diff options
Diffstat (limited to 'arch/i386')
106 files changed, 1676 insertions, 4860 deletions
diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig index b1b2b30b1b8e..97b64d7d6bf6 100644 --- a/arch/i386/Kconfig +++ b/arch/i386/Kconfig @@ -18,6 +18,10 @@ config GENERIC_TIME bool default y +config GENERIC_CMOS_UPDATE + bool + default y + config CLOCKSOURCE_WATCHDOG bool default y @@ -222,6 +226,8 @@ config PARAVIRT However, when run without a hypervisor the kernel is theoretically slower. If in doubt, say N. +source "arch/i386/xen/Kconfig" + config VMI bool "VMI Paravirt-ops support" depends on PARAVIRT @@ -452,8 +458,7 @@ config MICROCODE tristate "/dev/cpu/microcode - Intel IA32 CPU microcode support" select FW_LOADER ---help--- - If you say Y here and also to "/dev file system support" in the - 'File systems' section, you will be able to update the microcode on + If you say Y here, you will be able to update the microcode on Intel processors in the IA32 family, e.g. Pentium Pro, Pentium II, Pentium III, Pentium 4, Xeon etc. You will obviously need the actual microcode binary data itself which is not shipped with the @@ -542,6 +547,7 @@ config HIGHMEM4G config HIGHMEM64G bool "64GB" depends on !M386 && !M486 + select X86_PAE help Select this if you have a 32-bit processor and more than 4 gigabytes of physical RAM. @@ -571,12 +577,12 @@ choice config VMSPLIT_3G bool "3G/1G user/kernel split" config VMSPLIT_3G_OPT - depends on !HIGHMEM + depends on !X86_PAE bool "3G/1G user/kernel split (for full 1G low memory)" config VMSPLIT_2G bool "2G/2G user/kernel split" config VMSPLIT_2G_OPT - depends on !HIGHMEM + depends on !X86_PAE bool "2G/2G user/kernel split (for full 2G low memory)" config VMSPLIT_1G bool "1G/3G user/kernel split" @@ -596,17 +602,26 @@ config HIGHMEM default y config X86_PAE - bool - depends on HIGHMEM64G - default y + bool "PAE (Physical Address Extension) Support" + default n + depends on !HIGHMEM4G select RESOURCES_64BIT + help + PAE is required for NX support, and furthermore enables + larger swapspace support for non-overcommit purposes. It + has the cost of more pagetable lookup overhead, and also + consumes more pagetable space per process. # Common NUMA Features config NUMA - bool "Numa Memory Allocation and Scheduler Support" - depends on SMP && HIGHMEM64G && (X86_NUMAQ || (X86_SUMMIT || X86_GENERICARCH) && ACPI) + bool "Numa Memory Allocation and Scheduler Support (EXPERIMENTAL)" + depends on SMP && HIGHMEM64G && (X86_NUMAQ || (X86_SUMMIT || X86_GENERICARCH) && ACPI) && EXPERIMENTAL default n if X86_PC default y if (X86_NUMAQ || X86_SUMMIT) + help + NUMA support for i386. This is currently high experimental + and should be only used for kernel development. It might also + cause boot failures. comment "NUMA (Summit) requires SMP, 64GB highmem support, ACPI" depends on X86_SUMMIT && (!HIGHMEM64G || !ACPI) @@ -815,6 +830,7 @@ config CRASH_DUMP config PHYSICAL_START hex "Physical address where the kernel is loaded" if (EMBEDDED || CRASH_DUMP) + default "0x1000000" if X86_NUMAQ default "0x100000" help This gives the physical address where the kernel is loaded. @@ -925,7 +941,7 @@ source "drivers/acpi/Kconfig" menuconfig APM tristate "APM (Advanced Power Management) BIOS support" - depends on PM && !X86_VISWS + depends on PM_SLEEP && !X86_VISWS ---help--- APM is a BIOS specification for saving power using several different techniques. This is mostly useful for battery powered laptops with @@ -1212,21 +1228,31 @@ source "drivers/Kconfig" source "fs/Kconfig" -menu "Instrumentation Support" +menuconfig INSTRUMENTATION + bool "Instrumentation Support" depends on EXPERIMENTAL + default y + ---help--- + Say Y here to get to see options related to performance measurement, + debugging, and testing. This option alone does not add any kernel code. + + If you say N, all options in this submenu will be skipped and disabled. + +if INSTRUMENTATION source "arch/i386/oprofile/Kconfig" config KPROBES - bool "Kprobes (EXPERIMENTAL)" - depends on KALLSYMS && EXPERIMENTAL && MODULES + bool "Kprobes" + depends on KALLSYMS && MODULES help Kprobes allows you to trap at almost any kernel address and execute a callback function. register_kprobe() establishes a probepoint and specifies the callback. Kprobes is useful for kernel debugging, non-intrusive instrumentation and testing. If in doubt, say "N". -endmenu + +endif # INSTRUMENTATION source "arch/i386/Kconfig.debug" diff --git a/arch/i386/Kconfig.cpu b/arch/i386/Kconfig.cpu index 5c95ceb7f122..11a24d54f27b 100644 --- a/arch/i386/Kconfig.cpu +++ b/arch/i386/Kconfig.cpu @@ -297,11 +297,6 @@ config X86_POPAD_OK depends on !M386 default y -config X86_CMPXCHG64 - bool - depends on X86_PAE - default y - config X86_ALIGNMENT_16 bool depends on MWINCHIP3D || MWINCHIP2 || MWINCHIPC6 || MCYRIXIII || X86_ELAN || MK6 || M586MMX || M586TSC || M586 || M486 || MVIAC3_2 || MGEODEGX1 @@ -344,8 +339,8 @@ config X86_CMOV depends on (MK7 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7) default y -config X86_MINIMUM_CPU_MODEL +config X86_MINIMUM_CPU_FAMILY int - default "4" if X86_XADD || X86_CMPXCHG || X86_BSWAP - default "0" + default "4" if X86_XADD || X86_CMPXCHG || X86_BSWAP || X86_WP_WORKS_OK + default "3" diff --git a/arch/i386/Kconfig.debug b/arch/i386/Kconfig.debug index b31c0802e1cc..f03531eacdfb 100644 --- a/arch/i386/Kconfig.debug +++ b/arch/i386/Kconfig.debug @@ -36,11 +36,11 @@ config DEBUG_STACK_USAGE This option will slow down process creation somewhat. comment "Page alloc debug is incompatible with Software Suspend on i386" - depends on DEBUG_KERNEL && SOFTWARE_SUSPEND + depends on DEBUG_KERNEL && HIBERNATION config DEBUG_PAGEALLOC bool "Debug page memory allocations" - depends on DEBUG_KERNEL && !SOFTWARE_SUSPEND && !HUGETLBFS + depends on DEBUG_KERNEL && !HIBERNATION && !HUGETLBFS help Unmap pages from the kernel linear mapping after free_pages(). This results in a large slowdown, but helps to find certain types diff --git a/arch/i386/Makefile b/arch/i386/Makefile index 541b3aeb5723..52b932478c6d 100644 --- a/arch/i386/Makefile +++ b/arch/i386/Makefile @@ -93,6 +93,9 @@ mflags-$(CONFIG_X86_ES7000) := -Iinclude/asm-i386/mach-es7000 mcore-$(CONFIG_X86_ES7000) := mach-default core-$(CONFIG_X86_ES7000) := arch/i386/mach-es7000/ +# Xen paravirtualization support +core-$(CONFIG_XEN) += arch/i386/xen/ + # default subarch .h files mflags-y += -Iinclude/asm-i386/mach-default @@ -108,6 +111,7 @@ drivers-$(CONFIG_PCI) += arch/i386/pci/ # must be linked after kernel/ drivers-$(CONFIG_OPROFILE) += arch/i386/oprofile/ drivers-$(CONFIG_PM) += arch/i386/power/ +drivers-$(CONFIG_FB) += arch/i386/video/ CFLAGS += $(mflags-y) AFLAGS += $(mflags-y) diff --git a/arch/i386/boot/.gitignore b/arch/i386/boot/.gitignore index 495f20c085de..18465143cfa2 100644 --- a/arch/i386/boot/.gitignore +++ b/arch/i386/boot/.gitignore @@ -1,3 +1,5 @@ bootsect bzImage setup +setup.bin +setup.elf diff --git a/arch/i386/boot/Makefile b/arch/i386/boot/Makefile index bfbc32098a4a..93386a4e40b4 100644 --- a/arch/i386/boot/Makefile +++ b/arch/i386/boot/Makefile @@ -25,27 +25,56 @@ SVGA_MODE := -DSVGA_MODE=NORMAL_VGA #RAMDISK := -DRAMDISK=512 -targets := vmlinux.bin bootsect bootsect.o \ - setup setup.o zImage bzImage +targets := vmlinux.bin setup.bin setup.elf zImage bzImage subdir- := compressed +setup-y += a20.o apm.o cmdline.o copy.o cpu.o cpucheck.o edd.o +setup-y += header.o main.o mca.o memory.o pm.o pmjump.o +setup-y += printf.o string.o tty.o video.o version.o voyager.o + +# The link order of the video-*.o modules can matter. In particular, +# video-vga.o *must* be listed first, followed by video-vesa.o. +# Hardware-specific drivers should follow in the order they should be +# probed, and video-bios.o should typically be last. +setup-y += video-vga.o +setup-y += video-vesa.o +setup-y += video-bios.o +targets += $(setup-y) hostprogs-y := tools/build HOSTCFLAGS_build.o := $(LINUXINCLUDE) # --------------------------------------------------------------------------- +# How to compile the 16-bit code. Note we always compile for -march=i386, +# that way we can complain to the user if the CPU is insufficient. +cflags-i386 := +cflags-x86_64 := -m32 +CFLAGS := $(LINUXINCLUDE) -g -Os -D_SETUP -D__KERNEL__ \ + $(cflags-$(ARCH)) \ + -Wall -Wstrict-prototypes \ + -march=i386 -mregparm=3 \ + -include $(srctree)/$(src)/code16gcc.h \ + -fno-strict-aliasing -fomit-frame-pointer \ + $(call cc-option, -ffreestanding) \ + $(call cc-option, -fno-toplevel-reorder,\ + $(call cc-option, -fno-unit-at-a-time)) \ + $(call cc-option, -fno-stack-protector) \ + $(call cc-option, -mpreferred-stack-boundary=2) +AFLAGS := $(CFLAGS) -D__ASSEMBLY__ + $(obj)/zImage: IMAGE_OFFSET := 0x1000 $(obj)/zImage: EXTRA_AFLAGS := $(SVGA_MODE) $(RAMDISK) $(obj)/bzImage: IMAGE_OFFSET := 0x100000 +$(obj)/bzImage: EXTRA_CFLAGS := -D__BIG_KERNEL__ $(obj)/bzImage: EXTRA_AFLAGS := $(SVGA_MODE) $(RAMDISK) -D__BIG_KERNEL__ $(obj)/bzImage: BUILDFLAGS := -b quiet_cmd_image = BUILD $@ -cmd_image = $(obj)/tools/build $(BUILDFLAGS) $(obj)/bootsect $(obj)/setup \ +cmd_image = $(obj)/tools/build $(BUILDFLAGS) $(obj)/setup.bin \ $(obj)/vmlinux.bin $(ROOT_DEV) > $@ -$(obj)/zImage $(obj)/bzImage: $(obj)/bootsect $(obj)/setup \ +$(obj)/zImage $(obj)/bzImage: $(obj)/setup.bin \ $(obj)/vmlinux.bin $(obj)/tools/build FORCE $(call if_changed,image) @echo 'Kernel: $@ is ready' ' (#'`cat .version`')' @@ -53,12 +82,17 @@ $(obj)/zImage $(obj)/bzImage: $(obj)/bootsect $(obj)/setup \ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE $(call if_changed,objcopy) -LDFLAGS_bootsect := -Ttext 0x0 -s --oformat binary -LDFLAGS_setup := -Ttext 0x0 -s --oformat binary -e begtext +SETUP_OBJS = $(addprefix $(obj)/,$(setup-y)) -$(obj)/setup $(obj)/bootsect: %: %.o FORCE +LDFLAGS_setup.elf := -T +$(obj)/setup.elf: $(src)/setup.ld $(SETUP_OBJS) FORCE $(call if_changed,ld) +OBJCOPYFLAGS_setup.bin := -O binary + +$(obj)/setup.bin: $(obj)/setup.elf FORCE + $(call if_changed,objcopy) + $(obj)/compressed/vmlinux: FORCE $(Q)$(MAKE) $(build)=$(obj)/compressed IMAGE_OFFSET=$(IMAGE_OFFSET) $@ diff --git a/arch/i386/boot/bootsect.S b/arch/i386/boot/bootsect.S deleted file mode 100644 index 011b7a4993d4..000000000000 --- a/arch/i386/boot/bootsect.S +++ /dev/null @@ -1,98 +0,0 @@ -/* - * bootsect.S Copyright (C) 1991, 1992 Linus Torvalds - * - * modified by Drew Eckhardt - * modified by Bruce Evans (bde) - * modified by Chris Noe (May 1999) (as86 -> gas) - * gutted by H. Peter Anvin (Jan 2003) - * - * BIG FAT NOTE: We're in real mode using 64k segments. Therefore segment - * addresses must be multiplied by 16 to obtain their respective linear - * addresses. To avoid confusion, linear addresses are written using leading - * hex while segment addresses are written as segment:offset. - * - */ - -#include <asm/boot.h> - -SETUPSECTS = 4 /* default nr of setup-sectors */ -BOOTSEG = 0x07C0 /* original address of boot-sector */ -INITSEG = DEF_INITSEG /* we move boot here - out of the way */ -SETUPSEG = DEF_SETUPSEG /* setup starts here */ -SYSSEG = DEF_SYSSEG /* system loaded at 0x10000 (65536) */ -SYSSIZE = DEF_SYSSIZE /* system size: # of 16-byte clicks */ - /* to be loaded */ -ROOT_DEV = 0 /* ROOT_DEV is now written by "build" */ -SWAP_DEV = 0 /* SWAP_DEV is now written by "build" */ - -#ifndef SVGA_MODE -#define SVGA_MODE ASK_VGA -#endif - -#ifndef RAMDISK -#define RAMDISK 0 -#endif - -#ifndef ROOT_RDONLY -#define ROOT_RDONLY 1 -#endif - -.code16 -.text - -.global _start -_start: - - # Normalize the start address - jmpl $BOOTSEG, $start2 - -start2: - movw %cs, %ax - movw %ax, %ds - movw %ax, %es - movw %ax, %ss - movw $0x7c00, %sp - sti - cld - - movw $bugger_off_msg, %si - -msg_loop: - lodsb - andb %al, %al - jz die - movb $0xe, %ah - movw $7, %bx - int $0x10 - jmp msg_loop - -die: - # Allow the user to press a key, then reboot - xorw %ax, %ax - int $0x16 - int $0x19 - - # int 0x19 should never return. In case it does anyway, - # invoke the BIOS reset code... - ljmp $0xf000,$0xfff0 - - -bugger_off_msg: - .ascii "Direct booting from floppy is no longer supported.\r\n" - .ascii "Please use a boot loader program instead.\r\n" - .ascii "\n" - .ascii "Remove disk and press any key to reboot . . .\r\n" - .byte 0 - - - # Kernel attributes; used by setup - - .org 497 -setup_sects: .byte SETUPSECTS -root_flags: .word ROOT_RDONLY -syssize: .word SYSSIZE -swap_dev: .word SWAP_DEV -ram_size: .word RAMDISK -vid_mode: .word SVGA_MODE -root_dev: .word ROOT_DEV -boot_flag: .word 0xAA55 diff --git a/arch/i386/boot/compressed/Makefile b/arch/i386/boot/compressed/Makefile index a661217f33ec..189fa1dbefcc 100644 --- a/arch/i386/boot/compressed/Makefile +++ b/arch/i386/boot/compressed/Makefile @@ -9,9 +9,14 @@ targets := vmlinux vmlinux.bin vmlinux.bin.gz head.o misc.o piggy.o \ EXTRA_AFLAGS := -traditional LDFLAGS_vmlinux := -T -CFLAGS_misc.o += -fPIC hostprogs-y := relocs +CFLAGS := -m32 -D__KERNEL__ $(LINUX_INCLUDE) -O2 \ + -fno-strict-aliasing -fPIC \ + $(call cc-option,-ffreestanding) \ + $(call cc-option,-fno-stack-protector) +LDFLAGS := -m elf_i386 + $(obj)/vmlinux: $(src)/vmlinux.lds $(obj)/head.o $(obj)/misc.o $(obj)/piggy.o FORCE $(call if_changed,ld) @: diff --git a/arch/i386/boot/compressed/head.S b/arch/i386/boot/compressed/head.S index 3517a32aaf41..f35ea2237522 100644 --- a/arch/i386/boot/compressed/head.S +++ b/arch/i386/boot/compressed/head.S @@ -45,10 +45,10 @@ startup_32: * at and where we were actually loaded at. This can only be done * with a short local call on x86. Nothing else will tell us what * address we are running at. The reserved chunk of the real-mode - * data at 0x34-0x3f are used as the stack for this calculation. - * Only 4 bytes are needed. + * data at 0x1e4 (defined as a scratch field) are used as the stack + * for this calculation. Only 4 bytes are needed. */ - leal 0x40(%esi), %esp + leal (0x1e4+4)(%esi), %esp call 1f 1: popl %ebp subl $1b, %ebp diff --git a/arch/i386/boot/compressed/relocs.c b/arch/i386/boot/compressed/relocs.c index ce4fda261aaf..2d77ee728f92 100644 --- a/arch/i386/boot/compressed/relocs.c +++ b/arch/i386/boot/compressed/relocs.c @@ -31,6 +31,9 @@ static const char* safe_abs_relocs[] = { "__kernel_rt_sigreturn", "__kernel_sigreturn", "SYSENTER_RETURN", + "VDSO_NOTE_MASK", + "xen_irq_disable_direct_reloc", + "xen_save_fl_direct_reloc", }; static int is_safe_abs_reloc(const char* sym_name) diff --git a/arch/i386/boot/edd.S b/arch/i386/boot/edd.S deleted file mode 100644 index 34321368011a..000000000000 --- a/arch/i386/boot/edd.S +++ /dev/null @@ -1,231 +0,0 @@ -/* - * BIOS Enhanced Disk Drive support - * Copyright (C) 2002, 2003, 2004 Dell, Inc. - * by Matt Domsch <Matt_Domsch@dell.com> October 2002 - * conformant to T13 Committee www.t13.org - * projects 1572D, 1484D, 1386D, 1226DT - * disk signature read by Matt Domsch <Matt_Domsch@dell.com> - * and Andrew Wilks <Andrew_Wilks@dell.com> September 2003, June 2004 - * legacy CHS retrieval by Patrick J. LoPresti <patl@users.sourceforge.net> - * March 2004 - * Command line option parsing, Matt Domsch, November 2004 - */ - -#include <linux/edd.h> -#include <asm/setup.h> - -#if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE) - -# It is assumed that %ds == INITSEG here - - movb $0, (EDD_MBR_SIG_NR_BUF) - movb $0, (EDDNR) - -# Check the command line for options: -# edd=of disables EDD completely (edd=off) -# edd=sk skips the MBR test (edd=skipmbr) -# edd=on re-enables EDD (edd=on) - - pushl %esi - movw $edd_mbr_sig_start, %di # Default to edd=on - - movl %cs:(cmd_line_ptr), %esi - andl %esi, %esi - jz old_cl # Old boot protocol? - -# Convert to a real-mode pointer in fs:si - movl %esi, %eax - shrl $4, %eax - movw %ax, %fs - andw $0xf, %si - jmp have_cl_pointer - -# Old-style boot protocol? -old_cl: - push %ds # aka INITSEG - pop %fs - - cmpw $0xa33f, (0x20) - jne done_cl # No command line at all? - movw (0x22), %si # Pointer relative to INITSEG - -# fs:si has the pointer to the command line now -have_cl_pointer: - -# Loop through kernel command line one byte at a time. Just in -# case the loader is buggy and failed to null-terminate the command line -# terminate if we get close enough to the end of the segment that we -# cannot fit "edd=XX"... -cl_atspace: - cmpw $-5, %si # Watch for segment wraparound - jae done_cl - movl %fs:(%si), %eax - andb %al, %al # End of line? - jz done_cl - cmpl $EDD_CL_EQUALS, %eax - jz found_edd_equals - cmpb $0x20, %al # <= space consider whitespace - ja cl_skipword - incw %si - jmp cl_atspace - -cl_skipword: - cmpw $-5, %si # Watch for segment wraparound - jae done_cl - movb %fs:(%si), %al # End of string? - andb %al, %al - jz done_cl - cmpb $0x20, %al - jbe cl_atspace - incw %si - jmp cl_skipword - -found_edd_equals: -# only looking at first two characters after equals -# late overrides early on the command line, so keep going after finding something - movw %fs:4(%si), %ax - cmpw $EDD_CL_OFF, %ax # edd=of - je do_edd_off - cmpw $EDD_CL_SKIP, %ax # edd=sk - je do_edd_skipmbr - cmpw $EDD_CL_ON, %ax # edd=on - je do_edd_on - jmp cl_skipword -do_edd_skipmbr: - movw $edd_start, %di - jmp cl_skipword -do_edd_off: - movw $edd_done, %di - jmp cl_skipword -do_edd_on: - movw $edd_mbr_sig_start, %di - jmp cl_skipword - -done_cl: - popl %esi - jmpw *%di - -# Read the first sector of each BIOS disk device and store the 4-byte signature -edd_mbr_sig_start: - movb $0x80, %dl # from device 80 - movw $EDD_MBR_SIG_BUF, %bx # store buffer ptr in bx -edd_mbr_sig_read: - movl $0xFFFFFFFF, %eax - movl %eax, (%bx) # assume failure - pushw %bx - movb $READ_SECTORS, %ah - movb $1, %al # read 1 sector - movb $0, %dh # at head 0 - movw $1, %cx # cylinder 0, sector 0 - pushw %es - pushw %ds - popw %es - movw $EDDBUF, %bx # disk's data goes into EDDBUF - pushw %dx # work around buggy BIOSes - stc # work around buggy BIOSes - int $0x13 - sti # work around buggy BIOSes - popw %dx - popw %es - popw %bx - jc edd_mbr_sig_done # on failure, we're done. - cmpb $0, %ah # some BIOSes do not set CF - jne edd_mbr_sig_done # on failure, we're done. - movl (EDDBUF+EDD_MBR_SIG_OFFSET), %eax # read sig out of the MBR - movl %eax, (%bx) # store success - incb (EDD_MBR_SIG_NR_BUF) # note that we stored something - incb %dl # increment to next device - addw $4, %bx # increment sig buffer ptr - cmpb $EDD_MBR_SIG_MAX, (EDD_MBR_SIG_NR_BUF) # Out of space? - jb edd_mbr_sig_read # keep looping -edd_mbr_sig_done: - -# Do the BIOS Enhanced Disk Drive calls -# This consists of two calls: -# int 13h ah=41h "Check Extensions Present" -# int 13h ah=48h "Get Device Parameters" -# int 13h ah=08h "Legacy Get Device Parameters" -# -# A buffer of size EDDMAXNR*(EDDEXTSIZE+EDDPARMSIZE) is reserved for our use -# in the boot_params at EDDBUF. The first four bytes of which are -# used to store the device number, interface support map and version -# results from fn41. The next four bytes are used to store the legacy -# cylinders, heads, and sectors from fn08. The following 74 bytes are used to -# store the results from fn48. Starting from device 80h, fn41, then fn48 -# are called and their results stored in EDDBUF+n*(EDDEXTSIZE+EDDPARMIZE). -# Then the pointer is incremented to store the data for the next call. -# This repeats until either a device doesn't exist, or until EDDMAXNR -# devices have been stored. -# The one tricky part is that ds:si always points EDDEXTSIZE bytes into -# the structure, and the fn41 and fn08 results are stored at offsets -# from there. This removes the need to increment the pointer for -# every store, and leaves it ready for the fn48 call. -# A second one-byte buffer, EDDNR, in the boot_params stores -# the number of BIOS devices which exist, up to EDDMAXNR. -# In setup.c, copy_edd() stores both boot_params buffers away -# for later use, as they would get overwritten otherwise. -# This code is sensitive to the size of the structs in edd.h -edd_start: - # %ds points to the bootsector - # result buffer for fn48 - movw $EDDBUF+EDDEXTSIZE, %si # in ds:si, fn41 results - # kept just before that - movb $0x80, %dl # BIOS device 0x80 - -edd_check_ext: - movb $CHECKEXTENSIONSPRESENT, %ah # Function 41 - movw $EDDMAGIC1, %bx # magic - int $0x13 # make the call - jc edd_done # no more BIOS devices - - cmpw $EDDMAGIC2, %bx # is magic right? - jne edd_next # nope, next... - - movb %dl, %ds:-8(%si) # store device number - movb %ah, %ds:-7(%si) # store version - movw %cx, %ds:-6(%si) # store extensions - incb (EDDNR) # note that we stored something - -edd_get_device_params: - movw $EDDPARMSIZE, %ds:(%si) # put size - movw $0x0, %ds:2(%si) # work around buggy BIOSes - movb $GETDEVICEPARAMETERS, %ah # Function 48 - int $0x13 # make the call - # Don't check for fail return - # it doesn't matter. -edd_get_legacy_chs: - xorw %ax, %ax - movw %ax, %ds:-4(%si) - movw %ax, %ds:-2(%si) - # Ralf Brown's Interrupt List says to set ES:DI to - # 0000h:0000h "to guard against BIOS bugs" - pushw %es - movw %ax, %es - movw %ax, %di - pushw %dx # legacy call clobbers %dl - movb $LEGACYGETDEVICEPARAMETERS, %ah # Function 08 - int $0x13 # make the call - jc edd_legacy_done # failed - movb %cl, %al # Low 6 bits are max - andb $0x3F, %al # sector number - movb %al, %ds:-1(%si) # Record max sect - movb %dh, %ds:-2(%si) # Record max head number - movb %ch, %al # Low 8 bits of max cyl - shr $6, %cl - movb %cl, %ah # High 2 bits of max cyl - movw %ax, %ds:-4(%si) - -edd_legacy_done: - popw %dx - popw %es - movw %si, %ax # increment si - addw $EDDPARMSIZE+EDDEXTSIZE, %ax - movw %ax, %si - -edd_next: - incb %dl # increment to next device - cmpb $EDDMAXNR, (EDDNR) # Out of space? - jb edd_check_ext # keep looping - -edd_done: -#endif diff --git a/arch/i386/boot/install.sh b/arch/i386/boot/install.sh index 5e44c736eea8..88d77761d01b 100644 --- a/arch/i386/boot/install.sh +++ b/arch/i386/boot/install.sh @@ -51,4 +51,11 @@ fi cat $2 > $4/vmlinuz cp $3 $4/System.map -if [ -x /sbin/lilo ]; then /sbin/lilo; else /etc/lilo/install; fi +if [ -x /sbin/lilo ]; then + /sbin/lilo +elif [ -x /etc/lilo/install ]; then + /etc/lilo/install +else + sync + echo "Cannot find LILO." +fi diff --git a/arch/i386/boot/setup.S b/arch/i386/boot/setup.S deleted file mode 100644 index 6dbcc95b2120..000000000000 --- a/arch/i386/boot/setup.S +++ /dev/null @@ -1,1075 +0,0 @@ -/* - * 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 - * <lermen@elserv.ffm.fgan.de>, <almesber@lrc.epfl.ch> - * - * Video handling moved to video.S by Martin Mares, March 1996 - * <mj@k332.feld.cvut.cz> - * - * 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. - * <stiker@northlink.com> - * - * 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 <michaelm@mjmm.org> - * - * New A20 code ported from SYSLINUX by H. Peter Anvin. AMD Elan bugfixes - * by Robert Schwebel, December 2001 <robert@schwebel.de> - */ - -#include <asm/segment.h> -#include <linux/utsrelease.h> -#include <linux/compile.h> -#include <asm/boot.h> -#include <asm/e820.h> -#include <asm/page.h> -#include <asm/setup.h> - -/* 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 (-__PAGE_OFFSET-(512 << 20)-1) & 0x7fffffff - # (Header version 0x0203 or later) - # The highest safe address for - # the contents of an initrd - -kernel_alignment: .long CONFIG_PHYSICAL_ALIGN #physical addr alignment - #required for protected mode - #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) - -# Part of above routine, this one just prints ascii al -prtchr: pushw %ax - pushw %cx - movw $7,%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 - pushw %cs - popw %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: - hlt - 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..." - -# check minimum cpuid -# we do this here because it is the last place we can actually -# show a user visible error message. Later the video modus -# might be already messed up. -loader_ok: - call verify_cpu - testl %eax,%eax - jz cpu_ok - movw %cs,%ax # aka SETUPSEG - movw %ax,%ds - lea cpu_panic_mess,%si - call prtstr -1: jmp 1b - -cpu_panic_mess: - .asciz "PANIC: CPU too old for this kernel." - -#include "../kernel/verify_cpu.S" - -cpu_ok: -# 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 Micro Channel (MCA) bus - movw %cs, %ax # aka SETUPSEG - subw $DELTA_INITSEG, %ax # aka INITSEG - movw %ax, %ds - xorw %ax, %ax - movw %ax, (0xa0) # set table length to 0 - movb $0xc0, %ah - stc - int $0x15 # moves feature table to es:bx - jc no_mca - - pushw %ds - movw %es, %ax - movw %ax, %ds - movw %cs, %ax # aka SETUPSEG - subw $DELTA_INITSEG, %ax # aka INITSEG - movw %ax, %es - movw %bx, %si - movw $0xa0, %di - movw (%si), %cx - addw $2, %cx # table length is a short - cmpw $0x10, %cx - jc sysdesc_ok - - movw $0x10, %cx # we keep only first 16 bytes -sysdesc_ok: - rep - movsb - popw %ds -no_mca: -#ifdef CONFIG_X86_VOYAGER - movb $0xff, 0x40 # flag on config found - movb $0xc0, %al - mov $0xff, %ah - int $0x15 # put voyager config info at es:di - jc no_voyager - movw $0x40, %si # place voyager info in apm table - cld - movw $7, %cx -voyager_rep: - movb %es:(%di), %al - movb %al,(%si) - incw %di - incw %si - decw %cx - jnz voyager_rep -no_voyager: -#endif -# 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: - -#if defined(CONFIG_X86_SPEEDSTEP_SMI) || defined(CONFIG_X86_SPEEDSTEP_SMI_MODULE) - movl $0x0000E980, %eax # IST Support - movl $0x47534943, %edx # Request value - int $0x15 - - movl %eax, (96) - movl %ebx, (100) - movl %ecx, (104) - movl %edx, (108) -#endif - -#if defined(CONFIG_APM) || defined(CONFIG_APM_MODULE) -# Then check for an APM BIOS... - # %ds points to the bootsector - movw $0, 0x40 # version = 0 means no APM BIOS - movw $0x05300, %ax # APM BIOS installation check - xorw %bx, %bx - int $0x15 - jc done_apm_bios # Nope, no APM BIOS - - cmpw $0x0504d, %bx # Check for "PM" signature - jne done_apm_bios # No signature, no APM BIOS - - andw $0x02, %cx # Is 32 bit supported? - je done_apm_bios # No 32-bit, no (good) APM BIOS - - movw $0x05304, %ax # Disconnect first just in case - xorw %bx, %bx - int $0x15 # ignore return code - movw $0x05303, %ax # 32 bit connect - xorl %ebx, %ebx - xorw %cx, %cx # paranoia :-) - xorw %dx, %dx # ... - xorl %esi, %esi # ... - xorw %di, %di # ... - int $0x15 - jc no_32_apm_bios # Ack, error. - - movw %ax, (66) # BIOS code segment - movl %ebx, (68) # BIOS entry point offset - movw %cx, (72) # BIOS 16 bit code segment - movw %dx, (74) # BIOS data segment - movl %esi, (78) # BIOS code segment lengths - movw %di, (82) # BIOS data segment length -# Redo the installation check as the 32 bit connect -# modifies the flags returned on some BIOSs - movw $0x05300, %ax # APM BIOS installation check - xorw %bx, %bx - xorw %cx, %cx # paranoia - int $0x15 - jc apm_disconnect # error -> shouldn't happen - - cmpw $0x0504d, %bx # check for "PM" signature - jne apm_disconnect # no sig -> shouldn't happen - - movw %ax, (64) # record the APM BIOS version - movw %cx, (76) # and flags - jmp done_apm_bios - -apm_disconnect: # Tidy up - movw $0x05304, %ax # Disconnect - xorw %bx, %bx - int $0x15 # ignore return code - - jmp done_apm_bios - -no_32_apm_bios: - andw $0xfffd, (76) # remove 32 bit support bit -done_apm_bios: -#endif - -#include "edd.S" - -# 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: -# 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 - -# -# Enable A20. This is at the very best an annoying procedure. -# A20 code ported from SYSLINUX 1.52-1.63 by H. Peter Anvin. -# AMD Elan bug fix by Robert Schwebel. -# - -#if defined(CONFIG_X86_ELAN) - movb $0x02, %al # alternate A20 gate - outb %al, $0x92 # this works on SC410/SC520 -a20_elan_wait: - call a20_test - jz a20_elan_wait - jmp a20_done -#endif - - -A20_TEST_LOOPS = 32 # Iterations per wait -A20_ENABLE_LOOPS = 255 # Total loops to try - - -#ifndef CONFIG_X86_VOYAGER -a20_try_loop: - - # First, see if we are on a system with no A20 gate. -a20_none: - call a20_test - jnz a20_done - - # Next, try the BIOS (INT 0x15, AX=0x2401) -a20_bios: - movw $0x2401, %ax - pushfl # Be paranoid about flags - int $0x15 - popfl - - call a20_test - jnz a20_done - - # Try enabling A20 through the keyboard controller -#endif /* CONFIG_X86_VOYAGER */ -a20_kbc: - call empty_8042 - -#ifndef CONFIG_X86_VOYAGER - call a20_test # Just in case the BIOS worked - jnz a20_done # but had a delayed reaction. -#endif - - movb $0xD1, %al # command write - outb %al, $0x64 - call empty_8042 - - movb $0xDF, %al # A20 on - outb %al, $0x60 - call empty_8042 - -#ifndef CONFIG_X86_VOYAGER - # 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. -a20_kbc_wait: - xorw %cx, %cx -a20_kbc_wait_loop: - call a20_test - jnz a20_done - loop a20_kbc_wait_loop - - # Final attempt: use "configuration port A" -a20_fast: - inb $0x92, %al # Configuration Port A - orb $0x02, %al # "fast A20" version - andb $0xFE, %al # don't accidentally reset - outb %al, $0x92 - - # Wait for configuration port A to take effect -a20_fast_wait: - xorw %cx, %cx -a20_fast_wait_loop: - call a20_test - jnz a20_done - loop a20_fast_wait_loop - - # A20 is still not responding. Try frobbing it again. - # - decb (a20_tries) - jnz a20_try_loop - - movw $a20_err_msg, %si - call prtstr - -a20_die: - hlt - jmp a20_die - -a20_tries: - .byte A20_ENABLE_LOOPS - -a20_err_msg: - .ascii "linux: fatal error: A20 gate not responding!" - .byte 13, 10, 0 - - # If we get here, all is good -a20_done: - -#endif /* CONFIG_X86_VOYAGER */ -# set up gdt and idt and 32bit start address - 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 %eax, code32 - addl $gdt, %eax - movl %eax, (gdt_48+2) - lgdt gdt_48 # load gdt with whatever is - # appropriate - -# 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 - -# jump to startup_32 in arch/i386/boot/compressed/head.S -# -# NOTE: For high loaded big kernels we need a -# jmpi 0x100000,__BOOT_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 startup_32 # will be set to %cs+startup_32 - .word __BOOT_CS -.code32 -startup_32: - movl $(__BOOT_DS), %eax - movl %eax, %ds - movl %eax, %es - movl %eax, %fs - movl %eax, %gs - movl %eax, %ss - - xorl %eax, %eax -1: incl %eax # check that A20 really IS enabled - movl %eax, 0x00000000 # loop forever if it isn't - cmpl %eax, 0x00100000 - je 1b - - # Jump to the 32bit entry point - jmpl *(code32_start - start + (DELTA_INITSEG << 4))(%esi) -.code16 - -# Here's a bunch of information about your current kernel.. -kernel_version: .ascii UTS_RELEASE - .ascii " (" - .ascii LINUX_COMPILE_BY - .ascii "@" - .ascii LINUX_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 - - -#ifndef CONFIG_X86_VOYAGER -# This routine tests whether or not A20 is enabled. If so, it -# exits with zf = 0. -# -# The memory address used, 0x200, is the int $0x80 vector, which -# should be safe. - -A20_TEST_ADDR = 4*0x80 - -a20_test: - pushw %cx - pushw %ax - xorw %cx, %cx - movw %cx, %fs # Low memory - decw %cx - movw %cx, %gs # High memory area - movw $A20_TEST_LOOPS, %cx - movw %fs:(A20_TEST_ADDR), %ax - pushw %ax -a20_test_wait: - incw %ax - movw %ax, %fs:(A20_TEST_ADDR) - call delay # Serialize and make delay constant - cmpw %gs:(A20_TEST_ADDR+0x10), %ax - loope a20_test_wait - - popw %fs:(A20_TEST_ADDR) - popw %ax - popw %cx - ret - -#endif /* CONFIG_X86_VOYAGER */ - -# 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 -# -# NOTE: The intel manual says gdt should be sixteen bytes aligned for -# efficiency reasons. However, there are machines which are known not -# to boot with misaligned GDTs, so alter this at your peril! If you alter -# GDT_ENTRY_BOOT_CS (in asm/segment.h) remember to leave at least two -# empty GDT entries (one for NULL and one reserved). -# -# NOTE: On some CPUs, the GDT must be 8 byte aligned. This is -# true for the Voyager Quad CPU card which will not boot without -# This directive. 