2005-04-17 06:20:36 +08:00
|
|
|
#include <linux/init.h>
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
|
|
|
|
#include <linux/string.h>
|
|
|
|
#include <linux/bitops.h>
|
|
|
|
#include <linux/smp.h>
|
|
|
|
#include <linux/thread_info.h>
|
2005-11-14 08:07:23 +08:00
|
|
|
#include <linux/module.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
#include <asm/processor.h>
|
2007-10-18 00:04:33 +08:00
|
|
|
#include <asm/pgtable.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <asm/msr.h>
|
|
|
|
#include <asm/uaccess.h>
|
2008-01-30 20:31:09 +08:00
|
|
|
#include <asm/ptrace.h>
|
|
|
|
#include <asm/ds.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
#include "cpu.h"
|
|
|
|
|
|
|
|
#ifdef CONFIG_X86_LOCAL_APIC
|
|
|
|
#include <asm/mpspec.h>
|
|
|
|
#include <asm/apic.h>
|
|
|
|
#include <mach_apic.h>
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifdef CONFIG_X86_INTEL_USERCOPY
|
|
|
|
/*
|
|
|
|
* Alignment at which movsl is preferred for bulk memory copies.
|
|
|
|
*/
|
2005-07-08 08:56:59 +08:00
|
|
|
struct movsl_mask movsl_mask __read_mostly;
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif
|
|
|
|
|
2006-03-23 18:59:33 +08:00
|
|
|
void __cpuinit early_intel_workaround(struct cpuinfo_x86 *c)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
if (c->x86_vendor != X86_VENDOR_INTEL)
|
|
|
|
return;
|
|
|
|
/* Netburst reports 64 bytes clflush size, but does IO in 128 bytes */
|
|
|
|
if (c->x86 == 15 && c->x86_cache_alignment == 64)
|
|
|
|
c->x86_cache_alignment = 128;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Early probe support logic for ppro memory erratum #50
|
|
|
|
*
|
|
|
|
* This is called before we do cpu ident work
|
|
|
|
*/
|
|
|
|
|
2006-03-23 18:59:33 +08:00
|
|
|
int __cpuinit ppro_with_ram_bug(void)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
/* Uses data from early_cpu_detect now */
|
|
|
|
if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
|
|
|
|
boot_cpu_data.x86 == 6 &&
|
|
|
|
boot_cpu_data.x86_model == 1 &&
|
|
|
|
boot_cpu_data.x86_mask < 8) {
|
|
|
|
printk(KERN_INFO "Pentium Pro with Errata#50 detected. Taking evasive action.\n");
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
* P4 Xeon errata 037 workaround.
|
|
|
|
* Hardware prefetcher may cause stale data to be loaded into the cache.
|
|
|
|
*/
|
2006-03-23 18:59:33 +08:00
|
|
|
static void __cpuinit Intel_errata_workarounds(struct cpuinfo_x86 *c)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
unsigned long lo, hi;
|
|
|
|
|
|
|
|
if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_mask == 1)) {
|
|
|
|
rdmsr (MSR_IA32_MISC_ENABLE, lo, hi);
|
|
|
|
if ((lo & (1<<9)) == 0) {
|
|
|
|
printk (KERN_INFO "CPU: C0 stepping P4 Xeon detected.\n");
|
|
|
|
printk (KERN_INFO "CPU: Disabling hardware prefetching (Errata 037)\n");
|
|
|
|
lo |= (1<<9); /* Disable hw prefetching */
|
|
|
|
wrmsr (MSR_IA32_MISC_ENABLE, lo, hi);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2005-04-17 06:25:15 +08:00
|
|
|
/*
|
|
|
|
* find out the number of processor cores on the die
|
|
|
|
*/
|
2006-03-23 18:59:33 +08:00
|
|
|
static int __cpuinit num_cpu_cores(struct cpuinfo_x86 *c)
|
2005-04-17 06:25:15 +08:00
|
|
|
{
|
2005-09-04 06:56:42 +08:00
|
|
|
unsigned int eax, ebx, ecx, edx;
|
2005-04-17 06:25:15 +08:00
|
|
|
|
|
|
|
if (c->cpuid_level < 4)
|
|
|
|
return 1;
|
|
|
|
|
2005-09-04 06:56:42 +08:00
|
|
|
/* Intel has a non-standard dependency on %ecx for this CPUID level. */
|
|
|
|
cpuid_count(4, 0, &eax, &ebx, &ecx, &edx);
|
2005-04-17 06:25:15 +08:00
|
|
|
if (eax & 0x1f)
|
|
|
|
return ((eax >> 26) + 1);
|
|
|
|
else
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
2007-10-18 00:04:33 +08:00
|
|
|
#ifdef CONFIG_X86_F00F_BUG
|
|
|
|
static void __cpuinit trap_init_f00f_bug(void)
|
|
|
|
{
|
|
|
|
__set_fixmap(FIX_F00F_IDT, __pa(&idt_table), PAGE_KERNEL_RO);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Update the IDT descriptor and reload the IDT so that
|
|
|
|
* it uses the read-only mapped virtual address.
