#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 DEBUGCTL_RESERVED_BITS (~(0x3fULL))
-
-/* Turn on to get debugging output*/
-/* #define NESTED_DEBUG */
+#define NESTED_EXIT_HOST 0 /* Exit handled on host level */
+#define NESTED_EXIT_DONE 1 /* Exit caused nested vmexit */
+#define NESTED_EXIT_CONTINUE 2 /* Further checks needed */
-#ifdef NESTED_DEBUG
-#define nsvm_printk(fmt, args...) printk(KERN_INFO fmt, ## args)
-#else
-#define nsvm_printk(fmt, args...) do {} while(0)
-#endif
+#define DEBUGCTL_RESERVED_BITS (~(0x3fULL))
static const u32 host_save_user_msrs[] = {
#ifdef CONFIG_X86_64
struct kvm_vcpu;
+struct nested_state {
+ struct vmcb *hsave;
+ u64 hsave_msr;
+ u64 vmcb;
+
+ /* These are the merged vectors */
+ u32 *msrpm;
+
+ /* gpa pointers to the real vectors */
+ u64 vmcb_msrpm;
+
+ /* A VMEXIT is required but not yet emulated */
+ bool exit_required;
+
+ /* cache for intercepts of the guest */
+ u16 intercept_cr_read;
+ u16 intercept_cr_write;
+ u16 intercept_dr_read;
+ u16 intercept_dr_write;
+ u32 intercept_exceptions;
+ u64 intercept;
+
+};
+
struct vcpu_svm {
struct kvm_vcpu vcpu;
struct vmcb *vmcb;
u64 host_gs_base;
u32 *msrpm;
- struct vmcb *hsave;
- u64 hsave_msr;
- u64 nested_vmcb;
+ struct nested_state nested;
- /* These are the merged vectors */
- u32 *nested_msrpm;
+ bool nmi_singlestep;
- /* gpa pointers to the real vectors */
- u64 nested_vmcb_msrpm;
+ unsigned int3_injected;
+ unsigned long int3_rip;
};
/* enable NPT for AMD64 and X86 with PAE */
module_param(npt, int, S_IRUGO);
-static int nested = 0;
+static int nested = 1;
module_param(nested, int, S_IRUGO);
static void svm_flush_tlb(struct kvm_vcpu *vcpu);
+static void svm_complete_interrupts(struct vcpu_svm *svm);
-static int nested_svm_exit_handled(struct vcpu_svm *svm, bool kvm_override);
+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_vmsave(struct vcpu_svm *svm, void *nested_vmcb,
- void *arg2, void *opaque);
static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
bool has_error_code, u32 error_code);
static inline bool is_nested(struct vcpu_svm *svm)
{
- return svm->nested_vmcb;
+ return svm->nested.vmcb;
+}
+
+static inline void enable_gif(struct vcpu_svm *svm)
+{
+ svm->vcpu.arch.hflags |= HF_GIF_MASK;
+}
+
+static inline void disable_gif(struct vcpu_svm *svm)
+{
+ svm->vcpu.arch.hflags &= ~HF_GIF_MASK;
+}
+
+static inline bool gif_set(struct vcpu_svm *svm)
+{
+ return !!(svm->vcpu.arch.hflags & HF_GIF_MASK);
}
static unsigned long iopm_base;
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;
}
struct vcpu_svm *svm = to_svm(vcpu);
if (!svm->next_rip) {
- if (emulate_instruction(vcpu, vcpu->run, 0, 0, EMULTYPE_SKIP) !=
+ if (emulate_instruction(vcpu, 0, 0, EMULTYPE_SKIP) !=
EMULATE_DONE)
printk(KERN_DEBUG "%s: NOP\n", __func__);
return;
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;
cpu_svm_disable();
}
-static void svm_hardware_enable(void *garbage)
+static int svm_hardware_enable(void *garbage)
{
- struct svm_cpu_data *svm_data;
+ struct svm_cpu_data *sd;
uint64_t efer;
struct desc_ptr gdt_descr;
struct desc_struct *gdt;
int me = raw_smp_processor_id();
+ rdmsrl(MSR_EFER, efer);
+ if (efer & EFER_SVME)
+ return -EBUSY;
+
if (!has_svm()) {
- printk(KERN_ERR "svm_cpu_init: err EOPNOTSUPP on %d\n", me);
- return;
+ printk(KERN_ERR "svm_hardware_enable: err EOPNOTSUPP on %d\n",
+ me);
+ return -EINVAL;
}
- svm_data = per_cpu(svm_data, me);
+ sd = per_cpu(svm_data, me);
- if (!svm_data) {
- printk(KERN_ERR "svm_cpu_init: svm_data is NULL on %d\n",
+ if (!sd) {
+ printk(KERN_ERR "svm_hardware_enable: svm_data is NULL on %d\n",
me);
- return;
+ return -EINVAL;
}
- svm_data->asid_generation = 1;
- svm_data->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1;
- svm_data->next_asid = svm_data->max_asid + 1;
+ sd->asid_generation = 1;
+ sd->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1;
+ sd->next_asid = sd->max_asid + 1;
- asm volatile ("sgdt %0" : "=m"(gdt_descr));
+ kvm_get_gdt(&gdt_descr);
gdt = (struct desc_struct *)gdt_descr.address;
- svm_data->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS);
+ sd->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS);
- rdmsrl(MSR_EFER, efer);
wrmsrl(MSR_EFER, efer | EFER_SVME);
- wrmsrl(MSR_VM_HSAVE_PA,
- page_to_pfn(svm_data->save_area) << PAGE_SHIFT);
+ wrmsrl(MSR_VM_HSAVE_PA, page_to_pfn(sd->save_area) << PAGE_SHIFT);
+
+ return 0;
}
static void svm_cpu_uninit(int cpu)
{
- struct svm_cpu_data *svm_data
- = per_cpu(svm_data, raw_smp_processor_id());
+ struct svm_cpu_data *sd = per_cpu(svm_data, raw_smp_processor_id());
- if (!svm_data)
+ if (!sd)
return;
per_cpu(svm_data, raw_smp_processor_id()) = NULL;
- __free_page(svm_data->save_area);
- kfree(svm_data);
+ __free_page(sd->save_area);
+ kfree(sd);
}
static int svm_cpu_init(int cpu)
{
- struct svm_cpu_data *svm_data;
+ struct svm_cpu_data *sd;
int r;
- svm_data = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL);
- if (!svm_data)
+ sd = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL);
+ if (!sd)
return -ENOMEM;
- svm_data->cpu = cpu;
- svm_data->save_area = alloc_page(GFP_KERNEL);
+ sd->cpu = cpu;
+ sd->save_area = alloc_page(GFP_KERNEL);
r = -ENOMEM;
- if (!svm_data->save_area)
+ if (!sd->save_area)
goto err_1;
- per_cpu(svm_data, cpu) = svm_data;
+ per_cpu(svm_data, cpu) = sd;
return 0;
err_1:
- kfree(svm_data);
+ kfree(sd);
return r;
}
kvm_enable_efer_bits(EFER_SVME);
}
- for_each_online_cpu(cpu) {
+ for_each_possible_cpu(cpu) {
r = svm_cpu_init(cpu);
if (r)
goto err;
{
int cpu;
- for_each_online_cpu(cpu)
+ for_each_possible_cpu(cpu)
svm_cpu_uninit(cpu);
__free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER);
struct vmcb_control_area *control = &svm->vmcb->control;
struct vmcb_save_area *save = &svm->vmcb->save;
+ svm->vcpu.fpu_active = 1;
+
control->intercept_cr_read = INTERCEPT_CR0_MASK |
INTERCEPT_CR3_MASK |
INTERCEPT_CR4_MASK;
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) |
control->intercept = (1ULL << INTERCEPT_INTR) |
(1ULL << INTERCEPT_NMI) |
(1ULL << INTERCEPT_SMI) |
+ (1ULL << INTERCEPT_SELECTIVE_CR0) |
(1ULL << INTERCEPT_CPUID) |
(1ULL << INTERCEPT_INVD) |
(1ULL << INTERCEPT_HLT) |
save->rip = 0x0000fff0;
svm->vcpu.arch.regs[VCPU_REGS_RIP] = save->rip;
- /*
- * cr0 val on cpu init should be 0x60000010, we enable cpu
- * cache by default. the orderly way is to enable cache in bios.
+ /* This is the guest-visible cr0 value.
+ * svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0.
*/
- save->cr0 = 0x00000010 | X86_CR0_PG | X86_CR0_WP;
+ svm->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
+ kvm_set_cr0(&svm->vcpu, svm->vcpu.arch.cr0);
+
save->cr4 = X86_CR4_PAE;
/* rdx = ?? */
control->intercept &= ~((1ULL << INTERCEPT_TASK_SWITCH) |
(1ULL << INTERCEPT_INVLPG));
control->intercept_exceptions &= ~(1 << PF_VECTOR);
- control->intercept_cr_read &= ~(INTERCEPT_CR0_MASK|
- INTERCEPT_CR3_MASK);
- control->intercept_cr_write &= ~(INTERCEPT_CR0_MASK|
- INTERCEPT_CR3_MASK);
+ control->intercept_cr_read &= ~INTERCEPT_CR3_MASK;
+ control->intercept_cr_write &= ~INTERCEPT_CR3_MASK;
save->g_pat = 0x0007040600070406ULL;
- /* enable caching because the QEMU Bios doesn't enable it */
- save->cr0 = X86_CR0_ET;
save->cr3 = 0;
save->cr4 = 0;
}
force_new_asid(&svm->vcpu);
- svm->nested_vmcb = 0;
- svm->vcpu.arch.hflags = HF_GIF_MASK;
+ svm->nested.vmcb = 0;
+ svm->vcpu.arch.hflags = 0;
+
+ if (svm_has(SVM_FEATURE_PAUSE_FILTER)) {
+ control->pause_filter_count = 3000;
+ control->intercept |= (1ULL << INTERCEPT_PAUSE);
+ }
+
+ enable_gif(svm);
}
static int svm_vcpu_reset(struct kvm_vcpu *vcpu)
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;
- svm->hsave = page_address(hsave_page);
+ goto free_page3;
- svm->nested_msrpm = page_address(nested_msrpm_pages);
+ 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);
clear_page(svm->vmcb);
init_vmcb(svm);
fx_init(&svm->vcpu);
- svm->vcpu.fpu_active = 1;
svm->vcpu.arch.apic_base = 0xfee00000 | MSR_IA32_APICBASE_ENABLE;
if (kvm_vcpu_is_bsp(&svm->vcpu))
svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP;
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:
__free_page(pfn_to_page(svm->vmcb_pa >> PAGE_SHIFT));
__free_pages(virt_to_page(svm->msrpm), MSRPM_ALLOC_ORDER);
- __free_page(virt_to_page(svm->hsave));
- __free_pages(virt_to_page(svm->nested_msrpm), MSRPM_ALLOC_ORDER);
+ __free_page(virt_to_page(svm->nested.hsave));
+ __free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER);
kvm_vcpu_uninit(vcpu);
kmem_cache_free(kvm_vcpu_cache, svm);
}
int i;
if (unlikely(cpu != vcpu->cpu)) {
- u64 tsc_this, delta;
-
- /*
- * Make sure that the guest sees a monotonically
- * increasing TSC.
- */
- rdtscll(tsc_this);
- delta = vcpu->arch.host_tsc - tsc_this;
- svm->vmcb->control.tsc_offset += delta;
+ u64 delta;
+
+ if (check_tsc_unstable()) {
+ /*
+ * Make sure that the guest sees a monotonically
+ * increasing TSC.
+ */
+ delta = vcpu->arch.host_tsc - native_read_tsc();
+ svm->vmcb->control.tsc_offset += delta;
+ if (is_nested(svm))
+ svm->nested.hsave->control.tsc_offset += delta;
+ }
vcpu->cpu = cpu;
kvm_migrate_timers(vcpu);
svm->asid_generation = 0;
for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++)
wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]);
- rdtscll(vcpu->arch.host_tsc);
+ vcpu->arch.host_tsc = native_read_tsc();
}
static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu)
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 svm_decache_cr4_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 (!svm->vcpu.fpu_active)
+ *hcr0 |= SVM_CR0_SELECTIVE_MASK;
+ else
+ *hcr0 = (*hcr0 & ~SVM_CR0_SELECTIVE_MASK)
+ | (gcr0 & SVM_CR0_SELECTIVE_MASK);
+
+
+ if (gcr0 == *hcr0 && svm->vcpu.fpu_active) {
+ 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;
+ }
+ }
+}
+
static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
{
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);
}
}
#endif
- if (npt_enabled)
- goto set;
+ vcpu->arch.cr0 = cr0;
- if ((vcpu->arch.cr0 & X86_CR0_TS) && !(cr0 & X86_CR0_TS)) {
- svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR);
- vcpu->fpu_active = 1;
- }
+ if (!npt_enabled)
+ cr0 |= X86_CR0_PG | X86_CR0_WP;
- vcpu->arch.cr0 = cr0;
- cr0 |= X86_CR0_PG | X86_CR0_WP;
- if (!vcpu->fpu_active) {
- svm->vmcb->control.intercept_exceptions |= (1 << NM_VECTOR);
+ if (!vcpu->fpu_active)
cr0 |= X86_CR0_TS;
- }
-set:
/*
* re-enable caching here because the QEMU bios
* does not do it - this results in some delay at
*/
cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
svm->vmcb->save.cr0 = cr0;
+ update_cr0_intercept(svm);
}
static void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
svm->vmcb->control.intercept_exceptions &=
~((1 << DB_VECTOR) | (1 << BP_VECTOR));
- if (vcpu->arch.singlestep)
+ if (svm->nmi_singlestep)
svm->vmcb->control.intercept_exceptions |= (1 << DB_VECTOR);
if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) {
vcpu->guest_debug = 0;
}
-static int svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg)
+static void svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg)
{
- int old_debug = vcpu->guest_debug;
struct vcpu_svm *svm = to_svm(vcpu);
- vcpu->guest_debug = dbg->control;
-
- update_db_intercept(vcpu);
-
if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
svm->vmcb->save.dr7 = dbg->arch.debugreg[7];
else
svm->vmcb->save.dr7 = vcpu->arch.dr7;
- if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
- svm->vmcb->save.rflags |= X86_EFLAGS_TF | X86_EFLAGS_RF;
- else if (old_debug & KVM_GUESTDBG_SINGLESTEP)
- svm->vmcb->save.rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF);
-
- return 0;
+ update_db_intercept(vcpu);
}
static void load_host_msrs(struct kvm_vcpu *vcpu)
#endif
}
-static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *svm_data)
+static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd)
{
- if (svm_data->next_asid > svm_data->max_asid) {
- ++svm_data->asid_generation;
- svm_data->next_asid = 1;
+ if (sd->next_asid > sd->max_asid) {
+ ++sd->asid_generation;
+ sd->next_asid = 1;
svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ALL_ASID;
}
- svm->asid_generation = svm_data->asid_generation;
- svm->vmcb->control.asid = svm_data->next_asid++;
+ svm->asid_generation = sd->asid_generation;
+ 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, struct kvm_run *kvm_run)
+static int pf_interception(struct vcpu_svm *svm)
{
u64 fault_address;
u32 error_code;
error_code = svm->vmcb->control.exit_info_1;
trace_kvm_page_fault(fault_address, error_code);
- /*
- * FIXME: Tis shouldn't be necessary here, but there is a flush
- * missing in the MMU code. Until we find this bug, flush the
- * complete TLB here on an NPF
- */
- if (npt_enabled)
- svm_flush_tlb(&svm->vcpu);
- else {
- if (kvm_event_needs_reinjection(&svm->vcpu))
- kvm_mmu_unprotect_page_virt(&svm->vcpu, fault_address);
- }
+ if (!npt_enabled && kvm_event_needs_reinjection(&svm->vcpu))
+ kvm_mmu_unprotect_page_virt(&svm->vcpu, fault_address);
return kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code);
}
-static int db_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int db_interception(struct vcpu_svm *svm)
{
+ struct kvm_run *kvm_run = svm->vcpu.run;
+
if (!(svm->vcpu.guest_debug &
(KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) &&
- !svm->vcpu.arch.singlestep) {
+ !svm->nmi_singlestep) {
kvm_queue_exception(&svm->vcpu, DB_VECTOR);
return 1;
}
- if (svm->vcpu.arch.singlestep) {
- svm->vcpu.arch.singlestep = false;
+ if (svm->nmi_singlestep) {
+ svm->nmi_singlestep = false;
if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP))
svm->vmcb->save.rflags &=
~(X86_EFLAGS_TF | X86_EFLAGS_RF);
return 1;
}
-static int bp_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int bp_interception(struct vcpu_svm *svm)
{
+ struct kvm_run *kvm_run = svm->vcpu.run;
+
kvm_run->exit_reason = KVM_EXIT_DEBUG;
kvm_run->debug.arch.pc = svm->vmcb->save.cs.base + svm->vmcb->save.rip;
kvm_run->debug.arch.exception = BP_VECTOR;
return 0;
}
-static int ud_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int ud_interception(struct vcpu_svm *svm)
{
int er;
- er = emulate_instruction(&svm->vcpu, kvm_run, 0, 0, EMULTYPE_TRAP_UD);
+ er = emulate_instruction(&svm->vcpu, 0, 0, EMULTYPE_TRAP_UD);
if (er != EMULATE_DONE)
kvm_queue_exception(&svm->vcpu, UD_VECTOR);
return 1;
}
-static int nm_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static void svm_fpu_activate(struct kvm_vcpu *vcpu)
{
- svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR);
- if (!(svm->vcpu.arch.cr0 & X86_CR0_TS))
- svm->vmcb->save.cr0 &= ~X86_CR0_TS;
+ 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 mc_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int mc_interception(struct vcpu_svm *svm)
{
/*
* On an #MC intercept the MCE handler is not called automatically in
return 1;
}
-static int shutdown_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int shutdown_interception(struct vcpu_svm *svm)
{
+ struct kvm_run *kvm_run = svm->vcpu.run;
+
/*
* VMCB is undefined after a SHUTDOWN intercept
* so reinitialize it.
return 0;
}
-static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int io_interception(struct vcpu_svm *svm)
{
u32 io_info = svm->vmcb->control.exit_info_1; /* address size bug? */
int size, in, string;
if (string) {
if (emulate_instruction(&svm->vcpu,
- kvm_run, 0, 0, 0) == EMULATE_DO_MMIO)
+ 0, 0, 0) == EMULATE_DO_MMIO)
return 0;
return 1;
}
size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT;
skip_emulated_instruction(&svm->vcpu);
- return kvm_emulate_pio(&svm->vcpu, kvm_run, in, size, port);
+ return kvm_emulate_pio(&svm->vcpu, in, size, port);
}
-static int nmi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int nmi_interception(struct vcpu_svm *svm)
{
return 1;
}
-static int intr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int intr_interception(struct vcpu_svm *svm)
{
++svm->vcpu.stat.irq_exits;
return 1;
}
-static int nop_on_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int nop_on_interception(struct vcpu_svm *svm)
{
return 1;
}
-static int halt_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int halt_interception(struct vcpu_svm *svm)
{
svm->next_rip = kvm_rip_read(&svm->vcpu) + 1;
skip_emulated_instruction(&svm->vcpu);
return kvm_emulate_halt(&svm->vcpu);
}
-static int vmmcall_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int vmmcall_interception(struct vcpu_svm *svm)
{
svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
skip_emulated_instruction(&svm->vcpu);
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)
{
- if (is_nested(svm)) {
- svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + nr;
- svm->vmcb->control.exit_code_hi = 0;
- svm->vmcb->control.exit_info_1 = error_code;
- svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2;
- if (nested_svm_exit_handled(svm, false)) {
- nsvm_printk("VMexit -> EXCP 0x%x\n", nr);
-
- nested_svm_vmexit(svm);
- return 1;
- }
- }
+ int vmexit;
- return 0;
+ if (!is_nested(svm))
+ return 0;
+
+ svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + nr;
+ svm->vmcb->control.exit_code_hi = 0;
+ svm->vmcb->control.exit_info_1 = error_code;
+ svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2;
+
+ 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)) {
- if (!(svm->vcpu.arch.hflags & HF_VINTR_MASK))
- return 0;
+ if (!is_nested(svm))
+ return true;
- if (!(svm->vcpu.arch.hflags & HF_HIF_MASK))
- return 0;
+ if (!(svm->vcpu.arch.hflags & HF_VINTR_MASK))
+ return true;
- svm->vmcb->control.exit_code = SVM_EXIT_INTR;
+ if (!(svm->vcpu.arch.hflags & HF_HIF_MASK))
+ return false;
- if (nested_svm_exit_handled(svm, false)) {
- nsvm_printk("VMexit -> INTR\n");
- nested_svm_vmexit(svm);
- return 1;
- }
+ svm->vmcb->control.exit_code = SVM_EXIT_INTR;
+
+ if (svm->nested.intercept & 1ULL) {
+ /*
+ * The #vmexit can't be emulated here directly because this
+ * code path runs with irqs and preemtion disabled. A
+ * #vmexit emulation might sleep. Only signal request for
+ * the #vmexit here.
+ */
+ svm->nested.exit_required = true;
+ trace_kvm_nested_intr_vmexit(svm->vmcb->save.rip);
+ return false;
}
- return 0;
+ return true;
}
-static struct page *nested_svm_get_page(struct vcpu_svm *svm, u64 gpa)
+static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, struct page **_page)
{
struct page *page;
- down_read(¤t->mm->mmap_sem);
+ might_sleep();
+
page = gfn_to_page(svm->vcpu.kvm, gpa >> PAGE_SHIFT);
- up_read(¤t->mm->mmap_sem);
+ if (is_error_page(page))
+ goto error;
- if (is_error_page(page)) {
- printk(KERN_INFO "%s: could not find page at 0x%llx\n",
- __func__, gpa);
- kvm_release_page_clean(page);
- kvm_inject_gp(&svm->vcpu, 0);
- return NULL;
- }
- return page;
-}
+ *_page = page;
-static int nested_svm_do(struct vcpu_svm *svm,
- u64 arg1_gpa, u64 arg2_gpa, void *opaque,
- int (*handler)(struct vcpu_svm *svm,
- void *arg1,
- void *arg2,
- void *opaque))
-{
- struct page *arg1_page;
- struct page *arg2_page = NULL;
- void *arg1;
- void *arg2 = NULL;
- int retval;
+ return kmap(page);
- arg1_page = nested_svm_get_page(svm, arg1_gpa);
- if(arg1_page == NULL)
- return 1;
+error:
+ kvm_release_page_clean(page);
+ kvm_inject_gp(&svm->vcpu, 0);
- if (arg2_gpa) {
- arg2_page = nested_svm_get_page(svm, arg2_gpa);
- if(arg2_page == NULL) {
- kvm_release_page_clean(arg1_page);
- return 1;
- }
- }
+ return NULL;
+}
- arg1 = kmap_atomic(arg1_page, KM_USER0);
- if (arg2_gpa)
- arg2 = kmap_atomic(arg2_page, KM_USER1);
+static void nested_svm_unmap(struct page *page)
+{
+ kunmap(page);
+ kvm_release_page_dirty(page);
+}
- retval = handler(svm, arg1, arg2, opaque);
+static bool nested_svm_exit_handled_msr(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;
- kunmap_atomic(arg1, KM_USER0);
- if (arg2_gpa)
- kunmap_atomic(arg2, KM_USER1);
+ if (!(svm->nested.intercept & (1ULL << INTERCEPT_MSR_PROT)))
+ return false;
- kvm_release_page_dirty(arg1_page);
- if (arg2_gpa)
- kvm_release_page_dirty(arg2_page);
+ 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;
+ }
+
+ if (!kvm_read_guest(svm->vcpu.kvm, svm->nested.vmcb_msrpm + t1, &val, 1))
+ ret = val & ((1 << param) << t0);
- return retval;
+out:
+ return ret;
}
-static int nested_svm_exit_handled_real(struct vcpu_svm *svm,
- void *arg1,
- void *arg2,
- void *opaque)
+static int nested_svm_exit_special(struct vcpu_svm *svm)
{
- struct vmcb *nested_vmcb = (struct vmcb *)arg1;
- bool kvm_overrides = *(bool *)opaque;
u32 exit_code = svm->vmcb->control.exit_code;
- if (kvm_overrides) {
- switch (exit_code) {
- case SVM_EXIT_INTR:
- case SVM_EXIT_NMI:
- return 0;
+ switch (exit_code) {
+ case SVM_EXIT_INTR:
+ case SVM_EXIT_NMI:
+ return NESTED_EXIT_HOST;
/* For now we are always handling NPFs when using them */
- case SVM_EXIT_NPF:
- if (npt_enabled)
- return 0;
- break;
- /* When we're shadowing, trap PFs */
- case SVM_EXIT_EXCP_BASE + PF_VECTOR:
- if (!npt_enabled)
- return 0;
- break;
- default:
- break;
- }
+ case SVM_EXIT_NPF:
+ if (npt_enabled)
+ return NESTED_EXIT_HOST;
+ break;
+ /* When we're shadowing, trap PFs */
+ case SVM_EXIT_EXCP_BASE + PF_VECTOR:
+ if (!npt_enabled)
+ return NESTED_EXIT_HOST;
+ break;
+ case SVM_EXIT_EXCP_BASE + NM_VECTOR:
+ nm_interception(svm);
+ break;
+ default:
+ break;
}
+ return NESTED_EXIT_CONTINUE;
+}
+
+/*
+ * If this function returns true, this #vmexit was already handled
+ */
+static int nested_svm_intercept(struct vcpu_svm *svm)
+{
+ u32 exit_code = svm->vmcb->control.exit_code;
+ int vmexit = NESTED_EXIT_HOST;
+
switch (exit_code) {
+ case SVM_EXIT_MSR:
+ vmexit = nested_svm_exit_handled_msr(svm);
+ break;
case SVM_EXIT_READ_CR0 ... SVM_EXIT_READ_CR8: {
u32 cr_bits = 1 << (exit_code - SVM_EXIT_READ_CR0);
- if (nested_vmcb->control.intercept_cr_read & cr_bits)
- return 1;
+ if (svm->nested.intercept_cr_read & cr_bits)
+ vmexit = NESTED_EXIT_DONE;
break;
}
case SVM_EXIT_WRITE_CR0 ... SVM_EXIT_WRITE_CR8: {
u32 cr_bits = 1 << (exit_code - SVM_EXIT_WRITE_CR0);
- if (nested_vmcb->control.intercept_cr_write & cr_bits)
- return 1;
+ if (svm->nested.intercept_cr_write & cr_bits)
+ vmexit = NESTED_EXIT_DONE;
break;
}
case SVM_EXIT_READ_DR0 ... SVM_EXIT_READ_DR7: {
u32 dr_bits = 1 << (exit_code - SVM_EXIT_READ_DR0);
- if (nested_vmcb->control.intercept_dr_read & dr_bits)
- return 1;
+ if (svm->nested.intercept_dr_read & dr_bits)
+ vmexit = NESTED_EXIT_DONE;
break;
}
case SVM_EXIT_WRITE_DR0 ... SVM_EXIT_WRITE_DR7: {
u32 dr_bits = 1 << (exit_code - SVM_EXIT_WRITE_DR0);
- if (nested_vmcb->control.intercept_dr_write & dr_bits)
- return 1;
+ if (svm->nested.intercept_dr_write & dr_bits)
+ vmexit = NESTED_EXIT_DONE;
break;
}
case SVM_EXIT_EXCP_BASE ... SVM_EXIT_EXCP_BASE + 0x1f: {
u32 excp_bits = 1 << (exit_code - SVM_EXIT_EXCP_BASE);
- if (nested_vmcb->control.intercept_exceptions & excp_bits)
- return 1;
+ if (svm->nested.intercept_exceptions & excp_bits)
+ vmexit = NESTED_EXIT_DONE;
break;
}
default: {
u64 exit_bits = 1ULL << (exit_code - SVM_EXIT_INTR);
- nsvm_printk("exit code: 0x%x\n", exit_code);
- if (nested_vmcb->control.intercept & exit_bits)
- return 1;
+ if (svm->nested.intercept & exit_bits)
+ vmexit = NESTED_EXIT_DONE;
}
}
- return 0;
+ return vmexit;
}
-static int nested_svm_exit_handled_msr(struct vcpu_svm *svm,
- void *arg1, void *arg2,
- void *opaque)
+static int nested_svm_exit_handled(struct vcpu_svm *svm)
{
- struct vmcb *nested_vmcb = (struct vmcb *)arg1;
- u8 *msrpm = (u8 *)arg2;
- u32 t0, t1;
- u32 msr = svm->vcpu.arch.regs[VCPU_REGS_RCX];
- u32 param = svm->vmcb->control.exit_info_1 & 1;
+ int vmexit;
- if (!(nested_vmcb->control.intercept & (1ULL << INTERCEPT_MSR_PROT)))
- return 0;
+ vmexit = nested_svm_intercept(svm);
- 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:
- return 1;
- break;
- }
- if (msrpm[t1] & ((1 << param) << t0))
- return 1;
+ if (vmexit == NESTED_EXIT_DONE)
+ nested_svm_vmexit(svm);
- return 0;
+ return vmexit;
}
-static int nested_svm_exit_handled(struct vcpu_svm *svm, bool kvm_override)
+static inline void copy_vmcb_control_area(struct vmcb *dst_vmcb, struct vmcb *from_vmcb)
{
- bool k = kvm_override;
+ struct vmcb_control_area *dst = &dst_vmcb->control;
+ struct vmcb_control_area *from = &from_vmcb->control;
- switch (svm->vmcb->control.exit_code) {
- case SVM_EXIT_MSR:
- return nested_svm_do(svm, svm->nested_vmcb,
- svm->nested_vmcb_msrpm, NULL,
- nested_svm_exit_handled_msr);
- default: break;
- }
+ dst->intercept_cr_read = from->intercept_cr_read;
+ dst->intercept_cr_write = from->intercept_cr_write;
+ dst->intercept_dr_read = from->intercept_dr_read;
+ dst->intercept_dr_write = from->intercept_dr_write;
+ dst->intercept_exceptions = from->intercept_exceptions;
+ dst->intercept = from->intercept;
+ dst->iopm_base_pa = from->iopm_base_pa;
+ dst->msrpm_base_pa = from->msrpm_base_pa;
+ dst->tsc_offset = from->tsc_offset;
+ dst->asid = from->asid;
+ dst->tlb_ctl = from->tlb_ctl;
+ dst->int_ctl = from->int_ctl;
+ dst->int_vector = from->int_vector;
+ dst->int_state = from->int_state;
+ dst->exit_code = from->exit_code;
+ dst->exit_code_hi = from->exit_code_hi;
+ dst->exit_info_1 = from->exit_info_1;
+ dst->exit_info_2 = from->exit_info_2;
+ dst->exit_int_info = from->exit_int_info;
+ dst->exit_int_info_err = from->exit_int_info_err;
+ dst->nested_ctl = from->nested_ctl;
+ dst->event_inj = from->event_inj;
+ dst->event_inj_err = from->event_inj_err;
+ dst->nested_cr3 = from->nested_cr3;
+ dst->lbr_ctl = from->lbr_ctl;
+}
+
+static int nested_svm_vmexit(struct vcpu_svm *svm)
+{
+ struct vmcb *nested_vmcb;
+ struct vmcb *hsave = svm->nested.hsave;
+ struct vmcb *vmcb = svm->vmcb;
+ struct page *page;
- return nested_svm_do(svm, svm->nested_vmcb, 0, &k,
- nested_svm_exit_handled_real);
-}
-
-static int nested_svm_vmexit_real(struct vcpu_svm *svm, void *arg1,
- void *arg2, void *opaque)
-{
- struct vmcb *nested_vmcb = (struct vmcb *)arg1;
- struct vmcb *hsave = svm->hsave;
- u64 nested_save[] = { nested_vmcb->save.cr0,
- nested_vmcb->save.cr3,
- nested_vmcb->save.cr4,
- nested_vmcb->save.efer,
- nested_vmcb->control.intercept_cr_read,
- nested_vmcb->control.intercept_cr_write,
- nested_vmcb->control.intercept_dr_read,
- nested_vmcb->control.intercept_dr_write,
- nested_vmcb->control.intercept_exceptions,
- nested_vmcb->control.intercept,
- nested_vmcb->control.msrpm_base_pa,
- nested_vmcb->control.iopm_base_pa,
- nested_vmcb->control.tsc_offset };
+ trace_kvm_nested_vmexit_inject(vmcb->control.exit_code,
+ vmcb->control.exit_info_1,
+ vmcb->control.exit_info_2,
+ vmcb->control.exit_int_info,
+ vmcb->control.exit_int_info_err);
+
+ 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 */
- memcpy(nested_vmcb, svm->vmcb, sizeof(struct vmcb));
- nested_vmcb->save.cr0 = nested_save[0];
- if (!npt_enabled)
- nested_vmcb->save.cr3 = nested_save[1];
- nested_vmcb->save.cr4 = nested_save[2];
- nested_vmcb->save.efer = nested_save[3];
- nested_vmcb->control.intercept_cr_read = nested_save[4];
- nested_vmcb->control.intercept_cr_write = nested_save[5];
- nested_vmcb->control.intercept_dr_read = nested_save[6];
- nested_vmcb->control.intercept_dr_write = nested_save[7];
- nested_vmcb->control.intercept_exceptions = nested_save[8];
- nested_vmcb->control.intercept = nested_save[9];
- nested_vmcb->control.msrpm_base_pa = nested_save[10];
- nested_vmcb->control.iopm_base_pa = nested_save[11];
- nested_vmcb->control.tsc_offset = nested_save[12];
+ disable_gif(svm);
+
+ nested_vmcb->save.es = vmcb->save.es;
+ nested_vmcb->save.cs = vmcb->save.cs;
+ nested_vmcb->save.ss = vmcb->save.ss;
+ 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;
+ nested_vmcb->save.rax = vmcb->save.rax;
+ nested_vmcb->save.dr7 = vmcb->save.dr7;
+ nested_vmcb->save.dr6 = vmcb->save.dr6;
+ nested_vmcb->save.cpl = vmcb->save.cpl;
+
+ nested_vmcb->control.int_ctl = vmcb->control.int_ctl;
+ nested_vmcb->control.int_vector = vmcb->control.int_vector;
+ nested_vmcb->control.int_state = vmcb->control.int_state;
+ nested_vmcb->control.exit_code = vmcb->control.exit_code;
+ nested_vmcb->control.exit_code_hi = vmcb->control.exit_code_hi;
+ nested_vmcb->control.exit_info_1 = vmcb->control.exit_info_1;
+ nested_vmcb->control.exit_info_2 = vmcb->control.exit_info_2;
+ nested_vmcb->control.exit_int_info = vmcb->control.exit_int_info;
+ nested_vmcb->control.exit_int_info_err = vmcb->control.exit_int_info_err;
+
+ /*
+ * If we emulate a VMRUN/#VMEXIT in the same host #vmexit cycle we have
+ * to make sure that we do not lose injected events. So check event_inj
+ * here and copy it to exit_int_info if it is valid.
+ * Exit_int_info and event_inj can't be both valid because the case
+ * below only happens on a VMRUN instruction intercept which has
+ * no valid exit_int_info set.
+ */
+ if (vmcb->control.event_inj & SVM_EVTINJ_VALID) {
+ struct vmcb_control_area *nc = &nested_vmcb->control;
+
+ nc->exit_int_info = vmcb->control.event_inj;
+ nc->exit_int_info_err = vmcb->control.event_inj_err;
+ }
+
+ nested_vmcb->control.tlb_ctl = 0;
+ nested_vmcb->control.event_inj = 0;
+ nested_vmcb->control.event_inj_err = 0;
/* We always set V_INTR_MASKING and remember the old value in hflags */
if (!(svm->vcpu.arch.hflags & HF_VINTR_MASK))
nested_vmcb->control.int_ctl &= ~V_INTR_MASKING_MASK;
- if ((nested_vmcb->control.int_ctl & V_IRQ_MASK) &&
- (nested_vmcb->control.int_vector)) {
- nsvm_printk("WARNING: IRQ 0x%x still enabled on #VMEXIT\n",
- nested_vmcb->control.int_vector);
- }
-
/* Restore the original control entries */
- svm->vmcb->control = hsave->control;
+ copy_vmcb_control_area(vmcb, hsave);
- /* Kill any pending exceptions */
- if (svm->vcpu.arch.exception.pending == true)
- nsvm_printk("WARNING: Pending Exception\n");
kvm_clear_exception_queue(&svm->vcpu);
kvm_clear_interrupt_queue(&svm->vcpu);
svm->vmcb->save.cpl = 0;
svm->vmcb->control.exit_int_info = 0;
- svm->vcpu.arch.hflags &= ~HF_GIF_MASK;
- /* Exit nested SVM mode */
- svm->nested_vmcb = 0;
-
- return 0;
-}
-
-static int nested_svm_vmexit(struct vcpu_svm *svm)
-{
- nsvm_printk("VMexit\n");
- if (nested_svm_do(svm, svm->nested_vmcb, 0,
- NULL, nested_svm_vmexit_real))
- return 1;
+ nested_svm_unmap(page);
kvm_mmu_reset_context(&svm->vcpu);
kvm_mmu_load(&svm->vcpu);
return 0;
}
-static int nested_svm_vmrun_msrpm(struct vcpu_svm *svm, void *arg1,
- void *arg2, void *opaque)
+static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
{
+ u32 *nested_msrpm;
+ struct page *page;
int i;
- u32 *nested_msrpm = (u32*)arg1;
+
+ nested_msrpm = nested_svm_map(svm, svm->nested.vmcb_msrpm, &page);
+ if (!nested_msrpm)
+ return false;
+
for (i=0; i< PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER) / 4; i++)
- svm->nested_msrpm[i] = svm->msrpm[i] | nested_msrpm[i];
- svm->vmcb->control.msrpm_base_pa = __pa(svm->nested_msrpm);
+ svm->nested.msrpm[i] = svm->msrpm[i] | nested_msrpm[i];
- return 0;
+ svm->vmcb->control.msrpm_base_pa = __pa(svm->nested.msrpm);
+
+ nested_svm_unmap(page);
+
+ return true;
}
-static int nested_svm_vmrun(struct vcpu_svm *svm, void *arg1,
- void *arg2, void *opaque)
+static bool nested_svm_vmrun(struct vcpu_svm *svm)
{
- struct vmcb *nested_vmcb = (struct vmcb *)arg1;