16 byte aligment is recommended by intel. -# - .align 16 -gdt: - .fill GDT_ENTRY_BOOT_CS,8,0 - - .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: - .align 4 - - .word 0 # alignment byte -idt_48: - .word 0 # idt limit = 0 - .word 0, 0 # idt base = 0L - - .word 0 # alignment byte -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: diff --git a/arch/i386/boot/tools/build.c b/arch/i386/boot/tools/build.c index 05798419a6a9..b4248740ff0d 100644 --- a/arch/i386/boot/tools/build.c +++ b/arch/i386/boot/tools/build.c @@ -1,13 +1,12 @@ /* * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 1997 Martin Mares + * Copyright (C) 2007 H. Peter Anvin */ /* - * This file builds a disk-image from three different files: + * This file builds a disk-image from two different files: * - * - bootsect: compatibility mbr which prints an error message if - * someone tries to boot the kernel directly. * - setup: 8086 machine code, sets up system parm * - system: 80386 code for actual system * @@ -21,6 +20,7 @@ * High loaded stuff by Hans Lermen & Werner Almesberger, Feb. 1996 * Cross compiling fixes by Gertjan van Wingerde, July 1996 * Rewritten by Martin Mares, April 1997 + * Substantially overhauled by H. Peter Anvin, April 2007 */ #include <stdio.h> @@ -32,23 +32,25 @@ #include <sys/sysmacros.h> #include <unistd.h> #include <fcntl.h> +#include <sys/mman.h> #include <asm/boot.h> -typedef unsigned char byte; -typedef unsigned short word; -typedef unsigned long u32; +typedef unsigned char u8; +typedef unsigned short u16; +typedef unsigned long u32; #define DEFAULT_MAJOR_ROOT 0 #define DEFAULT_MINOR_ROOT 0 -/* Minimal number of setup sectors (see also bootsect.S) */ -#define SETUP_SECTS 4 +/* Minimal number of setup sectors */ +#define SETUP_SECT_MIN 5 +#define SETUP_SECT_MAX 64 -byte buf[1024]; -int fd; +/* This must be large enough to hold the entire setup */ +u8 buf[SETUP_SECT_MAX*512]; int is_big_kernel; -void die(const char * str, ...) +static void die(const char * str, ...) { va_list args; va_start(args, str); @@ -57,15 +59,9 @@ void die(const char * str, ...) exit(1); } -void file_open(const char *name) +static void usage(void) { - if ((fd = open(name, O_RDONLY, 0)) < 0) - die("Unable to open `%s': %m", name); -} - -void usage(void) -{ - die("Usage: build [-b] bootsect setup system [rootdev] [> image]"); + die("Usage: build [-b] setup system [rootdev] [> image]"); } int main(int argc, char ** argv) @@ -73,27 +69,30 @@ int main(int argc, char ** argv) unsigned int i, sz, setup_sectors; int c; u32 sys_size; - byte major_root, minor_root; + u8 major_root, minor_root; struct stat sb; + FILE *file; + int fd; + void *kernel; if (argc > 2 && !strcmp(argv[1], "-b")) { is_big_kernel = 1; argc--, argv++; } - if ((argc < 4) || (argc > 5)) + if ((argc < 3) || (argc > 4)) usage(); - if (argc > 4) { - if (!strcmp(argv[4], "CURRENT")) { + if (argc > 3) { + if (!strcmp(argv[3], "CURRENT")) { if (stat("/", &sb)) { perror("/"); die("Couldn't stat /"); } major_root = major(sb.st_dev); minor_root = minor(sb.st_dev); - } else if (strcmp(argv[4], "FLOPPY")) { - if (stat(argv[4], &sb)) { - perror(argv[4]); + } else if (strcmp(argv[3], "FLOPPY")) { + if (stat(argv[3], &sb)) { + perror(argv[3]); die("Couldn't stat root device."); } major_root = major(sb.st_rdev); @@ -108,79 +107,62 @@ int main(int argc, char ** argv) } fprintf(stderr, "Root device is (%d, %d)\n", major_root, minor_root); - file_open(argv[1]); - i = read(fd, buf, sizeof(buf)); - fprintf(stderr,"Boot sector %d bytes.\n",i); - if (i != 512) - die("Boot block must be exactly 512 bytes"); + /* Copy the setup code */ + file = fopen(argv[1], "r"); + if (!file) + die("Unable to open `%s': %m", argv[1]); + c = fread(buf, 1, sizeof(buf), file); + if (ferror(file)) + die("read-error on `setup'"); + if (c < 1024) + die("The setup must be at least 1024 bytes"); if (buf[510] != 0x55 || buf[511] != 0xaa) die("Boot block hasn't got boot flag (0xAA55)"); + fclose(file); + + /* Pad unused space with zeros */ + setup_sectors = (c + 511) / 512; + if (setup_sectors < SETUP_SECT_MIN) + setup_sectors = SETUP_SECT_MIN; + i = setup_sectors*512; + memset(buf+c, 0, i-c); + + /* Set the default root device */ buf[508] = minor_root; buf[509] = major_root; - if (write(1, buf, 512) != 512) - die("Write call failed"); - close (fd); - - file_open(argv[2]); /* Copy the setup code */ - for (i=0 ; (c=read(fd, buf, sizeof(buf)))>0 ; i+=c ) - if (write(1, buf, c) != c) - die("Write call failed"); - if (c != 0) - die("read-error on `setup'"); - close (fd); - - setup_sectors = (i + 511) / 512; /* Pad unused space with zeros */ - /* for compatibility with ancient versions of LILO. */ - if (setup_sectors < SETUP_SECTS) - setup_sectors = SETUP_SECTS; - fprintf(stderr, "Setup is %d bytes.\n", i); - memset(buf, 0, sizeof(buf)); - while (i < setup_sectors * 512) { - c = setup_sectors * 512 - i; - if (c > sizeof(buf)) - c = sizeof(buf); - if (write(1, buf, c) != c) - die("Write call failed"); - i += c; - } - file_open(argv[3]); - if (fstat (fd, &sb)) - die("Unable to stat `%s': %m", argv[3]); + fprintf(stderr, "Setup is %d bytes (padded to %d bytes).\n", c, i); + + /* Open and stat the kernel file */ + fd = open(argv[2], O_RDONLY); + if (fd < 0) + die("Unable to open `%s': %m", argv[2]); + if (fstat(fd, &sb)) + die("Unable to stat `%s': %m", argv[2]); sz = sb.st_size; - fprintf (stderr, "System is %d kB\n", sz/1024); + fprintf (stderr, "System is %d kB\n", (sz+1023)/1024); + kernel = mmap(NULL, sz, PROT_READ, MAP_SHARED, fd, 0); + if (kernel == MAP_FAILED) + die("Unable to mmap '%s': %m", argv[2]); sys_size = (sz + 15) / 16; if (!is_big_kernel && sys_size > DEF_SYSSIZE) die("System is too big. Try using bzImage or modules."); - while (sz > 0) { - int l, n; - - l = (sz > sizeof(buf)) ? sizeof(buf) : sz; - if ((n=read(fd, buf, l)) != l) { - if (n < 0) - die("Error reading %s: %m", argv[3]); - else - die("%s: Unexpected EOF", argv[3]); - } - if (write(1, buf, l) != l) - die("Write failed"); - sz -= l; - } + + /* Patch the setup code with the appropriate size parameters */ + buf[0x1f1] = setup_sectors-1; + buf[0x1f4] = sys_size; + buf[0x1f5] = sys_size >> 8; + buf[0x1f6] = sys_size >> 16; + buf[0x1f7] = sys_size >> 24; + + if (fwrite(buf, 1, i, stdout) != i) + die("Writing setup failed"); + + /* Copy the kernel code */ + if (fwrite(kernel, 1, sz, stdout) != sz) + die("Writing kernel failed"); close(fd); - if (lseek(1, 497, SEEK_SET) != 497) /* Write sizes to the bootsector */ - die("Output: seek failed"); - buf[0] = setup_sectors; - if (write(1, buf, 1) != 1) - die("Write of setup sector count failed"); - if (lseek(1, 500, SEEK_SET) != 500) - die("Output: seek failed"); - buf[0] = (sys_size & 0xff); - buf[1] = ((sys_size >> 8) & 0xff); - buf[2] = ((sys_size >> 16) & 0xff); - buf[3] = ((sys_size >> 24) & 0xff); - if (write(1, buf, 4) != 4) - die("Write of image length failed"); - - return 0; /* Everything is OK */ + /* Everything is OK */ + return 0; } diff --git a/arch/i386/boot/video.S b/arch/i386/boot/video.S deleted file mode 100644 index 8143c9516cb4..000000000000 --- a/arch/i386/boot/video.S +++ /dev/null @@ -1,2043 +0,0 @@ -/* video.S - * - * Display adapter & video mode setup, version 2.13 (14-May-99) - * - * Copyright (C) 1995 -- 1998 Martin Mares <mj@ucw.cz> - * Based on the original setup.S code (C) Linus Torvalds and Mats Anderson - * - * Rewritten to use GNU 'as' by Chris Noe <stiker@northlink.com> May 1999 - * - * For further information, look at Documentation/svga.txt. - * - */ - -/* Enable autodetection of SVGA adapters and modes. */ -#undef CONFIG_VIDEO_SVGA - -/* Enable autodetection of VESA modes */ -#define CONFIG_VIDEO_VESA - -/* Enable compacting of mode table */ -#define CONFIG_VIDEO_COMPACT - -/* Retain screen contents when switching modes */ -#define CONFIG_VIDEO_RETAIN - -/* Enable local mode list */ -#undef CONFIG_VIDEO_LOCAL - -/* Force 400 scan lines for standard modes (hack to fix bad BIOS behaviour */ -#undef CONFIG_VIDEO_400_HACK - -/* Hack that lets you force specific BIOS mode ID and specific dimensions */ -#undef CONFIG_VIDEO_GFX_HACK -#define VIDEO_GFX_BIOS_AX 0x4f02 /* 800x600 on ThinkPad */ -#define VIDEO_GFX_BIOS_BX 0x0102 -#define VIDEO_GFX_DUMMY_RESOLUTION 0x6425 /* 100x37 */ - -/* 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 - -/* Special video modes */ -#define VIDEO_FIRST_SPECIAL 0x0f00 -#define VIDEO_80x25 0x0f00 -#define VIDEO_8POINT 0x0f01 -#define VIDEO_80x43 0x0f02 -#define VIDEO_80x28 0x0f03 -#define VIDEO_CURRENT_MODE 0x0f04 -#define VIDEO_80x30 0x0f05 -#define VIDEO_80x34 0x0f06 -#define VIDEO_80x60 0x0f07 -#define VIDEO_GFX_HACK 0x0f08 -#define VIDEO_LAST_SPECIAL 0x0f09 - -/* Video modes given by resolution */ -#define VIDEO_FIRST_RESOLUTION 0x1000 - -/* The "recalculate timings" flag */ -#define VIDEO_RECALC 0x8000 - -/* Positions of various video parameters passed to the kernel */ -/* (see also include/linux/tty.h) */ -#define PARAM_CURSOR_POS 0x00 -#define PARAM_VIDEO_PAGE 0x04 -#define PARAM_VIDEO_MODE 0x06 -#define PARAM_VIDEO_COLS 0x07 -#define PARAM_VIDEO_EGA_BX 0x0a -#define PARAM_VIDEO_LINES 0x0e -#define PARAM_HAVE_VGA 0x0f -#define PARAM_FONT_POINTS 0x10 - -#define PARAM_LFB_WIDTH 0x12 -#define PARAM_LFB_HEIGHT 0x14 -#define PARAM_LFB_DEPTH 0x16 -#define PARAM_LFB_BASE 0x18 -#define PARAM_LFB_SIZE 0x1c -#define PARAM_LFB_LINELENGTH 0x24 -#define PARAM_LFB_COLORS 0x26 -#define PARAM_VESAPM_SEG 0x2e -#define PARAM_VESAPM_OFF 0x30 -#define PARAM_LFB_PAGES 0x32 -#define PARAM_VESA_ATTRIB 0x34 -#define PARAM_CAPABILITIES 0x36 - -/* Define DO_STORE according to CONFIG_VIDEO_RETAIN */ -#ifdef CONFIG_VIDEO_RETAIN -#define DO_STORE call store_screen -#else -#define DO_STORE -#endif /* CONFIG_VIDEO_RETAIN */ - -# This is the main entry point called by setup.S -# %ds *must* be pointing to the bootsector -video: pushw %ds # We use different segments - pushw %ds # FS contains original DS - popw %fs - pushw %cs # DS is equal to CS - popw %ds - pushw %cs # ES is equal to CS - popw %es - xorw %ax, %ax - movw %ax, %gs # GS is zero - cld - call basic_detect # Basic adapter type testing (EGA/VGA/MDA/CGA) -#ifdef CONFIG_VIDEO_SELECT - movw %fs:(0x01fa), %ax # User selected video mode - cmpw $ASK_VGA, %ax # Bring up the menu - jz vid2 - - call mode_set # Set the mode - jc vid1 - - leaw badmdt, %si # Invalid mode ID - call prtstr -vid2: call mode_menu -vid1: -#ifdef CONFIG_VIDEO_RETAIN - call restore_screen # Restore screen contents -#endif /* CONFIG_VIDEO_RETAIN */ - call store_edid -#endif /* CONFIG_VIDEO_SELECT */ - call mode_params # Store mode parameters - popw %ds # Restore original DS - ret - -# Detect if we have CGA, MDA, EGA or VGA and pass it to the kernel. -basic_detect: - movb $0, %fs:(PARAM_HAVE_VGA) - movb $0x12, %ah # Check EGA/VGA - movb $0x10, %bl - int $0x10 - movw %bx, %fs:(PARAM_VIDEO_EGA_BX) # Identifies EGA to the kernel - cmpb $0x10, %bl # No, it's a CGA/MDA/HGA card. - je basret - - incb adapter - movw $0x1a00, %ax # Check EGA or VGA? - int $0x10 - cmpb $0x1a, %al # 1a means VGA... - jne basret # anything else is EGA. - - incb %fs:(PARAM_HAVE_VGA) # We've detected a VGA - incb adapter -basret: ret - -# Store the video mode parameters for later usage by the kernel. -# This is done by asking the BIOS except for the rows/columns -# parameters in the default 80x25 mode -- these are set directly, -# because some very obscure BIOSes supply insane values. -mode_params: -#ifdef CONFIG_VIDEO_SELECT - cmpb $0, graphic_mode - jnz mopar_gr -#endif - movb $0x03, %ah # Read cursor position - xorb %bh, %bh - int $0x10 - movw %dx, %fs:(PARAM_CURSOR_POS) - movb $0x0f, %ah # Read page/mode/width - int $0x10 - movw %bx, %fs:(PARAM_VIDEO_PAGE) - movw %ax, %fs:(PARAM_VIDEO_MODE) # Video mode and screen width - cmpb $0x7, %al # MDA/HGA => segment differs - jnz mopar0 - - movw $0xb000, video_segment -mopar0: movw %gs:(0x485), %ax # Font size - movw %ax, %fs:(PARAM_FONT_POINTS) # (valid only on EGA/VGA) - movw force_size, %ax # Forced size? - orw %ax, %ax - jz mopar1 - - movb %ah, %fs:(PARAM_VIDEO_COLS) - movb %al, %fs:(PARAM_VIDEO_LINES) - ret - -mopar1: movb $25, %al - cmpb $0, adapter # If we are on CGA/MDA/HGA, the - jz mopar2 # screen must have 25 lines. - - movb %gs:(0x484), %al # On EGA/VGA, use the EGA+ BIOS - incb %al # location of max lines. -mopar2: movb %al, %fs:(PARAM_VIDEO_LINES) - ret - -#ifdef CONFIG_VIDEO_SELECT -# Fetching of VESA frame buffer parameters -mopar_gr: - leaw modelist+1024, %di - movb $0x23, %fs:(PARAM_HAVE_VGA) - movw 16(%di), %ax - movw %ax, %fs:(PARAM_LFB_LINELENGTH) - movw 18(%di), %ax - movw %ax, %fs:(PARAM_LFB_WIDTH) - movw 20(%di), %ax - movw %ax, %fs:(PARAM_LFB_HEIGHT) - movb 25(%di), %al - movb $0, %ah - movw %ax, %fs:(PARAM_LFB_DEPTH) - movb 29(%di), %al - movb $0, %ah - movw %ax, %fs:(PARAM_LFB_PAGES) - movl 40(%di), %eax - movl %eax, %fs:(PARAM_LFB_BASE) - movl 31(%di), %eax - movl %eax, %fs:(PARAM_LFB_COLORS) - movl 35(%di), %eax - movl %eax, %fs:(PARAM_LFB_COLORS+4) - movw 0(%di), %ax - movw %ax, %fs:(PARAM_VESA_ATTRIB) - -# get video mem size - leaw modelist+1024, %di - movw $0x4f00, %ax - int $0x10 - xorl %eax, %eax - movw 18(%di), %ax - movl %eax, %fs:(PARAM_LFB_SIZE) - -# store mode capabilities - movl 10(%di), %eax - movl %eax, %fs:(PARAM_CAPABILITIES) - -# switching the DAC to 8-bit is for <= 8 bpp only - movw %fs:(PARAM_LFB_DEPTH), %ax - cmpw $8, %ax - jg dac_done - -# get DAC switching capability - xorl %eax, %eax - movb 10(%di), %al - testb $1, %al - jz dac_set - -# attempt to switch DAC to 8-bit - movw $0x4f08, %ax - movw $0x0800, %bx - int $0x10 - cmpw $0x004f, %ax - jne dac_set - movb %bh, dac_size # store actual DAC size - -dac_set: -# set color size to DAC size - movb dac_size, %al - movb %al, %fs:(PARAM_LFB_COLORS+0) - movb %al, %fs:(PARAM_LFB_COLORS+2) - movb %al, %fs:(PARAM_LFB_COLORS+4) - movb %al, %fs:(PARAM_LFB_COLORS+6) - -# set color offsets to 0 - movb $0, %fs:(PARAM_LFB_COLORS+1) - movb $0, %fs:(PARAM_LFB_COLORS+3) - movb $0, %fs:(PARAM_LFB_COLORS+5) - movb $0, %fs:(PARAM_LFB_COLORS+7) - -dac_done: -# get protected mode interface informations - movw $0x4f0a, %ax - xorw %bx, %bx - xorw %di, %di - int $0x10 - cmp $0x004f, %ax - jnz no_pm - - movw %es, %fs:(PARAM_VESAPM_SEG) - movw %di, %fs:(PARAM_VESAPM_OFF) -no_pm: ret - -# The video mode menu -mode_menu: - leaw keymsg, %si # "Return/Space/Timeout" message - call prtstr - call flush -nokey: call getkt - - cmpb $0x0d, %al # ENTER ? - je listm # yes - manual mode selection - - cmpb $0x20, %al # SPACE ? - je defmd1 # no - repeat - - call beep - jmp nokey - -defmd1: ret # No mode chosen? Default 80x25 - -listm: call mode_table # List mode table -listm0: leaw name_bann, %si # Print adapter name - call prtstr - movw card_name, %si - orw %si, %si - jnz an2 - - movb adapter, %al - leaw old_name, %si - orb %al, %al - jz an1 - - leaw ega_name, %si - decb %al - jz an1 - - leaw vga_name, %si - jmp an1 - -an2: call prtstr - leaw svga_name, %si -an1: call prtstr - leaw listhdr, %si # Table header - call prtstr - movb $0x30, %dl # DL holds mode number - leaw modelist, %si -lm1: cmpw $ASK_VGA, (%si) # End? - jz lm2 - - movb %dl, %al # Menu selection number - call prtchr - call prtsp2 - lodsw - call prthw # Mode ID - call prtsp2 - movb 0x1(%si), %al - call prtdec # Rows - movb $0x78, %al # the letter 'x' - call prtchr - lodsw - call prtdec # Columns - movb $0x0d, %al # New line - call prtchr - movb $0x0a, %al - call prtchr - incb %dl # Next character - cmpb $0x3a, %dl - jnz lm1 - - movb $0x61, %dl - jmp lm1 - -lm2: leaw prompt, %si # Mode prompt - call prtstr - leaw edit_buf, %di # Editor buffer -lm3: call getkey - cmpb $0x0d, %al # Enter? - jz lment - - cmpb $0x08, %al # Backspace? - jz lmbs - - cmpb $0x20, %al # Printable? - jc lm3 - - cmpw $edit_buf+4, %di # Enough space? - jz lm3 - - stosb - call prtchr - jmp lm3 - -lmbs: cmpw $edit_buf, %di # Backspace - jz lm3 - - decw %di - movb $0x08, %al - call prtchr - call prtspc - movb $0x08, %al - call prtchr - jmp lm3 - -lment: movb $0, (%di) - leaw crlft, %si - call prtstr - leaw edit_buf, %si - cmpb $0, (%si) # Empty string = default mode - jz lmdef - - cmpb $0, 1(%si) # One character = menu selection - jz mnusel - - cmpw $0x6373, (%si) # "scan" => mode scanning - jnz lmhx - - cmpw $0x6e61, 2(%si) - jz lmscan - -lmhx: xorw %bx, %bx # Else => mode ID in hex -lmhex: lodsb - orb %al, %al - jz lmuse1 - - subb $0x30, %al - jc lmbad - - cmpb $10, %al - jc lmhx1 - - subb $7, %al - andb $0xdf, %al - cmpb $10, %al - jc lmbad - - cmpb $16, %al - jnc lmbad - -lmhx1: shlw $4, %bx - orb %al, %bl - jmp lmhex - -lmuse1: movw %bx, %ax - jmp lmuse - -mnusel: lodsb # Menu selection - xorb %ah, %ah - subb $0x30, %al - jc lmbad - - cmpb $10, %al - jc lmuse - - cmpb $0x61-0x30, %al - jc lmbad - - subb $0x61-0x30-10, %al - cmpb $36, %al - jnc lmbad - -lmuse: call mode_set - jc lmdef - -lmbad: leaw unknt, %si - call prtstr - jmp lm2 -lmscan: cmpb $0, adapter # Scanning only on EGA/VGA - jz lmbad - - movw $0, mt_end # Scanning of modes is - movb $1, scanning # done as new autodetection. - call mode_table - jmp listm0 -lmdef: ret - -# Additional parts of mode_set... (relative jumps, you know) -setv7: # Video7 extended modes - DO_STORE - subb $VIDEO_FIRST_V7>>8, %bh - movw $0x6f05, %ax - int $0x10 - stc - ret - -_setrec: jmp setrec # Ugly... -_set_80x25: jmp set_80x25 - -# Aliases for backward compatibility. -setalias: - movw $VIDEO_80x25, %ax - incw %bx - jz mode_set - - movb $VIDEO_8POINT-VIDEO_FIRST_SPECIAL, %al - incw %bx - jnz setbad # Fall-through! - -# Setting of user mode (AX=mode ID) => CF=success -mode_set: - movw %ax, %fs:(0x01fa) # Store mode for use in acpi_wakeup.S - movw %ax, %bx - 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 - - cmpb $VIDEO_FIRST_VESA>>8, %ah - jnc check_vesa - - orb %ah, %ah - jz setmenu - - decb %ah - jz setbios - -setbad: clc - movb $0, do_restore # The screen needn't be restored - ret - -setvesa: - DO_STORE - subb $VIDEO_FIRST_VESA>>8, %bh - movw $0x4f02, %ax # VESA BIOS mode set call - int $0x10 - cmpw $0x004f, %ax # AL=4f if implemented - jnz setbad # AH=0 if OK - - stc - ret - -setbios: - DO_STORE - int $0x10 # Standard BIOS mode set call - pushw %bx - movb $0x0f, %ah # Check if really set - int $0x10 - popw %bx - cmpb %bl, %al - jnz setbad - - stc - ret - -setspc: xorb %bh, %bh # Set special mode - cmpb $VIDEO_LAST_SPECIAL-VIDEO_FIRST_SPECIAL, %bl - jnc setbad - - addw %bx, %bx - jmp *spec_inits(%bx) - -setmenu: - orb %al, %al # 80x25 is an exception - jz _set_80x25 - - pushw %bx # Set mode chosen from menu - call mode_table # Build the mode table - popw %ax - shlw $2, %ax - addw %ax, %si - cmpw %di, %si - jnc setbad - - movw (%si), %ax # Fetch mode ID -_m_s: jmp mode_set - -setres: pushw %bx # Set mode chosen by resolution - call mode_table - popw %bx - xchgb %bl, %bh -setr1: lodsw - cmpw $ASK_VGA, %ax # End of the list? - jz setbad - - lodsw - cmpw %bx, %ax - jnz setr1 - - movw -4(%si), %ax # Fetch mode ID - jmp _m_s - -check_vesa: -#ifdef CONFIG_FIRMWARE_EDID - leaw modelist+1024, %di - movw $0x4f00, %ax - int $0x10 - cmpw $0x004f, %ax - jnz setbad - - movw 4(%di), %ax - movw %ax, vbe_version -#endif - leaw modelist+1024, %di - subb $VIDEO_FIRST_VESA>>8, %bh - movw %bx, %cx # Get mode information structure - movw $0x4f01, %ax - int $0x10 - addb $VIDEO_FIRST_VESA>>8, %bh - cmpw $0x004f, %ax - jnz setbad - - movb (%di), %al # Check capabilities. - andb $0x19, %al - cmpb $0x09, %al - jz setvesa # This is a text mode - - movb (%di), %al # Check capabilities. - andb $0x99, %al - cmpb $0x99, %al - jnz _setbad # Doh! No linear frame buffer. - - 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 _setbad # AH=0 if OK - - movb $1, graphic_mode # flag graphic mode - movb $0, do_restore # no screen restore - stc - ret - -_setbad: jmp setbad # Ugly... - -# Recalculate vertical display end registers -- this fixes various -# inconsistencies of extended modes on many adapters. Called when -# the VIDEO_RECALC flag is set in the mode ID. - -setrec: subb $VIDEO_RECALC>>8, %ah # Set the base mode - call mode_set - jnc rct3 - - movw %gs:(0x485), %ax # Font size in pixels - movb %gs:(0x484), %bl # Number of rows - incb %bl - mulb %bl # Number of visible - decw %ax # scan lines - 1 - movw $0x3d4, %dx - movw %ax, %bx - movb $0x12, %al # Lower 8 bits - movb %bl, %ah - outw %ax, %dx - movb $0x07, %al # Bits 8 and 9 in the overflow register - call inidx - xchgb %al, %ah - andb $0xbd, %ah - shrb %bh - jnc rct1 - orb $0x02, %ah -rct1: shrb %bh - jnc rct2 - orb $0x40, %ah -rct2: movb $0x07, %al - outw %ax, %dx - stc -rct3: ret - -# Table of routines for setting of the special modes. -spec_inits: - .word set_80x25 - .word set_8pixel - .word set_80x43 - .word set_80x28 - .word set_current - .word set_80x30 - .word set_80x34 - .word set_80x60 - .word set_gfx - -# Set the 80x25 mode. If already set, do nothing. -set_80x25: - movw $0x5019, force_size # Override possibly broken BIOS -use_80x25: -#ifdef CONFIG_VIDEO_400_HACK - movw $0x1202, %ax # Force 400 scan lines - movb $0x30, %bl - int $0x10 -#else - movb $0x0f, %ah # Get current mode ID - int $0x10 - cmpw $0x5007, %ax # Mode 7 (80x25 mono) is the only one available - jz st80 # on CGA/MDA/HGA and is also available on EGAM - - cmpw $0x5003, %ax # Unknown mode, force 80x25 color - jnz force3 - -st80: cmpb $0, adapter # CGA/MDA/HGA => mode 3/7 is always 80x25 - jz set80 - - movb %gs:(0x0484), %al # This is EGA+ -- beware of 80x50 etc. - orb %al, %al # Some buggy BIOS'es set 0 rows - jz set80 - - cmpb $24, %al # It's hopefully correct - jz set80 -#endif /* CONFIG_VIDEO_400_HACK */ -force3: DO_STORE - movw $0x0003, %ax # Forced set - int $0x10 -set80: stc - ret - -# Set the 80x50/80x43 8-pixel mode. Simple BIOS calls. -set_8pixel: - DO_STORE - call use_80x25 # The base is 80x25 -set_8pt: - movw $0x1112, %ax # Use 8x8 font - xorb %bl, %bl - int $0x10 - movw $0x1200, %ax # Use alternate print screen - movb $0x20, %bl - int $0x10 - movw $0x1201, %ax # Turn off cursor emulation - movb $0x34, %bl - int $0x10 - movb $0x01, %ah # Define cursor scan lines 6-7 - movw $0x0607, %cx - int $0x10 -set_current: - stc - ret - -# Set the 80x28 mode. This mode works on all VGA's, because it's a standard -# 80x25 mode with 14-point fonts instead of 16-point. -set_80x28: - DO_STORE - call use_80x25 # The base is 80x25 -set14: movw $0x1111, %ax # Use 9x14 font - xorb %bl, %bl - int $0x10 - movb $0x01, %ah # Define cursor scan lines 11-12 - movw $0x0b0c, %cx - int $0x10 - stc - ret - -# Set the 80x43 mode. This mode is works on all VGA's. -# It's a 350-scanline mode with 8-pixel font. -set_80x43: - DO_STORE - movw $0x1201, %ax # Set 350 scans - movb $0x30, %bl - int $0x10 - movw $0x0003, %ax # Reset video mode - int $0x10 - jmp set_8pt # Use 8-pixel font - -# Set the 80x30 mode (all VGA's). 480 scanlines, 16-pixel font. -set_80x30: - call use_80x25 # Start with real 80x25 - DO_STORE - movw $0x3cc, %dx # Get CRTC port - inb %dx, %al - movb $0xd4, %dl - rorb %al # Mono or color? - jc set48a - - movb $0xb4, %dl -set48a: movw $0x0c11, %ax # Vertical sync end (also unlocks CR0-7) - call outidx - movw $0x0b06, %ax # Vertical total - call outidx - movw $0x3e07, %ax # (Vertical) overflow - call outidx - movw $0xea10, %ax # Vertical sync start - call outidx - movw $0xdf12, %ax # Vertical display end - call outidx - movw $0xe715, %ax # Vertical blank start - call outidx - movw $0x0416, %ax # Vertical blank end - call outidx - pushw %dx - movb $0xcc, %dl # Misc output register (read) - inb %dx, %al - movb $0xc2, %dl # (write) - andb $0x0d, %al # Preserve clock select bits and color bit - orb $0xe2, %al # Set correct sync polarity - outb %al, %dx - popw %dx - movw $0x501e, force_size - stc # That's all. - ret - -# Set the 80x34 mode (all VGA's). 480 scans, 14-pixel font. -set_80x34: - call set_80x30 # Set 480 scans - call set14 # And 14-pt font - movw $0xdb12, %ax # VGA vertical display end - movw $0x5022, force_size -setvde: call outidx - stc - ret - -# Set the 80x60 mode (all VGA's). 480 scans, 8-pixel font. -set_80x60: - call set_80x30 # Set 480 scans - call set_8pt # And 8-pt font - movw $0xdf12, %ax # VGA vertical display end - movw $0x503c, force_size - jmp setvde - -# Special hack for ThinkPad graphics -set_gfx: -#ifdef CONFIG_VIDEO_GFX_HACK - movw $VIDEO_GFX_BIOS_AX, %ax - movw $VIDEO_GFX_BIOS_BX, %bx - int $0x10 - movw $VIDEO_GFX_DUMMY_RESOLUTION, force_size - stc -#endif - ret - -#ifdef CONFIG_VIDEO_RETAIN - -# Store screen contents to temporary buffer. -store_screen: - cmpb $0, do_restore # Already stored? - jnz stsr - - testb $CAN_USE_HEAP, loadflags # Have we space for storing? - jz stsr - - pushw %ax - pushw %bx - pushw force_size # Don't force specific size - movw $0, force_size - call mode_params # Obtain params of current mode - popw force_size - movb %fs:(PARAM_VIDEO_LINES), %ah - movb %fs:(PARAM_VIDEO_COLS), %al - movw %ax, %bx # BX=dimensions - mulb %ah - movw %ax, %cx # CX=number of characters - addw %ax, %ax # Calculate image size - addw $modelist+1024+4, %ax - cmpw heap_end_ptr, %ax - jnc sts1 # Unfortunately, out of memory - - movw %fs:(PARAM_CURSOR_POS), %ax # Store mode params - leaw modelist+1024, %di - stosw - movw %bx, %ax - stosw - pushw %ds # Store the screen - movw video_segment, %ds - xorw %si, %si - rep - movsw - popw %ds - incb do_restore # Screen will be restored later -sts1: popw %bx - popw %ax -stsr: ret - -# Restore screen contents from temporary buffer. -restore_screen: - cmpb $0, do_restore # Has the screen been stored? - jz res1 - - call mode_params # Get parameters of current mode - movb %fs:(PARAM_VIDEO_LINES), %cl - movb %fs:(PARAM_VIDEO_COLS), %ch - leaw modelist+1024, %si # Screen buffer - lodsw # Set cursor position - movw %ax, %dx - cmpb %cl, %dh - jc res2 - - movb %cl, %dh - decb %dh -res2: cmpb %ch, %dl - jc res3 - - movb %ch, %dl - decb %dl -res3: movb $0x02, %ah - movb $0x00, %bh - int $0x10 - lodsw # Display size - movb %ah, %dl # DL=number of lines - movb $0, %ah # BX=phys. length of orig. line - movw %ax, %bx - cmpb %cl, %dl # Too many? - jc res4 - - pushw %ax - movb %dl, %al - subb %cl, %al - mulb %bl - addw %ax, %si - addw %ax, %si - popw %ax - movb %cl, %dl -res4: cmpb %ch, %al # Too wide? - jc res5 - - movb %ch, %al # AX=width of src. line -res5: movb $0, %cl - xchgb %ch, %cl - movw %cx, %bp # BP=width of dest. line - pushw %es - movw video_segment, %es - xorw %di, %di # Move the data - addw %bx, %bx # Convert BX and BP to _bytes_ - addw %bp, %bp -res6: pushw %si - pushw %di - movw %ax, %cx - rep - movsw - popw %di - popw %si - addw %bp, %di - addw %bx, %si - decb %dl - jnz res6 - - popw %es # Done -res1: ret -#endif /* CONFIG_VIDEO_RETAIN */ - -# Write to indexed VGA register (AL=index, AH=data, DX=index reg. port) -outidx: outb %al, %dx - pushw %ax - movb %ah, %al - incw %dx - outb %al, %dx - decw %dx - popw %ax - ret - -# Build the table of video modes (stored after the setup.S code at the -# `modelist' label. Each video mode record looks like: -# .word MODE-ID (our special mode ID (see above)) -# .byte rows (number of rows) -# .byte columns (number of columns) -# Returns address of the end of the table in DI, the end is marked -# with a ASK_VGA ID. -mode_table: - movw mt_end, %di # Already filled? - orw %di, %di - jnz mtab1x - - leaw modelist, %di # Store standard modes: - movl $VIDEO_80x25 + 0x50190000, %eax # The 80x25 mode (ALL) - stosl - movb adapter, %al # CGA/MDA/HGA -- no more modes - orb %al, %al - jz mtabe - - decb %al - jnz mtabv - - movl $VIDEO_8POINT + 0x502b0000, %eax # The 80x43 EGA mode - stosl - jmp mtabe - -mtab1x: jmp mtab1 - -mtabv: leaw vga_modes, %si # All modes for std VGA - movw $vga_modes_end-vga_modes, %cx - rep # I'm unable to use movsw as I don't know how to store a half - movsb # of the expression above to cx without using explicit shr. - - cmpb $0, scanning # Mode scan requested? - jz mscan1 - - call mode_scan -mscan1: - -#ifdef CONFIG_VIDEO_LOCAL - call local_modes -#endif /* CONFIG_VIDEO_LOCAL */ - -#ifdef CONFIG_VIDEO_VESA - call vesa_modes # Detect VESA VGA modes -#endif /* CONFIG_VIDEO_VESA */ - -#ifdef CONFIG_VIDEO_SVGA - cmpb $0, scanning # Bypass when scanning - jnz mscan2 - - call svga_modes # Detect SVGA cards & modes -mscan2: -#endif /* CONFIG_VIDEO_SVGA */ - -mtabe: - -#ifdef CONFIG_VIDEO_COMPACT - leaw modelist, %si - movw %di, %dx - movw %si, %di -cmt1: cmpw %dx, %si # Scan all modes - jz cmt2 - - leaw modelist, %bx # Find in previous entries - movw 2(%si), %cx -cmt3: cmpw %bx, %si - jz cmt4 - - cmpw 2(%bx), %cx # Found => don't copy this entry - jz cmt5 - - addw $4, %bx - jmp cmt3 - -cmt4: movsl # Copy entry - jmp cmt1 - -cmt5: addw $4, %si # Skip entry - jmp cmt1 - -cmt2: -#endif /* CONFIG_VIDEO_COMPACT */ - - movw $ASK_VGA, (%di) # End marker - movw %di, mt_end -mtab1: leaw modelist, %si # SI=mode list, DI=list end -ret0: ret - -# Modes usable on all standard VGAs -vga_modes: - .word VIDEO_8POINT - .word 0x5032 # 80x50 - .word VIDEO_80x43 - .word 0x502b # 80x43 - .word VIDEO_80x28 - .word 0x501c # 80x28 - .word VIDEO_80x30 - .word 0x501e # 80x30 - .word VIDEO_80x34 - .word 0x5022 # 80x34 - .word VIDEO_80x60 - .word 0x503c # 80x60 -#ifdef CONFIG_VIDEO_GFX_HACK - .word VIDEO_GFX_HACK - .word VIDEO_GFX_DUMMY_RESOLUTION -#endif - -vga_modes_end: -# Detect VESA modes. - -#ifdef CONFIG_VIDEO_VESA -vesa_modes: - cmpb $2, adapter # VGA only - jnz ret0 - - movw %di, %bp # BP=original mode table end - addw $0x200, %di # Buffer space - movw $0x4f00, %ax # VESA Get card info call - int $0x10 - movw %bp, %di - cmpw $0x004f, %ax # Successful? - jnz ret0 - - cmpw $0x4556, 0x200(%di) - jnz ret0 - - cmpw $0x4153, 0x202(%di) - jnz ret0 - - movw $vesa_name, card_name # Set name to "VESA VGA" - pushw %gs - lgsw 0x20e(%di), %si # GS:SI=mode list - movw $128, %cx # Iteration limit -vesa1: -# gas version 2.9.1, using BFD version 2.9.1.0.23 buggers the next inst. -# XXX: lodsw %gs:(%si), %ax # Get next mode in the list - gs; lodsw - cmpw $0xffff, %ax # End of the table? - jz vesar - - cmpw $0x0080, %ax # Check validity of mode ID - jc vesa2 - - orb %ah, %ah # Valid IDs: 0x0000-0x007f/0x0100-0x07ff - jz vesan # Certain BIOSes report 0x80-0xff! - - cmpw $0x0800, %ax - jnc vesae - -vesa2: pushw %cx - movw %ax, %cx # Get mode information structure - movw $0x4f01, %ax - int $0x10 - movw %cx, %bx # BX=mode number - addb $VIDEO_FIRST_VESA>>8, %bh - popw %cx - cmpw $0x004f, %ax - jnz vesan # Don't report errors (buggy BIOSES) - - movb (%di), %al # Check capabilities. We require - andb $0x19, %al # a color text mode. - cmpb $0x09, %al - jnz vesan - - cmpw $0xb800, 8(%di) # Standard video memory address required - jnz vesan - - testb $2, (%di) # Mode characteristics supplied? - movw %bx, (%di) # Store mode number - jz vesa3 - - xorw %dx, %dx - movw 0x12(%di), %bx # Width - orb %bh, %bh - jnz vesan - - movb %bl, 0x3(%di) - movw 0x14(%di), %ax # Height - orb %ah, %ah - jnz vesan - - movb %al, 2(%di) - mulb %bl - cmpw $8193, %ax # Small enough for Linux console driver? - jnc vesan - - jmp vesaok - -vesa3: subw $0x8108, %bx # This mode has no detailed info specified, - jc vesan # so it must be a standard VESA mode. - - cmpw $5, %bx - jnc vesan - - movw vesa_text_mode_table(%bx), %ax - movw %ax, 2(%di) -vesaok: addw $4, %di # The mode is valid. Store it. -vesan: loop vesa1 # Next mode. Limit exceeded => error -vesae: leaw vesaer, %si - call prtstr - movw %bp, %di # Discard already found modes. -vesar: popw %gs - ret - -# Dimensions of standard VESA text modes -vesa_text_mode_table: - .byte 60, 80 # 0108 - .byte 25, 132 # 0109 - .byte 43, 132 # 010A - .byte 50, 132 # 010B - .byte 60, 132 # 010C -#endif /* CONFIG_VIDEO_VESA */ - -# Scan for video modes. A bit dirty, but should work. -mode_scan: - movw $0x0100, %cx # Start with mode 0 -scm1: movb $0, %ah # Test the mode - movb %cl, %al - int $0x10 - movb $0x0f, %ah - int $0x10 - cmpb %cl, %al - jnz scm2 # Mode not set - - movw $0x3c0, %dx # Test if it's a text mode - movb $0x10, %al # Mode bits - call inidx - andb $0x03, %al - jnz scm2 - - movb $0xce, %dl # Another set of mode bits - movb $0x06, %al - call inidx - shrb %al - jc scm2 - - movb $0xd4, %dl # Cursor location - movb $0x0f, %al - call inidx - orb %al, %al - jnz scm2 - - movw %cx, %ax # Ok, store the mode - stosw - movb %gs:(0x484), %al # Number of rows - incb %al - stosb - movw %gs:(0x44a), %ax # Number of columns - stosb -scm2: incb %cl - jns scm1 - - movw $0x0003, %ax # Return back to mode 3 - int $0x10 - ret - -tstidx: outw %ax, %dx # OUT DX,AX and inidx -inidx: outb %al, %dx # Read from indexed VGA register - incw %dx # AL=index, DX=index reg port -> AL=data - inb %dx, %al - decw %dx - ret - -# Try to detect type of SVGA card and supply (usually approximate) video -# mode table for it. - -#ifdef CONFIG_VIDEO_SVGA -svga_modes: - leaw svga_table, %si # Test all known SVGA adapters -dosvga: lodsw - movw %ax, %bp # Default mode table - orw %ax, %ax - jz didsv1 - - lodsw # Pointer to test routine - pushw %si - pushw %di - pushw %es - movw $0xc000, %bx - movw %bx, %es - call *%ax # Call test routine - popw %es - popw %di - popw %si - orw %bp, %bp - jz dosvga - - movw %bp, %si # Found, copy the modes - movb svga_prefix, %ah -cpsvga: lodsb - orb %al, %al - jz didsv - - stosw - movsw - jmp cpsvga - -didsv: movw %si, card_name # Store pointer to card name -didsv1: ret - -# Table of all known SVGA cards. For each card, we store a pointer to -# a table of video modes supported by the card and a pointer to a routine -# used for testing of presence of the card. The video mode table is always -# followed by the name of the card or the chipset. -svga_table: - .word ati_md, ati_test - .word oak_md, oak_test - .word paradise_md, paradise_test - .word realtek_md, realtek_test - .word s3_md, s3_test - .word chips_md, chips_test - .word video7_md, video7_test - .word cirrus5_md, cirrus5_test - .word cirrus6_md, cirrus6_test - .word cirrus1_md, cirrus1_test - .word ahead_md, ahead_test - .word everex_md, everex_test - .word genoa_md, genoa_test - .word trident_md, trident_test - .word tseng_md, tseng_test - .word 0 - -# Test routines and mode tables: - -# S3 - The test algorithm was taken from the SuperProbe package -# for XFree86 1.2.1. Report bugs to Christoph.Niemann@linux.org -s3_test: - movw $0x0f35, %cx # we store some constants in cl/ch - movw $0x03d4, %dx - movb $0x38, %al - call inidx - movb %al, %bh # store current CRT-register 0x38 - movw $0x0038, %ax - call outidx # disable writing to special regs - movb %cl, %al # check whether we can write special reg 0x35 - call inidx - movb %al, %bl # save the current value of CRT reg 0x35 - andb $0xf0, %al # clear bits 0-3 - movb %al, %ah - movb %cl, %al # and write it to CRT reg 0x35 - call outidx - call inidx # now read it back - andb %ch, %al # clear the upper 4 bits - jz s3_2 # the first test failed. But we have a - - movb %bl, %ah # second chance - movb %cl, %al - call outidx - jmp s3_1 # do the other tests - -s3_2: movw %cx, %ax # load ah with 0xf and al with 0x35 - orb %bl, %ah # set the upper 4 bits of ah with the orig value - call outidx # write ... - call inidx # ... and reread - andb %cl, %al # turn off the upper 4 bits - pushw %ax - movb %bl, %ah # restore old value in register 0x35 - movb %cl, %al - call outidx - popw %ax - cmpb %ch, %al # setting lower 4 bits was successful => bad - je no_s3 # writing is allowed => this is not an S3 - -s3_1: movw $0x4838, %ax # allow writing to special regs by putting - call outidx # magic number into CRT-register 0x38 - movb %cl, %al # check whether we can write special reg 0x35 - call inidx - movb %al, %bl - andb $0xf0, %al - movb %al, %ah - movb %cl, %al - call outidx - call inidx - andb %ch, %al - jnz no_s3 # no, we can't write => no S3 - - movw %cx, %ax - orb %bl, %ah - call outidx - call inidx - andb %ch, %al - pushw %ax - movb %bl, %ah # restore old value in register 0x35 - movb %cl, %al - call outidx - popw %ax - cmpb %ch, %al - jne no_s31 # writing not possible => no S3 - movb $0x30, %al - call inidx # now get the S3 id ... - leaw idS3, %di - movw $0x10, %cx - repne - scasb - je no_s31 - - movb %bh, %ah - movb $0x38, %al - jmp s3rest - -no_s3: movb $0x35, %al # restore CRT register 0x35 - movb %bl, %ah - call outidx -no_s31: xorw %bp, %bp # Detection failed -s3rest: movb %bh, %ah - movb $0x38, %al # restore old value of CRT register 0x38 - jmp outidx - -idS3: .byte 0x81, 0x82, 0x90, 0x91, 0x92, 0x93, 0x94, 0x95 - .byte 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa8, 0xb0 - -s3_md: .byte 0x54, 0x2b, 0x84 - .byte 0x55, 0x19, 0x84 - .byte 0 - .ascii "S3" - .byte 0 - -# ATI cards. -ati_test: - leaw idati, %si - movw $0x31, %di - movw $0x09, %cx - repe - cmpsb - je atiok - - xorw %bp, %bp -atiok: ret - -idati: .ascii "761295520" - -ati_md: .byte 0x23, 0x19, 0x84 - .byte 0x33, 0x2c, 0x84 - .byte 0x22, 0x1e, 0x64 - .byte 0x21, 0x19, 0x64 - .byte 0x58, 0x21, 0x50 - .byte 0x5b, 0x1e, 0x50 - .byte 0 - .ascii "ATI" - .byte 0 - -# AHEAD -ahead_test: - movw $0x200f, %ax - movw $0x3ce, %dx - outw %ax, %dx - incw %dx - inb %dx, %al - cmpb $0x20, %al - je isahed - - cmpb $0x21, %al - je isahed - - xorw %bp, %bp -isahed: ret - -ahead_md: - .byte 0x22, 0x2c, 0x84 - .byte 0x23, 0x19, 0x84 - .byte 0x24, 0x1c, 0x84 - .byte 0x2f, 0x32, 0xa0 - .byte 0x32, 0x22, 0x50 - .byte 0x34, 0x42, 0x50 - .byte 0 - .ascii "Ahead" - .byte 0 - -# Chips & Tech. -chips_test: - movw $0x3c3, %dx - inb %dx, %al - orb $0x10, %al - outb %al, %dx - movw $0x104, %dx - inb %dx, %al - movb %al, %bl - movw $0x3c3, %dx - inb %dx, %al - andb $0xef, %al - outb %al, %dx - cmpb $0xa5, %bl - je cantok - - xorw %bp, %bp -cantok: ret - -chips_md: - .byte 0x60, 0x19, 0x84 - .byte 0x61, 0x32, 0x84 - .byte 0 - .ascii "Chips & Technologies" - .byte 0 - -# Cirrus Logic 5X0 -cirrus1_test: - movw $0x3d4, %dx - movb $0x0c, %al - outb %al, %dx - incw %dx - inb %dx, %al - movb %al, %bl - xorb %al, %al - outb %al, %dx - decw %dx - movb $0x1f, %al - outb %al, %dx - incw %dx - inb %dx, %al - movb %al, %bh - xorb %ah, %ah - shlb $4, %al - movw %ax, %cx - movb %bh, %al - shrb $4, %al - addw %ax, %cx - shlw $8, %cx - addw $6, %cx - movw %cx, %ax - movw $0x3c4, %dx - outw %ax, %dx - incw %dx - inb %dx, %al - andb %al, %al - jnz nocirr - - movb %bh, %al - outb %al, %dx - inb %dx, %al - cmpb $0x01, %al - je iscirr - -nocirr: xorw %bp, %bp -iscirr: movw $0x3d4, %dx - movb %bl, %al - xorb %ah, %ah - shlw $8, %ax - addw $0x0c, %ax - outw %ax, %dx - ret - -cirrus1_md: - .byte 0x1f, 0x19, 0x84 - .byte 0x20, 0x2c, 0x84 - .byte 0x22, 0x1e, 0x84 - .byte 0x31, 0x25, 0x64 - .byte 0 - .ascii "Cirrus Logic 5X0" - .byte 0 - -# Cirrus Logic 54XX -cirrus5_test: - movw $0x3c4, %dx - movb $6, %al - call inidx - movb %al, %bl # BL=backup - movw $6, %ax - call tstidx - cmpb $0x0f, %al - jne c5fail - - movw $0x1206, %ax - call tstidx - cmpb $0x12, %al - jne c5fail - - movb $0x1e, %al - call inidx - movb %al, %bh - movb %bh, %ah - andb $0xc0, %ah - movb $0x1e, %al - call tstidx - andb $0x3f, %al - jne c5xx - - movb $0x1e, %al - movb %bh, %ah - orb $0x3f, %ah - call tstidx - xorb $0x3f, %al - andb $0x3f, %al -c5xx: pushf - movb $0x1e, %al - movb %bh, %ah - outw %ax, %dx - popf - je c5done - -c5fail: xorw %bp, %bp -c5done: movb $6, %al - movb %bl, %ah - outw %ax, %dx - ret - -cirrus5_md: - .byte 0x14, 0x19, 0x84 - .byte 0x54, 0x2b, 0x84 - .byte 0 - .ascii "Cirrus Logic 54XX" - .byte 0 - -# Cirrus Logic 64XX -- no known extra modes, but must be identified, because -# it's misidentified by the Ahead test. -cirrus6_test: - movw $0x3ce, %dx - movb $0x0a, %al - call inidx - movb %al, %bl # BL=backup - movw $0xce0a, %ax - call tstidx - orb %al, %al - jne c2fail - - movw $0xec0a, %ax - call tstidx - cmpb $0x01, %al - jne c2fail - - movb $0xaa, %al - call inidx # 4X, 5X, 7X and 8X are valid 64XX chip ID's. - shrb $4, %al - subb $4, %al - jz c6done - - decb %al - jz c6done - - subb $2, %al - jz c6done - - decb %al - jz c6done - -c2fail: xorw %bp, %bp -c6done: movb $0x0a, %al - movb %bl, %ah - outw %ax, %dx - ret - -cirrus6_md: - .byte 0 - .ascii "Cirrus Logic 64XX" - .byte 0 - -# Everex / Trident -everex_test: - movw $0x7000, %ax - xorw %bx, %bx - int $0x10 - cmpb $0x70, %al - jne noevrx - - shrw $4, %dx - cmpw $0x678, %dx - je evtrid - - cmpw $0x236, %dx - jne evrxok - -evtrid: leaw trident_md, %bp -evrxok: ret - -noevrx: xorw %bp, %bp - ret - -everex_md: - .byte 0x03, 0x22, 0x50 - .byte 0x04, 0x3c, 0x50 - .byte 0x07, 0x2b, 0x64 - .byte 0x08, 0x4b, 0x64 - .byte 0x0a, 0x19, 0x84 - .byte 0x0b, 0x2c, 0x84 - .byte 0x16, 0x1e, 0x50 - .byte 0x18, 0x1b, 0x64 - .byte 0x21, 0x40, 0xa0 - .byte 0x40, 0x1e, 0x84 - .byte 0 - .ascii "Everex/Trident" - .byte 0 - -# Genoa. -genoa_test: - leaw idgenoa, %si # Check Genoa 'clues' - xorw %ax, %ax - movb %es:(0x37), %al - movw %ax, %di - movw $0x04, %cx - decw %si - decw %di -l1: incw %si - incw %di - movb (%si), %al - testb %al, %al - jz l2 - - cmpb %es:(%di), %al -l2: loope l1 - orw %cx, %cx - je isgen - - xorw %bp, %bp -isgen: ret - -idgenoa: .byte 0x77, 0x00, 0x99, 0x66 - -genoa_md: - .byte 0x58, 0x20, 0x50 - .byte 0x5a, 0x2a, 0x64 - .byte 0x60, 0x19, 0x84 - .byte 0x61, 0x1d, 0x84 - .byte 0x62, 0x20, 0x84 - .byte 0x63, 0x2c, 0x84 - .byte 0x64, 0x3c, 0x84 - .byte 0x6b, 0x4f, 0x64 - .byte 0x72, 0x3c, 0x50 - .byte 0x74, 0x42, 0x50 - .byte 0x78, 0x4b, 0x64 - .byte 0 - .ascii "Genoa" - .byte 0 - -# OAK -oak_test: - leaw idoakvga, %si - movw $0x08, %di - movw $0x08, %cx - repe - cmpsb - je isoak - - xorw %bp, %bp -isoak: ret - -idoakvga: .ascii "OAK VGA " - -oak_md: .byte 0x4e, 0x3c, 0x50 - .byte 0x4f, 0x3c, 0x84 - .byte 0x50, 0x19, 0x84 - .byte 0x51, 0x2b, 0x84 - .byte 0 - .ascii "OAK" - .byte 0 - -# WD Paradise. -paradise_test: - leaw idparadise, %si - movw $0x7d, %di - movw $0x04, %cx - repe - cmpsb - je ispara - - xorw %bp, %bp -ispara: ret - -idparadise: .ascii "VGA=" - -paradise_md: - .byte 0x41, 0x22, 0x50 - .byte 0x47, 0x1c, 0x84 - .byte 0x55, 0x19, 0x84 - .byte 0x54, 0x2c, 0x84 - .byte 0 - .ascii "Paradise" - .byte 0 - -# Trident. -trident_test: - movw $0x3c4, %dx - movb $0x0e, %al - outb %al, %dx - incw %dx - inb %dx, %al - xchgb %al, %ah - xorb %al, %al - outb %al, %dx - inb %dx, %al - xchgb %ah, %al - movb %al, %bl # Strange thing ... in the book this wasn't - andb $0x02, %bl # necessary but it worked on my card which - jz setb2 # is a trident. Without it the screen goes - # blurred ... - andb $0xfd, %al - jmp clrb2 - -setb2: orb $0x02, %al -clrb2: outb %al, %dx - andb $0x0f, %ah - cmpb $0x02, %ah - je istrid - - xorw %bp, %bp -istrid: ret - -trident_md: - .byte 0x50, 0x1e, 0x50 - .byte 0x51, 0x2b, 0x50 - .byte 0x52, 0x3c, 0x50 - .byte 0x57, 0x19, 0x84 - .byte 0x58, 0x1e, 0x84 - .byte 0x59, 0x2b, 0x84 - .byte 0x5a, 0x3c, 0x84 - .byte 0 - .ascii "Trident" - .byte 0 - -# Tseng. -tseng_test: - movw $0x3cd, %dx - inb %dx, %al # Could things be this simple ! :-) - movb %al, %bl - movb $0x55, %al - outb %al, %dx - inb %dx, %al - movb %al, %ah - movb %bl, %al - outb %al, %dx - cmpb $0x55, %ah - je istsen - -isnot: xorw %bp, %bp -istsen: ret - -tseng_md: - .byte 0x26, 0x3c, 0x50 - .byte 0x2a, 0x28, 0x64 - .byte 0x23, 0x19, 0x84 - .byte 0x24, 0x1c, 0x84 - .byte 0x22, 0x2c, 0x84 - .byte 0x21, 0x3c, 0x84 - .byte 0 - .ascii "Tseng" - .byte 0 - -# Video7. -video7_test: - movw $0x3cc, %dx - inb %dx, %al - movw $0x3b4, %dx - andb $0x01, %al - jz even7 - - movw $0x3d4, %dx -even7: movb $0x0c, %al - outb %al, %dx - incw %dx - inb %dx, %al - movb %al, %bl - movb $0x55, %al - outb %al, %dx - inb %dx, %al - decw %dx - movb $0x1f, %al - outb %al, %dx - incw %dx - inb %dx, %al - movb %al, %bh - decw %dx - movb $0x0c, %al - outb %al, %dx - incw %dx - movb %bl, %al - outb %al, %dx - movb $0x55, %al - xorb $0xea, %al - cmpb %bh, %al - jne isnot - - movb $VIDEO_FIRST_V7>>8, svga_prefix # Use special mode switching - ret - -video7_md: - .byte 0x40, 0x2b, 0x50 - .byte 0x43, 0x3c, 0x50 - .byte 0x44, 0x3c, 0x64 - .byte 0x41, 0x19, 0x84 - .byte 0x42, 0x2c, 0x84 - .byte 0x45, 0x1c, 0x84 - .byte 0 - .ascii "Video 7" - .byte 0 - -# Realtek VGA -realtek_test: - leaw idrtvga, %si - movw $0x45, %di - movw $0x0b, %cx - repe - cmpsb - je isrt - - xorw %bp, %bp -isrt: ret - -idrtvga: .ascii "REALTEK VGA" - -realtek_md: - .byte 0x1a, 0x3c, 0x50 - .byte 0x1b, 0x19, 0x84 - .byte 0x1c, 0x1e, 0x84 - .byte 0x1d, 0x2b, 0x84 - .byte 0x1e, 0x3c, 0x84 - .byte 0 - .ascii "REALTEK" - .byte 0 - -#endif /* CONFIG_VIDEO_SVGA */ - -# User-defined local mode table (VGA only) -#ifdef CONFIG_VIDEO_LOCAL -local_modes: - leaw local_mode_table, %si -locm1: lodsw - orw %ax, %ax - jz locm2 - - stosw - movsw - jmp locm1 - -locm2: ret - -# This is the table of local video modes which can be supplied manually -# by the user. Each entry consists of mode ID (word) and dimensions -# (byte for column count and another byte for row count). These modes -# are placed before all SVGA and VESA modes and override them if table -# compacting is enabled. The table must end with a zero word followed -# by NUL-terminated video adapter name. -local_mode_table: - .word 0x0100 # Example: 40x25 - .byte 25,40 - .word 0 - .ascii "Local" - .byte 0 -#endif /* CONFIG_VIDEO_LOCAL */ - -# Read a key and return the ASCII code in al, scan code in ah -getkey: xorb %ah, %ah - int $0x16 - ret - -# Read a key with a timeout of 30 seconds. -# The hardware clock is used to get the time. -getkt: call gettime - addb $30, %al # Wait 30 seconds - cmpb $60, %al - jl lminute - - subb $60, %al -lminute: - movb %al, %cl -again: movb $0x01, %ah - int $0x16 - jnz getkey # key pressed, so get it - - call gettime - cmpb %cl, %al - jne again - - movb $0x20, %al # timeout, return `space' - ret - -# Flush the keyboard buffer -flush: movb $0x01, %ah - int $0x16 - jz empty - - xorb %ah, %ah - int $0x16 - jmp flush - -empty: ret - -# Print hexadecimal number. -prthw: pushw %ax - movb %ah, %al - call prthb - popw %ax -prthb: pushw %ax - shrb $4, %al - call prthn - popw %ax - andb $0x0f, %al -prthn: cmpb $0x0a, %al - jc prth1 - - addb $0x07, %al -prth1: addb $0x30, %al - jmp prtchr - -# Print decimal number in al -prtdec: pushw %ax - pushw %cx - xorb %ah, %ah - movb $0x0a, %cl - idivb %cl - cmpb $0x09, %al - jbe lt100 - - call prtdec - jmp skip10 - -lt100: addb $0x30, %al - call prtchr -skip10: movb %ah, %al - addb $0x30, %al - call prtchr - popw %cx - popw %ax - ret - -store_edid: -#ifdef CONFIG_FIRMWARE_EDID - pushw %es # just save all registers - pushw %ax - pushw %bx - pushw %cx - pushw %dx - pushw %di - - pushw %fs - popw %es - - movl $0x13131313, %eax # memset block with 0x13 - movw $32, %cx - movw $0x140, %di - cld - rep - stosl - - cmpw $0x0200, vbe_version # only do EDID on >= VBE2.0 - jl no_edid - - pushw %es # save ES - xorw %di, %di # Report Capability - pushw %di - popw %es # ES:DI must be 0:0 - movw $0x4f15, %ax - xorw %bx, %bx - xorw %cx, %cx - int $0x10 - popw %es # restore ES - - cmpb $0x00, %ah # call successful - jne no_edid - - cmpb $0x4f, %al # function supported - jne no_edid - - movw $0x4f15, %ax # do VBE/DDC - movw $0x01, %bx - movw $0x00, %cx - movw $0x00, %dx - movw $0x140, %di - int $0x10 - -no_edid: - popw %di # restore all registers - popw %dx - popw %cx - popw %bx - popw %ax - popw %es -#endif - ret - -# VIDEO_SELECT-only variables -mt_end: .word 0 # End of video mode table if built -edit_buf: .space 6 # Line editor buffer -card_name: .word 0 # Pointer to adapter name -scanning: .byte 0 # Performing mode scan -do_restore: .byte 0 # Screen contents altered during mode change -svga_prefix: .byte VIDEO_FIRST_BIOS>>8 # Default prefix for BIOS modes -graphic_mode: .byte 0 # Graphic mode with a linear frame buffer -dac_size: .byte 6 # DAC bit depth -vbe_version: .word 0 # VBE bios version - -# Status messages -keymsg: .ascii "Press <RETURN> to see video modes available, " - .ascii "<SPACE> to continue or wait 30 secs" - .byte 0x0d, 0x0a, 0 - -listhdr: .byte 0x0d, 0x0a - .ascii "Mode: COLSxROWS:" - -crlft: .byte 0x0d, 0x0a, 0 - -prompt: .byte 0x0d, 0x0a - .asciz "Enter mode number or `scan': " - -unknt: .asciz "Unknown mode ID. Try again." - -badmdt: .ascii "You passed an undefined mode number." - .byte 0x0d, 0x0a, 0 - -vesaer: .ascii "Error: Scanning of VESA modes failed. Please " - .ascii "report to <mj@ucw.cz>." - .byte 0x0d, 0x0a, 0 - -old_name: .asciz "CGA/MDA/HGA" - -ega_name: .asciz "EGA" - -svga_name: .ascii " " - -vga_name: .asciz "VGA" - -vesa_name: .asciz "VESA" - -name_bann: .asciz "Video adapter: " -#endif /* CONFIG_VIDEO_SELECT */ - -# Other variables: -adapter: .byte 0 # Video adapter: 0=CGA/MDA/HGA,1=EGA,2=VGA -video_segment: .word 0xb800 # Video memory segment -force_size: .word 0 # Use this size instead of the one in BIOS vars diff --git a/arch/i386/defconfig b/arch/i386/defconfig index 1a3a2217b7c2..54ee1764fdae 100644 --- a/arch/i386/defconfig +++ b/arch/i386/defconfig @@ -1,7 +1,7 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.22-rc2 -# Mon May 21 13:23:44 2007 +# Linux kernel version: 2.6.22-git14 +# Fri Jul 20 09:53:15 2007 # CONFIG_X86_32=y CONFIG_GENERIC_TIME=y @@ -37,19 +37,18 @@ CONFIG_LOCALVERSION="" CONFIG_LOCALVERSION_AUTO=y CONFIG_SWAP=y CONFIG_SYSVIPC=y -# CONFIG_IPC_NS is not set CONFIG_SYSVIPC_SYSCTL=y CONFIG_POSIX_MQUEUE=y # CONFIG_BSD_PROCESS_ACCT is not set # CONFIG_TASKSTATS is not set -# CONFIG_UTS_NS is not set +# CONFIG_USER_NS is not set # CONFIG_AUDIT is not set CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=18 # CONFIG_CPUSETS is not set CONFIG_SYSFS_DEPRECATED=y -# CONFIG_RELAY is not set +CONFIG_RELAY=y CONFIG_BLK_DEV_INITRD=y CONFIG_INITRAMFS_SOURCE="" CONFIG_CC_OPTIMIZE_FOR_SIZE=y @@ -73,16 +72,13 @@ CONFIG_TIMERFD=y CONFIG_EVENTFD=y CONFIG_SHMEM=y CONFIG_VM_EVENT_COUNTERS=y -CONFIG_SLAB=y -# CONFIG_SLUB is not set +CONFIG_SLUB_DEBUG=y +# CONFIG_SLAB is not set +CONFIG_SLUB=y # CONFIG_SLOB is not set CONFIG_RT_MUTEXES=y # CONFIG_TINY_SHMEM is not set CONFIG_BASE_SMALL=0 - -# -# Loadable module support -# CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y @@ -90,14 +86,11 @@ CONFIG_MODULE_FORCE_UNLOAD=y # CONFIG_MODULE_SRCVERSION_ALL is not set # CONFIG_KMOD is not set CONFIG_STOP_MACHINE=y - -# -# Block layer -# CONFIG_BLOCK=y CONFIG_LBD=y # CONFIG_BLK_DEV_IO_TRACE is not set # CONFIG_LSF is not set +# CONFIG_BLK_DEV_BSG is not set # # IO Schedulers @@ -166,7 +159,6 @@ CONFIG_X86_WP_WORKS_OK=y CONFIG_X86_INVLPG=y CONFIG_X86_BSWAP=y CONFIG_X86_POPAD_OK=y -CONFIG_X86_CMPXCHG64=y CONFIG_X86_GOOD_APIC=y CONFIG_X86_INTEL_USERCOPY=y CONFIG_X86_USE_PPRO_CHECKSUM=y @@ -202,6 +194,7 @@ CONFIG_X86_CPUID=y # CONFIG_EDD is not set # CONFIG_DELL_RBU is not set # CONFIG_DCDBAS is not set +CONFIG_DMIID=y # CONFIG_NOHIGHMEM is not set CONFIG_HIGHMEM4G=y # CONFIG_HIGHMEM64G is not set @@ -218,7 +211,9 @@ CONFIG_FLAT_NODE_MEM_MAP=y CONFIG_SPLIT_PTLOCK_CPUS=4 CONFIG_RESOURCES_64BIT=y CONFIG_ZONE_DMA_FLAG=1 +CONFIG_BOUNCE=y CONFIG_NR_QUICK=1 +CONFIG_VIRT_TO_BUS=y # CONFIG_HIGHPTE is not set # CONFIG_MATH_EMULATION is not set CONFIG_MTRR=y @@ -245,7 +240,6 @@ CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y CONFIG_PM=y CONFIG_PM_LEGACY=y # CONFIG_PM_DEBUG is not set -# CONFIG_PM_SYSFS_DEPRECATED is not set # # ACPI (Advanced Configuration and Power Interface) Support @@ -285,7 +279,7 @@ CONFIG_CPU_FREQ_GOV_PERFORMANCE=y # CONFIG_CPU_FREQ_GOV_POWERSAVE is not set CONFIG_CPU_FREQ_GOV_USERSPACE=y CONFIG_CPU_FREQ_GOV_ONDEMAND=y -# CONFIG_CPU_FREQ_GOV_CONSERVATIVE is not set +CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y # # CPUFreq processor drivers @@ -326,7 +320,7 @@ CONFIG_PCI_MMCONFIG=y CONFIG_ARCH_SUPPORTS_MSI=y CONFIG_PCI_MSI=y # CONFIG_PCI_DEBUG is not set -CONFIG_HT_IRQ=y +# CONFIG_HT_IRQ is not set CONFIG_ISA_DMA_API=y # CONFIG_ISA is not set # CONFIG_MCA is not set @@ -382,7 +376,7 @@ CONFIG_IP_PNP_DHCP=y CONFIG_INET_TUNNEL=y CONFIG_INET_XFRM_MODE_TRANSPORT=y CONFIG_INET_XFRM_MODE_TUNNEL=y -CONFIG_INET_XFRM_MODE_BEET=y +# CONFIG_INET_XFRM_MODE_BEET is not set CONFIG_INET_DIAG=y CONFIG_INET_TCP_DIAG=y # CONFIG_TCP_CONG_ADVANCED is not set @@ -401,27 +395,15 @@ CONFIG_IPV6=y # CONFIG_INET6_TUNNEL is not set CONFIG_INET6_XFRM_MODE_TRANSPORT=y CONFIG_INET6_XFRM_MODE_TUNNEL=y -CONFIG_INET6_XFRM_MODE_BEET=y +# CONFIG_INET6_XFRM_MODE_BEET is not set # CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION is not set CONFIG_IPV6_SIT=y # CONFIG_IPV6_TUNNEL is not set # CONFIG_IPV6_MULTIPLE_TABLES is not set # CONFIG_NETWORK_SECMARK is not set # CONFIG_NETFILTER is not set - -# -# DCCP Configuration (EXPERIMENTAL) -# # CONFIG_IP_DCCP is not set - -# -# SCTP Configuration (EXPERIMENTAL) -# # CONFIG_IP_SCTP is not set - -# -# TIPC Configuration (EXPERIMENTAL) -# # CONFIG_TIPC is not set # CONFIG_ATM is not set # CONFIG_BRIDGE is not set @@ -458,6 +440,7 @@ CONFIG_IPV6_SIT=y # CONFIG_MAC80211 is not set # CONFIG_IEEE80211 is not set # CONFIG_RFKILL is not set +# CONFIG_NET_9P is not set # # Device Drivers @@ -472,21 +455,9 @@ CONFIG_FW_LOADER=y # CONFIG_DEBUG_DRIVER is not set # CONFIG_DEBUG_DEVRES is not set # CONFIG_SYS_HYPERVISOR is not set - -# -# Connector - unified userspace <-> kernelspace linker -# # CONFIG_CONNECTOR is not set # CONFIG_MTD is not set - -# -# Parallel port support -# # CONFIG_PARPORT is not set - -# -# Plug and Play support -# CONFIG_PNP=y # CONFIG_PNP_DEBUG is not set @@ -494,10 +465,7 @@ CONFIG_PNP=y # Protocols # CONFIG_PNPACPI=y - -# -# Block devices -# +CONFIG_BLK_DEV=y CONFIG_BLK_DEV_FD=y # CONFIG_BLK_CPQ_DA is not set # CONFIG_BLK_CPQ_CISS_DA is not set @@ -515,17 +483,14 @@ CONFIG_BLK_DEV_RAM_SIZE=4096 CONFIG_BLK_DEV_RAM_BLOCKSIZE=1024 # CONFIG_CDROM_PKTCDVD is not set # CONFIG_ATA_OVER_ETH is not set - -# -# Misc devices -# +CONFIG_MISC_DEVICES=y # CONFIG_IBM_ASM is not set # CONFIG_PHANTOM is not set +# CONFIG_EEPROM_93CX6 is not set # CONFIG_SGI_IOC4 is not set # CONFIG_TIFM_CORE is not set # CONFIG_SONY_LAPTOP is not set # CONFIG_THINKPAD_ACPI is not set -# CONFIG_BLINK is not set CONFIG_IDE=y CONFIG_BLK_DEV_IDE=y @@ -597,6 +562,7 @@ CONFIG_BLK_DEV_IDEDMA=y # # CONFIG_RAID_ATTRS is not set CONFIG_SCSI=y +CONFIG_SCSI_DMA=y # CONFIG_SCSI_TGT is not set CONFIG_SCSI_NETLINK=y # CONFIG_SCSI_PROC_FS is not set @@ -607,8 +573,9 @@ CONFIG_SCSI_NETLINK=y CONFIG_BLK_DEV_SD=y # CONFIG_CHR_DEV_ST is not set # CONFIG_CHR_DEV_OSST is not set -# CONFIG_BLK_DEV_SR is not set -# CONFIG_CHR_DEV_SG is not set +CONFIG_BLK_DEV_SR=y +# CONFIG_BLK_DEV_SR_VENDOR is not set +CONFIG_CHR_DEV_SG=y # CONFIG_CHR_DEV_SCH is not set # @@ -668,6 +635,7 @@ CONFIG_AIC79XX_DEBUG_MASK=0 # CONFIG_SCSI_INIA100 is not set # CONFIG_SCSI_STEX is not set # CONFIG_SCSI_SYM53C8XX_2 is not set +# CONFIG_SCSI_IPR is not set # CONFIG_SCSI_QLOGIC_1280 is not set # CONFIG_SCSI_QLA_FC is not set # CONFIG_SCSI_QLA_ISCSI is not set @@ -676,14 +644,73 @@ CONFIG_AIC79XX_DEBUG_MASK=0 # CONFIG_SCSI_DC390T is not set # CONFIG_SCSI_NSP32 is not set # CONFIG_SCSI_DEBUG is not set -# CONFIG_SCSI_ESP_CORE is not set # CONFIG_SCSI_SRP is not set -# CONFIG_ATA is not set - -# -# Multi-device support (RAID and LVM) -# -# CONFIG_MD is not set +CONFIG_ATA=y +# CONFIG_ATA_NONSTANDARD is not set +CONFIG_ATA_ACPI=y +CONFIG_SATA_AHCI=y +CONFIG_SATA_SVW=y +CONFIG_ATA_PIIX=y +# CONFIG_SATA_MV is not set +CONFIG_SATA_NV=y +# CONFIG_PDC_ADMA is not set +# CONFIG_SATA_QSTOR is not set +# CONFIG_SATA_PROMISE is not set +# CONFIG_SATA_SX4 is not set +CONFIG_SATA_SIL=y +# CONFIG_SATA_SIL24 is not set +# CONFIG_SATA_SIS is not set +# CONFIG_SATA_ULI is not set +CONFIG_SATA_VIA=y +# CONFIG_SATA_VITESSE is not set +# CONFIG_SATA_INIC162X is not set +# CONFIG_PATA_ALI is not set +# CONFIG_PATA_AMD is not set +# CONFIG_PATA_ARTOP is not set +# CONFIG_PATA_ATIIXP is not set +# CONFIG_PATA_CMD640_PCI is not set +# CONFIG_PATA_CMD64X is not set +# CONFIG_PATA_CS5520 is not set +# CONFIG_PATA_CS5530 is not set +# CONFIG_PATA_CS5535 is not set +# CONFIG_PATA_CYPRESS is not set +# CONFIG_PATA_EFAR is not set +# CONFIG_ATA_GENERIC is not set +# CONFIG_PATA_HPT366 is not set +# CONFIG_PATA_HPT37X is not set +# CONFIG_PATA_HPT3X2N is not set +# CONFIG_PATA_HPT3X3 is not set +# CONFIG_PATA_IT821X is not set +# CONFIG_PATA_IT8213 is not set +# CONFIG_PATA_JMICRON is not set +# CONFIG_PATA_TRIFLEX is not set +# CONFIG_PATA_MARVELL is not set +# CONFIG_PATA_MPIIX is not set +# CONFIG_PATA_OLDPIIX is not set +# CONFIG_PATA_NETCELL is not set +# CONFIG_PATA_NS87410 is not set +# CONFIG_PATA_OPTI is not set +# CONFIG_PATA_OPTIDMA is not set +# CONFIG_PATA_PDC_OLD is not set +# CONFIG_PATA_RADISYS is not set +# CONFIG_PATA_RZ1000 is not set +# CONFIG_PATA_SC1200 is not set +# CONFIG_PATA_SERVERWORKS is not set +# CONFIG_PATA_PDC2027X is not set +# CONFIG_PATA_SIL680 is not set +# CONFIG_PATA_SIS is not set +# CONFIG_PATA_VIA is not set +# CONFIG_PATA_WINBOND is not set +CONFIG_MD=y +# CONFIG_BLK_DEV_MD is not set +CONFIG_BLK_DEV_DM=y +# CONFIG_DM_DEBUG is not set +# CONFIG_DM_CRYPT is not set +# CONFIG_DM_SNAPSHOT is not set +# CONFIG_DM_MIRROR is not set +# CONFIG_DM_ZERO is not set +# CONFIG_DM_MULTIPATH is not set +# CONFIG_DM_DELAY is not set # # Fusion MPT device support @@ -724,42 +751,27 @@ CONFIG_IEEE1394_OHCI1394=y # CONFIG_IEEE1394_ETH1394 is not set # CONFIG_IEEE1394_DV1394 is not set CONFIG_IEEE1394_RAWIO=y - -# -# I2O device support -# # CONFIG_I2O is not set -# CONFIG_MACINTOSH_DRIVERS is not set - -# -# Network device support -# +CONFIG_MACINTOSH_DRIVERS=y +# CONFIG_MAC_EMUMOUSEBTN is not set CONFIG_NETDEVICES=y +CONFIG_NETDEVICES_MULTIQUEUE=y # CONFIG_DUMMY is not set # CONFIG_BONDING is not set +# CONFIG_MACVLAN is not set # CONFIG_EQUALIZER is not set # CONFIG_TUN is not set # CONFIG_NET_SB1000 is not set - -# -# ARCnet devices -# # CONFIG_ARCNET is not set # CONFIG_PHYLIB is not set - -# -# Ethernet (10 or 100Mbit) -# CONFIG_NET_ETHERNET=y CONFIG_MII=y # CONFIG_HAPPYMEAL is not set # CONFIG_SUNGEM is not set # CONFIG_CASSINI is not set -# CONFIG_NET_VENDOR_3COM is not set - -# -# Tulip family network device support -# +CONFIG_NET_VENDOR_3COM=y +CONFIG_VORTEX=y +# CONFIG_TYPHOON is not set CONFIG_NET_TULIP=y # CONFIG_DE2104X is not set CONFIG_TULIP=y @@ -810,7 +822,6 @@ CONFIG_R8169=y # CONFIG_SIS190 is not set # CONFIG_SKGE is not set CONFIG_SKY2=y -# CONFIG_SK98LIN is not set # CONFIG_VIA_VELOCITY is not set CONFIG_TIGON3=y CONFIG_BNX2=y @@ -824,10 +835,6 @@ CONFIG_NETDEV_10000=y # CONFIG_MYRI10GE is not set # CONFIG_NETXEN_NIC is not set # CONFIG_MLX4_CORE is not set - -# -# Token Ring devices -# # CONFIG_TR is not set # @@ -856,15 +863,7 @@ CONFIG_NETCONSOLE=y CONFIG_NETPOLL=y # CONFIG_NETPOLL_TRAP is not set CONFIG_NET_POLL_CONTROLLER=y - -# -# ISDN subsystem -# # CONFIG_ISDN is not set - -# -# Telephony Support -# # CONFIG_PHONE is not set # @@ -872,6 +871,7 @@ CONFIG_NET_POLL_CONTROLLER=y # CONFIG_INPUT=y # CONFIG_INPUT_FF_MEMLESS is not set +# CONFIG_INPUT_POLLDEV is not set # # Userland interfaces @@ -937,6 +937,7 @@ CONFIG_HW_CONSOLE=y # CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_FIX_EARLYCON_MEM=y CONFIG_SERIAL_8250_PCI=y CONFIG_SERIAL_8250_PNP=y CONFIG_SERIAL_8250_NR_UARTS=4 @@ -952,10 +953,6 @@ CONFIG_SERIAL_CORE_CONSOLE=y CONFIG_UNIX98_PTYS=y CONFIG_LEGACY_PTYS=y CONFIG_LEGACY_PTY_COUNT=256 - -# -# IPMI -# # CONFIG_IPMI_HANDLER is not set # CONFIG_WATCHDOG is not set CONFIG_HW_RANDOM=y @@ -989,11 +986,7 @@ CONFIG_MAX_RAW_DEVS=256 CONFIG_HPET=y # CONFIG_HPET_RTC_IRQ is not set CONFIG_HPET_MMAP=y -CONFIG_HANGCHECK_TIMER=y - -# -# TPM devices -# +# CONFIG_HANGCHECK_TIMER is not set # CONFIG_TCG_TPM is not set # CONFIG_TELCLOCK is not set CONFIG_DEVPORT=y @@ -1004,11 +997,8 @@ CONFIG_DEVPORT=y # # CONFIG_SPI is not set # CONFIG_SPI_MASTER is not set - -# -# Dallas's 1-wire bus -# # CONFIG_W1 is not set +# CONFIG_POWER_SUPPLY is not set # CONFIG_HWMON is not set # @@ -1042,7 +1032,7 @@ CONFIG_DAB=y CONFIG_VGA_CONSOLE=y CONFIG_VGACON_SOFT_SCROLLBACK=y CONFIG_VGACON_SOFT_SCROLLBACK_SIZE=128 -# CONFIG_VIDEO_SELECT is not set +CONFIG_VIDEO_SELECT=y CONFIG_DUMMY_CONSOLE=y # @@ -1059,15 +1049,11 @@ CONFIG_SOUND=y # Open Sound System # CONFIG_SOUND_PRIME=y -# CONFIG_OSS_OBSOLETE is not set # CONFIG_SOUND_TRIDENT is not set # CONFIG_SOUND_MSNDCLAS is not set # CONFIG_SOUND_MSNDPIN is not set # CONFIG_SOUND_OSS is not set - -# -# HID Devices -# +CONFIG_HID_SUPPORT=y CONFIG_HID=y # CONFIG_HID_DEBUG is not set @@ -1078,10 +1064,7 @@ CONFIG_USB_HID=y # CONFIG_USB_HIDINPUT_POWERBOOK is not set # CONFIG_HID_FF is not set # CONFIG_USB_HIDDEV is not set - -# -# USB support -# +CONFIG_USB_SUPPORT=y CONFIG_USB_ARCH_HAS_HCD=y CONFIG_USB_ARCH_HAS_OHCI=y CONFIG_USB_ARCH_HAS_EHCI=y @@ -1095,6 +1078,7 @@ CONFIG_USB_DEVICEFS=y # CONFIG_USB_DEVICE_CLASS is not set # CONFIG_USB_DYNAMIC_MINORS is not set # CONFIG_USB_SUSPEND is not set +# CONFIG_USB_PERSIST is not set # CONFIG_USB_OTG is not set # @@ -1104,7 +1088,6 @@ CONFIG_USB_EHCI_HCD=y # CONFIG_USB_EHCI_SPLIT_ISO is not set # CONFIG_USB_EHCI_ROOT_HUB_TT is not set # CONFIG_USB_EHCI_TT_NEWSCHED is not set -# CONFIG_USB_EHCI_BIG_ENDIAN_MMIO is not set # CONFIG_USB_ISP116X_HCD is not set CONFIG_USB_OHCI_HCD=y # CONFIG_USB_OHCI_BIG_ENDIAN_DESC is not set @@ -1112,6 +1095,7 @@ CONFIG_USB_OHCI_HCD=y CONFIG_USB_OHCI_LITTLE_ENDIAN=y CONFIG_USB_UHCI_HCD=y # CONFIG_USB_SL811_HCD is not set +# CONFIG_USB_R8A66597_HCD is not set # # USB Device Class drivers @@ -1202,15 +1186,7 @@ CONFIG_USB_MON=y # # LED Triggers # - -# -# InfiniBand support -# # CONFIG_INFINIBAND is not set - -# -# EDAC - error detection and reporting (RAS) (EXPERIMENTAL) -# # CONFIG_EDAC is not set # @@ -1230,11 +1206,13 @@ CONFIG_USB_MON=y # # DMA Devices # +CONFIG_VIRTUALIZATION=y +# CONFIG_KVM is not set # -# Virtualization +# Userspace I/O # -# CONFIG_KVM is not set +# CONFIG_UIO is not set # # File systems @@ -1272,6 +1250,7 @@ CONFIG_DNOTIFY=y # CONFIG_AUTOFS_FS is not set CONFIG_AUTOFS4_FS=y # CONFIG_FUSE_FS is not set +CONFIG_GENERIC_ACL=y # # CD-ROM/DVD Filesystems @@ -1299,7 +1278,7 @@ CONFIG_PROC_KCORE=y CONFIG_PROC_SYSCTL=y CONFIG_SYSFS=y CONFIG_TMPFS=y -# CONFIG_TMPFS_POSIX_ACL is not set +CONFIG_TMPFS_POSIX_ACL=y CONFIG_HUGETLBFS=y CONFIG_HUGETLB_PAGE=y CONFIG_RAMFS=y @@ -1349,7 +1328,6 @@ CONFIG_SUNRPC=y # CONFIG_NCP_FS is not set # CONFIG_CODA_FS is not set # CONFIG_AFS_FS is not set -# CONFIG_9P_FS is not set # # Partition Types @@ -1405,10 +1383,7 @@ CONFIG_NLS_UTF8=y # Distributed Lock Manager # # CONFIG_DLM is not set - -# -# Instrumentation Support -# +CONFIG_INSTRUMENTATION=y CONFIG_PROFILING=y CONFIG_OPROFILE=y CONFIG_KPROBES=y @@ -1418,7 +1393,7 @@ CONFIG_KPROBES=y # CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set -CONFIG_ENABLE_MUST_CHECK=y +# CONFIG_ENABLE_MUST_CHECK is not set CONFIG_MAGIC_SYSRQ=y CONFIG_UNUSED_SYMBOLS=y # CONFIG_DEBUG_FS is not set @@ -1426,15 +1401,17 @@ CONFIG_UNUSED_SYMBOLS=y CONFIG_DEBUG_KERNEL=y # CONFIG_DEBUG_SHIRQ is not set CONFIG_DETECT_SOFTLOCKUP=y +# CONFIG_SCHED_DEBUG is not set # CONFIG_SCHEDSTATS is not set -# CONFIG_TIMER_STATS is not set -# CONFIG_DEBUG_SLAB is not set +CONFIG_TIMER_STATS=y +# CONFIG_SLUB_DEBUG_ON is not set # CONFIG_DEBUG_RT_MUTEXES is not set # CONFIG_RT_MUTEX_TESTER is not set # CONFIG_DEBUG_SPINLOCK is not set # CONFIG_DEBUG_MUTEXES is not set # CONFIG_DEBUG_LOCK_ALLOC is not set # CONFIG_PROVE_LOCKING is not set +# CONFIG_LOCK_STAT is not set # CONFIG_DEBUG_SPINLOCK_SLEEP is not set # CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set # CONFIG_DEBUG_KOBJECT is not set @@ -1444,7 +1421,6 @@ CONFIG_DEBUG_BUGVERBOSE=y # CONFIG_DEBUG_VM is not set # CONFIG_DEBUG_LIST is not set # CONFIG_FRAME_POINTER is not set -# CONFIG_UNWIND_INFO is not set # CONFIG_FORCED_INLINING is not set # CONFIG_RCU_TORTURE_TEST is not set # CONFIG_LKDTM is not set @@ -1463,10 +1439,6 @@ CONFIG_DOUBLEFAULT=y # # CONFIG_KEYS is not set # CONFIG_SECURITY is not set - -# -# Cryptographic options -# # CONFIG_CRYPTO is not set # @@ -1477,6 +1449,7 @@ CONFIG_BITREVERSE=y # CONFIG_CRC16 is not set # CONFIG_CRC_ITU_T is not set CONFIG_CRC32=y +# CONFIG_CRC7 is not set # CONFIG_LIBCRC32C is not set CONFIG_ZLIB_INFLATE=y CONFIG_PLIST=y diff --git a/arch/i386/kernel/Makefile b/arch/i386/kernel/Makefile index e9297cbfb6b9..9d33b00de659 100644 --- a/arch/i386/kernel/Makefile +++ b/arch/i386/kernel/Makefile @@ -39,6 +39,7 @@ obj-$(CONFIG_VM86) += vm86.o obj-$(CONFIG_EARLY_PRINTK) += early_printk.o obj-$(CONFIG_HPET_TIMER) += hpet.o obj-$(CONFIG_K8_NB) += k8.o +obj-$(CONFIG_MGEODE_LX) += geode.o obj-$(CONFIG_VMI) += vmi.o vmiclock.o obj-$(CONFIG_PARAVIRT) += paravirt.o diff --git a/arch/i386/kernel/acpi/boot.c b/arch/i386/kernel/acpi/boot.c index a574cd2c8b61..cacdd883bf2b 100644 --- a/arch/i386/kernel/acpi/boot.c +++ b/arch/i386/kernel/acpi/boot.c @@ -618,6 +618,8 @@ static int __init acpi_parse_sbf(struct acpi_table_header *table) #ifdef CONFIG_HPET_TIMER #include <asm/hpet.h> +static struct __initdata resource *hpet_res; + static int __init acpi_parse_hpet(struct acpi_table_header *table) { struct acpi_table_hpet *hpet_tbl; @@ -638,8 +640,42 @@ static int __init acpi_parse_hpet(struct acpi_table_header *table) printk(KERN_INFO PREFIX "HPET id: %#x base: %#lx\n", hpet_tbl->id, hpet_address); + /* + * Allocate and initialize the HPET firmware resource for adding into + * the resource tree during the lateinit timeframe. + */ +#define HPET_RESOURCE_NAME_SIZE 9 + hpet_res = alloc_bootmem(sizeof(*hpet_res) + HPET_RESOURCE_NAME_SIZE); + + if (!hpet_res) + return 0; + + memset(hpet_res, 0, sizeof(*hpet_res)); + hpet_res->name = (void *)&hpet_res[1]; + hpet_res->flags = IORESOURCE_MEM; + snprintf((char *)hpet_res->name, HPET_RESOURCE_NAME_SIZE, "HPET %u", + hpet_tbl->sequence); + + hpet_res->start = hpet_address; + hpet_res->end = hpet_address + (1 * 1024) - 1; + return 0; } + +/* + * hpet_insert_resource inserts the HPET resources used into the resource + * tree. + */ +static __init int hpet_insert_resource(void) +{ + if (!hpet_res) + return 1; + + return insert_resource(&iomem_resource, hpet_res); +} + +late_initcall(hpet_insert_resource); + #else #define acpi_parse_hpet NULL #endif @@ -950,14 +986,6 @@ static struct dmi_system_id __initdata acpi_dmi_table[] = { }, { .callback = force_acpi_ht, - .ident = "DELL GX240", - .