t
  *
- * Atomically increments @ptr by 1.
+ * Atomically increments @v by 1.
  */
-extern void atomic64_inc(atomic64_t *ptr);
+static inline void atomic64_inc(atomic64_t *v)
+{
+	asm volatile(ATOMIC64_ALTERNATIVE_(inc, inc_return)
+		     : : "S" (v)
+		     : "memory", "eax", "ecx", "edx"
+		     );
+}
 
 /**
  * atomic64_dec - decrement atomic64 variable
@@ -124,37 +208,97 @@ extern void atomic64_inc(atomic64_t *ptr);
  *
  * Atomically decrements @ptr by 1.
  */
-extern void atomic64_dec(atomic64_t *ptr);
+static inline void atomic64_dec(atomic64_t *v)
+{
+	asm volatile(ATOMIC64_ALTERNATIVE_(dec, dec_return)
+		     : : "S" (v)
+		     : "memory", "eax", "ecx", "edx"
+		     );
+}
 
 /**
  * atomic64_dec_and_test - decrement and test
- * @ptr: pointer to type atomic64_t
+ * @v: pointer to type atomic64_t
  *
- * Atomically decrements @ptr by 1 and
+ * Atomically decrements @v by 1 and
  * returns true if the result is 0, or false for all other
  * cases.
  */
-extern int atomic64_dec_and_test(atomic64_t *ptr);
+static inline int atomic64_dec_and_test(atomic64_t *v)
+{
+	return atomic64_dec_return(v) == 0;
+}
 
 /**
  * atomic64_inc_and_test - increment and test
- * @ptr: pointer to type atomic64_t
+ * @v: pointer to type atomic64_t
  *
- * Atomically increments @ptr by 1
+ * Atomically increments @v by 1
  * and returns true if the result is zero, or false for all
  * other cases.
  */
-extern int atomic64_inc_and_test(atomic64_t *ptr);
+static inline int atomic64_inc_and_test(atomic64_t *v)
+{
+	return atomic64_inc_return(v) == 0;
+}
 
 /**
  * atomic64_add_negative - add and test if negative
- * @delta: integer value to add
- * @ptr:   pointer to type atomic64_t
+ * @i: integer value to add
+ * @v: pointer to type atomic64_t
  *
- * Atomically adds @delta to @ptr and returns true
+ * Atomically adds @i to @v and returns true
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
-extern int atomic64_add_negative(u64 delta, atomic64_t *ptr);
+static inline int atomic64_add_negative(long long i, atomic64_t *v)
+{
+	return atomic64_add_return(i, v) < 0;
+}
+
+/**
+ * atomic64_add_unless - add unless the number is a given value
+ * @v: pointer of type atomic64_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, so long as it was not @u.
+ * Returns non-zero if @v was not @u, and zero otherwise.
+ */
+static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
+{
+	unsigned low = (unsigned)u;
+	unsigned high = (unsigned)(u >> 32);
+	asm volatile(ATOMIC64_ALTERNATIVE(add_unless) "\n\t"
+		     : "+A" (a), "+c" (v), "+S" (low), "+D" (high)
+		     : : "memory");
+	return (int)a;
+}
+
+
+static inline int atomic64_inc_not_zero(atomic64_t *v)
+{
+	int r;
+	asm volatile(ATOMIC64_ALTERNATIVE(inc_not_zero)
+		     : "=a" (r)
+		     : "S" (v)
+		     : "ecx", "edx", "memory"
+		     );
+	return r;
+}
+
+static inline long long atomic64_dec_if_positive(atomic64_t *v)
+{
+	long long r;
+	asm volatile(ATOMIC64_ALTERNATIVE(dec_if_positive)
+		     : "=A" (r)
+		     : "S" (v)
+		     : "ecx", "memory"
+		     );
+	return r;
+}
+
+#undef ATOMIC64_ALTERNATIVE
+#undef ATOMIC64_ALTERNATIVE_
 
 #endif /* _ASM_X86_ATOMIC64_32_H */