[PATCH 00/10] local_t : adding and standardising local atomic primitives

[PATCH 00/10] local_t : adding and standardising local atomic primitives

[Mathieu Desnoyers]

local_t : adding and standardising local atomic primitives

These patches extend and standardise local_t operations on each architectures,
allowing a rich set of atomic operations to be done on per-cpu data with
minimal performance impact. On architectures where there seems to be no
difference between the SMP and UP operation (same memory barriers, same
LOCKing), local.h simply includes asm-generic/local.h, which removes duplicated
code from the current kernel tree.

These patches apply on 2.6.20.
It depends on the patch "atomic.h : standardising atomic primitives"

These patches compile fine against :

arm
i686
ia64
m68k
mips
mipsel
x86_64
ppc 405
powerpc 970
s390
sparc
sparc64

Signed-off-by : Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

[PATCH 01/10] local_t : architecture independant extension

[Mathieu Desnoyers]

local_t : architecture independant extension

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

--- a/include/asm-generic/local.h
+++ b/include/asm-generic/local.h
@@ -33,6 +33,19 @@ typedef struct
 #define local_add(i,l)	atomic_long_add((i),(&(l)->a))
 #define local_sub(i,l)	atomic_long_sub((i),(&(l)->a))
 
+#define local_sub_and_test(i, l) atomic_long_sub_and_test((i), (&(l)->a))
+#define local_dec_and_test(l) atomic_long_dec_and_test(&(l)->a)
+#define local_inc_and_test(l) atomic_long_inc_and_test(&(l)->a)
+#define local_add_negative(i, l) atomic_long_add_negative((i), (&(l)->a))
+#define local_add_return(i, l) atomic_long_add_return((i), (&(l)->a))
+#define local_sub_return(i, l) atomic_long_sub_return((i), (&(l)->a))
+#define local_inc_return(l) atomic_long_inc_return(&(l)->a)
+
+#define local_cmpxchg(l, o, n) atomic_long_cmpxchg((&(l)->a), (o), (n))
+#define local_xchg(l, n) atomic_long_xchg((&(l)->a), (n))
+#define local_add_unless(l, a, u) atomic_long_add_unless((&(l)->a), (a), (u))
+#define local_inc_not_zero(l) atomic_long_inc_not_zero(&(l)->a)
+
 /* Non-atomic variants, ie. preemption disabled and won't be touched
  * in interrupt, etc.  Some archs can optimize this case well. */
 #define __local_inc(l)		local_set((l), local_read(l) + 1)
@@ -44,19 +57,19 @@ typedef struct
  * much more efficient than these naive implementations.  Note they take
  * a variable (eg. mystruct.foo), not an address.
  */
-#define cpu_local_read(v)	local_read(&__get_cpu_var(v))
-#define cpu_local_set(v, i)	local_set(&__get_cpu_var(v), (i))
-#define cpu_local_inc(v)	local_inc(&__get_cpu_var(v))
-#define cpu_local_dec(v)	local_dec(&__get_cpu_var(v))
-#define cpu_local_add(i, v)	local_add((i), &__get_cpu_var(v))
-#define cpu_local_sub(i, v)	local_sub((i), &__get_cpu_var(v))
+#define cpu_local_read(l)	local_read(&__get_cpu_var(l))
+#define cpu_local_set(l, i)	local_set(&__get_cpu_var(l), (i))
+#define cpu_local_inc(l)	local_inc(&__get_cpu_var(l))
+#define cpu_local_dec(l)	local_dec(&__get_cpu_var(l))
+#define cpu_local_add(i, l)	local_add((i), &__get_cpu_var(l))
+#define cpu_local_sub(i, l)	local_sub((i), &__get_cpu_var(l))
 
 /* Non-atomic increments, ie. preemption disabled and won't be touched
  * in interrupt, etc.  Some archs can optimize this case well.
  */
-#define __cpu_local_inc(v)	__local_inc(&__get_cpu_var(v))
-#define __cpu_local_dec(v)	__local_dec(&__get_cpu_var(v))
-#define __cpu_local_add(i, v)	__local_add((i), &__get_cpu_var(v))
-#define __cpu_local_sub(i, v)	__local_sub((i), &__get_cpu_var(v))
+#define __cpu_local_inc(l)	__local_inc(&__get_cpu_var(l))
+#define __cpu_local_dec(l)	__local_dec(&__get_cpu_var(l))
+#define __cpu_local_add(i, l)	__local_add((i), &__get_cpu_var(l))
+#define __cpu_local_sub(i, l)	__local_sub((i), &__get_cpu_var(l))
 
 #endif /* _ASM_GENERIC_LOCAL_H */

[PATCH 02/10] local_t : alpha extension

[Mathieu Desnoyers]

local_t : alpha extension

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

--- a/include/asm-alpha/local.h
+++ b/include/asm-alpha/local.h
@@ -4,37 +4,115 @@
 #include <linux/percpu.h>
 #include <asm/atomic.h>
 
-typedef atomic64_t local_t;
+typedef struct
+{
+	atomic_long_t a;
+} local_t;
 
-#define LOCAL_INIT(i)	ATOMIC64_INIT(i)
-#define local_read(v)	atomic64_read(v)
-#define local_set(v,i)	atomic64_set(v,i)
+#define LOCAL_INIT(i)	{ ATOMIC_LONG_INIT(i) }
+#define local_read(l)	atomic_long_read(&(l)->a)
+#define local_set(l,i)	atomic_long_set(&(l)->a, (i))
+#define local_inc(l)	atomic_long_inc(&(l)->a)
+#define local_dec(l)	atomic_long_dec(&(l)->a)
+#define local_add(i,l)	atomic_long_add((i),(&(l)->a))
+#define local_sub(i,l)	atomic_long_sub((i),(&(l)->a))
 
-#define local_inc(v)	atomic64_inc(v)
-#define local_dec(v)	atomic64_dec(v)
-#define local_add(i, v)	atomic64_add(i, v)
-#define local_sub(i, v)	atomic64_sub(i, v)
+static __inline__ long local_add_return(long i, local_t * l)
+{
+	long temp, result;
+	__asm__ __volatile__(
+	"1:	ldq_l %0,%1\n"
+	"	addq %0,%3,%2\n"
+	"	addq %0,%3,%0\n"
+	"	stq_c %0,%1\n"
+	"	beq %0,2f\n"
+	".subsection 2\n"
+	"2:	br 1b\n"
+	".previous"
+	:"=&r" (temp), "=m" (l->a.counter), "=&r" (result)
+	:"Ir" (i), "m" (l->a.counter) : "memory");
+	return result;
+}
 
-#define __local_inc(v)		((v)->counter++)
-#define __local_dec(v)		((v)->counter++)
-#define __local_add(i,v)	((v)->counter+=(i))
-#define __local_sub(i,v)	((v)->counter-=(i))
+static __inline__ long local_sub_return(long i, local_t * l)
+{
+	long temp, result;
+	__asm__ __volatile__(
+	"1:	ldq_l %0,%1\n"
+	"	subq %0,%3,%2\n"
+	"	subq %0,%3,%0\n"
+	"	stq_c %0,%1\n"
+	"	beq %0,2f\n"
+	".subsection 2\n"
+	"2:	br 1b\n"
+	".previous"
+	:"=&r" (temp), "=m" (l->a.counter), "=&r" (result)
+	:"Ir" (i), "m" (l->a.counter) : "memory");
+	return result;
+}
+
+#define local_cmpxchg(l, o, n) \
+	(cmpxchg_local(&((l)->a.counter), (o), (n)))
+#define local_xchg(l, n) (xchg_local(&((l)->a.counter), (n)))
+
+/**
+ * local_add_unless - add unless the number is a given value
+ * @l: pointer of type local_t
+ * @a: the amount to add to l...
+ * @u: ...unless l is equal to u.
+ *
+ * Atomically adds @a to @l, so long as it was not @u.
+ * Returns non-zero if @l was not @u, and zero otherwise.
+ */
+#define local_add_unless(l, a, u)				\
+({								\
+	long c, old;						\
+	c = local_read(l);					\
+	for (;;) {						\
+		if (unlikely(c == (u)))				\
+			break;					\
+		old = local_cmpxchg((l), c, c + (a));	\
+		if (likely(old == c))				\
+			break;					\
+		c = old;					\
+	}							\
+	c != (u);						\
+})
+#define local_inc_not_zero(l) local_add_unless((l), 1, 0)
+
+#define local_add_negative(a, l) (local_add_return((a), (l)) < 0)
+
+#define local_dec_return(l) local_sub_return(1,(l))
+
+#define local_inc_return(l) local_add_return(1,(l))
+
+#define local_sub_and_test(i,l) (local_sub_return((i), (l)) == 0)
+
+#define local_inc_and_test(l) (local_add_return(1, (l)) == 0)
+
+#define local_dec_and_test(l) (local_sub_return(1, (l)) == 0)
+
+/* Verify if faster than atomic ops */
+#define __local_inc(l)		((l)->a.counter++)
+#define __local_dec(l)		((l)->a.counter++)
+#define __local_add(i,l)	((l)->a.counter+=(i))
+#define __local_sub(i,l)	((l)->a.counter-=(i))
 
 /* Use these for per-cpu local_t variables: on some archs they are
  * much more efficient than these naive implementations.  Note they take
  * a variable, not an address.
  */
-#define cpu_local_read(v)	local_read(&__get_cpu_var(v))
-#define cpu_local_set(v, i)	local_set(&__get_cpu_var(v), (i))
-
-#define cpu_local_inc(v)	local_inc(&__get_cpu_var(v))
-#define cpu_local_dec(v)	local_dec(&__get_cpu_var(v))
-#define cpu_local_add(i, v)	local_add((i), &__get_cpu_var(v))
-#define cpu_local_sub(i, v)	local_sub((i), &__get_cpu_var(v))
-
-#define __cpu_local_inc(v)	__local_inc(&__get_cpu_var(v))
-#define __cpu_local_dec(v)	__local_dec(&__get_cpu_var(v))
-#define __cpu_local_add(i, v)	__local_add((i), &__get_cpu_var(v))
-#define __cpu_local_sub(i, v)	__local_sub((i), &__get_cpu_var(v))
+#define cpu_local_read(l)	local_read(&__get_cpu_var(l))
+#define cpu_local_set(l, i)	local_set(&__get_cpu_var(l), (i))
+
+#define cpu_local_inc(l)	local_inc(&__get_cpu_var(l))
+#define cpu_local_dec(l)	local_dec(&__get_cpu_var(l))
+#define cpu_local_add(i, l)	local_add((i), &__get_cpu_var(l))
+#define cpu_local_sub(i, l)	local_sub((i), &__get_cpu_var(l))
+
+#define __cpu_local_inc(l)	__local_inc(&__get_cpu_var(l))
+#define __cpu_local_dec(l)	__local_dec(&__get_cpu_var(l))
+#define __cpu_local_add(i, l)	__local_add((i), &__get_cpu_var(l))
+#define __cpu_local_sub(i, l)	__local_sub((i), &__get_cpu_var(l))
 
 #endif /* _ALPHA_LOCAL_H */
--- a/include/asm-alpha/system.h
+++ b/include/asm-alpha/system.h
@@ -443,6 +443,111 @@ extern void __xchg_called_with_bad_pointer(void);
      (__typeof__(*(ptr))) __xchg((ptr), (unsigned long)_x_, sizeof(*(ptr))); \
   })
 
+static inline unsigned long
+__xchg_u8_local(volatile char *m, unsigned long val)
+{
+	unsigned long ret, tmp, addr64;
+
+	__asm__ __volatile__(
+	"	andnot	%4,7,%3\n"
+	"	insbl	%1,%4,%1\n"
+	"1:	ldq_l	%2,0(%3)\n"
+	"	extbl	%2,%4,%0\n"
+	"	mskbl	%2,%4,%2\n"
+	"	or	%1,%2,%2\n"
+	"	stq_c	%2,0(%3)\n"
+	"	beq	%2,2f\n"
+	".subsection 2\n"
+	"2:	br	1b\n"
+	".previous"
+	: "=&r" (ret), "=&r" (val), "=&r" (tmp), "=&r" (addr64)
+	: "r" ((long)m), "1" (val) : "memory");
+
+	return ret;
+}
+
+static inline unsigned long
+__xchg_u16_local(volatile short *m, unsigned long val)
+{
+	unsigned long ret, tmp, addr64;
+
+	__asm__ __volatile__(
+	"	andnot	%4,7,%3\n"
+	"	inswl	%1,%4,%1\n"
+	"1:	ldq_l	%2,0(%3)\n"
+	"	extwl	%2,%4,%0\n"
+	"	mskwl	%2,%4,%2\n"
+	"	or	%1,%2,%2\n"
+	"	stq_c	%2,0(%3)\n"
+	"	beq	%2,2f\n"
+	".subsection 2\n"
+	"2:	br	1b\n"
+	".previous"
+	: "=&r" (ret), "=&r" (val), "=&r" (tmp), "=&r" (addr64)
+	: "r" ((long)m), "1" (val) : "memory");
+
+	return ret;
+}
+
+static inline unsigned long
+__xchg_u32_local(volatile int *m, unsigned long val)
+{
+	unsigned long dummy;
+
+	__asm__ __volatile__(
+	"1:	ldl_l %0,%4\n"
+	"	bis $31,%3,%1\n"
+	"	stl_c %1,%2\n"
+	"	beq %1,2f\n"
+	".subsection 2\n"
+	"2:	br 1b\n"
+	".previous"
+	: "=&r" (val), "=&r" (dummy), "=m" (*m)
+	: "rI" (val), "m" (*m) : "memory");
+
+	return val;
+}
+
+static inline unsigned long
+__xchg_u64_local(volatile long *m, unsigned long val)
+{
+	unsigned long dummy;
+
+	__asm__ __volatile__(
+	"1:	ldq_l %0,%4\n"
+	"	bis $31,%3,%1\n"
+	"	stq_c %1,%2\n"
+	"	beq %1,2f\n"
+	".subsection 2\n"
+	"2:	br 1b\n"
+	".previous"
+	: "=&r" (val), "=&r" (dummy), "=m" (*m)
+	: "rI" (val), "m" (*m) : "memory");
+
+	return val;
+}
+
+#define __xchg_local(ptr, x, size) \
+({ \
+	unsigned long __xchg__res; \
+	volatile void *__xchg__ptr = (ptr); \
+	switch (size) { \
+		case 1: __xchg__res = __xchg_u8_local(__xchg__ptr, x); break; \
+		case 2: __xchg__res = __xchg_u16_local(__xchg__ptr, x); break; \
+		case 4: __xchg__res = __xchg_u32_local(__xchg__ptr, x); break; \
+		case 8: __xchg__res = __xchg_u64_local(__xchg__ptr, x); break; \
+		default: __xchg_called_with_bad_pointer(); __xchg__res = x; \
+	} \
+	__xchg__res; \
+})
+
+#define xchg_local(ptr,x)						     \
+  ({									     \
+     __typeof__(*(ptr)) _x_ = (x);					     \
+     (__typeof__(*(ptr))) __xchg_local((ptr), (unsigned long)_x_,	     \
+     		sizeof(*(ptr))); \
+  })
+
 #define tas(ptr) (xchg((ptr),1))
 
 
@@ -596,6 +701,128 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size)
 				    (unsigned long)_n_, sizeof(*(ptr))); \
   })
 
+static inline unsigned long
+__cmpxchg_u8_local(volatile char *m, long old, long new)
+{
+	unsigned long prev, tmp, cmp, addr64;
+
+	__asm__ __volatile__(
+	"	andnot	%5,7,%4\n"
+	"	insbl	%1,%5,%1\n"
+	"1:	ldq_l	%2,0(%4)\n"
+	"	extbl	%2,%5,%0\n"
+	"	cmpeq	%0,%6,%3\n"
+	"	beq	%3,2f\n"
+	"	mskbl	%2,%5,%2\n"
+	"	or	%1,%2,%2\n"
+	"	stq_c	%2,0(%4)\n"
+	"	beq	%2,3f\n"
+	"2:\n"
+	".subsection 2\n"
+	"3:	br	1b\n"
+	".previous"
+	: "=&r" (prev), "=&r" (new), "=&r" (tmp), "=&r" (cmp), "=&r" (addr64)
+	: "r" ((long)m), "Ir" (old), "1" (new) : "memory");
+
+	return prev;
+}
+
+static inline unsigned long
+__cmpxchg_u16_local(volatile short *m, long old, long new)
+{
+	unsigned long prev, tmp, cmp, addr64;
+
+	__asm__ __volatile__(
+	"	andnot	%5,7,%4\n"
+	"	inswl	%1,%5,%1\n"
+	"1:	ldq_l	%2,0(%4)\n"
+	"	extwl	%2,%5,%0\n"
+	"	cmpeq	%0,%6,%3\n"
+	"	beq	%3,2f\n"
+	"	mskwl	%2,%5,%2\n"
+	"	or	%1,%2,%2\n"
+	"	stq_c	%2,0(%4)\n"
+	"	beq	%2,3f\n"
+	"2:\n"
+	".subsection 2\n"
+	"3:	br	1b\n"
+	".previous"
+	: "=&r" (prev), "=&r" (new), "=&r" (tmp), "=&r" (cmp), "=&r" (addr64)
+	: "r" ((long)m), "Ir" (old), "1" (new) : "memory");
+
+	return prev;
+}
+
+static inline unsigned long
+__cmpxchg_u32_local(volatile int *m, int old, int new)
+{
+	unsigned long prev, cmp;
+
+	__asm__ __volatile__(
+	"1:	ldl_l %0,%5\n"
+	"	cmpeq %0,%3,%1\n"
+	"	beq %1,2f\n"
+	"	mov %4,%1\n"
+	"	stl_c %1,%2\n"
+	"	beq %1,3f\n"
+	"2:\n"
+	".subsection 2\n"
+	"3:	br 1b\n"
+	".previous"
+	: "=&r"(prev), "=&r"(cmp), "=m"(*m)
+	: "r"((long) old), "r"(new), "m"(*m) : "memory");
+
+	return prev;
+}
+
+static inline unsigned long
+__cmpxchg_u64_local(volatile long *m, unsigned long old, unsigned long new)
+{
+	unsigned long prev, cmp;
+
+	__asm__ __volatile__(
+	"1:	ldq_l %0,%5\n"
+	"	cmpeq %0,%3,%1\n"
+	"	beq %1,2f\n"
+	"	mov %4,%1\n"
+	"	stq_c %1,%2\n"
+	"	beq %1,3f\n"
+	"2:\n"
+	".subsection 2\n"
+	"3:	br 1b\n"
+	".previous"
+	: "=&r"(prev), "=&r"(cmp), "=m"(*m)
+	: "r"((long) old), "r"(new), "m"(*m) : "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_local(volatile void *ptr, unsigned long old, unsigned long new,
+		int size)
+{
+	switch (size) {
+		case 1:
+			return __cmpxchg_u8_local(ptr, old, new);
+		case 2:
+			return __cmpxchg_u16_local(ptr, old, new);
+		case 4:
+			return __cmpxchg_u32_local(ptr, old, new);
+		case 8:
+			return __cmpxchg_u64_local(ptr, old, new);
+	}
+	__cmpxchg_called_with_bad_pointer();
+	return old;
+}
+
+#define cmpxchg_local(ptr,o,n)						 \
+  ({									 \
+     __typeof__(*(ptr)) _o_ = (o);					 \
+     __typeof__(*(ptr)) _n_ = (n);					 \
+     (__typeof__(*(ptr))) __cmpxchg_local((ptr), (unsigned long)_o_,	 \
+				    (unsigned long)_n_, sizeof(*(ptr))); \
+  })
+
 #endif /* __ASSEMBLY__ */
 