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "Dell Computer Corporation"), - DMI_MATCH(DMI_BOARD_NAME, "OptiPlex GX240"), - }, - }, - { - .callback = force_acpi_ht, .ident = "HP VISUALIZE NT Workstation", .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "Hewlett-Packard"), diff --git a/arch/i386/kernel/acpi/sleep.c b/arch/i386/kernel/acpi/sleep.c index 4ee83577bf61..c42b5ab49deb 100644 --- a/arch/i386/kernel/acpi/sleep.c +++ b/arch/i386/kernel/acpi/sleep.c @@ -14,7 +14,7 @@ /* address in low memory of the wakeup routine. */ unsigned long acpi_wakeup_address = 0; -unsigned long acpi_video_flags; +unsigned long acpi_realmode_flags; extern char wakeup_start, wakeup_end; extern unsigned long FASTCALL(acpi_copy_wakeup_routine(unsigned long)); @@ -68,9 +68,11 @@ static int __init acpi_sleep_setup(char *str) { while ((str != NULL) && (*str != '\0')) { if (strncmp(str, "s3_bios", 7) == 0) - acpi_video_flags = 1; + acpi_realmode_flags |= 1; if (strncmp(str, "s3_mode", 7) == 0) - acpi_video_flags |= 2; + acpi_realmode_flags |= 2; + if (strncmp(str, "s3_beep", 7) == 0) + acpi_realmode_flags |= 4; str = strchr(str, ','); if (str != NULL) str += strspn(str, ", \t"); @@ -80,9 +82,11 @@ static int __init acpi_sleep_setup(char *str) __setup("acpi_sleep=", acpi_sleep_setup); +/* Ouch, we want to delete this. We already have better version in userspace, in + s2ram from suspend.sf.net project */ static __init int reset_videomode_after_s3(struct dmi_system_id *d) { - acpi_video_flags |= 2; + acpi_realmode_flags |= 2; return 0; } diff --git a/arch/i386/kernel/acpi/wakeup.S b/arch/i386/kernel/acpi/wakeup.S index a2295a34b2c7..f22ba8534d26 100644 --- a/arch/i386/kernel/acpi/wakeup.S +++ b/arch/i386/kernel/acpi/wakeup.S @@ -13,6 +13,21 @@ # cs = 0x1234, eip = 0x05 # +#define BEEP \ + inb $97, %al; \ + outb %al, $0x80; \ + movb $3, %al; \ + outb %al, $97; \ + outb %al, $0x80; \ + movb $-74, %al; \ + outb %al, $67; \ + outb %al, $0x80; \ + movb $-119, %al; \ + outb %al, $66; \ + outb %al, $0x80; \ + movb $15, %al; \ + outb %al, $66; + ALIGN .align 4096 ENTRY(wakeup_start) @@ -31,6 +46,11 @@ wakeup_code: movw %cs, %ax movw %ax, %ds # Make ds:0 point to wakeup_start movw %ax, %ss + + testl $4, realmode_flags - wakeup_code + jz 1f + BEEP +1: mov $(wakeup_stack - wakeup_code), %sp # Private stack is needed for ASUS board movw $0x0e00 + 'S', %fs:(0x12) @@ -41,7 +61,7 @@ wakeup_code: cmpl $0x12345678, %eax jne bogus_real_magic - testl $1, video_flags - wakeup_code + testl $1, realmode_flags - wakeup_code jz 1f lcall $0xc000,$3 movw %cs, %ax @@ -49,7 +69,7 @@ wakeup_code: movw %ax, %ss 1: - testl $2, video_flags - wakeup_code + testl $2, realmode_flags - wakeup_code jz 1f mov video_mode - wakeup_code, %ax call mode_set @@ -88,7 +108,11 @@ wakeup_code: cmpl $0x12345678, %eax jne bogus_real_magic - ljmpl $__KERNEL_CS,$wakeup_pmode_return + testl $8, realmode_flags - wakeup_code + jz 1f + BEEP +1: + ljmpl $__KERNEL_CS, $wakeup_pmode_return real_save_gdt: .word 0 .long 0 @@ -97,7 +121,8 @@ real_save_cr3: .long 0 real_save_cr4: .long 0 real_magic: .long 0 video_mode: .long 0 -video_flags: .long 0 +realmode_flags: .long 0 +beep_flags: .long 0 real_efer_save_restore: .long 0 real_save_efer_edx: .long 0 real_save_efer_eax: .long 0 @@ -126,51 +151,30 @@ bogus_real_magic: #define VIDEO_FIRST_V7 0x0900 # Setting of user mode (AX=mode ID) => CF=success + +# For now, we only handle VESA modes (0x0200..0x03ff). To handle other +# modes, we should probably compile in the video code from the boot +# directory. mode_set: 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_vesa -#if 0 - orb %ah, %ah - jz setmenu -#endif - - decb %ah -# jz setbios Add bios modes later + subb $VIDEO_FIRST_VESA>>8, %bh + cmpb $2, %bh + jb check_vesa -setbad: clc +setbad: + clc ret check_vesa: - 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 _setbad # AH=0 if OK + jnz setbad # AH=0 if OK stc ret -_setbad: jmp setbad - .code32 ALIGN @@ -260,8 +264,8 @@ ENTRY(acpi_copy_wakeup_routine) movl saved_videomode, %edx movl %edx, video_mode - wakeup_start (%eax) - movl acpi_video_flags, %edx - movl %edx, video_flags - wakeup_start (%eax) + movl acpi_realmode_flags, %edx + movl %edx, realmode_flags - wakeup_start (%eax) movl $0x12345678, real_magic - wakeup_start (%eax) movl $0x12345678, saved_magic popl %ebx diff --git a/arch/i386/kernel/alternative.c b/arch/i386/kernel/alternative.c index d8cda14fff8b..bd72d94e713e 100644 --- a/arch/i386/kernel/alternative.c +++ b/arch/i386/kernel/alternative.c @@ -2,12 +2,19 @@ #include <linux/sched.h> #include <linux/spinlock.h> #include <linux/list.h> +#include <linux/kprobes.h> +#include <linux/mm.h> +#include <linux/vmalloc.h> #include <asm/alternative.h> #include <asm/sections.h> +#include <asm/pgtable.h> +#include <asm/mce.h> +#include <asm/nmi.h> -static int noreplace_smp = 0; -static int smp_alt_once = 0; -static int debug_alternative = 0; +#define MAX_PATCH_LEN (255-1) + +#ifdef CONFIG_HOTPLUG_CPU +static int smp_alt_once; static int __init bootonly(char *str) { @@ -15,6 +22,11 @@ static int __init bootonly(char *str) return 1; } __setup("smp-alt-boot", bootonly); +#else +#define smp_alt_once 1 +#endif + +static int debug_alternative; static int __init debug_alt(char *str) { @@ -23,6 +35,8 @@ static int __init debug_alt(char *str) } __setup("debug-alternative", debug_alt); +static int noreplace_smp; + static int __init setup_noreplace_smp(char *str) { noreplace_smp = 1; @@ -136,7 +150,8 @@ static unsigned char** find_nop_table(void) #endif /* CONFIG_X86_64 */ -static void nop_out(void *insns, unsigned int len) +/* Use this to add nops to a buffer, then text_poke the whole buffer. */ +static void add_nops(void *insns, unsigned int len) { unsigned char **noptable = find_nop_table(); @@ -162,15 +177,15 @@ extern u8 *__smp_locks[], *__smp_locks_end[]; void apply_alternatives(struct alt_instr *start, struct alt_instr *end) { struct alt_instr *a; - u8 *instr; - int diff; + char insnbuf[MAX_PATCH_LEN]; DPRINTK("%s: alt table %p -> %p\n", __FUNCTION__, start, end); for (a = start; a < end; a++) { + u8 *instr = a->instr; BUG_ON(a->replacementlen > a->instrlen); + BUG_ON(a->instrlen > sizeof(insnbuf)); if (!boot_cpu_has(a->cpuid)) continue; - instr = a->instr; #ifdef CONFIG_X86_64 /* vsyscall code is not mapped yet. resolve it manually. */ if (instr >= (u8 *)VSYSCALL_START && instr < (u8*)VSYSCALL_END) { @@ -179,9 +194,10 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end) __FUNCTION__, a->instr, instr); } #endif - memcpy(instr, a->replacement, a->replacementlen); - diff = a->instrlen - a->replacementlen; - nop_out(instr + a->replacementlen, diff); + memcpy(insnbuf, a->replacement, a->replacementlen); + add_nops(insnbuf + a->replacementlen, + a->instrlen - a->replacementlen); + text_poke(instr, insnbuf, a->instrlen); } } @@ -196,23 +212,25 @@ static void alternatives_smp_lock(u8 **start, u8 **end, u8 *text, u8 *text_end) continue; if (*ptr > text_end) continue; - **ptr = 0xf0; /* lock prefix */ + text_poke(*ptr, ((unsigned char []){0xf0}), 1); /* add lock prefix */ }; } static void alternatives_smp_unlock(u8 **start, u8 **end, u8 *text, u8 *text_end) { u8 **ptr; + char insn[1]; if (noreplace_smp) return; + add_nops(insn, 1); for (ptr = start; ptr < end; ptr++) { if (*ptr < text) continue; if (*ptr > text_end) continue; - nop_out(*ptr, 1); + text_poke(*ptr, insn, 1); }; } @@ -339,6 +357,7 @@ void apply_paravirt(struct paravirt_patch_site *start, struct paravirt_patch_site *end) { struct paravirt_patch_site *p; + char insnbuf[MAX_PATCH_LEN]; if (noreplace_paravirt) return; @@ -346,18 +365,18 @@ void apply_paravirt(struct paravirt_patch_site *start, for (p = start; p < end; p++) { unsigned int used; - used = paravirt_ops.patch(p->instrtype, p->clobbers, p->instr, - p->len); + BUG_ON(p->len > MAX_PATCH_LEN); + /* prep the buffer with the original instructions */ + memcpy(insnbuf, p->instr, p->len); + used = paravirt_ops.patch(p->instrtype, p->clobbers, insnbuf, + (unsigned long)p->instr, p->len); BUG_ON(used > p->len); /* Pad the rest with nops */ - nop_out(p->instr + used, p->len - used); + add_nops(insnbuf + used, p->len - used); + text_poke(p->instr, insnbuf, p->len); } - - /* Sync to be conservative, in case we patched following - * instructions */ - sync_core(); } extern struct paravirt_patch_site __start_parainstructions[], __stop_parainstructions[]; @@ -367,6 +386,14 @@ void __init alternative_instructions(void) { unsigned long flags; + /* The patching is not fully atomic, so try to avoid local interruptions + that might execute the to be patched code. + Other CPUs are not running. */ + stop_nmi(); +#ifdef CONFIG_X86_MCE + stop_mce(); +#endif + local_irq_save(flags); apply_alternatives(__alt_instructions, __alt_instructions_end); @@ -376,8 +403,6 @@ void __init alternative_instructions(void) #ifdef CONFIG_HOTPLUG_CPU if (num_possible_cpus() < 2) smp_alt_once = 1; -#else - smp_alt_once = 1; #endif #ifdef CONFIG_SMP @@ -401,4 +426,25 @@ void __init alternative_instructions(void) #endif apply_paravirt(__parainstructions, __parainstructions_end); local_irq_restore(flags); + + restart_nmi(); +#ifdef CONFIG_X86_MCE + restart_mce(); +#endif +} + +/* + * Warning: + * When you use this code to patch more than one byte of an instruction + * you need to make sure that other CPUs cannot execute this code in parallel. + * Also no thread must be currently preempted in the middle of these instructions. + * And on the local CPU you need to be protected again NMI or MCE handlers + * seeing an inconsistent instruction while you patch. + */ +void __kprobes text_poke(void *addr, unsigned char *opcode, int len) +{ + memcpy(addr, opcode, len); + sync_core(); + /* Could also do a CLFLUSH here to speed up CPU recovery; but + that causes hangs on some VIA CPUs. */ } diff --git a/arch/i386/kernel/apic.c b/arch/i386/kernel/apic.c index 67824f3bb974..3d67ae18d762 100644 --- a/arch/i386/kernel/apic.c +++ b/arch/i386/kernel/apic.c @@ -61,8 +61,9 @@ static int enable_local_apic __initdata = 0; /* Local APIC timer verification ok */ static int local_apic_timer_verify_ok; -/* Disable local APIC timer from the kernel commandline or via dmi quirk */ -static int local_apic_timer_disabled; +/* Disable local APIC timer from the kernel commandline or via dmi quirk + or using CPU MSR check */ +int local_apic_timer_disabled; /* Local APIC timer works in C2 */ int local_apic_timer_c2_ok; EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok); @@ -263,6 +264,9 @@ static void lapic_timer_setup(enum clock_event_mode mode, v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR); apic_write_around(APIC_LVTT, v); break; + case CLOCK_EVT_MODE_RESUME: + /* Nothing to do here */ + break; } local_irq_restore(flags); @@ -315,7 +319,7 @@ static void __devinit setup_APIC_timer(void) #define LAPIC_CAL_LOOPS (HZ/10) -static __initdata volatile int lapic_cal_loops = -1; +static __initdata int lapic_cal_loops = -1; static __initdata long lapic_cal_t1, lapic_cal_t2; static __initdata unsigned long long lapic_cal_tsc1, lapic_cal_tsc2; static __initdata unsigned long lapic_cal_pm1, lapic_cal_pm2; @@ -367,12 +371,9 @@ void __init setup_boot_APIC_clock(void) long delta, deltapm; int pm_referenced = 0; - if (boot_cpu_has(X86_FEATURE_LAPIC_TIMER_BROKEN)) - local_apic_timer_disabled = 1; - /* * The local apic timer can be disabled via the kernel - * commandline or from the test above. Register the lapic + * commandline or from the CPU detection code. Register the lapic * timer as a dummy clock event source on SMP systems, so the * broadcast mechanism is used. On UP systems simply ignore it. */ @@ -485,7 +486,7 @@ void __init setup_boot_APIC_clock(void) /* Let the interrupts run */ local_irq_enable(); - while(lapic_cal_loops <= LAPIC_CAL_LOOPS) + while (lapic_cal_loops <= LAPIC_CAL_LOOPS) cpu_relax(); local_irq_disable(); @@ -521,6 +522,9 @@ void __init setup_boot_APIC_clock(void) */ if (nmi_watchdog != NMI_IO_APIC) lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY; + else + printk(KERN_WARNING "APIC timer registered as dummy," + " due to nmi_watchdog=1!\n"); } /* Setup the lapic or request the broadcast */ @@ -1081,7 +1085,7 @@ static int __init detect_init_APIC (void) if (l & MSR_IA32_APICBASE_ENABLE) mp_lapic_addr = l & MSR_IA32_APICBASE_BASE; - if (nmi_watchdog != NMI_NONE) + if (nmi_watchdog != NMI_NONE && nmi_watchdog != NMI_DISABLED) nmi_watchdog = NMI_LOCAL_APIC; printk(KERN_INFO "Found and enabled local APIC!\n"); diff --git a/arch/i386/kernel/apm.c b/arch/i386/kernel/apm.c index 4112afe712b9..f02a8aca826b 100644 --- a/arch/i386/kernel/apm.c +++ b/arch/i386/kernel/apm.c @@ -222,6 +222,7 @@ #include <linux/capability.h> #include <linux/device.h> #include <linux/kernel.h> +#include <linux/freezer.h> #include <linux/smp.h> #include <linux/dmi.h> #include <linux/suspend.h> @@ -2234,7 +2235,7 @@ static int __init apm_init(void) apm_info.bios.cseg_16_len = 0; /* 64k */ if (debug) { - printk(KERN_INFO "apm: entry %x:%lx cseg16 %x dseg %x", + printk(KERN_INFO "apm: entry %x:%x cseg16 %x dseg %x", apm_info.bios.cseg, apm_info.bios.offset, apm_info.bios.cseg_16, apm_info.bios.dseg); if (apm_info.bios.version > 0x100) @@ -2311,7 +2312,6 @@ static int __init apm_init(void) remove_proc_entry("apm", NULL); return err; } - kapmd_task->flags |= PF_NOFREEZE; wake_up_process(kapmd_task); if (num_online_cpus() > 1 && !smp ) { diff --git a/arch/i386/kernel/asm-offsets.c b/arch/i386/kernel/asm-offsets.c index 27a776c9044d..7288ac88d746 100644 --- a/arch/i386/kernel/asm-offsets.c +++ b/arch/i386/kernel/asm-offsets.c @@ -17,6 +17,13 @@ #include <asm/thread_info.h> #include <asm/elf.h> +#include <xen/interface/xen.h> + +#ifdef CONFIG_LGUEST_GUEST +#include <linux/lguest.h> +#include "../../../drivers/lguest/lg.h" +#endif + #define DEFINE(sym, val) \ asm volatile("\n->" #sym " %0 " #val : : "i" (val)) @@ -59,6 +66,7 @@ void foo(void) OFFSET(TI_addr_limit, thread_info, addr_limit); OFFSET(TI_restart_block, thread_info, restart_block); OFFSET(TI_sysenter_return, thread_info, sysenter_return); + OFFSET(TI_cpu, thread_info, cpu); BLANK(); OFFSET(GDS_size, Xgt_desc_struct, size); @@ -115,4 +123,25 @@ void foo(void) OFFSET(PARAVIRT_iret, paravirt_ops, iret); OFFSET(PARAVIRT_read_cr0, paravirt_ops, read_cr0); #endif + +#ifdef CONFIG_XEN + BLANK(); + OFFSET(XEN_vcpu_info_mask, vcpu_info, evtchn_upcall_mask); + OFFSET(XEN_vcpu_info_pending, vcpu_info, evtchn_upcall_pending); +#endif + +#ifdef CONFIG_LGUEST_GUEST + BLANK(); + OFFSET(LGUEST_DATA_irq_enabled, lguest_data, irq_enabled); + OFFSET(LGUEST_PAGES_host_gdt_desc, lguest_pages, state.host_gdt_desc); + OFFSET(LGUEST_PAGES_host_idt_desc, lguest_pages, state.host_idt_desc); + OFFSET(LGUEST_PAGES_host_cr3, lguest_pages, state.host_cr3); + OFFSET(LGUEST_PAGES_host_sp, lguest_pages, state.host_sp); + OFFSET(LGUEST_PAGES_guest_gdt_desc, lguest_pages,state.guest_gdt_desc); + OFFSET(LGUEST_PAGES_guest_idt_desc, lguest_pages,state.guest_idt_desc); + OFFSET(LGUEST_PAGES_guest_gdt, lguest_pages, state.guest_gdt); + OFFSET(LGUEST_PAGES_regs_trapnum, lguest_pages, regs.trapnum); + OFFSET(LGUEST_PAGES_regs_errcode, lguest_pages, regs.errcode); + OFFSET(LGUEST_PAGES_regs, lguest_pages, regs); +#endif } diff --git a/arch/i386/kernel/cpu/Makefile b/arch/i386/kernel/cpu/Makefile index 74f27a463db0..778396c78d65 100644 --- a/arch/i386/kernel/cpu/Makefile +++ b/arch/i386/kernel/cpu/Makefile @@ -8,8 +8,7 @@ obj-y += amd.o obj-y += cyrix.o obj-y += centaur.o obj-y += transmeta.o -obj-y += intel.o intel_cacheinfo.o -obj-y += rise.o +obj-y += intel.o intel_cacheinfo.o addon_cpuid_features.o obj-y += nexgen.o obj-y += umc.o diff --git a/arch/i386/kernel/cpu/amd.c b/arch/i386/kernel/cpu/amd.c index 6f47eeeb93ea..dcf6bbb1c7c0 100644 --- a/arch/i386/kernel/cpu/amd.c +++ b/arch/i386/kernel/cpu/amd.c @@ -3,6 +3,7 @@ #include <linux/mm.h> #include <asm/io.h> #include <asm/processor.h> +#include <asm/apic.h> #include "cpu.h" @@ -22,6 +23,7 @@ extern void vide(void); __asm__(".align 4\nvide: ret"); +#ifdef CONFIG_X86_LOCAL_APIC #define ENABLE_C1E_MASK 0x18000000 #define CPUID_PROCESSOR_SIGNATURE 1 #define CPUID_XFAM 0x0ff00000 @@ -52,6 +54,7 @@ static __cpuinit int amd_apic_timer_broken(void) } return 0; } +#endif int force_mwait __cpuinitdata; @@ -231,6 +234,9 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) switch (c->x86) { case 15: + /* Use K8 tuning for Fam10h and Fam11h */ + case 0x10: + case 0x11: set_bit(X86_FEATURE_K8, c->x86_capability); break; case 6: @@ -272,11 +278,17 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) } #endif - if (cpuid_eax(0x80000000) >= 0x80000006) - num_cache_leaves = 3; + if (cpuid_eax(0x80000000) >= 0x80000006) { + if ((c->x86 == 0x10) && (cpuid_edx(0x80000006) & 0xf000)) + num_cache_leaves = 4; + else + num_cache_leaves = 3; + } +#ifdef CONFIG_X86_LOCAL_APIC if (amd_apic_timer_broken()) - set_bit(X86_FEATURE_LAPIC_TIMER_BROKEN, c->x86_capability); + local_apic_timer_disabled = 1; +#endif if (c->x86 == 0x10 && !force_mwait) clear_bit(X86_FEATURE_MWAIT, c->x86_capability); diff --git a/arch/i386/kernel/cpu/bugs.c b/arch/i386/kernel/cpu/bugs.c index 54428a2500f3..59266f03d1cd 100644 --- a/arch/i386/kernel/cpu/bugs.c +++ b/arch/i386/kernel/cpu/bugs.c @@ -11,6 +11,7 @@ */ #include <linux/init.h> #include <linux/utsname.h> +#include <asm/bugs.h> #include <asm/processor.h> #include <asm/i387.h> #include <asm/msr.h> diff --git a/arch/i386/kernel/cpu/common.c b/arch/i386/kernel/cpu/common.c index 794d593c47eb..d506201d397c 100644 --- a/arch/i386/kernel/cpu/common.c +++ b/arch/i386/kernel/cpu/common.c @@ -353,6 +353,8 @@ static void __cpuinit generic_identify(struct cpuinfo_x86 * c) if ( xlvl >= 0x80000004 ) get_model_name(c); /* Default name */ } + + init_scattered_cpuid_features(c); } early_intel_workaround(c); @@ -604,7 +606,6 @@ extern int nsc_init_cpu(void); extern int amd_init_cpu(void); extern int centaur_init_cpu(void); extern int transmeta_init_cpu(void); -extern int rise_init_cpu(void); extern int nexgen_init_cpu(void); extern int umc_init_cpu(void); @@ -616,7 +617,6 @@ void __init early_cpu_init(void) amd_init_cpu(); centaur_init_cpu(); transmeta_init_cpu(); - rise_init_cpu(); nexgen_init_cpu(); umc_init_cpu(); early_cpu_detect(); diff --git a/arch/i386/kernel/cpu/cpufreq/Kconfig b/arch/i386/kernel/cpu/cpufreq/Kconfig index e912aae9473c..d8c6f132dc7a 100644 --- a/arch/i386/kernel/cpu/cpufreq/Kconfig +++ b/arch/i386/kernel/cpu/cpufreq/Kconfig @@ -90,10 +90,17 @@ config X86_POWERNOW_K8 If in doubt, say N. config X86_POWERNOW_K8_ACPI - bool - depends on X86_POWERNOW_K8 && ACPI_PROCESSOR - depends on !(X86_POWERNOW_K8 = y && ACPI_PROCESSOR = m) + bool "ACPI Support" + select ACPI_PROCESSOR + depends on ACPI && X86_POWERNOW_K8 default y + help + This provides access to the K8s Processor Performance States via ACPI. + This driver is probably required for CPUFreq to work with multi-socket and + SMP systems. It is not required on at least some single-socket yet + multi-core systems, even if SMP is enabled. + + It is safe to say Y here. config X86_GX_SUSPMOD tristate "Cyrix MediaGX/NatSemi Geode Suspend Modulation" @@ -109,7 +116,7 @@ config X86_GX_SUSPMOD config X86_SPEEDSTEP_CENTRINO tristate "Intel Enhanced SpeedStep" select CPU_FREQ_TABLE - select X86_SPEEDSTEP_CENTRINO_TABLE if (!X86_SPEEDSTEP_CENTRINO_ACPI) + select X86_SPEEDSTEP_CENTRINO_TABLE help This adds the CPUFreq driver for Enhanced SpeedStep enabled mobile CPUs. This means Intel Pentium M (Centrino) CPUs. However, @@ -121,20 +128,6 @@ config X86_SPEEDSTEP_CENTRINO If in doubt, say N. -config X86_SPEEDSTEP_CENTRINO_ACPI - bool "Use ACPI tables to decode valid frequency/voltage (deprecated)" - depends on X86_SPEEDSTEP_CENTRINO && ACPI_PROCESSOR - depends on !(X86_SPEEDSTEP_CENTRINO = y && ACPI_PROCESSOR = m) - help - This is deprecated and this functionality is now merged into - acpi_cpufreq (X86_ACPI_CPUFREQ). Use that driver instead of - speedstep_centrino. - Use primarily the information provided in the BIOS ACPI tables - to determine valid CPU frequency and voltage pairings. It is - required for the driver to work on non-Banias CPUs. - - If in doubt, say Y. - config X86_SPEEDSTEP_CENTRINO_TABLE bool "Built-in tables for Banias CPUs" depends on X86_SPEEDSTEP_CENTRINO @@ -230,7 +223,7 @@ comment "shared options" config X86_ACPI_CPUFREQ_PROC_INTF bool "/proc/acpi/processor/../performance interface (deprecated)" depends on PROC_FS - depends on X86_ACPI_CPUFREQ || X86_SPEEDSTEP_CENTRINO_ACPI || X86_POWERNOW_K7_ACPI || X86_POWERNOW_K8_ACPI + depends on X86_ACPI_CPUFREQ || X86_POWERNOW_K7_ACPI || X86_POWERNOW_K8_ACPI help This enables the deprecated /proc/acpi/processor/../performance interface. While it is helpful for debugging, the generic, diff --git a/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c index 18c8b67ea3a7..705e13a30781 100644 --- a/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -68,7 +68,8 @@ struct acpi_cpufreq_data { }; static struct acpi_cpufreq_data *drv_data[NR_CPUS]; -static struct acpi_processor_performance *acpi_perf_data[NR_CPUS]; +/* acpi_perf_data is a pointer to percpu data. */ +static struct acpi_processor_performance *acpi_perf_data; static struct cpufreq_driver acpi_cpufreq_driver; @@ -508,26 +509,14 @@ acpi_cpufreq_guess_freq(struct acpi_cpufreq_data *data, unsigned int cpu) * do _PDC and _PSD and find out the processor dependency for the * actual init that will happen later... */ -static int acpi_cpufreq_early_init(void) +static int __init acpi_cpufreq_early_init(void) { - struct acpi_processor_performance *data; - cpumask_t covered; - unsigned int i, j; - dprintk("acpi_cpufreq_early_init\n"); - for_each_possible_cpu(i) { - data = kzalloc(sizeof(struct acpi_processor_performance), - GFP_KERNEL); - if (!data) { - for_each_cpu_mask(j, covered) { - kfree(acpi_perf_data[j]); - acpi_perf_data[j] = NULL; - } - return -ENOMEM; - } - acpi_perf_data[i] = data; - cpu_set(i, covered); + acpi_perf_data = alloc_percpu(struct acpi_processor_performance); + if (!acpi_perf_data) { + dprintk("Memory allocation error for acpi_perf_data.\n"); + return -ENOMEM; } /* Do initialization in ACPI core */ @@ -576,14 +565,11 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) dprintk("acpi_cpufreq_cpu_init\n"); - if (!acpi_perf_data[cpu]) - return -ENODEV; - data = kzalloc(sizeof(struct acpi_cpufreq_data), GFP_KERNEL); if (!data) return -ENOMEM; - data->acpi_data = acpi_perf_data[cpu]; + data->acpi_data = percpu_ptr(acpi_perf_data, cpu); drv_data[cpu] = data; if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) @@ -665,8 +651,8 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) data->max_freq = perf->states[0].core_frequency * 1000; /* table init */ for (i=0; i<perf->state_count; i++) { - if (i>0 && perf->states[i].core_frequency == - perf->states[i-1].core_frequency) + if (i>0 && perf->states[i].core_frequency >= + data->freq_table[valid_states-1].frequency / 1000) continue; data->freq_table[valid_states].index = i; @@ -780,24 +766,25 @@ static struct cpufreq_driver acpi_cpufreq_driver = { static int __init acpi_cpufreq_init(void) { + int ret; + dprintk("acpi_cpufreq_init\n"); - acpi_cpufreq_early_init(); + ret = acpi_cpufreq_early_init(); + if (ret) + return ret; return cpufreq_register_driver(&acpi_cpufreq_driver); } static void __exit acpi_cpufreq_exit(void) { - unsigned int i; dprintk("acpi_cpufreq_exit\n"); cpufreq_unregister_driver(&acpi_cpufreq_driver); - for_each_possible_cpu(i) { - kfree(acpi_perf_data[i]); - acpi_perf_data[i] = NULL; - } + free_percpu(acpi_perf_data); + return; } diff --git a/arch/i386/kernel/cpu/cpufreq/cpufreq-nforce2.c b/arch/i386/kernel/cpu/cpufreq/cpufreq-nforce2.c index 0d49d73d1b71..66acd5039918 100644 --- a/arch/i386/kernel/cpu/cpufreq/cpufreq-nforce2.c +++ b/arch/i386/kernel/cpu/cpufreq/cpufreq-nforce2.c @@ -391,8 +391,6 @@ static struct cpufreq_driver nforce2_driver = { */ static unsigned int nforce2_detect_chipset(void) { - u8 revision; - nforce2_chipset_dev = pci_get_subsys(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NFORCE2, PCI_ANY_ID, PCI_ANY_ID, NULL); @@ -400,10 +398,8 @@ static unsigned int nforce2_detect_chipset(void) if (nforce2_chipset_dev == NULL) return -ENODEV; - pci_read_config_byte(nforce2_chipset_dev, PCI_REVISION_ID, &revision); - printk(KERN_INFO "cpufreq: Detected nForce2 chipset revision %X\n", - revision); + nforce2_chipset_dev->revision); printk(KERN_INFO "cpufreq: FSB changing is maybe unstable and can lead to crashes and data loss.