summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/Makefile3
-rw-r--r--arch/x86/kernel/acpi/realmode/wakeup.S38
-rw-r--r--arch/x86/kernel/acpi/realmode/wakeup.h5
-rw-r--r--arch/x86/kernel/acpi/sleep.c16
-rw-r--r--arch/x86/kernel/aperture_64.c307
-rw-r--r--arch/x86/kernel/apic_32.c12
-rw-r--r--arch/x86/kernel/apic_64.c36
-rw-r--r--arch/x86/kernel/apm_32.c25
-rw-r--r--arch/x86/kernel/cpu/Makefile4
-rw-r--r--arch/x86/kernel/cpu/addon_cpuid_features.c17
-rw-r--r--arch/x86/kernel/cpu/amd.c42
-rw-r--r--arch/x86/kernel/cpu/amd_64.c211
-rw-r--r--arch/x86/kernel/cpu/bugs.c27
-rw-r--r--arch/x86/kernel/cpu/bugs_64.c (renamed from arch/x86/kernel/bugs_64.c)0
-rw-r--r--arch/x86/kernel/cpu/centaur_64.c43
-rw-r--r--arch/x86/kernel/cpu/cpu.h5
-rw-r--r--arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c44
-rw-r--r--arch/x86/kernel/cpu/intel_64.c103
-rw-r--r--arch/x86/kernel/cpu/intel_cacheinfo.c1
-rw-r--r--arch/x86/kernel/cpu/mcheck/k7.c36
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_64.c24
-rw-r--r--arch/x86/kernel/cpu/mcheck/p4.c90
-rw-r--r--arch/x86/kernel/early-quirks.c13
-rw-r--r--arch/x86/kernel/efi_32.c8
-rw-r--r--arch/x86/kernel/entry_64.S5
-rw-r--r--arch/x86/kernel/head_64.S29
-rw-r--r--arch/x86/kernel/hpet.c43
-rw-r--r--arch/x86/kernel/i387.c4
-rw-r--r--arch/x86/kernel/i8259.c (renamed from arch/x86/kernel/i8259_32.c)132
-rw-r--r--arch/x86/kernel/i8259_64.c512
-rw-r--r--arch/x86/kernel/io_apic_32.c474
-rw-r--r--arch/x86/kernel/io_apic_64.c132
-rw-r--r--arch/x86/kernel/ipi.c1
-rw-r--r--arch/x86/kernel/irq_32.c38
-rw-r--r--arch/x86/kernel/irq_64.c28
-rw-r--r--arch/x86/kernel/irqinit_32.c114
-rw-r--r--arch/x86/kernel/irqinit_64.c203
-rw-r--r--arch/x86/kernel/ldt.c6
-rw-r--r--arch/x86/kernel/machine_kexec_32.c4
-rw-r--r--arch/x86/kernel/microcode.c29
-rw-r--r--arch/x86/kernel/mmconf-fam10h_64.c1
-rw-r--r--arch/x86/kernel/nmi_32.c13
-rw-r--r--arch/x86/kernel/nmi_64.c11
-rw-r--r--arch/x86/kernel/paravirt.c4
-rw-r--r--arch/x86/kernel/pci-dma.c13
-rw-r--r--arch/x86/kernel/pci-gart_64.c83
-rw-r--r--arch/x86/kernel/process.c190
-rw-r--r--arch/x86/kernel/process_32.c61
-rw-r--r--arch/x86/kernel/process_64.c35
-rw-r--r--arch/x86/kernel/quirks.c58
-rw-r--r--arch/x86/kernel/reboot.c18
-rw-r--r--arch/x86/kernel/reboot_fixups_32.c4
-rw-r--r--arch/x86/kernel/setup_64.c452
-rw-r--r--arch/x86/kernel/smpboot.c8
-rw-r--r--arch/x86/kernel/sys_i386_32.c64
-rw-r--r--arch/x86/kernel/time_32.c3
-rw-r--r--arch/x86/kernel/traps_64.c3
-rw-r--r--arch/x86/kernel/tsc_32.c6
-rw-r--r--arch/x86/kernel/tsc_64.c2
-rw-r--r--arch/x86/kernel/vmlinux_32.lds.S7
-rw-r--r--arch/x86/kernel/vmlinux_64.lds.S8
-rw-r--r--arch/x86/kernel/vsmp_64.c3
62 files changed, 2014 insertions, 1897 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 77807d4769c..8a42b797cd6 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -18,14 +18,13 @@ CFLAGS_tsc_64.o := $(nostackp)
obj-y := process_$(BITS).o signal_$(BITS).o entry_$(BITS).o
obj-y += traps_$(BITS).o irq_$(BITS).o
obj-y += time_$(BITS).o ioport.o ldt.o
-obj-y += setup_$(BITS).o i8259_$(BITS).o setup.o
+obj-y += setup_$(BITS).o i8259.o irqinit_$(BITS).o setup.o
obj-$(CONFIG_X86_32) += sys_i386_32.o i386_ksyms_32.o
obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o
obj-$(CONFIG_X86_64) += syscall_64.o vsyscall_64.o setup64.o
obj-y += bootflag.o e820_$(BITS).o
obj-y += pci-dma.o quirks.o i8237.o topology.o kdebugfs.o
obj-y += alternative.o i8253.o pci-nommu.o
-obj-$(CONFIG_X86_64) += bugs_64.o
obj-y += tsc_$(BITS).o io_delay.o rtc.o
obj-$(CONFIG_X86_TRAMPOLINE) += trampoline.o
diff --git a/arch/x86/kernel/acpi/realmode/wakeup.S b/arch/x86/kernel/acpi/realmode/wakeup.S
index f9b77fb37e5..3355973b12a 100644
--- a/arch/x86/kernel/acpi/realmode/wakeup.S
+++ b/arch/x86/kernel/acpi/realmode/wakeup.S
@@ -5,6 +5,7 @@
#include <asm/msr-index.h>
#include <asm/page.h>
#include <asm/pgtable.h>
+#include <asm/processor-flags.h>
.code16
.section ".header", "a"
@@ -24,6 +25,11 @@ pmode_gdt: .quad 0
realmode_flags: .long 0
real_magic: .long 0
trampoline_segment: .word 0
+_pad1: .byte 0
+wakeup_jmp: .byte 0xea /* ljmpw */
+wakeup_jmp_off: .word 3f
+wakeup_jmp_seg: .word 0
+wakeup_gdt: .quad 0, 0, 0
signature: .long 0x51ee1111
.text
@@ -34,11 +40,34 @@ _start:
cli
cld
+ /* Apparently some dimwit BIOS programmers don't know how to
+ program a PM to RM transition, and we might end up here with
+ junk in the data segment descriptor registers. The only way
+ to repair that is to go into PM and fix it ourselves... */
+ movw $16, %cx
+ lgdtl %cs:wakeup_gdt
+ movl %cr0, %eax
+ orb $X86_CR0_PE, %al
+ movl %eax, %cr0
+ jmp 1f
+1: ljmpw $8, $2f
+2:
+ movw %cx, %ds
+ movw %cx, %es
+ movw %cx, %ss
+ movw %cx, %fs
+ movw %cx, %gs
+
+ andb $~X86_CR0_PE, %al
+ movl %eax, %cr0
+ jmp wakeup_jmp
+3:
/* Set up segments */
movw %cs, %ax
movw %ax, %ds
movw %ax, %es
movw %ax, %ss
+ lidtl wakeup_idt
movl $wakeup_stack_end, %esp
@@ -98,7 +127,14 @@ bogus_real_magic:
jmp 1b
.data
- .balign 4
+ .balign 8
+
+ /* This is the standard real-mode IDT */
+wakeup_idt:
+ .word 0xffff /* limit */
+ .long 0 /* address */
+ .word 0
+
.globl HEAP, heap_end
HEAP:
.long wakeup_heap
diff --git a/arch/x86/kernel/acpi/realmode/wakeup.h b/arch/x86/kernel/acpi/realmode/wakeup.h
index ef8166fe802..69d38d0b2b6 100644
--- a/arch/x86/kernel/acpi/realmode/wakeup.h
+++ b/arch/x86/kernel/acpi/realmode/wakeup.h
@@ -24,6 +24,11 @@ struct wakeup_header {
u32 realmode_flags;
u32 real_magic;
u16 trampoline_segment; /* segment with trampoline code, 64-bit only */
+ u8 _pad1;
+ u8 wakeup_jmp;
+ u16 wakeup_jmp_off;
+ u16 wakeup_jmp_seg;
+ u64 wakeup_gdt[3];
u32 signature; /* To check we have correct structure */
} __attribute__((__packed__));
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index afc25ee9964..36af01f029e 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -50,6 +50,20 @@ int acpi_save_state_mem(void)
header->video_mode = saved_video_mode;
+ header->wakeup_jmp_seg = acpi_wakeup_address >> 4;
+ /* GDT[0]: GDT self-pointer */
+ header->wakeup_gdt[0] =
+ (u64)(sizeof(header->wakeup_gdt) - 1) +
+ ((u64)(acpi_wakeup_address +
+ ((char *)&header->wakeup_gdt - (char *)acpi_realmode))
+ << 16);
+ /* GDT[1]: real-mode-like code segment */
+ header->wakeup_gdt[1] = (0x009bULL << 40) +
+ ((u64)acpi_wakeup_address << 16) + 0xffff;
+ /* GDT[2]: real-mode-like data segment */
+ header->wakeup_gdt[2] = (0x0093ULL << 40) +
+ ((u64)acpi_wakeup_address << 16) + 0xffff;
+
#ifndef CONFIG_64BIT
store_gdt((struct desc_ptr *)&header->pmode_gdt);
@@ -111,7 +125,7 @@ void __init acpi_reserve_bootmem(void)
return;
}
- acpi_wakeup_address = acpi_realmode;
+ acpi_wakeup_address = virt_to_phys((void *)acpi_realmode);
}
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 479926d9e00..e819362c706 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -35,6 +35,18 @@ int fallback_aper_force __initdata;
int fix_aperture __initdata = 1;
+struct bus_dev_range {
+ int bus;
+ int dev_base;
+ int dev_limit;
+};
+
+static struct bus_dev_range bus_dev_ranges[] __initdata = {
+ { 0x00, 0x18, 0x20},
+ { 0xff, 0x00, 0x20},
+ { 0xfe, 0x00, 0x20}
+};
+
static struct resource gart_resource = {
.name = "GART",
.flags = IORESOURCE_MEM,
@@ -55,8 +67,9 @@ static u32 __init allocate_aperture(void)
u32 aper_size;
void *p;
- if (fallback_aper_order > 7)
- fallback_aper_order = 7;
+ /* aper_size should <= 1G */
+ if (fallback_aper_order > 5)
+ fallback_aper_order = 5;
aper_size = (32 * 1024 * 1024) << fallback_aper_order;
/*
@@ -65,7 +78,20 @@ static u32 __init allocate_aperture(void)
* memory. Unfortunately we cannot move it up because that would
* make the IOMMU useless.
*/
- p = __alloc_bootmem_nopanic(aper_size, aper_size, 0);
+ /*
+ * using 512M as goal, in case kexec will load kernel_big
+ * that will do the on position decompress, and could overlap with
+ * that positon with gart that is used.
+ * sequende:
+ * kernel_small
+ * ==> kexec (with kdump trigger path or previous doesn't shutdown gart)
+ * ==> kernel_small(gart area become e820_reserved)
+ * ==> kexec (with kdump trigger path or previous doesn't shutdown gart)
+ * ==> kerne_big (uncompressed size will be big than 64M or 128M)
+ * so don't use 512M below as gart iommu, leave the space for kernel
+ * code for safe
+ */
+ p = __alloc_bootmem_nopanic(aper_size, aper_size, 512ULL<<20);
if (!p || __pa(p)+aper_size > 0xffffffff) {
printk(KERN_ERR
"Cannot allocate aperture memory hole (%p,%uK)\n",
@@ -83,69 +109,53 @@ static u32 __init allocate_aperture(void)
return (u32)__pa(p);
}
-static int __init aperture_valid(u64 aper_base, u32 aper_size)
-{
- if (!aper_base)
- return 0;
-
- if (aper_base + aper_size > 0x100000000UL) {
- printk(KERN_ERR "Aperture beyond 4GB. Ignoring.\n");
- return 0;
- }
- if (e820_any_mapped(aper_base, aper_base + aper_size, E820_RAM)) {
- printk(KERN_ERR "Aperture pointing to e820 RAM. Ignoring.\n");
- return 0;
- }
- if (aper_size < 64*1024*1024) {
- printk(KERN_ERR "Aperture too small (%d MB)\n", aper_size>>20);
- return 0;
- }
-
- return 1;
-}
/* Find a PCI capability */
-static __u32 __init find_cap(int num, int slot, int func, int cap)
+static u32 __init find_cap(int bus, int slot, int func, int cap)
{
int bytes;
u8 pos;
- if (!(read_pci_config_16(num, slot, func, PCI_STATUS) &
+ if (!(read_pci_config_16(bus, slot, func, PCI_STATUS) &
PCI_STATUS_CAP_LIST))
return 0;
- pos = read_pci_config_byte(num, slot, func, PCI_CAPABILITY_LIST);
+ pos = read_pci_config_byte(bus, slot, func, PCI_CAPABILITY_LIST);
for (bytes = 0; bytes < 48 && pos >= 0x40; bytes++) {
u8 id;
pos &= ~3;
- id = read_pci_config_byte(num, slot, func, pos+PCI_CAP_LIST_ID);
+ id = read_pci_config_byte(bus, slot, func, pos+PCI_CAP_LIST_ID);
if (id == 0xff)
break;
if (id == cap)
return pos;
- pos = read_pci_config_byte(num, slot, func,
+ pos = read_pci_config_byte(bus, slot, func,
pos+PCI_CAP_LIST_NEXT);
}
return 0;
}
/* Read a standard AGPv3 bridge header */
-static __u32 __init read_agp(int num, int slot, int func, int cap, u32 *order)
+static u32 __init read_agp(int bus, int slot, int func, int cap, u32 *order)
{
u32 apsize;
u32 apsizereg;
int nbits;
u32 aper_low, aper_hi;
u64 aper;
+ u32 old_order;
- printk(KERN_INFO "AGP bridge at %02x:%02x:%02x\n", num, slot, func);
- apsizereg = read_pci_config_16(num, slot, func, cap + 0x14);
+ printk(KERN_INFO "AGP bridge at %02x:%02x:%02x\n", bus, slot, func);
+ apsizereg = read_pci_config_16(bus, slot, func, cap + 0x14);
if (apsizereg == 0xffffffff) {
printk(KERN_ERR "APSIZE in AGP bridge unreadable\n");
return 0;
}
+ /* old_order could be the value from NB gart setting */
+ old_order = *order;
+
apsize = apsizereg & 0xfff;
/* Some BIOS use weird encodings not in the AGPv3 table. */
if (apsize & 0xff)
@@ -155,14 +165,26 @@ static __u32 __init read_agp(int num, int slot, int func, int cap, u32 *order)
if ((int)*order < 0) /* < 32MB */
*order = 0;
- aper_low = read_pci_config(num, slot, func, 0x10);
- aper_hi = read_pci_config(num, slot, func, 0x14);
+ aper_low = read_pci_config(bus, slot, func, 0x10);
+ aper_hi = read_pci_config(bus, slot, func, 0x14);
aper = (aper_low & ~((1<<22)-1)) | ((u64)aper_hi << 32);
+ /*
+ * On some sick chips, APSIZE is 0. It means it wants 4G
+ * so let double check that order, and lets trust AMD NB settings:
+ */
+ printk(KERN_INFO "Aperture from AGP @ %Lx old size %u MB\n",
+ aper, 32 << old_order);
+ if (aper + (32ULL<<(20 + *order)) > 0x100000000ULL) {
+ printk(KERN_INFO "Aperture size %u MB (APSIZE %x) is not right, using settings from NB\n",
+ 32 << *order, apsizereg);
+ *order = old_order;
+ }
+
printk(KERN_INFO "Aperture from AGP @ %Lx size %u MB (APSIZE %x)\n",
aper, 32 << *order, apsizereg);
- if (!aperture_valid(aper, (32*1024*1024) << *order))
+ if (!aperture_valid(aper, (32*1024*1024) << *order, 32<<20))
return 0;
return (u32)aper;
}
@@ -180,17 +202,17 @@ static __u32 __init read_agp(int num, int slot, int func, int cap, u32 *order)
* the AGP bridges should be always an own bus on the HT hierarchy,
* but do it here for future safety.
*/
-static __u32 __init search_agp_bridge(u32 *order, int *valid_agp)
+static u32 __init search_agp_bridge(u32 *order, int *valid_agp)
{
- int num, slot, func;
+ int bus, slot, func;
/* Poor man's PCI discovery */
- for (num = 0; num < 256; num++) {
+ for (bus = 0; bus < 256; bus++) {
for (slot = 0; slot < 32; slot++) {
for (func = 0; func < 8; func++) {
u32 class, cap;
u8 type;
- class = read_pci_config(num, slot, func,
+ class = read_pci_config(bus, slot, func,
PCI_CLASS_REVISION);
if (class == 0xffffffff)
break;
@@ -199,17 +221,17 @@ static __u32 __init search_agp_bridge(u32 *order, int *valid_agp)
case PCI_CLASS_BRIDGE_HOST:
case PCI_CLASS_BRIDGE_OTHER: /* needed? */
/* AGP bridge? */
- cap = find_cap(num, slot, func,
+ cap = find_cap(bus, slot, func,
PCI_CAP_ID_AGP);
if (!cap)
break;
*valid_agp = 1;
- return read_agp(num, slot, func, cap,
+ return read_agp(bus, slot, func, cap,
order);
}
/* No multi-function device? */
- type = read_pci_config_byte(num, slot, func,
+ type = read_pci_config_byte(bus, slot, func,
PCI_HEADER_TYPE);
if (!(type & 0x80))
break;
@@ -249,36 +271,50 @@ void __init early_gart_iommu_check(void)
* or BIOS forget to put that in reserved.
* try to update e820 to make that region as reserved.
*/
- int fix, num;
+ int i, fix, slot;
u32 ctl;
u32 aper_size = 0, aper_order = 0, last_aper_order = 0;
u64 aper_base = 0, last_aper_base = 0;
- int aper_enabled = 0, last_aper_enabled = 0;
+ int aper_enabled = 0, last_aper_enabled = 0, last_valid = 0;
if (!early_pci_allowed())
return;
+ /* This is mostly duplicate of iommu_hole_init */
fix = 0;
- for (num = 24; num < 32; num++) {
- if (!early_is_k8_nb(read_pci_config(0, num, 3, 0x00)))
- continue;
-
- ctl = read_pci_config(0, num, 3, 0x90);
- aper_enabled = ctl & 1;
- aper_order = (ctl >> 1) & 7;
- aper_size = (32 * 1024 * 1024) << aper_order;
- aper_base = read_pci_config(0, num, 3, 0x94) & 0x7fff;
- aper_base <<= 25;
-
- if ((last_aper_order && aper_order != last_aper_order) ||
- (last_aper_base && aper_base != last_aper_base) ||
- (last_aper_enabled && aper_enabled != last_aper_enabled)) {
- fix = 1;
- break;
+ for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
+ int bus;
+ int dev_base, dev_limit;
+
+ bus = bus_dev_ranges[i].bus;
+ dev_base = bus_dev_ranges[i].dev_base;
+ dev_limit = bus_dev_ranges[i].dev_limit;
+
+ for (slot = dev_base; slot < dev_limit; slot++) {
+ if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00)))
+ continue;
+
+ ctl = read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL);
+ aper_enabled = ctl & AMD64_GARTEN;
+ aper_order = (ctl >> 1) & 7;
+ aper_size = (32 * 1024 * 1024) << aper_order;
+ aper_base = read_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE) & 0x7fff;
+ aper_base <<= 25;
+
+ if (last_valid) {
+ if ((aper_order != last_aper_order) ||
+ (aper_base != last_aper_base) ||
+ (aper_enabled != last_aper_enabled)) {
+ fix = 1;
+ break;
+ }
+ }
+
+ last_aper_order = aper_order;
+ last_aper_base = aper_base;
+ last_aper_enabled = aper_enabled;
+ last_valid = 1;
}
- last_aper_order = aper_order;
- last_aper_base = aper_base;
- last_aper_enabled = aper_enabled;
}
if (!fix && !aper_enabled)
@@ -290,32 +326,46 @@ void __init early_gart_iommu_check(void)
if (gart_fix_e820 && !fix && aper_enabled) {
if (e820_any_mapped(aper_base, aper_base + aper_size,
E820_RAM)) {
- /* reserved it, so we can resuse it in second kernel */
+ /* reserve it, so we can reuse it in second kernel */
printk(KERN_INFO "update e820 for GART\n");
add_memory_region(aper_base, aper_size, E820_RESERVED);
update_e820();
}
- return;
}
+ if (!fix)
+ return;
+
/* different nodes have different setting, disable them all at first*/
- for (num = 24; num < 32; num++) {
- if (!early_is_k8_nb(read_pci_config(0, num, 3, 0x00)))
- continue;
+ for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
+ int bus;
+ int dev_base, dev_limit;
+
+ bus = bus_dev_ranges[i].bus;
+ dev_base = bus_dev_ranges[i].dev_base;
+ dev_limit = bus_dev_ranges[i].dev_limit;
+
+ for (slot = dev_base; slot < dev_limit; slot++) {
+ if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00)))
+ continue;
- ctl = read_pci_config(0, num, 3, 0x90);
- ctl &= ~1;
- write_pci_config(0, num, 3, 0x90, ctl);
+ ctl = read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL);
+ ctl &= ~AMD64_GARTEN;
+ write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, ctl);
+ }
}
}
+static int __initdata printed_gart_size_msg;
+
void __init gart_iommu_hole_init(void)
{
+ u32 agp_aper_base = 0, agp_aper_order = 0;
u32 aper_size, aper_alloc = 0, aper_order = 0, last_aper_order = 0;
u64 aper_base, last_aper_base = 0;
- int fix, num, valid_agp = 0;
- int node;
+ int fix, slot, valid_agp = 0;
+ int i, node;
if (gart_iommu_aperture_disabled || !fix_aperture ||
!early_pci_allowed())
@@ -323,38 +373,63 @@ void __init gart_iommu_hole_init(void)
printk(KERN_INFO "Checking aperture...\n");
+ if (!fallback_aper_force)
+ agp_aper_base = search_agp_bridge(&agp_aper_order, &valid_agp);
+
fix = 0;
node = 0;
- for (num = 24; num < 32; num++) {
- if (!early_is_k8_nb(read_pci_config(0, num, 3, 0x00)))
- continue;
-
- iommu_detected = 1;
- gart_iommu_aperture = 1;
-
- aper_order = (read_pci_config(0, num, 3, 0x90) >> 1) & 7;
- aper_size = (32 * 1024 * 1024) << aper_order;
- aper_base = read_pci_config(0, num, 3, 0x94) & 0x7fff;
- aper_base <<= 25;
-
- printk(KERN_INFO "Node %d: aperture @ %Lx size %u MB\n",
- node, aper_base, aper_size >> 20);
- node++;
-
- if (!aperture_valid(aper_base, aper_size)) {
- fix = 1;
- break;
- }
+ for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
+ int bus;
+ int dev_base, dev_limit;
+
+ bus = bus_dev_ranges[i].bus;
+ dev_base = bus_dev_ranges[i].dev_base;
+ dev_limit = bus_dev_ranges[i].dev_limit;
+
+ for (slot = dev_base; slot < dev_limit; slot++) {
+ if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00)))
+ continue;
+
+ iommu_detected = 1;
+ gart_iommu_aperture = 1;
+
+ aper_order = (read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL) >> 1) & 7;
+ aper_size = (32 * 1024 * 1024) << aper_order;
+ aper_base = read_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE) & 0x7fff;
+ aper_base <<= 25;
+
+ printk(KERN_INFO "Node %d: aperture @ %Lx size %u MB\n",
+ node, aper_base, aper_size >> 20);
+ node++;
+
+ if (!aperture_valid(aper_base, aper_size, 64<<20)) {
+ if (valid_agp && agp_aper_base &&
+ agp_aper_base == aper_base &&
+ agp_aper_order == aper_order) {
+ /* the same between two setting from NB and agp */
+ if (!no_iommu && end_pfn > MAX_DMA32_PFN && !printed_gart_size_msg) {
+ printk(KERN_ERR "you are using iommu with agp, but GART size is less than 64M\n");
+ printk(KERN_ERR "please increase GART size in your BIOS setup\n");
+ printk(KERN_ERR "if BIOS doesn't have that option, contact your HW vendor!\n");
+ printed_gart_size_msg = 1;
+ }
+ } else {
+ fix = 1;
+ goto out;
+ }
+ }
- if ((last_aper_order && aper_order != last_aper_order) ||
- (last_aper_base && aper_base != last_aper_base)) {
- fix = 1;
- break;
+ if ((last_aper_order && aper_order != last_aper_order) ||
+ (last_aper_base && aper_base != last_aper_base)) {
+ fix = 1;
+ goto out;
+ }
+ last_aper_order = aper_order;
+ last_aper_base = aper_base;
}
- last_aper_order = aper_order;
- last_aper_base = aper_base;
}
+out:
if (!fix && !fallback_aper_force) {
if (last_aper_base) {
unsigned long n = (32 * 1024 * 1024) << last_aper_order;
@@ -364,8 +439,10 @@ void __init gart_iommu_hole_init(void)
return;
}
- if (!fallback_aper_force)
- aper_alloc = search_agp_bridge(&aper_order, &valid_agp);
+ if (!fallback_aper_force) {
+ aper_alloc = agp_aper_base;
+ aper_order = agp_aper_order;
+ }
if (aper_alloc) {
/* Got the aperture from the AGP bridge */
@@ -401,16 +478,24 @@ void __init gart_iommu_hole_init(void)
}
/* Fix up the north bridges */
- for (num = 24; num < 32; num++) {
- if (!early_is_k8_nb(read_pci_config(0, num, 3, 0x00)))
- continue;
-
- /*
- * Don't enable translation yet. That is done later.
- * Assume this BIOS didn't initialise the GART so
- * just overwrite all previous bits
- */
- write_pci_config(0, num, 3, 0x90, aper_order<<1);
- write_pci_config(0, num, 3, 0x94, aper_alloc>>25);
+ for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
+ int bus;
+ int dev_base, dev_limit;
+
+ bus = bus_dev_ranges[i].bus;
+ dev_base = bus_dev_ranges[i].dev_base;
+ dev_limit = bus_dev_ranges[i].dev_limit;
+ for (slot = dev_base; slot < dev_limit; slot++) {
+ if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00)))
+ continue;
+
+ /* Don't enable translation yet. That is done later.
+ Assume this BIOS didn't initialise the GART so
+ just overwrite all previous bits */
+ write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, aper_order << 1);
+ write_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE, aper_alloc >> 25);
+ }
}
+
+ set_up_gart_resume(aper_order, aper_alloc);
}
diff --git a/arch/x86/kernel/apic_32.c b/arch/x86/kernel/apic_32.c
index 4b99b1bdeb6..45d8da405ad 100644
--- a/arch/x86/kernel/apic_32.c
+++ b/arch/x86/kernel/apic_32.c
@@ -64,9 +64,8 @@ static int enable_local_apic __initdata;
/* Local APIC timer verification ok */
static int local_apic_timer_verify_ok;
-/* Disable local APIC timer from the kernel commandline or via dmi quirk
- or using CPU MSR check */
-int local_apic_timer_disabled;
+/* Disable local APIC timer from the kernel commandline or via dmi quirk */
+static int local_apic_timer_disabled;
/* Local APIC timer works in C2 */
int local_apic_timer_c2_ok;
EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok);
@@ -1154,9 +1153,6 @@ static int __init detect_init_APIC(void)
if (l & MSR_IA32_APICBASE_ENABLE)
mp_lapic_addr = l & MSR_IA32_APICBASE_BASE;
- if (nmi_watchdog != NMI_NONE && nmi_watchdog != NMI_DISABLED)
- nmi_watchdog = NMI_LOCAL_APIC;
-
printk(KERN_INFO "Found and enabled local APIC!\n");
apic_pm_activate();
@@ -1269,6 +1265,10 @@ int __init APIC_init_uniprocessor(void)
setup_local_APIC();
+#ifdef CONFIG_X86_IO_APIC
+ if (!smp_found_config || skip_ioapic_setup || !nr_ioapics)
+#endif
+ localise_nmi_watchdog();
end_local_APIC_setup();
#ifdef CONFIG_X86_IO_APIC
if (smp_found_config)
diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c
index 0633cfd0dc2..3ef7752aa8e 100644
--- a/arch/x86/kernel/apic_64.c
+++ b/arch/x86/kernel/apic_64.c
@@ -43,7 +43,7 @@
#include <mach_ipi.h>
#include <mach_apic.h>
-int disable_apic_timer __cpuinitdata;
+static int disable_apic_timer __cpuinitdata;
static int apic_calibrate_pmtmr __initdata;
int disable_apic;
@@ -422,32 +422,8 @@ void __init setup_boot_APIC_clock(void)
setup_APIC_timer();
}
-/*
- * AMD C1E enabled CPUs have a real nasty problem: Some BIOSes set the
- * C1E flag only in the secondary CPU, so when we detect the wreckage
- * we already have enabled the boot CPU local apic timer. Check, if
- * disable_apic_timer is set and the DUMMY flag is cleared. If yes,
- * set the DUMMY flag again and force the broadcast mode in the
- * clockevents layer.
