MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");
-static int __read_mostly bypass_guest_pf = 1;
-module_param(bypass_guest_pf, bool, S_IRUGO);
-
static int __read_mostly enable_vpid = 1;
module_param_named(vpid, enable_vpid, bool, 0444);
/* vmcs02_list cache of VMCSs recently used to run L2 guests */
struct list_head vmcs02_pool;
int vmcs02_num;
+ u64 vmcs01_tsc_offset;
+ /* L2 must run next, and mustn't decide to exit to L1. */
+ bool nested_run_pending;
+ /*
+ * Guest pages referred to in vmcs02 with host-physical pointers, so
+ * we must keep them pinned while L2 runs.
+ */
+ struct page *apic_access_page;
};
struct vcpu_vmx {
return flexpriority_enabled;
}
+static inline bool nested_cpu_has(struct vmcs12 *vmcs12, u32 bit)
+{
+ return vmcs12->cpu_based_vm_exec_control & bit;
+}
+
+static inline bool nested_cpu_has2(struct vmcs12 *vmcs12, u32 bit)
+{
+ return (vmcs12->cpu_based_vm_exec_control &
+ CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) &&
+ (vmcs12->secondary_vm_exec_control & bit);
+}
+
+static inline bool nested_cpu_has_virtual_nmis(struct vmcs12 *vmcs12,
+ struct kvm_vcpu *vcpu)
+{
+ return vmcs12->pin_based_vm_exec_control & PIN_BASED_VIRTUAL_NMIS;
+}
+
+static inline bool is_exception(u32 intr_info)
+{
+ return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
+ == (INTR_TYPE_HARD_EXCEPTION | INTR_INFO_VALID_MASK);
+}
+
+static void nested_vmx_vmexit(struct kvm_vcpu *vcpu);
+static void nested_vmx_entry_failure(struct kvm_vcpu *vcpu,
+ struct vmcs12 *vmcs12,
+ u32 reason, unsigned long qualification);
+
static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr)
{
int i;
: "=qm"(error) : "a"(&phys_addr), "m"(phys_addr)
: "cc", "memory");
if (error)
- printk(KERN_ERR "kvm: vmptrld %p/%llx fail\n",
+ printk(KERN_ERR "kvm: vmptrld %p/%llx failed\n",
vmcs, phys_addr);
}
eb &= ~(1u << PF_VECTOR); /* bypass_guest_pf = 0 */
if (vcpu->fpu_active)
eb &= ~(1u << NM_VECTOR);
+
+ /* When we are running a nested L2 guest and L1 specified for it a
+ * certain exception bitmap, we must trap the same exceptions and pass
+ * them to L1. When running L2, we will only handle the exceptions
+ * specified above if L1 did not want them.
+ */
+ if (is_guest_mode(vcpu))
+ eb |= get_vmcs12(vcpu)->exception_bitmap;
+
vmcs_write32(EXCEPTION_BITMAP, eb);
}
vmcs_writel(GUEST_CR0, cr0);
update_exception_bitmap(vcpu);
vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS;
+ if (is_guest_mode(vcpu))
+ vcpu->arch.cr0_guest_owned_bits &=
+ ~get_vmcs12(vcpu)->cr0_guest_host_mask;
vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits);
}
static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu);
+/*
+ * Return the cr0 value that a nested guest would read. This is a combination
+ * of the real cr0 used to run the guest (guest_cr0), and the bits shadowed by
+ * its hypervisor (cr0_read_shadow).
+ */
+static inline unsigned long nested_read_cr0(struct vmcs12 *fields)
+{
+ return (fields->guest_cr0 & ~fields->cr0_guest_host_mask) |
+ (fields->cr0_read_shadow & fields->cr0_guest_host_mask);
+}
+static inline unsigned long nested_read_cr4(struct vmcs12 *fields)
+{
+ return (fields->guest_cr4 & ~fields->cr4_guest_host_mask) |
+ (fields->cr4_read_shadow & fields->cr4_guest_host_mask);
+}
+
static void vmx_fpu_deactivate(struct kvm_vcpu *vcpu)
{
+ /* Note that there is no vcpu->fpu_active = 0 here. The caller must
+ * set this *before* calling this function.
+ */
vmx_decache_cr0_guest_bits(vcpu);
vmcs_set_bits(GUEST_CR0, X86_CR0_TS | X86_CR0_MP);
update_exception_bitmap(vcpu);
vcpu->arch.cr0_guest_owned_bits = 0;
vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits);
- vmcs_writel(CR0_READ_SHADOW, vcpu->arch.cr0);
+ if (is_guest_mode(vcpu)) {
+ /*
+ * L1's specified read shadow might not contain the TS bit,
+ * so now that we turned on shadowing of this bit, we need to
+ * set this bit of the shadow. Like in nested_vmx_run we need
+ * nested_read_cr0(vmcs12), but vmcs12->guest_cr0 is not yet
+ * up-to-date here because we just decached cr0.TS (and we'll
+ * only update vmcs12->guest_cr0 on nested exit).
+ */
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+ vmcs12->guest_cr0 = (vmcs12->guest_cr0 & ~X86_CR0_TS) |
+ (vcpu->arch.cr0 & X86_CR0_TS);
+ vmcs_writel(CR0_READ_SHADOW, nested_read_cr0(vmcs12));
+ } else
+ vmcs_writel(CR0_READ_SHADOW, vcpu->arch.cr0);
}
static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu)
vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE);
}
+/*
+ * KVM wants to inject page-faults which it got to the guest. This function
+ * checks whether in a nested guest, we need to inject them to L1 or L2.
+ * This function assumes it is called with the exit reason in vmcs02 being
+ * a #PF exception (this is the only case in which KVM injects a #PF when L2
+ * is running).
