This commit adds the architecture support required to enable the optimised implementation of lockrefs.
That's as simple as defining arch_spin_value_unlocked() and selecting the Kconfig option. We also define cmpxchg64_relaxed(), because the lockref code does not need the cmpxchg to have barrier semantics. Using Linus' test case[1] on one system I see a 4x improvement for the basic enablement, and a further 1.3x for cmpxchg64_relaxed(), for a total of 5.3x vs the baseline. On another system I see more like 2x improvement. [1]: http://marc.info/?l=linux-fsdevel&m=137782380714721&w=4 Signed-off-by: Michael Ellerman <m...@ellerman.id.au> --- arch/powerpc/Kconfig | 1 + arch/powerpc/include/asm/cmpxchg.h | 1 + arch/powerpc/include/asm/spinlock.h | 5 +++++ 3 files changed, 7 insertions(+) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index b44b52c..b34b53d 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -139,6 +139,7 @@ config PPC select OLD_SIGACTION if PPC32 select HAVE_DEBUG_STACKOVERFLOW select HAVE_IRQ_EXIT_ON_IRQ_STACK + select ARCH_USE_CMPXCHG_LOCKREF if PPC64 config GENERIC_CSUM def_bool CPU_LITTLE_ENDIAN diff --git a/arch/powerpc/include/asm/cmpxchg.h b/arch/powerpc/include/asm/cmpxchg.h index e245aab..d463c68 100644 --- a/arch/powerpc/include/asm/cmpxchg.h +++ b/arch/powerpc/include/asm/cmpxchg.h @@ -300,6 +300,7 @@ __cmpxchg_local(volatile void *ptr, unsigned long old, unsigned long new, BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ cmpxchg_local((ptr), (o), (n)); \ }) +#define cmpxchg64_relaxed cmpxchg64_local #else #include <asm-generic/cmpxchg-local.h> #define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n)) diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h index 5f54a74..5162f8c 100644 --- a/arch/powerpc/include/asm/spinlock.h +++ b/arch/powerpc/include/asm/spinlock.h @@ -54,6 +54,11 @@ #define SYNC_IO #endif +static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock) +{ + return lock.slock == 0; +} + /* * This returns the old value in the lock, so we succeeded * in getting the lock if the return value is 0. -- 1.8.3.2 _______________________________________________ Linuxppc-dev mailing list Linuxppc-dev@lists.ozlabs.org https://lists.ozlabs.org/listinfo/linuxppc-dev