\n"); diff --git a/arch/i386/kernel/cpu/cpufreq/gx-suspmod.c b/arch/i386/kernel/cpu/cpufreq/gx-suspmod.c index 6667e9cceb9f..461dabc4e495 100644 --- a/arch/i386/kernel/cpu/cpufreq/gx-suspmod.c +++ b/arch/i386/kernel/cpu/cpufreq/gx-suspmod.c @@ -79,7 +79,7 @@ #include <linux/smp.h> #include <linux/cpufreq.h> #include <linux/pci.h> -#include <asm/processor.h> +#include <asm/processor-cyrix.h> #include <asm/errno.h> /* PCI config registers, all at F0 */ @@ -115,7 +115,6 @@ struct gxfreq_params { u8 pci_suscfg; u8 pci_pmer1; u8 pci_pmer2; - u8 pci_rev; struct pci_dev *cs55x0; }; @@ -276,7 +275,7 @@ static void gx_set_cpuspeed(unsigned int khz) pci_write_config_byte(gx_params->cs55x0, PCI_VIDTC, 100);/* typical 50 to 100ms */ pci_write_config_byte(gx_params->cs55x0, PCI_PMER1, pmer1); - if (gx_params->pci_rev < 0x10) { /* CS5530(rev 1.2, 1.3) */ + if (gx_params->cs55x0->revision < 0x10) { /* CS5530(rev 1.2, 1.3) */ suscfg = gx_params->pci_suscfg | SUSMOD; } else { /* CS5530A,B.. */ suscfg = gx_params->pci_suscfg | SUSMOD | PWRSVE; @@ -471,7 +470,6 @@ static int __init cpufreq_gx_init(void) pci_read_config_byte(params->cs55x0, PCI_PMER2, &(params->pci_pmer2)); pci_read_config_byte(params->cs55x0, PCI_MODON, &(params->on_duration)); pci_read_config_byte(params->cs55x0, PCI_MODOFF, &(params->off_duration)); - pci_read_config_byte(params->cs55x0, PCI_REVISION_ID, ¶ms->pci_rev); if ((ret = cpufreq_register_driver(&gx_suspmod_driver))) { kfree(params); diff --git a/arch/i386/kernel/cpu/cpufreq/longhaul.c b/arch/i386/kernel/cpu/cpufreq/longhaul.c index a3df9c039bd4..f0cce3c2dc3a 100644 --- a/arch/i386/kernel/cpu/cpufreq/longhaul.c +++ b/arch/i386/kernel/cpu/cpufreq/longhaul.c @@ -29,6 +29,7 @@ #include <linux/pci.h> #include <linux/slab.h> #include <linux/string.h> +#include <linux/delay.h> #include <asm/msr.h> #include <asm/timex.h> @@ -55,7 +56,6 @@ /* Flags */ #define USE_ACPI_C3 (1 << 1) #define USE_NORTHBRIDGE (1 << 2) -#define USE_VT8235 (1 << 3) static int cpu_model; static unsigned int numscales=16; @@ -63,22 +63,20 @@ static unsigned int fsb; static const struct mV_pos *vrm_mV_table; static const unsigned char *mV_vrm_table; -struct f_msr { - u8 vrm; - u8 pos; -}; -static struct f_msr f_msr_table[32]; static unsigned int highest_speed, lowest_speed; /* kHz */ static unsigned int minmult, maxmult; static int can_scale_voltage; static struct acpi_processor *pr = NULL; static struct acpi_processor_cx *cx = NULL; +static u32 acpi_regs_addr; static u8 longhaul_flags; -static u8 longhaul_pos; +static unsigned int longhaul_index; /* Module parameters */ static int scale_voltage; +static int disable_acpi_c3; +static int revid_errata; #define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "longhaul", msg) @@ -144,7 +142,7 @@ static void do_longhaul1(unsigned int clock_ratio_index) rdmsrl(MSR_VIA_BCR2, bcr2.val); /* Enable software clock multiplier */ bcr2.bits.ESOFTBF = 1; - bcr2.bits.CLOCKMUL = clock_ratio_index; + bcr2.bits.CLOCKMUL = clock_ratio_index & 0xff; /* Sync to timer tick */ safe_halt(); @@ -163,26 +161,27 @@ static void do_longhaul1(unsigned int clock_ratio_index) /* For processor with Longhaul MSR */ -static void do_powersaver(int cx_address, unsigned int clock_ratio_index) +static void do_powersaver(int cx_address, unsigned int clock_ratio_index, + unsigned int dir) { union msr_longhaul longhaul; - u8 dest_pos; u32 t; - dest_pos = f_msr_table[clock_ratio_index].pos; - rdmsrl(MSR_VIA_LONGHAUL, longhaul.val); /* Setup new frequency */ - longhaul.bits.RevisionKey = longhaul.bits.RevisionID; + if (!revid_errata) + longhaul.bits.RevisionKey = longhaul.bits.RevisionID; + else + longhaul.bits.RevisionKey = 0; longhaul.bits.SoftBusRatio = clock_ratio_index & 0xf; longhaul.bits.SoftBusRatio4 = (clock_ratio_index & 0x10) >> 4; /* Setup new voltage */ if (can_scale_voltage) - longhaul.bits.SoftVID = f_msr_table[clock_ratio_index].vrm; + longhaul.bits.SoftVID = (clock_ratio_index >> 8) & 0x1f; /* Sync to timer tick */ safe_halt(); /* Raise voltage if necessary */ - if (can_scale_voltage && longhaul_pos < dest_pos) { + if (can_scale_voltage && dir) { longhaul.bits.EnableSoftVID = 1; wrmsrl(MSR_VIA_LONGHAUL, longhaul.val); /* Change voltage */ @@ -199,7 +198,6 @@ static void do_powersaver(int cx_address, unsigned int clock_ratio_index) } longhaul.bits.EnableSoftVID = 0; wrmsrl(MSR_VIA_LONGHAUL, longhaul.val); - longhaul_pos = dest_pos; } /* Change frequency on next halt or sleep */ @@ -220,7 +218,7 @@ static void do_powersaver(int cx_address, unsigned int clock_ratio_index) wrmsrl(MSR_VIA_LONGHAUL, longhaul.val); /* Reduce voltage if necessary */ - if (can_scale_voltage && longhaul_pos > dest_pos) { + if (can_scale_voltage && !dir) { longhaul.bits.EnableSoftVID = 1; wrmsrl(MSR_VIA_LONGHAUL, longhaul.val); /* Change voltage */ @@ -237,7 +235,6 @@ static void do_powersaver(int cx_address, unsigned int clock_ratio_index) } longhaul.bits.EnableSoftVID = 0; wrmsrl(MSR_VIA_LONGHAUL, longhaul.val); - longhaul_pos = dest_pos; } } @@ -248,25 +245,28 @@ static void do_powersaver(int cx_address, unsigned int clock_ratio_index) * Sets a new clock ratio. */ -static void longhaul_setstate(unsigned int clock_ratio_index) +static void longhaul_setstate(unsigned int table_index) { + unsigned int clock_ratio_index; int speed, mult; struct cpufreq_freqs freqs; - static unsigned int old_ratio=-1; unsigned long flags; unsigned int pic1_mask, pic2_mask; + u16 bm_status = 0; + u32 bm_timeout = 1000; + unsigned int dir = 0; - if (old_ratio == clock_ratio_index) - return; - old_ratio = clock_ratio_index; - - mult = clock_ratio[clock_ratio_index]; + clock_ratio_index = longhaul_table[table_index].index; + /* Safety precautions */ + mult = clock_ratio[clock_ratio_index & 0x1f]; if (mult == -1) return; - speed = calc_speed(mult); if ((speed > highest_speed) || (speed < lowest_speed)) return; + /* Voltage transition before frequency transition? */ + if (can_scale_voltage && longhaul_index < table_index) + dir = 1; freqs.old = calc_speed(longhaul_get_cpu_mult()); freqs.new = speed; @@ -276,7 +276,7 @@ static void longhaul_setstate(unsigned int clock_ratio_index) dprintk ("Setting to FSB:%dMHz Mult:%d.%dx (%s)\n", fsb, mult/10, mult%10, print_speed(speed/1000)); - +retry_loop: preempt_disable(); local_irq_save(flags); @@ -285,11 +285,24 @@ static void longhaul_setstate(unsigned int clock_ratio_index) outb(0xFF,0xA1); /* Overkill */ outb(0xFE,0x21); /* TMR0 only */ + /* Wait while PCI bus is busy. */ + if (acpi_regs_addr && (longhaul_flags & USE_NORTHBRIDGE + || ((pr != NULL) && pr->flags.bm_control))) { + bm_status = inw(acpi_regs_addr); + bm_status &= 1 << 4; + while (bm_status && bm_timeout) { + outw(1 << 4, acpi_regs_addr); + bm_timeout--; + bm_status = inw(acpi_regs_addr); + bm_status &= 1 << 4; + } + } + if (longhaul_flags & USE_NORTHBRIDGE) { /* Disable AGP and PCI arbiters */ outb(3, 0x22); } else if ((pr != NULL) && pr->flags.bm_control) { - /* Disable bus master arbitration */ + /* Disable bus master arbitration */ acpi_set_register(ACPI_BITREG_ARB_DISABLE, 1); } switch (longhaul_version) { @@ -314,9 +327,9 @@ static void longhaul_setstate(unsigned int clock_ratio_index) if (longhaul_flags & USE_ACPI_C3) { /* Don't allow wakeup */ acpi_set_register(ACPI_BITREG_BUS_MASTER_RLD, 0); - do_powersaver(cx->address, clock_ratio_index); + do_powersaver(cx->address, clock_ratio_index, dir); } else { - do_powersaver(0, clock_ratio_index); + do_powersaver(0, clock_ratio_index, dir); } break; } @@ -335,7 +348,51 @@ static void longhaul_setstate(unsigned int clock_ratio_index) preempt_enable(); freqs.new = calc_speed(longhaul_get_cpu_mult()); + /* Check if requested frequency is set. */ + if (unlikely(freqs.new != speed)) { + printk(KERN_INFO PFX "Failed to set requested frequency!\n"); + /* Revision ID = 1 but processor is expecting revision key + * equal to 0. Jumpers at the bottom of processor will change + * multiplier and FSB, but will not change bits in Longhaul + * MSR nor enable voltage scaling. */ + if (!revid_errata) { + printk(KERN_INFO PFX "Enabling \"Ignore Revision ID\" " + "option.\n"); + revid_errata = 1; + msleep(200); + goto retry_loop; + } + /* Why ACPI C3 sometimes doesn't work is a mystery for me. + * But it does happen. Processor is entering ACPI C3 state, + * but it doesn't change frequency. I tried poking various + * bits in northbridge registers, but without success. */ + if (longhaul_flags & USE_ACPI_C3) { + printk(KERN_INFO PFX "Disabling ACPI C3 support.\n"); + longhaul_flags &= ~USE_ACPI_C3; + if (revid_errata) { + printk(KERN_INFO PFX "Disabling \"Ignore " + "Revision ID\" option.\n"); + revid_errata = 0; + } + msleep(200); + goto retry_loop; + } + /* This shouldn't happen. Longhaul ver. 2 was reported not + * working on processors without voltage scaling, but with + * RevID = 1. RevID errata will make things right. Just + * to be 100% sure. */ + if (longhaul_version == TYPE_LONGHAUL_V2) { + printk(KERN_INFO PFX "Switching to Longhaul ver. 1\n"); + longhaul_version = TYPE_LONGHAUL_V1; + msleep(200); + goto retry_loop; + } + } + /* Report true CPU frequency */ cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); + + if (!bm_timeout) + printk(KERN_INFO PFX "Warning: Timeout while waiting for idle PCI bus.\n"); } /* @@ -369,7 +426,8 @@ static int guess_fsb(int mult) static int __init longhaul_get_ranges(void) { - unsigned int j, k = 0; + unsigned int i, j, k = 0; + unsigned int ratio; int mult; /* Get current frequency */ @@ -423,8 +481,7 @@ static int __init longhaul_get_ranges(void) if(!longhaul_table) return -ENOMEM; - for (j=0; j < numscales; j++) { - unsigned int ratio; + for (j = 0; j < numscales; j++) { ratio = clock_ratio[j]; if (ratio == -1) continue; @@ -434,13 +491,41 @@ static int __init longhaul_get_ranges(void) longhaul_table[k].index = j; k++; } + if (k <= 1) { + kfree(longhaul_table); + return -ENODEV; + } + /* Sort */ + for (j = 0; j < k - 1; j++) { + unsigned int min_f, min_i; + min_f = longhaul_table[j].frequency; + min_i = j; + for (i = j + 1; i < k; i++) { + if (longhaul_table[i].frequency < min_f) { + min_f = longhaul_table[i].frequency; + min_i = i; + } + } + if (min_i != j) { + unsigned int temp; + temp = longhaul_table[j].frequency; + longhaul_table[j].frequency = longhaul_table[min_i].frequency; + longhaul_table[min_i].frequency = temp; + temp = longhaul_table[j].index; + longhaul_table[j].index = longhaul_table[min_i].index; + longhaul_table[min_i].index = temp; + } + } longhaul_table[k].frequency = CPUFREQ_TABLE_END; - if (!k) { - kfree (longhaul_table); - return -EINVAL; - } + /* Find index we are running on */ + for (j = 0; j < k; j++) { + if (clock_ratio[longhaul_table[j].index & 0x1f] == mult) { + longhaul_index = j; + break; + } + } return 0; } @@ -448,7 +533,7 @@ static int __init longhaul_get_ranges(void) static void __init longhaul_setup_voltagescaling(void) { union msr_longhaul longhaul; - struct mV_pos minvid, maxvid; + struct mV_pos minvid, maxvid, vid; unsigned int j, speed, pos, kHz_step, numvscales; int min_vid_speed; @@ -459,11 +544,11 @@ static void __init longhaul_setup_voltagescaling(void) } if (!longhaul.bits.VRMRev) { - printk (KERN_INFO PFX "VRM 8.5\n"); + printk(KERN_INFO PFX "VRM 8.5\n"); vrm_mV_table = &vrm85_mV[0]; mV_vrm_table = &mV_vrm85[0]; } else { - printk (KERN_INFO PFX "Mobile VRM\n"); + printk(KERN_INFO PFX "Mobile VRM\n"); if (cpu_model < CPU_NEHEMIAH) return; vrm_mV_table = &mobilevrm_mV[0]; @@ -523,7 +608,6 @@ static void __init longhaul_setup_voltagescaling(void) /* Calculate kHz for one voltage step */ kHz_step = (highest_speed - min_vid_speed) / numvscales; - j = 0; while (longhaul_table[j].frequency != CPUFREQ_TABLE_END) { speed = longhaul_table[j].frequency; @@ -531,15 +615,14 @@ static void __init longhaul_setup_voltagescaling(void) pos = (speed - min_vid_speed) / kHz_step + minvid.pos; else pos = minvid.pos; - f_msr_table[longhaul_table[j].index].vrm = mV_vrm_table[pos]; - f_msr_table[longhaul_table[j].index].pos = pos; + longhaul_table[j].index |= mV_vrm_table[pos] << 8; + vid = vrm_mV_table[mV_vrm_table[pos]]; + printk(KERN_INFO PFX "f: %d kHz, index: %d, vid: %d mV\n", speed, j, vid.mV); j++; } - longhaul_pos = maxvid.pos; can_scale_voltage = 1; - printk(KERN_INFO PFX "Voltage scaling enabled. " - "Use of \"conservative\" governor is highly recommended.\n"); + printk(KERN_INFO PFX "Voltage scaling enabled.\n"); } @@ -553,15 +636,44 @@ static int longhaul_target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation) { unsigned int table_index = 0; - unsigned int new_clock_ratio = 0; + unsigned int i; + unsigned int dir = 0; + u8 vid, current_vid; if (cpufreq_frequency_table_target(policy, longhaul_table, target_freq, relation, &table_index)) return -EINVAL; - new_clock_ratio = longhaul_table[table_index].index & 0xFF; - - longhaul_setstate(new_clock_ratio); + /* Don't set same frequency again */ + if (longhaul_index == table_index) + return 0; + if (!can_scale_voltage) + longhaul_setstate(table_index); + else { + /* On test system voltage transitions exceeding single + * step up or down were turning motherboard off. Both + * "ondemand" and "userspace" are unsafe. C7 is doing + * this in hardware, C3 is old and we need to do this + * in software. */ + i = longhaul_index; + current_vid = (longhaul_table[longhaul_index].index >> 8) & 0x1f; + if (table_index > longhaul_index) + dir = 1; + while (i != table_index) { + vid = (longhaul_table[i].index >> 8) & 0x1f; + if (vid != current_vid) { + longhaul_setstate(i); + current_vid = vid; + msleep(200); + } + if (dir) + i++; + else + i--; + } + longhaul_setstate(table_index); + } + longhaul_index = table_index; return 0; } @@ -590,11 +702,10 @@ static acpi_status longhaul_walk_callback(acpi_handle obj_handle, static int enable_arbiter_disable(void) { struct pci_dev *dev; - int status; + int status = 1; int reg; u8 pci_cmd; - status = 1; /* Find PLE133 host bridge */ reg = 0x78; dev = pci_get_device(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8601_0, @@ -627,13 +738,17 @@ static int enable_arbiter_disable(void) return 0; } -static int longhaul_setup_vt8235(void) +static int longhaul_setup_southbridge(void) { struct pci_dev *dev; u8 pci_cmd; /* Find VT8235 southbridge */ dev = pci_get_device(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8235, NULL); + if (dev == NULL) + /* Find VT8237 southbridge */ + dev = pci_get_device(PCI_VENDOR_ID_VIA, + PCI_DEVICE_ID_VIA_8237, NULL); if (dev != NULL) { /* Set transition time to max */ pci_read_config_byte(dev, 0xec, &pci_cmd); @@ -645,6 +760,14 @@ static int longhaul_setup_vt8235(void) pci_read_config_byte(dev, 0xe5, &pci_cmd); pci_cmd |= 1 << 7; pci_write_config_byte(dev, 0xe5, pci_cmd); + /* Get address of ACPI registers block*/ + pci_read_config_byte(dev, 0x81, &pci_cmd); + if (pci_cmd & 1 << 7) { + pci_read_config_dword(dev, 0x88, &acpi_regs_addr); + acpi_regs_addr &= 0xff00; + printk(KERN_INFO PFX "ACPI I/O at 0x%x\n", acpi_regs_addr); + } + pci_dev_put(dev); return 1; } @@ -657,7 +780,6 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy) char *cpuname=NULL; int ret; u32 lo, hi; - int vt8235_present; /* Check what we have on this motherboard */ switch (c->x86_model) { @@ -755,7 +877,7 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy) }; /* Doesn't hurt */ - vt8235_present = longhaul_setup_vt8235(); + longhaul_setup_southbridge(); /* Find ACPI data for processor */ acpi_walk_namespace(ACPI_TYPE_PROCESSOR, ACPI_ROOT_OBJECT, @@ -765,35 +887,29 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy) /* Check ACPI support for C3 state */ if (pr != NULL && longhaul_version == TYPE_POWERSAVER) { cx = &pr->power.states[ACPI_STATE_C3]; - if (cx->address > 0 && cx->latency <= 1000) { + if (cx->address > 0 && cx->latency <= 1000) longhaul_flags |= USE_ACPI_C3; - goto print_support_type; - } } + /* Disable if it isn't working */ + if (disable_acpi_c3) + longhaul_flags &= ~USE_ACPI_C3; /* Check if northbridge is friendly */ - if (enable_arbiter_disable()) { + if (enable_arbiter_disable()) longhaul_flags |= USE_NORTHBRIDGE; - goto print_support_type; - } - /* Use VT8235 southbridge if present */ - if (longhaul_version == TYPE_POWERSAVER && vt8235_present) { - longhaul_flags |= USE_VT8235; - goto print_support_type; - } + /* Check ACPI support for bus master arbiter disable */ - if ((pr == NULL) || !(pr->flags.bm_control)) { + if (!(longhaul_flags & USE_ACPI_C3 + || longhaul_flags & USE_NORTHBRIDGE) + && ((pr == NULL) || !(pr->flags.bm_control))) { printk(KERN_ERR PFX "No ACPI support. Unsupported northbridge.\n"); return -ENODEV; } -print_support_type: if (longhaul_flags & USE_NORTHBRIDGE) - printk (KERN_INFO PFX "Using northbridge support.\n"); - else if (longhaul_flags & USE_VT8235) - printk (KERN_INFO PFX "Using VT8235 support.\n"); - else - printk (KERN_INFO PFX "Using ACPI support.\n"); + printk(KERN_INFO PFX "Using northbridge support.\n"); + if (longhaul_flags & USE_ACPI_C3) + printk(KERN_INFO PFX "Using ACPI support.\n"); ret = longhaul_get_ranges(); if (ret != 0) @@ -885,8 +1001,20 @@ static void __exit longhaul_exit(void) kfree(longhaul_table); } +/* Even if BIOS is exporting ACPI C3 state, and it is used + * with success when CPU is idle, this state doesn't + * trigger frequency transition in some cases. */ +module_param (disable_acpi_c3, int, 0644); +MODULE_PARM_DESC(disable_acpi_c3, "Don't use ACPI C3 support"); +/* Change CPU voltage with frequency. Very usefull to save + * power, but most VIA C3 processors aren't supporting it. */ module_param (scale_voltage, int, 0644); MODULE_PARM_DESC(scale_voltage, "Scale voltage of processor"); +/* Force revision key to 0 for processors which doesn't + * support voltage scaling, but are introducing itself as + * such. */ +module_param(revid_errata, int, 0644); +MODULE_PARM_DESC(revid_errata, "Ignore CPU Revision ID"); MODULE_AUTHOR ("Dave Jones <davej@codemonkey.org.uk>"); MODULE_DESCRIPTION ("Longhaul driver for VIA Cyrix processors."); diff --git a/arch/i386/kernel/cpu/cpufreq/longhaul.h b/arch/i386/kernel/cpu/cpufreq/longhaul.h index 102548f12842..4fcc320997df 100644 --- a/arch/i386/kernel/cpu/cpufreq/longhaul.h +++ b/arch/i386/kernel/cpu/cpufreq/longhaul.h @@ -180,7 +180,7 @@ static const int __initdata ezrat_clock_ratio[32] = { -1, /* 0000 -> RESERVED (10.0x) */ 110, /* 0001 -> 11.0x */ - 120, /* 0010 -> 12.0x */ + -1, /* 0010 -> 12.0x */ -1, /* 0011 -> RESERVED (9.0x)*/ 105, /* 0100 -> 10.5x */ 115, /* 0101 -> 11.5x */ @@ -237,7 +237,7 @@ static const int __initdata ezrat_eblcr[32] = { static const int __initdata nehemiah_clock_ratio[32] = { 100, /* 0000 -> 10.0x */ - 160, /* 0001 -> 16.0x */ + -1, /* 0001 -> 16.0x */ 40, /* 0010 -> 4.0x */ 90, /* 0011 -> 9.0x */ 95, /* 0100 -> 9.5x */ @@ -252,10 +252,10 @@ static const int __initdata nehemiah_clock_ratio[32] = { 75, /* 1101 -> 7.5x */ 85, /* 1110 -> 8.5x */ 120, /* 1111 -> 12.0x */ - 100, /* 0000 -> 10.0x */ + -1, /* 0000 -> 10.0x */ 110, /* 0001 -> 11.0x */ - 120, /* 0010 -> 12.0x */ - 90, /* 0011 -> 9.0x */ + -1, /* 0010 -> 12.0x */ + -1, /* 0011 -> 9.0x */ 105, /* 0100 -> 10.5x */ 115, /* 0101 -> 11.5x */ 125, /* 0110 -> 12.5x */ @@ -267,7 +267,7 @@ static const int __initdata nehemiah_clock_ratio[32] = { 145, /* 1100 -> 14.5x */ 155, /* 1101 -> 15.5x */ -1, /* 1110 -> RESERVED (13.0x) */ - 120, /* 1111 -> 12.0x */ + -1, /* 1111 -> 12.0x */ }; static const int __initdata nehemiah_eblcr[32] = { diff --git a/arch/i386/kernel/cpu/cpufreq/powernow-k8.c b/arch/i386/kernel/cpu/cpufreq/powernow-k8.c index 4ade55c5f333..34ed53a06730 100644 --- a/arch/i386/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/i386/kernel/cpu/cpufreq/powernow-k8.c @@ -599,14 +599,17 @@ static void print_basics(struct powernow_k8_data *data) for (j = 0; j < data->numps; j++) { if (data->powernow_table[j].frequency != CPUFREQ_ENTRY_INVALID) { if (cpu_family == CPU_HW_PSTATE) { - printk(KERN_INFO PFX " %d : fid 0x%x gid 0x%x (%d MHz)\n", j, (data->powernow_table[j].index & 0xff00) >> 8, - (data->powernow_table[j].index & 0xff0000) >> 16, - data->powernow_table[j].frequency/1000); + printk(KERN_INFO PFX " %d : fid 0x%x did 0x%x (%d MHz)\n", + j, + (data->powernow_table[j].index & 0xff00) >> 8, + (data->powernow_table[j].index & 0xff0000) >> 16, + data->powernow_table[j].frequency/1000); } else { - printk(KERN_INFO PFX " %d : fid 0x%x (%d MHz), vid 0x%x\n", j, - data->powernow_table[j].index & 0xff, - data->powernow_table[j].frequency/1000, - data->powernow_table[j].index >> 8); + printk(KERN_INFO PFX " %d : fid 0x%x (%d MHz), vid 0x%x\n", + j, + data->powernow_table[j].index & 0xff, + data->powernow_table[j].frequency/1000, + data->powernow_table[j].index >> 8); } } } @@ -1086,7 +1089,7 @@ static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsi if (cpu_family == CPU_HW_PSTATE) dprintk("targ: curr fid 0x%x, did 0x%x\n", - data->currfid, data->currvid); + data->currfid, data->currdid); else { dprintk("targ: curr fid 0x%x, vid 0x%x\n", data->currfid, data->currvid); @@ -1322,16 +1325,22 @@ static struct cpufreq_driver cpufreq_amd64_driver = { static int __cpuinit powernowk8_init(void) { unsigned int i, supported_cpus = 0; + unsigned int booted_cores = 1; for_each_online_cpu(i) { if (check_supported_cpu(i)) supported_cpus++; } +#ifdef CONFIG_SMP + booted_cores = cpu_data[0].booted_cores; +#endif + if (supported_cpus == num_online_cpus()) { printk(KERN_INFO PFX "Found %d %s " - "processors (" VERSION ")\n", supported_cpus, - boot_cpu_data.x86_model_id); + "processors (%d cpu cores) (" VERSION ")\n", + supported_cpus/booted_cores, + boot_cpu_data.x86_model_id, supported_cpus); return cpufreq_register_driver(&cpufreq_amd64_driver); } diff --git a/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c index 35489fd68852..6c5dc2c85aeb 100644 --- a/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c +++ b/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c @@ -21,12 +21,6 @@ #include <linux/delay.h> #include <linux/compiler.h> -#ifdef CONFIG_X86_SPEEDSTEP_CENTRINO_ACPI -#include <linux/acpi.h> -#include <linux/dmi.h> -#include <acpi/processor.h> -#endif - #include <asm/msr.h> #include <asm/processor.h> #include <asm/cpufeature.h> @@ -257,9 +251,7 @@ static int centrino_cpu_init_table(struct cpufreq_policy *policy) /* Matched a non-match */ dprintk("no table support for CPU model \"%s\"\n", cpu->x86_model_id); -#ifndef CONFIG_X86_SPEEDSTEP_CENTRINO_ACPI - dprintk("try compiling with CONFIG_X86_SPEEDSTEP_CENTRINO_ACPI enabled\n"); -#endif + dprintk("try using the acpi-cpufreq driver\n"); return -ENOENT; } @@ -346,213 +338,6 @@ static unsigned int get_cur_freq(unsigned int cpu) } -#ifdef CONFIG_X86_SPEEDSTEP_CENTRINO_ACPI - -static struct acpi_processor_performance *acpi_perf_data[NR_CPUS]; - -/* - * centrino_cpu_early_init_acpi - Do the preregistering with ACPI P-States - * library - * - * Before doing the actual init, we need to do _PSD related setup whenever - * supported by the BIOS. These are handled by this early_init routine. - */ -static int centrino_cpu_early_init_acpi(void) -{ - unsigned int i, j; - struct acpi_processor_performance *data; - - for_each_possible_cpu(i) { - data = kzalloc(sizeof(struct acpi_processor_performance), - GFP_KERNEL); - if (!data) { - for_each_possible_cpu(j) { - kfree(acpi_perf_data[j]); - acpi_perf_data[j] = NULL; - } - return (-ENOMEM); - } - acpi_perf_data[i] = data; - } - - acpi_processor_preregister_performance(acpi_perf_data); - return 0; -} - - -#ifdef CONFIG_SMP -/* - * Some BIOSes do SW_ANY coordination internally, either set it up in hw - * or do it in BIOS firmware and won't inform about it to OS. If not - * detected, this has a side effect of making CPU run at a different speed - * than OS intended it to run at. Detect it and handle it cleanly. - */ -static int bios_with_sw_any_bug; -static int sw_any_bug_found(struct dmi_system_id *d) -{ - bios_with_sw_any_bug = 1; - return 0; -} - -static struct dmi_system_id sw_any_bug_dmi_table[] = { - { - .callback = sw_any_bug_found, - .ident = "Supermicro Server X6DLP", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Supermicro"), - DMI_MATCH(DMI_BIOS_VERSION, "080010"), - DMI_MATCH(DMI_PRODUCT_NAME, "X6DLP"), - }, - }, - { } -}; -#endif - -/* - * centrino_cpu_init_acpi - register with ACPI P-States library - * - * Register with the ACPI P-States library (part of drivers/acpi/processor.c) - * in order to determine correct frequency and voltage pairings by reading - * the _PSS of the ACPI DSDT or SSDT tables. - */ -static int centrino_cpu_init_acpi(struct cpufreq_policy *policy) -{ - unsigned long cur_freq; - int result = 0, i; - unsigned int cpu = policy->cpu; - struct acpi_processor_performance *p; - - p = acpi_perf_data[cpu]; - - /* register with ACPI core */ - if (acpi_processor_register_performance(p, cpu)) { - dprintk(PFX "obtaining ACPI data failed\n"); - return -EIO; - } - - policy->shared_type = p->shared_type; - /* - * Will let policy->cpus know about dependency only when software - * coordination is required. - */ - if (policy->shared_type == CPUFREQ_SHARED_TYPE_ALL || - policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) { - policy->cpus = p->shared_cpu_map; - } - -#ifdef CONFIG_SMP - dmi_check_system(sw_any_bug_dmi_table); - if (bios_with_sw_any_bug && cpus_weight(policy->cpus) == 1) { - policy->shared_type = CPUFREQ_SHARED_TYPE_ALL; - policy->cpus = cpu_core_map[cpu]; - } -#endif - - /* verify the acpi_data */ - if (p->state_count <= 1) { - dprintk("No P-States\n"); - result = -ENODEV; - goto err_unreg; - } - - if ((p->control_register.space_id != ACPI_ADR_SPACE_FIXED_HARDWARE) || - (p->status_register.space_id != ACPI_ADR_SPACE_FIXED_HARDWARE)) { - dprintk("Invalid control/status registers (%x - %x)\n", - p->control_register.space_id, p->status_register.space_id); - result = -EIO; - goto err_unreg; - } - - for (i=0; i<p->state_count; i++) { - if ((p->states[i].control & INTEL_MSR_RANGE) != - (p->states[i].status & INTEL_MSR_RANGE)) { - dprintk("Different MSR bits in control (%llu) and status (%llu)\n", - p->states[i].control, p->states[i].status); - result = -EINVAL; - goto err_unreg; - } - - if (!p->states[i].core_frequency) { - dprintk("Zero core frequency for state %u\n", i); - result = -EINVAL; - goto err_unreg; - } - - if (p->states[i].core_frequency > p->states[0].core_frequency) { - dprintk("P%u has larger frequency (%llu) than P0 (%llu), skipping\n", i, - p->states[i].core_frequency, p->states[0].core_frequency); - p->states[i].core_frequency = 0; - continue; - } - } - - centrino_model[cpu] = kzalloc(sizeof(struct cpu_model), GFP_KERNEL); - if (!centrino_model[cpu]) { - result = -ENOMEM; - goto err_unreg; - } - - centrino_model[cpu]->model_name=NULL; - centrino_model[cpu]->max_freq = p->states[0].core_frequency * 1000; - centrino_model[cpu]->op_points = kmalloc(sizeof(struct cpufreq_frequency_table) * - (p->state_count + 1), GFP_KERNEL); - if (!centrino_model[cpu]->op_points) { - result = -ENOMEM; - goto err_kfree; - } - - for (i=0; i<p->state_count; i++) { - centrino_model[cpu]->op_points[i].index = p->states[i].control & INTEL_MSR_RANGE; - centrino_model[cpu]->op_points[i].frequency = p->states[i].core_frequency * 1000; - dprintk("adding state %i with frequency %u and control value %04x\n", - i, centrino_model[cpu]->op_points[i].frequency, centrino_model[cpu]->op_points[i].index); - } - centrino_model[cpu]->op_points[p->state_count].frequency = CPUFREQ_TABLE_END; - - cur_freq = get_cur_freq(cpu); - - for (i=0; i<p->state_count; i++) { - if (!p->states[i].core_frequency) { - dprintk("skipping state %u\n", i); - centrino_model[cpu]->op_points[i].frequency = CPUFREQ_ENTRY_INVALID; - continue; - } - - if (extract_clock(centrino_model[cpu]->op_points[i].index, cpu, 0) != - (centrino_model[cpu]->op_points[i].frequency)) { - dprintk("Invalid encoded frequency (%u vs. %u)\n", - extract_clock(centrino_model[cpu]->op_points[i].index, cpu, 0), - centrino_model[cpu]->op_points[i].frequency); - result = -EINVAL; - goto err_kfree_all; - } - - if (cur_freq == centrino_model[cpu]->op_points[i].frequency) - p->state = i; - } - - /* notify BIOS that we exist */ - acpi_processor_notify_smm(THIS_MODULE); - printk("speedstep-centrino with X86_SPEEDSTEP_CENTRINO_ACPI " - "config is deprecated.\n " - "Use X86_ACPI_CPUFREQ (acpi-cpufreq) instead.\n" ); - - return 0; - - err_kfree_all: - kfree(centrino_model[cpu]->op_points); - err_kfree: - kfree(centrino_model[cpu]); - err_unreg: - acpi_processor_unregister_performance(p, cpu); - dprintk(PFX "invalid ACPI data\n"); - return (result); -} -#else -static inline int centrino_cpu_init_acpi(struct cpufreq_policy *policy) { return -ENODEV; } -static inline int centrino_cpu_early_init_acpi(void) { return 0; } -#endif - static int centrino_cpu_init(struct cpufreq_policy *policy) { struct cpuinfo_x86 *cpu = &cpu_data[policy->cpu]; @@ -568,27 +353,25 @@ static int centrino_cpu_init(struct cpufreq_policy *policy) if (cpu_has(cpu, X86_FEATURE_CONSTANT_TSC)) centrino_driver.flags |= CPUFREQ_CONST_LOOPS; - if (centrino_cpu_init_acpi(policy)) { - if (policy->cpu != 0) - return -ENODEV; + if (policy->cpu != 0) + return -ENODEV; - for (i = 0; i < N_IDS; i++) - if (centrino_verify_cpu_id(cpu, &cpu_ids[i])) - break; + for (i = 0; i < N_IDS; i++) + if (centrino_verify_cpu_id(cpu, &cpu_ids[i])) + break; - if (i != N_IDS) - centrino_cpu[policy->cpu] = &cpu_ids[i]; + if (i != N_IDS) + centrino_cpu[policy->cpu] = &cpu_ids[i]; - if (!centrino_cpu[policy->cpu]) { - dprintk("found unsupported CPU with " - "Enhanced SpeedStep: send /proc/cpuinfo to " - MAINTAINER "\n"); - return -ENODEV; - } + if (!centrino_cpu[policy->cpu]) { + dprintk("found unsupported CPU with " + "Enhanced SpeedStep: send /proc/cpuinfo to " + MAINTAINER "\n"); + return -ENODEV; + } - if (centrino_cpu_init_table(policy)) { - return -ENODEV; - } + if (centrino_cpu_init_table(policy)) { + return -ENODEV; } /* Check to see if Enhanced SpeedStep is enabled, and try to @@ -634,20 +417,6 @@ static int centrino_cpu_exit(struct cpufreq_policy *policy) cpufreq_frequency_table_put_attr(cpu); -#ifdef CONFIG_X86_SPEEDSTEP_CENTRINO_ACPI - if (!centrino_model[cpu]->model_name) { - static struct acpi_processor_performance *p; - - if (acpi_perf_data[cpu]) { - p = acpi_perf_data[cpu]; - dprintk("unregistering and freeing ACPI data\n"); - acpi_processor_unregister_performance(p, cpu); - kfree(centrino_model[cpu]->op_points); - kfree(centrino_model[cpu]); - } - } -#endif - centrino_model[cpu] = NULL; return 0; @@ -849,25 +618,12 @@ static int __init centrino_init(void) if (!cpu_has(cpu, X86_FEATURE_EST)) return -ENODEV; - centrino_cpu_early_init_acpi(); - return cpufreq_register_driver(¢rino_driver); } static void __exit centrino_exit(void) { -#ifdef CONFIG_X86_SPEEDSTEP_CENTRINO_ACPI - unsigned int j; -#endif - cpufreq_unregister_driver(¢rino_driver); - -#ifdef CONFIG_X86_SPEEDSTEP_CENTRINO_ACPI - for_each_possible_cpu(j) { - kfree(acpi_perf_data[j]); - acpi_perf_data[j] = NULL; - } -#endif } MODULE_AUTHOR ("Jeremy Fitzhardinge <jeremy@goop.org>"); diff --git a/arch/i386/kernel/cpu/cpufreq/speedstep-ich.c b/arch/i386/kernel/cpu/cpufreq/speedstep-ich.c index 698f980eb443..a5b2346faf1f 100644 --- a/arch/i386/kernel/cpu/cpufreq/speedstep-ich.c +++ b/arch/i386/kernel/cpu/cpufreq/speedstep-ich.c @@ -205,7 +205,6 @@ static unsigned int speedstep_detect_chipset (void) * host brige. Abort on these systems. */ static struct pci_dev *hostbridge; - u8 rev = 0; hostbridge = pci_get_subsys(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82815_MC, @@ -216,8 +215,7 @@ static unsigned int speedstep_detect_chipset (void) if (!hostbridge) return 2; /* 2-M */ - pci_read_config_byte(hostbridge, PCI_REVISION_ID, &rev); - if (rev < 5) { + if (hostbridge->revision < 5) { dprintk("hostbridge does not support speedstep\n"); speedstep_chipset_dev = NULL; pci_dev_put(hostbridge); diff --git a/arch/i386/kernel/cpu/cyrix.c b/arch/i386/kernel/cpu/cyrix.c index e88d2fba156b..122d2d75aa9f 100644 --- a/arch/i386/kernel/cpu/cyrix.c +++ b/arch/i386/kernel/cpu/cyrix.c @@ -4,7 +4,7 @@ #include <linux/pci.h> #include <asm/dma.h> #include <asm/io.h> -#include <asm/processor.h> +#include <asm/processor-cyrix.h> #include <asm/timer.h> #include <asm/pci-direct.h> #include <asm/tsc.h> diff --git a/arch/i386/kernel/cpu/intel_cacheinfo.c b/arch/i386/kernel/cpu/intel_cacheinfo.c index e5be819492ef..db6c25aa5776 100644 --- a/arch/i386/kernel/cpu/intel_cacheinfo.c +++ b/arch/i386/kernel/cpu/intel_cacheinfo.c @@ -4,7 +4,7 @@ * Changes: * Venkatesh Pallipadi : Adding cache identification through cpuid(4) * Ashok Raj <ashok.raj@intel.com>: Work with CPU hotplug infrastructure. - * Andi Kleen : CPUID4 emulation on AMD. + * Andi Kleen / Andreas Herrmann : CPUID4 emulation on AMD. */ #include <linux/init.h> @@ -135,7 +135,7 @@ unsigned short num_cache_leaves; /* AMD doesn't have CPUID4. Emulate it here to report the same information to the user. This makes some assumptions about the machine: - No L3, L2 not shared, no SMT etc. that is currently true on AMD CPUs. + L2 not shared, no SMT etc. that is currently true on AMD CPUs. In theory the TLBs could be reported as fake type (they are in "dummy"). Maybe later */ @@ -159,13 +159,26 @@ union l2_cache { unsigned val; }; +union l3_cache { + struct { + unsigned line_size : 8; + unsigned lines_per_tag : 4; + unsigned assoc : 4; + unsigned res : 2; + unsigned size_encoded : 14; + }; + unsigned val; +}; + static const unsigned short assocs[] = { [1] = 1, [2] = 2, [4] = 4, [6] = 8, - [8] = 16, + [8] = 16, [0xa] = 32, [0xb] = 48, + [0xc] = 64, [0xf] = 0xffff // ?? - }; -static const unsigned char levels[] = { 1, 1, 2 }; -static const unsigned char types[] = { 1, 2, 3 }; +}; + +static const unsigned char levels[] = { 1, 1, 2, 3 }; +static const unsigned char types[] = { 1, 2, 3, 3 }; static void __cpuinit amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax, union _cpuid4_leaf_ebx *ebx, @@ -175,37 +188,58 @@ static void __cpuinit amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax, unsigned line_size, lines_per_tag, assoc, size_in_kb; union l1_cache l1i, l1d; union l2_cache l2; + union l3_cache l3; + union l1_cache *l1 = &l1d; eax->full = 0; ebx->full = 0; ecx->full = 0; cpuid(0x80000005, &dummy, &dummy, &l1d.val, &l1i.val); - cpuid(0x80000006, &dummy, &dummy, &l2.val, &dummy); - - if (leaf > 2 || !l1d.val || !l1i.val || !l2.val) - return; - - eax->split.is_self_initializing = 1; - eax->split.type = types[leaf]; - eax->split.level = levels[leaf]; - eax->split.num_threads_sharing = 0; - eax->split.num_cores_on_die = current_cpu_data.x86_max_cores - 1; - - if (leaf <= 1) { - union l1_cache *l1 = leaf == 0 ? &l1d : &l1i; + cpuid(0x80000006, &dummy, &dummy, &l2.val, &l3.val); + + switch (leaf) { + case 1: + l1 = &l1i; + case 0: + if (!l1->val) + return; assoc = l1->assoc; line_size = l1->line_size; lines_per_tag = l1->lines_per_tag; size_in_kb = l1->size_in_kb; - } else { + break; + case 2: + if (!l2.val) + return; assoc = l2.assoc; line_size = l2.line_size; lines_per_tag = l2.lines_per_tag; /* cpu_data has errata corrections for K7 applied */ size_in_kb = current_cpu_data.x86_cache_size; + break; + case 3: + if (!l3.val) + return; + assoc = l3.assoc; + line_size = l3.line_size; + lines_per_tag = l3.lines_per_tag; + size_in_kb = l3.size_encoded * 512; + break; + default: + return; } + eax->split.is_self_initializing = 1; + eax->split.type = types[leaf]; + eax->split.level = levels[leaf]; + if (leaf == 3) + eax->split.num_threads_sharing = current_cpu_data.x86_max_cores - 1; + else + eax->split.num_threads_sharing = 0; + eax->split.num_cores_on_die = current_cpu_data.x86_max_cores - 1; + + if (assoc == 0xf) eax->split.is_fully_associative = 1; ebx->split.coherency_line_size = line_size - 1; @@ -239,8 +273,7 @@ static int __cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_le return 0; } -/* will only be called once; __init is safe here */ -static int __init find_num_cache_leaves(void) +static int __cpuinit find_num_cache_leaves(void) { unsigned int eax, ebx, ecx, edx; union _cpuid4_leaf_eax cache_eax; @@ -482,7 +515,7 @@ static int __cpuinit detect_cache_attributes(unsigned int cpu) cpuid4_info[cpu] = kzalloc( sizeof(struct _cpuid4_info) * num_cache_leaves, GFP_KERNEL); - if (unlikely(cpuid4_info[cpu] == NULL)) + if (cpuid4_info[cpu] == NULL) return -ENOMEM; oldmask = current->cpus_allowed; @@ -710,11 +743,13 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev) return retval; } -static void __cpuexit cache_remove_dev(struct sys_device * sys_dev) +static void __cpuinit cache_remove_dev(struct sys_device * sys_dev) { unsigned int cpu = sys_dev->id; unsigned long i; + if (cpuid4_info[cpu] == NULL) + return; for (i = 0; i < num_cache_leaves; i++) { cache_remove_shared_cpu_map(cpu, i); kobject_unregister(&(INDEX_KOBJECT_PTR(cpu,i)->kobj)); diff --git a/arch/i386/kernel/cpu/mcheck/mce.c b/arch/i386/kernel/cpu/mcheck/mce.c index 56cd485b127c..34c781eddee4 100644 --- a/arch/i386/kernel/cpu/mcheck/mce.c +++ b/arch/i386/kernel/cpu/mcheck/mce.c @@ -60,6 +60,20 @@ void mcheck_init(struct cpuinfo_x86 *c) } } +static unsigned long old_cr4 __initdata; + +void __init stop_mce(void) +{ + old_cr4 = read_cr4(); + clear_in_cr4(X86_CR4_MCE); +} + +void __init restart_mce(void) +{ + if (old_cr4 & X86_CR4_MCE) + set_in_cr4(X86_CR4_MCE); +} + static int __init mcheck_disable(char *str) { mce_disabled = 1; diff --git a/arch/i386/kernel/cpu/mcheck/non-fatal.c b/arch/i386/kernel/cpu/mcheck/non-fatal.c index 6b5d3518a1c0..bf39409b3838 100644 --- a/arch/i386/kernel/cpu/mcheck/non-fatal.c +++ b/arch/i386/kernel/cpu/mcheck/non-fatal.c @@ -57,7 +57,7 @@ static DECLARE_DELAYED_WORK(mce_work, mce_work_fn); static void mce_work_fn(struct work_struct *work) { on_each_cpu(mce_checkregs, NULL, 1, 1); - schedule_delayed_work(&mce_work, MCE_RATE); + schedule_delayed_work(&mce_work, round_jiffies_relative(MCE_RATE)); } static int __init init_nonfatal_mce_checker(void) @@ -82,7 +82,7 @@ static int __init init_nonfatal_mce_checker(void) /* * Check for non-fatal errors every MCE_RATE s */ - schedule_delayed_work(&mce_work, MCE_RATE); + schedule_delayed_work(&mce_work, round_jiffies_relative(MCE_RATE)); printk(KERN_INFO "Machine check exception polling timer started.