summaryrefslogtreecommitdiffstats
path: root/arch/x86_64/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86_64/kernel')
-rw-r--r--arch/x86_64/kernel/Makefile7
-rw-r--r--arch/x86_64/kernel/acpi/sleep.c24
-rw-r--r--arch/x86_64/kernel/acpi/wakeup.S286
-rw-r--r--arch/x86_64/kernel/aperture.c5
-rw-r--r--arch/x86_64/kernel/apic.c35
-rw-r--r--arch/x86_64/kernel/asm-offsets.c10
-rw-r--r--arch/x86_64/kernel/bugs.c21
-rw-r--r--arch/x86_64/kernel/e820.c5
-rw-r--r--arch/x86_64/kernel/early-quirks.c13
-rw-r--r--arch/x86_64/kernel/early_printk.c5
-rw-r--r--arch/x86_64/kernel/entry.S5
-rw-r--r--arch/x86_64/kernel/functionlist1284
-rw-r--r--arch/x86_64/kernel/genapic.c104
-rw-r--r--arch/x86_64/kernel/genapic_cluster.c137
-rw-r--r--arch/x86_64/kernel/genapic_flat.c25
-rw-r--r--arch/x86_64/kernel/head.S340
-rw-r--r--arch/x86_64/kernel/head64.c41
-rw-r--r--arch/x86_64/kernel/io_apic.c31
-rw-r--r--arch/x86_64/kernel/ioport.c1
-rw-r--r--arch/x86_64/kernel/machine_kexec.c14
-rw-r--r--arch/x86_64/kernel/mce.c32
-rw-r--r--arch/x86_64/kernel/mpparse.c2
-rw-r--r--arch/x86_64/kernel/nmi.c678
-rw-r--r--arch/x86_64/kernel/pci-calgary.c2
-rw-r--r--arch/x86_64/kernel/pci-gart.c2
-rw-r--r--arch/x86_64/kernel/pci-nommu.c2
-rw-r--r--arch/x86_64/kernel/pci-swiotlb.c2
-rw-r--r--arch/x86_64/kernel/process.c12
-rw-r--r--arch/x86_64/kernel/setup.c35
-rw-r--r--arch/x86_64/kernel/setup64.c5
-rw-r--r--arch/x86_64/kernel/signal.c6
-rw-r--r--arch/x86_64/kernel/smp.c30
-rw-r--r--arch/x86_64/kernel/smpboot.c47
-rw-r--r--arch/x86_64/kernel/suspend.c19
-rw-r--r--arch/x86_64/kernel/suspend_asm.S7
-rw-r--r--arch/x86_64/kernel/syscall.c1
-rw-r--r--arch/x86_64/kernel/time.c71
-rw-r--r--arch/x86_64/kernel/trampoline.S123
-rw-r--r--arch/x86_64/kernel/traps.c34
-rw-r--r--arch/x86_64/kernel/tsc.c17
-rw-r--r--arch/x86_64/kernel/tsc_sync.c4
-rw-r--r--arch/x86_64/kernel/verify_cpu.S119
-rw-r--r--arch/x86_64/kernel/vmlinux.lds.S20
-rw-r--r--arch/x86_64/kernel/vsyscall.c68
44 files changed, 934 insertions, 2797 deletions
diff --git a/arch/x86_64/kernel/Makefile b/arch/x86_64/kernel/Makefile
index bb47e86f3d0..4d94c51803d 100644
--- a/arch/x86_64/kernel/Makefile
+++ b/arch/x86_64/kernel/Makefile
@@ -8,7 +8,8 @@ obj-y := process.o signal.o entry.o traps.o irq.o \
ptrace.o time.o ioport.o ldt.o setup.o i8259.o sys_x86_64.o \
x8664_ksyms.o i387.o syscall.o vsyscall.o \
setup64.o bootflag.o e820.o reboot.o quirks.o i8237.o \
- pci-dma.o pci-nommu.o alternative.o hpet.o tsc.o
+ pci-dma.o pci-nommu.o alternative.o hpet.o tsc.o bugs.o \
+ perfctr-watchdog.o
obj-$(CONFIG_STACKTRACE) += stacktrace.o
obj-$(CONFIG_X86_MCE) += mce.o therm_throt.o
@@ -21,8 +22,7 @@ obj-$(CONFIG_MICROCODE) += microcode.o
obj-$(CONFIG_X86_CPUID) += cpuid.o
obj-$(CONFIG_SMP) += smp.o smpboot.o trampoline.o tsc_sync.o
obj-y += apic.o nmi.o
-obj-y += io_apic.o mpparse.o \
- genapic.o genapic_cluster.o genapic_flat.o
+obj-y += io_apic.o mpparse.o genapic.o genapic_flat.o
obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o crash.o
obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
obj-$(CONFIG_PM) += suspend.o
@@ -58,3 +58,4 @@ i8237-y += ../../i386/kernel/i8237.o
msr-$(subst m,y,$(CONFIG_X86_MSR)) += ../../i386/kernel/msr.o
alternative-y += ../../i386/kernel/alternative.o
pcspeaker-y += ../../i386/kernel/pcspeaker.o
+perfctr-watchdog-y += ../../i386/kernel/cpu/perfctr-watchdog.o
diff --git a/arch/x86_64/kernel/acpi/sleep.c b/arch/x86_64/kernel/acpi/sleep.c
index e1548fbe95a..195b7034a14 100644
--- a/arch/x86_64/kernel/acpi/sleep.c
+++ b/arch/x86_64/kernel/acpi/sleep.c
@@ -60,19 +60,6 @@ extern char wakeup_start, wakeup_end;
extern unsigned long acpi_copy_wakeup_routine(unsigned long);
-static pgd_t low_ptr;
-
-static void init_low_mapping(void)
-{
- pgd_t *slot0 = pgd_offset(current->mm, 0UL);
- low_ptr = *slot0;
- /* FIXME: We're playing with the current task's page tables here, which
- * is potentially dangerous on SMP systems.
- */
- set_pgd(slot0, *pgd_offset(current->mm, PAGE_OFFSET));
- local_flush_tlb();
-}
-
/**
* acpi_save_state_mem - save kernel state
*
@@ -81,8 +68,6 @@ static void init_low_mapping(void)
*/
int acpi_save_state_mem(void)
{
- init_low_mapping();
-
memcpy((void *)acpi_wakeup_address, &wakeup_start,
&wakeup_end - &wakeup_start);
acpi_copy_wakeup_routine(acpi_wakeup_address);
@@ -95,8 +80,6 @@ int acpi_save_state_mem(void)
*/
void acpi_restore_state_mem(void)
{
- set_pgd(pgd_offset(current->mm, 0UL), low_ptr);
- local_flush_tlb();
}
/**
@@ -109,10 +92,11 @@ void acpi_restore_state_mem(void)
*/
void __init acpi_reserve_bootmem(void)
{
- acpi_wakeup_address = (unsigned long)alloc_bootmem_low(PAGE_SIZE);
- if ((&wakeup_end - &wakeup_start) > PAGE_SIZE)
+ acpi_wakeup_address = (unsigned long)alloc_bootmem_low(PAGE_SIZE*2);
+ if ((&wakeup_end - &wakeup_start) > (PAGE_SIZE*2))
printk(KERN_CRIT
- "ACPI: Wakeup code way too big, will crash on attempt to suspend\n");
+ "ACPI: Wakeup code way too big, will crash on attempt"
+ " to suspend\n");
}
static int __init acpi_sleep_setup(char *str)
diff --git a/arch/x86_64/kernel/acpi/wakeup.S b/arch/x86_64/kernel/acpi/wakeup.S
index 185faa911db..8550a6ffa27 100644
--- a/arch/x86_64/kernel/acpi/wakeup.S
+++ b/arch/x86_64/kernel/acpi/wakeup.S
@@ -1,6 +1,7 @@
.text
#include <linux/linkage.h>
#include <asm/segment.h>
+#include <asm/pgtable.h>
#include <asm/page.h>
#include <asm/msr.h>
@@ -30,22 +31,28 @@ wakeup_code:
cld
# setup data segment
movw %cs, %ax
- movw %ax, %ds # Make ds:0 point to wakeup_start
+ movw %ax, %ds # Make ds:0 point to wakeup_start
movw %ax, %ss
- mov $(wakeup_stack - wakeup_code), %sp # Private stack is needed for ASUS board
+ # Private stack is needed for ASUS board
+ mov $(wakeup_stack - wakeup_code), %sp
- pushl $0 # Kill any dangerous flags
+ pushl $0 # Kill any dangerous flags
popfl
movl real_magic - wakeup_code, %eax
cmpl $0x12345678, %eax
jne bogus_real_magic
+ call verify_cpu # Verify the cpu supports long
+ # mode
+ testl %eax, %eax
+ jnz no_longmode
+
testl $1, video_flags - wakeup_code
jz 1f
lcall $0xc000,$3
movw %cs, %ax
- movw %ax, %ds # Bios might have played with that
+ movw %ax, %ds # Bios might have played with that
movw %ax, %ss
1:
@@ -61,12 +68,15 @@ wakeup_code:
movb $0xa2, %al ; outb %al, $0x80
- lidt %ds:idt_48a - wakeup_code
- xorl %eax, %eax
- movw %ds, %ax # (Convert %ds:gdt to a linear ptr)
- shll $4, %eax
- addl $(gdta - wakeup_code), %eax
- movl %eax, gdt_48a +2 - wakeup_code
+ mov %ds, %ax # Find 32bit wakeup_code addr
+ movzx %ax, %esi # (Convert %ds:gdt to a liner ptr)
+ shll $4, %esi
+ # Fix up the vectors
+ addl %esi, wakeup_32_vector - wakeup_code
+ addl %esi, wakeup_long64_vector - wakeup_code
+ addl %esi, gdt_48a + 2 - wakeup_code # Fixup the gdt pointer
+
+ lidtl %ds:idt_48a - wakeup_code
lgdtl %ds:gdt_48a - wakeup_code # load gdt with whatever is
# appropriate
@@ -75,86 +85,63 @@ wakeup_code:
jmp 1f
1:
- .byte 0x66, 0xea # prefix + jmpi-opcode
- .long wakeup_32 - __START_KERNEL_map
- .word __KERNEL_CS
+ ljmpl *(wakeup_32_vector - wakeup_code)
+
+ .balign 4
+wakeup_32_vector:
+ .long wakeup_32 - wakeup_code
+ .word __KERNEL32_CS, 0
.code32
wakeup_32:
# Running in this code, but at low address; paging is not yet turned on.
movb $0xa5, %al ; outb %al, $0x80
- /* Check if extended functions are implemented */
- movl $0x80000000, %eax
- cpuid
- cmpl $0x80000000, %eax
- jbe bogus_cpu
- wbinvd
- mov $0x80000001, %eax
- cpuid
- btl $29, %edx
- jnc bogus_cpu
- movl %edx,%edi
-
- movw $__KERNEL_DS, %ax
- movw %ax, %ds
- movw %ax, %es
- movw %ax, %fs
- movw %ax, %gs
-
- movw $__KERNEL_DS, %ax
- movw %ax, %ss
+ movl $__KERNEL_DS, %eax
+ movl %eax, %ds
- mov $(wakeup_stack - __START_KERNEL_map), %esp
- movl saved_magic - __START_KERNEL_map, %eax
- cmpl $0x9abcdef0, %eax
- jne bogus_32_magic
+ movw $0x0e00 + 'i', %ds:(0xb8012)
+ movb $0xa8, %al ; outb %al, $0x80;
/*
* Prepare for entering 64bits mode
*/
- /* Enable PAE mode and PGE */
+ /* Enable PAE */
xorl %eax, %eax
btsl $5, %eax
- btsl $7, %eax
movl %eax, %cr4
/* Setup early boot stage 4 level pagetables */
- movl $(wakeup_level4_pgt - __START_KERNEL_map), %eax
+ leal (wakeup_level4_pgt - wakeup_code)(%esi), %eax
movl %eax, %cr3
- /* Setup EFER (Extended Feature Enable Register) */
- movl $MSR_EFER, %ecx
- rdmsr
- /* Fool rdmsr and reset %eax to avoid dependences */
- xorl %eax, %eax
+ /* Check if nx is implemented */
+ movl $0x80000001, %eax
+ cpuid
+ movl %edx,%edi
+
/* Enable Long Mode */
+ xorl %eax, %eax
btsl $_EFER_LME, %eax
- /* Enable System Call */
- btsl $_EFER_SCE, %eax
- /* No Execute supported? */
+ /* No Execute supported? */
btl $20,%edi
jnc 1f
btsl $_EFER_NX, %eax
-1:
/* Make changes effective */
+1: movl $MSR_EFER, %ecx
+ xorl %edx, %edx
wrmsr
- wbinvd
xorl %eax, %eax
btsl $31, %eax /* Enable paging and in turn activate Long Mode */
btsl $0, %eax /* Enable protected mode */
- btsl $1, %eax /* Enable MP */
- btsl $4, %eax /* Enable ET */
- btsl $5, %eax /* Enable NE */
- btsl $16, %eax /* Enable WP */
- btsl $18, %eax /* Enable AM */
/* Make changes effective */
movl %eax, %cr0
+
/* At this point:
CR4.PAE must be 1
CS.L must be 0
@@ -162,11 +149,6 @@ wakeup_32:
Next instruction must be a branch
This must be on identity-mapped page
*/
- jmp reach_compatibility_mode
-reach_compatibility_mode:
- movw $0x0e00 + 'i', %ds:(0xb8012)
- movb $0xa8, %al ; outb %al, $0x80;
-
/*
* At this point we're in long mode but in 32bit compatibility mode
* with EFER.LME = 1, CS.L = 0, CS.D = 1 (and in turn
@@ -174,24 +156,19 @@ reach_compatibility_mode:
* the new gdt/idt that has __KERNEL_CS with CS.L = 1.
*/
- movw $0x0e00 + 'n', %ds:(0xb8014)
- movb $0xa9, %al ; outb %al, $0x80
-
- /* Load new GDT with the 64bit segment using 32bit descriptor */
- movl $(pGDT32 - __START_KERNEL_map), %eax
- lgdt (%eax)
-
- movl $(wakeup_jumpvector - __START_KERNEL_map), %eax
/* Finally jump in 64bit mode */
- ljmp *(%eax)
+ ljmp *(wakeup_long64_vector - wakeup_code)(%esi)
-wakeup_jumpvector:
- .long wakeup_long64 - __START_KERNEL_map
- .word __KERNEL_CS
+ .balign 4
+wakeup_long64_vector:
+ .long wakeup_long64 - wakeup_code
+ .word __KERNEL_CS, 0
.code64
- /* Hooray, we are in Long 64-bit mode (but still running in low memory) */
+ /* Hooray, we are in Long 64-bit mode (but still running in
+ * low memory)
+ */
wakeup_long64:
/*
* We must switch to a new descriptor in kernel space for the GDT
@@ -199,7 +176,15 @@ wakeup_long64:
* addresses where we're currently running on. We have to do that here
* because in 32bit we couldn't load a 64bit linear address.
*/
- lgdt cpu_gdt_descr - __START_KERNEL_map
+ lgdt cpu_gdt_descr
+
+ movw $0x0e00 + 'n', %ds:(0xb8014)
+ movb $0xa9, %al ; outb %al, $0x80
+
+ movq saved_magic, %rax
+ movq $0x123456789abcdef0, %rdx
+ cmpq %rdx, %rax
+ jne bogus_64_magic
movw $0x0e00 + 'u', %ds:(0xb8016)
@@ -211,75 +196,58 @@ wakeup_long64:
movw %ax, %es
movw %ax, %fs
movw %ax, %gs
- movq saved_esp, %rsp
+ movq saved_rsp, %rsp
movw $0x0e00 + 'x', %ds:(0xb8018)
- movq saved_ebx, %rbx
- movq saved_edi, %rdi
- movq saved_esi, %rsi
- movq saved_ebp, %rbp
+ movq saved_rbx, %rbx
+ movq saved_rdi, %rdi
+ movq saved_rsi, %rsi
+ movq saved_rbp, %rbp
movw $0x0e00 + '!', %ds:(0xb801a)
- movq saved_eip, %rax
+ movq saved_rip, %rax
jmp *%rax
.code32
.align 64
gdta:
+ /* Its good to keep gdt in sync with one in trampoline.S */
.word 0, 0, 0, 0 # dummy
-
- .word 0, 0, 0, 0 # unused
-
- .word 0xFFFF # 4Gb - (0x100000*0x1000 = 4Gb)
- .word 0 # base address = 0
- .word 0x9B00 # code read/exec. ??? Why I need 0x9B00 (as opposed to 0x9A00 in order for this to work?)
- .word 0x00CF # granularity = 4096, 386
- # (+5th nibble of limit)
-
- .word 0xFFFF # 4Gb - (0x100000*0x1000 = 4Gb)
- .word 0 # base address = 0
- .word 0x9200 # data read/write
- .word 0x00CF # granularity = 4096, 386
- # (+5th nibble of limit)
-# this is 64bit descriptor for code
- .word 0xFFFF
- .word 0
- .word 0x9A00 # code read/exec
- .word 0x00AF # as above, but it is long mode and with D=0
+ /* ??? Why I need the accessed bit set in order for this to work? */
+ .quad 0x00cf9b000000ffff # __KERNEL32_CS
+ .quad 0x00af9b000000ffff # __KERNEL_CS
+ .quad 0x00cf93000000ffff # __KERNEL_DS
idt_48a:
.word 0 # idt limit = 0
.word 0, 0 # idt base = 0L
gdt_48a:
- .word 0x8000 # gdt limit=2048,
+ .word 0x800 # gdt limit=2048,
# 256 GDT entries
- .word 0, 0 # gdt base (filled in later)
-
+ .long gdta - wakeup_code # gdt base (relocated in later)
-real_save_gdt: .word 0
- .quad 0
real_magic: .quad 0
video_mode: .quad 0
video_flags: .quad 0
+.code16
bogus_real_magic:
- movb $0xba,%al ; outb %al,$0x80
+ movb $0xba,%al ; outb %al,$0x80
jmp bogus_real_magic
-bogus_32_magic:
+.code64
+bogus_64_magic:
movb $0xb3,%al ; outb %al,$0x80
- jmp bogus_32_magic
+ jmp bogus_64_magic
-bogus_31_magic:
- movb $0xb1,%al ; outb %al,$0x80
- jmp bogus_31_magic
-
-bogus_cpu:
- movb $0xbc,%al ; outb %al,$0x80
- jmp bogus_cpu
+.code16
+no_longmode:
+ movb $0xbc,%al ; outb %al,$0x80
+ jmp no_longmode
+#include "../verify_cpu.S"
/* This code uses an extended set of video mode numbers. These include:
* Aliases for standard modes
@@ -301,6 +269,7 @@ bogus_cpu:
#define VIDEO_FIRST_V7 0x0900
# Setting of user mode (AX=mode ID) => CF=success
+.code16
mode_seta:
movw %ax, %bx
#if 0
@@ -346,21 +315,18 @@ check_vesaa:
_setbada: jmp setbada
- .code64
-bogus_magic:
- movw $0x0e00 + 'B', %ds:(0xb8018)
- jmp bogus_magic
-
-bogus_magic2:
- movw $0x0e00 + '2', %ds:(0xb8018)
- jmp bogus_magic2
-
-
wakeup_stack_begin: # Stack grows down
.org 0xff0
wakeup_stack: # Just below end of page
+.org 0x1000
+ENTRY(wakeup_level4_pgt)
+ .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
+ .fill 510,8,0
+ /* (2^48-(2*1024*1024*1024))/(2^39) = 511 */
+ .quad level3_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE
+
ENTRY(wakeup_end)
##
@@ -373,28 +339,11 @@ ENTRY(wakeup_end)
#
# Returned address is location of code in low memory (past data and stack)
#
+ .code64
ENTRY(acpi_copy_wakeup_routine)
pushq %rax
- pushq %rcx
pushq %rdx
- sgdt saved_gdt
- sidt saved_idt
- sldt saved_ldt
- str saved_tss
-
- movq %cr3, %rdx
- movq %rdx, saved_cr3
- movq %cr4, %rdx
- movq %rdx, saved_cr4
- movq %cr0, %rdx
- movq %rdx, saved_cr0
- sgdt real_save_gdt - wakeup_start (,%rdi)
- movl $MSR_EFER, %ecx
- rdmsr
- movl %eax, saved_efer
- movl %edx, saved_efer2
-
movl saved_video_mode, %edx
movl %edx, video_mode - wakeup_start (,%rdi)
movl acpi_video_flags, %edx
@@ -403,21 +352,13 @@ ENTRY(acpi_copy_wakeup_routine)
movq $0x123456789abcdef0, %rdx
movq %rdx, saved_magic
- movl saved_magic - __START_KERNEL_map, %eax
- cmpl $0x9abcdef0, %eax
- jne bogus_32_magic
-
- # make sure %cr4 is set correctly (features, etc)
- movl saved_cr4 - __START_KERNEL_map, %eax
- movq %rax, %cr4
+ movq saved_magic, %rax
+ movq $0x123456789abcdef0, %rdx
+ cmpq %rdx, %rax
+ jne bogus_64_magic
- movl saved_cr0 - __START_KERNEL_map, %eax
- movq %rax, %cr0
- jmp 1f # Flush pipelines
-1:
# restore the regs we used
popq %rdx
- popq %rcx
popq %rax
ENTRY(do_suspend_lowlevel_s4bios)
ret
@@ -450,13 +391,13 @@ do_suspend_lowlevel:
movq %r15, saved_context_r15(%rip)
pushfq ; popq saved_context_eflags(%rip)
- movq $.L97, saved_eip(%rip)
+ movq $.L97, saved_rip(%rip)
- movq %rsp,saved_esp
- movq %rbp,saved_ebp
- movq %rbx,saved_ebx
- movq %rdi,saved_edi
- movq %rsi,saved_esi
+ movq %rsp,saved_rsp
+ movq %rbp,saved_rbp
+ movq %rbx,saved_rbx
+ movq %rdi,saved_rdi
+ movq %rsi,saved_rsi
addq $8, %rsp
movl $3, %edi
@@ -503,25 +444,12 @@ do_suspend_lowlevel:
.data
ALIGN
-ENTRY(saved_ebp) .quad 0
-ENTRY(saved_esi) .quad 0
-ENTRY(saved_edi) .quad 0
-ENTRY(saved_ebx) .quad 0
+ENTRY(saved_rbp) .quad 0
+ENTRY(saved_rsi) .quad 0
+ENTRY(saved_rdi) .quad 0
+ENTRY(saved_rbx) .quad 0
-ENTRY(saved_eip) .quad 0
-ENTRY(saved_esp) .quad 0
+ENTRY(saved_rip) .quad 0
+ENTRY(saved_rsp) .quad 0
ENTRY(saved_magic) .quad 0
-
-ALIGN
-# saved registers
-saved_gdt: .quad 0,0
-saved_idt: .quad 0,0
-saved_ldt: .quad 0
-saved_tss: .quad 0
-
-saved_cr0: .quad 0
-saved_cr3: .quad 0
-saved_cr4: .quad 0
-saved_efer: .quad 0
-saved_efer2: .quad 0
diff --git a/arch/x86_64/kernel/aperture.c b/arch/x86_64/kernel/aperture.c
index b487396c4c5..a52af582059 100644
--- a/arch/x86_64/kernel/aperture.c
+++ b/arch/x86_64/kernel/aperture.c
@@ -51,7 +51,6 @@ static void __init insert_aperture_resource(u32 aper_base, u32 aper_size)
static u32 __init allocate_aperture(void)
{
- pg_data_t *nd0 = NODE_DATA(0);
u32 aper_size;
void *p;
@@ -65,12 +64,12 @@ static u32 __init allocate_aperture(void)
* Unfortunately we cannot move it up because that would make the
* IOMMU useless.
*/
- p = __alloc_bootmem_node(nd0, aper_size, aper_size, 0);
+ p = __alloc_bootmem_nopanic(aper_size, aper_size, 0);
if (!p || __pa(p)+aper_size > 0xffffffff) {
printk("Cannot allocate aperture memory hole (%p,%uK)\n",
p, aper_size>>10);
if (p)
- free_bootmem_node(nd0, __pa(p), aper_size);
+ free_bootmem(__pa(p), aper_size);
return 0;
}
printk("Mapping aperture over %d KB of RAM @ %lx\n",
diff --git a/arch/x86_64/kernel/apic.c b/arch/x86_64/kernel/apic.c
index bd3e45d47c3..d198f7d82e5 100644
--- a/arch/x86_64/kernel/apic.c
+++ b/arch/x86_64/kernel/apic.c
@@ -68,6 +68,28 @@ int using_apic_timer __read_mostly = 0;
static void apic_pm_activate(void);
+void apic_wait_icr_idle(void)
+{
+ while (apic_read(APIC_ICR) & APIC_ICR_BUSY)
+ cpu_relax();
+}
+
+unsigned int safe_apic_wait_icr_idle(void)
+{
+ unsigned int send_status;
+ int timeout;
+
+ timeout = 0;
+ do {
+ send_status = apic_read(APIC_ICR) & APIC_ICR_BUSY;
+ if (!send_status)
+ break;
+ udelay(100);
+ } while (timeout++ < 1000);
+
+ return send_status;
+}
+
void enable_NMI_through_LVT0 (void * dummy)
{
unsigned int v;
@@ -817,14 +839,15 @@ static void setup_APIC_timer(unsigned int clocks)
static int __init calibrate_APIC_clock(void)
{
- int apic, apic_start, tsc, tsc_start;
+ unsigned apic, apic_start;
+ unsigned long tsc, tsc_start;
int result;
/*
* Put whatever arbitrary (but long enough) timeout
* value into the APIC clock, we just want to get the
* counter running for calibration.
*/
- __setup_APIC_LVTT(1000000000);
+ __setup_APIC_LVTT(4000000000);
apic_start = apic_read(APIC_TMCCT);
#ifdef CONFIG_X86_PM_TIMER
@@ -835,15 +858,15 @@ static int __init calibrate_APIC_clock(void)
} else
#endif
{
- rdtscl(tsc_start);
+ rdtscll(tsc_start);
do {
apic = apic_read(APIC_TMCCT);
- rdtscl(tsc);
+ rdtscll(tsc);
} while ((tsc - tsc_start) < TICK_COUNT &&
- (apic - apic_start) < TICK_COUNT);
+ (apic_start - apic) < TICK_COUNT);
- result = (apic_start - apic) * 1000L * cpu_khz /
+ result = (apic_start - apic) * 1000L * tsc_khz /
(tsc - tsc_start);
}
printk("result %d\n", result);
diff --git a/arch/x86_64/kernel/asm-offsets.c b/arch/x86_64/kernel/asm-offsets.c
index 96687e2beb2..778953bc636 100644
--- a/arch/x86_64/kernel/asm-offsets.c
+++ b/arch/x86_64/kernel/asm-offsets.c
@@ -21,6 +21,14 @@
#define BLANK() asm volatile("\n->" : : )
+#define __NO_STUBS 1
+#undef __SYSCALL
+#undef _ASM_X86_64_UNISTD_H_
+#define __SYSCALL(nr, sym) [nr] = 1,
+static char syscalls[] = {
+#include <asm/unistd.h>
+};
+
int main(void)
{
#define ENTRY(entry) DEFINE(tsk_ ## entry, offsetof(struct task_struct, entry))
@@ -71,5 +79,7 @@ int main(void)
DEFINE(TSS_ist, offsetof(struct tss_struct, ist));
BLANK();
DEFINE(crypto_tfm_ctx_offset, offsetof(struct crypto_tfm, __crt_ctx));
+ BLANK();
+ DEFINE(__NR_syscall_max, sizeof(syscalls) - 1);
return 0;
}
diff --git a/arch/x86_64/kernel/bugs.c b/arch/x86_64/kernel/bugs.c
new file mode 100644
index 00000000000..12b585b5345
--- /dev/null
+++ b/arch/x86_64/kernel/bugs.c
@@ -0,0 +1,21 @@
+/*
+ * arch/x86_64/kernel/bugs.c
+ *
+ * Copyright (C) 1994 Linus Torvalds
+ * Copyright (C) 2000 SuSE
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <asm/alternative.h>
+#include <asm/processor.h>
+
+void __init check_bugs(void)
+{
+ identify_cpu(&boot_cpu_data);
+#if !defined(CONFIG_SMP)
+ printk("CPU: ");
+ print_cpu_info(&boot_cpu_data);
+#endif
+ alternative_instructions();
+}
diff --git a/arch/x86_64/kernel/e820.c b/arch/x86_64/kernel/e820.c
index a490fabfcf4..be8965427a9 100644
--- a/arch/x86_64/kernel/e820.c
+++ b/arch/x86_64/kernel/e820.c
@@ -25,7 +25,7 @@
#include <asm/bootsetup.h>
#include <asm/sections.h>
-struct e820map e820 __initdata;
+struct e820map e820;
/*
* PFN of last memory page.
@@ -98,7 +98,7 @@ static inline int bad_addr(unsigned long *addrp, unsigned long size)
* This function checks if any part of the range <start,end> is mapped
* with type.
*/
-int __meminit
+int
e820_any_mapped(unsigned long start, unsigned long end, unsigned type)
{
int i;
@@ -112,6 +112,7 @@ e820_any_mapped(unsigned long start, unsigned long end, unsigned type)
}
return 0;
}
+EXPORT_SYMBOL_GPL(e820_any_mapped);
/*
* This function checks if the entire range <start,end> is mapped with type.
diff --git a/arch/x86_64/kernel/early-quirks.c b/arch/x86_64/kernel/early-quirks.c
index fede55a5399..990d9c218a5 100644
--- a/arch/x86_64/kernel/early-quirks.c
+++ b/arch/x86_64/kernel/early-quirks.c
@@ -71,18 +71,6 @@ static void __init ati_bugs(void)
}
}
-static void intel_bugs(void)
-{
- u16 device = read_pci_config_16(0, 0, 0, PCI_DEVICE_ID);
-
-#ifdef CONFIG_SMP
- if (device == PCI_DEVICE_ID_INTEL_E7320_MCH ||
- device == PCI_DEVICE_ID_INTEL_E7520_MCH ||
- device == PCI_DEVICE_ID_INTEL_E7525_MCH)
- quirk_intel_irqbalance();
-#endif
-}
-
struct chipset {
u16 vendor;
void (*f)(void);
@@ -92,7 +80,6 @@ static struct chipset early_qrk[] __initdata = {
{ PCI_VENDOR_ID_NVIDIA, nvidia_bugs },
{ PCI_VENDOR_ID_VIA, via_bugs },
{ PCI_VENDOR_ID_ATI, ati_bugs },
- { PCI_VENDOR_ID_INTEL, intel_bugs},
{}
};
diff --git a/arch/x86_64/kernel/early_printk.c b/arch/x86_64/kernel/early_printk.c
index 47b6d90349d..92213d2b7c1 100644
--- a/arch/x86_64/kernel/early_printk.c
+++ b/arch/x86_64/kernel/early_printk.c
@@ -11,11 +11,10 @@
#ifdef __i386__
#include <asm/setup.h>
-#define VGABASE (__ISA_IO_base + 0xb8000)
#else
#include <asm/bootsetup.h>
-#define VGABASE ((void __iomem *)0xffffffff800b8000UL)
#endif
+#define VGABASE (__ISA_IO_base + 0xb8000)
static int max_ypos = 25, max_xpos = 80;
static int current_ypos = 25, current_xpos = 0;
@@ -176,7 +175,7 @@ static noinline long simnow(long cmd, long a, long b, long c)
return ret;
}
-void __init simnow_init(char *str)
+static void __init simnow_init(char *str)
{
char *fn = "klog";
if (*str == '=')
diff --git a/arch/x86_64/kernel/entry.S b/arch/x86_64/kernel/entry.S
index ed4350ced3d..fa984b53e7e 100644
--- a/arch/x86_64/kernel/entry.S
+++ b/arch/x86_64/kernel/entry.S
@@ -701,6 +701,7 @@ END(spurious_interrupt)
CFI_ADJUST_CFA_OFFSET 8
pushq %rax /* push real oldrax to the rdi slot */
CFI_ADJUST_CFA_OFFSET 8
+ CFI_REL_OFFSET rax,0
leaq \sym(%rip),%rax
jmp error_entry
CFI_ENDPROC
@@ -710,6 +711,7 @@ END(spurious_interrupt)
XCPT_FRAME
pushq %rax
CFI_ADJUST_CFA_OFFSET 8
+ CFI_REL_OFFSET rax,0
leaq \sym(%rip),%rax
jmp error_entry
CFI_ENDPROC
@@ -817,6 +819,7 @@ paranoid_schedule\trace:
*/
KPROBE_ENTRY(error_entry)
_frame RDI
+ CFI_REL_OFFSET rax,0
/* rdi slot contains rax, oldrax contains error code */
cld
subq $14*8,%rsp
@@ -824,6 +827,7 @@ KPROBE_ENTRY(error_entry)
movq %rsi,13*8(%rsp)
CFI_REL_OFFSET rsi,RSI
movq 14*8(%rsp),%rsi /* load rax from rdi slot */
+ CFI_REGISTER rax,rsi
movq %rdx,12*8(%rsp)
CFI_REL_OFFSET rdx,RDX
movq %rcx,11*8(%rsp)
@@ -857,6 +861,7 @@ error_swapgs:
swapgs
error_sti:
movq %rdi,RDI(%rsp)
+ CFI_REL_OFFSET rdi,RDI
movq %rsp,%rdi
movq ORIG_RAX(%rsp),%rsi /* get error code */
movq $-1,ORIG_RAX(%rsp)
diff --git a/arch/x86_64/kernel/functionlist b/arch/x86_64/kernel/functionlist
deleted file mode 100644
index 7ae18ec1245..00000000000
--- a/arch/x86_64/kernel/functionlist
+++ /dev/null
@@ -1,1284 +0,0 @@
-*(.text.flush_thread)
-*(.text.check_poison_obj)
-*(.text.copy_page)
-*(.text.__set_personality)
-*(.text.gart_map_sg)
-*(.text.kmem_cache_free)
-*(.text.find_get_page)
-*(.text._raw_spin_lock)
-*(.text.ide_outb)
-*(.text.unmap_vmas)
-*(.text.copy_page_range)
-*(.text.kprobe_handler)
-*(.text.__handle_mm_fault)
-*(.text.__d_lookup)
-*(.text.copy_user_generic)
-*(.text.__link_path_walk)
-*(.text.get_page_from_freelist)
-*(.text.kmem_cache_alloc)
-*(.text.drive_cmd_intr)
-*(.text.ia32_setup_sigcontext)
-*(.text.huge_pte_offset)
-*(.text.do_page_fault)
-*(.text.page_remove_rmap)
-*(.text.release_pages)
-*(.text.ide_end_request)
-*(.text.__mutex_lock_slowpath)
-*(.text.__find_get_block)
-*(.text.kfree)
-*(.text.vfs_read)
-*(.text._raw_spin_unlock)
-*(.text.free_hot_cold_page)
-*(.text.fget_light)
-*(.text.schedule)
-*(.text.memcmp)
-*(.text.touch_atime)
-*(.text.__might_sleep)
-*(.text.__down_read_trylock)
-*(.text.arch_pick_mmap_layout)
-*(.text.find_vma)
-*(.text.__make_request)
-*(.text.do_generic_mapping_read)
-*(.text.mutex_lock_interruptible)
-*(.text.__generic_file_aio_read)
-*(.text._atomic_dec_and_lock)
-*(.text.__wake_up_bit)
-*(.text.add_to_page_cache)
-*(.text.cache_alloc_debugcheck_after)
-*(.text.vm_normal_page)
-*(.text.mutex_debug_check_no_locks_freed)
-*(.text.net_rx_action)
-*(.text.__find_first_zero_bit)
-*(.text.put_page)
-*(.text._raw_read_lock)
-*(.text.__delay)
-*(.text.dnotify_parent)
-*(.text.do_path_lookup)
-*(.text.do_sync_read)
-*(.text.do_lookup)
-*(.text.bit_waitqueue)
-*(.text.file_read_actor)
-*(.text.strncpy_from_user)
-*(.text.__pagevec_lru_add_active)
-*(.text.fget)
-*(.text.dput)
-*(.text.__strnlen_user)
-*(.text.inotify_inode_queue_event)
-*(.text.rw_verify_area)
-*(.text.ide_intr)
-*(.text.inotify_dentry_parent_queue_event)
-*(.text.permission)
-*(.text.memscan)
-*(.text.hpet_rtc_interrupt)
-*(.text.do_mmap_pgoff)
-*(.text.current_fs_time)
-*(.text.vfs_getattr)
-*(.text.kmem_flagcheck)
-*(.text.mark_page_accessed)
-*(.text.free_pages_and_swap_cache)
-*(.text.generic_fillattr)
-*(.text.__block_prepare_write)
-*(.text.__set_page_dirty_nobuffers)
-*(.text.link_path_walk)
-*(.text.find_get_pages_tag)
-*(.text.ide_do_request)
-*(.text.__alloc_pages)
-*(.text.generic_permission)
-*(.text.mod_page_state_offset)
-*(.text.free_pgd_range)
-*(.text.generic_file_buffered_write)
-*(.text.number)
-*(.text.ide_do_rw_disk)
-*(.text.__brelse)
-*(.text.__mod_page_state_offset)
-*(.text.rotate_reclaimable_page)
-*(.text.find_vma_prepare)
-*(.text.find_vma_prev)
-*(.text.lru_cache_add_active)
-*(.text.__kmalloc_track_caller)
-*(.text.smp_invalidate_interrupt)
-*(.text.handle_IRQ_event)
-*(.text.__find_get_block_slow)
-*(.text.do_wp_page)
-*(.text.do_select)
-*(.text.set_user_nice)
-*(.text.sys_read)
-*(.text.do_munmap)
-*(.text.csum_partial)
-*(.text.__do_softirq)
-*(.text.may_open)
-*(.text.getname)
-*(.text.get_empty_filp)
-*(.text.__fput)
-*(.text.remove_mapping)
-*(.text.filp_ctor)
-*(.text.poison_obj)
-*(.text.unmap_region)
-*(.text.test_set_page_writeback)
-*(.text.__do_page_cache_readahead)
-*(.text.sock_def_readable)
-*(.text.ide_outl)
-*(.text.shrink_zone)
-*(.text.rb_insert_color)
-*(.text.get_request)
-*(.text.sys_pread64)
-*(.text.spin_bug)
-*(.text.ide_outsl)
-*(.text.mask_and_ack_8259A)
-*(.text.filemap_nopage)
-*(.text.page_add_file_rmap)
-*(.text.find_lock_page)
-*(.text.tcp_poll)
-*(.text.__mark_inode_dirty)
-*(.text.file_ra_state_init)
-*(.text.generic_file_llseek)
-*(.text.__pagevec_lru_add)
-*(.text.page_cache_readahead)
-*(.text.n_tty_receive_buf)
-*(.text.zonelist_policy)
-*(.text.vma_adjust)
-*(.text.test_clear_page_dirty)
-*(.text.sync_buffer)
-*(.text.do_exit)
-*(.text.__bitmap_weight)
-*(.text.alloc_pages_current)
-*(.text.get_unused_fd)
-*(.text.zone_watermark_ok)
-*(.text.cpuset_update_task_memory_state)
-*(.text.__bitmap_empty)
-*(.text.sys_munmap)
-*(.text.__inode_dir_notify)
-*(.text.__generic_file_aio_write_nolock)
-*(.text.__pte_alloc)
-*(.text.sys_select)
-*(.text.vm_acct_memory)
-*(.text.vfs_write)
-*(.text.__lru_add_drain)
-*(.text.prio_tree_insert)
-*(.text.generic_file_aio_read)
-*(.text.vma_merge)
-*(.text.block_write_full_page)
-*(.text.__page_set_anon_rmap)
-*(.text.apic_timer_interrupt)
-*(.text.release_console_sem)
-*(.text.sys_write)
-*(.text.sys_brk)
-*(.text.dup_mm)
-*(.text.read_current_timer)
-*(.text.ll_rw_block)
-*(.text.blk_rq_map_sg)
-*(.text.dbg_userword)
-*(.text.__block_commit_write)
-*(.text.cache_grow)
-*(.text.copy_strings)
-*(.text.release_task)
-*(.text.do_sync_write)
-*(.text.unlock_page)
-*(.text.load_elf_binary)
-*(.text.__follow_mount)
-*(.text.__getblk)
-*(.text.do_sys_open)
-*(.text.current_kernel_time)
-*(.text.call_rcu)
-*(.text.write_chan)
-*(.text.vsnprintf)
-*(.text.dummy_inode_setsecurity)
-*(.text.submit_bh)
-*(.text.poll_freewait)
-*(.text.bio_alloc_bioset)
-*(.text.skb_clone)
-*(.text.page_waitqueue)
-*(.text.__mutex_lock_interruptible_slowpath)
-*(.text.get_index)
-*(.text.csum_partial_copy_generic)
-*(.text.bad_range)
-*(.text.remove_vma)
-*(.text.cp_new_stat)
-*(.text.alloc_arraycache)
-*(.text.test_clear_page_writeback)
-*(.text.strsep)
-*(.text.open_namei)
-*(.text._raw_read_unlock)
-*(.text.get_vma_policy)
-*(.text.__down_write_trylock)
-*(.text.find_get_pages)
-*(.text.tcp_rcv_established)
-*(.text.generic_make_request)
-*(.text.__block_write_full_page)
-*(.text.cfq_set_request)
-*(.text.sys_inotify_init)
-*(.text.split_vma)
-*(.text.__mod_timer)
-*(.text.get_options)
-*(.text.vma_link)
-*(.text.mpage_writepages)
-*(.text.truncate_complete_page)
-*(.text.tcp_recvmsg)
-*(.text.sigprocmask)
-*(.text.filemap_populate)
-*(.text.sys_close)
-*(.text.inotify_dev_queue_event)
-*(.text.do_task_stat)
-*(.text.__dentry_open)
-*(.text.unlink_file_vma)
-*(.text.__pollwait)
-*(.text.packet_rcv_spkt)
-*(.text.drop_buffers)
-*(.text.free_pgtables)
-*(.text.generic_file_direct_write)
-*(.text.copy_process)
-*(.text.netif_receive_skb)
-*(.text.dnotify_flush)
-*(.text.print_bad_pte)
-*(.text.anon_vma_unlink)
-*(.text.sys_mprotect)
-*(.text.sync_sb_inodes)
-*(.text.find_inode_fast)
-*(.text.dummy_inode_readlink)
-*(.text.putname)
-*(.text.init_smp_flush)
-*(.text.dbg_redzone2)
-*(.text.sk_run_filter)
-*(.text.may_expand_vm)
-*(.text.generic_file_aio_write)
-*(.text.find_next_zero_bit)
-*(.text.file_kill)
-*(.text.audit_getname)
-*(.text.arch_unmap_area_topdown)
-*(.text.alloc_page_vma)
-*(.text.tcp_transmit_skb)
-*(.text.rb_next)
-*(.text.dbg_redzone1)
-*(.text.generic_file_mmap)
-*(.text.vfs_fstat)
-*(.text.sys_time)
-*(.text.page_lock_anon_vma)
-*(.text.get_unmapped_area)
-*(.text.remote_llseek)
-*(.text.__up_read)
-*(.text.fd_install)
-*(.text.eventpoll_init_file)
-*(.text.dma_alloc_coherent)
-*(.text.create_empty_buffers)
-*(.text.__mutex_unlock_slowpath)
-*(.text.dup_fd)
-*(.text.d_alloc)
-*(.text.tty_ldisc_try)
-*(.text.sys_stime)
-*(.text.__rb_rotate_right)
-*(.text.d_validate)
-*(.text.rb_erase)
-*(.text.path_release)
-*(.text.memmove)
-*(.text.invalidate_complete_page)
-*(.text.clear_inode)
-*(.text.cache_estimate)
-*(.text.alloc_buffer_head)
-*(.text.smp_call_function_interrupt)
-*(.text.flush_tlb_others)
-*(.text.file_move)
-*(.text.balance_dirty_pages_ratelimited)
-*(.text.vma_prio_tree_add)
-*(.text.timespec_trunc)
-*(.text.mempool_alloc)
-*(.text.iget_locked)
-*(.text.d_alloc_root)
-*(.text.cpuset_populate_dir)
-*(.text.anon_vma_prepare)
-*(.text.sys_newstat)
-*(.text.alloc_page_interleave)
-*(.text.__path_lookup_intent_open)
-*(.text.__pagevec_free)
-*(.text.inode_init_once)
-*(.text.free_vfsmnt)
-*(.text.__user_walk_fd)
-*(.text.cfq_idle_slice_timer)
-*(.text.sys_mmap)
-*(.text.sys_llseek)
-*(.text.prio_tree_remove)
-*(.text.filp_close)
-*(.text.file_permission)
-*(.text.vma_prio_tree_remove)
-*(.text.tcp_ack)
-*(.text.nameidata_to_filp)
-*(.text.sys_lseek)
-*(.text.percpu_counter_mod)
-*(.text.igrab)
-*(.text.__bread)
-*(.text.alloc_inode)
-*(.text.filldir)
-*(.text.__rb_rotate_left)
-*(.text.irq_affinity_write_proc)
-*(.text.init_request_from_bio)
-*(.text.find_or_create_page)
-*(.text.tty_poll)
-*(.text.tcp_sendmsg)
-*(.text.ide_wait_stat)
-*(.text.free_buffer_head)
-*(.text.flush_signal_handlers)
-*(.text.tcp_v4_rcv)
-*(.text.nr_blockdev_pages)
-*(.text.locks_remove_flock)
-*(.text.__iowrite32_copy)
-*(.text.do_filp_open)
-*(.text.try_to_release_page)
-*(.text.page_add_new_anon_rmap)
-*(.text.kmem_cache_size)
-*(.text.eth_type_trans)
-*(.text.try_to_free_buffers)
-*(.text.schedule_tail)
-*(.text.proc_lookup)
-*(.text.no_llseek)
-*(.text.kfree_skbmem)
-*(.text.do_wait)
-*(.text.do_mpage_readpage)
-*(.text.vfs_stat_fd)
-*(.text.tty_write)
-*(.text.705)
-*(.text.sync_page)
-*(.text.__remove_shared_vm_struct)
-*(.text.__kfree_skb)
-*(.text.sock_poll)
-*(.text.get_request_wait)
-*(.text.do_sigaction)
-*(.text.do_brk)
-*(.text.tcp_event_data_recv)
-*(.text.read_chan)
-*(.text.pipe_writev)
-*(.text.__emul_lookup_dentry)
-*(.text.rtc_get_rtc_time)
-*(.text.print_objinfo)
-*(.text.file_update_time)
-*(.text.do_signal)
-*(.text.disable_8259A_irq)
-*(.text.blk_queue_bounce)
-*(.text.__anon_vma_link)
-*(.text.__vma_link)
-*(.text.vfs_rename)
-*(.text.sys_newlstat)
-*(.text.sys_newfstat)
-*(.text.sys_mknod)
-*(.text.__show_regs)
-*(.text.iput)
-*(.text.get_signal_to_deliver)
-*(.text.flush_tlb_page)
-*(.text.debug_mutex_wake_waiter)
-*(.text.copy_thread)
-*(.text.clear_page_dirty_for_io)
-*(.text.buffer_io_error)
-*(.text.vfs_permission)
-*(.text.truncate_inode_pages_range)
-*(.text.sys_recvfrom)
-*(.text.remove_suid)
-*(.text.mark_buffer_dirty)
-*(.text.local_bh_enable)
-*(.text.get_zeroed_page)
-*(.text.get_vmalloc_info)
-*(.text.flush_old_exec)
-*(.text.dummy_inode_permission)
-*(.text.__bio_add_page)
-*(.text.prio_tree_replace)
-*(.text.notify_change)
-*(.text.mntput_no_expire)
-*(.text.fput)
-*(.text.__end_that_request_first)
-*(.text.wake_up_bit)
-*(.text.unuse_mm)
-*(.text.shrink_icache_memory)
-*(.text.sched_balance_self)
-*(.text.__pmd_alloc)
-*(.text.pipe_poll)
-*(.text.normal_poll)
-*(.text.__free_pages)
-*(.text.follow_mount)
-*(.text.cdrom_start_packet_command)
-*(.text.blk_recount_segments)
-*(.text.bio_put)
-*(.text.__alloc_skb)
-*(.text.__wake_up)
-*(.text.vm_stat_account)
-*(.text.sys_fcntl)
-*(.text.sys_fadvise64)
-*(.text._raw_write_unlock)
-*(.text.__pud_alloc)
-*(.text.alloc_page_buffers)
-*(.text.vfs_llseek)
-*(.text.sockfd_lookup)
-*(.text._raw_write_lock)
-*(.text.put_compound_page)
-*(.text.prune_dcache)
-*(.text.pipe_readv)
-*(.text.mempool_free)
-*(.text.make_ahead_window)
-*(.text.lru_add_drain)
-*(.text.constant_test_bit)
-*(.text.__clear_user)
-*(.text.arch_unmap_area)
-*(.text.anon_vma_link)
-*(.text.sys_chroot)
-*(.text.setup_arg_pages)
-*(.text.radix_tree_preload)
-*(.text.init_rwsem)
-*(.text.generic_osync_inode)
-*(.text.generic_delete_inode)
-*(.text.do_sys_poll)
-*(.text.dev_queue_xmit)
-*(.text.default_llseek)
-*(.text.__writeback_single_inode)
-*(.text.vfs_ioctl)
-*(.text.__up_write)
-*(.text.unix_poll)
-*(.text.sys_rt_sigprocmask)
-*(.text.sock_recvmsg)
-*(.text.recalc_bh_state)
-*(.text.__put_unused_fd)
-*(.text.process_backlog)
-*(.text.locks_remove_posix)
-*(.text.lease_modify)
-*(.text.expand_files)
-*(.text.end_buffer_read_nobh)
-*(.text.d_splice_alias)
-*(.text.debug_mutex_init_waiter)
-*(.text.copy_from_user)
-*(.text.cap_vm_enough_memory)
-*(.text.show_vfsmnt)
-*(.text.release_sock)
-*(.text.pfifo_fast_enqueue)
-*(.text.half_md4_transform)
-*(.text.fs_may_remount_ro)
-*(.text.do_fork)
-*(.text.copy_hugetlb_page_range)
-*(.text.cache_free_debugcheck)
-*(.text.__tcp_select_window)
-*(.text.task_handoff_register)
-*(.text.sys_open)
-*(.text.strlcpy)
-*(.text.skb_copy_datagram_iovec)
-*(.text.set_up_list3s)
-*(.text.release_open_intent)
-*(.text.qdisc_restart)
-*(.text.n_tty_chars_in_buffer)
-*(.text.inode_change_ok)
-*(.text.__downgrade_write)
-*(.text.debug_mutex_unlock)
-*(.text.add_timer_randomness)
-*(.text.sock_common_recvmsg)
-*(.text.set_bh_page)
-*(.text.printk_lock)
-*(.text.path_release_on_umount)
-*(.text.ip_output)
-*(.text.ide_build_dmatable)
-*(.text.__get_user_8)
-*(.text.end_buffer_read_sync)
-*(.text.__d_path)
-*(.text.d_move)
-*(.text.del_timer)
-*(.text.constant_test_bit)
-*(.text.blockable_page_cache_readahead)
-*(.text.tty_read)
-*(.text.sys_readlink)
-*(.text.sys_faccessat)
-*(.text.read_swap_cache_async)