 #define arch_align_stack(x) (x)

[PATCH 03/10] local_t : i386 extension

[Mathieu Desnoyers]

local_t : i386 extension

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

--- a/include/asm-i386/local.h
+++ b/include/asm-i386/local.h
@@ -2,47 +2,198 @@
 #define _ARCH_I386_LOCAL_H
 
 #include <linux/percpu.h>
+#include <asm/system.h>
+#include <asm/atomic.h>
 
 typedef struct
 {
-	volatile long counter;
+	atomic_long_t a;
 } local_t;
 
-#define LOCAL_INIT(i)	{ (i) }
+#define LOCAL_INIT(i)	{ ATOMIC_LONG_INIT(i) }
 
-#define local_read(v)	((v)->counter)
-#define local_set(v,i)	(((v)->counter) = (i))
+#define local_read(l)	atomic_long_read(&(l)->a)
+#define local_set(l,i)	atomic_long_set(&(l)->a, (i))
 
-static __inline__ void local_inc(local_t *v)
+static __inline__ void local_inc(local_t *l)
 {
 	__asm__ __volatile__(
 		"incl %0"
-		:"+m" (v->counter));
+		:"+m" (l->a.counter));
 }
 
-static __inline__ void local_dec(local_t *v)
+static __inline__ void local_dec(local_t *l)
 {
 	__asm__ __volatile__(
 		"decl %0"
-		:"+m" (v->counter));
+		:"+m" (l->a.counter));
 }
 
-static __inline__ void local_add(long i, local_t *v)
+static __inline__ void local_add(long i, local_t *l)
 {
 	__asm__ __volatile__(
 		"addl %1,%0"
-		:"+m" (v->counter)
+		:"+m" (l->a.counter)
 		:"ir" (i));
 }
 
-static __inline__ void local_sub(long i, local_t *v)
+static __inline__ void local_sub(long i, local_t *l)
 {
 	__asm__ __volatile__(
 		"subl %1,%0"
-		:"+m" (v->counter)
+		:"+m" (l->a.counter)
 		:"ir" (i));
 }
 
+/**
+ * local_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @l: pointer of type local_t
+ * 
+ * Atomically subtracts @i from @l and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+static __inline__ int local_sub_and_test(long i, local_t *l)
+{
+	unsigned char c;
+
+	__asm__ __volatile__(
+		"subl %2,%0; sete %1"
+		:"+m" (l->a.counter), "=qm" (c)
+		:"ir" (i) : "memory");
+	return c;
+}
+
+/**
+ * local_dec_and_test - decrement and test
+ * @l: pointer of type local_t
+ * 
+ * Atomically decrements @l by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */ 
+static __inline__ int local_dec_and_test(local_t *l)
+{
+	unsigned char c;
+
+	__asm__ __volatile__(
+		"decl %0; sete %1"
+		:"+m" (l->a.counter), "=qm" (c)
+		: : "memory");
+	return c != 0;
+}
+
+/**
+ * local_inc_and_test - increment and test 
+ * @l: pointer of type local_t
+ * 
+ * Atomically increments @l by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */ 
+static __inline__ int local_inc_and_test(local_t *l)
+{
+	unsigned char c;
+
+	__asm__ __volatile__(
+		"incl %0; sete %1"
+		:"+m" (l->a.counter), "=qm" (c)
+		: : "memory");
+	return c != 0;
+}
+
+/**
+ * local_add_negative - add and test if negative
+ * @l: pointer of type local_t
+ * @i: integer value to add
+ * 
+ * Atomically adds @i to @l and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
+ */ 
+static __inline__ int local_add_negative(long i, local_t *l)
+{
+	unsigned char c;
+
+	__asm__ __volatile__(
+		"addl %2,%0; sets %1"
+		:"+m" (l->a.counter), "=qm" (c)
+		:"ir" (i) : "memory");
+	return c;
+}
+
+/**
+ * local_add_return - add and return
+ * @l: pointer of type local_t
+ * @i: integer value to add
+ *
+ * Atomically adds @i to @l and returns @i + @l
+ */
+static __inline__ long local_add_return(long i, local_t *l)
+{
+	long __i;
+#ifdef CONFIG_M386
+	unsigned long flags;
+	if(unlikely(boot_cpu_data.x86==3))
+		goto no_xadd;
+#endif
+	/* Modern 486+ processor */
+	__i = i;
+	__asm__ __volatile__(
+		"xaddl %0, %1;"
+		:"+r" (i), "+m" (l->a.counter)
+		: : "memory");
+	return i + __i;
+
+#ifdef CONFIG_M386
+no_xadd: /* Legacy 386 processor */
+	local_irq_save(flags);
+	__i = local_read(l);
+	local_set(l, i + __i);
+	local_irq_restore(flags);
+	return i + __i;
+#endif
+}
+
+static __inline__ long local_sub_return(long i, local_t *l)
+{
+	return local_add_return(-i,l);
+}
+
+#define local_inc_return(l)  (local_add_return(1,l))
+#define local_dec_return(l)  (local_sub_return(1,l))
+
+#define local_cmpxchg(l, o, n) \
+	(cmpxchg_local(&((l)->a.counter), (o), (n)))
+/* Always has a lock prefix */
+#define local_xchg(l, n) (xchg(&((l)->a.counter), (n)))
+
+/**
+ * local_add_unless - add unless the number is a given value
+ * @l: pointer of type local_t
+ * @a: the amount to add to l...
+ * @u: ...unless l is equal to u.
+ *
+ * Atomically adds @a to @l, so long as it was not @u.
+ * Returns non-zero if @l was not @u, and zero otherwise.
+ */
+#define local_add_unless(l, a, u)				\
+({								\
+	long c, old;						\
+	c = local_read(l);					\
+	for (;;) {						\
+		if (unlikely(c == (u)))				\
+			break;					\
+		old = local_cmpxchg((l), c, c + (a));	\
+		if (likely(old == c))				\
+			break;					\
+		c = old;					\
+	}							\
+	c != (u);						\
+})
+#define local_inc_not_zero(l) local_add_unless((l), 1, 0)
+
 /* On x86, these are no better than the atomic variants. */
 #define __local_inc(l)		local_inc(l)
 #define __local_dec(l)		local_dec(l)
@@ -56,27 +207,27 @@ static __inline__ void local_sub(long i, local_t *v)
 
 /* Need to disable preemption for the cpu local counters otherwise we could
    still access a variable of a previous CPU in a non atomic way. */
-#define cpu_local_wrap_v(v)	 	\
+#define cpu_local_wrap_v(l)	 	\
 	({ local_t res__;		\
 	   preempt_disable(); 		\
-	   res__ = (v);			\
+	   res__ = (l);			\
 	   preempt_enable();		\
 	   res__; })
-#define cpu_local_wrap(v)		\
+#define cpu_local_wrap(l)		\
 	({ preempt_disable();		\
-	   v;				\
+	   l;				\
 	   preempt_enable(); })		\
 
-#define cpu_local_read(v)    cpu_local_wrap_v(local_read(&__get_cpu_var(v)))
-#define cpu_local_set(v, i)  cpu_local_wrap(local_set(&__get_cpu_var(v), (i)))
-#define cpu_local_inc(v)     cpu_local_wrap(local_inc(&__get_cpu_var(v)))
-#define cpu_local_dec(v)     cpu_local_wrap(local_dec(&__get_cpu_var(v)))
-#define cpu_local_add(i, v)  cpu_local_wrap(local_add((i), &__get_cpu_var(v)))
-#define cpu_local_sub(i, v)  cpu_local_wrap(local_sub((i), &__get_cpu_var(v)))
-
-#define __cpu_local_inc(v)	cpu_local_inc(v)
-#define __cpu_local_dec(v)	cpu_local_dec(v)
-#define __cpu_local_add(i, v)	cpu_local_add((i), (v))
-#define __cpu_local_sub(i, v)	cpu_local_sub((i), (v))
+#define cpu_local_read(l)    cpu_local_wrap_v(local_read(&__get_cpu_var(l)))
+#define cpu_local_set(l, i)  cpu_local_wrap(local_set(&__get_cpu_var(l), (i)))
+#define cpu_local_inc(l)     cpu_local_wrap(local_inc(&__get_cpu_var(l)))
+#define cpu_local_dec(l)     cpu_local_wrap(local_dec(&__get_cpu_var(l)))
+#define cpu_local_add(i, l)  cpu_local_wrap(local_add((i), &__get_cpu_var(l)))
+#define cpu_local_sub(i, l)  cpu_local_wrap(local_sub((i), &__get_cpu_var(l)))
+
+#define __cpu_local_inc(l)	cpu_local_inc(l)
+#define __cpu_local_dec(l)	cpu_local_dec(l)
+#define __cpu_local_add(i, l)	cpu_local_add((i), (l))
+#define __cpu_local_sub(i, l)	cpu_local_sub((i), (l))
 
 #endif /* _ARCH_I386_LOCAL_H */
--- a/include/asm-i386/system.h
+++ b/include/asm-i386/system.h
@@ -274,6 +274,9 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz
 #define sync_cmpxchg(ptr,o,n)\
 	((__typeof__(*(ptr)))__sync_cmpxchg((ptr),(unsigned long)(o),\
 					(unsigned long)(n),sizeof(*(ptr))))
+#define cmpxchg_local(ptr,o,n)\
+	((__typeof__(*(ptr)))__cmpxchg_local((ptr),(unsigned long)(o),\
+					(unsigned long)(n),sizeof(*(ptr))))
 #endif
 
 static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
@@ -336,6 +339,33 @@ static inline unsigned long __sync_cmpxchg(volatile void *ptr,
 	return old;
 }
 
+static inline unsigned long __cmpxchg_local(volatile void *ptr,
+			unsigned long old, unsigned long new, int size)
+{
+	unsigned long prev;
+	switch (size) {
+	case 1:
+		__asm__ __volatile__("cmpxchgb %b1,%2"
+				     : "=a"(prev)
+				     : "q"(new), "m"(*__xg(ptr)), "0"(old)
+				     : "memory");
+		return prev;
+	case 2:
+		__asm__ __volatile__("cmpxchgw %w1,%2"
+				     : "=a"(prev)
+				     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+				     : "memory");
+		return prev;
+	case 4:
+		__asm__ __volatile__("cmpxchgl %1,%2"
+				     : "=a"(prev)
+				     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+				     : "memory");
+		return prev;
+	}
+	return old;
+}
+
 #ifndef CONFIG_X86_CMPXCHG
 /*
  * Building a kernel capable running on 80386. It may be necessary to
@@ -372,6 +402,17 @@ static inline unsigned long cmpxchg_386(volatile void *ptr, unsigned long old,
 					(unsigned long)(n), sizeof(*(ptr))); \
 	__ret;								\
 })
+#define cmpxchg_local(ptr,o,n)						\
+({									\
+	__typeof__(*(ptr)) __ret;					\
+	if (likely(boot_cpu_data.x86 > 3))				\
+		__ret = __cmpxchg_local((ptr), (unsigned long)(o),	\
+					(unsigned long)(n), sizeof(*(ptr))); \
+	else								\
+		__ret = cmpxchg_386((ptr), (unsigned long)(o),		\
+					(unsigned long)(n), sizeof(*(ptr))); \
+	__ret;								\
+})
 #endif
 
 #ifdef CONFIG_X86_CMPXCHG64
@@ -390,10 +431,26 @@ static inline unsigned long long __cmpxchg64(volatile void *ptr, unsigned long l
 	return prev;
 }
 
+static inline unsigned long long __cmpxchg64_local(volatile void *ptr,
+			unsigned long long old, unsigned long long new)
+{
+	unsigned long long prev;
+	__asm__ __volatile__("cmpxchg8b %3"
+			     : "=A"(prev)
+			     : "b"((unsigned long)new),
+			       "c"((unsigned long)(new >> 32)),
+			       "m"(*__xg(ptr)),
+			       "0"(old)
+			     : "memory");
+	return prev;
+}
+
 #define cmpxchg64(ptr,o,n)\
 	((__typeof__(*(ptr)))__cmpxchg64((ptr),(unsigned long long)(o),\
 					(unsigned long long)(n)))
-
+#define cmpxchg64_local(ptr,o,n)\
+	((__typeof__(*(ptr)))__cmpxchg64_local((ptr),(unsigned long long)(o),\
+					(unsigned long long)(n)))
 #endif
     
 /*

[PATCH 04/10] local_t : ia64 extension

[Mathieu Desnoyers]

local_t : ia64 extension

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

--- a/include/asm-ia64/local.h
+++ b/include/asm-ia64/local.h
@@ -1,50 +1 @@
-#ifndef _ASM_IA64_LOCAL_H
-#define _ASM_IA64_LOCAL_H
-
-/*
- * Copyright (C) 2003 Hewlett-Packard Co
- *	David Mosberger-Tang <davidm@hpl.hp.com>
- */
-
-#include <linux/percpu.h>
-
-typedef struct {
-	atomic64_t val;
-} local_t;
-
-#define LOCAL_INIT(i)	((local_t) { { (i) } })
-#define local_read(l)	atomic64_read(&(l)->val)
-#define local_set(l, i)	atomic64_set(&(l)->val, i)
-#define local_inc(l)	atomic64_inc(&(l)->val)
-#define local_dec(l)	atomic64_dec(&(l)->val)
-#define local_add(i, l)	atomic64_add((i), &(l)->val)
-#define local_sub(i, l)	atomic64_sub((i), &(l)->val)
-
-/* Non-atomic variants, i.e., preemption disabled and won't be touched in interrupt, etc.  */
-
-#define __local_inc(l)		(++(l)->val.counter)
-#define __local_dec(l)		(--(l)->val.counter)
-#define __local_add(i,l)	((l)->val.counter += (i))
-#define __local_sub(i,l)	((l)->val.counter -= (i))
-
-/*
- * Use these for per-cpu local_t variables.  Note they take a variable (eg. mystruct.foo),
- * not an address.
- */
-#define cpu_local_read(v)	local_read(&__ia64_per_cpu_var(v))
-#define cpu_local_set(v, i)	local_set(&__ia64_per_cpu_var(v), (i))
-#define cpu_local_inc(v)	local_inc(&__ia64_per_cpu_var(v))
-#define cpu_local_dec(v)	local_dec(&__ia64_per_cpu_var(v))
-#define cpu_local_add(i, v)	local_add((i), &__ia64_per_cpu_var(v))
-#define cpu_local_sub(i, v)	local_sub((i), &__ia64_per_cpu_var(v))
-
-/*
- * Non-atomic increments, i.e., preemption disabled and won't be touched in interrupt,
- * etc.
- */
-#define __cpu_local_inc(v)	__local_inc(&__ia64_per_cpu_var(v))
-#define __cpu_local_dec(v)	__local_dec(&__ia64_per_cpu_var(v))
-#define __cpu_local_add(i, v)	__local_add((i), &__ia64_per_cpu_var(v))
-#define __cpu_local_sub(i, v)	__local_sub((i), &__ia64_per_cpu_var(v))
-
-#endif /* _ASM_IA64_LOCAL_H */
+#include <asm-generic/local.h>

[PATCH 05/10] local_t : mips extension

[Mathieu Desnoyers]

local_t : mips extension

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

--- a/include/asm-mips/local.h
+++ b/include/asm-mips/local.h
@@ -1,60 +1,524 @@
-#ifndef _ASM_LOCAL_H
-#define _ASM_LOCAL_H
+#ifndef _ARCH_MIPS_LOCAL_H
+#define _ARCH_MIPS_LOCAL_H
 
 #include <linux/percpu.h>
 #include <asm/atomic.h>
+#include <asm/war.h>
 
-#ifdef CONFIG_32BIT
+typedef struct
+{
+	atomic_long_t a;
+} local_t;
 
-typedef atomic_t local_t;
+#define LOCAL_INIT(i)	{ local_LONG_INIT(i) }
 
-#define LOCAL_INIT(i)	ATOMIC_INIT(i)
-#define local_read(v)	atomic_read(v)
-#define local_set(v,i)	atomic_set(v,i)
+#define local_read(l)	local_long_read(&(l)->a)
+#define local_set(l,i)	local_long_set(&(l)->a, (i))
 
-#define local_inc(v)	atomic_inc(v)
-#define local_dec(v)	atomic_dec(v)
-#define local_add(i, v)	atomic_add(i, v)
-#define local_sub(i, v)	atomic_sub(i, v)
+#define local_add(i,l)	local_long_add((i),(&(l)->a))
+#define local_sub(i,l)	local_long_sub((i),(&(l)->a))
+#define local_inc(l)	local_long_inc(&(l)->a)
+#define local_dec(l)	local_long_dec(&(l)->a)
 
-#endif
 
-#ifdef CONFIG_64BIT
+#ifndef CONFIG_64BIT
 
-typedef atomic64_t local_t;
+/*
+ * Same as above, but return the result value
+ */
+static __inline__ int local_add_return(int i, local_t * l)
+{
+	unsigned long result;
+
+	if (cpu_has_llsc && R10000_LLSC_WAR) {
+		unsigned long temp;
+
+		__asm__ __volatile__(
+		"	.set	mips3					\n"
+		"1:	ll	%1, %2		# local_add_return	\n"
+		"	addu	%0, %1, %3				\n"
+		"	sc	%0, %2					\n"
+		"	beqzl	%0, 1b					\n"
+		"	addu	%0, %1, %3				\n"
+		"	.set	mips0					\n"
+		: "=&r" (result), "=&r" (temp), "=m" (l->a.counter)
+		: "Ir" (i), "m" (l->a.counter)
+		: "memory");
+	} else if (cpu_has_llsc) {
+		unsigned long temp;
+
+		__asm__ __volatile__(
+		"	.set	mips3					\n"
+		"1:	ll	%1, %2		# local_add_return	\n"
+		"	addu	%0, %1, %3				\n"
+		"	sc	%0, %2					\n"
+		"	beqz	%0, 1b					\n"
+		"	addu	%0, %1, %3				\n"
+		"	.set	mips0					\n"
+		: "=&r" (result), "=&r" (temp), "=m" (l->a.counter)
+		: "Ir" (i), "m" (l->a.counter)
+		: "memory");
+	} else {
+		unsigned long flags;
+
+		local_irq_save(flags);
+		result = l->a.counter;
+		result += i;
+		l->a.counter = result;
+		local_irq_restore(flags);
+	}
+
+	return result;
+}
+
+static __inline__ int local_sub_return(int i, local_t * l)
+{
+	unsigned long result;
+
+	if (cpu_has_llsc && R10000_LLSC_WAR) {
+		unsigned long temp;
+
+		__asm__ __volatile__(
+		"	.set	mips3					\n"
+		"1:	ll	%1, %2		# local_sub_return	\n"
+		"	subu	%0, %1, %3				\n"
+		"	sc	%0, %2					\n"
+		"	beqzl	%0, 1b					\n"
+		"	subu	%0, %1, %3				\n"
+		"	.set	mips0					\n"
+		: "=&r" (result), "=&r" (temp), "=m" (l->a.counter)
+		: "Ir" (i), "m" (l->a.counter)
+		: "memory");
+	} else if (cpu_has_llsc) {
+		unsigned long temp;
+
+		__asm__ __volatile__(
+		"	.set	mips3					\n"
+		"1:	ll	%1, %2		# local_sub_return	\n"
+		"	subu	%0, %1, %3				\n"
+		"	sc	%0, %2					\n"
+		"	beqz	%0, 1b					\n"
+		"	subu	%0, %1, %3				\n"
+		"	.set	mips0					\n"
+		: "=&r" (result), "=&r" (temp), "=m" (l->a.counter)
+		: "Ir" (i), "m" (l->a.counter)
+		: "memory");
+	} else {
+		unsigned long flags;
 
