1 files changed, 148 insertions, 171 deletions

diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index 6a5b0ec460da..ab838205c1c6 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -9,11 +9,37 @@
 /* An 64bit atomic type */
 
 typedef struct {
-	u64 __aligned(8) counter;
+	s64 __aligned(8) counter;
 } atomic64_t;
 
 #define ATOMIC64_INIT(val)	{ (val) }
 
+/*
+ * Read an atomic64_t non-atomically.
+ *
+ * This is intended to be used in cases where a subsequent atomic operation
+ * will handle the torn value, and can be used to prime the first iteration
+ * of unconditional try_cmpxchg() loops, e.g.:
+ *
+ * 	s64 val = arch_atomic64_read_nonatomic(v);
+ * 	do { } while (!arch_atomic64_try_cmpxchg(v, &val, val OP i);
+ *
+ * This is NOT safe to use where the value is not always checked by a
+ * subsequent atomic operation, such as in conditional try_cmpxchg() loops
+ * that can break before the atomic operation, e.g.:
+ *
+ * 	s64 val = arch_atomic64_read_nonatomic(v);
+ * 	do {
+ * 		if (condition(val))
+ * 			break;
+ * 	} while (!arch_atomic64_try_cmpxchg(v, &val, val OP i);
+ */
+static __always_inline s64 arch_atomic64_read_nonatomic(const atomic64_t *v)
+{
+	/* See comment in arch_atomic_read(). */
+	return __READ_ONCE(v->counter);
+}
+
 #define __ATOMIC64_DECL(sym) void atomic64_##sym(atomic64_t *, ...)
 #ifndef ATOMIC64_EXPORT
 #define ATOMIC64_DECL_ONE __ATOMIC64_DECL
@@ -22,16 +48,20 @@ typedef struct {
 	ATOMIC64_EXPORT(atomic64_##sym)
 #endif
 
-#ifdef CONFIG_X86_CMPXCHG64
-#define __alternative_atomic64(f, g, out, in...) \
-	asm volatile("call %P[func]" \
-		     : out : [func] "i" (atomic64_##g##_cx8), ## in)
+#ifdef CONFIG_X86_CX8
+#define __alternative_atomic64(f, g, out, in, clobbers...)		\
+	asm volatile("call %c[func]"					\
+		     : ALT_OUTPUT_SP(out) \
+		     : [func] "i" (atomic64_##g##_cx8)			\
+		       COMMA(in)					\
+		     : clobbers)
 
 #define ATOMIC64_DECL(sym) ATOMIC64_DECL_ONE(sym##_cx8)
 #else
-#define __alternative_atomic64(f, g, out, in...) \
-	alternative_call(atomic64_##f##_386, atomic64_##g##_cx8, \
-			 X86_FEATURE_CX8, ASM_OUTPUT2(out), ## in)
+#define __alternative_atomic64(f, g, out, in, clobbers...)		\
+	alternative_call(atomic64_##f##_386, atomic64_##g##_cx8,	\
+			 X86_FEATURE_CX8, ASM_OUTPUT(out),		\
+			 ASM_INPUT(in), clobbers)
 
 #define ATOMIC64_DECL(sym) ATOMIC64_DECL_ONE(sym##_cx8); \
 	ATOMIC64_DECL_ONE(sym##_386)
@@ -42,8 +72,8 @@ ATOMIC64_DECL_ONE(inc_386);
 ATOMIC64_DECL_ONE(dec_386);
 #endif
 
-#define alternative_atomic64(f, out, in...) \
-	__alternative_atomic64(f, f, ASM_OUTPUT2(out), ## in)
+#define alternative_atomic64(f, out, in, clobbers...) \
+	__alternative_atomic64(f, f, ASM_OUTPUT(out), ASM_INPUT(in), clobbers)
 
 ATOMIC64_DECL(read);
 ATOMIC64_DECL(set);
@@ -61,204 +91,154 @@ ATOMIC64_DECL(add_unless);
 #undef __ATOMIC64_DECL
 #undef ATOMIC64_EXPORT
 
-/**
- * arch_atomic64_cmpxchg - cmpxchg atomic64 variable
- * @v: 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 __always_inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
+{
+	return arch_cmpxchg64(&v->counter, old, new);
+}
+#define arch_atomic64_cmpxchg arch_atomic64_cmpxchg
 
-static inline long long arch_atomic64_cmpxchg(atomic64_t *v, long long o,
-					      long long n)
+static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new)
 {
-	return arch_cmpxchg64(&v->counter, o, n);
+	return arch_try_cmpxchg64(&v->counter, old, new);
 }
+#define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg
 