- struct vmcb *hsave = svm->hsave;
+ struct vmcb *nested_vmcb;
+ struct vmcb *hsave = svm->nested.hsave;
+ struct vmcb *vmcb = svm->vmcb;
+ struct page *page;
+ u64 vmcb_gpa;
- /* nested_vmcb is our indicator if nested SVM is activated */
- svm->nested_vmcb = svm->vmcb->save.rax;
+ vmcb_gpa = svm->vmcb->save.rax;
+
+ nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page);
+ if (!nested_vmcb)
+ return false;
+
+ trace_kvm_nested_vmrun(svm->vmcb->save.rip - 3, svm->nested.vmcb,
+ nested_vmcb->save.rip,
+ nested_vmcb->control.int_ctl,
+ nested_vmcb->control.event_inj,
+ nested_vmcb->control.nested_ctl);
/* Clear internal status */
kvm_clear_exception_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 */
- memcpy(hsave, svm->vmcb, sizeof(struct vmcb));
- /* We need to remember the original CR3 in the SPT case */
- if (!npt_enabled)
- hsave->save.cr3 = svm->vcpu.arch.cr3;
- hsave->save.cr4 = svm->vcpu.arch.cr4;
- hsave->save.rip = svm->next_rip;
+ hsave->save.es = vmcb->save.es;
+ hsave->save.cs = vmcb->save.cs;
+ hsave->save.ss = vmcb->save.ss;
+ hsave->save.ds = vmcb->save.ds;
+ hsave->save.gdtr = vmcb->save.gdtr;
+ hsave->save.idtr = vmcb->save.idtr;
+ 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;
+ hsave->save.rip = svm->next_rip;
+ hsave->save.rsp = vmcb->save.rsp;
+ hsave->save.rax = vmcb->save.rax;
+ if (npt_enabled)
+ hsave->save.cr3 = vmcb->save.cr3;
+ else
+ hsave->save.cr3 = svm->vcpu.arch.cr3;
+
+ copy_vmcb_control_area(hsave, vmcb);
if (svm->vmcb->save.rflags & X86_EFLAGS_IF)
svm->vcpu.arch.hflags |= HF_HIF_MASK;
kvm_set_cr3(&svm->vcpu, nested_vmcb->save.cr3);
kvm_mmu_reset_context(&svm->vcpu);
}
- svm->vmcb->save.cr2 = nested_vmcb->save.cr2;
+ 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);
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;
+
+ /* cache intercepts */
+ svm->nested.intercept_cr_read = nested_vmcb->control.intercept_cr_read;
+ svm->nested.intercept_cr_write = nested_vmcb->control.intercept_cr_write;
+ svm->nested.intercept_dr_read = nested_vmcb->control.intercept_dr_read;
+ svm->nested.intercept_dr_write = nested_vmcb->control.intercept_dr_write;
+ svm->nested.intercept_exceptions = nested_vmcb->control.intercept_exceptions;
+ svm->nested.intercept = nested_vmcb->control.intercept;
+
+ force_new_asid(&svm->vcpu);
+ svm->vmcb->control.int_ctl = nested_vmcb->control.int_ctl | V_INTR_MASKING_MASK;
+ if (nested_vmcb->control.int_ctl & V_INTR_MASKING_MASK)
+ svm->vcpu.arch.hflags |= HF_VINTR_MASK;
+ 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 |=
svm->vmcb->control.intercept |= nested_vmcb->control.intercept;
- svm->nested_vmcb_msrpm = nested_vmcb->control.msrpm_base_pa;
-
- force_new_asid(&svm->vcpu);
- svm->vmcb->control.exit_int_info = nested_vmcb->control.exit_int_info;
- svm->vmcb->control.exit_int_info_err = nested_vmcb->control.exit_int_info_err;
- svm->vmcb->control.int_ctl = nested_vmcb->control.int_ctl | V_INTR_MASKING_MASK;
- if (nested_vmcb->control.int_ctl & V_IRQ_MASK) {
- nsvm_printk("nSVM Injecting Interrupt: 0x%x\n",
- nested_vmcb->control.int_ctl);
- }
- if (nested_vmcb->control.int_ctl & V_INTR_MASKING_MASK)
- svm->vcpu.arch.hflags |= HF_VINTR_MASK;
- else
- svm->vcpu.arch.hflags &= ~HF_VINTR_MASK;
-
- nsvm_printk("nSVM exit_int_info: 0x%x | int_state: 0x%x\n",
- nested_vmcb->control.exit_int_info,
- nested_vmcb->control.int_state);
-
+ 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;
- if (nested_vmcb->control.event_inj & SVM_EVTINJ_VALID)
- nsvm_printk("Injecting Event: 0x%x\n",
- nested_vmcb->control.event_inj);
svm->vmcb->control.event_inj = nested_vmcb->control.event_inj;
svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err;
- svm->vcpu.arch.hflags |= HF_GIF_MASK;
+ nested_svm_unmap(page);
- return 0;
+ /* nested_vmcb is our indicator if nested SVM is activated */
+ svm->nested.vmcb = vmcb_gpa;
+
+ enable_gif(svm);
+
+ return true;
}
-static int nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb)
+static void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb)
{
to_vmcb->save.fs = from_vmcb->save.fs;
to_vmcb->save.gs = from_vmcb->save.gs;
to_vmcb->save.sysenter_cs = from_vmcb->save.sysenter_cs;
to_vmcb->save.sysenter_esp = from_vmcb->save.sysenter_esp;
to_vmcb->save.sysenter_eip = from_vmcb->save.sysenter_eip;
-
- return 1;
-}
-
-static int nested_svm_vmload(struct vcpu_svm *svm, void *nested_vmcb,
- void *arg2, void *opaque)
-{
- return nested_svm_vmloadsave((struct vmcb *)nested_vmcb, svm->vmcb);
}
-static int nested_svm_vmsave(struct vcpu_svm *svm, void *nested_vmcb,
- void *arg2, void *opaque)
+static int vmload_interception(struct vcpu_svm *svm)
{
- return nested_svm_vmloadsave(svm->vmcb, (struct vmcb *)nested_vmcb);
-}
+ struct vmcb *nested_vmcb;
+ struct page *page;
-static int vmload_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
-{
if (nested_svm_check_permissions(svm))
return 1;
svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
skip_emulated_instruction(&svm->vcpu);
- nested_svm_do(svm, svm->vmcb->save.rax, 0, NULL, nested_svm_vmload);
+ 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(page);
return 1;
}
-static int vmsave_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+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_svm_do(svm, svm->vmcb->save.rax, 0, NULL, nested_svm_vmsave);
+ 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(page);
return 1;
}
-static int vmrun_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int vmrun_interception(struct vcpu_svm *svm)
{
- nsvm_printk("VMrun\n");
if (nested_svm_check_permissions(svm))
return 1;
svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
skip_emulated_instruction(&svm->vcpu);
- if (nested_svm_do(svm, svm->vmcb->save.rax, 0,
- NULL, nested_svm_vmrun))
+ if (!nested_svm_vmrun(svm))
return 1;
- if (nested_svm_do(svm, svm->nested_vmcb_msrpm, 0,
- NULL, nested_svm_vmrun_msrpm))
- return 1;
+ if (!nested_svm_vmrun_msrpm(svm))
+ goto failed;
+
+ return 1;
+
+failed:
+
+ svm->vmcb->control.exit_code = SVM_EXIT_ERR;
+ svm->vmcb->control.exit_code_hi = 0;
+ svm->vmcb->control.exit_info_1 = 0;
+ svm->vmcb->control.exit_info_2 = 0;
+
+ nested_svm_vmexit(svm);
return 1;
}
-static int stgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int stgi_interception(struct vcpu_svm *svm)
{
if (nested_svm_check_permissions(svm))
return 1;
svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
skip_emulated_instruction(&svm->vcpu);
- svm->vcpu.arch.hflags |= HF_GIF_MASK;
+ enable_gif(svm);
return 1;
}
-static int clgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int clgi_interception(struct vcpu_svm *svm)
{
if (nested_svm_check_permissions(svm))
return 1;
svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
skip_emulated_instruction(&svm->vcpu);
- svm->vcpu.arch.hflags &= ~HF_GIF_MASK;
+ disable_gif(svm);
/* After a CLGI no interrupts should come */
svm_clear_vintr(svm);
return 1;
}
-static int invlpga_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int invlpga_interception(struct vcpu_svm *svm)
{
struct kvm_vcpu *vcpu = &svm->vcpu;
- nsvm_printk("INVLPGA\n");
+
+ trace_kvm_invlpga(svm->vmcb->save.rip, vcpu->arch.regs[VCPU_REGS_RCX],
+ vcpu->arch.regs[VCPU_REGS_RAX]);
/* Let's treat INVLPGA the same as INVLPG (can be optimized!) */
kvm_mmu_invlpg(vcpu, vcpu->arch.regs[VCPU_REGS_RAX]);
return 1;
}
-static int invalid_op_interception(struct vcpu_svm *svm,
- struct kvm_run *kvm_run)
+static int skinit_interception(struct vcpu_svm *svm)
+{
+ trace_kvm_skinit(svm->vmcb->save.rip, svm->vcpu.arch.regs[VCPU_REGS_RAX]);
+
+ kvm_queue_exception(&svm->vcpu, UD_VECTOR);
+ return 1;
+}
+
+static int invalid_op_interception(struct vcpu_svm *svm)
{
kvm_queue_exception(&svm->vcpu, UD_VECTOR);
return 1;
}
-static int task_switch_interception(struct vcpu_svm *svm,
- struct kvm_run *kvm_run)
+static int task_switch_interception(struct vcpu_svm *svm)
{
u16 tss_selector;
int reason;
return kvm_task_switch(&svm->vcpu, tss_selector, reason);
}
-static int cpuid_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int cpuid_interception(struct vcpu_svm *svm)
{
svm->next_rip = kvm_rip_read(&svm->vcpu) + 2;
kvm_emulate_cpuid(&svm->vcpu);
return 1;
}
-static int iret_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int iret_interception(struct vcpu_svm *svm)
{
++svm->vcpu.stat.nmi_window_exits;
svm->vmcb->control.intercept &= ~(1UL << INTERCEPT_IRET);
return 1;
}
-static int invlpg_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int invlpg_interception(struct vcpu_svm *svm)
{
- if (emulate_instruction(&svm->vcpu, kvm_run, 0, 0, 0) != EMULATE_DONE)
+ if (emulate_instruction(&svm->vcpu, 0, 0, 0) != EMULATE_DONE)
pr_unimpl(&svm->vcpu, "%s: failed\n", __func__);
return 1;
}
-static int emulate_on_interception(struct vcpu_svm *svm,
- struct kvm_run *kvm_run)
+static int emulate_on_interception(struct vcpu_svm *svm)
{
- if (emulate_instruction(&svm->vcpu, NULL, 0, 0, 0) != EMULATE_DONE)
+ if (emulate_instruction(&svm->vcpu, 0, 0, 0) != EMULATE_DONE)
pr_unimpl(&svm->vcpu, "%s: failed\n", __func__);
return 1;
}
-static int cr8_write_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int cr8_write_interception(struct vcpu_svm *svm)
{
+ struct kvm_run *kvm_run = svm->vcpu.run;
+
u8 cr8_prev = kvm_get_cr8(&svm->vcpu);
/* instruction emulation calls kvm_set_cr8() */
- emulate_instruction(&svm->vcpu, NULL, 0, 0, 0);
+ emulate_instruction(&svm->vcpu, 0, 0, 0);
if (irqchip_in_kernel(svm->vcpu.kvm)) {
svm->vmcb->control.intercept_cr_write &= ~INTERCEPT_CR8_MASK;
return 1;
switch (ecx) {
case MSR_IA32_TSC: {
- u64 tsc;
+ u64 tsc_offset;
+
+ if (is_nested(svm))
+ tsc_offset = svm->nested.hsave->control.tsc_offset;
+ else
+ tsc_offset = svm->vmcb->control.tsc_offset;
- rdtscll(tsc);
- *data = svm->vmcb->control.tsc_offset + tsc;
+ *data = tsc_offset + native_read_tsc();
break;
}
case MSR_K6_STAR:
*data = svm->vmcb->save.last_excp_to;
break;
case MSR_VM_HSAVE_PA:
- *data = svm->hsave_msr;
+ *data = svm->nested.hsave_msr;
break;
case MSR_VM_CR:
*data = 0;
return 0;
}
-static int rdmsr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int rdmsr_interception(struct vcpu_svm *svm)
{
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;
switch (ecx) {
case MSR_IA32_TSC: {
- u64 tsc;
+ u64 tsc_offset = data - native_read_tsc();
+ u64 g_tsc_offset = 0;
+
+ if (is_nested(svm)) {
+ g_tsc_offset = svm->vmcb->control.tsc_offset -
+ svm->nested.hsave->control.tsc_offset;
+ svm->nested.hsave->control.tsc_offset = tsc_offset;
+ }
+
+ svm->vmcb->control.tsc_offset = tsc_offset + g_tsc_offset;
- rdtscll(tsc);
- svm->vmcb->control.tsc_offset = data - tsc;
break;
}
case MSR_K6_STAR:
svm_disable_lbrv(svm);
break;
case MSR_VM_HSAVE_PA:
- svm->hsave_msr = data;
+ svm->nested.hsave_msr = data;
break;
case MSR_VM_CR:
case MSR_VM_IGNNE:
return 0;
}
-static int wrmsr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int wrmsr_interception(struct vcpu_svm *svm)
{
u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX];
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;
}
-static int msr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int msr_interception(struct vcpu_svm *svm)
{
if (svm->vmcb->control.exit_info_1)
- return wrmsr_interception(svm, kvm_run);
+ return wrmsr_interception(svm);
else
- return rdmsr_interception(svm, kvm_run);
+ return rdmsr_interception(svm);
}
-static int interrupt_window_interception(struct vcpu_svm *svm,
- struct kvm_run *kvm_run)
+static int interrupt_window_interception(struct vcpu_svm *svm)
{
+ struct kvm_run *kvm_run = svm->vcpu.run;
+
svm_clear_vintr(svm);
svm->vmcb->control.int_ctl &= ~V_IRQ_MASK;
/*
return 1;
}
-static int (*svm_exit_handlers[])(struct vcpu_svm *svm,
- struct kvm_run *kvm_run) = {
+static int pause_interception(struct vcpu_svm *svm)
+{
+ kvm_vcpu_on_spin(&(svm->vcpu));
+ return 1;
+}
+
+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,
- /* for now: */
+ [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_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,
[SVM_EXIT_CPUID] = cpuid_interception,
[SVM_EXIT_IRET] = iret_interception,
[SVM_EXIT_INVD] = emulate_on_interception,
+ [SVM_EXIT_PAUSE] = pause_interception,
[SVM_EXIT_HLT] = halt_interception,
[SVM_EXIT_INVLPG] = invlpg_interception,
[SVM_EXIT_INVLPGA] = invlpga_interception,
[SVM_EXIT_VMSAVE] = vmsave_interception,
[SVM_EXIT_STGI] = stgi_interception,
[SVM_EXIT_CLGI] = clgi_interception,
- [SVM_EXIT_SKINIT] = invalid_op_interception,
+ [SVM_EXIT_SKINIT] = skinit_interception,
[SVM_EXIT_WBINVD] = emulate_on_interception,
[SVM_EXIT_MONITOR] = invalid_op_interception,
[SVM_EXIT_MWAIT] = invalid_op_interception,
[SVM_EXIT_NPF] = pf_interception,
};
-static int handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
+static int handle_exit(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
+ struct kvm_run *kvm_run = vcpu->run;
u32 exit_code = svm->vmcb->control.exit_code;
trace_kvm_exit(exit_code, svm->vmcb->save.rip);
+ if (unlikely(svm->nested.exit_required)) {
+ nested_svm_vmexit(svm);
+ svm->nested.exit_required = false;
+
+ return 1;
+ }
+
if (is_nested(svm)) {
- nsvm_printk("nested handle_exit: 0x%x | 0x%lx | 0x%lx | 0x%lx\n",
- exit_code, svm->vmcb->control.exit_info_1,
- svm->vmcb->control.exit_info_2, svm->vmcb->save.rip);
- if (nested_svm_exit_handled(svm, true)) {
- nested_svm_vmexit(svm);
- nsvm_printk("-> #VMEXIT\n");
+ int vmexit;
+
+ trace_kvm_nested_vmexit(svm->vmcb->save.rip, exit_code,
+ svm->vmcb->control.exit_info_1,
+ svm->vmcb->control.exit_info_2,
+ svm->vmcb->control.exit_int_info,
+ svm->vmcb->control.exit_int_info_err);
+
+ vmexit = nested_svm_exit_special(svm);
+
+ if (vmexit == NESTED_EXIT_CONTINUE)
+ vmexit = nested_svm_exit_handled(svm);
+
+ if (vmexit == NESTED_EXIT_DONE)
return 1;
- }
}
- if (npt_enabled) {
- int mmu_reload = 0;
- if ((vcpu->arch.cr0 ^ svm->vmcb->save.cr0) & X86_CR0_PG) {
- svm_set_cr0(vcpu, svm->vmcb->save.cr0);
- mmu_reload = 1;
- }
+ 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 (mmu_reload) {
- kvm_mmu_reset_context(vcpu);
- kvm_mmu_load(vcpu);
- }
- }
-
if (svm->vmcb->control.exit_code == SVM_EXIT_ERR) {
kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
return 0;
}
- return svm_exit_handlers[exit_code](svm, kvm_run);
+ return svm_exit_handlers[exit_code](svm);
}
static void reload_tss(struct kvm_vcpu *vcpu)
{
int cpu = raw_smp_processor_id();
- struct svm_cpu_data *svm_data = per_cpu(svm_data, cpu);
- svm_data->tss_desc->type = 9; /* available 32/64-bit TSS */
+ struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
+ sd->tss_desc->type = 9; /* available 32/64-bit TSS */
load_TR_desc();
}
{
int cpu = raw_smp_processor_id();
- struct svm_cpu_data *svm_data = per_cpu(svm_data, cpu);
+ struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
svm->vmcb->control.tlb_ctl = TLB_CONTROL_DO_NOTHING;
/* FIXME: handle wraparound of asid_generation */
- if (svm->asid_generation != svm_data->asid_generation)
- new_asid(svm, svm_data);
+ if (svm->asid_generation != sd->asid_generation)
+ new_asid(svm, sd);
}
static void svm_inject_nmi(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
- BUG_ON(!(svm->vcpu.arch.hflags & HF_GIF_MASK));
+ BUG_ON(!(gif_set(svm)));
svm->vmcb->control.event_inj = vcpu->arch.interrupt.nr |
SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR;
{
struct vcpu_svm *svm = to_svm(vcpu);
+ if (is_nested(svm) && (vcpu->arch.hflags & HF_VINTR_MASK))
+ return;
+
if (irr == -1)
return;
!(svm->vcpu.arch.hflags & HF_NMI_MASK);
}
+static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_svm *svm = to_svm(vcpu);
+
+ return !!(svm->vcpu.arch.hflags & HF_NMI_MASK);
+}
+
+static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked)
+{
+ struct vcpu_svm *svm = to_svm(vcpu);
+
+ if (masked) {
+ svm->vcpu.arch.hflags |= HF_NMI_MASK;
+ svm->vmcb->control.intercept |= (1UL << INTERCEPT_IRET);
+ } else {
+ svm->vcpu.arch.hflags &= ~HF_NMI_MASK;
+ svm->vmcb->control.intercept &= ~(1UL << INTERCEPT_IRET);
+ }
+}
+
static int svm_interrupt_allowed(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct vmcb *vmcb = svm->vmcb;
- return (vmcb->save.rflags & X86_EFLAGS_IF) &&
- !(vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) &&
- (svm->vcpu.arch.hflags & HF_GIF_MASK) &&
- !is_nested(svm);
+ int ret;
+
+ if (!gif_set(svm) ||
+ (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK))
+ return 0;
+
+ ret = !!(vmcb->save.rflags & X86_EFLAGS_IF);
+
+ if (is_nested(svm))
+ return ret && !(svm->vcpu.arch.hflags & HF_VINTR_MASK);
+
+ return ret;
}
static void enable_irq_window(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
- nsvm_printk("Trying to open IRQ window\n");
-
- 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 (svm->vcpu.arch.hflags & HF_GIF_MASK) {
+ if (gif_set(svm) && nested_svm_intr(svm)) {
svm_set_vintr(svm);
svm_inject_irq(svm, 0x0);
}
/* Something prevents NMI from been injected. Single step over
possible problem (IRET or exception injection or interrupt
shadow) */
- vcpu->arch.singlestep = true;
+ svm->nmi_singlestep = true;
svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF);
update_db_intercept(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);
#define R "e"
#endif
-static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static void svm_vcpu_run(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
u16 fs_selector;
u16 gs_selector;
u16 ldt_selector;
+ /*
+ * 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];
fs_selector = kvm_read_fs();
gs_selector = kvm_read_gs();
ldt_selector = kvm_read_ldt();
- if (!is_nested(svm))
- svm->vmcb->save.cr2 = vcpu->arch.cr2;
+ svm->vmcb->save.cr2 = vcpu->arch.cr2;
/* required for live migration with NPT */
if (npt_enabled)
svm->vmcb->save.cr3 = vcpu->arch.cr3;
vcpu->arch.regs_avail &= ~(1 << VCPU_EXREG_PDPTR);
vcpu->arch.regs_dirty &= ~(1 << VCPU_EXREG_PDPTR);
}
-
- svm_complete_interrupts(svm);
}
#undef R
svm->vmcb->save.cr3 = root;
force_new_asid(vcpu);
-
- if (vcpu->fpu_active) {
- svm->vmcb->control.intercept_exceptions |= (1 << NM_VECTOR);
- svm->vmcb->save.cr0 |= X86_CR0_TS;
- vcpu->fpu_active = 0;
- }
}
static int is_disabled(void)
return 0;
}
+static void svm_cpuid_update(struct kvm_vcpu *vcpu)
+{
+}
+
static const struct trace_print_flags svm_exit_reasons_str[] = {
{ SVM_EXIT_READ_CR0, "read_cr0" },
{ SVM_EXIT_READ_CR3, "read_cr3" },
{ -1, NULL }
};
+static int svm_get_lpage_level(void)
+{
+ return PT_PDPE_LEVEL;
+}
+
+static bool svm_rdtscp_supported(void)
+{
+ return false;
+}
+
+static void svm_fpu_deactivate(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_svm *svm = to_svm(vcpu);
+
+ 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 = {
.cpu_has_kvm_support = has_svm,
.disabled_by_bios = is_disabled,
.set_segment = svm_set_segment,
.get_cpl = svm_get_cpl,
.get_cs_db_l_bits = kvm_get_cs_db_l_bits,
+ .decache_cr0_guest_bits = svm_decache_cr0_guest_bits,
.decache_cr4_guest_bits = svm_decache_cr4_guest_bits,
.set_cr0 = svm_set_cr0,
.set_cr3 = svm_set_cr3,
.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,
.queue_exception = svm_queue_exception,
.interrupt_allowed = svm_interrupt_allowed,
.nmi_allowed = svm_nmi_allowed,
+ .get_nmi_mask = svm_get_nmi_mask,
+ .set_nmi_mask = svm_set_nmi_mask,
.enable_nmi_window = enable_nmi_window,
.enable_irq_window = enable_irq_window,
.update_cr8_intercept = update_cr8_intercept,
.get_mt_mask = svm_get_mt_mask,
.exit_reasons_str = svm_exit_reasons_str,
+ .get_lpage_level = svm_get_lpage_level,
+
+ .cpuid_update = svm_cpuid_update,
+
+ .rdtscp_supported = svm_rdtscp_supported,
};
static int __init svm_init(void)