Merge branches 'x86/apic', 'x86/asm', 'x86/cleanups', 'x86/debug', 'x86/kconfig', 'x86/mm', 'x86/ptrace', 'x86/setup' and 'x86/urgent'; commit 'v2.6.29-rc8' into x86/core
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index 85598f7..1602373 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -64,6 +64,7 @@
__initramfs_end = .;
#endif
. = ALIGN(4096);
+ __per_cpu_load = .;
__per_cpu_start = .;
*(.data.percpu.page_aligned)
*(.data.percpu)
diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S
index f45e4e5..3765efc 100644
--- a/arch/ia64/kernel/vmlinux.lds.S
+++ b/arch/ia64/kernel/vmlinux.lds.S
@@ -213,17 +213,9 @@
{ *(.data.cacheline_aligned) }
/* Per-cpu data: */
- percpu : { } :percpu
. = ALIGN(PERCPU_PAGE_SIZE);
- __phys_per_cpu_start = .;
- .data.percpu PERCPU_ADDR : AT(__phys_per_cpu_start - LOAD_OFFSET)
- {
- __per_cpu_start = .;
- *(.data.percpu.page_aligned)
- *(.data.percpu)
- *(.data.percpu.shared_aligned)
- __per_cpu_end = .;
- }
+ PERCPU_VADDR(PERCPU_ADDR, :percpu)
+ __phys_per_cpu_start = __per_cpu_load;
. = __phys_per_cpu_start + PERCPU_PAGE_SIZE; /* ensure percpu data fits
* into percpu page size
*/
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 295ccc5..67f07f4 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -181,14 +181,7 @@
__initramfs_end = .;
}
#endif
- . = ALIGN(PAGE_SIZE);
- .data.percpu : AT(ADDR(.data.percpu) - LOAD_OFFSET) {
- __per_cpu_start = .;
- *(.data.percpu.page_aligned)
- *(.data.percpu)
- *(.data.percpu.shared_aligned)
- __per_cpu_end = .;
- }
+ PERCPU(PAGE_SIZE)
. = ALIGN(8);
.machine.desc : AT(ADDR(.machine.desc) - LOAD_OFFSET) {
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index d571cc7..34bc3a8 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1132,7 +1132,7 @@
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
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 1836191..f05d8c9 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -153,34 +153,23 @@
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 @@
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 57a29fe..fb737ce 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -23,6 +23,7 @@
SVGA_MODE := -DSVGA_MODE=NORMAL_VGA
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
@@ -109,9 +110,11 @@
$(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 $(FDINITRD),initrd=initrd.img,)
@@ -120,7 +123,7 @@
sed -e 's|@OBJ@|$(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 '$(image_cmdline)' | \
@@ -128,10 +131,10 @@
if [ -f '$(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 $(obj)/fdimage ; sync
@@ -140,9 +143,9 @@
if [ -f '$(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 $(obj)/fdimage ; sync
@@ -151,9 +154,9 @@
if [ -f '$(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 \
@@ -163,7 +166,7 @@
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 ; \
@@ -174,12 +177,13 @@
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/include/asm/cpu_debug.h b/arch/x86/include/asm/cpu_debug.h
index d24d64f..56f1635 100755
--- a/arch/x86/include/asm/cpu_debug.h
+++ b/arch/x86/include/asm/cpu_debug.h
@@ -171,6 +171,17 @@
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 {
@@ -178,11 +189,6 @@
int init; /* Register index file */
};
-struct cpu_file_base {
- char *name; /* Register file name */
- unsigned flag; /* Register file flag */
-};
-
struct cpu_debug_range {
unsigned min; /* Register range min */
unsigned max; /* Register range max */
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 8f1d2fb..aee103b 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 7613950..ae85a8d 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -75,9 +75,9 @@
#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_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 5e79ca6..9c371e4 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -296,6 +296,8 @@
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 2ac0ab7..b617b11 100644
--- a/arch/x86/kernel/check.c
+++ b/arch/x86/kernel/check.c
@@ -83,7 +83,7 @@
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/addon_cpuid_features.c b/arch/x86/kernel/cpu/addon_cpuid_features.c
index 6882a73..8220ae6 100644
--- a/arch/x86/kernel/cpu/addon_cpuid_features.c
+++ b/arch/x86/kernel/cpu/addon_cpuid_features.c
@@ -29,7 +29,7 @@
