diff options
Diffstat (limited to 'arch/powerpc')
91 files changed, 8174 insertions, 1498 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 1493c7896fe..c523029674e 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -581,17 +581,12 @@ config ARCH_FLATMEM_ENABLE def_bool y depends on PPC64 && !NUMA -config ARCH_DISCONTIGMEM_ENABLE - def_bool y - depends on SMP && PPC_PSERIES - -config ARCH_DISCONTIGMEM_DEFAULT +config ARCH_SPARSEMEM_ENABLE def_bool y - depends on ARCH_DISCONTIGMEM_ENABLE -config ARCH_SPARSEMEM_ENABLE +config ARCH_SPARSEMEM_DEFAULT def_bool y - depends on ARCH_DISCONTIGMEM_ENABLE + depends on SMP && PPC_PSERIES source "mm/Kconfig" @@ -599,6 +594,10 @@ config HAVE_ARCH_EARLY_PFN_TO_NID def_bool y depends on NEED_MULTIPLE_NODES +config ARCH_MEMORY_PROBE + def_bool y + depends on MEMORY_HOTPLUG + # Some NUMA nodes have memory ranges that span # other nodes. Even though a pfn is valid and # between a node's start and end pfns, it may not diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index b3ae2993efb..9a74b7ab03a 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -4,6 +4,7 @@ ifeq ($(CONFIG_PPC64),y) EXTRA_CFLAGS += -mno-minimal-toc +CFLAGS_ioctl32.o += -Ifs/ endif ifeq ($(CONFIG_PPC32),y) CFLAGS_prom_init.o += -fPIC @@ -11,17 +12,29 @@ CFLAGS_btext.o += -fPIC endif obj-y := semaphore.o cputable.o ptrace.o syscalls.o \ - signal_32.o pmc.o + irq.o signal_32.o pmc.o vdso.o +obj-y += vdso32/ obj-$(CONFIG_PPC64) += setup_64.o binfmt_elf32.o sys_ppc32.o \ - signal_64.o ptrace32.o systbl.o + signal_64.o ptrace32.o systbl.o \ + paca.o ioctl32.o cpu_setup_power4.o \ + firmware.o sysfs.o udbg.o +obj-$(CONFIG_PPC64) += vdso64/ obj-$(CONFIG_ALTIVEC) += vecemu.o vector.o obj-$(CONFIG_POWER4) += idle_power4.o obj-$(CONFIG_PPC_OF) += of_device.o -obj-$(CONFIG_PPC_RTAS) += rtas.o +procfs-$(CONFIG_PPC64) := proc_ppc64.o +obj-$(CONFIG_PROC_FS) += $(procfs-y) +rtaspci-$(CONFIG_PPC64) := rtas_pci.o +obj-$(CONFIG_PPC_RTAS) += rtas.o $(rtaspci-y) obj-$(CONFIG_RTAS_FLASH) += rtas_flash.o obj-$(CONFIG_RTAS_PROC) += rtas-proc.o +obj-$(CONFIG_LPARCFG) += lparcfg.o obj-$(CONFIG_IBMVIO) += vio.o obj-$(CONFIG_GENERIC_TBSYNC) += smp-tbsync.o +obj-$(CONFIG_PPC_PSERIES) += udbg_16550.o +obj-$(CONFIG_PPC_MAPLE) += udbg_16550.o +udbgscc-$(CONFIG_PPC64) := udbg_scc.o +obj-$(CONFIG_PPC_PMAC) += $(udbgscc-y) ifeq ($(CONFIG_PPC_MERGE),y) diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index b7575725199..4550eb4f4fb 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -37,12 +37,12 @@ #include <asm/cputable.h> #include <asm/thread_info.h> #include <asm/rtas.h> +#include <asm/vdso_datapage.h> #ifdef CONFIG_PPC64 #include <asm/paca.h> #include <asm/lppaca.h> #include <asm/iseries/hv_lp_event.h> #include <asm/cache.h> -#include <asm/systemcfg.h> #include <asm/compat.h> #endif @@ -106,7 +106,6 @@ int main(void) DEFINE(ICACHEL1LINESIZE, offsetof(struct ppc64_caches, iline_size)); DEFINE(ICACHEL1LOGLINESIZE, offsetof(struct ppc64_caches, log_iline_size)); DEFINE(ICACHEL1LINESPERPAGE, offsetof(struct ppc64_caches, ilines_per_page)); - DEFINE(PLATFORM, offsetof(struct systemcfg, platform)); DEFINE(PLATFORM_LPAR, PLATFORM_LPAR); /* paca */ @@ -252,25 +251,42 @@ int main(void) DEFINE(TASK_SIZE, TASK_SIZE); DEFINE(NUM_USER_SEGMENTS, TASK_SIZE>>28); -#else /* CONFIG_PPC64 */ - /* systemcfg offsets for use by vdso */ - DEFINE(CFG_TB_ORIG_STAMP, offsetof(struct systemcfg, tb_orig_stamp)); - DEFINE(CFG_TB_TICKS_PER_SEC, offsetof(struct systemcfg, tb_ticks_per_sec)); - DEFINE(CFG_TB_TO_XS, offsetof(struct systemcfg, tb_to_xs)); - DEFINE(CFG_STAMP_XSEC, offsetof(struct systemcfg, stamp_xsec)); - DEFINE(CFG_TB_UPDATE_COUNT, offsetof(struct systemcfg, tb_update_count)); - DEFINE(CFG_TZ_MINUTEWEST, offsetof(struct systemcfg, tz_minuteswest)); - DEFINE(CFG_TZ_DSTTIME, offsetof(struct systemcfg, tz_dsttime)); - DEFINE(CFG_SYSCALL_MAP32, offsetof(struct systemcfg, syscall_map_32)); - DEFINE(CFG_SYSCALL_MAP64, offsetof(struct systemcfg, syscall_map_64)); +#endif /* ! CONFIG_PPC64 */ - /* timeval/timezone offsets for use by vdso */ + /* datapage offsets for use by vdso */ + DEFINE(CFG_TB_ORIG_STAMP, offsetof(struct vdso_data, tb_orig_stamp)); + DEFINE(CFG_TB_TICKS_PER_SEC, offsetof(struct vdso_data, tb_ticks_per_sec)); + DEFINE(CFG_TB_TO_XS, offsetof(struct vdso_data, tb_to_xs)); + DEFINE(CFG_STAMP_XSEC, offsetof(struct vdso_data, stamp_xsec)); + DEFINE(CFG_TB_UPDATE_COUNT, offsetof(struct vdso_data, tb_update_count)); + DEFINE(CFG_TZ_MINUTEWEST, offsetof(struct vdso_data, tz_minuteswest)); + DEFINE(CFG_TZ_DSTTIME, offsetof(struct vdso_data, tz_dsttime)); + DEFINE(CFG_SYSCALL_MAP32, offsetof(struct vdso_data, syscall_map_32)); + DEFINE(WTOM_CLOCK_SEC, offsetof(struct vdso_data, wtom_clock_sec)); + DEFINE(WTOM_CLOCK_NSEC, offsetof(struct vdso_data, wtom_clock_nsec)); +#ifdef CONFIG_PPC64 + DEFINE(CFG_SYSCALL_MAP64, offsetof(struct vdso_data, syscall_map_64)); DEFINE(TVAL64_TV_SEC, offsetof(struct timeval, tv_sec)); DEFINE(TVAL64_TV_USEC, offsetof(struct timeval, tv_usec)); DEFINE(TVAL32_TV_SEC, offsetof(struct compat_timeval, tv_sec)); DEFINE(TVAL32_TV_USEC, offsetof(struct compat_timeval, tv_usec)); + DEFINE(TSPC32_TV_SEC, offsetof(struct compat_timespec, tv_sec)); + DEFINE(TSPC32_TV_NSEC, offsetof(struct compat_timespec, tv_nsec)); +#else + DEFINE(TVAL32_TV_SEC, offsetof(struct timeval, tv_sec)); + DEFINE(TVAL32_TV_USEC, offsetof(struct timeval, tv_usec)); + DEFINE(TSPEC32_TV_SEC, offsetof(struct timespec, tv_sec)); + DEFINE(TSPEC32_TV_NSEC, offsetof(struct timespec, tv_nsec)); +#endif + /* timeval/timezone offsets for use by vdso */ DEFINE(TZONE_TZ_MINWEST, offsetof(struct timezone, tz_minuteswest)); DEFINE(TZONE_TZ_DSTTIME, offsetof(struct timezone, tz_dsttime)); -#endif /* CONFIG_PPC64 */ + + /* Other bits used by the vdso */ + DEFINE(CLOCK_REALTIME, CLOCK_REALTIME); + DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC); + DEFINE(NSEC_PER_SEC, NSEC_PER_SEC); + DEFINE(CLOCK_REALTIME_RES, TICK_NSEC); + return 0; } diff --git a/arch/powerpc/kernel/cpu_setup_power4.S b/arch/powerpc/kernel/cpu_setup_power4.S new file mode 100644 index 00000000000..cca942fe611 --- /dev/null +++ b/arch/powerpc/kernel/cpu_setup_power4.S @@ -0,0 +1,233 @@ +/* + * This file contains low level CPU setup functions. + * Copyright (C) 2003 Benjamin Herrenschmidt (benh@kernel.crashing.org) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + */ + +#include <linux/config.h> +#include <asm/processor.h> +#include <asm/page.h> +#include <asm/cputable.h> +#include <asm/ppc_asm.h> +#include <asm/asm-offsets.h> +#include <asm/cache.h> + +_GLOBAL(__970_cpu_preinit) + /* + * Do nothing if not running in HV mode + */ + mfmsr r0 + rldicl. r0,r0,4,63 + beqlr + + /* + * Deal only with PPC970 and PPC970FX. + */ + mfspr r0,SPRN_PVR + srwi r0,r0,16 + cmpwi r0,0x39 + beq 1f + cmpwi r0,0x3c + beq 1f + cmpwi r0,0x44 + bnelr +1: + + /* Make sure HID4:rm_ci is off before MMU is turned off, that large + * pages are enabled with HID4:61 and clear HID5:DCBZ_size and + * HID5:DCBZ32_ill + */ + li r0,0 + mfspr r3,SPRN_HID4 + rldimi r3,r0,40,23 /* clear bit 23 (rm_ci) */ + rldimi r3,r0,2,61 /* clear bit 61 (lg_pg_en) */ + sync + mtspr SPRN_HID4,r3 + isync + sync + mfspr r3,SPRN_HID5 + rldimi r3,r0,6,56 /* clear bits 56 & 57 (DCBZ*) */ + sync + mtspr SPRN_HID5,r3 + isync + sync + + /* Setup some basic HID1 features */ + mfspr r0,SPRN_HID1 + li r3,0x1200 /* enable i-fetch cacheability */ + sldi r3,r3,44 /* and prefetch */ + or r0,r0,r3 + mtspr SPRN_HID1,r0 + mtspr SPRN_HID1,r0 + isync + + /* Clear HIOR */ + li r0,0 + sync + mtspr SPRN_HIOR,0 /* Clear interrupt prefix */ + isync + blr + +_GLOBAL(__setup_cpu_power4) + blr + +_GLOBAL(__setup_cpu_be) + /* Set large page sizes LP=0: 16MB, LP=1: 64KB */ + addi r3, 0, 0 + ori r3, r3, HID6_LB + sldi r3, r3, 32 + nor r3, r3, r3 + mfspr r4, SPRN_HID6 + and r4, r4, r3 + addi r3, 0, 0x02000 + sldi r3, r3, 32 + or r4, r4, r3 + mtspr SPRN_HID6, r4 + blr + +_GLOBAL(__setup_cpu_ppc970) + mfspr r0,SPRN_HID0 + li r11,5 /* clear DOZE and SLEEP */ + rldimi r0,r11,52,8 /* set NAP and DPM */ + mtspr SPRN_HID0,r0 + mfspr r0,SPRN_HID0 + mfspr r0,SPRN_HID0 + mfspr r0,SPRN_HID0 + mfspr r0,SPRN_HID0 + mfspr r0,SPRN_HID0 + mfspr r0,SPRN_HID0 + sync + isync + blr + +/* Definitions for the table use to save CPU states */ +#define CS_HID0 0 +#define CS_HID1 8 +#define CS_HID4 16 +#define CS_HID5 24 +#define CS_SIZE 32 + + .data + .balign L1_CACHE_BYTES,0 +cpu_state_storage: + .space CS_SIZE + .balign L1_CACHE_BYTES,0 + .text + +/* Called in normal context to backup CPU 0 state. This + * does not include cache settings. This function is also + * called for machine sleep. This does not include the MMU + * setup, BATs, etc... but rather the "special" registers + * like HID0, HID1, HID4, etc... + */ +_GLOBAL(__save_cpu_setup) + /* Some CR fields are volatile, we back it up all */ + mfcr r7 + + /* Get storage ptr */ + LOADADDR(r5,cpu_state_storage) + + /* We only deal with 970 for now */ + mfspr r0,SPRN_PVR + srwi r0,r0,16 + cmpwi r0,0x39 + beq 1f + cmpwi r0,0x3c + beq 1f + cmpwi r0,0x44 + bne 2f + +1: /* Save HID0,1,4 and 5 */ + mfspr r3,SPRN_HID0 + std r3,CS_HID0(r5) + mfspr r3,SPRN_HID1 + std r3,CS_HID1(r5) + mfspr r3,SPRN_HID4 + std r3,CS_HID4(r5) + mfspr r3,SPRN_HID5 + std r3,CS_HID5(r5) + +2: + mtcr r7 + blr + +/* Called with no MMU context (typically MSR:IR/DR off) to + * restore CPU state as backed up by the previous + * function. This does not include cache setting + */ +_GLOBAL(__restore_cpu_setup) + /* Get storage ptr (FIXME when using anton reloc as we + * are running with translation disabled here + */ + LOADADDR(r5,cpu_state_storage) + + /* We only deal with 970 for now */ + mfspr r0,SPRN_PVR + srwi r0,r0,16 + cmpwi r0,0x39 + beq 1f + cmpwi r0,0x3c + beq 1f + cmpwi r0,0x44 + bnelr + +1: /* Before accessing memory, we make sure rm_ci is clear */ + li r0,0 + mfspr r3,SPRN_HID4 + rldimi r3,r0,40,23 /* clear bit 23 (rm_ci) */ + sync + mtspr SPRN_HID4,r3 + isync + sync + + /* Clear interrupt prefix */ + li r0,0 + sync + mtspr SPRN_HIOR,0 + isync + + /* Restore HID0 */ + ld r3,CS_HID0(r5) + sync + isync + mtspr SPRN_HID0,r3 + mfspr r3,SPRN_HID0 + mfspr r3,SPRN_HID0 + mfspr r3,SPRN_HID0 + mfspr r3,SPRN_HID0 + mfspr r3,SPRN_HID0 + mfspr r3,SPRN_HID0 + sync + isync + + /* Restore HID1 */ + ld r3,CS_HID1(r5) + sync + isync + mtspr SPRN_HID1,r3 + mtspr SPRN_HID1,r3 + sync + isync + + /* Restore HID4 */ + ld r3,CS_HID4(r5) + sync + isync + mtspr SPRN_HID4,r3 + sync + isync + + /* Restore HID5 */ + ld r3,CS_HID5(r5) + sync + isync + mtspr SPRN_HID5,r3 + sync + isync + blr + diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index cc4e9eb1c13..1d85cedbbb7 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -52,6 +52,9 @@ extern void __setup_cpu_ppc970(unsigned long offset, struct cpu_spec* spec); #define COMMON_USER (PPC_FEATURE_32 | PPC_FEATURE_HAS_FPU | \ PPC_FEATURE_HAS_MMU) #define COMMON_USER_PPC64 (COMMON_USER | PPC_FEATURE_64) +#define COMMON_USER_POWER4 (COMMON_USER_PPC64 | PPC_FEATURE_POWER4) +#define COMMON_USER_POWER5 (COMMON_USER_PPC64 | PPC_FEATURE_POWER5) +#define COMMON_USER_POWER5_PLUS (COMMON_USER_PPC64 | PPC_FEATURE_POWER5_PLUS) /* We only set the spe features if the kernel was compiled with @@ -160,7 +163,7 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x00350000, .cpu_name = "POWER4 (gp)", .cpu_features = CPU_FTRS_POWER4, - .cpu_user_features = COMMON_USER_PPC64, + .cpu_user_features = COMMON_USER_POWER4, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -175,7 +178,7 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x00380000, .cpu_name = "POWER4+ (gq)", .cpu_features = CPU_FTRS_POWER4, - .cpu_user_features = COMMON_USER_PPC64, + .cpu_user_features = COMMON_USER_POWER4, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -190,7 +193,7 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x00390000, .cpu_name = "PPC970", .cpu_features = CPU_FTRS_PPC970, - .cpu_user_features = COMMON_USER_PPC64 | + .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP, .icache_bsize = 128, .dcache_bsize = 128, @@ -212,7 +215,7 @@ struct cpu_spec cpu_specs[] = { #else .cpu_features = CPU_FTRS_PPC970, #endif - .cpu_user_features = COMMON_USER_PPC64 | + .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP, .icache_bsize = 128, .dcache_bsize = 128, @@ -230,7 +233,7 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x00440000, .cpu_name = "PPC970MP", .cpu_features = CPU_FTRS_PPC970, - .cpu_user_features = COMMON_USER_PPC64 | + .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP, .icache_bsize = 128, .dcache_bsize = 128, @@ -245,7 +248,7 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x003a0000, .cpu_name = "POWER5 (gr)", .cpu_features = CPU_FTRS_POWER5, - .cpu_user_features = COMMON_USER_PPC64, + .cpu_user_features = COMMON_USER_POWER5, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, @@ -260,7 +263,7 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x003b0000, .cpu_name = "POWER5 (gs)", .cpu_features = CPU_FTRS_POWER5, - .cpu_user_features = COMMON_USER_PPC64, + .cpu_user_features = COMMON_USER_POWER5_PLUS, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, @@ -276,7 +279,7 @@ struct cpu_spec cpu_specs[] = { .cpu_name = "Cell Broadband Engine", .cpu_features = CPU_FTRS_CELL, .cpu_user_features = COMMON_USER_PPC64 | - PPC_FEATURE_HAS_ALTIVEC_COMP, + PPC_FEATURE_CELL | PPC_FEATURE_HAS_ALTIVEC_COMP, .icache_bsize = 128, .dcache_bsize = 128, .cpu_setup = __setup_cpu_be, diff --git a/arch/powerpc/kernel/firmware.c b/arch/powerpc/kernel/firmware.c new file mode 100644 index 00000000000..65eae752a52 --- /dev/null +++ b/arch/powerpc/kernel/firmware.c @@ -0,0 +1,45 @@ +/* + * Extracted from cputable.c + * + * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org) + * + * Modifications for ppc64: + * Copyright (C) 2003 Dave Engebretsen <engebret@us.ibm.com> + * Copyright (C) 2005 Stephen Rothwell, IBM Corporation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/config.h> + +#include <asm/firmware.h> + +unsigned long ppc64_firmware_features; + +#ifdef CONFIG_PPC_PSERIES +firmware_feature_t firmware_features_table[FIRMWARE_MAX_FEATURES] = { + {FW_FEATURE_PFT, "hcall-pft"}, + {FW_FEATURE_TCE, "hcall-tce"}, + {FW_FEATURE_SPRG0, "hcall-sprg0"}, + {FW_FEATURE_DABR, "hcall-dabr"}, + {FW_FEATURE_COPY, "hcall-copy"}, + {FW_FEATURE_ASR, "hcall-asr"}, + {FW_FEATURE_DEBUG, "hcall-debug"}, + {FW_FEATURE_PERF, "hcall-perf"}, + {FW_FEATURE_DUMP, "hcall-dump"}, + {FW_FEATURE_INTERRUPT, "hcall-interrupt"}, + {FW_FEATURE_MIGRATE, "hcall-migrate"}, + {FW_FEATURE_PERFMON, "hcall-perfmon"}, + {FW_FEATURE_CRQ, "hcall-crq"}, + {FW_FEATURE_VIO, "hcall-vio"}, + {FW_FEATURE_RDMA, "hcall-rdma"}, + {FW_FEATURE_LLAN, "hcall-lLAN"}, + {FW_FEATURE_BULK, "hcall-bulk"}, + {FW_FEATURE_XDABR, "hcall-xdabr"}, + {FW_FEATURE_MULTITCE, "hcall-multi-tce"}, + {FW_FEATURE_SPLPAR, "hcall-splpar"}, +}; +#endif diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S index 4d6001fa1cf..b780b42c95f 100644 --- a/arch/powerpc/kernel/fpu.S +++ b/arch/powerpc/kernel/fpu.S @@ -41,20 +41,20 @@ _GLOBAL(load_up_fpu) #ifndef CONFIG_SMP LOADBASE(r3, last_task_used_math) toreal(r3) - LDL r4,OFF(last_task_used_math)(r3) - CMPI 0,r4,0 + PPC_LL r4,OFF(last_task_used_math)(r3) + PPC_LCMPI 0,r4,0 beq 1f toreal(r4) addi r4,r4,THREAD /* want last_task_used_math->thread */ SAVE_32FPRS(0, r4) mffs fr0 stfd fr0,THREAD_FPSCR(r4) - LDL r5,PT_REGS(r4) + PPC_LL r5,PT_REGS(r4) toreal(r5) - LDL r4,_MSR-STACK_FRAME_OVERHEAD(r5) + PPC_LL r4,_MSR-STACK_FRAME_OVERHEAD(r5) li r10,MSR_FP|MSR_FE0|MSR_FE1 andc r4,r4,r10 /* disable FP for previous task */ - STL r4,_MSR-STACK_FRAME_OVERHEAD(r5) + PPC_STL r4,_MSR-STACK_FRAME_OVERHEAD(r5) 1: #endif /* CONFIG_SMP */ /* enable use of FP after return */ @@ -77,7 +77,7 @@ _GLOBAL(load_up_fpu) #ifndef CONFIG_SMP subi r4,r5,THREAD fromreal(r4) - STL r4,OFF(last_task_used_math)(r3) + PPC_STL r4,OFF(last_task_used_math)(r3) #endif /* CONFIG_SMP */ /* restore registers and return */ /* we haven't used ctr or xer or lr */ @@ -97,24 +97,24 @@ _GLOBAL(giveup_fpu) MTMSRD(r5) /* enable use of fpu now */ SYNC_601 isync - CMPI 0,r3,0 + PPC_LCMPI 0,r3,0 beqlr- /* if no previous owner, done */ addi r3,r3,THREAD /* want THREAD of task */ - LDL r5,PT_REGS(r3) - CMPI 0,r5,0 + PPC_LL r5,PT_REGS(r3) + PPC_LCMPI 0,r5,0 SAVE_32FPRS(0, r3) mffs fr0 stfd fr0,THREAD_FPSCR(r3) beq 1f - LDL r4,_MSR-STACK_FRAME_OVERHEAD(r5) + PPC_LL r4,_MSR-STACK_FRAME_OVERHEAD(r5) li r3,MSR_FP|MSR_FE0|MSR_FE1 andc r4,r4,r3 /* disable FP for previous task */ - STL r4,_MSR-STACK_FRAME_OVERHEAD(r5) + PPC_STL r4,_MSR-STACK_FRAME_OVERHEAD(r5) 1: #ifndef CONFIG_SMP li r5,0 LOADBASE(r4,last_task_used_math) - STL r5,OFF(last_task_used_math)(r4) + PPC_STL r5,OFF(last_task_used_math)(r4) #endif /* CONFIG_SMP */ blr diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index b102e3a2415..ccdf94731e3 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -1100,6 +1100,7 @@ start_here: mr r3,r31 mr r4,r30 bl machine_init + bl __save_cpu_setup bl MMU_init #ifdef CONFIG_APUS diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 16ab40daa73..8a8bf79ef04 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -28,7 +28,6 @@ #include <asm/reg.h> #include <asm/page.h> #include <asm/mmu.h> -#include <asm/systemcfg.h> #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> #include <asm/bug.h> @@ -1697,25 +1696,14 @@ _GLOBAL(pmac_secondary_start) * SPRG3 = paca virtual address */ _GLOBAL(__secondary_start) + /* Set thread priority to MEDIUM */ + HMT_MEDIUM - HMT_MEDIUM /* Set thread priority to MEDIUM */ - + /* Load TOC */ ld r2,PACATOC(r13) - li r6,0 - stb r6,PACAPROCENABLED(r13) - -#ifndef CONFIG_PPC_ISERIES - /* Initialize the page table pointer register. */ - LOADADDR(r6,_SDR1) - ld r6,0(r6) /* get the value of _SDR1 */ - mtspr SPRN_SDR1,r6 /* set the htab location */ -#endif - /* Initialize the first segment table (or SLB) entry */ - ld r3,PACASTABVIRT(r13) /* get addr of segment table */ -BEGIN_FTR_SECTION - bl .stab_initialize -END_FTR_SECTION_IFCLR(CPU_FTR_SLB) - bl .slb_initialize + + /* Do early setup for that CPU (stab, slb, hash table pointer) */ + bl .early_setup_secondary /* Initialize the kernel stack. Just a repeat for iSeries. */ LOADADDR(r3,current_set) @@ -1724,37 +1712,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_SLB) addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD std r1,PACAKSAVE(r13) - ld r3,PACASTABREAL(r13) /* get raddr of segment table */ - ori r4,r3,1 /* turn on valid bit */ - -#ifdef CONFIG_PPC_ISERIES - li r0,-1 /* hypervisor call */ - li r3,1 - sldi r3,r3,63 /* 0x8000000000000000 */ - ori r3,r3,4 /* 0x8000000000000004 */ - sc /* HvCall_setASR */ -#else - /* set the ASR */ - ld r3,systemcfg@got(r2) /* r3 = ptr to systemcfg */ - ld r3,0(r3) - lwz r3,PLATFORM(r3) /* r3 = platform flags */ - andi. r3,r3,PLATFORM_LPAR /* Test if bit 0 is set (LPAR bit) */ - beq 98f /* branch if result is 0 */ - mfspr r3,SPRN_PVR - srwi r3,r3,16 - cmpwi r3,0x37 /* SStar */ - beq 97f - cmpwi r3,0x36 /* IStar */ - beq 97f - cmpwi r3,0x34 /* Pulsar */ - bne 98f -97: li r3,H_SET_ASR /* hcall = H_SET_ASR */ - HVSC /* Invoking hcall */ - b 99f -98: /* !(rpa hypervisor) || !(star) */ - mtasr r4 /* set the stab location */ -99: -#endif + /* Clear backchain so we get nice backtraces */ li r7,0 mtlr r7 @@ -1777,6 +1735,7 @@ _GLOBAL(start_secondary_prolog) li r3,0 std r3,0(r1) /* Zero the stack frame pointer */ bl .start_secondary + b . #endif /* @@ -1896,40 +1855,6 @@ _STATIC(start_here_multiplatform) mr r3,r31 bl .early_setup - /* set the ASR */ - ld r3,PACASTABREAL(r13) - ori r4,r3,1 /* turn on valid bit */ - ld r3,systemcfg@got(r2) /* r3 = ptr to systemcfg */ - ld r3,0(r3) - lwz r3,PLATFORM(r3) /* r3 = platform flags */ - andi. r3,r3,PLATFORM_LPAR /* Test if bit 0 is set (LPAR bit) */ - beq 98f /* branch if result is 0 */ - mfspr r3,SPRN_PVR - srwi r3,r3,16 - cmpwi r3,0x37 /* SStar */ - beq 97f - cmpwi r3,0x36 /* IStar */ - beq 97f - cmpwi r3,0x34 /* Pulsar */ - bne 98f -97: li r3,H_SET_ASR /* hcall = H_SET_ASR */ - HVSC /* Invoking hcall */ - b 99f -98: /* !(rpa hypervisor) || !(star) */ - mtasr r4 /* set the stab location */ -99: - /* Set SDR1 (hash table pointer) */ - ld r3,systemcfg@got(r2) /* r3 = ptr to systemcfg */ - ld r3,0(r3) - lwz r3,PLATFORM(r3) /* r3 = platform flags */ - /* Test if bit 0 is set (LPAR bit) */ - andi. r3,r3,PLATFORM_LPAR - bne 98f /* branch if result is !0 */ - LOADADDR(r6,_SDR1) /* Only if NOT LPAR */ - add r6,r6,r26 - ld r6,0(r6) /* get the value of _SDR1 */ - mtspr SPRN_SDR1,r6 /* set the htab location */ -98: LOADADDR(r3,.start_here_common) SET_REG_TO_CONST(r4, MSR_KERNEL) mtspr SPRN_SRR0,r3 diff --git a/arch/powerpc/kernel/ioctl32.c b/arch/powerpc/kernel/ioctl32.c new file mode 100644 index 00000000000..3fa6a93adbd --- /dev/null +++ b/arch/powerpc/kernel/ioctl32.c @@ -0,0 +1,49 @@ +/* + * ioctl32.c: Conversion between 32bit and 64bit native ioctls. + * + * Based on sparc64 ioctl32.c by: + * + * Copyright (C) 1997-2000 Jakub Jelinek (jakub@redhat.com) + * Copyright (C) 1998 Eddie C. Dost (ecd@skynet.be) + * + * ppc64 changes: + * + * Copyright (C) 2000 Ken Aaker (kdaaker@rchland.vnet.ibm.com) + * Copyright (C) 2001 Anton Blanchard (antonb@au.ibm.com) + * + * These routines maintain argument size conversion between 32bit and 64bit + * ioctls. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#define INCLUDES +#include "compat_ioctl.c" +#include <linux/syscalls.h> + +#define CODE +#include "compat_ioctl.c" + +#define HANDLE_IOCTL(cmd,handler) { cmd, (ioctl_trans_handler_t)handler, NULL }, +#define COMPATIBLE_IOCTL(cmd) HANDLE_IOCTL(cmd,sys_ioctl) + +#define IOCTL_TABLE_START \ + struct ioctl_trans ioctl_start[] = { +#define IOCTL_TABLE_END \ + }; + +IOCTL_TABLE_START +#include <linux/compat_ioctl.h> +#define DECLARES +#include "compat_ioctl.c" + +/* Little p (/dev/rtc, /dev/envctrl, etc.) */ +COMPATIBLE_IOCTL(_IOR('p', 20, int[7])) /* RTCGET */ +COMPATIBLE_IOCTL(_IOW('p', 21, int[7])) /* RTCSET */ + +IOCTL_TABLE_END + +int ioctl_table_size = ARRAY_SIZE(ioctl_start); diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c new file mode 100644 index 00000000000..4b7940693f3 --- /dev/null +++ b/arch/powerpc/kernel/irq.c @@ -0,0 +1,478 @@ +/* + * arch/ppc/kernel/irq.c + * + * Derived from arch/i386/kernel/irq.c + * Copyright (C) 1992 Linus Torvalds + * Adapted from arch/i386 by Gary Thomas + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) + * Updated and modified by Cort Dougan <cort@fsmlabs.com> + * Copyright (C) 1996-2001 Cort Dougan + * Adapted for Power Macintosh by Paul Mackerras + * Copyright (C) 1996 Paul Mackerras (paulus@cs.anu.edu.au) + * Amiga/APUS changes by Jesper Skov (jskov@cygnus.co.uk). + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * This file contains the code used by various IRQ handling routines: + * asking for different IRQ's should be done through these routines + * instead of just grabbing them. Thus setups with different IRQ numbers + * shouldn't result in any weird surprises, and installing new handlers + * should be easier. + * + * The MPC8xx has an interrupt mask in the SIU. If a bit is set, the + * interrupt is _enabled_. As expected, IRQ0 is bit 0 in the 32-bit + * mask register (of which only 16 are defined), hence the weird shifting + * and complement of the cached_irq_mask. I want to be able to stuff + * this right into the SIU SMASK register. + * Many of the prep/chrp functions are conditional compiled on CONFIG_8xx + * to reduce code space and undefined function references. + */ + +#include <linux/errno.h> +#include <linux/module.h> +#include <linux/threads.h> +#include <linux/kernel_stat.h> +#include <linux/signal.h> +#include <linux/sched.h> +#include <linux/ptrace.h> +#include <linux/ioport.h> +#include <linux/interrupt.h> +#include <linux/timex.h> +#include <linux/config.h> +#include <linux/init.h> +#include <linux/slab.h> +#include <linux/pci.h> +#include <linux/delay.h> +#include <linux/irq.h> +#include <linux/proc_fs.h> +#include <linux/random.h> +#include <linux/seq_file.h> +#include <linux/cpumask.h> +#include <linux/profile.h> +#include <linux/bitops.h> +#ifdef CONFIG_PPC64 +#include <linux/kallsyms.h> +#endif + +#include <asm/uaccess.h> +#include <asm/system.h> +#include <asm/io.h> +#include <asm/pgtable.h> +#include <asm/irq.h> +#include <asm/cache.h> +#include <asm/prom.h> +#include <asm/ptrace.h> +#include <asm/machdep.h> +#ifdef CONFIG_PPC64 +#include <asm/iseries/it_lp_queue.h> +#include <asm/paca.h> +#endif + +static int ppc_spurious_interrupts; + +#if defined(CONFIG_PPC_ISERIES) && defined(CONFIG_SMP) +extern void iSeries_smp_message_recv(struct pt_regs *); +#endif + +#ifdef CONFIG_PPC32 +#define NR_MASK_WORDS ((NR_IRQS + 31) / 32) + +unsigned long ppc_cached_irq_mask[NR_MASK_WORDS]; +atomic_t ppc_n_lost_interrupts; + +#ifdef CONFIG_TAU_INT +extern int tau_initialized; +extern int tau_interrupts(int); +#endif + +#if defined(CONFIG_SMP) && !defined(CONFIG_PPC_MERGE) +extern atomic_t ipi_recv; +extern atomic_t ipi_sent; +#endif +#endif /* CONFIG_PPC32 */ + +#ifdef CONFIG_PPC64 +EXPORT_SYMBOL(irq_desc); + +int distribute_irqs = 1; +int __irq_offset_value; +u64 ppc64_interrupt_controller; +#endif /* CONFIG_PPC64 */ + +int show_interrupts(struct seq_file *p, void *v) +{ + int i = *(loff_t *)v, j; + struct irqaction *action; + irq_desc_t *desc; + unsigned long flags; + + if (i == 0) { + seq_puts(p, " "); + for_each_online_cpu(j) + seq_printf(p, "CPU%d ", j); + seq_putc(p, '\n'); + } + + if (i < NR_IRQS) { + desc = get_irq_desc(i); + spin_lock_irqsave(&desc->lock, flags); + action = desc->action; + if (!action || !action->handler) + goto skip; + seq_printf(p, "%3d: ", i); +#ifdef CONFIG_SMP + for_each_online_cpu(j) + seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]); +#else + seq_printf(p, "%10u ", kstat_irqs(i)); +#endif /* CONFIG_SMP */ + if (desc->handler) + seq_printf(p, " %s ", desc->handler->typename); + else + seq_puts(p, " None "); + seq_printf(p, "%s", (desc->status & IRQ_LEVEL) ? "Level " : "Edge "); + seq_printf(p, " %s", action->name); + for (action = action->next; action; action = action->next) + seq_printf(p, ", %s", action->name); + seq_putc(p, '\n'); +skip: + spin_unlock_irqrestore(&desc->lock, flags); + } else if (i == NR_IRQS) { +#ifdef CONFIG_PPC32 +#ifdef CONFIG_TAU_INT + if (tau_initialized){ + seq_puts(p, "TAU: "); + for (j = 0; j < NR_CPUS; j++) + if (cpu_online(j)) + seq_printf(p, "%10u ", tau_interrupts(j)); + seq_puts(p, " PowerPC Thermal Assist (cpu temp)\n"); + } +#endif +#if defined(CONFIG_SMP) && !defined(CONFIG_PPC_MERGE) + /* should this be per processor send/receive? */ + seq_printf(p, "IPI (recv/sent): %10u/%u\n", + atomic_read(&ipi_recv), atomic_read(&ipi_sent)); +#endif +#endif /* CONFIG_PPC32 */ + seq_printf(p, "BAD: %10u\n", ppc_spurious_interrupts); + } + return 0; +} + +#ifdef CONFIG_HOTPLUG_CPU +void fixup_irqs(cpumask_t map) +{ + unsigned int irq; + static int warned; + + for_each_irq(irq) { + cpumask_t mask; + + if (irq_desc[irq].status & IRQ_PER_CPU) + continue; + + cpus_and(mask, irq_affinity[irq], map); + if (any_online_cpu(mask) == NR_CPUS) { + printk("Breaking affinity for irq %i\n", irq); + mask = map; + } + if (irq_desc[irq].handler->set_affinity) + irq_desc[irq].handler->set_affinity(irq, mask); + else if (irq_desc[irq].action && !(warned++)) + printk("Cannot set affinity for irq %i\n", irq); + } + + local_irq_enable(); + mdelay(1); + local_irq_disable(); +} +#endif + +#ifdef CONFIG_PPC_ISERIES +void do_IRQ(struct pt_regs *regs) +{ + struct paca_struct *lpaca; + + irq_enter(); + +#ifdef CONFIG_DEBUG_STACKOVERFLOW + /* Debugging check for stack overflow: is there less than 2KB free? */ + { + long sp; + + sp = __get_SP() & (THREAD_SIZE-1); + + if (unlikely(sp < (sizeof(struct thread_info) + 2048))) { + printk("do_IRQ: stack overflow: %ld\n", + sp - sizeof(struct thread_info)); + dump_stack(); + } + } +#endif + + lpaca = get_paca(); +#ifdef CONFIG_SMP + if (lpaca->lppaca.int_dword.fields.ipi_cnt) { + lpaca->lppaca.int_dword.fields.ipi_cnt = 0; + iSeries_smp_message_recv(regs); + } +#endif /* CONFIG_SMP */ + if (hvlpevent_is_pending()) + process_hvlpevents(regs); + + irq_exit(); + + if (lpaca->lppaca.int_dword.fields.decr_int) { + lpaca->lppaca.int_dword.fields.decr_int = 0; + /* Signal a fake decrementer interrupt */ + timer_interrupt(regs); + } +} + +#else /* CONFIG_PPC_ISERIES */ + +void do_IRQ(struct pt_regs *regs) +{ + int irq; +#ifdef CONFIG_IRQSTACKS + struct thread_info *curtp, *irqtp; +#endif + + irq_enter(); + +#ifdef CONFIG_DEBUG_STACKOVERFLOW + /* Debugging check for stack overflow: is there less than 2KB free? */ + { + long sp; + + sp = __get_SP() & (THREAD_SIZE-1); + + if (unlikely(sp < (sizeof(struct thread_info) + 2048))) { + printk("do_IRQ: stack overflow: %ld\n", + sp - sizeof(struct thread_info)); + dump_stack(); + } + } +#endif + + /* + * Every platform is required to implement ppc_md.get_irq. + * This function will either return an irq number or -1 to + * indicate there are no more pending. + * The value -2 is for buggy hardware and means that this IRQ + * has already been handled. -- Tom + */ + irq = ppc_md.get_irq(regs); + + if (irq >= 0) { +#ifdef CONFIG_IRQSTACKS + /* Switch to the irq stack to handle this */ + curtp = current_thread_info(); + irqtp = hardirq_ctx[smp_processor_id()]; + if (curtp != irqtp) { + irqtp->task = curtp->task; + irqtp->flags = 0; + call___do_IRQ(irq, regs, irqtp); + irqtp->task = NULL; + if (irqtp->flags) + set_bits(irqtp->flags, &curtp->flags); + } else +#endif + __do_IRQ(irq, regs); + } else +#ifdef CONFIG_PPC32 + if (irq != -2) +#endif + /* That's not SMP safe ... but who cares ? */ + ppc_spurious_interrupts++; + irq_exit(); +} + +#endif /* CONFIG_PPC_ISERIES */ + +void __init init_IRQ(void) +{ +#ifdef CONFIG_PPC64 + static int once = 0; + + if (once) + return; + + once++; + +#endif + ppc_md.init_IRQ(); +#ifdef CONFIG_PPC64 + irq_ctx_init(); +#endif +} + +#ifdef CONFIG_PPC64 +#ifndef CONFIG_PPC_ISERIES +/* + * Virtual IRQ mapping code, used on systems with XICS interrupt controllers. + */ + +#define UNDEFINED_IRQ 0xffffffff +unsigned int virt_irq_to_real_map[NR_IRQS]; + +/* + * Don't use virtual irqs 0, 1, 2 for devices. + * The pcnet32 driver considers interrupt numbers < 2 to be invalid, + * and 2 is the XICS IPI interrupt. + * We limit virtual irqs to 17 less than NR_IRQS so that when we + * offset them by 16 (to reserve the first 16 for ISA interrupts) + * we don't end up with an interrupt number >= NR_IRQS. + */ +#define MIN_VIRT_IRQ 3 +#define MAX_VIRT_IRQ (NR_IRQS - NUM_ISA_INTERRUPTS - 1) +#define NR_VIRT_IRQS (MAX_VIRT_IRQ - MIN_VIRT_IRQ + 1) + +void +virt_irq_init(void) +{ + int i; + for (i = 0; i < NR_IRQS; i++) + virt_irq_to_real_map[i] = UNDEFINED_IRQ; +} + +/* Create a mapping for a real_irq if it doesn't already exist. + * Return the virtual irq as a convenience. + */ +int virt_irq_create_mapping(unsigned int real_irq) +{ + unsigned int virq, first_virq; + static int warned; + + if (ppc64_interrupt_controller == IC_OPEN_PIC) + return real_irq; /* no mapping for openpic (for now) */ + + if (ppc64_interrupt_controller == IC_CELL_PIC) + return real_irq; /* no mapping for iic either */ + + /* don't map interrupts < MIN_VIRT_IRQ */ + if (real_irq < MIN_VIRT_IRQ) { + virt_irq_to_real_map[real_irq] = real_irq; + return real_irq; + } + + /* map to a number between MIN_VIRT_IRQ and MAX_VIRT_IRQ */ + virq = real_irq; + if (virq > MAX_VIRT_IRQ) + virq = (virq % NR_VIRT_IRQS) + MIN_VIRT_IRQ; + + /* search for this number or a free slot */ + first_virq = virq; + while (virt_irq_to_real_map[virq] != UNDEFINED_IRQ) { + if (virt_irq_to_real_map[virq] == real_irq) + return virq; + if (++virq > MAX_VIRT_IRQ) + virq = MIN_VIRT_IRQ; + if (virq == first_virq) + goto nospace; /* oops, no free slots */ + } + + virt_irq_to_real_map[virq] = real_irq; + return virq; + + nospace: + if (!warned) { + printk(KERN_CRIT "Interrupt table is full\n"); + printk(KERN_CRIT "Increase NR_IRQS (currently %d) " + "in your kernel sources and rebuild.\n", NR_IRQS); + warned = 1; + } + return NO_IRQ; +} + +/* + * In most cases will get a hit on the very first slot checked in the + * virt_irq_to_real_map. Only when there are a large number of + * IRQs will this be expensive. + */ +unsigned int real_irq_to_virt_slowpath(unsigned int real_irq) +{ + unsigned int virq; + unsigned int first_virq; + + virq = real_irq; + + if (virq > MAX_VIRT_IRQ) + virq = (virq % NR_VIRT_IRQS) + MIN_VIRT_IRQ; + + first_virq = virq; + + do { + if (virt_irq_to_real_map[virq] == real_irq) + return virq; + + virq++; + + if (virq >= MAX_VIRT_IRQ) + virq = 0; + + } while (first_virq != virq); + + return NO_IRQ; + +} + +#endif /* CONFIG_PPC_ISERIES */ + +#ifdef CONFIG_IRQSTACKS +struct thread_info *softirq_ctx[NR_CPUS]; +struct thread_info *hardirq_ctx[NR_CPUS]; + +void irq_ctx_init(void) +{ + struct thread_info *tp; + int i; + + for_each_cpu(i) { + memset((void *)softirq_ctx[i], 0, THREAD_SIZE); + tp = softirq_ctx[i]; + tp->cpu = i; + tp->preempt_count = SOFTIRQ_OFFSET; + + memset((void *)hardirq_ctx[i], 0, THREAD_SIZE); + tp = hardirq_ctx[i]; + tp->cpu = i; + tp->preempt_count = HARDIRQ_OFFSET; + } +} + +void do_softirq(void) +{ + unsigned long flags; + struct thread_info *curtp, *irqtp; + + if (in_interrupt()) + return; + + local_irq_save(flags); + + if (local_softirq_pending()) { + curtp = current_thread_info(); + irqtp = softirq_ctx[smp_processor_id()]; + irqtp->task = curtp->task; + call_do_softirq(irqtp); + irqtp->task = NULL; + } + + local_irq_restore(flags); +} +EXPORT_SYMBOL(do_softirq); + +#endif /* CONFIG_IRQSTACKS */ + +static int __init setup_noirqdistrib(char *str) +{ + distribute_irqs = 0; + return 1; +} + +__setup("noirqdistrib", setup_noirqdistrib); +#endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c new file mode 100644 index 00000000000..1b3ba8a440a --- /dev/null +++ b/arch/powerpc/kernel/lparcfg.c @@ -0,0 +1,609 @@ +/* + * PowerPC64 LPAR Configuration Information Driver + * + * Dave Engebretsen engebret@us.ibm.com + * Copyright (c) 2003 Dave Engebretsen + * Will Schmidt willschm@us.ibm.com + * SPLPAR updates, Copyright (c) 2003 Will Schmidt IBM Corporation. + * seq_file updates, Copyright (c) 2004 Will Schmidt IBM Corporation. + * Nathan Lynch nathanl@austin.ibm.com + * Added lparcfg_write, Copyright (C) 2004 Nathan Lynch IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * This driver creates a proc file at /proc/ppc64/lparcfg which contains + * keyword - value pairs that specify the configuration of the partition. + */ + +#include <linux/config.h> +#include <linux/module.h> +#include <linux/types.h> +#include <linux/errno.h> +#include <linux/proc_fs.h> +#include <linux/init.h> +#include <linux/seq_file.h> +#include <asm/uaccess.h> +#include <asm/iseries/hv_lp_config.h> +#include <asm/lppaca.h> +#include <asm/hvcall.h> +#include <asm/firmware.h> +#include <asm/rtas.h> +#include <asm/system.h> +#include <asm/time.h> +#include <asm/iseries/it_exp_vpd_panel.h> +#include <asm/prom.h> +#include <asm/vdso_datapage.h> + +#define MODULE_VERS "1.6" +#define MODULE_NAME "lparcfg" + +/* #define LPARCFG_DEBUG */ + +/* find a better place for this function... */ +static void log_plpar_hcall_return(unsigned long rc, char *tag) +{ + if (rc == 0) /* success, return */ + return; +/* check for null tag ? */ + if (rc == H_Hardware) + printk(KERN_INFO + "plpar-hcall (%s) failed with hardware fault\n", tag); + else if (rc == H_Function) + printk(KERN_INFO + "plpar-hcall (%s) failed; function not allowed\n", tag); + else if (rc == H_Authority) + printk(KERN_INFO + "plpar-hcall (%s) failed; not authorized to this function\n", + tag); + else if (rc == H_Parameter) + printk(KERN_INFO "plpar-hcall (%s) failed; Bad parameter(s)\n", + tag); + else + printk(KERN_INFO + "plpar-hcall (%s) failed with unexpected rc(0x%lx)\n", + tag, rc); + +} + +static struct proc_dir_entry *proc_ppc64_lparcfg; +#define LPARCFG_BUFF_SIZE 4096 + +#ifdef CONFIG_PPC_ISERIES + +/* + * For iSeries legacy systems, the PPA purr function is available from the + * emulated_time_base field in the paca. + */ +static unsigned long get_purr(void) +{ + unsigned long sum_purr = 0; + int cpu; + struct paca_struct *lpaca; + + for_each_cpu(cpu) { + lpaca = paca + cpu; + sum_purr += lpaca->lppaca.emulated_time_base; + +#ifdef PURR_DEBUG + printk(KERN_INFO "get_purr for cpu (%d) has value (%ld) \n", + cpu, lpaca->lppaca.emulated_time_base); +#endif + } + return sum_purr; +} + +#define lparcfg_write NULL + +/* + * Methods used to fetch LPAR data when running on an iSeries platform. + */ +static int lparcfg_data(struct seq_file *m, void *v) +{ + unsigned long pool_id, lp_index; + int shared, entitled_capacity, max_entitled_capacity; + int processors, max_processors; + struct paca_struct *lpaca = get_paca(); + unsigned long purr = get_purr(); + + seq_printf(m, "%s %s \n", MODULE_NAME, MODULE_VERS); + + shared = (int)(lpaca->lppaca_ptr->shared_proc); + seq_printf(m, "serial_number=%c%c%c%c%c%c%c\n", + e2a(xItExtVpdPanel.mfgID[2]), + e2a(xItExtVpdPanel.mfgID[3]), + e2a(xItExtVpdPanel.systemSerial[1]), + e2a(xItExtVpdPanel.systemSerial[2]), + e2a(xItExtVpdPanel.systemSerial[3]), + e2a(xItExtVpdPanel.systemSerial[4]), + e2a(xItExtVpdPanel.systemSerial[5])); + + seq_printf(m, "system_type=%c%c%c%c\n", + e2a(xItExtVpdPanel.machineType[0]), + e2a(xItExtVpdPanel.machineType[1]), + e2a(xItExtVpdPanel.machineType[2]), + e2a(xItExtVpdPanel.machineType[3])); + + lp_index = HvLpConfig_getLpIndex(); + seq_printf(m, "partition_id=%d\n", (int)lp_index); + + seq_printf(m, "system_active_processors=%d\n", + (int)HvLpConfig_getSystemPhysicalProcessors()); + + seq_printf(m, "system_potential_processors=%d\n", + (int)HvLpConfig_getSystemPhysicalProcessors()); + + processors = (int)HvLpConfig_getPhysicalProcessors(); + seq_printf(m, "partition_active_processors=%d\n", processors); + + max_processors = (int)HvLpConfig_getMaxPhysicalProcessors(); + seq_printf(m, "partition_potential_processors=%d\n", max_processors); + + if (shared) { + entitled_capacity = HvLpConfig_getSharedProcUnits(); + max_entitled_capacity = HvLpConfig_getMaxSharedProcUnits(); + } else { + entitled_capacity = processors * 100; + max_entitled_capacity = max_processors * 100; + } + seq_printf(m, "partition_entitled_capacity=%d\n", entitled_capacity); + + seq_printf(m, "partition_max_entitled_capacity=%d\n", + max_entitled_capacity); + + if (shared) { + pool_id = HvLpConfig_getSharedPoolIndex(); + seq_printf(m, "pool=%d\n", (int)pool_id); + seq_printf(m, "pool_capacity=%d\n", + (int)(HvLpConfig_getNumProcsInSharedPool(pool_id) * + 100)); + seq_printf(m, "purr=%ld\n", purr); + } + + seq_printf(m, "shared_processor_mode=%d\n", shared); + + return 0; +} +#endif /* CONFIG_PPC_ISERIES */ + +#ifdef CONFIG_PPC_PSERIES +/* + * Methods used to fetch LPAR data when running on a pSeries platform. + */ + +/* + * H_GET_PPP hcall returns info in 4 parms. + * entitled_capacity,unallocated_capacity, + * aggregation, resource_capability). + * + * R4 = Entitled Processor Capacity Percentage. + * R5 = Unallocated Processor Capacity Percentage. + * R6 (AABBCCDDEEFFGGHH). + * XXXX - reserved (0) + * XXXX - reserved (0) + * XXXX - Group Number + * XXXX - Pool Number. + * R7 (IIJJKKLLMMNNOOPP). + * XX - reserved. (0) + * XX - bit 0-6 reserved (0). bit 7 is Capped indicator. + * XX - variable processor Capacity Weight + * XX - Unallocated Variable Processor Capacity Weight. + * XXXX - Active processors in Physical Processor Pool. + * XXXX - Processors active on platform. + */ +static unsigned int h_get_ppp(unsigned long *entitled, + unsigned long *unallocated, + unsigned long *aggregation, + unsigned long *resource) +{ + unsigned long rc; + rc = plpar_hcall_4out(H_GET_PPP, 0, 0, 0, 0, entitled, unallocated, + aggregation, resource); + + log_plpar_hcall_return(rc, "H_GET_PPP"); + + return rc; +} + +static void h_pic(unsigned long *pool_idle_time, unsigned long *num_procs) +{ + unsigned long rc; + unsigned long dummy; + rc = plpar_hcall(H_PIC, 0, 0, 0, 0, pool_idle_time, num_procs, &dummy); + + if (rc != H_Authority) + log_plpar_hcall_return(rc, "H_PIC"); +} + +/* Track sum of all purrs across all processors. This is used to further */ +/* calculate usage values by different applications */ + +static unsigned long get_purr(void) +{ + unsigned long sum_purr = 0; + int cpu; + struct cpu_usage *cu; + + for_each_cpu(cpu) { + cu = &per_cpu(cpu_usage_array, cpu); + sum_purr += cu->current_tb; + } + return sum_purr; +} + +#define SPLPAR_CHARACTERISTICS_TOKEN 20 +#define SPLPAR_MAXLENGTH 1026*(sizeof(char)) + +/* + * parse_system_parameter_string() + * Retrieve the potential_processors, max_entitled_capacity and friends + * through the get-system-parameter rtas call. Replace keyword strings as + * necessary. + */ +static void parse_system_parameter_string(struct seq_file *m) +{ + int call_status; + + char *local_buffer = kmalloc(SPLPAR_MAXLENGTH, GFP_KERNEL); + if (!local_buffer) { + printk(KERN_ERR "%s %s kmalloc failure at line %d \n", + __FILE__, __FUNCTION__, __LINE__); + return; + } + + spin_lock(&rtas_data_buf_lock); + memset(rtas_data_buf, 0, SPLPAR_MAXLENGTH); + call_status = rtas_call(rtas_token("ibm,get-system-parameter"), 3, 1, + NULL, + SPLPAR_CHARACTERISTICS_TOKEN, + __pa(rtas_data_buf)); + memcpy(local_buffer, rtas_data_buf, SPLPAR_MAXLENGTH); + spin_unlock(&rtas_data_buf_lock); + + if (call_status != 0) { + printk(KERN_INFO + "%s %s Error calling get-system-parameter (0x%x)\n", + __FILE__, __FUNCTION__, call_status); + } else { + int splpar_strlen; + int idx, w_idx; + char *workbuffer = kmalloc(SPLPAR_MAXLENGTH, GFP_KERNEL); + if (!workbuffer) { + printk(KERN_ERR "%s %s kmalloc failure at line %d \n", + __FILE__, __FUNCTION__, __LINE__); + kfree(local_buffer); + return; + } +#ifdef LPARCFG_DEBUG + printk(KERN_INFO "success calling get-system-parameter \n"); +#endif + splpar_strlen = local_buffer[0] * 16 + local_buffer[1]; + local_buffer += 2; /* step over strlen value */ + + memset(workbuffer, 0, SPLPAR_MAXLENGTH); + w_idx = 0; + idx = 0; + while ((*local_buffer) && (idx < splpar_strlen)) { + workbuffer[w_idx++] = local_buffer[idx++]; + if ((local_buffer[idx] == ',') + || (local_buffer[idx] == '\0')) { + workbuffer[w_idx] = '\0'; + if (w_idx) { + /* avoid the empty string */ + seq_printf(m, "%s\n", workbuffer); + } + memset(workbuffer, 0, SPLPAR_MAXLENGTH); + idx++; /* skip the comma */ + w_idx = 0; + } else if (local_buffer[idx] == '=') { + /* code here to replace workbuffer contents + with different keyword strings */ + if (0 == strcmp(workbuffer, "MaxEntCap")) { + strcpy(workbuffer, + "partition_max_entitled_capacity"); + w_idx = strlen(workbuffer); + } + if (0 == strcmp(workbuffer, "MaxPlatProcs")) { + strcpy(workbuffer, + "system_potential_processors"); + w_idx = strlen(workbuffer); + } + } + } + kfree(workbuffer); + local_buffer -= 2; /* back up over strlen value */ + } + kfree(local_buffer); +} + +/* Return the number of processors in the system. + * This function reads through the device tree and counts + * the virtual processors, this does not include threads. + */ +static int lparcfg_count_active_processors(void) +{ + struct device_node *cpus_dn = NULL; + int count = 0; + + while ((cpus_dn = of_find_node_by_type(cpus_dn, "cpu"))) { +#ifdef LPARCFG_DEBUG + printk(KERN_ERR "cpus_dn %p \n", cpus_dn); +#endif + count++; + } + return count; +} + +static int lparcfg_data(struct seq_file *m, void *v) +{ + int partition_potential_processors; + int partition_active_processors; + struct device_node *rootdn; + const char *model = ""; + const char *system_id = ""; + unsigned int *lp_index_ptr, lp_index = 0; + struct device_node *rtas_node; + int *lrdrp; + + rootdn = find_path_device("/"); + if (rootdn) { + model = get_property(rootdn, "model", NULL); + system_id = get_property(rootdn, "system-id", NULL); + lp_index_ptr = (unsigned int *) + get_property(rootdn, "ibm,partition-no", NULL); + if (lp_index_ptr) + lp_index = *lp_index_ptr; + } + + seq_printf(m, "%s %s \n", MODULE_NAME, MODULE_VERS); + + seq_printf(m, "serial_number=%s\n", system_id); + + seq_printf(m, "system_type=%s\n", model); + + seq_printf(m, "partition_id=%d\n", (int)lp_index); + + rtas_node = find_path_device("/rtas"); + lrdrp = (int *)get_property(rtas_node, "ibm,lrdr-capacity", NULL); + + if (lrdrp == NULL) { + partition_potential_processors = vdso_data->processorCount; + } else { + partition_potential_processors = *(lrdrp + 4); + } + + partition_active_processors = lparcfg_count_active_processors(); + + if (firmware_has_feature(FW_FEATURE_SPLPAR)) { + unsigned long h_entitled, h_unallocated; + unsigned long h_aggregation, h_resource; + unsigned long pool_idle_time, pool_procs; + unsigned long purr; + + h_get_ppp(&h_entitled, &h_unallocated, &h_aggregation, + &h_resource); + + seq_printf(m, "R4=0x%lx\n", h_entitled); + seq_printf(m, "R5=0x%lx\n", h_unallocated); + seq_printf(m, "R6=0x%lx\n", h_aggregation); + seq_printf(m, "R7=0x%lx\n", h_resource); + + purr = get_purr(); + + /* this call handles the ibm,get-system-parameter contents */ + parse_system_parameter_string(m); + + seq_printf(m, "partition_entitled_capacity=%ld\n", h_entitled); + + seq_printf(m, "group=%ld\n", (h_aggregation >> 2 * 8) & 0xffff); + + seq_printf(m, "system_active_processors=%ld\n", + (h_resource >> 0 * 8) & 0xffff); + + /* pool related entries are apropriate for shared configs */ + if (paca[0].lppaca.shared_proc) { + + h_pic(&pool_idle_time, &pool_procs); + + seq_printf(m, "pool=%ld\n", + (h_aggregation >> 0 * 8) & 0xffff); + + /* report pool_capacity in percentage */ + seq_printf(m, "pool_capacity=%ld\n", + ((h_resource >> 2 * 8) & 0xffff) * 100); + + seq_printf(m, "pool_idle_time=%ld\n", pool_idle_time); + + seq_printf(m, "pool_num_procs=%ld\n", pool_procs); + } + + seq_printf(m, "unallocated_capacity_weight=%ld\n", + (h_resource >> 4 * 8) & 0xFF); + + seq_printf(m, "capacity_weight=%ld\n", + (h_resource >> 5 * 8) & 0xFF); + + seq_printf(m, "capped=%ld\n", (h_resource >> 6 * 8) & 0x01); + + seq_printf(m, "unallocated_capacity=%ld\n", h_unallocated); + + seq_printf(m, "purr=%ld\n", purr); + + } else { /* non SPLPAR case */ + + seq_printf(m, "system_active_processors=%d\n", + partition_potential_processors); + + seq_printf(m, "system_potential_processors=%d\n", + partition_potential_processors); + + seq_printf(m, "partition_max_entitled_capacity=%d\n", + partition_potential_processors * 100); + + seq_printf(m, "partition_entitled_capacity=%d\n", + partition_active_processors * 100); + } + + seq_printf(m, "partition_active_processors=%d\n", + partition_active_processors); + + seq_printf(m, "partition_potential_processors=%d\n", + partition_potential_processors); + + seq_printf(m, "shared_processor_mode=%d\n", paca[0].lppaca.shared_proc); + + return 0; +} + +/* + * Interface for changing system parameters (variable capacity weight + * and entitled capacity). Format of input is "param_name=value"; + * anything after value is ignored. Valid parameters at this time are + * "partition_entitled_capacity" and "capacity_weight". We use + * H_SET_PPP to alter parameters. + * + * This function should be invoked only on systems with + * FW_FEATURE_SPLPAR. + */ +static ssize_t lparcfg_write(struct file *file, const char __user * buf, + size_t count, loff_t * off) +{ + char *kbuf; + char *tmp; + u64 new_entitled, *new_entitled_ptr = &new_entitled; + u8 new_weight, *new_weight_ptr = &new_weight; + + unsigned long current_entitled; /* parameters for h_get_ppp */ + unsigned long dummy; + unsigned long resource; + u8 current_weight; + + ssize_t retval = -ENOMEM; + + kbuf = kmalloc(count, GFP_KERNEL); + if (!kbuf) + goto out; + + retval = -EFAULT; + if (copy_from_user(kbuf, buf, count)) + goto out; + + retval = -EINVAL; + kbuf[count - 1] = '\0'; + tmp = strchr(kbuf, '='); + if (!tmp) + goto out; + + *tmp++ = '\0'; + + if (!strcmp(kbuf, "partition_entitled_capacity")) { + char *endp; + *new_entitled_ptr = (u64) simple_strtoul(tmp, &endp, 10); + if (endp == tmp) + goto out; + new_weight_ptr = ¤t_weight; + } else if (!strcmp(kbuf, "capacity_weight")) { + char *endp; + *new_weight_ptr = (u8) simple_strtoul(tmp, &endp, 10); + if (endp == tmp) + goto out; + new_entitled_ptr = ¤t_entitled; + } else + goto out; + + /* Get our current parameters */ + retval = h_get_ppp(¤t_entitled, &dummy, &dummy, &resource); + if (retval) { + retval = -EIO; + goto out; + } + + current_weight = (resource >> 5 * 8) & 0xFF; + + pr_debug("%s: current_entitled = %lu, current_weight = %lu\n", + __FUNCTION__, current_entitled, current_weight); + + pr_debug("%s: new_entitled = %lu, new_weight = %lu\n", + __FUNCTION__, *new_entitled_ptr, *new_weight_ptr); + + retval = plpar_hcall_norets(H_SET_PPP, *new_entitled_ptr, + *new_weight_ptr); + + if (retval == H_Success || retval == H_Constrained) { + retval = count; + } else if (retval == H_Busy) { + retval = -EBUSY; + } else if (retval == H_Hardware) { + retval = -EIO; + } else if (retval == H_Parameter) { + retval = -EINVAL; + } else { + printk(KERN_WARNING "%s: received unknown hv return code %ld", + __FUNCTION__, retval); + retval = -EIO; + } + +out: + kfree(kbuf); + return retval; +} + +#endif /* CONFIG_PPC_PSERIES */ + +static int lparcfg_open(struct inode *inode, struct file *file) +{ + return single_open(file, lparcfg_data, NULL); +} + +struct file_operations lparcfg_fops = { + .owner = THIS_MODULE, + .read = seq_read, + .open = lparcfg_open, + .release = single_release, +}; + +int __init lparcfg_init(void) +{ + struct proc_dir_entry *ent; + mode_t mode = S_IRUSR | S_IRGRP | S_IROTH; + + /* Allow writing if we have FW_FEATURE_SPLPAR */ + if (firmware_has_feature(FW_FEATURE_SPLPAR)) { + lparcfg_fops.write = lparcfg_write; + mode |= S_IWUSR; + } + + ent = create_proc_entry("ppc64/lparcfg", mode, NULL); + if (ent) { + ent->proc_fops = &lparcfg_fops; + ent->data = kmalloc(LPARCFG_BUFF_SIZE, GFP_KERNEL); + if (!ent->data) { + printk(KERN_ERR + "Failed to allocate buffer for lparcfg\n"); + remove_proc_entry("lparcfg", ent->parent); + return -ENOMEM; + } + } else { + printk(KERN_ERR "Failed to create ppc64/lparcfg\n"); + return -EIO; + } + + proc_ppc64_lparcfg = ent; + return 0; +} + +void __exit lparcfg_cleanup(void) +{ + if (proc_ppc64_lparcfg) { + kfree(proc_ppc64_lparcfg->data); + remove_proc_entry("lparcfg", proc_ppc64_lparcfg->parent); + } +} + +module_init(lparcfg_init); +module_exit(lparcfg_cleanup); +MODULE_DESCRIPTION("Interface for LPAR configuration data"); +MODULE_AUTHOR("Dave Engebretsen"); +MODULE_LICENSE("GPL"); diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 3bedb532aed..f6d84a75ed2 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -519,7 +519,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_SPLIT_ID_CACHE) * * flush_icache_range(unsigned long start, unsigned long stop) */ -_GLOBAL(flush_icache_range) +_GLOBAL(__flush_icache_range) BEGIN_FTR_SECTION blr /* for 601, do nothing */ END_FTR_SECTION_IFCLR(CPU_FTR_SPLIT_ID_CACHE) @@ -607,27 +607,6 @@ _GLOBAL(invalidate_dcache_range) sync /* wait for dcbi's to get to ram */ blr -#ifdef CONFIG_NOT_COHERENT_CACHE -/* - * 40x cores have 8K or 16K dcache and 32 byte line size. - * 44x has a 32K dcache and 32 byte line size. - * 8xx has 1, 2, 4, 8K variants. - * For now, cover the worst case of the 44x. - * Must be called with external interrupts disabled. - */ -#define CACHE_NWAYS 64 -#define CACHE_NLINES 16 - -_GLOBAL(flush_dcache_all) - li r4, (2 * CACHE_NWAYS * CACHE_NLINES) - mtctr r4 - lis r5, KERNELBASE@h -1: lwz r3, 0(r5) /* Load one word from every line */ - addi r5, r5, L1_CACHE_BYTES - bdnz 1b - blr -#endif /* CONFIG_NOT_COHERENT_CACHE */ - /* * Flush a particular page from the data cache to RAM. * Note: this is necessary because the instruction cache does *not* diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index ae1433da09b..ae48a002f81 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -89,12 +89,12 @@ _GLOBAL(call_do_softirq) mtlr r0 blr -_GLOBAL(call_handle_IRQ_event) +_GLOBAL(call___do_IRQ) mflr r0 std r0,16(r1) - stdu r1,THREAD_SIZE-112(r6) - mr r1,r6 - bl .handle_IRQ_event + stdu r1,THREAD_SIZE-112(r5) + mr r1,r5 + bl .__do_IRQ ld r1,0(r1) ld r0,16(r1) mtlr r0 diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c new file mode 100644 index 00000000000..a7b68f911eb --- /dev/null +++ b/arch/powerpc/kernel/paca.c @@ -0,0 +1,135 @@ +/* + * c 2001 PPC 64 Team, IBM Corp + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/config.h> +#include <linux/types.h> +#include <linux/threads.h> +#include <linux/module.h> + +#include <asm/processor.h> +#include <asm/ptrace.h> +#include <asm/page.h> +#include <asm/lppaca.h> +#include <asm/iseries/it_lp_queue.h> +#include <asm/paca.h> + + +/* This symbol is provided by the linker - let it fill in the paca + * field correctly */ +extern unsigned long __toc_start; + +/* The Paca is an array with one entry per processor. Each contains an + * lppaca, which contains the information shared between the + * hypervisor and Linux. Each also contains an ItLpRegSave area which + * is used by the hypervisor to save registers. + * On systems with hardware multi-threading, there are two threads + * per processor. The Paca array must contain an entry for each thread. + * The VPD Areas will give a max logical processors = 2 * max physical + * processors. The processor VPD array needs one entry per physical + * processor (not thread). + */ +#define PACA_INIT_COMMON(number, start, asrr, asrv) \ + .lock_token = 0x8000, \ + .paca_index = (number), /* Paca Index */ \ + .default_decr = 0x00ff0000, /* Initial Decr */ \ + .kernel_toc = (unsigned long)(&__toc_start) + 0x8000UL, \ + .stab_real = (asrr), /* Real pointer to segment table */ \ + .stab_addr = (asrv), /* Virt pointer to segment table */ \ + .cpu_start = (start), /* Processor start */ \ + .hw_cpu_id = 0xffff, \ + .lppaca = { \ + .desc = 0xd397d781, /* "LpPa" */ \ + .size = sizeof(struct lppaca), \ + .dyn_proc_status = 2, \ + .decr_val = 0x00ff0000, \ + .fpregs_in_use = 1, \ + .end_of_quantum = 0xfffffffffffffffful, \ + .slb_count = 64, \ + .vmxregs_in_use = 0, \ + }, \ + +#ifdef CONFIG_PPC_ISERIES +#define PACA_INIT_ISERIES(number) \ + .lppaca_ptr = &paca[number].lppaca, \ + .reg_save_ptr = &paca[number].reg_save, \ + .reg_save = { \ + .xDesc = 0xd397d9e2, /* "LpRS" */ \ + .xSize = sizeof(struct ItLpRegSave) \ + } + +#define PACA_INIT(number) \ +{ \ + PACA_INIT_COMMON(number, 0, 0, 0) \ + PACA_INIT_ISERIES(number) \ +} + +#define BOOTCPU_PACA_INIT(number) \ +{ \ + PACA_INIT_COMMON(number, 1, 0, (u64)&initial_stab) \ + PACA_INIT_ISERIES(number) \ +} + +#else +#define PACA_INIT(number) \ +{ \ + PACA_INIT_COMMON(number, 0, 0, 0) \ +} + +#define BOOTCPU_PACA_INIT(number) \ +{ \ + PACA_INIT_COMMON(number, 1, STAB0_PHYS_ADDR, (u64)&initial_stab) \ +} +#endif + +struct paca_struct paca[] = { + BOOTCPU_PACA_INIT(0), +#if NR_CPUS > 1 + PACA_INIT( 1), PACA_INIT( 2), PACA_INIT( 3), +#if NR_CPUS > 4 + PACA_INIT( 4), PACA_INIT( 5), PACA_INIT( 6), PACA_INIT( 7), +#if NR_CPUS > 8 + PACA_INIT( 8), PACA_INIT( 9), PACA_INIT( 10), PACA_INIT( 11), + PACA_INIT( 12), PACA_INIT( 13), PACA_INIT( 14), PACA_INIT( 15), + PACA_INIT( 16), PACA_INIT( 17), PACA_INIT( 18), PACA_INIT( 19), + PACA_INIT( 20), PACA_INIT( 21), PACA_INIT( 22), PACA_INIT( 23), + PACA_INIT( 24), PACA_INIT( 25), PACA_INIT( 26), PACA_INIT( 27), + PACA_INIT( 28), PACA_INIT( 29), PACA_INIT( 30), PACA_INIT( 31), +#if NR_CPUS > 32 + PACA_INIT( 32), PACA_INIT( 33), PACA_INIT( 34), PACA_INIT( 35), + PACA_INIT( 36), PACA_INIT( 37), PACA_INIT( 38), PACA_INIT( 39), + PACA_INIT( 40), PACA_INIT( 41), PACA_INIT( 42), PACA_INIT( 43), + PACA_INIT( 44), PACA_INIT( 45), PACA_INIT( 46), PACA_INIT( 47), + PACA_INIT( 48), PACA_INIT( 49), PACA_INIT( 50), PACA_INIT( 51), + PACA_INIT( 52), PACA_INIT( 53), PACA_INIT( 54), PACA_INIT( 55), + PACA_INIT( 56), PACA_INIT( 57), PACA_INIT( 58), PACA_INIT( 59), + PACA_INIT( 60), PACA_INIT( 61), PACA_INIT( 62), PACA_INIT( 63), +#if NR_CPUS > 64 + PACA_INIT( 64), PACA_INIT( 65), PACA_INIT( 66), PACA_INIT( 67), + PACA_INIT( 68), PACA_INIT( 69), PACA_INIT( 70), PACA_INIT( 71), + PACA_INIT( 72), PACA_INIT( 73), PACA_INIT( 74), PACA_INIT( 75), + PACA_INIT( 76), PACA_INIT( 77), PACA_INIT( 78), PACA_INIT( 79), + PACA_INIT( 80), PACA_INIT( 81), PACA_INIT( 82), PACA_INIT( 83), + PACA_INIT( 84), PACA_INIT( 85), PACA_INIT( 86), PACA_INIT( 87), + PACA_INIT( 88), PACA_INIT( 89), PACA_INIT( 90), PACA_INIT( 91), + PACA_INIT( 92), PACA_INIT( 93), PACA_INIT( 94), PACA_INIT( 95), + PACA_INIT( 96), PACA_INIT( 97), PACA_INIT( 98), PACA_INIT( 99), + PACA_INIT(100), PACA_INIT(101), PACA_INIT(102), PACA_INIT(103), + PACA_INIT(104), PACA_INIT(105), PACA_INIT(106), PACA_INIT(107), + PACA_INIT(108), PACA_INIT(109), PACA_INIT(110), PACA_INIT(111), + PACA_INIT(112), PACA_INIT(113), PACA_INIT(114), PACA_INIT(115), + PACA_INIT(116), PACA_INIT(117), PACA_INIT(118), PACA_INIT(119), + PACA_INIT(120), PACA_INIT(121), PACA_INIT(122), PACA_INIT(123), + PACA_INIT(124), PACA_INIT(125), PACA_INIT(126), PACA_INIT(127), +#endif +#endif +#endif +#endif +#endif +}; +EXPORT_SYMBOL(paca); diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index 47d6f7e2ea9..5dcf4ba05ee 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -44,6 +44,7 @@ #include <asm/cputable.h> #include <asm/btext.h> #include <asm/div64.h> +#include <asm/signal.h> #ifdef CONFIG_8xx #include <asm/commproc.h> @@ -56,7 +57,6 @@ extern void machine_check_exception(struct pt_regs *regs); extern void alignment_exception(struct pt_regs *regs); extern void program_check_exception(struct pt_regs *regs); extern void single_step_exception(struct pt_regs *regs); -extern int do_signal(sigset_t *, struct pt_regs *); extern int pmac_newworld; extern int sys_sigreturn(struct pt_regs *regs); @@ -188,9 +188,6 @@ EXPORT_SYMBOL(adb_try_handler_change); EXPORT_SYMBOL(cuda_request); EXPORT_SYMBOL(cuda_poll); #endif /* CONFIG_ADB_CUDA */ -#if defined(CONFIG_PPC_MULTIPLATFORM) && defined(CONFIG_PPC32) -EXPORT_SYMBOL(_machine); -#endif #ifdef CONFIG_PPC_PMAC EXPORT_SYMBOL(sys_ctrler); #endif diff --git a/arch/powerpc/kernel/proc_ppc64.c b/arch/powerpc/kernel/proc_ppc64.c new file mode 100644 index 00000000000..7ba42a405f4 --- /dev/null +++ b/arch/powerpc/kernel/proc_ppc64.c @@ -0,0 +1,126 @@ +/* + * Copyright (C) 2001 Mike Corrigan & Dave Engebretsen IBM Corporation + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program 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 General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include <linux/config.h> +#include <linux/init.h> +#include <linux/mm.h> +#include <linux/proc_fs.h> +#include <linux/slab.h> +#include <linux/kernel.h> + +#include <asm/vdso_datapage.h> +#include <asm/rtas.h> +#include <asm/uaccess.h> +#include <asm/prom.h> + +static loff_t page_map_seek( struct file *file, loff_t off, int whence); +static ssize_t page_map_read( struct file *file, char __user *buf, size_t nbytes, + loff_t *ppos); +static int page_map_mmap( struct file *file, struct vm_area_struct *vma ); + +static struct file_operations page_map_fops = { + .llseek = page_map_seek, + .read = page_map_read, + .mmap = page_map_mmap +}; + +/* + * Create the ppc64 and ppc64/rtas directories early. This allows us to + * assume that they have been previously created in drivers. + */ +static int __init proc_ppc64_create(void) +{ + struct proc_dir_entry *root; + + root = proc_mkdir("ppc64", NULL); + if (!root) + return 1; + + if (!(platform_is_pseries() || _machine == PLATFORM_CELL)) + return 0; + + if (!proc_mkdir("rtas", root)) + return 1; + + if (!proc_symlink("rtas", NULL, "ppc64/rtas")) + return 1; + + return 0; +} +core_initcall(proc_ppc64_create); + +static int __init proc_ppc64_init(void) +{ + struct proc_dir_entry *pde; + + pde = create_proc_entry("ppc64/systemcfg", S_IFREG|S_IRUGO, NULL); + if (!pde) + return 1; + pde->nlink = 1; + pde->data = vdso_data; + pde->size = PAGE_SIZE; + pde->proc_fops = &page_map_fops; + + return 0; +} +__initcall(proc_ppc64_init); + +static loff_t page_map_seek( struct file *file, loff_t off, int whence) +{ + loff_t new; + struct proc_dir_entry *dp = PDE(file->f_dentry->d_inode); + + switch(whence) { + case 0: + new = off; + break; + case 1: + new = file->f_pos + off; + break; + case 2: + new = dp->size + off; + break; + default: + return -EINVAL; + } + if ( new < 0 || new > dp->size ) + return -EINVAL; + return (file->f_pos = new); +} + +static ssize_t page_map_read( struct file *file, char __user *buf, size_t nbytes, + loff_t *ppos) +{ + struct proc_dir_entry *dp = PDE(file->f_dentry->d_inode); + return simple_read_from_buffer(buf, nbytes, ppos, dp->data, dp->size); +} + +static int page_map_mmap( struct file *file, struct vm_area_struct *vma ) +{ + struct proc_dir_entry *dp = PDE(file->f_dentry->d_inode); + + vma->vm_flags |= VM_SHM | VM_LOCKED; + + if ((vma->vm_end - vma->vm_start) > dp->size) + return -EINVAL; + + remap_pfn_range(vma, vma->vm_start, __pa(dp->data) >> PAGE_SHIFT, + dp->size, vma->vm_page_prot); + return 0; +} + diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index f645adb5753..6a5b468edb4 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -48,9 +48,6 @@ #include <asm/machdep.h> #include <asm/pSeries_reconfig.h> #include <asm/pci-bridge.h> -#ifdef CONFIG_PPC64 -#include <asm/systemcfg.h> -#endif #ifdef DEBUG #define DBG(fmt...) printk(KERN_ERR fmt) @@ -74,10 +71,6 @@ struct isa_reg_property { typedef int interpret_func(struct device_node *, unsigned long *, int, int, int); -extern struct rtas_t rtas; -extern struct lmb lmb; -extern unsigned long klimit; - static int __initdata dt_root_addr_cells; static int __initdata dt_root_size_cells; @@ -391,7 +384,7 @@ static int __devinit finish_node_interrupts(struct device_node *np, #ifdef CONFIG_PPC64 /* We offset irq numbers for the u3 MPIC by 128 in PowerMac */ - if (systemcfg->platform == PLATFORM_POWERMAC && ic && ic->parent) { + if (_machine == PLATFORM_POWERMAC && ic && ic->parent) { char *name = get_property(ic->parent, "name", NULL); if (name && !strcmp(name, "u3")) np->intrs[intrcount].line += 128; @@ -1087,9 +1080,9 @@ void __init unflatten_device_tree(void) static int __init early_init_dt_scan_cpus(unsigned long node, const char *uname, int depth, void *data) { - char *type = of_get_flat_dt_prop(node, "device_type", NULL); u32 *prop; - unsigned long size = 0; + unsigned long size; + char *type = of_get_flat_dt_prop(node, "device_type", &size); /* We are scanning "cpu" nodes only */ if (type == NULL || strcmp(type, "cpu") != 0) @@ -1115,7 +1108,7 @@ static int __init early_init_dt_scan_cpus(unsigned long node, #ifdef CONFIG_ALTIVEC /* Check if we have a VMX and eventually update CPU features */ - prop = (u32 *)of_get_flat_dt_prop(node, "ibm,vmx", &size); + prop = (u32 *)of_get_flat_dt_prop(node, "ibm,vmx", NULL); if (prop && (*prop) > 0) { cur_cpu_spec->cpu_features |= CPU_FTR_ALTIVEC; cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_ALTIVEC; @@ -1161,13 +1154,9 @@ static int __init early_init_dt_scan_chosen(unsigned long node, prop = (u32 *)of_get_flat_dt_prop(node, "linux,platform", NULL); if (prop == NULL) return 0; -#ifdef CONFIG_PPC64 - systemcfg->platform = *prop; -#else #ifdef CONFIG_PPC_MULTIPLATFORM _machine = *prop; #endif -#endif #ifdef CONFIG_PPC64 /* check if iommu is forced on or off */ @@ -1264,7 +1253,14 @@ static int __init early_init_dt_scan_memory(unsigned long node, unsigned long l; /* We are scanning "memory" nodes only */ - if (type == NULL || strcmp(type, "memory") != 0) + if (type == NULL) { + /* + * The longtrail doesn't have a device_type on the + * /memory node, so look for the node called /memory@0. + */ + if (depth != 1 || strcmp(uname, "memory@0") != 0) + return 0; + } else if (strcmp(type, "memory") != 0) return 0; reg = (cell_t *)of_get_flat_dt_prop(node, "reg", &l); @@ -1339,9 +1335,6 @@ void __init early_init_devtree(void *params) of_scan_flat_dt(early_init_dt_scan_memory, NULL); lmb_enforce_memory_limit(memory_limit); lmb_analyze(); -#ifdef CONFIG_PPC64 - systemcfg->physicalMemorySize = lmb_phys_mem_size(); -#endif lmb_reserve(0, __pa(klimit)); DBG("Phys. mem: %lx\n", lmb_phys_mem_size()); @@ -1908,7 +1901,7 @@ static int of_finish_dynamic_node(struct device_node *node, /* We don't support that function on PowerMac, at least * not yet */ - if (systemcfg->platform == PLATFORM_POWERMAC) + if (_machine == PLATFORM_POWERMAC) return -ENODEV; /* fix up new node's linux_phandle field */ @@ -1992,9 +1985,11 @@ int prom_add_property(struct device_node* np, struct property* prop) *next = prop; write_unlock(&devtree_lock); +#ifdef CONFIG_PROC_DEVICETREE /* try to add to proc as well if it was initialized */ if (np->pde) proc_device_tree_add_prop(np->pde, prop); +#endif /* CONFIG_PROC_DEVICETREE */ return 0; } diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 6dc33d19fc2..4ce0105c308 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -94,11 +94,17 @@ extern const struct linux_logo logo_linux_clut224; #ifdef CONFIG_PPC64 #define RELOC(x) (*PTRRELOC(&(x))) #define ADDR(x) (u32) add_reloc_offset((unsigned long)(x)) +#define OF_WORKAROUNDS 0 #else #define RELOC(x) (x) #define ADDR(x) (u32) (x) +#define OF_WORKAROUNDS of_workarounds +int of_workarounds; #endif +#define OF_WA_CLAIM 1 /* do phys/virt claim separately, then map */ +#define OF_WA_LONGTRAIL 2 /* work around longtrail bugs */ + #define PROM_BUG() do { \ prom_printf("kernel BUG at %s line 0x%x!\n", \ RELOC(__FILE__), __LINE__); \ @@ -111,11 +117,6 @@ extern const struct linux_logo logo_linux_clut224; #define prom_debug(x...) #endif -#ifdef CONFIG_PPC32 -#define PLATFORM_POWERMAC _MACH_Pmac -#define PLATFORM_CHRP _MACH_chrp -#endif - typedef u32 prom_arg_t; @@ -128,10 +129,11 @@ struct prom_args { struct prom_t { ihandle root; - ihandle chosen; + phandle chosen; int cpu; ihandle stdout; ihandle mmumap; + ihandle memory; }; struct mem_map_entry { @@ -360,16 +362,36 @@ static void __init prom_printf(const char *format, ...) static unsigned int __init prom_claim(unsigned long virt, unsigned long size, unsigned long align) { - int ret; struct prom_t *_prom = &RELOC(prom); - ret = call_prom("claim", 3, 1, (prom_arg_t)virt, (prom_arg_t)size, - (prom_arg_t)align); - if (ret != -1 && _prom->mmumap != 0) - /* old pmacs need us to map as well */ + if (align == 0 && (OF_WORKAROUNDS & OF_WA_CLAIM)) { + /* + * Old OF requires we claim physical and virtual separately + * and then map explicitly (assuming virtual mode) + */ + int ret; + prom_arg_t result; + + ret = call_prom_ret("call-method", 5, 2, &result, + ADDR("claim"), _prom->memory, + align, size, virt); + if (ret != 0 || result == -1) + return -1; + ret = call_prom_ret("call-method", 5, 2, &result, + ADDR("claim"), _prom->mmumap, + align, size, virt); + if (ret != 0) { + call_prom("call-method", 4, 1, ADDR("release"), + _prom->memory, size, virt); + return -1; + } + /* the 0x12 is M (coherence) + PP == read/write */ call_prom("call-method", 6, 1, - ADDR("map"), _prom->mmumap, 0, size, virt, virt); - return ret; + ADDR("map"), _prom->mmumap, 0x12, size, virt, virt); + return virt; + } + return call_prom("claim", 3, 1, (prom_arg_t)virt, (prom_arg_t)size, + (prom_arg_t)align); } static void __init __attribute__((noreturn)) prom_panic(const char *reason) @@ -415,11 +437,52 @@ static int inline prom_getproplen(phandle node, const char *pname) return call_prom("getproplen", 2, 1, node, ADDR(pname)); } -static int inline prom_setprop(phandle node, const char *pname, - void *value, size_t valuelen) +static void add_string(char **str, const char *q) { - return call_prom("setprop", 4, 1, node, ADDR(pname), - (u32)(unsigned long) value, (u32) valuelen); + char *p = *str; + + while (*q) + *p++ = *q++; + *p++ = ' '; + *str = p; +} + +static char *tohex(unsigned int x) +{ + static char digits[] = "0123456789abcdef"; + static char result[9]; + int i; + + result[8] = 0; + i = 8; + do { + --i; + result[i] = digits[x & 0xf]; + x >>= 4; + } while (x != 0 && i > 0); + return &result[i]; +} + +static int __init prom_setprop(phandle node, const char *nodename, + const char *pname, void *value, size_t valuelen) +{ + char cmd[256], *p; + + if (!(OF_WORKAROUNDS & OF_WA_LONGTRAIL)) + return call_prom("setprop", 4, 1, node, ADDR(pname), + (u32)(unsigned long) value, (u32) valuelen); + + /* gah... setprop doesn't work on longtrail, have to use interpret */ + p = cmd; + add_string(&p, "dev"); + add_string(&p, nodename); + add_string(&p, tohex((u32)(unsigned long) value)); + add_string(&p, tohex(valuelen)); + add_string(&p, tohex(ADDR(pname))); + add_string(&p, tohex(strlen(RELOC(pname)))); + add_string(&p, "property"); + *p = 0; + return call_prom("interpret", 1, 1, (u32)(unsigned long) cmd); } /* We can't use the standard versions because of RELOC headaches. */ @@ -980,7 +1043,7 @@ static void __init prom_instantiate_rtas(void) rtas_inst = call_prom("open", 1, 1, ADDR("/rtas")); if (!IHANDLE_VALID(rtas_inst)) { - prom_printf("opening rtas package failed"); + prom_printf("opening rtas package failed (%x)\n", rtas_inst); return; } @@ -988,7 +1051,7 @@ static void __init prom_instantiate_rtas(void) if (call_prom_ret("call-method", 3, 2, &entry, ADDR("instantiate-rtas"), - rtas_inst, base) == PROM_ERROR + rtas_inst, base) != 0 || entry == 0) { prom_printf(" failed\n"); return; @@ -997,8 +1060,10 @@ static void __init prom_instantiate_rtas(void) reserve_mem(base, size); - prom_setprop(rtas_node, "linux,rtas-base", &base, sizeof(base)); - prom_setprop(rtas_node, "linux,rtas-entry", &entry, sizeof(entry)); + prom_setprop(rtas_node, "/rtas", "linux,rtas-base", + &base, sizeof(base)); + prom_setprop(rtas_node, "/rtas", "linux,rtas-entry", + &entry, sizeof(entry)); prom_debug("rtas base = 0x%x\n", base); prom_debug("rtas entry = 0x%x\n", entry); @@ -1089,10 +1154,6 @@ static void __init prom_initialize_tce_table(void) if (base < local_alloc_bottom) local_alloc_bottom = base; - /* Save away the TCE table attributes for later use. */ - prom_setprop(node, "linux,tce-base", &base, sizeof(base)); - prom_setprop(node, "linux,tce-size", &minsize, sizeof(minsize)); - /* It seems OF doesn't null-terminate the path :-( */ memset(path, 0, sizeof(path)); /* Call OF to setup the TCE hardware */ @@ -1101,6 +1162,10 @@ static void __init prom_initialize_tce_table(void) prom_printf("package-to-path failed\n"); } + /* Save away the TCE table attributes for later use. */ + prom_setprop(node, path, "linux,tce-base", &base, sizeof(base)); + prom_setprop(node, path, "linux,tce-size", &minsize, sizeof(minsize)); + prom_debug("TCE table: %s\n", path); prom_debug("\tnode = 0x%x\n", node); prom_debug("\tbase = 0x%x\n", base); @@ -1342,6 +1407,7 @@ static void __init prom_init_client_services(unsigned long pp) /* * For really old powermacs, we need to map things we claim. * For that, we need the ihandle of the mmu. + * Also, on the longtrail, we need to work around other bugs. */ static void __init prom_find_mmu(void) { @@ -1355,12 +1421,19 @@ static void __init prom_find_mmu(void) if (prom_getprop(oprom, "model", version, sizeof(version)) <= 0) return; version[sizeof(version) - 1] = 0; - prom_printf("OF version is '%s'\n", version); /* XXX might need to add other versions here */ - if (strcmp(version, "Open Firmware, 1.0.5") != 0) + if (strcmp(version, "Open Firmware, 1.0.5") == 0) + of_workarounds = OF_WA_CLAIM; + else if (strncmp(version, "FirmWorks,3.", 12) == 0) { + of_workarounds = OF_WA_CLAIM | OF_WA_LONGTRAIL; + call_prom("interpret", 1, 1, "dev /memory 0 to allow-reclaim"); + } else return; + _prom->memory = call_prom("open", 1, 1, ADDR("/memory")); prom_getprop(_prom->chosen, "mmu", &_prom->mmumap, sizeof(_prom->mmumap)); + if (!IHANDLE_VALID(_prom->memory) || !IHANDLE_VALID(_prom->mmumap)) + of_workarounds &= ~OF_WA_CLAIM; /* hmmm */ } #else #define prom_find_mmu() @@ -1382,16 +1455,17 @@ static void __init prom_init_stdout(void) memset(path, 0, 256); call_prom("instance-to-path", 3, 1, _prom->stdout, path, 255); val = call_prom("instance-to-package", 1, 1, _prom->stdout); - prom_setprop(_prom->chosen, "linux,stdout-package", &val, sizeof(val)); + prom_setprop(_prom->chosen, "/chosen", "linux,stdout-package", + &val, sizeof(val)); prom_printf("OF stdout device is: %s\n", RELOC(of_stdout_device)); - prom_setprop(_prom->chosen, "linux,stdout-path", - RELOC(of_stdout_device), strlen(RELOC(of_stdout_device))+1); + prom_setprop(_prom->chosen, "/chosen", "linux,stdout-path", + path, strlen(path) + 1); /* If it's a display, note it */ memset(type, 0, sizeof(type)); prom_getprop(val, "device_type", type, sizeof(type)); if (strcmp(type, RELOC("display")) == 0) - prom_setprop(val, "linux,boot-display", NULL, 0); + prom_setprop(val, path, "linux,boot-display", NULL, 0); } static void __init prom_close_stdin(void) @@ -1514,7 +1588,7 @@ static void __init prom_check_displays(void) /* Success */ prom_printf("done\n"); - prom_setprop(node, "linux,opened", NULL, 0); + prom_setprop(node, path, "linux,opened", NULL, 0); /* Setup a usable color table when the appropriate * method is available. Should update this to set-colors */ @@ -1884,9 +1958,11 @@ static void __init fixup_device_tree(void) /* interrupt on this revision of u3 is number 0 and level */ interrupts[0] = 0; interrupts[1] = 1; - prom_setprop(i2c, "interrupts", &interrupts, sizeof(interrupts)); + prom_setprop(i2c, "/u3@0,f8000000/i2c@f8001000", "interrupts", + &interrupts, sizeof(interrupts)); parent = (u32)mpic; - prom_setprop(i2c, "interrupt-parent", &parent, sizeof(parent)); + prom_setprop(i2c, "/u3@0,f8000000/i2c@f8001000", "interrupt-parent", + &parent, sizeof(parent)); #endif } @@ -1922,11 +1998,11 @@ static void __init prom_check_initrd(unsigned long r3, unsigned long r4) RELOC(prom_initrd_end) = RELOC(prom_initrd_start) + r4; val = RELOC(prom_initrd_start); - prom_setprop(_prom->chosen, "linux,initrd-start", &val, - sizeof(val)); + prom_setprop(_prom->chosen, "/chosen", "linux,initrd-start", + &val, sizeof(val)); val = RELOC(prom_initrd_end); - prom_setprop(_prom->chosen, "linux,initrd-end", &val, - sizeof(val)); + prom_setprop(_prom->chosen, "/chosen", "linux,initrd-end", + &val, sizeof(val)); reserve_mem(RELOC(prom_initrd_start), RELOC(prom_initrd_end) - RELOC(prom_initrd_start)); @@ -1969,14 +2045,15 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, prom_init_client_services(pp); /* - * Init prom stdout device + * See if this OF is old enough that we need to do explicit maps + * and other workarounds */ - prom_init_stdout(); + prom_find_mmu(); /* - * See if this OF is old enough that we need to do explicit maps + * Init prom stdout device */ - prom_find_mmu(); + prom_init_stdout(); /* * Check for an initrd @@ -1989,14 +2066,15 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, */ RELOC(of_platform) = prom_find_machine_type(); getprop_rval = RELOC(of_platform); - prom_setprop(_prom->chosen, "linux,platform", + prom_setprop(_prom->chosen, "/chosen", "linux,platform", &getprop_rval, sizeof(getprop_rval)); #ifdef CONFIG_PPC_PSERIES /* * On pSeries, inform the firmware about our capabilities */ - if (RELOC(of_platform) & PLATFORM_PSERIES) + if (RELOC(of_platform) == PLATFORM_PSERIES || + RELOC(of_platform) == PLATFORM_PSERIES_LPAR) prom_send_capabilities(); #endif @@ -2050,21 +2128,23 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, * Fill in some infos for use by the kernel later on */ if (RELOC(prom_memory_limit)) - prom_setprop(_prom->chosen, "linux,memory-limit", + prom_setprop(_prom->chosen, "/chosen", "linux,memory-limit", &RELOC(prom_memory_limit), sizeof(prom_memory_limit)); #ifdef CONFIG_PPC64 if (RELOC(ppc64_iommu_off)) - prom_setprop(_prom->chosen, "linux,iommu-off", NULL, 0); + prom_setprop(_prom->chosen, "/chosen", "linux,iommu-off", + NULL, 0); if (RELOC(iommu_force_on)) - prom_setprop(_prom->chosen, "linux,iommu-force-on", NULL, 0); + prom_setprop(_prom->chosen, "/chosen", "linux,iommu-force-on", + NULL, 0); if (RELOC(prom_tce_alloc_start)) { - prom_setprop(_prom->chosen, "linux,tce-alloc-start", + prom_setprop(_prom->chosen, "/chosen", "linux,tce-alloc-start", &RELOC(prom_tce_alloc_start), sizeof(prom_tce_alloc_start)); - prom_setprop(_prom->chosen, "linux,tce-alloc-end", + prom_setprop(_prom->chosen, "/chosen", "linux,tce-alloc-end", &RELOC(prom_tce_alloc_end), sizeof(prom_tce_alloc_end)); } @@ -2081,8 +2161,13 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, prom_printf("copying OF device tree ...\n"); flatten_device_tree(); - /* in case stdin is USB and still active on IBM machines... */ - prom_close_stdin(); + /* + * in case stdin is USB and still active on IBM machines... + * Unfortunately quiesce crashes on some powermacs if we have + * closed stdin already (in particular the powerbook 101). + */ + if (RELOC(of_platform) != PLATFORM_POWERMAC) + prom_close_stdin(); /* * Call OF "quiesce" method to shut down pending DMA's from diff --git a/arch/powerpc/kernel/rtas-proc.c b/arch/powerpc/kernel/rtas-proc.c index 5bdd5b079d9..7a95b8a2835 100644 --- a/arch/powerpc/kernel/rtas-proc.c +++ b/arch/powerpc/kernel/rtas-proc.c @@ -32,7 +32,6 @@ #include <asm/rtas.h> #include <asm/machdep.h> /* for ppc_md */ #include <asm/time.h> -#include <asm/systemcfg.h> /* Token for Sensors */ #define KEY_SWITCH 0x0001 @@ -259,7 +258,7 @@ static int __init proc_rtas_init(void) { struct proc_dir_entry *entry; - if (!