-*(.text.pty_write_room)
-*(.text.page_address_in_vma)
-*(.text.kthread)
-*(.text.cfq_exit_io_context)
-*(.text.__tcp_push_pending_frames)
-*(.text.sys_pipe)
-*(.text.submit_bio)
-*(.text.pid_revalidate)
-*(.text.page_referenced_file)
-*(.text.lock_sock)
-*(.text.get_page_state_node)
-*(.text.generic_block_bmap)
-*(.text.do_setitimer)
-*(.text.dev_queue_xmit_nit)
-*(.text.copy_from_read_buf)
-*(.text.__const_udelay)
-*(.text.console_conditional_schedule)
-*(.text.wake_up_new_task)
-*(.text.wait_for_completion_interruptible)
-*(.text.tcp_rcv_rtt_update)
-*(.text.sys_mlockall)
-*(.text.set_fs_altroot)
-*(.text.schedule_timeout)
-*(.text.nr_free_pagecache_pages)
-*(.text.nf_iterate)
-*(.text.mapping_tagged)
-*(.text.ip_queue_xmit)
-*(.text.ip_local_deliver)
-*(.text.follow_page)
-*(.text.elf_map)
-*(.text.dummy_file_permission)
-*(.text.dispose_list)
-*(.text.dentry_open)
-*(.text.dentry_iput)
-*(.text.bio_alloc)
-*(.text.wait_on_page_bit)
-*(.text.vfs_readdir)
-*(.text.vfs_lstat)
-*(.text.seq_escape)
-*(.text.__posix_lock_file)
-*(.text.mm_release)
-*(.text.kref_put)
-*(.text.ip_rcv)
-*(.text.__iget)
-*(.text.free_pages)
-*(.text.find_mergeable_anon_vma)
-*(.text.find_extend_vma)
-*(.text.dummy_inode_listsecurity)
-*(.text.bio_add_page)
-*(.text.__vm_enough_memory)
-*(.text.vfs_stat)
-*(.text.tty_paranoia_check)
-*(.text.tcp_read_sock)
-*(.text.tcp_data_queue)
-*(.text.sys_uname)
-*(.text.sys_renameat)
-*(.text.__strncpy_from_user)
-*(.text.__mutex_init)
-*(.text.__lookup_hash)
-*(.text.kref_get)
-*(.text.ip_route_input)
-*(.text.__insert_inode_hash)
-*(.text.do_sock_write)
-*(.text.blk_done_softirq)
-*(.text.__wake_up_sync)
-*(.text.__vma_link_rb)
-*(.text.tty_ioctl)
-*(.text.tracesys)
-*(.text.sys_getdents)
-*(.text.sys_dup)
-*(.text.stub_execve)
-*(.text.sha_transform)
-*(.text.radix_tree_tag_clear)
-*(.text.put_unused_fd)
-*(.text.put_files_struct)
-*(.text.mpage_readpages)
-*(.text.may_delete)
-*(.text.kmem_cache_create)
-*(.text.ip_mc_output)
-*(.text.interleave_nodes)
-*(.text.groups_search)
-*(.text.generic_drop_inode)
-*(.text.generic_commit_write)
-*(.text.fcntl_setlk)
-*(.text.exit_mmap)
-*(.text.end_page_writeback)
-*(.text.__d_rehash)
-*(.text.debug_mutex_free_waiter)
-*(.text.csum_ipv6_magic)
-*(.text.count)
-*(.text.cleanup_rbuf)
-*(.text.check_spinlock_acquired_node)
-*(.text.can_vma_merge_after)
-*(.text.bio_endio)
-*(.text.alloc_pidmap)
-*(.text.write_ldt)
-*(.text.vmtruncate_range)
-*(.text.vfs_create)
-*(.text.__user_walk)
-*(.text.update_send_head)
-*(.text.unmap_underlying_metadata)
-*(.text.tty_ldisc_deref)
-*(.text.tcp_setsockopt)
-*(.text.tcp_send_ack)
-*(.text.sys_pause)
-*(.text.sys_gettimeofday)
-*(.text.sync_dirty_buffer)
-*(.text.strncmp)
-*(.text.release_posix_timer)
-*(.text.proc_file_read)
-*(.text.prepare_to_wait)
-*(.text.locks_mandatory_locked)
-*(.text.interruptible_sleep_on_timeout)
-*(.text.inode_sub_bytes)
-*(.text.in_group_p)
-*(.text.hrtimer_try_to_cancel)
-*(.text.filldir64)
-*(.text.fasync_helper)
-*(.text.dummy_sb_pivotroot)
-*(.text.d_lookup)
-*(.text.d_instantiate)
-*(.text.__d_find_alias)
-*(.text.cpu_idle_wait)
-*(.text.cond_resched_lock)
-*(.text.chown_common)
-*(.text.blk_congestion_wait)
-*(.text.activate_page)
-*(.text.unlock_buffer)
-*(.text.tty_wakeup)
-*(.text.tcp_v4_do_rcv)
-*(.text.tcp_current_mss)
-*(.text.sys_openat)
-*(.text.sys_fchdir)
-*(.text.strnlen_user)
-*(.text.strnlen)
-*(.text.strchr)
-*(.text.sock_common_getsockopt)
-*(.text.skb_checksum)
-*(.text.remove_wait_queue)
-*(.text.rb_replace_node)
-*(.text.radix_tree_node_ctor)
-*(.text.pty_chars_in_buffer)
-*(.text.profile_hit)
-*(.text.prio_tree_left)
-*(.text.pgd_clear_bad)
-*(.text.pfifo_fast_dequeue)
-*(.text.page_referenced)
-*(.text.open_exec)
-*(.text.mmput)
-*(.text.mm_init)
-*(.text.__ide_dma_off_quietly)
-*(.text.ide_dma_intr)
-*(.text.hrtimer_start)
-*(.text.get_io_context)
-*(.text.__get_free_pages)
-*(.text.find_first_zero_bit)
-*(.text.file_free_rcu)
-*(.text.dummy_socket_sendmsg)
-*(.text.do_unlinkat)
-*(.text.do_arch_prctl)
-*(.text.destroy_inode)
-*(.text.can_vma_merge_before)
-*(.text.block_sync_page)
-*(.text.block_prepare_write)
-*(.text.bio_init)
-*(.text.arch_ptrace)
-*(.text.wake_up_inode)
-*(.text.wait_on_retry_sync_kiocb)
-*(.text.vma_prio_tree_next)
-*(.text.tcp_rcv_space_adjust)
-*(.text.__tcp_ack_snd_check)
-*(.text.sys_utime)
-*(.text.sys_recvmsg)
-*(.text.sys_mremap)
-*(.text.sys_bdflush)
-*(.text.sleep_on)
-*(.text.set_page_dirty_lock)
-*(.text.seq_path)
-*(.text.schedule_timeout_interruptible)
-*(.text.sched_fork)
-*(.text.rt_run_flush)
-*(.text.profile_munmap)
-*(.text.prepare_binprm)
-*(.text.__pagevec_release_nonlru)
-*(.text.m_show)
-*(.text.lookup_mnt)
-*(.text.__lookup_mnt)
-*(.text.lock_timer_base)
-*(.text.is_subdir)
-*(.text.invalidate_bh_lru)
-*(.text.init_buffer_head)
-*(.text.ifind_fast)
-*(.text.ide_dma_start)
-*(.text.__get_page_state)
-*(.text.flock_to_posix_lock)
-*(.text.__find_symbol)
-*(.text.do_futex)
-*(.text.do_execve)
-*(.text.dirty_writeback_centisecs_handler)
-*(.text.dev_watchdog)
-*(.text.can_share_swap_page)
-*(.text.blkdev_put)
-*(.text.bio_get_nr_vecs)
-*(.text.xfrm_compile_policy)
-*(.text.vma_prio_tree_insert)
-*(.text.vfs_lstat_fd)
-*(.text.__user_path_lookup_open)
-*(.text.thread_return)
-*(.text.tcp_send_delayed_ack)
-*(.text.sock_def_error_report)
-*(.text.shrink_slab)
-*(.text.serial_out)
-*(.text.seq_read)
-*(.text.secure_ip_id)
-*(.text.search_binary_handler)
-*(.text.proc_pid_unhash)
-*(.text.pagevec_lookup)
-*(.text.new_inode)
-*(.text.memcpy_toiovec)
-*(.text.locks_free_lock)
-*(.text.__lock_page)
-*(.text.__lock_buffer)
-*(.text.load_module)
-*(.text.is_bad_inode)
-*(.text.invalidate_inode_buffers)
-*(.text.insert_vm_struct)
-*(.text.inode_setattr)
-*(.text.inode_add_bytes)
-*(.text.ide_read_24)
-*(.text.ide_get_error_location)
-*(.text.ide_do_drive_cmd)
-*(.text.get_locked_pte)
-*(.text.get_filesystem_list)
-*(.text.generic_file_open)
-*(.text.follow_down)
-*(.text.find_next_bit)
-*(.text.__find_first_bit)
-*(.text.exit_mm)
-*(.text.exec_keys)
-*(.text.end_buffer_write_sync)
-*(.text.end_bio_bh_io_sync)
-*(.text.dummy_socket_shutdown)
-*(.text.d_rehash)
-*(.text.d_path)
-*(.text.do_ioctl)
-*(.text.dget_locked)
-*(.text.copy_thread_group_keys)
-*(.text.cdrom_end_request)
-*(.text.cap_bprm_apply_creds)
-*(.text.blk_rq_bio_prep)
-*(.text.__bitmap_intersects)
-*(.text.bio_phys_segments)
-*(.text.bio_free)
-*(.text.arch_get_unmapped_area_topdown)
-*(.text.writeback_in_progress)
-*(.text.vfs_follow_link)
-*(.text.tcp_rcv_state_process)
-*(.text.tcp_check_space)
-*(.text.sys_stat)
-*(.text.sys_rt_sigreturn)
-*(.text.sys_rt_sigaction)
-*(.text.sys_remap_file_pages)
-*(.text.sys_pwrite64)
-*(.text.sys_fchownat)
-*(.text.sys_fchmodat)
-*(.text.strncat)
-*(.text.strlcat)
-*(.text.strcmp)
-*(.text.steal_locks)
-*(.text.sock_create)
-*(.text.sk_stream_rfree)
-*(.text.sk_stream_mem_schedule)
-*(.text.skip_atoi)
-*(.text.sk_alloc)
-*(.text.show_stat)
-*(.text.set_fs_pwd)
-*(.text.set_binfmt)
-*(.text.pty_unthrottle)
-*(.text.proc_symlink)
-*(.text.pipe_release)
-*(.text.pageout)
-*(.text.n_tty_write_wakeup)
-*(.text.n_tty_ioctl)
-*(.text.nr_free_zone_pages)
-*(.text.migration_thread)
-*(.text.mempool_free_slab)
-*(.text.meminfo_read_proc)
-*(.text.max_sane_readahead)
-*(.text.lru_cache_add)
-*(.text.kill_fasync)
-*(.text.kernel_read)
-*(.text.invalidate_mapping_pages)
-*(.text.inode_has_buffers)
-*(.text.init_once)
-*(.text.inet_sendmsg)
-*(.text.idedisk_issue_flush)
-*(.text.generic_file_write)
-*(.text.free_more_memory)
-*(.text.__free_fdtable)
-*(.text.filp_dtor)
-*(.text.exit_sem)
-*(.text.exit_itimers)
-*(.text.error_interrupt)
-*(.text.end_buffer_async_write)
-*(.text.eligible_child)
-*(.text.elf_map)
-*(.text.dump_task_regs)
-*(.text.dummy_task_setscheduler)
-*(.text.dummy_socket_accept)
-*(.text.dummy_file_free_security)
-*(.text.__down_read)
-*(.text.do_sock_read)
-*(.text.do_sigaltstack)
-*(.text.do_mremap)
-*(.text.current_io_context)
-*(.text.cpu_swap_callback)
-*(.text.copy_vma)
-*(.text.cap_bprm_set_security)
-*(.text.blk_insert_request)
-*(.text.bio_map_kern_endio)
-*(.text.bio_hw_segments)
-*(.text.bictcp_cong_avoid)
-*(.text.add_interrupt_randomness)
-*(.text.wait_for_completion)
-*(.text.version_read_proc)
-*(.text.unix_write_space)
-*(.text.tty_ldisc_ref_wait)
-*(.text.tty_ldisc_put)
-*(.text.try_to_wake_up)
-*(.text.tcp_v4_tw_remember_stamp)
-*(.text.tcp_try_undo_dsack)
-*(.text.tcp_may_send_now)
-*(.text.sys_waitid)
-*(.text.sys_sched_getparam)
-*(.text.sys_getppid)
-*(.text.sys_getcwd)
-*(.text.sys_dup2)
-*(.text.sys_chmod)
-*(.text.sys_chdir)
-*(.text.sprintf)
-*(.text.sock_wfree)
-*(.text.sock_aio_write)
-*(.text.skb_drop_fraglist)
-*(.text.skb_dequeue)
-*(.text.set_close_on_exec)
-*(.text.set_brk)
-*(.text.seq_puts)
-*(.text.SELECT_DRIVE)
-*(.text.sched_exec)
-*(.text.return_EIO)
-*(.text.remove_from_page_cache)
-*(.text.rcu_start_batch)
-*(.text.__put_task_struct)
-*(.text.proc_pid_readdir)
-*(.text.proc_get_inode)
-*(.text.prepare_to_wait_exclusive)
-*(.text.pipe_wait)
-*(.text.pipe_new)
-*(.text.pdflush_operation)
-*(.text.__pagevec_release)
-*(.text.pagevec_lookup_tag)
-*(.text.packet_rcv)
-*(.text.n_tty_set_room)
-*(.text.nr_free_pages)
-*(.text.__net_timestamp)
-*(.text.mpage_end_io_read)
-*(.text.mod_timer)
-*(.text.__memcpy)
-*(.text.mb_cache_shrink_fn)
-*(.text.lock_rename)
-*(.text.kstrdup)
-*(.text.is_ignored)
-*(.text.int_very_careful)
-*(.text.inotify_inode_is_dead)
-*(.text.inotify_get_cookie)
-*(.text.inode_get_bytes)
-*(.text.init_timer)
-*(.text.init_dev)
-*(.text.inet_getname)
-*(.text.ide_map_sg)
-*(.text.__ide_dma_end)
-*(.text.hrtimer_get_remaining)
-*(.text.get_task_mm)
-*(.text.get_random_int)
-*(.text.free_pipe_info)
-*(.text.filemap_write_and_wait_range)
-*(.text.exit_thread)
-*(.text.enter_idle)
-*(.text.end_that_request_first)
-*(.text.end_8259A_irq)
-*(.text.dummy_file_alloc_security)
-*(.text.do_group_exit)
-*(.text.debug_mutex_init)
-*(.text.cpuset_exit)
-*(.text.cpu_idle)
-*(.text.copy_semundo)
-*(.text.copy_files)
-*(.text.chrdev_open)
-*(.text.cdrom_transfer_packet_command)
-*(.text.cdrom_mode_sense)
-*(.text.blk_phys_contig_segment)
-*(.text.blk_get_queue)
-*(.text.bio_split)
-*(.text.audit_alloc)
-*(.text.anon_pipe_buf_release)
-*(.text.add_wait_queue_exclusive)
-*(.text.add_wait_queue)
-*(.text.acct_process)
-*(.text.account)
-*(.text.zeromap_page_range)
-*(.text.yield)
-*(.text.writeback_acquire)
-*(.text.worker_thread)
-*(.text.wait_on_page_writeback_range)
-*(.text.__wait_on_buffer)
-*(.text.vscnprintf)
-*(.text.vmalloc_to_pfn)
-*(.text.vgacon_save_screen)
-*(.text.vfs_unlink)
-*(.text.vfs_rmdir)
-*(.text.unregister_md_personality)
-*(.text.unlock_new_inode)
-*(.text.unix_stream_sendmsg)
-*(.text.unix_stream_recvmsg)
-*(.text.unhash_process)
-*(.text.udp_v4_lookup_longway)
-*(.text.tty_ldisc_flush)
-*(.text.tty_ldisc_enable)
-*(.text.tty_hung_up_p)
-*(.text.tty_buffer_free_all)
-*(.text.tso_fragment)
-*(.text.try_to_del_timer_sync)
-*(.text.tcp_v4_err)
-*(.text.tcp_unhash)
-*(.text.tcp_seq_next)
-*(.text.tcp_select_initial_window)
-*(.text.tcp_sacktag_write_queue)
-*(.text.tcp_cwnd_validate)
-*(.text.sys_vhangup)
-*(.text.sys_uselib)
-*(.text.sys_symlink)
-*(.text.sys_signal)
-*(.text.sys_poll)
-*(.text.sys_mount)
-*(.text.sys_kill)
-*(.text.sys_ioctl)
-*(.text.sys_inotify_add_watch)
-*(.text.sys_getuid)
-*(.text.sys_getrlimit)
-*(.text.sys_getitimer)
-*(.text.sys_getgroups)
-*(.text.sys_ftruncate)
-*(.text.sysfs_lookup)
-*(.text.sys_exit_group)
-*(.text.stub_fork)
-*(.text.sscanf)
-*(.text.sock_map_fd)
-*(.text.sock_get_timestamp)
-*(.text.__sock_create)
-*(.text.smp_call_function_single)
-*(.text.sk_stop_timer)
-*(.text.skb_copy_and_csum_datagram)
-*(.text.__skb_checksum_complete)
-*(.text.single_next)
-*(.text.sigqueue_alloc)
-*(.text.shrink_dcache_parent)
-*(.text.select_idle_routine)
-*(.text.run_workqueue)
-*(.text.run_local_timers)
-*(.text.remove_inode_hash)
-*(.text.remove_dquot_ref)
-*(.text.register_binfmt)
-*(.text.read_cache_pages)
-*(.text.rb_last)
-*(.text.pty_open)
-*(.text.proc_root_readdir)
-*(.text.proc_pid_flush)
-*(.text.proc_pident_lookup)
-*(.text.proc_fill_super)
-*(.text.proc_exe_link)
-*(.text.posix_locks_deadlock)
-*(.text.pipe_iov_copy_from_user)
-*(.text.opost)
-*(.text.nf_register_hook)
-*(.text.netif_rx_ni)
-*(.text.m_start)
-*(.text.mpage_writepage)
-*(.text.mm_alloc)
-*(.text.memory_open)
-*(.text.mark_buffer_async_write)
-*(.text.lru_add_drain_all)
-*(.text.locks_init_lock)
-*(.text.locks_delete_lock)
-*(.text.lock_hrtimer_base)
-*(.text.load_script)
-*(.text.__kill_fasync)
-*(.text.ip_mc_sf_allow)
-*(.text.__ioremap)
-*(.text.int_with_check)
-*(.text.int_sqrt)
-*(.text.install_thread_keyring)
-*(.text.init_page_buffers)
-*(.text.inet_sock_destruct)
-*(.text.idle_notifier_register)
-*(.text.ide_execute_command)
-*(.text.ide_end_drive_cmd)
-*(.text.__ide_dma_host_on)
-*(.text.hrtimer_run_queues)
-*(.text.hpet_mask_rtc_irq_bit)
-*(.text.__get_zone_counts)
-*(.text.get_zone_counts)
-*(.text.get_write_access)
-*(.text.get_fs_struct)
-*(.text.get_dirty_limits)
-*(.text.generic_readlink)
-*(.text.free_hot_page)
-*(.text.finish_wait)
-*(.text.find_inode)
-*(.text.find_first_bit)
-*(.text.__filemap_fdatawrite_range)
-*(.text.__filemap_copy_from_user_iovec)
-*(.text.exit_aio)
-*(.text.elv_set_request)
-*(.text.elv_former_request)
-*(.text.dup_namespace)
-*(.text.dupfd)
-*(.text.dummy_socket_getsockopt)
-*(.text.dummy_sb_post_mountroot)
-*(.text.dummy_quotactl)
-*(.text.dummy_inode_rename)
-*(.text.__do_SAK)
-*(.text.do_pipe)
-*(.text.do_fsync)
-*(.text.d_instantiate_unique)
-*(.text.d_find_alias)
-*(.text.deny_write_access)
-*(.text.dentry_unhash)
-*(.text.d_delete)
-*(.text.datagram_poll)
-*(.text.cpuset_fork)
-*(.text.cpuid_read)
-*(.text.copy_namespace)
-*(.text.cond_resched)
-*(.text.check_version)
-*(.text.__change_page_attr)
-*(.text.cfq_slab_kill)
-*(.text.cfq_completed_request)
-*(.text.cdrom_pc_intr)
-*(.text.cdrom_decode_status)
-*(.text.cap_capset_check)
-*(.text.blk_put_request)
-*(.text.bio_fs_destructor)
-*(.text.bictcp_min_cwnd)
-*(.text.alloc_chrdev_region)
-*(.text.add_element)
-*(.text.acct_update_integrals)
-*(.text.write_boundary_block)
-*(.text.writeback_release)
-*(.text.writeback_inodes)
-*(.text.wake_up_state)
-*(.text.__wake_up_locked)
-*(.text.wake_futex)
-*(.text.wait_task_inactive)
-*(.text.__wait_on_freeing_inode)
-*(.text.wait_noreap_copyout)
-*(.text.vmstat_start)
-*(.text.vgacon_do_font_op)
-*(.text.vfs_readv)
-*(.text.vfs_quota_sync)
-*(.text.update_queue)
-*(.text.unshare_files)
-*(.text.unmap_vm_area)
-*(.text.unix_socketpair)
-*(.text.unix_release_sock)
-*(.text.unix_detach_fds)
-*(.text.unix_create1)
-*(.text.unix_bind)
-*(.text.udp_sendmsg)
-*(.text.udp_rcv)
-*(.text.udp_queue_rcv_skb)
-*(.text.uart_write)
-*(.text.uart_startup)
-*(.text.uart_open)
-*(.text.tty_vhangup)
-*(.text.tty_termios_baud_rate)
-*(.text.tty_release)
-*(.text.tty_ldisc_ref)
-*(.text.throttle_vm_writeout)
-*(.text.058)
-*(.text.tcp_xmit_probe_skb)
-*(.text.tcp_v4_send_check)
-*(.text.tcp_v4_destroy_sock)
-*(.text.tcp_sync_mss)
-*(.text.tcp_snd_test)
-*(.text.tcp_slow_start)
-*(.text.tcp_send_fin)
-*(.text.tcp_rtt_estimator)
-*(.text.tcp_parse_options)
-*(.text.tcp_ioctl)
-*(.text.tcp_init_tso_segs)
-*(.text.tcp_init_cwnd)
-*(.text.tcp_getsockopt)
-*(.text.tcp_fin)
-*(.text.tcp_connect)
-*(.text.tcp_cong_avoid)
-*(.text.__tcp_checksum_complete_user)
-*(.text.task_dumpable)
-*(.text.sys_wait4)
-*(.text.sys_utimes)
-*(.text.sys_symlinkat)
-*(.text.sys_socketpair)
-*(.text.sys_rmdir)
-*(.text.sys_readahead)
-*(.text.sys_nanosleep)
-*(.text.sys_linkat)
-*(.text.sys_fstat)
-*(.text.sysfs_readdir)
-*(.text.sys_execve)
-*(.text.sysenter_tracesys)
-*(.text.sys_chown)
-*(.text.stub_clone)
-*(.text.strrchr)
-*(.text.strncpy)
-*(.text.stopmachine_set_state)
-*(.text.sock_sendmsg)
-*(.text.sock_release)
-*(.text.sock_fasync)
-*(.text.sock_close)
-*(.text.sk_stream_write_space)
-*(.text.sk_reset_timer)
-*(.text.skb_split)
-*(.text.skb_recv_datagram)
-*(.text.skb_queue_tail)
-*(.text.sk_attach_filter)
-*(.text.si_swapinfo)
-*(.text.simple_strtoll)
-*(.text.set_termios)
-*(.text.set_task_comm)
-*(.text.set_shrinker)
-*(.text.set_normalized_timespec)
-*(.text.set_brk)
-*(.text.serial_in)
-*(.text.seq_printf)
-*(.text.secure_dccp_sequence_number)
-*(.text.rwlock_bug)
-*(.text.rt_hash_code)
-*(.text.__rta_fill)
-*(.text.__request_resource)
-*(.text.relocate_new_kernel)
-*(.text.release_thread)
-*(.text.release_mem)
-*(.text.rb_prev)
-*(.text.rb_first)
-*(.text.random_poll)
-*(.text.__put_super_and_need_restart)
-*(.text.pty_write)
-*(.text.ptrace_stop)
-*(.text.proc_self_readlink)
-*(.text.proc_root_lookup)
-*(.text.proc_root_link)
-*(.text.proc_pid_make_inode)
-*(.text.proc_pid_attr_write)
-*(.text.proc_lookupfd)
-*(.text.proc_delete_inode)
-*(.text.posix_same_owner)
-*(.text.posix_block_lock)
-*(.text.poll_initwait)
-*(.text.pipe_write)
-*(.text.pipe_read_fasync)
-*(.text.pipe_ioctl)
-*(.text.pdflush)
-*(.text.pci_user_read_config_dword)
-*(.text.page_readlink)
-*(.text.null_lseek)
-*(.text.nf_hook_slow)
-*(.text.netlink_sock_destruct)
-*(.text.netlink_broadcast)
-*(.text.neigh_resolve_output)
-*(.text.name_to_int)
-*(.text.mwait_idle)
-*(.text.mutex_trylock)
-*(.text.mutex_debug_check_no_locks_held)
-*(.text.m_stop)
-*(.text.mpage_end_io_write)
-*(.text.mpage_alloc)
-*(.text.move_page_tables)
-*(.text.mounts_open)
-*(.text.__memset)
-*(.text.memcpy_fromiovec)
-*(.text.make_8259A_irq)
-*(.text.lookup_user_key_possessed)
-*(.text.lookup_create)
-*(.text.locks_insert_lock)
-*(.text.locks_alloc_lock)
-*(.text.kthread_should_stop)
-*(.text.kswapd)
-*(.text.kobject_uevent)
-*(.text.kobject_get_path)
-*(.text.kobject_get)
-*(.text.klist_children_put)
-*(.text.__ip_route_output_key)
-*(.text.ip_flush_pending_frames)
-*(.text.ip_compute_csum)
-*(.text.ip_append_data)
-*(.text.ioc_set_batching)
-*(.text.invalidate_inode_pages)
-*(.text.__invalidate_device)
-*(.text.install_arg_page)
-*(.text.in_sched_functions)
-*(.text.inotify_unmount_inodes)
-*(.text.init_once)
-*(.text.init_cdrom_command)
-*(.text.inet_stream_connect)
-*(.text.inet_sk_rebuild_header)
-*(.text.inet_csk_addr2sockaddr)
-*(.text.inet_create)
-*(.text.ifind)
-*(.text.ide_setup_dma)
-*(.text.ide_outsw)
-*(.text.ide_fixstring)
-*(.text.ide_dma_setup)
-*(.text.ide_cdrom_packet)
-*(.text.ide_cd_put)
-*(.text.ide_build_sglist)
-*(.text.i8259A_shutdown)
-*(.text.hung_up_tty_ioctl)
-*(.text.hrtimer_nanosleep)
-*(.text.hrtimer_init)
-*(.text.hrtimer_cancel)
-*(.text.hash_futex)
-*(.text.group_send_sig_info)
-*(.text.grab_cache_page_nowait)
-*(.text.get_wchan)
-*(.text.get_stack)
-*(.text.get_page_state)
-*(.text.getnstimeofday)
-*(.text.get_node)
-*(.text.get_kprobe)
-*(.text.generic_unplug_device)
-*(.text.free_task)
-*(.text.frag_show)
-*(.text.find_next_zero_string)
-*(.text.filp_open)
-*(.text.fillonedir)
-*(.text.exit_io_context)
-*(.text.exit_idle)
-*(.text.exact_lock)
-*(.text.eth_header)
-*(.text.dummy_unregister_security)
-*(.text.dummy_socket_post_create)
-*(.text.dummy_socket_listen)
-*(.text.dummy_quota_on)
-*(.text.dummy_inode_follow_link)
-*(.text.dummy_file_receive)
-*(.text.dummy_file_mprotect)
-*(.text.dummy_file_lock)
-*(.text.dummy_file_ioctl)
-*(.text.dummy_bprm_post_apply_creds)
-*(.text.do_writepages)
-*(.text.__down_interruptible)
-*(.text.do_notify_resume)
-*(.text.do_acct_process)
-*(.text.del_timer_sync)
-*(.text.default_rebuild_header)
-*(.text.d_callback)
-*(.text.dcache_readdir)
-*(.text.ctrl_dumpfamily)
-*(.text.cpuset_rmdir)
-*(.text.copy_strings_kernel)
-*(.text.con_write_room)
-*(.text.complete_all)
-*(.text.collect_sigign_sigcatch)
-*(.text.clear_user)
-*(.text.check_unthrottle)
-*(.text.cdrom_release)
-*(.text.cdrom_newpc_intr)
-*(.text.cdrom_ioctl)
-*(.text.cdrom_check_status)
-*(.text.cdev_put)
-*(.text.cdev_add)
-*(.text.cap_ptrace)
-*(.text.cap_bprm_secureexec)
-*(.text.cache_alloc_refill)
-*(.text.bmap)
-*(.text.blk_run_queue)
-*(.text.blk_queue_dma_alignment)
-*(.text.blk_ordered_req_seq)
-*(.text.blk_backing_dev_unplug)
-*(.text.__bitmap_subset)
-*(.text.__bitmap_and)
-*(.text.bio_unmap_user)
-*(.text.__bforget)
-*(.text.bd_forget)
-*(.text.bad_pipe_w)
-*(.text.bad_get_user)
-*(.text.audit_free)
-*(.text.anon_vma_ctor)
-*(.text.anon_pipe_buf_map)
-*(.text.alloc_sock_iocb)
-*(.text.alloc_fdset)
-*(.text.aio_kick_handler)
-*(.text.__add_entropy_words)
-*(.text.add_disk_randomness)
diff --git a/arch/x86_64/kernel/genapic.c b/arch/x86_64/kernel/genapic.c
index 0b3603adf56..47496a40e84 100644
--- a/arch/x86_64/kernel/genapic.c
+++ b/arch/x86_64/kernel/genapic.c
@@ -11,120 +11,54 @@
#include <linux/threads.h>
#include <linux/cpumask.h>
#include <linux/string.h>
+#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/ctype.h>
#include <linux/init.h>
-#include <linux/module.h>
#include <asm/smp.h>
#include <asm/ipi.h>
+#include <asm/genapic.h>
-#if defined(CONFIG_ACPI)
+#ifdef CONFIG_ACPI
#include <acpi/acpi_bus.h>
#endif
/* which logical CPU number maps to which CPU (physical APIC ID) */
-u8 x86_cpu_to_apicid[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = BAD_APICID };
+u8 x86_cpu_to_apicid[NR_CPUS] __read_mostly
+ = { [0 ... NR_CPUS-1] = BAD_APICID };
EXPORT_SYMBOL(x86_cpu_to_apicid);
-u8 x86_cpu_to_log_apicid[NR_CPUS] = { [0 ... NR_CPUS-1] = BAD_APICID };
-extern struct genapic apic_cluster;
-extern struct genapic apic_flat;
-extern struct genapic apic_physflat;
+u8 x86_cpu_to_log_apicid[NR_CPUS] = { [0 ... NR_CPUS-1] = BAD_APICID };
-struct genapic *genapic = &apic_flat;
-struct genapic *genapic_force;
+struct genapic __read_mostly *genapic = &apic_flat;
/*
* Check the APIC IDs in bios_cpu_apicid and choose the APIC mode.
*/
-void __init clustered_apic_check(void)
+void __init setup_apic_routing(void)
{
- long i;
- u8 clusters, max_cluster;
- u8 id;
- u8 cluster_cnt[NUM_APIC_CLUSTERS];
- int max_apic = 0;
-
- /* genapic selection can be forced because of certain quirks.
- */
- if (genapic_force) {
- genapic = genapic_force;
- goto print;
- }
-
-#if defined(CONFIG_ACPI)
+#ifdef CONFIG_ACPI
/*
- * Some x86_64 machines use physical APIC mode regardless of how many
- * procs/clusters are present (x86_64 ES7000 is an example).
+ * Quirk: some x86_64 machines can only use physical APIC mode
+ * regardless of how many processors are present (x86_64 ES7000
+ * is an example).
*/
- if (acpi_gbl_FADT.header.revision > FADT2_REVISION_ID)
- if (acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL) {
- genapic = &apic_cluster;
- goto print;
- }
-#endif
-
- memset(cluster_cnt, 0, sizeof(cluster_cnt));
- for (i = 0; i < NR_CPUS; i++) {
- id = bios_cpu_apicid[i];
- if (id == BAD_APICID)
- continue;
- if (id > max_apic)
- max_apic = id;
- cluster_cnt[APIC_CLUSTERID(id)]++;
- }
-
- /* Don't use clustered mode on AMD platforms. */
- if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
+ if (acpi_gbl_FADT.header.revision > FADT2_REVISION_ID &&
+ (acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL))
genapic = &apic_physflat;
-#ifndef CONFIG_HOTPLUG_CPU
- /* In the CPU hotplug case we cannot use broadcast mode
- because that opens a race when a CPU is removed.
- Stay at physflat mode in this case.
- It is bad to do this unconditionally though. Once
- we have ACPI platform support for CPU hotplug
- we should detect hotplug capablity from ACPI tables and
- only do this when really needed. -AK */
- if (max_apic <= 8)
- genapic = &apic_flat;
+ else
#endif
- goto print;
- }
- clusters = 0;
- max_cluster = 0;
-
- for (i = 0; i < NUM_APIC_CLUSTERS; i++) {
- if (cluster_cnt[i] > 0) {
- ++clusters;
- if (cluster_cnt[i] > max_cluster)
- max_cluster = cluster_cnt[i];
- }
- }
-
- /*
- * If we have clusters <= 1 and CPUs <= 8 in cluster 0, then flat mode,
- * else if max_cluster <= 4 and cluster_cnt[15] == 0, clustered logical
- * else physical mode.
- * (We don't use lowest priority delivery + HW APIC IRQ steering, so
- * can ignore the clustered logical case and go straight to physical.)
- */
- if (clusters <= 1 && max_cluster <= 8 && cluster_cnt[0] == max_cluster) {
-#ifdef CONFIG_HOTPLUG_CPU
- /* Don't use APIC shortcuts in CPU hotplug to avoid races */
- genapic = &apic_physflat;
-#else
+ if (cpus_weight(cpu_possible_map) <= 8)
genapic = &apic_flat;
-#endif
- } else
- genapic = &apic_cluster;
+ else
+ genapic = &apic_physflat;
-print:
printk(KERN_INFO "Setting APIC routing to %s\n", genapic->name);
}
-/* Same for both flat and clustered. */
+/* Same for both flat and physical. */
void send_IPI_self(int vector)
{
diff --git a/arch/x86_64/kernel/genapic_cluster.c b/arch/x86_64/kernel/genapic_cluster.c
deleted file mode 100644
index 73d76308b95..00000000000
--- a/arch/x86_64/kernel/genapic_cluster.c
+++ /dev/null
@@ -1,137 +0,0 @@
-/*
- * Copyright 2004 James Cleverdon, IBM.
- * Subject to the GNU Public License, v.2
- *
- * Clustered APIC subarch code. Up to 255 CPUs, physical delivery.
- * (A more realistic maximum is around 230 CPUs.)
- *
- * Hacked for x86-64 by James Cleverdon from i386 architecture code by
- * Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and
- * James Cleverdon.
- */
-#include <linux/threads.h>
-#include <linux/cpumask.h>
-#include <linux/string.h>
-#include <linux/kernel.h>
-#include <linux/ctype.h>
-#include <linux/init.h>
-#include <asm/smp.h>
-#include <asm/ipi.h>
-
-
-/*
- * Set up the logical destination ID.
- *
- * Intel recommends to set DFR, LDR and TPR before enabling
- * an APIC. See e.g. "AP-388 82489DX User's Manual" (Intel
- * document number 292116). So here it goes...
- */
-static void cluster_init_apic_ldr(void)
-{
- unsigned long val, id;
- long i, count;
- u8 lid;
- u8 my_id = hard_smp_processor_id();
- u8 my_cluster = APIC_CLUSTER(my_id);
-
- /* Create logical APIC IDs by counting CPUs already in cluster. */
- for (count = 0, i = NR_CPUS; --i >= 0; ) {
- lid = x86_cpu_to_log_apicid[i];
- if (lid != BAD_APICID && APIC_CLUSTER(lid) == my_cluster)
- ++count;
- }
- /*
- * We only have a 4 wide bitmap in cluster mode. There's no way
- * to get above 60 CPUs and still give each one it's own bit.
- * But, we're using physical IRQ delivery, so we don't care.
- * Use bit 3 for the 4th through Nth CPU in each cluster.
- */
- if (count >= XAPIC_DEST_CPUS_SHIFT)
- count = 3;
- id = my_cluster | (1UL << count);
- x86_cpu_to_log_apicid[smp_processor_id()] = id;
- apic_write(APIC_DFR, APIC_DFR_CLUSTER);
- val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
- val |= SET_APIC_LOGICAL_ID(id);
- apic_write(APIC_LDR, val);
-}
-
-/* Start with all IRQs pointing to boot CPU. IRQ balancing will shift them. */
-
-static cpumask_t cluster_target_cpus(void)
-{
- return cpumask_of_cpu(0);
-}
-
-static cpumask_t cluster_vector_allocation_domain(int cpu)
-{
- cpumask_t domain = CPU_MASK_NONE;
- cpu_set(cpu, domain);
- return domain;
-}
-
-static void cluster_send_IPI_mask(cpumask_t mask, int vector)
-{
- send_IPI_mask_sequence(mask, vector);
-}
-
-static void cluster_send_IPI_allbutself(int vector)
-{
- cpumask_t mask = cpu_online_map;
-
- cpu_clear(smp_processor_id(), mask);
-
- if (!cpus_empty(mask))
- cluster_send_IPI_mask(mask, vector);
-}
-
-static void cluster_send_IPI_all(int vector)
-{
- cluster_send_IPI_mask(cpu_online_map, vector);
-}
-
-static int cluster_apic_id_registered(void)
-{
- return 1;
-}
-
-static unsigned int cluster_cpu_mask_to_apicid(cpumask_t cpumask)
-{
- int cpu;
-
- /*
- * We're using fixed IRQ delivery, can only return one phys APIC ID.
- * May as well be the first.
- */
- cpu = first_cpu(cpumask);
- if ((unsigned)cpu < NR_CPUS)
- return x86_cpu_to_apicid[cpu];
- else
- return BAD_APICID;
-}
-
-/* cpuid returns the value latched in the HW at reset, not the APIC ID
- * register's value. For any box whose BIOS changes APIC IDs, like
- * clustered APIC systems, we must use hard_smp_processor_id.
- *
- * See Intel's IA-32 SW Dev's Manual Vol2 under CPUID.
- */
-static unsigned int phys_pkg_id(int index_msb)
-{
- return hard_smp_processor_id() >> index_msb;
-}
-
-struct genapic apic_cluster = {
- .name = "clustered",
- .int_delivery_mode = dest_Fixed,
- .int_dest_mode = (APIC_DEST_PHYSICAL != 0),
- .target_cpus = cluster_target_cpus,
- .vector_allocation_domain = cluster_vector_allocation_domain,
- .apic_id_registered = cluster_apic_id_registered,
- .init_apic_ldr = cluster_init_apic_ldr,
- .send_IPI_all = cluster_send_IPI_all,
- .send_IPI_allbutself = cluster_send_IPI_allbutself,
- .send_IPI_mask = cluster_send_IPI_mask,
- .cpu_mask_to_apicid = cluster_cpu_mask_to_apicid,
- .phys_pkg_id = phys_pkg_id,
-};
diff --git a/arch/x86_64/kernel/genapic_flat.c b/arch/x86_64/kernel/genapic_flat.c
index 7c01db8fa9d..ecb01eefdd2 100644
--- a/arch/x86_64/kernel/genapic_flat.c
+++ b/arch/x86_64/kernel/genapic_flat.c
@@ -8,6 +8,7 @@
* Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and
* James Cleverdon.
*/
+#include <linux/errno.h>
#include <linux/threads.h>
#include <linux/cpumask.h>
#include <linux/string.h>
@@ -16,6 +17,7 @@
#include <linux/init.h>
#include <asm/smp.h>
#include <asm/ipi.h>
+#include <asm/genapic.h>
static cpumask_t flat_target_cpus(void)
{
@@ -60,31 +62,10 @@ static void flat_init_apic_ldr(void)
static void flat_send_IPI_mask(cpumask_t cpumask, int vector)
{
unsigned long mask = cpus_addr(cpumask)[0];
- unsigned long cfg;
unsigned long flags;
local_irq_save(flags);
-
- /*
- * Wait for idle.
- */
- apic_wait_icr_idle();
-
- /*
- * prepare target chip field
- */
- cfg = __prepare_ICR2(mask);
- apic_write(APIC_ICR2, cfg);
-
- /*
- * program the ICR
- */
- cfg = __prepare_ICR(0, vector, APIC_DEST_LOGICAL);
-
- /*
- * Send the IPI. The write to APIC_ICR fires this off.
- */
- apic_write(APIC_ICR, cfg);
+ __send_IPI_dest_field(mask, vector, APIC_DEST_LOGICAL);
local_irq_restore(flags);
}
diff --git a/arch/x86_64/kernel/head.S b/arch/x86_64/kernel/head.S
index 598a4d0351f..1fab487dee8 100644
--- a/arch/x86_64/kernel/head.S
+++ b/arch/x86_64/kernel/head.S
@@ -5,6 +5,7 @@
* Copyright (C) 2000 Pavel Machek <pavel@suse.cz>
* Copyright (C) 2000 Karsten Keil <kkeil@suse.de>
* Copyright (C) 2001,2002 Andi Kleen <ak@suse.de>
+ * Copyright (C) 2005 Eric Biederman <ebiederm@xmission.com>
*/
@@ -13,97 +14,131 @@
#include <linux/init.h>
#include <asm/desc.h>
#include <asm/segment.h>
+#include <asm/pgtable.h>
#include <asm/page.h>
#include <asm/msr.h>
#include <asm/cache.h>
-
+
/* we are not able to switch in one step to the final KERNEL ADRESS SPACE
- * because we need identity-mapped pages on setup so define __START_KERNEL to
- * 0x100000 for this stage
- *
+ * because we need identity-mapped pages.
+ *
*/
.text
.section .bootstrap.text
- .code32
- .globl startup_32
-/* %bx: 1 if coming from smp trampoline on secondary cpu */
-startup_32:
-
+ .code64
+ .globl startup_64
+startup_64:
+
/*
- * At this point the CPU runs in 32bit protected mode (CS.D = 1) with
- * paging disabled and the point of this file is to switch to 64bit
- * long mode with a kernel mapping for kerneland to jump into the
- * kernel virtual addresses.
- * There is no stack until we set one up.
+ * At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 1,
+ * and someone has loaded an identity mapped page table
+ * for us. These identity mapped page tables map all of the
+ * kernel pages and possibly all of memory.
+ *
+ * %esi holds a physical pointer to real_mode_data.
+ *
+ * We come here either directly from a 64bit bootloader, or from
+ * arch/x86_64/boot/compressed/head.S.
+ *
+ * We only come here initially at boot nothing else comes here.
+ *
+ * Since we may be loaded at an address different from what we were
+ * compiled to run at we first fixup the physical addresses in our page
+ * tables and then reload them.
*/
- /* Initialize the %ds segment register */
- movl $__KERNEL_DS,%eax
- movl %eax,%ds
-
- /* Load new GDT with the 64bit segments using 32bit descriptor */
- lgdt pGDT32 - __START_KERNEL_map
-
- /* If the CPU doesn't support CPUID this will double fault.
- * Unfortunately it is hard to check for CPUID without a stack.
+ /* Compute the delta between the address I am compiled to run at and the
+ * address I am actually running at.
*/
-
- /* Check if extended functions are implemented */
- movl $0x80000000, %eax
- cpuid
- cmpl $0x80000000, %eax
- jbe no_long_mode
- /* Check if long mode is implemented */
- mov $0x80000001, %eax
- cpuid
- btl $29, %edx
- jnc no_long_mode
-
- /*
- * Prepare for entering 64bits mode
+ leaq _text(%rip), %rbp
+ subq $_text - __START_KERNEL_map, %rbp
+
+ /* Is the address not 2M aligned? */
+ movq %rbp, %rax
+ andl $~LARGE_PAGE_MASK, %eax
+ testl %eax, %eax
+ jnz bad_address
+
+ /* Is the address too large? */
+ leaq _text(%rip), %rdx
+ movq $PGDIR_SIZE, %rax
+ cmpq %rax, %rdx
+ jae bad_address
+
+ /* Fixup the physical addresses in the page table
*/
+ addq %rbp, init_level4_pgt + 0(%rip)
+ addq %rbp, init_level4_pgt + (258*8)(%rip)
+ addq %rbp, init_level4_pgt + (511*8)(%rip)
+
+ addq %rbp, level3_ident_pgt + 0(%rip)
+ addq %rbp, level3_kernel_pgt + (510*8)(%rip)
+
+ /* Add an Identity mapping if I am above 1G */
+ leaq _text(%rip), %rdi
+ andq $LARGE_PAGE_MASK, %rdi
+
+ movq %rdi, %rax
+ shrq $PUD_SHIFT, %rax
+ andq $(PTRS_PER_PUD - 1), %rax
+ jz ident_complete
+
+ leaq (level2_spare_pgt - __START_KERNEL_map + _KERNPG_TABLE)(%rbp), %rdx
+ leaq level3_ident_pgt(%rip), %rbx
+ movq %rdx, 0(%rbx, %rax, 8)
+
+ movq %rdi, %rax
+ shrq $PMD_SHIFT, %rax
+ andq $(PTRS_PER_PMD - 1), %rax
+ leaq __PAGE_KERNEL_LARGE_EXEC(%rdi), %rdx
+ leaq level2_spare_pgt(%rip), %rbx
+ movq %rdx, 0(%rbx, %rax, 8)
+ident_complete:
+
+ /* Fixup the kernel text+data virtual addresses
+ */
+ leaq level2_kernel_pgt(%rip), %rdi
+ leaq 4096(%rdi), %r8
+ /* See if it is a valid page table entry */
+1: testq $1, 0(%rdi)
+ jz 2f
+ addq %rbp, 0(%rdi)
+ /* Go to the next page */
+2: addq $8, %rdi
+ cmp %r8, %rdi
+ jne 1b
+
+ /* Fixup phys_base */
+ addq %rbp, phys_base(%rip)
- /* Enable PAE mode */
- xorl %eax, %eax
- btsl $5, %eax
- movl %eax, %cr4
-
- /* Setup early boot stage 4 level pagetables */
- movl $(boot_level4_pgt - __START_KERNEL_map), %eax
- movl %eax, %cr3
-
- /* Setup EFER (Extended Feature Enable Register) */
- movl $MSR_EFER, %ecx
- rdmsr
-
- /* Enable Long Mode */
- btsl $_EFER_LME, %eax
-
- /* Make changes effective */
- wrmsr
+#ifdef CONFIG_SMP
+ addq %rbp, trampoline_level4_pgt + 0(%rip)
+ addq %rbp, trampoline_level4_pgt + (511*8)(%rip)
+#endif
+#ifdef CONFIG_ACPI_SLEEP
+ addq %rbp, wakeup_level4_pgt + 0(%rip)
+ addq %rbp, wakeup_level4_pgt + (511*8)(%rip)
+#endif
- xorl %eax, %eax
- btsl $31, %eax /* Enable paging and in turn activate Long Mode */
- btsl $0, %eax /* Enable protected mode */
- /* Make changes effective */
- movl %eax, %cr0
- /*
- * At this point we're in long mode but in 32bit compatibility mode
- * with EFER.LME = 1, CS.L = 0, CS.D = 1 (and in turn
- * EFER.LMA = 1). Now we want to jump in 64bit mode, to do that we use
- * the new gdt/idt that has __KERNEL_CS with CS.L = 1.
+ /* Due to ENTRY(), sometimes the empty space gets filled with
+ * zeros. Better take a jmp than relying on empty space being
+ * filled with 0x90 (nop)
*/
- ljmp $__KERNEL_CS, $(startup_64 - __START_KERNEL_map)
-
- .code64
- .org 0x100
- .globl startup_64
-startup_64:
- /* We come here either from startup_32
- * or directly from a 64bit bootloader.
- * Since we may have come directly from a bootloader we
- * reload the page tables here.
+ jmp secondary_startup_64
+ENTRY(secondary_startup_64)
+ /*
+ * At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 1,
+ * and someone has loaded a mapped page table.
+ *
+ * %esi holds a physical pointer to real_mode_data.
+ *
+ * We come here either from startup_64 (using physical addresses)
+ * or from trampoline.S (using virtual addresses).
+ *
+ * Using virtual addresses from trampoline.S removes the need
+ * to have any identity mapped pages in the kernel page table
+ * after the boot processor executes this code.
*/
/* Enable PAE mode and PGE */
@@ -113,9 +148,15 @@ startup_64:
movq %rax, %cr4
/* Setup early boot stage 4 level pagetables. */
- movq $(boot_level4_pgt - __START_KERNEL_map), %rax
+ movq $(init_level4_pgt - __START_KERNEL_map), %rax
+ addq phys_base(%rip), %rax
movq %rax, %cr3
+ /* Ensure I am executing from virtual addresses */
+ movq $1f, %rax
+ jmp *%rax
+1:
+
/* Check if nx is implemented */
movl $0x80000001, %eax
cpuid
@@ -124,17 +165,11 @@ startup_64:
/* Setup EFER (Extended Feature Enable Register) */
movl $MSR_EFER, %ecx
rdmsr
-
- /* Enable System Call */
- btsl $_EFER_SCE, %eax
-
- /* No Execute supported? */
- btl $20,%edi
+ btsl $_EFER_SCE, %eax /* Enable System Call */
+ btl $20,%edi /* No Execute supported? */
jnc 1f
btsl $_EFER_NX, %eax
-1:
- /* Make changes effective */
- wrmsr
+1: wrmsr /* Make changes effective */
/* Setup cr0 */
#define CR0_PM 1 /* protected mode */
@@ -161,7 +196,7 @@ startup_64:
* addresses where we're currently running on. We have to do that here
* because in 32bit we couldn't load a 64bit linear address.
*/
- lgdt cpu_gdt_descr
+ lgdt cpu_gdt_descr(%rip)
/* set up data segments. actually 0 would do too */
movl $__KERNEL_DS,%eax
@@ -212,6 +247,9 @@ initial_code:
init_rsp:
.quad init_thread_union+THREAD_SIZE-8
+bad_address:
+ jmp bad_address
+
ENTRY(early_idt_handler)
cmpl $2,early_recursion_flag(%rip)
jz 1f
@@ -240,110 +278,66 @@ early_idt_msg:
early_idt_ripmsg:
.asciz "RIP %s\n"
-.code32
-ENTRY(no_long_mode)
- /* This isn't an x86-64 CPU so hang */
-1:
- jmp 1b
-
-.org 0xf00
- .globl pGDT32
-pGDT32:
- .word gdt_end-cpu_gdt_table-1
- .long cpu_gdt_table-__START_KERNEL_map
-
-.org 0xf10
-ljumpvector:
- .long startup_64-__START_KERNEL_map
- .word __KERNEL_CS
+.balign PAGE_SIZE
-ENTRY(stext)
-ENTRY(_stext)
-
- $page = 0
#define NEXT_PAGE(name) \
- $page = $page + 1; \
- .org $page * 0x1000; \
- phys_/**/name = $page * 0x1000 + __PHYSICAL_START; \
+ .balign PAGE_SIZE; \
ENTRY(name)
+/* Automate the creation of 1 to 1 mapping pmd entries */
+#define PMDS(START, PERM, COUNT) \
+ i = 0 ; \
+ .rept (COUNT) ; \
+ .quad (START) + (i << 21) + (PERM) ; \
+ i = i + 1 ; \
+ .endr
+
+ /*
+ * This default setting generates an ident mapping at address 0x100000
+ * and a mapping for the kernel that precisely maps virtual address
+ * 0xffffffff80000000 to physical address 0x000000. (always using
+ * 2Mbyte large pages provided by PAE mode)
+ */
NEXT_PAGE(init_level4_pgt)
- /* This gets initialized in x86_64_start_kernel */
- .fill 512,8,0
+ .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
+ .fill 257,8,0
+ .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
+ .fill 252,8,0
+ /* (2^48-(2*1024*1024*1024))/(2^39) = 511 */
+ .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE
NEXT_PAGE(level3_ident_pgt)
- .quad phys_level2_ident_pgt | 0x007
+ .quad level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
.fill 511,8,0
NEXT_PAGE(level3_kernel_pgt)
.fill 510,8,0
/* (2^48-(2*1024*1024*1024)-((2^39)*511))/(2^30) = 510 */
- .quad phys_level2_kernel_pgt | 0x007
+ .quad level2_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE
.fill 1,8,0
NEXT_PAGE(level2_ident_pgt)
- /* 40MB for bootup. */
- i = 0
- .rept 20
- .quad i << 21 | 0x083
- i = i + 1
- .endr
- /* Temporary mappings for the super early allocator in arch/x86_64/mm/init.c */
- .globl temp_boot_pmds
-temp_boot_pmds:
- .fill 492,8,0
-
+ /* Since I easily can, map the first 1G.
+ * Don't set NX because code runs from these pages.
+ */
+ PMDS(0x0000000000000000, __PAGE_KERNEL_LARGE_EXEC, PTRS_PER_PMD)
+
NEXT_PAGE(level2_kernel_pgt)
/* 40MB kernel mapping. The kernel code cannot be bigger than that.
When you change this change KERNEL_TEXT_SIZE in page.h too. */
/* (2^48-(2*1024*1024*1024)-((2^39)*511)-((2^30)*510)) = 0 */
- i = 0
- .rept 20
- .quad i << 21 | 0x183
- i = i + 1
- .endr
+ PMDS(0x0000000000000000, __PAGE_KERNEL_LARGE_EXEC|_PAGE_GLOBAL,
+ KERNEL_TEXT_SIZE/PMD_SIZE)
/* Module mapping starts here */
- .fill 492,8,0
+ .fill (PTRS_PER_PMD - (KERNEL_TEXT_SIZE/PMD_SIZE)),8,0
-NEXT_PAGE(level3_physmem_pgt)
- .quad phys_level2_kernel_pgt | 0x007 /* so that __va works even before pagetable_init */
- .fill 511,8,0
+NEXT_PAGE(level2_spare_pgt)
+ .fill 512,8,0
+#undef PMDS
#undef NEXT_PAGE
.data
-
-#ifdef CONFIG_ACPI_SLEEP
- .align PAGE_SIZE
-ENTRY(wakeup_level4_pgt)
- .quad phys_level3_ident_pgt | 0x007
- .fill 255,8,0
- .quad phys_level3_physmem_pgt | 0x007
- .fill 254,8,0
- /* (2^48-(2*1024*1024*1024))/(2^39) = 511 */
- .quad phys_level3_kernel_pgt | 0x007
-#endif
-
-#ifndef CONFIG_HOTPLUG_CPU
- __INITDATA
-#endif
- /*
- * This default setting generates an ident mapping at address 0x100000
- * and a mapping for the kernel that precisely maps virtual address
- * 0xffffffff80000000 to physical address 0x000000. (always using
- * 2Mbyte large pages provided by PAE mode)
- */
- .align PAGE_SIZE
-ENTRY(boot_level4_pgt)
- .quad phys_level3_ident_pgt | 0x007
- .fill 255,8,0
- .quad phys_level3_physmem_pgt | 0x007
- .fill 254,8,0
- /* (2^48-(2*1024*1024*1024))/(2^39) = 511 */
- .quad phys_level3_kernel_pgt | 0x007
-
- .data
-
.align 16
.globl cpu_gdt_descr
cpu_gdt_descr:
@@ -357,6 +351,10 @@ gdt:
.endr
#endif
+ENTRY(phys_base)
+ /* This must match the first entry in level2_kernel_pgt */
+ .quad 0x0000000000000000
+
/* We need valid kernel segments for data and code in long mode too
* IRET will check the segment types kkeil 2000/10/28
* Also sysret mandates a special GDT layout
@@ -370,13 +368,13 @@ gdt:
ENTRY(cpu_gdt_table)
.quad 0x0000000000000000 /* NULL descriptor */
+ .quad 0x00cf9b000000ffff /* __KERNEL32_CS */
+ .quad 0x00af9b000000ffff /* __KERNEL_CS */
+ .quad 0x00cf93000000ffff /* __KERNEL_DS */
+ .quad 0x00cffb000000ffff /* __USER32_CS */
+ .quad 0x00cff3000000ffff /* __USER_DS, __USER32_DS */
+ .quad 0x00affb000000ffff /* __USER_CS */
.quad 0x0 /* unused */
- .quad 0x00af9a000000ffff /* __KERNEL_CS */
- .quad 0x00cf92000000ffff /* __KERNEL_DS */
- .quad 0x00cffa000000ffff /* __USER32_CS */
- .quad 0x00cff2000000ffff /* __USER_DS, __USER32_DS */
- .quad 0x00affa000000ffff /* __USER_CS */
- .quad 0x00cf9a000000ffff /* __KERNEL32_CS */
.quad 0,0 /* TSS */
.quad 0,0 /* LDT */
.quad 0,0,0 /* three TLS descriptors */
diff --git a/arch/x86_64/kernel/head64.c b/arch/x86_64/kernel/head64.c
index 5f197b0a330..213d90e0475 100644
--- a/arch/x86_64/kernel/head64.c
+++ b/arch/x86_64/kernel/head64.c
@@ -18,8 +18,16 @@
#include <asm/setup.h>
#include <asm/desc.h>
#include <asm/pgtable.h>
+#include <asm/tlbflush.h>
#include <asm/sections.h>
+static void __init zap_identity_mappings(void)
+{
+ pgd_t *pgd = pgd_offset_k(0UL);
+ pgd_clear(pgd);
+ __flush_tlb();
+}
+
/* Don't add a printk in there. printk relies on the PDA which is not initialized
yet. */
static void __init clear_bss(void)
@@ -29,25 +37,24 @@ static void __init clear_bss(void)
}
#define NEW_CL_POINTER 0x228 /* Relative to real mode data */
-#define OLD_CL_MAGIC_ADDR 0x90020
+#define OLD_CL_MAGIC_ADDR 0x20
#define OLD_CL_MAGIC 0xA33F
-#define OLD_CL_BASE_ADDR 0x90000
-#define OLD_CL_OFFSET 0x90022
+#define OLD_CL_OFFSET 0x22
static void __init copy_bootdata(char *real_mode_data)
{
- int new_data;
+ unsigned long new_data;
char * command_line;
memcpy(x86_boot_params, real_mode_data, BOOT_PARAM_SIZE);
- new_data = *(int *) (x86_boot_params + NEW_CL_POINTER);
+ new_data = *(u32 *) (x86_boot_params + NEW_CL_POINTER);
if (!new_data) {
- if (OLD_CL_MAGIC != * (u16 *) OLD_CL_MAGIC_ADDR) {
+ if (OLD_CL_MAGIC != *(u16 *)(real_mode_data + OLD_CL_MAGIC_ADDR)) {
return;
}
- new_data = OLD_CL_BASE_ADDR + * (u16 *) OLD_CL_OFFSET;
+ new_data = __pa(real_mode_data) + *(u16 *)(real_mode_data + OLD_CL_OFFSET);
}
- command_line = (char *) ((u64)(new_data));
+ command_line = __va(new_data);
memcpy(boot_command_line, command_line, COMMAND_LINE_SIZE);
}
@@ -55,26 +62,30 @@ void __init x86_64_start_kernel(char * real_mode_data)
{
int i;
+ /*
+ * Make sure kernel is aligned to 2MB address. Catching it at compile
+ * time is better. Change your config file and compile the kernel
+ * for a 2MB aligned address (CONFIG_PHYSICAL_START)
+ */
+ BUILD_BUG_ON(CONFIG_PHYSICAL_START & (__KERNEL_ALIGN - 1));
+
/* clear bss before set_intr_gate with early_idt_handler */
clear_bss();
+ /* Make NULL pointers segfault */
+ zap_identity_mappings();
+
for (i = 0; i < IDT_ENTRIES; i++)
set_intr_gate(i, early_idt_handler);
asm volatile("lidt %0" :: "m" (idt_descr));
early_printk("Kernel alive\n");
- /*
- * switch to init_level4_pgt from boot_level4_pgt
- */
- memcpy(init_level4_pgt, boot_level4_pgt, PTRS_PER_PGD*sizeof(pgd_t));
- asm volatile("movq %0,%%cr3" :: "r" (__pa_symbol(&init_level4_pgt)));
-
for (i = 0; i < NR_CPUS; i++)
cpu_pda(i) = &boot_cpu_pda[i];
pda_init(0);
- copy_bootdata(real_mode_data);
+ copy_bootdata(__va(real_mode_data));
#ifdef CONFIG_SMP
cpu_set(0, cpu_online_map);
#endif
diff --git a/arch/x86_64/kernel/io_apic.c b/arch/x86_64/kernel/io_apic.c
index b7d2b76b92d..2a2df14dab7 100644
--- a/arch/x86_64/kernel/io_apic.c
+++ b/arch/x86_64/kernel/io_apic.c
@@ -907,10 +907,6 @@ static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, in
enable_8259A_irq(0);
}
-void __init UNEXPECTED_IO_APIC(void)
-{
-}
-
void __apicdebuginit print_IO_APIC(void)
{
int apic, i;
@@ -946,40 +942,16 @@ void __apicdebuginit print_IO_APIC(void)
printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].mpc_apicid);
printk(KERN_DEBUG ".... register #00: %08X\n", reg_00.raw);
printk(KERN_DEBUG "....... : physical APIC id: %02X\n", reg_00.bits.ID);
- if (reg_00.bits.__reserved_1 || reg_00.bits.__reserved_2)
- UNEXPECTED_IO_APIC();
printk(KERN_DEBUG ".... register #01: %08X\n", *(int *)&reg_01);
printk(KERN_DEBUG "....... : max redirection entries: %04X\n", reg_01.bits.entries);
- if ( (reg_01.bits.entries != 0x0f) && /* older (Neptune) boards */
- (reg_01.bits.entries != 0x17) && /* typical ISA+PCI boards */
- (reg_01.bits.entries != 0x1b) && /* Compaq Proliant boards */
- (reg_01.bits.entries != 0x1f) && /* dual Xeon boards */
- (reg_01.bits.entries != 0x22) && /* bigger Xeon boards */
- (reg_01.bits.entries != 0x2E) &&
- (reg_01.bits.entries != 0x3F) &&
- (reg_01.bits.entries != 0x03)
- )
- UNEXPECTED_IO_APIC();
printk(KERN_DEBUG "....... : PRQ implemented: %X\n", reg_01.bits.PRQ);
printk(KERN_DEBUG "....... : IO APIC version: %04X\n", reg_01.bits.version);
- if ( (reg_01.bits.version != 0x01) && /* 82489DX IO-APICs */
- (reg_01.bits.version != 0x02) && /* 82801BA IO-APICs (ICH2) */
- (reg_01.bits.version != 0x10) && /* oldest IO-APICs */
- (reg_01.bits.version != 0x11) && /* Pentium/Pro IO-APICs */
- (reg_01.bits.version != 0x13) && /* Xeon IO-APICs */
- (reg_01.bits.version != 0x20) /* Intel P64H (82806 AA) */
- )
- UNEXPECTED_IO_APIC();
- if (reg_01.bits.__reserved_1 || reg_01.bits.__reserved_2)
- UNEXPECTED_IO_APIC();
if (reg_01.bits.version >= 0x10) {
printk(KERN_DEBUG ".... register #02: %08X\n", reg_02.raw);
printk(KERN_DEBUG "....... : arbitration: %02X\n", reg_02.bits.arbitration);
- if (reg_02.bits.__reserved_1 || reg_02.bits.__reserved_2)
- UNEXPECTED_IO_APIC();
}
printk(KERN_DEBUG ".... IRQ redirection table:\n");
@@ -1407,8 +1379,7 @@ static void irq_complete_move(unsigned int irq)
vector = ~get_irq_regs()->orig_rax;
me = smp_processor_id();
- if ((vector == cfg->vector) &&
- cpu_isset(smp_processor_id(), cfg->domain)) {
+ if ((vector == cfg->vector) && cpu_isset(me, cfg->domain)) {
cpumask_t cleanup_mask;
cpus_and(cleanup_mask, cfg->old_domain, cpu_online_map);
diff --git a/arch/x86_64/kernel/ioport.c b/arch/x86_64/kernel/ioport.c
index 745b1f0f494..387d347b0e0 100644
--- a/arch/x86_64/kernel/ioport.c
+++ b/arch/x86_64/kernel/ioport.c
@@ -16,6 +16,7 @@
#include <linux/stddef.h>
#include <linux/slab.h>
#include <linux/thread_info.h>
+#include <linux/syscalls.h>
/* Set EXTENT bits starting at BASE in BITMAP to value TURN_ON. */
static void set_bitmap(unsigned long *bitmap, unsigned int base, unsigned int extent, int new_value)
diff --git a/arch/x86_64/kernel/machine_kexec.c b/arch/x86_64/kernel/machine_kexec.c
index 0497e3bd5bf..a8bb33c1a8f 100644
--- a/arch/x86_64/kernel/machine_kexec.c
+++ b/arch/x86_64/kernel/machine_kexec.c
@@ -191,19 +191,19 @@ NORET_TYPE void machine_kexec(struct kimage *image)
page_list[PA_CONTROL_PAGE] = __pa(control_page);
page_list[VA_CONTROL_PAGE] = (unsigned long)relocate_kernel;
- page_list[PA_PGD] = __pa(kexec_pgd);
+ page_list[PA_PGD] = __pa_symbol(&kexec_pgd);
page_list[VA_PGD] = (unsigned long)kexec_pgd;
- page_list[PA_PUD_0] = __pa(kexec_pud0);
+ page_list[PA_PUD_0] = __pa_symbol(&kexec_pud0);
page_list[VA_PUD_0] = (unsigned long)kexec_pud0;
- page_list[PA_PMD_0] = __pa(kexec_pmd0);
+ page_list[PA_PMD_0] = __pa_symbol(&kexec_pmd0);
page_list[VA_PMD_0] = (unsigned long)kexec_pmd0;
- page_list[PA_PTE_0] = __pa(kexec_pte0);
+ page_list[PA_PTE_0] = __pa_symbol(&kexec_pte0);
page_list[VA_PTE_0] = (unsigned long)kexec_pte0;
- page_list[PA_PUD_1] = __pa(kexec_pud1);
+ page_list[PA_PUD_1] = __pa_symbol(&kexec_pud1);
page_list[VA_PUD_1] = (unsigned long)kexec_pud1;
- page_list[PA_PMD_1] = __pa(kexec_pmd1);
+ page_list[PA_PMD_1] = __pa_symbol(&kexec_pmd1);
page_list[VA_PMD_1] = (unsigned long)kexec_pmd1;
- page_list[PA_PTE_1] = __pa(kexec_pte1);
+ page_list[PA_PTE_1] = __pa_symbol(&kexec_pte1);
page_list[VA_PTE_1] = (unsigned long)kexec_pte1;
page_list[PA_TABLE_PAGE] =
diff --git a/arch/x86_64/kernel/mce.c b/arch/x86_64/kernel/mce.c
index 8011a8e1c7d..fa267268247 100644
--- a/arch/x86_64/kernel/mce.c
+++ b/arch/x86_64/kernel/mce.c
@@ -323,10 +323,13 @@ void mce_log_therm_throt_event(unsigned int cpu, __u64 status)
#endif /* CONFIG_X86_MCE_INTEL */
/*
- * Periodic polling timer for "silent" machine check errors.
+ * Periodic polling timer for "silent" machine check errors. If the
+ * poller finds an MCE, poll 2x faster. When the poller finds no more
+ * errors, poll 2x slower (up to check_interval seconds).
*/
static int check_interval = 5 * 60; /* 5 minutes */
+static int next_interval; /* in jiffies */
static void mcheck_timer(struct work_struct *work);
static DECLARE_DELAYED_WORK(mcheck_work, mcheck_timer);
@@ -339,7 +342,6 @@ static void mcheck_check_cpu(void *info)
static void mcheck_timer(struct work_struct *work)
{
on_each_cpu(mcheck_check_cpu, NULL, 1, 1);
- schedule_delayed_work(&mcheck_work, check_interval * HZ);
/*
* It's ok to read stale data here for notify_user and
@@ -349,17 +351,30 @@ static void mcheck_timer(struct work_struct *work)
* writes.
*/
if (notify_user && console_logged) {
+ static unsigned long last_print;
+ unsigned long now = jiffies;
+
+ /* if we logged an MCE, reduce the polling interval */
+ next_interval = max(next_interval/2, HZ/100);
notify_user = 0;
clear_bit(0, &console_logged);
- printk(KERN_INFO "Machine check events logged\n");
+ if (time_after_eq(now, last_print + (check_interval*HZ))) {
+ last_print = now;
+ printk(KERN_INFO "Machine check events logged\n");
+ }
+ } else {
+ next_interval = min(next_interval*2, check_interval*HZ);
}
+
+ schedule_delayed_work(&mcheck_work, next_interval);
}
static __init int periodic_mcheck_init(void)
{
- if (check_interval)
- schedule_delayed_work(&mcheck_work, check_interval*HZ);
+ next_interval = check_interval * HZ;
+ if (next_interval)
+ schedule_delayed_work(&mcheck_work, next_interval);
return 0;
}
__initcall(periodic_mcheck_init);
@@ -597,12 +612,13 @@ static int mce_resume(struct sys_device *dev)
/* Reinit MCEs after user configuration changes */
static void mce_restart(void)
{
- if (check_interval)
+ if (next_interval)
cancel_delayed_work(&mcheck_work);
/* Timer race is harmless here */
on_each_cpu(mce_init, NULL, 1, 1);
- if (check_interval)
- schedule_delayed_work(&mcheck_work, check_interval*HZ);
+ next_interval = check_interval * HZ;
+ if (next_interval)
+ schedule_delayed_work(&mcheck_work, next_interval);
}
static struct sysdev_class mce_sysclass = {
diff --git a/arch/x86_64/kernel/mpparse.c b/arch/x86_64/kernel/mpparse.c
index 455aa0b932f..d0dc4891599 100644
--- a/arch/x86_64/kernel/mpparse.c
+++ b/arch/x86_64/kernel/mpparse.c
@@ -300,7 +300,7 @@ static int __init smp_read_mpc(struct mp_config_table *mpc)
}
}
}
- clustered_apic_check();
+ setup_apic_routing();
if (!num_processors)
printk(KERN_ERR "MPTABLE: no processors registered!\n");
return num_processors;
diff --git a/arch/x86_64/kernel/nmi.c b/arch/x86_64/kernel/nmi.c
index dfab9f16736..6cd2b30e2ff 100644
--- a/arch/x86_64/kernel/nmi.c
+++ b/arch/x86_64/kernel/nmi.c
@@ -27,28 +27,11 @@
#include <asm/proto.h>
#include <asm/kdebug.h>
#include <asm/mce.h>
-#include <asm/intel_arch_perfmon.h>
int unknown_nmi_panic;
int nmi_watchdog_enabled;
int panic_on_unrecovered_nmi;
-/* perfctr_nmi_owner tracks the ownership of the perfctr registers:
- * evtsel_nmi_owner tracks the ownership of the event selection
- * - different performance counters/ event selection may be reserved for
- * different subsystems this reservation system just tries to coordinate
- * things a little
- */
-
-/* this number is calculated from Intel's MSR_P4_CRU_ESCR5 register and it's
- * offset from MSR_P4_BSU_ESCR0. It will be the max for all platforms (for now)
- */
-#define NMI_MAX_COUNTER_BITS 66
-#define NMI_MAX_COUNTER_LONGS BITS_TO_LONGS(NMI_MAX_COUNTER_BITS)
-
-static DEFINE_PER_CPU(unsigned, perfctr_nmi_owner[NMI_MAX_COUNTER_LONGS]);
-static DEFINE_PER_CPU(unsigned, evntsel_nmi_owner[NMI_MAX_COUNTER_LONGS]);
-
static cpumask_t backtrace_mask = CPU_MASK_NONE;
/* nmi_active:
@@ -63,191 +46,11 @@ int panic_on_timeout;
unsigned int nmi_watchdog = NMI_DEFAULT;
static unsigned int nmi_hz = HZ;
-struct nmi_watchdog_ctlblk {
- int enabled;
- u64 check_bit;
- unsigned int cccr_msr;
- unsigned int perfctr_msr; /* the MSR to reset in NMI handler */
- unsigned int evntsel_msr; /* the MSR to select the events to handle */
-};
-static DEFINE_PER_CPU(struct nmi_watchdog_ctlblk, nmi_watchdog_ctlblk);
+static DEFINE_PER_CPU(short, wd_enabled);
/* local prototypes */
static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu);
-/* converts an msr to an appropriate reservation bit */
-static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr)
-{
- /* returns the bit offset of the performance counter register */
- switch (boot_cpu_data.x86_vendor) {
- case X86_VENDOR_AMD:
- return (msr - MSR_K7_PERFCTR0);
- case X86_VENDOR_INTEL:
- if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON))
- return (msr - MSR_ARCH_PERFMON_PERFCTR0);
- else
- return (msr - MSR_P4_BPU_PERFCTR0);
- }
- return 0;
-}
-
-/* converts an msr to an appropriate reservation bit */
-static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr)
-{
- /* returns the bit offset of the event selection register */
- switch (boot_cpu_data.x86_vendor) {
- case X86_VENDOR_AMD:
- return (msr - MSR_K7_EVNTSEL0);
- case X86_VENDOR_INTEL:
- if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON))
- return (msr - MSR_ARCH_PERFMON_EVENTSEL0);
- else
- return (msr - MSR_P4_BSU_ESCR0);
- }
- return 0;
-}
-
-/* checks for a bit availability (hack for oprofile) */
-int avail_to_resrv_perfctr_nmi_bit(unsigned int counter)
-{
- int cpu;
- BUG_ON(counter > NMI_MAX_COUNTER_BITS);
- for_each_possible_cpu (cpu) {
- if (test_bit(counter, &per_cpu(perfctr_nmi_owner, cpu)))
- return 0;
- }
- return 1;
-}
-
-/* checks the an msr for availability */
-int avail_to_resrv_perfctr_nmi(unsigned int msr)
-{
- unsigned int counter;
- int cpu;
-
- counter = nmi_perfctr_msr_to_bit(msr);
- BUG_ON(counter > NMI_MAX_COUNTER_BITS);
-
- for_each_possible_cpu (cpu) {
- if (test_bit(counter, &per_cpu(perfctr_nmi_owner, cpu)))
- return 0;
- }
- return 1;
-}
-
-static int __reserve_perfctr_nmi(int cpu, unsigned int msr)
-{
- unsigned int counter;
- if (cpu < 0)
- cpu = smp_processor_id();
-
- counter = nmi_perfctr_msr_to_bit(msr);
- BUG_ON(counter > NMI_MAX_COUNTER_BITS);
-
- if (!test_and_set_bit(counter, &per_cpu(perfctr_nmi_owner, cpu)))
- return 1;
- return 0;
-}
-
-static void __release_perfctr_nmi(int cpu, unsigned int msr)
-{
- unsigned int counter;
- if (cpu < 0)
- cpu = smp_processor_id();
-
- counter = nmi_perfctr_msr_to_bit(msr);
- BUG_ON(counter > NMI_MAX_COUNTER_BITS);
-
- clear_bit(counter, &per_cpu(perfctr_nmi_owner, cpu));
-}
-
-int reserve_perfctr_nmi(unsigned int msr)
-{
- int cpu, i;
- for_each_possible_cpu (cpu) {
- if (!__reserve_perfctr_nmi(cpu, msr)) {
- for_each_possible_cpu (i) {
- if (i >= cpu)
- break;
- __release_perfctr_nmi(i, msr);
- }
- return 0;
- }
- }
- return 1;
-}
-
-void release_perfctr_nmi(unsigned int msr)
-{
- int cpu;
- for_each_possible_cpu (cpu)
- __release_perfctr_nmi(cpu, msr);
-}
-
-int __reserve_evntsel_nmi(int cpu, unsigned int msr)
-{
- unsigned int counter;
- if (cpu < 0)
- cpu = smp_processor_id();
-
- counter = nmi_evntsel_msr_to_bit(msr);
- BUG_ON(counter > NMI_MAX_COUNTER_BITS);
-
- if (!test_and_set_bit(counter, &per_cpu(evntsel_nmi_owner, cpu)[0]))
- return 1;
- return 0;
-}
-
-static void __release_evntsel_nmi(int cpu, unsigned int msr)
-{
- unsigned int counter;
- if (cpu < 0)
- cpu = smp_processor_id();
-
- counter = nmi_evntsel_msr_to_bit(msr);
- BUG_ON(counter > NMI_MAX_COUNTER_BITS);
-
- clear_bit(counter, &per_cpu(evntsel_nmi_owner, cpu)[0]);
-}
-
-int reserve_evntsel_nmi(unsigned int msr)
-{
- int cpu, i;
- for_each_possible_cpu (cpu) {
- if (!__reserve_evntsel_nmi(cpu, msr)) {
- for_each_possible_cpu (i) {
- if (i >= cpu)
- break;
- __release_evntsel_nmi(i, msr);
- }
- return 0;
- }
- }
- return 1;
-}
-
-void release_evntsel_nmi(unsigned int msr)
-{
- int cpu;
- for_each_possible_cpu (cpu) {
- __release_evntsel_nmi(cpu, msr);
- }
-}
-
-static __cpuinit inline int nmi_known_cpu(void)
-{
- switch (boot_cpu_data.x86_vendor) {
- case X86_VENDOR_AMD:
- return boot_cpu_data.x86 == 15 || boot_cpu_data.x86 == 16;
- case X86_VENDOR_INTEL:
- if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON))
- return 1;
- else
- return (boot_cpu_data.x86 == 15);
- }
- return 0;
-}
-
/* Run after command line and cpu_init init, but before all other checks */
void nmi_watchdog_default(void)
{
@@ -277,23 +80,6 @@ static __init void nmi_cpu_busy(void *data)
}
#endif
-static unsigned int adjust_for_32bit_ctr(unsigned int hz)
-{
- unsigned int retval = hz;
-
- /*
- * On Intel CPUs with ARCH_PERFMON only 32 bits in the counter
- * are writable, with higher bits sign extending from bit 31.
- * So, we can only program the counter with 31 bit values and
- * 32nd bit should be 1, for 33.. to be 1.
- * Find the appropriate nmi_hz
- */
- if ((((u64)cpu_khz * 1000) / retval) > 0x7fffffffULL) {
- retval = ((u64)cpu_khz * 1000) / 0x7fffffffUL + 1;
- }
- return retval;
-}
-
int __init check_nmi_watchdog (void)
{
int *counts;
@@ -322,14 +108,14 @@ int __init check_nmi_watchdog (void)
mdelay((20*1000)/nmi_hz); // wait 20 ticks
for_each_online_cpu(cpu) {
- if (!per_cpu(nmi_watchdog_ctlblk, cpu).enabled)
+ if (!per_cpu(wd_enabled, cpu))
continue;
if (cpu_pda(cpu)->__nmi_count - counts[cpu] <= 5) {
printk("CPU#%d: NMI appears to be stuck (%d->%d)!\n",
cpu,
counts[cpu],
cpu_pda(cpu)->__nmi_count);
- per_cpu(nmi_watchdog_ctlblk, cpu).enabled = 0;
+ per_cpu(wd_enabled, cpu) = 0;
atomic_dec(&nmi_active);
}
}
@@ -344,13 +130,8 @@ int __init check_nmi_watchdog (void)
/* now that we know it works we can reduce NMI frequency to
something more reasonable; makes a difference in some configs */
- if (nmi_watchdog == NMI_LOCAL_APIC) {
- struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
- nmi_hz = 1;
- if (wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR0)
- nmi_hz = adjust_for_32bit_ctr(nmi_hz);
- }
+ if (nmi_watchdog == NMI_LOCAL_APIC)
+ nmi_hz = lapic_adjust_nmi_hz(1);
kfree(counts);
return 0;
@@ -379,57 +160,6 @@ int __init setup_nmi_watchdog(char *str)
__setup("nmi_watchdog=", setup_nmi_watchdog);
-static void disable_lapic_nmi_watchdog(void)
-{
- BUG_ON(nmi_watchdog != NMI_LOCAL_APIC);
-
- if (atomic_read(&nmi_active) <= 0)
- return;
-
- on_each_cpu(stop_apic_nmi_watchdog, NULL, 0, 1);
-
- BUG_ON(atomic_read(&nmi_active) != 0);
-}
-
-static void enable_lapic_nmi_watchdog(void)
-{
- BUG_ON(nmi_watchdog != NMI_LOCAL_APIC);
-
- /* are we already enabled */
- if (atomic_read(&nmi_active) != 0)
- return;
-
- /* are we lapic aware */
- if (nmi_known_cpu() <= 0)
- return;
-
- on_each_cpu(setup_apic_nmi_watchdog, NULL, 0, 1);
- touch_nmi_watchdog();
-}
-
-void disable_timer_nmi_watchdog(void)
-{
- BUG_ON(nmi_watchdog != NMI_IO_APIC);
-
- if (atomic_read(&nmi_active) <= 0)
- return;
-
- disable_irq(0);
- on_each_cpu(stop_apic_nmi_watchdog, NULL, 0, 1);
-
- BUG_ON(atomic_read(&nmi_active) != 0);
-}
-
-void enable_timer_nmi_watchdog(void)
-{
- BUG_ON(nmi_watchdog != NMI_IO_APIC);
-
- if (atomic_read(&nmi_active) == 0) {
- touch_nmi_watchdog();
- on_each_cpu(setup_apic_nmi_watchdog, NULL, 0, 1);
- enable_irq(0);
- }
-}
static void __acpi_nmi_disable(void *__unused)
{
@@ -515,275 +245,9 @@ late_initcall(init_lapic_nmi_sysfs);
#endif /* CONFIG_PM */
-/*
- * Activate the NMI watchdog via the local APIC.
- * Original code written by Keith Owens.
- */
-
-/* Note that these events don't tick when the CPU idles. This means
- the frequency varies with CPU load. */
-
-#define K7_EVNTSEL_ENABLE (1 << 22)
-#define K7_EVNTSEL_INT (1 << 20)
-#define K7_EVNTSEL_OS (1 << 17)
-#define K7_EVNTSEL_USR (1 << 16)
-#define K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING 0x76
-#define K7_NMI_EVENT K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING
-
-static int setup_k7_watchdog(void)
-{
- unsigned int perfctr_msr, evntsel_msr;
- unsigned int evntsel;
- struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
- perfctr_msr = MSR_K7_PERFCTR0;
- evntsel_msr = MSR_K7_EVNTSEL0;
- if (!__reserve_perfctr_nmi(-1, perfctr_msr))
- goto fail;
-
- if (!__reserve_evntsel_nmi(-1, evntsel_msr))
- goto fail1;
-
- /* Simulator may not support it */
- if (checking_wrmsrl(evntsel_msr, 0UL))
- goto fail2;
- wrmsrl(perfctr_msr, 0UL);
-
- evntsel = K7_EVNTSEL_INT
- | K7_EVNTSEL_OS
- | K7_EVNTSEL_USR
- | K7_NMI_EVENT;
-
- /* setup the timer */
- wrmsr(evntsel_msr, evntsel, 0);
- wrmsrl(perfctr_msr, -((u64)cpu_khz * 1000 / nmi_hz));
- apic_write(APIC_LVTPC, APIC_DM_NMI);
- evntsel |= K7_EVNTSEL_ENABLE;
- wrmsr(evntsel_msr, evntsel, 0);
-
- wd->perfctr_msr = perfctr_msr;
- wd->evntsel_msr = evntsel_msr;
- wd->cccr_msr = 0; //unused
- wd->check_bit = 1ULL<<63;
- return 1;
-fail2:
- __release_evntsel_nmi(-1, evntsel_msr);
-fail1:
- __release_perfctr_nmi(-1, perfctr_msr);
-fail:
- return 0;
-}
-
-static void stop_k7_watchdog(void)
-{
- struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
- wrmsr(wd->evntsel_msr, 0, 0);
-
- __release_evntsel_nmi(-1, wd->evntsel_msr);
- __release_perfctr_nmi(-1, wd->perfctr_msr);
-}
-
-/* Note that these events don't tick when the CPU idles. This means
- the frequency varies with CPU load. */
-
-#define MSR_P4_MISC_ENABLE_PERF_AVAIL (1<<7)
-#define P4_ESCR_EVENT_SELECT(N) ((N)<<25)
-#define P4_ESCR_OS (1<<3)
-#define P4_ESCR_USR (1<<2)
-#define P4_CCCR_OVF_PMI0 (1<<26)
-#define P4_CCCR_OVF_PMI1 (1<<27)
-#define P4_CCCR_THRESHOLD(N) ((N)<<20)
-#define P4_CCCR_COMPLEMENT (1<<19)
-#define P4_CCCR_COMPARE (1<<18)
-#define P4_CCCR_REQUIRED (3<<16)
-#define P4_CCCR_ESCR_SELECT(N) ((N)<<13)
-#define P4_CCCR_ENABLE (1<<12)
-#define P4_CCCR_OVF (1<<31)
-/* Set up IQ_COUNTER0 to behave like a clock, by having IQ_CCCR0 filter
- CRU_ESCR0 (with any non-null event selector) through a complemented
- max threshold. [IA32-Vol3, Section 14.9.9] */
-
-static int setup_p4_watchdog(void)
-{
- unsigned int perfctr_msr, evntsel_msr, cccr_msr;
- unsigned int evntsel, cccr_val;
- unsigned int misc_enable, dummy;
- unsigned int ht_num;
- struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
- rdmsr(MSR_IA32_MISC_ENABLE, misc_enable, dummy);
- if (!(misc_enable & MSR_P4_MISC_ENABLE_PERF_AVAIL))
- return 0;
-
-#ifdef CONFIG_SMP
- /* detect which hyperthread we are on */
- if (smp_num_siblings == 2) {
- unsigned int ebx, apicid;
-
- ebx = cpuid_ebx(1);
- apicid = (ebx >> 24) & 0xff;
- ht_num = apicid & 1;
- } else
-#endif
- ht_num = 0;
-
- /* performance counters are shared resources
- * assign each hyperthread its own set
- * (re-use the ESCR0 register, seems safe
- * and keeps the cccr_val the same)
- */
- if (!ht_num) {
- /* logical cpu 0 */
- perfctr_msr = MSR_P4_IQ_PERFCTR0;
- evntsel_msr = MSR_P4_CRU_ESCR0;
- cccr_msr = MSR_P4_IQ_CCCR0;
- cccr_val = P4_CCCR_OVF_PMI0 | P4_CCCR_ESCR_SELECT(4);
- } else {
- /* logical cpu 1 */
- perfctr_msr = MSR_P4_IQ_PERFCTR1;
- evntsel_msr = MSR_P4_CRU_ESCR0;
- cccr_msr = MSR_P4_IQ_CCCR1;
- cccr_val = P4_CCCR_OVF_PMI1 | P4_CCCR_ESCR_SELECT(4);
- }
-
- if (!__reserve_perfctr_nmi(-1, perfctr_msr))
- goto fail;
-
- if (!__reserve_evntsel_nmi(-1, evntsel_msr))
- goto fail1;
-
- evntsel = P4_ESCR_EVENT_SELECT(0x3F)
- | P4_ESCR_OS
- | P4_ESCR_USR;
-
- cccr_val |= P4_CCCR_THRESHOLD(15)
- | P4_CCCR_COMPLEMENT
- | P4_CCCR_COMPARE
- | P4_CCCR_REQUIRED;
-
- wrmsr(evntsel_msr, evntsel, 0);
- wrmsr(cccr_msr, cccr_val, 0);
- wrmsrl(perfctr_msr, -((u64)cpu_khz * 1000 / nmi_hz));
- apic_write(APIC_LVTPC, APIC_DM_NMI);
- cccr_val |= P4_CCCR_ENABLE;
- wrmsr(cccr_msr, cccr_val, 0);
-
- wd->perfctr_msr = perfctr_msr;
- wd->evntsel_msr = evntsel_msr;
- wd->cccr_msr = cccr_msr;
- wd->check_bit = 1ULL<<39;
- return 1;
-fail1:
- __release_perfctr_nmi(-1, perfctr_msr);
-fail:
- return 0;
-}
-
-static void stop_p4_watchdog(void)
-{
- struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
- wrmsr(wd->cccr_msr, 0, 0);
- wrmsr(wd->evntsel_msr, 0, 0);
-
- __release_evntsel_nmi(-1, wd->evntsel_msr);
- __release_perfctr_nmi(-1, wd->perfctr_msr);
-}
-
-#define ARCH_PERFMON_NMI_EVENT_SEL ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL
-#define ARCH_PERFMON_NMI_EVENT_UMASK ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK
-
-static int setup_intel_arch_watchdog(void)
-{
- unsigned int ebx;
- union cpuid10_eax eax;
- unsigned int unused;
- unsigned int perfctr_msr, evntsel_msr;
- unsigned int evntsel;
- struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
- /*
- * Check whether the Architectural PerfMon supports
- * Unhalted Core Cycles Event or not.
- * NOTE: Corresponding bit = 0 in ebx indicates event present.
- */
- cpuid(10, &(eax.full), &ebx, &unused, &unused);
- if ((eax.split.mask_length < (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX+1)) ||
- (ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT))
- goto fail;
-
- perfctr_msr = MSR_ARCH_PERFMON_PERFCTR0;
- evntsel_msr = MSR_ARCH_PERFMON_EVENTSEL0;
-
- if (!__reserve_perfctr_nmi(-1, perfctr_msr))
- goto fail;
-
- if (!__reserve_evntsel_nmi(-1, evntsel_msr))
- goto fail1;
-
- wrmsrl(perfctr_msr, 0UL);
-
- evntsel = ARCH_PERFMON_EVENTSEL_INT
- | ARCH_PERFMON_EVENTSEL_OS
- | ARCH_PERFMON_EVENTSEL_USR
- | ARCH_PERFMON_NMI_EVENT_SEL
- | ARCH_PERFMON_NMI_EVENT_UMASK;
-
- /* setup the timer */
- wrmsr(evntsel_msr, evntsel, 0);
-
- nmi_hz = adjust_for_32bit_ctr(nmi_hz);
- wrmsr(perfctr_msr, (u32)(-((u64)cpu_khz * 1000 / nmi_hz)), 0);
-
- apic_write(APIC_LVTPC, APIC_DM_NMI);
- evntsel |= ARCH_PERFMON_EVENTSEL0_ENABLE;
- wrmsr(evntsel_msr, evntsel, 0);
-
- wd->perfctr_msr = perfctr_msr;
- wd->evntsel_msr = evntsel_msr;
- wd->cccr_msr = 0; //unused
- wd->check_bit = 1ULL << (eax.split.bit_width - 1);
- return 1;
-fail1:
- __release_perfctr_nmi(-1, perfctr_msr);
-fail:
- return 0;
-}
-
-static void stop_intel_arch_watchdog(void)
-{
- unsigned int ebx;
- union cpuid10_eax eax;
- unsigned int unused;
- struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
- /*
- * Check whether the Architectural PerfMon supports
- * Unhalted Core Cycles Event or not.
- * NOTE: Corresponding bit = 0 in ebx indicates event present.
- */
- cpuid(10, &(eax.full), &ebx, &unused, &unused);
- if ((eax.split.mask_length < (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX+1)) ||
- (ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT))
- return;
-
- wrmsr(wd->evntsel_msr, 0, 0);
-
- __release_evntsel_nmi(-1, wd->evntsel_msr);
- __release_perfctr_nmi(-1, wd->perfctr_msr);
-}
-
void setup_apic_nmi_watchdog(void *unused)
{
- struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
- /* only support LOCAL and IO APICs for now */
- if ((nmi_watchdog != NMI_LOCAL_APIC) &&
- (nmi_watchdog != NMI_IO_APIC))
- return;
-
- if (wd->enabled == 1)
+ if (__get_cpu_var(wd_enabled) == 1)
return;
/* cheap hack to support suspend/resume */
@@ -791,62 +255,31 @@ void setup_apic_nmi_watchdog(void *unused)
if ((smp_processor_id() != 0) && (atomic_read(&nmi_active) <= 0))
return;
- if (nmi_watchdog == NMI_LOCAL_APIC) {
- switch (boot_cpu_data.x86_vendor) {
- case X86_VENDOR_AMD:
- if (strstr(boot_cpu_data.x86_model_id, "Screwdriver"))
- return;
- if (!setup_k7_watchdog())
- return;
- break;
- case X86_VENDOR_INTEL:
- if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
- if (!setup_intel_arch_watchdog())
- return;
- break;
- }
- if (!setup_p4_watchdog())
- return;
- break;
- default:
+ switch (nmi_watchdog) {
+ case NMI_LOCAL_APIC:
+ __get_cpu_var(wd_enabled) = 1;
+ if (lapic_watchdog_init(nmi_hz) < 0) {
+ __get_cpu_var(wd_enabled) = 0;
return;
}
+ /* FALL THROUGH */
+ case NMI_IO_APIC:
+ __get_cpu_var(wd_enabled) = 1;
+ atomic_inc(&nmi_active);
}
- wd->enabled = 1;
- atomic_inc(&nmi_active);
}
void stop_apic_nmi_watchdog(void *unused)
{
- struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
/* only support LOCAL and IO APICs for now */
if ((nmi_watchdog != NMI_LOCAL_APIC) &&
(nmi_watchdog != NMI_IO_APIC))
return;
-
- if (wd->enabled == 0)
+ if (__get_cpu_var(wd_enabled) == 0)
return;
-
- if (nmi_watchdog == NMI_LOCAL_APIC) {
- switch (boot_cpu_data.x86_vendor) {
- case X86_VENDOR_AMD:
- if (strstr(boot_cpu_data.x86_model_id, "Screwdriver"))
- return;
- stop_k7_watchdog();
- break;
- case X86_VENDOR_INTEL:
- if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
- stop_intel_arch_watchdog();
- break;
- }
- stop_p4_watchdog();
- break;
- default:
- return;
- }
- }
- wd->enabled = 0;
+ if (nmi_watchdog == NMI_LOCAL_APIC)
+ lapic_watchdog_stop();
+ __get_cpu_var(wd_enabled) = 0;
atomic_dec(&nmi_active);
}
@@ -885,9 +318,7 @@ int __kprobes nmi_watchdog_tick(struct pt_regs * regs, unsigned reason)
int sum;
int touched = 0;
int cpu = smp_processor_id();
- struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
- u64 dummy;
- int rc=0;
+ int rc = 0;
/* check for other users first */
if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT)
@@ -934,55 +365,20 @@ int __kprobes nmi_watchdog_tick(struct pt_regs * regs, unsigned reason)
}
/* see if the nmi watchdog went off */
- if (wd->enabled) {
- if (nmi_watchdog == NMI_LOCAL_APIC) {
- rdmsrl(wd->perfctr_msr, dummy);
- if (dummy & wd->check_bit){
- /* this wasn't a watchdog timer interrupt */
- goto done;
- }
-
- /* only Intel uses the cccr msr */
- if (wd->cccr_msr != 0) {
- /*
- * P4 quirks:
- * - An overflown perfctr will assert its interrupt
- * until the OVF flag in its CCCR is cleared.
- * - LVTPC is masked on interrupt and must be
- * unmasked by the LVTPC handler.
- */
- rdmsrl(wd->cccr_msr, dummy);
- dummy &= ~P4_CCCR_OVF;
- wrmsrl(wd->cccr_msr, dummy);
- apic_write(APIC_LVTPC, APIC_DM_NMI);
- /* start the cycle over again */
- wrmsrl(wd->perfctr_msr,
- -((u64)cpu_khz * 1000 / nmi_hz));
- } else if (wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR0) {
- /*
- * ArchPerfom/Core Duo needs to re-unmask
- * the apic vector
- */
- apic_write(APIC_LVTPC, APIC_DM_NMI);
- /* ARCH_PERFMON has 32 bit counter writes */
- wrmsr(wd->perfctr_msr,
- (u32)(-((u64)cpu_khz * 1000 / nmi_hz)), 0);
- } else {
- /* start the cycle over again */
- wrmsrl(wd->perfctr_msr,
- -((u64)cpu_khz * 1000 / nmi_hz));
- }
- rc = 1;
- } else if (nmi_watchdog == NMI_IO_APIC) {
- /* don't know how to accurately check for this.
- * just assume it was a watchdog timer interrupt
- * This matches the old behaviour.
- */
- rc = 1;
- } else
- printk(KERN_WARNING "Unknown enabled NMI hardware?!\n");
+ if (!__get_cpu_var(wd_enabled))
+ return rc;
+ switch (nmi_watchdog) {
+ case NMI_LOCAL_APIC:
+ rc |= lapic_wd_event(nmi_hz);
+ break;
+ case NMI_IO_APIC:
+ /* don't know how to accurately check for this.
+ * just assume it was a watchdog timer interrupt
+ * This matches the old behaviour.
+ */
+ rc = 1;
+ break;
}
-done:
return rc;
}
@@ -1067,12 +463,4 @@ void __trigger_all_cpu_backtrace(void)
EXPORT_SYMBOL(nmi_active);
EXPORT_SYMBOL(nmi_watchdog);
-EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi);
-EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi_bit);
-EXPORT_SYMBOL(reserve_perfctr_nmi);
-EXPORT_SYMBOL(release_perfctr_nmi);
-EXPORT_SYMBOL(reserve_evntsel_nmi);
-EXPORT_SYMBOL(release_evntsel_nmi);
-EXPORT_SYMBOL(disable_timer_nmi_watchdog);
-EXPORT_SYMBOL(enable_timer_nmi_watchdog);
EXPORT_SYMBOL(touch_nmi_watchdog);
diff --git a/arch/x86_64/kernel/pci-calgary.c b/arch/x86_64/kernel/pci-calgary.c
index 04480c3b68f..5bd20b542c1 100644
--- a/arch/x86_64/kernel/pci-calgary.c
+++ b/arch/x86_64/kernel/pci-calgary.c
@@ -507,7 +507,7 @@ error:
return ret;
}
-static struct dma_mapping_ops calgary_dma_ops = {
+static const struct dma_mapping_ops calgary_dma_ops = {
.alloc_coherent = calgary_alloc_coherent,
.map_single = calgary_map_single,
.unmap_single = calgary_unmap_single,
diff --git a/arch/x86_64/kernel/pci-gart.c b/arch/x86_64/kernel/pci-gart.c
index 0bae862e9a5..0a762e10f2b 100644
--- a/arch/x86_64/kernel/pci-gart.c
+++ b/arch/x86_64/kernel/pci-gart.c
@@ -556,7 +556,7 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
extern int agp_amd64_init(void);
-static struct dma_mapping_ops gart_dma_ops = {
+static const struct dma_mapping_ops gart_dma_ops = {
.mapping_error = NULL,
.map_single = gart_map_single,
.map_simple = gart_map_simple,
diff --git a/arch/x86_64/kernel/pci-nommu.c b/arch/x86_64/kernel/pci-nommu.c
index df09ab05a1b..6dade0c867c 100644
--- a/arch/x86_64/kernel/pci-nommu.c
+++ b/arch/x86_64/kernel/pci-nommu.c
@@ -79,7 +79,7 @@ void nommu_unmap_sg(struct device *dev, struct scatterlist *sg,
{
}
-struct dma_mapping_ops nommu_dma_ops = {
+const struct dma_mapping_ops nommu_dma_ops = {
.map_single = nommu_map_single,
.unmap_single = nommu_unmap_single,
.map_sg = nommu_map_sg,
diff --git a/arch/x86_64/kernel/pci-swiotlb.c b/arch/x86_64/kernel/pci-swiotlb.c
index eb18be5a656..4b4569abc60 100644
--- a/arch/x86_64/kernel/pci-swiotlb.c
+++ b/arch/x86_64/kernel/pci-swiotlb.c
@@ -12,7 +12,7 @@
int swiotlb __read_mostly;
EXPORT_SYMBOL(swiotlb);
-struct dma_mapping_ops swiotlb_dma_ops = {
+const struct dma_mapping_ops swiotlb_dma_ops = {
.mapping_error = swiotlb_dma_mapping_error,
.alloc_coherent = swiotlb_alloc_coherent,
.free_coherent = swiotlb_free_coherent,
diff --git a/arch/x86_64/kernel/process.c b/arch/x86_64/kernel/process.c
index d8d5ccc245c..4f21765078b 100644
--- a/arch/x86_64/kernel/process.c
+++ b/arch/x86_64/kernel/process.c
@@ -288,16 +288,18 @@ void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
static int __init idle_setup (char *str)
{
- if (!strncmp(str, "poll", 4)) {
+ if (!strcmp(str, "poll")) {
printk("using polling idle threads.\n");
pm_idle = poll_idle;
- }
+ } else if (!strcmp(str, "mwait"))
+ force_mwait = 1;
+ else
+ return -1;
boot_option_idle_override = 1;
- return 1;
+ return 0;
}
-
-__setup("idle=", idle_setup);
+early_param("idle", idle_setup);
/* Prints also some state that isn't saved in the pt_regs */
void __show_regs(struct pt_regs * regs)
diff --git a/arch/x86_64/kernel/setup.c b/arch/x86_64/kernel/setup.c
index 3d98b696881..db30b5bcef6 100644
--- a/arch/x86_64/kernel/setup.c
+++ b/arch/x86_64/kernel/setup.c
@@ -79,6 +79,8 @@ int bootloader_type;
unsigned long saved_video_mode;
+int force_mwait __cpuinitdata;
+
/*
* Early DMI memory
*/
@@ -205,10 +207,10 @@ static void discover_ebda(void)
* there is a real-mode segmented pointer pointing to the
* 4K EBDA area at 0x40E
*/
- ebda_addr = *(unsigned short *)EBDA_ADDR_POINTER;
+ ebda_addr = *(unsigned short *)__va(EBDA_ADDR_POINTER);
ebda_addr <<= 4;
- ebda_size = *(unsigned short *)(unsigned long)ebda_addr;
+ ebda_size = *(unsigned short *)__va(ebda_addr);
/* Round EBDA up to pages */
if (ebda_size == 0)
@@ -243,11 +245,12 @@ void __init setup_arch(char **cmdline_p)
init_mm.end_code = (unsigned long) &_etext;
init_mm.end_data = (unsigned long) &_edata;
init_mm.brk = (unsigned long) &_end;
+ init_mm.pgd = __va(__pa_symbol(&init_level4_pgt));
- code_resource.start = virt_to_phys(&_text);
- code_resource.end = virt_to_phys(&_etext)-1;
- data_resource.start = virt_to_phys(&_etext);
- data_resource.end = virt_to_phys(&_edata)-1;
+ code_resource.start = __pa_symbol(&_text);
+ code_resource.end = __pa_symbol(&_etext)-1;
+ data_resource.start = __pa_symbol(&_etext);
+ data_resource.end = __pa_symbol(&_edata)-1;
early_identify_cpu(&boot_cpu_data);
@@ -274,8 +277,6 @@ void __init setup_arch(char **cmdline_p)
dmi_scan_machine();
- zap_low_mappings(0);
-
#ifdef CONFIG_ACPI
/*
* Initialize the ACPI boot-time table parser (gets the RSDP and SDT).
@@ -329,15 +330,8 @@ void __init setup_arch(char **cmdline_p)
#endif
#ifdef CONFIG_SMP
- /*
- * But first pinch a few for the stack/trampoline stuff
- * FIXME: Don't need the extra page at 4K, but need to fix
- * trampoline before removing it. (see the GDT stuff)
- */
- reserve_bootmem_generic(PAGE_SIZE, PAGE_SIZE);
-
/* Reserve SMP trampoline */
- reserve_bootmem_generic(SMP_TRAMPOLINE_BASE, PAGE_SIZE);
+ reserve_bootmem_generic(SMP_TRAMPOLINE_BASE, 2*PAGE_SIZE);
#endif
#ifdef CONFIG_ACPI_SLEEP
@@ -612,6 +606,10 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
/* RDTSC can be speculated around */
clear_bit(X86_FEATURE_SYNC_RDTSC, &c->x86_capability);
+
+ /* Family 10 doesn't support C states in MWAIT so don't use it */
+ if (c->x86 == 0x10 && !force_mwait)
+ clear_bit(X86_FEATURE_MWAIT, &c->x86_capability);
}
static void __cpuinit detect_ht(struct cpuinfo_x86 *c)
@@ -987,9 +985,8 @@ static int show_cpuinfo(struct seq_file *m, void *v)
"stc",
"100mhzsteps",
"hwpstate",
- NULL, /* tsc invariant mapped to constant_tsc */
- NULL,
- /* nothing */ /* constant_tsc - moved to flags */
+ "", /* tsc invariant mapped to constant_tsc */
+ /* nothing */
};
diff --git a/arch/x86_64/kernel/setup64.c b/arch/x86_64/kernel/setup64.c
index 6a70b55f719..64379a80d76 100644
--- a/arch/x86_64/kernel/setup64.c
+++ b/arch/x86_64/kernel/setup64.c
@@ -103,9 +103,9 @@ void __init setup_per_cpu_areas(void)
if (!NODE_DATA(cpu_to_node(i))) {
printk("cpu with no node %d, num_online_nodes %d\n",
i, num_online_nodes());
- ptr = alloc_bootmem(size);
+ ptr = alloc_bootmem_pages(size);
} else {
- ptr = alloc_bootmem_node(NODE_DATA(cpu_to_node(i)), size);
+ ptr = alloc_bootmem_pages_node(NODE_DATA(cpu_to_node(i)), size);
}
if (!ptr)
panic("Cannot allocate cpu data for CPU %d\n", i);
@@ -201,7 +201,6 @@ void __cpuinit cpu_init (void)
/* CPU 0 is initialised in head64.c */
if (cpu != 0) {
pda_init(cpu);
- zap_low_mappings(cpu);
} else
estacks = boot_exception_stacks;
diff --git a/arch/x86_64/kernel/signal.c b/arch/x86_64/kernel/signal.c
index 49ec324cd14..c819625f331 100644
--- a/arch/x86_64/kernel/signal.c
+++ b/arch/x86_64/kernel/signal.c
@@ -141,7 +141,7 @@ asmlinkage long sys_rt_sigreturn(struct pt_regs *regs)
goto badframe;
#ifdef DEBUG_SIG
- printk("%d sigreturn rip:%lx rsp:%lx frame:%p rax:%lx\n",current->pid,regs.rip,regs.rsp,frame,eax);
+ printk("%d sigreturn rip:%lx rsp:%lx frame:%p rax:%lx\n",current->pid,regs->rip,regs->rsp,frame,eax);
#endif
if (do_sigaltstack(&frame->uc.uc_stack, NULL, regs->rsp) == -EFAULT)
@@ -301,7 +301,7 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
if (test_thread_flag(TIF_SINGLESTEP))
ptrace_notify(SIGTRAP);
#ifdef DEBUG_SIG
- printk("SIG deliver (%s:%d): sp=%p pc=%p ra=%p\n",
+ printk("SIG deliver (%s:%d): sp=%p pc=%lx ra=%p\n",
current->comm, current->pid, frame, regs->rip, frame->pretcode);
#endif
@@ -463,7 +463,7 @@ void
do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
{
#ifdef DEBUG_SIG
- printk("do_notify_resume flags:%x rip:%lx rsp:%lx caller:%lx pending:%lx\n",
+ printk("do_notify_resume flags:%x rip:%lx rsp:%lx caller:%p pending:%x\n",
thread_info_flags, regs->rip, regs->rsp, __builtin_return_address(0),signal_pending(current));
#endif
diff --git a/arch/x86_64/kernel/smp.c b/arch/x86_64/kernel/smp.c
index af1ec4d23cf..22abae4e9f3 100644
--- a/arch/x86_64/kernel/smp.c
+++ b/arch/x86_64/kernel/smp.c
@@ -76,7 +76,7 @@ static inline void leave_mm(int cpu)
if (read_pda(mmu_state) == TLBSTATE_OK)
BUG();
cpu_clear(cpu, read_pda(active_mm)->cpu_vm_mask);
- load_cr3(swapper_pg_dir);
+ load_cr3(init_mm.pgd);
}
/*
@@ -452,42 +452,34 @@ int smp_call_function (void (*func) (void *info), void *info, int nonatomic,
}
EXPORT_SYMBOL(smp_call_function);
-void smp_stop_cpu(void)
+static void stop_this_cpu(void *dummy)
{
- unsigned long flags;
+ local_irq_disable();
/*
* Remove this CPU:
*/
cpu_clear(smp_processor_id(), cpu_online_map);
- local_irq_save(flags);
disable_local_APIC();
- local_irq_restore(flags);
-}
-
-static void smp_really_stop_cpu(void *dummy)
-{
- smp_stop_cpu();
for (;;)
halt();
}
void smp_send_stop(void)
{
- int nolock = 0;
+ int nolock;
+ unsigned long flags;
+
if (reboot_force)
return;
+
/* Don't deadlock on the call lock in panic */
- if (!spin_trylock(&call_lock)) {
- /* ignore locking because we have panicked anyways */
- nolock = 1;
- }
- __smp_call_function(smp_really_stop_cpu, NULL, 0, 0);
+ nolock = !spin_trylock(&call_lock);
+ local_irq_save(flags);
+ __smp_call_function(stop_this_cpu, NULL, 0, 0);
if (!nolock)
spin_unlock(&call_lock);
-
- local_irq_disable();
disable_local_APIC();
- local_irq_enable();
+ local_irq_restore(flags);
}
/*
diff --git a/arch/x86_64/kernel/smpboot.c b/arch/x86_64/kernel/smpboot.c
index cd4643a3702..4d9dacfae57 100644
--- a/arch/x86_64/kernel/smpboot.c
+++ b/arch/x86_64/kernel/smpboot.c
@@ -60,7 +60,6 @@
#include <asm/irq.h>
#include <asm/hw_irq.h>
#include <asm/numa.h>
-#include <asm/genapic.h>
/* Number of siblings per CPU package */
int smp_num_siblings = 1;
@@ -68,7 +67,6 @@ EXPORT_SYMBOL(smp_num_siblings);
/* Last level cache ID of each logical CPU */
u8 cpu_llc_id[NR_CPUS] __cpuinitdata = {[0 ... NR_CPUS-1] = BAD_APICID};
-EXPORT_SYMBOL(cpu_llc_id);
/* Bitmask of currently online CPUs */
cpumask_t cpu_online_map __read_mostly;
@@ -392,7 +390,8 @@ static void inquire_remote_apic(int apicid)
{
unsigned i, regs[] = { APIC_ID >> 4, APIC_LVR >> 4, APIC_SPIV >> 4 };
char *names[] = { "ID", "VERSION", "SPIV" };
- int timeout, status;
+ int timeout;
+ unsigned int status;
printk(KERN_INFO "Inquiring remote APIC #%d...\n", apicid);
@@ -402,7 +401,9 @@ static void inquire_remote_apic(int apicid)
/*
* Wait for idle.
*/
- apic_wait_icr_idle();
+ status = safe_apic_wait_icr_idle();
+ if (status)
+ printk("a previous APIC delivery may have failed\n");
apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(apicid));
apic_write(APIC_ICR, APIC_DM_REMRD | regs[i]);
@@ -430,8 +431,8 @@ static void inquire_remote_apic(int apicid)
*/
static int __cpuinit wakeup_secondary_via_INIT(int phys_apicid, unsigned int start_rip)
{
- unsigned long send_status = 0, accept_status = 0;
- int maxlvt, timeout, num_starts, j;
+ unsigned long send_status, accept_status = 0;
+ int maxlvt, num_starts, j;
Dprintk("Asserting INIT.\n");
@@ -447,12 +448,7 @@ static int __cpuinit wakeup_secondary_via_INIT(int phys_apicid, unsigned int sta
| APIC_DM_INIT);
Dprintk("Waiting for send to finish...\n");
- timeout = 0;
- do {
- Dprintk("+");
- udelay(100);
- send_status = apic_read(APIC_ICR) & APIC_ICR_BUSY;
- } while (send_status && (timeout++ < 1000));
+ send_status = safe_apic_wait_icr_idle();
mdelay(10);
@@ -465,12 +461,7 @@ static int __cpuinit wakeup_secondary_via_INIT(int phys_apicid, unsigned int sta
apic_write(APIC_ICR, APIC_INT_LEVELTRIG | APIC_DM_INIT);
Dprintk("Waiting for send to finish...\n");
- timeout = 0;
- do {
- Dprintk("+");
- udelay(100);
- send_status = apic_read(APIC_ICR) & APIC_ICR_BUSY;
- } while (send_status && (timeout++ < 1000));
+ send_status = safe_apic_wait_icr_idle();
mb();
atomic_set(&init_deasserted, 1);
@@ -509,12 +500,7 @@ static int __cpuinit wakeup_secondary_via_INIT(int phys_apicid, unsigned int sta
Dprintk("Startup point 1.\n");
Dprintk("Waiting for send to finish...\n");
- timeout = 0;
- do {
- Dprintk("+");
- udelay(100);
- send_status = apic_read(APIC_ICR) & APIC_ICR_BUSY;
- } while (send_status && (timeout++ < 1000));
+ send_status = safe_apic_wait_icr_idle();
/*
* Give the other CPU some time to accept the IPI.
@@ -945,6 +931,12 @@ int __cpuinit __cpu_up(unsigned int cpu)
return -ENOSYS;
}
+ /*
+ * Save current MTRR state in case it was changed since early boot
+ * (e.g. by the ACPI SMI) to initialize new CPUs with MTRRs in sync:
+ */
+ mtrr_save_state();
+
per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
/* Boot it! */
err = do_boot_cpu(cpu, apicid);
@@ -965,13 +957,6 @@ int __cpuinit __cpu_up(unsigned int cpu)
while (!cpu_isset(cpu, cpu_online_map))
cpu_relax();
-
- if (num_online_cpus() > 8 && genapic == &apic_flat) {
- printk(KERN_WARNING
- "flat APIC routing can't be used with > 8 cpus\n");
- BUG();
- }
-
err = 0;
return err;
diff --git a/arch/x86_64/kernel/suspend.c b/arch/x86_64/kernel/suspend.c
index 91f7e678bae..6a5a98f2a75 100644
--- a/arch/x86_64/kernel/suspend.c
+++ b/arch/x86_64/kernel/suspend.c
@@ -12,6 +12,10 @@
#include <asm/proto.h>
#include <asm/page.h>
#include <asm/pgtable.h>
+#include <asm/mtrr.h>
+
+/* References to section boundaries */
+extern const void __nosave_begin, __nosave_end;
struct saved_context saved_context;
@@ -33,7 +37,6 @@ void __save_processor_state(struct saved_context *ctxt)
asm volatile ("str %0" : "=m" (ctxt->tr));
/* XMM0..XMM15 should be handled by kernel_fpu_begin(). */
- /* EFER should be constant for kernel version, no need to handle it. */
/*
* segment registers
*/
@@ -46,10 +49,12 @@ void __save_processor_state(struct saved_context *ctxt)
rdmsrl(MSR_FS_BASE, ctxt->fs_base);
rdmsrl(MSR_GS_BASE, ctxt->gs_base);
rdmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base);
+ mtrr_save_fixed_ranges(NULL);
/*
* control registers
*/
+ rdmsrl(MSR_EFER, ctxt->efer);
asm volatile ("movq %%cr0, %0" : "=r" (ctxt->cr0));
asm volatile ("movq %%cr2, %0" : "=r" (ctxt->cr2));
asm volatile ("movq %%cr3, %0" : "=r" (ctxt->cr3));
@@ -75,6 +80,7 @@ void __restore_processor_state(struct saved_context *ctxt)
/*
* control registers
*/
+ wrmsrl(MSR_EFER, ctxt->efer);
asm volatile ("movq %0, %%cr8" :: "r" (ctxt->cr8));
asm volatile ("movq %0, %%cr4" :: "r" (ctxt->cr4));
asm volatile ("movq %0, %%cr3" :: "r" (ctxt->cr3));
@@ -219,4 +225,15 @@ int swsusp_arch_resume(void)
restore_image();
return 0;
}
+
+/*
+ * pfn_is_nosave - check if given pfn is in the 'nosave' section
+ */
+
+int pfn_is_nosave(unsigned long pfn)
+{
+ unsigned long nosave_begin_pfn = __pa_symbol(&__nosave_begin) >> PAGE_SHIFT;
+ unsigned long nosave_end_pfn = PAGE_ALIGN(__pa_symbol(&__nosave_end)) >> PAGE_SHIFT;
+ return (pfn >= nosave_begin_pfn) && (pfn < nosave_end_pfn);
+}
#endif /* CONFIG_SOFTWARE_SUSPEND */
diff --git a/arch/x86_64/kernel/suspend_asm.S b/arch/x86_64/kernel/suspend_asm.S
index bfbe00763c6..16d183f67bc 100644
--- a/arch/x86_64/kernel/suspend_asm.S
+++ b/arch/x86_64/kernel/suspend_asm.S
@@ -71,9 +71,10 @@ loop:
jmp loop
done:
/* go back to the original page tables */
- leaq init_level4_pgt(%rip), %rax
- subq $__START_KERNEL_map, %rax
- movq %rax, %cr3
+ movq $(init_level4_pgt - __START_KERNEL_map), %rax
+ addq phys_base(%rip), %rax
+ movq %rax, %cr3
+
/* Flush TLB, including "global" things (vmalloc) */
movq mmu_cr4_features(%rip), %rax
movq %rax, %rdx
diff --git a/arch/x86_64/kernel/syscall.c b/arch/x86_64/kernel/syscall.c
index 213fd6ab789..63d592c276c 100644
--- a/arch/x86_64/kernel/syscall.c
+++ b/arch/x86_64/kernel/syscall.c
@@ -3,6 +3,7 @@
#include <linux/linkage.h>
#include <linux/sys.h>
#include <linux/cache.h>
+#include <asm/asm-offsets.h>
#define __NO_STUBS
diff --git a/arch/x86_64/kernel/time.c b/arch/x86_64/kernel/time.c
index 75d73a9aa9f..0652e173813 100644
--- a/arch/x86_64/kernel/time.c
+++ b/arch/x86_64/kernel/time.c
@@ -39,13 +39,11 @@
#include <asm/proto.h>
#include <asm/hpet.h>
#include <asm/sections.h>
-#include <linux/cpufreq.h>
#include <linux/hpet.h>
#include <asm/apic.h>
#include <asm/hpet.h>
-
-extern void i8254_timer_resume(void);
-extern int using_apic_timer;
+#include <asm/mpspec.h>
+#include <asm/nmi.h>
static char *timename = NULL;
@@ -252,6 +250,51 @@ static unsigned long get_cmos_time(void)
return mktime(year, mon, day, hour, min, sec);
}
+/* calibrate_cpu is used on systems with fixed rate TSCs to determine
+ * processor frequency */
+#define TICK_COUNT 100000000
+static unsigned int __init tsc_calibrate_cpu_khz(void)
+{
+ int tsc_start, tsc_now;
+ int i, no_ctr_free;
+ unsigned long evntsel3 = 0, pmc3 = 0, pmc_now = 0;
+ unsigned long flags;
+
+ for (i = 0; i < 4; i++)
+ if (avail_to_resrv_perfctr_nmi_bit(i))
+ break;
+ no_ctr_free = (i == 4);
+ if (no_ctr_free) {
+ i = 3;
+ rdmsrl(MSR_K7_EVNTSEL3, evntsel3);
+ wrmsrl(MSR_K7_EVNTSEL3, 0);
+ rdmsrl(MSR_K7_PERFCTR3, pmc3);
+ } else {
+ reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i);
+ reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
+ }
+ local_irq_save(flags);
+ /* start meauring cycles, incrementing from 0 */
+ wrmsrl(MSR_K7_PERFCTR0 + i, 0);
+ wrmsrl(MSR_K7_EVNTSEL0 + i, 1 << 22 | 3 << 16 | 0x76);
+ rdtscl(tsc_start);
+ do {
+ rdmsrl(MSR_K7_PERFCTR0 + i, pmc_now);
+ tsc_now = get_cycles_sync();
+ } while ((tsc_now - tsc_start) < TICK_COUNT);
+
+ local_irq_restore(flags);
+ if (no_ctr_free) {
+ wrmsrl(MSR_K7_EVNTSEL3, 0);
+ wrmsrl(MSR_K7_PERFCTR3, pmc3);
+ wrmsrl(MSR_K7_EVNTSEL3, evntsel3);
+ } else {
+ release_perfctr_nmi(MSR_K7_PERFCTR0 + i);
+ release_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
+ }
+
+ return pmc_now * tsc_khz / (tsc_now - tsc_start);
+}
/*
* pit_calibrate_tsc() uses the speaker output (channel 2) of
@@ -285,7 +328,7 @@ static unsigned int __init pit_calibrate_tsc(void)
#define PIT_MODE 0x43
#define PIT_CH0 0x40
-static void __init __pit_init(int val, u8 mode)
+static void __pit_init(int val, u8 mode)
{
unsigned long flags;
@@ -301,12 +344,12 @@ void __init pit_init(void)
__pit_init(LATCH, 0x34); /* binary, mode 2, LSB/MSB, ch 0 */
}
-void __init pit_stop_interrupt(void)
+void pit_stop_interrupt(void)
{
__pit_init(0, 0x30); /* mode 0 */
}
-void __init stop_timer_interrupt(void)
+void stop_timer_interrupt(void)
{
char *name;
if (hpet_address) {
@@ -339,23 +382,29 @@ void __init time_init(void)
if (hpet_use_timer) {
/* set tick_nsec to use the proper rate for HPET */
tick_nsec = TICK_NSEC_HPET;
- cpu_khz = hpet_calibrate_tsc();
+ tsc_khz = hpet_calibrate_tsc();
timename = "HPET";
} else {
pit_init();
- cpu_khz = pit_calibrate_tsc();
+ tsc_khz = pit_calibrate_tsc();
timename = "PIT";
}
+ cpu_khz = tsc_khz;
+ if (cpu_has(&boot_cpu_data, X86_FEATURE_CONSTANT_TSC) &&
+ boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
+ boot_cpu_data.x86 == 16)
+ cpu_khz = tsc_calibrate_cpu_khz();
+
if (unsynchronized_tsc())
- mark_tsc_unstable();
+ mark_tsc_unstable("TSCs unsynchronized");
if (cpu_has(&boot_cpu_data, X86_FEATURE_RDTSCP))
vgetcpu_mode = VGETCPU_RDTSCP;
else
vgetcpu_mode = VGETCPU_LSL;
- set_cyc2ns_scale(cpu_khz);
+ set_cyc2ns_scale(tsc_khz);
printk(KERN_INFO "time.c: Detected %d.%03d MHz processor.\n",
cpu_khz / 1000, cpu_khz % 1000);
init_tsc_clocksource();
diff --git a/arch/x86_64/kernel/trampoline.S b/arch/x86_64/kernel/trampoline.S
index c79b99a9e2f..e7e2764c461 100644
--- a/arch/x86_64/kernel/trampoline.S
+++ b/arch/x86_64/kernel/trampoline.S
@@ -3,6 +3,7 @@
* Trampoline.S Derived from Setup.S by Linus Torvalds
*
* 4 Jan 1997 Michael Chastain: changed to gnu as.
+ * 15 Sept 2005 Eric Biederman: 64bit PIC support
*
* Entry: CS:IP point to the start of our code, we are
* in real mode with no stack, but the rest of the
@@ -17,15 +18,20 @@
* and IP is zero. Thus, data addresses need to be absolute
* (no relocation) and are taken with regard to r_base.
*
+ * With the addition of trampoline_level4_pgt this code can
+ * now enter a 64bit kernel that lives at arbitrary 64bit
+ * physical addresses.
+ *
* If you work on this file, check the object module with objdump
* --full-contents --reloc to make sure there are no relocation
- * entries. For the GDT entry we do hand relocation in smpboot.c
- * because of 64bit linker limitations.
+ * entries.
*/
#include <linux/linkage.h>
-#include <asm/segment.h>
+#include <asm/pgtable.h>
#include <asm/page.h>
+#include <asm/msr.h>
+#include <asm/segment.h>
.data
@@ -33,15 +39,33 @@
ENTRY(trampoline_data)
r_base = .
+ cli # We should be safe anyway
wbinvd
mov %cs, %ax # Code and data in the same place
mov %ax, %ds
+ mov %ax, %es
+ mov %ax, %ss
- cli # We should be safe anyway
movl $0xA5A5A5A5, trampoline_data - r_base
# write marker for master knows we're running
+ # Setup stack
+ movw $(trampoline_stack_end - r_base), %sp
+
+ call verify_cpu # Verify the cpu supports long mode
+ testl %eax, %eax # Check for return code
+ jnz no_longmode
+
+ mov %cs, %ax
+ movzx %ax, %esi # Find the 32bit trampoline location
+ shll $4, %esi
+
+ # Fixup the vectors
+ addl %esi, startup_32_vector - r_base
+ addl %esi, startup_64_vector - r_base
+ addl %esi, tgdt + 2 - r_base # Fixup the gdt pointer
+
/*
* GDT tables in non default location kernel can be beyond 16MB and
* lgdt will not be able to load the address as in real mode default
@@ -49,23 +73,94 @@ r_base = .
* to 32 bit.
*/
- lidtl idt_48 - r_base # load idt with 0, 0
- lgdtl gdt_48 - r_base # load gdt with whatever is appropriate
+ lidtl tidt - r_base # load idt with 0, 0
+ lgdtl tgdt - r_base # load gdt with whatever is appropriate
xor %ax, %ax
inc %ax # protected mode (PE) bit
lmsw %ax # into protected mode
- # flaush prefetch and jump to startup_32 in arch/x86_64/kernel/head.S
- ljmpl $__KERNEL32_CS, $(startup_32-__START_KERNEL_map)
+
+ # flush prefetch and jump to startup_32
+ ljmpl *(startup_32_vector - r_base)
+
+ .code32
+ .balign 4
+startup_32:
+ movl $__KERNEL_DS, %eax # Initialize the %ds segment register
+ movl %eax, %ds
+
+ xorl %eax, %eax
+ btsl $5, %eax # Enable PAE mode
+ movl %eax, %cr4
+
+ # Setup trampoline 4 level pagetables
+ leal (trampoline_level4_pgt - r_base)(%esi), %eax
+ movl %eax, %cr3
+
+ movl $MSR_EFER, %ecx
+ movl $(1 << _EFER_LME), %eax # Enable Long Mode
+ xorl %edx, %edx
+ wrmsr
+
+ xorl %eax, %eax
+ btsl $31, %eax # Enable paging and in turn activate Long Mode
+ btsl $0, %eax # Enable protected mode
+ movl %eax, %cr0
+
+ /*
+ * At this point we're in long mode but in 32bit compatibility mode
+ * with EFER.LME = 1, CS.L = 0, CS.D = 1 (and in turn
+ * EFER.LMA = 1). Now we want to jump in 64bit mode, to do that we use
+ * the new gdt/idt that has __KERNEL_CS with CS.L = 1.
+ */
+ ljmp *(startup_64_vector - r_base)(%esi)
+
+ .code64
+ .balign 4
+startup_64:
+ # Now jump into the kernel using virtual addresses
+ movq $secondary_startup_64, %rax
+ jmp *%rax
+
+ .code16
+no_longmode:
+ hlt
+ jmp no_longmode
+#include "verify_cpu.S"
# Careful these need to be in the same 64K segment as the above;
-idt_48:
+tidt:
.word 0 # idt limit = 0
.word 0, 0 # idt base = 0L
-gdt_48:
- .short GDT_ENTRIES*8 - 1 # gdt limit
- .long cpu_gdt_table-__START_KERNEL_map
+ # Duplicate the global descriptor table
+ # so the kernel can live anywhere
+ .balign 4
+tgdt:
+ .short tgdt_end - tgdt # gdt limit
+ .long tgdt - r_base
+ .short 0
+ .quad 0x00cf9b000000ffff # __KERNEL32_CS
+ .quad 0x00af9b000000ffff # __KERNEL_CS
+ .quad 0x00cf93000000ffff # __KERNEL_DS
+tgdt_end:
+
+ .balign 4
+startup_32_vector:
+ .long startup_32 - r_base
+ .word __KERNEL32_CS, 0
+
+ .balign 4
+startup_64_vector:
+ .long startup_64 - r_base
+ .word __KERNEL_CS, 0
+
+trampoline_stack:
+ .org 0x1000
+trampoline_stack_end:
+ENTRY(trampoline_level4_pgt)
+ .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
+ .fill 510,8,0
+ .quad level3_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE
-.globl trampoline_end
-trampoline_end:
+ENTRY(trampoline_end)
diff --git a/arch/x86_64/kernel/traps.c b/arch/x86_64/kernel/traps.c
index 09d2e8a10a4..d76fc32d459 100644
--- a/arch/x86_64/kernel/traps.c
+++ b/arch/x86_64/kernel/traps.c
@@ -426,8 +426,7 @@ void show_registers(struct pt_regs *regs)
const int cpu = smp_processor_id();
struct task_struct *cur = cpu_pda(cpu)->pcurrent;
- rsp = regs->rsp;
-
+ rsp = regs->rsp;
printk("CPU %d ", cpu);
__show_regs(regs);
printk("Process %s (pid: %d, threadinfo %p, task %p)\n",
@@ -438,7 +437,6 @@ void show_registers(struct pt_regs *regs)
* time of the fault..
*/
if (in_kernel) {
-
printk("Stack: ");
_show_stack(NULL, regs, (unsigned long*)rsp);
@@ -581,10 +579,20 @@ static void __kprobes do_trap(int trapnr, int signr, char *str,
{
struct task_struct *tsk = current;
- tsk->thread.error_code = error_code;
- tsk->thread.trap_no = trapnr;
-
if (user_mode(regs)) {
+ /*
+ * We want error_code and trap_no set for userspace
+ * faults and kernelspace faults which result in
+ * die(), but not kernelspace faults which are fixed
+ * up. die() gives the process no chance to handle
+ * the signal and notice the kernel fault information,
+ * so that won't result in polluting the information
+ * about previously queued, but not yet delivered,
+ * faults. See also do_general_protection below.
+ */
+ tsk->thread.error_code = error_code;
+ tsk->thread.trap_no = trapnr;
+
if (exception_trace && unhandled_signal(tsk, signr))
printk(KERN_INFO
"%s[%d] trap %s rip:%lx rsp:%lx error:%lx\n",
@@ -605,8 +613,11 @@ static void __kprobes do_trap(int trapnr, int signr, char *str,
fixup = search_exception_tables(regs->rip);
if (fixup)
regs->rip = fixup->fixup;
- else
+ else {
+ tsk->thread.error_code = error_code;
+ tsk->thread.trap_no = trapnr;
die(str, regs, error_code);
+ }
return;
}
}
@@ -682,10 +693,10 @@ asmlinkage void __kprobes do_general_protection(struct pt_regs * regs,
conditional_sti(regs);
- tsk->thread.error_code = error_code;
- tsk->thread.trap_no = 13;
-
if (user_mode(regs)) {
+ tsk->thread.error_code = error_code;
+ tsk->thread.trap_no = 13;
+
if (exception_trace && unhandled_signal(tsk, SIGSEGV))
printk(KERN_INFO
"%s[%d] general protection rip:%lx rsp:%lx error:%lx\n",
@@ -704,6 +715,9 @@ asmlinkage void __kprobes do_general_protection(struct pt_regs * regs,
regs->rip = fixup->fixup;
return;
}
+
+ tsk->thread.error_code = error_code;
+ tsk->thread.trap_no = 13;
if (notify_die(DIE_GPF, "general protection fault", regs,
error_code, 13, SIGSEGV) == NOTIFY_STOP)
return;
diff --git a/arch/x86_64/kernel/tsc.c b/arch/x86_64/kernel/tsc.c
index 1a0edbbffaa..48f9a8e6aa9 100644
--- a/arch/x86_64/kernel/tsc.c
+++ b/arch/x86_64/kernel/tsc.c
@@ -13,6 +13,8 @@ static int notsc __initdata = 0;
unsigned int cpu_khz; /* TSC clocks / usec, not used here */
EXPORT_SYMBOL(cpu_khz);
+unsigned int tsc_khz;
+EXPORT_SYMBOL(tsc_khz);
static unsigned int cyc2ns_scale __read_mostly;
@@ -77,7 +79,7 @@ static void handle_cpufreq_delayed_get(struct work_struct *v)
static unsigned int ref_freq = 0;
static unsigned long loops_per_jiffy_ref = 0;
-static unsigned long cpu_khz_ref = 0;
+static unsigned long tsc_khz_ref = 0;
static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
void *data)
@@ -99,7 +101,7 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
if (!ref_freq) {
ref_freq = freq->old;
loops_per_jiffy_ref = *lpj;
- cpu_khz_ref = cpu_khz;
+ tsc_khz_ref = tsc_khz;
}
if ((val == CPUFREQ_PRECHANGE && freq->old < freq->new) ||
(val == CPUFREQ_POSTCHANGE && freq->old > freq->new) ||
@@ -107,12 +109,12 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
*lpj =
cpufreq_scale(loops_per_jiffy_ref, ref_freq, freq->new);
- cpu_khz = cpufreq_scale(cpu_khz_ref, ref_freq, freq->new);
+ tsc_khz = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new);
if (!(freq->flags & CPUFREQ_CONST_LOOPS))
- mark_tsc_unstable();
+ mark_tsc_unstable("cpufreq changes");
}
- set_cyc2ns_scale(cpu_khz_ref);
+ set_cyc2ns_scale(tsc_khz_ref);
return 0;
}
@@ -197,10 +199,11 @@ static struct clocksource clocksource_tsc = {
.vread = vread_tsc,
};
-void mark_tsc_unstable(void)
+void mark_tsc_unstable(char *reason)
{
if (!tsc_unstable) {
tsc_unstable = 1;
+ printk("Marking TSC unstable due to %s\n", reason);
/* Change only the rating, when not registered */
if (clocksource_tsc.mult)
clocksource_change_rating(&clocksource_tsc, 0);
@@ -213,7 +216,7 @@ EXPORT_SYMBOL_GPL(mark_tsc_unstable);
void __init init_tsc_clocksource(void)
{
if (!notsc) {
- clocksource_tsc.mult = clocksource_khz2mult(cpu_khz,
+ clocksource_tsc.mult = clocksource_khz2mult(tsc_khz,
clocksource_tsc.shift);
if (check_tsc_unstable())
clocksource_tsc.rating = 0;
diff --git a/arch/x86_64/kernel/tsc_sync.c b/arch/x86_64/kernel/tsc_sync.c
index 014f0db45df..355f5f506c8 100644
--- a/arch/x86_64/kernel/tsc_sync.c
+++ b/arch/x86_64/kernel/tsc_sync.c
@@ -50,7 +50,7 @@ static __cpuinit void check_tsc_warp(void)
/*
* The measurement runs for 20 msecs:
*/
- end = start + cpu_khz * 20ULL;
+ end = start + tsc_khz * 20ULL;
now = start;
for (i = 0; ; i++) {
@@ -138,7 +138,7 @@ void __cpuinit check_tsc_sync_source(int cpu)
printk("\n");
printk(KERN_WARNING "Measured %Ld cycles TSC warp between CPUs,"
" turning off TSC clock.\n", max_warp);
- mark_tsc_unstable();
+ mark_tsc_unstable("check_tsc_sync_source failed");
nr_warps = 0;
max_warp = 0;
last_tsc = 0;
diff --git a/arch/x86_64/kernel/verify_cpu.S b/arch/x86_64/kernel/verify_cpu.S
new file mode 100644
index 00000000000..e035f594819
--- /dev/null
+++ b/arch/x86_64/kernel/verify_cpu.S
@@ -0,0 +1,119 @@
+/*
+ *
+ * verify_cpu.S - Code for cpu long mode and SSE verification. This
+ * code has been borrowed from boot/setup.S and was introduced by
+ * Andi Kleen.
+ *
+ * Copyright (c) 2007 Andi Kleen (ak@suse.de)
+ * Copyright (c) 2007 Eric Biederman (ebiederm@xmission.com)
+ * Copyright (c) 2007 Vivek Goyal (vgoyal@in.ibm.com)
+ *
+ * This source code is licensed under the GNU General Public License,
+ * Version 2. See the file COPYING for more details.
+ *
+ * This is a common code for verification whether CPU supports
+ * long mode and SSE or not. It is not called directly instead this
+ * file is included at various places and compiled in that context.
+ * Following are the current usage.
+ *
+ * This file is included by both 16bit and 32bit code.
+ *
+ * arch/x86_64/boot/setup.S : Boot cpu verification (16bit)
+ * arch/x86_64/boot/compressed/head.S: Boot cpu verification (32bit)
+ * arch/x86_64/kernel/trampoline.S: secondary processor verfication (16bit)
+ * arch/x86_64/kernel/acpi/wakeup.S:Verfication at resume (16bit)
+ *
+ * verify_cpu, returns the status of cpu check in register %eax.
+ * 0: Success 1: Failure
+ *
+ * The caller needs to check for the error code and take the action
+ * appropriately. Either display a message or halt.
+ */
+
+#include <asm/cpufeature.h>
+
+verify_cpu:
+ pushfl # Save caller passed flags
+ pushl $0 # Kill any dangerous flags
+ popfl
+
+ /* minimum CPUID flags for x86-64 as defined by AMD */
+#define M(x) (1<<(x))
+#define M2(a,b) M(a)|M(b)
+#define M4(a,b,c,d) M(a)|M(b)|M(c)|M(d)
+
+#define SSE_MASK \
+ (M2(X86_FEATURE_XMM,X86_FEATURE_XMM2))
+#define REQUIRED_MASK1 \
+ (M4(X86_FEATURE_FPU,X86_FEATURE_PSE,X86_FEATURE_TSC,X86_FEATURE_MSR)|\
+ M4(X86_FEATURE_PAE,X86_FEATURE_CX8,X86_FEATURE_PGE,X86_FEATURE_CMOV)|\
+ M(X86_FEATURE_FXSR))
+#define REQUIRED_MASK2 \
+ (M(X86_FEATURE_LM - 32))
+
+ pushfl # standard way to check for cpuid
+ popl %eax
+ movl %eax,%ebx
+ xorl $0x200000,%eax
+ pushl %eax
+ popfl
+ pushfl
+ popl %eax
+ cmpl %eax,%ebx
+ jz verify_cpu_no_longmode # cpu has no cpuid
+
+ movl $0x0,%eax # See if cpuid 1 is implemented
+ cpuid
+ cmpl $0x1,%eax
+ jb verify_cpu_no_longmode # no cpuid 1
+
+ xor %di,%di
+ cmpl $0x68747541,%ebx # AuthenticAMD
+ jnz verify_cpu_noamd
+ cmpl $0x69746e65,%edx
+ jnz verify_cpu_noamd
+ cmpl $0x444d4163,%ecx
+ jnz verify_cpu_noamd
+ mov $1,%di # cpu is from AMD
+
+verify_cpu_noamd:
+ movl $0x1,%eax # Does the cpu have what it takes
+ cpuid
+ andl $REQUIRED_MASK1,%edx
+ xorl $REQUIRED_MASK1,%edx
+ jnz verify_cpu_no_longmode
+
+ movl $0x80000000,%eax # See if extended cpuid is implemented
+ cpuid
+ cmpl $0x80000001,%eax
+ jb verify_cpu_no_longmode # no extended cpuid
+
+ movl $0x80000001,%eax # Does the cpu have what it takes
+ cpuid
+ andl $REQUIRED_MASK2,%edx
+ xorl $REQUIRED_MASK2,%edx
+ jnz verify_cpu_no_longmode
+
+verify_cpu_sse_test:
+ movl $1,%eax
+ cpuid
+ andl $SSE_MASK,%edx
+ cmpl $SSE_MASK,%edx
+ je verify_cpu_sse_ok
+ test %di,%di
+ jz verify_cpu_no_longmode # only try to force SSE on AMD
+ movl $0xc0010015,%ecx # HWCR
+ rdmsr
+ btr $15,%eax # enable SSE
+ wrmsr
+ xor %di,%di # don't loop
+ jmp verify_cpu_sse_test # try again
+
+verify_cpu_no_longmode:
+ popfl # Restore caller passed flags
+ movl $1,%eax
+ ret
+verify_cpu_sse_ok:
+ popfl # Restore caller passed flags
+ xorl %eax, %eax
+ ret
diff --git a/arch/x86_64/kernel/vmlinux.lds.S b/arch/x86_64/kernel/vmlinux.lds.S
index 5176ecf006e..88cfa50b424 100644
--- a/arch/x86_64/kernel/vmlinux.lds.S
+++ b/arch/x86_64/kernel/vmlinux.lds.S
@@ -29,9 +29,7 @@ SECTIONS
.text : AT(ADDR(.text) - LOAD_OFFSET) {
/* First the code that has to be first for bootstrapping */
*(.bootstrap.text)
- /* Then all the functions that are "hot" in profiles, to group them
- onto the same hugetlb entry */
- #include "functionlist"
+ _stext = .;
/* Then the rest */
*(.text)
SCHED_TEXT
@@ -50,10 +48,10 @@ SECTIONS
__ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) { *(__ex_table) }
__stop___ex_table = .;
- RODATA
-
BUG_TABLE
+ RODATA
+
. = ALIGN(PAGE_SIZE); /* Align data segment to page size boundary */
/* Data */
.data : AT(ADDR(.data) - LOAD_OFFSET) {
@@ -94,6 +92,12 @@ SECTIONS
{ *(.vsyscall_gtod_data) }
vsyscall_gtod_data = VVIRT(.vsyscall_gtod_data);
+
+ .vsyscall_1 ADDR(.vsyscall_0) + 1024: AT(VLOAD(.vsyscall_1))
+ { *(.vsyscall_1) }
+ .vsyscall_2 ADDR(.vsyscall_0) + 2048: AT(VLOAD(.vsyscall_2))
+ { *(.vsyscall_2) }
+
.vgetcpu_mode : AT(VLOAD(.vgetcpu_mode)) { *(.vgetcpu_mode) }
vgetcpu_mode = VVIRT(.vgetcpu_mode);
@@ -101,10 +105,6 @@ SECTIONS
.jiffies : AT(VLOAD(.jiffies)) { *(.jiffies) }
jiffies = VVIRT(.jiffies);
- .vsyscall_1 ADDR(.vsyscall_0) + 1024: AT(VLOAD(.vsyscall_1))
- { *(.vsyscall_1) }
- .vsyscall_2 ADDR(.vsyscall_0) + 2048: AT(VLOAD(.vsyscall_2))
- { *(.vsyscall_2) }
.vsyscall_3 ADDR(.vsyscall_0) + 3072: AT(VLOAD(.vsyscall_3))
{ *(.vsyscall_3) }
@@ -194,7 +194,7 @@ SECTIONS
__initramfs_end = .;
#endif
- . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+ . = ALIGN(4096);
__per_cpu_start = .;
.data.percpu : AT(ADDR(.data.percpu) - LOAD_OFFSET) { *(.data.percpu) }
__per_cpu_end = .;
diff --git a/arch/x86_64/kernel/vsyscall.c b/arch/x86_64/kernel/vsyscall.c
index b43c698cf7d..dc32cef9619 100644
--- a/arch/x86_64/kernel/vsyscall.c
+++ b/arch/x86_64/kernel/vsyscall.c
@@ -45,14 +45,34 @@
#define __vsyscall(nr) __attribute__ ((unused,__section__(".vsyscall_" #nr)))
#define __syscall_clobber "r11","rcx","memory"
+#define __pa_vsymbol(x) \
+ ({unsigned long v; \
+ extern char __vsyscall_0; \
+ asm("" : "=r" (v) : "0" (x)); \
+ ((v - VSYSCALL_FIRST_PAGE) + __pa_symbol(&__vsyscall_0)); })
+/*
+ * vsyscall_gtod_data contains data that is :
+ * - readonly from vsyscalls
+ * - writen by timer interrupt or systcl (/proc/sys/kernel/vsyscall64)
+ * Try to keep this structure as small as possible to avoid cache line ping pongs
+ */
struct vsyscall_gtod_data_t {
- seqlock_t lock;
- int sysctl_enabled;
- struct timeval wall_time_tv;
+ seqlock_t lock;
+
+ /* open coded 'struct timespec' */
+ time_t wall_time_sec;
+ u32 wall_time_nsec;
+
+ int sysctl_enabled;
struct timezone sys_tz;
- cycle_t offset_base;
- struct clocksource clock;
+ struct { /* extract of a clocksource struct */
+ cycle_t (*vread)(void);
+ cycle_t cycle_last;
+ cycle_t mask;
+ u32 mult;
+ u32 shift;
+ } clock;
};
int __vgetcpu_mode __section_vgetcpu_mode;
@@ -68,9 +88,13 @@ void update_vsyscall(struct timespec *wall_time, struct clocksource *clock)
write_seqlock_irqsave(&vsyscall_gtod_data.lock, flags);
/* copy vsyscall data */
- vsyscall_gtod_data.clock = *clock;
- vsyscall_gtod_data.wall_time_tv.tv_sec = wall_time->tv_sec;
- vsyscall_gtod_data.wall_time_tv.tv_usec = wall_time->tv_nsec/1000;
+ vsyscall_gtod_data.clock.vread = clock->vread;
+ vsyscall_gtod_data.clock.cycle_last = clock->cycle_last;
+ vsyscall_gtod_data.clock.mask = clock->mask;
+ vsyscall_gtod_data.clock.mult = clock->mult;
+ vsyscall_gtod_data.clock.shift = clock->shift;
+ vsyscall_gtod_data.wall_time_sec = wall_time->tv_sec;
+ vsyscall_gtod_data.wall_time_nsec = wall_time->tv_nsec;
vsyscall_gtod_data.sys_tz = sys_tz;
write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags);
}
@@ -105,7 +129,8 @@ static __always_inline long time_syscall(long *t)
static __always_inline void do_vgettimeofday(struct timeval * tv)
{
cycle_t now, base, mask, cycle_delta;
- unsigned long seq, mult, shift, nsec_delta;
+ unsigned seq;
+ unsigned long mult, shift, nsec;
cycle_t (*vread)(void);
do {
seq = read_seqbegin(&__vsyscall_gtod_data.lock);
@@ -121,21 +146,20 @@ static __always_inline void do_vgettimeofday(struct timeval * tv)
mult = __vsyscall_gtod_data.clock.mult;
shift = __vsyscall_gtod_data.clock.shift;
- *tv = __vsyscall_gtod_data.wall_time_tv;
-
+ tv->tv_sec = __vsyscall_gtod_data.wall_time_sec;
+ nsec = __vsyscall_gtod_data.wall_time_nsec;
} while (read_seqretry(&__vsyscall_gtod_data.lock, seq));
/* calculate interval: */
cycle_delta = (now - base) & mask;
/* convert to nsecs: */
- nsec_delta = (cycle_delta * mult) >> shift;
+ nsec += (cycle_delta * mult) >> shift;
- /* convert to usecs and add to timespec: */
- tv->tv_usec += nsec_delta / NSEC_PER_USEC;
- while (tv->tv_usec > USEC_PER_SEC) {
+ while (nsec >= NSEC_PER_SEC) {
tv->tv_sec += 1;
- tv->tv_usec -= USEC_PER_SEC;
+ nsec -= NSEC_PER_SEC;
}
+ tv->tv_usec = nsec / NSEC_PER_USEC;
}
int __vsyscall(0) vgettimeofday(struct timeval * tv, struct timezone * tz)
@@ -151,11 +175,13 @@ int __vsyscall(0) vgettimeofday(struct timeval * tv, struct timezone * tz)
* unlikely */
time_t __vsyscall(1) vtime(time_t *t)
{
+ time_t result;
if (unlikely(!__vsyscall_gtod_data.sysctl_enabled))
return time_syscall(t);
- else if (t)
- *t = __vsyscall_gtod_data.wall_time_tv.tv_sec;
- return __vsyscall_gtod_data.wall_time_tv.tv_sec;
+ result = __vsyscall_gtod_data.wall_time_sec;
+ if (t)
+ *t = result;
+ return result;
}
/* Fast way to get current CPU and node.
@@ -224,10 +250,10 @@ static int vsyscall_sysctl_change(ctl_table *ctl, int write, struct file * filp,
return ret;
/* gcc has some trouble with __va(__pa()), so just do it this
way. */
- map1 = ioremap(__pa_symbol(&vsysc1), 2);
+ map1 = ioremap(__pa_vsymbol(&vsysc1), 2);
if (!map1)
return -ENOMEM;
- map2 = ioremap(__pa_symbol(&vsysc2), 2);
+ map2 = ioremap(__pa_vsymbol(&vsysc2), 2);
if (!map2) {
ret = -ENOMEM;
goto out;