+ */
+static int nested_pf_handled(struct kvm_vcpu *vcpu)
+{
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+
+ /* TODO: also check PFEC_MATCH/MASK, not just EB.PF. */
+ if (!(vmcs12->exception_bitmap & PF_VECTOR))
+ return 0;
+
+ nested_vmx_vmexit(vcpu);
+ return 1;
+}
+
static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
bool has_error_code, u32 error_code,
bool reinject)
struct vcpu_vmx *vmx = to_vmx(vcpu);
u32 intr_info = nr | INTR_INFO_VALID_MASK;
+ if (nr == PF_VECTOR && is_guest_mode(vcpu) &&
+ nested_pf_handled(vcpu))
+ return;
+
if (has_error_code) {
vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code);
intr_info |= INTR_INFO_DELIVER_CODE_MASK;
static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
{
vmcs_write64(TSC_OFFSET, offset);
+ if (is_guest_mode(vcpu))
+ /*
+ * We're here if L1 chose not to trap the TSC MSR. Since
+ * prepare_vmcs12() does not copy tsc_offset, we need to also
+ * set the vmcs12 field here.
+ */
+ get_vmcs12(vcpu)->tsc_offset = offset -
+ to_vmx(vcpu)->nested.vmcs01_tsc_offset;
}
static void vmx_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment)
{
u64 offset = vmcs_read64(TSC_OFFSET);
vmcs_write64(TSC_OFFSET, offset + adjustment);
+ if (is_guest_mode(vcpu)) {
+ /* Even when running L2, the adjustment needs to apply to L1 */
+ to_vmx(vcpu)->nested.vmcs01_tsc_offset += adjustment;
+ }
}
static u64 vmx_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
/* exit controls */
nested_vmx_exit_ctls_low = 0;
+ /* Note that guest use of VM_EXIT_ACK_INTR_ON_EXIT is not supported. */
#ifdef CONFIG_X86_64
nested_vmx_exit_ctls_high = VM_EXIT_HOST_ADDR_SPACE_SIZE;
#else
vmx->vcpu.arch.cr4_guest_owned_bits = KVM_CR4_GUEST_OWNED_BITS;
if (enable_ept)
vmx->vcpu.arch.cr4_guest_owned_bits |= X86_CR4_PGE;
+ if (is_guest_mode(&vmx->vcpu))
+ vmx->vcpu.arch.cr4_guest_owned_bits &=
+ ~get_vmcs12(&vmx->vcpu)->cr4_guest_host_mask;
vmcs_writel(CR4_GUEST_HOST_MASK, ~vmx->vcpu.arch.cr4_guest_owned_bits);
}
return exec_control;
}
+static void ept_set_mmio_spte_mask(void)
+{
+ /*
+ * EPT Misconfigurations can be generated if the value of bits 2:0
+ * of an EPT paging-structure entry is 110b (write/execute).
+ * Also, magic bits (0xffull << 49) is set to quickly identify mmio
+ * spte.
+ */
+ kvm_mmu_set_mmio_spte_mask(0xffull << 49 | 0x6ull);
+}
+
/*
* Sets up the vmcs for emulated real mode.
*/
static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
{
+#ifdef CONFIG_X86_64
unsigned long a;
+#endif
int i;
/* I/O */
vmcs_write32(PLE_WINDOW, ple_window);
}
- vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, !!bypass_guest_pf);
- vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, !!bypass_guest_pf);
+ vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, 0);
+ vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, 0);
vmcs_write32(CR3_TARGET_COUNT, 0); /* 22.2.1 */
vmcs_write16(HOST_FS_SELECTOR, 0); /* 22.2.4 */
return ret;
}
+/*
+ * In nested virtualization, check if L1 asked to exit on external interrupts.
+ * For most existing hypervisors, this will always return true.
+ */
+static bool nested_exit_on_intr(struct kvm_vcpu *vcpu)
+{
+ return get_vmcs12(vcpu)->pin_based_vm_exec_control &
+ PIN_BASED_EXT_INTR_MASK;
+}
+
static void enable_irq_window(struct kvm_vcpu *vcpu)
{
u32 cpu_based_vm_exec_control;
+ if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu))
+ /* We can get here when nested_run_pending caused
+ * vmx_interrupt_allowed() to return false. In this case, do
+ * nothing - the interrupt will be injected later.
+ */
+ return;
cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_INTR_PENDING;
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
+ if (is_guest_mode(vcpu))
+ return;
+
if (!cpu_has_virtual_nmis()) {
/*
* Tracking the NMI-blocked state in software is built upon
static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu)
{
+ if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) {
+ struct vmcs12 *vmcs12;
+ if (to_vmx(vcpu)->nested.nested_run_pending)
+ return 0;
+ nested_vmx_vmexit(vcpu);
+ vmcs12 = get_vmcs12(vcpu);
+ vmcs12->vm_exit_reason = EXIT_REASON_EXTERNAL_INTERRUPT;
+ vmcs12->vm_exit_intr_info = 0;
+ /* fall through to normal code, but now in L1, not L2 */
+ }
+
return (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) &&
!(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
(GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS));
hypercall[2] = 0xc1;
}
+/* called to set cr0 as approriate for a mov-to-cr0 exit. */
+static int handle_set_cr0(struct kvm_vcpu *vcpu, unsigned long val)
+{
+ if (to_vmx(vcpu)->nested.vmxon &&
+ ((val & VMXON_CR0_ALWAYSON) != VMXON_CR0_ALWAYSON))
+ return 1;
+
+ if (is_guest_mode(vcpu)) {
+ /*
+ * We get here when L2 changed cr0 in a way that did not change
+ * any of L1's shadowed bits (see nested_vmx_exit_handled_cr),
+ * but did change L0 shadowed bits. This can currently happen
+ * with the TS bit: L0 may want to leave TS on (for lazy fpu
+ * loading) while pretending to allow the guest to change it.
