diff options
Diffstat (limited to 'arch/powerpc/kernel')
43 files changed, 29300 insertions, 0 deletions
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile new file mode 100644 index 000000000000..572d4f5eaacb --- /dev/null +++ b/arch/powerpc/kernel/Makefile @@ -0,0 +1,56 @@ +# +# Makefile for the linux kernel. +# + +ifeq ($(CONFIG_PPC64),y) +EXTRA_CFLAGS += -mno-minimal-toc +endif +ifeq ($(CONFIG_PPC32),y) +CFLAGS_prom_init.o += -fPIC +CFLAGS_btext.o += -fPIC +endif + +obj-y := semaphore.o cputable.o ptrace.o syscalls.o \ + signal_32.o pmc.o +obj-$(CONFIG_PPC64) += setup_64.o binfmt_elf32.o sys_ppc32.o \ + ptrace32.o systbl.o +obj-$(CONFIG_ALTIVEC) += vecemu.o vector.o +obj-$(CONFIG_POWER4) += idle_power4.o +obj-$(CONFIG_PPC_OF) += of_device.o +obj-$(CONFIG_PPC_RTAS) += rtas.o +obj-$(CONFIG_IBMVIO) += vio.o + +ifeq ($(CONFIG_PPC_MERGE),y) + +extra-$(CONFIG_PPC_STD_MMU) := head_32.o +extra-$(CONFIG_PPC64) := head_64.o +extra-$(CONFIG_40x) := head_4xx.o +extra-$(CONFIG_44x) := head_44x.o +extra-$(CONFIG_FSL_BOOKE) := head_fsl_booke.o +extra-$(CONFIG_8xx) := head_8xx.o +extra-y += vmlinux.lds + +obj-y += process.o init_task.o time.o \ + prom.o traps.o setup-common.o +obj-$(CONFIG_PPC32) += entry_32.o setup_32.o misc_32.o systbl.o +obj-$(CONFIG_PPC64) += misc_64.o +obj-$(CONFIG_PPC_OF) += prom_init.o +obj-$(CONFIG_MODULES) += ppc_ksyms.o +obj-$(CONFIG_BOOTX_TEXT) += btext.o +obj-$(CONFIG_6xx) += idle_6xx.o + +ifeq ($(CONFIG_PPC_ISERIES),y) +$(obj)/head_64.o: $(obj)/lparmap.s +AFLAGS_head_64.o += -I$(obj) +endif + +else +# stuff used from here for ARCH=ppc or ARCH=ppc64 +obj-$(CONFIG_PPC64) += traps.o process.o init_task.o time.o \ + setup-common.o + + +endif + +extra-$(CONFIG_PPC_FPU) += fpu.o +extra-$(CONFIG_PPC64) += entry_64.o diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c new file mode 100644 index 000000000000..330cd783206f --- /dev/null +++ b/arch/powerpc/kernel/asm-offsets.c @@ -0,0 +1,273 @@ +/* + * This program is used to generate definitions needed by + * assembly language modules. + * + * We use the technique used in the OSF Mach kernel code: + * generate asm statements containing #defines, + * compile this file to assembler, and then extract the + * #defines from the assembly-language output. + * + * 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/signal.h> +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/string.h> +#include <linux/types.h> +#include <linux/mman.h> +#include <linux/mm.h> +#ifdef CONFIG_PPC64 +#include <linux/time.h> +#include <linux/hardirq.h> +#else +#include <linux/ptrace.h> +#include <linux/suspend.h> +#endif + +#include <asm/io.h> +#include <asm/page.h> +#include <asm/pgtable.h> +#include <asm/processor.h> +#include <asm/cputable.h> +#include <asm/thread_info.h> +#include <asm/rtas.h> +#ifdef CONFIG_PPC64 +#include <asm/paca.h> +#include <asm/lppaca.h> +#include <asm/iSeries/HvLpEvent.h> +#include <asm/cache.h> +#include <asm/systemcfg.h> +#include <asm/compat.h> +#endif + +#define DEFINE(sym, val) \ + asm volatile("\n->" #sym " %0 " #val : : "i" (val)) + +#define BLANK() asm volatile("\n->" : : ) + +int main(void) +{ + DEFINE(THREAD, offsetof(struct task_struct, thread)); + DEFINE(MM, offsetof(struct task_struct, mm)); +#ifdef CONFIG_PPC64 + DEFINE(AUDITCONTEXT, offsetof(struct task_struct, audit_context)); +#else + DEFINE(THREAD_INFO, offsetof(struct task_struct, thread_info)); + DEFINE(PTRACE, offsetof(struct task_struct, ptrace)); +#endif /* CONFIG_PPC64 */ + + DEFINE(KSP, offsetof(struct thread_struct, ksp)); + DEFINE(PT_REGS, offsetof(struct thread_struct, regs)); + DEFINE(THREAD_FPEXC_MODE, offsetof(struct thread_struct, fpexc_mode)); + DEFINE(THREAD_FPR0, offsetof(struct thread_struct, fpr[0])); + DEFINE(THREAD_FPSCR, offsetof(struct thread_struct, fpscr)); +#ifdef CONFIG_ALTIVEC + DEFINE(THREAD_VR0, offsetof(struct thread_struct, vr[0])); + DEFINE(THREAD_VRSAVE, offsetof(struct thread_struct, vrsave)); + DEFINE(THREAD_VSCR, offsetof(struct thread_struct, vscr)); + DEFINE(THREAD_USED_VR, offsetof(struct thread_struct, used_vr)); +#endif /* CONFIG_ALTIVEC */ +#ifdef CONFIG_PPC64 + DEFINE(KSP_VSID, offsetof(struct thread_struct, ksp_vsid)); +#else /* CONFIG_PPC64 */ + DEFINE(PGDIR, offsetof(struct thread_struct, pgdir)); + DEFINE(LAST_SYSCALL, offsetof(struct thread_struct, last_syscall)); +#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE) + DEFINE(THREAD_DBCR0, offsetof(struct thread_struct, dbcr0)); + DEFINE(PT_PTRACED, PT_PTRACED); +#endif +#ifdef CONFIG_SPE + DEFINE(THREAD_EVR0, offsetof(struct thread_struct, evr[0])); + DEFINE(THREAD_ACC, offsetof(struct thread_struct, acc)); + DEFINE(THREAD_SPEFSCR, offsetof(struct thread_struct, spefscr)); + DEFINE(THREAD_USED_SPE, offsetof(struct thread_struct, used_spe)); +#endif /* CONFIG_SPE */ +#endif /* CONFIG_PPC64 */ + + DEFINE(TI_FLAGS, offsetof(struct thread_info, flags)); + DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count)); + DEFINE(TI_SC_NOERR, offsetof(struct thread_info, syscall_noerror)); +#ifdef CONFIG_PPC32 + DEFINE(TI_TASK, offsetof(struct thread_info, task)); + DEFINE(TI_EXECDOMAIN, offsetof(struct thread_info, exec_domain)); + DEFINE(TI_CPU, offsetof(struct thread_info, cpu)); +#endif /* CONFIG_PPC32 */ + +#ifdef CONFIG_PPC64 + DEFINE(DCACHEL1LINESIZE, offsetof(struct ppc64_caches, dline_size)); + DEFINE(DCACHEL1LOGLINESIZE, offsetof(struct ppc64_caches, log_dline_size)); + DEFINE(DCACHEL1LINESPERPAGE, offsetof(struct ppc64_caches, dlines_per_page)); + 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 */ + DEFINE(PACA_SIZE, sizeof(struct paca_struct)); + DEFINE(PACAPACAINDEX, offsetof(struct paca_struct, paca_index)); + DEFINE(PACAPROCSTART, offsetof(struct paca_struct, cpu_start)); + DEFINE(PACAKSAVE, offsetof(struct paca_struct, kstack)); + DEFINE(PACACURRENT, offsetof(struct paca_struct, __current)); + DEFINE(PACASAVEDMSR, offsetof(struct paca_struct, saved_msr)); + DEFINE(PACASTABREAL, offsetof(struct paca_struct, stab_real)); + DEFINE(PACASTABVIRT, offsetof(struct paca_struct, stab_addr)); + DEFINE(PACASTABRR, offsetof(struct paca_struct, stab_rr)); + DEFINE(PACAR1, offsetof(struct paca_struct, saved_r1)); + DEFINE(PACATOC, offsetof(struct paca_struct, kernel_toc)); + DEFINE(PACAPROCENABLED, offsetof(struct paca_struct, proc_enabled)); + DEFINE(PACASLBCACHE, offsetof(struct paca_struct, slb_cache)); + DEFINE(PACASLBCACHEPTR, offsetof(struct paca_struct, slb_cache_ptr)); + DEFINE(PACACONTEXTID, offsetof(struct paca_struct, context.id)); +#ifdef CONFIG_HUGETLB_PAGE + DEFINE(PACALOWHTLBAREAS, offsetof(struct paca_struct, context.low_htlb_areas)); + DEFINE(PACAHIGHHTLBAREAS, offsetof(struct paca_struct, context.high_htlb_areas)); +#endif /* CONFIG_HUGETLB_PAGE */ + DEFINE(PACADEFAULTDECR, offsetof(struct paca_struct, default_decr)); + DEFINE(PACA_EXGEN, offsetof(struct paca_struct, exgen)); + DEFINE(PACA_EXMC, offsetof(struct paca_struct, exmc)); + DEFINE(PACA_EXSLB, offsetof(struct paca_struct, exslb)); + DEFINE(PACA_EXDSI, offsetof(struct paca_struct, exdsi)); + DEFINE(PACAEMERGSP, offsetof(struct paca_struct, emergency_sp)); + DEFINE(PACALPPACA, offsetof(struct paca_struct, lppaca)); + DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id)); + + DEFINE(LPPACASRR0, offsetof(struct lppaca, saved_srr0)); + DEFINE(LPPACASRR1, offsetof(struct lppaca, saved_srr1)); + DEFINE(LPPACAANYINT, offsetof(struct lppaca, int_dword.any_int)); + DEFINE(LPPACADECRINT, offsetof(struct lppaca, int_dword.fields.decr_int)); +#endif /* CONFIG_PPC64 */ + + /* RTAS */ + DEFINE(RTASBASE, offsetof(struct rtas_t, base)); + DEFINE(RTASENTRY, offsetof(struct rtas_t, entry)); + + /* Interrupt register frame */ + DEFINE(STACK_FRAME_OVERHEAD, STACK_FRAME_OVERHEAD); +#ifndef CONFIG_PPC64 + DEFINE(INT_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs)); +#else /* CONFIG_PPC64 */ + DEFINE(SWITCH_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs)); + /* 288 = # of volatile regs, int & fp, for leaf routines */ + /* which do not stack a frame. See the PPC64 ABI. */ + DEFINE(INT_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 288); + /* Create extra stack space for SRR0 and SRR1 when calling prom/rtas. */ + DEFINE(PROM_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 16); + DEFINE(RTAS_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 16); +#endif /* CONFIG_PPC64 */ + DEFINE(GPR0, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[0])); + DEFINE(GPR1, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[1])); + DEFINE(GPR2, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[2])); + DEFINE(GPR3, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[3])); + DEFINE(GPR4, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[4])); + DEFINE(GPR5, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[5])); + DEFINE(GPR6, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[6])); + DEFINE(GPR7, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[7])); + DEFINE(GPR8, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[8])); + DEFINE(GPR9, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[9])); + DEFINE(GPR10, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[10])); + DEFINE(GPR11, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[11])); + DEFINE(GPR12, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[12])); + DEFINE(GPR13, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[13])); +#ifndef CONFIG_PPC64 + DEFINE(GPR14, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[14])); + DEFINE(GPR15, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[15])); + DEFINE(GPR16, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[16])); + DEFINE(GPR17, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[17])); + DEFINE(GPR18, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[18])); + DEFINE(GPR19, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[19])); + DEFINE(GPR20, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[20])); + DEFINE(GPR21, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[21])); + DEFINE(GPR22, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[22])); + DEFINE(GPR23, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[23])); + DEFINE(GPR24, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[24])); + DEFINE(GPR25, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[25])); + DEFINE(GPR26, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[26])); + DEFINE(GPR27, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[27])); + DEFINE(GPR28, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[28])); + DEFINE(GPR29, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[29])); + DEFINE(GPR30, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[30])); + DEFINE(GPR31, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[31])); +#endif /* CONFIG_PPC64 */ + /* + * Note: these symbols include _ because they overlap with special + * register names + */ + DEFINE(_NIP, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, nip)); + DEFINE(_MSR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, msr)); + DEFINE(_CTR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, ctr)); + DEFINE(_LINK, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, link)); + DEFINE(_CCR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, ccr)); + DEFINE(_XER, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, xer)); + DEFINE(_DAR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, dar)); + DEFINE(_DSISR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, dsisr)); + DEFINE(ORIG_GPR3, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, orig_gpr3)); + DEFINE(RESULT, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, result)); + DEFINE(_TRAP, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, trap)); +#ifndef CONFIG_PPC64 + DEFINE(_MQ, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, mq)); + /* + * The PowerPC 400-class & Book-E processors have neither the DAR + * nor the DSISR SPRs. Hence, we overload them to hold the similar + * DEAR and ESR SPRs for such processors. For critical interrupts + * we use them to hold SRR0 and SRR1. + */ + DEFINE(_DEAR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, dar)); + DEFINE(_ESR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, dsisr)); +#else /* CONFIG_PPC64 */ + DEFINE(SOFTE, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, softe)); + + /* These _only_ to be used with {PROM,RTAS}_FRAME_SIZE!!! */ + DEFINE(_SRR0, STACK_FRAME_OVERHEAD+sizeof(struct pt_regs)); + DEFINE(_SRR1, STACK_FRAME_OVERHEAD+sizeof(struct pt_regs)+8); +#endif /* CONFIG_PPC64 */ + + DEFINE(CLONE_VM, CLONE_VM); + DEFINE(CLONE_UNTRACED, CLONE_UNTRACED); + +#ifndef CONFIG_PPC64 + DEFINE(MM_PGD, offsetof(struct mm_struct, pgd)); +#endif /* ! CONFIG_PPC64 */ + + /* About the CPU features table */ + DEFINE(CPU_SPEC_ENTRY_SIZE, sizeof(struct cpu_spec)); + DEFINE(CPU_SPEC_PVR_MASK, offsetof(struct cpu_spec, pvr_mask)); + DEFINE(CPU_SPEC_PVR_VALUE, offsetof(struct cpu_spec, pvr_value)); + DEFINE(CPU_SPEC_FEATURES, offsetof(struct cpu_spec, cpu_features)); + DEFINE(CPU_SPEC_SETUP, offsetof(struct cpu_spec, cpu_setup)); + +#ifndef CONFIG_PPC64 + DEFINE(pbe_address, offsetof(struct pbe, address)); + DEFINE(pbe_orig_address, offsetof(struct pbe, orig_address)); + DEFINE(pbe_next, offsetof(struct pbe, next)); + + 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)); + + /* timeval/timezone offsets for use by vdso */ + 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(TZONE_TZ_MINWEST, offsetof(struct timezone, tz_minuteswest)); + DEFINE(TZONE_TZ_DSTTIME, offsetof(struct timezone, tz_dsttime)); +#endif /* CONFIG_PPC64 */ + return 0; +} diff --git a/arch/powerpc/kernel/binfmt_elf32.c b/arch/powerpc/kernel/binfmt_elf32.c new file mode 100644 index 000000000000..8ad6b0f33651 --- /dev/null +++ b/arch/powerpc/kernel/binfmt_elf32.c @@ -0,0 +1,75 @@ +/* + * binfmt_elf32.c: Support 32-bit PPC ELF binaries on Power3 and followons. + * based on the SPARC64 version. + * Copyright (C) 1995, 1996, 1997, 1998 David S. Miller (davem@redhat.com) + * Copyright (C) 1995, 1996, 1997, 1998 Jakub Jelinek (jj@ultra.linux.cz) + * + * Copyright (C) 2000,2001 Ken Aaker (kdaaker@rchland.vnet.ibm.com), IBM Corp + * Copyright (C) 2001 Anton Blanchard (anton@au.ibm.com), IBM + * + * 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 ELF_ARCH EM_PPC +#define ELF_CLASS ELFCLASS32 +#define ELF_DATA ELFDATA2MSB; + +#include <asm/processor.h> +#include <linux/module.h> +#include <linux/config.h> +#include <linux/elfcore.h> +#include <linux/compat.h> + +#define elf_prstatus elf_prstatus32 +struct elf_prstatus32 +{ + struct elf_siginfo pr_info; /* Info associated with signal */ + short pr_cursig; /* Current signal */ + unsigned int pr_sigpend; /* Set of pending signals */ + unsigned int pr_sighold; /* Set of held signals */ + pid_t pr_pid; + pid_t pr_ppid; + pid_t pr_pgrp; + pid_t pr_sid; + struct compat_timeval pr_utime; /* User time */ + struct compat_timeval pr_stime; /* System time */ + struct compat_timeval pr_cutime; /* Cumulative user time */ + struct compat_timeval pr_cstime; /* Cumulative system time */ + elf_gregset_t pr_reg; /* General purpose registers. */ + int pr_fpvalid; /* True if math co-processor being used. */ +}; + +#define elf_prpsinfo elf_prpsinfo32 +struct elf_prpsinfo32 +{ + char pr_state; /* numeric process state */ + char pr_sname; /* char for pr_state */ + char pr_zomb; /* zombie */ + char pr_nice; /* nice val */ + unsigned int pr_flag; /* flags */ + u32 pr_uid; + u32 pr_gid; + pid_t pr_pid, pr_ppid, pr_pgrp, pr_sid; + /* Lots missing */ + char pr_fname[16]; /* filename of executable */ + char pr_psargs[ELF_PRARGSZ]; /* initial part of arg list */ +}; + +#include <linux/time.h> + +#undef cputime_to_timeval +#define cputime_to_timeval cputime_to_compat_timeval +static __inline__ void +cputime_to_compat_timeval(const cputime_t cputime, struct compat_timeval *value) +{ + unsigned long jiffies = cputime_to_jiffies(cputime); + value->tv_usec = (jiffies % HZ) * (1000000L / HZ); + value->tv_sec = jiffies / HZ; +} + +#define init_elf_binfmt init_elf32_binfmt + +#include "../../../fs/binfmt_elf.c" diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c new file mode 100644 index 000000000000..bdfba92b2b38 --- /dev/null +++ b/arch/powerpc/kernel/btext.c @@ -0,0 +1,853 @@ +/* + * Procedures for drawing on the screen early on in the boot process. + * + * Benjamin Herrenschmidt <benh@kernel.crashing.org> + */ +#include <linux/config.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/init.h> +#include <linux/module.h> + +#include <asm/sections.h> +#include <asm/prom.h> +#include <asm/btext.h> +#include <asm/prom.h> +#include <asm/page.h> +#include <asm/mmu.h> +#include <asm/pgtable.h> +#include <asm/io.h> +#include <asm/lmb.h> +#include <asm/processor.h> + +#define NO_SCROLL + +#ifndef NO_SCROLL +static void scrollscreen(void); +#endif + +static void draw_byte(unsigned char c, long locX, long locY); +static void draw_byte_32(unsigned char *bits, unsigned int *base, int rb); +static void draw_byte_16(unsigned char *bits, unsigned int *base, int rb); +static void draw_byte_8(unsigned char *bits, unsigned int *base, int rb); + +static int g_loc_X; +static int g_loc_Y; +static int g_max_loc_X; +static int g_max_loc_Y; + +static int dispDeviceRowBytes; +static int dispDeviceDepth; +static int dispDeviceRect[4]; +static unsigned char *dispDeviceBase, *logicalDisplayBase; + +unsigned long disp_BAT[2] __initdata = {0, 0}; + +#define cmapsz (16*256) + +static unsigned char vga_font[cmapsz]; + +int boot_text_mapped; +int force_printk_to_btext = 0; + +#ifdef CONFIG_PPC32 +/* Calc BAT values for mapping the display and store them + * in disp_BAT. Those values are then used from head.S to map + * the display during identify_machine() and MMU_Init() + * + * The display is mapped to virtual address 0xD0000000, rather + * than 1:1, because some some CHRP machines put the frame buffer + * in the region starting at 0xC0000000 (KERNELBASE). + * This mapping is temporary and will disappear as soon as the + * setup done by MMU_Init() is applied. + * + * For now, we align the BAT and then map 8Mb on 601 and 16Mb + * on other PPCs. This may cause trouble if the framebuffer + * is really badly aligned, but I didn't encounter this case + * yet. + */ +void __init +btext_prepare_BAT(void) +{ + unsigned long vaddr = KERNELBASE + 0x10000000; + unsigned long addr; + unsigned long lowbits; + + addr = (unsigned long)dispDeviceBase; + if (!addr) { + boot_text_mapped = 0; + return; + } + if (PVR_VER(mfspr(SPRN_PVR)) != 1) { + /* 603, 604, G3, G4, ... */ + lowbits = addr & ~0xFF000000UL; + addr &= 0xFF000000UL; + disp_BAT[0] = vaddr | (BL_16M<<2) | 2; + disp_BAT[1] = addr | (_PAGE_NO_CACHE | _PAGE_GUARDED | BPP_RW); + } else { + /* 601 */ + lowbits = addr & ~0xFF800000UL; + addr &= 0xFF800000UL; + disp_BAT[0] = vaddr | (_PAGE_NO_CACHE | PP_RWXX) | 4; + disp_BAT[1] = addr | BL_8M | 0x40; + } + logicalDisplayBase = (void *) (vaddr + lowbits); +} +#endif + +/* This function will enable the early boot text when doing OF booting. This + * way, xmon output should work too + */ +void __init +btext_setup_display(int width, int height, int depth, int pitch, + unsigned long address) +{ + g_loc_X = 0; + g_loc_Y = 0; + g_max_loc_X = width / 8; + g_max_loc_Y = height / 16; + logicalDisplayBase = (unsigned char *)address; + dispDeviceBase = (unsigned char *)address; + dispDeviceRowBytes = pitch; + dispDeviceDepth = depth; + dispDeviceRect[0] = dispDeviceRect[1] = 0; + dispDeviceRect[2] = width; + dispDeviceRect[3] = height; + boot_text_mapped = 1; +} + +/* Here's a small text engine to use during early boot + * or for debugging purposes + * + * todo: + * + * - build some kind of vgacon with it to enable early printk + * - move to a separate file + * - add a few video driver hooks to keep in sync with display + * changes. + */ + +void map_boot_text(void) +{ + unsigned long base, offset, size; + unsigned char *vbase; + + /* By default, we are no longer mapped */ + boot_text_mapped = 0; + if (dispDeviceBase == 0) + return; + base = ((unsigned long) dispDeviceBase) & 0xFFFFF000UL; + offset = ((unsigned long) dispDeviceBase) - base; + size = dispDeviceRowBytes * dispDeviceRect[3] + offset + + dispDeviceRect[0]; + vbase = __ioremap(base, size, _PAGE_NO_CACHE); + if (vbase == 0) + return; + logicalDisplayBase = vbase + offset; + boot_text_mapped = 1; +} + +int btext_initialize(struct device_node *np) +{ + unsigned int width, height, depth, pitch; + unsigned long address = 0; + u32 *prop; + + prop = (u32 *)get_property(np, "width", NULL); + if (prop == NULL) + return -EINVAL; + width = *prop; + prop = (u32 *)get_property(np, "height", NULL); + if (prop == NULL) + return -EINVAL; + height = *prop; + prop = (u32 *)get_property(np, "depth", NULL); + if (prop == NULL) + return -EINVAL; + depth = *prop; + pitch = width * ((depth + 7) / 8); + prop = (u32 *)get_property(np, "linebytes", NULL); + if (prop) + pitch = *prop; + if (pitch == 1) + pitch = 0x1000; + prop = (u32 *)get_property(np, "address", NULL); + if (prop) + address = *prop; + + /* FIXME: Add support for PCI reg properties */ + + if (address == 0) + return -EINVAL; + + g_loc_X = 0; + g_loc_Y = 0; + g_max_loc_X = width / 8; + g_max_loc_Y = height / 16; + logicalDisplayBase = (unsigned char *)address; + dispDeviceBase = (unsigned char *)address; + dispDeviceRowBytes = pitch; + dispDeviceDepth = depth; + dispDeviceRect[0] = dispDeviceRect[1] = 0; + dispDeviceRect[2] = width; + dispDeviceRect[3] = height; + + map_boot_text(); + + return 0; +} + +void __init init_boot_display(void) +{ + char *name; + struct device_node *np = NULL; + int rc = -ENODEV; + + printk("trying to initialize btext ...\n"); + + name = (char *)get_property(of_chosen, "linux,stdout-path", NULL); + if (name != NULL) { + np = of_find_node_by_path(name); + if (np != NULL) { + if (strcmp(np->type, "display") != 0) { + printk("boot stdout isn't a display !\n"); + of_node_put(np); + np = NULL; + } + } + } + if (np) + rc = btext_initialize(np); + if (rc == 0) + return; + + for (np = NULL; (np = of_find_node_by_type(np, "display"));) { + if (get_property(np, "linux,opened", NULL)) { + printk("trying %s ...\n", np->full_name); + rc = btext_initialize(np); + printk("result: %d\n", rc); + } + if (rc == 0) + return; + } +} + +/* Calc the base address of a given point (x,y) */ +static unsigned char * calc_base(int x, int y) +{ + unsigned char *base; + + base = logicalDisplayBase; + if (base == 0) + base = dispDeviceBase; + base += (x + dispDeviceRect[0]) * (dispDeviceDepth >> 3); + base += (y + dispDeviceRect[1]) * dispDeviceRowBytes; + return base; +} + +/* Adjust the display to a new resolution */ +void btext_update_display(unsigned long phys, int width, int height, + int depth, int pitch) +{ + if (dispDeviceBase == 0) + return; + + /* check it's the same frame buffer (within 256MB) */ + if ((phys ^ (unsigned long)dispDeviceBase) & 0xf0000000) + return; + + dispDeviceBase = (__u8 *) phys; + dispDeviceRect[0] = 0; + dispDeviceRect[1] = 0; + dispDeviceRect[2] = width; + dispDeviceRect[3] = height; + dispDeviceDepth = depth; + dispDeviceRowBytes = pitch; + if (boot_text_mapped) { + iounmap(logicalDisplayBase); + boot_text_mapped = 0; + } + map_boot_text(); + g_loc_X = 0; + g_loc_Y = 0; + g_max_loc_X = width / 8; + g_max_loc_Y = height / 16; +} +EXPORT_SYMBOL(btext_update_display); + +void btext_clearscreen(void) +{ + unsigned long *base = (unsigned long *)calc_base(0, 0); + unsigned long width = ((dispDeviceRect[2] - dispDeviceRect[0]) * + (dispDeviceDepth >> 3)) >> 3; + int i,j; + + for (i=0; i<(dispDeviceRect[3] - dispDeviceRect[1]); i++) + { + unsigned long *ptr = base; + for(j=width; j; --j) + *(ptr++) = 0; + base += (dispDeviceRowBytes >> 3); + } +} + +#ifndef NO_SCROLL +static void scrollscreen(void) +{ + unsigned long *src = (unsigned long *)calc_base(0,16); + unsigned long *dst = (unsigned long *)calc_base(0,0); + unsigned long width = ((dispDeviceRect[2] - dispDeviceRect[0]) * + (dispDeviceDepth >> 3)) >> 3; + int i,j; + + for (i=0; i<(dispDeviceRect[3] - dispDeviceRect[1] - 16); i++) + { + unsigned long *src_ptr = src; + unsigned long *dst_ptr = dst; + for(j=width; j; --j) + *(dst_ptr++) = *(src_ptr++); + src += (dispDeviceRowBytes >> 3); + dst += (dispDeviceRowBytes >> 3); + } + for (i=0; i<16; i++) + { + unsigned long *dst_ptr = dst; + for(j=width; j; --j) + *(dst_ptr++) = 0; + dst += (dispDeviceRowBytes >> 3); + } +} +#endif /* ndef NO_SCROLL */ + +void btext_drawchar(char c) +{ + int cline = 0; +#ifdef NO_SCROLL + int x; +#endif + if (!boot_text_mapped) + return; + + switch (c) { + case '\b': + if (g_loc_X > 0) + --g_loc_X; + break; + case '\t': + g_loc_X = (g_loc_X & -8) + 8; + break; + case '\r': + g_loc_X = 0; + break; + case '\n': + g_loc_X = 0; + g_loc_Y++; + cline = 1; + break; + default: + draw_byte(c, g_loc_X++, g_loc_Y); + } + if (g_loc_X >= g_max_loc_X) { + g_loc_X = 0; + g_loc_Y++; + cline = 1; + } +#ifndef NO_SCROLL + while (g_loc_Y >= g_max_loc_Y) { + scrollscreen(); + g_loc_Y--; + } +#else + /* wrap around from bottom to top of screen so we don't + waste time scrolling each line. -- paulus. */ + if (g_loc_Y >= g_max_loc_Y) + g_loc_Y = 0; + if (cline) { + for (x = 0; x < g_max_loc_X; ++x) + draw_byte(' ', x, g_loc_Y); + } +#endif +} + +void btext_drawstring(const char *c) +{ + if (!boot_text_mapped) + return; + while (*c) + btext_drawchar(*c++); +} + +void btext_drawhex(unsigned long v) +{ + char *hex_table = "0123456789abcdef"; + + if (!boot_text_mapped) + return; +#ifdef CONFIG_PPC64 + btext_drawchar(hex_table[(v >> 60) & 0x0000000FUL]); + btext_drawchar(hex_table[(v >> 56) & 0x0000000FUL]); + btext_drawchar(hex_table[(v >> 52) & 0x0000000FUL]); + btext_drawchar(hex_table[(v >> 48) & 0x0000000FUL]); + btext_drawchar(hex_table[(v >> 44) & 0x0000000FUL]); + btext_drawchar(hex_table[(v >> 40) & 0x0000000FUL]); + btext_drawchar(hex_table[(v >> 36) & 0x0000000FUL]); + btext_drawchar(hex_table[(v >> 32) & 0x0000000FUL]); +#endif + btext_drawchar(hex_table[(v >> 28) & 0x0000000FUL]); + btext_drawchar(hex_table[(v >> 24) & 0x0000000FUL]); + btext_drawchar(hex_table[(v >> 20) & 0x0000000FUL]); + btext_drawchar(hex_table[(v >> 16) & 0x0000000FUL]); + btext_drawchar(hex_table[(v >> 12) & 0x0000000FUL]); + btext_drawchar(hex_table[(v >> 8) & 0x0000000FUL]); + btext_drawchar(hex_table[(v >> 4) & 0x0000000FUL]); + btext_drawchar(hex_table[(v >> 0) & 0x0000000FUL]); + btext_drawchar(' '); +} + +static void draw_byte(unsigned char c, long locX, long locY) +{ + unsigned char *base = calc_base(locX << 3, locY << 4); + unsigned char *font = &vga_font[((unsigned int)c) * 16]; + int rb = dispDeviceRowBytes; + + switch(dispDeviceDepth) { + case 24: + case 32: + draw_byte_32(font, (unsigned int *)base, rb); + break; + case 15: + case 16: + draw_byte_16(font, (unsigned int *)base, rb); + break; + case 8: + draw_byte_8(font, (unsigned int *)base, rb); + break; + } +} + +static unsigned int expand_bits_8[16] = { + 0x00000000, + 0x000000ff, + 0x0000ff00, + 0x0000ffff, + 0x00ff0000, + 0x00ff00ff, + 0x00ffff00, + 0x00ffffff, + 0xff000000, + 0xff0000ff, + 0xff00ff00, + 0xff00ffff, + 0xffff0000, + 0xffff00ff, + 0xffffff00, + 0xffffffff +}; + +static unsigned int expand_bits_16[4] = { + 0x00000000, + 0x0000ffff, + 0xffff0000, + 0xffffffff +}; + + +static void draw_byte_32(unsigned char *font, unsigned int *base, int rb) +{ + int l, bits; + int fg = 0xFFFFFFFFUL; + int bg = 0x00000000UL; + + for (l = 0; l < 16; ++l) + { + bits = *font++; + base[0] = (-(bits >> 7) & fg) ^ bg; + base[1] = (-((bits >> 6) & 1) & fg) ^ bg; + base[2] = (-((bits >> 5) & 1) & fg) ^ bg; + base[3] = (-((bits >> 4) & 1) & fg) ^ bg; + base[4] = (-((bits >> 3) & 1) & fg) ^ bg; + base[5] = (-((bits >> 2) & 1) & fg) ^ bg; + base[6] = (-((bits >> 1) & 1) & fg) ^ bg; + base[7] = (-(bits & 1) & fg) ^ bg; + base = (unsigned int *) ((char *)base + rb); + } +} + +static void draw_byte_16(unsigned char *font, unsigned int *base, int rb) +{ + int l, bits; + int fg = 0xFFFFFFFFUL; + int bg = 0x00000000UL; + unsigned int *eb = (int *)expand_bits_16; + + for (l = 0; l < 16; ++l) + { + bits = *font++; + base[0] = (eb[bits >> 6] & fg) ^ bg; + base[1] = (eb[(bits >> 4) & 3] & fg) ^ bg; + base[2] = (eb[(bits >> 2) & 3] & fg) ^ bg; + base[3] = (eb[bits & 3] & fg) ^ bg; + base = (unsigned int *) ((char *)base + rb); + } +} + +static void draw_byte_8(unsigned char *font, unsigned int *base, int rb) +{ + int l, bits; + int fg = 0x0F0F0F0FUL; + int bg = 0x00000000UL; + unsigned int *eb = (int *)expand_bits_8; + + for (l = 0; l < 16; ++l) + { + bits = *font++; + base[0] = (eb[bits >> 4] & fg) ^ bg; + base[1] = (eb[bits & 0xf] & fg) ^ bg; + base = (unsigned int *) ((char *)base + rb); + } +} + +static unsigned char vga_font[cmapsz] = { +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0x81, 0xa5, 0x81, 0x81, 0xbd, +0x99, 0x81, 0x81, 0x7e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0xff, +0xdb, 0xff, 0xff, 0xc3, 0xe7, 0xff, 0xff, 0x7e, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x6c, 0xfe, 0xfe, 0xfe, 0xfe, 0x7c, 0x38, 0x10, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x7c, 0xfe, +0x7c, 0x38, 0x10, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, +0x3c, 0x3c, 0xe7, 0xe7, 0xe7, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x18, 0x3c, 0x7e, 0xff, 0xff, 0x7e, 0x18, 0x18, 0x3c, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x3c, +0x3c, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, +0xff, 0xff, 0xe7, 0xc3, 0xc3, 0xe7, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, +0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x66, 0x42, 0x42, 0x66, 0x3c, 0x00, +0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, 0xff, 0xc3, 0x99, 0xbd, +0xbd, 0x99, 0xc3, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x1e, 0x0e, +0x1a, 0x32, 0x78, 0xcc, 0xcc, 0xcc, 0xcc, 0x78, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x3c, 0x66, 0x66, 0x66, 0x66, 0x3c, 0x18, 0x7e, 0x18, 0x18, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3f, 0x33, 0x3f, 0x30, 0x30, 0x30, +0x30, 0x70, 0xf0, 0xe0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7f, 0x63, +0x7f, 0x63, 0x63, 0x63, 0x63, 0x67, 0xe7, 0xe6, 0xc0, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x18, 0x18, 0xdb, 0x3c, 0xe7, 0x3c, 0xdb, 0x18, 0x18, +0x00, 0x00, 0x00, 0x00, 0x00, 0x80, 0xc0, 0xe0, 0xf0, 0xf8, 0xfe, 0xf8, +0xf0, 0xe0, 0xc0, 0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x02, 0x06, 0x0e, +0x1e, 0x3e, 0xfe, 0x3e, 0x1e, 0x0e, 0x06, 0x02, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x18, 0x3c, 0x7e, 0x18, 0x18, 0x18, 0x7e, 0x3c, 0x18, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66, +0x66, 0x00, 0x66, 0x66, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7f, 0xdb, +0xdb, 0xdb, 0x7b, 0x1b, 0x1b, 0x1b, 0x1b, 0x1b, 0x00, 0x00, 0x00, 0x00, +0x00, 0x7c, 0xc6, 0x60, 0x38, 0x6c, 0xc6, 0xc6, 0x6c, 0x38, 0x0c, 0xc6, +0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0xfe, 0xfe, 0xfe, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x3c, +0x7e, 0x18, 0x18, 0x18, 0x7e, 0x3c, 0x18, 0x7e, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x18, 0x3c, 0x7e, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, +0x18, 0x7e, 0x3c, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x18, 0x0c, 0xfe, 0x0c, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x30, 0x60, 0xfe, 0x60, 0x30, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc0, 0xc0, +0xc0, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x24, 0x66, 0xff, 0x66, 0x24, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x38, 0x7c, 0x7c, 0xfe, 0xfe, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0xfe, 0x7c, 0x7c, +0x38, 0x38, 0x10, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x18, 0x3c, 0x3c, 0x3c, 0x18, 0x18, 0x18, 0x00, 0x18, 0x18, +0x00, 0x00, 0x00, 0x00, 0x00, 0x66, 0x66, 0x66, 0x24, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x6c, +0x6c, 0xfe, 0x6c, 0x6c, 0x6c, 0xfe, 0x6c, 0x6c, 0x00, 0x00, 0x00, 0x00, +0x18, 0x18, 0x7c, 0xc6, 0xc2, 0xc0, 0x7c, 0x06, 0x06, 0x86, 0xc6, 0x7c, +0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc2, 0xc6, 0x0c, 0x18, +0x30, 0x60, 0xc6, 0x86, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x38, 0x6c, +0x6c, 0x38, 0x76, 0xdc, 0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, +0x00, 0x30, 0x30, 0x30, 0x60, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0c, 0x18, 0x30, 0x30, 0x30, 0x30, +0x30, 0x30, 0x18, 0x0c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x30, 0x18, +0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x18, 0x30, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x66, 0x3c, 0xff, 0x3c, 0x66, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x7e, +0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x30, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x02, 0x06, 0x0c, 0x18, 0x30, 0x60, 0xc0, 0x80, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xce, 0xde, 0xf6, 0xe6, 0xc6, 0xc6, 0x7c, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x38, 0x78, 0x18, 0x18, 0x18, +0x18, 0x18, 0x18, 0x7e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, +0x06, 0x0c, 0x18, 0x30, 0x60, 0xc0, 0xc6, 0xfe, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x7c, 0xc6, 0x06, 0x06, 0x3c, 0x06, 0x06, 0x06, 0xc6, 0x7c, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0c, 0x1c, 0x3c, 0x6c, 0xcc, 0xfe, +0x0c, 0x0c, 0x0c, 0x1e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0xc0, +0xc0, 0xc0, 0xfc, 0x06, 0x06, 0x06, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x38, 0x60, 0xc0, 0xc0, 0xfc, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0xc6, 0x06, 0x06, 0x0c, 0x18, +0x30, 0x30, 0x30, 0x30, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, +0xc6, 0xc6, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0x7e, 0x06, 0x06, 0x06, 0x0c, 0x78, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x00, 0x00, +0x00, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x18, 0x18, 0x00, 0x00, 0x00, 0x18, 0x18, 0x30, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x06, 0x0c, 0x18, 0x30, 0x60, 0x30, 0x18, 0x0c, 0x06, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0x00, 0x00, +0x7e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x60, +0x30, 0x18, 0x0c, 0x06, 0x0c, 0x18, 0x30, 0x60, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x7c, 0xc6, 0xc6, 0x0c, 0x18, 0x18, 0x18, 0x00, 0x18, 0x18, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xde, 0xde, +0xde, 0xdc, 0xc0, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x38, +0x6c, 0xc6, 0xc6, 0xfe, 0xc6, 0xc6, 0xc6, 0xc6, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0xfc, 0x66, 0x66, 0x66, 0x7c, 0x66, 0x66, 0x66, 0x66, 0xfc, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x66, 0xc2, 0xc0, 0xc0, 0xc0, +0xc0, 0xc2, 0x66, 0x3c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf8, 0x6c, +0x66, 0x66, 0x66, 0x66, 0x66, 0x66, 0x6c, 0xf8, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0xfe, 0x66, 0x62, 0x68, 0x78, 0x68, 0x60, 0x62, 0x66, 0xfe, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0x66, 0x62, 0x68, 0x78, 0x68, +0x60, 0x60, 0x60, 0xf0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x66, +0xc2, 0xc0, 0xc0, 0xde, 0xc6, 0xc6, 0x66, 0x3a, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0xc6, 0xc6, 0xc6, 0xc6, 0xfe, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x18, 0x18, 0x18, 0x18, 0x18, +0x18, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x1e, 0x0c, +0x0c, 0x0c, 0x0c, 0x0c, 0xcc, 0xcc, 0xcc, 0x78, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0xe6, 0x66, 0x66, 0x6c, 0x78, 0x78, 0x6c, 0x66, 0x66, 0xe6, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf0, 0x60, 0x60, 0x60, 0x60, 0x60, +0x60, 0x62, 0x66, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0xe7, +0xff, 0xff, 0xdb, 0xc3, 0xc3, 0xc3, 0xc3, 0xc3, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0xc6, 0xe6, 0xf6, 0xfe, 0xde, 0xce, 0xc6, 0xc6, 0xc6, 0xc6, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, +0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfc, 0x66, +0x66, 0x66, 0x7c, 0x60, 0x60, 0x60, 0x60, 0xf0, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xd6, 0xde, 0x7c, +0x0c, 0x0e, 0x00, 0x00, 0x00, 0x00, 0xfc, 0x66, 0x66, 0x66, 0x7c, 0x6c, +0x66, 0x66, 0x66, 0xe6, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, +0xc6, 0x60, 0x38, 0x0c, 0x06, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0xff, 0xdb, 0x99, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, +0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0xc3, +0xc3, 0xc3, 0xc3, 0xc3, 0xc3, 0x66, 0x3c, 0x18, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0xc3, 0xc3, 0xc3, 0xc3, 0xc3, 0xdb, 0xdb, 0xff, 0x66, 0x66, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0xc3, 0x66, 0x3c, 0x18, 0x18, +0x3c, 0x66, 0xc3, 0xc3, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0xc3, +0xc3, 0x66, 0x3c, 0x18, 0x18, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0xff, 0xc3, 0x86, 0x0c, 0x18, 0x30, 0x60, 0xc1, 0xc3, 0xff, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x30, 0x30, 0x30, 0x30, 0x30, +0x30, 0x30, 0x30, 0x3c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x80, +0xc0, 0xe0, 0x70, 0x38, 0x1c, 0x0e, 0x06, 0x02, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x3c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x3c, +0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x6c, 0xc6, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0x00, 0x00, +0x30, 0x30, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x78, 0x0c, 0x7c, +0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xe0, 0x60, +0x60, 0x78, 0x6c, 0x66, 0x66, 0x66, 0x66, 0x7c, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, 0xc0, 0xc0, 0xc0, 0xc6, 0x7c, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x1c, 0x0c, 0x0c, 0x3c, 0x6c, 0xcc, +0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x7c, 0xc6, 0xfe, 0xc0, 0xc0, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x38, 0x6c, 0x64, 0x60, 0xf0, 0x60, 0x60, 0x60, 0x60, 0xf0, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x76, 0xcc, 0xcc, +0xcc, 0xcc, 0xcc, 0x7c, 0x0c, 0xcc, 0x78, 0x00, 0x00, 0x00, 0xe0, 0x60, +0x60, 0x6c, 0x76, 0x66, 0x66, 0x66, 0x66, 0xe6, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x18, 0x18, 0x00, 0x38, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x06, 0x06, 0x00, 0x0e, 0x06, 0x06, +0x06, 0x06, 0x06, 0x06, 0x66, 0x66, 0x3c, 0x00, 0x00, 0x00, 0xe0, 0x60, +0x60, 0x66, 0x6c, 0x78, 0x78, 0x6c, 0x66, 0xe6, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x38, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xe6, 0xff, 0xdb, +0xdb, 0xdb, 0xdb, 0xdb, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0xdc, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xdc, 0x66, 0x66, +0x66, 0x66, 0x66, 0x7c, 0x60, 0x60, 0xf0, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x76, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0x7c, 0x0c, 0x0c, 0x1e, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0xdc, 0x76, 0x66, 0x60, 0x60, 0x60, 0xf0, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, 0x60, +0x38, 0x0c, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x30, +0x30, 0xfc, 0x30, 0x30, 0x30, 0x30, 0x36, 0x1c, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0x76, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0xc3, 0xc3, +0xc3, 0x66, 0x3c, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0xc3, 0xc3, 0xc3, 0xdb, 0xdb, 0xff, 0x66, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0x66, 0x3c, 0x18, 0x3c, 0x66, 0xc3, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0xc6, 0xc6, +0xc6, 0xc6, 0xc6, 0x7e, 0x06, 0x0c, 0xf8, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0xfe, 0xcc, 0x18, 0x30, 0x60, 0xc6, 0xfe, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x0e, 0x18, 0x18, 0x18, 0x70, 0x18, 0x18, 0x18, 0x18, 0x0e, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18, 0x00, 0x18, +0x18, 0x18, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x70, 0x18, +0x18, 0x18, 0x0e, 0x18, 0x18, 0x18, 0x18, 0x70, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x76, 0xdc, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x6c, 0xc6, +0xc6, 0xc6, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x66, +0xc2, 0xc0, 0xc0, 0xc0, 0xc2, 0x66, 0x3c, 0x0c, 0x06, 0x7c, 0x00, 0x00, +0x00, 0x00, 0xcc, 0x00, 0x00, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0x76, +0x00, 0x00, 0x00, 0x00, 0x00, 0x0c, 0x18, 0x30, 0x00, 0x7c, 0xc6, 0xfe, +0xc0, 0xc0, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x6c, +0x00, 0x78, 0x0c, 0x7c, 0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0xcc, 0x00, 0x00, 0x78, 0x0c, 0x7c, 0xcc, 0xcc, 0xcc, 0x76, +0x00, 0x00, 0x00, 0x00, 0x00, 0x60, 0x30, 0x18, 0x00, 0x78, 0x0c, 0x7c, +0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x38, 0x6c, 0x38, +0x00, 0x78, 0x0c, 0x7c, 0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x3c, 0x66, 0x60, 0x60, 0x66, 0x3c, 0x0c, 0x06, +0x3c, 0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x6c, 0x00, 0x7c, 0xc6, 0xfe, +0xc0, 0xc0, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00, +0x00, 0x7c, 0xc6, 0xfe, 0xc0, 0xc0, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, +0x00, 0x60, 0x30, 0x18, 0x00, 0x7c, 0xc6, 0xfe, 0xc0, 0xc0, 0xc6, 0x7c, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x66, 0x00, 0x00, 0x38, 0x18, 0x18, +0x18, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x3c, 0x66, +0x00, 0x38, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00, +0x00, 0x60, 0x30, 0x18, 0x00, 0x38, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c, +0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00, 0x10, 0x38, 0x6c, 0xc6, 0xc6, +0xfe, 0xc6, 0xc6, 0xc6, 0x00, 0x00, 0x00, 0x00, 0x38, 0x6c, 0x38, 0x00, +0x38, 0x6c, 0xc6, 0xc6, 0xfe, 0xc6, 0xc6, 0xc6, 0x00, 0x00, 0x00, 0x00, +0x18, 0x30, 0x60, 0x00, 0xfe, 0x66, 0x60, 0x7c, 0x60, 0x60, 0x66, 0xfe, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x6e, 0x3b, 0x1b, +0x7e, 0xd8, 0xdc, 0x77, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3e, 0x6c, +0xcc, 0xcc, 0xfe, 0xcc, 0xcc, 0xcc, 0xcc, 0xce, 0x00, 0x00, 0x00, 0x00, +0x00, 0x10, 0x38, 0x6c, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00, 0x00, 0x7c, 0xc6, 0xc6, +0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x60, 0x30, 0x18, +0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, +0x00, 0x30, 0x78, 0xcc, 0x00, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0x76, +0x00, 0x00, 0x00, 0x00, 0x00, 0x60, 0x30, 0x18, 0x00, 0xcc, 0xcc, 0xcc, +0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00, +0x00, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7e, 0x06, 0x0c, 0x78, 0x00, +0x00, 0xc6, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c, +0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, +0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x7e, +0xc3, 0xc0, 0xc0, 0xc0, 0xc3, 0x7e, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, +0x00, 0x38, 0x6c, 0x64, 0x60, 0xf0, 0x60, 0x60, 0x60, 0x60, 0xe6, 0xfc, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0x66, 0x3c, 0x18, 0xff, 0x18, +0xff, 0x18, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfc, 0x66, 0x66, +0x7c, 0x62, 0x66, 0x6f, 0x66, 0x66, 0x66, 0xf3, 0x00, 0x00, 0x00, 0x00, +0x00, 0x0e, 0x1b, 0x18, 0x18, 0x18, 0x7e, 0x18, 0x18, 0x18, 0x18, 0x18, +0xd8, 0x70, 0x00, 0x00, 0x00, 0x18, 0x30, 0x60, 0x00, 0x78, 0x0c, 0x7c, +0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0c, 0x18, 0x30, +0x00, 0x38, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00, +0x00, 0x18, 0x30, 0x60, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c, +0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x30, 0x60, 0x00, 0xcc, 0xcc, 0xcc, +0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x76, 0xdc, +0x00, 0xdc, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66, 0x00, 0x00, 0x00, 0x00, +0x76, 0xdc, 0x00, 0xc6, 0xe6, 0xf6, 0xfe, 0xde, 0xce, 0xc6, 0xc6, 0xc6, +0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x6c, 0x6c, 0x3e, 0x00, 0x7e, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x38, 0x6c, 0x6c, +0x38, 0x00, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x30, 0x30, 0x00, 0x30, 0x30, 0x60, 0xc0, 0xc6, 0xc6, 0x7c, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0xc0, +0xc0, 0xc0, 0xc0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0xfe, 0x06, 0x06, 0x06, 0x06, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0xc0, 0xc0, 0xc2, 0xc6, 0xcc, 0x18, 0x30, 0x60, 0xce, 0x9b, 0x06, +0x0c, 0x1f, 0x00, 0x00, 0x00, 0xc0, 0xc0, 0xc2, 0xc6, 0xcc, 0x18, 0x30, +0x66, 0xce, 0x96, 0x3e, 0x06, 0x06, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, +0x00, 0x18, 0x18, 0x18, 0x3c, 0x3c, 0x3c, 0x18, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x36, 0x6c, 0xd8, 0x6c, 0x36, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xd8, 0x6c, 0x36, +0x6c, 0xd8, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x11, 0x44, 0x11, 0x44, +0x11, 0x44, 0x11, 0x44, 0x11, 0x44, 0x11, 0x44, 0x11, 0x44, 0x11, 0x44, +0x55, 0xaa, 0x55, 0xaa, 0x55, 0xaa, 0x55, 0xaa, 0x55, 0xaa, 0x55, 0xaa, +0x55, 0xaa, 0x55, 0xaa, 0xdd, 0x77, 0xdd, 0x77, 0xdd, 0x77, 0xdd, 0x77, +0xdd, 0x77, 0xdd, 0x77, 0xdd, 0x77, 0xdd, 0x77, 0x18, 0x18, 0x18, 0x18, +0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, +0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0xf8, 0x18, 0x18, 0x18, 0x18, +0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0xf8, 0x18, 0xf8, +0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x36, 0x36, 0x36, 0x36, +0x36, 0x36, 0x36, 0xf6, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0x36, 0x36, 0x36, 0x36, +0x36, 0x36, 0x36, 0x36, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf8, 0x18, 0xf8, +0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x36, 0x36, 0x36, 0x36, +0x36, 0xf6, 0x06, 0xf6, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, +0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, +0x36, 0x36, 0x36, 0x36, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0x06, 0xf6, +0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, +0x36, 0xf6, 0x06, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0xfe, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18, 0x18, 0xf8, 0x18, 0xf8, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0xf8, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, +0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x1f, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0xff, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0xff, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, +0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x1f, 0x18, 0x18, 0x18, 0x18, +0x18, 0x18, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18, +0x18, 0x18, 0x18, 0xff, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, +0x18, 0x18, 0x18, 0x18, 0x18, 0x1f, 0x18, 0x1f, 0x18, 0x18, 0x18, 0x18, +0x18, 0x18, 0x18, 0x18, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x37, +0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, +0x36, 0x37, 0x30, 0x3f, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x3f, 0x30, 0x37, 0x36, 0x36, 0x36, 0x36, +0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0xf7, 0x00, 0xff, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0xff, 0x00, 0xf7, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, +0x36, 0x36, 0x36, 0x36, 0x36, 0x37, 0x30, 0x37, 0x36, 0x36, 0x36, 0x36, +0x36, 0x36, 0x36, 0x36, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0x00, 0xff, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x36, 0x36, 0x36, 0x36, +0x36, 0xf7, 0x00, 0xf7, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, +0x18, 0x18, 0x18, 0x18, 0x18, 0xff, 0x00, 0xff, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0xff, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0xff, 0x00, 0xff, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0x36, 0x36, 0x36, 0x36, +0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x3f, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18, +0x18, 0x1f, 0x18, 0x1f, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x1f, 0x18, 0x1f, 0x18, 0x18, 0x18, 0x18, +0x18, 0x18, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3f, +0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, +0x36, 0x36, 0x36, 0xff, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, +0x18, 0x18, 0x18, 0x18, 0x18, 0xff, 0x18, 0xff, 0x18, 0x18, 0x18, 0x18, +0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0xf8, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x1f, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, +0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, +0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, +0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xf0, 0xf0, 0xf0, 0xf0, +0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, +0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, +0x0f, 0x0f, 0x0f, 0x0f, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x76, 0xdc, 0xd8, 0xd8, 0xd8, 0xdc, 0x76, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x78, 0xcc, 0xcc, 0xcc, 0xd8, 0xcc, 0xc6, 0xc6, 0xc6, 0xcc, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0xc6, 0xc6, 0xc0, 0xc0, 0xc0, +0xc0, 0xc0, 0xc0, 0xc0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0xfe, 0x6c, 0x6c, 0x6c, 0x6c, 0x6c, 0x6c, 0x6c, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0xfe, 0xc6, 0x60, 0x30, 0x18, 0x30, 0x60, 0xc6, 0xfe, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0xd8, 0xd8, +0xd8, 0xd8, 0xd8, 0x70, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x66, 0x66, 0x66, 0x66, 0x66, 0x7c, 0x60, 0x60, 0xc0, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x76, 0xdc, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0x18, 0x3c, 0x66, 0x66, +0x66, 0x3c, 0x18, 0x7e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x38, +0x6c, 0xc6, 0xc6, 0xfe, 0xc6, 0xc6, 0x6c, 0x38, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x38, 0x6c, 0xc6, 0xc6, 0xc6, 0x6c, 0x6c, 0x6c, 0x6c, 0xee, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x1e, 0x30, 0x18, 0x0c, 0x3e, 0x66, +0x66, 0x66, 0x66, 0x3c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x7e, 0xdb, 0xdb, 0xdb, 0x7e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x03, 0x06, 0x7e, 0xdb, 0xdb, 0xf3, 0x7e, 0x60, 0xc0, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x1c, 0x30, 0x60, 0x60, 0x7c, 0x60, +0x60, 0x60, 0x30, 0x1c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, +0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0xfe, 0x00, 0x00, 0xfe, 0x00, 0x00, 0xfe, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x7e, 0x18, +0x18, 0x00, 0x00, 0xff, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x30, +0x18, 0x0c, 0x06, 0x0c, 0x18, 0x30, 0x00, 0x7e, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x0c, 0x18, 0x30, 0x60, 0x30, 0x18, 0x0c, 0x00, 0x7e, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0e, 0x1b, 0x1b, 0x1b, 0x18, 0x18, +0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, +0x18, 0x18, 0x18, 0x18, 0xd8, 0xd8, 0xd8, 0x70, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x00, 0x7e, 0x00, 0x18, 0x18, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x76, 0xdc, 0x00, +0x76, 0xdc, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x38, 0x6c, 0x6c, +0x38, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0f, 0x0c, 0x0c, +0x0c, 0x0c, 0x0c, 0xec, 0x6c, 0x6c, 0x3c, 0x1c, 0x00, 0x00, 0x00, 0x00, +0x00, 0xd8, 0x6c, 0x6c, 0x6c, 0x6c, 0x6c, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x70, 0xd8, 0x30, 0x60, 0xc8, 0xf8, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x7c, 0x7c, 0x7c, 0x7c, 0x7c, 0x7c, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, +}; diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c new file mode 100644 index 000000000000..b91345fa0805 --- /dev/null +++ b/arch/powerpc/kernel/cputable.c @@ -0,0 +1,996 @@ +/* + * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org) + * + * Modifications for ppc64: + * Copyright (C) 2003 Dave Engebretsen <engebret@us.ibm.com> + * + * 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/string.h> +#include <linux/sched.h> +#include <linux/threads.h> +#include <linux/init.h> +#include <linux/module.h> + +#include <asm/oprofile_impl.h> +#include <asm/cputable.h> + +struct cpu_spec* cur_cpu_spec = NULL; +EXPORT_SYMBOL(cur_cpu_spec); + +/* NOTE: + * Unlike ppc32, ppc64 will only call this once for the boot CPU, it's + * the responsibility of the appropriate CPU save/restore functions to + * eventually copy these settings over. Those save/restore aren't yet + * part of the cputable though. That has to be fixed for both ppc32 + * and ppc64 + */ +#ifdef CONFIG_PPC64 +extern void __setup_cpu_power3(unsigned long offset, struct cpu_spec* spec); +extern void __setup_cpu_power4(unsigned long offset, struct cpu_spec* spec); +extern void __setup_cpu_be(unsigned long offset, struct cpu_spec* spec); +#else +extern void __setup_cpu_603(unsigned long offset, struct cpu_spec* spec); +extern void __setup_cpu_604(unsigned long offset, struct cpu_spec* spec); +extern void __setup_cpu_750(unsigned long offset, struct cpu_spec* spec); +extern void __setup_cpu_750cx(unsigned long offset, struct cpu_spec* spec); +extern void __setup_cpu_750fx(unsigned long offset, struct cpu_spec* spec); +extern void __setup_cpu_7400(unsigned long offset, struct cpu_spec* spec); +extern void __setup_cpu_7410(unsigned long offset, struct cpu_spec* spec); +extern void __setup_cpu_745x(unsigned long offset, struct cpu_spec* spec); +#endif /* CONFIG_PPC32 */ +extern void __setup_cpu_ppc970(unsigned long offset, struct cpu_spec* spec); + +/* This table only contains "desktop" CPUs, it need to be filled with embedded + * ones as well... + */ +#define COMMON_USER (PPC_FEATURE_32 | PPC_FEATURE_HAS_FPU | \ + PPC_FEATURE_HAS_MMU) +#define COMMON_USER_PPC64 (COMMON_USER | PPC_FEATURE_64) + + +/* We only set the spe features if the kernel was compiled with + * spe support + */ +#ifdef CONFIG_SPE +#define PPC_FEATURE_SPE_COMP PPC_FEATURE_HAS_SPE +#else +#define PPC_FEATURE_SPE_COMP 0 +#endif + +struct cpu_spec cpu_specs[] = { +#ifdef CONFIG_PPC64 + { /* Power3 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00400000, + .cpu_name = "POWER3 (630)", + .cpu_features = CPU_FTRS_POWER3, + .cpu_user_features = COMMON_USER_PPC64, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 8, + .cpu_setup = __setup_cpu_power3, +#ifdef CONFIG_OPROFILE + .oprofile_cpu_type = "ppc64/power3", + .oprofile_model = &op_model_rs64, +#endif + }, + { /* Power3+ */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00410000, + .cpu_name = "POWER3 (630+)", + .cpu_features = CPU_FTRS_POWER3, + .cpu_user_features = COMMON_USER_PPC64, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 8, + .cpu_setup = __setup_cpu_power3, +#ifdef CONFIG_OPROFILE + .oprofile_cpu_type = "ppc64/power3", + .oprofile_model = &op_model_rs64, +#endif + }, + { /* Northstar */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00330000, + .cpu_name = "RS64-II (northstar)", + .cpu_features = CPU_FTRS_RS64, + .cpu_user_features = COMMON_USER_PPC64, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 8, + .cpu_setup = __setup_cpu_power3, +#ifdef CONFIG_OPROFILE + .oprofile_cpu_type = "ppc64/rs64", + .oprofile_model = &op_model_rs64, +#endif + }, + { /* Pulsar */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00340000, + .cpu_name = "RS64-III (pulsar)", + .cpu_features = CPU_FTRS_RS64, + .cpu_user_features = COMMON_USER_PPC64, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 8, + .cpu_setup = __setup_cpu_power3, +#ifdef CONFIG_OPROFILE + .oprofile_cpu_type = "ppc64/rs64", + .oprofile_model = &op_model_rs64, +#endif + }, + { /* I-star */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00360000, + .cpu_name = "RS64-III (icestar)", + .cpu_features = CPU_FTRS_RS64, + .cpu_user_features = COMMON_USER_PPC64, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 8, + .cpu_setup = __setup_cpu_power3, +#ifdef CONFIG_OPROFILE + .oprofile_cpu_type = "ppc64/rs64", + .oprofile_model = &op_model_rs64, +#endif + }, + { /* S-star */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00370000, + .cpu_name = "RS64-IV (sstar)", + .cpu_features = CPU_FTRS_RS64, + .cpu_user_features = COMMON_USER_PPC64, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 8, + .cpu_setup = __setup_cpu_power3, +#ifdef CONFIG_OPROFILE + .oprofile_cpu_type = "ppc64/rs64", + .oprofile_model = &op_model_rs64, +#endif + }, + { /* Power4 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00350000, + .cpu_name = "POWER4 (gp)", + .cpu_features = CPU_FTRS_POWER4, + .cpu_user_features = COMMON_USER_PPC64, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 8, + .cpu_setup = __setup_cpu_power4, +#ifdef CONFIG_OPROFILE + .oprofile_cpu_type = "ppc64/power4", + .oprofile_model = &op_model_rs64, +#endif + }, + { /* Power4+ */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00380000, + .cpu_name = "POWER4+ (gq)", + .cpu_features = CPU_FTRS_POWER4, + .cpu_user_features = COMMON_USER_PPC64, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 8, + .cpu_setup = __setup_cpu_power4, +#ifdef CONFIG_OPROFILE + .oprofile_cpu_type = "ppc64/power4", + .oprofile_model = &op_model_power4, +#endif + }, + { /* PPC970 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00390000, + .cpu_name = "PPC970", + .cpu_features = CPU_FTRS_PPC970, + .cpu_user_features = COMMON_USER_PPC64 | + PPC_FEATURE_HAS_ALTIVEC_COMP, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 8, + .cpu_setup = __setup_cpu_ppc970, +#ifdef CONFIG_OPROFILE + .oprofile_cpu_type = "ppc64/970", + .oprofile_model = &op_model_power4, +#endif + }, +#endif /* CONFIG_PPC64 */ +#if defined(CONFIG_PPC64) || defined(CONFIG_POWER4) + { /* PPC970FX */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x003c0000, + .cpu_name = "PPC970FX", +#ifdef CONFIG_PPC32 + .cpu_features = CPU_FTRS_970_32, +#else + .cpu_features = CPU_FTRS_PPC970, +#endif + .cpu_user_features = COMMON_USER_PPC64 | + PPC_FEATURE_HAS_ALTIVEC_COMP, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 8, + .cpu_setup = __setup_cpu_ppc970, +#ifdef CONFIG_OPROFILE + .oprofile_cpu_type = "ppc64/970", + .oprofile_model = &op_model_power4, +#endif + }, +#endif /* defined(CONFIG_PPC64) || defined(CONFIG_POWER4) */ +#ifdef CONFIG_PPC64 + { /* PPC970MP */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00440000, + .cpu_name = "PPC970MP", + .cpu_features = CPU_FTRS_PPC970, + .cpu_user_features = COMMON_USER_PPC64 | + PPC_FEATURE_HAS_ALTIVEC_COMP, + .icache_bsize = 128, + .dcache_bsize = 128, + .cpu_setup = __setup_cpu_ppc970, +#ifdef CONFIG_OPROFILE + .oprofile_cpu_type = "ppc64/970", + .oprofile_model = &op_model_power4, +#endif + }, + { /* Power5 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x003a0000, + .cpu_name = "POWER5 (gr)", + .cpu_features = CPU_FTRS_POWER5, + .cpu_user_features = COMMON_USER_PPC64, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .cpu_setup = __setup_cpu_power4, +#ifdef CONFIG_OPROFILE + .oprofile_cpu_type = "ppc64/power5", + .oprofile_model = &op_model_power4, +#endif + }, + { /* Power5 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x003b0000, + .cpu_name = "POWER5 (gs)", + .cpu_features = CPU_FTRS_POWER5, + .cpu_user_features = COMMON_USER_PPC64, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .cpu_setup = __setup_cpu_power4, +#ifdef CONFIG_OPROFILE + .oprofile_cpu_type = "ppc64/power5", + .oprofile_model = &op_model_power4, +#endif + }, + { /* BE DD1.x */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00700000, + .cpu_name = "Cell Broadband Engine", + .cpu_features = CPU_FTRS_CELL, + .cpu_user_features = COMMON_USER_PPC64 | + PPC_FEATURE_HAS_ALTIVEC_COMP, + .icache_bsize = 128, + .dcache_bsize = 128, + .cpu_setup = __setup_cpu_be, + }, + { /* default match */ + .pvr_mask = 0x00000000, + .pvr_value = 0x00000000, + .cpu_name = "POWER4 (compatible)", + .cpu_features = CPU_FTRS_COMPATIBLE, + .cpu_user_features = COMMON_USER_PPC64, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .cpu_setup = __setup_cpu_power4, + } +#endif /* CONFIG_PPC64 */ +#ifdef CONFIG_PPC32 +#if CLASSIC_PPC + { /* 601 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00010000, + .cpu_name = "601", + .cpu_features = CPU_FTRS_PPC601, + .cpu_user_features = COMMON_USER | PPC_FEATURE_601_INSTR | + PPC_FEATURE_UNIFIED_CACHE | PPC_FEATURE_NO_TB, + .icache_bsize = 32, + .dcache_bsize = 32, + }, + { /* 603 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00030000, + .cpu_name = "603", + .cpu_features = CPU_FTRS_603, + .cpu_user_features = COMMON_USER, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_603 + }, + { /* 603e */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00060000, + .cpu_name = "603e", + .cpu_features = CPU_FTRS_603, + .cpu_user_features = COMMON_USER, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_603 + }, + { /* 603ev */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00070000, + .cpu_name = "603ev", + .cpu_features = CPU_FTRS_603, + .cpu_user_features = COMMON_USER, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_603 + }, + { /* 604 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00040000, + .cpu_name = "604", + .cpu_features = CPU_FTRS_604, + .cpu_user_features = COMMON_USER, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 2, + .cpu_setup = __setup_cpu_604 + }, + { /* 604e */ + .pvr_mask = 0xfffff000, + .pvr_value = 0x00090000, + .cpu_name = "604e", + .cpu_features = CPU_FTRS_604, + .cpu_user_features = COMMON_USER, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .cpu_setup = __setup_cpu_604 + }, + { /* 604r */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00090000, + .cpu_name = "604r", + .cpu_features = CPU_FTRS_604, + .cpu_user_features = COMMON_USER, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .cpu_setup = __setup_cpu_604 + }, + { /* 604ev */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x000a0000, + .cpu_name = "604ev", + .cpu_features = CPU_FTRS_604, + .cpu_user_features = COMMON_USER, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .cpu_setup = __setup_cpu_604 + }, + { /* 740/750 (0x4202, don't support TAU ?) */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x00084202, + .cpu_name = "740/750", + .cpu_features = CPU_FTRS_740_NOTAU, + .cpu_user_features = COMMON_USER, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .cpu_setup = __setup_cpu_750 + }, + { /* 750CX (80100 and 8010x?) */ + .pvr_mask = 0xfffffff0, + .pvr_value = 0x00080100, + .cpu_name = "750CX", + .cpu_features = CPU_FTRS_750, + .cpu_user_features = COMMON_USER, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .cpu_setup = __setup_cpu_750cx + }, + { /* 750CX (82201 and 82202) */ + .pvr_mask = 0xfffffff0, + .pvr_value = 0x00082200, + .cpu_name = "750CX", + .cpu_features = CPU_FTRS_750, + .cpu_user_features = COMMON_USER, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .cpu_setup = __setup_cpu_750cx + }, + { /* 750CXe (82214) */ + .pvr_mask = 0xfffffff0, + .pvr_value = 0x00082210, + .cpu_name = "750CXe", + .cpu_features = CPU_FTRS_750, + .cpu_user_features = COMMON_USER, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .cpu_setup = __setup_cpu_750cx + }, + { /* 750CXe "Gekko" (83214) */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x00083214, + .cpu_name = "750CXe", + .cpu_features = CPU_FTRS_750, + .cpu_user_features = COMMON_USER, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .cpu_setup = __setup_cpu_750cx + }, + { /* 745/755 */ + .pvr_mask = 0xfffff000, + .pvr_value = 0x00083000, + .cpu_name = "745/755", + .cpu_features = CPU_FTRS_750, + .cpu_user_features = COMMON_USER, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .cpu_setup = __setup_cpu_750 + }, + { /* 750FX rev 1.x */ + .pvr_mask = 0xffffff00, + .pvr_value = 0x70000100, + .cpu_name = "750FX", + .cpu_features = CPU_FTRS_750FX1, + .cpu_user_features = COMMON_USER, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .cpu_setup = __setup_cpu_750 + }, + { /* 750FX rev 2.0 must disable HID0[DPM] */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x70000200, + .cpu_name = "750FX", + .cpu_features = CPU_FTRS_750FX2, + .cpu_user_features = COMMON_USER, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .cpu_setup = __setup_cpu_750 + }, + { /* 750FX (All revs except 2.0) */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x70000000, + .cpu_name = "750FX", + .cpu_features = CPU_FTRS_750FX, + .cpu_user_features = COMMON_USER, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .cpu_setup = __setup_cpu_750fx + }, + { /* 750GX */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x70020000, + .cpu_name = "750GX", + .cpu_features = CPU_FTRS_750GX, + .cpu_user_features = COMMON_USER, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .cpu_setup = __setup_cpu_750fx + }, + { /* 740/750 (L2CR bit need fixup for 740) */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00080000, + .cpu_name = "740/750", + .cpu_features = CPU_FTRS_740, + .cpu_user_features = COMMON_USER, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .cpu_setup = __setup_cpu_750 + }, + { /* 7400 rev 1.1 ? (no TAU) */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x000c1101, + .cpu_name = "7400 (1.1)", + .cpu_features = CPU_FTRS_7400_NOTAU, + .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .cpu_setup = __setup_cpu_7400 + }, + { /* 7400 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x000c0000, + .cpu_name = "7400", + .cpu_features = CPU_FTRS_7400, + .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .cpu_setup = __setup_cpu_7400 + }, + { /* 7410 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x800c0000, + .cpu_name = "7410", + .cpu_features = CPU_FTRS_7400, + .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + .cpu_setup = __setup_cpu_7410 + }, + { /* 7450 2.0 - no doze/nap */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x80000200, + .cpu_name = "7450", + .cpu_features = CPU_FTRS_7450_20, + .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 6, + .cpu_setup = __setup_cpu_745x + }, + { /* 7450 2.1 */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x80000201, + .cpu_name = "7450", + .cpu_features = CPU_FTRS_7450_21, + .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 6, + .cpu_setup = __setup_cpu_745x + }, + { /* 7450 2.3 and newer */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x80000000, + .cpu_name = "7450", + .cpu_features = CPU_FTRS_7450_23, + .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 6, + .cpu_setup = __setup_cpu_745x + }, + { /* 7455 rev 1.x */ + .pvr_mask = 0xffffff00, + .pvr_value = 0x80010100, + .cpu_name = "7455", + .cpu_features = CPU_FTRS_7455_1, + .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 6, + .cpu_setup = __setup_cpu_745x + }, + { /* 7455 rev 2.0 */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x80010200, + .cpu_name = "7455", + .cpu_features = CPU_FTRS_7455_20, + .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 6, + .cpu_setup = __setup_cpu_745x + }, + { /* 7455 others */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x80010000, + .cpu_name = "7455", + .cpu_features = CPU_FTRS_7455, + .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 6, + .cpu_setup = __setup_cpu_745x + }, + { /* 7447/7457 Rev 1.0 */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x80020100, + .cpu_name = "7447/7457", + .cpu_features = CPU_FTRS_7447_10, + .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 6, + .cpu_setup = __setup_cpu_745x + }, + { /* 7447/7457 Rev 1.1 */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x80020101, + .cpu_name = "7447/7457", + .cpu_features = CPU_FTRS_7447_10, + .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 6, + .cpu_setup = __setup_cpu_745x + }, + { /* 7447/7457 Rev 1.2 and later */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x80020000, + .cpu_name = "7447/7457", + .cpu_features = CPU_FTRS_7447, + .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 6, + .cpu_setup = __setup_cpu_745x + }, + { /* 7447A */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x80030000, + .cpu_name = "7447A", + .cpu_features = CPU_FTRS_7447A, + .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 6, + .cpu_setup = __setup_cpu_745x + }, + { /* 7448 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x80040000, + .cpu_name = "7448", + .cpu_features = CPU_FTRS_7447A, + .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 6, + .cpu_setup = __setup_cpu_745x + }, + { /* 82xx (8240, 8245, 8260 are all 603e cores) */ + .pvr_mask = 0x7fff0000, + .pvr_value = 0x00810000, + .cpu_name = "82xx", + .cpu_features = CPU_FTRS_82XX, + .cpu_user_features = COMMON_USER, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_603 + }, + { /* All G2_LE (603e core, plus some) have the same pvr */ + .pvr_mask = 0x7fff0000, + .pvr_value = 0x00820000, + .cpu_name = "G2_LE", + .cpu_features = CPU_FTRS_G2_LE, + .cpu_user_features = COMMON_USER, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_603 + }, + { /* e300 (a 603e core, plus some) on 83xx */ + .pvr_mask = 0x7fff0000, + .pvr_value = 0x00830000, + .cpu_name = "e300", + .cpu_features = CPU_FTRS_E300, + .cpu_user_features = COMMON_USER, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_603 + }, + { /* default match, we assume split I/D cache & TB (non-601)... */ + .pvr_mask = 0x00000000, + .pvr_value = 0x00000000, + .cpu_name = "(generic PPC)", + .cpu_features = CPU_FTRS_CLASSIC32, + .cpu_user_features = COMMON_USER, + .icache_bsize = 32, + .dcache_bsize = 32, + }, +#endif /* CLASSIC_PPC */ +#ifdef CONFIG_8xx + { /* 8xx */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00500000, + .cpu_name = "8xx", + /* CPU_FTR_MAYBE_CAN_DOZE is possible, + * if the 8xx code is there.... */ + .cpu_features = CPU_FTRS_8XX, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .icache_bsize = 16, + .dcache_bsize = 16, + }, +#endif /* CONFIG_8xx */ +#ifdef CONFIG_40x + { /* 403GC */ + .pvr_mask = 0xffffff00, + .pvr_value = 0x00200200, + .cpu_name = "403GC", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .icache_bsize = 16, + .dcache_bsize = 16, + }, + { /* 403GCX */ + .pvr_mask = 0xffffff00, + .pvr_value = 0x00201400, + .cpu_name = "403GCX", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | + PPC_FEATURE_HAS_MMU | PPC_FEATURE_NO_TB, + .icache_bsize = 16, + .dcache_bsize = 16, + }, + { /* 403G ?? */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00200000, + .cpu_name = "403G ??", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .icache_bsize = 16, + .dcache_bsize = 16, + }, + { /* 405GP */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x40110000, + .cpu_name = "405GP", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | + PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .icache_bsize = 32, + .dcache_bsize = 32, + }, + { /* STB 03xxx */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x40130000, + .cpu_name = "STB03xxx", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | + PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .icache_bsize = 32, + .dcache_bsize = 32, + }, + { /* STB 04xxx */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x41810000, + .cpu_name = "STB04xxx", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | + PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .icache_bsize = 32, + .dcache_bsize = 32, + }, + { /* NP405L */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x41610000, + .cpu_name = "NP405L", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | + PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .icache_bsize = 32, + .dcache_bsize = 32, + }, + { /* NP4GS3 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x40B10000, + .cpu_name = "NP4GS3", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | + PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .icache_bsize = 32, + .dcache_bsize = 32, + }, + { /* NP405H */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x41410000, + .cpu_name = "NP405H", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | + PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .icache_bsize = 32, + .dcache_bsize = 32, + }, + { /* 405GPr */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x50910000, + .cpu_name = "405GPr", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | + PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .icache_bsize = 32, + .dcache_bsize = 32, + }, + { /* STBx25xx */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x51510000, + .cpu_name = "STBx25xx", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | + PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .icache_bsize = 32, + .dcache_bsize = 32, + }, + { /* 405LP */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x41F10000, + .cpu_name = "405LP", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .icache_bsize = 32, + .dcache_bsize = 32, + }, + { /* Xilinx Virtex-II Pro */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x20010000, + .cpu_name = "Virtex-II Pro", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | + PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .icache_bsize = 32, + .dcache_bsize = 32, + }, + { /* 405EP */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x51210000, + .cpu_name = "405EP", + .cpu_features = CPU_FTRS_40X, + .cpu_user_features = PPC_FEATURE_32 | + PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .icache_bsize = 32, + .dcache_bsize = 32, + }, + +#endif /* CONFIG_40x */ +#ifdef CONFIG_44x + { + .pvr_mask = 0xf0000fff, + .pvr_value = 0x40000850, + .cpu_name = "440EP Rev. A", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = COMMON_USER, /* 440EP has an FPU */ + .icache_bsize = 32, + .dcache_bsize = 32, + }, + { + .pvr_mask = 0xf0000fff, + .pvr_value = 0x400008d3, + .cpu_name = "440EP Rev. B", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = COMMON_USER, /* 440EP has an FPU */ + .icache_bsize = 32, + .dcache_bsize = 32, + }, + { /* 440GP Rev. B */ + .pvr_mask = 0xf0000fff, + .pvr_value = 0x40000440, + .cpu_name = "440GP Rev. B", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .icache_bsize = 32, + .dcache_bsize = 32, + }, + { /* 440GP Rev. C */ + .pvr_mask = 0xf0000fff, + .pvr_value = 0x40000481, + .cpu_name = "440GP Rev. C", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .icache_bsize = 32, + .dcache_bsize = 32, + }, + { /* 440GX Rev. A */ + .pvr_mask = 0xf0000fff, + .pvr_value = 0x50000850, + .cpu_name = "440GX Rev. A", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .icache_bsize = 32, + .dcache_bsize = 32, + }, + { /* 440GX Rev. B */ + .pvr_mask = 0xf0000fff, + .pvr_value = 0x50000851, + .cpu_name = "440GX Rev. B", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .icache_bsize = 32, + .dcache_bsize = 32, + }, + { /* 440GX Rev. C */ + .pvr_mask = 0xf0000fff, + .pvr_value = 0x50000892, + .cpu_name = "440GX Rev. C", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .icache_bsize = 32, + .dcache_bsize = 32, + }, + { /* 440GX Rev. F */ + .pvr_mask = 0xf0000fff, + .pvr_value = 0x50000894, + .cpu_name = "440GX Rev. F", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .icache_bsize = 32, + .dcache_bsize = 32, + }, + { /* 440SP Rev. A */ + .pvr_mask = 0xff000fff, + .pvr_value = 0x53000891, + .cpu_name = "440SP Rev. A", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .icache_bsize = 32, + .dcache_bsize = 32, + }, +#endif /* CONFIG_44x */ +#ifdef CONFIG_FSL_BOOKE + { /* e200z5 */ + .pvr_mask = 0xfff00000, + .pvr_value = 0x81000000, + .cpu_name = "e200z5", + /* xxx - galak: add CPU_FTR_MAYBE_CAN_DOZE */ + .cpu_features = CPU_FTRS_E200, + .cpu_user_features = PPC_FEATURE_32 | + PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_EFP_SINGLE | + PPC_FEATURE_UNIFIED_CACHE, + .dcache_bsize = 32, + }, + { /* e200z6 */ + .pvr_mask = 0xfff00000, + .pvr_value = 0x81100000, + .cpu_name = "e200z6", + /* xxx - galak: add CPU_FTR_MAYBE_CAN_DOZE */ + .cpu_features = CPU_FTRS_E200, + .cpu_user_features = PPC_FEATURE_32 | + PPC_FEATURE_HAS_MMU | PPC_FEATURE_SPE_COMP | + PPC_FEATURE_HAS_EFP_SINGLE | + PPC_FEATURE_UNIFIED_CACHE, + .dcache_bsize = 32, + }, + { /* e500 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x80200000, + .cpu_name = "e500", + /* xxx - galak: add CPU_FTR_MAYBE_CAN_DOZE */ + .cpu_features = CPU_FTRS_E500, + .cpu_user_features = PPC_FEATURE_32 | + PPC_FEATURE_HAS_MMU | PPC_FEATURE_SPE_COMP | + PPC_FEATURE_HAS_EFP_SINGLE, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + }, + { /* e500v2 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x80210000, + .cpu_name = "e500v2", + /* xxx - galak: add CPU_FTR_MAYBE_CAN_DOZE */ + .cpu_features = CPU_FTRS_E500_2, + .cpu_user_features = PPC_FEATURE_32 | + PPC_FEATURE_HAS_MMU | PPC_FEATURE_SPE_COMP | + PPC_FEATURE_HAS_EFP_SINGLE | PPC_FEATURE_HAS_EFP_DOUBLE, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 4, + }, +#endif +#if !CLASSIC_PPC + { /* default match */ + .pvr_mask = 0x00000000, + .pvr_value = 0x00000000, + .cpu_name = "(generic PPC)", + .cpu_features = CPU_FTRS_GENERIC_32, + .cpu_user_features = PPC_FEATURE_32, + .icache_bsize = 32, + .dcache_bsize = 32, + } +#endif /* !CLASSIC_PPC */ +#endif /* CONFIG_PPC32 */ +}; diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S new file mode 100644 index 000000000000..2e99ae41723c --- /dev/null +++ b/arch/powerpc/kernel/entry_32.S @@ -0,0 +1,1000 @@ +/* + * PowerPC version + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) + * Rewritten by Cort Dougan (cort@fsmlabs.com) for PReP + * Copyright (C) 1996 Cort Dougan <cort@fsmlabs.com> + * Adapted for Power Macintosh by Paul Mackerras. + * Low-level exception handlers and MMU support + * rewritten by Paul Mackerras. + * Copyright (C) 1996 Paul Mackerras. + * MPC8xx modifications Copyright (C) 1997 Dan Malek (dmalek@jlc.net). + * + * This file contains the system call entry code, context switch + * code, and exception/interrupt return code for PowerPC. + * + * 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/errno.h> +#include <linux/sys.h> +#include <linux/threads.h> +#include <asm/reg.h> +#include <asm/page.h> +#include <asm/mmu.h> +#include <asm/cputable.h> +#include <asm/thread_info.h> +#include <asm/ppc_asm.h> +#include <asm/asm-offsets.h> +#include <asm/unistd.h> + +#undef SHOW_SYSCALLS +#undef SHOW_SYSCALLS_TASK + +/* + * MSR_KERNEL is > 0x10000 on 4xx/Book-E since it include MSR_CE. + */ +#if MSR_KERNEL >= 0x10000 +#define LOAD_MSR_KERNEL(r, x) lis r,(x)@h; ori r,r,(x)@l +#else +#define LOAD_MSR_KERNEL(r, x) li r,(x) +#endif + +#ifdef CONFIG_BOOKE +#include "head_booke.h" +#define TRANSFER_TO_HANDLER_EXC_LEVEL(exc_level) \ + mtspr exc_level##_SPRG,r8; \ + BOOKE_LOAD_EXC_LEVEL_STACK(exc_level); \ + lwz r0,GPR10-INT_FRAME_SIZE(r8); \ + stw r0,GPR10(r11); \ + lwz r0,GPR11-INT_FRAME_SIZE(r8); \ + stw r0,GPR11(r11); \ + mfspr r8,exc_level##_SPRG + + .globl mcheck_transfer_to_handler +mcheck_transfer_to_handler: + TRANSFER_TO_HANDLER_EXC_LEVEL(MCHECK) + b transfer_to_handler_full + + .globl debug_transfer_to_handler +debug_transfer_to_handler: + TRANSFER_TO_HANDLER_EXC_LEVEL(DEBUG) + b transfer_to_handler_full + + .globl crit_transfer_to_handler +crit_transfer_to_handler: + TRANSFER_TO_HANDLER_EXC_LEVEL(CRIT) + /* fall through */ +#endif + +#ifdef CONFIG_40x + .globl crit_transfer_to_handler +crit_transfer_to_handler: + lwz r0,crit_r10@l(0) + stw r0,GPR10(r11) + lwz r0,crit_r11@l(0) + stw r0,GPR11(r11) + /* fall through */ +#endif + +/* + * This code finishes saving the registers to the exception frame + * and jumps to the appropriate handler for the exception, turning + * on address translation. + * Note that we rely on the caller having set cr0.eq iff the exception + * occurred in kernel mode (i.e. MSR:PR = 0). + */ + .globl transfer_to_handler_full +transfer_to_handler_full: + SAVE_NVGPRS(r11) + /* fall through */ + + .globl transfer_to_handler +transfer_to_handler: + stw r2,GPR2(r11) + stw r12,_NIP(r11) + stw r9,_MSR(r11) + andi. r2,r9,MSR_PR + mfctr r12 + mfspr r2,SPRN_XER + stw r12,_CTR(r11) + stw r2,_XER(r11) + mfspr r12,SPRN_SPRG3 + addi r2,r12,-THREAD + tovirt(r2,r2) /* set r2 to current */ + beq 2f /* if from user, fix up THREAD.regs */ + addi r11,r1,STACK_FRAME_OVERHEAD + stw r11,PT_REGS(r12) +#if defined(CONFIG_40x) || defined(CONFIG_BOOKE) + /* Check to see if the dbcr0 register is set up to debug. Use the + single-step bit to do this. */ + lwz r12,THREAD_DBCR0(r12) + andis. r12,r12,DBCR0_IC@h + beq+ 3f + /* From user and task is ptraced - load up global dbcr0 */ + li r12,-1 /* clear all pending debug events */ + mtspr SPRN_DBSR,r12 + lis r11,global_dbcr0@ha + tophys(r11,r11) + addi r11,r11,global_dbcr0@l + lwz r12,0(r11) + mtspr SPRN_DBCR0,r12 + lwz r12,4(r11) + addi r12,r12,-1 + stw r12,4(r11) +#endif + b 3f +2: /* if from kernel, check interrupted DOZE/NAP mode and + * check for stack overflow + */ +#ifdef CONFIG_6xx + mfspr r11,SPRN_HID0 + mtcr r11 +BEGIN_FTR_SECTION + bt- 8,power_save_6xx_restore /* Check DOZE */ +END_FTR_SECTION_IFSET(CPU_FTR_CAN_DOZE) +BEGIN_FTR_SECTION + bt- 9,power_save_6xx_restore /* Check NAP */ +END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP) +#endif /* CONFIG_6xx */ + .globl transfer_to_handler_cont +transfer_to_handler_cont: + lwz r11,THREAD_INFO-THREAD(r12) + cmplw r1,r11 /* if r1 <= current->thread_info */ + ble- stack_ovf /* then the kernel stack overflowed */ +3: + mflr r9 + lwz r11,0(r9) /* virtual address of handler */ + lwz r9,4(r9) /* where to go when done */ + FIX_SRR1(r10,r12) + mtspr SPRN_SRR0,r11 + mtspr SPRN_SRR1,r10 + mtlr r9 + SYNC + RFI /* jump to handler, enable MMU */ + +/* + * On kernel stack overflow, load up an initial stack pointer + * and call StackOverflow(regs), which should not return. + */ +stack_ovf: + /* sometimes we use a statically-allocated stack, which is OK. */ + lis r11,_end@h + ori r11,r11,_end@l + cmplw r1,r11 + ble 3b /* r1 <= &_end is OK */ + SAVE_NVGPRS(r11) + addi r3,r1,STACK_FRAME_OVERHEAD + lis r1,init_thread_union@ha + addi r1,r1,init_thread_union@l + addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD + lis r9,StackOverflow@ha + addi r9,r9,StackOverflow@l + LOAD_MSR_KERNEL(r10,MSR_KERNEL) + FIX_SRR1(r10,r12) + mtspr SPRN_SRR0,r9 + mtspr SPRN_SRR1,r10 + SYNC + RFI + +/* + * Handle a system call. + */ + .stabs "arch/powerpc/kernel/",N_SO,0,0,0f + .stabs "entry_32.S",N_SO,0,0,0f +0: + +_GLOBAL(DoSyscall) + stw r0,THREAD+LAST_SYSCALL(r2) + stw r3,ORIG_GPR3(r1) + li r12,0 + stw r12,RESULT(r1) + lwz r11,_CCR(r1) /* Clear SO bit in CR */ + rlwinm r11,r11,0,4,2 + stw r11,_CCR(r1) +#ifdef SHOW_SYSCALLS + bl do_show_syscall +#endif /* SHOW_SYSCALLS */ + rlwinm r10,r1,0,0,(31-THREAD_SHIFT) /* current_thread_info() */ + li r11,0 + stb r11,TI_SC_NOERR(r10) + lwz r11,TI_FLAGS(r10) + andi. r11,r11,_TIF_SYSCALL_T_OR_A + bne- syscall_dotrace +syscall_dotrace_cont: + cmplwi 0,r0,NR_syscalls + lis r10,sys_call_table@h + ori r10,r10,sys_call_table@l + slwi r0,r0,2 + bge- 66f + lwzx r10,r10,r0 /* Fetch system call handler [ptr] */ + mtlr r10 + addi r9,r1,STACK_FRAME_OVERHEAD + PPC440EP_ERR42 + blrl /* Call handler */ + .globl ret_from_syscall +ret_from_syscall: +#ifdef SHOW_SYSCALLS + bl do_show_syscall_exit +#endif + mr r6,r3 + li r11,-_LAST_ERRNO + cmplw 0,r3,r11 + rlwinm r12,r1,0,0,(31-THREAD_SHIFT) /* current_thread_info() */ + blt+ 30f + lbz r11,TI_SC_NOERR(r12) + cmpwi r11,0 + bne 30f + neg r3,r3 + lwz r10,_CCR(r1) /* Set SO bit in CR */ + oris r10,r10,0x1000 + stw r10,_CCR(r1) + + /* disable interrupts so current_thread_info()->flags can't change */ +30: LOAD_MSR_KERNEL(r10,MSR_KERNEL) /* doesn't include MSR_EE */ + SYNC + MTMSRD(r10) + lwz r9,TI_FLAGS(r12) + andi. r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SIGPENDING|_TIF_NEED_RESCHED) + bne- syscall_exit_work +syscall_exit_cont: +#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE) + /* If the process has its own DBCR0 value, load it up. The single + step bit tells us that dbcr0 should be loaded. */ + lwz r0,THREAD+THREAD_DBCR0(r2) + andis. r10,r0,DBCR0_IC@h + bnel- load_dbcr0 +#endif + stwcx. r0,0,r1 /* to clear the reservation */ + lwz r4,_LINK(r1) + lwz r5,_CCR(r1) + mtlr r4 + mtcr r5 + lwz r7,_NIP(r1) + lwz r8,_MSR(r1) + FIX_SRR1(r8, r0) + lwz r2,GPR2(r1) + lwz r1,GPR1(r1) + mtspr SPRN_SRR0,r7 + mtspr SPRN_SRR1,r8 + SYNC + RFI + +66: li r3,-ENOSYS + b ret_from_syscall + + .globl ret_from_fork +ret_from_fork: + REST_NVGPRS(r1) + bl schedule_tail + li r3,0 + b ret_from_syscall + +/* Traced system call support */ +syscall_dotrace: + SAVE_NVGPRS(r1) + li r0,0xc00 + stw r0,_TRAP(r1) + addi r3,r1,STACK_FRAME_OVERHEAD + bl do_syscall_trace_enter + lwz r0,GPR0(r1) /* Restore original registers */ + lwz r3,GPR3(r1) + lwz r4,GPR4(r1) + lwz r5,GPR5(r1) + lwz r6,GPR6(r1) + lwz r7,GPR7(r1) + lwz r8,GPR8(r1) + REST_NVGPRS(r1) + b syscall_dotrace_cont + +syscall_exit_work: + stw r6,RESULT(r1) /* Save result */ + stw r3,GPR3(r1) /* Update return value */ + andi. r0,r9,_TIF_SYSCALL_T_OR_A + beq 5f + ori r10,r10,MSR_EE + SYNC + MTMSRD(r10) /* re-enable interrupts */ + lwz r4,_TRAP(r1) + andi. r4,r4,1 + beq 4f + SAVE_NVGPRS(r1) + li r4,0xc00 + stw r4,_TRAP(r1) +4: + addi r3,r1,STACK_FRAME_OVERHEAD + bl do_syscall_trace_leave + REST_NVGPRS(r1) +2: + lwz r3,GPR3(r1) + LOAD_MSR_KERNEL(r10,MSR_KERNEL) /* doesn't include MSR_EE */ + SYNC + MTMSRD(r10) /* disable interrupts again */ + rlwinm r12,r1,0,0,(31-THREAD_SHIFT) /* current_thread_info() */ + lwz r9,TI_FLAGS(r12) +5: + andi. r0,r9,_TIF_NEED_RESCHED + bne 1f + lwz r5,_MSR(r1) + andi. r5,r5,MSR_PR + beq syscall_exit_cont + andi. r0,r9,_TIF_SIGPENDING + beq syscall_exit_cont + b do_user_signal +1: + ori r10,r10,MSR_EE + SYNC + MTMSRD(r10) /* re-enable interrupts */ + bl schedule + b 2b + +#ifdef SHOW_SYSCALLS +do_show_syscall: +#ifdef SHOW_SYSCALLS_TASK + lis r11,show_syscalls_task@ha + lwz r11,show_syscalls_task@l(r11) + cmp 0,r2,r11 + bnelr +#endif + stw r31,GPR31(r1) + mflr r31 + lis r3,7f@ha + addi r3,r3,7f@l + lwz r4,GPR0(r1) + lwz r5,GPR3(r1) + lwz r6,GPR4(r1) + lwz r7,GPR5(r1) + lwz r8,GPR6(r1) + lwz r9,GPR7(r1) + bl printk + lis r3,77f@ha + addi r3,r3,77f@l + lwz r4,GPR8(r1) + mr r5,r2 + bl printk + lwz r0,GPR0(r1) + lwz r3,GPR3(r1) + lwz r4,GPR4(r1) + lwz r5,GPR5(r1) + lwz r6,GPR6(r1) + lwz r7,GPR7(r1) + lwz r8,GPR8(r1) + mtlr r31 + lwz r31,GPR31(r1) + blr + +do_show_syscall_exit: +#ifdef SHOW_SYSCALLS_TASK + lis r11,show_syscalls_task@ha + lwz r11,show_syscalls_task@l(r11) + cmp 0,r2,r11 + bnelr +#endif + stw r31,GPR31(r1) + mflr r31 + stw r3,RESULT(r1) /* Save result */ + mr r4,r3 + lis r3,79f@ha + addi r3,r3,79f@l + bl printk + lwz r3,RESULT(r1) + mtlr r31 + lwz r31,GPR31(r1) + blr + +7: .string "syscall %d(%x, %x, %x, %x, %x, " +77: .string "%x), current=%p\n" +79: .string " -> %x\n" + .align 2,0 + +#ifdef SHOW_SYSCALLS_TASK + .data + .globl show_syscalls_task +show_syscalls_task: + .long -1 + .text +#endif +#endif /* SHOW_SYSCALLS */ + +/* + * The sigsuspend and rt_sigsuspend system calls can call do_signal + * and thus put the process into the stopped state where we might + * want to examine its user state with ptrace. Therefore we need + * to save all the nonvolatile registers (r13 - r31) before calling + * the C code. + */ + .globl ppc_sigsuspend +ppc_sigsuspend: + SAVE_NVGPRS(r1) + lwz r0,_TRAP(r1) + rlwinm r0,r0,0,0,30 /* clear LSB to indicate full */ + stw r0,_TRAP(r1) /* register set saved */ + b sys_sigsuspend + + .globl ppc_rt_sigsuspend +ppc_rt_sigsuspend: + SAVE_NVGPRS(r1) + lwz r0,_TRAP(r1) + rlwinm r0,r0,0,0,30 + stw r0,_TRAP(r1) + b sys_rt_sigsuspend + + .globl ppc_fork +ppc_fork: + SAVE_NVGPRS(r1) + lwz r0,_TRAP(r1) + rlwinm r0,r0,0,0,30 /* clear LSB to indicate full */ + stw r0,_TRAP(r1) /* register set saved */ + b sys_fork + + .globl ppc_vfork +ppc_vfork: + SAVE_NVGPRS(r1) + lwz r0,_TRAP(r1) + rlwinm r0,r0,0,0,30 /* clear LSB to indicate full */ + stw r0,_TRAP(r1) /* register set saved */ + b sys_vfork + + .globl ppc_clone +ppc_clone: + SAVE_NVGPRS(r1) + lwz r0,_TRAP(r1) + rlwinm r0,r0,0,0,30 /* clear LSB to indicate full */ + stw r0,_TRAP(r1) /* register set saved */ + b sys_clone + + .globl ppc_swapcontext +ppc_swapcontext: + SAVE_NVGPRS(r1) + lwz r0,_TRAP(r1) + rlwinm r0,r0,0,0,30 /* clear LSB to indicate full */ + stw r0,_TRAP(r1) /* register set saved */ + b sys_swapcontext + +/* + * Top-level page fault handling. + * This is in assembler because if do_page_fault tells us that + * it is a bad kernel page fault, we want to save the non-volatile + * registers before calling bad_page_fault. + */ + .globl handle_page_fault +handle_page_fault: + stw r4,_DAR(r1) + addi r3,r1,STACK_FRAME_OVERHEAD + bl do_page_fault + cmpwi r3,0 + beq+ ret_from_except + SAVE_NVGPRS(r1) + lwz r0,_TRAP(r1) + clrrwi r0,r0,1 + stw r0,_TRAP(r1) + mr r5,r3 + addi r3,r1,STACK_FRAME_OVERHEAD + lwz r4,_DAR(r1) + bl bad_page_fault + b ret_from_except_full + +/* + * This routine switches between two different tasks. The process + * state of one is saved on its kernel stack. Then the state + * of the other is restored from its kernel stack. The memory + * management hardware is updated to the second process's state. + * Finally, we can return to the second process. + * On entry, r3 points to the THREAD for the current task, r4 + * points to the THREAD for the new task. + * + * This routine is always called with interrupts disabled. + * + * Note: there are two ways to get to the "going out" portion + * of this code; either by coming in via the entry (_switch) + * or via "fork" which must set up an environment equivalent + * to the "_switch" path. If you change this , you'll have to + * change the fork code also. + * + * The code which creates the new task context is in 'copy_thread' + * in arch/ppc/kernel/process.c + */ +_GLOBAL(_switch) + stwu r1,-INT_FRAME_SIZE(r1) + mflr r0 + stw r0,INT_FRAME_SIZE+4(r1) + /* r3-r12 are caller saved -- Cort */ + SAVE_NVGPRS(r1) + stw r0,_NIP(r1) /* Return to switch caller */ + mfmsr r11 + li r0,MSR_FP /* Disable floating-point */ +#ifdef CONFIG_ALTIVEC +BEGIN_FTR_SECTION + oris r0,r0,MSR_VEC@h /* Disable altivec */ + mfspr r12,SPRN_VRSAVE /* save vrsave register value */ + stw r12,THREAD+THREAD_VRSAVE(r2) +END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) +#endif /* CONFIG_ALTIVEC */ +#ifdef CONFIG_SPE + oris r0,r0,MSR_SPE@h /* Disable SPE */ + mfspr r12,SPRN_SPEFSCR /* save spefscr register value */ + stw r12,THREAD+THREAD_SPEFSCR(r2) +#endif /* CONFIG_SPE */ + and. r0,r0,r11 /* FP or altivec or SPE enabled? */ + beq+ 1f + andc r11,r11,r0 + MTMSRD(r11) + isync +1: stw r11,_MSR(r1) + mfcr r10 + stw r10,_CCR(r1) + stw r1,KSP(r3) /* Set old stack pointer */ + +#ifdef CONFIG_SMP + /* We need a sync somewhere here to make sure that if the + * previous task gets rescheduled on another CPU, it sees all + * stores it has performed on this one. + */ + sync +#endif /* CONFIG_SMP */ + + tophys(r0,r4) + CLR_TOP32(r0) + mtspr SPRN_SPRG3,r0 /* Update current THREAD phys addr */ + lwz r1,KSP(r4) /* Load new stack pointer */ + + /* save the old current 'last' for return value */ + mr r3,r2 + addi r2,r4,-THREAD /* Update current */ + +#ifdef CONFIG_ALTIVEC +BEGIN_FTR_SECTION + lwz r0,THREAD+THREAD_VRSAVE(r2) + mtspr SPRN_VRSAVE,r0 /* if G4, restore VRSAVE reg */ +END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) +#endif /* CONFIG_ALTIVEC */ +#ifdef CONFIG_SPE + lwz r0,THREAD+THREAD_SPEFSCR(r2) + mtspr SPRN_SPEFSCR,r0 /* restore SPEFSCR reg */ +#endif /* CONFIG_SPE */ + + lwz r0,_CCR(r1) + mtcrf 0xFF,r0 + /* r3-r12 are destroyed -- Cort */ + REST_NVGPRS(r1) + + lwz r4,_NIP(r1) /* Return to _switch caller in new task */ + mtlr r4 + addi r1,r1,INT_FRAME_SIZE + blr + + .globl fast_exception_return +fast_exception_return: +#if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE)) + andi. r10,r9,MSR_RI /* check for recoverable interrupt */ + beq 1f /* if not, we've got problems */ +#endif + +2: REST_4GPRS(3, r11) + lwz r10,_CCR(r11) + REST_GPR(1, r11) + mtcr r10 + lwz r10,_LINK(r11) + mtlr r10 + REST_GPR(10, r11) + mtspr SPRN_SRR1,r9 + mtspr SPRN_SRR0,r12 + REST_GPR(9, r11) + REST_GPR(12, r11) + lwz r11,GPR11(r11) + SYNC + RFI + +#if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE)) +/* check if the exception happened in a restartable section */ +1: lis r3,exc_exit_restart_end@ha + addi r3,r3,exc_exit_restart_end@l + cmplw r12,r3 + bge 3f + lis r4,exc_exit_restart@ha + addi r4,r4,exc_exit_restart@l + cmplw r12,r4 + blt 3f + lis r3,fee_restarts@ha + tophys(r3,r3) + lwz r5,fee_restarts@l(r3) + addi r5,r5,1 + stw r5,fee_restarts@l(r3) + mr r12,r4 /* restart at exc_exit_restart */ + b 2b + + .comm fee_restarts,4 + +/* aargh, a nonrecoverable interrupt, panic */ +/* aargh, we don't know which trap this is */ +/* but the 601 doesn't implement the RI bit, so assume it's OK */ +3: +BEGIN_FTR_SECTION + b 2b +END_FTR_SECTION_IFSET(CPU_FTR_601) + li r10,-1 + stw r10,_TRAP(r11) + addi r3,r1,STACK_FRAME_OVERHEAD + lis r10,MSR_KERNEL@h + ori r10,r10,MSR_KERNEL@l + bl transfer_to_handler_full + .long nonrecoverable_exception + .long ret_from_except +#endif + + .globl sigreturn_exit +sigreturn_exit: + subi r1,r3,STACK_FRAME_OVERHEAD + rlwinm r12,r1,0,0,(31-THREAD_SHIFT) /* current_thread_info() */ + lwz r9,TI_FLAGS(r12) + andi. r0,r9,_TIF_SYSCALL_T_OR_A + beq+ ret_from_except_full + bl do_syscall_trace_leave + /* fall through */ + + .globl ret_from_except_full +ret_from_except_full: + REST_NVGPRS(r1) + /* fall through */ + + .globl ret_from_except +ret_from_except: + /* Hard-disable interrupts so that current_thread_info()->flags + * can't change between when we test it and when we return + * from the interrupt. */ + LOAD_MSR_KERNEL(r10,MSR_KERNEL) + SYNC /* Some chip revs have problems here... */ + MTMSRD(r10) /* disable interrupts */ + + lwz r3,_MSR(r1) /* Returning to user mode? */ + andi. r0,r3,MSR_PR + beq resume_kernel + +user_exc_return: /* r10 contains MSR_KERNEL here */ + /* Check current_thread_info()->flags */ + rlwinm r9,r1,0,0,(31-THREAD_SHIFT) + lwz r9,TI_FLAGS(r9) + andi. r0,r9,(_TIF_SIGPENDING|_TIF_NEED_RESCHED) + bne do_work + +restore_user: +#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE) + /* Check whether this process has its own DBCR0 value. The single + step bit tells us that dbcr0 should be loaded. */ + lwz r0,THREAD+THREAD_DBCR0(r2) + andis. r10,r0,DBCR0_IC@h + bnel- load_dbcr0 +#endif + +#ifdef CONFIG_PREEMPT + b restore + +/* N.B. the only way to get here is from the beq following ret_from_except. */ +resume_kernel: + /* check current_thread_info->preempt_count */ + rlwinm r9,r1,0,0,(31-THREAD_SHIFT) + lwz r0,TI_PREEMPT(r9) + cmpwi 0,r0,0 /* if non-zero, just restore regs and return */ + bne restore + lwz r0,TI_FLAGS(r9) + andi. r0,r0,_TIF_NEED_RESCHED + beq+ restore + andi. r0,r3,MSR_EE /* interrupts off? */ + beq restore /* don't schedule if so */ +1: bl preempt_schedule_irq + rlwinm r9,r1,0,0,(31-THREAD_SHIFT) + lwz r3,TI_FLAGS(r9) + andi. r0,r3,_TIF_NEED_RESCHED + bne- 1b +#else +resume_kernel: +#endif /* CONFIG_PREEMPT */ + + /* interrupts are hard-disabled at this point */ +restore: + lwz r0,GPR0(r1) + lwz r2,GPR2(r1) + REST_4GPRS(3, r1) + REST_2GPRS(7, r1) + + lwz r10,_XER(r1) + lwz r11,_CTR(r1) + mtspr SPRN_XER,r10 + mtctr r11 + + PPC405_ERR77(0,r1) + stwcx. r0,0,r1 /* to clear the reservation */ + +#if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE)) + lwz r9,_MSR(r1) + andi. r10,r9,MSR_RI /* check if this exception occurred */ + beql nonrecoverable /* at a bad place (MSR:RI = 0) */ + + lwz r10,_CCR(r1) + lwz r11,_LINK(r1) + mtcrf 0xFF,r10 + mtlr r11 + + /* + * Once we put values in SRR0 and SRR1, we are in a state + * where exceptions are not recoverable, since taking an + * exception will trash SRR0 and SRR1. Therefore we clear the + * MSR:RI bit to indicate this. If we do take an exception, + * we can't return to the point of the exception but we + * can restart the exception exit path at the label + * exc_exit_restart below. -- paulus + */ + LOAD_MSR_KERNEL(r10,MSR_KERNEL & ~MSR_RI) + SYNC + MTMSRD(r10) /* clear the RI bit */ + .globl exc_exit_restart +exc_exit_restart: + lwz r9,_MSR(r1) + lwz r12,_NIP(r1) + FIX_SRR1(r9,r10) + mtspr SPRN_SRR0,r12 + mtspr SPRN_SRR1,r9 + REST_4GPRS(9, r1) + lwz r1,GPR1(r1) + .globl exc_exit_restart_end +exc_exit_restart_end: + SYNC + RFI + +#else /* !