summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/include/asm/cpufeatures.h1
-rw-r--r--arch/x86/include/asm/kvm_emulate.h4
-rw-r--r--arch/x86/include/asm/kvm_host.h40
-rw-r--r--arch/x86/include/asm/svm.h6
-rw-r--r--arch/x86/include/asm/vmx.h22
-rw-r--r--arch/x86/kvm/cpuid.c34
-rw-r--r--arch/x86/kvm/cpuid.h186
-rw-r--r--arch/x86/kvm/emulate.c42
-rw-r--r--arch/x86/kvm/hyperv.c8
-rw-r--r--arch/x86/kvm/kvm_cache_regs.h2
-rw-r--r--arch/x86/kvm/lapic.c2
-rw-r--r--arch/x86/kvm/lapic.h3
-rw-r--r--arch/x86/kvm/mmu.c267
-rw-r--r--arch/x86/kvm/mmu.h23
-rw-r--r--arch/x86/kvm/mmu_audit.c4
-rw-r--r--arch/x86/kvm/mtrr.c2
-rw-r--r--arch/x86/kvm/paging_tmpl.h6
-rw-r--r--arch/x86/kvm/svm.c139
-rw-r--r--arch/x86/kvm/trace.h11
-rw-r--r--arch/x86/kvm/vmx.c620
-rw-r--r--arch/x86/kvm/x86.c213
-rw-r--r--arch/x86/kvm/x86.h54
22 files changed, 1068 insertions, 621 deletions
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 42bbbf0f173d..2519c6c801c9 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -288,6 +288,7 @@
#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */
#define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */
#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */
+#define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */
/* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */
#define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index fde36f189836..fa2558e12024 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -219,8 +219,8 @@ struct x86_emulate_ops {
struct x86_instruction_info *info,
enum x86_intercept_stage stage);
- void (*get_cpuid)(struct x86_emulate_ctxt *ctxt,
- u32 *eax, u32 *ebx, u32 *ecx, u32 *edx);
+ bool (*get_cpuid)(struct x86_emulate_ctxt *ctxt, u32 *eax, u32 *ebx,
+ u32 *ecx, u32 *edx, bool check_limit);
void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked);
unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt);
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 369e41c23f07..8844eee290b2 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -79,15 +79,14 @@
| X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \
| X86_CR0_NW | X86_CR0_CD | X86_CR0_PG))
-#define CR3_L_MODE_RESERVED_BITS 0xFFFFFF0000000000ULL
#define CR3_PCID_INVD BIT_64(63)
#define CR4_RESERVED_BITS \
(~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\
| X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE \
| 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_VMXE | X86_CR4_SMAP \
- | X86_CR4_PKE))
+ | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_VMXE \
+ | X86_CR4_SMAP | X86_CR4_PKE))
#define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR)
@@ -204,7 +203,6 @@ enum {
#define PFERR_GUEST_PAGE_MASK (1ULL << PFERR_GUEST_PAGE_BIT)
#define PFERR_NESTED_GUEST_PAGE (PFERR_GUEST_PAGE_MASK | \
- PFERR_USER_MASK | \
PFERR_WRITE_MASK | \
PFERR_PRESENT_MASK)
@@ -317,15 +315,17 @@ struct kvm_pio_request {
int size;
};
+#define PT64_ROOT_MAX_LEVEL 5
+
struct rsvd_bits_validate {
- u64 rsvd_bits_mask[2][4];
+ u64 rsvd_bits_mask[2][PT64_ROOT_MAX_LEVEL];
u64 bad_mt_xwr;
};
/*
- * x86 supports 3 paging modes (4-level 64-bit, 3-level 64-bit, and 2-level
- * 32-bit). The kvm_mmu structure abstracts the details of the current mmu
- * mode.
+ * x86 supports 4 paging modes (5-level 64-bit, 4-level 64-bit, 3-level 32-bit,
+ * and 2-level 32-bit). The kvm_mmu structure abstracts the details of the
+ * current mmu mode.
