X-Git-Url: http://v3vee.org/palacios/gitweb/gitweb.cgi?a=blobdiff_plain;f=kitten%2Farch%2Fx86_64%2Fboot%2Fsetup.S;fp=kitten%2Farch%2Fx86_64%2Fboot%2Fsetup.S;h=5092de59720d52ae4c39e0bc5bad3b1e07853c6d;hb=66a1a4c7a9edcd7d8bc207aca093d694a6e6b5b2;hp=0000000000000000000000000000000000000000;hpb=f7cf9c19ecb0a589dd45ae0d2c91814bd3c2acc2;p=palacios.git diff --git a/kitten/arch/x86_64/boot/setup.S b/kitten/arch/x86_64/boot/setup.S new file mode 100644 index 0000000..5092de5 --- /dev/null +++ b/kitten/arch/x86_64/boot/setup.S @@ -0,0 +1,824 @@ +/* + * setup.S Copyright (C) 1991, 1992 Linus Torvalds + * + * setup.s is responsible for getting the system data from the BIOS, + * and putting them into the appropriate places in system memory. + * both setup.s and system has been loaded by the bootblock. + * + * This code asks the bios for memory/disk/other parameters, and + * puts them in a "safe" place: 0x90000-0x901FF, ie where the + * boot-block used to be. It is then up to the protected mode + * system to read them from there before the area is overwritten + * for buffer-blocks. + * + * Move PS/2 aux init code to psaux.c + * (troyer@saifr00.cfsat.Honeywell.COM) 03Oct92 + * + * some changes and additional features by Christoph Niemann, + * March 1993/June 1994 (Christoph.Niemann@linux.org) + * + * add APM BIOS checking by Stephen Rothwell, May 1994 + * (sfr@canb.auug.org.au) + * + * High load stuff, initrd support and position independency + * by Hans Lermen & Werner Almesberger, February 1996 + * , + * + * Video handling moved to video.S by Martin Mares, March 1996 + * + * + * Extended memory detection scheme retwiddled by orc@pell.chi.il.us (david + * parsons) to avoid loadlin confusion, July 1997 + * + * Transcribed from Intel (as86) -> AT&T (gas) by Chris Noe, May 1999. + * + * + * Fix to work around buggy BIOSes which don't use carry bit correctly + * and/or report extended memory in CX/DX for e801h memory size detection + * call. As a result the kernel got wrong figures. The int15/e801h docs + * from Ralf Brown interrupt list seem to indicate AX/BX should be used + * anyway. So to avoid breaking many machines (presumably there was a reason + * to orginally use CX/DX instead of AX/BX), we do a kludge to see + * if CX/DX have been changed in the e801 call and if so use AX/BX . + * Michael Miller, April 2001 + * + * Added long mode checking and SSE force. March 2003, Andi Kleen. + */ + +#include +#include +#include +#include +#include +#include +#include + +/* Signature words to ensure LILO loaded us right */ +#define SIG1 0xAA55 +#define SIG2 0x5A5A + +INITSEG = DEF_INITSEG # 0x9000, we move boot here, out of the way +SYSSEG = DEF_SYSSEG # 0x1000, system loaded at 0x10000 (65536). +SETUPSEG = DEF_SETUPSEG # 0x9020, this is the current segment + # ... and the former contents of CS + +DELTA_INITSEG = SETUPSEG - INITSEG # 0x0020 + +.code16 +.globl begtext, begdata, begbss, endtext, enddata, endbss + +.text +begtext: +.data +begdata: +.bss +begbss: +.text + +start: + jmp trampoline + +# This is the setup header, and it must start at %cs:2 (old 0x9020:2) + + .ascii "HdrS" # header signature + .word 0x0206 # header version number (>= 0x0105) + # or else old loadlin-1.5 will fail) +realmode_swtch: .word 0, 0 # default_switch, SETUPSEG +start_sys_seg: .word SYSSEG + .word kernel_version # pointing to kernel version string + # above section of header is compatible + # with loadlin-1.5 (header v1.5). Don't + # change it. + +type_of_loader: .byte 0 # = 0, old one (LILO, Loadlin, + # Bootlin, SYSLX, bootsect...) + # See Documentation/i386/boot.txt for + # assigned ids + +# flags, unused bits must be zero (RFU) bit within loadflags +loadflags: +LOADED_HIGH = 1 # If set, the kernel is loaded high +CAN_USE_HEAP = 0x80 # If set, the loader also has set + # heap_end_ptr to tell how much + # space behind setup.S can be used for + # heap purposes. + # Only the loader knows what is free +#ifndef __BIG_KERNEL__ + .byte 0 +#else + .byte LOADED_HIGH +#endif + +setup_move_size: .word 0x8000 # size to move, when setup is not + # loaded at 0x90000. We will move setup + # to 0x90000 then just before jumping + # into the kernel. However, only the + # loader knows how much data behind + # us also needs to be loaded. + +code32_start: # here loaders can put a different + # start address for 32-bit code. +#ifndef __BIG_KERNEL__ + .long 0x1000 # 0x1000 = default for zImage +#else + .long 0x100000 # 0x100000 = default for big kernel +#endif + +ramdisk_image: .long 0 # address of loaded ramdisk image + # Here the loader puts the 32-bit + # address where it loaded the image. + # This only will be read by the kernel. + +ramdisk_size: .long 0 # its size in bytes + +bootsect_kludge: + .long 0 # obsolete + +heap_end_ptr: .word modelist+1024 # (Header version 0x0201 or later) + # space from here (exclusive) down to + # end of setup code can be used by setup + # for local heap purposes. + +pad1: .word 0 +cmd_line_ptr: .long 0 # (Header version 0x0202 or later) + # If nonzero, a 32-bit pointer + # to the kernel command line. + # The command line should be + # located between the start of + # setup and the end of low + # memory (0xa0000), or it may + # get overwritten before it + # gets read. If this field is + # used, there is no longer + # anything magical about the + # 0x90000 segment; the setup + # can be located anywhere in + # low memory 0x10000 or higher. + +ramdisk_max: .long 0xffffffff +kernel_alignment: .long 0x200000 # physical addr alignment required for + # protected mode relocatable kernel +#ifdef CONFIG_RELOCATABLE +relocatable_kernel: .byte 1 +#else +relocatable_kernel: .byte 0 +#endif +pad2: .byte 0 +pad3: .word 0 + +cmdline_size: .long COMMAND_LINE_SIZE-1 #length of the command line, + #added with boot protocol + #version 2.06 + +trampoline: call start_of_setup + .align 16 + # The offset at this point is 0x240 + .space (0xeff-0x240+1) # E820 & EDD space (ending at 0xeff) +# End of setup header ##################################################### + +start_of_setup: +# Bootlin depends on this being done early + movw $0x01500, %ax + movb $0x81, %dl + int $0x13 + +#ifdef SAFE_RESET_DISK_CONTROLLER +# Reset the disk controller. + movw $0x0000, %ax + movb $0x80, %dl + int $0x13 +#endif + +# Set %ds = %cs, we know that SETUPSEG = %cs at this point + movw %cs, %ax # aka SETUPSEG + movw %ax, %ds +# Check signature at end of setup + cmpw $SIG1, setup_sig1 + jne bad_sig + + cmpw $SIG2, setup_sig2 + jne bad_sig + + jmp good_sig1 + +# Routine to print asciiz string at ds:si +prtstr: + lodsb + andb %al, %al + jz fin + + call prtchr + jmp prtstr + +fin: ret + +# Space printing +prtsp2: call prtspc # Print double space +prtspc: movb $0x20, %al # Print single space (note: fall-thru) + +prtchr: + pushw %ax + pushw %cx + movw $0007,%bx + movw $0x01, %cx + movb $0x0e, %ah + int $0x10 + popw %cx + popw %ax + ret + +beep: movb $0x07, %al + jmp prtchr + +no_sig_mess: .string "No setup signature found ..." + +good_sig1: + jmp good_sig + +# We now have to find the rest of the setup code/data +bad_sig: + movw %cs, %ax # SETUPSEG + subw $DELTA_INITSEG, %ax # INITSEG + movw %ax, %ds + xorb %bh, %bh + movb (497), %bl # get setup sect from bootsect + subw $4, %bx # LILO