(CONFIG_4xx || CONFIG_BOOKE) */ + /* + * This is a bit different on 4xx/Book-E because it doesn't have + * the RI bit in the MSR. + * The TLB miss handler checks if we have interrupted + * the exception exit path and restarts it if so + * (well maybe one day it will... :). + */ + lwz r11,_LINK(r1) + mtlr r11 + lwz r10,_CCR(r1) + mtcrf 0xff,r10 + REST_2GPRS(9, r1) + .globl exc_exit_restart +exc_exit_restart: + lwz r11,_NIP(r1) + lwz r12,_MSR(r1) +exc_exit_start: + mtspr SPRN_SRR0,r11 + mtspr SPRN_SRR1,r12 + REST_2GPRS(11, r1) + lwz r1,GPR1(r1) + .globl exc_exit_restart_end +exc_exit_restart_end: + PPC405_ERR77_SYNC + rfi + b . /* prevent prefetch past rfi */ + +/* + * Returning from a critical interrupt in user mode doesn't need + * to be any different from a normal exception. For a critical + * interrupt in the kernel, we just return (without checking for + * preemption) since the interrupt may have happened at some crucial + * place (e.g. inside the TLB miss handler), and because we will be + * running with r1 pointing into critical_stack, not the current + * process's kernel stack (and therefore current_thread_info() will + * give the wrong answer). + * We have to restore various SPRs that may have been in use at the + * time of the critical interrupt. + * + */ +#ifdef CONFIG_40x +#define PPC_40x_TURN_OFF_MSR_DR \ + /* avoid any possible TLB misses here by turning off MSR.DR, we \ + * assume the instructions here are mapped by a pinned TLB entry */ \ + li r10,MSR_IR; \ + mtmsr r10; \ + isync; \ + tophys(r1, r1); +#else +#define PPC_40x_TURN_OFF_MSR_DR +#endif + +#define RET_FROM_EXC_LEVEL(exc_lvl_srr0, exc_lvl_srr1, exc_lvl_rfi) \ + REST_NVGPRS(r1); \ + lwz r3,_MSR(r1); \ + andi. r3,r3,MSR_PR; \ + LOAD_MSR_KERNEL(r10,MSR_KERNEL); \ + bne user_exc_return; \ + lwz r0,GPR0(r1); \ + lwz r2,GPR2(r1); \ + REST_4GPRS(3, r1); \ + REST_2GPRS(7, r1); \ + lwz r10,_XER(r1); \ + lwz r11,_CTR(r1); \ + mtspr SPRN_XER,r10; \ + mtctr r11; \ + PPC405_ERR77(0,r1); \ + stwcx. r0,0,r1; /* to clear the reservation */ \ + lwz r11,_LINK(r1); \ + mtlr r11; \ + lwz r10,_CCR(r1); \ + mtcrf 0xff,r10; \ + PPC_40x_TURN_OFF_MSR_DR; \ + lwz r9,_DEAR(r1); \ + lwz r10,_ESR(r1); \ + mtspr SPRN_DEAR,r9; \ + mtspr SPRN_ESR,r10; \ + lwz r11,_NIP(r1); \ + lwz r12,_MSR(r1); \ + mtspr exc_lvl_srr0,r11; \ + mtspr exc_lvl_srr1,r12; \ + lwz r9,GPR9(r1); \ + lwz r12,GPR12(r1); \ + lwz r10,GPR10(r1); \ + lwz r11,GPR11(r1); \ + lwz r1,GPR1(r1); \ + PPC405_ERR77_SYNC; \ + exc_lvl_rfi; \ + b .; /* prevent prefetch past exc_lvl_rfi */ + + .globl ret_from_crit_exc +ret_from_crit_exc: + RET_FROM_EXC_LEVEL(SPRN_CSRR0, SPRN_CSRR1, RFCI) + +#ifdef CONFIG_BOOKE + .globl ret_from_debug_exc +ret_from_debug_exc: + RET_FROM_EXC_LEVEL(SPRN_DSRR0, SPRN_DSRR1, RFDI) + + .globl ret_from_mcheck_exc +ret_from_mcheck_exc: + RET_FROM_EXC_LEVEL(SPRN_MCSRR0, SPRN_MCSRR1, RFMCI) +#endif /* CONFIG_BOOKE */ + +/* + * Load the DBCR0 value for a task that is being ptraced, + * having first saved away the global DBCR0. Note that r0 + * has the dbcr0 value to set upon entry to this. + */ +load_dbcr0: + mfmsr r10 /* first disable debug exceptions */ + rlwinm r10,r10,0,~MSR_DE + mtmsr r10 + isync + mfspr r10,SPRN_DBCR0 + lis r11,global_dbcr0@ha + addi r11,r11,global_dbcr0@l + stw r10,0(r11) + mtspr SPRN_DBCR0,r0 + lwz r10,4(r11) + addi r10,r10,1 + stw r10,4(r11) + li r11,-1 + mtspr SPRN_DBSR,r11 /* clear all pending debug events */ + blr + + .comm global_dbcr0,8 +#endif /* !(CONFIG_4xx || CONFIG_BOOKE) */ + +do_work: /* r10 contains MSR_KERNEL here */ + andi. r0,r9,_TIF_NEED_RESCHED + beq do_user_signal + +do_resched: /* r10 contains MSR_KERNEL here */ + ori r10,r10,MSR_EE + SYNC + MTMSRD(r10) /* hard-enable interrupts */ + bl schedule +recheck: + LOAD_MSR_KERNEL(r10,MSR_KERNEL) + SYNC + MTMSRD(r10) /* disable interrupts */ + rlwinm r9,r1,0,0,(31-THREAD_SHIFT) + lwz r9,TI_FLAGS(r9) + andi. r0,r9,_TIF_NEED_RESCHED + bne- do_resched + andi. r0,r9,_TIF_SIGPENDING + beq restore_user +do_user_signal: /* r10 contains MSR_KERNEL here */ + ori r10,r10,MSR_EE + SYNC + MTMSRD(r10) /* hard-enable interrupts */ + /* save r13-r31 in the exception frame, if not already done */ + lwz r3,_TRAP(r1) + andi. r0,r3,1 + beq 2f + SAVE_NVGPRS(r1) + rlwinm r3,r3,0,0,30 + stw r3,_TRAP(r1) +2: li r3,0 + addi r4,r1,STACK_FRAME_OVERHEAD + bl do_signal + REST_NVGPRS(r1) + b recheck + +/* + * We come here when we are at the end of handling an exception + * that occurred at a place where taking an exception will lose + * state information, such as the contents of SRR0 and SRR1. + */ +nonrecoverable: + lis r10,exc_exit_restart_end@ha + addi r10,r10,exc_exit_restart_end@l + cmplw r12,r10 + bge 3f + lis r11,exc_exit_restart@ha + addi r11,r11,exc_exit_restart@l + cmplw r12,r11 + blt 3f + lis r10,ee_restarts@ha + lwz r12,ee_restarts@l(r10) + addi r12,r12,1 + stw r12,ee_restarts@l(r10) + mr r12,r11 /* restart at exc_exit_restart */ + blr +3: /* OK, we can't recover, kill this process */ + /* but the 601 doesn't implement the RI bit, so assume it's OK */ +BEGIN_FTR_SECTION + blr +END_FTR_SECTION_IFSET(CPU_FTR_601) + lwz r3,_TRAP(r1) + andi. r0,r3,1 + beq 4f + SAVE_NVGPRS(r1) + rlwinm r3,r3,0,0,30 + stw r3,_TRAP(r1) +4: addi r3,r1,STACK_FRAME_OVERHEAD + bl nonrecoverable_exception + /* shouldn't return */ + b 4b + + .comm ee_restarts,4 + +/* + * PROM code for specific machines follows. Put it + * here so it's easy to add arch-specific sections later. + * -- Cort + */ +#ifdef CONFIG_PPC_RTAS +/* + * On CHRP, the Run-Time Abstraction Services (RTAS) have to be + * called with the MMU off. + */ +_GLOBAL(enter_rtas) + stwu r1,-INT_FRAME_SIZE(r1) + mflr r0 + stw r0,INT_FRAME_SIZE+4(r1) + LOADADDR(r4, rtas) + lis r6,1f@ha /* physical return address for rtas */ + addi r6,r6,1f@l + tophys(r6,r6) + tophys(r7,r1) + lwz r8,RTASENTRY(r4) + lwz r4,RTASBASE(r4) + mfmsr r9 + stw r9,8(r1) + LOAD_MSR_KERNEL(r0,MSR_KERNEL) + SYNC /* disable interrupts so SRR0/1 */ + MTMSRD(r0) /* don't get trashed */ + li r9,MSR_KERNEL & ~(MSR_IR|MSR_DR) + mtlr r6 + mtspr SPRN_SPRG2,r7 + mtspr SPRN_SRR0,r8 + mtspr SPRN_SRR1,r9 + RFI +1: tophys(r9,r1) + lwz r8,INT_FRAME_SIZE+4(r9) /* get return address */ + lwz r9,8(r9) /* original msr value */ + FIX_SRR1(r9,r0) + addi r1,r1,INT_FRAME_SIZE + li r0,0 + mtspr SPRN_SPRG2,r0 + mtspr SPRN_SRR0,r8 + mtspr SPRN_SRR1,r9 + RFI /* return to caller */ + + .globl machine_check_in_rtas +machine_check_in_rtas: + twi 31,0,0 + /* XXX load up BATs and panic */ + +#endif /* CONFIG_PPC_RTAS */ diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S new file mode 100644 index 000000000000..984a10630714 --- /dev/null +++ b/arch/powerpc/kernel/entry_64.S @@ -0,0 +1,842 @@ +/* + * arch/ppc64/kernel/entry.S + * + * PowerPC version + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) + * Rewritten by Cort Dougan (cort@cs.nmt.edu) for PReP + * Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu> + * Adapted for Power Macintosh by Paul Mackerras. + * Low-level exception handlers and MMU support + * rewritten by Paul Mackerras. + * Copyright (C) 1996 Paul Mackerras. + * MPC8xx modifications Copyright (C) 1997 Dan Malek (dmalek@jlc.net). + * + * This file contains the system call entry code, context switch + * code, and exception/interrupt return code for PowerPC. + * + * 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/errno.h> +#include <asm/unistd.h> +#include <asm/processor.h> +#include <asm/page.h> +#include <asm/mmu.h> +#include <asm/thread_info.h> +#include <asm/ppc_asm.h> +#include <asm/asm-offsets.h> +#include <asm/cputable.h> + +#ifdef CONFIG_PPC_ISERIES +#define DO_SOFT_DISABLE +#endif + +/* + * System calls. + */ + .section ".toc","aw" +.SYS_CALL_TABLE: + .tc .sys_call_table[TC],.sys_call_table + +/* This value is used to mark exception frames on the stack. */ +exception_marker: + .tc ID_72656773_68657265[TC],0x7265677368657265 + + .section ".text" + .align 7 + +#undef SHOW_SYSCALLS + + .globl system_call_common +system_call_common: + andi. r10,r12,MSR_PR + mr r10,r1 + addi r1,r1,-INT_FRAME_SIZE + beq- 1f + ld r1,PACAKSAVE(r13) +1: std r10,0(r1) + std r11,_NIP(r1) + std r12,_MSR(r1) + std r0,GPR0(r1) + std r10,GPR1(r1) + std r2,GPR2(r1) + std r3,GPR3(r1) + std r4,GPR4(r1) + std r5,GPR5(r1) + std r6,GPR6(r1) + std r7,GPR7(r1) + std r8,GPR8(r1) + li r11,0 + std r11,GPR9(r1) + std r11,GPR10(r1) + std r11,GPR11(r1) + std r11,GPR12(r1) + std r9,GPR13(r1) + crclr so + mfcr r9 + mflr r10 + li r11,0xc01 + std r9,_CCR(r1) + std r10,_LINK(r1) + std r11,_TRAP(r1) + mfxer r9 + mfctr r10 + std r9,_XER(r1) + std r10,_CTR(r1) + std r3,ORIG_GPR3(r1) + ld r2,PACATOC(r13) + addi r9,r1,STACK_FRAME_OVERHEAD + ld r11,exception_marker@toc(r2) + std r11,-16(r9) /* "regshere" marker */ +#ifdef CONFIG_PPC_ISERIES + /* Hack for handling interrupts when soft-enabling on iSeries */ + cmpdi cr1,r0,0x5555 /* syscall 0x5555 */ + andi. r10,r12,MSR_PR /* from kernel */ + crand 4*cr0+eq,4*cr1+eq,4*cr0+eq + beq hardware_interrupt_entry + lbz r10,PACAPROCENABLED(r13) + std r10,SOFTE(r1) +#endif + mfmsr r11 + ori r11,r11,MSR_EE + mtmsrd r11,1 + +#ifdef SHOW_SYSCALLS + bl .do_show_syscall + REST_GPR(0,r1) + REST_4GPRS(3,r1) + REST_2GPRS(7,r1) + addi r9,r1,STACK_FRAME_OVERHEAD +#endif + clrrdi r11,r1,THREAD_SHIFT + li r12,0 + ld r10,TI_FLAGS(r11) + stb r12,TI_SC_NOERR(r11) + andi. r11,r10,_TIF_SYSCALL_T_OR_A + bne- syscall_dotrace +syscall_dotrace_cont: + cmpldi 0,r0,NR_syscalls + bge- syscall_enosys + +system_call: /* label this so stack traces look sane */ +/* + * Need to vector to 32 Bit or default sys_call_table here, + * based on caller's run-mode / personality. + */ + ld r11,.SYS_CALL_TABLE@toc(2) + andi. r10,r10,_TIF_32BIT + beq 15f + addi r11,r11,8 /* use 32-bit syscall entries */ + clrldi r3,r3,32 + clrldi r4,r4,32 + clrldi r5,r5,32 + clrldi r6,r6,32 + clrldi r7,r7,32 + clrldi r8,r8,32 +15: + slwi r0,r0,4 + ldx r10,r11,r0 /* Fetch system call handler [ptr] */ + mtctr r10 + bctrl /* Call handler */ + +syscall_exit: +#ifdef SHOW_SYSCALLS + std r3,GPR3(r1) + bl .do_show_syscall_exit + ld r3,GPR3(r1) +#endif + std r3,RESULT(r1) + ld r5,_CCR(r1) + li r10,-_LAST_ERRNO + cmpld r3,r10 + clrrdi r12,r1,THREAD_SHIFT + bge- syscall_error +syscall_error_cont: + + /* check for syscall tracing or audit */ + ld r9,TI_FLAGS(r12) + andi. r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP) + bne- syscall_exit_trace +syscall_exit_trace_cont: + + /* disable interrupts so current_thread_info()->flags can't change, + and so that we don't get interrupted after loading SRR0/1. */ + ld r8,_MSR(r1) + andi. r10,r8,MSR_RI + beq- unrecov_restore + mfmsr r10 + rldicl r10,r10,48,1 + rotldi r10,r10,16 + mtmsrd r10,1 + ld r9,TI_FLAGS(r12) + andi. r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SIGPENDING|_TIF_NEED_RESCHED) + bne- syscall_exit_work + ld r7,_NIP(r1) + stdcx. r0,0,r1 /* to clear the reservation */ + andi. r6,r8,MSR_PR + ld r4,_LINK(r1) + beq- 1f /* only restore r13 if */ + ld r13,GPR13(r1) /* returning to usermode */ +1: ld r2,GPR2(r1) + li r12,MSR_RI + andc r10,r10,r12 + mtmsrd r10,1 /* clear MSR.RI */ + ld r1,GPR1(r1) + mtlr r4 + mtcr r5 + mtspr SPRN_SRR0,r7 + mtspr SPRN_SRR1,r8 + rfid + b . /* prevent speculative execution */ + +syscall_enosys: + li r3,-ENOSYS + std r3,RESULT(r1) + clrrdi r12,r1,THREAD_SHIFT + ld r5,_CCR(r1) + +syscall_error: + lbz r11,TI_SC_NOERR(r12) + cmpwi 0,r11,0 + bne- syscall_error_cont + neg r3,r3 + oris r5,r5,0x1000 /* Set SO bit in CR */ + std r5,_CCR(r1) + b syscall_error_cont + +/* Traced system call support */ +syscall_dotrace: + bl .save_nvgprs + addi r3,r1,STACK_FRAME_OVERHEAD + bl .do_syscall_trace_enter + ld r0,GPR0(r1) /* Restore original registers */ + ld r3,GPR3(r1) + ld r4,GPR4(r1) + ld r5,GPR5(r1) + ld r6,GPR6(r1) + ld r7,GPR7(r1) + ld r8,GPR8(r1) + addi r9,r1,STACK_FRAME_OVERHEAD + clrrdi r10,r1,THREAD_SHIFT + ld r10,TI_FLAGS(r10) + b syscall_dotrace_cont + +syscall_exit_trace: + std r3,GPR3(r1) + bl .save_nvgprs + addi r3,r1,STACK_FRAME_OVERHEAD + bl .do_syscall_trace_leave + REST_NVGPRS(r1) + ld r3,GPR3(r1) + ld r5,_CCR(r1) + clrrdi r12,r1,THREAD_SHIFT + b syscall_exit_trace_cont + +/* Stuff to do on exit from a system call. */ +syscall_exit_work: + std r3,GPR3(r1) + std r5,_CCR(r1) + b .ret_from_except_lite + +/* Save non-volatile GPRs, if not already saved. */ +_GLOBAL(save_nvgprs) + ld r11,_TRAP(r1) + andi. r0,r11,1 + beqlr- + SAVE_NVGPRS(r1) + clrrdi r0,r11,1 + std r0,_TRAP(r1) + blr + +/* + * The sigsuspend and rt_sigsuspend system calls can call do_signal + * and thus put the process into the stopped state where we might + * want to examine its user state with ptrace. Therefore we need + * to save all the nonvolatile registers (r14 - r31) before calling + * the C code. Similarly, fork, vfork and clone need the full + * register state on the stack so that it can be copied to the child. + */ +_GLOBAL(ppc32_sigsuspend) + bl .save_nvgprs + bl .compat_sys_sigsuspend + b 70f + +_GLOBAL(ppc64_rt_sigsuspend) + bl .save_nvgprs + bl .sys_rt_sigsuspend + b 70f + +_GLOBAL(ppc32_rt_sigsuspend) + bl .save_nvgprs + bl .compat_sys_rt_sigsuspend +70: cmpdi 0,r3,0 + /* If it returned an error, we need to return via syscall_exit to set + the SO bit in cr0 and potentially stop for ptrace. */ + bne syscall_exit + /* If sigsuspend() returns zero, we are going into a signal handler. We + may need to call audit_syscall_exit() to mark the exit from sigsuspend() */ +#ifdef CONFIG_AUDIT + ld r3,PACACURRENT(r13) + ld r4,AUDITCONTEXT(r3) + cmpdi 0,r4,0 + beq .ret_from_except /* No audit_context: Leave immediately. */ + li r4, 2 /* AUDITSC_FAILURE */ + li r5,-4 /* It's always -EINTR */ + bl .audit_syscall_exit +#endif + b .ret_from_except + +_GLOBAL(ppc_fork) + bl .save_nvgprs + bl .sys_fork + b syscall_exit + +_GLOBAL(ppc_vfork) + bl .save_nvgprs + bl .sys_vfork + b syscall_exit + +_GLOBAL(ppc_clone) + bl .save_nvgprs + bl .sys_clone + b syscall_exit + +_GLOBAL(ppc32_swapcontext) + bl .save_nvgprs + bl .compat_sys_swapcontext + b 80f + +_GLOBAL(ppc64_swapcontext) + bl .save_nvgprs + bl .sys_swapcontext + b 80f + +_GLOBAL(ppc32_sigreturn) + bl .compat_sys_sigreturn + b 80f + +_GLOBAL(ppc32_rt_sigreturn) + bl .compat_sys_rt_sigreturn + b 80f + +_GLOBAL(ppc64_rt_sigreturn) + bl .sys_rt_sigreturn + +80: cmpdi 0,r3,0 + blt syscall_exit + clrrdi r4,r1,THREAD_SHIFT + ld r4,TI_FLAGS(r4) + andi. r4,r4,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP) + beq+ 81f + addi r3,r1,STACK_FRAME_OVERHEAD + bl .do_syscall_trace_leave +81: b .ret_from_except + +_GLOBAL(ret_from_fork) + bl .schedule_tail + REST_NVGPRS(r1) + li r3,0 + b syscall_exit + +/* + * This routine switches between two different tasks. The process + * state of one is saved on its kernel stack. Then the state + * of the other is restored from its kernel stack. The memory + * management hardware is updated to the second process's state. + * Finally, we can return to the second process, via ret_from_except. + * On entry, r3 points to the THREAD for the current task, r4 + * points to the THREAD for the new task. + * + * Note: there are two ways to get to the "going out" portion + * of this code; either by coming in via the entry (_switch) + * or via "fork" which must set up an environment equivalent + * to the "_switch" path. If you change this you'll have to change + * the fork code also. + * + * The code which creates the new task context is in 'copy_thread' + * in arch/ppc64/kernel/process.c + */ + .align 7 +_GLOBAL(_switch) + mflr r0 + std r0,16(r1) + stdu r1,-SWITCH_FRAME_SIZE(r1) + /* r3-r13 are caller saved -- Cort */ + SAVE_8GPRS(14, r1) + SAVE_10GPRS(22, r1) + mflr r20 /* Return to switch caller */ + mfmsr r22 + li r0, MSR_FP +#ifdef CONFIG_ALTIVEC +BEGIN_FTR_SECTION + oris r0,r0,MSR_VEC@h /* Disable altivec */ + mfspr r24,SPRN_VRSAVE /* save vrsave register value */ + std r24,THREAD_VRSAVE(r3) +END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) +#endif /* CONFIG_ALTIVEC */ + and. r0,r0,r22 + beq+ 1f + andc r22,r22,r0 + mtmsrd r22 + isync +1: std r20,_NIP(r1) + mfcr r23 + std r23,_CCR(r1) + std r1,KSP(r3) /* Set old stack pointer */ + +#ifdef CONFIG_SMP + /* We need a sync somewhere here to make sure that if the + * previous task gets rescheduled on another CPU, it sees all + * stores it has performed on this one. + */ + sync +#endif /* CONFIG_SMP */ + + addi r6,r4,-THREAD /* Convert THREAD to 'current' */ + std r6,PACACURRENT(r13) /* Set new 'current' */ + + ld r8,KSP(r4) /* new stack pointer */ +BEGIN_FTR_SECTION + clrrdi r6,r8,28 /* get its ESID */ + clrrdi r9,r1,28 /* get current sp ESID */ + clrldi. r0,r6,2 /* is new ESID c00000000? */ + cmpd cr1,r6,r9 /* or is new ESID the same as current ESID? */ + cror eq,4*cr1+eq,eq + beq 2f /* if yes, don't slbie it */ + + /* Bolt in the new stack SLB entry */ + ld r7,KSP_VSID(r4) /* Get new stack's VSID */ + oris r0,r6,(SLB_ESID_V)@h + ori r0,r0,(SLB_NUM_BOLTED-1)@l + slbie r6 + slbie r6 /* Workaround POWER5 < DD2.1 issue */ + slbmte r7,r0 + isync + +2: +END_FTR_SECTION_IFSET(CPU_FTR_SLB) + clrrdi r7,r8,THREAD_SHIFT /* base of new stack */ + /* Note: this uses SWITCH_FRAME_SIZE rather than INT_FRAME_SIZE + because we don't need to leave the 288-byte ABI gap at the + top of the kernel stack. */ + addi r7,r7,THREAD_SIZE-SWITCH_FRAME_SIZE + + mr r1,r8 /* start using new stack pointer */ + std r7,PACAKSAVE(r13) + + ld r6,_CCR(r1) + mtcrf 0xFF,r6 + +#ifdef CONFIG_ALTIVEC +BEGIN_FTR_SECTION + ld r0,THREAD_VRSAVE(r4) + mtspr SPRN_VRSAVE,r0 /* if G4, restore VRSAVE reg */ +END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) +#endif /* CONFIG_ALTIVEC */ + + /* r3-r13 are destroyed -- Cort */ + REST_8GPRS(14, r1) + REST_10GPRS(22, r1) + + /* convert old thread to its task_struct for return value */ + addi r3,r3,-THREAD + ld r7,_NIP(r1) /* Return to _switch caller in new task */ + mtlr r7 + addi r1,r1,SWITCH_FRAME_SIZE + blr + + .align 7 +_GLOBAL(ret_from_except) + ld r11,_TRAP(r1) + andi. r0,r11,1 + bne .ret_from_except_lite + REST_NVGPRS(r1) + +_GLOBAL(ret_from_except_lite) + /* + * Disable interrupts so that current_thread_info()->flags + * can't change between when we test it and when we return + * from the interrupt. + */ + mfmsr r10 /* Get current interrupt state */ + rldicl r9,r10,48,1 /* clear MSR_EE */ + rotldi r9,r9,16 + mtmsrd r9,1 /* Update machine state */ + +#ifdef CONFIG_PREEMPT + clrrdi r9,r1,THREAD_SHIFT /* current_thread_info() */ + li r0,_TIF_NEED_RESCHED /* bits to check */ + ld r3,_MSR(r1) + ld r4,TI_FLAGS(r9) + /* Move MSR_PR bit in r3 to _TIF_SIGPENDING position in r0 */ + rlwimi r0,r3,32+TIF_SIGPENDING-MSR_PR_LG,_TIF_SIGPENDING + and. r0,r4,r0 /* check NEED_RESCHED and maybe SIGPENDING */ + bne do_work + +#else /* !CONFIG_PREEMPT */ + ld r3,_MSR(r1) /* Returning to user mode? */ + andi. r3,r3,MSR_PR + beq restore /* if not, just restore regs and return */ + + /* Check current_thread_info()->flags */ + clrrdi r9,r1,THREAD_SHIFT + ld r4,TI_FLAGS(r9) + andi. r0,r4,_TIF_USER_WORK_MASK + bne do_work +#endif + +restore: +#ifdef CONFIG_PPC_ISERIES + ld r5,SOFTE(r1) + cmpdi 0,r5,0 + beq 4f + /* Check for pending interrupts (iSeries) */ + ld r3,PACALPPACA+LPPACAANYINT(r13) + cmpdi r3,0 + beq+ 4f /* skip do_IRQ if no interrupts */ + + li r3,0 + stb r3,PACAPROCENABLED(r13) /* ensure we are soft-disabled */ + ori r10,r10,MSR_EE + mtmsrd r10 /* hard-enable again */ + addi r3,r1,STACK_FRAME_OVERHEAD + bl .do_IRQ + b .ret_from_except_lite /* loop back and handle more */ + +4: stb r5,PACAPROCENABLED(r13) +#endif + + ld r3,_MSR(r1) + andi. r0,r3,MSR_RI + beq- unrecov_restore + + andi. r0,r3,MSR_PR + + /* + * r13 is our per cpu area, only restore it if we are returning to + * userspace + */ + beq 1f + REST_GPR(13, r1) +1: + ld r3,_CTR(r1) + ld r0,_LINK(r1) + mtctr r3 + mtlr r0 + ld r3,_XER(r1) + mtspr SPRN_XER,r3 + + REST_8GPRS(5, r1) + + stdcx. r0,0,r1 /* to clear the reservation */ + + mfmsr r0 + li r2, MSR_RI + andc r0,r0,r2 + mtmsrd r0,1 + + ld r0,_MSR(r1) + mtspr SPRN_SRR1,r0 + + ld r2,_CCR(r1) + mtcrf 0xFF,r2 + ld r2,_NIP(r1) + mtspr SPRN_SRR0,r2 + + ld r0,GPR0(r1) + ld r2,GPR2(r1) + ld r3,GPR3(r1) + ld r4,GPR4(r1) + ld r1,GPR1(r1) + + rfid + b . /* prevent speculative execution */ + +/* Note: this must change if we start using the TIF_NOTIFY_RESUME bit */ +do_work: +#ifdef CONFIG_PREEMPT + andi. r0,r3,MSR_PR /* Returning to user mode? */ + bne user_work + /* Check that preempt_count() == 0 and interrupts are enabled */ + lwz r8,TI_PREEMPT(r9) + cmpwi cr1,r8,0 +#ifdef CONFIG_PPC_ISERIES + ld r0,SOFTE(r1) + cmpdi r0,0 +#else + andi. r0,r3,MSR_EE +#endif + crandc eq,cr1*4+eq,eq + bne restore + /* here we are preempting the current task */ +1: +#ifdef CONFIG_PPC_ISERIES + li r0,1 + stb r0,PACAPROCENABLED(r13) +#endif + ori r10,r10,MSR_EE + mtmsrd r10,1 /* reenable interrupts */ + bl .preempt_schedule + mfmsr r10 + clrrdi r9,r1,THREAD_SHIFT + rldicl r10,r10,48,1 /* disable interrupts again */ + rotldi r10,r10,16 + mtmsrd r10,1 + ld r4,TI_FLAGS(r9) + andi. r0,r4,_TIF_NEED_RESCHED + bne 1b + b restore + +user_work: +#endif + /* Enable interrupts */ + ori r10,r10,MSR_EE + mtmsrd r10,1 + + andi. r0,r4,_TIF_NEED_RESCHED + beq 1f + bl .schedule + b .ret_from_except_lite + +1: bl .save_nvgprs + li r3,0 + addi r4,r1,STACK_FRAME_OVERHEAD + bl .do_signal + b .ret_from_except + +unrecov_restore: + addi r3,r1,STACK_FRAME_OVERHEAD + bl .unrecoverable_exception + b unrecov_restore + +#ifdef CONFIG_PPC_RTAS +/* + * On CHRP, the Run-Time Abstraction Services (RTAS) have to be + * called with the MMU off. + * + * In addition, we need to be in 32b mode, at least for now. + * + * Note: r3 is an input parameter to rtas, so don't trash it... + */ +_GLOBAL(enter_rtas) + mflr r0 + std r0,16(r1) + stdu r1,-RTAS_FRAME_SIZE(r1) /* Save SP and create stack space. */ + + /* Because RTAS is running in 32b mode, it clobbers the high order half + * of all registers that it saves. We therefore save those registers + * RTAS might touch to the stack. (r0, r3-r13 are caller saved) + */ + SAVE_GPR(2, r1) /* Save the TOC */ + SAVE_GPR(13, r1) /* Save paca */ + SAVE_8GPRS(14, r1) /* Save the non-volatiles */ + SAVE_10GPRS(22, r1) /* ditto */ + + mfcr r4 + std r4,_CCR(r1) + mfctr r5 + std r5,_CTR(r1) + mfspr r6,SPRN_XER + std r6,_XER(r1) + mfdar r7 + std r7,_DAR(r1) + mfdsisr r8 + std r8,_DSISR(r1) + mfsrr0 r9 + std r9,_SRR0(r1) + mfsrr1 r10 + std r10,_SRR1(r1) + + /* There is no way it is acceptable to get here with interrupts enabled, + * check it with the asm equivalent of WARN_ON + */ + mfmsr r6 + andi. r0,r6,MSR_EE +1: tdnei r0,0 +.section __bug_table,"a" + .llong 1b,__LINE__ + 0x1000000, 1f, 2f +.previous +.section .rodata,"a" +1: .asciz __FILE__ +2: .asciz "enter_rtas" +.previous + + /* Unfortunately, the stack pointer and the MSR are also clobbered, + * so they are saved in the PACA which allows us to restore + * our original state after RTAS returns. + */ + std r1,PACAR1(r13) + std r6,PACASAVEDMSR(r13) + + /* Setup our real return addr */ + SET_REG_TO_LABEL(r4,.rtas_return_loc) + SET_REG_TO_CONST(r9,KERNELBASE) + sub r4,r4,r9 + mtlr r4 + + li r0,0 + ori r0,r0,MSR_EE|MSR_SE|MSR_BE|MSR_RI + andc r0,r6,r0 + + li r9,1 + rldicr r9,r9,MSR_SF_LG,(63-MSR_SF_LG) + ori r9,r9,MSR_IR|MSR_DR|MSR_FE0|MSR_FE1|MSR_FP + andc r6,r0,r9 + ori r6,r6,MSR_RI + sync /* disable interrupts so SRR0/1 */ + mtmsrd r0 /* don't get trashed */ + + SET_REG_TO_LABEL(r4,rtas) + ld r5,RTASENTRY(r4) /* get the rtas->entry value */ + ld r4,RTASBASE(r4) /* get the rtas->base value */ + + mtspr SPRN_SRR0,r5 + mtspr SPRN_SRR1,r6 + rfid + b . /* prevent speculative execution */ + +_STATIC(rtas_return_loc) + /* relocation is off at this point */ + mfspr r4,SPRN_SPRG3 /* Get PACA */ + SET_REG_TO_CONST(r5, KERNELBASE) + sub r4,r4,r5 /* RELOC the PACA base pointer */ + + mfmsr r6 + li r0,MSR_RI + andc r6,r6,r0 + sync + mtmsrd r6 + + ld r1,PACAR1(r4) /* Restore our SP */ + LOADADDR(r3,.rtas_restore_regs) + ld r4,PACASAVEDMSR(r4) /* Restore our MSR */ + + mtspr SPRN_SRR0,r3 + mtspr SPRN_SRR1,r4 + rfid + b . /* prevent speculative execution */ + +_STATIC(rtas_restore_regs) + /* relocation is on at this point */ + REST_GPR(2, r1) /* Restore the TOC */ + REST_GPR(13, r1) /* Restore paca */ + REST_8GPRS(14, r1) /* Restore the non-volatiles */ + REST_10GPRS(22, r1) /* ditto */ + + mfspr r13,SPRN_SPRG3 + + ld r4,_CCR(r1) + mtcr r4 + ld r5,_CTR(r1) + mtctr r5 + ld r6,_XER(r1) + mtspr SPRN_XER,r6 + ld r7,_DAR(r1) + mtdar r7 + ld r8,_DSISR(r1) + mtdsisr r8 + ld r9,_SRR0(r1) + mtsrr0 r9 + ld r10,_SRR1(r1) + mtsrr1 r10 + + addi r1,r1,RTAS_FRAME_SIZE /* Unstack our frame */ + ld r0,16(r1) /* get return address */ + + mtlr r0 + blr /* return to caller */ + +#endif /* CONFIG_PPC_RTAS */ + +#ifdef CONFIG_PPC_MULTIPLATFORM + +_GLOBAL(enter_prom) + mflr r0 + std r0,16(r1) + stdu r1,-PROM_FRAME_SIZE(r1) /* Save SP and create stack space */ + + /* Because PROM is running in 32b mode, it clobbers the high order half + * of all registers that it saves. We therefore save those registers + * PROM might touch to the stack. (r0, r3-r13 are caller saved) + */ + SAVE_8GPRS(2, r1) + SAVE_GPR(13, r1) + SAVE_8GPRS(14, r1) + SAVE_10GPRS(22, r1) + mfcr r4 + std r4,_CCR(r1) + mfctr r5 + std r5,_CTR(r1) + mfspr r6,SPRN_XER + std r6,_XER(r1) + mfdar r7 + std r7,_DAR(r1) + mfdsisr r8 + std r8,_DSISR(r1) + mfsrr0 r9 + std r9,_SRR0(r1) + mfsrr1 r10 + std r10,_SRR1(r1) + mfmsr r11 + std r11,_MSR(r1) + + /* Get the PROM entrypoint */ + ld r0,GPR4(r1) + mtlr r0 + + /* Switch MSR to 32 bits mode + */ + mfmsr r11 + li r12,1 + rldicr r12,r12,MSR_SF_LG,(63-MSR_SF_LG) + andc r11,r11,r12 + li r12,1 + rldicr r12,r12,MSR_ISF_LG,(63-MSR_ISF_LG) + andc r11,r11,r12 + mtmsrd r11 + isync + + /* Restore arguments & enter PROM here... */ + ld r3,GPR3(r1) + blrl + + /* Just make sure that r1 top 32 bits didn't get + * corrupt by OF + */ + rldicl r1,r1,0,32 + + /* Restore the MSR (back to 64 bits) */ + ld r0,_MSR(r1) + mtmsrd r0 + isync + + /* Restore other registers */ + REST_GPR(2, r1) + REST_GPR(13, r1) + REST_8GPRS(14, r1) + REST_10GPRS(22, r1) + ld r4,_CCR(r1) + mtcr r4 + ld r5,_CTR(r1) + mtctr r5 + ld r6,_XER(r1) + mtspr SPRN_XER,r6 + ld r7,_DAR(r1) + mtdar r7 + ld r8,_DSISR(r1) + mtdsisr r8 + ld r9,_SRR0(r1) + mtsrr0 r9 + ld r10,_SRR1(r1) + mtsrr1 r10 + + addi r1,r1,PROM_FRAME_SIZE + ld r0,16(r1) + mtlr r0 + blr + +#endif /* CONFIG_PPC_MULTIPLATFORM */ diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S new file mode 100644 index 000000000000..4d6001fa1cf2 --- /dev/null +++ b/arch/powerpc/kernel/fpu.S @@ -0,0 +1,144 @@ +/* + * FPU support code, moved here from head.S so that it can be used + * by chips which use other head-whatever.S files. + * + * 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/reg.h> +#include <asm/page.h> +#include <asm/mmu.h> +#include <asm/pgtable.h> +#include <asm/cputable.h> +#include <asm/cache.h> +#include <asm/thread_info.h> +#include <asm/ppc_asm.h> +#include <asm/asm-offsets.h> + +/* + * This task wants to use the FPU now. + * On UP, disable FP for the task which had the FPU previously, + * and save its floating-point registers in its thread_struct. + * Load up this task's FP registers from its thread_struct, + * enable the FPU for the current task and return to the task. + */ +_GLOBAL(load_up_fpu) + mfmsr r5 + ori r5,r5,MSR_FP + SYNC + MTMSRD(r5) /* enable use of fpu now */ + isync +/* + * For SMP, we don't do lazy FPU switching because it just gets too + * horrendously complex, especially when a task switches from one CPU + * to another. Instead we call giveup_fpu in switch_to. + */ +#ifndef CONFIG_SMP + LOADBASE(r3, last_task_used_math) + toreal(r3) + LDL r4,OFF(last_task_used_math)(r3) + CMPI 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) + toreal(r5) + LDL 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) +1: +#endif /* CONFIG_SMP */ + /* enable use of FP after return */ +#ifdef CONFIG_PPC32 + mfspr r5,SPRN_SPRG3 /* current task's THREAD (phys) */ + lwz r4,THREAD_FPEXC_MODE(r5) + ori r9,r9,MSR_FP /* enable FP for current */ + or r9,r9,r4 +#else + ld r4,PACACURRENT(r13) + addi r5,r4,THREAD /* Get THREAD */ + ld r4,THREAD_FPEXC_MODE(r5) + ori r12,r12,MSR_FP + or r12,r12,r4 + std r12,_MSR(r1) +#endif + lfd fr0,THREAD_FPSCR(r5) + mtfsf 0xff,fr0 + REST_32FPRS(0, r5) +#ifndef CONFIG_SMP + subi r4,r5,THREAD + fromreal(r4) + STL r4,OFF(last_task_used_math)(r3) +#endif /* CONFIG_SMP */ + /* restore registers and return */ + /* we haven't used ctr or xer or lr */ + b fast_exception_return + +/* + * giveup_fpu(tsk) + * Disable FP for the task given as the argument, + * and save the floating-point registers in its thread_struct. + * Enables the FPU for use in the kernel on return. + */ +_GLOBAL(giveup_fpu) + mfmsr r5 + ori r5,r5,MSR_FP + SYNC_601 + ISYNC_601 + MTMSRD(r5) /* enable use of fpu now */ + SYNC_601 + isync + CMPI 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 + SAVE_32FPRS(0, r3) + mffs fr0 + stfd fr0,THREAD_FPSCR(r3) + beq 1f + LDL 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) +1: +#ifndef CONFIG_SMP + li r5,0 + LOADBASE(r4,last_task_used_math) + STL r5,OFF(last_task_used_math)(r4) +#endif /* CONFIG_SMP */ + blr + +/* + * These are used in the alignment trap handler when emulating + * single-precision loads and stores. + * We restore and save the fpscr so the task gets the same result + * and exceptions as if the cpu had performed the load or store. + */ + +_GLOBAL(cvt_fd) + lfd 0,THREAD_FPSCR(r5) /* load up fpscr value */ + mtfsf 0xff,0 + lfs 0,0(r3) + stfd 0,0(r4) + mffs 0 + stfd 0,THREAD_FPSCR(r5) /* save new fpscr value */ + blr + +_GLOBAL(cvt_df) + lfd 0,THREAD_FPSCR(r5) /* load up fpscr value */ + mtfsf 0xff,0 + lfd 0,0(r3) + stfs 0,0(r4) + mffs 0 + stfd 0,THREAD_FPSCR(r5) /* save new fpscr value */ + blr diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S new file mode 100644 index 000000000000..b102e3a2415e --- /dev/null +++ b/arch/powerpc/kernel/head_32.S @@ -0,0 +1,1381 @@ +/* + * PowerPC version + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) + * + * Rewritten by Cort Dougan (cort@cs.nmt.edu) for PReP + * Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu> + * Adapted for Power Macintosh by Paul Mackerras. + * Low-level exception handlers and MMU support + * rewritten by Paul Mackerras. + * Copyright (C) 1996 Paul Mackerras. + * MPC8xx modifications Copyright (C) 1997 Dan Malek (dmalek@jlc.net). + * Amiga/APUS changes by Jesper Skov (jskov@cygnus.co.uk). + * + * This file contains the low-level support and setup for the + * PowerPC platform, including trap and interrupt dispatch. + * (The PPC 8xx embedded CPUs use head_8xx.S instead.) + * + * 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/reg.h> +#include <asm/page.h> +#include <asm/mmu.h> +#include <asm/pgtable.h> +#include <asm/cputable.h> +#include <asm/cache.h> +#include <asm/thread_info.h> +#include <asm/ppc_asm.h> +#include <asm/asm-offsets.h> + +#ifdef CONFIG_APUS +#include <asm/amigappc.h> +#endif + +/* 601 only have IBAT; cr0.eq is set on 601 when using this macro */ +#define LOAD_BAT(n, reg, RA, RB) \ + /* see the comment for clear_bats() -- Cort */ \ + li RA,0; \ + mtspr SPRN_IBAT##n##U,RA; \ + mtspr SPRN_DBAT##n##U,RA; \ + lwz RA,(n*16)+0(reg); \ + lwz RB,(n*16)+4(reg); \ + mtspr SPRN_IBAT##n##U,RA; \ + mtspr SPRN_IBAT##n##L,RB; \ + beq 1f; \ + lwz RA,(n*16)+8(reg); \ + lwz RB,(n*16)+12(reg); \ + mtspr SPRN_DBAT##n##U,RA; \ + mtspr SPRN_DBAT##n##L,RB; \ +1: + + .text + .stabs "arch/powerpc/kernel/",N_SO,0,0,0f + .stabs "head_32.S",N_SO,0,0,0f +0: + .globl _stext +_stext: + +/* + * _start is defined this way because the XCOFF loader in the OpenFirmware + * on the powermac expects the entry point to be a procedure descriptor. + */ + .text + .globl _start +_start: + /* + * These are here for legacy reasons, the kernel used to + * need to look like a coff function entry for the pmac + * but we're always started by some kind of bootloader now. + * -- Cort + */ + nop /* used by __secondary_hold on prep (mtx) and chrp smp */ + nop /* used by __secondary_hold on prep (mtx) and chrp smp */ + nop + +/* PMAC + * Enter here with the kernel text, data and bss loaded starting at + * 0, running with virtual == physical mapping. + * r5 points to the prom entry point (the client interface handler + * address). Address translation is turned on, with the prom + * managing the hash table. Interrupts are disabled. The stack + * pointer (r1) points to just below the end of the half-meg region + * from 0x380000 - 0x400000, which is mapped in already. + * + * If we are booted from MacOS via BootX, we enter with the kernel + * image loaded somewhere, and the following values in registers: + * r3: 'BooX' (0x426f6f58) + * r4: virtual address of boot_infos_t + * r5: 0 + * + * APUS + * r3: 'APUS' + * r4: physical address of memory base + * Linux/m68k style BootInfo structure at &_end. + * + * PREP + * This is jumped to on prep systems right after the kernel is relocated + * to its proper place in memory by the boot loader. The expected layout + * of the regs is: + * r3: ptr to residual data + * r4: initrd_start or if no initrd then 0 + * r5: initrd_end - unused if r4 is 0 + * r6: Start of command line string + * r7: End of command line string + * + * This just gets a minimal mmu environment setup so we can call + * start_here() to do the real work. + * -- Cort + */ + + .globl __start +__start: +/* + * We have to do any OF calls before we map ourselves to KERNELBASE, + * because OF may have I/O devices mapped into that area + * (particularly on CHRP). + */ + cmpwi 0,r5,0 + beq 1f + bl prom_init + trap + +1: mr r31,r3 /* save parameters */ + mr r30,r4 + li r24,0 /* cpu # */ + +/* + * early_init() does the early machine identification and does + * the necessary low-level setup and clears the BSS + * -- Cort <cort@fsmlabs.com> + */ + bl early_init + +#ifdef CONFIG_APUS +/* On APUS the __va/__pa constants need to be set to the correct + * values before continuing. + */ + mr r4,r30 + bl fix_mem_constants +#endif /* CONFIG_APUS */ + +/* Switch MMU off, clear BATs and flush TLB. At this point, r3 contains + * the physical address we are running at, returned by early_init() + */ + bl mmu_off +__after_mmu_off: + bl clear_bats + bl flush_tlbs + + bl initial_bats + +/* + * Call setup_cpu for CPU 0 and initialize 6xx Idle + */ + bl reloc_offset + li r24,0 /* cpu# */ + bl call_setup_cpu /* Call setup_cpu for this CPU */ +#ifdef CONFIG_6xx + bl reloc_offset + bl init_idle_6xx +#endif /* CONFIG_6xx */ + + +#ifndef CONFIG_APUS +/* + * We need to run with _start at physical address 0. + * On CHRP, we are loaded at 0x10000 since OF on CHRP uses + * the exception vectors at 0 (and therefore this copy + * overwrites OF's exception vectors with our own). + * The MMU is off at this point. + */ + bl reloc_offset + mr r26,r3 + addis r4,r3,KERNELBASE@h /* current address of _start */ + cmpwi 0,r4,0 /* are we already running at 0? */ + bne relocate_kernel +#endif /* CONFIG_APUS */ +/* + * we now have the 1st 16M of ram mapped with the bats. + * prep needs the mmu to be turned on here, but pmac already has it on. + * this shouldn't bother the pmac since it just gets turned on again + * as we jump to our code at KERNELBASE. -- Cort + * Actually no, pmac doesn't have it on any more. BootX enters with MMU + * off, and in other cases, we now turn it off before changing BATs above. + */ +turn_on_mmu: + mfmsr r0 + ori r0,r0,MSR_DR|MSR_IR + mtspr SPRN_SRR1,r0 + lis r0,start_here@h + ori r0,r0,start_here@l + mtspr SPRN_SRR0,r0 + SYNC + RFI /* enables MMU */ + +/* + * We need __secondary_hold as a place to hold the other cpus on + * an SMP machine, even when we are running a UP kernel. + */ + . = 0xc0 /* for prep bootloader */ + li r3,1 /* MTX only has 1 cpu */ + .globl __secondary_hold +__secondary_hold: + /* tell the master we're here */ + stw r3,__secondary_hold_acknowledge@l(0) +#ifdef CONFIG_SMP +100: lwz r4,0(0) + /* wait until we're told to start */ + cmpw 0,r4,r3 + bne 100b + /* our cpu # was at addr 0 - go */ + mr r24,r3 /* cpu # */ + b __secondary_start +#else + b . +#endif /* CONFIG_SMP */ + + .globl __secondary_hold_spinloop +__secondary_hold_spinloop: + .long 0 + .globl __secondary_hold_acknowledge +__secondary_hold_acknowledge: + .long -1 + +/* + * Exception entry code. This code runs with address translation + * turned off, i.e. using physical addresses. + * We assume sprg3 has the physical address of the current + * task's thread_struct. + */ +#define EXCEPTION_PROLOG \ + mtspr SPRN_SPRG0,r10; \ + mtspr SPRN_SPRG1,r11; \ + mfcr r10; \ + EXCEPTION_PROLOG_1; \ + EXCEPTION_PROLOG_2 + +#define EXCEPTION_PROLOG_1 \ + mfspr r11,SPRN_SRR1; /* check whether user or kernel */ \ + andi. r11,r11,MSR_PR; \ + tophys(r11,r1); /* use tophys(r1) if kernel */ \ + beq 1f; \ + mfspr r11,SPRN_SPRG3; \ + lwz r11,THREAD_INFO-THREAD(r11); \ + addi r11,r11,THREAD_SIZE; \ + tophys(r11,r11); \ +1: subi r11,r11,INT_FRAME_SIZE /* alloc exc. frame */ + + +#define EXCEPTION_PROLOG_2 \ + CLR_TOP32(r11); \ + stw r10,_CCR(r11); /* save registers */ \ + stw r12,GPR12(r11); \ + stw r9,GPR9(r11); \ + mfspr r10,SPRN_SPRG0; \ + stw r10,GPR10(r11); \ + mfspr r12,SPRN_SPRG1; \ + stw r12,GPR11(r11); \ + mflr r10; \ + stw r10,_LINK(r11); \ + mfspr r12,SPRN_SRR0; \ + mfspr r9,SPRN_SRR1; \ + stw r1,GPR1(r11); \ + stw r1,0(r11); \ + tovirt(r1,r11); /* set new kernel sp */ \ + li r10,MSR_KERNEL & ~(MSR_IR|MSR_DR); /* can take exceptions */ \ + MTMSRD(r10); /* (except for mach check in rtas) */ \ + stw r0,GPR0(r11); \ + lis r10,0x7265; /* put exception frame marker */ \ + addi r10,r10,0x6773; \ + stw r10,8(r11); \ + SAVE_4GPRS(3, r11); \ + SAVE_2GPRS(7, r11) + +/* + * Note: code which follows this uses cr0.eq (set if from kernel), + * r11, r12 (SRR0), and r9 (SRR1). + * + * Note2: once we have set r1 we are in a position to take exceptions + * again, and we could thus set MSR:RI at that point. + */ + +/* + * Exception vectors. + */ +#define EXCEPTION(n, label, hdlr, xfer) \ + . = n; \ +label: \ + EXCEPTION_PROLOG; \ + addi r3,r1,STACK_FRAME_OVERHEAD; \ + xfer(n, hdlr) + +#define EXC_XFER_TEMPLATE(n, hdlr, trap, copyee, tfer, ret) \ + li r10,trap; \ + stw r10,_TRAP(r11); \ + li r10,MSR_KERNEL; \ + copyee(r10, r9); \ + bl tfer; \ +i##n: \ + .long hdlr; \ + .long ret + +#define COPY_EE(d, s) rlwimi d,s,0,16,16 +#define NOCOPY(d, s) + +#define EXC_XFER_STD(n, hdlr) \ + EXC_XFER_TEMPLATE(n, hdlr, n, NOCOPY, transfer_to_handler_full, \ + ret_from_except_full) + +#define EXC_XFER_LITE(n, hdlr) \ + EXC_XFER_TEMPLATE(n, hdlr, n+1, NOCOPY, transfer_to_handler, \ + ret_from_except) + +#define EXC_XFER_EE(n, hdlr) \ + EXC_XFER_TEMPLATE(n, hdlr, n, COPY_EE, transfer_to_handler_full, \ + ret_from_except_full) + +#define EXC_XFER_EE_LITE(n, hdlr) \ + EXC_XFER_TEMPLATE(n, hdlr, n+1, COPY_EE, transfer_to_handler, \ + ret_from_except) + +/* System reset */ +/* core99 pmac starts the seconary here by changing the vector, and + putting it back to what it was (unknown_exception) when done. */ +#if defined(CONFIG_GEMINI) && defined(CONFIG_SMP) + . = 0x100 + b __secondary_start_gemini +#else + EXCEPTION(0x100, Reset, unknown_exception, EXC_XFER_STD) +#endif + +/* Machine check */ +/* + * On CHRP, this is complicated by the fact that we could get a + * machine check inside RTAS, and we have no guarantee that certain + * critical registers will have the values we expect. The set of + * registers that might have bad values includes all the GPRs + * and all the BATs. We indicate that we are in RTAS by putting + * a non-zero value, the address of the exception frame to use, + * in SPRG2. The machine check handler checks SPRG2 and uses its + * value if it is non-zero. If we ever needed to free up SPRG2, + * we could use a field in the thread_info or thread_struct instead. + * (Other exception handlers assume that r1 is a valid kernel stack + * pointer when we take an exception from supervisor mode.) + * -- paulus. + */ + . = 0x200 + mtspr SPRN_SPRG0,r10 + mtspr SPRN_SPRG1,r11 + mfcr r10 +#ifdef CONFIG_PPC_CHRP + mfspr r11,SPRN_SPRG2 + cmpwi 0,r11,0 + bne 7f +#endif /* CONFIG_PPC_CHRP */ + EXCEPTION_PROLOG_1 +7: EXCEPTION_PROLOG_2 + addi r3,r1,STACK_FRAME_OVERHEAD +#ifdef CONFIG_PPC_CHRP + mfspr r4,SPRN_SPRG2 + cmpwi cr1,r4,0 + bne cr1,1f +#endif + EXC_XFER_STD(0x200, machine_check_exception) +#ifdef CONFIG_PPC_CHRP +1: b machine_check_in_rtas +#endif + +/* Data access exception. */ + . = 0x300 +DataAccess: + EXCEPTION_PROLOG + mfspr r10,SPRN_DSISR + andis. r0,r10,0xa470 /* weird error? */ + bne 1f /* if not, try to put a PTE */ + mfspr r4,SPRN_DAR /* into the hash table */ + rlwinm r3,r10,32-15,21,21 /* DSISR_STORE -> _PAGE_RW */ + bl hash_page +1: stw r10,_DSISR(r11) + mr r5,r10 + mfspr r4,SPRN_DAR + EXC_XFER_EE_LITE(0x300, handle_page_fault) + + +/* Instruction access exception. */ + . = 0x400 +InstructionAccess: + EXCEPTION_PROLOG + andis. r0,r9,0x4000 /* no pte found? */ + beq 1f /* if so, try to put a PTE */ + li r3,0 /* into the hash table */ + mr r4,r12 /* SRR0 is fault address */ + bl hash_page +1: mr r4,r12 + mr r5,r9 + EXC_XFER_EE_LITE(0x400, handle_page_fault) + +/* External interrupt */ + EXCEPTION(0x500, HardwareInterrupt, do_IRQ, EXC_XFER_LITE) + +/* Alignment exception */ + . = 0x600 +Alignment: + EXCEPTION_PROLOG + mfspr r4,SPRN_DAR + stw r4,_DAR(r11) + mfspr r5,SPRN_DSISR + stw r5,_DSISR(r11) + addi r3,r1,STACK_FRAME_OVERHEAD + EXC_XFER_EE(0x600, alignment_exception) + +/* Program check exception */ + EXCEPTION(0x700, ProgramCheck, program_check_exception, EXC_XFER_STD) + +/* Floating-point unavailable */ + . = 0x800 +FPUnavailable: + EXCEPTION_PROLOG + bne load_up_fpu /* if from user, just load it up */ + addi r3,r1,STACK_FRAME_OVERHEAD + EXC_XFER_EE_LITE(0x800, kernel_fp_unavailable_exception) + +/* Decrementer */ + EXCEPTION(0x900, Decrementer, timer_interrupt, EXC_XFER_LITE) + + EXCEPTION(0xa00, Trap_0a, unknown_exception, EXC_XFER_EE) + EXCEPTION(0xb00, Trap_0b, unknown_exception, EXC_XFER_EE) + +/* System call */ + . = 0xc00 +SystemCall: + EXCEPTION_PROLOG + EXC_XFER_EE_LITE(0xc00, DoSyscall) + +/* Single step - not used on 601 */ + EXCEPTION(0xd00, SingleStep, single_step_exception, EXC_XFER_STD) + EXCEPTION(0xe00, Trap_0e, unknown_exception, EXC_XFER_EE) + +/* + * The Altivec unavailable trap is at 0x0f20. Foo. + * We effectively remap it to 0x3000. + * We include an altivec unavailable exception vector even if + * not configured for Altivec, so that you can't panic a + * non-altivec kernel running on a machine with altivec just + * by executing an altivec instruction. + */ + . = 0xf00 + b Trap_0f + + . = 0xf20 + b AltiVecUnavailable + +Trap_0f: + EXCEPTION_PROLOG + addi r3,r1,STACK_FRAME_OVERHEAD + EXC_XFER_EE(0xf00, unknown_exception) + +/* + * Handle TLB miss for instruction on 603/603e. + * Note: we get an alternate set of r0 - r3 to use automatically. + */ + . = 0x1000 +InstructionTLBMiss: +/* + * r0: stored ctr + * r1: linux style pte ( later becomes ppc hardware pte ) + * r2: ptr to linux-style pte + * r3: scratch + */ + mfctr r0 + /* Get PTE (linux-style) and check access */ + mfspr r3,SPRN_IMISS + lis r1,KERNELBASE@h /* check if kernel address */ + cmplw 0,r3,r1 + mfspr r2,SPRN_SPRG3 + li r1,_PAGE_USER|_PAGE_PRESENT /* low addresses tested as user */ + lwz r2,PGDIR(r2) + blt+ 112f + lis r2,swapper_pg_dir@ha /* if kernel address, use */ + addi r2,r2,swapper_pg_dir@l /* kernel page table */ + mfspr r1,SPRN_SRR1 /* and MSR_PR bit from SRR1 */ + rlwinm r1,r1,32-12,29,29 /* shift MSR_PR to _PAGE_USER posn */ +112: tophys(r2,r2) + rlwimi r2,r3,12,20,29 /* insert top 10 bits of address */ + lwz r2,0(r2) /* get pmd entry */ + rlwinm. r2,r2,0,0,19 /* extract address of pte page */ + beq- InstructionAddressInvalid /* return if no mapping */ + rlwimi r2,r3,22,20,29 /* insert next 10 bits of address */ + lwz r3,0(r2) /* get linux-style pte */ + andc. r1,r1,r3 /* check access & ~permission */ + bne- InstructionAddressInvalid /* return if access not permitted */ + ori r3,r3,_PAGE_ACCESSED /* set _PAGE_ACCESSED in pte */ + /* + * NOTE! We are assuming this is not an SMP system, otherwise + * we would need to update the pte atomically with lwarx/stwcx. + */ + stw r3,0(r2) /* update PTE (accessed bit) */ + /* Convert linux-style PTE to low word of PPC-style PTE */ + rlwinm r1,r3,32-10,31,31 /* _PAGE_RW -> PP lsb */ + rlwinm r2,r3,32-7,31,31 /* _PAGE_DIRTY -> PP lsb */ + and r1,r1,r2 /* writable if _RW and _DIRTY */ + rlwimi r3,r3,32-1,30,30 /* _PAGE_USER -> PP msb */ + rlwimi r3,r3,32-1,31,31 /* _PAGE_USER -> PP lsb */ + ori r1,r1,0xe14 /* clear out reserved bits and M */ + andc r1,r3,r1 /* PP = user? (rw&dirty? 2: 3): 0 */ + mtspr SPRN_RPA,r1 + mfspr r3,SPRN_IMISS + tlbli r3 + mfspr r3,SPRN_SRR1 /* Need to restore CR0 */ + mtcrf 0x80,r3 + rfi +InstructionAddressInvalid: + mfspr r3,SPRN_SRR1 + rlwinm r1,r3,9,6,6 /* Get load/store bit */ + + addis r1,r1,0x2000 + mtspr SPRN_DSISR,r1 /* (shouldn't be needed) */ + mtctr r0 /* Restore CTR */ + andi. r2,r3,0xFFFF /* Clear upper bits of SRR1 */ + or r2,r2,r1 + mtspr SPRN_SRR1,r2 + mfspr r1,SPRN_IMISS /* Get failing address */ + rlwinm. r2,r2,0,31,31 /* Check for little endian access */ + rlwimi r2,r2,1,30,30 /* change 1 -> 3 */ + xor r1,r1,r2 + mtspr SPRN_DAR,r1 /* Set fault address */ + mfmsr r0 /* Restore "normal" registers */ + xoris r0,r0,MSR_TGPR>>16 + mtcrf 0x80,r3 /* Restore CR0 */ + mtmsr r0 + b InstructionAccess + +/* + * Handle TLB miss for DATA Load operation on 603/603e + */ + . = 0x1100 +DataLoadTLBMiss: +/* + * r0: stored ctr + * r1: linux style pte ( later becomes ppc hardware pte ) + * r2: ptr to linux-style pte + * r3: scratch + */ + mfctr r0 + /* Get PTE (linux-style) and check access */ + mfspr r3,SPRN_DMISS + lis r1,KERNELBASE@h /* check if kernel address */ + cmplw 0,r3,r1 + mfspr r2,SPRN_SPRG3 + li r1,_PAGE_USER|_PAGE_PRESENT /* low addresses tested as user */ + lwz r2,PGDIR(r2) + blt+ 112f + lis r2,swapper_pg_dir@ha /* if kernel address, use */ + addi r2,r2,swapper_pg_dir@l /* kernel page table */ + mfspr r1,SPRN_SRR1 /* and MSR_PR bit from SRR1 */ + rlwinm r1,r1,32-12,29,29 /* shift MSR_PR to _PAGE_USER posn */ +112: tophys(r2,r2) + rlwimi r2,r3,12,20,29 /* insert top 10 bits of address */ + lwz r2,0(r2) /* get pmd entry */ + rlwinm. r2,r2,0,0,19 /* extract address of pte page */ + beq- DataAddressInvalid /* return if no mapping */ + rlwimi r2,r3,22,20,29 /* insert next 10 bits of address */ + lwz r3,0(r2) /* get linux-style pte */ + andc. r1,r1,r3 /* check access & ~permission */ + bne- DataAddressInvalid /* return if access not permitted */ + ori r3,r3,_PAGE_ACCESSED /* set _PAGE_ACCESSED in pte */ + /* + * NOTE! We are assuming this is not an SMP system, otherwise + * we would need to update the pte atomically with lwarx/stwcx. + */ + stw r3,0(r2) /* update PTE (accessed bit) */ + /* Convert linux-style PTE to low word of PPC-style PTE */ + rlwinm r1,r3,32-10,31,31 /* _PAGE_RW -> PP lsb */ + rlwinm r2,r3,32-7,31,31 /* _PAGE_DIRTY -> PP lsb */ + and r1,r1,r2 /* writable if _RW and _DIRTY */ + rlwimi r3,r3,32-1,30,30 /* _PAGE_USER -> PP msb */ + rlwimi r3,r3,32-1,31,31 /* _PAGE_USER -> PP lsb */ + ori r1,r1,0xe14 /* clear out reserved bits and M */ + andc r1,r3,r1 /* PP = user? (rw&dirty? 2: 3): 0 */ + mtspr SPRN_RPA,r1 + mfspr r3,SPRN_DMISS + tlbld r3 + mfspr r3,SPRN_SRR1 /* Need to restore CR0 */ + mtcrf 0x80,r3 + rfi +DataAddressInvalid: + mfspr r3,SPRN_SRR1 + rlwinm r1,r3,9,6,6 /* Get load/store bit */ + addis r1,r1,0x2000 + mtspr SPRN_DSISR,r1 + mtctr r0 /* Restore CTR */ + andi. r2,r3,0xFFFF /* Clear upper bits of SRR1 */ + mtspr SPRN_SRR1,r2 + mfspr r1,SPRN_DMISS /* Get failing address */ + rlwinm. r2,r2,0,31,31 /* Check for little endian access */ + beq 20f /* Jump if big endian */ + xori r1,r1,3 +20: mtspr SPRN_DAR,r1 /* Set fault address */ + mfmsr r0 /* Restore "normal" registers */ + xoris r0,r0,MSR_TGPR>>16 + mtcrf 0x80,r3 /* Restore CR0 */ + mtmsr r0 + b DataAccess + +/* + * Handle TLB miss for DATA Store on 603/603e + */ + . = 0x1200 +DataStoreTLBMiss: +/* + * r0: stored ctr + * r1: linux style pte ( later becomes ppc hardware pte ) + * r2: ptr to linux-style pte + * r3: scratch + */ + mfctr r0 + /* Get PTE (linux-style) and check access */ + mfspr r3,SPRN_DMISS + lis r1,KERNELBASE@h /* check if kernel address */ + cmplw 0,r3,r1 + mfspr r2,SPRN_SPRG3 + li r1,_PAGE_RW|_PAGE_USER|_PAGE_PRESENT /* access flags */ + lwz r2,PGDIR(r2) + blt+ 112f + lis r2,swapper_pg_dir@ha /* if kernel address, use */ + addi r2,r2,swapper_pg_dir@l /* kernel page table */ + mfspr r1,SPRN_SRR1 /* and MSR_PR bit from SRR1 */ + rlwinm r1,r1,32-12,29,29 /* shift MSR_PR to _PAGE_USER posn */ +112: tophys(r2,r2) + rlwimi r2,r3,12,20,29 /* insert top 10 bits of address */ + lwz r2,0(r2) /* get pmd entry */ + rlwinm. r2,r2,0,0,19 /* extract address of pte page */ + beq- DataAddressInvalid /* return if no mapping */ + rlwimi r2,r3,22,20,29 /* insert next 10 bits of address */ + lwz r3,0(r2) /* get linux-style pte */ + andc. r1,r1,r3 /* check access & ~permission */ + bne- DataAddressInvalid /* return if access not permitted */ + ori r3,r3,_PAGE_ACCESSED|_PAGE_DIRTY + /* + * NOTE! We are assuming this is not an SMP system, otherwise + * we would need to update the pte atomically with lwarx/stwcx. + */ + stw r3,0(r2) /* update PTE (accessed/dirty bits) */ + /* Convert linux-style PTE to low word of PPC-style PTE */ + rlwimi r3,r3,32-1,30,30 /* _PAGE_USER -> PP msb */ + li r1,0xe15 /* clear out reserved bits and M */ + andc r1,r3,r1 /* PP = user? 2: 0 */ + mtspr SPRN_RPA,r1 + mfspr r3,SPRN_DMISS + tlbld r3 + mfspr r3,SPRN_SRR1 /* Need to restore CR0 */ + mtcrf 0x80,r3 + rfi + +#ifndef CONFIG_ALTIVEC +#define altivec_assist_exception unknown_exception +#endif + + EXCEPTION(0x1300, Trap_13, instruction_breakpoint_exception, EXC_XFER_EE) + EXCEPTION(0x1400, SMI, SMIException, EXC_XFER_EE) + EXCEPTION(0x1500, Trap_15, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1600, Trap_16, altivec_assist_exception, EXC_XFER_EE) + EXCEPTION(0x1700, Trap_17, TAUException, EXC_XFER_STD) + EXCEPTION(0x1800, Trap_18, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1900, Trap_19, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1a00, Trap_1a, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1b00, Trap_1b, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1c00, Trap_1c, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1d00, Trap_1d, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1e00, Trap_1e, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1f00, Trap_1f, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x2000, RunMode, RunModeException, EXC_XFER_EE) + EXCEPTION(0x2100, Trap_21, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x2200, Trap_22, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x2300, Trap_23, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x2400, Trap_24, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x2500, Trap_25, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x2600, Trap_26, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x2700, Trap_27, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x2800, Trap_28, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x2900, Trap_29, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x2a00, Trap_2a, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x2b00, Trap_2b, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x2c00, Trap_2c, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x2d00, Trap_2d, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x2e00, Trap_2e, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x2f00, MOLTrampoline, unknown_exception, EXC_XFER_EE_LITE) + + .globl mol_trampoline + .set mol_trampoline, i0x2f00 + + . = 0x3000 + +AltiVecUnavailable: + EXCEPTION_PROLOG +#ifdef CONFIG_ALTIVEC + bne load_up_altivec /* if from user, just load it up */ +#endif /* CONFIG_ALTIVEC */ + EXC_XFER_EE_LITE(0xf20, altivec_unavailable_exception) + +#ifdef CONFIG_ALTIVEC +/* Note that the AltiVec support is closely modeled after the FP + * support. Changes to one are likely to be applicable to the + * other! */ +load_up_altivec: +/* + * Disable AltiVec for the task which had AltiVec previously, + * and save its AltiVec registers in its thread_struct. + * Enables AltiVec for use in the kernel on return. + * On SMP we know the AltiVec units are free, since we give it up every + * switch. -- Kumar + */ + mfmsr r5 + oris r5,r5,MSR_VEC@h + MTMSRD(r5) /* enable use of AltiVec now */ + isync +/* + * For SMP, we don't do lazy AltiVec switching because it just gets too + * horrendously complex, especially when a task switches from one CPU + * to another. Instead we call giveup_altivec in switch_to. + */ +#ifndef CONFIG_SMP + tophys(r6,0) + addis r3,r6,last_task_used_altivec@ha + lwz r4,last_task_used_altivec@l(r3) + cmpwi 0,r4,0 + beq 1f + add r4,r4,r6 + addi r4,r4,THREAD /* want THREAD of last_task_used_altivec */ + SAVE_32VRS(0,r10,r4) + mfvscr vr0 + li r10,THREAD_VSCR + stvx vr0,r10,r4 + lwz r5,PT_REGS(r4) + add r5,r5,r6 + lwz r4,_MSR-STACK_FRAME_OVERHEAD(r5) + lis r10,MSR_VEC@h + andc r4,r4,r10 /* disable altivec for previous task */ + stw r4,_MSR-STACK_FRAME_OVERHEAD(r5) +1: +#endif /* CONFIG_SMP */ + /* enable use of AltiVec after return */ + oris r9,r9,MSR_VEC@h + mfspr r5,SPRN_SPRG3 /* current task's THREAD (phys) */ + li r4,1 + li r10,THREAD_VSCR + stw r4,THREAD_USED_VR(r5) + lvx vr0,r10,r5 + mtvscr vr0 + REST_32VRS(0,r10,r5) +#ifndef CONFIG_SMP + subi r4,r5,THREAD + sub r4,r4,r6 + stw r4,last_task_used_altivec@l(r3) +#endif /* CONFIG_SMP */ + /* restore registers and return */ + /* we haven't used ctr or xer or lr */ + b fast_exception_return + +/* + * AltiVec unavailable trap from kernel - print a message, but let + * the task use AltiVec in the kernel until it returns to user mode. + */ +KernelAltiVec: + lwz r3,_MSR(r1) + oris r3,r3,MSR_VEC@h + stw r3,_MSR(r1) /* enable use of AltiVec after return */ + lis r3,87f@h + ori r3,r3,87f@l + mr r4,r2 /* current */ + lwz r5,_NIP(r1) + bl printk + b ret_from_except +87: .string "AltiVec used in kernel (task=%p, pc=%x) \n" + .align 4,0 + +/* + * giveup_altivec(tsk) + * Disable AltiVec for the task given as the argument, + * and save the AltiVec registers in its thread_struct. + * Enables AltiVec for use in the kernel on return. + */ + + .globl giveup_altivec +giveup_altivec: + mfmsr r5 + oris r5,r5,MSR_VEC@h + SYNC + MTMSRD(r5) /* enable use of AltiVec now */ + isync + cmpwi 0,r3,0 + beqlr- /* if no previous owner, done */ + addi r3,r3,THREAD /* want THREAD of task */ + lwz r5,PT_REGS(r3) + cmpwi 0,r5,0 + SAVE_32VRS(0, r4, r3) + mfvscr vr0 + li r4,THREAD_VSCR + stvx vr0,r4,r3 + beq 1f + lwz r4,_MSR-STACK_FRAME_OVERHEAD(r5) + lis r3,MSR_VEC@h + andc r4,r4,r3 /* disable AltiVec for previous task */ + stw r4,_MSR-STACK_FRAME_OVERHEAD(r5) +1: +#ifndef CONFIG_SMP + li r5,0 + lis r4,last_task_used_altivec@ha + stw r5,last_task_used_altivec@l(r4) +#endif /* CONFIG_SMP */ + blr +#endif /* CONFIG_ALTIVEC */ + +/* + * This code is jumped to from the startup code to copy + * the kernel image to physical address 0. + */ +relocate_kernel: + addis r9,r26,klimit@ha /* fetch klimit */ + lwz r25,klimit@l(r9) + addis r25,r25,-KERNELBASE@h + li r3,0 /* Destination base address */ + li r6,0 /* Destination offset */ + li r5,0x4000 /* # bytes of memory to copy */ + bl copy_and_flush /* copy the first 0x4000 bytes */ + addi r0,r3,4f@l /* jump to the address of 4f */ + mtctr r0 /* in copy and do the rest. */ + bctr /* jump to the copy */ +4: mr r5,r25 + bl copy_and_flush /* copy the rest */ + b turn_on_mmu + +/* + * Copy routine used to copy the kernel to start at physical address 0 + * and flush and invalidate the caches as needed. + * r3 = dest addr, r4 = source addr, r5 = copy limit, r6 = start offset + * on exit, r3, r4, r5 are unchanged, r6 is updated to be >= r5. + */ +_GLOBAL(copy_and_flush) + addi r5,r5,-4 + addi r6,r6,-4 +4: li r0,L1_CACHE_BYTES/4 + mtctr r0 +3: addi r6,r6,4 /* copy a cache line */ + lwzx r0,r6,r4 + stwx r0,r6,r3 + bdnz 3b + dcbst r6,r3 /* write it to memory */ + sync + icbi r6,r3 /* flush the icache line */ + cmplw 0,r6,r5 + blt 4b + sync /* additional sync needed on g4 */ + isync + addi r5,r5,4 + addi r6,r6,4 + blr + +#ifdef CONFIG_APUS +/* + * On APUS the physical base address of the kernel is not known at compile + * time, which means the __pa/__va constants used are incorrect. In the + * __init section is recorded the virtual addresses of instructions using + * these constants, so all that has to be done is fix these before + * continuing the kernel boot. + * + * r4 = The physical address of the kernel base. + */ +fix_mem_constants: + mr r10,r4 + addis r10,r10,-KERNELBASE@h /* virt_to_phys constant */ + neg r11,r10 /* phys_to_virt constant */ + + lis r12,__vtop_table_begin@h + ori r12,r12,__vtop_table_begin@l + add r12,r12,r10 /* table begin phys address */ + lis r13,__vtop_table_end@h + ori r13,r13,__vtop_table_end@l + add r13,r13,r10 /* table end phys address */ + subi r12,r12,4 + subi r13,r13,4 +1: lwzu r14,4(r12) /* virt address of instruction */ + add r14,r14,r10 /* phys address of instruction */ + lwz r15,0(r14) /* instruction, now insert top */ + rlwimi r15,r10,16,16,31 /* half of vp const in low half */ + stw r15,0(r14) /* of instruction and restore. */ + dcbst r0,r14 /* write it to memory */ + sync + icbi r0,r14 /* flush the icache line */ + cmpw r12,r13 + bne 1b + sync /* additional sync needed on g4 */ + isync + +/* + * Map the memory where the exception handlers will + * be copied to when hash constants have been patched. + */ +#ifdef CONFIG_APUS_FAST_EXCEPT + lis r8,0xfff0 +#else + lis r8,0 +#endif + ori r8,r8,0x2 /* 128KB, supervisor */ + mtspr SPRN_DBAT3U,r8 + mtspr SPRN_DBAT3L,r8 + + lis r12,__ptov_table_begin@h + ori r12,r12,__ptov_table_begin@l + add r12,r12,r10 /* table begin phys address */ + lis r13,__ptov_table_end@h + ori r13,r13,__ptov_table_end@l + add r13,r13,r10 /* table end phys address */ + subi r12,r12,4 + subi r13,r13,4 +1: lwzu r14,4(r12) /* virt address of instruction */ + add r14,r14,r10 /* phys address of instruction */ + lwz r15,0(r14) /* instruction, now insert top */ + rlwimi r15,r11,16,16,31 /* half of pv const in low half*/ + stw r15,0(r14) /* of instruction and restore. */ + dcbst r0,r14 /* write it to memory */ + sync + icbi r0,r14 /* flush the icache line */ + cmpw r12,r13 + bne 1b + + sync /* additional sync needed on g4 */ + isync /* No speculative loading until now */ + blr + +/*********************************************************************** + * Please note that on APUS the exception handlers are located at the + * physical address 0xfff0000. For this reason, the exception handlers + * cannot use relative branches to access the code below. + ***********************************************************************/ +#endif /* CONFIG_APUS */ + +#ifdef CONFIG_SMP +#ifdef CONFIG_GEMINI + .globl __secondary_start_gemini +__secondary_start_gemini: + mfspr r4,SPRN_HID0 + ori r4,r4,HID0_ICFI + li r3,0 + ori r3,r3,HID0_ICE + andc r4,r4,r3 + mtspr SPRN_HID0,r4 + sync + b __secondary_start +#endif /* CONFIG_GEMINI */ + + .globl __secondary_start_pmac_0 +__secondary_start_pmac_0: + /* NB the entries for cpus 0, 1, 2 must each occupy 8 bytes. */ + li r24,0 + b 1f + li r24,1 + b 1f + li r24,2 + b 1f + li r24,3 +1: + /* on powersurge, we come in here with IR=0 and DR=1, and DBAT 0 + set to map the 0xf0000000 - 0xffffffff region */ + mfmsr r0 + rlwinm r0,r0,0,28,26 /* clear DR (0x10) */ + SYNC + mtmsr r0 + isync + + .globl __secondary_start +__secondary_start: + /* Copy some CPU settings from CPU 0 */ + bl __restore_cpu_setup + + lis r3,-KERNELBASE@h + mr r4,r24 + bl call_setup_cpu /* Call setup_cpu for this CPU */ +#ifdef CONFIG_6xx + lis r3,-KERNELBASE@h + bl init_idle_6xx +#endif /* CONFIG_6xx */ + + /* get current_thread_info and current */ + lis r1,secondary_ti@ha + tophys(r1,r1) + lwz r1,secondary_ti@l(r1) + tophys(r2,r1) + lwz r2,TI_TASK(r2) + + /* stack */ + addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD + li r0,0 + tophys(r3,r1) + stw r0,0(r3) + + /* load up the MMU */ + bl load_up_mmu + + /* ptr to phys current thread */ + tophys(r4,r2) + addi r4,r4,THREAD /* phys address of our thread_struct */ + CLR_TOP32(r4) + mtspr SPRN_SPRG3,r4 + li r3,0 + mtspr SPRN_SPRG2,r3 /* 0 => not in RTAS */ + + /* enable MMU and jump to start_secondary */ + li r4,MSR_KERNEL + FIX_SRR1(r4,r5) + lis r3,start_secondary@h + ori r3,r3,start_secondary@l + mtspr SPRN_SRR0,r3 + mtspr SPRN_SRR1,r4 + SYNC + RFI +#endif /* CONFIG_SMP */ + +/* + * Those generic dummy functions are kept for CPUs not + * included in CONFIG_6xx + */ +#if !defined(CONFIG_6xx) +_GLOBAL(__save_cpu_setup) + blr +_GLOBAL(__restore_cpu_setup) + blr +#endif /* !defined(CONFIG_6xx) */ + + +/* + * Load stuff into the MMU. Intended to be called with + * IR=0 and DR=0. + */ +load_up_mmu: + sync /* Force all PTE updates to finish */ + isync + tlbia /* Clear all TLB entries */ + sync /* wait for tlbia/tlbie to finish */ + TLBSYNC /* ... on all CPUs */ + /* Load the SDR1 register (hash table base & size) */ + lis r6,_SDR1@ha + tophys(r6,r6) + lwz r6,_SDR1@l(r6) + mtspr SPRN_SDR1,r6 + li r0,16 /* load up segment register values */ + mtctr r0 /* for context 0 */ + lis r3,0x2000 /* Ku = 1, VSID = 0 */ + li r4,0 +3: mtsrin r3,r4 + addi r3,r3,0x111 /* increment VSID */ + addis r4,r4,0x1000 /* address of next segment */ + bdnz 3b + +/* Load the BAT registers with the values set up by MMU_init. + MMU_init takes care of whether we're on a 601 or not. */ + mfpvr r3 + srwi r3,r3,16 + cmpwi r3,1 + lis r3,BATS@ha + addi r3,r3,BATS@l + tophys(r3,r3) + LOAD_BAT(0,r3,r4,r5) + LOAD_BAT(1,r3,r4,r5) + LOAD_BAT(2,r3,r4,r5) + LOAD_BAT(3,r3,r4,r5) + + blr + +/* + * This is where the main kernel code starts. + */ +start_here: + /* ptr to current */ + lis r2,init_task@h + ori r2,r2,init_task@l + /* Set up for using our exception vectors */ + /* ptr to phys current thread */ + tophys(r4,r2) + addi r4,r4,THREAD /* init task's THREAD */ + CLR_TOP32(r4) + mtspr SPRN_SPRG3,r4 + li r3,0 + mtspr SPRN_SPRG2,r3 /* 0 => not in RTAS */ + + /* stack */ + lis r1,init_thread_union@ha + addi r1,r1,init_thread_union@l + li r0,0 + stwu r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1) +/* + * Do early platform-specific initialization, + * and set up the MMU. + */ + mr r3,r31 + mr r4,r30 + bl machine_init + bl MMU_init + +#ifdef CONFIG_APUS + /* Copy exception code to exception vector base on APUS. */ + lis r4,KERNELBASE@h +#ifdef CONFIG_APUS_FAST_EXCEPT + lis r3,0xfff0 /* Copy to 0xfff00000 */ +#else + lis r3,0 /* Copy to 0x00000000 */ +#endif + li r5,0x4000 /* # bytes of memory to copy */ + li r6,0 + bl copy_and_flush /* copy the first 0x4000 bytes */ +#endif /* CONFIG_APUS */ + +/* + * Go back to running unmapped so we can load up new values + * for SDR1 (hash table pointer) and the segment registers + * and change to using our exception vectors. + */ + lis r4,2f@h + ori r4,r4,2f@l + tophys(r4,r4) + li r3,MSR_KERNEL & ~(MSR_IR|MSR_DR) + FIX_SRR1(r3,r5) + mtspr SPRN_SRR0,r4 + mtspr SPRN_SRR1,r3 + SYNC + RFI +/* Load up the kernel context */ +2: bl load_up_mmu + +#ifdef CONFIG_BDI_SWITCH + /* Add helper information for the Abatron bdiGDB debugger. + * We do this here because we know the mmu is disabled, and + * will be enabled for real in just a few instructions. + */ + lis r5, abatron_pteptrs@h + ori r5, r5, abatron_pteptrs@l + stw r5, 0xf0(r0) /* This much match your Abatron config */ + lis r6, swapper_pg_dir@h + ori r6, r6, swapper_pg_dir@l + tophys(r5, r5) + stw r6, 0(r5) +#endif /* CONFIG_BDI_SWITCH */ + +/* Now turn on the MMU for real! */ + li r4,MSR_KERNEL + FIX_SRR1(r4,r5) + lis r3,start_kernel@h + ori r3,r3,start_kernel@l + mtspr SPRN_SRR0,r3 + mtspr SPRN_SRR1,r4 + SYNC + RFI + +/* + * Set up the segment registers for a new context. + */ +_GLOBAL(set_context) + mulli r3,r3,897 /* multiply context by skew factor */ + rlwinm r3,r3,4,8,27 /* VSID = (context & 0xfffff) << 4 */ + addis r3,r3,0x6000 /* Set Ks, Ku bits */ + li r0,NUM_USER_SEGMENTS + mtctr r0 + +#ifdef CONFIG_BDI_SWITCH + /* Context switch the PTE pointer for the Abatron BDI2000. + * The PGDIR is passed as second argument. + */ + lis r5, KERNELBASE@h + lwz r5, 0xf0(r5) + stw r4, 0x4(r5) +#endif + li r4,0 + isync +3: + mtsrin r3,r4 + addi r3,r3,0x111 /* next VSID */ + rlwinm r3,r3,0,8,3 /* clear out any overflow from VSID field */ + addis r4,r4,0x1000 /* address of next segment */ + bdnz 3b + sync + isync + blr + +/* + * An undocumented "feature" of 604e requires that the v bit + * be cleared before changing BAT values. + * + * Also, newer IBM firmware does not clear bat3 and 4 so + * this makes sure it's done. + * -- Cort + */ +clear_bats: + li r10,0 + mfspr r9,SPRN_PVR + rlwinm r9,r9,16,16,31 /* r9 = 1 for 601, 4 for 604 */ + cmpwi r9, 1 + beq 1f + + mtspr SPRN_DBAT0U,r10 + mtspr SPRN_DBAT0L,r10 + mtspr SPRN_DBAT1U,r10 + mtspr SPRN_DBAT1L,r10 + mtspr SPRN_DBAT2U,r10 + mtspr SPRN_DBAT2L,r10 + mtspr SPRN_DBAT3U,r10 + mtspr SPRN_DBAT3L,r10 +1: + mtspr SPRN_IBAT0U,r10 + mtspr SPRN_IBAT0L,r10 + mtspr SPRN_IBAT1U,r10 + mtspr SPRN_IBAT1L,r10 + mtspr SPRN_IBAT2U,r10 + mtspr SPRN_IBAT2L,r10 + mtspr SPRN_IBAT3U,r10 + mtspr SPRN_IBAT3L,r10 +BEGIN_FTR_SECTION + /* Here's a tweak: at this point, CPU setup have + * not been called yet, so HIGH_BAT_EN may not be + * set in HID0 for the 745x processors. However, it + * seems that doesn't affect our ability to actually + * write to these SPRs. + */ + mtspr SPRN_DBAT4U,r10 + mtspr SPRN_DBAT4L,r10 + mtspr SPRN_DBAT5U,r10 + mtspr SPRN_DBAT5L,r10 + mtspr SPRN_DBAT6U,r10 + mtspr SPRN_DBAT6L,r10 + mtspr SPRN_DBAT7U,r10 + mtspr SPRN_DBAT7L,r10 + mtspr SPRN_IBAT4U,r10 + mtspr SPRN_IBAT4L,r10 + mtspr SPRN_IBAT5U,r10 + mtspr SPRN_IBAT5L,r10 + mtspr SPRN_IBAT6U,r10 + mtspr SPRN_IBAT6L,r10 + mtspr SPRN_IBAT7U,r10 + mtspr SPRN_IBAT7L,r10 +END_FTR_SECTION_IFSET(CPU_FTR_HAS_HIGH_BATS) + blr + +flush_tlbs: + lis r10, 0x40 +1: addic. r10, r10, -0x1000 + tlbie r10 + blt 1b + sync + blr + +mmu_off: + addi r4, r3, __after_mmu_off - _start + mfmsr r3 + andi. r0,r3,MSR_DR|MSR_IR /* MMU enabled? */ + beqlr + andc r3,r3,r0 + mtspr SPRN_SRR0,r4 + mtspr SPRN_SRR1,r3 + sync + RFI + +/* + * Use the first pair of BAT registers to map the 1st 16MB + * of RAM to KERNELBASE. From this point on we can't safely + * call OF any more. + */ +initial_bats: + lis r11,KERNELBASE@h + mfspr r9,SPRN_PVR + rlwinm r9,r9,16,16,31 /* r9 = 1 for 601, 4 for 604 */ + cmpwi 0,r9,1 + bne 4f + ori r11,r11,4 /* set up BAT registers for 601 */ + li r8,0x7f /* valid, block length = 8MB */ + oris r9,r11,0x800000@h /* set up BAT reg for 2nd 8M */ + oris r10,r8,0x800000@h /* set up BAT reg for 2nd 8M */ + mtspr SPRN_IBAT0U,r11 /* N.B. 601 has valid bit in */ + mtspr SPRN_IBAT0L,r8 /* lower BAT register */ + mtspr SPRN_IBAT1U,r9 + mtspr SPRN_IBAT1L,r10 + isync + blr + +4: tophys(r8,r11) +#ifdef CONFIG_SMP + ori r8,r8,0x12 /* R/W access, M=1 */ +#else + ori r8,r8,2 /* R/W access */ +#endif /* CONFIG_SMP */ +#ifdef CONFIG_APUS + ori r11,r11,BL_8M<<2|0x2 /* set up 8MB BAT registers for 604 */ +#else + ori r11,r11,BL_256M<<2|0x2 /* set up BAT registers for 604 */ +#endif /* CONFIG_APUS */ + + mtspr SPRN_DBAT0L,r8 /* N.B. 6xx (not 601) have valid */ + mtspr SPRN_DBAT0U,r11 /* bit in upper BAT register */ + mtspr SPRN_IBAT0L,r8 + mtspr SPRN_IBAT0U,r11 + isync + blr + + +#ifdef CONFIG_8260 +/* Jump into the system reset for the rom. + * We first disable the MMU, and then jump to the ROM reset address. + * + * r3 is the board info structure, r4 is the location for starting. + * I use this for building a small kernel that can load other kernels, + * rather than trying to write or rely on a rom monitor that can tftp load. + */ + .globl m8260_gorom +m8260_gorom: + mfmsr r0 + rlwinm r0,r0,0,17,15 /* clear MSR_EE in r0 */ + sync + mtmsr r0 + sync + mfspr r11, SPRN_HID0 + lis r10, 0 + ori r10,r10,HID0_ICE|HID0_DCE + andc r11, r11, r10 + mtspr SPRN_HID0, r11 + isync + li r5, MSR_ME|MSR_RI + lis r6,2f@h + addis r6,r6,-KERNELBASE@h + ori r6,r6,2f@l + mtspr SPRN_SRR0,r6 + mtspr SPRN_SRR1,r5 + isync + sync + rfi +2: + mtlr r4 + blr +#endif + + +/* + * We put a few things here that have to be page-aligned. + * This stuff goes at the beginning of the data segment, + * which is page-aligned. + */ + .data + .globl sdata +sdata: + .globl empty_zero_page +empty_zero_page: + .space 4096 + + .globl swapper_pg_dir +swapper_pg_dir: + .space 4096 + +/* + * This space gets a copy of optional info passed to us by the bootstrap + * Used to pass parameters into the kernel like root=/dev/sda1, etc. + */ + .globl cmd_line +cmd_line: + .space 512 + + .globl intercept_table +intercept_table: + .long 0, 0, i0x200, i0x300, i0x400, 0, i0x600, i0x700 + .long i0x800, 0, 0, 0, 0, i0xd00, 0, 0 + .long 0, 0, 0, i0x1300, 0, 0, 0, 0 + .long 0, 0, 0, 0, 0, 0, 0, 0 + .long 0, 0, 0, 0, 0, 0, 0, 0 + .long 0, 0, 0, 0, 0, 0, 0, 0 + +/* Room for two PTE pointers, usually the kernel and current user pointers + * to their respective root page table. + */ +abatron_pteptrs: + .space 8 diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S new file mode 100644 index 000000000000..8b49679fad54 --- /dev/null +++ b/arch/powerpc/kernel/head_44x.S @@ -0,0 +1,782 @@ +/* + * arch/ppc/kernel/head_44x.S + * + * Kernel execution entry point code. + * + * Copyright (c) 1995-1996 Gary Thomas <gdt@linuxppc.org> + * Initial PowerPC version. + * Copyright (c) 1996 Cort Dougan <cort@cs.nmt.edu> + * Rewritten for PReP + * Copyright (c) 1996 Paul Mackerras <paulus@cs.anu.edu.au> + * Low-level exception handers, MMU support, and rewrite. + * Copyright (c) 1997 Dan Malek <dmalek@jlc.net> + * PowerPC 8xx modifications. + * Copyright (c) 1998-1999 TiVo, Inc. + * PowerPC 403GCX modifications. + * Copyright (c) 1999 Grant Erickson <grant@lcse.umn.edu> + * PowerPC 403GCX/405GP modifications. + * Copyright 2000 MontaVista Software Inc. + * PPC405 modifications + * PowerPC 403GCX/405GP modifications. + * Author: MontaVista Software, Inc. + * frank_rowand@mvista.com or source@mvista.com + * debbie_chu@mvista.com + * Copyright 2002-2005 MontaVista Software, Inc. + * PowerPC 44x support, Matt Porter <mporter@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/mmu.h> +#include <asm/pgtable.h> +#include <asm/ibm4xx.h> +#include <asm/ibm44x.h> +#include <asm/cputable.h> +#include <asm/thread_info.h> +#include <asm/ppc_asm.h> +#include <asm/asm-offsets.h> +#include "head_booke.h" + + +/* As with the other PowerPC ports, it is expected that when code + * execution begins here, the following registers contain valid, yet + * optional, information: + * + * r3 - Board info structure pointer (DRAM, frequency, MAC address, etc.) + * r4 - Starting address of the init RAM disk + * r5 - Ending address of the init RAM disk + * r6 - Start of kernel command line string (e.g. "mem=128") + * r7 - End of kernel command line string + * + */ + .text +_GLOBAL(_stext) +_GLOBAL(_start) + /* + * Reserve a word at a fixed location to store the address + * of abatron_pteptrs + */ + nop +/* + * Save parameters we are passed + */ + mr r31,r3 + mr r30,r4 + mr r29,r5 + mr r28,r6 + mr r27,r7 + li r24,0 /* CPU number */ + +/* + * Set up the initial MMU state + * + * We are still executing code at the virtual address + * mappings set by the firmware for the base of RAM. + * + * We first invalidate all TLB entries but the one + * we are running from. We then load the KERNELBASE + * mappings so we can begin to use kernel addresses + * natively and so the interrupt vector locations are + * permanently pinned (necessary since Book E + * implementations always have translation enabled). + * + * TODO: Use the known TLB entry we are running from to + * determine which physical region we are located + * in. This can be used to determine where in RAM + * (on a shared CPU system) or PCI memory space + * (on a DRAMless system) we are located. + * For now, we assume a perfect world which means + * we are located at the base of DRAM (physical 0). + */ + +/* + * Search TLB for entry that we are currently using. + * Invalidate all entries but the one we are using. + */ + /* Load our current PID->MMUCR TID and MSR IS->MMUCR STS */ + mfspr r3,SPRN_PID /* Get PID */ + mfmsr r4 /* Get MSR */ + andi. r4,r4,MSR_IS@l /* TS=1? */ + beq wmmucr /* If not, leave STS=0 */ + oris r3,r3,PPC44x_MMUCR_STS@h /* Set STS=1 */ +wmmucr: mtspr SPRN_MMUCR,r3 /* Put MMUCR */ + sync + + bl invstr /* Find our address */ +invstr: mflr r5 /* Make it accessible */ + tlbsx r23,0,r5 /* Find entry we are in */ + li r4,0 /* Start at TLB entry 0 */ + li r3,0 /* Set PAGEID inval value */ +1: cmpw r23,r4 /* Is this our entry? */ + beq skpinv /* If so, skip the inval */ + tlbwe r3,r4,PPC44x_TLB_PAGEID /* If not, inval the entry */ +skpinv: addi r4,r4,1 /* Increment */ + cmpwi r4,64 /* Are we done? */ + bne 1b /* If not, repeat */ + isync /* If so, context change */ + +/* + * Configure and load pinned entry into TLB slot 63. + */ + + lis r3,KERNELBASE@h /* Load the kernel virtual address */ + ori r3,r3,KERNELBASE@l + + /* Kernel is at the base of RAM */ + li r4, 0 /* Load the kernel physical address */ + + /* Load the kernel PID = 0 */ + li r0,0 + mtspr SPRN_PID,r0 + sync + + /* Initialize MMUCR */ + li r5,0 + mtspr SPRN_MMUCR,r5 + sync + + /* pageid fields */ + clrrwi r3,r3,10 /* Mask off the effective page number */ + ori r3,r3,PPC44x_TLB_VALID | PPC44x_TLB_256M + + /* xlat fields */ + clrrwi r4,r4,10 /* Mask off the real page number */ + /* ERPN is 0 for first 4GB page */ + + /* attrib fields */ + /* Added guarded bit to protect against speculative loads/stores */ + li r5,0 + ori r5,r5,(PPC44x_TLB_SW | PPC44x_TLB_SR | PPC44x_TLB_SX | PPC44x_TLB_G) + + li r0,63 /* TLB slot 63 */ + + tlbwe r3,r0,PPC44x_TLB_PAGEID /* Load the pageid fields */ + tlbwe r4,r0,PPC44x_TLB_XLAT /* Load the translation fields */ + tlbwe r5,r0,PPC44x_TLB_ATTRIB /* Load the attrib/access fields */ + + /* Force context change */ + mfmsr r0 + mtspr SPRN_SRR1, r0 + lis r0,3f@h + ori r0,r0,3f@l + mtspr SPRN_SRR0,r0 + sync + rfi + + /* If necessary, invalidate original entry we used */ +3: cmpwi r23,63 + beq 4f + li r6,0 + tlbwe r6,r23,PPC44x_TLB_PAGEID + isync + +4: +#ifdef CONFIG_SERIAL_TEXT_DEBUG + /* + * Add temporary UART mapping for early debug. + * We can map UART registers wherever we want as long as they don't + * interfere with other system mappings (e.g. with pinned entries). + * For an example of how we handle this - see ocotea.h. --ebs + */ + /* pageid fields */ + lis r3,UART0_IO_BASE@h + ori r3,r3,PPC44x_TLB_VALID | PPC44x_TLB_4K + + /* xlat fields */ + lis r4,UART0_PHYS_IO_BASE@h /* RPN depends on SoC */ +#ifndef CONFIG_440EP + ori r4,r4,0x0001 /* ERPN is 1 for second 4GB page */ +#endif + + /* attrib fields */ + li r5,0 + ori r5,r5,(PPC44x_TLB_SW | PPC44x_TLB_SR | PPC44x_TLB_I | PPC44x_TLB_G) + + li r0,0 /* TLB slot 0 */ + + tlbwe r3,r0,PPC44x_TLB_PAGEID /* Load the pageid fields */ + tlbwe r4,r0,PPC44x_TLB_XLAT /* Load the translation fields */ + tlbwe r5,r0,PPC44x_TLB_ATTRIB /* Load the attrib/access fields */ + + /* Force context change */ + isync +#endif /* CONFIG_SERIAL_TEXT_DEBUG */ + + /* Establish the interrupt vector offsets */ + SET_IVOR(0, CriticalInput); + SET_IVOR(1, MachineCheck); + SET_IVOR(2, DataStorage); + SET_IVOR(3, InstructionStorage); + SET_IVOR(4, ExternalInput); + SET_IVOR(5, Alignment); + SET_IVOR(6, Program); + SET_IVOR(7, FloatingPointUnavailable); + SET_IVOR(8, SystemCall); + SET_IVOR(9, AuxillaryProcessorUnavailable); + SET_IVOR(10, Decrementer); + SET_IVOR(11, FixedIntervalTimer); + SET_IVOR(12, WatchdogTimer); + SET_IVOR(13, DataTLBError); + SET_IVOR(14, InstructionTLBError); + SET_IVOR(15, Debug); + + /* Establish the interrupt vector base */ + lis r4,interrupt_base@h /* IVPR only uses the high 16-bits */ + mtspr SPRN_IVPR,r4 + +#ifdef CONFIG_440EP + /* Clear DAPUIB flag in CCR0 (enable APU between CPU and FPU) */ + mfspr r2,SPRN_CCR0 + lis r3,0xffef + ori r3,r3,0xffff + and r2,r2,r3 + mtspr SPRN_CCR0,r2 + isync +#endif + + /* + * This is where the main kernel code starts. + */ + + /* ptr to current */ + lis r2,init_task@h + ori r2,r2,init_task@l + + /* ptr to current thread */ + addi r4,r2,THREAD /* init task's THREAD */ + mtspr SPRN_SPRG3,r4 + + /* stack */ + lis r1,init_thread_union@h + ori r1,r1,init_thread_union@l + li r0,0 + stwu r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1) + + bl early_init + +/* + * Decide what sort of machine this is and initialize the MMU. + */ + mr r3,r31 + mr r4,r30 + mr r5,r29 + mr r6,r28 + mr r7,r27 + bl machine_init + bl MMU_init + + /* Setup PTE pointers for the Abatron bdiGDB */ + lis r6, swapper_pg_dir@h + ori r6, r6, swapper_pg_dir@l + lis r5, abatron_pteptrs@h + ori r5, r5, abatron_pteptrs@l + lis r4, KERNELBASE@h + ori r4, r4, KERNELBASE@l + stw r5, 0(r4) /* Save abatron_pteptrs at a fixed location */ + stw r6, 0(r5) + + /* Let's move on */ + lis r4,start_kernel@h + ori r4,r4,start_kernel@l + lis r3,MSR_KERNEL@h + ori r3,r3,MSR_KERNEL@l + mtspr SPRN_SRR0,r4 + mtspr SPRN_SRR1,r3 + rfi /* change context and jump to start_kernel */ + +/* + * Interrupt vector entry code + * + * The Book E MMUs are always on so we don't need to handle + * interrupts in real mode as with previous PPC processors. In + * this case we handle interrupts in the kernel virtual address + * space. + * + * Interrupt vectors are dynamically placed relative to the + * interrupt prefix as determined by the address of interrupt_base. + * The interrupt vectors offsets are programmed using the labels + * for each interrupt vector entry. + * + * Interrupt vectors must be aligned on a 16 byte boundary. + * We align on a 32 byte cache line boundary for good measure. + */ + +interrupt_base: + /* Critical Input Interrupt */ + CRITICAL_EXCEPTION(0x0100, CriticalInput, unknown_exception) + + /* Machine Check Interrupt */ +#ifdef CONFIG_440A + MCHECK_EXCEPTION(0x0200, MachineCheck, machine_check_exception) +#else + CRITICAL_EXCEPTION(0x0200, MachineCheck, machine_check_exception) +#endif + + /* Data Storage Interrupt */ + START_EXCEPTION(DataStorage) + mtspr SPRN_SPRG0, r10 /* Save some working registers */ + mtspr SPRN_SPRG1, r11 + mtspr SPRN_SPRG4W, r12 + mtspr SPRN_SPRG5W, r13 + mfcr r11 + mtspr SPRN_SPRG7W, r11 + + /* + * Check if it was a store fault, if not then bail + * because a user tried to access a kernel or + * read-protected page. Otherwise, get the + * offending address and handle it. + */ + mfspr r10, SPRN_ESR + andis. r10, r10, ESR_ST@h + beq 2f + + mfspr r10, SPRN_DEAR /* Get faulting address */ + + /* If we are faulting a kernel address, we have to use the + * kernel page tables. + */ + lis r11, TASK_SIZE@h + cmplw r10, r11 + blt+ 3f + lis r11, swapper_pg_dir@h + ori r11, r11, swapper_pg_dir@l + + mfspr r12,SPRN_MMUCR + rlwinm r12,r12,0,0,23 /* Clear TID */ + + b 4f + + /* Get the PGD for the current thread */ +3: + mfspr r11,SPRN_SPRG3 + lwz r11,PGDIR(r11) + + /* Load PID into MMUCR TID */ + mfspr r12,SPRN_MMUCR /* Get MMUCR */ + mfspr r13,SPRN_PID /* Get PID */ + rlwimi r12,r13,0,24,31 /* Set TID */ + +4: + mtspr SPRN_MMUCR,r12 + + rlwinm r12, r10, 13, 19, 29 /* Compute pgdir/pmd offset */ + lwzx r11, r12, r11 /* Get pgd/pmd entry */ + rlwinm. r12, r11, 0, 0, 20 /* Extract pt base address */ + beq 2f /* Bail if no table */ + + rlwimi r12, r10, 23, 20, 28 /* Compute pte address */ + lwz r11, 4(r12) /* Get pte entry */ + + andi. r13, r11, _PAGE_RW /* Is it writeable? */ + beq 2f /* Bail if not */ + + /* Update 'changed'. + */ + ori r11, r11, _PAGE_DIRTY|_PAGE_ACCESSED|_PAGE_HWWRITE + stw r11, 4(r12) /* Update Linux page table */ + + li r13, PPC44x_TLB_SR@l /* Set SR */ + rlwimi r13, r11, 29, 29, 29 /* SX = _PAGE_HWEXEC */ + rlwimi r13, r11, 0, 30, 30 /* SW = _PAGE_RW */ + rlwimi r13, r11, 29, 28, 28 /* UR = _PAGE_USER */ + rlwimi r12, r11, 31, 26, 26 /* (_PAGE_USER>>1)->r12 */ + rlwimi r12, r11, 29, 30, 30 /* (_PAGE_USER>>3)->r12 */ + and r12, r12, r11 /* HWEXEC/RW & USER */ + rlwimi r13, r12, 0, 26, 26 /* UX = HWEXEC & USER */ + rlwimi r13, r12, 3, 27, 27 /* UW = RW & USER */ + + rlwimi r11,r13,0,26,31 /* Insert static perms */ + + rlwinm r11,r11,0,20,15 /* Clear U0-U3 */ + + /* find the TLB index that caused the fault. It has to be here. */ + tlbsx r10, 0, r10 + + tlbwe r11, r10, PPC44x_TLB_ATTRIB /* Write ATTRIB */ + + /* Done...restore registers and get out of here. + */ + mfspr r11, SPRN_SPRG7R + mtcr r11 + mfspr r13, SPRN_SPRG5R + mfspr r12, SPRN_SPRG4R + + mfspr r11, SPRN_SPRG1 + mfspr r10, SPRN_SPRG0 + rfi /* Force context change */ + +2: + /* + * The bailout. Restore registers to pre-exception conditions + * and call the heavyweights to help us out. + */ + mfspr r11, SPRN_SPRG7R + mtcr r11 + mfspr r13, SPRN_SPRG5R + mfspr r12, SPRN_SPRG4R + + mfspr r11, SPRN_SPRG1 + mfspr r10, SPRN_SPRG0 + b data_access + + /* Instruction Storage Interrupt */ + INSTRUCTION_STORAGE_EXCEPTION + + /* External Input Interrupt */ + EXCEPTION(0x0500, ExternalInput, do_IRQ, EXC_XFER_LITE) + + /* Alignment Interrupt */ + ALIGNMENT_EXCEPTION + + /* Program Interrupt */ + PROGRAM_EXCEPTION + + /* Floating Point Unavailable Interrupt */ +#ifdef CONFIG_PPC_FPU + FP_UNAVAILABLE_EXCEPTION +#else + EXCEPTION(0x2010, FloatingPointUnavailable, unknown_exception, EXC_XFER_EE) +#endif + + /* System Call Interrupt */ + START_EXCEPTION(SystemCall) + NORMAL_EXCEPTION_PROLOG + EXC_XFER_EE_LITE(0x0c00, DoSyscall) + + /* Auxillary Processor Unavailable Interrupt */ + EXCEPTION(0x2020, AuxillaryProcessorUnavailable, unknown_exception, EXC_XFER_EE) + + /* Decrementer Interrupt */ + DECREMENTER_EXCEPTION + + /* Fixed Internal Timer Interrupt */ + /* TODO: Add FIT support */ + EXCEPTION(0x1010, FixedIntervalTimer, unknown_exception, EXC_XFER_EE) + + /* Watchdog Timer Interrupt */ + /* TODO: Add watchdog support */ +#ifdef CONFIG_BOOKE_WDT + CRITICAL_EXCEPTION(0x1020, WatchdogTimer, WatchdogException) +#else + CRITICAL_EXCEPTION(0x1020, WatchdogTimer, unknown_exception) +#endif + + /* Data TLB Error Interrupt */ + START_EXCEPTION(DataTLBError) + mtspr SPRN_SPRG0, r10 /* Save some working registers */ + mtspr SPRN_SPRG1, r11 + mtspr SPRN_SPRG4W, r12 + mtspr SPRN_SPRG5W, r13 + mfcr r11 + mtspr SPRN_SPRG7W, r11 + mfspr r10, SPRN_DEAR /* Get faulting address */ + + /* If we are faulting a kernel address, we have to use the + * kernel page tables. + */ + lis r11, TASK_SIZE@h + cmplw r10, r11 + blt+ 3f + lis r11, swapper_pg_dir@h + ori r11, r11, swapper_pg_dir@l + + mfspr r12,SPRN_MMUCR + rlwinm r12,r12,0,0,23 /* Clear TID */ + + b 4f + + /* Get the PGD for the current thread */ +3: + mfspr r11,SPRN_SPRG3 + lwz r11,PGDIR(r11) + + /* Load PID into MMUCR TID */ + mfspr r12,SPRN_MMUCR + mfspr r13,SPRN_PID /* Get PID */ + rlwimi r12,r13,0,24,31 /* Set TID */ + +4: + mtspr SPRN_MMUCR,r12 + + rlwinm r12, r10, 13, 19, 29 /* Compute pgdir/pmd offset */ + lwzx r11, r12, r11 /* Get pgd/pmd entry */ + rlwinm. r12, r11, 0, 0, 20 /* Extract pt base address */ + beq 2f /* Bail if no table */ + + rlwimi r12, r10, 23, 20, 28 /* Compute pte address */ + lwz r11, 4(r12) /* Get pte entry */ + andi. r13, r11, _PAGE_PRESENT /* Is the page present? */ + beq 2f /* Bail if not present */ + + ori r11, r11, _PAGE_ACCESSED + stw r11, 4(r12) + + /* Jump to common tlb load */ + b finish_tlb_load + +2: + /* The bailout. Restore registers to pre-exception conditions + * and call the heavyweights to help us out. + */ + mfspr r11, SPRN_SPRG7R + mtcr r11 + mfspr r13, SPRN_SPRG5R + mfspr r12, SPRN_SPRG4R + mfspr r11, SPRN_SPRG1 + mfspr r10, SPRN_SPRG0 + b data_access + + /* Instruction TLB Error Interrupt */ + /* + * Nearly the same as above, except we get our + * information from different registers and bailout + * to a different point. + */ + START_EXCEPTION(InstructionTLBError) + mtspr SPRN_SPRG0, r10 /* Save some working registers */ + mtspr SPRN_SPRG1, r11 + mtspr SPRN_SPRG4W, r12 + mtspr SPRN_SPRG5W, r13 + mfcr r11 + mtspr SPRN_SPRG7W, r11 + mfspr r10, SPRN_SRR0 /* Get faulting address */ + + /* If we are faulting a kernel address, we have to use the + * kernel page tables. + */ + lis r11, TASK_SIZE@h + cmplw r10, r11 + blt+ 3f + lis r11, swapper_pg_dir@h + ori r11, r11, swapper_pg_dir@l + + mfspr r12,SPRN_MMUCR + rlwinm r12,r12,0,0,23 /* Clear TID */ + + b 4f + + /* Get the PGD for the current thread */ +3: + mfspr r11,SPRN_SPRG3 + lwz r11,PGDIR(r11) + + /* Load PID into MMUCR TID */ + mfspr r12,SPRN_MMUCR + mfspr r13,SPRN_PID /* Get PID */ + rlwimi r12,r13,0,24,31 /* Set TID */ + +4: + mtspr SPRN_MMUCR,r12 + + rlwinm r12, r10, 13, 19, 29 /* Compute pgdir/pmd offset */ + lwzx r11, r12, r11 /* Get pgd/pmd entry */ + rlwinm. r12, r11, 0, 0, 20 /* Extract pt base address */ + beq 2f /* Bail if no table */ + + rlwimi r12, r10, 23, 20, 28 /* Compute pte address */ + lwz r11, 4(r12) /* Get pte entry */ + andi. r13, r11, _PAGE_PRESENT /* Is the page present? */ + beq 2f /* Bail if not present */ + + ori r11, r11, _PAGE_ACCESSED + stw r11, 4(r12) + + /* Jump to common TLB load point */ + b finish_tlb_load + +2: + /* The bailout. Restore registers to pre-exception conditions + * and call the heavyweights to help us out. + */ + mfspr r11, SPRN_SPRG7R + mtcr r11 + mfspr r13, SPRN_SPRG5R + mfspr r12, SPRN_SPRG4R + mfspr r11, SPRN_SPRG1 + mfspr r10, SPRN_SPRG0 + b InstructionStorage + + /* Debug Interrupt */ + DEBUG_EXCEPTION + +/* + * Local functions + */ + /* + * Data TLB exceptions will bail out to this point + * if they can't resolve the lightweight TLB fault. + */ +data_access: + NORMAL_EXCEPTION_PROLOG + mfspr r5,SPRN_ESR /* Grab the ESR, save it, pass arg3 */ + stw r5,_ESR(r11) + mfspr r4,SPRN_DEAR /* Grab the DEAR, save it, pass arg2 */ + EXC_XFER_EE_LITE(0x0300, handle_page_fault) + +/* + + * Both the instruction and data TLB miss get to this + * point to load the TLB. + * r10 - EA of fault + * r11 - available to use + * r12 - Pointer to the 64-bit PTE + * r13 - available to use + * MMUCR - loaded with proper value when we get here + * Upon exit, we reload everything and RFI. + */ +finish_tlb_load: + /* + * We set execute, because we don't have the granularity to + * properly set this at the page level (Linux problem). + * If shared is set, we cause a zero PID->TID load. + * Many of these bits are software only. Bits we don't set + * here we (properly should) assume have the appropriate value. + */ + + /* Load the next available TLB index */ + lis r13, tlb_44x_index@ha + lwz r13, tlb_44x_index@l(r13) + /* Load the TLB high watermark */ + lis r11, tlb_44x_hwater@ha + lwz r11, tlb_44x_hwater@l(r11) + + /* Increment, rollover, and store TLB index */ + addi r13, r13, 1 + cmpw 0, r13, r11 /* reserve entries */ + ble 7f + li r13, 0 +7: + /* Store the next available TLB index */ + lis r11, tlb_44x_index@ha + stw r13, tlb_44x_index@l(r11) + + lwz r11, 0(r12) /* Get MS word of PTE */ + lwz r12, 4(r12) /* Get LS word of PTE */ + rlwimi r11, r12, 0, 0 , 19 /* Insert RPN */ + tlbwe r11, r13, PPC44x_TLB_XLAT /* Write XLAT */ + + /* + * Create PAGEID. This is the faulting address, + * page size, and valid flag. + */ + li r11, PPC44x_TLB_VALID | PPC44x_TLB_4K + rlwimi r10, r11, 0, 20, 31 /* Insert valid and page size */ + tlbwe r10, r13, PPC44x_TLB_PAGEID /* Write PAGEID */ + + li r10, PPC44x_TLB_SR@l /* Set SR */ + rlwimi r10, r12, 0, 30, 30 /* Set SW = _PAGE_RW */ + rlwimi r10, r12, 29, 29, 29 /* SX = _PAGE_HWEXEC */ + rlwimi r10, r12, 29, 28, 28 /* UR = _PAGE_USER */ + rlwimi r11, r12, 31, 26, 26 /* (_PAGE_USER>>1)->r12 */ + and r11, r12, r11 /* HWEXEC & USER */ + rlwimi r10, r11, 0, 26, 26 /* UX = HWEXEC & USER */ + + rlwimi r12, r10, 0, 26, 31 /* Insert static perms */ + rlwinm r12, r12, 0, 20, 15 /* Clear U0-U3 */ + tlbwe r12, r13, PPC44x_TLB_ATTRIB /* Write ATTRIB */ + + /* Done...restore registers and get out of here. + */ + mfspr r11, SPRN_SPRG7R + mtcr r11 + mfspr r13, SPRN_SPRG5R + mfspr r12, SPRN_SPRG4R + mfspr r11, SPRN_SPRG1 + mfspr r10, SPRN_SPRG0 + rfi /* Force context change */ + +/* + * Global functions + */ + +/* + * extern void giveup_altivec(struct task_struct *prev) + * + * The 44x core does not have an AltiVec unit. + */ +_GLOBAL(giveup_altivec) + blr + +/* + * extern void giveup_fpu(struct task_struct *prev) + * + * The 44x core does not have an FPU. + */ +#ifndef CONFIG_PPC_FPU +_GLOBAL(giveup_fpu) + blr +#endif + +/* + * extern void abort(void) + * + * At present, this routine just applies a system reset. + */ +_GLOBAL(abort) + mfspr r13,SPRN_DBCR0 + oris r13,r13,DBCR0_RST_SYSTEM@h + mtspr SPRN_DBCR0,r13 + +_GLOBAL(set_context) + +#ifdef CONFIG_BDI_SWITCH + /* Context switch the PTE pointer for the Abatron BDI2000. + * The PGDIR is the second parameter. + */ + lis r5, abatron_pteptrs@h + ori r5, r5, abatron_pteptrs@l + stw r4, 0x4(r5) +#endif + mtspr SPRN_PID,r3 + isync /* Force context change */ + blr + +/* + * We put a few things here that have to be page-aligned. This stuff + * goes at the beginning of the data segment, which is page-aligned. + */ + .data + .align 12 + .globl sdata +sdata: + .globl empty_zero_page +empty_zero_page: + .space 4096 + +/* + * To support >32-bit physical addresses, we use an 8KB pgdir. + */ + .globl swapper_pg_dir +swapper_pg_dir: + .space 8192 + +/* Reserved 4k for the critical exception stack & 4k for the machine + * check stack per CPU for kernel mode exceptions */ + .section .bss + .align 12 +exception_stack_bottom: + .space BOOKE_EXCEPTION_STACK_SIZE + .globl exception_stack_top +exception_stack_top: + +/* + * This space gets a copy of optional info passed to us by the bootstrap + * which is used to pass parameters into the kernel like root=/dev/sda1, etc. + */ + .globl cmd_line +cmd_line: + .space 512 + +/* + * Room for two PTE pointers, usually the kernel and current user pointers + * to their respective root page table. + */ +abatron_pteptrs: + .space 8 diff --git a/arch/powerpc/kernel/head_4xx.S b/arch/powerpc/kernel/head_4xx.S new file mode 100644 index 000000000000..2590e97f5539 --- /dev/null +++ b/arch/powerpc/kernel/head_4xx.S @@ -0,0 +1,1022 @@ +/* + * Copyright (c) 1995-1996 Gary Thomas <gdt@linuxppc.org> + * Initial PowerPC version. + * Copyright (c) 1996 Cort Dougan <cort@cs.nmt.edu> + * Rewritten for PReP + * Copyright (c) 1996 Paul Mackerras <paulus@cs.anu.edu.au> + * Low-level exception handers, MMU support, and rewrite. + * Copyright (c) 1997 Dan Malek <dmalek@jlc.net> + * PowerPC 8xx modifications. + * Copyright (c) 1998-1999 TiVo, Inc. + * PowerPC 403GCX modifications. + * Copyright (c) 1999 Grant Erickson <grant@lcse.umn.edu> + * PowerPC 403GCX/405GP modifications. + * Copyright 2000 MontaVista Software Inc. + * PPC405 modifications + * PowerPC 403GCX/405GP modifications. + * Author: MontaVista Software, Inc. + * frank_rowand@mvista.com or source@mvista.com + * debbie_chu@mvista.com + * + * + * Module name: head_4xx.S + * + * Description: + * Kernel execution entry point code. + * + * 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/mmu.h> +#include <asm/pgtable.h> +#include <asm/ibm4xx.h> +#include <asm/cputable.h> +#include <asm/thread_info.h> +#include <asm/ppc_asm.h> +#include <asm/asm-offsets.h> + +/* As with the other PowerPC ports, it is expected that when code + * execution begins here, the following registers contain valid, yet + * optional, information: + * + * r3 - Board info structure pointer (DRAM, frequency, MAC address, etc.) + * r4 - Starting address of the init RAM disk + * r5 - Ending address of the init RAM disk + * r6 - Start of kernel command line string (e.g. "mem=96m") + * r7 - End of kernel command line string + * + * This is all going to change RSN when we add bi_recs....... -- Dan + */ + .text +_GLOBAL(_stext) +_GLOBAL(_start) + + /* Save parameters we are passed. + */ + mr r31,r3 + mr r30,r4 + mr r29,r5 + mr r28,r6 + mr r27,r7 + + /* We have to turn on the MMU right away so we get cache modes + * set correctly. + */ + bl initial_mmu + +/* We now have the lower 16 Meg mapped into TLB entries, and the caches + * ready to work. + */ +turn_on_mmu: + lis r0,MSR_KERNEL@h + ori r0,r0,MSR_KERNEL@l + mtspr SPRN_SRR1,r0 + lis r0,start_here@h + ori r0,r0,start_here@l + mtspr SPRN_SRR0,r0 + SYNC + rfi /* enables MMU */ + b . /* prevent prefetch past rfi */ + +/* + * This area is used for temporarily saving registers during the + * critical exception prolog. + */ + . = 0xc0 +crit_save: +_GLOBAL(crit_r10) + .space 4 +_GLOBAL(crit_r11) + .space 4 + +/* + * Exception vector entry code. This code runs with address translation + * turned off (i.e. using physical addresses). We assume SPRG3 has the + * physical address of the current task thread_struct. + * Note that we have to have decremented r1 before we write to any fields + * of the exception frame, since a critical interrupt could occur at any + * time, and it will write to the area immediately below the current r1. + */ +#define NORMAL_EXCEPTION_PROLOG \ + mtspr SPRN_SPRG0,r10; /* save two registers to work with */\ + mtspr SPRN_SPRG1,r11; \ + mtspr SPRN_SPRG2,r1; \ + mfcr r10; /* save CR in r10 for now */\ + mfspr r11,SPRN_SRR1; /* check whether user or kernel */\ + andi. r11,r11,MSR_PR; \ + beq 1f; \ + mfspr r1,SPRN_SPRG3; /* if from user, start at top of */\ + lwz r1,THREAD_INFO-THREAD(r1); /* this thread's kernel stack */\ + addi r1,r1,THREAD_SIZE; \ +1: subi r1,r1,INT_FRAME_SIZE; /* Allocate an exception frame */\ + tophys(r11,r1); \ + stw r10,_CCR(r11); /* save various registers */\ + stw r12,GPR12(r11); \ + stw r9,GPR9(r11); \ + mfspr r10,SPRN_SPRG0; \ + stw r10,GPR10(r11); \ + mfspr r12,SPRN_SPRG1; \ + stw r12,GPR11(r11); \ + mflr r10; \ + stw r10,_LINK(r11); \ + mfspr r10,SPRN_SPRG2; \ + mfspr r12,SPRN_SRR0; \ + stw r10,GPR1(r11); \ + mfspr r9,SPRN_SRR1; \ + stw r10,0(r11); \ + rlwinm r9,r9,0,14,12; /* clear MSR_WE (necessary?) */\ + stw r0,GPR0(r11); \ + SAVE_4GPRS(3, r11); \ + SAVE_2GPRS(7, r11) + +/* + * Exception prolog for critical exceptions. This is a little different + * from the normal exception prolog above since a critical exception + * can potentially occur at any point during normal exception processing. + * Thus we cannot use the same SPRG registers as the normal prolog above. + * Instead we use a couple of words of memory at low physical addresses. + * This is OK since we don't support SMP on these processors. + */ +#define CRITICAL_EXCEPTION_PROLOG \ + stw r10,crit_r10@l(0); /* save two registers to work with */\ + stw r11,crit_r11@l(0); \ + mfcr r10; /* save CR in r10 for now */\ + mfspr r11,SPRN_SRR3; /* check whether user or kernel */\ + andi. r11,r11,MSR_PR; \ + lis r11,critical_stack_top@h; \ + ori r11,r11,critical_stack_top@l; \ + beq 1f; \ + /* COMING FROM USER MODE */ \ + mfspr r11,SPRN_SPRG3; /* if from user, start at top of */\ + lwz r11,THREAD_INFO-THREAD(r11); /* this thread's kernel stack */\ + addi r11,r11,THREAD_SIZE; \ +1: subi r11,r11,INT_FRAME_SIZE; /* Allocate an exception frame */\ + tophys(r11,r11); \ + stw r10,_CCR(r11); /* save various registers */\ + stw r12,GPR12(r11); \ + stw r9,GPR9(r11); \ + mflr r10; \ + stw r10,_LINK(r11); \ + mfspr r12,SPRN_DEAR; /* save DEAR and ESR in the frame */\ + stw r12,_DEAR(r11); /* since they may have had stuff */\ + mfspr r9,SPRN_ESR; /* in them at the point where the */\ + stw r9,_ESR(r11); /* exception was taken */\ + mfspr r12,SPRN_SRR2; \ + stw r1,GPR1(r11); \ + mfspr r9,SPRN_SRR3; \ + stw r1,0(r11); \ + tovirt(r1,r11); \ + rlwinm r9,r9,0,14,12; /* clear MSR_WE (necessary?) */\ + stw r0,GPR0(r11); \ + SAVE_4GPRS(3, r11); \ + SAVE_2GPRS(7, r11) + + /* + * State at this point: + * r9 saved in stack frame, now saved SRR3 & ~MSR_WE + * r10 saved in crit_r10 and in stack frame, trashed + * r11 saved in crit_r11 and in stack frame, + * now phys stack/exception frame pointer + * r12 saved in stack frame, now saved SRR2 + * CR saved in stack frame, CR0.EQ = !SRR3.PR + * LR, DEAR, ESR in stack frame + * r1 saved in stack frame, now virt stack/excframe pointer + * r0, r3-r8 saved in stack frame + */ + +/* + * Exception vectors. + */ +#define START_EXCEPTION(n, label) \ + . = n; \ +label: + +#define EXCEPTION(n, label, hdlr, xfer) \ + START_EXCEPTION(n, label); \ + NORMAL_EXCEPTION_PROLOG; \ + addi r3,r1,STACK_FRAME_OVERHEAD; \ + xfer(n, hdlr) + +#define CRITICAL_EXCEPTION(n, label, hdlr) \ + START_EXCEPTION(n, label); \ + CRITICAL_EXCEPTION_PROLOG; \ + addi r3,r1,STACK_FRAME_OVERHEAD; \ + EXC_XFER_TEMPLATE(hdlr, n+2, (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), \ + NOCOPY, crit_transfer_to_handler, \ + ret_from_crit_exc) + +#define EXC_XFER_TEMPLATE(hdlr, trap, msr, copyee, tfer, ret) \ + li r10,trap; \ + stw r10,_TRAP(r11); \ + lis r10,msr@h; \ + ori r10,r10,msr@l; \ + copyee(r10, r9); \ + bl tfer; \ + .long hdlr; \ + .long ret + +#define COPY_EE(d, s) rlwimi d,s,0,16,16 +#define NOCOPY(d, s) + +#define EXC_XFER_STD(n, hdlr) \ + EXC_XFER_TEMPLATE(hdlr, n, MSR_KERNEL, NOCOPY, transfer_to_handler_full, \ + ret_from_except_full) + +#define EXC_XFER_LITE(n, hdlr) \ + EXC_XFER_TEMPLATE(hdlr, n+1, MSR_KERNEL, NOCOPY, transfer_to_handler, \ + ret_from_except) + +#define EXC_XFER_EE(n, hdlr) \ + EXC_XFER_TEMPLATE(hdlr, n, MSR_KERNEL, COPY_EE, transfer_to_handler_full, \ + ret_from_except_full) + +#define EXC_XFER_EE_LITE(n, hdlr) \ + EXC_XFER_TEMPLATE(hdlr, n+1, MSR_KERNEL, COPY_EE, transfer_to_handler, \ + ret_from_except) + + +/* + * 0x0100 - Critical Interrupt Exception + */ + CRITICAL_EXCEPTION(0x0100, CriticalInterrupt, unknown_exception) + +/* + * 0x0200 - Machine Check Exception + */ + CRITICAL_EXCEPTION(0x0200, MachineCheck, machine_check_exception) + +/* + * 0x0300 - Data Storage Exception + * This happens for just a few reasons. U0 set (but we don't do that), + * or zone protection fault (user violation, write to protected page). + * If this is just an update of modified status, we do that quickly + * and exit. Otherwise, we call heavywight functions to do the work. + */ + START_EXCEPTION(0x0300, DataStorage) + mtspr SPRN_SPRG0, r10 /* Save some working registers */ + mtspr SPRN_SPRG1, r11 +#ifdef CONFIG_403GCX + stw r12, 0(r0) + stw r9, 4(r0) + mfcr r11 + mfspr r12, SPRN_PID + stw r11, 8(r0) + stw r12, 12(r0) +#else + mtspr SPRN_SPRG4, r12 + mtspr SPRN_SPRG5, r9 + mfcr r11 + mfspr r12, SPRN_PID + mtspr SPRN_SPRG7, r11 + mtspr SPRN_SPRG6, r12 +#endif + + /* First, check if it was a zone fault (which means a user + * tried to access a kernel or read-protected page - always + * a SEGV). All other faults here must be stores, so no + * need to check ESR_DST as well. */ + mfspr r10, SPRN_ESR + andis. r10, r10, ESR_DIZ@h + bne 2f + + mfspr r10, SPRN_DEAR /* Get faulting address */ + + /* If we are faulting a kernel address, we have to use the + * kernel page tables. + */ + lis r11, TASK_SIZE@h + cmplw r10, r11 + blt+ 3f + lis r11, swapper_pg_dir@h + ori r11, r11, swapper_pg_dir@l + li r9, 0 + mtspr SPRN_PID, r9 /* TLB will have 0 TID */ + b 4f + + /* Get the PGD for the current thread. + */ +3: + mfspr r11,SPRN_SPRG3 + lwz r11,PGDIR(r11) +4: + tophys(r11, r11) + rlwimi r11, r10, 12, 20, 29 /* Create L1 (pgdir/pmd) address */ + lwz r11, 0(r11) /* Get L1 entry */ + rlwinm. r12, r11, 0, 0, 19 /* Extract L2 (pte) base address */ + beq 2f /* Bail if no table */ + + rlwimi r12, r10, 22, 20, 29 /* Compute PTE address */ + lwz r11, 0(r12) /* Get Linux PTE */ + + andi. r9, r11, _PAGE_RW /* Is it writeable? */ + beq 2f /* Bail if not */ + + /* Update 'changed'. + */ + ori r11, r11, _PAGE_DIRTY|_PAGE_ACCESSED|_PAGE_HWWRITE + stw r11, 0(r12) /* Update Linux page table */ + + /* Most of the Linux PTE is ready to load into the TLB LO. + * We set ZSEL, where only the LS-bit determines user access. + * We set execute, because we don't have the granularity to + * properly set this at the page level (Linux problem). + * If shared is set, we cause a zero PID->TID load. + * Many of these bits are software only. Bits we don't set + * here we (properly should) assume have the appropriate value. + */ + li r12, 0x0ce2 + andc r11, r11, r12 /* Make sure 20, 21 are zero */ + + /* find the TLB index that caused the fault. It has to be here. + */ + tlbsx r9, 0, r10 + + tlbwe r11, r9, TLB_DATA /* Load TLB LO */ + + /* Done...restore registers and get out of here. + */ +#ifdef CONFIG_403GCX + lwz r12, 12(r0) + lwz r11, 8(r0) + mtspr SPRN_PID, r12 + mtcr r11 + lwz r9, 4(r0) + lwz r12, 0(r0) +#else + mfspr r12, SPRN_SPRG6 + mfspr r11, SPRN_SPRG7 + mtspr SPRN_PID, r12 + mtcr r11 + mfspr r9, SPRN_SPRG5 + mfspr r12, SPRN_SPRG4 +#endif + mfspr r11, SPRN_SPRG1 + mfspr r10, SPRN_SPRG0 + PPC405_ERR77_SYNC + rfi /* Should sync shadow TLBs */ + b . /* prevent prefetch past rfi */ + +2: + /* The bailout. Restore registers to pre-exception conditions + * and call the heavyweights to help us out. + */ +#ifdef CONFIG_403GCX + lwz r12, 12(r0) + lwz r11, 8(r0) + mtspr SPRN_PID, r12 + mtcr r11 + lwz r9, 4(r0) + lwz r12, 0(r0) +#else + mfspr r12, SPRN_SPRG6 + mfspr r11, SPRN_SPRG7 + mtspr SPRN_PID, r12 + mtcr r11 + mfspr r9, SPRN_SPRG5 + mfspr r12, SPRN_SPRG4 +#endif + mfspr r11, SPRN_SPRG1 + mfspr r10, SPRN_SPRG0 + b DataAccess + +/* + * 0x0400 - Instruction Storage Exception + * This is caused by a fetch from non-execute or guarded pages. + */ + START_EXCEPTION(0x0400, InstructionAccess) + NORMAL_EXCEPTION_PROLOG + mr r4,r12 /* Pass SRR0 as arg2 */ + li r5,0 /* Pass zero as arg3 */ + EXC_XFER_EE_LITE(0x400, handle_page_fault) + +/* 0x0500 - External Interrupt Exception */ + EXCEPTION(0x0500, HardwareInterrupt, do_IRQ, EXC_XFER_LITE) + +/* 0x0600 - Alignment Exception */ + START_EXCEPTION(0x0600, Alignment) + NORMAL_EXCEPTION_PROLOG + mfspr r4,SPRN_DEAR /* Grab the DEAR and save it */ + stw r4,_DEAR(r11) + addi r3,r1,STACK_FRAME_OVERHEAD + EXC_XFER_EE(0x600, alignment_exception) + +/* 0x0700 - Program Exception */ + START_EXCEPTION(0x0700, ProgramCheck) + NORMAL_EXCEPTION_PROLOG + mfspr r4,SPRN_ESR /* Grab the ESR and save it */ + stw r4,_ESR(r11) + addi r3,r1,STACK_FRAME_OVERHEAD + EXC_XFER_STD(0x700, program_check_exception) + + EXCEPTION(0x0800, Trap_08, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x0900, Trap_09, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x0A00, Trap_0A, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x0B00, Trap_0B, unknown_exception, EXC_XFER_EE) + +/* 0x0C00 - System Call Exception */ + START_EXCEPTION(0x0C00, SystemCall) + NORMAL_EXCEPTION_PROLOG + EXC_XFER_EE_LITE(0xc00, DoSyscall) + + EXCEPTION(0x0D00, Trap_0D, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x0E00, Trap_0E, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x0F00, Trap_0F, unknown_exception, EXC_XFER_EE) + +/* 0x1000 - Programmable Interval Timer (PIT) Exception */ + START_EXCEPTION(0x1000, Decrementer) + NORMAL_EXCEPTION_PROLOG + lis r0,TSR_PIS@h + mtspr SPRN_TSR,r0 /* Clear the PIT exception */ + addi r3,r1,STACK_FRAME_OVERHEAD + EXC_XFER_LITE(0x1000, timer_interrupt) + +#if 0 +/* NOTE: + * FIT and WDT handlers are not implemented yet. + */ + +/* 0x1010 - Fixed Interval Timer (FIT) Exception +*/ + STND_EXCEPTION(0x1010, FITException, unknown_exception) + +/* 0x1020 - Watchdog Timer (WDT) Exception +*/ +#ifdef CONFIG_BOOKE_WDT + CRITICAL_EXCEPTION(0x1020, WDTException, WatchdogException) +#else + CRITICAL_EXCEPTION(0x1020, WDTException, unknown_exception) +#endif +#endif + +/* 0x1100 - Data TLB Miss Exception + * As the name implies, translation is not in the MMU, so search the + * page tables and fix it. The only purpose of this function is to + * load TLB entries from the page table if they exist. + */ + START_EXCEPTION(0x1100, DTLBMiss) + mtspr SPRN_SPRG0, r10 /* Save some working registers */ + mtspr SPRN_SPRG1, r11 +#ifdef CONFIG_403GCX + stw r12, 0(r0) + stw r9, 4(r0) + mfcr r11 + mfspr r12, SPRN_PID + stw r11, 8(r0) + stw r12, 12(r0) +#else + mtspr SPRN_SPRG4, r12 + mtspr SPRN_SPRG5, r9 + mfcr r11 + mfspr r12, SPRN_PID + mtspr SPRN_SPRG7, r11 + mtspr SPRN_SPRG6, r12 +#endif + mfspr r10, SPRN_DEAR /* Get faulting address */ + + /* If we are faulting a kernel address, we have to use the + * kernel page tables. + */ + lis r11, TASK_SIZE@h + cmplw r10, r11 + blt+ 3f + lis r11, swapper_pg_dir@h + ori r11, r11, swapper_pg_dir@l + li r9, 0 + mtspr SPRN_PID, r9 /* TLB will have 0 TID */ + b 4f + + /* Get the PGD for the current thread. + */ +3: + mfspr r11,SPRN_SPRG3 + lwz r11,PGDIR(r11) +4: + tophys(r11, r11) + rlwimi r11, r10, 12, 20, 29 /* Create L1 (pgdir/pmd) address */ + lwz r12, 0(r11) /* Get L1 entry */ + andi. r9, r12, _PMD_PRESENT /* Check if it points to a PTE page */ + beq 2f /* Bail if no table */ + + rlwimi r12, r10, 22, 20, 29 /* Compute PTE address */ + lwz r11, 0(r12) /* Get Linux PTE */ + andi. r9, r11, _PAGE_PRESENT + beq 5f + + ori r11, r11, _PAGE_ACCESSED + stw r11, 0(r12) + + /* Create TLB tag. This is the faulting address plus a static + * set of bits. These are size, valid, E, U0. + */ + li r12, 0x00c0 + rlwimi r10, r12, 0, 20, 31 + + b finish_tlb_load + +2: /* Check for possible large-page pmd entry */ + rlwinm. r9, r12, 2, 22, 24 + beq 5f + + /* Create TLB tag. This is the faulting address, plus a static + * set of bits (valid, E, U0) plus the size from the PMD. + */ + ori r9, r9, 0x40 + rlwimi r10, r9, 0, 20, 31 + mr r11, r12 + + b finish_tlb_load + +5: + /* The bailout. Restore registers to pre-exception conditions + * and call the heavyweights to help us out. + */ +#ifdef CONFIG_403GCX + lwz r12, 12(r0) + lwz r11, 8(r0) + mtspr SPRN_PID, r12 + mtcr r11 + lwz r9, 4(r0) + lwz r12, 0(r0) +#else + mfspr r12, SPRN_SPRG6 + mfspr r11, SPRN_SPRG7 + mtspr SPRN_PID, r12 + mtcr r11 + mfspr r9, SPRN_SPRG5 + mfspr r12, SPRN_SPRG4 +#endif + mfspr r11, SPRN_SPRG1 + mfspr r10, SPRN_SPRG0 + b DataAccess + +/* 0x1200 - Instruction TLB Miss Exception + * Nearly the same as above, except we get our information from different + * registers and bailout to a different point. + */ + START_EXCEPTION(0x1200, ITLBMiss) + mtspr SPRN_SPRG0, r10 /* Save some working registers */ + mtspr SPRN_SPRG1, r11 +#ifdef CONFIG_403GCX + stw r12, 0(r0) + stw r9, 4(r0) + mfcr r11 + mfspr r12, SPRN_PID + stw r11, 8(r0) + stw r12, 12(r0) +#else + mtspr SPRN_SPRG4, r12 + mtspr SPRN_SPRG5, r9 + mfcr r11 + mfspr r12, SPRN_PID + mtspr SPRN_SPRG7, r11 + mtspr SPRN_SPRG6, r12 +#endif + mfspr r10, SPRN_SRR0 /* Get faulting address */ + + /* If we are faulting a kernel address, we have to use the + * kernel page tables. + */ + lis r11, TASK_SIZE@h + cmplw r10, r11 + blt+ 3f + lis r11, swapper_pg_dir@h + ori r11, r11, swapper_pg_dir@l + li r9, 0 + mtspr SPRN_PID, r9 /* TLB will have 0 TID */ + b 4f + + /* Get the PGD for the current thread. + */ +3: + mfspr r11,SPRN_SPRG3 + lwz r11,PGDIR(r11) +4: + tophys(r11, r11) + rlwimi r11, r10, 12, 20, 29 /* Create L1 (pgdir/pmd) address */ + lwz r12, 0(r11) /* Get L1 entry */ + andi. r9, r12, _PMD_PRESENT /* Check if it points to a PTE page */ + beq 2f /* Bail if no table */ + + rlwimi r12, r10, 22, 20, 29 /* Compute PTE address */ + lwz r11, 0(r12) /* Get Linux PTE */ + andi. r9, r11, _PAGE_PRESENT + beq 5f + + ori r11, r11, _PAGE_ACCESSED + stw r11, 0(r12) + + /* Create TLB tag. This is the faulting address plus a static + * set of bits. These are size, valid, E, U0. + */ + li r12, 0x00c0 + rlwimi r10, r12, 0, 20, 31 + + b finish_tlb_load + +2: /* Check for possible large-page pmd entry */ + rlwinm. r9, r12, 2, 22, 24 + beq 5f + + /* Create TLB tag. This is the faulting address, plus a static + * set of bits (valid, E, U0) plus the size from the PMD. + */ + ori r9, r9, 0x40 + rlwimi r10, r9, 0, 20, 31 + mr r11, r12 + + b finish_tlb_load + +5: + /* The bailout. Restore registers to pre-exception conditions + * and call the heavyweights to help us out. + */ +#ifdef CONFIG_403GCX + lwz r12, 12(r0) + lwz r11, 8(r0) + mtspr SPRN_PID, r12 + mtcr r11 + lwz r9, 4(r0) + lwz r12, 0(r0) +#else + mfspr r12, SPRN_SPRG6 + mfspr r11, SPRN_SPRG7 + mtspr SPRN_PID, r12 + mtcr r11 + mfspr r9, SPRN_SPRG5 + mfspr r12, SPRN_SPRG4 +#endif + mfspr r11, SPRN_SPRG1 + mfspr r10, SPRN_SPRG0 + b InstructionAccess + + EXCEPTION(0x1300, Trap_13, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1400, Trap_14, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1500, Trap_15, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1600, Trap_16, unknown_exception, EXC_XFER_EE) +#ifdef CONFIG_IBM405_ERR51 + /* 405GP errata 51 */ + START_EXCEPTION(0x1700, Trap_17) + b DTLBMiss +#else + EXCEPTION(0x1700, Trap_17, unknown_exception, EXC_XFER_EE) +#endif + EXCEPTION(0x1800, Trap_18, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1900, Trap_19, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1A00, Trap_1A, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1B00, Trap_1B, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1C00, Trap_1C, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1D00, Trap_1D, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1E00, Trap_1E, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1F00, Trap_1F, unknown_exception, EXC_XFER_EE) + +/* Check for a single step debug exception while in an exception + * handler before state has been saved. This is to catch the case + * where an instruction that we are trying to single step causes + * an exception (eg ITLB/DTLB miss) and thus the first instruction of + * the exception handler generates a single step debug exception. + * + * If we get a debug trap on the first instruction of an exception handler, + * we reset the MSR_DE in the _exception handler's_ MSR (the debug trap is + * a critical exception, so we are using SPRN_CSRR1 to manipulate the MSR). + * The exception handler was handling a non-critical interrupt, so it will + * save (and later restore) the MSR via SPRN_SRR1, which will still have + * the MSR_DE bit set. + */ + /* 0x2000 - Debug Exception */ + START_EXCEPTION(0x2000, DebugTrap) + CRITICAL_EXCEPTION_PROLOG + + /* + * If this is a single step or branch-taken exception in an + * exception entry sequence, it was probably meant to apply to + * the code where the exception occurred (since exception entry + * doesn't turn off DE automatically). We simulate the effect + * of turning off DE on entry to an exception handler by turning + * off DE in the SRR3 value and clearing the debug status. + */ + mfspr r10,SPRN_DBSR /* check single-step/branch taken */ + andis. r10,r10,DBSR_IC@h + beq+ 2f + + andi. r10,r9,MSR_IR|MSR_PR /* check supervisor + MMU off */ + beq 1f /* branch and fix it up */ + + mfspr r10,SPRN_SRR2 /* Faulting instruction address */ + cmplwi r10,0x2100 + bgt+ 2f /* address above exception vectors */ + + /* here it looks like we got an inappropriate debug exception. */ +1: rlwinm r9,r9,0,~MSR_DE /* clear DE in the SRR3 value */ + lis r10,DBSR_IC@h /* clear the IC event */ + mtspr SPRN_DBSR,r10 + /* restore state and get out */ + lwz r10,_CCR(r11) + lwz r0,GPR0(r11) + lwz r1,GPR1(r11) + mtcrf 0x80,r10 + mtspr SPRN_SRR2,r12 + mtspr SPRN_SRR3,r9 + lwz r9,GPR9(r11) + lwz r12,GPR12(r11) + lwz r10,crit_r10@l(0) + lwz r11,crit_r11@l(0) + PPC405_ERR77_SYNC + rfci + b . + + /* continue normal handling for a critical exception... */ +2: mfspr r4,SPRN_DBSR + addi r3,r1,STACK_FRAME_OVERHEAD + EXC_XFER_TEMPLATE(DebugException, 0x2002, \ + (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), \ + NOCOPY, crit_transfer_to_handler, ret_from_crit_exc) + +/* + * The other Data TLB exceptions bail out to this point + * if they can't resolve the lightweight TLB fault. + */ +DataAccess: + NORMAL_EXCEPTION_PROLOG + mfspr r5,SPRN_ESR /* Grab the ESR, save it, pass arg3 */ + stw r5,_ESR(r11) + mfspr r4,SPRN_DEAR /* Grab the DEAR, save it, pass arg2 */ + EXC_XFER_EE_LITE(0x300, handle_page_fault) + +/* Other PowerPC processors, namely those derived from the 6xx-series + * have vectors from 0x2100 through 0x2F00 defined, but marked as reserved. + * However, for the 4xx-series processors these are neither defined nor + * reserved. + */ + + /* Damn, I came up one instruction too many to fit into the + * exception space :-). Both the instruction and data TLB + * miss get to this point to load the TLB. + * r10 - TLB_TAG value + * r11 - Linux PTE + * r12, r9 - avilable to use + * PID - loaded with proper value when we get here + * Upon exit, we reload everything and RFI. + * Actually, it will fit now, but oh well.....a common place + * to load the TLB. + */ +tlb_4xx_index: + .long 0 +finish_tlb_load: + /* load the next available TLB index. + */ + lwz r9, tlb_4xx_index@l(0) + addi r9, r9, 1 + andi. r9, r9, (PPC4XX_TLB_SIZE-1) + stw r9, tlb_4xx_index@l(0) + +6: + /* + * Clear out the software-only bits in the PTE to generate the + * TLB_DATA value. These are the bottom 2 bits of the RPM, the + * top 3 bits of the zone field, and M. + */ + li r12, 0x0ce2 + andc r11, r11, r12 + + tlbwe r11, r9, TLB_DATA /* Load TLB LO */ + tlbwe r10, r9, TLB_TAG /* Load TLB HI */ + + /* Done...restore registers and get out of here. + */ +#ifdef CONFIG_403GCX + lwz r12, 12(r0) + lwz r11, 8(r0) + mtspr SPRN_PID, r12 + mtcr r11 + lwz r9, 4(r0) + lwz r12, 0(r0) +#else + mfspr r12, SPRN_SPRG6 + mfspr r11, SPRN_SPRG7 + mtspr SPRN_PID, r12 + mtcr r11 + mfspr r9, SPRN_SPRG5 + mfspr r12, SPRN_SPRG4 +#endif + mfspr r11, SPRN_SPRG1 + mfspr r10, SPRN_SPRG0 + PPC405_ERR77_SYNC + rfi /* Should sync shadow TLBs */ + b . /* prevent prefetch past rfi */ + +/* extern void giveup_fpu(struct task_struct *prev) + * + * The PowerPC 4xx family of processors do not have an FPU, so this just + * returns. + */ +_GLOBAL(giveup_fpu) + blr + +/* This is where the main kernel code starts. + */ +start_here: + + /* ptr to current */ + lis r2,init_task@h + ori r2,r2,init_task@l + + /* ptr to phys current thread */ + tophys(r4,r2) + addi r4,r4,THREAD /* init task's THREAD */ + mtspr SPRN_SPRG3,r4 + + /* stack */ + lis r1,init_thread_union@ha + addi r1,r1,init_thread_union@l + li r0,0 + stwu r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1) + + bl early_init /* We have to do this with MMU on */ + +/* + * Decide what sort of machine this is and initialize the MMU. + */ + mr r3,r31 + mr r4,r30 + mr r5,r29 + mr r6,r28 + mr r7,r27 + bl machine_init + bl MMU_init + +/* Go back to running unmapped so we can load up new values + * and change to using our exception vectors. + * On the 4xx, all we have to do is invalidate the TLB to clear + * the old 16M byte TLB mappings. + */ + lis r4,2f@h + ori r4,r4,2f@l + tophys(r4,r4) + lis r3,(MSR_KERNEL & ~(MSR_IR|MSR_DR))@h + ori r3,r3,(MSR_KERNEL & ~(MSR_IR|MSR_DR))@l + mtspr SPRN_SRR0,r4 + mtspr SPRN_SRR1,r3 + rfi + b . /* prevent prefetch past rfi */ + +/* Load up the kernel context */ +2: + sync /* Flush to memory before changing TLB */ + tlbia + isync /* Flush shadow TLBs */ + + /* set up the PTE pointers for the Abatron bdiGDB. + */ + lis r6, swapper_pg_dir@h + ori r6, r6, swapper_pg_dir@l + lis r5, abatron_pteptrs@h + ori r5, r5, abatron_pteptrs@l + stw r5, 0xf0(r0) /* Must match your Abatron config file */ + tophys(r5,r5) + stw r6, 0(r5) + +/* Now turn on the MMU for real! */ + lis r4,MSR_KERNEL@h + ori r4,r4,MSR_KERNEL@l + lis r3,start_kernel@h + ori r3,r3,start_kernel@l + mtspr SPRN_SRR0,r3 + mtspr SPRN_SRR1,r4 + rfi /* enable MMU and jump to start_kernel */ + b . /* prevent prefetch past rfi */ + +/* Set up the initial MMU state so we can do the first level of + * kernel initialization. This maps the first 16 MBytes of memory 1:1 + * virtual to physical and more importantly sets the cache mode. + */ +initial_mmu: + tlbia /* Invalidate all TLB entries */ + isync + + /* We should still be executing code at physical address 0x0000xxxx + * at this point. However, start_here is at virtual address + * 0xC000xxxx. So, set up a TLB mapping to cover this once + * translation is enabled. + */ + + lis r3,KERNELBASE@h /* Load the kernel virtual address */ + ori r3,r3,KERNELBASE@l + tophys(r4,r3) /* Load the kernel physical address */ + + iccci r0,r3 /* Invalidate the i-cache before use */ + + /* Load the kernel PID. + */ + li r0,0 + mtspr SPRN_PID,r0 + sync + + /* Configure and load two entries into TLB slots 62 and 63. + * In case we are pinning TLBs, these are reserved in by the + * other TLB functions. If not reserving, then it doesn't + * matter where they are loaded. + */ + clrrwi r4,r4,10 /* Mask off the real page number */ + ori r4,r4,(TLB_WR | TLB_EX) /* Set the write and execute bits */ + + clrrwi r3,r3,10 /* Mask off the effective page number */ + ori r3,r3,(TLB_VALID | TLB_PAGESZ(PAGESZ_16M)) + + li r0,63 /* TLB slot 63 */ + + tlbwe r4,r0,TLB_DATA /* Load the data portion of the entry */ + tlbwe r3,r0,TLB_TAG /* Load the tag portion of the entry */ + +#if defined(CONFIG_SERIAL_TEXT_DEBUG) && defined(SERIAL_DEBUG_IO_BASE) + + /* Load a TLB entry for the UART, so that ppc4xx_progress() can use + * the UARTs nice and early. We use a 4k real==virtual mapping. */ + + lis r3,SERIAL_DEBUG_IO_BASE@h + ori r3,r3,SERIAL_DEBUG_IO_BASE@l + mr r4,r3 + clrrwi r4,r4,12 + ori r4,r4,(TLB_WR|TLB_I|TLB_M|TLB_G) + + clrrwi r3,r3,12 + ori r3,r3,(TLB_VALID | TLB_PAGESZ(PAGESZ_4K)) + + li r0,0 /* TLB slot 0 */ + tlbwe r4,r0,TLB_DATA + tlbwe r3,r0,TLB_TAG +#endif /* CONFIG_SERIAL_DEBUG_TEXT && SERIAL_DEBUG_IO_BASE */ + + isync + + /* Establish the exception vector base + */ + lis r4,KERNELBASE@h /* EVPR only uses the high 16-bits */ + tophys(r0,r4) /* Use the physical address */ + mtspr SPRN_EVPR,r0 + + blr + +_GLOBAL(abort) + mfspr r13,SPRN_DBCR0 + oris r13,r13,DBCR0_RST_SYSTEM@h + mtspr SPRN_DBCR0,r13 + +_GLOBAL(set_context) + +#ifdef CONFIG_BDI_SWITCH + /* Context switch the PTE pointer for the Abatron BDI2000. + * The PGDIR is the second parameter. + */ + lis r5, KERNELBASE@h + lwz r5, 0xf0(r5) + stw r4, 0x4(r5) +#endif + sync + mtspr SPRN_PID,r3 + isync /* Need an isync to flush shadow */ + /* TLBs after changing PID */ + blr + +/* We put a few things here that have to be page-aligned. This stuff + * goes at the beginning of the data segment, which is page-aligned. + */ + .data + .align 12 + .globl sdata +sdata: + .globl empty_zero_page +empty_zero_page: + .space 4096 + .globl swapper_pg_dir +swapper_pg_dir: + .space 4096 + + +/* Stack for handling critical exceptions from kernel mode */ + .section .bss + .align 12 +exception_stack_bottom: + .space 4096 +critical_stack_top: + .globl exception_stack_top +exception_stack_top: + +/* This space gets a copy of optional info passed to us by the bootstrap + * which is used to pass parameters into the kernel like root=/dev/sda1, etc. + */ + .globl cmd_line +cmd_line: + .space 512 + +/* Room for two PTE pointers, usually the kernel and current user pointers + * to their respective root page table. + */ +abatron_pteptrs: + .space 8 diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S new file mode 100644 index 000000000000..147215a0d6c0 --- /dev/null +++ b/arch/powerpc/kernel/head_64.S @@ -0,0 +1,1957 @@ +/* + * arch/ppc64/kernel/head.S + * + * PowerPC version + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) + * + * Rewritten by Cort Dougan (cort@cs.nmt.edu) for PReP + * Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu> + * Adapted for Power Macintosh by Paul Mackerras. + * Low-level exception handlers and MMU support + * rewritten by Paul Mackerras. + * Copyright (C) 1996 Paul Mackerras. + * + * Adapted for 64bit PowerPC by Dave Engebretsen, Peter Bergner, and + * Mike Corrigan {engebret|bergner|mikejc}@us.ibm.com + * + * This file contains the low-level support and setup for the + * PowerPC-64 platform, including trap and interrupt dispatch. + * + * 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/threads.h> +#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> +#include <asm/cputable.h> +#include <asm/setup.h> +#include <asm/hvcall.h> +#include <asm/iSeries/LparMap.h> +#include <asm/thread_info.h> + +#ifdef CONFIG_PPC_ISERIES +#define DO_SOFT_DISABLE +#endif + +/* + * We layout physical memory as follows: + * 0x0000 - 0x00ff : Secondary processor spin code + * 0x0100 - 0x2fff : pSeries Interrupt prologs + * 0x3000 - 0x5fff : interrupt support, iSeries and common interrupt prologs + * 0x6000 - 0x6fff : Initial (CPU0) segment table + * 0x7000 - 0x7fff : FWNMI data area + * 0x8000 - : Early init and support code + */ + +/* + * SPRG Usage + * + * Register Definition + * + * SPRG0 reserved for hypervisor + * SPRG1 temp - used to save gpr + * SPRG2 temp - used to save gpr + * SPRG3 virt addr of paca + */ + +/* + * Entering into this code we make the following assumptions: + * For pSeries: + * 1. The MMU is off & open firmware is running in real mode. + * 2. The kernel is entered at __start + * + * For iSeries: + * 1. The MMU is on (as it always is for iSeries) + * 2. The kernel is entered at system_reset_iSeries + */ + + .text + .globl _stext +_stext: +#ifdef CONFIG_PPC_MULTIPLATFORM +_GLOBAL(__start) + /* NOP this out unconditionally */ +BEGIN_FTR_SECTION + b .__start_initialization_multiplatform +END_FTR_SECTION(0, 1) +#endif /* CONFIG_PPC_MULTIPLATFORM */ + + /* Catch branch to 0 in real mode */ + trap + +#ifdef CONFIG_PPC_ISERIES + /* + * At offset 0x20, there is a pointer to iSeries LPAR data. + * This is required by the hypervisor + */ + . = 0x20 + .llong hvReleaseData-KERNELBASE + + /* + * At offset 0x28 and 0x30 are offsets to the mschunks_map + * array (used by the iSeries LPAR debugger to do translation + * between physical addresses and absolute addresses) and + * to the pidhash table (also used by the debugger) + */ + .llong mschunks_map-KERNELBASE + .llong 0 /* pidhash-KERNELBASE SFRXXX */ + + /* Offset 0x38 - Pointer to start of embedded System.map */ + .globl embedded_sysmap_start +embedded_sysmap_start: + .llong 0 + /* Offset 0x40 - Pointer to end of embedded System.map */ + .globl embedded_sysmap_end +embedded_sysmap_end: + .llong 0 + +#endif /* CONFIG_PPC_ISERIES */ + + /* Secondary processors spin on this value until it goes to 1. */ + .globl __secondary_hold_spinloop +__secondary_hold_spinloop: + .llong 0x0 + + /* Secondary processors write this value with their cpu # */ + /* after they enter the spin loop immediately below. */ + .globl __secondary_hold_acknowledge +__secondary_hold_acknowledge: + .llong 0x0 + + . = 0x60 +/* + * The following code is used on pSeries to hold secondary processors + * in a spin loop after they have been freed from OpenFirmware, but + * before the bulk of the kernel has been relocated. This code + * is relocated to physical address 0x60 before prom_init is run. + * All of it must fit below the first exception vector at 0x100. + */ +_GLOBAL(__secondary_hold) + mfmsr r24 + ori r24,r24,MSR_RI + mtmsrd r24 /* RI on */ + + /* Grab our linux cpu number */ + mr r24,r3 + + /* Tell the master cpu we're here */ + /* Relocation is off & we are located at an address less */ + /* than 0x100, so only need to grab low order offset. */ + std r24,__secondary_hold_acknowledge@l(0) + sync + + /* All secondary cpus wait here until told to start. */ +100: ld r4,__secondary_hold_spinloop@l(0) + cmpdi 0,r4,1 + bne 100b + +#ifdef CONFIG_HMT + b .hmt_init +#else +#ifdef CONFIG_SMP + mr r3,r24 + b .pSeries_secondary_smp_init +#else + BUG_OPCODE +#endif +#endif + +/* This value is used to mark exception frames on the stack. */ + .section ".toc","aw" +exception_marker: + .tc ID_72656773_68657265[TC],0x7265677368657265 + .text + +/* + * The following macros define the code that appears as + * the prologue to each of the exception handlers. They + * are split into two parts to allow a single kernel binary + * to be used for pSeries and iSeries. + * LOL. One day... - paulus + */ + +/* + * We make as much of the exception code common between native + * exception handlers (including pSeries LPAR) and iSeries LPAR + * implementations as possible. + */ + +/* + * This is the start of the interrupt handlers for pSeries + * This code runs with relocation off. + */ +#define EX_R9 0 +#define EX_R10 8 +#define EX_R11 16 +#define EX_R12 24 +#define EX_R13 32 +#define EX_SRR0 40 +#define EX_R3 40 /* SLB miss saves R3, but not SRR0 */ +#define EX_DAR 48 +#define EX_LR 48 /* SLB miss saves LR, but not DAR */ +#define EX_DSISR 56 +#define EX_CCR 60 + +#define EXCEPTION_PROLOG_PSERIES(area, label) \ + mfspr r13,SPRN_SPRG3; /* get paca address into r13 */ \ + std r9,area+EX_R9(r13); /* save r9 - r12 */ \ + std r10,area+EX_R10(r13); \ + std r11,area+EX_R11(r13); \ + std r12,area+EX_R12(r13); \ + mfspr r9,SPRN_SPRG1; \ + std r9,area+EX_R13(r13); \ + mfcr r9; \ + clrrdi r12,r13,32; /* get high part of &label */ \ + mfmsr r10; \ + mfspr r11,SPRN_SRR0; /* save SRR0 */ \ + ori r12,r12,(label)@l; /* virt addr of handler */ \ + ori r10,r10,MSR_IR|MSR_DR|MSR_RI; \ + mtspr SPRN_SRR0,r12; \ + mfspr r12,SPRN_SRR1; /* and SRR1 */ \ + mtspr SPRN_SRR1,r10; \ + rfid; \ + b . /* prevent speculative execution */ + +/* + * This is the start of the interrupt handlers for iSeries + * This code runs with relocation on. + */ +#define EXCEPTION_PROLOG_ISERIES_1(area) \ + mfspr r13,SPRN_SPRG3; /* get paca address into r13 */ \ + std r9,area+EX_R9(r13); /* save r9 - r12 */ \ + std r10,area+EX_R10(r13); \ + std r11,area+EX_R11(r13); \ + std r12,area+EX_R12(r13); \ + mfspr r9,SPRN_SPRG1; \ + std r9,area+EX_R13(r13); \ + mfcr r9 + +#define EXCEPTION_PROLOG_ISERIES_2 \ + mfmsr r10; \ + ld r11,PACALPPACA+LPPACASRR0(r13); \ + ld r12,PACALPPACA+LPPACASRR1(r13); \ + ori r10,r10,MSR_RI; \ + mtmsrd r10,1 + +/* + * The common exception prolog is used for all except a few exceptions + * such as a segment miss on a kernel address. We have to be prepared + * to take another exception from the point where we first touch the + * kernel stack onwards. + * + * On entry r13 points to the paca, r9-r13 are saved in the paca, + * r9 contains the saved CR, r11 and r12 contain the saved SRR0 and + * SRR1, and relocation is on. + */ +#define EXCEPTION_PROLOG_COMMON(n, area) \ + andi. r10,r12,MSR_PR; /* See if coming from user */ \ + mr r10,r1; /* Save r1 */ \ + subi r1,r1,INT_FRAME_SIZE; /* alloc frame on kernel stack */ \ + beq- 1f; \ + ld r1,PACAKSAVE(r13); /* kernel stack to use */ \ +1: cmpdi cr1,r1,0; /* check if r1 is in userspace */ \ + bge- cr1,bad_stack; /* abort if it is */ \ + std r9,_CCR(r1); /* save CR in stackframe */ \ + std r11,_NIP(r1); /* save SRR0 in stackframe */ \ + std r12,_MSR(r1); /* save SRR1 in stackframe */ \ + std r10,0(r1); /* make stack chain pointer */ \ + std r0,GPR0(r1); /* save r0 in stackframe */ \ + std r10,GPR1(r1); /* save r1 in stackframe */ \ + std r2,GPR2(r1); /* save r2 in stackframe */ \ + SAVE_4GPRS(3, r1); /* save r3 - r6 in stackframe */ \ + SAVE_2GPRS(7, r1); /* save r7, r8 in stackframe */ \ + ld r9,area+EX_R9(r13); /* move r9, r10 to stackframe */ \ + ld r10,area+EX_R10(r13); \ + std r9,GPR9(r1); \ + std r10,GPR10(r1); \ + ld r9,area+EX_R11(r13); /* move r11 - r13 to stackframe */ \ + ld r10,area+EX_R12(r13); \ + ld r11,area+EX_R13(r13); \ + std r9,GPR11(r1); \ + std r10,GPR12(r1); \ + std r11,GPR13(r1); \ + ld r2,PACATOC(r13); /* get kernel TOC into r2 */ \ + mflr r9; /* save LR in stackframe */ \ + std r9,_LINK(r1); \ + mfctr r10; /* save CTR in stackframe */ \ + std r10,_CTR(r1); \ + mfspr r11,SPRN_XER; /* save XER in stackframe */ \ + std r11,_XER(r1); \ + li r9,(n)+1; \ + std r9,_TRAP(r1); /* set trap number */ \ + li r10,0; \ + ld r11,exception_marker@toc(r2); \ + std r10,RESULT(r1); /* clear regs->result */ \ + std r11,STACK_FRAME_OVERHEAD-16(r1); /* mark the frame */ + +/* + * Exception vectors. + */ +#define STD_EXCEPTION_PSERIES(n, label) \ + . = n; \ + .globl label##_pSeries; \ +label##_pSeries: \ + HMT_MEDIUM; \ + mtspr SPRN_SPRG1,r13; /* save r13 */ \ + RUNLATCH_ON(r13); \ + EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common) + +#define STD_EXCEPTION_ISERIES(n, label, area) \ + .globl label##_iSeries; \ +label##_iSeries: \ + HMT_MEDIUM; \ + mtspr SPRN_SPRG1,r13; /* save r13 */ \ + RUNLATCH_ON(r13); \ + EXCEPTION_PROLOG_ISERIES_1(area); \ + EXCEPTION_PROLOG_ISERIES_2; \ + b label##_common + +#define MASKABLE_EXCEPTION_ISERIES(n, label) \ + .globl label##_iSeries; \ +label##_iSeries: \ + HMT_MEDIUM; \ + mtspr SPRN_SPRG1,r13; /* save r13 */ \ + RUNLATCH_ON(r13); \ + EXCEPTION_PROLOG_ISERIES_1(PACA_EXGEN); \ + lbz r10,PACAPROCENABLED(r13); \ + cmpwi 0,r10,0; \ + beq- label##_iSeries_masked; \ + EXCEPTION_PROLOG_ISERIES_2; \ + b label##_common; \ + +#ifdef DO_SOFT_DISABLE +#define DISABLE_INTS \ + lbz r10,PACAPROCENABLED(r13); \ + li r11,0; \ + std r10,SOFTE(r1); \ + mfmsr r10; \ + stb r11,PACAPROCENABLED(r13); \ + ori r10,r10,MSR_EE; \ + mtmsrd r10,1 + +#define ENABLE_INTS \ + lbz r10,PACAPROCENABLED(r13); \ + mfmsr r11; \ + std r10,SOFTE(r1); \ + ori r11,r11,MSR_EE; \ + mtmsrd r11,1 + +#else /* hard enable/disable interrupts */ +#define DISABLE_INTS + +#define ENABLE_INTS \ + ld r12,_MSR(r1); \ + mfmsr r11; \ + rlwimi r11,r12,0,MSR_EE; \ + mtmsrd r11,1 + +#endif + +#define STD_EXCEPTION_COMMON(trap, label, hdlr) \ + .align 7; \ + .globl label##_common; \ +label##_common: \ + EXCEPTION_PROLOG_COMMON(trap, PACA_EXGEN); \ + DISABLE_INTS; \ + bl .save_nvgprs; \ + addi r3,r1,STACK_FRAME_OVERHEAD; \ + bl hdlr; \ + b .ret_from_except + +#define STD_EXCEPTION_COMMON_LITE(trap, label, hdlr) \ + .align 7; \ + .globl label##_common; \ +label##_common: \ + EXCEPTION_PROLOG_COMMON(trap, PACA_EXGEN); \ + DISABLE_INTS; \ + addi r3,r1,STACK_FRAME_OVERHEAD; \ + bl hdlr; \ + b .ret_from_except_lite + +/* + * Start of pSeries system interrupt routines + */ + . = 0x100 + .globl __start_interrupts +__start_interrupts: + + STD_EXCEPTION_PSERIES(0x100, system_reset) + + . = 0x200 +_machine_check_pSeries: + HMT_MEDIUM + mtspr SPRN_SPRG1,r13 /* save r13 */ + RUNLATCH_ON(r13) + EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common) + + . = 0x300 + .globl data_access_pSeries +data_access_pSeries: + HMT_MEDIUM + mtspr SPRN_SPRG1,r13 +BEGIN_FTR_SECTION + mtspr SPRN_SPRG2,r12 + mfspr r13,SPRN_DAR + mfspr r12,SPRN_DSISR + srdi r13,r13,60 + rlwimi r13,r12,16,0x20 + mfcr r12 + cmpwi r13,0x2c + beq .do_stab_bolted_pSeries + mtcrf 0x80,r12 + mfspr r12,SPRN_SPRG2 +END_FTR_SECTION_IFCLR(CPU_FTR_SLB) + EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common) + + . = 0x380 + .globl data_access_slb_pSeries +data_access_slb_pSeries: + HMT_MEDIUM + mtspr SPRN_SPRG1,r13 + RUNLATCH_ON(r13) + mfspr r13,SPRN_SPRG3 /* get paca address into r13 */ + std r9,PACA_EXSLB+EX_R9(r13) /* save r9 - r12 */ + std r10,PACA_EXSLB+EX_R10(r13) + std r11,PACA_EXSLB+EX_R11(r13) + std r12,PACA_EXSLB+EX_R12(r13) + std r3,PACA_EXSLB+EX_R3(r13) + mfspr r9,SPRN_SPRG1 + std r9,PACA_EXSLB+EX_R13(r13) + mfcr r9 + mfspr r12,SPRN_SRR1 /* and SRR1 */ + mfspr r3,SPRN_DAR + b .do_slb_miss /* Rel. branch works in real mode */ + + STD_EXCEPTION_PSERIES(0x400, instruction_access) + + . = 0x480 + .globl instruction_access_slb_pSeries +instruction_access_slb_pSeries: + HMT_MEDIUM + mtspr SPRN_SPRG1,r13 + RUNLATCH_ON(r13) + mfspr r13,SPRN_SPRG3 /* get paca address into r13 */ + std r9,PACA_EXSLB+EX_R9(r13) /* save r9 - r12 */ + std r10,PACA_EXSLB+EX_R10(r13) + std r11,PACA_EXSLB+EX_R11(r13) + std r12,PACA_EXSLB+EX_R12(r13) + std r3,PACA_EXSLB+EX_R3(r13) + mfspr r9,SPRN_SPRG1 + std r9,PACA_EXSLB+EX_R13(r13) + mfcr r9 + mfspr r12,SPRN_SRR1 /* and SRR1 */ + mfspr r3,SPRN_SRR0 /* SRR0 is faulting address */ + b .do_slb_miss /* Rel. branch works in real mode */ + + STD_EXCEPTION_PSERIES(0x500, hardware_interrupt) + STD_EXCEPTION_PSERIES(0x600, alignment) + STD_EXCEPTION_PSERIES(0x700, program_check) + STD_EXCEPTION_PSERIES(0x800, fp_unavailable) + STD_EXCEPTION_PSERIES(0x900, decrementer) + STD_EXCEPTION_PSERIES(0xa00, trap_0a) + STD_EXCEPTION_PSERIES(0xb00, trap_0b) + + . = 0xc00 + .globl system_call_pSeries +system_call_pSeries: + HMT_MEDIUM + RUNLATCH_ON(r9) + mr r9,r13 + mfmsr r10 + mfspr r13,SPRN_SPRG3 + mfspr r11,SPRN_SRR0 + clrrdi r12,r13,32 + oris r12,r12,system_call_common@h + ori r12,r12,system_call_common@l + mtspr SPRN_SRR0,r12 + ori r10,r10,MSR_IR|MSR_DR|MSR_RI + mfspr r12,SPRN_SRR1 + mtspr SPRN_SRR1,r10 + rfid + b . /* prevent speculative execution */ + + STD_EXCEPTION_PSERIES(0xd00, single_step) + STD_EXCEPTION_PSERIES(0xe00, trap_0e) + + /* We need to deal with the Altivec unavailable exception + * here which is at 0xf20, thus in the middle of the + * prolog code of the PerformanceMonitor one. A little + * trickery is thus necessary + */ + . = 0xf00 + b performance_monitor_pSeries + + STD_EXCEPTION_PSERIES(0xf20, altivec_unavailable) + + STD_EXCEPTION_PSERIES(0x1300, instruction_breakpoint) + STD_EXCEPTION_PSERIES(0x1700, altivec_assist) + + . = 0x3000 + +/*** pSeries interrupt support ***/ + + /* moved from 0xf00 */ + STD_EXCEPTION_PSERIES(., performance_monitor) + + .align 7 +_GLOBAL(do_stab_bolted_pSeries) + mtcrf 0x80,r12 + mfspr r12,SPRN_SPRG2 + EXCEPTION_PROLOG_PSERIES(PACA_EXSLB, .do_stab_bolted) + +/* + * Vectors for the FWNMI option. Share common code. + */ + .globl system_reset_fwnmi +system_reset_fwnmi: + HMT_MEDIUM + mtspr SPRN_SPRG1,r13 /* save r13 */ + RUNLATCH_ON(r13) + EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common) + + .globl machine_check_fwnmi +machine_check_fwnmi: + HMT_MEDIUM + mtspr SPRN_SPRG1,r13 /* save r13 */ + RUNLATCH_ON(r13) + EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common) + +#ifdef CONFIG_PPC_ISERIES +/*** ISeries-LPAR interrupt handlers ***/ + + STD_EXCEPTION_ISERIES(0x200, machine_check, PACA_EXMC) + + .globl data_access_iSeries +data_access_iSeries: + mtspr SPRN_SPRG1,r13 +BEGIN_FTR_SECTION + mtspr SPRN_SPRG2,r12 + mfspr r13,SPRN_DAR + mfspr r12,SPRN_DSISR + srdi r13,r13,60 + rlwimi r13,r12,16,0x20 + mfcr r12 + cmpwi r13,0x2c + beq .do_stab_bolted_iSeries + mtcrf 0x80,r12 + mfspr r12,SPRN_SPRG2 +END_FTR_SECTION_IFCLR(CPU_FTR_SLB) + EXCEPTION_PROLOG_ISERIES_1(PACA_EXGEN) + EXCEPTION_PROLOG_ISERIES_2 + b data_access_common + +.do_stab_bolted_iSeries: + mtcrf 0x80,r12 + mfspr r12,SPRN_SPRG2 + EXCEPTION_PROLOG_ISERIES_1(PACA_EXSLB) + EXCEPTION_PROLOG_ISERIES_2 + b .do_stab_bolted + + .globl data_access_slb_iSeries +data_access_slb_iSeries: + mtspr SPRN_SPRG1,r13 /* save r13 */ + EXCEPTION_PROLOG_ISERIES_1(PACA_EXSLB) + std r3,PACA_EXSLB+EX_R3(r13) + ld r12,PACALPPACA+LPPACASRR1(r13) + mfspr r3,SPRN_DAR + b .do_slb_miss + + STD_EXCEPTION_ISERIES(0x400, instruction_access, PACA_EXGEN) + + .globl instruction_access_slb_iSeries +instruction_access_slb_iSeries: + mtspr SPRN_SPRG1,r13 /* save r13 */ + EXCEPTION_PROLOG_ISERIES_1(PACA_EXSLB) + std r3,PACA_EXSLB+EX_R3(r13) + ld r12,PACALPPACA+LPPACASRR1(r13) + ld r3,PACALPPACA+LPPACASRR0(r13) + b .do_slb_miss + + MASKABLE_EXCEPTION_ISERIES(0x500, hardware_interrupt) + STD_EXCEPTION_ISERIES(0x600, alignment, PACA_EXGEN) + STD_EXCEPTION_ISERIES(0x700, program_check, PACA_EXGEN) + STD_EXCEPTION_ISERIES(0x800, fp_unavailable, PACA_EXGEN) + MASKABLE_EXCEPTION_ISERIES(0x900, decrementer) + STD_EXCEPTION_ISERIES(0xa00, trap_0a, PACA_EXGEN) + STD_EXCEPTION_ISERIES(0xb00, trap_0b, PACA_EXGEN) + + .globl system_call_iSeries +system_call_iSeries: + mr r9,r13 + mfspr r13,SPRN_SPRG3 + EXCEPTION_PROLOG_ISERIES_2 + b system_call_common + + STD_EXCEPTION_ISERIES( 0xd00, single_step, PACA_EXGEN) + STD_EXCEPTION_ISERIES( 0xe00, trap_0e, PACA_EXGEN) + STD_EXCEPTION_ISERIES( 0xf00, performance_monitor, PACA_EXGEN) + + .globl system_reset_iSeries +system_reset_iSeries: + mfspr r13,SPRN_SPRG3 /* Get paca address */ + mfmsr r24 + ori r24,r24,MSR_RI + mtmsrd r24 /* RI on */ + lhz r24,PACAPACAINDEX(r13) /* Get processor # */ + cmpwi 0,r24,0 /* Are we processor 0? */ + beq .__start_initialization_iSeries /* Start up the first processor */ + mfspr r4,SPRN_CTRLF + li r5,CTRL_RUNLATCH /* Turn off the run light */ + andc r4,r4,r5 + mtspr SPRN_CTRLT,r4 + +1: + HMT_LOW +#ifdef CONFIG_SMP + lbz r23,PACAPROCSTART(r13) /* Test if this processor + * should start */ + sync + LOADADDR(r3,current_set) + sldi r28,r24,3 /* get current_set[cpu#] */ + ldx r3,r3,r28 + addi r1,r3,THREAD_SIZE + subi r1,r1,STACK_FRAME_OVERHEAD + + cmpwi 0,r23,0 + beq iSeries_secondary_smp_loop /* Loop until told to go */ + bne .__secondary_start /* Loop until told to go */ +iSeries_secondary_smp_loop: + /* Let the Hypervisor know we are alive */ + /* 8002 is a call to HvCallCfg::getLps, a harmless Hypervisor function */ + lis r3,0x8002 + rldicr r3,r3,32,15 /* r0 = (r3 << 32) & 0xffff000000000000 */ +#else /* CONFIG_SMP */ + /* Yield the processor. This is required for non-SMP kernels + which are running on multi-threaded machines. */ + lis r3,0x8000 + rldicr r3,r3,32,15 /* r3 = (r3 << 32) & 0xffff000000000000 */ + addi r3,r3,18 /* r3 = 0x8000000000000012 which is "yield" */ + li r4,0 /* "yield timed" */ + li r5,-1 /* "yield forever" */ +#endif /* CONFIG_SMP */ + li r0,-1 /* r0=-1 indicates a Hypervisor call */ + sc /* Invoke the hypervisor via a system call */ + mfspr r13,SPRN_SPRG3 /* Put r13 back ???? */ + b 1b /* If SMP not configured, secondaries + * loop forever */ + + .globl decrementer_iSeries_masked +decrementer_iSeries_masked: + li r11,1 + stb r11,PACALPPACA+LPPACADECRINT(r13) + lwz r12,PACADEFAULTDECR(r13) + mtspr SPRN_DEC,r12 + /* fall through */ + + .globl hardware_interrupt_iSeries_masked +hardware_interrupt_iSeries_masked: + mtcrf 0x80,r9 /* Restore regs */ + ld r11,PACALPPACA+LPPACASRR0(r13) + ld r12,PACALPPACA+LPPACASRR1(r13) + mtspr SPRN_SRR0,r11 + mtspr SPRN_SRR1,r12 + ld r9,PACA_EXGEN+EX_R9(r13) + ld r10,PACA_EXGEN+EX_R10(r13) + ld r11,PACA_EXGEN+EX_R11(r13) + ld r12,PACA_EXGEN+EX_R12(r13) + ld r13,PACA_EXGEN+EX_R13(r13) + rfid + b . /* prevent speculative execution */ +#endif /* CONFIG_PPC_ISERIES */ + +/*** Common interrupt handlers ***/ + + STD_EXCEPTION_COMMON(0x100, system_reset, .system_reset_exception) + + /* + * Machine check is different because we use a different + * save area: PACA_EXMC instead of PACA_EXGEN. + */ + .align 7 + .globl machine_check_common +machine_check_common: + EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC) + DISABLE_INTS + bl .save_nvgprs + addi r3,r1,STACK_FRAME_OVERHEAD + bl .machine_check_exception + b .ret_from_except + + STD_EXCEPTION_COMMON_LITE(0x900, decrementer, .timer_interrupt) + STD_EXCEPTION_COMMON(0xa00, trap_0a, .unknown_exception) + STD_EXCEPTION_COMMON(0xb00, trap_0b, .unknown_exception) + STD_EXCEPTION_COMMON(0xd00, single_step, .single_step_exception) + STD_EXCEPTION_COMMON(0xe00, trap_0e, .unknown_exception) + STD_EXCEPTION_COMMON(0xf00, performance_monitor, .performance_monitor_exception) + STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, .instruction_breakpoint_exception) +#ifdef CONFIG_ALTIVEC + STD_EXCEPTION_COMMON(0x1700, altivec_assist, .altivec_assist_exception) +#else + STD_EXCEPTION_COMMON(0x1700, altivec_assist, .unknown_exception) +#endif + +/* + * Here we have detected that the kernel stack pointer is bad. + * R9 contains the saved CR, r13 points to the paca, + * r10 contains the (bad) kernel stack pointer, + * r11 and r12 contain the saved SRR0 and SRR1. + * We switch to using an emergency stack, save the registers there, + * and call kernel_bad_stack(), which panics. + */ +bad_stack: + ld r1,PACAEMERGSP(r13) + subi r1,r1,64+INT_FRAME_SIZE + std r9,_CCR(r1) + std r10,GPR1(r1) + std r11,_NIP(r1) + std r12,_MSR(r1) + mfspr r11,SPRN_DAR + mfspr r12,SPRN_DSISR + std r11,_DAR(r1) + std r12,_DSISR(r1) + mflr r10 + mfctr r11 + mfxer r12 + std r10,_LINK(r1) + std r11,_CTR(r1) + std r12,_XER(r1) + SAVE_GPR(0,r1) + SAVE_GPR(2,r1) + SAVE_4GPRS(3,r1) + SAVE_2GPRS(7,r1) + SAVE_10GPRS(12,r1) + SAVE_10GPRS(22,r1) + addi r11,r1,INT_FRAME_SIZE + std r11,0(r1) + li r12,0 + std r12,0(r11) + ld r2,PACATOC(r13) +1: addi r3,r1,STACK_FRAME_OVERHEAD + bl .kernel_bad_stack + b 1b + +/* + * Return from an exception with minimal checks. + * The caller is assumed to have done EXCEPTION_PROLOG_COMMON. + * If interrupts have been enabled, or anything has been + * done that might have changed the scheduling status of + * any task or sent any task a signal, you should use + * ret_from_except or ret_from_except_lite instead of this. + */ + .globl fast_exception_return +fast_exception_return: + ld r12,_MSR(r1) + ld r11,_NIP(r1) + andi. r3,r12,MSR_RI /* check if RI is set */ + beq- unrecov_fer + ld r3,_CCR(r1) + ld r4,_LINK(r1) + ld r5,_CTR(r1) + ld r6,_XER(r1) + mtcr r3 + mtlr r4 + mtctr r5 + mtxer r6 + REST_GPR(0, r1) + REST_8GPRS(2, r1) + + mfmsr r10 + clrrdi r10,r10,2 /* clear RI (LE is 0 already) */ + mtmsrd r10,1 + + mtspr SPRN_SRR1,r12 + mtspr SPRN_SRR0,r11 + REST_4GPRS(10, r1) + ld r1,GPR1(r1) + rfid + b . /* prevent speculative execution */ + +unrecov_fer: + bl .save_nvgprs +1: addi r3,r1,STACK_FRAME_OVERHEAD + bl .unrecoverable_exception + b 1b + +/* + * Here r13 points to the paca, r9 contains the saved CR, + * SRR0 and SRR1 are saved in r11 and r12, + * r9 - r13 are saved in paca->exgen. + */ + .align 7 + .globl data_access_common +data_access_common: + RUNLATCH_ON(r10) /* It wont fit in the 0x300 handler */ + mfspr r10,SPRN_DAR + std r10,PACA_EXGEN+EX_DAR(r13) + mfspr r10,SPRN_DSISR + stw r10,PACA_EXGEN+EX_DSISR(r13) + EXCEPTION_PROLOG_COMMON(0x300, PACA_EXGEN) + ld r3,PACA_EXGEN+EX_DAR(r13) + lwz r4,PACA_EXGEN+EX_DSISR(r13) + li r5,0x300 + b .do_hash_page /* Try to handle as hpte fault */ + + .align 7 + .globl instruction_access_common +instruction_access_common: + EXCEPTION_PROLOG_COMMON(0x400, PACA_EXGEN) + ld r3,_NIP(r1) + andis. r4,r12,0x5820 + li r5,0x400 + b .do_hash_page /* Try to handle as hpte fault */ + + .align 7 + .globl hardware_interrupt_common + .globl hardware_interrupt_entry +hardware_interrupt_common: + EXCEPTION_PROLOG_COMMON(0x500, PACA_EXGEN) +hardware_interrupt_entry: + DISABLE_INTS + addi r3,r1,STACK_FRAME_OVERHEAD + bl .do_IRQ + b .ret_from_except_lite + + .align 7 + .globl alignment_common +alignment_common: + mfspr r10,SPRN_DAR + std r10,PACA_EXGEN+EX_DAR(r13) + mfspr r10,SPRN_DSISR + stw r10,PACA_EXGEN+EX_DSISR(r13) + EXCEPTION_PROLOG_COMMON(0x600, PACA_EXGEN) + ld r3,PACA_EXGEN+EX_DAR(r13) + lwz r4,PACA_EXGEN+EX_DSISR(r13) + std r3,_DAR(r1) + std r4,_DSISR(r1) + bl .save_nvgprs + addi r3,r1,STACK_FRAME_OVERHEAD + ENABLE_INTS + bl .alignment_exception + b .ret_from_except + + .align 7 + .globl program_check_common +program_check_common: + EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN) + bl .save_nvgprs + addi r3,r1,STACK_FRAME_OVERHEAD + ENABLE_INTS + bl .program_check_exception + b .ret_from_except + + .align 7 + .globl fp_unavailable_common +fp_unavailable_common: + EXCEPTION_PROLOG_COMMON(0x800, PACA_EXGEN) + bne .load_up_fpu /* if from user, just load it up */ + bl .save_nvgprs + addi r3,r1,STACK_FRAME_OVERHEAD + ENABLE_INTS + bl .kernel_fp_unavailable_exception + BUG_OPCODE + + .align 7 + .globl altivec_unavailable_common +altivec_unavailable_common: + EXCEPTION_PROLOG_COMMON(0xf20, PACA_EXGEN) +#ifdef CONFIG_ALTIVEC +BEGIN_FTR_SECTION + bne .load_up_altivec /* if from user, just load it up */ +END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) +#endif + bl .save_nvgprs + addi r3,r1,STACK_FRAME_OVERHEAD + ENABLE_INTS + bl .altivec_unavailable_exception + b .ret_from_except + +#ifdef CONFIG_ALTIVEC +/* + * load_up_altivec(unused, unused, tsk) + * Disable VMX for the task which had it previously, + * and save its vector registers in its thread_struct. + * Enables the VMX for use in the kernel on return. + * On SMP we know the VMX is free, since we give it up every + * switch (ie, no lazy save of the vector registers). + * On entry: r13 == 'current' && last_task_used_altivec != 'current' + */ +_STATIC(load_up_altivec) + mfmsr r5 /* grab the current MSR */ + oris r5,r5,MSR_VEC@h + mtmsrd r5 /* enable use of VMX now */ + isync + +/* + * For SMP, we don't do lazy VMX switching because it just gets too + * horrendously complex, especially when a task switches from one CPU + * to another. Instead we call giveup_altvec in switch_to. + * VRSAVE isn't dealt with here, that is done in the normal context + * switch code. Note that we could rely on vrsave value to eventually + * avoid saving all of the VREGs here... + */ +#ifndef CONFIG_SMP + ld r3,last_task_used_altivec@got(r2) + ld r4,0(r3) + cmpdi 0,r4,0 + beq 1f + /* Save VMX state to last_task_used_altivec's THREAD struct */ + addi r4,r4,THREAD + SAVE_32VRS(0,r5,r4) + mfvscr vr0 + li r10,THREAD_VSCR + stvx vr0,r10,r4 + /* Disable VMX for last_task_used_altivec */ + ld r5,PT_REGS(r4) + ld r4,_MSR-STACK_FRAME_OVERHEAD(r5) + lis r6,MSR_VEC@h + andc r4,r4,r6 + std r4,_MSR-STACK_FRAME_OVERHEAD(r5) +1: +#endif /* CONFIG_SMP */ + /* Hack: if we get an altivec unavailable trap with VRSAVE + * set to all zeros, we assume this is a broken application + * that fails to set it properly, and thus we switch it to + * all 1's + */ + mfspr r4,SPRN_VRSAVE + cmpdi 0,r4,0 + bne+ 1f + li r4,-1 + mtspr SPRN_VRSAVE,r4 +1: + /* enable use of VMX after return */ + ld r4,PACACURRENT(r13) + addi r5,r4,THREAD /* Get THREAD */ + oris r12,r12,MSR_VEC@h + std r12,_MSR(r1) + li r4,1 + li r10,THREAD_VSCR + stw r4,THREAD_USED_VR(r5) + lvx vr0,r10,r5 + mtvscr vr0 + REST_32VRS(0,r4,r5) +#ifndef CONFIG_SMP + /* Update last_task_used_math to 'current' */ + subi r4,r5,THREAD /* Back to 'current' */ + std r4,0(r3) +#endif /* CONFIG_SMP */ + /* restore registers and return */ + b fast_exception_return +#endif /* CONFIG_ALTIVEC */ + +/* + * Hash table stuff + */ + .align 7 +_GLOBAL(do_hash_page) + std r3,_DAR(r1) + std r4,_DSISR(r1) + + andis. r0,r4,0xa450 /* weird error? */ + bne- .handle_page_fault /* if not, try to insert a HPTE */ +BEGIN_FTR_SECTION + andis. r0,r4,0x0020 /* Is it a segment table fault? */ + bne- .do_ste_alloc /* If so handle it */ +END_FTR_SECTION_IFCLR(CPU_FTR_SLB) + + /* + * We need to set the _PAGE_USER bit if MSR_PR is set or if we are + * accessing a userspace segment (even from the kernel). We assume + * kernel addresses always have the high bit set. + */ + rlwinm r4,r4,32-25+9,31-9,31-9 /* DSISR_STORE -> _PAGE_RW */ + rotldi r0,r3,15 /* Move high bit into MSR_PR posn */ + orc r0,r12,r0 /* MSR_PR | ~high_bit */ + rlwimi r4,r0,32-13,30,30 /* becomes _PAGE_USER access bit */ + ori r4,r4,1 /* add _PAGE_PRESENT */ + rlwimi r4,r5,22+2,31-2,31-2 /* Set _PAGE_EXEC if trap is 0x400 */ + + /* + * On iSeries, we soft-disable interrupts here, then + * hard-enable interrupts so that the hash_page code can spin on + * the hash_table_lock without problems on a shared processor. + */ + DISABLE_INTS + + /* + * r3 contains the faulting address + * r4 contains the required access permissions + * r5 contains the trap number + * + * at return r3 = 0 for success + */ + bl .hash_page /* build HPTE if possible */ + cmpdi r3,0 /* see if hash_page succeeded */ + +#ifdef DO_SOFT_DISABLE + /* + * If we had interrupts soft-enabled at the point where the + * DSI/ISI occurred, and an interrupt came in during hash_page, + * handle it now. + * We jump to ret_from_except_lite rather than fast_exception_return + * because ret_from_except_lite will check for and handle pending + * interrupts if necessary. + */ + beq .ret_from_except_lite + /* For a hash failure, we don't bother re-enabling interrupts */ + ble- 12f + + /* + * hash_page couldn't handle it, set soft interrupt enable back + * to what it was before the trap. Note that .local_irq_restore + * handles any interrupts pending at this point. + */ + ld r3,SOFTE(r1) + bl .local_irq_restore + b 11f +#else + beq fast_exception_return /* Return from exception on success */ + ble- 12f /* Failure return from hash_page */ + + /* fall through */ +#endif + +/* Here we have a page fault that hash_page can't handle. */ +_GLOBAL(handle_page_fault) + ENABLE_INTS +11: ld r4,_DAR(r1) + ld r5,_DSISR(r1) + addi r3,r1,STACK_FRAME_OVERHEAD + bl .do_page_fault + cmpdi r3,0 + beq+ .ret_from_except_lite + bl .save_nvgprs + mr r5,r3 + addi r3,r1,STACK_FRAME_OVERHEAD + lwz r4,_DAR(r1) + bl .bad_page_fault + b .ret_from_except + +/* We have a page fault that hash_page could handle but HV refused + * the PTE insertion + */ +12: bl .save_nvgprs + addi r3,r1,STACK_FRAME_OVERHEAD + lwz r4,_DAR(r1) + bl .low_hash_fault + b .ret_from_except + + /* here we have a segment miss */ +_GLOBAL(do_ste_alloc) + bl .ste_allocate /* try to insert stab entry */ + cmpdi r3,0 + beq+ fast_exception_return + b .handle_page_fault + +/* + * r13 points to the PACA, r9 contains the saved CR, + * r11 and r12 contain the saved SRR0 and SRR1. + * r9 - r13 are saved in paca->exslb. + * We assume we aren't going to take any exceptions during this procedure. + * We assume (DAR >> 60) == 0xc. + */ + .align 7 +_GLOBAL(do_stab_bolted) + stw r9,PACA_EXSLB+EX_CCR(r13) /* save CR in exc. frame */ + std r11,PACA_EXSLB+EX_SRR0(r13) /* save SRR0 in exc. frame */ + + /* Hash to the primary group */ + ld r10,PACASTABVIRT(r13) + mfspr r11,SPRN_DAR + srdi r11,r11,28 + rldimi r10,r11,7,52 /* r10 = first ste of the group */ + + /* Calculate VSID */ + /* This is a kernel address, so protovsid = ESID */ + ASM_VSID_SCRAMBLE(r11, r9) + rldic r9,r11,12,16 /* r9 = vsid << 12 */ + + /* Search the primary group for a free entry */ +1: ld r11,0(r10) /* Test valid bit of the current ste */ + andi. r11,r11,0x80 + beq 2f + addi r10,r10,16 + andi. r11,r10,0x70 + bne 1b + + /* Stick for only searching the primary group for now. */ + /* At least for now, we use a very simple random castout scheme */ + /* Use the TB as a random number ; OR in 1 to avoid entry 0 */ + mftb r11 + rldic r11,r11,4,57 /* r11 = (r11 << 4) & 0x70 */ + ori r11,r11,0x10 + + /* r10 currently points to an ste one past the group of interest */ + /* make it point to the randomly selected entry */ + subi r10,r10,128 + or r10,r10,r11 /* r10 is the entry to invalidate */ + + isync /* mark the entry invalid */ + ld r11,0(r10) + rldicl r11,r11,56,1 /* clear the valid bit */ + rotldi r11,r11,8 + std r11,0(r10) + sync + + clrrdi r11,r11,28 /* Get the esid part of the ste */ + slbie r11 + +2: std r9,8(r10) /* Store the vsid part of the ste */ + eieio + + mfspr r11,SPRN_DAR /* Get the new esid */ + clrrdi r11,r11,28 /* Permits a full 32b of ESID */ + ori r11,r11,0x90 /* Turn on valid and kp */ + std r11,0(r10) /* Put new entry back into the stab */ + + sync + + /* All done -- return from exception. */ + lwz r9,PACA_EXSLB+EX_CCR(r13) /* get saved CR */ + ld r11,PACA_EXSLB+EX_SRR0(r13) /* get saved SRR0 */ + + andi. r10,r12,MSR_RI + beq- unrecov_slb + + mtcrf 0x80,r9 /* restore CR */ + + mfmsr r10 + clrrdi r10,r10,2 + mtmsrd r10,1 + + mtspr SPRN_SRR0,r11 + mtspr SPRN_SRR1,r12 + ld r9,PACA_EXSLB+EX_R9(r13) + ld r10,PACA_EXSLB+EX_R10(r13) + ld r11,PACA_EXSLB+EX_R11(r13) + ld r12,PACA_EXSLB+EX_R12(r13) + ld r13,PACA_EXSLB+EX_R13(r13) + rfid + b . /* prevent speculative execution */ + +/* + * r13 points to the PACA, r9 contains the saved CR, + * r11 and r12 contain the saved SRR0 and SRR1. + * r3 has the faulting address + * r9 - r13 are saved in paca->exslb. + * r3 is saved in paca->slb_r3 + * We assume we aren't going to take any exceptions during this procedure. + */ +_GLOBAL(do_slb_miss) + mflr r10 + + stw r9,PACA_EXSLB+EX_CCR(r13) /* save CR in exc. frame */ + std r10,PACA_EXSLB+EX_LR(r13) /* save LR */ + + bl .slb_allocate /* handle it */ + + /* All done -- return from exception. */ + + ld r10,PACA_EXSLB+EX_LR(r13) + ld r3,PACA_EXSLB+EX_R3(r13) + lwz r9,PACA_EXSLB+EX_CCR(r13) /* get saved CR */ +#ifdef CONFIG_PPC_ISERIES + ld r11,PACALPPACA+LPPACASRR0(r13) /* get SRR0 value */ +#endif /* CONFIG_PPC_ISERIES */ + + mtlr r10 + + andi. r10,r12,MSR_RI /* check for unrecoverable exception */ + beq- unrecov_slb + +.machine push +.machine "power4" + mtcrf 0x80,r9 + mtcrf 0x01,r9 /* slb_allocate uses cr0 and cr7 */ +.machine pop + +#ifdef CONFIG_PPC_ISERIES + mtspr SPRN_SRR0,r11 + mtspr SPRN_SRR1,r12 +#endif /* CONFIG_PPC_ISERIES */ + ld r9,PACA_EXSLB+EX_R9(r13) + ld r10,PACA_EXSLB+EX_R10(r13) + ld r11,PACA_EXSLB+EX_R11(r13) + ld r12,PACA_EXSLB+EX_R12(r13) + ld r13,PACA_EXSLB+EX_R13(r13) + rfid + b . /* prevent speculative execution */ + +unrecov_slb: + EXCEPTION_PROLOG_COMMON(0x4100, PACA_EXSLB) + DISABLE_INTS + bl .save_nvgprs +1: addi r3,r1,STACK_FRAME_OVERHEAD + bl .unrecoverable_exception + b 1b + +/* + * Space for CPU0's segment table. + * + * On iSeries, the hypervisor must fill in at least one entry before + * we get control (with relocate on). The address is give to the hv + * as a page number (see xLparMap in lpardata.c), so this must be at a + * fixed address (the linker can't compute (u64)&initial_stab >> + * PAGE_SHIFT). + */ + . = STAB0_PHYS_ADDR /* 0x6000 */ + .globl initial_stab +initial_stab: + .space 4096 + +/* + * Data area reserved for FWNMI option. + * This address (0x7000) is fixed by the RPA. + */ + .= 0x7000 + .globl fwnmi_data_area +fwnmi_data_area: + + /* iSeries does not use the FWNMI stuff, so it is safe to put + * this here, even if we later allow kernels that will boot on + * both pSeries and iSeries */ +#ifdef CONFIG_PPC_ISERIES + . = LPARMAP_PHYS +#include "lparmap.s" +/* + * This ".text" is here for old compilers that generate a trailing + * .note section when compiling .c files to .s + */ + .text +#endif /* CONFIG_PPC_ISERIES */ + + . = 0x8000 + +/* + * On pSeries, secondary processors spin in the following code. + * At entry, r3 = this processor's number (physical cpu id) + */ +_GLOBAL(pSeries_secondary_smp_init) + mr r24,r3 + + /* turn on 64-bit mode */ + bl .enable_64b_mode + isync + + /* Copy some CPU settings from CPU 0 */ + bl .__restore_cpu_setup + + /* Set up a paca value for this processor. Since we have the + * physical cpu id in r24, we need to search the pacas to find + * which logical id maps to our physical one. + */ + LOADADDR(r13, paca) /* Get base vaddr of paca array */ + li r5,0 /* logical cpu id */ +1: lhz r6,PACAHWCPUID(r13) /* Load HW procid from paca */ + cmpw r6,r24 /* Compare to our id */ + beq 2f + addi r13,r13,PACA_SIZE /* Loop to next PACA on miss */ + addi r5,r5,1 + cmpwi r5,NR_CPUS + blt 1b + + mr r3,r24 /* not found, copy phys to r3 */ + b .kexec_wait /* next kernel might do better */ + +2: mtspr SPRN_SPRG3,r13 /* Save vaddr of paca in SPRG3 */ + /* From now on, r24 is expected to be logical cpuid */ + mr r24,r5 +3: HMT_LOW + lbz r23,PACAPROCSTART(r13) /* Test if this processor should */ + /* start. */ + sync + + /* Create a temp kernel stack for use before relocation is on. */ + ld r1,PACAEMERGSP(r13) + subi r1,r1,STACK_FRAME_OVERHEAD + + cmpwi 0,r23,0 +#ifdef CONFIG_SMP + bne .__secondary_start +#endif + b 3b /* Loop until told to go */ + +#ifdef CONFIG_PPC_ISERIES +_STATIC(__start_initialization_iSeries) + /* Clear out the BSS */ + LOADADDR(r11,__bss_stop) + LOADADDR(r8,__bss_start) + sub r11,r11,r8 /* bss size */ + addi r11,r11,7 /* round up to an even double word */ + rldicl. r11,r11,61,3 /* shift right by 3 */ + beq 4f + addi r8,r8,-8 + li r0,0 + mtctr r11 /* zero this many doublewords */ +3: stdu r0,8(r8) + bdnz 3b +4: + LOADADDR(r1,init_thread_union) + addi r1,r1,THREAD_SIZE + li r0,0 + stdu r0,-STACK_FRAME_OVERHEAD(r1) + + LOADADDR(r3,cpu_specs) + LOADADDR(r4,cur_cpu_spec) + li r5,0 + bl .identify_cpu + + LOADADDR(r2,__toc_start) + addi r2,r2,0x4000 + addi r2,r2,0x4000 + + bl .iSeries_early_setup + bl .early_setup + + /* relocation is on at this point */ + + b .start_here_common +#endif /* CONFIG_PPC_ISERIES */ + +#ifdef CONFIG_PPC_MULTIPLATFORM + +_STATIC(__mmu_off) + mfmsr r3 + andi. r0,r3,MSR_IR|MSR_DR + beqlr + andc r3,r3,r0 + mtspr SPRN_SRR0,r4 + mtspr SPRN_SRR1,r3 + sync + rfid + b . /* prevent speculative execution */ + + +/* + * Here is our main kernel entry point. We support currently 2 kind of entries + * depending on the value of r5. + * + * r5 != NULL -> OF entry, we go to prom_init, "legacy" parameter content + * in r3...r7 + * + * r5 == NULL -> kexec style entry. r3 is a physical pointer to the + * DT block, r4 is a physical pointer to the kernel itself + * + */ +_GLOBAL(__start_initialization_multiplatform) + /* + * Are we booted from a PROM Of-type client-interface ? + */ + cmpldi cr0,r5,0 + bne .__boot_from_prom /* yes -> prom */ + + /* Save parameters */ + mr r31,r3 + mr r30,r4 + + /* Make sure we are running in 64 bits mode */ + bl .enable_64b_mode + + /* Setup some critical 970 SPRs before switching MMU off */ + bl .__970_cpu_preinit + + /* cpu # */ + li r24,0 + + /* Switch off MMU if not already */ + LOADADDR(r4, .__after_prom_start - KERNELBASE) + add r4,r4,r30 + bl .__mmu_off + b .__after_prom_start + +_STATIC(__boot_from_prom) + /* Save parameters */ + mr r31,r3 + mr r30,r4 + mr r29,r5 + mr r28,r6 + mr r27,r7 + + /* Make sure we are running in 64 bits mode */ + bl .enable_64b_mode + + /* put a relocation offset into r3 */ + bl .reloc_offset + + LOADADDR(r2,__toc_start) + addi r2,r2,0x4000 + addi r2,r2,0x4000 + + /* Relocate the TOC from a virt addr to a real addr */ + add r2,r2,r3 + + /* Restore parameters */ + mr r3,r31 + mr r4,r30 + mr r5,r29 + mr r6,r28 + mr r7,r27 + + /* Do all of the interaction with OF client interface */ + bl .prom_init + /* We never return */ + trap + +/* + * At this point, r3 contains the physical address we are running at, + * returned by prom_init() + */ +_STATIC(__after_prom_start) + +/* + * We need to run with __start at physical address 0. + * This will leave some code in the first 256B of + * real memory, which are reserved for software use. + * The remainder of the first page is loaded with the fixed + * interrupt vectors. The next two pages are filled with + * unknown exception placeholders. + * + * Note: This process overwrites the OF exception vectors. + * r26 == relocation offset + * r27 == KERNELBASE + */ + bl .reloc_offset + mr r26,r3 + SET_REG_TO_CONST(r27,KERNELBASE) + + li r3,0 /* target addr */ + + // XXX FIXME: Use phys returned by OF (r30) + add r4,r27,r26 /* source addr */ + /* current address of _start */ + /* i.e. where we are running */ + /* the source addr */ + + LOADADDR(r5,copy_to_here) /* # bytes of memory to copy */ + sub r5,r5,r27 + + li r6,0x100 /* Start offset, the first 0x100 */ + /* bytes were copied earlier. */ + + bl .copy_and_flush /* copy the first n bytes */ + /* this includes the code being */ + /* executed here. */ + + LOADADDR(r0, 4f) /* Jump to the copy of this code */ + mtctr r0 /* that we just made/relocated */ + bctr + +4: LOADADDR(r5,klimit) + add r5,r5,r26 + ld r5,0(r5) /* get the value of klimit */ + sub r5,r5,r27 + bl .copy_and_flush /* copy the rest */ + b .start_here_multiplatform + +#endif /* CONFIG_PPC_MULTIPLATFORM */ + +/* + * Copy routine used to copy the kernel to start at physical address 0 + * and flush and invalidate the caches as needed. + * r3 = dest addr, r4 = source addr, r5 = copy limit, r6 = start offset + * on exit, r3, r4, r5 are unchanged, r6 is updated to be >= r5. + * + * Note: this routine *only* clobbers r0, r6 and lr + */ +_GLOBAL(copy_and_flush) + addi r5,r5,-8 + addi r6,r6,-8 +4: li r0,16 /* Use the least common */ + /* denominator cache line */ + /* size. This results in */ + /* extra cache line flushes */ + /* but operation is correct. */ + /* Can't get cache line size */ + /* from NACA as it is being */ + /* moved too. */ + + mtctr r0 /* put # words/line in ctr */ +3: addi r6,r6,8 /* copy a cache line */ + ldx r0,r6,r4 + stdx r0,r6,r3 + bdnz 3b + dcbst r6,r3 /* write it to memory */ + sync + icbi r6,r3 /* flush the icache line */ + cmpld 0,r6,r5 + blt 4b + sync + addi r5,r5,8 + addi r6,r6,8 + blr + +.align 8 +copy_to_here: + +#ifdef CONFIG_SMP +#ifdef CONFIG_PPC_PMAC +/* + * On PowerMac, secondary processors starts from the reset vector, which + * is temporarily turned into a call to one of the functions below. + */ + .section ".text"; + .align 2 ; + + .globl __secondary_start_pmac_0 +__secondary_start_pmac_0: + /* NB the entries for cpus 0, 1, 2 must each occupy 8 bytes. */ + li r24,0 + b 1f + li r24,1 + b 1f + li r24,2 + b 1f + li r24,3 +1: + +_GLOBAL(pmac_secondary_start) + /* turn on 64-bit mode */ + bl .enable_64b_mode + isync + + /* Copy some CPU settings from CPU 0 */ + bl .__restore_cpu_setup + + /* pSeries do that early though I don't think we really need it */ + mfmsr r3 + ori r3,r3,MSR_RI + mtmsrd r3 /* RI on */ + + /* Set up a paca value for this processor. */ + LOADADDR(r4, paca) /* Get base vaddr of paca array */ + mulli r13,r24,PACA_SIZE /* Calculate vaddr of right paca */ + add r13,r13,r4 /* for this processor. */ + mtspr SPRN_SPRG3,r13 /* Save vaddr of paca in SPRG3 */ + + /* Create a temp kernel stack for use before relocation is on. */ + ld r1,PACAEMERGSP(r13) + subi r1,r1,STACK_FRAME_OVERHEAD + + b .__secondary_start + +#endif /* CONFIG_PPC_PMAC */ + +/* + * This function is called after the master CPU has released the + * secondary processors. The execution environment is relocation off. + * The paca for this processor has the following fields initialized at + * this point: + * 1. Processor number + * 2. Segment table pointer (virtual address) + * On entry the following are set: + * r1 = stack pointer. vaddr for iSeries, raddr (temp stack) for pSeries + * r24 = cpu# (in Linux terms) + * r13 = paca virtual address + * SPRG3 = paca virtual address + */ +_GLOBAL(__secondary_start) + + HMT_MEDIUM /* Set thread priority to MEDIUM */ + + 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 */ + bl .stab_initialize + + /* Initialize the kernel stack. Just a repeat for iSeries. */ + LOADADDR(r3,current_set) + sldi r28,r24,3 /* get current_set[cpu#] */ + ldx r1,r3,r28 + 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 + li r7,0 + mtlr r7 + + /* enable MMU and jump to start_secondary */ + LOADADDR(r3,.start_secondary_prolog) + SET_REG_TO_CONST(r4, MSR_KERNEL) +#ifdef DO_SOFT_DISABLE + ori r4,r4,MSR_EE +#endif + mtspr SPRN_SRR0,r3 + mtspr SPRN_SRR1,r4 + rfid + b . /* prevent speculative execution */ + +/* + * Running with relocation on at this point. All we want to do is + * zero the stack back-chain pointer before going into C code. + */ +_GLOBAL(start_secondary_prolog) + li r3,0 + std r3,0(r1) /* Zero the stack frame pointer */ + bl .start_secondary +#endif + +/* + * This subroutine clobbers r11 and r12 + */ +_GLOBAL(enable_64b_mode) + mfmsr r11 /* grab the current MSR */ + li r12,1 + rldicr r12,r12,MSR_SF_LG,(63-MSR_SF_LG) + or r11,r11,r12 + li r12,1 + rldicr r12,r12,MSR_ISF_LG,(63-MSR_ISF_LG) + or r11,r11,r12 + mtmsrd r11 + isync + blr + +#ifdef CONFIG_PPC_MULTIPLATFORM +/* + * This is where the main kernel code starts. + */ +_STATIC(start_here_multiplatform) + /* get a new offset, now that the kernel has moved. */ + bl .reloc_offset + mr r26,r3 + + /* Clear out the BSS. It may have been done in prom_init, + * already but that's irrelevant since prom_init will soon + * be detached from the kernel completely. Besides, we need + * to clear it now for kexec-style entry. + */ + LOADADDR(r11,__bss_stop) + LOADADDR(r8,__bss_start) + sub r11,r11,r8 /* bss size */ + addi r11,r11,7 /* round up to an even double word */ + rldicl. r11,r11,61,3 /* shift right by 3 */ + beq 4f + addi r8,r8,-8 + li r0,0 + mtctr r11 /* zero this many doublewords */ +3: stdu r0,8(r8) + bdnz 3b +4: + + mfmsr r6 + ori r6,r6,MSR_RI + mtmsrd r6 /* RI on */ + +#ifdef CONFIG_HMT + /* Start up the second thread on cpu 0 */ + mfspr r3,SPRN_PVR + srwi r3,r3,16 + cmpwi r3,0x34 /* Pulsar */ + beq 90f + cmpwi r3,0x36 /* Icestar */ + beq 90f + cmpwi r3,0x37 /* SStar */ + beq 90f + b 91f /* HMT not supported */ +90: li r3,0 + bl .hmt_start_secondary +91: +#endif + + /* The following gets the stack and TOC set up with the regs */ + /* pointing to the real addr of the kernel stack. This is */ + /* all done to support the C function call below which sets */ + /* up the htab. This is done because we have relocated the */ + /* kernel but are still running in real mode. */ + + LOADADDR(r3,init_thread_union) + add r3,r3,r26 + + /* set up a stack pointer (physical address) */ + addi r1,r3,THREAD_SIZE + li r0,0 + stdu r0,-STACK_FRAME_OVERHEAD(r1) + + /* set up the TOC (physical address) */ + LOADADDR(r2,__toc_start) + addi r2,r2,0x4000 + addi r2,r2,0x4000 + add r2,r2,r26 + + LOADADDR(r3,cpu_specs) + add r3,r3,r26 + LOADADDR(r4,cur_cpu_spec) + add r4,r4,r26 + mr r5,r26 + bl .identify_cpu + + /* Save some low level config HIDs of CPU0 to be copied to + * other CPUs later on, or used for suspend/resume + */ + bl .__save_cpu_setup + sync + + /* Setup a valid physical PACA pointer in SPRG3 for early_setup + * note that boot_cpuid can always be 0 nowadays since there is + * nowhere it can be initialized differently before we reach this + * code + */ + LOADADDR(r27, boot_cpuid) + add r27,r27,r26 + lwz r27,0(r27) + + LOADADDR(r24, paca) /* Get base vaddr of paca array */ + mulli r13,r27,PACA_SIZE /* Calculate vaddr of right paca */ + add r13,r13,r24 /* for this processor. */ + add r13,r13,r26 /* convert to physical addr */ + mtspr SPRN_SPRG3,r13 /* PPPBBB: Temp... -Peter */ + + /* Do very early kernel initializations, including initial hash table, + * stab and slb setup before we turn on relocation. */ + + /* Restore parameters passed from prom_init/kexec */ + 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 + mtspr SPRN_SRR1,r4 + rfid + b . /* prevent speculative execution */ +#endif /* CONFIG_PPC_MULTIPLATFORM */ + + /* This is where all platforms converge execution */ +_STATIC(start_here_common) + /* relocation is on at this point */ + + /* The following code sets up the SP and TOC now that we are */ + /* running with translation enabled. */ + + LOADADDR(r3,init_thread_union) + + /* set up the stack */ + addi r1,r3,THREAD_SIZE + li r0,0 + stdu r0,-STACK_FRAME_OVERHEAD(r1) + + /* Apply the CPUs-specific fixups (nop out sections not relevant + * to this CPU + */ + li r3,0 + bl .do_cpu_ftr_fixups + + LOADADDR(r26, boot_cpuid) + lwz r26,0(r26) + + LOADADDR(r24, paca) /* Get base vaddr of paca array */ + mulli r13,r26,PACA_SIZE /* Calculate vaddr of right paca */ + add r13,r13,r24 /* for this processor. */ + mtspr SPRN_SPRG3,r13 + + /* ptr to current */ + LOADADDR(r4,init_task) + std r4,PACACURRENT(r13) + + /* Load the TOC */ + ld r2,PACATOC(r13) + std r1,PACAKSAVE(r13) + + bl .setup_system + + /* Load up the kernel context */ +5: +#ifdef DO_SOFT_DISABLE + li r5,0 + stb r5,PACAPROCENABLED(r13) /* Soft Disabled */ + mfmsr r5 + ori r5,r5,MSR_EE /* Hard Enabled */ + mtmsrd r5 +#endif + + bl .start_kernel + +_GLOBAL(hmt_init) +#ifdef CONFIG_HMT + LOADADDR(r5, hmt_thread_data) + mfspr r7,SPRN_PVR + srwi r7,r7,16 + cmpwi r7,0x34 /* Pulsar */ + beq 90f + cmpwi r7,0x36 /* Icestar */ + beq 91f + cmpwi r7,0x37 /* SStar */ + beq 91f + b 101f +90: mfspr r6,SPRN_PIR + andi. r6,r6,0x1f + b 92f +91: mfspr r6,SPRN_PIR + andi. r6,r6,0x3ff +92: sldi r4,r24,3 + stwx r6,r5,r4 + bl .hmt_start_secondary + b 101f + +__hmt_secondary_hold: + LOADADDR(r5, hmt_thread_data) + clrldi r5,r5,4 + li r7,0 + mfspr r6,SPRN_PIR + mfspr r8,SPRN_PVR + srwi r8,r8,16 + cmpwi r8,0x34 + bne 93f + andi. r6,r6,0x1f + b 103f +93: andi. r6,r6,0x3f + +103: lwzx r8,r5,r7 + cmpw r8,r6 + beq 104f + addi r7,r7,8 + b 103b + +104: addi r7,r7,4 + lwzx r9,r5,r7 + mr r24,r9 +101: +#endif + mr r3,r24 + b .pSeries_secondary_smp_init + +#ifdef CONFIG_HMT +_GLOBAL(hmt_start_secondary) + LOADADDR(r4,__hmt_secondary_hold) + clrldi r4,r4,4 + mtspr SPRN_NIADORM, r4 + mfspr r4, SPRN_MSRDORM + li r5, -65 + and r4, r4, r5 + mtspr SPRN_MSRDORM, r4 + lis r4,0xffef + ori r4,r4,0x7403 + mtspr SPRN_TSC, r4 + li r4,0x1f4 + mtspr SPRN_TST, r4 + mfspr r4, SPRN_HID0 + ori r4, r4, 0x1 + mtspr SPRN_HID0, r4 + mfspr r4, SPRN_CTRLF + oris r4, r4, 0x40 + mtspr SPRN_CTRLT, r4 + blr +#endif + +#if defined(CONFIG_KEXEC) || defined(CONFIG_SMP) +_GLOBAL(smp_release_cpus) + /* All secondary cpus are spinning on a common + * spinloop, release them all now so they can start + * to spin on their individual paca spinloops. + * For non SMP kernels, the secondary cpus never + * get out of the common spinloop. + * XXX This does nothing useful on iSeries, secondaries are + * already waiting on their paca. + */ + li r3,1 + LOADADDR(r5,__secondary_hold_spinloop) + std r3,0(r5) + sync + blr +#endif /* CONFIG_SMP */ + + +/* + * We put a few things here that have to be page-aligned. + * This stuff goes at the beginning of the bss, which is page-aligned. + */ + .section ".bss" + + .align PAGE_SHIFT + + .globl empty_zero_page +empty_zero_page: + .space PAGE_SIZE + + .globl swapper_pg_dir +swapper_pg_dir: + .space PAGE_SIZE + +/* + * This space gets a copy of optional info passed to us by the bootstrap + * Used to pass parameters into the kernel like root=/dev/sda1, etc. + */ + .globl cmd_line +cmd_line: + .space COMMAND_LINE_SIZE diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S new file mode 100644 index 000000000000..bc6d1ac55235 --- /dev/null +++ b/arch/powerpc/kernel/head_8xx.S @@ -0,0 +1,860 @@ +/* + * arch/ppc/kernel/except_8xx.S + * + * PowerPC version + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) + * Rewritten by Cort Dougan (cort@cs.nmt.edu) for PReP + * Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu> + * Low-level exception handlers and MMU support + * rewritten by Paul Mackerras. + * Copyright (C) 1996 Paul Mackerras. + * MPC8xx modifications by Dan Malek + * Copyright (C) 1997 Dan Malek (dmalek@jlc.net). + * + * This file contains low-level support and setup for PowerPC 8xx + * embedded processors, including trap and interrupt dispatch. + * + * 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/mmu.h> +#include <asm/cache.h> +#include <asm/pgtable.h> +#include <asm/cputable.h> +#include <asm/thread_info.h> +#include <asm/ppc_asm.h> +#include <asm/asm-offsets.h> + +/* Macro to make the code more readable. */ +#ifdef CONFIG_8xx_CPU6 +#define DO_8xx_CPU6(val, reg) \ + li reg, val; \ + stw reg, 12(r0); \ + lwz reg, 12(r0); +#else +#define DO_8xx_CPU6(val, reg) +#endif + .text + .globl _stext +_stext: + .text + .globl _start +_start: + +/* MPC8xx + * This port was done on an MBX board with an 860. Right now I only + * support an ELF compressed (zImage) boot from EPPC-Bug because the + * code there loads up some registers before calling us: + * r3: ptr to board info data + * r4: initrd_start or if no initrd then 0 + * r5: initrd_end - unused if r4 is 0 + * r6: Start of command line string + * r7: End of command line string + * + * I decided to use conditional compilation instead of checking PVR and + * adding more processor specific branches around code I don't need. + * Since this is an embedded processor, I also appreciate any memory + * savings I can get. + * + * The MPC8xx does not have any BATs, but it supports large page sizes. + * We first initialize the MMU to support 8M byte pages, then load one + * entry into each of the instruction and data TLBs to map the first + * 8M 1:1. I also mapped an additional I/O space 1:1 so we can get to + * the "internal" processor registers before MMU_init is called. + * + * The TLB code currently contains a major hack. Since I use the condition + * code register, I have to save and restore it. I am out of registers, so + * I just store it in memory location 0 (the TLB handlers are not reentrant). + * To avoid making any decisions, I need to use the "segment" valid bit + * in the first level table, but that would require many changes to the + * Linux page directory/table functions that I don't want to do right now. + * + * I used to use SPRG2 for a temporary register in the TLB handler, but it + * has since been put to other uses. I now use a hack to save a register + * and the CCR at memory location 0.....Someday I'll fix this..... + * -- Dan + */ + .globl __start +__start: + mr r31,r3 /* save parameters */ + mr r30,r4 + mr r29,r5 + mr r28,r6 + mr r27,r7 + + /* We have to turn on the MMU right away so we get cache modes + * set correctly. + */ + bl initial_mmu + +/* We now have the lower 8 Meg mapped into TLB entries, and the caches + * ready to work. + */ + +turn_on_mmu: + mfmsr r0 + ori r0,r0,MSR_DR|MSR_IR + mtspr SPRN_SRR1,r0 + lis r0,start_here@h + ori r0,r0,start_here@l + mtspr SPRN_SRR0,r0 + SYNC + rfi /* enables MMU */ + +/* + * Exception entry code. This code runs with address translation + * turned off, i.e. using physical addresses. + * We assume sprg3 has the physical address of the current + * task's thread_struct. + */ +#define EXCEPTION_PROLOG \ + mtspr SPRN_SPRG0,r10; \ + mtspr SPRN_SPRG1,r11; \ + mfcr r10; \ + EXCEPTION_PROLOG_1; \ + EXCEPTION_PROLOG_2 + +#define EXCEPTION_PROLOG_1 \ + mfspr r11,SPRN_SRR1; /* check whether user or kernel */ \ + andi. r11,r11,MSR_PR; \ + tophys(r11,r1); /* use tophys(r1) if kernel */ \ + beq 1f; \ + mfspr r11,SPRN_SPRG3; \ + lwz r11,THREAD_INFO-THREAD(r11); \ + addi r11,r11,THREAD_SIZE; \ + tophys(r11,r11); \ +1: subi r11,r11,INT_FRAME_SIZE /* alloc exc. frame */ + + +#define EXCEPTION_PROLOG_2 \ + CLR_TOP32(r11); \ + stw r10,_CCR(r11); /* save registers */ \ + stw r12,GPR12(r11); \ + stw r9,GPR9(r11); \ + mfspr r10,SPRN_SPRG0; \ + stw r10,GPR10(r11); \ + mfspr r12,SPRN_SPRG1; \ + stw r12,GPR11(r11); \ + mflr r10; \ + stw r10,_LINK(r11); \ + mfspr r12,SPRN_SRR0; \ + mfspr r9,SPRN_SRR1; \ + stw r1,GPR1(r11); \ + stw r1,0(r11); \ + tovirt(r1,r11); /* set new kernel sp */ \ + li r10,MSR_KERNEL & ~(MSR_IR|MSR_DR); /* can take exceptions */ \ + MTMSRD(r10); /* (except for mach check in rtas) */ \ + stw r0,GPR0(r11); \ + SAVE_4GPRS(3, r11); \ + SAVE_2GPRS(7, r11) + +/* + * Note: code which follows this uses cr0.eq (set if from kernel), + * r11, r12 (SRR0), and r9 (SRR1). + * + * Note2: once we have set r1 we are in a position to take exceptions + * again, and we could thus set MSR:RI at that point. + */ + +/* + * Exception vectors. + */ +#define EXCEPTION(n, label, hdlr, xfer) \ + . = n; \ +label: \ + EXCEPTION_PROLOG; \ + addi r3,r1,STACK_FRAME_OVERHEAD; \ + xfer(n, hdlr) + +#define EXC_XFER_TEMPLATE(n, hdlr, trap, copyee, tfer, ret) \ + li r10,trap; \ + stw r10,_TRAP(r11); \ + li r10,MSR_KERNEL; \ + copyee(r10, r9); \ + bl tfer; \ +i##n: \ + .long hdlr; \ + .long ret + +#define COPY_EE(d, s) rlwimi d,s,0,16,16 +#define NOCOPY(d, s) + +#define EXC_XFER_STD(n, hdlr) \ + EXC_XFER_TEMPLATE(n, hdlr, n, NOCOPY, transfer_to_handler_full, \ + ret_from_except_full) + +#define EXC_XFER_LITE(n, hdlr) \ + EXC_XFER_TEMPLATE(n, hdlr, n+1, NOCOPY, transfer_to_handler, \ + ret_from_except) + +#define EXC_XFER_EE(n, hdlr) \ + EXC_XFER_TEMPLATE(n, hdlr, n, COPY_EE, transfer_to_handler_full, \ + ret_from_except_full) + +#define EXC_XFER_EE_LITE(n, hdlr) \ + EXC_XFER_TEMPLATE(n, hdlr, n+1, COPY_EE, transfer_to_handler, \ + ret_from_except) + +/* System reset */ + EXCEPTION(0x100, Reset, unknown_exception, EXC_XFER_STD) + +/* Machine check */ + . = 0x200 +MachineCheck: + EXCEPTION_PROLOG + mfspr r4,SPRN_DAR + stw r4,_DAR(r11) + mfspr r5,SPRN_DSISR + stw r5,_DSISR(r11) + addi r3,r1,STACK_FRAME_OVERHEAD + EXC_XFER_STD(0x200, machine_check_exception) + +/* Data access exception. + * This is "never generated" by the MPC8xx. We jump to it for other + * translation errors. + */ + . = 0x300 +DataAccess: + EXCEPTION_PROLOG + mfspr r10,SPRN_DSISR + stw r10,_DSISR(r11) + mr r5,r10 + mfspr r4,SPRN_DAR + EXC_XFER_EE_LITE(0x300, handle_page_fault) + +/* Instruction access exception. + * This is "never generated" by the MPC8xx. We jump to it for other + * translation errors. + */ + . = 0x400 +InstructionAccess: + EXCEPTION_PROLOG + mr r4,r12 + mr r5,r9 + EXC_XFER_EE_LITE(0x400, handle_page_fault) + +/* External interrupt */ + EXCEPTION(0x500, HardwareInterrupt, do_IRQ, EXC_XFER_LITE) + +/* Alignment exception */ + . = 0x600 +Alignment: + EXCEPTION_PROLOG + mfspr r4,SPRN_DAR + stw r4,_DAR(r11) + mfspr r5,SPRN_DSISR + stw r5,_DSISR(r11) + addi r3,r1,STACK_FRAME_OVERHEAD + EXC_XFER_EE(0x600, alignment_exception) + +/* Program check exception */ + EXCEPTION(0x700, ProgramCheck, program_check_exception, EXC_XFER_STD) + +/* No FPU on MPC8xx. This exception is not supposed to happen. +*/ + EXCEPTION(0x800, FPUnavailable, unknown_exception, EXC_XFER_STD) + +/* Decrementer */ + EXCEPTION(0x900, Decrementer, timer_interrupt, EXC_XFER_LITE) + + EXCEPTION(0xa00, Trap_0a, unknown_exception, EXC_XFER_EE) + EXCEPTION(0xb00, Trap_0b, unknown_exception, EXC_XFER_EE) + +/* System call */ + . = 0xc00 +SystemCall: + EXCEPTION_PROLOG + EXC_XFER_EE_LITE(0xc00, DoSyscall) + +/* Single step - not used on 601 */ + EXCEPTION(0xd00, SingleStep, single_step_exception, EXC_XFER_STD) + EXCEPTION(0xe00, Trap_0e, unknown_exception, EXC_XFER_EE) + EXCEPTION(0xf00, Trap_0f, unknown_exception, EXC_XFER_EE) + +/* On the MPC8xx, this is a software emulation interrupt. It occurs + * for all unimplemented and illegal instructions. + */ + EXCEPTION(0x1000, SoftEmu, SoftwareEmulation, EXC_XFER_STD) + + . = 0x1100 +/* + * For the MPC8xx, this is a software tablewalk to load the instruction + * TLB. It is modelled after the example in the Motorola manual. The task + * switch loads the M_TWB register with the pointer to the first level table. + * If we discover there is no second level table (value is zero) or if there + * is an invalid pte, we load that into the TLB, which causes another fault + * into the TLB Error interrupt where we can handle such problems. + * We have to use the MD_xxx registers for the tablewalk because the + * equivalent MI_xxx registers only perform the attribute functions. + */ +InstructionTLBMiss: +#ifdef CONFIG_8xx_CPU6 + stw r3, 8(r0) +#endif + DO_8xx_CPU6(0x3f80, r3) + mtspr SPRN_M_TW, r10 /* Save a couple of working registers */ + mfcr r10 + stw r10, 0(r0) + stw r11, 4(r0) + mfspr r10, SPRN_SRR0 /* Get effective address of fault */ + DO_8xx_CPU6(0x3780, r3) + mtspr SPRN_MD_EPN, r10 /* Have to use MD_EPN for walk, MI_EPN can't */ + mfspr r10, SPRN_M_TWB /* Get level 1 table entry address */ + + /* If we are faulting a kernel address, we have to use the + * kernel page tables. + */ + andi. r11, r10, 0x0800 /* Address >= 0x80000000 */ + beq 3f + lis r11, swapper_pg_dir@h + ori r11, r11, swapper_pg_dir@l + rlwimi r10, r11, 0, 2, 19 +3: + lwz r11, 0(r10) /* Get the level 1 entry */ + rlwinm. r10, r11,0,0,19 /* Extract page descriptor page address */ + beq 2f /* If zero, don't try to find a pte */ + + /* We have a pte table, so load the MI_TWC with the attributes + * for this "segment." + */ + ori r11,r11,1 /* Set valid bit */ + DO_8xx_CPU6(0x2b80, r3) + mtspr SPRN_MI_TWC, r11 /* Set segment attributes */ + DO_8xx_CPU6(0x3b80, r3) + mtspr SPRN_MD_TWC, r11 /* Load pte table base address */ + mfspr r11, SPRN_MD_TWC /* ....and get the pte address */ + lwz r10, 0(r11) /* Get the pte */ + + ori r10, r10, _PAGE_ACCESSED + stw r10, 0(r11) + + /* The Linux PTE won't go exactly into the MMU TLB. + * Software indicator bits 21, 22 and 28 must be clear. + * Software indicator bits 24, 25, 26, and 27 must be + * set. All other Linux PTE bits control the behavior + * of the MMU. + */ +2: li r11, 0x00f0 + rlwimi r10, r11, 0, 24, 28 /* Set 24-27, clear 28 */ + DO_8xx_CPU6(0x2d80, r3) + mtspr SPRN_MI_RPN, r10 /* Update TLB entry */ + + mfspr r10, SPRN_M_TW /* Restore registers */ + lwz r11, 0(r0) + mtcr r11 + lwz r11, 4(r0) +#ifdef CONFIG_8xx_CPU6 + lwz r3, 8(r0) +#endif + rfi + + . = 0x1200 +DataStoreTLBMiss: +#ifdef CONFIG_8xx_CPU6 + stw r3, 8(r0) +#endif + DO_8xx_CPU6(0x3f80, r3) + mtspr SPRN_M_TW, r10 /* Save a couple of working registers */ + mfcr r10 + stw r10, 0(r0) + stw r11, 4(r0) + mfspr r10, SPRN_M_TWB /* Get level 1 table entry address */ + + /* If we are faulting a kernel address, we have to use the + * kernel page tables. + */ + andi. r11, r10, 0x0800 + beq 3f + lis r11, swapper_pg_dir@h + ori r11, r11, swapper_pg_dir@l + rlwimi r10, r11, 0, 2, 19 +3: + lwz r11, 0(r10) /* Get the level 1 entry */ + rlwinm. r10, r11,0,0,19 /* Extract page descriptor page address */ + beq 2f /* If zero, don't try to find a pte */ + + /* We have a pte table, so load fetch the pte from the table. + */ + ori r11, r11, 1 /* Set valid bit in physical L2 page */ + DO_8xx_CPU6(0x3b80, r3) + mtspr SPRN_MD_TWC, r11 /* Load pte table base address */ + mfspr r10, SPRN_MD_TWC /* ....and get the pte address */ + lwz r10, 0(r10) /* Get the pte */ + + /* Insert the Guarded flag into the TWC from the Linux PTE. + * It is bit 27 of both the Linux PTE and the TWC (at least + * I got that right :-). It will be better when we can put + * this into the Linux pgd/pmd and load it in the operation + * above. + */ + rlwimi r11, r10, 0, 27, 27 + DO_8xx_CPU6(0x3b80, r3) + mtspr SPRN_MD_TWC, r11 + + mfspr r11, SPRN_MD_TWC /* get the pte address again */ + ori r10, r10, _PAGE_ACCESSED + stw r10, 0(r11) + + /* The Linux PTE won't go exactly into the MMU TLB. + * Software indicator bits 21, 22 and 28 must be clear. + * Software indicator bits 24, 25, 26, and 27 must be + * set. All other Linux PTE bits control the behavior + * of the MMU. + */ +2: li r11, 0x00f0 + rlwimi r10, r11, 0, 24, 28 /* Set 24-27, clear 28 */ + DO_8xx_CPU6(0x3d80, r3) + mtspr SPRN_MD_RPN, r10 /* Update TLB entry */ + + mfspr r10, SPRN_M_TW /* Restore registers */ + lwz r11, 0(r0) + mtcr r11 + lwz r11, 4(r0) +#ifdef CONFIG_8xx_CPU6 + lwz r3, 8(r0) +#endif + rfi + +/* This is an instruction TLB error on the MPC8xx. This could be due + * to many reasons, such as executing guarded memory or illegal instruction + * addresses. There is nothing to do but handle a big time error fault. + */ + . = 0x1300 +InstructionTLBError: + b InstructionAccess + +/* This is the data TLB error on the MPC8xx. This could be due to + * many reasons, including a dirty update to a pte. We can catch that + * one here, but anything else is an error. First, we track down the + * Linux pte. If it is valid, write access is allowed, but the + * page dirty bit is not set, we will set it and reload the TLB. For + * any other case, we bail out to a higher level function that can + * handle it. + */ + . = 0x1400 +DataTLBError: +#ifdef CONFIG_8xx_CPU6 + stw r3, 8(r0) +#endif + DO_8xx_CPU6(0x3f80, r3) + mtspr SPRN_M_TW, r10 /* Save a couple of working registers */ + mfcr r10 + stw r10, 0(r0) + stw r11, 4(r0) + + /* First, make sure this was a store operation. + */ + mfspr r10, SPRN_DSISR + andis. r11, r10, 0x0200 /* If set, indicates store op */ + beq 2f + + /* The EA of a data TLB miss is automatically stored in the MD_EPN + * register. The EA of a data TLB error is automatically stored in + * the DAR, but not the MD_EPN register. We must copy the 20 most + * significant bits of the EA from the DAR to MD_EPN before we + * start walking the page tables. We also need to copy the CASID + * value from the M_CASID register. + * Addendum: The EA of a data TLB error is _supposed_ to be stored + * in DAR, but it seems that this doesn't happen in some cases, such + * as when the error is due to a dcbi instruction to a page with a + * TLB that doesn't have the changed bit set. In such cases, there + * does not appear to be any way to recover the EA of the error + * since it is neither in DAR nor MD_EPN. As a workaround, the + * _PAGE_HWWRITE bit is set for all kernel data pages when the PTEs + * are initialized in mapin_ram(). This will avoid the problem, + * assuming we only use the dcbi instruction on kernel addresses. + */ + mfspr r10, SPRN_DAR + rlwinm r11, r10, 0, 0, 19 + ori r11, r11, MD_EVALID + mfspr r10, SPRN_M_CASID + rlwimi r11, r10, 0, 28, 31 + DO_8xx_CPU6(0x3780, r3) + mtspr SPRN_MD_EPN, r11 + + mfspr r10, SPRN_M_TWB /* Get level 1 table entry address */ + + /* If we are faulting a kernel address, we have to use the + * kernel page tables. + */ + andi. r11, r10, 0x0800 + beq 3f + lis r11, swapper_pg_dir@h + ori r11, r11, swapper_pg_dir@l + rlwimi r10, r11, 0, 2, 19 +3: + lwz r11, 0(r10) /* Get the level 1 entry */ + rlwinm. r10, r11,0,0,19 /* Extract page descriptor page address */ + beq 2f /* If zero, bail */ + + /* We have a pte table, so fetch the pte from the table. + */ + ori r11, r11, 1 /* Set valid bit in physical L2 page */ + DO_8xx_CPU6(0x3b80, r3) + mtspr SPRN_MD_TWC, r11 /* Load pte table base address */ + mfspr r11, SPRN_MD_TWC /* ....and get the pte address */ + lwz r10, 0(r11) /* Get the pte */ + + andi. r11, r10, _PAGE_RW /* Is it writeable? */ + beq 2f /* Bail out if not */ + + /* Update 'changed', among others. + */ + ori r10, r10, _PAGE_DIRTY|_PAGE_ACCESSED|_PAGE_HWWRITE + mfspr r11, SPRN_MD_TWC /* Get pte address again */ + stw r10, 0(r11) /* and update pte in table */ + + /* The Linux PTE won't go exactly into the MMU TLB. + * Software indicator bits 21, 22 and 28 must be clear. + * Software indicator bits 24, 25, 26, and 27 must be + * set. All other Linux PTE bits control the behavior + * of the MMU. + */ + li r11, 0x00f0 + rlwimi r10, r11, 0, 24, 28 /* Set 24-27, clear 28 */ + DO_8xx_CPU6(0x3d80, r3) + mtspr SPRN_MD_RPN, r10 /* Update TLB entry */ + + mfspr r10, SPRN_M_TW /* Restore registers */ + lwz r11, 0(r0) + mtcr r11 + lwz r11, 4(r0) +#ifdef CONFIG_8xx_CPU6 + lwz r3, 8(r0) +#endif + rfi +2: + mfspr r10, SPRN_M_TW /* Restore registers */ + lwz r11, 0(r0) + mtcr r11 + lwz r11, 4(r0) +#ifdef CONFIG_8xx_CPU6 + lwz r3, 8(r0) +#endif + b DataAccess + + EXCEPTION(0x1500, Trap_15, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1600, Trap_16, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1700, Trap_17, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1800, Trap_18, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1900, Trap_19, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1a00, Trap_1a, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1b00, Trap_1b, unknown_exception, EXC_XFER_EE) + +/* On the MPC8xx, these next four traps are used for development + * support of breakpoints and such. Someday I will get around to + * using them. + */ + EXCEPTION(0x1c00, Trap_1c, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1d00, Trap_1d, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1e00, Trap_1e, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1f00, Trap_1f, unknown_exception, EXC_XFER_EE) + + . = 0x2000 + + .globl giveup_fpu +giveup_fpu: + blr + +/* + * This is where the main kernel code starts. + */ +start_here: + /* ptr to current */ + lis r2,init_task@h + ori r2,r2,init_task@l + + /* ptr to phys current thread */ + tophys(r4,r2) + addi r4,r4,THREAD /* init task's THREAD */ + mtspr SPRN_SPRG3,r4 + li r3,0 + mtspr SPRN_SPRG2,r3 /* 0 => r1 has kernel sp */ + + /* stack */ + lis r1,init_thread_union@ha + addi r1,r1,init_thread_union@l + li r0,0 + stwu r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1) + + bl early_init /* We have to do this with MMU on */ + +/* + * Decide what sort of machine this is and initialize the MMU. + */ + mr r3,r31 + mr r4,r30 + mr r5,r29 + mr r6,r28 + mr r7,r27 + bl machine_init + bl MMU_init + +/* + * Go back to running unmapped so we can load up new values + * and change to using our exception vectors. + * On the 8xx, all we have to do is invalidate the TLB to clear + * the old 8M byte TLB mappings and load the page table base register. + */ + /* The right way to do this would be to track it down through + * init's THREAD like the context switch code does, but this is + * easier......until someone changes init's static structures. + */ + lis r6, swapper_pg_dir@h + ori r6, r6, swapper_pg_dir@l + tophys(r6,r6) +#ifdef CONFIG_8xx_CPU6 + lis r4, cpu6_errata_word@h + ori r4, r4, cpu6_errata_word@l + li r3, 0x3980 + stw r3, 12(r4) + lwz r3, 12(r4) +#endif + mtspr SPRN_M_TWB, r6 + lis r4,2f@h + ori r4,r4,2f@l + tophys(r4,r4) + li r3,MSR_KERNEL & ~(MSR_IR|MSR_DR) + mtspr SPRN_SRR0,r4 + mtspr SPRN_SRR1,r3 + rfi +/* Load up the kernel context */ +2: + SYNC /* Force all PTE updates to finish */ + tlbia /* Clear all TLB entries */ + sync /* wait for tlbia/tlbie to finish */ + TLBSYNC /* ... on all CPUs */ + + /* set up the PTE pointers for the Abatron bdiGDB. + */ + tovirt(r6,r6) + lis r5, abatron_pteptrs@h + ori r5, r5, abatron_pteptrs@l + stw r5, 0xf0(r0) /* Must match your Abatron config file */ + tophys(r5,r5) + stw r6, 0(r5) + +/* Now turn on the MMU for real! */ + li r4,MSR_KERNEL + lis r3,start_kernel@h + ori r3,r3,start_kernel@l + mtspr SPRN_SRR0,r3 + mtspr SPRN_SRR1,r4 + rfi /* enable MMU and jump to start_kernel */ + +/* Set up the initial MMU state so we can do the first level of + * kernel initialization. This maps the first 8 MBytes of memory 1:1 + * virtual to physical. Also, set the cache mode since that is defined + * by TLB entries and perform any additional mapping (like of the IMMR). + * If configured to pin some TLBs, we pin the first 8 Mbytes of kernel, + * 24 Mbytes of data, and the 8M IMMR space. Anything not covered by + * these mappings is mapped by page tables. + */ +initial_mmu: + tlbia /* Invalidate all TLB entries */ +#ifdef CONFIG_PIN_TLB + lis r8, MI_RSV4I@h + ori r8, r8, 0x1c00 +#else + li r8, 0 +#endif + mtspr SPRN_MI_CTR, r8 /* Set instruction MMU control */ + +#ifdef CONFIG_PIN_TLB + lis r10, (MD_RSV4I | MD_RESETVAL)@h + ori r10, r10, 0x1c00 + mr r8, r10 +#else + lis r10, MD_RESETVAL@h +#endif +#ifndef CONFIG_8xx_COPYBACK + oris r10, r10, MD_WTDEF@h +#endif + mtspr SPRN_MD_CTR, r10 /* Set data TLB control */ + + /* Now map the lower 8 Meg into the TLBs. For this quick hack, + * we can load the instruction and data TLB registers with the + * same values. + */ + lis r8, KERNELBASE@h /* Create vaddr for TLB */ + ori r8, r8, MI_EVALID /* Mark it valid */ + mtspr SPRN_MI_EPN, r8 + mtspr SPRN_MD_EPN, r8 + li r8, MI_PS8MEG /* Set 8M byte page */ + ori r8, r8, MI_SVALID /* Make it valid */ + mtspr SPRN_MI_TWC, r8 + mtspr SPRN_MD_TWC, r8 + li r8, MI_BOOTINIT /* Create RPN for address 0 */ + mtspr SPRN_MI_RPN, r8 /* Store TLB entry */ + mtspr SPRN_MD_RPN, r8 + lis r8, MI_Kp@h /* Set the protection mode */ + mtspr SPRN_MI_AP, r8 + mtspr SPRN_MD_AP, r8 + + /* Map another 8 MByte at the IMMR to get the processor + * internal registers (among other things). + */ +#ifdef CONFIG_PIN_TLB + addi r10, r10, 0x0100 + mtspr SPRN_MD_CTR, r10 +#endif + mfspr r9, 638 /* Get current IMMR */ + andis. r9, r9, 0xff80 /* Get 8Mbyte boundary */ + + mr r8, r9 /* Create vaddr for TLB */ + ori r8, r8, MD_EVALID /* Mark it valid */ + mtspr SPRN_MD_EPN, r8 + li r8, MD_PS8MEG /* Set 8M byte page */ + ori r8, r8, MD_SVALID /* Make it valid */ + mtspr SPRN_MD_TWC, r8 + mr r8, r9 /* Create paddr for TLB */ + ori r8, r8, MI_BOOTINIT|0x2 /* Inhibit cache -- Cort */ + mtspr SPRN_MD_RPN, r8 + +#ifdef CONFIG_PIN_TLB + /* Map two more 8M kernel data pages. + */ + addi r10, r10, 0x0100 + mtspr SPRN_MD_CTR, r10 + + lis r8, KERNELBASE@h /* Create vaddr for TLB */ + addis r8, r8, 0x0080 /* Add 8M */ + ori r8, r8, MI_EVALID /* Mark it valid */ + mtspr SPRN_MD_EPN, r8 + li r9, MI_PS8MEG /* Set 8M byte page */ + ori r9, r9, MI_SVALID /* Make it valid */ + mtspr SPRN_MD_TWC, r9 + li r11, MI_BOOTINIT /* Create RPN for address 0 */ + addis r11, r11, 0x0080 /* Add 8M */ + mtspr SPRN_MD_RPN, r8 + + addis r8, r8, 0x0080 /* Add 8M */ + mtspr SPRN_MD_EPN, r8 + mtspr SPRN_MD_TWC, r9 + addis r11, r11, 0x0080 /* Add 8M */ + mtspr SPRN_MD_RPN, r8 +#endif + + /* Since the cache is enabled according to the information we + * just loaded into the TLB, invalidate and enable the caches here. + * We should probably check/set other modes....later. + */ + lis r8, IDC_INVALL@h + mtspr SPRN_IC_CST, r8 + mtspr SPRN_DC_CST, r8 + lis r8, IDC_ENABLE@h + mtspr SPRN_IC_CST, r8 +#ifdef CONFIG_8xx_COPYBACK + mtspr SPRN_DC_CST, r8 +#else + /* For a debug option, I left this here to easily enable + * the write through cache mode + */ + lis r8, DC_SFWT@h + mtspr SPRN_DC_CST, r8 + lis r8, IDC_ENABLE@h + mtspr SPRN_DC_CST, r8 +#endif + blr + + +/* + * Set up to use a given MMU context. + * r3 is context number, r4 is PGD pointer. + * + * We place the physical address of the new task page directory loaded + * into the MMU base register, and set the ASID compare register with + * the new "context." + */ +_GLOBAL(set_context) + +#ifdef CONFIG_BDI_SWITCH + /* Context switch the PTE pointer for the Abatron BDI2000. + * The PGDIR is passed as second argument. + */ + lis r5, KERNELBASE@h + lwz r5, 0xf0(r5) + stw r4, 0x4(r5) +#endif + +#ifdef CONFIG_8xx_CPU6 + lis r6, cpu6_errata_word@h + ori r6, r6, cpu6_errata_word@l + tophys (r4, r4) + li r7, 0x3980 + stw r7, 12(r6) + lwz r7, 12(r6) + mtspr SPRN_M_TWB, r4 /* Update MMU base address */ + li r7, 0x3380 + stw r7, 12(r6) + lwz r7, 12(r6) + mtspr SPRN_M_CASID, r3 /* Update context */ +#else + mtspr SPRN_M_CASID,r3 /* Update context */ + tophys (r4, r4) + mtspr SPRN_M_TWB, r4 /* and pgd */ +#endif + SYNC + blr + +#ifdef CONFIG_8xx_CPU6 +/* It's here because it is unique to the 8xx. + * It is important we get called with interrupts disabled. I used to + * do that, but it appears that all code that calls this already had + * interrupt disabled. + */ + .globl set_dec_cpu6 +set_dec_cpu6: + lis r7, cpu6_errata_word@h + ori r7, r7, cpu6_errata_word@l + li r4, 0x2c00 + stw r4, 8(r7) + lwz r4, 8(r7) + mtspr 22, r3 /* Update Decrementer */ + SYNC + blr +#endif + +/* + * We put a few things here that have to be page-aligned. + * This stuff goes at the beginning of the data segment, + * which is page-aligned. + */ + .data + .globl sdata +sdata: + .globl empty_zero_page +empty_zero_page: + .space 4096 + + .globl swapper_pg_dir +swapper_pg_dir: + .space 4096 + +/* + * This space gets a copy of optional info passed to us by the bootstrap + * Used to pass parameters into the kernel like root=/dev/sda1, etc. + */ + .globl cmd_line +cmd_line: + .space 512 + +/* Room for two PTE table poiners, usually the kernel and current user + * pointer to their respective root page table (pgdir). + */ +abatron_pteptrs: + .space 8 + +#ifdef CONFIG_8xx_CPU6 + .globl cpu6_errata_word +cpu6_errata_word: + .space 16 +#endif + diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S new file mode 100644 index 000000000000..5063c603fad4 --- /dev/null +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -0,0 +1,1063 @@ +/* + * arch/ppc/kernel/head_fsl_booke.S + * + * Kernel execution entry point code. + * + * Copyright (c) 1995-1996 Gary Thomas <gdt@linuxppc.org> + * Initial PowerPC version. + * Copyright (c) 1996 Cort Dougan <cort@cs.nmt.edu> + * Rewritten for PReP + * Copyright (c) 1996 Paul Mackerras <paulus@cs.anu.edu.au> + * Low-level exception handers, MMU support, and rewrite. + * Copyright (c) 1997 Dan Malek <dmalek@jlc.net> + * PowerPC 8xx modifications. + * Copyright (c) 1998-1999 TiVo, Inc. + * PowerPC 403GCX modifications. + * Copyright (c) 1999 Grant Erickson <grant@lcse.umn.edu> + * PowerPC 403GCX/405GP modifications. + * Copyright 2000 MontaVista Software Inc. + * PPC405 modifications + * PowerPC 403GCX/405GP modifications. + * Author: MontaVista Software, Inc. + * frank_rowand@mvista.com or source@mvista.com + * debbie_chu@mvista.com + * Copyright 2002-2004 MontaVista Software, Inc. + * PowerPC 44x support, Matt Porter <mporter@kernel.crashing.org> + * Copyright 2004 Freescale Semiconductor, Inc + * PowerPC e500 modifications, Kumar Gala <kumar.gala@freescale.com> + * + * 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/threads.h> +#include <asm/processor.h> +#include <asm/page.h> +#include <asm/mmu.h> +#include <asm/pgtable.h> +#include <asm/cputable.h> +#include <asm/thread_info.h> +#include <asm/ppc_asm.h> +#include <asm/asm-offsets.h> +#include "head_booke.h" + +/* As with the other PowerPC ports, it is expected that when code + * execution begins here, the following registers contain valid, yet + * optional, information: + * + * r3 - Board info structure pointer (DRAM, frequency, MAC address, etc.) + * r4 - Starting address of the init RAM disk + * r5 - Ending address of the init RAM disk + * r6 - Start of kernel command line string (e.g. "mem=128") + * r7 - End of kernel command line string + * + */ + .text +_GLOBAL(_stext) +_GLOBAL(_start) + /* + * Reserve a word at a fixed location to store the address + * of abatron_pteptrs + */ + nop +/* + * Save parameters we are passed + */ + mr r31,r3 + mr r30,r4 + mr r29,r5 + mr r28,r6 + mr r27,r7 + li r24,0 /* CPU number */ + +/* We try to not make any assumptions about how the boot loader + * setup or used the TLBs. We invalidate all mappings from the + * boot loader and load a single entry in TLB1[0] to map the + * first 16M of kernel memory. Any boot info passed from the + * bootloader needs to live in this first 16M. + * + * Requirement on bootloader: + * - The page we're executing in needs to reside in TLB1 and + * have IPROT=1. If not an invalidate broadcast could + * evict the entry we're currently executing in. + * + * r3 = Index of TLB1 were executing in + * r4 = Current MSR[IS] + * r5 = Index of TLB1 temp mapping + * + * Later in mapin_ram we will correctly map lowmem, and resize TLB1[0] + * if needed + */ + +/* 1. Find the index of the entry we're executing in */ + bl invstr /* Find our address */ +invstr: mflr r6 /* Make it accessible */ + mfmsr r7 + rlwinm r4,r7,27,31,31 /* extract MSR[IS] */ + mfspr r7, SPRN_PID0 + slwi r7,r7,16 + or r7,r7,r4 + mtspr SPRN_MAS6,r7 + tlbsx 0,r6 /* search MSR[IS], SPID=PID0 */ +#ifndef CONFIG_E200 + mfspr r7,SPRN_MAS1 + andis. r7,r7,MAS1_VALID@h + bne match_TLB + mfspr r7,SPRN_PID1 + slwi r7,r7,16 + or r7,r7,r4 + mtspr SPRN_MAS6,r7 + tlbsx 0,r6 /* search MSR[IS], SPID=PID1 */ + mfspr r7,SPRN_MAS1 + andis. r7,r7,MAS1_VALID@h + bne match_TLB + mfspr r7, SPRN_PID2 + slwi r7,r7,16 + or r7,r7,r4 + mtspr SPRN_MAS6,r7 + tlbsx 0,r6 /* Fall through, we had to match */ +#endif +match_TLB: + mfspr r7,SPRN_MAS0 + rlwinm r3,r7,16,20,31 /* Extract MAS0(Entry) */ + + mfspr r7,SPRN_MAS1 /* Insure IPROT set */ + oris r7,r7,MAS1_IPROT@h + mtspr SPRN_MAS1,r7 + tlbwe + +/* 2. Invalidate all entries except the entry we're executing in */ + mfspr r9,SPRN_TLB1CFG + andi. r9,r9,0xfff + li r6,0 /* Set Entry counter to 0 */ +1: lis r7,0x1000 /* Set MAS0(TLBSEL) = 1 */ + rlwimi r7,r6,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r6) */ + mtspr SPRN_MAS0,r7 + tlbre + mfspr r7,SPRN_MAS1 + rlwinm r7,r7,0,2,31 /* Clear MAS1 Valid and IPROT */ + cmpw r3,r6 + beq skpinv /* Dont update the current execution TLB */ + mtspr SPRN_MAS1,r7 + tlbwe + isync +skpinv: addi r6,r6,1 /* Increment */ + cmpw r6,r9 /* Are we done? */ + bne 1b /* If not, repeat */ + + /* Invalidate TLB0 */ + li r6,0x04 + tlbivax 0,r6 +#ifdef CONFIG_SMP + tlbsync +#endif + /* Invalidate TLB1 */ + li r6,0x0c + tlbivax 0,r6 +#ifdef CONFIG_SMP + tlbsync +#endif + msync + +/* 3. Setup a temp mapping and jump to it */ + andi. r5, r3, 0x1 /* Find an entry not used and is non-zero */ + addi r5, r5, 0x1 + lis r7,0x1000 /* Set MAS0(TLBSEL) = 1 */ + rlwimi r7,r3,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r3) */ + mtspr SPRN_MAS0,r7 + tlbre + + /* Just modify the entry ID and EPN for the temp mapping */ + lis r7,0x1000 /* Set MAS0(TLBSEL) = 1 */ + rlwimi r7,r5,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r5) */ + mtspr SPRN_MAS0,r7 + xori r6,r4,1 /* Setup TMP mapping in the other Address space */ + slwi r6,r6,12 + oris r6,r6,(MAS1_VALID|MAS1_IPROT)@h + ori r6,r6,(MAS1_TSIZE(BOOKE_PAGESZ_4K))@l + mtspr SPRN_MAS1,r6 + mfspr r6,SPRN_MAS2 + li r7,0 /* temp EPN = 0 */ + rlwimi r7,r6,0,20,31 + mtspr SPRN_MAS2,r7 + tlbwe + + xori r6,r4,1 + slwi r6,r6,5 /* setup new context with other address space */ + bl 1f /* Find our address */ +1: mflr r9 + rlwimi r7,r9,0,20,31 + addi r7,r7,24 + mtspr SPRN_SRR0,r7 + mtspr SPRN_SRR1,r6 + rfi + +/* 4. Clear out PIDs & Search info */ + li r6,0 + mtspr SPRN_PID0,r6 +#ifndef CONFIG_E200 + mtspr SPRN_PID1,r6 + mtspr SPRN_PID2,r6 +#endif + mtspr SPRN_MAS6,r6 + +/* 5. Invalidate mapping we started in */ + lis r7,0x1000 /* Set MAS0(TLBSEL) = 1 */ + rlwimi r7,r3,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r3) */ + mtspr SPRN_MAS0,r7 + tlbre + li r6,0 + mtspr SPRN_MAS1,r6 + tlbwe + /* Invalidate TLB1 */ + li r9,0x0c + tlbivax 0,r9 +#ifdef CONFIG_SMP + tlbsync +#endif + msync + +/* 6. Setup KERNELBASE mapping in TLB1[0] */ + lis r6,0x1000 /* Set MAS0(TLBSEL) = TLB1(1), ESEL = 0 */ + mtspr SPRN_MAS0,r6 + lis r6,(MAS1_VALID|MAS1_IPROT)@h + ori r6,r6,(MAS1_TSIZE(BOOKE_PAGESZ_16M))@l + mtspr SPRN_MAS1,r6 + li r7,0 + lis r6,KERNELBASE@h + ori r6,r6,KERNELBASE@l + rlwimi r6,r7,0,20,31 + mtspr SPRN_MAS2,r6 + li r7,(MAS3_SX|MAS3_SW|MAS3_SR) + mtspr SPRN_MAS3,r7 + tlbwe + +/* 7. Jump to KERNELBASE mapping */ + lis r7,MSR_KERNEL@h + ori r7,r7,MSR_KERNEL@l + bl 1f /* Find our address */ +1: mflr r9 + rlwimi r6,r9,0,20,31 + addi r6,r6,24 + mtspr SPRN_SRR0,r6 + mtspr SPRN_SRR1,r7 + rfi /* start execution out of TLB1[0] entry */ + +/* 8. Clear out the temp mapping */ + lis r7,0x1000 /* Set MAS0(TLBSEL) = 1 */ + rlwimi r7,r5,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r5) */ + mtspr SPRN_MAS0,r7 + tlbre + mtspr SPRN_MAS1,r8 + tlbwe + /* Invalidate TLB1 */ + li r9,0x0c + tlbivax 0,r9 +#ifdef CONFIG_SMP + tlbsync +#endif + msync + + /* Establish the interrupt vector offsets */ + SET_IVOR(0, CriticalInput); + SET_IVOR(1, MachineCheck); + SET_IVOR(2, DataStorage); + SET_IVOR(3, InstructionStorage); + SET_IVOR(4, ExternalInput); + SET_IVOR(5, Alignment); + SET_IVOR(6, Program); + SET_IVOR(7, FloatingPointUnavailable); + SET_IVOR(8, SystemCall); + SET_IVOR(9, AuxillaryProcessorUnavailable); + SET_IVOR(10, Decrementer); + SET_IVOR(11, FixedIntervalTimer); + SET_IVOR(12, WatchdogTimer); + SET_IVOR(13, DataTLBError); + SET_IVOR(14, InstructionTLBError); + SET_IVOR(15, Debug); + SET_IVOR(32, SPEUnavailable); + SET_IVOR(33, SPEFloatingPointData); + SET_IVOR(34, SPEFloatingPointRound); +#ifndef CONFIG_E200 + SET_IVOR(35, PerformanceMonitor); +#endif + + /* Establish the interrupt vector base */ + lis r4,interrupt_base@h /* IVPR only uses the high 16-bits */ + mtspr SPRN_IVPR,r4 + + /* Setup the defaults for TLB entries */ + li r2,(MAS4_TSIZED(BOOKE_PAGESZ_4K))@l +#ifdef CONFIG_E200 + oris r2,r2,MAS4_TLBSELD(1)@h +#endif + mtspr SPRN_MAS4, r2 + +#if 0 + /* Enable DOZE */ + mfspr r2,SPRN_HID0 + oris r2,r2,HID0_DOZE@h + mtspr SPRN_HID0, r2 +#endif +#ifdef CONFIG_E200 + /* enable dedicated debug exception handling resources (Debug APU) */ + mfspr r2,SPRN_HID0 + ori r2,r2,HID0_DAPUEN@l + mtspr SPRN_HID0,r2 +#endif + +#if !defined(CONFIG_BDI_SWITCH) + /* + * The Abatron BDI JTAG debugger does not tolerate others + * mucking with the debug registers. + */ + lis r2,DBCR0_IDM@h + mtspr SPRN_DBCR0,r2 + /* clear any residual debug events */ + li r2,-1 + mtspr SPRN_DBSR,r2 +#endif + + /* + * This is where the main kernel code starts. + */ + + /* ptr to current */ + lis r2,init_task@h + ori r2,r2,init_task@l + + /* ptr to current thread */ + addi r4,r2,THREAD /* init task's THREAD */ + mtspr SPRN_SPRG3,r4 + + /* stack */ + lis r1,init_thread_union@h + ori r1,r1,init_thread_union@l + li r0,0 + stwu r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1) + + bl early_init + + mfspr r3,SPRN_TLB1CFG + andi. r3,r3,0xfff + lis r4,num_tlbcam_entries@ha + stw r3,num_tlbcam_entries@l(r4) +/* + * Decide what sort of machine this is and initialize the MMU. + */ + mr r3,r31 + mr r4,r30 + mr r5,r29 + mr r6,r28 + mr r7,r27 + bl machine_init + bl MMU_init + + /* Setup PTE pointers for the Abatron bdiGDB */ + lis r6, swapper_pg_dir@h + ori r6, r6, swapper_pg_dir@l + lis r5, abatron_pteptrs@h + ori r5, r5, abatron_pteptrs@l + lis r4, KERNELBASE@h + ori r4, r4, KERNELBASE@l + stw r5, 0(r4) /* Save abatron_pteptrs at a fixed location */ + stw r6, 0(r5) + + /* Let's move on */ + lis r4,start_kernel@h + ori r4,r4,start_kernel@l + lis r3,MSR_KERNEL@h + ori r3,r3,MSR_KERNEL@l + mtspr SPRN_SRR0,r4 + mtspr SPRN_SRR1,r3 + rfi /* change context and jump to start_kernel */ + +/* Macros to hide the PTE size differences + * + * FIND_PTE -- walks the page tables given EA & pgdir pointer + * r10 -- EA of fault + * r11 -- PGDIR pointer + * r12 -- free + * label 2: is the bailout case + * + * if we find the pte (fall through): + * r11 is low pte word + * r12 is pointer to the pte + */ +#ifdef CONFIG_PTE_64BIT +#define PTE_FLAGS_OFFSET 4 +#define FIND_PTE \ + rlwinm r12, r10, 13, 19, 29; /* Compute pgdir/pmd offset */ \ + lwzx r11, r12, r11; /* Get pgd/pmd entry */ \ + rlwinm. r12, r11, 0, 0, 20; /* Extract pt base address */ \ + beq 2f; /* Bail if no table */ \ + rlwimi r12, r10, 23, 20, 28; /* Compute pte address */ \ + lwz r11, 4(r12); /* Get pte entry */ +#else +#define PTE_FLAGS_OFFSET 0 +#define FIND_PTE \ + rlwimi r11, r10, 12, 20, 29; /* Create L1 (pgdir/pmd) address */ \ + lwz r11, 0(r11); /* Get L1 entry */ \ + rlwinm. r12, r11, 0, 0, 19; /* Extract L2 (pte) base address */ \ + beq 2f; /* Bail if no table */ \ + rlwimi r12, r10, 22, 20, 29; /* Compute PTE address */ \ + lwz r11, 0(r12); /* Get Linux PTE */ +#endif + +/* + * Interrupt vector entry code + * + * The Book E MMUs are always on so we don't need to handle + * interrupts in real mode as with previous PPC processors. In + * this case we handle interrupts in the kernel virtual address + * space. + * + * Interrupt vectors are dynamically placed relative to the + * interrupt prefix as determined by the address of interrupt_base. + * The interrupt vectors offsets are programmed using the labels + * for each interrupt vector entry. + * + * Interrupt vectors must be aligned on a 16 byte boundary. + * We align on a 32 byte cache line boundary for good measure. + */ + +interrupt_base: + /* Critical Input Interrupt */ + CRITICAL_EXCEPTION(0x0100, CriticalInput, unknown_exception) + + /* Machine Check Interrupt */ +#ifdef CONFIG_E200 + /* no RFMCI, MCSRRs on E200 */ + CRITICAL_EXCEPTION(0x0200, MachineCheck, machine_check_exception) +#else + MCHECK_EXCEPTION(0x0200, MachineCheck, machine_check_exception) +#endif + + /* Data Storage Interrupt */ + START_EXCEPTION(DataStorage) + mtspr SPRN_SPRG0, r10 /* Save some working registers */ + mtspr SPRN_SPRG1, r11 + mtspr SPRN_SPRG4W, r12 + mtspr SPRN_SPRG5W, r13 + mfcr r11 + mtspr SPRN_SPRG7W, r11 + + /* + * Check if it was a store fault, if not then bail + * because a user tried to access a kernel or + * read-protected page. Otherwise, get the + * offending address and handle it. + */ + mfspr r10, SPRN_ESR + andis. r10, r10, ESR_ST@h + beq 2f + + mfspr r10, SPRN_DEAR /* Get faulting address */ + + /* If we are faulting a kernel address, we have to use the + * kernel page tables. + */ + lis r11, TASK_SIZE@h + ori r11, r11, TASK_SIZE@l + cmplw 0, r10, r11 + bge 2f + + /* Get the PGD for the current thread */ +3: + mfspr r11,SPRN_SPRG3 + lwz r11,PGDIR(r11) +4: + FIND_PTE + + /* Are _PAGE_USER & _PAGE_RW set & _PAGE_HWWRITE not? */ + andi. r13, r11, _PAGE_RW|_PAGE_USER|_PAGE_HWWRITE + cmpwi 0, r13, _PAGE_RW|_PAGE_USER + bne 2f /* Bail if not */ + + /* Update 'changed'. */ + ori r11, r11, _PAGE_DIRTY|_PAGE_ACCESSED|_PAGE_HWWRITE + stw r11, PTE_FLAGS_OFFSET(r12) /* Update Linux page table */ + + /* MAS2 not updated as the entry does exist in the tlb, this + fault taken to detect state transition (eg: COW -> DIRTY) + */ + andi. r11, r11, _PAGE_HWEXEC + rlwimi r11, r11, 31, 27, 27 /* SX <- _PAGE_HWEXEC */ + ori r11, r11, (MAS3_UW|MAS3_SW|MAS3_UR|MAS3_SR)@l /* set static perms */ + + /* update search PID in MAS6, AS = 0 */ + mfspr r12, SPRN_PID0 + slwi r12, r12, 16 + mtspr SPRN_MAS6, r12 + + /* find the TLB index that caused the fault. It has to be here. */ + tlbsx 0, r10 + + /* only update the perm bits, assume the RPN is fine */ + mfspr r12, SPRN_MAS3 + rlwimi r12, r11, 0, 20, 31 + mtspr SPRN_MAS3,r12 + tlbwe + + /* Done...restore registers and get out of here. */ + mfspr r11, SPRN_SPRG7R + mtcr r11 + mfspr r13, SPRN_SPRG5R + mfspr r12, SPRN_SPRG4R + mfspr r11, SPRN_SPRG1 + mfspr r10, SPRN_SPRG0 + rfi /* Force context change */ + +2: + /* + * The bailout. Restore registers to pre-exception conditions + * and call the heavyweights to help us out. + */ + mfspr r11, SPRN_SPRG7R + mtcr r11 + mfspr r13, SPRN_SPRG5R + mfspr r12, SPRN_SPRG4R + mfspr r11, SPRN_SPRG1 + mfspr r10, SPRN_SPRG0 + b data_access + + /* Instruction Storage Interrupt */ + INSTRUCTION_STORAGE_EXCEPTION + + /* External Input Interrupt */ + EXCEPTION(0x0500, ExternalInput, do_IRQ, EXC_XFER_LITE) + + /* Alignment Interrupt */ + ALIGNMENT_EXCEPTION + + /* Program Interrupt */ + PROGRAM_EXCEPTION + + /* Floating Point Unavailable Interrupt */ +#ifdef CONFIG_PPC_FPU + FP_UNAVAILABLE_EXCEPTION +#else +#ifdef CONFIG_E200 + /* E200 treats 'normal' floating point instructions as FP Unavail exception */ + EXCEPTION(0x0800, FloatingPointUnavailable, program_check_exception, EXC_XFER_EE) +#else + EXCEPTION(0x0800, FloatingPointUnavailable, unknown_exception, EXC_XFER_EE) +#endif +#endif + + /* System Call Interrupt */ + START_EXCEPTION(SystemCall) + NORMAL_EXCEPTION_PROLOG + EXC_XFER_EE_LITE(0x0c00, DoSyscall) + + /* Auxillary Processor Unavailable Interrupt */ + EXCEPTION(0x2900, AuxillaryProcessorUnavailable, unknown_exception, EXC_XFER_EE) + + /* Decrementer Interrupt */ + DECREMENTER_EXCEPTION + + /* Fixed Internal Timer Interrupt */ + /* TODO: Add FIT support */ + EXCEPTION(0x3100, FixedIntervalTimer, unknown_exception, EXC_XFER_EE) + + /* Watchdog Timer Interrupt */ +#ifdef CONFIG_BOOKE_WDT + CRITICAL_EXCEPTION(0x3200, WatchdogTimer, WatchdogException) +#else + CRITICAL_EXCEPTION(0x3200, WatchdogTimer, unknown_exception) +#endif + + /* Data TLB Error Interrupt */ + START_EXCEPTION(DataTLBError) + mtspr SPRN_SPRG0, r10 /* Save some working registers */ + mtspr SPRN_SPRG1, r11 + mtspr SPRN_SPRG4W, r12 + mtspr SPRN_SPRG5W, r13 + mfcr r11 + mtspr SPRN_SPRG7W, r11 + mfspr r10, SPRN_DEAR /* Get faulting address */ + + /* If we are faulting a kernel address, we have to use the + * kernel page tables. + */ + lis r11, TASK_SIZE@h + ori r11, r11, TASK_SIZE@l + cmplw 5, r10, r11 + blt 5, 3f + lis r11, swapper_pg_dir@h + ori r11, r11, swapper_pg_dir@l + + mfspr r12,SPRN_MAS1 /* Set TID to 0 */ + rlwinm r12,r12,0,16,1 + mtspr SPRN_MAS1,r12 + + b 4f + + /* Get the PGD for the current thread */ +3: + mfspr r11,SPRN_SPRG3 + lwz r11,PGDIR(r11) + +4: + FIND_PTE + andi. r13, r11, _PAGE_PRESENT /* Is the page present? */ + beq 2f /* Bail if not present */ + +#ifdef CONFIG_PTE_64BIT + lwz r13, 0(r12) +#endif + ori r11, r11, _PAGE_ACCESSED + stw r11, PTE_FLAGS_OFFSET(r12) + + /* Jump to common tlb load */ + b finish_tlb_load +2: + /* The bailout. Restore registers to pre-exception conditions + * and call the heavyweights to help us out. + */ + mfspr r11, SPRN_SPRG7R + mtcr r11 + mfspr r13, SPRN_SPRG5R + mfspr r12, SPRN_SPRG4R + mfspr r11, SPRN_SPRG1 + mfspr r10, SPRN_SPRG0 + b data_access + + /* Instruction TLB Error Interrupt */ + /* + * Nearly the same as above, except we get our + * information from different registers and bailout + * to a different point. + */ + START_EXCEPTION(InstructionTLBError) + mtspr SPRN_SPRG0, r10 /* Save some working registers */ + mtspr SPRN_SPRG1, r11 + mtspr SPRN_SPRG4W, r12 + mtspr SPRN_SPRG5W, r13 + mfcr r11 + mtspr SPRN_SPRG7W, r11 + mfspr r10, SPRN_SRR0 /* Get faulting address */ + + /* If we are faulting a kernel address, we have to use the + * kernel page tables. + */ + lis r11, TASK_SIZE@h + ori r11, r11, TASK_SIZE@l + cmplw 5, r10, r11 + blt 5, 3f + lis r11, swapper_pg_dir@h + ori r11, r11, swapper_pg_dir@l + + mfspr r12,SPRN_MAS1 /* Set TID to 0 */ + rlwinm r12,r12,0,16,1 + mtspr SPRN_MAS1,r12 + + b 4f + + /* Get the PGD for the current thread */ +3: + mfspr r11,SPRN_SPRG3 + lwz r11,PGDIR(r11) + +4: + FIND_PTE + andi. r13, r11, _PAGE_PRESENT /* Is the page present? */ + beq 2f /* Bail if not present */ + +#ifdef CONFIG_PTE_64BIT + lwz r13, 0(r12) +#endif + ori r11, r11, _PAGE_ACCESSED + stw r11, PTE_FLAGS_OFFSET(r12) + + /* Jump to common TLB load point */ + b finish_tlb_load + +2: + /* The bailout. Restore registers to pre-exception conditions + * and call the heavyweights to help us out. + */ + mfspr r11, SPRN_SPRG7R + mtcr r11 + mfspr r13, SPRN_SPRG5R + mfspr r12, SPRN_SPRG4R + mfspr r11, SPRN_SPRG1 + mfspr r10, SPRN_SPRG0 + b InstructionStorage + +#ifdef CONFIG_SPE + /* SPE Unavailable */ + START_EXCEPTION(SPEUnavailable) + NORMAL_EXCEPTION_PROLOG + bne load_up_spe + addi r3,r1,STACK_FRAME_OVERHEAD + EXC_XFER_EE_LITE(0x2010, KernelSPE) +#else + EXCEPTION(0x2020, SPEUnavailable, unknown_exception, EXC_XFER_EE) +#endif /* CONFIG_SPE */ + + /* SPE Floating Point Data */ +#ifdef CONFIG_SPE + EXCEPTION(0x2030, SPEFloatingPointData, SPEFloatingPointException, EXC_XFER_EE); +#else + EXCEPTION(0x2040, SPEFloatingPointData, unknown_exception, EXC_XFER_EE) +#endif /* CONFIG_SPE */ + + /* SPE Floating Point Round */ + EXCEPTION(0x2050, SPEFloatingPointRound, unknown_exception, EXC_XFER_EE) + + /* Performance Monitor */ + EXCEPTION(0x2060, PerformanceMonitor, performance_monitor_exception, EXC_XFER_STD) + + + /* Debug Interrupt */ + DEBUG_EXCEPTION + +/* + * Local functions + */ + + /* + * Data TLB exceptions will bail out to this point + * if they can't resolve the lightweight TLB fault. + */ +data_access: + NORMAL_EXCEPTION_PROLOG + mfspr r5,SPRN_ESR /* Grab the ESR, save it, pass arg3 */ + stw r5,_ESR(r11) + mfspr r4,SPRN_DEAR /* Grab the DEAR, save it, pass arg2 */ + andis. r10,r5,(ESR_ILK|ESR_DLK)@h + bne 1f + EXC_XFER_EE_LITE(0x0300, handle_page_fault) +1: + addi r3,r1,STACK_FRAME_OVERHEAD + EXC_XFER_EE_LITE(0x0300, CacheLockingException) + +/* + + * Both the instruction and data TLB miss get to this + * point to load the TLB. + * r10 - EA of fault + * r11 - TLB (info from Linux PTE) + * r12, r13 - available to use + * CR5 - results of addr < TASK_SIZE + * MAS0, MAS1 - loaded with proper value when we get here + * MAS2, MAS3 - will need additional info from Linux PTE + * Upon exit, we reload everything and RFI. + */ +finish_tlb_load: + /* + * We set execute, because we don't have the granularity to + * properly set this at the page level (Linux problem). + * Many of these bits are software only. Bits we don't set + * here we (properly should) assume have the appropriate value. + */ + + mfspr r12, SPRN_MAS2 +#ifdef CONFIG_PTE_64BIT + rlwimi r12, r11, 26, 24, 31 /* extract ...WIMGE from pte */ +#else + rlwimi r12, r11, 26, 27, 31 /* extract WIMGE from pte */ +#endif + mtspr SPRN_MAS2, r12 + + bge 5, 1f + + /* is user addr */ + andi. r12, r11, (_PAGE_USER | _PAGE_HWWRITE | _PAGE_HWEXEC) + andi. r10, r11, _PAGE_USER /* Test for _PAGE_USER */ + srwi r10, r12, 1 + or r12, r12, r10 /* Copy user perms into supervisor */ + iseleq r12, 0, r12 + b 2f + + /* is kernel addr */ +1: rlwinm r12, r11, 31, 29, 29 /* Extract _PAGE_HWWRITE into SW */ + ori r12, r12, (MAS3_SX | MAS3_SR) + +#ifdef CONFIG_PTE_64BIT +2: rlwimi r12, r13, 24, 0, 7 /* grab RPN[32:39] */ + rlwimi r12, r11, 24, 8, 19 /* grab RPN[40:51] */ + mtspr SPRN_MAS3, r12 +BEGIN_FTR_SECTION + srwi r10, r13, 8 /* grab RPN[8:31] */ + mtspr SPRN_MAS7, r10 +END_FTR_SECTION_IFSET(CPU_FTR_BIG_PHYS) +#else +2: rlwimi r11, r12, 0, 20, 31 /* Extract RPN from PTE and merge with perms */ + mtspr SPRN_MAS3, r11 +#endif +#ifdef CONFIG_E200 + /* Round robin TLB1 entries assignment */ + mfspr r12, SPRN_MAS0 + + /* Extract TLB1CFG(NENTRY) */ + mfspr r11, SPRN_TLB1CFG + andi. r11, r11, 0xfff + + /* Extract MAS0(NV) */ + andi. r13, r12, 0xfff + addi r13, r13, 1 + cmpw 0, r13, r11 + addi r12, r12, 1 + + /* check if we need to wrap */ + blt 7f + + /* wrap back to first free tlbcam entry */ + lis r13, tlbcam_index@ha + lwz r13, tlbcam_index@l(r13) + rlwimi r12, r13, 0, 20, 31 +7: + mtspr SPRN_MAS0,r12 +#endif /* CONFIG_E200 */ + + tlbwe + + /* Done...restore registers and get out of here. */ + mfspr r11, SPRN_SPRG7R + mtcr r11 + mfspr r13, SPRN_SPRG5R + mfspr r12, SPRN_SPRG4R + mfspr r11, SPRN_SPRG1 + mfspr r10, SPRN_SPRG0 + rfi /* Force context change */ + +#ifdef CONFIG_SPE +/* Note that the SPE support is closely modeled after the AltiVec + * support. Changes to one are likely to be applicable to the + * other! */ +load_up_spe: +/* + * Disable SPE for the task which had SPE previously, + * and save its SPE registers in its thread_struct. + * Enables SPE for use in the kernel on return. + * On SMP we know the SPE units are free, since we give it up every + * switch. -- Kumar + */ + mfmsr r5 + oris r5,r5,MSR_SPE@h + mtmsr r5 /* enable use of SPE now */ + isync +/* + * For SMP, we don't do lazy SPE switching because it just gets too + * horrendously complex, especially when a task switches from one CPU + * to another. Instead we call giveup_spe in switch_to. + */ +#ifndef CONFIG_SMP + lis r3,last_task_used_spe@ha + lwz r4,last_task_used_spe@l(r3) + cmpi 0,r4,0 + beq 1f + addi r4,r4,THREAD /* want THREAD of last_task_used_spe */ + SAVE_32EVRS(0,r10,r4) + evxor evr10, evr10, evr10 /* clear out evr10 */ + evmwumiaa evr10, evr10, evr10 /* evr10 <- ACC = 0 * 0 + ACC */ + li r5,THREAD_ACC + evstddx evr10, r4, r5 /* save off accumulator */ + lwz r5,PT_REGS(r4) + lwz r4,_MSR-STACK_FRAME_OVERHEAD(r5) + lis r10,MSR_SPE@h + andc r4,r4,r10 /* disable SPE for previous task */ + stw r4,_MSR-STACK_FRAME_OVERHEAD(r5) +1: +#endif /* CONFIG_SMP */ + /* enable use of SPE after return */ + oris r9,r9,MSR_SPE@h + mfspr r5,SPRN_SPRG3 /* current task's THREAD (phys) */ + li r4,1 + li r10,THREAD_ACC + stw r4,THREAD_USED_SPE(r5) + evlddx evr4,r10,r5 + evmra evr4,evr4 + REST_32EVRS(0,r10,r5) +#ifndef CONFIG_SMP + subi r4,r5,THREAD + stw r4,last_task_used_spe@l(r3) +#endif /* CONFIG_SMP */ + /* restore registers and return */ +2: REST_4GPRS(3, r11) + lwz r10,_CCR(r11) + REST_GPR(1, r11) + mtcr r10 + lwz r10,_LINK(r11) + mtlr r10 + REST_GPR(10, r11) + mtspr SPRN_SRR1,r9 + mtspr SPRN_SRR0,r12 + REST_GPR(9, r11) + REST_GPR(12, r11) + lwz r11,GPR11(r11) + SYNC + rfi + +/* + * SPE unavailable trap from kernel - print a message, but let + * the task use SPE in the kernel until it returns to user mode. + */ +KernelSPE: + lwz r3,_MSR(r1) + oris r3,r3,MSR_SPE@h + stw r3,_MSR(r1) /* enable use of SPE after return */ + lis r3,87f@h + ori r3,r3,87f@l + mr r4,r2 /* current */ + lwz r5,_NIP(r1) + bl printk + b ret_from_except +87: .string "SPE used in kernel (task=%p, pc=%x) \n" + .align 4,0 + +#endif /* CONFIG_SPE */ + +/* + * Global functions + */ + +/* + * extern void loadcam_entry(unsigned int index) + * + * Load TLBCAM[index] entry in to the L2 CAM MMU + */ +_GLOBAL(loadcam_entry) + lis r4,TLBCAM@ha + addi r4,r4,TLBCAM@l + mulli r5,r3,20 + add r3,r5,r4 + lwz r4,0(r3) + mtspr SPRN_MAS0,r4 + lwz r4,4(r3) + mtspr SPRN_MAS1,r4 + lwz r4,8(r3) + mtspr SPRN_MAS2,r4 + lwz r4,12(r3) + mtspr SPRN_MAS3,r4 + tlbwe + isync + blr + +/* + * extern void giveup_altivec(struct task_struct *prev) + * + * The e500 core does not have an AltiVec unit. + */ +_GLOBAL(giveup_altivec) + blr + +#ifdef CONFIG_SPE +/* + * extern void giveup_spe(struct task_struct *prev) + * + */ +_GLOBAL(giveup_spe) + mfmsr r5 + oris r5,r5,MSR_SPE@h + SYNC + mtmsr r5 /* enable use of SPE now */ + isync + cmpi 0,r3,0 + beqlr- /* if no previous owner, done */ + addi r3,r3,THREAD /* want THREAD of task */ + lwz r5,PT_REGS(r3) + cmpi 0,r5,0 + SAVE_32EVRS(0, r4, r3) + evxor evr6, evr6, evr6 /* clear out evr6 */ + evmwumiaa evr6, evr6, evr6 /* evr6 <- ACC = 0 * 0 + ACC */ + li r4,THREAD_ACC + evstddx evr6, r4, r3 /* save off accumulator */ + mfspr r6,SPRN_SPEFSCR + stw r6,THREAD_SPEFSCR(r3) /* save spefscr register value */ + beq 1f + lwz r4,_MSR-STACK_FRAME_OVERHEAD(r5) + lis r3,MSR_SPE@h + andc r4,r4,r3 /* disable SPE for previous task */ + stw r4,_MSR-STACK_FRAME_OVERHEAD(r5) +1: +#ifndef CONFIG_SMP + li r5,0 + lis r4,last_task_used_spe@ha + stw r5,last_task_used_spe@l(r4) +#endif /* CONFIG_SMP */ + blr +#endif /* CONFIG_SPE */ + +/* + * extern void giveup_fpu(struct task_struct *prev) + * + * Not all FSL Book-E cores have an FPU + */ +#ifndef CONFIG_PPC_FPU +_GLOBAL(giveup_fpu) + blr +#endif + +/* + * extern void abort(void) + * + * At present, this routine just applies a system reset. + */ +_GLOBAL(abort) + li r13,0 + mtspr SPRN_DBCR0,r13 /* disable all debug events */ + mfmsr r13 + ori r13,r13,MSR_DE@l /* Enable Debug Events */ + mtmsr r13 + mfspr r13,SPRN_DBCR0 + lis r13,(DBCR0_IDM|DBCR0_RST_CHIP)@h + mtspr SPRN_DBCR0,r13 + +_GLOBAL(set_context) + +#ifdef CONFIG_BDI_SWITCH + /* Context switch the PTE pointer for the Abatron BDI2000. + * The PGDIR is the second parameter. + */ + lis r5, abatron_pteptrs@h + ori r5, r5, abatron_pteptrs@l + stw r4, 0x4(r5) +#endif + mtspr SPRN_PID,r3 + isync /* Force context change */ + blr + +/* + * We put a few things here that have to be page-aligned. This stuff + * goes at the beginning of the data segment, which is page-aligned. + */ + .data + .align 12 + .globl sdata +sdata: + .globl empty_zero_page +empty_zero_page: + .space 4096 + .globl swapper_pg_dir +swapper_pg_dir: + .space 4096 + +/* Reserved 4k for the critical exception stack & 4k for the machine + * check stack per CPU for kernel mode exceptions */ + .section .bss + .align 12 +exception_stack_bottom: + .space BOOKE_EXCEPTION_STACK_SIZE * NR_CPUS + .globl exception_stack_top +exception_stack_top: + +/* + * This space gets a copy of optional info passed to us by the bootstrap + * which is used to pass parameters into the kernel like root=/dev/sda1, etc. + */ + .globl cmd_line +cmd_line: + .space 512 + +/* + * Room for two PTE pointers, usually the kernel and current user pointers + * to their respective root page table. + */ +abatron_pteptrs: + .space 8 diff --git a/arch/powerpc/kernel/idle_6xx.S b/arch/powerpc/kernel/idle_6xx.S new file mode 100644 index 000000000000..444fdcc769f1 --- /dev/null +++ b/arch/powerpc/kernel/idle_6xx.S @@ -0,0 +1,233 @@ +/* + * This file contains the power_save function for 6xx & 7xxx CPUs + * rewritten in assembler + * + * Warning ! This code assumes that if your machine has a 750fx + * it will have PLL 1 set to low speed mode (used during NAP/DOZE). + * if this is not the case some additional changes will have to + * be done to check a runtime var (a bit like powersave-nap) + * + * 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/threads.h> +#include <asm/reg.h> +#include <asm/page.h> +#include <asm/cputable.h> +#include <asm/thread_info.h> +#include <asm/ppc_asm.h> +#include <asm/asm-offsets.h> + +#undef DEBUG + + .text + +/* + * Init idle, called at early CPU setup time from head.S for each CPU + * Make sure no rest of NAP mode remains in HID0, save default + * values for some CPU specific registers. Called with r24 + * containing CPU number and r3 reloc offset + */ +_GLOBAL(init_idle_6xx) +BEGIN_FTR_SECTION + mfspr r4,SPRN_HID0 + rlwinm r4,r4,0,10,8 /* Clear NAP */ + mtspr SPRN_HID0, r4 + b 1f +END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP) + blr +1: + slwi r5,r24,2 + add r5,r5,r3 +BEGIN_FTR_SECTION + mfspr r4,SPRN_MSSCR0 + addis r6,r5, nap_save_msscr0@ha + stw r4,nap_save_msscr0@l(r6) +END_FTR_SECTION_IFSET(CPU_FTR_NAP_DISABLE_L2_PR) +BEGIN_FTR_SECTION + mfspr r4,SPRN_HID1 + addis r6,r5,nap_save_hid1@ha + stw r4,nap_save_hid1@l(r6) +END_FTR_SECTION_IFSET(CPU_FTR_DUAL_PLL_750FX) + blr + +/* + * Here is the power_save_6xx function. This could eventually be + * split into several functions & changing the function pointer + * depending on the various features. + */ +_GLOBAL(ppc6xx_idle) + /* Check if we can nap or doze, put HID0 mask in r3 + */ + lis r3, 0 +BEGIN_FTR_SECTION + lis r3,HID0_DOZE@h +END_FTR_SECTION_IFSET(CPU_FTR_CAN_DOZE) +BEGIN_FTR_SECTION + /* We must dynamically check for the NAP feature as it + * can be cleared by CPU init after the fixups are done + */ + lis r4,cur_cpu_spec@ha + lwz r4,cur_cpu_spec@l(r4) + lwz r4,CPU_SPEC_FEATURES(r4) + andi. r0,r4,CPU_FTR_CAN_NAP + beq 1f + /* Now check if user or arch enabled NAP mode */ + lis r4,powersave_nap@ha + lwz r4,powersave_nap@l(r4) + cmpwi 0,r4,0 + beq 1f + lis r3,HID0_NAP@h +1: +END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP) + cmpwi 0,r3,0 + beqlr + + /* Clear MSR:EE */ + mfmsr r7 + rlwinm r0,r7,0,17,15 + mtmsr r0 + + /* Check current_thread_info()->flags */ + rlwinm r4,r1,0,0,18 + lwz r4,TI_FLAGS(r4) + andi. r0,r4,_TIF_NEED_RESCHED + beq 1f + mtmsr r7 /* out of line this ? */ + blr +1: + /* Some pre-nap cleanups needed on some CPUs */ + andis. r0,r3,HID0_NAP@h + beq 2f +BEGIN_FTR_SECTION + /* Disable L2 prefetch on some 745x and try to ensure + * L2 prefetch engines are idle. As explained by errata + * text, we can't be sure they are, we just hope very hard + * that well be enough (sic !). At least I noticed Apple + * doesn't even bother doing the dcbf's here... + */ + mfspr r4,SPRN_MSSCR0 + rlwinm r4,r4,0,0,29 + sync + mtspr SPRN_MSSCR0,r4 + sync + isync + lis r4,KERNELBASE@h + dcbf 0,r4 + dcbf 0,r4 + dcbf 0,r4 + dcbf 0,r4 +END_FTR_SECTION_IFSET(CPU_FTR_NAP_DISABLE_L2_PR) +#ifdef DEBUG + lis r6,nap_enter_count@ha + lwz r4,nap_enter_count@l(r6) + addi r4,r4,1 + stw r4,nap_enter_count@l(r6) +#endif +2: +BEGIN_FTR_SECTION + /* Go to low speed mode on some 750FX */ + lis r4,powersave_lowspeed@ha + lwz r4,powersave_lowspeed@l(r4) + cmpwi 0,r4,0 + beq 1f + mfspr r4,SPRN_HID1 + oris r4,r4,0x0001 + mtspr SPRN_HID1,r4 +1: +END_FTR_SECTION_IFSET(CPU_FTR_DUAL_PLL_750FX) + + /* Go to NAP or DOZE now */ + mfspr r4,SPRN_HID0 + lis r5,(HID0_NAP|HID0_SLEEP)@h +BEGIN_FTR_SECTION + oris r5,r5,HID0_DOZE@h +END_FTR_SECTION_IFSET(CPU_FTR_CAN_DOZE) + andc r4,r4,r5 + or r4,r4,r3 +BEGIN_FTR_SECTION + oris r4,r4,HID0_DPM@h /* that should be done once for all */ +END_FTR_SECTION_IFCLR(CPU_FTR_NO_DPM) + mtspr SPRN_HID0,r4 +BEGIN_FTR_SECTION + DSSALL + sync +END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) + ori r7,r7,MSR_EE /* Could be ommited (already set) */ + oris r7,r7,MSR_POW@h + sync + isync + mtmsr r7 + isync + sync + blr + +/* + * Return from NAP/DOZE mode, restore some CPU specific registers, + * we are called with DR/IR still off and r2 containing physical + * address of current. + */ +_GLOBAL(power_save_6xx_restore) + mfspr r11,SPRN_HID0 + rlwinm. r11,r11,0,10,8 /* Clear NAP & copy NAP bit !state to cr1 EQ */ + cror 4*cr1+eq,4*cr0+eq,4*cr0+eq +BEGIN_FTR_SECTION + rlwinm r11,r11,0,9,7 /* Clear DOZE */ +END_FTR_SECTION_IFSET(CPU_FTR_CAN_DOZE) + mtspr SPRN_HID0, r11 + +#ifdef DEBUG + beq cr1,1f + lis r11,(nap_return_count-KERNELBASE)@ha + lwz r9,nap_return_count@l(r11) + addi r9,r9,1 + stw r9,nap_return_count@l(r11) +1: +#endif + + rlwinm r9,r1,0,0,18 + tophys(r9,r9) + lwz r11,TI_CPU(r9) + slwi r11,r11,2 + /* Todo make sure all these are in the same page + * and load r22 (@ha part + CPU offset) only once + */ +BEGIN_FTR_SECTION + beq cr1,1f + addis r9,r11,(nap_save_msscr0-KERNELBASE)@ha + lwz r9,nap_save_msscr0@l(r9) + mtspr SPRN_MSSCR0, r9 + sync + isync +1: +END_FTR_SECTION_IFSET(CPU_FTR_NAP_DISABLE_L2_PR) +BEGIN_FTR_SECTION + addis r9,r11,(nap_save_hid1-KERNELBASE)@ha + lwz r9,nap_save_hid1@l(r9) + mtspr SPRN_HID1, r9 +END_FTR_SECTION_IFSET(CPU_FTR_DUAL_PLL_750FX) + b transfer_to_handler_cont + + .data + +_GLOBAL(nap_save_msscr0) + .space 4*NR_CPUS + +_GLOBAL(nap_save_hid1) + .space 4*NR_CPUS + +_GLOBAL(powersave_nap) + .long 0 +_GLOBAL(powersave_lowspeed) + .long 0 + +#ifdef DEBUG +_GLOBAL(nap_enter_count) + .space 4 +_GLOBAL(nap_return_count) + .space 4 +#endif diff --git a/arch/powerpc/kernel/idle_power4.S b/arch/powerpc/kernel/idle_power4.S new file mode 100644 index 000000000000..1494e2f177f7 --- /dev/null +++ b/arch/powerpc/kernel/idle_power4.S @@ -0,0 +1,78 @@ +/* + * This file contains the power_save function for 6xx & 7xxx CPUs + * rewritten in assembler + * + * Warning ! This code assumes that if your machine has a 750fx + * it will have PLL 1 set to low speed mode (used during NAP/DOZE). + * if this is not the case some additional changes will have to + * be done to check a runtime var (a bit like powersave-nap) + * + * 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/threads.h> +#include <asm/processor.h> +#include <asm/page.h> +#include <asm/cputable.h> +#include <asm/thread_info.h> +#include <asm/ppc_asm.h> +#include <asm/asm-offsets.h> + +#undef DEBUG + + .text + +/* + * Here is the power_save_6xx function. This could eventually be + * split into several functions & changing the function pointer + * depending on the various features. + */ +_GLOBAL(power4_idle) +BEGIN_FTR_SECTION + blr +END_FTR_SECTION_IFCLR(CPU_FTR_CAN_NAP) + /* We must dynamically check for the NAP feature as it + * can be cleared by CPU init after the fixups are done + */ + LOADBASE(r3,cur_cpu_spec) + ld r4,OFF(cur_cpu_spec)(r3) + ld r4,CPU_SPEC_FEATURES(r4) + andi. r0,r4,CPU_FTR_CAN_NAP + beqlr + /* Now check if user or arch enabled NAP mode */ + LOADBASE(r3,powersave_nap) + lwz r4,OFF(powersave_nap)(r3) + cmpwi 0,r4,0 + beqlr + + /* Clear MSR:EE */ + mfmsr r7 + li r4,0 + ori r4,r4,MSR_EE + andc r0,r7,r4 + mtmsrd r0 + + /* Check current_thread_info()->flags */ + clrrdi r4,r1,THREAD_SHIFT + ld r4,TI_FLAGS(r4) + andi. r0,r4,_TIF_NEED_RESCHED + beq 1f + mtmsrd r7 /* out of line this ? */ + blr +1: + /* Go to NAP now */ +BEGIN_FTR_SECTION + DSSALL + sync +END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) + oris r7,r7,MSR_POW@h + sync + isync + mtmsrd r7 + isync + sync + blr diff --git a/arch/powerpc/kernel/init_task.c b/arch/powerpc/kernel/init_task.c new file mode 100644 index 000000000000..941043ae040f --- /dev/null +++ b/arch/powerpc/kernel/init_task.c @@ -0,0 +1,36 @@ +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <linux/init.h> +#include <linux/init_task.h> +#include <linux/fs.h> +#include <linux/mqueue.h> +#include <asm/uaccess.h> + +static struct fs_struct init_fs = INIT_FS; +static struct files_struct init_files = INIT_FILES; +static struct signal_struct init_signals = INIT_SIGNALS(init_signals); +static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); +struct mm_struct init_mm = INIT_MM(init_mm); + +EXPORT_SYMBOL(init_mm); + +/* + * Initial thread structure. + * + * We need to make sure that this is 16384-byte aligned due to the + * way process stacks are handled. This is done by having a special + * "init_task" linker map entry.. + */ +union thread_union init_thread_union + __attribute__((__section__(".data.init_task"))) = + { INIT_THREAD_INFO(init_task) }; + +/* + * Initial task structure. + * + * All other task structs will be allocated on slabs in fork.c + */ +struct task_struct init_task = INIT_TASK(init_task); + +EXPORT_SYMBOL(init_task); diff --git a/arch/powerpc/kernel/lparmap.c b/arch/powerpc/kernel/lparmap.c new file mode 100644 index 000000000000..b81de286df5e --- /dev/null +++ b/arch/powerpc/kernel/lparmap.c @@ -0,0 +1,31 @@ +/* + * Copyright (C) 2005 Stephen Rothwell 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 <asm/mmu.h> +#include <asm/page.h> +#include <asm/iSeries/LparMap.h> + +const struct LparMap __attribute__((__section__(".text"))) xLparMap = { + .xNumberEsids = HvEsidsToMap, + .xNumberRanges = HvRangesToMap, + .xSegmentTableOffs = STAB0_PAGE, + + .xEsids = { + { .xKernelEsid = GET_ESID(KERNELBASE), + .xKernelVsid = KERNEL_VSID(KERNELBASE), }, + { .xKernelEsid = GET_ESID(VMALLOCBASE), + .xKernelVsid = KERNEL_VSID(VMALLOCBASE), }, + }, + + .xRanges = { + { .xPages = HvPagesToMap, + .xOffset = 0, + .xVPN = KERNEL_VSID(KERNELBASE) << (SID_SHIFT - PAGE_SHIFT), + }, + }, +}; diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S new file mode 100644 index 000000000000..3bedb532aed9 --- /dev/null +++ b/arch/powerpc/kernel/misc_32.S @@ -0,0 +1,1037 @@ +/* + * This file contains miscellaneous low-level functions. + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) + * + * Largely rewritten by Cort Dougan (cort@cs.nmt.edu) + * and 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/config.h> +#include <linux/sys.h> +#include <asm/unistd.h> +#include <asm/errno.h> +#include <asm/reg.h> +#include <asm/page.h> +#include <asm/cache.h> +#include <asm/cputable.h> +#include <asm/mmu.h> +#include <asm/ppc_asm.h> +#include <asm/thread_info.h> +#include <asm/asm-offsets.h> + + .text + + .align 5 +_GLOBAL(__delay) + cmpwi 0,r3,0 + mtctr r3 + beqlr +1: bdnz 1b + blr + +/* + * This returns the high 64 bits of the product of two 64-bit numbers. + */ +_GLOBAL(mulhdu) + cmpwi r6,0 + cmpwi cr1,r3,0 + mr r10,r4 + mulhwu r4,r4,r5 + beq 1f + mulhwu r0,r10,r6 + mullw r7,r10,r5 + addc r7,r0,r7 + addze r4,r4 +1: beqlr cr1 /* all done if high part of A is 0 */ + mr r10,r3 + mullw r9,r3,r5 + mulhwu r3,r3,r5 + beq 2f + mullw r0,r10,r6 + mulhwu r8,r10,r6 + addc r7,r0,r7 + adde r4,r4,r8 + addze r3,r3 +2: addc r4,r4,r9 + addze r3,r3 + blr + +/* + * Returns (address we're running at) - (address we were linked at) + * for use before the text and data are mapped to KERNELBASE. + */ +_GLOBAL(reloc_offset) + mflr r0 + bl 1f +1: mflr r3 + LOADADDR(r4,1b) + subf r3,r4,r3 + mtlr r0 + blr + +/* + * add_reloc_offset(x) returns x + reloc_offset(). + */ +_GLOBAL(add_reloc_offset) + mflr r0 + bl 1f +1: mflr r5 + LOADADDR(r4,1b) + subf r5,r4,r5 + add r3,r3,r5 + mtlr r0 + blr + +/* + * sub_reloc_offset(x) returns x - reloc_offset(). + */ +_GLOBAL(sub_reloc_offset) + mflr r0 + bl 1f +1: mflr r5 + lis r4,1b@ha + addi r4,r4,1b@l + subf r5,r4,r5 + subf r3,r5,r3 + mtlr r0 + blr + +/* + * reloc_got2 runs through the .got2 section adding an offset + * to each entry. + */ +_GLOBAL(reloc_got2) + mflr r11 + lis r7,__got2_start@ha + addi r7,r7,__got2_start@l + lis r8,__got2_end@ha + addi r8,r8,__got2_end@l + subf r8,r7,r8 + srwi. r8,r8,2 + beqlr + mtctr r8 + bl 1f +1: mflr r0 + lis r4,1b@ha + addi r4,r4,1b@l + subf r0,r4,r0 + add r7,r0,r7 +2: lwz r0,0(r7) + add r0,r0,r3 + stw r0,0(r7) + addi r7,r7,4 + bdnz 2b + mtlr r11 + blr + +/* + * identify_cpu, + * called with r3 = data offset and r4 = CPU number + * doesn't change r3 + */ +_GLOBAL(identify_cpu) + addis r8,r3,cpu_specs@ha + addi r8,r8,cpu_specs@l + mfpvr r7 +1: + lwz r5,CPU_SPEC_PVR_MASK(r8) + and r5,r5,r7 + lwz r6,CPU_SPEC_PVR_VALUE(r8) + cmplw 0,r6,r5 + beq 1f + addi r8,r8,CPU_SPEC_ENTRY_SIZE + b 1b +1: + addis r6,r3,cur_cpu_spec@ha + addi r6,r6,cur_cpu_spec@l + sub r8,r8,r3 + stw r8,0(r6) + blr + +/* + * do_cpu_ftr_fixups - goes through the list of CPU feature fixups + * and writes nop's over sections of code that don't apply for this cpu. + * r3 = data offset (not changed) + */ +_GLOBAL(do_cpu_ftr_fixups) + /* Get CPU 0 features */ + addis r6,r3,cur_cpu_spec@ha + addi r6,r6,cur_cpu_spec@l + lwz r4,0(r6) + add r4,r4,r3 + lwz r4,CPU_SPEC_FEATURES(r4) + + /* Get the fixup table */ + addis r6,r3,__start___ftr_fixup@ha + addi r6,r6,__start___ftr_fixup@l + addis r7,r3,__stop___ftr_fixup@ha + addi r7,r7,__stop___ftr_fixup@l + + /* Do the fixup */ +1: cmplw 0,r6,r7 + bgelr + addi r6,r6,16 + lwz r8,-16(r6) /* mask */ + and r8,r8,r4 + lwz r9,-12(r6) /* value */ + cmplw 0,r8,r9 + beq 1b + lwz r8,-8(r6) /* section begin */ + lwz r9,-4(r6) /* section end */ + subf. r9,r8,r9 + beq 1b + /* write nops over the section of code */ + /* todo: if large section, add a branch at the start of it */ + srwi r9,r9,2 + mtctr r9 + add r8,r8,r3 + lis r0,0x60000000@h /* nop */ +3: stw r0,0(r8) + andi. r10,r4,CPU_FTR_SPLIT_ID_CACHE@l + beq 2f + dcbst 0,r8 /* suboptimal, but simpler */ + sync + icbi 0,r8 +2: addi r8,r8,4 + bdnz 3b + sync /* additional sync needed on g4 */ + isync + b 1b + +/* + * call_setup_cpu - call the setup_cpu function for this cpu + * r3 = data offset, r24 = cpu number + * + * Setup function is called with: + * r3 = data offset + * r4 = ptr to CPU spec (relocated) + */ +_GLOBAL(call_setup_cpu) + addis r4,r3,cur_cpu_spec@ha + addi r4,r4,cur_cpu_spec@l + lwz r4,0(r4) + add r4,r4,r3 + lwz r5,CPU_SPEC_SETUP(r4) + cmpi 0,r5,0 + add r5,r5,r3 + beqlr + mtctr r5 + bctr + +#if defined(CONFIG_CPU_FREQ_PMAC) && defined(CONFIG_6xx) + +/* This gets called by via-pmu.c to switch the PLL selection + * on 750fx CPU. This function should really be moved to some + * other place (as most of the cpufreq code in via-pmu + */ +_GLOBAL(low_choose_750fx_pll) + /* Clear MSR:EE */ + mfmsr r7 + rlwinm r0,r7,0,17,15 + mtmsr r0 + + /* If switching to PLL1, disable HID0:BTIC */ + cmplwi cr0,r3,0 + beq 1f + mfspr r5,SPRN_HID0 + rlwinm r5,r5,0,27,25 + sync + mtspr SPRN_HID0,r5 + isync + sync + +1: + /* Calc new HID1 value */ + mfspr r4,SPRN_HID1 /* Build a HID1:PS bit from parameter */ + rlwinm r5,r3,16,15,15 /* Clear out HID1:PS from value read */ + rlwinm r4,r4,0,16,14 /* Could have I used rlwimi here ? */ + or r4,r4,r5 + mtspr SPRN_HID1,r4 + + /* Store new HID1 image */ + rlwinm r6,r1,0,0,18 + lwz r6,TI_CPU(r6) + slwi r6,r6,2 + addis r6,r6,nap_save_hid1@ha + stw r4,nap_save_hid1@l(r6) + + /* If switching to PLL0, enable HID0:BTIC */ + cmplwi cr0,r3,0 + bne 1f + mfspr r5,SPRN_HID0 + ori r5,r5,HID0_BTIC + sync + mtspr SPRN_HID0,r5 + isync + sync + +1: + /* Return */ + mtmsr r7 + blr + +_GLOBAL(low_choose_7447a_dfs) + /* Clear MSR:EE */ + mfmsr r7 + rlwinm r0,r7,0,17,15 + mtmsr r0 + + /* Calc new HID1 value */ + mfspr r4,SPRN_HID1 + insrwi r4,r3,1,9 /* insert parameter into bit 9 */ + sync + mtspr SPRN_HID1,r4 + sync + isync + + /* Return */ + mtmsr r7 + blr + +#endif /* CONFIG_CPU_FREQ_PMAC && CONFIG_6xx */ + +/* + * complement mask on the msr then "or" some values on. + * _nmask_and_or_msr(nmask, value_to_or) + */ +_GLOBAL(_nmask_and_or_msr) + mfmsr r0 /* Get current msr */ + andc r0,r0,r3 /* And off the bits set in r3 (first parm) */ + or r0,r0,r4 /* Or on the bits in r4 (second parm) */ + SYNC /* Some chip revs have problems here... */ + mtmsr r0 /* Update machine state */ + isync + blr /* Done */ + + +/* + * Flush MMU TLB + */ +_GLOBAL(_tlbia) +#if defined(CONFIG_40x) + sync /* Flush to memory before changing mapping */ + tlbia + isync /* Flush shadow TLB */ +#elif defined(CONFIG_44x) + li r3,0 + sync + + /* Load high watermark */ + lis r4,tlb_44x_hwater@ha + lwz r5,tlb_44x_hwater@l(r4) + +1: tlbwe r3,r3,PPC44x_TLB_PAGEID + addi r3,r3,1 + cmpw 0,r3,r5 + ble 1b + + isync +#elif defined(CONFIG_FSL_BOOKE) + /* Invalidate all entries in TLB0 */ + li r3, 0x04 + tlbivax 0,3 + /* Invalidate all entries in TLB1 */ + li r3, 0x0c + tlbivax 0,3 + /* Invalidate all entries in TLB2 */ + li r3, 0x14 + tlbivax 0,3 + /* Invalidate all entries in TLB3 */ + li r3, 0x1c + tlbivax 0,3 + msync +#ifdef CONFIG_SMP + tlbsync +#endif /* CONFIG_SMP */ +#else /* !(CONFIG_40x || CONFIG_44x || CONFIG_FSL_BOOKE) */ +#if defined(CONFIG_SMP) + rlwinm r8,r1,0,0,18 + lwz r8,TI_CPU(r8) + oris r8,r8,10 + mfmsr r10 + SYNC + rlwinm r0,r10,0,17,15 /* clear bit 16 (MSR_EE) */ + rlwinm r0,r0,0,28,26 /* clear DR */ + mtmsr r0 + SYNC_601 + isync + lis r9,mmu_hash_lock@h + ori r9,r9,mmu_hash_lock@l + tophys(r9,r9) +10: lwarx r7,0,r9 + cmpwi 0,r7,0 + bne- 10b + stwcx. r8,0,r9 + bne- 10b + sync + tlbia + sync + TLBSYNC + li r0,0 + stw r0,0(r9) /* clear mmu_hash_lock */ + mtmsr r10 + SYNC_601 + isync +#else /* CONFIG_SMP */ + sync + tlbia + sync +#endif /* CONFIG_SMP */ +#endif /* ! defined(CONFIG_40x) */ + blr + +/* + * Flush MMU TLB for a particular address + */ +_GLOBAL(_tlbie) +#if defined(CONFIG_40x) + tlbsx. r3, 0, r3 + bne 10f + sync + /* There are only 64 TLB entries, so r3 < 64, which means bit 25 is clear. + * Since 25 is the V bit in the TLB_TAG, loading this value will invalidate + * the TLB entry. */ + tlbwe r3, r3, TLB_TAG + isync +10: +#elif defined(CONFIG_44x) + mfspr r4,SPRN_MMUCR + mfspr r5,SPRN_PID /* Get PID */ + rlwimi r4,r5,0,24,31 /* Set TID */ + mtspr SPRN_MMUCR,r4 + + tlbsx. r3, 0, r3 + bne 10f + sync + /* There are only 64 TLB entries, so r3 < 64, + * which means bit 22, is clear. Since 22 is + * the V bit in the TLB_PAGEID, loading this + * value will invalidate the TLB entry. + */ + tlbwe r3, r3, PPC44x_TLB_PAGEID + isync +10: +#elif defined(CONFIG_FSL_BOOKE) + rlwinm r4, r3, 0, 0, 19 + ori r5, r4, 0x08 /* TLBSEL = 1 */ + ori r6, r4, 0x10 /* TLBSEL = 2 */ + ori r7, r4, 0x18 /* TLBSEL = 3 */ + tlbivax 0, r4 + tlbivax 0, r5 + tlbivax 0, r6 + tlbivax 0, r7 + msync +#if defined(CONFIG_SMP) + tlbsync +#endif /* CONFIG_SMP */ +#else /* !(CONFIG_40x || CONFIG_44x || CONFIG_FSL_BOOKE) */ +#if defined(CONFIG_SMP) + rlwinm r8,r1,0,0,18 + lwz r8,TI_CPU(r8) + oris r8,r8,11 + mfmsr r10 + SYNC + rlwinm r0,r10,0,17,15 /* clear bit 16 (MSR_EE) */ + rlwinm r0,r0,0,28,26 /* clear DR */ + mtmsr r0 + SYNC_601 + isync + lis r9,mmu_hash_lock@h + ori r9,r9,mmu_hash_lock@l + tophys(r9,r9) +10: lwarx r7,0,r9 + cmpwi 0,r7,0 + bne- 10b + stwcx. r8,0,r9 + bne- 10b + eieio + tlbie r3 + sync + TLBSYNC + li r0,0 + stw r0,0(r9) /* clear mmu_hash_lock */ + mtmsr r10 + SYNC_601 + isync +#else /* CONFIG_SMP */ + tlbie r3 + sync +#endif /* CONFIG_SMP */ +#endif /* ! CONFIG_40x */ + blr + +/* + * Flush instruction cache. + * This is a no-op on the 601. + */ +_GLOBAL(flush_instruction_cache) +#if defined(CONFIG_8xx) + isync + lis r5, IDC_INVALL@h + mtspr SPRN_IC_CST, r5 +#elif defined(CONFIG_4xx) +#ifdef CONFIG_403GCX + li r3, 512 + mtctr r3 + lis r4, KERNELBASE@h +1: iccci 0, r4 + addi r4, r4, 16 + bdnz 1b +#else + lis r3, KERNELBASE@h + iccci 0,r3 +#endif +#elif CONFIG_FSL_BOOKE +BEGIN_FTR_SECTION + mfspr r3,SPRN_L1CSR0 + ori r3,r3,L1CSR0_CFI|L1CSR0_CLFC + /* msync; isync recommended here */ + mtspr SPRN_L1CSR0,r3 + isync + blr +END_FTR_SECTION_IFCLR(CPU_FTR_SPLIT_ID_CACHE) + mfspr r3,SPRN_L1CSR1 + ori r3,r3,L1CSR1_ICFI|L1CSR1_ICLFR + mtspr SPRN_L1CSR1,r3 +#else + mfspr r3,SPRN_PVR + rlwinm r3,r3,16,16,31 + cmpwi 0,r3,1 + beqlr /* for 601, do nothing */ + /* 603/604 processor - use invalidate-all bit in HID0 */ + mfspr r3,SPRN_HID0 + ori r3,r3,HID0_ICFI + mtspr SPRN_HID0,r3 +#endif /* CONFIG_8xx/4xx */ + isync + blr + +/* + * Write any modified data cache blocks out to memory + * and invalidate the corresponding instruction cache blocks. + * This is a no-op on the 601. + * + * flush_icache_range(unsigned long start, unsigned long stop) + */ +_GLOBAL(flush_icache_range) +BEGIN_FTR_SECTION + blr /* for 601, do nothing */ +END_FTR_SECTION_IFCLR(CPU_FTR_SPLIT_ID_CACHE) + li r5,L1_CACHE_BYTES-1 + andc r3,r3,r5 + subf r4,r3,r4 + add r4,r4,r5 + srwi. r4,r4,L1_CACHE_SHIFT + beqlr + mtctr r4 + mr r6,r3 +1: dcbst 0,r3 + addi r3,r3,L1_CACHE_BYTES + bdnz 1b + sync /* wait for dcbst's to get to ram */ + mtctr r4 +2: icbi 0,r6 + addi r6,r6,L1_CACHE_BYTES + bdnz 2b + sync /* additional sync needed on g4 */ + isync + blr +/* + * Write any modified data cache blocks out to memory. + * Does not invalidate the corresponding cache lines (especially for + * any corresponding instruction cache). + * + * clean_dcache_range(unsigned long start, unsigned long stop) + */ +_GLOBAL(clean_dcache_range) + li r5,L1_CACHE_BYTES-1 + andc r3,r3,r5 + subf r4,r3,r4 + add r4,r4,r5 + srwi. r4,r4,L1_CACHE_SHIFT + beqlr + mtctr r4 + +1: dcbst 0,r3 + addi r3,r3,L1_CACHE_BYTES + bdnz 1b + sync /* wait for dcbst's to get to ram */ + blr + +/* + * Write any modified data cache blocks out to memory and invalidate them. + * Does not invalidate the corresponding instruction cache blocks. + * + * flush_dcache_range(unsigned long start, unsigned long stop) + */ +_GLOBAL(flush_dcache_range) + li r5,L1_CACHE_BYTES-1 + andc r3,r3,r5 + subf r4,r3,r4 + add r4,r4,r5 + srwi. r4,r4,L1_CACHE_SHIFT + beqlr + mtctr r4 + +1: dcbf 0,r3 + addi r3,r3,L1_CACHE_BYTES + bdnz 1b + sync /* wait for dcbst's to get to ram */ + blr + +/* + * Like above, but invalidate the D-cache. This is used by the 8xx + * to invalidate the cache so the PPC core doesn't get stale data + * from the CPM (no cache snooping here :-). + * + * invalidate_dcache_range(unsigned long start, unsigned long stop) + */ +_GLOBAL(invalidate_dcache_range) + li r5,L1_CACHE_BYTES-1 + andc r3,r3,r5 + subf r4,r3,r4 + add r4,r4,r5 + srwi. r4,r4,L1_CACHE_SHIFT + beqlr + mtctr r4 + +1: dcbi 0,r3 + addi r3,r3,L1_CACHE_BYTES + bdnz 1b + 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* + * snoop from the data cache. + * This is a no-op on the 601 which has a unified cache. + * + * void __flush_dcache_icache(void *page) + */ +_GLOBAL(__flush_dcache_icache) +BEGIN_FTR_SECTION + blr /* for 601, do nothing */ +END_FTR_SECTION_IFCLR(CPU_FTR_SPLIT_ID_CACHE) + rlwinm r3,r3,0,0,19 /* Get page base address */ + li r4,4096/L1_CACHE_BYTES /* Number of lines in a page */ + mtctr r4 + mr r6,r3 +0: dcbst 0,r3 /* Write line to ram */ + addi r3,r3,L1_CACHE_BYTES + bdnz 0b + sync + mtctr r4 +1: icbi 0,r6 + addi r6,r6,L1_CACHE_BYTES + bdnz 1b + sync + isync + blr + +/* + * Flush a particular page from the data cache to RAM, identified + * by its physical address. We turn off the MMU so we can just use + * the physical address (this may be a highmem page without a kernel + * mapping). + * + * void __flush_dcache_icache_phys(unsigned long physaddr) + */ +_GLOBAL(__flush_dcache_icache_phys) +BEGIN_FTR_SECTION + blr /* for 601, do nothing */ +END_FTR_SECTION_IFCLR(CPU_FTR_SPLIT_ID_CACHE) + mfmsr r10 + rlwinm r0,r10,0,28,26 /* clear DR */ + mtmsr r0 + isync + rlwinm r3,r3,0,0,19 /* Get page base address */ + li r4,4096/L1_CACHE_BYTES /* Number of lines in a page */ + mtctr r4 + mr r6,r3 +0: dcbst 0,r3 /* Write line to ram */ + addi r3,r3,L1_CACHE_BYTES + bdnz 0b + sync + mtctr r4 +1: icbi 0,r6 + addi r6,r6,L1_CACHE_BYTES + bdnz 1b + sync + mtmsr r10 /* restore DR */ + isync + blr + +/* + * Clear pages using the dcbz instruction, which doesn't cause any + * memory traffic (except to write out any cache lines which get + * displaced). This only works on cacheable memory. + * + * void clear_pages(void *page, int order) ; + */ +_GLOBAL(clear_pages) + li r0,4096/L1_CACHE_BYTES + slw r0,r0,r4 + mtctr r0 +#ifdef CONFIG_8xx + li r4, 0 +1: stw r4, 0(r3) + stw r4, 4(r3) + stw r4, 8(r3) + stw r4, 12(r3) +#else +1: dcbz 0,r3 +#endif + addi r3,r3,L1_CACHE_BYTES + bdnz 1b + blr + +/* + * Copy a whole page. We use the dcbz instruction on the destination + * to reduce memory traffic (it eliminates the unnecessary reads of + * the destination into cache). This requires that the destination + * is cacheable. + */ +#define COPY_16_BYTES \ + lwz r6,4(r4); \ + lwz r7,8(r4); \ + lwz r8,12(r4); \ + lwzu r9,16(r4); \ + stw r6,4(r3); \ + stw r7,8(r3); \ + stw r8,12(r3); \ + stwu r9,16(r3) + +_GLOBAL(copy_page) + addi r3,r3,-4 + addi r4,r4,-4 + +#ifdef CONFIG_8xx + /* don't use prefetch on 8xx */ + li r0,4096/L1_CACHE_BYTES + mtctr r0 +1: COPY_16_BYTES + bdnz 1b + blr + +#else /* not 8xx, we can prefetch */ + li r5,4 + +#if MAX_COPY_PREFETCH > 1 + li r0,MAX_COPY_PREFETCH + li r11,4 + mtctr r0 +11: dcbt r11,r4 + addi r11,r11,L1_CACHE_BYTES + bdnz 11b +#else /* MAX_COPY_PREFETCH == 1 */ + dcbt r5,r4 + li r11,L1_CACHE_BYTES+4 +#endif /* MAX_COPY_PREFETCH */ + li r0,4096/L1_CACHE_BYTES - MAX_COPY_PREFETCH + crclr 4*cr0+eq +2: + mtctr r0 +1: + dcbt r11,r4 + dcbz r5,r3 + COPY_16_BYTES +#if L1_CACHE_BYTES >= 32 + COPY_16_BYTES +#if L1_CACHE_BYTES >= 64 + COPY_16_BYTES + COPY_16_BYTES +#if L1_CACHE_BYTES >= 128 + COPY_16_BYTES + COPY_16_BYTES + COPY_16_BYTES + COPY_16_BYTES +#endif +#endif +#endif + bdnz 1b + beqlr + crnot 4*cr0+eq,4*cr0+eq + li r0,MAX_COPY_PREFETCH + li r11,4 + b 2b +#endif /* CONFIG_8xx */ + +/* + * void atomic_clear_mask(atomic_t mask, atomic_t *addr) + * void atomic_set_mask(atomic_t mask, atomic_t *addr); + */ +_GLOBAL(atomic_clear_mask) +10: lwarx r5,0,r4 + andc r5,r5,r3 + PPC405_ERR77(0,r4) + stwcx. r5,0,r4 + bne- 10b + blr +_GLOBAL(atomic_set_mask) +10: lwarx r5,0,r4 + or r5,r5,r3 + PPC405_ERR77(0,r4) + stwcx. r5,0,r4 + bne- 10b + blr + +/* + * I/O string operations + * + * insb(port, buf, len) + * outsb(port, buf, len) + * insw(port, buf, len) + * outsw(port, buf, len) + * insl(port, buf, len) + * outsl(port, buf, len) + * insw_ns(port, buf, len) + * outsw_ns(port, buf, len) + * insl_ns(port, buf, len) + * outsl_ns(port, buf, len) + * + * The *_ns versions don't do byte-swapping. + */ +_GLOBAL(_insb) + cmpwi 0,r5,0 + mtctr r5 + subi r4,r4,1 + blelr- +00: lbz r5,0(r3) + eieio + stbu r5,1(r4) + bdnz 00b + blr + +_GLOBAL(_outsb) + cmpwi 0,r5,0 + mtctr r5 + subi r4,r4,1 + blelr- +00: lbzu r5,1(r4) + stb r5,0(r3) + eieio + bdnz 00b + blr + +_GLOBAL(_insw) + cmpwi 0,r5,0 + mtctr r5 + subi r4,r4,2 + blelr- +00: lhbrx r5,0,r3 + eieio + sthu r5,2(r4) + bdnz 00b + blr + +_GLOBAL(_outsw) + cmpwi 0,r5,0 + mtctr r5 + subi r4,r4,2 + blelr- +00: lhzu r5,2(r4) + eieio + sthbrx r5,0,r3 + bdnz 00b + blr + +_GLOBAL(_insl) + cmpwi 0,r5,0 + mtctr r5 + subi r4,r4,4 + blelr- +00: lwbrx r5,0,r3 + eieio + stwu r5,4(r4) + bdnz 00b + blr + +_GLOBAL(_outsl) + cmpwi 0,r5,0 + mtctr r5 + subi r4,r4,4 + blelr- +00: lwzu r5,4(r4) + stwbrx r5,0,r3 + eieio + bdnz 00b + blr + +_GLOBAL(__ide_mm_insw) +_GLOBAL(_insw_ns) + cmpwi 0,r5,0 + mtctr r5 + subi r4,r4,2 + blelr- +00: lhz r5,0(r3) + eieio + sthu r5,2(r4) + bdnz 00b + blr + +_GLOBAL(__ide_mm_outsw) +_GLOBAL(_outsw_ns) + cmpwi 0,r5,0 + mtctr r5 + subi r4,r4,2 + blelr- +00: lhzu r5,2(r4) + sth r5,0(r3) + eieio + bdnz 00b + blr + +_GLOBAL(__ide_mm_insl) +_GLOBAL(_insl_ns) + cmpwi 0,r5,0 + mtctr r5 + subi r4,r4,4 + blelr- +00: lwz r5,0(r3) + eieio + stwu r5,4(r4) + bdnz 00b + blr + +_GLOBAL(__ide_mm_outsl) +_GLOBAL(_outsl_ns) + cmpwi 0,r5,0 + mtctr r5 + subi r4,r4,4 + blelr- +00: lwzu r5,4(r4) + stw r5,0(r3) + eieio + bdnz 00b + blr + +/* + * Extended precision shifts. + * + * Updated to be valid for shift counts from 0 to 63 inclusive. + * -- Gabriel + * + * R3/R4 has 64 bit value + * R5 has shift count + * result in R3/R4 + * + * ashrdi3: arithmetic right shift (sign propagation) + * lshrdi3: logical right shift + * ashldi3: left shift + */ +_GLOBAL(__ashrdi3) + subfic r6,r5,32 + srw r4,r4,r5 # LSW = count > 31 ? 0 : LSW >> count + addi r7,r5,32 # could be xori, or addi with -32 + slw r6,r3,r6 # t1 = count > 31 ? 0 : MSW << (32-count) + rlwinm r8,r7,0,32 # t3 = (count < 32) ? 32 : 0 + sraw r7,r3,r7 # t2 = MSW >> (count-32) + or r4,r4,r6 # LSW |= t1 + slw r7,r7,r8 # t2 = (count < 32) ? 0 : t2 + sraw r3,r3,r5 # MSW = MSW >> count + or r4,r4,r7 # LSW |= t2 + blr + +_GLOBAL(__ashldi3) + subfic r6,r5,32 + slw r3,r3,r5 # MSW = count > 31 ? 0 : MSW << count + addi r7,r5,32 # could be xori, or addi with -32 + srw r6,r4,r6 # t1 = count > 31 ? 0 : LSW >> (32-count) + slw r7,r4,r7 # t2 = count < 32 ? 0 : LSW << (count-32) + or r3,r3,r6 # MSW |= t1 + slw r4,r4,r5 # LSW = LSW << count + or r3,r3,r7 # MSW |= t2 + blr + +_GLOBAL(__lshrdi3) + subfic r6,r5,32 + srw r4,r4,r5 # LSW = count > 31 ? 0 : LSW >> count + addi r7,r5,32 # could be xori, or addi with -32 + slw r6,r3,r6 # t1 = count > 31 ? 0 : MSW << (32-count) + srw r7,r3,r7 # t2 = count < 32 ? 0 : MSW >> (count-32) + or r4,r4,r6 # LSW |= t1 + srw r3,r3,r5 # MSW = MSW >> count + or r4,r4,r7 # LSW |= t2 + blr + +_GLOBAL(abs) + srawi r4,r3,31 + xor r3,r3,r4 + sub r3,r3,r4 + blr + +_GLOBAL(_get_SP) + mr r3,r1 /* Close enough */ + blr + +/* + * Create a kernel thread + * kernel_thread(fn, arg, flags) + */ +_GLOBAL(kernel_thread) + stwu r1,-16(r1) + stw r30,8(r1) + stw r31,12(r1) + mr r30,r3 /* function */ + mr r31,r4 /* argument */ + ori r3,r5,CLONE_VM /* flags */ + oris r3,r3,CLONE_UNTRACED>>16 + li r4,0 /* new sp (unused) */ + li r0,__NR_clone + sc + cmpwi 0,r3,0 /* parent or child? */ + bne 1f /* return if parent */ + li r0,0 /* make top-level stack frame */ + stwu r0,-16(r1) + mtlr r30 /* fn addr in lr */ + mr r3,r31 /* load arg and call fn */ + PPC440EP_ERR42 + blrl + li r0,__NR_exit /* exit if function returns */ + li r3,0 + sc +1: lwz r30,8(r1) + lwz r31,12(r1) + addi r1,r1,16 + blr + +_GLOBAL(execve) + li r0,__NR_execve + sc + bnslr + neg r3,r3 + blr + +/* + * This routine is just here to keep GCC happy - sigh... + */ +_GLOBAL(__main) + blr diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S new file mode 100644 index 000000000000..b3e95ff0dba0 --- /dev/null +++ b/arch/powerpc/kernel/misc_64.S @@ -0,0 +1,880 @@ +/* + * arch/powerpc/kernel/misc64.S + * + * This file contains miscellaneous low-level functions. + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) + * + * Largely rewritten by Cort Dougan (cort@cs.nmt.edu) + * and Paul Mackerras. + * Adapted for iSeries by Mike Corrigan (mikejc@us.ibm.com) + * PPC64 updates by Dave Engebretsen (engebret@us.ibm.com) + * + * 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/sys.h> +#include <asm/unistd.h> +#include <asm/errno.h> +#include <asm/processor.h> +#include <asm/page.h> +#include <asm/cache.h> +#include <asm/ppc_asm.h> +#include <asm/asm-offsets.h> +#include <asm/cputable.h> +#include <asm/thread_info.h> + + .text + +/* + * Returns (address we are running at) - (address we were linked at) + * for use before the text and data are mapped to KERNELBASE. + */ + +_GLOBAL(reloc_offset) + mflr r0 + bl 1f +1: mflr r3 + LOADADDR(r4,1b) + subf r3,r4,r3 + mtlr r0 + blr + +/* + * add_reloc_offset(x) returns x + reloc_offset(). + */ +_GLOBAL(add_reloc_offset) + mflr r0 + bl 1f +1: mflr r5 + LOADADDR(r4,1b) + subf r5,r4,r5 + add r3,r3,r5 + mtlr r0 + blr + +_GLOBAL(get_msr) + mfmsr r3 + blr + +_GLOBAL(get_dar) + mfdar r3 + blr + +_GLOBAL(get_srr0) + mfsrr0 r3 + blr + +_GLOBAL(get_srr1) + mfsrr1 r3 + blr + +_GLOBAL(get_sp) + mr r3,r1 + blr + +#ifdef CONFIG_IRQSTACKS +_GLOBAL(call_do_softirq) + mflr r0 + std r0,16(r1) + stdu r1,THREAD_SIZE-112(r3) + mr r1,r3 + bl .__do_softirq + ld r1,0(r1) + ld r0,16(r1) + mtlr r0 + blr + +_GLOBAL(call_handle_IRQ_event) + mflr r0 + std r0,16(r1) + stdu r1,THREAD_SIZE-112(r6) + mr r1,r6 + bl .handle_IRQ_event + ld r1,0(r1) + ld r0,16(r1) + mtlr r0 + blr +#endif /* CONFIG_IRQSTACKS */ + + /* + * To be called by C code which needs to do some operations with MMU + * disabled. Note that interrupts have to be disabled by the caller + * prior to calling us. The code called _MUST_ be in the RMO of course + * and part of the linear mapping as we don't attempt to translate the + * stack pointer at all. The function is called with the stack switched + * to this CPU emergency stack + * + * prototype is void *call_with_mmu_off(void *func, void *data); + * + * the called function is expected to be of the form + * + * void *called(void *data); + */ +_GLOBAL(call_with_mmu_off) + mflr r0 /* get link, save it on stackframe */ + std r0,16(r1) + mr r1,r5 /* save old stack ptr */ + ld r1,PACAEMERGSP(r13) /* get emerg. stack */ + subi r1,r1,STACK_FRAME_OVERHEAD + std r0,16(r1) /* save link on emerg. stack */ + std r5,0(r1) /* save old stack ptr in backchain */ + ld r3,0(r3) /* get to real function ptr (assume same TOC) */ + bl 2f /* we need LR to return, continue at label 2 */ + + ld r0,16(r1) /* we return here from the call, get LR and */ + ld r1,0(r1) /* .. old stack ptr */ + mtspr SPRN_SRR0,r0 /* and get back to virtual mode with these */ + mfmsr r4 + ori r4,r4,MSR_IR|MSR_DR + mtspr SPRN_SRR1,r4 + rfid + +2: mtspr SPRN_SRR0,r3 /* coming from above, enter real mode */ + mr r3,r4 /* get parameter */ + mfmsr r0 + ori r0,r0,MSR_IR|MSR_DR + xori r0,r0,MSR_IR|MSR_DR + mtspr SPRN_SRR1,r0 + rfid + + + .section ".toc","aw" +PPC64_CACHES: + .tc ppc64_caches[TC],ppc64_caches + .section ".text" + +/* + * Write any modified data cache blocks out to memory + * and invalidate the corresponding instruction cache blocks. + * + * flush_icache_range(unsigned long start, unsigned long stop) + * + * flush all bytes from start through stop-1 inclusive + */ + +_KPROBE(__flush_icache_range) + +/* + * Flush the data cache to memory + * + * Different systems have different cache line sizes + * and in some cases i-cache and d-cache line sizes differ from + * each other. + */ + ld r10,PPC64_CACHES@toc(r2) + lwz r7,DCACHEL1LINESIZE(r10)/* Get cache line size */ + addi r5,r7,-1 + andc r6,r3,r5 /* round low to line bdy */ + subf r8,r6,r4 /* compute length */ + add r8,r8,r5 /* ensure we get enough */ + lwz r9,DCACHEL1LOGLINESIZE(r10) /* Get log-2 of cache line size */ + srw. r8,r8,r9 /* compute line count */ + beqlr /* nothing to do? */ + mtctr r8 +1: dcbst 0,r6 + add r6,r6,r7 + bdnz 1b + sync + +/* Now invalidate the instruction cache */ + + lwz r7,ICACHEL1LINESIZE(r10) /* Get Icache line size */ + addi r5,r7,-1 + andc r6,r3,r5 /* round low to line bdy */ + subf r8,r6,r4 /* compute length */ + add r8,r8,r5 + lwz r9,ICACHEL1LOGLINESIZE(r10) /* Get log-2 of Icache line size */ + srw. r8,r8,r9 /* compute line count */ + beqlr /* nothing to do? */ + mtctr r8 +2: icbi 0,r6 + add r6,r6,r7 + bdnz 2b + isync + blr + .previous .text +/* + * Like above, but only do the D-cache. + * + * flush_dcache_range(unsigned long start, unsigned long stop) + * + * flush all bytes from start to stop-1 inclusive + */ +_GLOBAL(flush_dcache_range) + +/* + * Flush the data cache to memory + * + * Different systems have different cache line sizes + */ + ld r10,PPC64_CACHES@toc(r2) + lwz r7,DCACHEL1LINESIZE(r10) /* Get dcache line size */ + addi r5,r7,-1 + andc r6,r3,r5 /* round low to line bdy */ + subf r8,r6,r4 /* compute length */ + add r8,r8,r5 /* ensure we get enough */ + lwz r9,DCACHEL1LOGLINESIZE(r10) /* Get log-2 of dcache line size */ + srw. r8,r8,r9 /* compute line count */ + beqlr /* nothing to do? */ + mtctr r8 +0: dcbst 0,r6 + add r6,r6,r7 + bdnz 0b + sync + blr + +/* + * Like above, but works on non-mapped physical addresses. + * Use only for non-LPAR setups ! It also assumes real mode + * is cacheable. Used for flushing out the DART before using + * it as uncacheable memory + * + * flush_dcache_phys_range(unsigned long start, unsigned long stop) + * + * flush all bytes from start to stop-1 inclusive + */ +_GLOBAL(flush_dcache_phys_range) + ld r10,PPC64_CACHES@toc(r2) + lwz r7,DCACHEL1LINESIZE(r10) /* Get dcache line size */ + addi r5,r7,-1 + andc r6,r3,r5 /* round low to line bdy */ + subf r8,r6,r4 /* compute length */ + add r8,r8,r5 /* ensure we get enough */ + lwz r9,DCACHEL1LOGLINESIZE(r10) /* Get log-2 of dcache line size */ + srw. r8,r8,r9 /* compute line count */ + beqlr /* nothing to do? */ + mfmsr r5 /* Disable MMU Data Relocation */ + ori r0,r5,MSR_DR + xori r0,r0,MSR_DR + sync + mtmsr r0 + sync + isync + mtctr r8 +0: dcbst 0,r6 + add r6,r6,r7 + bdnz 0b + sync + isync + mtmsr r5 /* Re-enable MMU Data Relocation */ + sync + isync + blr + +_GLOBAL(flush_inval_dcache_range) + ld r10,PPC64_CACHES@toc(r2) + lwz r7,DCACHEL1LINESIZE(r10) /* Get dcache line size */ + addi r5,r7,-1 + andc r6,r3,r5 /* round low to line bdy */ + subf r8,r6,r4 /* compute length */ + add r8,r8,r5 /* ensure we get enough */ + lwz r9,DCACHEL1LOGLINESIZE(r10)/* Get log-2 of dcache line size */ + srw. r8,r8,r9 /* compute line count */ + beqlr /* nothing to do? */ + sync + isync + mtctr r8 +0: dcbf 0,r6 + add r6,r6,r7 + bdnz 0b + sync + isync + blr + + +/* + * Flush a particular page from the data cache to RAM. + * Note: this is necessary because the instruction cache does *not* + * snoop from the data cache. + * + * void __flush_dcache_icache(void *page) + */ +_GLOBAL(__flush_dcache_icache) +/* + * Flush the data cache to memory + * + * Different systems have different cache line sizes + */ + +/* Flush the dcache */ + ld r7,PPC64_CACHES@toc(r2) + clrrdi r3,r3,PAGE_SHIFT /* Page align */ + lwz r4,DCACHEL1LINESPERPAGE(r7) /* Get # dcache lines per page */ + lwz r5,DCACHEL1LINESIZE(r7) /* Get dcache line size */ + mr r6,r3 + mtctr r4 +0: dcbst 0,r6 + add r6,r6,r5 + bdnz 0b + sync + +/* Now invalidate the icache */ + + lwz r4,ICACHEL1LINESPERPAGE(r7) /* Get # icache lines per page */ + lwz r5,ICACHEL1LINESIZE(r7) /* Get icache line size */ + mtctr r4 +1: icbi 0,r3 + add r3,r3,r5 + bdnz 1b + isync + blr + +/* + * I/O string operations + * + * insb(port, buf, len) + * outsb(port, buf, len) + * insw(port, buf, len) + * outsw(port, buf, len) + * insl(port, buf, len) + * outsl(port, buf, len) + * insw_ns(port, buf, len) + * outsw_ns(port, buf, len) + * insl_ns(port, buf, len) + * outsl_ns(port, buf, len) + * + * The *_ns versions don't do byte-swapping. + */ +_GLOBAL(_insb) + cmpwi 0,r5,0 + mtctr r5 + subi r4,r4,1 + blelr- +00: lbz r5,0(r3) + eieio + stbu r5,1(r4) + bdnz 00b + twi 0,r5,0 + isync + blr + +_GLOBAL(_outsb) + cmpwi 0,r5,0 + mtctr r5 + subi r4,r4,1 + blelr- +00: lbzu r5,1(r4) + stb r5,0(r3) + bdnz 00b + sync + blr + +_GLOBAL(_insw) + cmpwi 0,r5,0 + mtctr r5 + subi r4,r4,2 + blelr- +00: lhbrx r5,0,r3 + eieio + sthu r5,2(r4) + bdnz 00b + twi 0,r5,0 + isync + blr + +_GLOBAL(_outsw) + cmpwi 0,r5,0 + mtctr r5 + subi r4,r4,2 + blelr- +00: lhzu r5,2(r4) + sthbrx r5,0,r3 + bdnz 00b + sync + blr + +_GLOBAL(_insl) + cmpwi 0,r5,0 + mtctr r5 + subi r4,r4,4 + blelr- +00: lwbrx r5,0,r3 + eieio + stwu r5,4(r4) + bdnz 00b + twi 0,r5,0 + isync + blr + +_GLOBAL(_outsl) + cmpwi 0,r5,0 + mtctr r5 + subi r4,r4,4 + blelr- +00: lwzu r5,4(r4) + stwbrx r5,0,r3 + bdnz 00b + sync + blr + +/* _GLOBAL(ide_insw) now in drivers/ide/ide-iops.c */ +_GLOBAL(_insw_ns) + cmpwi 0,r5,0 + mtctr r5 + subi r4,r4,2 + blelr- +00: lhz r5,0(r3) + eieio + sthu r5,2(r4) + bdnz 00b + twi 0,r5,0 + isync + blr + +/* _GLOBAL(ide_outsw) now in drivers/ide/ide-iops.c */ +_GLOBAL(_outsw_ns) + cmpwi 0,r5,0 + mtctr r5 + subi r4,r4,2 + blelr- +00: lhzu r5,2(r4) + sth r5,0(r3) + bdnz 00b + sync + blr + +_GLOBAL(_insl_ns) + cmpwi 0,r5,0 + mtctr r5 + subi r4,r4,4 + blelr- +00: lwz r5,0(r3) + eieio + stwu r5,4(r4) + bdnz 00b + twi 0,r5,0 + isync + blr + +_GLOBAL(_outsl_ns) + cmpwi 0,r5,0 + mtctr r5 + subi r4,r4,4 + blelr- +00: lwzu r5,4(r4) + stw r5,0(r3) + bdnz 00b + sync + blr + +/* + * identify_cpu and calls setup_cpu + * In: r3 = base of the cpu_specs array + * r4 = address of cur_cpu_spec + * r5 = relocation offset + */ +_GLOBAL(identify_cpu) + mfpvr r7 +1: + lwz r8,CPU_SPEC_PVR_MASK(r3) + and r8,r8,r7 + lwz r9,CPU_SPEC_PVR_VALUE(r3) + cmplw 0,r9,r8 + beq 1f + addi r3,r3,CPU_SPEC_ENTRY_SIZE + b 1b +1: + sub r0,r3,r5 + std r0,0(r4) + ld r4,CPU_SPEC_SETUP(r3) + add r4,r4,r5 + ld r4,0(r4) + add r4,r4,r5 + mtctr r4 + /* Calling convention for cpu setup is r3=offset, r4=cur_cpu_spec */ + mr r4,r3 + mr r3,r5 + bctr + +/* + * do_cpu_ftr_fixups - goes through the list of CPU feature fixups + * and writes nop's over sections of code that don't apply for this cpu. + * r3 = data offset (not changed) + */ +_GLOBAL(do_cpu_ftr_fixups) + /* Get CPU 0 features */ + LOADADDR(r6,cur_cpu_spec) + sub r6,r6,r3 + ld r4,0(r6) + sub r4,r4,r3 + ld r4,CPU_SPEC_FEATURES(r4) + /* Get the fixup table */ + LOADADDR(r6,__start___ftr_fixup) + sub r6,r6,r3 + LOADADDR(r7,__stop___ftr_fixup) + sub r7,r7,r3 + /* Do the fixup */ +1: cmpld r6,r7 + bgelr + addi r6,r6,32 + ld r8,-32(r6) /* mask */ + and r8,r8,r4 + ld r9,-24(r6) /* value */ + cmpld r8,r9 + beq 1b + ld r8,-16(r6) /* section begin */ + ld r9,-8(r6) /* section end */ + subf. r9,r8,r9 + beq 1b + /* write nops over the section of code */ + /* todo: if large section, add a branch at the start of it */ + srwi r9,r9,2 + mtctr r9 + sub r8,r8,r3 + lis r0,0x60000000@h /* nop */ +3: stw r0,0(r8) + andi. r10,r4,CPU_FTR_SPLIT_ID_CACHE@l + beq 2f + dcbst 0,r8 /* suboptimal, but simpler */ + sync + icbi 0,r8 +2: addi r8,r8,4 + bdnz 3b + sync /* additional sync needed on g4 */ + isync + b 1b + +#if defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_MAPLE) +/* + * Do an IO access in real mode + */ +_GLOBAL(real_readb) + mfmsr r7 + ori r0,r7,MSR_DR + xori r0,r0,MSR_DR + sync + mtmsrd r0 + sync + isync + mfspr r6,SPRN_HID4 + rldicl r5,r6,32,0 + ori r5,r5,0x100 + rldicl r5,r5,32,0 + sync + mtspr SPRN_HID4,r5 + isync + slbia + isync + lbz r3,0(r3) + sync + mtspr SPRN_HID4,r6 + isync + slbia + isync + mtmsrd r7 + sync + isync + blr + + /* + * Do an IO access in real mode + */ +_GLOBAL(real_writeb) + mfmsr r7 + ori r0,r7,MSR_DR + xori r0,r0,MSR_DR + sync + mtmsrd r0 + sync + isync + mfspr r6,SPRN_HID4 + rldicl r5,r6,32,0 + ori r5,r5,0x100 + rldicl r5,r5,32,0 + sync + mtspr SPRN_HID4,r5 + isync + slbia + isync + stb r3,0(r4) + sync + mtspr SPRN_HID4,r6 + isync + slbia + isync + mtmsrd r7 + sync + isync + blr +#endif /* defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_MAPLE) */ + +/* + * Create a kernel thread + * kernel_thread(fn, arg, flags) + */ +_GLOBAL(kernel_thread) + std r29,-24(r1) + std r30,-16(r1) + stdu r1,-STACK_FRAME_OVERHEAD(r1) + mr r29,r3 + mr r30,r4 + ori r3,r5,CLONE_VM /* flags */ + oris r3,r3,(CLONE_UNTRACED>>16) + li r4,0 /* new sp (unused) */ + li r0,__NR_clone + sc + cmpdi 0,r3,0 /* parent or child? */ + bne 1f /* return if parent */ + li r0,0 + stdu r0,-STACK_FRAME_OVERHEAD(r1) + ld r2,8(r29) + ld r29,0(r29) + mtlr r29 /* fn addr in lr */ + mr r3,r30 /* load arg and call fn */ + blrl + li r0,__NR_exit /* exit after child exits */ + li r3,0 + sc +1: addi r1,r1,STACK_FRAME_OVERHEAD + ld r29,-24(r1) + ld r30,-16(r1) + blr + +/* + * disable_kernel_fp() + * Disable the FPU. + */ +_GLOBAL(disable_kernel_fp) + mfmsr r3 + rldicl r0,r3,(63-MSR_FP_LG),1 + rldicl r3,r0,(MSR_FP_LG+1),0 + mtmsrd r3 /* disable use of fpu now */ + isync + blr + +#ifdef CONFIG_ALTIVEC + +#if 0 /* this has no callers for now */ +/* + * disable_kernel_altivec() + * Disable the VMX. + */ +_GLOBAL(disable_kernel_altivec) + mfmsr r3 + rldicl r0,r3,(63-MSR_VEC_LG),1 + rldicl r3,r0,(MSR_VEC_LG+1),0 + mtmsrd r3 /* disable use of VMX now */ + isync + blr +#endif /* 0 */ + +/* + * giveup_altivec(tsk) + * Disable VMX for the task given as the argument, + * and save the vector registers in its thread_struct. + * Enables the VMX for use in the kernel on return. + */ +_GLOBAL(giveup_altivec) + mfmsr r5 + oris r5,r5,MSR_VEC@h + mtmsrd r5 /* enable use of VMX now */ + isync + cmpdi 0,r3,0 + beqlr- /* if no previous owner, done */ + addi r3,r3,THREAD /* want THREAD of task */ + ld r5,PT_REGS(r3) + cmpdi 0,r5,0 + SAVE_32VRS(0,r4,r3) + mfvscr vr0 + li r4,THREAD_VSCR + stvx vr0,r4,r3 + beq 1f + ld r4,_MSR-STACK_FRAME_OVERHEAD(r5) + lis r3,MSR_VEC@h + andc r4,r4,r3 /* disable FP for previous task */ + std r4,_MSR-STACK_FRAME_OVERHEAD(r5) +1: +#ifndef CONFIG_SMP + li r5,0 + ld r4,last_task_used_altivec@got(r2) + std r5,0(r4) +#endif /* CONFIG_SMP */ + blr + +#endif /* CONFIG_ALTIVEC */ + +_GLOBAL(__setup_cpu_power3) + blr + +_GLOBAL(execve) + li r0,__NR_execve + sc + bnslr + neg r3,r3 + blr + +/* kexec_wait(phys_cpu) + * + * wait for the flag to change, indicating this kernel is going away but + * the slave code for the next one is at addresses 0 to 100. + * + * This is used by all slaves. + * + * Physical (hardware) cpu id should be in r3. + */ +_GLOBAL(kexec_wait) + bl 1f +1: mflr r5 + addi r5,r5,kexec_flag-1b + +99: HMT_LOW +#ifdef CONFIG_KEXEC /* use no memory without kexec */ + lwz r4,0(r5) + cmpwi 0,r4,0 + bnea 0x60 +#endif + b 99b + +/* this can be in text because we won't change it until we are + * running in real anyways + */ +kexec_flag: + .long 0 + + +#ifdef CONFIG_KEXEC + +/* kexec_smp_wait(void) + * + * call with interrupts off + * note: this is a terminal routine, it does not save lr + * + * get phys id from paca + * set paca id to -1 to say we got here + * switch to real mode + * join other cpus in kexec_wait(phys_id) + */ +_GLOBAL(kexec_smp_wait) + lhz r3,PACAHWCPUID(r13) + li r4,-1 + sth r4,PACAHWCPUID(r13) /* let others know we left */ + bl real_mode + b .kexec_wait + +/* + * switch to real mode (turn mmu off) + * we use the early kernel trick that the hardware ignores bits + * 0 and 1 (big endian) of the effective address in real mode + * + * don't overwrite r3 here, it is live for kexec_wait above. + */ +real_mode: /* assume normal blr return */ +1: li r9,MSR_RI + li r10,MSR_DR|MSR_IR + mflr r11 /* return address to SRR0 */ + mfmsr r12 + andc r9,r12,r9 + andc r10,r12,r10 + + mtmsrd r9,1 + mtspr SPRN_SRR1,r10 + mtspr SPRN_SRR0,r11 + rfid + + +/* + * kexec_sequence(newstack, start, image, control, clear_all()) + * + * does the grungy work with stack switching and real mode switches + * also does simple calls to other code + */ + +_GLOBAL(kexec_sequence) + mflr r0 + std r0,16(r1) + + /* switch stacks to newstack -- &kexec_stack.stack */ + stdu r1,THREAD_SIZE-112(r3) + mr r1,r3 + + li r0,0 + std r0,16(r1) + + /* save regs for local vars on new stack. + * yes, we won't go back, but ... + */ + std r31,-8(r1) + std r30,-16(r1) + std r29,-24(r1) + std r28,-32(r1) + std r27,-40(r1) + std r26,-48(r1) + std r25,-56(r1) + + stdu r1,-112-64(r1) + + /* save args into preserved regs */ + mr r31,r3 /* newstack (both) */ + mr r30,r4 /* start (real) */ + mr r29,r5 /* image (virt) */ + mr r28,r6 /* control, unused */ + mr r27,r7 /* clear_all() fn desc */ + mr r26,r8 /* spare */ + lhz r25,PACAHWCPUID(r13) /* get our phys cpu from paca */ + + /* disable interrupts, we are overwriting kernel data next */ + mfmsr r3 + rlwinm r3,r3,0,17,15 + mtmsrd r3,1 + + /* copy dest pages, flush whole dest image */ + mr r3,r29 + bl .kexec_copy_flush /* (image) */ + + /* turn off mmu */ + bl real_mode + + /* clear out hardware hash page table and tlb */ + ld r5,0(r27) /* deref function descriptor */ + mtctr r5 + bctrl /* ppc_md.hash_clear_all(void); */ + +/* + * kexec image calling is: + * the first 0x100 bytes of the entry point are copied to 0 + * + * all slaves branch to slave = 0x60 (absolute) + * slave(phys_cpu_id); + * + * master goes to start = entry point + * start(phys_cpu_id, start, 0); + * + * + * a wrapper is needed to call existing kernels, here is an approximate + * description of one method: + * + * v2: (2.6.10) + * start will be near the boot_block (maybe 0x100 bytes before it?) + * it will have a 0x60, which will b to boot_block, where it will wait + * and 0 will store phys into struct boot-block and load r3 from there, + * copy kernel 0-0x100 and tell slaves to back down to 0x60 again + * + * v1: (2.6.9) + * boot block will have all cpus scanning device tree to see if they + * are the boot cpu ????? + * other device tree differences (prop sizes, va vs pa, etc)... + */ + + /* copy 0x100 bytes starting at start to 0 */ + li r3,0 + mr r4,r30 + li r5,0x100 + li r6,0 + bl .copy_and_flush /* (dest, src, copy limit, start offset) */ +1: /* assume normal blr return */ + + /* release other cpus to the new kernel secondary start at 0x60 */ + mflr r5 + li r6,1 + stw r6,kexec_flag-1b(5) + mr r3,r25 # my phys cpu + mr r4,r30 # start, aka phys mem offset + mtlr 4 + li r5,0 + blr /* image->start(physid, image->start, 0); */ +#endif /* CONFIG_KEXEC */ diff --git a/arch/powerpc/kernel/of_device.c b/arch/powerpc/kernel/of_device.c new file mode 100644 index 000000000000..7065e40e2f42 --- /dev/null +++ b/arch/powerpc/kernel/of_device.c @@ -0,0 +1,276 @@ +#include <linux/config.h> +#include <linux/string.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/mod_devicetable.h> +#include <linux/slab.h> + +#include <asm/errno.h> +#include <asm/of_device.h> + +/** + * of_match_device - Tell if an of_device structure has a matching + * of_match structure + * @ids: array of of device match structures to search in + * @dev: the of device structure to match against + * + * Used by a driver to check whether an of_device present in the + * system is in its list of supported devices. + */ +const struct of_device_id *of_match_device(const struct of_device_id *matches, + const struct of_device *dev) +{ + if (!dev->node) + return NULL; + while (matches->name[0] || matches->type[0] || matches->compatible[0]) { + int match = 1; + if (matches->name[0]) + match &= dev->node->name + && !strcmp(matches->name, dev->node->name); + if (matches->type[0]) + match &= dev->node->type + && !strcmp(matches->type, dev->node->type); + if (matches->compatible[0]) + match &= device_is_compatible(dev->node, + matches->compatible); + if (match) + return matches; + matches++; + } + return NULL; +} + +static int of_platform_bus_match(struct device *dev, struct device_driver *drv) +{ + struct of_device * of_dev = to_of_device(dev); + struct of_platform_driver * of_drv = to_of_platform_driver(drv); + const struct of_device_id * matches = of_drv->match_table; + + if (!matches) + return 0; + + return of_match_device(matches, of_dev) != NULL; +} + +struct of_device *of_dev_get(struct of_device *dev) +{ + struct device *tmp; + + if (!dev) + return NULL; + tmp = get_device(&dev->dev); + if (tmp) + return to_of_device(tmp); + else + return NULL; +} + +void of_dev_put(struct of_device *dev) +{ + if (dev) + put_device(&dev->dev); +} + + +static int of_device_probe(struct device *dev) +{ + int error = -ENODEV; + struct of_platform_driver *drv; + struct of_device *of_dev; + const struct of_device_id *match; + + drv = to_of_platform_driver(dev->driver); + of_dev = to_of_device(dev); + + if (!drv->probe) + return error; + + of_dev_get(of_dev); + + match = of_match_device(drv->match_table, of_dev); + if (match) + error = drv->probe(of_dev, match); + if (error) + of_dev_put(of_dev); + + return error; +} + +static int of_device_remove(struct device *dev) +{ + struct of_device * of_dev = to_of_device(dev); + struct of_platform_driver * drv = to_of_platform_driver(dev->driver); + + if (dev->driver && drv->remove) + drv->remove(of_dev); + return 0; +} + +static int of_device_suspend(struct device *dev, pm_message_t state) +{ + struct of_device * of_dev = to_of_device(dev); + struct of_platform_driver * drv = to_of_platform_driver(dev->driver); + int error = 0; + + if (dev->driver && drv->suspend) + error = drv->suspend(of_dev, state); + return error; +} + +static int of_device_resume(struct device * dev) +{ + struct of_device * of_dev = to_of_device(dev); + struct of_platform_driver * drv = to_of_platform_driver(dev->driver); + int error = 0; + + if (dev->driver && drv->resume) + error = drv->resume(of_dev); + return error; +} + +struct bus_type of_platform_bus_type = { + .name = "of_platform", + .match = of_platform_bus_match, + .suspend = of_device_suspend, + .resume = of_device_resume, +}; + +static int __init of_bus_driver_init(void) +{ + return bus_register(&of_platform_bus_type); +} + +postcore_initcall(of_bus_driver_init); + +int of_register_driver(struct of_platform_driver *drv) +{ + int count = 0; + + /* initialize common driver fields */ + drv->driver.name = drv->name; + drv->driver.bus = &of_platform_bus_type; + drv->driver.probe = of_device_probe; + drv->driver.remove = of_device_remove; + + /* register with core */ + count = driver_register(&drv->driver); + return count ? count : 1; +} + +void of_unregister_driver(struct of_platform_driver *drv) +{ + driver_unregister(&drv->driver); +} + + +static ssize_t dev_show_devspec(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct of_device *ofdev; + + ofdev = to_of_device(dev); + return sprintf(buf, "%s", ofdev->node->full_name); +} + +static DEVICE_ATTR(devspec, S_IRUGO, dev_show_devspec, NULL); + +/** + * of_release_dev - free an of device structure when all users of it are finished. + * @dev: device that's been disconnected + * + * Will be called only by the device core when all users of this of device are + * done. + */ +void of_release_dev(struct device *dev) +{ + struct of_device *ofdev; + + ofdev = to_of_device(dev); + of_node_put(ofdev->node); + kfree(ofdev); +} + +int of_device_register(struct of_device *ofdev) +{ + int rc; + struct of_device **odprop; + + BUG_ON(ofdev->node == NULL); + + odprop = (struct of_device **)get_property(ofdev->node, "linux,device", NULL); + if (!odprop) { + struct property *new_prop; + + new_prop = kmalloc(sizeof(struct property) + sizeof(struct of_device *), + GFP_KERNEL); + if (new_prop == NULL) + return -ENOMEM; + new_prop->name = "linux,device"; + new_prop->length = sizeof(sizeof(struct of_device *)); + new_prop->value = (unsigned char *)&new_prop[1]; + odprop = (struct of_device **)new_prop->value; + *odprop = NULL; + prom_add_property(ofdev->node, new_prop); + } + *odprop = ofdev; + + rc = device_register(&ofdev->dev); + if (rc) + return rc; + + device_create_file(&ofdev->dev, &dev_attr_devspec); + + return 0; +} + +void of_device_unregister(struct of_device *ofdev) +{ + struct of_device **odprop; + + device_remove_file(&ofdev->dev, &dev_attr_devspec); + + odprop = (struct of_device **)get_property(ofdev->node, "linux,device", NULL); + if (odprop) + *odprop = NULL; + + device_unregister(&ofdev->dev); +} + +struct of_device* of_platform_device_create(struct device_node *np, + const char *bus_id, + struct device *parent) +{ + struct of_device *dev; + + dev = kmalloc(sizeof(*dev), GFP_KERNEL); + if (!dev) + return NULL; + memset(dev, 0, sizeof(*dev)); + + dev->node = of_node_get(np); + dev->dma_mask = 0xffffffffUL; + dev->dev.dma_mask = &dev->dma_mask; + dev->dev.parent = parent; + dev->dev.bus = &of_platform_bus_type; + dev->dev.release = of_release_dev; + + strlcpy(dev->dev.bus_id, bus_id, BUS_ID_SIZE); + + if (of_device_register(dev) != 0) { + kfree(dev); + return NULL; + } + + return dev; +} + +EXPORT_SYMBOL(of_match_device); +EXPORT_SYMBOL(of_platform_bus_type); +EXPORT_SYMBOL(of_register_driver); +EXPORT_SYMBOL(of_unregister_driver); +EXPORT_SYMBOL(of_device_register); +EXPORT_SYMBOL(of_device_unregister); +EXPORT_SYMBOL(of_dev_get); +EXPORT_SYMBOL(of_dev_put); +EXPORT_SYMBOL(of_platform_device_create); +EXPORT_SYMBOL(of_release_dev); diff --git a/arch/powerpc/kernel/pmc.c b/arch/powerpc/kernel/pmc.c new file mode 100644 index 000000000000..2d333cc84082 --- /dev/null +++ b/arch/powerpc/kernel/pmc.c @@ -0,0 +1,112 @@ +/* + * arch/powerpc/kernel/pmc.c + * + * Copyright (C) 2004 David Gibson, IBM Corporation. + * Includes code formerly from arch/ppc/kernel/perfmon.c: + * Author: Andy Fleming + * Copyright (c) 2004 Freescale Semiconductor, Inc + * + * 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/errno.h> +#include <linux/spinlock.h> +#include <linux/module.h> + +#include <asm/processor.h> +#include <asm/pmc.h> + +#if defined(CONFIG_FSL_BOOKE) && !defined(CONFIG_E200) +static void dummy_perf(struct pt_regs *regs) +{ + unsigned int pmgc0 = mfpmr(PMRN_PMGC0); + + pmgc0 &= ~PMGC0_PMIE; + mtpmr(PMRN_PMGC0, pmgc0); +} +#elif defined(CONFIG_PPC64) || defined(CONFIG_6xx) + +#ifndef MMCR0_PMAO +#define MMCR0_PMAO 0 +#endif + +/* Ensure exceptions are disabled */ +static void dummy_perf(struct pt_regs *regs) +{ + unsigned int mmcr0 = mfspr(SPRN_MMCR0); + + mmcr0 &= ~(MMCR0_PMXE|MMCR0_PMAO); + mtspr(SPRN_MMCR0, mmcr0); +} +#else +static void dummy_perf(struct pt_regs *regs) +{ +} +#endif + +static DEFINE_SPINLOCK(pmc_owner_lock); +static void *pmc_owner_caller; /* mostly for debugging */ +perf_irq_t perf_irq = dummy_perf; + +int reserve_pmc_hardware(perf_irq_t new_perf_irq) +{ + int err = 0; + + spin_lock(&pmc_owner_lock); + + if (pmc_owner_caller) { + printk(KERN_WARNING "reserve_pmc_hardware: " + "PMC hardware busy (reserved by caller %p)\n", + pmc_owner_caller); + err = -EBUSY; + goto out; + } + + pmc_owner_caller = __builtin_return_address(0); + perf_irq = new_perf_irq ? : dummy_perf; + + out: + spin_unlock(&pmc_owner_lock); + return err; +} +EXPORT_SYMBOL_GPL(reserve_pmc_hardware); + +void release_pmc_hardware(void) +{ + spin_lock(&pmc_owner_lock); + + WARN_ON(! pmc_owner_caller); + + pmc_owner_caller = NULL; + perf_irq = dummy_perf; + + spin_unlock(&pmc_owner_lock); +} +EXPORT_SYMBOL_GPL(release_pmc_hardware); + +#ifdef CONFIG_PPC64 +void power4_enable_pmcs(void) +{ + unsigned long hid0; + + hid0 = mfspr(SPRN_HID0); + hid0 |= 1UL << (63 - 20); + + /* POWER4 requires the following sequence */ + asm volatile( + "sync\n" + "mtspr %1, %0\n" + "mfspr %0, %1\n" + "mfspr %0, %1\n" + "mfspr %0, %1\n" + "mfspr %0, %1\n" + "mfspr %0, %1\n" + "mfspr %0, %1\n" + "isync" : "=&r" (hid0) : "i" (SPRN_HID0), "0" (hid0): + "memory"); +} +#endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c new file mode 100644 index 000000000000..8bc540337ba0 --- /dev/null +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -0,0 +1,273 @@ +#include <linux/config.h> +#include <linux/module.h> +#include <linux/threads.h> +#include <linux/smp.h> +#include <linux/sched.h> +#include <linux/elfcore.h> +#include <linux/string.h> +#include <linux/interrupt.h> +#include <linux/tty.h> +#include <linux/vt_kern.h> +#include <linux/nvram.h> +#include <linux/console.h> +#include <linux/irq.h> +#include <linux/pci.h> +#include <linux/delay.h> +#include <linux/ide.h> +#include <linux/bitops.h> + +#include <asm/page.h> +#include <asm/semaphore.h> +#include <asm/processor.h> +#include <asm/uaccess.h> +#include <asm/io.h> +#include <asm/ide.h> +#include <asm/atomic.h> +#include <asm/checksum.h> +#include <asm/pgtable.h> +#include <asm/tlbflush.h> +#include <linux/adb.h> +#include <linux/cuda.h> +#include <linux/pmu.h> +#include <asm/prom.h> +#include <asm/system.h> +#include <asm/pci-bridge.h> +#include <asm/irq.h> +#include <asm/pmac_feature.h> +#include <asm/dma.h> +#include <asm/machdep.h> +#include <asm/hw_irq.h> +#include <asm/nvram.h> +#include <asm/mmu_context.h> +#include <asm/backlight.h> +#include <asm/time.h> +#include <asm/cputable.h> +#include <asm/btext.h> +#include <asm/div64.h> + +#ifdef CONFIG_8xx +#include <asm/commproc.h> +#endif + +#ifdef CONFIG_PPC32 +extern void transfer_to_handler(void); +extern void do_IRQ(struct pt_regs *regs); +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); + +EXPORT_SYMBOL(clear_pages); +EXPORT_SYMBOL(ISA_DMA_THRESHOLD); +EXPORT_SYMBOL(DMA_MODE_READ); +EXPORT_SYMBOL(DMA_MODE_WRITE); +EXPORT_SYMBOL(__div64_32); + +EXPORT_SYMBOL(do_signal); +EXPORT_SYMBOL(transfer_to_handler); +EXPORT_SYMBOL(do_IRQ); +EXPORT_SYMBOL(machine_check_exception); +EXPORT_SYMBOL(alignment_exception); +EXPORT_SYMBOL(program_check_exception); +EXPORT_SYMBOL(single_step_exception); +EXPORT_SYMBOL(sys_sigreturn); +#endif + +#if defined(CONFIG_PPC_PREP) +EXPORT_SYMBOL(_prep_type); +EXPORT_SYMBOL(ucSystemType); +#endif + +#if !defined(__INLINE_BITOPS) +EXPORT_SYMBOL(set_bit); +EXPORT_SYMBOL(clear_bit); +EXPORT_SYMBOL(change_bit); +EXPORT_SYMBOL(test_and_set_bit); +EXPORT_SYMBOL(test_and_clear_bit); +EXPORT_SYMBOL(test_and_change_bit); +#endif /* __INLINE_BITOPS */ + +EXPORT_SYMBOL(strcpy); +EXPORT_SYMBOL(strncpy); +EXPORT_SYMBOL(strcat); +EXPORT_SYMBOL(strncat); +EXPORT_SYMBOL(strchr); +EXPORT_SYMBOL(strrchr); +EXPORT_SYMBOL(strpbrk); +EXPORT_SYMBOL(strstr); +EXPORT_SYMBOL(strlen); +EXPORT_SYMBOL(strnlen); +EXPORT_SYMBOL(strcmp); +EXPORT_SYMBOL(strncmp); +EXPORT_SYMBOL(strcasecmp); + +EXPORT_SYMBOL(csum_partial); +EXPORT_SYMBOL(csum_partial_copy_generic); +EXPORT_SYMBOL(ip_fast_csum); +EXPORT_SYMBOL(csum_tcpudp_magic); + +EXPORT_SYMBOL(__copy_tofrom_user); +EXPORT_SYMBOL(__clear_user); +EXPORT_SYMBOL(__strncpy_from_user); +EXPORT_SYMBOL(__strnlen_user); + +EXPORT_SYMBOL(_insb); +EXPORT_SYMBOL(_outsb); +EXPORT_SYMBOL(_insw); +EXPORT_SYMBOL(_outsw); +EXPORT_SYMBOL(_insl); +EXPORT_SYMBOL(_outsl); +EXPORT_SYMBOL(_insw_ns); +EXPORT_SYMBOL(_outsw_ns); +EXPORT_SYMBOL(_insl_ns); +EXPORT_SYMBOL(_outsl_ns); +EXPORT_SYMBOL(ioremap); +#ifdef CONFIG_44x +EXPORT_SYMBOL(ioremap64); +#endif +EXPORT_SYMBOL(__ioremap); +EXPORT_SYMBOL(iounmap); +#ifdef CONFIG_PPC32 +EXPORT_SYMBOL(ioremap_bot); /* aka VMALLOC_END */ +#endif + +#if defined(CONFIG_PPC32) && (defined(CONFIG_BLK_DEV_IDE) || defined(CONFIG_BLK_DEV_IDE_MODULE)) +EXPORT_SYMBOL(ppc_ide_md); +#endif + +#if defined(CONFIG_PCI) && defined(CONFIG_PPC32) +EXPORT_SYMBOL(isa_io_base); +EXPORT_SYMBOL(isa_mem_base); +EXPORT_SYMBOL(pci_dram_offset); +EXPORT_SYMBOL(pci_alloc_consistent); +EXPORT_SYMBOL(pci_free_consistent); +EXPORT_SYMBOL(pci_bus_io_base); +EXPORT_SYMBOL(pci_bus_io_base_phys); +EXPORT_SYMBOL(pci_bus_mem_base_phys); +EXPORT_SYMBOL(pci_bus_to_hose); +EXPORT_SYMBOL(pci_resource_to_bus); +EXPORT_SYMBOL(pci_phys_to_bus); +EXPORT_SYMBOL(pci_bus_to_phys); +#endif /* CONFIG_PCI */ + +#ifdef CONFIG_NOT_COHERENT_CACHE +EXPORT_SYMBOL(flush_dcache_all); +#endif + +EXPORT_SYMBOL(start_thread); +EXPORT_SYMBOL(kernel_thread); + +EXPORT_SYMBOL(giveup_fpu); +#ifdef CONFIG_ALTIVEC +EXPORT_SYMBOL(giveup_altivec); +#endif /* CONFIG_ALTIVEC */ +#ifdef CONFIG_SPE +EXPORT_SYMBOL(giveup_spe); +#endif /* CONFIG_SPE */ + +#ifdef CONFIG_PPC64 +EXPORT_SYMBOL(__flush_icache_range); +#else +EXPORT_SYMBOL(flush_instruction_cache); +EXPORT_SYMBOL(flush_icache_range); +EXPORT_SYMBOL(flush_tlb_kernel_range); +EXPORT_SYMBOL(flush_tlb_page); +EXPORT_SYMBOL(_tlbie); +#endif +EXPORT_SYMBOL(flush_dcache_range); + +#ifdef CONFIG_SMP +EXPORT_SYMBOL(smp_call_function); +#ifdef CONFIG_PPC32 +EXPORT_SYMBOL(smp_hw_index); +#endif +#endif + +#ifdef CONFIG_ADB +EXPORT_SYMBOL(adb_request); +EXPORT_SYMBOL(adb_register); +EXPORT_SYMBOL(adb_unregister); +EXPORT_SYMBOL(adb_poll); +EXPORT_SYMBOL(adb_try_handler_change); +#endif /* CONFIG_ADB */ +#ifdef CONFIG_ADB_CUDA +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 +#ifdef CONFIG_VT +EXPORT_SYMBOL(kd_mksound); +#endif +EXPORT_SYMBOL(to_tm); + +#ifdef CONFIG_PPC32 +long long __ashrdi3(long long, int); +long long __ashldi3(long long, int); +long long __lshrdi3(long long, int); +EXPORT_SYMBOL(__ashrdi3); +EXPORT_SYMBOL(__ashldi3); +EXPORT_SYMBOL(__lshrdi3); +#endif + +EXPORT_SYMBOL(memcpy); +EXPORT_SYMBOL(memset); +EXPORT_SYMBOL(memmove); +EXPORT_SYMBOL(memscan); +EXPORT_SYMBOL(memcmp); +EXPORT_SYMBOL(memchr); + +#if defined(CONFIG_FB_VGA16_MODULE) +EXPORT_SYMBOL(screen_info); +#endif + +#ifdef CONFIG_PPC32 +EXPORT_SYMBOL(__delay); +EXPORT_SYMBOL(timer_interrupt); +EXPORT_SYMBOL(irq_desc); +EXPORT_SYMBOL(tb_ticks_per_jiffy); +EXPORT_SYMBOL(console_drivers); +EXPORT_SYMBOL(cacheable_memcpy); +#endif + +EXPORT_SYMBOL(__up); +EXPORT_SYMBOL(__down); +EXPORT_SYMBOL(__down_interruptible); + +#ifdef CONFIG_8xx +EXPORT_SYMBOL(cpm_install_handler); +EXPORT_SYMBOL(cpm_free_handler); +#endif /* CONFIG_8xx */ +#if defined(CONFIG_8xx) || defined(CONFIG_40x) || defined(CONFIG_85xx) ||\ + defined(CONFIG_83xx) +EXPORT_SYMBOL(__res); +#endif + +#ifdef CONFIG_PPC32 +EXPORT_SYMBOL(next_mmu_context); +EXPORT_SYMBOL(set_context); +#endif + +#ifdef CONFIG_PPC_STD_MMU_32 +extern long mol_trampoline; +EXPORT_SYMBOL(mol_trampoline); /* For MOL */ +EXPORT_SYMBOL(flush_hash_pages); /* For MOL */ +EXPORT_SYMBOL_GPL(__handle_mm_fault); /* For MOL */ +#ifdef CONFIG_SMP +extern int mmu_hash_lock; +EXPORT_SYMBOL(mmu_hash_lock); /* For MOL */ +#endif /* CONFIG_SMP */ +extern long *intercept_table; +EXPORT_SYMBOL(intercept_table); +#endif /* CONFIG_PPC_STD_MMU_32 */ +#if defined(CONFIG_40x) || defined(CONFIG_BOOKE) +EXPORT_SYMBOL(__mtdcr); +EXPORT_SYMBOL(__mfdcr); +#endif diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c new file mode 100644 index 000000000000..8f85dabe4df3 --- /dev/null +++ b/arch/powerpc/kernel/process.c @@ -0,0 +1,919 @@ +/* + * arch/ppc/kernel/process.c + * + * Derived from "arch/i386/kernel/process.c" + * Copyright (C) 1995 Linus Torvalds + * + * Updated and modified by Cort Dougan (cort@cs.nmt.edu) and + * Paul Mackerras (paulus@cs.anu.edu.au) + * + * PowerPC version + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.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/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/ptrace.h> +#include <linux/slab.h> +#include <linux/user.h> +#include <linux/elf.h> +#include <linux/init.h> +#include <linux/prctl.h> +#include <linux/init_task.h> +#include <linux/module.h> +#include <linux/kallsyms.h> +#include <linux/mqueue.h> +#include <linux/hardirq.h> +#include <linux/utsname.h> +#include <linux/kprobes.h> + +#include <asm/pgtable.h> +#include <asm/uaccess.h> +#include <asm/system.h> +#include <asm/io.h> +#include <asm/processor.h> +#include <asm/mmu.h> +#include <asm/prom.h> +#ifdef CONFIG_PPC64 +#include <asm/firmware.h> +#include <asm/plpar_wrappers.h> +#include <asm/time.h> +#endif + +extern unsigned long _get_SP(void); + +#ifndef CONFIG_SMP +struct task_struct *last_task_used_math = NULL; +struct task_struct *last_task_used_altivec = NULL; +struct task_struct *last_task_used_spe = NULL; +#endif + +/* + * Make sure the floating-point register state in the + * the thread_struct is up to date for task tsk. + */ +void flush_fp_to_thread(struct task_struct *tsk) +{ + if (tsk->thread.regs) { + /* + * We need to disable preemption here because if we didn't, + * another process could get scheduled after the regs->msr + * test but before we have finished saving the FP registers + * to the thread_struct. That process could take over the + * FPU, and then when we get scheduled again we would store + * bogus values for the remaining FP registers. + */ + preempt_disable(); + if (tsk->thread.regs->msr & MSR_FP) { +#ifdef CONFIG_SMP + /* + * This should only ever be called for current or + * for a stopped child process. Since we save away + * the FP register state on context switch on SMP, + * there is something wrong if a stopped child appears + * to still have its FP state in the CPU registers. + */ + BUG_ON(tsk != current); +#endif + giveup_fpu(current); + } + preempt_enable(); + } +} + +void enable_kernel_fp(void) +{ + WARN_ON(preemptible()); + +#ifdef CONFIG_SMP + if (current->thread.regs && (current->thread.regs->msr & MSR_FP)) + giveup_fpu(current); + else + giveup_fpu(NULL); /* just enables FP for kernel */ +#else + giveup_fpu(last_task_used_math); +#endif /* CONFIG_SMP */ +} +EXPORT_SYMBOL(enable_kernel_fp); + +int dump_task_fpu(struct task_struct *tsk, elf_fpregset_t *fpregs) +{ + if (!tsk->thread.regs) + return 0; + flush_fp_to_thread(current); + + memcpy(fpregs, &tsk->thread.fpr[0], sizeof(*fpregs)); + + return 1; +} + +#ifdef CONFIG_ALTIVEC +void enable_kernel_altivec(void) +{ + WARN_ON(preemptible()); + +#ifdef CONFIG_SMP + if (current->thread.regs && (current->thread.regs->msr & MSR_VEC)) + giveup_altivec(current); + else + giveup_altivec(NULL); /* just enable AltiVec for kernel - force */ +#else + giveup_altivec(last_task_used_altivec); +#endif /* CONFIG_SMP */ +} +EXPORT_SYMBOL(enable_kernel_altivec); + +/* + * Make sure the VMX/Altivec register state in the + * the thread_struct is up to date for task tsk. + */ +void flush_altivec_to_thread(struct task_struct *tsk) +{ + if (tsk->thread.regs) { + preempt_disable(); + if (tsk->thread.regs->msr & MSR_VEC) { +#ifdef CONFIG_SMP + BUG_ON(tsk != current); +#endif + giveup_altivec(current); + } + preempt_enable(); + } +} + +int dump_task_altivec(struct pt_regs *regs, elf_vrregset_t *vrregs) +{ + flush_altivec_to_thread(current); + memcpy(vrregs, ¤t->thread.vr[0], sizeof(*vrregs)); + return 1; +} +#endif /* CONFIG_ALTIVEC */ + +#ifdef CONFIG_SPE + +void enable_kernel_spe(void) +{ + WARN_ON(preemptible()); + +#ifdef CONFIG_SMP + if (current->thread.regs && (current->thread.regs->msr & MSR_SPE)) + giveup_spe(current); + else + giveup_spe(NULL); /* just enable SPE for kernel - force */ +#else + giveup_spe(last_task_used_spe); +#endif /* __SMP __ */ +} +EXPORT_SYMBOL(enable_kernel_spe); + +void flush_spe_to_thread(struct task_struct *tsk) +{ + if (tsk->thread.regs) { + preempt_disable(); + if (tsk->thread.regs->msr & MSR_SPE) { +#ifdef CONFIG_SMP + BUG_ON(tsk != current); +#endif + giveup_spe(current); + } + preempt_enable(); + } +} + +int dump_spe(struct pt_regs *regs, elf_vrregset_t *evrregs) +{ + flush_spe_to_thread(current); + /* We copy u32 evr[32] + u64 acc + u32 spefscr -> 35 */ + memcpy(evrregs, ¤t->thread.evr[0], sizeof(u32) * 35); + return 1; +} +#endif /* CONFIG_SPE */ + +static void set_dabr_spr(unsigned long val) +{ + mtspr(SPRN_DABR, val); +} + +int set_dabr(unsigned long dabr) +{ + int ret = 0; + +#ifdef CONFIG_PPC64 + if (firmware_has_feature(FW_FEATURE_XDABR)) { + /* We want to catch accesses from kernel and userspace */ + unsigned long flags = H_DABRX_KERNEL|H_DABRX_USER; + ret = plpar_set_xdabr(dabr, flags); + } else if (firmware_has_feature(FW_FEATURE_DABR)) { + ret = plpar_set_dabr(dabr); + } else +#endif + set_dabr_spr(dabr); + + return ret; +} + +#ifdef CONFIG_PPC64 +DEFINE_PER_CPU(struct cpu_usage, cpu_usage_array); +static DEFINE_PER_CPU(unsigned long, current_dabr); +#endif + +struct task_struct *__switch_to(struct task_struct *prev, + struct task_struct *new) +{ + struct thread_struct *new_thread, *old_thread; + unsigned long flags; + struct task_struct *last; + +#ifdef CONFIG_SMP + /* avoid complexity of lazy save/restore of fpu + * by just saving it every time we switch out if + * this task used the fpu during the last quantum. + * + * If it tries to use the fpu again, it'll trap and + * reload its fp regs. So we don't have to do a restore + * every switch, just a save. + * -- Cort + */ + if (prev->thread.regs && (prev->thread.regs->msr & MSR_FP)) + giveup_fpu(prev); +#ifdef CONFIG_ALTIVEC + /* + * If the previous thread used altivec in the last quantum + * (thus changing altivec regs) then save them. + * We used to check the VRSAVE register but not all apps + * set it, so we don't rely on it now (and in fact we need + * to save & restore VSCR even if VRSAVE == 0). -- paulus + * + * On SMP we always save/restore altivec regs just to avoid the + * complexity of changing processors. + * -- Cort + */ + if (prev->thread.regs && (prev->thread.regs->msr & MSR_VEC)) + giveup_altivec(prev); +#endif /* CONFIG_ALTIVEC */ +#ifdef CONFIG_SPE + /* + * If the previous thread used spe in the last quantum + * (thus changing spe regs) then save them. + * + * On SMP we always save/restore spe regs just to avoid the + * complexity of changing processors. + */ + if ((prev->thread.regs && (prev->thread.regs->msr & MSR_SPE))) + giveup_spe(prev); +#endif /* CONFIG_SPE */ + +#else /* CONFIG_SMP */ +#ifdef CONFIG_ALTIVEC + /* Avoid the trap. On smp this this never happens since + * we don't set last_task_used_altivec -- Cort + */ + if (new->thread.regs && last_task_used_altivec == new) + new->thread.regs->msr |= MSR_VEC; +#endif /* CONFIG_ALTIVEC */ +#ifdef CONFIG_SPE + /* Avoid the trap. On smp this this never happens since + * we don't set last_task_used_spe + */ + if (new->thread.regs && last_task_used_spe == new) + new->thread.regs->msr |= MSR_SPE; +#endif /* CONFIG_SPE */ + +#endif /* CONFIG_SMP */ + +#ifdef CONFIG_PPC64 /* for now */ + if (unlikely(__get_cpu_var(current_dabr) != new->thread.dabr)) { + set_dabr(new->thread.dabr); + __get_cpu_var(current_dabr) = new->thread.dabr; + } + + flush_tlb_pending(); +#endif + + new_thread = &new->thread; + old_thread = ¤t->thread; + +#ifdef CONFIG_PPC64 + /* + * Collect processor utilization data per process + */ + if (firmware_has_feature(FW_FEATURE_SPLPAR)) { + struct cpu_usage *cu = &__get_cpu_var(cpu_usage_array); + long unsigned start_tb, current_tb; + start_tb = old_thread->start_tb; + cu->current_tb = current_tb = mfspr(SPRN_PURR); + old_thread->accum_tb += (current_tb - start_tb); + new_thread->start_tb = current_tb; + } +#endif + + local_irq_save(flags); + last = _switch(old_thread, new_thread); + + local_irq_restore(flags); + + return last; +} + +static int instructions_to_print = 16; + +#ifdef CONFIG_PPC64 +#define BAD_PC(pc) ((REGION_ID(pc) != KERNEL_REGION_ID) && \ + (REGION_ID(pc) != VMALLOC_REGION_ID)) +#else +#define BAD_PC(pc) ((pc) < KERNELBASE) +#endif + +static void show_instructions(struct pt_regs *regs) +{ + int i; + unsigned long pc = regs->nip - (instructions_to_print * 3 / 4 * + sizeof(int)); + + printk("Instruction dump:"); + + for (i = 0; i < instructions_to_print; i++) { + int instr; + + if (!(i % 8)) + printk("\n"); + + if (BAD_PC(pc) || __get_user(instr, (unsigned int *)pc)) { + printk("XXXXXXXX "); + } else { + if (regs->nip == pc) + printk("<%08x> ", instr); + else + printk("%08x ", instr); + } + + pc += sizeof(int); + } + + printk("\n"); +} + +static struct regbit { + unsigned long bit; + const char *name; +} msr_bits[] = { + {MSR_EE, "EE"}, + {MSR_PR, "PR"}, + {MSR_FP, "FP"}, + {MSR_ME, "ME"}, + {MSR_IR, "IR"}, + {MSR_DR, "DR"}, + {0, NULL} +}; + +static void printbits(unsigned long val, struct regbit *bits) +{ + const char *sep = ""; + + printk("<"); + for (; bits->bit; ++bits) + if (val & bits->bit) { + printk("%s%s", sep, bits->name); + sep = ","; + } + printk(">"); +} + +#ifdef CONFIG_PPC64 +#define REG "%016lX" +#define REGS_PER_LINE 4 +#define LAST_VOLATILE 13 +#else +#define REG "%08lX" +#define REGS_PER_LINE 8 +#define LAST_VOLATILE 12 +#endif + +void show_regs(struct pt_regs * regs) +{ + int i, trap; + + printk("NIP: "REG" LR: "REG" CTR: "REG"\n", + regs->nip, regs->link, regs->ctr); + printk("REGS: %p TRAP: %04lx %s (%s)\n", + regs, regs->trap, print_tainted(), system_utsname.release); + printk("MSR: "REG" ", regs->msr); + printbits(regs->msr, msr_bits); + printk(" CR: %08lX XER: %08lX\n", regs->ccr, regs->xer); + trap = TRAP(regs); + if (trap == 0x300 || trap == 0x600) + printk("DAR: "REG", DSISR: "REG"\n", regs->dar, regs->dsisr); + printk("TASK = %p[%d] '%s' THREAD: %p", + current, current->pid, current->comm, current->thread_info); + +#ifdef CONFIG_SMP + printk(" CPU: %d", smp_processor_id()); +#endif /* CONFIG_SMP */ + + for (i = 0; i < 32; i++) { + if ((i % REGS_PER_LINE) == 0) + printk("\n" KERN_INFO "GPR%02d: ", i); + printk(REG " ", regs->gpr[i]); + if (i == LAST_VOLATILE && !FULL_REGS(regs)) + break; + } + printk("\n"); +#ifdef CONFIG_KALLSYMS + /* + * Lookup NIP late so we have the best change of getting the + * above info out without failing + */ + printk("NIP ["REG"] ", regs->nip); + print_symbol("%s\n", regs->nip); + printk("LR ["REG"] ", regs->link); + print_symbol("%s\n", regs->link); +#endif + show_stack(current, (unsigned long *) regs->gpr[1]); + if (!user_mode(regs)) + show_instructions(regs); +} + +void exit_thread(void) +{ + kprobe_flush_task(current); + +#ifndef CONFIG_SMP + if (last_task_used_math == current) + last_task_used_math = NULL; +#ifdef CONFIG_ALTIVEC + if (last_task_used_altivec == current) + last_task_used_altivec = NULL; +#endif /* CONFIG_ALTIVEC */ +#ifdef CONFIG_SPE + if (last_task_used_spe == current) + last_task_used_spe = NULL; +#endif +#endif /* CONFIG_SMP */ +} + +void flush_thread(void) +{ +#ifdef CONFIG_PPC64 + struct thread_info *t = current_thread_info(); + + if (t->flags & _TIF_ABI_PENDING) + t->flags ^= (_TIF_ABI_PENDING | _TIF_32BIT); +#endif + kprobe_flush_task(current); + +#ifndef CONFIG_SMP + if (last_task_used_math == current) + last_task_used_math = NULL; +#ifdef CONFIG_ALTIVEC + if (last_task_used_altivec == current) + last_task_used_altivec = NULL; +#endif /* CONFIG_ALTIVEC */ +#ifdef CONFIG_SPE + if (last_task_used_spe == current) + last_task_used_spe = NULL; +#endif +#endif /* CONFIG_SMP */ + +#ifdef CONFIG_PPC64 /* for now */ + if (current->thread.dabr) { + current->thread.dabr = 0; + set_dabr(0); + } +#endif +} + +void +release_thread(struct task_struct *t) +{ +} + +/* + * This gets called before we allocate a new thread and copy + * the current task into it. + */ +void prepare_to_copy(struct task_struct *tsk) +{ + flush_fp_to_thread(current); + flush_altivec_to_thread(current); + flush_spe_to_thread(current); +} + +/* + * Copy a thread.. + */ +int copy_thread(int nr, unsigned long clone_flags, unsigned long usp, + unsigned long unused, struct task_struct *p, + struct pt_regs *regs) +{ + struct pt_regs *childregs, *kregs; + extern void ret_from_fork(void); + unsigned long sp = (unsigned long)p->thread_info + THREAD_SIZE; + + CHECK_FULL_REGS(regs); + /* Copy registers */ + sp -= sizeof(struct pt_regs); + childregs = (struct pt_regs *) sp; + *childregs = *regs; + if ((childregs->msr & MSR_PR) == 0) { + /* for kernel thread, set `current' and stackptr in new task */ + childregs->gpr[1] = sp + sizeof(struct pt_regs); +#ifdef CONFIG_PPC32 + childregs->gpr[2] = (unsigned long) p; +#else + clear_ti_thread_flag(p->thread_info, TIF_32BIT); +#endif + p->thread.regs = NULL; /* no user register state */ + } else { + childregs->gpr[1] = usp; + p->thread.regs = childregs; + if (clone_flags & CLONE_SETTLS) { +#ifdef CONFIG_PPC64 + if (!test_thread_flag(TIF_32BIT)) + childregs->gpr[13] = childregs->gpr[6]; + else +#endif + childregs->gpr[2] = childregs->gpr[6]; + } + } + childregs->gpr[3] = 0; /* Result from fork() */ + sp -= STACK_FRAME_OVERHEAD; + + /* + * The way this works is that at some point in the future + * some task will call _switch to switch to the new task. + * That will pop off the stack frame created below and start + * the new task running at ret_from_fork. The new task will + * do some house keeping and then return from the fork or clone + * system call, using the stack frame created above. + */ + sp -= sizeof(struct pt_regs); + kregs = (struct pt_regs *) sp; + sp -= STACK_FRAME_OVERHEAD; + p->thread.ksp = sp; + +#ifdef CONFIG_PPC64 + if (cpu_has_feature(CPU_FTR_SLB)) { + unsigned long sp_vsid = get_kernel_vsid(sp); + + sp_vsid <<= SLB_VSID_SHIFT; + sp_vsid |= SLB_VSID_KERNEL; + if (cpu_has_feature(CPU_FTR_16M_PAGE)) + sp_vsid |= SLB_VSID_L; + + p->thread.ksp_vsid = sp_vsid; + } + + /* + * The PPC64 ABI makes use of a TOC to contain function + * pointers. The function (ret_from_except) is actually a pointer + * to the TOC entry. The first entry is a pointer to the actual + * function. + */ + kregs->nip = *((unsigned long *)ret_from_fork); +#else + kregs->nip = (unsigned long)ret_from_fork; + p->thread.last_syscall = -1; +#endif + + return 0; +} + +/* + * Set up a thread for executing a new program + */ +void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) +{ +#ifdef CONFIG_PPC64 + unsigned long load_addr = regs->gpr[2]; /* saved by ELF_PLAT_INIT */ +#endif + + set_fs(USER_DS); + + /* + * If we exec out of a kernel thread then thread.regs will not be + * set. Do it now. + */ + if (!current->thread.regs) { + unsigned long childregs = (unsigned long)current->thread_info + + THREAD_SIZE; + childregs -= sizeof(struct pt_regs); + current->thread.regs = (struct pt_regs *)childregs; + } + + memset(regs->gpr, 0, sizeof(regs->gpr)); + regs->ctr = 0; + regs->link = 0; + regs->xer = 0; + regs->ccr = 0; + regs->gpr[1] = sp; + +#ifdef CONFIG_PPC32 + regs->mq = 0; + regs->nip = start; + regs->msr = MSR_USER; +#else + if (!test_thread_flag(TIF_32BIT)) { + unsigned long entry, toc; + + /* start is a relocated pointer to the function descriptor for + * the elf _start routine. The first entry in the function + * descriptor is the entry address of _start and the second + * entry is the TOC value we need to use. + */ + __get_user(entry, (unsigned long __user *)start); + __get_user(toc, (unsigned long __user *)start+1); + + /* Check whether the e_entry function descriptor entries + * need to be relocated before we can use them. + */ + if (load_addr != 0) { + entry += load_addr; + toc += load_addr; + } + regs->nip = entry; + regs->gpr[2] = toc; + regs->msr = MSR_USER64; + } else { + regs->nip = start; + regs->gpr[2] = 0; + regs->msr = MSR_USER32; + } +#endif + +#ifndef CONFIG_SMP + if (last_task_used_math == current) + last_task_used_math = NULL; +#ifdef CONFIG_ALTIVEC + if (last_task_used_altivec == current) + last_task_used_altivec = NULL; +#endif +#ifdef CONFIG_SPE + if (last_task_used_spe == current) + last_task_used_spe = NULL; +#endif +#endif /* CONFIG_SMP */ + memset(current->thread.fpr, 0, sizeof(current->thread.fpr)); + current->thread.fpscr.val = 0; +#ifdef CONFIG_ALTIVEC + memset(current->thread.vr, 0, sizeof(current->thread.vr)); + memset(¤t->thread.vscr, 0, sizeof(current->thread.vscr)); + current->thread.vscr.u[3] = 0x00010000; /* Java mode disabled */ + current->thread.vrsave = 0; + current->thread.used_vr = 0; +#endif /* CONFIG_ALTIVEC */ +#ifdef CONFIG_SPE + memset(current->thread.evr, 0, sizeof(current->thread.evr)); + current->thread.acc = 0; + current->thread.spefscr = 0; + current->thread.used_spe = 0; +#endif /* CONFIG_SPE */ +} + +#define PR_FP_ALL_EXCEPT (PR_FP_EXC_DIV | PR_FP_EXC_OVF | PR_FP_EXC_UND \ + | PR_FP_EXC_RES | PR_FP_EXC_INV) + +int set_fpexc_mode(struct task_struct *tsk, unsigned int val) +{ + struct pt_regs *regs = tsk->thread.regs; + + /* This is a bit hairy. If we are an SPE enabled processor + * (have embedded fp) we store the IEEE exception enable flags in + * fpexc_mode. fpexc_mode is also used for setting FP exception + * mode (asyn, precise, disabled) for 'Classic' FP. */ + if (val & PR_FP_EXC_SW_ENABLE) { +#ifdef CONFIG_SPE + tsk->thread.fpexc_mode = val & + (PR_FP_EXC_SW_ENABLE | PR_FP_ALL_EXCEPT); + return 0; +#else + return -EINVAL; +#endif + } + + /* on a CONFIG_SPE this does not hurt us. The bits that + * __pack_fe01 use do not overlap with bits used for + * PR_FP_EXC_SW_ENABLE. Additionally, the MSR[FE0,FE1] bits + * on CONFIG_SPE implementations are reserved so writing to + * them does not change anything */ + if (val > PR_FP_EXC_PRECISE) + return -EINVAL; + tsk->thread.fpexc_mode = __pack_fe01(val); + if (regs != NULL && (regs->msr & MSR_FP) != 0) + regs->msr = (regs->msr & ~(MSR_FE0|MSR_FE1)) + | tsk->thread.fpexc_mode; + return 0; +} + +int get_fpexc_mode(struct task_struct *tsk, unsigned long adr) +{ + unsigned int val; + + if (tsk->thread.fpexc_mode & PR_FP_EXC_SW_ENABLE) +#ifdef CONFIG_SPE + val = tsk->thread.fpexc_mode; +#else + return -EINVAL; +#endif + else + val = __unpack_fe01(tsk->thread.fpexc_mode); + return put_user(val, (unsigned int __user *) adr); +} + +#define TRUNC_PTR(x) ((typeof(x))(((unsigned long)(x)) & 0xffffffff)) + +int sys_clone(unsigned long clone_flags, unsigned long usp, + int __user *parent_tidp, void __user *child_threadptr, + int __user *child_tidp, int p6, + struct pt_regs *regs) +{ + CHECK_FULL_REGS(regs); + if (usp == 0) + usp = regs->gpr[1]; /* stack pointer for child */ +#ifdef CONFIG_PPC64 + if (test_thread_flag(TIF_32BIT)) { + parent_tidp = TRUNC_PTR(parent_tidp); + child_tidp = TRUNC_PTR(child_tidp); + } +#endif + return do_fork(clone_flags, usp, regs, 0, parent_tidp, child_tidp); +} + +int sys_fork(unsigned long p1, unsigned long p2, unsigned long p3, + unsigned long p4, unsigned long p5, unsigned long p6, + struct pt_regs *regs) +{ + CHECK_FULL_REGS(regs); + return do_fork(SIGCHLD, regs->gpr[1], regs, 0, NULL, NULL); +} + +int sys_vfork(unsigned long p1, unsigned long p2, unsigned long p3, + unsigned long p4, unsigned long p5, unsigned long p6, + struct pt_regs *regs) +{ + CHECK_FULL_REGS(regs); + return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs->gpr[1], + regs, 0, NULL, NULL); +} + +int sys_execve(unsigned long a0, unsigned long a1, unsigned long a2, + unsigned long a3, unsigned long a4, unsigned long a5, + struct pt_regs *regs) +{ + int error; + char *filename; + + filename = getname((char __user *) a0); + error = PTR_ERR(filename); + if (IS_ERR(filename)) + goto out; + flush_fp_to_thread(current); + flush_altivec_to_thread(current); + flush_spe_to_thread(current); + error = do_execve(filename, (char __user * __user *) a1, + (char __user * __user *) a2, regs); + if (error == 0) { + task_lock(current); + current->ptrace &= ~PT_DTRACE; + task_unlock(current); + } + putname(filename); +out: + return error; +} + +static int validate_sp(unsigned long sp, struct task_struct *p, + unsigned long nbytes) +{ + unsigned long stack_page = (unsigned long)p->thread_info; + + if (sp >= stack_page + sizeof(struct thread_struct) + && sp <= stack_page + THREAD_SIZE - nbytes) + return 1; + +#ifdef CONFIG_IRQSTACKS + stack_page = (unsigned long) hardirq_ctx[task_cpu(p)]; + if (sp >= stack_page + sizeof(struct thread_struct) + && sp <= stack_page + THREAD_SIZE - nbytes) + return 1; + + stack_page = (unsigned long) softirq_ctx[task_cpu(p)]; + if (sp >= stack_page + sizeof(struct thread_struct) + && sp <= stack_page + THREAD_SIZE - nbytes) + return 1; +#endif + + return 0; +} + +#ifdef CONFIG_PPC64 +#define MIN_STACK_FRAME 112 /* same as STACK_FRAME_OVERHEAD, in fact */ +#define FRAME_LR_SAVE 2 +#define INT_FRAME_SIZE (sizeof(struct pt_regs) + STACK_FRAME_OVERHEAD + 288) +#define REGS_MARKER 0x7265677368657265ul +#define FRAME_MARKER 12 +#else +#define MIN_STACK_FRAME 16 +#define FRAME_LR_SAVE 1 +#define INT_FRAME_SIZE (sizeof(struct pt_regs) + STACK_FRAME_OVERHEAD) +#define REGS_MARKER 0x72656773ul +#define FRAME_MARKER 2 +#endif + +unsigned long get_wchan(struct task_struct *p) +{ + unsigned long ip, sp; + int count = 0; + + if (!p || p == current || p->state == TASK_RUNNING) + return 0; + + sp = p->thread.ksp; + if (!validate_sp(sp, p, MIN_STACK_FRAME)) + return 0; + + do { + sp = *(unsigned long *)sp; + if (!validate_sp(sp, p, MIN_STACK_FRAME)) + return 0; + if (count > 0) { + ip = ((unsigned long *)sp)[FRAME_LR_SAVE]; + if (!in_sched_functions(ip)) + return ip; + } + } while (count++ < 16); + return 0; +} +EXPORT_SYMBOL(get_wchan); + +static int kstack_depth_to_print = 64; + +void show_stack(struct task_struct *tsk, unsigned long *stack) +{ + unsigned long sp, ip, lr, newsp; + int count = 0; + int firstframe = 1; + + sp = (unsigned long) stack; + if (tsk == NULL) + tsk = current; + if (sp == 0) { + if (tsk == current) + asm("mr %0,1" : "=r" (sp)); + else + sp = tsk->thread.ksp; + } + + lr = 0; + printk("Call Trace:\n"); + do { + if (!validate_sp(sp, tsk, MIN_STACK_FRAME)) + return; + + stack = (unsigned long *) sp; + newsp = stack[0]; + ip = stack[FRAME_LR_SAVE]; + if (!firstframe || ip != lr) { + printk("["REG"] ["REG"] ", sp, ip); + print_symbol("%s", ip); + if (firstframe) + printk(" (unreliable)"); + printk("\n"); + } + firstframe = 0; + + /* + * See if this is an exception frame. + * We look for the "regshere" marker in the current frame. + */ + if (validate_sp(sp, tsk, INT_FRAME_SIZE) + && stack[FRAME_MARKER] == REGS_MARKER) { + struct pt_regs *regs = (struct pt_regs *) + (sp + STACK_FRAME_OVERHEAD); + printk("--- Exception: %lx", regs->trap); + print_symbol(" at %s\n", regs->nip); + lr = regs->link; + print_symbol(" LR = %s\n", lr); + firstframe = 1; + } + + sp = newsp; + } while (count++ < kstack_depth_to_print); +} + +void dump_stack(void) +{ + show_stack(current, NULL); +} +EXPORT_SYMBOL(dump_stack); diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c new file mode 100644 index 000000000000..2eccd0e159e3 --- /dev/null +++ b/arch/powerpc/kernel/prom.c @@ -0,0 +1,2170 @@ +/* + * Procedures for creating, accessing and interpreting the device tree. + * + * Paul Mackerras August 1996. + * Copyright (C) 1996-2005 Paul Mackerras. + * + * Adapted for 64bit PowerPC by Dave Engebretsen and Peter Bergner. + * {engebret|bergner}@us.ibm.com + * + * 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. + */ + +#undef DEBUG + +#include <stdarg.h> +#include <linux/config.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/init.h> +#include <linux/threads.h> +#include <linux/spinlock.h> +#include <linux/types.h> +#include <linux/pci.h> +#include <linux/stringify.h> +#include <linux/delay.h> +#include <linux/initrd.h> +#include <linux/bitops.h> +#include <linux/module.h> + +#include <asm/prom.h> +#include <asm/rtas.h> +#include <asm/lmb.h> +#include <asm/page.h> +#include <asm/processor.h> +#include <asm/irq.h> +#include <asm/io.h> +#include <asm/smp.h> +#include <asm/system.h> +#include <asm/mmu.h> +#include <asm/pgtable.h> +#include <asm/pci.h> +#include <asm/iommu.h> +#include <asm/btext.h> +#include <asm/sections.h> +#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) +#else +#define DBG(fmt...) +#endif + +struct pci_reg_property { + struct pci_address addr; + u32 size_hi; + u32 size_lo; +}; + +struct isa_reg_property { + u32 space; + u32 address; + u32 size; +}; + + +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; + +#ifdef CONFIG_PPC64 +static int __initdata iommu_is_off; +int __initdata iommu_force_on; +unsigned long tce_alloc_start, tce_alloc_end; +#endif + +typedef u32 cell_t; + +#if 0 +static struct boot_param_header *initial_boot_params __initdata; +#else +struct boot_param_header *initial_boot_params; +#endif + +static struct device_node *allnodes = NULL; + +/* use when traversing tree through the allnext, child, sibling, + * or parent members of struct device_node. + */ +static DEFINE_RWLOCK(devtree_lock); + +/* export that to outside world */ +struct device_node *of_chosen; + +struct device_node *dflt_interrupt_controller; +int num_interrupt_controllers; + +/* + * Wrapper for allocating memory for various data that needs to be + * attached to device nodes as they are processed at boot or when + * added to the device tree later (e.g. DLPAR). At boot there is + * already a region reserved so we just increment *mem_start by size; + * otherwise we call kmalloc. + */ +static void * prom_alloc(unsigned long size, unsigned long *mem_start) +{ + unsigned long tmp; + + if (!mem_start) + return kmalloc(size, GFP_KERNEL); + + tmp = *mem_start; + *mem_start += size; + return (void *)tmp; +} + +/* + * Find the device_node with a given phandle. + */ +static struct device_node * find_phandle(phandle ph) +{ + struct device_node *np; + + for (np = allnodes; np != 0; np = np->allnext) + if (np->linux_phandle == ph) + return np; + return NULL; +} + +/* + * Find the interrupt parent of a node. + */ +static struct device_node * __devinit intr_parent(struct device_node *p) +{ + phandle *parp; + + parp = (phandle *) get_property(p, "interrupt-parent", NULL); + if (parp == NULL) + return p->parent; + p = find_phandle(*parp); + if (p != NULL) + return p; + /* + * On a powermac booted with BootX, we don't get to know the + * phandles for any nodes, so find_phandle will return NULL. + * Fortunately these machines only have one interrupt controller + * so there isn't in fact any ambiguity. -- paulus + */ + if (num_interrupt_controllers == 1) + p = dflt_interrupt_controller; + return p; +} + +/* + * Find out the size of each entry of the interrupts property + * for a node. + */ +int __devinit prom_n_intr_cells(struct device_node *np) +{ + struct device_node *p; + unsigned int *icp; + + for (p = np; (p = intr_parent(p)) != NULL; ) { + icp = (unsigned int *) + get_property(p, "#interrupt-cells", NULL); + if (icp != NULL) + return *icp; + if (get_property(p, "interrupt-controller", NULL) != NULL + || get_property(p, "interrupt-map", NULL) != NULL) { + printk("oops, node %s doesn't have #interrupt-cells\n", + p->full_name); + return 1; + } + } +#ifdef DEBUG_IRQ + printk("prom_n_intr_cells failed for %s\n", np->full_name); +#endif + return 1; +} + +/* + * Map an interrupt from a device up to the platform interrupt + * descriptor. + */ +static int __devinit map_interrupt(unsigned int **irq, struct device_node **ictrler, + struct device_node *np, unsigned int *ints, + int nintrc) +{ + struct device_node *p, *ipar; + unsigned int *imap, *imask, *ip; + int i, imaplen, match; + int newintrc = 0, newaddrc = 0; + unsigned int *reg; + int naddrc; + + reg = (unsigned int *) get_property(np, "reg", NULL); + naddrc = prom_n_addr_cells(np); + p = intr_parent(np); + while (p != NULL) { + if (get_property(p, "interrupt-controller", NULL) != NULL) + /* this node is an interrupt controller, stop here */ + break; + imap = (unsigned int *) + get_property(p, "interrupt-map", &imaplen); + if (imap == NULL) { + p = intr_parent(p); + continue; + } + imask = (unsigned int *) + get_property(p, "interrupt-map-mask", NULL); + if (imask == NULL) { + printk("oops, %s has interrupt-map but no mask\n", + p->full_name); + return 0; + } + imaplen /= sizeof(unsigned int); + match = 0; + ipar = NULL; + while (imaplen > 0 && !match) { + /* check the child-interrupt field */ + match = 1; + for (i = 0; i < naddrc && match; ++i) + match = ((reg[i] ^ imap[i]) & imask[i]) == 0; + for (; i < naddrc + nintrc && match; ++i) + match = ((ints[i-naddrc] ^ imap[i]) & imask[i]) == 0; + imap += naddrc + nintrc; + imaplen -= naddrc + nintrc; + /* grab the interrupt parent */ + ipar = find_phandle((phandle) *imap++); + --imaplen; + if (ipar == NULL && num_interrupt_controllers == 1) + /* cope with BootX not giving us phandles */ + ipar = dflt_interrupt_controller; + if (ipar == NULL) { + printk("oops, no int parent %x in map of %s\n", + imap[-1], p->full_name); + return 0; + } + /* find the parent's # addr and intr cells */ + ip = (unsigned int *) + get_property(ipar, "#interrupt-cells", NULL); + if (ip == NULL) { + printk("oops, no #interrupt-cells on %s\n", + ipar->full_name); + return 0; + } + newintrc = *ip; + ip = (unsigned int *) + get_property(ipar, "#address-cells", NULL); + newaddrc = (ip == NULL)? 0: *ip; + imap += newaddrc + newintrc; + imaplen -= newaddrc + newintrc; + } + if (imaplen < 0) { + printk("oops, error decoding int-map on %s, len=%d\n", + p->full_name, imaplen); + return 0; + } + if (!match) { +#ifdef DEBUG_IRQ + printk("oops, no match in %s int-map for %s\n", + p->full_name, np->full_name); +#endif + return 0; + } + p = ipar; + naddrc = newaddrc; + nintrc = newintrc; + ints = imap - nintrc; + reg = ints - naddrc; + } + if (p == NULL) { +#ifdef DEBUG_IRQ + printk("hmmm, int tree for %s doesn't have ctrler\n", + np->full_name); +#endif + return 0; + } + *irq = ints; + *ictrler = p; + return nintrc; +} + +static unsigned char map_isa_senses[4] = { + IRQ_SENSE_LEVEL | IRQ_POLARITY_NEGATIVE, + IRQ_SENSE_LEVEL | IRQ_POLARITY_POSITIVE, + IRQ_SENSE_EDGE | IRQ_POLARITY_NEGATIVE, + IRQ_SENSE_EDGE | IRQ_POLARITY_POSITIVE +}; + +static unsigned char map_mpic_senses[4] = { + IRQ_SENSE_EDGE | IRQ_POLARITY_POSITIVE, + IRQ_SENSE_LEVEL | IRQ_POLARITY_NEGATIVE, + /* 2 seems to be used for the 8259 cascade... */ + IRQ_SENSE_LEVEL | IRQ_POLARITY_POSITIVE, + IRQ_SENSE_EDGE | IRQ_POLARITY_NEGATIVE, +}; + +static int __devinit finish_node_interrupts(struct device_node *np, + unsigned long *mem_start, + int measure_only) +{ + unsigned int *ints; + int intlen, intrcells, intrcount; + int i, j, n, sense; + unsigned int *irq, virq; + struct device_node *ic; + + if (num_interrupt_controllers == 0) { + /* + * Old machines just have a list of interrupt numbers + * and no interrupt-controller nodes. + */ + ints = (unsigned int *) get_property(np, "AAPL,interrupts", + &intlen); + /* XXX old interpret_pci_props looked in parent too */ + /* XXX old interpret_macio_props looked for interrupts + before AAPL,interrupts */ + if (ints == NULL) + ints = (unsigned int *) get_property(np, "interrupts", + &intlen); + if (ints == NULL) + return 0; + + np->n_intrs = intlen / sizeof(unsigned int); + np->intrs = prom_alloc(np->n_intrs * sizeof(np->intrs[0]), + mem_start); + if (!np->intrs) + return -ENOMEM; + if (measure_only) + return 0; + + for (i = 0; i < np->n_intrs; ++i) { + np->intrs[i].line = *ints++; + np->intrs[i].sense = IRQ_SENSE_LEVEL + | IRQ_POLARITY_NEGATIVE; + } + return 0; + } + + ints = (unsigned int *) get_property(np, "interrupts", &intlen); + if (ints == NULL) + return 0; + intrcells = prom_n_intr_cells(np); + intlen /= intrcells * sizeof(unsigned int); + + np->intrs = prom_alloc(intlen * sizeof(*(np->intrs)), mem_start); + if (!np->intrs) + return -ENOMEM; + + if (measure_only) + return 0; + + intrcount = 0; + for (i = 0; i < intlen; ++i, ints += intrcells) { + n = map_interrupt(&irq, &ic, np, ints, intrcells); + if (n <= 0) + continue; + + /* don't map IRQ numbers under a cascaded 8259 controller */ + if (ic && device_is_compatible(ic, "chrp,iic")) { + np->intrs[intrcount].line = irq[0]; + sense = (n > 1)? (irq[1] & 3): 3; + np->intrs[intrcount].sense = map_isa_senses[sense]; + } else { + virq = virt_irq_create_mapping(irq[0]); +#ifdef CONFIG_PPC64 + if (virq == NO_IRQ) { + printk(KERN_CRIT "Could not allocate interrupt" + " number for %s\n", np->full_name); + continue; + } +#endif + np->intrs[intrcount].line = irq_offset_up(virq); + sense = (n > 1)? (irq[1] & 3): 1; + np->intrs[intrcount].sense = map_mpic_senses[sense]; + } + +#ifdef CONFIG_PPC64 + /* We offset irq numbers for the u3 MPIC by 128 in PowerMac */ + if (systemcfg->platform == PLATFORM_POWERMAC && ic && ic->parent) { + char *name = get_property(ic->parent, "name", NULL); + if (name && !strcmp(name, "u3")) + np->intrs[intrcount].line += 128; + else if (!(name && !strcmp(name, "mac-io"))) + /* ignore other cascaded controllers, such as + the k2-sata-root */ + break; + } +#endif + if (n > 2) { + printk("hmmm, got %d intr cells for %s:", n, + np->full_name); + for (j = 0; j < n; ++j) + printk(" %d", irq[j]); + printk("\n"); + } + ++intrcount; + } + np->n_intrs = intrcount; + + return 0; +} + +static int __devinit interpret_pci_props(struct device_node *np, + unsigned long *mem_start, + int naddrc, int nsizec, + int measure_only) +{ + struct address_range *adr; + struct pci_reg_property *pci_addrs; + int i, l, n_addrs; + + pci_addrs = (struct pci_reg_property *) + get_property(np, "assigned-addresses", &l); + if (!pci_addrs) + return 0; + + n_addrs = l / sizeof(*pci_addrs); + + adr = prom_alloc(n_addrs * sizeof(*adr), mem_start); + if (!adr) + return -ENOMEM; + + if (measure_only) + return 0; + + np->addrs = adr; + np->n_addrs = n_addrs; + + for (i = 0; i < n_addrs; i++) { + adr[i].space = pci_addrs[i].addr.a_hi; + adr[i].address = pci_addrs[i].addr.a_lo | + ((u64)pci_addrs[i].addr.a_mid << 32); + adr[i].size = pci_addrs[i].size_lo; + } + + return 0; +} + +static int __init interpret_dbdma_props(struct device_node *np, + unsigned long *mem_start, + int naddrc, int nsizec, + int measure_only) +{ + struct reg_property32 *rp; + struct address_range *adr; + unsigned long base_address; + int i, l; + struct device_node *db; + + base_address = 0; + if (!measure_only) { + for (db = np->parent; db != NULL; db = db->parent) { + if (!strcmp(db->type, "dbdma") && db->n_addrs != 0) { + base_address = db->addrs[0].address; + break; + } + } + } + + rp = (struct reg_property32 *) get_property(np, "reg", &l); + if (rp != 0 && l >= sizeof(struct reg_property32)) { + i = 0; + adr = (struct address_range *) (*mem_start); + while ((l -= sizeof(struct reg_property32)) >= 0) { + if (!measure_only) { + adr[i].space = 2; + adr[i].address = rp[i].address + base_address; + adr[i].size = rp[i].size; + } + ++i; + } + np->addrs = adr; + np->n_addrs = i; + (*mem_start) += i * sizeof(struct address_range); + } + + return 0; +} + +static int __init interpret_macio_props(struct device_node *np, + unsigned long *mem_start, + int naddrc, int nsizec, + int measure_only) +{ + struct reg_property32 *rp; + struct address_range *adr; + unsigned long base_address; + int i, l; + struct device_node *db; + + base_address = 0; + if (!measure_only) { + for (db = np->parent; db != NULL; db = db->parent) { + if (!strcmp(db->type, "mac-io") && db->n_addrs != 0) { + base_address = db->addrs[0].address; + break; + } + } + } + + rp = (struct reg_property32 *) get_property(np, "reg", &l); + if (rp != 0 && l >= sizeof(struct reg_property32)) { + i = 0; + adr = (struct address_range *) (*mem_start); + while ((l -= sizeof(struct reg_property32)) >= 0) { + if (!measure_only) { + adr[i].space = 2; + adr[i].address = rp[i].address + base_address; + adr[i].size = rp[i].size; + } + ++i; + } + np->addrs = adr; + np->n_addrs = i; + (*mem_start) += i * sizeof(struct address_range); + } + + return 0; +} + +static int __init interpret_isa_props(struct device_node *np, + unsigned long *mem_start, + int naddrc, int nsizec, + int measure_only) +{ + struct isa_reg_property *rp; + struct address_range *adr; + int i, l; + + rp = (struct isa_reg_property *) get_property(np, "reg", &l); + if (rp != 0 && l >= sizeof(struct isa_reg_property)) { + i = 0; + adr = (struct address_range *) (*mem_start); + while ((l -= sizeof(struct isa_reg_property)) >= 0) { + if (!measure_only) { + adr[i].space = rp[i].space; + adr[i].address = rp[i].address; + adr[i].size = rp[i].size; + } + ++i; + } + np->addrs = adr; + np->n_addrs = i; + (*mem_start) += i * sizeof(struct address_range); + } + + return 0; +} + +static int __init interpret_root_props(struct device_node *np, + unsigned long *mem_start, + int naddrc, int nsizec, + int measure_only) +{ + struct address_range *adr; + int i, l; + unsigned int *rp; + int rpsize = (naddrc + nsizec) * sizeof(unsigned int); + + rp = (unsigned int *) get_property(np, "reg", &l); + if (rp != 0 && l >= rpsize) { + i = 0; + adr = (struct address_range *) (*mem_start); + while ((l -= rpsize) >= 0) { + if (!measure_only) { + adr[i].space = 0; + adr[i].address = rp[naddrc - 1]; + adr[i].size = rp[naddrc + nsizec - 1]; + } + ++i; + rp += naddrc + nsizec; + } + np->addrs = adr; + np->n_addrs = i; + (*mem_start) += i * sizeof(struct address_range); + } + + return 0; +} + +static int __devinit finish_node(struct device_node *np, + unsigned long *mem_start, + interpret_func *ifunc, + int naddrc, int nsizec, + int measure_only) +{ + struct device_node *child; + int *ip, rc = 0; + + /* get the device addresses and interrupts */ + if (ifunc != NULL) + rc = ifunc(np, mem_start, naddrc, nsizec, measure_only); + if (rc) + goto out; + + rc = finish_node_interrupts(np, mem_start, measure_only); + if (rc) + goto out; + + /* Look for #address-cells and #size-cells properties. */ + ip = (int *) get_property(np, "#address-cells", NULL); + if (ip != NULL) + naddrc = *ip; + ip = (int *) get_property(np, "#size-cells", NULL); + if (ip != NULL) + nsizec = *ip; + + if (!strcmp(np->name, "device-tree") || np->parent == NULL) + ifunc = interpret_root_props; + else if (np->type == 0) + ifunc = NULL; + else if (!strcmp(np->type, "pci") || !strcmp(np->type, "vci")) + ifunc = interpret_pci_props; + else if (!strcmp(np->type, "dbdma")) + ifunc = interpret_dbdma_props; + else if (!strcmp(np->type, "mac-io") || ifunc == interpret_macio_props) + ifunc = interpret_macio_props; + else if (!strcmp(np->type, "isa")) + ifunc = interpret_isa_props; + else if (!strcmp(np->name, "uni-n") || !strcmp(np->name, "u3")) + ifunc = interpret_root_props; + else if (!((ifunc == interpret_dbdma_props + || ifunc == interpret_macio_props) + && (!strcmp(np->type, "escc") + || !strcmp(np->type, "media-bay")))) + ifunc = NULL; + + for (child = np->child; child != NULL; child = child->sibling) { + rc = finish_node(child, mem_start, ifunc, + naddrc, nsizec, measure_only); + if (rc) + goto out; + } +out: + return rc; +} + +static void __init scan_interrupt_controllers(void) +{ + struct device_node *np; + int n = 0; + char *name, *ic; + int iclen; + + for (np = allnodes; np != NULL; np = np->allnext) { + ic = get_property(np, "interrupt-controller", &iclen); + name = get_property(np, "name", NULL); + /* checking iclen makes sure we don't get a false + match on /chosen.interrupt_controller */ + if ((name != NULL + && strcmp(name, "interrupt-controller") == 0) + || (ic != NULL && iclen == 0 + && strcmp(name, "AppleKiwi"))) { + if (n == 0) + dflt_interrupt_controller = np; + ++n; + } + } + num_interrupt_controllers = n; +} + +/** + * finish_device_tree is called once things are running normally + * (i.e. with text and data mapped to the address they were linked at). + * It traverses the device tree and fills in some of the additional, + * fields in each node like {n_}addrs and {n_}intrs, the virt interrupt + * mapping is also initialized at this point. + */ +void __init finish_device_tree(void) +{ + unsigned long start, end, size = 0; + + DBG(" -> finish_device_tree\n"); + +#ifdef CONFIG_PPC64 + /* Initialize virtual IRQ map */ + virt_irq_init(); +#endif + scan_interrupt_controllers(); + + /* + * Finish device-tree (pre-parsing some properties etc...) + * We do this in 2 passes. One with "measure_only" set, which + * will only measure the amount of memory needed, then we can + * allocate that memory, and call finish_node again. However, + * we must be careful as most routines will fail nowadays when + * prom_alloc() returns 0, so we must make sure our first pass + * doesn't start at 0. We pre-initialize size to 16 for that + * reason and then remove those additional 16 bytes + */ + size = 16; + finish_node(allnodes, &size, NULL, 0, 0, 1); + size -= 16; + end = start = (unsigned long) __va(lmb_alloc(size, 128)); + finish_node(allnodes, &end, NULL, 0, 0, 0); + BUG_ON(end != start + size); + + DBG(" <- finish_device_tree\n"); +} + +static inline char *find_flat_dt_string(u32 offset) +{ + return ((char *)initial_boot_params) + + initial_boot_params->off_dt_strings + offset; +} + +/** + * This function is used to scan the flattened device-tree, it is + * used to extract the memory informations at boot before we can + * unflatten the tree + */ +static int __init scan_flat_dt(int (*it)(unsigned long node, + const char *uname, int depth, + void *data), + void *data) +{ + unsigned long p = ((unsigned long)initial_boot_params) + + initial_boot_params->off_dt_struct; + int rc = 0; + int depth = -1; + + do { + u32 tag = *((u32 *)p); + char *pathp; + + p += 4; + if (tag == OF_DT_END_NODE) { + depth --; + continue; + } + if (tag == OF_DT_NOP) + continue; + if (tag == OF_DT_END) + break; + if (tag == OF_DT_PROP) { + u32 sz = *((u32 *)p); + p += 8; + if (initial_boot_params->version < 0x10) + p = _ALIGN(p, sz >= 8 ? 8 : 4); + p += sz; + p = _ALIGN(p, 4); + continue; + } + if (tag != OF_DT_BEGIN_NODE) { + printk(KERN_WARNING "Invalid tag %x scanning flattened" + " device tree !\n", tag); + return -EINVAL; + } + depth++; + pathp = (char *)p; + p = _ALIGN(p + strlen(pathp) + 1, 4); + if ((*pathp) == '/') { + char *lp, *np; + for (lp = NULL, np = pathp; *np; np++) + if ((*np) == '/') + lp = np+1; + if (lp != NULL) + pathp = lp; + } + rc = it(p, pathp, depth, data); + if (rc != 0) + break; + } while(1); + + return rc; +} + +/** + * This function can be used within scan_flattened_dt callback to get + * access to properties + */ +static void* __init get_flat_dt_prop(unsigned long node, const char *name, + unsigned long *size) +{ + unsigned long p = node; + + do { + u32 tag = *((u32 *)p); + u32 sz, noff; + const char *nstr; + + p += 4; + if (tag == OF_DT_NOP) + continue; + if (tag != OF_DT_PROP) + return NULL; + + sz = *((u32 *)p); + noff = *((u32 *)(p + 4)); + p += 8; + if (initial_boot_params->version < 0x10) + p = _ALIGN(p, sz >= 8 ? 8 : 4); + + nstr = find_flat_dt_string(noff); + if (nstr == NULL) { + printk(KERN_WARNING "Can't find property index" + " name !\n"); + return NULL; + } + if (strcmp(name, nstr) == 0) { + if (size) + *size = sz; + return (void *)p; + } + p += sz; + p = _ALIGN(p, 4); + } while(1); +} + +static void *__init unflatten_dt_alloc(unsigned long *mem, unsigned long size, + unsigned long align) +{ + void *res; + + *mem = _ALIGN(*mem, align); + res = (void *)*mem; + *mem += size; + + return res; +} + +static unsigned long __init unflatten_dt_node(unsigned long mem, + unsigned long *p, + struct device_node *dad, + struct device_node ***allnextpp, + unsigned long fpsize) +{ + struct device_node *np; + struct property *pp, **prev_pp = NULL; + char *pathp; + u32 tag; + unsigned int l, allocl; + int has_name = 0; + int new_format = 0; + + tag = *((u32 *)(*p)); + if (tag != OF_DT_BEGIN_NODE) { + printk("Weird tag at start of node: %x\n", tag); + return mem; + } + *p += 4; + pathp = (char *)*p; + l = allocl = strlen(pathp) + 1; + *p = _ALIGN(*p + l, 4); + + /* version 0x10 has a more compact unit name here instead of the full + * path. we accumulate the full path size using "fpsize", we'll rebuild + * it later. We detect this because the first character of the name is + * not '/'. + */ + if ((*pathp) != '/') { + new_format = 1; + if (fpsize == 0) { + /* root node: special case. fpsize accounts for path + * plus terminating zero. root node only has '/', so + * fpsize should be 2, but we want to avoid the first + * level nodes to have two '/' so we use fpsize 1 here + */ + fpsize = 1; + allocl = 2; + } else { + /* account for '/' and path size minus terminal 0 + * already in 'l' + */ + fpsize += l; + allocl = fpsize; + } + } + + + np = unflatten_dt_alloc(&mem, sizeof(struct device_node) + allocl, + __alignof__(struct device_node)); + if (allnextpp) { + memset(np, 0, sizeof(*np)); + np->full_name = ((char*)np) + sizeof(struct device_node); + if (new_format) { + char *p = np->full_name; + /* rebuild full path for new format */ + if (dad && dad->parent) { + strcpy(p, dad->full_name); +#ifdef DEBUG + if ((strlen(p) + l + 1) != allocl) { + DBG("%s: p: %d, l: %d, a: %d\n", + pathp, strlen(p), l, allocl); + } +#endif + p += strlen(p); + } + *(p++) = '/'; + memcpy(p, pathp, l); + } else + memcpy(np->full_name, pathp, l); + prev_pp = &np->properties; + **allnextpp = np; + *allnextpp = &np->allnext; + if (dad != NULL) { + np->parent = dad; + /* we temporarily use the next field as `last_child'*/ + if (dad->next == 0) + dad->child = np; + else + dad->next->sibling = np; + dad->next = np; + } + kref_init(&np->kref); + } + while(1) { + u32 sz, noff; + char *pname; + + tag = *((u32 *)(*p)); + if (tag == OF_DT_NOP) { + *p += 4; + continue; + } + if (tag != OF_DT_PROP) + break; + *p += 4; + sz = *((u32 *)(*p)); + noff = *((u32 *)((*p) + 4)); + *p += 8; + if (initial_boot_params->version < 0x10) + *p = _ALIGN(*p, sz >= 8 ? 8 : 4); + + pname = find_flat_dt_string(noff); + if (pname == NULL) { + printk("Can't find property name in list !\n"); + break; + } + if (strcmp(pname, "name") == 0) + has_name = 1; + l = strlen(pname) + 1; + pp = unflatten_dt_alloc(&mem, sizeof(struct property), + __alignof__(struct property)); + if (allnextpp) { + if (strcmp(pname, "linux,phandle") == 0) { + np->node = *((u32 *)*p); + if (np->linux_phandle == 0) + np->linux_phandle = np->node; + } + if (strcmp(pname, "ibm,phandle") == 0) + np->linux_phandle = *((u32 *)*p); + pp->name = pname; + pp->length = sz; + pp->value = (void *)*p; + *prev_pp = pp; + prev_pp = &pp->next; + } + *p = _ALIGN((*p) + sz, 4); + } + /* with version 0x10 we may not have the name property, recreate + * it here from the unit name if absent + */ + if (!has_name) { + char *p = pathp, *ps = pathp, *pa = NULL; + int sz; + + while (*p) { + if ((*p) == '@') + pa = p; + if ((*p) == '/') + ps = p + 1; + p++; + } + if (pa < ps) + pa = p; + sz = (pa - ps) + 1; + pp = unflatten_dt_alloc(&mem, sizeof(struct property) + sz, + __alignof__(struct property)); + if (allnextpp) { + pp->name = "name"; + pp->length = sz; + pp->value = (unsigned char *)(pp + 1); + *prev_pp = pp; + prev_pp = &pp->next; + memcpy(pp->value, ps, sz - 1); + ((char *)pp->value)[sz - 1] = 0; + DBG("fixed up name for %s -> %s\n", pathp, pp->value); + } + } + if (allnextpp) { + *prev_pp = NULL; + np->name = get_property(np, "name", NULL); + np->type = get_property(np, "device_type", NULL); + + if (!np->name) + np->name = "<NULL>"; + if (!np->type) + np->type = "<NULL>"; + } + while (tag == OF_DT_BEGIN_NODE) { + mem = unflatten_dt_node(mem, p, np, allnextpp, fpsize); + tag = *((u32 *)(*p)); + } + if (tag != OF_DT_END_NODE) { + printk("Weird tag at end of node: %x\n", tag); + return mem; + } + *p += 4; + return mem; +} + + +/** + * unflattens the device-tree passed by the firmware, creating the + * tree of struct device_node. It also fills the "name" and "type" + * pointers of the nodes so the normal device-tree walking functions + * can be used (this used to be done by finish_device_tree) + */ +void __init unflatten_device_tree(void) +{ + unsigned long start, mem, size; + struct device_node **allnextp = &allnodes; + char *p = NULL; + int l = 0; + + DBG(" -> unflatten_device_tree()\n"); + + /* First pass, scan for size */ + start = ((unsigned long)initial_boot_params) + + initial_boot_params->off_dt_struct; + size = unflatten_dt_node(0, &start, NULL, NULL, 0); + size = (size | 3) + 1; + + DBG(" size is %lx, allocating...\n", size); + + /* Allocate memory for the expanded device tree */ + mem = lmb_alloc(size + 4, __alignof__(struct device_node)); + if (!mem) { + DBG("Couldn't allocate memory with lmb_alloc()!\n"); + panic("Couldn't allocate memory with lmb_alloc()!\n"); + } + mem = (unsigned long) __va(mem); + + ((u32 *)mem)[size / 4] = 0xdeadbeef; + + DBG(" unflattening %lx...\n", mem); + + /* Second pass, do actual unflattening */ + start = ((unsigned long)initial_boot_params) + + initial_boot_params->off_dt_struct; + unflatten_dt_node(mem, &start, NULL, &allnextp, 0); + if (*((u32 *)start) != OF_DT_END) + printk(KERN_WARNING "Weird tag at end of tree: %08x\n", *((u32 *)start)); + if (((u32 *)mem)[size / 4] != 0xdeadbeef) + printk(KERN_WARNING "End of tree marker overwritten: %08x\n", + ((u32 *)mem)[size / 4] ); + *allnextp = NULL; + + /* Get pointer to OF "/chosen" node for use everywhere */ + of_chosen = of_find_node_by_path("/chosen"); + if (of_chosen == NULL) + of_chosen = of_find_node_by_path("/chosen@0"); + + /* Retreive command line */ + if (of_chosen != NULL) { + p = (char *)get_property(of_chosen, "bootargs", &l); + if (p != NULL && l > 0) + strlcpy(cmd_line, p, min(l, COMMAND_LINE_SIZE)); + } +#ifdef CONFIG_CMDLINE + if (l == 0 || (l == 1 && (*p) == 0)) + strlcpy(cmd_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE); +#endif /* CONFIG_CMDLINE */ + + DBG("Command line is: %s\n", cmd_line); + + DBG(" <- unflatten_device_tree()\n"); +} + + +static int __init early_init_dt_scan_cpus(unsigned long node, + const char *uname, int depth, void *data) +{ + char *type = get_flat_dt_prop(node, "device_type", NULL); + u32 *prop; + unsigned long size = 0; + + /* We are scanning "cpu" nodes only */ + if (type == NULL || strcmp(type, "cpu") != 0) + return 0; + +#ifdef CONFIG_PPC_PSERIES + /* On LPAR, look for the first ibm,pft-size property for the hash table size + */ + if (systemcfg->platform == PLATFORM_PSERIES_LPAR && ppc64_pft_size == 0) { + u32 *pft_size; + pft_size = get_flat_dt_prop(node, "ibm,pft-size", NULL); + if (pft_size != NULL) { + /* pft_size[0] is the NUMA CEC cookie */ + ppc64_pft_size = pft_size[1]; + } + } +#endif + + boot_cpuid = 0; + boot_cpuid_phys = 0; + if (initial_boot_params && initial_boot_params->version >= 2) { + /* version 2 of the kexec param format adds the phys cpuid + * of booted proc. + */ + boot_cpuid_phys = initial_boot_params->boot_cpuid_phys; + } else { + /* Check if it's the boot-cpu, set it's hw index now */ + if (get_flat_dt_prop(node, "linux,boot-cpu", NULL) != NULL) { + prop = get_flat_dt_prop(node, "reg", NULL); + if (prop != NULL) + boot_cpuid_phys = *prop; + } + } + set_hard_smp_processor_id(0, boot_cpuid_phys); + +#ifdef CONFIG_ALTIVEC + /* Check if we have a VMX and eventually update CPU features */ + prop = (u32 *)get_flat_dt_prop(node, "ibm,vmx", &size); + if (prop && (*prop) > 0) { + cur_cpu_spec->cpu_features |= CPU_FTR_ALTIVEC; + cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_ALTIVEC; + } + + /* Same goes for Apple's "altivec" property */ + prop = (u32 *)get_flat_dt_prop(node, "altivec", NULL); + if (prop) { + cur_cpu_spec->cpu_features |= CPU_FTR_ALTIVEC; + cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_ALTIVEC; + } +#endif /* CONFIG_ALTIVEC */ + +#ifdef CONFIG_PPC_PSERIES + /* + * Check for an SMT capable CPU and set the CPU feature. We do + * this by looking at the size of the ibm,ppc-interrupt-server#s + * property + */ + prop = (u32 *)get_flat_dt_prop(node, "ibm,ppc-interrupt-server#s", + &size); + cur_cpu_spec->cpu_features &= ~CPU_FTR_SMT; + if (prop && ((size / sizeof(u32)) > 1)) + cur_cpu_spec->cpu_features |= CPU_FTR_SMT; +#endif + + return 0; +} + +static int __init early_init_dt_scan_chosen(unsigned long node, + const char *uname, int depth, void *data) +{ + u32 *prop; + unsigned long *lprop; + + DBG("search \"chosen\", depth: %d, uname: %s\n", depth, uname); + + if (depth != 1 || + (strcmp(uname, "chosen") != 0 && strcmp(uname, "chosen@0") != 0)) + return 0; + + /* get platform type */ + prop = (u32 *)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 */ + if (get_flat_dt_prop(node, "linux,iommu-off", NULL) != NULL) + iommu_is_off = 1; + if (get_flat_dt_prop(node, "linux,iommu-force-on", NULL) != NULL) + iommu_force_on = 1; +#endif + + lprop = get_flat_dt_prop(node, "linux,memory-limit", NULL); + if (lprop) + memory_limit = *lprop; + +#ifdef CONFIG_PPC64 + lprop = get_flat_dt_prop(node, "linux,tce-alloc-start", NULL); + if (lprop) + tce_alloc_start = *lprop; + lprop = get_flat_dt_prop(node, "linux,tce-alloc-end", NULL); + if (lprop) + tce_alloc_end = *lprop; +#endif + +#ifdef CONFIG_PPC_RTAS + /* To help early debugging via the front panel, we retreive a minimal + * set of RTAS infos now if available + */ + { + u64 *basep, *entryp; + + basep = get_flat_dt_prop(node, "linux,rtas-base", NULL); + entryp = get_flat_dt_prop(node, "linux,rtas-entry", NULL); + prop = get_flat_dt_prop(node, "linux,rtas-size", NULL); + if (basep && entryp && prop) { + rtas.base = *basep; + rtas.entry = *entryp; + rtas.size = *prop; + } + } +#endif /* CONFIG_PPC_RTAS */ + + /* break now */ + return 1; +} + +static int __init early_init_dt_scan_root(unsigned long node, + const char *uname, int depth, void *data) +{ + u32 *prop; + + if (depth != 0) + return 0; + + prop = get_flat_dt_prop(node, "#size-cells", NULL); + dt_root_size_cells = (prop == NULL) ? 1 : *prop; + DBG("dt_root_size_cells = %x\n", dt_root_size_cells); + + prop = get_flat_dt_prop(node, "#address-cells", NULL); + dt_root_addr_cells = (prop == NULL) ? 2 : *prop; + DBG("dt_root_addr_cells = %x\n", dt_root_addr_cells); + + /* break now */ + return 1; +} + +static unsigned long __init dt_mem_next_cell(int s, cell_t **cellp) +{ + cell_t *p = *cellp; + unsigned long r; + + /* Ignore more than 2 cells */ + while (s > sizeof(unsigned long) / 4) { + p++; + s--; + } + r = *p++; +#ifdef CONFIG_PPC64 + if (s > 1) { + r <<= 32; + r |= *(p++); + s--; + } +#endif + + *cellp = p; + return r; +} + + +static int __init early_init_dt_scan_memory(unsigned long node, + const char *uname, int depth, void *data) +{ + char *type = get_flat_dt_prop(node, "device_type", NULL); + cell_t *reg, *endp; + unsigned long l; + + /* We are scanning "memory" nodes only */ + if (type == NULL || strcmp(type, "memory") != 0) + return 0; + + reg = (cell_t *)get_flat_dt_prop(node, "reg", &l); + if (reg == NULL) + return 0; + + endp = reg + (l / sizeof(cell_t)); + + DBG("memory scan node %s ..., reg size %ld, data: %x %x %x %x, ...\n", + uname, l, reg[0], reg[1], reg[2], reg[3]); + + while ((endp - reg) >= (dt_root_addr_cells + dt_root_size_cells)) { + unsigned long base, size; + + base = dt_mem_next_cell(dt_root_addr_cells, ®); + size = dt_mem_next_cell(dt_root_size_cells, ®); + + if (size == 0) + continue; + DBG(" - %lx , %lx\n", base, size); +#ifdef CONFIG_PPC64 + if (iommu_is_off) { + if (base >= 0x80000000ul) + continue; + if ((base + size) > 0x80000000ul) + size = 0x80000000ul - base; + } +#endif + lmb_add(base, size); + } + return 0; +} + +static void __init early_reserve_mem(void) +{ + unsigned long base, size; + unsigned long *reserve_map; + + reserve_map = (unsigned long *)(((unsigned long)initial_boot_params) + + initial_boot_params->off_mem_rsvmap); + while (1) { + base = *(reserve_map++); + size = *(reserve_map++); + if (size == 0) + break; + DBG("reserving: %lx -> %lx\n", base, size); + lmb_reserve(base, size); + } + +#if 0 + DBG("memory reserved, lmbs :\n"); + lmb_dump_all(); +#endif +} + +void __init early_init_devtree(void *params) +{ + DBG(" -> early_init_devtree()\n"); + + /* Setup flat device-tree pointer */ + initial_boot_params = params; + + /* Retrieve various informations from the /chosen node of the + * device-tree, including the platform type, initrd location and + * size, TCE reserve, and more ... + */ + scan_flat_dt(early_init_dt_scan_chosen, NULL); + + /* Scan memory nodes and rebuild LMBs */ + lmb_init(); + scan_flat_dt(early_init_dt_scan_root, NULL); + 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()); + + /* Reserve LMB regions used by kernel, initrd, dt, etc... */ + early_reserve_mem(); + + DBG("Scanning CPUs ...\n"); + + /* Retreive hash table size from flattened tree plus other + * CPU related informations (altivec support, boot CPU ID, ...) + */ + scan_flat_dt(early_init_dt_scan_cpus, NULL); + + DBG(" <- early_init_devtree()\n"); +} + +#undef printk + +int +prom_n_addr_cells(struct device_node* np) +{ + int* ip; + do { + if (np->parent) + np = np->parent; + ip = (int *) get_property(np, "#address-cells", NULL); + if (ip != NULL) + return *ip; + } while (np->parent); + /* No #address-cells property for the root node, default to 1 */ + return 1; +} + +int +prom_n_size_cells(struct device_node* np) +{ + int* ip; + do { + if (np->parent) + np = np->parent; + ip = (int *) get_property(np, "#size-cells", NULL); + if (ip != NULL) + return *ip; + } while (np->parent); + /* No #size-cells property for the root node, default to 1 */ + return 1; +} + +/** + * Work out the sense (active-low level / active-high edge) + * of each interrupt from the device tree. + */ +void __init prom_get_irq_senses(unsigned char *senses, int off, int max) +{ + struct device_node *np; + int i, j; + + /* default to level-triggered */ + memset(senses, IRQ_SENSE_LEVEL | IRQ_POLARITY_NEGATIVE, max - off); + + for (np = allnodes; np != 0; np = np->allnext) { + for (j = 0; j < np->n_intrs; j++) { + i = np->intrs[j].line; + if (i >= off && i < max) + senses[i-off] = np->intrs[j].sense; + } + } +} + +/** + * Construct and return a list of the device_nodes with a given name. + */ +struct device_node *find_devices(const char *name) +{ + struct device_node *head, **prevp, *np; + + prevp = &head; + for (np = allnodes; np != 0; np = np->allnext) { + if (np->name != 0 && strcasecmp(np->name, name) == 0) { + *prevp = np; + prevp = &np->next; + } + } + *prevp = NULL; + return head; +} +EXPORT_SYMBOL(find_devices); + +/** + * Construct and return a list of the device_nodes with a given type. + */ +struct device_node *find_type_devices(const char *type) +{ + struct device_node *head, **prevp, *np; + + prevp = &head; + for (np = allnodes; np != 0; np = np->allnext) { + if (np->type != 0 && strcasecmp(np->type, type) == 0) { + *prevp = np; + prevp = &np->next; + } + } + *prevp = NULL; + return head; +} +EXPORT_SYMBOL(find_type_devices); + +/** + * Returns all nodes linked together + */ +struct device_node *find_all_nodes(void) +{ + struct device_node *head, **prevp, *np; + + prevp = &head; + for (np = allnodes; np != 0; np = np->allnext) { + *prevp = np; + prevp = &np->next; + } + *prevp = NULL; + return head; +} +EXPORT_SYMBOL(find_all_nodes); + +/** Checks if the given "compat" string matches one of the strings in + * the device's "compatible" property + */ +int device_is_compatible(struct device_node *device, const char *compat) +{ + const char* cp; + int cplen, l; + + cp = (char *) get_property(device, "compatible", &cplen); + if (cp == NULL) + return 0; + while (cplen > 0) { + if (strncasecmp(cp, compat, strlen(compat)) == 0) + return 1; + l = strlen(cp) + 1; + cp += l; + cplen -= l; + } + + return 0; +} +EXPORT_SYMBOL(device_is_compatible); + + +/** + * Indicates whether the root node has a given value in its + * compatible property. + */ +int machine_is_compatible(const char *compat) +{ + struct device_node *root; + int rc = 0; + + root = of_find_node_by_path("/"); + if (root) { + rc = device_is_compatible(root, compat); + of_node_put(root); + } + return rc; +} +EXPORT_SYMBOL(machine_is_compatible); + +/** + * Construct and return a list of the device_nodes with a given type + * and compatible property. + */ +struct device_node *find_compatible_devices(const char *type, + const char *compat) +{ + struct device_node *head, **prevp, *np; + + prevp = &head; + for (np = allnodes; np != 0; np = np->allnext) { + if (type != NULL + && !(np->type != 0 && strcasecmp(np->type, type) == 0)) + continue; + if (device_is_compatible(np, compat)) { + *prevp = np; + prevp = &np->next; + } + } + *prevp = NULL; + return head; +} +EXPORT_SYMBOL(find_compatible_devices); + +/** + * Find the device_node with a given full_name. + */ +struct device_node *find_path_device(const char *path) +{ + struct device_node *np; + + for (np = allnodes; np != 0; np = np->allnext) + if (np->full_name != 0 && strcasecmp(np->full_name, path) == 0) + return np; + return NULL; +} +EXPORT_SYMBOL(find_path_device); + +/******* + * + * New implementation of the OF "find" APIs, return a refcounted + * object, call of_node_put() when done. The device tree and list + * are protected by a rw_lock. + * + * Note that property management will need some locking as well, + * this isn't dealt with yet. + * + *******/ + +/** + * of_find_node_by_name - Find a node by its "name" property + * @from: The node to start searching from or NULL, the node + * you pass will not be searched, only the next one + * will; typically, you pass what the previous call + * returned. of_node_put() will be called on it + * @name: The name string to match against + * + * Returns a node pointer with refcount incremented, use + * of_node_put() on it when done. + */ +struct device_node *of_find_node_by_name(struct device_node *from, + const char *name) +{ + struct device_node *np; + + read_lock(&devtree_lock); + np = from ? from->allnext : allnodes; + for (; np != 0; np = np->allnext) + if (np->name != 0 && strcasecmp(np->name, name) == 0 + && of_node_get(np)) + break; + if (from) + of_node_put(from); + read_unlock(&devtree_lock); + return np; +} +EXPORT_SYMBOL(of_find_node_by_name); + +/** + * of_find_node_by_type - Find a node by its "device_type" property + * @from: The node to start searching from or NULL, the node + * you pass will not be searched, only the next one + * will; typically, you pass what the previous call + * returned. of_node_put() will be called on it + * @name: The type string to match against + * + * Returns a node pointer with refcount incremented, use + * of_node_put() on it when done. + */ +struct device_node *of_find_node_by_type(struct device_node *from, + const char *type) +{ + struct device_node *np; + + read_lock(&devtree_lock); + np = from ? from->allnext : allnodes; + for (; np != 0; np = np->allnext) + if (np->type != 0 && strcasecmp(np->type, type) == 0 + && of_node_get(np)) + break; + if (from) + of_node_put(from); + read_unlock(&devtree_lock); + return np; +} +EXPORT_SYMBOL(of_find_node_by_type); + +/** + * of_find_compatible_node - Find a node based on type and one of the + * tokens in its "compatible" property + * @from: The node to start searching from or NULL, the node + * you pass will not be searched, only the next one + * will; typically, you pass what the previous call + * returned. of_node_put() will be called on it + * @type: The type string to match "device_type" or NULL to ignore + * @compatible: The string to match to one of the tokens in the device + * "compatible" list. + * + * Returns a node pointer with refcount incremented, use + * of_node_put() on it when done. + */ +struct device_node *of_find_compatible_node(struct device_node *from, + const char *type, const char *compatible) +{ + struct device_node *np; + + read_lock(&devtree_lock); + np = from ? from->allnext : allnodes; + for (; np != 0; np = np->allnext) { + if (type != NULL + && !(np->type != 0 && strcasecmp(np->type, type) == 0)) + continue; + if (device_is_compatible(np, compatible) && of_node_get(np)) + break; + } + if (from) + of_node_put(from); + read_unlock(&devtree_lock); + return np; +} +EXPORT_SYMBOL(of_find_compatible_node); + +/** + * of_find_node_by_path - Find a node matching a full OF path + * @path: The full path to match + * + * Returns a node pointer with refcount incremented, use + * of_node_put() on it when done. + */ +struct device_node *of_find_node_by_path(const char *path) +{ + struct device_node *np = allnodes; + + read_lock(&devtree_lock); + for (; np != 0; np = np->allnext) { + if (np->full_name != 0 && strcasecmp(np->full_name, path) == 0 + && of_node_get(np)) + break; + } + read_unlock(&devtree_lock); + return np; +} +EXPORT_SYMBOL(of_find_node_by_path); + +/** + * of_find_node_by_phandle - Find a node given a phandle + * @handle: phandle of the node to find + * + * Returns a node pointer with refcount incremented, use + * of_node_put() on it when done. + */ +struct device_node *of_find_node_by_phandle(phandle handle) +{ + struct device_node *np; + + read_lock(&devtree_lock); + for (np = allnodes; np != 0; np = np->allnext) + if (np->linux_phandle == handle) + break; + if (np) + of_node_get(np); + read_unlock(&devtree_lock); + return np; +} +EXPORT_SYMBOL(of_find_node_by_phandle); + +/** + * of_find_all_nodes - Get next node in global list + * @prev: Previous node or NULL to start iteration + * of_node_put() will be called on it + * + * Returns a node pointer with refcount incremented, use + * of_node_put() on it when done. + */ +struct device_node *of_find_all_nodes(struct device_node *prev) +{ + struct device_node *np; + + read_lock(&devtree_lock); + np = prev ? prev->allnext : allnodes; + for (; np != 0; np = np->allnext) + if (of_node_get(np)) + break; + if (prev) + of_node_put(prev); + read_unlock(&devtree_lock); + return np; +} +EXPORT_SYMBOL(of_find_all_nodes); + +/** + * of_get_parent - Get a node's parent if any + * @node: Node to get parent + * + * Returns a node pointer with refcount incremented, use + * of_node_put() on it when done. + */ +struct device_node *of_get_parent(const struct device_node *node) +{ + struct device_node *np; + + if (!node) + return NULL; + + read_lock(&devtree_lock); + np = of_node_get(node->parent); + read_unlock(&devtree_lock); + return np; +} +EXPORT_SYMBOL(of_get_parent); + +/** + * of_get_next_child - Iterate a node childs + * @node: parent node + * @prev: previous child of the parent node, or NULL to get first + * + * Returns a node pointer with refcount incremented, use + * of_node_put() on it when done. + */ +struct device_node *of_get_next_child(const struct device_node *node, + struct device_node *prev) +{ + struct device_node *next; + + read_lock(&devtree_lock); + next = prev ? prev->sibling : node->child; + for (; next != 0; next = next->sibling) + if (of_node_get(next)) + break; + if (prev) + of_node_put(prev); + read_unlock(&devtree_lock); + return next; +} +EXPORT_SYMBOL(of_get_next_child); + +/** + * of_node_get - Increment refcount of a node + * @node: Node to inc refcount, NULL is supported to + * simplify writing of callers + * + * Returns node. + */ +struct device_node *of_node_get(struct device_node *node) +{ + if (node) + kref_get(&node->kref); + return node; +} +EXPORT_SYMBOL(of_node_get); + +static inline struct device_node * kref_to_device_node(struct kref *kref) +{ + return container_of(kref, struct device_node, kref); +} + +/** + * of_node_release - release a dynamically allocated node + * @kref: kref element of the node to be released + * + * In of_node_put() this function is passed to kref_put() + * as the destructor. + */ +static void of_node_release(struct kref *kref) +{ + struct device_node *node = kref_to_device_node(kref); + struct property *prop = node->properties; + + if (!OF_IS_DYNAMIC(node)) + return; + while (prop) { + struct property *next = prop->next; + kfree(prop->name); + kfree(prop->value); + kfree(prop); + prop = next; + } + kfree(node->intrs); + kfree(node->addrs); + kfree(node->full_name); + kfree(node->data); + kfree(node); +} + +/** + * of_node_put - Decrement refcount of a node + * @node: Node to dec refcount, NULL is supported to + * simplify writing of callers + * + */ +void of_node_put(struct device_node *node) +{ + if (node) + kref_put(&node->kref, of_node_release); +} +EXPORT_SYMBOL(of_node_put); + +/* + * Plug a device node into the tree and global list. + */ +void of_attach_node(struct device_node *np) +{ + write_lock(&devtree_lock); + np->sibling = np->parent->child; + np->allnext = allnodes; + np->parent->child = np; + allnodes = np; + write_unlock(&devtree_lock); +} + +/* + * "Unplug" a node from the device tree. The caller must hold + * a reference to the node. The memory associated with the node + * is not freed until its refcount goes to zero. + */ +void of_detach_node(const struct device_node *np) +{ + struct device_node *parent; + + write_lock(&devtree_lock); + + parent = np->parent; + + if (allnodes == np) + allnodes = np->allnext; + else { + struct device_node *prev; + for (prev = allnodes; + prev->allnext != np; + prev = prev->allnext) + ; + prev->allnext = np->allnext; + } + + if (parent->child == np) + parent->child = np->sibling; + else { + struct device_node *prevsib; + for (prevsib = np->parent->child; + prevsib->sibling != np; + prevsib = prevsib->sibling) + ; + prevsib->sibling = np->sibling; + } + + write_unlock(&devtree_lock); +} + +#ifdef CONFIG_PPC_PSERIES +/* + * Fix up the uninitialized fields in a new device node: + * name, type, n_addrs, addrs, n_intrs, intrs, and pci-specific fields + * + * A lot of boot-time code is duplicated here, because functions such + * as finish_node_interrupts, interpret_pci_props, etc. cannot use the + * slab allocator. + * + * This should probably be split up into smaller chunks. + */ + +static int of_finish_dynamic_node(struct device_node *node, + unsigned long *unused1, int unused2, + int unused3, int unused4) +{ + struct device_node *parent = of_get_parent(node); + int err = 0; + phandle *ibm_phandle; + + node->name = get_property(node, "name", NULL); + node->type = get_property(node, "device_type", NULL); + + if (!parent) { + err = -ENODEV; + goto out; + } + + /* We don't support that function on PowerMac, at least + * not yet + */ + if (systemcfg->platform == PLATFORM_POWERMAC) + return -ENODEV; + + /* fix up new node's linux_phandle field */ + if ((ibm_phandle = (unsigned int *)get_property(node, "ibm,phandle", NULL))) + node->linux_phandle = *ibm_phandle; + +out: + of_node_put(parent); + return err; +} + +static int prom_reconfig_notifier(struct notifier_block *nb, + unsigned long action, void *node) +{ + int err; + + switch (action) { + case PSERIES_RECONFIG_ADD: + err = finish_node(node, NULL, of_finish_dynamic_node, 0, 0, 0); + if (err < 0) { + printk(KERN_ERR "finish_node returned %d\n", err); + err = NOTIFY_BAD; + } + break; + default: + err = NOTIFY_DONE; + break; + } + return err; +} + +static struct notifier_block prom_reconfig_nb = { + .notifier_call = prom_reconfig_notifier, + .priority = 10, /* This one needs to run first */ +}; + +static int __init prom_reconfig_setup(void) +{ + return pSeries_reconfig_notifier_register(&prom_reconfig_nb); +} +__initcall(prom_reconfig_setup); +#endif + +/* + * Find a property with a given name for a given node + * and return the value. + */ +unsigned char *get_property(struct device_node *np, const char *name, + int *lenp) +{ + struct property *pp; + + for (pp = np->properties; pp != 0; pp = pp->next) + if (strcmp(pp->name, name) == 0) { + if (lenp != 0) + *lenp = pp->length; + return pp->value; + } + return NULL; +} +EXPORT_SYMBOL(get_property); + +/* + * Add a property to a node + */ +void prom_add_property(struct device_node* np, struct property* prop) +{ + struct property **next = &np->properties; + + prop->next = NULL; + while (*next) + next = &(*next)->next; + *next = prop; +} + +/* I quickly hacked that one, check against spec ! */ +static inline unsigned long +bus_space_to_resource_flags(unsigned int bus_space) +{ + u8 space = (bus_space >> 24) & 0xf; + if (space == 0) + space = 0x02; + if (space == 0x02) + return IORESOURCE_MEM; + else if (space == 0x01) + return IORESOURCE_IO; + else { + printk(KERN_WARNING "prom.c: bus_space_to_resource_flags(), space: %x\n", + bus_space); + return 0; + } +} + +#ifdef CONFIG_PCI +static struct resource *find_parent_pci_resource(struct pci_dev* pdev, + struct address_range *range) +{ + unsigned long mask; + int i; + + /* Check this one */ + mask = bus_space_to_resource_flags(range->space); + for (i=0; i<DEVICE_COUNT_RESOURCE; i++) { + if ((pdev->resource[i].flags & mask) == mask && + pdev->resource[i].start <= range->address && + pdev->resource[i].end > range->address) { + if ((range->address + range->size - 1) > pdev->resource[i].end) { + /* Add better message */ + printk(KERN_WARNING "PCI/OF resource overlap !\n"); + return NULL; + } + break; + } + } + if (i == DEVICE_COUNT_RESOURCE) + return NULL; + return &pdev->resource[i]; +} + +/* + * Request an OF device resource. Currently handles child of PCI devices, + * or other nodes attached to the root node. Ultimately, put some + * link to resources in the OF node. + */ +struct resource *request_OF_resource(struct device_node* node, int index, + const char* name_postfix) +{ + struct pci_dev* pcidev; + u8 pci_bus, pci_devfn; + unsigned long iomask; + struct device_node* nd; + struct resource* parent; + struct resource *res = NULL; + int nlen, plen; + + if (index >= node->n_addrs) + goto fail; + + /* Sanity check on bus space */ + iomask = bus_space_to_resource_flags(node->addrs[index].space); + if (iomask & IORESOURCE_MEM) + parent = &iomem_resource; + else if (iomask & IORESOURCE_IO) + parent = &ioport_resource; + else + goto fail; + + /* Find a PCI parent if any */ + nd = node; + pcidev = NULL; + while (nd) { + if (!pci_device_from_OF_node(nd, &pci_bus, &pci_devfn)) + pcidev = pci_find_slot(pci_bus, pci_devfn); + if (pcidev) break; + nd = nd->parent; + } + if (pcidev) + parent = find_parent_pci_resource(pcidev, &node->addrs[index]); + if (!parent) { + printk(KERN_WARNING "request_OF_resource(%s), parent not found\n", + node->name); + goto fail; + } + + res = __request_region(parent, node->addrs[index].address, + node->addrs[index].size, NULL); + if (!res) + goto fail; + nlen = strlen(node->name); + plen = name_postfix ? strlen(name_postfix) : 0; + res->name = (const char *)kmalloc(nlen+plen+1, GFP_KERNEL); + if (res->name) { + strcpy((char *)res->name, node->name); + if (plen) + strcpy((char *)res->name+nlen, name_postfix); + } + return res; +fail: + return NULL; +} +EXPORT_SYMBOL(request_OF_resource); + +int release_OF_resource(struct device_node *node, int index) +{ + struct pci_dev* pcidev; + u8 pci_bus, pci_devfn; + unsigned long iomask, start, end; + struct device_node* nd; + struct resource* parent; + struct resource *res = NULL; + + if (index >= node->n_addrs) + return -EINVAL; + + /* Sanity check on bus space */ + iomask = bus_space_to_resource_flags(node->addrs[index].space); + if (iomask & IORESOURCE_MEM) + parent = &iomem_resource; + else if (iomask & IORESOURCE_IO) + parent = &ioport_resource; + else + return -EINVAL; + + /* Find a PCI parent if any */ + nd = node; + pcidev = NULL; + while(nd) { + if (!pci_device_from_OF_node(nd, &pci_bus, &pci_devfn)) + pcidev = pci_find_slot(pci_bus, pci_devfn); + if (pcidev) break; + nd = nd->parent; + } + if (pcidev) + parent = find_parent_pci_resource(pcidev, &node->addrs[index]); + if (!parent) { + printk(KERN_WARNING "release_OF_resource(%s), parent not found\n", + node->name); + return -ENODEV; + } + + /* Find us in the parent and its childs */ + res = parent->child; + start = node->addrs[index].address; + end = start + node->addrs[index].size - 1; + while (res) { + if (res->start == start && res->end == end && + (res->flags & IORESOURCE_BUSY)) + break; + if (res->start <= start && res->end >= end) + res = res->child; + else + res = res->sibling; + } + if (!res) + return -ENODEV; + + if (res->name) { + kfree(res->name); + res->name = NULL; + } + release_resource(res); + kfree(res); + + return 0; +} +EXPORT_SYMBOL(release_OF_resource); +#endif /* CONFIG_PCI */ diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c new file mode 100644 index 000000000000..9750b3cd8ecd --- /dev/null +++ b/arch/powerpc/kernel/prom_init.c @@ -0,0 +1,2109 @@ +/* + * Procedures for interfacing to Open Firmware. + * + * Paul Mackerras August 1996. + * Copyright (C) 1996-2005 Paul Mackerras. + * + * Adapted for 64bit PowerPC by Dave Engebretsen and Peter Bergner. + * {engebret|bergner}@us.ibm.com + * + * 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. + */ + +#undef DEBUG_PROM + +#include <stdarg.h> +#include <linux/config.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/init.h> +#include <linux/threads.h> +#include <linux/spinlock.h> +#include <linux/types.h> +#include <linux/pci.h> +#include <linux/proc_fs.h> +#include <linux/stringify.h> +#include <linux/delay.h> +#include <linux/initrd.h> +#include <linux/bitops.h> +#include <asm/prom.h> +#include <asm/rtas.h> +#include <asm/page.h> +#include <asm/processor.h> +#include <asm/irq.h> +#include <asm/io.h> +#include <asm/smp.h> +#include <asm/system.h> +#include <asm/mmu.h> +#include <asm/pgtable.h> +#include <asm/pci.h> +#include <asm/iommu.h> +#include <asm/btext.h> +#include <asm/sections.h> +#include <asm/machdep.h> + +#ifdef CONFIG_LOGO_LINUX_CLUT224 +#include <linux/linux_logo.h> +extern const struct linux_logo logo_linux_clut224; +#endif + +/* + * Properties whose value is longer than this get excluded from our + * copy of the device tree. This value does need to be big enough to + * ensure that we don't lose things like the interrupt-map property + * on a PCI-PCI bridge. + */ +#define MAX_PROPERTY_LENGTH (1UL * 1024 * 1024) + +/* + * Eventually bump that one up + */ +#define DEVTREE_CHUNK_SIZE 0x100000 + +/* + * This is the size of the local memory reserve map that gets copied + * into the boot params passed to the kernel. That size is totally + * flexible as the kernel just reads the list until it encounters an + * entry with size 0, so it can be changed without breaking binary + * compatibility + */ +#define MEM_RESERVE_MAP_SIZE 8 + +/* + * prom_init() is called very early on, before the kernel text + * and data have been mapped to KERNELBASE. At this point the code + * is running at whatever address it has been loaded at. + * On ppc32 we compile with -mrelocatable, which means that references + * to extern and static variables get relocated automatically. + * On ppc64 we have to relocate the references explicitly with + * RELOC. (Note that strings count as static variables.) + * + * Because OF may have mapped I/O devices into the area starting at + * KERNELBASE, particularly on CHRP machines, we can't safely call + * OF once the kernel has been mapped to KERNELBASE. Therefore all + * OF calls must be done within prom_init(). + * + * ADDR is used in calls to call_prom. The 4th and following + * arguments to call_prom should be 32-bit values. + * On ppc64, 64 bit values are truncated to 32 bits (and + * fortunately don't get interpreted as two arguments). + */ +#ifdef CONFIG_PPC64 +#define RELOC(x) (*PTRRELOC(&(x))) +#define ADDR(x) (u32) add_reloc_offset((unsigned long)(x)) +#else +#define RELOC(x) (x) +#define ADDR(x) (u32) (x) +#endif + +#define PROM_BUG() do { \ + prom_printf("kernel BUG at %s line 0x%x!\n", \ + RELOC(__FILE__), __LINE__); \ + __asm__ __volatile__(".long " BUG_ILLEGAL_INSTR); \ +} while (0) + +#ifdef DEBUG_PROM +#define prom_debug(x...) prom_printf(x) +#else +#define prom_debug(x...) +#endif + +#ifdef CONFIG_PPC32 +#define PLATFORM_POWERMAC _MACH_Pmac +#define PLATFORM_CHRP _MACH_chrp +#endif + + +typedef u32 prom_arg_t; + +struct prom_args { + u32 service; + u32 nargs; + u32 nret; + prom_arg_t args[10]; +}; + +struct prom_t { + ihandle root; + ihandle chosen; + int cpu; + ihandle stdout; + ihandle mmumap; +}; + +struct mem_map_entry { + unsigned long base; + unsigned long size; +}; + +typedef u32 cell_t; + +extern void __start(unsigned long r3, unsigned long r4, unsigned long r5); + +#ifdef CONFIG_PPC64 +extern int enter_prom(struct prom_args *args, unsigned long entry); +#else +static inline int enter_prom(struct prom_args *args, unsigned long entry) +{ + return ((int (*)(struct prom_args *))entry)(args); +} +#endif + +extern void copy_and_flush(unsigned long dest, unsigned long src, + unsigned long size, unsigned long offset); + +/* prom structure */ +static struct prom_t __initdata prom; + +static unsigned long prom_entry __initdata; + +#define PROM_SCRATCH_SIZE 256 + +static char __initdata of_stdout_device[256]; +static char __initdata prom_scratch[PROM_SCRATCH_SIZE]; + +static unsigned long __initdata dt_header_start; +static unsigned long __initdata dt_struct_start, dt_struct_end; +static unsigned long __initdata dt_string_start, dt_string_end; + +static unsigned long __initdata prom_initrd_start, prom_initrd_end; + +#ifdef CONFIG_PPC64 +static int __initdata iommu_force_on; +static int __initdata ppc64_iommu_off; +static unsigned long __initdata prom_tce_alloc_start; +static unsigned long __initdata prom_tce_alloc_end; +#endif + +static int __initdata of_platform; + +static char __initdata prom_cmd_line[COMMAND_LINE_SIZE]; + +static unsigned long __initdata prom_memory_limit; + +static unsigned long __initdata alloc_top; +static unsigned long __initdata alloc_top_high; +static unsigned long __initdata alloc_bottom; +static unsigned long __initdata rmo_top; +static unsigned long __initdata ram_top; + +static struct mem_map_entry __initdata mem_reserve_map[MEM_RESERVE_MAP_SIZE]; +static int __initdata mem_reserve_cnt; + +static cell_t __initdata regbuf[1024]; + + +#define MAX_CPU_THREADS 2 + +/* TO GO */ +#ifdef CONFIG_HMT +struct { + unsigned int pir; + unsigned int threadid; +} hmt_thread_data[NR_CPUS]; +#endif /* CONFIG_HMT */ + +/* + * Error results ... some OF calls will return "-1" on error, some + * will return 0, some will return either. To simplify, here are + * macros to use with any ihandle or phandle return value to check if + * it is valid + */ + +#define PROM_ERROR (-1u) +#define PHANDLE_VALID(p) ((p) != 0 && (p) != PROM_ERROR) +#define IHANDLE_VALID(i) ((i) != 0 && (i) != PROM_ERROR) + + +/* This is the one and *ONLY* place where we actually call open + * firmware. + */ + +static int __init call_prom(const char *service, int nargs, int nret, ...) +{ + int i; + struct prom_args args; + va_list list; + + args.service = ADDR(service); + args.nargs = nargs; + args.nret = nret; + + va_start(list, nret); + for (i = 0; i < nargs; i++) + args.args[i] = va_arg(list, prom_arg_t); + va_end(list); + + for (i = 0; i < nret; i++) + args.args[nargs+i] = 0; + + if (enter_prom(&args, RELOC(prom_entry)) < 0) + return PROM_ERROR; + + return (nret > 0) ? args.args[nargs] : 0; +} + +static int __init call_prom_ret(const char *service, int nargs, int nret, + prom_arg_t *rets, ...) +{ + int i; + struct prom_args args; + va_list list; + + args.service = ADDR(service); + args.nargs = nargs; + args.nret = nret; + + va_start(list, rets); + for (i = 0; i < nargs; i++) + args.args[i] = va_arg(list, prom_arg_t); + va_end(list); + + for (i = 0; i < nret; i++) + rets[nargs+i] = 0; + + if (enter_prom(&args, RELOC(prom_entry)) < 0) + return PROM_ERROR; + + if (rets != NULL) + for (i = 1; i < nret; ++i) + rets[i-1] = args.args[nargs+i]; + + return (nret > 0) ? args.args[nargs] : 0; +} + + +static void __init prom_print(const char *msg) +{ + const char *p, *q; + struct prom_t *_prom = &RELOC(prom); + + if (_prom->stdout == 0) + return; + + for (p = msg; *p != 0; p = q) { + for (q = p; *q != 0 && *q != '\n'; ++q) + ; + if (q > p) + call_prom("write", 3, 1, _prom->stdout, p, q - p); + if (*q == 0) + break; + ++q; + call_prom("write", 3, 1, _prom->stdout, ADDR("\r\n"), 2); + } +} + + +static void __init prom_print_hex(unsigned long val) +{ + int i, nibbles = sizeof(val)*2; + char buf[sizeof(val)*2+1]; + struct prom_t *_prom = &RELOC(prom); + + for (i = nibbles-1; i >= 0; i--) { + buf[i] = (val & 0xf) + '0'; + if (buf[i] > '9') + buf[i] += ('a'-'0'-10); + val >>= 4; + } + buf[nibbles] = '\0'; + call_prom("write", 3, 1, _prom->stdout, buf, nibbles); +} + + +static void __init prom_printf(const char *format, ...) +{ + const char *p, *q, *s; + va_list args; + unsigned long v; + struct prom_t *_prom = &RELOC(prom); + + va_start(args, format); +#ifdef CONFIG_PPC64 + format = PTRRELOC(format); +#endif + for (p = format; *p != 0; p = q) { + for (q = p; *q != 0 && *q != '\n' && *q != '%'; ++q) + ; + if (q > p) + call_prom("write", 3, 1, _prom->stdout, p, q - p); + if (*q == 0) + break; + if (*q == '\n') { + ++q; + call_prom("write", 3, 1, _prom->stdout, + ADDR("\r\n"), 2); + continue; + } + ++q; + if (*q == 0) + break; + switch (*q) { + case 's': + ++q; + s = va_arg(args, const char *); + prom_print(s); + break; + case 'x': + ++q; + v = va_arg(args, unsigned long); + prom_print_hex(v); + break; + } + } +} + + +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 */ + call_prom("call-method", 6, 1, + ADDR("map"), _prom->mmumap, 0, size, virt, virt); + return ret; +} + +static void __init __attribute__((noreturn)) prom_panic(const char *reason) +{ +#ifdef CONFIG_PPC64 + reason = PTRRELOC(reason); +#endif + prom_print(reason); + /* ToDo: should put up an SRC here on p/iSeries */ + call_prom("exit", 0, 0); + + for (;;) /* should never get here */ + ; +} + + +static int __init prom_next_node(phandle *nodep) +{ + phandle node; + + if ((node = *nodep) != 0 + && (*nodep = call_prom("child", 1, 1, node)) != 0) + return 1; + if ((*nodep = call_prom("peer", 1, 1, node)) != 0) + return 1; + for (;;) { + if ((node = call_prom("parent", 1, 1, node)) == 0) + return 0; + if ((*nodep = call_prom("peer", 1, 1, node)) != 0) + return 1; + } +} + +static int __init prom_getprop(phandle node, const char *pname, + void *value, size_t valuelen) +{ + return call_prom("getprop", 4, 1, node, ADDR(pname), + (u32)(unsigned long) value, (u32) valuelen); +} + +static int __init prom_getproplen(phandle node, const char *pname) +{ + return call_prom("getproplen", 2, 1, node, ADDR(pname)); +} + +static int __init prom_setprop(phandle node, const char *pname, + void *value, size_t valuelen) +{ + return call_prom("setprop", 4, 1, node, ADDR(pname), + (u32)(unsigned long) value, (u32) valuelen); +} + +/* We can't use the standard versions because of RELOC headaches. */ +#define isxdigit(c) (('0' <= (c) && (c) <= '9') \ + || ('a' <= (c) && (c) <= 'f') \ + || ('A' <= (c) && (c) <= 'F')) + +#define isdigit(c) ('0' <= (c) && (c) <= '9') +#define islower(c) ('a' <= (c) && (c) <= 'z') +#define toupper(c) (islower(c) ? ((c) - 'a' + 'A') : (c)) + +unsigned long prom_strtoul(const char *cp, const char **endp) +{ + unsigned long result = 0, base = 10, value; + + if (*cp == '0') { + base = 8; + cp++; + if (toupper(*cp) == 'X') { + cp++; + base = 16; + } + } + + while (isxdigit(*cp) && + (value = isdigit(*cp) ? *cp - '0' : toupper(*cp) - 'A' + 10) < base) { + result = result * base + value; + cp++; + } + + if (endp) + *endp = cp; + + return result; +} + +unsigned long prom_memparse(const char *ptr, const char **retptr) +{ + unsigned long ret = prom_strtoul(ptr, retptr); + int shift = 0; + + /* + * We can't use a switch here because GCC *may* generate a + * jump table which won't work, because we're not running at + * the address we're linked at. + */ + if ('G' == **retptr || 'g' == **retptr) + shift = 30; + + if ('M' == **retptr || 'm' == **retptr) + shift = 20; + + if ('K' == **retptr || 'k' == **retptr) + shift = 10; + + if (shift) { + ret <<= shift; + (*retptr)++; + } + + return ret; +} + +/* + * Early parsing of the command line passed to the kernel, used for + * "mem=x" and the options that affect the iommu + */ +static void __init early_cmdline_parse(void) +{ + struct prom_t *_prom = &RELOC(prom); + char *opt, *p; + int l = 0; + + RELOC(prom_cmd_line[0]) = 0; + p = RELOC(prom_cmd_line); + if ((long)_prom->chosen > 0) + l = prom_getprop(_prom->chosen, "bootargs", p, COMMAND_LINE_SIZE-1); +#ifdef CONFIG_CMDLINE + if (l == 0) /* dbl check */ + strlcpy(RELOC(prom_cmd_line), + RELOC(CONFIG_CMDLINE), sizeof(prom_cmd_line)); +#endif /* CONFIG_CMDLINE */ + prom_printf("command line: %s\n", RELOC(prom_cmd_line)); + +#ifdef CONFIG_PPC64 + opt = strstr(RELOC(prom_cmd_line), RELOC("iommu=")); + if (opt) { + prom_printf("iommu opt is: %s\n", opt); + opt += 6; + while (*opt && *opt == ' ') + opt++; + if (!strncmp(opt, RELOC("off"), 3)) + RELOC(ppc64_iommu_off) = 1; + else if (!strncmp(opt, RELOC("force"), 5)) + RELOC(iommu_force_on) = 1; + } +#endif + + opt = strstr(RELOC(prom_cmd_line), RELOC("mem=")); + if (opt) { + opt += 4; + RELOC(prom_memory_limit) = prom_memparse(opt, (const char **)&opt); +#ifdef CONFIG_PPC64 + /* Align to 16 MB == size of ppc64 large page */ + RELOC(prom_memory_limit) = ALIGN(RELOC(prom_memory_limit), 0x1000000); +#endif + } +} + +#ifdef CONFIG_PPC_PSERIES +/* + * To tell the firmware what our capabilities are, we have to pass + * it a fake 32-bit ELF header containing a couple of PT_NOTE sections + * that contain structures that contain the actual values. + */ +static struct fake_elf { + Elf32_Ehdr elfhdr; + Elf32_Phdr phdr[2]; + struct chrpnote { + u32 namesz; + u32 descsz; + u32 type; + char name[8]; /* "PowerPC" */ + struct chrpdesc { + u32 real_mode; + u32 real_base; + u32 real_size; + u32 virt_base; + u32 virt_size; + u32 load_base; + } chrpdesc; + } chrpnote; + struct rpanote { + u32 namesz; + u32 descsz; + u32 type; + char name[24]; /* "IBM,RPA-Client-Config" */ + struct rpadesc { + u32 lpar_affinity; + u32 min_rmo_size; + u32 min_rmo_percent; + u32 max_pft_size; + u32 splpar; + u32 min_load; + u32 new_mem_def; + u32 ignore_me; + } rpadesc; + } rpanote; +} fake_elf = { + .elfhdr = { + .e_ident = { 0x7f, 'E', 'L', 'F', + ELFCLASS32, ELFDATA2MSB, EV_CURRENT }, + .e_type = ET_EXEC, /* yeah right */ + .e_machine = EM_PPC, + .e_version = EV_CURRENT, + .e_phoff = offsetof(struct fake_elf, phdr), + .e_phentsize = sizeof(Elf32_Phdr), + .e_phnum = 2 + }, + .phdr = { + [0] = { + .p_type = PT_NOTE, + .p_offset = offsetof(struct fake_elf, chrpnote), + .p_filesz = sizeof(struct chrpnote) + }, [1] = { + .p_type = PT_NOTE, + .p_offset = offsetof(struct fake_elf, rpanote), + .p_filesz = sizeof(struct rpanote) + } + }, + .chrpnote = { + .namesz = sizeof("PowerPC"), + .descsz = sizeof(struct chrpdesc), + .type = 0x1275, + .name = "PowerPC", + .chrpdesc = { + .real_mode = ~0U, /* ~0 means "don't care" */ + .real_base = ~0U, + .real_size = ~0U, + .virt_base = ~0U, + .virt_size = ~0U, + .load_base = ~0U + }, + }, + .rpanote = { + .namesz = sizeof("IBM,RPA-Client-Config"), + .descsz = sizeof(struct rpadesc), + .type = 0x12759999, + .name = "IBM,RPA-Client-Config", + .rpadesc = { + .lpar_affinity = 0, + .min_rmo_size = 64, /* in megabytes */ + .min_rmo_percent = 0, + .max_pft_size = 48, /* 2^48 bytes max PFT size */ + .splpar = 1, + .min_load = ~0U, + .new_mem_def = 0 + } + } +}; + +static void __init prom_send_capabilities(void) +{ + ihandle elfloader; + + elfloader = call_prom("open", 1, 1, ADDR("/packages/elf-loader")); + if (elfloader == 0) { + prom_printf("couldn't open /packages/elf-loader\n"); + return; + } + call_prom("call-method", 3, 1, ADDR("process-elf-header"), + elfloader, ADDR(&fake_elf)); + call_prom("close", 1, 0, elfloader); +} +#endif + +/* + * Memory allocation strategy... our layout is normally: + * + * at 14Mb or more we have vmlinux, then a gap and initrd. In some + * rare cases, initrd might end up being before the kernel though. + * We assume this won't override the final kernel at 0, we have no + * provision to handle that in this version, but it should hopefully + * never happen. + * + * alloc_top is set to the top of RMO, eventually shrink down if the + * TCEs overlap + * + * alloc_bottom is set to the top of kernel/initrd + * + * from there, allocations are done this way : rtas is allocated + * topmost, and the device-tree is allocated from the bottom. We try + * to grow the device-tree allocation as we progress. If we can't, + * then we fail, we don't currently have a facility to restart + * elsewhere, but that shouldn't be necessary. + * + * Note that calls to reserve_mem have to be done explicitly, memory + * allocated with either alloc_up or alloc_down isn't automatically + * reserved. + */ + + +/* + * Allocates memory in the RMO upward from the kernel/initrd + * + * When align is 0, this is a special case, it means to allocate in place + * at the current location of alloc_bottom or fail (that is basically + * extending the previous allocation). Used for the device-tree flattening + */ +static unsigned long __init alloc_up(unsigned long size, unsigned long align) +{ + unsigned long base = RELOC(alloc_bottom); + unsigned long addr = 0; + + if (align) + base = _ALIGN_UP(base, align); + prom_debug("alloc_up(%x, %x)\n", size, align); + if (RELOC(ram_top) == 0) + prom_panic("alloc_up() called with mem not initialized\n"); + + if (align) + base = _ALIGN_UP(RELOC(alloc_bottom), align); + else + base = RELOC(alloc_bottom); + + for(; (base + size) <= RELOC(alloc_top); + base = _ALIGN_UP(base + 0x100000, align)) { + prom_debug(" trying: 0x%x\n\r", base); + addr = (unsigned long)prom_claim(base, size, 0); + if (addr != PROM_ERROR && addr != 0) + break; + addr = 0; + if (align == 0) + break; + } + if (addr == 0) + return 0; + RELOC(alloc_bottom) = addr; + + prom_debug(" -> %x\n", addr); + prom_debug(" alloc_bottom : %x\n", RELOC(alloc_bottom)); + prom_debug(" alloc_top : %x\n", RELOC(alloc_top)); + prom_debug(" alloc_top_hi : %x\n", RELOC(alloc_top_high)); + prom_debug(" rmo_top : %x\n", RELOC(rmo_top)); + prom_debug(" ram_top : %x\n", RELOC(ram_top)); + + return addr; +} + +/* + * Allocates memory downward, either from top of RMO, or if highmem + * is set, from the top of RAM. Note that this one doesn't handle + * failures. It does claim memory if highmem is not set. + */ +static unsigned long __init alloc_down(unsigned long size, unsigned long align, + int highmem) +{ + unsigned long base, addr = 0; + + prom_debug("alloc_down(%x, %x, %s)\n", size, align, + highmem ? RELOC("(high)") : RELOC("(low)")); + if (RELOC(ram_top) == 0) + prom_panic("alloc_down() called with mem not initialized\n"); + + if (highmem) { + /* Carve out storage for the TCE table. */ + addr = _ALIGN_DOWN(RELOC(alloc_top_high) - size, align); + if (addr <= RELOC(alloc_bottom)) + return 0; + /* Will we bump into the RMO ? If yes, check out that we + * didn't overlap existing allocations there, if we did, + * we are dead, we must be the first in town ! + */ + if (addr < RELOC(rmo_top)) { + /* Good, we are first */ + if (RELOC(alloc_top) == RELOC(rmo_top)) + RELOC(alloc_top) = RELOC(rmo_top) = addr; + else + return 0; + } + RELOC(alloc_top_high) = addr; + goto bail; + } + + base = _ALIGN_DOWN(RELOC(alloc_top) - size, align); + for (; base > RELOC(alloc_bottom); + base = _ALIGN_DOWN(base - 0x100000, align)) { + prom_debug(" trying: 0x%x\n\r", base); + addr = (unsigned long)prom_claim(base, size, 0); + if (addr != PROM_ERROR && addr != 0) + break; + addr = 0; + } + if (addr == 0) + return 0; + RELOC(alloc_top) = addr; + + bail: + prom_debug(" -> %x\n", addr); + prom_debug(" alloc_bottom : %x\n", RELOC(alloc_bottom)); + prom_debug(" alloc_top : %x\n", RELOC(alloc_top)); + prom_debug(" alloc_top_hi : %x\n", RELOC(alloc_top_high)); + prom_debug(" rmo_top : %x\n", RELOC(rmo_top)); + prom_debug(" ram_top : %x\n", RELOC(ram_top)); + + return addr; +} + +/* + * Parse a "reg" cell + */ +static unsigned long __init prom_next_cell(int s, cell_t **cellp) +{ + cell_t *p = *cellp; + unsigned long r = 0; + + /* Ignore more than 2 cells */ + while (s > sizeof(unsigned long) / 4) { + p++; + s--; + } + r = *p++; +#ifdef CONFIG_PPC64 + if (s > 1) { + r <<= 32; + r |= *(p++); + } +#endif + *cellp = p; + return r; +} + +/* + * Very dumb function for adding to the memory reserve list, but + * we don't need anything smarter at this point + * + * XXX Eventually check for collisions. They should NEVER happen. + * If problems seem to show up, it would be a good start to track + * them down. + */ +static void reserve_mem(unsigned long base, unsigned long size) +{ + unsigned long top = base + size; + unsigned long cnt = RELOC(mem_reserve_cnt); + + if (size == 0) + return; + + /* We need to always keep one empty entry so that we + * have our terminator with "size" set to 0 since we are + * dumb and just copy this entire array to the boot params + */ + base = _ALIGN_DOWN(base, PAGE_SIZE); + top = _ALIGN_UP(top, PAGE_SIZE); + size = top - base; + + if (cnt >= (MEM_RESERVE_MAP_SIZE - 1)) + prom_panic("Memory reserve map exhausted !\n"); + RELOC(mem_reserve_map)[cnt].base = base; + RELOC(mem_reserve_map)[cnt].size = size; + RELOC(mem_reserve_cnt) = cnt + 1; +} + +/* + * Initialize memory allocation mecanism, parse "memory" nodes and + * obtain that way the top of memory and RMO to setup out local allocator + */ +static void __init prom_init_mem(void) +{ + phandle node; + char *path, type[64]; + unsigned int plen; + cell_t *p, *endp; + struct prom_t *_prom = &RELOC(prom); + u32 rac, rsc; + + /* + * We iterate the memory nodes to find + * 1) top of RMO (first node) + * 2) top of memory + */ + rac = 2; + prom_getprop(_prom->root, "#address-cells", &rac, sizeof(rac)); + rsc = 1; + prom_getprop(_prom->root, "#size-cells", &rsc, sizeof(rsc)); + prom_debug("root_addr_cells: %x\n", (unsigned long) rac); + prom_debug("root_size_cells: %x\n", (unsigned long) rsc); + + prom_debug("scanning memory:\n"); + path = RELOC(prom_scratch); + + for (node = 0; prom_next_node(&node); ) { + type[0] = 0; + prom_getprop(node, "device_type", type, sizeof(type)); + + if (type[0] == 0) { + /* + * CHRP Longtrail machines have no device_type + * on the memory node, so check the name instead... + */ + prom_getprop(node, "name", type, sizeof(type)); + } + if (strcmp(type, RELOC("memory"))) + continue; + + plen = prom_getprop(node, "reg", RELOC(regbuf), sizeof(regbuf)); + if (plen > sizeof(regbuf)) { + prom_printf("memory node too large for buffer !\n"); + plen = sizeof(regbuf); + } + p = RELOC(regbuf); + endp = p + (plen / sizeof(cell_t)); + +#ifdef DEBUG_PROM + memset(path, 0, PROM_SCRATCH_SIZE); + call_prom("package-to-path", 3, 1, node, path, PROM_SCRATCH_SIZE-1); + prom_debug(" node %s :\n", path); +#endif /* DEBUG_PROM */ + + while ((endp - p) >= (rac + rsc)) { + unsigned long base, size; + + base = prom_next_cell(rac, &p); + size = prom_next_cell(rsc, &p); + + if (size == 0) + continue; + prom_debug(" %x %x\n", base, size); + if (base == 0) + RELOC(rmo_top) = size; + if ((base + size) > RELOC(ram_top)) + RELOC(ram_top) = base + size; + } + } + + RELOC(alloc_bottom) = PAGE_ALIGN((unsigned long)&RELOC(_end) + 0x4000); + + /* Check if we have an initrd after the kernel, if we do move our bottom + * point to after it + */ + if (RELOC(prom_initrd_start)) { + if (RELOC(prom_initrd_end) > RELOC(alloc_bottom)) + RELOC(alloc_bottom) = PAGE_ALIGN(RELOC(prom_initrd_end)); + } + + /* + * If prom_memory_limit is set we reduce the upper limits *except* for + * alloc_top_high. This must be the real top of RAM so we can put + * TCE's up there. + */ + + RELOC(alloc_top_high) = RELOC(ram_top); + + if (RELOC(prom_memory_limit)) { + if (RELOC(prom_memory_limit) <= RELOC(alloc_bottom)) { + prom_printf("Ignoring mem=%x <= alloc_bottom.\n", + RELOC(prom_memory_limit)); + RELOC(prom_memory_limit) = 0; + } else if (RELOC(prom_memory_limit) >= RELOC(ram_top)) { + prom_printf("Ignoring mem=%x >= ram_top.\n", + RELOC(prom_memory_limit)); + RELOC(prom_memory_limit) = 0; + } else { + RELOC(ram_top) = RELOC(prom_memory_limit); + RELOC(rmo_top) = min(RELOC(rmo_top), RELOC(prom_memory_limit)); + } + } + + /* + * Setup our top alloc point, that is top of RMO or top of + * segment 0 when running non-LPAR. + * Some RS64 machines have buggy firmware where claims up at + * 1GB fail. Cap at 768MB as a workaround. + * Since 768MB is plenty of room, and we need to cap to something + * reasonable on 32-bit, cap at 768MB on all machines. + */ + if (!RELOC(rmo_top)) + RELOC(rmo_top) = RELOC(ram_top); + RELOC(rmo_top) = min(0x30000000ul, RELOC(rmo_top)); + RELOC(alloc_top) = RELOC(rmo_top); + + prom_printf("memory layout at init:\n"); + prom_printf(" memory_limit : %x (16 MB aligned)\n", RELOC(prom_memory_limit)); + prom_printf(" alloc_bottom : %x\n", RELOC(alloc_bottom)); + prom_printf(" alloc_top : %x\n", RELOC(alloc_top)); + prom_printf(" alloc_top_hi : %x\n", RELOC(alloc_top_high)); + prom_printf(" rmo_top : %x\n", RELOC(rmo_top)); + prom_printf(" ram_top : %x\n", RELOC(ram_top)); +} + + +/* + * Allocate room for and instantiate RTAS + */ +static void __init prom_instantiate_rtas(void) +{ + phandle rtas_node; + ihandle rtas_inst; + u32 base, entry = 0; + u32 size = 0; + + prom_debug("prom_instantiate_rtas: start...\n"); + + rtas_node = call_prom("finddevice", 1, 1, ADDR("/rtas")); + prom_debug("rtas_node: %x\n", rtas_node); + if (!PHANDLE_VALID(rtas_node)) + return; + + prom_getprop(rtas_node, "rtas-size", &size, sizeof(size)); + if (size == 0) + return; + + base = alloc_down(size, PAGE_SIZE, 0); + if (base == 0) { + prom_printf("RTAS allocation failed !\n"); + return; + } + + rtas_inst = call_prom("open", 1, 1, ADDR("/rtas")); + if (!IHANDLE_VALID(rtas_inst)) { + prom_printf("opening rtas package failed"); + return; + } + + prom_printf("instantiating rtas at 0x%x ...", base); + + if (call_prom_ret("call-method", 3, 2, &entry, + ADDR("instantiate-rtas"), + rtas_inst, base) == PROM_ERROR + || entry == 0) { + prom_printf(" failed\n"); + return; + } + prom_printf(" done\n"); + + 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_debug("rtas base = 0x%x\n", base); + prom_debug("rtas entry = 0x%x\n", entry); + prom_debug("rtas size = 0x%x\n", (long)size); + + prom_debug("prom_instantiate_rtas: end...\n"); +} + +#ifdef CONFIG_PPC64 +/* + * Allocate room for and initialize TCE tables + */ +static void __init prom_initialize_tce_table(void) +{ + phandle node; + ihandle phb_node; + char compatible[64], type[64], model[64]; + char *path = RELOC(prom_scratch); + u64 base, align; + u32 minalign, minsize; + u64 tce_entry, *tce_entryp; + u64 local_alloc_top, local_alloc_bottom; + u64 i; + + if (RELOC(ppc64_iommu_off)) + return; + + prom_debug("starting prom_initialize_tce_table\n"); + + /* Cache current top of allocs so we reserve a single block */ + local_alloc_top = RELOC(alloc_top_high); + local_alloc_bottom = local_alloc_top; + + /* Search all nodes looking for PHBs. */ + for (node = 0; prom_next_node(&node); ) { + compatible[0] = 0; + type[0] = 0; + model[0] = 0; + prom_getprop(node, "compatible", + compatible, sizeof(compatible)); + prom_getprop(node, "device_type", type, sizeof(type)); + prom_getprop(node, "model", model, sizeof(model)); + + if ((type[0] == 0) || (strstr(type, RELOC("pci")) == NULL)) + continue; + + /* Keep the old logic in tack to avoid regression. */ + if (compatible[0] != 0) { + if ((strstr(compatible, RELOC("python")) == NULL) && + (strstr(compatible, RELOC("Speedwagon")) == NULL) && + (strstr(compatible, RELOC("Winnipeg")) == NULL)) + continue; + } else if (model[0] != 0) { + if ((strstr(model, RELOC("ython")) == NULL) && + (strstr(model, RELOC("peedwagon")) == NULL) && + (strstr(model, RELOC("innipeg")) == NULL)) + continue; + } + + if (prom_getprop(node, "tce-table-minalign", &minalign, + sizeof(minalign)) == PROM_ERROR) + minalign = 0; + if (prom_getprop(node, "tce-table-minsize", &minsize, + sizeof(minsize)) == PROM_ERROR) + minsize = 4UL << 20; + + /* + * Even though we read what OF wants, we just set the table + * size to 4 MB. This is enough to map 2GB of PCI DMA space. + * By doing this, we avoid the pitfalls of trying to DMA to + * MMIO space and the DMA alias hole. + * + * On POWER4, firmware sets the TCE region by assuming + * each TCE table is 8MB. Using this memory for anything + * else will impact performance, so we always allocate 8MB. + * Anton + */ + if (__is_processor(PV_POWER4) || __is_processor(PV_POWER4p)) + minsize = 8UL << 20; + else + minsize = 4UL << 20; + + /* Align to the greater of the align or size */ + align = max(minalign, minsize); + base = alloc_down(minsize, align, 1); + if (base == 0) + prom_panic("ERROR, cannot find space for TCE table.\n"); + 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 */ + if (call_prom("package-to-path", 3, 1, node, + path, PROM_SCRATCH_SIZE-1) == PROM_ERROR) { + prom_printf("package-to-path failed\n"); + } + + prom_debug("TCE table: %s\n", path); + prom_debug("\tnode = 0x%x\n", node); + prom_debug("\tbase = 0x%x\n", base); + prom_debug("\tsize = 0x%x\n", minsize); + + /* Initialize the table to have a one-to-one mapping + * over the allocated size. + */ + tce_entryp = (unsigned long *)base; + for (i = 0; i < (minsize >> 3) ;tce_entryp++, i++) { + tce_entry = (i << PAGE_SHIFT); + tce_entry |= 0x3; + *tce_entryp = tce_entry; + } + + prom_printf("opening PHB %s", path); + phb_node = call_prom("open", 1, 1, path); + if (phb_node == 0) + prom_printf("... failed\n"); + else + prom_printf("... done\n"); + + call_prom("call-method", 6, 0, ADDR("set-64-bit-addressing"), + phb_node, -1, minsize, + (u32) base, (u32) (base >> 32)); + call_prom("close", 1, 0, phb_node); + } + + reserve_mem(local_alloc_bottom, local_alloc_top - local_alloc_bottom); + + if (RELOC(prom_memory_limit)) { + /* + * We align the start to a 16MB boundary so we can map + * the TCE area using large pages if possible. + * The end should be the top of RAM so no need to align it. + */ + RELOC(prom_tce_alloc_start) = _ALIGN_DOWN(local_alloc_bottom, + 0x1000000); + RELOC(prom_tce_alloc_end) = local_alloc_top; + } + + /* Flag the first invalid entry */ + prom_debug("ending prom_initialize_tce_table\n"); +} +#endif + +/* + * With CHRP SMP we need to use the OF to start the other processors. + * We can't wait until smp_boot_cpus (the OF is trashed by then) + * so we have to put the processors into a holding pattern controlled + * by the kernel (not OF) before we destroy the OF. + * + * This uses a chunk of low memory, puts some holding pattern + * code there and sends the other processors off to there until + * smp_boot_cpus tells them to do something. The holding pattern + * checks that address until its cpu # is there, when it is that + * cpu jumps to __secondary_start(). smp_boot_cpus() takes care + * of setting those values. + * + * We also use physical address 0x4 here to tell when a cpu + * is in its holding pattern code. + * + * -- Cort + */ +extern void __secondary_hold(void); +extern unsigned long __secondary_hold_spinloop; +extern unsigned long __secondary_hold_acknowledge; + +/* + * We want to reference the copy of __secondary_hold_* in the + * 0 - 0x100 address range + */ +#define LOW_ADDR(x) (((unsigned long) &(x)) & 0xff) + +static void __init prom_hold_cpus(void) +{ + unsigned long i; + unsigned int reg; + phandle node; + char type[64]; + int cpuid = 0; + unsigned int interrupt_server[MAX_CPU_THREADS]; + unsigned int cpu_threads, hw_cpu_num; + int propsize; + struct prom_t *_prom = &RELOC(prom); + unsigned long *spinloop + = (void *) LOW_ADDR(__secondary_hold_spinloop); + unsigned long *acknowledge + = (void *) LOW_ADDR(__secondary_hold_acknowledge); +#ifdef CONFIG_PPC64 + /* __secondary_hold is actually a descriptor, not the text address */ + unsigned long secondary_hold + = __pa(*PTRRELOC((unsigned long *)__secondary_hold)); +#else + unsigned long secondary_hold = LOW_ADDR(__secondary_hold); +#endif + + prom_debug("prom_hold_cpus: start...\n"); + prom_debug(" 1) spinloop = 0x%x\n", (unsigned long)spinloop); + prom_debug(" 1) *spinloop = 0x%x\n", *spinloop); + prom_debug(" 1) acknowledge = 0x%x\n", + (unsigned long)acknowledge); + prom_debug(" 1) *acknowledge = 0x%x\n", *acknowledge); + prom_debug(" 1) secondary_hold = 0x%x\n", secondary_hold); + + /* Set the common spinloop variable, so all of the secondary cpus + * will block when they are awakened from their OF spinloop. + * This must occur for both SMP and non SMP kernels, since OF will + * be trashed when we move the kernel. + */ + *spinloop = 0; + +#ifdef CONFIG_HMT + for (i = 0; i < NR_CPUS; i++) + RELOC(hmt_thread_data)[i].pir = 0xdeadbeef; +#endif + /* look for cpus */ + for (node = 0; prom_next_node(&node); ) { + type[0] = 0; + prom_getprop(node, "device_type", type, sizeof(type)); + if (strcmp(type, RELOC("cpu")) != 0) + continue; + + /* Skip non-configured cpus. */ + if (prom_getprop(node, "status", type, sizeof(type)) > 0) + if (strcmp(type, RELOC("okay")) != 0) + continue; + + reg = -1; + prom_getprop(node, "reg", ®, sizeof(reg)); + + prom_debug("\ncpuid = 0x%x\n", cpuid); + prom_debug("cpu hw idx = 0x%x\n", reg); + + /* Init the acknowledge var which will be reset by + * the secondary cpu when it awakens from its OF + * spinloop. + */ + *acknowledge = (unsigned long)-1; + + propsize = prom_getprop(node, "ibm,ppc-interrupt-server#s", + &interrupt_server, + sizeof(interrupt_server)); + if (propsize < 0) { + /* no property. old hardware has no SMT */ + cpu_threads = 1; + interrupt_server[0] = reg; /* fake it with phys id */ + } else { + /* We have a threaded processor */ + cpu_threads = propsize / sizeof(u32); + if (cpu_threads > MAX_CPU_THREADS) { + prom_printf("SMT: too many threads!\n" + "SMT: found %x, max is %x\n", + cpu_threads, MAX_CPU_THREADS); + cpu_threads = 1; /* ToDo: panic? */ + } + } + + hw_cpu_num = interrupt_server[0]; + if (hw_cpu_num != _prom->cpu) { + /* Primary Thread of non-boot cpu */ + prom_printf("%x : starting cpu hw idx %x... ", cpuid, reg); + call_prom("start-cpu", 3, 0, node, + secondary_hold, reg); + + for (i = 0; (i < 100000000) && + (*acknowledge == ((unsigned long)-1)); i++ ) + mb(); + + if (*acknowledge == reg) + prom_printf("done\n"); + else + prom_printf("failed: %x\n", *acknowledge); + } +#ifdef CONFIG_SMP + else + prom_printf("%x : boot cpu %x\n", cpuid, reg); +#endif /* CONFIG_SMP */ + + /* Reserve cpu #s for secondary threads. They start later. */ + cpuid += cpu_threads; + } +#ifdef CONFIG_HMT + /* Only enable HMT on processors that provide support. */ + if (__is_processor(PV_PULSAR) || + __is_processor(PV_ICESTAR) || + __is_processor(PV_SSTAR)) { + prom_printf(" starting secondary threads\n"); + + for (i = 0; i < NR_CPUS; i += 2) { + if (!cpu_online(i)) + continue; + + if (i == 0) { + unsigned long pir = mfspr(SPRN_PIR); + if (__is_processor(PV_PULSAR)) { + RELOC(hmt_thread_data)[i].pir = + pir & 0x1f; + } else { + RELOC(hmt_thread_data)[i].pir = + pir & 0x3ff; + } + } + } + } else { + prom_printf("Processor is not HMT capable\n"); + } +#endif + + if (cpuid > NR_CPUS) + prom_printf("WARNING: maximum CPUs (" __stringify(NR_CPUS) + ") exceeded: ignoring extras\n"); + + prom_debug("prom_hold_cpus: end...\n"); +} + + +static void __init prom_init_client_services(unsigned long pp) +{ + struct prom_t *_prom = &RELOC(prom); + + /* Get a handle to the prom entry point before anything else */ + RELOC(prom_entry) = pp; + + /* get a handle for the stdout device */ + _prom->chosen = call_prom("finddevice", 1, 1, ADDR("/chosen")); + if (!PHANDLE_VALID(_prom->chosen)) + prom_panic("cannot find chosen"); /* msg won't be printed :( */ + + /* get device tree root */ + _prom->root = call_prom("finddevice", 1, 1, ADDR("/")); + if (!PHANDLE_VALID(_prom->root)) + prom_panic("cannot find device tree root"); /* msg won't be printed :( */ + + _prom->mmumap = 0; +} + +#ifdef CONFIG_PPC32 +/* + * For really old powermacs, we need to map things we claim. + * For that, we need the ihandle of the mmu. + */ +static void __init prom_find_mmu(void) +{ + struct prom_t *_prom = &RELOC(prom); + phandle oprom; + char version[64]; + + oprom = call_prom("finddevice", 1, 1, ADDR("/openprom")); + if (!PHANDLE_VALID(oprom)) + return; + 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) + return; + prom_getprop(_prom->chosen, "mmu", &_prom->mmumap, + sizeof(_prom->mmumap)); +} +#else +#define prom_find_mmu() +#endif + +static void __init prom_init_stdout(void) +{ + struct prom_t *_prom = &RELOC(prom); + char *path = RELOC(of_stdout_device); + char type[16]; + u32 val; + + if (prom_getprop(_prom->chosen, "stdout", &val, sizeof(val)) <= 0) + prom_panic("cannot find stdout"); + + _prom->stdout = val; + + /* Get the full OF pathname of the stdout device */ + 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_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); + + /* 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); +} + +static void __init prom_close_stdin(void) +{ + struct prom_t *_prom = &RELOC(prom); + ihandle val; + + if (prom_getprop(_prom->chosen, "stdin", &val, sizeof(val)) > 0) + call_prom("close", 1, 0, val); +} + +static int __init prom_find_machine_type(void) +{ + struct prom_t *_prom = &RELOC(prom); + char compat[256]; + int len, i = 0; + phandle rtas; + + len = prom_getprop(_prom->root, "compatible", + compat, sizeof(compat)-1); + if (len > 0) { + compat[len] = 0; + while (i < len) { + char *p = &compat[i]; + int sl = strlen(p); + if (sl == 0) + break; + if (strstr(p, RELOC("Power Macintosh")) || + strstr(p, RELOC("MacRISC"))) + return PLATFORM_POWERMAC; +#ifdef CONFIG_PPC64 + if (strstr(p, RELOC("Momentum,Maple"))) + return PLATFORM_MAPLE; +#endif + i += sl + 1; + } + } +#ifdef CONFIG_PPC64 + /* Default to pSeries. We need to know if we are running LPAR */ + rtas = call_prom("finddevice", 1, 1, ADDR("/rtas")); + if (PHANDLE_VALID(rtas)) { + int x = prom_getproplen(rtas, "ibm,hypertas-functions"); + if (x != PROM_ERROR) { + prom_printf("Hypertas detected, assuming LPAR !\n"); + return PLATFORM_PSERIES_LPAR; + } + } + return PLATFORM_PSERIES; +#else + return PLATFORM_CHRP; +#endif +} + +static int __init prom_set_color(ihandle ih, int i, int r, int g, int b) +{ + return call_prom("call-method", 6, 1, ADDR("color!"), ih, i, b, g, r); +} + +/* + * If we have a display that we don't know how to drive, + * we will want to try to execute OF's open method for it + * later. However, OF will probably fall over if we do that + * we've taken over the MMU. + * So we check whether we will need to open the display, + * and if so, open it now. + */ +static void __init prom_check_displays(void) +{ + char type[16], *path; + phandle node; + ihandle ih; + int i; + + static unsigned char default_colors[] = { + 0x00, 0x00, 0x00, + 0x00, 0x00, 0xaa, + 0x00, 0xaa, 0x00, + 0x00, 0xaa, 0xaa, + 0xaa, 0x00, 0x00, + 0xaa, 0x00, 0xaa, + 0xaa, 0xaa, 0x00, + 0xaa, 0xaa, 0xaa, + 0x55, 0x55, 0x55, + 0x55, 0x55, 0xff, + 0x55, 0xff, 0x55, + 0x55, 0xff, 0xff, + 0xff, 0x55, 0x55, + 0xff, 0x55, 0xff, + 0xff, 0xff, 0x55, + 0xff, 0xff, 0xff + }; + const unsigned char *clut; + + prom_printf("Looking for displays\n"); + for (node = 0; prom_next_node(&node); ) { + memset(type, 0, sizeof(type)); + prom_getprop(node, "device_type", type, sizeof(type)); + if (strcmp(type, RELOC("display")) != 0) + continue; + + /* It seems OF doesn't null-terminate the path :-( */ + path = RELOC(prom_scratch); + memset(path, 0, PROM_SCRATCH_SIZE); + + /* + * leave some room at the end of the path for appending extra + * arguments + */ + if (call_prom("package-to-path", 3, 1, node, path, + PROM_SCRATCH_SIZE-10) == PROM_ERROR) + continue; + prom_printf("found display : %s, opening ... ", path); + + ih = call_prom("open", 1, 1, path); + if (ih == 0) { + prom_printf("failed\n"); + continue; + } + + /* Success */ + prom_printf("done\n"); + prom_setprop(node, "linux,opened", NULL, 0); + + /* Setup a usable color table when the appropriate + * method is available. Should update this to set-colors */ + clut = RELOC(default_colors); + for (i = 0; i < 32; i++, clut += 3) + if (prom_set_color(ih, i, clut[0], clut[1], + clut[2]) != 0) + break; + +#ifdef CONFIG_LOGO_LINUX_CLUT224 + clut = PTRRELOC(RELOC(logo_linux_clut224.clut)); + for (i = 0; i < RELOC(logo_linux_clut224.clutsize); i++, clut += 3) + if (prom_set_color(ih, i + 32, clut[0], clut[1], + clut[2]) != 0) + break; +#endif /* CONFIG_LOGO_LINUX_CLUT224 */ + } +} + + +/* Return (relocated) pointer to this much memory: moves initrd if reqd. */ +static void __init *make_room(unsigned long *mem_start, unsigned long *mem_end, + unsigned long needed, unsigned long align) +{ + void *ret; + + *mem_start = _ALIGN(*mem_start, align); + while ((*mem_start + needed) > *mem_end) { + unsigned long room, chunk; + + prom_debug("Chunk exhausted, claiming more at %x...\n", + RELOC(alloc_bottom)); + room = RELOC(alloc_top) - RELOC(alloc_bottom); + if (room > DEVTREE_CHUNK_SIZE) + room = DEVTREE_CHUNK_SIZE; + if (room < PAGE_SIZE) + prom_panic("No memory for flatten_device_tree (no room)"); + chunk = alloc_up(room, 0); + if (chunk == 0) + prom_panic("No memory for flatten_device_tree (claim failed)"); + *mem_end = RELOC(alloc_top); + } + + ret = (void *)*mem_start; + *mem_start += needed; + + return ret; +} + +#define dt_push_token(token, mem_start, mem_end) \ + do { *((u32 *)make_room(mem_start, mem_end, 4, 4)) = token; } while(0) + +static unsigned long __init dt_find_string(char *str) +{ + char *s, *os; + + s = os = (char *)RELOC(dt_string_start); + s += 4; + while (s < (char *)RELOC(dt_string_end)) { + if (strcmp(s, str) == 0) + return s - os; + s += strlen(s) + 1; + } + return 0; +} + +/* + * The Open Firmware 1275 specification states properties must be 31 bytes or + * less, however not all firmwares obey this. Make it 64 bytes to be safe. + */ +#define MAX_PROPERTY_NAME 64 + +static void __init scan_dt_build_strings(phandle node, + unsigned long *mem_start, + unsigned long *mem_end) +{ + char *prev_name, *namep, *sstart; + unsigned long soff; + phandle child; + + sstart = (char *)RELOC(dt_string_start); + + /* get and store all property names */ + prev_name = RELOC(""); + for (;;) { + /* 64 is max len of name including nul. */ + namep = make_room(mem_start, mem_end, MAX_PROPERTY_NAME, 1); + if (call_prom("nextprop", 3, 1, node, prev_name, namep) != 1) { + /* No more nodes: unwind alloc */ + *mem_start = (unsigned long)namep; + break; + } + + /* skip "name" */ + if (strcmp(namep, RELOC("name")) == 0) { + *mem_start = (unsigned long)namep; + prev_name = RELOC("name"); + continue; + } + /* get/create string entry */ + soff = dt_find_string(namep); + if (soff != 0) { + *mem_start = (unsigned long)namep; + namep = sstart + soff; + } else { + /* Trim off some if we can */ + *mem_start = (unsigned long)namep + strlen(namep) + 1; + RELOC(dt_string_end) = *mem_start; + } + prev_name = namep; + } + + /* do all our children */ + child = call_prom("child", 1, 1, node); + while (child != 0) { + scan_dt_build_strings(child, mem_start, mem_end); + child = call_prom("peer", 1, 1, child); + } +} + +static void __init scan_dt_build_struct(phandle node, unsigned long *mem_start, + unsigned long *mem_end) +{ + phandle child; + char *namep, *prev_name, *sstart, *p, *ep, *lp, *path; + unsigned long soff; + unsigned char *valp; + static char pname[MAX_PROPERTY_NAME]; + int l, room; + + dt_push_token(OF_DT_BEGIN_NODE, mem_start, mem_end); + + /* get the node's full name */ + namep = (char *)*mem_start; + room = *mem_end - *mem_start; + if (room > 255) + room = 255; + l = call_prom("package-to-path", 3, 1, node, namep, room); + if (l >= 0) { + /* Didn't fit? Get more room. */ + if (l >= room) { + if (l >= *mem_end - *mem_start) + namep = make_room(mem_start, mem_end, l+1, 1); + call_prom("package-to-path", 3, 1, node, namep, l); + } + namep[l] = '\0'; + + /* Fixup an Apple bug where they have bogus \0 chars in the + * middle of the path in some properties, and extract + * the unit name (everything after the last '/'). + */ + for (lp = p = namep, ep = namep + l; p < ep; p++) { + if (*p == '/') + lp = namep; + else if (*p != 0) + *lp++ = *p; + } + *lp = 0; + *mem_start = _ALIGN((unsigned long)lp + 1, 4); + } + + /* get it again for debugging */ + path = RELOC(prom_scratch); + memset(path, 0, PROM_SCRATCH_SIZE); + call_prom("package-to-path", 3, 1, node, path, PROM_SCRATCH_SIZE-1); + + /* get and store all properties */ + prev_name = RELOC(""); + sstart = (char *)RELOC(dt_string_start); + for (;;) { + if (call_prom("nextprop", 3, 1, node, prev_name, + RELOC(pname)) != 1) + break; + + /* skip "name" */ + if (strcmp(RELOC(pname), RELOC("name")) == 0) { + prev_name = RELOC("name"); + continue; + } + + /* find string offset */ + soff = dt_find_string(RELOC(pname)); + if (soff == 0) { + prom_printf("WARNING: Can't find string index for" + " <%s>, node %s\n", RELOC(pname), path); + break; + } + prev_name = sstart + soff; + + /* get length */ + l = call_prom("getproplen", 2, 1, node, RELOC(pname)); + + /* sanity checks */ + if (l == PROM_ERROR) + continue; + if (l > MAX_PROPERTY_LENGTH) { + prom_printf("WARNING: ignoring large property "); + /* It seems OF doesn't null-terminate the path :-( */ + prom_printf("[%s] ", path); + prom_printf("%s length 0x%x\n", RELOC(pname), l); + continue; + } + + /* push property head */ + dt_push_token(OF_DT_PROP, mem_start, mem_end); + dt_push_token(l, mem_start, mem_end); + dt_push_token(soff, mem_start, mem_end); + + /* push property content */ + valp = make_room(mem_start, mem_end, l, 4); + call_prom("getprop", 4, 1, node, RELOC(pname), valp, l); + *mem_start = _ALIGN(*mem_start, 4); + } + + /* Add a "linux,phandle" property. */ + soff = dt_find_string(RELOC("linux,phandle")); + if (soff == 0) + prom_printf("WARNING: Can't find string index for" + " <linux-phandle> node %s\n", path); + else { + dt_push_token(OF_DT_PROP, mem_start, mem_end); + dt_push_token(4, mem_start, mem_end); + dt_push_token(soff, mem_start, mem_end); + valp = make_room(mem_start, mem_end, 4, 4); + *(u32 *)valp = node; + } + + /* do all our children */ + child = call_prom("child", 1, 1, node); + while (child != 0) { + scan_dt_build_struct(child, mem_start, mem_end); + child = call_prom("peer", 1, 1, child); + } + + dt_push_token(OF_DT_END_NODE, mem_start, mem_end); +} + +static void __init flatten_device_tree(void) +{ + phandle root; + unsigned long mem_start, mem_end, room; + struct boot_param_header *hdr; + struct prom_t *_prom = &RELOC(prom); + char *namep; + u64 *rsvmap; + + /* + * Check how much room we have between alloc top & bottom (+/- a + * few pages), crop to 4Mb, as this is our "chuck" size + */ + room = RELOC(alloc_top) - RELOC(alloc_bottom) - 0x4000; + if (room > DEVTREE_CHUNK_SIZE) + room = DEVTREE_CHUNK_SIZE; + prom_debug("starting device tree allocs at %x\n", RELOC(alloc_bottom)); + + /* Now try to claim that */ + mem_start = (unsigned long)alloc_up(room, PAGE_SIZE); + if (mem_start == 0) + prom_panic("Can't allocate initial device-tree chunk\n"); + mem_end = RELOC(alloc_top); + + /* Get root of tree */ + root = call_prom("peer", 1, 1, (phandle)0); + if (root == (phandle)0) + prom_panic ("couldn't get device tree root\n"); + + /* Build header and make room for mem rsv map */ + mem_start = _ALIGN(mem_start, 4); + hdr = make_room(&mem_start, &mem_end, + sizeof(struct boot_param_header), 4); + RELOC(dt_header_start) = (unsigned long)hdr; + rsvmap = make_room(&mem_start, &mem_end, sizeof(mem_reserve_map), 8); + + /* Start of strings */ + mem_start = PAGE_ALIGN(mem_start); + RELOC(dt_string_start) = mem_start; + mem_start += 4; /* hole */ + + /* Add "linux,phandle" in there, we'll need it */ + namep = make_room(&mem_start, &mem_end, 16, 1); + strcpy(namep, RELOC("linux,phandle")); + mem_start = (unsigned long)namep + strlen(namep) + 1; + + /* Build string array */ + prom_printf("Building dt strings...\n"); + scan_dt_build_strings(root, &mem_start, &mem_end); + RELOC(dt_string_end) = mem_start; + + /* Build structure */ + mem_start = PAGE_ALIGN(mem_start); + RELOC(dt_struct_start) = mem_start; + prom_printf("Building dt structure...\n"); + scan_dt_build_struct(root, &mem_start, &mem_end); + dt_push_token(OF_DT_END, &mem_start, &mem_end); + RELOC(dt_struct_end) = PAGE_ALIGN(mem_start); + + /* Finish header */ + hdr->boot_cpuid_phys = _prom->cpu; + hdr->magic = OF_DT_HEADER; + hdr->totalsize = RELOC(dt_struct_end) - RELOC(dt_header_start); + hdr->off_dt_struct = RELOC(dt_struct_start) - RELOC(dt_header_start); + hdr->off_dt_strings = RELOC(dt_string_start) - RELOC(dt_header_start); + hdr->dt_strings_size = RELOC(dt_string_end) - RELOC(dt_string_start); + hdr->off_mem_rsvmap = ((unsigned long)rsvmap) - RELOC(dt_header_start); + hdr->version = OF_DT_VERSION; + /* Version 16 is not backward compatible */ + hdr->last_comp_version = 0x10; + + /* Reserve the whole thing and copy the reserve map in, we + * also bump mem_reserve_cnt to cause further reservations to + * fail since it's too late. + */ + reserve_mem(RELOC(dt_header_start), hdr->totalsize); + memcpy(rsvmap, RELOC(mem_reserve_map), sizeof(mem_reserve_map)); + +#ifdef DEBUG_PROM + { + int i; + prom_printf("reserved memory map:\n"); + for (i = 0; i < RELOC(mem_reserve_cnt); i++) + prom_printf(" %x - %x\n", + RELOC(mem_reserve_map)[i].base, + RELOC(mem_reserve_map)[i].size); + } +#endif + RELOC(mem_reserve_cnt) = MEM_RESERVE_MAP_SIZE; + + prom_printf("Device tree strings 0x%x -> 0x%x\n", + RELOC(dt_string_start), RELOC(dt_string_end)); + prom_printf("Device tree struct 0x%x -> 0x%x\n", + RELOC(dt_struct_start), RELOC(dt_struct_end)); + +} + + +static void __init fixup_device_tree(void) +{ +#if defined(CONFIG_PPC64) && defined(CONFIG_PPC_PMAC) + phandle u3, i2c, mpic; + u32 u3_rev; + u32 interrupts[2]; + u32 parent; + + /* Some G5s have a missing interrupt definition, fix it up here */ + u3 = call_prom("finddevice", 1, 1, ADDR("/u3@0,f8000000")); + if (!PHANDLE_VALID(u3)) + return; + i2c = call_prom("finddevice", 1, 1, ADDR("/u3@0,f8000000/i2c@f8001000")); + if (!PHANDLE_VALID(i2c)) + return; + mpic = call_prom("finddevice", 1, 1, ADDR("/u3@0,f8000000/mpic@f8040000")); + if (!PHANDLE_VALID(mpic)) + return; + + /* check if proper rev of u3 */ + if (prom_getprop(u3, "device-rev", &u3_rev, sizeof(u3_rev)) + == PROM_ERROR) + return; + if (u3_rev != 0x35 && u3_rev != 0x37) + return; + /* does it need fixup ? */ + if (prom_getproplen(i2c, "interrupts") > 0) + return; + + prom_printf("fixing up bogus interrupts for u3 i2c...\n"); + + /* interrupt on this revision of u3 is number 0 and level */ + interrupts[0] = 0; + interrupts[1] = 1; + prom_setprop(i2c, "interrupts", &interrupts, sizeof(interrupts)); + parent = (u32)mpic; + prom_setprop(i2c, "interrupt-parent", &parent, sizeof(parent)); +#endif +} + + +static void __init prom_find_boot_cpu(void) +{ + struct prom_t *_prom = &RELOC(prom); + u32 getprop_rval; + ihandle prom_cpu; + phandle cpu_pkg; + + _prom->cpu = 0; + if (prom_getprop(_prom->chosen, "cpu", &prom_cpu, sizeof(prom_cpu)) <= 0) + return; + + cpu_pkg = call_prom("instance-to-package", 1, 1, prom_cpu); + + prom_getprop(cpu_pkg, "reg", &getprop_rval, sizeof(getprop_rval)); + _prom->cpu = getprop_rval; + + prom_debug("Booting CPU hw index = 0x%x\n", _prom->cpu); +} + +static void __init prom_check_initrd(unsigned long r3, unsigned long r4) +{ +#ifdef CONFIG_BLK_DEV_INITRD + struct prom_t *_prom = &RELOC(prom); + + if (r3 && r4 && r4 != 0xdeadbeef) { + unsigned long val; + + RELOC(prom_initrd_start) = (r3 >= KERNELBASE) ? __pa(r3) : r3; + RELOC(prom_initrd_end) = RELOC(prom_initrd_start) + r4; + + val = RELOC(prom_initrd_start); + prom_setprop(_prom->chosen, "linux,initrd-start", &val, + sizeof(val)); + val = RELOC(prom_initrd_end); + prom_setprop(_prom->chosen, "linux,initrd-end", &val, + sizeof(val)); + + reserve_mem(RELOC(prom_initrd_start), + RELOC(prom_initrd_end) - RELOC(prom_initrd_start)); + + prom_debug("initrd_start=0x%x\n", RELOC(prom_initrd_start)); + prom_debug("initrd_end=0x%x\n", RELOC(prom_initrd_end)); + } +#endif /* CONFIG_BLK_DEV_INITRD */ +} + +/* + * We enter here early on, when the Open Firmware prom is still + * handling exceptions and the MMU hash table for us. + */ + +unsigned long __init prom_init(unsigned long r3, unsigned long r4, + unsigned long pp, + unsigned long r6, unsigned long r7) +{ + struct prom_t *_prom; + unsigned long hdr; + u32 getprop_rval; + unsigned long offset = reloc_offset(); + +#ifdef CONFIG_PPC32 + reloc_got2(offset); +#endif + + _prom = &RELOC(prom); + + /* + * First zero the BSS + */ + memset(&RELOC(__bss_start), 0, __bss_stop - __bss_start); + + /* + * Init interface to Open Firmware, get some node references, + * like /chosen + */ + prom_init_client_services(pp); + + /* + * Init prom stdout device + */ + prom_init_stdout(); + + /* + * See if this OF is old enough that we need to do explicit maps + */ + prom_find_mmu(); + + /* + * Check for an initrd + */ + prom_check_initrd(r3, r4); + + /* + * Get default machine type. At this point, we do not differentiate + * between pSeries SMP and pSeries LPAR + */ + RELOC(of_platform) = prom_find_machine_type(); + getprop_rval = RELOC(of_platform); + prom_setprop(_prom->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) + prom_send_capabilities(); +#endif + + /* + * On pSeries and BPA, copy the CPU hold code + */ + if (RELOC(of_platform) != PLATFORM_POWERMAC) + copy_and_flush(0, KERNELBASE + offset, 0x100, 0); + + /* + * Do early parsing of command line + */ + early_cmdline_parse(); + + /* + * Initialize memory management within prom_init + */ + prom_init_mem(); + + /* + * Determine which cpu is actually running right _now_ + */ + prom_find_boot_cpu(); + + /* + * Initialize display devices + */ + prom_check_displays(); + +#ifdef CONFIG_PPC64 + /* + * Initialize IOMMU (TCE tables) on pSeries. Do that before anything else + * that uses the allocator, we need to make sure we get the top of memory + * available for us here... + */ + if (RELOC(of_platform) == PLATFORM_PSERIES) + prom_initialize_tce_table(); +#endif + + /* + * On non-powermacs, try to instantiate RTAS and puts all CPUs + * in spin-loops. PowerMacs don't have a working RTAS and use + * a different way to spin CPUs + */ + if (RELOC(of_platform) != PLATFORM_POWERMAC) { + prom_instantiate_rtas(); + prom_hold_cpus(); + } + + /* + * Fill in some infos for use by the kernel later on + */ + if (RELOC(prom_memory_limit)) + prom_setprop(_prom->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); + + if (RELOC(iommu_force_on)) + prom_setprop(_prom->chosen, "linux,iommu-force-on", NULL, 0); + + if (RELOC(prom_tce_alloc_start)) { + prom_setprop(_prom->chosen, "linux,tce-alloc-start", + &RELOC(prom_tce_alloc_start), + sizeof(prom_tce_alloc_start)); + prom_setprop(_prom->chosen, "linux,tce-alloc-end", + &RELOC(prom_tce_alloc_end), + sizeof(prom_tce_alloc_end)); + } +#endif + + /* + * Fixup any known bugs in the device-tree + */ + fixup_device_tree(); + + /* + * Now finally create the flattened device-tree + */ + prom_printf("copying OF device tree ...\n"); + flatten_device_tree(); + + /* in case stdin is USB and still active on IBM machines... */ + prom_close_stdin(); + + /* + * Call OF "quiesce" method to shut down pending DMA's from + * devices etc... + */ + prom_printf("Calling quiesce ...\n"); + call_prom("quiesce", 0, 0); + + /* + * And finally, call the kernel passing it the flattened device + * tree and NULL as r5, thus triggering the new entry point which + * is common to us and kexec + */ + hdr = RELOC(dt_header_start); + prom_printf("returning from prom_init\n"); + prom_debug("->dt_header_start=0x%x\n", hdr); + +#ifdef CONFIG_PPC32 + reloc_got2(-offset); +#endif + + __start(hdr, KERNELBASE + offset, 0); + + return 0; +} diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c new file mode 100644 index 000000000000..568ea335d616 --- /dev/null +++ b/arch/powerpc/kernel/ptrace.c @@ -0,0 +1,613 @@ +/* + * PowerPC version + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) + * + * Derived from "arch/m68k/kernel/ptrace.c" + * Copyright (C) 1994 by Hamish Macdonald + * Taken from linux/kernel/ptrace.c and modified for M680x0. + * linux/kernel/ptrace.c is by Ross Biro 1/23/92, edited by Linus Torvalds + * + * Modified by Cort Dougan (cort@hq.fsmlabs.com) + * and Paul Mackerras (paulus@samba.org). + * + * This file is subject to the terms and conditions of the GNU General + * Public License. See the file README.legal in the main directory of + * this archive for more details. + */ + +#include <linux/config.h> +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/smp_lock.h> +#include <linux/errno.h> +#include <linux/ptrace.h> +#include <linux/user.h> +#include <linux/security.h> +#include <linux/signal.h> +#include <linux/seccomp.h> +#include <linux/audit.h> +#ifdef CONFIG_PPC32 +#include <linux/module.h> +#endif + +#include <asm/uaccess.h> +#include <asm/page.h> +#include <asm/pgtable.h> +#include <asm/system.h> +#ifdef CONFIG_PPC64 +#include <asm/ptrace-common.h> +#endif + +#ifdef CONFIG_PPC32 +/* + * Set of msr bits that gdb can change on behalf of a process. + */ +#if defined(CONFIG_40x) || defined(CONFIG_BOOKE) +#define MSR_DEBUGCHANGE 0 +#else +#define MSR_DEBUGCHANGE (MSR_SE | MSR_BE) +#endif +#endif /* CONFIG_PPC32 */ + +/* + * does not yet catch signals sent when the child dies. + * in exit.c or in signal.c. + */ + +#ifdef CONFIG_PPC32 +/* + * Get contents of register REGNO in task TASK. + */ +static inline unsigned long get_reg(struct task_struct *task, int regno) +{ + if (regno < sizeof(struct pt_regs) / sizeof(unsigned long) + && task->thread.regs != NULL) + return ((unsigned long *)task->thread.regs)[regno]; + return (0); +} + +/* + * Write contents of register REGNO in task TASK. + */ +static inline int put_reg(struct task_struct *task, int regno, + unsigned long data) +{ + if (regno <= PT_MQ && task->thread.regs != NULL) { + if (regno == PT_MSR) + data = (data & MSR_DEBUGCHANGE) + | (task->thread.regs->msr & ~MSR_DEBUGCHANGE); + ((unsigned long *)task->thread.regs)[regno] = data; + return 0; + } + return -EIO; +} + +#ifdef CONFIG_ALTIVEC +/* + * Get contents of AltiVec register state in task TASK + */ +static inline int get_vrregs(unsigned long __user *data, struct task_struct *task) +{ + int i, j; + + if (!access_ok(VERIFY_WRITE, data, 133 * sizeof(unsigned long))) + return -EFAULT; + + /* copy AltiVec registers VR[0] .. VR[31] */ + for (i = 0; i < 32; i++) + for (j = 0; j < 4; j++, data++) + if (__put_user(task->thread.vr[i].u[j], data)) + return -EFAULT; + + /* copy VSCR */ + for (i = 0; i < 4; i++, data++) + if (__put_user(task->thread.vscr.u[i], data)) + return -EFAULT; + + /* copy VRSAVE */ + if (__put_user(task->thread.vrsave, data)) + return -EFAULT; + + return 0; +} + +/* + * Write contents of AltiVec register state into task TASK. + */ +static inline int set_vrregs(struct task_struct *task, unsigned long __user *data) +{ + int i, j; + + if (!access_ok(VERIFY_READ, data, 133 * sizeof(unsigned long))) + return -EFAULT; + + /* copy AltiVec registers VR[0] .. VR[31] */ + for (i = 0; i < 32; i++) + for (j = 0; j < 4; j++, data++) + if (__get_user(task->thread.vr[i].u[j], data)) + return -EFAULT; + + /* copy VSCR */ + for (i = 0; i < 4; i++, data++) + if (__get_user(task->thread.vscr.u[i], data)) + return -EFAULT; + + /* copy VRSAVE */ + if (__get_user(task->thread.vrsave, data)) + return -EFAULT; + + return 0; +} +#endif + +#ifdef CONFIG_SPE + +/* + * For get_evrregs/set_evrregs functions 'data' has the following layout: + * + * struct { + * u32 evr[32]; + * u64 acc; + * u32 spefscr; + * } + */ + +/* + * Get contents of SPE register state in task TASK. + */ +static inline int get_evrregs(unsigned long *data, struct task_struct *task) +{ + int i; + + if (!access_ok(VERIFY_WRITE, data, 35 * sizeof(unsigned long))) + return -EFAULT; + + /* copy SPEFSCR */ + if (__put_user(task->thread.spefscr, &data[34])) + return -EFAULT; + + /* copy SPE registers EVR[0] .. EVR[31] */ + for (i = 0; i < 32; i++, data++) + if (__put_user(task->thread.evr[i], data)) + return -EFAULT; + + /* copy ACC */ + if (__put_user64(task->thread.acc, (unsigned long long *)data)) + return -EFAULT; + + return 0; +} + +/* + * Write contents of SPE register state into task TASK. + */ +static inline int set_evrregs(struct task_struct *task, unsigned long *data) +{ + int i; + + if (!access_ok(VERIFY_READ, data, 35 * sizeof(unsigned long))) + return -EFAULT; + + /* copy SPEFSCR */ + if (__get_user(task->thread.spefscr, &data[34])) + return -EFAULT; + + /* copy SPE registers EVR[0] .. EVR[31] */ + for (i = 0; i < 32; i++, data++) + if (__get_user(task->thread.evr[i], data)) + return -EFAULT; + /* copy ACC */ + if (__get_user64(task->thread.acc, (unsigned long long*)data)) + return -EFAULT; + + return 0; +} +#endif /* CONFIG_SPE */ + +static inline void +set_single_step(struct task_struct *task) +{ + struct pt_regs *regs = task->thread.regs; + + if (regs != NULL) { +#if defined(CONFIG_40x) || defined(CONFIG_BOOKE) + task->thread.dbcr0 = DBCR0_IDM | DBCR0_IC; + regs->msr |= MSR_DE; +#else + regs->msr |= MSR_SE; +#endif + } +} + +static inline void +clear_single_step(struct task_struct *task) +{ + struct pt_regs *regs = task->thread.regs; + + if (regs != NULL) { +#if defined(CONFIG_40x) || defined(CONFIG_BOOKE) + task->thread.dbcr0 = 0; + regs->msr &= ~MSR_DE; +#else + regs->msr &= ~MSR_SE; +#endif + } +} +#endif /* CONFIG_PPC32 */ + +/* + * Called by kernel/ptrace.c when detaching.. + * + * Make sure single step bits etc are not set. + */ +void ptrace_disable(struct task_struct *child) +{ + /* make sure the single step bit is not set. */ + clear_single_step(child); +} + +long sys_ptrace(long request, long pid, long addr, long data) +{ + struct task_struct *child; + int ret = -EPERM; + + lock_kernel(); + if (request == PTRACE_TRACEME) { + /* are we already being traced? */ + if (current->ptrace & PT_PTRACED) + goto out; + ret = security_ptrace(current->parent, current); + if (ret) + goto out; + /* set the ptrace bit in the process flags. */ + current->ptrace |= PT_PTRACED; + ret = 0; + goto out; + } + ret = -ESRCH; + read_lock(&tasklist_lock); + child = find_task_by_pid(pid); + if (child) + get_task_struct(child); + read_unlock(&tasklist_lock); + if (!child) + goto out; + + ret = -EPERM; + if (pid == 1) /* you may not mess with init */ + goto out_tsk; + + if (request == PTRACE_ATTACH) { + ret = ptrace_attach(child); + goto out_tsk; + } + + ret = ptrace_check_attach(child, request == PTRACE_KILL); + if (ret < 0) + goto out_tsk; + + switch (request) { + /* when I and D space are separate, these will need to be fixed. */ + case PTRACE_PEEKTEXT: /* read word at location addr. */ + case PTRACE_PEEKDATA: { + unsigned long tmp; + int copied; + + copied = access_process_vm(child, addr, &tmp, sizeof(tmp), 0); + ret = -EIO; + if (copied != sizeof(tmp)) + break; + ret = put_user(tmp,(unsigned long __user *) data); + break; + } + + /* read the word at location addr in the USER area. */ + case PTRACE_PEEKUSR: { + unsigned long index, tmp; + + ret = -EIO; + /* convert to index and check */ +#ifdef CONFIG_PPC32 + index = (unsigned long) addr >> 2; + if ((addr & 3) || (index > PT_FPSCR) + || (child->thread.regs == NULL)) +#else + index = (unsigned long) addr >> 3; + if ((addr & 7) || (index > PT_FPSCR)) +#endif + break; + +#ifdef CONFIG_PPC32 + CHECK_FULL_REGS(child->thread.regs); +#endif + if (index < PT_FPR0) { + tmp = get_reg(child, (int) index); + } else { + flush_fp_to_thread(child); + tmp = ((unsigned long *)child->thread.fpr)[index - PT_FPR0]; + } + ret = put_user(tmp,(unsigned long __user *) data); + break; + } + + /* If I and D space are separate, this will have to be fixed. */ + case PTRACE_POKETEXT: /* write the word at location addr. */ + case PTRACE_POKEDATA: + ret = 0; + if (access_process_vm(child, addr, &data, sizeof(data), 1) + == sizeof(data)) + break; + ret = -EIO; + break; + + /* write the word at location addr in the USER area */ + case PTRACE_POKEUSR: { + unsigned long index; + + ret = -EIO; + /* convert to index and check */ +#ifdef CONFIG_PPC32 + index = (unsigned long) addr >> 2; + if ((addr & 3) || (index > PT_FPSCR) + || (child->thread.regs == NULL)) +#else + index = (unsigned long) addr >> 3; + if ((addr & 7) || (index > PT_FPSCR)) +#endif + break; + +#ifdef CONFIG_PPC32 + CHECK_FULL_REGS(child->thread.regs); +#endif + if (index == PT_ORIG_R3) + break; + if (index < PT_FPR0) { + ret = put_reg(child, index, data); + } else { + flush_fp_to_thread(child); + ((unsigned long *)child->thread.fpr)[index - PT_FPR0] = data; + ret = 0; + } + break; + } + + case PTRACE_SYSCALL: /* continue and stop at next (return from) syscall */ + case PTRACE_CONT: { /* restart after signal. */ + ret = -EIO; + if (!valid_signal(data)) + break; + if (request == PTRACE_SYSCALL) + set_tsk_thread_flag(child, TIF_SYSCALL_TRACE); + else + clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE); + child->exit_code = data; + /* make sure the single step bit is not set. */ + clear_single_step(child); + wake_up_process(child); + ret = 0; + break; + } + +/* + * make the child exit. Best I can do is send it a sigkill. + * perhaps it should be put in the status that it wants to + * exit. + */ + case PTRACE_KILL: { + ret = 0; + if (child->exit_state == EXIT_ZOMBIE) /* already dead */ + break; + child->exit_code = SIGKILL; + /* make sure the single step bit is not set. */ + clear_single_step(child); + wake_up_process(child); + break; + } + + case PTRACE_SINGLESTEP: { /* set the trap flag. */ + ret = -EIO; + if (!valid_signal(data)) + break; + clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE); + set_single_step(child); + child->exit_code = data; + /* give it a chance to run. */ + wake_up_process(child); + ret = 0; + break; + } + +#ifdef CONFIG_PPC64 + case PTRACE_GET_DEBUGREG: { + ret = -EINVAL; + /* We only support one DABR and no IABRS at the moment */ + if (addr > 0) + break; + ret = put_user(child->thread.dabr, + (unsigned long __user *)data); + break; + } + + case PTRACE_SET_DEBUGREG: + ret = ptrace_set_debugreg(child, addr, data); + break; +#endif + + case PTRACE_DETACH: + ret = ptrace_detach(child, data); + break; + +#ifdef CONFIG_PPC64 + case PPC_PTRACE_GETREGS: { /* Get GPRs 0 - 31. */ + int i; + unsigned long *reg = &((unsigned long *)child->thread.regs)[0]; + unsigned long __user *tmp = (unsigned long __user *)addr; + + for (i = 0; i < 32; i++) { + ret = put_user(*reg, tmp); + if (ret) + break; + reg++; + tmp++; + } + break; + } + + case PPC_PTRACE_SETREGS: { /* Set GPRs 0 - 31. */ + int i; + unsigned long *reg = &((unsigned long *)child->thread.regs)[0]; + unsigned long __user *tmp = (unsigned long __user *)addr; + + for (i = 0; i < 32; i++) { + ret = get_user(*reg, tmp); + if (ret) + break; + reg++; + tmp++; + } + break; + } + + case PPC_PTRACE_GETFPREGS: { /* Get FPRs 0 - 31. */ + int i; + unsigned long *reg = &((unsigned long *)child->thread.fpr)[0]; + unsigned long __user *tmp = (unsigned long __user *)addr; + + flush_fp_to_thread(child); + + for (i = 0; i < 32; i++) { + ret = put_user(*reg, tmp); + if (ret) + break; + reg++; + tmp++; + } + break; + } + + case PPC_PTRACE_SETFPREGS: { /* Get FPRs 0 - 31. */ + int i; + unsigned long *reg = &((unsigned long *)child->thread.fpr)[0]; + unsigned long __user *tmp = (unsigned long __user *)addr; + + flush_fp_to_thread(child); + + for (i = 0; i < 32; i++) { + ret = get_user(*reg, tmp); + if (ret) + break; + reg++; + tmp++; + } + break; + } +#endif /* CONFIG_PPC64 */ + +#ifdef CONFIG_ALTIVEC + case PTRACE_GETVRREGS: + /* Get the child altivec register state. */ + flush_altivec_to_thread(child); + ret = get_vrregs((unsigned long __user *)data, child); + break; + + case PTRACE_SETVRREGS: + /* Set the child altivec register state. */ + flush_altivec_to_thread(child); + ret = set_vrregs(child, (unsigned long __user *)data); + break; +#endif +#ifdef CONFIG_SPE + case PTRACE_GETEVRREGS: + /* Get the child spe register state. */ + if (child->thread.regs->msr & MSR_SPE) + giveup_spe(child); + ret = get_evrregs((unsigned long __user *)data, child); + break; + + case PTRACE_SETEVRREGS: + /* Set the child spe register state. */ + /* this is to clear the MSR_SPE bit to force a reload + * of register state from memory */ + if (child->thread.regs->msr & MSR_SPE) + giveup_spe(child); + ret = set_evrregs(child, (unsigned long __user *)data); + break; +#endif + + default: + ret = ptrace_request(child, request, addr, data); + break; + } +out_tsk: + put_task_struct(child); +out: + unlock_kernel(); + return ret; +} + +static void do_syscall_trace(void) +{ + /* the 0x80 provides a way for the tracing parent to distinguish + between a syscall stop and SIGTRAP delivery */ + ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD) + ? 0x80 : 0)); + + /* + * this isn't the same as continuing with a signal, but it will do + * for normal use. strace only continues with a signal if the + * stopping signal is not SIGTRAP. -brl + */ + if (current->exit_code) { + send_sig(current->exit_code, current, 1); + current->exit_code = 0; + } +} + +void do_syscall_trace_enter(struct pt_regs *regs) +{ +#ifdef CONFIG_PPC64 + secure_computing(regs->gpr[0]); +#endif + + if (test_thread_flag(TIF_SYSCALL_TRACE) + && (current->ptrace & PT_PTRACED)) + do_syscall_trace(); + + if (unlikely(current->audit_context)) + audit_syscall_entry(current, +#ifdef CONFIG_PPC32 + AUDIT_ARCH_PPC, +#else + test_thread_flag(TIF_32BIT)?AUDIT_ARCH_PPC:AUDIT_ARCH_PPC64, +#endif + regs->gpr[0], + regs->gpr[3], regs->gpr[4], + regs->gpr[5], regs->gpr[6]); +} + +void do_syscall_trace_leave(struct pt_regs *regs) +{ +#ifdef CONFIG_PPC32 + secure_computing(regs->gpr[0]); +#endif + + if (unlikely(current->audit_context)) + audit_syscall_exit(current, + (regs->ccr&0x1000)?AUDITSC_FAILURE:AUDITSC_SUCCESS, + regs->result); + + if ((test_thread_flag(TIF_SYSCALL_TRACE) +#ifdef CONFIG_PPC64 + || test_thread_flag(TIF_SINGLESTEP) +#endif + ) + && (current->ptrace & PT_PTRACED)) + do_syscall_trace(); +} + +#ifdef CONFIG_PPC32 +EXPORT_SYMBOL(do_syscall_trace_enter); +EXPORT_SYMBOL(do_syscall_trace_leave); +#endif diff --git a/arch/powerpc/kernel/ptrace32.c b/arch/powerpc/kernel/ptrace32.c new file mode 100644 index 000000000000..91eb952e0293 --- /dev/null +++ b/arch/powerpc/kernel/ptrace32.c @@ -0,0 +1,450 @@ +/* + * ptrace for 32-bit processes running on a 64-bit kernel. + * + * PowerPC version + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) + * + * Derived from "arch/m68k/kernel/ptrace.c" + * Copyright (C) 1994 by Hamish Macdonald + * Taken from linux/kernel/ptrace.c and modified for M680x0. + * linux/kernel/ptrace.c is by Ross Biro 1/23/92, edited by Linus Torvalds + * + * Modified by Cort Dougan (cort@hq.fsmlabs.com) + * and Paul Mackerras (paulus@samba.org). + * + * This file is subject to the terms and conditions of the GNU General + * Public License. See the file COPYING in the main directory of + * this archive for more details. + */ + +#include <linux/config.h> +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/smp_lock.h> +#include <linux/errno.h> +#include <linux/ptrace.h> +#include <linux/user.h> +#include <linux/security.h> +#include <linux/signal.h> + +#include <asm/uaccess.h> +#include <asm/page.h> +#include <asm/pgtable.h> +#include <asm/system.h> +#include <asm/ptrace-common.h> + +/* + * does not yet catch signals sent when the child dies. + * in exit.c or in signal.c. + */ + +long compat_sys_ptrace(int request, int pid, unsigned long addr, + unsigned long data) +{ + struct task_struct *child; + int ret = -EPERM; + + lock_kernel(); + if (request == PTRACE_TRACEME) { + /* are we already being traced? */ + if (current->ptrace & PT_PTRACED) + goto out; + ret = security_ptrace(current->parent, current); + if (ret) + goto out; + /* set the ptrace bit in the process flags. */ + current->ptrace |= PT_PTRACED; + ret = 0; + goto out; + } + ret = -ESRCH; + read_lock(&tasklist_lock); + child = find_task_by_pid(pid); + if (child) + get_task_struct(child); + read_unlock(&tasklist_lock); + if (!child) + goto out; + + ret = -EPERM; + if (pid == 1) /* you may not mess with init */ + goto out_tsk; + + if (request == PTRACE_ATTACH) { + ret = ptrace_attach(child); + goto out_tsk; + } + + ret = ptrace_check_attach(child, request == PTRACE_KILL); + if (ret < 0) + goto out_tsk; + + switch (request) { + /* when I and D space are separate, these will need to be fixed. */ + case PTRACE_PEEKTEXT: /* read word at location addr. */ + case PTRACE_PEEKDATA: { + unsigned int tmp; + int copied; + + copied = access_process_vm(child, addr, &tmp, sizeof(tmp), 0); + ret = -EIO; + if (copied != sizeof(tmp)) + break; + ret = put_user(tmp, (u32 __user *)data); + break; + } + + /* + * Read 4 bytes of the other process' storage + * data is a pointer specifying where the user wants the + * 4 bytes copied into + * addr is a pointer in the user's storage that contains an 8 byte + * address in the other process of the 4 bytes that is to be read + * (this is run in a 32-bit process looking at a 64-bit process) + * when I and D space are separate, these will need to be fixed. + */ + case PPC_PTRACE_PEEKTEXT_3264: + case PPC_PTRACE_PEEKDATA_3264: { + u32 tmp; + int copied; + u32 __user * addrOthers; + + ret = -EIO; + + /* Get the addr in the other process that we want to read */ + if (get_user(addrOthers, (u32 __user * __user *)addr) != 0) + break; + + copied = access_process_vm(child, (u64)addrOthers, &tmp, + sizeof(tmp), 0); + if (copied != sizeof(tmp)) + break; + ret = put_user(tmp, (u32 __user *)data); + break; + } + + /* Read a register (specified by ADDR) out of the "user area" */ + case PTRACE_PEEKUSR: { + int index; + unsigned long tmp; + + ret = -EIO; + /* convert to index and check */ + index = (unsigned long) addr >> 2; + if ((addr & 3) || (index > PT_FPSCR32)) + break; + + if (index < PT_FPR0) { + tmp = get_reg(child, index); + } else { + flush_fp_to_thread(child); + /* + * the user space code considers the floating point + * to be an array of unsigned int (32 bits) - the + * index passed in is based on this assumption. + */ + tmp = ((unsigned int *)child->thread.fpr)[index - PT_FPR0]; + } + ret = put_user((unsigned int)tmp, (u32 __user *)data); + break; + } + + /* + * Read 4 bytes out of the other process' pt_regs area + * data is a pointer specifying where the user wants the + * 4 bytes copied into + * addr is the offset into the other process' pt_regs structure + * that is to be read + * (this is run in a 32-bit process looking at a 64-bit process) + */ + case PPC_PTRACE_PEEKUSR_3264: { + u32 index; + u32 reg32bits; + u64 tmp; + u32 numReg; + u32 part; + + ret = -EIO; + /* Determine which register the user wants */ + index = (u64)addr >> 2; + numReg = index / 2; + /* Determine which part of the register the user wants */ + if (index % 2) + part = 1; /* want the 2nd half of the register (right-most). */ + else + part = 0; /* want the 1st half of the register (left-most). */ + + /* Validate the input - check to see if address is on the wrong boundary or beyond the end of the user area */ + if ((addr & 3) || numReg > PT_FPSCR) + break; + + if (numReg >= PT_FPR0) { + flush_fp_to_thread(child); + tmp = ((unsigned long int *)child->thread.fpr)[numReg - PT_FPR0]; + } else { /* register within PT_REGS struct */ + tmp = get_reg(child, numReg); + } + reg32bits = ((u32*)&tmp)[part]; + ret = put_user(reg32bits, (u32 __user *)data); + break; + } + + /* If I and D space are separate, this will have to be fixed. */ + case PTRACE_POKETEXT: /* write the word at location addr. */ + case PTRACE_POKEDATA: { + unsigned int tmp; + tmp = data; + ret = 0; + if (access_process_vm(child, addr, &tmp, sizeof(tmp), 1) + == sizeof(tmp)) + break; + ret = -EIO; + break; + } + + /* + * Write 4 bytes into the other process' storage + * data is the 4 bytes that the user wants written + * addr is a pointer in the user's storage that contains an + * 8 byte address in the other process where the 4 bytes + * that is to be written + * (this is run in a 32-bit process looking at a 64-bit process) + * when I and D space are separate, these will need to be fixed. + */ + case PPC_PTRACE_POKETEXT_3264: + case PPC_PTRACE_POKEDATA_3264: { + u32 tmp = data; + u32 __user * addrOthers; + + /* Get the addr in the other process that we want to write into */ + ret = -EIO; + if (get_user(addrOthers, (u32 __user * __user *)addr) != 0) + break; + ret = 0; + if (access_process_vm(child, (u64)addrOthers, &tmp, + sizeof(tmp), 1) == sizeof(tmp)) + break; + ret = -EIO; + break; + } + + /* write the word at location addr in the USER area */ + case PTRACE_POKEUSR: { + unsigned long index; + + ret = -EIO; + /* convert to index and check */ + index = (unsigned long) addr >> 2; + if ((addr & 3) || (index > PT_FPSCR32)) + break; + + if (index == PT_ORIG_R3) + break; + if (index < PT_FPR0) { + ret = put_reg(child, index, data); + } else { + flush_fp_to_thread(child); + /* + * the user space code considers the floating point + * to be an array of unsigned int (32 bits) - the + * index passed in is based on this assumption. + */ + ((unsigned int *)child->thread.fpr)[index - PT_FPR0] = data; + ret = 0; + } + break; + } + + /* + * Write 4 bytes into the other process' pt_regs area + * data is the 4 bytes that the user wants written + * addr is the offset into the other process' pt_regs structure + * that is to be written into + * (this is run in a 32-bit process looking at a 64-bit process) + */ + case PPC_PTRACE_POKEUSR_3264: { + u32 index; + u32 numReg; + + ret = -EIO; + /* Determine which register the user wants */ + index = (u64)addr >> 2; + numReg = index / 2; + /* + * Validate the input - check to see if address is on the + * wrong boundary or beyond the end of the user area + */ + if ((addr & 3) || (numReg > PT_FPSCR)) + break; + /* Insure it is a register we let them change */ + if ((numReg == PT_ORIG_R3) + || ((numReg > PT_CCR) && (numReg < PT_FPR0))) + break; + if (numReg >= PT_FPR0) { + flush_fp_to_thread(child); + } + if (numReg == PT_MSR) + data = (data & MSR_DEBUGCHANGE) + | (child->thread.regs->msr & ~MSR_DEBUGCHANGE); + ((u32*)child->thread.regs)[index] = data; + ret = 0; + break; + } + + case PTRACE_SYSCALL: /* continue and stop at next (return from) syscall */ + case PTRACE_CONT: { /* restart after signal. */ + ret = -EIO; + if (!valid_signal(data)) + break; + if (request == PTRACE_SYSCALL) + set_tsk_thread_flag(child, TIF_SYSCALL_TRACE); + else + clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE); + child->exit_code = data; + /* make sure the single step bit is not set. */ + clear_single_step(child); + wake_up_process(child); + ret = 0; + break; + } + + /* + * make the child exit. Best I can do is send it a sigkill. + * perhaps it should be put in the status that it wants to + * exit. + */ + case PTRACE_KILL: { + ret = 0; + if (child->exit_state == EXIT_ZOMBIE) /* already dead */ + break; + child->exit_code = SIGKILL; + /* make sure the single step bit is not set. */ + clear_single_step(child); + wake_up_process(child); + break; + } + + case PTRACE_SINGLESTEP: { /* set the trap flag. */ + ret = -EIO; + if (!valid_signal(data)) + break; + clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE); + set_single_step(child); + child->exit_code = data; + /* give it a chance to run. */ + wake_up_process(child); + ret = 0; + break; + } + + case PTRACE_GET_DEBUGREG: { + ret = -EINVAL; + /* We only support one DABR and no IABRS at the moment */ + if (addr > 0) + break; + ret = put_user(child->thread.dabr, (u32 __user *)data); + break; + } + + case PTRACE_SET_DEBUGREG: + ret = ptrace_set_debugreg(child, addr, data); + break; + + case PTRACE_DETACH: + ret = ptrace_detach(child, data); + break; + + case PPC_PTRACE_GETREGS: { /* Get GPRs 0 - 31. */ + int i; + unsigned long *reg = &((unsigned long *)child->thread.regs)[0]; + unsigned int __user *tmp = (unsigned int __user *)addr; + + for (i = 0; i < 32; i++) { + ret = put_user(*reg, tmp); + if (ret) + break; + reg++; + tmp++; + } + break; + } + + case PPC_PTRACE_SETREGS: { /* Set GPRs 0 - 31. */ + int i; + unsigned long *reg = &((unsigned long *)child->thread.regs)[0]; + unsigned int __user *tmp = (unsigned int __user *)addr; + + for (i = 0; i < 32; i++) { + ret = get_user(*reg, tmp); + if (ret) + break; + reg++; + tmp++; + } + break; + } + + case PPC_PTRACE_GETFPREGS: { /* Get FPRs 0 - 31. */ + int i; + unsigned long *reg = &((unsigned long *)child->thread.fpr)[0]; + unsigned int __user *tmp = (unsigned int __user *)addr; + + flush_fp_to_thread(child); + + for (i = 0; i < 32; i++) { + ret = put_user(*reg, tmp); + if (ret) + break; + reg++; + tmp++; + } + break; + } + + case PPC_PTRACE_SETFPREGS: { /* Get FPRs 0 - 31. */ + int i; + unsigned long *reg = &((unsigned long *)child->thread.fpr)[0]; + unsigned int __user *tmp = (unsigned int __user *)addr; + + flush_fp_to_thread(child); + + for (i = 0; i < 32; i++) { + ret = get_user(*reg, tmp); + if (ret) + break; + reg++; + tmp++; + } + break; + } + + case PTRACE_GETEVENTMSG: + ret = put_user(child->ptrace_message, (unsigned int __user *) data); + break; + +#ifdef CONFIG_ALTIVEC + case PTRACE_GETVRREGS: + /* Get the child altivec register state. */ + flush_altivec_to_thread(child); + ret = get_vrregs((unsigned long __user *)data, child); + break; + + case PTRACE_SETVRREGS: + /* Set the child altivec register state. */ + flush_altivec_to_thread(child); + ret = set_vrregs(child, (unsigned long __user *)data); + break; +#endif + + default: + ret = ptrace_request(child, request, addr, data); + break; + } +out_tsk: + put_task_struct(child); +out: + unlock_kernel(); + return ret; +} diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c new file mode 100644 index 000000000000..4d22eeeeb91d --- /dev/null +++ b/arch/powerpc/kernel/rtas.c @@ -0,0 +1,680 @@ +/* + * + * Procedures for interfacing to the RTAS on CHRP machines. + * + * Peter Bergner, IBM March 2001. + * Copyright (C) 2001 IBM. + * + * 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/kernel.h> +#include <linux/types.h> +#include <linux/spinlock.h> +#include <linux/module.h> +#include <linux/init.h> + +#include <asm/prom.h> +#include <asm/rtas.h> +#include <asm/semaphore.h> +#include <asm/machdep.h> +#include <asm/page.h> +#include <asm/param.h> +#include <asm/system.h> +#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 +}; + +EXPORT_SYMBOL(rtas); + +DEFINE_SPINLOCK(rtas_data_buf_lock); +char rtas_data_buf[RTAS_DATA_BUF_SIZE] __cacheline_aligned; +unsigned long rtas_rmo_buf; + +/* + * call_rtas_display_status and call_rtas_display_status_delay + * are designed only for very early low-level debugging, which + * is why the token is hard-coded to 10. + */ +void call_rtas_display_status(unsigned char c) +{ + struct rtas_args *args = &rtas.args; + unsigned long s; + + if (!rtas.base) + return; + spin_lock_irqsave(&rtas.lock, s); + + args->token = 10; + args->nargs = 1; + args->nret = 1; + args->rets = (rtas_arg_t *)&(args->args[1]); + args->args[0] = (int)c; + + enter_rtas(__pa(args)); + + spin_unlock_irqrestore(&rtas.lock, s); +} + +void call_rtas_display_status_delay(unsigned char c) +{ + static int pending_newline = 0; /* did last write end with unprinted newline? */ + static int width = 16; + + if (c == '\n') { + while (width-- > 0) + call_rtas_display_status(' '); + width = 16; + udelay(500000); + pending_newline = 1; + } else { + if (pending_newline) { + call_rtas_display_status('\r'); + call_rtas_display_status('\n'); + } + pending_newline = 0; + if (width--) { + call_rtas_display_status(c); + udelay(10000); + } + } +} + +void rtas_progress(char *s, unsigned short hex) +{ + struct device_node *root; + int width, *p; + char *os; + static int display_character, set_indicator; + static int display_width, display_lines, *row_width, form_feed; + static DEFINE_SPINLOCK(progress_lock); + static int current_line; + static int pending_newline = 0; /* did last write end with unprinted newline? */ + + if (!rtas.base) + return; + + if (display_width == 0) { + display_width = 0x10; + if ((root = find_path_device("/rtas"))) { + if ((p = (unsigned int *)get_property(root, + "ibm,display-line-length", NULL))) + display_width = *p; + if ((p = (unsigned int *)get_property(root, + "ibm,form-feed", NULL))) + form_feed = *p; + if ((p = (unsigned int *)get_property(root, + "ibm,display-number-of-lines", NULL))) + display_lines = *p; + row_width = (unsigned int *)get_property(root, + "ibm,display-truncation-length", NULL); + } + display_character = rtas_token("display-character"); + set_indicator = rtas_token("set-indicator"); + } + + if (display_character == RTAS_UNKNOWN_SERVICE) { + /* use hex display if available */ + if (set_indicator != RTAS_UNKNOWN_SERVICE) + rtas_call(set_indicator, 3, 1, NULL, 6, 0, hex); + return; + } + + spin_lock(&progress_lock); + + /* + * Last write ended with newline, but we didn't print it since + * it would just clear the bottom line of output. Print it now + * instead. + * + * If no newline is pending and form feed is supported, clear the + * display with a form feed; otherwise, print a CR to start output + * at the beginning of the line. + */ + if (pending_newline) { + rtas_call(display_character, 1, 1, NULL, '\r'); + rtas_call(display_character, 1, 1, NULL, '\n'); + pending_newline = 0; + } else { + current_line = 0; + if (form_feed) + rtas_call(display_character, 1, 1, NULL, + (char)form_feed); + else + rtas_call(display_character, 1, 1, NULL, '\r'); + } + + if (row_width) + width = row_width[current_line]; + else + width = display_width; + os = s; + while (*os) { + if (*os == '\n' || *os == '\r') { + /* If newline is the last character, save it + * until next call to avoid bumping up the + * display output. + */ + if (*os == '\n' && !os[1]) { + pending_newline = 1; + current_line++; + if (current_line > display_lines-1) + current_line = display_lines-1; + spin_unlock(&progress_lock); + return; + } + + /* RTAS wants CR-LF, not just LF */ + + if (*os == '\n') { + rtas_call(display_character, 1, 1, NULL, '\r'); + rtas_call(display_character, 1, 1, NULL, '\n'); + } else { + /* CR might be used to re-draw a line, so we'll + * leave it alone and not add LF. + */ + rtas_call(display_character, 1, 1, NULL, *os); + } + + if (row_width) + width = row_width[current_line]; + else + width = display_width; + } else { + width--; + rtas_call(display_character, 1, 1, NULL, *os); + } + + os++; + + /* if we overwrite the screen length */ + if (width <= 0) + while ((*os != 0) && (*os != '\n') && (*os != '\r')) + os++; + } + + spin_unlock(&progress_lock); +} + +int rtas_token(const char *service) +{ + int *tokp; + if (rtas.dev == NULL) + return RTAS_UNKNOWN_SERVICE; + tokp = (int *) get_property(rtas.dev, service, NULL); + return tokp ? *tokp : RTAS_UNKNOWN_SERVICE; +} + +#ifdef CONFIG_RTAS_ERROR_LOGGING +/* + * Return the firmware-specified size of the error log buffer + * for all rtas calls that require an error buffer argument. + * This includes 'check-exception' and 'rtas-last-error'. + */ +int rtas_get_error_log_max(void) +{ + static int rtas_error_log_max; + if (rtas_error_log_max) + return rtas_error_log_max; + + rtas_error_log_max = rtas_token ("rtas-error-log-max"); + if ((rtas_error_log_max == RTAS_UNKNOWN_SERVICE) || + (rtas_error_log_max > RTAS_ERROR_LOG_MAX)) { + printk (KERN_WARNING "RTAS: bad log buffer size %d\n", + rtas_error_log_max); + rtas_error_log_max = RTAS_ERROR_LOG_MAX; + } + return rtas_error_log_max; +} +EXPORT_SYMBOL(rtas_get_error_log_max); + + +char rtas_err_buf[RTAS_ERROR_LOG_MAX]; +int rtas_last_error_token; + +/** Return a copy of the detailed error text associated with the + * most recent failed call to rtas. Because the error text + * might go stale if there are any other intervening rtas calls, + * this routine must be called atomically with whatever produced + * the error (i.e. with rtas.lock still held from the previous call). + */ +static char *__fetch_rtas_last_error(char *altbuf) +{ + struct rtas_args err_args, save_args; + u32 bufsz; + char *buf = NULL; + + if (rtas_last_error_token == -1) + return NULL; + + bufsz = rtas_get_error_log_max(); + + err_args.token = rtas_last_error_token; + err_args.nargs = 2; + err_args.nret = 1; + err_args.args[0] = (rtas_arg_t)__pa(rtas_err_buf); + err_args.args[1] = bufsz; + err_args.args[2] = 0; + + save_args = rtas.args; + rtas.args = err_args; + + enter_rtas(__pa(&rtas.args)); + + err_args = rtas.args; + rtas.args = save_args; + + /* Log the error in the unlikely case that there was one. */ + if (unlikely(err_args.args[2] == 0)) { + if (altbuf) { + buf = altbuf; + } else { + buf = rtas_err_buf; + if (mem_init_done) + buf = kmalloc(RTAS_ERROR_LOG_MAX, GFP_ATOMIC); + } + if (buf) + memcpy(buf, rtas_err_buf, RTAS_ERROR_LOG_MAX); + } + + return buf; +} + +#define get_errorlog_buffer() kmalloc(RTAS_ERROR_LOG_MAX, GFP_KERNEL) + +#else /* CONFIG_RTAS_ERROR_LOGGING */ +#define __fetch_rtas_last_error(x) NULL +#define get_errorlog_buffer() NULL +#endif + +int rtas_call(int token, int nargs, int nret, int *outputs, ...) +{ + va_list list; + int i; + unsigned long s; + struct rtas_args *rtas_args; + char *buff_copy = NULL; + int ret; + + if (token == RTAS_UNKNOWN_SERVICE) + return -1; + + /* Gotta do something different here, use global lock for now... */ + spin_lock_irqsave(&rtas.lock, s); + rtas_args = &rtas.args; + + rtas_args->token = token; + rtas_args->nargs = nargs; + rtas_args->nret = nret; + rtas_args->rets = (rtas_arg_t *)&(rtas_args->args[nargs]); + va_start(list, outputs); + for (i = 0; i < nargs; ++i) + rtas_args->args[i] = va_arg(list, rtas_arg_t); + va_end(list); + + for (i = 0; i < nret; ++i) + rtas_args->rets[i] = 0; + + enter_rtas(__pa(rtas_args)); + + /* A -1 return code indicates that the last command couldn't + be completed due to a hardware error. */ + if (rtas_args->rets[0] == -1) + buff_copy = __fetch_rtas_last_error(NULL); + + if (nret > 1 && outputs != NULL) + for (i = 0; i < nret-1; ++i) + outputs[i] = rtas_args->rets[i+1]; + ret = (nret > 0)? rtas_args->rets[0]: 0; + + /* Gotta do something different here, use global lock for now... */ + spin_unlock_irqrestore(&rtas.lock, s); + + if (buff_copy) { + log_error(buff_copy, ERR_TYPE_RTAS_LOG, 0); + if (mem_init_done) + kfree(buff_copy); + } + return ret; +} + +/* Given an RTAS status code of 990n compute the hinted delay of 10^n + * (last digit) milliseconds. For now we bound at n=5 (100 sec). + */ +unsigned int rtas_extended_busy_delay_time(int status) +{ + int order = status - 9900; + unsigned long ms; + + if (order < 0) + order = 0; /* RTC depends on this for -2 clock busy */ + else if (order > 5) + order = 5; /* bound */ + + /* Use microseconds for reasonable accuracy */ + for (ms = 1; order > 0; order--) + ms *= 10; + + return ms; +} + +int rtas_error_rc(int rtas_rc) +{ + int rc; + + switch (rtas_rc) { + case -1: /* Hardware Error */ + rc = -EIO; + break; + case -3: /* Bad indicator/domain/etc */ + rc = -EINVAL; + break; + case -9000: /* Isolation error */ + rc = -EFAULT; + break; + case -9001: /* Outstanding TCE/PTE */ + rc = -EEXIST; + break; + case -9002: /* No usable slot */ + rc = -ENODEV; + break; + default: + printk(KERN_ERR "%s: unexpected RTAS error %d\n", + __FUNCTION__, rtas_rc); + rc = -ERANGE; + break; + } + return rc; +} + +int rtas_get_power_level(int powerdomain, int *level) +{ + int token = rtas_token("get-power-level"); + int rc; + + if (token == RTAS_UNKNOWN_SERVICE) + return -ENOENT; + + while ((rc = rtas_call(token, 1, 2, level, powerdomain)) == RTAS_BUSY) + udelay(1); + + if (rc < 0) + return rtas_error_rc(rc); + return rc; +} + +int rtas_set_power_level(int powerdomain, int level, int *setlevel) +{ + int token = rtas_token("set-power-level"); + unsigned int wait_time; + int rc; + + if (token == RTAS_UNKNOWN_SERVICE) + return -ENOENT; + + while (1) { + rc = rtas_call(token, 2, 2, setlevel, powerdomain, level); + if (rc == RTAS_BUSY) + udelay(1); + else if (rtas_is_extended_busy(rc)) { + wait_time = rtas_extended_busy_delay_time(rc); + udelay(wait_time * 1000); + } else + break; + } + + if (rc < 0) + return rtas_error_rc(rc); + return rc; +} + +int rtas_get_sensor(int sensor, int index, int *state) +{ + int token = rtas_token("get-sensor-state"); + unsigned int wait_time; + int rc; + + if (token == RTAS_UNKNOWN_SERVICE) + return -ENOENT; + + while (1) { + rc = rtas_call(token, 2, 2, state, sensor, index); + if (rc == RTAS_BUSY) + udelay(1); + else if (rtas_is_extended_busy(rc)) { + wait_time = rtas_extended_busy_delay_time(rc); + udelay(wait_time * 1000); + } else + break; + } + + if (rc < 0) + return rtas_error_rc(rc); + return rc; +} + +int rtas_set_indicator(int indicator, int index, int new_value) +{ + int token = rtas_token("set-indicator"); + unsigned int wait_time; + int rc; + + if (token == RTAS_UNKNOWN_SERVICE) + return -ENOENT; + + while (1) { + rc = rtas_call(token, 3, 1, NULL, indicator, index, new_value); + if (rc == RTAS_BUSY) + udelay(1); + else if (rtas_is_extended_busy(rc)) { + wait_time = rtas_extended_busy_delay_time(rc); + udelay(wait_time * 1000); + } + else + break; + } + + if (rc < 0) + return rtas_error_rc(rc); + return rc; +} + +void rtas_restart(char *cmd) +{ + printk("RTAS system-reboot returned %d\n", + rtas_call(rtas_token("system-reboot"), 0, 1, NULL)); + for (;;); +} + +void rtas_power_off(void) +{ + /* allow power on only with power button press */ + printk("RTAS power-off returned %d\n", + rtas_call(rtas_token("power-off"), 2, 1, NULL, -1, -1)); + for (;;); +} + +void rtas_halt(void) +{ + rtas_power_off(); +} + +/* Must be in the RMO region, so we place it here */ +static char rtas_os_term_buf[2048]; + +void rtas_os_term(char *str) +{ + int status; + + if (RTAS_UNKNOWN_SERVICE == rtas_token("ibm,os-term")) + return; + + snprintf(rtas_os_term_buf, 2048, "OS panic: %s", str); + + do { + status = rtas_call(rtas_token("ibm,os-term"), 1, 1, NULL, + __pa(rtas_os_term_buf)); + + if (status == RTAS_BUSY) + udelay(1); + else if (status != 0) + printk(KERN_EMERG "ibm,os-term call failed %d\n", + status); + } while (status == RTAS_BUSY); +} + + +asmlinkage int ppc_rtas(struct rtas_args __user *uargs) +{ + struct rtas_args args; + unsigned long flags; + char *buff_copy, *errbuf = NULL; + int nargs; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (copy_from_user(&args, uargs, 3 * sizeof(u32)) != 0) + return -EFAULT; + + nargs = args.nargs; + if (nargs > ARRAY_SIZE(args.args) + || args.nret > ARRAY_SIZE(args.args) + || nargs + args.nret > ARRAY_SIZE(args.args)) + return -EINVAL; + + /* Copy in args. */ + if (copy_from_user(args.args, uargs->args, + nargs * sizeof(rtas_arg_t)) != 0) + return -EFAULT; + + buff_copy = get_errorlog_buffer(); + + spin_lock_irqsave(&rtas.lock, flags); + + rtas.args = args; + enter_rtas(__pa(&rtas.args)); + args = rtas.args; + + args.rets = &args.args[nargs]; + + /* A -1 return code indicates that the last command couldn't + be completed due to a hardware error. */ + if (args.rets[0] == -1) + errbuf = __fetch_rtas_last_error(buff_copy); + + spin_unlock_irqrestore(&rtas.lock, flags); + + if (buff_copy) { + if (errbuf) + log_error(errbuf, ERR_TYPE_RTAS_LOG, 0); + kfree(buff_copy); + } + + /* Copy out args. */ + if (copy_to_user(uargs->args + nargs, + args.args + nargs, + args.nret * sizeof(rtas_arg_t)) != 0) + return -EFAULT; + + return 0; +} + +#ifdef CONFIG_SMP +/* This version can't take the spinlock, because it never returns */ + +struct rtas_args rtas_stop_self_args = { + /* The token is initialized for real in setup_system() */ + .token = RTAS_UNKNOWN_SERVICE, + .nargs = 0, + .nret = 1, + .rets = &rtas_stop_self_args.args[0], +}; + +void rtas_stop_self(void) +{ + struct rtas_args *rtas_args = &rtas_stop_self_args; + + local_irq_disable(); + + BUG_ON(rtas_args->token == RTAS_UNKNOWN_SERVICE); + + printk("cpu %u (hwid %u) Ready to die...\n", + smp_processor_id(), hard_smp_processor_id()); + enter_rtas(__pa(rtas_args)); + + panic("Alas, I survived.\n"); +} +#endif + +/* + * Call early during boot, before mem init or bootmem, to retreive the RTAS + * informations from the device-tree and allocate the RMO buffer for userland + * accesses. + */ +void __init rtas_initialize(void) +{ + unsigned long rtas_region = RTAS_INSTANTIATE_MAX; + + /* Get RTAS dev node and fill up our "rtas" structure with infos + * about it. + */ + rtas.dev = of_find_node_by_name(NULL, "rtas"); + if (rtas.dev) { + u32 *basep, *entryp; + u32 *sizep; + + basep = (u32 *)get_property(rtas.dev, "linux,rtas-base", NULL); + sizep = (u32 *)get_property(rtas.dev, "rtas-size", NULL); + if (basep != NULL && sizep != NULL) { + rtas.base = *basep; + rtas.size = *sizep; + entryp = (u32 *)get_property(rtas.dev, "linux,rtas-entry", NULL); + if (entryp == NULL) /* Ugh */ + rtas.entry = rtas.base; + else + rtas.entry = *entryp; + } else + rtas.dev = NULL; + } + if (!rtas.dev) + return; + + /* If RTAS was found, allocate the RMO buffer for it and look for + * the stop-self token if any + */ +#ifdef CONFIG_PPC64 + if (systemcfg->platform == 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); + +#ifdef CONFIG_HOTPLUG_CPU + rtas_stop_self_args.token = rtas_token("stop-self"); +#endif /* CONFIG_HOTPLUG_CPU */ +#ifdef CONFIG_RTAS_ERROR_LOGGING + rtas_last_error_token = rtas_token("rtas-last-error"); +#endif +} + + +EXPORT_SYMBOL(rtas_token); +EXPORT_SYMBOL(rtas_call); +EXPORT_SYMBOL(rtas_data_buf); +EXPORT_SYMBOL(rtas_data_buf_lock); +EXPORT_SYMBOL(rtas_extended_busy_delay_time); +EXPORT_SYMBOL(rtas_get_sensor); +EXPORT_SYMBOL(rtas_get_power_level); +EXPORT_SYMBOL(rtas_set_power_level); +EXPORT_SYMBOL(rtas_set_indicator); diff --git a/arch/powerpc/kernel/semaphore.c b/arch/powerpc/kernel/semaphore.c new file mode 100644 index 000000000000..2f8c3c951394 --- /dev/null +++ b/arch/powerpc/kernel/semaphore.c @@ -0,0 +1,135 @@ +/* + * PowerPC-specific semaphore code. + * + * Copyright (C) 1999 Cort Dougan <cort@cs.nmt.edu> + * + * 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. + * + * April 2001 - Reworked by Paul Mackerras <paulus@samba.org> + * to eliminate the SMP races in the old version between the updates + * of `count' and `waking'. Now we use negative `count' values to + * indicate that some process(es) are waiting for the semaphore. + */ + +#include <linux/sched.h> +#include <linux/init.h> +#include <linux/module.h> + +#include <asm/atomic.h> +#include <asm/semaphore.h> +#include <asm/errno.h> + +/* + * Atomically update sem->count. + * This does the equivalent of the following: + * + * old_count = sem->count; + * tmp = MAX(old_count, 0) + incr; + * sem->count = tmp; + * return old_count; + */ +static inline int __sem_update_count(struct semaphore *sem, int incr) +{ + int old_count, tmp; + + __asm__ __volatile__("\n" +"1: lwarx %0,0,%3\n" +" srawi %1,%0,31\n" +" andc %1,%0,%1\n" +" add %1,%1,%4\n" + PPC405_ERR77(0,%3) +" stwcx. %1,0,%3\n" +" bne 1b" + : "=&r" (old_count), "=&r" (tmp), "=m" (sem->count) + : "r" (&sem->count), "r" (incr), "m" (sem->count) + : "cc"); + + return old_count; +} + +void __up(struct semaphore *sem) +{ + /* + * Note that we incremented count in up() before we came here, + * but that was ineffective since the result was <= 0, and + * any negative value of count is equivalent to 0. + * This ends up setting count to 1, unless count is now > 0 + * (i.e. because some other cpu has called up() in the meantime), + * in which case we just increment count. + */ + __sem_update_count(sem, 1); + wake_up(&sem->wait); +} +EXPORT_SYMBOL(__up); + +/* + * Note that when we come in to __down or __down_interruptible, + * we have already decremented count, but that decrement was + * ineffective since the result was < 0, and any negative value + * of count is equivalent to 0. + * Thus it is only when we decrement count from some value > 0 + * that we have actually got the semaphore. + */ +void __sched __down(struct semaphore *sem) +{ + struct task_struct *tsk = current; + DECLARE_WAITQUEUE(wait, tsk); + + __set_task_state(tsk, TASK_UNINTERRUPTIBLE); + add_wait_queue_exclusive(&sem->wait, &wait); + + /* + * Try to get the semaphore. If the count is > 0, then we've + * got the semaphore; we decrement count and exit the loop. + * If the count is 0 or negative, we set it to -1, indicating + * that we are asleep, and then sleep. + */ + while (__sem_update_count(sem, -1) <= 0) { + schedule(); + set_task_state(tsk, TASK_UNINTERRUPTIBLE); + } + remove_wait_queue(&sem->wait, &wait); + __set_task_state(tsk, TASK_RUNNING); + + /* + * If there are any more sleepers, wake one of them up so + * that it can either get the semaphore, or set count to -1 + * indicating that there are still processes sleeping. + */ + wake_up(&sem->wait); +} +EXPORT_SYMBOL(__down); + +int __sched __down_interruptible(struct semaphore * sem) +{ + int retval = 0; + struct task_struct *tsk = current; + DECLARE_WAITQUEUE(wait, tsk); + + __set_task_state(tsk, TASK_INTERRUPTIBLE); + add_wait_queue_exclusive(&sem->wait, &wait); + + while (__sem_update_count(sem, -1) <= 0) { + if (signal_pending(current)) { + /* + * A signal is pending - give up trying. + * Set sem->count to 0 if it is negative, + * since we are no longer sleeping. + */ + __sem_update_count(sem, 0); + retval = -EINTR; + break; + } + schedule(); + set_task_state(tsk, TASK_INTERRUPTIBLE); + } + remove_wait_queue(&sem->wait, &wait); + __set_task_state(tsk, TASK_RUNNING); + + wake_up(&sem->wait); + return retval; +} +EXPORT_SYMBOL(__down_interruptible); diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c new file mode 100644 index 000000000000..1292460fcde2 --- /dev/null +++ b/arch/powerpc/kernel/setup-common.c @@ -0,0 +1,410 @@ +/* + * Common boot and setup code for both 32-bit and 64-bit. + * Extracted from arch/powerpc/kernel/setup_64.c. + * + * Copyright (C) 2001 PPC64 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/module.h> +#include <linux/string.h> +#include <linux/sched.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/reboot.h> +#include <linux/delay.h> +#include <linux/initrd.h> +#include <linux/ide.h> +#include <linux/seq_file.h> +#include <linux/ioport.h> +#include <linux/console.h> +#include <linux/utsname.h> +#include <linux/tty.h> +#include <linux/root_dev.h> +#include <linux/notifier.h> +#include <linux/cpu.h> +#include <linux/unistd.h> +#include <linux/serial.h> +#include <linux/serial_8250.h> +#include <asm/io.h> +#include <asm/prom.h> +#include <asm/processor.h> +#include <asm/pgtable.h> +#include <asm/smp.h> +#include <asm/elf.h> +#include <asm/machdep.h> +#include <asm/time.h> +#include <asm/cputable.h> +#include <asm/sections.h> +#include <asm/btext.h> +#include <asm/nvram.h> +#include <asm/setup.h> +#include <asm/system.h> +#include <asm/rtas.h> +#include <asm/iommu.h> +#include <asm/serial.h> +#include <asm/cache.h> +#include <asm/page.h> +#include <asm/mmu.h> +#include <asm/lmb.h> + +#undef DEBUG + +#ifdef DEBUG +#define DBG(fmt...) udbg_printf(fmt) +#else +#define DBG(fmt...) +#endif + +/* + * This still seems to be needed... -- paulus + */ +struct screen_info screen_info = { + .orig_x = 0, + .orig_y = 25, + .orig_video_cols = 80, + .orig_video_lines = 25, + .orig_video_isVGA = 1, + .orig_video_points = 16 +}; + +#ifdef __DO_IRQ_CANON +/* XXX should go elsewhere eventually */ +int ppc_do_canonicalize_irqs; +EXPORT_SYMBOL(ppc_do_canonicalize_irqs); +#endif + +/* also used by kexec */ +void machine_shutdown(void) +{ + if (ppc_md.nvram_sync) + ppc_md.nvram_sync(); +} + +void machine_restart(char *cmd) +{ + machine_shutdown(); + ppc_md.restart(cmd); +#ifdef CONFIG_SMP + smp_send_stop(); +#endif + printk(KERN_EMERG "System Halted, OK to turn off power\n"); + local_irq_disable(); + while (1) ; +} + +void machine_power_off(void) +{ + machine_shutdown(); + ppc_md.power_off(); +#ifdef CONFIG_SMP + smp_send_stop(); +#endif + printk(KERN_EMERG "System Halted, OK to turn off power\n"); + local_irq_disable(); + while (1) ; +} +/* Used by the G5 thermal driver */ +EXPORT_SYMBOL_GPL(machine_power_off); + +void (*pm_power_off)(void) = machine_power_off; +EXPORT_SYMBOL_GPL(pm_power_off); + +void machine_halt(void) +{ + machine_shutdown(); + ppc_md.halt(); +#ifdef CONFIG_SMP + smp_send_stop(); +#endif + printk(KERN_EMERG "System Halted, OK to turn off power\n"); + local_irq_disable(); + while (1) ; +} + + +#ifdef CONFIG_TAU +extern u32 cpu_temp(unsigned long cpu); +extern u32 cpu_temp_both(unsigned long cpu); +#endif /* CONFIG_TAU */ + +#ifdef CONFIG_SMP +DEFINE_PER_CPU(unsigned int, pvr); +#endif + +static int show_cpuinfo(struct seq_file *m, void *v) +{ + unsigned long cpu_id = (unsigned long)v - 1; + unsigned int pvr; + unsigned short maj; + unsigned short min; + + if (cpu_id == NR_CPUS) { +#if defined(CONFIG_SMP) && defined(CONFIG_PPC32) + unsigned long bogosum = 0; + int i; + for (i = 0; i < NR_CPUS; ++i) + if (cpu_online(i)) + bogosum += loops_per_jiffy; + seq_printf(m, "total bogomips\t: %lu.%02lu\n", + bogosum/(500000/HZ), bogosum/(5000/HZ) % 100); +#endif /* CONFIG_SMP && CONFIG_PPC32 */ + seq_printf(m, "timebase\t: %lu\n", ppc_tb_freq); + + if (ppc_md.show_cpuinfo != NULL) + ppc_md.show_cpuinfo(m); + + return 0; + } + + /* We only show online cpus: disable preempt (overzealous, I + * knew) to prevent cpu going down. */ + preempt_disable(); + if (!cpu_online(cpu_id)) { + preempt_enable(); + return 0; + } + +#ifdef CONFIG_SMP +#ifdef CONFIG_PPC64 /* XXX for now */ + pvr = per_cpu(pvr, cpu_id); +#else + pvr = cpu_data[cpu_id].pvr; +#endif +#else + pvr = mfspr(SPRN_PVR); +#endif + maj = (pvr >> 8) & 0xFF; + min = pvr & 0xFF; + + seq_printf(m, "processor\t: %lu\n", cpu_id); + seq_printf(m, "cpu\t\t: "); + + if (cur_cpu_spec->pvr_mask) + seq_printf(m, "%s", cur_cpu_spec->cpu_name); + else + seq_printf(m, "unknown (%08x)", pvr); + +#ifdef CONFIG_ALTIVEC + if (cpu_has_feature(CPU_FTR_ALTIVEC)) + seq_printf(m, ", altivec supported"); +#endif /* CONFIG_ALTIVEC */ + + seq_printf(m, "\n"); + +#ifdef CONFIG_TAU + if (cur_cpu_spec->cpu_features & CPU_FTR_TAU) { +#ifdef CONFIG_TAU_AVERAGE + /* more straightforward, but potentially misleading */ + seq_printf(m, "temperature \t: %u C (uncalibrated)\n", + cpu_temp(i)); +#else + /* show the actual temp sensor range */ + u32 temp; + temp = cpu_temp_both(i); + seq_printf(m, "temperature \t: %u-%u C (uncalibrated)\n", + temp & 0xff, temp >> 16); +#endif + } +#endif /* CONFIG_TAU */ + + /* + * Assume here that all clock rates are the same in a + * smp system. -- Cort + */ + if (ppc_proc_freq) + seq_printf(m, "clock\t\t: %lu.%06luMHz\n", + ppc_proc_freq / 1000000, ppc_proc_freq % 1000000); + + if (ppc_md.show_percpuinfo != NULL) + ppc_md.show_percpuinfo(m, cpu_id); + + /* If we are a Freescale core do a simple check so + * we dont have to keep adding cases in the future */ + if (PVR_VER(pvr) & 0x8000) { + maj = PVR_MAJ(pvr); + min = PVR_MIN(pvr); + } else { + switch (PVR_VER(pvr)) { + case 0x0020: /* 403 family */ + maj = PVR_MAJ(pvr) + 1; + min = PVR_MIN(pvr); + break; + case 0x1008: /* 740P/750P ?? */ + maj = ((pvr >> 8) & 0xFF) - 1; + min = pvr & 0xFF; + break; + default: + maj = (pvr >> 8) & 0xFF; + min = pvr & 0xFF; + break; + } + } + + seq_printf(m, "revision\t: %hd.%hd (pvr %04x %04x)\n", + maj, min, PVR_VER(pvr), PVR_REV(pvr)); + +#ifdef CONFIG_PPC32 + seq_printf(m, "bogomips\t: %lu.%02lu\n", + loops_per_jiffy / (500000/HZ), + (loops_per_jiffy / (5000/HZ)) % 100); +#endif + +#ifdef CONFIG_SMP + seq_printf(m, "\n"); +#endif + + preempt_enable(); + return 0; +} + +static void *c_start(struct seq_file *m, loff_t *pos) +{ + unsigned long i = *pos; + + return i <= NR_CPUS ? (void *)(i + 1) : NULL; +} + +static void *c_next(struct seq_file *m, void *v, loff_t *pos) +{ + ++*pos; + return c_start(m, pos); +} + +static void c_stop(struct seq_file *m, void *v) +{ +} + +struct seq_operations cpuinfo_op = { + .start =c_start, + .next = c_next, + .stop = c_stop, + .show = show_cpuinfo, +}; + +#ifdef CONFIG_PPC_MULTIPLATFORM +static int __init set_preferred_console(void) +{ + struct device_node *prom_stdout = NULL; + char *name; + u32 *spd; + int offset = 0; + + DBG(" -> set_preferred_console()\n"); + + /* The user has requested a console so this is already set up. */ + if (strstr(saved_command_line, "console=")) { + DBG(" console was specified !\n"); + return -EBUSY; + } + + if (!of_chosen) { + DBG(" of_chosen is NULL !\n"); + return -ENODEV; + } + /* We are getting a weird phandle from OF ... */ + /* ... So use the full path instead */ + name = (char *)get_property(of_chosen, "linux,stdout-path", NULL); + if (name == NULL) { + DBG(" no linux,stdout-path !\n"); + return -ENODEV; + } + prom_stdout = of_find_node_by_path(name); + if (!prom_stdout) { + DBG(" can't find stdout package %s !\n", name); + return -ENODEV; + } + DBG("stdout is %s\n", prom_stdout->full_name); + + name = (char *)get_property(prom_stdout, "name", NULL); + if (!name) { + DBG(" stdout package has no name !\n"); + goto not_found; + } + spd = (u32 *)get_property(prom_stdout, "current-speed", NULL); + + if (0) + ; +#ifdef CONFIG_SERIAL_8250_CONSOLE + else if (strcmp(name, "serial") == 0) { + int i; + u32 *reg = (u32 *)get_property(prom_stdout, "reg", &i); + if (i > 8) { + switch (reg[1]) { + case 0x3f8: + offset = 0; + break; + case 0x2f8: + offset = 1; + break; + case 0x898: + offset = 2; + break; + case 0x890: + offset = 3; + break; + default: + /* We dont recognise the serial port */ + goto not_found; + } + } + } +#endif /* CONFIG_SERIAL_8250_CONSOLE */ +#ifdef CONFIG_PPC_PSERIES + else if (strcmp(name, "vty") == 0) { + u32 *reg = (u32 *)get_property(prom_stdout, "reg", NULL); + char *compat = (char *)get_property(prom_stdout, "compatible", NULL); + + if (reg && compat && (strcmp(compat, "hvterm-protocol") == 0)) { + /* Host Virtual Serial Interface */ + switch (reg[0]) { + case 0x30000000: + offset = 0; + break; + case 0x30000001: + offset = 1; + break; + default: + goto not_found; + } + of_node_put(prom_stdout); + DBG("Found hvsi console at offset %d\n", offset); + return add_preferred_console("hvsi", offset, NULL); + } else { + /* pSeries LPAR virtual console */ + of_node_put(prom_stdout); + DBG("Found hvc console\n"); + return add_preferred_console("hvc", 0, NULL); + } + } +#endif /* CONFIG_PPC_PSERIES */ +#ifdef CONFIG_SERIAL_PMACZILOG_CONSOLE + else if (strcmp(name, "ch-a") == 0) + offset = 0; + else if (strcmp(name, "ch-b") == 0) + offset = 1; +#endif /* CONFIG_SERIAL_PMACZILOG_CONSOLE */ + else + goto not_found; + of_node_put(prom_stdout); + + DBG("Found serial console at ttyS%d\n", offset); + + if (spd) { + static char __initdata opt[16]; + sprintf(opt, "%d", *spd); + return add_preferred_console("ttyS", offset, opt); + } else + return add_preferred_console("ttyS", offset, NULL); + + not_found: + DBG("No preferred console found !\n"); + of_node_put(prom_stdout); + return -ENODEV; +} +console_initcall(set_preferred_console); +#endif /* CONFIG_PPC_MULTIPLATFORM */ diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c new file mode 100644 index 000000000000..9680ae99b084 --- /dev/null +++ b/arch/powerpc/kernel/setup_32.c @@ -0,0 +1,372 @@ +/* + * Common prep/pmac/chrp boot and setup code. + */ + +#include <linux/config.h> +#include <linux/module.h> +#include <linux/string.h> +#include <linux/sched.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/reboot.h> +#include <linux/delay.h> +#include <linux/initrd.h> +#include <linux/ide.h> +#include <linux/tty.h> +#include <linux/bootmem.h> +#include <linux/seq_file.h> +#include <linux/root_dev.h> +#include <linux/cpu.h> +#include <linux/console.h> + +#include <asm/residual.h> +#include <asm/io.h> +#include <asm/prom.h> +#include <asm/processor.h> +#include <asm/pgtable.h> +#include <asm/setup.h> +#include <asm/amigappc.h> +#include <asm/smp.h> +#include <asm/elf.h> +#include <asm/cputable.h> +#include <asm/bootx.h> +#include <asm/btext.h> +#include <asm/machdep.h> +#include <asm/uaccess.h> +#include <asm/system.h> +#include <asm/pmac_feature.h> +#include <asm/sections.h> +#include <asm/nvram.h> +#include <asm/xmon.h> +#include <asm/time.h> + +#define DBG(fmt...) + +#if defined CONFIG_KGDB +#include <asm/kgdb.h> +#endif + +extern void platform_init(void); +extern void bootx_init(unsigned long r4, unsigned long phys); + +extern void ppc6xx_idle(void); +extern void power4_idle(void); + +boot_infos_t *boot_infos; +struct ide_machdep_calls ppc_ide_md; + +/* XXX should go elsewhere */ +int __irq_offset_value; +EXPORT_SYMBOL(__irq_offset_value); + +int boot_cpuid; +EXPORT_SYMBOL_GPL(boot_cpuid); +int boot_cpuid_phys; + +unsigned long ISA_DMA_THRESHOLD; +unsigned int DMA_MODE_READ; +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); + +dev_t boot_dev; +#endif /* CONFIG_PPC_MULTIPLATFORM */ + +#ifdef CONFIG_MAGIC_SYSRQ +unsigned long SYSRQ_KEY = 0x54; +#endif /* CONFIG_MAGIC_SYSRQ */ + +#ifdef CONFIG_VGA_CONSOLE +unsigned long vgacon_remap_base; +#endif + +struct machdep_calls ppc_md; +EXPORT_SYMBOL(ppc_md); + +/* + * These are used in binfmt_elf.c to put aux entries on the stack + * for each elf executable being started. + */ +int dcache_bsize; +int icache_bsize; +int ucache_bsize; + +/* + * We're called here very early in the boot. We determine the machine + * type and call the appropriate low-level setup functions. + * -- Cort <cort@fsmlabs.com> + * + * Note that the kernel may be running at an address which is different + * from the address that it was linked at, so we must use RELOC/PTRRELOC + * to access static data (including strings). -- paulus + */ +unsigned long __init early_init(unsigned long dt_ptr) +{ + unsigned long offset = reloc_offset(); + + /* First zero the BSS -- use memset_io, some platforms don't have + * caches on yet */ + memset_io(PTRRELOC(&__bss_start), 0, _end - __bss_start); + + /* + * Identify the CPU type and fix up code sections + * that depend on which cpu we have. + */ + identify_cpu(offset, 0); + do_cpu_ftr_fixups(offset); + + return KERNELBASE + offset; +} + +#ifdef CONFIG_PPC_MULTIPLATFORM +/* + * The PPC_MULTIPLATFORM version of platform_init... + */ +void __init platform_init(void) +{ + /* if we didn't get any bootinfo telling us what we are... */ + if (_machine == 0) { + /* prep boot loader tells us if we're prep or not */ + if ( *(unsigned long *)(KERNELBASE) == (0xdeadc0de) ) + _machine = _MACH_prep; + } + +#ifdef CONFIG_PPC_PREP + /* not much more to do here, if prep */ + if (_machine == _MACH_prep) { + prep_init(); + return; + } +#endif + +#ifdef CONFIG_ADB + if (strstr(cmd_line, "adb_sync")) { + extern int __adb_probe_sync; + __adb_probe_sync = 1; + } +#endif /* CONFIG_ADB */ + + switch (_machine) { +#ifdef CONFIG_PPC_PMAC + case _MACH_Pmac: + pmac_init(); + break; +#endif +#ifdef CONFIG_PPC_CHRP + case _MACH_chrp: + chrp_init(); + break; +#endif + } +} +#endif + +/* + * Find out what kind of machine we're on and save any data we need + * from the early boot process (devtree is copied on pmac by prom_init()). + * This is called very early on the boot process, after a minimal + * MMU environment has been set up but before MMU_init is called. + */ +void __init machine_init(unsigned long dt_ptr, unsigned long phys) +{ + early_init_devtree(__va(dt_ptr)); + +#ifdef CONFIG_CMDLINE + strlcpy(cmd_line, CONFIG_CMDLINE, sizeof(cmd_line)); +#endif /* CONFIG_CMDLINE */ + + platform_init(); + +#ifdef CONFIG_6xx + ppc_md.power_save = ppc6xx_idle; +#endif + + if (ppc_md.progress) + ppc_md.progress("id mach(): done", 0x200); +} + +#ifdef CONFIG_BOOKE_WDT +/* Checks wdt=x and wdt_period=xx command-line option */ +int __init early_parse_wdt(char *p) +{ + if (p && strncmp(p, "0", 1) != 0) + booke_wdt_enabled = 1; + + return 0; +} +early_param("wdt", early_parse_wdt); + +int __init early_parse_wdt_period (char *p) +{ + if (p) + booke_wdt_period = simple_strtoul(p, NULL, 0); + + return 0; +} +early_param("wdt_period", early_parse_wdt_period); +#endif /* CONFIG_BOOKE_WDT */ + +/* Checks "l2cr=xxxx" command-line option */ +int __init ppc_setup_l2cr(char *str) +{ + if (cpu_has_feature(CPU_FTR_L2CR)) { + unsigned long val = simple_strtoul(str, NULL, 0); + printk(KERN_INFO "l2cr set to %lx\n", val); + _set_L2CR(0); /* force invalidate by disable cache */ + _set_L2CR(val); /* and enable it */ + } + return 1; +} +__setup("l2cr=", ppc_setup_l2cr); + +#ifdef CONFIG_GENERIC_NVRAM + +/* Generic nvram hooks used by drivers/char/gen_nvram.c */ +unsigned char nvram_read_byte(int addr) +{ + if (ppc_md.nvram_read_val) + return ppc_md.nvram_read_val(addr); + return 0xff; +} +EXPORT_SYMBOL(nvram_read_byte); + +void nvram_write_byte(unsigned char val, int addr) +{ + if (ppc_md.nvram_write_val) + ppc_md.nvram_write_val(addr, val); +} +EXPORT_SYMBOL(nvram_write_byte); + +void nvram_sync(void) +{ + if (ppc_md.nvram_sync) + ppc_md.nvram_sync(); +} +EXPORT_SYMBOL(nvram_sync); + +#endif /* CONFIG_NVRAM */ + +static struct cpu cpu_devices[NR_CPUS]; + +int __init ppc_init(void) +{ + int i; + + /* clear the progress line */ + if ( ppc_md.progress ) ppc_md.progress(" ", 0xffff); + + /* register CPU devices */ + for (i = 0; i < NR_CPUS; i++) + if (cpu_possible(i)) + register_cpu(&cpu_devices[i], i, NULL); + + /* call platform init */ + if (ppc_md.init != NULL) { + ppc_md.init(); + } + return 0; +} + +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 */ + loops_per_jiffy = 500000000 / HZ; + + unflatten_device_tree(); + finish_device_tree(); + +#ifdef CONFIG_BOOTX_TEXT + init_boot_display(); +#endif + +#ifdef CONFIG_PPC_PMAC + /* This could be called "early setup arch", it must be done + * now because xmon need it + */ + if (_machine == _MACH_Pmac) + 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); + +#if defined(CONFIG_KGDB) + if (ppc_md.kgdb_map_scc) + ppc_md.kgdb_map_scc(); + set_debug_traps(); + if (strstr(cmd_line, "gdb")) { + if (ppc_md.progress) + ppc_md.progress("setup_arch: kgdb breakpoint", 0x4000); + printk("kgdb breakpoint activated\n"); + breakpoint(); + } +#endif + + /* + * Set cache line size based on type of cpu as a default. + * Systems with OF can look in the properties on the cpu node(s) + * for a possibly more accurate value. + */ + if (cpu_has_feature(CPU_FTR_SPLIT_ID_CACHE)) { + dcache_bsize = cur_cpu_spec->dcache_bsize; + icache_bsize = cur_cpu_spec->icache_bsize; + ucache_bsize = 0; + } else + ucache_bsize = dcache_bsize = icache_bsize + = cur_cpu_spec->dcache_bsize; + + /* reboot on panic */ + panic_timeout = 180; + + 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; + + /* Save unparsed command line copy for /proc/cmdline */ + strlcpy(saved_command_line, cmd_line, COMMAND_LINE_SIZE); + *cmdline_p = cmd_line; + + parse_early_param(); + + /* set up the bootmem stuff with available memory */ + do_init_bootmem(); + if ( ppc_md.progress ) ppc_md.progress("setup_arch: bootmem", 0x3eab); + +#ifdef CONFIG_PPC_OCP + /* Initialize OCP device list */ + ocp_early_init(); + if ( ppc_md.progress ) ppc_md.progress("ocp: exit", 0x3eab); +#endif + +#ifdef CONFIG_DUMMY_CONSOLE + conswitchp = &dummy_con; +#endif + + ppc_md.setup_arch(); + if ( ppc_md.progress ) ppc_md.progress("arch: exit", 0x3eab); + + paging_init(); + + /* this is for modules since _machine can be a define -- Cort */ + ppc_md.ppc_machine = _machine; +} diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c new file mode 100644 index 000000000000..40c48100bf1b --- /dev/null +++ b/arch/powerpc/kernel/setup_64.c @@ -0,0 +1,1028 @@ +/* + * + * Common boot and setup code. + * + * Copyright (C) 2001 PPC64 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. + */ + +#undef DEBUG + +#include <linux/config.h> +#include <linux/module.h> +#include <linux/string.h> +#include <linux/sched.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/reboot.h> +#include <linux/delay.h> +#include <linux/initrd.h> +#include <linux/ide.h> +#include <linux/seq_file.h> +#include <linux/ioport.h> +#include <linux/console.h> +#include <linux/utsname.h> +#include <linux/tty.h> +#include <linux/root_dev.h> +#include <linux/notifier.h> +#include <linux/cpu.h> +#include <linux/unistd.h> +#include <linux/serial.h> +#include <linux/serial_8250.h> +#include <asm/io.h> +#include <asm/prom.h> +#include <asm/processor.h> +#include <asm/pgtable.h> +#include <asm/smp.h> +#include <asm/elf.h> +#include <asm/machdep.h> +#include <asm/paca.h> +#include <asm/ppcdebug.h> +#include <asm/time.h> +#include <asm/cputable.h> +#include <asm/sections.h> +#include <asm/btext.h> +#include <asm/nvram.h> +#include <asm/setup.h> +#include <asm/system.h> +#include <asm/rtas.h> +#include <asm/iommu.h> +#include <asm/serial.h> +#include <asm/cache.h> +#include <asm/page.h> +#include <asm/mmu.h> +#include <asm/lmb.h> +#include <asm/iSeries/ItLpNaca.h> +#include <asm/firmware.h> +#include <asm/systemcfg.h> +#include <asm/xmon.h> + +#ifdef DEBUG +#define DBG(fmt...) udbg_printf(fmt) +#else +#define DBG(fmt...) +#endif + +/* + * Here are some early debugging facilities. You can enable one + * but your kernel will not boot on anything else if you do so + */ + +/* This one is for use on LPAR machines that support an HVC console + * on vterm 0 + */ +extern void udbg_init_debug_lpar(void); +/* This one is for use on Apple G5 machines + */ +extern void udbg_init_pmac_realmode(void); +/* That's RTAS panel debug */ +extern void call_rtas_display_status_delay(unsigned char c); +/* Here's maple real mode debug */ +extern void udbg_init_maple_realmode(void); + +#define EARLY_DEBUG_INIT() do {} while(0) + +#if 0 +#define EARLY_DEBUG_INIT() udbg_init_debug_lpar() +#define EARLY_DEBUG_INIT() udbg_init_maple_realmode() +#define EARLY_DEBUG_INIT() udbg_init_pmac_realmode() +#define EARLY_DEBUG_INIT() \ + 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); + +extern void smp_release_cpus(void); + +int have_of = 1; +int boot_cpuid = 0; +int boot_cpuid_phys = 0; +dev_t boot_dev; +u64 ppc64_pft_size; + +struct ppc64_caches ppc64_caches; +EXPORT_SYMBOL_GPL(ppc64_caches); + +/* + * These are used in binfmt_elf.c to put aux entries on the stack + * for each elf executable being started. + */ +int dcache_bsize; +int icache_bsize; +int ucache_bsize; + +/* The main machine-dep calls structure + */ +struct machdep_calls ppc_md; +EXPORT_SYMBOL(ppc_md); + +#ifdef CONFIG_MAGIC_SYSRQ +unsigned long SYSRQ_KEY; +#endif /* CONFIG_MAGIC_SYSRQ */ + + +static int ppc64_panic_event(struct notifier_block *, unsigned long, void *); +static struct notifier_block ppc64_panic_block = { + .notifier_call = ppc64_panic_event, + .priority = INT_MIN /* may not return; must be done last */ +}; + +#ifdef CONFIG_SMP + +static int smt_enabled_cmdline; + +/* Look for ibm,smt-enabled OF option */ +static void check_smt_enabled(void) +{ + struct device_node *dn; + char *smt_option; + + /* Allow the command line to overrule the OF option */ + if (smt_enabled_cmdline) + return; + + dn = of_find_node_by_path("/options"); + + if (dn) { + smt_option = (char *)get_property(dn, "ibm,smt-enabled", NULL); + + if (smt_option) { + if (!strcmp(smt_option, "on")) + smt_enabled_at_boot = 1; + else if (!strcmp(smt_option, "off")) + smt_enabled_at_boot = 0; + } + } +} + +/* Look for smt-enabled= cmdline option */ +static int __init early_smt_enabled(char *p) +{ + smt_enabled_cmdline = 1; + + if (!p) + return 0; + + if (!strcmp(p, "on") || !strcmp(p, "1")) + smt_enabled_at_boot = 1; + else if (!strcmp(p, "off") || !strcmp(p, "0")) + smt_enabled_at_boot = 0; + + return 0; +} +early_param("smt-enabled", early_smt_enabled); + +/** + * setup_cpu_maps - initialize the following cpu maps: + * cpu_possible_map + * cpu_present_map + * cpu_sibling_map + * + * Having the possible map set up early allows us to restrict allocations + * of things like irqstacks to num_possible_cpus() rather than NR_CPUS. + * + * We do not initialize the online map here; cpus set their own bits in + * cpu_online_map as they come up. + * + * This function is valid only for Open Firmware systems. finish_device_tree + * must be called before using this. + * + * While we're here, we may as well set the "physical" cpu ids in the paca. + */ +static void __init setup_cpu_maps(void) +{ + struct device_node *dn = NULL; + int cpu = 0; + int swap_cpuid = 0; + + check_smt_enabled(); + + while ((dn = of_find_node_by_type(dn, "cpu")) && cpu < NR_CPUS) { + u32 *intserv; + int j, len = sizeof(u32), nthreads; + + intserv = (u32 *)get_property(dn, "ibm,ppc-interrupt-server#s", + &len); + if (!intserv) + intserv = (u32 *)get_property(dn, "reg", NULL); + + nthreads = len / sizeof(u32); + + for (j = 0; j < nthreads && cpu < NR_CPUS; j++) { + cpu_set(cpu, cpu_present_map); + set_hard_smp_processor_id(cpu, intserv[j]); + + if (intserv[j] == boot_cpuid_phys) + swap_cpuid = cpu; + cpu_set(cpu, cpu_possible_map); + cpu++; + } + } + + /* Swap CPU id 0 with boot_cpuid_phys, so we can always assume that + * boot cpu is logical 0. + */ + if (boot_cpuid_phys != get_hard_smp_processor_id(0)) { + u32 tmp; + tmp = get_hard_smp_processor_id(0); + set_hard_smp_processor_id(0, boot_cpuid_phys); + set_hard_smp_processor_id(swap_cpuid, tmp); + } + + /* + * 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"))) { + int num_addr_cell, num_size_cell, maxcpus; + unsigned int *ireg; + + num_addr_cell = prom_n_addr_cells(dn); + num_size_cell = prom_n_size_cells(dn); + + ireg = (unsigned int *) + get_property(dn, "ibm,lrdr-capacity", NULL); + + if (!ireg) + goto out; + + maxcpus = ireg[num_addr_cell + num_size_cell]; + + /* Double maxcpus for processors which have SMT capability */ + if (cpu_has_feature(CPU_FTR_SMT)) + maxcpus *= 2; + + if (maxcpus > NR_CPUS) { + printk(KERN_WARNING + "Partition configured for %d cpus, " + "operating system maximum is %d.\n", + maxcpus, NR_CPUS); + maxcpus = NR_CPUS; + } else + printk(KERN_INFO "Partition configured for %d cpus.\n", + maxcpus); + + for (cpu = 0; cpu < maxcpus; cpu++) + cpu_set(cpu, cpu_possible_map); + out: + of_node_put(dn); + } + + /* + * Do the sibling map; assume only two threads per processor. + */ + for_each_cpu(cpu) { + cpu_set(cpu, cpu_sibling_map[cpu]); + if (cpu_has_feature(CPU_FTR_SMT)) + cpu_set(cpu ^ 0x1, cpu_sibling_map[cpu]); + } + + systemcfg->processorCount = num_present_cpus(); +} +#endif /* CONFIG_SMP */ + +extern struct machdep_calls pSeries_md; +extern struct machdep_calls pmac_md; +extern struct machdep_calls maple_md; +extern struct machdep_calls bpa_md; +extern struct machdep_calls iseries_md; + +/* Ultimately, stuff them in an elf section like initcalls... */ +static struct machdep_calls __initdata *machines[] = { +#ifdef CONFIG_PPC_PSERIES + &pSeries_md, +#endif /* CONFIG_PPC_PSERIES */ +#ifdef CONFIG_PPC_PMAC + &pmac_md, +#endif /* CONFIG_PPC_PMAC */ +#ifdef CONFIG_PPC_MAPLE + &maple_md, +#endif /* CONFIG_PPC_MAPLE */ +#ifdef CONFIG_PPC_BPA + &bpa_md, +#endif +#ifdef CONFIG_PPC_ISERIES + &iseries_md, +#endif + NULL +}; + +/* + * Early initialization entry point. This is called by head.S + * with MMU translation disabled. We rely on the "feature" of + * the CPU that ignores the top 2 bits of the address in real + * mode so we can access kernel globals normally provided we + * only toy with things in the RMO region. From here, we do + * some early parsing of the device-tree to setup out LMB + * data structures, and allocate & initialize the hash table + * and segment tables so we can start running with translation + * enabled. + * + * It is this function which will call the probe() callback of + * the various platform types and copy the matching one to the + * global ppc_md structure. Your platform can eventually do + * some very early initializations from the probe() routine, but + * this is not recommended, be very careful as, for example, the + * device-tree is not accessible via normal means at this point. + */ + +void __init early_setup(unsigned long dt_ptr) +{ + struct paca_struct *lpaca = get_paca(); + static struct machdep_calls **mach; + + /* + * Enable early debugging if any specified (see top of + * this file) + */ + EARLY_DEBUG_INIT(); + + DBG(" -> early_setup()\n"); + + /* + * Fill the default DBG level (do we want to keep + * that old mecanism around forever ?) + */ + ppcdbg_initialize(); + + /* + * Do early initializations using the flattened device + * tree, like retreiving the physical memory map or + * calculating/retreiving the hash table size + */ + early_init_devtree(__va(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); + + for (mach = machines; *mach; mach++) { + if ((*mach)->probe(systemcfg->platform)) + break; + } + /* What can we do if we didn't find ? */ + if (*mach == NULL) { + DBG("No suitable machine found !\n"); + for (;;); + } + ppc_md = **mach; + + DBG("Found, Initializing memory management...\n"); + + /* + * Initialize stab / SLB management + */ + if (!firmware_has_feature(FW_FEATURE_ISERIES)) + stab_initialize(lpaca->stab_real); + + /* + * Initialize the MMU Hash table and create the linear mapping + * of memory + */ + htab_initialize(); + + DBG(" <- early_setup()\n"); +} + + +/* + * 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 + */ +static void __init initialize_cache_info(void) +{ + struct device_node *np; + unsigned long num_cpus = 0; + + DBG(" -> initialize_cache_info()\n"); + + for (np = NULL; (np = of_find_node_by_type(np, "cpu"));) { + num_cpus += 1; + + /* We're assuming *all* of the CPUs have the same + * d-cache and i-cache sizes... -Peter + */ + + if ( num_cpus == 1 ) { + u32 *sizep, *lsizep; + u32 size, lsize; + const char *dc, *ic; + + /* Then read cache informations */ + if (systemcfg->platform == PLATFORM_POWERMAC) { + dc = "d-cache-block-size"; + ic = "i-cache-block-size"; + } else { + dc = "d-cache-line-size"; + ic = "i-cache-line-size"; + } + + size = 0; + lsize = cur_cpu_spec->dcache_bsize; + sizep = (u32 *)get_property(np, "d-cache-size", NULL); + if (sizep != NULL) + size = *sizep; + lsizep = (u32 *) get_property(np, dc, NULL); + if (lsizep != NULL) + lsize = *lsizep; + if (sizep == 0 || lsizep == 0) + 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.log_dline_size = __ilog2(lsize); + ppc64_caches.dlines_per_page = PAGE_SIZE / lsize; + + size = 0; + lsize = cur_cpu_spec->icache_bsize; + sizep = (u32 *)get_property(np, "i-cache-size", NULL); + if (sizep != NULL) + size = *sizep; + lsizep = (u32 *)get_property(np, ic, NULL); + if (lsizep != NULL) + lsize = *lsizep; + if (sizep == 0 || lsizep == 0) + 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.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"); +} + +static void __init check_for_initrd(void) +{ +#ifdef CONFIG_BLK_DEV_INITRD + u64 *prop; + + DBG(" -> check_for_initrd()\n"); + + if (of_chosen) { + prop = (u64 *)get_property(of_chosen, + "linux,initrd-start", NULL); + if (prop != NULL) { + initrd_start = (unsigned long)__va(*prop); + prop = (u64 *)get_property(of_chosen, + "linux,initrd-end", NULL); + if (prop != NULL) { + initrd_end = (unsigned long)__va(*prop); + initrd_below_start_ok = 1; + } else + initrd_start = 0; + } + } + + /* If we were passed an initrd, set the ROOT_DEV properly if the values + * look sensible. If not, clear initrd reference. + */ + if (initrd_start >= KERNELBASE && initrd_end >= KERNELBASE && + initrd_end > initrd_start) + ROOT_DEV = Root_RAM0; + else + initrd_start = initrd_end = 0; + + if (initrd_start) + printk("Found initrd at 0x%lx:0x%lx\n", initrd_start, initrd_end); + + DBG(" <- check_for_initrd()\n"); +#endif /* CONFIG_BLK_DEV_INITRD */ +} + +/* + * Do some initial setup of the system. The parameters are those which + * were passed in from the bootloader. + */ +void __init setup_system(void) +{ + DBG(" -> setup_system()\n"); + + /* + * Unflatten the device-tree passed by prom_init or kexec + */ + unflatten_device_tree(); + + /* + * Fill the ppc64_caches & systemcfg structures with informations + * retreived from the device-tree. Need to be called before + * finish_device_tree() since the later requires some of the + * informations filled up here to properly parse the interrupt + * tree. + * It also sets up the cache line sizes which allows to call + * routines like flush_icache_range (used by the hash init + * later on). + */ + initialize_cache_info(); + +#ifdef CONFIG_PPC_RTAS + /* + * Initialize RTAS if available + */ + rtas_initialize(); +#endif /* CONFIG_PPC_RTAS */ + + /* + * Check if we have an initrd provided via the device-tree + */ + check_for_initrd(); + + /* + * Do some platform specific early initializations, that includes + * setting up the hash table pointers. It also sets up some interrupt-mapping + * related options that will be used by finish_device_tree() + */ + ppc_md.init_early(); + + /* + * "Finish" the device-tree, that is do the actual parsing of + * some of the properties like the interrupt map + */ + finish_device_tree(); + +#ifdef CONFIG_BOOTX_TEXT + init_boot_display(); +#endif + + /* + * Initialize xmon + */ +#ifdef CONFIG_XMON_DEFAULT + xmon_init(1); +#endif + /* + * Register early console + */ + register_early_udbg_console(); + + /* Save unparsed command line copy for /proc/cmdline */ + strlcpy(saved_command_line, cmd_line, COMMAND_LINE_SIZE); + + parse_early_param(); + +#ifdef CONFIG_SMP + /* + * iSeries has already initialized the cpu maps at this point. + */ + setup_cpu_maps(); + + /* Release secondary cpus out of their spinloops at 0x60 now that + * we can map physical -> logical CPU ids + */ + smp_release_cpus(); +#endif + + printk("Starting Linux PPC64 %s\n", system_utsname.version); + + printk("-----------------------------------------------------\n"); + printk("ppc64_pft_size = 0x%lx\n", ppc64_pft_size); + printk("ppc64_debug_switch = 0x%lx\n", ppc64_debug_switch); + 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_caches.dcache_line_size = 0x%x\n", + ppc64_caches.dline_size); + printk("ppc64_caches.icache_line_size = 0x%x\n", + ppc64_caches.iline_size); + printk("htab_address = 0x%p\n", htab_address); + printk("htab_hash_mask = 0x%lx\n", htab_hash_mask); + printk("-----------------------------------------------------\n"); + + mm_init_ppc64(); + + DBG(" <- setup_system()\n"); +} + +static int ppc64_panic_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + ppc_md.panic((char *)ptr); /* May not return */ + return NOTIFY_DONE; +} + +#ifdef CONFIG_PPC_ISERIES +/* + * On iSeries we just parse the mem=X option from the command line. + * On pSeries it's a bit more complicated, see prom_init_mem() + */ +static int __init early_parsemem(char *p) +{ + if (!p) + return 0; + + memory_limit = ALIGN(memparse(p, &p), PAGE_SIZE); + + return 0; +} +early_param("mem", early_parsemem); +#endif /* CONFIG_PPC_ISERIES */ + +#ifdef CONFIG_IRQSTACKS +static void __init irqstack_early_init(void) +{ + unsigned int i; + + /* + * interrupt stacks must be under 256MB, we cannot afford to take + * SLB misses on them. + */ + for_each_cpu(i) { + softirq_ctx[i] = (struct thread_info *)__va(lmb_alloc_base(THREAD_SIZE, + THREAD_SIZE, 0x10000000)); + hardirq_ctx[i] = (struct thread_info *)__va(lmb_alloc_base(THREAD_SIZE, + THREAD_SIZE, 0x10000000)); + } +} +#else +#define irqstack_early_init() +#endif + +/* + * Stack space used when we detect a bad kernel stack pointer, and + * early in SMP boots before relocation is enabled. + */ +static void __init emergency_stack_init(void) +{ + unsigned long limit; + unsigned int i; + + /* + * Emergency stacks must be under 256MB, we cannot afford to take + * SLB misses on them. The ABI also requires them to be 128-byte + * aligned. + * + * Since we use these as temporary stacks during secondary CPU + * bringup, we need to get at them in real mode. This means they + * must also be within the RMO region. + */ + limit = min(0x10000000UL, lmb.rmo_size); + + for_each_cpu(i) + paca[i].emergency_sp = __va(lmb_alloc_base(PAGE_SIZE, 128, + limit)) + PAGE_SIZE; +} + +/* + * 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. + */ +void __init setup_arch(char **cmdline_p) +{ + extern void do_init_bootmem(void); + + ppc64_boot_msg(0x12, "Setup Arch"); + + *cmdline_p = cmd_line; + + /* + * Set cache line size based on type of cpu as a default. + * Systems with OF can look in the properties on the cpu node(s) + * for a possibly more accurate value. + */ + dcache_bsize = ppc64_caches.dline_size; + icache_bsize = ppc64_caches.iline_size; + + /* reboot on panic */ + panic_timeout = 180; + + if (ppc_md.panic) + notifier_chain_register(&panic_notifier_list, &ppc64_panic_block); + + init_mm.start_code = PAGE_OFFSET; + init_mm.end_code = (unsigned long) _etext; + init_mm.end_data = (unsigned long) _edata; + init_mm.brk = klimit; + + irqstack_early_init(); + emergency_stack_init(); + + stabs_alloc(); + + /* set up the bootmem stuff with available memory */ + do_init_bootmem(); + sparse_init(); + + /* initialize the syscall map in systemcfg */ + setup_syscall_map(); + +#ifdef CONFIG_DUMMY_CONSOLE + conswitchp = &dummy_con; +#endif + + ppc_md.setup_arch(); + + /* Use the default idle loop if the platform hasn't provided one. */ + if (NULL == ppc_md.idle_loop) { + ppc_md.idle_loop = default_idle; + printk(KERN_INFO "Using default idle loop\n"); + } + + paging_init(); + ppc64_boot_msg(0x15, "Setup Done"); +} + + +/* ToDo: do something useful if ppc_md is not yet setup. */ +#define PPC64_LINUX_FUNCTION 0x0f000000 +#define PPC64_IPL_MESSAGE 0xc0000000 +#define PPC64_TERM_MESSAGE 0xb0000000 + +static void ppc64_do_msg(unsigned int src, const char *msg) +{ + if (ppc_md.progress) { + char buf[128]; + + sprintf(buf, "%08X\n", src); + ppc_md.progress(buf, 0); + snprintf(buf, 128, "%s", msg); + ppc_md.progress(buf, 0); + } +} + +/* Print a boot progress message. */ +void ppc64_boot_msg(unsigned int src, const char *msg) +{ + ppc64_do_msg(PPC64_LINUX_FUNCTION|PPC64_IPL_MESSAGE|src, msg); + printk("[boot]%04x %s\n", src, msg); +} + +/* Print a termination message (print only -- does not stop the kernel) */ +void ppc64_terminate_msg(unsigned int src, const char *msg) +{ + ppc64_do_msg(PPC64_LINUX_FUNCTION|PPC64_TERM_MESSAGE|src, msg); + printk("[terminate]%04x %s\n", src, msg); +} + +#ifndef CONFIG_PPC_ISERIES +/* + * This function can be used by platforms to "find" legacy serial ports. + * It works for "serial" nodes under an "isa" node, and will try to + * respect the "ibm,aix-loc" property if any. It works with up to 8 + * ports. + */ + +#define MAX_LEGACY_SERIAL_PORTS 8 +static struct plat_serial8250_port serial_ports[MAX_LEGACY_SERIAL_PORTS+1]; +static unsigned int old_serial_count; + +void __init generic_find_legacy_serial_ports(u64 *physport, + unsigned int *default_speed) +{ + struct device_node *np; + u32 *sizeprop; + + struct isa_reg_property { + u32 space; + u32 address; + u32 size; + }; + struct pci_reg_property { + struct pci_address addr; + u32 size_hi; + u32 size_lo; + }; + + DBG(" -> generic_find_legacy_serial_port()\n"); + + *physport = 0; + if (default_speed) + *default_speed = 0; + + np = of_find_node_by_path("/"); + if (!np) + return; + + /* First fill our array */ + for (np = NULL; (np = of_find_node_by_type(np, "serial"));) { + struct device_node *isa, *pci; + struct isa_reg_property *reg; + unsigned long phys_size, addr_size, io_base; + u32 *rangesp; + u32 *interrupts, *clk, *spd; + char *typep; + int index, rlen, rentsize; + + /* Ok, first check if it's under an "isa" parent */ + isa = of_get_parent(np); + if (!isa || strcmp(isa->name, "isa")) { + DBG("%s: no isa parent found\n", np->full_name); + continue; + } + + /* Now look for an "ibm,aix-loc" property that gives us ordering + * if any... + */ + typep = (char *)get_property(np, "ibm,aix-loc", NULL); + + /* Get the ISA port number */ + reg = (struct isa_reg_property *)get_property(np, "reg", NULL); + if (reg == NULL) + goto next_port; + /* We assume the interrupt number isn't translated ... */ + interrupts = (u32 *)get_property(np, "interrupts", NULL); + /* get clock freq. if present */ + clk = (u32 *)get_property(np, "clock-frequency", NULL); + /* get default speed if present */ + spd = (u32 *)get_property(np, "current-speed", NULL); + /* Default to locate at end of array */ + index = old_serial_count; /* end of the array by default */ + + /* If we have a location index, then use it */ + if (typep && *typep == 'S') { + index = simple_strtol(typep+1, NULL, 0) - 1; + /* if index is out of range, use end of array instead */ + if (index >= MAX_LEGACY_SERIAL_PORTS) + index = old_serial_count; + /* if our index is still out of range, that mean that + * array is full, we could scan for a free slot but that + * make little sense to bother, just skip the port + */ + if (index >= MAX_LEGACY_SERIAL_PORTS) + goto next_port; + if (index >= old_serial_count) + old_serial_count = index + 1; + /* Check if there is a port who already claimed our slot */ + if (serial_ports[index].iobase != 0) { + /* if we still have some room, move it, else override */ + if (old_serial_count < MAX_LEGACY_SERIAL_PORTS) { + DBG("Moved legacy port %d -> %d\n", index, + old_serial_count); + serial_ports[old_serial_count++] = + serial_ports[index]; + } else { + DBG("Replacing legacy port %d\n", index); + } + } + } + if (index >= MAX_LEGACY_SERIAL_PORTS) + goto next_port; + if (index >= old_serial_count) + old_serial_count = index + 1; + + /* Now fill the entry */ + memset(&serial_ports[index], 0, sizeof(struct plat_serial8250_port)); + serial_ports[index].uartclk = clk ? *clk : BASE_BAUD * 16; + serial_ports[index].iobase = reg->address; + serial_ports[index].irq = interrupts ? interrupts[0] : 0; + serial_ports[index].flags = ASYNC_BOOT_AUTOCONF; + + DBG("Added legacy port, index: %d, port: %x, irq: %d, clk: %d\n", + index, + serial_ports[index].iobase, + serial_ports[index].irq, + serial_ports[index].uartclk); + + /* Get phys address of IO reg for port 1 */ + if (index != 0) + goto next_port; + + pci = of_get_parent(isa); + if (!pci) { + DBG("%s: no pci parent found\n", np->full_name); + goto next_port; + } + + rangesp = (u32 *)get_property(pci, "ranges", &rlen); + if (rangesp == NULL) { + of_node_put(pci); + goto next_port; + } + rlen /= 4; + + /* we need the #size-cells of the PCI bridge node itself */ + phys_size = 1; + sizeprop = (u32 *)get_property(pci, "#size-cells", NULL); + if (sizeprop != NULL) + phys_size = *sizeprop; + /* we need the parent #addr-cells */ + addr_size = prom_n_addr_cells(pci); + rentsize = 3 + addr_size + phys_size; + io_base = 0; + for (;rlen >= rentsize; rlen -= rentsize,rangesp += rentsize) { + if (((rangesp[0] >> 24) & 0x3) != 1) + continue; /* not IO space */ + io_base = rangesp[3]; + if (addr_size == 2) + io_base = (io_base << 32) | rangesp[4]; + } + if (io_base != 0) { + *physport = io_base + reg->address; + if (default_speed && spd) + *default_speed = *spd; + } + of_node_put(pci); + next_port: + of_node_put(isa); + } + + DBG(" <- generic_find_legacy_serial_port()\n"); +} + +static struct platform_device serial_device = { + .name = "serial8250", + .id = PLAT8250_DEV_PLATFORM, + .dev = { + .platform_data = serial_ports, + }, +}; + +static int __init serial_dev_init(void) +{ + return platform_device_register(&serial_device); +} +arch_initcall(serial_dev_init); + +#endif /* CONFIG_PPC_ISERIES */ + +int check_legacy_ioport(unsigned long base_port) +{ + if (ppc_md.check_legacy_ioport == NULL) + return 0; + return ppc_md.check_legacy_ioport(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) + ppc_md.cpu_die(); +} diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c new file mode 100644 index 000000000000..444c3e81884c --- /dev/null +++ b/arch/powerpc/kernel/signal_32.c @@ -0,0 +1,1269 @@ +/* + * Signal handling for 32bit PPC and 32bit tasks on 64bit PPC + * + * PowerPC version + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) + * Copyright (C) 2001 IBM + * Copyright (C) 1997,1998 Jakub Jelinek (jj@sunsite.mff.cuni.cz) + * Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu) + * + * Derived from "arch/i386/kernel/signal.c" + * Copyright (C) 1991, 1992 Linus Torvalds + * 1997-11-28 Modified for POSIX.1b signals by Richard Henderson + * + * 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/sched.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/smp_lock.h> +#include <linux/kernel.h> +#include <linux/signal.h> +#include <linux/errno.h> +#include <linux/elf.h> +#ifdef CONFIG_PPC64 +#include <linux/syscalls.h> +#include <linux/compat.h> +#include <linux/ptrace.h> +#else +#include <linux/wait.h> +#include <linux/ptrace.h> +#include <linux/unistd.h> +#include <linux/stddef.h> +#include <linux/tty.h> +#include <linux/binfmts.h> +#include <linux/suspend.h> +#endif + +#include <asm/uaccess.h> +#include <asm/cacheflush.h> +#ifdef CONFIG_PPC64 +#include <asm/ppc32.h> +#include <asm/ppcdebug.h> +#include <asm/unistd.h> +#include <asm/vdso.h> +#else +#include <asm/ucontext.h> +#include <asm/pgtable.h> +#endif + +#undef DEBUG_SIG + +#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) + +#ifdef CONFIG_PPC64 +#define do_signal do_signal32 +#define sys_sigsuspend compat_sys_sigsuspend +#define sys_rt_sigsuspend compat_sys_rt_sigsuspend +#define sys_rt_sigreturn compat_sys_rt_sigreturn +#define sys_sigaction compat_sys_sigaction +#define sys_swapcontext compat_sys_swapcontext +#define sys_sigreturn compat_sys_sigreturn + +#define old_sigaction old_sigaction32 +#define sigcontext sigcontext32 +#define mcontext mcontext32 +#define ucontext ucontext32 + +/* + * Returning 0 means we return to userspace via + * ret_from_except and thus restore all user + * registers from *regs. This is what we need + * to do when a signal has been delivered. + */ +#define sigreturn_exit(regs) return 0 + +#define GP_REGS_SIZE min(sizeof(elf_gregset_t32), sizeof(struct pt_regs32)) +#undef __SIGNAL_FRAMESIZE +#define __SIGNAL_FRAMESIZE __SIGNAL_FRAMESIZE32 +#undef ELF_NVRREG +#define ELF_NVRREG ELF_NVRREG32 + +/* + * Functions for flipping sigsets (thanks to brain dead generic + * implementation that makes things simple for little endian only) + */ +static inline int put_sigset_t(compat_sigset_t __user *uset, sigset_t *set) +{ + compat_sigset_t cset; + + switch (_NSIG_WORDS) { + case 4: cset.sig[5] = set->sig[3] & 0xffffffffull; + cset.sig[7] = set->sig[3] >> 32; + case 3: cset.sig[4] = set->sig[2] & 0xffffffffull; + cset.sig[5] = set->sig[2] >> 32; + case 2: cset.sig[2] = set->sig[1] & 0xffffffffull; + cset.sig[3] = set->sig[1] >> 32; + case 1: cset.sig[0] = set->sig[0] & 0xffffffffull; + cset.sig[1] = set->sig[0] >> 32; + } + return copy_to_user(uset, &cset, sizeof(*uset)); +} + +static inline int get_sigset_t(sigset_t *set, + const compat_sigset_t __user *uset) +{ + compat_sigset_t s32; + + if (copy_from_user(&s32, uset, sizeof(*uset))) + return -EFAULT; + + /* + * Swap the 2 words of the 64-bit sigset_t (they are stored + * in the "wrong" endian in 32-bit user storage). + */ + switch (_NSIG_WORDS) { + case 4: set->sig[3] = s32.sig[6] | (((long)s32.sig[7]) << 32); + case 3: set->sig[2] = s32.sig[4] | (((long)s32.sig[5]) << 32); + case 2: set->sig[1] = s32.sig[2] | (((long)s32.sig[3]) << 32); + case 1: set->sig[0] = s32.sig[0] | (((long)s32.sig[1]) << 32); + } + return 0; +} + +static inline int get_old_sigaction(struct k_sigaction *new_ka, + struct old_sigaction __user *act) +{ + compat_old_sigset_t mask; + compat_uptr_t handler, restorer; + + if (get_user(handler, &act->sa_handler) || + __get_user(restorer, &act->sa_restorer) || + __get_user(new_ka->sa.sa_flags, &act->sa_flags) || + __get_user(mask, &act->sa_mask)) + return -EFAULT; + new_ka->sa.sa_handler = compat_ptr(handler); + new_ka->sa.sa_restorer = compat_ptr(restorer); + siginitset(&new_ka->sa.sa_mask, mask); + return 0; +} + +static inline compat_uptr_t to_user_ptr(void *kp) +{ + return (compat_uptr_t)(u64)kp; +} + +#define from_user_ptr(p) compat_ptr(p) + +static inline int save_general_regs(struct pt_regs *regs, + struct mcontext __user *frame) +{ + elf_greg_t64 *gregs = (elf_greg_t64 *)regs; + int i; + + for (i = 0; i <= PT_RESULT; i ++) + if (__put_user((unsigned int)gregs[i], &frame->mc_gregs[i])) + return -EFAULT; + return 0; +} + +static inline int restore_general_regs(struct pt_regs *regs, + struct mcontext __user *sr) +{ + elf_greg_t64 *gregs = (elf_greg_t64 *)regs; + int i; + + for (i = 0; i <= PT_RESULT; i++) { + if ((i == PT_MSR) || (i == PT_SOFTE)) + continue; + if (__get_user(gregs[i], &sr->mc_gregs[i])) + return -EFAULT; + } + return 0; +} + +#else /* CONFIG_PPC64 */ + +extern void sigreturn_exit(struct pt_regs *); + +#define GP_REGS_SIZE min(sizeof(elf_gregset_t), sizeof(struct pt_regs)) + +static inline int put_sigset_t(sigset_t __user *uset, sigset_t *set) +{ + return copy_to_user(uset, set, sizeof(*uset)); +} + +static inline int get_sigset_t(sigset_t *set, const sigset_t __user *uset) +{ + return copy_from_user(set, uset, sizeof(*uset)); +} + +static inline int get_old_sigaction(struct k_sigaction *new_ka, + struct old_sigaction __user *act) +{ + old_sigset_t mask; + + if (!access_ok(VERIFY_READ, act, sizeof(*act)) || + __get_user(new_ka->sa.sa_handler, &act->sa_handler) || + __get_user(new_ka->sa.sa_restorer, &act->sa_restorer)) + return -EFAULT; + __get_user(new_ka->sa.sa_flags, &act->sa_flags); + __get_user(mask, &act->sa_mask); + siginitset(&new_ka->sa.sa_mask, mask); + return 0; +} + +#define to_user_ptr(p) (p) +#define from_user_ptr(p) (p) + +static inline int save_general_regs(struct pt_regs *regs, + struct mcontext __user *frame) +{ + return __copy_to_user(&frame->mc_gregs, regs, GP_REGS_SIZE); +} + +static inline int restore_general_regs(struct pt_regs *regs, + struct mcontext __user *sr) +{ + /* copy up to but not including MSR */ + if (__copy_from_user(regs, &sr->mc_gregs, + PT_MSR * sizeof(elf_greg_t))) + return -EFAULT; + /* copy from orig_r3 (the word after the MSR) up to the end */ + if (__copy_from_user(®s->orig_gpr3, &sr->mc_gregs[PT_ORIG_R3], + GP_REGS_SIZE - PT_ORIG_R3 * sizeof(elf_greg_t))) + return -EFAULT; + return 0; +} + +#endif /* CONFIG_PPC64 */ + +int do_signal(sigset_t *oldset, struct pt_regs *regs); + +/* + * Atomically swap in the new signal mask, and wait for a signal. + */ +long sys_sigsuspend(old_sigset_t mask, int p2, int p3, int p4, int p6, int p7, + struct pt_regs *regs) +{ + sigset_t saveset; + + mask &= _BLOCKABLE; + spin_lock_irq(¤t->sighand->siglock); + saveset = current->blocked; + siginitset(¤t->blocked, mask); + recalc_sigpending(); + spin_unlock_irq(¤t->sighand->siglock); + + regs->result = -EINTR; + regs->gpr[3] = EINTR; + regs->ccr |= 0x10000000; + while (1) { + current->state = TASK_INTERRUPTIBLE; + schedule(); + if (do_signal(&saveset, regs)) + sigreturn_exit(regs); + } +} + +long sys_rt_sigsuspend( +#ifdef CONFIG_PPC64 + compat_sigset_t __user *unewset, +#else + sigset_t __user *unewset, +#endif + size_t sigsetsize, int p3, int p4, + int p6, int p7, struct pt_regs *regs) +{ + sigset_t saveset, newset; + + /* XXX: Don't preclude handling different sized sigset_t's. */ + if (sigsetsize != sizeof(sigset_t)) + return -EINVAL; + + if (get_sigset_t(&newset, unewset)) + return -EFAULT; + sigdelsetmask(&newset, ~_BLOCKABLE); + + spin_lock_irq(¤t->sighand->siglock); + saveset = current->blocked; + current->blocked = newset; + recalc_sigpending(); + spin_unlock_irq(¤t->sighand->siglock); + + regs->result = -EINTR; + regs->gpr[3] = EINTR; + regs->ccr |= 0x10000000; + while (1) { + current->state = TASK_INTERRUPTIBLE; + schedule(); + if (do_signal(&saveset, regs)) + sigreturn_exit(regs); + } +} + +#ifdef CONFIG_PPC32 +long sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss, int r5, + int r6, int r7, int r8, struct pt_regs *regs) +{ + return do_sigaltstack(uss, uoss, regs->gpr[1]); +} +#endif + +long sys_sigaction(int sig, struct old_sigaction __user *act, + struct old_sigaction __user *oact) +{ + struct k_sigaction new_ka, old_ka; + int ret; + +#ifdef CONFIG_PPC64 + if (sig < 0) + sig = -sig; +#endif + + if (act) { + if (get_old_sigaction(&new_ka, act)) + return -EFAULT; + } + + ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); + if (!ret && oact) { + if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) || + __put_user(to_user_ptr(old_ka.sa.sa_handler), + &oact->sa_handler) || + __put_user(to_user_ptr(old_ka.sa.sa_restorer), + &oact->sa_restorer) || + __put_user(old_ka.sa.sa_flags, &oact->sa_flags) || + __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask)) + return -EFAULT; + } + + return ret; +} + +/* + * When we have signals to deliver, we set up on the + * user stack, going down from the original stack pointer: + * a sigregs struct + * a sigcontext struct + * a gap of __SIGNAL_FRAMESIZE bytes + * + * Each of these things must be a multiple of 16 bytes in size. + * + */ +struct sigregs { + struct mcontext mctx; /* all the register values */ + /* + * Programs using the rs6000/xcoff abi can save up to 19 gp + * regs and 18 fp regs below sp before decrementing it. + */ + int abigap[56]; +}; + +/* We use the mc_pad field for the signal return trampoline. */ +#define tramp mc_pad + +/* + * When we have rt signals to deliver, we set up on the + * user stack, going down from the original stack pointer: + * one rt_sigframe struct (siginfo + ucontext + ABI gap) + * a gap of __SIGNAL_FRAMESIZE+16 bytes + * (the +16 is to get the siginfo and ucontext in the same + * positions as in older kernels). + * + * Each of these things must be a multiple of 16 bytes in size. + * + */ +struct rt_sigframe { +#ifdef CONFIG_PPC64 + compat_siginfo_t info; +#else + struct siginfo info; +#endif + struct ucontext uc; + /* + * Programs using the rs6000/xcoff abi can save up to 19 gp + * regs and 18 fp regs below sp before decrementing it. + */ + int abigap[56]; +}; + +/* + * Save the current user registers on the user stack. + * We only save the altivec/spe registers if the process has used + * altivec/spe instructions at some point. + */ +static int save_user_regs(struct pt_regs *regs, struct mcontext __user *frame, + int sigret) +{ +#ifdef CONFIG_PPC32 + CHECK_FULL_REGS(regs); +#endif + /* Make sure floating point registers are stored in regs */ + flush_fp_to_thread(current); + + /* save general and floating-point registers */ + if (save_general_regs(regs, frame) || + __copy_to_user(&frame->mc_fregs, current->thread.fpr, + ELF_NFPREG * sizeof(double))) + return 1; + + current->thread.fpscr.val = 0; /* turn off all fp exceptions */ + +#ifdef CONFIG_ALTIVEC + /* save altivec registers */ + if (current->thread.used_vr) { + flush_altivec_to_thread(current); + if (__copy_to_user(&frame->mc_vregs, current->thread.vr, + ELF_NVRREG * sizeof(vector128))) + return 1; + /* set MSR_VEC in the saved MSR value to indicate that + frame->mc_vregs contains valid data */ + if (__put_user(regs->msr | MSR_VEC, &frame->mc_gregs[PT_MSR])) + return 1; + } + /* else assert((regs->msr & MSR_VEC) == 0) */ + + /* We always copy to/from vrsave, it's 0 if we don't have or don't + * use altivec. Since VSCR only contains 32 bits saved in the least + * significant bits of a vector, we "cheat" and stuff VRSAVE in the + * most significant bits of that same vector. --BenH + */ + if (__put_user(current->thread.vrsave, (u32 __user *)&frame->mc_vregs[32])) + return 1; +#endif /* CONFIG_ALTIVEC */ + +#ifdef CONFIG_SPE + /* save spe registers */ + if (current->thread.used_spe) { + flush_spe_to_thread(current); + if (__copy_to_user(&frame->mc_vregs, current->thread.evr, + ELF_NEVRREG * sizeof(u32))) + return 1; + /* set MSR_SPE in the saved MSR value to indicate that + frame->mc_vregs contains valid data */ + if (__put_user(regs->msr | MSR_SPE, &frame->mc_gregs[PT_MSR])) + return 1; + } + /* else assert((regs->msr & MSR_SPE) == 0) */ + + /* We always copy to/from spefscr */ + if (__put_user(current->thread.spefscr, (u32 __user *)&frame->mc_vregs + ELF_NEVRREG)) + return 1; +#endif /* CONFIG_SPE */ + + if (sigret) { + /* Set up the sigreturn trampoline: li r0,sigret; sc */ + if (__put_user(0x38000000UL + sigret, &frame->tramp[0]) + || __put_user(0x44000002UL, &frame->tramp[1])) + return 1; + flush_icache_range((unsigned long) &frame->tramp[0], + (unsigned long) &frame->tramp[2]); + } + + return 0; +} + +/* + * Restore the current user register values from the user stack, + * (except for MSR). + */ +static long restore_user_regs(struct pt_regs *regs, + struct mcontext __user *sr, int sig) +{ + long err; + unsigned int save_r2 = 0; +#if defined(CONFIG_ALTIVEC) || defined(CONFIG_SPE) + unsigned long msr; +#endif + + /* + * restore general registers but not including MSR or SOFTE. Also + * take care of keeping r2 (TLS) intact if not a signal + */ + if (!sig) + save_r2 = (unsigned int)regs->gpr[2]; + err = restore_general_regs(regs, sr); + if (!sig) + regs->gpr[2] = (unsigned long) save_r2; + if (err) + return 1; + + /* force the process to reload the FP registers from + current->thread when it next does FP instructions */ + regs->msr &= ~(MSR_FP | MSR_FE0 | MSR_FE1); + if (__copy_from_user(current->thread.fpr, &sr->mc_fregs, + sizeof(sr->mc_fregs))) + return 1; + +#ifdef CONFIG_ALTIVEC + /* force the process to reload the altivec registers from + current->thread when it next does altivec instructions */ + regs->msr &= ~MSR_VEC; + if (!__get_user(msr, &sr->mc_gregs[PT_MSR]) && (msr & MSR_VEC) != 0) { + /* restore altivec registers from the stack */ + if (__copy_from_user(current->thread.vr, &sr->mc_vregs, + sizeof(sr->mc_vregs))) + return 1; + } else if (current->thread.used_vr) + memset(current->thread.vr, 0, ELF_NVRREG * sizeof(vector128)); + + /* Always get VRSAVE back */ + if (__get_user(current->thread.vrsave, (u32 __user *)&sr->mc_vregs[32])) + return 1; +#endif /* CONFIG_ALTIVEC */ + +#ifdef CONFIG_SPE + /* force the process to reload the spe registers from + current->thread when it next does spe instructions */ + regs->msr &= ~MSR_SPE; + if (!__get_user(msr, &sr->mc_gregs[PT_MSR]) && (msr & MSR_SPE) != 0) { + /* restore spe registers from the stack */ + if (__copy_from_user(current->thread.evr, &sr->mc_vregs, + ELF_NEVRREG * sizeof(u32))) + return 1; + } else if (current->thread.used_spe) + memset(current->thread.evr, 0, ELF_NEVRREG * sizeof(u32)); + + /* Always get SPEFSCR back */ + if (__get_user(current->thread.spefscr, (u32 __user *)&sr->mc_vregs + ELF_NEVRREG)) + return 1; +#endif /* CONFIG_SPE */ + +#ifndef CONFIG_SMP + preempt_disable(); + if (last_task_used_math == current) + last_task_used_math = NULL; + if (last_task_used_altivec == current) + last_task_used_altivec = NULL; +#ifdef CONFIG_SPE + if (last_task_used_spe == current) + last_task_used_spe = NULL; +#endif + preempt_enable(); +#endif + return 0; +} + +#ifdef CONFIG_PPC64 +long compat_sys_rt_sigaction(int sig, const struct sigaction32 __user *act, + struct sigaction32 __user *oact, size_t sigsetsize) +{ + struct k_sigaction new_ka, old_ka; + int ret; + + /* XXX: Don't preclude handling different sized sigset_t's. */ + if (sigsetsize != sizeof(compat_sigset_t)) + return -EINVAL; + + if (act) { + compat_uptr_t handler; + + ret = get_user(handler, &act->sa_handler); + new_ka.sa.sa_handler = compat_ptr(handler); + ret |= get_sigset_t(&new_ka.sa.sa_mask, &act->sa_mask); + ret |= __get_user(new_ka.sa.sa_flags, &act->sa_flags); + if (ret) + return -EFAULT; + } + + ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); + if (!ret && oact) { + ret = put_user((long)old_ka.sa.sa_handler, &oact->sa_handler); + ret |= put_sigset_t(&oact->sa_mask, &old_ka.sa.sa_mask); + ret |= __put_user(old_ka.sa.sa_flags, &oact->sa_flags); + } + return ret; +} + +/* + * Note: it is necessary to treat how as an unsigned int, with the + * corresponding cast to a signed int to insure that the proper + * conversion (sign extension) between the register representation + * of a signed int (msr in 32-bit mode) and the register representation + * of a signed int (msr in 64-bit mode) is performed. + */ +long compat_sys_rt_sigprocmask(u32 how, compat_sigset_t __user *set, + compat_sigset_t __user *oset, size_t sigsetsize) +{ + sigset_t s; + sigset_t __user *up; + int ret; + mm_segment_t old_fs = get_fs(); + + if (set) { + if (get_sigset_t(&s, set)) + return -EFAULT; + } + + set_fs(KERNEL_DS); + /* This is valid because of the set_fs() */ + up = (sigset_t __user *) &s; + ret = sys_rt_sigprocmask((int)how, set ? up : NULL, oset ? up : NULL, + sigsetsize); + set_fs(old_fs); + if (ret) + return ret; + if (oset) { + if (put_sigset_t(oset, &s)) + return -EFAULT; + } + return 0; +} + +long compat_sys_rt_sigpending(compat_sigset_t __user *set, compat_size_t sigsetsize) +{ + sigset_t s; + int ret; + mm_segment_t old_fs = get_fs(); + + set_fs(KERNEL_DS); + /* The __user pointer cast is valid because of the set_fs() */ + ret = sys_rt_sigpending((sigset_t __user *) &s, sigsetsize); + set_fs(old_fs); + if (!ret) { + if (put_sigset_t(set, &s)) + return -EFAULT; + } + return ret; +} + + +int copy_siginfo_to_user32(struct compat_siginfo __user *d, siginfo_t *s) +{ + int err; + + if (!access_ok (VERIFY_WRITE, d, sizeof(*d))) + return -EFAULT; + + /* If you change siginfo_t structure, please be sure + * this code is fixed accordingly. + * It should never copy any pad contained in the structure + * to avoid security leaks, but must copy the generic + * 3 ints plus the relevant union member. + * This routine must convert siginfo from 64bit to 32bit as well + * at the same time. + */ + err = __put_user(s->si_signo, &d->si_signo); + err |= __put_user(s->si_errno, &d->si_errno); + err |= __put_user((short)s->si_code, &d->si_code); + if (s->si_code < 0) + err |= __copy_to_user(&d->_sifields._pad, &s->_sifields._pad, + SI_PAD_SIZE32); + else switch(s->si_code >> 16) { + case __SI_CHLD >> 16: + err |= __put_user(s->si_pid, &d->si_pid); + err |= __put_user(s->si_uid, &d->si_uid); + err |= __put_user(s->si_utime, &d->si_utime); + err |= __put_user(s->si_stime, &d->si_stime); + err |= __put_user(s->si_status, &d->si_status); + break; + case __SI_FAULT >> 16: + err |= __put_user((unsigned int)(unsigned long)s->si_addr, + &d->si_addr); + break; + case __SI_POLL >> 16: + err |= __put_user(s->si_band, &d->si_band); + err |= __put_user(s->si_fd, &d->si_fd); + break; + case __SI_TIMER >> 16: + err |= __put_user(s->si_tid, &d->si_tid); + err |= __put_user(s->si_overrun, &d->si_overrun); + err |= __put_user(s->si_int, &d->si_int); + break; + case __SI_RT >> 16: /* This is not generated by the kernel as of now. */ + case __SI_MESGQ >> 16: + err |= __put_user(s->si_int, &d->si_int); + /* fallthrough */ + case __SI_KILL >> 16: + default: + err |= __put_user(s->si_pid, &d->si_pid); + err |= __put_user(s->si_uid, &d->si_uid); + break; + } + return err; +} + +#define copy_siginfo_to_user copy_siginfo_to_user32 + +/* + * Note: it is necessary to treat pid and sig as unsigned ints, with the + * corresponding cast to a signed int to insure that the proper conversion + * (sign extension) between the register representation of a signed int + * (msr in 32-bit mode) and the register representation of a signed int + * (msr in 64-bit mode) is performed. + */ +long compat_sys_rt_sigqueueinfo(u32 pid, u32 sig, compat_siginfo_t __user *uinfo) +{ + siginfo_t info; + int ret; + mm_segment_t old_fs = get_fs(); + + if (copy_from_user (&info, uinfo, 3*sizeof(int)) || + copy_from_user (info._sifields._pad, uinfo->_sifields._pad, SI_PAD_SIZE32)) + return -EFAULT; + set_fs (KERNEL_DS); + /* The __user pointer cast is valid becasuse of the set_fs() */ + ret = sys_rt_sigqueueinfo((int)pid, (int)sig, (siginfo_t __user *) &info); + set_fs (old_fs); + return ret; +} +/* + * Start Alternate signal stack support + * + * System Calls + * sigaltatck compat_sys_sigaltstack + */ + +int compat_sys_sigaltstack(u32 __new, u32 __old, int r5, + int r6, int r7, int r8, struct pt_regs *regs) +{ + stack_32_t __user * newstack = (stack_32_t __user *)(long) __new; + stack_32_t __user * oldstack = (stack_32_t __user *)(long) __old; + stack_t uss, uoss; + int ret; + mm_segment_t old_fs; + unsigned long sp; + compat_uptr_t ss_sp; + + /* + * set sp to the user stack on entry to the system call + * the system call router sets R9 to the saved registers + */ + sp = regs->gpr[1]; + + /* Put new stack info in local 64 bit stack struct */ + if (newstack) { + if (get_user(ss_sp, &newstack->ss_sp) || + __get_user(uss.ss_flags, &newstack->ss_flags) || + __get_user(uss.ss_size, &newstack->ss_size)) + return -EFAULT; + uss.ss_sp = compat_ptr(ss_sp); + } + + old_fs = get_fs(); + set_fs(KERNEL_DS); + /* The __user pointer casts are valid because of the set_fs() */ + ret = do_sigaltstack( + newstack ? (stack_t __user *) &uss : NULL, + oldstack ? (stack_t __user *) &uoss : NULL, + sp); + set_fs(old_fs); + /* Copy the stack information to the user output buffer */ + if (!ret && oldstack && + (put_user((long)uoss.ss_sp, &oldstack->ss_sp) || + __put_user(uoss.ss_flags, &oldstack->ss_flags) || + __put_user(uoss.ss_size, &oldstack->ss_size))) + return -EFAULT; + return ret; +} +#endif /* CONFIG_PPC64 */ + + +/* + * Restore the user process's signal mask + */ +#ifdef CONFIG_PPC64 +extern void restore_sigmask(sigset_t *set); +#else /* CONFIG_PPC64 */ +static void restore_sigmask(sigset_t *set) +{ + sigdelsetmask(set, ~_BLOCKABLE); + spin_lock_irq(¤t->sighand->siglock); + current->blocked = *set; + recalc_sigpending(); + spin_unlock_irq(¤t->sighand->siglock); +} +#endif + +/* + * Set up a signal frame for a "real-time" signal handler + * (one which gets siginfo). + */ +static int handle_rt_signal(unsigned long sig, struct k_sigaction *ka, + siginfo_t *info, sigset_t *oldset, + struct pt_regs *regs, unsigned long newsp) +{ + struct rt_sigframe __user *rt_sf; + struct mcontext __user *frame; + unsigned long origsp = newsp; + + /* Set up Signal Frame */ + /* Put a Real Time Context onto stack */ + newsp -= sizeof(*rt_sf); + rt_sf = (struct rt_sigframe __user *)newsp; + + /* create a stack frame for the caller of the handler */ + newsp -= __SIGNAL_FRAMESIZE + 16; + + if (!access_ok(VERIFY_WRITE, (void __user *)newsp, origsp - newsp)) + goto badframe; + + /* Put the siginfo & fill in most of the ucontext */ + if (copy_siginfo_to_user(&rt_sf->info, info) + || __put_user(0, &rt_sf->uc.uc_flags) + || __put_user(0, &rt_sf->uc.uc_link) + || __put_user(current->sas_ss_sp, &rt_sf->uc.uc_stack.ss_sp) + || __put_user(sas_ss_flags(regs->gpr[1]), + &rt_sf->uc.uc_stack.ss_flags) + || __put_user(current->sas_ss_size, &rt_sf->uc.uc_stack.ss_size) + || __put_user(to_user_ptr(&rt_sf->uc.uc_mcontext), + &rt_sf->uc.uc_regs) + || put_sigset_t(&rt_sf->uc.uc_sigmask, oldset)) + goto badframe; + + /* 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 + { + if (save_user_regs(regs, frame, __NR_rt_sigreturn)) + goto badframe; + regs->link = (unsigned long) frame->tramp; + } + if (put_user(regs->gpr[1], (u32 __user *)newsp)) + goto badframe; + regs->gpr[1] = newsp; + regs->gpr[3] = sig; + regs->gpr[4] = (unsigned long) &rt_sf->info; + regs->gpr[5] = (unsigned long) &rt_sf->uc; + regs->gpr[6] = (unsigned long) rt_sf; + regs->nip = (unsigned long) ka->sa.sa_handler; + regs->trap = 0; +#ifdef CONFIG_PPC64 + regs->result = 0; + + if (test_thread_flag(TIF_SINGLESTEP)) + ptrace_notify(SIGTRAP); +#endif + return 1; + +badframe: +#ifdef DEBUG_SIG + printk("badframe in handle_rt_signal, regs=%p frame=%p newsp=%lx\n", + regs, frame, newsp); +#endif + force_sigsegv(sig, current); + return 0; +} + +static int do_setcontext(struct ucontext __user *ucp, struct pt_regs *regs, int sig) +{ + sigset_t set; + struct mcontext __user *mcp; + + if (get_sigset_t(&set, &ucp->uc_sigmask)) + return -EFAULT; +#ifdef CONFIG_PPC64 + { + u32 cmcp; + + if (__get_user(cmcp, &ucp->uc_regs)) + return -EFAULT; + mcp = (struct mcontext __user *)(u64)cmcp; + } +#else + if (__get_user(mcp, &ucp->uc_regs)) + return -EFAULT; +#endif + restore_sigmask(&set); + if (restore_user_regs(regs, mcp, sig)) + return -EFAULT; + + return 0; +} + +long sys_swapcontext(struct ucontext __user *old_ctx, + struct ucontext __user *new_ctx, + int ctx_size, int r6, int r7, int r8, struct pt_regs *regs) +{ + unsigned char tmp; + + /* Context size is for future use. Right now, we only make sure + * we are passed something we understand + */ + if (ctx_size < sizeof(struct ucontext)) + return -EINVAL; + + if (old_ctx != NULL) { + if (!access_ok(VERIFY_WRITE, old_ctx, sizeof(*old_ctx)) + || save_user_regs(regs, &old_ctx->uc_mcontext, 0) + || put_sigset_t(&old_ctx->uc_sigmask, ¤t->blocked) + || __put_user(to_user_ptr(&old_ctx->uc_mcontext), + &old_ctx->uc_regs)) + return -EFAULT; + } + if (new_ctx == NULL) + return 0; + if (!access_ok(VERIFY_READ, new_ctx, sizeof(*new_ctx)) + || __get_user(tmp, (u8 __user *) new_ctx) + || __get_user(tmp, (u8 __user *) (new_ctx + 1) - 1)) + return -EFAULT; + + /* + * If we get a fault copying the context into the kernel's + * image of the user's registers, we can't just return -EFAULT + * because the user's registers will be corrupted. For instance + * the NIP value may have been updated but not some of the + * other registers. Given that we have done the access_ok + * and successfully read the first and last bytes of the region + * above, this should only happen in an out-of-memory situation + * or if another thread unmaps the region containing the context. + * We kill the task with a SIGSEGV in this situation. + */ + if (do_setcontext(new_ctx, regs, 0)) + do_exit(SIGSEGV); + sigreturn_exit(regs); + /* doesn't actually return back to here */ + return 0; +} + +long sys_rt_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, + struct pt_regs *regs) +{ + struct rt_sigframe __user *rt_sf; + + /* Always make any pending restarted system calls return -EINTR */ + current_thread_info()->restart_block.fn = do_no_restart_syscall; + + rt_sf = (struct rt_sigframe __user *) + (regs->gpr[1] + __SIGNAL_FRAMESIZE + 16); + if (!access_ok(VERIFY_READ, rt_sf, sizeof(*rt_sf))) + goto bad; + if (do_setcontext(&rt_sf->uc, regs, 1)) + goto bad; + + /* + * It's not clear whether or why it is desirable to save the + * sigaltstack setting on signal delivery and restore it on + * signal return. But other architectures do this and we have + * always done it up until now so it is probably better not to + * change it. -- paulus + */ +#ifdef CONFIG_PPC64 + /* + * We use the compat_sys_ version that does the 32/64 bits conversion + * and takes userland pointer directly. What about error checking ? + * nobody does any... + */ + compat_sys_sigaltstack((u32)(u64)&rt_sf->uc.uc_stack, 0, 0, 0, 0, 0, regs); + return (int)regs->result; +#else + do_sigaltstack(&rt_sf->uc.uc_stack, NULL, regs->gpr[1]); + sigreturn_exit(regs); /* doesn't return here */ + return 0; +#endif + + bad: + force_sig(SIGSEGV, current); + return 0; +} + +#ifdef CONFIG_PPC32 +int sys_debug_setcontext(struct ucontext __user *ctx, + int ndbg, struct sig_dbg_op __user *dbg, + int r6, int r7, int r8, + struct pt_regs *regs) +{ + struct sig_dbg_op op; + int i; + unsigned long new_msr = regs->msr; +#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE) + unsigned long new_dbcr0 = current->thread.dbcr0; +#endif + + for (i=0; i<ndbg; i++) { + if (__copy_from_user(&op, dbg, sizeof(op))) + return -EFAULT; + switch (op.dbg_type) { + case SIG_DBG_SINGLE_STEPPING: +#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE) + if (op.dbg_value) { + new_msr |= MSR_DE; + new_dbcr0 |= (DBCR0_IDM | DBCR0_IC); + } else { + new_msr &= ~MSR_DE; + new_dbcr0 &= ~(DBCR0_IDM | DBCR0_IC); + } +#else + if (op.dbg_value) + new_msr |= MSR_SE; + else + new_msr &= ~MSR_SE; +#endif + break; + case SIG_DBG_BRANCH_TRACING: +#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE) + return -EINVAL; +#else + if (op.dbg_value) + new_msr |= MSR_BE; + else + new_msr &= ~MSR_BE; +#endif + break; + + default: + return -EINVAL; + } + } + + /* We wait until here to actually install the values in the + registers so if we fail in the above loop, it will not + affect the contents of these registers. After this point, + failure is a problem, anyway, and it's very unlikely unless + the user is really doing something wrong. */ + regs->msr = new_msr; +#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE) + current->thread.dbcr0 = new_dbcr0; +#endif + + /* + * If we get a fault copying the context into the kernel's + * image of the user's registers, we can't just return -EFAULT + * because the user's registers will be corrupted. For instance + * the NIP value may have been updated but not some of the + * other registers. Given that we have done the access_ok + * and successfully read the first and last bytes of the region + * above, this should only happen in an out-of-memory situation + * or if another thread unmaps the region containing the context. + * We kill the task with a SIGSEGV in this situation. + */ + if (do_setcontext(ctx, regs, 1)) { + force_sig(SIGSEGV, current); + goto out; + } + + /* + * It's not clear whether or why it is desirable to save the + * sigaltstack setting on signal delivery and restore it on + * signal return. But other architectures do this and we have + * always done it up until now so it is probably better not to + * change it. -- paulus + */ + do_sigaltstack(&ctx->uc_stack, NULL, regs->gpr[1]); + + sigreturn_exit(regs); + /* doesn't actually return back to here */ + + out: + return 0; +} +#endif + +/* + * OK, we're invoking a handler + */ +static int handle_signal(unsigned long sig, struct k_sigaction *ka, + siginfo_t *info, sigset_t *oldset, struct pt_regs *regs, + unsigned long newsp) +{ + struct sigcontext __user *sc; + struct sigregs __user *frame; + unsigned long origsp = newsp; + + /* Set up Signal Frame */ + newsp -= sizeof(struct sigregs); + frame = (struct sigregs __user *) newsp; + + /* Put a sigcontext on the stack */ + newsp -= sizeof(*sc); + sc = (struct sigcontext __user *) newsp; + + /* create a stack frame for the caller of the handler */ + newsp -= __SIGNAL_FRAMESIZE; + + if (!access_ok(VERIFY_WRITE, (void __user *) newsp, origsp - newsp)) + goto badframe; + +#if _NSIG != 64 +#error "Please adjust handle_signal()" +#endif + if (__put_user(to_user_ptr(ka->sa.sa_handler), &sc->handler) + || __put_user(oldset->sig[0], &sc->oldmask) +#ifdef CONFIG_PPC64 + || __put_user((oldset->sig[0] >> 32), &sc->_unused[3]) +#else + || __put_user(oldset->sig[1], &sc->_unused[3]) +#endif + || __put_user(to_user_ptr(frame), &sc->regs) + || __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 + { + if (save_user_regs(regs, &frame->mctx, __NR_sigreturn)) + goto badframe; + regs->link = (unsigned long) frame->mctx.tramp; + } + + if (put_user(regs->gpr[1], (u32 __user *)newsp)) + goto badframe; + regs->gpr[1] = newsp; + regs->gpr[3] = sig; + regs->gpr[4] = (unsigned long) sc; + regs->nip = (unsigned long) ka->sa.sa_handler; + regs->trap = 0; +#ifdef CONFIG_PPC64 + regs->result = 0; + + if (test_thread_flag(TIF_SINGLESTEP)) + ptrace_notify(SIGTRAP); +#endif + + return 1; + +badframe: +#ifdef DEBUG_SIG + printk("badframe in handle_signal, regs=%p frame=%p newsp=%lx\n", + regs, frame, newsp); +#endif + force_sigsegv(sig, current); + return 0; +} + +/* + * Do a signal return; undo the signal stack. + */ +long sys_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, + struct pt_regs *regs) +{ + struct sigcontext __user *sc; + struct sigcontext sigctx; + struct mcontext __user *sr; + sigset_t set; + + /* Always make any pending restarted system calls return -EINTR */ + current_thread_info()->restart_block.fn = do_no_restart_syscall; + + sc = (struct sigcontext __user *)(regs->gpr[1] + __SIGNAL_FRAMESIZE); + if (copy_from_user(&sigctx, sc, sizeof(sigctx))) + goto badframe; + +#ifdef CONFIG_PPC64 + /* + * Note that PPC32 puts the upper 32 bits of the sigmask in the + * unused part of the signal stackframe + */ + set.sig[0] = sigctx.oldmask + ((long)(sigctx._unused[3]) << 32); +#else + set.sig[0] = sigctx.oldmask; + set.sig[1] = sigctx._unused[3]; +#endif + restore_sigmask(&set); + + sr = (struct mcontext __user *)from_user_ptr(sigctx.regs); + if (!access_ok(VERIFY_READ, sr, sizeof(*sr)) + || restore_user_regs(regs, sr, 1)) + goto badframe; + +#ifdef CONFIG_PPC64 + return (int)regs->result; +#else + sigreturn_exit(regs); /* doesn't return */ + return 0; +#endif + +badframe: + force_sig(SIGSEGV, current); + return 0; +} + +/* + * Note that 'init' is a special process: it doesn't get signals it doesn't + * want to handle. Thus you cannot kill init even with a SIGKILL even by + * mistake. + */ +int do_signal(sigset_t *oldset, struct pt_regs *regs) +{ + siginfo_t info; + struct k_sigaction ka; + unsigned int frame, newsp; + int signr, ret; + +#ifdef CONFIG_PPC32 + if (try_to_freeze()) { + signr = 0; + if (!signal_pending(current)) + goto no_signal; + } +#endif + + if (!oldset) + oldset = ¤t->blocked; + + newsp = frame = 0; + + signr = get_signal_to_deliver(&info, &ka, regs, NULL); +#ifdef CONFIG_PPC32 +no_signal: +#endif + if (TRAP(regs) == 0x0C00 /* System Call! */ + && regs->ccr & 0x10000000 /* error signalled */ + && ((ret = regs->gpr[3]) == ERESTARTSYS + || ret == ERESTARTNOHAND || ret == ERESTARTNOINTR + || ret == ERESTART_RESTARTBLOCK)) { + + if (signr > 0 + && (ret == ERESTARTNOHAND || ret == ERESTART_RESTARTBLOCK + || (ret == ERESTARTSYS + && !(ka.sa.sa_flags & SA_RESTART)))) { + /* make the system call return an EINTR error */ + regs->result = -EINTR; + regs->gpr[3] = EINTR; + /* note that the cr0.SO bit is already set */ + } else { + regs->nip -= 4; /* Back up & retry system call */ + regs->result = 0; + regs->trap = 0; + if (ret == ERESTART_RESTARTBLOCK) + regs->gpr[0] = __NR_restart_syscall; + else + regs->gpr[3] = regs->orig_gpr3; + } + } + + if (signr == 0) + return 0; /* no signals delivered */ + + if ((ka.sa.sa_flags & SA_ONSTACK) && current->sas_ss_size + && !on_sig_stack(regs->gpr[1])) + newsp = current->sas_ss_sp + current->sas_ss_size; + else + newsp = regs->gpr[1]; + newsp &= ~0xfUL; + +#ifdef CONFIG_PPC64 + /* + * Reenable the DABR before delivering the signal to + * user space. The DABR will have been cleared if it + * triggered inside the kernel. + */ + if (current->thread.dabr) + set_dabr(current->thread.dabr); +#endif + + /* Whee! Actually deliver the signal. */ + if (ka.sa.sa_flags & SA_SIGINFO) + ret = handle_rt_signal(signr, &ka, &info, oldset, regs, newsp); + else + ret = handle_signal(signr, &ka, &info, oldset, regs, newsp); + + if (ret) { + spin_lock_irq(¤t->sighand->siglock); + sigorsets(¤t->blocked, ¤t->blocked, + &ka.sa.sa_mask); + if (!(ka.sa.sa_flags & SA_NODEFER)) + sigaddset(¤t->blocked, signr); + recalc_sigpending(); + spin_unlock_irq(¤t->sighand->siglock); + } + + return ret; +} diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c new file mode 100644 index 000000000000..a8210ed5c686 --- /dev/null +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -0,0 +1,1008 @@ +/* + * sys_ppc32.c: Conversion between 32bit and 64bit native syscalls. + * + * Copyright (C) 2001 IBM + * Copyright (C) 1997,1998 Jakub Jelinek (jj@sunsite.mff.cuni.cz) + * Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu) + * + * These routines maintain argument size conversion between 32bit and 64bit + * environment. + * + * 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/kernel.h> +#include <linux/sched.h> +#include <linux/fs.h> +#include <linux/mm.h> +#include <linux/file.h> +#include <linux/signal.h> +#include <linux/resource.h> +#include <linux/times.h> +#include <linux/utsname.h> +#include <linux/timex.h> +#include <linux/smp.h> +#include <linux/smp_lock.h> +#include <linux/sem.h> +#include <linux/msg.h> +#include <linux/shm.h> +#include <linux/poll.h> +#include <linux/personality.h> +#include <linux/stat.h> +#include <linux/mman.h> +#include <linux/in.h> +#include <linux/syscalls.h> +#include <linux/unistd.h> +#include <linux/sysctl.h> +#include <linux/binfmts.h> +#include <linux/security.h> +#include <linux/compat.h> +#include <linux/ptrace.h> +#include <linux/elf.h> + +#include <asm/ptrace.h> +#include <asm/types.h> +#include <asm/ipc.h> +#include <asm/uaccess.h> +#include <asm/unistd.h> +#include <asm/semaphore.h> +#include <asm/time.h> +#include <asm/mmu_context.h> +#include <asm/systemcfg.h> +#include <asm/ppc-pci.h> + +/* readdir & getdents */ +#define NAME_OFFSET(de) ((int) ((de)->d_name - (char __user *) (de))) +#define ROUND_UP(x) (((x)+sizeof(u32)-1) & ~(sizeof(u32)-1)) + +struct old_linux_dirent32 { + u32 d_ino; + u32 d_offset; + unsigned short d_namlen; + char d_name[1]; +}; + +struct readdir_callback32 { + struct old_linux_dirent32 __user * dirent; + int count; +}; + +static int fillonedir(void * __buf, const char * name, int namlen, + off_t offset, ino_t ino, unsigned int d_type) +{ + struct readdir_callback32 * buf = (struct readdir_callback32 *) __buf; + struct old_linux_dirent32 __user * dirent; + + if (buf->count) + return -EINVAL; + buf->count++; + dirent = buf->dirent; + put_user(ino, &dirent->d_ino); + put_user(offset, &dirent->d_offset); + put_user(namlen, &dirent->d_namlen); + copy_to_user(dirent->d_name, name, namlen); + put_user(0, dirent->d_name + namlen); + return 0; +} + +asmlinkage int old32_readdir(unsigned int fd, struct old_linux_dirent32 __user *dirent, unsigned int count) +{ + int error = -EBADF; + struct file * file; + struct readdir_callback32 buf; + + file = fget(fd); + if (!file) + goto out; + + buf.count = 0; + buf.dirent = dirent; + + error = vfs_readdir(file, (filldir_t)fillonedir, &buf); + if (error < 0) + goto out_putf; + error = buf.count; + +out_putf: + fput(file); +out: + return error; +} + +asmlinkage long ppc32_select(u32 n, compat_ulong_t __user *inp, + compat_ulong_t __user *outp, compat_ulong_t __user *exp, + compat_uptr_t tvp_x) +{ + /* sign extend n */ + return compat_sys_select((int)n, inp, outp, exp, compat_ptr(tvp_x)); +} + +int cp_compat_stat(struct kstat *stat, struct compat_stat __user *statbuf) +{ + long err; + + if (stat->size > MAX_NON_LFS || !new_valid_dev(stat->dev) || + !new_valid_dev(stat->rdev)) + return -EOVERFLOW; + + err = access_ok(VERIFY_WRITE, statbuf, sizeof(*statbuf)) ? 0 : -EFAULT; + err |= __put_user(new_encode_dev(stat->dev), &statbuf->st_dev); + err |= __put_user(stat->ino, &statbuf->st_ino); + err |= __put_user(stat->mode, &statbuf->st_mode); + err |= __put_user(stat->nlink, &statbuf->st_nlink); + err |= __put_user(stat->uid, &statbuf->st_uid); + err |= __put_user(stat->gid, &statbuf->st_gid); + err |= __put_user(new_encode_dev(stat->rdev), &statbuf->st_rdev); + err |= __put_user(stat->size, &statbuf->st_size); + err |= __put_user(stat->atime.tv_sec, &statbuf->st_atime); + err |= __put_user(stat->atime.tv_nsec, &statbuf->st_atime_nsec); + err |= __put_user(stat->mtime.tv_sec, &statbuf->st_mtime); + err |= __put_user(stat->mtime.tv_nsec, &statbuf->st_mtime_nsec); + err |= __put_user(stat->ctime.tv_sec, &statbuf->st_ctime); + err |= __put_user(stat->ctime.tv_nsec, &statbuf->st_ctime_nsec); + err |= __put_user(stat->blksize, &statbuf->st_blksize); + err |= __put_user(stat->blocks, &statbuf->st_blocks); + err |= __put_user(0, &statbuf->__unused4[0]); + err |= __put_user(0, &statbuf->__unused4[1]); + + return err; +} + +/* Note: it is necessary to treat option as an unsigned int, + * with the corresponding cast to a signed int to insure that the + * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) + * and the register representation of a signed int (msr in 64-bit mode) is performed. + */ +asmlinkage long compat_sys_sysfs(u32 option, u32 arg1, u32 arg2) +{ + return sys_sysfs((int)option, arg1, arg2); +} + +/* Handle adjtimex compatibility. */ +struct timex32 { + u32 modes; + s32 offset, freq, maxerror, esterror; + s32 status, constant, precision, tolerance; + struct compat_timeval time; + s32 tick; + s32 ppsfreq, jitter, shift, stabil; + s32 jitcnt, calcnt, errcnt, stbcnt; + s32 :32; s32 :32; s32 :32; s32 :32; + s32 :32; s32 :32; s32 :32; s32 :32; + s32 :32; s32 :32; s32 :32; s32 :32; +}; + +extern int do_adjtimex(struct timex *); +extern void ppc_adjtimex(void); + +asmlinkage long compat_sys_adjtimex(struct timex32 __user *utp) +{ + struct timex txc; + int ret; + + memset(&txc, 0, sizeof(struct timex)); + + if(get_user(txc.modes, &utp->modes) || + __get_user(txc.offset, &utp->offset) || + __get_user(txc.freq, &utp->freq) || + __get_user(txc.maxerror, &utp->maxerror) || + __get_user(txc.esterror, &utp->esterror) || + __get_user(txc.status, &utp->status) || + __get_user(txc.constant, &utp->constant) || + __get_user(txc.precision, &utp->precision) || + __get_user(txc.tolerance, &utp->tolerance) || + __get_user(txc.time.tv_sec, &utp->time.tv_sec) || + __get_user(txc.time.tv_usec, &utp->time.tv_usec) || + __get_user(txc.tick, &utp->tick) || + __get_user(txc.ppsfreq, &utp->ppsfreq) || + __get_user(txc.jitter, &utp->jitter) || + __get_user(txc.shift, &utp->shift) || + __get_user(txc.stabil, &utp->stabil) || + __get_user(txc.jitcnt, &utp->jitcnt) || + __get_user(txc.calcnt, &utp->calcnt) || + __get_user(txc.errcnt, &utp->errcnt) || + __get_user(txc.stbcnt, &utp->stbcnt)) + return -EFAULT; + + ret = do_adjtimex(&txc); + + /* adjust the conversion of TB to time of day to track adjtimex */ + ppc_adjtimex(); + + if(put_user(txc.modes, &utp->modes) || + __put_user(txc.offset, &utp->offset) || + __put_user(txc.freq, &utp->freq) || + __put_user(txc.maxerror, &utp->maxerror) || + __put_user(txc.esterror, &utp->esterror) || + __put_user(txc.status, &utp->status) || + __put_user(txc.constant, &utp->constant) || + __put_user(txc.precision, &utp->precision) || + __put_user(txc.tolerance, &utp->tolerance) || + __put_user(txc.time.tv_sec, &utp->time.tv_sec) || + __put_user(txc.time.tv_usec, &utp->time.tv_usec) || + __put_user(txc.tick, &utp->tick) || + __put_user(txc.ppsfreq, &utp->ppsfreq) || + __put_user(txc.jitter, &utp->jitter) || + __put_user(txc.shift, &utp->shift) || + __put_user(txc.stabil, &utp->stabil) || + __put_user(txc.jitcnt, &utp->jitcnt) || + __put_user(txc.calcnt, &utp->calcnt) || + __put_user(txc.errcnt, &utp->errcnt) || + __put_user(txc.stbcnt, &utp->stbcnt)) + ret = -EFAULT; + + return ret; +} + +asmlinkage long compat_sys_pause(void) +{ + current->state = TASK_INTERRUPTIBLE; + schedule(); + + return -ERESTARTNOHAND; +} + +static inline long get_ts32(struct timespec *o, struct compat_timeval __user *i) +{ + long usec; + + if (!access_ok(VERIFY_READ, i, sizeof(*i))) + return -EFAULT; + if (__get_user(o->tv_sec, &i->tv_sec)) + return -EFAULT; + if (__get_user(usec, &i->tv_usec)) + return -EFAULT; + o->tv_nsec = usec * 1000; + return 0; +} + +static inline long put_tv32(struct compat_timeval __user *o, struct timeval *i) +{ + return (!access_ok(VERIFY_WRITE, o, sizeof(*o)) || + (__put_user(i->tv_sec, &o->tv_sec) | + __put_user(i->tv_usec, &o->tv_usec))); +} + +struct sysinfo32 { + s32 uptime; + u32 loads[3]; + u32 totalram; + u32 freeram; + u32 sharedram; + u32 bufferram; + u32 totalswap; + u32 freeswap; + unsigned short procs; + unsigned short pad; + u32 totalhigh; + u32 freehigh; + u32 mem_unit; + char _f[20-2*sizeof(int)-sizeof(int)]; +}; + +asmlinkage long compat_sys_sysinfo(struct sysinfo32 __user *info) +{ + struct sysinfo s; + int ret, err; + int bitcount=0; + mm_segment_t old_fs = get_fs (); + + /* The __user cast is valid due to set_fs() */ + set_fs (KERNEL_DS); + ret = sys_sysinfo((struct sysinfo __user *)&s); + set_fs (old_fs); + + /* Check to see if any memory value is too large for 32-bit and + * scale down if needed. + */ + if ((s.totalram >> 32) || (s.totalswap >> 32)) { + while (s.mem_unit < PAGE_SIZE) { + s.mem_unit <<= 1; + bitcount++; + } + s.totalram >>=bitcount; + s.freeram >>= bitcount; + s.sharedram >>= bitcount; + s.bufferram >>= bitcount; + s.totalswap >>= bitcount; + s.freeswap >>= bitcount; + s.totalhigh >>= bitcount; + s.freehigh >>= bitcount; + } + + err = put_user (s.uptime, &info->uptime); + err |= __put_user (s.loads[0], &info->loads[0]); + err |= __put_user (s.loads[1], &info->loads[1]); + err |= __put_user (s.loads[2], &info->loads[2]); + err |= __put_user (s.totalram, &info->totalram); + err |= __put_user (s.freeram, &info->freeram); + err |= __put_user (s.sharedram, &info->sharedram); + err |= __put_user (s.bufferram, &info->bufferram); + err |= __put_user (s.totalswap, &info->totalswap); + err |= __put_user (s.freeswap, &info->freeswap); + err |= __put_user (s.procs, &info->procs); + err |= __put_user (s.totalhigh, &info->totalhigh); + err |= __put_user (s.freehigh, &info->freehigh); + err |= __put_user (s.mem_unit, &info->mem_unit); + if (err) + return -EFAULT; + + return ret; +} + + + + +/* Translations due to time_t size differences. Which affects all + sorts of things, like timeval and itimerval. */ +extern struct timezone sys_tz; + +asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv, struct timezone __user *tz) +{ + if (tv) { + struct timeval ktv; + do_gettimeofday(&ktv); + if (put_tv32(tv, &ktv)) + return -EFAULT; + } + if (tz) { + if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) + return -EFAULT; + } + + return 0; +} + + + +asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv, struct timezone __user *tz) +{ + struct timespec kts; + struct timezone ktz; + + if (tv) { + if (get_ts32(&kts, tv)) + return -EFAULT; + } + if (tz) { + if (copy_from_user(&ktz, tz, sizeof(ktz))) + return -EFAULT; + } + + return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL); +} + +#ifdef CONFIG_SYSVIPC +long compat_sys_ipc(u32 call, u32 first, u32 second, u32 third, compat_uptr_t ptr, + u32 fifth) +{ + int version; + + version = call >> 16; /* hack for backward compatibility */ + call &= 0xffff; + + switch (call) { + + case SEMTIMEDOP: + if (fifth) + /* sign extend semid */ + return compat_sys_semtimedop((int)first, + compat_ptr(ptr), second, + compat_ptr(fifth)); + /* else fall through for normal semop() */ + case SEMOP: + /* struct sembuf is the same on 32 and 64bit :)) */ + /* sign extend semid */ + return sys_semtimedop((int)first, compat_ptr(ptr), second, + NULL); + case SEMGET: + /* sign extend key, nsems */ + return sys_semget((int)first, (int)second, third); + case SEMCTL: + /* sign extend semid, semnum */ + return compat_sys_semctl((int)first, (int)second, third, + compat_ptr(ptr)); + + case MSGSND: + /* sign extend msqid */ + return compat_sys_msgsnd((int)first, (int)second, third, + compat_ptr(ptr)); + case MSGRCV: + /* sign extend msqid, msgtyp */ + return compat_sys_msgrcv((int)first, second, (int)fifth, + third, version, compat_ptr(ptr)); + case MSGGET: + /* sign extend key */ + return sys_msgget((int)first, second); + case MSGCTL: + /* sign extend msqid */ + return compat_sys_msgctl((int)first, second, compat_ptr(ptr)); + + case SHMAT: + /* sign extend shmid */ + return compat_sys_shmat((int)first, second, third, version, + compat_ptr(ptr)); + case SHMDT: + return sys_shmdt(compat_ptr(ptr)); + case SHMGET: + /* sign extend key_t */ + return sys_shmget((int)first, second, third); + case SHMCTL: + /* sign extend shmid */ + return compat_sys_shmctl((int)first, second, compat_ptr(ptr)); + + default: + return -ENOSYS; + } + + return -ENOSYS; +} +#endif + +/* Note: it is necessary to treat out_fd and in_fd as unsigned ints, + * with the corresponding cast to a signed int to insure that the + * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) + * and the register representation of a signed int (msr in 64-bit mode) is performed. + */ +asmlinkage long compat_sys_sendfile(u32 out_fd, u32 in_fd, compat_off_t __user * offset, u32 count) +{ + mm_segment_t old_fs = get_fs(); + int ret; + off_t of; + off_t __user *up; + + if (offset && get_user(of, offset)) + return -EFAULT; + + /* The __user pointer cast is valid because of the set_fs() */ + set_fs(KERNEL_DS); + up = offset ? (off_t __user *) &of : NULL; + ret = sys_sendfile((int)out_fd, (int)in_fd, up, count); + set_fs(old_fs); + + if (offset && put_user(of, offset)) + return -EFAULT; + + return ret; +} + +asmlinkage int compat_sys_sendfile64(int out_fd, int in_fd, compat_loff_t __user *offset, s32 count) +{ + mm_segment_t old_fs = get_fs(); + int ret; + loff_t lof; + loff_t __user *up; + + if (offset && get_user(lof, offset)) + return -EFAULT; + + /* The __user pointer cast is valid because of the set_fs() */ + set_fs(KERNEL_DS); + up = offset ? (loff_t __user *) &lof : NULL; + ret = sys_sendfile64(out_fd, in_fd, up, count); + set_fs(old_fs); + + if (offset && put_user(lof, offset)) + return -EFAULT; + + return ret; +} + +long compat_sys_execve(unsigned long a0, unsigned long a1, unsigned long a2, + unsigned long a3, unsigned long a4, unsigned long a5, + struct pt_regs *regs) +{ + int error; + char * filename; + + filename = getname((char __user *) a0); + error = PTR_ERR(filename); + if (IS_ERR(filename)) + goto out; + flush_fp_to_thread(current); + flush_altivec_to_thread(current); + + error = compat_do_execve(filename, compat_ptr(a1), compat_ptr(a2), regs); + + if (error == 0) { + task_lock(current); + current->ptrace &= ~PT_DTRACE; + task_unlock(current); + } + putname(filename); + +out: + return error; +} + +/* Note: it is necessary to treat option as an unsigned int, + * with the corresponding cast to a signed int to insure that the + * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) + * and the register representation of a signed int (msr in 64-bit mode) is performed. + */ +asmlinkage long compat_sys_prctl(u32 option, u32 arg2, u32 arg3, u32 arg4, u32 arg5) +{ + return sys_prctl((int)option, + (unsigned long) arg2, + (unsigned long) arg3, + (unsigned long) arg4, + (unsigned long) arg5); +} + +/* Note: it is necessary to treat pid as an unsigned int, + * with the corresponding cast to a signed int to insure that the + * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) + * and the register representation of a signed int (msr in 64-bit mode) is performed. + */ +asmlinkage long compat_sys_sched_rr_get_interval(u32 pid, struct compat_timespec __user *interval) +{ + struct timespec t; + int ret; + mm_segment_t old_fs = get_fs (); + + /* The __user pointer cast is valid because of the set_fs() */ + set_fs (KERNEL_DS); + ret = sys_sched_rr_get_interval((int)pid, (struct timespec __user *) &t); + set_fs (old_fs); + if (put_compat_timespec(&t, interval)) + return -EFAULT; + return ret; +} + +asmlinkage int compat_sys_pciconfig_read(u32 bus, u32 dfn, u32 off, u32 len, u32 ubuf) +{ + return sys_pciconfig_read((unsigned long) bus, + (unsigned long) dfn, + (unsigned long) off, + (unsigned long) len, + compat_ptr(ubuf)); +} + +asmlinkage int compat_sys_pciconfig_write(u32 bus, u32 dfn, u32 off, u32 len, u32 ubuf) +{ + return sys_pciconfig_write((unsigned long) bus, + (unsigned long) dfn, + (unsigned long) off, + (unsigned long) len, + compat_ptr(ubuf)); +} + +asmlinkage int compat_sys_pciconfig_iobase(u32 which, u32 in_bus, u32 in_devfn) +{ + return sys_pciconfig_iobase(which, in_bus, in_devfn); +} + + +/* Note: it is necessary to treat mode as an unsigned int, + * with the corresponding cast to a signed int to insure that the + * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) + * and the register representation of a signed int (msr in 64-bit mode) is performed. + */ +asmlinkage long compat_sys_access(const char __user * filename, u32 mode) +{ + return sys_access(filename, (int)mode); +} + + +/* Note: it is necessary to treat mode as an unsigned int, + * with the corresponding cast to a signed int to insure that the + * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) + * and the register representation of a signed int (msr in 64-bit mode) is performed. + */ +asmlinkage long compat_sys_creat(const char __user * pathname, u32 mode) +{ + return sys_creat(pathname, (int)mode); +} + + +/* Note: it is necessary to treat pid and options as unsigned ints, + * with the corresponding cast to a signed int to insure that the + * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) + * and the register representation of a signed int (msr in 64-bit mode) is performed. + */ +asmlinkage long compat_sys_waitpid(u32 pid, unsigned int __user * stat_addr, u32 options) +{ + return sys_waitpid((int)pid, stat_addr, (int)options); +} + + +/* Note: it is necessary to treat gidsetsize as an unsigned int, + * with the corresponding cast to a signed int to insure that the + * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) + * and the register representation of a signed int (msr in 64-bit mode) is performed. + */ +asmlinkage long compat_sys_getgroups(u32 gidsetsize, gid_t __user *grouplist) +{ + return sys_getgroups((int)gidsetsize, grouplist); +} + + +/* Note: it is necessary to treat pid as an unsigned int, + * with the corresponding cast to a signed int to insure that the + * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) + * and the register representation of a signed int (msr in 64-bit mode) is performed. + */ +asmlinkage long compat_sys_getpgid(u32 pid) +{ + return sys_getpgid((int)pid); +} + + + +/* Note: it is necessary to treat pid as an unsigned int, + * with the corresponding cast to a signed int to insure that the + * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) + * and the register representation of a signed int (msr in 64-bit mode) is performed. + */ +asmlinkage long compat_sys_getsid(u32 pid) +{ + return sys_getsid((int)pid); +} + + +/* Note: it is necessary to treat pid and sig as unsigned ints, + * with the corresponding cast to a signed int to insure that the + * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) + * and the register representation of a signed int (msr in 64-bit mode) is performed. + */ +asmlinkage long compat_sys_kill(u32 pid, u32 sig) +{ + return sys_kill((int)pid, (int)sig); +} + + +/* Note: it is necessary to treat mode as an unsigned int, + * with the corresponding cast to a signed int to insure that the + * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) + * and the register representation of a signed int (msr in 64-bit mode) is performed. + */ +asmlinkage long compat_sys_mkdir(const char __user * pathname, u32 mode) +{ + return sys_mkdir(pathname, (int)mode); +} + +long compat_sys_nice(u32 increment) +{ + /* sign extend increment */ + return sys_nice((int)increment); +} + +off_t ppc32_lseek(unsigned int fd, u32 offset, unsigned int origin) +{ + /* sign extend n */ + return sys_lseek(fd, (int)offset, origin); +} + +/* Note: it is necessary to treat bufsiz as an unsigned int, + * with the corresponding cast to a signed int to insure that the + * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) + * and the register representation of a signed int (msr in 64-bit mode) is performed. + */ +asmlinkage long compat_sys_readlink(const char __user * path, char __user * buf, u32 bufsiz) +{ + return sys_readlink(path, buf, (int)bufsiz); +} + +/* Note: it is necessary to treat option as an unsigned int, + * with the corresponding cast to a signed int to insure that the + * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) + * and the register representation of a signed int (msr in 64-bit mode) is performed. + */ +asmlinkage long compat_sys_sched_get_priority_max(u32 policy) +{ + return sys_sched_get_priority_max((int)policy); +} + + +/* Note: it is necessary to treat policy as an unsigned int, + * with the corresponding cast to a signed int to insure that the + * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) + * and the register representation of a signed int (msr in 64-bit mode) is performed. + */ +asmlinkage long compat_sys_sched_get_priority_min(u32 policy) +{ + return sys_sched_get_priority_min((int)policy); +} + + +/* Note: it is necessary to treat pid as an unsigned int, + * with the corresponding cast to a signed int to insure that the + * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) + * and the register representation of a signed int (msr in 64-bit mode) is performed. + */ +asmlinkage long compat_sys_sched_getparam(u32 pid, struct sched_param __user *param) +{ + return sys_sched_getparam((int)pid, param); +} + + +/* Note: it is necessary to treat pid as an unsigned int, + * with the corresponding cast to a signed int to insure that the + * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) + * and the register representation of a signed int (msr in 64-bit mode) is performed. + */ +asmlinkage long compat_sys_sched_getscheduler(u32 pid) +{ + return sys_sched_getscheduler((int)pid); +} + + +/* Note: it is necessary to treat pid as an unsigned int, + * with the corresponding cast to a signed int to insure that the + * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) + * and the register representation of a signed int (msr in 64-bit mode) is performed. + */ +asmlinkage long compat_sys_sched_setparam(u32 pid, struct sched_param __user *param) +{ + return sys_sched_setparam((int)pid, param); +} + + +/* Note: it is necessary to treat pid and policy as unsigned ints, + * with the corresponding cast to a signed int to insure that the + * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) + * and the register representation of a signed int (msr in 64-bit mode) is performed. + */ +asmlinkage long compat_sys_sched_setscheduler(u32 pid, u32 policy, struct sched_param __user *param) +{ + return sys_sched_setscheduler((int)pid, (int)policy, param); +} + + +/* Note: it is necessary to treat len as an unsigned int, + * with the corresponding cast to a signed int to insure that the + * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) + * and the register representation of a signed int (msr in 64-bit mode) is performed. + */ +asmlinkage long compat_sys_setdomainname(char __user *name, u32 len) +{ + return sys_setdomainname(name, (int)len); +} + + +/* Note: it is necessary to treat gidsetsize as an unsigned int, + * with the corresponding cast to a signed int to insure that the + * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) + * and the register representation of a signed int (msr in 64-bit mode) is performed. + */ +asmlinkage long compat_sys_setgroups(u32 gidsetsize, gid_t __user *grouplist) +{ + return sys_setgroups((int)gidsetsize, grouplist); +} + + +asmlinkage long compat_sys_sethostname(char __user *name, u32 len) +{ + /* sign extend len */ + return sys_sethostname(name, (int)len); +} + + +/* Note: it is necessary to treat pid and pgid as unsigned ints, + * with the corresponding cast to a signed int to insure that the + * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) + * and the register representation of a signed int (msr in 64-bit mode) is performed. + */ +asmlinkage long compat_sys_setpgid(u32 pid, u32 pgid) +{ + return sys_setpgid((int)pid, (int)pgid); +} + +long compat_sys_getpriority(u32 which, u32 who) +{ + /* sign extend which and who */ + return sys_getpriority((int)which, (int)who); +} + +long compat_sys_setpriority(u32 which, u32 who, u32 niceval) +{ + /* sign extend which, who and niceval */ + return sys_setpriority((int)which, (int)who, (int)niceval); +} + +long compat_sys_ioprio_get(u32 which, u32 who) +{ + /* sign extend which and who */ + return sys_ioprio_get((int)which, (int)who); +} + +long compat_sys_ioprio_set(u32 which, u32 who, u32 ioprio) +{ + /* sign extend which, who and ioprio */ + return sys_ioprio_set((int)which, (int)who, (int)ioprio); +} + +/* Note: it is necessary to treat newmask as an unsigned int, + * with the corresponding cast to a signed int to insure that the + * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) + * and the register representation of a signed int (msr in 64-bit mode) is performed. + */ +asmlinkage long compat_sys_ssetmask(u32 newmask) +{ + return sys_ssetmask((int) newmask); +} + +asmlinkage long compat_sys_syslog(u32 type, char __user * buf, u32 len) +{ + /* sign extend len */ + return sys_syslog(type, buf, (int)len); +} + + +/* Note: it is necessary to treat mask as an unsigned int, + * with the corresponding cast to a signed int to insure that the + * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) + * and the register representation of a signed int (msr in 64-bit mode) is performed. + */ +asmlinkage long compat_sys_umask(u32 mask) +{ + return sys_umask((int)mask); +} + +#ifdef CONFIG_SYSCTL +struct __sysctl_args32 { + u32 name; + int nlen; + u32 oldval; + u32 oldlenp; + u32 newval; + u32 newlen; + u32 __unused[4]; +}; + +asmlinkage long compat_sys_sysctl(struct __sysctl_args32 __user *args) +{ + struct __sysctl_args32 tmp; + int error; + size_t oldlen; + size_t __user *oldlenp = NULL; + unsigned long addr = (((unsigned long)&args->__unused[0]) + 7) & ~7; + + if (copy_from_user(&tmp, args, sizeof(tmp))) + return -EFAULT; + + if (tmp.oldval && tmp.oldlenp) { + /* Duh, this is ugly and might not work if sysctl_args + is in read-only memory, but do_sysctl does indirectly + a lot of uaccess in both directions and we'd have to + basically copy the whole sysctl.c here, and + glibc's __sysctl uses rw memory for the structure + anyway. */ + oldlenp = (size_t __user *)addr; + if (get_user(oldlen, (compat_size_t __user *)compat_ptr(tmp.oldlenp)) || + put_user(oldlen, oldlenp)) + return -EFAULT; + } + + lock_kernel(); + error = do_sysctl(compat_ptr(tmp.name), tmp.nlen, + compat_ptr(tmp.oldval), oldlenp, + compat_ptr(tmp.newval), tmp.newlen); + unlock_kernel(); + if (oldlenp) { + if (!error) { + if (get_user(oldlen, oldlenp) || + put_user(oldlen, (compat_size_t __user *)compat_ptr(tmp.oldlenp))) + error = -EFAULT; + } + copy_to_user(args->__unused, tmp.__unused, sizeof(tmp.__unused)); + } + return error; +} +#endif + +unsigned long compat_sys_mmap2(unsigned long addr, size_t len, + unsigned long prot, unsigned long flags, + unsigned long fd, unsigned long pgoff) +{ + /* This should remain 12 even if PAGE_SIZE changes */ + return sys_mmap(addr, len, prot, flags, fd, pgoff << 12); +} + +long compat_sys_tgkill(u32 tgid, u32 pid, int sig) +{ + /* sign extend tgid, pid */ + return sys_tgkill((int)tgid, (int)pid, sig); +} + +/* + * long long munging: + * The 32 bit ABI passes long longs in an odd even register pair. + */ + +compat_ssize_t compat_sys_pread64(unsigned int fd, char __user *ubuf, compat_size_t count, + u32 reg6, u32 poshi, u32 poslo) +{ + return sys_pread64(fd, ubuf, count, ((loff_t)poshi << 32) | poslo); +} + +compat_ssize_t compat_sys_pwrite64(unsigned int fd, char __user *ubuf, compat_size_t count, + u32 reg6, u32 poshi, u32 poslo) +{ + return sys_pwrite64(fd, ubuf, count, ((loff_t)poshi << 32) | poslo); +} + +compat_ssize_t compat_sys_readahead(int fd, u32 r4, u32 offhi, u32 offlo, u32 count) +{ + return sys_readahead(fd, ((loff_t)offhi << 32) | offlo, count); +} + +asmlinkage int compat_sys_truncate64(const char __user * path, u32 reg4, + unsigned long high, unsigned long low) +{ + return sys_truncate(path, (high << 32) | low); +} + +asmlinkage int compat_sys_ftruncate64(unsigned int fd, u32 reg4, unsigned long high, + unsigned long low) +{ + return sys_ftruncate(fd, (high << 32) | low); +} + +long ppc32_lookup_dcookie(u32 cookie_high, u32 cookie_low, char __user *buf, + size_t len) +{ + return sys_lookup_dcookie((u64)cookie_high << 32 | cookie_low, + buf, len); +} + +long ppc32_fadvise64(int fd, u32 unused, u32 offset_high, u32 offset_low, + size_t len, int advice) +{ + return sys_fadvise64(fd, (u64)offset_high << 32 | offset_low, len, + advice); +} + +long ppc32_timer_create(clockid_t clock, + struct compat_sigevent __user *ev32, + timer_t __user *timer_id) +{ + sigevent_t event; + timer_t t; + long err; + mm_segment_t savefs; + + if (ev32 == NULL) + return sys_timer_create(clock, NULL, timer_id); + + if (get_compat_sigevent(&event, ev32)) + return -EFAULT; + + if (!access_ok(VERIFY_WRITE, timer_id, sizeof(timer_t))) + return -EFAULT; + + savefs = get_fs(); + set_fs(KERNEL_DS); + /* The __user pointer casts are valid due to the set_fs() */ + err = sys_timer_create(clock, + (sigevent_t __user *) &event, + (timer_t __user *) &t); + set_fs(savefs); + + if (err == 0) + err = __put_user(t, timer_id); + + return err; +} + +asmlinkage long compat_sys_add_key(const char __user *_type, + const char __user *_description, + const void __user *_payload, + u32 plen, + u32 ringid) +{ + return sys_add_key(_type, _description, _payload, plen, ringid); +} + +asmlinkage long compat_sys_request_key(const char __user *_type, + const char __user *_description, + const char __user *_callout_info, + u32 destringid) +{ + return sys_request_key(_type, _description, _callout_info, destringid); +} + diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c new file mode 100644 index 000000000000..f72ced11212d --- /dev/null +++ b/arch/powerpc/kernel/syscalls.c @@ -0,0 +1,358 @@ +/* + * Implementation of various system calls for Linux/PowerPC + * + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) + * + * Derived from "arch/i386/kernel/sys_i386.c" + * Adapted from the i386 version by Gary Thomas + * Modified by Cort Dougan (cort@cs.nmt.edu) + * and Paul Mackerras (paulus@cs.anu.edu.au). + * + * This file contains various random system calls that + * have a non-standard calling sequence on the Linux/PPC + * platform. + * + * 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/errno.h> +#include <linux/sched.h> +#include <linux/syscalls.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/smp_lock.h> +#include <linux/sem.h> +#include <linux/msg.h> +#include <linux/shm.h> +#include <linux/stat.h> +#include <linux/mman.h> +#include <linux/sys.h> +#include <linux/ipc.h> +#include <linux/utsname.h> +#include <linux/file.h> +#include <linux/init.h> +#include <linux/personality.h> + +#include <asm/uaccess.h> +#include <asm/ipc.h> +#include <asm/semaphore.h> +#include <asm/time.h> +#include <asm/unistd.h> + +extern unsigned long wall_jiffies; + + +/* + * sys_ipc() is the de-multiplexer for the SysV IPC calls.. + * + * This is really horribly ugly. + */ +int sys_ipc(uint call, int first, unsigned long second, long third, + void __user *ptr, long fifth) +{ + int version, ret; + + version = call >> 16; /* hack for backward compatibility */ + call &= 0xffff; + + ret = -ENOSYS; + switch (call) { + case SEMOP: + ret = sys_semtimedop(first, (struct sembuf __user *)ptr, + (unsigned)second, NULL); + break; + case SEMTIMEDOP: + ret = sys_semtimedop(first, (struct sembuf __user *)ptr, + (unsigned)second, + (const struct timespec __user *) fifth); + break; + case SEMGET: + ret = sys_semget (first, (int)second, third); + break; + case SEMCTL: { + union semun fourth; + + ret = -EINVAL; + if (!ptr) + break; + if ((ret = get_user(fourth.