*/
struct kvm_mmu {
void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long root);
@@ -548,8 +548,8 @@ struct kvm_vcpu_arch {
struct kvm_queued_exception {
bool pending;
+ bool injected;
bool has_error_code;
- bool reinject;
u8 nr;
u32 error_code;
u8 nested_apf;
@@ -687,8 +687,12 @@ struct kvm_vcpu_arch {
int pending_ioapic_eoi;
int pending_external_vector;
- /* GPA available (AMD only) */
+ /* GPA available */
bool gpa_available;
+ gpa_t gpa_val;
+
+ /* be preempted when it's in kernel-mode(cpl=0) */
+ bool preempted_in_kernel;
};
struct kvm_lpage_info {
@@ -979,7 +983,7 @@ struct kvm_x86_ops {
void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu);
int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
- int (*get_tdp_level)(void);
+ int (*get_tdp_level)(struct kvm_vcpu *vcpu);
u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
int (*get_lpage_level)(void);
bool (*rdtscp_supported)(void);
@@ -1297,20 +1301,6 @@ static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code)
kvm_queue_exception_e(vcpu, GP_VECTOR, error_code);
}
-static inline u64 get_canonical(u64 la)
-{
- return ((int64_t)la << 16) >> 16;
-}
-
-static inline bool is_noncanonical_address(u64 la)
-{
-#ifdef CONFIG_X86_64
- return get_canonical(la) != la;
-#else
- return false;
-#endif
-}
-
#define TSS_IOPB_BASE_OFFSET 0x66
#define TSS_BASE_SIZE 0x68
#define TSS_IOPB_SIZE (65536 / 8)
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 58fffe79e417..14835dd205a5 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -107,6 +107,9 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
#define V_IRQ_SHIFT 8
#define V_IRQ_MASK (1 << V_IRQ_SHIFT)
+#define V_GIF_SHIFT 9
+#define V_GIF_MASK (1 << V_GIF_SHIFT)
+
#define V_INTR_PRIO_SHIFT 16
#define V_INTR_PRIO_MASK (0x0f << V_INTR_PRIO_SHIFT)
@@ -116,6 +119,9 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
#define V_INTR_MASKING_SHIFT 24
#define V_INTR_MASKING_MASK (1 << V_INTR_MASKING_SHIFT)
+#define V_GIF_ENABLE_SHIFT 25
+#define V_GIF_ENABLE_MASK (1 << V_GIF_ENABLE_SHIFT)
+
#define AVIC_ENABLE_SHIFT 31
#define AVIC_ENABLE_MASK (1 << AVIC_ENABLE_SHIFT)
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 35cd06f636ab..caec8417539f 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -72,6 +72,7 @@
#define SECONDARY_EXEC_PAUSE_LOOP_EXITING 0x00000400
#define SECONDARY_EXEC_RDRAND 0x00000800
#define SECONDARY_EXEC_ENABLE_INVPCID 0x00001000
+#define SECONDARY_EXEC_ENABLE_VMFUNC 0x00002000
#define SECONDARY_EXEC_SHADOW_VMCS 0x00004000
#define SECONDARY_EXEC_RDSEED 0x00010000
#define SECONDARY_EXEC_ENABLE_PML 0x00020000
@@ -114,6 +115,10 @@
#define VMX_MISC_SAVE_EFER_LMA 0x00000020
#define VMX_MISC_ACTIVITY_HLT 0x00000040
+/* VMFUNC functions */
+#define VMX_VMFUNC_EPTP_SWITCHING 0x00000001
+#define VMFUNC_EPTP_ENTRIES 512
+
static inline u32 vmx_basic_vmcs_revision_id(u64 vmx_basic)
{
return vmx_basic & GENMASK_ULL(30, 0);
@@ -187,6 +192,8 @@ enum vmcs_field {
APIC_ACCESS_ADDR_HIGH = 0x00002015,
POSTED_INTR_DESC_ADDR = 0x00002016,
POSTED_INTR_DESC_ADDR_HIGH = 0x00002017,
+ VM_FUNCTION_CONTROL = 0x00002018,
+ VM_FUNCTION_CONTROL_HIGH = 0x00002019,
EPT_POINTER = 0x0000201a,
EPT_POINTER_HIGH = 0x0000201b,
EOI_EXIT_BITMAP0 = 0x0000201c,
@@ -197,6 +204,8 @@ enum vmcs_field {
EOI_EXIT_BITMAP2_HIGH = 0x00002021,
EOI_EXIT_BITMAP3 = 0x00002022,
EOI_EXIT_BITMAP3_HIGH = 0x00002023,
+ EPTP_LIST_ADDRESS = 0x00002024,
+ EPTP_LIST_ADDRESS_HIGH = 0x00002025,
VMREAD_BITMAP = 0x00002026,
VMWRITE_BITMAP = 0x00002028,
XSS_EXIT_BITMAP = 0x0000202C,
@@ -444,6 +453,7 @@ enum vmcs_field {
#define VMX_EPT_EXECUTE_ONLY_BIT (1ull)
#define VMX_EPT_PAGE_WALK_4_BIT (1ull << 6)
+#define VMX_EPT_PAGE_WALK_5_BIT (1ull << 7)
#define VMX_EPTP_UC_BIT (1ull << 8)
#define VMX_EPTP_WB_BIT (1ull << 14)
#define VMX_EPT_2MB_PAGE_BIT (1ull << 16)
@@ -459,12 +469,14 @@ enum vmcs_field {
#define VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT (1ull << 10) /* (42 - 32) */
#define VMX_VPID_EXTENT_SINGLE_NON_GLOBAL_BIT (1ull << 11) /* (43 - 32) */
-#define VMX_EPT_DEFAULT_GAW 3
-#define VMX_EPT_MAX_GAW 0x4
#define VMX_EPT_MT_EPTE_SHIFT 3
-#define VMX_EPT_GAW_EPTP_SHIFT 3
-#define VMX_EPT_AD_ENABLE_BIT (1ull << 6)
-#define VMX_EPT_DEFAULT_MT 0x6ull
+#define VMX_EPTP_PWL_MASK 0x38ull
+#define VMX_EPTP_PWL_4 0x18ull
+#define VMX_EPTP_PWL_5 0x20ull
+#define VMX_EPTP_AD_ENABLE_BIT (1ull << 6)
+#define VMX_EPTP_MT_MASK 0x7ull
+#define VMX_EPTP_MT_WB 0x6ull
+#define VMX_EPTP_MT_UC 0x0ull
#define VMX_EPT_READABLE_MASK 0x1ull
#define VMX_EPT_WRITABLE_MASK 0x2ull
#define VMX_EPT_EXECUTABLE_MASK 0x4ull
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 19adbb418443..0099e10eb045 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -126,16 +126,20 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
best->ebx = xstate_required_size(vcpu->arch.xcr0, true);
/*
- * The existing code assumes virtual address is 48-bit in the canonical
- * address checks; exit if it is ever changed.
+ * The existing code assumes virtual address is 48-bit or 57-bit in the
+ * canonical address checks; exit if it is ever changed.
*/
best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0);
- if (best && ((best->eax & 0xff00) >> 8) != 48 &&
- ((best->eax & 0xff00) >> 8) != 0)
- return -EINVAL;
+ if (best) {
+ int vaddr_bits = (best->eax & 0xff00) >> 8;
+
+ if (vaddr_bits != 48 && vaddr_bits != 57 && vaddr_bits != 0)
+ return -EINVAL;
+ }
/* Update physical-address width */
vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
+ kvm_mmu_reset_context(vcpu);
kvm_pmu_refresh(vcpu);
return 0;
@@ -383,7 +387,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
/* cpuid 7.0.ecx*/
const u32 kvm_cpuid_7_0_ecx_x86_features =
- F(AVX512VBMI) | F(PKU) | 0 /*OSPKE*/ | F(AVX512_VPOPCNTDQ);
+ F(AVX512VBMI) | F(LA57) | F(PKU) |
+ 0 /*OSPKE*/ | F(AVX512_VPOPCNTDQ);
/* cpuid 7.0.edx*/
const u32 kvm_cpuid_7_0_edx_x86_features =
@@ -853,16 +858,24 @@ static struct kvm_cpuid_entry2* check_cpuid_limit(struct kvm_vcpu *vcpu,
return kvm_find_cpuid_entry(vcpu, maxlevel->eax, index);
}
-void kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx)
+bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx,
+ u32 *ecx, u32 *edx, bool check_limit)
{
u32 function = *eax, index = *ecx;
struct kvm_cpuid_entry2 *best;
+ bool entry_found = true;
best = kvm_find_cpuid_entry(vcpu, function, index);
- if (!best)
+ if (!best) {
+ entry_found = false;
+ if (!check_limit)
+ goto out;
+
best = check_cpuid_limit(vcpu, function, index);
+ }
+out:
if (best) {
*eax = best->eax;
*ebx = best->ebx;
@@ -870,7 +883,8 @@ void kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx)
*edx = best->edx;
} else
*eax = *ebx = *ecx = *edx = 0;
- trace_kvm_cpuid(function, *eax, *ebx, *ecx, *edx);
+ trace_kvm_cpuid(function, *eax, *ebx, *ecx, *edx, entry_found);
+ return entry_found;
}
EXPORT_SYMBOL_GPL(kvm_cpuid);
@@ -883,7 +897,7 @@ int kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
eax = kvm_register_read(vcpu, VCPU_REGS_RAX);
ecx = kvm_register_read(vcpu, VCPU_REGS_RCX);
- kvm_cpuid(vcpu, &eax, &ebx, &ecx, &edx);
+ kvm_cpuid(vcpu, &eax, &ebx, &ecx, &edx, true);
kvm_register_write(vcpu, VCPU_REGS_RAX, eax);
kvm_register_write(vcpu, VCPU_REGS_RBX, ebx);
kvm_register_write(vcpu, VCPU_REGS_RCX, ecx);
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index da6728383052..1ea3c0e1e3a9 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -3,6 +3,7 @@
#include "x86.h"
#include <asm/cpu.h>
+#include <asm/processor.h>
int kvm_update_cpuid(struct kvm_vcpu *vcpu);
bool kvm_mpx_supported(void);
@@ -20,7 +21,8 @@ int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu,
int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu,
struct kvm_cpuid2 *cpuid,
struct kvm_cpuid_entry2 __user *entries);
-void kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx);
+bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx,
+ u32 *ecx, u32 *edx, bool check_limit);
int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu);
@@ -29,95 +31,87 @@ static inline int cpuid_maxphyaddr(struct kvm_vcpu *vcpu)
return vcpu->arch.maxphyaddr;
}
-static inline bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
-
- if (!static_cpu_has(X86_FEATURE_XSAVE))
- return false;
-
- best = kvm_find_cpuid_entry(vcpu, 1, 0);
- return best && (best->ecx & bit(X86_FEATURE_XSAVE));
-}
-
-static inline bool guest_cpuid_has_mtrr(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
-
- best = kvm_find_cpuid_entry(vcpu, 1, 0);
- return best && (best->edx & bit(X86_FEATURE_MTRR));
-}
-
-static inline bool guest_cpuid_has_tsc_adjust(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
-
- best = kvm_find_cpuid_entry(vcpu, 7, 0);
- return best && (best->ebx & bit(X86_FEATURE_TSC_ADJUST));
-}
+struct cpuid_reg {
+ u32 function;
+ u32 index;
+ int reg;
+};
-static inline bool guest_cpuid_has_smep(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
-
- best = kvm_find_cpuid_entry(vcpu, 7, 0);
- return best && (best->ebx & bit(X86_FEATURE_SMEP));
-}
+static const struct cpuid_reg reverse_cpuid[] = {
+ [CPUID_1_EDX] = { 1, 0, CPUID_EDX},
+ [CPUID_8000_0001_EDX] = {0x80000001, 0, CPUID_EDX},
+ [CPUID_8086_0001_EDX] = {0x80860001, 0, CPUID_EDX},
+ [CPUID_1_ECX] = { 1, 0, CPUID_ECX},
+ [CPUID_C000_0001_EDX] = {0xc0000001, 0, CPUID_EDX},
+ [CPUID_8000_0001_ECX] = {0xc0000001, 0, CPUID_ECX},
+ [CPUID_7_0_EBX] = { 7, 0, CPUID_EBX},
+ [CPUID_D_1_EAX] = { 0xd, 1, CPUID_EAX},
+ [CPUID_F_0_EDX] = { 0xf, 0, CPUID_EDX},
+ [CPUID_F_1_EDX] = { 0xf, 1, CPUID_EDX},
+ [CPUID_8000_0008_EBX] = {0x80000008, 0, CPUID_EBX},
+ [CPUID_6_EAX] = { 6, 0, CPUID_EAX},
+ [CPUID_8000_000A_EDX] = {0x8000000a, 0, CPUID_EDX},
+ [CPUID_7_ECX] = { 7, 0, CPUID_ECX},
+ [CPUID_8000_0007_EBX] = {0x80000007, 0, CPUID_EBX},
+};
-static inline bool guest_cpuid_has_smap(struct kvm_vcpu *vcpu)
+static __always_inline struct cpuid_reg x86_feature_cpuid(unsigned x86_feature)
{
- struct kvm_cpuid_entry2 *best;
-
- best = kvm_find_cpuid_entry(vcpu, 7, 0);
- return best && (best->ebx & bit(X86_FEATURE_SMAP));
-}
+ unsigned x86_leaf = x86_feature / 32;
-static inline bool guest_cpuid_has_fsgsbase(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
+ BUILD_BUG_ON(!__builtin_constant_p(x86_leaf));
+ BUILD_BUG_ON(x86_leaf >= ARRAY_SIZE(reverse_cpuid));
+ BUILD_BUG_ON(reverse_cpuid[x86_leaf].function == 0);
- best = kvm_find_cpuid_entry(vcpu, 7, 0);
- return best && (best->ebx & bit(X86_FEATURE_FSGSBASE));
+ return reverse_cpuid[x86_leaf];
}
-static inline bool guest_cpuid_has_pku(struct kvm_vcpu *vcpu)
+static __always_inline int *guest_cpuid_get_register(struct kvm_vcpu *vcpu, unsigned x86_feature)
{
- struct kvm_cpuid_entry2 *best;
-
- best = kvm_find_cpuid_entry(vcpu, 7, 0);
- return best && (best->ecx & bit(X86_FEATURE_PKU));
-}
+ struct kvm_cpuid_entry2 *entry;
+ const struct cpuid_reg cpuid = x86_feature_cpuid(x86_feature);
-static inline bool guest_cpuid_has_longmode(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
+ entry = kvm_find_cpuid_entry(vcpu, cpuid.function, cpuid.index);
+ if (!entry)
+ return NULL;
- best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
- return best && (best->edx & bit(X86_FEATURE_LM));
+ switch (cpuid.reg) {
+ case CPUID_EAX:
+ return &entry->eax;
+ case CPUID_EBX:
+ return &entry->ebx;
+ case CPUID_ECX:
+ return &entry->ecx;
+ case CPUID_EDX:
+ return &entry->edx;
+ default:
+ BUILD_BUG();
+ return NULL;
+ }
}
-static inline bool guest_cpuid_has_osvw(struct kvm_vcpu *vcpu)
+static __always_inline bool guest_cpuid_has(struct kvm_vcpu *vcpu, unsigned x86_feature)
{
- struct kvm_cpuid_entry2 *best;
+ int *reg;
- best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
- return best && (best->ecx & bit(X86_FEATURE_OSVW));
-}
+ if (x86_feature == X86_FEATURE_XSAVE &&
+ !static_cpu_has(X86_FEATURE_XSAVE))
+ return false;
-static inline bool guest_cpuid_has_pcid(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
+ reg = guest_cpuid_get_register(vcpu, x86_feature);
+ if (!reg)
+ return false;
- best = kvm_find_cpuid_entry(vcpu, 1, 0);
- return best && (best->ecx & bit(X86_FEATURE_PCID));
+ return *reg & bit(x86_feature);
}
-static inline bool guest_cpuid_has_x2apic(struct kvm_vcpu *vcpu)
+static __always_inline void guest_cpuid_clear(struct kvm_vcpu *vcpu, unsigned x86_feature)
{
- struct kvm_cpuid_entry2 *best;
+ int *reg;
- best = kvm_find_cpuid_entry(vcpu, 1, 0);
- return best && (best->ecx & bit(X86_FEATURE_X2APIC));
+ reg = guest_cpuid_get_register(vcpu, x86_feature);
+ if (reg)
+ *reg &= ~bit(x86_feature);
}
static inline bool guest_cpuid_is_amd(struct kvm_vcpu *vcpu)
@@ -128,58 +122,6 @@ static inline bool guest_cpuid_is_amd(struct kvm_vcpu *vcpu)
return best && best->ebx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx;
}
-static inline bool guest_cpuid_has_gbpages(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
-
- best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
- return best && (best->edx & bit(X86_FEATURE_GBPAGES));
-}
-
-static inline bool guest_cpuid_has_rtm(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
-
- best = kvm_find_cpuid_entry(vcpu, 7, 0);
- return best && (best->ebx & bit(X86_FEATURE_RTM));
-}
-
-static inline bool guest_cpuid_has_mpx(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
-
- best = kvm_find_cpuid_entry(vcpu, 7, 0);
- return best && (best->ebx & bit(X86_FEATURE_MPX));
-}
-
-static inline bool guest_cpuid_has_rdtscp(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
-
- best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
- return best && (best->edx & bit(X86_FEATURE_RDTSCP));
-}
-
-/*
- * NRIPS is provided through cpuidfn 0x8000000a.edx bit 3
- */
-#define BIT_NRIPS 3
-
-static inline bool guest_cpuid_has_nrips(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
-
- best = kvm_find_cpuid_entry(vcpu, 0x8000000a, 0);
-
- /*
- * NRIPS is a scattered cpuid feature, so we can't use
- * X86_FEATURE_NRIPS here (X86_FEATURE_NRIPS would be bit
- * position 8, not 3).
- */
- return best && (best->edx & bit(BIT_NRIPS));
-}
-#undef BIT_NRIPS
-
static inline int guest_cpuid_family(struct kvm_vcpu *vcpu)
{
struct kvm_cpuid_entry2 *best;
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index fb0055953fbc..16bf6655aa85 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -28,6 +28,7 @@
#include "x86.h"
#include "tss.h"
+#include "mmu.h"
/*
* Operand types
@@ -688,16 +689,18 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
ulong la;
u32 lim;
u16 sel;
+ u8 va_bits;
la = seg_base(ctxt, addr.seg) + addr.ea;
*max_size = 0;
switch (mode) {
case X86EMUL_MODE_PROT64:
*linear = la;
- if (is_noncanonical_address(la))
+ va_bits = ctxt_virt_addr_bits(ctxt);
+ if (get_canonical(la, va_bits) != la)
goto bad;
- *max_size = min_t(u64, ~0u, (1ull << 48) - la);
+ *max_size = min_t(u64, ~0u, (1ull << va_bits) - la);
if (size > *max_size)
goto bad;
break;
@@ -1748,8 +1751,8 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
sizeof(base3), &ctxt->exception);
if (ret != X86EMUL_CONTINUE)
return ret;
- if (is_noncanonical_address(get_desc_base(&seg_desc) |
- ((u64)base3 << 32)))
+ if (emul_is_noncanonical_address(get_desc_base(&seg_desc) |
+ ((u64)base3 << 32), ctxt))
return emulate_gp(ctxt, 0);
}
load:
@@ -2333,7 +2336,7 @@ static int emulator_has_longmode(struct x86_emulate_ctxt *ctxt)
eax = 0x80000001;
ecx = 0;
- ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx);
+ ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false);
return edx & bit(X86_FEATURE_LM);
}
@@ -2636,7 +2639,7 @@ static bool vendor_intel(struct x86_emulate_ctxt *ctxt)
u32 eax, ebx, ecx, edx;
eax = ecx = 0;
- ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx);
+ ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false);
return ebx == X86EMUL_CPUID_VENDOR_GenuineIntel_ebx
&& ecx == X86EMUL_CPUID_VENDOR_GenuineIntel_ecx
&& edx == X86EMUL_CPUID_VENDOR_GenuineIntel_edx;
@@ -2656,7 +2659,7 @@ static bool em_syscall_is_enabled(struct x86_emulate_ctxt *ctxt)
eax = 0x00000000;
ecx = 0x00000000;
- ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx);
+ ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false);
/*
* Intel ("GenuineIntel")
* remark: Intel CPUs only support "syscall" in 64bit
@@ -2840,8 +2843,8 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt)
ss_sel = cs_sel + 8;
cs.d = 0;
cs.l = 1;
- if (is_noncanonical_address(rcx) ||
- is_noncanonical_address(rdx))
+ if (emul_is_noncanonical_address(rcx, ctxt) ||
+ emul_is_noncanonical_address(rdx, ctxt))
return emulate_gp(ctxt, 0);
break;
}
@@ -3551,7 +3554,7 @@ static int em_movbe(struct x86_emulate_ctxt *ctxt)
/*
* Check MOVBE is set in the guest-visible CPUID leaf.
*/
- ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx);
+ ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false);
if (!(ecx & FFL(MOVBE)))
return emulate_ud(ctxt);
@@ -3756,7 +3759,7 @@ static int em_lgdt_lidt(struct x86_emulate_ctxt *ctxt, bool lgdt)
if (rc != X86EMUL_CONTINUE)
return rc;
if (ctxt->mode == X86EMUL_MODE_PROT64 &&
- is_noncanonical_address(desc_ptr.address))
+ emul_is_noncanonical_address(desc_ptr.address, ctxt))
return emulate_gp(ctxt, 0);
if (lgdt)
ctxt->ops->set_gdt(ctxt, &desc_ptr);
@@ -3865,7 +3868,7 @@ static int em_cpuid(struct x86_emulate_ctxt *ctxt)
eax = reg_read(ctxt, VCPU_REGS_RAX);
ecx = reg_read(ctxt, VCPU_REGS_RCX);
- ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx);
+ ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, true);
*reg_write(ctxt, VCPU_REGS_RAX) = eax;
*reg_write(ctxt, VCPU_REGS_RBX) = ebx;
*reg_write(ctxt, VCPU_REGS_RCX) = ecx;
@@ -3924,7 +3927,7 @@ static int check_fxsr(struct x86_emulate_ctxt *ctxt)
{
u32 eax = 1, ebx, ecx = 0, edx;
- ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx);
+ ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false);
if (!(edx & FFL(FXSR)))
return emulate_ud(ctxt);
@@ -4097,8 +4100,17 @@ static int check_cr_write(struct x86_emulate_ctxt *ctxt)
u64 rsvd = 0;
ctxt->ops->get_msr(ctxt, MSR_EFER, &efer);
- if (efer & EFER_LMA)
- rsvd = CR3_L_MODE_RESERVED_BITS & ~CR3_PCID_INVD;
+ if (efer & EFER_LMA) {
+ u64 maxphyaddr;
+ u32 eax = 0x80000008;
+
+ if (ctxt->ops->get_cpuid(ctxt, &eax, NULL, NULL,
+ NULL, false))
+ maxphyaddr = eax & 0xff;
+ else
+ maxphyaddr = 36;
+ rsvd = rsvd_bits(maxphyaddr, 62);
+ }
if (new_val & rsvd)
return emulate_gp(ctxt, 0);
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 337b6d2730fa..dc97f2544b6f 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1160,6 +1160,12 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
return stimer_get_count(vcpu_to_stimer(vcpu, timer_index),
pdata);
}
+ case HV_X64_MSR_TSC_FREQUENCY:
+ data = (u64)vcpu->arch.virtual_tsc_khz * 1000;
+ break;
+ case HV_X64_MSR_APIC_FREQUENCY:
+ data = APIC_BUS_FREQUENCY;
+ break;
default:
vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
return 1;
@@ -1268,7 +1274,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
switch (code) {
case HVCALL_NOTIFY_LONG_SPIN_WAIT:
- kvm_vcpu_on_spin(vcpu);
+ kvm_vcpu_on_spin(vcpu, true);
break;
case HVCALL_POST_MESSAGE:
case HVCALL_SIGNAL_EVENT:
diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h
index e1e89ee4af75..9add410f195f 100644
--- a/arch/x86/kvm/kvm_cache_regs.h
+++ b/arch/x86/kvm/kvm_cache_regs.h
@@ -4,7 +4,7 @@
#define KVM_POSSIBLE_CR0_GUEST_BITS X86_CR0_TS
#define KVM_POSSIBLE_CR4_GUEST_BITS \
(X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \
- | X86_CR4_OSXMMEXCPT | X86_CR4_PGE)
+ | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE)
static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu,
enum kvm_reg reg)
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 589dcc117086..aaf10b6f5380 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -54,8 +54,6 @@
#define PRIu64 "u"
#define PRIo64 "o"
-#define APIC_BUS_CYCLE_NS 1
-
/* #define apic_debug(fmt,arg...) printk(KERN_WARNING fmt,##arg) */
#define apic_debug(fmt, arg...)
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 29caa2c3dff9..215721e1426a 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -12,6 +12,9 @@
#define KVM_APIC_SHORT_MASK 0xc0000
#define KVM_APIC_DEST_MASK 0x800
+#define APIC_BUS_CYCLE_NS 1
+#define APIC_BUS_FREQUENCY (1000000000ULL / APIC_BUS_CYCLE_NS)
+
struct kvm_timer {
struct hrtimer timer;
s64 period; /* unit: ns */
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 04d750813c9d..eca30c1eb1d9 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2169,8 +2169,8 @@ static bool kvm_sync_pages(struct kvm_vcpu *vcpu, gfn_t gfn,
}
struct mmu_page_path {
- struct kvm_mmu_page *parent[PT64_ROOT_LEVEL];
- unsigned int idx[PT64_ROOT_LEVEL];
+ struct kvm_mmu_page *parent[PT64_ROOT_MAX_LEVEL];
+ unsigned int idx[PT64_ROOT_MAX_LEVEL];
};
#define for_each_sp(pvec, sp, parents, i) \
@@ -2385,8 +2385,8 @@ static void shadow_walk_init(struct kvm_shadow_walk_iterator *iterator,
iterator->shadow_addr = vcpu->arch.mmu.root_hpa;
iterator->level = vcpu->arch.mmu.shadow_root_level;
- if (iterator->level == PT64_ROOT_LEVEL &&
- vcpu->arch.mmu.root_level < PT64_ROOT_LEVEL &&
+ if (iterator->level == PT64_ROOT_4LEVEL &&
+ vcpu->arch.mmu.root_level < PT64_ROOT_4LEVEL &&
!vcpu->arch.mmu.direct_map)
--iterator->level;
@@ -2610,9 +2610,7 @@ static bool prepare_zap_oldest_mmu_page(struct kvm *kvm,
sp = list_last_entry(&kvm->arch.active_mmu_pages,
struct kvm_mmu_page, link);
- kvm_mmu_prepare_zap_page(kvm, sp, invalid_list);
-
- return true;
+ return kvm_mmu_prepare_zap_page(kvm, sp, invalid_list);
}
/*
@@ -3262,7 +3260,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable);
-static void make_mmu_pages_available(struct kvm_vcpu *vcpu);
+static int make_mmu_pages_available(struct kvm_vcpu *vcpu);
static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
gfn_t gfn, bool prefault)
@@ -3302,7 +3300,8 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
spin_lock(&vcpu->kvm->mmu_lock);
if (mmu_notifier_retry(vcpu->kvm, mmu_seq))
goto out_unlock;
- make_mmu_pages_available(vcpu);
+ if (make_mmu_pages_available(vcpu) < 0)
+ goto out_unlock;
if (likely(!force_pt_level))
transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level);
r = __direct_map(vcpu, write, map_writable, level, gfn, pfn, prefault);
@@ -3326,8 +3325,8 @@ static void mmu_free_roots(struct kvm_vcpu *vcpu)
if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
return;
- if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL &&
- (vcpu->arch.mmu.root_level == PT64_ROOT_LEVEL ||
+ if (vcpu->arch.mmu.shadow_root_level >= PT64_ROOT_4LEVEL &&
+ (vcpu->arch.mmu.root_level >= PT64_ROOT_4LEVEL ||
vcpu->arch.mmu.direct_map)) {
hpa_t root = vcpu->arch.mmu.root_hpa;
@@ -3379,10 +3378,14 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
struct kvm_mmu_page *sp;
unsigned i;
- if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) {
+ if (vcpu->arch.mmu.shadow_root_level >= PT64_ROOT_4LEVEL) {
spin_lock(&vcpu->kvm->mmu_lock);
- make_mmu_pages_available(vcpu);
- sp = kvm_mmu_get_page(vcpu, 0, 0, PT64_ROOT_LEVEL, 1, ACC_ALL);
+ if(make_mmu_pages_available(vcpu) < 0) {
+ spin_unlock(&vcpu->kvm->mmu_lock);
+ return 1;
+ }
+ sp = kvm_mmu_get_page(vcpu, 0, 0,
+ vcpu->arch.mmu.shadow_root_level, 1, ACC_ALL);
++sp->root_count;
spin_unlock(&vcpu->kvm->mmu_lock);
vcpu->arch.mmu.root_hpa = __pa(sp->spt);
@@ -3392,7 +3395,10 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
MMU_WARN_ON(VALID_PAGE(root));
spin_lock(&vcpu->kvm->mmu_lock);
- make_mmu_pages_available(vcpu);
+ if (make_mmu_pages_available(vcpu) < 0) {
+ spin_unlock(&vcpu->kvm->mmu_lock);
+ return 1;
+ }
sp = kvm_mmu_get_page(vcpu, i << (30 - PAGE_SHIFT),
i << 30, PT32_ROOT_LEVEL, 1, ACC_ALL);
root = __pa(sp->spt);
@@ -3423,15 +3429,18 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
* Do we shadow a long mode page table? If so we need to
* write-protect the guests page table root.
*/
- if (vcpu->arch.mmu.root_level == PT64_ROO