diff options
Diffstat (limited to 'arch/ppc64/kernel/head.S')
-rw-r--r-- | arch/ppc64/kernel/head.S | 2139 |
1 files changed, 2139 insertions, 0 deletions
diff --git a/arch/ppc64/kernel/head.S b/arch/ppc64/kernel/head.S new file mode 100644 index 00000000000..fe05f3fbf9d --- /dev/null +++ b/arch/ppc64/kernel/head.S @@ -0,0 +1,2139 @@ +/* + * arch/ppc64/kernel/head.S + * + * PowerPC version + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) + * + * Rewritten by Cort Dougan (cort@cs.nmt.edu) for PReP + * Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu> + * Adapted for Power Macintosh by Paul Mackerras. + * Low-level exception handlers and MMU support + * rewritten by Paul Mackerras. + * Copyright (C) 1996 Paul Mackerras. + * + * Adapted for 64bit PowerPC by Dave Engebretsen, Peter Bergner, and + * Mike Corrigan {engebret|bergner|mikejc}@us.ibm.com + * + * This file contains the low-level support and setup for the + * PowerPC-64 platform, including trap and interrupt dispatch. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#define SECONDARY_PROCESSORS + +#include <linux/config.h> +#include <linux/threads.h> +#include <asm/processor.h> +#include <asm/page.h> +#include <asm/mmu.h> +#include <asm/naca.h> +#include <asm/systemcfg.h> +#include <asm/ppc_asm.h> +#include <asm/offsets.h> +#include <asm/bug.h> +#include <asm/cputable.h> +#include <asm/setup.h> +#include <asm/hvcall.h> + +#ifdef CONFIG_PPC_ISERIES +#define DO_SOFT_DISABLE +#endif + +/* + * hcall interface to pSeries LPAR + */ +#define H_SET_ASR 0x30 + +/* + * We layout physical memory as follows: + * 0x0000 - 0x00ff : Secondary processor spin code + * 0x0100 - 0x2fff : pSeries Interrupt prologs + * 0x3000 - 0x3fff : Interrupt support + * 0x4000 - 0x4fff : NACA + * 0x6000 : iSeries and common interrupt prologs + * 0x9000 - 0x9fff : Initial segment table + */ + +/* + * SPRG Usage + * + * Register Definition + * + * SPRG0 reserved for hypervisor + * SPRG1 temp - used to save gpr + * SPRG2 temp - used to save gpr + * SPRG3 virt addr of paca + */ + +/* + * Entering into this code we make the following assumptions: + * For pSeries: + * 1. The MMU is off & open firmware is running in real mode. + * 2. The kernel is entered at __start + * + * For iSeries: + * 1. The MMU is on (as it always is for iSeries) + * 2. The kernel is entered at system_reset_iSeries + */ + + .text + .globl _stext +_stext: +#ifdef CONFIG_PPC_MULTIPLATFORM +_GLOBAL(__start) + /* NOP this out unconditionally */ +BEGIN_FTR_SECTION + b .__start_initialization_multiplatform +END_FTR_SECTION(0, 1) +#endif /* CONFIG_PPC_MULTIPLATFORM */ + + /* Catch branch to 0 in real mode */ + trap +#ifdef CONFIG_PPC_ISERIES + /* + * At offset 0x20, there is a pointer to iSeries LPAR data. + * This is required by the hypervisor + */ + . = 0x20 + .llong hvReleaseData-KERNELBASE + + /* + * At offset 0x28 and 0x30 are offsets to the msChunks + * array (used by the iSeries LPAR debugger to do translation + * between physical addresses and absolute addresses) and + * to the pidhash table (also used by the debugger) + */ + .llong msChunks-KERNELBASE + .llong 0 /* pidhash-KERNELBASE SFRXXX */ + + /* Offset 0x38 - Pointer to start of embedded System.map */ + .globl embedded_sysmap_start +embedded_sysmap_start: + .llong 0 + /* Offset 0x40 - Pointer to end of embedded System.map */ + .globl embedded_sysmap_end +embedded_sysmap_end: + .llong 0 + +#else /* CONFIG_PPC_ISERIES */ + + /* Secondary processors spin on this value until it goes to 1. */ + .globl __secondary_hold_spinloop +__secondary_hold_spinloop: + .llong 0x0 + + /* Secondary processors write this value with their cpu # */ + /* after they enter the spin loop immediately below. */ + .globl __secondary_hold_acknowledge +__secondary_hold_acknowledge: + .llong 0x0 + + . = 0x60 +/* + * The following code is used on pSeries to hold secondary processors + * in a spin loop after they have been freed from OpenFirmware, but + * before the bulk of the kernel has been relocated. This code + * is relocated to physical address 0x60 before prom_init is run. + * All of it must fit below the first exception vector at 0x100. + */ +_GLOBAL(__secondary_hold) + mfmsr r24 + ori r24,r24,MSR_RI + mtmsrd r24 /* RI on */ + + /* Grab our linux cpu number */ + mr r24,r3 + + /* Tell the master cpu we're here */ + /* Relocation is off & we are located at an address less */ + /* than 0x100, so only need to grab low order offset. */ + std r24,__secondary_hold_acknowledge@l(0) + sync + + /* All secondary cpu's wait here until told to start. */ +100: ld r4,__secondary_hold_spinloop@l(0) + cmpdi 0,r4,1 + bne 100b + +#ifdef CONFIG_HMT + b .hmt_init +#else +#ifdef CONFIG_SMP + mr r3,r24 + b .pSeries_secondary_smp_init +#else + BUG_OPCODE +#endif +#endif +#endif + +/* This value is used to mark exception frames on the stack. */ + .section ".toc","aw" +exception_marker: + .tc ID_72656773_68657265[TC],0x7265677368657265 + .text + +/* + * The following macros define the code that appears as + * the prologue to each of the exception handlers. They + * are split into two parts to allow a single kernel binary + * to be used for pSeries and iSeries. + * LOL. One day... - paulus + */ + +/* + * We make as much of the exception code common between native + * exception handlers (including pSeries LPAR) and iSeries LPAR + * implementations as possible. + */ + +/* + * This is the start of the interrupt handlers for pSeries + * This code runs with relocation off. + */ +#define EX_R9 0 +#define EX_R10 8 +#define EX_R11 16 +#define EX_R12 24 +#define EX_R13 32 +#define EX_SRR0 40 +#define EX_R3 40 /* SLB miss saves R3, but not SRR0 */ +#define EX_DAR 48 +#define EX_LR 48 /* SLB miss saves LR, but not DAR */ +#define EX_DSISR 56 +#define EX_CCR 60 + +#define EXCEPTION_PROLOG_PSERIES(area, label) \ + mfspr r13,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,SPRG1; \ + std r9,area+EX_R13(r13); \ + mfcr r9; \ + clrrdi r12,r13,32; /* get high part of &label */ \ + mfmsr r10; \ + mfspr r11,SRR0; /* save SRR0 */ \ + ori r12,r12,(label)@l; /* virt addr of handler */ \ + ori r10,r10,MSR_IR|MSR_DR|MSR_RI; \ + mtspr SRR0,r12; \ + mfspr r12,SRR1; /* and SRR1 */ \ + mtspr 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,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,SPRG1; \ + std r9,area+EX_R13(r13); \ + mfcr r9 + +#define EXCEPTION_PROLOG_ISERIES_2 \ + mfmsr r10; \ + ld r11,PACALPPACA+LPPACASRR0(r13); \ + ld r12,PACALPPACA+LPPACASRR1(r13); \ + ori r10,r10,MSR_RI; \ + mtmsrd r10,1 + +/* + * The common exception prolog is used for all except a few exceptions + * such as a segment miss on a kernel address. We have to be prepared + * to take another exception from the point where we first touch the + * kernel stack onwards. + * + * On entry r13 points to the paca, r9-r13 are saved in the paca, + * r9 contains the saved CR, r11 and r12 contain the saved SRR0 and + * SRR1, and relocation is on. + */ +#define EXCEPTION_PROLOG_COMMON(n, area) \ + andi. r10,r12,MSR_PR; /* See if coming from user */ \ + mr r10,r1; /* Save r1 */ \ + subi r1,r1,INT_FRAME_SIZE; /* alloc frame on kernel stack */ \ + beq- 1f; \ + ld r1,PACAKSAVE(r13); /* kernel stack to use */ \ +1: cmpdi cr1,r1,0; /* check if r1 is in userspace */ \ + bge- cr1,bad_stack; /* abort if it is */ \ + std r9,_CCR(r1); /* save CR in stackframe */ \ + std r11,_NIP(r1); /* save SRR0 in stackframe */ \ + std r12,_MSR(r1); /* save SRR1 in stackframe */ \ + std r10,0(r1); /* make stack chain pointer */ \ + std r0,GPR0(r1); /* save r0 in stackframe */ \ + std r10,GPR1(r1); /* save r1 in stackframe */ \ + std r2,GPR2(r1); /* save r2 in stackframe */ \ + SAVE_4GPRS(3, r1); /* save r3 - r6 in stackframe */ \ + SAVE_2GPRS(7, r1); /* save r7, r8 in stackframe */ \ + ld r9,area+EX_R9(r13); /* move r9, r10 to stackframe */ \ + ld r10,area+EX_R10(r13); \ + std r9,GPR9(r1); \ + std r10,GPR10(r1); \ + ld r9,area+EX_R11(r13); /* move r11 - r13 to stackframe */ \ + ld r10,area+EX_R12(r13); \ + ld r11,area+EX_R13(r13); \ + std r9,GPR11(r1); \ + std r10,GPR12(r1); \ + std r11,GPR13(r1); \ + ld r2,PACATOC(r13); /* get kernel TOC into r2 */ \ + mflr r9; /* save LR in stackframe */ \ + std r9,_LINK(r1); \ + mfctr r10; /* save CTR in stackframe */ \ + std r10,_CTR(r1); \ + mfspr r11,XER; /* save XER in stackframe */ \ + std r11,_XER(r1); \ + li r9,(n)+1; \ + std r9,_TRAP(r1); /* set trap number */ \ + li r10,0; \ + ld r11,exception_marker@toc(r2); \ + std r10,RESULT(r1); /* clear regs->result */ \ + std r11,STACK_FRAME_OVERHEAD-16(r1); /* mark the frame */ + +/* + * Exception vectors. + */ +#define STD_EXCEPTION_PSERIES(n, label) \ + . = n; \ + .globl label##_pSeries; \ +label##_pSeries: \ + HMT_MEDIUM; \ + mtspr SPRG1,r13; /* save r13 */ \ + EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common) + +#define STD_EXCEPTION_ISERIES(n, label, area) \ + .globl label##_iSeries; \ +label##_iSeries: \ + HMT_MEDIUM; \ + mtspr 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 SPRG1,r13; /* save r13 */ \ + EXCEPTION_PROLOG_ISERIES_1(PACA_EXGEN); \ + lbz r10,PACAPROCENABLED(r13); \ + cmpwi 0,r10,0; \ + beq- label##_iSeries_masked; \ + EXCEPTION_PROLOG_ISERIES_2; \ + b label##_common; \ + +#ifdef DO_SOFT_DISABLE +#define DISABLE_INTS \ + lbz r10,PACAPROCENABLED(r13); \ + li r11,0; \ + std r10,SOFTE(r1); \ + mfmsr r10; \ + stb r11,PACAPROCENABLED(r13); \ + ori r10,r10,MSR_EE; \ + mtmsrd r10,1 + +#define ENABLE_INTS \ + lbz r10,PACAPROCENABLED(r13); \ + mfmsr r11; \ + std r10,SOFTE(r1); \ + ori r11,r11,MSR_EE; \ + mtmsrd r11,1 + +#else /* hard enable/disable interrupts */ +#define DISABLE_INTS + +#define ENABLE_INTS \ + ld r12,_MSR(r1); \ + mfmsr r11; \ + rlwimi r11,r12,0,MSR_EE; \ + mtmsrd r11,1 + +#endif + +#define STD_EXCEPTION_COMMON(trap, label, hdlr) \ + .align 7; \ + .globl label##_common; \ +label##_common: \ + EXCEPTION_PROLOG_COMMON(trap, PACA_EXGEN); \ + DISABLE_INTS; \ + bl .save_nvgprs; \ + addi r3,r1,STACK_FRAME_OVERHEAD; \ + bl hdlr; \ + b .ret_from_except + +#define STD_EXCEPTION_COMMON_LITE(trap, label, hdlr) \ + .align 7; \ + .globl label##_common; \ +label##_common: \ + EXCEPTION_PROLOG_COMMON(trap, PACA_EXGEN); \ + DISABLE_INTS; \ + addi r3,r1,STACK_FRAME_OVERHEAD; \ + bl hdlr; \ + b .ret_from_except_lite + +/* + * Start of pSeries system interrupt routines + */ + . = 0x100 + .globl __start_interrupts +__start_interrupts: + + STD_EXCEPTION_PSERIES(0x100, system_reset) + + . = 0x200 +_machine_check_pSeries: + HMT_MEDIUM + mtspr SPRG1,r13 /* save r13 */ + EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common) + + . = 0x300 + .globl data_access_pSeries +data_access_pSeries: + HMT_MEDIUM + mtspr SPRG1,r13 +BEGIN_FTR_SECTION + mtspr SPRG2,r12 + mfspr r13,DAR + mfspr r12,DSISR + srdi r13,r13,60 + rlwimi r13,r12,16,0x20 + mfcr r12 + cmpwi r13,0x2c + beq .do_stab_bolted_pSeries + mtcrf 0x80,r12 + mfspr r12,SPRG2 +END_FTR_SECTION_IFCLR(CPU_FTR_SLB) + EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common) + + . = 0x380 + .globl data_access_slb_pSeries +data_access_slb_pSeries: + HMT_MEDIUM + mtspr SPRG1,r13 + mfspr r13,SPRG3 /* get paca address into r13 */ + std r9,PACA_EXSLB+EX_R9(r13) /* save r9 - r12 */ + std r10,PACA_EXSLB+EX_R10(r13) + std r11,PACA_EXSLB+EX_R11(r13) + std r12,PACA_EXSLB+EX_R12(r13) + std r3,PACA_EXSLB+EX_R3(r13) + mfspr r9,SPRG1 + std r9,PACA_EXSLB+EX_R13(r13) + mfcr r9 + mfspr r12,SRR1 /* and SRR1 */ + mfspr r3,DAR + b .do_slb_miss /* Rel. branch works in real mode */ + + STD_EXCEPTION_PSERIES(0x400, instruction_access) + + . = 0x480 + .globl instruction_access_slb_pSeries +instruction_access_slb_pSeries: + HMT_MEDIUM + mtspr SPRG1,r13 + mfspr r13,SPRG3 /* get paca address into r13 */ + std r9,PACA_EXSLB+EX_R9(r13) /* save r9 - r12 */ + std r10,PACA_EXSLB+EX_R10(r13) + std r11,PACA_EXSLB+EX_R11(r13) + std r12,PACA_EXSLB+EX_R12(r13) + std r3,PACA_EXSLB+EX_R3(r13) + mfspr r9,SPRG1 + std r9,PACA_EXSLB+EX_R13(r13) + mfcr r9 + mfspr r12,SRR1 /* and SRR1 */ + mfspr r3,SRR0 /* SRR0 is faulting address */ + b .do_slb_miss /* Rel. branch works in real mode */ + + STD_EXCEPTION_PSERIES(0x500, hardware_interrupt) + STD_EXCEPTION_PSERIES(0x600, alignment) + STD_EXCEPTION_PSERIES(0x700, program_check) + STD_EXCEPTION_PSERIES(0x800, fp_unavailable) + STD_EXCEPTION_PSERIES(0x900, decrementer) + STD_EXCEPTION_PSERIES(0xa00, trap_0a) + STD_EXCEPTION_PSERIES(0xb00, trap_0b) + + . = 0xc00 + .globl system_call_pSeries +system_call_pSeries: + HMT_MEDIUM + mr r9,r13 + mfmsr r10 + mfspr r13,SPRG3 + mfspr r11,SRR0 + clrrdi r12,r13,32 + oris r12,r12,system_call_common@h + ori r12,r12,system_call_common@l + mtspr SRR0,r12 + ori r10,r10,MSR_IR|MSR_DR|MSR_RI + mfspr r12,SRR1 + mtspr SRR1,r10 + rfid + b . /* prevent speculative execution */ + + STD_EXCEPTION_PSERIES(0xd00, single_step) + STD_EXCEPTION_PSERIES(0xe00, trap_0e) + + /* We need to deal with the Altivec unavailable exception + * here which is at 0xf20, thus in the middle of the + * prolog code of the PerformanceMonitor one. A little + * trickery is thus necessary + */ + . = 0xf00 + b performance_monitor_pSeries + + STD_EXCEPTION_PSERIES(0xf20, altivec_unavailable) + + STD_EXCEPTION_PSERIES(0x1300, instruction_breakpoint) + STD_EXCEPTION_PSERIES(0x1700, altivec_assist) + + /* moved from 0xf00 */ + STD_EXCEPTION_PSERIES(0x3000, performance_monitor) + + . = 0x3100 +_GLOBAL(do_stab_bolted_pSeries) + mtcrf 0x80,r12 + mfspr r12,SPRG2 + EXCEPTION_PROLOG_PSERIES(PACA_EXSLB, .do_stab_bolted) + + + /* Space for the