mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-16 04:37:07 +07:00
b51ef52df7
MSR_IA32_ENERGY_PERF_BIAS is lost after suspend/resume: x86_energy_perf_policy -r before cpu0: 0x0000000000000006 cpu1: 0x0000000000000006 cpu2: 0x0000000000000006 cpu3: 0x0000000000000006 cpu4: 0x0000000000000006 cpu5: 0x0000000000000006 cpu6: 0x0000000000000006 cpu7: 0x0000000000000006 after cpu0: 0x0000000000000000 cpu1: 0x0000000000000006 cpu2: 0x0000000000000006 cpu3: 0x0000000000000006 cpu4: 0x0000000000000006 cpu5: 0x0000000000000006 cpu6: 0x0000000000000006 cpu7: 0x0000000000000006 Resulting in inconsistent energy policy settings across CPUs. This register is set via init_intel() at bootup. During resume, the secondary CPUs are brought online again and init_intel() is callled which re-initializes the register. The boot CPU however never reinitializes the register. Add a syscore callback to reinitialize the register for the boot CPU. Signed-off-by: Laura Abbott <labbott@fedoraproject.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1437428878-4105-1-git-send-email-labbott@fedoraproject.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
772 lines
22 KiB
C
772 lines
22 KiB
C
#include <linux/kernel.h>
|
|
|
|
#include <linux/string.h>
|
|
#include <linux/bitops.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/thread_info.h>
|
|
#include <linux/module.h>
|
|
#include <linux/uaccess.h>
|
|
|
|
#include <asm/processor.h>
|
|
#include <asm/pgtable.h>
|
|
#include <asm/msr.h>
|
|
#include <asm/bugs.h>
|
|
#include <asm/cpu.h>
|
|
|
|
#ifdef CONFIG_X86_64
|
|
#include <linux/topology.h>
|
|
#endif
|
|
|
|
#include "cpu.h"
|
|
|
|
#ifdef CONFIG_X86_LOCAL_APIC
|
|
#include <asm/mpspec.h>
|
|
#include <asm/apic.h>
|
|
#endif
|
|
|
|
static void early_init_intel(struct cpuinfo_x86 *c)
|
|
{
|
|
u64 misc_enable;
|
|
|
|
/* Unmask CPUID levels if masked: */
|
|
if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) {
|
|
if (msr_clear_bit(MSR_IA32_MISC_ENABLE,
|
|
MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT) > 0) {
|
|
c->cpuid_level = cpuid_eax(0);
|
|
get_cpu_cap(c);
|
|
}
|
|
}
|
|
|
|
if ((c->x86 == 0xf && c->x86_model >= 0x03) ||
|
|
(c->x86 == 0x6 && c->x86_model >= 0x0e))
|
|
set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
|
|
|
|
if (c->x86 >= 6 && !cpu_has(c, X86_FEATURE_IA64)) {
|
|
unsigned lower_word;
|
|
|
|
wrmsr(MSR_IA32_UCODE_REV, 0, 0);
|
|
/* Required by the SDM */
|
|
sync_core();
|
|
rdmsr(MSR_IA32_UCODE_REV, lower_word, c->microcode);
|
|
}
|
|
|
|
/*
|
|
* Atom erratum AAE44/AAF40/AAG38/AAH41:
|
|
*
|
|
* A race condition between speculative fetches and invalidating
|
|
* a large page. This is worked around in microcode, but we
|
|
* need the microcode to have already been loaded... so if it is
|
|
* not, recommend a BIOS update and disable large pages.
|
|
*/
|
|
if (c->x86 == 6 && c->x86_model == 0x1c && c->x86_mask <= 2 &&
|
|
c->microcode < 0x20e) {
|
|
printk(KERN_WARNING "Atom PSE erratum detected, BIOS microcode update recommended\n");
|
|
clear_cpu_cap(c, X86_FEATURE_PSE);
|
|
}
|
|
|
|
#ifdef CONFIG_X86_64
|
|
set_cpu_cap(c, X86_FEATURE_SYSENTER32);
|
|
#else
|
|
/* 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;
|
|
#endif
|
|
|
|
/* CPUID workaround for 0F33/0F34 CPU */
|
|
if (c->x86 == 0xF && c->x86_model == 0x3
|
|
&& (c->x86_mask == 0x3 || c->x86_mask == 0x4))
|
|
c->x86_phys_bits = 36;
|
|
|
|
/*
|
|
* c->x86_power is 8000_0007 edx. Bit 8 is TSC runs at constant rate
|
|
* with P/T states and does not stop in deep C-states.
|
|
*
|
|
* It is also reliable across cores and sockets. (but not across
|
|
* cabinets - we turn it off in that case explicitly.)
|
|
*/
|
|
if (c->x86_power & (1 << 8)) {
|
|
set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
|
|
set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
|
|
if (!check_tsc_unstable())
|
|
set_sched_clock_stable();
|
|
}
|
|
|
|
/* Penwell and Cloverview have the TSC which doesn't sleep on S3 */
|
|
if (c->x86 == 6) {
|
|
switch (c->x86_model) {
|
|
case 0x27: /* Penwell */
|
|
case 0x35: /* Cloverview */
|
|
set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC_S3);
|
|
break;
|
|
default:
|
|
break;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* There is a known erratum on Pentium III and Core Solo
|
|
* and Core Duo CPUs.
|
|
* " Page with PAT set to WC while associated MTRR is UC
|
|
* may consolidate to UC "
|
|
* Because of this erratum, it is better to stick with
|
|
* setting WC in MTRR rather than using PAT on these CPUs.
|
|
*
|
|
* Enable PAT WC only on P4, Core 2 or later CPUs.
|
|
*/
|
|
if (c->x86 == 6 && c->x86_model < 15)
|
|
clear_cpu_cap(c, X86_FEATURE_PAT);
|
|
|
|
#ifdef CONFIG_KMEMCHECK
|
|
/*
|
|
* P4s have a "fast strings" feature which causes single-
|
|
* stepping REP instructions to only generate a #DB on
|
|
* cache-line boundaries.
|
|
*
|
|
* Ingo Molnar reported a Pentium D (model 6) and a Xeon
|
|
* (model 2) with the same problem.
|
|
*/
|
|
if (c->x86 == 15)
|
|
if (msr_clear_bit(MSR_IA32_MISC_ENABLE,
|
|
MSR_IA32_MISC_ENABLE_FAST_STRING_BIT) > 0)
|
|
pr_info("kmemcheck: Disabling fast string operations\n");
|
|
#endif
|
|
|
|
/*
|
|
* If fast string is not enabled in IA32_MISC_ENABLE for any reason,
|
|
* clear the fast string and enhanced fast string CPU capabilities.
|
|
*/
|
|
if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) {
|
|
rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
|
|
if (!(misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING)) {
|
|
printk(KERN_INFO "Disabled fast string operations\n");
|
|
setup_clear_cpu_cap(X86_FEATURE_REP_GOOD);
|
|
setup_clear_cpu_cap(X86_FEATURE_ERMS);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Intel Quark Core DevMan_001.pdf section 6.4.11
|
|
* "The operating system also is required to invalidate (i.e., flush)
|
|
* the TLB when any changes are made to any of the page table entries.
|
|
* The operating system must reload CR3 to cause the TLB to be flushed"
|
|
*
|
|
* As a result cpu_has_pge() in arch/x86/include/asm/tlbflush.h should
|
|
* be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE
|
|
* to be modified
|
|
*/
|
|
if (c->x86 == 5 && c->x86_model == 9) {
|
|
pr_info("Disabling PGE capability bit\n");
|
|
setup_clear_cpu_cap(X86_FEATURE_PGE);
|
|
}
|
|
}
|
|
|
|
#ifdef CONFIG_X86_32
|
|
/*
|
|
* Early probe support logic for ppro memory erratum #50
|
|
*
|
|
* This is called before we do cpu ident work
|
|
*/
|
|
|
|
int ppro_with_ram_bug(void)
|
|
{
|
|
/* 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;
|
|
}
|
|
|
|
static void intel_smp_check(struct cpuinfo_x86 *c)
|
|
{
|
|
/* calling is from identify_secondary_cpu() ? */
|
|
if (!c->cpu_index)
|
|
return;
|
|
|
|
/*
|
|
* Mask B, Pentium, but not Pentium MMX
|
|
*/
|
|
if (c->x86 == 5 &&
|
|
c->x86_mask >= 1 && c->x86_mask <= 4 &&
|
|
c->x86_model <= 3) {
|
|
/*
|
|
* Remember we have B step Pentia with bugs
|
|
*/
|
|
WARN_ONCE(1, "WARNING: SMP operation may be unreliable"
|
|
"with B stepping processors.\n");
|
|
}
|
|
}
|
|
|
|
static int forcepae;
|
|
static int __init forcepae_setup(char *__unused)
|
|
{
|
|
forcepae = 1;
|
|
return 1;
|
|
}
|
|
__setup("forcepae", forcepae_setup);
|
|
|
|
static void intel_workarounds(struct cpuinfo_x86 *c)
|
|
{
|
|
#ifdef CONFIG_X86_F00F_BUG
|
|
/*
|
|
* All models of Pentium and Pentium with MMX technology CPUs
|
|
* have the F0 0F bug, which lets nonprivileged users lock up the
|
|
* system. Announce that the fault handler will be checking for it.
|
|
* The Quark is also family 5, but does not have the same bug.
|
|
*/
|
|
clear_cpu_bug(c, X86_BUG_F00F);
|
|
if (!paravirt_enabled() && c->x86 == 5 && c->x86_model < 9) {
|
|
static int f00f_workaround_enabled;
|
|
|
|
set_cpu_bug(c, X86_BUG_F00F);
|
|
if (!f00f_workaround_enabled) {
|
|
printk(KERN_NOTICE "Intel Pentium with F0 0F bug - workaround enabled.\n");
|
|
f00f_workaround_enabled = 1;
|
|
}
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* 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_cpu_cap(c, X86_FEATURE_SEP);
|
|
|
|
/*
|
|
* PAE CPUID issue: many Pentium M report no PAE but may have a
|
|
* functionally usable PAE implementation.
|
|
* Forcefully enable PAE if kernel parameter "forcepae" is present.
|
|
*/
|
|
if (forcepae) {
|
|
printk(KERN_WARNING "PAE forced!\n");
|
|
set_cpu_cap(c, X86_FEATURE_PAE);
|
|
add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_NOW_UNRELIABLE);
|
|
}
|
|
|
|
/*
|
|
* P4 Xeon errata 037 workaround.
|
|
* Hardware prefetcher may cause stale data to be loaded into the cache.
|
|
*/
|
|
if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_mask == 1)) {
|
|
if (msr_set_bit(MSR_IA32_MISC_ENABLE,
|
|
MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT)
|
|
> 0) {
|
|
pr_info("CPU: C0 stepping P4 Xeon detected.\n");
|
|
pr_info("CPU: Disabling hardware prefetching (Errata 037)\n");
|
|
}
|
|
}
|
|
|
|
/*
|
|
* See if we have a good local APIC by checking for buggy Pentia,
|
|
* i.e. all B steppings and the C2 stepping of P54C when using their
|
|
* integrated APIC (see 11AP erratum in "Pentium Processor
|
|
* Specification Update").
|
|
*/
|
|
if (cpu_has_apic && (c->x86<<8 | c->x86_model<<4) == 0x520 &&
|
|
(c->x86_mask < 0x6 || c->x86_mask == 0xb))
|
|
set_cpu_bug(c, X86_BUG_11AP);
|
|
|
|
|
|
#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
|
|
|
|
intel_smp_check(c);
|
|
}
|
|
#else
|
|
static void intel_workarounds(struct cpuinfo_x86 *c)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
static void srat_detect_node(struct cpuinfo_x86 *c)
|
|
{
|
|
#ifdef CONFIG_NUMA
|
|
unsigned node;
|
|
int cpu = smp_processor_id();
|
|
|
|
/* Don't do the funky fallback heuristics the AMD version employs
|
|
for now. */
|
|
node = numa_cpu_node(cpu);
|
|
if (node == NUMA_NO_NODE || !node_online(node)) {
|
|
/* reuse the value from init_cpu_to_node() */
|
|
node = cpu_to_node(cpu);
|
|
}
|
|
numa_set_node(cpu, node);
|
|
#endif
|
|
}
|
|
|
|
/*
|
|
* find out the number of processor cores on the die
|
|
*/
|
|
static int intel_num_cpu_cores(struct cpuinfo_x86 *c)
|
|
{
|
|
unsigned int eax, ebx, ecx, edx;
|
|
|
|
if (c->cpuid_level < 4)
|
|
return 1;
|
|
|
|
/* Intel has a non-standard dependency on %ecx for this CPUID level. */
|
|
cpuid_count(4, 0, &eax, &ebx, &ecx, &edx);
|
|
if (eax & 0x1f)
|
|
return (eax >> 26) + 1;
|
|
else
|
|
return 1;
|
|
}
|
|
|
|
static void detect_vmx_virtcap(struct cpuinfo_x86 *c)
|
|
{
|
|
/* Intel VMX MSR indicated features */
|
|
#define X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW 0x00200000
|
|
#define X86_VMX_FEATURE_PROC_CTLS_VNMI 0x00400000
|
|
#define X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS 0x80000000
|
|
#define X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC 0x00000001
|
|
#define X86_VMX_FEATURE_PROC_CTLS2_EPT 0x00000002
|
|
#define X86_VMX_FEATURE_PROC_CTLS2_VPID 0x00000020
|
|
|
|
u32 vmx_msr_low, vmx_msr_high, msr_ctl, msr_ctl2;
|
|
|
|
clear_cpu_cap(c, X86_FEATURE_TPR_SHADOW);
|
|
clear_cpu_cap(c, X86_FEATURE_VNMI);
|
|
clear_cpu_cap(c, X86_FEATURE_FLEXPRIORITY);
|
|
clear_cpu_cap(c, X86_FEATURE_EPT);
|
|
clear_cpu_cap(c, X86_FEATURE_VPID);
|
|
|
|
rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, vmx_msr_low, vmx_msr_high);
|
|
msr_ctl = vmx_msr_high | vmx_msr_low;
|
|
if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW)
|
|
set_cpu_cap(c, X86_FEATURE_TPR_SHADOW);
|
|
if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_VNMI)
|
|
set_cpu_cap(c, X86_FEATURE_VNMI);
|
|
if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS) {
|
|
rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2,
|
|
vmx_msr_low, vmx_msr_high);
|
|
msr_ctl2 = vmx_msr_high | vmx_msr_low;
|
|
if ((msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC) &&
|
|
(msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW))
|
|
set_cpu_cap(c, X86_FEATURE_FLEXPRIORITY);
|
|
if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT)
|
|
set_cpu_cap(c, X86_FEATURE_EPT);
|
|
if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VPID)
|
|
set_cpu_cap(c, X86_FEATURE_VPID);
|
|
}
|
|
}
|
|
|
|
static void init_intel_energy_perf(struct cpuinfo_x86 *c)
|
|
{
|
|
u64 epb;
|
|
|
|
/*
|
|
* Initialize MSR_IA32_ENERGY_PERF_BIAS if not already initialized.
|
|
* (x86_energy_perf_policy(8) is available to change it at run-time.)
|
|
*/
|
|
if (!cpu_has(c, X86_FEATURE_EPB))
|
|
return;
|
|
|
|
rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
|
|
if ((epb & 0xF) != ENERGY_PERF_BIAS_PERFORMANCE)
|
|
return;
|
|
|
|
pr_warn_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n");
|
|
pr_warn_once("ENERGY_PERF_BIAS: View and update with x86_energy_perf_policy(8)\n");
|
|
epb = (epb & ~0xF) | ENERGY_PERF_BIAS_NORMAL;
|
|
wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
|
|
}
|
|
|
|
static void intel_bsp_resume(struct cpuinfo_x86 *c)
|
|
{
|
|
/*
|
|
* MSR_IA32_ENERGY_PERF_BIAS is lost across suspend/resume,
|
|
* so reinitialize it properly like during bootup:
|
|
*/
|
|
init_intel_energy_perf(c);
|
|
}
|
|
|
|
static void init_intel(struct cpuinfo_x86 *c)
|
|
{
|
|
unsigned int l2 = 0;
|
|
|
|
early_init_intel(c);
|
|
|
|
intel_workarounds(c);
|
|
|
|
/*
|
|
* Detect the extended topology information if available. This
|
|
* will reinitialise the initial_apicid which will be used
|
|
* in init_intel_cacheinfo()
|
|
*/
|
|
detect_extended_topology(c);
|
|
|
|
if (!cpu_has(c, X86_FEATURE_XTOPOLOGY)) {
|
|
/*
|
|
* let's use the legacy cpuid vector 0x1 and 0x4 for topology
|
|
* detection.
|
|
*/
|
|
c->x86_max_cores = intel_num_cpu_cores(c);
|
|
#ifdef CONFIG_X86_32
|
|
detect_ht(c);
|
|
#endif
|
|
}
|
|
|
|
l2 = init_intel_cacheinfo(c);
|
|
|
|
/* Detect legacy cache sizes if init_intel_cacheinfo did not */
|
|
if (l2 == 0) {
|
|
cpu_detect_cache_sizes(c);
|
|
l2 = c->x86_cache_size;
|
|
}
|
|
|
|
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_xmm2)
|
|
set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
|
|
if (cpu_has_ds) {
|
|
unsigned int l1;
|
|
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 (c->x86 == 6 && cpu_has_clflush &&
|
|
(c->x86_model == 29 || c->x86_model == 46 || c->x86_model == 47))
|
|
set_cpu_bug(c, X86_BUG_CLFLUSH_MONITOR);
|
|
|
|
#ifdef CONFIG_X86_64
|
|
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);
|
|
#else
|
|
/*
|
|
* Names for the Pentium II/Celeron processors
|
|
* detectable only by also checking the cache size.
|
|
* Dixon is NOT a Celeron.
|
|
*/
|
|
if (c->x86 == 6) {
|
|
char *p = NULL;
|
|
|
|
switch (c->x86_model) {
|
|
case 5:
|
|
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);
|
|
}
|
|
|
|
if (c->x86 == 15)
|
|
set_cpu_cap(c, X86_FEATURE_P4);
|
|
if (c->x86 == 6)
|
|
set_cpu_cap(c, X86_FEATURE_P3);
|
|
#endif
|
|
|
|
/* Work around errata */
|
|
srat_detect_node(c);
|
|
|
|
if (cpu_has(c, X86_FEATURE_VMX))
|
|
detect_vmx_virtcap(c);
|
|
|
|
init_intel_energy_perf(c);
|
|
}
|
|
|
|
#ifdef CONFIG_X86_32
|
|
static unsigned int intel_size_cache(struct cpuinfo_x86 *c, unsigned int size)
|
|
{
|
|
/*
|
|
* 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;
|
|
|
|
/*
|
|
* Intel Quark SoC X1000 contains a 4-way set associative
|
|
* 16K cache with a 16 byte cache line and 256 lines per tag
|
|
*/
|
|
if ((c->x86 == 5) && (c->x86_model == 9))
|
|
size = 16;
|
|
return size;
|
|
}
|
|
#endif
|
|
|
|
#define TLB_INST_4K 0x01
|
|
#define TLB_INST_4M 0x02
|
|
#define TLB_INST_2M_4M 0x03
|
|
|
|
#define TLB_INST_ALL 0x05
|
|
#define TLB_INST_1G 0x06
|
|
|
|
#define TLB_DATA_4K 0x11
|
|
#define TLB_DATA_4M 0x12
|
|
#define TLB_DATA_2M_4M 0x13
|
|
#define TLB_DATA_4K_4M 0x14
|
|
|
|
#define TLB_DATA_1G 0x16
|
|
|
|
#define TLB_DATA0_4K 0x21
|
|
#define TLB_DATA0_4M 0x22
|
|
#define TLB_DATA0_2M_4M 0x23
|
|
|
|
#define STLB_4K 0x41
|
|
#define STLB_4K_2M 0x42
|
|
|
|
static const struct _tlb_table intel_tlb_table[] = {
|
|
{ 0x01, TLB_INST_4K, 32, " TLB_INST 4 KByte pages, 4-way set associative" },
|
|
{ 0x02, TLB_INST_4M, 2, " TLB_INST 4 MByte pages, full associative" },
|
|
{ 0x03, TLB_DATA_4K, 64, " TLB_DATA 4 KByte pages, 4-way set associative" },
|
|
{ 0x04, TLB_DATA_4M, 8, " TLB_DATA 4 MByte pages, 4-way set associative" },
|
|
{ 0x05, TLB_DATA_4M, 32, " TLB_DATA 4 MByte pages, 4-way set associative" },
|
|
{ 0x0b, TLB_INST_4M, 4, " TLB_INST 4 MByte pages, 4-way set associative" },
|
|
{ 0x4f, TLB_INST_4K, 32, " TLB_INST 4 KByte pages */" },
|
|
{ 0x50, TLB_INST_ALL, 64, " TLB_INST 4 KByte and 2-MByte or 4-MByte pages" },
|
|
{ 0x51, TLB_INST_ALL, 128, " TLB_INST 4 KByte and 2-MByte or 4-MByte pages" },
|
|
{ 0x52, TLB_INST_ALL, 256, " TLB_INST 4 KByte and 2-MByte or 4-MByte pages" },
|
|
{ 0x55, TLB_INST_2M_4M, 7, " TLB_INST 2-MByte or 4-MByte pages, fully associative" },
|
|
{ 0x56, TLB_DATA0_4M, 16, " TLB_DATA0 4 MByte pages, 4-way set associative" },
|
|
{ 0x57, TLB_DATA0_4K, 16, " TLB_DATA0 4 KByte pages, 4-way associative" },
|
|
{ 0x59, TLB_DATA0_4K, 16, " TLB_DATA0 4 KByte pages, fully associative" },
|
|
{ 0x5a, TLB_DATA0_2M_4M, 32, " TLB_DATA0 2-MByte or 4 MByte pages, 4-way set associative" },
|
|
{ 0x5b, TLB_DATA_4K_4M, 64, " TLB_DATA 4 KByte and 4 MByte pages" },
|
|
{ 0x5c, TLB_DATA_4K_4M, 128, " TLB_DATA 4 KByte and 4 MByte pages" },
|
|
{ 0x5d, TLB_DATA_4K_4M, 256, " TLB_DATA 4 KByte and 4 MByte pages" },
|
|
{ 0x61, TLB_INST_4K, 48, " TLB_INST 4 KByte pages, full associative" },
|
|
{ 0x63, TLB_DATA_1G, 4, " TLB_DATA 1 GByte pages, 4-way set associative" },
|
|
{ 0x76, TLB_INST_2M_4M, 8, " TLB_INST 2-MByte or 4-MByte pages, fully associative" },
|
|
{ 0xb0, TLB_INST_4K, 128, " TLB_INST 4 KByte pages, 4-way set associative" },
|
|
{ 0xb1, TLB_INST_2M_4M, 4, " TLB_INST 2M pages, 4-way, 8 entries or 4M pages, 4-way entries" },
|
|
{ 0xb2, TLB_INST_4K, 64, " TLB_INST 4KByte pages, 4-way set associative" },
|
|
{ 0xb3, TLB_DATA_4K, 128, " TLB_DATA 4 KByte pages, 4-way set associative" },
|
|
{ 0xb4, TLB_DATA_4K, 256, " TLB_DATA 4 KByte pages, 4-way associative" },
|
|
{ 0xb5, TLB_INST_4K, 64, " TLB_INST 4 KByte pages, 8-way set associative" },
|
|
{ 0xb6, TLB_INST_4K, 128, " TLB_INST 4 KByte pages, 8-way set associative" },
|
|
{ 0xba, TLB_DATA_4K, 64, " TLB_DATA 4 KByte pages, 4-way associative" },
|
|
{ 0xc0, TLB_DATA_4K_4M, 8, " TLB_DATA 4 KByte and 4 MByte pages, 4-way associative" },
|
|
{ 0xc1, STLB_4K_2M, 1024, " STLB 4 KByte and 2 MByte pages, 8-way associative" },
|
|
{ 0xc2, TLB_DATA_2M_4M, 16, " DTLB 2 MByte/4MByte pages, 4-way associative" },
|
|
{ 0xca, STLB_4K, 512, " STLB 4 KByte pages, 4-way associative" },
|
|
{ 0x00, 0, 0 }
|
|
};
|
|
|
|
static void intel_tlb_lookup(const unsigned char desc)
|
|
{
|
|
unsigned char k;
|
|
if (desc == 0)
|
|
return;
|
|
|
|
/* look up this descriptor in the table */
|
|
for (k = 0; intel_tlb_table[k].descriptor != desc && \
|
|
intel_tlb_table[k].descriptor != 0; k++)
|
|
;
|
|
|
|
if (intel_tlb_table[k].tlb_type == 0)
|
|
return;
|
|
|
|
switch (intel_tlb_table[k].tlb_type) {
|
|
case STLB_4K:
|
|
if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
|
|
tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
|
|
if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
|
|
tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
|
|
break;
|
|
case STLB_4K_2M:
|
|
if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
|
|
tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
|
|
if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
|
|
tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
|
|
if (tlb_lli_2m[ENTRIES] < intel_tlb_table[k].entries)
|
|
tlb_lli_2m[ENTRIES] = intel_tlb_table[k].entries;
|
|
if (tlb_lld_2m[ENTRIES] < intel_tlb_table[k].entries)
|
|
tlb_lld_2m[ENTRIES] = intel_tlb_table[k].entries;
|
|
if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
|
|
tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
|
|
if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
|
|
tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
|
|
break;
|
|
case TLB_INST_ALL:
|
|
if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
|
|
tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
|
|
if (tlb_lli_2m[ENTRIES] < intel_tlb_table[k].entries)
|
|
tlb_lli_2m[ENTRIES] = intel_tlb_table[k].entries;
|
|
if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
|
|
tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
|
|
break;
|
|
case TLB_INST_4K:
|
|
if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
|
|
tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
|
|
break;
|
|
case TLB_INST_4M:
|
|
if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
|
|
tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
|
|
break;
|
|
case TLB_INST_2M_4M:
|
|
if (tlb_lli_2m[ENTRIES] < intel_tlb_table[k].entries)
|
|
tlb_lli_2m[ENTRIES] = intel_tlb_table[k].entries;
|
|
if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
|
|
tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
|
|
break;
|
|
case TLB_DATA_4K:
|
|
case TLB_DATA0_4K:
|
|
if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
|
|
tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
|
|
break;
|
|
case TLB_DATA_4M:
|
|
case TLB_DATA0_4M:
|
|
if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
|
|
tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
|
|
break;
|
|
case TLB_DATA_2M_4M:
|
|
case TLB_DATA0_2M_4M:
|
|
if (tlb_lld_2m[ENTRIES] < intel_tlb_table[k].entries)
|
|
tlb_lld_2m[ENTRIES] = intel_tlb_table[k].entries;
|
|
if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
|
|
tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
|
|
break;
|
|
case TLB_DATA_4K_4M:
|
|
if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
|
|
tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
|
|
if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
|
|
tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
|
|
break;
|
|
case TLB_DATA_1G:
|
|
if (tlb_lld_1g[ENTRIES] < intel_tlb_table[k].entries)
|
|
tlb_lld_1g[ENTRIES] = intel_tlb_table[k].entries;
|
|
break;
|
|
}
|
|
}
|
|
|
|
static void intel_detect_tlb(struct cpuinfo_x86 *c)
|
|
{
|
|
int i, j, n;
|
|
unsigned int regs[4];
|
|
unsigned char *desc = (unsigned char *)regs;
|
|
|
|
if (c->cpuid_level < 2)
|
|
return;
|
|
|
|
/* Number of times to iterate */
|
|
n = cpuid_eax(2) & 0xFF;
|
|
|
|
for (i = 0 ; i < n ; i++) {
|
|
cpuid(2, ®s[0], ®s[1], ®s[2], ®s[3]);
|
|
|
|
/* If bit 31 is set, this is an unknown format */
|
|
for (j = 0 ; j < 3 ; j++)
|
|
if (regs[j] & (1 << 31))
|
|
regs[j] = 0;
|
|
|
|
/* Byte 0 is level count, not a descriptor */
|
|
for (j = 1 ; j < 16 ; j++)
|
|
intel_tlb_lookup(desc[j]);
|
|
}
|
|
}
|
|
|
|
static const struct cpu_dev intel_cpu_dev = {
|
|
.c_vendor = "Intel",
|
|
.c_ident = { "GenuineIntel" },
|
|
#ifdef CONFIG_X86_32
|
|
.legacy_models = {
|
|
{ .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"
|
|
}
|
|
},
|
|
{ .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",
|
|
[9] = "Quark SoC X1000",
|
|
}
|
|
},
|
|
{ .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)",
|
|
}
|
|
},
|
|
{ .family = 15, .model_names =
|
|
{
|
|
[0] = "Pentium 4 (Unknown)",
|
|
[1] = "Pentium 4 (Willamette)",
|
|
[2] = "Pentium 4 (Northwood)",
|
|
[4] = "Pentium 4 (Foster)",
|
|
[5] = "Pentium 4 (Foster)",
|
|
}
|
|
},
|
|
},
|
|
.legacy_cache_size = intel_size_cache,
|
|
#endif
|
|
.c_detect_tlb = intel_detect_tlb,
|
|
.c_early_init = early_init_intel,
|
|
.c_init = init_intel,
|
|
.c_bsp_resume = intel_bsp_resume,
|
|
.c_x86_vendor = X86_VENDOR_INTEL,
|
|
};
|
|
|
|
cpu_dev_register(intel_cpu_dev);
|
|
|