+ */
+ if (kvm_set_cr0(vcpu, (val & vcpu->arch.cr0_guest_owned_bits) |
+ (vcpu->arch.cr0 & ~vcpu->arch.cr0_guest_owned_bits)))
+ return 1;
+ vmcs_writel(CR0_READ_SHADOW, val);
+ return 0;
+ } else
+ return kvm_set_cr0(vcpu, val);
+}
+
+static int handle_set_cr4(struct kvm_vcpu *vcpu, unsigned long val)
+{
+ if (is_guest_mode(vcpu)) {
+ if (kvm_set_cr4(vcpu, (val & vcpu->arch.cr4_guest_owned_bits) |
+ (vcpu->arch.cr4 & ~vcpu->arch.cr4_guest_owned_bits)))
+ return 1;
+ vmcs_writel(CR4_READ_SHADOW, val);
+ return 0;
+ } else
+ return kvm_set_cr4(vcpu, val);
+}
+
+/* called to set cr0 as approriate for clts instruction exit. */
+static void handle_clts(struct kvm_vcpu *vcpu)
+{
+ if (is_guest_mode(vcpu)) {
+ /*
+ * We get here when L2 did CLTS, and L1 didn't shadow CR0.TS
+ * but we did (!fpu_active). We need to keep GUEST_CR0.TS on,
+ * just pretend it's off (also in arch.cr0 for fpu_activate).
+ */
+ vmcs_writel(CR0_READ_SHADOW,
+ vmcs_readl(CR0_READ_SHADOW) & ~X86_CR0_TS);
+ vcpu->arch.cr0 &= ~X86_CR0_TS;
+ } else
+ vmx_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS));
+}
+
static int handle_cr(struct kvm_vcpu *vcpu)
{
unsigned long exit_qualification, val;
trace_kvm_cr_write(cr, val);
switch (cr) {
case 0:
- err = kvm_set_cr0(vcpu, val);
+ err = handle_set_cr0(vcpu, val);
kvm_complete_insn_gp(vcpu, err);
return 1;
case 3:
kvm_complete_insn_gp(vcpu, err);
return 1;
case 4:
- err = kvm_set_cr4(vcpu, val);
+ err = handle_set_cr4(vcpu, val);
kvm_complete_insn_gp(vcpu, err);
return 1;
case 8: {
};
break;
case 2: /* clts */
- vmx_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS));
+ handle_clts(vcpu);
trace_kvm_cr_write(0, kvm_read_cr0(vcpu));
skip_emulated_instruction(vcpu);
vmx_fpu_activate(vcpu);
return 1;
}
-static int handle_vmx_insn(struct kvm_vcpu *vcpu)
-{
- kvm_queue_exception(vcpu, UD_VECTOR);
- return 1;
-}
-
static int handle_invd(struct kvm_vcpu *vcpu)
{
return emulate_instruction(vcpu, 0) == EMULATE_DONE;
static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
{
u64 sptes[4];
- int nr_sptes, i;
+ int nr_sptes, i, ret;
gpa_t gpa;
gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
+ ret = handle_mmio_page_fault_common(vcpu, gpa, true);
+ if (likely(ret == 1))
+ return x86_emulate_instruction(vcpu, gpa, 0, NULL, 0) ==
+ EMULATE_DONE;
+ if (unlikely(!ret))
+ return 1;
+
+ /* It is the real ept misconfig */
printk(KERN_ERR "EPT: Misconfiguration.\n");
printk(KERN_ERR "EPT: GPA: 0x%llx\n", gpa);
vmx->nested.current_vmptr = -1ull;
vmx->nested.current_vmcs12 = NULL;
}
+ /* Unpin physical memory we referred to in current vmcs02 */
+ if (vmx->nested.apic_access_page) {
+ nested_release_page(vmx->nested.apic_access_page);
+ vmx->nested.apic_access_page = 0;
+ }
nested_free_all_saved_vmcss(vmx);
}
return 1;
}
+static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch);
+
+/* Emulate the VMLAUNCH instruction */
+static int handle_vmlaunch(struct kvm_vcpu *vcpu)
+{
+ return nested_vmx_run(vcpu, true);
+}
+
+/* Emulate the VMRESUME instruction */
+static int handle_vmresume(struct kvm_vcpu *vcpu)
+{
+
+ return nested_vmx_run(vcpu, false);
+}
+
enum vmcs_field_type {
VMCS_FIELD_TYPE_U16 = 0,
VMCS_FIELD_TYPE_U64 = 1,
[EXIT_REASON_INVLPG] = handle_invlpg,
[EXIT_REASON_VMCALL] = handle_vmcall,
[EXIT_REASON_VMCLEAR] = handle_vmclear,
- [EXIT_REASON_VMLAUNCH] = handle_vmx_insn,
+ [EXIT_REASON_VMLAUNCH] = handle_vmlaunch,
[EXIT_REASON_VMPTRLD] = handle_vmptrld,
[EXIT_REASON_VMPTRST] = handle_vmptrst,
[EXIT_REASON_VMREAD] = handle_vmread,
- [EXIT_REASON_VMRESUME] = handle_vmx_insn,
+ [EXIT_REASON_VMRESUME] = handle_vmresume,
[EXIT_REASON_VMWRITE] = handle_vmwrite,
[EXIT_REASON_VMOFF] = handle_vmoff,
[EXIT_REASON_VMON] = handle_vmon,
static const int kvm_vmx_max_exit_handlers =
ARRAY_SIZE(kvm_vmx_exit_handlers);
+/*
+ * Return 1 if we should exit from L2 to L1 to handle an MSR access access,
+ * rather than handle it ourselves in L0. I.e., check whether L1 expressed
+ * disinterest in the current event (read or write a specific MSR) by using an
+ * MSR bitmap. This may be the case even when L0 doesn't use MSR bitmaps.