(systemcfg->platform & PLATFORM_PSERIES)) + if (_machine != PLATFORM_PSERIES && _machine != PLATFORM_PSERIES_LPAR) return 1; rtas_node = of_find_node_by_name(NULL, "rtas"); diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 9d4e07f6f1e..4283fa33f78 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -29,9 +29,6 @@ #include <asm/delay.h> #include <asm/uaccess.h> #include <asm/lmb.h> -#ifdef CONFIG_PPC64 -#include <asm/systemcfg.h> -#endif struct rtas_t rtas = { .lock = SPIN_LOCK_UNLOCKED @@ -671,7 +668,7 @@ void __init rtas_initialize(void) * the stop-self token if any */ #ifdef CONFIG_PPC64 - if (systemcfg->platform == PLATFORM_PSERIES_LPAR) + if (_machine == PLATFORM_PSERIES_LPAR) rtas_region = min(lmb.rmo_size, RTAS_INSTANTIATE_MAX); #endif rtas_rmo_buf = lmb_alloc_base(RTAS_RMOBUF_MAX, PAGE_SIZE, rtas_region); diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c new file mode 100644 index 00000000000..0e5a8e11665 --- /dev/null +++ b/arch/powerpc/kernel/rtas_pci.c @@ -0,0 +1,513 @@ +/* + * arch/ppc64/kernel/rtas_pci.c + * + * Copyright (C) 2001 Dave Engebretsen, IBM Corporation + * Copyright (C) 2003 Anton Blanchard <anton@au.ibm.com>, IBM + * + * RTAS specific routines for PCI. + * + * Based on code from pci.c, chrp_pci.c and pSeries_pci.c + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program 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 General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include <linux/kernel.h> +#include <linux/threads.h> +#include <linux/pci.h> +#include <linux/string.h> +#include <linux/init.h> +#include <linux/bootmem.h> + +#include <asm/io.h> +#include <asm/pgtable.h> +#include <asm/irq.h> +#include <asm/prom.h> +#include <asm/machdep.h> +#include <asm/pci-bridge.h> +#include <asm/iommu.h> +#include <asm/rtas.h> +#include <asm/mpic.h> +#include <asm/ppc-pci.h> + +/* RTAS tokens */ +static int read_pci_config; +static int write_pci_config; +static int ibm_read_pci_config; +static int ibm_write_pci_config; + +static inline int config_access_valid(struct pci_dn *dn, int where) +{ + if (where < 256) + return 1; + if (where < 4096 && dn->pci_ext_config_space) + return 1; + + return 0; +} + +static int of_device_available(struct device_node * dn) +{ + char * status; + + status = get_property(dn, "status", NULL); + + if (!status) + return 1; + + if (!strcmp(status, "okay")) + return 1; + + return 0; +} + +static int rtas_read_config(struct pci_dn *pdn, int where, int size, u32 *val) +{ + int returnval = -1; + unsigned long buid, addr; + int ret; + + if (!pdn) + return PCIBIOS_DEVICE_NOT_FOUND; + if (!config_access_valid(pdn, where)) + return PCIBIOS_BAD_REGISTER_NUMBER; + + addr = ((where & 0xf00) << 20) | (pdn->busno << 16) | + (pdn->devfn << 8) | (where & 0xff); + buid = pdn->phb->buid; + if (buid) { + ret = rtas_call(ibm_read_pci_config, 4, 2, &returnval, + addr, BUID_HI(buid), BUID_LO(buid), size); + } else { + ret = rtas_call(read_pci_config, 2, 2, &returnval, addr, size); + } + *val = returnval; + + if (ret) + return PCIBIOS_DEVICE_NOT_FOUND; + + if (returnval == EEH_IO_ERROR_VALUE(size) && + eeh_dn_check_failure (pdn->node, NULL)) + return PCIBIOS_DEVICE_NOT_FOUND; + + return PCIBIOS_SUCCESSFUL; +} + +static int rtas_pci_read_config(struct pci_bus *bus, + unsigned int devfn, + int where, int size, u32 *val) +{ + struct device_node *busdn, *dn; + + if (bus->self) + busdn = pci_device_to_OF_node(bus->self); + else + busdn = bus->sysdata; /* must be a phb */ + + /* Search only direct children of the bus */ + for (dn = busdn->child; dn; dn = dn->sibling) { + struct pci_dn *pdn = PCI_DN(dn); + if (pdn && pdn->devfn == devfn + && of_device_available(dn)) + return rtas_read_config(pdn, where, size, val); + } + + return PCIBIOS_DEVICE_NOT_FOUND; +} + +int rtas_write_config(struct pci_dn *pdn, int where, int size, u32 val) +{ + unsigned long buid, addr; + int ret; + + if (!pdn) + return PCIBIOS_DEVICE_NOT_FOUND; + if (!config_access_valid(pdn, where)) + return PCIBIOS_BAD_REGISTER_NUMBER; + + addr = ((where & 0xf00) << 20) | (pdn->busno << 16) | + (pdn->devfn << 8) | (where & 0xff); + buid = pdn->phb->buid; + if (buid) { + ret = rtas_call(ibm_write_pci_config, 5, 1, NULL, addr, + BUID_HI(buid), BUID_LO(buid), size, (ulong) val); + } else { + ret = rtas_call(write_pci_config, 3, 1, NULL, addr, size, (ulong)val); + } + + if (ret) + return PCIBIOS_DEVICE_NOT_FOUND; + + return PCIBIOS_SUCCESSFUL; +} + +static int rtas_pci_write_config(struct pci_bus *bus, + unsigned int devfn, + int where, int size, u32 val) +{ + struct device_node *busdn, *dn; + + if (bus->self) + busdn = pci_device_to_OF_node(bus->self); + else + busdn = bus->sysdata; /* must be a phb */ + + /* Search only direct children of the bus */ + for (dn = busdn->child; dn; dn = dn->sibling) { + struct pci_dn *pdn = PCI_DN(dn); + if (pdn && pdn->devfn == devfn + && of_device_available(dn)) + return rtas_write_config(pdn, where, size, val); + } + return PCIBIOS_DEVICE_NOT_FOUND; +} + +struct pci_ops rtas_pci_ops = { + rtas_pci_read_config, + rtas_pci_write_config +}; + +int is_python(struct device_node *dev) +{ + char *model = (char *)get_property(dev, "model", NULL); + + if (model && strstr(model, "Python")) + return 1; + + return 0; +} + +static int get_phb_reg_prop(struct device_node *dev, + unsigned int addr_size_words, + struct reg_property64 *reg) +{ + unsigned int *ui_ptr = NULL, len; + + /* Found a PHB, now figure out where his registers are mapped. */ + ui_ptr = (unsigned int *)get_property(dev, "reg", &len); + if (ui_ptr == NULL) + return 1; + + if (addr_size_words == 1) { + reg->address = ((struct reg_property32 *)ui_ptr)->address; + reg->size = ((struct reg_property32 *)ui_ptr)->size; + } else { + *reg = *((struct reg_property64 *)ui_ptr); + } + + return 0; +} + +static void python_countermeasures(struct device_node *dev, + unsigned int addr_size_words) +{ + struct reg_property64 reg_struct; + void __iomem *chip_regs; + volatile u32 val; + + if (get_phb_reg_prop(dev, addr_size_words, ®_struct)) + return; + + /* Python's register file is 1 MB in size. */ + chip_regs = ioremap(reg_struct.address & ~(0xfffffUL), 0x100000); + + /* + * Firmware doesn't always clear this bit which is critical + * for good performance - Anton + */ + +#define PRG_CL_RESET_VALID 0x00010000 + + val = in_be32(chip_regs + 0xf6030); + if (val & PRG_CL_RESET_VALID) { + printk(KERN_INFO "Python workaround: "); + val &= ~PRG_CL_RESET_VALID; + out_be32(chip_regs + 0xf6030, val); + /* + * We must read it back for changes to + * take effect + */ + val = in_be32(chip_regs + 0xf6030); + printk("reg0: %x\n", val); + } + + iounmap(chip_regs); +} + +void __init init_pci_config_tokens (void) +{ + read_pci_config = rtas_token("read-pci-config"); + write_pci_config = rtas_token("write-pci-config"); + ibm_read_pci_config = rtas_token("ibm,read-pci-config"); + ibm_write_pci_config = rtas_token("ibm,write-pci-config"); +} + +unsigned long __devinit get_phb_buid (struct device_node *phb) +{ + int addr_cells; + unsigned int *buid_vals; + unsigned int len; + unsigned long buid; + + if (ibm_read_pci_config == -1) return 0; + + /* PHB's will always be children of the root node, + * or so it is promised by the current firmware. */ + if (phb->parent == NULL) + return 0; + if (phb->parent->parent) + return 0; + + buid_vals = (unsigned int *) get_property(phb, "reg", &len); + if (buid_vals == NULL) + return 0; + + addr_cells = prom_n_addr_cells(phb); + if (addr_cells == 1) { + buid = (unsigned long) buid_vals[0]; + } else { + buid = (((unsigned long)buid_vals[0]) << 32UL) | + (((unsigned long)buid_vals[1]) & 0xffffffff); + } + return buid; +} + +static int phb_set_bus_ranges(struct device_node *dev, + struct pci_controller *phb) +{ + int *bus_range; + unsigned int len; + + bus_range = (int *) get_property(dev, "bus-range", &len); + if (bus_range == NULL || len < 2 * sizeof(int)) { + return 1; + } + + phb->first_busno = bus_range[0]; + phb->last_busno = bus_range[1]; + + return 0; +} + +static int __devinit setup_phb(struct device_node *dev, + struct pci_controller *phb, + unsigned int addr_size_words) +{ + pci_setup_pci_controller(phb); + + if (is_python(dev)) + python_countermeasures(dev, addr_size_words); + + if (phb_set_bus_ranges(dev, phb)) + return 1; + + phb->arch_data = dev; + phb->ops = &rtas_pci_ops; + phb->buid = get_phb_buid(dev); + + return 0; +} + +static void __devinit add_linux_pci_domain(struct device_node *dev, + struct pci_controller *phb, + struct property *of_prop) +{ + memset(of_prop, 0, sizeof(struct property)); + of_prop->name = "linux,pci-domain"; + of_prop->length = sizeof(phb->global_number); + of_prop->value = (unsigned char *)&of_prop[1]; + memcpy(of_prop->value, &phb->global_number, sizeof(phb->global_number)); + prom_add_property(dev, of_prop); +} + +static struct pci_controller * __init alloc_phb(struct device_node *dev, + unsigned int addr_size_words) +{ + struct pci_controller *phb; + struct property *of_prop; + + phb = alloc_bootmem(sizeof(struct pci_controller)); + if (phb == NULL) + return NULL; + + of_prop = alloc_bootmem(sizeof(struct property) + + sizeof(phb->global_number)); + if (!of_prop) + return NULL; + + if (setup_phb(dev, phb, addr_size_words)) + return NULL; + + add_linux_pci_domain(dev, phb, of_prop); + + return phb; +} + +static struct pci_controller * __devinit alloc_phb_dynamic(struct device_node *dev, unsigned int addr_size_words) +{ + struct pci_controller *phb; + + phb = (struct pci_controller *)kmalloc(sizeof(struct pci_controller), + GFP_KERNEL); + if (phb == NULL) + return NULL; + + if (setup_phb(dev, phb, addr_size_words)) + return NULL; + + phb->is_dynamic = 1; + + /* TODO: linux,pci-domain? */ + + return phb; +} + +unsigned long __init find_and_init_phbs(void) +{ + struct device_node *node; + struct pci_controller *phb; + unsigned int root_size_cells = 0; + unsigned int index; + unsigned int *opprop = NULL; + struct device_node *root = of_find_node_by_path("/"); + + if (ppc64_interrupt_controller == IC_OPEN_PIC) { + opprop = (unsigned int *)get_property(root, + "platform-open-pic", NULL); + } + + root_size_cells = prom_n_size_cells(root); + + index = 0; + + for (node = of_get_next_child(root, NULL); + node != NULL; + node = of_get_next_child(root, node)) { + if (node->type == NULL || strcmp(node->type, "pci") != 0) + continue; + + phb = alloc_phb(node, root_size_cells); + if (!phb) + continue; + + pci_process_bridge_OF_ranges(phb, node, 0); + pci_setup_phb_io(phb, index == 0); +#ifdef CONFIG_PPC_PSERIES + if (ppc64_interrupt_controller == IC_OPEN_PIC && pSeries_mpic) { + int addr = root_size_cells * (index + 2) - 1; + mpic_assign_isu(pSeries_mpic, index, opprop[addr]); + } +#endif + index++; + } + + of_node_put(root); + pci_devs_phb_init(); + + /* + * pci_probe_only and pci_assign_all_buses can be set via properties + * in chosen. + */ + if (of_chosen) { + int *prop; + + prop = (int *)get_property(of_chosen, "linux,pci-probe-only", + NULL); + if (prop) + pci_probe_only = *prop; + + prop = (int *)get_property(of_chosen, + "linux,pci-assign-all-buses", NULL); + if (prop) + pci_assign_all_buses = *prop; + } + + return 0; +} + +struct pci_controller * __devinit init_phb_dynamic(struct device_node *dn) +{ + struct device_node *root = of_find_node_by_path("/"); + unsigned int root_size_cells = 0; + struct pci_controller *phb; + int primary; + + root_size_cells = prom_n_size_cells(root); + + primary = list_empty(&hose_list); + phb = alloc_phb_dynamic(dn, root_size_cells); + if (!phb) + return NULL; + + pci_process_bridge_OF_ranges(phb, dn, primary); + + pci_setup_phb_io_dynamic(phb, primary); + of_node_put(root); + + pci_devs_phb_init_dynamic(phb); + scan_phb(phb); + + return phb; +} +EXPORT_SYMBOL(init_phb_dynamic); + +/* RPA-specific bits for removing PHBs */ +int pcibios_remove_root_bus(struct pci_controller *phb) +{ + struct pci_bus *b = phb->bus; + struct resource *res; + int rc, i; + + res = b->resource[0]; + if (!res->flags) { + printk(KERN_ERR "%s: no IO resource for PHB %s\n", __FUNCTION__, + b->name); + return 1; + } + + rc = unmap_bus_range(b); + if (rc) { + printk(KERN_ERR "%s: failed to unmap IO on bus %s\n", + __FUNCTION__, b->name); + return 1; + } + + if (release_resource(res)) { + printk(KERN_ERR "%s: failed to release IO on bus %s\n", + __FUNCTION__, b->name); + return 1; + } + + for (i = 1; i < 3; ++i) { + res = b->resource[i]; + if (!res->flags && i == 0) { + printk(KERN_ERR "%s: no MEM resource for PHB %s\n", + __FUNCTION__, b->name); + return 1; + } + if (res->flags && release_resource(res)) { + printk(KERN_ERR + "%s: failed to release IO %d on bus %s\n", + __FUNCTION__, i, b->name); + return 1; + } + } + + list_del(&phb->list_node); + if (phb->is_dynamic) + kfree(phb); + + return 0; +} +EXPORT_SYMBOL(pcibios_remove_root_bus); diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index e22856ecb5a..33e7f2c7f19 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -33,6 +33,7 @@ #include <asm/io.h> #include <asm/prom.h> #include <asm/processor.h> +#include <asm/vdso_datapage.h> #include <asm/pgtable.h> #include <asm/smp.h> #include <asm/elf.h> @@ -51,6 +52,9 @@ #include <asm/page.h> #include <asm/mmu.h> #include <asm/lmb.h> +#include <asm/xmon.h> + +#include "setup.h" #undef DEBUG @@ -60,6 +64,13 @@ #define DBG(fmt...) #endif +#ifdef CONFIG_PPC_MULTIPLATFORM +int _machine = 0; +EXPORT_SYMBOL(_machine); +#endif + +unsigned long klimit = (unsigned long) _end; + /* * This still seems to be needed... -- paulus */ @@ -433,10 +444,8 @@ void __init check_for_initrd(void) if (initrd_start >= KERNELBASE && initrd_end >= KERNELBASE && initrd_end > initrd_start) ROOT_DEV = Root_RAM0; - else { - printk("Bogus initrd %08lx %08lx\n", initrd_start, initrd_end); + else initrd_start = initrd_end = 0; - } if (initrd_start) printk("Found initrd at 0x%lx:0x%lx\n", initrd_start, initrd_end); @@ -510,8 +519,8 @@ void __init smp_setup_cpu_maps(void) * On pSeries LPAR, we need to know how many cpus * could possibly be added to this partition. */ - if (systemcfg->platform == PLATFORM_PSERIES_LPAR && - (dn = of_find_node_by_path("/rtas"))) { + if (_machine == PLATFORM_PSERIES_LPAR && + (dn = of_find_node_by_path("/rtas"))) { int num_addr_cell, num_size_cell, maxcpus; unsigned int *ireg; @@ -555,7 +564,27 @@ void __init smp_setup_cpu_maps(void) cpu_set(cpu ^ 0x1, cpu_sibling_map[cpu]); } - systemcfg->processorCount = num_present_cpus(); + vdso_data->processorCount = num_present_cpus(); #endif /* CONFIG_PPC64 */ } #endif /* CONFIG_SMP */ + +#ifdef CONFIG_XMON +static int __init early_xmon(char *p) +{ + /* ensure xmon is enabled */ + if (p) { + if (strncmp(p, "on", 2) == 0) + xmon_init(1); + if (strncmp(p, "off", 3) == 0) + xmon_init(0); + if (strncmp(p, "early", 5) != 0) + return 0; + } + xmon_init(1); + debugger(NULL); + + return 0; +} +early_param("xmon", early_xmon); +#endif diff --git a/arch/powerpc/kernel/setup.h b/arch/powerpc/kernel/setup.h new file mode 100644 index 00000000000..2ebba755272 --- /dev/null +++ b/arch/powerpc/kernel/setup.h @@ -0,0 +1,6 @@ +#ifndef _POWERPC_KERNEL_SETUP_H +#define _POWERPC_KERNEL_SETUP_H + +void check_for_initrd(void); + +#endif /* _POWERPC_KERNEL_SETUP_H */ diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 3af2631e3fa..c98cfcc9cd9 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -40,6 +40,8 @@ #include <asm/xmon.h> #include <asm/time.h> +#include "setup.h" + #define DBG(fmt...) #if defined CONFIG_KGDB @@ -70,8 +72,6 @@ unsigned int DMA_MODE_WRITE; int have_of = 1; #ifdef CONFIG_PPC_MULTIPLATFORM -int _machine = 0; - extern void prep_init(void); extern void pmac_init(void); extern void chrp_init(void); @@ -279,7 +279,6 @@ arch_initcall(ppc_init); /* Warning, IO base is not yet inited */ void __init setup_arch(char **cmdline_p) { - extern char *klimit; extern void do_init_bootmem(void); /* so udelay does something sensible, assume <= 1000 bogomips */ @@ -303,14 +302,9 @@ void __init setup_arch(char **cmdline_p) pmac_feature_init(); /* New cool way */ #endif -#ifdef CONFIG_XMON - xmon_map_scc(); - if (strstr(cmd_line, "xmon")) { - xmon_init(1); - debugger(NULL); - } -#endif /* CONFIG_XMON */ - if ( ppc_md.progress ) ppc_md.progress("setup_arch: enter", 0x3eab); +#ifdef CONFIG_XMON_DEFAULT + xmon_init(1); +#endif #if defined(CONFIG_KGDB) if (ppc_md.kgdb_map_scc) @@ -343,7 +337,7 @@ void __init setup_arch(char **cmdline_p) init_mm.start_code = PAGE_OFFSET; init_mm.end_code = (unsigned long) _etext; init_mm.end_data = (unsigned long) _edata; - init_mm.brk = (unsigned long) klimit; + init_mm.brk = klimit; /* Save unparsed command line copy for /proc/cmdline */ strlcpy(saved_command_line, cmd_line, COMMAND_LINE_SIZE); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 0471e843b6c..fdbd9f9122f 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -57,10 +57,11 @@ #include <asm/lmb.h> #include <asm/iseries/it_lp_naca.h> #include <asm/firmware.h> -#include <asm/systemcfg.h> #include <asm/xmon.h> #include <asm/udbg.h> +#include "setup.h" + #ifdef DEBUG #define DBG(fmt...) udbg_printf(fmt) #else @@ -94,15 +95,6 @@ extern void udbg_init_maple_realmode(void); do { udbg_putc = call_rtas_display_status_delay; } while(0) #endif -/* extern void *stab; */ -extern unsigned long klimit; - -extern void mm_init_ppc64(void); -extern void stab_initialize(unsigned long stab); -extern void htab_initialize(void); -extern void early_init_devtree(void *flat_dt); -extern void unflatten_device_tree(void); - int have_of = 1; int boot_cpuid = 0; int boot_cpuid_phys = 0; @@ -254,11 +246,10 @@ void __init early_setup(unsigned long dt_ptr) * Iterate all ppc_md structures until we find the proper * one for the current machine type */ - DBG("Probing machine type for platform %x...\n", - systemcfg->platform); + DBG("Probing machine type for platform %x...\n", _machine); for (mach = machines; *mach; mach++) { - if ((*mach)->probe(systemcfg->platform)) + if ((*mach)->probe(_machine)) break; } /* What can we do if we didn't find ? */ @@ -290,6 +281,28 @@ void __init early_setup(unsigned long dt_ptr) DBG(" <- early_setup()\n"); } +#ifdef CONFIG_SMP +void early_setup_secondary(void) +{ + struct paca_struct *lpaca = get_paca(); + + /* Mark enabled in PACA */ + lpaca->proc_enabled = 0; + + /* Initialize hash table for that CPU */ + htab_initialize_secondary(); + + /* Initialize STAB/SLB. We use a virtual address as it works + * in real mode on pSeries and we want a virutal address on + * iSeries anyway + */ + if (cpu_has_feature(CPU_FTR_SLB)) + slb_initialize(); + else + stab_initialize(lpaca->stab_addr); +} + +#endif /* CONFIG_SMP */ #if defined(CONFIG_SMP) || defined(CONFIG_KEXEC) void smp_release_cpus(void) @@ -315,7 +328,8 @@ void smp_release_cpus(void) #endif /* CONFIG_SMP || CONFIG_KEXEC */ /* - * Initialize some remaining members of the ppc64_caches and systemcfg structures + * Initialize some remaining members of the ppc64_caches and systemcfg + * structures * (at least until we get rid of them completely). This is mostly some * cache informations about the CPU that will be used by cache flush * routines and/or provided to userland @@ -340,7 +354,7 @@ static void __init initialize_cache_info(void) const char *dc, *ic; /* Then read cache informations */ - if (systemcfg->platform == PLATFORM_POWERMAC) { + if (_machine == PLATFORM_POWERMAC) { dc = "d-cache-block-size"; ic = "i-cache-block-size"; } else { @@ -360,9 +374,8 @@ static void __init initialize_cache_info(void) DBG("Argh, can't find dcache properties ! " "sizep: %p, lsizep: %p\n", sizep, lsizep); - systemcfg->dcache_size = ppc64_caches.dsize = size; - systemcfg->dcache_line_size = - ppc64_caches.dline_size = lsize; + ppc64_caches.dsize = size; + ppc64_caches.dline_size = lsize; ppc64_caches.log_dline_size = __ilog2(lsize); ppc64_caches.dlines_per_page = PAGE_SIZE / lsize; @@ -378,20 +391,13 @@ static void __init initialize_cache_info(void) DBG("Argh, can't find icache properties ! " "sizep: %p, lsizep: %p\n", sizep, lsizep); - systemcfg->icache_size = ppc64_caches.isize = size; - systemcfg->icache_line_size = - ppc64_caches.iline_size = lsize; + ppc64_caches.isize = size; + ppc64_caches.iline_size = lsize; ppc64_caches.log_iline_size = __ilog2(lsize); ppc64_caches.ilines_per_page = PAGE_SIZE / lsize; } } - /* Add an eye catcher and the systemcfg layout version number */ - strcpy(systemcfg->eye_catcher, "SYSTEMCFG:PPC64"); - systemcfg->version.major = SYSTEMCFG_MAJOR; - systemcfg->version.minor = SYSTEMCFG_MINOR; - systemcfg->processor = mfspr(SPRN_PVR); - DBG(" <- initialize_cache_info()\n"); } @@ -478,15 +484,14 @@ void __init setup_system(void) printk("-----------------------------------------------------\n"); printk("ppc64_pft_size = 0x%lx\n", ppc64_pft_size); - printk("ppc64_interrupt_controller = 0x%ld\n", ppc64_interrupt_controller); - printk("systemcfg = 0x%p\n", systemcfg); - printk("systemcfg->platform = 0x%x\n", systemcfg->platform); - printk("systemcfg->processorCount = 0x%lx\n", systemcfg->processorCount); - printk("systemcfg->physicalMemorySize = 0x%lx\n", systemcfg->physicalMemorySize); + printk("ppc64_interrupt_controller = 0x%ld\n", + ppc64_interrupt_controller); + printk("platform = 0x%x\n", _machine); + printk("physicalMemorySize = 0x%lx\n", lmb_phys_mem_size()); printk("ppc64_caches.dcache_line_size = 0x%x\n", - ppc64_caches.dline_size); + ppc64_caches.dline_size); printk("ppc64_caches.icache_line_size = 0x%x\n", - ppc64_caches.iline_size); + ppc64_caches.iline_size); printk("htab_address = 0x%p\n", htab_address); printk("htab_hash_mask = 0x%lx\n", htab_hash_mask); printk("-----------------------------------------------------\n"); @@ -551,33 +556,6 @@ static void __init emergency_stack_init(void) } /* - * Called from setup_arch to initialize the bitmap of available - * syscalls in the systemcfg page - */ -void __init setup_syscall_map(void) -{ - unsigned int i, count64 = 0, count32 = 0; - extern unsigned long *sys_call_table; - extern unsigned long sys_ni_syscall; - - - for (i = 0; i < __NR_syscalls; i++) { - if (sys_call_table[i*2] != sys_ni_syscall) { - count64++; - systemcfg->syscall_map_64[i >> 5] |= - 0x80000000UL >> (i & 0x1f); - } - if (sys_call_table[i*2+1] != sys_ni_syscall) { - count32++; - systemcfg->syscall_map_32[i >> 5] |= - 0x80000000UL >> (i & 0x1f); - } - } - printk(KERN_INFO "Syscall map setup, %d 32-bit and %d 64-bit syscalls\n", - count32, count64); -} - -/* * Called into from start_kernel, after lock_kernel has been called. * Initializes bootmem, which is unsed to manage page allocation until * mem_init is called. @@ -618,9 +596,6 @@ void __init setup_arch(char **cmdline_p) do_init_bootmem(); sparse_init(); - /* initialize the syscall map in systemcfg */ - setup_syscall_map(); - #ifdef CONFIG_DUMMY_CONSOLE conswitchp = &dummy_con; #endif @@ -858,26 +833,6 @@ int check_legacy_ioport(unsigned long base_port) } EXPORT_SYMBOL(check_legacy_ioport); -#ifdef CONFIG_XMON -static int __init early_xmon(char *p) -{ - /* ensure xmon is enabled */ - if (p) { - if (strncmp(p, "on", 2) == 0) - xmon_init(1); - if (strncmp(p, "off", 3) == 0) - xmon_init(0); - if (strncmp(p, "early", 5) != 0) - return 0; - } - xmon_init(1); - debugger(NULL); - - return 0; -} -early_param("xmon", early_xmon); -#endif - void cpu_die(void) { if (ppc_md.cpu_die) diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 081d931eae4..8bdf95b7e42 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -42,10 +42,11 @@ #include <asm/uaccess.h> #include <asm/cacheflush.h> +#include <asm/sigcontext.h> +#include <asm/vdso.h> #ifdef CONFIG_PPC64 #include "ppc32.h" #include <asm/unistd.h> -#include <asm/vdso.h> #else #include <asm/ucontext.h> #include <asm/pgtable.h> @@ -808,14 +809,11 @@ static int handle_rt_signal(unsigned long sig, struct k_sigaction *ka, /* Save user registers on the stack */ frame = &rt_sf->uc.uc_mcontext; -#ifdef CONFIG_PPC64 if (vdso32_rt_sigtramp && current->thread.vdso_base) { if (save_user_regs(regs, frame, 0)) goto badframe; regs->link = current->thread.vdso_base + vdso32_rt_sigtramp; - } else -#endif - { + } else { if (save_user_regs(regs, frame, __NR_rt_sigreturn)) goto badframe; regs->link = (unsigned long) frame->tramp; @@ -1089,14 +1087,11 @@ static int handle_signal(unsigned long sig, struct k_sigaction *ka, || __put_user(sig, &sc->signal)) goto badframe; -#ifdef CONFIG_PPC64 if (vdso32_sigtramp && current->thread.vdso_base) { if (save_user_regs(regs, &frame->mctx, 0)) goto badframe; regs->link = current->thread.vdso_base + vdso32_sigtramp; - } else -#endif - { + } else { if (save_user_regs(regs, &frame->mctx, __NR_sigreturn)) goto badframe; regs->link = (unsigned long) frame->mctx.tramp; diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 5c330c3366e..62dfc5b8d76 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -44,6 +44,7 @@ #include <asm/cputable.h> #include <asm/system.h> #include <asm/mpic.h> +#include <asm/vdso_datapage.h> #ifdef CONFIG_PPC64 #include <asm/paca.h> #endif @@ -368,9 +369,11 @@ int generic_cpu_disable(void) if (cpu == boot_cpuid) return -EBUSY; - systemcfg->processorCount--; cpu_clear(cpu, cpu_online_map); +#ifdef CONFIG_PPC64 + vdso_data->processorCount--; fixup_irqs(cpu_online_map); +#endif return 0; } @@ -388,9 +391,11 @@ int generic_cpu_enable(unsigned int cpu) while (!cpu_online(cpu)) cpu_relax(); +#ifdef CONFIG_PPC64 fixup_irqs(cpu_online_map); /* counter the irq disable in fixup_irqs */ local_irq_enable(); +#endif return 0; } @@ -419,7 +424,9 @@ void generic_mach_cpu_die(void) while (__get_cpu_var(cpu_state) != CPU_UP_PREPARE) cpu_relax(); +#ifdef CONFIG_PPC64 flush_tlb_pending(); +#endif cpu_set(cpu, cpu_online_map); local_irq_enable(); } @@ -510,6 +517,7 @@ int __devinit start_secondary(void *unused) smp_store_cpu_info(cpu); set_dec(tb_ticks_per_jiffy); + preempt_disable(); cpu_callin_map[cpu] = 1; smp_ops->setup_cpu(cpu); diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index a8210ed5c68..9c921d1c408 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -52,7 +52,6 @@ #include <asm/semaphore.h> #include <asm/time.h> #include <asm/mmu_context.h> -#include <asm/systemcfg.h> #include <asm/ppc-pci.h> /* readdir & getdents */ diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c new file mode 100644 index 00000000000..0f0c3a9ae2e --- /dev/null +++ b/arch/powerpc/kernel/sysfs.c @@ -0,0 +1,383 @@ +#include <linux/config.h> +#include <linux/sysdev.h> +#include <linux/cpu.h> +#include <linux/smp.h> +#include <linux/percpu.h> +#include <linux/init.h> +#include <linux/sched.h> +#include <linux/module.h> +#include <linux/nodemask.h> +#include <linux/cpumask.h> +#include <linux/notifier.h> + +#include <asm/current.h> +#include <asm/processor.h> +#include <asm/cputable.h> +#include <asm/firmware.h> +#include <asm/hvcall.h> +#include <asm/prom.h> +#include <asm/paca.h> +#include <asm/lppaca.h> +#include <asm/machdep.h> +#include <asm/smp.h> + +static DEFINE_PER_CPU(struct cpu, cpu_devices); + +/* SMT stuff */ + +#ifdef CONFIG_PPC_MULTIPLATFORM +/* default to snooze disabled */ +DEFINE_PER_CPU(unsigned long, smt_snooze_delay); + +static ssize_t store_smt_snooze_delay(struct sys_device *dev, const char *buf, + size_t count) +{ + struct cpu *cpu = container_of(dev, struct cpu, sysdev); + ssize_t ret; + unsigned long snooze; + + ret = sscanf(buf, "%lu", &snooze); + if (ret != 1) + return -EINVAL; + + per_cpu(smt_snooze_delay, cpu->sysdev.id) = snooze; + + return count; +} + +static ssize_t show_smt_snooze_delay(struct sys_device *dev, char *buf) +{ + struct cpu *cpu = container_of(dev, struct cpu, sysdev); + + return sprintf(buf, "%lu\n", per_cpu(smt_snooze_delay, cpu->sysdev.id)); +} + +static SYSDEV_ATTR(smt_snooze_delay, 0644, show_smt_snooze_delay, + store_smt_snooze_delay); + +/* Only parse OF options if the matching cmdline option was not specified */ +static int smt_snooze_cmdline; + +static int __init smt_setup(void) +{ + struct device_node *options; + unsigned int *val; + unsigned int cpu; + + if (!cpu_has_feature(CPU_FTR_SMT)) + return 1; + + options = find_path_device("/options"); + if (!options) + return 1; + + val = (unsigned int *)get_property(options, "ibm,smt-snooze-delay", + NULL); + if (!smt_snooze_cmdline && val) { + for_each_cpu(cpu) + per_cpu(smt_snooze_delay, cpu) = *val; + } + + return 1; +} +__initcall(smt_setup); + +static int __init setup_smt_snooze_delay(char *str) +{ + unsigned int cpu; + int snooze; + + if (!cpu_has_feature(CPU_FTR_SMT)) + return 1; + + smt_snooze_cmdline = 1; + + if (get_option(&str, &snooze)) { + for_each_cpu(cpu) + per_cpu(smt_snooze_delay, cpu) = snooze; + } + + return 1; +} +__setup("smt-snooze-delay=", setup_smt_snooze_delay); + +#endif /* CONFIG_PPC_MULTIPLATFORM */ + +/* + * Enabling PMCs will slow partition context switch times so we only do + * it the first time we write to the PMCs. + */ + +static DEFINE_PER_CPU(char, pmcs_enabled); + +void ppc64_enable_pmcs(void) +{ + /* Only need to enable them once */ + if (__get_cpu_var(pmcs_enabled)) + return; + + __get_cpu_var(pmcs_enabled) = 1; + + if (ppc_md.enable_pmcs) + ppc_md.enable_pmcs(); +} +EXPORT_SYMBOL(ppc64_enable_pmcs); + +/* XXX convert to rusty's on_one_cpu */ +static unsigned long run_on_cpu(unsigned long cpu, + unsigned long (*func)(unsigned long), + unsigned long arg) +{ + cpumask_t old_affinity = current->cpus_allowed; + unsigned long ret; + + /* should return -EINVAL to userspace */ + if (set_cpus_allowed(current, cpumask_of_cpu(cpu))) + return 0; + + ret = func(arg); + + set_cpus_allowed(current, old_affinity); + + return ret; +} + +#define SYSFS_PMCSETUP(NAME, ADDRESS) \ +static unsigned long read_##NAME(unsigned long junk) \ +{ \ + return mfspr(ADDRESS); \ +} \ +static unsigned long write_##NAME(unsigned long val) \ +{ \ + ppc64_enable_pmcs(); \ + mtspr(ADDRESS, val); \ + return 0; \ +} \ +static ssize_t show_##NAME(struct sys_device *dev, char *buf) \ +{ \ + struct cpu *cpu = container_of(dev, struct cpu, sysdev); \ + unsigned long val = run_on_cpu(cpu->sysdev.id, read_##NAME, 0); \ + return sprintf(buf, "%lx\n", val); \ +} \ +static ssize_t __attribute_used__ \ + store_##NAME(struct sys_device *dev, const char *buf, size_t count) \ +{ \ + struct cpu *cpu = container_of(dev, struct cpu, sysdev); \ + unsigned long val; \ + int ret = sscanf(buf, "%lx", &val); \ + if (ret != 1) \ + return -EINVAL; \ + run_on_cpu(cpu->sysdev.id, write_##NAME, val); \ + return count; \ +} + +SYSFS_PMCSETUP(mmcr0, SPRN_MMCR0); +SYSFS_PMCSETUP(mmcr1, SPRN_MMCR1); +SYSFS_PMCSETUP(mmcra, SPRN_MMCRA); +SYSFS_PMCSETUP(pmc1, SPRN_PMC1); +SYSFS_PMCSETUP(pmc2, SPRN_PMC2); +SYSFS_PMCSETUP(pmc3, SPRN_PMC3); +SYSFS_PMCSETUP(pmc4, SPRN_PMC4); +SYSFS_PMCSETUP(pmc5, SPRN_PMC5); +SYSFS_PMCSETUP(pmc6, SPRN_PMC6); +SYSFS_PMCSETUP(pmc7, SPRN_PMC7); +SYSFS_PMCSETUP(pmc8, SPRN_PMC8); +SYSFS_PMCSETUP(purr, SPRN_PURR); + +static SYSDEV_ATTR(mmcr0, 0600, show_mmcr0, store_mmcr0); +static SYSDEV_ATTR(mmcr1, 0600, show_mmcr1, store_mmcr1); +static SYSDEV_ATTR(mmcra, 0600, show_mmcra, store_mmcra); +static SYSDEV_ATTR(pmc1, 0600, show_pmc1, store_pmc1); +static SYSDEV_ATTR(pmc2, 0600, show_pmc2, store_pmc2); +static SYSDEV_ATTR(pmc3, 0600, show_pmc3, store_pmc3); +static SYSDEV_ATTR(pmc4, 0600, show_pmc4, store_pmc4); +static SYSDEV_ATTR(pmc5, 0600, show_pmc5, store_pmc5); +static SYSDEV_ATTR(pmc6, 0600, show_pmc6, store_pmc6); +static SYSDEV_ATTR(pmc7, 0600, show_pmc7, store_pmc7); +static SYSDEV_ATTR(pmc8, 0600, show_pmc8, store_pmc8); +static SYSDEV_ATTR(purr, 0600, show_purr, NULL); + +static void register_cpu_online(unsigned int cpu) +{ + struct cpu *c = &per_cpu(cpu_devices, cpu); + struct sys_device *s = &c->sysdev; + +#ifndef CONFIG_PPC_ISERIES + if (cpu_has_feature(CPU_FTR_SMT)) + sysdev_create_file(s, &attr_smt_snooze_delay); +#endif + + /* PMC stuff */ + + sysdev_create_file(s, &attr_mmcr0); + sysdev_create_file(s, &attr_mmcr1); + + if (cpu_has_feature(CPU_FTR_MMCRA)) + sysdev_create_file(s, &attr_mmcra); + + if (cur_cpu_spec->num_pmcs >= 1) + sysdev_create_file(s, &attr_pmc1); + if (cur_cpu_spec->num_pmcs >= 2) + sysdev_create_file(s, &attr_pmc2); + if (cur_cpu_spec->num_pmcs >= 3) + sysdev_create_file(s, &attr_pmc3); + if (cur_cpu_spec->num_pmcs >= 4) + sysdev_create_file(s, &attr_pmc4); + if (cur_cpu_spec->num_pmcs >= 5) + sysdev_create_file(s, &attr_pmc5); + if (cur_cpu_spec->num_pmcs >= 6) + sysdev_create_file(s, &attr_pmc6); + if (cur_cpu_spec->num_pmcs >= 7) + sysdev_create_file(s, &attr_pmc7); + if (cur_cpu_spec->num_pmcs >= 8) + sysdev_create_file(s, &attr_pmc8); + + if (cpu_has_feature(CPU_FTR_SMT)) + sysdev_create_file(s, &attr_purr); +} + +#ifdef CONFIG_HOTPLUG_CPU +static void unregister_cpu_online(unsigned int cpu) +{ + struct cpu *c = &per_cpu(cpu_devices, cpu); + struct sys_device *s = &c->sysdev; + + BUG_ON(c->no_control); + +#ifndef CONFIG_PPC_ISERIES + if (cpu_has_feature(CPU_FTR_SMT)) + sysdev_remove_file(s, &attr_smt_snooze_delay); +#endif + + /* PMC stuff */ + + sysdev_remove_file(s, &attr_mmcr0); + sysdev_remove_file(s, &attr_mmcr1); + + if (cpu_has_feature(CPU_FTR_MMCRA)) + sysdev_remove_file(s, &attr_mmcra); + + if (cur_cpu_spec->num_pmcs >= 1) + sysdev_remove_file(s, &attr_pmc1); + if (cur_cpu_spec->num_pmcs >= 2) + sysdev_remove_file(s, &attr_pmc2); + if (cur_cpu_spec->num_pmcs >= 3) + sysdev_remove_file(s, &attr_pmc3); + if (cur_cpu_spec->num_pmcs >= 4) + sysdev_remove_file(s, &attr_pmc4); + if (cur_cpu_spec->num_pmcs >= 5) + sysdev_remove_file(s, &attr_pmc5); + if (cur_cpu_spec->num_pmcs >= 6) + sysdev_remove_file(s, &attr_pmc6); + if (cur_cpu_spec->num_pmcs >= 7) + sysdev_remove_file(s, &attr_pmc7); + if (cur_cpu_spec->num_pmcs >= 8) + sysdev_remove_file(s, &attr_pmc8); + + if (cpu_has_feature(CPU_FTR_SMT)) + sysdev_remove_file(s, &attr_purr); +} +#endif /* CONFIG_HOTPLUG_CPU */ + +static int __devinit sysfs_cpu_notify(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + unsigned int cpu = (unsigned int)(long)hcpu; + + switch (action) { + case CPU_ONLINE: + register_cpu_online(cpu); + break; +#ifdef CONFIG_HOTPLUG_CPU + case CPU_DEAD: + unregister_cpu_online(cpu); + break; +#endif + } + return NOTIFY_OK; +} + +static struct notifier_block __devinitdata sysfs_cpu_nb = { + .notifier_call = sysfs_cpu_notify, +}; + +/* NUMA stuff */ + +#ifdef CONFIG_NUMA +static struct node node_devices[MAX_NUMNODES]; + +static void register_nodes(void) +{ + int i; + + for (i = 0; i < MAX_NUMNODES; i++) { + if (node_online(i)) { + int p_node = parent_node(i); + struct node *parent = NULL; + + if (p_node != i) + parent = &node_devices[p_node]; + + register_node(&node_devices[i], i, parent); + } + } +} +#else +static void register_nodes(void) +{ + return; +} +#endif + +/* Only valid if CPU is present. */ +static ssize_t show_physical_id(struct sys_device *dev, char *buf) +{ + struct cpu *cpu = container_of(dev, struct cpu, sysdev); + + return sprintf(buf, "%d\n", get_hard_smp_processor_id(cpu->sysdev.id)); +} +static SYSDEV_ATTR(physical_id, 0444, show_physical_id, NULL); + +static int __init topology_init(void) +{ + int cpu; + struct node *parent = NULL; + + register_nodes(); + + register_cpu_notifier(&sysfs_cpu_nb); + + for_each_cpu(cpu) { + struct cpu *c = &per_cpu(cpu_devices, cpu); + +#ifdef CONFIG_NUMA + /* The node to which a cpu belongs can't be known + * until the cpu is made present. + */ + parent = NULL; + if (cpu_present(cpu)) + parent = &node_devices[cpu_to_node(cpu)]; +#endif + /* + * For now, we just see if the system supports making + * the RTAS calls for CPU hotplug. But, there may be a + * more comprehensive way to do this for an individual + * CPU. For instance, the boot cpu might never be valid + * for hotplugging. + */ + if (!ppc_md.cpu_die) + c->no_control = 1; + + if (cpu_online(cpu) || (c->no_control == 0)) { + register_cpu(c, cpu, parent); + + sysdev_create_file(&c->sysdev, &attr_physical_id); + } + + if (cpu_online(cpu)) + register_cpu_online(cpu); + } + + return 0; +} +__initcall(topology_init); diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index a6282b625b4..070b4b458aa 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -62,8 +62,8 @@ #include <asm/irq.h> #include <asm/div64.h> #include <asm/smp.h> +#include <asm/vdso_datapage.h> #ifdef CONFIG_PPC64 -#include <asm/systemcfg.h> #include <asm/firmware.h> #endif #ifdef CONFIG_PPC_ISERIES @@ -261,7 +261,6 @@ static inline void update_gtod(u64 new_tb_stamp, u64 new_stamp_xsec, do_gtod.varp = temp_varp; do_gtod.var_idx = temp_idx; -#ifdef CONFIG_PPC64 /* * tb_update_count is used to allow the userspace gettimeofday code * to assure itself that it sees a consistent view of the tb_to_xs and @@ -271,14 +270,15 @@ static inline void update_gtod(u64 new_tb_stamp, u64 new_stamp_xsec, * tb_to_xs and stamp_xsec values are consistent. If not, then it * loops back and reads them again until this criteria is met. */ - ++(systemcfg->tb_update_count); + ++(vdso_data->tb_update_count); smp_wmb(); - systemcfg->tb_orig_stamp = new_tb_stamp; - systemcfg->stamp_xsec = new_stamp_xsec; - systemcfg->tb_to_xs = new_tb_to_xs; + vdso_data->tb_orig_stamp = new_tb_stamp; + vdso_data->stamp_xsec = new_stamp_xsec; + vdso_data->tb_to_xs = new_tb_to_xs; + vdso_data->wtom_clock_sec = wall_to_monotonic.tv_sec; + vdso_data->wtom_clock_nsec = wall_to_monotonic.tv_nsec; smp_wmb(); - ++(systemcfg->tb_update_count); -#endif + ++(vdso_data->tb_update_count); } /* @@ -357,8 +357,8 @@ static void iSeries_tb_recal(void) do_gtod.tb_ticks_per_sec = tb_ticks_per_sec; tb_to_xs = divres.result_low; do_gtod.varp->tb_to_xs = tb_to_xs; - systemcfg->tb_ticks_per_sec = tb_ticks_per_sec; - systemcfg->tb_to_xs = tb_to_xs; + vdso_data->tb_ticks_per_sec = tb_ticks_per_sec; + vdso_data->tb_to_xs = tb_to_xs; } else { printk( "Titan recalibrate: FAILED (difference > 4 percent)\n" @@ -483,6 +483,8 @@ void __init smp_space_timers(unsigned int max_cpus) unsigned long offset = tb_ticks_per_jiffy / max_cpus; unsigned long previous_tb = per_cpu(last_jiffy, boot_cpuid); + /* make sure tb > per_cpu(last_jiffy, cpu) for all cpus always */ + previous_tb -= tb_ticks_per_jiffy; for_each_cpu(i) { if (i != boot_cpuid) { previous_tb += offset; @@ -558,10 +560,8 @@ int do_settimeofday(struct timespec *tv) new_xsec += (u64)new_sec * XSEC_PER_SEC - tb_delta_xs; update_gtod(tb_last_jiffy, new_xsec, do_gtod.varp->tb_to_xs); -#ifdef CONFIG_PPC64 - systemcfg->tz_minuteswest = sys_tz.tz_minuteswest; - systemcfg->tz_dsttime = sys_tz.tz_dsttime; -#endif + vdso_data->tz_minuteswest = sys_tz.tz_minuteswest; + vdso_data->tz_dsttime = sys_tz.tz_dsttime; write_sequnlock_irqrestore(&xtime_lock, flags); clock_was_set(); @@ -710,13 +710,12 @@ void __init time_init(void) do_gtod.tb_ticks_per_sec = tb_ticks_per_sec; do_gtod.varp->tb_to_xs = tb_to_xs; do_gtod.tb_to_us = tb_to_us; -#ifdef CONFIG_PPC64 - systemcfg->tb_orig_stamp = tb_last_jiffy; - systemcfg->tb_update_count = 0; - systemcfg->tb_ticks_per_sec = tb_ticks_per_sec; - systemcfg->stamp_xsec = xtime.tv_sec * XSEC_PER_SEC; - systemcfg->tb_to_xs = tb_to_xs; -#endif + + vdso_data->tb_orig_stamp = tb_last_jiffy; + vdso_data->tb_update_count = 0; + vdso_data->tb_ticks_per_sec = tb_ticks_per_sec; + vdso_data->stamp_xsec = xtime.tv_sec * XSEC_PER_SEC; + vdso_data->tb_to_xs = tb_to_xs; time_freq = 0; diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 32f215825e8..1511454c469 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -49,7 +49,6 @@ #ifdef CONFIG_PPC64 #include <asm/firmware.h> #include <asm/processor.h> -#include <asm/systemcfg.h> #endif #ifdef CONFIG_PPC64 /* XXX */ @@ -129,7 +128,7 @@ int die(const char *str, struct pt_regs *regs, long err) nl = 1; #endif #ifdef CONFIG_PPC64 - switch (systemcfg->platform) { + switch (_machine) { case PLATFORM_PSERIES: printk("PSERIES "); nl = 1; @@ -887,10 +886,6 @@ void altivec_unavailable_exception(struct pt_regs *regs) die("Unrecoverable VMX/Altivec Unavailable Exception", regs, SIGABRT); } -#ifdef CONFIG_PPC64 -extern perf_irq_t perf_irq; -#endif - #if defined(CONFIG_PPC64) || defined(CONFIG_E500) void performance_monitor_exception(struct pt_regs *regs) { diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c new file mode 100644 index 00000000000..0d878e72fc4 --- /dev/null +++ b/arch/powerpc/kernel/udbg.c @@ -0,0 +1,125 @@ +/* + * polling mode stateless debugging stuff, originally for NS16550 Serial Ports + * + * c 2001 PPC 64 Team, IBM Corp + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <stdarg.h> +#include <linux/config.h> +#include <linux/types.h> +#include <linux/sched.h> +#include <linux/console.h> +#include <asm/processor.h> + +void (*udbg_putc)(unsigned char c); +unsigned char (*udbg_getc)(void); +int (*udbg_getc_poll)(void); + +/* udbg library, used by xmon et al */ +void udbg_puts(const char *s) +{ + if (udbg_putc) { + char c; + + if (s && *s != '\0') { + while ((c = *s++) != '\0') + udbg_putc(c); + } + } +#if 0 + else { + printk("%s", s); + } +#endif +} + +int