__pad, (void __user * __user *)ptr))) + break; + ret = sys_semctl(first, (int)second, third, fourth); + break; + } + case MSGSND: + ret = sys_msgsnd(first, (struct msgbuf __user *)ptr, + (size_t)second, third); + break; + case MSGRCV: + switch (version) { + case 0: { + struct ipc_kludge tmp; + + ret = -EINVAL; + if (!ptr) + break; + if ((ret = copy_from_user(&tmp, + (struct ipc_kludge __user *) ptr, + sizeof (tmp)) ? -EFAULT : 0)) + break; + ret = sys_msgrcv(first, tmp.msgp, (size_t) second, + tmp.msgtyp, third); + break; + } + default: + ret = sys_msgrcv (first, (struct msgbuf __user *) ptr, + (size_t)second, fifth, third); + break; + } + break; + case MSGGET: + ret = sys_msgget((key_t)first, (int)second); + break; + case MSGCTL: + ret = sys_msgctl(first, (int)second, + (struct msqid_ds __user *)ptr); + break; + case SHMAT: { + ulong raddr; + ret = do_shmat(first, (char __user *)ptr, (int)second, &raddr); + if (ret) + break; + ret = put_user(raddr, (ulong __user *) third); + break; + } + case SHMDT: + ret = sys_shmdt((char __user *)ptr); + break; + case SHMGET: + ret = sys_shmget(first, (size_t)second, third); + break; + case SHMCTL: + ret = sys_shmctl(first, (int)second, + (struct shmid_ds __user *)ptr); + break; + } + + return ret; +} + +/* + * sys_pipe() is the normal C calling standard for creating + * a pipe. It's not the way unix traditionally does this, though. + */ +int sys_pipe(int __user *fildes) +{ + int fd[2]; + int error; + + error = do_pipe(fd); + if (!error) { + if (copy_to_user(fildes, fd, 2*sizeof(int))) + error = -EFAULT; + } + return error; +} + +static inline unsigned long do_mmap2(unsigned long addr, size_t len, + unsigned long prot, unsigned long flags, + unsigned long fd, unsigned long off, int shift) +{ + struct file * file = NULL; + unsigned long ret = -EINVAL; + + if (shift) { + if (off & ((1 << shift) - 1)) + goto out; + off >>= shift; + } + + ret = -EBADF; + if (!(flags & MAP_ANONYMOUS)) { + if (!(file = fget(fd))) + goto out; + } + + flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE); + + down_write(¤t->mm->mmap_sem); + ret = do_mmap_pgoff(file, addr, len, prot, flags, off); + up_write(¤t->mm->mmap_sem); + if (file) + fput(file); +out: + return ret; +} + +unsigned long sys_mmap2(unsigned long addr, size_t len, + unsigned long prot, unsigned long flags, + unsigned long fd, unsigned long pgoff) +{ + return do_mmap2(addr, len, prot, flags, fd, pgoff, PAGE_SHIFT-12); +} + +unsigned long sys_mmap(unsigned long addr, size_t len, + unsigned long prot, unsigned long flags, + unsigned long fd, off_t offset) +{ + return do_mmap2(addr, len, prot, flags, fd, offset, PAGE_SHIFT); +} + +#ifdef CONFIG_PPC32 +/* + * Due to some executables calling the wrong select we sometimes + * get wrong args. This determines how the args are being passed + * (a single ptr to them all args passed) then calls + * sys_select() with the appropriate args. -- Cort + */ +int +ppc_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timeval __user *tvp) +{ + if ( (unsigned long)n >= 4096 ) + { + unsigned long __user *buffer = (unsigned long __user *)n; + if (!access_ok(VERIFY_READ, buffer, 5*sizeof(unsigned long)) + || __get_user(n, buffer) + || __get_user(inp, ((fd_set __user * __user *)(buffer+1))) + || __get_user(outp, ((fd_set __user * __user *)(buffer+2))) + || __get_user(exp, ((fd_set __user * __user *)(buffer+3))) + || __get_user(tvp, ((struct timeval __user * __user *)(buffer+4)))) + return -EFAULT; + } + return sys_select(n, inp, outp, exp, tvp); +} +#endif + +#ifdef CONFIG_PPC64 +long ppc64_personality(unsigned long personality) +{ + long ret; + + if (personality(current->personality) == PER_LINUX32 + && personality == PER_LINUX) + personality = PER_LINUX32; + ret = sys_personality(personality); + if (ret == PER_LINUX32) + ret = PER_LINUX; + return ret; +} +#endif + +#ifdef CONFIG_PPC64 +#define OVERRIDE_MACHINE (personality(current->personality) == PER_LINUX32) +#else +#define OVERRIDE_MACHINE 0 +#endif + +static inline int override_machine(char *mach) +{ + if (OVERRIDE_MACHINE) { + /* change ppc64 to ppc */ + if (__put_user(0, mach+3) || __put_user(0, mach+4)) + return -EFAULT; + } + return 0; +} + +long ppc_newuname(struct new_utsname __user * name) +{ + int err = 0; + + down_read(&uts_sem); + if (copy_to_user(name, &system_utsname, sizeof(*name))) + err = -EFAULT; + up_read(&uts_sem); + if (!err) + err = override_machine(name->machine); + return err; +} + +int sys_uname(struct old_utsname __user *name) +{ + int err = 0; + + down_read(&uts_sem); + if (copy_to_user(name, &system_utsname, sizeof(*name))) + err = -EFAULT; + up_read(&uts_sem); + if (!err) + err = override_machine(name->machine); + return err; +} + +int sys_olduname(struct oldold_utsname __user *name) +{ + int error; + + if (!access_ok(VERIFY_WRITE, name, sizeof(struct oldold_utsname))) + return -EFAULT; + + down_read(&uts_sem); + error = __copy_to_user(&name->sysname, &system_utsname.sysname, + __OLD_UTS_LEN); + error |= __put_user(0, name->sysname + __OLD_UTS_LEN); + error |= __copy_to_user(&name->nodename, &system_utsname.nodename, + __OLD_UTS_LEN); + error |= __put_user(0, name->nodename + __OLD_UTS_LEN); + error |= __copy_to_user(&name->release, &system_utsname.release, + __OLD_UTS_LEN); + error |= __put_user(0, name->release + __OLD_UTS_LEN); + error |= __copy_to_user(&name->version, &system_utsname.version, + __OLD_UTS_LEN); + error |= __put_user(0, name->version + __OLD_UTS_LEN); + error |= __copy_to_user(&name->machine, &system_utsname.machine, + __OLD_UTS_LEN); + error |= override_machine(name->machine); + up_read(&uts_sem); + + return error? -EFAULT: 0; +} + +#ifdef CONFIG_PPC64 +time_t sys64_time(time_t __user * tloc) +{ + time_t secs; + time_t usecs; + + long tb_delta = tb_ticks_since(tb_last_stamp); + tb_delta += (jiffies - wall_jiffies) * tb_ticks_per_jiffy; + + secs = xtime.tv_sec; + usecs = (xtime.tv_nsec/1000) + tb_delta / tb_ticks_per_usec; + while (usecs >= USEC_PER_SEC) { + ++secs; + usecs -= USEC_PER_SEC; + } + + if (tloc) { + if (put_user(secs,tloc)) + secs = -EFAULT; + } + + return secs; +} +#endif + +long ppc_fadvise64_64(int fd, int advice, u32 offset_high, u32 offset_low, + u32 len_high, u32 len_low) +{ + return sys_fadvise64(fd, (u64)offset_high << 32 | offset_low, + (u64)len_high << 32 | len_low, advice); +} + +void do_show_syscall(unsigned long r3, unsigned long r4, unsigned long r5, + unsigned long r6, unsigned long r7, unsigned long r8, + struct pt_regs *regs) +{ + printk("syscall %ld(%lx, %lx, %lx, %lx, %lx, %lx) regs=%p current=%p" + " cpu=%d\n", regs->gpr[0], r3, r4, r5, r6, r7, r8, regs, + current, smp_processor_id()); +} + +void do_show_syscall_exit(unsigned long r3) +{ + printk(" -> %lx, current=%p cpu=%d\n", r3, current, smp_processor_id()); +} diff --git a/arch/powerpc/kernel/systbl.S b/arch/powerpc/kernel/systbl.S new file mode 100644 index 000000000000..65eaea91b499 --- /dev/null +++ b/arch/powerpc/kernel/systbl.S @@ -0,0 +1,321 @@ +/* + * This file contains the table of syscall-handling functions. + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) + * + * Largely rewritten by Cort Dougan (cort@cs.nmt.edu) + * and Paul Mackerras. + * + * Adapted for iSeries by Mike Corrigan (mikejc@us.ibm.com) + * PPC64 updates by Dave Engebretsen (engebret@us.ibm.com) + * + * 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/ppc_asm.h> + +#ifdef CONFIG_PPC64 +#define SYSCALL(func) .llong .sys_##func,.sys_##func +#define COMPAT_SYS(func) .llong .sys_##func,.compat_sys_##func +#define PPC_SYS(func) .llong .ppc_##func,.ppc_##func +#define OLDSYS(func) .llong .sys_ni_syscall,.sys_ni_syscall +#define SYS32ONLY(func) .llong .sys_ni_syscall,.compat_sys_##func +#define SYSX(f, f3264, f32) .llong .f,.f3264 +#else +#define SYSCALL(func) .long sys_##func +#define COMPAT_SYS(func) .long sys_##func +#define PPC_SYS(func) .long ppc_##func +#define OLDSYS(func) .long sys_##func +#define SYS32ONLY(func) .long sys_##func +#define SYSX(f, f3264, f32) .long f32 +#endif + +#ifdef CONFIG_PPC64 +#define sys_sigpending sys_ni_syscall +#define sys_old_getrlimit sys_ni_syscall +#else +#define ppc_rtas sys_ni_syscall +#endif + +_GLOBAL(sys_call_table) +SYSCALL(restart_syscall) +SYSCALL(exit) +PPC_SYS(fork) +SYSCALL(read) +SYSCALL(write) +COMPAT_SYS(open) +SYSCALL(close) +COMPAT_SYS(waitpid) +COMPAT_SYS(creat) +SYSCALL(link) +SYSCALL(unlink) +COMPAT_SYS(execve) +SYSCALL(chdir) +SYSX(sys64_time,compat_sys_time,sys_time) +SYSCALL(mknod) +SYSCALL(chmod) +SYSCALL(lchown) +SYSCALL(ni_syscall) +OLDSYS(stat) +SYSX(sys_lseek,ppc32_lseek,sys_lseek) +SYSCALL(getpid) +COMPAT_SYS(mount) +SYSX(sys_ni_syscall,sys_oldumount,sys_oldumount) +SYSCALL(setuid) +SYSCALL(getuid) +COMPAT_SYS(stime) +COMPAT_SYS(ptrace) +SYSCALL(alarm) +OLDSYS(fstat) +COMPAT_SYS(pause) +COMPAT_SYS(utime) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +COMPAT_SYS(access) +COMPAT_SYS(nice) +SYSCALL(ni_syscall) +SYSCALL(sync) +COMPAT_SYS(kill) +SYSCALL(rename) +COMPAT_SYS(mkdir) +SYSCALL(rmdir) +SYSCALL(dup) +SYSCALL(pipe) +COMPAT_SYS(times) +SYSCALL(ni_syscall) +SYSCALL(brk) +SYSCALL(setgid) +SYSCALL(getgid) +SYSCALL(signal) +SYSCALL(geteuid) +SYSCALL(getegid) +SYSCALL(acct) +SYSCALL(umount) +SYSCALL(ni_syscall) +COMPAT_SYS(ioctl) +COMPAT_SYS(fcntl) +SYSCALL(ni_syscall) +COMPAT_SYS(setpgid) +SYSCALL(ni_syscall) +SYSX(sys_ni_syscall,sys_olduname, sys_olduname) +COMPAT_SYS(umask) +SYSCALL(chroot) +SYSCALL(ustat) +SYSCALL(dup2) +SYSCALL(getppid) +SYSCALL(getpgrp) +SYSCALL(setsid) +SYS32ONLY(sigaction) +SYSCALL(sgetmask) +COMPAT_SYS(ssetmask) +SYSCALL(setreuid) +SYSCALL(setregid) +SYSX(sys_ni_syscall,ppc32_sigsuspend,ppc_sigsuspend) +COMPAT_SYS(sigpending) +COMPAT_SYS(sethostname) +COMPAT_SYS(setrlimit) +COMPAT_SYS(old_getrlimit) +COMPAT_SYS(getrusage) +COMPAT_SYS(gettimeofday) +COMPAT_SYS(settimeofday) +COMPAT_SYS(getgroups) +COMPAT_SYS(setgroups) +SYSX(sys_ni_syscall,sys_ni_syscall,ppc_select) +SYSCALL(symlink) +OLDSYS(lstat) +COMPAT_SYS(readlink) +SYSCALL(uselib) +SYSCALL(swapon) +SYSCALL(reboot) +SYSX(sys_ni_syscall,old32_readdir,old_readdir) +SYSCALL(mmap) +SYSCALL(munmap) +SYSCALL(truncate) +SYSCALL(ftruncate) +SYSCALL(fchmod) +SYSCALL(fchown) +COMPAT_SYS(getpriority) +COMPAT_SYS(setpriority) +SYSCALL(ni_syscall) +COMPAT_SYS(statfs) +COMPAT_SYS(fstatfs) +SYSCALL(ni_syscall) +COMPAT_SYS(socketcall) +COMPAT_SYS(syslog) +COMPAT_SYS(setitimer) +COMPAT_SYS(getitimer) +COMPAT_SYS(newstat) +COMPAT_SYS(newlstat) +COMPAT_SYS(newfstat) +SYSX(sys_ni_syscall,sys_uname,sys_uname) +SYSCALL(ni_syscall) +SYSCALL(vhangup) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +COMPAT_SYS(wait4) +SYSCALL(swapoff) +COMPAT_SYS(sysinfo) +COMPAT_SYS(ipc) +SYSCALL(fsync) +SYSX(sys_ni_syscall,ppc32_sigreturn,sys_sigreturn) +PPC_SYS(clone) +COMPAT_SYS(setdomainname) +PPC_SYS(newuname) +SYSCALL(ni_syscall) +COMPAT_SYS(adjtimex) +SYSCALL(mprotect) +SYSX(sys_ni_syscall,compat_sys_sigprocmask,sys_sigprocmask) +SYSCALL(ni_syscall) +SYSCALL(init_module) +SYSCALL(delete_module) +SYSCALL(ni_syscall) +SYSCALL(quotactl) +COMPAT_SYS(getpgid) +SYSCALL(fchdir) +SYSCALL(bdflush) +COMPAT_SYS(sysfs) +SYSX(ppc64_personality,ppc64_personality,sys_personality) +SYSCALL(ni_syscall) +SYSCALL(setfsuid) +SYSCALL(setfsgid) +SYSCALL(llseek) +COMPAT_SYS(getdents) +SYSX(sys_select,ppc32_select,ppc_select) +SYSCALL(flock) +SYSCALL(msync) +COMPAT_SYS(readv) +COMPAT_SYS(writev) +COMPAT_SYS(getsid) +SYSCALL(fdatasync) +COMPAT_SYS(sysctl) +SYSCALL(mlock) +SYSCALL(munlock) +SYSCALL(mlockall) +SYSCALL(munlockall) +COMPAT_SYS(sched_setparam) +COMPAT_SYS(sched_getparam) +COMPAT_SYS(sched_setscheduler) +COMPAT_SYS(sched_getscheduler) +SYSCALL(sched_yield) +COMPAT_SYS(sched_get_priority_max) +COMPAT_SYS(sched_get_priority_min) +COMPAT_SYS(sched_rr_get_interval) +COMPAT_SYS(nanosleep) +SYSCALL(mremap) +SYSCALL(setresuid) +SYSCALL(getresuid) +SYSCALL(ni_syscall) +SYSCALL(poll) +COMPAT_SYS(nfsservctl) +SYSCALL(setresgid) +SYSCALL(getresgid) +COMPAT_SYS(prctl) +SYSX(ppc64_rt_sigreturn,ppc32_rt_sigreturn,sys_rt_sigreturn) +COMPAT_SYS(rt_sigaction) +COMPAT_SYS(rt_sigprocmask) +COMPAT_SYS(rt_sigpending) +COMPAT_SYS(rt_sigtimedwait) +COMPAT_SYS(rt_sigqueueinfo) +SYSX(ppc64_rt_sigsuspend,ppc32_rt_sigsuspend,ppc_rt_sigsuspend) +COMPAT_SYS(pread64) +COMPAT_SYS(pwrite64) +SYSCALL(chown) +SYSCALL(getcwd) +SYSCALL(capget) +SYSCALL(capset) +COMPAT_SYS(sigaltstack) +SYSX(sys_sendfile64,compat_sys_sendfile,sys_sendfile) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +PPC_SYS(vfork) +COMPAT_SYS(getrlimit) +COMPAT_SYS(readahead) +SYS32ONLY(mmap2) +SYS32ONLY(truncate64) +SYS32ONLY(ftruncate64) +SYSX(sys_ni_syscall,sys_stat64,sys_stat64) +SYSX(sys_ni_syscall,sys_lstat64,sys_lstat64) +SYSX(sys_ni_syscall,sys_fstat64,sys_fstat64) +COMPAT_SYS(pciconfig_read) +COMPAT_SYS(pciconfig_write) +COMPAT_SYS(pciconfig_iobase) +SYSCALL(ni_syscall) +SYSCALL(getdents64) +SYSCALL(pivot_root) +SYSX(sys_ni_syscall,compat_sys_fcntl64,sys_fcntl64) +SYSCALL(madvise) +SYSCALL(mincore) +SYSCALL(gettid) +SYSCALL(tkill) +SYSCALL(setxattr) +SYSCALL(lsetxattr) +SYSCALL(fsetxattr) +SYSCALL(getxattr) +SYSCALL(lgetxattr) +SYSCALL(fgetxattr) +SYSCALL(listxattr) +SYSCALL(llistxattr) +SYSCALL(flistxattr) +SYSCALL(removexattr) +SYSCALL(lremovexattr) +SYSCALL(fremovexattr) +COMPAT_SYS(futex) +COMPAT_SYS(sched_setaffinity) +COMPAT_SYS(sched_getaffinity) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYS32ONLY(sendfile64) +COMPAT_SYS(io_setup) +SYSCALL(io_destroy) +COMPAT_SYS(io_getevents) +COMPAT_SYS(io_submit) +SYSCALL(io_cancel) +SYSCALL(set_tid_address) +SYSX(sys_fadvise64,ppc32_fadvise64,sys_fadvise64) +SYSCALL(exit_group) +SYSX(sys_lookup_dcookie,ppc32_lookup_dcookie,sys_lookup_dcookie) +SYSCALL(epoll_create) +SYSCALL(epoll_ctl) +SYSCALL(epoll_wait) +SYSCALL(remap_file_pages) +SYSX(sys_timer_create,ppc32_timer_create,sys_timer_create) +COMPAT_SYS(timer_settime) +COMPAT_SYS(timer_gettime) +SYSCALL(timer_getoverrun) +SYSCALL(timer_delete) +COMPAT_SYS(clock_settime) +COMPAT_SYS(clock_gettime) +COMPAT_SYS(clock_getres) +COMPAT_SYS(clock_nanosleep) +SYSX(ppc64_swapcontext,ppc32_swapcontext,ppc_swapcontext) +COMPAT_SYS(tgkill) +COMPAT_SYS(utimes) +COMPAT_SYS(statfs64) +COMPAT_SYS(fstatfs64) +SYSX(sys_ni_syscall, ppc_fadvise64_64, ppc_fadvise64_64) +PPC_SYS(rtas) +OLDSYS(debug_setcontext) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +COMPAT_SYS(mbind) +COMPAT_SYS(get_mempolicy) +COMPAT_SYS(set_mempolicy) +COMPAT_SYS(mq_open) +SYSCALL(mq_unlink) +COMPAT_SYS(mq_timedsend) +COMPAT_SYS(mq_timedreceive) +COMPAT_SYS(mq_notify) +COMPAT_SYS(mq_getsetattr) +COMPAT_SYS(kexec_load) +COMPAT_SYS(add_key) +COMPAT_SYS(request_key) +COMPAT_SYS(keyctl) +COMPAT_SYS(waitid) +COMPAT_SYS(ioprio_set) +COMPAT_SYS(ioprio_get) +SYSCALL(inotify_init) +SYSCALL(inotify_add_watch) +SYSCALL(inotify_rm_watch) diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c new file mode 100644 index 000000000000..23436b6c1881 --- /dev/null +++ b/arch/powerpc/kernel/time.c @@ -0,0 +1,1005 @@ +/* + * Common time routines among all ppc machines. + * + * Written by Cort Dougan (cort@cs.nmt.edu) to merge + * Paul Mackerras' version and mine for PReP and Pmac. + * MPC8xx/MBX changes by Dan Malek (dmalek@jlc.net). + * Converted for 64-bit by Mike Corrigan (mikejc@us.ibm.com) + * + * First round of bugfixes by Gabriel Paubert (paubert@iram.es) + * to make clock more stable (2.4.0-test5). The only thing + * that this code assumes is that the timebases have been synchronized + * by firmware on SMP and are never stopped (never do sleep + * on SMP then, nap and doze are OK). + * + * Speeded up do_gettimeofday by getting rid of references to + * xtime (which required locks for consistency). (mikejc@us.ibm.com) + * + * TODO (not necessarily in this file): + * - improve precision and reproducibility of timebase frequency + * measurement at boot time. (for iSeries, we calibrate the timebase + * against the Titan chip's clock.) + * - for astronomical applications: add a new function to get + * non ambiguous timestamps even around leap seconds. This needs + * a new timestamp format and a good name. + * + * 1997-09-10 Updated NTP code according to technical memorandum Jan '96 + * "A Kernel Model for Precision Timekeeping" by Dave Mills + * + * 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/errno.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/param.h> +#include <linux/string.h> +#include <linux/mm.h> +#include <linux/interrupt.h> +#include <linux/timex.h> +#include <linux/kernel_stat.h> +#include <linux/time.h> +#include <linux/init.h> +#include <linux/profile.h> +#include <linux/cpu.h> +#include <linux/security.h> +#include <linux/percpu.h> +#include <linux/rtc.h> + +#include <asm/io.h> +#include <asm/processor.h> +#include <asm/nvram.h> +#include <asm/cache.h> +#include <asm/machdep.h> +#include <asm/uaccess.h> +#include <asm/time.h> +#include <asm/prom.h> +#include <asm/irq.h> +#include <asm/div64.h> +#ifdef CONFIG_PPC64 +#include <asm/systemcfg.h> +#include <asm/firmware.h> +#endif +#ifdef CONFIG_PPC_ISERIES +#include <asm/iSeries/ItLpQueue.h> +#include <asm/iSeries/HvCallXm.h> +#endif + +/* keep track of when we need to update the rtc */ +time_t last_rtc_update; +extern int piranha_simulator; +#ifdef CONFIG_PPC_ISERIES +unsigned long iSeries_recal_titan = 0; +unsigned long iSeries_recal_tb = 0; +static unsigned long first_settimeofday = 1; +#endif + +/* The decrementer counts down by 128 every 128ns on a 601. */ +#define DECREMENTER_COUNT_601 (1000000000 / HZ) + +#define XSEC_PER_SEC (1024*1024) + +#ifdef CONFIG_PPC64 +#define SCALE_XSEC(xsec, max) (((xsec) * max) / XSEC_PER_SEC) +#else +/* compute ((xsec << 12) * max) >> 32 */ +#define SCALE_XSEC(xsec, max) mulhwu((xsec) << 12, max) +#endif + +unsigned long tb_ticks_per_jiffy; +unsigned long tb_ticks_per_usec = 100; /* sane default */ +EXPORT_SYMBOL(tb_ticks_per_usec); +unsigned long tb_ticks_per_sec; +u64 tb_to_xs; +unsigned tb_to_us; +unsigned long processor_freq; +DEFINE_SPINLOCK(rtc_lock); +EXPORT_SYMBOL_GPL(rtc_lock); + +u64 tb_to_ns_scale; +unsigned tb_to_ns_shift; + +struct gettimeofday_struct do_gtod; + +extern unsigned long wall_jiffies; + +extern struct timezone sys_tz; +static long timezone_offset; + +void ppc_adjtimex(void); + +static unsigned adjusting_time = 0; + +unsigned long ppc_proc_freq; +unsigned long ppc_tb_freq; + +#ifdef CONFIG_PPC32 /* XXX for now */ +#define boot_cpuid 0 +#endif + +u64 tb_last_jiffy __cacheline_aligned_in_smp; +unsigned long tb_last_stamp; + +/* + * Note that on ppc32 this only stores the bottom 32 bits of + * the timebase value, but that's enough to tell when a jiffy + * has passed. + */ +DEFINE_PER_CPU(unsigned long, last_jiffy); + +static __inline__ void timer_check_rtc(void) +{ + /* + * update the rtc when needed, this should be performed on the + * right fraction of a second. Half or full second ? + * Full second works on mk48t59 clocks, others need testing. + * Note that this update is basically only used through + * the adjtimex system calls. Setting the HW clock in + * any other way is a /dev/rtc and userland business. + * This is still wrong by -0.5/+1.5 jiffies because of the + * timer interrupt resolution and possible delay, but here we + * hit a quantization limit which can only be solved by higher + * resolution timers and decoupling time management from timer + * interrupts. This is also wrong on the clocks + * which require being written at the half second boundary. + * We should have an rtc call that only sets the minutes and + * seconds like on Intel to avoid problems with non UTC clocks. + */ + if (ppc_md.set_rtc_time && ntp_synced() && + xtime.tv_sec - last_rtc_update >= 659 && + abs((xtime.tv_nsec/1000) - (1000000-1000000/HZ)) < 500000/HZ && + jiffies - wall_jiffies == 1) { + struct rtc_time tm; + to_tm(xtime.tv_sec + 1 + timezone_offset, &tm); + tm.tm_year -= 1900; + tm.tm_mon -= 1; + if (ppc_md.set_rtc_time(&tm) == 0) + last_rtc_update = xtime.tv_sec + 1; + else + /* Try again one minute later */ + last_rtc_update += 60; + } +} + +/* + * This version of gettimeofday has microsecond resolution. + */ +static inline void __do_gettimeofday(struct timeval *tv, u64 tb_val) +{ + unsigned long sec, usec; + u64 tb_ticks, xsec; + struct gettimeofday_vars *temp_varp; + u64 temp_tb_to_xs, temp_stamp_xsec; + + /* + * These calculations are faster (gets rid of divides) + * if done in units of 1/2^20 rather than microseconds. + * The conversion to microseconds at the end is done + * without a divide (and in fact, without a multiply) + */ + temp_varp = do_gtod.varp; + tb_ticks = tb_val - temp_varp->tb_orig_stamp; + temp_tb_to_xs = temp_varp->tb_to_xs; + temp_stamp_xsec = temp_varp->stamp_xsec; + xsec = temp_stamp_xsec + mulhdu(tb_ticks, temp_tb_to_xs); + sec = xsec / XSEC_PER_SEC; + usec = (unsigned long)xsec & (XSEC_PER_SEC - 1); + usec = SCALE_XSEC(usec, 1000000); + + tv->tv_sec = sec; + tv->tv_usec = usec; +} + +void do_gettimeofday(struct timeval *tv) +{ + if (__USE_RTC()) { + /* do this the old way */ + unsigned long flags, seq; + unsigned int sec, nsec, usec, lost; + + do { + seq = read_seqbegin_irqsave(&xtime_lock, flags); + sec = xtime.tv_sec; + nsec = xtime.tv_nsec + tb_ticks_since(tb_last_stamp); + lost = jiffies - wall_jiffies; + } while (read_seqretry_irqrestore(&xtime_lock, seq, flags)); + usec = nsec / 1000 + lost * (1000000 / HZ); + while (usec >= 1000000) { + usec -= 1000000; + ++sec; + } + tv->tv_sec = sec; + tv->tv_usec = usec; + return; + } + __do_gettimeofday(tv, get_tb()); +} + +EXPORT_SYMBOL(do_gettimeofday); + +/* Synchronize xtime with do_gettimeofday */ + +static inline void timer_sync_xtime(unsigned long cur_tb) +{ +#ifdef CONFIG_PPC64 + /* why do we do this? */ + struct timeval my_tv; + + __do_gettimeofday(&my_tv, cur_tb); + + if (xtime.tv_sec <= my_tv.tv_sec) { + xtime.tv_sec = my_tv.tv_sec; + xtime.tv_nsec = my_tv.tv_usec * 1000; + } +#endif +} + +/* + * There are two copies of tb_to_xs and stamp_xsec so that no + * lock is needed to access and use these values in + * do_gettimeofday. We alternate the copies and as long as a + * reasonable time elapses between changes, there will never + * be inconsistent values. ntpd has a minimum of one minute + * between updates. + */ +static inline void update_gtod(u64 new_tb_stamp, u64 new_stamp_xsec, + u64 new_tb_to_xs) +{ + unsigned temp_idx; + struct gettimeofday_vars *temp_varp; + + temp_idx = (do_gtod.var_idx == 0); + temp_varp = &do_gtod.vars[temp_idx]; + + temp_varp->tb_to_xs = new_tb_to_xs; + temp_varp->tb_orig_stamp = new_tb_stamp; + temp_varp->stamp_xsec = new_stamp_xsec; + smp_mb(); + 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 + * stamp_xsec variables. It reads the tb_update_count, then reads + * tb_to_xs and stamp_xsec and then reads tb_update_count again. If + * the two values of tb_update_count match and are even then the + * 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); + smp_wmb(); + systemcfg->tb_orig_stamp = new_tb_stamp; + systemcfg->stamp_xsec = new_stamp_xsec; + systemcfg->tb_to_xs = new_tb_to_xs; + smp_wmb(); + ++(systemcfg->tb_update_count); +#endif +} + +/* + * When the timebase - tb_orig_stamp gets too big, we do a manipulation + * between tb_orig_stamp and stamp_xsec. The goal here is to keep the + * difference tb - tb_orig_stamp small enough to always fit inside a + * 32 bits number. This is a requirement of our fast 32 bits userland + * implementation in the vdso. If we "miss" a call to this function + * (interrupt latency, CPU locked in a spinlock, ...) and we end up + * with a too big difference, then the vdso will fallback to calling + * the syscall + */ +static __inline__ void timer_recalc_offset(u64 cur_tb) +{ + unsigned long offset; + u64 new_stamp_xsec; + + if (__USE_RTC()) + return; + offset = cur_tb - do_gtod.varp->tb_orig_stamp; + if ((offset & 0x80000000u) == 0) + return; + new_stamp_xsec = do_gtod.varp->stamp_xsec + + mulhdu(offset, do_gtod.varp->tb_to_xs); + update_gtod(cur_tb, new_stamp_xsec, do_gtod.varp->tb_to_xs); +} + +#ifdef CONFIG_SMP +unsigned long profile_pc(struct pt_regs *regs) +{ + unsigned long pc = instruction_pointer(regs); + + if (in_lock_functions(pc)) + return regs->link; + + return pc; +} +EXPORT_SYMBOL(profile_pc); +#endif + +#ifdef CONFIG_PPC_ISERIES + +/* + * This function recalibrates the timebase based on the 49-bit time-of-day + * value in the Titan chip. The Titan is much more accurate than the value + * returned by the service processor for the timebase frequency. + */ + +static void iSeries_tb_recal(void) +{ + struct div_result divres; + unsigned long titan, tb; + tb = get_tb(); + titan = HvCallXm_loadTod(); + if ( iSeries_recal_titan ) { + unsigned long tb_ticks = tb - iSeries_recal_tb; + unsigned long titan_usec = (titan - iSeries_recal_titan) >> 12; + unsigned long new_tb_ticks_per_sec = (tb_ticks * USEC_PER_SEC)/titan_usec; + unsigned long new_tb_ticks_per_jiffy = (new_tb_ticks_per_sec+(HZ/2))/HZ; + long tick_diff = new_tb_ticks_per_jiffy - tb_ticks_per_jiffy; + char sign = '+'; + /* make sure tb_ticks_per_sec and tb_ticks_per_jiffy are consistent */ + new_tb_ticks_per_sec = new_tb_ticks_per_jiffy * HZ; + + if ( tick_diff < 0 ) { + tick_diff = -tick_diff; + sign = '-'; + } + if ( tick_diff ) { + if ( tick_diff < tb_ticks_per_jiffy/25 ) { + printk( "Titan recalibrate: new tb_ticks_per_jiffy = %lu (%c%ld)\n", + new_tb_ticks_per_jiffy, sign, tick_diff ); + tb_ticks_per_jiffy = new_tb_ticks_per_jiffy; + tb_ticks_per_sec = new_tb_ticks_per_sec; + div128_by_32( XSEC_PER_SEC, 0, tb_ticks_per_sec, &divres ); + 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; + } + else { + printk( "Titan recalibrate: FAILED (difference > 4 percent)\n" + " new tb_ticks_per_jiffy = %lu\n" + " old tb_ticks_per_jiffy = %lu\n", + new_tb_ticks_per_jiffy, tb_ticks_per_jiffy ); + } + } + } + iSeries_recal_titan = titan; + iSeries_recal_tb = tb; +} +#endif + +/* + * For iSeries shared processors, we have to let the hypervisor + * set the hardware decrementer. We set a virtual decrementer + * in the lppaca and call the hypervisor if the virtual + * decrementer is less than the current value in the hardware + * decrementer. (almost always the new decrementer value will + * be greater than the current hardware decementer so the hypervisor + * call will not be needed) + */ + +/* + * timer_interrupt - gets called when the decrementer overflows, + * with interrupts disabled. + */ +void timer_interrupt(struct pt_regs * regs) +{ + int next_dec; + int cpu = smp_processor_id(); + unsigned long ticks; + +#ifdef CONFIG_PPC32 + if (atomic_read(&ppc_n_lost_interrupts) != 0) + do_IRQ(regs); +#endif + + irq_enter(); + + profile_tick(CPU_PROFILING, regs); + +#ifdef CONFIG_PPC_ISERIES + get_paca()->lppaca.int_dword.fields.decr_int = 0; +#endif + + while ((ticks = tb_ticks_since(per_cpu(last_jiffy, cpu))) + >= tb_ticks_per_jiffy) { + /* Update last_jiffy */ + per_cpu(last_jiffy, cpu) += tb_ticks_per_jiffy; + /* Handle RTCL overflow on 601 */ + if (__USE_RTC() && per_cpu(last_jiffy, cpu) >= 1000000000) + per_cpu(last_jiffy, cpu) -= 1000000000; + + /* + * We cannot disable the decrementer, so in the period + * between this cpu's being marked offline in cpu_online_map + * and calling stop-self, it is taking timer interrupts. + * Avoid calling into the scheduler rebalancing code if this + * is the case. + */ + if (!cpu_is_offline(cpu)) + update_process_times(user_mode(regs)); + + /* + * No need to check whether cpu is offline here; boot_cpuid + * should have been fixed up by now. + */ + if (cpu != boot_cpuid) + continue; + + write_seqlock(&xtime_lock); + tb_last_jiffy += tb_ticks_per_jiffy; + tb_last_stamp = per_cpu(last_jiffy, cpu); + timer_recalc_offset(tb_last_jiffy); + do_timer(regs); + timer_sync_xtime(tb_last_jiffy); + timer_check_rtc(); + write_sequnlock(&xtime_lock); + if (adjusting_time && (time_adjust == 0)) + ppc_adjtimex(); + } + + next_dec = tb_ticks_per_jiffy - ticks; + set_dec(next_dec); + +#ifdef CONFIG_PPC_ISERIES + if (hvlpevent_is_pending()) + process_hvlpevents(regs); +#endif + +#ifdef CONFIG_PPC64 + /* collect purr register values often, for accurate calculations */ + if (firmware_has_feature(FW_FEATURE_SPLPAR)) { + struct cpu_usage *cu = &__get_cpu_var(cpu_usage_array); + cu->current_tb = mfspr(SPRN_PURR); + } +#endif + + irq_exit(); +} + +void wakeup_decrementer(void) +{ + int i; + + set_dec(tb_ticks_per_jiffy); + /* + * We don't expect this to be called on a machine with a 601, + * so using get_tbl is fine. + */ + tb_last_stamp = tb_last_jiffy = get_tb(); + for_each_cpu(i) + per_cpu(last_jiffy, i) = tb_last_stamp; +} + +#ifdef CONFIG_SMP +void __init smp_space_timers(unsigned int max_cpus) +{ + int i; + unsigned long offset = tb_ticks_per_jiffy / max_cpus; + unsigned long previous_tb = per_cpu(last_jiffy, boot_cpuid); + + for_each_cpu(i) { + if (i != boot_cpuid) { + previous_tb += offset; + per_cpu(last_jiffy, i) = previous_tb; + } + } +} +#endif + +/* + * Scheduler clock - returns current time in nanosec units. + * + * Note: mulhdu(a, b) (multiply high double unsigned) returns + * the high 64 bits of a * b, i.e. (a * b) >> 64, where a and b + * are 64-bit unsigned numbers. + */ +unsigned long long sched_clock(void) +{ + if (__USE_RTC()) + return get_rtc(); + return mulhdu(get_tb(), tb_to_ns_scale) << tb_to_ns_shift; +} + +int do_settimeofday(struct timespec *tv) +{ + time_t wtm_sec, new_sec = tv->tv_sec; + long wtm_nsec, new_nsec = tv->tv_nsec; + unsigned long flags; + long int tb_delta; + u64 new_xsec, tb_delta_xs; + + if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC) + return -EINVAL; + + write_seqlock_irqsave(&xtime_lock, flags); + + /* + * Updating the RTC is not the job of this code. If the time is + * stepped under NTP, the RTC will be updated after STA_UNSYNC + * is cleared. Tools like clock/hwclock either copy the RTC + * to the system time, in which case there is no point in writing + * to the RTC again, or write to the RTC but then they don't call + * settimeofday to perform this operation. + */ +#ifdef CONFIG_PPC_ISERIES + if (first_settimeofday) { + iSeries_tb_recal(); + first_settimeofday = 0; + } +#endif + tb_delta = tb_ticks_since(tb_last_stamp); + tb_delta += (jiffies - wall_jiffies) * tb_ticks_per_jiffy; + tb_delta_xs = mulhdu(tb_delta, do_gtod.varp->tb_to_xs); + + wtm_sec = wall_to_monotonic.tv_sec + (xtime.tv_sec - new_sec); + wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - new_nsec); + + set_normalized_timespec(&xtime, new_sec, new_nsec); + set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec); + + /* In case of a large backwards jump in time with NTP, we want the + * clock to be updated as soon as the PLL is again in lock. + */ + last_rtc_update = new_sec - 658; + + ntp_clear(); + + new_xsec = 0; + if (new_nsec != 0) { + new_xsec = (u64)new_nsec * XSEC_PER_SEC; + do_div(new_xsec, NSEC_PER_SEC); + } + 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 + + write_sequnlock_irqrestore(&xtime_lock, flags); + clock_was_set(); + return 0; +} + +EXPORT_SYMBOL(do_settimeofday); + +void __init generic_calibrate_decr(void) +{ + struct device_node *cpu; + unsigned int *fp; + int node_found; + + /* + * The cpu node should have a timebase-frequency property + * to tell us the rate at which the decrementer counts. + */ + cpu = of_find_node_by_type(NULL, "cpu"); + + ppc_tb_freq = DEFAULT_TB_FREQ; /* hardcoded default */ + node_found = 0; + if (cpu != 0) { + fp = (unsigned int *)get_property(cpu, "timebase-frequency", + NULL); + if (fp != 0) { + node_found = 1; + ppc_tb_freq = *fp; + } + } + if (!node_found) + printk(KERN_ERR "WARNING: Estimating decrementer frequency " + "(not found)\n"); + + ppc_proc_freq = DEFAULT_PROC_FREQ; + node_found = 0; + if (cpu != 0) { + fp = (unsigned int *)get_property(cpu, "clock-frequency", + NULL); + if (fp != 0) { + node_found = 1; + ppc_proc_freq = *fp; + } + } +#ifdef CONFIG_BOOKE + /* Set the time base to zero */ + mtspr(SPRN_TBWL, 0); + mtspr(SPRN_TBWU, 0); + + /* Clear any pending timer interrupts */ + mtspr(SPRN_TSR, TSR_ENW | TSR_WIS | TSR_DIS | TSR_FIS); + + /* Enable decrementer interrupt */ + mtspr(SPRN_TCR, TCR_DIE); +#endif + if (!node_found) + printk(KERN_ERR "WARNING: Estimating processor frequency " + "(not found)\n"); + + of_node_put(cpu); +} + +unsigned long get_boot_time(void) +{ + struct rtc_time tm; + + if (ppc_md.get_boot_time) + return ppc_md.get_boot_time(); + if (!ppc_md.get_rtc_time) + return 0; + ppc_md.get_rtc_time(&tm); + return mktime(tm.tm_year+1900, tm.tm_mon+1, tm.tm_mday, + tm.tm_hour, tm.tm_min, tm.tm_sec); +} + +/* This function is only called on the boot processor */ +void __init time_init(void) +{ + unsigned long flags; + unsigned long tm = 0; + struct div_result res; + u64 scale; + unsigned shift; + + if (ppc_md.time_init != NULL) + timezone_offset = ppc_md.time_init(); + + if (__USE_RTC()) { + /* 601 processor: dec counts down by 128 every 128ns */ + ppc_tb_freq = 1000000000; + tb_last_stamp = get_rtcl(); + tb_last_jiffy = tb_last_stamp; + } else { + /* Normal PowerPC with timebase register */ + ppc_md.calibrate_decr(); + printk(KERN_INFO "time_init: decrementer frequency = %lu.%.6lu MHz\n", + ppc_tb_freq / 1000000, ppc_tb_freq % 1000000); + printk(KERN_INFO "time_init: processor frequency = %lu.%.6lu MHz\n", + ppc_proc_freq / 1000000, ppc_proc_freq % 1000000); + tb_last_stamp = tb_last_jiffy = get_tb(); + } + + tb_ticks_per_jiffy = ppc_tb_freq / HZ; + tb_ticks_per_sec = tb_ticks_per_jiffy * HZ; + tb_ticks_per_usec = ppc_tb_freq / 1000000; + tb_to_us = mulhwu_scale_factor(ppc_tb_freq, 1000000); + div128_by_32(1024*1024, 0, tb_ticks_per_sec, &res); + tb_to_xs = res.result_low; + +#ifdef CONFIG_PPC64 + get_paca()->default_decr = tb_ticks_per_jiffy; +#endif + + /* + * Compute scale factor for sched_clock. + * The calibrate_decr() function has set tb_ticks_per_sec, + * which is the timebase frequency. + * We compute 1e9 * 2^64 / tb_ticks_per_sec and interpret + * the 128-bit result as a 64.64 fixed-point number. + * We then shift that number right until it is less than 1.0, + * giving us the scale factor and shift count to use in + * sched_clock(). + */ + div128_by_32(1000000000, 0, tb_ticks_per_sec, &res); + scale = res.result_low; + for (shift = 0; res.result_high != 0; ++shift) { + scale = (scale >> 1) | (res.result_high << 63); + res.result_high >>= 1; + } + tb_to_ns_scale = scale; + tb_to_ns_shift = shift; + +#ifdef CONFIG_PPC_ISERIES + if (!piranha_simulator) +#endif + tm = get_boot_time(); + + write_seqlock_irqsave(&xtime_lock, flags); + xtime.tv_sec = tm; + xtime.tv_nsec = 0; + do_gtod.varp = &do_gtod.vars[0]; + do_gtod.var_idx = 0; + do_gtod.varp->tb_orig_stamp = tb_last_jiffy; + __get_cpu_var(last_jiffy) = tb_last_stamp; + do_gtod.varp->stamp_xsec = (u64) xtime.tv_sec * XSEC_PER_SEC; + 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 + + time_freq = 0; + + /* If platform provided a timezone (pmac), we correct the time */ + if (timezone_offset) { + sys_tz.tz_minuteswest = -timezone_offset / 60; + sys_tz.tz_dsttime = 0; + xtime.tv_sec -= timezone_offset; + } + + last_rtc_update = xtime.tv_sec; + set_normalized_timespec(&wall_to_monotonic, + -xtime.tv_sec, -xtime.tv_nsec); + write_sequnlock_irqrestore(&xtime_lock, flags); + + /* Not exact, but the timer interrupt takes care of this */ + set_dec(tb_ticks_per_jiffy); +} + +/* + * After adjtimex is called, adjust the conversion of tb ticks + * to microseconds to keep do_gettimeofday synchronized + * with ntpd. + * + * Use the time_adjust, time_freq and time_offset computed by adjtimex to + * adjust the frequency. + */ + +/* #define DEBUG_PPC_ADJTIMEX 1 */ + +void ppc_adjtimex(void) +{ +#ifdef CONFIG_PPC64 + unsigned long den, new_tb_ticks_per_sec, tb_ticks, old_xsec, + new_tb_to_xs, new_xsec, new_stamp_xsec; + unsigned long tb_ticks_per_sec_delta; + long delta_freq, ltemp; + struct div_result divres; + unsigned long flags; + long singleshot_ppm = 0; + + /* + * Compute parts per million frequency adjustment to + * accomplish the time adjustment implied by time_offset to be + * applied over the elapsed time indicated by time_constant. + * Use SHIFT_USEC to get it into the same units as + * time_freq. + */ + if ( time_offset < 0 ) { + ltemp = -time_offset; + ltemp <<= SHIFT_USEC - SHIFT_UPDATE; + ltemp >>= SHIFT_KG + time_constant; + ltemp = -ltemp; + } else { + ltemp = time_offset; + ltemp <<= SHIFT_USEC - SHIFT_UPDATE; + ltemp >>= SHIFT_KG + time_constant; + } + + /* If there is a single shot time adjustment in progress */ + if ( time_adjust ) { +#ifdef DEBUG_PPC_ADJTIMEX + printk("ppc_adjtimex: "); + if ( adjusting_time == 0 ) + printk("starting "); + printk("single shot time_adjust = %ld\n", time_adjust); +#endif + + adjusting_time = 1; + + /* + * Compute parts per million frequency adjustment + * to match time_adjust + */ + singleshot_ppm = tickadj * HZ; + /* + * The adjustment should be tickadj*HZ to match the code in + * linux/kernel/timer.c, but experiments show that this is too + * large. 3/4 of tickadj*HZ seems about right + */ + singleshot_ppm -= singleshot_ppm / 4; + /* Use SHIFT_USEC to get it into the same units as time_freq */ + singleshot_ppm <<= SHIFT_USEC; + if ( time_adjust < 0 ) + singleshot_ppm = -singleshot_ppm; + } + else { +#ifdef DEBUG_PPC_ADJTIMEX + if ( adjusting_time ) + printk("ppc_adjtimex: ending single shot time_adjust\n"); +#endif + adjusting_time = 0; + } + + /* Add up all of the frequency adjustments */ + delta_freq = time_freq + ltemp + singleshot_ppm; + + /* + * Compute a new value for tb_ticks_per_sec based on + * the frequency adjustment + */ + den = 1000000 * (1 << (SHIFT_USEC - 8)); + if ( delta_freq < 0 ) { + tb_ticks_per_sec_delta = ( tb_ticks_per_sec * ( (-delta_freq) >> (SHIFT_USEC - 8))) / den; + new_tb_ticks_per_sec = tb_ticks_per_sec + tb_ticks_per_sec_delta; + } + else { + tb_ticks_per_sec_delta = ( tb_ticks_per_sec * ( delta_freq >> (SHIFT_USEC - 8))) / den; + new_tb_ticks_per_sec = tb_ticks_per_sec - tb_ticks_per_sec_delta; + } + +#ifdef DEBUG_PPC_ADJTIMEX + printk("ppc_adjtimex: ltemp = %ld, time_freq = %ld, singleshot_ppm = %ld\n", ltemp, time_freq, singleshot_ppm); + printk("ppc_adjtimex: tb_ticks_per_sec - base = %ld new = %ld\n", tb_ticks_per_sec, new_tb_ticks_per_sec); +#endif + + /* + * Compute a new value of tb_to_xs (used to convert tb to + * microseconds) and a new value of stamp_xsec which is the + * time (in 1/2^20 second units) corresponding to + * tb_orig_stamp. This new value of stamp_xsec compensates + * for the change in frequency (implied by the new tb_to_xs) + * which guarantees that the current time remains the same. + */ + write_seqlock_irqsave( &xtime_lock, flags ); + tb_ticks = get_tb() - do_gtod.varp->tb_orig_stamp; + div128_by_32(1024*1024, 0, new_tb_ticks_per_sec, &divres); + new_tb_to_xs = divres.result_low; + new_xsec = mulhdu(tb_ticks, new_tb_to_xs); + + old_xsec = mulhdu(tb_ticks, do_gtod.varp->tb_to_xs); + new_stamp_xsec = do_gtod.varp->stamp_xsec + old_xsec - new_xsec; + + update_gtod(do_gtod.varp->tb_orig_stamp, new_stamp_xsec, new_tb_to_xs); + + write_sequnlock_irqrestore( &xtime_lock, flags ); +#endif /* CONFIG_PPC64 */ +} + + +#define FEBRUARY 2 +#define STARTOFTIME 1970 +#define SECDAY 86400L +#define SECYR (SECDAY * 365) +#define leapyear(year) ((year) % 4 == 0 && \ + ((year) % 100 != 0 || (year) % 400 == 0)) +#define days_in_year(a) (leapyear(a) ? 366 : 365) +#define days_in_month(a) (month_days[(a) - 1]) + +static int month_days[12] = { + 31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31 +}; + +/* + * This only works for the Gregorian calendar - i.e. after 1752 (in the UK) + */ +void GregorianDay(struct rtc_time * tm) +{ + int leapsToDate; + int lastYear; + int day; + int MonthOffset[] = { 0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334 }; + + lastYear = tm->tm_year - 1; + + /* + * Number of leap corrections to apply up to end of last year + */ + leapsToDate = lastYear / 4 - lastYear / 100 + lastYear / 400; + + /* + * This year is a leap year if it is divisible by 4 except when it is + * divisible by 100 unless it is divisible by 400 + * + * e.g. 1904 was a leap year, 1900 was not, 1996 is, and 2000 was + */ + day = tm->tm_mon > 2 && leapyear(tm->tm_year); + + day += lastYear*365 + leapsToDate + MonthOffset[tm->tm_mon-1] + + tm->tm_mday; + + tm->tm_wday = day % 7; +} + +void to_tm(int tim, struct rtc_time * tm) +{ + register int i; + register long hms, day; + + day = tim / SECDAY; + hms = tim % SECDAY; + + /* Hours, minutes, seconds are easy */ + tm->tm_hour = hms / 3600; + tm->tm_min = (hms % 3600) / 60; + tm->tm_sec = (hms % 3600) % 60; + + /* Number of years in days */ + for (i = STARTOFTIME; day >= days_in_year(i); i++) + day -= days_in_year(i); + tm->tm_year = i; + + /* Number of months in days left */ + if (leapyear(tm->tm_year)) + days_in_month(FEBRUARY) = 29; + for (i = 1; day >= days_in_month(i); i++) + day -= days_in_month(i); + days_in_month(FEBRUARY) = 28; + tm->tm_mon = i; + + /* Days are what is left over (+1) from all that. */ + tm->tm_mday = day + 1; + + /* + * Determine the day of week + */ + GregorianDay(tm); +} + +/* Auxiliary function to compute scaling factors */ +/* Actually the choice of a timebase running at 1/4 the of the bus + * frequency giving resolution of a few tens of nanoseconds is quite nice. + * It makes this computation very precise (27-28 bits typically) which + * is optimistic considering the stability of most processor clock + * oscillators and the precision with which the timebase frequency + * is measured but does not harm. + */ +unsigned mulhwu_scale_factor(unsigned inscale, unsigned outscale) +{ + unsigned mlt=0, tmp, err; + /* No concern for performance, it's done once: use a stupid + * but safe and compact method to find the multiplier. + */ + + for (tmp = 1U<<31; tmp != 0; tmp >>= 1) { + if (mulhwu(inscale, mlt|tmp) < outscale) + mlt |= tmp; + } + + /* We might still be off by 1 for the best approximation. + * A side effect of this is that if outscale is too large + * the returned value will be zero. + * Many corner cases have been checked and seem to work, + * some might have been forgotten in the test however. + */ + + err = inscale * (mlt+1); + if (err <= inscale/2) + mlt++; + return mlt; +} + +/* + * Divide a 128-bit dividend by a 32-bit divisor, leaving a 128 bit + * result. + */ +void div128_by_32(u64 dividend_high, u64 dividend_low, + unsigned divisor, struct div_result *dr) +{ + unsigned long a, b, c, d; + unsigned long w, x, y, z; + u64 ra, rb, rc; + + a = dividend_high >> 32; + b = dividend_high & 0xffffffff; + c = dividend_low >> 32; + d = dividend_low & 0xffffffff; + + w = a / divisor; + ra = ((u64)(a - (w * divisor)) << 32) + b; + + rb = ((u64) do_div(ra, divisor) << 32) + c; + x = ra; + + rc = ((u64) do_div(rb, divisor) << 32) + d; + y = rb; + + do_div(rc, divisor); + z = rc; + + dr->result_high = ((u64)w << 32) + x; + dr->result_low = ((u64)y << 32) + z; + +} diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c new file mode 100644 index 000000000000..5d638ecddbd0 --- /dev/null +++ b/arch/powerpc/kernel/traps.c @@ -0,0 +1,1101 @@ +/* + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.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. + * + * Modified by Cort Dougan (cort@cs.nmt.edu) + * and Paul Mackerras (paulus@samba.org) + */ + +/* + * This file handles the architecture-dependent parts of hardware exceptions + */ + +#include <linux/config.h> +#include <linux/errno.h> +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/stddef.h> +#include <linux/unistd.h> +#include <linux/ptrace.h> +#include <linux/slab.h> +#include <linux/user.h> +#include <linux/a.out.h> +#include <linux/interrupt.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/prctl.h> +#include <linux/delay.h> +#include <linux/kprobes.h> + +#include <asm/kdebug.h> +#include <asm/pgtable.h> +#include <asm/uaccess.h> +#include <asm/system.h> +#include <asm/io.h> +#include <asm/machdep.h> +#include <asm/rtas.h> +#include <asm/xmon.h> +#include <asm/pmc.h> +#ifdef CONFIG_PPC32 +#include <asm/reg.h> +#endif +#ifdef CONFIG_PMAC_BACKLIGHT +#include <asm/backlight.h> +#endif +#ifdef CONFIG_PPC64 +#include <asm/firmware.h> +#include <asm/processor.h> +#include <asm/systemcfg.h> +#endif + +#ifdef CONFIG_PPC64 /* XXX */ +#define _IO_BASE pci_io_base +#endif + +#ifdef CONFIG_DEBUGGER +int (*__debugger)(struct pt_regs *regs); +int (*__debugger_ipi)(struct pt_regs *regs); +int (*__debugger_bpt)(struct pt_regs *regs); +int (*__debugger_sstep)(struct pt_regs *regs); +int (*__debugger_iabr_match)(struct pt_regs *regs); +int (*__debugger_dabr_match)(struct pt_regs *regs); +int (*__debugger_fault_handler)(struct pt_regs *regs); + +EXPORT_SYMBOL(__debugger); +EXPORT_SYMBOL(__debugger_ipi); +EXPORT_SYMBOL(__debugger_bpt); +EXPORT_SYMBOL(__debugger_sstep); +EXPORT_SYMBOL(__debugger_iabr_match); +EXPORT_SYMBOL(__debugger_dabr_match); +EXPORT_SYMBOL(__debugger_fault_handler); +#endif + +struct notifier_block *powerpc_die_chain; +static DEFINE_SPINLOCK(die_notifier_lock); + +int register_die_notifier(struct notifier_block *nb) +{ + int err = 0; + unsigned long flags; + + spin_lock_irqsave(&die_notifier_lock, flags); + err = notifier_chain_register(&powerpc_die_chain, nb); + spin_unlock_irqrestore(&die_notifier_lock, flags); + return err; +} + +/* + * Trap & Exception support + */ + +static DEFINE_SPINLOCK(die_lock); + +int die(const char *str, struct pt_regs *regs, long err) +{ + static int die_counter; + int nl = 0; + + if (debugger(regs)) + return 1; + + console_verbose(); + spin_lock_irq(&die_lock); + bust_spinlocks(1); +#ifdef CONFIG_PMAC_BACKLIGHT + if (_machine == _MACH_Pmac) { + set_backlight_enable(1); + set_backlight_level(BACKLIGHT_MAX); + } +#endif + printk("Oops: %s, sig: %ld [#%d]\n", str, err, ++die_counter); +#ifdef CONFIG_PREEMPT + printk("PREEMPT "); + nl = 1; +#endif +#ifdef CONFIG_SMP + printk("SMP NR_CPUS=%d ", NR_CPUS); + nl = 1; +#endif +#ifdef CONFIG_DEBUG_PAGEALLOC + printk("DEBUG_PAGEALLOC "); + nl = 1; +#endif +#ifdef CONFIG_NUMA + printk("NUMA "); + nl = 1; +#endif +#ifdef CONFIG_PPC64 + switch (systemcfg->platform) { + case PLATFORM_PSERIES: + printk("PSERIES "); + nl = 1; + break; + case PLATFORM_PSERIES_LPAR: + printk("PSERIES LPAR "); + nl = 1; + break; + case PLATFORM_ISERIES_LPAR: + printk("ISERIES LPAR "); + nl = 1; + break; + case PLATFORM_POWERMAC: + printk("POWERMAC "); + nl = 1; + break; + case PLATFORM_BPA: + printk("BPA "); + nl = 1; + break; + } +#endif + if (nl) + printk("\n"); + print_modules(); + show_regs(regs); + bust_spinlocks(0); + spin_unlock_irq(&die_lock); + + if (in_interrupt()) + panic("Fatal exception in interrupt"); + + if (panic_on_oops) { +#ifdef CONFIG_PPC64 + printk(KERN_EMERG "Fatal exception: panic in 5 seconds\n"); + ssleep(5); +#endif + panic("Fatal exception"); + } + do_exit(err); + + return 0; +} + +void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr) +{ + siginfo_t info; + + if (!user_mode(regs)) { + if (die("Exception in kernel mode", regs, signr)) + return; + } + + memset(&info, 0, sizeof(info)); + info.si_signo = signr; + info.si_code = code; + info.si_addr = (void __user *) addr; + force_sig_info(signr, &info, current); + + /* + * Init gets no signals that it doesn't have a handler for. + * That's all very well, but if it has caused a synchronous + * exception and we ignore the resulting signal, it will just + * generate the same exception over and over again and we get + * nowhere. Better to kill it and let the kernel panic. + */ + if (current->pid == 1) { + __sighandler_t handler; + + spin_lock_irq(¤t->sighand->siglock); + handler = current->sighand->action[signr-1].sa.sa_handler; + spin_unlock_irq(¤t->sighand->siglock); + if (handler == SIG_DFL) { + /* init has generated a synchronous exception + and it doesn't have a handler for the signal */ + printk(KERN_CRIT "init has generated signal %d " + "but has no handler for it\n", signr); + do_exit(signr); + } + } +} + +#ifdef CONFIG_PPC64 +void system_reset_exception(struct pt_regs *regs) +{ + /* See if any machine dependent calls */ + if (ppc_md.system_reset_exception) + ppc_md.system_reset_exception(regs); + + die("System Reset", regs, SIGABRT); + + /* Must die if the interrupt is not recoverable */ + if (!(regs->msr & MSR_RI)) + panic("Unrecoverable System Reset"); + + /* What should we do here? We could issue a shutdown or hard reset. */ +} +#endif + +/* + * I/O accesses can cause machine checks on powermacs. + * Check if the NIP corresponds to the address of a sync + * instruction for which there is an entry in the exception + * table. + * Note that the 601 only takes a machine check on TEA + * (transfer error ack) signal assertion, and does not + * set any of the top 16 bits of SRR1. + * -- paulus. + */ +static inline int check_io_access(struct pt_regs *regs) +{ +#ifdef CONFIG_PPC_PMAC + unsigned long msr = regs->msr; + const struct exception_table_entry *entry; + unsigned int *nip = (unsigned int *)regs->nip; + + if (((msr & 0xffff0000) == 0 || (msr & (0x80000 | 0x40000))) + && (entry = search_exception_tables(regs->nip)) != NULL) { + /* + * Check that it's a sync instruction, or somewhere + * in the twi; isync; nop sequence that inb/inw/inl uses. + * As the address is in the exception table + * we should be able to read the instr there. + * For the debug message, we look at the preceding + * load or store. + */ + if (*nip == 0x60000000) /* nop */ + nip -= 2; + else if (*nip == 0x4c00012c) /* isync */ + --nip; + if (*nip == 0x7c0004ac || (*nip >> 26) == 3) { + /* sync or twi */ + unsigned int rb; + + --nip; + rb = (*nip >> 11) & 0x1f; + printk(KERN_DEBUG "%s bad port %lx at %p\n", + (*nip & 0x100)? "OUT to": "IN from", + regs->gpr[rb] - _IO_BASE, nip); + regs->msr |= MSR_RI; + regs->nip = entry->fixup; + return 1; + } + } +#endif /* CONFIG_PPC_PMAC */ + return 0; +} + +#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE) +/* On 4xx, the reason for the machine check or program exception + is in the ESR. */ +#define get_reason(regs) ((regs)->dsisr) +#ifndef CONFIG_FSL_BOOKE +#define get_mc_reason(regs) ((regs)->dsisr) +#else +#define get_mc_reason(regs) (mfspr(SPRN_MCSR)) +#endif +#define REASON_FP ESR_FP +#define REASON_ILLEGAL (ESR_PIL | ESR_PUO) +#define REASON_PRIVILEGED ESR_PPR +#define REASON_TRAP ESR_PTR + +/* single-step stuff */ +#define single_stepping(regs) (current->thread.dbcr0 & DBCR0_IC) +#define clear_single_step(regs) (current->thread.dbcr0 &= ~DBCR0_IC) + +#else +/* On non-4xx, the reason for the machine check or program + exception is in the MSR. */ +#define get_reason(regs) ((regs)->msr) +#define get_mc_reason(regs) ((regs)->msr) +#define REASON_FP 0x100000 +#define REASON_ILLEGAL 0x80000 +#define REASON_PRIVILEGED 0x40000 +#define REASON_TRAP 0x20000 + +#define single_stepping(regs) ((regs)->msr & MSR_SE) +#define clear_single_step(regs) ((regs)->msr &= ~MSR_SE) +#endif + +/* + * This is "fall-back" implementation for configurations + * which don't provide platform-specific machine check info + */ +void __attribute__ ((weak)) +platform_machine_check(struct pt_regs *regs) +{ +} + +void machine_check_exception(struct pt_regs *regs) +{ +#ifdef CONFIG_PPC64 + int recover = 0; + + /* See if any machine dependent calls */ + if (ppc_md.machine_check_exception) + recover = ppc_md.machine_check_exception(regs); + + if (recover) + return; +#else + unsigned long reason = get_mc_reason(regs); + + if (user_mode(regs)) { + regs->msr |= MSR_RI; + _exception(SIGBUS, regs, BUS_ADRERR, regs->nip); + return; + } + +#if defined(CONFIG_8xx) && defined(CONFIG_PCI) + /* the qspan pci read routines can cause machine checks -- Cort */ + bad_page_fault(regs, regs->dar, SIGBUS); + return; +#endif + + if (debugger_fault_handler(regs)) { + regs->msr |= MSR_RI; + return; + } + + if (check_io_access(regs)) + return; + +#if defined(CONFIG_4xx) && !defined(CONFIG_440A) + if (reason & ESR_IMCP) { + printk("Instruction"); + mtspr(SPRN_ESR, reason & ~ESR_IMCP); + } else + printk("Data"); + printk(" machine check in kernel mode.\n"); +#elif defined(CONFIG_440A) + printk("Machine check in kernel mode.\n"); + if (reason & ESR_IMCP){ + printk("Instruction Synchronous Machine Check exception\n"); + mtspr(SPRN_ESR, reason & ~ESR_IMCP); + } + else { + u32 mcsr = mfspr(SPRN_MCSR); + if (mcsr & MCSR_IB) + printk("Instruction Read PLB Error\n"); + if (mcsr & MCSR_DRB) + printk("Data Read PLB Error\n"); + if (mcsr & MCSR_DWB) + printk("Data Write PLB Error\n"); + if (mcsr & MCSR_TLBP) + printk("TLB Parity Error\n"); + if (mcsr & MCSR_ICP){ + flush_instruction_cache(); + printk("I-Cache Parity Error\n"); + } + if (mcsr & MCSR_DCSP) + printk("D-Cache Search Parity Error\n"); + if (mcsr & MCSR_DCFP) + printk("D-Cache Flush Parity Error\n"); + if (mcsr & MCSR_IMPE) + printk("Machine Check exception is imprecise\n"); + + /* Clear MCSR */ + mtspr(SPRN_MCSR, mcsr); + } +#elif defined (CONFIG_E500) + printk("Machine check in kernel mode.\n"); + printk("Caused by (from MCSR=%lx): ", reason); + + if (reason & MCSR_MCP) + printk("Machine Check Signal\n"); + if (reason & MCSR_ICPERR) + printk("Instruction Cache Parity Error\n"); + if (reason & MCSR_DCP_PERR) + printk("Data Cache Push Parity Error\n"); + if (reason & MCSR_DCPERR) + printk("Data Cache Parity Error\n"); + if (reason & MCSR_GL_CI) + printk("Guarded Load or Cache-Inhibited stwcx.\n"); + if (reason & MCSR_BUS_IAERR) + printk("Bus - Instruction Address Error\n"); + if (reason & MCSR_BUS_RAERR) + printk("Bus - Read Address Error\n"); + if (reason & MCSR_BUS_WAERR) + printk("Bus - Write Address Error\n"); + if (reason & MCSR_BUS_IBERR) + printk("Bus - Instruction Data Error\n"); + if (reason & MCSR_BUS_RBERR) + printk("Bus - Read Data Bus Error\n"); + if (reason & MCSR_BUS_WBERR) + printk("Bus - Read Data Bus Error\n"); + if (reason & MCSR_BUS_IPERR) + printk("Bus - Instruction Parity Error\n"); + if (reason & MCSR_BUS_RPERR) + printk("Bus - Read Parity Error\n"); +#elif defined (CONFIG_E200) + printk("Machine check in kernel mode.\n"); + printk("Caused by (from MCSR=%lx): ", reason); + + if (reason & MCSR_MCP) + printk("Machine Check Signal\n"); + if (reason & MCSR_CP_PERR) + printk("Cache Push Parity Error\n"); + if (reason & MCSR_CPERR) + printk("Cache Parity Error\n"); + if (reason & MCSR_EXCP_ERR) + printk("ISI, ITLB, or Bus Error on first instruction fetch for an exception handler\n"); + if (reason & MCSR_BUS_IRERR) + printk("Bus - Read Bus Error on instruction fetch\n"); + if (reason & MCSR_BUS_DRERR) + printk("Bus - Read Bus Error on data load\n"); + if (reason & MCSR_BUS_WRERR) + printk("Bus - Write Bus Error on buffered store or cache line push\n"); +#else /* !CONFIG_4xx && !CONFIG_E500 && !CONFIG_E200 */ + printk("Machine check in kernel mode.\n"); + printk("Caused by (from SRR1=%lx): ", reason); + switch (reason & 0x601F0000) { + case 0x80000: + printk("Machine check signal\n"); + break; + case 0: /* for 601 */ + case 0x40000: + case 0x140000: /* 7450 MSS error and TEA */ + printk("Transfer error ack signal\n"); + break; + case 0x20000: + printk("Data parity error signal\n"); + break; + case 0x10000: + printk("Address parity error signal\n"); + break; + case 0x20000000: + printk("L1 Data Cache error\n"); + break; + case 0x40000000: + printk("L1 Instruction Cache error\n"); + break; + case 0x00100000: + printk("L2 data cache parity error\n"); + break; + default: + printk("Unknown values in msr\n"); + } +#endif /* CONFIG_4xx */ + + /* + * Optional platform-provided routine to print out + * additional info, e.g. bus error registers. + */ + platform_machine_check(regs); +#endif /* CONFIG_PPC64 */ + + if (debugger_fault_handler(regs)) + return; + die("Machine check", regs, SIGBUS); + + /* Must die if the interrupt is not recoverable */ + if (!(regs->msr & MSR_RI)) + panic("Unrecoverable Machine check"); +} + +void SMIException(struct pt_regs *regs) +{ + die("System Management Interrupt", regs, SIGABRT); +} + +void unknown_exception(struct pt_regs *regs) +{ + printk("Bad trap at PC: %lx, SR: %lx, vector=%lx\n", + regs->nip, regs->msr, regs->trap); + + _exception(SIGTRAP, regs, 0, 0); +} + +void instruction_breakpoint_exception(struct pt_regs *regs) +{ + if (notify_die(DIE_IABR_MATCH, "iabr_match", regs, 5, + 5, SIGTRAP) == NOTIFY_STOP) + return; + if (debugger_iabr_match(regs)) + return; + _exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip); +} + +void RunModeException(struct pt_regs *regs) +{ + _exception(SIGTRAP, regs, 0, 0); +} + +void __kprobes single_step_exception(struct pt_regs *regs) +{ + regs->msr &= ~(MSR_SE | MSR_BE); /* Turn off 'trace' bits */ + + if (notify_die(DIE_SSTEP, "single_step", regs, 5, + 5, SIGTRAP) == NOTIFY_STOP) + return; + if (debugger_sstep(regs)) + return; + + _exception(SIGTRAP, regs, TRAP_TRACE, regs->nip); +} + +/* + * After we have successfully emulated an instruction, we have to + * check if the instruction was being single-stepped, and if so, + * pretend we got a single-step exception. This was pointed out + * by Kumar Gala. -- paulus + */ +static void emulate_single_step(struct pt_regs *regs) +{ + if (single_stepping(regs)) { + clear_single_step(regs); + _exception(SIGTRAP, regs, TRAP_TRACE, 0); + } +} + +static void parse_fpe(struct pt_regs *regs) +{ + int code = 0; + unsigned long fpscr; + + flush_fp_to_thread(current); + + fpscr = current->thread.fpscr.val; + + /* Invalid operation */ + if ((fpscr & FPSCR_VE) && (fpscr & FPSCR_VX)) + code = FPE_FLTINV; + + /* Overflow */ + else if ((fpscr & FPSCR_OE) && (fpscr & FPSCR_OX)) + code = FPE_FLTOVF; + + /* Underflow */ + else if ((fpscr & FPSCR_UE) && (fpscr & FPSCR_UX)) + code = FPE_FLTUND; + + /* Divide by zero */ + else if ((fpscr & FPSCR_ZE) && (fpscr & FPSCR_ZX)) + code = FPE_FLTDIV; + + /* Inexact result */ + else if ((fpscr & FPSCR_XE) && (fpscr & FPSCR_XX)) + code = FPE_FLTRES; + + _exception(SIGFPE, regs, code, regs->nip); +} + +/* + * Illegal instruction emulation support. Originally written to + * provide the PVR to user applications using the mfspr rd, PVR. + * Return non-zero if we can't emulate, or -EFAULT if the associated + * memory access caused an access fault. Return zero on success. + * + * There are a couple of ways to do this, either "decode" the instruction + * or directly match lots of bits. In this case, matching lots of + * bits is faster and easier. + * + */ +#define INST_MFSPR_PVR 0x7c1f42a6 +#define INST_MFSPR_PVR_MASK 0xfc1fffff + +#define INST_DCBA 0x7c0005ec +#define INST_DCBA_MASK 0x7c0007fe + +#define INST_MCRXR 0x7c000400 +#define INST_MCRXR_MASK 0x7c0007fe + +#define INST_STRING 0x7c00042a +#define INST_STRING_MASK 0x7c0007fe +#define INST_STRING_GEN_MASK 0x7c00067e +#define INST_LSWI 0x7c0004aa +#define INST_LSWX 0x7c00042a +#define INST_STSWI 0x7c0005aa +#define INST_STSWX 0x7c00052a + +static int emulate_string_inst(struct pt_regs *regs, u32 instword) +{ + u8 rT = (instword >> 21) & 0x1f; + u8 rA = (instword >> 16) & 0x1f; + u8 NB_RB = (instword >> 11) & 0x1f; + u32 num_bytes; + unsigned long EA; + int pos = 0; + + /* Early out if we are an invalid form of lswx */ + if ((instword & INST_STRING_MASK) == INST_LSWX) + if ((rT == rA) || (rT == NB_RB)) + return -EINVAL; + + EA = (rA == 0) ? 0 : regs->gpr[rA]; + + switch (instword & INST_STRING_MASK) { + case INST_LSWX: + case INST_STSWX: + EA += NB_RB; + num_bytes = regs->xer & 0x7f; + break; + case INST_LSWI: + case INST_STSWI: + num_bytes = (NB_RB == 0) ? 32 : NB_RB; + break; + default: + return -EINVAL; + } + + while (num_bytes != 0) + { + u8 val; + u32 shift = 8 * (3 - (pos & 0x3)); + + switch ((instword & INST_STRING_MASK)) { + case INST_LSWX: + case INST_LSWI: + if (get_user(val, (u8 __user *)EA)) + return -EFAULT; + /* first time updating this reg, + * zero it out */ + if (pos == 0) + regs->gpr[rT] = 0; + regs->gpr[rT] |= val << shift; + break; + case INST_STSWI: + case INST_STSWX: + val = regs->gpr[rT] >> shift; + if (put_user(val, (u8 __user *)EA)) + return -EFAULT; + break; + } + /* move EA to next address */ + EA += 1; + num_bytes--; + + /* manage our position within the register */ + if (++pos == 4) { + pos = 0; + if (++rT == 32) + rT = 0; + } + } + + return 0; +} + +static int emulate_instruction(struct pt_regs *regs) +{ + u32 instword; + u32 rd; + + if (!user_mode(regs)) + return -EINVAL; + CHECK_FULL_REGS(regs); + + if (get_user(instword, (u32 __user *)(regs->nip))) + return -EFAULT; + + /* Emulate the mfspr rD, PVR. */ + if ((instword & INST_MFSPR_PVR_MASK) == INST_MFSPR_PVR) { + rd = (instword >> 21) & 0x1f; + regs->gpr[rd] = mfspr(SPRN_PVR); + return 0; + } + + /* Emulating the dcba insn is just a no-op. */ + if ((instword & INST_DCBA_MASK) == INST_DCBA) + return 0; + + /* Emulate the mcrxr insn. */ + if ((instword & INST_MCRXR_MASK) == INST_MCRXR) { + int shift = (instword >> 21) & 0x1c; + unsigned long msk = 0xf0000000UL >> shift; + + regs->ccr = (regs->ccr & ~msk) | ((regs->xer >> shift) & msk); + regs->xer &= ~0xf0000000UL; + return 0; + } + + /* Emulate load/store string insn. */ + if ((instword & INST_STRING_GEN_MASK) == INST_STRING) + return emulate_string_inst(regs, instword); + + return -EINVAL; +} + +/* + * Look through the list of trap instructions that are used for BUG(), + * BUG_ON() and WARN_ON() and see if we hit one. At this point we know + * that the exception was caused by a trap instruction of some kind. + * Returns 1 if we should continue (i.e. it was a WARN_ON) or 0 + * otherwise. + */ +extern struct bug_entry __start___bug_table[], __stop___bug_table[]; + +#ifndef CONFIG_MODULES +#define module_find_bug(x) NULL +#endif + +struct bug_entry *find_bug(unsigned long bugaddr) +{ + struct bug_entry *bug; + + for (bug = __start___bug_table; bug < __stop___bug_table; ++bug) + if (bugaddr == bug->bug_addr) + return bug; + return module_find_bug(bugaddr); +} + +static int check_bug_trap(struct pt_regs *regs) +{ + struct bug_entry *bug; + unsigned long addr; + + if (regs->msr & MSR_PR) + return 0; /* not in kernel */ + addr = regs->nip; /* address of trap instruction */ + if (addr < PAGE_OFFSET) + return 0; + bug = find_bug(regs->nip); + if (bug == NULL) + return 0; + if (bug->line & BUG_WARNING_TRAP) { + /* this is a WARN_ON rather than BUG/BUG_ON */ +#ifdef CONFIG_XMON + xmon_printf(KERN_ERR "Badness in %s at %s:%d\n", + bug->function, bug->file, + bug->line & ~BUG_WARNING_TRAP); +#endif /* CONFIG_XMON */ + printk(KERN_ERR "Badness in %s at %s:%d\n", + bug->function, bug->file, + bug->line & ~BUG_WARNING_TRAP); + dump_stack(); + return 1; + } +#ifdef CONFIG_XMON + xmon_printf(KERN_CRIT "kernel BUG in %s at %s:%d!\n", + bug->function, bug->file, bug->line); + xmon(regs); +#endif /* CONFIG_XMON */ + printk(KERN_CRIT "kernel BUG in %s at %s:%d!\n", + bug->function, bug->file, bug->line); + + return 0; +} + +void __kprobes program_check_exception(struct pt_regs *regs) +{ + unsigned int reason = get_reason(regs); + extern int do_mathemu(struct pt_regs *regs); + +#ifdef CONFIG_MATH_EMULATION + /* (reason & REASON_ILLEGAL) would be the obvious thing here, + * but there seems to be a hardware bug on the 405GP (RevD) + * that means ESR is sometimes set incorrectly - either to + * ESR_DST (!?) or 0. In the process of chasing this with the + * hardware people - not sure if it can happen on any illegal + * instruction or only on FP instructions, whether there is a + * pattern to occurences etc. -dgibson 31/Mar/2003 */ + if (!(reason & REASON_TRAP) && do_mathemu(regs) == 0) { + emulate_single_step(regs); + return; + } +#endif /* CONFIG_MATH_EMULATION */ + + if (reason & REASON_FP) { + /* IEEE FP exception */ + parse_fpe(regs); + return; + } + if (reason & REASON_TRAP) { + /* trap exception */ + if (notify_die(DIE_BPT, "breakpoint", regs, 5, 5, SIGTRAP) + == NOTIFY_STOP) + return; + if (debugger_bpt(regs)) + return; + if (check_bug_trap(regs)) { + regs->nip += 4; + return; + } + _exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip); + return; + } + + /* Try to emulate it if we should. */ + if (reason & (REASON_ILLEGAL | REASON_PRIVILEGED)) { + switch (emulate_instruction(regs)) { + case 0: + regs->nip += 4; + emulate_single_step(regs); + return; + case -EFAULT: + _exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip); + return; + } + } + + if (reason & REASON_PRIVILEGED) + _exception(SIGILL, regs, ILL_PRVOPC, regs->nip); + else + _exception(SIGILL, regs, ILL_ILLOPC, regs->nip); +} + +void alignment_exception(struct pt_regs *regs) +{ + int fixed; + + fixed = fix_alignment(regs); + + if (fixed == 1) { + regs->nip += 4; /* skip over emulated instruction */ + emulate_single_step(regs); + return; + } + + /* Operand address was bad */ + if (fixed == -EFAULT) { + if (user_mode(regs)) + _exception(SIGSEGV, regs, SEGV_ACCERR, regs->dar); + else + /* Search exception table */ + bad_page_fault(regs, regs->dar, SIGSEGV); + return; + } + _exception(SIGBUS, regs, BUS_ADRALN, regs->dar); +} + +void StackOverflow(struct pt_regs *regs) +{ + printk(KERN_CRIT "Kernel stack overflow in process %p, r1=%lx\n", + current, regs->gpr[1]); + debugger(regs); + show_regs(regs); + panic("kernel stack overflow"); +} + +void nonrecoverable_exception(struct pt_regs *regs) +{ + printk(KERN_ERR "Non-recoverable exception at PC=%lx MSR=%lx\n", + regs->nip, regs->msr); + debugger(regs); + die("nonrecoverable exception", regs, SIGKILL); +} + +void trace_syscall(struct pt_regs *regs) +{ + printk("Task: %p(%d), PC: %08lX/%08lX, Syscall: %3ld, Result: %s%ld %s\n", + current, current->pid, regs->nip, regs->link, regs->gpr[0], + regs->ccr&0x10000000?"Error=":"", regs->gpr[3], print_tainted()); +} + +void kernel_fp_unavailable_exception(struct pt_regs *regs) +{ + printk(KERN_EMERG "Unrecoverable FP Unavailable Exception " + "%lx at %lx\n", regs->trap, regs->nip); + die("Unrecoverable FP Unavailable Exception", regs, SIGABRT); +} + +void altivec_unavailable_exception(struct pt_regs *regs) +{ +#if !defined(CONFIG_ALTIVEC) + if (user_mode(regs)) { + /* A user program has executed an altivec instruction, + but this kernel doesn't support altivec. */ + _exception(SIGILL, regs, ILL_ILLOPC, regs->nip); + return; + } +#endif + printk(KERN_EMERG "Unrecoverable VMX/Altivec Unavailable Exception " + "%lx at %lx\n", regs->trap, regs->nip); + 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) +{ + perf_irq(regs); +} +#endif + +#ifdef CONFIG_8xx +void SoftwareEmulation(struct pt_regs *regs) +{ + extern int do_mathemu(struct pt_regs *); + extern int Soft_emulate_8xx(struct pt_regs *); + int errcode; + + CHECK_FULL_REGS(regs); + + if (!user_mode(regs)) { + debugger(regs); + die("Kernel Mode Software FPU Emulation", regs, SIGFPE); + } + +#ifdef CONFIG_MATH_EMULATION + errcode = do_mathemu(regs); +#else + errcode = Soft_emulate_8xx(regs); +#endif + if (errcode) { + if (errcode > 0) + _exception(SIGFPE, regs, 0, 0); + else if (errcode == -EFAULT) + _exception(SIGSEGV, regs, 0, 0); + else + _exception(SIGILL, regs, ILL_ILLOPC, regs->nip); + } else + emulate_single_step(regs); +} +#endif /* CONFIG_8xx */ + +#if defined(CONFIG_40x) || defined(CONFIG_BOOKE) + +void DebugException(struct pt_regs *regs, unsigned long debug_status) +{ + if (debug_status & DBSR_IC) { /* instruction completion */ + regs->msr &= ~MSR_DE; + if (user_mode(regs)) { + current->thread.dbcr0 &= ~DBCR0_IC; + } else { + /* Disable instruction completion */ + mtspr(SPRN_DBCR0, mfspr(SPRN_DBCR0) & ~DBCR0_IC); + /* Clear the instruction completion event */ + mtspr(SPRN_DBSR, DBSR_IC); + if (debugger_sstep(regs)) + return; + } + _exception(SIGTRAP, regs, TRAP_TRACE, 0); + } +} +#endif /* CONFIG_4xx || CONFIG_BOOKE */ + +#if !defined(CONFIG_TAU_INT) +void TAUException(struct pt_regs *regs) +{ + printk("TAU trap at PC: %lx, MSR: %lx, vector=%lx %s\n", + regs->nip, regs->msr, regs->trap, print_tainted()); +} +#endif /* CONFIG_INT_TAU */ + +#ifdef CONFIG_ALTIVEC +void altivec_assist_exception(struct pt_regs *regs) +{ + int err; + + if (!user_mode(regs)) { + printk(KERN_EMERG "VMX/Altivec assist exception in kernel mode" + " at %lx\n", regs->nip); + die("Kernel VMX/Altivec assist exception", regs, SIGILL); + } + + flush_altivec_to_thread(current); + + err = emulate_altivec(regs); + if (err == 0) { + regs->nip += 4; /* skip emulated instruction */ + emulate_single_step(regs); + return; + } + + if (err == -EFAULT) { + /* got an error reading the instruction */ + _exception(SIGSEGV, regs, SEGV_ACCERR, regs->nip); + } else { + /* didn't recognize the instruction */ + /* XXX quick hack for now: set the non-Java bit in the VSCR */ + if (printk_ratelimit()) + printk(KERN_ERR "Unrecognized altivec instruction " + "in %s at %lx\n", current->comm, regs->nip); + current->thread.vscr.u[3] |= 0x10000; + } +} +#endif /* CONFIG_ALTIVEC */ + +#ifdef CONFIG_FSL_BOOKE +void CacheLockingException(struct pt_regs *regs, unsigned long address, + unsigned long error_code) +{ + /* We treat cache locking instructions from the user + * as priv ops, in the future we could try to do + * something smarter + */ + if (error_code & (ESR_DLK|ESR_ILK)) + _exception(SIGILL, regs, ILL_PRVOPC, regs->nip); + return; +} +#endif /* CONFIG_FSL_BOOKE */ + +#ifdef CONFIG_SPE +void SPEFloatingPointException(struct pt_regs *regs) +{ + unsigned long spefscr; + int fpexc_mode; + int code = 0; + + spefscr = current->thread.spefscr; + fpexc_mode = current->thread.fpexc_mode; + + /* Hardware does not neccessarily set sticky + * underflow/overflow/invalid flags */ + if ((spefscr & SPEFSCR_FOVF) && (fpexc_mode & PR_FP_EXC_OVF)) { + code = FPE_FLTOVF; + spefscr |= SPEFSCR_FOVFS; + } + else if ((spefscr & SPEFSCR_FUNF) && (fpexc_mode & PR_FP_EXC_UND)) { + code = FPE_FLTUND; + spefscr |= SPEFSCR_FUNFS; + } + else if ((spefscr & SPEFSCR_FDBZ) && (fpexc_mode & PR_FP_EXC_DIV)) + code = FPE_FLTDIV; + else if ((spefscr & SPEFSCR_FINV) && (fpexc_mode & PR_FP_EXC_INV)) { + code = FPE_FLTINV; + spefscr |= SPEFSCR_FINVS; + } + else if ((spefscr & (SPEFSCR_FG | SPEFSCR_FX)) && (fpexc_mode & PR_FP_EXC_RES)) + code = FPE_FLTRES; + + current->thread.spefscr = spefscr; + + _exception(SIGFPE, regs, code, regs->nip); + return; +} +#endif + +/* + * We enter here if we get an unrecoverable exception, that is, one + * that happened at a point where the RI (recoverable interrupt) bit + * in the MSR is 0. This indicates that SRR0/1 are live, and that + * we therefore lost state by taking this exception. + */ +void unrecoverable_exception(struct pt_regs *regs) +{ + printk(KERN_EMERG "Unrecoverable exception %lx at %lx\n", + regs->trap, regs->nip); + die("Unrecoverable exception", regs, SIGABRT); +} + +#ifdef CONFIG_BOOKE_WDT +/* + * Default handler for a Watchdog exception, + * spins until a reboot occurs + */ +void __attribute__ ((weak)) WatchdogHandler(struct pt_regs *regs) +{ + /* Generic WatchdogHandler, implement your own */ + mtspr(SPRN_TCR, mfspr(SPRN_TCR)&(~TCR_WIE)); + return; +} + +void WatchdogException(struct pt_regs *regs) +{ + printk (KERN_EMERG "PowerPC Book-E Watchdog Exception\n"); + WatchdogHandler(regs); +} +#endif + +/* + * We enter here if we discover during exception entry that we are + * running in supervisor mode with a userspace value in the stack pointer. + */ +void kernel_bad_stack(struct pt_regs *regs) +{ + printk(KERN_EMERG "Bad kernel stack pointer %lx at %lx\n", + regs->gpr[1], regs->nip); + die("Bad kernel stack pointer", regs, SIGABRT); +} + +void __init trap_init(void) +{ +} diff --git a/arch/powerpc/kernel/vecemu.c b/arch/powerpc/kernel/vecemu.c new file mode 100644 index 000000000000..604d0947cb20 --- /dev/null +++ b/arch/powerpc/kernel/vecemu.c @@ -0,0 +1,345 @@ +/* + * Routines to emulate some Altivec/VMX instructions, specifically + * those that can trap when given denormalized operands in Java mode. + */ +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/sched.h> +#include <asm/ptrace.h> +#include <asm/processor.h> +#include <asm/uaccess.h> + +/* Functions in vector.S */ +extern void vaddfp(vector128 *dst, vector128 *a, vector128 *b); +extern void vsubfp(vector128 *dst, vector128 *a, vector128 *b); +extern void vmaddfp(vector128 *dst, vector128 *a, vector128 *b, vector128 *c); +extern void vnmsubfp(vector128 *dst, vector128 *a, vector128 *b, vector128 *c); +extern void vrefp(vector128 *dst, vector128 *src); +extern void vrsqrtefp(vector128 *dst, vector128 *src); +extern void vexptep(vector128 *dst, vector128 *src); + +static unsigned int exp2s[8] = { + 0x800000, + 0x8b95c2, + 0x9837f0, + 0xa5fed7, + 0xb504f3, + 0xc5672a, + 0xd744fd, + 0xeac0c7 +}; + +/* + * Computes an estimate of 2^x. The `s' argument is the 32-bit + * single-precision floating-point representation of x. + */ +static unsigned int eexp2(unsigned int s) +{ + int exp, pwr; + unsigned int mant, frac; + + /* extract exponent field from input */ + exp = ((s >> 23) & 0xff) - 127; + if (exp > 7) { + /* check for NaN input */ + if (exp == 128 && (s & 0x7fffff) != 0) + return s | 0x400000; /* return QNaN */ + /* 2^-big = 0, 2^+big = +Inf */ + return (s & 0x80000000)? 0: 0x7f800000; /* 0 or +Inf */ + } + if (exp < -23) + return 0x3f800000; /* 1.0 */ + + /* convert to fixed point integer in 9.23 representation */ + pwr = (s & 0x7fffff) | 0x800000; + if (exp > 0) + pwr <<= exp; + else + pwr >>= -exp; + if (s & 0x80000000) + pwr = -pwr; + + /* extract integer part, which becomes exponent part of result */ + exp = (pwr >> 23) + 126; + if (exp >= 254) + return 0x7f800000; + if (exp < -23) + return 0; + + /* table lookup on top 3 bits of fraction to get mantissa */ + mant = exp2s[(pwr >> 20) & 7]; + + /* linear interpolation using remaining 20 bits of fraction */ + asm("mulhwu %0,%1,%2" : "=r" (frac) + : "r" (pwr << 12), "r" (0x172b83ff)); + asm("mulhwu %0,%1,%2" : "=r" (frac) : "r" (frac), "r" (mant)); + mant += frac; + + if (exp >= 0) + return mant + (exp << 23); + + /* denormalized result */ + exp = -exp; + mant += 1 << (exp - 1); + return mant >> exp; +} + +/* + * Computes an estimate of log_2(x). The `s' argument is the 32-bit + * single-precision floating-point representation of x. + */ +static unsigned int elog2(unsigned int s) +{ + int exp, mant, lz, frac; + + exp = s & 0x7f800000; + mant = s & 0x7fffff; + if (exp == 0x7f800000) { /* Inf or NaN */ + if (mant != 0) + s |= 0x400000; /* turn NaN into QNaN */ + return s; + } + if ((exp | mant) == 0) /* +0 or -0 */ + return 0xff800000; /* return -Inf */ + + if (exp == 0) { + /* denormalized */ + asm("cntlzw %0,%1" : "=r" (lz) : "r" (mant)); + mant <<= lz - 8; + exp = (-118 - lz) << 23; + } else { + mant |= 0x800000; + exp -= 127 << 23; + } + + if (mant >= 0xb504f3) { /* 2^0.5 * 2^23 */ + exp |= 0x400000; /* 0.5 * 2^23 */ + asm("mulhwu %0,%1,%2" : "=r" (mant) + : "r" (mant), "r" (0xb504f334)); /* 2^-0.5 * 2^32 */ + } + if (mant >= 0x9837f0) { /* 2^0.25 * 2^23 */ + exp |= 0x200000; /* 0.25 * 2^23 */ + asm("mulhwu %0,%1,%2" : "=r" (mant) + : "r" (mant), "r" (0xd744fccb)); /* 2^-0.25 * 2^32 */ + } + if (mant >= 0x8b95c2) { /* 2^0.125 * 2^23 */ + exp |= 0x100000; /* 0.125 * 2^23 */ + asm("mulhwu %0,%1,%2" : "=r" (mant) + : "r" (mant), "r" (0xeac0c6e8)); /* 2^-0.125 * 2^32 */ + } + if (mant > 0x800000) { /* 1.0 * 2^23 */ + /* calculate (mant - 1) * 1.381097463 */ + /* 1.381097463 == 0.125 / (2^0.125 - 1) */ + asm("mulhwu %0,%1,%2" : "=r" (frac) + : "r" ((mant - 0x800000) << 1), "r" (0xb0c7cd3a)); + exp += frac; + } + s = exp & 0x80000000; + if (exp != 0) { + if (s) + exp = -exp; + asm("cntlzw %0,%1" : "=r" (lz) : "r" (exp)); + lz = 8 - lz; + if (lz > 0) + exp >>= lz; + else if (lz < 0) + exp <<= -lz; + s += ((lz + 126) << 23) + exp; + } + return s; +} + +#define VSCR_SAT 1 + +static int ctsxs(unsigned int x, int scale, unsigned int *vscrp) +{ + int exp, mant; + + exp = (x >> 23) & 0xff; + mant = x & 0x7fffff; + if (exp == 255 && mant != 0) + return 0; /* NaN -> 0 */ + exp = exp - 127 + scale; + if (exp < 0) + return 0; /* round towards zero */ + if (exp >= 31) { + /* saturate, unless the result would be -2^31 */ + if (x + (scale << 23) != 0xcf000000) + *vscrp |= VSCR_SAT; + return (x & 0x80000000)? 0x80000000: 0x7fffffff; + } + mant |= 0x800000; + mant = (mant << 7) >> (30 - exp); + return (x & 0x80000000)? -mant: mant; +} + +static unsigned int ctuxs(unsigned int x, int scale, unsigned int *vscrp) +{ + int exp; + unsigned int mant; + + exp = (x >> 23) & 0xff; + mant = x & 0x7fffff; + if (exp == 255 && mant != 0) + return 0; /* NaN -> 0 */ + exp = exp - 127 + scale; + if (exp < 0) + return 0; /* round towards zero */ + if (x & 0x80000000) { + /* negative => saturate to 0 */ + *vscrp |= VSCR_SAT; + return 0; + } + if (exp >= 32) { + /* saturate */ + *vscrp |= VSCR_SAT; + return 0xffffffff; + } + mant |= 0x800000; + mant = (mant << 8) >> (31 - exp); + return mant; +} + +/* Round to floating integer, towards 0 */ +static unsigned int rfiz(unsigned int x) +{ + int exp; + + exp = ((x >> 23) & 0xff) - 127; + if (exp == 128 && (x & 0x7fffff) != 0) + return x | 0x400000; /* NaN -> make it a QNaN */ + if (exp >= 23) + return x; /* it's an integer already (or Inf) */ + if (exp < 0) + return x & 0x80000000; /* |x| < 1.0 rounds to 0 */ + return x & ~(0x7fffff >> exp); +} + +/* Round to floating integer, towards +/- Inf */ +static unsigned int rfii(unsigned int x) +{ + int exp, mask; + + exp = ((x >> 23) & 0xff) - 127; + if (exp == 128 && (x & 0x7fffff) != 0) + return x | 0x400000; /* NaN -> make it a QNaN */ + if (exp >= 23) + return x; /* it's an integer already (or Inf) */ + if ((x & 0x7fffffff) == 0) + return x; /* +/-0 -> +/-0 */ + if (exp < 0) + /* 0 < |x| < 1.0 rounds to +/- 1.0 */ + return (x & 0x80000000) | 0x3f800000; + mask = 0x7fffff >> exp; + /* mantissa overflows into exponent - that's OK, + it can't overflow into the sign bit */ + return (x + mask) & ~mask; +} + +/* Round to floating integer, to nearest */ +static unsigned int rfin(unsigned int x) +{ + int exp, half; + + exp = ((x >> 23) & 0xff) - 127; + if (exp == 128 && (x & 0x7fffff) != 0) + return x | 0x400000; /* NaN -> make it a QNaN */ + if (exp >= 23) + return x; /* it's an integer already (or Inf) */ + if (exp < -1) + return x & 0x80000000; /* |x| < 0.5 -> +/-0 */ + if (exp == -1) + /* 0.5 <= |x| < 1.0 rounds to +/- 1.0 */ + return (x & 0x80000000) | 0x3f800000; + half = 0x400000 >> exp; + /* add 0.5 to the magnitude and chop off the fraction bits */ + return (x + half) & ~(0x7fffff >> exp); +} + +int emulate_altivec(struct pt_regs *regs) +{ + unsigned int instr, i; + unsigned int va, vb, vc, vd; + vector128 *vrs; + + if (get_user(instr, (unsigned int __user *) regs->nip)) + return -EFAULT; + if ((instr >> 26) != 4) + return -EINVAL; /* not an altivec instruction */ + vd = (instr >> 21) & 0x1f; + va = (instr >> 16) & 0x1f; + vb = (instr >> 11) & 0x1f; + vc = (instr >> 6) & 0x1f; + + vrs = current->thread.vr; + switch (instr & 0x3f) { + case 10: + switch (vc) { + case 0: /* vaddfp */ + vaddfp(&vrs[vd], &vrs[va], &vrs[vb]); + break; + case 1: /* vsubfp */ + vsubfp(&vrs[vd], &vrs[va], &vrs[vb]); + break; + case 4: /* vrefp */ + vrefp(&vrs[vd], &vrs[vb]); + break; + case 5: /* vrsqrtefp */ + vrsqrtefp(&vrs[vd], &vrs[vb]); + break; + case 6: /* vexptefp */ + for (i = 0; i < 4; ++i) + vrs[vd].u[i] = eexp2(vrs[vb].u[i]); + break; + case 7: /* vlogefp */ + for (i = 0; i < 4; ++i) + vrs[vd].u[i] = elog2(vrs[vb].u[i]); + break; + case 8: /* vrfin */ + for (i = 0; i < 4; ++i) + vrs[vd].u[i] = rfin(vrs[vb].u[i]); + break; + case 9: /* vrfiz */ + for (i = 0; i < 4; ++i) + vrs[vd].u[i] = rfiz(vrs[vb].u[i]); + break; + case 10: /* vrfip */ + for (i = 0; i < 4; ++i) { + u32 x = vrs[vb].u[i]; + x = (x & 0x80000000)? rfiz(x): rfii(x); + vrs[vd].u[i] = x; + } + break; + case 11: /* vrfim */ + for (i = 0; i < 4; ++i) { + u32 x = vrs[vb].u[i]; + x = (x & 0x80000000)? rfii(x): rfiz(x); + vrs[vd].u[i] = x; + } + break; + case 14: /* vctuxs */ + for (i = 0; i < 4; ++i) + vrs[vd].u[i] = ctuxs(vrs[vb].u[i], va, + ¤t->thread.vscr.u[3]); + break; + case 15: /* vctsxs */ + for (i = 0; i < 4; ++i) + vrs[vd].u[i] = ctsxs(vrs[vb].u[i], va, + ¤t->thread.vscr.u[3]); + break; + default: + return -EINVAL; + } + break; + case 46: /* vmaddfp */ + vmaddfp(&vrs[vd], &vrs[va], &vrs[vb], &vrs[vc]); + break; + case 47: /* vnmsubfp */ + vnmsubfp(&vrs[vd], &vrs[va], &vrs[vb], &vrs[vc]); + break; + default: + return -EINVAL; + } + + return 0; +} diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S new file mode 100644 index 000000000000..66b3d03c5fa5 --- /dev/null +++ b/arch/powerpc/kernel/vector.S @@ -0,0 +1,197 @@ +#include <linux/config.h> +#include <asm/ppc_asm.h> +#include <asm/reg.h> + +/* + * The routines below are in assembler so we can closely control the + * usage of floating-point registers. These routines must be called + * with preempt disabled. + */ +#ifdef CONFIG_PPC32 + .data +fpzero: + .long 0 +fpone: + .long 0x3f800000 /* 1.0 in single-precision FP */ +fphalf: + .long 0x3f000000 /* 0.5 in single-precision FP */ + +#define LDCONST(fr, name) \ + lis r11,name@ha; \ + lfs fr,name@l(r11) +#else + + .section ".toc","aw" +fpzero: + .tc FD_0_0[TC],0 +fpone: + .tc FD_3ff00000_0[TC],0x3ff0000000000000 /* 1.0 */ +fphalf: + .tc FD_3fe00000_0[TC],0x3fe0000000000000 /* 0.5 */ + +#define LDCONST(fr, name) \ + lfd fr,name@toc(r2) +#endif + + .text +/* + * Internal routine to enable floating point and set FPSCR to 0. + * Don't call it from C; it doesn't use the normal calling convention. + */ +fpenable: +#ifdef CONFIG_PPC32 + stwu r1,-64(r1) +#else + stdu r1,-64(r1) +#endif + mfmsr r10 + ori r11,r10,MSR_FP + mtmsr r11 + isync + stfd fr0,24(r1) + stfd fr1,16(r1) + stfd fr31,8(r1) + LDCONST(fr1, fpzero) + mffs fr31 + mtfsf 0xff,fr1 + blr + +fpdisable: + mtlr r12 + mtfsf 0xff,fr31 + lfd fr31,8(r1) + lfd fr1,16(r1) + lfd fr0,24(r1) + mtmsr r10 + isync + addi r1,r1,64 + blr + +/* + * Vector add, floating point. + */ +_GLOBAL(vaddfp) + mflr r12 + bl fpenable + li r0,4 + mtctr r0 + li r6,0 +1: lfsx fr0,r4,r6 + lfsx fr1,r5,r6 + fadds fr0,fr0,fr1 + stfsx fr0,r3,r6 + addi r6,r6,4 + bdnz 1b + b fpdisable + +/* + * Vector subtract, floating point. + */ +_GLOBAL(vsubfp) + mflr r12 + bl fpenable + li r0,4 + mtctr r0 + li r6,0 +1: lfsx fr0,r4,r6 + lfsx fr1,r5,r6 + fsubs fr0,fr0,fr1 + stfsx fr0,r3,r6 + addi r6,r6,4 + bdnz 1b + b fpdisable + +/* + * Vector multiply and add, floating point. + */ +_GLOBAL(vmaddfp) + mflr r12 + bl fpenable + stfd fr2,32(r1) + li r0,4 + mtctr r0 + li r7,0 +1: lfsx fr0,r4,r7 + lfsx fr1,r5,r7 + lfsx fr2,r6,r7 + fmadds fr0,fr0,fr2,fr1 + stfsx fr0,r3,r7 + addi r7,r7,4 + bdnz 1b + lfd fr2,32(r1) + b fpdisable + +/* + * Vector negative multiply and subtract, floating point. + */ +_GLOBAL(vnmsubfp) + mflr r12 + bl fpenable + stfd fr2,32(r1) + li r0,4 + mtctr r0 + li r7,0 +1: lfsx fr0,r4,r7 + lfsx fr1,r5,r7 + lfsx fr2,r6,r7 + fnmsubs fr0,fr0,fr2,fr1 + stfsx fr0,r3,r7 + addi r7,r7,4 + bdnz 1b + lfd fr2,32(r1) + b fpdisable + +/* + * Vector reciprocal estimate. We just compute 1.0/x. + * r3 -> destination, r4 -> source. + */ +_GLOBAL(vrefp) + mflr r12 + bl fpenable + li r0,4 + LDCONST(fr1, fpone) + mtctr r0 + li r6,0 +1: lfsx fr0,r4,r6 + fdivs fr0,fr1,fr0 + stfsx fr0,r3,r6 + addi r6,r6,4 + bdnz 1b + b fpdisable + +/* + * Vector reciprocal square-root estimate, floating point. + * We use the frsqrte instruction for the initial estimate followed + * by 2 iterations of Newton-Raphson to get sufficient accuracy. + * r3 -> destination, r4 -> source. + */ +_GLOBAL(vrsqrtefp) + mflr r12 + bl fpenable + stfd fr2,32(r1) + stfd fr3,40(r1) + stfd fr4,48(r1) + stfd fr5,56(r1) + li r0,4 + LDCONST(fr4, fpone) + LDCONST(fr5, fphalf) + mtctr r0 + li r6,0 +1: lfsx fr0,r4,r6 + frsqrte fr1,fr0 /* r = frsqrte(s) */ + fmuls fr3,fr1,fr0 /* r * s */ + fmuls fr2,fr1,fr5 /* r * 0.5 */ + fnmsubs fr3,fr1,fr3,fr4 /* 1 - s * r * r */ + fmadds fr1,fr2,fr3,fr1 /* r = r + 0.5 * r * (1 - s * r * r) */ + fmuls fr3,fr1,fr0 /* r * s */ + fmuls fr2,fr1,fr5 /* r * 0.5 */ + fnmsubs fr3,fr1,fr3,fr4 /* 1 - s * r * r */ + fmadds fr1,fr2,fr3,fr1 /* r = r + 0.5 * r * (1 - s * r * r) */ + stfsx fr1,r3,r6 + addi r6,r6,4 + bdnz 1b + lfd fr5,56(r1) + lfd fr4,48(r1) + lfd fr3,40(r1) + lfd fr2,32(r1) + b fpdisable diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c new file mode 100644 index 000000000000..97082a4203ad --- /dev/null +++ b/arch/powerpc/kernel/vio.c @@ -0,0 +1,271 @@ +/* + * IBM PowerPC Virtual I/O Infrastructure Support. + * + * Copyright (c) 2003-2005 IBM Corp. + * Dave Engebretsen engebret@us.ibm.com + * Santiago Leon santil@us.ibm.com + * Hollis Blanchard <hollisb@us.ibm.com> + * Stephen Rothwell + * + * 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/init.h> +#include <linux/console.h> +#include <linux/module.h> +#include <linux/mm.h> +#include <linux/dma-mapping.h> +#include <asm/iommu.h> +#include <asm/dma.h> +#include <asm/vio.h> + +static const struct vio_device_id *vio_match_device( + const struct vio_device_id *, const struct vio_dev *); + +struct vio_dev vio_bus_device = { /* fake "parent" device */ + .name = vio_bus_device.dev.bus_id, + .type = "", + .dev.bus_id = "vio", + .dev.bus = &vio_bus_type, +}; + +static struct vio_bus_ops vio_bus_ops; + +/* + * Convert from struct device to struct vio_dev and pass to driver. + * dev->driver has already been set by generic code because vio_bus_match + * succeeded. + */ +static int vio_bus_probe(struct device *dev) +{ + struct vio_dev *viodev = to_vio_dev(dev); + struct vio_driver *viodrv = to_vio_driver(dev->driver); + const struct vio_device_id *id; + int error = -ENODEV; + + if (!viodrv->probe) + return error; + + id = vio_match_device(viodrv->id_table, viodev); + if (id) + error = viodrv->probe(viodev, id); + + return error; +} + +/* convert from struct device to struct vio_dev and pass to driver. */ +static int vio_bus_remove(struct device *dev) +{ + struct vio_dev *viodev = to_vio_dev(dev); + struct vio_driver *viodrv = to_vio_driver(dev->driver); + + if (viodrv->remove) + return viodrv->remove(viodev); + + /* driver can't remove */ + return 1; +} + +/* convert from struct device to struct vio_dev and pass to driver. */ +static void vio_bus_shutdown(struct device *dev) +{ + struct vio_dev *viodev = to_vio_dev(dev); + struct vio_driver *viodrv = to_vio_driver(dev->driver); + + if (viodrv->shutdown) + viodrv->shutdown(viodev); +} + +/** + * vio_register_driver: - Register a new vio driver + * @drv: The vio_driver structure to be registered. + */ +int vio_register_driver(struct vio_driver *viodrv) +{ + printk(KERN_DEBUG "%s: driver %s registering\n", __FUNCTION__, + viodrv->driver.name); + + /* fill in 'struct driver' fields */ + viodrv->driver.bus = &vio_bus_type; + viodrv->driver.probe = vio_bus_probe; + viodrv->driver.remove = vio_bus_remove; + viodrv->driver.shutdown = vio_bus_shutdown; + + return driver_register(&viodrv->driver); +} +EXPORT_SYMBOL(vio_register_driver); + +/** + * vio_unregister_driver - Remove registration of vio driver. + * @driver: The vio_driver struct to be removed form registration + */ +void vio_unregister_driver(struct vio_driver *viodrv) +{ + driver_unregister(&viodrv->driver); +} +EXPORT_SYMBOL(vio_unregister_driver); + +/** + * vio_match_device: - Tell if a VIO device has a matching + * VIO device id structure. + * @ids: array of VIO device id structures to search in + * @dev: the VIO device structure to match against + * + * Used by a driver to check whether a VIO device present in the + * system is in its list of supported devices. Returns the matching + * vio_device_id structure or NULL if there is no match. + */ +static const struct vio_device_id *vio_match_device( + const struct vio_device_id *ids, const struct vio_dev *dev) +{ + while (ids->type[0] != '\0') { + if (vio_bus_ops.match(ids, dev)) + return ids; + ids++; + } + return NULL; +} + +/** + * vio_bus_init: - Initialize the virtual IO bus + */ +int __init vio_bus_init(struct vio_bus_ops *ops) +{ + int err; + + vio_bus_ops = *ops; + + err = bus_register(&vio_bus_type); + if (err) { + printk(KERN_ERR "failed to register VIO bus\n"); + return err; + } + + /* + * The fake parent of all vio devices, just to give us + * a nice directory + */ + err = device_register(&vio_bus_device.dev); + if (err) { + printk(KERN_WARNING "%s: device_register returned %i\n", + __FUNCTION__, err); + return err; + } + + return 0; +} + +/* vio_dev refcount hit 0 */ +static void __devinit vio_dev_release(struct device *dev) +{ + if (vio_bus_ops.release_device) + vio_bus_ops.release_device(dev); + kfree(to_vio_dev(dev)); +} + +static ssize_t viodev_show_name(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "%s\n", to_vio_dev(dev)->name); +} +DEVICE_ATTR(name, S_IRUSR | S_IRGRP | S_IROTH, viodev_show_name, NULL); + +struct vio_dev * __devinit vio_register_device(struct vio_dev *viodev) +{ + /* init generic 'struct device' fields: */ + viodev->dev.parent = &vio_bus_device.dev; + viodev->dev.bus = &vio_bus_type; + viodev->dev.release = vio_dev_release; + + /* register with generic device framework */ + if (device_register(&viodev->dev)) { + printk(KERN_ERR "%s: failed to register device %s\n", + __FUNCTION__, viodev->dev.bus_id); + return NULL; + } + device_create_file(&viodev->dev, &dev_attr_name); + + return viodev; +} + +void __devinit vio_unregister_device(struct vio_dev *viodev) +{ + if (vio_bus_ops.unregister_device) + vio_bus_ops.unregister_device(viodev); + device_remove_file(&viodev->dev, &dev_attr_name); + device_unregister(&viodev->dev); +} +EXPORT_SYMBOL(vio_unregister_device); + +static dma_addr_t vio_map_single(struct device *dev, void *vaddr, + size_t size, enum dma_data_direction direction) +{ + return iommu_map_single(to_vio_dev(dev)->iommu_table, vaddr, size, + direction); +} + +static void vio_unmap_single(struct device *dev, dma_addr_t dma_handle, + size_t size, enum dma_data_direction direction) +{ + iommu_unmap_single(to_vio_dev(dev)->iommu_table, dma_handle, size, + direction); +} + +static int vio_map_sg(struct device *dev, struct scatterlist *sglist, + int nelems, enum dma_data_direction direction) +{ + return iommu_map_sg(dev, to_vio_dev(dev)->iommu_table, sglist, + nelems, direction); +} + +static void vio_unmap_sg(struct device *dev, struct scatterlist *sglist, + int nelems, enum dma_data_direction direction) +{ + iommu_unmap_sg(to_vio_dev(dev)->iommu_table, sglist, nelems, direction); +} + +static void *vio_alloc_coherent(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t flag) +{ + return iommu_alloc_coherent(to_vio_dev(dev)->iommu_table, size, + dma_handle, flag); +} + +static void vio_free_coherent(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_handle) +{ + iommu_free_coherent(to_vio_dev(dev)->iommu_table, size, vaddr, + dma_handle); +} + +static int vio_dma_supported(struct device *dev, u64 mask) +{ + return 1; +} + +struct dma_mapping_ops vio_dma_ops = { + .alloc_coherent = vio_alloc_coherent, + .free_coherent = vio_free_coherent, + .map_single = vio_map_single, + .unmap_single = vio_unmap_single, + .map_sg = vio_map_sg, + .unmap_sg = vio_unmap_sg, + .dma_supported = vio_dma_supported, +}; + +static int vio_bus_match(struct device *dev, struct device_driver *drv) +{ + const struct vio_dev *vio_dev = to_vio_dev(dev); + struct vio_driver *vio_drv = to_vio_driver(drv); + const struct vio_device_id *ids = vio_drv->id_table; + + return (ids != NULL) && (vio_match_device(ids, vio_dev) != NULL); +} + +struct bus_type vio_bus_type = { + .name = "vio", + .match = vio_bus_match, +}; diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S new file mode 100644 index 000000000000..d4dfcfbce272 --- /dev/null +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -0,0 +1,279 @@ +#include <linux/config.h> +#ifdef CONFIG_PPC64 +#include <asm/page.h> +#else +#define PAGE_SIZE 4096 +#endif +#include <asm-generic/vmlinux.lds.h> + +#ifdef CONFIG_PPC64 +OUTPUT_ARCH(powerpc:common64) +jiffies = jiffies_64; +#else +OUTPUT_ARCH(powerpc:common) +jiffies = jiffies_64 + 4; +#endif +SECTIONS +{ + /* Sections to be discarded. */ + /DISCARD/ : { + *(.exitcall.exit) + *(.exit.data) + } + + + /* Read-only sections, merged into text segment: */ +#ifdef CONFIG_PPC32 + . = + SIZEOF_HEADERS; + .interp : { *(.interp) } + .hash : { *(.hash) } + .dynsym : { *(.dynsym) } + .dynstr : { *(.dynstr) } + .rel.text : { *(.rel.text) } + .rela.text : { *(.rela.text) } + .rel.data : { *(.rel.data) } + .rela.data : { *(.rela.data) } + .rel.rodata : { *(.rel.rodata) } + .rela.rodata : { *(.rela.rodata) } + .rel.got : { *(.rel.got) } + .rela.got : { *(.rela.got) } + .rel.ctors : { *(.rel.ctors) } + .rela.ctors : { *(.rela.ctors) } + .rel.dtors : { *(.rel.dtors) } + .rela.dtors : { *(.rela.dtors) } + .rel.bss : { *(.rel.bss) } + .rela.bss : { *(.rela.bss) } + .rel.plt : { *(.rel.plt) } + .rela.plt : { *(.rela.plt) } +/* .init : { *(.init) } =0*/ + .plt : { *(.plt) } +#endif + .text : { + *(.text .text.*) + SCHED_TEXT + LOCK_TEXT + KPROBES_TEXT + *(.fixup) +#ifdef CONFIG_PPC32 + *(.got1) + __got2_start = .; + *(.got2) + __got2_end = .; +#else + . = ALIGN(PAGE_SIZE); + _etext = .; +#endif + } +#ifdef CONFIG_PPC32 + _etext = .; + PROVIDE (etext = .); + + RODATA + .fini : { *(.fini) } =0 + .ctors : { *(.ctors) } + .dtors : { *(.dtors) } + + .fixup : { *(.fixup) } +#endif + + __ex_table : { + __start___ex_table = .; + *(__ex_table) + __stop___ex_table = .; + } + + __bug_table : { + __start___bug_table = .; + *(__bug_table) + __stop___bug_table = .; + } + +#ifdef CONFIG_PPC64 + __ftr_fixup : { + __start___ftr_fixup = .; + *(__ftr_fixup) + __stop___ftr_fixup = .; + } + + RODATA +#endif + +#ifdef CONFIG_PPC32 + /* Read-write section, merged into data segment: */ + . = ALIGN(PAGE_SIZE); + _sdata = .; + .data : + { + *(.data) + *(.data1) + *(.sdata) + *(.sdata2) + *(.got.plt) *(.got) + *(.dynamic) + CONSTRUCTORS + } + + . = ALIGN(PAGE_SIZE); + __nosave_begin = .; + .data_nosave : { *(.data.nosave) } + . = ALIGN(PAGE_SIZE); + __nosave_end = .; + + . = ALIGN(32); + .data.cacheline_aligned : { *(.data.cacheline_aligned) } + + _edata = .; + PROVIDE (edata = .); + + . = ALIGN(8192); + .data.init_task : { *(.data.init_task) } +#endif + + /* will be freed after init */ + . = ALIGN(PAGE_SIZE); + __init_begin = .; + .init.text : { + _sinittext = .; + *(.init.text) + _einittext = .; + } +#ifdef CONFIG_PPC32 + /* .exit.text is discarded at runtime, not link time, + to deal with references from __bug_table */ + .exit.text : { *(.exit.text) } +#endif + .init.data : { + *(.init.data); + __vtop_table_begin = .; + *(.vtop_fixup); + __vtop_table_end = .; + __ptov_table_begin = .; + *(.ptov_fixup); + __ptov_table_end = .; + } + + . = ALIGN(16); + .init.setup : { + __setup_start = .; + *(.init.setup) + __setup_end = .; + } + + .initcall.init : { + __initcall_start = .; + *(.initcall1.init) + *(.initcall2.init) + *(.initcall3.init) + *(.initcall4.init) + *(.initcall5.init) + *(.initcall6.init) + *(.initcall7.init) + __initcall_end = .; + } + + .con_initcall.init : { + __con_initcall_start = .; + *(.con_initcall.init) + __con_initcall_end = .; + } + + SECURITY_INIT + +#ifdef CONFIG_PPC32 + __start___ftr_fixup = .; + __ftr_fixup : { *(__ftr_fixup) } + __stop___ftr_fixup = .; +#else + . = ALIGN(PAGE_SIZE); + .init.ramfs : { + __initramfs_start = .; + *(.init.ramfs) + __initramfs_end = .; + } +#endif + +#ifdef CONFIG_PPC32 + . = ALIGN(32); +#endif + .data.percpu : { + __per_cpu_start = .; + *(.data.percpu) + __per_cpu_end = .; + } + + . = ALIGN(PAGE_SIZE); +#ifdef CONFIG_PPC64 + . = ALIGN(16384); + __init_end = .; + /* freed after init ends here */ + + /* Read/write sections */ + . = ALIGN(PAGE_SIZE); + . = ALIGN(16384); + _sdata = .; + /* The initial task and kernel stack */ + .data.init_task : { + *(.data.init_task) + } + + . = ALIGN(PAGE_SIZE); + .data.page_aligned : { + *(.data.page_aligned) + } + + .data.cacheline_aligned : { + *(.data.cacheline_aligned) + } + + .data : { + *(.data .data.rel* .toc1) + *(.branch_lt) + } + + .opd : { + *(.opd) + } + + .got : { + __toc_start = .; + *(.got) + *(.toc) + . = ALIGN(PAGE_SIZE); + _edata = .; + } + + . = ALIGN(PAGE_SIZE); +#else + __initramfs_start = .; + .init.ramfs : { + *(.init.ramfs) + } + __initramfs_end = .; + + . = ALIGN(4096); + __init_end = .; + + . = ALIGN(4096); + _sextratext = .; + _eextratext = .; + + __bss_start = .; +#endif + + .bss : { + __bss_start = .; + *(.sbss) *(.scommon) + *(.dynbss) + *(.bss) + *(COMMON) + __bss_stop = .; + } + +#ifdef CONFIG_PPC64 + . = ALIGN(PAGE_SIZE); +#endif + _end = . ; +#ifdef CONFIG_PPC32 + PROVIDE (end = .); +#endif +} |