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 f47df59..7e4a459 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -502,7 +502,7 @@
}
#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 89bfdd9..983e083 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -468,7 +468,7 @@
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 a1625f5..51b09c4 100644
--- a/arch/x86/kernel/cpu/centaur_64.c
+++ b/arch/x86/kernel/cpu/centaur_64.c
@@ -25,7 +25,7 @@
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 f886997..e2962cc 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/delay.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/string.h>
+#include <linux/delay.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/kgdb.h>
+#include <linux/smp.h>
+#include <linux/io.h>
+
+#include <asm/stackprotector.h>
#include <asm/mmu_context.h>
-#include <asm/mtrr.h>
-#include <asm/mce.h>
-#include <asm/pat.h>
-#include <asm/asm.h>
-#include <asm/numa.h>
-#include <asm/smp.h>
-#include <asm/cpu.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/smp.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 @@
#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 @@
* 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 @@
* 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 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);
+ unsigned long lo, hi;
- /* Disabling the serial number may affect the cpuid level */
- c->cpuid_level = cpuid_eax(0);
- }
+ 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 @@
u32 feature;
u32 level;
};
+
static const struct cpuid_dependent_feature __cpuinitconst
cpuid_dependent_features[] = {
{ X86_FEATURE_MWAIT, 0x00000005 },
@@ -243,7 +249,11 @@
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 @@
* 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 @@
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 @@
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 @@
#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 @@
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 */
}
}
@@ -438,28 +452,31 @@
if (smp_num_siblings == 1) {
printk(KERN_INFO "CPU: Hyper-Threading is disabled\n");
- } else if (smp_num_siblings > 1) {
-
- if (smp_num_siblings > nr_cpu_ids) {
- printk(KERN_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);
-
- smp_num_siblings = smp_num_siblings / c->x86_max_cores;
-
- index_msb = get_count_order(smp_num_siblings);
-
- 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);
+ goto out;
}
+ 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);
+
+ smp_num_siblings = smp_num_siblings / c->x86_max_cores;
+
+ index_msb = get_count_order(smp_num_siblings);
+
+ 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);
+
out:
if ((c->x86_max_cores * smp_num_siblings) > 1) {
printk(KERN_INFO "CPU: Physical Processor ID: %d\n",
@@ -473,8 +490,8 @@
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 @@
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 @@
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 @@
/* 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 @@
/* 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 @@
/* 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 @@
}
}
-#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 @@
{
#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 @@
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 @@
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 @@
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 @@
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 @@
/* 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 @@
}
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 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 int show_msr __cpuinitdata;
+
static __init int setup_show_msr(char *arg)
{
int num;
@@ -894,12 +931,14 @@
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 @@
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 @@
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 @@
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 @@
*/
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 @@
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 @@
* 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 @@
* 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.