-#define LOCAL_INIT(i)	ATOMIC64_INIT(i)
-#define local_read(v)	atomic64_read(v)
-#define local_set(v,i)	atomic64_set(v,i)
+		local_irq_save(flags);
+		result = l->a.counter;
+		result -= i;
+		l->a.counter = result;
+		local_irq_restore(flags);
+	}
 
-#define local_inc(v)	atomic64_inc(v)
-#define local_dec(v)	atomic64_dec(v)
-#define local_add(i, v)	atomic64_add(i, v)
-#define local_sub(i, v)	atomic64_sub(i, v)
+	return result;
+}
 
-#endif
+/*
+ * local_sub_if_positive - conditionally subtract integer from atomic variable
+ * @i: integer value to subtract
+ * @l: pointer of type local_t
+ *
+ * Atomically test @l and subtract @i if @l is greater or equal than @i.
+ * The function returns the old value of @l minus @i.
+ */
+static __inline__ int local_sub_if_positive(int i, local_t * l)
+{
+	unsigned long result;
+
+	if (cpu_has_llsc && R10000_LLSC_WAR) {
+		unsigned long temp;
+
+		__asm__ __volatile__(
+		"	.set	mips3					\n"
+		"1:	ll	%1, %2		# local_sub_if_positive\n"
+		"	subu	%0, %1, %3				\n"
+		"	bltz	%0, 1f					\n"
+		"	sc	%0, %2					\n"
+		"	.set	noreorder				\n"
+		"	beqzl	%0, 1b					\n"
+		"	 subu	%0, %1, %3				\n"
+		"	.set	reorder					\n"
+		"1:							\n"
+		"	.set	mips0					\n"
+		: "=&r" (result), "=&r" (temp), "=m" (l->a.counter)
+		: "Ir" (i), "m" (l->a.counter)
+		: "memory");
+	} else if (cpu_has_llsc) {
+		unsigned long temp;
+
+		__asm__ __volatile__(
+		"	.set	mips3					\n"
+		"1:	ll	%1, %2		# local_sub_if_positive\n"
+		"	subu	%0, %1, %3				\n"
+		"	bltz	%0, 1f					\n"
+		"	sc	%0, %2					\n"
+		"	.set	noreorder				\n"
+		"	beqz	%0, 1b					\n"
+		"	 subu	%0, %1, %3				\n"
+		"	.set	reorder					\n"
+		"1:							\n"
+		"	.set	mips0					\n"
+		: "=&r" (result), "=&r" (temp), "=m" (l->a.counter)
+		: "Ir" (i), "m" (l->a.counter)
+		: "memory");
+	} else {
+		unsigned long flags;
+
+		local_irq_save(flags);
+		result = l->a.counter;
+		result -= i;
+		if (result >= 0)
+			l->a.counter = result;
+		local_irq_restore(flags);
+	}
+
+	return result;
+}
+
+#define local_cmpxchg(l, o, n) \
+	(cmpxchg_local(&((l)->a.counter), (o), (n)))
+#define local_xchg(l, n) (xchg_local(&((l)->a.counter), (n)))
+
+/**
+ * local_add_unless - add unless the number is a given value
+ * @l: pointer of type local_t
+ * @a: the amount to add to l...
+ * @u: ...unless l is equal to u.
+ *
+ * Atomically adds @a to @l, so long as it was not @u.
+ * Returns non-zero if @l was not @u, and zero otherwise.
+ */
+#define local_add_unless(l, a, u)				\
+({								\
+	long c, old;						\
+	c = local_read(l);					\
+	while (c != (u) && (old = local_cmpxchg((l), c, c + (a))) != c) \
+		c = old;					\
+	c != (u);						\
+})
+#define local_inc_not_zero(l) local_add_unless((l), 1, 0)
 
-#define __local_inc(v)		((v)->counter++)
-#define __local_dec(v)		((v)->counter--)
-#define __local_add(i,v)	((v)->counter+=(i))
-#define __local_sub(i,v)	((v)->counter-=(i))
+#define local_dec_return(l) local_sub_return(1,(l))
+#define local_inc_return(l) local_add_return(1,(l))
 
 /*
- * Use these for per-cpu local_t variables: on some archs they are
+ * local_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @l: pointer of type local_t
+ *
+ * Atomically subtracts @i from @l and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+#define local_sub_and_test(i,l) (local_sub_return((i), (l)) == 0)
+
+/*
+ * local_inc_and_test - increment and test
+ * @l: pointer of type local_t
+ *
+ * Atomically increments @l by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+#define local_inc_and_test(l) (local_inc_return(l) == 0)
+
+/*
+ * local_dec_and_test - decrement by 1 and test
+ * @l: pointer of type local_t
+ *
+ * Atomically decrements @l by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+#define local_dec_and_test(l) (local_sub_return(1, (l)) == 0)
+
+/*
+ * local_dec_if_positive - decrement by 1 if old value positive
+ * @l: pointer of type local_t
+ */
+#define local_dec_if_positive(l)	local_sub_if_positive(1, l)
+
+/*
+ * local_add_negative - add and test if negative
+ * @l: pointer of type local_t
+ * @i: integer value to add
+ *
+ * Atomically adds @i to @l and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
+ */
+#define local_add_negative(i,l) (local_add_return(i, (l)) < 0)
+
+#else /* CONFIG_64BIT */
+
+/*
+ * Same as above, but return the result value
+ */
+static __inline__ long local_add_return(long i, local_t * l)
+{
+	unsigned long result;
+
+	if (cpu_has_llsc && R10000_LLSC_WAR) {
+		unsigned long temp;
+
+		__asm__ __volatile__(
+		"	.set	mips3					\n"
+		"1:	lld	%1, %2		# local_add_return	\n"
+		"	addu	%0, %1, %3				\n"
+		"	scd	%0, %2					\n"
+		"	beqzl	%0, 1b					\n"
+		"	addu	%0, %1, %3				\n"
+		"	.set	mips0					\n"
+		: "=&r" (result), "=&r" (temp), "=m" (l->a.counter)
+		: "Ir" (i), "m" (l->a.counter)
+		: "memory");
+	} else if (cpu_has_llsc) {
+		unsigned long temp;
+
+		__asm__ __volatile__(
+		"	.set	mips3					\n"
+		"1:	lld	%1, %2		# local_add_return	\n"
+		"	addu	%0, %1, %3				\n"
+		"	scd	%0, %2					\n"
+		"	beqz	%0, 1b					\n"
+		"	addu	%0, %1, %3				\n"
+		"	.set	mips0					\n"
+		: "=&r" (result), "=&r" (temp), "=m" (l->a.counter)
+		: "Ir" (i), "m" (l->a.counter)
+		: "memory");
+	} else {
+		unsigned long flags;
+
+		local_irq_save(flags);
+		result = l->a.counter;
+		result += i;
+		l->a.counter = result;
+		local_irq_restore(flags);
+	}
+
+	return result;
+}
+
+static __inline__ long local_sub_return(long i, local_t * l)
+{
+	unsigned long result;
+
+	if (cpu_has_llsc && R10000_LLSC_WAR) {
+		unsigned long temp;
+
+		__asm__ __volatile__(
+		"	.set	mips3					\n"
+		"1:	lld	%1, %2		# local_sub_return	\n"
+		"	subu	%0, %1, %3				\n"
+		"	scd	%0, %2					\n"
+		"	beqzl	%0, 1b					\n"
+		"	subu	%0, %1, %3				\n"
+		"	.set	mips0					\n"
+		: "=&r" (result), "=&r" (temp), "=m" (l->a.counter)
+		: "Ir" (i), "m" (l->a.counter)
+		: "memory");
+	} else if (cpu_has_llsc) {
+		unsigned long temp;
+
+		__asm__ __volatile__(
+		"	.set	mips3					\n"
+		"1:	lld	%1, %2		# local_sub_return	\n"
+		"	subu	%0, %1, %3				\n"
+		"	scd	%0, %2					\n"
+		"	beqz	%0, 1b					\n"
+		"	subu	%0, %1, %3				\n"
+		"	.set	mips0					\n"
+		: "=&r" (result), "=&r" (temp), "=m" (l->a.counter)
+		: "Ir" (i), "m" (l->a.counter)
+		: "memory");
+	} else {
+		unsigned long flags;
+
+		local_irq_save(flags);
+		result = l->a.counter;
+		result -= i;
+		l->a.counter = result;
+		local_irq_restore(flags);
+	}
+
+	return result;
+}
+
+/*
+ * local_sub_if_positive - conditionally subtract integer from atomic variable
+ * @i: integer value to subtract
+ * @l: pointer of type local_t
+ *
+ * Atomically test @l and subtract @i if @l is greater or equal than @i.
+ * The function returns the old value of @l minus @i.
+ */
+static __inline__ long local_sub_if_positive(long i, local_t * l)
+{
+	unsigned long result;
+
+	if (cpu_has_llsc && R10000_LLSC_WAR) {
+		unsigned long temp;
+
+		__asm__ __volatile__(
+		"	.set	mips3					\n"
+		"1:	lld	%1, %2		# local_sub_if_positive\n"
+		"	dsubu	%0, %1, %3				\n"
+		"	bltz	%0, 1f					\n"
+		"	scd	%0, %2					\n"
+		"	.set	noreorder				\n"
+		"	beqzl	%0, 1b					\n"
+		"	 dsubu	%0, %1, %3				\n"
+		"	.set	reorder					\n"
+		"1:							\n"
+		"	.set	mips0					\n"
+		: "=&r" (result), "=&r" (temp), "=m" (l->a.counter)
+		: "Ir" (i), "m" (l->a.counter)
+		: "memory");
+	} else if (cpu_has_llsc) {
+		unsigned long temp;
+
+		__asm__ __volatile__(
+		"	.set	mips3					\n"
+		"1:	lld	%1, %2		# local_sub_if_positive\n"
+		"	dsubu	%0, %1, %3				\n"
+		"	bltz	%0, 1f					\n"
+		"	scd	%0, %2					\n"
+		"	.set	noreorder				\n"
+		"	beqz	%0, 1b					\n"
+		"	 dsubu	%0, %1, %3				\n"
+		"	.set	reorder					\n"
+		"1:							\n"
+		"	.set	mips0					\n"
+		: "=&r" (result), "=&r" (temp), "=m" (l->a.counter)
+		: "Ir" (i), "m" (l->a.counter)
+		: "memory");
+	} else {
+		unsigned long flags;
+
+		local_irq_save(flags);
+		result = l->a.counter;
+		result -= i;
+		if (result >= 0)
+			l->a.counter = result;
+		local_irq_restore(flags);
+	}
+
+	return result;
+}
+
+#define local_cmpxchg(l, o, n) \
+	((long)cmpxchg_local(&((l)->a.counter), (o), (n)))
+#define local_xchg(l, (n)) (xchg_local(&((l)->a.counter),(n)))
+
+/**
+ * local_add_unless - add unless the number is a given value
+ * @l: pointer of type local_t
+ * @a: the amount to add to l...
+ * @u: ...unless l is equal to u.
+ *
+ * Atomically adds @a to @l, so long as it was not @u.
+ * Returns non-zero if @l was not @u, and zero otherwise.
+ */
+#define local_add_unless(l, a, u)				\
+({								\
+	long c, old;						\
+	c = local_read(l);					\
+	while (c != (u) && (old = local_cmpxchg((l), c, c + (a))) != c) \
+		c = old;					\
+	c != (u);						\
+})
+#define local_inc_not_zero(l) local_add_unless((l), 1, 0)
+
+#define local_dec_return(l) local_sub_return(1,(l))
+#define local_inc_return(l) local_add_return(1,(l))
+
+/*
+ * local_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @l: pointer of type local_t
+ *
+ * Atomically subtracts @i from @l and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+#define local_sub_and_test(i,l) (local_sub_return((i), (l)) == 0)
+
+/*
+ * local_inc_and_test - increment and test
+ * @l: pointer of type local_t
+ *
+ * Atomically increments @l by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+#define local_inc_and_test(l) (local_inc_return(l) == 0)
+
+/*
+ * local_dec_and_test - decrement by 1 and test
+ * @l: pointer of type local_t
+ *
+ * Atomically decrements @l by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+#define local_dec_and_test(l) (local_sub_return(1, (l)) == 0)
+
+/*
+ * local_dec_if_positive - decrement by 1 if old value positive
+ * @l: pointer of type local_t
+ */
+#define local_dec_if_positive(l)	local_sub_if_positive(1, l)
+
+/*
+ * local_add_negative - add and test if negative
+ * @l: pointer of type local_t
+ * @i: integer value to add
+ *
+ * Atomically adds @i to @l and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
+ */
+#define local_add_negative(i,l) (local_add_return(i, (l)) < 0)
+
+#endif /* !CONFIG_64BIT */
+
+
+/* Use these for per-cpu local_t variables: on some archs they are
  * much more efficient than these naive implementations.  Note they take
  * a variable, not an address.
  */
-#define cpu_local_read(v)	local_read(&__get_cpu_var(v))
-#define cpu_local_set(v, i)	local_set(&__get_cpu_var(v), (i))
 
-#define cpu_local_inc(v)	local_inc(&__get_cpu_var(v))
-#define cpu_local_dec(v)	local_dec(&__get_cpu_var(v))
-#define cpu_local_add(i, v)	local_add((i), &__get_cpu_var(v))
-#define cpu_local_sub(i, v)	local_sub((i), &__get_cpu_var(v))
+#define __local_inc(l)		((l)->a.counter++)
+#define __local_dec(l)		((l)->a.counter++)
+#define __local_add(i,l)	((l)->a.counter+=(i))
+#define __local_sub(i,l)	((l)->a.counter-=(i))
+
+/* Need to disable preemption for the cpu local counters otherwise we could
+   still access a variable of a previous CPU in a non atomic way. */
+#define cpu_local_wrap_v(l)	 	\
+	({ local_t res__;		\
+	   preempt_disable(); 		\
+	   res__ = (l);			\
+	   preempt_enable();		\
+	   res__; })
+#define cpu_local_wrap(l)		\
+	({ preempt_disable();		\
+	   l;				\
+	   preempt_enable(); })		\
+
+#define cpu_local_read(l)    cpu_local_wrap_v(local_read(&__get_cpu_var(l)))
+#define cpu_local_set(l, i)  cpu_local_wrap(local_set(&__get_cpu_var(l), (i)))
+#define cpu_local_inc(l)     cpu_local_wrap(local_inc(&__get_cpu_var(l)))
+#define cpu_local_dec(l)     cpu_local_wrap(local_dec(&__get_cpu_var(l)))
+#define cpu_local_add(i, l)  cpu_local_wrap(local_add((i), &__get_cpu_var(l)))
+#define cpu_local_sub(i, l)  cpu_local_wrap(local_sub((i), &__get_cpu_var(l)))
 
-#define __cpu_local_inc(v)	__local_inc(&__get_cpu_var(v))
-#define __cpu_local_dec(v)	__local_dec(&__get_cpu_var(v))
-#define __cpu_local_add(i, v)	__local_add((i), &__get_cpu_var(v))
-#define __cpu_local_sub(i, v)	__local_sub((i), &__get_cpu_var(v))
+#define __cpu_local_inc(l)	cpu_local_inc(l)
+#define __cpu_local_dec(l)	cpu_local_dec(l)
+#define __cpu_local_add(i, l)	cpu_local_add((i), (l))
+#define __cpu_local_sub(i, l)	cpu_local_sub((i), (l))
 
-#endif /* _ASM_LOCAL_H */
+#endif /* _ARCH_MIPS_LOCAL_H */
--- a/include/asm-mips/system.h
+++ b/include/asm-mips/system.h
@@ -253,6 +253,58 @@ static inline unsigned long __cmpxchg_u32(volatile int * m, unsigned long old,
 	return retval;
 }
 
