aboutsummaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig13
-rw-r--r--arch/x86/Makefile29
-rw-r--r--arch/x86/boot/Makefile53
-rw-r--r--arch/x86/boot/header.S29
-rw-r--r--arch/x86/boot/pm.c44
-rw-r--r--arch/x86/boot/tools/build.c9
-rw-r--r--arch/x86/include/asm/boot.h4
-rwxr-xr-xarch/x86/include/asm/cpu_debug.h199
-rw-r--r--arch/x86/include/asm/desc.h3
-rw-r--r--arch/x86/include/asm/highmem.h1
-rw-r--r--arch/x86/include/asm/kexec.h13
-rw-r--r--arch/x86/include/asm/linkage.h19
-rw-r--r--arch/x86/include/asm/percpu.h8
-rw-r--r--arch/x86/include/asm/processor.h5
-rw-r--r--arch/x86/include/asm/xen/hypercall.h2
-rw-r--r--arch/x86/kernel/check.c2
-rw-r--r--arch/x86/kernel/cpu/Makefile2
-rw-r--r--arch/x86/kernel/cpu/addon_cpuid_features.c2
-rw-r--r--arch/x86/kernel/cpu/amd.c2
-rw-r--r--arch/x86/kernel/cpu/centaur.c2
-rw-r--r--arch/x86/kernel/cpu/centaur_64.c2
-rw-r--r--arch/x86/kernel/cpu/common.c396
-rw-r--r--arch/x86/kernel/cpu/cpu.h11
-rwxr-xr-xarch/x86/kernel/cpu/cpu_debug.c839
-rw-r--r--arch/x86/kernel/cpu/cpufreq/p4-clockmod.c1
-rw-r--r--arch/x86/kernel/cpu/cyrix.c16
-rw-r--r--arch/x86/kernel/cpu/intel.c7
-rw-r--r--arch/x86/kernel/cpu/intel_cacheinfo.c8
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_64.c4
-rw-r--r--arch/x86/kernel/cpu/transmeta.c2
-rw-r--r--arch/x86/kernel/cpu/umc.c2
-rw-r--r--arch/x86/kernel/ds.c3
-rw-r--r--arch/x86/kernel/e820.c53
-rw-r--r--arch/x86/kernel/early_printk.c20
-rw-r--r--arch/x86/kernel/entry_32.S18
-rw-r--r--arch/x86/kernel/entry_64.S4
-rw-r--r--arch/x86/kernel/machine_kexec_32.c17
-rw-r--r--arch/x86/kernel/machine_kexec_64.c99
-rw-r--r--arch/x86/kernel/mmconf-fam10h_64.c2
-rw-r--r--arch/x86/kernel/mpparse.c6
-rw-r--r--arch/x86/kernel/ptrace.c3
-rw-r--r--arch/x86/kernel/quirks.c3
-rw-r--r--arch/x86/kernel/relocate_kernel_32.S24
-rw-r--r--arch/x86/kernel/relocate_kernel_64.S189
-rw-r--r--arch/x86/kernel/setup_percpu.c70
-rw-r--r--arch/x86/kernel/tlb_uv.c2
-rw-r--r--arch/x86/kernel/visws_quirks.c2
-rw-r--r--arch/x86/kernel/vmlinux_64.lds.S7
-rw-r--r--arch/x86/lguest/boot.c21
-rw-r--r--arch/x86/lib/memcpy_64.S143
-rw-r--r--arch/x86/mm/highmem_32.c15
-rw-r--r--arch/x86/mm/init.c8
-rw-r--r--arch/x86/mm/init_32.c23
-rw-r--r--arch/x86/mm/init_64.c8
-rw-r--r--arch/x86/mm/iomap_32.c27
-rw-r--r--arch/x86/mm/ioremap.c57
-rw-r--r--arch/x86/mm/kmmio.c17
-rw-r--r--arch/x86/mm/memtest.c3
-rw-r--r--arch/x86/mm/pageattr.c11
-rw-r--r--arch/x86/mm/pat.c5
-rw-r--r--arch/x86/pci/common.c4
-rw-r--r--arch/x86/pci/fixup.c4
62 files changed, 1949 insertions, 648 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 31758378bcd..34bc3a89228 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -169,6 +169,9 @@ config GENERIC_HARDIRQS
bool
default y
+config GENERIC_HARDIRQS_NO__DO_IRQ
+ def_bool y
+
config GENERIC_IRQ_PROBE
bool
default y
@@ -931,6 +934,12 @@ config X86_CPUID
with major 203 and minors 0 to 31 for /dev/cpu/0/cpuid to
/dev/cpu/31/cpuid.
+config X86_CPU_DEBUG
+ tristate "/sys/kernel/debug/x86/cpu/* - CPU Debug support"
+ ---help---
+ If you select this option, this will provide various x86 CPUs
+ information through debugfs.
+
choice
prompt "High Memory Support"
default HIGHMEM4G if !X86_NUMAQ
@@ -1123,7 +1132,7 @@ config NUMA_EMU
config NODES_SHIFT
int "Maximum NUMA Nodes (as a power of 2)" if !MAXSMP
- range 1 9 if X86_64
+ range 1 9
default "9" if MAXSMP
default "6" if X86_64
default "4" if X86_NUMAQ
@@ -1431,7 +1440,7 @@ config CRASH_DUMP
config KEXEC_JUMP
bool "kexec jump (EXPERIMENTAL)"
depends on EXPERIMENTAL
- depends on KEXEC && HIBERNATION && X86_32
+ depends on KEXEC && HIBERNATION
---help---
Jump between original kernel and kexeced kernel and invoke
code in physical address mode via KEXEC
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 1836191839e..f05d8c91d9e 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -153,34 +153,23 @@ endif
boot := arch/x86/boot
-PHONY += zImage bzImage compressed zlilo bzlilo \
- zdisk bzdisk fdimage fdimage144 fdimage288 isoimage install
+BOOT_TARGETS = bzlilo bzdisk fdimage fdimage144 fdimage288 isoimage install
+
+PHONY += bzImage $(BOOT_TARGETS)
# Default kernel to build
all: bzImage
# KBUILD_IMAGE specify target image being built
- KBUILD_IMAGE := $(boot)/bzImage
-zImage zlilo zdisk: KBUILD_IMAGE := $(boot)/zImage
+KBUILD_IMAGE := $(boot)/bzImage
-zImage bzImage: vmlinux
+bzImage: vmlinux
$(Q)$(MAKE) $(build)=$(boot) $(KBUILD_IMAGE)
$(Q)mkdir -p $(objtree)/arch/$(UTS_MACHINE)/boot
$(Q)ln -fsn ../../x86/boot/bzImage $(objtree)/arch/$(UTS_MACHINE)/boot/$@
-compressed: zImage
-
-zlilo bzlilo: vmlinux
- $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(KBUILD_IMAGE) zlilo
-
-zdisk bzdisk: vmlinux
- $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(KBUILD_IMAGE) zdisk
-
-fdimage fdimage144 fdimage288 isoimage: vmlinux
- $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(KBUILD_IMAGE) $@
-
-install:
- $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(KBUILD_IMAGE) install
+$(BOOT_TARGETS): vmlinux
+ $(Q)$(MAKE) $(build)=$(boot) $@
PHONY += vdso_install
vdso_install:
@@ -205,7 +194,3 @@ define archhelp
echo ' FDARGS="..." arguments for the booted kernel'
echo ' FDINITRD=file initrd for the booted kernel'
endef
-
-CLEAN_FILES += arch/x86/boot/fdimage \
- arch/x86/boot/image.iso \
- arch/x86/boot/mtools.conf
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index c70eff69a1f..fb737ce5888 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -6,26 +6,24 @@
# for more details.
#
# Copyright (C) 1994 by Linus Torvalds
+# Changed by many, many contributors over the years.
#
# ROOT_DEV specifies the default root-device when making the image.
# This can be either FLOPPY, CURRENT, /dev/xxxx or empty, in which case
# the default of FLOPPY is used by 'build'.
-ROOT_DEV := CURRENT
+ROOT_DEV := CURRENT
# If you want to preset the SVGA mode, uncomment the next line and
# set SVGA_MODE to whatever number you want.
# Set it to -DSVGA_MODE=NORMAL_VGA if you just want the EGA/VGA mode.
# The number is the same as you would ordinarily press at bootup.
-SVGA_MODE := -DSVGA_MODE=NORMAL_VGA
+SVGA_MODE := -DSVGA_MODE=NORMAL_VGA
-# If you want the RAM disk device, define this to be the size in blocks.
-
-#RAMDISK := -DRAMDISK=512
-
-targets := vmlinux.bin setup.bin setup.elf zImage bzImage
+targets := vmlinux.bin setup.bin setup.elf bzImage
+targets += fdimage fdimage144 fdimage288 image.iso mtools.conf
subdir- := compressed
setup-y += a20.o cmdline.o copy.o cpu.o cpucheck.o edd.o
@@ -71,17 +69,13 @@ KBUILD_CFLAGS := $(LINUXINCLUDE) -g -Os -D_SETUP -D__KERNEL__ \
KBUILD_CFLAGS += $(call cc-option,-m32)
KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__
-$(obj)/zImage: asflags-y := $(SVGA_MODE) $(RAMDISK)
-$(obj)/bzImage: ccflags-y := -D__BIG_KERNEL__
-$(obj)/bzImage: asflags-y := $(SVGA_MODE) $(RAMDISK) -D__BIG_KERNEL__
-$(obj)/bzImage: BUILDFLAGS := -b
+$(obj)/bzImage: asflags-y := $(SVGA_MODE)
quiet_cmd_image = BUILD $@
-cmd_image = $(obj)/tools/build $(BUILDFLAGS) $(obj)/setup.bin \
- $(obj)/vmlinux.bin $(ROOT_DEV) > $@
+cmd_image = $(obj)/tools/build $(obj)/setup.bin $(obj)/vmlinux.bin \
+ $(ROOT_DEV) > $@
-$(obj)/zImage $(obj)/bzImage: $(obj)/setup.bin \
- $(obj)/vmlinux.bin $(obj)/tools/build FORCE
+$(obj)/bzImage: $(obj)/setup.bin $(obj)/vmlinux.bin $(obj)/tools/build FORCE
$(call if_changed,image)
@echo 'Kernel: $@ is ready' ' (#'`cat .version`')'
@@ -116,9 +110,11 @@ $(obj)/setup.bin: $(obj)/setup.elf FORCE
$(obj)/compressed/vmlinux: FORCE
$(Q)$(MAKE) $(build)=$(obj)/compressed $@
-# Set this if you want to pass append arguments to the zdisk/fdimage/isoimage kernel
+# Set this if you want to pass append arguments to the
+# bzdisk/fdimage/isoimage kernel
FDARGS =
-# Set this if you want an initrd included with the zdisk/fdimage/isoimage kernel
+# Set this if you want an initrd included with the
+# bzdisk/fdimage/isoimage kernel
FDINITRD =
image_cmdline = default linux $(FDARGS) $(if $(FDINITRD),initrd=initrd.img,)
@@ -127,7 +123,7 @@ $(obj)/mtools.conf: $(src)/mtools.conf.in
sed -e 's|@OBJ@|$(obj)|g' < $< > $@
# This requires write access to /dev/fd0
-zdisk: $(BOOTIMAGE) $(obj)/mtools.conf
+bzdisk: $(obj)/bzImage $(obj)/mtools.conf
MTOOLSRC=$(obj)/mtools.conf mformat a: ; sync
syslinux /dev/fd0 ; sync
echo '$(image_cmdline)' | \
@@ -135,10 +131,10 @@ zdisk: $(BOOTIMAGE) $(obj)/mtools.conf
if [ -f '$(FDINITRD)' ] ; then \
MTOOLSRC=$(obj)/mtools.conf mcopy '$(FDINITRD)' a:initrd.img ; \
fi
- MTOOLSRC=$(obj)/mtools.conf mcopy $(BOOTIMAGE) a:linux ; sync
+ MTOOLSRC=$(obj)/mtools.conf mcopy $(obj)/bzImage a:linux ; sync
# These require being root or having syslinux 2.02 or higher installed
-fdimage fdimage144: $(BOOTIMAGE) $(obj)/mtools.conf
+fdimage fdimage144: $(obj)/bzImage $(obj)/mtools.conf
dd if=/dev/zero of=$(obj)/fdimage bs=1024 count=1440
MTOOLSRC=$(obj)/mtools.conf mformat v: ; sync
syslinux $(obj)/fdimage ; sync
@@ -147,9 +143,9 @@ fdimage fdimage144: $(BOOTIMAGE) $(obj)/mtools.conf
if [ -f '$(FDINITRD)' ] ; then \
MTOOLSRC=$(obj)/mtools.conf mcopy '$(FDINITRD)' v:initrd.img ; \
fi
- MTOOLSRC=$(obj)/mtools.conf mcopy $(BOOTIMAGE) v:linux ; sync
+ MTOOLSRC=$(obj)/mtools.conf mcopy $(obj)/bzImage v:linux ; sync
-fdimage288: $(BOOTIMAGE) $(obj)/mtools.conf
+fdimage288: $(obj)/bzImage $(obj)/mtools.conf
dd if=/dev/zero of=$(obj)/fdimage bs=1024 count=2880
MTOOLSRC=$(obj)/mtools.conf mformat w: ; sync
syslinux $(obj)/fdimage ; sync
@@ -158,9 +154,9 @@ fdimage288: $(BOOTIMAGE) $(obj)/mtools.conf
if [ -f '$(FDINITRD)' ] ; then \
MTOOLSRC=$(obj)/mtools.conf mcopy '$(FDINITRD)' w:initrd.img ; \
fi
- MTOOLSRC=$(obj)/mtools.conf mcopy $(BOOTIMAGE) w:linux ; sync
+ MTOOLSRC=$(obj)/mtools.conf mcopy $(obj)/bzImage w:linux ; sync
-isoimage: $(BOOTIMAGE)
+isoimage: $(obj)/bzImage
-rm -rf $(obj)/isoimage
mkdir $(obj)/isoimage
for i in lib lib64 share end ; do \
@@ -170,7 +166,7 @@ isoimage: $(BOOTIMAGE)
fi ; \
if [ $$i = end ] ; then exit 1 ; fi ; \
done
- cp $(BOOTIMAGE) $(obj)/isoimage/linux
+ cp $(obj)/bzImage $(obj)/isoimage/linux
echo '$(image_cmdline)' > $(obj)/isoimage/isolinux.cfg
if [ -f '$(FDINITRD)' ] ; then \
cp '$(FDINITRD)' $(obj)/isoimage/initrd.img ; \
@@ -181,12 +177,13 @@ isoimage: $(BOOTIMAGE)
isohybrid $(obj)/image.iso 2>/dev/null || true
rm -rf $(obj)/isoimage
-zlilo: $(BOOTIMAGE)
+bzlilo: $(obj)/bzImage
if [ -f $(INSTALL_PATH)/vmlinuz ]; then mv $(INSTALL_PATH)/vmlinuz $(INSTALL_PATH)/vmlinuz.old; fi
if [ -f $(INSTALL_PATH)/System.map ]; then mv $(INSTALL_PATH)/System.map $(INSTALL_PATH)/System.old; fi
- cat $(BOOTIMAGE) > $(INSTALL_PATH)/vmlinuz
+ cat $(obj)/bzImage > $(INSTALL_PATH)/vmlinuz
cp System.map $(INSTALL_PATH)/
if [ -x /sbin/lilo ]; then /sbin/lilo; else /etc/lilo/install; fi
install:
- sh $(srctree)/$(src)/install.sh $(KERNELRELEASE) $(BOOTIMAGE) System.map "$(INSTALL_PATH)"
+ sh $(srctree)/$(src)/install.sh $(KERNELRELEASE) $(obj)/bzImage \
+ System.map "$(INSTALL_PATH)"
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index 7ccff4884a2..5d84d1c74e4 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -24,12 +24,8 @@
#include "boot.h"
#include "offsets.h"
-SETUPSECTS = 4 /* default nr of setup-sectors */
BOOTSEG = 0x07C0 /* original address of boot-sector */
-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" */
+SYSSEG = 0x1000 /* historical load address >> 4 */
#ifndef SVGA_MODE
#define SVGA_MODE ASK_VGA
@@ -97,12 +93,12 @@ bugger_off_msg:
.section ".header", "a"
.globl hdr
hdr:
-setup_sects: .byte SETUPSECTS
+setup_sects: .byte 0 /* Filled in by build.c */
root_flags: .word ROOT_RDONLY
-syssize: .long SYSSIZE
-ram_size: .word RAMDISK
+syssize: .long 0 /* Filled in by build.c */
+ram_size: .word 0 /* Obsolete */
vid_mode: .word SVGA_MODE
-root_dev: .word ROOT_DEV
+root_dev: .word 0 /* Filled in by build.c */
boot_flag: .word 0xAA55
# offset 512, entry point
@@ -123,14 +119,15 @@ _start:
# or else old loadlin-1.5 will fail)
.globl realmode_swtch
realmode_swtch: .word 0, 0 # default_switch, SETUPSEG
-start_sys_seg: .word SYSSEG
+start_sys_seg: .word SYSSEG # obsolete and meaningless, but just
+ # in case something decided to "use" it
.word kernel_version-512 # 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...)
+type_of_loader: .byte 0 # 0 means ancient bootloader, newer
+ # bootloaders know to change this.
# See Documentation/i386/boot.txt for
# assigned ids
@@ -142,11 +139,7 @@ CAN_USE_HEAP = 0x80 # If set, the loader also has set
# 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
@@ -157,11 +150,7 @@ setup_move_size: .word 0x8000 # size to move, when setup is not
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
diff --git a/arch/x86/boot/pm.c b/arch/x86/boot/pm.c
index 85a1cd8a8ff..8062f891525 100644
--- a/arch/x86/boot/pm.c
+++ b/arch/x86/boot/pm.c
@@ -33,47 +33,6 @@ static void realmode_switch_hook(void)
}
/*
- * A zImage kernel is loaded at 0x10000 but wants to run at 0x1000.
- * A bzImage kernel is loaded and runs at 0x100000.
- */
-static void move_kernel_around(void)
-{
- /* Note: rely on the compile-time option here rather than
- the LOADED_HIGH flag. The Qemu kernel loader unconditionally
- sets the loadflags to zero. */
-#ifndef __BIG_KERNEL__
- u16 dst_seg, src_seg;
- u32 syssize;
-
- dst_seg = 0x1000 >> 4;
- src_seg = 0x10000 >> 4;
- syssize = boot_params.hdr.syssize; /* Size in 16-byte paragraphs */
-
- while (syssize) {
- int paras = (syssize >= 0x1000) ? 0x1000 : syssize;
- int dwords = paras << 2;
-
- asm volatile("pushw %%es ; "
- "pushw %%ds ; "
- "movw %1,%%es ; "
- "movw %2,%%ds ; "
- "xorw %%di,%%di ; "
- "xorw %%si,%%si ; "
- "rep;movsl ; "
- "popw %%ds ; "
- "popw %%es"
- : "+c" (dwords)
- : "r" (dst_seg), "r" (src_seg)
- : "esi", "edi");
-
- syssize -= paras;
- dst_seg += paras;
- src_seg += paras;
- }
-#endif
-}
-
-/*
* Disable all interrupts at the legacy PIC.