loads 4 sectors of setup + shlw $8, %bx # convert to words (1sect=2^8 words) + movw %bx, %cx + shrw $3, %bx # convert to segment + addw $SYSSEG, %bx + movw %bx, %cs:start_sys_seg +# Move rest of setup code/data to here + movw $2048, %di # four sectors loaded by LILO + subw %si, %si + movw %cs, %ax # aka SETUPSEG + movw %ax, %es + movw $SYSSEG, %ax + movw %ax, %ds + rep + movsw + movw %cs, %ax # aka SETUPSEG + movw %ax, %ds + cmpw $SIG1, setup_sig1 + jne no_sig + + cmpw $SIG2, setup_sig2 + jne no_sig + + jmp good_sig + +no_sig: + lea no_sig_mess, %si + call prtstr + +no_sig_loop: + jmp no_sig_loop + +good_sig: + movw %cs, %ax # aka SETUPSEG + subw $DELTA_INITSEG, %ax # aka INITSEG + movw %ax, %ds +# Check if an old loader tries to load a big-kernel + testb $LOADED_HIGH, %cs:loadflags # Do we have a big kernel? + jz loader_ok # No, no danger for old loaders. + + cmpb $0, %cs:type_of_loader # Do we have a loader that + # can deal with us? + jnz loader_ok # Yes, continue. + + pushw %cs # No, we have an old loader, + popw %ds # die. + lea loader_panic_mess, %si + call prtstr + + jmp no_sig_loop + +loader_panic_mess: .string "Wrong loader, giving up..." + +loader_ok: + /* check for long mode. */ + /* we have to do this before the VESA setup, otherwise the user + can't see the error message. */ + + pushw %ds + movw %cs,%ax + movw %ax,%ds + + call verify_cpu + testl %eax,%eax + jz sse_ok + +no_longmode: + call beep + lea long_mode_panic,%si + call prtstr +no_longmode_loop: + jmp no_longmode_loop +long_mode_panic: + .string "BOOT FAILURE: This system does not support x86_64 long mode." + .byte 0 + +#include "../kernel/verify_cpu.S" +sse_ok: + popw %ds + +# tell BIOS we want to go to long mode + movl $0xec00,%eax # declare target operating mode + movl $2,%ebx # long mode + int $0x15 + +# Get memory size (extended mem, kB) + + xorl %eax, %eax + movl %eax, (0x1e0) +#ifndef STANDARD_MEMORY_BIOS_CALL + movb %al, (E820NR) +# Try three different memory detection schemes. First, try +# e820h, which lets us assemble a memory map, then try e801h, +# which returns a 32-bit memory size, and finally 88h, which +# returns 0-64m + +# method E820H: +# the memory map from hell. e820h returns memory classified into +# a whole bunch of different types, and allows memory holes and +# everything. We scan through this memory map and build a list +# of the first 32 memory areas, which we return at [E820MAP]. +# This is documented at http://www.acpi.info/, in the ACPI 2.0 specification. + +#define SMAP 0x534d4150 + +meme820: + xorl %ebx, %ebx # continuation counter + movw $E820MAP, %di # point into the whitelist + # so we can have the bios + # directly write into it. + +jmpe820: + movl $0x0000e820, %eax # e820, upper word zeroed + movl $SMAP, %edx # ascii 'SMAP' + movl $20, %ecx # size of the e820rec + pushw %ds # data record. + popw %es + int $0x15 # make the call + jc bail820 # fall to e801 if it fails + + cmpl $SMAP, %eax # check the return is `SMAP' + jne bail820 # fall to e801 if it fails + +# cmpl $1, 16(%di) # is this usable memory? +# jne again820 + + # If this is usable memory, we save it by simply advancing %di by + # sizeof(e820rec). + # +good820: + movb (E820NR), %al # up to 128 entries + cmpb $E820MAX, %al + jae bail820 + + incb (E820NR) + movw %di, %ax + addw $20, %ax + movw %ax, %di +again820: + cmpl $0, %ebx # check to see if + jne jmpe820 # %ebx is set to EOF +bail820: + + +# method E801H: +# memory size is in 1k chunksizes, to avoid confusing loadlin. +# we store the 0xe801 memory size in a completely different place, +# because it will most likely be longer than 16 