- */
-static void __cpuinit check_boot_apic_timer_broadcast(void)
-{
- if (!disable_apic_timer ||
- (lapic_clockevent.features & CLOCK_EVT_FEAT_DUMMY))
- return;
-
- printk(KERN_INFO "AMD C1E detected late. Force timer broadcast.\n");
- lapic_clockevent.features |= CLOCK_EVT_FEAT_DUMMY;
-
- local_irq_enable();
- clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE,
- &boot_cpu_physical_apicid);
- local_irq_disable();
-}
-
void __cpuinit setup_secondary_APIC_clock(void)
{
- check_boot_apic_timer_broadcast();
setup_APIC_timer();
}
@@ -875,7 +851,7 @@ static int __init detect_init_APIC(void)
void __init early_init_lapic_mapping(void)
{
- unsigned long apic_phys;
+ unsigned long phys_addr;
/*
* If no local APIC can be found then go out
@@ -884,11 +860,11 @@ void __init early_init_lapic_mapping(void)
if (!smp_found_config)
return;
- apic_phys = mp_lapic_addr;
+ phys_addr = mp_lapic_addr;
- set_fixmap_nocache(FIX_APIC_BASE, apic_phys);
+ set_fixmap_nocache(FIX_APIC_BASE, phys_addr);
apic_printk(APIC_VERBOSE, "mapped APIC to %16lx (%16lx)\n",
- APIC_BASE, apic_phys);
+ APIC_BASE, phys_addr);
/*
* Fetch the APIC ID of the BSP in case we have a
@@ -954,6 +930,8 @@ int __init APIC_init_uniprocessor(void)
if (!skip_ioapic_setup && nr_ioapics)
enable_IO_APIC();
+ if (!smp_found_config || skip_ioapic_setup || !nr_ioapics)
+ localise_nmi_watchdog();
end_local_APIC_setup();
if (smp_found_config && !skip_ioapic_setup && nr_ioapics)
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index bf9290e2901..00e6d137095 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -228,6 +228,7 @@
#include <linux/suspend.h>
#include <linux/kthread.h>
#include <linux/jiffies.h>
+#include <linux/smp_lock.h>
#include <asm/system.h>
#include <asm/uaccess.h>
@@ -1149,7 +1150,7 @@ static void queue_event(apm_event_t event, struct apm_user *sender)
as->event_tail = 0;
}
as->events[as->event_head] = event;
- if ((!as->suser) || (!as->writer))
+ if (!as->suser || !as->writer)
continue;
switch (event) {
case APM_SYS_SUSPEND:
@@ -1396,7 +1397,7 @@ static void apm_mainloop(void)
static int check_apm_user(struct apm_user *as, const char *func)
{
- if ((as == NULL) || (as->magic != APM_BIOS_MAGIC)) {
+ if (as == NULL || as->magic != APM_BIOS_MAGIC) {
printk(KERN_ERR "apm: %s passed bad filp\n", func);
return 1;
}
@@ -1459,18 +1460,19 @@ static unsigned int do_poll(struct file *fp, poll_table *wait)
return 0;
}
-static int do_ioctl(struct inode *inode, struct file *filp,
- u_int cmd, u_long arg)
+static long do_ioctl(struct file *filp, u_int cmd, u_long arg)
{
struct apm_user *as;
+ int ret;
as = filp->private_data;
if (check_apm_user(as, "ioctl"))
return -EIO;
- if ((!as->suser) || (!as->writer))
+ if (!as->suser || !as->writer)
return -EPERM;
switch (cmd) {
case APM_IOC_STANDBY:
+ lock_kernel();
if (as->standbys_read > 0) {
as->standbys_read--;
as->standbys_pending--;
@@ -1479,8 +1481,10 @@ static int do_ioctl(struct inode *inode, struct file *filp,
queue_event(APM_USER_STANDBY, as);
if (standbys_pending <= 0)
standby();
+ unlock_kernel();
break;
case APM_IOC_SUSPEND:
+ lock_kernel();
if (as->suspends_read > 0) {
as->suspends_read--;
as->suspends_pending--;
@@ -1488,16 +1492,17 @@ static int do_ioctl(struct inode *inode, struct file *filp,
} else
queue_event(APM_USER_SUSPEND, as);
if (suspends_pending <= 0) {
- return suspend(1);
+ ret = suspend(1);
} else {
as->suspend_wait = 1;
wait_event_interruptible(apm_suspend_waitqueue,
as->suspend_wait == 0);
- return as->suspend_result;
+ ret = as->suspend_result;
}
- break;
+ unlock_kernel();
+ return ret;
default:
- return -EINVAL;
+ return -ENOTTY;
}
return 0;
}
@@ -1860,7 +1865,7 @@ static const struct file_operations apm_bios_fops = {
.owner = THIS_MODULE,
.read = do_read,
.poll = do_poll,
- .ioctl = do_ioctl,
+ .unlocked_ioctl = do_ioctl,
.open = do_open,
.release = do_release,
};
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index a0c6f819088..65b1be5fe9c 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -6,11 +6,15 @@ obj-y := intel_cacheinfo.o addon_cpuid_features.o
obj-y += proc.o feature_names.o
obj-$(CONFIG_X86_32) += common.o bugs.o
+obj-$(CONFIG_X86_64) += bugs_64.o
obj-$(CONFIG_X86_32) += amd.o
+obj-$(CONFIG_X86_64) += amd_64.o
obj-$(CONFIG_X86_32) += cyrix.o
obj-$(CONFIG_X86_32) += centaur.o
+obj-$(CONFIG_X86_64) += centaur_64.o
obj-$(CONFIG_X86_32) += transmeta.o
obj-$(CONFIG_X86_32) += intel.o
+obj-$(CONFIG_X86_64) += intel_64.o
obj-$(CONFIG_X86_32) += umc.o
obj-$(CONFIG_X86_MCE) += mcheck/
diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/addon_cpuid_features.c
index c2e1ce33c7c..84a8220a607 100644
--- a/arch/x86/kernel/cpu/addon_cpuid_features.c
+++ b/arch/x86/kernel/cpu/addon_cpuid_features.c
@@ -1,9 +1,7 @@
-
/*
* Routines to indentify additional cpu features that are scattered in
* cpuid space.
*/
-
#include <linux/cpu.h>
#include <asm/pat.h>
@@ -53,19 +51,20 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c)
#ifdef CONFIG_X86_PAT
void __cpuinit validate_pat_support(struct cpuinfo_x86 *c)
{
+ if (!cpu_has_pat)
+ pat_disable("PAT not supported by CPU.");
+
switch (c->x86_vendor) {
- case X86_VENDOR_AMD:
- if (c->x86 >= 0xf && c->x86 <= 0x11)
- return;
- break;
case X86_VENDOR_INTEL:
if (c->x86 == 0xF || (c->x86 == 6 && c->x86_model >= 15))
return;
break;
+ case X86_VENDOR_AMD:
+ case X86_VENDOR_CENTAUR:
+ case X86_VENDOR_TRANSMETA:
+ return;
}
- pat_disable(cpu_has_pat ?
- "PAT disabled. Not yet verified on this CPU type." :
- "PAT not supported by CPU.");
+ pat_disable("PAT disabled. Not yet verified on this CPU type.");
}
#endif
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 24586682829..81a07ca65d4 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -24,43 +24,6 @@
extern void vide(void);
__asm__(".align 4\nvide: ret");
-#ifdef CONFIG_X86_LOCAL_APIC
-#define ENABLE_C1E_MASK 0x18000000
-#define CPUID_PROCESSOR_SIGNATURE 1
-#define CPUID_XFAM 0x0ff00000
-#define CPUID_XFAM_K8 0x00000000
-#define CPUID_XFAM_10H 0x00100000
-#define CPUID_XFAM_11H 0x00200000
-#define CPUID_XMOD 0x000f0000
-#define CPUID_XMOD_REV_F 0x00040000
-
-/* AMD systems with C1E don't have a working lAPIC timer. Check for that. */
-static __cpuinit int amd_apic_timer_broken(void)
-{
- u32 lo, hi;
- u32 eax = cpuid_eax(CPUID_PROCESSOR_SIGNATURE);
- switch (eax & CPUID_XFAM) {
- case CPUID_XFAM_K8:
- if ((eax & CPUID_XMOD) < CPUID_XMOD_REV_F)
- break;
- case CPUID_XFAM_10H:
- case CPUID_XFAM_11H:
- rdmsr(MSR_K8_ENABLE_C1E, lo, hi);
- if (lo & ENABLE_C1E_MASK) {
- if (smp_processor_id() != boot_cpu_physical_apicid)
- printk(KERN_INFO "AMD C1E detected late. "
- " Force timer broadcast.\n");
- return 1;
- }
- break;
- default:
- /* err on the side of caution */
- return 1;
- }
- return 0;
-}
-#endif
-
int force_mwait __cpuinitdata;
static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
@@ -297,11 +260,6 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
num_cache_leaves = 3;
}
-#ifdef CONFIG_X86_LOCAL_APIC
- if (amd_apic_timer_broken())
- local_apic_timer_disabled = 1;
-#endif
-
/* K6s reports MCEs but don't actually have all the MSRs */
if (c->x86 < 6)
clear_cpu_cap(c, X86_FEATURE_MCE);
diff --git a/arch/x86/kernel/cpu/amd_64.c b/arch/x86/kernel/cpu/amd_64.c
new file mode 100644
index 00000000000..30b7557c964
--- /dev/null
+++ b/arch/x86/kernel/cpu/amd_64.c
@@ -0,0 +1,211 @@
+#include <linux/init.h>
+#include <linux/mm.h>
+
+#include <asm/numa_64.h>
+#include <asm/mmconfig.h>
+#include <asm/cacheflush.h>
+
+#include <mach_apic.h>
+
+#include "cpu.h"
+
+int force_mwait __cpuinitdata;
+
+#ifdef CONFIG_NUMA
+static int __cpuinit nearby_node(int apicid)
+{
+ int i, node;
+
+ for (i = apicid - 1; i >= 0; i--) {
+ node = apicid_to_node[i];
+ if (node != NUMA_NO_NODE && node_online(node))
+ return node;
+ }
+ for (i = apicid + 1; i < MAX_LOCAL_APIC; i++) {
+ node = apicid_to_node[i];
+ if (node != NUMA_NO_NODE && node_online(node))
+ return node;
+ }
+ return first_node(node_online_map); /* Shouldn't happen */
+}
+#endif
+
+/*
+ * On a AMD dual core setup the lower bits of the APIC id distingush the cores.
+ * Assumes number of cores is a power of two.
+ */
+static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_SMP
+ unsigned bits;
+#ifdef CONFIG_NUMA
+ int cpu = smp_processor_id();
+ int node = 0;
+ unsigned apicid = hard_smp_processor_id();
+#endif
+ bits = c->x86_coreid_bits;
+
+ /* Low order bits define the core id (index of core in socket) */
+ c->cpu_core_id = c->initial_apicid & ((1 << bits)-1);
+ /* Convert the initial APIC ID into the socket ID */
+ c->phys_proc_id = c->initial_apicid >> bits;
+
+#ifdef CONFIG_NUMA
+ node = c->phys_proc_id;
+ if (apicid_to_node[apicid] != NUMA_NO_NODE)
+ node = apicid_to_node[apicid];
+ if (!node_online(node)) {
+ /* Two possibilities here:
+ - The CPU is missing memory and no node was created.
+ In that case try picking one from a nearby CPU
+ - The APIC IDs differ from the HyperTransport node IDs
+ which the K8 northbridge parsing fills in.
+ Assume they are all increased by a constant offset,
+ but in the same order as the HT nodeids.
+ If that doesn't result in a usable node fall back to the
+ path for the previous case. */
+
+ int ht_nodeid = c->initial_apicid;
+
+ if (ht_nodeid >= 0 &&
+ apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
+ node = apicid_to_node[ht_nodeid];
+ /* Pick a nearby node */
+ if (!node_online(node))
+ node = nearby_node(apicid);
+ }
+ numa_set_node(cpu, node);
+
+ printk(KERN_INFO "CPU %d/%x -> Node %d\n", cpu, apicid, node);
+#endif
+#endif
+}
+
+static void __cpuinit early_init_amd_mc(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_SMP
+ unsigned bits, ecx;
+
+ /* Multi core CPU? */
+ if (c->extended_cpuid_level < 0x80000008)
+ return;
+
+ ecx = cpuid_ecx(0x80000008);
+
+ c->x86_max_cores = (ecx & 0xff) + 1;
+
+ /* CPU telling us the core id bits shift? */
+ bits = (ecx >> 12) & 0xF;
+
+ /* Otherwise recompute */
+ if (bits == 0) {
+ while ((1 << bits) < c->x86_max_cores)
+ bits++;
+ }
+
+ c->x86_coreid_bits = bits;
+
+#endif
+}
+
+static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
+{
+ early_init_amd_mc(c);
+
+ /* c->x86_power is 8000_0007 edx. Bit 8 is constant TSC */
+ if (c->x86_power & (1<<8))
+ set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+}
+
+static void __cpuinit init_amd(struct cpuinfo_x86 *c)
+{
+ unsigned level;
+
+#ifdef CONFIG_SMP
+ unsigned long value;
+
+ /*
+ * Disable TLB flush filter by setting HWCR.FFDIS on K8
+ * bit 6 of msr C001_0015
+ *
+ * Errata 63 for SH-B3 steppings
+ * Errata 122 for all steppings (F+ have it disabled by default)
+ */
+ if (c->x86 == 15) {
+ rdmsrl(MSR_K8_HWCR, value);
+ value |= 1 << 6;
+ wrmsrl(MSR_K8_HWCR, value);
+ }
+#endif
+
+ /* Bit 31 in normal CPUID used for nonstandard 3DNow ID;
+ 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway */
+ clear_cpu_cap(c, 0*32+31);
+
+ /* On C+ stepping K8 rep microcode works well for copy/memset */
+ level = cpuid_eax(1);
+ if (c->x86 == 15 && ((level >= 0x0f48 && level < 0x0f50) ||
+ level >= 0x0f58))
+ set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+ if (c->x86 == 0x10 || c->x86 == 0x11)
+ set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+
+ /* Enable workaround for FXSAVE leak */
+ if (c->x86 >= 6)
+ set_cpu_cap(c, X86_FEATURE_FXSAVE_LEAK);
+
+ level = get_model_name(c);
+ if (!level) {
+ switch (c->x86) {
+ case 15:
+ /* Should distinguish Models here, but this is only
+ a fallback anyways. */
+ strcpy(c->x86_model_id, "Hammer");
+ break;
+ }
+ }
+ display_cacheinfo(c);
+
+ /* Multi core CPU? */
+ if (c->extended_cpuid_level >= 0x80000008)
+ amd_detect_cmp(c);
+
+ if (c->extended_cpuid_level >= 0x80000006 &&
+ (cpuid_edx(0x80000006) & 0xf000))
+ num_cache_leaves = 4;
+ else
+ num_cache_leaves = 3;
+
+ if (c->x86 == 0xf || c->x86 == 0x10 || c->x86 == 0x11)
+ set_cpu_cap(c, X86_FEATURE_K8);
+
+ /* MFENCE stops RDTSC speculation */
+ set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
+
+ if (c->x86 == 0x10)
+ fam10h_check_enable_mmcfg();
+
+ if (c == &boot_cpu_data && c->x86 >= 0xf && c->x86 <= 0x11) {
+ unsigned long long tseg;
+
+ /*
+ * Split up direct mapping around the TSEG SMM area.
+ * Don't do it for gbpages because there seems very little
+ * benefit in doing so.
+ */
+ if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg) &&
+ (tseg >> PMD_SHIFT) <
+ (max_pfn_mapped >> (PMD_SHIFT-PAGE_SHIFT)))
+ set_memory_4k((unsigned long)__va(tseg), 1);
+ }
+}
+
+static struct cpu_dev amd_cpu_dev __cpuinitdata = {
+ .c_vendor = "AMD",
+ .c_ident = { "AuthenticAMD" },
+ .c_early_init = early_init_amd,
+ .c_init = init_amd,
+};
+
+cpu_vendor_dev_register(X86_VENDOR_AMD, &amd_cpu_dev);
+
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 170d2f5523b..1b1c56bb338 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -59,8 +59,12 @@ static void __init check_fpu(void)
return;
}
-/* trap_init() enabled FXSR and company _before_ testing for FP problems here. */
- /* Test for the divl bug.. */
+ /*
+ * trap_init() enabled FXSR and company _before_ testing for FP
+ * problems here.
+ *
+ * Test for the divl bug..
+ */
__asm__("fninit\n\t"
"fldl %1\n\t"
"fdivl %2\n\t"
@@ -108,10 +112,15 @@ static void __init check_popad(void)
"movl $12345678,%%eax; movl $0,%%edi; pusha; popa; movl (%%edx,%%edi),%%ecx "
: "=&a" (res)
: "d" (inp)
- : "ecx", "edi" );
- /* If this fails, it means that any user program may lock the CPU hard. Too bad. */
- if (res != 12345678) printk( "Buggy.\n" );
- else printk( "OK.\n" );
+ : "ecx", "edi");
+ /*
+ * If this fails, it means that any user program may lock the
+ * CPU hard. Too bad.
+ */
+ if (res != 12345678)
+ printk("Buggy.\n");
+ else
+ printk("OK.\n");
#endif
}
@@ -137,7 +146,8 @@ static void __init check_config(void)
* i486+ only features! (WP works in supervisor mode and the
* new "invlpg" and "bswap" instructions)
*/
-#if defined(CONFIG_X86_WP_WORKS_OK) || defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_BSWAP)
+#if defined(CONFIG_X86_WP_WORKS_OK) || defined(CONFIG_X86_INVLPG) || \
+ defined(CONFIG_X86_BSWAP)
if (boot_cpu_data.x86 == 3)
panic("Kernel requires i486+ for 'invlpg' and other features");
#endif
@@ -170,6 +180,7 @@ void __init check_bugs(void)
check_fpu();
check_hlt();
check_popad();
- init_utsname()->machine[1] = '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
+ init_utsname()->machine[1] =
+ '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
alternative_instructions();
}
diff --git a/arch/x86/kernel/bugs_64.c b/arch/x86/kernel/cpu/bugs_64.c
index 9a3ed0649d4..9a3ed0649d4 100644
--- a/arch/x86/kernel/bugs_64.c
+++ b/arch/x86/kernel/cpu/bugs_64.c
diff --git a/arch/x86/kernel/cpu/centaur_64.c b/arch/x86/kernel/cpu/centaur_64.c
new file mode 100644
index 00000000000..13526fd5cce
--- /dev/null
+++ b/arch/x86/kernel/cpu/centaur_64.c
@@ -0,0 +1,43 @@
+#include <linux/init.h>
+#include <linux/smp.h>
+
+#include <asm/cpufeature.h>
+#include <asm/processor.h>
+
+#include "cpu.h"
+
+static void __cpuinit early_init_centaur(struct cpuinfo_x86 *c)
+{
+ if (c->x86 == 0x6 && c->x86_model >= 0xf)
+ set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+}
+
+static void __cpuinit init_centaur(struct cpuinfo_x86 *c)
+{
+ /* Cache sizes */
+ unsigned n;
+
+ n = c->extended_cpuid_level;
+ if (n >= 0x80000008) {
+ unsigned eax = cpuid_eax(0x80000008);
+ c->x86_virt_bits = (eax >> 8) & 0xff;
+ c->x86_phys_bits = eax & 0xff;
+ }
+
+ if (c->x86 == 0x6 && c->x86_model >= 0xf) {
+ c->x86_cache_alignment = c->x86_clflush_size * 2;
+ set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+ set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+ }
+ set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
+}
+
+static struct cpu_dev centaur_cpu_dev __cpuinitdata = {
+ .c_vendor = "Centaur",
+ .c_ident = { "CentaurHauls" },
+ .c_early_init = early_init_centaur,
+ .c_init = init_centaur,
+};
+
+cpu_vendor_dev_register(X86_VENDOR_CENTAUR, &centaur_cpu_dev);
+
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 783691b2a73..4d894e8565f 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -1,3 +1,6 @@
+#ifndef ARCH_X86_CPU_H
+
+#define ARCH_X86_CPU_H
struct cpu_model_info {
int vendor;
@@ -36,3 +39,5 @@ extern struct cpu_vendor_dev __x86cpuvendor_start[], __x86cpuvendor_end[];
extern int get_model_name(struct cpuinfo_x86 *c);
extern void display_cacheinfo(struct cpuinfo_x86 *c);
+
+#endif
diff --git a/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c b/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c
index f03e9153618..965ea52767a 100644
--- a/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c
+++ b/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c
@@ -26,9 +26,10 @@
#define NFORCE2_SAFE_DISTANCE 50
/* Delay in ms between FSB changes */
-//#define NFORCE2_DELAY 10
+/* #define NFORCE2_DELAY 10 */
-/* nforce2_chipset:
+/*
+ * nforce2_chipset:
* FSB is changed using the chipset
*/
static struct pci_dev *nforce2_chipset_dev;
@@ -36,13 +37,13 @@ static struct pci_dev *nforce2_chipset_dev;
/* fid:
* multiplier * 10
*/
-static int fid = 0;
+static int fid;
/* min_fsb, max_fsb:
* minimum and maximum FSB (= FSB at boot time)
*/
-static int min_fsb = 0;
-static int max_fsb = 0;
+static int min_fsb;
+static int max_fsb;
MODULE_AUTHOR("Sebastian Witt <se.witt@gmx.net>");
MODULE_DESCRIPTION("nForce2 FSB changing cpufreq driver");
@@ -53,7 +54,7 @@ module_param(min_fsb, int, 0444);
MODULE_PARM_DESC(fid, "CPU multiplier to use (11.5 = 115)");
MODULE_PARM_DESC(min_fsb,
- "Minimum FSB to use, if not defined: current FSB - 50");
+ "Minimum FSB to use, if not defined: current FSB - 50");
#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "cpufreq-nforce2", msg)
@@ -139,7 +140,7 @@ static unsigned int nforce2_fsb_read(int bootfsb)
/* Get chipset boot FSB from subdevice 5 (FSB at boot-time) */
nforce2_sub5 = pci_get_subsys(PCI_VENDOR_ID_NVIDIA,
- 0x01EF,PCI_ANY_ID,PCI_ANY_ID,NULL);
+ 0x01EF, PCI_ANY_ID, PCI_ANY_ID, NULL);
if (!nforce2_sub5)
return 0;
@@ -147,13 +148,13 @@ static unsigned int nforce2_fsb_read(int bootfsb)
fsb /= 1000000;
/* Check if PLL register is already set */
- pci_read_config_byte(nforce2_chipset_dev,NFORCE2_PLLENABLE, (u8 *)&temp);
+ pci_read_config_byte(nforce2_chipset_dev, NFORCE2_PLLENABLE, (u8 *)&temp);
- if(bootfsb || !temp)
+ if (bootfsb || !temp)
return fsb;
-
+
/* Use PLL register FSB value */
- pci_read_config_dword(nforce2_chipset_dev,NFORCE2_PLLREG, &temp);
+ pci_read_config_dword(nforce2_chipset_dev, NFORCE2_PLLREG, &temp);
fsb = nforce2_calc_fsb(temp);
return fsb;
@@ -184,7 +185,7 @@ static int nforce2_set_fsb(unsigned int fsb)
}
/* First write? Then set actual value */
- pci_read_config_byte(nforce2_chipset_dev,NFORCE2_PLLENABLE, (u8 *)&temp);
+ pci_read_config_byte(nforce2_chipset_dev, NFORCE2_PLLENABLE, (u8 *)&temp);
if (!temp) {
pll = nforce2_calc_pll(tfsb);
@@ -210,7 +211,8 @@ static int nforce2_set_fsb(unsigned int fsb)
tfsb--;
/* Calculate the PLL reg. value */
- if ((pll = nforce2_calc_pll(tfsb)) == -1)
+ pll = nforce2_calc_pll(tfsb);
+ if (pll == -1)
return -EINVAL;
nforce2_write_pll(pll);
@@ -249,7 +251,7 @@ static unsigned int nforce2_get(unsigned int cpu)
static int nforce2_target(struct cpufreq_policy *policy,
unsigned int target_freq, unsigned int relation)
{
-// unsigned long flags;
+/* unsigned long flags; */
struct cpufreq_freqs freqs;
unsigned int target_fsb;
@@ -271,17 +273,17 @@ static int nforce2_target(struct cpufreq_policy *policy,
cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
/* Disable IRQs */
- //local_irq_save(flags);
+ /* local_irq_save(flags); */
if (nforce2_set_fsb(target_fsb) < 0)
printk(KERN_ERR "cpufreq: Changing FSB to %d failed\n",
- target_fsb);
+ target_fsb);
else
dprintk("Changed FSB successfully to %d\n",
- target_fsb);
+ target_fsb);
/* Enable IRQs */
- //local_irq_restore(flags);
+ /* local_irq_restore(flags); */
cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
@@ -302,8 +304,8 @@ static int nforce2_verify(struct cpufreq_policy *policy)
policy->max = (fsb_pol_max + 1) * fid * 100;
cpufreq_verify_within_limits(policy,
- policy->cpuinfo.min_freq,
- policy->cpuinfo.max_freq);
+ policy->cpuinfo.min_freq,
+ policy->cpuinfo.max_freq);
return 0;
}
@@ -347,7 +349,7 @@ static int nforce2_cpu_init(struct cpufreq_policy *policy)
/* Set maximum FSB to FSB at boot time */
max_fsb = nforce2_fsb_read(1);
- if(!max_fsb)
+ if (!max_fsb)
return -EIO;
if (!min_fsb)
diff --git a/arch/x86/kernel/cpu/intel_64.c b/arch/x86/kernel/cpu/intel_64.c
new file mode 100644
index 00000000000..fcb1cc9d75c
--- /dev/null
+++ b/arch/x86/kernel/cpu/intel_64.c
@@ -0,0 +1,103 @@
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <asm/processor.h>
+#include <asm/ptrace.h>
+#include <asm/topology.h>
+#include <asm/numa_64.h>
+
+#include "cpu.h"
+
+static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
+{
+ if ((c->x86 == 0xf && c->x86_model >= 0x03) ||
+ (c->x86 == 0x6 && c->x86_model >= 0x0e))
+ set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+}
+
+/*
+ * find out the number of processor cores on the die
+ */
+static int __cpuinit intel_num_cpu_cores(struct cpuinfo_x86 *c)
+{
+ unsigned int eax, t;
+
+ if (c->cpuid_level < 4)
+ return 1;
+
+ cpuid_count(4, 0, &eax, &t, &t, &t);
+
+ if (eax & 0x1f)
+ return ((eax >> 26) + 1);
+ else
+ return 1;
+}
+
+static void __cpuinit srat_detect_node(void)
+{
+#ifdef CONFIG_NUMA
+ unsigned node;
+ int cpu = smp_processor_id();
+ int apicid = hard_smp_processor_id();
+
+ /* Don't do the funky fallback heuristics the AMD version employs
+ for now. */
+ node = apicid_to_node[apicid];
+ if (node == NUMA_NO_NODE || !node_online(node))
+ node = first_node(node_online_map);
+ numa_set_node(cpu, node);
+
+ printk(KERN_INFO "CPU %d/%x -> Node %d\n", cpu, apicid, node);
+#endif
+}
+
+static void __cpuinit init_intel(struct cpuinfo_x86 *c)
+{
+ /* Cache sizes */
+ unsigned n;
+
+ init_intel_cacheinfo(c);
+ if (c->cpuid_level > 9) {
+ unsigned eax = cpuid_eax(10);
+ /* Check for version and the number of counters */
+ if ((eax & 0xff) && (((eax>>8) & 0xff) > 1))
+ set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON);
+ }
+
+ if (cpu_has_ds) {
+ unsigned int l1, l2;
+ rdmsr(MSR_IA32_MISC_ENABLE, l1, l2);
+ if (!(l1 & (1<<11)))
+ set_cpu_cap(c, X86_FEATURE_BTS);
+ if (!(l1 & (1<<12)))
+ set_cpu_cap(c, X86_FEATURE_PEBS);
+ }
+
+
+ if (cpu_has_bts)
+ ds_init_intel(c);
+
+ n = c->extended_cpuid_level;
+ if (n >= 0x80000008) {
+ unsigned eax = cpuid_eax(0x80000008);
+ c->x86_virt_bits = (eax >> 8) & 0xff;
+ c->x86_phys_bits = eax & 0xff;
+ }
+
+ if (c->x86 == 15)
+ c->x86_cache_alignment = c->x86_clflush_size * 2;
+ if (c->x86 == 6)
+ set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+ set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
+ c->x86_max_cores = intel_num_cpu_cores(c);
+
+ srat_detect_node();
+}
+
+static struct cpu_dev intel_cpu_dev __cpuinitdata = {
+ .c_vendor = "Intel",
+ .c_ident = { "GenuineIntel" },
+ .c_early_init = early_init_intel,
+ .c_init = init_intel,
+};
+cpu_vendor_dev_register(X86_VENDOR_INTEL, &intel_cpu_dev);
+
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 26d615dcb14..2c8afafa18e 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -62,6 +62,7 @@ static struct _cache_table cache_table[] __cpuinitdata =
{ 0x4b, LVL_3, 8192 }, /* 16-way set assoc, 64 byte line size */
{ 0x4c, LVL_3, 12288 }, /* 12-way set assoc, 64 byte line size */
{ 0x4d, LVL_3, 16384 }, /* 16-way set assoc, 64 byte line size */
+ { 0x4e, LVL_2, 6144 }, /* 24-way set assoc, 64 byte line size */
{ 0x60, LVL_1_DATA, 16 }, /* 8-way set assoc, sectored cache, 64 byte line size */
{ 0x66, LVL_1_DATA, 8 }, /* 4-way set assoc, sectored cache, 64 byte line size */
{ 0x67, LVL_1_DATA, 16 }, /* 4-way set assoc, sectored cache, 64 byte line size */
diff --git a/arch/x86/kernel/cpu/mcheck/k7.c b/arch/x86/kernel/cpu/mcheck/k7.c
index e633c9c2b76..f390c9f6635 100644
--- a/arch/x86/kernel/cpu/mcheck/k7.c
+++ b/arch/x86/kernel/cpu/mcheck/k7.c
@@ -9,23 +9,23 @@
#include <linux/interrupt.h>
#include <linux/smp.h>
-#include <asm/processor.h>
+#include <asm/processor.h>
#include <asm/system.h>
#include <asm/msr.h>
#include "mce.h"
/* Machine Check Handler For AMD Athlon/Duron */
-static void k7_machine_check(struct pt_regs * regs, long error_code)
+static void k7_machine_check(struct pt_regs *regs, long error_code)
{
- int recover=1;
+ int recover = 1;
u32 alow, ahigh, high, low;
u32 mcgstl, mcgsth;
int i;
- rdmsr (MSR_IA32_MCG_STATUS, mcgstl, mcgsth);
+ rdmsr(MSR_IA32_MCG_STATUS, mcgstl, mcgsth);
if (mcgstl & (1<<0)) /* Recoverable ? */
- recover=0;
+ recover = 0;
printk(KERN_EMERG "CPU %d: Machine Check Exception: %08x%08x\n",
smp_processor_id(), mcgsth, mcgstl);
@@ -60,12 +60,12 @@ static void k7_machine_check(struct pt_regs * regs, long error_code)
}
if (recover&2)
- panic ("CPU context corrupt");
+ panic("CPU context corrupt");
if (recover&1)
- panic ("Unable to continue");
- printk (KERN_EMERG "Attempting to continue.\n");
+ panic("Unable to continue");
+ printk(KERN_EMERG "Attempting to continue.\n");
mcgstl &= ~(1<<2);
- wrmsr (MSR_IA32_MCG_STATUS,mcgstl, mcgsth);
+ wrmsr(MSR_IA32_MCG_STATUS, mcgstl, mcgsth);
}
@@ -81,25 +81,25 @@ void amd_mcheck_init(struct cpuinfo_x86 *c)
machine_check_vector = k7_machine_check;
wmb();
- printk (KERN_INFO "Intel machine check architecture supported.\n");
- rdmsr (MSR_IA32_MCG_CAP, l, h);
+ printk(KERN_INFO "Intel machine check architecture supported.\n");
+ rdmsr(MSR_IA32_MCG_CAP, l, h);
if (l & (1<<8)) /* Control register present ? */
- wrmsr (MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
+ wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
nr_mce_banks = l & 0xff;
/* Clear status for MC index 0 separately, we don't touch CTL,
* as some K7 Athlons cause spurious MCEs when its enabled. */
if (boot_cpu_data.x86 == 6) {
- wrmsr (MSR_IA32_MC0_STATUS, 0x0, 0x0);
+ wrmsr(MSR_IA32_MC0_STATUS, 0x0, 0x0);
i = 1;
} else
i = 0;
- for (; i<nr_mce_banks; i++) {
- wrmsr (MSR_IA32_MC0_CTL+4*i, 0xffffffff, 0xffffffff);
- wrmsr (MSR_IA32_MC0_STATUS+4*i, 0x0, 0x0);
+ for (; i < nr_mce_banks; i++) {
+ wrmsr(MSR_IA32_MC0_CTL+4*i, 0xffffffff, 0xffffffff);
+ wrmsr(MSR_IA32_MC0_STATUS+4*i, 0x0, 0x0);
}
- set_in_cr4 (X86_CR4_MCE);
- printk (KERN_INFO "Intel machine check reporting enabled on CPU#%d.\n",
+ set_in_cr4(X86_CR4_MCE);
+ printk(KERN_INFO "Intel machine check reporting enabled on CPU#%d.\n",
smp_processor_id());
}
diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c
index e07e8c068ae..501ca1cea27 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_64.c
@@ -31,7 +31,7 @@
#include <asm/idle.h>
#define MISC_MCELOG_MINOR 227
-#define NR_BANKS 6
+#define NR_SYSFS_BANKS 6
atomic_t mce_entry;
@@ -46,7 +46,7 @@ static int mce_dont_init;
*/
static int tolerant = 1;
static int banks;
-static unsigned long bank[NR_BANKS] = { [0 ... NR_BANKS-1] = ~0UL };
+static unsigned long bank[NR_SYSFS_BANKS] = { [0 ... NR_SYSFS_BANKS-1] = ~0UL };
static unsigned long notify_user;
static int rip_msr;
static int mce_bootlog = -1;
@@ -209,7 +209,7 @@ void do_machine_check(struct pt_regs * regs, long error_code)
barrier();
for (i = 0; i < banks; i++) {
- if (!bank[i])
+ if (i < NR_SYSFS_BANKS && !bank[i])
continue;
m.misc = 0;
@@ -444,9 +444,10 @@ static void mce_init(void *dummy)
rdmsrl(MSR_IA32_MCG_CAP, cap);
banks = cap & 0xff;
- if (banks > NR_BANKS) {
- printk(KERN_INFO "MCE: warning: using only %d banks\n", banks);
- banks = NR_BANKS;
+ if (banks > MCE_EXTENDED_BANK) {
+ banks = MCE_EXTENDED_BANK;
+ printk(KERN_INFO "MCE: warning: using only %d banks\n",
+ MCE_EXTENDED_BANK);
}
/* Use accurate RIP reporting if available. */
if ((cap & (1<<9)) && ((cap >> 16) & 0xff) >= 9)
@@ -462,7 +463,11 @@ static void mce_init(void *dummy)
wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
for (i = 0; i < banks; i++) {
- wrmsrl(MSR_IA32_MC0_CTL+4*i, bank[i]);
+ if (i < NR_SYSFS_BANKS)
+ wrmsrl(MSR_IA32_MC0_CTL+4*i, bank[i]);
+ else
+ wrmsrl(MSR_IA32_MC0_CTL+4*i, ~0UL);
+
wrmsrl(MSR_IA32_MC0_STATUS+4*i, 0);
}
}
@@ -766,7 +771,10 @@ DEFINE_PER_CPU(struct sys_device, device_mce);
} \
static SYSDEV_ATTR(name, 0644, show_ ## name, set_ ## name);
-/* TBD should generate these dynamically based on number of available banks */
+/*
+ * TBD should generate these dynamically based on number of available banks.
