diff options
Diffstat (limited to 'arch/powerpc/kernel')
59 files changed, 1614 insertions, 1357 deletions
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index b0cb2e6..ca51f0c 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -24,6 +24,7 @@ obj-$(CONFIG_PPC64) += vdso64/ obj-$(CONFIG_ALTIVEC) += vecemu.o vector.o obj-$(CONFIG_PPC_970_NAP) += idle_power4.o obj-$(CONFIG_PPC_OF) += of_device.o of_platform.o prom_parse.o +obj-$(CONFIG_PPC_CLOCK) += clock.o procfs-$(CONFIG_PPC64) := proc_ppc64.o obj-$(CONFIG_PROC_FS) += $(procfs-y) rtaspci-$(CONFIG_PPC64)-$(CONFIG_PCI) := rtas_pci.o @@ -37,25 +38,27 @@ obj-$(CONFIG_GENERIC_TBSYNC) += smp-tbsync.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_6xx) += idle_6xx.o l2cr_6xx.o cpu_setup_6xx.o obj-$(CONFIG_TAU) += tau_6xx.o -obj-$(CONFIG_HIBERNATION) += swsusp.o suspend.o -obj32-$(CONFIG_HIBERNATION) += swsusp_32.o -obj64-$(CONFIG_HIBERNATION) += swsusp_64.o swsusp_asm64.o -obj32-$(CONFIG_MODULES) += module_32.o +obj-$(CONFIG_HIBERNATION) += swsusp.o suspend.o \ + swsusp_$(CONFIG_WORD_SIZE).o +obj64-$(CONFIG_HIBERNATION) += swsusp_asm64.o +obj-$(CONFIG_MODULES) += module_$(CONFIG_WORD_SIZE).o +obj-$(CONFIG_44x) += cpu_setup_44x.o ifeq ($(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_40x) := head_40x.o extra-$(CONFIG_44x) := head_44x.o extra-$(CONFIG_FSL_BOOKE) := head_fsl_booke.o extra-$(CONFIG_8xx) := head_8xx.o extra-y += vmlinux.lds obj-y += time.o prom.o traps.o setup-common.o \ - udbg.o misc.o io.o -obj-$(CONFIG_PPC32) += entry_32.o setup_32.o misc_32.o -obj-$(CONFIG_PPC64) += misc_64.o dma_64.o iommu.o + udbg.o misc.o io.o \ + misc_$(CONFIG_WORD_SIZE).o +obj-$(CONFIG_PPC32) += entry_32.o setup_32.o +obj-$(CONFIG_PPC64) += dma_64.o iommu.o obj-$(CONFIG_PPC_MULTIPLATFORM) += prom_init.o obj-$(CONFIG_MODULES) += ppc_ksyms.o obj-$(CONFIG_BOOTX_TEXT) += btext.o @@ -63,37 +66,27 @@ obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_PPC_UDBG_16550) += legacy_serial.o udbg_16550.o -module-$(CONFIG_PPC64) += module_64.o -obj-$(CONFIG_MODULES) += $(module-y) - -pci64-$(CONFIG_PPC64) += pci_64.o pci_dn.o isa-bridge.o -pci32-$(CONFIG_PPC32) := pci_32.o -obj-$(CONFIG_PCI) += $(pci64-y) $(pci32-y) pci-common.o +pci64-$(CONFIG_PPC64) += pci_dn.o isa-bridge.o +obj-$(CONFIG_PCI) += pci_$(CONFIG_WORD_SIZE).o $(pci64-y) \ + pci-common.o obj-$(CONFIG_PCI_MSI) += msi.o -kexec-$(CONFIG_PPC64) := machine_kexec_64.o -kexec-$(CONFIG_PPC32) := machine_kexec_32.o -obj-$(CONFIG_KEXEC) += machine_kexec.o crash.o $(kexec-y) +obj-$(CONFIG_KEXEC) += machine_kexec.o crash.o \ + machine_kexec_$(CONFIG_WORD_SIZE).o obj-$(CONFIG_AUDIT) += audit.o obj64-$(CONFIG_AUDIT) += compat_audit.o +obj-$(CONFIG_8XX_MINIMAL_FPEMU) += softemu8xx.o + ifneq ($(CONFIG_PPC_INDIRECT_IO),y) obj-y += iomap.o endif -ifeq ($(CONFIG_PPC_ISERIES),y) -CFLAGS_lparmap.s += -g0 -extra-y += lparmap.s -$(obj)/head_64.o: $(obj)/lparmap.s -AFLAGS_head_64.o += -I$(obj) -endif - else # stuff used from here for ARCH=ppc smpobj-$(CONFIG_SMP) += smp.o endif -obj-$(CONFIG_PPC32) += $(obj32-y) obj-$(CONFIG_PPC64) += $(obj64-y) extra-$(CONFIG_PPC_FPU) += fpu.o diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index 5c9ff7f..e06f75d 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -38,7 +38,7 @@ struct aligninfo { /* Bits in the flags field */ #define LD 0 /* load */ #define ST 1 /* store */ -#define SE 2 /* sign-extend value */ +#define SE 2 /* sign-extend value, or FP ld/st as word */ #define F 4 /* to/from fp regs */ #define U 8 /* update index register */ #define M 0x10 /* multiple load/store */ @@ -46,6 +46,8 @@ struct aligninfo { #define S 0x40 /* single-precision fp or... */ #define SX 0x40 /* ... byte count in XER */ #define HARD 0x80 /* string, stwcx. */ +#define E4 0x40 /* SPE endianness is word */ +#define E8 0x80 /* SPE endianness is double word */ /* DSISR bits reported for a DCBZ instruction: */ #define DCBZ 0x5f /* 8xx/82xx dcbz faults when cache not enabled */ @@ -87,9 +89,9 @@ static struct aligninfo aligninfo[128] = { { 8, LD+F+U }, /* 00 1 1001: lfdu */ { 4, ST+F+S+U }, /* 00 1 1010: stfsu */ { 8, ST+F+U }, /* 00 1 1011: stfdu */ - INVALID, /* 00 1 1100 */ + { 16, LD+F }, /* 00 1 1100: lfdp */ INVALID, /* 00 1 1101 */ - INVALID, /* 00 1 1110 */ + { 16, ST+F }, /* 00 1 1110: stfdp */ INVALID, /* 00 1 1111 */ { 8, LD }, /* 01 0 0000: ldx */ INVALID, /* 01 0 0001 */ @@ -167,10 +169,10 @@ static struct aligninfo aligninfo[128] = { { 8, LD+F }, /* 11 0 1001: lfdx */ { 4, ST+F+S }, /* 11 0 1010: stfsx */ { 8, ST+F }, /* 11 0 1011: stfdx */ - INVALID, /* 11 0 1100 */ - { 8, LD+M }, /* 11 0 1101: lmd */ - INVALID, /* 11 0 1110 */ - { 8, ST+M }, /* 11 0 1111: stmd */ + { 16, LD+F }, /* 11 0 1100: lfdpx */ + { 4, LD+F+SE }, /* 11 0 1101: lfiwax */ + { 16, ST+F }, /* 11 0 1110: stfdpx */ + { 4, ST+F }, /* 11 0 1111: stfiwx */ { 4, LD+U }, /* 11 1 0000: lwzux */ INVALID, /* 11 1 0001 */ { 4, ST+U }, /* 11 1 0010: stwux */ @@ -356,6 +358,284 @@ static int emulate_multiple(struct pt_regs *regs, unsigned char __user *addr, return 1; } +/* + * Emulate floating-point pair loads and stores. + * Only POWER6 has these instructions, and it does true little-endian, + * so we don't need the address swizzling. + */ +static int emulate_fp_pair(struct pt_regs *regs, unsigned char __user *addr, + unsigned int reg, unsigned int flags) +{ + char *ptr = (char *) ¤t->thread.fpr[reg]; + int i, ret; + + if (!(flags & F)) + return 0; + if (reg & 1) + return 0; /* invalid form: FRS/FRT must be even */ + if (!(flags & SW)) { + /* not byte-swapped - easy */ + if (!(flags & ST)) + ret = __copy_from_user(ptr, addr, 16); + else + ret = __copy_to_user(addr, ptr, 16); + } else { + /* each FPR value is byte-swapped separately */ + ret = 0; + for (i = 0; i < 16; ++i) { + if (!(flags & ST)) + ret |= __get_user(ptr[i^7], addr + i); + else + ret |= __put_user(ptr[i^7], addr + i); + } + } + if (ret) + return -EFAULT; + return 1; /* exception handled and fixed up */ +} + +#ifdef CONFIG_SPE + +static struct aligninfo spe_aligninfo[32] = { + { 8, LD+E8 }, /* 0 00 00: evldd[x] */ + { 8, LD+E4 }, /* 0 00 01: evldw[x] */ + { 8, LD }, /* 0 00 10: evldh[x] */ + INVALID, /* 0 00 11 */ + { 2, LD }, /* 0 01 00: evlhhesplat[x] */ + INVALID, /* 0 01 01 */ + { 2, LD }, /* 0 01 10: evlhhousplat[x] */ + { 2, LD+SE }, /* 0 01 11: evlhhossplat[x] */ + { 4, LD }, /* 0 10 00: evlwhe[x] */ + INVALID, /* 0 10 01 */ + { 4, LD }, /* 0 10 10: evlwhou[x] */ + { 4, LD+SE }, /* 0 10 11: evlwhos[x] */ + { 4, LD+E4 }, /* 0 11 00: evlwwsplat[x] */ + INVALID, /* 0 11 01 */ + { 4, LD }, /* 0 11 10: evlwhsplat[x] */ + INVALID, /* 0 11 11 */ + + { 8, ST+E8 }, /* 1 00 00: evstdd[x] */ + { 8, ST+E4 }, /* 1 00 01: evstdw[x] */ + { 8, ST }, /* 1 00 10: evstdh[x] */ + INVALID, /* 1 00 11 */ + INVALID, /* 1 01 00 */ + INVALID, /* 1 01 01 */ + INVALID, /* 1 01 10 */ + INVALID, /* 1 01 11 */ + { 4, ST }, /* 1 10 00: evstwhe[x] */ + INVALID, /* 1 10 01 */ + { 4, ST }, /* 1 10 10: evstwho[x] */ + INVALID, /* 1 10 11 */ + { 4, ST+E4 }, /* 1 11 00: evstwwe[x] */ + INVALID, /* 1 11 01 */ + { 4, ST+E4 }, /* 1 11 10: evstwwo[x] */ + INVALID, /* 1 11 11 */ +}; + +#define EVLDD 0x00 +#define EVLDW 0x01 +#define EVLDH 0x02 +#define EVLHHESPLAT 0x04 +#define EVLHHOUSPLAT 0x06 +#define EVLHHOSSPLAT 0x07 +#define EVLWHE 0x08 +#define EVLWHOU 0x0A +#define EVLWHOS 0x0B +#define EVLWWSPLAT 0x0C +#define EVLWHSPLAT 0x0E +#define EVSTDD 0x10 +#define EVSTDW 0x11 +#define EVSTDH 0x12 +#define EVSTWHE 0x18 +#define EVSTWHO 0x1A +#define EVSTWWE 0x1C +#define EVSTWWO 0x1E + +/* + * Emulate SPE loads and stores. + * Only Book-E has these instructions, and it does true little-endian, + * so we don't need the address swizzling. + */ +static int emulate_spe(struct pt_regs *regs, unsigned int reg, + unsigned int instr) +{ + int t, ret; + union { + u64 ll; + u32 w[2]; + u16 h[4]; + u8 v[8]; + } data, temp; + unsigned char __user *p, *addr; + unsigned long *evr = ¤t->thread.evr[reg]; + unsigned int nb, flags; + + instr = (instr >> 1) & 0x1f; + + /* DAR has the operand effective address */ + addr = (unsigned char __user *)regs->dar; + + nb = spe_aligninfo[instr].len; + flags = spe_aligninfo[instr].flags; + + /* Verify the address of the operand */ + if (unlikely(user_mode(regs) && + !access_ok((flags & ST ? VERIFY_WRITE : VERIFY_READ), + addr, nb))) + return -EFAULT; + + /* userland only */ + if (unlikely(!user_mode(regs))) + return 0; + + flush_spe_to_thread(current); + + /* If we are loading, get the data from user space, else + * get it from register values + */ + if (flags & ST) { + data.ll = 0; + switch (instr) { + case EVSTDD: + case EVSTDW: + case EVSTDH: + data.w[0] = *evr; + data.w[1] = regs->gpr[reg]; + break; + case EVSTWHE: + data.h[2] = *evr >> 16; + data.h[3] = regs->gpr[reg] >> 16; + break; + case EVSTWHO: + data.h[2] = *evr & 0xffff; + data.h[3] = regs->gpr[reg] & 0xffff; + break; + case EVSTWWE: + data.w[1] = *evr; + break; + case EVSTWWO: + data.w[1] = regs->gpr[reg]; + break; + default: + return -EINVAL; + } + } else { + temp.ll = data.ll = 0; + ret = 0; + p = addr; + + switch (nb) { + case 8: + ret |= __get_user_inatomic(temp.v[0], p++); + ret |= __get_user_inatomic(temp.v[1], p++); + ret |= __get_user_inatomic(temp.v[2], p++); + ret |= __get_user_inatomic(temp.v[3], p++); + case 4: + ret |= __get_user_inatomic(temp.v[4], p++); + ret |= __get_user_inatomic(temp.v[5], p++); + case 2: + ret |= __get_user_inatomic(temp.v[6], p++); + ret |= __get_user_inatomic(temp.v[7], p++); + if (unlikely(ret)) + return -EFAULT; + } + + switch (instr) { + case EVLDD: + case EVLDW: + case EVLDH: + data.ll = temp.ll; + break; + case EVLHHESPLAT: + data.h[0] = temp.h[3]; + data.h[2] = temp.h[3]; + break; + case EVLHHOUSPLAT: + case EVLHHOSSPLAT: + data.h[1] = temp.h[3]; + data.h[3] = temp.h[3]; + break; + case EVLWHE: + data.h[0] = temp.h[2]; + data.h[2] = temp.h[3]; + break; + case EVLWHOU: + case EVLWHOS: + data.h[1] = temp.h[2]; + data.h[3] = temp.h[3]; + break; + case EVLWWSPLAT: + data.w[0] = temp.w[1]; + data.w[1] = temp.w[1]; + break; + case EVLWHSPLAT: + data.h[0] = temp.h[2]; + data.h[1] = temp.h[2]; + data.h[2] = temp.h[3]; + data.h[3] = temp.h[3]; + break; + default: + return -EINVAL; + } + } + + if (flags & SW) { + switch (flags & 0xf0) { + case E8: + SWAP(data.v[0], data.v[7]); + SWAP(data.v[1], data.v[6]); + SWAP(data.v[2], data.v[5]); + SWAP(data.v[3], data.v[4]); + break; + case E4: + + SWAP(data.v[0], data.v[3]); + SWAP(data.v[1], data.v[2]); + SWAP(data.v[4], data.v[7]); + SWAP(data.v[5], data.v[6]); + break; + /* Its half word endian */ + default: + SWAP(data.v[0], data.v[1]); + SWAP(data.v[2], data.v[3]); + SWAP(data.v[4], data.v[5]); + SWAP(data.v[6], data.v[7]); + break; + } + } + + if (flags & SE) { + data.w[0] = (s16)data.h[1]; + data.w[1] = (s16)data.h[3]; + } + + /* Store result to memory or update registers */ + if (flags & ST) { + ret = 0; + p = addr; + switch (nb) { + case 8: + ret |= __put_user_inatomic(data.v[0], p++); + ret |= __put_user_inatomic(data.v[1], p++); + ret |= __put_user_inatomic(data.v[2], p++); + ret |= __put_user_inatomic(data.v[3], p++); + case 4: + ret |= __put_user_inatomic(data.v[4], p++); + ret |= __put_user_inatomic(data.v[5], p++); + case 2: + ret |= __put_user_inatomic(data.v[6], p++); + ret |= __put_user_inatomic(data.v[7], p++); + } + if (unlikely(ret)) + return -EFAULT; + } else { + *evr = data.w[0]; + regs->gpr[reg] = data.w[1]; + } + + return 1; +} +#endif /* CONFIG_SPE */ /* * Called on alignment exception. Attempts to fixup @@ -414,6 +694,12 @@ int fix_alignment(struct pt_regs *regs) /* extract the operation and registers from the dsisr */ reg = (dsisr >> 5) & 0x1f; /* source/dest register */ areg = dsisr & 0x1f; /* register to update */ + +#ifdef CONFIG_SPE + if ((instr >> 26) == 0x4) + return emulate_spe(regs, reg, instr); +#endif + instr = (dsisr >> 10) & 0x7f; instr |= (dsisr >> 13) & 0x60; @@ -471,6 +757,10 @@ int fix_alignment(struct pt_regs *regs) flush_fp_to_thread(current); } + /* Special case for 16-byte FP loads and stores */ + if (nb == 16) + return emulate_fp_pair(regs, addr, reg, flags); + /* If we are loading, get the data from user space, else * get it from register values */ @@ -531,7 +821,8 @@ int fix_alignment(struct pt_regs *regs) * or floating point single precision conversion */ switch (flags & ~(U|SW)) { - case LD+SE: /* sign extend */ + case LD+SE: /* sign extending integer loads */ + case LD+F+SE: /* sign extend for lfiwax */ if ( nb == 2 ) data.ll = data.x16.low16; else /* nb must be 4 */ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 2cb1d94..0ae5d57 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -312,5 +312,17 @@ int main(void) #ifdef CONFIG_BUG DEFINE(BUG_ENTRY_SIZE, sizeof(struct bug_entry)); #endif + +#ifdef CONFIG_PPC_ISERIES + /* the assembler miscalculates the VSID values */ + DEFINE(PAGE_OFFSET_ESID, GET_ESID(PAGE_OFFSET)); + DEFINE(PAGE_OFFSET_VSID, KERNEL_VSID(PAGE_OFFSET)); + DEFINE(VMALLOC_START_ESID, GET_ESID(VMALLOC_START)); + DEFINE(VMALLOC_START_VSID, KERNEL_VSID(VMALLOC_START)); +#endif + +#ifdef CONFIG_PPC64 + DEFINE(PGD_TABLE_SIZE, PGD_TABLE_SIZE); +#endif return 0; } diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c index e7b6846..3ef51fb 100644 --- a/arch/powerpc/kernel/btext.c +++ b/arch/powerpc/kernel/btext.c @@ -11,7 +11,6 @@ #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> diff --git a/arch/powerpc/kernel/clock.c b/arch/powerpc/kernel/clock.c new file mode 100644 index 0000000..ce668f5 --- /dev/null +++ b/arch/powerpc/kernel/clock.c @@ -0,0 +1,82 @@ +/* + * Dummy clk implementations for powerpc. + * These need to be overridden in platform code. + */ + +#include <linux/clk.h> +#include <linux/err.h> +#include <linux/errno.h> +#include <linux/module.h> +#include <asm/clk_interface.h> + +struct clk_interface clk_functions; + +struct clk *clk_get(struct device *dev, const char *id) +{ + if (clk_functions.clk_get) + return clk_functions.clk_get(dev, id); + return ERR_PTR(-ENOSYS); +} +EXPORT_SYMBOL(clk_get); + +void clk_put(struct clk *clk) +{ + if (clk_functions.clk_put) + clk_functions.clk_put(clk); +} +EXPORT_SYMBOL(clk_put); + +int clk_enable(struct clk *clk) +{ + if (clk_functions.clk_enable) + return clk_functions.clk_enable(clk); + return -ENOSYS; +} +EXPORT_SYMBOL(clk_enable); + +void clk_disable(struct clk *clk) +{ + if (clk_functions.clk_disable) + clk_functions.clk_disable(clk); +} +EXPORT_SYMBOL(clk_disable); + +unsigned long clk_get_rate(struct clk *clk) +{ + if (clk_functions.clk_get_rate) + return clk_functions.clk_get_rate(clk); + return 0; +} +EXPORT_SYMBOL(clk_get_rate); + +long clk_round_rate(struct clk *clk, unsigned long rate) +{ + if (clk_functions.clk_round_rate) + return clk_functions.clk_round_rate(clk, rate); + return -ENOSYS; +} +EXPORT_SYMBOL(clk_round_rate); + +int clk_set_rate(struct clk *clk, unsigned long rate) +{ + if (clk_functions.clk_set_rate) + return clk_functions.clk_set_rate(clk, rate); + return -ENOSYS; +} +EXPORT_SYMBOL(clk_set_rate); + +struct clk *clk_get_parent(struct clk *clk) +{ + if (clk_functions.clk_get_parent) + return clk_functions.clk_get_parent(clk); + return ERR_PTR(-ENOSYS); +} +EXPORT_SYMBOL(clk_get_parent); + +int clk_set_parent(struct clk *clk, struct clk *parent) +{ + if (clk_functions.clk_set_parent) + return clk_functions.clk_set_parent(clk, parent); + return -ENOSYS; +} +EXPORT_SYMBOL(clk_set_parent); diff --git a/arch/powerpc/kernel/cpu_setup_44x.S b/arch/powerpc/kernel/cpu_setup_44x.S new file mode 100644 index 0000000..8e1812e --- /dev/null +++ b/arch/powerpc/kernel/cpu_setup_44x.S @@ -0,0 +1,56 @@ +/* + * This file contains low level CPU setup functions. + * Valentine Barshak <vbarshak@ru.mvista.com> + * MontaVista Software, Inc (c) 2007 + * + * Based on cpu_setup_6xx code by + * Benjamin Herrenschmidt <benh@kernel.crashing.org> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + */ + +#include <asm/processor.h> +#include <asm/cputable.h> +#include <asm/ppc_asm.h> + +_GLOBAL(__setup_cpu_440ep) + b __init_fpu_44x +_GLOBAL(__setup_cpu_440epx) + mflr r4 + bl __init_fpu_44x + bl __plb_disable_wrp + mtlr r4 + blr +_GLOBAL(__setup_cpu_440grx) + b __plb_disable_wrp + + +/* enable APU between CPU and FPU */ +_GLOBAL(__init_fpu_44x) + mfspr r3,SPRN_CCR0 + /* Clear DAPUIB flag in CCR0 */ + rlwinm r3,r3,0,12,10 + mtspr SPRN_CCR0,r3 + isync + blr + +/* + * Workaround for the incorrect write to DDR SDRAM errata. + * The write address can be corrupted during writes to + * DDR SDRAM when write pipelining is enabled on PLB0. + * Disable write pipelining here. + */ +#define DCRN_PLB4A0_ACR 0x81 + +_GLOBAL(__plb_disable_wrp) + mfdcr r3,DCRN_PLB4A0_ACR + /* clear WRP bit in PLB4A0_ACR */ + rlwinm r3,r3,0,8,6 + mtdcr DCRN_PLB4A0_ACR,r3 + isync + blr + diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index b1f8000..d3fb7d0 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -31,6 +31,9 @@ EXPORT_SYMBOL(cur_cpu_spec); * and ppc64 */ #ifdef CONFIG_PPC32 +extern void __setup_cpu_440ep(unsigned long offset, struct cpu_spec* spec); +extern void __setup_cpu_440epx(unsigned long offset, struct cpu_spec* spec); +extern void __setup_cpu_440grx(unsigned long offset, struct cpu_spec* spec); 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); @@ -68,16 +71,7 @@ extern void __restore_cpu_ppc970(void); #define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \ PPC_FEATURE_BOOKE) -/* 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 - -static struct cpu_spec cpu_specs[] = { +static struct cpu_spec __initdata cpu_specs[] = { #ifdef CONFIG_PPC64 { /* Power3 */ .pvr_mask = 0xffff0000, @@ -333,14 +327,6 @@ static struct cpu_spec cpu_specs[] = { .cpu_user_features = COMMON_USER_POWER5_PLUS, .icache_bsize = 128, .dcache_bsize = 128, - .num_pmcs = 6, - .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power6", - .oprofile_type = PPC_OPROFILE_POWER4, - .oprofile_mmcra_sihv = POWER6_MMCRA_SIHV, - .oprofile_mmcra_sipr = POWER6_MMCRA_SIPR, - .oprofile_mmcra_clear = POWER6_MMCRA_THRM | - POWER6_MMCRA_OTHER, .platform = "power5+", }, { /* Power6 */ @@ -370,14 +356,6 @@ static struct cpu_spec cpu_specs[] = { .cpu_user_features = COMMON_USER_POWER6, .icache_bsize = 128, .dcache_bsize = 128, - .num_pmcs = 6, - .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power6", - .oprofile_type = PPC_OPROFILE_POWER4, - .oprofile_mmcra_sihv = POWER6_MMCRA_SIHV, - .oprofile_mmcra_sipr = POWER6_MMCRA_SIPR, - .oprofile_mmcra_clear = POWER6_MMCRA_THRM | - POWER6_MMCRA_OTHER, .platform = "power6", }, { /* Cell Broadband Engine */ @@ -1109,6 +1087,17 @@ static struct cpu_spec cpu_specs[] = { .dcache_bsize = 32, .platform = "ppc405", }, + { /* 405EX */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x12910000, + .cpu_name = "405EX", + .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, + .platform = "ppc405", + }, #endif /* CONFIG_40x */ #ifdef CONFIG_44x @@ -1120,6 +1109,7 @@ static struct cpu_spec cpu_specs[] = { .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, .icache_bsize = 32, .dcache_bsize = 32, + .cpu_setup = __setup_cpu_440ep, .platform = "ppc440", }, { @@ -1130,6 +1120,29 @@ static struct cpu_spec cpu_specs[] = { .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, .icache_bsize = 32, .dcache_bsize = 32, + .cpu_setup = __setup_cpu_440ep, + .platform = "ppc440", + }, + { /* 440EPX */ + .pvr_mask = 0xf0000ffb, + .pvr_value = 0x200008D0, + .cpu_name = "440EPX", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_440epx, + .platform = "ppc440", + }, + { /* 440GRX */ + .pvr_mask = 0xf0000ffb, + .pvr_value = 0x200008D8, + .cpu_name = "440GRX", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = COMMON_USER_BOOKE, + .icache_bsize = 32, + .dcache_bsize = 32, + .cpu_setup = __setup_cpu_440grx, .platform = "ppc440", }, { /* 440GP Rev. B */ @@ -1243,8 +1256,8 @@ static struct cpu_spec cpu_specs[] = { /* xxx - galak: add CPU_FTR_MAYBE_CAN_DOZE */ .cpu_features = CPU_FTRS_E200, .cpu_user_features = COMMON_USER_BOOKE | - PPC_FEATURE_SPE_COMP | - PPC_FEATURE_HAS_EFP_SINGLE | + PPC_FEATURE_HAS_SPE_COMP | + PPC_FEATURE_HAS_EFP_SINGLE_COMP | PPC_FEATURE_UNIFIED_CACHE, .dcache_bsize = 32, .platform = "ppc5554", @@ -1256,8 +1269,8 @@ static struct cpu_spec cpu_specs[] = { /* xxx - galak: add CPU_FTR_MAYBE_CAN_DOZE */ .cpu_features = CPU_FTRS_E500, .cpu_user_features = COMMON_USER_BOOKE | - PPC_FEATURE_SPE_COMP | - PPC_FEATURE_HAS_EFP_SINGLE, + PPC_FEATURE_HAS_SPE_COMP | + PPC_FEATURE_HAS_EFP_SINGLE_COMP, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -1272,9 +1285,9 @@ static struct cpu_spec cpu_specs[] = { /* xxx - galak: add CPU_FTR_MAYBE_CAN_DOZE */ .cpu_features = CPU_FTRS_E500_2, .cpu_user_features = COMMON_USER_BOOKE | - PPC_FEATURE_SPE_COMP | - PPC_FEATURE_HAS_EFP_SINGLE | - PPC_FEATURE_HAS_EFP_DOUBLE, + PPC_FEATURE_HAS_SPE_COMP | + PPC_FEATURE_HAS_EFP_SINGLE_COMP | + PPC_FEATURE_HAS_EFP_DOUBLE_COMP, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -1298,29 +1311,49 @@ static struct cpu_spec cpu_specs[] = { #endif /* CONFIG_PPC32 */ }; -struct cpu_spec *identify_cpu(unsigned long offset, unsigned int pvr) +static struct cpu_spec the_cpu_spec; + +struct cpu_spec * __init identify_cpu(unsigned long offset, unsigned int pvr) { struct cpu_spec *s = cpu_specs; - struct cpu_spec **cur = &cur_cpu_spec; + struct cpu_spec *t = &the_cpu_spec; int i; s = PTRRELOC(s); - cur = PTRRELOC(cur); + t = PTRRELOC(t); for (i = 0; i < ARRAY_SIZE(cpu_specs); i++,s++) if ((pvr & s->pvr_mask) == s->pvr_value) { - *cur = cpu_specs + i; -#ifdef CONFIG_PPC64 - /* ppc64 expects identify_cpu to also call setup_cpu - * for that processor. I will consolidate that at a - * later time, for now, just use our friend #ifdef. + /* + * If we are overriding a previous value derived + * from the real PVR with a new value obtained + * using a logical PVR value, don't modify the + * performance monitor fields. + */ + if (t->num_pmcs && !s->num_pmcs) { + t->cpu_name = s->cpu_name; + t->cpu_features = s->cpu_features; + t->cpu_user_features = s->cpu_user_features; + t->icache_bsize = s->icache_bsize; + t->dcache_bsize = s->dcache_bsize; + t->cpu_setup = s->cpu_setup; + t->cpu_restore = s->cpu_restore; + t->platform = s->platform; + } else + *t = *s; + *PTRRELOC(&cur_cpu_spec) = &the_cpu_spec; +#if defined(CONFIG_PPC64) || defined(CONFIG_BOOKE) + /* ppc64 and booke expect identify_cpu to also call + * setup_cpu for that processor. I will consolidate + * that at a later time, for now, just use #ifdef. * we also don't need to PTRRELOC the function pointer - * on ppc64 as we are running at 0 in real mode. + * on ppc64 and booke as we are running at 0 in real + * mode on ppc64 and reloc_offset is always 0 on booke. */ if (s->cpu_setup) { s->cpu_setup(offset, s); } -#endif /* CONFIG_PPC64 */ +#endif /* CONFIG_PPC64 || CONFIG_BOOKE */ return s; } BUG(); diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c index 37658ea..77c749a 100644 --- a/arch/powerpc/kernel/crash.c +++ b/arch/powerpc/kernel/crash.c @@ -24,7 +24,6 @@ #include <linux/init.h> #include <linux/irq.h> #include <linux/types.h> -#include <linux/irq.h> #include <asm/processor.h> #include <asm/machdep.h> diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c index 2f6f5a7..29ff77c 100644 --- a/arch/powerpc/kernel/crash_dump.c +++ b/arch/powerpc/kernel/crash_dump.c @@ -25,7 +25,7 @@ #define DBG(fmt...) #endif -void reserve_kdump_trampoline(void) +void __init reserve_kdump_trampoline(void) { lmb_reserve(0, KDUMP_RESERVE_LIMIT); } @@ -54,8 +54,10 @@ void __init setup_kdump_trampoline(void) create_trampoline(i); } +#ifdef CONFIG_PPC_PSERIES create_trampoline(__pa(system_reset_fwnmi) - PHYSICAL_START); create_trampoline(__pa(machine_check_fwnmi) - PHYSICAL_START); +#endif /* CONFIG_PPC_PSERIES */ DBG(" <- setup_kdump_trampoline()\n"); } diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 4074c0b..21d889e 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -504,9 +504,11 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #endif /* CONFIG_ALTIVEC */ #ifdef CONFIG_SPE +BEGIN_FTR_SECTION oris r0,r0,MSR_SPE@h /* Disable SPE */ mfspr r12,SPRN_SPEFSCR /* save spefscr register value */ stw r12,THREAD+THREAD_SPEFSCR(r2) +END_FTR_SECTION_IFSET(CPU_FTR_SPE) #endif /* CONFIG_SPE */ and. r0,r0,r11 /* FP or altivec or SPE enabled? */ beq+ 1f @@ -542,8 +544,10 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #endif /* CONFIG_ALTIVEC */ #ifdef CONFIG_SPE +BEGIN_FTR_SECTION lwz r0,THREAD+THREAD_SPEFSCR(r2) mtspr SPRN_SPEFSCR,r0 /* restore SPEFSCR reg */ +END_FTR_SECTION_IFSET(CPU_FTR_SPE) #endif /* CONFIG_SPE */ lwz r0,_CCR(r1) diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 952eba6..0ec1340 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -373,8 +373,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) ld r8,KSP(r4) /* new stack pointer */ BEGIN_FTR_SECTION + b 2f +END_FTR_SECTION_IFCLR(CPU_FTR_SLB) +BEGIN_FTR_SECTION clrrdi r6,r8,28 /* get its ESID */ clrrdi r9,r1,28 /* get current sp ESID */ +END_FTR_SECTION_IFCLR(CPU_FTR_1T_SEGMENT) +BEGIN_FTR_SECTION + clrrdi r6,r8,40 /* get its 1T ESID */ + clrrdi r9,r1,40 /* get current sp 1T ESID */ +END_FTR_SECTION_IFSET(CPU_FTR_1T_SEGMENT) 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 @@ -384,16 +392,21 @@ BEGIN_FTR_SECTION 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 - - /* Update the last bolted SLB */ +BEGIN_FTR_SECTION + li r9,MMU_SEGSIZE_1T /* insert B field */ + oris r6,r6,(MMU_SEGSIZE_1T << SLBIE_SSIZE_SHIFT)@h + rldimi r7,r9,SLB_VSID_SSIZE_SHIFT,0 +END_FTR_SECTION_IFSET(CPU_FTR_1T_SEGMENT) + + /* Update the last bolted SLB. No write barriers are needed + * here, provided we only update the current CPU's SLB shadow + * buffer. + */ ld r9,PACA_SLBSHADOWPTR(r13) li r12,0 std r12,SLBSHADOW_STACKESID(r9) /* Clear ESID */ - eieio std r7,SLBSHADOW_STACKVSID(r9) /* Save VSID */ - eieio std r0,SLBSHADOW_STACKESID(r9) /* Save ESID */ - eieio slbie r6 slbie r6 /* Workaround POWER5 < DD2.1 issue */ @@ -401,7 +414,6 @@ BEGIN_FTR_SECTION 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 diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index 7d73a13..a5b13ae 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -48,20 +48,17 @@ mtspr SPRN_DBAT##n##L,RB; \ 1: - .text + .section .text.head, "ax" .stabs "arch/powerpc/kernel/",N_SO,0,0,0f .stabs "head_32.S",N_SO,0,0,0f 0: - .globl _stext -_stext: +_ENTRY(_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: +_ENTRY(_start); /* * These are here for legacy reasons, the kernel used to * need to look like a coff function entry for the pmac @@ -152,6 +149,9 @@ __after_mmu_off: #if defined(CONFIG_BOOTX_TEXT) bl setup_disp_bat #endif +#ifdef CONFIG_PPC_EARLY_DEBUG_CPM + bl setup_cpm_bat +#endif /* * Call setup_cpu for CPU 0 and initialize 6xx Idle @@ -469,16 +469,16 @@ InstructionTLBMiss: 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 + lis r1,PAGE_OFFSET@h /* check if kernel address */ + cmplw 0,r1,r3 mfspr r2,SPRN_SPRG3 li r1,_PAGE_USER|_PAGE_PRESENT /* low addresses tested as user */ lwz r2,PGDIR(r2) - blt+ 112f + bge- 112f + mfspr r2,SPRN_SRR1 /* and MSR_PR bit from SRR1 */ + rlwimi r1,r2,32-12,29,29 /* shift MSR_PR to _PAGE_USER posn */ 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 */ @@ -543,16 +543,16 @@ DataLoadTLBMiss: 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 + lis r1,PAGE_OFFSET@h /* check if kernel address */ + cmplw 0,r1,r3 mfspr r2,SPRN_SPRG3 li r1,_PAGE_USER|_PAGE_PRESENT /* low addresses tested as user */ lwz r2,PGDIR(r2) - blt+ 112f + bge- 112f + mfspr r2,SPRN_SRR1 /* and MSR_PR bit from SRR1 */ + rlwimi r1,r2,32-12,29,29 /* shift MSR_PR to _PAGE_USER posn */ 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 */ @@ -615,16 +615,16 @@ DataStoreTLBMiss: 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 + lis r1,PAGE_OFFSET@h /* check if kernel address */ + cmplw 0,r1,r3 mfspr r2,SPRN_SPRG3 li r1,_PAGE_RW|_PAGE_USER|_PAGE_PRESENT /* access flags */ lwz r2,PGDIR(r2) - blt+ 112f + bge- 112f + mfspr r2,SPRN_SRR1 /* and MSR_PR bit from SRR1 */ + rlwimi r1,r2,32-12,29,29 /* shift MSR_PR to _PAGE_USER posn */ 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 */ @@ -841,7 +841,7 @@ relocate_kernel: * 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) +_ENTRY(copy_and_flush) addi r5,r5,-4 addi r6,r6,-4 4: li r0,L1_CACHE_BYTES/4 @@ -954,9 +954,9 @@ __secondary_start: * included in CONFIG_6xx */ #if !defined(CONFIG_6xx) -_GLOBAL(__save_cpu_setup) +_ENTRY(__save_cpu_setup) blr -_GLOBAL(__restore_cpu_setup) +_ENTRY(__restore_cpu_setup) blr #endif /* !defined(CONFIG_6xx) */ @@ -1080,7 +1080,7 @@ start_here: /* * Set up the segment registers for a new context. */ -_GLOBAL(set_context) +_ENTRY(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 */ @@ -1248,6 +1248,19 @@ setup_disp_bat: blr #endif /* CONFIG_BOOTX_TEXT */ +#ifdef CONFIG_PPC_EARLY_DEBUG_CPM +setup_cpm_bat: + lis r8, 0xf000 + ori r8, r8, 0x002a + mtspr SPRN_DBAT1L, r8 + + lis r11, 0xf000 + ori r11, r11, (BL_1M << 2) | 2 + mtspr SPRN_DBAT1U, r11 + + blr +#endif + #ifdef CONFIG_8260 /* Jump into the system reset for the rom. * We first disable the MMU, and then jump to the ROM reset address. @@ -1300,14 +1313,6 @@ empty_zero_page: 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 diff --git a/arch/powerpc/kernel/head_4xx.S b/arch/powerpc/kernel/head_40x.S index adc7f80..cfefc2d 100644 --- a/arch/powerpc/kernel/head_4xx.S +++ b/arch/powerpc/kernel/head_40x.S @@ -35,7 +35,6 @@ #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> @@ -53,9 +52,9 @@ * * This is all going to change RSN when we add bi_recs....... -- Dan */ - .text -_GLOBAL(_stext) -_GLOBAL(_start) + .section .text.head, "ax" +_ENTRY(_stext); +_ENTRY(_start); /* Save parameters we are passed. */ @@ -90,9 +89,9 @@ turn_on_mmu: */ . = 0xc0 crit_save: -_GLOBAL(crit_r10) +_ENTRY(crit_r10) .space 4 -_GLOBAL(crit_r11) +_ENTRY(crit_r11) .space 4 /* @@ -290,7 +289,7 @@ label: /* If we are faulting a kernel address, we have to use the * kernel page tables. */ - lis r11, TASK_SIZE@h + lis r11, PAGE_OFFSET@h cmplw r10, r11 blt+ 3f lis r11, swapper_pg_dir@h @@ -482,7 +481,7 @@ label: /* If we are faulting a kernel address, we have to use the * kernel page tables. */ - lis r11, TASK_SIZE@h + lis r11, PAGE_OFFSET@h cmplw r10, r11 blt+ 3f lis r11, swapper_pg_dir@h @@ -582,7 +581,7 @@ label: /* If we are faulting a kernel address, we have to use the * kernel page tables. */ - lis r11, TASK_SIZE@h + lis r11, PAGE_OFFSET@h cmplw r10, r11 blt+ 3f lis r11, swapper_pg_dir@h @@ -772,7 +771,7 @@ finish_tlb_load: */ lwz r9, tlb_4xx_index@l(0) addi r9, r9, 1 - andi. r9, r9, (PPC4XX_TLB_SIZE-1) + andi. r9, r9, (PPC40X_TLB_SIZE-1) stw r9, tlb_4xx_index@l(0) 6: @@ -815,7 +814,7 @@ finish_tlb_load: * The PowerPC 4xx family of processors do not have an FPU, so this just * returns. */ -_GLOBAL(giveup_fpu) +_ENTRY(giveup_fpu) blr /* This is where the main kernel code starts. @@ -1007,13 +1006,6 @@ 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. */ diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S index 8869596..409db61 100644 --- a/arch/powerpc/kernel/head_44x.S +++ b/arch/powerpc/kernel/head_44x.S @@ -50,9 +50,9 @@ * r7 - End of kernel command line string * */ - .text -_GLOBAL(_stext) -_GLOBAL(_start) + .section .text.head, "ax" +_ENTRY(_stext); +_ENTRY(_start); /* * Reserve a word at a fixed location to store the address * of abatron_pteptrs @@ -217,16 +217,6 @@ skpinv: addi r4,r4,1 /* Increment */ 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. */ @@ -329,7 +319,7 @@ interrupt_base: /* If we are faulting a kernel address, we have to use the * kernel page tables. */ - lis r11, TASK_SIZE@h + lis r11, PAGE_OFFSET@h cmplw r10, r11 blt+ 3f lis r11, swapper_pg_dir@h @@ -468,7 +458,7 @@ interrupt_base: /* If we are faulting a kernel address, we have to use the * kernel page tables. */ - lis r11, TASK_SIZE@h + lis r11, PAGE_OFFSET@h cmplw r10, r11 blt+ 3f lis r11, swapper_pg_dir@h @@ -538,7 +528,7 @@ interrupt_base: /* If we are faulting a kernel address, we have to use the * kernel page tables. */ - lis r11, TASK_SIZE@h + lis r11, PAGE_OFFSET@h cmplw r10, r11 blt+ 3f lis r11, swapper_pg_dir@h @@ -744,14 +734,6 @@ exception_stack_bottom: 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. */ diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 1718000..97c5857 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -34,6 +34,8 @@ #include <asm/iseries/lpar_map.h> #include <asm/thread_info.h> #include <asm/firmware.h> +#include <asm/page_64.h> +#include <asm/exception.h> #define DO_SOFT_DISABLE @@ -144,344 +146,9 @@ exception_marker: .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_DAR 48 -#define EX_DSISR 56 -#define EX_CCR 60 -#define EX_R3 64 -#define EX_LR 72 - -/* - * We're short on space and time in the exception prolog, so we can't - * use the normal SET_REG_IMMEDIATE macro. Normally we just need the - * low halfword of the address, but for Kdump we need the whole low - * word. - */ -#ifdef CONFIG_CRASH_DUMP -#define LOAD_HANDLER(reg, label) \ - oris reg,reg,(label)@h; /* virt addr of handler ... */ \ - ori reg,reg,(label)@l; /* .. and the rest */ -#else -#define LOAD_HANDLER(reg, label) \ - ori reg,reg,(label)@l; /* virt addr of handler ... */ -#endif - -/* - * Equal to EXCEPTION_PROLOG_PSERIES, except that it forces 64bit mode. - * The firmware calls the registered system_reset_fwnmi and - * machine_check_fwnmi handlers in 32bit mode if the cpu happens to run - * a 32bit application at the time of the event. - * This firmware bug is present on POWER4 and JS20. - */ -#define EXCEPTION_PROLOG_PSERIES_FORCE_64BIT(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; \ - /* force 64bit mode */ \ - li r11,5; /* MSR_SF_LG|MSR_ISF_LG */ \ - rldimi r10,r11,61,0; /* insert into top 3 bits */ \ - /* done 64bit mode */ \ - mfspr r11,SPRN_SRR0; /* save SRR0 */ \ - LOAD_HANDLER(r12,label) \ - 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 */ - -#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 */ \ - LOAD_HANDLER(r12,label) \ - 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 r12,PACALPPACAPTR(r13); \ - ld r11,LPPACASRR0(r12); \ - ld r12,LPPACASRR1(r12); \ - 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- cr1,2f; /* abort if it is */ \ - b 3f; \ -2: li r1,(n); /* will be reloaded later */ \ - sth r1,PACA_TRAP_SAVE(r13); \ - b bad_stack; \ -3: 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 */ \ - ACCOUNT_CPU_USER_ENTRY(r9, r10); \ - 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); \ - lbz r10,PACASOFTIRQEN(r13); \ - mfspr r11,SPRN_XER; /* save XER in stackframe */ \ - std r10,SOFTE(r1); \ - 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 */ \ - EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common) - -#define HSTD_EXCEPTION_PSERIES(n, label) \ - . = n; \ - .globl label##_pSeries; \ -label##_pSeries: \ - HMT_MEDIUM; \ - mtspr SPRN_SPRG1,r20; /* save r20 */ \ - mfspr r20,SPRN_HSRR0; /* copy HSRR0 to SRR0 */ \ - mtspr SPRN_SRR0,r20; \ - mfspr r20,SPRN_HSRR1; /* copy HSRR0 to SRR0 */ \ - mtspr SPRN_SRR1,r20; \ - mfspr r20,SPRN_SPRG1; /* restore r20 */ \ - mtspr SPRN_SPRG1,r13; /* save r13 */ \ - EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common) - - -#define MASKABLE_EXCEPTION_PSERIES(n, label) \ - . = n; \ - .globl label##_pSeries; \ -label##_pSeries: \ - HMT_MEDIUM; \ - mtspr SPRN_SPRG1,r13; /* save r13 */ \ - mfspr r13,SPRN_SPRG3; /* get paca address into r13 */ \ - std r9,PACA_EXGEN+EX_R9(r13); /* save r9, r10 */ \ - std r10,PACA_EXGEN+EX_R10(r13); \ - lbz r10,PACASOFTIRQEN(r13); \ - mfcr r9; \ - cmpwi r10,0; \ - beq masked_interrupt; \ - mfspr r10,SPRN_SPRG1; \ - std r10,PACA_EXGEN+EX_R13(r13); \ - std r11,PACA_EXGEN+EX_R11(r13); \ - std r12,PACA_EXGEN+EX_R12(r13); \ - clrrdi r12,r13,32; /* get high part of &label */ \ - mfmsr r10; \ - mfspr r11,SPRN_SRR0; /* save SRR0 */ \ - LOAD_HANDLER(r12,label##_common) \ - 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 */ - -#define STD_EXCEPTION_ISERIES(n, label, area) \ - .globl label##_iSeries; \ -label##_iSeries: \ - HMT_MEDIUM; \ - mtspr SPRN_SPRG1,r13; /* save 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 */ \ - EXCEPTION_PROLOG_ISERIES_1(PACA_EXGEN); \ - lbz r10,PACASOFTIRQEN(r13); \ - cmpwi 0,r10,0; \ - beq- label##_iSeries_masked; \ - EXCEPTION_PROLOG_ISERIES_2; \ - b label##_common; \ - -#ifdef CONFIG_PPC_ISERIES -#define DISABLE_INTS \ - li r11,0; \ - stb r11,PACASOFTIRQEN(r13); \ -BEGIN_FW_FTR_SECTION; \ - stb r11,PACAHARDIRQEN(r13); \ -END_FW_FTR_SECTION_IFCLR(FW_FEATURE_ISERIES); \ -BEGIN_FW_FTR_SECTION; \ - mfmsr r10; \ - ori r10,r10,MSR_EE; \ - mtmsrd r10,1; \ -END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES) - -#else -#define DISABLE_INTS \ - li r11,0; \ - stb r11,PACASOFTIRQEN(r13); \ - stb r11,PACAHARDIRQEN(r13) - -#endif /* CONFIG_PPC_ISERIES */ - -#define ENABLE_INTS \ - ld r12,_MSR(r1); \ - mfmsr r11; \ - rlwimi r11,r12,0,MSR_EE; \ - mtmsrd r11,1 - -#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 - -/* - * Like STD_EXCEPTION_COMMON, but for exceptions that can occur - * in the idle task and therefore need the special idle handling. - */ -#define STD_EXCEPTION_COMMON_IDLE(trap, label, hdlr) \ - .align 7; \ - .globl label##_common; \ -label##_common: \ - EXCEPTION_PROLOG_COMMON(trap, PACA_EXGEN); \ - FINISH_NAP; \ - 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); \ - FINISH_NAP; \ - DISABLE_INTS; \ - bl .ppc64_runlatch_on; \ - addi r3,r1,STACK_FRAME_OVERHEAD; \ - bl hdlr; \ - b .ret_from_except_lite - -/* - * When the idle code in power4_idle puts the CPU into NAP mode, - * it has to do so in a loop, and relies on the external interrupt - * and decrementer interrupt entry code to get it out of the loop. - * It sets the _TLF_NAPPING bit in current_thread_info()->local_flags - * to signal that it is in the loop and needs help to get out. - */ -#ifdef CONFIG_PPC_970_NAP -#define FINISH_NAP \ -BEGIN_FTR_SECTION \ - clrrdi r11,r1,THREAD_SHIFT; \ - ld r9,TI_LOCAL_FLAGS(r11); \ - andi. r10,r9,_TLF_NAPPING; \ - bnel power4_fixup_nap; \ -END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP) -#else -#define FINISH_NAP -#endif - -/* - * Start of pSeries system interrupt routines - */ . = 0x100 .globl __start_interrupts __start_interrupts: @@ -674,6 +341,7 @@ slb_miss_user_pseries: b . /* prevent spec. execution */ #endif /* __DISABLED__ */ +#ifdef CONFIG_PPC_PSERIES /* * Vectors for the FWNMI option. Share common code. */ @@ -691,191 +359,7 @@ machine_check_fwnmi: mtspr SPRN_SPRG1,r13 /* save r13 */ EXCEPTION_PROLOG_PSERIES_FORCE_64BIT(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 */ - mfspr r13,SPRN_SPRG3 /* get paca address into r13 */ - std r3,PACA_EXSLB+EX_R3(r13) - mfspr r3,SPRN_DAR - std r9,PACA_EXSLB+EX_R9(r13) - mfcr r9 -#ifdef __DISABLED__ - cmpdi r3,0 - bge slb_miss_user_iseries -#endif - std r10,PACA_EXSLB+EX_R10(r13) - std r11,PACA_EXSLB+EX_R11(r13) - std r12,PACA_EXSLB+EX_R12(r13) - mfspr r10,SPRN_SPRG1 - std r10,PACA_EXSLB+EX_R13(r13) - ld r12,PACALPPACAPTR(r13) - ld r12,LPPACASRR1(r12) - b .slb_miss_realmode - - STD_EXCEPTION_ISERIES(0x400, instruction_access, PACA_EXGEN) - - .globl instruction_access_slb_iSeries -instruction_access_slb_iSeries: - mtspr SPRN_SPRG1,r13 /* save r13 */ - mfspr r13,SPRN_SPRG3 /* get paca address into r13 */ - std r3,PACA_EXSLB+EX_R3(r13) - ld r3,PACALPPACAPTR(r13) - ld r3,LPPACASRR0(r3) /* get SRR0 value */ - std r9,PACA_EXSLB+EX_R9(r13) - mfcr r9 -#ifdef __DISABLED__ - cmpdi r3,0 - bge .slb_miss_user_iseries -#endif - std r10,PACA_EXSLB+EX_R10(r13) - std r11,PACA_EXSLB+EX_R11(r13) - std r12,PACA_EXSLB+EX_R12(r13) - mfspr r10,SPRN_SPRG1 - std r10,PACA_EXSLB+EX_R13(r13) - ld r12,PACALPPACAPTR(r13) - ld r12,LPPACASRR1(r12) - b .slb_miss_realmode - -#ifdef __DISABLED__ -slb_miss_user_iseries: - std r10,PACA_EXGEN+EX_R10(r13) - std r11,PACA_EXGEN+EX_R11(r13) - std r12,PACA_EXGEN+EX_R12(r13) - mfspr r10,SPRG1 - ld r11,PACA_EXSLB+EX_R9(r13) - ld r12,PACA_EXSLB+EX_R3(r13) - std r10,PACA_EXGEN+EX_R13(r13) - std r11,PACA_EXGEN+EX_R9(r13) - std r12,PACA_EXGEN+EX_R3(r13) - EXCEPTION_PROLOG_ISERIES_2 - b slb_miss_user_common -#endif - - 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? */ - bne 1f - b .__start_initialization_iSeries /* Start up the first processor */ -1: 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 - LOAD_REG_IMMEDIATE(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 */ - -decrementer_iSeries_masked: - /* We may not have a valid TOC pointer in here. */ - li r11,1 - ld r12,PACALPPACAPTR(r13) - stb r11,LPPACADECRINT(r12) - LOAD_REG_IMMEDIATE(r12, tb_ticks_per_jiffy) - lwz r12,0(r12) - mtspr SPRN_DEC,r12 - /* fall through */ - -hardware_interrupt_iSeries_masked: - mtcrf 0x80,r9 /* Restore regs */ - ld r12,PACALPPACAPTR(r13) - ld r11,LPPACASRR0(r12) - ld r12,LPPACASRR1(r12) - 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 */ +#endif /* CONFIG_PPC_PSERIES */ /*** Common interrupt handlers ***/ @@ -1175,7 +659,9 @@ hardware_interrupt_common: FINISH_NAP hardware_interrupt_entry: DISABLE_INTS +BEGIN_FTR_SECTION bl .ppc64_runlatch_on +END_FTR_SECTION_IFSET(CPU_FTR_CTRL) addi r3,r1,STACK_FRAME_OVERHEAD bl .do_IRQ b .ret_from_except_lite @@ -1449,7 +935,7 @@ _GLOBAL(do_stab_bolted) /* Calculate VSID */ /* This is a kernel address, so protovsid = ESID */ - ASM_VSID_SCRAMBLE(r11, r9) + ASM_VSID_SCRAMBLE(r11, r9, 256M) rldic r9,r11,12,16 /* r9 = vsid << 12 */ /* Search the primary group for a free entry */ @@ -1519,8 +1005,8 @@ _GLOBAL(do_stab_bolted) * 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 + * we get control (with relocate on). The address is given to the hv + * as a page number (see xLparMap below), so this must be at a * fixed address (the linker can't compute (u64)&initial_stab >> * PAGE_SHIFT). */ @@ -1529,6 +1015,7 @@ _GLOBAL(do_stab_bolted) initial_stab: .space 4096 +#ifdef CONFIG_PPC_PSERIES /* * Data area reserved for FWNMI option. * This address (0x7000) is fixed by the RPA. @@ -1536,21 +1023,34 @@ initial_stab: .= 0x7000 .globl fwnmi_data_area fwnmi_data_area: +#endif /* CONFIG_PPC_PSERIES */ /* 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 + .globl xLparMap +xLparMap: + .quad HvEsidsToMap /* xNumberEsids */ + .quad HvRangesToMap /* xNumberRanges */ + .quad STAB0_PAGE /* xSegmentTableOffs */ + .zero 40 /* xRsvd */ + /* xEsids (HvEsidsToMap entries of 2 quads) */ + .quad PAGE_OFFSET_ESID /* xKernelEsid */ + .quad PAGE_OFFSET_VSID /* xKernelVsid */ + .quad VMALLOC_START_ESID /* xKernelEsid */ + .quad VMALLOC_START_VSID /* xKernelVsid */ + /* xRanges (HvRangesToMap entries of 3 quads) */ + .quad HvPagesToMap /* xPages */ + .quad 0 /* xOffset */ + .quad PAGE_OFFSET_VSID << (SID_SHIFT - HW_PAGE_SHIFT) /* xVPN */ + #endif /* CONFIG_PPC_ISERIES */ +#ifdef CONFIG_PPC_PSERIES . = 0x8000 +#endif /* CONFIG_PPC_PSERIES */ /* * On pSeries and most other platforms, secondary processors spin @@ -1611,39 +1111,6 @@ _GLOBAL(generic_secondary_smp_init) b __secondary_start #endif -#ifdef CONFIG_PPC_ISERIES -_INIT_STATIC(__start_initialization_iSeries) - /* Clear out the BSS */ - LOAD_REG_IMMEDIATE(r11,__bss_stop) - LOAD_REG_IMMEDIATE(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: - LOAD_REG_IMMEDIATE(r1,init_thread_union) - addi r1,r1,THREAD_SIZE - li r0,0 - stdu r0,-STACK_FRAME_OVERHEAD(r1) - - LOAD_REG_IMMEDIATE(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 */ - - _STATIC(__mmu_off) mfmsr r3 andi. r0,r3,MSR_IR|MSR_DR @@ -1891,6 +1358,7 @@ _GLOBAL(pmac_secondary_start) * r13 = paca virtual address * SPRG3 = paca virtual address */ + .globl __secondary_start __secondary_start: /* Set thread priority to MEDIUM */ HMT_MEDIUM @@ -2021,7 +1489,7 @@ _INIT_STATIC(start_here_multiplatform) b . /* prevent speculative execution */ /* This is where all platforms converge execution */ -_INIT_STATIC(start_here_common) +_INIT_GLOBAL(start_here_common) /* relocation is on at this point */ /* The following code sets up the SP and TOC now that we are */ @@ -2078,12 +1546,4 @@ empty_zero_page: .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 + .space PGD_TABLE_SIZE diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 901be47..f745839 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -38,12 +38,9 @@ #else #define DO_8xx_CPU6(val, reg) #endif - .text - .globl _stext -_stext: - .text - .globl _start -_start: + .section .text.head, "ax" +_ENTRY(_stext); +_ENTRY(_start); /* MPC8xx * This port was done on an MBX board with an 860. Right now I only @@ -301,6 +298,12 @@ InstructionTLBMiss: stw r10, 0(r0) stw r11, 4(r0) mfspr r10, SPRN_SRR0 /* Get effective address of fault */ +#ifdef CONFIG_8xx_CPU15 + addi r11, r10, 0x1000 + tlbie r11 + addi r11, r10, -0x1000 + tlbie r11 +#endif 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 */ @@ -730,13 +733,13 @@ initial_mmu: 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 + mtspr SPRN_MD_RPN, r11 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 + mtspr SPRN_MD_RPN, r11 #endif /* Since the cache is enabled according to the information we @@ -835,14 +838,6 @@ empty_zero_page: 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). */ diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index 1f155d3..4b98227 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -2,27 +2,27 @@ * Kernel execution entry point code. * * Copyright (c) 1995-1996 Gary Thomas <gdt@linuxppc.org> - * Initial PowerPC version. + * Initial PowerPC version. * Copyright (c) 1996 Cort Dougan <cort@cs.nmt.edu> - * Rewritten for PReP + * Rewritten for PReP * Copyright (c) 1996 Paul Mackerras <paulus@cs.anu.edu.au> - * Low-level exception handers, MMU support, and rewrite. + * Low-level exception handers, MMU support, and rewrite. * Copyright (c) 1997 Dan Malek <dmalek@jlc.net> - * PowerPC 8xx modifications. + * PowerPC 8xx modifications. * Copyright (c) 1998-1999 TiVo, Inc. - * PowerPC 403GCX modifications. + * PowerPC 403GCX modifications. * Copyright (c) 1999 Grant Erickson <grant@lcse.umn.edu> - * PowerPC 403GCX/405GP modifications. + * 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 + * 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> + * PowerPC 44x support, Matt Porter <mporter@kernel.crashing.org> * Copyright 2004 Freescale Semiconductor, Inc - * PowerPC e500 modifications, Kumar Gala <galak@kernel.crashing.org> + * PowerPC e500 modifications, Kumar Gala <galak@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 @@ -52,9 +52,9 @@ * r7 - End of kernel command line string * */ - .text -_GLOBAL(_stext) -_GLOBAL(_start) + .section .text.head, "ax" +_ENTRY(_stext); +_ENTRY(_start); /* * Reserve a word at a fixed location to store the address * of abatron_pteptrs @@ -146,13 +146,13 @@ skpinv: addi r6,r6,1 /* Increment */ bne 1b /* If not, repeat */ /* Invalidate TLB0 */ - li r6,0x04 + li r6,0x04 tlbivax 0,r6 #ifdef CONFIG_SMP tlbsync #endif /* Invalidate TLB1 */ - li r6,0x0c + li r6,0x0c tlbivax 0,r6 #ifdef CONFIG_SMP tlbsync @@ -211,7 +211,7 @@ skpinv: addi r6,r6,1 /* Increment */ mtspr SPRN_MAS1,r6 tlbwe /* Invalidate TLB1 */ - li r9,0x0c + li r9,0x0c tlbivax 0,r9 #ifdef CONFIG_SMP tlbsync @@ -254,7 +254,7 @@ skpinv: addi r6,r6,1 /* Increment */ mtspr SPRN_MAS1,r8 tlbwe /* Invalidate TLB1 */ - li r9,0x0c + li r9,0x0c tlbivax 0,r9 #ifdef CONFIG_SMP tlbsync @@ -294,7 +294,7 @@ skpinv: addi r6,r6,1 /* Increment */ #ifdef CONFIG_E200 oris r2,r2,MAS4_TLBSELD(1)@h #endif - mtspr SPRN_MAS4, r2 + mtspr SPRN_MAS4, r2 #if 0 /* Enable DOZE */ @@ -305,7 +305,7 @@ skpinv: addi r6,r6,1 /* Increment */ #ifdef CONFIG_E200 /* enable dedicated debug exception handling resources (Debug APU) */ mfspr r2,SPRN_HID0 - ori r2,r2,HID0_DAPUEN@l + ori r2,r2,HID0_DAPUEN@l mtspr SPRN_HID0,r2 #endif @@ -391,7 +391,7 @@ skpinv: addi r6,r6,1 /* Increment */ #ifdef CONFIG_PTE_64BIT #define PTE_FLAGS_OFFSET 4 #define FIND_PTE \ - rlwinm r12, r10, 13, 19, 29; /* Compute pgdir/pmd offset */ \ + 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 */ \ @@ -461,8 +461,7 @@ interrupt_base: /* 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 + lis r11, PAGE_OFFSET@h cmplw 0, r10, r11 bge 2f @@ -487,7 +486,7 @@ interrupt_base: */ 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 */ + 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 @@ -584,8 +583,7 @@ interrupt_base: /* 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 + lis r11, PAGE_OFFSET@h cmplw 5, r10, r11 blt 5, 3f lis r11, swapper_pg_dir@h @@ -645,8 +643,7 @@ interrupt_base: /* 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 + lis r11, PAGE_OFFSET@h cmplw 5, r10, r11 blt 5, 3f lis r11, swapper_pg_dir@h @@ -694,7 +691,7 @@ interrupt_base: START_EXCEPTION(SPEUnavailable) NORMAL_EXCEPTION_PROLOG bne load_up_spe - addi r3,r1,STACK_FRAME_OVERHEAD + addi r3,r1,STACK_FRAME_OVERHEAD EXC_XFER_EE_LITE(0x2010, KernelSPE) #else EXCEPTION(0x2020, SPEUnavailable, unknown_exception, EXC_XFER_EE) @@ -741,10 +738,10 @@ data_access: * 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 + * r10 - EA of fault + * r11 - TLB (info from Linux PTE) + * r12, r13 - available to use + * CR5 - results of addr >= PAGE_OFFSET * 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. @@ -813,7 +810,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_BIG_PHYS) lwz r13, tlbcam_index@l(r13) rlwimi r12, r13, 0, 20, 31 7: - mtspr SPRN_MAS0,r12 + mtspr SPRN_MAS0,r12 #endif /* CONFIG_E200 */ tlbwe @@ -855,17 +852,17 @@ load_up_spe: 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 */ + 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 */ + 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 */ +#endif /* !CONFIG_SMP */ /* enable use of SPE after return */ oris r9,r9,MSR_SPE@h mfspr r5,SPRN_SPRG3 /* current task's THREAD (phys) */ @@ -878,7 +875,7 @@ load_up_spe: #ifndef CONFIG_SMP subi r4,r5,THREAD stw r4,last_task_used_spe@l(r3) -#endif /* CONFIG_SMP */ +#endif /* !CONFIG_SMP */ /* restore registers and return */ 2: REST_4GPRS(3, r11) lwz r10,_CCR(r11) @@ -963,10 +960,10 @@ _GLOBAL(giveup_spe) lwz r5,PT_REGS(r3) cmpi 0,r5,0 SAVE_32EVRS(0, r4, r3) - evxor evr6, evr6, evr6 /* clear out evr6 */ + 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 */ + evstddx evr6, r4, r3 /* save off accumulator */ mfspr r6,SPRN_SPEFSCR stw r6,THREAD_SPEFSCR(r3) /* save spefscr register value */ beq 1f @@ -979,7 +976,7 @@ _GLOBAL(giveup_spe) li r5,0 lis r4,last_task_used_spe@ha stw r5,last_task_used_spe@l(r4) -#endif /* CONFIG_SMP */ +#endif /* !CONFIG_SMP */ blr #endif /* CONFIG_SPE */ @@ -1000,15 +997,15 @@ _GLOBAL(giveup_fpu) */ _GLOBAL(abort) li r13,0 - mtspr SPRN_DBCR0,r13 /* disable all debug events */ + mtspr SPRN_DBCR0,r13 /* disable all debug events */ isync mfmsr r13 ori r13,r13,MSR_DE@l /* Enable Debug Events */ mtmsr r13 isync - mfspr r13,SPRN_DBCR0 - lis r13,(DBCR0_IDM|DBCR0_RST_CHIP)@h - mtspr SPRN_DBCR0,r13 + mfspr r13,SPRN_DBCR0 + lis r13,(DBCR0_IDM|DBCR0_RST_CHIP)@h + mtspr SPRN_DBCR0,r13 isync _GLOBAL(set_context) @@ -1043,21 +1040,13 @@ swapper_pg_dir: /* Reserved 4k for the critical exception stack & 4k for the machine * check stack per CPU for kernel mode exceptions */ .section .bss - .align 12 + .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. */ diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c index d6a38cd..53bf646 100644 --- a/arch/powerpc/kernel/ibmebus.c +++ b/arch/powerpc/kernel/ibmebus.c @@ -371,7 +371,8 @@ static int ibmebus_match_path(struct device *dev, void *data) static char *ibmebus_chomp(const char *in, size_t count) { - char *out = (char*)kmalloc(count + 1, GFP_KERNEL); + char *out = kmalloc(count + 1, GFP_KERNEL); + if (!out) return NULL; @@ -396,10 +397,10 @@ static ssize_t ibmebus_store_probe(struct bus_type *bus, return -ENOMEM; if (bus_find_device(&ibmebus_bus_type, NULL, path, - ibmebus_match_path)) { + ibmebus_match_path)) { printk(KERN_WARNING "%s: %s has already been probed\n", __FUNCTION__, path); - rc = -EINVAL; + rc = -EEXIST; goto out; } diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index a9e9cbd..abd2957 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -24,6 +24,7 @@ #include <linux/smp.h> #include <linux/cpu.h> #include <linux/sysctl.h> +#include <linux/tick.h> #include <asm/system.h> #include <asm/processor.h> @@ -59,6 +60,7 @@ void cpu_idle(void) set_thread_flag(TIF_POLLING_NRFLAG); while (1) { + tick_nohz_stop_sched_tick(); while (!need_resched() && !cpu_should_die()) { ppc64_runlatch_off(); @@ -90,6 +92,7 @@ void cpu_idle(void) HMT_medium(); ppc64_runlatch_on(); + tick_nohz_restart_sched_tick(); if (cpu_should_die()) cpu_die(); preempt_enable_no_resched(); diff --git a/arch/powerpc/kernel/iomap.c b/arch/powerpc/kernel/iomap.c index 2a5cf86..1577434 100644 --- a/arch/powerpc/kernel/iomap.c +++ b/arch/powerpc/kernel/iomap.c @@ -119,8 +119,8 @@ EXPORT_SYMBOL(ioport_unmap); void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max) { - unsigned long start = pci_resource_start(dev, bar); - unsigned long len = pci_resource_len(dev, bar); + resource_size_t start = pci_resource_start(dev, bar); + resource_size_t len = pci_resource_len(dev, bar); unsigned long flags = pci_resource_flags(dev, bar); if (!len) diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index c08ceca..e4ec6ee 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -30,7 +30,6 @@ #include <linux/spinlock.h> #include <linux/string.h> #include <linux/dma-mapping.h> -#include <linux/init.h> #include <linux/bitops.h> #include <asm/io.h> #include <asm/prom.h> diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 9bf63d5..2250f9e 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -52,6 +52,7 @@ #include <linux/mutex.h> #include <linux/bootmem.h> #include <linux/pci.h> +#include <linux/debugfs.h> #include <asm/uaccess.h> #include <asm/system.h> @@ -272,7 +273,7 @@ void do_IRQ(struct pt_regs *regs) struct thread_info *curtp, *irqtp; #endif - irq_enter(); + irq_enter(); #ifdef CONFIG_DEBUG_STACKOVERFLOW /* Debugging check for stack overflow: is there less than 2KB free? */ @@ -321,7 +322,7 @@ void do_IRQ(struct pt_regs *regs) /* That's not SMP safe ... but who cares ? */ ppc_spurious_interrupts++; - irq_exit(); + irq_exit(); set_irq_regs(old_regs); #ifdef CONFIG_PPC_ISERIES @@ -417,10 +418,16 @@ irq_hw_number_t virq_to_hw(unsigned int virq) } EXPORT_SYMBOL_GPL(virq_to_hw); -__init_refok struct irq_host *irq_alloc_host(unsigned int revmap_type, - unsigned int revmap_arg, - struct irq_host_ops *ops, - irq_hw_number_t inval_irq) +static int default_irq_host_match(struct irq_host *h, struct device_node *np) +{ + return h->of_node != NULL && h->of_node == np; +} + +struct irq_host *irq_alloc_host(struct device_node *of_node, + unsigned int revmap_type, + unsigned int revmap_arg, + struct irq_host_ops *ops, + irq_hw_number_t inval_irq) { struct irq_host *host; unsigned int size = sizeof(struct irq_host); @@ -431,13 +438,7 @@ __init_refok struct irq_host *irq_alloc_host(unsigned int revmap_type, /* Allocate structure and revmap table if using linear mapping */ if (revmap_type == IRQ_HOST_MAP_LINEAR) size += revmap_arg * sizeof(unsigned int); - if (mem_init_done) - host = kzalloc(size, GFP_KERNEL); - else { - host = alloc_bootmem(size); - if (host) - memset(host, 0, size); - } + host = zalloc_maybe_bootmem(size, GFP_KERNEL); if (host == NULL) return NULL; @@ -445,6 +446,10 @@ __init_refok struct irq_host *irq_alloc_host(unsigned int revmap_type, host->revmap_type = revmap_type; host->inval_irq = inval_irq; host->ops = ops; + host->of_node = of_node; + + if (host->ops->match == NULL) + host->ops->match = default_irq_host_match; spin_lock_irqsave(&irq_big_lock, flags); @@ -476,7 +481,7 @@ __init_refok struct irq_host *irq_alloc_host(unsigned int revmap_type, host->inval_irq = 0; /* setup us as the host for all legacy interrupts */ for (i = 1; i < NUM_ISA_INTERRUPTS; i++) { - irq_map[i].hwirq = 0; + irq_map[i].hwirq = i; smp_wmb(); irq_map[i].host = host; smp_wmb(); @@ -520,7 +525,7 @@ struct irq_host *irq_find_host(struct device_node *node) */ spin_lock_irqsave(&irq_big_lock, flags); list_for_each_entry(h, &irq_hosts, link) - if (h->ops->match == NULL || h->ops->match(h, node)) { + if (h->ops->match(h, node)) { found = h; break; } @@ -995,6 +1000,68 @@ static int irq_late_init(void) } arch_initcall(irq_late_init); +#ifdef CONFIG_VIRQ_DEBUG +static int virq_debug_show(struct seq_file *m, void *private) +{ + unsigned long flags; + irq_desc_t *desc; + const char *p; + char none[] = "none"; + int i; + + seq_printf(m, "%-5s %-7s %-15s %s\n", "virq", "hwirq", + "chip name", "host name"); + + for (i = 1; i < NR_IRQS; i++) { + desc = get_irq_desc(i); + spin_lock_irqsave(&desc->lock, flags); + + if (desc->action && desc->action->handler) { + seq_printf(m, "%5d ", i); + seq_printf(m, "0x%05lx ", virq_to_hw(i)); + + if (desc->chip && desc->chip->typename) + p = desc->chip->typename; + else + p = none; + seq_printf(m, "%-15s ", p); + + if (irq_map[i].host && irq_map[i].host->of_node) + p = irq_map[i].host->of_node->full_name; + else + p = none; + seq_printf(m, "%s\n", p); + } + + spin_unlock_irqrestore(&desc->lock, flags); + } + + return 0; +} + +static int virq_debug_open(struct inode *inode, struct file *file) +{ + return single_open(file, virq_debug_show, inode->i_private); +} + +static const struct file_operations virq_debug_fops = { + .open = virq_debug_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init irq_debugfs_init(void) +{ + if (debugfs_create_file("virq_mapping", S_IRUGO, powerpc_debugfs_root, + NULL, &virq_debug_fops)) + return -ENOMEM; + + return 0; +} +__initcall(irq_debugfs_init); +#endif /* CONFIG_VIRQ_DEBUG */ + #endif /* CONFIG_PPC_MERGE */ #ifdef CONFIG_PPC64 diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index 90fa11c..4ed5887 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -340,9 +340,10 @@ void __init find_legacy_serial_ports(void) } /* First fill our array with opb bus ports */ - for (np = NULL; (np = of_find_compatible_node(np, "serial", "ns16750")) != NULL;) { + for (np = NULL; (np = of_find_compatible_node(np, "serial", "ns16550")) != NULL;) { struct device_node *opb = of_get_parent(np); - if (opb && !strcmp(opb->type, "opb")) { + if (opb && (!strcmp(opb->type, "opb") || + of_device_is_compatible(opb, "ibm,opb"))) { index = add_legacy_soc_port(np, np); if (index >= 0 && np == stdout) legacy_serial_console = index; diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c index 6444eaa..ff781b2 100644 --- a/arch/powerpc/kernel/lparcfg.c +++ b/arch/powerpc/kernel/lparcfg.c @@ -77,7 +77,7 @@ static int iseries_lparcfg_data(struct seq_file *m, void *v) int processors, max_processors; unsigned long purr = get_purr(); - shared = (int)(get_lppaca()->shared_proc); + shared = (int)(local_paca->lppaca_ptr->shared_proc); seq_printf(m, "system_active_processors=%d\n", (int)HvLpConfig_getSystemPhysicalProcessors()); diff --git a/arch/powerpc/kernel/lparmap.c b/arch/powerpc/kernel/lparmap.c deleted file mode 100644 index af11285..0000000 --- a/arch/powerpc/kernel/lparmap.c +++ /dev/null @@ -1,32 +0,0 @@ -/* - * 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/pgtable.h> -#include <asm/iseries/lpar_map.h> - -/* The # is to stop gcc trying to make .text nonexecutable */ -const struct LparMap __attribute__((__section__(".text #"))) xLparMap = { - .xNumberEsids = HvEsidsToMap, - .xNumberRanges = HvRangesToMap, - .xSegmentTableOffs = STAB0_PAGE, - - .xEsids = { - { .xKernelEsid = GET_ESID(PAGE_OFFSET), - .xKernelVsid = KERNEL_VSID(PAGE_OFFSET), }, - { .xKernelEsid = GET_ESID(VMALLOC_START), - .xKernelVsid = KERNEL_VSID(VMALLOC_START), }, - }, - - .xRanges = { - { .xPages = HvPagesToMap, - .xOffset = 0, - .xVPN = KERNEL_VSID(PAGE_OFFSET) << (SID_SHIFT - HW_PAGE_SHIFT), - }, - }, -}; diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index f9676f5..0ed31f2 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -34,21 +34,10 @@ #undef DEBUG_NVRAM -static int nvram_scan_partitions(void); -static int nvram_setup_partition(void); -static int nvram_create_os_partition(void); -static int nvram_remove_os_partition(void); - static struct nvram_partition * nvram_part; static long nvram_error_log_index = -1; static long nvram_error_log_size = 0; -int no_logging = 1; /* Until we initialize everything, - * make sure we don't try logging - * anything */ - -extern volatile int error_log_cnt; - struct err_log_info { int error_type; unsigned int seq_num; @@ -636,16 +625,13 @@ void __exit nvram_cleanup(void) * sequence #: The unique sequence # for each event. (until it wraps) * error log: The error log from event_scan */ -int nvram_write_error_log(char * buff, int length, unsigned int err_type) +int nvram_write_error_log(char * buff, int length, + unsigned int err_type, unsigned int error_log_cnt) { int rc; loff_t tmp_index; struct err_log_info info; - if (no_logging) { - return -EPERM; - } - if (nvram_error_log_index == -1) { return -ESPIPE; } @@ -678,7 +664,8 @@ int nvram_write_error_log(char * buff, int length, unsigned int err_type) * * Reads nvram for error log for at most 'length' */ -int nvram_read_error_log(char * buff, int length, unsigned int * err_type) +int nvram_read_error_log(char * buff, int length, + unsigned int * err_type, unsigned int * error_log_cnt) { int rc; loff_t tmp_index; @@ -704,7 +691,7 @@ int nvram_read_error_log(char * buff, int length, unsigned int * err_type) return rc; } - error_log_cnt = info.seq_num; + *error_log_cnt = info.seq_num; *err_type = info.error_type; return 0; diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c index f70e787..eca8ccc 100644 --- a/arch/powerpc/kernel/of_platform.c +++ b/arch/powerpc/kernel/of_platform.c @@ -19,11 +19,11 @@ #include <linux/mod_devicetable.h> #include <linux/slab.h> #include <linux/pci.h> +#include <linux/of_device.h> +#include <linux/of_platform.h> #include <asm/errno.h> #include <asm/dcr.h> -#include <asm/of_device.h> -#include <asm/of_platform.h> #include <asm/topology.h> #include <asm/pci-bridge.h> #include <asm/ppc-pci.h> @@ -70,7 +70,10 @@ postcore_initcall(of_bus_driver_init); int of_register_platform_driver(struct of_platform_driver *drv) { /* initialize common driver fields */ - drv->driver.name = drv->name; + if (!drv->driver.name) + drv->driver.name = drv->name; + if (!drv->driver.owner) + drv->driver.owner = drv->owner; drv->driver.bus = &of_platform_bus_type; /* register with core */ @@ -385,9 +388,11 @@ static struct of_device_id of_pci_phb_ids[] = { }; static struct of_platform_driver of_pci_phb_driver = { - .name = "of-pci", - .match_table = of_pci_phb_ids, - .probe = of_pci_phb_probe, + .match_table = of_pci_phb_ids, + .probe = of_pci_phb_probe, + .driver = { + .name = "of-pci", + }, }; static __init int of_pci_phb_init(void) diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 083cfbd..2ae3b6f 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -65,14 +65,11 @@ static void __devinit pci_setup_pci_controller(struct pci_controller *hose) spin_unlock(&hose_spinlock); } -__init_refok struct pci_controller * pcibios_alloc_controller(struct device_node *dev) +struct pci_controller * pcibios_alloc_controller(struct device_node *dev) { struct pci_controller *phb; - if (mem_init_done) - phb = kmalloc(sizeof(struct pci_controller), GFP_KERNEL); - else - phb = alloc_bootmem(sizeof (struct pci_controller)); + phb = alloc_maybe_bootmem(sizeof(struct pci_controller), GFP_KERNEL); if (phb == NULL) return NULL; pci_setup_pci_controller(phb); diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index 04a3109..0e2bee4 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -1457,8 +1457,8 @@ null_write_config(struct pci_bus *bus, unsigned int devfn, int offset, static struct pci_ops null_pci_ops = { - null_read_config, - null_write_config + .read = null_read_config, + .write = null_write_config, }; /* diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 291ffbc..9f63bdc 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -588,7 +588,7 @@ int pci_proc_domain(struct pci_bus *bus) return 0; else { struct pci_controller *hose = pci_bus_to_host(bus); - return hose->buid; + return hose->buid != 0; } } diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c index d7d36df..b483903 100644 --- a/arch/powerpc/kernel/pci_dn.c +++ b/arch/powerpc/kernel/pci_dn.c @@ -23,8 +23,6 @@ #include <linux/pci.h> #include <linux/string.h> #include <linux/init.h> -#include <linux/slab.h> -#include <linux/bootmem.h> #include <asm/io.h> #include <asm/prom.h> @@ -45,10 +43,7 @@ static void * __devinit update_dn_pci_info(struct device_node *dn, void *data) const u32 *regs; struct pci_dn *pdn; - if (mem_init_done) - pdn = kmalloc(sizeof(*pdn), GFP_KERNEL); - else - pdn = alloc_bootmem(sizeof(*pdn)); + pdn = alloc_maybe_bootmem(sizeof(*pdn), GFP_KERNEL); if (pdn == NULL) return NULL; memset(pdn, 0, sizeof(*pdn)); diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index a20f195..c6b1aa3 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -12,12 +12,12 @@ #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/cacheflush.h> #include <asm/uaccess.h> #include <asm/io.h> #include <asm/atomic.h> @@ -95,10 +95,6 @@ EXPORT_SYMBOL(__strnlen_user); EXPORT_SYMBOL(copy_4K_page); #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); @@ -180,7 +176,7 @@ EXPORT_SYMBOL(cacheable_memcpy); EXPORT_SYMBOL(cpm_install_handler); EXPORT_SYMBOL(cpm_free_handler); #endif /* CONFIG_8xx */ -#if defined(CONFIG_8xx) || defined(CONFIG_40x) +#if defined(CONFIG_8xx) EXPORT_SYMBOL(__res); #endif diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 8a1b001..7949c203 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -354,6 +354,14 @@ static void show_instructions(struct pt_regs *regs) if (!(i % 8)) printk("\n"); +#if !defined(CONFIG_BOOKE) + /* If executing with the IMMU off, adjust pc rather + * than print XXXXXXXX. + */ + if (!(regs->msr & MSR_IR)) + pc = (unsigned long)phys_to_virt(pc); +#endif + /* We use __get_user here *only* to avoid an OOPS on a * bad address because the pc *should* only be a * kernel address. @@ -556,10 +564,15 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long usp, #ifdef CONFIG_PPC64 if (cpu_has_feature(CPU_FTR_SLB)) { - unsigned long sp_vsid = get_kernel_vsid(sp); + unsigned long sp_vsid; unsigned long llp = mmu_psize_defs[mmu_linear_psize].sllp; - sp_vsid <<= SLB_VSID_SHIFT; + if (cpu_has_feature(CPU_FTR_1T_SEGMENT)) + sp_vsid = get_kernel_vsid(sp, MMU_SEGSIZE_1T) + << SLB_VSID_SHIFT_1T; + else + sp_vsid = get_kernel_vsid(sp, MMU_SEGSIZE_256M) + << SLB_VSID_SHIFT; sp_vsid |= SLB_VSID_KERNEL | llp; p->thread.ksp_vsid = sp_vsid; } @@ -676,9 +689,13 @@ int set_fpexc_mode(struct task_struct *tsk, unsigned int val) * 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; + if (cpu_has_feature(CPU_FTR_SPE)) { + tsk->thread.fpexc_mode = val & + (PR_FP_EXC_SW_ENABLE | PR_FP_ALL_EXCEPT); + return 0; + } else { + return -EINVAL; + } #else return -EINVAL; #endif @@ -704,7 +721,10 @@ int get_fpexc_mode(struct task_struct *tsk, unsigned long adr) if (tsk->thread.fpexc_mode & PR_FP_EXC_SW_ENABLE) #ifdef CONFIG_SPE - val = tsk->thread.fpexc_mode; + if (cpu_has_feature(CPU_FTR_SPE)) + val = tsk->thread.fpexc_mode; + else + return -EINVAL; #else return -EINVAL; #endif diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index a38197b..9f329a8 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -52,7 +52,6 @@ #include <asm/pSeries_reconfig.h> #include <asm/pci-bridge.h> #include <asm/kexec.h> -#include <asm/system.h> #ifdef DEBUG #define DBG(fmt...) printk(KERN_ERR fmt) @@ -431,9 +430,11 @@ static int __init early_parse_mem(char *p) } early_param("mem", early_parse_mem); -/* - * The device tree may be allocated below our memory limit, or inside the - * crash kernel region for kdump. If so, move it out now. +/** + * move_device_tree - move tree to an unused area, if needed. + * + * The device tree may be allocated beyond our memory limit, or inside the + * crash kernel region for kdump. If so, move it out of the way. */ static void move_device_tree(void) { @@ -530,10 +531,7 @@ static struct ibm_pa_feature { {CPU_FTR_CTRL, 0, 0, 3, 0}, {CPU_FTR_NOEXECUTE, 0, 0, 6, 0}, {CPU_FTR_NODSISRALIGN, 0, 1, 1, 1}, -#if 0 - /* put this back once we know how to test if firmware does 64k IO */ {CPU_FTR_CI_LARGE_PAGE, 0, 1, 2, 0}, -#endif {CPU_FTR_REAL_LE, PPC_FEATURE_TRUE_LE, 5, 0, 0}, }; @@ -780,13 +778,13 @@ static int __init early_init_dt_scan_chosen(unsigned long node, #endif #ifdef CONFIG_KEXEC - lprop = (u64*)of_get_flat_dt_prop(node, "linux,crashkernel-base", NULL); - if (lprop) - crashk_res.start = *lprop; + lprop = (u64*)of_get_flat_dt_prop(node, "linux,crashkernel-base", NULL); + if (lprop) + crashk_res.start = *lprop; - lprop = (u64*)of_get_flat_dt_prop(node, "linux,crashkernel-size", NULL); - if (lprop) - crashk_res.end = crashk_res.start + *lprop - 1; + lprop = (u64*)of_get_flat_dt_prop(node, "linux,crashkernel-size", NULL); + if (lprop) + crashk_res.end = crashk_res.start + *lprop - 1; #endif early_init_dt_check_for_initrd(node); diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index a1d582e..1db10f7 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -1199,7 +1199,7 @@ static void __init prom_initialize_tce_table(void) if ((type[0] == 0) || (strstr(type, RELOC("pci")) == NULL)) continue; - /* Keep the old logic in tack to avoid regression. */ + /* Keep the old logic intact to avoid regression. */ if (compatible[0] != 0) { if ((strstr(compatible, RELOC("python")) == NULL) && (strstr(compatible, RELOC("Speedwagon")) == NULL) && @@ -2046,6 +2046,7 @@ static void __init fixup_device_tree_maple(void) /* * Pegasos and BriQ lacks the "ranges" property in the isa node * Pegasos needs decimal IRQ 14/15, not hexadecimal + * Pegasos has the IDE configured in legacy mode, but advertised as native */ static void __init fixup_device_tree_chrp(void) { @@ -2083,9 +2084,13 @@ static void __init fixup_device_tree_chrp(void) prom_printf("Fixing up IDE interrupt on Pegasos...\n"); prop[0] = 14; prop[1] = 0x0; - prop[2] = 15; - prop[3] = 0x0; - prom_setprop(ph, name, "interrupts", prop, 4*sizeof(u32)); + prom_setprop(ph, name, "interrupts", prop, 2*sizeof(u32)); + prom_printf("Fixing up IDE class-code on Pegasos...\n"); + rc = prom_getprop(ph, "class-code", prop, sizeof(u32)); + if (rc == sizeof(u32)) { + prop[0] &= ~0x5; + prom_setprop(ph, name, "class-code", prop, sizeof(u32)); + } } } #else @@ -2226,7 +2231,7 @@ static void __init fixup_device_tree(void) static void __init prom_find_boot_cpu(void) { - struct prom_t *_prom = &RELOC(prom); + struct prom_t *_prom = &RELOC(prom); u32 getprop_rval; ihandle prom_cpu; phandle cpu_pkg; @@ -2246,7 +2251,7 @@ static void __init prom_find_boot_cpu(void) static void __init prom_check_initrd(unsigned long r3, unsigned long r4) { #ifdef CONFIG_BLK_DEV_INITRD - struct prom_t *_prom = &RELOC(prom); + struct prom_t *_prom = &RELOC(prom); if (r3 && r4 && r4 != 0xdeadbeef) { unsigned long val; @@ -2279,7 +2284,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, unsigned long pp, unsigned long r6, unsigned long r7) { - struct prom_t *_prom; + struct prom_t *_prom; unsigned long hdr; unsigned long offset = reloc_offset(); @@ -2338,8 +2343,8 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, /* * Copy the CPU hold code */ - if (RELOC(of_platform) != PLATFORM_POWERMAC) - copy_and_flush(0, KERNELBASE + offset, 0x100, 0); + if (RELOC(of_platform) != PLATFORM_POWERMAC) + copy_and_flush(0, KERNELBASE + offset, 0x100, 0); /* * Do early parsing of command line diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 8a177bd..cf7732c 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -331,6 +331,7 @@ static long arch_ptrace_old(struct task_struct *child, long request, long addr, unsigned long *reg = &((unsigned long *)child->thread.regs)[0]; unsigned long __user *tmp = (unsigned long __user *)addr; + CHECK_FULL_REGS(child->thread.regs); for (i = 0; i < 32; i++) { ret = put_user(*reg, tmp); if (ret) @@ -346,6 +347,7 @@ static long arch_ptrace_old(struct task_struct *child, long request, long addr, unsigned long *reg = &((unsigned long *)child->thread.regs)[0]; unsigned long __user *tmp = (unsigned long __user *)addr; + CHECK_FULL_REGS(child->thread.regs); for (i = 0; i < 32; i++) { ret = get_user(*reg, tmp); if (ret) @@ -517,6 +519,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) ret = -EIO; break; } + CHECK_FULL_REGS(child->thread.regs); ret = 0; for (ui = 0; ui < PT_REGS_COUNT; ui ++) { ret |= __put_user(ptrace_get_reg(child, ui), @@ -537,6 +540,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) ret = -EIO; break; } + CHECK_FULL_REGS(child->thread.regs); ret = 0; for (ui = 0; ui < PT_REGS_COUNT; ui ++) { ret = __get_user(tmp, (unsigned long __user *) data); @@ -576,8 +580,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) #ifdef CONFIG_SPE case PTRACE_GETEVRREGS: /* Get the child spe register state. */ - if (child->thread.regs->msr & MSR_SPE) - giveup_spe(child); + flush_spe_to_thread(child); ret = get_evrregs((unsigned long __user *)data, child); break; @@ -585,8 +588,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) /* 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); + flush_spe_to_thread(child); ret = set_evrregs(child, (unsigned long __user *)data); break; #endif diff --git a/arch/powerpc/kernel/ptrace32.c b/arch/powerpc/kernel/ptrace32.c index 9e6baea..fea6206 100644 --- a/arch/powerpc/kernel/ptrace32.c +++ b/arch/powerpc/kernel/ptrace32.c @@ -53,6 +53,7 @@ static long compat_ptrace_old(struct task_struct *child, long request, unsigned long *reg = &((unsigned long *)child->thread.regs)[0]; unsigned int __user *tmp = (unsigned int __user *)addr; + CHECK_FULL_REGS(child->thread.regs); for (i = 0; i < 32; i++) { ret = put_user(*reg, tmp); if (ret) @@ -68,6 +69,7 @@ static long compat_ptrace_old(struct task_struct *child, long request, unsigned long *reg = &((unsigned long *)child->thread.regs)[0]; unsigned int __user *tmp = (unsigned int __user *)addr; + CHECK_FULL_REGS(child->thread.regs); for (i = 0; i < 32; i++) { ret = get_user(*reg, tmp); if (ret) @@ -164,6 +166,7 @@ long compat_sys_ptrace(int request, int pid, unsigned long addr, if ((addr & 3) || (index > PT_FPSCR32)) break; + CHECK_FULL_REGS(child->thread.regs); if (index < PT_FPR0) { tmp = ptrace_get_reg(child, index); } else { @@ -210,6 +213,7 @@ long compat_sys_ptrace(int request, int pid, unsigned long addr, if ((addr & 3) || numReg > PT_FPSCR) break; + CHECK_FULL_REGS(child->thread.regs); if (numReg >= PT_FPR0) { flush_fp_to_thread(child); tmp = ((unsigned long int *)child->thread.fpr)[numReg - PT_FPR0]; @@ -270,6 +274,7 @@ long compat_sys_ptrace(int request, int pid, unsigned long addr, if ((addr & 3) || (index > PT_FPSCR32)) break; + CHECK_FULL_REGS(child->thread.regs); if (index < PT_FPR0) { ret = ptrace_put_reg(child, index, data); } else { @@ -307,6 +312,7 @@ long compat_sys_ptrace(int request, int pid, unsigned long addr, */ if ((addr & 3) || (numReg > PT_FPSCR)) break; + CHECK_FULL_REGS(child->thread.regs); if (numReg < PT_FPR0) { unsigned long freg = ptrace_get_reg(child, numReg); if (index % 2) @@ -342,6 +348,7 @@ long compat_sys_ptrace(int request, int pid, unsigned long addr, ret = -EIO; break; } + CHECK_FULL_REGS(child->thread.regs); ret = 0; for (ui = 0; ui < PT_REGS_COUNT; ui ++) { ret |= __put_user(ptrace_get_reg(child, ui), @@ -359,6 +366,7 @@ long compat_sys_ptrace(int request, int pid, unsigned long addr, ret = -EIO; break; } + CHECK_FULL_REGS(child->thread.regs); ret = 0; for (ui = 0; ui < PT_REGS_COUNT; ui ++) { ret = __get_user(tmp, (unsigned int __user *) data); diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c index a5de621..21f14e5 100644 --- a/arch/powerpc/kernel/rtas_pci.c +++ b/arch/powerpc/kernel/rtas_pci.c @@ -171,8 +171,8 @@ static int rtas_pci_write_config(struct pci_bus *bus, } struct pci_ops rtas_pci_ops = { - rtas_pci_read_config, - rtas_pci_write_config + .read = rtas_pci_read_config, + .write = rtas_pci_write_config, }; int is_python(struct device_node *dev) diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 50ef38c..36c90ba 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -76,6 +76,8 @@ EXPORT_SYMBOL(machine_id); unsigned long klimit = (unsigned long) _end; +char cmd_line[COMMAND_LINE_SIZE]; + /* * This still seems to be needed... -- paulus */ diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 7ec6ba5..cd870a8 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -10,7 +10,9 @@ #include <linux/reboot.h> #include <linux/delay.h> #include <linux/initrd.h> +#if defined(CONFIG_IDE) || defined(CONFIG_IDE_MODULE) #include <linux/ide.h> +#endif #include <linux/tty.h> #include <linux/bootmem.h> #include <linux/seq_file.h> @@ -18,13 +20,11 @@ #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> @@ -51,7 +51,10 @@ extern void bootx_init(unsigned long r4, unsigned long phys); +#if defined(CONFIG_BLK_DEV_IDE) || defined(CONFIG_BLK_DEV_IDE_MODULE) struct ide_machdep_calls ppc_ide_md; +EXPORT_SYMBOL(ppc_ide_md); +#endif int boot_cpuid; EXPORT_SYMBOL_GPL(boot_cpuid); @@ -287,7 +290,8 @@ void __init setup_arch(char **cmdline_p) conswitchp = &dummy_con; #endif - ppc_md.setup_arch(); + if (ppc_md.setup_arch) + ppc_md.setup_arch(); if ( ppc_md.progress ) ppc_md.progress("arch: exit", 0x3eab); paging_init(); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 6018178..008ab68 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -181,9 +181,9 @@ void __init early_setup(unsigned long dt_ptr) DBG(" -> early_setup(), dt_ptr: 0x%lx\n", dt_ptr); /* - * Do early initializations using the flattened device - * tree, like retreiving the physical memory map or - * calculating/retreiving the hash table size + * Do early initialization using the flattened device + * tree, such as retrieving the physical memory map or + * calculating/retrieving the hash table size. */ early_init_devtree(__va(dt_ptr)); @@ -530,7 +530,8 @@ void __init setup_arch(char **cmdline_p) conswitchp = &dummy_con; #endif - ppc_md.setup_arch(); + if (ppc_md.setup_arch) + ppc_md.setup_arch(); paging_init(); ppc64_boot_msg(0x15, "Setup Done"); diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index c434d6c..a65a44f 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -16,6 +16,12 @@ #include "signal.h" +/* Log an error when sending an unhandled signal to a process. Controlled + * through debug.exception-trace sysctl. + */ + +int show_unhandled_signals = 0; + /* * Allocate space for the signal frame */ diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 590057e..6126bca 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -705,11 +705,13 @@ int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka, { struct rt_sigframe __user *rt_sf; struct mcontext __user *frame; + void __user *addr; unsigned long newsp = 0; /* Set up Signal Frame */ /* Put a Real Time Context onto stack */ rt_sf = get_sigframe(ka, regs, sizeof(*rt_sf)); + addr = rt_sf; if (unlikely(rt_sf == NULL)) goto badframe; @@ -728,6 +730,7 @@ int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka, /* Save user registers on the stack */ frame = &rt_sf->uc.uc_mcontext; + addr = frame; if (vdso32_rt_sigtramp && current->mm->context.vdso_base) { if (save_user_regs(regs, frame, 0)) goto badframe; @@ -742,6 +745,7 @@ int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka, /* create a stack frame for the caller of the handler */ newsp = ((unsigned long)rt_sf) - (__SIGNAL_FRAMESIZE + 16); + addr = (void __user *)regs->gpr[1]; if (put_user(regs->gpr[1], (u32 __user *)newsp)) goto badframe; @@ -762,6 +766,12 @@ badframe: printk("badframe in handle_rt_signal, regs=%p frame=%p newsp=%lx\n", regs, frame, newsp); #endif + if (show_unhandled_signals && printk_ratelimit()) + printk(KERN_INFO "%s[%d]: bad frame in handle_rt_signal32: " + "%p nip %08lx lr %08lx\n", + current->comm, current->pid, + addr, regs->nip, regs->link); + force_sigsegv(sig, current); return 0; } @@ -886,6 +896,12 @@ long sys_rt_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, return 0; bad: + if (show_unhandled_signals && printk_ratelimit()) + printk(KERN_INFO "%s[%d]: bad frame in sys_rt_sigreturn: " + "%p nip %08lx lr %08lx\n", + current->comm, current->pid, + rt_sf, regs->nip, regs->link); + force_sig(SIGSEGV, current); return 0; } @@ -967,6 +983,13 @@ int sys_debug_setcontext(struct ucontext __user *ctx, * We kill the task with a SIGSEGV in this situation. */ if (do_setcontext(ctx, regs, 1)) { + if (show_unhandled_signals && printk_ratelimit()) + printk(KERN_INFO "%s[%d]: bad frame in " + "sys_debug_setcontext: %p nip %08lx " + "lr %08lx\n", + current->comm, current->pid, + ctx, regs->nip, regs->link); + force_sig(SIGSEGV, current); goto out; } @@ -1048,6 +1071,12 @@ badframe: printk("badframe in handle_signal, regs=%p frame=%p newsp=%lx\n", regs, frame, newsp); #endif + if (show_unhandled_signals && printk_ratelimit()) + printk(KERN_INFO "%s[%d]: bad frame in handle_signal32: " + "%p nip %08lx lr %08lx\n", + current->comm, current->pid, + frame, regs->nip, regs->link); + force_sigsegv(sig, current); return 0; } @@ -1061,12 +1090,14 @@ long sys_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, struct sigcontext __user *sc; struct sigcontext sigctx; struct mcontext __user *sr; + void __user *addr; 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); + addr = sc; if (copy_from_user(&sigctx, sc, sizeof(sigctx))) goto badframe; @@ -1083,6 +1114,7 @@ long sys_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, restore_sigmask(&set); sr = (struct mcontext __user *)from_user_ptr(sigctx.regs); + addr = sr; if (!access_ok(VERIFY_READ, sr, sizeof(*sr)) || restore_user_regs(regs, sr, 1)) goto badframe; @@ -1091,6 +1123,12 @@ long sys_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, return 0; badframe: + if (show_unhandled_signals && printk_ratelimit()) + printk(KERN_INFO "%s[%d]: bad frame in sys_sigreturn: " + "%p nip %08lx lr %08lx\n", + current->comm, current->pid, + addr, regs->nip, regs->link); + force_sig(SIGSEGV, current); return 0; } diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index de895e6..faeb8f2 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -64,6 +64,11 @@ struct rt_sigframe { char abigap[288]; } __attribute__ ((aligned (16))); +static const char fmt32[] = KERN_INFO \ + "%s[%d]: bad frame in %s: %08lx nip %08lx lr %08lx\n"; +static const char fmt64[] = KERN_INFO \ + "%s[%d]: bad frame in %s: %016lx nip %016lx lr %016lx\n"; + /* * Set up the sigcontext for the signal frame. */ @@ -315,6 +320,11 @@ badframe: printk("badframe in sys_rt_sigreturn, regs=%p uc=%p &uc->uc_mcontext=%p\n", regs, uc, &uc->uc_mcontext); #endif + if (show_unhandled_signals && printk_ratelimit()) + printk(regs->msr & MSR_SF ? fmt64 : fmt32, + current->comm, current->pid, "rt_sigreturn", + (long)uc, regs->nip, regs->link); + force_sig(SIGSEGV, current); return 0; } @@ -398,6 +408,11 @@ badframe: printk("badframe in setup_rt_frame, regs=%p frame=%p newsp=%lx\n", regs, frame, newsp); #endif + if (show_unhandled_signals && printk_ratelimit()) + printk(regs->msr & MSR_SF ? fmt64 : fmt32, + current->comm, current->pid, "setup_rt_frame", + (long)frame, regs->nip, regs->link); + force_sigsegv(signr, current); return 0; } diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 1ea4316..d30f08f 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -152,11 +152,6 @@ static void stop_this_cpu(void *dummy) ; } -void smp_send_stop(void) -{ - smp_call_function(stop_this_cpu, NULL, 1, 0); -} - /* * Structure and data for smp_call_function(). This is designed to minimise * static memory requirements. It also looks cleaner. @@ -198,9 +193,6 @@ int smp_call_function_map(void (*func) (void *info), void *info, int nonatomic, int cpu; u64 timeout; - /* Can deadlock when called with interrupts disabled */ - WARN_ON(irqs_disabled()); - if (unlikely(smp_ops == NULL)) return ret; @@ -270,10 +262,19 @@ int smp_call_function_map(void (*func) (void *info), void *info, int nonatomic, return ret; } +static int __smp_call_function(void (*func)(void *info), void *info, + int nonatomic, int wait) +{ + return smp_call_function_map(func,info,nonatomic,wait,cpu_online_map); +} + int smp_call_function(void (*func) (void *info), void *info, int nonatomic, int wait) { - return smp_call_function_map(func,info,nonatomic,wait,cpu_online_map); + /* Can deadlock when called with interrupts disabled */ + WARN_ON(irqs_disabled()); + + return __smp_call_function(func, info, nonatomic, wait); } EXPORT_SYMBOL(smp_call_function); @@ -283,6 +284,9 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info, int cpumask_t map = CPU_MASK_NONE; int ret = 0; + /* Can deadlock when called with interrupts disabled */ + WARN_ON(irqs_disabled()); + if (!cpu_online(cpu)) return -EINVAL; @@ -299,6 +303,11 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info, int } EXPORT_SYMBOL(smp_call_function_single); +void smp_send_stop(void) +{ + __smp_call_function(stop_this_cpu, NULL, 1, 0); +} + void smp_call_function_interrupt(void) { void (*func) (void *info); @@ -560,6 +569,8 @@ int __devinit start_secondary(void *unused) if (system_state > SYSTEM_BOOTING) snapshot_timebase(); + secondary_cpu_time_init(); + spin_lock(&call_lock); cpu_set(cpu, cpu_online_map); spin_unlock(&call_lock); diff --git a/arch/powerpc/kernel/softemu8xx.c b/arch/powerpc/kernel/softemu8xx.c new file mode 100644 index 0000000..67d6f68 --- /dev/null +++ b/arch/powerpc/kernel/softemu8xx.c @@ -0,0 +1,202 @@ +/* + * Software emulation of some PPC instructions for the 8xx core. + * + * Copyright (C) 1998 Dan Malek (dmalek@jlc.net) + * + * Software floating emuation for the MPC8xx processor. I did this mostly + * because it was easier than trying to get the libraries compiled for + * software floating point. The goal is still to get the libraries done, + * but I lost patience and needed some hacks to at least get init and + * shells running. The first problem is the setjmp/longjmp that save + * and restore the floating point registers. + * + * For this emulation, our working registers are found on the register + * save area. + */ + +#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 <asm/pgtable.h> +#include <asm/uaccess.h> +#include <asm/system.h> +#include <asm/io.h> + +/* Eventually we may need a look-up table, but this works for now. +*/ +#define LFS 48 +#define LFD 50 +#define LFDU 51 +#define STFD 54 +#define STFDU 55 +#define FMR 63 + +void print_8xx_pte(struct mm_struct *mm, unsigned long addr) +{ + pgd_t *pgd; + pmd_t *pmd; + pte_t *pte; + + printk(" pte @ 0x%8lx: ", addr); + pgd = pgd_offset(mm, addr & PAGE_MASK); + if (pgd) { + pmd = pmd_offset(pud_offset(pgd, addr & PAGE_MASK), + addr & PAGE_MASK); + if (pmd && pmd_present(*pmd)) { + pte = pte_offset_kernel(pmd, addr & PAGE_MASK); + if (pte) { + printk(" (0x%08lx)->(0x%08lx)->0x%08lx\n", + (long)pgd, (long)pte, (long)pte_val(*pte)); +#define pp ((long)pte_val(*pte)) + printk(" RPN: %05lx PP: %lx SPS: %lx SH: %lx " + "CI: %lx v: %lx\n", + pp>>12, /* rpn */ + (pp>>10)&3, /* pp */ + (pp>>3)&1, /* small */ + (pp>>2)&1, /* shared */ + (pp>>1)&1, /* cache inhibit */ + pp&1 /* valid */ + ); +#undef pp + } + else { + printk("no pte\n"); + } + } + else { + printk("no pmd\n"); + } + } + else { + printk("no pgd\n"); + } +} + +int get_8xx_pte(struct mm_struct *mm, unsigned long addr) +{ + pgd_t *pgd; + pmd_t *pmd; + pte_t *pte; + int retval = 0; + + pgd = pgd_offset(mm, addr & PAGE_MASK); + if (pgd) { + pmd = pmd_offset(pud_offset(pgd, addr & PAGE_MASK), + addr & PAGE_MASK); + if (pmd && pmd_present(*pmd)) { + pte = pte_offset_kernel(pmd, addr & PAGE_MASK); + if (pte) { + retval = (int)pte_val(*pte); + } + } + } + return retval; +} + +/* + * We return 0 on success, 1 on unimplemented instruction, and EFAULT + * if a load/store faulted. + */ +int Soft_emulate_8xx(struct pt_regs *regs) +{ + u32 inst, instword; + u32 flreg, idxreg, disp; + int retval; + s16 sdisp; + u32 *ea, *ip; + + retval = 0; + + instword = *((u32 *)regs->nip); + inst = instword >> 26; + + flreg = (instword >> 21) & 0x1f; + idxreg = (instword >> 16) & 0x1f; + disp = instword & 0xffff; + + ea = (u32 *)(regs->gpr[idxreg] + disp); + ip = (u32 *)¤t->thread.fpr[flreg]; + + switch ( inst ) + { + case LFD: + /* this is a 16 bit quantity that is sign extended + * so use a signed short here -- Cort + */ + sdisp = (instword & 0xffff); + ea = (u32 *)(regs->gpr[idxreg] + sdisp); + if (copy_from_user(ip, ea, sizeof(double))) + retval = -EFAULT; + break; + + case LFDU: + if (copy_from_user(ip, ea, sizeof(double))) + retval = -EFAULT; + else + regs->gpr[idxreg] = (u32)ea; + break; + case LFS: + sdisp = (instword & 0xffff); + ea = (u32 *)(regs->gpr[idxreg] + sdisp); + if (copy_from_user(ip, ea, sizeof(float))) + retval = -EFAULT; + break; + case STFD: + /* this is a 16 bit quantity that is sign extended + * so use a signed short here -- Cort + */ + sdisp = (instword & 0xffff); + ea = (u32 *)(regs->gpr[idxreg] + sdisp); + if (copy_to_user(ea, ip, sizeof(double))) + retval = -EFAULT; + break; + + case STFDU: + if (copy_to_user(ea, ip, sizeof(double))) + retval = -EFAULT; + else + regs->gpr[idxreg] = (u32)ea; + break; + case FMR: + /* assume this is a fp move -- Cort */ + memcpy(ip, ¤t->thread.fpr[(instword>>11)&0x1f], + sizeof(double)); + break; + default: + retval = 1; + printk("Bad emulation %s/%d\n" + " NIP: %08lx instruction: %08x opcode: %x " + "A: %x B: %x C: %x code: %x rc: %x\n", + current->comm,current->pid, + regs->nip, + instword,inst, + (instword>>16)&0x1f, + (instword>>11)&0x1f, + (instword>>6)&0x1f, + (instword>>1)&0x3ff, + instword&1); + { + int pa; + print_8xx_pte(current->mm,regs->nip); + pa = get_8xx_pte(current->mm,regs->nip) & PAGE_MASK; + pa |= (regs->nip & ~PAGE_MASK); + pa = (unsigned long)__va(pa); + printk("Kernel VA for NIP %x ", pa); + print_8xx_pte(current->mm,pa); + } + } + + if (retval == 0) + regs->nip += 4; + + return retval; +} diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 55d29ed..25d9a96 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -197,6 +197,36 @@ SYSFS_PMCSETUP(pa6t_pmc3, SPRN_PA6T_PMC3); SYSFS_PMCSETUP(pa6t_pmc4, SPRN_PA6T_PMC4); SYSFS_PMCSETUP(pa6t_pmc5, SPRN_PA6T_PMC5); +#ifdef CONFIG_DEBUG_KERNEL +SYSFS_PMCSETUP(hid0, SPRN_HID0); +SYSFS_PMCSETUP(hid1, SPRN_HID1); +SYSFS_PMCSETUP(hid4, SPRN_HID4); +SYSFS_PMCSETUP(hid5, SPRN_HID5); +SYSFS_PMCSETUP(ima0, SPRN_PA6T_IMA0); +SYSFS_PMCSETUP(ima1, SPRN_PA6T_IMA1); +SYSFS_PMCSETUP(ima2, SPRN_PA6T_IMA2); +SYSFS_PMCSETUP(ima3, SPRN_PA6T_IMA3); +SYSFS_PMCSETUP(ima4, SPRN_PA6T_IMA4); +SYSFS_PMCSETUP(ima5, SPRN_PA6T_IMA5); +SYSFS_PMCSETUP(ima6, SPRN_PA6T_IMA6); +SYSFS_PMCSETUP(ima7, SPRN_PA6T_IMA7); +SYSFS_PMCSETUP(ima8, SPRN_PA6T_IMA8); +SYSFS_PMCSETUP(ima9, SPRN_PA6T_IMA9); +SYSFS_PMCSETUP(imaat, SPRN_PA6T_IMAAT); +SYSFS_PMCSETUP(btcr, SPRN_PA6T_BTCR); +SYSFS_PMCSETUP(pccr, SPRN_PA6T_PCCR); +SYSFS_PMCSETUP(rpccr, SPRN_PA6T_RPCCR); +SYSFS_PMCSETUP(der, SPRN_PA6T_DER); +SYSFS_PMCSETUP(mer, SPRN_PA6T_MER); +SYSFS_PMCSETUP(ber, SPRN_PA6T_BER); +SYSFS_PMCSETUP(ier, SPRN_PA6T_IER); +SYSFS_PMCSETUP(sier, SPRN_PA6T_SIER); +SYSFS_PMCSETUP(siar, SPRN_PA6T_SIAR); +SYSFS_PMCSETUP(tsr0, SPRN_PA6T_TSR0); +SYSFS_PMCSETUP(tsr1, SPRN_PA6T_TSR1); +SYSFS_PMCSETUP(tsr2, SPRN_PA6T_TSR2); +SYSFS_PMCSETUP(tsr3, SPRN_PA6T_TSR3); +#endif /* CONFIG_DEBUG_KERNEL */ static SYSDEV_ATTR(mmcra, 0600, show_mmcra, store_mmcra); static SYSDEV_ATTR(spurr, 0600, show_spurr, NULL); @@ -228,6 +258,36 @@ static struct sysdev_attribute pa6t_attrs[] = { _SYSDEV_ATTR(pmc3, 0600, show_pa6t_pmc3, store_pa6t_pmc3), _SYSDEV_ATTR(pmc4, 0600, show_pa6t_pmc4, store_pa6t_pmc4), _SYSDEV_ATTR(pmc5, 0600, show_pa6t_pmc5, store_pa6t_pmc5), +#ifdef CONFIG_DEBUG_KERNEL + _SYSDEV_ATTR(hid0, 0600, show_hid0, store_hid0), + _SYSDEV_ATTR(hid1, 0600, show_hid1, store_hid1), + _SYSDEV_ATTR(hid4, 0600, show_hid4, store_hid4), + _SYSDEV_ATTR(hid5, 0600, show_hid5, store_hid5), + _SYSDEV_ATTR(ima0, 0600, show_ima0, store_ima0), + _SYSDEV_ATTR(ima1, 0600, show_ima1, store_ima1), + _SYSDEV_ATTR(ima2, 0600, show_ima2, store_ima2), + _SYSDEV_ATTR(ima3, 0600, show_ima3, store_ima3), + _SYSDEV_ATTR(ima4, 0600, show_ima4, store_ima4), + _SYSDEV_ATTR(ima5, 0600, show_ima5, store_ima5), + _SYSDEV_ATTR(ima6, 0600, show_ima6, store_ima6), + _SYSDEV_ATTR(ima7, 0600, show_ima7, store_ima7), + _SYSDEV_ATTR(ima8, 0600, show_ima8, store_ima8), + _SYSDEV_ATTR(ima9, 0600, show_ima9, store_ima9), + _SYSDEV_ATTR(imaat, 0600, show_imaat, store_imaat), + _SYSDEV_ATTR(btcr, 0600, show_btcr, store_btcr), + _SYSDEV_ATTR(pccr, 0600, show_pccr, store_pccr), + _SYSDEV_ATTR(rpccr, 0600, show_rpccr, store_rpccr), + _SYSDEV_ATTR(der, 0600, show_der, store_der), + _SYSDEV_ATTR(mer, 0600, show_mer, store_mer), + _SYSDEV_ATTR(ber, 0600, show_ber, store_ber), + _SYSDEV_ATTR(ier, 0600, show_ier, store_ier), + _SYSDEV_ATTR(sier, 0600, show_sier, store_sier), + _SYSDEV_ATTR(siar, 0600, show_siar, store_siar), + _SYSDEV_ATTR(tsr0, 0600, show_tsr0, store_tsr0), + _SYSDEV_ATTR(tsr1, 0600, show_tsr1, store_tsr1), + _SYSDEV_ATTR(tsr2, 0600, show_tsr2, store_tsr2), + _SYSDEV_ATTR(tsr3, 0600, show_tsr3, store_tsr3), +#endif /* CONFIG_DEBUG_KERNEL */ }; @@ -380,12 +440,14 @@ int cpu_add_sysdev_attr_group(struct attribute_group *attrs) { int cpu; struct sys_device *sysdev; + int ret; mutex_lock(&cpu_mutex); for_each_possible_cpu(cpu) { sysdev = get_cpu_sysdev(cpu); - sysfs_create_group(&sysdev->kobj, attrs); + ret = sysfs_create_group(&sysdev->kobj, attrs); + WARN_ON(ret != 0); } mutex_unlock(&cpu_mutex); diff --git a/arch/powerpc/kernel/systbl.S b/arch/powerpc/kernel/systbl.S index 579de70..93219c3 100644 --- a/arch/powerpc/kernel/systbl.S +++ b/arch/powerpc/kernel/systbl.S @@ -39,6 +39,8 @@ #ifdef CONFIG_PPC64 #define sys_sigpending sys_ni_syscall #define sys_old_getrlimit sys_ni_syscall + + .p2align 3 #endif _GLOBAL(sys_call_table) diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index c627cf8..9368da3 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -65,24 +65,68 @@ #include <asm/div64.h> #include <asm/smp.h> #include <asm/vdso_datapage.h> -#ifdef CONFIG_PPC64 #include <asm/firmware.h> -#endif #ifdef CONFIG_PPC_ISERIES #include <asm/iseries/it_lp_queue.h> #include <asm/iseries/hv_call_xm.h> #endif -#include <asm/smp.h> -/* keep track of when we need to update the rtc */ -time_t last_rtc_update; +/* powerpc clocksource/clockevent code */ + +#include <linux/clockchips.h> +#include <linux/clocksource.h> + +static cycle_t rtc_read(void); +static struct clocksource clocksource_rtc = { + .name = "rtc", + .rating = 400, + .flags = CLOCK_SOURCE_IS_CONTINUOUS, + .mask = CLOCKSOURCE_MASK(64), + .shift = 22, + .mult = 0, /* To be filled in */ + .read = rtc_read, +}; + +static cycle_t timebase_read(void); +static struct clocksource clocksource_timebase = { + .name = "timebase", + .rating = 400, + .flags = CLOCK_SOURCE_IS_CONTINUOUS, + .mask = CLOCKSOURCE_MASK(64), + .shift = 22, + .mult = 0, /* To be filled in */ + .read = timebase_read, +}; + +#define DECREMENTER_MAX 0x7fffffff + +static int decrementer_set_next_event(unsigned long evt, + struct clock_event_device *dev); +static void decrementer_set_mode(enum clock_event_mode mode, + struct clock_event_device *dev); + +static struct clock_event_device decrementer_clockevent = { + .name = "decrementer", + .rating = 200, + .shift = 16, + .mult = 0, /* To be filled in */ + .irq = 0, + .set_next_event = decrementer_set_next_event, + .set_mode = decrementer_set_mode, + .features = CLOCK_EVT_FEAT_ONESHOT, +}; + +static DEFINE_PER_CPU(struct clock_event_device, decrementers); +void init_decrementer_clockevent(void); +static DEFINE_PER_CPU(u64, decrementer_next_tb); + #ifdef CONFIG_PPC_ISERIES static unsigned long __initdata iSeries_recal_titan; static signed long __initdata iSeries_recal_tb; -#endif -/* The decrementer counts down by 128 every 128ns on a 601. */ -#define DECREMENTER_COUNT_601 (1000000000 / HZ) +/* Forward declaration is only needed for iSereis compiles */ +void __init clocksource_init(void); +#endif #define XSEC_PER_SEC (1024*1024) @@ -349,98 +393,6 @@ void udelay(unsigned long usecs) } EXPORT_SYMBOL(udelay); -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) { - 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) -{ - 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; - - /* Sampling the time base must be done after loading - * do_gtod.varp in order to avoid racing with update_gtod. - */ - data_barrier(temp_varp); - tb_ticks = get_tb() - 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; - - do { - seq = read_seqbegin_irqsave(&xtime_lock, flags); - sec = xtime.tv_sec; - nsec = xtime.tv_nsec + tb_ticks_since(tb_last_jiffy); - } while (read_seqretry_irqrestore(&xtime_lock, seq, flags)); - usec = nsec / 1000; - while (usec >= 1000000) { - usec -= 1000000; - ++sec; - } - tv->tv_sec = sec; - tv->tv_usec = usec; - return; - } - __do_gettimeofday(tv); -} - -EXPORT_SYMBOL(do_gettimeofday); /* * There are two copies of tb_to_xs and stamp_xsec so that no @@ -486,56 +438,6 @@ static inline void update_gtod(u64 new_tb_stamp, u64 new_stamp_xsec, ++(vdso_data->tb_update_count); } -/* - * 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; - u64 tlen, t2x; - u64 tb, xsec_old, xsec_new; - struct gettimeofday_vars *varp; - - if (__USE_RTC()) - return; - tlen = current_tick_length(); - offset = cur_tb - do_gtod.varp->tb_orig_stamp; - if (tlen == last_tick_len && offset < 0x80000000u) - return; - if (tlen != last_tick_len) { - t2x = mulhdu(tlen << TICKLEN_SHIFT, ticklen_to_xs); - last_tick_len = tlen; - } else - t2x = do_gtod.varp->tb_to_xs; - new_stamp_xsec = (u64) xtime.tv_nsec * XSEC_PER_SEC; - do_div(new_stamp_xsec, 1000000000); - new_stamp_xsec += (u64) xtime.tv_sec * XSEC_PER_SEC; - - ++vdso_data->tb_update_count; - smp_mb(); - - /* - * Make sure time doesn't go backwards for userspace gettimeofday. - */ - tb = get_tb(); - varp = do_gtod.varp; - xsec_old = mulhdu(tb - varp->tb_orig_stamp, varp->tb_to_xs) - + varp->stamp_xsec; - xsec_new = mulhdu(tb - cur_tb, t2x) + new_stamp_xsec; - if (xsec_new < xsec_old) - new_stamp_xsec += xsec_old - xsec_new; - - update_gtod(cur_tb, new_stamp_xsec, t2x); -} - #ifdef CONFIG_SMP unsigned long profile_pc(struct pt_regs *regs) { @@ -607,6 +509,8 @@ static int __init iSeries_tb_recal(void) iSeries_recal_titan = titan; iSeries_recal_tb = tb; + /* Called here as now we know accurate values for the timebase */ + clocksource_init(); return 0; } late_initcall(iSeries_tb_recal); @@ -636,20 +540,30 @@ void __init iSeries_time_init_early(void) void timer_interrupt(struct pt_regs * regs) { struct pt_regs *old_regs; - int next_dec; int cpu = smp_processor_id(); - unsigned long ticks; - u64 tb_next_jiffy; + struct clock_event_device *evt = &per_cpu(decrementers, cpu); + u64 now; + + /* Ensure a positive value is written to the decrementer, or else + * some CPUs will continuue to take decrementer exceptions */ + set_dec(DECREMENTER_MAX); #ifdef CONFIG_PPC32 if (atomic_read(&ppc_n_lost_interrupts) != 0) do_IRQ(regs); #endif + now = get_tb_or_rtc(); + if (now < per_cpu(decrementer_next_tb, cpu)) { + /* not time for this event yet */ + now = per_cpu(decrementer_next_tb, cpu) - now; + if (now <= DECREMENTER_MAX) + set_dec((unsigned int)now - 1); + return; + } old_regs = set_irq_regs(regs); irq_enter(); - profile_tick(CPU_PROFILING); calculate_steal_time(); #ifdef CONFIG_PPC_ISERIES @@ -657,46 +571,20 @@ void timer_interrupt(struct pt_regs * regs) get_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)) - account_process_time(regs); - - /* - * No need to check whether cpu is offline here; boot_cpuid - * should have been fixed up by now. - */ - if (cpu != boot_cpuid) - continue; + /* + * 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)) + account_process_time(regs); - write_seqlock(&xtime_lock); - tb_next_jiffy = tb_last_jiffy + tb_ticks_per_jiffy; - if (__USE_RTC() && tb_next_jiffy >= 1000000000) - tb_next_jiffy -= 1000000000; - if (per_cpu(last_jiffy, cpu) >= tb_next_jiffy) { - tb_last_jiffy = tb_next_jiffy; - do_timer(1); - timer_recalc_offset(tb_last_jiffy); - timer_check_rtc(); - } - write_sequnlock(&xtime_lock); - } - - next_dec = tb_ticks_per_jiffy - ticks; - set_dec(next_dec); + if (evt->event_handler) + evt->event_handler(evt); + else + evt->set_next_event(DECREMENTER_MAX, evt); #ifdef CONFIG_PPC_ISERIES if (firmware_has_feature(FW_FEATURE_ISERIES) && hvlpevent_is_pending()) @@ -762,71 +650,6 @@ unsigned long long sched_clock(void) return mulhdu(get_tb() - boot_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; - u64 new_xsec; - unsigned long tb_delta; - - 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. - */ - - /* Make userspace gettimeofday spin until we're done. */ - ++vdso_data->tb_update_count; - smp_mb(); - - /* - * Subtract off the number of nanoseconds since the - * beginning of the last tick. - */ - tb_delta = tb_ticks_since(tb_last_jiffy); - tb_delta = mulhdu(tb_delta, do_gtod.varp->tb_to_xs); /* in xsec */ - new_nsec -= SCALE_XSEC(tb_delta, 1000000000); - - 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 = xtime.tv_nsec; - if (new_xsec != 0) { - new_xsec *= XSEC_PER_SEC; - do_div(new_xsec, NSEC_PER_SEC); - } - new_xsec += (u64)xtime.tv_sec * XSEC_PER_SEC; - update_gtod(tb_last_jiffy, new_xsec, do_gtod.varp->tb_to_xs); - - vdso_data->tz_minuteswest = sys_tz.tz_minuteswest; - vdso_data->tz_dsttime = sys_tz.tz_dsttime; - - write_sequnlock_irqrestore(&xtime_lock, flags); - clock_was_set(); - return 0; -} - -EXPORT_SYMBOL(do_settimeofday); - static int __init get_freq(char *name, int cells, unsigned long *val) { struct device_node *cpu; @@ -869,7 +692,7 @@ void __init generic_calibrate_decr(void) "(not found)\n"); } -#ifdef CONFIG_BOOKE +#if defined(CONFIG_BOOKE) || defined(CONFIG_40x) /* Set the time base to zero */ mtspr(SPRN_TBWL, 0); mtspr(SPRN_TBWU, 0); @@ -882,12 +705,35 @@ void __init generic_calibrate_decr(void) #endif } -unsigned long get_boot_time(void) +int update_persistent_clock(struct timespec now) { struct rtc_time tm; - if (ppc_md.get_boot_time) - return ppc_md.get_boot_time(); + if (!ppc_md.set_rtc_time) + return 0; + + to_tm(now.tv_sec + 1 + timezone_offset, &tm); + tm.tm_year -= 1900; + tm.tm_mon -= 1; + + return ppc_md.set_rtc_time(&tm); +} + +unsigned long read_persistent_clock(void) +{ + struct rtc_time tm; + static int first = 1; + + /* XXX this is a litle fragile but will work okay in the short term */ + if (first) { + first = 0; + if (ppc_md.time_init) + timezone_offset = ppc_md.time_init(); + + /* get_boot_time() isn't guaranteed to be safe to call late */ + if (ppc_md.get_boot_time) + return ppc_md.get_boot_time() -timezone_offset; + } if (!ppc_md.get_rtc_time) return 0; ppc_md.get_rtc_time(&tm); @@ -895,18 +741,128 @@ unsigned long get_boot_time(void) tm.tm_hour, tm.tm_min, tm.tm_sec); } +/* clocksource code */ +static cycle_t rtc_read(void) +{ + return (cycle_t)get_rtc(); +} + +static cycle_t timebase_read(void) +{ + return (cycle_t)get_tb(); +} + +void update_vsyscall(struct timespec *wall_time, struct clocksource *clock) +{ + u64 t2x, stamp_xsec; + + if (clock != &clocksource_timebase) + return; + + /* Make userspace gettimeofday spin until we're done. */ + ++vdso_data->tb_update_count; + smp_mb(); + + /* XXX this assumes clock->shift == 22 */ + /* 4611686018 ~= 2^(20+64-22) / 1e9 */ + t2x = (u64) clock->mult * 4611686018ULL; + stamp_xsec = (u64) xtime.tv_nsec * XSEC_PER_SEC; + do_div(stamp_xsec, 1000000000); + stamp_xsec += (u64) xtime.tv_sec * XSEC_PER_SEC; + update_gtod(clock->cycle_last, stamp_xsec, t2x); +} + +void update_vsyscall_tz(void) +{ + /* Make userspace gettimeofday spin until we're done. */ + ++vdso_data->tb_update_count; + smp_mb(); + vdso_data->tz_minuteswest = sys_tz.tz_minuteswest; + vdso_data->tz_dsttime = sys_tz.tz_dsttime; + smp_mb(); + ++vdso_data->tb_update_count; +} + +void __init clocksource_init(void) +{ + struct clocksource *clock; + + if (__USE_RTC()) + clock = &clocksource_rtc; + else + clock = &clocksource_timebase; + + clock->mult = clocksource_hz2mult(tb_ticks_per_sec, clock->shift); + + if (clocksource_register(clock)) { + printk(KERN_ERR "clocksource: %s is already registered\n", + clock->name); + return; + } + + printk(KERN_INFO "clocksource: %s mult[%x] shift[%d] registered\n", + clock->name, clock->mult, clock->shift); +} + +static int decrementer_set_next_event(unsigned long evt, + struct clock_event_device *dev) +{ + __get_cpu_var(decrementer_next_tb) = get_tb_or_rtc() + evt; + /* The decrementer interrupts on the 0 -> -1 transition */ + if (evt) + --evt; + set_dec(evt); + return 0; +} + +static void decrementer_set_mode(enum clock_event_mode mode, + struct clock_event_device *dev) +{ + if (mode != CLOCK_EVT_MODE_ONESHOT) + decrementer_set_next_event(DECREMENTER_MAX, dev); +} + +static void register_decrementer_clockevent(int cpu) +{ + struct clock_event_device *dec = &per_cpu(decrementers, cpu); + + *dec = decrementer_clockevent; + dec->cpumask = cpumask_of_cpu(cpu); + + printk(KERN_ERR "clockevent: %s mult[%lx] shift[%d] cpu[%d]\n", + dec->name, dec->mult, dec->shift, cpu); + + clockevents_register_device(dec); +} + +void init_decrementer_clockevent(void) +{ + int cpu = smp_processor_id(); + + decrementer_clockevent.mult = div_sc(ppc_tb_freq, NSEC_PER_SEC, + decrementer_clockevent.shift); + decrementer_clockevent.max_delta_ns = + clockevent_delta2ns(DECREMENTER_MAX, &decrementer_clockevent); + decrementer_clockevent.min_delta_ns = 1000; + + register_decrementer_clockevent(cpu); +} + +void secondary_cpu_time_init(void) +{ + /* FIME: Should make unrelatred change to move snapshot_timebase + * call here ! */ + register_decrementer_clockevent(smp_processor_id()); +} + /* 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, x; 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; @@ -981,19 +937,14 @@ void __init time_init(void) /* Save the current timebase to pretty up CONFIG_PRINTK_TIME */ boot_tb = get_tb_or_rtc(); - tm = get_boot_time(); - write_seqlock_irqsave(&xtime_lock, flags); /* 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; - tm -= timezone_offset; } - 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; @@ -1011,13 +962,13 @@ void __init time_init(void) time_freq = 0; - 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); + /* Register the clocksource, if we're not running on iSeries */ + if (!firmware_has_feature(FW_FEATURE_ISERIES)) + clocksource_init(); + + init_decrementer_clockevent(); } diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index d8502e3..bf9e39c 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -172,11 +172,21 @@ int die(const char *str, struct pt_regs *regs, long err) void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr) { siginfo_t info; + const char fmt32[] = KERN_INFO "%s[%d]: unhandled signal %d " \ + "at %08lx nip %08lx lr %08lx code %x\n"; + const char fmt64[] = KERN_INFO "%s[%d]: unhandled signal %d " \ + "at %016lx nip %016lx lr %016lx code %x\n"; if (!user_mode(regs)) { if (die("Exception in kernel mode", regs, signr)) return; - } + } else if (show_unhandled_signals && + unhandled_signal(current, signr) && + printk_ratelimit()) { + printk(regs->msr & MSR_SF ? fmt64 : fmt32, + current->comm, current->pid, signr, + addr, regs->nip, regs->link, code); + } memset(&info, 0, sizeof(info)); info.si_signo = signr; @@ -324,47 +334,10 @@ static inline int check_io_access(struct pt_regs *regs) #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) +static int generic_machine_check_exception(struct pt_regs *regs) { - int recover = 0; unsigned long reason = get_mc_reason(regs); - /* See if any machine dependent calls */ - if (ppc_md.machine_check_exception) - recover = ppc_md.machine_check_exception(regs); - - if (recover) - return; - - 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"); @@ -480,11 +453,41 @@ void machine_check_exception(struct pt_regs *regs) } #endif /* CONFIG_4xx */ - /* - * Optional platform-provided routine to print out - * additional info, e.g. bus error registers. - */ - platform_machine_check(regs); + return 0; +} + +void machine_check_exception(struct pt_regs *regs) +{ + int recover = 0; + + /* See if any machine dependent calls */ + if (ppc_md.machine_check_exception) + recover = ppc_md.machine_check_exception(regs); + else + recover = generic_machine_check_exception(regs); + + if (recover) + return; + + 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 (debugger_fault_handler(regs)) return; @@ -913,7 +916,9 @@ void SoftwareEmulation(struct pt_regs *regs) { extern int do_mathemu(struct pt_regs *); extern int Soft_emulate_8xx(struct pt_regs *); +#if defined(CONFIG_MATH_EMULATION) || defined(CONFIG_8XX_MINIMAL_FPEMU) int errcode; +#endif CHECK_FULL_REGS(regs); @@ -943,7 +948,7 @@ void SoftwareEmulation(struct pt_regs *regs) return; } -#else +#elif defined(CONFIG_8XX_MINIMAL_FPEMU) errcode = Soft_emulate_8xx(regs); switch (errcode) { case 0: @@ -956,6 +961,8 @@ void SoftwareEmulation(struct pt_regs *regs) _exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip); return; } +#else + _exception(SIGILL, regs, ILL_ILLOPC, regs->nip); #endif } #endif /* CONFIG_8xx */ diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c index 0f9b4ea..d723070 100644 --- a/arch/powerpc/kernel/udbg.c +++ b/arch/powerpc/kernel/udbg.c @@ -54,6 +54,8 @@ void __init udbg_early_init(void) #elif defined(CONFIG_PPC_EARLY_DEBUG_44x) /* PPC44x debug */ udbg_init_44x_as1(); +#elif defined(CONFIG_PPC_EARLY_DEBUG_CPM) + udbg_init_cpm(); #endif } diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c index 7afab5b..833a3d0 100644 --- a/arch/powerpc/kernel/udbg_16550.c +++ b/arch/powerpc/kernel/udbg_16550.c @@ -206,11 +206,22 @@ static void udbg_44x_as1_putc(char c) } } +static int udbg_44x_as1_getc(void) +{ + if (udbg_comport) { + while ((as1_readb(&udbg_comport->lsr) & LSR_DR) == 0) + ; /* wait for char */ + return as1_readb(&udbg_comport->rbr); + } + return -1; +} + void __init udbg_init_44x_as1(void) { udbg_comport = (volatile struct NS16550 __iomem *)PPC44x_EARLY_DEBUG_VIRTADDR; udbg_putc = udbg_44x_as1_putc; + udbg_getc = udbg_44x_as1_getc; } #endif /* CONFIG_PPC_EARLY_DEBUG_44x */ diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 213fa31..2322ba5 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -766,7 +766,9 @@ static int __init vdso_init(void) return 0; } +#ifdef CONFIG_PPC_MERGE arch_initcall(vdso_init); +#endif int in_gate_area_no_task(unsigned long addr) { diff --git a/arch/powerpc/kernel/vdso32/.gitignore b/arch/powerpc/kernel/vdso32/.gitignore index e45fba9..fea58098 100644 --- a/arch/powerpc/kernel/vdso32/.gitignore +++ b/arch/powerpc/kernel/vdso32/.gitignore @@ -1 +1,2 @@ vdso32.lds +vdso32.so.dbg diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile index 3726358..c3d57bd 100644 --- a/arch/powerpc/kernel/vdso32/Makefile +++ b/arch/powerpc/kernel/vdso32/Makefile @@ -9,11 +9,11 @@ ifeq ($(CONFIG_PPC32),y) CROSS32CC := $(CC) endif -targets := $(obj-vdso32) vdso32.so +targets := $(obj-vdso32) vdso32.so vdso32.so.dbg obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32)) -EXTRA_CFLAGS := -shared -s -fno-common -fno-builtin +EXTRA_CFLAGS := -shared -fno-common -fno-builtin EXTRA_CFLAGS += -nostdlib -Wl,-soname=linux-vdso32.so.1 \ $(call ld-option, -Wl$(comma)--hash-style=sysv) EXTRA_AFLAGS := -D__VDSO32__ -s @@ -26,9 +26,14 @@ CPPFLAGS_vdso32.lds += -P -C -Upowerpc $(obj)/vdso32_wrapper.o : $(obj)/vdso32.so # link rule for the .so file, .lds has to be first -$(obj)/vdso32.so: $(src)/vdso32.lds $(obj-vdso32) +$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) $(call if_changed,vdso32ld) +# strip rule for the .so file +$(obj)/%.so: OBJCOPYFLAGS := -S +$(obj)/%.so: $(obj)/%.so.dbg FORCE + $(call if_changed,objcopy) + # assembly rules for the .S files $(obj-vdso32): %.o: %.S $(call if_changed_dep,vdso32as) @@ -39,3 +44,12 @@ quiet_cmd_vdso32ld = VDSO32L $@ quiet_cmd_vdso32as = VDSO32A $@ cmd_vdso32as = $(CROSS32CC) $(a_flags) -c -o $@ $< +# install commands for the unstripped file +quiet_cmd_vdso_install = INSTALL $@ + cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@ + +vdso32.so: $(obj)/vdso32.so.dbg + @mkdir -p $(MODLIB)/vdso + $(call cmd,vdso_install) + +vdso_install: vdso32.so diff --git a/arch/powerpc/kernel/vdso64/.gitignore b/arch/powerpc/kernel/vdso64/.gitignore index 3fd18cf..77a0b42 100644 --- a/arch/powerpc/kernel/vdso64/.gitignore +++ b/arch/powerpc/kernel/vdso64/.gitignore @@ -1 +1,2 @@ vdso64.lds +vdso64.so.dbg diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile index 43af9b2..fa7f1b8 100644 --- a/arch/powerpc/kernel/vdso64/Makefile +++ b/arch/powerpc/kernel/vdso64/Makefile @@ -4,10 +4,10 @@ obj-vdso64 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o # Build rules -targets := $(obj-vdso64) vdso64.so +targets := $(obj-vdso64) vdso64.so vdso64.so.dbg obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64)) -EXTRA_CFLAGS := -shared -s -fno-common -fno-builtin +EXTRA_CFLAGS := -shared -fno-common -fno-builtin EXTRA_CFLAGS += -nostdlib -Wl,-soname=linux-vdso64.so.1 \ $(call ld-option, -Wl$(comma)--hash-style=sysv) EXTRA_AFLAGS := -D__VDSO64__ -s @@ -20,9 +20,14 @@ CPPFLAGS_vdso64.lds += -P -C -U$(ARCH) $(obj)/vdso64_wrapper.o : $(obj)/vdso64.so # link rule for the .so file, .lds has to be first -$(obj)/vdso64.so: $(src)/vdso64.lds $(obj-vdso64) +$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) $(call if_changed,vdso64ld) +# strip rule for the .so file +$(obj)/%.so: OBJCOPYFLAGS := -S +$(obj)/%.so: $(obj)/%.so.dbg FORCE + $(call if_changed,objcopy) + # assembly rules for the .S files $(obj-vdso64): %.o: %.S $(call if_changed_dep,vdso64as) @@ -33,4 +38,12 @@ quiet_cmd_vdso64ld = VDSO64L $@ quiet_cmd_vdso64as = VDSO64A $@ cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $< +# install commands for the unstripped file +quiet_cmd_vdso_install = INSTALL $@ + cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@ + +vdso64.so: $(obj)/vdso64.so.dbg + @mkdir -p $(MODLIB)/vdso + $(call cmd,vdso_install) +vdso_install: vdso64.so diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index 62c1bc1..cb22a35 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -39,6 +39,8 @@ extern struct kset devices_subsys; /* needed for vio_find_name() */ +static struct bus_type vio_bus_type; + static struct vio_dev vio_bus_device = { /* fake "parent" device */ .name = vio_bus_device.dev.bus_id, .type = "", @@ -46,60 +48,33 @@ static struct vio_dev vio_bus_device = { /* fake "parent" device */ .dev.bus = &vio_bus_type, }; -#ifdef CONFIG_PPC_ISERIES -struct device *iSeries_vio_dev = &vio_bus_device.dev; -EXPORT_SYMBOL(iSeries_vio_dev); +static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev) +{ + const unsigned char *dma_window; + struct iommu_table *tbl; + unsigned long offset, size; -static struct iommu_table veth_iommu_table; -static struct iommu_table vio_iommu_table; + if (firmware_has_feature(FW_FEATURE_ISERIES)) + return vio_build_iommu_table_iseries(dev); -static void __init iommu_vio_init(void) -{ - iommu_table_getparms_iSeries(255, 0, 0xff, &veth_iommu_table); - veth_iommu_table.it_size /= 2; - vio_iommu_table = veth_iommu_table; - vio_iommu_table.it_offset += veth_iommu_table.it_size; - - if (!iommu_init_table(&veth_iommu_table, -1)) - printk("Virtual Bus VETH TCE table failed.\n"); - if (!iommu_init_table(&vio_iommu_table, -1)) - printk("Virtual Bus VIO TCE table failed.\n"); -} -#endif + dma_window = of_get_property(dev->dev.archdata.of_node, + "ibm,my-dma-window", NULL); + if (!dma_window) + return NULL; -static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev) -{ -#ifdef CONFIG_PPC_ISERIES - if (firmware_has_feature(FW_FEATURE_ISERIES)) { - if (strcmp(dev->type, "network") == 0) - return &veth_iommu_table; - return &vio_iommu_table; - } else -#endif - { - const unsigned char *dma_window; - struct iommu_table *tbl; - unsigned long offset, size; - - dma_window = of_get_property(dev->dev.archdata.of_node, - "ibm,my-dma-window", NULL); - if (!dma_window) - return NULL; - - tbl = kmalloc(sizeof(*tbl), GFP_KERNEL); - - of_parse_dma_window(dev->dev.archdata.of_node, dma_window, - &tbl->it_index, &offset, &size); - - /* TCE table size - measured in tce entries */ - tbl->it_size = size >> IOMMU_PAGE_SHIFT; - /* offset for VIO should always be 0 */ - tbl->it_offset = offset >> IOMMU_PAGE_SHIFT; - tbl->it_busno = 0; - tbl->it_type = TCE_VB; - - return iommu_init_table(tbl, -1); - } + tbl = kmalloc(sizeof(*tbl), GFP_KERNEL); + + of_parse_dma_window(dev->dev.archdata.of_node, dma_window, + &tbl->it_index, &offset, &size); + + /* TCE table size - measured in tce entries */ + tbl->it_size = size >> IOMMU_PAGE_SHIFT; + /* offset for VIO should always be 0 */ + tbl->it_offset = offset >> IOMMU_PAGE_SHIFT; + tbl->it_busno = 0; + tbl->it_type = TCE_VB; + + return iommu_init_table(tbl, -1); } /** @@ -160,16 +135,6 @@ static int vio_bus_remove(struct device *dev) 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 (dev->driver && viodrv->shutdown) - viodrv->shutdown(viodev); -} - /** * vio_register_driver: - Register a new vio driver * @drv: The vio_driver structure to be registered. @@ -282,15 +247,6 @@ static int __init vio_bus_init(void) int err; struct device_node *node_vroot; -#ifdef CONFIG_PPC_ISERIES - if (firmware_has_feature(FW_FEATURE_ISERIES)) { - iommu_vio_init(); - vio_bus_device.dev.archdata.dma_ops = &dma_iommu_ops; - vio_bus_device.dev.archdata.dma_data = &vio_iommu_table; - iSeries_vio_dev = &vio_bus_device.dev; - } -#endif /* CONFIG_PPC_ISERIES */ - err = bus_register(&vio_bus_type); if (err) { printk(KERN_ERR "failed to register VIO bus\n"); @@ -317,11 +273,8 @@ static int __init vio_bus_init(void) * the device tree. Drivers will associate with them later. */ for (of_node = node_vroot->child; of_node != NULL; - of_node = of_node->sibling) { - printk(KERN_DEBUG "%s: processing %p\n", - __FUNCTION__, of_node); + of_node = of_node->sibling) vio_register_device_node(of_node); - } of_node_put(node_vroot); } @@ -391,14 +344,13 @@ static int vio_hotplug(struct device *dev, char **envp, int num_envp, return 0; } -struct bus_type vio_bus_type = { +static struct bus_type vio_bus_type = { .name = "vio", .dev_attrs = vio_dev_attrs, .uevent = vio_hotplug, .match = vio_bus_match, .probe = vio_bus_probe, .remove = vio_bus_remove, - .shutdown = vio_bus_shutdown, }; /** diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 0c45855..823a8cb 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -34,6 +34,8 @@ SECTIONS /* Text and gots */ .text : { + ALIGN_FUNCTION(); + *(.text.head) _text = .; TEXT_TEXT SCHED_TEXT |