#define SEG_TYPE_LDT 2
#define SEG_TYPE_BUSY_TSS16 3
-#define SVM_FEATURE_NPT (1 << 0)
-#define SVM_FEATURE_LBRV (1 << 1)
-#define SVM_FEATURE_SVML (1 << 2)
-#define SVM_FEATURE_NRIP (1 << 3)
-#define SVM_FEATURE_PAUSE_FILTER (1 << 10)
+#define SVM_FEATURE_NPT (1 << 0)
+#define SVM_FEATURE_LBRV (1 << 1)
+#define SVM_FEATURE_SVML (1 << 2)
+#define SVM_FEATURE_NRIP (1 << 3)
+#define SVM_FEATURE_PAUSE_FILTER (1 << 10)
#define NESTED_EXIT_HOST 0 /* Exit handled on host level */
#define NESTED_EXIT_DONE 1 /* Exit caused nested vmexit */
struct nested_state {
struct vmcb *hsave;
u64 hsave_msr;
+ u64 vm_cr_msr;
u64 vmcb;
/* These are the merged vectors */
/* gpa pointers to the real vectors */
u64 vmcb_msrpm;
+ u64 vmcb_iopm;
/* A VMEXIT is required but not yet emulated */
bool exit_required;
};
+#define MSRPM_OFFSETS 16
+static u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
+
struct vcpu_svm {
struct kvm_vcpu vcpu;
struct vmcb *vmcb;
unsigned long int3_rip;
};
+#define MSR_INVALID 0xffffffffU
+
+static struct svm_direct_access_msrs {
+ u32 index; /* Index of the MSR */
+ bool always; /* True if intercept is always on */
+} direct_access_msrs[] = {
+ { .index = MSR_K6_STAR, .always = true },
+ { .index = MSR_IA32_SYSENTER_CS, .always = true },
+#ifdef CONFIG_X86_64
+ { .index = MSR_GS_BASE, .always = true },
+ { .index = MSR_FS_BASE, .always = true },
+ { .index = MSR_KERNEL_GS_BASE, .always = true },
+ { .index = MSR_LSTAR, .always = true },
+ { .index = MSR_CSTAR, .always = true },
+ { .index = MSR_SYSCALL_MASK, .always = true },
+#endif
+ { .index = MSR_IA32_LASTBRANCHFROMIP, .always = false },
+ { .index = MSR_IA32_LASTBRANCHTOIP, .always = false },
+ { .index = MSR_IA32_LASTINTFROMIP, .always = false },
+ { .index = MSR_IA32_LASTINTTOIP, .always = false },
+ { .index = MSR_INVALID, .always = false },
+};
+
/* enable NPT for AMD64 and X86 with PAE */
#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
static bool npt_enabled = true;
#else
-static bool npt_enabled = false;
+static bool npt_enabled;
#endif
static int npt = 1;
struct kvm_ldttss_desc {
u16 limit0;
u16 base0;
- unsigned base1 : 8, type : 5, dpl : 2, p : 1;
- unsigned limit1 : 4, zero0 : 3, g : 1, base2 : 8;
+ unsigned base1:8, type:5, dpl:2, p:1;
+ unsigned limit1:4, zero0:3, g:1, base2:8;
u32 base3;
u32 zero1;
} __attribute__((packed));
#define MSRS_RANGE_SIZE 2048
#define MSRS_IN_RANGE (MSRS_RANGE_SIZE * 8 / 2)
+static u32 svm_msrpm_offset(u32 msr)
+{
+ u32 offset;
+ int i;
+
+ for (i = 0; i < NUM_MSR_MAPS; i++) {
+ if (msr < msrpm_ranges[i] ||
+ msr >= msrpm_ranges[i] + MSRS_IN_RANGE)
+ continue;
+
+ offset = (msr - msrpm_ranges[i]) / 4; /* 4 msrs per u8 */
+ offset += (i * MSRS_RANGE_SIZE); /* add range offset */
+
+ /* Now we have the u8 offset - but need the u32 offset */
+ return offset / 4;
+ }
+
+ /* MSR not in any range */
+ return MSR_INVALID;
+}
+
#define MAX_INST_SIZE 15
static inline u32 svm_has(u32 feat)
static inline void invlpga(unsigned long addr, u32 asid)
{
- asm volatile (__ex(SVM_INVLPGA) :: "a"(addr), "c"(asid));
+ asm volatile (__ex(SVM_INVLPGA) : : "a"(addr), "c"(asid));
}
static inline void force_new_asid(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
+ if (svm->vmcb->control.next_rip != 0)
+ svm->next_rip = svm->vmcb->control.next_rip;
+
if (!svm->next_rip) {
if (emulate_instruction(vcpu, 0, 0, EMULTYPE_SKIP) !=
EMULATE_DONE)
}
static void svm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
- bool has_error_code, u32 error_code)
+ bool has_error_code, u32 error_code,
+ bool reinject)
{
struct vcpu_svm *svm = to_svm(vcpu);
- /* If we are within a nested VM we'd better #VMEXIT and let the
- guest handle the exception */
- if (nested_svm_check_exception(svm, nr, has_error_code, error_code))
+ /*
+ * If we are within a nested VM we'd better #VMEXIT and let the guest
+ * handle the exception
+ */
+ if (!reinject &&
+ nested_svm_check_exception(svm, nr, has_error_code, error_code))
return;
if (nr == BP_VECTOR && !svm_has(SVM_FEATURE_NRIP)) {
sd->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1;
sd->next_asid = sd->max_asid + 1;
- kvm_get_gdt(&gdt_descr);
+ native_store_gdt(&gdt_descr);
gdt = (struct desc_struct *)gdt_descr.address;
sd->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS);
}
+static bool valid_msr_intercept(u32 index)
+{
+ int i;
