KVM: expose latest Intel cpu new features (BMI1/BMI2/FMA/AVX2) to guest

[mirror_ubuntu-bionic-kernel.git] / arch / x86 / kvm / cpuid.c

/*
 * Kernel-based Virtual Machine driver for Linux
 * cpuid support routines
 *
 * derived from arch/x86/kvm/x86.c
 *
 * Copyright 2011 Red Hat, Inc. and/or its affiliates.
 * Copyright IBM Corporation, 2008
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 */

#include <linux/kvm_host.h>
#include <linux/module.h>
#include <asm/user.h>
#include <asm/xsave.h>
#include "cpuid.h"
#include "lapic.h"
#include "mmu.h"
#include "trace.h"

void kvm_update_cpuid(struct kvm_vcpu *vcpu)
{
	struct kvm_cpuid_entry2 *best;
	struct kvm_lapic *apic = vcpu->arch.apic;

	best = kvm_find_cpuid_entry(vcpu, 1, 0);
	if (!best)
		return;

	/* Update OSXSAVE bit */
	if (cpu_has_xsave && best->function == 0x1) {
		best->ecx &= ~(bit(X86_FEATURE_OSXSAVE));
		if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE))
			best->ecx |= bit(X86_FEATURE_OSXSAVE);
	}

	if (apic) {
		if (best->ecx & bit(X86_FEATURE_TSC_DEADLINE_TIMER))
			apic->lapic_timer.timer_mode_mask = 3 << 17;
		else
			apic->lapic_timer.timer_mode_mask = 1 << 17;
	}
}

static int is_efer_nx(void)
{
	unsigned long long efer = 0;

	rdmsrl_safe(MSR_EFER, &efer);
	return efer & EFER_NX;
}

static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu)
{
	int i;
	struct kvm_cpuid_entry2 *e, *entry;

	entry = NULL;
	for (i = 0; i < vcpu->arch.cpuid_nent; ++i) {
		e = &vcpu->arch.cpuid_entries[i];
		if (e->function == 0x80000001) {
			entry = e;
			break;
		}
	}
	if (entry && (entry->edx & (1 << 20)) && !is_efer_nx()) {
		entry->edx &= ~(1 << 20);
		printk(KERN_INFO "kvm: guest NX capability removed\n");
	}
}

/* when an old userspace process fills a new kernel module */
int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
			     struct kvm_cpuid *cpuid,
			     struct kvm_cpuid_entry __user *entries)
{
	int r, i;
	struct kvm_cpuid_entry *cpuid_entries;

	r = -E2BIG;
	if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
		goto out;
	r = -ENOMEM;
	cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry) * cpuid->nent);
	if (!cpuid_entries)
		goto out;
	r = -EFAULT;
	if (copy_from_user(cpuid_entries, entries,
			   cpuid->nent * sizeof(struct kvm_cpuid_entry)))
		goto out_free;
	for (i = 0; i < cpuid->nent; i++) {
		vcpu->arch.cpuid_entries[i].function = cpuid_entries[i].function;
		vcpu->arch.cpuid_entries[i].eax = cpuid_entries[i].eax;
		vcpu->arch.cpuid_entries[i].ebx = cpuid_entries[i].ebx;
		vcpu->arch.cpuid_entries[i].ecx = cpuid_entries[i].ecx;
		vcpu->arch.cpuid_entries[i].edx = cpuid_entries[i].edx;
		vcpu->arch.cpuid_entries[i].index = 0;
		vcpu->arch.cpuid_entries[i].flags = 0;
		vcpu->arch.cpuid_entries[i].padding[0] = 0;
		vcpu->arch.cpuid_entries[i].padding[1] = 0;
		vcpu->arch.cpuid_entries[i].padding[2] = 0;
	}
	vcpu->arch.cpuid_nent = cpuid->nent;
	cpuid_fix_nx_cap(vcpu);
	r = 0;
	kvm_apic_set_version(vcpu);
	kvm_x86_ops->cpuid_update(vcpu);
	kvm_update_cpuid(vcpu);

out_free:
	vfree(cpuid_entries);
out:
	return r;
}

int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu,
			      struct kvm_cpuid2 *cpuid,
			      struct kvm_cpuid_entry2 __user *entries)
{
	int r;

	r = -E2BIG;
	if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
		goto out;
	r = -EFAULT;
	if (copy_from_user(&vcpu->arch.cpuid_entries, entries,
			   cpuid->nent * sizeof(struct kvm_cpuid_entry2)))
		goto out;
	vcpu->arch.cpuid_nent = cpuid->nent;
	kvm_apic_set_version(vcpu);
	kvm_x86_ops->cpuid_update(vcpu);
	kvm_update_cpuid(vcpu);
	return 0;

out:
	return r;
}

int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu,
			      struct kvm_cpuid2 *cpuid,
			      struct kvm_cpuid_entry2 __user *entries)
{
	int r;

	r = -E2BIG;
	if (cpuid->nent < vcpu->arch.cpuid_nent)
		goto out;
	r = -EFAULT;
	if (copy_to_user(entries, &vcpu->arch.cpuid_entries,
			 vcpu->arch.cpuid_nent * sizeof(struct kvm_cpuid_entry2)))
		goto out;
	return 0;

out:
	cpuid->nent = vcpu->arch.cpuid_nent;
	return r;
}

static void cpuid_mask(u32 *word, int wordnum)
{
	*word &= boot_cpu_data.x86_capability[wordnum];
}

static void do_cpuid_1_ent(struct kvm_cpuid_entry2 *entry, u32 function,
			   u32 index)
{
	entry->function = function;
	entry->index = index;
	cpuid_count(entry->function, entry->index,
		    &entry->eax, &entry->ebx, &entry->ecx, &entry->edx);
	entry->flags = 0;
}

static bool supported_xcr0_bit(unsigned bit)
{
	u64 mask = ((u64)1 << bit);

	return mask & (XSTATE_FP | XSTATE_SSE | XSTATE_YMM) & host_xcr0;
}

#define F(x) bit(X86_FEATURE_##x)

static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
			 u32 index, int *nent, int maxnent)
{
	unsigned f_nx = is_efer_nx() ? F(NX) : 0;
#ifdef CONFIG_X86_64
	unsigned f_gbpages = (kvm_x86_ops->get_lpage_level() == PT_PDPE_LEVEL)
				? F(GBPAGES) : 0;
	unsigned f_lm = F(LM);
#else
	unsigned f_gbpages = 0;
	unsigned f_lm = 0;
#endif
	unsigned f_rdtscp = kvm_x86_ops->rdtscp_supported() ? F(RDTSCP) : 0;

	/* cpuid 1.edx */
	const u32 kvm_supported_word0_x86_features =
		F(FPU) | F(VME) | F(DE) | F(PSE) |
		F(TSC) | F(MSR) | F(PAE) | F(MCE) |
		F(CX8) | F(APIC) | 0 /* Reserved */ | F(SEP) |
		F(MTRR) | F(PGE) | F(MCA) | F(CMOV) |
		F(PAT) | F(PSE36) | 0 /* PSN */ | F(CLFLSH) |
		0 /* Reserved, DS, ACPI */ | F(MMX) |
		F(FXSR) | F(XMM) | F(XMM2) | F(SELFSNOOP) |
		0 /* HTT, TM, Reserved, PBE */;
	/* cpuid 0x80000001.edx */
	const u32 kvm_supported_word1_x86_features =
		F(FPU) | F(VME) | F(DE) | F(PSE) |
		F(TSC) | F(MSR) | F(PAE) | F(MCE) |
		F(CX8) | F(APIC) | 0 /* Reserved */ | F(SYSCALL) |
		F(MTRR) | F(PGE) | F(MCA) | F(CMOV) |
		F(PAT) | F(PSE36) | 0 /* Reserved */ |
		f_nx | 0 /* Reserved */ | F(MMXEXT) | F(MMX) |
		F(FXSR) | F(FXSR_OPT) | f_gbpages | f_rdtscp |
		0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW);
	/* cpuid 1.ecx */
	const u32 kvm_supported_word4_x86_features =
		F(XMM3) | F(PCLMULQDQ) | 0 /* DTES64, MONITOR */ |
		0 /* DS-CPL, VMX, SMX, EST */ |
		0 /* TM2 */ | F(SSSE3) | 0 /* CNXT-ID */ | 0 /* Reserved */ |
		F(FMA) | F(CX16) | 0 /* xTPR Update, PDCM */ |
		0 /* Reserved, DCA */ | F(XMM4_1) |
		F(XMM4_2) | F(X2APIC) | F(MOVBE) | F(POPCNT) |
		0 /* Reserved*/ | F(AES) | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX) |
		F(F16C) | F(RDRAND);
	/* cpuid 0x80000001.ecx */
	const u32 kvm_supported_word6_x86_features =
		F(LAHF_LM) | F(CMP_LEGACY) | 0 /*SVM*/ | 0 /* ExtApicSpace */ |
		F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) |
		F(3DNOWPREFETCH) | 0 /* OSVW */ | 0 /* IBS */ | F(XOP) |
		0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM);

	/* cpuid 0xC0000001.edx */
	const u32 kvm_supported_word5_x86_features =
		F(XSTORE) | F(XSTORE_EN) | F(XCRYPT) | F(XCRYPT_EN) |
		F(ACE2) | F(ACE2_EN) | F(PHE) | F(PHE_EN) |
		F(PMM) | F(PMM_EN);

	/* cpuid 7.0.ebx */
	const u32 kvm_supported_word9_x86_features =
		F(FSGSBASE) | F(BMI1) | F(AVX2) | F(SMEP) | F(BMI2) | F(ERMS);

	/* all calls to cpuid_count() should be made on the same cpu */
	get_cpu();
	do_cpuid_1_ent(entry, function, index);
	++*nent;

	switch (function) {
	case 0:
		entry->eax = min(entry->eax, (u32)0xd);
		break;
	case 1:
		entry->edx &= kvm_supported_word0_x86_features;
		cpuid_mask(&entry->edx, 0);
		entry->ecx &= kvm_supported_word4_x86_features;
		cpuid_mask(&entry->ecx, 4);
		/* we support x2apic emulation even if host does not support
		 * it since we emulate x2apic in software */
		entry->ecx |= F(X2APIC);
		break;
	/* function 2 entries are STATEFUL. That is, repeated cpuid commands
	 * may return different values. This forces us to get_cpu() before
	 * issuing the first command, and also to emulate this annoying behavior
	 * in kvm_emulate_cpuid() using KVM_CPUID_FLAG_STATE_READ_NEXT */
	case 2: {
		int t, times = entry->eax & 0xff;

		entry->flags |= KVM_CPUID_FLAG_STATEFUL_FUNC;
		entry->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
		for (t = 1; t < times && *nent < maxnent; ++t) {
			do_cpuid_1_ent(&entry[t], function, 0);
			entry[t].flags |= KVM_CPUID_FLAG_STATEFUL_FUNC;
			++*nent;
		}
		break;
	}
	/* function 4 has additional index. */
	case 4: {
		int i, cache_type;

		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
		/* read more entries until cache_type is zero */
		for (i = 1; *nent < maxnent; ++i) {
			cache_type = entry[i - 1].eax & 0x1f;
			if (!cache_type)
				break;
			do_cpuid_1_ent(&entry[i], function, i);
			entry[i].flags |=
			       KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
			++*nent;
		}
		break;
	}
	case 7: {
		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
		/* Mask ebx against host capbability word 9 */
		if (index == 0) {
			entry->ebx &= kvm_supported_word9_x86_features;
			cpuid_mask(&entry->ebx, 9);
		} else
			entry->ebx = 0;
		entry->eax = 0;
		entry->ecx = 0;
		entry->edx = 0;
		break;
	}
	case 9:
		break;
	/* function 0xb has additional index. */
	case 0xb: {
		int i, level_type;

		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
		/* read more entries until level_type is zero */
		for (i = 1; *nent < maxnent; ++i) {
			level_type = entry[i - 1].ecx & 0xff00;
			if (!level_type)
				break;
			do_cpuid_1_ent(&entry[i], function, i);
			entry[i].flags |=
			       KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
			++*nent;
		}
		break;
	}
	case 0xd: {
		int idx, i;

		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
		for (idx = 1, i = 1; *nent < maxnent && idx < 64; ++idx) {
			do_cpuid_1_ent(&entry[i], function, idx);
			if (entry[i].eax == 0 || !supported_xcr0_bit(idx))
				continue;
			entry[i].flags |=
			       KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
			++*nent;
			++i;
		}
		break;
	}
	case KVM_CPUID_SIGNATURE: {
		char signature[12] = "KVMKVMKVM\0\0";
		u32 *sigptr = (u32 *)signature;
		entry->eax = 0;
		entry->ebx = sigptr[0];
		entry->ecx = sigptr[1];
		entry->edx = sigptr[2];
		break;
	}
	case KVM_CPUID_FEATURES:
		entry->eax = (1 << KVM_FEATURE_CLOCKSOURCE) |
			     (1 << KVM_FEATURE_NOP_IO_DELAY) |
			     (1 << KVM_FEATURE_CLOCKSOURCE2) |
			     (1 << KVM_FEATURE_ASYNC_PF) |
			     (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT);

		if (sched_info_on())
			entry->eax |= (1 << KVM_FEATURE_STEAL_TIME);

		entry->ebx = 0;
		entry->ecx = 0;
		entry->edx = 0;
		break;
	case 0x80000000:
		entry->eax = min(entry->eax, 0x8000001a);
		break;
	case 0x80000001:
		entry->edx &= kvm_supported_word1_x86_features;
		cpuid_mask(&entry->edx, 1);
		entry->ecx &= kvm_supported_word6_x86_features;
		cpuid_mask(&entry->ecx, 6);
		break;
	case 0x80000008: {
		unsigned g_phys_as = (entry->eax >> 16) & 0xff;
		unsigned virt_as = max((entry->eax >> 8) & 0xff, 48U);
		unsigned phys_as = entry->eax & 0xff;

		if (!g_phys_as)
			g_phys_as = phys_as;
		entry->eax = g_phys_as | (virt_as << 8);
		entry->ebx = entry->edx = 0;
		break;
	}
	case 0x80000019:
		entry->ecx = entry->edx = 0;
		break;
	case 0x8000001a:
		break;
	case 0x8000001d:
		break;
	/*Add support for Centaur's CPUID instruction*/
	case 0xC0000000:
		/*Just support up to 0xC0000004 now*/
		entry->eax = min(entry->eax, 0xC0000004);
		break;
	case 0xC0000001:
		entry->edx &= kvm_supported_word5_x86_features;
		cpuid_mask(&entry->edx, 5);
		break;
	case 3: /* Processor serial number */
	case 5: /* MONITOR/MWAIT */
	case 6: /* Thermal management */
	case 0xA: /* Architectural Performance Monitoring */
	case 0x80000007: /* Advanced power management */
	case 0xC0000002:
	case 0xC0000003:
	case 0xC0000004:
	default:
		entry->eax = entry->ebx = entry->ecx = entry->edx = 0;
		break;
	}

	kvm_x86_ops->set_supported_cpuid(function, entry);

	put_cpu();
}

#undef F

int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
				      struct kvm_cpuid_entry2 __user *entries)
{
	struct kvm_cpuid_entry2 *cpuid_entries;
	int limit, nent = 0, r = -E2BIG;
	u32 func;

	if (cpuid->nent < 1)
		goto out;
	if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
		cpuid->nent = KVM_MAX_CPUID_ENTRIES;
	r = -ENOMEM;
	cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry2) * cpuid->nent);
	if (!cpuid_entries)
		goto out;

	do_cpuid_ent(&cpuid_entries[0], 0, 0, &nent, cpuid->nent);
	limit = cpuid_entries[0].eax;
	for (func = 1; func <= limit && nent < cpuid->nent; ++func)
		do_cpuid_ent(&cpuid_entries[nent], func, 0,
			     &nent, cpuid->nent);
	r = -E2BIG;
	if (nent >= cpuid->nent)
		goto out_free;

	do_cpuid_ent(&cpuid_entries[nent], 0x80000000, 0, &nent, cpuid->nent);
	limit = cpuid_entries[nent - 1].eax;
	for (func = 0x80000001; func <= limit && nent < cpuid->nent; ++func)
		do_cpuid_ent(&cpuid_entries[nent], func, 0,
			     &nent, cpuid->nent);



	r = -E2BIG;
	if (nent >= cpuid->nent)
		goto out_free;

	/* Add support for Centaur's CPUID instruction. */
	if (boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR) {
		do_cpuid_ent(&cpuid_entries[nent], 0xC0000000, 0,
				&nent, cpuid->nent);

		r = -E2BIG;
		if (nent >= cpuid->nent)
			goto out_free;

		limit = cpuid_entries[nent - 1].eax;
		for (func = 0xC0000001;
			func <= limit && nent < cpuid->nent; ++func)
			do_cpuid_ent(&cpuid_entries[nent], func, 0,
					&nent, cpuid->nent);

		r = -E2BIG;
		if (nent >= cpuid->nent)
			goto out_free;
	}

	do_cpuid_ent(&cpuid_entries[nent], KVM_CPUID_SIGNATURE, 0, &nent,
		     cpuid->nent);

	r = -E2BIG;
	if (nent >= cpuid->nent)
		goto out_free;

	do_cpuid_ent(&cpuid_entries[nent], KVM_CPUID_FEATURES, 0, &nent,
		     cpuid->nent);

	r = -E2BIG;
	if (nent >= cpuid->nent)
		goto out_free;

	r = -EFAULT;
	if (copy_to_user(entries, cpuid_entries,
			 nent * sizeof(struct kvm_cpuid_entry2)))
		goto out_free;
	cpuid->nent = nent;
	r = 0;

out_free:
	vfree(cpuid_entries);
out:
	return r;
}

static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i)
{
	struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i];
	int j, nent = vcpu->arch.cpuid_nent;

	e->flags &= ~KVM_CPUID_FLAG_STATE_READ_NEXT;
	/* when no next entry is found, the current entry[i] is reselected */
	for (j = i + 1; ; j = (j + 1) % nent) {
		struct kvm_cpuid_entry2 *ej = &vcpu->arch.cpuid_entries[j];
		if (ej->function == e->function) {
			ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
			return j;
		}
	}
	return 0; /* silence gcc, even though control never reaches here */
}

/* find an entry with matching function, matching index (if needed), and that
 * should be read next (if it's stateful) */
static int is_matching_cpuid_entry(struct kvm_cpuid_entry2 *e,
	u32 function, u32 index)
{
	if (e->function != function)
		return 0;
	if ((e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) && e->index != index)
		return 0;
	if ((e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC) &&
	    !(e->flags & KVM_CPUID_FLAG_STATE_READ_NEXT))
		return 0;
	return 1;
}

struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
					      u32 function, u32 index)
{
	int i;
	struct kvm_cpuid_entry2 *best = NULL;

	for (i = 0; i < vcpu->arch.cpuid_nent; ++i) {
		struct kvm_cpuid_entry2 *e;

		e = &vcpu->arch.cpuid_entries[i];
		if (is_matching_cpuid_entry(e, function, index)) {
			if (e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC)
				move_to_next_stateful_cpuid_entry(vcpu, i);
			best = e;
			break;
		}
	}
	return best;
}
EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry);

int cpuid_maxphyaddr(struct kvm_vcpu *vcpu)
{
	struct kvm_cpuid_entry2 *best;

	best = kvm_find_cpuid_entry(vcpu, 0x80000000, 0);
	if (!best || best->eax < 0x80000008)
		goto not_found;
	best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0);
	if (best)
		return best->eax & 0xff;
not_found:
	return 36;
}

/*
 * If no match is found, check whether we exceed the vCPU's limit
 * and return the content of the highest valid _standard_ leaf instead.
 * This is to satisfy the CPUID specification.
 */
static struct kvm_cpuid_entry2* check_cpuid_limit(struct kvm_vcpu *vcpu,
                                                  u32 function, u32 index)
{
	struct kvm_cpuid_entry2 *maxlevel;

	maxlevel = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0);
	if (!maxlevel || maxlevel->eax >= function)
		return NULL;
	if (function & 0x80000000) {
		maxlevel = kvm_find_cpuid_entry(vcpu, 0, 0);
		if (!maxlevel)
			return NULL;
	}
	return kvm_find_cpuid_entry(vcpu, maxlevel->eax, index);
}

void kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
{
	u32 function, index;
	struct kvm_cpuid_entry2 *best;

	function = kvm_register_read(vcpu, VCPU_REGS_RAX);
	index = kvm_register_read(vcpu, VCPU_REGS_RCX);
	kvm_register_write(vcpu, VCPU_REGS_RAX, 0);
	kvm_register_write(vcpu, VCPU_REGS_RBX, 0);
	kvm_register_write(vcpu, VCPU_REGS_RCX, 0);
	kvm_register_write(vcpu, VCPU_REGS_RDX, 0);
	best = kvm_find_cpuid_entry(vcpu, function, index);

	if (!best)
		best = check_cpuid_limit(vcpu, function, index);

	if (best) {
		kvm_register_write(vcpu, VCPU_REGS_RAX, best->eax);
		kvm_register_write(vcpu, VCPU_REGS_RBX, best->ebx);
		kvm_register_write(vcpu, VCPU_REGS_RCX, best->ecx);
		kvm_register_write(vcpu, VCPU_REGS_RDX, best->edx);
	}
	kvm_x86_ops->skip_emulated_instruction(vcpu);
	trace_kvm_cpuid(function,
			kvm_register_read(vcpu, VCPU_REGS_RAX),
			kvm_register_read(vcpu, VCPU_REGS_RBX),
			kvm_register_read(vcpu, VCPU_REGS_RCX),
			kvm_register_read(vcpu, VCPU_REGS_RDX));
}
EXPORT_SYMBOL_GPL(kvm_emulate_cpuid);