2008-06-04 20:34:43

by Cliff Wickman

[permalink] [raw]
Subject: [PATCH 1/1] x86 atomic operations: atomic_or_long atomic_inc_short



From: Cliff Wickman <[email protected]>

Provide atomic operations for increment of a 16-bit integer and
logical OR into a 64-bit integer.

[ This patch was split off of patch:
SGI UV: TLB shootdown using broadcast assist unit
and improved with advice from Jeremy Fitzhardinge <[email protected]> ]

Diffed against 2.6.26-rc4

Signed-off-by: Cliff Wickman <[email protected]>

---
include/asm-x86/atomic_64.h | 26 ++++++++++++++++++++++++++
1 file changed, 26 insertions(+)

Index: linux/include/asm-x86/atomic_64.h
===================================================================
--- linux.orig/include/asm-x86/atomic_64.h
+++ linux/include/asm-x86/atomic_64.h
@@ -431,6 +431,32 @@ static inline int atomic64_add_unless(at
return c != (u);
}

+/**
+ * atomic_inc_short - increment of a short integer
+ * @v: pointer to type int
+ *
+ * Atomically adds 1 to @v
+ * Returns the new value of @u
+ */
+static inline short int atomic_inc_short(short int *v)
+{
+ asm(LOCK_PREFIX "addw $1, %0" : "+m" (*v));
+ return *v;
+}
+
+/**
+ * atomic_or_long - OR of two long integers
+ * @v1: pointer to type unsigned long
+ * @v2: pointer to type unsigned long
+ *
+ * Atomically ORs @v1 and @v2
+ * Returns the result of the OR
+ */
+static inline void atomic_or_long(unsigned long *v1, unsigned long v2)
+{
+ asm(LOCK_PREFIX "orq %1, %0" : "+m" (*v1) : "r" (v2));
+}
+
#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)

/* These are x86-specific, used by some header files */


2008-06-05 15:27:48

by Jeremy Fitzhardinge

[permalink] [raw]
Subject: Re: [PATCH 1/1] x86 atomic operations: atomic_or_long atomic_inc_short

Cliff Wickman wrote:
> From: Cliff Wickman <[email protected]>
>
> Provide atomic operations for increment of a 16-bit integer and
> logical OR into a 64-bit integer.
>
> [ This patch was split off of patch:
> SGI UV: TLB shootdown using broadcast assist unit
> and improved with advice from Jeremy Fitzhardinge <[email protected]> ]
>
> Diffed against 2.6.26-rc4
>
> Signed-off-by: Cliff Wickman <[email protected]>
>
Reviewed-by: Jeremy Fitzhardinge <[email protected]>

> ---
> include/asm-x86/atomic_64.h | 26 ++++++++++++++++++++++++++
> 1 file changed, 26 insertions(+)
>
> Index: linux/include/asm-x86/atomic_64.h
> ===================================================================
> --- linux.orig/include/asm-x86/atomic_64.h
> +++ linux/include/asm-x86/atomic_64.h
> @@ -431,6 +431,32 @@ static inline int atomic64_add_unless(at
> return c != (u);
> }
>
> +/**
> + * atomic_inc_short - increment of a short integer
> + * @v: pointer to type int
> + *
> + * Atomically adds 1 to @v
> + * Returns the new value of @u
> + */
> +static inline short int atomic_inc_short(short int *v)
> +{
> + asm(LOCK_PREFIX "addw $1, %0" : "+m" (*v));
> + return *v;
> +}
> +
> +/**
> + * atomic_or_long - OR of two long integers
> + * @v1: pointer to type unsigned long
> + * @v2: pointer to type unsigned long
> + *
> + * Atomically ORs @v1 and @v2
> + * Returns the result of the OR
> + */
> +static inline void atomic_or_long(unsigned long *v1, unsigned long v2)
> +{
> + asm(LOCK_PREFIX "orq %1, %0" : "+m" (*v1) : "r" (v2));
> +}
> +
> #define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
>
> /* These are x86-specific, used by some header files */
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
>

2008-06-10 10:11:39

by Ingo Molnar

[permalink] [raw]
Subject: Re: [PATCH 1/1] x86 atomic operations: atomic_or_long atomic_inc_short


* Cliff Wickman <[email protected]> wrote:

> From: Cliff Wickman <[email protected]>
>
> Provide atomic operations for increment of a 16-bit integer and
> logical OR into a 64-bit integer.
>
> [ This patch was split off of patch:
> SGI UV: TLB shootdown using broadcast assist unit
> and improved with advice from Jeremy Fitzhardinge <[email protected]> ]

applied to tip/x86/uv, thanks Cliff.

Ingo