-/**
- * arch_atomic64_xchg - xchg atomic64 variable
- * @v: pointer to type atomic64_t
- * @n: value to assign
- *
- * Atomically xchgs the value of @v to @n and returns
- * the old value.
- */
-static inline long long arch_atomic64_xchg(atomic64_t *v, long long n)
+static __always_inline s64 arch_atomic64_xchg(atomic64_t *v, s64 n)
 {
-	long long o;
+	s64 o;
 	unsigned high = (unsigned)(n >> 32);
 	unsigned low = (unsigned)n;
-	alternative_atomic64(xchg, "=&A" (o),
-			     "S" (v), "b" (low), "c" (high)
-			     : "memory");
+	alternative_atomic64(xchg,
+			     "=&A" (o),
+			     ASM_INPUT("S" (v), "b" (low), "c" (high)),
+			     "memory");
 	return o;
 }
+#define arch_atomic64_xchg arch_atomic64_xchg
 
-/**
- * arch_atomic64_set - set atomic64 variable
- * @v: pointer to type atomic64_t
- * @i: value to assign
- *
- * Atomically sets the value of @v to @n.
- */
-static inline void arch_atomic64_set(atomic64_t *v, long long i)
+static __always_inline void arch_atomic64_set(atomic64_t *v, s64 i)
 {
 	unsigned high = (unsigned)(i >> 32);
 	unsigned low = (unsigned)i;
-	alternative_atomic64(set, /* no output */,
-			     "S" (v), "b" (low), "c" (high)
-			     : "eax", "edx", "memory");
+	alternative_atomic64(set,
+			     /* no output */,
+			     ASM_INPUT("S" (v), "b" (low), "c" (high)),
+			     "eax", "edx", "memory");
 }
 
-/**
- * arch_atomic64_read - read atomic64 variable
- * @v: pointer to type atomic64_t
- *
- * Atomically reads the value of @v and returns it.
- */
-static inline long long arch_atomic64_read(const atomic64_t *v)
+static __always_inline s64 arch_atomic64_read(const atomic64_t *v)
 {
-	long long r;
-	alternative_atomic64(read, "=&A" (r), "c" (v) : "memory");
+	s64 r;
+	alternative_atomic64(read, "=&A" (r), "c" (v), "memory");
 	return r;
 }
 
-/**
- * arch_atomic64_add_return - add and return
- * @i: integer value to add
- * @v: pointer to type atomic64_t
- *
- * Atomically adds @i to @v and returns @i + *@v
- */
-static inline long long arch_atomic64_add_return(long long i, atomic64_t *v)
+static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v)
 {
 	alternative_atomic64(add_return,
-			     ASM_OUTPUT2("+A" (i), "+c" (v)),
-			     ASM_NO_INPUT_CLOBBER("memory"));
+			     ASM_OUTPUT("+A" (i), "+c" (v)),
+			     /* no input */,
+			     "memory");
 	return i;
 }
+#define arch_atomic64_add_return arch_atomic64_add_return
 
-/*
- * Other variants with different arithmetic operators:
- */
-static inline long long arch_atomic64_sub_return(long long i, atomic64_t *v)
+static __always_inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v)
 {
 	alternative_atomic64(sub_return,
-			     ASM_OUTPUT2("+A" (i), "+c" (v)),
-			     ASM_NO_INPUT_CLOBBER("memory"));
+			     ASM_OUTPUT("+A" (i), "+c" (v)),
+			     /* no input */,
+			     "memory");
 	return i;
 }
+#define arch_atomic64_sub_return arch_atomic64_sub_return
 
-static inline long long arch_atomic64_inc_return(atomic64_t *v)
+static __always_inline s64 arch_atomic64_inc_return(atomic64_t *v)
 {
-	long long a;
-	alternative_atomic64(inc_return, "=&A" (a),
-			     "S" (v) : "memory", "ecx");
+	s64 a;
+	alternative_atomic64(inc_return,
+			     "=&A" (a),
+			     "S" (v),
+			     "memory", "ecx");
 	return a;
 }
 #define arch_atomic64_inc_return arch_atomic64_inc_return
 
