@@ -31,12 +31,14 @@ config ARM64
select GENERIC_STRNLEN_USER
select GENERIC_TIME_VSYSCALL
select HARDIRQS_SW_RESEND
+ select HAVE_ALIGNED_STRUCT_PAGE if SLUB
select HAVE_ARCH_AUDITSYSCALL
select HAVE_ARCH_JUMP_LABEL
select HAVE_ARCH_KGDB
select HAVE_ARCH_TRACEHOOK
select HAVE_C_RECORDMCOUNT
select HAVE_CC_STACKPROTECTOR
+ select HAVE_CMPXCHG_DOUBLE
select HAVE_DEBUG_BUGVERBOSE
select HAVE_DEBUG_KMEMLEAK
select HAVE_DMA_API_DEBUG
@@ -19,6 +19,7 @@
#define __ASM_CMPXCHG_H
#include <linux/bug.h>
+#include <linux/mmdebug.h>
#include <asm/barrier.h>
@@ -152,6 +153,51 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
return oldval;
}
+#define system_has_cmpxchg_double() 1
+
+static inline int __cmpxchg_double(volatile void *ptr1, volatile void *ptr2,
+ unsigned long old1, unsigned long old2,
+ unsigned long new1, unsigned long new2, int size)
+{
+ unsigned long loop, lost;
+
+ switch (size) {
+ case 8:
+ VM_BUG_ON((unsigned long *)ptr2 - (unsigned long *)ptr1 != 1);
+ do {
+ asm volatile("// __cmpxchg_double8\n"
+ " ldxp %0, %1, %2\n"
+ " eor %0, %0, %3\n"
+ " eor %1, %1, %4\n"
+ " orr %1, %0, %1\n"
+ " mov %w0, #0\n"
+ " cbnz %1, 1f\n"
+ " stxp %w0, %5, %6, %2\n"
+ "1:\n"
+ : "=&r"(loop), "=&r"(lost), "+Q" (*(u64 *)ptr1)
+ : "r" (old1), "r"(old2), "r"(new1), "r"(new2));
+ } while (loop);
+ break;
+ default:
+ BUILD_BUG();
+ }
+
+ return !lost;
+}
+
+static inline int __cmpxchg_double_mb(volatile void *ptr1, volatile void *ptr2,
+ unsigned long old1, unsigned long old2,
+ unsigned long new1, unsigned long new2, int size)
+{
+ int ret;
+
+ smp_mb();
+ ret = __cmpxchg_double(ptr1, ptr2, old1, old2, new1, new2, size);
+ smp_mb();
+
+ return ret;
+}
+
static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
unsigned long new, int size)
{
@@ -173,6 +219,15 @@ static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
__ret; \
})
+#define cmpxchg_double(ptr1, ptr2, o1, o2, n1, n2) \
+({\
+ int __ret;\
+ __ret = __cmpxchg_double_mb((ptr1), (ptr2), (unsigned long)(o1), \
+ (unsigned long)(o2), (unsigned long)(n1), \
+ (unsigned long)(n2), sizeof(*(ptr1)));\
+ __ret; \
+})
+
#define cmpxchg_local(ptr, o, n) \
({ \
__typeof__(*(ptr)) __ret; \
The arm64 architecture has the ability to exclusively load and store a pair of registers from an address (ldxp/stxp). Also the SLUB can take advantage of a cmpxchg_double implementation to avoid taking some locks. This patch provides an implementation of cmpxchg_double for 64-bit pairs, and activates the logic required for the SLUB to use these functions (HAVE_ALIGNED_STRUCT_PAGE and HAVE_CMPXCHG_DOUBLE). On a Juno platform running on only the A57s I get quite a noticeable performance improvement with hackbench. Before patch applied: $ ./hackbench 100 process 1000 Running with 100*40 (== 4000) tasks. Time: 206.331 After patch applied: $ ./hackbench 100 process 1000 Running with 100*40 (== 4000) tasks. Time: 182.396 Signed-off-by: Steve Capper <steve.capper@linaro.org> --- arch/arm64/Kconfig | 2 ++ arch/arm64/include/asm/cmpxchg.h | 55 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 57 insertions(+)