\n"); return 0; } diff --git a/arch/i386/kernel/cpu/mcheck/therm_throt.c b/arch/i386/kernel/cpu/mcheck/therm_throt.c index 7ba7c3abd3a4..1203dc5ab87a 100644 --- a/arch/i386/kernel/cpu/mcheck/therm_throt.c +++ b/arch/i386/kernel/cpu/mcheck/therm_throt.c @@ -134,19 +134,21 @@ static __cpuinit int thermal_throttle_cpu_callback(struct notifier_block *nfb, int err; sys_dev = get_cpu_sysdev(cpu); - mutex_lock(&therm_cpu_lock); switch (action) { case CPU_ONLINE: case CPU_ONLINE_FROZEN: + mutex_lock(&therm_cpu_lock); err = thermal_throttle_add_dev(sys_dev); + mutex_unlock(&therm_cpu_lock); WARN_ON(err); break; case CPU_DEAD: case CPU_DEAD_FROZEN: + mutex_lock(&therm_cpu_lock); thermal_throttle_remove_dev(sys_dev); + mutex_unlock(&therm_cpu_lock); break; } - mutex_unlock(&therm_cpu_lock); return NOTIFY_OK; } diff --git a/arch/i386/kernel/cpu/mtrr/cyrix.c b/arch/i386/kernel/cpu/mtrr/cyrix.c index 1001f1e0fe6d..2287d4863a8a 100644 --- a/arch/i386/kernel/cpu/mtrr/cyrix.c +++ b/arch/i386/kernel/cpu/mtrr/cyrix.c @@ -3,6 +3,7 @@ #include <asm/mtrr.h> #include <asm/msr.h> #include <asm/io.h> +#include <asm/processor-cyrix.h> #include "mtrr.h" int arr3_protected; diff --git a/arch/i386/kernel/cpu/mtrr/generic.c b/arch/i386/kernel/cpu/mtrr/generic.c index f6e46943e6ef..56f64e34829f 100644 --- a/arch/i386/kernel/cpu/mtrr/generic.c +++ b/arch/i386/kernel/cpu/mtrr/generic.c @@ -79,7 +79,7 @@ static void print_fixed(unsigned base, unsigned step, const mtrr_type*types) } /* Grab all of the MTRR state for this CPU into *state */ -void get_mtrr_state(void) +void __init get_mtrr_state(void) { unsigned int i; struct mtrr_var_range *vrs; diff --git a/arch/i386/kernel/cpu/mtrr/main.c b/arch/i386/kernel/cpu/mtrr/main.c index 75dc6d5214bc..c48b6fea5ab4 100644 --- a/arch/i386/kernel/cpu/mtrr/main.c +++ b/arch/i386/kernel/cpu/mtrr/main.c @@ -643,7 +643,7 @@ static struct sysdev_driver mtrr_sysdev_driver = { * initialized (i.e. before smp_init()). * */ -__init void mtrr_bp_init(void) +void __init mtrr_bp_init(void) { init_ifs(); diff --git a/arch/i386/kernel/cpu/mtrr/state.c b/arch/i386/kernel/cpu/mtrr/state.c index 7b39a2f954d9..c9014ca4a575 100644 --- a/arch/i386/kernel/cpu/mtrr/state.c +++ b/arch/i386/kernel/cpu/mtrr/state.c @@ -3,6 +3,7 @@ #include <asm/io.h> #include <asm/mtrr.h> #include <asm/msr.h> +#include <asm-i386/processor-cyrix.h> #include "mtrr.h" diff --git a/arch/i386/kernel/cpu/perfctr-watchdog.c b/arch/i386/kernel/cpu/perfctr-watchdog.c index 996f6f89ce8e..93fecd4b03de 100644 --- a/arch/i386/kernel/cpu/perfctr-watchdog.c +++ b/arch/i386/kernel/cpu/perfctr-watchdog.c @@ -263,8 +263,8 @@ static int setup_k7_watchdog(unsigned nmi_hz) unsigned int evntsel; struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - perfctr_msr = MSR_K7_PERFCTR0; - evntsel_msr = MSR_K7_EVNTSEL0; + perfctr_msr = wd_ops->perfctr; + evntsel_msr = wd_ops->evntsel; wrmsrl(perfctr_msr, 0UL); @@ -325,7 +325,7 @@ static struct wd_ops k7_wd_ops = { .stop = single_msr_stop_watchdog, .perfctr = MSR_K7_PERFCTR0, .evntsel = MSR_K7_EVNTSEL0, - .checkbit = 1ULL<<63, + .checkbit = 1ULL<<47, }; /* Intel Model 6 (PPro+,P2,P3,P-M,Core1) */ @@ -343,8 +343,8 @@ static int setup_p6_watchdog(unsigned nmi_hz) unsigned int evntsel; struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - perfctr_msr = MSR_P6_PERFCTR0; - evntsel_msr = MSR_P6_EVNTSEL0; + perfctr_msr = wd_ops->perfctr; + evntsel_msr = wd_ops->evntsel; /* KVM doesn't implement this MSR */ if (wrmsr_safe(perfctr_msr, 0, 0) < 0) @@ -569,8 +569,8 @@ static int setup_intel_arch_watchdog(unsigned nmi_hz) (ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT)) return 0; - perfctr_msr = MSR_ARCH_PERFMON_PERFCTR1; - evntsel_msr = MSR_ARCH_PERFMON_EVENTSEL1; + perfctr_msr = wd_ops->perfctr; + evntsel_msr = wd_ops->evntsel; wrmsrl(perfctr_msr, 0UL); @@ -601,6 +601,16 @@ static struct wd_ops intel_arch_wd_ops = { .setup = setup_intel_arch_watchdog, .rearm = p6_rearm, .stop = single_msr_stop_watchdog, + .perfctr = MSR_ARCH_PERFMON_PERFCTR1, + .evntsel = MSR_ARCH_PERFMON_EVENTSEL1, +}; + +static struct wd_ops coreduo_wd_ops = { + .reserve = single_msr_reserve, + .unreserve = single_msr_unreserve, + .setup = setup_intel_arch_watchdog, + .rearm = p6_rearm, + .stop = single_msr_stop_watchdog, .perfctr = MSR_ARCH_PERFMON_PERFCTR0, .evntsel = MSR_ARCH_PERFMON_EVENTSEL0, }; @@ -615,6 +625,12 @@ static void probe_nmi_watchdog(void) wd_ops = &k7_wd_ops; break; case X86_VENDOR_INTEL: + /* Work around Core Duo (Yonah) errata AE49 where perfctr1 + doesn't have a working enable bit. */ + if (boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 14) { + wd_ops = &coreduo_wd_ops; + break; + } if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) { wd_ops = &intel_arch_wd_ops; break; diff --git a/arch/i386/kernel/cpu/proc.c b/arch/i386/kernel/cpu/proc.c index 89d91e6cc972..1e31b6caffb1 100644 --- a/arch/i386/kernel/cpu/proc.c +++ b/arch/i386/kernel/cpu/proc.c @@ -29,7 +29,8 @@ static int show_cpuinfo(struct seq_file *m, void *v) NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, "syscall", NULL, NULL, NULL, NULL, NULL, NULL, NULL, "mp", "nx", NULL, "mmxext", NULL, - NULL, "fxsr_opt", "pdpe1gb", "rdtscp", NULL, "lm", "3dnowext", "3dnow", + NULL, "fxsr_opt", "pdpe1gb", "rdtscp", NULL, "lm", + "3dnowext", "3dnow", /* Transmeta-defined */ "recovery", "longrun", NULL, "lrti", NULL, NULL, NULL, NULL, @@ -40,8 +41,9 @@ static int show_cpuinfo(struct seq_file *m, void *v) /* Other (Linux-defined) */ "cxmmx", "k6_mtrr", "cyrix_arr", "centaur_mcr", NULL, NULL, NULL, NULL, - "constant_tsc", "up", NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + "constant_tsc", "up", NULL, "arch_perfmon", + "pebs", "bts", NULL, "sync_rdtsc", + "rep_good", NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, /* Intel-defined (#2) */ @@ -57,9 +59,16 @@ static int show_cpuinfo(struct seq_file *m, void *v) NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, /* AMD-defined (#2) */ - "lahf_lm", "cmp_legacy", "svm", "extapic", "cr8legacy", "abm", - "sse4a", "misalignsse", - "3dnowprefetch", "osvw", "ibs", NULL, NULL, NULL, NULL, NULL, + "lahf_lm", "cmp_legacy", "svm", "extapic", "cr8_legacy", + "altmovcr8", "abm", "sse4a", + "misalignsse", "3dnowprefetch", + "osvw", "ibs", NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + + /* Auxiliary (Linux-defined) */ + "ida", NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, }; diff --git a/arch/i386/kernel/cpu/rise.c b/arch/i386/kernel/cpu/rise.c deleted file mode 100644 index 50076f22e90f..000000000000 --- a/arch/i386/kernel/cpu/rise.c +++ /dev/null @@ -1,52 +0,0 @@ -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/bitops.h> -#include <asm/processor.h> - -#include "cpu.h" - -static void __cpuinit init_rise(struct cpuinfo_x86 *c) -{ - printk("CPU: Rise iDragon"); - if (c->x86_model > 2) - printk(" II"); - printk("\n"); - - /* Unhide possibly hidden capability flags - The mp6 iDragon family don't have MSRs. - We switch on extra features with this cpuid weirdness: */ - __asm__ ( - "movl $0x6363452a, %%eax\n\t" - "movl $0x3231206c, %%ecx\n\t" - "movl $0x2a32313a, %%edx\n\t" - "cpuid\n\t" - "movl $0x63634523, %%eax\n\t" - "movl $0x32315f6c, %%ecx\n\t" - "movl $0x2333313a, %%edx\n\t" - "cpuid\n\t" : : : "eax", "ebx", "ecx", "edx" - ); - set_bit(X86_FEATURE_CX8, c->x86_capability); -} - -static struct cpu_dev rise_cpu_dev __cpuinitdata = { - .c_vendor = "Rise", - .c_ident = { "RiseRiseRise" }, - .c_models = { - { .vendor = X86_VENDOR_RISE, .family = 5, .model_names = - { - [0] = "iDragon", - [2] = "iDragon", - [8] = "iDragon II", - [9] = "iDragon II" - } - }, - }, - .c_init = init_rise, -}; - -int __init rise_init_cpu(void) -{ - cpu_devs[X86_VENDOR_RISE] = &rise_cpu_dev; - return 0; -} - diff --git a/arch/i386/kernel/e820.c b/arch/i386/kernel/e820.c index 9645bb51f76a..3c86b979a40a 100644 --- a/arch/i386/kernel/e820.c +++ b/arch/i386/kernel/e820.c @@ -10,6 +10,7 @@ #include <linux/efi.h> #include <linux/pfn.h> #include <linux/uaccess.h> +#include <linux/suspend.h> #include <asm/pgtable.h> #include <asm/page.h> @@ -320,6 +321,37 @@ static int __init request_standard_resources(void) subsys_initcall(request_standard_resources); +#if defined(CONFIG_PM) && defined(CONFIG_HIBERNATION) +/** + * e820_mark_nosave_regions - Find the ranges of physical addresses that do not + * correspond to e820 RAM areas and mark the corresponding pages as nosave for + * hibernation. + * + * This function requires the e820 map to be sorted and without any + * overlapping entries and assumes the first e820 area to be RAM. + */ +void __init e820_mark_nosave_regions(void) +{ + int i; + unsigned long pfn; + + pfn = PFN_DOWN(e820.map[0].addr + e820.map[0].size); + for (i = 1; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + + if (pfn < PFN_UP(ei->addr)) + register_nosave_region(pfn, PFN_UP(ei->addr)); + + pfn = PFN_DOWN(ei->addr + ei->size); + if (ei->type != E820_RAM) + register_nosave_region(PFN_UP(ei->addr), pfn); + + if (pfn >= max_low_pfn) + break; + } +} +#endif + void __init add_memory_region(unsigned long long start, unsigned long long size, int type) { @@ -734,7 +766,7 @@ void __init print_memory_map(char *who) case E820_NVS: printk("(ACPI NVS)\n"); break; - default: printk("type %lu\n", e820.map[i].type); + default: printk("type %u\n", e820.map[i].type); break; } } diff --git a/arch/i386/kernel/efi.c b/arch/i386/kernel/efi.c index a1808022ea19..2452c6fbe992 100644 --- a/arch/i386/kernel/efi.c +++ b/arch/i386/kernel/efi.c @@ -278,7 +278,7 @@ void efi_memmap_walk(efi_freemem_callback_t callback, void *arg) struct range { unsigned long start; unsigned long end; - } prev, curr; + } uninitialized_var(prev), curr; efi_memory_desc_t *md; unsigned long start, end; void *p; diff --git a/arch/i386/kernel/entry.S b/arch/i386/kernel/entry.S index 3c3c220488c9..a714d6b43506 100644 --- a/arch/i386/kernel/entry.S +++ b/arch/i386/kernel/entry.S @@ -409,8 +409,6 @@ restore_nocheck_notrace: 1: INTERRUPT_RETURN .section .fixup,"ax" iret_exc: - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) pushl $0 # no error code pushl $do_iret_error jmp error_code @@ -1023,6 +1021,91 @@ ENTRY(kernel_thread_helper) CFI_ENDPROC ENDPROC(kernel_thread_helper) +#ifdef CONFIG_XEN +ENTRY(xen_hypervisor_callback) + CFI_STARTPROC + pushl $0 + CFI_ADJUST_CFA_OFFSET 4 + SAVE_ALL + TRACE_IRQS_OFF + + /* Check to see if we got the event in the critical + region in xen_iret_direct, after we've reenabled + events and checked for pending events. This simulates + iret instruction's behaviour where it delivers a + pending interrupt when enabling interrupts. */ + movl PT_EIP(%esp),%eax + cmpl $xen_iret_start_crit,%eax + jb 1f + cmpl $xen_iret_end_crit,%eax + jae 1f + + call xen_iret_crit_fixup + +1: mov %esp, %eax + call xen_evtchn_do_upcall + jmp ret_from_intr + CFI_ENDPROC +ENDPROC(xen_hypervisor_callback) + +# Hypervisor uses this for application faults while it executes. +# We get here for two reasons: +# 1. Fault while reloading DS, ES, FS or GS +# 2. Fault while executing IRET +# Category 1 we fix up by reattempting the load, and zeroing the segment +# register if the load fails. +# Category 2 we fix up by jumping to do_iret_error. We cannot use the +# normal Linux return path in this case because if we use the IRET hypercall +# to pop the stack frame we end up in an infinite loop of failsafe callbacks. +# We distinguish between categories by maintaining a status value in EAX. +ENTRY(xen_failsafe_callback) + CFI_STARTPROC + pushl %eax + CFI_ADJUST_CFA_OFFSET 4 + movl $1,%eax +1: mov 4(%esp),%ds +2: mov 8(%esp),%es +3: mov 12(%esp),%fs +4: mov 16(%esp),%gs + testl %eax,%eax + popl %eax + CFI_ADJUST_CFA_OFFSET -4 + lea 16(%esp),%esp + CFI_ADJUST_CFA_OFFSET -16 + jz 5f + addl $16,%esp + jmp iret_exc # EAX != 0 => Category 2 (Bad IRET) +5: pushl $0 # EAX == 0 => Category 1 (Bad segment) + CFI_ADJUST_CFA_OFFSET 4 + SAVE_ALL + jmp ret_from_exception + CFI_ENDPROC + +.section .fixup,"ax" +6: xorl %eax,%eax + movl %eax,4(%esp) + jmp 1b +7: xorl %eax,%eax + movl %eax,8(%esp) + jmp 2b +8: xorl %eax,%eax + movl %eax,12(%esp) + jmp 3b +9: xorl %eax,%eax + movl %eax,16(%esp) + jmp 4b +.previous +.section __ex_table,"a" + .align 4 + .long 1b,6b + .long 2b,7b + .long 3b,8b + .long 4b,9b +.previous +ENDPROC(xen_failsafe_callback) + +#endif /* CONFIG_XEN */ + .section .rodata,"a" #include "syscall_table.S" diff --git a/arch/i386/kernel/head.S b/arch/i386/kernel/head.S index f74dfc419b56..8f0382161c91 100644 --- a/arch/i386/kernel/head.S +++ b/arch/i386/kernel/head.S @@ -162,12 +162,16 @@ page_pde_offset = (__PAGE_OFFSET >> 20); * which will be freed later */ -#ifdef CONFIG_HOTPLUG_CPU -.section .text,"ax",@progbits -#else +#ifndef CONFIG_HOTPLUG_CPU .section .init.text,"ax",@progbits #endif + /* Do an early initialization of the fixmap area */ + movl $(swapper_pg_dir - __PAGE_OFFSET), %edx + movl $(swapper_pg_pmd - __PAGE_OFFSET), %eax + addl $0x007, %eax /* 0x007 = PRESENT+RW+USER */ + movl %eax, 4092(%edx) + #ifdef CONFIG_SMP ENTRY(startup_32_smp) cld @@ -504,9 +508,12 @@ ENTRY(_stext) /* * BSS section */ -.section ".bss.page_aligned","w" +.section ".bss.page_aligned","wa" + .align PAGE_SIZE_asm ENTRY(swapper_pg_dir) .fill 1024,4,0 +ENTRY(swapper_pg_pmd) + .fill 1024,4,0 ENTRY(empty_zero_page) .fill 4096,1,0 @@ -530,6 +537,8 @@ fault_msg: .ascii "Int %d: CR2 %p err %p EIP %p CS %p flags %p\n" .asciz "Stack: %p %p %p %p %p %p %p %p\n" +#include "../xen/xen-head.S" + /* * The IDT and GDT 'descriptors' are a strange 48-bit object * only used by the lidt and lgdt instructions. They are not diff --git a/arch/i386/kernel/hpet.c b/arch/i386/kernel/hpet.c index cbb47519e0cf..533d4932bc79 100644 --- a/arch/i386/kernel/hpet.c +++ b/arch/i386/kernel/hpet.c @@ -5,6 +5,7 @@ #include <linux/init.h> #include <linux/sysdev.h> #include <linux/pm.h> +#include <linux/delay.h> #include <asm/hpet.h> #include <asm/io.h> @@ -187,6 +188,10 @@ static void hpet_set_mode(enum clock_event_mode mode, cfg &= ~HPET_TN_ENABLE; hpet_writel(cfg, HPET_T0_CFG); break; + + case CLOCK_EVT_MODE_RESUME: + hpet_enable_int(); + break; } } @@ -217,6 +222,7 @@ static struct clocksource clocksource_hpet = { .mask = HPET_MASK, .shift = HPET_SHIFT, .flags = CLOCK_SOURCE_IS_CONTINUOUS, + .resume = hpet_start_counter, }; /* @@ -313,7 +319,6 @@ int __init hpet_enable(void) clocksource_register(&clocksource_hpet); - if (id & HPET_ID_LEGSUP) { hpet_enable_int(); hpet_reserve_platform_timers(id); @@ -321,7 +326,7 @@ int __init hpet_enable(void) * Start hpet with the boot cpu mask and make it * global after the IO_APIC has been initialized. */ - hpet_clockevent.cpumask =cpumask_of_cpu(0); + hpet_clockevent.cpumask = cpumask_of_cpu(smp_processor_id()); clockevents_register_device(&hpet_clockevent); global_clock_event = &hpet_clockevent; return 1; @@ -546,68 +551,3 @@ irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } #endif - - -/* - * Suspend/resume part - */ - -#ifdef CONFIG_PM - -static int hpet_suspend(struct sys_device *sys_device, pm_message_t state) -{ - unsigned long cfg = hpet_readl(HPET_CFG); - - cfg &= ~(HPET_CFG_ENABLE|HPET_CFG_LEGACY); - hpet_writel(cfg, HPET_CFG); - - return 0; -} - -static int hpet_resume(struct sys_device *sys_device) -{ - unsigned int id; - - hpet_start_counter(); - - id = hpet_readl(HPET_ID); - - if (id & HPET_ID_LEGSUP) - hpet_enable_int(); - - return 0; -} - -static struct sysdev_class hpet_class = { - set_kset_name("hpet"), - .suspend = hpet_suspend, - .resume = hpet_resume, -}; - -static struct sys_device hpet_device = { - .id = 0, - .cls = &hpet_class, -}; - - -static __init int hpet_register_sysfs(void) -{ - int err; - - if (!is_hpet_capable()) - return 0; - - err = sysdev_class_register(&hpet_class); - - if (!err) { - err = sysdev_register(&hpet_device); - if (err) - sysdev_class_unregister(&hpet_class); - } - - return err; -} - -device_initcall(hpet_register_sysfs); - -#endif diff --git a/arch/i386/kernel/i8253.c b/arch/i386/kernel/i8253.c index f8a3c4054c70..6d839f2f1b1a 100644 --- a/arch/i386/kernel/i8253.c +++ b/arch/i386/kernel/i8253.c @@ -3,18 +3,17 @@ * */ #include <linux/clockchips.h> -#include <linux/spinlock.h> +#include <linux/init.h> +#include <linux/interrupt.h> #include <linux/jiffies.h> -#include <linux/sysdev.h> #include <linux/module.h> -#include <linux/init.h> +#include <linux/spinlock.h> #include <asm/smp.h> #include <asm/delay.h> #include <asm/i8253.h> #include <asm/io.h> - -#include "io_ports.h" +#include <asm/timer.h> DEFINE_SPINLOCK(i8253_lock); EXPORT_SYMBOL(i8253_lock); @@ -41,26 +40,27 @@ static void init_pit_timer(enum clock_event_mode mode, case CLOCK_EVT_MODE_PERIODIC: /* binary, mode 2, LSB/MSB, ch 0 */ outb_p(0x34, PIT_MODE); - udelay(10); outb_p(LATCH & 0xff , PIT_CH0); /* LSB */ - udelay(10); outb(LATCH >> 8 , PIT_CH0); /* MSB */ break; - /* - * Avoid unnecessary state transitions, as it confuses - * Geode / Cyrix based boxen. - */ case CLOCK_EVT_MODE_SHUTDOWN: - if (evt->mode == CLOCK_EVT_MODE_UNUSED) - break; case CLOCK_EVT_MODE_UNUSED: - if (evt->mode == CLOCK_EVT_MODE_SHUTDOWN) - break; + if (evt->mode == CLOCK_EVT_MODE_PERIODIC || + evt->mode == CLOCK_EVT_MODE_ONESHOT) { + outb_p(0x30, PIT_MODE); + outb_p(0, PIT_CH0); + outb_p(0, PIT_CH0); + } + break; + case CLOCK_EVT_MODE_ONESHOT: /* One shot setup */ outb_p(0x38, PIT_MODE); - udelay(10); + break; + + case CLOCK_EVT_MODE_RESUME: + /* Nothing to do here */ break; } spin_unlock_irqrestore(&i8253_lock, flags); diff --git a/arch/i386/kernel/init_task.c b/arch/i386/kernel/init_task.c index cff95d10a4d8..d26fc063a760 100644 --- a/arch/i386/kernel/init_task.c +++ b/arch/i386/kernel/init_task.c @@ -42,5 +42,5 @@ EXPORT_SYMBOL(init_task); * per-CPU TSS segments. Threads are completely 'soft' on Linux, * no more per-task TSS's. */ -DEFINE_PER_CPU(struct tss_struct, init_tss) ____cacheline_internodealigned_in_smp = INIT_TSS; +DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss) = INIT_TSS; diff --git a/arch/i386/kernel/io_apic.c b/arch/i386/kernel/io_apic.c index 7f8b7af2b95f..e2f4a1c68547 100644 --- a/arch/i386/kernel/io_apic.c +++ b/arch/i386/kernel/io_apic.c @@ -353,14 +353,6 @@ static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t cpumask) # include <linux/slab.h> /* kmalloc() */ # include <linux/timer.h> /* time_after() */ -#ifdef CONFIG_BALANCED_IRQ_DEBUG -# define TDprintk(x...) do { printk("<%ld:%s:%d>: ", jiffies, __FILE__, __LINE__); printk(x); } while (0) -# define Dprintk(x...) do { TDprintk(x); } while (0) -# else -# define TDprintk(x...) -# define Dprintk(x...) -# endif - #define IRQBALANCE_CHECK_ARCH -999 #define MAX_BALANCED_IRQ_INTERVAL (5*HZ) #define MIN_BALANCED_IRQ_INTERVAL (HZ/2) @@ -443,7 +435,7 @@ static inline void balance_irq(int cpu, int irq) static inline void rotate_irqs_among_cpus(unsigned long useful_load_threshold) { int i, j; - Dprintk("Rotating IRQs among CPUs.\n"); + for_each_online_cpu(i) { for (j = 0; j < NR_IRQS; j++) { if (!irq_desc[j].action) @@ -560,19 +552,11 @@ tryanothercpu: max_loaded = tmp_loaded; /* processor */ imbalance = (max_cpu_irq - min_cpu_irq) / 2; - Dprintk("max_loaded cpu = %d\n", max_loaded); - Dprintk("min_loaded cpu = %d\n", min_loaded); - Dprintk("max_cpu_irq load = %ld\n", max_cpu_irq); - Dprintk("min_cpu_irq load = %ld\n", min_cpu_irq); - Dprintk("load imbalance = %lu\n", imbalance); - /* if imbalance is less than approx 10% of max load, then * observe diminishing returns action. - quit */ - if (imbalance < (max_cpu_irq >> 3)) { - Dprintk("Imbalance too trivial\n"); + if (imbalance < (max_cpu_irq >> 3)) goto not_worth_the_effort; - } tryanotherirq: /* if we select an IRQ to move that can't go where we want, then @@ -629,9 +613,6 @@ tryanotherirq: cpus_and(tmp, target_cpu_mask, allowed_mask); if (!cpus_empty(tmp)) { - - Dprintk("irq = %d moved to cpu = %d\n", - selected_irq, min_loaded); /* mark for change destination */ set_pending_irq(selected_irq, cpumask_of_cpu(min_loaded)); @@ -651,7 +632,6 @@ not_worth_the_effort: */ balanced_irq_interval = min((long)MAX_BALANCED_IRQ_INTERVAL, balanced_irq_interval + BALANCED_IRQ_MORE_DELTA); - Dprintk("IRQ worth rotating not found\n"); return; } @@ -667,6 +647,7 @@ static int balanced_irq(void *unused) set_pending_irq(i, cpumask_of_cpu(0)); } + set_freezable(); for ( ; ; ) { time_remaining = schedule_timeout_interruptible(time_remaining); try_to_freeze(); @@ -773,14 +754,6 @@ static int pirq_entries [MAX_PIRQS]; static int pirqs_enabled; int skip_ioapic_setup; -static int __init ioapic_setup(char *str) -{ - skip_ioapic_setup = 1; - return 1; -} - -__setup("noapic", ioapic_setup); - static int __init ioapic_pirq_setup(char *str) { int i, max; @@ -1275,12 +1248,15 @@ static struct irq_chip ioapic_chip; static void ioapic_register_intr(int irq, int vector, unsigned long trigger) { if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) || - trigger == IOAPIC_LEVEL) + trigger == IOAPIC_LEVEL) { + irq_desc[irq].status |= IRQ_LEVEL; set_irq_chip_and_handler_name(irq, &ioapic_chip, handle_fasteoi_irq, "fasteoi"); - else + } else { + irq_desc[irq].status &= ~IRQ_LEVEL; set_irq_chip_and_handler_name(irq, &ioapic_chip, handle_edge_irq, "edge"); + } set_intr_gate(vector, interrupt[irq]); } @@ -1901,7 +1877,7 @@ __setup("no_timer_check", notimercheck); * - if this function detects that timer IRQs are defunct, then we fall * back to ISA timer IRQs */ -int __init timer_irq_works(void) +static int __init timer_irq_works(void) { unsigned long t1 = jiffies; diff --git a/arch/i386/kernel/irq.c b/arch/i386/kernel/irq.c index d2daf672f4a2..dd2b97fc00b2 100644 --- a/arch/i386/kernel/irq.c +++ b/arch/i386/kernel/irq.c @@ -21,7 +21,7 @@ #include <asm/apic.h> #include <asm/uaccess.h> -DEFINE_PER_CPU(irq_cpustat_t, irq_stat) ____cacheline_internodealigned_in_smp; +DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); EXPORT_PER_CPU_SYMBOL(irq_stat); DEFINE_PER_CPU(struct pt_regs *, irq_regs); @@ -149,15 +149,11 @@ fastcall unsigned int do_IRQ(struct pt_regs *regs) #ifdef CONFIG_4KSTACKS -/* - * These should really be __section__(".bss.page_aligned") as well, but - * gcc's 3.0 and earlier don't handle that correctly. - */ static char softirq_stack[NR_CPUS * THREAD_SIZE] - __attribute__((__aligned__(THREAD_SIZE))); + __attribute__((__section__(".bss.page_aligned"))); static char hardirq_stack[NR_CPUS * THREAD_SIZE] - __attribute__((__aligned__(THREAD_SIZE))); + __attribute__((__section__(".bss.page_aligned"))); /* * allocate per-cpu stacks for hardirq and for softirq processing diff --git a/arch/i386/kernel/kprobes.c b/arch/i386/kernel/kprobes.c index dde828a333c3..448a50b1324c 100644 --- a/arch/i386/kernel/kprobes.c +++ b/arch/i386/kernel/kprobes.c @@ -35,6 +35,7 @@ #include <asm/cacheflush.h> #include <asm/desc.h> #include <asm/uaccess.h> +#include <asm/alternative.h> void jprobe_return_end(void); @@ -169,16 +170,12 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) void __kprobes arch_arm_kprobe(struct kprobe *p) { - *p->addr = BREAKPOINT_INSTRUCTION; - flush_icache_range((unsigned long) p->addr, - (unsigned long) p->addr + sizeof(kprobe_opcode_t)); + text_poke(p->addr, ((unsigned char []){BREAKPOINT_INSTRUCTION}), 1); } void __kprobes arch_disarm_kprobe(struct kprobe *p) { - *p->addr = p->opcode; - flush_icache_range((unsigned long) p->addr, - (unsigned long) p->addr + sizeof(kprobe_opcode_t)); + text_poke(p->addr, &p->opcode, 1); } void __kprobes arch_remove_kprobe(struct kprobe *p) diff --git a/arch/i386/kernel/microcode.c b/arch/i386/kernel/microcode.c index d865d041bea1..09cf78110358 100644 --- a/arch/i386/kernel/microcode.c +++ b/arch/i386/kernel/microcode.c @@ -82,6 +82,7 @@ #include <linux/miscdevice.h> #include <linux/spinlock.h> #include <linux/mm.h> +#include <linux/fs.h> #include <linux/mutex.h> #include <linux/cpu.h> #include <linux/firmware.h> diff --git a/arch/i386/kernel/nmi.c b/arch/i386/kernel/nmi.c index fba121f7973f..c7227e2180f8 100644 --- a/arch/i386/kernel/nmi.c +++ b/arch/i386/kernel/nmi.c @@ -77,7 +77,7 @@ static int __init check_nmi_watchdog(void) unsigned int *prev_nmi_count; int cpu; - if ((nmi_watchdog == NMI_NONE) || (nmi_watchdog == NMI_DEFAULT)) + if ((nmi_watchdog == NMI_NONE) || (nmi_watchdog == NMI_DISABLED)) return 0; if (!atomic_read(&nmi_active)) @@ -115,12 +115,12 @@ static int __init check_nmi_watchdog(void) atomic_dec(&nmi_active); } } + endflag = 1; if (!atomic_read(&nmi_active)) { kfree(prev_nmi_count); atomic_set(&nmi_active, -1); return -1; } - endflag = 1; printk("OK.\n"); /* now that we know it works we can reduce NMI frequency to @@ -295,7 +295,7 @@ static unsigned int last_irq_sums [NR_CPUS], alert_counter [NR_CPUS]; -void touch_nmi_watchdog (void) +void touch_nmi_watchdog(void) { if (nmi_watchdog > 0) { unsigned cpu; @@ -304,8 +304,10 @@ void touch_nmi_watchdog (void) * Just reset the alert counters, (other CPUs might be * spinning on locks we hold): */ - for_each_present_cpu (cpu) - alert_counter[cpu] = 0; + for_each_present_cpu(cpu) { + if (alert_counter[cpu]) + alert_counter[cpu] = 0; + } } /* @@ -351,7 +353,7 @@ __kprobes int nmi_watchdog_tick(struct pt_regs * regs, unsigned reason) * Take the local apic timer and PIT/HPET into account. We don't * know which one is active, when we have highres/dyntick on */ - sum = per_cpu(irq_stat, cpu).apic_timer_irqs + kstat_irqs(0); + sum = per_cpu(irq_stat, cpu).apic_timer_irqs + kstat_cpu(cpu).irqs[0]; /* if the none of the timers isn't firing, this cpu isn't doing much */ if (!touched && last_irq_sums[cpu] == sum) { @@ -422,7 +424,7 @@ int proc_nmi_enabled(struct ctl_table *table, int write, struct file *file, if (!!old_state == !!nmi_watchdog_enabled) return 0; - if (atomic_read(&nmi_active) < 0) { + if (atomic_read(&nmi_active) < 0 || nmi_watchdog == NMI_DISABLED) { printk( KERN_WARNING "NMI watchdog is permanently disabled\n"); return -EIO; } diff --git a/arch/i386/kernel/paravirt.c b/arch/i386/kernel/paravirt.c index faab09abca5e..739cfb207dd7 100644 --- a/arch/i386/kernel/paravirt.c +++ b/arch/i386/kernel/paravirt.c @@ -69,7 +69,8 @@ DEF_NATIVE(read_tsc, "rdtsc"); DEF_NATIVE(ud2a, "ud2a"); -static unsigned native_patch(u8 type, u16 clobbers, void *insns, unsigned len) +static unsigned native_patch(u8 type, u16 clobbers, void *ibuf, + unsigned long addr, unsigned len) { const unsigned char *start, *end; unsigned ret; @@ -90,7 +91,7 @@ static unsigned native_patch(u8 type, u16 clobbers, void *insns, unsigned len) #undef SITE patch_site: - ret = paravirt_patch_insns(insns, len, start, end); + ret = paravirt_patch_insns(ibuf, len, start, end); break; case PARAVIRT_PATCH(make_pgd): @@ -107,7 +108,7 @@ static unsigned native_patch(u8 type, u16 clobbers, void *insns, unsigned len) break; default: - ret = paravirt_patch_default(type, clobbers, insns, len); + ret = paravirt_patch_default(type, clobbers, ibuf, addr, len); break; } @@ -124,63 +125,72 @@ unsigned paravirt_patch_ignore(unsigned len) return len; } -unsigned paravirt_patch_call(void *target, u16 tgt_clobbers, - void *site, u16 site_clobbers, +struct branch { + unsigned char opcode; + u32 delta; +} __attribute__((packed)); + +unsigned paravirt_patch_call(void *insnbuf, + const void *target, u16 tgt_clobbers, + unsigned long addr, u16 site_clobbers, unsigned len) { - unsigned char *call = site; - unsigned long delta = (unsigned long)target - (unsigned long)(call+5); + struct branch *b = insnbuf; + unsigned long delta = (unsigned long)target - (addr+5); if (tgt_clobbers & ~site_clobbers) return len; /* target would clobber too much for this site */ if (len < 5) return len; /* call too long for patch site */ - *call++ = 0xe8; /* call */ - *(unsigned long *)call = delta; + b->opcode = 0xe8; /* call */ + b->delta = delta; + BUILD_BUG_ON(sizeof(*b) != 5); return 5; } -unsigned paravirt_patch_jmp(void *target, void *site, unsigned len) +unsigned paravirt_patch_jmp(const void *target, void *insnbuf, + unsigned long addr, unsigned len) { - unsigned char *jmp = site; - unsigned long delta = (unsigned long)target - (unsigned long)(jmp+5); + struct branch *b = insnbuf; + unsigned long delta = (unsigned long)target - (addr+5); if (len < 5) return len; /* call too long for patch site */ - *jmp++ = 0xe9; /* jmp */ - *(unsigned long *)jmp = delta; + b->opcode = 0xe9; /* jmp */ + b->delta = delta; return 5; } -unsigned paravirt_patch_default(u8 type, u16 clobbers, void *site, unsigned len) +unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf, + unsigned long addr, unsigned len) { void *opfunc = *((void **)¶virt_ops + type); unsigned ret; if (opfunc == NULL) /* If there's no function, patch it with a ud2a (BUG) */ - ret = paravirt_patch_insns(site, len, start_ud2a, end_ud2a); + ret = paravirt_patch_insns(insnbuf, len, start_ud2a, end_ud2a); else if (opfunc == paravirt_nop) /* If the operation is a nop, then nop the callsite */ ret = paravirt_patch_nop(); else if (type == PARAVIRT_PATCH(iret) || type == PARAVIRT_PATCH(irq_enable_sysexit)) /* If operation requires a jmp, then jmp */ - ret = paravirt_patch_jmp(opfunc, site, len); + ret = paravirt_patch_jmp(opfunc, insnbuf, addr, len); else /* Otherwise call the function; assume target could clobber any caller-save reg */ - ret = paravirt_patch_call(opfunc, CLBR_ANY, - site, clobbers, len); + ret = paravirt_patch_call(insnbuf, opfunc, CLBR_ANY, + addr, clobbers, len); return ret; } -unsigned paravirt_patch_insns(void *site, unsigned len, +unsigned paravirt_patch_insns(void *insnbuf, unsigned len, const char *start, const char *end) { unsigned insn_len = end - start; @@ -188,7 +198,7 @@ unsigned paravirt_patch_insns(void *site, unsigned len, if (insn_len > len || start == NULL) insn_len = len; else - memcpy(site, start, insn_len); + memcpy(insnbuf, start, insn_len); return insn_len; } @@ -228,6 +238,41 @@ static int __init print_banner(void) } core_initcall(print_banner); +static struct resource reserve_ioports = { + .start = 0, + .end = IO_SPACE_LIMIT, + .name = "paravirt-ioport", + .flags = IORESOURCE_IO | IORESOURCE_BUSY, +}; + +static struct resource reserve_iomem = { + .start = 0, + .end = -1, + .name = "paravirt-iomem", + .flags = IORESOURCE_MEM | IORESOURCE_BUSY, +}; + +/* + * Reserve the whole legacy IO space to prevent any legacy drivers + * from wasting time probing for their hardware. This is a fairly + * brute-force approach to disabling all non-virtual drivers. + * + * Note that this must be called very early to have any effect. + */ +int paravirt_disable_iospace(void) +{ + int ret; + + ret = request_resource(&ioport_resource, &reserve_ioports); + if (ret == 0) { + ret = request_resource(&iomem_resource, &reserve_iomem); + if (ret) + release_resource(&reserve_ioports); + } + + return ret; +} + struct paravirt_ops paravirt_ops = { .name = "bare hardware", .paravirt_enabled = 0, @@ -267,7 +312,7 @@ struct paravirt_ops paravirt_ops = { .write_msr = native_write_msr_safe, .read_tsc = native_read_tsc, .read_pmc = native_read_pmc, - .get_scheduled_cycles = native_read_tsc, + .sched_clock = native_sched_clock, .get_cpu_khz = native_calculate_cpu_khz, .load_tr_desc = native_load_tr_desc, .set_ldt = native_set_ldt, diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c index 06dfa65ad180..84664710b784 100644 --- a/arch/i386/kernel/process.c +++ b/arch/i386/kernel/process.c @@ -300,6 +300,7 @@ early_param("idle", idle_setup); void show_regs(struct pt_regs * regs) { unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L; + unsigned long d0, d1, d2, d3, d6, d7; printk("\n"); printk("Pid: %d, comm: %20s\n", current->pid, current->comm); @@ -324,6 +325,17 @@ void show_regs(struct pt_regs * regs) cr3 = read_cr3(); cr4 = read_cr4_safe(); printk("CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n", cr0, cr2, cr3, cr4); + + get_debugreg(d0, 0); + get_debugreg(d1, 1); + get_debugreg(d2, 2); + get_debugreg(d3, 3); + printk("DR0: %08lx DR1: %08lx DR2: %08lx DR3: %08lx\n", + d0, d1, d2, d3); + get_debugreg(d6, 6); + get_debugreg(d7, 7); + printk("DR6: %08lx DR7: %08lx\n", d6, d7); + show_trace(NULL, regs, ®s->esp); } @@ -538,8 +550,31 @@ int dump_task_regs(struct task_struct *tsk, elf_gregset_t *regs) return 1; } -static noinline void __switch_to_xtra(struct task_struct *next_p, - struct tss_struct *tss) +#ifdef CONFIG_SECCOMP +void hard_disable_TSC(void) +{ + write_cr4(read_cr4() | X86_CR4_TSD); +} +void disable_TSC(void) +{ + preempt_disable(); + if (!test_and_set_thread_flag(TIF_NOTSC)) + /* + * Must flip the CPU state synchronously with + * TIF_NOTSC in the current running context. + */ + hard_disable_TSC(); + preempt_enable(); +} +void hard_enable_TSC(void) +{ + write_cr4(read_cr4() & ~X86_CR4_TSD); +} +#endif /* CONFIG_SECCOMP */ + +static noinline void +__switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, + struct tss_struct *tss) { struct thread_struct *next; @@ -555,6 +590,17 @@ static noinline void __switch_to_xtra(struct task_struct *next_p, set_debugreg(next->debugreg[7], 7); } +#ifdef CONFIG_SECCOMP + if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^ + test_tsk_thread_flag(next_p, TIF_NOTSC)) { + /* prev and next are different */ + if (test_tsk_thread_flag(next_p, TIF_NOTSC)) + hard_disable_TSC(); + else + hard_enable_TSC(); + } +#endif + if (!test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) { /* * Disable the bitmap via an invalid offset. We still cache @@ -586,33 +632,6 @@ static noinline void __switch_to_xtra(struct task_struct *next_p, } /* - * This function selects if the context switch from prev to next - * has to tweak the TSC disable bit in the cr4. - */ -static inline void disable_tsc(struct task_struct *prev_p, - struct task_struct *next_p) -{ - struct thread_info *prev, *next; - - /* - * gcc should eliminate the ->thread_info dereference if - * has_secure_computing returns 0 at compile time (SECCOMP=n). - */ - prev = task_thread_info(prev_p); - next = task_thread_info(next_p); - - if (has_secure_computing(prev) || has_secure_computing(next)) { - /* slow path here */ - if (has_secure_computing(prev) && - !has_secure_computing(next)) { - write_cr4(read_cr4() & ~X86_CR4_TSD); - } else if (!has_secure_computing(prev) && - has_secure_computing(next)) - write_cr4(read_cr4() | X86_CR4_TSD); - } -} - -/* * switch_to(x,yn) should switch tasks from x to y. * * We fsave/fwait so that an exception goes off at the right time @@ -689,11 +708,9 @@ struct task_struct fastcall * __switch_to(struct task_struct *prev_p, struct tas /* * Now maybe handle debug registers and/or IO bitmaps */ - if (unlikely((task_thread_info(next_p)->flags & _TIF_WORK_CTXSW) - || test_tsk_thread_flag(prev_p, TIF_IO_BITMAP))) - __switch_to_xtra(next_p, tss); - - disable_tsc(prev_p, next_p); + if (unlikely(task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV || + task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT)) + __switch_to_xtra(prev_p, next_p, tss); /* * Leave lazy mode, flushing any hypercalls made here. diff --git a/arch/i386/kernel/ptrace.c b/arch/i386/kernel/ptrace.c index 0c0ceec5de00..7c1b92522e95 100644 --- a/arch/i386/kernel/ptrace.c +++ b/arch/i386/kernel/ptrace.c @@ -164,14 +164,22 @@ static unsigned long convert_eip_to_linear(struct task_struct *child, struct pt_ u32 *desc; unsigned long base; - down(&child->mm->context.sem); - desc = child->mm->context.ldt + (seg & ~7); - base = (desc[0] >> 16) | ((desc[1] & 0xff) << 16) | (desc[1] & 0xff000000); + seg &= ~7UL; - /* 16-bit code segment? */ - if (!((desc[1] >> 22) & 1)) - addr &= 0xffff; - addr += base; + down(&child->mm->context.sem); + if (unlikely((seg >> 3) >= child->mm->context.size)) + addr = -1L; /* bogus selector, access would fault */ + else { + desc = child->mm->context.ldt + seg; + base = ((desc[0] >> 16) | + ((desc[1] & 0xff) << 16) | + (desc[1] & 0xff000000)); + + /* 16-bit code segment? */ + if (!((desc[1] >> 22) & 1)) + addr &= 0xffff; + addr += base; + } up(&child->mm->context.sem); } return addr; @@ -266,7 +274,6 @@ static void clear_singlestep(struct task_struct *child) void ptrace_disable(struct task_struct *child) { clear_singlestep(child); - clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE); clear_tsk_thread_flag(child, TIF_SYSCALL_EMU); } @@ -358,17 +365,9 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) switch (request) { /* when I and D space are separate, these will need to be fixed. */ case PTRACE_PEEKTEXT: /* read word at location addr. */ - case PTRACE_PEEKDATA: { - unsigned long tmp; - int copied; - - copied = access_process_vm(child, addr, &tmp, sizeof(tmp), 0); - ret = -EIO; - if (copied != sizeof(tmp)) - break; - ret = put_user(tmp, datap); + case PTRACE_PEEKDATA: + ret = generic_ptrace_peekdata(child, addr, data); break; - } /* read the word at location addr in the USER area. */ case PTRACE_PEEKUSR: { @@ -395,10 +394,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) /* when I and D space are separate, this will have to be fixed. */ case PTRACE_POKETEXT: /* write the word at location addr. */ case PTRACE_POKEDATA: - ret = 0; - if (access_process_vm(child, addr, &data, sizeof(data), 1) == sizeof(data)) - break; - ret = -EIO; + ret = generic_ptrace_pokedata(child, addr, data); break; case PTRACE_POKEUSR: /* write the word at location addr in the USER area */ diff --git a/arch/i386/kernel/reboot.c b/arch/i386/kernel/reboot.c index 5513f8d5b5be..0d796248866c 100644 --- a/arch/i386/kernel/reboot.c +++ b/arch/i386/kernel/reboot.c @@ -113,6 +113,15 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge 300/"), }, }, + { /* Handle problems with rebooting on Dell Optiplex 745's SFF*/ + .callback = set_bios_reboot, + .ident = "Dell OptiPlex 745", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 745"), + DMI_MATCH(DMI_BOARD_NAME, "0WF810"), + }, + }, { /* Handle problems with rebooting on Dell 2400's */ .callback = set_bios_reboot, .ident = "Dell PowerEdge 2400", diff --git a/arch/i386/kernel/setup.c b/arch/i386/kernel/setup.c index 698c24fe482e..d474cd639bcb 100644 --- a/arch/i386/kernel/setup.c +++ b/arch/i386/kernel/setup.c @@ -102,19 +102,10 @@ static unsigned int highmem_pages = -1; /* * Setup options */ -struct drive_info_struct { char dummy[32]; } drive_info; -#if defined(CONFIG_BLK_DEV_IDE) || defined(CONFIG_BLK_DEV_HD) || \ - defined(CONFIG_BLK_DEV_IDE_MODULE) || defined(CONFIG_BLK_DEV_HD_MODULE) -EXPORT_SYMBOL(drive_info); -#endif struct screen_info screen_info; EXPORT_SYMBOL(screen_info); struct apm_info apm_info; EXPORT_SYMBOL(apm_info); -struct sys_desc_table_struct { - unsigned short length; - unsigned char table[0]; -}; struct edid_info edid_info; EXPORT_SYMBOL_GPL(edid_info); struct ist_info ist_info; @@ -134,7 +125,7 @@ unsigned long saved_videomode; static char __initdata command_line[COMMAND_LINE_SIZE]; -unsigned char __initdata boot_params[PARAM_SIZE]; +struct boot_params __initdata boot_params; #if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE) struct edd edd; @@ -282,18 +273,18 @@ unsigned long __init find_max_low_pfn(void) printk(KERN_WARNING "Warning only %ldMB will be used.\n", MAXMEM>>20); if (max_pfn > MAX_NONPAE_PFN) - printk(KERN_WARNING "Use a PAE enabled kernel.\n"); + printk(KERN_WARNING "Use a HIGHMEM64G enabled kernel.\n"); else printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n"); max_pfn = MAXMEM_PFN; #else /* !CONFIG_HIGHMEM */ -#ifndef CONFIG_X86_PAE +#ifndef CONFIG_HIGHMEM64G if (max_pfn > MAX_NONPAE_PFN) { max_pfn = MAX_NONPAE_PFN; printk(KERN_WARNING "Warning only 4GB will be used.\n"); - printk(KERN_WARNING "Use a PAE enabled kernel.\n"); + printk(KERN_WARNING "Use a HIGHMEM64G enabled kernel.\n"); } -#endif /* !CONFIG_X86_PAE */ +#endif /* !CONFIG_HIGHMEM64G */ #endif /* !CONFIG_HIGHMEM */ } else { if (highmem_pages == -1) @@ -475,7 +466,7 @@ void __init setup_bootmem_allocator(void) * * This should all compile down to nothing when NUMA is off. */ -void __init remapped_pgdat_init(void) +static void __init remapped_pgdat_init(void) { int nid; @@ -528,7 +519,6 @@ void __init setup_arch(char **cmdline_p) #endif ROOT_DEV = old_decode_dev(ORIG_ROOT_DEV); - drive_info = DRIVE_INFO; screen_info = SCREEN_INFO; edid_info = EDID_INFO; apm_info.bios = APM_BIOS_INFO; @@ -611,6 +601,8 @@ void __init setup_arch(char **cmdline_p) * NOTE: at this point the bootmem allocator is fully available. */ + paravirt_post_allocator_init(); + dmi_scan_machine(); #ifdef CONFIG_X86_GENERICARCH @@ -648,6 +640,7 @@ void __init setup_arch(char **cmdline_p) #endif e820_register_memory(); + e820_mark_nosave_regions(); #ifdef CONFIG_VT #if defined(CONFIG_VGA_CONSOLE) diff --git a/arch/i386/kernel/signal.c b/arch/i386/kernel/signal.c index d574e38f0f77..f5dd85656c18 100644 --- a/arch/i386/kernel/signal.c +++ b/arch/i386/kernel/signal.c @@ -199,6 +199,13 @@ asmlinkage int sys_sigreturn(unsigned long __unused) return eax; badframe: + if (show_unhandled_signals && printk_ratelimit()) + printk("%s%s[%d] bad frame in sigreturn frame:%p eip:%lx" + " esp:%lx oeax:%lx\n", + current->pid > 1 ? KERN_INFO : KERN_EMERG, + current->comm, current->pid, frame, regs->eip, + regs->esp, regs->orig_eax); + force_sig(SIGSEGV, current); return 0; } diff --git a/arch/i386/kernel/smp.c b/arch/i386/kernel/smp.c index 6299c080f6e2..2d35d8502029 100644 --- a/arch/i386/kernel/smp.c +++ b/arch/i386/kernel/smp.c @@ -22,6 +22,7 @@ #include <asm/mtrr.h> #include <asm/tlbflush.h> +#include <asm/mmu_context.h> #include <mach_apic.h> /* @@ -249,13 +250,13 @@ static unsigned long flush_va; static DEFINE_SPINLOCK(tlbstate_lock); /* - * We cannot call mmdrop() because we are in interrupt context, + * We cannot call mmdrop() because we are in interrupt context, * instead update mm->cpu_vm_mask. * * We need to reload %cr3 since the page tables may be going * away from under us.. */ -static inline void leave_mm (unsigned long cpu) +void leave_mm(unsigned long cpu) { if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_OK) BUG(); diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c index 88baed1e7e83..e4f61d1c6248 100644 --- a/arch/i386/kernel/smpboot.c +++ b/arch/i386/kernel/smpboot.c @@ -148,7 +148,7 @@ void __init smp_alloc_memory(void) * a given CPU */ -static void __cpuinit smp_store_cpu_info(int id) +void __cpuinit smp_store_cpu_info(int id) { struct cpuinfo_x86 *c = cpu_data + id; @@ -308,8 +308,7 @@ cpumask_t cpu_coregroup_map(int cpu) /* representing cpus for which sibling maps can be computed */ static cpumask_t cpu_sibling_setup_map; -static inline void -set_cpu_sibling_map(int cpu) +void __cpuinit set_cpu_sibling_map(int cpu) { int i; struct cpuinfo_x86 *c = cpu_data; @@ -941,17 +940,6 @@ exit: } #endif -static void smp_tune_scheduling(void) -{ - if (cpu_khz) { - /* cache size in kB */ - long cachesize = boot_cpu_data.x86_cache_size; - - if (cachesize > 0) - max_cache_size = cachesize * 1024; - } -} - /* * Cycle through the processors sending APIC IPIs to boot each. */ @@ -980,7 +968,6 @@ static void __init smp_boot_cpus(unsigned int max_cpus) x86_cpu_to_apicid[0] = boot_cpu_physical_apicid; current_thread_info()->cpu = 0; - smp_tune_scheduling(); set_cpu_sibling_map(0); @@ -1156,8 +1143,7 @@ void __init native_smp_prepare_boot_cpu(void) } #ifdef CONFIG_HOTPLUG_CPU -static void -remove_siblinginfo(int cpu) +void remove_siblinginfo(int cpu) { int sibling; struct cpuinfo_x86 *c = cpu_data; diff --git a/arch/i386/kernel/smpcommon.c b/arch/i386/kernel/smpcommon.c index 1868ae18eb4d..bbfe85a0f699 100644 --- a/arch/i386/kernel/smpcommon.c +++ b/arch/i386/kernel/smpcommon.c @@ -47,7 +47,7 @@ int smp_call_function(void (*func) (void *info), void *info, int nonatomic, EXPORT_SYMBOL(smp_call_function); /** - * smp_call_function_single - Run a function on another CPU + * smp_call_function_single - Run a function on a specific CPU * @cpu: The target CPU. Cannot be the calling CPU. * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. @@ -66,9 +66,11 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info, int ret; int me = get_cpu(); if (cpu == me) { - WARN_ON(1); + local_irq_disable(); + func(info); + local_irq_enable(); put_cpu(); - return -EBUSY; + return 0; } ret = smp_call_function_mask(cpumask_of_cpu(cpu), func, info, wait); diff --git a/arch/i386/kernel/sys_i386.c b/arch/i386/kernel/sys_i386.c index e5dcb9379018..42147304de88 100644 --- a/arch/i386/kernel/sys_i386.c +++ b/arch/i386/kernel/sys_i386.c @@ -9,6 +9,7 @@ #include <linux/errno.h> #include <linux/sched.h> #include <linux/mm.h> +#include <linux/fs.h> #include <linux/smp.h> #include <linux/sem.h> #include <linux/msg.h> diff --git a/arch/i386/kernel/syscall_table.S b/arch/i386/kernel/syscall_table.S index bf6adce52267..8344c70adf61 100644 --- a/arch/i386/kernel/syscall_table.S +++ b/arch/i386/kernel/syscall_table.S @@ -323,3 +323,4 @@ ENTRY(sys_call_table) .long sys_signalfd .long sys_timerfd .long sys_eventfd + .long sys_fallocate diff --git a/arch/i386/kernel/sysenter.c b/arch/i386/kernel/sysenter.c index 6deb159d08e0..4eb2e408764f 100644 --- a/arch/i386/kernel/sysenter.c +++ b/arch/i386/kernel/sysenter.c @@ -16,6 +16,7 @@ #include <linux/string.h> #include <linux/elf.h> #include <linux/mm.h> +#include <linux/err.h> #include <linux/module.h> #include <asm/cpufeature.h> diff --git a/arch/i386/kernel/time.c b/arch/i386/kernel/time.c index a665df61f08c..19a6c678d02e 100644 --- a/arch/i386/kernel/time.c +++ b/arch/i386/kernel/time.c @@ -207,55 +207,9 @@ unsigned long read_persistent_clock(void) return retval; } -static void sync_cmos_clock(unsigned long dummy); - -static DEFINE_TIMER(sync_cmos_timer, sync_cmos_clock, 0, 0); -int no_sync_cmos_clock; - -static void sync_cmos_clock(unsigned long dummy) -{ - struct timeval now, next; - int fail = 1; - - /* - * If we have an externally synchronized Linux clock, then update - * CMOS clock accordingly every ~11 minutes. Set_rtc_mmss() has to be - * called as close as possible to 500 ms before the new second starts. - * This code is run on a timer. If the clock is set, that timer - * may not expire at the correct time. Thus, we adjust... - */ - if (!ntp_synced()) - /* - * Not synced, exit, do not restart a timer (if one is - * running, let it run out). - */ - return; - - do_gettimeofday(&now); - if (now.tv_usec >= USEC_AFTER - ((unsigned) TICK_SIZE) / 2 && - now.tv_usec <= USEC_BEFORE + ((unsigned) TICK_SIZE) / 2) - fail = set_rtc_mmss(now.tv_sec); - - next.tv_usec = USEC_AFTER - now.tv_usec; - if (next.tv_usec <= 0) - next.tv_usec += USEC_PER_SEC; - - if (!fail) - next.tv_sec = 659; - else - next.tv_sec = 0; - - if (next.tv_usec >= USEC_PER_SEC) { - next.tv_sec++; - next.tv_usec -= USEC_PER_SEC; - } - mod_timer(&sync_cmos_timer, jiffies + timeval_to_jiffies(&next)); -} - -void notify_arch_cmos_timer(void) +int update_persistent_clock(struct timespec now) { - if (!no_sync_cmos_clock) - mod_timer(&sync_cmos_timer, jiffies + 1); + return set_rtc_mmss(now.tv_sec); } extern void (*late_time_init)(void); diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c index 90da0575fcff..47b0bef335bd 100644 --- a/arch/i386/kernel/traps.c +++ b/arch/i386/kernel/traps.c @@ -41,6 +41,10 @@ #include <linux/mca.h> #endif +#if defined(CONFIG_EDAC) +#include <linux/edac.h> +#endif + #include <asm/processor.h> #include <asm/system.h> #include <asm/io.h> @@ -96,36 +100,45 @@ asmlinkage void machine_check(void); int kstack_depth_to_print = 24; static unsigned int code_bytes = 64; -static inline int valid_stack_ptr(struct thread_info *tinfo, void *p) +static inline int valid_stack_ptr(struct thread_info *tinfo, void *p, unsigned size) { return p > (void *)tinfo && - p < (void *)tinfo + THREAD_SIZE - 3; + p <= (void *)tinfo + THREAD_SIZE - size; } +/* The form of the top of the frame on the stack */ +struct stack_frame { + struct stack_frame *next_frame; + unsigned long return_address; +}; + static inline unsigned long print_context_stack(struct thread_info *tinfo, unsigned long *stack, unsigned long ebp, struct stacktrace_ops *ops, void *data) { - unsigned long addr; - #ifdef CONFIG_FRAME_POINTER - while (valid_stack_ptr(tinfo, (void *)ebp)) { - unsigned long new_ebp; - addr = *(unsigned long *)(ebp + 4); + struct stack_frame *frame = (struct stack_frame *)ebp; + while (valid_stack_ptr(tinfo, frame, sizeof(*frame))) { + struct stack_frame *next; + unsigned long addr; + + addr = frame->return_address; ops->address(data, addr); /* * break out of recursive entries (such as * end_of_stack_stop_unwind_function). Also, * we can never allow a frame pointer to * move downwards! - */ - new_ebp = *(unsigned long *)ebp; - if (new_ebp <= ebp) + */ + next = frame->next_frame; + if (next <= frame) break; - ebp = new_ebp; + frame = next; } #else - while (valid_stack_ptr(tinfo, stack)) { + while (valid_stack_ptr(tinfo, stack, sizeof(*stack))) { + unsigned long addr; + addr = *stack++; if (__kernel_text_address(addr)) ops->address(data, addr); @@ -148,7 +161,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, if (!stack) { unsigned long dummy; stack = &dummy; - if (task && task != current) + if (task != current) stack = (unsigned long *)task->thread.esp; } @@ -207,6 +220,7 @@ static void print_trace_address(void *data, unsigned long addr) { printk("%s [<%08lx>] ", (char *)data, addr); print_symbol("%s\n", addr); + touch_nmi_watchdog(); } static struct stacktrace_ops print_trace_ops = { @@ -390,7 +404,7 @@ void die(const char * str, struct pt_regs * regs, long err) unsigned long esp; unsigned short ss; - report_bug(regs->eip); + report_bug(regs->eip, regs); printk(KERN_EMERG "%s: %04lx [#%d]\n", str, err & 0xffff, ++die_counter); #ifdef CONFIG_PREEMPT @@ -433,6 +447,7 @@ void die(const char * str, struct pt_regs * regs, long err) bust_spinlocks(0); die.lock_owner = -1; + add_taint(TAINT_DIE); spin_unlock_irqrestore(&die.lock, flags); if (!regs) @@ -517,10 +532,12 @@ fastcall void do_##name(struct pt_regs * regs, long error_code) \ do_trap(trapnr, signr, str, 0, regs, error_code, NULL); \ } -#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \ +#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr, irq) \ fastcall void do_##name(struct pt_regs * regs, long error_code) \ { \ siginfo_t info; \ + if (irq) \ + local_irq_enable(); \ info.si_signo = signr; \ info.si_errno = 0; \ info.si_code = sicode; \ @@ -560,13 +577,13 @@ DO_VM86_ERROR( 3, SIGTRAP, "int3", int3) #endif DO_VM86_ERROR( 4, SIGSEGV, "overflow", overflow) DO_VM86_ERROR( 5, SIGSEGV, "bounds", bounds) -DO_ERROR_INFO( 6, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN, regs->eip) +DO_ERROR_INFO( 6, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN, regs->eip, 0) DO_ERROR( 9, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun) DO_ERROR(10, SIGSEGV, "invalid TSS", invalid_TSS) DO_ERROR(11, SIGBUS, "segment not present", segment_not_present) DO_ERROR(12, SIGBUS, "stack segment", stack_segment) -DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0) -DO_ERROR_INFO(32, SIGSEGV, "iret exception", iret_error, ILL_BADSTK, 0) +DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0, 0) +DO_ERROR_INFO(32, SIGSEGV, "iret exception", iret_error, ILL_BADSTK, 0, 1) fastcall void __kprobes do_general_protection(struct pt_regs * regs, long error_code) @@ -610,6 +627,13 @@ fastcall void __kprobes do_general_protection(struct pt_regs * regs, current->thread.error_code = error_code; current->thread.trap_no = 13; + if (show_unhandled_signals && unhandled_signal(current, SIGSEGV) && + printk_ratelimit()) + printk(KERN_INFO + "%s[%d] general protection eip:%lx esp:%lx error:%lx\n", + current->comm, current->pid, + regs->eip, regs->esp, error_code); + force_sig(SIGSEGV, current); return; @@ -635,6 +659,14 @@ mem_parity_error(unsigned char reason, struct pt_regs * regs) printk(KERN_EMERG "Uhhuh. NMI received for unknown reason %02x on " "CPU %d.\n", reason, smp_processor_id()); printk(KERN_EMERG "You have some hardware problem, likely on the PCI bus.\n"); + +#if defined(CONFIG_EDAC) + if(edac_handler_set()) { + edac_atomic_assert_error(); + return; + } +#endif + if (panic_on_unrecovered_nmi) panic("NMI: Not continuing"); @@ -752,6 +784,8 @@ static __kprobes void default_do_nmi(struct pt_regs * regs) reassert_nmi(); } +static int ignore_nmis; + fastcall __kprobes void do_nmi(struct pt_regs * regs, long error_code) { int cpu; @@ -762,11 +796,24 @@ fastcall __kprobes void do_nmi(struct pt_regs * regs, long error_code) ++nmi_count(cpu); - default_do_nmi(regs); + if (!ignore_nmis) + default_do_nmi(regs); nmi_exit(); } +void stop_nmi(void) +{ + acpi_nmi_disable(); + ignore_nmis++; +} + +void restart_nmi(void) +{ + ignore_nmis--; + acpi_nmi_enable(); +} + #ifdef CONFIG_KPROBES fastcall void __kprobes do_int3(struct pt_regs *regs, long error_code) { @@ -1053,6 +1100,7 @@ asmlinkage void math_state_restore(void) thread->status |= TS_USEDFPU; /* So we fnsave on switch_to() */ tsk->fpu_counter++; } +EXPORT_SYMBOL_GPL(math_state_restore); #ifndef CONFIG_MATH_EMULATION diff --git a/arch/i386/kernel/tsc.c b/arch/i386/kernel/tsc.c index f64b81f3033b..a39280b4dd3a 100644 --- a/arch/i386/kernel/tsc.c +++ b/arch/i386/kernel/tsc.c @@ -4,6 +4,7 @@ * See comments there for proper credits. */ +#include <linux/sched.h> #include <linux/clocksource.h> #include <linux/workqueue.h> #include <linux/cpufreq.h> @@ -26,6 +27,7 @@ static int tsc_enabled; * an extra value to store the TSC freq */ unsigned int tsc_khz; +EXPORT_SYMBOL_GPL(tsc_khz); int tsc_disable; @@ -57,10 +59,11 @@ __setup("notsc", tsc_setup); */ static int tsc_unstable; -static inline int check_tsc_unstable(void) +int check_tsc_unstable(void) { return tsc_unstable; } +EXPORT_SYMBOL_GPL(check_tsc_unstable); /* Accellerators for sched_clock() * convert from cycles(64bits) => nanoseconds (64bits) @@ -83,7 +86,7 @@ static inline int check_tsc_unstable(void) * * -johnstul@us.ibm.com "math is hard, lets go shopping!" */ -static unsigned long cyc2ns_scale __read_mostly; +unsigned long cyc2ns_scale __read_mostly; #define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */ @@ -92,32 +95,44 @@ static inline void set_cyc2ns_scale(unsigned long cpu_khz) cyc2ns_scale = (1000000 << CYC2NS_SCALE_FACTOR)/cpu_khz; } -static inline unsigned long long cycles_2_ns(unsigned long long cyc) -{ - return (cyc * cyc2ns_scale) >> CYC2NS_SCALE_FACTOR; -} - /* * Scheduler clock - returns current time in nanosec units. */ -unsigned long long sched_clock(void) +unsigned long long native_sched_clock(void) { unsigned long long this_offset; /* * Fall back to jiffies if there's no TSC available: + * ( But note that we still use it if the TSC is marked + * unstable. We do this because unlike Time Of Day, + * the scheduler clock tolerates small errors and it's + * very important for it to be as fast as the platform + * can achive it. ) */ - if (unlikely(!tsc_enabled)) + if (unlikely(!tsc_enabled && !tsc_unstable)) /* No locking but a rare wrong value is not a big deal: */ return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ); /* read the Time Stamp Counter: */ - get_scheduled_cycles(this_offset); + rdtscll(this_offset); /* return the value in ns */ return cycles_2_ns(this_offset); } +/* We need to define a real function for sched_clock, to override the + weak default version */ +#ifdef CONFIG_PARAVIRT +unsigned long long sched_clock(void) +{ + return paravirt_sched_clock(); +} +#else +unsigned long long sched_clock(void) + __attribute__((alias("native_sched_clock"))); +#endif + unsigned long native_calculate_cpu_khz(void) { unsigned long long start, end; diff --git a/arch/i386/kernel/verify_cpu.S b/arch/i386/kernel/verify_cpu.S deleted file mode 100644 index f1d1eacf4ab0..000000000000 --- a/arch/i386/kernel/verify_cpu.S +++ /dev/null @@ -1,94 +0,0 @@ -/* Check if CPU has some minimum CPUID bits - This runs in 16bit mode so that the caller can still use the BIOS - to output errors on the screen */ -#include <asm/cpufeature.h> -#include <asm/msr.h> - -verify_cpu: - pushfl # Save caller passed flags - pushl $0 # Kill any dangerous flags - popfl - -#if CONFIG_X86_MINIMUM_CPU_MODEL >= 4 - pushfl - pop %eax - orl $(1<<18),%eax # try setting AC - push %eax - popfl - pushfl - popl %eax - testl $(1<<18),%eax - jz bad -#endif -#if REQUIRED_MASK1 != 0 - pushfl # standard way to check for cpuid - popl %eax - movl %eax,%ebx - xorl $0x200000,%eax - pushl %eax - popfl - pushfl - popl %eax - cmpl %eax,%ebx - pushfl # standard way to check for cpuid - popl %eax - movl %eax,%ebx - xorl $0x200000,%eax - pushl %eax - popfl - pushfl - popl %eax - cmpl %eax,%ebx - jz bad # REQUIRED_MASK1 != 0 requires CPUID - - movl $0x0,%eax # See if cpuid 1 is implemented - cpuid - cmpl $0x1,%eax - jb bad # no cpuid 1 - -#if REQUIRED_MASK1 & NEED_CMPXCHG64 - /* Some VIA C3s need magic MSRs to enable CX64. Do this here */ - cmpl $0x746e6543,%ebx # Cent - jne 1f - cmpl $0x48727561,%edx # aurH - jne 1f - cmpl $0x736c7561,%ecx # auls - jne 1f - movl $1,%eax # check model - cpuid - movl %eax,%ebx - shr $8,%ebx - andl $0xf,%ebx - cmp $6,%ebx # check family == 6 - jne 1f - shr $4,%eax - andl $0xf,%eax - cmpl $6,%eax # check model >= 6 - jb 1f - # assume models >= 6 all support this MSR - movl $MSR_VIA_FCR,%ecx - rdmsr - orl $((1<<1)|(1<<7)),%eax # enable CMPXCHG64 and PGE - wrmsr -1: -#endif - movl $0x1,%eax # Does the cpu have what it takes - cpuid - -#if CONFIG_X86_MINIMUM_CPU_MODEL > 4 -#error add proper model checking here -#endif - - andl $REQUIRED_MASK1,%edx - xorl $REQUIRED_MASK1,%edx - jnz bad -#endif /* REQUIRED_MASK1 */ - - popfl - xor %eax,%eax - ret - -bad: - popfl - movl $1,%eax - ret diff --git a/arch/i386/kernel/vmi.c b/arch/i386/kernel/vmi.c index c12720d7cbc5..18673e0f193b 100644 --- a/arch/i386/kernel/vmi.c +++ b/arch/i386/kernel/vmi.c @@ -87,12 +87,14 @@ struct vmi_timer_ops vmi_timer_ops; #define IRQ_PATCH_INT_MASK 0 #define IRQ_PATCH_DISABLE 5 -static inline void patch_offset(unsigned char *eip, unsigned char *dest) +static inline void patch_offset(void *insnbuf, + unsigned long eip, unsigned long dest) { - *(unsigned long *)(eip+1) = dest-eip-5; + *(unsigned long *)(insnbuf+1) = dest-eip-5; } -static unsigned patch_internal(int call, unsigned len, void *insns) +static unsigned patch_internal(int call, unsigned len, void *insnbuf, + unsigned long eip) { u64 reloc; struct vmi_relocation_info *const rel = (struct vmi_relocation_info *)&reloc; @@ -100,14 +102,14 @@ static unsigned patch_internal(int call, unsigned len, void *insns) switch(rel->type) { case VMI_RELOCATION_CALL_REL: BUG_ON(len < 5); - *(char *)insns = MNEM_CALL; - patch_offset(insns, rel->eip); + *(char *)insnbuf = MNEM_CALL; + patch_offset(insnbuf, eip, (unsigned long)rel->eip); return 5; case VMI_RELOCATION_JUMP_REL: BUG_ON(len < 5); - *(char *)insns = MNEM_JMP; - patch_offset(insns, rel->eip); + *(char *)insnbuf = MNEM_JMP; + patch_offset(insnbuf, eip, (unsigned long)rel->eip); return 5; case VMI_RELOCATION_NOP: @@ -128,21 +130,26 @@ static