naca. Architected to be located at real address + * NACA_PHYS_ADDR. Various tools rely on this location being fixed. + * The first dword of the naca is required by iSeries LPAR to + * point to itVpdAreas. On pSeries native, this value is not used. + */ + . = NACA_PHYS_ADDR + .globl __end_interrupts +__end_interrupts: +#ifdef CONFIG_PPC_ISERIES + .globl naca +naca: + .llong itVpdAreas + + /* + * The iSeries LPAR map is at this fixed address + * so that the HvReleaseData structure can address + * it with a 32-bit offset. + * + * The VSID values below are dependent on the + * VSID generation algorithm. See include/asm/mmu_context.h. + */ + + . = 0x4800 + + .llong 2 /* # ESIDs to be mapped by hypervisor */ + .llong 1 /* # memory ranges to be mapped by hypervisor */ + .llong STAB0_PAGE /* Page # of segment table within load area */ + .llong 0 /* Reserved */ + .llong 0 /* Reserved */ + .llong 0 /* Reserved */ + .llong 0 /* Reserved */ + .llong 0 /* Reserved */ + .llong (KERNELBASE>>SID_SHIFT) + .llong 0x408f92c94 /* KERNELBASE VSID */ + /* We have to list the bolted VMALLOC segment here, too, so that it + * will be restored on shared processor switch */ + .llong (VMALLOCBASE>>SID_SHIFT) + .llong 0xf09b89af5 /* VMALLOCBASE VSID */ + .llong 8192 /* # pages to map (32 MB) */ + .llong 0 /* Offset from start of loadarea to start of map */ + .llong 0x408f92c940000 /* VPN of first page to map */ + + . = 0x6100 + +/*** ISeries-LPAR interrupt handlers ***/ + + STD_EXCEPTION_ISERIES(0x200, machine_check, PACA_EXMC) + + .globl data_access_iSeries +data_access_iSeries: + mtspr SPRG1,r13 +BEGIN_FTR_SECTION + mtspr SPRG2,r12 + mfspr r13,DAR + mfspr r12,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,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,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 SPRG1,r13 /* save r13 */ + EXCEPTION_PROLOG_ISERIES_1(PACA_EXSLB) + std r3,PACA_EXSLB+EX_R3(r13) + ld r12,PACALPPACA+LPPACASRR1(r13) + mfspr r3,DAR + b .do_slb_miss + + STD_EXCEPTION_ISERIES(0x400, instruction_access, PACA_EXGEN) + + .globl instruction_access_slb_iSeries +instruction_access_slb_iSeries: + mtspr SPRG1,r13 /* save r13 */ + EXCEPTION_PROLOG_ISERIES_1(PACA_EXSLB) + std r3,PACA_EXSLB+EX_R3(r13) + ld r12,PACALPPACA+LPPACASRR1(r13) + ld r3,PACALPPACA+LPPACASRR0(r13) + b .do_slb_miss + + MASKABLE_EXCEPTION_ISERIES(0x500, hardware_interrupt) + STD_EXCEPTION_ISERIES(0x600, alignment, PACA_EXGEN) + STD_EXCEPTION_ISERIES(0x700, program_check, PACA_EXGEN) + STD_EXCEPTION_ISERIES(0x800, fp_unavailable, PACA_EXGEN) + MASKABLE_EXCEPTION_ISERIES(0x900, decrementer) + STD_EXCEPTION_ISERIES(0xa00, trap_0a, PACA_EXGEN) + STD_EXCEPTION_ISERIES(0xb00, trap_0b, PACA_EXGEN) + + .globl system_call_iSeries +system_call_iSeries: + mr r9,r13 + mfspr r13,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,SPRG3 /* Get paca address */ + mfmsr r24 + ori r24,r24,MSR_RI + mtmsrd r24 /* RI on */ + lhz r24,PACAPACAINDEX(r13) /* Get processor # */ + cmpwi 0,r24,0 /* Are we processor 0? */ + beq .__start_initialization_iSeries /* Start up the first processor */ + mfspr r4,CTRLF + li r5,RUNLATCH /* Turn off the run light */ + andc r4,r4,r5 + mtspr CTRLT,r4 + +1: + HMT_LOW +#ifdef CONFIG_SMP + lbz r23,PACAPROCSTART(r13) /* Test if this processor + * should start */ + sync + LOADADDR(r3,current_set) + sldi r28,r24,3 /* get current_set[cpu#] */ + ldx r3,r3,r28 + addi r1,r3,THREAD_SIZE + subi r1,r1,STACK_FRAME_OVERHEAD + + cmpwi 0,r23,0 + beq iSeries_secondary_smp_loop /* Loop until told to go */ +#ifdef SECONDARY_PROCESSORS + bne .__secondary_start /* Loop until told to go */ +#endif +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,SPRG3 /* Put r13 back ???? */ + b 1b /* If SMP not configured, secondaries + * loop forever */ + + .globl decrementer_iSeries_masked +decrementer_iSeries_masked: + li r11,1 + stb r11,PACALPPACA+LPPACADECRINT(r13) + lwz r12,PACADEFAULTDECR(r13) + mtspr SPRN_DEC,r12 + /* fall through */ + + .globl hardware_interrupt_iSeries_masked +hardware_interrupt_iSeries_masked: + mtcrf 0x80,r9 /* Restore regs */ + ld r11,PACALPPACA+LPPACASRR0(r13) + ld r12,PACALPPACA+LPPACASRR1(r13) + mtspr SRR0,r11 + mtspr 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 + +/* + * Data area reserved for FWNMI option. + */ + .= 0x7000 + .globl fwnmi_data_area +fwnmi_data_area: + +/* + * Vectors for the FWNMI option. Share common code. + */ + . = 0x8000 + .globl system_reset_fwnmi +system_reset_fwnmi: + HMT_MEDIUM + mtspr SPRG1,r13 /* save r13 */ + EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common) + .globl machine_check_fwnmi +machine_check_fwnmi: + HMT_MEDIUM + mtspr SPRG1,r13 /* save r13 */ + EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common) + + /* + * Space for the initial segment table + * For LPAR, the hypervisor must fill in at least one entry + * before we get control (with relocate on) + */ + . = STAB0_PHYS_ADDR + .globl __start_stab +__start_stab: + + . = (STAB0_PHYS_ADDR + PAGE_SIZE) + .globl __end_stab +__end_stab: + + +/*** Common interrupt handlers ***/ + + STD_EXCEPTION_COMMON(0x100, system_reset, .system_reset_exception) + + /* + * Machine check is different because we use a different + * save area: PACA_EXMC instead of PACA_EXGEN. + */ + .align 7 + .globl machine_check_common +machine_check_common: + EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC) + DISABLE_INTS + bl .save_nvgprs + addi r3,r1,STACK_FRAME_OVERHEAD + bl .machine_check_exception + b .ret_from_except + + STD_EXCEPTION_COMMON_LITE(0x900, decrementer, .timer_interrupt) + STD_EXCEPTION_COMMON(0xa00, trap_0a, .unknown_exception) + STD_EXCEPTION_COMMON(0xb00, trap_0b, .unknown_exception) + STD_EXCEPTION_COMMON(0xd00, single_step, .single_step_exception) + STD_EXCEPTION_COMMON(0xe00, trap_0e, .unknown_exception) + STD_EXCEPTION_COMMON(0xf00, performance_monitor, .performance_monitor_exception) + STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, .instruction_breakpoint_exception) +#ifdef CONFIG_ALTIVEC + STD_EXCEPTION_COMMON(0x1700, altivec_assist, .altivec_assist_exception) +#else + STD_EXCEPTION_COMMON(0x1700, altivec_assist, .unknown_exception) +#endif + +/* + * Here we have detected that the kernel stack pointer is bad. + * R9 contains the saved CR, r13 points to the paca, + * r10 contains the (bad) kernel stack pointer, + * r11 and r12 contain the saved SRR0 and SRR1. + * We switch to using the paca guard page as an emergency stack, + * save the registers there, and call kernel_bad_stack(), which panics. + */ +bad_stack: + ld r1,PACAEMERGSP(r13) + subi r1,r1,64+INT_FRAME_SIZE + std r9,_CCR(r1) + std r10,GPR1(r1) + std r11,_NIP(r1) + std r12,_MSR(r1) + mfspr r11,DAR + mfspr r12,DSISR + std r11,_DAR(r1) + std r12,_DSISR(r1) + mflr r10 + mfctr r11 + mfxer r12 + std r10,_LINK(r1) + std r11,_CTR(r1) + std r12,_XER(r1) + SAVE_GPR(0,r1) + SAVE_GPR(2,r1) + SAVE_4GPRS(3,r1) + SAVE_2GPRS(7,r1) + SAVE_10GPRS(12,r1) + SAVE_10GPRS(22,r1) + addi r11,r1,INT_FRAME_SIZE + std r11,0(r1) + li r12,0 + std r12,0(r11) + ld r2,PACATOC(r13) +1: addi r3,r1,STACK_FRAME_OVERHEAD + bl .kernel_bad_stack + b 1b + +/* + * Return from an exception with minimal checks. + * The caller is assumed to have done EXCEPTION_PROLOG_COMMON. + * If interrupts have been enabled, or anything has been + * done that might have changed the scheduling status of + * any task or sent any task a signal, you should use + * ret_from_except or ret_from_except_lite instead of this. + */ +fast_exception_return: + ld r12,_MSR(r1) + ld r11,_NIP(r1) + andi. r3,r12,MSR_RI /* check if RI is set */ + beq- unrecov_fer + ld r3,_CCR(r1) + ld r4,_LINK(r1) + ld r5,_CTR(r1) + ld r6,_XER(r1) + mtcr r3 + mtlr r4 + mtctr r5 + mtxer r6 + REST_GPR(0, r1) + REST_8GPRS(2, r1) + + mfmsr r10 + clrrdi r10,r10,2 /* clear RI (LE is 0 already) */ + mtmsrd r10,1 + + mtspr SRR1,r12 + mtspr SRR0,r11 + REST_4GPRS(10, r1) + ld r1,GPR1(r1) + rfid + b . /* prevent speculative execution */ + +unrecov_fer: + bl .save_nvgprs +1: addi r3,r1,STACK_FRAME_OVERHEAD + bl .unrecoverable_exception + b 1b + +/* + * Here r13 points to the paca, r9 contains the saved CR, + * SRR0 and SRR1 are saved in r11 and r12, + * r9 - r13 are saved in paca->exgen. + */ + .align 7 + .globl data_access_common +data_access_common: + mfspr r10,DAR + std r10,PACA_EXGEN+EX_DAR(r13) + mfspr r10,DSISR + stw r10,PACA_EXGEN+EX_DSISR(r13) + EXCEPTION_PROLOG_COMMON(0x300, PACA_EXGEN) + ld r3,PACA_EXGEN+EX_DAR(r13) + lwz r4,PACA_EXGEN+EX_DSISR(r13) + li r5,0x300 + b .do_hash_page /* Try to handle as hpte fault */ + + .align 7 + .globl instruction_access_common +instruction_access_common: + EXCEPTION_PROLOG_COMMON(0x400, PACA_EXGEN) + ld r3,_NIP(r1) + andis. r4,r12,0x5820 + li r5,0x400 + b .do_hash_page /* Try to handle as hpte fault */ + + .align 7 + .globl hardware_interrupt_common + .globl hardware_interrupt_entry +hardware_interrupt_common: + EXCEPTION_PROLOG_COMMON(0x500, PACA_EXGEN) +hardware_interrupt_entry: + DISABLE_INTS + addi r3,r1,STACK_FRAME_OVERHEAD + bl .do_IRQ + b .ret_from_except_lite + + .align 7 + .globl alignment_common +alignment_common: + mfspr r10,DAR + std r10,PACA_EXGEN+EX_DAR(r13) + mfspr r10,DSISR + stw r10,PACA_EXGEN+EX_DSISR(r13) + EXCEPTION_PROLOG_COMMON(0x600, PACA_EXGEN) + ld r3,PACA_EXGEN+EX_DAR(r13) + lwz r4,PACA_EXGEN+EX_DSISR(r13) + std r3,_DAR(r1) + std r4,_DSISR(r1) + bl .save_nvgprs + addi r3,r1,STACK_FRAME_OVERHEAD + ENABLE_INTS + bl .alignment_exception + b .ret_from_except + + .align 7 + .globl program_check_common +program_check_common: + EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN) + bl .save_nvgprs + addi r3,r1,STACK_FRAME_OVERHEAD + ENABLE_INTS + bl .program_check_exception + b .ret_from_except + + .align 7 + .globl fp_unavailable_common +fp_unavailable_common: + EXCEPTION_PROLOG_COMMON(0x800, PACA_EXGEN) + bne .load_up_fpu /* if from user, just load it up */ + bl .save_nvgprs + addi r3,r1,STACK_FRAME_OVERHEAD + ENABLE_INTS + bl .kernel_fp_unavailable_exception + BUG_OPCODE + + .align 7 + .globl altivec_unavailable_common +altivec_unavailable_common: + EXCEPTION_PROLOG_COMMON(0xf20, PACA_EXGEN) +#ifdef CONFIG_ALTIVEC + bne .load_up_altivec /* if from user, just load it up */ +#endif + bl .save_nvgprs + addi r3,r1,STACK_FRAME_OVERHEAD + ENABLE_INTS + bl .altivec_unavailable_exception + b .ret_from_except + +/* + * Hash table stuff + */ + .align 7 +_GLOBAL(do_hash_page) + std r3,_DAR(r1) + std r4,_DSISR(r1) + + andis. r0,r4,0xa450 /* weird error? */ + bne- .handle_page_fault /* if not, try to insert a HPTE */ +BEGIN_FTR_SECTION + andis. r0,r4,0x0020 /* Is it a segment table fault? */ + bne- .do_ste_alloc /* If so handle it */ +END_FTR_SECTION_IFCLR(CPU_FTR_SLB) + + /* + * We need to set the _PAGE_USER bit if MSR_PR is set or if we are + * accessing a userspace segment (even from the kernel). We assume + * kernel addresses always have the high bit set. + */ + rlwinm r4,r4,32-25+9,31-9,31-9 /* DSISR_STORE -> _PAGE_RW */ + rotldi r0,r3,15 /* Move high bit into MSR_PR posn */ + orc r0,r12,r0 /* MSR_PR | ~high_bit */ + rlwimi r4,r0,32-13,30,30 /* becomes _PAGE_USER access bit */ + ori r4,r4,1 /* add _PAGE_PRESENT */ + rlwimi r4,r5,22+2,31-2,31-2 /* Set _PAGE_EXEC if trap is 0x400 */ + + /* + * On iSeries, we soft-disable interrupts here, then + * hard-enable interrupts so that the hash_page code can spin on + * the hash_table_lock without problems on a shared processor. + */ + DISABLE_INTS + + /* + * r3 contains the faulting address + * r4 contains the required access permissions + * r5 contains the trap number + * + * at return r3 = 0 for success + */ + bl .hash_page /* build HPTE if possible */ + cmpdi r3,0 /* see if hash_page succeeded */ + +#ifdef DO_SOFT_DISABLE + /* + * If we had interrupts soft-enabled at the point where the + * DSI/ISI occurred, and an interrupt came in during hash_page, + * handle it now. + * We jump to ret_from_except_lite rather than fast_exception_return + * because ret_from_except_lite will check for and handle pending + * interrupts if necessary. + */ + beq .ret_from_except_lite + /* For a hash failure, we don't bother re-enabling interrupts */ + ble- 12f + + /* + * hash_page couldn't handle it, set soft interrupt enable back + * to what it was before the trap. Note that .local_irq_restore + * handles any interrupts pending at this point. + */ + ld r3,SOFTE(r1) + bl .local_irq_restore + b 11f +#else + beq fast_exception_return /* Return from exception on success */ + ble- 12f /* Failure return from hash_page */ + + /* fall through */ +#endif + +/* Here we have a page fault that hash_page can't handle. */ +_GLOBAL(handle_page_fault) + ENABLE_INTS +11: ld r4,_DAR(r1) + ld r5,_DSISR(r1) + addi r3,r1,STACK_FRAME_OVERHEAD + bl .do_page_fault + cmpdi r3,0 + beq+ .ret_from_except_lite + bl .save_nvgprs + mr r5,r3 + addi r3,r1,STACK_FRAME_OVERHEAD + lwz r4,_DAR(r1) + bl .bad_page_fault + b .ret_from_except + +/* We have a page fault that hash_page could handle but HV refused + * the PTE insertion + */ +12: bl .save_nvgprs + addi r3,r1,STACK_FRAME_OVERHEAD + lwz r4,_DAR(r1) + bl .low_hash_fault + b .ret_from_except + + /* here we have a segment miss */ +_GLOBAL(do_ste_alloc) + bl .ste_allocate /* try to insert stab entry */ + cmpdi r3,0 + beq+ fast_exception_return + b .handle_page_fault + +/* + * r13 points to the PACA, r9 contains the saved CR, + * r11 and r12 contain the saved SRR0 and SRR1. + * r9 - r13 are saved in paca->exslb. + * We assume we aren't going to take any exceptions during this procedure. + * We assume (DAR >> 60) == 0xc. + */ + .align 7 +_GLOBAL(do_stab_bolted) + stw r9,PACA_EXSLB+EX_CCR(r13) /* save CR in exc. frame */ + std r11,PACA_EXSLB+EX_SRR0(r13) /* save SRR0 in exc. frame */ + + /* Hash to the primary group */ + ld r10,PACASTABVIRT(r13) + mfspr r11,DAR + srdi r11,r11,28 + rldimi r10,r11,7,52 /* r10 = first ste of the group */ + + /* Calculate VSID */ + /* This is a kernel address, so protovsid = ESID */ + ASM_VSID_SCRAMBLE(r11, r9) + rldic r9,r11,12,16 /* r9 = vsid << 12 */ + + /* Search the primary group for a free entry */ +1: ld r11,0(r10) /* Test valid bit of the current ste */ + andi. r11,r11,0x80 + beq 2f + addi r10,r10,16 + andi. r11,r10,0x70 + bne 1b + + /* Stick for only searching the primary group for now. */ + /* At least for now, we use a very simple random castout scheme */ + /* Use the TB as a random number ; OR in 1 to avoid entry 0 */ + mftb r11 + rldic r11,r11,4,57 /* r11 = (r11 << 4) & 0x70 */ + ori r11,r11,0x10 + + /* r10 currently points to an ste one past the group of interest */ + /* make it point to the randomly selected entry */ + subi r10,r10,128 + or r10,r10,r11 /* r10 is the entry to invalidate */ + + isync /* mark the entry invalid */ + ld r11,0(r10) + rldicl r11,r11,56,1 /* clear the valid bit */ + rotldi r11,r11,8 + std r11,0(r10) + sync + + clrrdi r11,r11,28 /* Get the esid part of the ste */ + slbie r11 + +2: std r9,8(r10) /* Store the vsid part of the ste */ + eieio + + mfspr r11,DAR /* Get the new esid */ + clrrdi r11,r11,28 /* Permits a full 32b of ESID */ + ori r11,r11,0x90 /* Turn on valid and kp */ + std r11,0(r10) /* Put new entry back into the stab */ + + sync + + /* All done -- return from exception. */ + lwz r9,PACA_EXSLB+EX_CCR(r13) /* get saved CR */ + ld r11,PACA_EXSLB+EX_SRR0(r13) /* get saved SRR0 */ + + andi. r10,r12,MSR_RI + beq- unrecov_slb + + mtcrf 0x80,r9 /* restore CR */ + + mfmsr r10 + clrrdi r10,r10,2 + mtmsrd r10,1 + + mtspr SRR0,r11 + mtspr SRR1,r12 + ld r9,PACA_EXSLB+EX_R9(r13) + ld r10,PACA_EXSLB+EX_R10(r13) + ld r11,PACA_EXSLB+EX_R11(r13) + ld r12,PACA_EXSLB+EX_R12(r13) + ld r13,PACA_EXSLB+EX_R13(r13) + rfid + b . /* prevent speculative execution */ + +/* + * r13 points to the PACA, r9 contains the saved CR, + * r11 and r12 contain the saved SRR0 and SRR1. + * r3 has the faulting address + * r9 - r13 are saved in paca->exslb. + * r3 is saved in paca->slb_r3 + * We assume we aren't going to take any exceptions during this procedure. + */ +_GLOBAL(do_slb_miss) + mflr r10 + + stw r9,PACA_EXSLB+EX_CCR(r13) /* save CR in exc. frame */ + std r10,PACA_EXSLB+EX_LR(r13) /* save LR */ + + bl .slb_allocate /* handle it */ + + /* All done -- return from exception. */ + + ld r10,PACA_EXSLB+EX_LR(r13) + ld r3,PACA_EXSLB+EX_R3(r13) + lwz r9,PACA_EXSLB+EX_CCR(r13) /* get saved CR */ +#ifdef CONFIG_PPC_ISERIES + ld r11,PACALPPACA+LPPACASRR0(r13) /* get SRR0 value */ +#endif /* CONFIG_PPC_ISERIES */ + + mtlr r10 + + andi. r10,r12,MSR_RI /* check for unrecoverable exception */ + beq- unrecov_slb + +.machine push +.machine "power4" + mtcrf 0x80,r9 + mtcrf 0x01,r9 /* slb_allocate uses cr0 and cr7 */ +.machine pop + +#ifdef CONFIG_PPC_ISERIES + mtspr SRR0,r11 + mtspr SRR1,r12 +#endif /* CONFIG_PPC_ISERIES */ + ld r9,PACA_EXSLB+EX_R9(r13) + ld r10,PACA_EXSLB+EX_R10(r13) + ld r11,PACA_EXSLB+EX_R11(r13) + ld r12,PACA_EXSLB+EX_R12(r13) + ld r13,PACA_EXSLB+EX_R13(r13) + rfid + b . /* prevent speculative execution */ + +unrecov_slb: + EXCEPTION_PROLOG_COMMON(0x4100, PACA_EXSLB) + DISABLE_INTS + bl .save_nvgprs +1: addi r3,r1,STACK_FRAME_OVERHEAD + bl .unrecoverable_exception + b 1b + + +/* + * On pSeries, secondary processors spin in the following code. + * At entry, r3 = this processor's number (physical cpu id) + */ +_GLOBAL(pSeries_secondary_smp_init) + mr r24,r3 + + /* turn on 64-bit mode */ + bl .enable_64b_mode + isync + + /* Copy some CPU settings from CPU 0 */ + bl .__restore_cpu_setup + + /* Set up a paca value for this processor. Since we have the + * physical cpu id in r3, we need to search the pacas to find + * which logical id maps to our physical one. + */ + LOADADDR(r13, paca) /* Get base vaddr of paca array */ + li r5,0 /* logical cpu id */ +1: lhz r6,PACAHWCPUID(r13) /* Load HW procid from paca */ + cmpw r6,r24 /* Compare to our id */ + beq 2f + addi r13,r13,PACA_SIZE /* Loop to next PACA on miss */ + addi r5,r5,1 + cmpwi r5,NR_CPUS + blt 1b + +99: HMT_LOW /* Couldn't find our CPU id */ + b 99b + +2: mtspr SPRG3,r13 /* Save vaddr of paca in SPRG3 */ + /* From now on, r24 is expected to be logica cpuid */ + mr r24,r5 +3: HMT_LOW + lbz r23,PACAPROCSTART(r13) /* Test if this processor should */ + /* start. */ + sync + + /* Create a temp kernel stack for use before relocation is on. */ + ld r1,PACAEMERGSP(r13) + subi r1,r1,STACK_FRAME_OVERHEAD + + cmpwi 0,r23,0 +#ifdef CONFIG_SMP +#ifdef SECONDARY_PROCESSORS + bne .__secondary_start +#endif +#endif + b 3b /* Loop until told to go */ + +#ifdef CONFIG_PPC_ISERIES +_STATIC(__start_initialization_iSeries) + /* Clear out the BSS */ + LOADADDR(r11,__bss_stop) + LOADADDR(r8,__bss_start) + sub r11,r11,r8 /* bss size */ + addi r11,r11,7 /* round up to an even double word */ + rldicl. r11,r11,61,3 /* shift right by 3 */ + beq 4f + addi r8,r8,-8 + li r0,0 + mtctr r11 /* zero this many doublewords */ +3: stdu r0,8(r8) + bdnz 3b +4: + LOADADDR(r1,init_thread_union) + addi r1,r1,THREAD_SIZE + li r0,0 + stdu r0,-STACK_FRAME_OVERHEAD(r1) + + LOADADDR(r3,cpu_specs) + LOADADDR(r4,cur_cpu_spec) + li r5,0 + bl .identify_cpu + + LOADADDR(r2,__toc_start) + addi r2,r2,0x4000 + addi r2,r2,0x4000 + + bl .iSeries_early_setup + + /* relocation is on at this point */ + + b .start_here_common +#endif /* CONFIG_PPC_ISERIES */ + +#ifdef CONFIG_PPC_MULTIPLATFORM + +_STATIC(__mmu_off) + mfmsr r3 + andi. r0,r3,MSR_IR|MSR_DR + beqlr + andc r3,r3,r0 + mtspr SPRN_SRR0,r4 + mtspr SPRN_SRR1,r3 + sync + rfid + b . /* prevent speculative execution */ + + +/* + * Here is our main kernel entry point. We support currently 2 kind of entries + * depending on the value of r5. + * + * r5 != NULL -> OF entry, we go to prom_init, "legacy" parameter content + * in r3...r7 + * + * r5 == NULL -> kexec style entry. r3 is a physical pointer to the + * DT block, r4 is a physical pointer to the kernel itself + * + */ +_GLOBAL(__start_initialization_multiplatform) + /* + * Are we booted from a PROM Of-type client-interface ? + */ + cmpldi cr0,r5,0 + bne .__boot_from_prom /* yes -> prom */ + + /* Save parameters */ + mr r31,r3 + mr r30,r4 + + /* Make sure we are running in 64 bits mode */ + bl .enable_64b_mode + + /* Setup some critical 970 SPRs before switching MMU off */ + bl .__970_cpu_preinit + + /* cpu # */ + li r24,0 + + /* Switch off MMU if not already */ + LOADADDR(r4, .__after_prom_start - KERNELBASE) + add r4,r4,r30 + bl .__mmu_off + b .__after_prom_start + +_STATIC(__boot_from_prom) + /* Save parameters */ + mr r31,r3 + mr r30,r4 + mr r29,r5 + mr r28,r6 + mr r27,r7 + + /* Make sure we are running in 64 bits mode */ + bl .enable_64b_mode + + /* put a relocation offset into r3 */ + bl .reloc_offset + + LOADADDR(r2,__toc_start) + addi r2,r2,0x4000 + addi r2,r2,0x4000 + + /* Relocate the TOC from a virt addr to a real addr */ + sub r2,r2,r3 + + /* Restore parameters */ + mr r3,r31 + mr r4,r30 + mr r5,r29 + mr r6,r28 + mr r7,r27 + + /* Do all of the interaction with OF client interface */ + bl .prom_init + /* We never return */ + trap + +/* + * At this point, r3 contains the physical address we are running at, + * returned by prom_init() + */ +_STATIC(__after_prom_start) + +/* + * We need to run with __start at physical address 0. + * This will leave some code in the first 256B of + * real memory, which are reserved for software use. + * The remainder of the first page is loaded with the fixed + * interrupt vectors. The next two pages are filled with + * unknown exception placeholders. + * + * Note: This process overwrites the OF exception vectors. + * r26 == relocation offset + * r27 == KERNELBASE + */ + bl .reloc_offset + mr r26,r3 + SET_REG_TO_CONST(r27,KERNELBASE) + + li r3,0 /* target addr */ + + // XXX FIXME: Use phys returned by OF (r30) + sub r4,r27,r26 /* source addr */ + /* current address of _start */ + /* i.e. where we are running */ + /* the source addr */ + + LOADADDR(r5,copy_to_here) /* # bytes of memory to copy */ + sub r5,r5,r27 + + li r6,0x100 /* Start offset, the first 0x100 */ + /* bytes were copied earlier. */ + + bl .copy_and_flush /* copy the first n bytes */ + /* this includes the code being */ + /* executed here. */ + + LOADADDR(r0, 4f) /* Jump to the copy of this code */ + mtctr r0 /* that we just made/relocated */ + bctr + +4: LOADADDR(r5,klimit) + sub r5,r5,r26 + ld r5,0(r5) /* get the value of klimit */ + sub r5,r5,r27 + bl .copy_and_flush /* copy the rest */ + b .start_here_multiplatform + +#endif /* CONFIG_PPC_MULTIPLATFORM */ + +/* + * Copy routine used to copy the kernel to start at physical address 0 + * and flush and invalidate the caches as needed. + * r3 = dest addr, r4 = source addr, r5 = copy limit, r6 = start offset + * on exit, r3, r4, r5 are unchanged, r6 is updated to be >= r5. + * + * Note: this routine *only* clobbers r0, r6 and lr + */ +_GLOBAL(copy_and_flush) + addi r5,r5,-8 + addi r6,r6,-8 +4: li r0,16 /* Use the least common */ + /* denominator cache line */ + /* size. This results in */ + /* extra cache line flushes */ + /* but operation is correct. */ + /* Can't get cache line size */ + /* from NACA as it is being */ + /* moved too. */ + + mtctr r0 /* put # words/line in ctr */ +3: addi r6,r6,8 /* copy a cache line */ + ldx r0,r6,r4 + stdx r0,r6,r3 + bdnz 3b + dcbst r6,r3 /* write it to memory */ + sync + icbi r6,r3 /* flush the icache line */ + cmpld 0,r6,r5 + blt 4b + sync + addi r5,r5,8 + addi r6,r6,8 + blr + +.align 8 +copy_to_here: + +/* + * load_up_fpu(unused, unused, tsk) + * Disable FP for the task which had the FPU previously, + * and save its floating-point registers in its thread_struct. + * Enables the FPU for use in the kernel on return. + * On SMP we know the fpu is free, since we give it up every + * switch (ie, no lazy save of the FP registers). + * On entry: r13 == 'current' && last_task_used_math != 'current' + */ +_STATIC(load_up_fpu) + mfmsr r5 /* grab the current MSR */ + ori r5,r5,MSR_FP + mtmsrd r5 /* enable use of fpu now */ + isync +/* + * For SMP, we don't do lazy FPU switching because it just gets too + * horrendously complex, especially when a task switches from one CPU + * to another. Instead we call giveup_fpu in switch_to. + * + */ +#ifndef CONFIG_SMP + ld r3,last_task_used_math@got(r2) + ld r4,0(r3) + cmpdi 0,r4,0 + beq 1f + /* Save FP state to last_task_used_math's THREAD struct */ + addi r4,r4,THREAD + SAVE_32FPRS(0, r4) + mffs fr0 + stfd fr0,THREAD_FPSCR(r4) + /* Disable FP for last_task_used_math */ + ld r5,PT_REGS(r4) + ld r4,_MSR-STACK_FRAME_OVERHEAD(r5) + li r6,MSR_FP|MSR_FE0|MSR_FE1 + andc r4,r4,r6 + std r4,_MSR-STACK_FRAME_OVERHEAD(r5) +1: +#endif /* CONFIG_SMP */ + /* enable use of FP after return */ + ld r4,PACACURRENT(r13) + addi r5,r4,THREAD /* Get THREAD */ + ld r4,THREAD_FPEXC_MODE(r5) + ori r12,r12,MSR_FP + or r12,r12,r4 + std r12,_MSR(r1) + lfd fr0,THREAD_FPSCR(r5) + mtfsf 0xff,fr0 + REST_32FPRS(0, r5) +#ifndef CONFIG_SMP + /* Update last_task_used_math to 'current' */ + subi r4,r5,THREAD /* Back to 'current' */ + std r4,0(r3) +#endif /* CONFIG_SMP */ + /* restore registers and return */ + b fast_exception_return + +/* + * disable_kernel_fp() + * Disable the FPU. + */ +_GLOBAL(disable_kernel_fp) + mfmsr r3 + rldicl r0,r3,(63-MSR_FP_LG),1 + rldicl r3,r0,(MSR_FP_LG+1),0 + mtmsrd r3 /* disable use of fpu now */ + isync + blr + +/* + * giveup_fpu(tsk) + * Disable FP for the task given as the argument, + * and save the floating-point registers in its thread_struct. + * Enables the FPU for use in the kernel on return. + */ +_GLOBAL(giveup_fpu) + mfmsr r5 + ori r5,r5,MSR_FP + mtmsrd r5 /* enable use of fpu now */ + isync + cmpdi 0,r3,0 + beqlr- /* if no previous owner, done */ + addi r3,r3,THREAD /* want THREAD of task */ + ld r5,PT_REGS(r3) + cmpdi 0,r5,0 + SAVE_32FPRS(0, r3) + mffs fr0 + stfd fr0,THREAD_FPSCR(r3) + beq 1f + ld r4,_MSR-STACK_FRAME_OVERHEAD(r5) + li r3,MSR_FP|MSR_FE0|MSR_FE1 + andc r4,r4,r3 /* disable FP for previous task */ + std r4,_MSR-STACK_FRAME_OVERHEAD(r5) +1: +#ifndef CONFIG_SMP + li r5,0 + ld r4,last_task_used_math@got(r2) + std r5,0(r4) +#endif /* CONFIG_SMP */ + blr + + +#ifdef CONFIG_ALTIVEC + +/* + * load_up_altivec(unused, unused, tsk) + * Disable VMX for the task which had it previously, + * and save its vector registers in its thread_struct. + * Enables the VMX for use in the kernel on return. + * On SMP we know the VMX is free, since we give it up every + * switch (ie, no lazy save of the vector registers). + * On entry: r13 == 'current' && last_task_used_altivec != 'current' + */ +_STATIC(load_up_altivec) + mfmsr r5 /* grab the current MSR */ + oris r5,r5,MSR_VEC@h + mtmsrd r5 /* enable use of VMX now */ + isync + +/* + * For SMP, we don't do lazy VMX switching because it just gets too + * horrendously complex, especially when a task switches from one CPU + * to another. Instead we call giveup_altvec in switch_to. + * VRSAVE isn't dealt with here, that is done in the normal context + * switch code. Note that we could rely on vrsave value to eventually + * avoid saving all of the VREGs here... + */ +#ifndef CONFIG_SMP + ld