summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/include/asm/kvm-x86-ops.h3
-rw-r--r--arch/x86/include/asm/kvm-x86-pmu-ops.h2
-rw-r--r--arch/x86/include/asm/kvm_host.h75
-rw-r--r--arch/x86/include/uapi/asm/kvm.h3
-rw-r--r--arch/x86/kernel/kvmclock.c12
-rw-r--r--arch/x86/kvm/Kconfig47
-rw-r--r--arch/x86/kvm/Makefile16
-rw-r--r--arch/x86/kvm/cpuid.c33
-rw-r--r--arch/x86/kvm/cpuid.h13
-rw-r--r--arch/x86/kvm/debugfs.c2
-rw-r--r--arch/x86/kvm/emulate.c27
-rw-r--r--arch/x86/kvm/governed_features.h1
-rw-r--r--arch/x86/kvm/hyperv.h85
-rw-r--r--arch/x86/kvm/irq.c2
-rw-r--r--arch/x86/kvm/irq_comm.c9
-rw-r--r--arch/x86/kvm/kvm_emulate.h9
-rw-r--r--arch/x86/kvm/kvm_onhyperv.h20
-rw-r--r--arch/x86/kvm/lapic.c5
-rw-r--r--arch/x86/kvm/mmu.h8
-rw-r--r--arch/x86/kvm/mmu/mmu.c293
-rw-r--r--arch/x86/kvm/mmu/mmu_internal.h3
-rw-r--r--arch/x86/kvm/mmu/paging_tmpl.h2
-rw-r--r--arch/x86/kvm/mmu/tdp_mmu.c95
-rw-r--r--arch/x86/kvm/mmu/tdp_mmu.h3
-rw-r--r--arch/x86/kvm/pmu.c140
-rw-r--r--arch/x86/kvm/pmu.h47
-rw-r--r--arch/x86/kvm/reverse_cpuid.h35
-rw-r--r--arch/x86/kvm/svm/hyperv.h9
-rw-r--r--arch/x86/kvm/svm/nested.c49
-rw-r--r--arch/x86/kvm/svm/pmu.c17
-rw-r--r--arch/x86/kvm/svm/sev.c7
-rw-r--r--arch/x86/kvm/svm/svm.c18
-rw-r--r--arch/x86/kvm/svm/svm.h2
-rw-r--r--arch/x86/kvm/svm/svm_onhyperv.c10
-rw-r--r--arch/x86/kvm/svm/vmenter.S10
-rw-r--r--arch/x86/kvm/vmx/hyperv.c447
-rw-r--r--arch/x86/kvm/vmx/hyperv.h204
-rw-r--r--arch/x86/kvm/vmx/hyperv_evmcs.c315
-rw-r--r--arch/x86/kvm/vmx/hyperv_evmcs.h166
-rw-r--r--arch/x86/kvm/vmx/nested.c160
-rw-r--r--arch/x86/kvm/vmx/nested.h3
-rw-r--r--arch/x86/kvm/vmx/pmu_intel.c22
-rw-r--r--arch/x86/kvm/vmx/sgx.c1
-rw-r--r--arch/x86/kvm/vmx/vmenter.S2
-rw-r--r--arch/x86/kvm/vmx/vmx.c86
-rw-r--r--arch/x86/kvm/vmx/vmx.h14
-rw-r--r--arch/x86/kvm/vmx/vmx_onhyperv.c36
-rw-r--r--arch/x86/kvm/vmx/vmx_onhyperv.h125
-rw-r--r--arch/x86/kvm/vmx/vmx_ops.h2
-rw-r--r--arch/x86/kvm/x86.c168
-rw-r--r--arch/x86/kvm/x86.h2
-rw-r--r--arch/x86/kvm/xen.c9
52 files changed, 1825 insertions, 1049 deletions
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 26b628d84594..378ed944b849 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -55,8 +55,10 @@ KVM_X86_OP(set_rflags)
KVM_X86_OP(get_if_flag)
KVM_X86_OP(flush_tlb_all)
KVM_X86_OP(flush_tlb_current)
+#if IS_ENABLED(CONFIG_HYPERV)
KVM_X86_OP_OPTIONAL(flush_remote_tlbs)
KVM_X86_OP_OPTIONAL(flush_remote_tlbs_range)
+#endif
KVM_X86_OP(flush_tlb_gva)
KVM_X86_OP(flush_tlb_guest)
KVM_X86_OP(vcpu_pre_run)
@@ -135,6 +137,7 @@ KVM_X86_OP(msr_filter_changed)
KVM_X86_OP(complete_emulated_msr)
KVM_X86_OP(vcpu_deliver_sipi_vector)
KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons);
+KVM_X86_OP_OPTIONAL(get_untagged_addr)
#undef KVM_X86_OP
#undef KVM_X86_OP_OPTIONAL
diff --git a/arch/x86/include/asm/kvm-x86-pmu-ops.h b/arch/x86/include/asm/kvm-x86-pmu-ops.h
index 6c98f4bb4228..058bc636356a 100644
--- a/arch/x86/include/asm/kvm-x86-pmu-ops.h
+++ b/arch/x86/include/asm/kvm-x86-pmu-ops.h
@@ -22,7 +22,7 @@ KVM_X86_PMU_OP(get_msr)
KVM_X86_PMU_OP(set_msr)
KVM_X86_PMU_OP(refresh)
KVM_X86_PMU_OP(init)
-KVM_X86_PMU_OP(reset)
+KVM_X86_PMU_OP_OPTIONAL(reset)
KVM_X86_PMU_OP_OPTIONAL(deliver_pmi)