unsigned patch_internal(int call, unsigned len, void *insns) * Apply patch if appropriate, return length of new instruction * sequence. The callee does nop padding for us. */ -static unsigned vmi_patch(u8 type, u16 clobbers, void *insns, unsigned len) +static unsigned vmi_patch(u8 type, u16 clobbers, void *insns, + unsigned long eip, unsigned len) { switch (type) { case PARAVIRT_PATCH(irq_disable): - return patch_internal(VMI_CALL_DisableInterrupts, len, insns); + return patch_internal(VMI_CALL_DisableInterrupts, len, + insns, eip); case PARAVIRT_PATCH(irq_enable): - return patch_internal(VMI_CALL_EnableInterrupts, len, insns); + return patch_internal(VMI_CALL_EnableInterrupts, len, + insns, eip); case PARAVIRT_PATCH(restore_fl): - return patch_internal(VMI_CALL_SetInterruptMask, len, insns); + return patch_internal(VMI_CALL_SetInterruptMask, len, + insns, eip); case PARAVIRT_PATCH(save_fl): - return patch_internal(VMI_CALL_GetInterruptMask, len, insns); + return patch_internal(VMI_CALL_GetInterruptMask, len, + insns, eip); case PARAVIRT_PATCH(iret): - return patch_internal(VMI_CALL_IRET, len, insns); + return patch_internal(VMI_CALL_IRET, len, insns, eip); case PARAVIRT_PATCH(irq_enable_sysexit): - return patch_internal(VMI_CALL_SYSEXIT, len, insns); + return patch_internal(VMI_CALL_SYSEXIT, len, insns, eip); default: break; } @@ -362,7 +369,7 @@ static void *vmi_kmap_atomic_pte(struct page *page, enum km_type type) } #endif -static void vmi_allocate_pt(u32 pfn) +static void vmi_allocate_pt(struct mm_struct *mm, u32 pfn) { vmi_set_page_type(pfn, VMI_PAGE_L1); vmi_ops.allocate_page(pfn, VMI_PAGE_L1, 0, 0, 0); @@ -891,7 +898,7 @@ static inline int __init activate_vmi(void) paravirt_ops.setup_boot_clock = vmi_time_bsp_init; paravirt_ops.setup_secondary_clock = vmi_time_ap_init; #endif - paravirt_ops.get_scheduled_cycles = vmi_get_sched_cycles; + paravirt_ops.sched_clock = vmi_sched_clock; paravirt_ops.get_cpu_khz = vmi_cpu_khz; /* We have true wallclock functions; disable CMOS clock sync */ diff --git a/arch/i386/kernel/vmiclock.c b/arch/i386/kernel/vmiclock.c index 26a37f8a8762..b1b5ab08b26e 100644 --- a/arch/i386/kernel/vmiclock.c +++ b/arch/i386/kernel/vmiclock.c @@ -32,6 +32,7 @@ #include <asm/apicdef.h> #include <asm/apic.h> #include <asm/timer.h> +#include <asm/i8253.h> #include <irq_vectors.h> #include "io_ports.h" @@ -64,10 +65,10 @@ int vmi_set_wallclock(unsigned long now) return 0; } -/* paravirt_ops.get_scheduled_cycles = vmi_get_sched_cycles */ -unsigned long long vmi_get_sched_cycles(void) +/* paravirt_ops.sched_clock = vmi_sched_clock */ +unsigned long long vmi_sched_clock(void) { - return vmi_timer_ops.get_cycle_counter(VMI_CYCLES_AVAILABLE); + return cycles_2_ns(vmi_timer_ops.get_cycle_counter(VMI_CYCLES_AVAILABLE)); } /* paravirt_ops.get_cpu_khz = vmi_cpu_khz */ @@ -142,6 +143,7 @@ static void vmi_timer_set_mode(enum clock_event_mode mode, switch (mode) { case CLOCK_EVT_MODE_ONESHOT: + case CLOCK_EVT_MODE_RESUME: break; case CLOCK_EVT_MODE_PERIODIC: cycles_per_hz = vmi_timer_ops.get_cycle_frequency(); diff --git a/arch/i386/kernel/vmlinux.lds.S b/arch/i386/kernel/vmlinux.lds.S index aa87b06c7c82..7d72cce00529 100644 --- a/arch/i386/kernel/vmlinux.lds.S +++ b/arch/i386/kernel/vmlinux.lds.S @@ -60,7 +60,9 @@ SECTIONS __stop___ex_table = .; } - BUG_TABLE + NOTES :text :note + + BUG_TABLE :text . = ALIGN(4); .tracedata : AT(ADDR(.tracedata) - LOAD_OFFSET) { @@ -88,6 +90,7 @@ SECTIONS . = ALIGN(4096); .data.page_aligned : AT(ADDR(.data.page_aligned) - LOAD_OFFSET) { + *(.data.page_aligned) *(.data.idt) } @@ -180,6 +183,7 @@ SECTIONS .data.percpu : AT(ADDR(.data.percpu) - LOAD_OFFSET) { __per_cpu_start = .; *(.data.percpu) + *(.data.percpu.shared_aligned) __per_cpu_end = .; } . = ALIGN(4096); @@ -206,6 +210,4 @@ SECTIONS STABS_DEBUG DWARF_DEBUG - - NOTES } diff --git a/arch/i386/kernel/vsyscall-note.S b/arch/i386/kernel/vsyscall-note.S index d4b5be4f3d5f..07c0daf78237 100644 --- a/arch/i386/kernel/vsyscall-note.S +++ b/arch/i386/kernel/vsyscall-note.S @@ -3,23 +3,43 @@ * Here we can supply some information useful to userland. */ -#include <linux/uts.h> #include <linux/version.h> +#include <linux/elfnote.h> -#define ASM_ELF_NOTE_BEGIN(name, flags, vendor, type) \ - .section name, flags; \ - .balign 4; \ - .long 1f - 0f; /* name length */ \ - .long 3f - 2f; /* data length */ \ - .long type; /* note type */ \ -0: .asciz vendor; /* vendor name */ \ -1: .balign 4; \ -2: +/* Ideally this would use UTS_NAME, but using a quoted string here + doesn't work. Remember to change this when changing the + kernel's name. */ +ELFNOTE_START(Linux, 0, "a") + .long LINUX_VERSION_CODE +ELFNOTE_END -#define ASM_ELF_NOTE_END \ -3: .balign 4; /* pad out section */ \ - .previous +#ifdef CONFIG_XEN +/* + * Add a special note telling glibc's dynamic linker a fake hardware + * flavor that it will use to choose the search path for libraries in the + * same way it uses real hardware capabilities like "mmx". + * We supply "nosegneg" as the fake capability, to indicate that we + * do not like negative offsets in instructions using segment overrides, + * since we implement those inefficiently. This makes it possible to + * install libraries optimized to avoid those access patterns in someplace + * like /lib/i686/tls/nosegneg. Note that an /etc/ld.so.conf.d/file + * corresponding to the bits here is needed to make ldconfig work right. + * It should contain: + * hwcap 1 nosegneg + * to match the mapping of bit to name that we give here. + * + * At runtime, the fake hardware feature will be considered to be present + * if its bit is set in the mask word. So, we start with the mask 0, and + * at boot time we set VDSO_NOTE_NONEGSEG_BIT if running under Xen. + */ - ASM_ELF_NOTE_BEGIN(".note.kernel-version", "a", UTS_SYSNAME, 0) - .long LINUX_VERSION_CODE - ASM_ELF_NOTE_END +#include "../xen/vdso.h" /* Defines VDSO_NOTE_NONEGSEG_BIT. */ + + .globl VDSO_NOTE_MASK +ELFNOTE_START(GNU, 2, "a") + .long 1 /* ncaps */ +VDSO_NOTE_MASK: + .long 0 /* mask */ + .byte VDSO_NOTE_NONEGSEG_BIT; .asciz "nosegneg" /* bit, name */ +ELFNOTE_END +#endif diff --git a/arch/i386/lib/Makefile b/arch/i386/lib/Makefile index 22d8ac5815f0..4d105fdfe817 100644 --- a/arch/i386/lib/Makefile +++ b/arch/i386/lib/Makefile @@ -4,7 +4,7 @@ lib-y = checksum.o delay.o usercopy.o getuser.o putuser.o memcpy.o strstr.o \ - bitops.o semaphore.o + bitops.o semaphore.o string.o lib-$(CONFIG_X86_USE_3DNOW) += mmx.o diff --git a/arch/i386/mach-generic/Makefile b/arch/i386/mach-generic/Makefile index 77fbc9f64fbc..6914485c0d85 100644 --- a/arch/i386/mach-generic/Makefile +++ b/arch/i386/mach-generic/Makefile @@ -2,6 +2,6 @@ # Makefile for the generic architecture # -EXTRA_CFLAGS += -I../kernel +EXTRA_CFLAGS := -Iarch/i386/kernel obj-y := probe.o summit.o bigsmp.o es7000.o default.o ../mach-es7000/ diff --git a/arch/i386/mach-generic/es7000.c b/arch/i386/mach-generic/es7000.c index b47f951c0ec2..4742626f08c4 100644 --- a/arch/i386/mach-generic/es7000.c +++ b/arch/i386/mach-generic/es7000.c @@ -66,4 +66,4 @@ static int __init acpi_madt_oem_check(char *oem_id, char *oem_table_id) } #endif -struct genapic apic_es7000 = APIC_INIT("es7000", probe_es7000); +struct genapic __initdata_refok apic_es7000 = APIC_INIT("es7000", probe_es7000); diff --git a/arch/i386/mach-visws/traps.c b/arch/i386/mach-visws/traps.c index 5199bd03254a..843b67acf43b 100644 --- a/arch/i386/mach-visws/traps.c +++ b/arch/i386/mach-visws/traps.c @@ -23,13 +23,13 @@ static __init void lithium_init(void) set_fixmap(FIX_LI_PCIB, LI_PCI_B_PHYS); if ((li_pcia_read16(PCI_VENDOR_ID) != PCI_VENDOR_ID_SGI) || - (li_pcia_read16(PCI_DEVICE_ID) != PCI_VENDOR_ID_SGI_LITHIUM)) { + (li_pcia_read16(PCI_DEVICE_ID) != PCI_DEVICE_ID_SGI_LITHIUM)) { printk(KERN_EMERG "Lithium hostbridge %c not found\n", 'A'); panic("This machine is not SGI Visual Workstation 320/540"); } if ((li_pcib_read16(PCI_VENDOR_ID) != PCI_VENDOR_ID_SGI) || - (li_pcib_read16(PCI_DEVICE_ID) != PCI_VENDOR_ID_SGI_LITHIUM)) { + (li_pcib_read16(PCI_DEVICE_ID) != PCI_DEVICE_ID_SGI_LITHIUM)) { printk(KERN_EMERG "Lithium hostbridge %c not found\n", 'B'); panic("This machine is not SGI Visual Workstation 320/540"); } diff --git a/arch/i386/mach-voyager/Makefile b/arch/i386/mach-voyager/Makefile index f24d29651318..33b74cf0dd22 100644 --- a/arch/i386/mach-voyager/Makefile +++ b/arch/i386/mach-voyager/Makefile @@ -2,7 +2,7 @@ # Makefile for the linux kernel. # -EXTRA_CFLAGS += -I../kernel +EXTRA_CFLAGS := -Iarch/i386/kernel obj-y := setup.o voyager_basic.o voyager_thread.o obj-$(CONFIG_SMP) += voyager_smp.o voyager_cat.o diff --git a/arch/i386/mach-voyager/voyager_thread.c b/arch/i386/mach-voyager/voyager_thread.c index b4b24e0e45e1..f9d595338159 100644 --- a/arch/i386/mach-voyager/voyager_thread.c +++ b/arch/i386/mach-voyager/voyager_thread.c @@ -52,7 +52,7 @@ execute(const char *string) NULL, }; - if ((ret = call_usermodehelper(argv[0], argv, envp, 1)) != 0) { + if ((ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC)) != 0) { printk(KERN_ERR "Voyager failed to run \"%s\": %i\n", string, ret); } diff --git a/arch/i386/mm/fault.c b/arch/i386/mm/fault.c index 27ba2fd11483..fcb38e7f3543 100644 --- a/arch/i386/mm/fault.c +++ b/arch/i386/mm/fault.c @@ -284,6 +284,8 @@ static inline int vmalloc_fault(unsigned long address) return 0; } +int show_unhandled_signals = 1; + /* * This routine handles page faults. It determines the address, * and the problem, and then passes it off to one of the appropriate @@ -304,6 +306,7 @@ fastcall void __kprobes do_page_fault(struct pt_regs *regs, struct vm_area_struct * vma; unsigned long address; int write, si_code; + int fault; /* get the address */ address = read_cr2(); @@ -423,20 +426,18 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - switch (handle_mm_fault(mm, vma, address, write)) { - case VM_FAULT_MINOR: - tsk->min_flt++; - break; - case VM_FAULT_MAJOR: - tsk->maj_flt++; - break; - case VM_FAULT_SIGBUS: - goto do_sigbus; - case VM_FAULT_OOM: + fault = handle_mm_fault(mm, vma, address, write); + if (unlikely(fault & VM_FAULT_ERROR)) { + if (fault & VM_FAULT_OOM) goto out_of_memory; - default: - BUG(); + else if (fault & VM_FAULT_SIGBUS) + goto do_sigbus; + BUG(); } + if (fault & VM_FAULT_MAJOR) + tsk->maj_flt++; + else + tsk->min_flt++; /* * Did it hit the DOS screen memory VA from vm86 mode? @@ -471,6 +472,14 @@ bad_area_nosemaphore: if (is_prefetch(regs, address, error_code)) return; + if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) && + printk_ratelimit()) { + printk("%s%s[%d]: segfault at %08lx eip %08lx " + "esp %08lx error %lx\n", + tsk->pid > 1 ? KERN_INFO : KERN_EMERG, + tsk->comm, tsk->pid, address, regs->eip, + regs->esp, error_code); + } tsk->thread.cr2 = address; /* Kernel addresses are always protection faults */ tsk->thread.error_code = error_code | (address >= TASK_SIZE); diff --git a/arch/i386/mm/highmem.c b/arch/i386/mm/highmem.c index ad8d86cc683e..1c3bf95f7356 100644 --- a/arch/i386/mm/highmem.c +++ b/arch/i386/mm/highmem.c @@ -34,17 +34,16 @@ void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot) /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ pagefault_disable(); - idx = type + KM_TYPE_NR*smp_processor_id(); - BUG_ON(!pte_none(*(kmap_pte-idx))); - if (!PageHighMem(page)) return page_address(page); + idx = type + KM_TYPE_NR*smp_processor_id(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); + BUG_ON(!pte_none(*(kmap_pte-idx))); set_pte(kmap_pte-idx, mk_pte(page, prot)); arch_flush_lazy_mmu_mode(); - return (void*) vaddr; + return (void *)vaddr; } void *kmap_atomic(struct page *page, enum km_type type) diff --git a/arch/i386/mm/hugetlbpage.c b/arch/i386/mm/hugetlbpage.c index efdf95ac8031..6c06d9c0488e 100644 --- a/arch/i386/mm/hugetlbpage.c +++ b/arch/i386/mm/hugetlbpage.c @@ -367,7 +367,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, return -ENOMEM; if (flags & MAP_FIXED) { - if (prepare_hugepage_range(addr, len, pgoff)) + if (prepare_hugepage_range(addr, len)) return -EINVAL; return addr; } diff --git a/arch/i386/mm/init.c b/arch/i386/mm/init.c index 7135946d3663..730a5b177b1f 100644 --- a/arch/i386/mm/init.c +++ b/arch/i386/mm/init.c @@ -87,7 +87,7 @@ static pte_t * __init one_page_table_init(pmd_t *pmd) if (!(pmd_val(*pmd) & _PAGE_PRESENT)) { pte_t *page_table = (pte_t *) alloc_bootmem_low_pages(PAGE_SIZE); - paravirt_alloc_pt(__pa(page_table) >> PAGE_SHIFT); + paravirt_alloc_pt(&init_mm, __pa(page_table) >> PAGE_SHIFT); set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE)); BUG_ON(page_table != pte_offset_kernel(pmd, 0)); } @@ -432,7 +432,7 @@ static void __init pagetable_init (void) paravirt_pagetable_setup_done(pgd_base); } -#if defined(CONFIG_SOFTWARE_SUSPEND) || defined(CONFIG_ACPI_SLEEP) +#if defined(CONFIG_HIBERNATION) || defined(CONFIG_ACPI) /* * Swap suspend & friends need this for resume because things like the intel-agp * driver might have split up a kernel 4MB mapping. @@ -471,8 +471,13 @@ void zap_low_mappings (void) flush_tlb_all(); } +int nx_enabled = 0; + +#ifdef CONFIG_X86_PAE + static int disable_nx __initdata = 0; u64 __supported_pte_mask __read_mostly = ~_PAGE_NX; +EXPORT_SYMBOL_GPL(__supported_pte_mask); /* * noexec = on|off @@ -499,9 +504,6 @@ static int __init noexec_setup(char *str) } early_param("noexec", noexec_setup); -int nx_enabled = 0; -#ifdef CONFIG_X86_PAE - static void __init set_nx(void) { unsigned int v[4], l, h; @@ -751,8 +753,7 @@ void __init pgtable_cache_init(void) PTRS_PER_PMD*sizeof(pmd_t), PTRS_PER_PMD*sizeof(pmd_t), SLAB_PANIC, - pmd_ctor, - NULL); + pmd_ctor); if (!SHARED_KERNEL_PMD) { /* If we're in PAE mode and have a non-shared kernel pmd, then the pgd size must be a diff --git a/arch/i386/mm/ioremap.c b/arch/i386/mm/ioremap.c index fff08ae7b5ed..0b278315d737 100644 --- a/arch/i386/mm/ioremap.c +++ b/arch/i386/mm/ioremap.c @@ -196,7 +196,7 @@ void iounmap(volatile void __iomem *addr) /* Reset the direct mapping. Can block */ if ((p->flags >> 20) && p->phys_addr < virt_to_phys(high_memory) - 1) { change_page_attr(virt_to_page(__va(p->phys_addr)), - p->size >> PAGE_SHIFT, + get_vm_area_size(p) >> PAGE_SHIFT, PAGE_KERNEL); global_flush_tlb(); } diff --git a/arch/i386/mm/pageattr.c b/arch/i386/mm/pageattr.c index 2eb14a73be9c..4241a74d16c8 100644 --- a/arch/i386/mm/pageattr.c +++ b/arch/i386/mm/pageattr.c @@ -60,7 +60,7 @@ static struct page *split_large_page(unsigned long address, pgprot_t prot, address = __pa(address); addr = address & LARGE_PAGE_MASK; pbase = (pte_t *)page_address(base); - paravirt_alloc_pt(page_to_pfn(base)); + paravirt_alloc_pt(&init_mm, page_to_pfn(base)); for (i = 0; i < PTRS_PER_PTE; i++, addr += PAGE_SIZE) { set_pte(&pbase[i], pfn_pte(addr >> PAGE_SHIFT, addr == address ? prot : ref_prot)); @@ -136,6 +136,12 @@ static inline void revert_page(struct page *kpte_page, unsigned long address) ref_prot)); } +static inline void save_page(struct page *kpte_page) +{ + if (!test_and_set_bit(PG_arch_1, &kpte_page->flags)) + list_add(&kpte_page->lru, &df_list); +} + static int __change_page_attr(struct page *page, pgprot_t prot) { @@ -150,6 +156,9 @@ __change_page_attr(struct page *page, pgprot_t prot) if (!kpte) return -EINVAL; kpte_page = virt_to_page(kpte); + BUG_ON(PageLRU(kpte_page)); + BUG_ON(PageCompound(kpte_page)); + if (pgprot_val(prot) != pgprot_val(PAGE_KERNEL)) { if (!pte_huge(*kpte)) { set_pte_atomic(kpte, mk_pte(page, prot)); @@ -179,11 +188,11 @@ __change_page_attr(struct page *page, pgprot_t prot) * time (not via split_large_page) and in turn we must not * replace it with a largepage. */ + + save_page(kpte_page); if (!PageReserved(kpte_page)) { if (cpu_has_pse && (page_private(kpte_page) == 0)) { - ClearPagePrivate(kpte_page); paravirt_release_pt(page_to_pfn(kpte_page)); - list_add(&kpte_page->lru, &df_list); revert_page(kpte_page, address); } } @@ -236,6 +245,11 @@ void global_flush_tlb(void) spin_unlock_irq(&cpa_lock); flush_map(&l); list_for_each_entry_safe(pg, next, &l, lru) { + list_del(&pg->lru); + clear_bit(PG_arch_1, &pg->flags); + if (PageReserved(pg) || !cpu_has_pse || page_private(pg) != 0) + continue; + ClearPagePrivate(pg); __free_page(pg); } } diff --git a/arch/i386/mm/pgtable.c b/arch/i386/mm/pgtable.c index 8d7c0864cc04..01437c46baae 100644 --- a/arch/i386/mm/pgtable.c +++ b/arch/i386/mm/pgtable.c @@ -235,7 +235,7 @@ static inline void pgd_list_del(pgd_t *pgd) #if (PTRS_PER_PMD == 1) /* Non-PAE pgd constructor */ -void pgd_ctor(void *pgd) +static void pgd_ctor(void *pgd) { unsigned long flags; @@ -257,7 +257,7 @@ void pgd_ctor(void *pgd) } #else /* PTRS_PER_PMD > 1 */ /* PAE pgd constructor */ -void pgd_ctor(void *pgd) +static void pgd_ctor(void *pgd) { /* PAE, kernel PMD may be shared */ @@ -276,7 +276,7 @@ void pgd_ctor(void *pgd) } #endif /* PTRS_PER_PMD */ -void pgd_dtor(void *pgd) +static void pgd_dtor(void *pgd) { unsigned long flags; /* can be called from interrupt context */ diff --git a/arch/i386/pci/acpi.c b/arch/i386/pci/acpi.c index b33aea845f58..bc8a44bddaa7 100644 --- a/arch/i386/pci/acpi.c +++ b/arch/i386/pci/acpi.c @@ -8,20 +8,42 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_device *device, int domain, int busnum) { struct pci_bus *bus; + struct pci_sysdata *sd; + int pxm; + + /* Allocate per-root-bus (not per bus) arch-specific data. + * TODO: leak; this memory is never freed. + * It's arguable whether it's worth the trouble to care. + */ + sd = kzalloc(sizeof(*sd), GFP_KERNEL); + if (!sd) { + printk(KERN_ERR "PCI: OOM, not probing PCI bus %02x\n", busnum); + return NULL; + } if (domain != 0) { printk(KERN_WARNING "PCI: Multiple domains not supported\n"); + kfree(sd); return NULL; } - bus = pcibios_scan_root(busnum); + sd->node = -1; + + pxm = acpi_get_pxm(device->handle); +#ifdef CONFIG_ACPI_NUMA + if (pxm >= 0) + sd->node = pxm_to_node(pxm); +#endif + + bus = pci_scan_bus_parented(NULL, busnum, &pci_root_ops, sd); + if (!bus) + kfree(sd); + #ifdef CONFIG_ACPI_NUMA if (bus != NULL) { - int pxm = acpi_get_pxm(device->handle); if (pxm >= 0) { - bus->sysdata = (void *)(unsigned long)pxm_to_node(pxm); - printk("bus %d -> pxm %d -> node %ld\n", - busnum, pxm, (long)(bus->sysdata)); + printk("bus %d -> pxm %d -> node %d\n", + busnum, pxm, sd->node); } } #endif diff --git a/arch/i386/pci/common.c b/arch/i386/pci/common.c index 3f78d4d8ecf3..ebc6f3c66340 100644 --- a/arch/i386/pci/common.c +++ b/arch/i386/pci/common.c @@ -293,6 +293,7 @@ static struct dmi_system_id __devinitdata pciprobe_dmi_table[] = { struct pci_bus * __devinit pcibios_scan_root(int busnum) { struct pci_bus *bus = NULL; + struct pci_sysdata *sd; dmi_check_system(pciprobe_dmi_table); @@ -303,9 +304,19 @@ struct pci_bus * __devinit pcibios_scan_root(int busnum) } } + /* Allocate per-root-bus (not per bus) arch-specific data. + * TODO: leak; this memory is never freed. + * It's arguable whether it's worth the trouble to care. + */ + sd = kzalloc(sizeof(*sd), GFP_KERNEL); + if (!sd) { + printk(KERN_ERR "PCI: OOM, not probing PCI bus %02x\n", busnum); + return NULL; + } + printk(KERN_DEBUG "PCI: Probing PCI hardware (bus %02x)\n", busnum); - return pci_scan_bus_parented(NULL, busnum, &pci_root_ops, NULL); + return pci_scan_bus_parented(NULL, busnum, &pci_root_ops, sd); } extern u8 pci_cache_line_size; @@ -444,3 +455,26 @@ void pcibios_disable_device (struct pci_dev *dev) if (!dev->msi_enabled && pcibios_disable_irq) pcibios_disable_irq(dev); } + +struct pci_bus *pci_scan_bus_with_sysdata(int busno) +{ + struct pci_bus *bus = NULL; + struct pci_sysdata *sd; + + /* + * Allocate per-root-bus (not per bus) arch-specific data. + * TODO: leak; this memory is never freed. + * It's arguable whether it's worth the trouble to care. + */ + sd = kzalloc(sizeof(*sd), GFP_KERNEL); + if (!sd) { + printk(KERN_ERR "PCI: OOM, skipping PCI bus %02x\n", busno); + return NULL; + } + sd->node = -1; + bus = pci_scan_bus(busno, &pci_root_ops, sd); + if (!bus) + kfree(sd); + + return bus; +} diff --git a/arch/i386/pci/fixup.c b/arch/i386/pci/fixup.c index b95b42950ed4..c82cbf4c7226 100644 --- a/arch/i386/pci/fixup.c +++ b/arch/i386/pci/fixup.c @@ -25,9 +25,9 @@ static void __devinit pci_fixup_i450nx(struct pci_dev *d) pci_read_config_byte(d, reg++, &subb); DBG("i450NX PXB %d: %02x/%02x/%02x\n", pxb, busno, suba, subb); if (busno) - pci_scan_bus(busno, &pci_root_ops, NULL); /* Bus A */ + pci_scan_bus_with_sysdata(busno); /* Bus A */ if (suba < subb) - pci_scan_bus(suba+1, &pci_root_ops, NULL); /* Bus B */ + pci_scan_bus_with_sysdata(suba+1); /* Bus B */ } pcibios_last_bus = -1; } @@ -42,7 +42,7 @@ static void __devinit pci_fixup_i450gx(struct pci_dev *d) u8 busno; pci_read_config_byte(d, 0x4a, &busno); printk(KERN_INFO "PCI: i440KX/GX host bridge %s: secondary bus %02x\n", pci_name(d), busno); - pci_scan_bus(busno, &pci_root_ops, NULL); + pci_scan_bus_with_sysdata(busno); pcibios_last_bus = -1; } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82454GX, pci_fixup_i450gx); @@ -118,12 +118,9 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82371AB_3, pci static void pci_fixup_via_northbridge_bug(struct pci_dev *d) { u8 v; - u8 revision; int where = 0x55; int mask = 0x1f; /* clear bits 5, 6, 7 by default */ - pci_read_config_byte(d, PCI_REVISION_ID, &revision); - if (d->device == PCI_DEVICE_ID_VIA_8367_0) { /* fix pci bus latency issues resulted by NB bios error it appears on bug free^Wreduced kt266x's bios forces @@ -133,8 +130,8 @@ static void pci_fixup_via_northbridge_bug(struct pci_dev *d) where = 0x95; /* the memory write queue timer register is different for the KT266x's: 0x95 not 0x55 */ } else if (d->device == PCI_DEVICE_ID_VIA_8363_0 && - (revision == VIA_8363_KL133_REVISION_ID || - revision == VIA_8363_KM133_REVISION_ID)) { + (d->revision == VIA_8363_KL133_REVISION_ID || + d->revision == VIA_8363_KM133_REVISION_ID)) { mask = 0x3f; /* clear only bits 6 and 7; clearing bit 5 causes screen corruption on the KL133/KM133 */ } @@ -142,7 +139,7 @@ static void pci_fixup_via_northbridge_bug(struct pci_dev *d) pci_read_config_byte(d, where, &v); if (v & ~mask) { printk(KERN_WARNING "Disabling VIA memory write queue (PCI ID %04x, rev %02x): [%02x] %02x & %02x -> %02x\n", \ - d->device, revision, where, v, mask, v & mask); + d->device, d->revision, where, v, mask, v & mask); v &= mask; pci_write_config_byte(d, where, v); } diff --git a/arch/i386/pci/irq.c b/arch/i386/pci/irq.c index f2cb942f8281..8434f2323b87 100644 --- a/arch/i386/pci/irq.c +++ b/arch/i386/pci/irq.c @@ -138,8 +138,9 @@ static void __init pirq_peer_trick(void) for(i = 1; i < 256; i++) { if (!busmap[i] || pci_find_bus(0, i)) continue; - if (pci_scan_bus(i, &pci_root_ops, NULL)) - printk(KERN_INFO "PCI: Discovered primary peer bus %02x [IRQ]\n", i); + if (pci_scan_bus_with_sysdata(i)) + printk(KERN_INFO "PCI: Discovered primary peer " + "bus %02x [IRQ]\n", i); } pcibios_last_bus = -1; } @@ -549,6 +550,7 @@ static __init int intel_router_probe(struct irq_router *r, struct pci_dev *route case PCI_DEVICE_ID_INTEL_ICH9_3: case PCI_DEVICE_ID_INTEL_ICH9_4: case PCI_DEVICE_ID_INTEL_ICH9_5: + case PCI_DEVICE_ID_INTEL_TOLAPAI_0: r->name = "PIIX/ICH"; r->get = pirq_piix_get; r->set = pirq_piix_set; diff --git a/arch/i386/pci/legacy.c b/arch/i386/pci/legacy.c index 149a9588c256..5565d7016b75 100644 --- a/arch/i386/pci/legacy.c +++ b/arch/i386/pci/legacy.c @@ -26,7 +26,7 @@ static void __devinit pcibios_fixup_peer_bridges(void) l != 0x0000 && l != 0xffff) { DBG("Found device at %02x:%02x [%04x]\n", n, devfn, l); printk(KERN_INFO "PCI: Discovered peer bus %02x\n", n); - pci_scan_bus(n, &pci_root_ops, NULL); + pci_scan_bus_with_sysdata(n); break; } } diff --git a/arch/i386/pci/mmconfig-shared.c b/arch/i386/pci/mmconfig-shared.c index c7cabeed4d7b..4df637e34f81 100644 --- a/arch/i386/pci/mmconfig-shared.c +++ b/arch/i386/pci/mmconfig-shared.c @@ -24,6 +24,9 @@ DECLARE_BITMAP(pci_mmcfg_fallback_slots, 32*PCI_MMCFG_MAX_CHECK_BUS); +/* Indicate if the mmcfg resources have been placed into the resource table. */ +static int __initdata pci_mmcfg_resources_inserted; + /* K8 systems have some devices (typically in the builtin northbridge) that are only accessible using type1 Normally this can be expressed in the MCFG by not listing them @@ -170,7 +173,7 @@ static int __init pci_mmcfg_check_hostbridge(void) return name != NULL; } -static void __init pci_mmcfg_insert_resources(void) +static void __init pci_mmcfg_insert_resources(unsigned long resource_flags) { #define PCI_MMCFG_RESOURCE_NAME_LEN 19 int i; @@ -194,10 +197,13 @@ static void __init pci_mmcfg_insert_resources(void) cfg->pci_segment); res->start = cfg->address; res->end = res->start + (num_buses << 20) - 1; - res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + res->flags = IORESOURCE_MEM | resource_flags; insert_resource(&iomem_resource, res); names += PCI_MMCFG_RESOURCE_NAME_LEN; } + + /* Mark that the resources have been inserted. */ + pci_mmcfg_resources_inserted = 1; } static void __init pci_mmcfg_reject_broken(int type) @@ -267,7 +273,43 @@ void __init pci_mmcfg_init(int type) if (type == 1) unreachable_devices(); if (known_bridge) - pci_mmcfg_insert_resources(); + pci_mmcfg_insert_resources(IORESOURCE_BUSY); pci_probe = (pci_probe & ~PCI_PROBE_MASK) | PCI_PROBE_MMCONF; + } else { + /* + * Signal not to attempt to insert mmcfg resources because + * the architecture mmcfg setup could not initialize. + */ + pci_mmcfg_resources_inserted = 1; } } + +static int __init pci_mmcfg_late_insert_resources(void) +{ + /* + * If resources are already inserted or we are not using MMCONFIG, + * don't insert the resources. + */ + if ((pci_mmcfg_resources_inserted == 1) || + (pci_probe & PCI_PROBE_MMCONF) == 0 || + (pci_mmcfg_config_num == 0) || + (pci_mmcfg_config == NULL) || + (pci_mmcfg_config[0].address == 0)) + return 1; + + /* + * Attempt to insert the mmcfg resources but not with the busy flag + * marked so it won't cause request errors when __request_region is + * called. + */ + pci_mmcfg_insert_resources(0); + + return 0; +} + +/* + * Perform MMCONFIG resource insertion after PCI initialization to allow for + * misprogrammed MCFG tables that state larger sizes but actually conflict + * with other system resources. + */ +late_initcall(pci_mmcfg_late_insert_resources); diff --git a/arch/i386/pci/mmconfig.c b/arch/i386/pci/mmconfig.c index bb1afd9e589d..1bf5816d34c8 100644 --- a/arch/i386/pci/mmconfig.c +++ b/arch/i386/pci/mmconfig.c @@ -82,16 +82,15 @@ static int pci_mmcfg_read(unsigned int seg, unsigned int bus, switch (len) { case 1: - *value = readb(mmcfg_virt_addr + reg); + *value = mmio_config_readb(mmcfg_virt_addr + reg); break; case 2: - *value = readw(mmcfg_virt_addr + reg); + *value = mmio_config_readw(mmcfg_virt_addr + reg); break; case 4: - *value = readl(mmcfg_virt_addr + reg); + *value = mmio_config_readl(mmcfg_virt_addr + reg); break; } - spin_unlock_irqrestore(&pci_config_lock, flags); return 0; @@ -116,16 +115,15 @@ static int pci_mmcfg_write(unsigned int seg, unsigned int bus, switch (len) { case 1: - writeb(value, mmcfg_virt_addr + reg); + mmio_config_writeb(mmcfg_virt_addr + reg, value); break; case 2: - writew(value, mmcfg_virt_addr + reg); + mmio_config_writew(mmcfg_virt_addr + reg, value); break; case 4: - writel(value, mmcfg_virt_addr + reg); + mmio_config_writel(mmcfg_virt_addr + reg, value); break; } - spin_unlock_irqrestore(&pci_config_lock, flags); return 0; diff --git a/arch/i386/pci/numa.c b/arch/i386/pci/numa.c index adbe17a38f6f..f5f165f69e0c 100644 --- a/arch/i386/pci/numa.c +++ b/arch/i386/pci/numa.c @@ -96,10 +96,14 @@ static void __devinit pci_fixup_i450nx(struct pci_dev *d) pci_read_config_byte(d, reg++, &suba); pci_read_config_byte(d, reg++, &subb); DBG("i450NX PXB %d: %02x/%02x/%02x\n", pxb, busno, suba, subb); - if (busno) - pci_scan_bus(QUADLOCAL2BUS(quad,busno), &pci_root_ops, NULL); /* Bus A */ - if (suba < subb) - pci_scan_bus(QUADLOCAL2BUS(quad,suba+1), &pci_root_ops, NULL); /* Bus B */ + if (busno) { + /* Bus A */ + pci_scan_bus_with_sysdata(QUADLOCAL2BUS(quad, busno)); + } + if (suba < subb) { + /* Bus B */ + pci_scan_bus_with_sysdata(QUADLOCAL2BUS(quad, suba+1)); + } } pcibios_last_bus = -1; } @@ -123,8 +127,7 @@ static int __init pci_numa_init(void) continue; printk("Scanning PCI bus %d for quad %d\n", QUADLOCAL2BUS(quad,0), quad); - pci_scan_bus(QUADLOCAL2BUS(quad,0), - &pci_root_ops, NULL); + pci_scan_bus_with_sysdata(QUADLOCAL2BUS(quad, 0)); } return 0; } diff --git a/arch/i386/pci/pcbios.c b/arch/i386/pci/pcbios.c index 5f5193401bea..10ac8c316c46 100644 --- a/arch/i386/pci/pcbios.c +++ b/arch/i386/pci/pcbios.c @@ -412,7 +412,7 @@ struct irq_routing_options { u16 segment; } __attribute__((packed)); -struct irq_routing_table * __devinit pcibios_get_irq_routing_table(void) +struct irq_routing_table * pcibios_get_irq_routing_table(void) { struct irq_routing_options opt; struct irq_routing_table *rt = NULL; diff --git a/arch/i386/pci/pci.h b/arch/i386/pci/pci.h index e58bae2076ad..8c66f275756f 100644 --- a/arch/i386/pci/pci.h +++ b/arch/i386/pci/pci.h @@ -104,3 +104,46 @@ extern DECLARE_BITMAP(pci_mmcfg_fallback_slots, 32*PCI_MMCFG_MAX_CHECK_BUS); extern int __init pci_mmcfg_arch_reachable(unsigned int seg, unsigned int bus, unsigned int devfn); extern int __init pci_mmcfg_arch_init(void); + +/* + * AMD Fam10h CPUs are buggy, and cannot access MMIO config space + * on their northbrige except through the * %eax register. As such, you MUST + * NOT use normal IOMEM accesses, you need to only use the magic mmio-config + * accessor functions. + * In fact just use pci_config_*, nothing else please. + */ +static inline unsigned char mmio_config_readb(void __iomem *pos) +{ + u8 val; + asm volatile("movb (%1),%%al" : "=a" (val) : "r" (pos)); + return val; +} + +static inline unsigned short mmio_config_readw(void __iomem *pos) +{ + u16 val; + asm volatile("movw (%1),%%ax" : "=a" (val) : "r" (pos)); + return val; +} + +static inline unsigned int mmio_config_readl(void __iomem *pos) +{ + u32 val; + asm volatile("movl (%1),%%eax" : "=a" (val) : "r" (pos)); + return val; +} + +static inline void mmio_config_writeb(void __iomem *pos, u8 val) +{ + asm volatile("movb %%al,(%1)" :: "a" (val), "r" (pos) : "memory"); +} + +static inline void mmio_config_writew(void __iomem *pos, u16 val) +{ + asm volatile("movw %%ax,(%1)" :: "a" (val), "r" (pos) : "memory"); +} + +static inline void mmio_config_writel(void __iomem *pos, u32 val) +{ + asm volatile("movl %%eax,(%1)" :: "a" (val), "r" (pos) : "memory"); +} diff --git a/arch/i386/pci/visws.c b/arch/i386/pci/visws.c index f1b486d4190b..8ecb1c722594 100644 --- a/arch/i386/pci/visws.c +++ b/arch/i386/pci/visws.c @@ -101,8 +101,8 @@ static int __init pcibios_init(void) "bridge B (PIIX4) bus: %u\n", pci_bus1, pci_bus0); raw_pci_ops = &pci_direct_conf1; - pci_scan_bus(pci_bus0, &pci_root_ops, NULL); - pci_scan_bus(pci_bus1, &pci_root_ops, NULL); + pci_scan_bus_with_sysdata(pci_bus0); + pci_scan_bus_with_sysdata(pci_bus1); pci_fixup_irqs(visws_swizzle, visws_map_irq); pcibios_resource_survey(); return 0; diff --git a/arch/i386/power/Makefile b/arch/i386/power/Makefile index 2de7bbf03cd7..d764ec950065 100644 --- a/arch/i386/power/Makefile +++ b/arch/i386/power/Makefile @@ -1,2 +1,2 @@ obj-$(CONFIG_PM) += cpu.o -obj-$(CONFIG_SOFTWARE_SUSPEND) += swsusp.o suspend.o +obj-$(CONFIG_HIBERNATION) += swsusp.o suspend.o |