r3,last_task_used_altivec@got(r2) + ld r4,0(r3) + cmpdi 0,r4,0 + beq 1f + /* Save VMX state to last_task_used_altivec's THREAD struct */ + addi r4,r4,THREAD + SAVE_32VRS(0,r5,r4) + mfvscr vr0 + li r10,THREAD_VSCR + stvx vr0,r10,r4 + /* Disable VMX for last_task_used_altivec */ + ld r5,PT_REGS(r4) + ld r4,_MSR-STACK_FRAME_OVERHEAD(r5) + lis r6,MSR_VEC@h + andc r4,r4,r6 + std r4,_MSR-STACK_FRAME_OVERHEAD(r5) +1: +#endif /* CONFIG_SMP */ + /* Hack: if we get an altivec unavailable trap with VRSAVE + * set to all zeros, we assume this is a broken application + * that fails to set it properly, and thus we switch it to + * all 1's + */ + mfspr r4,SPRN_VRSAVE + cmpdi 0,r4,0 + bne+ 1f + li r4,-1 + mtspr SPRN_VRSAVE,r4 +1: + /* enable use of VMX after return */ + ld r4,PACACURRENT(r13) + addi r5,r4,THREAD /* Get THREAD */ + oris r12,r12,MSR_VEC@h + std r12,_MSR(r1) + li r4,1 + li r10,THREAD_VSCR + stw r4,THREAD_USED_VR(r5) + lvx vr0,r10,r5 + mtvscr vr0 + REST_32VRS(0,r4,r5) +#ifndef CONFIG_SMP + /* Update last_task_used_math to 'current' */ + subi r4,r5,THREAD /* Back to 'current' */ + std r4,0(r3) +#endif /* CONFIG_SMP */ + /* restore registers and return */ + b fast_exception_return + +/* + * disable_kernel_altivec() + * Disable the VMX. + */ +_GLOBAL(disable_kernel_altivec) + mfmsr r3 + rldicl r0,r3,(63-MSR_VEC_LG),1 + rldicl r3,r0,(MSR_VEC_LG+1),0 + mtmsrd r3 /* disable use of VMX now */ + isync + blr + +/* + * giveup_altivec(tsk) + * Disable VMX for the task given as the argument, + * and save the vector registers in its thread_struct. + * Enables the VMX for use in the kernel on return. + */ +_GLOBAL(giveup_altivec) + mfmsr r5 + oris r5,r5,MSR_VEC@h + mtmsrd r5 /* enable use of VMX now */ + isync + cmpdi 0,r3,0 + beqlr- /* if no previous owner, done */ + addi r3,r3,THREAD /* want THREAD of task */ + ld r5,PT_REGS(r3) + cmpdi 0,r5,0 + SAVE_32VRS(0,r4,r3) + mfvscr vr0 + li r4,THREAD_VSCR + stvx vr0,r4,r3 + beq 1f + ld r4,_MSR-STACK_FRAME_OVERHEAD(r5) + lis r3,MSR_VEC@h + andc r4,r4,r3 /* disable FP for previous task */ + std r4,_MSR-STACK_FRAME_OVERHEAD(r5) +1: +#ifndef CONFIG_SMP + li r5,0 + ld r4,last_task_used_altivec@got(r2) + std r5,0(r4) +#endif /* CONFIG_SMP */ + blr + +#endif /* CONFIG_ALTIVEC */ + +#ifdef CONFIG_SMP +#ifdef CONFIG_PPC_PMAC +/* + * On PowerMac, secondary processors starts from the reset vector, which + * is temporarily turned into a call to one of the functions below. + */ + .section ".text"; + .align 2 ; + + .globl pmac_secondary_start_1 +pmac_secondary_start_1: + li r24, 1 + b .pmac_secondary_start + + .globl pmac_secondary_start_2 +pmac_secondary_start_2: + li r24, 2 + b .pmac_secondary_start + + .globl pmac_secondary_start_3 +pmac_secondary_start_3: + li r24, 3 + b .pmac_secondary_start + +_GLOBAL(pmac_secondary_start) + /* turn on 64-bit mode */ + bl .enable_64b_mode + isync + + /* Copy some CPU settings from CPU 0 */ + bl .__restore_cpu_setup + + /* pSeries do that early though I don't think we really need it */ + mfmsr r3 + ori r3,r3,MSR_RI + mtmsrd r3 /* RI on */ + + /* Set up a paca value for this processor. */ + LOADADDR(r4, paca) /* Get base vaddr of paca array */ + mulli r13,r24,PACA_SIZE /* Calculate vaddr of right paca */ + add r13,r13,r4 /* for this processor. */ + mtspr SPRG3,r13 /* Save vaddr of paca in SPRG3 */ + + /* Create a temp kernel stack for use before relocation is on. */ + ld r1,PACAEMERGSP(r13) + subi r1,r1,STACK_FRAME_OVERHEAD + + b .__secondary_start + +#endif /* CONFIG_PPC_PMAC */ + +/* + * This function is called after the master CPU has released the + * secondary processors. The execution environment is relocation off. + * The paca for this processor has the following fields initialized at + * this point: + * 1. Processor number + * 2. Segment table pointer (virtual address) + * On entry the following are set: + * r1 = stack pointer. vaddr for iSeries, raddr (temp stack) for pSeries + * r24 = cpu# (in Linux terms) + * r13 = paca virtual address + * SPRG3 = paca virtual address + */ +_GLOBAL(__secondary_start) + + HMT_MEDIUM /* Set thread priority to MEDIUM */ + + ld r2,PACATOC(r13) + li r6,0 + stb r6,PACAPROCENABLED(r13) + +#ifndef CONFIG_PPC_ISERIES + /* Initialize the page table pointer register. */ + LOADADDR(r6,_SDR1) + ld r6,0(r6) /* get the value of _SDR1 */ + mtspr SDR1,r6 /* set the htab location */ +#endif + /* Initialize the first segment table (or SLB) entry */ + ld r3,PACASTABVIRT(r13) /* get addr of segment table */ + bl .stab_initialize + + /* Initialize the kernel stack. Just a repeat for iSeries. */ + LOADADDR(r3,current_set) + sldi r28,r24,3 /* get current_set[cpu#] */ + ldx r1,r3,r28 + addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD + std r1,PACAKSAVE(r13) + + ld r3,PACASTABREAL(r13) /* get raddr of segment table */ + ori r4,r3,1 /* turn on valid bit */ + +#ifdef CONFIG_PPC_ISERIES + li r0,-1 /* hypervisor call */ + li r3,1 + sldi r3,r3,63 /* 0x8000000000000000 */ + ori r3,r3,4 /* 0x8000000000000004 */ + sc /* HvCall_setASR */ +#else + /* set the ASR */ + ld r3,systemcfg@got(r2) /* r3 = ptr to systemcfg */ + lwz r3,PLATFORM(r3) /* r3 = platform flags */ + cmpldi r3,PLATFORM_PSERIES_LPAR + bne 98f + mfspr r3,PVR + srwi r3,r3,16 + cmpwi r3,0x37 /* SStar */ + beq 97f + cmpwi r3,0x36 /* IStar */ + beq 97f + cmpwi r3,0x34 /* Pulsar */ + bne 98f +97: li r3,H_SET_ASR /* hcall = H_SET_ASR */ + HVSC /* Invoking hcall */ + b 99f +98: /* !(rpa hypervisor) || !(star) */ + mtasr r4 /* set the stab location */ +99: +#endif + li r7,0 + mtlr r7 + + /* enable MMU and jump to start_secondary */ + LOADADDR(r3,.start_secondary_prolog) + SET_REG_TO_CONST(r4, MSR_KERNEL) +#ifdef DO_SOFT_DISABLE + ori r4,r4,MSR_EE +#endif + mtspr SRR0,r3 + mtspr SRR1,r4 + rfid + b . /* prevent speculative execution */ + +/* + * Running with relocation on at this point. All we want to do is + * zero the stack back-chain pointer before going into C code. + */ +_GLOBAL(start_secondary_prolog) + li r3,0 + std r3,0(r1) /* Zero the stack frame pointer */ + bl .start_secondary +#endif + +/* + * This subroutine clobbers r11 and r12 + */ +_GLOBAL(enable_64b_mode) + mfmsr r11 /* grab the current MSR */ + li r12,1 + rldicr r12,r12,MSR_SF_LG,(63-MSR_SF_LG) + or r11,r11,r12 + li r12,1 + rldicr r12,r12,MSR_ISF_LG,(63-MSR_ISF_LG) + or r11,r11,r12 + mtmsrd r11 + isync + blr + +#ifdef CONFIG_PPC_MULTIPLATFORM +/* + * This is where the main kernel code starts. + */ +_STATIC(start_here_multiplatform) + /* get a new offset, now that the kernel has moved. */ + bl .reloc_offset + mr r26,r3 + + /* Clear out the BSS. It may have been done in prom_init, + * already but that's irrelevant since prom_init will soon + * be detached from the kernel completely. Besides, we need + * to clear it now for