|
|
|
|
*/
|
|
|
|
idt_descr.address = fix_to_virt(FIX_F00F_IDT);
|
|
|
|
load_idt(&idt_descr);
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2006-03-23 18:59:33 +08:00
|
|
|
static void __cpuinit init_intel(struct cpuinfo_x86 *c)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
unsigned int l2 = 0;
|
|
|
|
char *p = NULL;
|
|
|
|
|
|
|
|
#ifdef CONFIG_X86_F00F_BUG
|
|
|
|
/*
|
|
|
|
* All current models of Pentium and Pentium with MMX technology CPUs
|
|
|
|
* have the F0 0F bug, which lets nonprivileged users lock up the system.
|
|
|
|
* Note that the workaround only should be initialized once...
|
|
|
|
*/
|
|
|
|
c->f00f_bug = 0;
|
2006-12-07 09:14:08 +08:00
|
|
|
if (!paravirt_enabled() && c->x86 == 5) {
|
2005-04-17 06:20:36 +08:00
|
|
|
static int f00f_workaround_enabled = 0;
|
|
|
|
|
|
|
|
c->f00f_bug = 1;
|
|
|
|
if ( !f00f_workaround_enabled ) {
|
|
|
|
trap_init_f00f_bug();
|
|
|
|
printk(KERN_NOTICE "Intel Pentium with F0 0F bug - workaround enabled.\n");
|
|
|
|
f00f_workaround_enabled = 1;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
|
|
|
select_idle_routine(c);
|
|
|
|
l2 = init_intel_cacheinfo(c);
|
2006-06-26 19:59:59 +08:00
|
|
|
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_bit(X86_FEATURE_ARCH_PERFMON, c->x86_capability);
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/* SEP CPUID bug: Pentium Pro reports SEP but doesn't have it until model 3 mask 3 */
|
|
|
|
if ((c->x86<<8 | c->x86_model<<4 | c->x86_mask) < 0x633)
|
|
|
|
clear_bit(X86_FEATURE_SEP, c->x86_capability);
|
|
|
|
|
|
|
|
/* Names for the Pentium II/Celeron processors
|
|
|
|
detectable only by also checking the cache size.
