diff options
Diffstat (limited to 'arch/x86_64/kernel/acpi/wakeup.S')
| -rw-r--r-- | arch/x86_64/kernel/acpi/wakeup.S | 527 |
1 files changed, 527 insertions, 0 deletions
diff --git a/arch/x86_64/kernel/acpi/wakeup.S b/arch/x86_64/kernel/acpi/wakeup.S new file mode 100644 index 000000000000..a4c630034cd4 --- /dev/null +++ b/arch/x86_64/kernel/acpi/wakeup.S @@ -0,0 +1,527 @@ +.text +#include <linux/linkage.h> +#include <asm/segment.h> +#include <asm/page.h> +#include <asm/msr.h> + +# Copyright 2003 Pavel Machek <pavel@suse.cz>, distribute under GPLv2 +# +# wakeup_code runs in real mode, and at unknown address (determined at run-time). +# Therefore it must only use relative jumps/calls. +# +# Do we need to deal with A20? It is okay: ACPI specs says A20 must be enabled +# +# If physical address of wakeup_code is 0x12345, BIOS should call us with +# cs = 0x1234, eip = 0x05 +# + + +ALIGN + .align 16 +ENTRY(wakeup_start) +wakeup_code: + wakeup_code_start = . + .code16 + +# Running in *copy* of this code, somewhere in low 1MB. + + movb $0xa1, %al ; outb %al, $0x80 + cli + cld + # setup data segment + movw %cs, %ax + movw %ax, %ds # Make ds:0 point to wakeup_start + movw %ax, %ss + mov $(wakeup_stack - wakeup_code), %sp # Private stack is needed for ASUS board + + pushl $0 # Kill any dangerous flags + popfl + + movl real_magic - wakeup_code, %eax + cmpl $0x12345678, %eax + jne bogus_real_magic + + testl $1, video_flags - wakeup_code + jz 1f + lcall $0xc000,$3 + movw %cs, %ax + movw %ax, %ds # Bios might have played with that + movw %ax, %ss +1: + + testl $2, video_flags - wakeup_code + jz 1f + mov video_mode - wakeup_code, %ax + call mode_seta +1: + + movw $0xb800, %ax + movw %ax,%fs + movw $0x0e00 + 'L', %fs:(0x10) + + movb $0xa2, %al ; outb %al, $0x80 + + lidt %ds:idt_48a - wakeup_code + xorl %eax, %eax + movw %ds, %ax # (Convert %ds:gdt to a linear ptr) + shll $4, %eax + addl $(gdta - wakeup_code), %eax + movl %eax, gdt_48a +2 - wakeup_code + lgdt %ds:gdt_48a - wakeup_code # load gdt with whatever is + # appropriate + + movl $1, %eax # protected mode (PE) bit + lmsw %ax # This is it! + jmp 1f +1: + + .byte 0x66, 0xea # prefix + jmpi-opcode + .long wakeup_32 - __START_KERNEL_map + .word __KERNEL_CS + + .code32 +wakeup_32: +# Running in this code, but at low address; paging is not yet turned on. + movb $0xa5, %al ; outb %al, $0x80 + + /* Check if extended functions are implemented */ + movl $0x80000000, %eax + cpuid + cmpl $0x80000000, %eax + jbe bogus_cpu + wbinvd + mov $0x80000001, %eax + cpuid + btl $29, %edx + jnc bogus_cpu + movl %edx,%edi + + movw $__KERNEL_DS, %ax + movw %ax, %ds + movw %ax, %es + movw %ax, %fs + movw %ax, %gs + + movw $__KERNEL_DS, %ax + movw %ax, %ss + + mov $(wakeup_stack - __START_KERNEL_map), %esp + movl saved_magic - __START_KERNEL_map, %eax + cmpl $0x9abcdef0, %eax + jne bogus_32_magic + + /* + * Prepare for entering 64bits mode + */ + + /* Enable PAE mode and PGE */ + xorl %eax, %eax + btsl $5, %eax + btsl $7, %eax + movl %eax, %cr4 + + /* Setup early boot stage 4 level pagetables */ + movl $(wakeup_level4_pgt - __START_KERNEL_map), %eax + movl %eax, %cr3 + + /* Setup EFER (Extended Feature Enable Register) */ + movl $MSR_EFER, %ecx + rdmsr + /* Fool rdmsr and reset %eax to avoid dependences */ + xorl %eax, %eax + /* Enable Long Mode */ + btsl $_EFER_LME, %eax + /* Enable System Call */ + btsl $_EFER_SCE, %eax + + /* No Execute supported? */ + btl $20,%edi + jnc 1f + btsl $_EFER_NX, %eax +1: + + /* Make changes effective */ + wrmsr + wbinvd + + xorl %eax, %eax + btsl $31, %eax /* Enable paging and in turn activate Long Mode */ + btsl $0, %eax /* Enable protected mode */ + btsl $1, %eax /* Enable MP */ + btsl $4, %eax /* Enable ET */ + btsl $5, %eax /* Enable NE */ + btsl $16, %eax /* Enable WP */ + btsl $18, %eax /* Enable AM */ + + /* Make changes effective */ + movl %eax, %cr0 + /* At this point: + CR4.PAE must be 1 + CS.L must be 0 + CR3 must point to PML4 + Next instruction must be a branch + This must be on identity-mapped page + */ + jmp reach_compatibility_mode +reach_compatibility_mode: + movw $0x0e00 + 'i', %ds:(0xb8012) + movb $0xa8, %al ; outb %al, $0x80; + + /* + * At this point we're in long mode but in 32bit compatibility mode + * with EFER.LME = 1, CS.L = 0, CS.D = 1 (and in turn + * EFER.LMA = 1). Now we want to jump in 64bit mode, to do that we load + * the new gdt/idt that has __KERNEL_CS with CS.L = 1. + */ + + movw $0x0e00 + 'n', %ds:(0xb8014) + movb $0xa9, %al ; outb %al, $0x80 + + /* Load new GDT with the 64bit segment using 32bit descriptor */ + movl $(pGDT32 - __START_KERNEL_map), %eax + lgdt (%eax) + + movl $(wakeup_jumpvector - __START_KERNEL_map), %eax + /* Finally jump in 64bit mode */ + ljmp *(%eax) + +wakeup_jumpvector: + .long wakeup_long64 - __START_KERNEL_map + .word __KERNEL_CS + +.code64 + + /* Hooray, we are in Long 64-bit mode (but still running in low memory) */ +wakeup_long64: + /* + * We must switch to a new descriptor in kernel space for the GDT + * because soon the kernel won't have access anymore to the userspace + * addresses where we're currently running on. We have to do that here + * because in 32bit we couldn't load a 64bit linear address. + */ + lgdt cpu_gdt_descr - __START_KERNEL_map + + movw $0x0e00 + 'u', %ds:(0xb8016) + + nop + nop + movw $__KERNEL_DS, %ax + movw %ax, %ss + movw %ax, %ds + movw %ax, %es + movw %ax, %fs + movw %ax, %gs + movq saved_esp, %rsp + + movw $0x0e00 + 'x', %ds:(0xb8018) + movq saved_ebx, %rbx + movq saved_edi, %rdi + movq saved_esi, %rsi + movq saved_ebp, %rbp + + movw $0x0e00 + '!', %ds:(0xb801a) + movq saved_eip, %rax + jmp *%rax + +.code32 + + .align 64 +gdta: + .word 0, 0, 0, 0 # dummy + + .word 0, 0, 0, 0 # unused + + .word 0xFFFF # 4Gb - (0x100000*0x1000 = 4Gb) + .word 0 # base address = 0 + .word 0x9B00 # code read/exec. ??? Why I need 0x9B00 (as opposed to 0x9A00 in order for this to work?) + .word 0x00CF # granularity = 4096, 386 + # (+5th nibble of limit) + + .word 0xFFFF # 4Gb - (0x100000*0x1000 = 4Gb) + .word 0 # base address = 0 + .word 0x9200 # data read/write + .word 0x00CF # granularity = 4096, 386 + # (+5th nibble of limit) +# this is 64bit descriptor for code + .word 0xFFFF + .word 0 + .word 0x9A00 # code read/exec + .word 0x00AF # as above, but it is long mode and with D=0 + +idt_48a: + .word 0 # idt limit = 0 + .word 0, 0 # idt base = 0L + +gdt_48a: + .word 0x8000 # gdt limit=2048, + # 256 GDT entries + .word 0, 0 # gdt base (filled in later) + + +real_save_gdt: .word 0 + .quad 0 +real_magic: .quad 0 +video_mode: .quad 0 +video_flags: .quad 0 + +bogus_real_magic: + movb $0xba,%al ; outb %al,$0x80 + jmp bogus_real_magic + +bogus_32_magic: + movb $0xb3,%al ; outb %al,$0x80 + jmp bogus_32_magic + +bogus_31_magic: + movb $0xb1,%al ; outb %al,$0x80 + jmp bogus_31_magic + +bogus_cpu: + movb $0xbc,%al ; outb %al,$0x80 + jmp bogus_cpu + + +/* This code uses an extended set of video mode numbers. These include: + * Aliases for standard modes + * NORMAL_VGA (-1) + * EXTENDED_VGA (-2) + * ASK_VGA (-3) + * Video modes numbered by menu position -- NOT RECOMMENDED because of lack + * of compatibility when extending the table. These are between 0x00 and 0xff. + */ +#define VIDEO_FIRST_MENU 0x0000 + +/* Standard BIOS video modes (BIOS number + 0x0100) */ +#define VIDEO_FIRST_BIOS 0x0100 + +/* VESA BIOS video modes (VESA number + 0x0200) */ +#define VIDEO_FIRST_VESA 0x0200 + +/* Video7 special modes (BIOS number + 0x0900) */ +#define VIDEO_FIRST_V7 0x0900 + +# Setting of user mode (AX=mode ID) => CF=success +mode_seta: + movw %ax, %bx +#if 0 + cmpb $0xff, %ah + jz setalias + + testb $VIDEO_RECALC>>8, %ah + jnz _setrec + + cmpb $VIDEO_FIRST_RESOLUTION>>8, %ah + jnc setres + + cmpb $VIDEO_FIRST_SPECIAL>>8, %ah + jz setspc + + cmpb $VIDEO_FIRST_V7>>8, %ah + jz setv7 +#endif + + cmpb $VIDEO_FIRST_VESA>>8, %ah + jnc check_vesaa +#if 0 + orb %ah, %ah + jz setmenu +#endif + + decb %ah +# jz setbios Add bios modes later + +setbada: clc + ret + +check_vesaa: + subb $VIDEO_FIRST_VESA>>8, %bh + orw $0x4000, %bx # Use linear frame buffer + movw $0x4f02, %ax # VESA BIOS mode set call + int $0x10 + cmpw $0x004f, %ax # AL=4f if implemented + jnz _setbada # AH=0 if OK + + stc + ret + +_setbada: jmp setbada + + .code64 +bogus_magic: + movw $0x0e00 + 'B', %ds:(0xb8018) + jmp bogus_magic + +bogus_magic2: + movw $0x0e00 + '2', %ds:(0xb8018) + jmp bogus_magic2 + + +wakeup_stack_begin: # Stack grows down + +.org 0xff0 +wakeup_stack: # Just below end of page + +ENTRY(wakeup_end) + +## +# acpi_copy_wakeup_routine +# +# Copy the above routine to low memory. +# +# Parameters: +# %rdi: place to copy wakeup routine to +# +# Returned address is location of code in low memory (past data and stack) +# +ENTRY(acpi_copy_wakeup_routine) + pushq %rax + pushq %rcx + pushq %rdx + + sgdt saved_gdt + sidt saved_idt + sldt saved_ldt + str saved_tss + + movq %cr3, %rdx + movq %rdx, saved_cr3 + movq %cr4, %rdx + movq %rdx, saved_cr4 + movq %cr0, %rdx + movq %rdx, saved_cr0 + sgdt real_save_gdt - wakeup_start (,%rdi) + movl $MSR_EFER, %ecx + rdmsr + movl %eax, saved_efer + movl %edx, saved_efer2 + + movl saved_video_mode, %edx + movl %edx, video_mode - wakeup_start (,%rdi) + movl acpi_video_flags, %edx + movl %edx, video_flags - wakeup_start (,%rdi) + movq $0x12345678, real_magic - wakeup_start (,%rdi) + movq $0x123456789abcdef0, %rdx + movq %rdx, saved_magic + + movl saved_magic - __START_KERNEL_map, %eax + cmpl $0x9abcdef0, %eax + jne bogus_32_magic + + # make sure %cr4 is set correctly (features, etc) + movl saved_cr4 - __START_KERNEL_map, %eax + movq %rax, %cr4 + + movl saved_cr0 - __START_KERNEL_map, %eax + movq %rax, %cr0 + jmp 1f # Flush pipelines +1: + # restore the regs we used + popq %rdx + popq %rcx + popq %rax +ENTRY(do_suspend_lowlevel_s4bios) + ret + + .align 2 + .p2align 4,,15 +.globl do_suspend_lowlevel + .type do_suspend_lowlevel,@function +do_suspend_lowlevel: +.LFB5: + subq $8, %rsp + xorl %eax, %eax + call save_processor_state + + movq %rsp, saved_context_esp(%rip) + movq %rax, saved_context_eax(%rip) + movq %rbx, saved_context_ebx(%rip) + movq %rcx, saved_context_ecx(%rip) + movq %rdx, saved_context_edx(%rip) + movq %rbp, saved_context_ebp(%rip) + movq %rsi, saved_context_esi(%rip) + movq %rdi, saved_context_edi(%rip) + movq %r8, saved_context_r08(%rip) + movq %r9, saved_context_r09(%rip) + movq %r10, saved_context_r10(%rip) + movq %r11, saved_context_r11(%rip) + movq %r12, saved_context_r12(%rip) + movq %r13, saved_context_r13(%rip) + movq %r14, saved_context_r14(%rip) + movq %r15, saved_context_r15(%rip) + pushfq ; popq saved_context_eflags(%rip) + + movq $.L97, saved_eip(%rip) + + movq %rsp,saved_esp + movq %rbp,saved_ebp + movq %rbx,saved_ebx + movq %rdi,saved_edi + movq %rsi,saved_esi + + addq $8, %rsp + movl $3, %edi + xorl %eax, %eax + jmp acpi_enter_sleep_state +.L97: + .p2align 4,,7 +.L99: + .align 4 + movl $24, %eax + movw %ax, %ds + movq saved_context+58(%rip), %rax + movq %rax, %cr4 + movq saved_context+50(%rip), %rax + movq %rax, %cr3 + movq saved_context+42(%rip), %rax + movq %rax, %cr2 + movq saved_context+34(%rip), %rax + movq %rax, %cr0 + pushq saved_context_eflags(%rip) ; popfq + movq saved_context_esp(%rip), %rsp + movq saved_context_ebp(%rip), %rbp + movq saved_context_eax(%rip), %rax + movq saved_context_ebx(%rip), %rbx + movq saved_context_ecx(%rip), %rcx + movq saved_context_edx(%rip), %rdx + movq saved_context_esi(%rip), %rsi + movq saved_context_edi(%rip), %rdi + movq saved_context_r08(%rip), %r8 + movq saved_context_r09(%rip), %r9 + movq saved_context_r10(%rip), %r10 + movq saved_context_r11(%rip), %r11 + movq saved_context_r12(%rip), %r12 + movq saved_context_r13(%rip), %r13 + movq saved_context_r14(%rip), %r14 + movq saved_context_r15(%rip), %r15 + + xorl %eax, %eax + addq $8, %rsp + jmp restore_processor_state +.LFE5: +.Lfe5: + .size do_suspend_lowlevel,.Lfe5-do_suspend_lowlevel + +.data +ALIGN +ENTRY(saved_ebp) .quad 0 +ENTRY(saved_esi) .quad 0 +ENTRY(saved_edi) .quad 0 +ENTRY(saved_ebx) .quad 0 + +ENTRY(saved_eip) .quad 0 +ENTRY(saved_esp) .quad 0 + +ENTRY(saved_magic) .quad 0 + +ALIGN +# saved registers +saved_gdt: .quad 0,0 +saved_idt: .quad 0,0 +saved_ldt: .quad 0 +saved_tss: .quad 0 + +saved_cr0: .quad 0 +saved_cr3: .quad 0 +saved_cr4: .quad 0 +saved_efer: .quad 0 +saved_efer2: .quad 0 |