@@ -1097,17 +1168,7 @@
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();
@@ -1128,7 +1189,8 @@
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);
@@ -1157,13 +1219,7 @@
__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:
@@ -1183,6 +1239,4 @@
xsave_init();
}
-
-
#endif
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index de4094a..9469ecb 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 @@
};
#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
index 9abbcbd..21c0cf8 100755
--- a/arch/x86/kernel/cpu/cpu_debug.c
+++ b/arch/x86/kernel/cpu/cpu_debug.c
@@ -11,6 +11,7 @@
#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>
@@ -40,41 +41,41 @@
static struct dentry *cpu_debugfs_dir;
static struct cpu_debug_base cpu_base[] = {
- { "mc", CPU_MC }, /* Machine Check */
- { "monitor", CPU_MONITOR }, /* Monitor */
- { "time", CPU_TIME }, /* Time */
- { "pmc", CPU_PMC }, /* Performance Monitor */
- { "platform", CPU_PLATFORM }, /* Platform */
- { "apic", CPU_APIC }, /* APIC */
- { "poweron", CPU_POWERON }, /* Power-on */
- { "control", CPU_CONTROL }, /* Control */
- { "features", CPU_FEATURES }, /* Features control */
- { "lastbranch", CPU_LBRANCH }, /* Last Branch */
- { "bios", CPU_BIOS }, /* BIOS */
- { "freq", CPU_FREQ }, /* Frequency */
- { "mtrr", CPU_MTRR }, /* MTRR */
- { "perf", CPU_PERF }, /* Performance */
- { "cache", CPU_CACHE }, /* Cache */
- { "sysenter", CPU_SYSENTER }, /* Sysenter */
- { "therm", CPU_THERM }, /* Thermal */
- { "misc", CPU_MISC }, /* Miscellaneous */
- { "debug", CPU_DEBUG }, /* Debug */
- { "pat", CPU_PAT }, /* PAT */
- { "vmx", CPU_VMX }, /* VMX */
- { "call", CPU_CALL }, /* System Call */
- { "base", CPU_BASE }, /* BASE Address */
- { "smm", CPU_SMM }, /* System mgmt mode */
- { "svm", CPU_SVM }, /*Secure Virtial Machine*/
- { "osvm", CPU_OSVM }, /* OS-Visible Workaround*/
- { "tss", CPU_TSS }, /* Task Stack Segment */
- { "cr", CPU_CR }, /* Control Registers */
- { "dt", CPU_DT }, /* Descriptor Table */
- { "registers", CPU_REG_ALL }, /* Select all Registers */
+ { "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 }, /* index */
- { "value", CPU_REG_ALL }, /* value */
+ { "index", CPU_REG_ALL, 0 },
+ { "value", CPU_REG_ALL, 1 },
};
/* Intel Registers Range */
@@ -608,9 +609,62 @@
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,
};
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index ffd0f5e..593171e 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -61,23 +61,23 @@
*/
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 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 @@
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 191117f..b09d4eb 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -54,6 +54,11 @@
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 @@
}
#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 7293508..c471eb1 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -32,7 +32,7 @@
};
/* 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 @@
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/transmeta.c b/arch/x86/kernel/cpu/transmeta.c
index 52b3fef..bb62b3e 100644
--- a/arch/x86/kernel/cpu/transmeta.c
+++ b/arch/x86/kernel/cpu/transmeta.c
@@ -98,7 +98,7 @@
#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 e777f79..fd2c37b 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/e820.c b/arch/x86/kernel/e820.c
index 508bec1..95b81c1 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -110,19 +110,25 @@
/*
* 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 @@
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 @@
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 @@
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 @@
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 @@
continue;
return addr;
}
- return -1UL;
+ return -1ULL;
}
/*
@@ -1034,13 +1046,22 @@
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 639ad98..335f049 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -250,7 +250,7 @@
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 @@
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 @@
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 @@
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 @@
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 @@
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 @@
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 899e893..c929add 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -442,8 +442,7 @@
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 @@
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 @@
#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 @@
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 @@
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 @@
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 @@
# 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 @@
# 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 7ba4621..a331ec3 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -368,6 +368,7 @@
END(save_rest)
/* save complete stack frame */
+ .pushsection .kprobes.text, "ax"
ENTRY(save_paranoid)
XCPT_FRAME 1 RDI+8
cld
@@ -396,6 +397,7 @@
1: ret
CFI_ENDPROC
END(save_paranoid)
+ .popsection
/*
* A newly forked process directly context switches into this address.
@@ -416,7 +418,6 @@
GET_THREAD_INFO(%rcx)
- CFI_REMEMBER_STATE
RESTORE_REST
testl $3, CS-ARGOFFSET(%rsp) # from kernel_thread?