*/
static void mask_all_interrupts(void)
@@ -147,9 +106,6 @@ void go_to_protected_mode(void)
/* Hook before leaving real mode, also disables interrupts */
realmode_switch_hook();
- /* Move the kernel/setup to their final resting places */
- move_kernel_around();
-
/* Enable the A20 gate */
if (enable_a20()) {
puts("A20 gate not responding, unable to boot...\n");
diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c
index 44dc1923c0e..ee3a4ea923a 100644
--- a/arch/x86/boot/tools/build.c
+++ b/arch/x86/boot/tools/build.c
@@ -130,7 +130,7 @@ static void die(const char * str, ...)
static void usage(void)
{
- die("Usage: build [-b] setup system [rootdev] [> image]");
+ die("Usage: build setup system [rootdev] [> image]");
}
int main(int argc, char ** argv)
@@ -145,11 +145,6 @@ int main(int argc, char ** argv)
void *kernel;
u32 crc = 0xffffffffUL;
- if (argc > 2 && !strcmp(argv[1], "-b"))
- {
- is_big_kernel = 1;
- argc--, argv++;
- }
if ((argc < 3) || (argc > 4))
usage();
if (argc > 3) {
@@ -216,8 +211,6 @@ int main(int argc, char ** argv)
die("Unable to mmap '%s': %m", argv[2]);
/* Number of 16-byte paragraphs, including space for a 4-byte CRC */
sys_size = (sz + 15 + 4) / 16;
- if (!is_big_kernel && sys_size > DEF_SYSSIZE)
- die("System is too big. Try using bzImage or modules.");
/* Patch the setup code with the appropriate size parameters */
buf[0x1f1] = setup_sectors-1;
diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h
index 6526cf08b0e..6ba23dd9fc9 100644
--- a/arch/x86/include/asm/boot.h
+++ b/arch/x86/include/asm/boot.h
@@ -1,10 +1,6 @@
#ifndef _ASM_X86_BOOT_H
#define _ASM_X86_BOOT_H
-/* Don't touch these, unless you really know what you're doing. */
-#define DEF_SYSSEG 0x1000
-#define DEF_SYSSIZE 0x7F00
-
/* Internal svga startup constants */
#define NORMAL_VGA 0xffff /* 80x25 mode */
#define EXTENDED_VGA 0xfffe /* 80x50 mode */
diff --git a/arch/x86/include/asm/cpu_debug.h b/arch/x86/include/asm/cpu_debug.h
new file mode 100755
index 00000000000..56f1635e461
--- /dev/null
+++ b/arch/x86/include/asm/cpu_debug.h
@@ -0,0 +1,199 @@
+#ifndef _ASM_X86_CPU_DEBUG_H
+#define _ASM_X86_CPU_DEBUG_H
+
+/*
+ * CPU x86 architecture debug
+ *
+ * Copyright(C) 2009 Jaswinder Singh Rajput
+ */
+
+/* Register flags */
+enum cpu_debug_bit {
+/* Model Specific Registers (MSRs) */
+ CPU_MC_BIT, /* Machine Check */
+ CPU_MONITOR_BIT, /* Monitor */
+ CPU_TIME_BIT, /* Time */
+ CPU_PMC_BIT, /* Performance Monitor */
+ CPU_PLATFORM_BIT, /* Platform */
+ CPU_APIC_BIT, /* APIC */
+ CPU_POWERON_BIT, /* Power-on */
+ CPU_CONTROL_BIT, /* Control */
+ CPU_FEATURES_BIT, /* Features control */
+ CPU_LBRANCH_BIT, /* Last Branch */
+ CPU_BIOS_BIT, /* BIOS */
+ CPU_FREQ_BIT, /* Frequency */
+ CPU_MTTR_BIT, /* MTRR */
+ CPU_PERF_BIT, /* Performance */
+ CPU_CACHE_BIT, /* Cache */
+ CPU_SYSENTER_BIT, /* Sysenter */
+ CPU_THERM_BIT, /* Thermal */
+ CPU_MISC_BIT, /* Miscellaneous */
+ CPU_DEBUG_BIT, /* Debug */
+ CPU_PAT_BIT, /* PAT */
+ CPU_VMX_BIT, /* VMX */
+ CPU_CALL_BIT, /* System Call */
+ CPU_BASE_BIT, /* BASE Address */
+ CPU_SMM_BIT, /* System mgmt mode */
+ CPU_SVM_BIT, /*Secure Virtual Machine*/
+ CPU_OSVM_BIT, /* OS-Visible Workaround*/
+/* Standard Registers */
+ CPU_TSS_BIT, /* Task Stack Segment */
+ CPU_CR_BIT, /* Control Registers */
+ CPU_DT_BIT, /* Descriptor Table */
+/* End of Registers flags */
+ CPU_REG_ALL_BIT, /* Select all Registers */
+};
+
+#define CPU_REG_ALL (~0) /* Select all Registers */
+
+#define CPU_MC (1 << CPU_MC_BIT)
+#define CPU_MONITOR (1 << CPU_MONITOR_BIT)
+#define CPU_TIME (1 << CPU_TIME_BIT)
+#define CPU_PMC (1 << CPU_PMC_BIT)
+#define CPU_PLATFORM (1 << CPU_PLATFORM_BIT)
+#define CPU_APIC (1 << CPU_APIC_BIT)
+#define CPU_POWERON (1 << CPU_POWERON_BIT)
+#define CPU_CONTROL (1 << CPU_CONTROL_BIT)
+#define CPU_FEATURES (1 << CPU_FEATURES_BIT)
+#define CPU_LBRANCH (1 << CPU_LBRANCH_BIT)
+#define CPU_BIOS (1 << CPU_BIOS_BIT)
+#define CPU_FREQ (1 << CPU_FREQ_BIT)
+#define CPU_MTRR (1 << CPU_MTTR_BIT)
+#define CPU_PERF (1 << CPU_PERF_BIT)
+#define CPU_CACHE (1 << CPU_CACHE_BIT)
+#define CPU_SYSENTER (1 << CPU_SYSENTER_BIT)
+#define CPU_THERM (1 << CPU_THERM_BIT)
+#define CPU_MISC (1 << CPU_MISC_BIT)
+#define CPU_DEBUG (1 << CPU_DEBUG_BIT)
+#define CPU_PAT (1 << CPU_PAT_BIT)
+#define CPU_VMX (1 << CPU_VMX_BIT)
+#define CPU_CALL (1 << CPU_CALL_BIT)
+#define CPU_BASE (1 << CPU_BASE_BIT)
+#define CPU_SMM (1 << CPU_SMM_BIT)
+#define CPU_SVM (1 << CPU_SVM_BIT)
+#define CPU_OSVM (1 << CPU_OSVM_BIT)
+#define CPU_TSS (1 << CPU_TSS_BIT)
+#define CPU_CR (1 << CPU_CR_BIT)
+#define CPU_DT (1 << CPU_DT_BIT)
+
+/* Register file flags */
+enum cpu_file_bit {
+ CPU_INDEX_BIT, /* index */
+ CPU_VALUE_BIT, /* value */
+};
+
+#define CPU_FILE_VALUE (1 << CPU_VALUE_BIT)
+
+/*
+ * DisplayFamily_DisplayModel Processor Families/Processor Number Series
+ * -------------------------- ------------------------------------------
+ * 05_01, 05_02, 05_04 Pentium, Pentium with MMX
+ *
+ * 06_01 Pentium Pro
+ * 06_03, 06_05 Pentium II Xeon, Pentium II
+ * 06_07, 06_08, 06_0A, 06_0B Pentium III Xeon, Pentum III
+ *
+ * 06_09, 060D Pentium M
+ *
+ * 06_0E Core Duo, Core Solo
+ *
+ * 06_0F Xeon 3000, 3200, 5100, 5300, 7300 series,
+ * Core 2 Quad, Core 2 Extreme, Core 2 Duo,
+ * Pentium dual-core
+ * 06_17 Xeon 5200, 5400 series, Core 2 Quad Q9650
+ *
+ * 06_1C Atom
+ *
+ * 0F_00, 0F_01, 0F_02 Xeon, Xeon MP, Pentium 4
+ * 0F_03, 0F_04 Xeon, Xeon MP, Pentium 4, Pentium D
+ *
+ * 0F_06 Xeon 7100, 5000 Series, Xeon MP,
+ * Pentium 4, Pentium D
+ */
+
+/* Register processors bits */
+enum cpu_processor_bit {
+ CPU_NONE,
+/* Intel */
+ CPU_INTEL_PENTIUM_BIT,
+ CPU_INTEL_P6_BIT,
+ CPU_INTEL_PENTIUM_M_BIT,
+ CPU_INTEL_CORE_BIT,
+ CPU_INTEL_CORE2_BIT,
+ CPU_INTEL_ATOM_BIT,
+ CPU_INTEL_XEON_P4_BIT,
+ CPU_INTEL_XEON_MP_BIT,
+};
+
+#define CPU_ALL (~0) /* Select all CPUs */
+
+#define CPU_INTEL_PENTIUM (1 << CPU_INTEL_PENTIUM_BIT)
+#define CPU_INTEL_P6 (1 << CPU_INTEL_P6_BIT)
+#define CPU_INTEL_PENTIUM_M (1 << CPU_INTEL_PENTIUM_M_BIT)
+#define CPU_INTEL_CORE (1 << CPU_INTEL_CORE_BIT)
+#define CPU_INTEL_CORE2 (1 << CPU_INTEL_CORE2_BIT)
+#define CPU_INTEL_ATOM (1 << CPU_INTEL_ATOM_BIT)
+#define CPU_INTEL_XEON_P4 (1 << CPU_INTEL_XEON_P4_BIT)
+#define CPU_INTEL_XEON_MP (1 << CPU_INTEL_XEON_MP_BIT)
+
+#define CPU_INTEL_PX (CPU_INTEL_P6 | CPU_INTEL_PENTIUM_M)
+#define CPU_INTEL_COREX (CPU_INTEL_CORE | CPU_INTEL_CORE2)
+#define CPU_INTEL_XEON (CPU_INTEL_XEON_P4 | CPU_INTEL_XEON_MP)
+#define CPU_CO_AT (CPU_INTEL_CORE | CPU_INTEL_ATOM)
+#define CPU_C2_AT (CPU_INTEL_CORE2 | CPU_INTEL_ATOM)
+#define CPU_CX_AT (CPU_INTEL_COREX | CPU_INTEL_ATOM)
+#define CPU_CX_XE (CPU_INTEL_COREX | CPU_INTEL_XEON)
+#define CPU_P6_XE (CPU_INTEL_P6 | CPU_INTEL_XEON)
+#define CPU_PM_CO_AT (CPU_INTEL_PENTIUM_M | CPU_CO_AT)
+#define CPU_C2_AT_XE (CPU_C2_AT | CPU_INTEL_XEON)
+#define CPU_CX_AT_XE (CPU_CX_AT | CPU_INTEL_XEON)
+#define CPU_P6_CX_AT (CPU_INTEL_P6 | CPU_CX_AT)
+#define CPU_P6_CX_XE (CPU_P6_XE | CPU_INTEL_COREX)
+#define CPU_P6_CX_AT_XE (CPU_INTEL_P6 | CPU_CX_AT_XE)
+#define CPU_PM_CX_AT_XE (CPU_INTEL_PENTIUM_M | CPU_CX_AT_XE)
+#define CPU_PM_CX_AT (CPU_INTEL_PENTIUM_M | CPU_CX_AT)
+#define CPU_PM_CX_XE (CPU_INTEL_PENTIUM_M | CPU_CX_XE)
+#define CPU_PX_CX_AT (CPU_INTEL_PX | CPU_CX_AT)
+#define CPU_PX_CX_AT_XE (CPU_INTEL_PX | CPU_CX_AT_XE)
+
+/* Select all Intel CPUs*/
+#define CPU_INTEL_ALL (CPU_INTEL_PENTIUM | CPU_PX_CX_AT_XE)
+
+#define MAX_CPU_FILES 512
+
+struct cpu_private {
+ unsigned cpu;
+ unsigned type;
+ unsigned reg;
+ unsigned file;
+};
+
+struct cpu_debug_base {
+ char *name; /* Register name */
+ unsigned flag; /* Register flag */
+ unsigned write; /* Register write flag */
+};
+
+/*
+ * Currently it looks similar to cpu_debug_base but once we add more files
+ * cpu_file_base will go in different direction
+ */
+struct cpu_file_base {
+ char *name; /* Register file name */
+ unsigned flag; /* Register file flag */
+ unsigned write; /* Register write flag */
+};
+
+struct cpu_cpuX_base {
+ struct dentry *dentry; /* Register dentry */
+ int init; /* Register index file */
+};
+
+struct cpu_debug_range {
+ unsigned min; /* Register range min */
+ unsigned max; /* Register range max */
+ unsigned flag; /* Supported flags */
+ unsigned model; /* Supported models */
+};
+
+#endif /* _ASM_X86_CPU_DEBUG_H */
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index dc27705f544..5623c50d67b 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -91,7 +91,6 @@ static inline int desc_empty(const void *ptr)
#define store_gdt(dtr) native_store_gdt(dtr)
#define store_idt(dtr) native_store_idt(dtr)
#define store_tr(tr) (tr = native_store_tr())
-#define store_ldt(ldt) asm("sldt %0":"=m" (ldt))
#define load_TLS(t, cpu) native_load_tls(t, cpu)
#define set_ldt native_set_ldt
@@ -112,6 +111,8 @@ static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries)
}
#endif /* CONFIG_PARAVIRT */
+#define store_ldt(ldt) asm("sldt %0" : "=m"(ldt))
+
static inline void native_write_idt_entry(gate_desc *idt, int entry,
const gate_desc *gate)
{
diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h
index bf9276bea66..014c2b85ae4 100644
--- a/arch/x86/include/asm/highmem.h
+++ b/arch/x86/include/asm/highmem.h
@@ -63,6 +63,7 @@ void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot);
void *kmap_atomic(struct page *page, enum km_type type);
void kunmap_atomic(void *kvaddr, enum km_type type);
void *kmap_atomic_pfn(unsigned long pfn, enum km_type type);
+void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot);
struct page *kmap_atomic_to_page(void *ptr);
#ifndef CONFIG_PARAVIRT
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index 0ceb6d19ed3..317ff1703d0 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -9,13 +9,13 @@
# define PAGES_NR 4
#else
# define PA_CONTROL_PAGE 0
-# define PA_TABLE_PAGE 1
-# define PAGES_NR 2
+# define VA_CONTROL_PAGE 1
+# define PA_TABLE_PAGE 2
+# define PA_SWAP_PAGE 3
+# define PAGES_NR 4
#endif
-#ifdef CONFIG_X86_32
# define KEXEC_CONTROL_CODE_MAX_SIZE 2048
-#endif
#ifndef __ASSEMBLY__
@@ -136,10 +136,11 @@ relocate_kernel(unsigned long indirection_page,
unsigned int has_pae,
unsigned int preserve_context);
#else
-NORET_TYPE void
+unsigned long
relocate_kernel(unsigned long indirection_page,
unsigned long page_list,
- unsigned long start_address) ATTRIB_NORET;
+ unsigned long start_address,
+ unsigned int preserve_context);
#endif
#define ARCH_HAS_KIMAGE_ARCH
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index 9320e2a8a26..12d55e773eb 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -1,14 +1,11 @@
#ifndef _ASM_X86_LINKAGE_H
#define _ASM_X86_LINKAGE_H
+#include <linux/stringify.h>
+
#undef notrace
#define notrace __attribute__((no_instrument_function))
-#ifdef CONFIG_X86_64
-#define __ALIGN .p2align 4,,15
-#define __ALIGN_STR ".p2align 4,,15"
-#endif
-
#ifdef CONFIG_X86_32
#define asmlinkage CPP_ASMLINKAGE __attribute__((regparm(0)))
/*
@@ -50,16 +47,20 @@
__asmlinkage_protect_n(ret, "g" (arg1), "g" (arg2), "g" (arg3), \
"g" (arg4), "g" (arg5), "g" (arg6))
-#endif
+#endif /* CONFIG_X86_32 */
+
+#ifdef __ASSEMBLY__
#define GLOBAL(name) \
.globl name; \
name:
-#ifdef CONFIG_X86_ALIGNMENT_16
-#define __ALIGN .align 16,0x90
-#define __ALIGN_STR ".align 16,0x90"
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_ALIGNMENT_16)
+#define __ALIGN .p2align 4, 0x90
+#define __ALIGN_STR __stringify(__ALIGN)
#endif
+#endif /* __ASSEMBLY__ */
+
#endif /* _ASM_X86_LINKAGE_H */
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 8f1d2fbec1d..aee103b26d0 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -43,14 +43,6 @@
#else /* ...!ASSEMBLY */
#include <linux/stringify.h>
-#include <asm/sections.h>
-
-#define __addr_to_pcpu_ptr(addr) \
- (void *)((unsigned long)(addr) - (unsigned long)pcpu_base_addr \
- + (unsigned long)__per_cpu_start)
-#define __pcpu_ptr_to_addr(ptr) \
- (void *)((unsigned long)(ptr) + (unsigned long)pcpu_base_addr \
- - (unsigned long)__per_cpu_start)
#ifdef CONFIG_SMP
#define __percpu_arg(x) "%%"__stringify(__percpu_seg)":%P" #x
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 76139506c3e..ae85a8d66a3 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -75,9 +75,9 @@ struct cpuinfo_x86 {
#else
/* Number of 4K pages in DTLB/ITLB combined(in pages): */
int x86_tlbsize;
+#endif
__u8 x86_virt_bits;
__u8 x86_phys_bits;
-#endif
/* CPUID returned core id bits: */
__u8 x86_coreid_bits;
/* Max extended CPUID function supported: */
@@ -391,6 +391,9 @@ DECLARE_PER_CPU(union irq_stack_union, irq_stack_union);
DECLARE_INIT_PER_CPU(irq_stack_union);
DECLARE_PER_CPU(char *, irq_stack_ptr);
+DECLARE_PER_CPU(unsigned int, irq_count);
+extern unsigned long kernel_eflags;
+extern asmlinkage void ignore_sysret(void);
#else /* X86_64 */
#ifdef CONFIG_CC_STACKPROTECTOR
DECLARE_PER_CPU(unsigned long, stack_canary);
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 5e79ca69432..9c371e4a9fa 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -296,6 +296,8 @@ HYPERVISOR_get_debugreg(int reg)
static inline int
HYPERVISOR_update_descriptor(u64 ma, u64 desc)
{
+ if (sizeof(u64) == sizeof(long))
+ return _hypercall2(int, update_descriptor, ma, desc);
return _hypercall4(int, update_descriptor, ma, ma>>32, desc, desc>>32);
}
diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c
index 2ac0ab71412..b617b1164f1 100644
--- a/arch/x86/kernel/check.c
+++ b/arch/x86/kernel/check.c
@@ -83,7 +83,7 @@ void __init setup_bios_corruption_check(void)
u64 size;
addr = find_e820_area_size(addr, &size, PAGE_SIZE);
- if (addr == 0)
+ if (!(addr + 1))
break;
if ((addr + size) > corruption_check_size)
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 82db7f45e2d..d4356f8b752 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -14,6 +14,8 @@ obj-y += vmware.o hypervisor.o
obj-$(CONFIG_X86_32) += bugs.o cmpxchg.o
obj-$(CONFIG_X86_64) += bugs_64.o
+obj-$(CONFIG_X86_CPU_DEBUG) += cpu_debug.o
+
obj-$(CONFIG_CPU_SUP_INTEL) += intel.o
obj-$(CONFIG_CPU_SUP_AMD) += amd.o
obj-$(CONFIG_CPU_SUP_CYRIX_32) += cyrix.o
diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/addon_cpuid_features.c
index 6882a735d9c..8220ae69849 100644
--- a/arch/x86/kernel/cpu/addon_cpuid_features.c
+++ b/arch/x86/kernel/cpu/addon_cpuid_features.c
@@ -29,7 +29,7 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c)
u32 regs[4];
const struct cpuid_bit *cb;
- static const struct cpuid_bit cpuid_bits[] = {
+ static const struct cpuid_bit __cpuinitconst cpuid_bits[] = {
{ X86_FEATURE_IDA, CR_EAX, 1, 0x00000006 },
{ 0, 0, 0, 0 }
};
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index f47df59016c..7e4a459daa6 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -502,7 +502,7 @@ static unsigned int __cpuinit amd_size_cache(struct cpuinfo_x86 *c, unsigned int
}
#endif
-static struct cpu_dev amd_cpu_dev __cpuinitdata = {
+static const struct cpu_dev __cpuinitconst amd_cpu_dev = {
.c_vendor = "AMD",
.c_ident = { "AuthenticAMD" },
#ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index 89bfdd9cacc..983e0830f0d 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -468,7 +468,7 @@ centaur_size_cache(struct cpuinfo_x86 *c, unsigned int size)
return size;
}
-static struct cpu_dev centaur_cpu_dev __cpuinitdata = {
+static const struct cpu_dev __cpuinitconst centaur_cpu_dev = {
.c_vendor = "Centaur",
.c_ident = { "CentaurHauls" },
.c_early_init = early_init_centaur,
diff --git a/arch/x86/kernel/cpu/centaur_64.c b/arch/x86/kernel/cpu/centaur_64.c
index a1625f5a1e7..51b09c48c9c 100644
--- a/arch/x86/kernel/cpu/centaur_64.c
+++ b/arch/x86/kernel/cpu/centaur_64.c
@@ -25,7 +25,7 @@ static void __cpuinit init_centaur(struct cpuinfo_x86 *c)
set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
}
-static struct cpu_dev centaur_cpu_dev __cpuinitdata = {
+static const struct cpu_dev centaur_cpu_dev __cpuinitconst = {
.c_vendor = "Centaur",
.c_ident = { "CentaurHauls" },
.c_early_init = early_init_centaur,
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 826d5c87627..e2962cc1e27 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1,52 +1,52 @@
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/string.h>
#include <linux/bootmem.h>
+#include <linux/linkage.h>
#include <linux/bitops.h>
+#include <linux/kernel.h>
#include <linux/module.h>
-#include <linux/kgdb.h>
-#include <linux/topology.h>
+#include <linux/percpu.h>
+#include <linux/string.h>
#include <linux/delay.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/kgdb.h>
#include <linux/smp.h>
-#include <linux/percpu.h>
-#include <asm/i387.h>
-#include <asm/msr.h>
-#include <asm/io.h>
-#include <asm/linkage.h>
+#include <linux/io.h>
+
+#include <asm/stackprotector.h>
#include <asm/mmu_context.h>
+#include <asm/hypervisor.h>
+#include <asm/processor.h>
+#include <asm/sections.h>
+#include <asm/topology.h>
+#include <asm/cpumask.h>
+#include <asm/pgtable.h>
+#include <asm/atomic.h>
+#include <asm/proto.h>
+#include <asm/setup.h>
+#include <asm/apic.h>
+#include <asm/desc.h>
+#include <asm/i387.h>
#include <asm/mtrr.h>
+#include <asm/numa.h>
+#include <asm/asm.h>
+#include <asm/cpu.h>
#include <asm/mce.h>
+#include <asm/msr.h>
#include <asm/pat.h>
-#include <asm/asm.h>
-#include <asm/numa.h>
#include <asm/smp.h>
-#include <asm/cpu.h>
-#include <asm/cpumask.h>
-#include <asm/apic.h>
#ifdef CONFIG_X86_LOCAL_APIC
#include <asm/uv/uv.h>
#endif
-#include <asm/pgtable.h>
-#include <asm/processor.h>
-#include <asm/desc.h>
-#include <asm/atomic.h>
-#include <asm/proto.h>
-#include <asm/sections.h>
-#include <asm/setup.h>
-#include <asm/hypervisor.h>
-#include <asm/stackprotector.h>
-
#include "cpu.h"
#ifdef CONFIG_X86_64
/* all of these masks are initialized in setup_cpu_local_masks() */
-cpumask_var_t cpu_callin_mask;
-cpumask_var_t cpu_callout_mask;
cpumask_var_t cpu_initialized_mask;
+cpumask_var_t cpu_callout_mask;
+cpumask_var_t cpu_callin_mask;
/* representing cpus for which sibling maps can be computed */
cpumask_var_t cpu_sibling_setup_mask;
@@ -62,15 +62,15 @@ void __init setup_cpu_local_masks(void)
#else /* CONFIG_X86_32 */
-cpumask_t cpu_callin_map;
+cpumask_t cpu_sibling_setup_map;
cpumask_t cpu_callout_map;
cpumask_t cpu_initialized;
-cpumask_t cpu_sibling_setup_map;
+cpumask_t cpu_callin_map;
#endif /* CONFIG_X86_32 */
-static struct cpu_dev *this_cpu __cpuinitdata;
+static const struct cpu_dev *this_cpu __cpuinitdata;
DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
#ifdef CONFIG_X86_64
@@ -79,48 +79,48 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
* IRET will check the segment types kkeil 2000/10/28
* Also sysret mandates a special GDT layout
*
- * The TLS descriptors are currently at a different place compared to i386.
+ * TLS descriptors are currently at a different place compared to i386.
* Hopefully nobody expects them at a fixed place (Wine?)