+static inline unsigned long __cmpxchg_u32_local(volatile int * m,
+	unsigned long old, unsigned long new)
+{
+	__u32 retval;
+
+	if (cpu_has_llsc && R10000_LLSC_WAR) {
+		__asm__ __volatile__(
+		"	.set	push					\n"
+		"	.set	noat					\n"
+		"	.set	mips3					\n"
+		"1:	ll	%0, %2			# __cmpxchg_u32	\n"
+		"	bne	%0, %z3, 2f				\n"
+		"	.set	mips0					\n"
+		"	move	$1, %z4					\n"
+		"	.set	mips3					\n"
+		"	sc	$1, %1					\n"
+		"	beqzl	$1, 1b					\n"
+		"2:							\n"
+		"	.set	pop					\n"
+		: "=&r" (retval), "=R" (*m)
+		: "R" (*m), "Jr" (old), "Jr" (new)
+		: "memory");
+	} else if (cpu_has_llsc) {
+		__asm__ __volatile__(
+		"	.set	push					\n"
+		"	.set	noat					\n"
+		"	.set	mips3					\n"
+		"1:	ll	%0, %2			# __cmpxchg_u32	\n"
+		"	bne	%0, %z3, 2f				\n"
+		"	.set	mips0					\n"
+		"	move	$1, %z4					\n"
+		"	.set	mips3					\n"
+		"	sc	$1, %1					\n"
+		"	beqz	$1, 1b					\n"
+		"2:							\n"
+		"	.set	pop					\n"
+		: "=&r" (retval), "=R" (*m)
+		: "R" (*m), "Jr" (old), "Jr" (new)
+		: "memory");
+	} else {
+		unsigned long flags;
+
+		local_irq_save(flags);
+		retval = *m;
+		if (retval == old)
+			*m = new;
+		local_irq_restore(flags);	/* implies memory barrier  */
+	}
+
+	return retval;
+}
+
 #ifdef CONFIG_64BIT
 static inline unsigned long __cmpxchg_u64(volatile int * m, unsigned long old,
 	unsigned long new)
@@ -303,10 +355,62 @@ static inline unsigned long __cmpxchg_u64(volatile int * m, unsigned long old,
 
 	return retval;
 }
+
+static inline unsigned long __cmpxchg_u64_local(volatile int * m,
+	unsigned long old, unsigned long new)
+{
+	__u64 retval;
+
+	if (cpu_has_llsc && R10000_LLSC_WAR) {
+		__asm__ __volatile__(
+		"	.set	push					\n"
+		"	.set	noat					\n"
+		"	.set	mips3					\n"
+		"1:	lld	%0, %2			# __cmpxchg_u64	\n"
+		"	bne	%0, %z3, 2f				\n"
+		"	move	$1, %z4					\n"
+		"	scd	$1, %1					\n"
+		"	beqzl	$1, 1b					\n"
+		"2:							\n"
+		"	.set	pop					\n"
+		: "=&r" (retval), "=R" (*m)
+		: "R" (*m), "Jr" (old), "Jr" (new)
+		: "memory");
+	} else if (cpu_has_llsc) {
+		__asm__ __volatile__(
+		"	.set	push					\n"
+		"	.set	noat					\n"
+		"	.set	mips3					\n"
+		"1:	lld	%0, %2			# __cmpxchg_u64	\n"
+		"	bne	%0, %z3, 2f				\n"
+		"	move	$1, %z4					\n"
+		"	scd	$1, %1					\n"
+		"	beqz	$1, 1b					\n"
+		"2:							\n"
+		"	.set	pop					\n"
+		: "=&r" (retval), "=R" (*m)
+		: "R" (*m), "Jr" (old), "Jr" (new)
+		: "memory");
+	} else {
+		unsigned long flags;
+
+		local_irq_save(flags);
+		retval = *m;
+		if (retval == old)
+			*m = new;
+		local_irq_restore(flags);	/* implies memory barrier  */
+	}
+
+	return retval;
+}
+
 #else
 extern unsigned long __cmpxchg_u64_unsupported_on_32bit_kernels(
 	volatile int * m, unsigned long old, unsigned long new);
 #define __cmpxchg_u64 __cmpxchg_u64_unsupported_on_32bit_kernels
+extern unsigned long __cmpxchg_u64_local_unsupported_on_32bit_kernels(
+	volatile int * m, unsigned long old, unsigned long new);
+#define __cmpxchg_u64_local __cmpxchg_u64_local_unsupported_on_32bit_kernels
 #endif
 
 /* This function doesn't exist, so you'll get a linker error
@@ -326,7 +430,26 @@ static inline unsigned long __cmpxchg(volatile void * ptr, unsigned long old,
 	return old;
 }
 
-#define cmpxchg(ptr,old,new) ((__typeof__(*(ptr)))__cmpxchg((ptr), (unsigned long)(old), (unsigned long)(new),sizeof(*(ptr))))
+static inline unsigned long __cmpxchg_local(volatile void * ptr,
+	unsigned long old, unsigned long new, int size)
+{
+	switch (size) {
+	case 4:
+		return __cmpxchg_u32_local(ptr, old, new);
+	case 8:
+		return __cmpxchg_u64_local(ptr, old, new);
+	}
+	__cmpxchg_called_with_bad_pointer();
+	return old;
+}
+
+#define cmpxchg(ptr,old,new) \
+	((__typeof__(*(ptr)))__cmpxchg((ptr), \
+		(unsigned long)(old), (unsigned long)(new),sizeof(*(ptr))))
+
+#define cmpxchg_local(ptr,old,new) \
+	((__typeof__(*(ptr)))__cmpxchg_local((ptr), \
+		(unsigned long)(old), (unsigned long)(new),sizeof(*(ptr))))
 
 extern void set_handler (unsigned long offset, void *addr, unsigned long len);
 extern void set_uncached_handler (unsigned long offset, void *addr, unsigned long len);

[PATCH 06/10] local_t : parisc cleanup

[Mathieu Desnoyers]

local_t : parisc cleanup

parisc architecture local_t cleanup : use asm-generic/local.h.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

--- a/include/asm-parisc/local.h
+++ b/include/asm-parisc/local.h
@@ -1,40 +1 @@
-#ifndef _ARCH_PARISC_LOCAL_H
-#define _ARCH_PARISC_LOCAL_H
-
-#include <linux/percpu.h>
-#include <asm/atomic.h>
-
-typedef atomic_long_t local_t;
-
-#define LOCAL_INIT(i)	ATOMIC_LONG_INIT(i)
-#define local_read(v)	atomic_long_read(v)
-#define local_set(v,i)	atomic_long_set(v,i)
-
-#define local_inc(v)	atomic_long_inc(v)
-#define local_dec(v)	atomic_long_dec(v)
-#define local_add(i, v)	atomic_long_add(i, v)
-#define local_sub(i, v)	atomic_long_sub(i, v)
-
-#define __local_inc(v)		((v)->counter++)
-#define __local_dec(v)		((v)->counter--)
-#define __local_add(i,v)	((v)->counter+=(i))
-#define __local_sub(i,v)	((v)->counter-=(i))
-
-/* Use these for per-cpu local_t variables: on some archs they are
- * much more efficient than these naive implementations.  Note they take
- * a variable, not an address.
- */
-#define cpu_local_read(v)	local_read(&__get_cpu_var(v))
-#define cpu_local_set(v, i)	local_set(&__get_cpu_var(v), (i))
-
-#define cpu_local_inc(v)	local_inc(&__get_cpu_var(v))
-#define cpu_local_dec(v)	local_dec(&__get_cpu_var(v))
-#define cpu_local_add(i, v)	local_add((i), &__get_cpu_var(v))
-#define cpu_local_sub(i, v)	local_sub((i), &__get_cpu_var(v))
-
-#define __cpu_local_inc(v)	__local_inc(&__get_cpu_var(v))
-#define __cpu_local_dec(v)	__local_dec(&__get_cpu_var(v))
-#define __cpu_local_add(i, v)	__local_add((i), &__get_cpu_var(v))
-#define __cpu_local_sub(i, v)	__local_sub((i), &__get_cpu_var(v))
-
-#endif /* _ARCH_PARISC_LOCAL_H */
+#include <asm-generic/local.h>

[PATCH 07/10] local_t : powerpc extension

[Mathieu Desnoyers]

local_t : powerpc extension

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

--- a/include/asm-powerpc/local.h
+++ b/include/asm-powerpc/local.h
@@ -1 +1,342 @@
-#include <asm-generic/local.h>
+#ifndef _ARCH_POWERPC_LOCAL_H
+#define _ARCH_POWERPC_LOCAL_H
+
+#include <linux/percpu.h>
+#include <asm/atomic.h>
+
+typedef struct
+{
+	atomic_long_t a;
+} local_t;
+
+#define LOCAL_INIT(i)	{ ATOMIC_LONG_INIT(i) }
+
+#define local_read(l)	atomic_long_read(&(l)->a)
+#define local_set(l,i)	atomic_long_set(&(l)->a, (i))
+
+#define local_add(i,l)	atomic_long_add((i),(&(l)->a))
+#define local_sub(i,l)	atomic_long_sub((i),(&(l)->a))
+#define local_inc(l)	atomic_long_inc(&(l)->a)
+#define local_dec(l)	atomic_long_dec(&(l)->a)
+
+#ifndef __powerpc64__
+
+static __inline__ int local_add_return(int a, local_t *l)
+{
+	int t;
+
+	__asm__ __volatile__(
+"1:	lwarx	%0,0,%2		# local_add_return\n\
+	add	%0,%1,%0\n"
+	PPC405_ERR77(0,%2)
+"	stwcx.	%0,0,%2 \n\
+	bne-	1b"
+	: "=&r" (t)
+	: "r" (a), "r" (&(l->a.counter))
+	: "cc", "memory");
+
+	return t;
+}
+
+#define local_add_negative(a, l)	(local_add_return((a), (l)) < 0)
+
+static __inline__ int local_sub_return(int a, local_t *l)
+{
+	int t;
+
+	__asm__ __volatile__(
+"1:	lwarx	%0,0,%2		# local_sub_return\n\
+	subf	%0,%1,%0\n"
+	PPC405_ERR77(0,%2)
+"	stwcx.	%0,0,%2 \n\
+	bne-	1b"
+	: "=&r" (t)
+	: "r" (a), "r" (&(l->a.counter))
+	: "cc", "memory");
+
+	return t;
+}
+
+static __inline__ int local_inc_return(local_t *l)
+{
+	int t;
+
+	__asm__ __volatile__(
+"1:	lwarx	%0,0,%1		# local_inc_return\n\
+	addic	%0,%0,1\n"
+	PPC405_ERR77(0,%1)
+"	stwcx.	%0,0,%1 \n\
+	bne-	1b"
+	: "=&r" (t)
+	: "r" (&(l->a.counter))
+	: "cc", "memory");
+
+	return t;
+}
+
+/*
+ * local_inc_and_test - increment and test
+ * @l: pointer of type local_t
+ *
+ * Atomically increments @l by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+#define local_inc_and_test(l) (local_inc_return(l) == 0)
+
+static __inline__ int local_dec_return(local_t *l)
+{
+	int t;
+
+	__asm__ __volatile__(
+"1:	lwarx	%0,0,%1		# local_dec_return\n\
+	addic	%0,%0,-1\n"
+	PPC405_ERR77(0,%1)
+"	stwcx.	%0,0,%1\n\
+	bne-	1b"
+	: "=&r" (t)
+	: "r" (&(l->a.counter))
+	: "cc", "memory");
+
+	return t;
+}
+
+#define local_cmpxchg(l, o, n) \
+	(cmpxchg_local(&((l)->a.counter), (o), (n)))
+#define local_xchg(l, n) (xchg_local(&((l)->a.counter), (n)))
+
+/**
+ * local_add_unless - add unless the number is a given value
+ * @l: pointer of type local_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @l, so long as it was not @u.
+ * Returns non-zero if @l was not @u, and zero otherwise.
+ */
+static __inline__ int local_add_unless(local_t *l, int a, int u)
+{
+	int t;
+
+	__asm__ __volatile__ (
+"1:	lwarx	%0,0,%1		# local_add_unless\n\
+	cmpw	0,%0,%3 \n\
+	beq-	2f \n\
+	add	%0,%2,%0 \n"
+	PPC405_ERR77(0,%2)
+"	stwcx.	%0,0,%1 \n\
+	bne-	1b \n"
+"	subf	%0,%2,%0 \n\
+2:"
+	: "=&r" (t)
+	: "r" (&(l->a.counter)), "r" (a), "r" (u)
+	: "cc", "memory");
+
+	return t != u;
+}
+
+#define local_inc_not_zero(l) local_add_unless((l), 1, 0)
+
+#define local_sub_and_test(a, l)	(local_sub_return((a), (l)) == 0)
+#define local_dec_and_test(l)		(local_dec_return((l)) == 0)
+
+/*
+ * Atomically test *l and decrement if it is greater than 0.
+ * The function returns the old value of *l minus 1.
+ */
+static __inline__ int local_dec_if_positive(local_t *l)
+{
+	int t;
+
+	__asm__ __volatile__(
+"1:	lwarx	%0,0,%1		# local_dec_if_positive\n\
+	cmpwi	%0,1\n\
+	addi	%0,%0,-1\n\
+	blt-	2f\n"
+	PPC405_ERR77(0,%1)
+"	stwcx.	%0,0,%1\n\
+	bne-	1b"
+	"\n\
+2:"	: "=&b" (t)
+	: "r" (&(l->a.counter))
+	: "cc", "memory");
+
+	return t;
+}
+
+#else /* __powerpc64__ */
+
+static __inline__ long local_add_return(long a, local_t *l)
+{
+	long t;
+
+	__asm__ __volatile__(
+"1:	ldarx	%0,0,%2		# local_add_return\n\
+	add	%0,%1,%0\n\
+	stdcx.	%0,0,%2 \n\
+	bne-	1b"
+	: "=&r" (t)
+	: "r" (a), "r" (&(l->a.counter))
+	: "cc", "memory");
+
+	return t;
+}
+
+#define local_add_negative(a, l)	(local_add_return((a), (l)) < 0)
+
+static __inline__ long local_sub_return(long a, local_t *l)
+{
+	long t;
+
+	__asm__ __volatile__(
+"1:	ldarx	%0,0,%2		# local_sub_return\n\
+	subf	%0,%1,%0\n\
+	stdcx.	%0,0,%2 \n\
+	bne-	1b"
+	: "=&r" (t)
+	: "r" (a), "r" (&(l->a.counter))
+	: "cc", "memory");
+
+	return t;
+}
+
+static __inline__ long local_inc_return(local_t *l)
+{
+	long t;
+
+	__asm__ __volatile__(
+"1:	ldarx	%0,0,%1		# local_inc_return\n\
+	addic	%0,%0,1\n\
+	stdcx.	%0,0,%1 \n\
+	bne-	1b"
+	: "=&r" (t)
+	: "r" (&(l->a.counter))
+	: "cc", "memory");
+
+	return t;
+}
+
+/*
+ * local_inc_and_test - increment and test
+ * @l: pointer of type local_t
+ *
+ * Atomically increments @l by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+#define local_inc_and_test(l) (local_inc_return(l) == 0)
+
+static __inline__ long local_dec_return(local_t *l)
+{
+	long t;
+
+	__asm__ __volatile__(
+"1:	ldarx	%0,0,%1		# local_dec_return\n\
+	addic	%0,%0,-1\n\
+	stdcx.	%0,0,%1\n\
+	bne-	1b"
+	: "=&r" (t)
+	: "r" (&(l->a.counter))
+	: "cc", "memory");
+
+	return t;
+}
+
+#define local_sub_and_test(a, l)	(local_sub_return((a), (l)) == 0)
+#define local_dec_and_test(l)	(local_dec_return((l)) == 0)
+
+/*
+ * Atomically test *l and decrement if it is greater than 0.
+ * The function returns the old value of *l minus 1.
+ */
+static __inline__ long local_dec_if_positive(local_t *l)
+{
+	long t;
+
+	__asm__ __volatile__(
+"1:	ldarx	%0,0,%1		# local_dec_if_positive\n\
+	addic.	%0,%0,-1\n\
+	blt-	2f\n\
+	stdcx.	%0,0,%1\n\
+	bne-	1b"
+	"\n\
+2:"	: "=&r" (t)
+	: "r" (&(l->a.counter))
+	: "cc", "memory");
+
+	return t;
+}
+
+#define local_cmpxchg(l, o, n) \
+	((long)cmpxchg_local(&((l)->a.counter), (o), (n)))
+#define local_xchg(l, (n)) (xchg_local(&((l)->a.counter), (n)))
+
+/**
+ * local_add_unless - add unless the number is a given value
+ * @l: pointer of type local_t
+ * @a: the amount to add to l...
+ * @u: ...unless l is equal to u.
+ *
+ * Atomically adds @a to @l, so long as it was not @u.
+ * Returns non-zero if @l was not @u, and zero otherwise.
+ */
+static __inline__ int local_add_unless(local_t *l, long a, long u)
+{
+	long t;
+
+	__asm__ __volatile__ (
+"1:	ldarx	%0,0,%1		# local_add_unless\n\
+	cmpd	0,%0,%3 \n\
+	beq-	2f \n\
+	add	%0,%2,%0 \n"
+"	stdcx.	%0,0,%1 \n\
+	bne-	1b \n"
+"	subf	%0,%2,%0 \n\
+2:"
+	: "=&r" (t)
+	: "r" (&(l->a.counter)), "r" (a), "r" (u)
+	: "cc", "memory");
+
+	return t != u;
+}
+
+#define local_inc_not_zero(l) local_add_unless((l), 1, 0)
+
+#endif /* !__powerpc64__ */
+
+/* Use these for per-cpu local_t variables: on some archs they are
+ * much more efficient than these naive implementations.  Note they take
+ * a variable, not an address.
+ */
+
+#define __local_inc(l)		((l)->a.counter++)
+#define __local_dec(l)		((l)->a.counter++)
+#define __local_add(i,l)	((l)->a.counter+=(i))
+#define __local_sub(i,l)	((l)->a.counter-=(i))
+
+/* Need to disable preemption for the cpu local counters otherwise we could
+   still access a variable of a previous CPU in a non atomic way. */
+#define cpu_local_wrap_v(l)	 	\
+	({ local_t res__;		\
+	   preempt_disable(); 		\
+	   res__ = (l);			\
+	   preempt_enable();		\
+	   res__; })
+#define cpu_local_wrap(l)		\
+	({ preempt_disable();		\
+	   l;				\
+	   preempt_enable(); })		\
+
+#define cpu_local_read(l)    cpu_local_wrap_v(local_read(&__get_cpu_var(l)))
+#define cpu_local_set(l, i)  cpu_local_wrap(local_set(&__get_cpu_var(l), (i)))
+#define cpu_local_inc(l)     cpu_local_wrap(local_inc(&__get_cpu_var(l)))
+#define cpu_local_dec(l)     cpu_local_wrap(local_dec(&__get_cpu_var(l)))
+#define cpu_local_add(i, l)  cpu_local_wrap(local_add((i), &__get_cpu_var(l)))
+#define cpu_local_sub(i, l)  cpu_local_wrap(local_sub((i), &__get_cpu_var(l)))
+
+#define __cpu_local_inc(l)	cpu_local_inc(l)
+#define __cpu_local_dec(l)	cpu_local_dec(l)
+#define __cpu_local_add(i, l)	cpu_local_add((i), (l))
+#define __cpu_local_sub(i, l)	cpu_local_sub((i), (l))
+
+#endif /* _ARCH_POWERPC_LOCAL_H */
--- a/include/asm-powerpc/system.h
+++ b/include/asm-powerpc/system.h
@@ -7,7 +7,6 @@
 #include <linux/kernel.h>
 
 #include <asm/hw_irq.h>
-#include <asm/atomic.h>
 
 /*
  * Memory barrier.
@@ -226,6 +225,29 @@ __xchg_u32(volatile void *p, unsigned long val)
 	return prev;
 }
 
+/*
+ * Atomic exchange
+ *
+ * Changes the memory location '*ptr' to be val and returns
+ * the previous value stored there.
+ */
+static __inline__ unsigned long
+__xchg_u32_local(volatile void *p, unsigned long val)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__(
+"1:	lwarx	%0,0,%2 \n"
+	PPC405_ERR77(0,%2)
+"	stwcx.	%3,0,%2 \n\
+	bne-	1b"
+	: "=&r" (prev), "+m" (*(volatile unsigned int *)p)
+	: "r" (p), "r" (val)
+	: "cc", "memory");
+
+	return prev;
+}
+
 #ifdef CONFIG_PPC64
 static __inline__ unsigned long
 __xchg_u64(volatile void *p, unsigned long val)
@@ -245,6 +267,23 @@ __xchg_u64(volatile void *p, unsigned long val)
 
 	return prev;
 }
+
+static __inline__ unsigned long
+__xchg_u64_local(volatile void *p, unsigned long val)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__(
+"1:	ldarx	%0,0,%2 \n"
+	PPC405_ERR77(0,%2)
+"	stdcx.	%3,0,%2 \n\
+	bne-	1b"
+	: "=&r" (prev), "+m" (*(volatile unsigned long *)p)
+	: "r" (p), "r" (val)
+	: "cc", "memory");
+
+	return prev;
+}
 #endif
 
 /*
@@ -268,12 +307,33 @@ __xchg(volatile void *ptr, unsigned long x, unsigned int size)
 	return x;
 }
 
+static __inline__ unsigned long
+__xchg_local(volatile void *ptr, unsigned long x, unsigned int size)
+{
+	switch (size) {
+	case 4:
+		return __xchg_u32_local(ptr, x);
+#ifdef CONFIG_PPC64
+	case 8:
+		return __xchg_u64_local(ptr, x);
+#endif
+	}
+	__xchg_called_with_bad_pointer();
+	return x;
+}
 #define xchg(ptr,x)							     \
   ({									     \
      __typeof__(*(ptr)) _x_ = (x);					     \
      (__typeof__(*(ptr))) __xchg((ptr), (unsigned long)_x_, sizeof(*(ptr))); \
   })
 
+#define xchg_local(ptr,x)						     \
+  ({									     \
+     __typeof__(*(ptr)) _x_ = (x);					     \
+     (__typeof__(*(ptr))) __xchg_local((ptr),				     \
+     		(unsigned long)_x_, sizeof(*(ptr))); 			     \
+  })
+
 #define tas(ptr) (xchg((ptr),1))
 
 /*
@@ -305,6 +365,28 @@ __cmpxchg_u32(volatile unsigned int *p, unsigned long old, unsigned long new)
 	return prev;
 }
 
+static __inline__ unsigned long
+__cmpxchg_u32_local(volatile unsigned int *p, unsigned long old,
+			unsigned long new)
+{
+	unsigned int prev;
+
+	__asm__ __volatile__ (
+"1:	lwarx	%0,0,%2		# __cmpxchg_u32\n\
+	cmpw	0,%0,%3\n\
+	bne-	2f\n"
+	PPC405_ERR77(0,%2)
+"	stwcx.	%4,0,%2\n\
+	bne-	1b"
+	"\n\
+2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+
 #ifdef CONFIG_PPC64
 static __inline__ unsigned long
 __cmpxchg_u64(volatile unsigned long *p, unsigned long old, unsigned long new)
@@ -327,6 +409,27 @@ __cmpxchg_u64(volatile unsigned long *p, unsigned long old, unsigned long new)
 
 	return prev;
 }
+
+static __inline__ unsigned long
+__cmpxchg_u64_local(volatile unsigned long *p, unsigned long old,
+			unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__ (
+"1:	ldarx	%0,0,%2		# __cmpxchg_u64\n\
+	cmpd	0,%0,%3\n\
+	bne-	2f\n\
+	stdcx.	%4,0,%2\n\
+	bne-	1b"
+	"\n\
+2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
 #endif
 
 /* This function doesn't exist, so you'll get a linker error
@@ -349,6 +452,22 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new,
 	return old;
 }
 
+static __inline__ unsigned long
+__cmpxchg_local(volatile void *ptr, unsigned long old, unsigned long new,
+	  unsigned int size)
+{
+	switch (size) {
+	case 4:
+		return __cmpxchg_u32_local(ptr, old, new);
+#ifdef CONFIG_PPC64
+	case 8:
+		return __cmpxchg_u64_local(ptr, old, new);
+#endif
+	}
+	__cmpxchg_called_with_bad_pointer();
+	return old;
+}
+
 #define cmpxchg(ptr,o,n)						 \
   ({									 \
      __typeof__(*(ptr)) _o_ = (o);					 \
@@ -357,6 +476,15 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new,
 				    (unsigned long)_n_, sizeof(*(ptr))); \
   })
 
+
+#define cmpxchg_local(ptr,o,n)						 \
+  ({									 \
+     __typeof__(*(ptr)) _o_ = (o);					 \
+     __typeof__(*(ptr)) _n_ = (n);					 \
+     (__typeof__(*(ptr))) __cmpxchg_local((ptr), (unsigned long)_o_,	 \
+				    (unsigned long)_n_, sizeof(*(ptr))); \
+  })
+
 #ifdef CONFIG_PPC64
 /*
  * We handle most unaligned accesses in hardware. On the other hand 

Re: [PATCH 07/10] local_t : powerpc extension

[Andrew Morton]

On Sun, 11 Feb 2007 14:18:12 -0500 Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> wrote:

> local_t : powerpc extension

This diff contains changes which are also present in "[PATCH 07/10]
atomic.h : Add atomic64 cmpxchg, xchg and add_unless to powerpc", resulting
in rather a mess.

I dropped the duplicated hunks from the later patch rather than this one,
but I haven't tried to compile the result yet.

Re: [PATCH 07/10] local_t : powerpc extension

[Mathieu Desnoyers]

* Andrew Morton (akpm@linux-foundation.org) wrote:
> On Sun, 11 Feb 2007 14:18:12 -0500 Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> wrote:
> 
> > local_t : powerpc extension
> 
> This diff contains changes which are also present in "[PATCH 07/10]
> atomic.h : Add atomic64 cmpxchg, xchg and add_unless to powerpc", resulting
> in rather a mess.
> 
> I dropped the duplicated hunks from the later patch rather than this one,
> but I haven't tried to compile the result yet.
> 

Yes, sorry about that : the atomic.h diff has been duplicated in both
the local and atomic changes.

The change to system.h for local.h is to add the xchg_local and
cmpxchg_local, while the change for atomic.h is to simply remove the
#include <asm/atomic.h> from system.h.

Here is a proper local.h diff, if it happens to become necessary, but
simply removing the duplicated asm-powerpc/system.h hunks will be ok.

Thanks,

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

--- a/include/asm-powerpc/local.h
+++ b/include/asm-powerpc/local.h
@@ -1 +1,342 @@
-#include <asm-generic/local.h>
+#ifndef _ARCH_POWERPC_LOCAL_H
+#define _ARCH_POWERPC_LOCAL_H
+
+#include <linux/percpu.h>
+#include <asm/atomic.h>
+
+typedef struct
+{
+	atomic_long_t a;
+} local_t;
+
+#define LOCAL_INIT(i)	{ ATOMIC_LONG_INIT(i) }
+
+#define local_read(l)	atomic_long_read(&(l)->a)
+#define local_set(l,i)	atomic_long_set(&(l)->a, (i))
+
+#define local_add(i,l)	atomic_long_add((i),(&(l)->a))
+#define local_sub(i,l)	atomic_long_sub((i),(&(l)->a))
+#define local_inc(l)	atomic_long_inc(&(l)->a)
+#define local_dec(l)	atomic_long_dec(&(l)->a)
+
+#ifndef __powerpc64__
+
+static __inline__ int local_add_return(int a, local_t *l)
+{
+	int t;
+
+	__asm__ __volatile__(
+"1:	lwarx	%0,0,%2		# local_add_return\n\
+	add	%0,%1,%0\n"
+	PPC405_ERR77(0,%2)
+"	stwcx.	%0,0,%2 \n\
+	bne-	1b"
+	: "=&r" (t)
+	: "r" (a), "r" (&(l->a.counter))
+	: "cc", "memory");
+
+	return t;
+}
+
+#define local_add_negative(a, l)	(local_add_return((a), (l)) < 0)
+
+static __inline__ int local_sub_return(int a, local_t *l)
+{
+	int t;
+
+	__asm__ __volatile__(
+"1:	lwarx	%0,0,%2		# local_sub_return\n\
+	subf	%0,%1,%0\n"
+	PPC405_ERR77(0,%2)
+"	stwcx.	%0,0,%2 \n\
+	bne-	1b"
+	: "=&r" (t)
+	: "r" (a), "r" (&(l->a.counter))
+	: "cc", "memory");
+
+	return t;
+}
+
+static __inline__ int local_inc_return(local_t *l)
+{
+	int t;
+
+	__asm__ __volatile__(
+"1:	lwarx	%0,0,%1		# local_inc_return\n\
+	addic	%0,%0,1\n"
+	PPC405_ERR77(0,%1)
+"	stwcx.	%0,0,%1 \n\
+	bne-	1b"
+	: "=&r" (t)
+	: "r" (&(l->a.counter))
+	: "cc", "memory");
+
+	return t;
+}
+
+/*
+ * local_inc_and_test - increment and test
+ * @l: pointer of type local_t
+ *
+ * Atomically increments @l by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+#define local_inc_and_test(l) (local_inc_return(l) == 0)
+
+static __inline__ int local_dec_return(local_t *l)
+{
+	int t;
+
+	__asm__ __volatile__(
+"1:	lwarx	%0,0,%1		# local_dec_return\n\
+	addic	%0,%0,-1\n"
+	PPC405_ERR77(0,%1)
+"	stwcx.	%0,0,%1\n\
+	bne-	1b"
+	: "=&r" (t)
+	: "r" (&(l->a.counter))
+	: "cc", "memory");
+
+	return t;
+}
+
+#define local_cmpxchg(l, o, n) \
+	(cmpxchg_local(&((l)->a.counter), (o), (n)))
+#define local_xchg(l, n) (xchg_local(&((l)->a.counter), (n)))
+
+/**
+ * local_add_unless - add unless the number is a given value
+ * @l: pointer of type local_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @l, so long as it was not @u.
+ * Returns non-zero if @l was not @u, and zero otherwise.
+ */
+static __inline__ int local_add_unless(local_t *l, int a, int u)
+{
+	int t;
+
+	__asm__ __volatile__ (
+"1:	lwarx	%0,0,%1		# local_add_unless\n\
+	cmpw	0,%0,%3 \n\
+	beq-	2f \n\
+	add	%0,%2,%0 \n"
+	PPC405_ERR77(0,%2)
+"	stwcx.	%0,0,%1 \n\
+	bne-	1b \n"
+"	subf	%0,%2,%0 \n\
+2:"
+	: "=&r" (t)
+	: "r" (&(l->a.counter)), "r" (a), "r" (u)
+	: "cc", "memory");
+
+	return t != u;
+}
+
+#define local_inc_not_zero(l) local_add_unless((l), 1, 0)
+
+#define local_sub_and_test(a, l)	(local_sub_return((a), (l)) == 0)
+#define local_dec_and_test(l)		(local_dec_return((l)) == 0)
+
+/*
+ * Atomically test *l and decrement if it is greater than 0.
+ * The function returns the old value of *l minus 1.
+ */
+static __inline__ int local_dec_if_positive(local_t *l)
+{
+	int t;
+
+	__asm__ __volatile__(
+"1:	lwarx	%0,0,%1		# local_dec_if_positive\n\
+	cmpwi	%0,1\n\
+	addi	%0,%0,-1\n\
+	blt-	2f\n"
+	PPC405_ERR77(0,%1)
+"	stwcx.	%0,0,%1\n\
+	bne-	1b"
+	"\n\
+2:"	: "=&b" (t)
+	: "r" (&(l->a.counter))
+	: "cc", "memory");
+
+	return t;
+}
+
+#else /* __powerpc64__ */
+
+static __inline__ long local_add_return(long a, local_t *l)
+{
+	long t;
+
+	__asm__ __volatile__(
+"1:	ldarx	%0,0,%2		# local_add_return\n\
+	add	%0,%1,%0\n\
+	stdcx.	%0,0,%2 \n\
+	bne-	1b"
+	: "=&r" (t)
+	: "r" (a), "r" (&(l->a.counter))
+	: "cc", "memory");
+
+	return t;
+}
+
+#define local_add_negative(a, l)	(local_add_return((a), (l)) < 0)
+
+static __inline__ long local_sub_return(long a, local_t *l)
+{
+	long t;
+
+	__asm__ __volatile__(
+"1:	ldarx	%0,0,%2		# local_sub_return\n\
+	subf	%0,%1,%0\n\
+	stdcx.	%0,0,%2 \n\
+	bne-	1b"
+	: "=&r" (t)
+	: "r" (a), "r" (&(l->a.counter))
+	: "cc", "memory");
+
+	return t;
+}
+
+static __inline__ long local_inc_return(local_t *l)
+{
+	long t;
+
+	__asm__ __volatile__(
+"1:	ldarx	%0,0,%1		# local_inc_return\n\
+	addic	%0,%0,1\n\
+	stdcx.	%0,0,%1 \n\
+	bne-	1b"
+	: "=&r" (t)
+	: "r" (&(l->a.counter))
+	: "cc", "memory");
+
+	return t;
+}
+
+/*
+ * local_inc_and_test - increment and test
+ * @l: pointer of type local_t
+ *
+ * Atomically increments @l by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+#define local_inc_and_test(l) (local_inc_return(l) == 0)
+
+static __inline__ long local_dec_return(local_t *l)
+{
+	long t;
+
+	__asm__ __volatile__(
+"1:	ldarx	%0,0,%1		# local_dec_return\n\
+	addic	%0,%0,-1\n\
+	stdcx.	%0,0,%1\n\
+	bne-	1b"
+	: "=&r" (t)
+	: "r" (&(l->a.counter))
+	: "cc", "memory");
+
+	return t;
+}
+
+#define local_sub_and_test(a, l)	(local_sub_return((a), (l)) == 0)
+#define local_dec_and_test(l)	(local_dec_return((l)) == 0)
+
+/*
+ * Atomically test *l and decrement if it is greater than 0.
+ * The function returns the old value of *l minus 1.
+ */
+static __inline__ long local_dec_if_positive(local_t *l)
+{
+	long t;
+
+	__asm__ __volatile__(
+"1:	ldarx	%0,0,%1		# local_dec_if_positive\n\
+	addic.	%0,%0,-1\n\
+	blt-	2f\n\
+	stdcx.	%0,0,%1\n\
+	bne-	1b"
+	"\n\
+2:"	: "=&r" (t)
+	: "r" (&(l->a.counter))
+	: "cc", "memory");
+
+	return t;
+}
+
+#define local_cmpxchg(l, o, n) \
+	((long)cmpxchg_local(&((l)->a.counter), (o), (n)))
+#define local_xchg(l, (n)) (xchg_local(&((l)->a.counter), (n)))
+
+/**
+ * local_add_unless - add unless the number is a given value
+ * @l: pointer of type local_t
+ * @a: the amount to add to l...
+ * @u: ...unless l is equal to u.
+ *
+ * Atomically adds @a to @l, so long as it was not @u.
+ * Returns non-zero if @l was not @u, and zero otherwise.
+ */
+static __inline__ int local_add_unless(local_t *l, long a, long u)
+{
+	long t;
+
+	__asm__ __volatile__ (
+"1:	ldarx	%0,0,%1		# local_add_unless\n\
+	cmpd	0,%0,%3 \n\
+	beq-	2f \n\
+	add	%0,%2,%0 \n"
+"	stdcx.	%0,0,%1 \n\
+	bne-	1b \n"
+"	subf	%0,%2,%0 \n\
+2:"
+	: "=&r" (t)
+	: "r" (&(l->a.counter)), "r" (a), "r" (u)
+	: "cc", "memory");
+
+	return t != u;
+}
+
+#define local_inc_not_zero(l) local_add_unless((l), 1, 0)
+
+#endif /* !__powerpc64__ */
+
+/* Use these for per-cpu local_t variables: on some archs they are
+ * much more efficient than these naive implementations.  Note they take
+ * a variable, not an address.
+ */
+
+#define __local_inc(l)		((l)->a.counter++)
+#define __local_dec(l)		((l)->a.counter++)
+#define __local_add(i,l)	((l)->a.counter+=(i))
+#define __local_sub(i,l)	((l)->a.counter-=(i))
+
+/* Need to disable preemption for the cpu local counters otherwise we could
+   still access a variable of a previous CPU in a non atomic way. */
+#define cpu_local_wrap_v(l)	 	\
+	({ local_t res__;		\
+	   preempt_disable(); 		\
+	   res__ = (l);			\
+	   preempt_enable();		\
+	   res__; })
+#define cpu_local_wrap(l)		\
+	({ preempt_disable();		\
+	   l;				\
+	   preempt_enable(); })		\
+
+#define cpu_local_read(l)    cpu_local_wrap_v(local_read(&__get_cpu_var(l)))
+#define cpu_local_set(l, i)  cpu_local_wrap(local_set(&__get_cpu_var(l), (i)))
+#define cpu_local_inc(l)     cpu_local_wrap(local_inc(&__get_cpu_var(l)))
+#define cpu_local_dec(l)     cpu_local_wrap(local_dec(&__get_cpu_var(l)))
+#define cpu_local_add(i, l)  cpu_local_wrap(local_add((i), &__get_cpu_var(l)))
+#define cpu_local_sub(i, l)  cpu_local_wrap(local_sub((i), &__get_cpu_var(l)))
+
+#define __cpu_local_inc(l)	cpu_local_inc(l)
+#define __cpu_local_dec(l)	cpu_local_dec(l)
+#define __cpu_local_add(i, l)	cpu_local_add((i), (l))
+#define __cpu_local_sub(i, l)	cpu_local_sub((i), (l))
+
+#endif /* _ARCH_POWERPC_LOCAL_H */
-- 
Mathieu Desnoyers
Computer Engineering Ph.D. Candidate, École Polytechnique de Montréal
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F  BA06 3F25 A8FE 3BAE 9A68

Re: [PATCH 07/10] local_t : powerpc extension

[Kumar Gala]

On Feb 15, 2007, at 1:20 AM, Mathieu Desnoyers wrote:

> * Andrew Morton (akpm@linux-foundation.org) wrote:
>> On Sun, 11 Feb 2007 14:18:12 -0500 Mathieu Desnoyers  
>> <mathieu.desnoyers@polymtl.ca> wrote:
>>
>>> local_t : powerpc extension
>>
>> This diff contains changes which are also present in "[PATCH 07/10]
>> atomic.h : Add atomic64 cmpxchg, xchg and add_unless to powerpc",  
>> resulting
>> in rather a mess.
>>
>> I dropped the duplicated hunks from the later patch rather than  
>> this one,
>> but I haven't tried to compile the result yet.
>>
>
> Yes, sorry about that : the atomic.h diff has been duplicated in both
> the local and atomic changes.
>
> The change to system.h for local.h is to add the xchg_local and
> cmpxchg_local, while the change for atomic.h is to simply remove the
> #include <asm/atomic.h> from system.h.
>
> Here is a proper local.h diff, if it happens to become necessary, but
> simply removing the duplicated asm-powerpc/system.h hunks will be ok.
>
> Thanks,
>
> Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
>
> --- a/include/asm-powerpc/local.h
> +++ b/include/asm-powerpc/local.h
> @@ -1 +1,342 @@
> -#include <asm-generic/local.h>
> +#ifndef _ARCH_POWERPC_LOCAL_H
> +#define _ARCH_POWERPC_LOCAL_H
> +
> +#include <linux/percpu.h>
> +#include <asm/atomic.h>
> +
> +typedef struct
> +{
> +	atomic_long_t a;
> +} local_t;
> +
> +#define LOCAL_INIT(i)	{ ATOMIC_LONG_INIT(i) }
> +
> +#define local_read(l)	atomic_long_read(&(l)->a)
> +#define local_set(l,i)	atomic_long_set(&(l)->a, (i))
> +
> +#define local_add(i,l)	atomic_long_add((i),(&(l)->a))
> +#define local_sub(i,l)	atomic_long_sub((i),(&(l)->a))
> +#define local_inc(l)	atomic_long_inc(&(l)->a)
> +#define local_dec(l)	atomic_long_dec(&(l)->a)
> +
> +#ifndef __powerpc64__
> +
> +static __inline__ int local_add_return(int a, local_t *l)
> +{

is there a reason this isn't local_add_return(long a, local_t *l) on  
ppc32?

