X-Git-Url: http://git.liburcu.org/?p=urcu.git;a=blobdiff_plain;f=include%2Furcu%2Farch%2Fppc.h;fp=include%2Furcu%2Farch%2Fppc.h;h=791529ebb1a08ff3db124103474522b77bf0ad15;hp=0000000000000000000000000000000000000000;hb=6893800a4d1cc14dff0395ddcd660a5138db183d;hpb=a59f39055b5ecb77b68cf78b9839aa9e8e4ec332 diff --git a/include/urcu/arch/ppc.h b/include/urcu/arch/ppc.h new file mode 100644 index 0000000..791529e --- /dev/null +++ b/include/urcu/arch/ppc.h @@ -0,0 +1,125 @@ +#ifndef _URCU_ARCH_PPC_H +#define _URCU_ARCH_PPC_H + +/* + * arch_ppc.h: trivial definitions for the powerpc architecture. + * + * Copyright (c) 2009 Paul E. McKenney, IBM Corporation. + * Copyright (c) 2009 Mathieu Desnoyers + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + */ + +#include +#include +#include +#include + +#ifdef __cplusplus +extern "C" { +#endif + +/* Include size of POWER5+ L3 cache lines: 256 bytes */ +#define CAA_CACHE_LINE_SIZE 256 + +#ifdef __NO_LWSYNC__ +#define LWSYNC_OPCODE "sync\n" +#else +#define LWSYNC_OPCODE "lwsync\n" +#endif + +/* + * Use sync for all cmm_mb/rmb/wmb barriers because lwsync does not + * preserve ordering of cacheable vs. non-cacheable accesses, so it + * should not be used to order with respect to MMIO operations. An + * eieio+lwsync pair is also not enough for cmm_rmb, because it will + * order cacheable and non-cacheable memory operations separately---i.e. + * not the latter against the former. + */ +#define cmm_mb() __asm__ __volatile__ ("sync":::"memory") + +/* + * lwsync orders loads in cacheable memory with respect to other loads, + * and stores in cacheable memory with respect to other stores. + * Therefore, use it for barriers ordering accesses to cacheable memory + * only. + */ +#define cmm_smp_rmb() __asm__ __volatile__ (LWSYNC_OPCODE:::"memory") +#define cmm_smp_wmb() __asm__ __volatile__ (LWSYNC_OPCODE:::"memory") + +#define mftbl() \ + __extension__ \ + ({ \ + unsigned long rval; \ + __asm__ __volatile__ ("mftbl %0" : "=r" (rval)); \ + rval; \ + }) + +#define mftbu() \ + __extension__ \ + ({ \ + unsigned long rval; \ + __asm__ __volatile__ ("mftbu %0" : "=r" (rval)); \ + rval; \ + }) + +#define mftb() \ + __extension__ \ + ({ \ + unsigned long long rval; \ + __asm__ __volatile__ ("mftb %0" : "=r" (rval)); \ + rval; \ + }) + +#define HAS_CAA_GET_CYCLES + +typedef uint64_t caa_cycles_t; + +#ifdef __powerpc64__ +static inline caa_cycles_t caa_get_cycles(void) +{ + return (caa_cycles_t) mftb(); +} +#else +static inline caa_cycles_t caa_get_cycles(void) +{ + unsigned long h, l; + + for (;;) { + h = mftbu(); + cmm_barrier(); + l = mftbl(); + cmm_barrier(); + if (mftbu() == h) + return (((caa_cycles_t) h) << 32) + l; + } +} +#endif + +/* + * On Linux, define the membarrier system call number if not yet available in + * the system headers. + */ +#if (defined(__linux__) && !defined(__NR_membarrier)) +#define __NR_membarrier 365 +#endif + +#ifdef __cplusplus +} +#endif + +#include + +#endif /* _URCU_ARCH_PPC_H */