-static inline long long arch_atomic64_dec_return(atomic64_t *v)
+static __always_inline s64 arch_atomic64_dec_return(atomic64_t *v)
 {
-	long long a;
-	alternative_atomic64(dec_return, "=&A" (a),
-			     "S" (v) : "memory", "ecx");
+	s64 a;
+	alternative_atomic64(dec_return,
+			     "=&A" (a),
+			     "S" (v),
+			     "memory", "ecx");
 	return a;
 }
 #define arch_atomic64_dec_return arch_atomic64_dec_return
 
-/**
- * arch_atomic64_add - add integer to atomic64 variable
- * @i: integer value to add
- * @v: pointer to type atomic64_t
- *
- * Atomically adds @i to @v.
- */
-static inline long long arch_atomic64_add(long long i, atomic64_t *v)
+static __always_inline void arch_atomic64_add(s64 i, atomic64_t *v)
 {
 	__alternative_atomic64(add, add_return,
-			       ASM_OUTPUT2("+A" (i), "+c" (v)),
-			       ASM_NO_INPUT_CLOBBER("memory"));
-	return i;
+			       ASM_OUTPUT("+A" (i), "+c" (v)),
+			       /* no input */,
+			       "memory");
 }
 
-/**
- * arch_atomic64_sub - subtract the atomic64 variable
- * @i: integer value to subtract
- * @v: pointer to type atomic64_t
- *
- * Atomically subtracts @i from @v.
- */
-static inline long long arch_atomic64_sub(long long i, atomic64_t *v)
+static __always_inline void arch_atomic64_sub(s64 i, atomic64_t *v)
 {
 	__alternative_atomic64(sub, sub_return,
-			       ASM_OUTPUT2("+A" (i), "+c" (v)),
-			       ASM_NO_INPUT_CLOBBER("memory"));
-	return i;
+			       ASM_OUTPUT("+A" (i), "+c" (v)),
+			       /* no input */,
+			       "memory");
 }
 
-/**
- * arch_atomic64_inc - increment atomic64 variable
- * @v: pointer to type atomic64_t
- *
- * Atomically increments @v by 1.
- */
-static inline void arch_atomic64_inc(atomic64_t *v)
+static __always_inline void arch_atomic64_inc(atomic64_t *v)
 {
-	__alternative_atomic64(inc, inc_return, /* no output */,
-			       "S" (v) : "memory", "eax", "ecx", "edx");
+	__alternative_atomic64(inc, inc_return,
+			       /* no output */,
+			       "S" (v),
+			       "memory", "eax", "ecx", "edx");
 }
 #define arch_atomic64_inc arch_atomic64_inc
 
-/**
- * arch_atomic64_dec - decrement atomic64 variable
- * @v: pointer to type atomic64_t
- *
- * Atomically decrements @v by 1.
- */
-static inline void arch_atomic64_dec(atomic64_t *v)
+static __always_inline void arch_atomic64_dec(atomic64_t *v)
 {
-	__alternative_atomic64(dec, dec_return, /* no output */,
-			       "S" (v) : "memory", "eax", "ecx", "edx");
+	__alternative_atomic64(dec, dec_return,
+			       /* no output */,
+			       "S" (v),
+			       "memory", "eax", "ecx", "edx");
 }
 #define arch_atomic64_dec arch_atomic64_dec
 
-/**
- * arch_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 the add was done, zero otherwise.
- */
-static inline int arch_atomic64_add_unless(atomic64_t *v, long long a,
-					   long long u)
+static __always_inline int arch_atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
 {
 	unsigned low = (unsigned)u;
 	unsigned high = (unsigned)(u >> 32);
 	alternative_atomic64(add_unless,
-			     ASM_OUTPUT2("+A" (a), "+c" (low), "+D" (high)),
-			     "S" (v) : "memory");
+			     ASM_OUTPUT("+A" (a), "+c" (low), "+D" (high)),
+			     "S" (v),
+			     "memory");
 	return (int)a;
 }
+#define arch_atomic64_add_unless arch_atomic64_add_unless
 
-static inline int arch_atomic64_inc_not_zero(atomic64_t *v)
+static __always_inline int arch_atomic64_inc_not_zero(atomic64_t *v)
 {
 	int r;
-	alternative_atomic64(inc_not_zero, "=&a" (r),
-			     "S" (v) : "ecx", "edx", "memory");
+	alternative_atomic64(inc_not_zero,
+			     "=&a" (r),
+			     "S" (v),
+			     "ecx", "edx", "memory");
 	return r;
 }
 #define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero
 