(same comment for other functions)

- k

Re: [PATCH] local_t : powerpc extension - use long for powerpc32

[Mathieu Desnoyers]

* Kumar Gala (galak@kernel.crashing.org) wrote:
> is there a reason this isn't local_add_return(long a, local_t *l) on  
> ppc32?
> 
> (same comment for other functions)
> 
> - k

no, except that we use the code is taken from atomic.h and used an
int parameter. However, due to the semantics of local_t, we should
manipulate longs instead of ints, even if they are the same size on a
given architecture (ppc32 and mips32 are affectec by this).

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

--- a/include/asm-powerpc/local.h
+++ b/include/asm-powerpc/local.h
@@ -21,9 +21,9 @@ typedef struct
 
 #ifndef __powerpc64__
 
-static __inline__ int local_add_return(int a, local_t *l)
+static __inline__ long local_add_return(long a, local_t *l)
 {
-	int t;
+	long t;
 
 	__asm__ __volatile__(
 "1:	lwarx	%0,0,%2		# local_add_return\n\
@@ -40,9 +40,9 @@ static __inline__ int local_add_return(int a, local_t *l)
 
 #define local_add_negative(a, l)	(local_add_return((a), (l)) < 0)
 
-static __inline__ int local_sub_return(int a, local_t *l)
+static __inline__ long local_sub_return(long a, local_t *l)
 {
-	int t;
+	long t;
 
 	__asm__ __volatile__(
 "1:	lwarx	%0,0,%2		# local_sub_return\n\
@@ -57,9 +57,9 @@ static __inline__ int local_sub_return(int a, local_t *l)
 	return t;
 }
 
-static __inline__ int local_inc_return(local_t *l)
+static __inline__ long local_inc_return(local_t *l)
 {
-	int t;
+	long t;
 
 	__asm__ __volatile__(
 "1:	lwarx	%0,0,%1		# local_inc_return\n\
@@ -84,9 +84,9 @@ static __inline__ int local_inc_return(local_t *l)
  */
 #define local_inc_and_test(l) (local_inc_return(l) == 0)
 
-static __inline__ int local_dec_return(local_t *l)
+static __inline__ long local_dec_return(local_t *l)
 {
-	int t;
+	long t;
 
 	__asm__ __volatile__(
 "1:	lwarx	%0,0,%1		# local_dec_return\n\
@@ -114,9 +114,9 @@ static __inline__ int local_dec_return(local_t *l)
  * Atomically adds @a to @l, so long as it was not @u.
  * Returns non-zero if @l was not @u, and zero otherwise.
  */
-static __inline__ int local_add_unless(local_t *l, int a, int u)
+static __inline__ int local_add_unless(local_t *l, long a, long u)
 {
-	int t;
+	long t;
 
 	__asm__ __volatile__ (
 "1:	lwarx	%0,0,%1		# local_add_unless\n\
@@ -144,9 +144,9 @@ static __inline__ int local_add_unless(local_t *l, int a, int u)
  * Atomically test *l and decrement if it is greater than 0.
  * The function returns the old value of *l minus 1.
  */
-static __inline__ int local_dec_if_positive(local_t *l)
+static __inline__ long local_dec_if_positive(local_t *l)
 {
-	int t;
+	long t;
 
 	__asm__ __volatile__(
 "1:	lwarx	%0,0,%1		# local_dec_if_positive\n\
-- 
Mathieu Desnoyers
Computer Engineering Ph.D. Candidate, École Polytechnique de Montréal
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F  BA06 3F25 A8FE 3BAE 9A68

Re: [PATCH] local_t : powerpc extension - use long for powerpc32

[Kumar Gala]

On Feb 15, 2007, at 2:02 PM, Mathieu Desnoyers wrote:

> * Kumar Gala (galak@kernel.crashing.org) wrote:
>> is there a reason this isn't local_add_return(long a, local_t *l) on
>> ppc32?
>>
>> (same comment for other functions)
>>
>> - k
>
> no, except that we use the code is taken from atomic.h and used an
> int parameter. However, due to the semantics of local_t, we should
> manipulate longs instead of ints, even if they are the same size on a
> given architecture (ppc32 and mips32 are affectec by this).
>
> Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Right, this means we can simply for ppc version down to:

+static __inline__ int local_add_return(int a, local_t *l)
+{
+	int t;
+
+	__asm__ __volatile__(
+"1:	PPC_LLARX	%0,0,%2		# local_add_return\n\
+	add	%0,%1,%0\n"
+	PPC405_ERR77(0,%2)
+"	PPC_STLCX	%0,0,%2 \n\
+	bne-	1b"
+	: "=&r" (t)
+	: "r" (a), "r" (&(l->a.counter))
+	: "cc", "memory");
+
+	return t;
+}

and that should work for both ppc32 & ppc64 and removes the  
duplication between the two.

- k

Re: [PATCH] local_t : powerpc extension - use long for powerpc32

[Mathieu Desnoyers]

* Kumar Gala (galak@kernel.crashing.org) wrote:
> 
> On Feb 15, 2007, at 2:02 PM, Mathieu Desnoyers wrote:
> 
> >* Kumar Gala (galak@kernel.crashing.org) wrote:
> >>is there a reason this isn't local_add_return(long a, local_t *l) on
> >>ppc32?
> >>
> >>(same comment for other functions)
> >>
> >>- k
> >
> >no, except that we use the code is taken from atomic.h and used an
> >int parameter. However, due to the semantics of local_t, we should
> >manipulate longs instead of ints, even if they are the same size on a
> >given architecture (ppc32 and mips32 are affectec by this).
> >
> >Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
> 
> Right, this means we can simply for ppc version down to:
> 
> +static __inline__ int local_add_return(int a, local_t *l)
> +{
> +	int t;
> +
> +	__asm__ __volatile__(
> +"1:	PPC_LLARX	%0,0,%2		# local_add_return\n\
> +	add	%0,%1,%0\n"
> +	PPC405_ERR77(0,%2)
> +"	PPC_STLCX	%0,0,%2 \n\
what about the dot after stwcx ? (stwcx.) ? Is it no longer required ?

> +	bne-	1b"
> +	: "=&r" (t)
> +	: "r" (a), "r" (&(l->a.counter))
> +	: "cc", "memory");
> +
> +	return t;
> +}
> 
> and that should work for both ppc32 & ppc64 and removes the  
> duplication between the two.
> 
> - k
> 

-- 
Mathieu Desnoyers
Computer Engineering Ph.D. Candidate, École Polytechnique de Montréal
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F  BA06 3F25 A8FE 3BAE 9A68

Re: [PATCH] local_t : powerpc extension - use long for powerpc32

[Kumar Gala]

On Feb 15, 2007, at 3:23 PM, Mathieu Desnoyers wrote:

> * Kumar Gala (galak@kernel.crashing.org) wrote:
>>
>> On Feb 15, 2007, at 2:02 PM, Mathieu Desnoyers wrote:
>>
>>> * Kumar Gala (galak@kernel.crashing.org) wrote:
>>>> is there a reason this isn't local_add_return(long a, local_t  
>>>> *l) on
>>>> ppc32?
>>>>
>>>> (same comment for other functions)
>>>>
>>>> - k
>>>
>>> no, except that we use the code is taken from atomic.h and used an
>>> int parameter. However, due to the semantics of local_t, we should
>>> manipulate longs instead of ints, even if they are the same size  
>>> on a
>>> given architecture (ppc32 and mips32 are affectec by this).
>>>
>>> Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
>>
>> Right, this means we can simply for ppc version down to:
>>
>> +static __inline__ int local_add_return(int a, local_t *l)
>> +{
>> +	int t;
>> +
>> +	__asm__ __volatile__(
>> +"1:	PPC_LLARX	%0,0,%2		# local_add_return\n\
>> +	add	%0,%1,%0\n"
>> +	PPC405_ERR77(0,%2)
>> +"	PPC_STLCX	%0,0,%2 \n\
> what about the dot after stwcx ? (stwcx.) ? Is it no longer required ?

Its implied, PPC_LLARX and PPC_STLCW are #defines that expand to  
proper instructions.

(look in include/asm-powerpc/asm-compat.h) for the defines.

Also, the PPC405_ERR77 will preprocess out on ppc64 if you were  
concerned.

- k

Re: [PATCH] local_t : powerpc extension - use long for powerpc32

[Mathieu Desnoyers]

Please forget about my last email :

#define PPC_STLCX       stringify_in_c(stdcx.)
and
#define PPC_STLCX       stringify_in_c(stwcx.)

are self explaining. :)

Mathieu

* Kumar Gala (galak@kernel.crashing.org) wrote:
> 
> On Feb 15, 2007, at 2:02 PM, Mathieu Desnoyers wrote:
> 
> >* Kumar Gala (galak@kernel.crashing.org) wrote:
> >>is there a reason this isn't local_add_return(long a, local_t *l) on
> >>ppc32?
> >>
> >>(same comment for other functions)
> >>
> >>- k
> >
> >no, except that we use the code is taken from atomic.h and used an
> >int parameter. However, due to the semantics of local_t, we should
> >manipulate longs instead of ints, even if they are the same size on a
> >given architecture (ppc32 and mips32 are affectec by this).
> >
> >Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
> 
> Right, this means we can simply for ppc version down to:
> 
> +static __inline__ int local_add_return(int a, local_t *l)
> +{
> +	int t;
> +
> +	__asm__ __volatile__(
> +"1:	PPC_LLARX	%0,0,%2		# local_add_return\n\
> +	add	%0,%1,%0\n"
> +	PPC405_ERR77(0,%2)
> +"	PPC_STLCX	%0,0,%2 \n\
> +	bne-	1b"
> +	: "=&r" (t)
> +	: "r" (a), "r" (&(l->a.counter))
> +	: "cc", "memory");
> +
> +	return t;
> +}
> 
> and that should work for both ppc32 & ppc64 and removes the  
> duplication between the two.
> 
> - k
> 

-- 
Mathieu Desnoyers
Computer Engineering Ph.D. Candidate, École Polytechnique de Montréal
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F  BA06 3F25 A8FE 3BAE 9A68

Re: [PATCH] local_t : powerpc extension - shrink powerpc local.h

[Mathieu Desnoyers]

local_t : powerpc extension - shrink powerpc local.h

By using PPC_LLARX and PPC_STLCX, we can cut in half the size of powerpc
local.h.

In applies on top of the local_t : powerpc extension - use long for powerpc32

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

--- a/include/asm-powerpc/local.h
+++ b/include/asm-powerpc/local.h
@@ -19,17 +19,15 @@ typedef struct
 #define local_inc(l)	atomic_long_inc(&(l)->a)
 #define local_dec(l)	atomic_long_dec(&(l)->a)
 
-#ifndef __powerpc64__
-
 static __inline__ long local_add_return(long a, local_t *l)
 {
 	long t;
 
 	__asm__ __volatile__(
-"1:	lwarx	%0,0,%2		# local_add_return\n\
+"1:"	PPC_LLARX	"%0,0,%2		# local_add_return\n\
 	add	%0,%1,%0\n"
 	PPC405_ERR77(0,%2)
-"	stwcx.	%0,0,%2 \n\
+	PPC_STLCX	"%0,0,%2 \n\
 	bne-	1b"
 	: "=&r" (t)
 	: "r" (a), "r" (&(l->a.counter))
@@ -45,10 +43,10 @@ static __inline__ long local_sub_return(long a, local_t *l)
 	long t;
 
 	__asm__ __volatile__(
-"1:	lwarx	%0,0,%2		# local_sub_return\n\
+"1:"	PPC_LLARX	"%0,0,%2		# local_sub_return\n\
 	subf	%0,%1,%0\n"
 	PPC405_ERR77(0,%2)
-"	stwcx.	%0,0,%2 \n\
+	PPC_STLCX	"%0,0,%2 \n\
 	bne-	1b"
 	: "=&r" (t)
 	: "r" (a), "r" (&(l->a.counter))
@@ -62,10 +60,10 @@ static __inline__ long local_inc_return(local_t *l)
 	long t;
 
 	__asm__ __volatile__(
-"1:	lwarx	%0,0,%1		# local_inc_return\n\
+"1:"	PPC_LLARX	"%0,0,%1		# local_inc_return\n\
 	addic	%0,%0,1\n"
 	PPC405_ERR77(0,%1)
-"	stwcx.	%0,0,%1 \n\
+	PPC_STLCX	"%0,0,%1 \n\
 	bne-	1b"
 	: "=&r" (t)
 	: "r" (&(l->a.counter))
@@ -89,10 +87,10 @@ static __inline__ long local_dec_return(local_t *l)
 	long t;
 
 	__asm__ __volatile__(
-"1:	lwarx	%0,0,%1		# local_dec_return\n\
+"1:"	PPC_LLARX	"%0,0,%1		# local_dec_return\n\
 	addic	%0,%0,-1\n"
 	PPC405_ERR77(0,%1)
-"	stwcx.	%0,0,%1\n\
+	PPC_STLCX	"%0,0,%1\n\
 	bne-	1b"
 	: "=&r" (t)
 	: "r" (&(l->a.counter))
@@ -119,12 +117,12 @@ static __inline__ int local_add_unless(local_t *l, long a, long u)
 	long t;
 
 	__asm__ __volatile__ (
-"1:	lwarx	%0,0,%1		# local_add_unless\n\
+"1:"	PPC_LLARX	"%0,0,%1		# local_add_unless\n\
 	cmpw	0,%0,%3 \n\
 	beq-	2f \n\
 	add	%0,%2,%0 \n"
 	PPC405_ERR77(0,%2)
-"	stwcx.	%0,0,%1 \n\
+	PPC_STLCX	"%0,0,%1 \n\
 	bne-	1b \n"
 "	subf	%0,%2,%0 \n\
 2:"
@@ -149,12 +147,12 @@ static __inline__ long local_dec_if_positive(local_t *l)
 	long t;
 
 	__asm__ __volatile__(
-"1:	lwarx	%0,0,%1		# local_dec_if_positive\n\
+"1:"	PPC_LLARX	"%0,0,%1		# local_dec_if_positive\n\
 	cmpwi	%0,1\n\
 	addi	%0,%0,-1\n\
 	blt-	2f\n"
 	PPC405_ERR77(0,%1)
-"	stwcx.	%0,0,%1\n\
+	PPC_STLCX	"%0,0,%1\n\
 	bne-	1b"
 	"\n\
 2:"	: "=&b" (t)
@@ -164,146 +162,6 @@ static __inline__ long local_dec_if_positive(local_t *l)
 	return t;
 }
 
-#else /* __powerpc64__ */
-
-static __inline__ long local_add_return(long a, local_t *l)
-{
-	long t;
-
-	__asm__ __volatile__(
-"1:	ldarx	%0,0,%2		# local_add_return\n\
-	add	%0,%1,%0\n\
-	stdcx.	%0,0,%2 \n\
-	bne-	1b"
-	: "=&r" (t)
-	: "r" (a), "r" (&(l->a.counter))
-	: "cc", "memory");
-
-	return t;
-}
-
-#define local_add_negative(a, l)	(local_add_return((a), (l)) < 0)
-
-static __inline__ long local_sub_return(long a, local_t *l)
-{
-	long t;
-
-	__asm__ __volatile__(
-"1:	ldarx	%0,0,%2		# local_sub_return\n\
-	subf	%0,%1,%0\n\
-	stdcx.	%0,0,%2 \n\
-	bne-	1b"
-	: "=&r" (t)
-	: "r" (a), "r" (&(l->a.counter))
-	: "cc", "memory");
-
-	return t;
-}
-
-static __inline__ long local_inc_return(local_t *l)
-{
-	long t;
-
-	__asm__ __volatile__(
-"1:	ldarx	%0,0,%1		# local_inc_return\n\
-	addic	%0,%0,1\n\
-	stdcx.	%0,0,%1 \n\
-	bne-	1b"
-	: "=&r" (t)
-	: "r" (&(l->a.counter))
-	: "cc", "memory");
-
-	return t;
-}
-
-/*
- * local_inc_and_test - increment and test
- * @l: pointer of type local_t
- *
- * Atomically increments @l by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define local_inc_and_test(l) (local_inc_return(l) == 0)
-
-static __inline__ long local_dec_return(local_t *l)
-{
-	long t;
-
-	__asm__ __volatile__(
-"1:	ldarx	%0,0,%1		# local_dec_return\n\
-	addic	%0,%0,-1\n\
-	stdcx.	%0,0,%1\n\
-	bne-	1b"
-	: "=&r" (t)
-	: "r" (&(l->a.counter))
-	: "cc", "memory");
-
-	return t;
-}
-
-#define local_sub_and_test(a, l)	(local_sub_return((a), (l)) == 0)
-#define local_dec_and_test(l)	(local_dec_return((l)) == 0)
-
-/*
- * Atomically test *l and decrement if it is greater than 0.
- * The function returns the old value of *l minus 1.
- */
-static __inline__ long local_dec_if_positive(local_t *l)
-{
-	long t;
-
-	__asm__ __volatile__(
-"1:	ldarx	%0,0,%1		# local_dec_if_positive\n\
-	addic.	%0,%0,-1\n\
-	blt-	2f\n\
-	stdcx.	%0,0,%1\n\
-	bne-	1b"
-	"\n\
-2:"	: "=&r" (t)
-	: "r" (&(l->a.counter))
-	: "cc", "memory");
-
-	return t;
-}
-
-#define local_cmpxchg(l, o, n) \
-	((long)cmpxchg_local(&((l)->a.counter), (o), (n)))
-#define local_xchg(l, (n)) (xchg_local(&((l)->a.counter), (n)))
-
-/**
- * local_add_unless - add unless the number is a given value
- * @l: pointer of type local_t
- * @a: the amount to add to l...
- * @u: ...unless l is equal to u.
- *
- * Atomically adds @a to @l, so long as it was not @u.
- * Returns non-zero if @l was not @u, and zero otherwise.
- */
-static __inline__ int local_add_unless(local_t *l, long a, long u)
-{
-	long t;
-
-	__asm__ __volatile__ (
-"1:	ldarx	%0,0,%1		# local_add_unless\n\
-	cmpd	0,%0,%3 \n\
-	beq-	2f \n\
-	add	%0,%2,%0 \n"
-"	stdcx.	%0,0,%1 \n\
-	bne-	1b \n"
-"	subf	%0,%2,%0 \n\
-2:"
-	: "=&r" (t)
-	: "r" (&(l->a.counter)), "r" (a), "r" (u)
-	: "cc", "memory");
-
-	return t != u;
-}
-
-#define local_inc_not_zero(l) local_add_unless((l), 1, 0)
-
-#endif /* !__powerpc64__ */
-
 /* Use these for per-cpu local_t variables: on some archs they are
  * much more efficient than these naive implementations.  Note they take
  * a variable, not an address.
-- 
Mathieu Desnoyers
Computer Engineering Ph.D. Candidate, École Polytechnique de Montréal
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F  BA06 3F25 A8FE 3BAE 9A68