+ * Have only 6 contol banks in /sysfs until then.
+ */
ACCESSOR(bank0ctl,bank[0],mce_restart())
ACCESSOR(bank1ctl,bank[1],mce_restart())
ACCESSOR(bank2ctl,bank[2],mce_restart())
diff --git a/arch/x86/kernel/cpu/mcheck/p4.c b/arch/x86/kernel/cpu/mcheck/p4.c
index cb03345554a..eef001ad3bd 100644
--- a/arch/x86/kernel/cpu/mcheck/p4.c
+++ b/arch/x86/kernel/cpu/mcheck/p4.c
@@ -8,7 +8,7 @@
#include <linux/interrupt.h>
#include <linux/smp.h>
-#include <asm/processor.h>
+#include <asm/processor.h>
#include <asm/system.h>
#include <asm/msr.h>
#include <asm/apic.h>
@@ -32,12 +32,12 @@ struct intel_mce_extended_msrs {
/* u32 *reserved[]; */
};
-static int mce_num_extended_msrs = 0;
+static int mce_num_extended_msrs;
#ifdef CONFIG_X86_MCE_P4THERMAL
static void unexpected_thermal_interrupt(struct pt_regs *regs)
-{
+{
printk(KERN_ERR "CPU%d: Unexpected LVT TMR interrupt!\n",
smp_processor_id());
add_taint(TAINT_MACHINE_CHECK);
@@ -83,7 +83,7 @@ static void intel_init_thermal(struct cpuinfo_x86 *c)
* be some SMM goo which handles it, so we can't even put a handler
* since it might be delivered via SMI already -zwanem.
*/
- rdmsr (MSR_IA32_MISC_ENABLE, l, h);
+ rdmsr(MSR_IA32_MISC_ENABLE, l, h);
h = apic_read(APIC_LVTTHMR);
if ((l & (1<<3)) && (h & APIC_DM_SMI)) {
printk(KERN_DEBUG "CPU%d: Thermal monitoring handled by SMI\n",
@@ -91,7 +91,7 @@ static void intel_init_thermal(struct cpuinfo_x86 *c)
return; /* -EBUSY */
}
- /* check whether a vector already exists, temporarily masked? */
+ /* check whether a vector already exists, temporarily masked? */
if (h & APIC_VECTOR_MASK) {
printk(KERN_DEBUG "CPU%d: Thermal LVT vector (%#x) already "
"installed\n",
@@ -104,18 +104,18 @@ static void intel_init_thermal(struct cpuinfo_x86 *c)
h |= (APIC_DM_FIXED | APIC_LVT_MASKED); /* we'll mask till we're ready */
apic_write_around(APIC_LVTTHMR, h);
- rdmsr (MSR_IA32_THERM_INTERRUPT, l, h);
- wrmsr (MSR_IA32_THERM_INTERRUPT, l | 0x03 , h);
+ rdmsr(MSR_IA32_THERM_INTERRUPT, l, h);
+ wrmsr(MSR_IA32_THERM_INTERRUPT, l | 0x03 , h);
/* ok we're good to go... */
vendor_thermal_interrupt = intel_thermal_interrupt;
-
- rdmsr (MSR_IA32_MISC_ENABLE, l, h);
- wrmsr (MSR_IA32_MISC_ENABLE, l | (1<<3), h);
- l = apic_read (APIC_LVTTHMR);
- apic_write_around (APIC_LVTTHMR, l & ~APIC_LVT_MASKED);
- printk (KERN_INFO "CPU%d: Thermal monitoring enabled\n", cpu);
+ rdmsr(MSR_IA32_MISC_ENABLE, l, h);
+ wrmsr(MSR_IA32_MISC_ENABLE, l | (1<<3), h);
+
+ l = apic_read(APIC_LVTTHMR);
+ apic_write_around(APIC_LVTTHMR, l & ~APIC_LVT_MASKED);
+ printk(KERN_INFO "CPU%d: Thermal monitoring enabled\n", cpu);
/* enable thermal throttle processing */
atomic_set(&therm_throt_en, 1);
@@ -129,28 +129,28 @@ static inline void intel_get_extended_msrs(struct intel_mce_extended_msrs *r)
{
u32 h;
- rdmsr (MSR_IA32_MCG_EAX, r->eax, h);
- rdmsr (MSR_IA32_MCG_EBX, r->ebx, h);
- rdmsr (MSR_IA32_MCG_ECX, r->ecx, h);
- rdmsr (MSR_IA32_MCG_EDX, r->edx, h);
- rdmsr (MSR_IA32_MCG_ESI, r->esi, h);
- rdmsr (MSR_IA32_MCG_EDI, r->edi, h);
- rdmsr (MSR_IA32_MCG_EBP, r->ebp, h);
- rdmsr (MSR_IA32_MCG_ESP, r->esp, h);
- rdmsr (MSR_IA32_MCG_EFLAGS, r->eflags, h);
- rdmsr (MSR_IA32_MCG_EIP, r->eip, h);
+ rdmsr(MSR_IA32_MCG_EAX, r->eax, h);
+ rdmsr(MSR_IA32_MCG_EBX, r->ebx, h);
+ rdmsr(MSR_IA32_MCG_ECX, r->ecx, h);
+ rdmsr(MSR_IA32_MCG_EDX, r->edx, h);
+ rdmsr(MSR_IA32_MCG_ESI, r->esi, h);
+ rdmsr(MSR_IA32_MCG_EDI, r->edi, h);
+ rdmsr(MSR_IA32_MCG_EBP, r->ebp, h);
+ rdmsr(MSR_IA32_MCG_ESP, r->esp, h);
+ rdmsr(MSR_IA32_MCG_EFLAGS, r->eflags, h);
+ rdmsr(MSR_IA32_MCG_EIP, r->eip, h);
}
-static void intel_machine_check(struct pt_regs * regs, long error_code)
+static void intel_machine_check(struct pt_regs *regs, long error_code)
{
- int recover=1;
+ int recover = 1;
u32 alow, ahigh, high, low;
u32 mcgstl, mcgsth;
int i;
- rdmsr (MSR_IA32_MCG_STATUS, mcgstl, mcgsth);
+ rdmsr(MSR_IA32_MCG_STATUS, mcgstl, mcgsth);
if (mcgstl & (1<<0)) /* Recoverable ? */
- recover=0;
+ recover = 0;
printk(KERN_EMERG "CPU %d: Machine Check Exception: %08x%08x\n",
smp_processor_id(), mcgsth, mcgstl);
@@ -191,20 +191,20 @@ static void intel_machine_check(struct pt_regs * regs, long error_code)
}
if (recover & 2)
- panic ("CPU context corrupt");
+ panic("CPU context corrupt");
if (recover & 1)
- panic ("Unable to continue");
+ panic("Unable to continue");
printk(KERN_EMERG "Attempting to continue.\n");
- /*
- * Do not clear the MSR_IA32_MCi_STATUS if the error is not
+ /*
+ * Do not clear the MSR_IA32_MCi_STATUS if the error is not
* recoverable/continuable.This will allow BIOS to look at the MSRs
* for errors if the OS could not log the error.
*/
- for (i=0; i<nr_mce_banks; i++) {
+ for (i = 0; i < nr_mce_banks; i++) {
u32 msr;
msr = MSR_IA32_MC0_STATUS+i*4;
- rdmsr (msr, low, high);
+ rdmsr(msr, low, high);
if (high&(1<<31)) {
/* Clear it */
wrmsr(msr, 0UL, 0UL);
@@ -214,7 +214,7 @@ static void intel_machine_check(struct pt_regs * regs, long error_code)
}
}
mcgstl &= ~(1<<2);
- wrmsr (MSR_IA32_MCG_STATUS,mcgstl, mcgsth);
+ wrmsr(MSR_IA32_MCG_STATUS, mcgstl, mcgsth);
}
@@ -222,30 +222,30 @@ void intel_p4_mcheck_init(struct cpuinfo_x86 *c)
{
u32 l, h;
int i;
-
+
machine_check_vector = intel_machine_check;
wmb();
- printk (KERN_INFO "Intel machine check architecture supported.\n");
- rdmsr (MSR_IA32_MCG_CAP, l, h);
+ printk(KERN_INFO "Intel machine check architecture supported.\n");
+ rdmsr(MSR_IA32_MCG_CAP, l, h);
if (l & (1<<8)) /* Control register present ? */
- wrmsr (MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
+ wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
nr_mce_banks = l & 0xff;
- for (i=0; i<nr_mce_banks; i++) {
- wrmsr (MSR_IA32_MC0_CTL+4*i, 0xffffffff, 0xffffffff);
- wrmsr (MSR_IA32_MC0_STATUS+4*i, 0x0, 0x0);
+ for (i = 0; i < nr_mce_banks; i++) {
+ wrmsr(MSR_IA32_MC0_CTL+4*i, 0xffffffff, 0xffffffff);
+ wrmsr(MSR_IA32_MC0_STATUS+4*i, 0x0, 0x0);
}
- set_in_cr4 (X86_CR4_MCE);
- printk (KERN_INFO "Intel machine check reporting enabled on CPU#%d.\n",
+ set_in_cr4(X86_CR4_MCE);
+ printk(KERN_INFO "Intel machine check reporting enabled on CPU#%d.\n",
smp_processor_id());
/* Check for P4/Xeon extended MCE MSRs */
- rdmsr (MSR_IA32_MCG_CAP, l, h);
+ rdmsr(MSR_IA32_MCG_CAP, l, h);
if (l & (1<<9)) {/* MCG_EXT_P */
mce_num_extended_msrs = (l >> 16) & 0xff;
- printk (KERN_INFO "CPU%d: Intel P4/Xeon Extended MCE MSRs (%d)"
+ printk(KERN_INFO "CPU%d: Intel P4/Xeon Extended MCE MSRs (%d)"
" available\n",
smp_processor_id(), mce_num_extended_msrs);
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 9f51e1ea9e8..84fd9f2a28f 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -98,17 +98,6 @@ static void __init nvidia_bugs(int num, int slot, int func)
}
-static void __init ati_bugs(int num, int slot, int func)
-{
-#ifdef CONFIG_X86_IO_APIC
- if (timer_over_8254 == 1) {
- timer_over_8254 = 0;
- printk(KERN_INFO
- "ATI board detected. Disabling timer routing over 8254.\n");
- }
-#endif
-}
-
#define QFLAG_APPLY_ONCE 0x1
#define QFLAG_APPLIED 0x2
#define QFLAG_DONE (QFLAG_APPLY_ONCE|QFLAG_APPLIED)
@@ -126,8 +115,6 @@ static struct chipset early_qrk[] __initdata = {
PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, nvidia_bugs },
{ PCI_VENDOR_ID_VIA, PCI_ANY_ID,
PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, via_bugs },
- { PCI_VENDOR_ID_ATI, PCI_ANY_ID,
- PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, ati_bugs },
{ PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB,
PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, fix_hypertransport_config },
{}
diff --git a/arch/x86/kernel/efi_32.c b/arch/x86/kernel/efi_32.c
index 5d23d85624d..4b63c8e1f13 100644
--- a/arch/x86/kernel/efi_32.c
+++ b/arch/x86/kernel/efi_32.c
@@ -49,13 +49,13 @@ void efi_call_phys_prelog(void)
local_irq_save(efi_rt_eflags);
/*
- * If I don't have PSE, I should just duplicate two entries in page
- * directory. If I have PSE, I just need to duplicate one entry in
+ * If I don't have PAE, I should just duplicate two entries in page
+ * directory. If I have PAE, I just need to duplicate one entry in
* page directory.
*/
cr4 = read_cr4();
- if (cr4 & X86_CR4_PSE) {
+ if (cr4 & X86_CR4_PAE) {
efi_bak_pg_dir_pointer[0].pgd =
swapper_pg_dir[pgd_index(0)].pgd;
swapper_pg_dir[0].pgd =
@@ -93,7 +93,7 @@ void efi_call_phys_epilog(void)
cr4 = read_cr4();
- if (cr4 & X86_CR4_PSE) {
+ if (cr4 & X86_CR4_PAE) {
swapper_pg_dir[pgd_index(0)].pgd =
efi_bak_pg_dir_pointer[0].pgd;
} else {
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 556a8df522a..5cf0aa993f4 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -420,7 +420,6 @@ END(\label)
PTREGSCALL stub_clone, sys_clone, %r8
PTREGSCALL stub_fork, sys_fork, %rdi
PTREGSCALL stub_vfork, sys_vfork, %rdi
- PTREGSCALL stub_rt_sigsuspend, sys_rt_sigsuspend, %rdx
PTREGSCALL stub_sigaltstack, sys_sigaltstack, %rdx
PTREGSCALL stub_iopl, sys_iopl, %rsi
@@ -1120,10 +1119,6 @@ ENTRY(coprocessor_segment_overrun)
zeroentry do_coprocessor_segment_overrun
END(coprocessor_segment_overrun)
-ENTRY(reserved)
- zeroentry do_reserved
-END(reserved)
-
/* runs on exception stack */
ENTRY(double_fault)
XCPT_FRAME
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 10a1955bb1d..263b9d14753 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -18,6 +18,7 @@
#include <asm/page.h>
#include <asm/msr.h>
#include <asm/cache.h>
+#include <asm/processor-flags.h>
#ifdef CONFIG_PARAVIRT
#include <asm/asm-offsets.h>
@@ -128,7 +129,7 @@ ident_complete:
/* Fixup phys_base */
addq %rbp, phys_base(%rip)
-#ifdef CONFIG_SMP
+#ifdef CONFIG_X86_TRAMPOLINE
addq %rbp, trampoline_level4_pgt + 0(%rip)
addq %rbp, trampoline_level4_pgt + (511*8)(%rip)
#endif
@@ -154,9 +155,7 @@ ENTRY(secondary_startup_64)
*/
/* Enable PAE mode and PGE */
- xorq %rax, %rax
- btsq $5, %rax
- btsq $7, %rax
+ movl $(X86_CR4_PAE | X86_CR4_PGE), %eax
movq %rax, %cr4
/* Setup early boot stage 4 level pagetables. */
@@ -184,14 +183,10 @@ ENTRY(secondary_startup_64)
1: wrmsr /* Make changes effective */
/* Setup cr0 */
-#define CR0_PM 1 /* protected mode */
-#define CR0_MP (1<<1)
-#define CR0_ET (1<<4)
-#define CR0_NE (1<<5)
-#define CR0_WP (1<<16)
-#define CR0_AM (1<<18)
-#define CR0_PAGING (1<<31)
- movl $CR0_PM|CR0_MP|CR0_ET|CR0_NE|CR0_WP|CR0_AM|CR0_PAGING,%eax
+#define CR0_STATE (X86_CR0_PE | X86_CR0_MP | X86_CR0_ET | \
+ X86_CR0_NE | X86_CR0_WP | X86_CR0_AM | \
+ X86_CR0_PG)
+ movl $CR0_STATE, %eax
/* Make changes effective */
movq %rax, %cr0
@@ -327,11 +322,11 @@ early_idt_ripmsg:
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 ; \
+#define PMDS(START, PERM, COUNT) \
+ i = 0 ; \
+ .rept (COUNT) ; \
+ .quad (START) + (i << PMD_SHIFT) + (PERM) ; \
+ i = i + 1 ; \
.endr
/*
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 9b5cfcdfc42..ea230ec6905 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -17,7 +17,7 @@
/* FSEC = 10^-15
NSEC = 10^-9 */
-#define FSEC_PER_NSEC 1000000
+#define FSEC_PER_NSEC 1000000L
/*
* HPET address is set in acpi/boot.c, when an ACPI entry exists
@@ -206,20 +206,19 @@ static void hpet_enable_legacy_int(void)
static void hpet_legacy_clockevent_register(void)
{
- uint64_t hpet_freq;
-
/* Start HPET legacy interrupts */
hpet_enable_legacy_int();
/*
- * The period is a femto seconds value. We need to calculate the
- * scaled math multiplication factor for nanosecond to hpet tick
- * conversion.
+ * The mult factor is defined as (include/linux/clockchips.h)
+ * mult/2^shift = cyc/ns (in contrast to ns/cyc in clocksource.h)
+ * hpet_period is in units of femtoseconds (per cycle), so
+ * mult/2^shift = cyc/ns = 10^6/hpet_period
+ * mult = (10^6 * 2^shift)/hpet_period
+ * mult = (FSEC_PER_NSEC << hpet_clockevent.shift)/hpet_period
*/
- hpet_freq = 1000000000000000ULL;
- do_div(hpet_freq, hpet_period);
- hpet_clockevent.mult = div_sc((unsigned long) hpet_freq,
- NSEC_PER_SEC, hpet_clockevent.shift);
+ hpet_clockevent.mult = div_sc((unsigned long) FSEC_PER_NSEC,
+ hpet_period, hpet_clockevent.shift);
/* Calculate the min / max delta */
hpet_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFFFF,
&hpet_clockevent);
@@ -324,7 +323,7 @@ static struct clocksource clocksource_hpet = {
static int hpet_clocksource_register(void)
{
- u64 tmp, start, now;
+ u64 start, now;
cycle_t t1;
/* Start the counter */
@@ -351,21 +350,15 @@ static int hpet_clocksource_register(void)
return -ENODEV;
}
- /* Initialize and register HPET clocksource
- *
- * hpet period is in femto seconds per cycle
- * so we need to convert this to ns/cyc units
- * approximated by mult/2^shift
- *
- * fsec/cyc * 1nsec/1000000fsec = nsec/cyc = mult/2^shift
- * fsec/cyc * 1ns/1000000fsec * 2^shift = mult
- * fsec/cyc * 2^shift * 1nsec/1000000fsec = mult
- * (fsec/cyc << shift)/1000000 = mult
- * (hpet_period << shift)/FSEC_PER_NSEC = mult
+ /*
+ * The definition of mult is (include/linux/clocksource.h)
+ * mult/2^shift = ns/cyc and hpet_period is in units of fsec/cyc
+ * so we first need to convert hpet_period to ns/cyc units:
+ * mult/2^shift = ns/cyc = hpet_period/10^6
+ * mult = (hpet_period * 2^shift)/10^6
+ * mult = (hpet_period << shift)/FSEC_PER_NSEC
*/
- tmp = (u64)hpet_period << HPET_SHIFT;
- do_div(tmp, FSEC_PER_NSEC);
- clocksource_hpet.mult = (u32)tmp;
+ clocksource_hpet.mult = div_sc(hpet_period, FSEC_PER_NSEC, HPET_SHIFT);
clocksource_register(&clocksource_hpet);
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index eb9ddd8efb8..95e80e5033c 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -162,7 +162,7 @@ int xfpregs_get(struct task_struct *target, const struct user_regset *regset,
int ret;
if (!cpu_has_fxsr)
- return -ENODEV;
+ return -EIO;
ret = init_fpu(target);
if (ret)
@@ -179,7 +179,7 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
int ret;
if (!cpu_has_fxsr)
- return -ENODEV;
+ return -EIO;
ret = init_fpu(target);
if (ret)
diff --git a/arch/x86/kernel/i8259_32.c b/arch/x86/kernel/i8259.c
index fe631967d62..7a0fda8f01b 100644
--- a/arch/x86/kernel/i8259_32.c
+++ b/arch/x86/kernel/i8259.c
@@ -1,8 +1,10 @@
+#include <linux/linkage.h>
#include <linux/errno.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/ioport.h>
#include <linux/interrupt.h>
+#include <linux/timex.h>
#include <linux/slab.h>
#include <linux/random.h>
#include <linux/init.h>
@@ -10,10 +12,12 @@
#include <linux/sysdev.h>
#include <linux/bitops.h>
+#include <asm/acpi.h>
#include <asm/atomic.h>
#include <asm/system.h>
#include <asm/io.h>
#include <asm/timer.h>
+#include <asm/hw_irq.h>
#include <asm/pgtable.h>
#include <asm/delay.h>
#include <asm/desc.h>
@@ -32,7 +36,7 @@ static int i8259A_auto_eoi;
DEFINE_SPINLOCK(i8259A_lock);
static void mask_and_ack_8259A(unsigned int);
-static struct irq_chip i8259A_chip = {
+struct irq_chip i8259A_chip = {
.name = "XT-PIC",
.mask = disable_8259A_irq,
.disable = disable_8259A_irq,
@@ -125,14 +129,14 @@ static inline int i8259A_irq_real(unsigned int irq)
int irqmask = 1<<irq;
if (irq < 8) {
- outb(0x0B,PIC_MASTER_CMD); /* ISR register */
+ outb(0x0B, PIC_MASTER_CMD); /* ISR register */
value = inb(PIC_MASTER_CMD) & irqmask;
- outb(0x0A,PIC_MASTER_CMD); /* back to the IRR register */
+ outb(0x0A, PIC_MASTER_CMD); /* back to the IRR register */
return value;
}
- outb(0x0B,PIC_SLAVE_CMD); /* ISR register */
+ outb(0x0B, PIC_SLAVE_CMD); /* ISR register */
value = inb(PIC_SLAVE_CMD) & (irqmask >> 8);
- outb(0x0A,PIC_SLAVE_CMD); /* back to the IRR register */
+ outb(0x0A, PIC_SLAVE_CMD); /* back to the IRR register */
return value;
}
@@ -171,12 +175,14 @@ handle_real_irq:
if (irq & 8) {
inb(PIC_SLAVE_IMR); /* DUMMY - (do we need this?) */
outb(cached_slave_mask, PIC_SLAVE_IMR);
- outb(0x60+(irq&7),PIC_SLAVE_CMD);/* 'Specific EOI' to slave */
- outb(0x60+PIC_CASCADE_IR,PIC_MASTER_CMD); /* 'Specific EOI' to master-IRQ2 */
+ /* 'Specific EOI' to slave */
+ outb(0x60+(irq&7), PIC_SLAVE_CMD);
+ /* 'Specific EOI' to master-IRQ2 */
+ outb(0x60+PIC_CASCADE_IR, PIC_MASTER_CMD);
} else {
inb(PIC_MASTER_IMR); /* DUMMY - (do we need this?) */
outb(cached_master_mask, PIC_MASTER_IMR);
- outb(0x60+irq,PIC_MASTER_CMD); /* 'Specific EOI to master */
+ outb(0x60+irq, PIC_MASTER_CMD); /* 'Specific EOI to master */
}
spin_unlock_irqrestore(&i8259A_lock, flags);
return;
@@ -199,7 +205,8 @@ spurious_8259A_irq:
* lets ACK and report it. [once per IRQ]
*/
if (!(spurious_irq_mask & irqmask)) {
- printk(KERN_DEBUG "spurious 8259A interrupt: IRQ%d.\n", irq);
+ printk(KERN_DEBUG
+ "spurious 8259A interrupt: IRQ%d.\n", irq);
spurious_irq_mask |= irqmask;
}
atomic_inc(&irq_err_count);
@@ -290,17 +297,34 @@ void init_8259A(int auto_eoi)
* outb_pic - this has to work on a wide range of PC hardware.
*/
outb_pic(0x11, PIC_MASTER_CMD); /* ICW1: select 8259A-1 init */
+#ifndef CONFIG_X86_64
outb_pic(0x20 + 0, PIC_MASTER_IMR); /* ICW2: 8259A-1 IR0-7 mapped to 0x20-0x27 */
outb_pic(1U << PIC_CASCADE_IR, PIC_MASTER_IMR); /* 8259A-1 (the master) has a slave on IR2 */
+#else /* CONFIG_X86_64 */
+ /* ICW2: 8259A-1 IR0-7 mapped to 0x30-0x37 */
+ outb_pic(IRQ0_VECTOR, PIC_MASTER_IMR);
+ /* 8259A-1 (the master) has a slave on IR2 */
+ outb_pic(0x04, PIC_MASTER_IMR);
+#endif /* CONFIG_X86_64 */
if (auto_eoi) /* master does Auto EOI */
outb_pic(MASTER_ICW4_DEFAULT | PIC_ICW4_AEOI, PIC_MASTER_IMR);
else /* master expects normal EOI */
outb_pic(MASTER_ICW4_DEFAULT, PIC_MASTER_IMR);
outb_pic(0x11, PIC_SLAVE_CMD); /* ICW1: select 8259A-2 init */
+#ifndef CONFIG_X86_64
outb_pic(0x20 + 8, PIC_SLAVE_IMR); /* ICW2: 8259A-2 IR0-7 mapped to 0x28-0x2f */
outb_pic(PIC_CASCADE_IR, PIC_SLAVE_IMR); /* 8259A-2 is a slave on master's IR2 */
outb_pic(SLAVE_ICW4_DEFAULT, PIC_SLAVE_IMR); /* (slave's support for AEOI in flat mode is to be investigated) */
+#else /* CONFIG_X86_64 */
+ /* ICW2: 8259A-2 IR0-7 mapped to 0x38-0x3f */
+ outb_pic(IRQ8_VECTOR, PIC_SLAVE_IMR);
+ /* 8259A-2 is a slave on master's IR2 */
+ outb_pic(PIC_CASCADE_IR, PIC_SLAVE_IMR);
+ /* (slave's support for AEOI in flat mode is to be investigated) */
+ outb_pic(SLAVE_ICW4_DEFAULT, PIC_SLAVE_IMR);
+
+#endif /* CONFIG_X86_64 */
if (auto_eoi)
/*
* In AEOI mode we just have to mask the interrupt
@@ -317,93 +341,3 @@ void init_8259A(int auto_eoi)
spin_unlock_irqrestore(&i8259A_lock, flags);
}
-
-/*
- * Note that on a 486, we don't want to do a SIGFPE on an irq13
- * as the irq is unreliable, and exception 16 works correctly
- * (ie as explained in the intel literature). On a 386, you
- * can't use exception 16 due to bad IBM design, so we have to
- * rely on the less exact irq13.
- *
- * Careful.. Not only is IRQ13 unreliable, but it is also
- * leads to races. IBM designers who came up with it should
- * be shot.
- */
-
-
-static irqreturn_t math_error_irq(int cpl, void *dev_id)
-{
- extern void math_error(void __user *);
- outb(0,0xF0);
- if (ignore_fpu_irq || !boot_cpu_data.hard_math)
- return IRQ_NONE;
- math_error((void __user *)get_irq_regs()->ip);
- return IRQ_HANDLED;
-}
-
-/*
- * New motherboards sometimes make IRQ 13 be a PCI interrupt,
- * so allow interrupt sharing.