+ */
+static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu,
+ struct vmcs12 *vmcs12, u32 exit_reason)
+{
+ u32 msr_index = vcpu->arch.regs[VCPU_REGS_RCX];
+ gpa_t bitmap;
+
+ if (!nested_cpu_has(get_vmcs12(vcpu), CPU_BASED_USE_MSR_BITMAPS))
+ return 1;
+
+ /*
+ * The MSR_BITMAP page is divided into four 1024-byte bitmaps,
+ * for the four combinations of read/write and low/high MSR numbers.
+ * First we need to figure out which of the four to use:
+ */
+ bitmap = vmcs12->msr_bitmap;
+ if (exit_reason == EXIT_REASON_MSR_WRITE)
+ bitmap += 2048;
+ if (msr_index >= 0xc0000000) {
+ msr_index -= 0xc0000000;
+ bitmap += 1024;
+ }
+
+ /* Then read the msr_index'th bit from this bitmap: */
+ if (msr_index < 1024*8) {
+ unsigned char b;
+ kvm_read_guest(vcpu->kvm, bitmap + msr_index/8, &b, 1);
+ return 1 & (b >> (msr_index & 7));
+ } else
+ return 1; /* let L1 handle the wrong parameter */
+}
+
+/*
+ * Return 1 if we should exit from L2 to L1 to handle a CR access exit,
+ * rather than handle it ourselves in L0. I.e., check if L1 wanted to
+ * intercept (via guest_host_mask etc.) the current event.
+ */
+static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu,
+ struct vmcs12 *vmcs12)
+{
+ unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+ int cr = exit_qualification & 15;
+ int reg = (exit_qualification >> 8) & 15;
+ unsigned long val = kvm_register_read(vcpu, reg);
+
+ switch ((exit_qualification >> 4) & 3) {
+ case 0: /* mov to cr */
+ switch (cr) {
+ case 0:
+ if (vmcs12->cr0_guest_host_mask &
+ (val ^ vmcs12->cr0_read_shadow))
+ return 1;
+ break;
+ case 3:
+ if ((vmcs12->cr3_target_count >= 1 &&
+ vmcs12->cr3_target_value0 == val) ||
+ (vmcs12->cr3_target_count >= 2 &&
+ vmcs12->cr3_target_value1 == val) ||
+ (vmcs12->cr3_target_count >= 3 &&
+ vmcs12->cr3_target_value2 == val) ||
+ (vmcs12->cr3_target_count >= 4 &&
+ vmcs12->cr3_target_value3 == val))
+ return 0;
+ if (nested_cpu_has(vmcs12, CPU_BASED_CR3_LOAD_EXITING))
+ return 1;
+ break;
+ case 4:
+ if (vmcs12->cr4_guest_host_mask &
+ (vmcs12->cr4_read_shadow ^ val))
+ return 1;
+ break;
+ case 8:
+ if (nested_cpu_has(vmcs12, CPU_BASED_CR8_LOAD_EXITING))
+ return 1;
+ break;
+ }
+ break;
+ case 2: /* clts */
+ if ((vmcs12->cr0_guest_host_mask & X86_CR0_TS) &&
+ (vmcs12->cr0_read_shadow & X86_CR0_TS))
+ return 1;
+ break;
+ case 1: /* mov from cr */
+ switch (cr) {
+ case 3:
+ if (vmcs12->cpu_based_vm_exec_control &
+ CPU_BASED_CR3_STORE_EXITING)
+ return 1;
+ break;
+ case 8:
+ if (vmcs12->cpu_based_vm_exec_control &
+ CPU_BASED_CR8_STORE_EXITING)
+ return 1;
+ break;
+ }
+ break;
+ case 3: /* lmsw */
+ /*
+ * lmsw can change bits 1..3 of cr0, and only set bit 0 of
+ * cr0. Other attempted changes are ignored, with no exit.
+ */
+ if (vmcs12->cr0_guest_host_mask & 0xe &
+ (val ^ vmcs12->cr0_read_shadow))
+ return 1;
+ if ((vmcs12->cr0_guest_host_mask & 0x1) &&
+ !(vmcs12->cr0_read_shadow & 0x1) &&
+ (val & 0x1))
+ return 1;
+ break;
+ }
+ return 0;
+}
+
+/*
+ * Return 1 if we should exit from L2 to L1 to handle an exit, or 0 if we
+ * should handle it ourselves in L0 (and then continue L2). Only call this
+ * when in is_guest_mode (L2).
+ */
+static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
+{
+ u32 exit_reason = vmcs_read32(VM_EXIT_REASON);
+ u32 intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+
+ if (vmx->nested.nested_run_pending)
+ return 0;
+
+ if (unlikely(vmx->fail)) {
+ printk(KERN_INFO "%s failed vm entry %x\n",
+ __func__, vmcs_read32(VM_INSTRUCTION_ERROR));
+ return 1;
+ }
+
+ switch (exit_reason) {
+ case EXIT_REASON_EXCEPTION_NMI:
+ if (!is_exception(intr_info))
+ return 0;
+ else if (is_page_fault(intr_info))
+ return enable_ept;
+ return vmcs12->exception_bitmap &
+ (1u << (intr_info & INTR_INFO_VECTOR_MASK));
+ case EXIT_REASON_EXTERNAL_INTERRUPT:
+ return 0;
+ case EXIT_REASON_TRIPLE_FAULT:
+ return 1;
+ case EXIT_REASON_PENDING_INTERRUPT:
+ case EXIT_REASON_NMI_WINDOW:
+ /*
+ * prepare_vmcs02() set the CPU_BASED_VIRTUAL_INTR_PENDING bit
+ * (aka Interrupt Window Exiting) only when L1 turned it on,
+ * so if we got a PENDING_INTERRUPT exit, this must be for L1.
+ * Same for NMI Window Exiting.
+ */
+ return 1;
+ case EXIT_REASON_TASK_SWITCH:
+ return 1;
+ case EXIT_REASON_CPUID:
+ return 1;
+ case EXIT_REASON_HLT:
+ return nested_cpu_has(vmcs12, CPU_BASED_HLT_EXITING);
+ case EXIT_REASON_INVD:
+ return 1;
+ case EXIT_REASON_INVLPG:
+ return nested_cpu_has(vmcs12, CPU_BASED_INVLPG_EXITING);
+ case EXIT_REASON_RDPMC:
+ return nested_cpu_has(vmcs12, CPU_BASED_RDPMC_EXITING);
+ case EXIT_REASON_RDTSC:
+ return nested_cpu_has(vmcs12, CPU_BASED_RDTSC_EXITING);
+ case EXIT_REASON_VMCALL: case EXIT_REASON_VMCLEAR:
+ case EXIT_REASON_VMLAUNCH: case EXIT_REASON_VMPTRLD:
+ case EXIT_REASON_VMPTRST: case EXIT_REASON_VMREAD:
+ case EXIT_REASON_VMRESUME: case EXIT_REASON_VMWRITE:
+ case EXIT_REASON_VMOFF: case EXIT_REASON_VMON:
+ /*
+ * VMX instructions trap unconditionally. This allows L1 to
+ * emulate them for its L2 guest, i.e., allows 3-level nesting!
+ */
+ return 1;
+ case EXIT_REASON_CR_ACCESS:
+ return nested_vmx_exit_handled_cr(vcpu, vmcs12);
+ case EXIT_REASON_DR_ACCESS:
+ return nested_cpu_has(vmcs12, CPU_BASED_MOV_DR_EXITING);
+ case EXIT_REASON_IO_INSTRUCTION:
+ /* TODO: support IO bitmaps */
+ return 1;
+ case EXIT_REASON_MSR_READ:
+ case EXIT_REASON_MSR_WRITE:
+ return nested_vmx_exit_handled_msr(vcpu, vmcs12, exit_reason);
+ case EXIT_REASON_INVALID_STATE:
+ return 1;
+ case EXIT_REASON_MWAIT_INSTRUCTION:
+ return nested_cpu_has(vmcs12, CPU_BASED_MWAIT_EXITING);
+ case EXIT_REASON_MONITOR_INSTRUCTION:
+ return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_EXITING);
+ case EXIT_REASON_PAUSE_INSTRUCTION:
+ return nested_cpu_has(vmcs12, CPU_BASED_PAUSE_EXITING) ||
+ nested_cpu_has2(vmcs12,
+ SECONDARY_EXEC_PAUSE_LOOP_EXITING);
+ case EXIT_REASON_MCE_DURING_VMENTRY:
+ return 0;
+ case EXIT_REASON_TPR_BELOW_THRESHOLD:
+ return 1;
+ case EXIT_REASON_APIC_ACCESS:
+ return nested_cpu_has2(vmcs12,
+ SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
+ case EXIT_REASON_EPT_VIOLATION:
+ case EXIT_REASON_EPT_MISCONFIG:
+ return 0;
+ case EXIT_REASON_WBINVD:
+ return nested_cpu_has2(vmcs12, SECONDARY_EXEC_WBINVD_EXITING);
+ case EXIT_REASON_XSETBV:
+ return 1;
+ default:
+ return 1;
+ }
+}
+
static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2)
{
*info1 = vmcs_readl(EXIT_QUALIFICATION);
if (vmx->emulation_required && emulate_invalid_guest_state)
return handle_invalid_guest_state(vcpu);
+ /*
+ * the KVM_REQ_EVENT optimization bit is only on for one entry, and if
+ * we did not inject a still-pending event to L1 now because of
+ * nested_run_pending, we need to re-enable this bit.
+ */
+ if (vmx->nested.nested_run_pending)
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+
+ if (!is_guest_mode(vcpu) && (exit_reason == EXIT_REASON_VMLAUNCH ||
+ exit_reason == EXIT_REASON_VMRESUME))
+ vmx->nested.nested_run_pending = 1;
+ else
+ vmx->nested.nested_run_pending = 0;
+
+ if (is_guest_mode(vcpu) && nested_vmx_exit_handled(vcpu)) {
+ nested_vmx_vmexit(vcpu);
+ return 1;
+ }
+
if (exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) {
vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY;
vcpu->run->fail_entry.hardware_entry_failure_reason
"(0x%x) and exit reason is 0x%x\n",
__func__, vectoring_info, exit_reason);
- if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked)) {
+ if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked &&
+ !(is_guest_mode(vcpu) && nested_cpu_has_virtual_nmis(
+ get_vmcs12(vcpu), vcpu)))) {
if (vmx_interrupt_allowed(vcpu)) {
vmx->soft_vnmi_blocked = 0;
} else if (vmx->vnmi_blocked_time > 1000000000LL &&
static void vmx_complete_interrupts(struct vcpu_vmx *vmx)
{
+ if (is_guest_mode(&vmx->vcpu))
+ return;
__vmx_complete_interrupts(vmx, vmx->idt_vectoring_info,
VM_EXIT_INSTRUCTION_LEN,
IDT_VECTORING_ERROR_CODE);
static void vmx_cancel_injection(struct kvm_vcpu *vcpu)
{
+ if (is_guest_mode(vcpu))
+ return;
__vmx_complete_interrupts(to_vmx(vcpu),
vmcs_read32(VM_ENTRY_INTR_INFO_FIELD),
VM_ENTRY_INSTRUCTION_LEN,
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
+ if (is_guest_mode(vcpu) && !vmx->nested.nested_run_pending) {
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+ if (vmcs12->idt_vectoring_info_field &
+ VECTORING_INFO_VALID_MASK) {
+ vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
+ vmcs12->idt_vectoring_info_field);
+ vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
+ vmcs12->vm_exit_instruction_len);
+ if (vmcs12->idt_vectoring_info_field &
+ VECTORING_INFO_DELIVER_CODE_MASK)
+ vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE,
+ vmcs12->idt_vectoring_error_code);
+ }
+ }
+
/* Record the guest's net vcpu time for enforced NMI injections. */
if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked))
vmx->entry_time = ktime_get();
vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
+ if (is_guest_mode(vcpu)) {
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+ vmcs12->idt_vectoring_info_field = vmx->idt_vectoring_info;
+ if (vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK) {
+ vmcs12->idt_vectoring_error_code =
+ vmcs_read32(IDT_VECTORING_ERROR_CODE);
+ vmcs12->vm_exit_instruction_len =
+ vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
+ }
+ }
+
asm("mov %0, %%ds; mov %0, %%es" : : "r"(__USER_DS));
vmx->loaded_vmcs->launched = 1;
static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
{
+ if (func == 1 && nested)
+ entry->ecx |= bit(X86_FEATURE_VMX);
+}
+
+/*
+ * prepare_vmcs02 is called when the L1 guest hypervisor runs its nested
+ * L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it
+ * with L0's requirements for its guest (a.k.a. vmsc01), so we can run the L2
+ * guest in a way that will both be appropriate to L1's requests, and our
+ * needs. In addition to modifying the active vmcs (which is vmcs02), this
+ * function also has additional necessary side-effects, like setting various
+ * vcpu->arch fields.