[PATCH 08/10] local_t : s390 cleanup

[Mathieu Desnoyers]

local_t : s390 cleanup

s390 architecture local_t cleanup : use asm-generic/local.h.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

--- a/include/asm-s390/local.h
+++ b/include/asm-s390/local.h
@@ -1,58 +1 @@
-#ifndef _ASM_LOCAL_H
-#define _ASM_LOCAL_H
-
-#include <linux/percpu.h>
-#include <asm/atomic.h>
-
-#ifndef __s390x__
-
-typedef atomic_t local_t;
-
-#define LOCAL_INIT(i)	ATOMIC_INIT(i)
-#define local_read(v)	atomic_read(v)
-#define local_set(v,i)	atomic_set(v,i)
-
-#define local_inc(v)	atomic_inc(v)
-#define local_dec(v)	atomic_dec(v)
-#define local_add(i, v)	atomic_add(i, v)
-#define local_sub(i, v)	atomic_sub(i, v)
-
-#else
-
-typedef atomic64_t local_t;
-
-#define LOCAL_INIT(i)	ATOMIC64_INIT(i)
-#define local_read(v)	atomic64_read(v)
-#define local_set(v,i)	atomic64_set(v,i)
-
-#define local_inc(v)	atomic64_inc(v)
-#define local_dec(v)	atomic64_dec(v)
-#define local_add(i, v)	atomic64_add(i, v)
-#define local_sub(i, v)	atomic64_sub(i, v)
-
-#endif
-
-#define __local_inc(v)		((v)->counter++)
-#define __local_dec(v)		((v)->counter--)
-#define __local_add(i,v)	((v)->counter+=(i))
-#define __local_sub(i,v)	((v)->counter-=(i))
-
-/*
- * Use these for per-cpu local_t variables: on some archs they are
- * much more efficient than these naive implementations.  Note they take
- * a variable, not an address.
- */
-#define cpu_local_read(v)	local_read(&__get_cpu_var(v))
-#define cpu_local_set(v, i)	local_set(&__get_cpu_var(v), (i))
-
-#define cpu_local_inc(v)	local_inc(&__get_cpu_var(v))
-#define cpu_local_dec(v)	local_dec(&__get_cpu_var(v))
-#define cpu_local_add(i, v)	local_add((i), &__get_cpu_var(v))
-#define cpu_local_sub(i, v)	local_sub((i), &__get_cpu_var(v))
-
-#define __cpu_local_inc(v)	__local_inc(&__get_cpu_var(v))
-#define __cpu_local_dec(v)	__local_dec(&__get_cpu_var(v))
-#define __cpu_local_add(i, v)	__local_add((i), &__get_cpu_var(v))
-#define __cpu_local_sub(i, v)	__local_sub((i), &__get_cpu_var(v))
-
-#endif /* _ASM_LOCAL_H */
+#include <asm-generic/local.h>

[PATCH 09/10] local_t : sparc64 cleanup

[Mathieu Desnoyers]

local_t : sparc64 cleanup

sparc64 local_t cleanup : simply use asm-generic/local.h.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

--- a/include/asm-sparc64/local.h
+++ b/include/asm-sparc64/local.h
@@ -1,40 +1 @@
-#ifndef _ARCH_SPARC64_LOCAL_H
-#define _ARCH_SPARC64_LOCAL_H
-
-#include <linux/percpu.h>
-#include <asm/atomic.h>
-
-typedef atomic64_t local_t;
-
-#define LOCAL_INIT(i)	ATOMIC64_INIT(i)
-#define local_read(v)	atomic64_read(v)
-#define local_set(v,i)	atomic64_set(v,i)
-
-#define local_inc(v)	atomic64_inc(v)
-#define local_dec(v)	atomic64_dec(v)
-#define local_add(i, v)	atomic64_add(i, v)
-#define local_sub(i, v)	atomic64_sub(i, v)
-
-#define __local_inc(v)		((v)->counter++)
-#define __local_dec(v)		((v)->counter--)
-#define __local_add(i,v)	((v)->counter+=(i))
-#define __local_sub(i,v)	((v)->counter-=(i))
-
-/* Use these for per-cpu local_t variables: on some archs they are
- * much more efficient than these naive implementations.  Note they take
- * a variable, not an address.
- */
-#define cpu_local_read(v)	local_read(&__get_cpu_var(v))
-#define cpu_local_set(v, i)	local_set(&__get_cpu_var(v), (i))
-
-#define cpu_local_inc(v)	local_inc(&__get_cpu_var(v))
-#define cpu_local_dec(v)	local_dec(&__get_cpu_var(v))
-#define cpu_local_add(i, v)	local_add((i), &__get_cpu_var(v))
-#define cpu_local_sub(i, v)	local_sub((i), &__get_cpu_var(v))
-
-#define __cpu_local_inc(v)	__local_inc(&__get_cpu_var(v))
-#define __cpu_local_dec(v)	__local_dec(&__get_cpu_var(v))
-#define __cpu_local_add(i, v)	__local_add((i), &__get_cpu_var(v))
-#define __cpu_local_sub(i, v)	__local_sub((i), &__get_cpu_var(v))
-
-#endif /* _ARCH_SPARC64_LOCAL_H */
+#include <asm-generic/local.h>

[PATCH 10/10] local_t : x86_64 extension

[Mathieu Desnoyers]

local_t : x86_64 extension

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

--- a/include/asm-x86_64/local.h
+++ b/include/asm-x86_64/local.h
@@ -2,49 +2,183 @@
 #define _ARCH_X8664_LOCAL_H
 
 #include <linux/percpu.h>
+#include <asm/atomic.h>
 
 typedef struct
 {
-	volatile long counter;
+	atomic_long_t a;
 } local_t;
 
-#define LOCAL_INIT(i)	{ (i) }
+#define LOCAL_INIT(i)	{ ATOMIC_LONG_INIT(i) }
 
-#define local_read(v)	((v)->counter)
-#define local_set(v,i)	(((v)->counter) = (i))
+#define local_read(l)	atomic_long_read(&(l)->a)
+#define local_set(l,i)	atomic_long_set(&(l)->a, (i))
 
-static inline void local_inc(local_t *v)
+static inline void local_inc(local_t *l)
 {
 	__asm__ __volatile__(
 		"incq %0"
-		:"=m" (v->counter)
-		:"m" (v->counter));
+		:"=m" (l->a.counter)
+		:"m" (l->a.counter));
 }
 
-static inline void local_dec(local_t *v)
+static inline void local_dec(local_t *l)
 {
 	__asm__ __volatile__(
 		"decq %0"
-		:"=m" (v->counter)
-		:"m" (v->counter));
+		:"=m" (l->a.counter)
+		:"m" (l->a.counter));
 }
 
-static inline void local_add(long i, local_t *v)
+static inline void local_add(long i, local_t *l)
 {
 	__asm__ __volatile__(
 		"addq %1,%0"
-		:"=m" (v->counter)
-		:"ir" (i), "m" (v->counter));
+		:"=m" (l->a.counter)
+		:"ir" (i), "m" (l->a.counter));
 }
 
-static inline void local_sub(long i, local_t *v)
+static inline void local_sub(long i, local_t *l)
 {
 	__asm__ __volatile__(
 		"subq %1,%0"
-		:"=m" (v->counter)
-		:"ir" (i), "m" (v->counter));
+		:"=m" (l->a.counter)
+		:"ir" (i), "m" (l->a.counter));
 }
 
+/**
+ * local_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @l: pointer to type local_t
+ *
+ * Atomically subtracts @i from @l and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+static __inline__ int local_sub_and_test(long i, local_t *l)
+{
+	unsigned char c;
+
+	__asm__ __volatile__(
+		"subq %2,%0; sete %1"
+		:"=m" (l->a.counter), "=qm" (c)
+		:"ir" (i), "m" (l->a.counter) : "memory");
+	return c;
+}
+
+/**
+ * local_dec_and_test - decrement and test
+ * @l: pointer to type local_t
+ *
+ * Atomically decrements @l by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+static __inline__ int local_dec_and_test(local_t *l)
+{
+	unsigned char c;
+
+	__asm__ __volatile__(
+		"decq %0; sete %1"
+		:"=m" (l->a.counter), "=qm" (c)
+		:"m" (l->a.counter) : "memory");
+	return c != 0;
+}
+
+/**
+ * local_inc_and_test - increment and test
+ * @l: pointer to type local_t
+ *
+ * Atomically increments @l by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+static __inline__ int local_inc_and_test(local_t *l)
+{
+	unsigned char c;
+
+	__asm__ __volatile__(
+		"incq %0; sete %1"
+		:"=m" (l->a.counter), "=qm" (c)
+		:"m" (l->a.counter) : "memory");
+	return c != 0;
+}
+
+/**
+ * local_add_negative - add and test if negative
+ * @i: integer value to add
+ * @l: pointer to type local_t
+ *
+ * Atomically adds @i to @l and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
+ */
+static __inline__ int local_add_negative(long i, local_t *l)
+{
+	unsigned char c;
+
+	__asm__ __volatile__(
+		"addq %2,%0; sets %1"
+		:"=m" (l->a.counter), "=qm" (c)
+		:"ir" (i), "m" (l->a.counter) : "memory");
+	return c;
+}
+
+/**
+ * local_add_return - add and return
+ * @i: integer value to add
+ * @l: pointer to type local_t
+ *
+ * Atomically adds @i to @l and returns @i + @l
+ */
+static __inline__ long local_add_return(long i, local_t *l)
+{
+	long __i = i;
+	__asm__ __volatile__(
+		"xaddq %0, %1;"
+		:"+r" (i), "+m" (l->a.counter)
+		: : "memory");
+	return i + __i;
+}
+
+static __inline__ long local_sub_return(long i, local_t *l)
+{
+	return local_add_return(-i,l);
+}
+
+#define local_inc_return(l)  (local_add_return(1,l))
+#define local_dec_return(l)  (local_sub_return(1,l))
+
+#define local_cmpxchg(l, o, n) \
+	(cmpxchg_local(&((l)->a.counter), (o), (n)))
+/* Always has a lock prefix */
+#define local_xchg(l, n) (xchg(&((l)->a.counter), (n)))
+
+/**
+ * atomic_up_add_unless - add unless the number is a given value
+ * @l: pointer of type local_t
+ * @a: the amount to add to l...
+ * @u: ...unless l is equal to u.
+ *
+ * Atomically adds @a to @l, so long as it was not @u.
+ * Returns non-zero if @l was not @u, and zero otherwise.
+ */
+#define local_add_unless(l, a, u)				\
+({								\
+	long c, old;						\
+	c = local_read(l);					\
+	for (;;) {						\
+		if (unlikely(c == (u)))				\
+			break;					\
+		old = local_cmpxchg((l), c, c + (a));	\
+		if (likely(old == c))				\
+			break;					\
+		c = old;					\
+	}							\
+	c != (u);						\
+})
+#define local_inc_not_zero(l) local_add_unless((l), 1, 0)
+
 /* On x86-64 these are better than the atomic variants on SMP kernels
    because they dont use a lock prefix. */
 #define __local_inc(l)		local_inc(l)
@@ -62,27 +196,27 @@ static inline void local_sub(long i, local_t *v)
 
 /* Need to disable preemption for the cpu local counters otherwise we could
    still access a variable of a previous CPU in a non atomic way. */
-#define cpu_local_wrap_v(v)	 	\
+#define cpu_local_wrap_v(l)	 	\
 	({ local_t res__;		\
 	   preempt_disable(); 		\
-	   res__ = (v);			\
+	   res__ = (l);			\
 	   preempt_enable();		\
 	   res__; })
-#define cpu_local_wrap(v)		\
+#define cpu_local_wrap(l)		\
 	({ preempt_disable();		\
-	   v;				\
+	   l;				\
 	   preempt_enable(); })		\
 
-#define cpu_local_read(v)    cpu_local_wrap_v(local_read(&__get_cpu_var(v)))
-#define cpu_local_set(v, i)  cpu_local_wrap(local_set(&__get_cpu_var(v), (i)))
-#define cpu_local_inc(v)     cpu_local_wrap(local_inc(&__get_cpu_var(v)))
-#define cpu_local_dec(v)     cpu_local_wrap(local_dec(&__get_cpu_var(v)))
-#define cpu_local_add(i, v)  cpu_local_wrap(local_add((i), &__get_cpu_var(v)))
-#define cpu_local_sub(i, v)  cpu_local_wrap(local_sub((i), &__get_cpu_var(v)))
+#define cpu_local_read(l)    cpu_local_wrap_v(local_read(&__get_cpu_var(l)))
+#define cpu_local_set(l, i)  cpu_local_wrap(local_set(&__get_cpu_var(l), (i)))
+#define cpu_local_inc(l)     cpu_local_wrap(local_inc(&__get_cpu_var(l)))
+#define cpu_local_dec(l)     cpu_local_wrap(local_dec(&__get_cpu_var(l)))
+#define cpu_local_add(i, l)  cpu_local_wrap(local_add((i), &__get_cpu_var(l)))
+#define cpu_local_sub(i, l)  cpu_local_wrap(local_sub((i), &__get_cpu_var(l)))
 
-#define __cpu_local_inc(v)	cpu_local_inc(v)
-#define __cpu_local_dec(v)	cpu_local_dec(v)
-#define __cpu_local_add(i, v)	cpu_local_add((i), (v))
-#define __cpu_local_sub(i, v)	cpu_local_sub((i), (v))
+#define __cpu_local_inc(l)	cpu_local_inc(l)
+#define __cpu_local_dec(l)	cpu_local_dec(l)
+#define __cpu_local_add(i, l)	cpu_local_add((i), (l))
+#define __cpu_local_sub(i, l)	cpu_local_sub((i), (l))
 
-#endif /* _ARCH_I386_LOCAL_H */
+#endif /* _ARCH_X8664_LOCAL_H */
--- a/include/asm-x86_64/system.h
+++ b/include/asm-x86_64/system.h
@@ -209,9 +209,45 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 	return old;
 }
 
+static inline unsigned long __cmpxchg_local(volatile void *ptr,
+			unsigned long old, unsigned long new, int size)
+{
+	unsigned long prev;
+	switch (size) {
+	case 1:
+		__asm__ __volatile__("cmpxchgb %b1,%2"
+				     : "=a"(prev)
+				     : "q"(new), "m"(*__xg(ptr)), "0"(old)
+				     : "memory");
+		return prev;
+	case 2:
+		__asm__ __volatile__("cmpxchgw %w1,%2"
+				     : "=a"(prev)
+				     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+				     : "memory");
+		return prev;
+	case 4:
+		__asm__ __volatile__("cmpxchgl %k1,%2"
+				     : "=a"(prev)
+				     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+				     : "memory");
+		return prev;
+	case 8:
+		__asm__ __volatile__("cmpxchgq %1,%2"
+				     : "=a"(prev)
+				     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+				     : "memory");
+		return prev;
+	}
+	return old;
+}
+
 #define cmpxchg(ptr,o,n)\
 	((__typeof__(*(ptr)))__cmpxchg((ptr),(unsigned long)(o),\
 					(unsigned long)(n),sizeof(*(ptr))))
+#define cmpxchg_local(ptr,o,n)\
+	((__typeof__(*(ptr)))__cmpxchg((ptr),(unsigned long)(o),\
+					(unsigned long)(n),sizeof(*(ptr))))
 
 #ifdef CONFIG_SMP
 #define smp_mb()	mb()

[PATCH 00/10] local_t : adding and standardising local atomic primitives

[Mathieu Desnoyers]

local_t : adding and standardising local atomic primitives

These patches extend and standardise local_t operations on each architectures,
allowing a rich set of atomic operations to be done on per-cpu data with
minimal performance impact. On architectures where there seems to be no
difference between the SMP and UP operation (same memory barriers, same
LOCKing), local.h simply includes asm-generic/local.h, which removes duplicated
code from the current kernel tree.

These patches apply on 2.6.20-rc5-git4.
It depends on the patch "atomic.h : standardising atomic primitives"

Signed-off-by : Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

[PATCH 10/10] local_t : x86_64 extension

[Mathieu Desnoyers]

local_t : x86_64 extension

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
--- a/include/asm-x86_64/local.h
+++ b/include/asm-x86_64/local.h
@@ -2,49 +2,183 @@
 #define _ARCH_X8664_LOCAL_H
 
 #include <linux/percpu.h>
+#include <asm/atomic.h>
 
 typedef struct
 {
-	volatile long counter;
+	atomic_long_t a;
 } local_t;
 
-#define LOCAL_INIT(i)	{ (i) }
+#define LOCAL_INIT(i)	{ ATOMIC_LONG_INIT(i) }
 
-#define local_read(v)	((v)->counter)
-#define local_set(v,i)	(((v)->counter) = (i))
+#define local_read(l)	atomic_long_read(&(l)->a)
+#define local_set(l,i)	atomic_long_set(&(l)->a, (i))
 
-static inline void local_inc(local_t *v)
+static inline void local_inc(local_t *l)
 {
 	__asm__ __volatile__(
 		"incq %0"
-		:"=m" (v->counter)
-		:"m" (v->counter));
+		:"=m" (l->a.counter)
+		:"m" (l->a.counter));
 }
 
-static inline void local_dec(local_t *v)
+static inline void local_dec(local_t *l)
 {
 	__asm__ __volatile__(
 		"decq %0"
-		:"=m" (v->counter)
-		:"m" (v->counter));
+		:"=m" (l->a.counter)
+		:"m" (l->a.counter));
 }
 
-static inline void local_add(long i, local_t *v)
+static inline void local_add(long i, local_t *l)
 {
 	__asm__ __volatile__(
 		"addq %1,%0"
-		:"=m" (v->counter)
-		:"ir" (i), "m" (v->counter));
+		:"=m" (l->a.counter)
+		:"ir" (i), "m" (l->a.counter));
 }
 
-static inline void local_sub(long i, local_t *v)
+static inline void local_sub(long i, local_t *l)
 {
 	__asm__ __volatile__(
 		"subq %1,%0"
-		:"=m" (v->counter)
-		:"ir" (i), "m" (v->counter));
+		:"=m" (l->a.counter)
+		:"ir" (i), "m" (l->a.counter));
 }
 
+/**
+ * local_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @l: pointer to type local_t
+ *
+ * Atomically subtracts @i from @l and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+static __inline__ int local_sub_and_test(long i, local_t *l)
+{
+	unsigned char c;
+
+	__asm__ __volatile__(
+		"subq %2,%0; sete %1"
+		:"=m" (l->a.counter), "=qm" (c)
+		:"ir" (i), "m" (l->a.counter) : "memory");
+	return c;
+}
+
+/**
+ * local_dec_and_test - decrement and test
+ * @l: pointer to type local_t
+ *
+ * Atomically decrements @l by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+static __inline__ int local_dec_and_test(local_t *l)
+{
+	unsigned char c;
+
+	__asm__ __volatile__(
+		"decq %0; sete %1"
+		:"=m" (l->a.counter), "=qm" (c)
+		:"m" (l->a.counter) : "memory");
+	return c != 0;
+}
+
+/**
+ * local_inc_and_test - increment and test
+ * @l: pointer to type local_t
+ *
+ * Atomically increments @l by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+static __inline__ int local_inc_and_test(local_t *l)
+{
+	unsigned char c;
+
+	__asm__ __volatile__(
+		"incq %0; sete %1"
+		:"=m" (l->a.counter), "=qm" (c)
+		:"m" (l->a.counter) : "memory");
+	return c != 0;
+}
+
+/**
+ * local_add_negative - add and test if negative
+ * @i: integer value to add
+ * @l: pointer to type local_t
+ *
+ * Atomically adds @i to @l and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
+ */
+static __inline__ int local_add_negative(long i, local_t *l)
+{
+	unsigned char c;
+
+	__asm__ __volatile__(
+		"addq %2,%0; sets %1"
+		:"=m" (l->a.counter), "=qm" (c)
+		:"ir" (i), "m" (l->a.counter) : "memory");
+	return c;
+}
+
+/**
+ * local_add_return - add and return
+ * @i: integer value to add
+ * @l: pointer to type local_t
+ *
+ * Atomically adds @i to @l and returns @i + @l
+ */
+static __inline__ long local_add_return(long i, local_t *l)
+{
+	long __i = i;
+	__asm__ __volatile__(
+		"xaddq %0, %1;"
+		:"+r" (i), "+m" (l->a.counter)
+		: : "memory");
+	return i + __i;
+}
+
+static __inline__ long local_sub_return(long i, local_t *l)
+{
+	return local_add_return(-i,l);
+}
+
+#define local_inc_return(l)  (local_add_return(1,l))
+#define local_dec_return(l)  (local_sub_return(1,l))
+
+#define local_cmpxchg(l, o, n) \
+	((long)cmpxchg_local(&((l)->a.counter), (o), (n)))
+/* Always has a lock prefix anyway */
+#define local_xchg(l, new) (xchg(&((l)->a.counter), new))
+
+/**
+ * atomic_up_add_unless - add unless the number is a given value
+ * @l: pointer of type local_t
+ * @a: the amount to add to l...
+ * @u: ...unless l is equal to u.
+ *
+ * Atomically adds @a to @l, so long as it was not @u.
+ * Returns non-zero if @l was not @u, and zero otherwise.
+ */
+#define local_add_unless(l, a, u)				\
+({								\
+	long c, old;						\
+	c = local_read(l);					\
+	for (;;) {						\
+		if (unlikely(c == (u)))				\
+			break;					\
+		old = local_cmpxchg((l), c, c + (a));	\
+		if (likely(old == c))				\
+			break;					\
+		c = old;					\
+	}							\
+	c != (u);						\
+})
+#define local_inc_not_zero(l) local_add_unless((l), 1, 0)
+
 /* On x86-64 these are better than the atomic variants on SMP kernels
    because they dont use a lock prefix. */
 #define __local_inc(l)		local_inc(l)
@@ -62,27 +196,27 @@ static inline void local_sub(long i, local_t *v)
 
 /* Need to disable preemption for the cpu local counters otherwise we could
    still access a variable of a previous CPU in a non atomic way. */
-#define cpu_local_wrap_v(v)	 	\
+#define cpu_local_wrap_v(l)	 	\
 	({ local_t res__;		\
 	   preempt_disable(); 		\
-	   res__ = (v);			\
+	   res__ = (l);			\
 	   preempt_enable();		\
 	   res__; })
-#define cpu_local_wrap(v)		\
+#define cpu_local_wrap(l)		\
 	({ preempt_disable();		\
-	   v;				\
+	   l;				\
 	   preempt_enable(); })		\
 
-#define cpu_local_read(v)    cpu_local_wrap_v(local_read(&__get_cpu_var(v)))
-#define cpu_local_set(v, i)  cpu_local_wrap(local_set(&__get_cpu_var(v), (i)))
-#define cpu_local_inc(v)     cpu_local_wrap(local_inc(&__get_cpu_var(v)))
-#define cpu_local_dec(v)     cpu_local_wrap(local_dec(&__get_cpu_var(v)))
-#define cpu_local_add(i, v)  cpu_local_wrap(local_add((i), &__get_cpu_var(v)))
-#define cpu_local_sub(i, v)  cpu_local_wrap(local_sub((i), &__get_cpu_var(v)))
+#define cpu_local_read(l)    cpu_local_wrap_v(local_read(&__get_cpu_var(l)))
+#define cpu_local_set(l, i)  cpu_local_wrap(local_set(&__get_cpu_var(l), (i)))
+#define cpu_local_inc(l)     cpu_local_wrap(local_inc(&__get_cpu_var(l)))
+#define cpu_local_dec(l)     cpu_local_wrap(local_dec(&__get_cpu_var(l)))
+#define cpu_local_add(i, l)  cpu_local_wrap(local_add((i), &__get_cpu_var(l)))
+#define cpu_local_sub(i, l)  cpu_local_wrap(local_sub((i), &__get_cpu_var(l)))
 
-#define __cpu_local_inc(v)	cpu_local_inc(v)
-#define __cpu_local_dec(v)	cpu_local_dec(v)
-#define __cpu_local_add(i, v)	cpu_local_add((i), (v))
-#define __cpu_local_sub(i, v)	cpu_local_sub((i), (v))
+#define __cpu_local_inc(l)	cpu_local_inc(l)
+#define __cpu_local_dec(l)	cpu_local_dec(l)
+#define __cpu_local_add(i, l)	cpu_local_add((i), (l))
+#define __cpu_local_sub(i, l)	cpu_local_sub((i), (l))
 
-#endif /* _ARCH_I386_LOCAL_H */
+#endif /* _ARCH_X8664_LOCAL_H */
--- a/include/asm-x86_64/system.h
+++ b/include/asm-x86_64/system.h
@@ -209,9 +209,45 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 	return old;
 }
 
+static inline unsigned long __cmpxchg_local(volatile void *ptr,
+			unsigned long old, unsigned long new, int size)
+{
+	unsigned long prev;
+	switch (size) {
+	case 1:
+		__asm__ __volatile__("cmpxchgb %b1,%2"
+				     : "=a"(prev)
+				     : "q"(new), "m"(*__xg(ptr)), "0"(old)
+				     : "memory");
+		return prev;
+	case 2:
+		__asm__ __volatile__("cmpxchgw %w1,%2"
+				     : "=a"(prev)
+				     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+				     : "memory");
+		return prev;
+	case 4:
+		__asm__ __volatile__("cmpxchgl %k1,%2"
+				     : "=a"(prev)
+				     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+				     : "memory");
+		return prev;
+	case 8:
+		__asm__ __volatile__("cmpxchgq %1,%2"
+				     : "=a"(prev)
+				     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+				     : "memory");
+		return prev;
+	}
+	return old;
+}
+
 #define cmpxchg(ptr,o,n)\
 	((__typeof__(*(ptr)))__cmpxchg((ptr),(unsigned long)(o),\
 					(unsigned long)(n),sizeof(*(ptr))))
+#define cmpxchg_local(ptr,o,n)\
+	((__typeof__(*(ptr)))__cmpxchg((ptr),(unsigned long)(o),\
+					(unsigned long)(n),sizeof(*(ptr))))
 
 #ifdef CONFIG_SMP
 #define smp_mb()	mb()

[PATCH 00/10] local_t : adding and standardising local atomic primitives

[Mathieu Desnoyers]

local_t : adding and standardising local atomic primitives

These patches extend and standardise local_t operations on each architectures,
allowing a rich set of atomic operations to be done on per-cpu data with
minimal performance impact. On architectures where there seems to be no
difference between the SMP and UP operation (same memory barriers, same
LOCKing), local.h simply includes asm-generic/local.h, which removes duplicated
code from the current kernel tree.

These patches apply on 2.6.20-rc4-git3.
It depends on the patches "atomic.h : standardising atomic primitives"

Signed-off-by : Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

[PATCH 10/10] local_t : x86_64 extension

[Mathieu Desnoyers]

local_t : x86_64 extension

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

--- a/include/asm-x86_64/local.h
+++ b/include/asm-x86_64/local.h
@@ -2,49 +2,183 @@
 #define _ARCH_X8664_LOCAL_H
 
 #include <linux/percpu.h>
+#include <asm/atomic.h>
 
 typedef struct
 {
-	volatile long counter;
+	atomic_long_t a;
 } local_t;
 
-#define LOCAL_INIT(i)	{ (i) }
+#define LOCAL_INIT(i)	{ ATOMIC_LONG_INIT(i) }
 
-#define local_read(v)	((v)->counter)
-#define local_set(v,i)	(((v)->counter) = (i))
+#define local_read(l)	atomic_long_read(&(l)->a)
+#define local_set(l,i)	atomic_long_set(&(l)->a, (i))
 
-static inline void local_inc(local_t *v)
+static inline void local_inc(local_t *l)
 {
 	__asm__ __volatile__(
 		"incq %0"
-		:"=m" (v->counter)
-		:"m" (v->counter));
+		:"=m" (l->a.counter)
+		:"m" (l->a.counter));
 }
 
-static inline void local_dec(local_t *v)
+static inline void local_dec(local_t *l)
 {
 	__asm__ __volatile__(
 		"decq %0"
-		:"=m" (v->counter)
-		:"m" (v->counter));
+		:"=m" (l->a.counter)
+		:"m" (l->a.counter));
 }
 
-static inline void local_add(long i, local_t *v)
+static inline void local_add(long i, local_t *l)
 {
 	__asm__ __volatile__(
 		"addq %1,%0"
-		:"=m" (v->counter)
-		:"ir" (i), "m" (v->counter));
+		:"=m" (l->a.counter)
+		:"ir" (i), "m" (l->a.counter));
 }
 
-static inline void local_sub(long i, local_t *v)
+static inline void local_sub(long i, local_t *l)
 {
 	__asm__ __volatile__(
 		"subq %1,%0"
-		:"=m" (v->counter)
-		:"ir" (i), "m" (v->counter));
+		:"=m" (l->a.counter)
+		:"ir" (i), "m" (l->a.counter));
 }
 
+/**
+ * local_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @l: pointer to type local_t
+ *
+ * Atomically subtracts @i from @l and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+static __inline__ int local_sub_and_test(long i, local_t *l)
+{
+	unsigned char c;
+
+	__asm__ __volatile__(
+		"subq %2,%0; sete %1"
+		:"=m" (l->a.counter), "=qm" (c)
+		:"ir" (i), "m" (l->a.counter) : "memory");
+	return c;
+}
+
+/**
+ * local_dec_and_test - decrement and test
+ * @l: pointer to type local_t
+ *
+ * Atomically decrements @l by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+static __inline__ int local_dec_and_test(local_t *l)
+{
+	unsigned char c;
+
+	__asm__ __volatile__(
+		"decq %0; sete %1"
+		:"=m" (l->a.counter), "=qm" (c)
+		:"m" (l->a.counter) : "memory");
+	return c != 0;
+}
+
+/**
+ * local_inc_and_test - increment and test
+ * @l: pointer to type local_t
+ *
+ * Atomically increments @l by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+static __inline__ int local_inc_and_test(local_t *l)
+{
+	unsigned char c;
+
+	__asm__ __volatile__(
+		"incq %0; sete %1"
+		:"=m" (l->a.counter), "=qm" (c)
+		:"m" (l->a.counter) : "memory");
+	return c != 0;
+}
+
+/**
+ * local_add_negative - add and test if negative
+ * @i: integer value to add
+ * @l: pointer to type local_t
+ *
+ * Atomically adds @i to @l and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
+ */
+static __inline__ int local_add_negative(long i, local_t *l)
+{
+	unsigned char c;
+
+	__asm__ __volatile__(
+		"addq %2,%0; sets %1"
+		:"=m" (l->a.counter), "=qm" (c)
+		:"ir" (i), "m" (l->a.counter) : "memory");
+	return c;
+}
+
+/**
+ * local_add_return - add and return
+ * @i: integer value to add
+ * @l: pointer to type local_t
+ *
+ * Atomically adds @i to @l and returns @i + @l
+ */
+static __inline__ long local_add_return(long i, local_t *l)
+{
+	long __i = i;
+	__asm__ __volatile__(
+		"xaddq %0, %1;"
+		:"+r" (i), "+m" (l->a.counter)
+		: : "memory");
+	return i + __i;
+}
+
+static __inline__ long local_sub_return(long i, local_t *l)
+{
+	return local_add_return(-i,l);
+}
+
+#define local_inc_return(l)  (local_add_return(1,l))
+#define local_dec_return(l)  (local_sub_return(1,l))
+
+#define local_cmpxchg(l, o, n) \
+	((long)cmpxchg_local(&((l)->a.counter), (o), (n)))
+/* Always has a lock prefix anyway */
+#define local_xchg(l, new) (xchg(&((l)->a.counter), new))
+
+/**
+ * atomic_up_add_unless - add unless the number is a given value
+ * @l: pointer of type local_t
+ * @a: the amount to add to l...
+ * @u: ...unless l is equal to u.
+ *
+ * Atomically adds @a to @l, so long as it was not @u.
+ * Returns non-zero if @l was not @u, and zero otherwise.
+ */
+#define local_add_unless(l, a, u)				\
+({								\
+	long c, old;						\
+	c = local_read(l);					\
+	for (;;) {						\
+		if (unlikely(c == (u)))				\
+			break;					\
+		old = local_cmpxchg((l), c, c + (a));	\
+		if (likely(old == c))				\
+			break;					\
+		c = old;					\
+	}							\
+	c != (u);						\
+})
+#define local_inc_not_zero(l) local_add_unless((l), 1, 0)
+
 /* On x86-64 these are better than the atomic variants on SMP kernels
    because they dont use a lock prefix. */
 #define __local_inc(l)		local_inc(l)
@@ -62,27 +196,27 @@ static inline void local_sub(long i, local_t *v)
 
 /* Need to disable preemption for the cpu local counters otherwise we could
    still access a variable of a previous CPU in a non atomic way. */
-#define cpu_local_wrap_v(v)	 	\
+#define cpu_local_wrap_v(l)	 	\
 	({ local_t res__;		\
 	   preempt_disable(); 		\
-	   res__ = (v);			\
+	   res__ = (l);			\
 	   preempt_enable();		\
 	   res__; })
-#define cpu_local_wrap(v)		\
+#define cpu_local_wrap(l)		\
 	({ preempt_disable();		\
-	   v;				\
+	   l;				\
 	   preempt_enable(); })		\
 
-#define cpu_local_read(v)    cpu_local_wrap_v(local_read(&__get_cpu_var(v)))
-#define cpu_local_set(v, i)  cpu_local_wrap(local_set(&__get_cpu_var(v), (i)))
-#define cpu_local_inc(v)     cpu_local_wrap(local_inc(&__get_cpu_var(v)))
-#define cpu_local_dec(v)     cpu_local_wrap(local_dec(&__get_cpu_var(v)))
-#define cpu_local_add(i, v)  cpu_local_wrap(local_add((i), &__get_cpu_var(v)))
-#define cpu_local_sub(i, v)  cpu_local_wrap(local_sub((i), &__get_cpu_var(v)))
+#define cpu_local_read(l)    cpu_local_wrap_v(local_read(&__get_cpu_var(l)))
+#define cpu_local_set(l, i)  cpu_local_wrap(local_set(&__get_cpu_var(l), (i)))
+#define cpu_local_inc(l)     cpu_local_wrap(local_inc(&__get_cpu_var(l)))
+#define cpu_local_dec(l)     cpu_local_wrap(local_dec(&__get_cpu_var(l)))
+#define cpu_local_add(i, l)  cpu_local_wrap(local_add((i), &__get_cpu_var(l)))
+#define cpu_local_sub(i, l)  cpu_local_wrap(local_sub((i), &__get_cpu_var(l)))
 
-#define __cpu_local_inc(v)	cpu_local_inc(v)
-#define __cpu_local_dec(v)	cpu_local_dec(v)
-#define __cpu_local_add(i, v)	cpu_local_add((i), (v))
-#define __cpu_local_sub(i, v)	cpu_local_sub((i), (v))
+#define __cpu_local_inc(l)	cpu_local_inc(l)
+#define __cpu_local_dec(l)	cpu_local_dec(l)
+#define __cpu_local_add(i, l)	cpu_local_add((i), (l))
+#define __cpu_local_sub(i, l)	cpu_local_sub((i), (l))
 
-#endif /* _ARCH_I386_LOCAL_H */
+#endif /* _ARCH_X8664_LOCAL_H */
--- a/include/asm-x86_64/system.h
+++ b/include/asm-x86_64/system.h
@@ -209,9 +209,45 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 	return old;
 }
 
+static inline unsigned long __cmpxchg_local(volatile void *ptr,
+			unsigned long old, unsigned long new, int size)
+{
+	unsigned long prev;
+	switch (size) {
+	case 1:
+		__asm__ __volatile__("cmpxchgb %b1,%2"
+				     : "=a"(prev)
+				     : "q"(new), "m"(*__xg(ptr)), "0"(old)
+				     : "memory");
+		return prev;
+	case 2:
+		__asm__ __volatile__("cmpxchgw %w1,%2"
+				     : "=a"(prev)
+				     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+				     : "memory");
+		return prev;
+	case 4:
+		__asm__ __volatile__("cmpxchgl %k1,%2"
+				     : "=a"(prev)
+				     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+				     : "memory");
+		return prev;
+	case 8:
+		__asm__ __volatile__("cmpxchgq %1,%2"
+				     : "=a"(prev)
+				     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+				     : "memory");
+		return prev;
+	}
+	return old;
+}
+
 #define cmpxchg(ptr,o,n)\
 	((__typeof__(*(ptr)))__cmpxchg((ptr),(unsigned long)(o),\
 					(unsigned long)(n),sizeof(*(ptr))))
+#define cmpxchg_local(ptr,o,n)\
+	((__typeof__(*(ptr)))__cmpxchg((ptr),(unsigned long)(o),\
+					(unsigned long)(n),sizeof(*(ptr))))
 
 #ifdef CONFIG_SMP
 #define smp_mb()	mb()