bits. +# (use 1e0 because that's what Larry Augustine uses in his +# alternative new memory detection scheme, and it's sensible +# to write everything into the same place.) + +meme801: + stc # fix to work around buggy + xorw %cx,%cx # BIOSes which don't clear/set + xorw %dx,%dx # carry on pass/error of + # e801h memory size call + # or merely pass cx,dx though + # without changing them. + movw $0xe801, %ax + int $0x15 + jc mem88 + + cmpw $0x0, %cx # Kludge to handle BIOSes + jne e801usecxdx # which report their extended + cmpw $0x0, %dx # memory in AX/BX rather than + jne e801usecxdx # CX/DX. The spec I have read + movw %ax, %cx # seems to indicate AX/BX + movw %bx, %dx # are more reasonable anyway... + +e801usecxdx: + andl $0xffff, %edx # clear sign extend + shll $6, %edx # and go from 64k to 1k chunks + movl %edx, (0x1e0) # store extended memory size + andl $0xffff, %ecx # clear sign extend + addl %ecx, (0x1e0) # and add lower memory into + # total size. + +# Ye Olde Traditional Methode. Returns the memory size (up to 16mb or +# 64mb, depending on the bios) in ax. +mem88: + +#endif + movb $0x88, %ah + int $0x15 + movw %ax, (2) + +# Set the keyboard repeat rate to the max + movw $0x0305, %ax + xorw %bx, %bx + int $0x16 + +# Check for video adapter and its parameters and allow the +# user to browse video modes. + call video # NOTE: we need %ds pointing + # to bootsector + +# Get hd0 data... + xorw %ax, %ax + movw %ax, %ds + ldsw (4 * 0x41), %si + movw %cs, %ax # aka SETUPSEG + subw $DELTA_INITSEG, %ax # aka INITSEG + pushw %ax + movw %ax, %es + movw $0x0080, %di + movw $0x10, %cx + pushw %cx + cld + rep + movsb +# Get hd1 data... + xorw %ax, %ax + movw %ax, %ds + ldsw (4 * 0x46), %si + popw %cx + popw %es + movw $0x0090, %di + rep + movsb +# Check that there IS a hd1 :-) + movw $0x01500, %ax + movb $0x81, %dl + int $0x13 + jc no_disk1 + + cmpb $3, %ah + je is_disk1 + +no_disk1: + movw %cs, %ax # aka SETUPSEG + subw $DELTA_INITSEG, %ax # aka INITSEG + movw %ax, %es + movw $0x0090, %di + movw $0x10, %cx + xorw %ax, %ax + cld + rep + stosb +is_disk1: + +# Check for PS/2 pointing device + movw %cs, %ax # aka SETUPSEG + subw $DELTA_INITSEG, %ax # aka INITSEG + movw %ax, %ds + movb $0, (0x1ff) # default is no pointing device + int $0x11 # int 0x11: equipment list + testb $0x04, %al # check if mouse installed + jz no_psmouse + + movb $0xAA, (0x1ff) # device present +no_psmouse: + +# Now we want to move to protected mode ... + cmpw $0, %cs:realmode_swtch + jz rmodeswtch_normal + + lcall *%cs:realmode_swtch + + jmp rmodeswtch_end + +rmodeswtch_normal: + pushw %cs + call default_switch + +rmodeswtch_end: +# we get the code32 start address and modify the below 'jmpi' +# (loader may have changed it) + movl %cs:code32_start, %eax + movl %eax, %cs:code32 + +# Now we move the system to its rightful place ... but we check if we have a +# big-kernel. In that case we *must* not move it ... + testb $LOADED_HIGH, %cs:loadflags + jz do_move0 # .. then we have a normal low + # loaded zImage + # .. or else we have a high + # loaded bzImage + jmp end_move # ... and we skip moving + +do_move0: + movw $0x100, %ax # start of destination segment + movw %cs, %bp # aka SETUPSEG + subw $DELTA_INITSEG, %bp # aka INITSEG + movw %cs:start_sys_seg, %bx # start of source segment + cld +do_move: + movw %ax, %es # destination segment + incb %ah # instead of add ax,#0x100 + movw %bx, %ds # source segment + addw $0x100, %bx + subw %di, %di + subw %si, %si + movw $0x800, %cx + rep + movsw + cmpw %bp, %bx # assume start_sys_seg > 0x200, + # so we will perhaps read one + # page more than needed, but + # never overwrite INITSEG + # because destination is a + # minimum one page below source + jb do_move + +end_move: +# then we load the segment descriptors + movw %cs, %ax # aka SETUPSEG + movw %ax, %ds + +# Check whether we need to be downward compatible with version <=201 + cmpl $0, cmd_line_ptr + jne end_move_self # loader uses version >=202 features + cmpb $0x20, type_of_loader + je end_move_self # bootsect loader, we know of it + +# Boot loader doesnt support boot protocol version 2.02. +# If we have our code not at 0x90000, we need to move it there now. +# We also then need to move the params behind it (commandline) +# Because we would overwrite the code on the current IP, we move +# it in two steps, jumping high after the first one. + movw %cs, %ax + cmpw $SETUPSEG, %ax + je end_move_self + + cli # make sure we really have + # interrupts disabled ! + # because after this the stack + # should not be used + subw $DELTA_INITSEG, %ax # aka INITSEG + movw %ss, %dx + cmpw %ax, %dx + jb move_self_1 + + addw $INITSEG, %dx + subw %ax, %dx # this will go into %ss after + # the move +move_self_1: + movw %ax, %ds + movw $INITSEG, %ax # real INITSEG + movw %ax, %es + movw %cs:setup_move_size, %cx + std # we have to move up, so we use + # direction down because the + # areas may overlap + movw %cx, %di + decw %di + movw %di, %si + subw $move_self_here+0x200, %cx + rep + movsb + ljmp $SETUPSEG, $move_self_here + +move_self_here: + movw $move_self_here+0x200, %cx + rep + movsb + movw $SETUPSEG, %ax + movw %ax, %ds + movw %dx, %ss +end_move_self: # now we are at the right place + lidt idt_48 # load idt with 0,0 + xorl %eax, %eax # Compute gdt_base + movw %ds, %ax # (Convert %ds:gdt to a linear ptr) + shll $4, %eax + addl $gdt, %eax + movl %eax, (gdt_48+2) + lgdt gdt_48 # load gdt with whatever is + # appropriate + +# that was painless, now we enable a20 + call empty_8042 + + movb $0xD1, %al # command write + outb %al, $0x64 + call empty_8042 + + movb $0xDF, %al # A20 on + outb %al, $0x60 + call empty_8042 + +# +# You must preserve the other bits here. Otherwise embarrasing things +# like laptops powering off on boot happen. Corrected version by Kira +# Brown from Linux 2.2 +# + inb $0x92, %al # + orb $02, %al # "fast A20" version + outb %al, $0x92 # some chips have only this + +# wait until a20 really *is* enabled; it can take a fair amount of +# time on certain systems; Toshiba Tecras are known to have this +# problem. The memory location used here (0x200) is the int 0x80 +# vector, which should be safe to use. + + xorw %ax, %ax # segment 0x0000 + movw %ax, %fs + decw %ax # segment 0xffff (HMA) + movw %ax, %gs +a20_wait: + incw %ax # unused memory location <0xfff0 + movw %ax, %fs:(0x200) # we use the "int 0x80" vector + cmpw %gs:(0x210), %ax # and its corresponding HMA addr + je a20_wait # loop until no longer aliased + +# make sure any possible coprocessor is properly reset.. + xorw %ax, %ax + outb %al, $0xf0 + call delay + + outb %al, $0xf1 + call delay + +# well, that went ok, I hope. Now we mask all interrupts - the rest +# is done in init_IRQ(). + movb $0xFF, %al # mask all interrupts for now + outb %al, $0xA1 + call delay + + movb $0xFB, %al # mask all irq's but irq2 which + outb %al, $0x21 # is cascaded + +# Well, that certainly wasn't fun :-(. Hopefully it works, and we don't +# need no steenking BIOS anyway (except for the initial loading :-). +# The BIOS-routine wants lots of unnecessary data, and it's less +# "interesting" anyway. This is how REAL programmers do it. +# +# Well, now's the time to actually move into protected mode. To make +# things as