KVM_X86_PMU_OP_OPTIONAL(cleanup)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 6711da000bb7..b5b2d0fde579 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -133,7 +133,8 @@
| X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_PCIDE \
| X86_CR4_OSXSAVE | X86_CR4_SMEP | X86_CR4_FSGSBASE \
| X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_VMXE \
- | X86_CR4_SMAP | X86_CR4_PKE | X86_CR4_UMIP))
+ | X86_CR4_SMAP | X86_CR4_PKE | X86_CR4_UMIP \
+ | X86_CR4_LAM_SUP))
#define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR)
@@ -500,8 +501,23 @@ struct kvm_pmc {
u8 idx;
bool is_paused;
bool intr;
+ /*
+ * Base value of the PMC counter, relative to the *consumed* count in
+ * the associated perf_event. This value includes counter updates from
+ * the perf_event and emulated_count since the last time the counter
+ * was reprogrammed, but it is *not* the current value as seen by the
+ * guest or userspace.
+ *
+ * The count is relative to the associated perf_event so that KVM
+ * doesn't need to reprogram the perf_event every time the guest writes
+ * to the counter.
+ */
u64 counter;
- u64 prev_counter;
+ /*
+ * PMC events triggered by KVM emulation that haven't been fully
+ * processed, i.e. haven't undergone overflow detection.
+ */
+ u64 emulated_counter;
u64 eventsel;
struct perf_event *perf_event;
struct kvm_vcpu *vcpu;
@@ -937,8 +953,10 @@ struct kvm_vcpu_arch {
/* used for guest single stepping over the given code position */
unsigned long singlestep_rip;
+#ifdef CONFIG_KVM_HYPERV
bool hyperv_enabled;
struct kvm_vcpu_hv *hyperv;
+#endif
#ifdef CONFIG_KVM_XEN
struct kvm_vcpu_xen xen;
#endif
@@ -1095,6 +1113,7 @@ enum hv_tsc_page_status {
HV_TSC_PAGE_BROKEN,
};
+#ifdef CONFIG_KVM_HYPERV
/* Hyper-V emulation context */
struct kvm_hv {
struct mutex hv_lock;
@@ -1125,9 +1144,9 @@ struct kvm_hv {
*/
unsigned int synic_auto_eoi_used;
- struct hv_partition_assist_pg *hv_pa_pg;
struct kvm_hv_syndbg hv_syndbg;
};
+#endif
struct msr_bitmap_range {
u32 flags;
@@ -1136,6 +1155,7 @@ struct msr_bitmap_range {
unsigned long *bitmap;
};
+#ifdef CONFIG_KVM_XEN
/* Xen emulation context */
struct kvm_xen {
struct mutex xen_lock;
@@ -1147,6 +1167,7 @@ struct kvm_xen {
struct idr evtchn_ports;
unsigned long poll_mask[BITS_TO_LONGS(KVM_MAX_VCPUS)];
};
+#endif
enum kvm_irqchip_mode {
KVM_IRQCHIP_NONE,
@@ -1255,6 +1276,7 @@ enum kvm_apicv_inhibit {
};
struct kvm_arch {
+ unsigned long vm_type;
unsigned long n_used_mmu_pages;
unsigned long n_requested_mmu_pages;
unsigned long n_max_mmu_pages;
@@ -1347,8 +1369,13 @@ struct kvm_arch {
/* reads protected by irq_srcu, writes by irq_lock */
struct hlist_head mask_notifier_list;
+#ifdef CONFIG_KVM_HYPERV
struct kvm_hv hyperv;
+#endif
+
+#ifdef CONFIG_KVM_XEN
struct kvm_xen xen;
+#endif
bool backwards_tsc_observed;
bool boot_vcpu_runs_old_kvmclock;
@@ -1406,9 +1433,8 @@ struct kvm_arch {
* the MMU lock in read mode + RCU or
* the MMU lock in write mode
*
- * For writes, this list is protected by:
- * the MMU lock in read mode + the tdp_mmu_pages_lock or
- * the MMU lock in write mode
+ * For writes, this list is protected by tdp_mmu_pages_lock; see
+ * below for the details.
*
* Roots will remain in the list until their tdp_mmu_root_count
* drops to zero, at which point the thread that decremented the
@@ -1425,8 +1451,10 @@ struct kvm_arch {
* - possible_nx_huge_pages;
* - the possible_nx_huge_page_link field of kvm_mmu_page structs used
* by the TDP MMU
- * It is acceptable, but not necessary, to acquire this lock when
- * the thread holds the MMU lock in write mode.
+ * Because the lock is only taken within the MMU lock, strictly
+ * speaking it is redundant to acquire this lock when the thread
+ * holds the MMU lock in write mode. However it often simplifies
+ * the code to do so.
*/
spinlock_t tdp_mmu_pages_lock;
#endif /* CONFIG_X86_64 */
@@ -1441,6 +1469,7 @@ struct kvm_arch {
#if IS_ENABLED(CONFIG_HYPERV)
hpa_t hv_root_tdp;
spinlock_t hv_root_tdp_lock;
+ struct hv_partition_assist_pg *hv_pa_pg;
#endif
/*
* VM-scope maximum vCPU ID. Used to determine the size of structures
@@ -1613,9 +1642,11 @@ struct kvm_x86_ops {
void (*flush_tlb_all)(struct kvm_vcpu *vcpu);
void (*flush_tlb_current)(struct kvm_vcpu *vcpu);
+#if IS_ENABLED(CONFIG_HYPERV)
int (*flush_remote_tlbs)(struct kvm *kvm);
int (*flush_remote_tlbs_range)(struct kvm *kvm, gfn_t gfn,
gfn_t nr_pages);
+#endif
/*
* Flush any TLB entries associated with the given GVA.
@@ -1761,6 +1792,8 @@ struct kvm_x86_ops {
* Returns vCPU specific APICv inhibit reasons
*/
unsigned long (*vcpu_get_apicv_inhibit_reasons)(struct kvm_vcpu *vcpu);
+
+ gva_t (*get_untagged_addr)(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags);
};
struct kvm_x86_nested_ops {
@@ -1824,6 +1857,7 @@ static inline struct kvm *kvm_arch_alloc_vm(void)
#define __KVM_HAVE_ARCH_VM_FREE
void kvm_arch_free_vm(struct kvm *kvm);
+#if IS_ENABLED(CONFIG_HYPERV)
#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS
static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
{
@@ -1835,6 +1869,15 @@ static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
}
#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE
+static inline int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn,
+ u64 nr_pages)
+{
+ if (!kvm_x86_ops.flush_remote_tlbs_range)
+ return -EOPNOTSUPP;
+
+ return static_call(kvm_x86_flush_remote_tlbs_range)(kvm, gfn, nr_pages);
+}
+#endif /* CONFIG_HYPERV */
#define kvm_arch_pmi_in_guest(vcpu) \
((vcpu) && (vcpu)->arch.handling_intr_from_guest)
@@ -1848,6 +1891,9 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu);
void kvm_mmu_init_vm(struct kvm *kvm);
void kvm_mmu_uninit_vm(struct kvm *kvm);
+void kvm_mmu_init_memslot_memory_attributes(struct kvm *kvm,
+ struct kvm_memory_slot *slot);
+
void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu);
void kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
@@ -2086,6 +2132,12 @@ void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd);
void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level,
int tdp_max_root_level, int tdp_huge_page_level);
+#ifdef CONFIG_KVM_PRIVATE_MEM
+#define kvm_arch_has_private_mem(kvm) ((kvm)->arch.vm_type != KVM_X86_DEFAULT_VM)
+#else
+#define kvm_arch_has_private_mem(kvm) false
+#endif
+
static inline u16 kvm_read_ldt(void)
{
u16 ldt;
@@ -2133,16 +2185,15 @@ enum {
#define HF_SMM_MASK (1 << 1)
#define HF_SMM_INSIDE_NMI_MASK (1 << 2)
-# define __KVM_VCPU_MULTIPLE_ADDRESS_SPACE
-# define KVM_ADDRESS_SPACE_NUM 2
+# define KVM_MAX_NR_ADDRESS_SPACES 2
+/* SMM is currently unsupported for guests with private memory. */
+# define kvm_arch_nr_memslot_as_ids(kvm) (kvm_arch_has_private_mem(kvm) ? 1 : 2)
# define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0)
# define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm)
#else
# define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, 0)
#endif
-#define KVM_ARCH_WANT_MMU_NOTIFIER
-
int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v);
int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
int kvm_cpu_has_extint(struct kvm_vcpu *v);
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 1a6a1f987949..a448d0964fc0 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -562,4 +562,7 @@ struct kvm_pmu_event_filter {
/* x86-specific KVM_EXIT_HYPERCALL flags. */
#define KVM_EXIT_HYPERCALL_LONG_MODE BIT(0)
+#define KVM_X86_DEFAULT_VM 0
+#define KVM_X86_SW_PROTECTED_VM 1
+
#endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index a95d0900e8c6..5bb395551c44 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -24,8 +24,8 @@
static int kvmclock __initdata = 1;
static int kvmclock_vsyscall __initdata = 1;
-static int msr_kvm_system_time __ro_after_init = MSR_KVM_SYSTEM_TIME;
-static int msr_kvm_wall_clock __ro_after_init = MSR_KVM_WALL_CLOCK;
+static int msr_kvm_system_time __ro_after_init;
+static int msr_kvm_wall_clock __ro_after_init;
static u64 kvm_sched_clock_offset __ro_after_init;
static int __init parse_no_kvmclock(char *arg)
@@ -195,7 +195,8 @@ static void kvm_setup_secondary_clock(void)
void kvmclock_disable(void)
{
- native_write_msr(msr_kvm_system_time, 0, 0);
+ if (msr_kvm_system_time)
+ native_write_msr(msr_kvm_system_time, 0, 0);
}
static void __init kvmclock_init_mem(void)
@@ -294,7 +295,10 @@ void __init kvmclock_init(void)
if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE2)) {
msr_kvm_system_time = MSR_KVM_SYSTEM_TIME_NEW;
msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK_NEW;
- } else if (!kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) {
+ } else if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) {
+ msr_kvm_system_time = MSR_KVM_SYSTEM_TIME;
+ msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK;
+ } else {
return;
}
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 950c12868d30..87e3da7b0439 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -23,17 +23,15 @@ config KVM
depends on HAVE_KVM
depends on HIGH_RES_TIMERS
depends on X86_LOCAL_APIC
- select PREEMPT_NOTIFIERS
- select MMU_NOTIFIER
+ select KVM_COMMON
+ select KVM_GENERIC_MMU_NOTIFIER
select HAVE_KVM_IRQCHIP
select HAVE_KVM_PFNCACHE
- select HAVE_KVM_IRQFD
select HAVE_KVM_DIRTY_RING_TSO
select HAVE_KVM_DIRTY_RING_ACQ_REL
select IRQ_BYPASS_MANAGER
select HAVE_KVM_IRQ_BYPASS
select HAVE_KVM_IRQ_ROUTING
- select HAVE_KVM_EVENTFD
select KVM_ASYNC_PF
select USER_RETURN_NOTIFIER
select KVM_MMIO
@@ -46,7 +44,6 @@ config KVM
select KVM_XFER_TO_GUEST_WORK
select KVM_GENERIC_DIRTYLOG_READ_PROTECT
select KVM_VFIO
- select INTERVAL_TREE
select HAVE_KVM_PM_NOTIFIER if PM
select KVM_GENERIC_HARDWARE_ENABLING
help
@@ -65,18 +62,30 @@ config KVM
config KVM_WERROR
bool "Compile KVM with -Werror"
- # KASAN may cause the build to fail due to larger frames
- default y if X86_64 && !KASAN
- # We use the dependency on !COMPILE_TEST to not be enabled
- # blindly in allmodconfig or allyesconfig configurations
- depends on KVM
- depends on (X86_64 && !KASAN) || !COMPILE_TEST
- depends on EXPERT
+ # Disallow KVM's -Werror if KASAN is enabled, e.g. to guard against
+ # randomized configs from selecting KVM_WERROR=y, which doesn't play
+ # nice with KASAN. KASAN builds generates warnings for the default
+ # FRAME_WARN, i.e. KVM_WERROR=y with KASAN=y requires special tuning.
+ # Building KVM with -Werror and KASAN is still doable via enabling
+ # the kernel-wide WERROR=y.
+ depends on KVM && EXPERT && !KASAN
help
Add -Werror to the build flags for KVM.
If in doubt, say "N".
+config KVM_SW_PROTECTED_VM
+ bool "Enable support for KVM software-protected VMs"
+ depends on EXPERT
+ depends on KVM && X86_64
+ select KVM_GENERIC_PRIVATE_MEM
+ help
+ Enable support for KVM software-protected VMs. Currently "protected"
+ means the VM can be backed with memory provided by
+ KVM_CREATE_GUEST_MEMFD.
+
+ If unsure, say "N".
+
config KVM_INTEL
tristate "KVM for Intel (and compatible) processors support"
depends on KVM && IA32_FEAT_CTL
@@ -129,6 +138,20 @@ config KVM_SMM
If unsure, say Y.
+config KVM_HYPERV
+ bool "Support for Microsoft Hyper-V emulation"
+ depends on KVM
+ default y
+ help
+ Provides KVM support for emulating Microsoft Hyper-V. This allows KVM
+ to expose a subset of the paravirtualized interfaces defined in the
+ Hyper-V Hypervisor Top-Level Functional Specification (TLFS):
+ https://docs.microsoft.com/en-us/virtualization/hyper-v-on-windows/reference/tlfs
+ These interfaces are required for the correct and performant functioning
+ of Windows and Hyper-V guests on KVM.
+
+ If unsure, say "Y".
+
config KVM_XEN
bool "Support for Xen hypercall interface"
depends on KVM
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index 80e3fe184d17..475b5fa917a6 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -11,25 +11,27 @@ include $(srctree)/virt/kvm/Makefile.kvm
kvm-y += x86.o emulate.o i8259.o irq.o lapic.o \
i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \
- hyperv.o debugfs.o mmu/mmu.o mmu/page_track.o \
+ debugfs.o mmu/mmu.o mmu/page_track.o \
mmu/spte.o
-ifdef CONFIG_HYPERV
-kvm-y += kvm_onhyperv.o
-endif
-
kvm-$(CONFIG_X86_64) += mmu/tdp_iter.o mmu/tdp_mmu.o
+kvm-$(CONFIG_KVM_HYPERV) += hyperv.o
kvm-$(CONFIG_KVM_XEN) += xen.o
kvm-$(CONFIG_KVM_SMM) += smm.o
kvm-intel-y += vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o \
- vmx/hyperv.o vmx/nested.o vmx/posted_intr.o
+ vmx/nested.o vmx/posted_intr.o
+
kvm-intel-$(CONFIG_X86_SGX_KVM) += vmx/sgx.o
+kvm-intel-$(CONFIG_KVM_HYPERV) += vmx/hyperv.o vmx/hyperv_evmcs.o
kvm-amd-y += svm/svm.o svm/vmenter.o svm/pmu.o svm/nested.o svm/avic.o \
- svm/sev.o svm/hyperv.o
+ svm/sev.o
+kvm-amd-$(CONFIG_KVM_HYPERV) += svm/hyperv.o
ifdef CONFIG_HYPERV
+kvm-y += kvm_onhyperv.o
+kvm-intel-y += vmx/vmx_onhyperv.o vmx/hyperv_evmcs.o
kvm-amd-y += svm/svm_onhyperv.o
endif
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 42d3f47f4c07..adba49afb5fe 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -314,11 +314,15 @@ EXPORT_SYMBOL_GPL(kvm_update_cpuid_runtime);
static bool kvm_cpuid_has_hyperv(struct kvm_cpuid_entry2 *entries, int nent)
{
+#ifdef CONFIG_KVM_HYPERV
struct kvm_cpuid_entry2 *entry;
entry = cpuid_entry2_find(entries, nent, HYPERV_CPUID_INTERFACE,
KVM_CPUID_INDEX_NOT_SIGNIFICANT);
return entry && entry->eax == HYPERV_CPUID_SIGNATURE_EAX;
+#else
+ return false;
+#endif
}
static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
@@ -433,11 +437,13 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2,
return 0;
}
+#ifdef CONFIG_KVM_HYPERV
if (kvm_cpuid_has_hyperv(e2, nent)) {
r = kvm_hv_vcpu_init(vcpu);
if (r)
return r;
}
+#endif
r = kvm_check_cpuid(vcpu, e2, nent);
if (r)
@@ -469,7 +475,7 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
return -E2BIG;
if (cpuid->nent) {
- e = vmemdup_user(entries, array_size(sizeof(*e), cpuid->nent));
+ e = vmemdup_array_user(entries, cpuid->nent, sizeof(*e));
if (IS_ERR(e))
return PTR_ERR(e);
@@ -513,7 +519,7 @@ int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu,
return -E2BIG;
if (cpuid->nent) {
- e2 = vmemdup_user(entries, array_size(sizeof(*e2), cpuid->nent));
+ e2 = vmemdup_array_user(entries, cpuid->nent, sizeof(*e2));
if (IS_ERR(e2))
return PTR_ERR(e2);
}
@@ -671,7 +677,7 @@ void kvm_set_cpu_caps(void)
kvm_cpu_cap_mask(CPUID_7_1_EAX,
F(AVX_VNNI) | F(AVX512_BF16) | F(CMPCCXADD) |
F(FZRM) | F(FSRS) | F(FSRC) |
- F(AMX_FP16) | F(AVX_IFMA)
+ F(AMX_FP16) | F(AVX_IFMA) | F(LAM)
);
kvm_cpu_cap_init_kvm_defined(CPUID_7_1_EDX,
@@ -679,6 +685,11 @@ void kvm_set_cpu_caps(void)
F(AMX_COMPLEX)
);
+ kvm_cpu_cap_init_kvm_defined(CPUID_7_2_EDX,
+ F(INTEL_PSFD) | F(IPRED_CTRL) | F(RRSBA_CTRL) | F(DDPD_U) |
+ F(BHI_CTRL) | F(MCDT_NO)
+ );
+
kvm_cpu_cap_mask(CPUID_D_1_EAX,
F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | F(XSAVES) | f_xfd
);
@@ -960,13 +971,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
break;
/* function 7 has additional index. */
case 7:
- entry->eax = min(entry->eax, 1u);
+ max_idx = entry->eax = min(entry->eax, 2u);
cpuid_entry_override(entry, CPUID_7_0_EBX);
cpuid_entry_override(entry, CPUID_7_ECX);
cpuid_entry_override(entry, CPUID_7_EDX);
- /* KVM only supports 0x7.0 and 0x7.1, capped above via min(). */
- if (entry->eax == 1) {
+ /* KVM only supports up to 0x7.2, capped above via min(). */
+ if (max_idx >= 1) {
entry = do_host_cpuid(array, function, 1);
if (!entry)
goto out;
@@ -976,6 +987,16 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
entry->ebx = 0;
entry->ecx = 0;
}
+ if (max_idx >= 2) {
+ entry = do_host_cpuid(array, function, 2);
+ if (!entry)
+ goto out;
+
+ cpuid_entry_override(entry, CPUID_7_2_EDX);
+ entry->ecx = 0;
+ entry->ebx = 0;
+ entry->eax = 0;
+ }
break;
case 0xa: { /* Architectural Performance Monitoring */
union cpuid10_eax eax;
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index 0b90532b6e26..856e3037e74f 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -47,11 +47,6 @@ static inline bool kvm_vcpu_is_legal_gpa(struct kvm_vcpu *vcpu, gpa_t gpa)
return !(gpa & vcpu->arch.reserved_gpa_bits);
}
-static inline bool kvm_vcpu_is_illegal_gpa(struct kvm_vcpu *vcpu, gpa_t gpa)
-{
- return !kvm_vcpu_is_legal_gpa(vcpu, gpa);
-}
-
static inline bool kvm_vcpu_is_legal_aligned_gpa(struct kvm_vcpu *vcpu,
gpa_t gpa, gpa_t alignment)
{
@@ -279,4 +274,12 @@ static __always_inline bool guest_can_use(struct kvm_vcpu *vcpu,
vcpu->arch.governed_features.enabled);
}
+static inline bool kvm_vcpu_is_legal_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
+{
+ if (guest_can_use(vcpu, X86_FEATURE_LAM))
+ cr3 &= ~(X86_CR3_LAM_U48 | X86_CR3_LAM_U57);
+
+ return kvm_vcpu_is_legal_