- */
-static struct irqaction fpu_irq = {
- .handler = math_error_irq,
- .mask = CPU_MASK_NONE,
- .name = "fpu",
-};
-
-void __init init_ISA_irqs (void)
-{
- int i;
-
-#ifdef CONFIG_X86_LOCAL_APIC
- init_bsp_APIC();
-#endif
- init_8259A(0);
-
- /*
- * 16 old-style INTA-cycle interrupts:
- */
- for (i = 0; i < 16; i++) {
- set_irq_chip_and_handler_name(i, &i8259A_chip,
- handle_level_irq, "XT");
- }
-}
-
-/* Overridden in paravirt.c */
-void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
-
-void __init native_init_IRQ(void)
-{
- int i;
-
- /* all the set up before the call gates are initialised */
- pre_intr_init_hook();
-
- /*
- * Cover the whole vector space, no vector can escape
- * us. (some of these will be overridden and become
- * 'special' SMP interrupts)
- */
- for (i = 0; i < (NR_VECTORS - FIRST_EXTERNAL_VECTOR); i++) {
- int vector = FIRST_EXTERNAL_VECTOR + i;
- if (i >= NR_IRQS)
- break;
- /* SYSCALL_VECTOR was reserved in trap_init. */
- if (!test_bit(vector, used_vectors))
- set_intr_gate(vector, interrupt[i]);
- }
-
- /* setup after call gates are initialised (usually add in
- * the architecture specific gates)
- */
- intr_init_hook();
-
- /*
- * External FPU? Set up irq13 if so, for
- * original braindamaged IBM FERR coupling.
- */
- if (boot_cpu_data.hard_math && !cpu_has_fpu)
- setup_irq(FPU_IRQ, &fpu_irq);
-
- irq_ctx_init(smp_processor_id());
-}
diff --git a/arch/x86/kernel/i8259_64.c b/arch/x86/kernel/i8259_64.c
deleted file mode 100644
index fa57a156850..00000000000
--- a/arch/x86/kernel/i8259_64.c
+++ /dev/null
@@ -1,512 +0,0 @@
-#include <linux/linkage.h>
-#include <linux/errno.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/ioport.h>
-#include <linux/interrupt.h>
-#include <linux/timex.h>
-#include <linux/slab.h>
-#include <linux/random.h>
-#include <linux/init.h>
-#include <linux/kernel_stat.h>
-#include <linux/sysdev.h>
-#include <linux/bitops.h>
-
-#include <asm/acpi.h>
-#include <asm/atomic.h>
-#include <asm/system.h>
-#include <asm/io.h>
-#include <asm/hw_irq.h>
-#include <asm/pgtable.h>
-#include <asm/delay.h>
-#include <asm/desc.h>
-#include <asm/apic.h>
-#include <asm/i8259.h>
-
-/*
- * Common place to define all x86 IRQ vectors
- *
- * This builds up the IRQ handler stubs using some ugly macros in irq.h
- *
- * These macros create the low-level assembly IRQ routines that save
- * register context and call do_IRQ(). do_IRQ() then does all the
- * operations that are needed to keep the AT (or SMP IOAPIC)
- * interrupt-controller happy.
- */
-
-#define BI(x,y) \
- BUILD_IRQ(x##y)
-
-#define BUILD_16_IRQS(x) \
- BI(x,0) BI(x,1) BI(x,2) BI(x,3) \
- BI(x,4) BI(x,5) BI(x,6) BI(x,7) \
- BI(x,8) BI(x,9) BI(x,a) BI(x,b) \
- BI(x,c) BI(x,d) BI(x,e) BI(x,f)
-
-/*
- * ISA PIC or low IO-APIC triggered (INTA-cycle or APIC) interrupts:
- * (these are usually mapped to vectors 0x30-0x3f)
- */
-
-/*
- * The IO-APIC gives us many more interrupt sources. Most of these
- * are unused but an SMP system is supposed to have enough memory ...
- * sometimes (mostly wrt. hw bugs) we get corrupted vectors all
- * across the spectrum, so we really want to be prepared to get all
- * of these. Plus, more powerful systems might have more than 64
- * IO-APIC registers.
- *
- * (these are usually mapped into the 0x30-0xff vector range)
- */
- BUILD_16_IRQS(0x2) BUILD_16_IRQS(0x3)
-BUILD_16_IRQS(0x4) BUILD_16_IRQS(0x5) BUILD_16_IRQS(0x6) BUILD_16_IRQS(0x7)
-BUILD_16_IRQS(0x8) BUILD_16_IRQS(0x9) BUILD_16_IRQS(0xa) BUILD_16_IRQS(0xb)
-BUILD_16_IRQS(0xc) BUILD_16_IRQS(0xd) BUILD_16_IRQS(0xe) BUILD_16_IRQS(0xf)
-
-#undef BUILD_16_IRQS
-#undef BI
-
-
-#define IRQ(x,y) \
- IRQ##x##y##_interrupt
-
-#define IRQLIST_16(x) \
- IRQ(x,0), IRQ(x,1), IRQ(x,2), IRQ(x,3), \
- IRQ(x,4), IRQ(x,5), IRQ(x,6), IRQ(x,7), \
- IRQ(x,8), IRQ(x,9), IRQ(x,a), IRQ(x,b), \
- IRQ(x,c), IRQ(x,d), IRQ(x,e), IRQ(x,f)
-
-/* for the irq vectors */
-static void (*__initdata interrupt[NR_VECTORS - FIRST_EXTERNAL_VECTOR])(void) = {
- IRQLIST_16(0x2), IRQLIST_16(0x3),
- IRQLIST_16(0x4), IRQLIST_16(0x5), IRQLIST_16(0x6), IRQLIST_16(0x7),
- IRQLIST_16(0x8), IRQLIST_16(0x9), IRQLIST_16(0xa), IRQLIST_16(0xb),
- IRQLIST_16(0xc), IRQLIST_16(0xd), IRQLIST_16(0xe), IRQLIST_16(0xf)
-};
-
-#undef IRQ
-#undef IRQLIST_16
-
-/*
- * This is the 'legacy' 8259A Programmable Interrupt Controller,
- * present in the majority of PC/AT boxes.
- * plus some generic x86 specific things if generic specifics makes
- * any sense at all.
- * this file should become arch/i386/kernel/irq.c when the old irq.c
- * moves to arch independent land
- */
-
-static int i8259A_auto_eoi;
-DEFINE_SPINLOCK(i8259A_lock);
-static void mask_and_ack_8259A(unsigned int);
-
-static struct irq_chip i8259A_chip = {
- .name = "XT-PIC",
- .mask = disable_8259A_irq,
- .disable = disable_8259A_irq,
- .unmask = enable_8259A_irq,
- .mask_ack = mask_and_ack_8259A,
-};
-
-/*
- * 8259A PIC functions to handle ISA devices:
- */
-
-/*
- * This contains the irq mask for both 8259A irq controllers,
- */
-unsigned int cached_irq_mask = 0xffff;
-
-/*
- * Not all IRQs can be routed through the IO-APIC, eg. on certain (older)
- * boards the timer interrupt is not really connected to any IO-APIC pin,
- * it's fed to the master 8259A's IR0 line only.
- *
- * Any '1' bit in this mask means the IRQ is routed through the IO-APIC.
- * this 'mixed mode' IRQ handling costs nothing because it's only used
- * at IRQ setup time.
- */
-unsigned long io_apic_irqs;
-
-void disable_8259A_irq(unsigned int irq)
-{
- unsigned int mask = 1 << irq;
- unsigned long flags;
-
- spin_lock_irqsave(&i8259A_lock, flags);
- cached_irq_mask |= mask;
- if (irq & 8)
- outb(cached_slave_mask, PIC_SLAVE_IMR);
- else
- outb(cached_master_mask, PIC_MASTER_IMR);
- spin_unlock_irqrestore(&i8259A_lock, flags);
-}
-
-void enable_8259A_irq(unsigned int irq)
-{
- unsigned int mask = ~(1 << irq);
- unsigned long flags;
-
- spin_lock_irqsave(&i8259A_lock, flags);
- cached_irq_mask &= mask;
- if (irq & 8)
- outb(cached_slave_mask, PIC_SLAVE_IMR);
- else
- outb(cached_master_mask, PIC_MASTER_IMR);
- spin_unlock_irqrestore(&i8259A_lock, flags);
-}
-
-int i8259A_irq_pending(unsigned int irq)
-{
- unsigned int mask = 1<<irq;
- unsigned long flags;
- int ret;
-
- spin_lock_irqsave(&i8259A_lock, flags);
- if (irq < 8)
- ret = inb(PIC_MASTER_CMD) & mask;
- else
- ret = inb(PIC_SLAVE_CMD) & (mask >> 8);
- spin_unlock_irqrestore(&i8259A_lock, flags);
-
- return ret;
-}
-
-void make_8259A_irq(unsigned int irq)
-{
- disable_irq_nosync(irq);
- io_apic_irqs &= ~(1<<irq);
- set_irq_chip_and_handler_name(irq, &i8259A_chip, handle_level_irq,
- "XT");
- enable_irq(irq);
-}
-
-/*
- * This function assumes to be called rarely. Switching between
- * 8259A registers is slow.
- * This has to be protected by the irq controller spinlock
- * before being called.
- */
-static inline int i8259A_irq_real(unsigned int irq)
-{
- int value;
- int irqmask = 1<<irq;
-
- if (irq < 8) {
- outb(0x0B,PIC_MASTER_CMD); /* ISR register */
- value = inb(PIC_MASTER_CMD) & irqmask;
- outb(0x0A,PIC_MASTER_CMD); /* back to the IRR register */
- return value;
- }
- outb(0x0B,PIC_SLAVE_CMD); /* ISR register */
- value = inb(PIC_SLAVE_CMD) & (irqmask >> 8);
- outb(0x0A,PIC_SLAVE_CMD); /* back to the IRR register */
- return value;
-}
-
-/*
- * Careful! The 8259A is a fragile beast, it pretty
- * much _has_ to be done exactly like this (mask it
- * first, _then_ send the EOI, and the order of EOI
- * to the two 8259s is important!
- */
-static void mask_and_ack_8259A(unsigned int irq)
-{
- unsigned int irqmask = 1 << irq;
- unsigned long flags;
-
- spin_lock_irqsave(&i8259A_lock, flags);
- /*
- * Lightweight spurious IRQ detection. We do not want
- * to overdo spurious IRQ handling - it's usually a sign
- * of hardware problems, so we only do the checks we can
- * do without slowing down good hardware unnecessarily.
- *
- * Note that IRQ7 and IRQ15 (the two spurious IRQs
- * usually resulting from the 8259A-1|2 PICs) occur
- * even if the IRQ is masked in the 8259A. Thus we
- * can check spurious 8259A IRQs without doing the
- * quite slow i8259A_irq_real() call for every IRQ.
- * This does not cover 100% of spurious interrupts,
- * but should be enough to warn the user that there
- * is something bad going on ...
- */
- if (cached_irq_mask & irqmask)
- goto spurious_8259A_irq;
- cached_irq_mask |= irqmask;
-
-handle_real_irq:
- if (irq & 8) {
- inb(PIC_SLAVE_IMR); /* DUMMY - (do we need this?) */
- outb(cached_slave_mask, PIC_SLAVE_IMR);
- /* 'Specific EOI' to slave */
- outb(0x60+(irq&7),PIC_SLAVE_CMD);
- /* 'Specific EOI' to master-IRQ2 */
- outb(0x60+PIC_CASCADE_IR,PIC_MASTER_CMD);
- } else {
- inb(PIC_MASTER_IMR); /* DUMMY - (do we need this?) */
- outb(cached_master_mask, PIC_MASTER_IMR);
- /* 'Specific EOI' to master */
- outb(0x60+irq,PIC_MASTER_CMD);
- }
- spin_unlock_irqrestore(&i8259A_lock, flags);
- return;
-
-spurious_8259A_irq:
- /*
- * this is the slow path - should happen rarely.
- */
- if (i8259A_irq_real(irq))
- /*
- * oops, the IRQ _is_ in service according to the
- * 8259A - not spurious, go handle it.
- */
- goto handle_real_irq;
-
- {
- static int spurious_irq_mask;
- /*
- * At this point we can be sure the IRQ is spurious,
- * lets ACK and report it. [once per IRQ]
- */
- if (!(spurious_irq_mask & irqmask)) {
- printk(KERN_DEBUG
- "spurious 8259A interrupt: IRQ%d.\n", irq);
- spurious_irq_mask |= irqmask;
- }
- atomic_inc(&irq_err_count);
- /*
- * Theoretically we do not have to handle this IRQ,
- * but in Linux this does not cause problems and is
- * simpler for us.
- */
- goto handle_real_irq;
- }
-}
-
-static char irq_trigger[2];
-/**
- * ELCR registers (0x4d0, 0x4d1) control edge/level of IRQ
- */
-static void restore_ELCR(char *trigger)
-{
- outb(trigger[0], 0x4d0);
- outb(trigger[1], 0x4d1);
-}
-
-static void save_ELCR(char *trigger)
-{
- /* IRQ 0,1,2,8,13 are marked as reserved */
- trigger[0] = inb(0x4d0) & 0xF8;
- trigger[1] = inb(0x4d1) & 0xDE;
-}
-
-static int i8259A_resume(struct sys_device *dev)
-{
- init_8259A(i8259A_auto_eoi);
- restore_ELCR(irq_trigger);
- return 0;
-}
-
-static int i8259A_suspend(struct sys_device *dev, pm_message_t state)
-{
- save_ELCR(irq_trigger);
- return 0;
-}
-
-static int i8259A_shutdown(struct sys_device *dev)
-{
- /* Put the i8259A into a quiescent state that
- * the kernel initialization code can get it
- * out of.
- */
- outb(0xff, PIC_MASTER_IMR); /* mask all of 8259A-1 */
- outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-1 */
- return 0;
-}
-
-static struct sysdev_class i8259_sysdev_class = {
- .name = "i8259",
- .suspend = i8259A_suspend,
- .resume = i8259A_resume,
- .shutdown = i8259A_shutdown,
-};
-
-static struct sys_device device_i8259A = {
- .id = 0,
- .cls = &i8259_sysdev_class,
-};
-
-static int __init i8259A_init_sysfs(void)
-{
- int error = sysdev_class_register(&i8259_sysdev_class);
- if (!error)
- error = sysdev_register(&device_i8259A);
- return error;
-}
-
-device_initcall(i8259A_init_sysfs);
-
-void init_8259A(int auto_eoi)
-{
- unsigned long flags;
-
- i8259A_auto_eoi = auto_eoi;
-
- spin_lock_irqsave(&i8259A_lock, flags);
-
- outb(0xff, PIC_MASTER_IMR); /* mask all of 8259A-1 */
- outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-2 */
-
- /*
- * outb_pic - this has to work on a wide range of PC hardware.
- */
- outb_pic(0x11, PIC_MASTER_CMD); /* ICW1: select 8259A-1 init */
- /* ICW2: 8259A-1 IR0-7 mapped to 0x30-0x37 */
- outb_pic(IRQ0_VECTOR, PIC_MASTER_IMR);
- /* 8259A-1 (the master) has a slave on IR2 */
- outb_pic(0x04, PIC_MASTER_IMR);
- if (auto_eoi) /* master does Auto EOI */
- outb_pic(MASTER_ICW4_DEFAULT | PIC_ICW4_AEOI, PIC_MASTER_IMR);
- else /* master expects normal EOI */
- outb_pic(MASTER_ICW4_DEFAULT, PIC_MASTER_IMR);
-
- outb_pic(0x11, PIC_SLAVE_CMD); /* ICW1: select 8259A-2 init */
- /* ICW2: 8259A-2 IR0-7 mapped to 0x38-0x3f */
- outb_pic(IRQ8_VECTOR, PIC_SLAVE_IMR);
- /* 8259A-2 is a slave on master's IR2 */
- outb_pic(PIC_CASCADE_IR, PIC_SLAVE_IMR);
- /* (slave's support for AEOI in flat mode is to be investigated) */
- outb_pic(SLAVE_ICW4_DEFAULT, PIC_SLAVE_IMR);
-
- if (auto_eoi)
- /*
- * In AEOI mode we just have to mask the interrupt
- * when acking.
- */
- i8259A_chip.mask_ack = disable_8259A_irq;
- else
- i8259A_chip.mask_ack = mask_and_ack_8259A;
-
- udelay(100); /* wait for 8259A to initialize */
-
- outb(cached_master_mask, PIC_MASTER_IMR); /* restore master IRQ mask */
- outb(cached_slave_mask, PIC_SLAVE_IMR); /* restore slave IRQ mask */
-
- spin_unlock_irqrestore(&i8259A_lock, flags);
-}
-
-
-
-
-/*
- * IRQ2 is cascade interrupt to second interrupt controller
- */
-
-static struct irqaction irq2 = {
- .handler = no_action,
- .mask = CPU_MASK_NONE,
- .name = "cascade",
-};
-DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
- [0 ... IRQ0_VECTOR - 1] = -1,
- [IRQ0_VECTOR] = 0,
- [IRQ1_VECTOR] = 1,
- [IRQ2_VECTOR] = 2,
- [IRQ3_VECTOR] = 3,
- [IRQ4_VECTOR] = 4,
- [IRQ5_VECTOR] = 5,
- [IRQ6_VECTOR] = 6,
- [IRQ7_VECTOR] = 7,
- [IRQ8_VECTOR] = 8,
- [IRQ9_VECTOR] = 9,
- [IRQ10_VECTOR] = 10,
- [IRQ11_VECTOR] = 11,
- [IRQ12_VECTOR] = 12,
- [IRQ13_VECTOR] = 13,
- [IRQ14_VECTOR] = 14,
- [IRQ15_VECTOR] = 15,
- [IRQ15_VECTOR + 1 ... NR_VECTORS - 1] = -1
-};
-
-void __init init_ISA_irqs (void)
-{
- int i;
-
- init_bsp_APIC();
- init_8259A(0);
-
- for (i = 0; i < NR_IRQS; i++) {
- irq_desc[i].status = IRQ_DISABLED;
- irq_desc[i].action = NULL;
- irq_desc[i].depth = 1;
-
- if (i < 16) {
- /*
- * 16 old-style INTA-cycle interrupts:
- */
- set_irq_chip_and_handler_name(i, &i8259A_chip,
- handle_level_irq, "XT");
- } else {
- /*
- * 'high' PCI IRQs filled in on demand
- */
- irq_desc[i].chip = &no_irq_chip;
- }
- }
-}
-
-void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
-
-void __init native_init_IRQ(void)
-{
- int i;
-
- init_ISA_irqs();
- /*
- * Cover the whole vector space, no vector can escape
- * us. (some of these will be overridden and become
- * 'special' SMP interrupts)
- */
- for (i = 0; i < (NR_VECTORS - FIRST_EXTERNAL_VECTOR); i++) {
- int vector = FIRST_EXTERNAL_VECTOR + i;
- if (vector != IA32_SYSCALL_VECTOR)
- set_intr_gate(vector, interrupt[i]);
- }
-
-#ifdef CONFIG_SMP
- /*
- * The reschedule interrupt is a CPU-to-CPU reschedule-helper
- * IPI, driven by wakeup.
- */
- set_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
-
- /* IPIs for invalidation */
- set_intr_gate(INVALIDATE_TLB_VECTOR_START+0, invalidate_interrupt0);
- set_intr_gate(INVALIDATE_TLB_VECTOR_START+1, invalidate_interrupt1);
- set_intr_gate(INVALIDATE_TLB_VECTOR_START+2, invalidate_interrupt2);
- set_intr_gate(INVALIDATE_TLB_VECTOR_START+3, invalidate_interrupt3);
- set_intr_gate(INVALIDATE_TLB_VECTOR_START+4, invalidate_interrupt4);
- set_intr_gate(INVALIDATE_TLB_VECTOR_START+5, invalidate_interrupt5);
- set_intr_gate(INVALIDATE_TLB_VECTOR_START+6, invalidate_interrupt6);
- set_intr_gate(INVALIDATE_TLB_VECTOR_START+7, invalidate_interrupt7);
-
- /* IPI for generic function call */
- set_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
-
- /* Low priority IPI to cleanup after moving an irq */
- set_intr_gate(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt);
-#endif
- set_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
- set_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt);
-
- /* self generated IPI for local APIC timer */
- set_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
-
- /* IPI vectors for APIC spurious and error interrupts */
- set_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
- set_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
-
- if (!acpi_ioapic)
- setup_irq(2, &irq2);
-}
diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index 4dc8600d9d2..d4f9df2b022 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -58,7 +58,7 @@ static struct { int pin, apic; } ioapic_i8259 = { -1, -1 };
static DEFINE_SPINLOCK(ioapic_lock);
static DEFINE_SPINLOCK(vector_lock);
-int timer_over_8254 __initdata = 1;
+int timer_through_8259 __initdata;
/*
* Is the SiS APIC rmw bug present ?
@@ -239,7 +239,7 @@ static void __init replace_pin_at_irq(unsigned int irq,
}
}
-static void __modify_IO_APIC_irq (unsigned int irq, unsigned long enable, unsigned long disable)
+static void __modify_IO_APIC_irq(unsigned int irq, unsigned long enable, unsigned long disable)
{
struct irq_pin_list *entry = irq_2_pin + irq;
unsigned int pin, reg;
@@ -259,30 +259,32 @@ static void __modify_IO_APIC_irq (unsigned int irq, unsigned long enable, unsign
}
/* mask = 1 */
-static void __mask_IO_APIC_irq (unsigned int irq)
+static void __mask_IO_APIC_irq(unsigned int irq)
{
- __modify_IO_APIC_irq(irq, 0x00010000, 0);
+ __modify_IO_APIC_irq(irq, IO_APIC_REDIR_MASKED, 0);
}
/* mask = 0 */
-static void __unmask_IO_APIC_irq (unsigned int irq)
+static void __unmask_IO_APIC_irq(unsigned int irq)
{
- __modify_IO_APIC_irq(irq, 0, 0x00010000);
+ __modify_IO_APIC_irq(irq, 0, IO_APIC_REDIR_MASKED);
}
/* mask = 1, trigger = 0 */
-static void __mask_and_edge_IO_APIC_irq (unsigned int irq)
+static void __mask_and_edge_IO_APIC_irq(unsigned int irq)
{
- __modify_IO_APIC_irq(irq, 0x00010000, 0x00008000);
+ __modify_IO_APIC_irq(irq, IO_APIC_REDIR_MASKED,
+ IO_APIC_REDIR_LEVEL_TRIGGER);
}
/* mask = 0, trigger = 1 */
-static void __unmask_and_level_IO_APIC_irq (unsigned int irq)
+static void __unmask_and_level_IO_APIC_irq(unsigned int irq)
{
- __modify_IO_APIC_irq(irq, 0x00008000, 0x00010000);
+ __modify_IO_APIC_irq(irq, IO_APIC_REDIR_LEVEL_TRIGGER,
+ IO_APIC_REDIR_MASKED);
}
-static void mask_IO_APIC_irq (unsigned int irq)
+static void mask_IO_APIC_irq(unsigned int irq)
{
unsigned long flags;
@@ -291,7 +293,7 @@ static void mask_IO_APIC_irq (unsigned int irq)
spin_unlock_irqrestore(&ioapic_lock, flags);
}
-static void unmask_IO_APIC_irq (unsigned int irq)
+static void unmask_IO_APIC_irq(unsigned int irq)
{
unsigned long flags;
@@ -303,7 +305,7 @@ static void unmask_IO_APIC_irq (unsigned int irq)
static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin)
{
struct IO_APIC_route_entry entry;
-
+
/* Check delivery_mode to be sure we're not clearing an SMI pin */
entry = ioapic_read_entry(apic, pin);
if (entry.delivery_mode == dest_SMI)
@@ -315,7 +317,7 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin)
ioapic_mask_entry(apic, pin);
}
-static void clear_IO_APIC (void)
+static void clear_IO_APIC(void)
{
int apic, pin;
@@ -332,7 +334,7 @@ static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t cpumask)
struct irq_pin_list *entry = irq_2_pin + irq;
unsigned int apicid_value;
cpumask_t tmp;
-
+
cpus_and(tmp, cpumask, cpu_online_map);
if (cpus_empty(tmp))
tmp = TARGET_CPUS;
@@ -361,7 +363,7 @@ static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t cpumask)
# include <linux/kernel_stat.h> /* kstat */
# include <linux/slab.h> /* kmalloc() */
# include <linux/timer.h>
-
+
#define IRQBALANCE_CHECK_ARCH -999
#define MAX_BALANCED_IRQ_INTERVAL (5*HZ)
#define MIN_BALANCED_IRQ_INTERVAL (HZ/2)
@@ -373,14 +375,14 @@ static int physical_balance __read_mostly;
static long balanced_irq_interval __read_mostly = MAX_BALANCED_IRQ_INTERVAL;
static struct irq_cpu_info {
- unsigned long * last_irq;
- unsigned long * irq_delta;
+ unsigned long *last_irq;
+ unsigned long *irq_delta;
unsigned long irq;
} irq_cpu_data[NR_CPUS];
#define CPU_IRQ(cpu) (irq_cpu_data[cpu].irq)
-#define LAST_CPU_IRQ(cpu,irq) (irq_cpu_data[cpu].last_irq[irq])
-#define IRQ_DELTA(cpu,irq) (irq_cpu_data[cpu].irq_delta[irq])
+#define LAST_CPU_IRQ(cpu, irq) (irq_cpu_data[cpu].last_irq[irq])
+#define IRQ_DELTA(cpu, irq) (irq_cpu_data[cpu].irq_delta[irq])
#define IDLE_ENOUGH(cpu,now) \
(idle_cpu(cpu) && ((now) - per_cpu(irq_stat, (cpu)).idle_timestamp > 1))
@@ -419,8 +421,8 @@ inside:
if (cpu == -1)
cpu = NR_CPUS-1;
}
- } while (!cpu_online(cpu) || !IRQ_ALLOWED(cpu,allowed_mask) ||
- (search_idle && !IDLE_ENOUGH(cpu,now)));
+ } while (!cpu_online(cpu) || !IRQ_ALLOWED(cpu, allowed_mask) ||
+ (search_idle && !IDLE_ENOUGH(cpu, now)));
return cpu;
}
@@ -430,15 +432,14 @@ static inline void balance_irq(int cpu, int irq)
unsigned long now = jiffies;
cpumask_t allowed_mask;
unsigned int new_cpu;
-
+
if (irqbalance_disabled)
- return;
+ return;
cpus_and(allowed_mask, cpu_online_map, balance_irq_affinity[irq]);
new_cpu = move(cpu, allowed_mask, now, 1);
- if (cpu != new_cpu) {
+ if (cpu != new_cpu)
set_pending_irq(irq, cpumask_of_cpu(new_cpu));
- }
}
static inline void rotate_irqs_among_cpus(unsigned long useful_load_threshold)
@@ -450,14 +451,14 @@ static inline void rotate_irqs_among_cpus(unsigned long useful_load_threshold)
if (!irq_desc[j].action)
continue;
/* Is it a significant load ? */
- if (IRQ_DELTA(CPU_TO_PACKAGEINDEX(i),j) <
+ if (IRQ_DELTA(CPU_TO_PACKAGEINDEX(i), j) <
useful_load_threshold)
continue;
balance_irq(i, j);
}
}
balanced_irq_interval = max((long)MIN_BALANCED_IRQ_INTERVAL,
- balanced_irq_interval - BALANCED_IRQ_LESS_DELTA);
+ balanced_irq_interval - BALANCED_IRQ_LESS_DELTA);
return;
}
@@ -486,22 +487,22 @@ static void do_irq_balance(void)
/* Is this an active IRQ or balancing disabled ? */
if (!irq_desc[j].action || irq_balancing_disabled(j))
continue;
- if ( package_index == i )
- IRQ_DELTA(package_index,j) = 0;
+ if (package_index == i)
+ IRQ_DELTA(package_index, j) = 0;
/* Determine the total count per processor per IRQ */
value_now = (unsigned long) kstat_cpu(i).irqs[j];
/* Determine the activity per processor per IRQ */
- delta = value_now - LAST_CPU_IRQ(i,j);
+ delta = value_now - LAST_CPU_IRQ(i, j);
/* Update last_cpu_irq[][] for the next time */
- LAST_CPU_IRQ(i,j) = value_now;
+ LAST_CPU_IRQ(i, j) = value_now;
/* Ignore IRQs whose rate is less than the clock */
if (delta < useful_load_threshold)
continue;
/* update the load for the processor or package total */
- IRQ_DELTA(package_index,j) += delta;
+ IRQ_DELTA(package_index, j) += delta;
/* Keep track of the higher numbered sibling as well */
if (i != package_index)
@@ -527,7 +528,8 @@ static void do_irq_balance(void)
max_cpu_irq = ULONG_MAX;
tryanothercpu:
- /* Look for heaviest loaded processor.
+ /*
+ * Look for heaviest loaded processor.
* We may come back to get the next heaviest loaded processor.
* Skip processors with trivial loads.
*/
@@ -536,7 +538,7 @@ tryanothercpu:
for_each_online_cpu(i) {
if (i != CPU_TO_PACKAGEINDEX(i))
continue;
- if (max_cpu_irq <= CPU_IRQ(i))
+ if (max_cpu_irq <= CPU_IRQ(i))
continue;
if (tmp_cpu_irq < CPU_IRQ(i)) {
tmp_cpu_irq = CPU_IRQ(i);
@@ -545,8 +547,9 @@ tryanothercpu:
}
if (tmp_loaded == -1) {
- /* In the case of small number of heavy interrupt sources,
- * loading some of the cpus too much. We use Ingo's original
+ /*
+ * In the case of small number of heavy interrupt sources,
+ * loading some of the cpus too much. We use Ingo's original
* approach to rotate them around.
*/
if (!first_attempt && imbalance >= useful_load_threshold) {
@@ -555,13 +558,14 @@ tryanothercpu:
}
goto not_worth_the_effort;
}
-
+
first_attempt = 0; /* heaviest search */
max_cpu_irq = tmp_cpu_irq; /* load */
max_loaded = tmp_loaded; /* processor */
imbalance = (max_cpu_irq - min_cpu_irq) / 2;
-
- /* if imbalance is less than approx 10% of max load, then
+
+ /*
+ * if imbalance is less than approx 10% of max load, then
* observe diminishing returns action. - quit
*/
if (imbalance < (max_cpu_irq >> 3))
@@ -577,26 +581,25 @@ tryanotherirq:
/* Is this an active IRQ? */
if (!irq_desc[j].action)
continue;
- if (imbalance <= IRQ_DELTA(max_loaded,j))
+ if (imbalance <= IRQ_DELTA(max_loaded, j))
continue;
/* Try to find the IRQ that is closest to the imbalance
* without going over.