simple as possible, we do no register set-up or anything, +# we let the gnu-compiled 32-bit programs do that. We just jump to +# absolute address 0x1000 (or the loader supplied one), +# in 32-bit protected mode. +# +# Note that the short jump isn't strictly needed, although there are +# reasons why it might be a good idea. It won't hurt in any case. + movw $1, %ax # protected mode (PE) bit + lmsw %ax # This is it! + jmp flush_instr + +flush_instr: + xorw %bx, %bx # Flag to indicate a boot + xorl %esi, %esi # Pointer to real-mode code + movw %cs, %si + subw $DELTA_INITSEG, %si + shll $4, %esi # Convert to 32-bit pointer +# NOTE: For high loaded big kernels we need a +# jmpi 0x100000,__KERNEL_CS +# +# but we yet haven't reloaded the CS register, so the default size +# of the target offset still is 16 bit. +# However, using an operand prefix (0x66), the CPU will properly +# take our 48 bit far pointer. (INTeL 80386 Programmer's Reference +# Manual, Mixing 16-bit and 32-bit code, page 16-6) + + .byte 0x66, 0xea # prefix + jmpi-opcode +code32: .long 0x1000 # will be set to 0x100000 + # for big kernels + .word __KERNEL_CS + +# Here's a bunch of information about your current kernel.. +kernel_version: .ascii UTS_RELEASE + .ascii " (" + .ascii LWK_COMPILE_BY + .ascii "@" + .ascii LWK_COMPILE_HOST + .ascii ") " + .ascii UTS_VERSION + .byte 0 + +# This is the default real mode switch routine. +# to be called just before protected mode transition +default_switch: + cli # no interrupts allowed ! + movb $0x80, %al # disable NMI for bootup + # sequence + outb %al, $0x70 + lret + + +# This routine checks that the keyboard command queue is empty +# (after emptying the output buffers) +# +# Some machines have delusions that the keyboard buffer is always full +# with no keyboard attached... +# +# If there is no keyboard controller, we will usually get 0xff +# to all the reads. With each IO taking a microsecond and +# a timeout of 100,000 iterations, this can take about half a +# second ("delay" == outb to port 0x80). That should be ok, +# and should also be plenty of time for a real keyboard controller +# to empty. +# + +empty_8042: + pushl %ecx + movl $100000, %ecx + +empty_8042_loop: + decl %ecx + jz empty_8042_end_loop + + call delay + + inb $0x64, %al # 8042 status port + testb $1, %al # output buffer? + jz no_output + + call delay + inb $0x60, %al # read it + jmp empty_8042_loop + +no_output: + testb $2, %al # is input buffer full? + jnz empty_8042_loop # yes - loop +empty_8042_end_loop: + popl %ecx + ret + +# Read the cmos clock. Return the seconds in al +gettime: + pushw %cx + movb $0x02, %ah + int $0x1a + movb %dh, %al # %dh contains the seconds + andb $0x0f, %al + movb %dh, %ah + movb $0x04, %cl + shrb %cl, %ah + aad + popw %cx + ret + +# Delay is needed after doing I/O +delay: + outb %al,$0x80 + ret + +# Descriptor tables +gdt: + .word 0, 0, 0, 0 # dummy + + .word 0, 0, 0, 0 # unused + + .word 0xFFFF # 4Gb - (0x100000*0x1000 = 4Gb) + .word 0 # base address = 0 + .word 0x9A00 # code read/exec + .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) +gdt_end: +idt_48: + .word 0 # idt limit = 0 + .word 0, 0 # idt base = 0L +gdt_48: + .word gdt_end-gdt-1 # gdt limit + .word 0, 0 # gdt base (filled in later) + +# Include video setup & detection code + +#include "video.S" + +# Setup signature -- must be last +setup_sig1: .word SIG1 +setup_sig2: .word SIG2 + +# After this point, there is some free space which is used by the video mode +# handling code to store the temporary mode table (not used by the kernel). + +modelist: + +.text +endtext: +.data +enddata: +.bss +endbss: