#include <linux/highmem.h>
#include <linux/sched.h>
#include <linux/ftrace_event.h>
+#include <linux/slab.h>
#include <asm/desc.h>
#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 */
struct nested_state nested;
bool nmi_singlestep;
+
+ unsigned int3_injected;
+ unsigned long int3_rip;
};
/* enable NPT for AMD64 and X86 with PAE */
static void svm_complete_interrupts(struct vcpu_svm *svm);
static int nested_svm_exit_handled(struct vcpu_svm *svm);
+static int nested_svm_intercept(struct vcpu_svm *svm);
static int nested_svm_vmexit(struct vcpu_svm *svm);
static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
bool has_error_code, u32 error_code);
efer &= ~EFER_LME;
to_svm(vcpu)->vmcb->save.efer = efer | EFER_SVME;
- vcpu->arch.shadow_efer = efer;
-}
-
-static void svm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
- bool has_error_code, u32 error_code)
-{
- 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))
- return;
-
- svm->vmcb->control.event_inj = nr
- | SVM_EVTINJ_VALID
- | (has_error_code ? SVM_EVTINJ_VALID_ERR : 0)
- | SVM_EVTINJ_TYPE_EXEPT;
- svm->vmcb->control.event_inj_err = error_code;
+ vcpu->arch.efer = efer;
}
static int is_external_interrupt(u32 info)
u32 ret = 0;
if (svm->vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK)
- ret |= X86_SHADOW_INT_STI | X86_SHADOW_INT_MOV_SS;
+ ret |= KVM_X86_SHADOW_INT_STI | KVM_X86_SHADOW_INT_MOV_SS;
return ret & mask;
}
svm_set_interrupt_shadow(vcpu, 0);
}
+static void svm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
+ bool has_error_code, u32 error_code)
+{
+ 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))
+ return;
+
+ if (nr == BP_VECTOR && !svm_has(SVM_FEATURE_NRIP)) {
+ unsigned long rip, old_rip = kvm_rip_read(&svm->vcpu);
+
+ /*
+ * For guest debugging where we have to reinject #BP if some
+ * INT3 is guest-owned:
+ * Emulate nRIP by moving RIP forward. Will fail if injection
+ * raises a fault that is not intercepted. Still better than
+ * failing in all cases.
+ */
+ skip_emulated_instruction(&svm->vcpu);
+ rip = kvm_rip_read(&svm->vcpu);
+ svm->int3_rip = rip + svm->vmcb->save.cs.base;
+ svm->int3_injected = rip - old_rip;
+ }
+
+ svm->vmcb->control.event_inj = nr
+ | SVM_EVTINJ_VALID
+ | (has_error_code ? SVM_EVTINJ_VALID_ERR : 0)
+ | SVM_EVTINJ_TYPE_EXEPT;
+ svm->vmcb->control.event_inj_err = error_code;
+}
+
static int has_svm(void)
{
const char *msg;
struct svm_cpu_data *sd;
uint64_t efer;
- struct descriptor_table gdt_descr;
+ struct desc_ptr gdt_descr;
struct desc_struct *gdt;
int me = raw_smp_processor_id();
sd->next_asid = sd->max_asid + 1;
kvm_get_gdt(&gdt_descr);
- gdt = (struct desc_struct *)gdt_descr.base;
+ gdt = (struct desc_struct *)gdt_descr.address;
sd->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS);
wrmsrl(MSR_EFER, efer | EFER_SVME);
control->intercept_dr_read = INTERCEPT_DR0_MASK |
INTERCEPT_DR1_MASK |
INTERCEPT_DR2_MASK |
- INTERCEPT_DR3_MASK;
+ INTERCEPT_DR3_MASK |
+ INTERCEPT_DR4_MASK |
+ INTERCEPT_DR5_MASK |
+ INTERCEPT_DR6_MASK |
+ INTERCEPT_DR7_MASK;
control->intercept_dr_write = INTERCEPT_DR0_MASK |
INTERCEPT_DR1_MASK |
INTERCEPT_DR2_MASK |
INTERCEPT_DR3_MASK |
+ INTERCEPT_DR4_MASK |
INTERCEPT_DR5_MASK |
+ INTERCEPT_DR6_MASK |
INTERCEPT_DR7_MASK;
control->intercept_exceptions = (1 << PF_VECTOR) |
if (err)
goto free_svm;
+ err = -ENOMEM;
page = alloc_page(GFP_KERNEL);
- if (!page) {
- err = -ENOMEM;
+ if (!page)
goto uninit;
- }
- err = -ENOMEM;
msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER);
if (!msrpm_pages)
- goto uninit;
+ goto free_page1;
nested_msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER);
if (!nested_msrpm_pages)
- goto uninit;
-
- svm->msrpm = page_address(msrpm_pages);
- svm_vcpu_init_msrpm(svm->msrpm);
+ goto free_page2;
hsave_page = alloc_page(GFP_KERNEL);
if (!hsave_page)
- goto uninit;
+ goto free_page3;
+
svm->nested.hsave = page_address(hsave_page);
+ svm->msrpm = page_address(msrpm_pages);
+ svm_vcpu_init_msrpm(svm->msrpm);
+
svm->nested.msrpm = page_address(nested_msrpm_pages);
svm->vmcb = page_address(page);
return &svm->vcpu;
+free_page3:
+ __free_pages(nested_msrpm_pages, MSRPM_ALLOC_ORDER);
+free_page2:
+ __free_pages(msrpm_pages, MSRPM_ALLOC_ORDER);
+free_page1:
+ __free_page(page);
uninit:
kvm_vcpu_uninit(&svm->vcpu);
free_svm:
return save->cpl;
}
-static void svm_get_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+static void svm_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
struct vcpu_svm *svm = to_svm(vcpu);
- dt->limit = svm->vmcb->save.idtr.limit;
- dt->base = svm->vmcb->save.idtr.base;
+ dt->size = svm->vmcb->save.idtr.limit;
+ dt->address = svm->vmcb->save.idtr.base;
}
-static void svm_set_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+static void svm_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
struct vcpu_svm *svm = to_svm(vcpu);
- svm->vmcb->save.idtr.limit = dt->limit;
- svm->vmcb->save.idtr.base = dt->base ;
+ svm->vmcb->save.idtr.limit = dt->size;
+ svm->vmcb->save.idtr.base = dt->address ;
}
-static void svm_get_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+static void svm_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
struct vcpu_svm *svm = to_svm(vcpu);
- dt->limit = svm->vmcb->save.gdtr.limit;
- dt->base = svm->vmcb->save.gdtr.base;
+ dt->size = svm->vmcb->save.gdtr.limit;
+ dt->address = svm->vmcb->save.gdtr.base;
}
-static void svm_set_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+static void svm_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
struct vcpu_svm *svm = to_svm(vcpu);
- svm->vmcb->save.gdtr.limit = dt->limit;
- svm->vmcb->save.gdtr.base = dt->base ;
+ svm->vmcb->save.gdtr.limit = dt->size;
+ svm->vmcb->save.gdtr.base = dt->address ;
}
static void svm_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
static void update_cr0_intercept(struct vcpu_svm *svm)
{
+ struct vmcb *vmcb = svm->vmcb;
ulong gcr0 = svm->vcpu.arch.cr0;
u64 *hcr0 = &svm->vmcb->save.cr0;
if (gcr0 == *hcr0 && svm->vcpu.fpu_active) {
- svm->vmcb->control.intercept_cr_read &= ~INTERCEPT_CR0_MASK;
- svm->vmcb->control.intercept_cr_write &= ~INTERCEPT_CR0_MASK;
+ vmcb->control.intercept_cr_read &= ~INTERCEPT_CR0_MASK;
+ vmcb->control.intercept_cr_write &= ~INTERCEPT_CR0_MASK;
+ if (is_nested(svm)) {
+ struct vmcb *hsave = svm->nested.hsave;
+
+ hsave->control.intercept_cr_read &= ~INTERCEPT_CR0_MASK;
+ hsave->control.intercept_cr_write &= ~INTERCEPT_CR0_MASK;
+ vmcb->control.intercept_cr_read |= svm->nested.intercept_cr_read;
+ vmcb->control.intercept_cr_write |= svm->nested.intercept_cr_write;
+ }
} else {
svm->vmcb->control.intercept_cr_read |= INTERCEPT_CR0_MASK;
svm->vmcb->control.intercept_cr_write |= INTERCEPT_CR0_MASK;
+ if (is_nested(svm)) {
+ struct vmcb *hsave = svm->nested.hsave;
+
+ hsave->control.intercept_cr_read |= INTERCEPT_CR0_MASK;
+ hsave->control.intercept_cr_write |= INTERCEPT_CR0_MASK;
+ }
}
}
struct vcpu_svm *svm = to_svm(vcpu);
#ifdef CONFIG_X86_64
- if (vcpu->arch.shadow_efer & EFER_LME) {
+ if (vcpu->arch.efer & EFER_LME) {
if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) {
- vcpu->arch.shadow_efer |= EFER_LMA;
+ vcpu->arch.efer |= EFER_LMA;
svm->vmcb->save.efer |= EFER_LMA | EFER_LME;
}
if (is_paging(vcpu) && !(cr0 & X86_CR0_PG)) {
- vcpu->arch.shadow_efer &= ~EFER_LMA;
+ vcpu->arch.efer &= ~EFER_LMA;
svm->vmcb->save.efer &= ~(EFER_LMA | EFER_LME);
}
}
svm->vmcb->control.asid = sd->next_asid++;
}
-static unsigned long svm_get_dr(struct kvm_vcpu *vcpu, int dr)
+static int svm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *dest)
{
struct vcpu_svm *svm = to_svm(vcpu);
- unsigned long val;
switch (dr) {
case 0 ... 3:
- val = vcpu->arch.db[dr];
+ *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)
- val = vcpu->arch.dr6;
+ *dest = vcpu->arch.dr6;
else
- val = svm->vmcb->save.dr6;
+ *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)
- val = vcpu->arch.dr7;
+ *dest = vcpu->arch.dr7;
else
- val = svm->vmcb->save.dr7;
+ *dest = svm->vmcb->save.dr7;
break;
- default:
- val = 0;
}
- return val;
+ return EMULATE_DONE;
}
-static void svm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long value,
- int *exception)
+static int svm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long value)
{
struct vcpu_svm *svm = to_svm(vcpu);
- *exception = 0;
-
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;
- return;
- case 4 ... 5:
- if (vcpu->arch.cr4 & X86_CR4_DE)
- *exception = UD_VECTOR;
- return;
+ break;
+ case 4:
+ if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
+ return EMULATE_FAIL; /* will re-inject UD */
+ /* fall through */
case 6:
- if (value & 0xffffffff00000000ULL) {
- *exception = GP_VECTOR;
- return;
- }
vcpu->arch.dr6 = (value & DR6_VOLATILE) | DR6_FIXED_1;
- return;
+ break;
+ case 5:
+ if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
+ return EMULATE_FAIL; /* will re-inject UD */
+ /* fall through */
case 7:
- if (value & 0xffffffff00000000ULL) {
- *exception = GP_VECTOR;
- return;
- }
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);
}
- return;
- default:
- /* FIXME: Possible case? */
- printk(KERN_DEBUG "%s: unexpected dr %u\n",
- __func__, dr);
- *exception = UD_VECTOR;
- return;
+ break;
}
+
+ return EMULATE_DONE;
}
static int pf_interception(struct vcpu_svm *svm)
return 1;
}
-static int nm_interception(struct vcpu_svm *svm)
+static void svm_fpu_activate(struct kvm_vcpu *vcpu)
{
- svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR);
+ struct vcpu_svm *svm = to_svm(vcpu);
+ u32 excp;
+
+ if (is_nested(svm)) {
+ u32 h_excp, n_excp;
+
+ h_excp = svm->nested.hsave->control.intercept_exceptions;
+ n_excp = svm->nested.intercept_exceptions;
+ h_excp &= ~(1 << NM_VECTOR);
+ excp = h_excp | n_excp;
+ } else {
+ excp = svm->vmcb->control.intercept_exceptions;
+ excp &= ~(1 << NM_VECTOR);
+ }
+
+ svm->vmcb->control.intercept_exceptions = excp;
+
svm->vcpu.fpu_active = 1;
update_cr0_intercept(svm);
+}
+static int nm_interception(struct vcpu_svm *svm)
+{
+ svm_fpu_activate(&svm->vcpu);
return 1;
}
static int nested_svm_check_permissions(struct vcpu_svm *svm)
{
- if (!(svm->vcpu.arch.shadow_efer & EFER_SVME)
+ if (!(svm->vcpu.arch.efer & EFER_SVME)
|| !is_paging(&svm->vcpu)) {
kvm_queue_exception(&svm->vcpu, UD_VECTOR);
return 1;
static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
bool has_error_code, u32 error_code)
{
+ int vmexit;
+
if (!is_nested(svm))
return 0;
svm->vmcb->control.exit_info_1 = error_code;
svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2;
- return nested_svm_exit_handled(svm);
+ vmexit = nested_svm_intercept(svm);
+ if (vmexit == NESTED_EXIT_DONE)
+ svm->nested.exit_required = true;
+
+ return vmexit;
}
-static inline int nested_svm_intr(struct vcpu_svm *svm)
+/* This function returns true if it is save to enable the irq window */
+static inline bool nested_svm_intr(struct vcpu_svm *svm)
{
if (!is_nested(svm))
- return 0;
+ return true;
if (!(svm->vcpu.arch.hflags & HF_VINTR_MASK))
- return 0;
+ return true;
if (!(svm->vcpu.arch.hflags & HF_HIF_MASK))
- return 0;
+ return false;
svm->vmcb->control.exit_code = SVM_EXIT_INTR;
*/
svm->nested.exit_required = true;
trace_kvm_nested_intr_vmexit(svm->vmcb->save.rip);
- return 1;
+ return false;
}
- return 0;
+ return true;
}
-static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, enum km_type idx)
+static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, struct page **_page)
{
struct page *page;
+ might_sleep();
+
page = gfn_to_page(svm->vcpu.kvm, gpa >> PAGE_SHIFT);
if (is_error_page(page))
goto error;
- return kmap_atomic(page, idx);
+ *_page = page;
+
+ return kmap(page);
error:
kvm_release_page_clean(page);
return NULL;
}
-static void nested_svm_unmap(void *addr, enum km_type idx)
+static void nested_svm_unmap(struct page *page)
{
- struct page *page;
-
- if (!addr)
- return;
-
- page = kmap_atomic_to_page(addr);
-
- kunmap_atomic(addr, idx);
+ kunmap(page);
kvm_release_page_dirty(page);
}
u32 msr = svm->vcpu.arch.regs[VCPU_REGS_RCX];
bool ret = false;
u32 t0, t1;
- u8 *msrpm;
+ u8 val;
if (!(svm->nested.intercept & (1ULL << INTERCEPT_MSR_PROT)))
return false;
- msrpm = nested_svm_map(svm, svm->nested.vmcb_msrpm, KM_USER0);
-
- if (!msrpm)
- goto out;
-
switch (msr) {
case 0 ... 0x1fff:
t0 = (msr * 2) % 8;
goto out;
}
- ret = msrpm[t1] & ((1 << param) << t0);
+ if (!kvm_read_guest(svm->vcpu.kvm, svm->nested.vmcb_msrpm + t1, &val, 1))
+ ret = val & ((1 << param) << t0);
out:
- nested_svm_unmap(msrpm, KM_USER0);
-
return ret;
}
if (!npt_enabled)
return NESTED_EXIT_HOST;
break;
+ case SVM_EXIT_EXCP_BASE + NM_VECTOR:
+ nm_interception(svm);
+ break;
default:
break;
}
/*
* If this function returns true, this #vmexit was already handled
*/
-static int nested_svm_exit_handled(struct vcpu_svm *svm)
+static int nested_svm_intercept(struct vcpu_svm *svm)
{
u32 exit_code = svm->vmcb->control.exit_code;
int vmexit = NESTED_EXIT_HOST;
}
}
- if (vmexit == NESTED_EXIT_DONE) {
+ return vmexit;
+}
+
+static int nested_svm_exit_handled(struct vcpu_svm *svm)
+{
+ int vmexit;
+
+ vmexit = nested_svm_intercept(svm);
+
+ if (vmexit == NESTED_EXIT_DONE)
nested_svm_vmexit(svm);
- }
return vmexit;
}
struct vmcb *nested_vmcb;
struct vmcb *hsave = svm->nested.hsave;
struct vmcb *vmcb = svm->vmcb;
+ struct page *page;
trace_kvm_nested_vmexit_inject(vmcb->control.exit_code,
vmcb->control.exit_info_1,
vmcb->control.exit_int_info,
vmcb->control.exit_int_info_err);
- nested_vmcb = nested_svm_map(svm, svm->nested.vmcb, KM_USER0);
+ nested_vmcb = nested_svm_map(svm, svm->nested.vmcb, &page);
if (!nested_vmcb)
return 1;
+ /* Exit nested SVM mode */
+ svm->nested.vmcb = 0;
+
/* Give the current vmcb to the guest */
disable_gif(svm);
nested_vmcb->save.ds = vmcb->save.ds;
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.cr2 = vmcb->save.cr2;
+ nested_vmcb->save.cr4 = svm->vcpu.arch.cr4;
nested_vmcb->save.rflags = vmcb->save.rflags;
nested_vmcb->save.rip = vmcb->save.rip;
nested_vmcb->save.rsp = vmcb->save.rsp;
svm->vmcb->save.cpl = 0;
svm->vmcb->control.exit_int_info = 0;
- /* Exit nested SVM mode */
- svm->nested.vmcb = 0;
-
- nested_svm_unmap(nested_vmcb, KM_USER0);
+ nested_svm_unmap(page);
kvm_mmu_reset_context(&svm->vcpu);
kvm_mmu_load(&svm->vcpu);
static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
{
u32 *nested_msrpm;
+ struct page *page;
int i;
- nested_msrpm = nested_svm_map(svm, svm->nested.vmcb_msrpm, KM_USER0);
+ nested_msrpm = nested_svm_map(svm, svm->nested.vmcb_msrpm, &page);
if (!nested_msrpm)
return false;
svm->vmcb->control.msrpm_base_pa = __pa(svm->nested.msrpm);
- nested_svm_unmap(nested_msrpm, KM_USER0);
+ nested_svm_unmap(page);
return true;
}
struct vmcb *nested_vmcb;
struct vmcb *hsave = svm->nested.hsave;
struct vmcb *vmcb = svm->vmcb;
+ struct page *page;
+ u64 vmcb_gpa;
+
+ vmcb_gpa = svm->vmcb->save.rax;
- nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, KM_USER0);
+ nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page);
if (!nested_vmcb)
return false;
- /* nested_vmcb is our indicator if nested SVM is activated */
- svm->nested.vmcb = svm->vmcb->save.rax;
-
trace_kvm_nested_vmrun(svm->vmcb->save.rip - 3, svm->nested.vmcb,
nested_vmcb->save.rip,
nested_vmcb->control.int_ctl,
hsave->save.ds = vmcb->save.ds;
hsave->save.gdtr = vmcb->save.gdtr;
hsave->save.idtr = vmcb->save.idtr;
- hsave->save.efer = svm->vcpu.arch.shadow_efer;
+ hsave->save.efer = svm->vcpu.arch.efer;
hsave->save.cr0 = kvm_read_cr0(&svm->vcpu);
hsave->save.cr4 = svm->vcpu.arch.cr4;
hsave->save.rflags = vmcb->save.rflags;
svm->vmcb->save.dr6 = nested_vmcb->save.dr6;
svm->vmcb->save.cpl = nested_vmcb->save.cpl;
- /* 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 |=
- nested_vmcb->control.intercept_cr_write;
- svm->vmcb->control.intercept_dr_read |=
- nested_vmcb->control.intercept_dr_read;
- svm->vmcb->control.intercept_dr_write |=
- nested_vmcb->control.intercept_dr_write;
- svm->vmcb->control.intercept_exceptions |=
- nested_vmcb->control.intercept_exceptions;
-
- svm->vmcb->control.intercept |= nested_vmcb->control.intercept;
-
svm->nested.vmcb_msrpm = nested_vmcb->control.msrpm_base_pa;
/* cache intercepts */
else
svm->vcpu.arch.hflags &= ~HF_VINTR_MASK;
+ if (svm->vcpu.arch.hflags & HF_VINTR_MASK) {
+ /* We only want the cr8 intercept bits of the guest */
+ svm->vmcb->control.intercept_cr_read &= ~INTERCEPT_CR8_MASK;
+ 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 */
+ svm->vmcb->control.intercept_cr_read |=
+ nested_vmcb->control.intercept_cr_read;
+ svm->vmcb->control.intercept_cr_write |=
+ nested_vmcb->control.intercept_cr_write;
+ svm->vmcb->control.intercept_dr_read |=
+ nested_vmcb->control.intercept_dr_read;
+ svm->vmcb->control.intercept_dr_write |=
+ nested_vmcb->control.intercept_dr_write;
+ svm->vmcb->control.intercept_exceptions |=
+ nested_vmcb->control.intercept_exceptions;
+
+ svm->vmcb->control.intercept |= nested_vmcb->control.intercept;
+
+ svm->vmcb->control.lbr_ctl = nested_vmcb->control.lbr_ctl;
svm->vmcb->control.int_vector = nested_vmcb->control.int_vector;
svm->vmcb->control.int_state = nested_vmcb->control.int_state;
svm->vmcb->control.tsc_offset += nested_vmcb->control.tsc_offset;
svm->vmcb->control.event_inj = nested_vmcb->control.event_inj;
svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err;
- nested_svm_unmap(nested_vmcb, KM_USER0);
+ nested_svm_unmap(page);
+
+ /* nested_vmcb is our indicator if nested SVM is activated */
+ svm->nested.vmcb = vmcb_gpa;
enable_gif(svm);
static int vmload_interception(struct vcpu_svm *svm)
{
struct vmcb *nested_vmcb;
+ struct page *page;
if (nested_svm_check_permissions(svm))
return 1;
svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
skip_emulated_instruction(&svm->vcpu);
- nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, KM_USER0);
+ nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page);
if (!nested_vmcb)
return 1;
nested_svm_vmloadsave(nested_vmcb, svm->vmcb);
- nested_svm_unmap(nested_vmcb, KM_USER0);
+ nested_svm_unmap(page);
return 1;
}
static int vmsave_interception(struct vcpu_svm *svm)
{
struct vmcb *nested_vmcb;
+ struct page *page;
if (nested_svm_check_permissions(svm))
return 1;
svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
skip_emulated_instruction(&svm->vcpu);
- nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, KM_USER0);
+ nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page);
if (!nested_vmcb)
return 1;
nested_svm_vmloadsave(svm->vmcb, nested_vmcb);
- nested_svm_unmap(nested_vmcb, KM_USER0);
+ nested_svm_unmap(page);
return 1;
}
u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX];
u64 data;
- if (svm_get_msr(&svm->vcpu, ecx, &data))
+ if (svm_get_msr(&svm->vcpu, ecx, &data)) {
+ trace_kvm_msr_read_ex(ecx);
kvm_inject_gp(&svm->vcpu, 0);
- else {
+ } else {
trace_kvm_msr_read(ecx, data);
svm->vcpu.arch.regs[VCPU_REGS_RAX] = data & 0xffffffff;
u64 data = (svm->vcpu.arch.regs[VCPU_REGS_RAX] & -1u)
| ((u64)(svm->vcpu.arch.regs[VCPU_REGS_RDX] & -1u) << 32);
- trace_kvm_msr_write(ecx, data);
svm->next_rip = kvm_rip_read(&svm->vcpu) + 2;
- if (svm_set_msr(&svm->vcpu, ecx, data))
+ if (svm_set_msr(&svm->vcpu, ecx, data)) {
+ trace_kvm_msr_write_ex(ecx, data);
kvm_inject_gp(&svm->vcpu, 0);
- else
+ } else {
+ trace_kvm_msr_write(ecx, data);
skip_emulated_instruction(&svm->vcpu);
+ }
return 1;
}
[SVM_EXIT_READ_DR1] = emulate_on_interception,
[SVM_EXIT_READ_DR2] = emulate_on_interception,
[SVM_EXIT_READ_DR3] = emulate_on_interception,
+ [SVM_EXIT_READ_DR4] = emulate_on_interception,
+ [SVM_EXIT_READ_DR5] = emulate_on_interception,
+ [SVM_EXIT_READ_DR6] = emulate_on_interception,
+ [SVM_EXIT_READ_DR7] = emulate_on_interception,
[SVM_EXIT_WRITE_DR0] = emulate_on_interception,
[SVM_EXIT_WRITE_DR1] = emulate_on_interception,
[SVM_EXIT_WRITE_DR2] = emulate_on_interception,
[SVM_EXIT_WRITE_DR3] = emulate_on_interception,
+ [SVM_EXIT_WRITE_DR4] = emulate_on_interception,
[SVM_EXIT_WRITE_DR5] = emulate_on_interception,
+ [SVM_EXIT_WRITE_DR6] = emulate_on_interception,
[SVM_EXIT_WRITE_DR7] = emulate_on_interception,
[SVM_EXIT_EXCP_BASE + DB_VECTOR] = db_interception,
[SVM_EXIT_EXCP_BASE + BP_VECTOR] = bp_interception,
{
struct vcpu_svm *svm = to_svm(vcpu);
+ if (is_nested(svm) && (vcpu->arch.hflags & HF_VINTR_MASK))
+ return;
+
if (irr == -1)
return;
{
struct vcpu_svm *svm = to_svm(vcpu);
- nested_svm_intr(svm);
-
/* 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)) {
+ if (gif_set(svm) && nested_svm_intr(svm)) {
svm_set_vintr(svm);
svm_inject_irq(svm, 0x0);
}
static void svm_prepare_guest_switch(struct kvm_vcpu *vcpu)
{
- if (npt_enabled)
- vcpu->fpu_active = 1;
}
static inline void sync_cr8_to_lapic(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
+ if (is_nested(svm) && (vcpu->arch.hflags & HF_VINTR_MASK))
+ return;
+
if (!(svm->vmcb->control.intercept_cr_write & INTERCEPT_CR8_MASK)) {
int cr8 = svm->vmcb->control.int_ctl & V_TPR_MASK;
kvm_set_cr8(vcpu, cr8);
struct vcpu_svm *svm = to_svm(vcpu);
u64 cr8;
+ if (is_nested(svm) && (vcpu->arch.hflags & HF_VINTR_MASK))
+ return;
+
cr8 = kvm_get_cr8(vcpu);
svm->vmcb->control.int_ctl &= ~V_TPR_MASK;
svm->vmcb->control.int_ctl |= cr8 & V_TPR_MASK;
u8 vector;
int type;
u32 exitintinfo = svm->vmcb->control.exit_int_info;
+ unsigned int3_injected = svm->int3_injected;
+
+ svm->int3_injected = 0;
if (svm->vcpu.arch.hflags & HF_IRET_MASK)
svm->vcpu.arch.hflags &= ~(HF_NMI_MASK | HF_IRET_MASK);
svm->vcpu.arch.nmi_injected = true;
break;
case SVM_EXITINTINFO_TYPE_EXEPT:
- /* In case of software exception do not reinject an exception
- vector, but re-execute and instruction instead */
if (is_nested(svm))
break;
- if (kvm_exception_is_soft(vector))
+ /*
+ * In case of software exceptions, do not reinject the vector,
+ * but re-execute the instruction instead. Rewind RIP first
+ * if we emulated INT3 before.
+ */
+ if (kvm_exception_is_soft(vector)) {
+ if (vector == BP_VECTOR && int3_injected &&
+ kvm_is_linear_rip(&svm->vcpu, svm->int3_rip))
+ kvm_rip_write(&svm->vcpu,
+ kvm_rip_read(&svm->vcpu) -
+ int3_injected);
break;
+ }
if (exitintinfo & SVM_EXITINTINFO_VALID_ERR) {
u32 err = svm->vmcb->control.exit_int_info_err;
kvm_queue_exception_e(&svm->vcpu, vector, err);
{
struct vcpu_svm *svm = to_svm(vcpu);
- if (npt_enabled) {
- /* hack: npt requires active fpu at this time */
- vcpu->fpu_active = 1;
- return;
- }
-
- update_cr0_intercept(svm);
svm->vmcb->control.intercept_exceptions |= 1 << NM_VECTOR;
+ if (is_nested(svm))
+ svm->nested.hsave->control.intercept_exceptions |= 1 << NM_VECTOR;
+ update_cr0_intercept(svm);
}
static struct kvm_x86_ops svm_x86_ops = {
.cache_reg = svm_cache_reg,
.get_rflags = svm_get_rflags,
.set_rflags = svm_set_rflags,
+ .fpu_activate = svm_fpu_activate,
.fpu_deactivate = svm_fpu_deactivate,
.tlb_flush = svm_flush_tlb,