udbg_write(const char *s, int n) +{ + int remain = n; + char c; + + if (!udbg_putc) + return 0; + + if (s && *s != '\0') { + while (((c = *s++) != '\0') && (remain-- > 0)) { + udbg_putc(c); + } + } + + return n - remain; +} + +int udbg_read(char *buf, int buflen) +{ + char c, *p = buf; + int i; + + if (!udbg_getc) + return 0; + + for (i = 0; i < buflen; ++i) { + do { + c = udbg_getc(); + } while (c == 0x11 || c == 0x13); + if (c == 0) + break; + *p++ = c; + } + + return i; +} + +#define UDBG_BUFSIZE 256 +void udbg_printf(const char *fmt, ...) +{ + unsigned char buf[UDBG_BUFSIZE]; + va_list args; + + va_start(args, fmt); + vsnprintf(buf, UDBG_BUFSIZE, fmt, args); + udbg_puts(buf); + va_end(args); +} + +/* + * Early boot console based on udbg + */ +static void udbg_console_write(struct console *con, const char *s, + unsigned int n) +{ + udbg_write(s, n); +} + +static struct console udbg_console = { + .name = "udbg", + .write = udbg_console_write, + .flags = CON_PRINTBUFFER, + .index = -1, +}; + +static int early_console_initialized; + +void __init disable_early_printk(void) +{ + if (!early_console_initialized) + return; + unregister_console(&udbg_console); + early_console_initialized = 0; +} + +/* called by setup_system */ +void register_early_udbg_console(void) +{ + early_console_initialized = 1; + register_console(&udbg_console); +} + +#if 0 /* if you want to use this as a regular output console */ +console_initcall(register_udbg_console); +#endif diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c new file mode 100644 index 00000000000..9313574ab93 --- /dev/null +++ b/arch/powerpc/kernel/udbg_16550.c @@ -0,0 +1,123 @@ +/* + * udbg for for NS16550 compatable serial ports + * + * Copyright (C) 2001-2005 PPC 64 Team, IBM Corp + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include <linux/config.h> +#include <linux/types.h> +#include <asm/udbg.h> +#include <asm/io.h> + +extern u8 real_readb(volatile u8 __iomem *addr); +extern void real_writeb(u8 data, volatile u8 __iomem *addr); + +struct NS16550 { + /* this struct must be packed */ + unsigned char rbr; /* 0 */ + unsigned char ier; /* 1 */ + unsigned char fcr; /* 2 */ + unsigned char lcr; /* 3 */ + unsigned char mcr; /* 4 */ + unsigned char lsr; /* 5 */ + unsigned char msr; /* 6 */ + unsigned char scr; /* 7 */ +}; + +#define thr rbr +#define iir fcr +#define dll rbr +#define dlm ier +#define dlab lcr + +#define LSR_DR 0x01 /* Data ready */ +#define LSR_OE 0x02 /* Overrun */ +#define LSR_PE 0x04 /* Parity error */ +#define LSR_FE 0x08 /* Framing error */ +#define LSR_BI 0x10 /* Break */ +#define LSR_THRE 0x20 /* Xmit holding register empty */ +#define LSR_TEMT 0x40 /* Xmitter empty */ +#define LSR_ERR 0x80 /* Error */ + +static volatile struct NS16550 __iomem *udbg_comport; + +static void udbg_550_putc(unsigned char c) +{ + if (udbg_comport) { + while ((in_8(&udbg_comport->lsr) & LSR_THRE) == 0) + /* wait for idle */; + out_8(&udbg_comport->thr, c); + if (c == '\n') + udbg_550_putc('\r'); + } +} + +static int udbg_550_getc_poll(void) +{ + if (udbg_comport) { + if ((in_8(&udbg_comport->lsr) & LSR_DR) != 0) + return in_8(&udbg_comport->rbr); + else + return -1; + } + return -1; +} + +static unsigned char udbg_550_getc(void) +{ + if (udbg_comport) { + while ((in_8(&udbg_comport->lsr) & LSR_DR) == 0) + /* wait for char */; + return in_8(&udbg_comport->rbr); + } + return 0; +} + +void udbg_init_uart(void __iomem *comport, unsigned int speed) +{ + u16 dll = speed ? (115200 / speed) : 12; + + if (comport) { + udbg_comport = (struct NS16550 __iomem *)comport; + out_8(&udbg_comport->lcr, 0x00); + out_8(&udbg_comport->ier, 0xff); + out_8(&udbg_comport->ier, 0x00); + out_8(&udbg_comport->lcr, 0x80); /* Access baud rate */ + out_8(&udbg_comport->dll, dll & 0xff); /* 1 = 115200, 2 = 57600, + 3 = 38400, 12 = 9600 baud */ + out_8(&udbg_comport->dlm, dll >> 8); /* dll >> 8 which should be zero + for fast rates; */ + out_8(&udbg_comport->lcr, 0x03); /* 8 data, 1 stop, no parity */ + out_8(&udbg_comport->mcr, 0x03); /* RTS/DTR */ + out_8(&udbg_comport->fcr ,0x07); /* Clear & enable FIFOs */ + udbg_putc = udbg_550_putc; + udbg_getc = udbg_550_getc; + udbg_getc_poll = udbg_550_getc_poll; + } +} + +#ifdef CONFIG_PPC_MAPLE +void udbg_maple_real_putc(unsigned char c) +{ + if (udbg_comport) { + while ((real_readb(&udbg_comport->lsr) & LSR_THRE) == 0) + /* wait for idle */; + real_writeb(c, &udbg_comport->thr); eieio(); + if (c == '\n') + udbg_maple_real_putc('\r'); + } +} + +void udbg_init_maple_realmode(void) +{ + udbg_comport = (volatile struct NS16550 __iomem *)0xf40003f8; + + udbg_putc = udbg_maple_real_putc; + udbg_getc = NULL; + udbg_getc_poll = NULL; +} +#endif /* CONFIG_PPC_MAPLE */ diff --git a/arch/powerpc/kernel/udbg_scc.c b/arch/powerpc/kernel/udbg_scc.c new file mode 100644 index 00000000000..820c5355150 --- /dev/null +++ b/arch/powerpc/kernel/udbg_scc.c @@ -0,0 +1,135 @@ +/* + * udbg for for zilog scc ports as found on Apple PowerMacs + * + * Copyright (C) 2001-2005 PPC 64 Team, IBM Corp + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include <linux/config.h> +#include <linux/types.h> +#include <asm/udbg.h> +#include <asm/processor.h> +#include <asm/io.h> +#include <asm/prom.h> +#include <asm/pmac_feature.h> + +extern u8 real_readb(volatile u8 __iomem *addr); +extern void real_writeb(u8 data, volatile u8 __iomem *addr); + +#define SCC_TXRDY 4 +#define SCC_RXRDY 1 + +static volatile u8 __iomem *sccc; +static volatile u8 __iomem *sccd; + +static void udbg_scc_putc(unsigned char c) +{ + if (sccc) { + while ((in_8(sccc) & SCC_TXRDY) == 0) + ; + out_8(sccd, c); + if (c == '\n') + udbg_scc_putc('\r'); + } +} + +static int udbg_scc_getc_poll(void) +{ + if (sccc) { + if ((in_8(sccc) & SCC_RXRDY) != 0) + return in_8(sccd); + else + return -1; + } + return -1; +} + +static unsigned char udbg_scc_getc(void) +{ + if (sccc) { + while ((in_8(sccc) & SCC_RXRDY) == 0) + ; + return in_8(sccd); + } + return 0; +} + +static unsigned char scc_inittab[] = { + 13, 0, /* set baud rate divisor */ + 12, 0, + 14, 1, /* baud rate gen enable, src=rtxc */ + 11, 0x50, /* clocks = br gen */ + 5, 0xea, /* tx 8 bits, assert DTR & RTS */ + 4, 0x46, /* x16 clock, 1 stop */ + 3, 0xc1, /* rx enable, 8 bits */ +}; + +void udbg_init_scc(struct device_node *np) +{ + u32 *reg; + unsigned long addr; + int i, x; + + if (np == NULL) + np = of_find_node_by_name(NULL, "escc"); + if (np == NULL || np->parent == NULL) + return; + + udbg_printf("found SCC...\n"); + /* Get address within mac-io ASIC */ + reg = (u32 *)get_property(np, "reg", NULL); + if (reg == NULL) + return; + addr = reg[0]; + udbg_printf("local addr: %lx\n", addr); + /* Get address of mac-io PCI itself */ + reg = (u32 *)get_property(np->parent, "assigned-addresses", NULL); + if (reg == NULL) + return; + addr += reg[2]; + udbg_printf("final addr: %lx\n", addr); + + /* Setup for 57600 8N1 */ + addr += 0x20; + sccc = (volatile u8 * __iomem) ioremap(addr & PAGE_MASK, PAGE_SIZE) ; + sccc += addr & ~PAGE_MASK; + sccd = sccc + 0x10; + + udbg_printf("ioremap result sccc: %p\n", sccc); + mb(); + + for (i = 20000; i != 0; --i) + x = in_8(sccc); + out_8(sccc, 0x09); /* reset A or B side */ + out_8(sccc, 0xc0); + for (i = 0; i < sizeof(scc_inittab); ++i) + out_8(sccc, scc_inittab[i]); + + udbg_putc = udbg_scc_putc; + udbg_getc = udbg_scc_getc; + udbg_getc_poll = udbg_scc_getc_poll; + + udbg_puts("Hello World !\n"); +} + +static void udbg_real_scc_putc(unsigned char c) +{ + while ((real_readb(sccc) & SCC_TXRDY) == 0) + ; + real_writeb(c, sccd); + if (c == '\n') + udbg_real_scc_putc('\r'); +} + +void udbg_init_pmac_realmode(void) +{ + sccc = (volatile u8 __iomem *)0x80013020ul; + sccd = (volatile u8 __iomem *)0x80013030ul; + + udbg_putc = udbg_real_scc_putc; + udbg_getc = NULL; + udbg_getc_poll = NULL; +} diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c new file mode 100644 index 00000000000..0d4d8bec0df --- /dev/null +++ b/arch/powerpc/kernel/vdso.c @@ -0,0 +1,746 @@ +/* + * linux/arch/ppc64/kernel/vdso.c + * + * Copyright (C) 2004 Benjamin Herrenschmidt, IBM Corp. + * <benh@kernel.crashing.org> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/config.h> +#include <linux/module.h> +#include <linux/errno.h> +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/smp_lock.h> +#include <linux/stddef.h> +#include <linux/unistd.h> +#include <linux/slab.h> +#include <linux/user.h> +#include <linux/elf.h> +#include <linux/security.h> +#include <linux/bootmem.h> + +#include <asm/pgtable.h> +#include <asm/system.h> +#include <asm/processor.h> +#include <asm/mmu.h> +#include <asm/mmu_context.h> +#include <asm/lmb.h> +#include <asm/machdep.h> +#include <asm/cputable.h> +#include <asm/sections.h> +#include <asm/vdso.h> +#include <asm/vdso_datapage.h> + +#undef DEBUG + +#ifdef DEBUG +#define DBG(fmt...) printk(fmt) +#else +#define DBG(fmt...) +#endif + +/* Max supported size for symbol names */ +#define MAX_SYMNAME 64 + +extern char vdso32_start, vdso32_end; +static void *vdso32_kbase = &vdso32_start; +unsigned int vdso32_pages; +unsigned long vdso32_sigtramp; +unsigned long vdso32_rt_sigtramp; + +#ifdef CONFIG_PPC64 +extern char vdso64_start, vdso64_end; +static void *vdso64_kbase = &vdso64_start; +unsigned int vdso64_pages; +unsigned long vdso64_rt_sigtramp; +#endif /* CONFIG_PPC64 */ + +/* + * The vdso data page (aka. systemcfg for old ppc64 fans) is here. + * Once the early boot kernel code no longer needs to muck around + * with it, it will become dynamically allocated + */ +static union { + struct vdso_data data; + u8 page[PAGE_SIZE]; +} vdso_data_store __attribute__((__section__(".data.page_aligned"))); +struct vdso_data *vdso_data = &vdso_data_store.data; + +/* Format of the patch table */ +struct vdso_patch_def +{ + unsigned long ftr_mask, ftr_value; + const char *gen_name; + const char *fix_name; +}; + +/* Table of functions to patch based on the CPU type/revision + * + * Currently, we only change sync_dicache to do nothing on processors + * with a coherent icache + */ +static struct vdso_patch_def vdso_patches[] = { + { + CPU_FTR_COHERENT_ICACHE, CPU_FTR_COHERENT_ICACHE, + "__kernel_sync_dicache", "__kernel_sync_dicache_p5" + }, + { + CPU_FTR_USE_TB, 0, + "__kernel_gettimeofday", NULL + }, +}; + +/* + * Some infos carried around for each of them during parsing at + * boot time. + */ +struct lib32_elfinfo +{ + Elf32_Ehdr *hdr; /* ptr to ELF */ + Elf32_Sym *dynsym; /* ptr to .dynsym section */ + unsigned long dynsymsize; /* size of .dynsym section */ + char *dynstr; /* ptr to .dynstr section */ + unsigned long text; /* offset of .text section in .so */ +}; + +struct lib64_elfinfo +{ + Elf64_Ehdr *hdr; + Elf64_Sym *dynsym; + unsigned long dynsymsize; + char *dynstr; + unsigned long text; +}; + + +#ifdef __DEBUG +static void dump_one_vdso_page(struct page *pg, struct page *upg) +{ + printk("kpg: %p (c:%d,f:%08lx)", __va(page_to_pfn(pg) << PAGE_SHIFT), + page_count(pg), + pg->flags); + if (upg/* && pg != upg*/) { + printk(" upg: %p (c:%d,f:%08lx)", __va(page_to_pfn(upg) + << PAGE_SHIFT), + page_count(upg), + upg->flags); + } + printk("\n"); +} + +static void dump_vdso_pages(struct vm_area_struct * vma) +{ + int i; + + if (!vma || test_thread_flag(TIF_32BIT)) { + printk("vDSO32 @ %016lx:\n", (unsigned long)vdso32_kbase); + for (i=0; i<vdso32_pages; i++) { + struct page *pg = virt_to_page(vdso32_kbase + + i*PAGE_SIZE); + struct page *upg = (vma && vma->vm_mm) ? + follow_page(vma->vm_mm, vma->vm_start + + i*PAGE_SIZE, 0) + : NULL; + dump_one_vdso_page(pg, upg); + } + } + if (!vma || !test_thread_flag(TIF_32BIT)) { + printk("vDSO64 @ %016lx:\n", (unsigned long)vdso64_kbase); + for (i=0; i<vdso64_pages; i++) { + struct page *pg = virt_to_page(vdso64_kbase + + i*PAGE_SIZE); + struct page *upg = (vma && vma->vm_mm) ? + follow_page(vma->vm_mm, vma->vm_start + + i*PAGE_SIZE, 0) + : NULL; + dump_one_vdso_page(pg, upg); + } + } +} +#endif /* DEBUG */ + +/* + * Keep a dummy vma_close for now, it will prevent VMA merging. + */ +static void vdso_vma_close(struct vm_area_struct * vma) +{ +} + +/* + * Our nopage() function, maps in the actual vDSO kernel pages, they will + * be mapped read-only by do_no_page(), and eventually COW'ed, either + * right away for an initial write access, or by do_wp_page(). + */ +static struct page * vdso_vma_nopage(struct vm_area_struct * vma, + unsigned long address, int *type) +{ + unsigned long offset = address - vma->vm_start; + struct page *pg; +#ifdef CONFIG_PPC64 + void *vbase = test_thread_flag(TIF_32BIT) ? + vdso32_kbase : vdso64_kbase; +#else + void *vbase = vdso32_kbase; +#endif + + DBG("vdso_vma_nopage(current: %s, address: %016lx, off: %lx)\n", + current->comm, address, offset); + + if (address < vma->vm_start || address > vma->vm_end) + return NOPAGE_SIGBUS; + + /* + * Last page is systemcfg. + */ + if ((vma->vm_end - address) <= PAGE_SIZE) + pg = virt_to_page(vdso_data); + else + pg = virt_to_page(vbase + offset); + + get_page(pg); + DBG(" ->page count: %d\n", page_count(pg)); + + return pg; +} + +static struct vm_operations_struct vdso_vmops = { + .close = vdso_vma_close, + .nopage = vdso_vma_nopage, +}; + +/* + * This is called from binfmt_elf, we create the special vma for the + * vDSO and insert it into the mm struct tree + */ +int arch_setup_additional_pages(struct linux_binprm *bprm, + int executable_stack) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + unsigned long vdso_pages; + unsigned long vdso_base; + +#ifdef CONFIG_PPC64 + if (test_thread_flag(TIF_32BIT)) { + vdso_pages = vdso32_pages; + vdso_base = VDSO32_MBASE; + } else { + vdso_pages = vdso64_pages; + vdso_base = VDSO64_MBASE; + } +#else + vdso_pages = vdso32_pages; + vdso_base = VDSO32_MBASE; +#endif + + current->thread.vdso_base = 0; + + /* vDSO has a problem and was disabled, just don't "enable" it for the + * process + */ + if (vdso_pages == 0) + return 0; + + vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL); + if (vma == NULL) + return -ENOMEM; + + memset(vma, 0, sizeof(*vma)); + + /* Add a page to the vdso size for the data page */ + vdso_pages ++; + + /* + * pick a base address for the vDSO in process space. We try to put it + * at vdso_base which is the "natural" base for it, but we might fail + * and end up putting it elsewhere. + */ + vdso_base = get_unmapped_area(NULL, vdso_base, + vdso_pages << PAGE_SHIFT, 0, 0); + if (vdso_base & ~PAGE_MASK) { + kmem_cache_free(vm_area_cachep, vma); + return (int)vdso_base; + } + + current->thread.vdso_base = vdso_base; + + vma->vm_mm = mm; + vma->vm_start = current->thread.vdso_base; + vma->vm_end = vma->vm_start + (vdso_pages << PAGE_SHIFT); + + /* + * our vma flags don't have VM_WRITE so by default, the process isn't + * allowed to write those pages. + * gdb can break that with ptrace interface, and thus trigger COW on + * those pages but it's then your responsibility to never do that on + * the "data" page of the vDSO or you'll stop getting kernel updates + * and your nice userland gettimeofday will be totally dead. + * It's fine to use that for setting breakpoints in the vDSO code + * pages though + */ + vma->vm_flags = VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | + VM_MAYEXEC | VM_RESERVED; + vma->vm_flags |= mm->def_flags; + vma->vm_page_prot = protection_map[vma->vm_flags & 0x7]; + vma->vm_ops = &vdso_vmops; + + down_write(&mm->mmap_sem); + if (insert_vm_struct(mm, vma)) { + up_write(&mm->mmap_sem); + kmem_cache_free(vm_area_cachep, vma); + return -ENOMEM; + } + mm->total_vm += (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; + up_write(&mm->mmap_sem); + + return 0; +} + +static void * __init find_section32(Elf32_Ehdr *ehdr, const char *secname, + unsigned long *size) +{ + Elf32_Shdr *sechdrs; + unsigned int i; + char *secnames; + + /* Grab section headers and strings so we can tell who is who */ + sechdrs = (void *)ehdr + ehdr->e_shoff; + secnames = (void *)ehdr + sechdrs[ehdr->e_shstrndx].sh_offset; + + /* Find the section they want */ + for (i = 1; i < ehdr->e_shnum; i++) { + if (strcmp(secnames+sechdrs[i].sh_name, secname) == 0) { + if (size) + *size = sechdrs[i].sh_size; + return (void *)ehdr + sechdrs[i].sh_offset; + } + } + *size = 0; + return NULL; +} + +static Elf32_Sym * __init find_symbol32(struct lib32_elfinfo *lib, + const char *symname) +{ + unsigned int i; + char name[MAX_SYMNAME], *c; + + for (i = 0; i < (lib->dynsymsize / sizeof(Elf32_Sym)); i++) { + if (lib->dynsym[i].st_name == 0) + continue; + strlcpy(name, lib->dynstr + lib->dynsym[i].st_name, + MAX_SYMNAME); + c = strchr(name, '@'); + if (c) + *c = 0; + if (strcmp(symname, name) == 0) + return &lib->dynsym[i]; + } + return NULL; +} + +/* Note that we assume the section is .text and the symbol is relative to + * the library base + */ +static unsigned long __init find_function32(struct lib32_elfinfo *lib, + const char *symname) +{ + Elf32_Sym *sym = find_symbol32(lib, symname); + + if (sym == NULL) { + printk(KERN_WARNING "vDSO32: function %s not found !\n", + symname); + return 0; + } + return sym->st_value - VDSO32_LBASE; +} + +static int vdso_do_func_patch32(struct lib32_elfinfo *v32, + struct lib64_elfinfo *v64, + const char *orig, const char *fix) +{ + Elf32_Sym *sym32_gen, *sym32_fix; + + sym32_gen = find_symbol32(v32, orig); + if (sym32_gen == NULL) { + printk(KERN_ERR "vDSO32: Can't find symbol %s !\n", orig); + return -1; + } + if (fix == NULL) { + sym32_gen->st_name = 0; + return 0; + } + sym32_fix = find_symbol32(v32, fix); + if (sym32_fix == NULL) { + printk(KERN_ERR "vDSO32: Can't find symbol %s !\n", fix); + return -1; + } + sym32_gen->st_value = sym32_fix->st_value; + sym32_gen->st_size = sym32_fix->st_size; + sym32_gen->st_info = sym32_fix->st_info; + sym32_gen->st_other = sym32_fix->st_other; + sym32_gen->st_shndx = sym32_fix->st_shndx; + + return 0; +} + + +#ifdef CONFIG_PPC64 + +static void * __init find_section64(Elf64_Ehdr *ehdr, const char *secname, + unsigned long *size) +{ + Elf64_Shdr *sechdrs; + unsigned int i; + char *secnames; + + /* Grab section headers and strings so we can tell who is who */ + sechdrs = (void *)ehdr + ehdr->e_shoff; + secnames = (void *)ehdr + sechdrs[ehdr->e_shstrndx].sh_offset; + + /* Find the section they want */ + for (i = 1; i < ehdr->e_shnum; i++) { + if (strcmp(secnames+sechdrs[i].sh_name, secname) == 0) { + if (size) + *size = sechdrs[i].sh_size; + return (void *)ehdr + sechdrs[i].sh_offset; + } + } + if (size) + *size = 0; + return NULL; +} + +static Elf64_Sym * __init find_symbol64(struct lib64_elfinfo *lib, + const char *symname) +{ + unsigned int i; + char name[MAX_SYMNAME], *c; + + for (i = 0; i < (lib->dynsymsize / sizeof(Elf64_Sym)); i++) { + if (lib->dynsym[i].st_name == 0) + continue; + strlcpy(name, lib->dynstr + lib->dynsym[i].st_name, + MAX_SYMNAME); + c = strchr(name, '@'); + if (c) + *c = 0; + if (strcmp(symname, name) == 0) + return &lib->dynsym[i]; + } + return NULL; +} + +/* Note that we assume the section is .text and the symbol is relative to + * the library base + */ +static unsigned long __init find_function64(struct lib64_elfinfo *lib, + const char *symname) +{ + Elf64_Sym *sym = find_symbol64(lib, symname); + + if (sym == NULL) { + printk(KERN_WARNING "vDSO64: function %s not found !\n", + symname); + return 0; + } +#ifdef VDS64_HAS_DESCRIPTORS + return *((u64 *)(vdso64_kbase + sym->st_value - VDSO64_LBASE)) - + VDSO64_LBASE; +#else + return sym->st_value - VDSO64_LBASE; +#endif +} + +static int vdso_do_func_patch64(struct lib32_elfinfo *v32, + struct lib64_elfinfo *v64, + const char *orig, const char *fix) +{ + Elf64_Sym *sym64_gen, *sym64_fix; + + sym64_gen = find_symbol64(v64, orig); + if (sym64_gen == NULL) { + printk(KERN_ERR "vDSO64: Can't find symbol %s !\n", orig); + return -1; + } + if (fix == NULL) { + sym64_gen->st_name = 0; + return 0; + } + sym64_fix = find_symbol64(v64, fix); + if (sym64_fix == NULL) { + printk(KERN_ERR "vDSO64: Can't find symbol %s !\n", fix); + return -1; + } + sym64_gen->st_value = sym64_fix->st_value; + sym64_gen->st_size = sym64_fix->st_size; + sym64_gen->st_info = sym64_fix->st_info; + sym64_gen->st_other = sym64_fix->st_other; + sym64_gen->st_shndx = sym64_fix->st_shndx; + + return 0; +} + +#endif /* CONFIG_PPC64 */ + + +static __init int vdso_do_find_sections(struct lib32_elfinfo *v32, + struct lib64_elfinfo *v64) +{ + void *sect; + + /* + * Locate symbol tables & text section + */ + + v32->dynsym = find_section32(v32->hdr, ".dynsym", &v32->dynsymsize); + v32->dynstr = find_section32(v32->hdr, ".dynstr", NULL); + if (v32->dynsym == NULL || v32->dynstr == NULL) { + printk(KERN_ERR "vDSO32: required symbol section not found\n"); + return -1; + } + sect = find_section32(v32->hdr, ".text", NULL); + if (sect == NULL) { + printk(KERN_ERR "vDSO32: the .text section was not found\n"); + return -1; + } + v32->text = sect - vdso32_kbase; + +#ifdef CONFIG_PPC64 + v64->dynsym = find_section64(v64->hdr, ".dynsym", &v64->dynsymsize); + v64->dynstr = find_section64(v64->hdr, ".dynstr", NULL); + if (v64->dynsym == NULL || v64->dynstr == NULL) { + printk(KERN_ERR "vDSO64: required symbol section not found\n"); + return -1; + } + sect = find_section64(v64->hdr, ".text", NULL); + if (sect == NULL) { + printk(KERN_ERR "vDSO64: the .text section was not found\n"); + return -1; + } + v64->text = sect - vdso64_kbase; +#endif /* CONFIG_PPC64 */ + + return 0; +} + +static __init void vdso_setup_trampolines(struct lib32_elfinfo *v32, + struct lib64_elfinfo *v64) +{ + /* + * Find signal trampolines + */ + +#ifdef CONFIG_PPC64 + vdso64_rt_sigtramp = find_function64(v64, "__kernel_sigtramp_rt64"); +#endif + vdso32_sigtramp = find_function32(v32, "__kernel_sigtramp32"); + vdso32_rt_sigtramp = find_function32(v32, "__kernel_sigtramp_rt32"); +} + +static __init int vdso_fixup_datapage(struct lib32_elfinfo *v32, + struct lib64_elfinfo *v64) +{ + Elf32_Sym *sym32; +#ifdef CONFIG_PPC64 + Elf64_Sym *sym64; + + sym64 = find_symbol64(v64, "__kernel_datapage_offset"); + if (sym64 == NULL) { + printk(KERN_ERR "vDSO64: Can't find symbol " + "__kernel_datapage_offset !\n"); + return -1; + } + *((int *)(vdso64_kbase + sym64->st_value - VDSO64_LBASE)) = + (vdso64_pages << PAGE_SHIFT) - + (sym64->st_value - VDSO64_LBASE); +#endif /* CONFIG_PPC64 */ + + sym32 = find_symbol32(v32, "__kernel_datapage_offset"); + if (sym32 == NULL) { + printk(KERN_ERR "vDSO32: Can't find symbol " + "__kernel_datapage_offset !\n"); + return -1; + } + *((int *)(vdso32_kbase + (sym32->st_value - VDSO32_LBASE))) = + (vdso32_pages << PAGE_SHIFT) - + (sym32->st_value - VDSO32_LBASE); + + return 0; +} + +static __init int vdso_fixup_alt_funcs(struct lib32_elfinfo *v32, + struct lib64_elfinfo *v64) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(vdso_patches); i++) { + struct vdso_patch_def *patch = &vdso_patches[i]; + int match = (cur_cpu_spec->cpu_features & patch->ftr_mask) + == patch->ftr_value; + if (!match) + continue; + + DBG("replacing %s with %s...\n", patch->gen_name, + patch->fix_name ? "NONE" : patch->fix_name); + + /* + * Patch the 32 bits and 64 bits symbols. Note that we do not + * patch the "." symbol on 64 bits. + * It would be easy to do, but doesn't seem to be necessary, + * patching the OPD symbol is enough. + */ + vdso_do_func_patch32(v32, v64, patch->gen_name, + patch->fix_name); +#ifdef CONFIG_PPC64 + vdso_do_func_patch64(v32, v64, patch->gen_name, + patch->fix_name); +#endif /* CONFIG_PPC64 */ + } + + return 0; +} + + +static __init int vdso_setup(void) +{ + struct lib32_elfinfo v32; + struct lib64_elfinfo v64; + + v32.hdr = vdso32_kbase; +#ifdef CONFIG_PPC64 + v64.hdr = vdso64_kbase; +#endif + if (vdso_do_find_sections(&v32, &v64)) + return -1; + + if (vdso_fixup_datapage(&v32, &v64)) + return -1; + + if (vdso_fixup_alt_funcs(&v32, &v64)) + return -1; + + vdso_setup_trampolines(&v32, &v64); + + return 0; +} + +/* + * Called from setup_arch to initialize the bitmap of available + * syscalls in the systemcfg page + */ +static void __init vdso_setup_syscall_map(void) +{ + unsigned int i; + extern unsigned long *sys_call_table; + extern unsigned long sys_ni_syscall; + + + for (i = 0; i < __NR_syscalls; i++) { +#ifdef CONFIG_PPC64 + if (sys_call_table[i*2] != sys_ni_syscall) + vdso_data->syscall_map_64[i >> 5] |= + 0x80000000UL >> (i & 0x1f); + if (sys_call_table[i*2+1] != sys_ni_syscall) + vdso_data->syscall_map_32[i >> 5] |= + 0x80000000UL >> (i & 0x1f); +#else /* CONFIG_PPC64 */ + if (sys_call_table[i] != sys_ni_syscall) + vdso_data->syscall_map_32[i >> 5] |= + 0x80000000UL >> (i & 0x1f); +#endif /* CONFIG_PPC64 */ + } +} + + +void __init vdso_init(void) +{ + int i; + +#ifdef CONFIG_PPC64 + /* + * Fill up the "systemcfg" stuff for backward compatiblity + */ + strcpy(vdso_data->eye_catcher, "SYSTEMCFG:PPC64"); + vdso_data->version.major = SYSTEMCFG_MAJOR; + vdso_data->version.minor = SYSTEMCFG_MINOR; + vdso_data->processor = mfspr(SPRN_PVR); + vdso_data->platform = _machine; + vdso_data->physicalMemorySize = lmb_phys_mem_size(); + vdso_data->dcache_size = ppc64_caches.dsize; + vdso_data->dcache_line_size = ppc64_caches.dline_size; + vdso_data->icache_size = ppc64_caches.isize; + vdso_data->icache_line_size = ppc64_caches.iline_size; + + /* + * Calculate the size of the 64 bits vDSO + */ + vdso64_pages = (&vdso64_end - &vdso64_start) >> PAGE_SHIFT; + DBG("vdso64_kbase: %p, 0x%x pages\n", vdso64_kbase, vdso64_pages); +#endif /* CONFIG_PPC64 */ + + + /* + * Calculate the size of the 32 bits vDSO + */ + vdso32_pages = (&vdso32_end - &vdso32_start) >> PAGE_SHIFT; + DBG("vdso32_kbase: %p, 0x%x pages\n", vdso32_kbase, vdso32_pages); + + + /* + * Setup the syscall map in the vDOS + */ + vdso_setup_syscall_map(); + /* + * Initialize the vDSO images in memory, that is do necessary + * fixups of vDSO symbols, locate trampolines, etc... + */ + if (vdso_setup()) { + printk(KERN_ERR "vDSO setup failure, not enabled !\n"); + vdso32_pages = 0; +#ifdef CONFIG_PPC64 + vdso64_pages = 0; +#endif + return; + } + + /* Make sure pages are in the correct state */ + for (i = 0; i < vdso32_pages; i++) { + struct page *pg = virt_to_page(vdso32_kbase + i*PAGE_SIZE); + ClearPageReserved(pg); + get_page(pg); + + } +#ifdef CONFIG_PPC64 + for (i = 0; i < vdso64_pages; i++) { + struct page *pg = virt_to_page(vdso64_kbase + i*PAGE_SIZE); + ClearPageReserved(pg); + get_page(pg); + } +#endif /* CONFIG_PPC64 */ + + get_page(virt_to_page(vdso_data)); +} + +int in_gate_area_no_task(unsigned long addr) +{ + return 0; +} + +int in_gate_area(struct task_struct *task, unsigned long addr) +{ + return 0; +} + +struct vm_area_struct *get_gate_vma(struct task_struct *tsk) +{ + return NULL; +} + diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile new file mode 100644 index 00000000000..8a3bed5f143 --- /dev/null +++ b/arch/powerpc/kernel/vdso32/Makefile @@ -0,0 +1,40 @@ + +# List of files in the vdso, has to be asm only for now + +obj-vdso32 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o + +# Build rules + +ifeq ($(CONFIG_PPC32),y) +CROSS32CC := $(CC) +endif + +targets := $(obj-vdso32) vdso32.so +obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32)) + + +EXTRA_CFLAGS := -shared -s -fno-common -fno-builtin +EXTRA_CFLAGS += -nostdlib -Wl,-soname=linux-vdso32.so.1 +EXTRA_AFLAGS := -D__VDSO32__ -s + +obj-y += vdso32_wrapper.o +extra-y += vdso32.lds +CPPFLAGS_vdso32.lds += -P -C -Upowerpc + +# Force dependency (incbin is bad) +$(obj)/vdso32_wrapper.o : $(obj)/vdso32.so + +# link rule for the .so file, .lds has to be first +$(obj)/vdso32.so: $(src)/vdso32.lds $(obj-vdso32) + $(call if_changed,vdso32ld) + +# assembly rules for the .S files +$(obj-vdso32): %.o: %.S + $(call if_changed_dep,vdso32as) + +# actual build commands +quiet_cmd_vdso32ld = VDSO32L $@ + cmd_vdso32ld = $(CROSS32CC) $(c_flags) -Wl,-T $^ -o $@ +quiet_cmd_vdso32as = VDSO32A $@ + cmd_vdso32as = $(CROSS32CC) $(a_flags) -c -o $@ $< + diff --git a/arch/powerpc/kernel/vdso32/cacheflush.S b/arch/powerpc/kernel/vdso32/cacheflush.S new file mode 100644 index 00000000000..c8db993574e --- /dev/null +++ b/arch/powerpc/kernel/vdso32/cacheflush.S @@ -0,0 +1,67 @@ +/* + * vDSO provided cache flush routines + * + * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org), + * IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include <linux/config.h> +#include <asm/processor.h> +#include <asm/ppc_asm.h> +#include <asm/vdso.h> +#include <asm/asm-offsets.h> + + .text + +/* + * Default "generic" version of __kernel_sync_dicache. + * + * void __kernel_sync_dicache(unsigned long start, unsigned long end) + * + * Flushes the data cache & invalidate the instruction cache for the + * provided range [start, end[ + * + * Note: all CPUs supported by this kernel have a 128 bytes cache + * line size so we don't have to peek that info from the datapage + */ +V_FUNCTION_BEGIN(__kernel_sync_dicache) + .cfi_startproc + li r5,127 + andc r6,r3,r5 /* round low to line bdy */ + subf r8,r6,r4 /* compute length */ + add r8,r8,r5 /* ensure we get enough */ + srwi. r8,r8,7 /* compute line count */ + beqlr /* nothing to do? */ + mtctr r8 + mr r3,r6 +1: dcbst 0,r3 + addi r3,r3,128 + bdnz 1b + sync + mtctr r8 +1: icbi 0,r6 + addi r6,r6,128 + bdnz 1b + isync + li r3,0 + blr + .cfi_endproc +V_FUNCTION_END(__kernel_sync_dicache) + + +/* + * POWER5 version of __kernel_sync_dicache + */ +V_FUNCTION_BEGIN(__kernel_sync_dicache_p5) + .cfi_startproc + sync + isync + li r3,0 + blr + .cfi_endproc +V_FUNCTION_END(__kernel_sync_dicache_p5) + diff --git a/arch/powerpc/kernel/vdso32/datapage.S b/arch/powerpc/kernel/vdso32/datapage.S new file mode 100644 index 00000000000..a08c26e8783 --- /dev/null +++ b/arch/powerpc/kernel/vdso32/datapage.S @@ -0,0 +1,84 @@ +/* + * Access to the shared data page by the vDSO & syscall map + * + * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org), IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/config.h> +#include <asm/processor.h> +#include <asm/ppc_asm.h> +#include <asm/asm-offsets.h> +#include <asm/unistd.h> +#include <asm/vdso.h> + + .text +V_FUNCTION_BEGIN(__get_datapage) + .cfi_startproc + /* We don't want that exposed or overridable as we want other objects + * to be able to bl directly to here + */ + .protected __get_datapage + .hidden __get_datapage + + mflr r0 + .cfi_register lr,r0 + + bcl 20,31,1f + .global __kernel_datapage_offset; +__kernel_datapage_offset: + .long 0 +1: + mflr r3 + mtlr r0 + lwz r0,0(r3) + add r3,r0,r3 + blr + .cfi_endproc +V_FUNCTION_END(__get_datapage) + +/* + * void *__kernel_get_syscall_map(unsigned int *syscall_count) ; + * + * returns a pointer to the syscall map. the map is agnostic to the + * size of "long", unlike kernel bitops, it stores bits from top to + * bottom so that memory actually contains a linear bitmap + * check for syscall N by testing bit (0x80000000 >> (N & 0x1f)) of + * 32 bits int at N >> 5. + */ +V_FUNCTION_BEGIN(__kernel_get_syscall_map) + .cfi_startproc + mflr r12 + .cfi_register lr,r12 + + mr r4,r3 + bl __get_datapage@local + mtlr r12 + addi r3,r3,CFG_SYSCALL_MAP32 + cmpli cr0,r4,0 + beqlr + li r0,__NR_syscalls + stw r0,0(r4) + blr + .cfi_endproc +V_FUNCTION_END(__kernel_get_syscall_map) + +/* + * void unsigned long long __kernel_get_tbfreq(void); + * + * returns the timebase frequency in HZ + */ +V_FUNCTION_BEGIN(__kernel_get_tbfreq) + .cfi_startproc + mflr r12 + .cfi_register lr,r12 + bl __get_datapage@local + lwz r3,CFG_TB_TICKS_PER_SEC(r3) + lwz r4,(CFG_TB_TICKS_PER_SEC + 4)(r3) + mtlr r12 + .cfi_endproc +V_FUNCTION_END(__kernel_get_tbfreq) diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S new file mode 100644 index 00000000000..aeb5fc9b87b --- /dev/null +++ b/arch/powerpc/kernel/vdso32/gettimeofday.S @@ -0,0 +1,315 @@ +/* + * Userland implementation of gettimeofday() for 32 bits processes in a + * ppc64 kernel for use in the vDSO + * + * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org, + * IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include <linux/config.h> +#include <asm/processor.h> +#include <asm/ppc_asm.h> +#include <asm/vdso.h> +#include <asm/asm-offsets.h> +#include <asm/unistd.h> + + .text +/* + * Exact prototype of gettimeofday + * + * int __kernel_gettimeofday(struct timeval *tv, struct timezone *tz); + * + */ +V_FUNCTION_BEGIN(__kernel_gettimeofday) + .cfi_startproc + mflr r12 + .cfi_register lr,r12 + + mr r10,r3 /* r10 saves tv */ + mr r11,r4 /* r11 saves tz */ + bl __get_datapage@local /* get data page */ + mr r9, r3 /* datapage ptr in r9 */ + bl __do_get_xsec@local /* get xsec from tb & kernel */ + bne- 2f /* out of line -> do syscall */ + + /* seconds are xsec >> 20 */ + rlwinm r5,r4,12,20,31 + rlwimi r5,r3,12,0,19 + stw r5,TVAL32_TV_SEC(r10) + + /* get remaining xsec and convert to usec. we scale + * up remaining xsec by 12 bits and get the top 32 bits + * of the multiplication + */ + rlwinm r5,r4,12,0,19 + lis r6,1000000@h + ori r6,r6,1000000@l + mulhwu r5,r5,r6 + stw r5,TVAL32_TV_USEC(r10) + + cmpli cr0,r11,0 /* check if tz is NULL */ + beq 1f + lwz r4,CFG_TZ_MINUTEWEST(r9)/* fill tz */ + lwz r5,CFG_TZ_DSTTIME(r9) + stw r4,TZONE_TZ_MINWEST(r11) + stw r5,TZONE_TZ_DSTTIME(r11) + +1: mtlr r12 + li r3,0 + blr + +2: + mtlr r12 + mr r3,r10 + mr r4,r11 + li r0,__NR_gettimeofday + sc + blr + .cfi_endproc +V_FUNCTION_END(__kernel_gettimeofday) + +/* + * Exact prototype of clock_gettime() + * + * int __kernel_clock_gettime(clockid_t clock_id, struct timespec *tp); + * + */ +V_FUNCTION_BEGIN(__kernel_clock_gettime) + .cfi_startproc + /* Check for supported clock IDs */ + cmpli cr0,r3,CLOCK_REALTIME + cmpli cr1,r3,CLOCK_MONOTONIC + cror cr0,cr0,cr1 + bne cr0,99f + + mflr r12 /* r12 saves lr */ + .cfi_register lr,r12 + mr r10,r3 /* r10 saves id */ + mr r11,r4 /* r11 saves tp */ + bl __get_datapage@local /* get data page */ + mr r9, r3 /* datapage ptr in r9 */ + beq cr1,50f /* if monotonic -> jump there */ + + /* + * CLOCK_REALTIME + */ + + bl __do_get_xsec@local /* get xsec from tb & kernel */ + bne- 98f /* out of line -> do syscall */ + + /* seconds are xsec >> 20 */ + rlwinm r5,r4,12,20,31 + rlwimi r5,r3,12,0,19 + stw r5,TSPC32_TV_SEC(r11) + + /* get remaining xsec and convert to nsec. we scale + * up remaining xsec by 12 bits and get the top 32 bits + * of the multiplication, then we multiply by 1000 + */ + rlwinm r5,r4,12,0,19 + lis r6,1000000@h + ori r6,r6,1000000@l + mulhwu r5,r5,r6 + mulli r5,r5,1000 + stw r5,TSPC32_TV_NSEC(r11) + mtlr r12 + li r3,0 + blr + + /* + * CLOCK_MONOTONIC + */ + +50: bl __do_get_xsec@local /* get xsec from tb & kernel */ + bne- 98f /* out of line -> do syscall */ + + /* seconds are xsec >> 20 */ + rlwinm r6,r4,12,20,31 + rlwimi r6,r3,12,0,19 + + /* get remaining xsec and convert to nsec. we scale + * up remaining xsec by 12 bits and get the top 32 bits + * of the multiplication, then we multiply by 1000 + */ + rlwinm r7,r4,12,0,19 + lis r5,1000000@h + ori r5,r5,1000000@l + mulhwu r7,r7,r5 + mulli r7,r7,1000 + + /* now we must fixup using wall to monotonic. We need to snapshot + * that value and do the counter trick again. Fortunately, we still + * have the counter value in r8 that was returned by __do_get_xsec. + * At this point, r6,r7 contain our sec/nsec values, r3,r4 and r5 + * can be used + */ + + lwz r3,WTOM_CLOCK_SEC(r9) + lwz r4,WTOM_CLOCK_NSEC(r9) + + /* We now have our result in r3,r4. We create a fake dependency + * on that result and re-check the counter + */ + or r5,r4,r3 + xor r0,r5,r5 + add r9,r9,r0 +#ifdef CONFIG_PPC64 + lwz r0,(CFG_TB_UPDATE_COUNT+4)(r9) +#else + lwz r0,(CFG_TB_UPDATE_COUNT)(r9) +#endif + cmpl cr0,r8,r0 /* check if updated */ + bne- 50b + + /* Calculate and store result. Note that this mimmics the C code, + * which may cause funny results if nsec goes negative... is that + * possible at all ? + */ + add r3,r3,r6 + add r4,r4,r7 + lis r5,NSEC_PER_SEC@h + ori r5,r5,NSEC_PER_SEC@l + cmpli cr0,r4,r5 + blt 1f + subf r4,r5,r4 + addi r3,r3,1 +1: stw r3,TSPC32_TV_SEC(r11) + stw r4,TSPC32_TV_NSEC(r11) + + mtlr r12 + li r3,0 + blr + + /* + * syscall fallback + */ +98: + mtlr r12 + mr r3,r10 + mr r4,r11 +99: + li r0,__NR_clock_gettime + sc + blr + .cfi_endproc +V_FUNCTION_END(__kernel_clock_gettime) + + +/* + * Exact prototype of clock_getres() + * + * int __kernel_clock_getres(clockid_t clock_id, struct timespec *res); + * + */ +V_FUNCTION_BEGIN(__kernel_clock_getres) + .cfi_startproc + /* Check for supported clock IDs */ + cmpwi cr0,r3,CLOCK_REALTIME + cmpwi cr1,r3,CLOCK_MONOTONIC + cror cr0,cr0,cr1 + bne cr0,99f + + li r3,0 + cmpli cr0,r4,0 + beqlr + lis r5,CLOCK_REALTIME_RES@h + ori r5,r5,CLOCK_REALTIME_RES@l + stw r3,TSPC32_TV_SEC(r4) + stw r5,TSPC32_TV_NSEC(r4) + blr + + /* + * syscall fallback + */ +99: + li r0,__NR_clock_getres + sc + blr + .cfi_endproc +V_FUNCTION_END(__kernel_clock_getres) + + +/* + * This is the core of gettimeofday() & friends, it returns the xsec + * value in r3 & r4 and expects the datapage ptr (non clobbered) + * in r9. clobbers r0,r4,r5,r6,r7,r8. + * When returning, r8 contains the counter value that can be reused + * by the monotonic clock implementation + */ +__do_get_xsec: + .cfi_startproc + /* Check for update count & load values. We use the low + * order 32 bits of the update count + */ +#ifdef CONFIG_PPC64 +1: lwz r8,(CFG_TB_UPDATE_COUNT+4)(r9) +#else +1: lwz r8,(CFG_TB_UPDATE_COUNT)(r9) +#endif + andi. r0,r8,1 /* pending update ? loop */ + bne- 1b + xor r0,r8,r8 /* create dependency */ + add r9,r9,r0 + + /* Load orig stamp (offset to TB) */ + lwz r5,CFG_TB_ORIG_STAMP(r9) + lwz r6,(CFG_TB_ORIG_STAMP+4)(r9) + + /* Get a stable TB value */ +2: mftbu r3 + mftbl r4 + mftbu r0 + cmpl cr0,r3,r0 + bne- 2b + + /* Substract tb orig stamp. If the high part is non-zero, we jump to + * the slow path which call the syscall. + * If it's ok, then we have our 32 bits tb_ticks value in r7 + */ + subfc r7,r6,r4 + subfe. r0,r5,r3 + bne- 3f + + /* Load scale factor & do multiplication */ + lwz r5,CFG_TB_TO_XS(r9) /* load values */ + lwz r6,(CFG_TB_TO_XS+4)(r9) + mulhwu r4,r7,r5 + mulhwu r6,r7,r6 + mullw r0,r7,r5 + addc r6,r6,r0 + + /* At this point, we have the scaled xsec value in r4 + XER:CA + * we load & add the stamp since epoch + */ + lwz r5,CFG_STAMP_XSEC(r9) + lwz r6,(CFG_STAMP_XSEC+4)(r9) + adde r4,r4,r6 + addze r3,r5 + + /* We now have our result in r3,r4. We create a fake dependency + * on that result and re-check the counter + */ + or r6,r4,r3 + xor r0,r6,r6 + add r9,r9,r0 +#ifdef CONFIG_PPC64 + lwz r0,(CFG_TB_UPDATE_COUNT+4)(r9) +#else + lwz r0,(CFG_TB_UPDATE_COUNT)(r9) +#endif + cmpl cr0,r8,r0 /* check if updated */ + bne- 1b + + /* Warning ! The caller expects CR:EQ to be set to indicate a + * successful calculation (so it won't fallback to the syscall + * method). We have overriden that CR bit in the counter check, + * but fortunately, the loop exit condition _is_ CR:EQ set, so + * we can exit safely here. If you change this code, be careful + * of that side effect. + */ +3: blr + .cfi_endproc diff --git a/arch/powerpc/kernel/vdso32/note.S b/arch/powerpc/kernel/vdso32/note.S new file mode 100644 index 00000000000..d4b5be4f3d5 --- /dev/null +++ b/arch/powerpc/kernel/vdso32/note.S @@ -0,0 +1,25 @@ +/* + * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text. + * Here we can supply some information useful to userland. + */ + +#include <linux/uts.h> +#include <linux/version.h> + +#define ASM_ELF_NOTE_BEGIN(name, flags, vendor, type) \ + .section name, flags; \ + .balign 4; \ + .long 1f - 0f; /* name