*/
- [GDT_ENTRY_KERNEL32_CS] = { { { 0x0000ffff, 0x00cf9b00 } } },
- [GDT_ENTRY_KERNEL_CS] = { { { 0x0000ffff, 0x00af9b00 } } },
- [GDT_ENTRY_KERNEL_DS] = { { { 0x0000ffff, 0x00cf9300 } } },
- [GDT_ENTRY_DEFAULT_USER32_CS] = { { { 0x0000ffff, 0x00cffb00 } } },
- [GDT_ENTRY_DEFAULT_USER_DS] = { { { 0x0000ffff, 0x00cff300 } } },
- [GDT_ENTRY_DEFAULT_USER_CS] = { { { 0x0000ffff, 0x00affb00 } } },
+ [GDT_ENTRY_KERNEL32_CS] = { { { 0x0000ffff, 0x00cf9b00 } } },
+ [GDT_ENTRY_KERNEL_CS] = { { { 0x0000ffff, 0x00af9b00 } } },
+ [GDT_ENTRY_KERNEL_DS] = { { { 0x0000ffff, 0x00cf9300 } } },
+ [GDT_ENTRY_DEFAULT_USER32_CS] = { { { 0x0000ffff, 0x00cffb00 } } },
+ [GDT_ENTRY_DEFAULT_USER_DS] = { { { 0x0000ffff, 0x00cff300 } } },
+ [GDT_ENTRY_DEFAULT_USER_CS] = { { { 0x0000ffff, 0x00affb00 } } },
#else
- [GDT_ENTRY_KERNEL_CS] = { { { 0x0000ffff, 0x00cf9a00 } } },
- [GDT_ENTRY_KERNEL_DS] = { { { 0x0000ffff, 0x00cf9200 } } },
- [GDT_ENTRY_DEFAULT_USER_CS] = { { { 0x0000ffff, 0x00cffa00 } } },
- [GDT_ENTRY_DEFAULT_USER_DS] = { { { 0x0000ffff, 0x00cff200 } } },
+ [GDT_ENTRY_KERNEL_CS] = { { { 0x0000ffff, 0x00cf9a00 } } },
+ [GDT_ENTRY_KERNEL_DS] = { { { 0x0000ffff, 0x00cf9200 } } },
+ [GDT_ENTRY_DEFAULT_USER_CS] = { { { 0x0000ffff, 0x00cffa00 } } },
+ [GDT_ENTRY_DEFAULT_USER_DS] = { { { 0x0000ffff, 0x00cff200 } } },
/*
* Segments used for calling PnP BIOS have byte granularity.
* They code segments and data segments have fixed 64k limits,
* the transfer segment sizes are set at run time.
*/
/* 32-bit code */
- [GDT_ENTRY_PNPBIOS_CS32] = { { { 0x0000ffff, 0x00409a00 } } },
+ [GDT_ENTRY_PNPBIOS_CS32] = { { { 0x0000ffff, 0x00409a00 } } },
/* 16-bit code */
- [GDT_ENTRY_PNPBIOS_CS16] = { { { 0x0000ffff, 0x00009a00 } } },
+ [GDT_ENTRY_PNPBIOS_CS16] = { { { 0x0000ffff, 0x00009a00 } } },
/* 16-bit data */
- [GDT_ENTRY_PNPBIOS_DS] = { { { 0x0000ffff, 0x00009200 } } },
+ [GDT_ENTRY_PNPBIOS_DS] = { { { 0x0000ffff, 0x00009200 } } },
/* 16-bit data */
- [GDT_ENTRY_PNPBIOS_TS1] = { { { 0x00000000, 0x00009200 } } },
+ [GDT_ENTRY_PNPBIOS_TS1] = { { { 0x00000000, 0x00009200 } } },
/* 16-bit data */
- [GDT_ENTRY_PNPBIOS_TS2] = { { { 0x00000000, 0x00009200 } } },
+ [GDT_ENTRY_PNPBIOS_TS2] = { { { 0x00000000, 0x00009200 } } },
/*
* The APM segments have byte granularity and their bases
* are set at run time. All have 64k limits.
*/
/* 32-bit code */
- [GDT_ENTRY_APMBIOS_BASE] = { { { 0x0000ffff, 0x00409a00 } } },
+ [GDT_ENTRY_APMBIOS_BASE] = { { { 0x0000ffff, 0x00409a00 } } },
/* 16-bit code */
- [GDT_ENTRY_APMBIOS_BASE+1] = { { { 0x0000ffff, 0x00009a00 } } },
+ [GDT_ENTRY_APMBIOS_BASE+1] = { { { 0x0000ffff, 0x00009a00 } } },
/* data */
- [GDT_ENTRY_APMBIOS_BASE+2] = { { { 0x0000ffff, 0x00409200 } } },
+ [GDT_ENTRY_APMBIOS_BASE+2] = { { { 0x0000ffff, 0x00409200 } } },
- [GDT_ENTRY_ESPFIX_SS] = { { { 0x00000000, 0x00c09200 } } },
- [GDT_ENTRY_PERCPU] = { { { 0x0000ffff, 0x00cf9200 } } },
+ [GDT_ENTRY_ESPFIX_SS] = { { { 0x00000000, 0x00c09200 } } },
+ [GDT_ENTRY_PERCPU] = { { { 0x0000ffff, 0x00cf9200 } } },
GDT_STACK_CANARY_INIT
#endif
} };
@@ -164,16 +164,17 @@ static inline int flag_is_changeable_p(u32 flag)
* the CPUID. Add "volatile" to not allow gcc to
* optimize the subsequent calls to this function.
*/
- asm volatile ("pushfl\n\t"
- "pushfl\n\t"
- "popl %0\n\t"
- "movl %0,%1\n\t"
- "xorl %2,%0\n\t"
- "pushl %0\n\t"
- "popfl\n\t"
- "pushfl\n\t"
- "popl %0\n\t"
- "popfl\n\t"
+ asm volatile ("pushfl \n\t"
+ "pushfl \n\t"
+ "popl %0 \n\t"
+ "movl %0, %1 \n\t"
+ "xorl %2, %0 \n\t"
+ "pushl %0 \n\t"
+ "popfl \n\t"
+ "pushfl \n\t"
+ "popl %0 \n\t"
+ "popfl \n\t"
+
: "=&r" (f1), "=&r" (f2)
: "ir" (flag));
@@ -188,18 +189,22 @@ static int __cpuinit have_cpuid_p(void)
static void __cpuinit squash_the_stupid_serial_number(struct cpuinfo_x86 *c)
{
- if (cpu_has(c, X86_FEATURE_PN) && disable_x86_serial_nr) {
- /* Disable processor serial number */
- unsigned long lo, hi;
- rdmsr(MSR_IA32_BBL_CR_CTL, lo, hi);
- lo |= 0x200000;
- wrmsr(MSR_IA32_BBL_CR_CTL, lo, hi);
- printk(KERN_NOTICE "CPU serial number disabled.\n");
- clear_cpu_cap(c, X86_FEATURE_PN);
-
- /* Disabling the serial number may affect the cpuid level */
- c->cpuid_level = cpuid_eax(0);
- }
+ unsigned long lo, hi;
+
+ if (!cpu_has(c, X86_FEATURE_PN) || !disable_x86_serial_nr)
+ return;
+
+ /* Disable processor serial number: */
+
+ rdmsr(MSR_IA32_BBL_CR_CTL, lo, hi);
+ lo |= 0x200000;
+ wrmsr(MSR_IA32_BBL_CR_CTL, lo, hi);
+
+ printk(KERN_NOTICE "CPU serial number disabled.\n");
+ clear_cpu_cap(c, X86_FEATURE_PN);
+
+ /* Disabling the serial number may affect the cpuid level */
+ c->cpuid_level = cpuid_eax(0);
}
static int __init x86_serial_nr_setup(char *s)
@@ -232,6 +237,7 @@ struct cpuid_dependent_feature {
u32 feature;
u32 level;
};
+
static const struct cpuid_dependent_feature __cpuinitconst
cpuid_dependent_features[] = {
{ X86_FEATURE_MWAIT, 0x00000005 },
@@ -243,7 +249,11 @@ cpuid_dependent_features[] = {
static void __cpuinit filter_cpuid_features(struct cpuinfo_x86 *c, bool warn)
{
const struct cpuid_dependent_feature *df;
+
for (df = cpuid_dependent_features; df->feature; df++) {
+
+ if (!cpu_has(c, df->feature))
+ continue;
/*
* Note: cpuid_level is set to -1 if unavailable, but
* extended_extended_level is set to 0 if unavailable
@@ -251,32 +261,32 @@ static void __cpuinit filter_cpuid_features(struct cpuinfo_x86 *c, bool warn)
* when signed; hence the weird messing around with
* signs here...
*/
- if (cpu_has(c, df->feature) &&
- ((s32)df->level < 0 ?
+ if (!((s32)df->level < 0 ?
(u32)df->level > (u32)c->extended_cpuid_level :
- (s32)df->level > (s32)c->cpuid_level)) {
- clear_cpu_cap(c, df->feature);
- if (warn)
- printk(KERN_WARNING
- "CPU: CPU feature %s disabled "
- "due to lack of CPUID level 0x%x\n",
- x86_cap_flags[df->feature],
- df->level);
- }
+ (s32)df->level > (s32)c->cpuid_level))
+ continue;
+
+ clear_cpu_cap(c, df->feature);
+ if (!warn)
+ continue;
+
+ printk(KERN_WARNING
+ "CPU: CPU feature %s disabled, no CPUID level 0x%x\n",
+ x86_cap_flags[df->feature], df->level);
}
}
/*
* Naming convention should be: <Name> [(<Codename>)]
* This table only is used unless init_<vendor>() below doesn't set it;
- * in particular, if CPUID levels 0x80000002..4 are supported, this isn't used
- *
+ * in particular, if CPUID levels 0x80000002..4 are supported, this
+ * isn't used
*/
/* Look up CPU names by table lookup. */
-static char __cpuinit *table_lookup_model(struct cpuinfo_x86 *c)
+static const char *__cpuinit table_lookup_model(struct cpuinfo_x86 *c)
{
- struct cpu_model_info *info;
+ const struct cpu_model_info *info;
if (c->x86_model >= 16)
return NULL; /* Range check */
@@ -307,8 +317,10 @@ void load_percpu_segment(int cpu)
load_stack_canary_segment();
}
-/* Current gdt points %fs at the "master" per-cpu area: after this,
- * it's on the real one. */
+/*
+ * Current gdt points %fs at the "master" per-cpu area: after this,
+ * it's on the real one.
+ */
void switch_to_new_gdt(int cpu)
{
struct desc_ptr gdt_descr;
@@ -321,7 +333,7 @@ void switch_to_new_gdt(int cpu)
load_percpu_segment(cpu);
}
-static struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {};
+static const struct cpu_dev *__cpuinitdata cpu_devs[X86_VENDOR_NUM] = {};
static void __cpuinit default_init(struct cpuinfo_x86 *c)
{
@@ -340,7 +352,7 @@ static void __cpuinit default_init(struct cpuinfo_x86 *c)
#endif
}
-static struct cpu_dev __cpuinitdata default_cpu = {
+static const struct cpu_dev __cpuinitconst default_cpu = {
.c_init = default_init,
.c_vendor = "Unknown",
.c_x86_vendor = X86_VENDOR_UNKNOWN,
@@ -354,22 +366,24 @@ static void __cpuinit get_model_name(struct cpuinfo_x86 *c)
if (c->extended_cpuid_level < 0x80000004)
return;
- v = (unsigned int *) c->x86_model_id;
+ v = (unsigned int *)c->x86_model_id;
cpuid(0x80000002, &v[0], &v[1], &v[2], &v[3]);
cpuid(0x80000003, &v[4], &v[5], &v[6], &v[7]);
cpuid(0x80000004, &v[8], &v[9], &v[10], &v[11]);
c->x86_model_id[48] = 0;
- /* Intel chips right-justify this string for some dumb reason;
- undo that brain damage */
+ /*
+ * Intel chips right-justify this string for some dumb reason;
+ * undo that brain damage:
+ */
p = q = &c->x86_model_id[0];
while (*p == ' ')
- p++;
+ p++;
if (p != q) {
- while (*p)
- *q++ = *p++;
- while (q <= &c->x86_model_id[48])
- *q++ = '\0'; /* Zero-pad the rest */
+ while (*p)
+ *q++ = *p++;
+ while (q <= &c->x86_model_id[48])
+ *q++ = '\0'; /* Zero-pad the rest */
}
}
@@ -438,27 +452,30 @@ void __cpuinit detect_ht(struct cpuinfo_x86 *c)
if (smp_num_siblings == 1) {
printk(KERN_INFO "CPU: Hyper-Threading is disabled\n");
- } else if (smp_num_siblings > 1) {
+ goto out;
+ }
- if (smp_num_siblings > nr_cpu_ids) {
- printk(KERN_WARNING "CPU: Unsupported number of siblings %d",
- smp_num_siblings);
- smp_num_siblings = 1;
- return;
- }
+ if (smp_num_siblings <= 1)
+ goto out;
+
+ if (smp_num_siblings > nr_cpu_ids) {
+ pr_warning("CPU: Unsupported number of siblings %d",
+ smp_num_siblings);
+ smp_num_siblings = 1;
+ return;
+ }
- index_msb = get_count_order(smp_num_siblings);
- c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, index_msb);
+ index_msb = get_count_order(smp_num_siblings);
+ c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, index_msb);
- smp_num_siblings = smp_num_siblings / c->x86_max_cores;
+ smp_num_siblings = smp_num_siblings / c->x86_max_cores;
- index_msb = get_count_order(smp_num_siblings);
+ index_msb = get_count_order(smp_num_siblings);
- core_bits = get_count_order(c->x86_max_cores);
+ core_bits = get_count_order(c->x86_max_cores);
- c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid, index_msb) &
- ((1 << core_bits) - 1);
- }
+ c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid, index_msb) &
+ ((1 << core_bits) - 1);
out:
if ((c->x86_max_cores * smp_num_siblings) > 1) {
@@ -473,8 +490,8 @@ out:
static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c)
{
char *v = c->x86_vendor_id;
- int i;
static int printed;
+ int i;
for (i = 0; i < X86_VENDOR_NUM; i++) {
if (!cpu_devs[i])
@@ -483,6 +500,7 @@ static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c)
if (!strcmp(v, cpu_devs[i]->c_ident[0]) ||
(cpu_devs[i]->c_ident[1] &&
!strcmp(v, cpu_devs[i]->c_ident[1]))) {
+
this_cpu = cpu_devs[i];
c->x86_vendor = this_cpu->c_x86_vendor;
return;
@@ -491,7 +509,9 @@ static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c)
if (!printed) {
printed++;
- printk(KERN_ERR "CPU: vendor_id '%s' unknown, using generic init.\n", v);
+ printk(KERN_ERR
+ "CPU: vendor_id '%s' unknown, using generic init.\n", v);
+
printk(KERN_ERR "CPU: Your system may be unstable.\n");
}
@@ -511,14 +531,17 @@ void __cpuinit cpu_detect(struct cpuinfo_x86 *c)
/* Intel-defined flags: level 0x00000001 */
if (c->cpuid_level >= 0x00000001) {
u32 junk, tfms, cap0, misc;
+
cpuid(0x00000001, &tfms, &misc, &junk, &cap0);
c->x86 = (tfms >> 8) & 0xf;
c->x86_model = (tfms >> 4) & 0xf;
c->x86_mask = tfms & 0xf;
+
if (c->x86 == 0xf)
c->x86 += (tfms >> 20) & 0xff;
if (c->x86 >= 0x6)
c->x86_model += ((tfms >> 16) & 0xf) << 4;
+
if (cap0 & (1<<19)) {
c->x86_clflush_size = ((misc >> 8) & 0xff) * 8;
c->x86_cache_alignment = c->x86_clflush_size;
@@ -534,6 +557,7 @@ static void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c)
/* Intel-defined flags: level 0x00000001 */
if (c->cpuid_level >= 0x00000001) {
u32 capability, excap;
+
cpuid(0x00000001, &tfms, &ebx, &excap, &capability);
c->x86_capability[0] = capability;
c->x86_capability[4] = excap;
@@ -542,6 +566,7 @@ static void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c)
/* AMD-defined flags: level 0x80000001 */
xlvl = cpuid_eax(0x80000000);
c->extended_cpuid_level = xlvl;
+
if ((xlvl & 0xffff0000) == 0x80000000) {
if (xlvl >= 0x80000001) {
c->x86_capability[1] = cpuid_edx(0x80000001);
@@ -549,13 +574,15 @@ static void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c)
}
}
-#ifdef CONFIG_X86_64
if (c->extended_cpuid_level >= 0x80000008) {
u32 eax = cpuid_eax(0x80000008);
c->x86_virt_bits = (eax >> 8) & 0xff;
c->x86_phys_bits = eax & 0xff;
}
+#ifdef CONFIG_X86_32
+ else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36))
+ c->x86_phys_bits = 36;
#endif
if (c->extended_cpuid_level >= 0x80000007)
@@ -602,8 +629,12 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_X86_64
c->x86_clflush_size = 64;
+ c->x86_phys_bits = 36;
+ c->x86_virt_bits = 48;
#else
c->x86_clflush_size = 32;
+ c->x86_phys_bits = 32;
+ c->x86_virt_bits = 32;
#endif
c->x86_cache_alignment = c->x86_clflush_size;
@@ -634,12 +665,12 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
void __init early_cpu_init(void)
{
- struct cpu_dev **cdev;
+ const struct cpu_dev *const *cdev;
int count = 0;
- printk("KERNEL supported cpus:\n");
+ printk(KERN_INFO "KERNEL supported cpus:\n");
for (cdev = __x86_cpu_dev_start; cdev < __x86_cpu_dev_end; cdev++) {
- struct cpu_dev *cpudev = *cdev;
+ const struct cpu_dev *cpudev = *cdev;
unsigned int j;
if (count >= X86_VENDOR_NUM)
@@ -650,7 +681,7 @@ void __init early_cpu_init(void)
for (j = 0; j < 2; j++) {
if (!cpudev->c_ident[j])
continue;
- printk(" %s %s\n", cpudev->c_vendor,
+ printk(KERN_INFO " %s %s\n", cpudev->c_vendor,
cpudev->c_ident[j]);
}
}
@@ -726,9 +757,13 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
c->x86_coreid_bits = 0;
#ifdef CONFIG_X86_64
c->x86_clflush_size = 64;
+ c->x86_phys_bits = 36;
+ c->x86_virt_bits = 48;
#else
c->cpuid_level = -1; /* CPUID not detected */
c->x86_clflush_size = 32;
+ c->x86_phys_bits = 32;
+ c->x86_virt_bits = 32;
#endif
c->x86_cache_alignment = c->x86_clflush_size;
memset(&c->x86_capability, 0, sizeof c->x86_capability);
@@ -759,8 +794,8 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
squash_the_stupid_serial_number(c);
/*
- * The vendor-specific functions might have changed features. Now
- * we do "generic changes."
+ * The vendor-specific functions might have changed features.
+ * Now we do "generic changes."
*/
/* Filter out anything that depends on CPUID levels we don't have */
@@ -768,7 +803,7 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
/* If the model name is still unset, do table lookup. */
if (!c->x86_model_id[0]) {
- char *p;
+ const char *p;
p = table_lookup_model(c);
if (p)
strcpy(c->x86_model_id, p);
@@ -843,11 +878,11 @@ void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c)
}
struct msr_range {
- unsigned min;
- unsigned max;
+ unsigned min;
+ unsigned max;
};
-static struct msr_range msr_range_array[] __cpuinitdata = {
+static const struct msr_range msr_range_array[] __cpuinitconst = {
{ 0x00000000, 0x00000418},
{ 0xc0000000, 0xc000040b},
{ 0xc0010000, 0xc0010142},
@@ -856,14 +891,15 @@ static struct msr_range msr_range_array[] __cpuinitdata = {
static void __cpuinit print_cpu_msr(void)
{
+ unsigned index_min, index_max;
unsigned index;
u64 val;
int i;
- unsigned index_min, index_max;
for (i = 0; i < ARRAY_SIZE(msr_range_array); i++) {
index_min = msr_range_array[i].min;
index_max = msr_range_array[i].max;
+
for (index = index_min; index < index_max; index++) {
if (rdmsrl_amd_safe(index, &val))
continue;
@@ -873,6 +909,7 @@ static void __cpuinit print_cpu_msr(void)
}
static int show_msr __cpuinitdata;
+
static __init int setup_show_msr(char *arg)
{
int num;
@@ -894,12 +931,14 @@ __setup("noclflush", setup_noclflush);
void __cpuinit print_cpu_info(struct cpuinfo_x86 *c)
{
- char *vendor = NULL;
+ const char *vendor = NULL;
- if (c->x86_vendor < X86_VENDOR_NUM)
+ if (c->x86_vendor < X86_VENDOR_NUM) {
vendor = this_cpu->c_vendor;
- else if (c->cpuid_level >= 0)
- vendor = c->x86_vendor_id;
+ } else {
+ if (c->cpuid_level >= 0)
+ vendor = c->x86_vendor_id;
+ }
if (vendor && !strstr(c->x86_model_id, vendor))
printk(KERN_CONT "%s ", vendor);
@@ -926,10 +965,12 @@ void __cpuinit print_cpu_info(struct cpuinfo_x86 *c)
static __init int setup_disablecpuid(char *arg)
{
int bit;
+
if (get_option(&arg, &bit) && bit < NCAPINTS*32)
setup_clear_cpu_cap(bit);
else
return 0;
+
return 1;
}
__setup("clearcpuid=", setup_disablecpuid);
@@ -939,6 +980,7 @@ struct desc_ptr idt_descr = { 256 * 16 - 1, (unsigned long) idt_table };
DEFINE_PER_CPU_FIRST(union irq_stack_union,
irq_stack_union) __aligned(PAGE_SIZE);
+
DEFINE_PER_CPU(char *, irq_stack_ptr) =
init_per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE - 64;
@@ -948,12 +990,21 @@ EXPORT_PER_CPU_SYMBOL(kernel_stack);
DEFINE_PER_CPU(unsigned int, irq_count) = -1;
+/*
+ * Special IST stacks which the CPU switches to when it calls
+ * an IST-marked descriptor entry. Up to 7 stacks (hardware
+ * limit), all of them are 4K, except the debug stack which
+ * is 8K.