-static inline long long arch_atomic64_dec_if_positive(atomic64_t *v)
+static __always_inline s64 arch_atomic64_dec_if_positive(atomic64_t *v)
 {
-	long long r;
-	alternative_atomic64(dec_if_positive, "=&A" (r),
-			     "S" (v) : "ecx", "memory");
+	s64 r;
+	alternative_atomic64(dec_if_positive,
+			     "=&A" (r),
+			     "S" (v),
+			     "ecx", "memory");
 	return r;
 }
 #define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive
@@ -266,69 +246,66 @@ static inline long long arch_atomic64_dec_if_positive(atomic64_t *v)
 #undef alternative_atomic64
 #undef __alternative_atomic64
 
-static inline void arch_atomic64_and(long long i, atomic64_t *v)
+static __always_inline void arch_atomic64_and(s64 i, atomic64_t *v)
 {
-	long long old, c = 0;
+	s64 val = arch_atomic64_read_nonatomic(v);
 
-	while ((old = arch_atomic64_cmpxchg(v, c, c & i)) != c)
-		c = old;
+	do { } while (!arch_atomic64_try_cmpxchg(v, &val, val & i));
 }
 
-static inline long long arch_atomic64_fetch_and(long long i, atomic64_t *v)
+static __always_inline s64 arch_atomic64_fetch_and(s64 i, atomic64_t *v)
 {
-	long long old, c = 0;
+	s64 val = arch_atomic64_read_nonatomic(v);
 
-	while ((old = arch_atomic64_cmpxchg(v, c, c & i)) != c)
-		c = old;
+	do { } while (!arch_atomic64_try_cmpxchg(v, &val, val & i));
 
-	return old;
+	return val;
 }
+#define arch_atomic64_fetch_and arch_atomic64_fetch_and
 
-static inline void arch_atomic64_or(long long i, atomic64_t *v)
+static __always_inline void arch_atomic64_or(s64 i, atomic64_t *v)
 {
-	long long old, c = 0;
+	s64 val = arch_atomic64_read_nonatomic(v);
 
-	while ((old = arch_atomic64_cmpxchg(v, c, c | i)) != c)
-		c = old;
+	do { } while (!arch_atomic64_try_cmpxchg(v, &val, val | i));
 }
 
-static inline long long arch_atomic64_fetch_or(long long i, atomic64_t *v)
+static __always_inline s64 arch_atomic64_fetch_or(s64 i, atomic64_t *v)
 {
-	long long old, c = 0;
+	s64 val = arch_atomic64_read_nonatomic(v);
 
-	while ((old = arch_atomic64_cmpxchg(v, c, c | i)) != c)
-		c = old;
+	do { } while (!arch_atomic64_try_cmpxchg(v, &val, val | i));
 
-	return old;
+	return val;
 }
+#define arch_atomic64_fetch_or arch_atomic64_fetch_or
 
-static inline void arch_atomic64_xor(long long i, atomic64_t *v)
+static __always_inline void arch_atomic64_xor(s64 i, atomic64_t *v)
 {
-	long long old, c = 0;
+	s64 val = arch_atomic64_read_nonatomic(v);
 
-	while ((old = arch_atomic64_cmpxchg(v, c, c ^ i)) != c)
-		c = old;
+	do { } while (!arch_atomic64_try_cmpxchg(v, &val, val ^ i));
 }
 
-static inline long long arch_atomic64_fetch_xor(long long i, atomic64_t *v)
+static __always_inline s64 arch_atomic64_fetch_xor(s64 i, atomic64_t *v)
 {
-	long long old, c = 0;
+	s64 val = arch_atomic64_read_nonatomic(v);
 
-	while ((old = arch_atomic64_cmpxchg(v, c, c ^ i)) != c)
-		c = old;
+	do { } while (!arch_atomic64_try_cmpxchg(v, &val, val ^ i));
 
-	return old;
+	return val;
 }
+#define arch_atomic64_fetch_xor arch_atomic64_fetch_xor
 
-static inline long long arch_atomic64_fetch_add(long long i, atomic64_t *v)
+static __always_inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v)
 {
-	long long old, c = 0;
+	s64 val = arch_atomic64_read_nonatomic(v);
 
-	while ((old = arch_atomic64_cmpxchg(v, c, c + i)) != c)
-		c = old;
+	do { } while (!arch_atomic64_try_cmpxchg(v, &val, val + i));
 
-	return old;
+	return val;
 }
+#define arch_atomic64_fetch_add arch_atomic64_fetch_add
 
 #define arch_atomic64_fetch_sub(i, v)	arch_atomic64_fetch_add(-(i), (v))