length */ \ + .long 3f - 2f; /* data length */ \ + .long type; /* note type */ \ +0: .asciz vendor; /* vendor name */ \ +1: .balign 4; \ +2: + +#define ASM_ELF_NOTE_END \ +3: .balign 4; /* pad out section */ \ + .previous + + ASM_ELF_NOTE_BEGIN(".note.kernel-version", "a", UTS_SYSNAME, 0) + .long LINUX_VERSION_CODE + ASM_ELF_NOTE_END diff --git a/arch/powerpc/kernel/vdso32/sigtramp.S b/arch/powerpc/kernel/vdso32/sigtramp.S new file mode 100644 index 00000000000..e0464278191 --- /dev/null +++ b/arch/powerpc/kernel/vdso32/sigtramp.S @@ -0,0 +1,300 @@ +/* + * Signal trampolines for 32 bits processes in a ppc64 kernel for + * use in the vDSO + * + * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org), IBM Corp. + * Copyright (C) 2004 Alan Modra (amodra@au.ibm.com)), IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include <linux/config.h> +#include <asm/processor.h> +#include <asm/ppc_asm.h> +#include <asm/unistd.h> +#include <asm/vdso.h> + + .text + +/* The nop here is a hack. The dwarf2 unwind routines subtract 1 from + the return address to get an address in the middle of the presumed + call instruction. Since we don't have a call here, we artifically + extend the range covered by the unwind info by adding a nop before + the real start. */ + nop +V_FUNCTION_BEGIN(__kernel_sigtramp32) +.Lsig_start = . - 4 + li r0,__NR_sigreturn + sc +.Lsig_end: +V_FUNCTION_END(__kernel_sigtramp32) + +.Lsigrt_start: + nop +V_FUNCTION_BEGIN(__kernel_sigtramp_rt32) + li r0,__NR_rt_sigreturn + sc +.Lsigrt_end: +V_FUNCTION_END(__kernel_sigtramp_rt32) + + .section .eh_frame,"a",@progbits + +/* Register r1 can be found at offset 4 of a pt_regs structure. + A pointer to the pt_regs is stored in memory at the old sp plus PTREGS. */ +#define cfa_save \ + .byte 0x0f; /* DW_CFA_def_cfa_expression */ \ + .uleb128 9f - 1f; /* length */ \ +1: \ + .byte 0x71; .sleb128 PTREGS; /* DW_OP_breg1 */ \ + .byte 0x06; /* DW_OP_deref */ \ + .byte 0x23; .uleb128 RSIZE; /* DW_OP_plus_uconst */ \ + .byte 0x06; /* DW_OP_deref */ \ +9: + +/* Register REGNO can be found at offset OFS of a pt_regs structure. + A pointer to the pt_regs is stored in memory at the old sp plus PTREGS. */ +#define rsave(regno, ofs) \ + .byte 0x10; /* DW_CFA_expression */ \ + .uleb128 regno; /* regno */ \ + .uleb128 9f - 1f; /* length */ \ +1: \ + .byte 0x71; .sleb128 PTREGS; /* DW_OP_breg1 */ \ + .byte 0x06; /* DW_OP_deref */ \ + .ifne ofs; \ + .byte 0x23; .uleb128 ofs; /* DW_OP_plus_uconst */ \ + .endif; \ +9: + +/* If msr bit 1<<25 is set, then VMX register REGNO is at offset REGNO*16 + of the VMX reg struct. The VMX reg struct is at offset VREGS of + the pt_regs struct. This macro is for REGNO == 0, and contains + 'subroutines' that the other macros jump to. */ +#define vsave_msr0(regno) \ + .byte 0x10; /* DW_CFA_expression */ \ + .uleb128 regno + 77; /* regno */ \ + .uleb128 9f - 1f; /* length */ \ +1: \ + .byte 0x30 + regno; /* DW_OP_lit0 */ \ +2: \ + .byte 0x40; /* DW_OP_lit16 */ \ + .byte 0x1e; /* DW_OP_mul */ \ +3: \ + .byte 0x71; .sleb128 PTREGS; /* DW_OP_breg1 */ \ + .byte 0x06; /* DW_OP_deref */ \ + .byte 0x12; /* DW_OP_dup */ \ + .byte 0x23; /* DW_OP_plus_uconst */ \ + .uleb128 33*RSIZE; /* msr offset */ \ + .byte 0x06; /* DW_OP_deref */ \ + .byte 0x0c; .long 1 << 25; /* DW_OP_const4u */ \ + .byte 0x1a; /* DW_OP_and */ \ + .byte 0x12; /* DW_OP_dup, ret 0 if bra taken */ \ + .byte 0x30; /* DW_OP_lit0 */ \ + .byte 0x29; /* DW_OP_eq */ \ + .byte 0x28; .short 0x7fff; /* DW_OP_bra to end */ \ + .byte 0x13; /* DW_OP_drop, pop the 0 */ \ + .byte 0x23; .uleb128 VREGS; /* DW_OP_plus_uconst */ \ + .byte 0x22; /* DW_OP_plus */ \ + .byte 0x2f; .short 0x7fff; /* DW_OP_skip to end */ \ +9: + +/* If msr bit 1<<25 is set, then VMX register REGNO is at offset REGNO*16 + of the VMX reg struct. REGNO is 1 thru 31. */ +#define vsave_msr1(regno) \ + .byte 0x10; /* DW_CFA_expression */ \ + .uleb128 regno + 77; /* regno */ \ + .uleb128 9f - 1f; /* length */ \ +1: \ + .byte 0x30 + regno; /* DW_OP_lit n */ \ + .byte 0x2f; .short 2b - 9f; /* DW_OP_skip */ \ +9: + +/* If msr bit 1<<25 is set, then VMX register REGNO is at offset OFS of + the VMX save block. */ +#define vsave_msr2(regno, ofs) \ + .byte 0x10; /* DW_CFA_expression */ \ + .uleb128 regno + 77; /* regno */ \ + .uleb128 9f - 1f; /* length */ \ +1: \ + .byte 0x0a; .short ofs; /* DW_OP_const2u */ \ + .byte 0x2f; .short 3b - 9f; /* DW_OP_skip */ \ +9: + +/* VMX register REGNO is at offset OFS of the VMX save area. */ +#define vsave(regno, ofs) \ + .byte 0x10; /* DW_CFA_expression */ \ + .uleb128 regno + 77; /* regno */ \ + .uleb128 9f - 1f; /* length */ \ +1: \ + .byte 0x71; .sleb128 PTREGS; /* DW_OP_breg1 */ \ + .byte 0x06; /* DW_OP_deref */ \ + .byte 0x23; .uleb128 VREGS; /* DW_OP_plus_uconst */ \ + .byte 0x23; .uleb128 ofs; /* DW_OP_plus_uconst */ \ +9: + +/* This is where the pt_regs pointer can be found on the stack. */ +#define PTREGS 64+28 + +/* Size of regs. */ +#define RSIZE 4 + +/* This is the offset of the VMX regs. */ +#define VREGS 48*RSIZE+34*8 + +/* Describe where general purpose regs are saved. */ +#define EH_FRAME_GEN \ + cfa_save; \ + rsave ( 0, 0*RSIZE); \ + rsave ( 2, 2*RSIZE); \ + rsave ( 3, 3*RSIZE); \ + rsave ( 4, 4*RSIZE); \ + rsave ( 5, 5*RSIZE); \ + rsave ( 6, 6*RSIZE); \ + rsave ( 7, 7*RSIZE); \ + rsave ( 8, 8*RSIZE); \ + rsave ( 9, 9*RSIZE); \ + rsave (10, 10*RSIZE); \ + rsave (11, 11*RSIZE); \ + rsave (12, 12*RSIZE); \ + rsave (13, 13*RSIZE); \ + rsave (14, 14*RSIZE); \ + rsave (15, 15*RSIZE); \ + rsave (16, 16*RSIZE); \ + rsave (17, 17*RSIZE); \ + rsave (18, 18*RSIZE); \ + rsave (19, 19*RSIZE); \ + rsave (20, 20*RSIZE); \ + rsave (21, 21*RSIZE); \ + rsave (22, 22*RSIZE); \ + rsave (23, 23*RSIZE); \ + rsave (24, 24*RSIZE); \ + rsave (25, 25*RSIZE); \ + rsave (26, 26*RSIZE); \ + rsave (27, 27*RSIZE); \ + rsave (28, 28*RSIZE); \ + rsave (29, 29*RSIZE); \ + rsave (30, 30*RSIZE); \ + rsave (31, 31*RSIZE); \ + rsave (67, 32*RSIZE); /* ap, used as temp for nip */ \ + rsave (65, 36*RSIZE); /* lr */ \ + rsave (70, 38*RSIZE) /* cr */ + +/* Describe where the FP regs are saved. */ +#define EH_FRAME_FP \ + rsave (32, 48*RSIZE + 0*8); \ + rsave (33, 48*RSIZE + 1*8); \ + rsave (34, 48*RSIZE + 2*8); \ + rsave (35, 48*RSIZE + 3*8); \ + rsave (36, 48*RSIZE + 4*8); \ + rsave (37, 48*RSIZE + 5*8); \ + rsave (38, 48*RSIZE + 6*8); \ + rsave (39, 48*RSIZE + 7*8); \ + rsave (40, 48*RSIZE + 8*8); \ + rsave (41, 48*RSIZE + 9*8); \ + rsave (42, 48*RSIZE + 10*8); \ + rsave (43, 48*RSIZE + 11*8); \ + rsave (44, 48*RSIZE + 12*8); \ + rsave (45, 48*RSIZE + 13*8); \ + rsave (46, 48*RSIZE + 14*8); \ + rsave (47, 48*RSIZE + 15*8); \ + rsave (48, 48*RSIZE + 16*8); \ + rsave (49, 48*RSIZE + 17*8); \ + rsave (50, 48*RSIZE + 18*8); \ + rsave (51, 48*RSIZE + 19*8); \ + rsave (52, 48*RSIZE + 20*8); \ + rsave (53, 48*RSIZE + 21*8); \ + rsave (54, 48*RSIZE + 22*8); \ + rsave (55, 48*RSIZE + 23*8); \ + rsave (56, 48*RSIZE + 24*8); \ + rsave (57, 48*RSIZE + 25*8); \ + rsave (58, 48*RSIZE + 26*8); \ + rsave (59, 48*RSIZE + 27*8); \ + rsave (60, 48*RSIZE + 28*8); \ + rsave (61, 48*RSIZE + 29*8); \ + rsave (62, 48*RSIZE + 30*8); \ + rsave (63, 48*RSIZE + 31*8) + +/* Describe where the VMX regs are saved. */ +#ifdef CONFIG_ALTIVEC +#define EH_FRAME_VMX \ + vsave_msr0 ( 0); \ + vsave_msr1 ( 1); \ + vsave_msr1 ( 2); \ + vsave_msr1 ( 3); \ + vsave_msr1 ( 4); \ + vsave_msr1 ( 5); \ + vsave_msr1 ( 6); \ + vsave_msr1 ( 7); \ + vsave_msr1 ( 8); \ + vsave_msr1 ( 9); \ + vsave_msr1 (10); \ + vsave_msr1 (11); \ + vsave_msr1 (12); \ + vsave_msr1 (13); \ + vsave_msr1 (14); \ + vsave_msr1 (15); \ + vsave_msr1 (16); \ + vsave_msr1 (17); \ + vsave_msr1 (18); \ + vsave_msr1 (19); \ + vsave_msr1 (20); \ + vsave_msr1 (21); \ + vsave_msr1 (22); \ + vsave_msr1 (23); \ + vsave_msr1 (24); \ + vsave_msr1 (25); \ + vsave_msr1 (26); \ + vsave_msr1 (27); \ + vsave_msr1 (28); \ + vsave_msr1 (29); \ + vsave_msr1 (30); \ + vsave_msr1 (31); \ + vsave_msr2 (33, 32*16+12); \ + vsave (32, 32*16) +#else +#define EH_FRAME_VMX +#endif + +.Lcie: + .long .Lcie_end - .Lcie_start +.Lcie_start: + .long 0 /* CIE ID */ + .byte 1 /* Version number */ + .string "zR" /* NUL-terminated augmentation string */ + .uleb128 4 /* Code alignment factor */ + .sleb128 -4 /* Data alignment factor */ + .byte 67 /* Return address register column, ap */ + .uleb128 1 /* Augmentation value length */ + .byte 0x1b /* DW_EH_PE_pcrel | DW_EH_PE_sdata4. */ + .byte 0x0c,1,0 /* DW_CFA_def_cfa: r1 ofs 0 */ + .balign 4 +.Lcie_end: + + .long .Lfde0_end - .Lfde0_start +.Lfde0_start: + .long .Lfde0_start - .Lcie /* CIE pointer. */ + .long .Lsig_start - . /* PC start, length */ + .long .Lsig_end - .Lsig_start + .uleb128 0 /* Augmentation */ + EH_FRAME_GEN + EH_FRAME_FP + EH_FRAME_VMX + .balign 4 +.Lfde0_end: + +/* We have a different stack layout for rt_sigreturn. */ +#undef PTREGS +#define PTREGS 64+16+128+20+28 + + .long .Lfde1_end - .Lfde1_start +.Lfde1_start: + .long .Lfde1_start - .Lcie /* CIE pointer. */ + .long .Lsigrt_start - . /* PC start, length */ + .long .Lsigrt_end - .Lsigrt_start + .uleb128 0 /* Augmentation */ + EH_FRAME_GEN + EH_FRAME_FP + EH_FRAME_VMX + .balign 4 +.Lfde1_end: diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S new file mode 100644 index 00000000000..f4bad720cb0 --- /dev/null +++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S @@ -0,0 +1,117 @@ + +/* + * This is the infamous ld script for the 32 bits vdso + * library + */ +#include <asm/vdso.h> + +/* Default link addresses for the vDSOs */ +OUTPUT_FORMAT("elf32-powerpc", "elf32-powerpc", "elf32-powerpc") +OUTPUT_ARCH(powerpc:common) +ENTRY(_start) + +SECTIONS +{ + . = VDSO32_LBASE + SIZEOF_HEADERS; + .hash : { *(.hash) } :text + .dynsym : { *(.dynsym) } + .dynstr : { *(.dynstr) } + .gnu.version : { *(.gnu.version) } + .gnu.version_d : { *(.gnu.version_d) } + .gnu.version_r : { *(.gnu.version_r) } + + .note : { *(.note.*) } :text :note + + . = ALIGN (16); + .text : + { + *(.text .stub .text.* .gnu.linkonce.t.*) + } + PROVIDE (__etext = .); + PROVIDE (_etext = .); + PROVIDE (etext = .); + + /* Other stuff is appended to the text segment: */ + .rodata : { *(.rodata .rodata.* .gnu.linkonce.r.*) } + .rodata1 : { *(.rodata1) } + + .eh_frame_hdr : { *(.eh_frame_hdr) } :text :eh_frame_hdr + .eh_frame : { KEEP (*(.eh_frame)) } :text + .gcc_except_table : { *(.gcc_except_table) } + .fixup : { *(.fixup) } + + .dynamic : { *(.dynamic) } :text :dynamic + .got : { *(.got) } + .plt : { *(.plt) } + + _end = .; + __end = .; + PROVIDE (end = .); + + + /* Stabs debugging sections are here too + */ + .stab 0 : { *(.stab) } + .stabstr 0 : { *(.stabstr) } + .stab.excl 0 : { *(.stab.excl) } + .stab.exclstr 0 : { *(.stab.exclstr) } + .stab.index 0 : { *(.stab.index) } + .stab.indexstr 0 : { *(.stab.indexstr) } + .comment 0 : { *(.comment) } + .debug 0 : { *(.debug) } + .line 0 : { *(.line) } + + .debug_srcinfo 0 : { *(.debug_srcinfo) } + .debug_sfnames 0 : { *(.debug_sfnames) } + + .debug_aranges 0 : { *(.debug_aranges) } + .debug_pubnames 0 : { *(.debug_pubnames) } + + .debug_info 0 : { *(.debug_info .gnu.linkonce.wi.*) } + .debug_abbrev 0 : { *(.debug_abbrev) } + .debug_line 0 : { *(.debug_line) } + .debug_frame 0 : { *(.debug_frame) } + .debug_str 0 : { *(.debug_str) } + .debug_loc 0 : { *(.debug_loc) } + .debug_macinfo 0 : { *(.debug_macinfo) } + + .debug_weaknames 0 : { *(.debug_weaknames) } + .debug_funcnames 0 : { *(.debug_funcnames) } + .debug_typenames 0 : { *(.debug_typenames) } + .debug_varnames 0 : { *(.debug_varnames) } + + /DISCARD/ : { *(.note.GNU-stack) } + /DISCARD/ : { *(.data .data.* .gnu.linkonce.d.* .sdata*) } + /DISCARD/ : { *(.bss .sbss .dynbss .dynsbss) } +} + + +PHDRS +{ + text PT_LOAD FILEHDR PHDRS FLAGS(5); /* PF_R|PF_X */ + note PT_NOTE FLAGS(4); /* PF_R */ + dynamic PT_DYNAMIC FLAGS(4); /* PF_R */ + eh_frame_hdr 0x6474e550; /* PT_GNU_EH_FRAME, but ld doesn't match the name */ +} + + +/* + * This controls what symbols we export from the DSO. + */ +VERSION +{ + VDSO_VERSION_STRING { + global: + __kernel_datapage_offset; /* Has to be there for the kernel to find */ + __kernel_get_syscall_map; + __kernel_gettimeofday; + __kernel_clock_gettime; + __kernel_clock_getres; + __kernel_get_tbfreq; + __kernel_sync_dicache; + __kernel_sync_dicache_p5; + __kernel_sigtramp32; + __kernel_sigtramp_rt32; + local: *; + }; +} diff --git a/arch/powerpc/kernel/vdso32/vdso32_wrapper.S b/arch/powerpc/kernel/vdso32/vdso32_wrapper.S new file mode 100644 index 00000000000..556f0caa5d8 --- /dev/null +++ b/arch/powerpc/kernel/vdso32/vdso32_wrapper.S @@ -0,0 +1,13 @@ +#include <linux/init.h> +#include <asm/page.h> + + .section ".data.page_aligned" + + .globl vdso32_start, vdso32_end + .balign PAGE_SIZE +vdso32_start: + .incbin "arch/powerpc/kernel/vdso32/vdso32.so" + .balign PAGE_SIZE +vdso32_end: + + .previous diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile new file mode 100644 index 00000000000..ab39988452c --- /dev/null +++ b/arch/powerpc/kernel/vdso64/Makefile @@ -0,0 +1,35 @@ +# List of files in the vdso, has to be asm only for now + +obj-vdso64 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o + +# Build rules + +targets := $(obj-vdso64) vdso64.so +obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64)) + +EXTRA_CFLAGS := -shared -s -fno-common -fno-builtin +EXTRA_CFLAGS += -nostdlib -Wl,-soname=linux-vdso64.so.1 +EXTRA_AFLAGS := -D__VDSO64__ -s + +obj-y += vdso64_wrapper.o +extra-y += vdso64.lds +CPPFLAGS_vdso64.lds += -P -C -U$(ARCH) + +# Force dependency (incbin is bad) +$(obj)/vdso64_wrapper.o : $(obj)/vdso64.so + +# link rule for the .so file, .lds has to be first +$(obj)/vdso64.so: $(src)/vdso64.lds $(obj-vdso64) + $(call if_changed,vdso64ld) + +# assembly rules for the .S files +$(obj-vdso64): %.o: %.S + $(call if_changed_dep,vdso64as) + +# actual build commands +quiet_cmd_vdso64ld = VDSO64L $@ + cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $^ -o $@ +quiet_cmd_vdso64as = VDSO64A $@ + cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $< + + diff --git a/arch/powerpc/kernel/vdso64/cacheflush.S b/arch/powerpc/kernel/vdso64/cacheflush.S new file mode 100644 index 00000000000..d4a0ad28d53 --- /dev/null +++ b/arch/powerpc/kernel/vdso64/cacheflush.S @@ -0,0 +1,66 @@ +/* + * vDSO provided cache flush routines + * + * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org), + * IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include <linux/config.h> +#include <asm/processor.h> +#include <asm/ppc_asm.h> +#include <asm/vdso.h> +#include <asm/asm-offsets.h> + + .text + +/* + * Default "generic" version of __kernel_sync_dicache. + * + * void __kernel_sync_dicache(unsigned long start, unsigned long end) + * + * Flushes the data cache & invalidate the instruction cache for the + * provided range [start, end[ + * + * Note: all CPUs supported by this kernel have a 128 bytes cache + * line size so we don't have to peek that info from the datapage + */ +V_FUNCTION_BEGIN(__kernel_sync_dicache) + .cfi_startproc + li r5,127 + andc r6,r3,r5 /* round low to line bdy */ + subf r8,r6,r4 /* compute length */ + add r8,r8,r5 /* ensure we get enough */ + srwi. r8,r8,7 /* compute line count */ + beqlr /* nothing to do? */ + mtctr r8 + mr r3,r6 +1: dcbst 0,r3 + addi r3,r3,128 + bdnz 1b + sync + mtctr r8 +1: icbi 0,r6 + addi r6,r6,128 + bdnz 1b + isync + li r3,0 + blr + .cfi_endproc +V_FUNCTION_END(__kernel_sync_dicache) + + +/* + * POWER5 version of __kernel_sync_dicache + */ +V_FUNCTION_BEGIN(__kernel_sync_dicache_p5) + .cfi_startproc + sync + isync + li r3,0 + blr + .cfi_endproc +V_FUNCTION_END(__kernel_sync_dicache_p5) diff --git a/arch/powerpc/kernel/vdso64/datapage.S b/arch/powerpc/kernel/vdso64/datapage.S new file mode 100644 index 00000000000..e67eda0f8cd --- /dev/null +++ b/arch/powerpc/kernel/vdso64/datapage.S @@ -0,0 +1,84 @@ +/* + * Access to the shared data page by the vDSO & syscall map + * + * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org), IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/config.h> +#include <asm/processor.h> +#include <asm/ppc_asm.h> +#include <asm/asm-offsets.h> +#include <asm/unistd.h> +#include <asm/vdso.h> + + .text +V_FUNCTION_BEGIN(__get_datapage) + .cfi_startproc + /* We don't want that exposed or overridable as we want other objects + * to be able to bl directly to here + */ + .protected __get_datapage + .hidden __get_datapage + + mflr r0 + .cfi_register lr,r0 + + bcl 20,31,1f + .global __kernel_datapage_offset; +__kernel_datapage_offset: + .long 0 +1: + mflr r3 + mtlr r0 + lwz r0,0(r3) + add r3,r0,r3 + blr + .cfi_endproc +V_FUNCTION_END(__get_datapage) + +/* + * void *__kernel_get_syscall_map(unsigned int *syscall_count) ; + * + * returns a pointer to the syscall map. the map is agnostic to the + * size of "long", unlike kernel bitops, it stores bits from top to + * bottom so that memory actually contains a linear bitmap + * check for syscall N by testing bit (0x80000000 >> (N & 0x1f)) of + * 32 bits int at N >> 5. + */ +V_FUNCTION_BEGIN(__kernel_get_syscall_map) + .cfi_startproc + mflr r12 + .cfi_register lr,r12 + + mr r4,r3 + bl V_LOCAL_FUNC(__get_datapage) + mtlr r12 + addi r3,r3,CFG_SYSCALL_MAP64 + cmpli cr0,r4,0 + beqlr + li r0,__NR_syscalls + stw r0,0(r4) + blr + .cfi_endproc +V_FUNCTION_END(__kernel_get_syscall_map) + + +/* + * void unsigned long __kernel_get_tbfreq(void); + * + * returns the timebase frequency in HZ + */ +V_FUNCTION_BEGIN(__kernel_get_tbfreq) + .cfi_startproc + mflr r12 + .cfi_register lr,r12 + bl V_LOCAL_FUNC(__get_datapage) + ld r3,CFG_TB_TICKS_PER_SEC(r3) + mtlr r12 + .cfi_endproc +V_FUNCTION_END(__kernel_get_tbfreq) diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S new file mode 100644 index 00000000000..d371c02a8c0 --- /dev/null +++ b/arch/powerpc/kernel/vdso64/gettimeofday.S @@ -0,0 +1,242 @@ +/* + * Userland implementation of gettimeofday() for 64 bits processes in a + * ppc64 kernel for use in the vDSO + * + * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org), + * IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include <linux/config.h> +#include <asm/processor.h> +#include <asm/ppc_asm.h> +#include <asm/vdso.h> +#include <asm/asm-offsets.h> +#include <asm/unistd.h> + + .text +/* + * Exact prototype of gettimeofday + * + * int __kernel_gettimeofday(struct timeval *tv, struct timezone *tz); + * + */ +V_FUNCTION_BEGIN(__kernel_gettimeofday) + .cfi_startproc + mflr r12 + .cfi_register lr,r12 + + mr r11,r3 /* r11 holds tv */ + mr r10,r4 /* r10 holds tz */ + bl V_LOCAL_FUNC(__get_datapage) /* get data page */ + bl V_LOCAL_FUNC(__do_get_xsec) /* get xsec from tb & kernel */ + lis r7,15 /* r7 = 1000000 = USEC_PER_SEC */ + ori r7,r7,16960 + rldicl r5,r4,44,20 /* r5 = sec = xsec / XSEC_PER_SEC */ + rldicr r6,r5,20,43 /* r6 = sec * XSEC_PER_SEC */ + std r5,TVAL64_TV_SEC(r11) /* store sec in tv */ + subf r0,r6,r4 /* r0 = xsec = (xsec - r6) */ + mulld r0,r0,r7 /* usec = (xsec * USEC_PER_SEC) / + * XSEC_PER_SEC + */ + rldicl r0,r0,44,20 + cmpldi cr0,r10,0 /* check if tz is NULL */ + std r0,TVAL64_TV_USEC(r11) /* store usec in tv */ + beq 1f + lwz r4,CFG_TZ_MINUTEWEST(r3)/* fill tz */ + lwz r5,CFG_TZ_DSTTIME(r3) + stw r4,TZONE_TZ_MINWEST(r10) + stw r5,TZONE_TZ_DSTTIME(r10) +1: mtlr r12 + li r3,0 /* always success */ + blr + .cfi_endproc +V_FUNCTION_END(__kernel_gettimeofday) + + +/* + * Exact prototype of clock_gettime() + * + * int __kernel_clock_gettime(clockid_t clock_id, struct timespec *tp); + * + */ +V_FUNCTION_BEGIN(__kernel_clock_gettime) + .cfi_startproc + /* Check for supported clock IDs */ + cmpwi cr0,r3,CLOCK_REALTIME + cmpwi cr1,r3,CLOCK_MONOTONIC + cror cr0,cr0,cr1 + bne cr0,99f + + mflr r12 /* r12 saves lr */ + .cfi_register lr,r12 + mr r10,r3 /* r10 saves id */ + mr r11,r4 /* r11 saves tp */ + bl V_LOCAL_FUNC(__get_datapage) /* get data page */ + beq cr1,50f /* if monotonic -> jump there */ + + /* + * CLOCK_REALTIME + */ + + bl V_LOCAL_FUNC(__do_get_xsec) /* get xsec from tb & kernel */ + + lis r7,0x3b9a /* r7 = 1000000000 = NSEC_PER_SEC */ + ori r7,r7,0xca00 + rldicl r5,r4,44,20 /* r5 = sec = xsec / XSEC_PER_SEC */ + rldicr r6,r5,20,43 /* r6 = sec * XSEC_PER_SEC */ + std r5,TSPC64_TV_SEC(r11) /* store sec in tv */ + subf r0,r6,r4 /* r0 = xsec = (xsec - r6) */ + mulld r0,r0,r7 /* nsec = (xsec * NSEC_PER_SEC) / + * XSEC_PER_SEC + */ + rldicl r0,r0,44,20 + std r0,TSPC64_TV_NSEC(r11) /* store nsec in tp */ + + mtlr r12 + li r3,0 + blr + + /* + * CLOCK_MONOTONIC + */ + +50: bl V_LOCAL_FUNC(__do_get_xsec) /* get xsec from tb & kernel */ + + lis r7,0x3b9a /* r7 = 1000000000 = NSEC_PER_SEC */ + ori r7,r7,0xca00 + rldicl r5,r4,44,20 /* r5 = sec = xsec / XSEC_PER_SEC */ + rldicr r6,r5,20,43 /* r6 = sec * XSEC_PER_SEC */ + subf r0,r6,r4 /* r0 = xsec = (xsec - r6) */ + mulld r0,r0,r7 /* nsec = (xsec * NSEC_PER_SEC) / + * XSEC_PER_SEC + */ + rldicl r6,r0,44,20 + + /* now we must fixup using wall to monotonic. We need to snapshot + * that value and do the counter trick again. Fortunately, we still + * have the counter value in r8 that was returned by __do_get_xsec. + * At this point, r5,r6 contain our sec/nsec values. + * can be used + */ + + lwz r4,WTOM_CLOCK_SEC(r9) + lwz r7,WTOM_CLOCK_NSEC(r9) + + /* We now have our result in r4,r7. We create a fake dependency + * on that result and re-check the counter + */ + or r9,r4,r7 + xor r0,r9,r9 + add r3,r3,r0 + ld r0,CFG_TB_UPDATE_COUNT(r3) + cmpld cr0,r0,r8 /* check if updated */ + bne- 50b + + /* Calculate and store result. Note that this mimmics the C code, + * which may cause funny results if nsec goes negative... is that + * possible at all ? + */ + add r4,r4,r5 + add r7,r7,r6 + lis r9,NSEC_PER_SEC@h + ori r9,r9,NSEC_PER_SEC@l + cmpli cr0,r7,r9 + blt 1f + subf r7,r9,r7 + addi r4,r4,1 +1: std r4,TSPC64_TV_SEC(r11) + std r7,TSPC64_TV_NSEC(r11) + + mtlr r12 + li r3,0 + blr + + /* + * syscall fallback + */ +98: + mtlr r12 + mr r3,r10 + mr r4,r11 +99: + li r0,__NR_clock_gettime + sc + blr + .cfi_endproc +V_FUNCTION_END(__kernel_clock_gettime) + + +/* + * Exact prototype of clock_getres() + * + * int __kernel_clock_getres(clockid_t clock_id, struct timespec *res); + * + */ +V_FUNCTION_BEGIN(__kernel_clock_getres) + .cfi_startproc + /* Check for supported clock IDs */ + cmpwi cr0,r3,CLOCK_REALTIME + cmpwi cr1,r3,CLOCK_MONOTONIC + cror cr0,cr0,cr1 + bne cr0,99f + + li r3,0 + cmpli cr0,r4,0 + beqlr + lis r5,CLOCK_REALTIME_RES@h + ori r5,r5,CLOCK_REALTIME_RES@l + std r3,TSPC64_TV_SEC(r4) + std r5,TSPC64_TV_NSEC(r4) + blr + + /* + * syscall fallback + */ +99: + li r0,__NR_clock_getres + sc + blr + .cfi_endproc +V_FUNCTION_END(__kernel_clock_getres) + + +/* + * This is the core of gettimeofday(), it returns the xsec + * value in r4 and expects the datapage ptr (non clobbered) + * in r3. clobbers r0,r4,r5,r6,r7,r8 + * When returning, r8 contains the counter value that can be reused + */ +V_FUNCTION_BEGIN(__do_get_xsec) + .cfi_startproc + /* check for update count & load values */ +1: ld r8,CFG_TB_UPDATE_COUNT(r3) + andi. r0,r4,1 /* pending update ? loop */ + bne- 1b + xor r0,r4,r4 /* create dependency */ + add r3,r3,r0 + + /* Get TB & offset it */ + mftb r7 + ld r9,CFG_TB_ORIG_STAMP(r3) + subf r7,r9,r7 + + /* Scale result */ + ld r5,CFG_TB_TO_XS(r3) + mulhdu r7,r7,r5 + + /* Add stamp since epoch */ + ld r6,CFG_STAMP_XSEC(r3) + add r4,r6,r7 + + xor r0,r4,r4 + add r3,r3,r0 + ld r0,CFG_TB_UPDATE_COUNT(r3) + cmpld cr0,r0,r8 /* check if updated */ + bne- 1b + blr + .cfi_endproc +V_FUNCTION_END(__do_get_xsec) diff --git a/arch/powerpc/kernel/vdso64/note.S b/arch/powerpc/kernel/vdso64/note.S new file mode 100644 index 00000000000..dc2a509f7e8 --- /dev/null +++ b/arch/powerpc/kernel/vdso64/note.S @@ -0,0 +1 @@ +#include "../vdso32/note.S" diff --git a/arch/powerpc/kernel/vdso64/sigtramp.S b/arch/powerpc/kernel/vdso64/sigtramp.S new file mode 100644 index 00000000000..31b604ab56d --- /dev/null +++ b/arch/powerpc/kernel/vdso64/sigtramp.S @@ -0,0 +1,295 @@ +/* + * Signal trampoline for 64 bits processes in a ppc64 kernel for + * use in the vDSO + * + * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org), IBM Corp. + * Copyright (C) 2004 Alan Modra (amodra@au.ibm.com)), IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include <linux/config.h> +#include <asm/processor.h> +#include <asm/ppc_asm.h> +#include <asm/unistd.h> +#include <asm/vdso.h> +#include <asm/ptrace.h> /* XXX for __SIGNAL_FRAMESIZE */ + + .text + +/* The nop here is a hack. The dwarf2 unwind routines subtract 1 from + the return address to get an address in the middle of the presumed + call instruction. Since we don't have a call here, we artifically + extend the range covered by the unwind info by padding before the + real start. */ + nop + .balign 8 +V_FUNCTION_BEGIN(__kernel_sigtramp_rt64) +.Lsigrt_start = . - 4 + addi r1, r1, __SIGNAL_FRAMESIZE + li r0,__NR_rt_sigreturn + sc +.Lsigrt_end: +V_FUNCTION_END(__kernel_sigtramp_rt64) +/* The ".balign 8" above and the following zeros mimic the old stack + trampoline layout. The last magic value is the ucontext pointer, + chosen in such a way that older libgcc unwind code returns a zero + for a sigcontext pointer. */ + .long 0,0,0 + .quad 0,-21*8 + +/* Register r1 can be found at offset 8 of a pt_regs structure. + A pointer to the pt_regs is stored in memory at the old sp plus PTREGS. */ +#define cfa_save \ + .byte 0x0f; /* DW_CFA_def_cfa_expression */ \ + .uleb128 9f - 1f; /* length */ \ +1: \ + .byte 0x71; .sleb128 PTREGS; /* DW_OP_breg1 */ \ + .byte 0x06; /* DW_OP_deref */ \ + .byte 0x23; .uleb128 RSIZE; /* DW_OP_plus_uconst */ \ + .byte 0x06; /* DW_OP_deref */ \ +9: + +/* Register REGNO can be found at offset OFS of a pt_regs structure. + A pointer to the pt_regs is stored in memory at the old sp plus PTREGS. */ +#define rsave(regno, ofs) \ + .byte 0x10; /* DW_CFA_expression */ \ + .uleb128 regno; /* regno */ \ + .uleb128 9f - 1f; /* length */ \ +1: \ + .byte 0x71; .sleb128 PTREGS; /* DW_OP_breg1 */ \ + .byte 0x06; /* DW_OP_deref */ \ + .ifne ofs; \ + .byte 0x23; .uleb128 ofs; /* DW_OP_plus_uconst */ \ + .endif; \ +9: + +/* If msr bit 1<<25 is set, then VMX register REGNO is at offset REGNO*16 + of the VMX reg struct. A pointer to the VMX reg struct is at VREGS in + the pt_regs struct. This macro is for REGNO == 0, and contains + 'subroutines' that the other macros jump to. */ +#define vsave_msr0(regno) \ + .byte 0x10; /* DW_CFA_expression */ \ + .uleb128 regno + 77; /* regno */ \ + .uleb128 9f - 1f; /* length */ \ +1: \ + .byte 0x30 + regno; /* DW_OP_lit0 */ \ +2: \ + .byte 0x40; /* DW_OP_lit16 */ \ + .byte 0x1e; /* DW_OP_mul */ \ +3: \ + .byte 0x71; .sleb128 PTREGS; /* DW_OP_breg1 */ \ + .byte 0x06; /* DW_OP_deref */ \ + .byte 0x12; /* DW_OP_dup */ \ + .byte 0x23; /* DW_OP_plus_uconst */ \ + .uleb128 33*RSIZE; /* msr offset */ \ + .byte 0x06; /* DW_OP_deref */ \ + .byte 0x0c; .long 1 << 25; /* DW_OP_const4u */ \ + .byte 0x1a; /* DW_OP_and */ \ + .byte 0x12; /* DW_OP_dup, ret 0 if bra taken */ \ + .byte 0x30; /* DW_OP_lit0 */ \ + .byte 0x29; /* DW_OP_eq */ \ + .byte 0x28; .short 0x7fff; /* DW_OP_bra to end */ \ + .byte 0x13; /* DW_OP_drop, pop the 0 */ \ + .byte 0x23; .uleb128 VREGS; /* DW_OP_plus_uconst */ \ + .byte 0x06; /* DW_OP_deref */ \ + .byte 0x22; /* DW_OP_plus */ \ + .byte 0x2f; .short 0x7fff; /* DW_OP_skip to end */ \ +9: + +/* If msr bit 1<<25 is set, then VMX register REGNO is at offset REGNO*16 + of the VMX reg struct. REGNO is 1 thru 31. */ +#define vsave_msr1(regno) \ + .byte 0x10; /* DW_CFA_expression */ \ + .uleb128 regno + 77; /* regno */ \ + .uleb128 9f - 1f; /* length */ \ +1: \ + .byte 0x30 + regno; /* DW_OP_lit n */ \ + .byte 0x2f; .short 2b - 9f; /* DW_OP_skip */ \ +9: + +/* If msr bit 1<<25 is set, then VMX register REGNO is at offset OFS of + the VMX save block. */ +#define vsave_msr2(regno, ofs) \ + .byte 0x10; /* DW_CFA_expression */ \ + .uleb128 regno + 77; /* regno */ \ + .uleb128 9f - 1f; /* length */ \ +1: \ + .byte 0x0a; .short ofs; /* DW_OP_const2u */ \ + .byte 0x2f; .short 3b - 9f; /* DW_OP_skip */ \ +9: + +/* VMX register REGNO is at offset OFS of the VMX save area. */ +#define vsave(regno, ofs) \ + .byte 0x10; /* DW_CFA_expression */ \ + .uleb128 regno + 77; /* regno */ \ + .uleb128 9f - 1f; /* length */ \ +1: \ + .byte 0x71; .sleb128 PTREGS; /* DW_OP_breg1 */ \ + .byte 0x06; /* DW_OP_deref */ \ + .byte 0x23; .uleb128 VREGS; /* DW_OP_plus_uconst */ \ + .byte 0x06; /* DW_OP_deref */ \ + .byte 0x23; .uleb128 ofs; /* DW_OP_plus_uconst */ \ +9: + +/* This is where the pt_regs pointer can be found on the stack. */ +#define PTREGS 128+168+56 + +/* Size of regs. */ +#define RSIZE 8 + +/* This is the offset of the VMX reg pointer. */ +#define VREGS 48*RSIZE+33*8 + +/* Describe where general purpose regs are saved. */ +#define EH_FRAME_GEN \ + cfa_save; \ + rsave ( 0, 0*RSIZE); \ + rsave ( 2, 2*RSIZE); \ + rsave ( 3, 3*RSIZE); \ + rsave ( 4, 4*RSIZE); \ + rsave ( 5, 5*RSIZE); \ + rsave ( 6, 6*RSIZE); \ + rsave ( 7, 7*RSIZE); \ + rsave ( 8, 8*RSIZE); \ + rsave ( 9, 9*RSIZE); \ + rsave (10, 10*RSIZE); \ + rsave (11, 11*RSIZE); \ + rsave (12, 12*RSIZE); \ + rsave (13, 13*RSIZE); \ + rsave (14, 14*RSIZE); \ + rsave (15, 15*RSIZE); \ + rsave (16, 16*RSIZE); \ + rsave (17, 17*RSIZE); \ + rsave (18, 18*RSIZE); \ + rsave (19, 19*RSIZE); \ + rsave (20, 20*RSIZE); \ + rsave (21, 21*RSIZE); \ + rsave (22, 22*RSIZE); \ + rsave (23, 23*RSIZE); \ + rsave (24, 24*RSIZE); \ + rsave (25, 25*RSIZE); \ + rsave (26, 26*RSIZE); \ + rsave (27, 27*RSIZE); \ + rsave (28, 28*RSIZE); \ + rsave (29, 29*RSIZE); \ + rsave (30, 30*RSIZE); \ + rsave (31, 31*RSIZE); \ + rsave (67, 32*RSIZE); /* ap, used as temp for nip */ \ + rsave (65, 36*RSIZE); /* lr */ \ + rsave (70, 38*RSIZE) /* cr */ + +/* Describe where the FP regs are saved. */ +#define EH_FRAME_FP \ + rsave (32, 48*RSIZE + 0*8); \ + rsave (33, 48*RSIZE + 1*8); \ + rsave (34, 48*RSIZE + 2*8); \ + rsave (35, 48*RSIZE + 3*8); \ + rsave (36, 48*RSIZE + 4*8); \ + rsave (37, 48*RSIZE + 5*8); \ + rsave (38, 48*RSIZE + 6*8); \ + rsave (39, 48*RSIZE + 7*8); \ + rsave (40, 48*RSIZE + 8*8); \ + rsave (41, 48*RSIZE + 9*8); \ + rsave (42, 48*RSIZE + 10*8); \ + rsave (43, 48*RSIZE + 11*8); \ + rsave (44, 48*RSIZE + 12*8); \ + rsave (45, 48*RSIZE + 13*8); \ + rsave (46, 48*RSIZE + 14*8); \ + rsave (47, 48*RSIZE + 15*8); \ + rsave (48, 48*RSIZE + 16*8); \ + rsave (49, 48*RSIZE + 17*8); \ + rsave (50, 48*RSIZE + 18*8); \ + rsave (51, 48*RSIZE + 19*8); \ + rsave (52, 48*RSIZE + 20*8); \ + rsave (53, 48*RSIZE + 21*8); \ + rsave (54, 48*RSIZE + 22*8); \ + rsave (55, 48*RSIZE + 23*8); \ + rsave (56, 48*RSIZE + 24*8); \ + rsave (57, 48*RSIZE + 25*8); \ + rsave (58, 48*RSIZE + 26*8); \ + rsave (59, 48*RSIZE + 27*8); \ + rsave (60, 48*RSIZE + 28*8); \ + rsave (61, 48*RSIZE + 29*8); \ + rsave (62, 48*RSIZE + 30*8); \ + rsave (63, 48*RSIZE + 31*8) + +/* Describe where the VMX regs are saved. */ +#ifdef CONFIG_ALTIVEC +#define EH_FRAME_VMX \ + vsave_msr0 ( 0); \ + vsave_msr1 ( 1); \ + vsave_msr1 ( 2); \ + vsave_msr1 ( 3); \ + vsave_msr1 ( 4); \ + vsave_msr1 ( 5); \ + vsave_msr1 ( 6); \ + vsave_msr1 ( 7); \ + vsave_msr1 ( 8); \ + vsave_msr1 ( 9); \ + vsave_msr1 (10); \ + vsave_msr1 (11); \ + vsave_msr1 (12); \ + vsave_msr1 (13); \ + vsave_msr1 (14); \ + vsave_msr1 (15); \ + vsave_msr1 (16); \ + vsave_msr1 (17); \ + vsave_msr1 (18); \ + vsave_msr1 (19); \ + vsave_msr1 (20); \ + vsave_msr1 (21); \ + vsave_msr1 (22); \ + vsave_msr1 (23); \ + vsave_msr1 (24); \ + vsave_msr1 (25); \ + vsave_msr1 (26); \ + vsave_msr1 (27); \ + vsave_msr1 (28); \ + vsave_msr1 (29); \ + vsave_msr1 (30); \ + vsave_msr1 (31); \ + vsave_msr2 (33, 32*16+12); \ + vsave (32, 33*16) +#else +#define EH_FRAME_VMX +#endif + + .section .eh_frame,"a",@progbits +.Lcie: + .long .Lcie_end - .Lcie_start +.Lcie_start: + .long 0 /* CIE ID */ + .byte 1 /* Version number */ + .string "zR" /* NUL-terminated augmentation string */ + .uleb128 4 /* Code alignment factor */ + .sleb128 -8 /* Data alignment factor */ + .byte 67 /* Return address register column, ap */ + .uleb128 1 /* Augmentation value length */ + .byte 0x14 /* DW_EH_PE_pcrel | DW_EH_PE_udata8. */ + .byte 0x0c,1,0 /* DW_CFA_def_cfa: r1 ofs 0 */ + .balign 8 +.Lcie_end: + + .long .Lfde0_end - .Lfde0_start +.Lfde0_start: + .long .Lfde0_start - .Lcie /* CIE pointer. */ + .quad .Lsigrt_start - . /* PC start, length */ + .quad .Lsigrt_end - .Lsigrt_start + .uleb128 0 /* Augmentation */ + EH_FRAME_GEN + EH_FRAME_FP + EH_FRAME_VMX +# Do we really need to describe the frame at this point? ie. will +# we ever have some call chain that returns somewhere past the addi? +# I don't think so, since gcc doesn't support async signals. +# .byte 0x41 /* DW_CFA_advance_loc 1*4 */ +#undef PTREGS +#define PTREGS 168+56 +# EH_FRAME_GEN +# EH_FRAME_FP +# EH_FRAME_VMX + .balign 8 +.Lfde0_end: diff --git a/arch/powerpc/kernel/vdso64/vdso64.lds.S b/arch/powerpc/kernel/vdso64/vdso64.lds.S new file mode 100644 index 00000000000..4bdf224464a --- /dev/null +++ b/arch/powerpc/kernel/vdso64/vdso64.lds.S @@ -0,0 +1,116 @@ +/* + * This is the infamous ld script for the 64 bits vdso + * library + */ +#include <asm/vdso.h> + +OUTPUT_FORMAT("elf64-powerpc", "elf64-powerpc", "elf64-powerpc") +OUTPUT_ARCH(powerpc:common64) +ENTRY(_start) + +SECTIONS +{ + . = VDSO64_LBASE + SIZEOF_HEADERS; + .hash : { *(.hash) } :text + .dynsym : { *(.dynsym) } + .dynstr : { *(.dynstr) } + .gnu.version : { *(.gnu.version) } + .gnu.version_d : { *(.gnu.version_d) } + .gnu.version_r : { *(.gnu.version_r) } + + .note : { *(.note.*) } :text :note + + . = ALIGN (16); + .text : + { + *(.text .stub .text.* .gnu.linkonce.t.*) + *(.sfpr .glink) + } :text + PROVIDE (__etext = .); + PROVIDE (_etext = .); + PROVIDE (etext = .); + + /* Other stuff is appended to the text segment: */ + .rodata : { *(.rodata .rodata.* .gnu.linkonce.r.*) } + .rodata1 : { *(.rodata1) } + .eh_frame_hdr : { *(.eh_frame_hdr) } :text :eh_frame_hdr + .eh_frame : { KEEP (*(.eh_frame)) } :text + .gcc_except_table : { *(.gcc_except_table) } + + .opd ALIGN(8) : { KEEP (*(.opd)) } + .got ALIGN(8) : { *(.got .toc) } + .rela.dyn ALIGN(8) : { *(.rela.dyn) } + + .dynamic : { *(.dynamic) } :text :dynamic + + _end = .; + PROVIDE (end = .); + + /* Stabs debugging sections are here too + */ + .stab 0 : { *(.stab) } + .stabstr 0 : { *(.stabstr) } + .stab.excl 0 : { *(.stab.excl) } + .stab.exclstr 0 : { *(.stab.exclstr) } + .stab.index 0 : { *(.stab.index) } + .stab.indexstr 0 : { *(.stab.indexstr) } + .comment 0 : { *(.comment) } + /* DWARF debug sectio/ns. + Symbols in the DWARF debugging sections are relative to the beginning + of the section so we begin them at 0. */ + /* DWARF 1 */ + .debug 0 : { *(.debug) } + .line 0 : { *(.line) } + /* GNU DWARF 1 extensions */ + .debug_srcinfo 0 : { *(.debug_srcinfo) } + .debug_sfnames 0 : { *(.debug_sfnames) } + /* DWARF 1.1 and DWARF 2 */ + .debug_aranges 0 : { *(.debug_aranges) } + .debug_pubnames 0 : { *(.debug_pubnames) } + /* DWARF 2 */ + .debug_info 0 : { *(.debug_info .gnu.linkonce.wi.*) } + .debug_abbrev 0 : { *(.debug_abbrev) } + .debug_line 0 : { *(.debug_line) } + .debug_frame 0 : { *(.debug_frame) } + .debug_str 0 : { *(.debug_str) } + .debug_loc 0 : { *(.debug_loc) } + .debug_macinfo 0 : { *(.debug_macinfo) } + /* SGI/MIPS DWARF 2 extensions */ + .debug_weaknames 0 : { *(.debug_weaknames) } + .debug_funcnames 0 : { *(.debug_funcnames) } + .debug_typenames 0 : { *(.debug_typenames) } + .debug_varnames 0 : { *(.debug_varnames) } + + /DISCARD/ : { *(.note.GNU-stack) } + /DISCARD/ : { *(.branch_lt) } + /DISCARD/ : { *(.data .data.* .gnu.linkonce.d.*) } + /DISCARD/ : { *(.bss .sbss .dynbss .dynsbss) } +} + +PHDRS +{ + text PT_LOAD FILEHDR PHDRS FLAGS(5); /* PF_R|PF_X */ + note PT_NOTE FLAGS(4); /* PF_R */ + dynamic PT_DYNAMIC FLAGS(4); /* PF_R */ + eh_frame_hdr 0x6474e550; /* PT_GNU_EH_FRAME, but ld doesn't match the name */ +} + +/* + * This controls what symbols we export from the DSO. + */ +VERSION +{ + VDSO_VERSION_STRING { + global: + __kernel_datapage_offset; /* Has to be there for the kernel to find */ + __kernel_get_syscall_map; + __kernel_gettimeofday; + __kernel_clock_gettime; + __kernel_clock_getres; + __kernel_get_tbfreq; + __kernel_sync_dicache; + __kernel_sync_dicache_p5; + __kernel_sigtramp_rt64; + local: *; + }; +} diff --git a/arch/powerpc/kernel/vdso64/vdso64_wrapper.S b/arch/powerpc/kernel/vdso64/vdso64_wrapper.S new file mode 100644 index 00000000000..0529cb9e3b9 --- /dev/null +++ b/arch/powerpc/kernel/vdso64/vdso64_wrapper.S @@ -0,0 +1,13 @@ +#include <linux/init.h> +#include <asm/page.h> + + .section ".data.page_aligned" + + .globl vdso64_start, vdso64_end + .balign PAGE_SIZE +vdso64_start: + .incbin "arch/powerpc/kernel/vdso64/vdso64.so" + .balign PAGE_SIZE +vdso64_end: + + .previous diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index 97082a4203a..71a6addf9f7 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -21,6 +21,7 @@ #include <asm/iommu.h> #include <asm/dma.h> #include <asm/vio.h> +#include <asm/prom.h> static const struct vio_device_id *vio_match_device( const struct vio_device_id *, const struct vio_dev *); @@ -265,7 +266,33 @@ static int vio_bus_match(struct device *dev, struct device_driver *drv) return (ids != NULL) && (vio_match_device(ids, vio_dev) != NULL); } +static int vio_hotplug(struct device *dev, char **envp, int num_envp, + char *buffer, int buffer_size) +{ + const struct vio_dev *vio_dev = to_vio_dev(dev); + char *cp; + int length; + + if (!num_envp) + return -ENOMEM; + + if (!vio_dev->dev.platform_data) + return -ENODEV; + cp = (char *)get_property(vio_dev->dev.platform_data, "compatible", &length); + if (!cp) + return -ENODEV; + + envp[0] = buffer; + length = scnprintf(buffer, buffer_size, "MODALIAS=vio:T%sS%s", + vio_dev->type, cp); + if (buffer_size - length <= 0) + return -ENOMEM; + envp[1] = NULL; + return 0; +} + struct bus_type vio_bus_type = { .name = "vio", + .hotplug = vio_hotplug, .match = vio_bus_match, }; diff --git a/arch/powerpc/lib/bitops.c b/arch/powerpc/lib/bitops.c index b67ce3004eb..f68ad71a018 100644 --- a/arch/powerpc/lib/bitops.c +++ b/arch/powerpc/lib/bitops.c @@ -41,7 +41,7 @@ unsigned long find_next_bit(const unsigned long *addr, unsigned long size, tmp = *p; found_first: - tmp &= (~0UL >> (64 - size)); + tmp &= (~0UL >> (BITS_PER_LONG - size)); if (tmp == 0UL) /* Are any bits set? */ return result + size; /* Nope. */ found_middle: diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 22e47487613..706e8a63ced 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -84,10 +84,11 @@ extern unsigned long dart_tablebase; #endif /* CONFIG_U3_DART */ +static unsigned long _SDR1; +struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT]; + hpte_t *htab_address; unsigned long htab_hash_mask; -unsigned long _SDR1; -struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT]; int mmu_linear_psize = MMU_PAGE_4K; int mmu_virtual_psize = MMU_PAGE_4K; #ifdef CONFIG_HUGETLB_PAGE @@ -165,7 +166,7 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend, * normal insert callback here. */ #ifdef CONFIG_PPC_ISERIES - if (systemcfg->platform == PLATFORM_ISERIES_LPAR) + if (_machine == PLATFORM_ISERIES_LPAR) ret = iSeries_hpte_insert(hpteg, va, virt_to_abs(paddr), tmp_mode, @@ -174,7 +175,7 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend, else #endif #ifdef CONFIG_PPC_PSERIES - if (systemcfg->platform & PLATFORM_LPAR) + if (_machine & PLATFORM_LPAR) ret = pSeries_lpar_hpte_insert(hpteg, va, virt_to_abs(paddr), tmp_mode, @@ -293,7 +294,7 @@ static void __init htab_init_page_sizes(void) * Not in the device-tree, let's fallback on known size * list for 16M capable GP & GR */ - if ((systemcfg->platform != PLATFORM_ISERIES_LPAR) && + if ((_machine != PLATFORM_ISERIES_LPAR) && cpu_has_feature(CPU_FTR_16M_PAGE)) memcpy(mmu_psize_defs, mmu_psize_defaults_gp, sizeof(mmu_psize_defaults_gp)); @@ -364,7 +365,7 @@ static int __init htab_dt_scan_pftsize(unsigned long node, static unsigned long __init htab_get_table_size(void) { - unsigned long rnd_mem_size, pteg_count; + unsigned long mem_size, rnd_mem_size, pteg_count; /* If hash size isn't already provided by the platform, we try to * retreive it from the device-tree. If it's not there neither, we @@ -376,8 +377,9 @@ static unsigned long __init htab_get_table_size(void) return 1UL << ppc64_pft_size; /* round mem_size up to next power of 2 */ - rnd_mem_size = 1UL << __ilog2(systemcfg->physicalMemorySize); - if (rnd_mem_size < systemcfg->physicalMemorySize) + mem_size = lmb_phys_mem_size(); + rnd_mem_size = 1UL << __ilog2(mem_size); + if (rnd_mem_size < mem_size) rnd_mem_size <<= 1; /* # pages / 2 */ @@ -386,6 +388,15 @@ static unsigned long __init htab_get_table_size(void) return pteg_count << 7; } +#ifdef CONFIG_MEMORY_HOTPLUG +void create_section_mapping(unsigned long start, unsigned long end) +{ + BUG_ON(htab_bolt_mapping(start, end, start, + _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_COHERENT | PP_RWXX, + mmu_linear_psize)); +} +#endif /* CONFIG_MEMORY_HOTPLUG */ + void __init htab_initialize(void) { unsigned long table, htab_size_bytes; @@ -410,7 +421,7 @@ void __init htab_initialize(void) htab_hash_mask = pteg_count - 1; - if (systemcfg->platform & PLATFORM_LPAR) { + if (platform_is_lpar()) { /* Using a hypervisor which owns the htab */ htab_address = NULL; _SDR1 = 0; @@ -431,6 +442,9 @@ void __init htab_initialize(void) /* Initialize the HPT with no entries */ memset((void *)table, 0, htab_size_bytes); + + /* Set SDR1 */ + mtspr(SPRN_SDR1, _SDR1); } mode_rw = _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_COHERENT | PP_RWXX; @@ -500,6 +514,12 @@ void __init htab_initialize(void) #undef KB #undef MB +void __init htab_initialize_secondary(void) +{ + if (!platform_is_lpar()) + mtspr(SPRN_SDR1, _SDR1); +} + /* * Called by asm hashtable.S for doing lazy icache flush */ diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c index 4612a79dfb6..7d4b8b5f060 100644 --- a/arch/powerpc/mm/init_32.c +++ b/arch/powerpc/mm/init_32.c @@ -84,9 +84,6 @@ void MMU_init(void); /* XXX should be in current.h -- paulus */ extern struct task_struct *current_set[NR_CPUS]; -char *klimit = _end; -struct device_node *memory_node; - extern int init_bootmem_done; /* diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index ce974c83d88..1134f70f231 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -20,6 +20,8 @@ * */ +#undef DEBUG + #include <linux/config.h> #include <linux/signal.h> #include <linux/sched.h> @@ -64,6 +66,12 @@ #include <asm/vdso.h> #include <asm/imalloc.h> +#ifdef DEBUG +#define DBG(fmt...) printk(fmt) +#else +#define DBG(fmt...) +#endif + #if PGTABLE_RANGE > USER_VSID_RANGE #warning Limited user VSID range means pagetable space is wasted #endif @@ -72,8 +80,6 @@ #warning TASK_SIZE is smaller than it needs to be. #endif -unsigned long klimit = (unsigned long)_end; - /* max amount of RAM to use */ unsigned long __max_memory; @@ -188,14 +194,14 @@ static void zero_ctor(void *addr, kmem_cache_t *cache, unsigned long flags) } #ifdef CONFIG_PPC_64K_PAGES -static const int pgtable_cache_size[2] = { - PTE_TABLE_SIZE, PGD_TABLE_SIZE +static const unsigned int pgtable_cache_size[3] = { + PTE_TABLE_SIZE, PMD_TABLE_SIZE, PGD_TABLE_SIZE }; static const char *pgtable_cache_name[ARRAY_SIZE(pgtable_cache_size)] = { - "pte_pmd_cache", "pgd_cache", + "pte_pmd_cache", "pmd_cache", "pgd_cache", }; #else -static const int pgtable_cache_size[2] = { +static const unsigned int pgtable_cache_size[2] = { PTE_TABLE_SIZE, PMD_TABLE_SIZE }; static const char *pgtable_cache_name[ARRAY_SIZE(pgtable_cache_size)] = { @@ -213,6 +219,8 @@ void pgtable_cache_init(void) int size = pgtable_cache_size[i]; const char *name = pgtable_cache_name[i]; + DBG("Allocating page table cache %s (#%d) " + "for size: %08x...\n", name, i, size); pgtable_cache[i] = kmem_cache_create(name, size, size, SLAB_HWCACHE_ALIGN | diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 6f55efd9be9..e2c95fcb805 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -46,9 +46,7 @@ #include <asm/prom.h> #include <asm/lmb.h> #include <asm/sections.h> -#ifdef CONFIG_PPC64 #include <asm/vdso.h> -#endif #include "mmu_decl.h" @@ -110,6 +108,7 @@ EXPORT_SYMBOL(phys_mem_access_prot); void online_page(struct page *page) { ClearPageReserved(page); + set_page_count(page, 0); free_cold_page(page); totalram_pages++; num_physpages++; @@ -127,6 +126,9 @@ int __devinit add_memory(u64 start, u64 size) unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; + start += KERNELBASE; + create_section_mapping(start, start + size); + /* this should work for most non-highmem platforms */ zone = pgdata->node_zones; @@ -393,10 +395,8 @@ void __init mem_init(void) mem_init_done = 1; -#ifdef CONFIG_PPC64 /* Initialize the vDSO */ vdso_init(); -#endif } /* diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index da09ba03c42..bd2cf133688 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -17,9 +17,8 @@ #include <linux/nodemask.h> #include <linux/cpu.h> #include <linux/notifier.h> +#include <asm/sparsemem.h> #include <asm/lmb.h> -#include <asm/machdep.h> -#include <asm/abs_addr.h> #include <asm/system.h> #include <asm/smp.h> @@ -28,45 +27,113 @@ static int numa_enabled = 1; static int numa_debug; #define dbg(args...) if (numa_debug) { printk(KERN_INFO args); } -#ifdef DEBUG_NUMA -#define ARRAY_INITIALISER -1 -#else -#define ARRAY_INITIALISER 0 -#endif - -int numa_cpu_lookup_table[NR_CPUS] = { [ 0 ... (NR_CPUS - 1)] = - ARRAY_INITIALISER}; -char *numa_memory_lookup_table; +int numa_cpu_lookup_table[NR_CPUS]; cpumask_t numa_cpumask_lookup_table[MAX_NUMNODES]; -int nr_cpus_in_node[MAX_NUMNODES] = { [0 ... (MAX_NUMNODES -1)] = 0}; - struct pglist_data *node_data[MAX_NUMNODES]; -bootmem_data_t __initdata plat_node_bdata[MAX_NUMNODES]; + +EXPORT_SYMBOL(numa_cpu_lookup_table); +EXPORT_SYMBOL(numa_cpumask_lookup_table); +EXPORT_SYMBOL(node_data); + +static bootmem_data_t __initdata plat_node_bdata[MAX_NUMNODES]; static int min_common_depth; /* - * We need somewhere to store start/span for each node until we have + * We need somewhere to store start/end/node for each region until we have * allocated the real node_data structures. */ +#define MAX_REGIONS (MAX_LMB_REGIONS*2) static struct { - unsigned long node_start_pfn; - unsigned long node_end_pfn; - unsigned long node_present_pages; -} init_node_data[MAX_NUMNODES] __initdata; + unsigned long start_pfn; + unsigned long end_pfn; + int nid; +} init_node_data[MAX_REGIONS] __initdata; -EXPORT_SYMBOL(node_data); -EXPORT_SYMBOL(numa_cpu_lookup_table); -EXPORT_SYMBOL(numa_memory_lookup_table); -EXPORT_SYMBOL(numa_cpumask_lookup_table); -EXPORT_SYMBOL(nr_cpus_in_node); +int __init early_pfn_to_nid(unsigned long pfn) +{ + unsigned int i; + + for (i = 0; init_node_data[i].end_pfn; i++) { + unsigned long start_pfn = init_node_data[i].start_pfn; + unsigned long end_pfn = init_node_data[i].end_pfn; + + if ((start_pfn <= pfn) && (pfn < end_pfn)) + return init_node_data[i].nid; + } + + return -1; +} + +void __init add_region(unsigned int nid, unsigned long start_pfn, + unsigned long pages) +{ + unsigned int i; + + dbg("add_region nid %d start_pfn 0x%lx pages 0x%lx\n", + nid, start_pfn, pages); + + for (i = 0; init_node_data[i].end_pfn; i++) { + if (init_node_data[i].nid != nid) + continue; + if (init_node_data[i].end_pfn == start_pfn) { + init_node_data[i].end_pfn += pages; + return; + } + if (init_node_data[i].start_pfn == (start_pfn + pages)) { + init_node_data[i].start_pfn -= pages; + return; + } + } + + /* + * Leave last entry NULL so we dont iterate off the end (we use + * entry.end_pfn to terminate the walk). + */ + if (i >= (MAX_REGIONS - 1)) { + printk(KERN_ERR "WARNING: too many memory regions in " + "numa code, truncating\n"); + return; + } + + init_node_data[i].start_pfn = start_pfn; + init_node_data[i].end_pfn = start_pfn + pages; + init_node_data[i].nid = nid; +} + +/* We assume init_node_data has no overlapping regions */ +void __init get_region(unsigned int nid, unsigned long *start_pfn, + unsigned long *end_pfn, unsigned long *pages_present) +{ + unsigned int i; + + *start_pfn = -1UL; + *end_pfn = *pages_present = 0; + + for (i = 0; init_node_data[i].end_pfn; i++) { + if (init_node_data[i].nid != nid) + continue; + + *pages_present += init_node_data[i].end_pfn - + init_node_data[i].start_pfn; + + if (init_node_data[i].start_pfn < *start_pfn) + *start_pfn = init_node_data[i].start_pfn; + + if (init_node_data[i].end_pfn > *end_pfn) + *end_pfn = init_node_data[i].end_pfn; + } + + /* We didnt find a matching region, return start/end as 0 */ + if (*start_pfn == -1UL) + start_pfn = 0; +} static inline void map_cpu_to_node(int cpu, int node) { numa_cpu_lookup_table[cpu] = node; - if (!(cpu_isset(cpu, numa_cpumask_lookup_table[node]))) { + + if (!(cpu_isset(cpu, numa_cpumask_lookup_table[node]))) cpu_set(cpu, numa_cpumask_lookup_table[node]); - nr_cpus_in_node[node]++; - } } #ifdef CONFIG_HOTPLUG_CPU @@ -78,7 +145,6 @@ static void unmap_cpu_from_node(unsigned long cpu) if (cpu_isset(cpu, numa_cpumask_lookup_table[node])) { cpu_clear(cpu, numa_cpumask_lookup_table[node]); - nr_cpus_in_node[node]--; } else { printk(KERN_ERR "WARNING: cpu %lu not found in node %d\n", cpu, node); @@ -86,7 +152,7 @@ static void unmap_cpu_from_node(unsigned long cpu) } #endif /* CONFIG_HOTPLUG_CPU */ -static struct device_node * __devinit find_cpu_node(unsigned int cpu) +static struct device_node *find_cpu_node(unsigned int cpu) { unsigned int hw_cpuid = get_hard_smp_processor_id(cpu); struct device_node *cpu_node = NULL; @@ -213,7 +279,7 @@ static int __init get_mem_size_cells(void) return rc; } -static unsigned long read_n_cells(int n, unsigned int **buf) +static unsigned long __init read_n_cells(int n, unsigned int **buf) { unsigned long result = 0; @@ -295,7 +361,8 @@ static int cpu_numa_callback(struct notifier_block *nfb, * or zero. If the returned value of size is 0 the region should be * discarded as it lies wholy above the memory limit. */ -static unsigned long __init numa_enforce_memory_limit(unsigned long start, unsigned long size) +static unsigned long __init numa_enforce_memory_limit(unsigned long start, + unsigned long size) { /* * We use lmb_end_of_DRAM() in here instead of memory_limit because @@ -320,8 +387,7 @@ static int __init parse_numa_properties(void) struct device_node *cpu = NULL; struct device_node *memory = NULL; int addr_cells, size_cells; - int max_domain = 0; - long entries = lmb_end_of_DRAM() >> MEMORY_INCREMENT_SHIFT; + int max_domain; unsigned long i; if (numa_enabled == 0) { @@ -329,13 +395,6 @@ static int __init parse_numa_properties(void) return -1; } - numa_memory_lookup_table = - (char *)abs_to_virt(lmb_alloc(entries * sizeof(char), 1)); - memset(numa_memory_lookup_table, 0, entries * sizeof(char)); - - for (i = 0; i < entries ; i++) - numa_memory_lookup_table[i] = ARRAY_INITIALISER; - min_common_depth = find_min_common_depth(); dbg("NUMA associativity depth for CPU/Memory: %d\n", min_common_depth); @@ -387,9 +446,6 @@ new_range: start = read_n_cells(addr_cells, &memcell_buf); size = read_n_cells(size_cells, &memcell_buf); - start = _ALIGN_DOWN(start, MEMORY_INCREMENT); - size = _ALIGN_UP(size, MEMORY_INCREMENT); - numa_domain = of_node_numa_domain(memory); if (numa_domain >= MAX_NUMNODES) { @@ -403,44 +459,15 @@ new_range: if (max_domain < numa_domain) max_domain = numa_domain; - if (! (size = numa_enforce_memory_limit(start, size))) { + if (!(size = numa_enforce_memory_limit(start, size))) { if (--ranges) goto new_range; else continue; } - /* - * Initialize new node struct, or add to an existing one. - */ - if (init_node_data[numa_domain].node_end_pfn) { - if ((start / PAGE_SIZE) < - init_node_data[numa_domain].node_start_pfn) - init_node_data[numa_domain].node_start_pfn = - start / PAGE_SIZE; - if (((start / PAGE_SIZE) + (size / PAGE_SIZE)) > - init_node_data[numa_domain].node_end_pfn) - init_node_data[numa_domain].node_end_pfn = - (start / PAGE_SIZE) + - (size / PAGE_SIZE); - - init_node_data[numa_domain].node_present_pages += - size / PAGE_SIZE; - } else { - node_set_online(numa_domain); - - init_node_data[numa_domain].node_start_pfn = - start / PAGE_SIZE; - init_node_data[numa_domain].node_end_pfn = - init_node_data[numa_domain].node_start_pfn + - size / PAGE_SIZE; - init_node_data[numa_domain].node_present_pages = - size / PAGE_SIZE; - } - - for (i = start ; i < (start+size); i += MEMORY_INCREMENT) - numa_memory_lookup_table[i >> MEMORY_INCREMENT_SHIFT] = - numa_domain; + add_region(numa_domain, start >> PAGE_SHIFT, + size >> PAGE_SHIFT); if (--ranges) goto new_range; @@ -456,32 +483,15 @@ static void __init setup_nonnuma(void) { unsigned long top_of_ram = lmb_end_of_DRAM(); unsigned long total_ram = lmb_phys_mem_size(); - unsigned long i; printk(KERN_INFO "Top of RAM: 0x%lx, Total RAM: 0x%lx\n", top_of_ram, total_ram); printk(KERN_INFO "Memory hole size: %ldMB\n", (top_of_ram - total_ram) >> 20); - if (!numa_memory_lookup_table) { - long entries = top_of_ram >> MEMORY_INCREMENT_SHIFT; - numa_memory_lookup_table = - (char *)abs_to_virt(lmb_alloc(entries * sizeof(char), 1)); - memset(numa_memory_lookup_table, 0, entries * sizeof(char)); - for (i = 0; i < entries ; i++) - numa_memory_lookup_table[i] = ARRAY_INITIALISER; - } - map_cpu_to_node(boot_cpuid, 0); - + add_region(0, 0, lmb_end_of_DRAM() >> PAGE_SHIFT); node_set_online(0); - - init_node_data[0].node_start_pfn = 0; - init_node_data[0].node_end_pfn = lmb_end_of_DRAM() / PAGE_SIZE; - init_node_data[0].node_present_pages = total_ram / PAGE_SIZE; - - for (i = 0 ; i < top_of_ram; i += MEMORY_INCREMENT) - numa_memory_lookup_table[i >> MEMORY_INCREMENT_SHIFT] = 0; } static void __init dump_numa_topology(void) @@ -499,8 +509,9 @@ static void __init dump_numa_topology(void) count = 0; - for (i = 0; i < lmb_end_of_DRAM(); i += MEMORY_INCREMENT) { - if (numa_memory_lookup_table[i >> MEMORY_INCREMENT_SHIFT] == node) { + for (i = 0; i < lmb_end_of_DRAM(); + i += (1 << SECTION_SIZE_BITS)) { + if (early_pfn_to_nid(i >> PAGE_SHIFT) == node) { if (count == 0) printk(" 0x%lx", i); ++count; @@ -525,10 +536,12 @@ static void __init dump_numa_topology(void) * * Returns the physical address of the memory. */ -static unsigned long careful_allocation(int nid, unsigned long size, - unsigned long align, unsigned long end) +static void __init *careful_allocation(int nid, unsigned long size, + unsigned long align, + unsigned long end_pfn) { - unsigned long ret = lmb_alloc_base(size, align, end); + int new_nid; + unsigned long ret = lmb_alloc_base(size, align, end_pfn << PAGE_SHIFT); /* retry over all memory */ if (!ret) @@ -542,28 +555,27 @@ static unsigned long careful_allocation(int nid, unsigned long size, * If the memory came from a previously allocated node, we must * retry with the bootmem allocator. */ - if (pa_to_nid(ret) < nid) { - nid = pa_to_nid(ret); - ret = (unsigned long)__alloc_bootmem_node(NODE_DATA(nid), + new_nid = early_pfn_to_nid(ret >> PAGE_SHIFT); + if (new_nid < nid) { + ret = (unsigned long)__alloc_bootmem_node(NODE_DATA(new_nid), size, align, 0); if (!ret) panic("numa.c: cannot allocate %lu bytes on node %d", - size, nid); + size, new_nid); - ret = virt_to_abs(ret); + ret = __pa(ret); dbg("alloc_bootmem %lx %lx\n", ret, size); } - return ret; + return (void *)ret; } void __init do_init_bootmem(void) { int nid; - int addr_cells, size_cells; - struct device_node *memory = NULL; + unsigned int i; static struct notifier_block ppc64_numa_nb = { .notifier_call = cpu_numa_callback, .priority = 1 /* Must run before sched domains notifier. */ @@ -581,99 +593,66 @@ void __init do_init_bootmem(void) register_cpu_notifier(&ppc64_numa_nb); for_each_online_node(nid) { - unsigned long start_paddr, end_paddr; - int i; + unsigned long start_pfn, end_pfn, pages_present; unsigned long bootmem_paddr; unsigned long bootmap_pages; - start_paddr = init_node_data[nid].node_start_pfn * PAGE_SIZE; - end_paddr = init_node_data[nid].node_end_pfn * PAGE_SIZE; + get_region(nid, &start_pfn, &end_pfn, &pages_present); /* Allocate the node structure node local if possible */ - NODE_DATA(nid) = (struct pglist_data *)careful_allocation(nid, + NODE_DATA(nid) = careful_allocation(nid, sizeof(struct pglist_data), - SMP_CACHE_BYTES, end_paddr); - NODE_DATA(nid) = abs_to_virt(NODE_DATA(nid)); + SMP_CACHE_BYTES, end_pfn); + NODE_DATA(nid) = __va(NODE_DATA(nid)); memset(NODE_DATA(nid), 0, sizeof(struct pglist_data)); dbg("node %d\n", nid); dbg("NODE_DATA() = %p\n", NODE_DATA(nid)); NODE_DATA(nid)->bdata = &plat_node_bdata[nid]; - NODE_DATA(nid)->node_start_pfn = - init_node_data[nid].node_start_pfn; - NODE_DATA(nid)->node_spanned_pages = - end_paddr - start_paddr; + NODE_DATA(nid)->node_start_pfn = start_pfn; + NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn; if (NODE_DATA(nid)->node_spanned_pages == 0) continue; - dbg("start_paddr = %lx\n", start_paddr); - dbg("end_paddr = %lx\n", end_paddr); + dbg("start_paddr = %lx\n", start_pfn << PAGE_SHIFT); + dbg("end_paddr = %lx\n", end_pfn << PAGE_SHIFT); - bootmap_pages = bootmem_bootmap_pages((end_paddr - start_paddr) >> PAGE_SHIFT); + bootmap_pages = bootmem_bootmap_pages(end_pfn - start_pfn); + bootmem_paddr = (unsigned long)careful_allocation(nid, + bootmap_pages << PAGE_SHIFT, + PAGE_SIZE, end_pfn); + memset(__va(bootmem_paddr), 0, bootmap_pages << PAGE_SHIFT); - bootmem_paddr = careful_allocation(nid, - bootmap_pages << PAGE_SHIFT, - PAGE_SIZE, end_paddr); - memset(abs_to_virt(bootmem_paddr), 0, - bootmap_pages << PAGE_SHIFT); dbg("bootmap_paddr = %lx\n", bootmem_paddr); init_bootmem_node(NODE_DATA(nid), bootmem_paddr >> PAGE_SHIFT, - start_paddr >> PAGE_SHIFT, - end_paddr >> PAGE_SHIFT); + start_pfn, end_pfn); - /* - * We need to do another scan of all memory sections to - * associate memory with the correct node. - */ - addr_cells = get_mem_addr_cells(); - size_cells = get_mem_size_cells(); - memory = NULL; - while ((memory = of_find_node_by_type(memory, "memory")) != NULL) { - unsigned long mem_start, mem_size; - int numa_domain, ranges; - unsigned int *memcell_buf; - unsigned int len; - - memcell_buf = (unsigned int *)get_property(memory, "reg", &len); - if (!memcell_buf || len <= 0) - continue; + /* Add free regions on this node */ + for (i = 0; init_node_data[i].end_pfn; i++) { + unsigned long start, end; - ranges = memory->n_addrs; /* ranges in cell */ -new_range: - mem_start = read_n_cells(addr_cells, &memcell_buf); - mem_size = read_n_cells(size_cells, &memcell_buf); - if (numa_enabled) { - numa_domain = of_node_numa_domain(memory); - if (numa_domain >= MAX_NUMNODES) - numa_domain = 0; - } else - numa_domain = 0; - - if (numa_domain != nid) + if (init_node_data[i].nid != nid) continue; - mem_size = numa_enforce_memory_limit(mem_start, mem_size); - if (mem_size) { - dbg("free_bootmem %lx %lx\n", mem_start, mem_size); - free_bootmem_node(NODE_DATA(nid), mem_start, mem_size); - } + start = init_node_data[i].start_pfn << PAGE_SHIFT; + end = init_node_data[i].end_pfn << PAGE_SHIFT; - if (--ranges) /* process all ranges in cell */ - goto new_range; + dbg("free_bootmem %lx %lx\n", start, end - start); + free_bootmem_node(NODE_DATA(nid), start, end - start); } - /* - * Mark reserved regions on this node - */ + /* Mark reserved regions on this node */ for (i = 0; i < lmb.reserved.cnt; i++) { unsigned long physbase = lmb.reserved.region[i].base; unsigned long size = lmb.reserved.region[i].size; + unsigned long start_paddr = start_pfn << PAGE_SHIFT; + unsigned long end_paddr = end_pfn << PAGE_SHIFT; - if (pa_to_nid(physbase) != nid && - pa_to_nid(physbase+size-1) != nid) + if (early_pfn_to_nid(physbase >> PAGE_SHIFT) != nid && + early_pfn_to_nid((physbase+size-1) >> PAGE_SHIFT) != nid) continue; if (physbase < end_paddr && @@ -693,46 +672,19 @@ new_range: size); } } - /* - * This loop may look famaliar, but we have to do it again - * after marking our reserved memory to mark memory present - * for sparsemem. - */ - addr_cells = get_mem_addr_cells(); - size_cells = get_mem_size_cells(); - memory = NULL; - while ((memory = of_find_node_by_type(memory, "memory")) != NULL) { - unsigned long mem_start, mem_size; - int numa_domain, ranges; - unsigned int *memcell_buf; - unsigned int len; - - memcell_buf = (unsigned int *)get_property(memory, "reg", &len); - if (!memcell_buf || len <= 0) - continue; - ranges = memory->n_addrs; /* ranges in cell */ -new_range2: - mem_start = read_n_cells(addr_cells, &memcell_buf); - mem_size = read_n_cells(size_cells, &memcell_buf); - if (numa_enabled) { - numa_domain = of_node_numa_domain(memory); - if (numa_domain >= MAX_NUMNODES) - numa_domain = 0; - } else - numa_domain = 0; - - if (numa_domain != nid) + /* Add regions into sparsemem */ + for (i = 0; init_node_data[i].end_pfn; i++) { + unsigned long start, end; + + if (init_node_data[i].nid != nid) continue; - mem_size = numa_enforce_memory_limit(mem_start, mem_size); - memory_present(numa_domain, mem_start >> PAGE_SHIFT, - (mem_start + mem_size) >> PAGE_SHIFT); + start = init_node_data[i].start_pfn; + end = init_node_data[i].end_pfn; - if (--ranges) /* process all ranges in cell */ - goto new_range2; + memory_present(nid, start, end); } - } } @@ -746,21 +698,18 @@ void __init paging_init(void) memset(zholes_size, 0, sizeof(zholes_size)); for_each_online_node(nid) { - unsigned long start_pfn; - unsigned long end_pfn; + unsigned long start_pfn, end_pfn, pages_present; - start_pfn = init_node_data[nid].node_start_pfn; - end_pfn = init_node_data[nid].node_end_pfn; + get_region(nid, &start_pfn, &end_pfn, &pages_present); zones_size[ZONE_DMA] = end_pfn - start_pfn; - zholes_size[ZONE_DMA] = zones_size[ZONE_DMA] - - init_node_data[nid].node_present_pages; + zholes_size[ZONE_DMA] = zones_size[ZONE_DMA] - pages_present; dbg("free_area_init node %d %lx %lx (hole: %lx)\n", nid, zones_size[ZONE_DMA], start_pfn, zholes_size[ZONE_DMA]); - free_area_init_node(nid, NODE_DATA(nid), zones_size, - start_pfn, zholes_size); + free_area_init_node(nid, NODE_DATA(nid), zones_size, start_pfn, + zholes_size); } } diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 900842451bd..c7f7bb6f30b 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -122,8 +122,11 @@ static int map_io_page(unsigned long ea, unsigned long pa, int flags) * */ if (htab_bolt_mapping(ea, ea + PAGE_SIZE, pa, flags, - mmu_virtual_psize)) - panic("Can't map bolted IO mapping"); + mmu_virtual_psize)) { + printk(KERN_ERR "Failed to do bolted mapping IO " + "memory at %016lx !\n", pa); + return -ENOMEM; + } } return 0; } diff --git a/arch/powerpc/mm/stab.c b/arch/powerpc/mm/stab.c index fa325dbf98f..cfbb4e1f966 100644 --- a/arch/powerpc/mm/stab.c +++ b/arch/powerpc/mm/stab.c @@ -20,6 +20,7 @@ #include <asm/cputable.h> #include <asm/lmb.h> #include <asm/abs_addr.h> +#include <asm/firmware.h> struct stab_entry { unsigned long esid_data; @@ -256,7 +257,7 @@ void stabs_alloc(void) paca[cpu].stab_addr = newstab; paca[cpu].stab_real = virt_to_abs(newstab); - printk(KERN_DEBUG "Segment table for CPU %d at 0x%lx " + printk(KERN_INFO "Segment table for CPU %d at 0x%lx " "virtual, 0x%lx absolute\n", cpu, paca[cpu].stab_addr, paca[cpu].stab_real); } @@ -270,10 +271,28 @@ void stabs_alloc(void) void stab_initialize(unsigned long stab) { unsigned long vsid = get_kernel_vsid(KERNELBASE); + unsigned long stabreal; asm volatile("isync; slbia; isync":::"memory"); make_ste(stab, GET_ESID(KERNELBASE), vsid); /* Order update */ asm volatile("sync":::"memory"); + + /* Set ASR */ + stabreal = get_paca()->stab_real | 0x1ul; + +#ifdef CONFIG_PPC_ISERIES + if (firmware_has_feature(FW_FEATURE_ISERIES)) { + HvCall1(HvCallBaseSetASR, stabreal); + return; + } +#endif /* CONFIG_PPC_ISERIES */ +#ifdef CONFIG_PPC_PSERIES + if (platform_is_lpar()) { + plpar_hcall_norets(H_SET_ASR, stabreal); + return; + } +#endif + mtspr(SPRN_ASR, stabreal); } diff --git a/arch/powerpc/oprofile/op_model_power4.c b/arch/powerpc/oprofile/op_model_power4.c index c4ee5478427..a3401b46f3b 100644 --- a/arch/powerpc/oprofile/op_model_power4.c +++ b/arch/powerpc/oprofile/op_model_power4.c @@ -14,7 +14,6 @@ #include <asm/system.h> #include <asm/processor.h> #include <asm/cputable.h> -#include <asm/systemcfg.h> #include <asm/rtas.h> #include <asm/oprofile_impl.h> #include <asm/reg.h> @@ -233,8 +232,7 @@ static unsigned long get_pc(struct pt_regs *regs) mmcra = mfspr(SPRN_MMCRA); /* Were we in the hypervisor? */ - if ((systemcfg->platform == PLATFORM_PSERIES_LPAR) && - (mmcra & MMCRA_SIHV)) + if (platform_is_lpar() && (mmcra & MMCRA_SIHV)) /* function descriptor madness */ return *((unsigned long *)hypervisor_bucket); diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c index ecd32d5d85f..4099ddab920 100644 --- a/arch/powerpc/platforms/chrp/setup.c +++ b/arch/powerpc/platforms/chrp/setup.c @@ -361,7 +361,9 @@ static void __init chrp_find_openpic(void) printk(KERN_INFO "OpenPIC at %lx\n", opaddr); irq_count = NR_IRQS - NUM_ISA_INTERRUPTS - 4; /* leave room for IPIs */ - prom_get_irq_senses(init_senses, NUM_8259_INTERRUPTS, NR_IRQS - 4); + prom_get_irq_senses(init_senses, NUM_ISA_INTERRUPTS, NR_IRQS - 4); + /* i8259 cascade is always positive level */ + init_senses[0] = IRQ_SENSE_LEVEL | IRQ_POLARITY_POSITIVE; iranges = (unsigned int *) get_property(np, "interrupt-ranges", &len); if (iranges == NULL) diff --git a/arch/powerpc/platforms/iseries/irq.c b/arch/powerpc/platforms/iseries/irq.c index a06603d84a4..01090e9ce0c 100644 --- a/arch/powerpc/platforms/iseries/irq.c +++ b/arch/powerpc/platforms/iseries/irq.c @@ -103,6 +103,9 @@ static void intReceived(struct XmPciLpEvent *eventParm, struct pt_regs *regsParm) { int irq; +#ifdef CONFIG_IRQSTACKS + struct thread_info *curtp, *irqtp; +#endif ++Pci_Interrupt_Count; @@ -110,7 +113,20 @@ static void intReceived(struct XmPciLpEvent *eventParm, case XmPciLpEvent_SlotInterrupt: irq = eventParm->hvLpEvent.xCorrelationToken; /* Dispatch the interrupt handlers for this irq */ - ppc_irq_dispatch_handler(regsParm, irq); +#ifdef CONFIG_IRQSTACKS + /* Switch to the irq stack to handle this */ + curtp = current_thread_info(); + irqtp = hardirq_ctx[smp_processor_id()]; + if (curtp != irqtp) { + irqtp->task = curtp->task; + irqtp->flags = 0; + call___do_IRQ(irq, regsParm, irqtp); + irqtp->task = NULL; + if (irqtp->flags) + set_bits(irqtp->flags, &curtp->flags); + } else +#endif + __do_IRQ(irq, regsParm); HvCallPci_eoi(eventParm->eventData.slotInterrupt.busNumber, eventParm->eventData.slotInterrupt.subBusNumber, eventParm->eventData.slotInterrupt.deviceId); @@ -310,10 +326,8 @@ static void iSeries_disable_IRQ(unsigned int irq) } /* - * Need to define this so ppc_irq_dispatch_handler will NOT call - * enable_IRQ at the end of interrupt handling. However, this does - * nothing because there is not enough information provided to do - * the EOI HvCall. This is done by XmPciLpEvent.c + * This does nothing because there is not enough information + * provided to do the EOI HvCall. This is done by XmPciLpEvent.c */ static void iSeries_end_IRQ(unsigned int irq) { diff --git a/arch/powerpc/platforms/iseries/misc.S b/arch/powerpc/platforms/iseries/misc.S index 09f14522e17..dfe7aa1ba09 100644 --- a/arch/powerpc/platforms/iseries/misc.S +++ b/arch/powerpc/platforms/iseries/misc.S @@ -15,6 +15,7 @@ #include <asm/processor.h> #include <asm/asm-offsets.h> +#include <asm/ppc_asm.h> .text diff --git a/arch/powerpc/platforms/iseries/setup.c b/arch/powerpc/platforms/iseries/setup.c index d3e4bf756c8..6a29f301436 100644 --- a/arch/powerpc/platforms/iseries/setup.c +++ b/arch/powerpc/platforms/iseries/setup.c @@ -39,7 +39,8 @@ #include <asm/sections.h> #include <asm/iommu.h> #include <asm/firmware.h> - +#include <asm/systemcfg.h> +#include <asm/system.h> #include <asm/time.h> #include <asm/paca.h> #include <asm/cache.h> @@ -71,7 +72,7 @@ extern void hvlog(char *fmt, ...); #endif /* Function Prototypes */ -static void build_iSeries_Memory_Map(void); +static unsigned long build_iSeries_Memory_Map(void); static void iseries_shared_idle(void); static void iseries_dedicated_idle(void); #ifdef CONFIG_PCI @@ -84,7 +85,6 @@ static void iSeries_pci_final_fixup(void) { } int piranha_simulator; extern int rd_size; /* Defined in drivers/block/rd.c */ -extern unsigned long klimit; extern unsigned long embedded_sysmap_start; extern unsigned long embedded_sysmap_end; @@ -403,9 +403,11 @@ void mschunks_alloc(unsigned long num_chunks) * a table used to translate Linux's physical addresses to these * absolute addresses. Absolute addresses are needed when * communicating with the hypervisor (e.g. to build HPT entries) + * + * Returns the physical memory size */ -static void __init build_iSeries_Memory_Map(void) +static unsigned long __init build_iSeries_Memory_Map(void) { u32 loadAreaFirstChunk, loadAreaLastChunk, loadAreaSize; u32 nextPhysChunk; @@ -538,7 +540,7 @@ static void __init build_iSeries_Memory_Map(void) * which should be equal to * nextPhysChunk */ - systemcfg->physicalMemorySize = chunk_to_addr(nextPhysChunk); + return chunk_to_addr(nextPhysChunk); } /* @@ -564,8 +566,8 @@ static void __init iSeries_setup_arch(void) printk("Max physical processors = %d\n", itVpdAreas.xSlicMaxPhysicalProcs); - systemcfg->processor = xIoHriProcessorVpd[procIx].xPVR; - printk("Processor version = %x\n", systemcfg->processor); + _systemcfg->processor = xIoHriProcessorVpd[procIx].xPVR; + printk("Processor version = %x\n", _systemcfg->processor); } static void iSeries_show_cpuinfo(struct seq_file *m) @@ -694,20 +696,18 @@ static void iseries_shared_idle(void) if (hvlpevent_is_pending()) process_iSeries_events(); + preempt_enable_no_resched(); schedule(); + preempt_disable(); } } static void iseries_dedicated_idle(void) { - long oldval; + set_thread_flag(TIF_POLLING_NRFLAG); while (1) { - oldval = test_and_clear_thread_flag(TIF_NEED_RESCHED); - - if (!oldval) { - set_thread_flag(TIF_POLLING_NRFLAG); - + if (!need_resched()) { while (!need_resched()) { ppc64_runlatch_off(); HMT_low(); @@ -720,13 +720,12 @@ static void iseries_dedicated_idle(void) } HMT_medium(); - clear_thread_flag(TIF_POLLING_NRFLAG); - } else { - set_need_resched(); } ppc64_runlatch_on(); + preempt_enable_no_resched(); schedule(); + preempt_disable(); } } @@ -931,7 +930,7 @@ void dt_cpus(struct iseries_flat_dt *dt) dt_end_node(dt); } -void build_flat_dt(struct iseries_flat_dt *dt) +void build_flat_dt(struct iseries_flat_dt *dt, unsigned long phys_mem_size) { u64 tmp[2]; @@ -947,7 +946,7 @@ void build_flat_dt(struct iseries_flat_dt *dt) dt_prop_str(dt, "name", "memory"); dt_prop_str(dt, "device_type", "memory"); tmp[0] = 0; - tmp[1] = systemcfg->physicalMemorySize; + tmp[1] = phys_mem_size; dt_prop_u64_list(dt, "reg", tmp, 2); dt_end_node(dt); @@ -967,13 +966,15 @@ void build_flat_dt(struct iseries_flat_dt *dt) void * __init iSeries_early_setup(void) { + unsigned long phys_mem_size; + iSeries_fixup_klimit(); /* * Initialize the table which translate Linux physical addresses to * AS/400 absolute addresses */ - build_iSeries_Memory_Map(); + phys_mem_size = build_iSeries_Memory_Map(); iSeries_get_cmdline(); @@ -983,7 +984,7 @@ void * __init iSeries_early_setup(void) /* Parse early parameters, in particular mem=x */ parse_early_param(); - build_flat_dt(&iseries_dt); + build_flat_dt(&iseries_dt, phys_mem_size); return (void *) __pa(&iseries_dt); } diff --git a/arch/powerpc/platforms/maple/pci.c b/arch/powerpc/platforms/maple/pci.c index 340c21caeae..895aeb3f75d 100644 --- a/arch/powerpc/platforms/maple/pci.c +++ b/arch/powerpc/platforms/maple/pci.c @@ -380,9 +380,6 @@ void __init maple_pcibios_fixup(void) for_each_pci_dev(dev) pci_read_irq_line(dev); - /* Do the mapping of the IO space */ - phbs_remap_io(); - DBG(" <- maple_pcibios_fixup\n"); } diff --git a/arch/powerpc/platforms/powermac/pci.c b/arch/powerpc/platforms/powermac/pci.c index 8f818d092e2..dfd41b9781a 100644 --- a/arch/powerpc/platforms/powermac/pci.c +++ b/arch/powerpc/platforms/powermac/pci.c @@ -918,9 +918,6 @@ void __init pmac_pci_init(void) PCI_DN(np)->busno = 0xf0; } - /* map in PCI I/O space */ - phbs_remap_io(); - /* pmac_check_ht_link(); */ /* Tell pci.c to not use the common resource allocation mechanism */ diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c index 83a49e80ac2..90040c49494 100644 --- a/arch/powerpc/platforms/powermac/pic.c +++ b/arch/powerpc/platforms/powermac/pic.c @@ -74,6 +74,9 @@ static DEFINE_SPINLOCK(pmac_pic_lock); #define GATWICK_IRQ_POOL_SIZE 10 static struct interrupt_info gatwick_int_pool[GATWICK_IRQ_POOL_SIZE]; +#define NR_MASK_WORDS ((NR_IRQS + 31) / 32) +static unsigned long ppc_lost_interrupts[NR_MASK_WORDS]; + /* * Mark an irq as "lost". This is only used on the pmac * since it can lose interrupts (see pmac_set_irq_mask). diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c index e1f9443cc87..957b0910342 100644 --- a/arch/powerpc/platforms/powermac/smp.c +++ b/arch/powerpc/platforms/powermac/smp.c @@ -305,9 +305,19 @@ static int __init smp_psurge_probe(void) psurge_start = ioremap(PSURGE_START, 4); psurge_pri_intr = ioremap(PSURGE_PRI_INTR, 4); - /* this is not actually strictly necessary -- paulus. */ - for (i = 1; i < ncpus; ++i) - smp_hw_index[i] = i; + /* + * This is necessary because OF doesn't know about the + * secondary cpu(s), and thus there aren't nodes in the + * device tree for them, and smp_setup_cpu_maps hasn't + * set their bits in cpu_possible_map and cpu_present_map. + */ + if (ncpus > NR_CPUS) + ncpus = NR_CPUS; + for (i = 1; i < ncpus ; ++i) { + cpu_set(i, cpu_present_map); + cpu_set(i, cpu_possible_map); + set_hard_smp_processor_id(i, i); + } if (ppc_md.progress) ppc_md.progress("smp_psurge_probe - done", 0x352); @@ -348,6 +358,7 @@ static void __init psurge_dual_sync_tb(int cpu_nr) int t; set_dec(tb_ticks_per_jiffy); + /* XXX fixme */ set_tb(0, 0); last_jiffy_stamp(cpu_nr) = 0; @@ -363,8 +374,6 @@ static void __init psurge_dual_sync_tb(int cpu_nr) /* now interrupt the secondary, starting both TBs */ psurge_set_ipi(1); - - smp_tb_synchronized = 1; } static struct irqaction psurge_irqaction = { @@ -625,9 +634,8 @@ void smp_core99_give_timebase(void) for (t = 100000; t > 0 && sec_tb_reset; --t) udelay(10); if (sec_tb_reset) + /* XXX BUG_ON here? */ printk(KERN_WARNING "Timeout waiting sync(2) on second CPU\n"); - else - smp_tb_synchronized = 1; /* Now, restart the timebase by leaving the GPIO to an open collector */ pmac_call_feature(PMAC_FTR_WRITE_GPIO, NULL, core99_tb_gpio, 0); @@ -810,19 +818,9 @@ static void __devinit smp_core99_setup_cpu(int cpu_nr) } -/* Core99 Macs (dual G4s and G5s) */ -struct smp_ops_t core99_smp_ops = { - .message_pass = smp_mpic_message_pass, - .probe = smp_core99_probe, - .kick_cpu = smp_core99_kick_cpu, - .setup_cpu = smp_core99_setup_cpu, - .give_timebase = smp_core99_give_timebase, - .take_timebase = smp_core99_take_timebase, -}; - #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PPC32) -int __cpu_disable(void) +int smp_core99_cpu_disable(void) { cpu_clear(smp_processor_id(), cpu_online_map); @@ -846,7 +844,7 @@ void cpu_die(void) low_cpu_die(); } -void __cpu_die(unsigned int cpu) +void smp_core99_cpu_die(unsigned int cpu) { int timeout; @@ -858,8 +856,21 @@ void __cpu_die(unsigned int cpu) } msleep(1); } - cpu_callin_map[cpu] = 0; cpu_dead[cpu] = 0; } #endif + +/* Core99 Macs (dual G4s and G5s) */ +struct smp_ops_t core99_smp_ops = { + .message_pass = smp_mpic_message_pass, + .probe = smp_core99_probe, + .kick_cpu = smp_core99_kick_cpu, + .setup_cpu = smp_core99_setup_cpu, + .give_timebase = smp_core99_give_timebase, + .take_timebase = smp_core99_take_timebase, +#if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PPC32) + .cpu_disable = smp_core99_cpu_disable, + .cpu_die = smp_core99_cpu_die, +#endif +}; diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile index b9938fece78..e7ca5b1f591 100644 --- a/arch/powerpc/platforms/pseries/Makefile +++ b/arch/powerpc/platforms/pseries/Makefile @@ -3,3 +3,5 @@ obj-y := pci.o lpar.o hvCall.o nvram.o reconfig.o \ obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_IBMVIO) += vio.o obj-$(CONFIG_XICS) += xics.o +obj-$(CONFIG_SCANLOG) += scanlog.o +obj-$(CONFIG_EEH) += eeh.o eeh_event.o diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c new file mode 100644 index 00000000000..79de2310e70 --- /dev/null +++ b/arch/powerpc/platforms/pseries/eeh.c @@ -0,0 +1,1212 @@ +/* + * eeh.c + * Copyright (C) 2001 Dave Engebretsen & Todd Inglett IBM Corporation + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program 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 General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include <linux/delay.h> +#include <linux/init.h> +#include <linux/list.h> +#include <linux/pci.h> +#include <linux/proc_fs.h> +#include <linux/rbtree.h> +#include <linux/seq_file.h> +#include <linux/spinlock.h> +#include <asm/atomic.h> +#include <asm/eeh.h> +#include <asm/eeh_event.h> +#include <asm/io.h> +#include <asm/machdep.h> +#include <asm/ppc-pci.h> +#include <asm/rtas.h> + +#undef DEBUG + +/** Overview: + * EEH, or "Extended Error Handling" is a PCI bridge technology for + * dealing with PCI bus errors that can't be dealt with within the + * usual PCI framework, except by check-stopping the CPU. Systems + * that are designed for high-availability/reliability cannot afford + * to crash due to a "mere" PCI error, thus the need for EEH. + * An EEH-capable bridge operates by converting a detected error + * into a "slot freeze", taking the PCI adapter off-line, making + * the slot behave, from the OS'es point of view, as if the slot + * were "empty": all reads return 0xff's and all writes are silently + * ignored. EEH slot isolation events can be triggered by parity + * errors on the address or data busses (e.g. during posted writes), + * which in turn might be caused by low voltage on the bus, dust, + * vibration, humidity, radioactivity or plain-old failed hardware. + * + * Note, however, that one of the leading causes of EEH slot + * freeze events are buggy device drivers, buggy device microcode, + * or buggy device hardware. This is because any attempt by the + * device to bus-master data to a memory address that is not + * assigned to the device will trigger a slot freeze. (The idea + * is to prevent devices-gone-wild from corrupting system memory). + * Buggy hardware/drivers will have a miserable time co-existing + * with EEH. + * + * Ideally, a PCI device driver, when suspecting that an isolation + * event has occured (e.g. by reading 0xff's), will then ask EEH + * whether this is the case, and then take appropriate steps to + * reset the PCI slot, the PCI device, and then resume operations. + * However, until that day, the checking is done here, with the + * eeh_check_failure() routine embedded in the MMIO macros. If + * the slot is found to be isolated, an "EEH Event" is synthesized + * and sent out for processing. + */ + +/* If a device driver keeps reading an MMIO register in an interrupt + * handler after a slot isolation event has occurred, we assume it + * is broken and panic. This sets the threshold for how many read + * attempts we allow before panicking. + */ +#define EEH_MAX_FAILS 100000 + +/* Misc forward declaraions */ +static void eeh_save_bars(struct pci_dev * pdev, struct pci_dn *pdn); + +/* RTAS tokens */ +static int ibm_set_eeh_option; +static int ibm_set_slot_reset; +static int ibm_read_slot_reset_state; +static int ibm_read_slot_reset_state2; +static int ibm_slot_error_detail; + +static int eeh_subsystem_enabled; + +/* Lock to avoid races due to multiple reports of an error */ +static DEFINE_SPINLOCK(confirm_error_lock); + +/* Buffer for reporting slot-error-detail rtas calls */ +static unsigned char slot_errbuf[RTAS_ERROR_LOG_MAX]; +static DEFINE_SPINLOCK(slot_errbuf_lock); +static int eeh_error_buf_size; + +/* System monitoring statistics */ +static DEFINE_PER_CPU(unsigned long, no_device); +static DEFINE_PER_CPU(unsigned long, no_dn); +static DEFINE_PER_CPU(unsigned long, no_cfg_addr); +static DEFINE_PER_CPU(unsigned long, ignored_check); +static DEFINE_PER_CPU(unsigned long, total_mmio_ffs); +static DEFINE_PER_CPU(unsigned long, false_positives); +static DEFINE_PER_CPU(unsigned long, ignored_failures); +static DEFINE_PER_CPU(unsigned long, slot_resets); + +/** + * The pci address cache subsystem. This subsystem places + * PCI device address resources into a red-black tree, sorted + * according to the address range, so that given only an i/o + * address, the corresponding PCI device can be **quickly** + * found. It is safe to perform an address lookup in an interrupt + * context; this ability is an important feature. + * + * Currently, the only customer of this code is the EEH subsystem; + * thus, this code has been somewhat tailored to suit EEH better. + * In particular, the cache does *not* hold the addresses of devices + * for which EEH is not enabled. + * + * (Implementation Note: The RB tree seems to be better/faster + * than any hash algo I could think of for this problem, even + * with the penalty of slow pointer chases for d-cache misses). + */ +struct pci_io_addr_range +{ + struct rb_node rb_node; + unsigned long addr_lo; + unsigned long addr_hi; + struct pci_dev *pcidev; + unsigned int flags; +}; + +static struct pci_io_addr_cache +{ + struct rb_root rb_root; + spinlock_t piar_lock; +} pci_io_addr_cache_root; + +static inline struct pci_dev *__pci_get_device_by_addr(unsigned long addr) +{ + struct rb_node *n = pci_io_addr_cache_root.rb_root.rb_node; + + while (n) { + struct pci_io_addr_range *piar; + piar = rb_entry(n, struct pci_io_addr_range, rb_node); + + if (addr < piar->addr_lo) { + n = n->rb_left; + } else { + if (addr > piar->addr_hi) { + n = n->rb_right; + } else { + pci_dev_get(piar->pcidev); + return piar->pcidev; + } + } + } + + return NULL; +} + +/** + * pci_get_device_by_addr - Get device, given only address + * @addr: mmio (PIO) phys address or i/o port number + * + * Given an mmio phys address, or a port number, find a pci device + * that implements this address. Be sure to pci_dev_put the device + * when finished. I/O port numbers are assumed to be offset + * from zero (that is, they do *not* have pci_io_addr added in). + * It is safe to call this function within an interrupt. + */ +static struct pci_dev *pci_get_device_by_addr(unsigned long addr) +{ + struct pci_dev *dev; + unsigned long flags; + + spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags); + dev = __pci_get_device_by_addr(addr); + spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags); + return dev; +} + +#ifdef DEBUG +/* + * Handy-dandy debug print routine, does nothing more + * than print out the contents of our addr cache. + */ +static void pci_addr_cache_print(struct pci_io_addr_cache *cache) +{ + struct rb_node *n; + int cnt = 0; + + n = rb_first(&cache->rb_root); + while (n) { + struct pci_io_addr_range *piar; + piar = rb_entry(n, struct pci_io_addr_range, rb_node); + printk(KERN_DEBUG "PCI: %s addr range %d [%lx-%lx]: %s\n", + (piar->flags & IORESOURCE_IO) ? "i/o" : "mem", cnt, + piar->addr_lo, piar->addr_hi, pci_name(piar->pcidev)); + cnt++; + n = rb_next(n); + } +} +#endif + +/* Insert address range into the rb tree. */ +static struct pci_io_addr_range * +pci_addr_cache_insert(struct pci_dev *dev, unsigned long alo, + unsigned long ahi, unsigned int flags) +{ + struct rb_node **p = &pci_io_addr_cache_root.rb_root.rb_node; + struct rb_node *parent = NULL; + struct pci_io_addr_range *piar; + + /* Walk tree, find a place to insert into tree */ + while (*p) { + parent = *p; + piar = rb_entry(parent, struct pci_io_addr_range, rb_node); + if (ahi < piar->addr_lo) { + p = &parent->rb_left; + } else if (alo > piar->addr_hi) { + p = &parent->rb_right; + } else { + if (dev != piar->pcidev || + alo != piar->addr_lo || ahi != piar->addr_hi) { + printk(KERN_WARNING "PIAR: overlapping address range\n"); + } + return piar; + } + } + piar = (struct pci_io_addr_range *)kmalloc(sizeof(struct pci_io_addr_range), GFP_ATOMIC); + if (!piar) + return NULL; + + piar->addr_lo = alo; + piar->addr_hi = ahi; + piar->pcidev = dev; + piar->flags = flags; + +#ifdef DEBUG + printk(KERN_DEBUG "PIAR: insert range=[%lx:%lx] dev=%s\n", + alo, ahi, pci_name (dev)); +#endif + + rb_link_node(&piar->rb_node, parent, p); + rb_insert_color(&piar->rb_node, &pci_io_addr_cache_root.rb_root); + + return piar; +} + +static void __pci_addr_cache_insert_device(struct pci_dev *dev) +{ + struct device_node *dn; + struct pci_dn *pdn; + int i; + int inserted = 0; + + dn = pci_device_to_OF_node(dev); + if (!dn) { + printk(KERN_WARNING "PCI: no pci dn found for dev=%s\n", pci_name(dev)); + return; + } + + /* Skip any devices for which EEH is not enabled. */ + pdn = PCI_DN(dn); + if (!(pdn->eeh_mode & EEH_MODE_SUPPORTED) || + pdn->eeh_mode & EEH_MODE_NOCHECK) { +#ifdef DEBUG + printk(KERN_INFO "PCI: skip building address cache for=%s - %s\n", + pci_name(dev), pdn->node->full_name); +#endif + return; + } + + /* The cache holds a reference to the device... */ + pci_dev_get(dev); + + /* Walk resources on this device, poke them into the tree */ + for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) { + unsigned long start = pci_resource_start(dev,i); + unsigned long end = pci_resource_end(dev,i); + unsigned int flags = pci_resource_flags(dev,i); + + /* We are interested only bus addresses, not dma or other stuff */ + if (0 == (flags & (IORESOURCE_IO | IORESOURCE_MEM))) + continue; + if (start == 0 || ~start == 0 || end == 0 || ~end == 0) + continue; + pci_addr_cache_insert(dev, start, end, flags); + inserted = 1; + } + + /* If there was nothing to add, the cache has no reference... */ + if (!inserted) + pci_dev_put(dev); +} + +/** + * pci_addr_cache_insert_device - Add a device to the address cache + * @dev: PCI device whose I/O addresses we are interested in. + * + * In order to support the fast lookup of devices based on addresses, + * we maintain a cache of devices that can be quickly searched. + * This routine adds a device to that cache. + */ +static void pci_addr_cache_insert_device(struct pci_dev *dev) +{ + unsigned long flags; + + spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags); + __pci_addr_cache_insert_device(dev); + spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags); +} + +static inline void __pci_addr_cache_remove_device(struct pci_dev *dev) +{ + struct rb_node *n; + int removed = 0; + +restart: + n = rb_first(&pci_io_addr_cache_root.rb_root); + while (n) { + struct pci_io_addr_range *piar; + piar = rb_entry(n, struct pci_io_addr_range, rb_node); + + if (piar->pcidev == dev) { + rb_erase(n, &pci_io_addr_cache_root.rb_root); + removed = 1; + kfree(piar); + goto restart; + } + n = rb_next(n); + } + + /* The cache no longer holds its reference to this device... */ + if (removed) + pci_dev_put(dev); +} + +/** + * pci_addr_cache_remove_device - remove pci device from addr cache + * @dev: device to remove + * + * Remove a device from the addr-cache tree. + * This is potentially expensive, since it will walk + * the tree multiple times (once per resource). + * But so what; device removal doesn't need to be that fast. + */ +static void pci_addr_cache_remove_device(struct pci_dev *dev) +{ + unsigned long flags; + + spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags); + __pci_addr_cache_remove_device(dev); + spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags); +} + +/** + * pci_addr_cache_build - Build a cache of I/O addresses + * + * Build a cache of pci i/o addresses. This cache will be used to + * find the pci device that corresponds to a given address. + * This routine scans all pci busses to build the cache. + * Must be run late in boot process, after the pci controllers + * have been scaned for devices (after all device resources are known). + */ +void __init pci_addr_cache_build(void) +{ + struct device_node *dn; + struct pci_dev *dev = NULL; + + if (!eeh_subsystem_enabled) + return; + + spin_lock_init(&pci_io_addr_cache_root.piar_lock); + + while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) { + /* Ignore PCI bridges ( XXX why ??) */ + if ((dev->class >> 16) == PCI_BASE_CLASS_BRIDGE) { + continue; + } + pci_addr_cache_insert_device(dev); + + /* Save the BAR's; firmware doesn't restore these after EEH reset */ + dn = pci_device_to_OF_node(dev); + eeh_save_bars(dev, PCI_DN(dn)); + } + +#ifdef DEBUG + /* Verify tree built up above, echo back the list of addrs. */ + pci_addr_cache_print(&pci_io_addr_cache_root); +#endif +} + +/* --------------------------------------------------------------- */ +/* Above lies the PCI Address Cache. Below lies the EEH event infrastructure */ + +void eeh_slot_error_detail (struct pci_dn *pdn, int severity) +{ + unsigned long flags; + int rc; + + /* Log the error with the rtas logger */ + spin_lock_irqsave(&slot_errbuf_lock, flags); + memset(slot_errbuf, 0, eeh_error_buf_size); + + rc = rtas_call(ibm_slot_error_detail, + 8, 1, NULL, pdn->eeh_config_addr, + BUID_HI(pdn->phb->buid), + BUID_LO(pdn->phb->buid), NULL, 0, + virt_to_phys(slot_errbuf), + eeh_error_buf_size, + severity); + + if (rc == 0) + log_error(slot_errbuf, ERR_TYPE_RTAS_LOG, 0); + spin_unlock_irqrestore(&slot_errbuf_lock, flags); +} + +/** + * read_slot_reset_state - Read the reset state of a device node's slot + * @dn: device node to read + * @rets: array to return results in + */ +static int read_slot_reset_state(struct pci_dn *pdn, int rets[]) +{ + int token, outputs; + + if (ibm_read_slot_reset_state2 != RTAS_UNKNOWN_SERVICE) { + token = ibm_read_slot_reset_state2; + outputs = 4; + } else { + token = ibm_read_slot_reset_state; + rets[2] = 0; /* fake PE Unavailable info */ + outputs = 3; + } + + return rtas_call(token, 3, outputs, rets, pdn->eeh_config_addr, + BUID_HI(pdn->phb->buid), BUID_LO(pdn->phb->buid)); +} + +/** + * eeh_token_to_phys - convert EEH address token to phys address + * @token i/o token, should be address in the form 0xA.... + */ +static inline unsigned long eeh_token_to_phys(unsigned long token) +{ + pte_t *ptep; + unsigned long pa; + + ptep = find_linux_pte(init_mm.pgd, token); + if (!ptep) + return token; + pa = pte_pfn(*ptep) << PAGE_SHIFT; + + return pa | (token & (PAGE_SIZE-1)); +} + +/** + * Return the "partitionable endpoint" (pe) under which this device lies + */ +static struct device_node * find_device_pe(struct device_node *dn) +{ + while ((dn->parent) && PCI_DN(dn->parent) && + (PCI_DN(dn->parent)->eeh_mode & EEH_MODE_SUPPORTED)) { + dn = dn->parent; + } + return dn; +} + +/** Mark all devices that are peers of this device as failed. + * Mark the device driver too, so that it can see the failure + * immediately; this is critical, since some drivers poll + * status registers in interrupts ... If a driver is polling, + * and the slot is frozen, then the driver can deadlock in + * an interrupt context, which is bad. + */ + +static void __eeh_mark_slot (struct device_node *dn, int mode_flag) +{ + while (dn) { + if (PCI_DN(dn)) { + PCI_DN(dn)->eeh_mode |= mode_flag; + + if (dn->child) + __eeh_mark_slot (dn->child, mode_flag); + } + dn = dn->sibling; + } +} + +void eeh_mark_slot (struct device_node *dn, int mode_flag) +{ + dn = find_device_pe (dn); + PCI_DN(dn)->eeh_mode |= mode_flag; + __eeh_mark_slot (dn->child, mode_flag); +} + +static void __eeh_clear_slot (struct device_node *dn, int mode_flag) +{ + while (dn) { + if (PCI_DN(dn)) { + PCI_DN(dn)->eeh_mode &= ~mode_flag; + PCI_DN(dn)->eeh_check_count = 0; + if (dn->child) + __eeh_clear_slot (dn->child, mode_flag); + } + dn = dn->sibling; + } +} + +void eeh_clear_slot (struct device_node *dn, int mode_flag) +{ + unsigned long flags; + spin_lock_irqsave(&confirm_error_lock, flags); + dn = find_device_pe (dn); + PCI_DN(dn)->eeh_mode &= ~mode_flag; + PCI_DN(dn)->eeh_check_count = 0; + __eeh_clear_slot (dn->child, mode_flag); + spin_unlock_irqrestore(&confirm_error_lock, flags); +} + +/** + * eeh_dn_check_failure - check if all 1's data is due to EEH slot freeze + * @dn device node + * @dev pci device, if known + * + * Check for an EEH failure for the given device node. Call this + * routine if the result of a read was all 0xff's and you want to + * find out if this is due to an EEH slot freeze. This routine + * will query firmware for the EEH status. + * + * Returns 0 if there has not been an EEH error; otherwise returns + * a non-zero value and queues up a slot isolation event notification. + * + * It is safe to call this routine in an interrupt context. + */ +int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev) +{ + int ret; + int rets[3]; + unsigned long flags; + struct pci_dn *pdn; + int rc = 0; + + __get_cpu_var(total_mmio_ffs)++; + + if (!eeh_subsystem_enabled) + return 0; + + if (!dn) { + __get_cpu_var(no_dn)++; + return 0; + } + pdn = PCI_DN(dn); + + /* Access to IO BARs might get this far and still not want checking. */ + if (!(pdn->eeh_mode & EEH_MODE_SUPPORTED) || + pdn->eeh_mode & EEH_MODE_NOCHECK) { + __get_cpu_var(ignored_check)++; +#ifdef DEBUG + printk ("EEH:ignored check (%x) for %s %s\n", + pdn->eeh_mode, pci_name (dev), dn->full_name); +#endif + return 0; + } + + if (!pdn->eeh_config_addr) { + __get_cpu_var(no_cfg_addr)++; + return 0; + } + + /* If we already have a pending isolation event for this + * slot, we know it's bad already, we don't need to check. + * Do this checking under a lock; as multiple PCI devices + * in one slot might report errors simultaneously, and we + * only want one error recovery routine running. + */ + spin_lock_irqsave(&confirm_error_lock, flags); + rc = 1; + if (pdn->eeh_mode & EEH_MODE_ISOLATED) { + pdn->eeh_check_count ++; + if (pdn->eeh_check_count >= EEH_MAX_FAILS) { + printk (KERN_ERR "EEH: Device driver ignored %d bad reads, panicing\n", + pdn->eeh_check_count); + dump_stack(); + + /* re-read the slot reset state */ + if (read_slot_reset_state(pdn, rets) != 0) + rets[0] = -1; /* reset state unknown */ + + /* If we are here, then we hit an infinite loop. Stop. */ + panic("EEH: MMIO halt (%d) on device:%s\n", rets[0], pci_name(dev)); + } + goto dn_unlock; + } + + /* + * Now test for an EEH failure. This is VERY expensive. + * Note that the eeh_config_addr may be a parent device + * in the case of a device behind a bridge, or it may be + * function zero of a multi-function device. + * In any case they must share a common PHB. + */ + ret = read_slot_reset_state(pdn, rets); + + /* If the call to firmware failed, punt */ + if (ret != 0) { + printk(KERN_WARNING "EEH: read_slot_reset_state() failed; rc=%d dn=%s\n", + ret, dn->full_name); + __get_cpu_var(false_positives)++; + rc = 0; + goto dn_unlock; + } + + /* If EEH is not supported on this device, punt. */ + if (rets[1] != 1) { + printk(KERN_WARNING "EEH: event on unsupported device, rc=%d dn=%s\n", + ret, dn->full_name); + __get_cpu_var(false_positives)++; + rc = 0; + goto dn_unlock; + } + + /* If not the kind of error we know about, punt. */ + if (rets[0] != 2 && rets[0] != 4 && rets[0] != 5) { + __get_cpu_var(false_positives)++; + rc = 0; + goto dn_unlock; + } + + /* Note that config-io to empty slots may fail; + * we recognize empty because they don't have children. */ + if ((rets[0] == 5) && (dn->child == NULL)) { + __get_cpu_var(false_positives)++; + rc = 0; + goto dn_unlock; + } + + __get_cpu_var(slot_resets)++; + + /* Avoid repeated reports of this failure, including problems + * with other functions on this device, and functions under + * bridges. */ + eeh_mark_slot (dn, EEH_MODE_ISOLATED); + spin_unlock_irqrestore(&confirm_error_lock, flags); + + eeh_send_failure_event (dn, dev, rets[0], rets[2]); + + /* Most EEH events are due to device driver bugs. Having + * a stack trace will help the device-driver authors figure + * out what happened. So print that out. */ + if (rets[0] != 5) dump_stack(); + return 1; + +dn_unlock: + spin_unlock_irqrestore(&confirm_error_lock, flags); + return rc; +} + +EXPORT_SYMBOL_GPL(eeh_dn_check_failure); + +/** + * eeh_check_failure - check if all 1's data is due to EEH slot freeze + * @token i/o token, should be address in the form 0xA.... + * @val value, should be all 1's (XXX why do we need this arg??) + * + * Check for an EEH failure at the given token address. Call this + * routine if the result of a read was all 0xff's and you want to + * find out if this is due to an EEH slot freeze event. This routine + * will query firmware for the EEH status. + * + * Note this routine is safe to call in an interrupt context. + */ +unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned long val) +{ + unsigned long addr; + struct pci_dev *dev; + struct device_node *dn; + + /* Finding the phys addr + pci device; this is pretty quick. */ + addr = eeh_token_to_phys((unsigned long __force) token); + dev = pci_get_device_by_addr(addr); + if (!dev) { + __get_cpu_var(no_device)++; + return val; + } + + dn = pci_device_to_OF_node(dev); + eeh_dn_check_failure (dn, dev); + + pci_dev_put(dev); + return val; +} + +EXPORT_SYMBOL(eeh_check_failure); + +/* ------------------------------------------------------------- */ +/* The code below deals with error recovery */ + +/** Return negative value if a permanent error, else return + * a number of milliseconds to wait until the PCI slot is + * ready to be used. + */ +static int +eeh_slot_availability(struct pci_dn *pdn) +{ + int rc; + int rets[3]; + + rc = read_slot_reset_state(pdn, rets); + + if (rc) return rc; + + if (rets[1] == 0) return -1; /* EEH is not supported */ + if (rets[0] == 0) return 0; /* Oll Korrect */ + if (rets[0] == 5) { + if (rets[2] == 0) return -1; /* permanently unavailable */ + return rets[2]; /* number of millisecs to wait */ + } + return -1; +} + +/** rtas_pci_slot_reset raises/lowers the pci #RST line + * state: 1/0 to raise/lower the #RST + * + * Clear the EEH-frozen condition on a slot. This routine + * asserts the PCI #RST line if the 'state' argument is '1', + * and drops the #RST line if 'state is '0'. This routine is + * safe to call in an interrupt context. + * + */ + +static void +rtas_pci_slot_reset(struct pci_dn *pdn, int state) +{ + int rc; + + BUG_ON (pdn==NULL); + + if (!pdn->phb) { + printk (KERN_WARNING "EEH: in slot reset, device node %s has no phb\n", + pdn->node->full_name); + return; + } + + rc = rtas_call(ibm_set_slot_reset,4,1, NULL, + pdn->eeh_config_addr, + BUID_HI(pdn->phb->buid), + BUID_LO(pdn->phb->buid), + state); + if (rc) { + printk (KERN_WARNING "EEH: Unable to reset the failed slot, (%d) #RST=%d dn=%s\n", + rc, state, pdn->node->full_name); + return; + } +} + +/** rtas_set_slot_reset -- assert the pci #RST line for 1/4 second + * dn -- device node to be reset. + */ + +void +rtas_set_slot_reset(struct pci_dn *pdn) +{ + int i, rc; + + rtas_pci_slot_reset (pdn, 1); + + /* The PCI bus requires that the reset be held high for at least + * a 100 milliseconds. We wait a bit longer 'just in case'. */ + +#define PCI_BUS_RST_HOLD_TIME_MSEC 250 + msleep (PCI_BUS_RST_HOLD_TIME_MSEC); + + /* We might get hit with another EEH freeze as soon as the + * pci slot reset line is dropped. Make sure we don't miss + * these, and clear the flag now. */ + eeh_clear_slot (pdn->node, EEH_MODE_ISOLATED); + + rtas_pci_slot_reset (pdn, 0); + + /* After a PCI slot has been reset, the PCI Express spec requires + * a 1.5 second idle time for the bus to stabilize, before starting + * up traffic. */ +#define PCI_BUS_SETTLE_TIME_MSEC 1800 + msleep (PCI_BUS_SETTLE_TIME_MSEC); + + /* Now double check with the firmware to make sure the device is + * ready to be used; if not, wait for recovery. */ + for (i=0; i<10; i++) { + rc = eeh_slot_availability (pdn); + if (rc <= 0) break; + + msleep (rc+100); + } +} + +/* ------------------------------------------------------- */ +/** Save and restore of PCI BARs + * + * Although firmware will set up BARs during boot, it doesn't + * set up device BAR's after a device reset, although it will, + * if requested, set up bridge configuration. Thus, we need to + * configure the PCI devices ourselves. + */ + +/** + * __restore_bars - Restore the Base Address Registers + * Loads the PCI configuration space base address registers, + * the expansion ROM base address, the latency timer, and etc. + * from the saved values in the device node. + */ +static inline void __restore_bars (struct pci_dn *pdn) +{ + int i; + + if (NULL==pdn->phb) return; + for (i=4; i<10; i++) { + rtas_write_config(pdn, i*4, 4, pdn->config_space[i]); + } + + /* 12 == Expansion ROM Address */ + rtas_write_config(pdn, 12*4, 4, pdn->config_space[12]); + +#define BYTE_SWAP(OFF) (8*((OFF)/4)+3-(OFF)) +#define SAVED_BYTE(OFF) (((u8 *)(pdn->config_space))[BYTE_SWAP(OFF)]) + + rtas_write_config (pdn, PCI_CACHE_LINE_SIZE, 1, + SAVED_BYTE(PCI_CACHE_LINE_SIZE)); + + rtas_write_config (pdn, PCI_LATENCY_TIMER, 1, + SAVED_BYTE(PCI_LATENCY_TIMER)); + + /* max latency, min grant, interrupt pin and line */ + rtas_write_config(pdn, 15*4, 4, pdn->config_space[15]); +} + +/** + * eeh_restore_bars - restore the PCI config space info + * + * This routine performs a recursive walk to the children + * of this device as well. + */ +void eeh_restore_bars(struct pci_dn *pdn) +{ + struct device_node *dn; + if (!pdn) + return; + + if (! pdn->eeh_is_bridge) + __restore_bars (pdn); + + dn = pdn->node->child; + while (dn) { + eeh_restore_bars (PCI_DN(dn)); + dn = dn->sibling; + } +} + +/** + * eeh_save_bars - save device bars + * + * Save the values of the device bars. Unlike the restore + * routine, this routine is *not* recursive. This is because + * PCI devices are added individuallly; but, for the restore, + * an entire slot is reset at a time. + */ +static void eeh_save_bars(struct pci_dev * pdev, struct pci_dn *pdn) +{ + int i; + + if (!pdev || !pdn ) + return; + + for (i = 0; i < 16; i++) + pci_read_config_dword(pdev, i * 4, &pdn->config_space[i]); + + if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE) + pdn->eeh_is_bridge = 1; +} + +void +rtas_configure_bridge(struct pci_dn *pdn) +{ + int token = rtas_token ("ibm,configure-bridge"); + int rc; + + if (token == RTAS_UNKNOWN_SERVICE) + return; + rc = rtas_call(token,3,1, NULL, + pdn->eeh_config_addr, + BUID_HI(pdn->phb->buid), + BUID_LO(pdn->phb->buid)); + if (rc) { + printk (KERN_WARNING "EEH: Unable to configure device bridge (%d) for %s\n", + rc, pdn->node->full_name); + } +} + +/* ------------------------------------------------------------- */ +/* The code below deals with enabling EEH for devices during the + * early boot sequence. EEH must be enabled before any PCI probing + * can be done. + */ + +#define EEH_ENABLE 1 + +struct eeh_early_enable_info { + unsigned int buid_hi; + unsigned int buid_lo; +}; + +/* Enable eeh for the given device node. */ +static void *early_enable_eeh(struct device_node *dn, void *data) +{ + struct eeh_early_enable_info *info = data; + int ret; + char *status = get_property(dn, "status", NULL); + u32 *class_code = (u32 *)get_property(dn, "class-code", NULL); + u32 *vendor_id = (u32 *)get_property(dn, "vendor-id", NULL); + u32 *device_id = (u32 *)get_property(dn, "device-id", NULL); + u32 *regs; + int enable; + struct pci_dn *pdn = PCI_DN(dn); + + pdn->eeh_mode = 0; + pdn->eeh_check_count = 0; + pdn->eeh_freeze_count = 0; + + if (status && strcmp(status, "ok") != 0) + return NULL; /* ignore devices with bad status */ + + /* Ignore bad nodes. */ + if (!class_code || !vendor_id || !device_id) + return NULL; + + /* There is nothing to check on PCI to ISA bridges */ + if (dn->type && !strcmp(dn->type, "isa")) { + pdn->eeh_mode |= EEH_MODE_NOCHECK; + return NULL; + } + + /* + * Now decide if we are going to "Disable" EEH checking + * for this device. We still run with the EEH hardware active, + * but we won't be checking for ff's. This means a driver + * could return bad data (very bad!), an interrupt handler could + * hang waiting on status bits that won't change, etc. + * But there are a few cases like display devices that make sense. + */ + enable = 1; /* i.e. we will do checking */ + if ((*class_code >> 16) == PCI_BASE_CLASS_DISPLAY) + enable = 0; + + if (!enable) + pdn->eeh_mode |= EEH_MODE_NOCHECK; + + /* Ok... see if this device supports EEH. Some do, some don't, + * and the only way to find out is to check each and every one. */ + regs = (u32 *)get_property(dn, "reg", NULL); + if (regs) { + /* First register entry is addr (00BBSS00) */ + /* Try to enable eeh */ + ret = rtas_call(ibm_set_eeh_option, 4, 1, NULL, + regs[0], info->buid_hi, info->buid_lo, + EEH_ENABLE); + + if (ret == 0) { + eeh_subsystem_enabled = 1; + pdn->eeh_mode |= EEH_MODE_SUPPORTED; + pdn->eeh_config_addr = regs[0]; +#ifdef DEBUG + printk(KERN_DEBUG "EEH: %s: eeh enabled\n", dn->full_name); +#endif + } else { + + /* This device doesn't support EEH, but it may have an + * EEH parent, in which case we mark it as supported. */ + if (dn->parent && PCI_DN(dn->parent) + && (PCI_DN(dn->parent)->eeh_mode & EEH_MODE_SUPPORTED)) { + /* Parent supports EEH. */ + pdn->eeh_mode |= EEH_MODE_SUPPORTED; + pdn->eeh_config_addr = PCI_DN(dn->parent)->eeh_config_addr; + return NULL; + } + } + } else { + printk(KERN_WARNING "EEH: %s: unable to get reg property.\n", + dn->full_name); + } + + return NULL; +} + +/* + * Initialize EEH by trying to enable it for all of the adapters in the system. + * As a side effect we can determine here if eeh is supported at all. + * Note that we leave EEH on so failed config cycles won't cause a machine + * check. If a user turns off EEH for a particular adapter they are really + * telling Linux to ignore errors. Some hardware (e.g. POWER5) won't + * grant access to a slot if EEH isn't enabled, and so we always enable + * EEH for all slots/all devices. + * + * The eeh-force-off option disables EEH checking globally, for all slots. + * Even if force-off is set, the EEH hardware is still enabled, so that + * newer systems can boot. + */ +void __init eeh_init(void) +{ + struct device_node *phb, *np; + struct eeh_early_enable_info info; + + spin_lock_init(&confirm_error_lock); + spin_lock_init(&slot_errbuf_lock); + + np = of_find_node_by_path("/rtas"); + if (np == NULL) + return; + + ibm_set_eeh_option = rtas_token("ibm,set-eeh-option"); + ibm_set_slot_reset = rtas_token("ibm,set-slot-reset"); + ibm_read_slot_reset_state2 = rtas_token("ibm,read-slot-reset-state2"); + ibm_read_slot_reset_state = rtas_token("ibm,read-slot-reset-state"); + ibm_slot_error_detail = rtas_token("ibm,slot-error-detail"); + + if (ibm_set_eeh_option == RTAS_UNKNOWN_SERVICE) + return; + + eeh_error_buf_size = rtas_token("rtas-error-log-max"); + if (eeh_error_buf_size == RTAS_UNKNOWN_SERVICE) { + eeh_error_buf_size = 1024; + } + if (eeh_error_buf_size > RTAS_ERROR_LOG_MAX) { + printk(KERN_WARNING "EEH: rtas-error-log-max is bigger than allocated " + "buffer ! (%d vs %d)", eeh_error_buf_size, RTAS_ERROR_LOG_MAX); + eeh_error_buf_size = RTAS_ERROR_LOG_MAX; + } + + /* Enable EEH for all adapters. Note that eeh requires buid's */ + for (phb = of_find_node_by_name(NULL, "pci"); phb; + phb = of_find_node_by_name(phb, "pci")) { + unsigned long buid; + + buid = get_phb_buid(phb); + if (buid == 0 || PCI_DN(phb) == NULL) + continue; + + info.buid_lo = BUID_LO(buid); + info.buid_hi = BUID_HI(buid); + traverse_pci_devices(phb, early_enable_eeh, &info); + } + + if (eeh_subsystem_enabled) + printk(KERN_INFO "EEH: PCI Enhanced I/O Error Handling Enabled\n"); + else + printk(KERN_WARNING "EEH: No capable adapters found\n"); +} + +/** + * eeh_add_device_early - enable EEH for the indicated device_node + * @dn: device node for which to set up EEH + * + * This routine must be used to perform EEH initialization for PCI + * devices that were added after system boot (e.g. hotplug, dlpar). + * This routine must be called before any i/o is performed to the + * adapter (inluding any config-space i/o). + * Whether this actually enables EEH or not for this device depends + * on the CEC architecture, type of the device, on earlier boot + * command-line arguments & etc. + */ +void eeh_add_device_early(struct device_node *dn) +{ + struct pci_controller *phb; + struct eeh_early_enable_info info; + + if (!dn || !PCI_DN(dn)) + return; + phb = PCI_DN(dn)->phb; + if (NULL == phb || 0 == phb->buid) { + printk(KERN_WARNING "EEH: Expected buid but found none for %s\n", + dn->full_name); + dump_stack(); + return; + } + + info.buid_hi = BUID_HI(phb->buid); + info.buid_lo = BUID_LO(phb->buid); + early_enable_eeh(dn, &info); +} +EXPORT_SYMBOL_GPL(eeh_add_device_early); + +/** + * eeh_add_device_late - perform EEH initialization for the indicated pci device + * @dev: pci device for which to set up EEH + * + * This routine must be used to complete EEH initialization for PCI + * devices that were added after system boot (e.g. hotplug, dlpar). + */ +void eeh_add_device_late(struct pci_dev *dev) +{ + struct device_node *dn; + struct pci_dn *pdn; + + if (!dev || !eeh_subsystem_enabled) + return; + +#ifdef DEBUG + printk(KERN_DEBUG "EEH: adding device %s\n", pci_name(dev)); +#endif + + pci_dev_get (dev); + dn = pci_device_to_OF_node(dev); + pdn = PCI_DN(dn); + pdn->pcidev = dev; + + pci_addr_cache_insert_device (dev); + eeh_save_bars(dev, pdn); +} +EXPORT_SYMBOL_GPL(eeh_add_device_late); + +/** + * eeh_remove_device - undo EEH setup for the indicated pci device + * @dev: pci device to be removed + * + * This routine should be when a device is removed from a running + * system (e.g. by hotplug or dlpar). + */ +void eeh_remove_device(struct pci_dev *dev) +{ + struct device_node *dn; + if (!dev || !eeh_subsystem_enabled) + return; + + /* Unregister the device with the EEH/PCI address search system */ +#ifdef DEBUG + printk(KERN_DEBUG "EEH: remove device %s\n", pci_name(dev)); +#endif + pci_addr_cache_remove_device(dev); + + dn = pci_device_to_OF_node(dev); + PCI_DN(dn)->pcidev = NULL; + pci_dev_put (dev); +} +EXPORT_SYMBOL_GPL(eeh_remove_device); + +static int proc_eeh_show(struct seq_file *m, void *v) +{ + unsigned int cpu; + unsigned long ffs = 0, positives = 0, failures = 0; + unsigned long resets = 0; + unsigned long no_dev = 0, no_dn = 0, no_cfg = 0, no_check = 0; + + for_each_cpu(cpu) { + ffs += per_cpu(total_mmio_ffs, cpu); + positives += per_cpu(false_positives, cpu); + failures += per_cpu(ignored_failures, cpu); + resets += per_cpu(slot_resets, cpu); + no_dev += per_cpu(no_device, cpu); + no_dn += per_cpu(no_dn, cpu); + no_cfg += per_cpu(no_cfg_addr, cpu); + no_check += per_cpu(ignored_check, cpu); + } + + if (0 == eeh_subsystem_enabled) { + seq_printf(m, "EEH Subsystem is globally disabled\n"); + seq_printf(m, "eeh_total_mmio_ffs=%ld\n", ffs); + } else { + seq_printf(m, "EEH Subsystem is enabled\n"); + seq_printf(m, + "no device=%ld\n" + "no device node=%ld\n" + "no config address=%ld\n" + "check not wanted=%ld\n" + "eeh_total_mmio_ffs=%ld\n" + "eeh_false_positives=%ld\n" + "eeh_ignored_failures=%ld\n" + "eeh_slot_resets=%ld\n", + no_dev, no_dn, no_cfg, no_check, + ffs, positives, failures, resets); + } + + return 0; +} + +static int proc_eeh_open(struct inode *inode, struct file *file) +{ + return single_open(file, proc_eeh_show, NULL); +} + +static struct file_operations proc_eeh_operations = { + .open = proc_eeh_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init eeh_init_proc(void) +{ + struct proc_dir_entry *e; + + if (platform_is_pseries()) { + e = create_proc_entry("ppc64/eeh", 0, NULL); + if (e) + e->proc_fops = &proc_eeh_operations; + } + + return 0; +} +__initcall(eeh_init_proc); diff --git a/arch/powerpc/platforms/pseries/eeh_event.c b/arch/powerpc/platforms/pseries/eeh_event.c new file mode 100644 index 00000000000..92497333c2b --- /dev/null +++ b/arch/powerpc/platforms/pseries/eeh_event.c @@ -0,0 +1,155 @@ +/* + * eeh_event.c + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program 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 General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * Copyright (c) 2005 Linas Vepstas <linas@linas.org> + */ + +#include <linux/list.h> +#include <linux/pci.h> +#include <asm/eeh_event.h> + +/** Overview: + * EEH error states may be detected within exception handlers; + * however, the recovery processing needs to occur asynchronously + * in a normal kernel context and not an interrupt context. + * This pair of routines creates an event and queues it onto a + * work-queue, where a worker thread can drive recovery. + */ + +/* EEH event workqueue setup. */ +static spinlock_t eeh_eventlist_lock = SPIN_LOCK_UNLOCKED; +LIST_HEAD(eeh_eventlist); +static void eeh_thread_launcher(void *); +DECLARE_WORK(eeh_event_wq, eeh_thread_launcher, NULL); + +/** + * eeh_panic - call panic() for an eeh event that cannot be handled. + * The philosophy of this routine is that it is better to panic and + * halt the OS than it is to risk possible data corruption by + * oblivious device drivers that don't know better. + * + * @dev pci device that had an eeh event + * @reset_state current reset state of the device slot + */ +static void eeh_panic(struct pci_dev *dev, int reset_state) +{ + /* + * Since the panic_on_oops sysctl is used to halt the system + * in light of potential corruption, we can use it here. + */ + if (panic_on_oops) { + panic("EEH: MMIO failure (%d) on device:%s\n", reset_state, + pci_name(dev)); + } + else { + printk(KERN_INFO "EEH: Ignored MMIO failure (%d) on device:%s\n", + reset_state, pci_name(dev)); + } +} + +/** + * eeh_event_handler - dispatch EEH events. The detection of a frozen + * slot can occur inside an interrupt, where it can be hard to do + * anything about it. The goal of this routine is to pull these + * detection events out of the context of the interrupt handler, and + * re-dispatch them for processing at a later time in a normal context. + * + * @dummy - unused + */ +static int eeh_event_handler(void * dummy) +{ + unsigned long flags; + struct eeh_event *event; + + daemonize ("eehd"); + + while (1) { + set_current_state(TASK_INTERRUPTIBLE); + + spin_lock_irqsave(&eeh_eventlist_lock, flags); + event = NULL; + if (!list_empty(&eeh_eventlist)) { + event = list_entry(eeh_eventlist.next, struct eeh_event, list); + list_del(&event->list); + } + spin_unlock_irqrestore(&eeh_eventlist_lock, flags); + if (event == NULL) + break; + + printk(KERN_INFO "EEH: Detected PCI bus error on device %s\n", + pci_name(event->dev)); + + eeh_panic (event->dev, event->state); + + kfree(event); + } + + return 0; +} + +/** + * eeh_thread_launcher + * + * @dummy - unused + */ +static void eeh_thread_launcher(void *dummy) +{ + if (kernel_thread(eeh_event_handler, NULL, CLONE_KERNEL) < 0) + printk(KERN_ERR "Failed to start EEH daemon\n"); +} + +/** + * eeh_send_failure_event - generate a PCI error event + * @dev pci device + * + * This routine can be called within an interrupt context; + * the actual event will be delivered in a normal context + * (from a workqueue). + */ +int eeh_send_failure_event (struct device_node *dn, + struct pci_dev *dev, + int state, + int time_unavail) +{ + unsigned long flags; + struct eeh_event *event; + + event = kmalloc(sizeof(*event), GFP_ATOMIC); + if (event == NULL) { + printk (KERN_ERR "EEH: out of memory, event not handled\n"); + return 1; + } + + if (dev) + pci_dev_get(dev); + + event->dn = dn; + event->dev = dev; + event->state = state; + event->time_unavail = time_unavail; + + /* We may or may not be called in an interrupt context */ + spin_lock_irqsave(&eeh_eventlist_lock, flags); + list_add(&event->list, &eeh_eventlist); + spin_unlock_irqrestore(&eeh_eventlist_lock, flags); + + schedule_work(&eeh_event_wq); + + return 0; +} + +/********************** END OF FILE ******************************/ diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index fcc50bfd43f..97ba5214417 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -42,7 +42,6 @@ #include <asm/machdep.h> #include <asm/abs_addr.h> #include <asm/pSeries_reconfig.h> -#include <asm/systemcfg.h> #include <asm/firmware.h> #include <asm/tce.h> #include <asm/ppc-pci.h> @@ -582,7 +581,7 @@ void iommu_init_early_pSeries(void) return; } - if (systemcfg->platform & PLATFORM_LPAR) { + if (platform_is_lpar()) { if (firmware_has_feature(FW_FEATURE_MULTITCE)) { ppc_md.tce_build = tce_buildmulti_pSeriesLP; ppc_md.tce_free = tce_freemulti_pSeriesLP; diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c index c198656a3bb..999a9620b5c 100644 --- a/arch/powerpc/platforms/pseries/pci.c +++ b/arch/powerpc/platforms/pseries/pci.c @@ -107,7 +107,6 @@ static void __init pSeries_request_regions(void) void __init pSeries_final_fixup(void) { - phbs_remap_io(); pSeries_request_regions(); pci_addr_cache_build(); @@ -123,7 +122,7 @@ static void fixup_winbond_82c105(struct pci_dev* dev) int i; unsigned int reg; - if (!(systemcfg->platform & PLATFORM_PSERIES)) + if (!platform_is_pseries()) return; printk("Using INTC for W82c105 IDE controller.\n"); diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c index d7d40033945..d8864164dbe 100644 --- a/arch/powerpc/platforms/pseries/reconfig.c +++ b/arch/powerpc/platforms/pseries/reconfig.c @@ -408,7 +408,7 @@ static int proc_ppc64_create_ofdt(void) { struct proc_dir_entry *ent; - if (!(systemcfg->platform & PLATFORM_PSERIES)) + if (!platform_is_pseries()) return 0; ent = create_proc_entry("ppc64/ofdt", S_IWUSR, NULL); diff --git a/arch/powerpc/platforms/pseries/rtasd.c b/arch/powerpc/platforms/pseries/rtasd.c index e26b0420b6d..a6f628d4c9d 100644 --- a/arch/powerpc/platforms/pseries/rtasd.c +++ b/arch/powerpc/platforms/pseries/rtasd.c @@ -27,7 +27,6 @@ #include <asm/prom.h> #include <asm/nvram.h> #include <asm/atomic.h> -#include <asm/systemcfg.h> #if 0 #define DEBUG(A...) printk(KERN_ERR A) @@ -482,10 +481,12 @@ static int __init rtas_init(void) { struct proc_dir_entry *entry; - /* No RTAS, only warn if we are on a pSeries box */ + if (!platform_is_pseries()) + return 0; + + /* No RTAS */ if (rtas_token("event-scan") == RTAS_UNKNOWN_SERVICE) { - if (systemcfg->platform & PLATFORM_PSERIES) - printk(KERN_INFO "rtasd: no event-scan on system\n"); + printk(KERN_INFO "rtasd: no event-scan on system\n"); return 1; } diff --git a/arch/powerpc/platforms/pseries/scanlog.c b/arch/powerpc/platforms/pseries/scanlog.c new file mode 100644 index 00000000000..2edc947f7c4 --- /dev/null +++ b/arch/powerpc/platforms/pseries/scanlog.c @@ -0,0 +1,235 @@ +/* + * c 2001 PPC 64 Team, IBM Corp + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * scan-log-data driver for PPC64 Todd Inglett <tinglett@vnet.ibm.com> + * + * When ppc64 hardware fails the service processor dumps internal state + * of the system. After a reboot the operating system can access a dump + * of this data using this driver. A dump exists if the device-tree + * /chosen/ibm,scan-log-data property exists. + * + * This driver exports /proc/ppc64/scan-log-dump which can be read. + * The driver supports only sequential reads. + * + * The driver looks at a write to the driver for the single word "reset". + * If given, the driver will reset the scanlog so the platform can free it. + */ + +#include <linux/module.h> +#include <linux/types.h> +#include <linux/errno.h> +#include <linux/proc_fs.h> +#include <linux/init.h> +#include <linux/delay.h> +#include <asm/uaccess.h> +#include <asm/rtas.h> +#include <asm/prom.h> + +#define MODULE_VERS "1.0" +#define MODULE_NAME "scanlog" + +/* Status returns from ibm,scan-log-dump */ +#define SCANLOG_COMPLETE 0 +#define SCANLOG_HWERROR -1 +#define SCANLOG_CONTINUE 1 + +#define DEBUG(A...) do { if (scanlog_debug) printk(KERN_ERR "scanlog: " A); } while (0) + +static int scanlog_debug; +static unsigned int ibm_scan_log_dump; /* RTAS token */ +static struct proc_dir_entry *proc_ppc64_scan_log_dump; /* The proc file */ + +static ssize_t scanlog_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct inode * inode = file->f_dentry->d_inode; + struct proc_dir_entry *dp; + unsigned int *data; + int status; + unsigned long len, off; + unsigned int wait_time; + + dp = PDE(inode); + data = (unsigned int *)dp->data; + + if (!data) { + printk(KERN_ERR "scanlog: read failed no data\n"); + return -EIO; + } + + if (count > RTAS_DATA_BUF_SIZE) + count = RTAS_DATA_BUF_SIZE; + + if (count < 1024) { + /* This is the min supported by this RTAS call. Rather + * than do all the buffering we insist the user code handle + * larger reads. As long as cp works... :) + */ + printk(KERN_ERR "scanlog: cannot perform a small read (%ld)\n", count); + return -EINVAL; + } + + if (!access_ok(VERIFY_WRITE, buf, count)) + return -EFAULT; + + for (;;) { + wait_time = 500; /* default wait if no data */ + spin_lock(&rtas_data_buf_lock); + memcpy(rtas_data_buf, data, RTAS_DATA_BUF_SIZE); + status = rtas_call(ibm_scan_log_dump, 2, 1, NULL, + (u32) __pa(rtas_data_buf), (u32) count); + memcpy(data, rtas_data_buf, RTAS_DATA_BUF_SIZE); + spin_unlock(&rtas_data_buf_lock); + + DEBUG("status=%d, data[0]=%x, data[1]=%x, data[2]=%x\n", + status, data[0], data[1], data[2]); + switch (status) { + case SCANLOG_COMPLETE: + DEBUG("hit eof\n"); + return 0; + case SCANLOG_HWERROR: + DEBUG("hardware error reading scan log data\n"); + return -EIO; + case SCANLOG_CONTINUE: + /* We may or may not have data yet */ + len = data[1]; + off = data[2]; + if (len > 0) { + if (copy_to_user(buf, ((char *)data)+off, len)) + return -EFAULT; + return len; + } + /* Break to sleep default time */ + break; + default: + if (status > 9900 && status <= 9905) { + wait_time = rtas_extended_busy_delay_time(status); + } else { + printk(KERN_ERR "scanlog: unknown error from rtas: %d\n", status); + return -EIO; + } + } + /* Apparently no data yet. Wait and try again. */ + msleep_interruptible(wait_time); + } + /*NOTREACHED*/ +} + +static ssize_t scanlog_write(struct file * file, const char __user * buf, + size_t count, loff_t *ppos) +{ + char stkbuf[20]; + int status; + + if (count > 19) count = 19; + if (copy_from_user (stkbuf, buf, count)) { + return -EFAULT; + } + stkbuf[count] = 0; + + if (buf) { + if (strncmp(stkbuf, "reset", 5) == 0) { + DEBUG("reset scanlog\n"); + status = rtas_call(ibm_scan_log_dump, 2, 1, NULL, 0, 0); + DEBUG("rtas returns %d\n", status); + } else if (strncmp(stkbuf, "debugon", 7) == 0) { + printk(KERN_ERR "scanlog: debug on\n"); + scanlog_debug = 1; + } else if (strncmp(stkbuf, "debugoff", 8) == 0) { + printk(KERN_ERR "scanlog: debug off\n"); + scanlog_debug = 0; + } + } + return count; +} + +static int scanlog_open(struct inode * inode, struct file * file) +{ + struct proc_dir_entry *dp = PDE(inode); + unsigned int *data = (unsigned int *)dp->data; + + if (!data) { + printk(KERN_ERR "scanlog: open failed no data\n"); + return -EIO; + } + + if (data[0] != 0) { + /* This imperfect test stops a second copy of the + * data (or a reset while data is being copied) + */ + return -EBUSY; + } + + data[0] = 0; /* re-init so we restart the scan */ + + return 0; +} + +static int scanlog_release(struct inode * inode, struct file * file) +{ + struct proc_dir_entry *dp = PDE(inode); + unsigned int *data = (unsigned int *)dp->data; + + if (!data) { + printk(KERN_ERR "scanlog: release failed no data\n"); + return -EIO; + } + data[0] = 0; + + return 0; +} + +struct file_operations scanlog_fops = { + .owner = THIS_MODULE, + .read = scanlog_read, + .write = scanlog_write, + .open = scanlog_open, + .release = scanlog_release, +}; + +int __init scanlog_init(void) +{ + struct proc_dir_entry *ent; + + ibm_scan_log_dump = rtas_token("ibm,scan-log-dump"); + if (ibm_scan_log_dump == RTAS_UNKNOWN_SERVICE) { + printk(KERN_ERR "scan-log-dump not implemented on this system\n"); + return -EIO; + } + + ent = create_proc_entry("ppc64/rtas/scan-log-dump", S_IRUSR, NULL); + if (ent) { + ent->proc_fops = &scanlog_fops; + /* Ideally we could allocate a buffer < 4G */ + ent->data = kmalloc(RTAS_DATA_BUF_SIZE, GFP_KERNEL); + if (!ent->data) { + printk(KERN_ERR "Failed to allocate a buffer\n"); + remove_proc_entry("scan-log-dump", ent->parent); + return -ENOMEM; + } + ((unsigned int *)ent->data)[0] = 0; + } else { + printk(KERN_ERR "Failed to create ppc64/scan-log-dump proc entry\n"); + return -EIO; + } + proc_ppc64_scan_log_dump = ent; + + return 0; +} + +void __exit scanlog_cleanup(void) +{ + if (proc_ppc64_scan_log_dump) { + kfree(proc_ppc64_scan_log_dump->data); + remove_proc_entry("scan-log-dump", proc_ppc64_scan_log_dump->parent); + } +} + +module_init(scanlog_init); +module_exit(scanlog_cleanup); +MODULE_LICENSE("GPL"); diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index e78c3936884..31990829310 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -249,7 +249,7 @@ static void __init pSeries_setup_arch(void) ppc_md.idle_loop = default_idle; } - if (systemcfg->platform & PLATFORM_LPAR) + if (platform_is_lpar()) ppc_md.enable_pmcs = pseries_lpar_enable_pmcs; else ppc_md.enable_pmcs = power4_enable_pmcs; @@ -306,9 +306,7 @@ static void __init fw_feature_init(void) } of_node_put(dn); - no_rtas: - printk(KERN_INFO "firmware_features = 0x%lx\n", - ppc64_firmware_features); +no_rtas: DBG(" <- fw_feature_init()\n"); } @@ -378,7 +376,7 @@ static void __init pSeries_init_early(void) fw_feature_init(); - if (systemcfg->platform & PLATFORM_LPAR) + if (platform_is_lpar()) hpte_init_lpar(); else { hpte_init_native(); @@ -388,7 +386,7 @@ static void __init pSeries_init_early(void) generic_find_legacy_serial_ports(&physport, &default_speed); - if (systemcfg->platform & PLATFORM_LPAR) + if (platform_is_lpar()) find_udbg_vterm(); else if (physport) { /* Map the uart for udbg. */ @@ -469,6 +467,7 @@ static inline void dedicated_idle_sleep(unsigned int cpu) * more. */ clear_thread_flag(TIF_POLLING_NRFLAG); + smp_mb__after_clear_bit(); /* * SMT dynamic mode. Cede will result in this thread going @@ -481,6 +480,7 @@ static inline void dedicated_idle_sleep(unsigned int cpu) cede_processor(); else local_irq_enable(); + set_thread_flag(TIF_POLLING_NRFLAG); } else { /* * Give the HV an opportunity at the processor, since we are @@ -492,11 +492,11 @@ static inline void dedicated_idle_sleep(unsigned int cpu) static void pseries_dedicated_idle(void) { - long oldval; struct paca_struct *lpaca = get_paca(); unsigned int cpu = smp_processor_id(); unsigned long start_snooze; unsigned long *smt_snooze_delay = &__get_cpu_var(smt_snooze_delay); + set_thread_flag(TIF_POLLING_NRFLAG); while (1) { /* @@ -505,10 +505,7 @@ static void pseries_dedicated_idle(void) */ lpaca->lppaca.idle = 1; - oldval = test_and_clear_thread_flag(TIF_NEED_RESCHED); - if (!oldval) { - set_thread_flag(TIF_POLLING_NRFLAG); - + if (!need_resched()) { start_snooze = __get_tb() + *smt_snooze_delay * tb_ticks_per_usec; @@ -531,15 +528,14 @@ static void pseries_dedicated_idle(void) } HMT_medium(); - clear_thread_flag(TIF_POLLING_NRFLAG); - } else { - set_need_resched(); } lpaca->lppaca.idle = 0; ppc64_runlatch_on(); + preempt_enable_no_resched(); schedule(); + preempt_disable(); if (cpu_is_offline(cpu) && system_state == SYSTEM_RUNNING) cpu_die(); @@ -583,7 +579,9 @@ static void pseries_shared_idle(void) lpaca->lppaca.idle = 0; ppc64_runlatch_on(); + preempt_enable_no_resched(); schedule(); + preempt_disable(); if (cpu_is_offline(cpu) && system_state == SYSTEM_RUNNING) cpu_die(); @@ -592,7 +590,7 @@ static void pseries_shared_idle(void) static int pSeries_pci_probe_mode(struct pci_bus *bus) { - if (systemcfg->platform & PLATFORM_LPAR) + if (platform_is_lpar()) return PCI_PROBE_DEVTREE; return PCI_PROBE_NORMAL; } diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c index 7a243e8ccd7..5800cde7d5a 100644 --- a/arch/powerpc/platforms/pseries/smp.c +++ b/arch/powerpc/platforms/pseries/smp.c @@ -46,6 +46,7 @@ #include <asm/rtas.h> #include <asm/pSeries_reconfig.h> #include <asm/mpic.h> +#include <asm/vdso_datapage.h> #include "plpar_wrappers.h" @@ -96,7 +97,7 @@ int pSeries_cpu_disable(void) int cpu = smp_processor_id(); cpu_clear(cpu, cpu_online_map); - systemcfg->processorCount--; + vdso_data->processorCount--; /*fix boot_cpuid here*/ if (cpu == boot_cpuid) @@ -441,7 +442,7 @@ void __init smp_init_pSeries(void) smp_ops->cpu_die = pSeries_cpu_die; /* Processors can be added/removed only on LPAR */ - if (systemcfg->platform == PLATFORM_PSERIES_LPAR) + if (platform_is_lpar()) pSeries_reconfig_notifier_register(&pSeries_smp_nb); #endif diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c index c72c86f05cb..72ac18067ec 100644 --- a/arch/powerpc/platforms/pseries/xics.c +++ b/arch/powerpc/platforms/pseries/xics.c @@ -545,7 +545,9 @@ nextnode: of_node_put(np); } - if (systemcfg->platform == PLATFORM_PSERIES) { + if (platform_is_lpar()) + ops = &pSeriesLP_ops; + else { #ifdef CONFIG_SMP for_each_cpu(i) { int hard_id; @@ -561,12 +563,11 @@ nextnode: #else xics_per_cpu[0] = ioremap(intr_base, intr_size); #endif /* CONFIG_SMP */ - } else if (systemcfg->platform == PLATFORM_PSERIES_LPAR) { - ops = &pSeriesLP_ops; } xics_8259_pic.enable = i8259_pic.enable; xics_8259_pic.disable = i8259_pic.disable; + xics_8259_pic.end = i8259_pic.end; for (i = 0; i < 16; ++i) get_irq_desc(i)->handler = &xics_8259_pic; for (; i < NR_IRQS; ++i) diff --git a/arch/powerpc/sysdev/u3_iommu.c b/arch/powerpc/sysdev/u3_iommu.c index 543d6590981..f32baf7f469 100644 --- a/arch/powerpc/sysdev/u3_iommu.c +++ b/arch/powerpc/sysdev/u3_iommu.c @@ -226,7 +226,7 @@ static void iommu_table_u3_setup(void) iommu_table_u3.it_busno = 0; iommu_table_u3.it_offset = 0; /* it_size is in number of entries */ - iommu_table_u3.it_size = dart_tablesize / sizeof(u32); + iommu_table_u3.it_size = (dart_tablesize / sizeof(u32)) >> DART_PAGE_FACTOR; /* Initialize the common IOMMU code */ iommu_table_u3.it_base = (unsigned long)dart_vbase; diff --git a/arch/powerpc/xmon/Makefile b/arch/powerpc/xmon/Makefile index 79a784f0e7a..b20312e5ed2 100644 --- a/arch/powerpc/xmon/Makefile +++ b/arch/powerpc/xmon/Makefile @@ -8,4 +8,4 @@ obj-$(CONFIG_8xx) += start_8xx.o obj-$(CONFIG_6xx) += start_32.o obj-$(CONFIG_4xx) += start_32.o obj-$(CONFIG_PPC64) += start_64.o -obj-y += xmon.o ppc-dis.o ppc-opc.o subr_prf.o setjmp.o +obj-y += xmon.o ppc-dis.o ppc-opc.o setjmp.o nonstdio.o diff --git a/arch/powerpc/xmon/nonstdio.c b/arch/powerpc/xmon/nonstdio.c new file mode 100644 index 00000000000..78765833f4c --- /dev/null +++ b/arch/powerpc/xmon/nonstdio.c @@ -0,0 +1,134 @@ +/* + * Copyright (C) 1996-2005 Paul Mackerras. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include <linux/string.h> +#include <asm/time.h> +#include "nonstdio.h" + +int xmon_putchar(int c) +{ + char ch = c; + + if (c == '\n') + xmon_putchar('\r'); + return xmon_write(&ch, 1) == 1? c: -1; +} + +static char line[256]; +static char *lineptr; +static int lineleft; + +int xmon_expect(const char *str, unsigned long timeout) +{ + int c; + unsigned long t0; + + /* assume 25MHz default timebase if tb_ticks_per_sec not set yet */ + timeout *= tb_ticks_per_sec? tb_ticks_per_sec: 25000000; + t0 = get_tbl(); + do { + lineptr = line; + for (;;) { + c = xmon_read_poll(); + if (c == -1) { + if (get_tbl() - t0 > timeout) + return 0; + continue; + } + if (c == '\n') + break; + if (c != '\r' && lineptr < &line[sizeof(line) - 1]) + *lineptr++ = c; + } + *lineptr = 0; + } while (strstr(line, str) == NULL); + return 1; +} + +int xmon_getchar(void) +{ + int c; + + if (lineleft == 0) { + lineptr = line; + for (;;) { + c = xmon_readchar(); + if (c == -1 || c == 4) + break; + if (c == '\r' || c == '\n') { + *lineptr++ = '\n'; + xmon_putchar('\n'); + break; + } + switch (c) { + case 0177: + case '\b': + if (lineptr > line) { + xmon_putchar('\b'); + xmon_putchar(' '); + xmon_putchar('\b'); + --lineptr; + } + break; + case 'U' & 0x1F: + while (lineptr > line) { + xmon_putchar('\b'); + xmon_putchar(' '); + xmon_putchar('\b'); + --lineptr; + } + break; + default: + if (lineptr >= &line[sizeof(line) - 1]) + xmon_putchar('\a'); + else { + xmon_putchar(c); + *lineptr++ = c; + } + } + } + lineleft = lineptr - line; + lineptr = line; + } + if (lineleft == 0) + return -1; + --lineleft; + return *lineptr++; +} + +char *xmon_gets(char *str, int nb) +{ + char *p; + int c; + + for (p = str; p < str + nb - 1; ) { + c = xmon_getchar(); + if (c == -1) { + if (p == str) + return NULL; + break; + } + *p++ = c; + if (c == '\n') + break; + } + *p = 0; + return str; +} + +void xmon_printf(const char *format, ...) +{ + va_list args; + int n; + static char xmon_outbuf[1024]; + + va_start(args, format); + n = vsnprintf(xmon_outbuf, sizeof(xmon_outbuf), format, args); + va_end(args); + xmon_write(xmon_outbuf, n); +} diff --git a/arch/powerpc/xmon/nonstdio.h b/arch/powerpc/xmon/nonstdio.h index 84211a21c6f..47cebbd2b1b 100644 --- a/arch/powerpc/xmon/nonstdio.h +++ b/arch/powerpc/xmon/nonstdio.h @@ -1,22 +1,14 @@ -typedef int FILE; -extern FILE *xmon_stdin, *xmon_stdout; #define EOF (-1) -#define stdin xmon_stdin -#define stdout xmon_stdout + #define printf xmon_printf -#define fprintf xmon_fprintf -#define fputs xmon_fputs -#define fgets xmon_fgets #define putchar xmon_putchar -#define getchar xmon_getchar -#define putc xmon_putc -#define getc xmon_getc -#define fopen(n, m) NULL -#define fflush(f) do {} while (0) -#define fclose(f) do {} while (0) -extern char *fgets(char *, int, void *); -extern void xmon_printf(const char *, ...); -extern void xmon_fprintf(void *, const char *, ...); -extern void xmon_sprintf(char *, const char *, ...); -#define perror(s) printf("%s: no files!\n", (s)) +extern int xmon_putchar(int c); +extern int xmon_getchar(void); +extern char *xmon_gets(char *, int); +extern void xmon_printf(const char *, ...); +extern void xmon_map_scc(void); +extern int xmon_expect(const char *str, unsigned long timeout); +extern int xmon_write(void *ptr, int nb); +extern int xmon_readchar(void); +extern int xmon_read_poll(void); diff --git a/arch/powerpc/xmon/setjmp.S b/arch/powerpc/xmon/setjmp.S index f8e40dfd2bf..96a91f10e2e 100644 --- a/arch/powerpc/xmon/setjmp.S +++ b/arch/powerpc/xmon/setjmp.S @@ -14,61 +14,61 @@ _GLOBAL(xmon_setjmp) mflr r0 - STL r0,0(r3) - STL r1,SZL(r3) - STL r2,2*SZL(r3) + PPC_STL r0,0(r3) + PPC_STL r1,SZL(r3) + PPC_STL r2,2*SZL(r3) mfcr r0 - STL r0,3*SZL(r3) - STL r13,4*SZL(r3) - STL r14,5*SZL(r3) - STL r15,6*SZL(r3) - STL r16,7*SZL(r3) - STL r17,8*SZL(r3) - STL r18,9*SZL(r3) - STL r19,10*SZL(r3) - STL r20,11*SZL(r3) - STL r21,12*SZL(r3) - STL r22,13*SZL(r3) - STL r23,14*SZL(r3) - STL r24,15*SZL(r3) - STL r25,16*SZL(r3) - STL r26,17*SZL(r3) - STL r27,18*SZL(r3) - STL r28,19*SZL(r3) - STL r29,20*SZL(r3) - STL r30,21*SZL(r3) - STL r31,22*SZL(r3) + PPC_STL r0,3*SZL(r3) + PPC_STL r13,4*SZL(r3) + PPC_STL r14,5*SZL(r3) + PPC_STL r15,6*SZL(r3) + PPC_STL r16,7*SZL(r3) + PPC_STL r17,8*SZL(r3) + PPC_STL r18,9*SZL(r3) + PPC_STL r19,10*SZL(r3) + PPC_STL r20,11*SZL(r3) + PPC_STL r21,12*SZL(r3) + PPC_STL r22,13*SZL(r3) + PPC_STL r23,14*SZL(r3) + PPC_STL r24,15*SZL(r3) + PPC_STL r25,16*SZL(r3) + PPC_STL r26,17*SZL(r3) + PPC_STL r27,18*SZL(r3) + PPC_STL r28,19*SZL(r3) + PPC_STL r29,20*SZL(r3) + PPC_STL r30,21*SZL(r3) + PPC_STL r31,22*SZL(r3) li r3,0 blr _GLOBAL(xmon_longjmp) - CMPI r4,0 + PPC_LCMPI r4,0 bne 1f li r4,1 -1: LDL r13,4*SZL(r3) - LDL r14,5*SZL(r3) - LDL r15,6*SZL(r3) - LDL r16,7*SZL(r3) - LDL r17,8*SZL(r3) - LDL r18,9*SZL(r3) - LDL r19,10*SZL(r3) - LDL r20,11*SZL(r3) - LDL r21,12*SZL(r3) - LDL r22,13*SZL(r3) - LDL r23,14*SZL(r3) - LDL r24,15*SZL(r3) - LDL r25,16*SZL(r3) - LDL r26,17*SZL(r3) - LDL r27,18*SZL(r3) - LDL r28,19*SZL(r3) - LDL r29,20*SZL(r3) - LDL r30,21*SZL(r3) - LDL r31,22*SZL(r3) - LDL r0,3*SZL(r3) +1: PPC_LL r13,4*SZL(r3) + PPC_LL r14,5*SZL(r3) + PPC_LL r15,6*SZL(r3) + PPC_LL r16,7*SZL(r3) + PPC_LL r17,8*SZL(r3) + PPC_LL r18,9*SZL(r3) + PPC_LL r19,10*SZL(r3) + PPC_LL r20,11*SZL(r3) + PPC_LL r21,12*SZL(r3) + PPC_LL r22,13*SZL(r3) + PPC_LL r23,14*SZL(r3) + PPC_LL r24,15*SZL(r3) + PPC_LL r25,16*SZL(r3) + PPC_LL r26,17*SZL(r3) + PPC_LL r27,18*SZL(r3) + PPC_LL r28,19*SZL(r3) + PPC_LL r29,20*SZL(r3) + PPC_LL r30,21*SZL(r3) + PPC_LL r31,22*SZL(r3) + PPC_LL r0,3*SZL(r3) mtcrf 0x38,r0 - LDL r0,0(r3) - LDL r1,SZL(r3) - LDL r2,2*SZL(r3) + PPC_LL r0,0(r3) + PPC_LL r1,SZL(r3) + PPC_LL r2,2*SZL(r3) mtlr r0 mr r3,r4 blr @@ -84,52 +84,52 @@ _GLOBAL(xmon_longjmp) * different ABIs, though). */ _GLOBAL(xmon_save_regs) - STL r0,0*SZL(r3) - STL r2,2*SZL(r3) - STL r3,3*SZL(r3) - STL r4,4*SZL(r3) - STL r5,5*SZL(r3) - STL r6,6*SZL(r3) - STL r7,7*SZL(r3) - STL r8,8*SZL(r3) - STL r9,9*SZL(r3) - STL r10,10*SZL(r3) - STL r11,11*SZL(r3) - STL r12,12*SZL(r3) - STL r13,13*SZL(r3) - STL r14,14*SZL(r3) - STL r15,15*SZL(r3) - STL r16,16*SZL(r3) - STL r17,17*SZL(r3) - STL r18,18*SZL(r3) - STL r19,19*SZL(r3) - STL r20,20*SZL(r3) - STL r21,21*SZL(r3) - STL r22,22*SZL(r3) - STL r23,23*SZL(r3) - STL r24,24*SZL(r3) - STL r25,25*SZL(r3) - STL r26,26*SZL(r3) - STL r27,27*SZL(r3) - STL r28,28*SZL(r3) - STL r29,29*SZL(r3) - STL r30,30*SZL(r3) - STL r31,31*SZL(r3) + PPC_STL r0,0*SZL(r3) + PPC_STL r2,2*SZL(r3) + PPC_STL r3,3*SZL(r3) + PPC_STL r4,4*SZL(r3) + PPC_STL r5,5*SZL(r3) + PPC_STL r6,6*SZL(r3) + PPC_STL r7,7*SZL(r3) + PPC_STL r8,8*SZL(r3) + PPC_STL r9,9*SZL(r3) + PPC_STL r10,10*SZL(r3) + PPC_STL r11,11*SZL(r3) + PPC_STL r12,12*SZL(r3) + PPC_STL r13,13*SZL(r3) + PPC_STL r14,14*SZL(r3) + PPC_STL r15,15*SZL(r3) + PPC_STL r16,16*SZL(r3) + PPC_STL r17,17*SZL(r3) + PPC_STL r18,18*SZL(r3) + PPC_STL r19,19*SZL(r3) + PPC_STL r20,20*SZL(r3) + PPC_STL r21,21*SZL(r3) + PPC_STL r22,22*SZL(r3) + PPC_STL r23,23*SZL(r3) + PPC_STL r24,24*SZL(r3) + PPC_STL r25,25*SZL(r3) + PPC_STL r26,26*SZL(r3) + PPC_STL r27,27*SZL(r3) + PPC_STL r28,28*SZL(r3) + PPC_STL r29,29*SZL(r3) + PPC_STL r30,30*SZL(r3) + PPC_STL r31,31*SZL(r3) /* go up one stack frame for SP */ - LDL r4,0(r1) - STL r4,1*SZL(r3) + PPC_LL r4,0(r1) + PPC_STL r4,1*SZL(r3) /* get caller's LR */ - LDL r0,LRSAVE(r4) - STL r0,_NIP-STACK_FRAME_OVERHEAD(r3) - STL r0,_LINK-STACK_FRAME_OVERHEAD(r3) + PPC_LL r0,LRSAVE(r4) + PPC_STL r0,_NIP-STACK_FRAME_OVERHEAD(r3) + PPC_STL r0,_LINK-STACK_FRAME_OVERHEAD(r3) mfmsr r0 - STL r0,_MSR-STACK_FRAME_OVERHEAD(r3) + PPC_STL r0,_MSR-STACK_FRAME_OVERHEAD(r3) mfctr r0 - STL r0,_CTR-STACK_FRAME_OVERHEAD(r3) + PPC_STL r0,_CTR-STACK_FRAME_OVERHEAD(r3) mfxer r0 - STL r0,_XER-STACK_FRAME_OVERHEAD(r3) + PPC_STL r0,_XER-STACK_FRAME_OVERHEAD(r3) mfcr r0 - STL r0,_CCR-STACK_FRAME_OVERHEAD(r3) + PPC_STL r0,_CCR-STACK_FRAME_OVERHEAD(r3) li r0,0 - STL r0,_TRAP-STACK_FRAME_OVERHEAD(r3) + PPC_STL r0,_TRAP-STACK_FRAME_OVERHEAD(r3) blr diff --git a/arch/powerpc/xmon/start_32.c b/arch/powerpc/xmon/start_32.c index 69b658c0f76..c2464df4217 100644 --- a/arch/powerpc/xmon/start_32.c +++ b/arch/powerpc/xmon/start_32.c @@ -11,7 +11,6 @@ #include <linux/cuda.h> #include <linux/kernel.h> #include <linux/errno.h> -#include <linux/sysrq.h> #include <linux/bitops.h> #include <asm/xmon.h> #include <asm/prom.h> @@ -22,10 +21,11 @@ #include <asm/processor.h> #include <asm/delay.h> #include <asm/btext.h> +#include <asm/time.h> +#include "nonstdio.h" static volatile unsigned char __iomem *sccc, *sccd; unsigned int TXRDY, RXRDY, DLAB; -static int xmon_expect(const char *str, unsigned int timeout); static int use_serial; static int use_screen; @@ -33,16 +33,6 @@ static int via_modem; static int xmon_use_sccb; static struct device_node *channel_node; -#define TB_SPEED 25000000 - -static inline unsigned int readtb(void) -{ - unsigned int ret; - - asm volatile("mftb %0" : "=r" (ret) :); - return ret; -} - void buf_access(void) { if (DLAB) @@ -91,23 +81,7 @@ static unsigned long chrp_find_phys_io_base(void) } #endif /* CONFIG_PPC_CHRP */ -#ifdef CONFIG_MAGIC_SYSRQ -static void sysrq_handle_xmon(int key, struct pt_regs *regs, - struct tty_struct *tty) -{ - xmon(regs); -} - -static struct sysrq_key_op sysrq_xmon_op = -{ - .handler = sysrq_handle_xmon, - .help_msg = "Xmon", - .action_msg = "Entering xmon", -}; -#endif - -void -xmon_map_scc(void) +void xmon_map_scc(void) { #ifdef CONFIG_PPC_MULTIPLATFORM volatile unsigned char __iomem *base; @@ -217,8 +191,6 @@ xmon_map_scc(void) RXRDY = 1; DLAB = 0x80; #endif /* platform */ - - register_sysrq_key('x', &sysrq_xmon_op); } static int scc_initialized = 0; @@ -238,8 +210,7 @@ static inline void do_poll_adb(void) #endif /* CONFIG_ADB_CUDA */ } -int -xmon_write(void *handle, void *ptr, int nb) +int xmon_write(void *ptr, int nb) { char *p = ptr; int i, c, ct; @@ -311,8 +282,7 @@ static unsigned char xmon_shift_keytab[128] = "\0.\0*\0+\0\0\0\0\0/\r\0-\0" /* 0x40 - 0x4f */ "\0\0000123456789\0\0\0"; /* 0x50 - 0x5f */ -static int -xmon_get_adb_key(void) +static int xmon_get_adb_key(void) { int k, t, on; @@ -350,32 +320,21 @@ xmon_get_adb_key(void) } #endif /* CONFIG_BOOTX_TEXT */ -int -xmon_read(void *handle, void *ptr, int nb) +int xmon_readchar(void) { - char *p = ptr; - int i; - #ifdef CONFIG_BOOTX_TEXT - if (use_screen) { - for (i = 0; i < nb; ++i) - *p++ = xmon_get_adb_key(); - return i; - } + if (use_screen) + return xmon_get_adb_key(); #endif - if (!scc_initialized) - xmon_init_scc(); - for (i = 0; i < nb; ++i) { + if (!scc_initialized) + xmon_init_scc(); while ((*sccc & RXRDY) == 0) - do_poll_adb(); + do_poll_adb(); buf_access(); - *p++ = *sccd; - } - return i; + return *sccd; } -int -xmon_read_poll(void) +int xmon_read_poll(void) { if ((*sccc & RXRDY) == 0) { do_poll_adb(); @@ -395,8 +354,7 @@ static unsigned char scc_inittab[] = { 3, 0xc1, /* rx enable, 8 bits */ }; -void -xmon_init_scc(void) +void xmon_init_scc(void) { if ( _machine == _MACH_chrp ) { @@ -410,6 +368,7 @@ xmon_init_scc(void) else if ( _machine == _MACH_Pmac ) { int i, x; + unsigned long timeout; if (channel_node != 0) pmac_call_feature( @@ -424,8 +383,12 @@ xmon_init_scc(void) PMAC_FTR_MODEM_ENABLE, channel_node, 0, 1); printk(KERN_INFO "Modem powered up by debugger !\n"); - t0 = readtb(); - while (readtb() - t0 < 3*TB_SPEED) + t0 = get_tbl(); + timeout = 3 * tb_ticks_per_sec; + if (timeout == 0) + /* assume 25MHz if tb_ticks_per_sec not set */ + timeout = 75000000; + while (get_tbl() - t0 < timeout) eieio(); } /* use the B channel if requested */ @@ -447,164 +410,19 @@ xmon_init_scc(void) scc_initialized = 1; if (via_modem) { for (;;) { - xmon_write(NULL, "ATE1V1\r", 7); + xmon_write("ATE1V1\r", 7); if (xmon_expect("OK", 5)) { - xmon_write(NULL, "ATA\r", 4); + xmon_write("ATA\r", 4); if (xmon_expect("CONNECT", 40)) break; } - xmon_write(NULL, "+++", 3); + xmon_write("+++", 3); xmon_expect("OK", 3); } } } -void *xmon_stdin; -void *xmon_stdout; -void *xmon_stderr; - -int xmon_putc(int c, void *f) -{ - char ch = c; - - if (c == '\n') - xmon_putc('\r', f); - return xmon_write(f, &ch, 1) == 1? c: -1; -} - -int xmon_putchar(int c) -{ - return xmon_putc(c, xmon_stdout); -} - -int xmon_fputs(char *str, void *f) -{ - int n = strlen(str); - - return xmon_write(f, str, n) == n? 0: -1; -} - -int -xmon_readchar(void) -{ - char ch; - - for (;;) { - switch (xmon_read(xmon_stdin, &ch, 1)) { - case 1: - return ch; - case -1: - xmon_printf("read(stdin) returned -1\r\n", 0, 0); - return -1; - } - } -} - -static char line[256]; -static char *lineptr; -static int lineleft; - -int xmon_expect(const char *str, unsigned int timeout) -{ - int c; - unsigned int t0; - - timeout *= TB_SPEED; - t0 = readtb(); - do { - lineptr = line; - for (;;) { - c = xmon_read_poll(); - if (c == -1) { - if (readtb() - t0 > timeout) - return 0; - continue; - } - if (c == '\n') - break; - if (c != '\r' && lineptr < &line[sizeof(line) - 1]) - *lineptr++ = c; - } - *lineptr = 0; - } while (strstr(line, str) == NULL); - return 1; -} - -int -xmon_getchar(void) -{ - int c; - - if (lineleft == 0) { - lineptr = line; - for (;;) { - c = xmon_readchar(); - if (c == -1 || c == 4) - break; - if (c == '\r' || c == '\n') { - *lineptr++ = '\n'; - xmon_putchar('\n'); - break; - } - switch (c) { - case 0177: - case '\b': - if (lineptr > line) { - xmon_putchar('\b'); - xmon_putchar(' '); - xmon_putchar('\b'); - --lineptr; - } - break; - case 'U' & 0x1F: - while (lineptr > line) { - xmon_putchar('\b'); - xmon_putchar(' '); - xmon_putchar('\b'); - --lineptr; - } - break; - default: - if (lineptr >= &line[sizeof(line) - 1]) - xmon_putchar('\a'); - else { - xmon_putchar(c); - *lineptr++ = c; - } - } - } - lineleft = lineptr - line; - lineptr = line; - } - if (lineleft == 0) - return -1; - --lineleft; - return *lineptr++; -} - -char * -xmon_fgets(char *str, int nb, void *f) -{ - char *p; - int c; - - for (p = str; p < str + nb - 1; ) { - c = xmon_getchar(); - if (c == -1) { - if (p == str) - return NULL; - break; - } - *p++ = c; - if (c == '\n') - break; - } - *p = 0; - return str; -} - -void -xmon_enter(void) +void xmon_enter(void) { #ifdef CONFIG_ADB_PMU if (_machine == _MACH_Pmac) { @@ -613,8 +431,7 @@ xmon_enter(void) #endif } -void -xmon_leave(void) +void xmon_leave(void) { #ifdef CONFIG_ADB_PMU if (_machine == _MACH_Pmac) { diff --git a/arch/powerpc/xmon/start_64.c b/arch/powerpc/xmon/start_64.c index e50c158191e..712552c4f24 100644 --- a/arch/powerpc/xmon/start_64.c +++ b/arch/powerpc/xmon/start_64.c @@ -6,182 +6,29 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> -#include <linux/string.h> -#include <linux/kernel.h> -#include <linux/errno.h> -#include <linux/sysrq.h> -#include <linux/init.h> #include <asm/machdep.h> -#include <asm/io.h> -#include <asm/page.h> -#include <asm/prom.h> -#include <asm/processor.h> #include <asm/udbg.h> -#include <asm/system.h> #include "nonstdio.h" -#ifdef CONFIG_MAGIC_SYSRQ - -static void sysrq_handle_xmon(int key, struct pt_regs *pt_regs, - struct tty_struct *tty) -{ - /* ensure xmon is enabled */ - xmon_init(1); - debugger(pt_regs); -} - -static struct sysrq_key_op sysrq_xmon_op = +void xmon_map_scc(void) { - .handler = sysrq_handle_xmon, - .help_msg = "Xmon", - .action_msg = "Entering xmon", -}; - -static int __init setup_xmon_sysrq(void) -{ - register_sysrq_key('x', &sysrq_xmon_op); - return 0; } -__initcall(setup_xmon_sysrq); -#endif /* CONFIG_MAGIC_SYSRQ */ -int -xmon_write(void *handle, void *ptr, int nb) +int xmon_write(void *ptr, int nb) { return udbg_write(ptr, nb); } -int -xmon_read(void *handle, void *ptr, int nb) +int xmon_readchar(void) { - return udbg_read(ptr, nb); + if (udbg_getc) + return udbg_getc(); + return -1; } -int -xmon_read_poll(void) +int xmon_read_poll(void) { if (udbg_getc_poll) return udbg_getc_poll(); return -1; } - -FILE *xmon_stdin; -FILE *xmon_stdout; - -int -xmon_putc(int c, void *f) -{ - char ch = c; - - if (c == '\n') - xmon_putc('\r', f); - return xmon_write(f, &ch, 1) == 1? c: -1; -} - -int -xmon_putchar(int c) -{ - return xmon_putc(c, xmon_stdout); -} - -int -xmon_fputs(char *str, void *f) -{ - int n = strlen(str); - - return xmon_write(f, str, n) == n? 0: -1; -} - -int -xmon_readchar(void) -{ - char ch; - - for (;;) { - switch (xmon_read(xmon_stdin, &ch, 1)) { - case 1: - return ch; - case -1: - xmon_printf("read(stdin) returned -1\r\n", 0, 0); - return -1; - } - } -} - -static char line[256]; -static char *lineptr; -static int lineleft; - -int -xmon_getchar(void) -{ - int c; - - if (lineleft == 0) { - lineptr = line; - for (;;) { - c = xmon_readchar(); - if (c == -1 || c == 4) - break; - if (c == '\r' || c == '\n') { - *lineptr++ = '\n'; - xmon_putchar('\n'); - break; - } - switch (c) { - case 0177: - case '\b': - if (lineptr > line) { - xmon_putchar('\b'); - xmon_putchar(' '); - xmon_putchar('\b'); - --lineptr; - } - break; - case 'U' & 0x1F: - while (lineptr > line) { - xmon_putchar('\b'); - xmon_putchar(' '); - xmon_putchar('\b'); - --lineptr; - } - break; - default: - if (lineptr >= &line[sizeof(line) - 1]) - xmon_putchar('\a'); - else { - xmon_putchar(c); - *lineptr++ = c; - } - } - } - lineleft = lineptr - line; - lineptr = line; - } - if (lineleft == 0) - return -1; - --lineleft; - return *lineptr++; -} - -char * -xmon_fgets(char *str, int nb, void *f) -{ - char *p; - int c; - - for (p = str; p < str + nb - 1; ) { - c = xmon_getchar(); - if (c == -1) { - if (p == str) - return NULL; - break; - } - *p++ = c; - if (c == '\n') - break; - } - *p = 0; - return str; -} diff --git a/arch/powerpc/xmon/start_8xx.c b/arch/powerpc/xmon/start_8xx.c index a48bd594cf6..4c17b0486ad 100644 --- a/arch/powerpc/xmon/start_8xx.c +++ b/arch/powerpc/xmon/start_8xx.c @@ -15,273 +15,30 @@ #include <asm/8xx_immap.h> #include <asm/mpc8xx.h> #include <asm/commproc.h> +#include "nonstdio.h" -extern void xmon_printf(const char *fmt, ...); extern int xmon_8xx_write(char *str, int nb); extern int xmon_8xx_read_poll(void); extern int xmon_8xx_read_char(void); -void prom_drawhex(uint); -void prom_drawstring(const char *str); -static int use_screen = 1; /* default */ - -#define TB_SPEED 25000000 - -static inline unsigned int readtb(void) -{ - unsigned int ret; - - asm volatile("mftb %0" : "=r" (ret) :); - return ret; -} - -void buf_access(void) -{ -} - -void -xmon_map_scc(void) +void xmon_map_scc(void) { - cpmp = (cpm8xx_t *)&(((immap_t *)IMAP_ADDR)->im_cpm); - use_screen = 0; - - prom_drawstring("xmon uses serial port\n"); } -static int scc_initialized = 0; - void xmon_init_scc(void); -int -xmon_write(void *handle, void *ptr, int nb) +int xmon_write(void *ptr, int nb) { - char *p = ptr; - int i, c, ct; - - if (!scc_initialized) - xmon_init_scc(); - return(xmon_8xx_write(ptr, nb)); } -int xmon_wants_key; - -int -xmon_read(void *handle, void *ptr, int nb) +int xmon_readchar(void) { - char *p = ptr; - int i; - - if (!scc_initialized) - xmon_init_scc(); - - for (i = 0; i < nb; ++i) { - *p++ = xmon_8xx_read_char(); - } - return i; + return xmon_8xx_read_char(); } -int -xmon_read_poll(void) +int xmon_read_poll(void) { return(xmon_8xx_read_poll()); } - -void -xmon_init_scc() -{ - scc_initialized = 1; -} - -#if 0 -extern int (*prom_entry)(void *); - -int -xmon_exit(void) -{ - struct prom_args { - char *service; - } args; - - for (;;) { - args.service = "exit"; - (*prom_entry)(&args); - } -} -#endif - -void *xmon_stdin; -void *xmon_stdout; -void *xmon_stderr; - -void -xmon_init(void) -{ -} - -int -xmon_putc(int c, void *f) -{ - char ch = c; - - if (c == '\n') - xmon_putc('\r', f); - return xmon_write(f, &ch, 1) == 1? c: -1; -} - -int -xmon_putchar(int c) -{ - return xmon_putc(c, xmon_stdout); -} - -int -xmon_fputs(char *str, void *f) -{ - int n = strlen(str); - - return xmon_write(f, str, n) == n? 0: -1; -} - -int -xmon_readchar(void) -{ - char ch; - - for (;;) { - switch (xmon_read(xmon_stdin, &ch, 1)) { - case 1: - return ch; - case -1: - xmon_printf("read(stdin) returned -1\r\n", 0, 0); - return -1; - } - } -} - -static char line[256]; -static char *lineptr; -static int lineleft; - -#if 0 -int xmon_expect(const char *str, unsigned int timeout) -{ - int c; - unsigned int t0; - - timeout *= TB_SPEED; - t0 = readtb(); - do { - lineptr = line; - for (;;) { - c = xmon_read_poll(); - if (c == -1) { - if (readtb() - t0 > timeout) - return 0; - continue; - } - if (c == '\n') - break; - if (c != '\r' && lineptr < &line[sizeof(line) - 1]) - *lineptr++ = c; - } - *lineptr = 0; - } while (strstr(line, str) == NULL); - return 1; -} -#endif - -int -xmon_getchar(void) -{ - int c; - - if (lineleft == 0) { - lineptr = line; - for (;;) { - c = xmon_readchar(); - if (c == -1 || c == 4) - break; - if (c == '\r' || c == '\n') { - *lineptr++ = '\n'; - xmon_putchar('\n'); - break; - } - switch (c) { - case 0177: - case '\b': - if (lineptr > line) { - xmon_putchar('\b'); - xmon_putchar(' '); - xmon_putchar('\b'); - --lineptr; - } - break; - case 'U' & 0x1F: - while (lineptr > line) { - xmon_putchar('\b'); - xmon_putchar(' '); - xmon_putchar('\b'); - --lineptr; - } - break; - default: - if (lineptr >= &line[sizeof(line) - 1]) - xmon_putchar('\a'); - else { - xmon_putchar(c); - *lineptr++ = c; - } - } - } - lineleft = lineptr - line; - lineptr = line; - } - if (lineleft == 0) - return -1; - --lineleft; - return *lineptr++; -} - -char * -xmon_fgets(char *str, int nb, void *f) -{ - char *p; - int c; - - for (p = str; p < str + nb - 1; ) { - c = xmon_getchar(); - if (c == -1) { - if (p == str) - return 0; - break; - } - *p++ = c; - if (c == '\n') - break; - } - *p = 0; - return str; -} - -void -prom_drawhex(uint val) -{ - unsigned char buf[10]; - - int i; - for (i = 7; i >= 0; i--) - { - buf[i] = "0123456789abcdef"[val & 0x0f]; - val >>= 4; - } - buf[8] = '\0'; - xmon_fputs(buf, xmon_stdout); -} - -void -prom_drawstring(const char *str) -{ - xmon_fputs(str, xmon_stdout); -} diff --git a/arch/powerpc/xmon/subr_prf.c b/arch/powerpc/xmon/subr_prf.c deleted file mode 100644 index b48738c6dd3..00000000000 --- a/arch/powerpc/xmon/subr_prf.c +++ /dev/null @@ -1,54 +0,0 @@ -/* - * Written by Cort Dougan to replace the version originally used - * by Paul Mackerras, which came from NetBSD and thus had copyright - * conflicts with Linux. - * - * This file makes liberal use of the standard linux utility - * routines to reduce the size of the binary. We assume we can - * trust some parts of Linux inside the debugger. - * -- Cort (cort@cs.nmt.edu) - * - * Copyright (C) 1999 Cort Dougan. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/module.h> -#include <stdarg.h> -#include "nonstdio.h" - -extern int xmon_write(void *, void *, int); - -void xmon_vfprintf(void *f, const char *fmt, va_list ap) -{ - static char xmon_buf[2048]; - int n; - - n = vsprintf(xmon_buf, fmt, ap); - xmon_write(f, xmon_buf, n); -} - -void xmon_printf(const char *fmt, ...) -{ - va_list ap; - - va_start(ap, fmt); - xmon_vfprintf(stdout, fmt, ap); - va_end(ap); -} -EXPORT_SYMBOL(xmon_printf); - -void xmon_fprintf(void *f, const char *fmt, ...) -{ - va_list ap; - - va_start(ap, fmt); - xmon_vfprintf(f, fmt, ap); - va_end(ap); -} - diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 1124f114620..ef4356b29a9 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -1,7 +1,7 @@ /* * Routines providing a simple monitor for use on the PowerMac. * - * Copyright (C) 1996 Paul Mackerras. + * Copyright (C) 1996-2005 Paul Mackerras. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -18,6 +18,7 @@ #include <linux/kallsyms.h> #include <linux/cpumask.h> #include <linux/module.h> +#include <linux/sysrq.h> #include <asm/ptrace.h> #include <asm/string.h> @@ -144,15 +145,10 @@ static void xmon_print_symbol(unsigned long address, const char *mid, static const char *getvecname(unsigned long vec); extern int print_insn_powerpc(unsigned long, unsigned long, int); -extern void printf(const char *fmt, ...); -extern void xmon_vfprintf(void *f, const char *fmt, va_list ap); -extern int xmon_putc(int c, void *f); -extern int putchar(int ch); extern void xmon_enter(void); extern void xmon_leave(void); -extern int xmon_read_poll(void); extern long setjmp(long *); extern void longjmp(long *, long); extern void xmon_save_regs(struct pt_regs *); @@ -748,7 +744,6 @@ cmds(struct pt_regs *excp) printf("%x:", smp_processor_id()); #endif /* CONFIG_SMP */ printf("mon> "); - fflush(stdout); flush_input(); termch = 0; cmd = skipbl(); @@ -1472,17 +1467,23 @@ read_spr(int n) { unsigned int instrs[2]; unsigned long (*code)(void); - unsigned long opd[3]; unsigned long ret = -1UL; +#ifdef CONFIG_PPC64 + unsigned long opd[3]; - instrs[0] = 0x7c6002a6 + ((n & 0x1F) << 16) + ((n & 0x3e0) << 6); - instrs[1] = 0x4e800020; opd[0] = (unsigned long)instrs; opd[1] = 0; opd[2] = 0; + code = (unsigned long (*)(void)) opd; +#else + code = (unsigned long (*)(void)) instrs; +#endif + + /* mfspr r3,n; blr */ + instrs[0] = 0x7c6002a6 + ((n & 0x1F) << 16) + ((n & 0x3e0) << 6); + instrs[1] = 0x4e800020; store_inst(instrs); store_inst(instrs+1); - code = (unsigned long (*)(void)) opd; if (setjmp(bus_error_jmp) == 0) { catch_memory_errors = 1; @@ -1504,16 +1505,21 @@ write_spr(int n, unsigned long val) { unsigned int instrs[2]; unsigned long (*code)(unsigned long); +#ifdef CONFIG_PPC64 unsigned long opd[3]; - instrs[0] = 0x7c6003a6 + ((n & 0x1F) << 16) + ((n & 0x3e0) << 6); - instrs[1] = 0x4e800020; opd[0] = (unsigned long)instrs; opd[1] = 0; opd[2] = 0; + code = (unsigned long (*)(unsigned long)) opd; +#else + code = (unsigned long (*)(unsigned long)) instrs; +#endif + + instrs[0] = 0x7c6003a6 + ((n & 0x1F) << 16) + ((n & 0x3e0) << 6); + instrs[1] = 0x4e800020; store_inst(instrs); store_inst(instrs+1); - code = (unsigned long (*)(unsigned long)) opd; if (setjmp(bus_error_jmp) == 0) { catch_memory_errors = 1; @@ -1797,7 +1803,7 @@ memex(void) for(;;){ if (!mnoread) n = mread(adrs, val, size); - printf("%.16x%c", adrs, brev? 'r': ' '); + printf(REG"%c", adrs, brev? 'r': ' '); if (!mnoread) { if (brev) byterev(val, size); @@ -1976,17 +1982,18 @@ prdump(unsigned long adrs, long ndump) nr = mread(adrs, temp, r); adrs += nr; for (m = 0; m < r; ++m) { - if ((m & 7) == 0 && m > 0) - putchar(' '); + if ((m & (sizeof(long) - 1)) == 0 && m > 0) + putchar(' '); if (m < nr) printf("%.2x", temp[m]); else printf("%s", fault_chars[fault_type]); } - if (m <= 8) - printf(" "); - for (; m < 16; ++m) + for (; m < 16; ++m) { + if ((m & (sizeof(long) - 1)) == 0) + putchar(' '); printf(" "); + } printf(" |"); for (m = 0; m < r; ++m) { if (m < nr) { @@ -2151,7 +2158,6 @@ memzcan(void) ok = mread(a, &v, 1); if (ok && !ook) { printf("%.8x .. ", a); - fflush(stdout); } else if (!ok && ook) printf("%.8x\n", a - mskip); ook = ok; @@ -2372,7 +2378,7 @@ int inchar(void) { if (lineptr == NULL || *lineptr == 0) { - if (fgets(line, sizeof(line), stdin) == NULL) { + if (xmon_gets(line, sizeof(line)) == NULL) { lineptr = NULL; return EOF; } @@ -2526,4 +2532,29 @@ void xmon_init(int enable) __debugger_dabr_match = NULL; __debugger_fault_handler = NULL; } + xmon_map_scc(); +} + +#ifdef CONFIG_MAGIC_SYSRQ +static void sysrq_handle_xmon(int key, struct pt_regs *pt_regs, + struct tty_struct *tty) +{ + /* ensure xmon is enabled */ + xmon_init(1); + debugger(pt_regs); +} + +static struct sysrq_key_op sysrq_xmon_op = +{ + .handler = sysrq_handle_xmon, + .help_msg = "Xmon", + .action_msg = "Entering xmon", +}; + +static int __init setup_xmon_sysrq(void) +{ + register_sysrq_key('x', &sysrq_xmon_op); + return 0; } +__initcall(setup_xmon_sysrq); +#endif /* CONFIG_MAGIC_SYSRQ */ |