+
+ for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++)
+ if (direct_access_msrs[i].index == index)
+ return true;
+
+ return false;
+}
+
static void set_msr_interception(u32 *msrpm, unsigned msr,
int read, int write)
{
+ u8 bit_read, bit_write;
+ unsigned long tmp;
+ u32 offset;
+
+ /*
+ * If this warning triggers extend the direct_access_msrs list at the
+ * beginning of the file
+ */
+ WARN_ON(!valid_msr_intercept(msr));
+
+ offset = svm_msrpm_offset(msr);
+ bit_read = 2 * (msr & 0x0f);
+ bit_write = 2 * (msr & 0x0f) + 1;
+ tmp = msrpm[offset];
+
+ BUG_ON(offset == MSR_INVALID);
+
+ read ? clear_bit(bit_read, &tmp) : set_bit(bit_read, &tmp);
+ write ? clear_bit(bit_write, &tmp) : set_bit(bit_write, &tmp);
+
+ msrpm[offset] = tmp;
+}
+
+static void svm_vcpu_init_msrpm(u32 *msrpm)
+{
int i;
- for (i = 0; i < NUM_MSR_MAPS; i++) {
- if (msr >= msrpm_ranges[i] &&
- msr < msrpm_ranges[i] + MSRS_IN_RANGE) {
- u32 msr_offset = (i * MSRS_IN_RANGE + msr -
- msrpm_ranges[i]) * 2;
-
- u32 *base = msrpm + (msr_offset / 32);
- u32 msr_shift = msr_offset % 32;
- u32 mask = ((write) ? 0 : 2) | ((read) ? 0 : 1);
- *base = (*base & ~(0x3 << msr_shift)) |
- (mask << msr_shift);
+ memset(msrpm, 0xff, PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER));
+
+ for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) {
+ if (!direct_access_msrs[i].always)
+ continue;
+
+ set_msr_interception(msrpm, direct_access_msrs[i].index, 1, 1);
+ }
+}
+
+static void add_msr_offset(u32 offset)
+{
+ int i;
+
+ for (i = 0; i < MSRPM_OFFSETS; ++i) {
+
+ /* Offset already in list? */
+ if (msrpm_offsets[i] == offset)
return;
- }
+
+ /* Slot used by another offset? */
+ if (msrpm_offsets[i] != MSR_INVALID)
+ continue;
+
+ /* Add offset to list */
+ msrpm_offsets[i] = offset;
+
+ return;
}
+
+ /*
+ * If this BUG triggers the msrpm_offsets table has an overflow. Just
+ * increase MSRPM_OFFSETS in this case.
+ */
BUG();
}
-static void svm_vcpu_init_msrpm(u32 *msrpm)
+static void init_msrpm_offsets(void)
{
- memset(msrpm, 0xff, PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER));
+ int i;
-#ifdef CONFIG_X86_64
- set_msr_interception(msrpm, MSR_GS_BASE, 1, 1);
- set_msr_interception(msrpm, MSR_FS_BASE, 1, 1);
- set_msr_interception(msrpm, MSR_KERNEL_GS_BASE, 1, 1);
- set_msr_interception(msrpm, MSR_LSTAR, 1, 1);
- set_msr_interception(msrpm, MSR_CSTAR, 1, 1);
- set_msr_interception(msrpm, MSR_SYSCALL_MASK, 1, 1);
-#endif
- set_msr_interception(msrpm, MSR_K6_STAR, 1, 1);
- set_msr_interception(msrpm, MSR_IA32_SYSENTER_CS, 1, 1);
+ memset(msrpm_offsets, 0xff, sizeof(msrpm_offsets));
+
+ for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) {
+ u32 offset;
+
+ offset = svm_msrpm_offset(direct_access_msrs[i].index);
+ BUG_ON(offset == MSR_INVALID);
+
+ add_msr_offset(offset);
+ }
}
static void svm_enable_lbrv(struct vcpu_svm *svm)
memset(iopm_va, 0xff, PAGE_SIZE * (1 << IOPM_ALLOC_ORDER));
iopm_base = page_to_pfn(iopm_pages) << PAGE_SHIFT;
+ init_msrpm_offsets();
+
if (boot_cpu_has(X86_FEATURE_NX))
kvm_enable_efer_bits(EFER_NX);
{
seg->selector = 0;
seg->attrib = SVM_SELECTOR_P_MASK | SVM_SELECTOR_S_MASK |
- SVM_SELECTOR_WRITE_MASK; /* Read/Write Data Segment */
+ SVM_SELECTOR_WRITE_MASK; /* Read/Write Data Segment */
seg->limit = 0xffff;
seg->base = 0;
}
svm->vcpu.fpu_active = 1;
- control->intercept_cr_read = INTERCEPT_CR0_MASK |
+ control->intercept_cr_read = INTERCEPT_CR0_MASK |
INTERCEPT_CR3_MASK |
INTERCEPT_CR4_MASK;
- control->intercept_cr_write = INTERCEPT_CR0_MASK |
+ control->intercept_cr_write = INTERCEPT_CR0_MASK |
INTERCEPT_CR3_MASK |
INTERCEPT_CR4_MASK |
INTERCEPT_CR8_MASK;
- control->intercept_dr_read = INTERCEPT_DR0_MASK |
+ control->intercept_dr_read = INTERCEPT_DR0_MASK |
INTERCEPT_DR1_MASK |
INTERCEPT_DR2_MASK |
INTERCEPT_DR3_MASK |
INTERCEPT_DR6_MASK |
INTERCEPT_DR7_MASK;
- control->intercept_dr_write = INTERCEPT_DR0_MASK |
+ control->intercept_dr_write = INTERCEPT_DR0_MASK |
INTERCEPT_DR1_MASK |
INTERCEPT_DR2_MASK |
INTERCEPT_DR3_MASK |
(1 << MC_VECTOR);
- control->intercept = (1ULL << INTERCEPT_INTR) |
+ control->intercept = (1ULL << INTERCEPT_INTR) |
(1ULL << INTERCEPT_NMI) |
(1ULL << INTERCEPT_SMI) |
(1ULL << INTERCEPT_SELECTIVE_CR0) |
save->rip = 0x0000fff0;
svm->vcpu.arch.regs[VCPU_REGS_RIP] = save->rip;
- /* This is the guest-visible cr0 value.
+ /*
+ * This is the guest-visible cr0 value.
* svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0.
*/
svm->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
svm_vcpu_init_msrpm(svm->msrpm);
svm->nested.msrpm = page_address(nested_msrpm_pages);
+ svm_vcpu_init_msrpm(svm->nested.msrpm);
svm->vmcb = page_address(page);
clear_page(svm->vmcb);
var->db = (s->attrib >> SVM_SELECTOR_DB_SHIFT) & 1;
var->g = (s->attrib >> SVM_SELECTOR_G_SHIFT) & 1;
- /* AMD's VMCB does not have an explicit unusable field, so emulate it
+ /*
+ * AMD's VMCB does not have an explicit unusable field, so emulate it
* for cross vendor migration purposes by "not present"
*/
var->unusable = !var->present || (var->type == 0);
var->type |= 0x1;
break;
case VCPU_SREG_SS:
- /* On AMD CPUs sometimes the DB bit in the segment
+ /*
+ * On AMD CPUs sometimes the DB bit in the segment
* descriptor is left as 1, although the whole segment has
* been made unusable. Clear it here to pass an Intel VMX
* entry check when cross vendor migrating.
{
struct vcpu_svm *svm = to_svm(vcpu);
+ if (is_nested(svm)) {
+ /*
+ * We are here because we run in nested mode, the host kvm
+ * intercepts cr0 writes but the l1 hypervisor does not.
+ * But the L1 hypervisor may intercept selective cr0 writes.
+ * This needs to be checked here.
+ */
+ unsigned long old, new;
+
+ /* Remove bits that would trigger a real cr0 write intercept */
+ old = vcpu->arch.cr0 & SVM_CR0_SELECTIVE_MASK;
+ new = cr0 & SVM_CR0_SELECTIVE_MASK;
+
+ if (old == new) {
+ /* cr0 write with ts and mp unchanged */
+ svm->vmcb->control.exit_code = SVM_EXIT_CR0_SEL_WRITE;
+ if (nested_svm_exit_handled(svm) == NESTED_EXIT_DONE)
+ return;
+ }
+ }
+
#ifdef CONFIG_X86_64
if (vcpu->arch.efer & EFER_LME) {
if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) {
svm->vmcb->control.asid = sd->next_asid++;
}
-static int svm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *dest)
-{
- struct vcpu_svm *svm = to_svm(vcpu);
-
- switch (dr) {
- case 0 ... 3:
- *dest = vcpu->arch.db[dr];
- break;
- case 4:
- if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
- return EMULATE_FAIL; /* will re-inject UD */
- /* fall through */
- case 6:
- if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
- *dest = vcpu->arch.dr6;
- else
- *dest = svm->vmcb->save.dr6;
- break;
- case 5:
- if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
- return EMULATE_FAIL; /* will re-inject UD */
- /* fall through */
- case 7:
- if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
- *dest = vcpu->arch.dr7;
- else
- *dest = svm->vmcb->save.dr7;
- break;
- }
-
- return EMULATE_DONE;
-}
-
-static int svm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long value)
+static void svm_set_dr7(struct kvm_vcpu *vcpu, unsigned long value)
{
struct vcpu_svm *svm = to_svm(vcpu);
- switch (dr) {
- case 0 ... 3:
- vcpu->arch.db[dr] = value;
- if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
- vcpu->arch.eff_db[dr] = value;
- break;
- case 4:
- if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
- return EMULATE_FAIL; /* will re-inject UD */
- /* fall through */
- case 6:
- vcpu->arch.dr6 = (value & DR6_VOLATILE) | DR6_FIXED_1;
- break;
- case 5:
- if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
- return EMULATE_FAIL; /* will re-inject UD */
- /* fall through */
- case 7:
- vcpu->arch.dr7 = (value & DR7_VOLATILE) | DR7_FIXED_1;
- if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) {
- svm->vmcb->save.dr7 = vcpu->arch.dr7;
- vcpu->arch.switch_db_regs = (value & DR7_BP_EN_MASK);
- }
- break;
- }
-
- return EMULATE_DONE;
+ svm->vmcb->save.dr7 = value;
}
static int pf_interception(struct vcpu_svm *svm)
}
if (svm->vcpu.guest_debug &
- (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)){
+ (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) {
kvm_run->exit_reason = KVM_EXIT_DEBUG;
kvm_run->debug.arch.pc =
svm->vmcb->save.cs.base + svm->vmcb->save.rip;
excp = h_excp | n_excp;
} else {
excp = svm->vmcb->control.intercept_exceptions;
- excp &= ~(1 << NM_VECTOR);
+ excp &= ~(1 << NM_VECTOR);
}
svm->vmcb->control.intercept_exceptions = excp;
return 1;
}
-static int mc_interception(struct vcpu_svm *svm)
+static void svm_handle_mce(struct vcpu_svm *svm)
{
/*
* On an #MC intercept the MCE handler is not called automatically in
"int $0x12\n");
/* not sure if we ever come back to this point */
+ return;
+}
+
+static int mc_interception(struct vcpu_svm *svm)
+{
return 1;
}
static int io_interception(struct vcpu_svm *svm)
{
+ struct kvm_vcpu *vcpu = &svm->vcpu;
u32 io_info = svm->vmcb->control.exit_info_1; /* address size bug? */
int size, in, string;
unsigned port;
++svm->vcpu.stat.io_exits;
-
- svm->next_rip = svm->vmcb->control.exit_info_2;
-
string = (io_info & SVM_IOIO_STR_MASK) != 0;
-
- if (string) {
- if (emulate_instruction(&svm->vcpu,
- 0, 0, 0) == EMULATE_DO_MMIO)
- return 0;
- return 1;
- }
-
in = (io_info & SVM_IOIO_TYPE_MASK) != 0;
+ if (string || in)
+ return !(emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DO_MMIO);
+
port = io_info >> 16;
size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT;
-
+ svm->next_rip = svm->vmcb->control.exit_info_2;
skip_emulated_instruction(&svm->vcpu);
- return kvm_emulate_pio(&svm->vcpu, in, size, port);
+
+ return kvm_fast_pio_out(vcpu, size, port);
}
static int nmi_interception(struct vcpu_svm *svm)
if (!(svm->vcpu.arch.hflags & HF_HIF_MASK))
return false;
- svm->vmcb->control.exit_code = SVM_EXIT_INTR;
+ svm->vmcb->control.exit_code = SVM_EXIT_INTR;
+ svm->vmcb->control.exit_info_1 = 0;
+ svm->vmcb->control.exit_info_2 = 0;
if (svm->nested.intercept & 1ULL) {
/*
return true;
}
+/* This function returns true if it is save to enable the nmi window */
+static inline bool nested_svm_nmi(struct vcpu_svm *svm)
+{
+ if (!is_nested(svm))
+ return true;
+
+ if (!(svm->nested.intercept & (1ULL << INTERCEPT_NMI)))
+ return true;
+
+ svm->vmcb->control.exit_code = SVM_EXIT_NMI;
+ svm->nested.exit_required = true;
+
+ return false;
+}
+
static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, struct page **_page)
{
struct page *page;
kvm_release_page_dirty(page);
}
-static bool nested_svm_exit_handled_msr(struct vcpu_svm *svm)
+static int nested_svm_intercept_ioio(struct vcpu_svm *svm)
{
- u32 param = svm->vmcb->control.exit_info_1 & 1;
- u32 msr = svm->vcpu.arch.regs[VCPU_REGS_RCX];
- bool ret = false;
- u32 t0, t1;
- u8 val;
+ unsigned port;
+ u8 val, bit;
+ u64 gpa;
+
+ if (!(svm->nested.intercept & (1ULL << INTERCEPT_IOIO_PROT)))
+ return NESTED_EXIT_HOST;
+
+ port = svm->vmcb->control.exit_info_1 >> 16;
+ gpa = svm->nested.vmcb_iopm + (port / 8);
+ bit = port % 8;
+ val = 0;
+
+ if (kvm_read_guest(svm->vcpu.kvm, gpa, &val, 1))
+ val &= (1 << bit);
+
+ return val ? NESTED_EXIT_DONE : NESTED_EXIT_HOST;
+}
+
+static int nested_svm_exit_handled_msr(struct vcpu_svm *svm)
+{
+ u32 offset, msr, value;
+ int write, mask;
if (!(svm->nested.intercept & (1ULL << INTERCEPT_MSR_PROT)))
- return false;
+ return NESTED_EXIT_HOST;
- switch (msr) {
- case 0 ... 0x1fff:
- t0 = (msr * 2) % 8;
- t1 = msr / 8;
- break;
- case 0xc0000000 ... 0xc0001fff:
- t0 = (8192 + msr - 0xc0000000) * 2;
- t1 = (t0 / 8);
- t0 %= 8;
- break;
- case 0xc0010000 ... 0xc0011fff:
- t0 = (16384 + msr - 0xc0010000) * 2;
- t1 = (t0 / 8);
- t0 %= 8;
- break;
- default:
- ret = true;
- goto out;
- }
+ msr = svm->vcpu.arch.regs[VCPU_REGS_RCX];
+ offset = svm_msrpm_offset(msr);
+ write = svm->vmcb->control.exit_info_1 & 1;
+ mask = 1 << ((2 * (msr & 0xf)) + write);
- if (!kvm_read_guest(svm->vcpu.kvm, svm->nested.vmcb_msrpm + t1, &val, 1))
- ret = val & ((1 << param) << t0);
+ if (offset == MSR_INVALID)
+ return NESTED_EXIT_DONE;
-out:
- return ret;
+ /* Offset is in 32 bit units but need in 8 bit units */
+ offset *= 4;
+
+ if (kvm_read_guest(svm->vcpu.kvm, svm->nested.vmcb_msrpm + offset, &value, 4))
+ return NESTED_EXIT_DONE;
+
+ return (value & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST;
}
static int nested_svm_exit_special(struct vcpu_svm *svm)
switch (exit_code) {
case SVM_EXIT_INTR:
case SVM_EXIT_NMI:
+ case SVM_EXIT_EXCP_BASE + MC_VECTOR:
return NESTED_EXIT_HOST;
- /* For now we are always handling NPFs when using them */
case SVM_EXIT_NPF:
+ /* For now we are always handling NPFs when using them */
if (npt_enabled)
return NESTED_EXIT_HOST;
break;
- /* When we're shadowing, trap PFs */
case SVM_EXIT_EXCP_BASE + PF_VECTOR:
+ /* When we're shadowing, trap PFs */
if (!npt_enabled)
return NESTED_EXIT_HOST;
break;
case SVM_EXIT_MSR:
vmexit = nested_svm_exit_handled_msr(svm);
break;
+ case SVM_EXIT_IOIO:
+ vmexit = nested_svm_intercept_ioio(svm);
+ break;
case SVM_EXIT_READ_CR0 ... SVM_EXIT_READ_CR8: {
u32 cr_bits = 1 << (exit_code - SVM_EXIT_READ_CR0);
if (svm->nested.intercept_cr_read & cr_bits)
vmexit = NESTED_EXIT_DONE;
break;
}
+ case SVM_EXIT_ERR: {
+ vmexit = NESTED_EXIT_DONE;
+ break;
+ }
default: {
u64 exit_bits = 1ULL << (exit_code - SVM_EXIT_INTR);
if (svm->nested.intercept & exit_bits)
nested_vmcb->save.gdtr = vmcb->save.gdtr;
nested_vmcb->save.idtr = vmcb->save.idtr;
nested_vmcb->save.cr0 = kvm_read_cr0(&svm->vcpu);
- if (npt_enabled)
- nested_vmcb->save.cr3 = vmcb->save.cr3;
- else
- nested_vmcb->save.cr3 = svm->vcpu.arch.cr3;
+ nested_vmcb->save.cr3 = svm->vcpu.arch.cr3;
nested_vmcb->save.cr2 = vmcb->save.cr2;
nested_vmcb->save.cr4 = svm->vcpu.arch.cr4;
nested_vmcb->save.rflags = vmcb->save.rflags;
static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
{
- u32 *nested_msrpm;
- struct page *page;
+ /*
+ * This function merges the msr permission bitmaps of kvm and the
+ * nested vmcb. It is omptimized in that it only merges the parts where
+ * the kvm msr permission bitmap may contain zero bits
+ */
int i;
- nested_msrpm = nested_svm_map(svm, svm->nested.vmcb_msrpm, &page);
- if (!nested_msrpm)
- return false;
+ if (!(svm->nested.intercept & (1ULL << INTERCEPT_MSR_PROT)))
+ return true;
- for (i=0; i< PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER) / 4; i++)
- svm->nested.msrpm[i] = svm->msrpm[i] | nested_msrpm[i];
+ for (i = 0; i < MSRPM_OFFSETS; i++) {
+ u32 value, p;
+ u64 offset;
- svm->vmcb->control.msrpm_base_pa = __pa(svm->nested.msrpm);
+ if (msrpm_offsets[i] == 0xffffffff)
+ break;
- nested_svm_unmap(page);
+ p = msrpm_offsets[i];
+ offset = svm->nested.vmcb_msrpm + (p * 4);
+
+ if (kvm_read_guest(svm->vcpu.kvm, offset, &value, 4))
+ return false;
+
+ svm->nested.msrpm[p] = svm->msrpm[p] | value;
+ }
+
+ svm->vmcb->control.msrpm_base_pa = __pa(svm->nested.msrpm);
return true;
}
if (!nested_vmcb)
return false;
- trace_kvm_nested_vmrun(svm->vmcb->save.rip - 3, svm->nested.vmcb,
+ trace_kvm_nested_vmrun(svm->vmcb->save.rip - 3, vmcb_gpa,
nested_vmcb->save.rip,
nested_vmcb->control.int_ctl,
nested_vmcb->control.event_inj,
nested_vmcb->control.nested_ctl);
+ trace_kvm_nested_intercepts(nested_vmcb->control.intercept_cr_read,
+ nested_vmcb->control.intercept_cr_write,
+ nested_vmcb->control.intercept_exceptions,
+ nested_vmcb->control.intercept);
+
/* Clear internal status */
kvm_clear_exception_queue(&svm->vcpu);
kvm_clear_interrupt_queue(&svm->vcpu);
- /* Save the old vmcb, so we don't need to pick what we save, but
- can restore everything when a VMEXIT occurs */
+ /*
+ * Save the old vmcb, so we don't need to pick what we save, but can
+ * restore everything when a VMEXIT occurs
+ */
hsave->save.es = vmcb->save.es;
hsave->save.cs = vmcb->save.cs;
hsave->save.ss = vmcb->save.ss;
if (npt_enabled) {
svm->vmcb->save.cr3 = nested_vmcb->save.cr3;
svm->vcpu.arch.cr3 = nested_vmcb->save.cr3;
- } else {
+ } else
kvm_set_cr3(&svm->vcpu, nested_vmcb->save.cr3);
- kvm_mmu_reset_context(&svm->vcpu);
- }
+
+ /* Guest paging mode is active - reset mmu */
+ kvm_mmu_reset_context(&svm->vcpu);
+
svm->vmcb->save.cr2 = svm->vcpu.arch.cr2 = nested_vmcb->save.cr2;
kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, nested_vmcb->save.rax);
kvm_register_write(&svm->vcpu, VCPU_REGS_RSP, nested_vmcb->save.rsp);
kvm_register_write(&svm->vcpu, VCPU_REGS_RIP, nested_vmcb->save.rip);
+
/* In case we don't even reach vcpu_run, the fields are not updated */
svm->vmcb->save.rax = nested_vmcb->save.rax;
svm->vmcb->save.rsp = nested_vmcb->save.rsp;
svm->vmcb->save.dr6 = nested_vmcb->save.dr6;
svm->vmcb->save.cpl = nested_vmcb->save.cpl;
- svm->nested.vmcb_msrpm = nested_vmcb->control.msrpm_base_pa;
+ svm->nested.vmcb_msrpm = nested_vmcb->control.msrpm_base_pa & ~0x0fffULL;
+ svm->nested.vmcb_iopm = nested_vmcb->control.iopm_base_pa & ~0x0fffULL;
/* cache intercepts */
svm->nested.intercept_cr_read = nested_vmcb->control.intercept_cr_read;
svm->vmcb->control.intercept_cr_write &= ~INTERCEPT_CR8_MASK;
}
- /* We don't want a nested guest to be more powerful than the guest,
- so all intercepts are ORed */
+ /* We don't want to see VMMCALLs from a nested guest */
+ svm->vmcb->control.intercept &= ~(1ULL << INTERCEPT_VMMCALL);
+
+ /*
+ * We don't want a nested guest to be more powerful than the guest, so
+ * all intercepts are ORed
+ */
svm->vmcb->control.intercept_cr_read |=
nested_vmcb->control.intercept_cr_read;
svm->vmcb->control.intercept_cr_write |=
svm->vmcb->control.exit_int_info & SVM_EXITINTINFO_TYPE_MASK;
uint32_t idt_v =
svm->vmcb->control.exit_int_info & SVM_EXITINTINFO_VALID;
+ bool has_error_code = false;
+ u32 error_code = 0;
tss_selector = (u16)svm->vmcb->control.exit_info_1;
svm->vcpu.arch.nmi_injected = false;
break;
case SVM_EXITINTINFO_TYPE_EXEPT:
+ if (svm->vmcb->control.exit_info_2 &
+ (1ULL << SVM_EXITINFOSHIFT_TS_HAS_ERROR_CODE)) {
+ has_error_code = true;
+ error_code =
+ (u32)svm->vmcb->control.exit_info_2;
+ }
kvm_clear_exception_queue(&svm->vcpu);
break;
case SVM_EXITINTINFO_TYPE_INTR:
(int_vec == OF_VECTOR || int_vec == BP_VECTOR)))
skip_emulated_instruction(&svm->vcpu);
- return kvm_task_switch(&svm->vcpu, tss_selector, reason);
+ if (kvm_task_switch(&svm->vcpu, tss_selector, reason,
+ has_error_code, error_code) == EMULATE_FAIL) {
+ svm->vcpu.run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+ svm->vcpu.run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+ svm->vcpu.run->internal.ndata = 0;
+ return 0;
+ }
+ return 1;
}
static int cpuid_interception(struct vcpu_svm *svm)
static int iret_interception(struct vcpu_svm *svm)
{
++svm->vcpu.stat.nmi_window_exits;
- svm->vmcb->control.intercept &= ~(1UL << INTERCEPT_IRET);
+ svm->vmcb->control.intercept &= ~(1ULL << INTERCEPT_IRET);
svm->vcpu.arch.hflags |= HF_IRET_MASK;
return 1;
}
case MSR_IA32_SYSENTER_ESP:
*data = svm->sysenter_esp;
break;
- /* Nobody will change the following 5 values in the VMCB so
- we can safely return them on rdmsr. They will always be 0
- until LBRV is implemented. */
+ /*
+ * Nobody will change the following 5 values in the VMCB so we can
+ * safely return them on rdmsr. They will always be 0 until LBRV is
+ * implemented.
+ */
case MSR_IA32_DEBUGCTLMSR:
*data = svm->vmcb->save.dbgctl;
break;
*data = svm->nested.hsave_msr;
break;
case MSR_VM_CR:
- *data = 0;
+ *data = svm->nested.vm_cr_msr;
break;
case MSR_IA32_UCODE_REV:
*data = 0x01000065;
return 1;
}
+static int svm_set_vm_cr(struct kvm_vcpu *vcpu, u64 data)
+{
+ struct vcpu_svm *svm = to_svm(vcpu);
+ int svm_dis, chg_mask;
+
+ if (data & ~SVM_VM_CR_VALID_MASK)
+ return 1;
+
+ chg_mask = SVM_VM_CR_VALID_MASK;
+
+ if (svm->nested.vm_cr_msr & SVM_VM_CR_SVM_DIS_MASK)
+ chg_mask &= ~(SVM_VM_CR_SVM_LOCK_MASK | SVM_VM_CR_SVM_DIS_MASK);
+
+ svm->nested.vm_cr_msr &= ~chg_mask;
+ svm->nested.vm_cr_msr |= (data & chg_mask);
+
+ svm_dis = svm->nested.vm_cr_msr & SVM_VM_CR_SVM_DIS_MASK;
+
+ /* check for svm_disable while efer.svme is set */
+ if (svm_dis && (vcpu->arch.efer & EFER_SVME))
+ return 1;
+
+ return 0;
+}
+
static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data)
{
struct vcpu_svm *svm = to_svm(vcpu);
svm->nested.hsave_msr = data;
break;
case MSR_VM_CR:
+ return svm_set_vm_cr(vcpu, data);
case MSR_VM_IGNNE:
pr_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data);
break;
}
static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = {
- [SVM_EXIT_READ_CR0] = emulate_on_interception,
- [SVM_EXIT_READ_CR3] = emulate_on_interception,
- [SVM_EXIT_READ_CR4] = emulate_on_interception,
- [SVM_EXIT_READ_CR8] = emulate_on_interception,
+ [SVM_EXIT_READ_CR0] = emulate_on_interception,
+ [SVM_EXIT_READ_CR3] = emulate_on_interception,
+ [SVM_EXIT_READ_CR4] = emulate_on_interception,
+ [SVM_EXIT_READ_CR8] = emulate_on_interception,
[SVM_EXIT_CR0_SEL_WRITE] = emulate_on_interception,
- [SVM_EXIT_WRITE_CR0] = emulate_on_interception,
- [SVM_EXIT_WRITE_CR3] = emulate_on_interception,
- [SVM_EXIT_WRITE_CR4] = emulate_on_interception,
- [SVM_EXIT_WRITE_CR8] = cr8_write_interception,
- [SVM_EXIT_READ_DR0] = emulate_on_interception,
+ [SVM_EXIT_WRITE_CR0] = emulate_on_interception,
+ [SVM_EXIT_WRITE_CR3] = emulate_on_interception,
+ [SVM_EXIT_WRITE_CR4] = emulate_on_interception,
+ [SVM_EXIT_WRITE_CR8] = cr8_write_interception,
+ [SVM_EXIT_READ_DR0] = emulate_on_interception,
[SVM_EXIT_READ_DR1] = emulate_on_interception,
[SVM_EXIT_READ_DR2] = emulate_on_interception,
[SVM_EXIT_READ_DR3] = emulate_on_interception,
[SVM_EXIT_EXCP_BASE + DB_VECTOR] = db_interception,
[SVM_EXIT_EXCP_BASE + BP_VECTOR] = bp_interception,
[SVM_EXIT_EXCP_BASE + UD_VECTOR] = ud_interception,
- [SVM_EXIT_EXCP_BASE + PF_VECTOR] = pf_interception,
- [SVM_EXIT_EXCP_BASE + NM_VECTOR] = nm_interception,
- [SVM_EXIT_EXCP_BASE + MC_VECTOR] = mc_interception,
- [SVM_EXIT_INTR] = intr_interception,
+ [SVM_EXIT_EXCP_BASE + PF_VECTOR] = pf_interception,
+ [SVM_EXIT_EXCP_BASE + NM_VECTOR] = nm_interception,
+ [SVM_EXIT_EXCP_BASE + MC_VECTOR] = mc_interception,
+ [SVM_EXIT_INTR] = intr_interception,
[SVM_EXIT_NMI] = nmi_interception,
[SVM_EXIT_SMI] = nop_on_interception,
[SVM_EXIT_INIT] = nop_on_interception,
[SVM_EXIT_VINTR] = interrupt_window_interception,
- /* [SVM_EXIT_CR0_SEL_WRITE] = emulate_on_interception, */
[SVM_EXIT_CPUID] = cpuid_interception,
[SVM_EXIT_IRET] = iret_interception,
[SVM_EXIT_INVD] = emulate_on_interception,
[SVM_EXIT_HLT] = halt_interception,
[SVM_EXIT_INVLPG] = invlpg_interception,
[SVM_EXIT_INVLPGA] = invlpga_interception,
- [SVM_EXIT_IOIO] = io_interception,
+ [SVM_EXIT_IOIO] = io_interception,
[SVM_EXIT_MSR] = msr_interception,
[SVM_EXIT_TASK_SWITCH] = task_switch_interception,
[SVM_EXIT_SHUTDOWN] = shutdown_interception,
struct kvm_run *kvm_run = vcpu->run;
u32 exit_code = svm->vmcb->control.exit_code;
- trace_kvm_exit(exit_code, svm->vmcb->save.rip);
+ trace_kvm_exit(exit_code, vcpu);
+
+ if (!(svm->vmcb->control.intercept_cr_write & INTERCEPT_CR0_MASK))
+ vcpu->arch.cr0 = svm->vmcb->save.cr0;
+ if (npt_enabled)
+ vcpu->arch.cr3 = svm->vmcb->save.cr3;
if (unlikely(svm->nested.exit_required)) {
nested_svm_vmexit(svm);
svm_complete_interrupts(svm);
- if (!(svm->vmcb->control.intercept_cr_write & INTERCEPT_CR0_MASK))
- vcpu->arch.cr0 = svm->vmcb->save.cr0;
- if (npt_enabled)
- vcpu->arch.cr3 = svm->vmcb->save.cr3;
-
if (svm->vmcb->control.exit_code == SVM_EXIT_ERR) {
kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
kvm_run->fail_entry.hardware_entry_failure_reason
svm->vmcb->control.event_inj = SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_NMI;
vcpu->arch.hflags |= HF_NMI_MASK;
- svm->vmcb->control.intercept |= (1UL << INTERCEPT_IRET);
+ svm->vmcb->control.intercept |= (1ULL << INTERCEPT_IRET);
++vcpu->stat.nmi_injections;
}
{
struct vcpu_svm *svm = to_svm(vcpu);
struct vmcb *vmcb = svm->vmcb;
- return !(vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) &&
- !(svm->vcpu.arch.hflags & HF_NMI_MASK);
+ int ret;
+ ret = !(vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) &&
+ !(svm->vcpu.arch.hflags & HF_NMI_MASK);
+ ret = ret && gif_set(svm) && nested_svm_nmi(svm);
+
+ return ret;
}
static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu)
if (masked) {
svm->vcpu.arch.hflags |= HF_NMI_MASK;
- svm->vmcb->control.intercept |= (1UL << INTERCEPT_IRET);
+ svm->vmcb->control.intercept |= (1ULL << INTERCEPT_IRET);
} else {
svm->vcpu.arch.hflags &= ~HF_NMI_MASK;
- svm->vmcb->control.intercept &= ~(1UL << INTERCEPT_IRET);
+ svm->vmcb->control.intercept &= ~(1ULL << INTERCEPT_IRET);
}
}
{
struct vcpu_svm *svm = to_svm(vcpu);
- /* In case GIF=0 we can't rely on the CPU to tell us when
- * GIF becomes 1, because that's a separate STGI/VMRUN intercept.
- * The next time we get that intercept, this function will be
- * called again though and we'll get the vintr intercept. */
+ /*
+ * In case GIF=0 we can't rely on the CPU to tell us when GIF becomes
+ * 1, because that's a separate STGI/VMRUN intercept. The next time we
+ * get that intercept, this function will be called again though and
+ * we'll get the vintr intercept.
+ */
if (gif_set(svm) && nested_svm_intr(svm)) {
svm_set_vintr(svm);
svm_inject_irq(svm, 0x0);
== HF_NMI_MASK)
return; /* IRET will cause a vm exit */
- /* Something prevents NMI from been injected. Single step over
- possible problem (IRET or exception injection or interrupt
- shadow) */
+ /*
+ * Something prevents NMI from been injected. Single step over possible
+ * problem (IRET or exception injection or interrupt shadow)
+ */
svm->nmi_singlestep = true;
svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF);
update_db_intercept(vcpu);
svm->vcpu.arch.nmi_injected = true;
break;
case SVM_EXITINTINFO_TYPE_EXEPT:
- if (is_nested(svm))
- break;
/*
* In case of software exceptions, do not reinject the vector,
* but re-execute the instruction instead. Rewind RIP first
}
if (exitintinfo & SVM_EXITINTINFO_VALID_ERR) {
u32 err = svm->vmcb->control.exit_int_info_err;
- kvm_queue_exception_e(&svm->vcpu, vector, err);
+ kvm_requeue_exception_e(&svm->vcpu, vector, err);
} else
- kvm_queue_exception(&svm->vcpu, vector);
+ kvm_requeue_exception(&svm->vcpu, vector);
break;
case SVM_EXITINTINFO_TYPE_INTR:
kvm_queue_interrupt(&svm->vcpu, vector, false);
u16 gs_selector;
u16 ldt_selector;
+ svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
+ svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
+ svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP];
+
/*
* A vmexit emulation is required before the vcpu can be executed
* again.
if (unlikely(svm->nested.exit_required))
return;
- svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
- svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
- svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP];
-
pre_svm_run(svm);
sync_lapic_to_cr8(vcpu);
vcpu->arch.regs_avail &= ~(1 << VCPU_EXREG_PDPTR);
vcpu->arch.regs_dirty &= ~(1 << VCPU_EXREG_PDPTR);
}
+
+ /*
+ * We need to handle MC intercepts here before the vcpu has a chance to
+ * change the physical cpu
+ */
+ if (unlikely(svm->vmcb->control.exit_code ==
+ SVM_EXIT_EXCP_BASE + MC_VECTOR))
+ svm_handle_mce(svm);
}
#undef R
{
}
+static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
+{
+ switch (func) {
+ case 0x8000000A:
+ entry->eax = 1; /* SVM revision 1 */
+ entry->ebx = 8; /* Lets support 8 ASIDs in case we add proper
+ ASID emulation to nested SVM */
+ entry->ecx = 0; /* Reserved */
+ entry->edx = 0; /* Do not support any additional features */
+
+ break;
+ }
+}
+
static const struct trace_print_flags svm_exit_reasons_str[] = {
- { SVM_EXIT_READ_CR0, "read_cr0" },
- { SVM_EXIT_READ_CR3, "read_cr3" },
- { SVM_EXIT_READ_CR4, "read_cr4" },
- { SVM_EXIT_READ_CR8, "read_cr8" },
- { SVM_EXIT_WRITE_CR0, "write_cr0" },
- { SVM_EXIT_WRITE_CR3, "write_cr3" },
- { SVM_EXIT_WRITE_CR4, "write_cr4" },
- { SVM_EXIT_WRITE_CR8, "write_cr8" },
- { SVM_EXIT_READ_DR0, "read_dr0" },
- { SVM_EXIT_READ_DR1, "read_dr1" },
- { SVM_EXIT_READ_DR2, "read_dr2" },
- { SVM_EXIT_READ_DR3, "read_dr3" },
- { SVM_EXIT_WRITE_DR0, "write_dr0" },
- { SVM_EXIT_WRITE_DR1, "write_dr1" },
- { SVM_EXIT_WRITE_DR2, "write_dr2" },
- { SVM_EXIT_WRITE_DR3, "write_dr3" },
- { SVM_EXIT_WRITE_DR5, "write_dr5" },
- { SVM_EXIT_WRITE_DR7, "write_dr7" },
+ { SVM_EXIT_READ_CR0, "read_cr0" },
+ { SVM_EXIT_READ_CR3, "read_cr3" },
+ { SVM_EXIT_READ_CR4, "read_cr4" },
+ { SVM_EXIT_READ_CR8, "read_cr8" },
+ { SVM_EXIT_WRITE_CR0, "write_cr0" },
+ { SVM_EXIT_WRITE_CR3, "write_cr3" },
+ { SVM_EXIT_WRITE_CR4, "write_cr4" },
+ { SVM_EXIT_WRITE_CR8, "write_cr8" },
+ { SVM_EXIT_READ_DR0, "read_dr0" },
+ { SVM_EXIT_READ_DR1, "read_dr1" },
+ { SVM_EXIT_READ_DR2, "read_dr2" },
+ { SVM_EXIT_READ_DR3, "read_dr3" },
+ { SVM_EXIT_WRITE_DR0, "write_dr0" },
+ { SVM_EXIT_WRITE_DR1, "write_dr1" },
+ { SVM_EXIT_WRITE_DR2, "write_dr2" },
+ { SVM_EXIT_WRITE_DR3, "write_dr3" },
+ { SVM_EXIT_WRITE_DR5, "write_dr5" },
+ { SVM_EXIT_WRITE_DR7, "write_dr7" },
{ SVM_EXIT_EXCP_BASE + DB_VECTOR, "DB excp" },
{ SVM_EXIT_EXCP_BASE + BP_VECTOR, "BP excp" },
{ SVM_EXIT_EXCP_BASE + UD_VECTOR, "UD excp" },
.set_idt = svm_set_idt,
.get_gdt = svm_get_gdt,
.set_gdt = svm_set_gdt,
- .get_dr = svm_get_dr,
- .set_dr = svm_set_dr,
+ .set_dr7 = svm_set_dr7,
.cache_reg = svm_cache_reg,
.get_rflags = svm_get_rflags,
.set_rflags = svm_set_rflags,
.cpuid_update = svm_cpuid_update,
.rdtscp_supported = svm_rdtscp_supported,
+
+ .set_supported_cpuid = svm_set_supported_cpuid,
};
static int __init svm_init(void)
{
return kvm_init(&svm_x86_ops, sizeof(struct vcpu_svm),
- THIS_MODULE);
+ __alignof__(struct vcpu_svm), THIS_MODULE);
}
static void __exit svm_exit(void)
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff