summaryrefslogtreecommitdiff
path: root/arch/x86/kvm/x86.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kvm/x86.c')
-rw-r--r--arch/x86/kvm/x86.c191
1 files changed, 154 insertions, 37 deletions
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a29df9ccbfde..314eb954bdee 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -54,6 +54,7 @@
#include <linux/pvclock_gtod.h>
#include <linux/kvm_irqfd.h>
#include <linux/irqbypass.h>
+#include <linux/nospec.h>
#include <trace/events/kvm.h>
#include <asm/debugreg.h>
@@ -191,6 +192,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "mmu_unsync", VM_STAT(mmu_unsync) },
{ "remote_tlb_flush", VM_STAT(remote_tlb_flush) },
{ "largepages", VM_STAT(lpages) },
+ { "nx_largepages_splitted", VM_STAT(nx_lpage_splits) },
{ NULL }
};
@@ -272,13 +274,14 @@ int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
int err;
- if (((value ^ smsr->values[slot].curr) & mask) == 0)
+ value = (value & mask) | (smsr->values[slot].host & ~mask);
+ if (value == smsr->values[slot].curr)
return 0;
- smsr->values[slot].curr = value;
err = wrmsrl_safe(shared_msrs_global.msrs[slot], value);
if (err)
return 1;
+ smsr->values[slot].curr = value;
if (!smsr->registered) {
smsr->urn.on_user_return = kvm_on_user_return;
user_return_notifier_register(&smsr->urn);
@@ -535,8 +538,14 @@ static int kvm_read_nested_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn,
data, offset, len, access);
}
+static inline u64 pdptr_rsvd_bits(struct kvm_vcpu *vcpu)
+{
+ return rsvd_bits(cpuid_maxphyaddr(vcpu), 63) | rsvd_bits(5, 8) |
+ rsvd_bits(1, 2);
+}
+
/*
- * Load the pae pdptrs. Return true is they are all valid.
+ * Load the pae pdptrs. Return 1 if they are all valid, 0 otherwise.
*/
int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3)
{
@@ -555,8 +564,7 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3)
}
for (i = 0; i < ARRAY_SIZE(pdpte); ++i) {
if ((pdpte[i] & PT_PRESENT_MASK) &&
- (pdpte[i] &
- vcpu->arch.mmu.guest_rsvd_check.rsvd_bits_mask[0][2])) {
+ (pdpte[i] & pdptr_rsvd_bits(vcpu))) {
ret = 0;
goto out;
}
@@ -582,7 +590,7 @@ static bool pdptrs_changed(struct kvm_vcpu *vcpu)
gfn_t gfn;
int r;
- if (is_long_mode(vcpu) || !is_pae(vcpu))
+ if (is_long_mode(vcpu) || !is_pae(vcpu) || !is_paging(vcpu))
return false;
if (!test_bit(VCPU_EXREG_PDPTR,
@@ -882,9 +890,11 @@ static u64 kvm_dr6_fixed(struct kvm_vcpu *vcpu)
static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
{
+ size_t size = ARRAY_SIZE(vcpu->arch.db);
+
switch (dr) {
case 0 ... 3:
- vcpu->arch.db[dr] = val;
+ vcpu->arch.db[array_index_nospec(dr, size)] = val;
if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
vcpu->arch.eff_db[dr] = val;
break;
@@ -921,9 +931,11 @@ EXPORT_SYMBOL_GPL(kvm_set_dr);
int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val)
{
+ size_t size = ARRAY_SIZE(vcpu->arch.db);
+
switch (dr) {
case 0 ... 3:
- *val = vcpu->arch.db[dr];
+ *val = vcpu->arch.db[array_index_nospec(dr, size)];
break;
case 4:
/* fall through */
@@ -1027,6 +1039,14 @@ u64 kvm_get_arch_capabilities(void)
rdmsrl_safe(MSR_IA32_ARCH_CAPABILITIES, &data);
/*
+ * If nx_huge_pages is enabled, KVM's shadow paging will ensure that
+ * the nested hypervisor runs with NX huge pages. If it is not,
+ * L1 is anyway vulnerable to ITLB_MULTIHIT explots from other
+ * L1 guests, so it need not worry about its own (L2) guests.
+ */
+ data |= ARCH_CAP_PSCHANGE_MC_NO;
+
+ /*
* If we're doing cache flushes (either "always" or "cond")
* we will do one whenever the guest does a vmlaunch/vmresume.
* If an outer hypervisor is doing the cache flush for us
@@ -1038,8 +1058,40 @@ u64 kvm_get_arch_capabilities(void)
if (l1tf_vmx_mitigation != VMENTER_L1D_FLUSH_NEVER)
data |= ARCH_CAP_SKIP_VMENTRY_L1DFLUSH;
+ if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
+ data |= ARCH_CAP_RDCL_NO;
+ if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS))
+ data |= ARCH_CAP_SSB_NO;
+ if (!boot_cpu_has_bug(X86_BUG_MDS))
+ data |= ARCH_CAP_MDS_NO;
+
+ /*
+ * On TAA affected systems, export MDS_NO=0 when:
+ * - TSX is enabled on the host, i.e. X86_FEATURE_RTM=1.
+ * - Updated microcode is present. This is detected by
+ * the presence of ARCH_CAP_TSX_CTRL_MSR and ensures
+ * that VERW clears CPU buffers.
+ *
+ * When MDS_NO=0 is exported, guests deploy clear CPU buffer
+ * mitigation and don't complain:
+ *
+ * "Vulnerable: Clear CPU buffers attempted, no microcode"
+ *
+ * If TSX is disabled on the system, guests are also mitigated against
+ * TAA and clear CPU buffer mitigation is not required for guests.
+ */
+ if (!boot_cpu_has(X86_FEATURE_RTM))
+ data &= ~ARCH_CAP_TAA_NO;
+ else if (!boot_cpu_has_bug(X86_BUG_TAA))
+ data |= ARCH_CAP_TAA_NO;
+ else if (data & ARCH_CAP_TSX_CTRL_MSR)
+ data &= ~ARCH_CAP_MDS_NO;
+
+ /* KVM does not emulate MSR_IA32_TSX_CTRL. */
+ data &= ~ARCH_CAP_TSX_CTRL_MSR;
return data;
}
+
EXPORT_SYMBOL_GPL(kvm_get_arch_capabilities);
static int kvm_get_msr_feature(struct kvm_msr_entry *msr)
@@ -1073,11 +1125,8 @@ static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
return 0;
}
-bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
+static bool __kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
{
- if (efer & efer_reserved_bits)
- return false;
-
if (efer & EFER_FFXSR) {
struct kvm_cpuid_entry2 *feat;
@@ -1095,19 +1144,33 @@ bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
}
return true;
+
+}
+bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
+{
+ if (efer & efer_reserved_bits)
+ return false;
+
+ return __kvm_valid_efer(vcpu, efer);
}
EXPORT_SYMBOL_GPL(kvm_valid_efer);
-static int set_efer(struct kvm_vcpu *vcpu, u64 efer)
+static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
{
u64 old_efer = vcpu->arch.efer;
+ u64 efer = msr_info->data;
- if (!kvm_valid_efer(vcpu, efer))
+ if (efer & efer_reserved_bits)
return 1;
- if (is_paging(vcpu)
- && (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME))
- return 1;
+ if (!msr_info->host_initiated) {
+ if (!__kvm_valid_efer(vcpu, efer))
+ return 1;
+
+ if (is_paging(vcpu) &&
+ (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME))
+ return 1;
+ }
efer &= ~EFER_LMA;
efer |= vcpu->arch.efer & EFER_LMA;
@@ -1354,7 +1417,7 @@ static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale)
vcpu->arch.tsc_always_catchup = 1;
return 0;
} else {
- WARN(1, "user requested TSC rate below hardware speed\n");
+ pr_warn_ratelimited("user requested TSC rate below hardware speed\n");
return -1;
}
}
@@ -1364,8 +1427,8 @@ static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale)
user_tsc_khz, tsc_khz);
if (ratio == 0 || ratio >= kvm_max_tsc_scaling_ratio) {
- WARN_ONCE(1, "Invalid TSC scaling ratio - virtual-tsc-khz=%u\n",
- user_tsc_khz);
+ pr_warn_ratelimited("Invalid TSC scaling ratio - virtual-tsc-khz=%u\n",
+ user_tsc_khz);
return -1;
}
@@ -2067,7 +2130,10 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data)
default:
if (msr >= MSR_IA32_MC0_CTL &&
msr < MSR_IA32_MCx_CTL(bank_num)) {
- u32 offset = msr - MSR_IA32_MC0_CTL;
+ u32 offset = array_index_nospec(
+ msr - MSR_IA32_MC0_CTL,
+ MSR_IA32_MCx_CTL(bank_num) - MSR_IA32_MC0_CTL);
+
/* only 0 or all 1s can be written to IA32_MCi_CTL
* some Linux kernels though clear bit 10 in bank 4 to
* workaround a BIOS/GART TBL issue on AMD K8s, ignore
@@ -2197,8 +2263,13 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
if (msr_info->host_initiated)
vcpu->arch.microcode_version = data;
break;
+ case MSR_IA32_ARCH_CAPABILITIES:
+ if (!msr_info->host_initiated)
+ return 1;
+ vcpu->arch.arch_capabilities = data;
+ break;
case MSR_EFER:
- return set_efer(vcpu, data);
+ return set_efer(vcpu, msr_info);
case MSR_K7_HWCR:
data &= ~(u64)0x40; /* ignore flush filter disable */
data &= ~(u64)0x100; /* ignore ignne emulation enable */
@@ -2430,7 +2501,10 @@ static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
default:
if (msr >= MSR_IA32_MC0_CTL &&
msr < MSR_IA32_MCx_CTL(bank_num)) {
- u32 offset = msr - MSR_IA32_MC0_CTL;
+ u32 offset = array_index_nospec(
+ msr - MSR_IA32_MC0_CTL,
+ MSR_IA32_MCx_CTL(bank_num) - MSR_IA32_MC0_CTL);
+
data = vcpu->arch.mce_banks[offset];
break;
}
@@ -2473,6 +2547,12 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
case MSR_IA32_UCODE_REV:
msr_info->data = vcpu->arch.microcode_version;
break;
+ case MSR_IA32_ARCH_CAPABILITIES:
+ if (!msr_info->host_initiated &&
+ !guest_cpuid_has_arch_capabilities(vcpu))
+ return 1;
+ msr_info->data = vcpu->arch.arch_capabilities;
+ break;
case MSR_MTRRcap:
case 0x200 ... 0x2ff:
return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data);
@@ -4598,6 +4678,13 @@ int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu, gva_t addr, void *val,
/* kvm_write_guest_virt_system can pull in tons of pages. */
vcpu->arch.l1tf_flush_l1d = true;
+ /*
+ * FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED
+ * is returned, but our callers are not ready for that and they blindly
+ * call kvm_inject_page_fault. Ensure that they at least do not leak
+ * uninitialized kernel stack memory into cr2 and error code.
+ */
+ memset(exception, 0, sizeof(*exception));
return kvm_write_guest_virt_helper(addr, val, bytes, vcpu,
PFERR_WRITE_MASK, exception);
}
@@ -5735,8 +5822,16 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
if (reexecute_instruction(vcpu, cr2, write_fault_to_spt,
emulation_type))
return EMULATE_DONE;
- if (ctxt->have_exception && inject_emulated_exception(vcpu))
+ if (ctxt->have_exception) {
+ /*
+ * #UD should result in just EMULATION_FAILED, and trap-like
+ * exception should not be encountered during decode.
+ */
+ WARN_ON_ONCE(ctxt->exception.vector == UD_VECTOR ||
+ exception_type(ctxt->exception.vector) == EXCPT_TRAP);
+ inject_emulated_exception(vcpu);
return EMULATE_DONE;
+ }
if (emulation_type & EMULTYPE_SKIP)
return EMULATE_FAIL;
return handle_emulation_failure(vcpu);
@@ -5801,12 +5896,13 @@ restart:
unsigned long rflags = kvm_x86_ops->get_rflags(vcpu);
toggle_interruptibility(vcpu, ctxt->interruptibility);
vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
- kvm_rip_write(vcpu, ctxt->eip);
- if (r == EMULATE_DONE && ctxt->tf)
- kvm_vcpu_do_singlestep(vcpu, &r);
if (!ctxt->have_exception ||
- exception_type(ctxt->exception.vector) == EXCPT_TRAP)
+ exception_type(ctxt->exception.vector) == EXCPT_TRAP) {
+ kvm_rip_write(vcpu, ctxt->eip);
+ if (r == EMULATE_DONE && ctxt->tf)
+ kvm_vcpu_do_singlestep(vcpu, &r);
__kvm_set_rflags(vcpu, ctxt->eflags);
+ }
/*
* For STI, interrupts are shadowed; so KVM_REQ_EVENT will
@@ -5908,17 +6004,17 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va
smp_call_function_single(freq->cpu, tsc_khz_changed, freq, 1);
- spin_lock(&kvm_lock);
+ mutex_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list) {
kvm_for_each_vcpu(i, vcpu, kvm) {
if (vcpu->cpu != freq->cpu)
continue;
kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
- if (vcpu->cpu != smp_processor_id())
+ if (vcpu->cpu != raw_smp_processor_id())
send_ipi = 1;
}
}
- spin_unlock(&kvm_lock);
+ mutex_unlock(&kvm_lock);
if (freq->old < freq->new && send_ipi) {
/*
@@ -6036,14 +6132,12 @@ static void kvm_set_mmio_spte_mask(void)
/* Set the present bit. */
mask |= 1ull;
-#ifdef CONFIG_X86_64
/*
* If reserved bit is not supported, clear the present bit to disable
* mmio page fault.
*/
if (maxphyaddr == 52)
mask &= ~1ull;
-#endif
kvm_mmu_set_mmio_spte_mask(mask);
}
@@ -6056,12 +6150,12 @@ static void pvclock_gtod_update_fn(struct work_struct *work)
struct kvm_vcpu *vcpu;
int i;
- spin_lock(&kvm_lock);
+ mutex_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list)
kvm_for_each_vcpu(i, vcpu, kvm)
kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
atomic_set(&kvm_guest_has_master_clock, 0);
- spin_unlock(&kvm_lock);
+ mutex_unlock(&kvm_lock);
}
static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn);
@@ -7448,7 +7542,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
kvm_update_cpuid(vcpu);
idx = srcu_read_lock(&vcpu->kvm->srcu);
- if (!is_long_mode(vcpu) && is_pae(vcpu)) {
+ if (!is_long_mode(vcpu) && is_pae(vcpu) && is_paging(vcpu)) {
load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu));
mmu_reset_needed = 1;
}
@@ -7672,6 +7766,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
{
int r;
+ vcpu->arch.arch_capabilities = kvm_get_arch_capabilities();
kvm_vcpu_mtrr_init(vcpu);
r = vcpu_load(vcpu);
if (r)
@@ -7712,7 +7807,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
kvm_mmu_unload(vcpu);
vcpu_put(vcpu);
- kvm_x86_ops->vcpu_free(vcpu);
+ kvm_arch_vcpu_free(vcpu);
}
void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
@@ -8028,6 +8123,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list);
INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
+ INIT_LIST_HEAD(&kvm->arch.lpage_disallowed_mmu_pages);
INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
atomic_set(&kvm->arch.noncoherent_dma_count, 0);
@@ -8056,6 +8152,11 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
return 0;
}
+int kvm_arch_post_init_vm(struct kvm *kvm)
+{
+ return kvm_mmu_post_init_vm(kvm);
+}
+
static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu)
{
int r;
@@ -8162,6 +8263,11 @@ int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
}
EXPORT_SYMBOL_GPL(x86_set_memory_region);
+void kvm_arch_pre_destroy_vm(struct kvm *kvm)
+{
+ kvm_mmu_pre_destroy_vm(kvm);
+}
+
void kvm_arch_destroy_vm(struct kvm *kvm)
{
if (current->mm == kvm->mm) {
@@ -8213,6 +8319,13 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
{
int i;
+ /*
+ * Clear out the previous array pointers for the KVM_MR_MOVE case. The
+ * old arrays will be freed by __kvm_set_memory_region() if installing
+ * the new memslot is successful.
+ */
+ memset(&slot->arch, 0, sizeof(slot->arch));
+
for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) {
struct kvm_lpage_info *linfo;
unsigned long ugfn;
@@ -8286,6 +8399,10 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
const struct kvm_userspace_memory_region *mem,
enum kvm_mr_change change)
{
+ if (change == KVM_MR_MOVE)
+ return kvm_arch_create_memslot(kvm, memslot,
+ mem->memory_size >> PAGE_SHIFT);
+
return 0;
}