@@ -428,7 +429,6 @@
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/irq.c b/arch/x86/kernel/irq.c
index b864341..b8ac3b6 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -45,16 +45,16 @@
/*
* /proc/interrupts printing:
*/
-static int show_other_interrupts(struct seq_file *p)
+static int show_other_interrupts(struct seq_file *p, int prec)
{
int j;
- seq_printf(p, "NMI: ");
+ seq_printf(p, "%*s: ", prec, "NMI");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->__nmi_count);
seq_printf(p, " Non-maskable interrupts\n");
#ifdef CONFIG_X86_LOCAL_APIC
- seq_printf(p, "LOC: ");
+ seq_printf(p, "%*s: ", prec, "LOC");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->apic_timer_irqs);
seq_printf(p, " Local timer interrupts\n");
@@ -66,40 +66,40 @@
seq_printf(p, " Platform interrupts\n");
}
#ifdef CONFIG_SMP
- seq_printf(p, "RES: ");
+ seq_printf(p, "%*s: ", prec, "RES");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->irq_resched_count);
seq_printf(p, " Rescheduling interrupts\n");
- seq_printf(p, "CAL: ");
+ seq_printf(p, "%*s: ", prec, "CAL");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->irq_call_count);
seq_printf(p, " Function call interrupts\n");
- seq_printf(p, "TLB: ");
+ seq_printf(p, "%*s: ", prec, "TLB");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->irq_tlb_count);
seq_printf(p, " TLB shootdowns\n");
#endif
#ifdef CONFIG_X86_MCE
- seq_printf(p, "TRM: ");
+ seq_printf(p, "%*s: ", prec, "TRM");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->irq_thermal_count);
seq_printf(p, " Thermal event interrupts\n");
# ifdef CONFIG_X86_64
- seq_printf(p, "THR: ");
+ seq_printf(p, "%*s: ", prec, "THR");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->irq_threshold_count);
seq_printf(p, " Threshold APIC interrupts\n");
# endif
#endif
#ifdef CONFIG_X86_LOCAL_APIC
- seq_printf(p, "SPU: ");
+ seq_printf(p, "%*s: ", prec, "SPU");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->irq_spurious_count);
seq_printf(p, " Spurious interrupts\n");
#endif
- seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count));
+ seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count));
#if defined(CONFIG_X86_IO_APIC)
- seq_printf(p, "MIS: %10u\n", atomic_read(&irq_mis_count));
+ seq_printf(p, "%*s: %10u\n", prec, "MIS", atomic_read(&irq_mis_count));
#endif
return 0;
}
@@ -107,19 +107,22 @@
int show_interrupts(struct seq_file *p, void *v)
{
unsigned long flags, any_count = 0;
- int i = *(loff_t *) v, j;
+ int i = *(loff_t *) v, j, prec;
struct irqaction *action;
struct irq_desc *desc;
if (i > nr_irqs)
return 0;
+ for (prec = 3, j = 1000; prec < 10 && j <= nr_irqs; ++prec)
+ j *= 10;
+
if (i == nr_irqs)
- return show_other_interrupts(p);
+ return show_other_interrupts(p, prec);
/* print header */
if (i == 0) {
- seq_printf(p, " ");
+ seq_printf(p, "%*s", prec + 8, "");
for_each_online_cpu(j)
seq_printf(p, "CPU%-8d", j);
seq_putc(p, '\n');
@@ -140,7 +143,7 @@
if (!action && !any_count)
goto out;
- seq_printf(p, "%3d: ", i);
+ seq_printf(p, "%*d: ", prec, i);
#ifndef CONFIG_SMP
seq_printf(p, "%10u ", kstat_irqs(i));
#else
diff --git a/arch/x86/kernel/mmconf-fam10h_64.c b/arch/x86/kernel/mmconf-fam10h_64.c
index 666e43d..712d15f 100644
--- a/arch/x86/kernel/mmconf-fam10h_64.c
+++ b/arch/x86/kernel/mmconf-fam10h_64.c
@@ -226,7 +226,7 @@
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 e819240..47673e0 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -890,12 +890,12 @@
#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 @@
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 3d9672e..1937871 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -685,9 +685,8 @@
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/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index efa615f..400331b 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -233,8 +233,8 @@
"%zu bytes\n", vm.addr, static_size);
ret = pcpu_setup_first_chunk(pcpur_get_page, static_size,
- PERCPU_FIRST_CHUNK_RESERVE,
- PMD_SIZE, dyn_size, vm.addr, NULL);
+ PERCPU_FIRST_CHUNK_RESERVE, dyn_size,
+ PMD_SIZE, vm.addr, NULL);
goto out_free_ar;
enomem:
@@ -257,31 +257,13 @@
* Embedding allocator
*
* The first chunk is sized to just contain the static area plus
- * module and dynamic reserves, 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. Note that if the needed size is smaller than the minimum
- * unit size, the leftover is returned to the bootmem allocator.
+ * 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_size __initdata;
-static size_t pcpue_unit_size __initdata;
-
-static struct page * __init pcpue_get_page(unsigned int cpu, int pageno)
-{
- size_t off = (size_t)pageno << PAGE_SHIFT;
-
- if (off >= pcpue_size)
- return NULL;
-
- return virt_to_page(pcpue_ptr + cpu * pcpue_unit_size + off);
-}
-
static ssize_t __init setup_pcpu_embed(size_t static_size)
{
- unsigned int cpu;
- size_t dyn_size;
+ size_t reserve = PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE;
/*
* If large page isn't supported, there's no benefit in doing
@@ -291,33 +273,8 @@
if (!cpu_has_pse || pcpu_need_numa())
return -EINVAL;
- /* allocate and copy */
- pcpue_size = PFN_ALIGN(static_size + PERCPU_MODULE_RESERVE +
- PERCPU_DYNAMIC_RESERVE);
- pcpue_unit_size = max_t(size_t, pcpue_size, PCPU_MIN_UNIT_SIZE);
- dyn_size = pcpue_size - static_size - PERCPU_FIRST_CHUNK_RESERVE;
-
- pcpue_ptr = pcpu_alloc_bootmem(0, num_possible_cpus() * pcpue_unit_size,
- PAGE_SIZE);
- if (!pcpue_ptr)
- return -ENOMEM;
-
- for_each_possible_cpu(cpu) {
- void *ptr = pcpue_ptr + cpu * pcpue_unit_size;
-
- free_bootmem(__pa(ptr + pcpue_size),
- pcpue_unit_size - pcpue_size);
- memcpy(ptr, __per_cpu_load, static_size);
- }
-
- /* we're ready, commit */
- pr_info("PERCPU: Embedded %zu pages at %p, static data %zu bytes\n",
- pcpue_size >> PAGE_SHIFT, pcpue_ptr, static_size);
-
- return pcpu_setup_first_chunk(pcpue_get_page, static_size,
- PERCPU_FIRST_CHUNK_RESERVE,
- pcpue_unit_size, dyn_size,
- pcpue_ptr, NULL);
+ return pcpu_embed_first_chunk(static_size, PERCPU_FIRST_CHUNK_RESERVE,
+ reserve - PERCPU_FIRST_CHUNK_RESERVE, -1);
}
/*
@@ -375,8 +332,8 @@
pcpu4k_nr_static_pages, static_size);
ret = pcpu_setup_first_chunk(pcpu4k_get_page, static_size,
- PERCPU_FIRST_CHUNK_RESERVE, -1, -1, NULL,
- pcpu4k_populate_pte);
+ PERCPU_FIRST_CHUNK_RESERVE, -1,
+ -1, NULL, pcpu4k_populate_pte);
goto out_free_ar;
enomem:
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index c22981f..ad5441e 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 @@
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 f256e73..522db5e 100644
--- a/arch/x86/mm/highmem_32.c
+++ b/arch/x86/mm/highmem_32.c
@@ -121,24 +121,8 @@
pagefault_enable();
}
-void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot)
-{
- enum fixed_addresses idx;
- unsigned long vaddr;
-
- pagefault_disable();
-
- debug_kmap_atomic_prot(type);
-
- 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;
-}
-
-/* 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)
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 15219e0..fd3da1d 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -94,9 +94,9 @@
#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)
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index 592984e..6e60ba6 100644
--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@@ -32,7 +32,23 @@
}
EXPORT_SYMBOL_GPL(is_io_mapping_possible);
-/* Map 'pfn' using fixed map 'type' and protections '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)
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index aca924a..55e127f 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 @@
#else
-static inline int phys_addr_valid(unsigned long addr)
-{
- return 1;
-}
-
#ifdef CONFIG_DEBUG_VIRTUAL
unsigned long __phys_addr(unsigned long x)
{
@@ -488,7 +487,12 @@
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)
{
@@ -503,6 +507,8 @@
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)];
}
@@ -520,8 +526,14 @@
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
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 2ed3715..640339e 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -677,10 +677,11 @@
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 82d22fc..8c362b9 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -90,7 +90,7 @@
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 @@
}
#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 7d388d5..9c49919 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -356,7 +356,7 @@
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 @@
*/
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 = {
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 065cdf8..b1ea37f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -104,6 +104,7 @@
#define VM_CAN_NONLINEAR 0x08000000 /* Has ->fault & does nonlinear pages */
#define VM_MIXEDMAP 0x10000000 /* Can contain "struct page" and pure PFN pages */
#define VM_SAO 0x20000000 /* Strong Access Ordering (powerpc) */
+#define VM_PFN_AT_MMAP 0x40000000 /* PFNMAP vma that is fully mapped at mmap time */
#ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */
#define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS
@@ -145,7 +146,7 @@
*/
static inline int is_linear_pfn_mapping(struct vm_area_struct *vma)
{
- return ((vma->vm_flags & VM_PFNMAP) && vma->vm_pgoff);
+ return (vma->vm_flags & VM_PFN_AT_MMAP);
}
static inline int is_pfn_mapping(struct vm_area_struct *vma)
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 54a968b..ee5615d 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -107,10 +107,14 @@
extern size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn,
size_t static_size, size_t reserved_size,
- ssize_t unit_size, ssize_t dyn_size,
+ ssize_t dyn_size, ssize_t unit_size,
void *base_addr,
pcpu_populate_pte_fn_t populate_pte_fn);
+extern ssize_t __init pcpu_embed_first_chunk(
+ size_t static_size, size_t reserved_size,
+ ssize_t dyn_size, ssize_t unit_size);
+
/*
* Use this to get to a cpu's version of the per-cpu object
* dynamically allocated. Non-atomic access to the current CPU's
diff --git a/kernel/sched.c b/kernel/sched.c
index 0a76d0b..61e6356 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -9599,10 +9599,11 @@
cpu = task_cpu(tsk);
ca = task_ca(tsk);
- for (; ca; ca = ca->parent) {
+ do {
u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
*cpuusage += cputime;
- }
+ ca = ca->parent;
+ } while (ca);
}
struct cgroup_subsys cpuacct_subsys = {
diff --git a/mm/allocpercpu.c b/mm/allocpercpu.c
index 3653c57..1882923 100644
--- a/mm/allocpercpu.c
+++ b/mm/allocpercpu.c
@@ -120,7 +120,7 @@
* on it. Larger alignment should only be used for module
* percpu sections on SMP for which this path isn't used.
*/
- WARN_ON_ONCE(align > __alignof__(unsigned long long));
+ WARN_ON_ONCE(align > SMP_CACHE_BYTES);
if (unlikely(!pdata))
return NULL;
diff --git a/mm/memory.c b/mm/memory.c
index baa999e..2032ad2 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1665,9 +1665,10 @@
* behaviour that some programs depend on. We mark the "original"
* un-COW'ed pages by matching them up with "vma->vm_pgoff".
*/
- if (addr == vma->vm_start && end == vma->vm_end)
+ if (addr == vma->vm_start && end == vma->vm_end) {
vma->vm_pgoff = pfn;
- else if (is_cow_mapping(vma->vm_flags))
+ vma->vm_flags |= VM_PFN_AT_MMAP;
+ } else if (is_cow_mapping(vma->vm_flags))
return -EINVAL;
vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
@@ -1679,6 +1680,7 @@
* needed from higher level routine calling unmap_vmas
*/
vma->vm_flags &= ~(VM_IO | VM_RESERVED | VM_PFNMAP);
+ vma->vm_flags &= ~VM_PFN_AT_MMAP;
return -EINVAL;
}
diff --git a/mm/percpu.c b/mm/percpu.c
index bfe6a3a..1aa5d8f 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -46,7 +46,8 @@
* - define CONFIG_HAVE_DYNAMIC_PER_CPU_AREA
*
* - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate
- * regular address to percpu pointer and back
+ * regular address to percpu pointer and back if they need to be
+ * different from the default
*
* - use pcpu_setup_first_chunk() during percpu area initialization to
* setup the first chunk containing the kernel static percpu area
@@ -67,11 +68,24 @@
#include <linux/workqueue.h>
#include <asm/cacheflush.h>
+#include <asm/sections.h>
#include <asm/tlbflush.h>
#define PCPU_SLOT_BASE_SHIFT 5 /* 1-31 shares the same slot */
#define PCPU_DFL_MAP_ALLOC 16 /* start a map with 16 ents */
+/* default addr <-> pcpu_ptr mapping, override in asm/percpu.h if necessary */
+#ifndef __addr_to_pcpu_ptr
+#define __addr_to_pcpu_ptr(addr) \
+ (void *)((unsigned long)(addr) - (unsigned long)pcpu_base_addr \
+ + (unsigned long)__per_cpu_start)
+#endif
+#ifndef __pcpu_ptr_to_addr
+#define __pcpu_ptr_to_addr(ptr) \
+ (void *)((unsigned long)(ptr) + (unsigned long)pcpu_base_addr \
+ - (unsigned long)__per_cpu_start)
+#endif
+
struct pcpu_chunk {
struct list_head list; /* linked to pcpu_slot lists */
struct rb_node rb_node; /* key is chunk->vm->addr */
@@ -1013,8 +1027,8 @@
* @get_page_fn: callback to fetch page pointer
* @static_size: the size of static percpu area in bytes
* @reserved_size: the size of reserved percpu area in bytes
- * @unit_size: unit size in bytes, must be multiple of PAGE_SIZE, -1 for auto
* @dyn_size: free size for dynamic allocation in bytes, -1 for auto
+ * @unit_size: unit size in bytes, must be multiple of PAGE_SIZE, -1 for auto
* @base_addr: mapped address, NULL for auto
* @populate_pte_fn: callback to allocate pagetable, NULL if unnecessary
*
@@ -1039,14 +1053,14 @@
* limited offset range for symbol relocations to guarantee module
* percpu symbols fall inside the relocatable range.
*
+ * @dyn_size, if non-negative, determines the number of bytes
+ * available for dynamic allocation in the first chunk. Specifying
+ * non-negative value makes percpu leave alone the area beyond
+ * @static_size + @reserved_size + @dyn_size.
+ *
* @unit_size, if non-negative, specifies unit size and must be
* aligned to PAGE_SIZE and equal to or larger than @static_size +
- * @reserved_size + @dyn_size.
- *
- * @dyn_size, if non-negative, limits the number of bytes available
- * for dynamic allocation in the first chunk. Specifying non-negative
- * value make percpu leave alone the area beyond @static_size +
- * @reserved_size + @dyn_size.
+ * @reserved_size + if non-negative, @dyn_size.
*
* Non-null @base_addr means that the caller already allocated virtual
* region for the first chunk and mapped it. percpu must not mess
@@ -1069,12 +1083,14 @@
*/
size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn,
size_t static_size, size_t reserved_size,
- ssize_t unit_size, ssize_t dyn_size,
+ ssize_t dyn_size, ssize_t unit_size,
void *base_addr,
pcpu_populate_pte_fn_t populate_pte_fn)
{
static struct vm_struct first_vm;
static int smap[2], dmap[2];
+ size_t size_sum = static_size + reserved_size +
+ (dyn_size >= 0 ? dyn_size : 0);
struct pcpu_chunk *schunk, *dchunk = NULL;
unsigned int cpu;
int nr_pages;
@@ -1085,20 +1101,18 @@
ARRAY_SIZE(dmap) >= PCPU_DFL_MAP_ALLOC);
BUG_ON(!static_size);
if (unit_size >= 0) {
- BUG_ON(unit_size < static_size + reserved_size +
- (dyn_size >= 0 ? dyn_size : 0));
+ BUG_ON(unit_size < size_sum);
BUG_ON(unit_size & ~PAGE_MASK);
- } else {
- BUG_ON(dyn_size >= 0);
+ BUG_ON(unit_size < PCPU_MIN_UNIT_SIZE);
+ } else
BUG_ON(base_addr);
- }
BUG_ON(base_addr && populate_pte_fn);
if (unit_size >= 0)
pcpu_unit_pages = unit_size >> PAGE_SHIFT;
else
pcpu_unit_pages = max_t(int, PCPU_MIN_UNIT_SIZE >> PAGE_SHIFT,
- PFN_UP(static_size + reserved_size));
+ PFN_UP(size_sum));
pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT;
pcpu_chunk_size = num_possible_cpus() * pcpu_unit_size;
@@ -1224,3 +1238,89 @@
pcpu_base_addr = (void *)pcpu_chunk_addr(schunk, 0, 0);
return pcpu_unit_size;
}
+
+/*
+ * Embedding first chunk setup helper.
+ */
+static void *pcpue_ptr __initdata;
+static size_t pcpue_size __initdata;
+static size_t pcpue_unit_size __initdata;
+
+static struct page * __init pcpue_get_page(unsigned int cpu, int pageno)
+{
+ size_t off = (size_t)pageno << PAGE_SHIFT;
+
+ if (off >= pcpue_size)
+ return NULL;
+
+ return virt_to_page(pcpue_ptr + cpu * pcpue_unit_size + off);
+}
+
+/**
+ * pcpu_embed_first_chunk - embed the first percpu chunk into bootmem
+ * @static_size: the size of static percpu area in bytes
+ * @reserved_size: the size of reserved percpu area in bytes
+ * @dyn_size: free size for dynamic allocation in bytes, -1 for auto
+ * @unit_size: unit size in bytes, must be multiple of PAGE_SIZE, -1 for auto
+ *
+ * This is a helper to ease setting up embedded first percpu chunk and
+ * can be called where pcpu_setup_first_chunk() is expected.
+ *
+ * If this function is used to setup the first chunk, it is 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 mapping which often uses larger
+ * page size.
+ *
+ * When @dyn_size is positive, dynamic area might be larger than
+ * specified to fill page alignment. Also, when @dyn_size is auto,
+ * @dyn_size does not fill the whole first chunk but only what's
+ * necessary for page alignment after static and reserved areas.
+ *
+ * If the needed size is smaller than the minimum or specified unit
+ * size, the leftover is returned to the bootmem allocator.
+ *
+ * RETURNS:
+ * The determined pcpu_unit_size which can be used to initialize
+ * percpu access on success, -errno on failure.
+ */
+ssize_t __init pcpu_embed_first_chunk(size_t static_size, size_t reserved_size,
+ ssize_t dyn_size, ssize_t unit_size)
+{
+ unsigned int cpu;
+
+ /* determine parameters and allocate */
+ pcpue_size = PFN_ALIGN(static_size + reserved_size +
+ (dyn_size >= 0 ? dyn_size : 0));
+ if (dyn_size != 0)
+ dyn_size = pcpue_size - static_size - reserved_size;
+
+ if (unit_size >= 0) {
+ BUG_ON(unit_size < pcpue_size);
+ pcpue_unit_size = unit_size;
+ } else
+ pcpue_unit_size = max_t(size_t, pcpue_size, PCPU_MIN_UNIT_SIZE);
+
+ pcpue_ptr = __alloc_bootmem_nopanic(
+ num_possible_cpus() * pcpue_unit_size,
+ PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
+ if (!pcpue_ptr)
+ return -ENOMEM;
+
+ /* return the leftover and copy */
+ for_each_possible_cpu(cpu) {
+ void *ptr = pcpue_ptr + cpu * pcpue_unit_size;
+
+ free_bootmem(__pa(ptr + pcpue_size),
+ pcpue_unit_size - pcpue_size);
+ memcpy(ptr, __per_cpu_load, static_size);
+ }
+
+ /* we're ready, commit */
+ pr_info("PERCPU: Embedded %zu pages at %p, static data %zu bytes\n",
+ pcpue_size >> PAGE_SHIFT, pcpue_ptr, static_size);
+
+ return pcpu_setup_first_chunk(pcpue_get_page, static_size,
+ reserved_size, dyn_size,
+ pcpue_unit_size, pcpue_ptr, NULL);
+}