path: root/arch/x86/kernel/cpu/intel.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/init.h>
#include <linux/uaccess.h>

#include <asm/cpufeature.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

/*
 * Just in case our CPU detection goes bad, or you have a weird system,
 * allow a way to override the automatic disabling of MPX.
 */
static int forcempx;

static int __init forcempx_setup(char *__unused)
{
	forcempx = 1;

	return 1;
}
__setup("intel-skd-046-workaround=disable", forcempx_setup);

void check_mpx_erratum(struct cpuinfo_x86 *c)
{
	if (forcempx)
		return;
	/*
	 * Turn off the MPX feature on CPUs where SMEP is not
	 * available or disabled.
	 *
	 * Works around Intel Erratum SKD046: "Branch Instructions
	 * May Initialize MPX Bound Registers Incorrectly".
	 *
	 * This might falsely disable MPX on systems without
	 * SMEP, like Atom processors without SMEP.  But there
	 * is no such hardware known at the moment.
	 */
	if (cpu_has(c, X86_FEATURE_MPX) && !cpu_has(c, X86_FEATURE_SMEP)) {
		setup_clear_cpu_cap(X86_FEATURE_MPX);
		pr_warn("x86/mpx: Disabling MPX since SMEP not present\n");
	}
}

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) {
		pr_warn("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 */
		case 0x4a:	/* Merrifield */
			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)) {
			pr_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, boot_cpu_has(X86_FEATURE_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);
	}

	if (c->cpuid_level >= 0x00000001) {
		u32 eax, ebx, ecx, edx;

		cpuid(0x00000001, &eax, &ebx, &ecx, &edx);
		/*
		 * If HTT (EDX[28]) is set EBX[16:23] contain the number of
		 * apicids which are reserved per package. Store the resulting
		 * shift value for the package management code.
		 */
		if (edx & (1U