|
|
|
|
Dixon is NOT a Celeron. */
|
|
|
|
if (c->x86 == 6) {
|
|
|
|
switch (c->x86_model) {
|
|
|
|
case 5:
|
|
|
|
if (c->x86_mask == 0) {
|
|
|
|
if (l2 == 0)
|
|
|
|
p = "Celeron (Covington)";
|
|
|
|
else if (l2 == 256)
|
|
|
|
p = "Mobile Pentium II (Dixon)";
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
|
|
|
|
case 6:
|
|
|
|
if (l2 == 128)
|
|
|
|
p = "Celeron (Mendocino)";
|
|
|
|
else if (c->x86_mask == 0 || c->x86_mask == 5)
|
|
|
|
p = "Celeron-A";
|
|
|
|
break;
|
|
|
|
|
|
|
|
case 8:
|
|
|
|
if (l2 == 128)
|
|
|
|
p = "Celeron (Coppermine)";
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if ( p )
|
|
|
|
strcpy(c->x86_model_id, p);
|
|
|
|
|
2005-11-06 00:25:54 +08:00
|
|
|
c->x86_max_cores = num_cpu_cores(c);
|
2005-04-17 06:25:15 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
detect_ht(c);
|
|
|
|
|
|
|
|
/* Work around errata */
|
|
|
|
Intel_errata_workarounds(c);
|
|
|
|
|
|
|
|
#ifdef CONFIG_X86_INTEL_USERCOPY
|
|
|
|
/*
|
|
|
|
* Set up the preferred alignment for movsl bulk memory moves
|
|
|
|
*/
|
|
|
|
switch (c->x86) {
|
|
|
|
case 4: /* 486: untested */
|
|
|
|
break;
|
|
|
|
case 5: /* Old Pentia: untested */
|
|
|
|
break;
|
|
|
|
case 6: /* PII/PIII only like movsl with 8-byte alignment */
|
|
|
|
movsl_mask.mask = 7;
|
|
|
|
break;
|
|
|
|
case 15: /* P4 is OK down to 8-byte alignment */
|
|
|
|
movsl_mask.mask = 7;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2008-01-30 20:32:38 +08:00
|
|
|
if (cpu_has_xmm2)
|
2008-01-30 20:32:37 +08:00
|
|
|
set_bit(X86_FEATURE_LFENCE_RDTSC, c->x86_capability);
|
2007-05-03 01:27:20 +08:00
|
|
|
if (c->x86 == 15) {
|
2005-04-17 06:20:36 +08:00
|
|
|
set_bit(X86_FEATURE_P4, c->x86_capability);
|
2007-05-03 01:27:20 +08:00
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
if (c->x86 == 6)
|
|
|
|
set_bit(X86_FEATURE_P3, c->x86_capability);
|
2006-01-12 05:42:45 +08:00
|
|
|
if ((c->x86 == 0xf && c->x86_model >= 0x03) ||
|
|
|
|
(c->x86 == 0x6 && c->x86_model >= 0x0e))
|
|
|
|
set_bit(X86_FEATURE_CONSTANT_TSC, c->x86_capability);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2006-12-07 09:14:01 +08:00
|
|
|
if (cpu_has_ds) {
|
|
|
|
unsigned int l1;
|
|
|
|
rdmsr(MSR_IA32_MISC_ENABLE, l1, l2);
|
2006-12-07 09:14:11 +08:00
|
|
|
if (!(l1 & (1<<11)))
|
|
|
|
set_bit(X86_FEATURE_BTS, c->x86_capability);
|
2006-12-07 09:14:01 +08:00
|
|
|
if (!(l1 & (1<<12)))
|
|
|
|
set_bit(X86_FEATURE_PEBS, c->x86_capability);
|
|
|
|
}
|
2008-01-30 20:31:09 +08:00
|
|
|
|
|
|
|
if (cpu_has_bts)
|
|
|
|
ds_init_intel(c);
|
2006-12-07 09:14:01 +08:00
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2006-09-26 16:52:36 +08:00
|
|
|
static unsigned int __cpuinit intel_size_cache(struct cpuinfo_x86 * c, unsigned int size)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
/* Intel PIII Tualatin. This comes in two flavours.
|
|
|
|
* One has 256kb of cache, the other 512. We have no way
|
|
|
|
* to determine which, so we use a boottime override
|
|
|
|
* for the 512kb model, and assume 256 otherwise.
|
|
|
|
*/
|
|
|
|
if ((c->x86 == 6) && (c->x86_model == 11) && (size == 0))
|
|
|
|
size = 256;
|
|
|
|
return size;
|
|
|
|
}
|
|
|
|
|
2006-03-23 18:59:33 +08:00
|
|
|
static struct cpu_dev intel_cpu_dev __cpuinitdata = {
|
2005-04-17 06:20:36 +08:00
|
|
|
.c_vendor = "Intel",
|
|
|
|
.c_ident = { "GenuineIntel" },
|
|
|
|
.c_models = {
|
|
|
|
{ .vendor = X86_VENDOR_INTEL, .family = 4, .model_names =
|
|
|
|
{
|
|
|
|
[0] = "486 DX-25/33",
|
|
|
|
[1] = "486 DX-50",
|
|
|
|
[2] = "486 SX",
|
|
|
|
[3] = "486 DX/2",
|
|
|
|
[4] = "486 SL",
|
|
|
|
[5] = "486 SX/2",
|
|
|
|
[7] = "486 DX/2-WB",
|
|
|
|
[8] = "486 DX/4",
|
|
|
|
[9] = "486 DX/4-WB"
|
|
|
|
}
|
|
|
|
},
|
|
|
|
{ .vendor = X86_VENDOR_INTEL, .family = 5, .model_names =
|
|
|
|
{
|
|
|
|
[0] = "Pentium 60/66 A-step",
|
|
|
|
[1] = "Pentium 60/66",
|
|
|
|
[2] = "Pentium 75 - 200",
|
|
|
|
[3] = "OverDrive PODP5V83",
|
|
|
|
[4] = "Pentium MMX",
|
|
|
|
[7] = "Mobile Pentium 75 - 200",
|
|
|
|
[8] = "Mobile Pentium MMX"
|
|
|
|
}
|
|
|
|
},
|
|
|
|
{ .vendor = X86_VENDOR_INTEL, .family = 6, .model_names =
|
|
|
|
{
|
|
|
|
[0] = "Pentium Pro A-step",
|
|
|
|
[1] = "Pentium Pro",
|
|
|
|
[3] = "Pentium II (Klamath)",
|
|
|
|
[4] = "Pentium II (Deschutes)",
|
|
|
|
[5] = "Pentium II (Deschutes)",
|
|
|
|
[6] = "Mobile Pentium II",
|
|
|
|
[7] = "Pentium III (Katmai)",
|
|
|
|
[8] = "Pentium III (Coppermine)",
|
|
|
|
[10] = "Pentium III (Cascades)",
|
|
|
|
[11] = "Pentium III (Tualatin)",
|
|
|
|
}
|
|
|
|
},
|
|
|
|
{ .vendor = X86_VENDOR_INTEL, .family = 15, .model_names =
|
|
|
|
{
|
|
|
|
[0] = "Pentium 4 (Unknown)",
|
|
|
|
[1] = "Pentium 4 (Willamette)",
|
|
|
|
[2] = "Pentium 4 (Northwood)",
|
|
|
|
[4] = "Pentium 4 (Foster)",
|
|
|
|
[5] = "Pentium 4 (Foster)",
|
|
|
|
}
|
|
|
|
},
|
|
|
|
},
|
|
|
|
.c_init = init_intel,
|
|
|
|
.c_size_cache = intel_size_cache,
|
|
|
|
};
|
|
|
|
|
|
|
|
__init int intel_cpu_init(void)
|
|
|
|
{
|
|
|
|
cpu_devs[X86_VENDOR_INTEL] = &intel_cpu_dev;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2005-11-14 08:07:23 +08:00
|
|
|
#ifndef CONFIG_X86_CMPXCHG
|
|
|
|
unsigned long cmpxchg_386_u8(volatile void *ptr, u8 old, u8 new)
|
|
|
|
{
|
|
|
|
u8 prev;
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
/* Poor man's cmpxchg for 386. Unsuitable for SMP */
|
|
|
|
local_irq_save(flags);
|
|
|
|
prev = *(u8 *)ptr;
|
|
|
|
if (prev == old)
|
|
|
|
*(u8 *)ptr = new;
|
|
|
|
local_irq_restore(flags);
|
|
|
|
return prev;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(cmpxchg_386_u8);
|
|
|
|
|
|
|
|
unsigned long cmpxchg_386_u16(volatile void *ptr, u16 old, u16 new)
|
|
|
|
{
|
|
|
|
u16 prev;
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
/* Poor man's cmpxchg for 386. Unsuitable for SMP */
|
|
|
|
local_irq_save(flags);
|
|
|
|
prev = *(u16 *)ptr;
|
|
|
|
if (prev == old)
|
|
|
|
*(u16 *)ptr = new;
|
|
|
|
local_irq_restore(flags);
|
|
|
|
return prev;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(cmpxchg_386_u16);
|
|
|
|
|
|
|
|
unsigned long cmpxchg_386_u32(volatile void *ptr, u32 old, u32 new)
|
|
|
|
{
|
|
|
|
u32 prev;
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
/* Poor man's cmpxchg for 386. Unsuitable for SMP */
|
|
|
|
local_irq_save(flags);
|
|
|
|
prev = *(u32 *)ptr;
|
|
|
|
if (prev == old)
|
|
|
|
*(u32 *)ptr = new;
|
|
|
|
local_irq_restore(flags);
|
|
|
|
return prev;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(cmpxchg_386_u32);
|
|
|
|
#endif
|
|
|
|
|
x86: fall back on interrupt disable in cmpxchg8b on 80386 and 80486
Actually, on 386, cmpxchg and cmpxchg_local fall back on
cmpxchg_386_u8/16/32: it disables interruptions around non atomic
updates to mimic the cmpxchg behavior.
The comment:
/* Poor man's cmpxchg for 386. Unsuitable for SMP */
already present in cmpxchg_386_u32 tells much about how this cmpxchg
implementation should not be used in a SMP context. However, the cmpxchg_local
can perfectly use this fallback, since it only needs to be atomic wrt the local
cpu.
This patch adds a cmpxchg_486_u64 and uses it as a fallback for cmpxchg64
and cmpxchg64_local on 80386 and 80486.
Q:
but why is it called cmpxchg_486 when the other functions are called
A:
Because the standard cmpxchg is missing only on 386, but cmpxchg8b is
missing both on 386 and 486.
Citing Intel's Instruction set reference:
cmpxchg:
This instruction is not supported on Intel processors earlier than the
Intel486 processors.
cmpxchg8b:
This instruction encoding is not supported on Intel processors earlier
than the Pentium processors.
Q:
What's the reason to have cmpxchg64_local on 32 bit architectures?
Without that need all this would just be a few simple defines.
A:
cmpxchg64_local on 32 bits architectures takes unsigned long long
parameters, but cmpxchg_local only takes longs. Since we have cmpxchg8b
to execute a 8 byte cmpxchg atomically on pentium and +, it makes sense
to provide a flavor of cmpxchg and cmpxchg_local using this instruction.
Also, for 32 bits architectures lacking the 64 bits atomic cmpxchg, it
makes sense _not_ to define cmpxchg64 while cmpxchg could still be
available.
Moreover, the fallback for cmpxchg8b on i386 for 386 and 486 is a
However, cmpxchg64_local will be emulated by disabling interrupts on all
architectures where it is not supported atomically.
Therefore, we *could* turn cmpxchg64_local into a cmpxchg_local, but it
would make the 386/486 fallbacks ugly, make its design different from
cmpxchg/cmpxchg64 (which really depends on atomic operations and cannot
be emulated) and require the __cmpxchg_local to be expressed as a macro
rather than an inline function so the parameters would not be fixed to
unsigned long long in every case.
So I think cmpxchg64_local makes sense there, but I am open to
suggestions.
Q:
Are there any callers?
A:
I am actually using it in LTTng in my timestamping code. I use it to
work around CPUs with asynchronous TSCs. I need to update 64 bits
values atomically on this 32 bits architecture.
Changelog:
- Ran though checkpatch.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-01-30 20:30:47 +08:00
|
|
|
#ifndef CONFIG_X86_CMPXCHG64
|
|
|
|
unsigned long long cmpxchg_486_u64(volatile void *ptr, u64 old, u64 new)
|
|
|
|
{
|
|
|
|
u64 prev;
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
/* Poor man's cmpxchg8b for 386 and 486. Unsuitable for SMP */
|
|
|
|
local_irq_save(flags);
|
|
|
|
prev = *(u64 *)ptr;
|
|
|
|
if (prev == old)
|
|
|
|
*(u64 *)ptr = new;
|
|
|
|
local_irq_restore(flags);
|
|
|
|
return prev;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(cmpxchg_486_u64);
|
|
|
|
#endif
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
// arch_initcall(intel_cpu_init);
|
|
|
|
|