*/
- if (move_this_load < IRQ_DELTA(max_loaded,j)) {
- move_this_load = IRQ_DELTA(max_loaded,j);
+ if (move_this_load < IRQ_DELTA(max_loaded, j)) {
+ move_this_load = IRQ_DELTA(max_loaded, j);
selected_irq = j;
}
}
- if (selected_irq == -1) {
+ if (selected_irq == -1)
goto tryanothercpu;
- }
imbalance = move_this_load;
-
+
/* For physical_balance case, we accumulated both load
* values in the one of the siblings cpu_irq[],
* to use the same code for physical and logical processors
- * as much as possible.
+ * as much as possible.
*
* NOTE: the cpu_irq[] array holds the sum of the load for
* sibling A and sibling B in the slot for the lowest numbered
@@ -625,11 +628,11 @@ tryanotherirq:
/* mark for change destination */
set_pending_irq(selected_irq, cpumask_of_cpu(min_loaded));
- /* Since we made a change, come back sooner to
+ /* Since we made a change, come back sooner to
* check for more variation.
*/
balanced_irq_interval = max((long)MIN_BALANCED_IRQ_INTERVAL,
- balanced_irq_interval - BALANCED_IRQ_LESS_DELTA);
+ balanced_irq_interval - BALANCED_IRQ_LESS_DELTA);
return;
}
goto tryanotherirq;
@@ -640,7 +643,7 @@ not_worth_the_effort:
* upward
*/
balanced_irq_interval = min((long)MAX_BALANCED_IRQ_INTERVAL,
- balanced_irq_interval + BALANCED_IRQ_MORE_DELTA);
+ balanced_irq_interval + BALANCED_IRQ_MORE_DELTA);
return;
}
@@ -679,13 +682,13 @@ static int __init balanced_irq_init(void)
cpumask_t tmp;
cpus_shift_right(tmp, cpu_online_map, 2);
- c = &boot_cpu_data;
+ c = &boot_cpu_data;
/* When not overwritten by the command line ask subarchitecture. */
if (irqbalance_disabled == IRQBALANCE_CHECK_ARCH)
irqbalance_disabled = NO_BALANCE_IRQ;
if (irqbalance_disabled)
return 0;
-
+
/* disable irqbalance completely if there is only one processor online */
if (num_online_cpus() < 2) {
irqbalance_disabled = 1;
@@ -699,16 +702,14 @@ static int __init balanced_irq_init(void)
physical_balance = 1;
for_each_online_cpu(i) {
- irq_cpu_data[i].irq_delta = kmalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL);
- irq_cpu_data[i].last_irq = kmalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL);
+ irq_cpu_data[i].irq_delta = kzalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL);
+ irq_cpu_data[i].last_irq = kzalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL);
if (irq_cpu_data[i].irq_delta == NULL || irq_cpu_data[i].last_irq == NULL) {
printk(KERN_ERR "balanced_irq_init: out of memory");
goto failed;
}
- memset(irq_cpu_data[i].irq_delta,0,sizeof(unsigned long) * NR_IRQS);
- memset(irq_cpu_data[i].last_irq,0,sizeof(unsigned long) * NR_IRQS);
}
-
+
printk(KERN_INFO "Starting balanced_irq\n");
if (!IS_ERR(kthread_run(balanced_irq, NULL, "kirqd")))
return 0;
@@ -843,7 +844,7 @@ static int __init find_isa_irq_apic(int irq, int type)
}
if (i < mp_irq_entries) {
int apic;
- for(apic = 0; apic < nr_ioapics; apic++) {
+ for (apic = 0; apic < nr_ioapics; apic++) {
if (mp_ioapics[apic].mpc_apicid == mp_irqs[i].mpc_dstapic)
return apic;
}
@@ -880,7 +881,7 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin)
!mp_irqs[i].mpc_irqtype &&
(bus == lbus) &&
(slot == ((mp_irqs[i].mpc_srcbusirq >> 2) & 0x1f))) {
- int irq = pin_2_irq(i,apic,mp_irqs[i].mpc_dstirq);
+ int irq = pin_2_irq(i, apic, mp_irqs[i].mpc_dstirq);
if (!(apic || IO_APIC_IRQ(irq)))
continue;
@@ -900,7 +901,7 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin)
EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector);
/*
- * This function currently is only a helper for the i386 smp boot process where
+ * This function currently is only a helper for the i386 smp boot process where
* we need to reprogram the ioredtbls to cater for the cpus which have come online
* so mask in all cases should simply be TARGET_CPUS
*/
@@ -975,37 +976,36 @@ static int MPBIOS_polarity(int idx)
/*
* Determine IRQ line polarity (high active or low active):
*/
- switch (mp_irqs[idx].mpc_irqflag & 3)
+ switch (mp_irqs[idx].mpc_irqflag & 3) {
+ case 0: /* conforms, ie. bus-type dependent polarity */
{
- case 0: /* conforms, ie. bus-type dependent polarity */
- {
- polarity = test_bit(bus, mp_bus_not_pci)?
- default_ISA_polarity(idx):
- default_PCI_polarity(idx);
- break;
- }
- case 1: /* high active */
- {
- polarity = 0;
- break;
- }
- case 2: /* reserved */
- {
- printk(KERN_WARNING "broken BIOS!!\n");
- polarity = 1;
- break;
- }
- case 3: /* low active */
- {
- polarity = 1;
- break;
- }
- default: /* invalid */
- {
- printk(KERN_WARNING "broken BIOS!!\n");
- polarity = 1;
- break;
- }
+ polarity = test_bit(bus, mp_bus_not_pci)?
+ default_ISA_polarity(idx):
+ default_PCI_polarity(idx);
+ break;
+ }
+ case 1: /* high active */
+ {
+ polarity = 0;
+ break;
+ }
+ case 2: /* reserved */
+ {
+ printk(KERN_WARNING "broken BIOS!!\n");
+ polarity = 1;
+ break;
+ }
+ case 3: /* low active */
+ {
+ polarity = 1;
+ break;
+ }
+ default: /* invalid */
+ {
+ printk(KERN_WARNING "broken BIOS!!\n");
+ polarity = 1;
+ break;
+ }
}
return polarity;
}
@@ -1018,69 +1018,67 @@ static int MPBIOS_trigger(int idx)
/*
* Determine IRQ trigger mode (edge or level sensitive):
*/
- switch ((mp_irqs[idx].mpc_irqflag>>2) & 3)
+ switch ((mp_irqs[idx].mpc_irqflag>>2) & 3) {
+ case 0: /* conforms, ie. bus-type dependent */
{
- case 0: /* conforms, ie. bus-type dependent */
- {
- trigger = test_bit(bus, mp_bus_not_pci)?
- default_ISA_trigger(idx):
- default_PCI_trigger(idx);
+ trigger = test_bit(bus, mp_bus_not_pci)?
+ default_ISA_trigger(idx):
+ default_PCI_trigger(idx);
#if defined(CONFIG_EISA) || defined(CONFIG_MCA)
- switch (mp_bus_id_to_type[bus])
- {
- case MP_BUS_ISA: /* ISA pin */
- {
- /* set before the switch */
- break;
- }
- case MP_BUS_EISA: /* EISA pin */
- {
- trigger = default_EISA_trigger(idx);
- break;
- }
- case MP_BUS_PCI: /* PCI pin */
- {
- /* set before the switch */
- break;
- }
- case MP_BUS_MCA: /* MCA pin */
- {
- trigger = default_MCA_trigger(idx);
- break;
- }
- default:
- {
- printk(KERN_WARNING "broken BIOS!!\n");
- trigger = 1;
- break;
- }
- }
-#endif
+ switch (mp_bus_id_to_type[bus]) {
+ case MP_BUS_ISA: /* ISA pin */
+ {
+ /* set before the switch */
break;
}
- case 1: /* edge */
+ case MP_BUS_EISA: /* EISA pin */
{
- trigger = 0;
+ trigger = default_EISA_trigger(idx);
break;
}
- case 2: /* reserved */
+ case MP_BUS_PCI: /* PCI pin */
{
- printk(KERN_WARNING "broken BIOS!!\n");
- trigger = 1;
+ /* set before the switch */
break;
}
- case 3: /* level */
+ case MP_BUS_MCA: /* MCA pin */
{
- trigger = 1;
+ trigger = default_MCA_trigger(idx);
break;
}
- default: /* invalid */
+ default:
{
printk(KERN_WARNING "broken BIOS!!\n");
- trigger = 0;
+ trigger = 1;
break;
}
}
+#endif
+ break;
+ }
+ case 1: /* edge */
+ {
+ trigger = 0;
+ break;
+ }
+ case 2: /* reserved */
+ {
+ printk(KERN_WARNING "broken BIOS!!\n");
+ trigger = 1;
+ break;
+ }
+ case 3: /* level */
+ {
+ trigger = 1;
+ break;
+ }
+ default: /* invalid */
+ {
+ printk(KERN_WARNING "broken BIOS!!\n");
+ trigger = 0;
+ break;
+ }
+ }
return trigger;
}
@@ -1148,8 +1146,8 @@ static inline int IO_APIC_irq_trigger(int irq)
for (apic = 0; apic < nr_ioapics; apic++) {
for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) {
- idx = find_irq_entry(apic,pin,mp_INT);
- if ((idx != -1) && (irq == pin_2_irq(idx,apic,pin)))
+ idx = find_irq_entry(apic, pin, mp_INT);
+ if ((idx != -1) && (irq == pin_2_irq(idx, apic, pin)))
return irq_trigger(idx);
}
}
@@ -1164,7 +1162,7 @@ static u8 irq_vector[NR_IRQ_VECTORS] __read_mostly = { FIRST_DEVICE_VECTOR , 0 }
static int __assign_irq_vector(int irq)
{
- static int current_vector = FIRST_DEVICE_VECTOR, current_offset = 0;
+ static int current_vector = FIRST_DEVICE_VECTOR, current_offset;
int vector, offset;
BUG_ON((unsigned)irq >= NR_IRQ_VECTORS);
@@ -1237,15 +1235,15 @@ static void __init setup_IO_APIC_irqs(void)
/*
* add it to the IO-APIC irq-routing table:
*/
- memset(&entry,0,sizeof(entry));
+ memset(&entry, 0, sizeof(entry));
entry.delivery_mode = INT_DELIVERY_MODE;
entry.dest_mode = INT_DEST_MODE;
entry.mask = 0; /* enable IRQ */
- entry.dest.logical.logical_dest =
+ entry.dest.logical.logical_dest =
cpu_mask_to_apicid(TARGET_CPUS);
- idx = find_irq_entry(apic,pin,mp_INT);
+ idx = find_irq_entry(apic, pin, mp_INT);
if (idx == -1) {
if (first_notcon) {
apic_printk(APIC_VERBOSE, KERN_DEBUG
@@ -1289,7 +1287,7 @@ static void __init setup_IO_APIC_irqs(void)
vector = assign_irq_vector(irq);
entry.vector = vector;
ioapic_register_intr(irq, vector, IOAPIC_AUTO);
-
+
if (!apic && (irq < 16))
disable_8259A_irq(irq);
}
@@ -1302,25 +1300,21 @@ static void __init setup_IO_APIC_irqs(void)
}
/*
- * Set up the 8259A-master output pin:
+ * Set up the timer pin, possibly with the 8259A-master behind.
*/
-static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, int vector)
+static void __init setup_timer_IRQ0_pin(unsigned int apic, unsigned int pin,
+ int vector)
{
struct IO_APIC_route_entry entry;
- memset(&entry,0,sizeof(entry));
-
- disable_8259A_irq(0);
-
- /* mask LVT0 */
- apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
+ memset(&entry, 0, sizeof(entry));
/*
* We use logical delivery to get the timer IRQ
* to the first CPU.
*/
entry.dest_mode = INT_DEST_MODE;
- entry.mask = 0; /* unmask IRQ now */
+ entry.mask = 1; /* mask IRQ now */
entry.dest.logical.logical_dest = cpu_mask_to_apicid(TARGET_CPUS);
entry.delivery_mode = INT_DELIVERY_MODE;
entry.polarity = 0;
@@ -1329,17 +1323,14 @@ static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, in
/*
* The timer IRQ doesn't have to know that behind the
- * scene we have a 8259A-master in AEOI mode ...
+ * scene we may have a 8259A-master in AEOI mode ...
*/
- irq_desc[0].chip = &ioapic_chip;
- set_irq_handler(0, handle_edge_irq);
+ ioapic_register_intr(0, vector, IOAPIC_EDGE);
/*
* Add it to the IO-APIC irq-routing table:
*/
ioapic_write_entry(apic, pin, entry);
-
- enable_8259A_irq(0);
}
void __init print_IO_APIC(void)
@@ -1354,7 +1345,7 @@ void __init print_IO_APIC(void)
if (apic_verbosity == APIC_QUIET)
return;
- printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
+ printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
for (i = 0; i < nr_ioapics; i++)
printk(KERN_DEBUG "number of IO-APIC #%d registers: %d.\n",
mp_ioapics[i].mpc_apicid, nr_ioapic_registers[i]);
@@ -1459,7 +1450,7 @@ void __init print_IO_APIC(void)
#if 0
-static void print_APIC_bitfield (int base)
+static void print_APIC_bitfield(int base)
{
unsigned int v;
int i, j;
@@ -1480,7 +1471,7 @@ static void print_APIC_bitfield (int base)
}
}
-void /*__init*/ print_local_APIC(void * dummy)
+void /*__init*/ print_local_APIC(void *dummy)
{
unsigned int v, ver, maxlvt;
@@ -1489,6 +1480,7 @@ void /*__init*/ print_local_APIC(void * dummy)
printk("\n" KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n",
smp_processor_id(), hard_smp_processor_id());
+ v = apic_read(APIC_ID);
printk(KERN_INFO "... APIC ID: %08x (%01x)\n", v,
GET_APIC_ID(read_apic_id()));
v = apic_read(APIC_LVR);
@@ -1563,7 +1555,7 @@ void /*__init*/ print_local_APIC(void * dummy)
printk("\n");
}
-void print_all_local_APICs (void)
+void print_all_local_APICs(void)
{
on_each_cpu(print_local_APIC, NULL, 1, 1);
}
@@ -1586,11 +1578,11 @@ void /*__init*/ print_PIC(void)
v = inb(0xa0) << 8 | inb(0x20);
printk(KERN_DEBUG "... PIC IRR: %04x\n", v);
- outb(0x0b,0xa0);
- outb(0x0b,0x20);
+ outb(0x0b, 0xa0);
+ outb(0x0b, 0x20);
v = inb(0xa0) << 8 | inb(0x20);
- outb(0x0a,0xa0);
- outb(0x0a,0x20);
+ outb(0x0a, 0xa0);
+ outb(0x0a, 0x20);
spin_unlock_irqrestore(&i8259A_lock, flags);
@@ -1626,7 +1618,7 @@ static void __init enable_IO_APIC(void)
spin_unlock_irqrestore(&ioapic_lock, flags);
nr_ioapic_registers[apic] = reg_01.bits.entries+1;
}
- for(apic = 0; apic < nr_ioapics; apic++) {
+ for (apic = 0; apic < nr_ioapics; apic++) {
int pin;
/* See if any of the pins is in ExtINT mode */
for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) {
@@ -1748,7 +1740,7 @@ static void __init setup_ioapic_ids_from_mpc(void)
spin_lock_irqsave(&ioapic_lock, flags);
reg_00.raw = io_apic_read(apic, 0);
spin_unlock_irqrestore(&ioapic_lock, flags);
-
+
old_id = mp_ioapics[apic].mpc_apicid;
if (mp_ioapics[apic].mpc_apicid >= get_physical_broadcast()) {
@@ -1800,7 +1792,7 @@ static void __init setup_ioapic_ids_from_mpc(void)
/*
* Read the right value from the MPC table and
* write it into the ID register.
- */
+ */
apic_printk(APIC_VERBOSE, KERN_INFO
"...changing IO-APIC physical APIC ID to %d ...",
mp_ioapics[apic].mpc_apicid);
@@ -2020,7 +2012,7 @@ static void ack_apic(unsigned int irq)
ack_APIC_irq();
}
-static void mask_lapic_irq (unsigned int irq)
+static void mask_lapic_irq(unsigned int irq)
{
unsigned long v;
@@ -2028,7 +2020,7 @@ static void mask_lapic_irq (unsigned int irq)
apic_write_around(APIC_LVT0, v | APIC_LVT_MASKED);
}
-static void unmask_lapic_irq (unsigned int irq)
+static void unmask_lapic_irq(unsigned int irq)
{
unsigned long v;
@@ -2037,7 +2029,7 @@ static void unmask_lapic_irq (unsigned int irq)
}
static struct irq_chip lapic_chip __read_mostly = {
- .name = "local-APIC-edge",
+ .name = "local-APIC",
.mask = mask_lapic_irq,
.unmask = unmask_lapic_irq,
.eoi = ack_apic,
@@ -2046,14 +2038,14 @@ static struct irq_chip lapic_chip __read_mostly = {
static void __init setup_nmi(void)
{
/*
- * Dirty trick to enable the NMI watchdog ...
+ * Dirty trick to enable the NMI watchdog ...
* We put the 8259A master into AEOI mode and
* unmask on all local APICs LVT0 as NMI.
*
* The idea to use the 8259A in AEOI mode ('8259A Virtual Wire')
* is from Maciej W. Rozycki - so we do not have to EOI from
* the NMI handler or the timer interrupt.
- */
+ */
apic_printk(APIC_VERBOSE, KERN_INFO "activating NMI Watchdog ...");
enable_NMI_through_LVT0();
@@ -2129,11 +2121,16 @@ static inline void __init unlock_ExtINT_logic(void)
static inline void __init check_timer(void)
{
int apic1, pin1, apic2, pin2;
+ int no_pin1 = 0;
int vector;
+ unsigned int ver;
unsigned long flags;
local_irq_save(flags);
+ ver = apic_read(APIC_LVR);
+ ver = GET_APIC_VERSION(ver);
+
/*
* get/set the timer IRQ vector:
*/
@@ -2142,17 +2139,17 @@ static inline void __init check_timer(void)
set_intr_gate(vector, interrupt[0]);
/*
- * Subtle, code in do_timer_interrupt() expects an AEOI
- * mode for the 8259A whenever interrupts are routed
- * through I/O APICs. Also IRQ0 has to be enabled in
- * the 8259A which implies the virtual wire has to be
- * disabled in the local APIC.
+ * As IRQ0 is to be enabled in the 8259A, the virtual
+ * wire has to be disabled in the local APIC. Also
+ * timer interrupts need to be acknowledged manually in
+ * the 8259A for the i82489DX when using the NMI
+ * watchdog as that APIC treats NMIs as level-triggered.
+ * The AEOI mode will finish them in the 8259A
+ * automatically.
*/
apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
init_8259A(1);
- timer_ack = 1;
- if (timer_over_8254 > 0)
- enable_8259A_irq(0);
+ timer_ack = (nmi_watchdog == NMI_IO_APIC && !APIC_INTEGRATED(ver));
pin1 = find_isa_irq_pin(0, mp_INT);
apic1 = find_isa_irq_apic(0, mp_INT);
@@ -2162,14 +2159,33 @@ static inline void __init check_timer(void)
printk(KERN_INFO "..TIMER: vector=0x%02X apic1=%d pin1=%d apic2=%d pin2=%d\n",
vector, apic1, pin1, apic2, pin2);
+ /*
+ * Some BIOS writers are clueless and report the ExtINTA
+ * I/O APIC input from the cascaded 8259A as the timer
+ * interrupt input. So just in case, if only one pin
+ * was found above, try it both directly and through the
+ * 8259A.
+ */
+ if (pin1 == -1) {
+ pin1 = pin2;
+ apic1 = apic2;
+ no_pin1 = 1;
+ } else if (pin2 == -1) {
+ pin2 = pin1;
+ apic2 = apic1;
+ }
+
if (pin1 != -1) {
/*
* Ok, does IRQ0 through the IOAPIC work?
*/
+ if (no_pin1) {
+ add_pin_to_irq(0, apic1, pin1);
+ setup_timer_IRQ0_pin(apic1, pin1, vector);
+ }
unmask_IO_APIC_irq(0);
if (timer_irq_works()) {
if (nmi_watchdog == NMI_IO_APIC) {
- disable_8259A_irq(0);
setup_nmi();
enable_8259A_irq(0);
}
@@ -2178,43 +2194,46 @@ static inline void __init check_timer(void)
goto out;
}
clear_IO_APIC_pin(apic1, pin1);
- printk(KERN_ERR "..MP-BIOS bug: 8254 timer not connected to "
- "IO-APIC\n");
- }
+ if (!no_pin1)
+ printk(KERN_ERR "..MP-BIOS bug: "
+ "8254 timer not connected to IO-APIC\n");
- printk(KERN_INFO "...trying to set up timer (IRQ0) through the 8259A ... ");
- if (pin2 != -1) {
+ printk(KERN_INFO "...trying to set up timer (IRQ0) "
+ "through the 8259A ... ");
printk("\n..... (found pin %d) ...", pin2);
/*
* legacy devices should be connected to IO APIC #0
*/
- setup_ExtINT_IRQ0_pin(apic2, pin2, vector);
+ replace_pin_at_irq(0, apic1, pin1, apic2, pin2);
+ setup_timer_IRQ0_pin(apic2, pin2, vector);
+ unmask_IO_APIC_irq(0);
+ enable_8259A_irq(0);
if (timer_irq_works()) {
printk("works.\n");
- if (pin1 != -1)
- replace_pin_at_irq(0, apic1, pin1, apic2, pin2);
- else
- add_pin_to_irq(0, apic2, pin2);
+ timer_through_8259 = 1;
if (nmi_watchdog == NMI_IO_APIC) {
+ disable_8259A_irq(0);
setup_nmi();
+ enable_8259A_irq(0);
}
goto out;
}
/*
* Cleanup, just in case ...
*/
+ disable_8259A_irq(0);
clear_IO_APIC_pin(apic2, pin2);
+ printk(" failed.\n");
}
- printk(" failed.\n");
if (nmi_watchdog == NMI_IO_APIC) {
printk(KERN_WARNING "timer doesn't work through the IO-APIC - disabling NMI Watchdog!\n");
- nmi_watchdog = 0;
+ nmi_watchdog = NMI_NONE;
}
+ timer_ack = 0;
printk(KERN_INFO "...trying to set up timer as Virtual Wire IRQ...");
- disable_8259A_irq(0);
set_irq_chip_and_handler_name(0, &lapic_chip, handle_fasteoi_irq,
"fasteoi");
apic_write_around(APIC_LVT0, APIC_DM_FIXED | vector); /* Fixed mode */
@@ -2224,12 +2243,12 @@ static inline void __init check_timer(void)
printk(" works.\n");
goto out;
}
+ disable_8259A_irq(0);
apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | vector);
printk(" failed.\n");
printk(KERN_INFO "...trying to set up timer as ExtINT IRQ...");
- timer_ack = 0;
init_8259A(0);
make_8259A_irq(0);
apic_write_around(APIC_LVT0, APIC_DM_EXTINT);
@@ -2286,28 +2305,14 @@ void __init setup_IO_APIC(void)
print_IO_APIC();
}
-static int __init setup_disable_8254_timer(char *s)
-{
- timer_over_8254 = -1;
- return 1;
-}
-static int __init setup_enable_8254_timer(char *s)
-{
- timer_over_8254 = 2;
- return 1;
-}
-
-__setup("disable_8254_timer", setup_disable_8254_timer);
-__setup("enable_8254_timer", setup_enable_8254_timer);
-
/*
* Called after all the initialization is done. If we didnt find any
* APIC bugs then we can allow the modify fast path
*/
-
+
static int __init io_apic_bug_finalize(void)
{
- if(sis_apic_bug == -1)
+ if (sis_apic_bug == -1)
sis_apic_bug = 0;
return 0;
}
@@ -2318,17 +2323,17 @@ struct sysfs_ioapic_data {
struct sys_device dev;
struct IO_APIC_route_entry entry[0];
};
-static struct sysfs_ioapic_data * mp_ioapic_data[MAX_IO_APICS];
+static struct sysfs_ioapic_data *mp_ioapic_data[MAX_IO_APICS];
static int ioapic_suspend(struct sys_device *dev, pm_message_t state)
{
struct IO_APIC_route_entry *entry;
struct sysfs_ioapic_data *data;
int i;
-
+
data = container_of(dev, struct sysfs_ioapic_data, dev);
entry = data->entry;
- for (i = 0; i < nr_ioapic_registers[dev->id]; i ++)
+ for (i = 0; i < nr_ioapic_registers[dev->id]; i++)
entry[i] = ioapic_read_entry(dev->id, i);
return 0;
@@ -2341,7 +2346,7 @@ static int ioapic_resume(struct sys_device *dev)
unsigned long flags;
union IO_APIC_reg_00 reg_00;
int i;
-
+
data = container_of(dev, struct sysfs_ioapic_data, dev);
entry = data->entry;
@@ -2352,7 +2357,7 @@ static int ioapic_resume(struct sys_device *dev)
io_apic_write(dev->id, 0, reg_00.raw);
}
spin_unlock_irqrestore(&ioapic_lock, flags);
- for (i = 0; i < nr_ioapic_registers[dev->id]; i ++)
+ for (i = 0; i < nr_ioapic_registers[dev->id]; i++)
ioapic_write_entry(dev->id, i, entry[i]);
return 0;
@@ -2366,24 +2371,23 @@ static struct sysdev_class ioapic_sysdev_class = {
static int __init ioapic_init_sysfs(void)
{
- struct sys_device * dev;
+ struct sys_device *dev;
int i, size, error = 0;
error = sysdev_class_register(&ioapic_sysdev_class);
if (error)
return error;
- for (i = 0; i < nr_ioapics; i++ ) {
- size = sizeof(struct sys_device) + nr_ioapic_registers[i]
+ for (i = 0; i < nr_ioapics; i++) {
+ size = sizeof(struct sys_device) + nr_ioapic_registers[i]
* sizeof(struct IO_APIC_route_entry);
- mp_ioapic_data[i] = kmalloc(size, GFP_KERNEL);
+ mp_ioapic_data[i] = kzalloc(size, GFP_KERNEL);
if (!mp_ioapic_data[i]) {
printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i);
continue;
}
- memset(mp_ioapic_data[i], 0, size);
dev = &mp_ioapic_data[i]->dev;
- dev->id = i;
+ dev->id = i;
dev->cls = &ioapic_sysdev_class;
error = sysdev_register(dev);
if (error) {
@@ -2458,7 +2462,7 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms
msg->address_lo =
MSI_ADDR_BASE_LO |
((INT_DEST_MODE == 0) ?
- MSI_ADDR_DEST_MODE_PHYSICAL:
+MSI_ADDR_DEST_MODE_PHYSICAL:
MSI_ADDR_DEST_MODE_LOGICAL) |
((INT_DELIVERY_MODE != dest_LowestPrio) ?
MSI_ADDR_REDIRECTION_CPU:
@@ -2469,7 +2473,7 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms
MSI_DATA_TRIGGER_EDGE |
MSI_DATA_LEVEL_ASSERT |
((INT_DELIVERY_MODE != dest_LowestPrio) ?
- MSI_DATA_DELIVERY_FIXED:
+MSI_DATA_DELIVERY_FIXED:
MSI_DATA_DELIVERY_LOWPRI) |
MSI_DATA_VECTOR(vector);
}
@@ -2640,12 +2644,12 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
#endif /* CONFIG_HT_IRQ */
/* --------------------------------------------------------------------------
- ACPI-based IOAPIC Configuration
+ ACPI-based IOAPIC Configuration
-------------------------------------------------------------------------- */
#ifdef CONFIG_ACPI
-int __init io_apic_get_unique_id (int ioapic, int apic_id)
+int __init io_apic_get_unique_id(int ioapic, int apic_id)
{
union IO_APIC_reg_00 reg_00;
static physid_mask_t apic_id_map = PHYSID_MASK_NONE;
@@ -2654,10 +2658,10 @@ int __init io_apic_get_unique_id (int ioapic, int apic_id)
int i = 0;
/*
- * The P4 platform supports up to 256 APIC IDs on two separate APIC
- * buses (one for LAPICs, one for IOAPICs), where predecessors only
+ * The P4 platform supports up to 256 APIC IDs on two separate APIC
+ * buses (one for LAPICs, one for IOAPICs), where predecessors only
* supports up to 16 on one shared APIC bus.
- *
+ *
* TBD: Expand LAPIC/IOAPIC support on P4-class systems to take full
* advantage of new APIC bus architecture.
*/
@@ -2676,7 +2680,7 @@ int __init io_apic_get_unique_id (int ioapic, int apic_id)
}
/*
- * Every APIC in a system must have a unique ID or we get lots of nice
+ * Every APIC in a system must have a unique ID or we get lots of nice
* 'stuck on smp_invalidate_needed IPI wait' messages.
*/
if (check_apicid_used(apic_id_map, apic_id)) {
@@ -2693,7 +2697,7 @@ int __init io_apic_get_unique_id (int ioapic, int apic_id)
"trying %d\n", ioapic, apic_id, i);
apic_id = i;
- }
+ }
tmp = apicid_to_cpu_present(apic_id);
physids_or(apic_id_map, apic_id_map, tmp);
@@ -2720,7 +2724,7 @@ int __init io_apic_get_unique_id (int ioapic, int apic_id)
}
-int __init io_apic_get_version (int ioapic)
+int __init io_apic_get_version(int ioapic)
{
union IO_APIC_reg_01 reg_01;
unsigned long flags;
@@ -2733,7 +2737,7 @@ int __init io_apic_get_version (int ioapic)
}
-int __init io_apic_get_redir_entries (int ioapic)
+int __init io_apic_get_redir_entries(int ioapic)
{
union IO_APIC_reg_01 reg_01;
unsigned long flags;
@@ -2746,7 +2750,7 @@ int __init io_apic_get_redir_entries (int ioapic)
}
-int io_apic_set_pci_routing (int ioapic, int pin, int irq, int edge_level, int active_high_low)
+int io_apic_set_pci_routing(int ioapic, int pin, int irq, int edge_level, int active_high_low)
{
struct IO_APIC_route_entry entry;
@@ -2762,7 +2766,7 @@ int io_apic_set_pci_routing (int ioapic, int pin, int irq, int edge_level, int a
* corresponding device driver registers for this IRQ.
*/
- memset(&entry,0,sizeof(entry));
+ memset(&entry, 0, sizeof(entry));
entry.delivery_mode = INT_DELIVERY_MODE;
entry.dest_mode = INT_DEST_MODE;
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index ef1a8dfcc52..e5ef6030356 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -61,7 +61,7 @@ struct irq_cfg {
};
/* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */
-struct irq_cfg irq_cfg[NR_IRQS] __read_mostly = {
+static struct irq_cfg irq_cfg[NR_IRQS] __read_mostly = {
[0] = { .domain = CPU_MASK_ALL, .vector = IRQ0_VECTOR, },
[1] = { .domain = CPU_MASK_ALL, .vector = IRQ1_VECTOR, },
[2] = { .domain = CPU_MASK_ALL, .vector = IRQ2_VECTOR, },
@@ -90,7 +90,7 @@ static int no_timer_check;
static int disable_timer_pin_1 __initdata;
-int timer_over_8254 __initdata = 1;
+int timer_through_8259 __initdata;
/* Where if anywhere is the i8259 connect in external int mode */
static struct { int pin, apic; } ioapic_i8259 = { -1, -1 };
@@ -183,7 +183,7 @@ static bool io_apic_level_ack_pending(unsigned int irq)
break;
reg = io_apic_read(entry->apic, 0x10 + pin*2);
/* Is the remote IRR bit set? */
- if ((reg >> 14) & 1) {
+ if (reg & IO_APIC_REDIR_REMOTE_IRR) {
spin_unlock_irqrestore(&ioapic_lock, flags);
return true;
}
@@ -298,7 +298,7 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, u8 vector)
break;
io_apic_write(apic, 0x11 + pin*2, dest);
reg = io_apic_read(apic, 0x10 + pin*2);
- reg &= ~0x000000ff;
+ reg &= ~IO_APIC_REDIR_VECTOR_MASK;
reg |= vector;
io_apic_modify(apic, reg);
if (!entry->next)
@@ -360,16 +360,37 @@ static void add_pin_to_irq(unsigned int irq, int apic, int pin)
entry->pin = pin;
}
+/*
+ * Reroute an IRQ to a different pin.
+ */
+static void __init replace_pin_at_irq(unsigned int irq,
+ int oldapic, int oldpin,
+ int newapic, int newpin)
+{
+ struct irq_pin_list *entry = irq_2_pin + irq;
+
+ while (1) {
+ if (entry->apic == oldapic && entry->pin == oldpin) {
+ entry->apic = newapic;
+ entry->pin = newpin;
+ }
+ if (!entry->next)
+ break;
+ entry = irq_2_pin + entry->next;
+ }
+}
+
#define DO_ACTION(name,R,ACTION, FINAL) \
\
static void name##_IO_APIC_irq (unsigned int irq) \
__DO_ACTION(R, ACTION, FINAL)
-DO_ACTION( __mask, 0, |= 0x00010000, io_apic_sync(entry->apic) )
- /* mask = 1 */
-DO_ACTION( __unmask, 0, &= 0xfffeffff, )
- /* mask = 0 */
+/* mask = 1 */
+DO_ACTION(__mask, 0, |= IO_APIC_REDIR_MASKED, io_apic_sync(entry->apic))
+
+/* mask = 0 */
+DO_ACTION(__unmask, 0, &= ~IO_APIC_REDIR_MASKED, )
static void mask_IO_APIC_irq (unsigned int irq)
{
@@ -430,20 +451,6 @@ static int __init disable_timer_pin_setup(char *arg)
}
__setup("disable_timer_pin_1", disable_timer_pin_setup);
-static int __init setup_disable_8254_timer(char *s)
-{
- timer_over_8254 = -1;
- return 1;
-}
-static int __init setup_enable_8254_timer(char *s)
-{
- timer_over_8254 = 2;
- return 1;
-}
-
-__setup("disable_8254_timer", setup_disable_8254_timer);
-__setup("enable_8254_timer", setup_enable_8254_timer);
-
/*
* Find the IRQ entry number of a certain pin.
@@ -911,26 +918,21 @@ static void __init setup_IO_APIC_irqs(void)
}
/*
- * Set up the 8259A-master output pin as broadcast to all
- * CPUs.
+ * Set up the timer pin, possibly with the 8259A-master behind.
*/
-static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, int vector)
+static void __init setup_timer_IRQ0_pin(unsigned int apic, unsigned int pin,
+ int vector)
{
struct IO_APIC_route_entry entry;
memset(&entry, 0, sizeof(entry));
- disable_8259A_irq(0);
-
- /* mask LVT0 */
- apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
-
/*
* We use logical delivery to get the timer IRQ
* to the first CPU.
*/
entry.dest_mode = INT_DEST_MODE;
- entry.mask = 0; /* unmask IRQ now */
+ entry.mask = 1; /* mask IRQ now */
entry.dest = cpu_mask_to_apicid(TARGET_CPUS);
entry.delivery_mode = INT_DELIVERY_MODE;
entry.polarity = 0;
@@ -939,7 +941,7 @@ static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, in
/*
* The timer IRQ doesn't have to know that behind the
- * scene we have a 8259A-master in AEOI mode ...
+ * scene we may have a 8259A-master in AEOI mode ...
*/
set_irq_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, "edge");
@@ -947,8 +949,6 @@ static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, in
* Add it to the IO-APIC irq-routing table:
*/
ioapic_write_entry(apic, pin, entry);
-
- enable_8259A_irq(0);
}
void __apicdebuginit print_IO_APIC(void)
@@ -1077,6 +1077,7 @@ void __apicdebuginit print_local_APIC(void * dummy)
printk("\n" KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n",
smp_processor_id(), hard_smp_processor_id());
+ v = apic_read(APIC_ID);
printk(KERN_INFO "... APIC ID: %08x (%01x)\n", v, GET_APIC_ID(read_apic_id()));
v = apic_read(APIC_LVR);
printk(KERN_INFO "... APIC VERSION: %08x\n", v);
@@ -1659,6 +1660,7 @@ static inline void __init check_timer(void)
struct irq_cfg *cfg = irq_cfg + 0;
int apic1, pin1, apic2, pin2;
unsigned long flags;
+ int no_pin1 = 0;
local_irq_save(flags);
@@ -1669,16 +1671,11 @@ static inline void __init check_timer(void)
assign_irq_vector(0, TARGET_CPUS);
/*
- * Subtle, code in do_timer_interrupt() expects an AEOI
- * mode for the 8259A whenever interrupts are routed
- * through I/O APICs. Also IRQ0 has to be enabled in
- * the 8259A which implies the virtual wire has to be
- * disabled in the local APIC.
+ * As IRQ0 is to be enabled in the 8259A, the virtual
+ * wire has to be disabled in the local APIC.
*/
apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
init_8259A(1);
- if (timer_over_8254 > 0)
- enable_8259A_irq(0);
pin1 = find_isa_irq_pin(0, mp_INT);
apic1 = find_isa_irq_apic(0, mp_INT);
@@ -1688,15 +1685,39 @@ static inline void __init check_timer(void)
apic_printk(APIC_VERBOSE,KERN_INFO "..TIMER: vector=0x%02X apic1=%d pin1=%d apic2=%d pin2=%d\n",
cfg->vector, apic1, pin1, apic2, pin2);
+ /*
+ * Some BIOS writers are clueless and report the ExtINTA
+ * I/O APIC input from the cascaded 8259A as the timer
+ * interrupt input. So just in case, if only one pin
+ * was found above, try it both directly and through the
+ * 8259A.
+ */
+ if (pin1 == -1) {
+ pin1 = pin2;
+ apic1 = apic2;
+ no_pin1 = 1;
+ } else if (pin2 == -1) {
+ pin2 = pin1;
+ apic2 = apic1;
+ }
+
+ replace_pin_at_irq(0, 0, 0, apic1, pin1);
+ apic1 = 0;
+ pin1 = 0;
+ setup_timer_IRQ0_pin(apic1, pin1, cfg->vector);
+
if (pin1 != -1) {
/*
* Ok, does IRQ0 through the IOAPIC work?
*/
+ if (no_pin1) {
+ add_pin_to_irq(0, apic1, pin1);
+ setup_timer_IRQ0_pin(apic1, pin1, cfg->vector);
+ }
unmask_IO_APIC_irq(0);
if (!no_timer_check && timer_irq_works()) {
nmi_watchdog_default();
if (nmi_watchdog == NMI_IO_APIC) {
- disable_8259A_irq(0);
setup_nmi();
enable_8259A_irq(0);
}
@@ -1705,42 +1726,48 @@ static inline void __init check_timer(void)
goto out;
}
clear_IO_APIC_pin(apic1, pin1);
- apic_printk(APIC_QUIET,KERN_ERR "..MP-BIOS bug: 8254 timer not "
- "connected to IO-APIC\n");
- }
+ if (!no_pin1)
+ apic_printk(APIC_QUIET,KERN_ERR "..MP-BIOS bug: "
+ "8254 timer not connected to IO-APIC\n");
- apic_printk(APIC_VERBOSE,KERN_INFO "...trying to set up timer (IRQ0) "
- "through the 8259A ... ");
- if (pin2 != -1) {
+ apic_printk(APIC_VERBOSE,KERN_INFO
+ "...trying to set up timer (IRQ0) "
+ "through the 8259A ... ");
apic_printk(APIC_VERBOSE,"\n..... (found apic %d pin %d) ...",
apic2, pin2);
/*
* legacy devices should be connected to IO APIC #0
*/
- setup_ExtINT_IRQ0_pin(apic2, pin2, cfg->vector);
+ replace_pin_at_irq(0, apic1, pin1, apic2, pin2);
+ setup_timer_IRQ0_pin(apic2, pin2, cfg->vector);
+ unmask_IO_APIC_irq(0);
+ enable_8259A_irq(0);
if (timer_irq_works()) {
apic_printk(APIC_VERBOSE," works.\n");
+ timer_through_8259 = 1;
nmi_watchdog_default();
if (nmi_watchdog == NMI_IO_APIC) {
+ disable_8259A_irq(0);
setup_nmi();
+ enable_8259A_irq(0);
}
goto out;
}
/*
* Cleanup, just in case ...
*/
+ disable_8259A_irq(0);
clear_IO_APIC_pin(apic2, pin2);
+ apic_printk(APIC_VERBOSE," failed.\n");
}
- apic_printk(APIC_VERBOSE," failed.\n");
if (nmi_watchdog == NMI_IO_APIC) {
printk(KERN_WARNING "timer doesn't work through the IO-APIC - disabling NMI Watchdog!\n");
- nmi_watchdog = 0;
+ nmi_watchdog = NMI_NONE;
}
apic_printk(APIC_VERBOSE, KERN_INFO "...trying to set up timer as Virtual Wire IRQ...");
- disable_8259A_irq(0);
irq_desc[0].chip = &lapic_irq_type;
apic_write(APIC_LVT0, APIC_DM_FIXED | cfg->vector); /* Fixed mode */
enable_8259A_irq(0);
@@ -1749,6 +1776,7 @@ static inline void __init check_timer(void)
apic_printk(APIC_VERBOSE," works.\n");
goto out;
}
+ disable_8259A_irq(0);
apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | cfg->vector);
apic_printk(APIC_VERBOSE," failed.\n");
diff --git a/arch/x86/kernel/ipi.c b/arch/x86/kernel/ipi.c
index c0df7b89ca2..9d98cda39ad 100644
--- a/arch/x86/kernel/ipi.c
+++ b/arch/x86/kernel/ipi.c
@@ -8,7 +8,6 @@
#include <linux/kernel_stat.h>
#include <linux/mc146818rtc.h>
#include <linux/cache.h>
-#include <linux/interrupt.h>
#include <linux/cpu.h>
#include <linux/module.h>
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 147352df28b..468acd04aa2 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -313,16 +313,20 @@ skip:
per_cpu(irq_stat,j).irq_tlb_count);
seq_printf(p, " TLB shootdowns\n");
#endif
+#ifdef CONFIG_X86_MCE
seq_printf(p, "TRM: ");
for_each_online_cpu(j)
seq_printf(p, "%10u ",
per_cpu(irq_stat,j).irq_thermal_count);
seq_printf(p, " Thermal event interrupts\n");
+#endif
+#ifdef CONFIG_X86_LOCAL_APIC
seq_printf(p, "SPU: ");
for_each_online_cpu(j)
seq_printf(p, "%10u ",
per_cpu(irq_stat,j).irq_spurious_count);
seq_printf(p, " Spurious interrupts\n");
+#endif
seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count));
#if defined(CONFIG_X86_IO_APIC)
seq_printf(p, "MIS: %10u\n", atomic_read(&irq_mis_count));
@@ -331,6 +335,40 @@ skip:
return 0;
}
+/*
+ * /proc/stat helpers
+ */
+u64 arch_irq_stat_cpu(unsigned int cpu)
+{
+ u64 sum = nmi_count(cpu);
+
+#ifdef CONFIG_X86_LOCAL_APIC
+ sum += per_cpu(irq_stat, cpu).apic_timer_irqs;
+#endif
+#ifdef CONFIG_SMP
+ sum += per_cpu(irq_stat, cpu).irq_resched_count;
+ sum += per_cpu(irq_stat, cpu).irq_call_count;
+ sum += per_cpu(irq_stat, cpu).irq_tlb_count;
+#endif
+#ifdef CONFIG_X86_MCE
+ sum += per_cpu(irq_stat, cpu).irq_thermal_count;
+#endif
+#ifdef CONFIG_X86_LOCAL_APIC
+ sum += per_cpu(irq_stat, cpu).irq_spurious_count;
+#endif
+ return sum;
+}
+
+u64 arch_irq_stat(void)
+{
+ u64 sum = atomic_read(&irq_err_count);
+
+#ifdef CONFIG_X86_IO_APIC
+ sum += atomic_read(&irq_mis_count);
+#endif
+ return sum;
+}
+
#ifdef CONFIG_HOTPLUG_CPU
#include <mach_apic.h>
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 3aac15466a9..1f78b238d8d 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -135,6 +135,7 @@ skip:
seq_printf(p, "%10u ", cpu_pda(j)->irq_tlb_count);
seq_printf(p, " TLB shootdowns\n");
#endif
+#ifdef CONFIG_X86_MCE
seq_printf(p, "TRM: ");
for_each_online_cpu(j)
seq_printf(p, "%10u ", cpu_pda(j)->irq_thermal_count);
@@ -143,6 +144,7 @@ skip:
for_each_online_cpu(j)
seq_printf(p, "%10u ", cpu_pda(j)->irq_threshold_count);
seq_printf(p, " Threshold APIC interrupts\n");
+#endif
seq_printf(p, "SPU: ");
for_each_online_cpu(j)
seq_printf(p, "%10u ", cpu_pda(j)->irq_spurious_count);
@@ -153,6 +155,32 @@ skip:
}
/*
+ * /proc/stat helpers
+ */
+u64 arch_irq_stat_cpu(unsigned int cpu)
+{
+ u64 sum = cpu_pda(cpu)->__nmi_count;
+
+ sum += cpu_pda(cpu)->apic_timer_irqs;
+#ifdef CONFIG_SMP
+ sum += cpu_pda(cpu)->irq_resched_count;
+ sum += cpu_pda(cpu)->irq_call_count;
+ sum += cpu_pda(cpu)->irq_tlb_count;
+#endif
+#ifdef CONFIG_X86_MCE
+ sum += cpu_pda(cpu)->irq_thermal_count;
+ sum += cpu_pda(cpu)->irq_threshold_count;
+#endif
+ sum += cpu_pda(cpu)->irq_spurious_count;
+ return sum;
+}
+
+u64 arch_irq_stat(void)
+{
+ return atomic_read(&irq_err_count);
+}
+
+/*
* do_IRQ handles all normal device IRQ's (the special
* SMP cross-CPU interrupts have their own specific
* handlers).
diff --git a/arch/x86/kernel/irqinit_32.c b/arch/x86/kernel/irqinit_32.c
new file mode 100644
index 00000000000..d66914287ee
--- /dev/null
+++ b/arch/x86/kernel/irqinit_32.c
@@ -0,0 +1,114 @@
+#include <linux/errno.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/ioport.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+#include <linux/random.h>
+#include <linux/init.h>
+#include <linux/kernel_stat.h>
+#include <linux/sysdev.h>
+#include <linux/bitops.h>
+
+#include <asm/atomic.h>
+#include <asm/system.h>
+#include <asm/io.h>
+#include <asm/timer.h>
+#include <asm/pgtable.h>
+#include <asm/delay.h>
+#include <asm/desc.h>
+#include <asm/apic.h>
+#include <asm/arch_hooks.h>
+#include <asm/i8259.h>
+
+
+
+/*
+ * Note that on a 486, we don't want to do a SIGFPE on an irq13
+ * as the irq is unreliable, and exception 16 works correctly
+ * (ie as explained in the intel literature). On a 386, you
+ * can't use exception 16 due to bad IBM design, so we have to
+ * rely on the less exact irq13.
+ *
+ * Careful.. Not only is IRQ13 unreliable, but it is also
+ * leads to races. IBM designers who came up with it should
+ * be shot.
+ */
+
+
+static irqreturn_t math_error_irq(int cpl, void *dev_id)
+{
+ extern void math_error(void __user *);
+ outb(0,0xF0);
+ if (ignore_fpu_irq || !boot_cpu_data.hard_math)
+ return IRQ_NONE;
+ math_error((void __user *)get_irq_regs()->ip);
+ return IRQ_HANDLED;
+}
+
+/*
+ * New motherboards sometimes make IRQ 13 be a PCI interrupt,
+ * so allow interrupt sharing.
+ */
+static struct irqaction fpu_irq = {
+ .handler = math_error_irq,
+ .mask = CPU_MASK_NONE,
+ .name = "fpu",
+};
+
+void __init init_ISA_irqs (void)
+{
+ int i;
+
+#ifdef CONFIG_X86_LOCAL_APIC
+ init_bsp_APIC();
+#endif
+ init_8259A(0);
+
+ /*
+ * 16 old-style INTA-cycle interrupts:
+ */
+ for (i = 0; i < 16; i++) {
+ set_irq_chip_and_handler_name(i, &i8259A_chip,
+ handle_level_irq, "XT");
+ }
+}
+
+/* Overridden in paravirt.c */
+void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
+
+void __init native_init_IRQ(void)
+{
+ int i;
+
+ /* all the set up before the call gates are initialised */
+ pre_intr_init_hook();
+
+ /*
+ * Cover the whole vector space, no vector can escape
+ * us. (some of these will be overridden and become
+ * 'special' SMP interrupts)
+ */
+ for (i = 0; i < (NR_VECTORS - FIRST_EXTERNAL_VECTOR); i++) {
+ int vector = FIRST_EXTERNAL_VECTOR + i;
+ if (i >= NR_IRQS)
+ break;
+ /* SYSCALL_VECTOR was reserved in trap_init. */
+ if (!test_bit(vector, used_vectors))
+ set_intr_gate(vector, interrupt[i]);
+ }
+
+ /* setup after call gates are initialised (usually add in
+ * the architecture specific gates)
+ */
+ intr_init_hook();
+
+ /*
+ * External FPU? Set up irq13 if so, for
+ * original braindamaged IBM FERR coupling.
+ */
+ if (boot_cpu_data.hard_math && !cpu_has_fpu)
+ setup_irq(FPU_IRQ, &fpu_irq);
+
+ irq_ctx_init(smp_processor_id());
+}
diff --git a/arch/x86/kernel/irqinit_64.c b/arch/x86/kernel/irqinit_64.c
new file mode 100644
index 00000000000..64bc0f14285
--- /dev/null
+++ b/arch/x86/kernel/irqinit_64.c
@@ -0,0 +1,203 @@
+#include <linux/linkage.h>
+#include <linux/errno.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/ioport.h>
+#include <linux/interrupt.h>
+#include <linux/timex.h>
+#include <linux/slab.h>
+#include <linux/random.h>
+#include <linux/init.h>
+#include <linux/kernel_stat.h>
+#include <linux/sysdev.h>
+#include <linux/bitops.h>
+
+#include <asm/acpi.h>
+#include <asm/atomic.h>
+#include <asm/system.h>
+#include <asm/io.h>
+#include <asm/hw_irq.h>
+#include <asm/pgtable.h>
+#include <asm/delay.h>
+#include <asm/desc.h>
+#include <asm/apic.h>
+#include <asm/i8259.h>
+
+/*
+ * Common place to define all x86 IRQ vectors
+ *
+ * This builds up the IRQ handler stubs using some ugly macros in irq.h
+ *
+ * These macros create the low-level assembly IRQ routines that save
+ * register context and call do_IRQ(). do_IRQ() then does all the
+ * operations that are needed to keep the AT (or SMP IOAPIC)
+ * interrupt-controller happy.
+ */
+
+#define BI(x,y) \
+ BUILD_IRQ(x##y)
+
+#define BUILD_16_IRQS(x) \
+ BI(x,0) BI(x,1) BI(x,2) BI(x,3) \
+ BI(x,4) BI(x,5) BI(x,6) BI(x,7) \
+ BI(x,8) BI(x,9) BI(x,a) BI(x,b) \
+ BI(x,c) BI(x,d) BI(x,e) BI(x,f)
+
+/*
+ * ISA PIC or low IO-APIC triggered (INTA-cycle or APIC) interrupts:
+ * (these are usually mapped to vectors 0x30-0x3f)
+ */
+
+/*
+ * The IO-APIC gives us many more interrupt sources. Most of these
+ * are unused but an SMP system is supposed to have enough memory ...
+ * sometimes (mostly wrt. hw bugs) we get corrupted vectors all
+ * across the spectrum, so we really want to be prepared to get all
+ * of these. Plus, more powerful systems might have more than 64
+ * IO-APIC registers.
+ *
+ * (these are usually mapped into the 0x30-0xff vector range)
+ */
+ BUILD_16_IRQS(0x2) BUILD_16_IRQS(0x3)
+BUILD_16_IRQS(0x4) BUILD_16_IRQS(0x5) BUILD_16_IRQS(0x6) BUILD_16_IRQS(0x7)
+BUILD_16_IRQS(0x8) BUILD_16_IRQS(0x9) BUILD_16_IRQS(0xa) BUILD_16_IRQS(0xb)
+BUILD_16_IRQS(0xc) BUILD_16_IRQS(0xd) BUILD_16_IRQS(0xe) BUILD_16_IRQS(0xf)
+
+#undef BUILD_16_IRQS
+#undef BI
+
+
+#define IRQ(x,y) \
+ IRQ##x##y##_interrupt
+
+#define IRQLIST_16(x) \
+ IRQ(x,0), IRQ(x,1), IRQ(x,2), IRQ(x,3), \
+ IRQ(x,4), IRQ(x,5), IRQ(x,6), IRQ(x,7), \
+ IRQ(x,8), IRQ(x,9), IRQ(x,a), IRQ(x,b), \
+ IRQ(x,c), IRQ(x,d), IRQ(x,e), IRQ(x,f)
+
+/* for the irq vectors */
+static void (*__initdata interrupt[NR_VECTORS - FIRST_EXTERNAL_VECTOR])(void) = {
+ IRQLIST_16(0x2), IRQLIST_16(0x3),
+ IRQLIST_16(0x4), IRQLIST_16(0x5), IRQLIST_16(0x6), IRQLIST_16(0x7),
+ IRQLIST_16(0x8), IRQLIST_16(0x9), IRQLIST_16(0xa), IRQLIST_16(0xb),
+ IRQLIST_16(0xc), IRQLIST_16(0xd), IRQLIST_16(0xe), IRQLIST_16(0xf)
+};
+
+#undef IRQ
+#undef IRQLIST_16
+
+
+
+
+/*
+ * IRQ2 is cascade interrupt to second interrupt controller
+ */
+
+static struct irqaction irq2 = {
+ .handler = no_action,
+ .mask = CPU_MASK_NONE,
+ .name = "cascade",
+};
+DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
+ [0 ... IRQ0_VECTOR - 1] = -1,
+ [IRQ0_VECTOR] = 0,
+ [IRQ1_VECTOR] = 1,
+ [IRQ2_VECTOR] = 2,
+ [IRQ3_VECTOR] = 3,
+ [IRQ4_VECTOR] = 4,
+ [IRQ5_VECTOR] = 5,
+ [IRQ6_VECTOR] = 6,
+ [IRQ7_VECTOR] = 7,
+ [IRQ8_VECTOR] = 8,
+ [IRQ9_VECTOR] = 9,
+ [IRQ10_VECTOR] = 10,
+ [IRQ11_VECTOR] = 11,
+ [IRQ12_VECTOR] = 12,
+ [IRQ13_VECTOR] = 13,
+ [IRQ14_VECTOR] = 14,
+ [IRQ15_VECTOR] = 15,
+ [IRQ15_VECTOR + 1 ... NR_VECTORS - 1] = -1
+};
+
+static void __init init_ISA_irqs (void)
+{
+ int i;
+
+ init_bsp_APIC();
+ init_8259A(0);
+
+ for (i = 0; i < NR_IRQS; i++) {
+ irq_desc[i].status = IRQ_DISABLED;
+ irq_desc[i].action = NULL;
+ irq_desc[i].depth = 1;
+
+ if (i < 16) {
+ /*
+ * 16 old-style INTA-cycle interrupts:
+ */
+ set_irq_chip_and_handler_name(i, &i8259A_chip,
+ handle_level_irq, "XT");
+ } else {
+ /*
+ * 'high' PCI IRQs filled in on demand
+ */
+ irq_desc[i].chip = &no_irq_chip;
+ }
+ }
+}
+
+void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
+
+void __init native_init_IRQ(void)
+{
+ int i;
+
+ init_ISA_irqs();
+ /*
+ * Cover the whole vector space, no vector can escape
+ * us. (some of these will be overridden and become
+ * 'special' SMP interrupts)
+ */
+ for (i = 0; i < (NR_VECTORS - FIRST_EXTERNAL_VECTOR); i++) {
+ int vector = FIRST_EXTERNAL_VECTOR + i;
+ if (vector != IA32_SYSCALL_VECTOR)
+ set_intr_gate(vector, interrupt[i]);
+ }
+
+#ifdef CONFIG_SMP
+ /*
+ * The reschedule interrupt is a CPU-to-CPU reschedule-helper
+ * IPI, driven by wakeup.
+ */
+ set_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
+
+ /* IPIs for invalidation */
+ set_intr_gate(INVALIDATE_TLB_VECTOR_START+0, invalidate_interrupt0);
+ set_intr_gate(INVALIDATE_TLB_VECTOR_START+1, invalidate_interrupt1);
+ set_intr_gate(INVALIDATE_TLB_VECTOR_START+2, invalidate_interrupt2);
+ set_intr_gate(INVALIDATE_TLB_VECTOR_START+3, invalidate_interrupt3);
+ set_intr_gate(INVALIDATE_TLB_VECTOR_START+4, invalidate_interrupt4);
+ set_intr_gate(INVALIDATE_TLB_VECTOR_START+5, invalidate_interrupt5);
+ set_intr_gate(INVALIDATE_TLB_VECTOR_START+6, invalidate_interrupt6);
+ set_intr_gate(INVALIDATE_TLB_VECTOR_START+7, invalidate_interrupt7);
+
+ /* IPI for generic function call */
+ set_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
+
+ /* Low priority IPI to cleanup after moving an irq */
+ set_intr_gate(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt);
+#endif
+ set_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
+ set_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt);
+
+ /* self generated IPI for local APIC timer */
+ set_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
+
+ /* IPI vectors for APIC spurious and error interrupts */
+ set_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
+ set_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
+
+ if (!acpi_ioapic)
+ setup_irq(2, &irq2);
+}
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index 0224c3637c7..21f2bae98c1 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -20,9 +20,9 @@
#include <asm/mmu_context.h>
#ifdef CONFIG_SMP
-static void flush_ldt(void *null)
+static void flush_ldt(void *current_mm)
{
- if (current->active_mm)
+ if (current->active_mm == current_mm)
load_LDT(&current->active_mm->context);
}
#endif
@@ -68,7 +68,7 @@ static int alloc_ldt(mm_context_t *pc, int mincount, int reload)
load_LDT(pc);
mask = cpumask_of_cpu(smp_processor_id());
if (!cpus_equal(current->mm->cpu_vm_mask, mask))
- smp_call_function(flush_ldt, NULL, 1, 1);
+ smp_call_function(flush_ldt, current->mm, 1, 1);
preempt_enable();
#else
load_LDT(pc);
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index d0b234c9fc3..f4960171bc6 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -39,7 +39,7 @@ static void set_idt(void *newidt, __u16 limit)
curidt.address = (unsigned long)newidt;
load_idt(&curidt);
-};
+}
static void set_gdt(void *newgdt, __u16 limit)
@@ -51,7 +51,7 @@ static void set_gdt(void *newgdt, __u16 limit)
curgdt.address = (unsigned long)newgdt;
load_gdt(&curgdt);
-};
+}
static void load_segments(void)
{
diff --git a/arch/x86/kernel/microcode.c b/arch/x86/kernel/microcode.c
index 69729e38b78..9758fea87c5 100644
--- a/arch/x86/kernel/microcode.c
+++ b/arch/x86/kernel/microcode.c
@@ -5,13 +5,14 @@
* 2006 Shaohua Li <shaohua.li@intel.com>
*
* This driver allows to upgrade microcode on Intel processors
- * belonging to IA-32 family - PentiumPro, Pentium II,
+ * belonging to IA-32 family - PentiumPro, Pentium II,
* Pentium III, Xeon, Pentium 4, etc.
*
- * Reference: Section 8.10 of Volume III, Intel Pentium 4 Manual,
- * Order Number 245472 or free download from:
- *
- * http://developer.intel.com/design/pentium4/manuals/245472.htm
+ * Reference: Section 8.11 of Volume 3a, IA-32 Intel? Architecture
+ * Software Developer's Manual
+ * Order Number 253668 or free download from:
+ *
+ * http://developer.intel.com/design/pentium4/manuals/253668.htm
*
* For more information, go to http://www.urbanmyth.org/microcode
*
@@ -58,12 +59,12 @@
* nature of implementation.
* 1.11 22 Mar 2002 Tigran Aivazian <tigran@veritas.com>
* Fix the panic when writing zero-length microcode chunk.
- * 1.12 29 Sep 2003 Nitin Kamble <nitin.a.kamble@intel.com>,
+ * 1.12 29 Sep 2003 Nitin Kamble <nitin.a.kamble@intel.com>,
* Jun Nakajima <jun.nakajima@intel.com>
* Support for the microcode updates in the new format.
* 1.13 10 Oct 2003 Tigran Aivazian <tigran@veritas.com>
* Removed ->read() method and obsoleted MICROCODE_IOCFREE ioctl
- * because we no longer hold a copy of applied microcode
+ * because we no longer hold a copy of applied microcode
* in kernel memory.
* 1.14 25 Jun 2004 Tigran Aivazian <tigran@veritas.com>
* Fix sigmatch() macro to handle old CPUs with pf == 0.
@@ -320,11 +321,11 @@ static void apply_microcode(int cpu)
return;
/* serialize access to the physical write to MSR 0x79 */
- spin_lock_irqsave(&microcode_update_lock, flags);
+ spin_lock_irqsave(&microcode_update_lock, flags);
/* write microcode via MSR 0x79 */
wrmsr(MSR_IA32_UCODE_WRITE,
- (unsigned long) uci->mc->bits,
+ (unsigned long) uci->mc->bits,
(unsigned long) uci->mc->bits >> 16 >> 16);
wrmsr(MSR_IA32_UCODE_REV, 0, 0);
@@ -341,7 +342,7 @@ static void apply_microcode(int cpu)
return;
}
printk(KERN_INFO "microcode: CPU%d updated from revision "
- "0x%x to 0x%x, date = %08x \n",
+ "0x%x to 0x%x, date = %08x \n",
cpu_num, uci->rev, val[1], uci->mc->hdr.date);
uci->rev = val[1];
}
@@ -534,7 +535,7 @@ static int cpu_request_microcode(int cpu)
c->x86, c->x86_model, c->x86_mask);
error = request_firmware(&firmware, name, &microcode_pdev->dev);
if (error) {
- pr_debug("microcode: ucode data file %s load failed\n", name);
+ pr_debug("microcode: data file %s load failed\n", name);
return error;
}
buf = firmware->data;
@@ -805,6 +806,9 @@ static int __init microcode_init (void)
{
int error;
+ printk(KERN_INFO
+ "IA-32 Microcode Update Driver: v" MICROCODE_VERSION " <tigran@aivazian.fsnet.co.uk>\n");
+
error = microcode_dev_init();
if (error)
return error;
@@ -825,9 +829,6 @@ static int __init microcode_init (void)
}
register_hotcpu_notifier(&mc_cpu_notifier);
-
- printk(KERN_INFO
- "IA-32 Microcode Update Driver: v" MICROCODE_VERSION " <tigran@aivazian.fsnet.co.uk>\n");
return 0;
}
diff --git a/arch/x86/kernel/mmconf-fam10h_64.c b/arch/x86/kernel/mmconf-fam10h_64.c
index edc5fbfe85c..fdfdc550b36 100644
--- a/arch/x86/kernel/mmconf-fam10h_64.c
+++ b/arch/x86/kernel/mmconf-fam10h_64.c
@@ -12,6 +12,7 @@
#include <asm/io.h>
#include <asm/msr.h>
#include <asm/acpi.h>
+#include <asm/mmconfig.h>
#include "../pci/pci.h"
diff --git a/arch/x86/kernel/nmi_32.c b/arch/x86/kernel/nmi_32.c
index 84160f74eeb..6580dae4627 100644
--- a/arch/x86/kernel/nmi_32.c
+++ b/arch/x86/kernel/nmi_32.c
@@ -24,8 +24,11 @@
#include <linux/kdebug.h>
#include <linux/slab.h>
+#include <asm/i8259.h>
+#include <asm/io_apic.h>
#include <asm/smp.h>
#include <asm/nmi.h>
+#include <asm/timer.h>
#include "mach_traps.h"
@@ -81,7 +84,7 @@ int __init check_nmi_watchdog(void)
prev_nmi_count = kmalloc(NR_CPUS * sizeof(int), GFP_KERNEL);
if (!prev_nmi_count)
- return -1;
+ goto error;
printk(KERN_INFO "Testing NMI watchdog ... ");
@@ -118,7 +121,7 @@ int __init check_nmi_watchdog(void)
if (!atomic_read(&nmi_active)) {
kfree(prev_nmi_count);
atomic_set(&nmi_active, -1);
- return -1;
+ goto error;
}
printk("OK.\n");
@@ -129,6 +132,12 @@ int __init check_nmi_watchdog(void)
kfree(prev_nmi_count);
return 0;
+error:
+ if (nmi_watchdog == NMI_IO_APIC && !timer_through_8259)
+ disable_8259A_irq(0);
+ timer_ack = 0;
+
+ return -1;
}
static int __init setup_nmi_watchdog(char *str)
diff --git a/arch/x86/kernel/nmi_64.c b/arch/x86/kernel/nmi_64.c
index 5a29ded994f..0060e44e898 100644
--- a/arch/x86/kernel/nmi_64.c
+++ b/arch/x86/kernel/nmi_64.c
@@ -21,6 +21,8 @@
#include <linux/cpumask.h>
#include <linux/kdebug.h>
+#include <asm/i8259.h>
+#include <asm/io_apic.h>
#include <asm/smp.h>
#include <asm/nmi.h>
#include <asm/proto.h>
@@ -90,7 +92,7 @@ int __init check_nmi_watchdog(void)
prev_nmi_count = kmalloc(NR_CPUS * sizeof(int), GFP_KERNEL);
if (!prev_nmi_count)
- return -1;
+ goto error;
printk(KERN_INFO "Testing NMI watchdog ... ");
@@ -121,7 +123,7 @@ int __init check_nmi_watchdog(void)
if (!atomic_read(&nmi_active)) {
kfree(prev_nmi_count);
atomic_set(&nmi_active, -1);
- return -1;
+ goto error;
}
printk("OK.\n");
@@ -132,6 +134,11 @@ int __init check_nmi_watchdog(void)
kfree(prev_nmi_count);
return 0;
+error:
+ if (nmi_watchdog == NMI_IO_APIC && !timer_through_8259)
+ disable_8259A_irq(0);
+
+ return -1;
}
static int __init setup_nmi_watchdog(char *str)
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 74f0c5ea2a0..f1ab0f72700 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -380,6 +380,9 @@ struct pv_mmu_ops pv_mmu_ops = {
.pte_update = paravirt_nop,
.pte_update_defer = paravirt_nop,
+ .ptep_modify_prot_start = __ptep_modify_prot_start,
+ .ptep_modify_prot_commit = __ptep_modify_prot_commit,
+
#ifdef CONFIG_HIGHPTE
.kmap_atomic_pte = kmap_atomic,
#endif
@@ -403,6 +406,7 @@ struct pv_mmu_ops pv_mmu_ops = {
#endif /* PAGETABLE_LEVELS >= 3 */
.pte_val = native_pte_val,
+ .pte_flags = native_pte_val,
.pgd_val = native_pgd_val,
.make_pte = native_make_pte,
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index dc00a1331ac..3c43109ba05 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -77,10 +77,14 @@ void __init dma32_reserve_bootmem(void)
if (end_pfn <= MAX_DMA32_PFN)
return;
+ /*
+ * check aperture_64.c allocate_aperture() for reason about
+ * using 512M as goal
+ */
align = 64ULL<<20;
size = round_up(dma32_bootmem_size, align);
dma32_bootmem_ptr = __alloc_bootmem_nopanic(size, align,
- __pa(MAX_DMA_ADDRESS));
+ 512ULL<<20);
if (dma32_bootmem_ptr)
dma32_bootmem_size = size;
else
@@ -88,7 +92,6 @@ void __init dma32_reserve_bootmem(void)
}
static void __init dma32_free_bootmem(void)
{
- int node;
if (end_pfn <= MAX_DMA32_PFN)
return;
@@ -96,9 +99,7 @@ static void __init dma32_free_bootmem(void)
if (!dma32_bootmem_ptr)
return;
- for_each_online_node(node)
- free_bootmem_node(NODE_DATA(node), __pa(dma32_bootmem_ptr),
- dma32_bootmem_size);
+ free_bootmem(__pa(dma32_bootmem_ptr), dma32_bootmem_size);
dma32_bootmem_ptr = NULL;
dma32_bootmem_size = 0;
@@ -357,7 +358,7 @@ int dma_supported(struct device *dev, u64 mask)
EXPORT_SYMBOL(dma_supported);
/* Allocate DMA memory on node near device */
-noinline struct page *
+static noinline struct page *
dma_alloc_pages(struct device *dev, gfp_t gfp, unsigned order)
{
int node;
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index aa8ec928caa..021f3c684a6 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -104,7 +104,6 @@ static unsigned long alloc_iommu(struct device *dev, int size)
size, base_index, boundary_size, 0);
}
if (offset != -1) {
- set_bit_string(iommu_gart_bitmap, offset, size);
next_bit = offset+size;
if (next_bit >= iommu_pages) {
next_bit = 0;
@@ -534,8 +533,8 @@ static __init unsigned read_aperture(struct pci_dev *dev, u32 *size)
unsigned aper_size = 0, aper_base_32, aper_order;
u64 aper_base;
- pci_read_config_dword(dev, 0x94, &aper_base_32);
- pci_read_config_dword(dev, 0x90, &aper_order);
+ pci_read_config_dword(dev, AMD64_GARTAPERTUREBASE, &aper_base_32);
+ pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &aper_order);
aper_order = (aper_order >> 1) & 7;
aper_base = aper_base_32 & 0x7fff;
@@ -549,14 +548,63 @@ static __init unsigned read_aperture(struct pci_dev *dev, u32 *size)
return aper_base;
}
+static void enable_gart_translations(void)
+{
+ int i;
+
+ for (i = 0; i < num_k8_northbridges; i++) {
+ struct pci_dev *dev = k8_northbridges[i];
+
+ enable_gart_translation(dev, __pa(agp_gatt_table));
+ }
+}
+
+/*
+ * If fix_up_north_bridges is set, the north bridges have to be fixed up on
+ * resume in the same way as they are handled in gart_iommu_hole_init().
+ */
+static bool fix_up_north_bridges;
+static u32 aperture_order;
+static u32 aperture_alloc;
+
+void set_up_gart_resume(u32 aper_order, u32 aper_alloc)
+{
+ fix_up_north_bridges = true;
+ aperture_order = aper_order;
+ aperture_alloc = aper_alloc;
+}
+
static int gart_resume(struct sys_device *dev)
{
+ printk(KERN_INFO "PCI-DMA: Resuming GART IOMMU\n");
+
+ if (fix_up_north_bridges) {
+ int i;
+
+ printk(KERN_INFO "PCI-DMA: Restoring GART aperture settings\n");
+
+ for (i = 0; i < num_k8_northbridges; i++) {
+ struct pci_dev *dev = k8_northbridges[i];
+
+ /*
+ * Don't enable translations just yet. That is the next
+ * step. Restore the pre-suspend aperture settings.
+ */
+ pci_write_config_dword(dev, AMD64_GARTAPERTURECTL,
+ aperture_order << 1);
+ pci_write_config_dword(dev, AMD64_GARTAPERTUREBASE,
+ aperture_alloc >> 25);
+ }
+ }
+
+ enable_gart_translations();
+
return 0;
}
static int gart_suspend(struct sys_device *dev, pm_message_t state)
{
- return -EINVAL;
+ return 0;
}
static struct sysdev_class gart_sysdev_class = {
@@ -614,27 +662,14 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
memset(gatt, 0, gatt_size);
agp_gatt_table = gatt;
- for (i = 0; i < num_k8_northbridges; i++) {
- u32 gatt_reg;
- u32 ctl;
-
- dev = k8_northbridges[i];
- gatt_reg = __pa(gatt) >> 12;
- gatt_reg <<= 4;
- pci_write_config_dword(dev, 0x98, gatt_reg);
- pci_read_config_dword(dev, 0x90, &ctl);
-
- ctl |= 1;
- ctl &= ~((1<<4) | (1<<5));
-
- pci_write_config_dword(dev, 0x90, ctl);
- }
+ enable_gart_translations();
error = sysdev_class_register(&gart_sysdev_class);
if (!error)
error = sysdev_register(&device_gart);
if (error)
panic("Could not register gart_sysdev -- would corrupt data on next suspend");
+
flush_gart();
printk(KERN_INFO "PCI-DMA: aperture base @ %x size %u KB\n",
@@ -677,11 +712,11 @@ void gart_iommu_shutdown(void)
u32 ctl;
dev = k8_northbridges[i];
- pci_read_config_dword(dev, 0x90, &ctl);
+ pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl);
- ctl &= ~1;
+ ctl &= ~GARTEN;
- pci_write_config_dword(dev, 0x90, ctl);
+ pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl);
}
}
@@ -788,10 +823,10 @@ void __init gart_iommu_init(void)
wbinvd();
/*
- * Try to workaround a bug (thanks to BenH)
+ * Try to workaround a bug (thanks to BenH):
* Set unmapped entries to a scratch page instead of 0.
* Any prefetches that hit unmapped entries won't get an bus abort
- * then.
+ * then. (P2P bridge may be prefetching on DMA reads).
*/
scratch = get_zeroed_page(GFP_KERNEL);
if (!scratch)
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index ba370dc8685..4061d63aabe 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -6,6 +6,7 @@
#include <linux/sched.h>
#include <linux/module.h>
#include <linux/pm.h>
+#include <linux/clockchips.h>
struct kmem_cache *task_xstate_cachep;
@@ -45,6 +46,76 @@ void arch_task_cache_init(void)
SLAB_PANIC, NULL);
}
+/*
+ * Idle related variables and functions
+ */
+unsigned long boot_option_idle_override = 0;
+EXPORT_SYMBOL(boot_option_idle_override);
+
+/*
+ * Powermanagement idle function, if any..
+ */
+void (*pm_idle)(void);
+EXPORT_SYMBOL(pm_idle);
+
+#ifdef CONFIG_X86_32
+/*
+ * This halt magic was a workaround for ancient floppy DMA
+ * wreckage. It should be safe to remove.
+ */
+static int hlt_counter;
+void disable_hlt(void)
+{
+ hlt_counter++;
+}
+EXPORT_SYMBOL(disable_hlt);
+
+void enable_hlt(void)
+{
+ hlt_counter--;
+}
+EXPORT_SYMBOL(enable_hlt);
+
+static inline int hlt_use_halt(void)
+{
+ return (!hlt_counter && boot_cpu_data.hlt_works_ok);
+}
+#else
+static inline int hlt_use_halt(void)
+{
+ return 1;
+}
+#endif
+
+/*
+ * We use this if we don't have any better
+ * idle routine..
+ */
+void default_idle(void)
+{
+ if (hlt_use_halt()) {
+ current_thread_info()->status &= ~TS_POLLING;
+ /*
+ * TS_POLLING-cleared state must be visible before we
+ * test NEED_RESCHED:
+ */
+ smp_mb();
+
+ if (!need_resched())
+ safe_halt(); /* enables interrupts racelessly */
+ else
+ local_irq_enable();
+ current_thread_info()->status |= TS_POLLING;
+ } else {
+ local_irq_enable();
+ /* loop is done by the caller */
+ cpu_relax();
+ }
+}
+#ifdef CONFIG_APM_MODULE
+EXPORT_SYMBOL(default_idle);
+#endif
+
static void do_nothing(void *unused)
{
}
@@ -122,44 +193,129 @@ static void poll_idle(void)
*
* idle=mwait overrides this decision and forces the usage of mwait.
*/
+
+#define MWAIT_INFO 0x05
+#define MWAIT_ECX_EXTENDED_INFO 0x01
+#define MWAIT_EDX_C1 0xf0
+
static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c)
{
+ u32 eax, ebx, ecx, edx;
+
if (force_mwait)
return 1;
- if (c->x86_vendor == X86_VENDOR_AMD) {
- switch(c->x86) {
- case 0x10:
- case 0x11:
- return 0;
- }
- }
+ if (c->cpuid_level < MWAIT_INFO)
+ return 0;
+
+ cpuid(MWAIT_INFO, &eax, &ebx, &ecx, &edx);
+ /* Check, whether EDX has extended info about MWAIT */
+ if (!(ecx & MWAIT_ECX_EXTENDED_INFO))
+ return 1;
+
+ /*
+ * edx enumeratios MONITOR/MWAIT extensions. Check, whether
+ * C1 supports MWAIT
+ */
+ return (edx & MWAIT_EDX_C1);
+}
+
+/*
+ * Check for AMD CPUs, which have potentially C1E support
+ */
+static int __cpuinit check_c1e_idle(const struct cpuinfo_x86 *c)
+{
+ if (c->x86_vendor != X86_VENDOR_AMD)
+ return 0;
+
+ if (c->x86 < 0x0F)
+ return 0;
+
+ /* Family 0x0f models < rev F do not have C1E */
+ if (c->x86 == 0x0f && c->x86_model < 0x40)
+ return 0;
+
return 1;
}
-void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
+/*
+ * C1E aware idle routine. We check for C1E active in the interrupt
+ * pending message MSR. If we detect C1E, then we handle it the same
+ * way as C3 power states (local apic timer and TSC stop)
+ */
+static void c1e_idle(void)
{
- static int selected;
+ static cpumask_t c1e_mask = CPU_MASK_NONE;
+ static int c1e_detected;
- if (selected)
+ if (need_resched())
return;
+
+ if (!c1e_detected) {
+ u32 lo, hi;
+
+ rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
+ if (lo & K8_INTP_C1E_ACTIVE_MASK) {
+ c1e_detected = 1;
+ mark_tsc_unstable("TSC halt in C1E");
+ printk(KERN_INFO "System has C1E enabled\n");
+ }
+ }
+
+ if (c1e_detected) {
+ int cpu = smp_processor_id();
+
+ if (!cpu_isset(cpu, c1e_mask)) {
+ cpu_set(cpu, c1e_mask);
+ /*
+ * Force broadcast so ACPI can not interfere. Needs
+ * to run with interrupts enabled as it uses
+ * smp_function_call.
+ */
+ local_irq_enable();
+ clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE,
+ &cpu);
+ printk(KERN_INFO "Switch to broadcast mode on CPU%d\n",
+ cpu);
+ local_irq_disable();
+ }
+ clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu);
+
+ default_idle();
+
+ /*
+ * The switch back from broadcast mode needs to be
+ * called with interrupts disabled.
+ */
+ local_irq_disable();
+ clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
+ local_irq_enable();
+ } else
+ default_idle();
+}
+
+void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
+{
#ifdef CONFIG_X86_SMP
if (pm_idle == poll_idle && smp_num_siblings > 1) {
printk(KERN_WARNING "WARNING: polling idle and HT enabled,"
" performance may degrade.\n");
}
#endif
+ if (pm_idle)
+ return;
+
if (cpu_has(c, X86_FEATURE_MWAIT) && mwait_usable(c)) {
/*
- * Skip, if setup has overridden idle.
* One CPU supports mwait => All CPUs supports mwait
*/
- if (!pm_idle) {
- printk(KERN_INFO "using mwait in idle threads.\n");
- pm_idle = mwait_idle;
- }
- }
- selected = 1;
+ printk(KERN_INFO "using mwait in idle threads.\n");
+ pm_idle = mwait_idle;
+ } else if (check_c1e_idle(c)) {
+ printk(KERN_INFO "using C1E aware idle routine\n");
+ pm_idle = c1e_idle;
+ } else
+ pm_idle = default_idle;
}
static int __init idle_setup(char *str)
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index e2db9ac5c61..c2a11d77b1b 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -58,11 +58,6 @@
asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
-static int hlt_counter;
-
-unsigned long boot_option_idle_override = 0;
-EXPORT_SYMBOL(boot_option_idle_override);
-
DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
EXPORT_PER_CPU_SYMBOL(current_task);
@@ -77,55 +72,6 @@ unsigned long thread_saved_pc(struct task_struct *tsk)
return ((unsigned long *)tsk->thread.sp)[3];
}
-/*
- * Powermanagement idle function, if any..
- */
-void (*pm_idle)(void);
-EXPORT_SYMBOL(pm_idle);
-
-void disable_hlt(void)
-{
- hlt_counter++;
-}
-
-EXPORT_SYMBOL(disable_hlt);
-
-void enable_hlt(void)
-{
- hlt_counter--;
-}
-
-EXPORT_SYMBOL(enable_hlt);
-
-/*
- * We use this if we don't have any better
- * idle routine..
- */
-void default_idle(void)
-{
- if (!hlt_counter && boot_cpu_data.hlt_works_ok) {
- current_thread_info()->status &= ~TS_POLLING;
- /*
- * TS_POLLING-cleared state must be visible before we
- * test NEED_RESCHED:
- */
- smp_mb();
-
- if (!need_resched())
- safe_halt(); /* enables interrupts racelessly */
- else
- local_irq_enable();
- current_thread_info()->status |= TS_POLLING;
- } else {
- local_irq_enable();
- /* loop is done by the caller */
- cpu_relax();
- }
-}
-#ifdef CONFIG_APM_MODULE
-EXPORT_SYMBOL(default_idle);
-#endif
-
#ifdef CONFIG_HOTPLUG_CPU
#include <asm/nmi.h>
/* We don't actually take CPU down, just spin without interrupts. */
@@ -168,24 +114,19 @@ void cpu_idle(void)
while (1) {
tick_nohz_stop_sched_tick();
while (!need_resched()) {
- void (*idle)(void);
check_pgt_cache();
rmb();
- idle = pm_idle;
if (rcu_pending(cpu))
rcu_check_callbacks(cpu, 0);
- if (!idle)
- idle = default_idle;
-
if (cpu_is_offline(cpu))
play_dead();
local_irq_disable();
__get_cpu_var(irq_stat).idle_timestamp = jiffies;
- idle();
+ pm_idle();
}
tick_nohz_restart_sched_tick();
preempt_enable_no_resched();
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index c6eb5c91e5f..290183e9731 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -56,15 +56,6 @@ asmlinkage extern void ret_from_fork(void);
unsigned long kernel_thread_flags = CLONE_VM | CLONE_UNTRACED;
-unsigned long boot_option_idle_override = 0;
-EXPORT_SYMBOL(boot_option_idle_override);
-
-/*
- * Powermanagement idle function, if any..
- */
-void (*pm_idle)(void);
-EXPORT_SYMBOL(pm_idle);
-
static ATOMIC_NOTIFIER_HEAD(idle_notifier);
void idle_notifier_register(struct notifier_block *n)
@@ -94,25 +85,6 @@ void exit_idle(void)
__exit_idle();
}
-/*
- * We use this if we don't have any better
- * idle routine..
- */
-void default_idle(void)
-{
- current_thread_info()->status &= ~TS_POLLING;
- /*
- * TS_POLLING-cleared state must be visible before we
- * test NEED_RESCHED:
- */
- smp_mb();
- if (!need_resched())
- safe_halt(); /* enables interrupts racelessly */
- else
- local_irq_enable();
- current_thread_info()->status |= TS_POLLING;
-}
-
#ifdef CONFIG_HOTPLUG_CPU
DECLARE_PER_CPU(int, cpu_state);
@@ -150,12 +122,9 @@ void cpu_idle(void)
while (1) {
tick_nohz_stop_sched_tick();
while (!need_resched()) {
- void (*idle)(void);
rmb();
- idle = pm_idle;
- if (!idle)
- idle = default_idle;
+
if (cpu_is_offline(smp_processor_id()))
play_dead();
/*
@@ -165,7 +134,7 @@ void cpu_idle(void)
*/
local_irq_disable();
enter_idle();
- idle();
+ pm_idle();
/* In many cases the interrupt that ended idle
has already called exit_idle. But some idle
loops can be woken up without interrupt. */
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index d89a648fe71..79bdcd11c66 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -65,6 +65,7 @@ static enum {
ICH_FORCE_HPET_RESUME,
VT8237_FORCE_HPET_RESUME,
NVIDIA_FORCE_HPET_RESUME,
+ ATI_FORCE_HPET_RESUME,
} force_hpet_resume_type;
static void __iomem *rcba_base;
@@ -158,6 +159,8 @@ static void ich_force_enable_hpet(struct pci_dev *dev)
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ESB2_0,
ich_force_enable_hpet);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH6_0,
+ ich_force_enable_hpet);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH6_1,
ich_force_enable_hpet);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH7_0,
@@ -174,6 +177,12 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH9_7,
static struct pci_dev *cached_dev;
+static void hpet_print_force_info(void)
+{
+ printk(KERN_INFO "HPET not enabled in BIOS. "
+ "You might try hpet=force boot option\n");
+}
+
static void old_ich_force_hpet_resume(void)
{
u32 val;
@@ -253,6 +262,8 @@ static void old_ich_force_enable_hpet_user(struct pci_dev *dev)
{
if (hpet_force_user)
old_ich_force_enable_hpet(dev);
+ else
+ hpet_print_force_info();
}
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801CA_0,
@@ -290,8 +301,13 @@ static void vt8237_force_enable_hpet(struct pci_dev *dev)
{
u32 uninitialized_var(val);
- if (!hpet_force_user || hpet_address || force_hpet_address)
+ if (hpet_address || force_hpet_address)
+ return;
+
+ if (!hpet_force_user) {
+ hpet_print_force_info();
return;
+ }
pci_read_config_dword(dev, 0x68, &val);
/*
@@ -330,6 +346,36 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8235,
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8237,
vt8237_force_enable_hpet);
+static void ati_force_hpet_resume(void)
+{
+ pci_write_config_dword(cached_dev, 0x14, 0xfed00000);
+ printk(KERN_DEBUG "Force enabled HPET at resume\n");
+}
+
+static void ati_force_enable_hpet(struct pci_dev *dev)
+{
+ u32 uninitialized_var(val);
+
+ if (hpet_address || force_hpet_address)
+ return;
+
+ if (!hpet_force_user) {
+ hpet_print_force_info();
+ return;
+ }
+
+ pci_write_config_dword(dev, 0x14, 0xfed00000);
+ pci_read_config_dword(dev, 0x14, &val);
+ force_hpet_address = val;
+ force_hpet_resume_type = ATI_FORCE_HPET_RESUME;
+ dev_printk(KERN_DEBUG, &dev->dev, "Force enabled HPET at 0x%lx\n",
+ force_hpet_address);
+ cached_dev = dev;
+ return;
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_IXP400_SMBUS,
+ ati_force_enable_hpet);
+
/*
* Undocumented chipset feature taken from LinuxBIOS.
*/
@@ -343,8 +389,13 @@ static void nvidia_force_enable_hpet(struct pci_dev *dev)
{
u32 uninitialized_var(val);
- if (!hpet_force_user || hpet_address || force_hpet_address)
+ if (hpet_address || force_hpet_address)
+ return;
+
+ if (!hpet_force_user) {
+ hpet_print_force_info();
return;
+ }
pci_write_config_dword(dev, 0x44, 0xfed00001);
pci_read_config_dword(dev, 0x44, &val);
@@ -397,6 +448,9 @@ void force_hpet_resume(void)
case NVIDIA_FORCE_HPET_RESUME:
nvidia_force_hpet_resume();
return;
+ case ATI_FORCE_HPET_RESUME:
+ ati_force_hpet_resume();
+ return;
default:
break;
}
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index f6be7d5f82f..f8a62160e15 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -27,7 +27,7 @@
void (*pm_power_off)(void);
EXPORT_SYMBOL(pm_power_off);
-static long no_idt[3];
+static const struct desc_ptr no_idt = {};
static int reboot_mode;
enum reboot_type reboot_type = BOOT_KBD;
int reboot_force;
@@ -201,15 +201,15 @@ core_initcall(reboot_init);
controller to pulse the CPU reset line, which is more thorough, but
doesn't work with at least one type of 486 motherboard. It is easy
to stop this code working; hence the copious comments. */
-static unsigned long long
+static const unsigned long long
real_mode_gdt_entries [3] =
{
0x0000000000000000ULL, /* Null descriptor */
- 0x00009a000000ffffULL, /* 16-bit real-mode 64k code at 0x00000000 */
- 0x000092000100ffffULL /* 16-bit real-mode 64k data at 0x00000100 */
+ 0x00009b000000ffffULL, /* 16-bit real-mode 64k code at 0x00000000 */
+ 0x000093000100ffffULL /* 16-bit real-mode 64k data at 0x00000100 */
};
-static struct desc_ptr
+static const struct desc_ptr
real_mode_gdt = { sizeof (real_mode_gdt_entries) - 1, (long)real_mode_gdt_entries },
real_mode_idt = { 0x3ff, 0 };
@@ -231,7 +231,7 @@ real_mode_idt = { 0x3ff, 0 };
More could be done here to set up the registers as if a CPU reset had
occurred; hopefully real BIOSs don't assume much. */
-static unsigned char real_mode_switch [] =
+static const unsigned char real_mode_switch [] =
{
0x66, 0x0f, 0x20, 0xc0, /* movl %cr0,%eax */
0x66, 0x83, 0xe0, 0x11, /* andl $0x00000011,%eax */
@@ -245,7 +245,7 @@ static unsigned char real_mode_switch [] =
0x24, 0x10, /* f: andb $0x10,al */
0x66, 0x0f, 0x22, 0xc0 /* movl %eax,%cr0 */
};
-static unsigned char jump_to_bios [] =
+static const unsigned char jump_to_bios [] =
{
0xea, 0x00, 0x00, 0xff, 0xff /* ljmp $0xffff,$0x0000 */
};
@@ -255,7 +255,7 @@ static unsigned char jump_to_bios [] =
* specified by the code and length parameters.
* We assume that length will aways be less that 100!
*/
-void machine_real_restart(unsigned char *code, int length)
+void machine_real_restart(const unsigned char *code, int length)
{
local_irq_disable();
@@ -368,7 +368,7 @@ static void native_machine_emergency_restart(void)
}
case BOOT_TRIPLE:
- load_idt((const struct desc_ptr *)&no_idt);
+ load_idt(&no_idt);
__asm__ __volatile__("int3");
reboot_type = BOOT_KBD;
diff --git a/arch/x86/kernel/reboot_fixups_32.c b/arch/x86/kernel/reboot_fixups_32.c
index dec0b5ec25c..61a837743fe 100644
--- a/arch/x86/kernel/reboot_fixups_32.c
+++ b/arch/x86/kernel/reboot_fixups_32.c
@@ -49,7 +49,7 @@ struct device_fixup {
void (*reboot_fixup)(struct pci_dev *);
};
-static struct device_fixup fixups_table[] = {
+static const struct device_fixup fixups_table[] = {
{ PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5530_LEGACY, cs5530a_warm_reset },
{ PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CS5536_ISA, cs5536_warm_reset },
{ PCI_VENDOR_ID_NS, PCI_DEVICE_ID_NS_SC1100_BRIDGE, cs5530a_warm_reset },
@@ -64,7 +64,7 @@ static struct device_fixup fixups_table[] = {
*/
void mach_reboot_fixups(void)
{
- struct device_fixup *cur;
+ const struct device_fixup *cur;
struct pci_dev *dev;
int i;
diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c
index 6dff1286ad8..545440e471b 100644
--- a/arch/x86/kernel/setup_64.c
+++ b/arch/x86/kernel/setup_64.c
@@ -71,6 +71,7 @@
#include <asm/topology.h>
#include <asm/trampoline.h>
#include <asm/pat.h>
+#include <asm/mmconfig.h>
#include <mach_apic.h>
#ifdef CONFIG_PARAVIRT
@@ -79,6 +80,8 @@
#define ARCH_SETUP
#endif
+#include "cpu/cpu.h"
+
/*
* Machine setup..
*/
@@ -95,8 +98,6 @@ int bootloader_type;
unsigned long saved_video_mode;
-int force_mwait __cpuinitdata;
-
/*
* Early DMI memory
*/
@@ -118,7 +119,7 @@ EXPORT_SYMBOL_GPL(edid_info);
extern int root_mountflags;
-char __initdata command_line[COMMAND_LINE_SIZE];
+static char __initdata command_line[COMMAND_LINE_SIZE];
static struct resource standard_io_resources[] = {
{ .name = "dma1", .start = 0x00, .end = 0x1f,
@@ -164,6 +165,7 @@ static struct resource bss_resource = {
.flags = IORESOURCE_RAM,
};
+static void __init early_cpu_init(void);
static void __cpuinit early_identify_cpu(struct cpuinfo_x86 *c);
#ifdef CONFIG_PROC_VMCORE
@@ -293,18 +295,6 @@ static void __init parse_setup_data(void)
}
}
-#ifdef CONFIG_PCI_MMCONFIG
-extern void __cpuinit fam10h_check_enable_mmcfg(void);
-extern void __init check_enable_amd_mmconf_dmi(void);
-#else
-void __cpuinit fam10h_check_enable_mmcfg(void)
-{
-}
-void __init check_enable_amd_mmconf_dmi(void)
-{
-}
-#endif
-
/*
* setup_arch - architecture-specific boot-time initializations
*
@@ -352,6 +342,7 @@ void __init setup_arch(char **cmdline_p)
bss_resource.start = virt_to_phys(&__bss_start);
bss_resource.end = virt_to_phys(&__bss_stop)-1;
+ early_cpu_init();
early_identify_cpu(&boot_cpu_data);
strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
@@ -537,7 +528,20 @@ void __init setup_arch(char **cmdline_p)
check_enable_amd_mmconf_dmi();
}
-static int __cpuinit get_model_name(struct cpuinfo_x86 *c)
+struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {};
+
+static void __cpuinit default_init(struct cpuinfo_x86 *c)
+{
+ display_cacheinfo(c);
+}
+
+static struct cpu_dev __cpuinitdata default_cpu = {
+ .c_init = default_init,
+ .c_vendor = "Unknown",
+};
+static struct cpu_dev *this_cpu __cpuinitdata = &default_cpu;
+
+int __cpuinit get_model_name(struct cpuinfo_x86 *c)
{
unsigned int *v;
@@ -553,7 +557,7 @@ static int __cpuinit get_model_name(struct cpuinfo_x86 *c)
}
-static void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c)
+void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c)
{
unsigned int n, dummy, eax, ebx, ecx, edx;
@@ -585,228 +589,6 @@ static void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c)
}
}
-#ifdef CONFIG_NUMA
-static int __cpuinit nearby_node(int apicid)
-{
- int i, node;
-
- for (i = apicid - 1; i >= 0; i--) {
- node = apicid_to_node[i];
- if (node != NUMA_NO_NODE && node_online(node))
- return node;
- }
- for (i = apicid + 1; i < MAX_LOCAL_APIC; i++) {
- node = apicid_to_node[i];
- if (node != NUMA_NO_NODE && node_online(node))
- return node;
- }
- return first_node(node_online_map); /* Shouldn't happen */
-}
-#endif
-
-/*
- * On a AMD dual core setup the lower bits of the APIC id distingush the cores.
- * Assumes number of cores is a power of two.
- */
-static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c)
-{
-#ifdef CONFIG_SMP
- unsigned bits;
-#ifdef CONFIG_NUMA
- int cpu = smp_processor_id();
- int node = 0;
- unsigned apicid = hard_smp_processor_id();
-#endif
- bits = c->x86_coreid_bits;
-
- /* Low order bits define the core id (index of core in socket) */
- c->cpu_core_id = c->initial_apicid & ((1 << bits)-1);
- /* Convert the initial APIC ID into the socket ID */
- c->phys_proc_id = c->initial_apicid >> bits;
-
-#ifdef CONFIG_NUMA
- node = c->phys_proc_id;
- if (apicid_to_node[apicid] != NUMA_NO_NODE)
- node = apicid_to_node[apicid];
- if (!node_online(node)) {
- /* Two possibilities here:
- - The CPU is missing memory and no node was created.
- In that case try picking one from a nearby CPU
- - The APIC IDs differ from the HyperTransport node IDs
- which the K8 northbridge parsing fills in.
- Assume they are all increased by a constant offset,
- but in the same order as the HT nodeids.
- If that doesn't result in a usable node fall back to the
- path for the previous case. */
-
- int ht_nodeid = c->initial_apicid;
-
- if (ht_nodeid >= 0 &&
- apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
- node = apicid_to_node[ht_nodeid];
- /* Pick a nearby node */
- if (!node_online(node))
- node = nearby_node(apicid);
- }
- numa_set_node(cpu, node);
-
- printk(KERN_INFO "CPU %d/%x -> Node %d\n", cpu, apicid, node);
-#endif
-#endif
-}
-
-static void __cpuinit early_init_amd_mc(struct cpuinfo_x86 *c)
-{
-#ifdef CONFIG_SMP
- unsigned bits, ecx;
-
- /* Multi core CPU? */
- if (c->extended_cpuid_level < 0x80000008)
- return;
-
- ecx = cpuid_ecx(0x80000008);
-
- c->x86_max_cores = (ecx & 0xff) + 1;
-
- /* CPU telling us the core id bits shift? */
- bits = (ecx >> 12) & 0xF;
-
- /* Otherwise recompute */
- if (bits == 0) {
- while ((1 << bits) < c->x86_max_cores)
- bits++;
- }
-
- c->x86_coreid_bits = bits;
-
-#endif
-}
-
-#define ENABLE_C1E_MASK 0x18000000
-#define CPUID_PROCESSOR_SIGNATURE 1
-#define CPUID_XFAM 0x0ff00000
-#define CPUID_XFAM_K8 0x00000000
-#define CPUID_XFAM_10H 0x00100000
-#define CPUID_XFAM_11H 0x00200000
-#define CPUID_XMOD 0x000f0000
-#define CPUID_XMOD_REV_F 0x00040000
-
-/* AMD systems with C1E don't have a working lAPIC timer. Check for that. */
-static __cpuinit int amd_apic_timer_broken(void)
-{
- u32 lo, hi, eax = cpuid_eax(CPUID_PROCESSOR_SIGNATURE);
-
- switch (eax & CPUID_XFAM) {
- case CPUID_XFAM_K8:
- if ((eax & CPUID_XMOD) < CPUID_XMOD_REV_F)
- break;
- case CPUID_XFAM_10H:
- case CPUID_XFAM_11H:
- rdmsr(MSR_K8_ENABLE_C1E, lo, hi);
- if (lo & ENABLE_C1E_MASK)
- return 1;
- break;
- default:
- /* err on the side of caution */
- return 1;
- }
- return 0;
-}
-
-static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
-{
- early_init_amd_mc(c);
-
- /* c->x86_power is 8000_0007 edx. Bit 8 is constant TSC */
- if (c->x86_power & (1<<8))
- set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
-}
-
-static void __cpuinit init_amd(struct cpuinfo_x86 *c)
-{
- unsigned level;
-
-#ifdef CONFIG_SMP
- unsigned long value;
-
- /*
- * Disable TLB flush filter by setting HWCR.FFDIS on K8
- * bit 6 of msr C001_0015
- *
- * Errata 63 for SH-B3 steppings
- * Errata 122 for all steppings (F+ have it disabled by default)
- */
- if (c->x86 == 15) {
- rdmsrl(MSR_K8_HWCR, value);
- value |= 1 << 6;
- wrmsrl(MSR_K8_HWCR, value);
- }
-#endif
-
- /* Bit 31 in normal CPUID used for nonstandard 3DNow ID;
- 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway */
- clear_cpu_cap(c, 0*32+31);
-
- /* On C+ stepping K8 rep microcode works well for copy/memset */
- level = cpuid_eax(1);
- if (c->x86 == 15 && ((level >= 0x0f48 && level < 0x0f50) ||
- level >= 0x0f58))
- set_cpu_cap(c, X86_FEATURE_REP_GOOD);
- if (c->x86 == 0x10 || c->x86 == 0x11)
- set_cpu_cap(c, X86_FEATURE_REP_GOOD);
-
- /* Enable workaround for FXSAVE leak */
- if (c->x86 >= 6)
- set_cpu_cap(c, X86_FEATURE_FXSAVE_LEAK);
-
- level = get_model_name(c);
- if (!level) {
- switch (c->x86) {
- case 15:
- /* Should distinguish Models here, but this is only
- a fallback anyways. */
- strcpy(c->x86_model_id, "Hammer");
- break;
- }
- }
- display_cacheinfo(c);
-
- /* Multi core CPU? */
- if (c->extended_cpuid_level >= 0x80000008)
- amd_detect_cmp(c);
-
- if (c->extended_cpuid_level >= 0x80000006 &&
- (cpuid_edx(0x80000006) & 0xf000))
- num_cache_leaves = 4;
- else
- num_cache_leaves = 3;
-
- if (c->x86 == 0xf || c->x86 == 0x10 || c->x86 == 0x11)
- set_cpu_cap(c, X86_FEATURE_K8);
-
- /* MFENCE stops RDTSC speculation */
- set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
-
- if (c->x86 == 0x10)
- fam10h_check_enable_mmcfg();
-
- if (amd_apic_timer_broken())
- disable_apic_timer = 1;
-
- if (c == &boot_cpu_data && c->x86 >= 0xf && c->x86 <= 0x11) {
- unsigned long long tseg;
-
- /*
- * Split up direct mapping around the TSEG SMM area.
- * Don't do it for gbpages because there seems very little
- * benefit in doing so.
- */
- if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg) &&
- (tseg >> PMD_SHIFT) < (max_pfn_mapped >> (PMD_SHIFT-PAGE_SHIFT)))
- set_memory_4k((unsigned long)__va(tseg), 1);
- }
-}
-
void __cpuinit detect_ht(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_SMP
@@ -857,135 +639,59 @@ out:
#endif
}
-/*
- * find out the number of processor cores on the die
- */
-static int __cpuinit intel_num_cpu_cores(struct cpuinfo_x86 *c)
-{
- unsigned int eax, t;
-
- if (c->cpuid_level < 4)
- return 1;
-
- cpuid_count(4, 0, &eax, &t, &t, &t);
-
- if (eax & 0x1f)
- return ((eax >> 26) + 1);
- else
- return 1;
-}
-
-static void __cpuinit srat_detect_node(void)
-{
-#ifdef CONFIG_NUMA
- unsigned node;
- int cpu = smp_processor_id();
- int apicid = hard_smp_processor_id();
-
- /* Don't do the funky fallback heuristics the AMD version employs
- for now. */
- node = apicid_to_node[apicid];
- if (node == NUMA_NO_NODE || !node_online(node))
- node = first_node(node_online_map);
- numa_set_node(cpu, node);
-
- printk(KERN_INFO "CPU %d/%x -> Node %d\n", cpu, apicid, node);
-#endif
-}
-
-static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
-{
- if ((c->x86 == 0xf && c->x86_model >= 0x03) ||
- (c->x86 == 0x6 && c->x86_model >= 0x0e))
- set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
-}
-
-static void __cpuinit init_intel(struct cpuinfo_x86 *c)
+static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c)
{
- /* Cache sizes */
- unsigned n;
-
- init_intel_cacheinfo(c);
- if (c->cpuid_level > 9) {
- unsigned eax = cpuid_eax(10);
- /* Check for version and the number of counters */
- if ((eax & 0xff) && (((eax>>8) & 0xff) > 1))
- set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON);
+ char *v = c->x86_vendor_id;
+ int i;
+ static int printed;
+
+ for (i = 0; i < X86_VENDOR_NUM; i++) {
+ if (cpu_devs[i]) {
+ if (!strcmp(v, cpu_devs[i]->c_ident[0]) ||
+ (cpu_devs[i]->c_ident[1] &&
+ !strcmp(v, cpu_devs[i]->c_ident[1]))) {
+ c->x86_vendor = i;
+ this_cpu = cpu_devs[i];
+ return;
+ }
+ }
}
-
- if (cpu_has_ds) {
- unsigned int l1, l2;
- rdmsr(MSR_IA32_MISC_ENABLE, l1, l2);
- if (!(l1 & (1<<11)))
- set_cpu_cap(c, X86_FEATURE_BTS);
- if (!(l1 & (1<<12)))
- set_cpu_cap(c, X86_FEATURE_PEBS);
+ if (!printed) {
+ printed++;
+ printk(KERN_ERR "CPU: Vendor unknown, using generic init.\n");
+ printk(KERN_ERR "CPU: Your system may be unstable.\n");
}
-
-
- if (cpu_has_bts)
- ds_init_intel(c);
-
- n = c->extended_cpuid_level;
- if (n >= 0x80000008) {
- unsigned eax = cpuid_eax(0x80000008);
- c->x86_virt_bits = (eax >> 8) & 0xff;
- c->x86_phys_bits = eax & 0xff;
- /* CPUID workaround for Intel 0F34 CPU */
- if (c->x86_vendor == X86_VENDOR_INTEL &&
- c->x86 == 0xF && c->x86_model == 0x3 &&
- c->x86_mask == 0x4)
- c->x86_phys_bits = 36;
- }
-
- if (c->x86 == 15)
- c->x86_cache_alignment = c->x86_clflush_size * 2;
- if (c->x86 == 6)
- set_cpu_cap(c, X86_FEATURE_REP_GOOD);
- set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
- c->x86_max_cores = intel_num_cpu_cores(c);
-
- srat_detect_node();
-}
-
-static void __cpuinit early_init_centaur(struct cpuinfo_x86 *c)
-{
- if (c->x86 == 0x6 && c->x86_model >= 0xf)
- set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+ c->x86_vendor = X86_VENDOR_UNKNOWN;
}
-static void __cpuinit init_centaur(struct cpuinfo_x86 *c)
+static void __init early_cpu_support_print(void)
{
- /* Cache sizes */
- unsigned n;
+ int i,j;
+ struct cpu_dev *cpu_devx;
- n = c->extended_cpuid_level;
- if (n >= 0x80000008) {
- unsigned eax = cpuid_eax(0x80000008);
- c->x86_virt_bits = (eax >> 8) & 0xff;
- c->x86_phys_bits = eax & 0xff;
- }
-
- if (c->x86 == 0x6 && c->x86_model >= 0xf) {
- c->x86_cache_alignment = c->x86_clflush_size * 2;
- set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
- set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+ printk("KERNEL supported cpus:\n");
+ for (i = 0; i < X86_VENDOR_NUM; i++) {
+ cpu_devx = cpu_devs[i];
+ if (!cpu_devx)
+ continue;
+ for (j = 0; j < 2; j++) {
+ if (!cpu_devx->c_ident[j])
+ continue;
+ printk(" %s %s\n", cpu_devx->c_vendor,
+ cpu_devx->c_ident[j]);
+ }
}
- set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
}
-static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c)
+static void __init early_cpu_init(void)
{
- char *v = c->x86_vendor_id;
+ struct cpu_vendor_dev *cvdev;
- if (!strcmp(v, "AuthenticAMD"))
- c->x86_vendor = X86_VENDOR_AMD;
- else if (!strcmp(v, "GenuineIntel"))
- c->x86_vendor = X86_VENDOR_INTEL;
- else if (!strcmp(v, "CentaurHauls"))
- c->x86_vendor = X86_VENDOR_CENTAUR;
- else
- c->x86_vendor = X86_VENDOR_UNKNOWN;
+ for (cvdev = __x86cpuvendor_start ;
+ cvdev < __x86cpuvendor_end ;
+ cvdev++)
+ cpu_devs[cvdev->vendor] = cvdev->cpu_dev;
+ early_cpu_support_print();
}
/* Do some early cpuid on the boot CPU to get some parameter that are
@@ -1066,17 +772,9 @@ static void __cpuinit early_identify_cpu(struct cpuinfo_x86 *c)
if (c->extended_cpuid_level >= 0x80000007)
c->x86_power = cpuid_edx(0x80000007);
- switch (c->x86_vendor) {
- case X86_VENDOR_AMD:
- early_init_amd(c);
- break;
- case X86_VENDOR_INTEL:
- early_init_intel(c);
- break;
- case X86_VENDOR_CENTAUR:
- early_init_centaur(c);
- break;
- }
+ if (c->x86_vendor != X86_VENDOR_UNKNOWN &&
+ cpu_devs[c->x86_vendor]->c_early_init)
+ cpu_devs[c->x86_vendor]->c_early_init(c);
validate_pat_support(c);
}
@@ -1104,24 +802,8 @@ void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
* At the end of this section, c->x86_capability better
* indicate the features this CPU genuinely supports!
*/
- switch (c->x86_vendor) {
- case X86_VENDOR_AMD:
- init_amd(c);
- break;
-
- case X86_VENDOR_INTEL:
- init_intel(c);
- break;
-
- case X86_VENDOR_CENTAUR:
- init_centaur(c);
- break;
-
- case X86_VENDOR_UNKNOWN:
- default:
- display_cacheinfo(c);
- break;
- }
+ if (this_cpu->c_init)
+ this_cpu->c_init(c);
detect_ht(c);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 56078d61c79..f2b66675629 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -59,7 +59,6 @@
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/mtrr.h>
-#include <asm/nmi.h>
#include <asm/vmi.h>
#include <asm/genapic.h>
#include <linux/mc146818rtc.h>
@@ -996,7 +995,6 @@ do_rest:
#endif
cpu_clear(cpu, cpu_callout_map); /* was set by do_boot_cpu() */
cpu_clear(cpu, cpu_initialized); /* was set by cpu_init() */
- cpu_clear(cpu, cpu_possible_map);
cpu_clear(cpu, cpu_present_map);
per_cpu(x86_cpu_to_apicid, cpu) = BAD_APICID;
}
@@ -1158,9 +1156,11 @@ static int __init smp_sanity_check(unsigned max_cpus)
* If SMP should be disabled, then really disable it!
*/
if (!max_cpus) {
- printk(KERN_INFO "SMP mode deactivated,"
- "forcing use of dummy APIC emulation.\n");
+ printk(KERN_INFO "SMP mode deactivated.\n");
smpboot_clear_io_apic();
+
+ localise_nmi_watchdog();
+
#ifdef CONFIG_X86_32
connect_bsp_APIC();
#endif
diff --git a/arch/x86/kernel/sys_i386_32.c b/arch/x86/kernel/sys_i386_32.c
index d2ab52cc1d6..7066cb855a6 100644
--- a/arch/x86/kernel/sys_i386_32.c
+++ b/arch/x86/kernel/sys_i386_32.c
@@ -19,8 +19,8 @@
#include <linux/utsname.h>
#include <linux/ipc.h>
-#include <asm/uaccess.h>
-#include <asm/unistd.h>
+#include <linux/uaccess.h>
+#include <linux/unistd.h>
asmlinkage long sys_mmap2(unsigned long addr, unsigned long len,
unsigned long prot, unsigned long flags,
@@ -103,7 +103,7 @@ asmlinkage int old_select(struct sel_arg_struct __user *arg)
*
* This is really horribly ugly.
*/
-asmlinkage int sys_ipc (uint call, int first, int second,
+asmlinkage int sys_ipc(uint call, int first, int second,
int third, void __user *ptr, long fifth)
{
int version, ret;
@@ -113,24 +113,24 @@ asmlinkage int sys_ipc (uint call, int first, int second,
switch (call) {
case SEMOP:
- return sys_semtimedop (first, (struct sembuf __user *)ptr, second, NULL);
+ return sys_semtimedop(first, (struct sembuf __user *)ptr, second, NULL);
case SEMTIMEDOP:
return sys_semtimedop(first, (struct sembuf __user *)ptr, second,
(const struct timespec __user *)fifth);
case SEMGET:
- return sys_semget (first, second, third);
+ return sys_semget(first, second, third);
case SEMCTL: {
union semun fourth;
if (!ptr)
return -EINVAL;
if (get_user(fourth.__pad, (void __user * __user *) ptr))
return -EFAULT;
- return sys_semctl (first, second, third, fourth);
+ return sys_semctl(first, second, third, fourth);
}
case MSGSND:
- return sys_msgsnd (first, (struct msgbuf __user *) ptr,
+ return sys_msgsnd(first, (struct msgbuf __user *) ptr,
second, third);
case MSGRCV:
switch (version) {
@@ -138,45 +138,45 @@ asmlinkage int sys_ipc (uint call, int first, int second,
struct ipc_kludge tmp;
if (!ptr)
return -EINVAL;
-
+
if (copy_from_user(&tmp,
- (struct ipc_kludge __user *) ptr,
- sizeof (tmp)))
+ (struct ipc_kludge __user *) ptr,
+ sizeof(tmp)))
return -EFAULT;
- return sys_msgrcv (first, tmp.msgp, second,
+ return sys_msgrcv(first, tmp.msgp, second,
tmp.msgtyp, third);
}
default:
- return sys_msgrcv (first,
+ return sys_msgrcv(first,
(struct msgbuf __user *) ptr,
second, fifth, third);
}
case MSGGET:
- return sys_msgget ((key_t) first, second);
+ return sys_msgget((key_t) first, second);
case MSGCTL:
- return sys_msgctl (first, second, (struct msqid_ds __user *) ptr);
+ return sys_msgctl(first, second, (struct msqid_ds __user *) ptr);
case SHMAT:
switch (version) {
default: {
ulong raddr;
- ret = do_shmat (first, (char __user *) ptr, second, &raddr);
+ ret = do_shmat(first, (char __user *) ptr, second, &raddr);
if (ret)
return ret;
- return put_user (raddr, (ulong __user *) third);
+ return put_user(raddr, (ulong __user *) third);
}
case 1: /* iBCS2 emulator entry point */
if (!segment_eq(get_fs(), get_ds()))
return -EINVAL;
/* The "(ulong *) third" is valid _only_ because of the kernel segment thing */
- return do_shmat (first, (char __user *) ptr, second, (ulong *) third);
+ return do_shmat(first, (char __user *) ptr, second, (ulong *) third);
}
- case SHMDT:
- return sys_shmdt ((char __user *)ptr);
+ case SHMDT:
+ return sys_shmdt((char __user *)ptr);
case SHMGET:
- return sys_shmget (first, second, third);
+ return sys_shmget(first, second, third);
case SHMCTL:
- return sys_shmctl (first, second,
+ return sys_shmctl(first, second,
(struct shmid_ds __user *) ptr);
default:
return -ENOSYS;
@@ -186,28 +186,28 @@ asmlinkage int sys_ipc (uint call, int first, int second,
/*
* Old cruft
*/
-asmlinkage int sys_uname(struct old_utsname __user * name)
+asmlinkage int sys_uname(struct old_utsname __user *name)
{
int err;
if (!name)
return -EFAULT;
down_read(&uts_sem);
- err = copy_to_user(name, utsname(), sizeof (*name));
+ err = copy_to_user(name, utsname(), sizeof(*name));
up_read(&uts_sem);
- return err?-EFAULT:0;
+ return err? -EFAULT:0;
}
-asmlinkage int sys_olduname(struct oldold_utsname __user * name)
+asmlinkage int sys_olduname(struct oldold_utsname __user *name)
{
int error;
if (!name)
return -EFAULT;
- if (!access_ok(VERIFY_WRITE,name,sizeof(struct oldold_utsname)))
+ if (!access_ok(VERIFY_WRITE, name, sizeof(struct oldold_utsname)))
return -EFAULT;
-
- down_read(&uts_sem);
-
+
+ down_read(&uts_sem);
+
error = __copy_to_user(&name->sysname, &utsname()->sysname,
__OLD_UTS_LEN);
error |= __put_user(0, name->sysname + __OLD_UTS_LEN);
@@ -223,9 +223,9 @@ asmlinkage int sys_olduname(struct oldold_utsname __user * name)
error |= __copy_to_user(&name->machine, &utsname()->machine,
__OLD_UTS_LEN);
error |= __put_user(0, name->machine + __OLD_UTS_LEN);
-
+
up_read(&uts_sem);
-
+
error = error ? -EFAULT : 0;
return error;
@@ -241,6 +241,6 @@ int kernel_execve(const char *filename, char *const argv[], char *const envp[])
long __res;
asm volatile ("push %%ebx ; movl %2,%%ebx ; int $0x80 ; pop %%ebx"
: "=a" (__res)
- : "0" (__NR_execve),"ri" (filename),"c" (argv), "d" (envp) : "memory");
+ : "0" (__NR_execve), "ri" (filename), "c" (argv), "d" (envp) : "memory");
return __res;
}
diff --git a/arch/x86/kernel/time_32.c b/arch/x86/kernel/time_32.c
index 2ff21f39893..5f29f12da50 100644
--- a/arch/x86/kernel/time_32.c
+++ b/arch/x86/kernel/time_32.c
@@ -84,8 +84,7 @@ irqreturn_t timer_interrupt(int irq, void *dev_id)
if (timer_ack) {
/*
* Subtle, when I/O APICs are used we have to ack timer IRQ
- * manually to reset the IRR bit for do_slow_gettimeoffset().
- * This will also deassert NMI lines for the watchdog if run
+ * manually to deassert NMI lines for the watchdog if run
* on an 82489DX-based system.
*/
spin_lock(&i8259A_lock);
diff --git a/arch/x86/kernel/traps_64.c b/arch/x86/kernel/traps_64.c
index adff76ea97c..ec6d3b2130c 100644
--- a/arch/x86/kernel/traps_64.c
+++ b/arch/x86/kernel/traps_64.c
@@ -71,7 +71,6 @@ asmlinkage void general_protection(void);
asmlinkage void page_fault(void);
asmlinkage void coprocessor_error(void);
asmlinkage void simd_coprocessor_error(void);
-asmlinkage void reserved(void);
asmlinkage void alignment_check(void);
asmlinkage void machine_check(void);
asmlinkage void spurious_interrupt_bug(void);
@@ -702,12 +701,10 @@ DO_ERROR_INFO( 0, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->ip)
DO_ERROR( 4, SIGSEGV, "overflow", overflow)
DO_ERROR( 5, SIGSEGV, "bounds", bounds)
DO_ERROR_INFO( 6, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN, regs->ip)
-DO_ERROR( 7, SIGSEGV, "device not available", device_not_available)
DO_ERROR( 9, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun)
DO_ERROR(10, SIGSEGV, "invalid TSS", invalid_TSS)
DO_ERROR(11, SIGBUS, "segment not present", segment_not_present)
DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0)
-DO_ERROR(18, SIGSEGV, "reserved", reserved)
/* Runs on IST stack */
asmlinkage void do_stack_segment(struct pt_regs *regs, long error_code)
diff --git a/arch/x86/kernel/tsc_32.c b/arch/x86/kernel/tsc_32.c
index 65b70637ad9..774a5a83c29 100644
--- a/arch/x86/kernel/tsc_32.c
+++ b/arch/x86/kernel/tsc_32.c
@@ -286,7 +286,6 @@ core_initcall(cpufreq_tsc);
/* clock source code */
-static unsigned long current_tsc_khz;
static struct clocksource clocksource_tsc;
/*
@@ -439,9 +438,8 @@ void __init tsc_init(void)
unsynchronized_tsc();
check_geode_tsc_reliable();
- current_tsc_khz = tsc_khz;
- clocksource_tsc.mult = clocksource_khz2mult(current_tsc_khz,
- clocksource_tsc.shift);
+ clocksource_tsc.mult = clocksource_khz2mult(tsc_khz,
+ clocksource_tsc.shift);
/* lower the rating if we already know its unstable: */
if (check_tsc_unstable()) {
clocksource_tsc.rating = 0;
diff --git a/arch/x86/kernel/tsc_64.c b/arch/x86/kernel/tsc_64.c
index 1784b8077a1..9898fb01edf 100644
--- a/arch/x86/kernel/tsc_64.c
+++ b/arch/x86/kernel/tsc_64.c
@@ -242,7 +242,7 @@ void __init tsc_calibrate(void)
if (hpet) {
printk(KERN_INFO "TSC calibrated against HPET\n");
if (hpet2 < hpet1)
- hpet2 += 0x100000000;
+ hpet2 += 0x100000000UL;
hpet2 -= hpet1;
tsc1 = (hpet2 * hpet_readl(HPET_PERIOD)) / 1000000;
} else {
diff --git a/arch/x86/kernel/vmlinux_32.lds.S b/arch/x86/kernel/vmlinux_32.lds.S
index ce5ed083a1e..2674f579627 100644
--- a/arch/x86/kernel/vmlinux_32.lds.S
+++ b/arch/x86/kernel/vmlinux_32.lds.S
@@ -60,13 +60,6 @@ SECTIONS
BUG_TABLE :text
- . = ALIGN(4);
- .tracedata : AT(ADDR(.tracedata) - LOAD_OFFSET) {
- __tracedata_start = .;
- *(.tracedata)
- __tracedata_end = .;
- }
-
RODATA
/* writeable */
diff --git a/arch/x86/kernel/vmlinux_64.lds.S b/arch/x86/kernel/vmlinux_64.lds.S
index fad3674b06a..fd246e22fe6 100644
--- a/arch/x86/kernel/vmlinux_64.lds.S
+++ b/arch/x86/kernel/vmlinux_64.lds.S
@@ -53,13 +53,6 @@ SECTIONS
RODATA
- . = ALIGN(4);
- .tracedata : AT(ADDR(.tracedata) - LOAD_OFFSET) {
- __tracedata_start = .;
- *(.tracedata)
- __tracedata_end = .;
- }
-
. = ALIGN(PAGE_SIZE); /* Align data segment to page size boundary */
/* Data */
.data : AT(ADDR(.data) - LOAD_OFFSET) {
@@ -177,6 +170,7 @@ SECTIONS
*(.con_initcall.init)
}
__con_initcall_end = .;
+ . = ALIGN(16);
__x86cpuvendor_start = .;
.x86cpuvendor.init : AT(ADDR(.x86cpuvendor.init) - LOAD_OFFSET) {
*(.x86cpuvendor.init)
diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c
index ba8c0b75ab0..0c029e8959c 100644
--- a/arch/x86/kernel/vsmp_64.c
+++ b/arch/x86/kernel/vsmp_64.c
@@ -15,9 +15,12 @@
#include <linux/init.h>
#include <linux/pci_ids.h>
#include <linux/pci_regs.h>
+
+#include <asm/apic.h>
#include <asm/pci-direct.h>
#include <asm/io.h>
#include <asm/paravirt.h>
+#include <asm/setup.h>
#if defined CONFIG_PCI && defined CONFIG_PARAVIRT
/*