+ */
+static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = {
+ [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STKSZ,
+ [DEBUG_STACK - 1] = DEBUG_STKSZ
+};
+
static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ])
__aligned(PAGE_SIZE);
-extern asmlinkage void ignore_sysret(void);
-
/* May not be marked __init: used by software suspend */
void syscall_init(void)
{
@@ -983,7 +1034,7 @@ unsigned long kernel_eflags;
*/
DEFINE_PER_CPU(struct orig_ist, orig_ist);
-#else /* x86_64 */
+#else /* CONFIG_X86_64 */
#ifdef CONFIG_CC_STACKPROTECTOR
DEFINE_PER_CPU(unsigned long, stack_canary);
@@ -995,9 +1046,26 @@ struct pt_regs * __cpuinit idle_regs(struct pt_regs *regs)
memset(regs, 0, sizeof(struct pt_regs));
regs->fs = __KERNEL_PERCPU;
regs->gs = __KERNEL_STACK_CANARY;
+
return regs;
}
-#endif /* x86_64 */
+#endif /* CONFIG_X86_64 */
+
+/*
+ * Clear all 6 debug registers:
+ */
+static void clear_all_debug_regs(void)
+{
+ int i;
+
+ for (i = 0; i < 8; i++) {
+ /* Ignore db4, db5 */
+ if ((i == 4) || (i == 5))
+ continue;
+
+ set_debugreg(0, i);
+ }
+}
/*
* cpu_init() initializes state that is per-CPU. Some data is already
@@ -1007,15 +1075,20 @@ struct pt_regs * __cpuinit idle_regs(struct pt_regs *regs)
* A lot of state is already set up in PDA init for 64 bit
*/
#ifdef CONFIG_X86_64
+
void __cpuinit cpu_init(void)
{
- int cpu = stack_smp_processor_id();
- struct tss_struct *t = &per_cpu(init_tss, cpu);
- struct orig_ist *orig_ist = &per_cpu(orig_ist, cpu);
- unsigned long v;
+ struct orig_ist *orig_ist;
struct task_struct *me;
+ struct tss_struct *t;
+ unsigned long v;
+ int cpu;
int i;
+ cpu = stack_smp_processor_id();
+ t = &per_cpu(init_tss, cpu);
+ orig_ist = &per_cpu(orig_ist, cpu);
+
#ifdef CONFIG_NUMA
if (cpu != 0 && percpu_read(node_number) == 0 &&
cpu_to_node(cpu) != NUMA_NO_NODE)
@@ -1056,19 +1129,17 @@ void __cpuinit cpu_init(void)
* set up and load the per-CPU TSS
*/
if (!orig_ist->ist[0]) {
- static const unsigned int sizes[N_EXCEPTION_STACKS] = {
- [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STKSZ,
- [DEBUG_STACK - 1] = DEBUG_STKSZ
- };
char *estacks = per_cpu(exception_stacks, cpu);
+
for (v = 0; v < N_EXCEPTION_STACKS; v++) {
- estacks += sizes[v];
+ estacks += exception_stack_sizes[v];
orig_ist->ist[v] = t->x86_tss.ist[v] =
(unsigned long)estacks;
}
}
t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
+
/*
* <= is required because the CPU will access up to
* 8 bits beyond the end of the IO permission bitmap.
@@ -1078,8 +1149,7 @@ void __cpuinit cpu_init(void)
atomic_inc(&init_mm.mm_count);
me->active_mm = &init_mm;
- if (me->mm)
- BUG();
+ BUG_ON(me->mm);
enter_lazy_tlb(&init_mm, me);
load_sp0(t, &current->thread);
@@ -1098,17 +1168,7 @@ void __cpuinit cpu_init(void)
arch_kgdb_ops.correct_hw_break();
else
#endif
- {
- /*
- * Clear all 6 debug registers:
- */
- set_debugreg(0UL, 0);
- set_debugreg(0UL, 1);
- set_debugreg(0UL, 2);
- set_debugreg(0UL, 3);
- set_debugreg(0UL, 6);
- set_debugreg(0UL, 7);
- }
+ clear_all_debug_regs();
fpu_init();
@@ -1129,7 +1189,8 @@ void __cpuinit cpu_init(void)
if (cpumask_test_and_set_cpu(cpu, cpu_initialized_mask)) {
printk(KERN_WARNING "CPU#%d already initialized!\n", cpu);
- for (;;) local_irq_enable();
+ for (;;)
+ local_irq_enable();
}
printk(KERN_INFO "Initializing CPU#%d\n", cpu);
@@ -1145,8 +1206,7 @@ void __cpuinit cpu_init(void)
*/
atomic_inc(&init_mm.mm_count);
curr->active_mm = &init_mm;
- if (curr->mm)
- BUG();
+ BUG_ON(curr->mm);
enter_lazy_tlb(&init_mm, curr);
load_sp0(t, thread);
@@ -1159,13 +1219,7 @@ void __cpuinit cpu_init(void)
__set_tss_desc(cpu, GDT_ENTRY_DOUBLEFAULT_TSS, &doublefault_tss);
#endif
- /* Clear all 6 debug registers: */
- set_debugreg(0, 0);
- set_debugreg(0, 1);
- set_debugreg(0, 2);
- set_debugreg(0, 3);
- set_debugreg(0, 6);
- set_debugreg(0, 7);
+ clear_all_debug_regs();
/*
* Force FPU initialization:
@@ -1185,6 +1239,4 @@ void __cpuinit cpu_init(void)
xsave_init();
}
-
-
#endif
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index de4094a3921..9469ecb5aeb 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -5,15 +5,15 @@
struct cpu_model_info {
int vendor;
int family;
- char *model_names[16];
+ const char *model_names[16];
};
/* attempt to consolidate cpu attributes */
struct cpu_dev {
- char * c_vendor;
+ const char * c_vendor;
/* some have two possibilities for cpuid string */
- char * c_ident[2];
+ const char * c_ident[2];
struct cpu_model_info c_models[4];
@@ -25,11 +25,12 @@ struct cpu_dev {
};
#define cpu_dev_register(cpu_devX) \
- static struct cpu_dev *__cpu_dev_##cpu_devX __used \
+ static const struct cpu_dev *const __cpu_dev_##cpu_devX __used \
__attribute__((__section__(".x86_cpu_dev.init"))) = \
&cpu_devX;
-extern struct cpu_dev *__x86_cpu_dev_start[], *__x86_cpu_dev_end[];
+extern const struct cpu_dev *const __x86_cpu_dev_start[],
+ *const __x86_cpu_dev_end[];
extern void display_cacheinfo(struct cpuinfo_x86 *c);
diff --git a/arch/x86/kernel/cpu/cpu_debug.c b/arch/x86/kernel/cpu/cpu_debug.c
new file mode 100755
index 00000000000..21c0cf8ced1
--- /dev/null
+++ b/arch/x86/kernel/cpu/cpu_debug.c
@@ -0,0 +1,839 @@
+/*
+ * CPU x86 architecture debug code
+ *
+ * Copyright(C) 2009 Jaswinder Singh Rajput
+ *
+ * For licencing details see kernel-base/COPYING
+ */
+
+#include <linux/interrupt.h>
+#include <linux/compiler.h>
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
+#include <linux/kprobes.h>
+#include <linux/uaccess.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/percpu.h>
+#include <linux/signal.h>
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+
+#include <asm/cpu_debug.h>
+#include <asm/paravirt.h>
+#include <asm/system.h>
+#include <asm/traps.h>
+#include <asm/apic.h>
+#include <asm/desc.h>
+
+static DEFINE_PER_CPU(struct cpu_cpuX_base, cpu_arr[CPU_REG_ALL_BIT]);
+static DEFINE_PER_CPU(struct cpu_private *, priv_arr[MAX_CPU_FILES]);
+static DEFINE_PER_CPU(unsigned, cpu_modelflag);
+static DEFINE_PER_CPU(int, cpu_priv_count);
+static DEFINE_PER_CPU(unsigned, cpu_model);
+
+static DEFINE_MUTEX(cpu_debug_lock);
+
+static struct dentry *cpu_debugfs_dir;
+
+static struct cpu_debug_base cpu_base[] = {
+ { "mc", CPU_MC, 0 },
+ { "monitor", CPU_MONITOR, 0 },
+ { "time", CPU_TIME, 0 },
+ { "pmc", CPU_PMC, 1 },
+ { "platform", CPU_PLATFORM, 0 },
+ { "apic", CPU_APIC, 0 },
+ { "poweron", CPU_POWERON, 0 },
+ { "control", CPU_CONTROL, 0 },
+ { "features", CPU_FEATURES, 0 },
+ { "lastbranch", CPU_LBRANCH, 0 },
+ { "bios", CPU_BIOS, 0 },
+ { "freq", CPU_FREQ, 0 },
+ { "mtrr", CPU_MTRR, 0 },
+ { "perf", CPU_PERF, 0 },
+ { "cache", CPU_CACHE, 0 },
+ { "sysenter", CPU_SYSENTER, 0 },
+ { "therm", CPU_THERM, 0 },
+ { "misc", CPU_MISC, 0 },
+ { "debug", CPU_DEBUG, 0 },
+ { "pat", CPU_PAT, 0 },
+ { "vmx", CPU_VMX, 0 },
+ { "call", CPU_CALL, 0 },
+ { "base", CPU_BASE, 0 },
+ { "smm", CPU_SMM, 0 },
+ { "svm", CPU_SVM, 0 },
+ { "osvm", CPU_OSVM, 0 },
+ { "tss", CPU_TSS, 0 },
+ { "cr", CPU_CR, 0 },
+ { "dt", CPU_DT, 0 },
+ { "registers", CPU_REG_ALL, 0 },
+};
+
+static struct cpu_file_base cpu_file[] = {
+ { "index", CPU_REG_ALL, 0 },
+ { "value", CPU_REG_ALL, 1 },
+};
+
+/* Intel Registers Range */
+static struct cpu_debug_range cpu_intel_range[] = {
+ { 0x00000000, 0x00000001, CPU_MC, CPU_INTEL_ALL },
+ { 0x00000006, 0x00000007, CPU_MONITOR, CPU_CX_AT_XE },
+ { 0x00000010, 0x00000010, CPU_TIME, CPU_INTEL_ALL },
+ { 0x00000011, 0x00000013, CPU_PMC, CPU_INTEL_PENTIUM },
+ { 0x00000017, 0x00000017, CPU_PLATFORM, CPU_PX_CX_AT_XE },
+ { 0x0000001B, 0x0000001B, CPU_APIC, CPU_P6_CX_AT_XE },
+
+ { 0x0000002A, 0x0000002A, CPU_POWERON, CPU_PX_CX_AT_XE },
+ { 0x0000002B, 0x0000002B, CPU_POWERON, CPU_INTEL_XEON },
+ { 0x0000002C, 0x0000002C, CPU_FREQ, CPU_INTEL_XEON },
+ { 0x0000003A, 0x0000003A, CPU_CONTROL, CPU_CX_AT_XE },
+
+ { 0x00000040, 0x00000043, CPU_LBRANCH, CPU_PM_CX_AT_XE },
+ { 0x00000044, 0x00000047, CPU_LBRANCH, CPU_PM_CO_AT },
+ { 0x00000060, 0x00000063, CPU_LBRANCH, CPU_C2_AT },
+ { 0x00000064, 0x00000067, CPU_LBRANCH, CPU_INTEL_ATOM },
+
+ { 0x00000079, 0x00000079, CPU_BIOS, CPU_P6_CX_AT_XE },
+ { 0x00000088, 0x0000008A, CPU_CACHE, CPU_INTEL_P6 },
+ { 0x0000008B, 0x0000008B, CPU_BIOS, CPU_P6_CX_AT_XE },
+ { 0x0000009B, 0x0000009B, CPU_MONITOR, CPU_INTEL_XEON },
+
+ { 0x000000C1, 0x000000C2, CPU_PMC, CPU_P6_CX_AT },
+ { 0x000000CD, 0x000000CD, CPU_FREQ, CPU_CX_AT },
+ { 0x000000E7, 0x000000E8, CPU_PERF, CPU_CX_AT },
+ { 0x000000FE, 0x000000FE, CPU_MTRR, CPU_P6_CX_XE },
+
+ { 0x00000116, 0x00000116, CPU_CACHE, CPU_INTEL_P6 },
+ { 0x00000118, 0x00000118, CPU_CACHE, CPU_INTEL_P6 },
+ { 0x00000119, 0x00000119, CPU_CACHE, CPU_INTEL_PX },
+ { 0x0000011A, 0x0000011B, CPU_CACHE, CPU_INTEL_P6 },
+ { 0x0000011E, 0x0000011E, CPU_CACHE, CPU_PX_CX_AT },
+
+ { 0x00000174, 0x00000176, CPU_SYSENTER, CPU_P6_CX_AT_XE },
+ { 0x00000179, 0x0000017A, CPU_MC, CPU_PX_CX_AT_XE },
+ { 0x0000017B, 0x0000017B, CPU_MC, CPU_P6_XE },
+ { 0x00000186, 0x00000187, CPU_PMC, CPU_P6_CX_AT },
+ { 0x00000198, 0x00000199, CPU_PERF, CPU_PM_CX_AT_XE },
+ { 0x0000019A, 0x0000019A, CPU_TIME, CPU_PM_CX_AT_XE },
+ { 0x0000019B, 0x0000019D, CPU_THERM, CPU_PM_CX_AT_XE },
+ { 0x000001A0, 0x000001A0, CPU_MISC, CPU_PM_CX_AT_XE },
+
+ { 0x000001C9, 0x000001C9, CPU_LBRANCH, CPU_PM_CX_AT },
+ { 0x000001D7, 0x000001D8, CPU_LBRANCH, CPU_INTEL_XEON },
+ { 0x000001D9, 0x000001D9, CPU_DEBUG, CPU_CX_AT_XE },
+ { 0x000001DA, 0x000001DA, CPU_LBRANCH, CPU_INTEL_XEON },
+ { 0x000001DB, 0x000001DB, CPU_LBRANCH, CPU_P6_XE },
+ { 0x000001DC, 0x000001DC, CPU_LBRANCH, CPU_INTEL_P6 },
+ { 0x000001DD, 0x000001DE, CPU_LBRANCH, CPU_PX_CX_AT_XE },
+ { 0x000001E0, 0x000001E0, CPU_LBRANCH, CPU_INTEL_P6 },
+
+ { 0x00000200, 0x0000020F, CPU_MTRR, CPU_P6_CX_XE },
+ { 0x00000250, 0x00000250, CPU_MTRR, CPU_P6_CX_XE },
+ { 0x00000258, 0x00000259, CPU_MTRR, CPU_P6_CX_XE },
+ { 0x00000268, 0x0000026F, CPU_MTRR, CPU_P6_CX_XE },
+ { 0x00000277, 0x00000277, CPU_PAT, CPU_C2_AT_XE },
+ { 0x000002FF, 0x000002FF, CPU_MTRR, CPU_P6_CX_XE },
+
+ { 0x00000300, 0x00000308, CPU_PMC, CPU_INTEL_XEON },
+ { 0x00000309, 0x0000030B, CPU_PMC, CPU_C2_AT_XE },
+ { 0x0000030C, 0x00000311, CPU_PMC, CPU_INTEL_XEON },
+ { 0x00000345, 0x00000345, CPU_PMC, CPU_C2_AT },
+ { 0x00000360, 0x00000371, CPU_PMC, CPU_INTEL_XEON },
+ { 0x0000038D, 0x00000390, CPU_PMC, CPU_C2_AT },
+ { 0x000003A0, 0x000003BE, CPU_PMC, CPU_INTEL_XEON },
+ { 0x000003C0, 0x000003CD, CPU_PMC, CPU_INTEL_XEON },
+ { 0x000003E0, 0x000003E1, CPU_PMC, CPU_INTEL_XEON },
+ { 0x000003F0, 0x000003F0, CPU_PMC, CPU_INTEL_XEON },
+ { 0x000003F1, 0x000003F1, CPU_PMC, CPU_C2_AT_XE },
+ { 0x000003F2, 0x000003F2, CPU_PMC, CPU_INTEL_XEON },
+
+ { 0x00000400, 0x00000402, CPU_MC, CPU_PM_CX_AT_XE },
+ { 0x00000403, 0x00000403, CPU_MC, CPU_INTEL_XEON },
+ { 0x00000404, 0x00000406, CPU_MC, CPU_PM_CX_AT_XE },
+ { 0x00000407, 0x00000407, CPU_MC, CPU_INTEL_XEON },
+ { 0x00000408, 0x0000040A, CPU_MC, CPU_PM_CX_AT_XE },
+ { 0x0000040B, 0x0000040B, CPU_MC, CPU_INTEL_XEON },
+ { 0x0000040C, 0x0000040E, CPU_MC, CPU_PM_CX_XE },
+ { 0x0000040F, 0x0000040F, CPU_MC, CPU_INTEL_XEON },
+ { 0x00000410, 0x00000412, CPU_MC, CPU_PM_CX_AT_XE },
+ { 0x00000413, 0x00000417, CPU_MC, CPU_CX_AT_XE },
+ { 0x00000480, 0x0000048B, CPU_VMX, CPU_CX_AT_XE },
+
+ { 0x00000600, 0x00000600, CPU_DEBUG, CPU_PM_CX_AT_XE },
+ { 0x00000680, 0x0000068F, CPU_LBRANCH, CPU_INTEL_XEON },
+ { 0x000006C0, 0x000006CF, CPU_LBRANCH, CPU_INTEL_XEON },
+
+ { 0x000107CC, 0x000107D3, CPU_PMC, CPU_INTEL_XEON_MP },
+
+ { 0xC0000080, 0xC0000080, CPU_FEATURES, CPU_INTEL_XEON },
+ { 0xC0000081, 0xC0000082, CPU_CALL, CPU_INTEL_XEON },
+ { 0xC0000084, 0xC0000084, CPU_CALL, CPU_INTEL_XEON },
+ { 0xC0000100, 0xC0000102, CPU_BASE, CPU_INTEL_XEON },
+};
+
+/* AMD Registers Range */
+static struct cpu_debug_range cpu_amd_range[] = {
+ { 0x00000010, 0x00000010, CPU_TIME, CPU_ALL, },
+ { 0x0000001B, 0x0000001B, CPU_APIC, CPU_ALL, },
+ { 0x000000FE, 0x000000FE, CPU_MTRR, CPU_ALL, },
+
+ { 0x00000174, 0x00000176, CPU_SYSENTER, CPU_ALL, },
+ { 0x00000179, 0x0000017A, CPU_MC, CPU_ALL, },
+ { 0x0000017B, 0x0000017B, CPU_MC, CPU_ALL, },
+ { 0x000001D9, 0x000001D9, CPU_DEBUG, CPU_ALL, },
+ { 0x000001DB, 0x000001DE, CPU_LBRANCH, CPU_ALL, },
+
+ { 0x00000200, 0x0000020F, CPU_MTRR, CPU_ALL, },
+ { 0x00000250, 0x00000250, CPU_MTRR, CPU_ALL, },
+ { 0x00000258, 0x00000259, CPU_MTRR, CPU_ALL, },
+ { 0x00000268, 0x0000026F, CPU_MTRR, CPU_ALL, },
+ { 0x00000277, 0x00000277, CPU_PAT, CPU_ALL, },
+ { 0x000002FF, 0x000002FF, CPU_MTRR, CPU_ALL, },
+
+ { 0x00000400, 0x00000417, CPU_MC, CPU_ALL, },
+
+ { 0xC0000080, 0xC0000080, CPU_FEATURES, CPU_ALL, },
+ { 0xC0000081, 0xC0000084, CPU_CALL, CPU_ALL, },
+ { 0xC0000100, 0xC0000102, CPU_BASE, CPU_ALL, },
+ { 0xC0000103, 0xC0000103, CPU_TIME, CPU_ALL, },
+
+ { 0xC0000408, 0xC000040A, CPU_MC, CPU_ALL, },
+
+ { 0xc0010000, 0xc0010007, CPU_PMC, CPU_ALL, },
+ { 0xc0010010, 0xc0010010, CPU_MTRR, CPU_ALL, },
+ { 0xc0010016, 0xc001001A, CPU_MTRR, CPU_ALL, },
+ { 0xc001001D, 0xc001001D, CPU_MTRR, CPU_ALL, },
+ { 0xc0010030, 0xc0010035, CPU_BIOS, CPU_ALL, },
+ { 0xc0010056, 0xc0010056, CPU_SMM, CPU_ALL, },
+ { 0xc0010061, 0xc0010063, CPU_SMM, CPU_ALL, },
+ { 0xc0010074, 0xc0010074, CPU_MC, CPU_ALL, },
+ { 0xc0010111, 0xc0010113, CPU_SMM, CPU_ALL, },
+ { 0xc0010114, 0xc0010118, CPU_SVM, CPU_ALL, },
+ { 0xc0010119, 0xc001011A, CPU_SMM, CPU_ALL, },
+ { 0xc0010140, 0xc0010141, CPU_OSVM, CPU_ALL, },
+ { 0xc0010156, 0xc0010156, CPU_SMM, CPU_ALL, },
+};
+
+
+static int get_cpu_modelflag(unsigned cpu)
+{
+ int flag;
+
+ switch (per_cpu(cpu_model, cpu)) {
+ /* Intel */
+ case 0x0501:
+ case 0x0502:
+ case 0x0504:
+ flag = CPU_INTEL_PENTIUM;
+ break;
+ case 0x0601:
+ case 0x0603:
+ case 0x0605:
+ case 0x0607:
+ case 0x0608:
+ case 0x060A:
+ case 0x060B:
+ flag = CPU_INTEL_P6;
+ break;
+ case 0x0609:
+ case 0x060D:
+ flag = CPU_INTEL_PENTIUM_M;
+ break;
+ case 0x060E:
+ flag = CPU_INTEL_CORE;
+ break;
+ case 0x060F:
+ case 0x0617:
+ flag = CPU_INTEL_CORE2;
+ break;
+ case 0x061C:
+ flag = CPU_INTEL_ATOM;
+ break;
+ case 0x0F00:
+ case 0x0F01:
+ case 0x0F02:
+ case 0x0F03:
+ case 0x0F04:
+ flag = CPU_INTEL_XEON_P4;
+ break;
+ case 0x0F06:
+ flag = CPU_INTEL_XEON_MP;
+ break;
+ default:
+ flag = CPU_NONE;
+ break;
+ }
+
+ return flag;
+}
+
+static int get_cpu_range_count(unsigned cpu)
+{
+ int index;
+
+ switch (per_cpu(cpu_model, cpu) >> 16) {
+ case X86_VENDOR_INTEL:
+ index = ARRAY_SIZE(cpu_intel_range);
+ break;
+ case X86_VENDOR_AMD:
+ index = ARRAY_SIZE(cpu_amd_range);
+ break;
+ default:
+ index = 0;
+ break;
+ }
+
+ return index;
+}
+
+static int is_typeflag_valid(unsigned cpu, unsigned flag)
+{
+ unsigned vendor, modelflag;
+ int i, index;
+
+ /* Standard Registers should be always valid */
+ if (flag >= CPU_TSS)
+ return 1;
+
+ modelflag = per_cpu(cpu_modelflag, cpu);
+ vendor = per_cpu(cpu_model, cpu) >> 16;
+ index = get_cpu_range_count(cpu);
+
+ for (i = 0; i < index; i++) {
+ switch (vendor) {
+ case X86_VENDOR_INTEL:
+ if ((cpu_intel_range[i].model & modelflag) &&
+ (cpu_intel_range[i].flag & flag))
+ return 1;
+ break;
+ case X86_VENDOR_AMD:
+ if (cpu_amd_range[i].flag & flag)
+ return 1;
+ break;
+ }
+ }
+
+ /* Invalid */
+ return 0;
+}
+
+static unsigned get_cpu_range(unsigned cpu, unsigned *min, unsigned *max,
+ int index, unsigned flag)
+{
+ unsigned modelflag;
+
+ modelflag = per_cpu(cpu_modelflag, cpu);
+ *max = 0;
+ switch (per_cpu(cpu_model, cpu) >> 16) {
+ case X86_VENDOR_INTEL:
+ if ((cpu_intel_range[index].model & modelflag) &&
+ (cpu_intel_range[index].flag & flag)) {
+ *min = cpu_intel_range[index].min;
+ *max = cpu_intel_range[index].max;
+ }
+ break;
+ case X86_VENDOR_AMD:
+ if (cpu_amd_range[index].flag & flag) {
+ *min = cpu_amd_range[index].min;
+ *max = cpu_amd_range[index].max;
+ }
+ break;
+ }
+
+ return *max;
+}
+
+/* This function can also be called with seq = NULL for printk */
+static void print_cpu_data(struct seq_file *seq, unsigned type,
+ u32 low, u32 high)
+{
+ struct cpu_private *priv;
+ u64 val = high;
+
+ if (seq) {
+ priv = seq->private;
+ if (priv->file) {
+ val = (val << 32) | low;
+ seq_printf(seq, "0x%llx\n", val);
+ } else
+ seq_printf(seq, " %08x: %08x_%08x\n",
+ type, high, low);
+ } else
+ printk(KERN_INFO " %08x: %08x_%08x\n", type, high, low);
+}
+
+/* This function can also be called with seq = NULL for printk */
+static void print_msr(struct seq_file *seq, unsigned cpu, unsigned flag)
+{
+ unsigned msr, msr_min, msr_max;
+ struct cpu_private *priv;
+ u32 low, high;
+ int i, range;
+
+ if (seq) {
+ priv = seq->private;
+ if (priv->file) {
+ if (!rdmsr_safe_on_cpu(priv->cpu, priv->reg,
+ &low, &high))
+ print_cpu_data(seq, priv->reg, low, high);
+ return;
+ }
+ }
+
+ range = get_cpu_range_count(cpu);
+
+ for (i = 0; i < range; i++) {
+ if (!get_cpu_range(cpu, &msr_min, &msr_max, i, flag))
+ continue;
+
+ for (msr = msr_min; msr <= msr_max; msr++) {
+ if (rdmsr_safe_on_cpu(cpu, msr, &low, &high))
+ continue;
+ print_cpu_data(seq, msr, low, high);
+ }
+ }
+}
+
+static void print_tss(void *arg)
+{
+ struct pt_regs *regs = task_pt_regs(current);
+ struct seq_file *seq = arg;
+ unsigned int seg;
+
+ seq_printf(seq, " RAX\t: %016lx\n", regs->ax);
+ seq_printf(seq, " RBX\t: %016lx\n", regs->bx);
+ seq_printf(seq, " RCX\t: %016lx\n", regs->cx);
+ seq_printf(seq, " RDX\t: %016lx\n", regs->dx);
+
+ seq_printf(seq, " RSI\t: %016lx\n", regs->si);
+ seq_printf(seq, " RDI\t: %016lx\n", regs->di);
+ seq_printf(seq, " RBP\t: %016lx\n", regs->bp);
+ seq_printf(seq, " ESP\t: %016lx\n", regs->sp);
+
+#ifdef CONFIG_X86_64
+ seq_printf(seq, " R08\t: %016lx\n", regs->r8);
+ seq_printf(seq, " R09\t: %016lx\n", regs->r9);
+ seq_printf(seq, " R10\t: %016lx\n", regs->r10);
+ seq_printf(seq, " R11\t: %016lx\n", regs->r11);
+ seq_printf(seq, " R12\t: %016lx\n", regs->r12);
+ seq_printf(seq, " R13\t: %016lx\n", regs->r13);
+ seq_printf(seq, " R14\t: %016lx\n", regs->r14);
+ seq_printf(seq, " R15\t: %016lx\n", regs->r15);
+#endif
+
+ asm("movl %%cs,%0" : "=r" (seg));
+ seq_printf(seq, " CS\t: %04x\n", seg);
+ asm("movl %%ds,%0" : "=r" (seg));
+ seq_printf(seq, " DS\t: %04x\n", seg);
+ seq_printf(seq, " SS\t: %04lx\n", regs->ss & 0xffff);
+ asm("movl %%es,%0" : "=r" (seg));
+ seq_printf(seq, " ES\t: %04x\n", seg);
+ asm("movl %%fs,%0" : "=r" (seg));
+ seq_printf(seq, " FS\t: %04x\n", seg);
+ asm("movl %%gs,%0" : "=r" (seg));
+ seq_printf(seq, " GS\t: %04x\n", seg);
+
+ seq_printf(seq, " EFLAGS\t: %016lx\n", regs->flags);
+
+ seq_printf(seq, " EIP\t: %016lx\n", regs->ip);
+}
+
+static void print_cr(void *arg)
+{
+ struct seq_file *seq = arg;
+
+ seq_printf(seq, " cr0\t: %016lx\n", read_cr0());
+ seq_printf(seq, " cr2\t: %016lx\n", read_cr2());
+ seq_printf(seq, " cr3\t: %016lx\n", read_cr3());
+ seq_printf(seq, " cr4\t: %016lx\n", read_cr4_safe());
+#ifdef CONFIG_X86_64
+ seq_printf(seq, " cr8\t: %016lx\n", read_cr8());
+#endif
+}
+
+static void print_desc_ptr(char *str, struct seq_file *seq, struct desc_ptr dt)
+{
+ seq_printf(seq, " %s\t: %016llx\n", str, (u64)(dt.address | dt.size));
+}
+
+static void print_dt(void *seq)
+{
+ struct desc_ptr dt;
+ unsigned long ldt;
+
+ /* IDT */
+ store_idt((struct desc_ptr *)&dt);
+ print_desc_ptr("IDT", seq, dt);
+
+ /* GDT */
+ store_gdt((struct desc_ptr *)&dt);
+ print_desc_ptr("GDT", seq, dt);
+
+ /* LDT */
+ store_ldt(ldt);
+ seq_printf(seq, " LDT\t: %016lx\n", ldt);
+
+ /* TR */
+ store_tr(ldt);
+ seq_printf(seq, " TR\t: %016lx\n", ldt);
+}
+
+static void print_dr(void *arg)
+{
+ struct seq_file *seq = arg;
+ unsigned long dr;
+ int i;
+
+ for (i = 0; i < 8; i++) {
+ /* Ignore db4, db5 */
+ if ((i == 4) || (i == 5))
+ continue;
+ get_debugreg(dr, i);
+ seq_printf(seq, " dr%d\t: %016lx\n", i, dr);
+ }
+
+ seq_printf(seq, "\n MSR\t:\n");
+}
+
+static void print_apic(void *arg)
+{
+ struct seq_file *seq = arg;
+
+#ifdef CONFIG_X86_LOCAL_APIC
+ seq_printf(seq, " LAPIC\t:\n");
+ seq_printf(seq, " ID\t\t: %08x\n", apic_read(APIC_ID) >> 24);
+ seq_printf(seq, " LVR\t\t: %08x\n", apic_read(APIC_LVR));
+ seq_printf(seq, " TASKPRI\t: %08x\n", apic_read(APIC_TASKPRI));
+ seq_printf(seq, " ARBPRI\t\t: %08x\n", apic_read(APIC_ARBPRI));
+ seq_printf(seq, " PROCPRI\t: %08x\n", apic_read(APIC_PROCPRI));
+ seq_printf(seq, " LDR\t\t: %08x\n", apic_read(APIC_LDR));
+ seq_printf(seq, " DFR\t\t: %08x\n", apic_read(APIC_DFR));
+ seq_printf(seq, " SPIV\t\t: %08x\n", apic_read(APIC_SPIV));
+ seq_printf(seq, " ISR\t\t: %08x\n", apic_read(APIC_ISR));
+ seq_printf(seq, " ESR\t\t: %08x\n", apic_read(APIC_ESR));
+ seq_printf(seq, " ICR\t\t: %08x\n", apic_read(APIC_ICR));
+ seq_printf(seq, " ICR2\t\t: %08x\n", apic_read(APIC_ICR2));
+ seq_printf(seq, " LVTT\t\t: %08x\n", apic_read(APIC_LVTT));
+ seq_printf(seq, " LVTTHMR\t: %08x\n", apic_read(APIC_LVTTHMR));
+ seq_printf(seq, " LVTPC\t\t: %08x\n", apic_read(APIC_LVTPC));
+ seq_printf(seq, " LVT0\t\t: %08x\n", apic_read(APIC_LVT0));
+ seq_printf(seq, " LVT1\t\t: %08x\n", apic_read(APIC_LVT1));
+ seq_printf(seq, " LVTERR\t\t: %08x\n", apic_read(APIC_LVTERR));
+ seq_printf(seq, " TMICT\t\t: %08x\n", apic_read(APIC_TMICT));
+ seq_printf(seq, " TMCCT\t\t: %08x\n", apic_read(APIC_TMCCT));
+ seq_printf(seq, " TDCR\t\t: %08x\n", apic_read(APIC_TDCR));
+#endif /* CONFIG_X86_LOCAL_APIC */
+
+ seq_printf(seq, "\n MSR\t:\n");
+}
+
+static int cpu_seq_show(struct seq_file *seq, void *v)
+{
+ struct cpu_private *priv = seq->private;
+
+ if (priv == NULL)
+ return -EINVAL;
+
+ switch (cpu_base[priv->type].flag) {
+ case CPU_TSS:
+ smp_call_function_single(priv->cpu, print_tss, seq, 1);
+ break;
+ case CPU_CR:
+ smp_call_function_single(priv->cpu, print_cr, seq, 1);
+ break;
+ case CPU_DT:
+ smp_call_function_single(priv->cpu, print_dt, seq, 1);
+ break;
+ case CPU_DEBUG:
+ if (priv->file == CPU_INDEX_BIT)
+ smp_call_function_single(priv->cpu, print_dr, seq, 1);
+ print_msr(seq, priv->cpu, cpu_base[priv->type].flag);
+ break;
+ case CPU_APIC:
+ if (priv->file == CPU_INDEX_BIT)
+ smp_call_function_single(priv->cpu, print_apic, seq, 1);
+ print_msr(seq, priv->cpu, cpu_base[priv->type].flag);
+ break;
+
+ default:
+ print_msr(seq, priv->cpu, cpu_base[priv->type].flag);
+ break;
+ }
+ seq_printf(seq, "\n");
+
+ return 0;
+}
+
+static void *cpu_seq_start(struct seq_file *seq, loff_t *pos)
+{
+ if (*pos == 0) /* One time is enough ;-) */
+ return seq;
+
+ return NULL;
+}
+
+static void *cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+ (*pos)++;
+
+ return cpu_seq_start(seq, pos);
+}
+
+static void cpu_seq_stop(struct seq_file *seq, void *v)
+{
+}
+
+static const struct seq_operations cpu_seq_ops = {
+ .start = cpu_seq_start,
+ .next = cpu_seq_next,
+ .stop = cpu_seq_stop,
+ .show = cpu_seq_show,
+};
+
+static int cpu_seq_open(struct inode *inode, struct file *file)
+{
+ struct cpu_private *priv = inode->i_private;
+ struct seq_file *seq;
+ int err;
+
+ err = seq_open(file, &cpu_seq_ops);
+ if (!err) {
+ seq = file->private_data;
+ seq->private = priv;
+ }
+
+ return err;
+}
+
+static int write_msr(struct cpu_private *priv, u64 val)
+{
+ u32 low, high;
+
+ high = (val >> 32) & 0xffffffff;
+ low = val & 0xffffffff;
+
+ if (!wrmsr_safe_on_cpu(priv->cpu, priv->reg, low, high))
+ return 0;
+
+ return -EPERM;
+}
+
+static int write_cpu_register(struct cpu_private *priv, const char *buf)
+{
+ int ret = -EPERM;
+ u64 val;
+
+ ret = strict_strtoull(buf, 0, &val);
+ if (ret < 0)
+ return ret;
+
+ /* Supporting only MSRs */
+ if (priv->type < CPU_TSS_BIT)
+ return write_msr(priv, val);
+
+ return ret;
+}
+
+static ssize_t cpu_write(struct file *file, const char __user *ubuf,
+ size_t count, loff_t *off)
+{
+ struct seq_file *seq = file->private_data;
+ struct cpu_private *priv = seq->private;
+ char buf[19];
+
+ if ((priv == NULL) || (count >= sizeof(buf)))
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, count))
+ return -EFAULT;
+
+ buf[count] = 0;
+
+ if ((cpu_base[priv->type].write) && (cpu_file[priv->file].write))
+ if (!write_cpu_register(priv, buf))
+ return count;
+
+ return -EACCES;
+}
+
+static const struct file_operations cpu_fops = {
+ .owner = THIS_MODULE,
+ .open = cpu_seq_open,
+ .read = seq_read,
+ .write = cpu_write,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
+static int cpu_create_file(unsigned cpu, unsigned type, unsigned reg,
+ unsigned file, struct dentry *dentry)
+{
+ struct cpu_private *priv = NULL;
+
+ /* Already intialized */
+ if (file == CPU_INDEX_BIT)
+ if (per_cpu(cpu_arr[type].init, cpu))
+ return 0;
+
+ priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+ if (priv == NULL)
+ return -ENOMEM;
+
+ priv->cpu = cpu;
+ priv->type = type;
+ priv->reg = reg;
+ priv->file = file;
+ mutex_lock(&cpu_debug_lock);
+ per_cpu(priv_arr[type], cpu) = priv;
+ per_cpu(cpu_priv_count, cpu)++;
+ mutex_unlock(&cpu_debug_lock);
+
+ if (file)
+ debugfs_create_file(cpu_file[file].name, S_IRUGO,
+ dentry, (void *)priv, &cpu_fops);
+ else {
+ debugfs_create_file(cpu_base[type].name, S_IRUGO,
+ per_cpu(cpu_arr[type].dentry, cpu),
+ (void *)priv, &cpu_fops);
+ mutex_lock(&cpu_debug_lock);
+ per_cpu(cpu_arr[type].init, cpu) = 1;
+ mutex_unlock(&cpu_debug_lock);
+ }
+
+ return 0;
+}
+
+static int cpu_init_regfiles(unsigned cpu, unsigned int type, unsigned reg,
+ struct dentry *dentry)
+{
+ unsigned file;
+ int err = 0;
+
+ for (file = 0; file < ARRAY_SIZE(cpu_file); file++) {
+ err = cpu_create_file(cpu, type, reg, file, dentry);
+ if (err)
+ return err;
+ }
+
+ return err;
+}
+
+static int cpu_init_msr(unsigned cpu, unsigned type, struct dentry *dentry)
+{
+ struct dentry *cpu_dentry = NULL;
+ unsigned reg, reg_min, reg_max;
+ int i, range, err = 0;
+ char reg_dir[12];
+ u32 low, high;
+
+ range = get_cpu_range_count(cpu);
+
+ for (i = 0; i < range; i++) {
+ if (!get_cpu_range(cpu, &reg_min, &reg_max, i,
+ cpu_base[type].flag))
+ continue;
+
+ for (reg = reg_min; reg <= reg_max; reg++) {
+ if (rdmsr_safe_on_cpu(cpu, reg, &low, &high))
+ continue;
+
+ sprintf(reg_dir, "0x%x", reg);
+ cpu_dentry = debugfs_create_dir(reg_dir, dentry);
+ err = cpu_init_regfiles(cpu, type, reg, cpu_dentry);
+ if (err)
+ return err;
+ }
+ }
+
+ return err;
+}
+
+static int cpu_init_allreg(unsigned cpu, struct dentry *dentry)
+{
+ struct dentry *cpu_dentry = NULL;
+ unsigned type;
+ int err = 0;
+
+ for (type = 0; type < ARRAY_SIZE(cpu_base) - 1; type++) {
+ if (!is_typeflag_valid(cpu, cpu_base[type].flag))
+ continue;
+ cpu_dentry = debugfs_create_dir(cpu_base[type].name, dentry);
+ per_cpu(cpu_arr[type].dentry, cpu) = cpu_dentry;
+
+ if (type < CPU_TSS_BIT)
+ err = cpu_init_msr(cpu, type, cpu_dentry);
+ else
+ err = cpu_create_file(cpu, type, 0, CPU_INDEX_BIT,
+ cpu_dentry);
+ if (err)
+ return err;
+ }
+
+ return err;
+}
+
+static int cpu_init_cpu(void)
+{
+ struct dentry *cpu_dentry = NULL;
+ struct cpuinfo_x86 *cpui;
+ char cpu_dir[12];
+ unsigned cpu;
+ int err = 0;
+
+ for (cpu = 0; cpu < nr_cpu_ids; cpu++) {
+ cpui = &cpu_data(cpu);
+ if (!cpu_has(cpui, X86_FEATURE_MSR))
+ continue;
+ per_cpu(cpu_model, cpu) = ((cpui->x86_vendor << 16) |
+ (cpui->x86 << 8) |
+ (cpui->x86_model));
+ per_cpu(cpu_modelflag, cpu) = get_cpu_modelflag(cpu);
+
+ sprintf(cpu_dir, "cpu%d", cpu);
+ cpu_dentry = debugfs_create_dir(cpu_dir, cpu_debugfs_dir);
+ err = cpu_init_allreg(cpu, cpu_dentry);
+
+ pr_info("cpu%d(%d) debug files %d\n",
+ cpu, nr_cpu_ids, per_cpu(cpu_priv_count, cpu));
+ if (per_cpu(cpu_priv_count, cpu) > MAX_CPU_FILES) {
+ pr_err("Register files count %d exceeds limit %d\n",
+ per_cpu(cpu_priv_count, cpu), MAX_CPU_FILES);
+ per_cpu(cpu_priv_count, cpu) = MAX_CPU_FILES;
+ err = -ENFILE;
+ }
+ if (err)
+ return err;
+ }
+
+ return err;
+}
+
+static int __init cpu_debug_init(void)
+{
+ cpu_debugfs_dir = debugfs_create_dir("cpu", arch_debugfs_dir);
+
+ return cpu_init_cpu();
+}
+
+static void __exit cpu_debug_exit(void)
+{
+ int i, cpu;
+
+ if (cpu_debugfs_dir)
+ debugfs_remove_recursive(cpu_debugfs_dir);
+
+ for (cpu = 0; cpu < nr_cpu_ids; cpu++)
+ for (i = 0; i < per_cpu(cpu_priv_count, cpu); i++)
+ kfree(per_cpu(priv_arr[i], cpu));
+}
+
+module_init(cpu_debug_init);
+module_exit(cpu_debug_exit);
+
+MODULE_AUTHOR("Jaswinder Singh Rajput");
+MODULE_DESCRIPTION("CPU Debug module");
+MODULE_LICENSE("GPL");
diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
index b585e04cbc9..3178c3acd97 100644
--- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
+++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
@@ -277,7 +277,6 @@ static struct cpufreq_driver p4clockmod_driver = {
.name = "p4-clockmod",
.owner = THIS_MODULE,
.attr = p4clockmod_attr,
- .hide_interface = 1,
};
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index ffd0f5ed071..593171e967e 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -61,23 +61,23 @@ static void __cpuinit do_cyrix_devid(unsigned char *dir0, unsigned char *dir1)
*/
static unsigned char Cx86_dir0_msb __cpuinitdata = 0;
-static char Cx86_model[][9] __cpuinitdata = {
+static const char __cpuinitconst Cx86_model[][9] = {
"Cx486", "Cx486", "5x86 ", "6x86", "MediaGX ", "6x86MX ",
"M II ", "Unknown"
};
-static char Cx486_name[][5] __cpuinitdata = {
+static const char __cpuinitconst Cx486_name[][5] = {
"SLC", "DLC", "SLC2", "DLC2", "SRx", "DRx",
"SRx2", "DRx2"
};
-static char Cx486S_name[][4] __cpuinitdata = {
+static const char __cpuinitconst Cx486S_name[][4] = {
"S", "S2", "Se", "S2e"
};
-static char Cx486D_name[][4] __cpuinitdata = {
+static const char __cpuinitconst Cx486D_name[][4] = {
"DX", "DX2", "?", "?", "?", "DX4"
};
static char Cx86_cb[] __cpuinitdata = "?.5x Core/Bus Clock";
-static char cyrix_model_mult1[] __cpuinitdata = "12??43";
-static char cyrix_model_mult2[] __cpuinitdata = "12233445";
+static const char __cpuinitconst cyrix_model_mult1[] = "12??43";
+static const char __cpuinitconst cyrix_model_mult2[] = "12233445";
/*
* Reset the slow-loop (SLOP) bit on the 686(L) which is set by some old
@@ -435,7 +435,7 @@ static void __cpuinit cyrix_identify(struct cpuinfo_x86 *c)
}
}
-static struct cpu_dev cyrix_cpu_dev __cpuinitdata = {
+static const struct cpu_dev __cpuinitconst cyrix_cpu_dev = {
.c_vendor = "Cyrix",
.c_ident = { "CyrixInstead" },
.c_early_init = early_init_cyrix,
@@ -446,7 +446,7 @@ static struct cpu_dev cyrix_cpu_dev __cpuinitdata = {
cpu_dev_register(cyrix_cpu_dev);
-static struct cpu_dev nsc_cpu_dev __cpuinitdata = {
+static const struct cpu_dev __cpuinitconst nsc_cpu_dev = {
.c_vendor = "NSC",
.c_ident = { "Geode by NSC" },
.c_init = init_nsc,
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 191117f1ad5..b09d4eb52bb 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -54,6 +54,11 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
c->x86_cache_alignment = 128;
#endif
+ /* CPUID workaround for 0F33/0F34 CPU */
+ if (c->x86 == 0xF && c->x86_model == 0x3
+ && (c->x86_mask == 0x3 || c->x86_mask == 0x4))
+ c->x86_phys_bits = 36;
+
/*
* c->x86_power is 8000_0007 edx. Bit 8 is TSC runs at constant rate
* with P/T states and does not stop in deep C-states
@@ -410,7 +415,7 @@ static unsigned int __cpuinit intel_size_cache(struct cpuinfo_x86 *c, unsigned i
}
#endif
-static struct cpu_dev intel_cpu_dev __cpuinitdata = {
+static const struct cpu_dev __cpuinitconst intel_cpu_dev = {
.c_vendor = "Intel",
.c_ident = { "GenuineIntel" },
#ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 7293508d8f5..c471eb1a389 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -32,7 +32,7 @@ struct _cache_table
};
/* all the cache descriptor types we care about (no TLB or trace cache entries) */
-static struct _cache_table cache_table[] __cpuinitdata =
+static const struct _cache_table __cpuinitconst cache_table[] =
{
{ 0x06, LVL_1_INST, 8 }, /* 4-way set assoc, 32 byte line size */
{ 0x08, LVL_1_INST, 16 }, /* 4-way set assoc, 32 byte line size */
@@ -206,15 +206,15 @@ union l3_cache {
unsigned val;
};
-static unsigned short assocs[] __cpuinitdata = {
+static const unsigned short __cpuinitconst assocs[] = {
[1] = 1, [2] = 2, [4] = 4, [6] = 8,
[8] = 16, [0xa] = 32, [0xb] = 48,
[0xc] = 64,
[0xf] = 0xffff // ??
};
-static unsigned char levels[] __cpuinitdata = { 1, 1, 2, 3 };
-static unsigned char types[] __cpuinitdata = { 1, 2, 3, 3 };
+static const unsigned char __cpuinitconst levels[] = { 1, 1, 2, 3 };
+static const unsigned char __cpuinitconst types[] = { 1, 2, 3, 3 };
static void __cpuinit
amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c
index bfbd5323a63..ca14604611e 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_64.c
@@ -639,7 +639,7 @@ static void mce_init_timer(void)
if (!next_interval)
return;
setup_timer(t, mcheck_timer, smp_processor_id());
- t->expires = round_jiffies_relative(jiffies + next_interval);
+ t->expires = round_jiffies(jiffies + next_interval);
add_timer(t);
}
@@ -1110,7 +1110,7 @@ static int __cpuinit mce_cpu_callback(struct notifier_block *nfb,
break;
case CPU_DOWN_FAILED:
case CPU_DOWN_FAILED_FROZEN:
- t->expires = round_jiffies_relative(jiffies + next_interval);
+ t->expires = round_jiffies(jiffies + next_interval);
add_timer_on(t, cpu);
smp_call_function_single(cpu, mce_reenable_cpu, &action, 1);
break;
diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c
index 52b3fefbd5a..bb62b3e5caa 100644
--- a/arch/x86/kernel/cpu/transmeta.c
+++ b/arch/x86/kernel/cpu/transmeta.c
@@ -98,7 +98,7 @@ static void __cpuinit init_transmeta(struct cpuinfo_x86 *c)
#endif
}
-static struct cpu_dev transmeta_cpu_dev __cpuinitdata = {
+static const struct cpu_dev __cpuinitconst transmeta_cpu_dev = {
.c_vendor = "Transmeta",
.c_ident = { "GenuineTMx86", "TransmetaCPU" },
.c_early_init = early_init_transmeta,
diff --git a/arch/x86/kernel/cpu/umc.c b/arch/x86/kernel/cpu/umc.c
index e777f79e096..fd2c37bf7ac 100644
--- a/arch/x86/kernel/cpu/umc.c
+++ b/arch/x86/kernel/cpu/umc.c
@@ -8,7 +8,7 @@
* so no special init takes place.
*/
-static struct cpu_dev umc_cpu_dev __cpuinitdata = {
+static const struct cpu_dev __cpuinitconst umc_cpu_dev = {
.c_vendor = "UMC",
.c_ident = { "UMC UMC UMC" },
.c_models = {
diff --git a/arch/x86/kernel/ds.c b/arch/x86/kernel/ds.c
index 169a120587b..87b67e3a765 100644
--- a/arch/x86/kernel/ds.c
+++ b/arch/x86/kernel/ds.c
@@ -729,7 +729,7 @@ struct pebs_tracer *ds_request_pebs(struct task_struct *task,
spin_unlock_irqrestore(&ds_lock, irq);
- ds_write_config(tracer->ds.context, &tracer->trace.ds, ds_bts);
+ ds_write_config(tracer->ds.context, &tracer->trace.ds, ds_pebs);
ds_resume_pebs(tracer);
return tracer;
@@ -1029,5 +1029,4 @@ void ds_copy_thread(struct task_struct *tsk, struct task_struct *father)
void ds_exit_thread(struct task_struct *tsk)
{
- WARN_ON(tsk->thread.ds_ctx);
}
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 508bec1cee2..95b81c18b6b 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -110,19 +110,25 @@ int __init e820_all_mapped(u64 start, u64 end, unsigned type)
/*
* Add a memory region to the kernel e820 map.
*/
-void __init e820_add_region(u64 start, u64 size, int type)
+static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size,
+ int type)
{
- int x = e820.nr_map;
+ int x = e820x->nr_map;
- if (x == ARRAY_SIZE(e820.map)) {
+ if (x == ARRAY_SIZE(e820x->map)) {
printk(KERN_ERR "Ooops! Too many entries in the memory map!\n");
return;
}
- e820.map[x].addr = start;
- e820.map[x].size = size;
- e820.map[x].type = type;
- e820.nr_map++;
+ e820x->map[x].addr = start;
+ e820x->map[x].size = size;
+ e820x->map[x].type = type;
+ e820x->nr_map++;
+}
+
+void __init e820_add_region(u64 start, u64 size, int type)
+{
+ __e820_add_region(&e820, start, size, type);
}
void __init e820_print_map(char *who)
@@ -417,11 +423,11 @@ static int __init append_e820_map(struct e820entry *biosmap, int nr_map)
return __append_e820_map(biosmap, nr_map);
}
-static u64 __init e820_update_range_map(struct e820map *e820x, u64 start,
+static u64 __init __e820_update_range(struct e820map *e820x, u64 start,
u64 size, unsigned old_type,
unsigned new_type)
{
- int i;
+ unsigned int i;
u64 real_updated_size = 0;
BUG_ON(old_type == new_type);
@@ -429,7 +435,7 @@ static u64 __init e820_update_range_map(struct e820map *e820x, u64 start,
if (size > (ULLONG_MAX - start))
size = ULLONG_MAX - start;
- for (i = 0; i < e820.nr_map; i++) {
+ for (i = 0; i < e820x->nr_map; i++) {
struct e820entry *ei = &e820x->map[i];
u64 final_start, final_end;
if (ei->type != old_type)
@@ -446,10 +452,16 @@ static u64 __init e820_update_range_map(struct e820map *e820x, u64 start,
final_end = min(start + size, ei->addr + ei->size);
if (final_start >= final_end)
continue;
- e820_add_region(final_start, final_end - final_start,
- new_type);
+
+ __e820_add_region(e820x, final_start, final_end - final_start,
+ new_type);
+
real_updated_size += final_end - final_start;
+ /*
+ * left range could be head or tail, so need to update
+ * size at first.
+ */
ei->size -= final_end - final_start;
if (ei->addr < final_start)
continue;
@@ -461,13 +473,13 @@ static u64 __init e820_update_range_map(struct e820map *e820x, u64 start,
u64 __init e820_update_range(u64 start, u64 size, unsigned old_type,
unsigned new_type)
{
- return e820_update_range_map(&e820, start, size, old_type, new_type);
+ return __e820_update_range(&e820, start, size, old_type, new_type);
}
static u64 __init e820_update_range_saved(u64 start, u64 size,
unsigned old_type, unsigned new_type)
{
- return e820_update_range_map(&e820_saved, start, size, old_type,
+ return __e820_update_range(&e820_saved, start, size, old_type,
new_type);
}
@@ -1020,8 +1032,8 @@ u64 __init find_e820_area_size(u64 start, u64 *sizep, u64 align)
continue;
return addr;
}
- return -1UL;
+ return -1ULL;
}
/*
@@ -1034,13 +1046,22 @@ u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align)
u64 start;
start = startt;
- while (size < sizet)
+ while (size < sizet && (start + 1))
start = find_e820_area_size(start, &size, align);
if (size < sizet)
return 0;
+#ifdef CONFIG_X86_32
+ if (start >= MAXMEM)
+ return 0;
+ if (start + size > MAXMEM)
+ size = MAXMEM - start;
+#endif
+
addr = round_down(start + size - sizet, align);
+ if (addr < start)
+ return 0;
e820_update_range(addr, sizet, E820_RAM, E820_RESERVED);
e820_update_range_saved(addr, sizet, E820_RAM, E820_RESERVED);
printk(KERN_INFO "update e820 for early_reserve_e820\n");
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index 639ad98238a..335f049d110 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -250,7 +250,7 @@ static int dbgp_wait_until_complete(void)
return (ctrl & DBGP_ERROR) ? -DBGP_ERRCODE(ctrl) : DBGP_LEN(ctrl);
}
-static void dbgp_mdelay(int ms)
+static void __init dbgp_mdelay(int ms)
{
int i;
@@ -311,7 +311,7 @@ static void dbgp_set_data(const void *buf, int size)
writel(hi, &ehci_debug->data47);
}
-static void dbgp_get_data(void *buf, int size)
+static void __init dbgp_get_data(void *buf, int size)
{
unsigned char *bytes = buf;
u32 lo, hi;
@@ -355,7 +355,7 @@ static int dbgp_bulk_write(unsigned devnum, unsigned endpoint,
return ret;
}
-static int dbgp_bulk_read(unsigned devnum, unsigned endpoint, void *data,
+static int __init dbgp_bulk_read(unsigned devnum, unsigned endpoint, void *data,
int size)
{
u32 pids, addr, ctrl;
@@ -386,8 +386,8 @@ static int dbgp_bulk_read(unsigned devnum, unsigned endpoint, void *data,
return ret;
}
-static int dbgp_control_msg(unsigned devnum, int requesttype, int request,
- int value, int index, void *data, int size)
+static int __init dbgp_control_msg(unsigned devnum, int requesttype,
+ int request, int value, int index, void *data, int size)
{
u32 pids, addr, ctrl;
struct usb_ctrlrequest req;
@@ -489,7 +489,7 @@ static u32 __init find_dbgp(int ehci_num, u32 *rbus, u32 *rslot, u32 *rfunc)
return 0;
}
-static int ehci_reset_port(int port)
+static int __init ehci_reset_port(int port)
{
u32 portsc;
u32 delay_time, delay;
@@ -532,7 +532,7 @@ static int ehci_reset_port(int port)
return -EBUSY;
}
-static int ehci_wait_for_port(int port)
+static int __init ehci_wait_for_port(int port)
{
u32 status;
int ret, reps;
@@ -557,13 +557,13 @@ static inline void dbgp_printk(const char *fmt, ...) { }
typedef void (*set_debug_port_t)(int port);
-static void default_set_debug_port(int port)
+static void __init default_set_debug_port(int port)
{
}
-static set_debug_port_t set_debug_port = default_set_debug_port;
+static set_debug_port_t __initdata set_debug_port = default_set_debug_port;
-static void nvidia_set_debug_port(int port)
+static void __init nvidia_set_debug_port(int port)
{
u32 dword;
dword = read_pci_config(ehci_dev.bus, ehci_dev.slot, ehci_dev.func,
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 899e8938e79..c929add475c 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -442,8 +442,7 @@ sysenter_past_esp:
GET_THREAD_INFO(%ebp)
- /* Note, _TIF_SECCOMP is bit number 8, and so it needs testw and not testb */
- testw $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp)
+ testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp)
jnz sysenter_audit
sysenter_do_call:
cmpl $(nr_syscalls), %eax
@@ -454,7 +453,7 @@ sysenter_do_call:
DISABLE_INTERRUPTS(CLBR_ANY)
TRACE_IRQS_OFF
movl TI_flags(%ebp), %ecx
- testw $_TIF_ALLWORK_MASK, %cx
+ testl $_TIF_ALLWORK_MASK, %ecx
jne sysexit_audit
sysenter_exit:
/* if something modifies registers it must also disable sysexit */
@@ -468,7 +467,7 @@ sysenter_exit:
#ifdef CONFIG_AUDITSYSCALL
sysenter_audit:
- testw $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%ebp)
+ testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%ebp)
jnz syscall_trace_entry
addl $4,%esp
CFI_ADJUST_CFA_OFFSET -4
@@ -485,7 +484,7 @@ sysenter_audit:
jmp sysenter_do_call
sysexit_audit:
- testw $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %cx
+ testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx
jne syscall_exit_work
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_ANY)
@@ -498,7 +497,7 @@ sysexit_audit:
DISABLE_INTERRUPTS(CLBR_ANY)
TRACE_IRQS_OFF
movl TI_flags(%ebp), %ecx
- testw $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %cx
+ testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx
jne syscall_exit_work
movl PT_EAX(%esp),%eax /* reload syscall return value */
jmp sysenter_exit
@@ -523,8 +522,7 @@ ENTRY(system_call)
SAVE_ALL
GET_THREAD_INFO(%ebp)
# system call tracing in operation / emulation
- /* Note, _TIF_SECCOMP is bit number 8, and so it needs testw and not testb */
- testw $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp)
+ testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp)
jnz syscall_trace_entry
cmpl $(nr_syscalls), %eax
jae syscall_badsys
@@ -538,7 +536,7 @@ syscall_exit:
# between sampling and the iret
TRACE_IRQS_OFF
movl TI_flags(%ebp), %ecx
- testw $_TIF_ALLWORK_MASK, %cx # current->work
+ testl $_TIF_ALLWORK_MASK, %ecx # current->work
jne syscall_exit_work
restore_all:
@@ -673,7 +671,7 @@ END(syscall_trace_entry)
# perform syscall exit tracing
ALIGN
syscall_exit_work:
- testb $_TIF_WORK_SYSCALL_EXIT, %cl
+ testl $_TIF_WORK_SYSCALL_EXIT, %ecx
jz work_pending
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_ANY) # could let syscall_trace_leave() call
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 7ba4621c0df..a331ec38af9 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -368,6 +368,7 @@ ENTRY(save_rest)
END(save_rest)
/* save complete stack frame */
+ .pushsection .kprobes.text, "ax"
ENTRY(save_paranoid)
XCPT_FRAME 1 RDI+8
cld
@@ -396,6 +397,7 @@ ENTRY(save_paranoid)
1: ret
CFI_ENDPROC
END(save_paranoid)
+ .popsection
/*
* A newly forked process directly context switches into this address.
@@ -416,7 +418,6 @@ ENTRY(ret_from_fork)
GET_THREAD_INFO(%rcx)
- CFI_REMEMBER_STATE
RESTORE_REST
testl $3, CS-ARGOFFSET(%rsp) # from kernel_thread?
@@ -428,7 +429,6 @@ ENTRY(ret_from_fork)
RESTORE_TOP_OF_STACK %rdi, -ARGOFFSET
jmp ret_from_sys_call # go to the SYSRET fastpath
- CFI_RESTORE_STATE
CFI_ENDPROC
END(ret_from_fork)
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index f5fc8c781a6..e7368c1da01 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -14,12 +14,12 @@
#include <linux/ftrace.h>
#include <linux/suspend.h>
#include <linux/gfp.h>
+#include <linux/io.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
-#include <asm/io.h>
#include <asm/apic.h>
#include <asm/cpufeature.h>
#include <asm/desc.h>
@@ -63,7 +63,7 @@ static void load_segments(void)
"\tmovl %%eax,%%fs\n"
"\tmovl %%eax,%%gs\n"
"\tmovl %%eax,%%ss\n"
- ::: "eax", "memory");
+ : : : "eax", "memory");
#undef STR
#undef __STR
}
@@ -205,7 +205,8 @@ void machine_kexec(struct kimage *image)
if (image->preserve_context) {
#ifdef CONFIG_X86_IO_APIC
- /* We need to put APICs in legacy mode so that we can
+ /*
+ * We need to put APICs in legacy mode so that we can
* get timer interrupts in second kernel. kexec/kdump
* paths already have calls to disable_IO_APIC() in
* one form or other. kexec jump path also need
@@ -227,7 +228,8 @@ void machine_kexec(struct kimage *image)
page_list[PA_SWAP_PAGE] = (page_to_pfn(image->swap_page)
<< PAGE_SHIFT);
- /* The segment registers are funny things, they have both a
+ /*
+ * The segment registers are funny things, they have both a
* visible and an invisible part. Whenever the visible part is
* set to a specific selector, the invisible part is loaded
* with from a table in memory. At no other time is the
@@ -237,11 +239,12 @@ void machine_kexec(struct kimage *image)
* segments, before I zap the gdt with an invalid value.
*/
load_segments();
- /* The gdt & idt are now invalid.
+ /*
+ * The gdt & idt are now invalid.
* If you want to load them you must set up your own idt & gdt.
*/
- set_gdt(phys_to_virt(0),0);
- set_idt(phys_to_virt(0),0);
+ set_gdt(phys_to_virt(0), 0);
+ set_idt(phys_to_virt(0), 0);
/* now call it */
image->start = relocate_kernel_ptr((unsigned long)image->head,
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 6993d51b7fd..89cea4d4467 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -12,11 +12,47 @@
#include <linux/reboot.h>
#include <linux/numa.h>
#include <linux/ftrace.h>
+#include <linux/io.h>
+#include <linux/suspend.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
-#include <asm/io.h>
+
+static int init_one_level2_page(struct kimage *image, pgd_t *pgd,
+ unsigned long addr)
+{
+ pud_t *pud;
+ pmd_t *pmd;
+ struct page *page;
+ int result = -ENOMEM;
+
+ addr &= PMD_MASK;
+ pgd += pgd_index(addr);
+ if (!pgd_present(*pgd)) {
+ page = kimage_alloc_control_pages(image, 0);
+ if (!page)
+ goto out;
+ pud = (pud_t *)page_address(page);
+ memset(pud, 0, PAGE_SIZE);
+ set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE));
+ }
+ pud = pud_offset(pgd, addr);
+ if (!pud_present(*pud)) {
+ page = kimage_alloc_control_pages(image, 0);
+ if (!page)
+ goto out;
+ pmd = (pmd_t *)page_address(page);
+ memset(pmd, 0, PAGE_SIZE);
+ set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
+ }
+ pmd = pmd_offset(pud, addr);
+ if (!pmd_present(*pmd))
+ set_pmd(pmd, __pmd(addr | __PAGE_KERNEL_LARGE_EXEC));
+ result = 0;
+out:
+ return result;
+}
static void init_level2_page(pmd_t *level2p, unsigned long addr)
{
@@ -83,9 +119,8 @@ static int init_level4_page(struct kimage *image, pgd_t *level4p,
}
level3p = (pud_t *)page_address(page);
result = init_level3_page(image, level3p, addr, last_addr);
- if (result) {
+ if (result)
goto out;
- }
set_pgd(level4p++, __pgd(__pa(level3p) | _KERNPG_TABLE));
addr += PGDIR_SIZE;
}
@@ -156,6 +191,13 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable)
result = init_level4_page(image, level4p, 0, max_pfn << PAGE_SHIFT);
if (result)
return result;
+ /*
+ * image->start may be outside 0 ~ max_pfn, for example when
+ * jump back to original kernel from kexeced kernel
+ */
+ result = init_one_level2_page(image, level4p, image->start);
+ if (result)
+ return result;
return init_transition_pgtable(image, level4p);
}
@@ -229,20 +271,45 @@ void machine_kexec(struct kimage *image)
{
unsigned long page_list[PAGES_NR];
void *control_page;
+ int save_ftrace_enabled;
- tracer_disable();
+#ifdef CONFIG_KEXEC_JUMP
+ if (kexec_image->preserve_context)
+ save_processor_state();
+#endif
+
+ save_ftrace_enabled = __ftrace_enabled_save();
/* Interrupts aren't acceptable while we reboot */
local_irq_disable();
+ if (image->preserve_context) {
+#ifdef CONFIG_X86_IO_APIC
+ /*
+ * We need to put APICs in legacy mode so that we can
+ * get timer interrupts in second kernel. kexec/kdump
+ * paths already have calls to disable_IO_APIC() in
+ * one form or other. kexec jump path also need
+ * one.
+ */
+ disable_IO_APIC();
+#endif
+ }
+
control_page = page_address(image->control_code_page) + PAGE_SIZE;
- memcpy(control_page, relocate_kernel, PAGE_SIZE);
+ memcpy(control_page, relocate_kernel, KEXEC_CONTROL_CODE_MAX_SIZE);
page_list[PA_CONTROL_PAGE] = virt_to_phys(control_page);
+ page_list[VA_CONTROL_PAGE] = (unsigned long)control_page;
page_list[PA_TABLE_PAGE] =
(unsigned long)__pa(page_address(image->control_code_page));
- /* The segment registers are funny things, they have both a
+ if (image->type == KEXEC_TYPE_DEFAULT)
+ page_list[PA_SWAP_PAGE] = (page_to_pfn(image->swap_page)
+ << PAGE_SHIFT);
+
+ /*
+ * The segment registers are funny things, they have both a
* visible and an invisible part. Whenever the visible part is
* set to a specific selector, the invisible part is loaded
* with from a table in memory. At no other time is the
@@ -252,15 +319,25 @@ void machine_kexec(struct kimage *image)
* segments, before I zap the gdt with an invalid value.
*/
load_segments();
- /* The gdt & idt are now invalid.
+ /*
+ * The gdt & idt are now invalid.
* If you want to load them you must set up your own idt & gdt.
*/
- set_gdt(phys_to_virt(0),0);
- set_idt(phys_to_virt(0),0);
+ set_gdt(phys_to_virt(0), 0);
+ set_idt(phys_to_virt(0), 0);
/* now call it */
- relocate_kernel((unsigned long)image->head, (unsigned long)page_list,
- image->start);
+ image->start = relocate_kernel((unsigned long)image->head,
+ (unsigned long)page_list,
+ image->start,
+ image->preserve_context);
+
+#ifdef CONFIG_KEXEC_JUMP
+ if (kexec_image->preserve_context)
+ restore_processor_state();
+#endif
+
+ __ftrace_enabled_restore(save_ftrace_enabled);
}
void arch_crash_save_vmcoreinfo(void)
diff --git a/arch/x86/kernel/mmconf-fam10h_64.c b/arch/x86/kernel/mmconf-fam10h_64.c
index 666e43df51f..712d15fdc41 100644
--- a/arch/x86/kernel/mmconf-fam10h_64.c
+++ b/arch/x86/kernel/mmconf-fam10h_64.c
@@ -226,7 +226,7 @@ static int __devinit set_check_enable_amd_mmconf(const struct dmi_system_id *d)
return 0;
}
-static struct dmi_system_id __devinitdata mmconf_dmi_table[] = {
+static const struct dmi_system_id __cpuinitconst mmconf_dmi_table[] = {
{
.callback = set_check_enable_amd_mmconf,
.ident = "Sun Microsystems Machine",
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index e8192401da4..47673e02ae5 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -890,12 +890,12 @@ static int __init replace_intsrc_all(struct mpc_table *mpc,
#ifdef CONFIG_X86_IO_APIC
struct mpc_intsrc *m = (struct mpc_intsrc *)mpt;
- printk(KERN_INFO "OLD ");
+ apic_printk(APIC_VERBOSE, "OLD ");
print_MP_intsrc_info(m);
i = get_MP_intsrc_index(m);
if (i > 0) {
assign_to_mpc_intsrc(&mp_irqs[i], m);
- printk(KERN_INFO "NEW ");
+ apic_printk(APIC_VERBOSE, "NEW ");
print_mp_irq_info(&mp_irqs[i]);
} else if (!i) {
/* legacy, do nothing */
@@ -943,7 +943,7 @@ static int __init replace_intsrc_all(struct mpc_table *mpc,
continue;
if (nr_m_spare > 0) {
- printk(KERN_INFO "*NEW* found ");
+ apic_printk(APIC_VERBOSE, "*NEW* found\n");
nr_m_spare--;
assign_to_mpc_intsrc(&mp_irqs[i], m_spare[nr_m_spare]);
m_spare[nr_m_spare] = NULL;
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 3d9672e59c1..19378715f41 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -685,9 +685,8 @@ static int ptrace_bts_config(struct task_struct *child,
if (!cfg.signal)
return -EINVAL;
- return -EOPNOTSUPP;
-
child->thread.bts_ovfl_signal = cfg.signal;
+ return -EOPNOTSUPP;
}
if ((cfg.flags & PTRACE_BTS_O_ALLOC) &&
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 309949e9e1c..6a5a2970f4c 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -74,8 +74,7 @@ static void ich_force_hpet_resume(void)
if (!force_hpet_address)
return;
- if (rcba_base == NULL)
- BUG();
+ BUG_ON(rcba_base == NULL);
/* read the Function Disable register, dword mode only */
val = readl(rcba_base + 0x3404);
diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S
index 2064d0aa8d2..41235531b11 100644
--- a/arch/x86/kernel/relocate_kernel_32.S
+++ b/arch/x86/kernel/relocate_kernel_32.S
@@ -17,7 +17,8 @@
#define PTR(x) (x << 2)
-/* control_page + KEXEC_CONTROL_CODE_MAX_SIZE
+/*
+ * control_page + KEXEC_CONTROL_CODE_MAX_SIZE
* ~ control_page + PAGE_SIZE are used as data storage and stack for
* jumping back
*/
@@ -76,8 +77,10 @@ relocate_kernel:
movl %eax, CP_PA_SWAP_PAGE(%edi)
movl %ebx, CP_PA_BACKUP_PAGES_MAP(%edi)
- /* get physical address of control page now */
- /* this is impossible after page table switch */
+ /*
+ * get physical address of control page now
+ * this is impossible after page table switch
+ */
movl PTR(PA_CONTROL_PAGE)(%ebp), %edi
/* switch to new set of page tables */
@@ -97,7 +100,8 @@ identity_mapped:
/* store the start address on the stack */
pushl %edx
- /* Set cr0 to a known state:
+ /*
+ * Set cr0 to a known state:
* - Paging disabled
* - Alignment check disabled
* - Write protect disabled
@@ -113,7 +117,8 @@ identity_mapped:
/* clear cr4 if applicable */
testl %ecx, %ecx
jz 1f
- /* Set cr4 to a known state:
+ /*
+ * Set cr4 to a known state:
* Setting everything to zero seems safe.
*/
xorl %eax, %eax
@@ -132,15 +137,18 @@ identity_mapped:
call swap_pages
addl $8, %esp
- /* To be certain of avoiding problems with self-modifying code
+ /*
+ * To be certain of avoiding problems with self-modifying code
* I need to execute a serializing instruction here.
* So I flush the TLB, it's handy, and not processor dependent.
*/
xorl %eax, %eax
movl %eax, %cr3
- /* set all of the registers to known values */
- /* leave %esp alone */
+ /*
+ * set all of the registers to known values
+ * leave %esp alone
+ */
testl %esi, %esi
jnz 1f
diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S
index d32cfb27a47..4de8f5b3d47 100644
--- a/arch/x86/kernel/relocate_kernel_64.S
+++ b/arch/x86/kernel/relocate_kernel_64.S
@@ -19,29 +19,77 @@
#define PTR(x) (x << 3)
#define PAGE_ATTR (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY)
+/*
+ * control_page + KEXEC_CONTROL_CODE_MAX_SIZE
+ * ~ control_page + PAGE_SIZE are used as data storage and stack for
+ * jumping back
+ */
+#define DATA(offset) (KEXEC_CONTROL_CODE_MAX_SIZE+(offset))
+
+/* Minimal CPU state */
+#define RSP DATA(0x0)
+#define CR0 DATA(0x8)
+#define CR3 DATA(0x10)
+#define CR4 DATA(0x18)
+
+/* other data */
+#define CP_PA_TABLE_PAGE DATA(0x20)
+#define CP_PA_SWAP_PAGE DATA(0x28)
+#define CP_PA_BACKUP_PAGES_MAP DATA(0x30)
+
.text
.align PAGE_SIZE
.code64
.globl relocate_kernel
relocate_kernel:
- /* %rdi indirection_page
+ /*
+ * %rdi indirection_page
* %rsi page_list
* %rdx start address
+ * %rcx preserve_context
*/
+ /* Save the CPU context, used for jumping back */
+ pushq %rbx
+ pushq %rbp
+ pushq %r12
+ pushq %r13
+ pushq %r14
+ pushq %r15
+ pushf
+
+ movq PTR(VA_CONTROL_PAGE)(%rsi), %r11
+ movq %rsp, RSP(%r11)
+ movq %cr0, %rax
+ movq %rax, CR0(%r11)
+ movq %cr3, %rax
+ movq %rax, CR3(%r11)
+ movq %cr4, %rax
+ movq %rax, CR4(%r11)
+
/* zero out flags, and disable interrupts */
pushq $0
popfq
- /* get physical address of control page now */
- /* this is impossible after page table switch */
+ /*
+ * get physical address of control page now
+ * this is impossible after page table switch
+ */
movq PTR(PA_CONTROL_PAGE)(%rsi), %r8
/* get physical address of page table now too */
- movq PTR(PA_TABLE_PAGE)(%rsi), %rcx
+ movq PTR(PA_TABLE_PAGE)(%rsi), %r9
+
+ /* get physical address of swap page now */
+ movq PTR(PA_SWAP_PAGE)(%rsi), %r10
+
+ /* save some information for jumping back */
+ movq %r9, CP_PA_TABLE_PAGE(%r11)
+ movq %r10, CP_PA_SWAP_PAGE(%r11)
+ movq %rdi, CP_PA_BACKUP_PAGES_MAP(%r11)
/* Switch to the identity mapped page tables */
- movq %rcx, %cr3
+ movq %r9, %cr3
/* setup a new stack at the end of the physical control page */
lea PAGE_SIZE(%r8), %rsp
@@ -55,7 +103,8 @@ identity_mapped:
/* store the start address on the stack */
pushq %rdx
- /* Set cr0 to a known state:
+ /*
+ * Set cr0 to a known state:
* - Paging enabled
* - Alignment check disabled
* - Write protect disabled
@@ -68,7 +117,8 @@ identity_mapped:
orl $(X86_CR0_PG | X86_CR0_PE), %eax
movq %rax, %cr0
- /* Set cr4 to a known state:
+ /*
+ * Set cr4 to a known state:
* - physical address extension enabled
*/
movq $X86_CR4_PAE, %rax
@@ -78,9 +128,87 @@ identity_mapped:
1:
/* Flush the TLB (needed?) */
- movq %rcx, %cr3
+ movq %r9, %cr3
+
+ movq %rcx, %r11
+ call swap_pages
+
+ /*
+ * To be certain of avoiding problems with self-modifying code
+ * I need to execute a serializing instruction here.
+ * So I flush the TLB by reloading %cr3 here, it's handy,
+ * and not processor dependent.
+ */
+ movq %cr3, %rax
+ movq %rax, %cr3
+
+ /*
+ * set all of the registers to known values
+ * leave %rsp alone
+ */
+
+ testq %r11, %r11
+ jnz 1f
+ xorq %rax, %rax
+ xorq %rbx, %rbx
+ xorq %rcx, %rcx
+ xorq %rdx, %rdx
+ xorq %rsi, %rsi
+ xorq %rdi, %rdi
+ xorq %rbp, %rbp
+ xorq %r8, %r8
+ xorq %r9, %r9
+ xorq %r10, %r9
+ xorq %r11, %r11
+ xorq %r12, %r12
+ xorq %r13, %r13
+ xorq %r14, %r14
+ xorq %r15, %r15
+
+ ret
+
+1:
+ popq %rdx
+ leaq PAGE_SIZE(%r10), %rsp
+ call *%rdx
+
+ /* get the re-entry point of the peer system */
+ movq 0(%rsp), %rbp
+ call 1f
+1:
+ popq %r8
+ subq $(1b - relocate_kernel), %r8
+ movq CP_PA_SWAP_PAGE(%r8), %r10
+ movq CP_PA_BACKUP_PAGES_MAP(%r8), %rdi
+ movq CP_PA_TABLE_PAGE(%r8), %rax
+ movq %rax, %cr3
+ lea PAGE_SIZE(%r8), %rsp
+ call swap_pages
+ movq $virtual_mapped, %rax
+ pushq %rax
+ ret
+
+virtual_mapped:
+ movq RSP(%r8), %rsp
+ movq CR4(%r8), %rax
+ movq %rax, %cr4
+ movq CR3(%r8), %rax
+ movq CR0(%r8), %r8
+ movq %rax, %cr3
+ movq %r8, %cr0
+ movq %rbp, %rax
+
+ popf
+ popq %r15
+ popq %r14
+ popq %r13
+ popq %r12
+ popq %rbp
+ popq %rbx
+ ret
/* Do the copies */
+swap_pages:
movq %rdi, %rcx /* Put the page_list in %rcx */
xorq %rdi, %rdi
xorq %rsi, %rsi
@@ -112,36 +240,27 @@ identity_mapped:
movq %rcx, %rsi /* For ever source page do a copy */
andq $0xfffffffffffff000, %rsi
+ movq %rdi, %rdx
+ movq %rsi, %rax
+
+ movq %r10, %rdi
movq $512, %rcx
rep ; movsq
- jmp 0b
-3:
-
- /* To be certain of avoiding problems with self-modifying code
- * I need to execute a serializing instruction here.
- * So I flush the TLB by reloading %cr3 here, it's handy,
- * and not processor dependent.
- */
- movq %cr3, %rax
- movq %rax, %cr3
- /* set all of the registers to known values */
- /* leave %rsp alone */
+ movq %rax, %rdi
+ movq %rdx, %rsi
+ movq $512, %rcx
+ rep ; movsq
- xorq %rax, %rax
- xorq %rbx, %rbx
- xorq %rcx, %rcx
- xorq %rdx, %rdx
- xorq %rsi, %rsi
- xorq %rdi, %rdi
- xorq %rbp, %rbp
- xorq %r8, %r8
- xorq %r9, %r9
- xorq %r10, %r9
- xorq %r11, %r11
- xorq %r12, %r12
- xorq %r13, %r13
- xorq %r14, %r14
- xorq %r15, %r15
+ movq %rdx, %rdi
+ movq %r10, %rsi
+ movq $512, %rcx
+ rep ; movsq
+ lea PAGE_SIZE(%rax), %rsi
+ jmp 0b
+3:
ret
+
+ .globl kexec_control_code_size
+.set kexec_control_code_size, . - relocate_kernel
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index c29f301d388..400331b50a5 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -42,6 +42,19 @@ unsigned long __per_cpu_offset[NR_CPUS] __read_mostly = {
};
EXPORT_SYMBOL(__per_cpu_offset);
+/*
+ * On x86_64 symbols referenced from code should be reachable using
+ * 32bit relocations. Reserve space for static percpu variables in
+ * modules so that they are always served from the first chunk which
+ * is located at the percpu segment base. On x86_32, anything can
+ * address anywhere. No need to reserve space in the first chunk.
+ */
+#ifdef CONFIG_X86_64
+#define PERCPU_FIRST_CHUNK_RESERVE PERCPU_MODULE_RESERVE
+#else
+#define PERCPU_FIRST_CHUNK_RESERVE 0
+#endif
+
/**
* pcpu_need_numa - determine percpu allocation needs to consider NUMA
*
@@ -141,7 +154,7 @@ static ssize_t __init setup_pcpu_remap(size_t static_size)
{
static struct vm_struct vm;
pg_data_t *last;
- size_t ptrs_size;
+ size_t ptrs_size, dyn_size;
unsigned int cpu;
ssize_t ret;
@@ -169,12 +182,14 @@ proceed:
* Currently supports only single page. Supporting multiple
* pages won't be too difficult if it ever becomes necessary.
*/
- pcpur_size = PFN_ALIGN(static_size + PERCPU_DYNAMIC_RESERVE);
+ pcpur_size = PFN_ALIGN(static_size + PERCPU_MODULE_RESERVE +
+ PERCPU_DYNAMIC_RESERVE);
if (pcpur_size > PMD_SIZE) {
pr_warning("PERCPU: static data is larger than large page, "
"can't use large page\n");
return -EINVAL;
}
+ dyn_size = pcpur_size - static_size - PERCPU_FIRST_CHUNK_RESERVE;
/* allocate pointer array and alloc large pages */
ptrs_size = PFN_ALIGN(num_possible_cpus() * sizeof(pcpur_ptrs[0]));
@@ -217,8 +232,9 @@ proceed:
pr_info("PERCPU: Remapped at %p with large pages, static data "
"%zu bytes\n", vm.addr, static_size);
- ret = pcpu_setup_first_chunk(pcpur_get_page, static_size, PMD_SIZE,
- pcpur_size - static_size, vm.addr, NULL);
+ ret = pcpu_setup_first_chunk(pcpur_get_page, static_size,
+ PERCPU_FIRST_CHUNK_RESERVE, dyn_size,
+ PMD_SIZE, vm.addr, NULL);
goto out_free_ar;
enomem:
@@ -241,24 +257,13 @@ static ssize_t __init setup_pcpu_remap(size_t static_size)
* Embedding allocator
*
* The first chunk is sized to just contain the static area plus
- * PERCPU_DYNAMIC_RESERVE and allocated as a contiguous area using
- * bootmem allocator and used as-is without being mapped into vmalloc
- * area. This enables the first chunk to piggy back on the linear
- * physical PMD mapping and doesn't add any additional pressure to
- * TLB.
+ * module and dynamic reserves and embedded into linear physical
+ * mapping so that it can use PMD mapping without additional TLB
+ * pressure.
*/
-static void *pcpue_ptr __initdata;
-static size_t pcpue_unit_size __initdata;
-
-static struct page * __init pcpue_get_page(unsigned int cpu, int pageno)
-{
- return virt_to_page(pcpue_ptr + cpu * pcpue_unit_size
- + ((size_t)pageno << PAGE_SHIFT));
-}
-
static ssize_t __init setup_pcpu_embed(size_t static_size)
{
- unsigned int cpu;
+ size_t reserve = PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE;
/*
* If large page isn't supported, there's no benefit in doing
@@ -268,26 +273,8 @@ static ssize_t __init setup_pcpu_embed(size_t static_size)
if (!cpu_has_pse || pcpu_need_numa())
return -EINVAL;
- /* allocate and copy */
- pcpue_unit_size = PFN_ALIGN(static_size + PERCPU_DYNAMIC_RESERVE);
- pcpue_unit_size = max_t(size_t, pcpue_unit_size, PCPU_MIN_UNIT_SIZE);
- pcpue_ptr = pcpu_alloc_bootmem(0, num_possible_cpus() * pcpue_unit_size,
- PAGE_SIZE);
- if (!pcpue_ptr)
- return -ENOMEM;
-
- for_each_possible_cpu(cpu)
- memcpy(pcpue_ptr + cpu * pcpue_unit_size, __per_cpu_load,
- static_size);
-
- /* we're ready, commit */
- pr_info("PERCPU: Embedded %zu pages at %p, static data %zu bytes\n",
- pcpue_unit_size >> PAGE_SHIFT, pcpue_ptr, static_size);
-
- return pcpu_setup_first_chunk(pcpue_get_page, static_size,
- pcpue_unit_size,
- pcpue_unit_size - static_size, pcpue_ptr,
- NULL);
+ return pcpu_embed_first_chunk(static_size, PERCPU_FIRST_CHUNK_RESERVE,
+ reserve - PERCPU_FIRST_CHUNK_RESERVE, -1);
}
/*
@@ -344,8 +331,9 @@ static ssize_t __init setup_pcpu_4k(size_t static_size)
pr_info("PERCPU: Allocated %d 4k pages, static data %zu bytes\n",
pcpu4k_nr_static_pages, static_size);
- ret = pcpu_setup_first_chunk(pcpu4k_get_page, static_size, 0, 0, NULL,
- pcpu4k_populate_pte);
+ ret = pcpu_setup_first_chunk(pcpu4k_get_page, static_size,
+ PERCPU_FIRST_CHUNK_RESERVE, -1,
+ -1, NULL, pcpu4k_populate_pte);
goto out_free_ar;
enomem:
diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c
index f04549afcfe..d038b9c45cf 100644
--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -314,8 +314,6 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
int locals = 0;
struct bau_desc *bau_desc;
- WARN_ON(!in_atomic());
-
cpumask_andnot(flush_mask, cpumask, cpumask_of(cpu));
uv_cpu = uv_blade_processor_id();
diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c
index 191a876e9e8..31ffc24eec4 100644
--- a/arch/x86/kernel/visws_quirks.c
+++ b/arch/x86/kernel/visws_quirks.c
@@ -578,7 +578,7 @@ static struct irq_chip piix4_virtual_irq_type = {
static irqreturn_t piix4_master_intr(int irq, void *dev_id)
{
int realirq;
- irq_desc_t *desc;
+ struct irq_desc *desc;
unsigned long flags;
spin_lock_irqsave(&i8259A_lock, flags);
diff --git a/arch/x86/kernel/vmlinux_64.lds.S b/arch/x86/kernel/vmlinux_64.lds.S
index fbfced6f680..5bf54e40c6e 100644
--- a/arch/x86/kernel/vmlinux_64.lds.S
+++ b/arch/x86/kernel/vmlinux_64.lds.S
@@ -275,3 +275,10 @@ ASSERT((_end - _text <= KERNEL_IMAGE_SIZE),
ASSERT((per_cpu__irq_stack_union == 0),
"irq_stack_union is not at start of per-cpu area");
#endif
+
+#ifdef CONFIG_KEXEC
+#include <asm/kexec.h>
+
+ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE,
+ "kexec control code size is too big")
+#endif
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index f3a5305b8ad..9fe4ddaa8f6 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -348,6 +348,11 @@ static void lguest_cpuid(unsigned int *ax, unsigned int *bx,
* flush_tlb_user() for both user and kernel mappings unless
* the Page Global Enable (PGE) feature bit is set. */
*dx |= 0x00002000;
+ /* We also lie, and say we're family id 5. 6 or greater
+ * leads to a rdmsr in early_init_intel which we can't handle.
+ * Family ID is returned as bits 8-12 in ax. */
+ *ax &= 0xFFFFF0FF;
+ *ax |= 0x00000500;
break;
case 0x80000000:
/* Futureproof this a little: if they ask how much extended
@@ -594,19 +599,21 @@ static void __init lguest_init_IRQ(void)
/* Some systems map "vectors" to interrupts weirdly. Lguest has
* a straightforward 1 to 1 mapping, so force that here. */
__get_cpu_var(vector_irq)[vector] = i;
- if (vector != SYSCALL_VECTOR) {
- set_intr_gate(vector,
- interrupt[vector-FIRST_EXTERNAL_VECTOR]);
- set_irq_chip_and_handler_name(i, &lguest_irq_controller,
- handle_level_irq,
- "level");
- }
+ if (vector != SYSCALL_VECTOR)
+ set_intr_gate(vector, interrupt[i]);
}
/* This call is required to set up for 4k stacks, where we have
* separate stacks for hard and soft interrupts. */
irq_ctx_init(smp_processor_id());
}
+void lguest_setup_irq(unsigned int irq)
+{
+ irq_to_desc_alloc_cpu(irq, 0);
+ set_irq_chip_and_handler_name(irq, &lguest_irq_controller,
+ handle_level_irq, "level");
+}
+
/*
* Time.
*
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index c22981fa2f3..ad5441ed1b5 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -1,30 +1,38 @@
/* Copyright 2002 Andi Kleen */
#include <linux/linkage.h>
-#include <asm/dwarf2.h>
+
#include <asm/cpufeature.h>
+#include <asm/dwarf2.h>
/*
* memcpy - Copy a memory block.
*
- * Input:
- * rdi destination
- * rsi source
- * rdx count
- *
+ * Input:
+ * rdi destination
+ * rsi source
+ * rdx count
+ *
* Output:
* rax original destination
- */
+ */
+/*
+ * memcpy_c() - fast string ops (REP MOVSQ) based variant.
+ *
+ * Calls to this get patched into the kernel image via the
+ * alternative instructions framework:
+ */
ALIGN
memcpy_c:
CFI_STARTPROC
- movq %rdi,%rax
- movl %edx,%ecx
- shrl $3,%ecx
- andl $7,%edx
+ movq %rdi, %rax
+
+ movl %edx, %ecx
+ shrl $3, %ecx
+ andl $7, %edx
rep movsq
- movl %edx,%ecx
+ movl %edx, %ecx
rep movsb
ret
CFI_ENDPROC
@@ -33,99 +41,110 @@ ENDPROC(memcpy_c)
ENTRY(__memcpy)
ENTRY(memcpy)
CFI_STARTPROC
- pushq %rbx
- CFI_ADJUST_CFA_OFFSET 8
- CFI_REL_OFFSET rbx, 0
- movq %rdi,%rax
- movl %edx,%ecx
- shrl $6,%ecx
+ /*
+ * Put the number of full 64-byte blocks into %ecx.
+ * Tail portion is handled at the end:
+ */
+ movq %rdi, %rax
+ movl %edx, %ecx
+ shrl $6, %ecx
jz .Lhandle_tail
.p2align 4
.Lloop_64:
+ /*
+ * We decrement the loop index here - and the zero-flag is
+ * checked at the end of the loop (instructions inbetween do
+ * not change the zero flag):
+ */
decl %ecx
- movq (%rsi),%r11
- movq 8(%rsi),%r8
+ /*
+ * Move in blocks of 4x16 bytes:
+ */
+ movq 0*8(%rsi), %r11
+ movq 1*8(%rsi), %r8
+ movq %r11, 0*8(%rdi)
+ movq %r8, 1*8(%rdi)
- movq %r11,(%rdi)
- movq %r8,1*8(%rdi)
+ movq 2*8(%rsi), %r9
+ movq 3*8(%rsi), %r10
+ movq %r9, 2*8(%rdi)
+ movq %r10, 3*8(%rdi)
- movq 2*8(%rsi),%r9
- movq 3*8(%rsi),%r10
+ movq 4*8(%rsi), %r11
+ movq 5*8(%rsi), %r8
+ movq %r11, 4*8(%rdi)
+ movq %r8, 5*8(%rdi)
- movq %r9,2*8(%rdi)
- movq %r10,3*8(%rdi)
+ movq 6*8(%rsi), %r9
+ movq 7*8(%rsi), %r10
+ movq %r9, 6*8(%rdi)
+ movq %r10, 7*8(%rdi)
- movq 4*8(%rsi),%r11
- movq 5*8(%rsi),%r8
+ leaq 64(%rsi), %rsi
+ leaq 64(%rdi), %rdi
- movq %r11,4*8(%rdi)
- movq %r8,5*8(%rdi)
-
- movq 6*8(%rsi),%r9
- movq 7*8(%rsi),%r10
-
- movq %r9,6*8(%rdi)
- movq %r10,7*8(%rdi)
-
- leaq 64(%rsi),%rsi
- leaq 64(%rdi),%rdi
jnz .Lloop_64
.Lhandle_tail:
- movl %edx,%ecx
- andl $63,%ecx
- shrl $3,%ecx
+ movl %edx, %ecx
+ andl $63, %ecx
+ shrl $3, %ecx
jz .Lhandle_7
+
.p2align 4
.Lloop_8:
decl %ecx
- movq (%rsi),%r8
- movq %r8,(%rdi)
- leaq 8(%rdi),%rdi
- leaq 8(%rsi),%rsi
+ movq (%rsi), %r8
+ movq %r8, (%rdi)
+ leaq 8(%rdi), %rdi
+ leaq 8(%rsi), %rsi
jnz .Lloop_8
.Lhandle_7:
- movl %edx,%ecx
- andl $7,%ecx
- jz .Lende
+ movl %edx, %ecx
+ andl $7, %ecx
+ jz .Lend
+
.p2align 4
.Lloop_1:
- movb (%rsi),%r8b
- movb %r8b,(%rdi)
+ movb (%rsi), %r8b
+ movb %r8b, (%rdi)
incq %rdi
incq %rsi
decl %ecx
jnz .Lloop_1
-.Lende:
- popq %rbx
- CFI_ADJUST_CFA_OFFSET -8
- CFI_RESTORE rbx
+.Lend:
ret
-.Lfinal:
CFI_ENDPROC
ENDPROC(memcpy)
ENDPROC(__memcpy)
- /* Some CPUs run faster using the string copy instructions.
- It is also a lot simpler. Use this when possible */
+ /*
+ * Some CPUs run faster using the string copy instructions.
+ * It is also a lot simpler. Use this when possible:
+ */
- .section .altinstr_replacement,"ax"
+ .section .altinstr_replacement, "ax"
1: .byte 0xeb /* jmp <disp8> */
.byte (memcpy_c - memcpy) - (2f - 1b) /* offset */
2:
.previous
- .section .altinstructions,"a"
+
+ .section .altinstructions, "a"
.align 8
.quad memcpy
.quad 1b
.byte X86_FEATURE_REP_GOOD
- /* Replace only beginning, memcpy is used to apply alternatives, so it
- * is silly to overwrite itself with nops - reboot is only outcome... */
+
+ /*
+ * Replace only beginning, memcpy is used to apply alternatives,
+ * so it is silly to overwrite itself with nops - reboot is the
+ * only outcome...
+ */
.byte 2b - 1b
.byte 2b - 1b
.previous
diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
index d11745334a6..522db5e3d0b 100644
--- a/arch/x86/mm/highmem_32.c
+++ b/arch/x86/mm/highmem_32.c
@@ -121,22 +121,13 @@ void kunmap_atomic(void *kvaddr, enum km_type type)
pagefault_enable();
}
-/* This is the same as kmap_atomic() but can map memory that doesn't
+/*
+ * This is the same as kmap_atomic() but can map memory that doesn't
* have a struct page associated with it.
*/
void *kmap_atomic_pfn(unsigned long pfn, enum km_type type)
{
- enum fixed_addresses idx;
- unsigned long vaddr;
-
- pagefault_disable();
-
- idx = type + KM_TYPE_NR*smp_processor_id();
- vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
- set_pte(kmap_pte-idx, pfn_pte(pfn, kmap_prot));
- arch_flush_lazy_mmu_mode();
-
- return (void*) vaddr;
+ return kmap_atomic_prot_pfn(pfn, type, kmap_prot);
}
EXPORT_SYMBOL_GPL(kmap_atomic_pfn); /* temporarily in use by i915 GEM until vmap */
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 6d63e3d1253..fd3da1dda1c 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -94,9 +94,9 @@ struct map_range {
#define NR_RANGE_MR 5
#endif
-static int save_mr(struct map_range *mr, int nr_range,
- unsigned long start_pfn, unsigned long end_pfn,
- unsigned long page_size_mask)
+static int __meminit save_mr(struct map_range *mr, int nr_range,
+ unsigned long start_pfn, unsigned long end_pfn,
+ unsigned long page_size_mask)
{
if (start_pfn < end_pfn) {
if (nr_range >= NR_RANGE_MR)
@@ -134,8 +134,8 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
{
unsigned long page_size_mask = 0;
unsigned long start_pfn, end_pfn;
+ unsigned long ret = 0;
unsigned long pos;
- unsigned long ret;
struct map_range mr[NR_RANGE_MR];
int nr_range, i;
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 2966c6b8d30..db81e9a8556 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -806,11 +806,6 @@ static unsigned long __init setup_node_bootmem(int nodeid,
{
unsigned long bootmap_size;
- if (start_pfn > max_low_pfn)
- return bootmap;
- if (end_pfn > max_low_pfn)
- end_pfn = max_low_pfn;
-
/* don't touch min_low_pfn */
bootmap_size = init_bootmem_node(NODE_DATA(nodeid),
bootmap >> PAGE_SHIFT,
@@ -843,13 +838,23 @@ void __init setup_bootmem_allocator(void)
max_pfn_mapped<<PAGE_SHIFT);
printk(KERN_INFO " low ram: 0 - %08lx\n", max_low_pfn<<PAGE_SHIFT);
+ for_each_online_node(nodeid) {
+ unsigned long start_pfn, end_pfn;
+
#ifdef CONFIG_NEED_MULTIPLE_NODES
- for_each_online_node(nodeid)
- bootmap = setup_node_bootmem(nodeid, node_start_pfn[nodeid],
- node_end_pfn[nodeid], bootmap);
+ start_pfn = node_start_pfn[nodeid];
+ end_pfn = node_end_pfn[nodeid];
+ if (start_pfn > max_low_pfn)
+ continue;
+ if (end_pfn > max_low_pfn)
+ end_pfn = max_low_pfn;
#else
- bootmap = setup_node_bootmem(0, 0, max_low_pfn, bootmap);
+ start_pfn = 0;
+ end_pfn = max_low_pfn;
#endif
+ bootmap = setup_node_bootmem(nodeid, start_pfn, end_pfn,
+ bootmap);
+ }
after_bootmem = 1;
}
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 8a853bc3b28..54efa57d1c0 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -85,7 +85,7 @@ early_param("gbpages", parse_direct_gbpages_on);
pteval_t __supported_pte_mask __read_mostly = ~_PAGE_IOMAP;
EXPORT_SYMBOL_GPL(__supported_pte_mask);
-static int do_not_nx __cpuinitdata;
+static int disable_nx __cpuinitdata;
/*
* noexec=on|off
@@ -100,9 +100,9 @@ static int __init nonx_setup(char *str)
return -EINVAL;
if (!strncmp(str, "on", 2)) {
__supported_pte_mask |= _PAGE_NX;
- do_not_nx = 0;
+ disable_nx = 0;
} else if (!strncmp(str, "off", 3)) {
- do_not_nx = 1;
+ disable_nx = 1;
__supported_pte_mask &= ~_PAGE_NX;
}
return 0;
@@ -114,7 +114,7 @@ void __cpuinit check_efer(void)
unsigned long efer;
rdmsrl(MSR_EFER, efer);
- if (!(efer & EFER_NX) || do_not_nx)
+ if (!(efer & EFER_NX) || disable_nx)
__supported_pte_mask &= ~_PAGE_NX;
}
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index 04102d42ff4..6e60ba698ce 100644
--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@@ -18,6 +18,7 @@
#include <asm/iomap.h>
#include <asm/pat.h>
+#include <asm/highmem.h>
#include <linux/module.h>
int is_io_mapping_possible(resource_size_t base, unsigned long size)
@@ -31,16 +32,27 @@ int is_io_mapping_possible(resource_size_t base, unsigned long size)
}
EXPORT_SYMBOL_GPL(is_io_mapping_possible);
-/* Map 'pfn' using fixed map 'type' and protections 'prot'
- */
-void *
-iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot)
+void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot)
{
enum fixed_addresses idx;
unsigned long vaddr;
pagefault_disable();
+ idx = type + KM_TYPE_NR * smp_processor_id();
+ vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
+ set_pte(kmap_pte - idx, pfn_pte(pfn, prot));
+ arch_flush_lazy_mmu_mode();
+
+ return (void *)vaddr;
+}
+
+/*
+ * Map 'pfn' using fixed map 'type' and protections 'prot'
+ */
+void *
+iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot)
+{
/*
* For non-PAT systems, promote PAGE_KERNEL_WC to PAGE_KERNEL_UC_MINUS.
* PAGE_KERNEL_WC maps to PWT, which translates to uncached if the
@@ -50,12 +62,7 @@ iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot)
if (!pat_enabled && pgprot_val(prot) == pgprot_val(PAGE_KERNEL_WC))
prot = PAGE_KERNEL_UC_MINUS;
- idx = type + KM_TYPE_NR*smp_processor_id();
- vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
- set_pte(kmap_pte-idx, pfn_pte(pfn, prot));
- arch_flush_lazy_mmu_mode();
-
- return (void*) vaddr;
+ return kmap_atomic_prot_pfn(pfn, type, prot);
}
EXPORT_SYMBOL_GPL(iomap_atomic_prot_pfn);
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 62773abdf08..55e127f71ed 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -22,13 +22,17 @@
#include <asm/pgalloc.h>
#include <asm/pat.h>
-#ifdef CONFIG_X86_64
-
-static inline int phys_addr_valid(unsigned long addr)
+static inline int phys_addr_valid(resource_size_t addr)
{
- return addr < (1UL << boot_cpu_data.x86_phys_bits);
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+ return !(addr >> boot_cpu_data.x86_phys_bits);
+#else
+ return 1;
+#endif
}
+#ifdef CONFIG_X86_64
+
unsigned long __phys_addr(unsigned long x)
{
if (x >= __START_KERNEL_map) {
@@ -65,11 +69,6 @@ EXPORT_SYMBOL(__virt_addr_valid);
#else
-static inline int phys_addr_valid(unsigned long addr)
-{
- return 1;
-}
-
#ifdef CONFIG_DEBUG_VIRTUAL
unsigned long __phys_addr(unsigned long x)
{
@@ -87,6 +86,8 @@ bool __virt_addr_valid(unsigned long x)
return false;
if (__vmalloc_start_set && is_vmalloc_addr((void *) x))
return false;
+ if (x >= FIXADDR_START)
+ return false;
return pfn_valid((x - PAGE_OFFSET) >> PAGE_SHIFT);
}
EXPORT_SYMBOL(__virt_addr_valid);
@@ -486,7 +487,12 @@ static int __init early_ioremap_debug_setup(char *str)
early_param("early_ioremap_debug", early_ioremap_debug_setup);
static __initdata int after_paging_init;
-static pte_t bm_pte[PAGE_SIZE/sizeof(pte_t)] __page_aligned_bss;
+#define __FIXADDR_TOP (-PAGE_SIZE)
+static pte_t bm_pte[(__fix_to_virt(FIX_DBGP_BASE)
+ ^ __fix_to_virt(FIX_BTMAP_BEGIN)) >> PMD_SHIFT
+ ? PAGE_SIZE / sizeof(pte_t) : 0] __page_aligned_bss;
+#undef __FIXADDR_TOP
+static __initdata pte_t *bm_ptep;
static inline pmd_t * __init early_ioremap_pmd(unsigned long addr)
{
@@ -501,19 +507,33 @@ static inline pmd_t * __init early_ioremap_pmd(unsigned long addr)
static inline pte_t * __init early_ioremap_pte(unsigned long addr)
{
+ if (!sizeof(bm_pte))
+ return &bm_ptep[pte_index(addr)];
return &bm_pte[pte_index(addr)];
}
+static unsigned long slot_virt[FIX_BTMAPS_SLOTS] __initdata;
+
void __init early_ioremap_init(void)
{
pmd_t *pmd;
+ int i;
if (early_ioremap_debug)
printk(KERN_INFO "early_ioremap_init()\n");
+ for (i = 0; i < FIX_BTMAPS_SLOTS; i++)
+ slot_virt[i] = fix_to_virt(FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*i);
+
pmd = early_ioremap_pmd(fix_to_virt(FIX_BTMAP_BEGIN));
- memset(bm_pte, 0, sizeof(bm_pte));
- pmd_populate_kernel(&init_mm, pmd, bm_pte);
+ if (sizeof(bm_pte)) {
+ memset(bm_pte, 0, sizeof(bm_pte));
+ pmd_populate_kernel(&init_mm, pmd, bm_pte);
+ } else {
+ bm_ptep = pte_offset_kernel(pmd, 0);
+ if (early_ioremap_debug)
+ printk(KERN_INFO "bm_ptep=%p\n", bm_ptep);
+ }
/*
* The boot-ioremap range spans multiple pmds, for which
@@ -577,6 +597,7 @@ static inline void __init early_clear_fixmap(enum fixed_addresses idx)
static void __iomem *prev_map[FIX_BTMAPS_SLOTS] __initdata;
static unsigned long prev_size[FIX_BTMAPS_SLOTS] __initdata;
+
static int __init check_early_ioremap_leak(void)
{
int count = 0;
@@ -598,7 +619,8 @@ static int __init check_early_ioremap_leak(void)
}
late_initcall(check_early_ioremap_leak);
-static void __init __iomem *__early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot)
+static void __init __iomem *
+__early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot)
{
unsigned long offset, last_addr;
unsigned int nrpages;
@@ -664,9 +686,9 @@ static void __init __iomem *__early_ioremap(unsigned long phys_addr, unsigned lo
--nrpages;
}
if (early_ioremap_debug)
- printk(KERN_CONT "%08lx + %08lx\n", offset, fix_to_virt(idx0));
+ printk(KERN_CONT "%08lx + %08lx\n", offset, slot_virt[slot]);
- prev_map[slot] = (void __iomem *)(offset + fix_to_virt(idx0));
+ prev_map[slot] = (void __iomem *)(offset + slot_virt[slot]);
return prev_map[slot];
}
@@ -734,8 +756,3 @@ void __init early_iounmap(void __iomem *addr, unsigned long size)
}
prev_map[slot] = NULL;
}
-
-void __this_fixmap_does_not_exist(void)
-{
- WARN_ON(1);
-}
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index 9f205030d9a..4f115e00486 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -310,7 +310,7 @@ static int post_kmmio_handler(unsigned long condition, struct pt_regs *regs)
struct kmmio_context *ctx = &get_cpu_var(kmmio_ctx);
if (!ctx->active) {
- pr_warning("kmmio: spurious debug trap on CPU %d.\n",
+ pr_debug("kmmio: spurious debug trap on CPU %d.\n",
smp_processor_id());
goto out;
}
@@ -451,23 +451,24 @@ static void rcu_free_kmmio_fault_pages(struct rcu_head *head)
static void remove_kmmio_fault_pages(struct rcu_head *head)
{
- struct kmmio_delayed_release *dr = container_of(
- head,
- struct kmmio_delayed_release,
- rcu);
+ struct kmmio_delayed_release *dr =
+ container_of(head, struct kmmio_delayed_release, rcu);
struct kmmio_fault_page *p = dr->release_list;
struct kmmio_fault_page **prevp = &dr->release_list;
unsigned long flags;
+
spin_lock_irqsave(&kmmio_lock, flags);
while (p) {
- if (!p->count)
+ if (!p->count) {
list_del_rcu(&p->list);
- else
+ prevp = &p->release_next;
+ } else {
*prevp = p->release_next;
- prevp = &p->release_next;
+ }
p = p->release_next;
}
spin_unlock_irqrestore(&kmmio_lock, flags);
+
/* This is the real RCU destroy call. */
call_rcu(&dr->rcu, rcu_free_kmmio_fault_pages);
}
diff --git a/arch/x86/mm/memtest.c b/arch/x86/mm/memtest.c
index 0bcd7883d03..605c8be0621 100644
--- a/arch/x86/mm/memtest.c
+++ b/arch/x86/mm/memtest.c
@@ -100,6 +100,9 @@ static int __init parse_memtest(char *arg)
{
if (arg)
memtest_pattern = simple_strtoul(arg, NULL, 0);
+ else
+ memtest_pattern = ARRAY_SIZE(patterns);
+
return 0;
}
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 8253bc97587..9c4294986af 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -522,6 +522,17 @@ static int split_large_page(pte_t *kpte, unsigned long address)
* primary protection behavior:
*/
__set_pmd_pte(kpte, address, mk_pte(base, __pgprot(_KERNPG_TABLE)));
+
+ /*
+ * Intel Atom errata AAH41 workaround.
+ *
+ * The real fix should be in hw or in a microcode update, but
+ * we also probabilistically try to reduce the window of having
+ * a large TLB mixed with 4K TLBs while instruction fetches are
+ * going on.
+ */
+ __flush_tlb_all();
+
base = NULL;
out_unlock:
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 2ed37158012..640339ee4fb 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -677,10 +677,11 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
is_ram = pat_pagerange_is_ram(paddr, paddr + size);
/*
- * reserve_pfn_range() doesn't support RAM pages.
+ * reserve_pfn_range() doesn't support RAM pages. Maintain the current
+ * behavior with RAM pages by returning success.
*/
if (is_ram != 0)
- return -EINVAL;
+ return 0;
ret = reserve_memtype(paddr, paddr + size, want_flags, &flags);
if (ret)
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 82d22fc601a..8c362b96b64 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -90,7 +90,7 @@ static int __devinit can_skip_ioresource_align(const struct dmi_system_id *d)
return 0;
}
-static struct dmi_system_id can_skip_pciprobe_dmi_table[] __devinitdata = {
+static const struct dmi_system_id can_skip_pciprobe_dmi_table[] __devinitconst = {
/*
* Systems where PCI IO resource ISA alignment can be skipped
* when the ISA enable bit in the bridge control is not set
@@ -183,7 +183,7 @@ static int __devinit assign_all_busses(const struct dmi_system_id *d)
}
#endif
-static struct dmi_system_id __devinitdata pciprobe_dmi_table[] = {
+static const struct dmi_system_id __devinitconst pciprobe_dmi_table[] = {
#ifdef __i386__
/*
* Laptops which need pci=assign-busses to see Cardbus cards
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index 7d388d5cf54..9c49919e4d1 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -356,7 +356,7 @@ static void __devinit pci_fixup_video(struct pci_dev *pdev)
DECLARE_PCI_FIXUP_FINAL(PCI_ANY_ID, PCI_ANY_ID, pci_fixup_video);
-static struct dmi_system_id __devinitdata msi_k8t_dmi_table[] = {
+static const struct dmi_system_id __devinitconst msi_k8t_dmi_table[] = {
{
.ident = "MSI-K8T-Neo2Fir",
.matches = {
@@ -413,7 +413,7 @@ DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8237,
*/
static u16 toshiba_line_size;
-static struct dmi_system_id __devinitdata toshiba_ohci1394_dmi_table[] = {
+static const struct dmi_system_id __devinitconst toshiba_ohci1394_dmi_table[] = {
{
.ident = "Toshiba PS5 based laptop",
.matches = {