kexec-style entry. + */ + LOADADDR(r11,__bss_stop) + LOADADDR(r8,__bss_start) + sub r11,r11,r8 /* bss size */ + addi r11,r11,7 /* round up to an even double word */ + rldicl. r11,r11,61,3 /* shift right by 3 */ + beq 4f + addi r8,r8,-8 + li r0,0 + mtctr r11 /* zero this many doublewords */ +3: stdu r0,8(r8) + bdnz 3b +4: + + mfmsr r6 + ori r6,r6,MSR_RI + mtmsrd r6 /* RI on */ + +#ifdef CONFIG_HMT + /* Start up the second thread on cpu 0 */ + mfspr r3,PVR + srwi r3,r3,16 + cmpwi r3,0x34 /* Pulsar */ + beq 90f + cmpwi r3,0x36 /* Icestar */ + beq 90f + cmpwi r3,0x37 /* SStar */ + beq 90f + b 91f /* HMT not supported */ +90: li r3,0 + bl .hmt_start_secondary +91: +#endif + + /* The following gets the stack and TOC set up with the regs */ + /* pointing to the real addr of the kernel stack. This is */ + /* all done to support the C function call below which sets */ + /* up the htab. This is done because we have relocated the */ + /* kernel but are still running in real mode. */ + + LOADADDR(r3,init_thread_union) + sub r3,r3,r26 + + /* set up a stack pointer (physical address) */ + addi r1,r3,THREAD_SIZE + li r0,0 + stdu r0,-STACK_FRAME_OVERHEAD(r1) + + /* set up the TOC (physical address) */ + LOADADDR(r2,__toc_start) + addi r2,r2,0x4000 + addi r2,r2,0x4000 + sub r2,r2,r26 + + LOADADDR(r3,cpu_specs) + sub r3,r3,r26 + LOADADDR(r4,cur_cpu_spec) + sub r4,r4,r26 + mr r5,r26 + bl .identify_cpu + + /* Save some low level config HIDs of CPU0 to be copied to + * other CPUs later on, or used for suspend/resume + */ + bl .__save_cpu_setup + sync + + /* Setup a valid physical PACA pointer in SPRG3 for early_setup + * note that boot_cpuid can always be 0 nowadays since there is + * nowhere it can be initialized differently before we reach this + * code + */ + LOADADDR(r27, boot_cpuid) + sub r27,r27,r26 + lwz r27,0(r27) + + LOADADDR(r24, paca) /* Get base vaddr of paca array */ + mulli r13,r27,PACA_SIZE /* Calculate vaddr of right paca */ + add r13,r13,r24 /* for this processor. */ + sub r13,r13,r26 /* convert to physical addr */ + mtspr SPRG3,r13 /* PPPBBB: Temp... -Peter */ + + /* Do very early kernel initializations, including initial hash table, + * stab and slb setup before we turn on relocation. */ + + /* Restore parameters passed from prom_init/kexec */ + mr r3,r31 + bl .early_setup + + /* set the ASR */ + ld r3,PACASTABREAL(r13) + ori r4,r3,1 /* turn on valid bit */ + ld r3,systemcfg@got(r2) /* r3 = ptr to systemcfg */ + lwz r3,PLATFORM(r3) /* r3 = platform flags */ + cmpldi r3,PLATFORM_PSERIES_LPAR + bne 98f + mfspr r3,PVR + srwi r3,r3,16 + cmpwi r3,0x37 /* SStar */ + beq 97f + cmpwi r3,0x36 /* IStar */ + beq 97f + cmpwi r3,0x34 /* Pulsar */ + bne 98f +97: li r3,H_SET_ASR /* hcall = H_SET_ASR */ + HVSC /* Invoking hcall */ + b 99f +98: /* !(rpa hypervisor) || !(star) */ + mtasr r4 /* set the stab location */ +99: + /* Set SDR1 (hash table pointer) */ + ld r3,systemcfg@got(r2) /* r3 = ptr to systemcfg */ + lwz r3,PLATFORM(r3) /* r3 = platform flags */ + /* Test if bit 0 is set (LPAR bit) */ + andi. r3,r3,0x1 + bne 98f + LOADADDR(r6,_SDR1) /* Only if NOT LPAR */ + sub r6,r6,r26 + ld r6,0(r6) /* get the value of _SDR1 */ + mtspr SDR1,r6 /* set the htab location */ +98: + LOADADDR(r3,.start_here_common) + SET_REG_TO_CONST(r4, MSR_KERNEL) + mtspr SRR0,r3 + mtspr SRR1,r4 + rfid + b . /* prevent speculative execution */ +#endif /* CONFIG_PPC_MULTIPLATFORM */ + + /* This is where all platforms converge execution */ +_STATIC(start_here_common) + /* relocation is on at this point */ + + /* The following code sets up the SP and TOC now that we are */ + /* running with translation enabled. */ + + LOADADDR(r3,init_thread_union) + + /* set up the stack */ + addi r1,r3,THREAD_SIZE + li r0,0 + stdu r0,-STACK_FRAME_OVERHEAD(r1) + + /* Apply the CPUs-specific fixups (nop out sections not relevant + * to this CPU + */ + li r3,0 + bl .do_cpu_ftr_fixups + + LOADADDR(r26, boot_cpuid) + lwz r26,0(r26) + + LOADADDR(r24, paca) /* Get base vaddr of paca array */ + mulli r13,r26,PACA_SIZE /* Calculate vaddr of right paca */ + add r13,r13,r24 /* for this processor. */ + mtspr SPRG3,r13 + + /* ptr to current */ + LOADADDR(r4,init_task) + std r4,PACACURRENT(r13) + + /* Load the TOC */ + ld r2,PACATOC(r13) + std r1,PACAKSAVE(r13) + + bl .setup_system + + /* Load up the kernel context */ +5: +#ifdef DO_SOFT_DISABLE + li r5,0 + stb r5,PACAPROCENABLED(r13) /* Soft Disabled */ + mfmsr r5 + ori r5,r5,MSR_EE /* Hard Enabled */ + mtmsrd r5 +#endif + + bl .start_kernel + +_GLOBAL(__setup_cpu_power3) + blr + +_GLOBAL(hmt_init) +#ifdef CONFIG_HMT + LOADADDR(r5, hmt_thread_data) + mfspr r7,PVR + srwi r7,r7,16 + cmpwi r7,0x34 /* Pulsar */ + beq 90f + cmpwi r7,0x36 /* Icestar */ + beq 91f + cmpwi r7,0x37 /* SStar */ + beq 91f + b 101f +90: mfspr r6,PIR + andi. r6,r6,0x1f + b 92f +91: mfspr r6,PIR + andi. r6,r6,0x3ff +92: sldi r4,r24,3 + stwx r6,r5,r4 + bl .hmt_start_secondary + b 101f + +__hmt_secondary_hold: + LOADADDR(r5, hmt_thread_data) + clrldi r5,r5,4 + li r7,0 + mfspr r6,PIR + mfspr r8,PVR + srwi r8,r8,16 + cmpwi r8,0x34 + bne 93f + andi. r6,r6,0x1f + b 103f +93: andi. r6,r6,0x3f + +103: lwzx r8,r5,r7 + cmpw r8,r6 + beq 104f + addi r7,r7,8 + b 103b + +104: addi r7,r7,4 + lwzx r9,r5,r7 + mr r24,r9 +101: +#endif + mr r3,r24 + b .pSeries_secondary_smp_init + +#ifdef CONFIG_HMT +_GLOBAL(hmt_start_secondary) + LOADADDR(r4,__hmt_secondary_hold) + clrldi r4,r4,4 + mtspr NIADORM, r4 + mfspr r4, MSRDORM + li r5, -65 + and r4, r4, r5 + mtspr MSRDORM, r4 + lis r4,0xffef + ori r4,r4,0x7403 + mtspr TSC, r4 + li r4,0x1f4 + mtspr TST, r4 + mfspr r4, HID0 + ori r4, r4, 0x1 + mtspr HID0, r4 + mfspr r4, CTRLF + oris r4, r4, 0x40 + mtspr CTRLT, r4 + blr +#endif + +#if defined(CONFIG_SMP) && !defined(CONFIG_PPC_ISERIES) +_GLOBAL(smp_release_cpus) + /* All secondary cpus are spinning on a common + * spinloop, release them all now so they can start + * to spin on their individual paca spinloops. + * For non SMP kernels, the secondary cpus never + * get out of the common spinloop. + */ + li r3,1 + LOADADDR(r5,__secondary_hold_spinloop) + std r3,0(r5) + sync + blr +#endif /* CONFIG_SMP && !CONFIG_PPC_ISERIES */ + + +/* + * We put a few things here that have to be page-aligned. + * This stuff goes at the beginning of the data segment, + * which is page-aligned. + */ + .data + .align 12 + .globl sdata +sdata: + .globl empty_zero_page +empty_zero_page: + .space 4096 + + .globl swapper_pg_dir +swapper_pg_dir: + .space 4096 + + .globl ioremap_dir +ioremap_dir: + .space 4096 + +#ifdef CONFIG_SMP +/* 1 page segment table per cpu (max 48, cpu0 allocated at STAB0_PHYS_ADDR) */ + .globl stab_array +stab_array: + .space 4096 * 48 +#endif + +/* + * 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 |