+ */
+static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ u32 exec_control;
+
+ vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector);
+ vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector);
+ vmcs_write16(GUEST_SS_SELECTOR, vmcs12->guest_ss_selector);
+ vmcs_write16(GUEST_DS_SELECTOR, vmcs12->guest_ds_selector);
+ vmcs_write16(GUEST_FS_SELECTOR, vmcs12->guest_fs_selector);
+ vmcs_write16(GUEST_GS_SELECTOR, vmcs12->guest_gs_selector);
+ vmcs_write16(GUEST_LDTR_SELECTOR, vmcs12->guest_ldtr_selector);
+ vmcs_write16(GUEST_TR_SELECTOR, vmcs12->guest_tr_selector);
+ vmcs_write32(GUEST_ES_LIMIT, vmcs12->guest_es_limit);
+ vmcs_write32(GUEST_CS_LIMIT, vmcs12->guest_cs_limit);
+ vmcs_write32(GUEST_SS_LIMIT, vmcs12->guest_ss_limit);
+ vmcs_write32(GUEST_DS_LIMIT, vmcs12->guest_ds_limit);
+ vmcs_write32(GUEST_FS_LIMIT, vmcs12->guest_fs_limit);
+ vmcs_write32(GUEST_GS_LIMIT, vmcs12->guest_gs_limit);
+ vmcs_write32(GUEST_LDTR_LIMIT, vmcs12->guest_ldtr_limit);
+ vmcs_write32(GUEST_TR_LIMIT, vmcs12->guest_tr_limit);
+ vmcs_write32(GUEST_GDTR_LIMIT, vmcs12->guest_gdtr_limit);
+ vmcs_write32(GUEST_IDTR_LIMIT, vmcs12->guest_idtr_limit);
+ vmcs_write32(GUEST_ES_AR_BYTES, vmcs12->guest_es_ar_bytes);
+ vmcs_write32(GUEST_CS_AR_BYTES, vmcs12->guest_cs_ar_bytes);
+ vmcs_write32(GUEST_SS_AR_BYTES, vmcs12->guest_ss_ar_bytes);
+ vmcs_write32(GUEST_DS_AR_BYTES, vmcs12->guest_ds_ar_bytes);
+ vmcs_write32(GUEST_FS_AR_BYTES, vmcs12->guest_fs_ar_bytes);
+ vmcs_write32(GUEST_GS_AR_BYTES, vmcs12->guest_gs_ar_bytes);
+ vmcs_write32(GUEST_LDTR_AR_BYTES, vmcs12->guest_ldtr_ar_bytes);
+ vmcs_write32(GUEST_TR_AR_BYTES, vmcs12->guest_tr_ar_bytes);
+ vmcs_writel(GUEST_ES_BASE, vmcs12->guest_es_base);
+ vmcs_writel(GUEST_CS_BASE, vmcs12->guest_cs_base);
+ vmcs_writel(GUEST_SS_BASE, vmcs12->guest_ss_base);
+ vmcs_writel(GUEST_DS_BASE, vmcs12->guest_ds_base);
+ vmcs_writel(GUEST_FS_BASE, vmcs12->guest_fs_base);
+ vmcs_writel(GUEST_GS_BASE, vmcs12->guest_gs_base);
+ vmcs_writel(GUEST_LDTR_BASE, vmcs12->guest_ldtr_base);
+ vmcs_writel(GUEST_TR_BASE, vmcs12->guest_tr_base);
+ vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base);
+ vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base);
+
+ vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl);
+ vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
+ vmcs12->vm_entry_intr_info_field);
+ vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE,
+ vmcs12->vm_entry_exception_error_code);
+ vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
+ vmcs12->vm_entry_instruction_len);
+ vmcs_write32(GUEST_INTERRUPTIBILITY_INFO,
+ vmcs12->guest_interruptibility_info);
+ vmcs_write32(GUEST_ACTIVITY_STATE, vmcs12->guest_activity_state);
+ vmcs_write32(GUEST_SYSENTER_CS, vmcs12->guest_sysenter_cs);
+ vmcs_writel(GUEST_DR7, vmcs12->guest_dr7);
+ vmcs_writel(GUEST_RFLAGS, vmcs12->guest_rflags);
+ vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS,
+ vmcs12->guest_pending_dbg_exceptions);
+ vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->guest_sysenter_esp);
+ vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->guest_sysenter_eip);
+
+ vmcs_write64(VMCS_LINK_POINTER, -1ull);
+
+ vmcs_write32(PIN_BASED_VM_EXEC_CONTROL,
+ (vmcs_config.pin_based_exec_ctrl |
+ vmcs12->pin_based_vm_exec_control));
+
+ /*
+ * Whether page-faults are trapped is determined by a combination of
+ * 3 settings: PFEC_MASK, PFEC_MATCH and EXCEPTION_BITMAP.PF.
+ * If enable_ept, L0 doesn't care about page faults and we should
+ * set all of these to L1's desires. However, if !enable_ept, L0 does
+ * care about (at least some) page faults, and because it is not easy
+ * (if at all possible?) to merge L0 and L1's desires, we simply ask
+ * to exit on each and every L2 page fault. This is done by setting
+ * MASK=MATCH=0 and (see below) EB.PF=1.
+ * Note that below we don't need special code to set EB.PF beyond the
+ * "or"ing of the EB of vmcs01 and vmcs12, because when enable_ept,
+ * vmcs01's EB.PF is 0 so the "or" will take vmcs12's value, and when
+ * !enable_ept, EB.PF is 1, so the "or" will always be 1.
+ *
+ * A problem with this approach (when !enable_ept) is that L1 may be
+ * injected with more page faults than it asked for. This could have
+ * caused problems, but in practice existing hypervisors don't care.
+ * To fix this, we will need to emulate the PFEC checking (on the L1
+ * page tables), using walk_addr(), when injecting PFs to L1.
+ */
+ vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK,
+ enable_ept ? vmcs12->page_fault_error_code_mask : 0);
+ vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH,
+ enable_ept ? vmcs12->page_fault_error_code_match : 0);
+
+ if (cpu_has_secondary_exec_ctrls()) {
+ u32 exec_control = vmx_secondary_exec_control(vmx);
+ if (!vmx->rdtscp_enabled)
+ exec_control &= ~SECONDARY_EXEC_RDTSCP;
+ /* Take the following fields only from vmcs12 */
+ exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+ if (nested_cpu_has(vmcs12,
+ CPU_BASED_ACTIVATE_SECONDARY_CONTROLS))
+ exec_control |= vmcs12->secondary_vm_exec_control;
+
+ if (exec_control & SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) {
+ /*
+ * Translate L1 physical address to host physical
+ * address for vmcs02. Keep the page pinned, so this
+ * physical address remains valid. We keep a reference
+ * to it so we can release it later.
+ */
+ if (vmx->nested.apic_access_page) /* shouldn't happen */
+ nested_release_page(vmx->nested.apic_access_page);
+ vmx->nested.apic_access_page =
+ nested_get_page(vcpu, vmcs12->apic_access_addr);
+ /*
+ * If translation failed, no matter: This feature asks
+ * to exit when accessing the given address, and if it
+ * can never be accessed, this feature won't do
+ * anything anyway.
+ */
+ if (!vmx->nested.apic_access_page)
+ exec_control &=
+ ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+ else
+ vmcs_write64(APIC_ACCESS_ADDR,
+ page_to_phys(vmx->nested.apic_access_page));
+ }
+
+ vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
+ }
+
+
+ /*
+ * Set host-state according to L0's settings (vmcs12 is irrelevant here)
+ * Some constant fields are set here by vmx_set_constant_host_state().
+ * Other fields are different per CPU, and will be set later when
+ * vmx_vcpu_load() is called, and when vmx_save_host_state() is called.
+ */
+ vmx_set_constant_host_state();
+
+ /*
+ * HOST_RSP is normally set correctly in vmx_vcpu_run() just before
+ * entry, but only if the current (host) sp changed from the value
+ * we wrote last (vmx->host_rsp). This cache is no longer relevant
+ * if we switch vmcs, and rather than hold a separate cache per vmcs,
+ * here we just force the write to happen on entry.
+ */
+ vmx->host_rsp = 0;
+
+ exec_control = vmx_exec_control(vmx); /* L0's desires */
+ exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING;
+ exec_control &= ~CPU_BASED_VIRTUAL_NMI_PENDING;
+ exec_control &= ~CPU_BASED_TPR_SHADOW;
+ exec_control |= vmcs12->cpu_based_vm_exec_control;
+ /*
+ * Merging of IO and MSR bitmaps not currently supported.
+ * Rather, exit every time.
+ */
+ exec_control &= ~CPU_BASED_USE_MSR_BITMAPS;
+ exec_control &= ~CPU_BASED_USE_IO_BITMAPS;
+ exec_control |= CPU_BASED_UNCOND_IO_EXITING;
+
+ vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, exec_control);
+
+ /* EXCEPTION_BITMAP and CR0_GUEST_HOST_MASK should basically be the
+ * bitwise-or of what L1 wants to trap for L2, and what we want to
+ * trap. Note that CR0.TS also needs updating - we do this later.
+ */
+ update_exception_bitmap(vcpu);
+ vcpu->arch.cr0_guest_owned_bits &= ~vmcs12->cr0_guest_host_mask;
+ vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits);
+
+ /* Note: IA32_MODE, LOAD_IA32_EFER are modified by vmx_set_efer below */
+ vmcs_write32(VM_EXIT_CONTROLS,
+ vmcs12->vm_exit_controls | vmcs_config.vmexit_ctrl);
+ vmcs_write32(VM_ENTRY_CONTROLS, vmcs12->vm_entry_controls |
+ (vmcs_config.vmentry_ctrl & ~VM_ENTRY_IA32E_MODE));
+
+ if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT)
+ vmcs_write64(GUEST_IA32_PAT, vmcs12->guest_ia32_pat);
+ else if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT)
+ vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
+
+
+ set_cr4_guest_host_mask(vmx);
+
+ vmcs_write64(TSC_OFFSET,
+ vmx->nested.vmcs01_tsc_offset + vmcs12->tsc_offset);
+
+ if (enable_vpid) {
+ /*
+ * Trivially support vpid by letting L2s share their parent
+ * L1's vpid. TODO: move to a more elaborate solution, giving
+ * each L2 its own vpid and exposing the vpid feature to L1.
+ */
+ vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
+ vmx_flush_tlb(vcpu);
+ }
+
+ if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)
+ vcpu->arch.efer = vmcs12->guest_ia32_efer;
+ if (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE)
+ vcpu->arch.efer |= (EFER_LMA | EFER_LME);
+ else
+ vcpu->arch.efer &= ~(EFER_LMA | EFER_LME);
+ /* Note: modifies VM_ENTRY/EXIT_CONTROLS and GUEST/HOST_IA32_EFER */
+ vmx_set_efer(vcpu, vcpu->arch.efer);
+
+ /*
+ * This sets GUEST_CR0 to vmcs12->guest_cr0, with possibly a modified
+ * TS bit (for lazy fpu) and bits which we consider mandatory enabled.
+ * The CR0_READ_SHADOW is what L2 should have expected to read given
+ * the specifications by L1; It's not enough to take
+ * vmcs12->cr0_read_shadow because on our cr0_guest_host_mask we we
+ * have more bits than L1 expected.
+ */
+ vmx_set_cr0(vcpu, vmcs12->guest_cr0);
+ vmcs_writel(CR0_READ_SHADOW, nested_read_cr0(vmcs12));
+
+ vmx_set_cr4(vcpu, vmcs12->guest_cr4);
+ vmcs_writel(CR4_READ_SHADOW, nested_read_cr4(vmcs12));
+
+ /* shadow page tables on either EPT or shadow page tables */
+ kvm_set_cr3(vcpu, vmcs12->guest_cr3);
+ kvm_mmu_reset_context(vcpu);
+
+ kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->guest_rsp);
+ kvm_register_write(vcpu, VCPU_REGS_RIP, vmcs12->guest_rip);
+}
+
+/*
+ * nested_vmx_run() handles a nested entry, i.e., a VMLAUNCH or VMRESUME on L1
+ * for running an L2 nested guest.
+ */
+static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
+{
+ struct vmcs12 *vmcs12;
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ int cpu;
+ struct loaded_vmcs *vmcs02;
+
+ if (!nested_vmx_check_permission(vcpu) ||
+ !nested_vmx_check_vmcs12(vcpu))
+ return 1;
+
+ skip_emulated_instruction(vcpu);
+ vmcs12 = get_vmcs12(vcpu);
+
+ /*
+ * The nested entry process starts with enforcing various prerequisites
+ * on vmcs12 as required by the Intel SDM, and act appropriately when
+ * they fail: As the SDM explains, some conditions should cause the
+ * instruction to fail, while others will cause the instruction to seem
+ * to succeed, but return an EXIT_REASON_INVALID_STATE.
+ * To speed up the normal (success) code path, we should avoid checking
+ * for misconfigurations which will anyway be caught by the processor
+ * when using the merged vmcs02.
+ */
+ if (vmcs12->launch_state == launch) {
+ nested_vmx_failValid(vcpu,
+ launch ? VMXERR_VMLAUNCH_NONCLEAR_VMCS
+ : VMXERR_VMRESUME_NONLAUNCHED_VMCS);
+ return 1;
+ }
+
+ if ((vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_MSR_BITMAPS) &&
+ !IS_ALIGNED(vmcs12->msr_bitmap, PAGE_SIZE)) {
+ /*TODO: Also verify bits beyond physical address width are 0*/
+ nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
+ return 1;
+ }
+
+ if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) &&
+ !IS_ALIGNED(vmcs12->apic_access_addr, PAGE_SIZE)) {
+ /*TODO: Also verify bits beyond physical address width are 0*/
+ nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
+ return 1;
+ }
+
+ if (vmcs12->vm_entry_msr_load_count > 0 ||
+ vmcs12->vm_exit_msr_load_count > 0 ||
+ vmcs12->vm_exit_msr_store_count > 0) {
+ if (printk_ratelimit())
+ printk(KERN_WARNING
+ "%s: VMCS MSR_{LOAD,STORE} unsupported\n", __func__);
+ nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
+ return 1;
+ }
+
+ if (!vmx_control_verify(vmcs12->cpu_based_vm_exec_control,
+ nested_vmx_procbased_ctls_low, nested_vmx_procbased_ctls_high) ||
+ !vmx_control_verify(vmcs12->secondary_vm_exec_control,
+ nested_vmx_secondary_ctls_low, nested_vmx_secondary_ctls_high) ||
+ !vmx_control_verify(vmcs12->pin_based_vm_exec_control,
+ nested_vmx_pinbased_ctls_low, nested_vmx_pinbased_ctls_high) ||
+ !vmx_control_verify(vmcs12->vm_exit_controls,
+ nested_vmx_exit_ctls_low, nested_vmx_exit_ctls_high) ||
+ !vmx_control_verify(vmcs12->vm_entry_controls,
+ nested_vmx_entry_ctls_low, nested_vmx_entry_ctls_high))
+ {
+ nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
+ return 1;
+ }
+
+ if (((vmcs12->host_cr0 & VMXON_CR0_ALWAYSON) != VMXON_CR0_ALWAYSON) ||
+ ((vmcs12->host_cr4 & VMXON_CR4_ALWAYSON) != VMXON_CR4_ALWAYSON)) {
+ nested_vmx_failValid(vcpu,
+ VMXERR_ENTRY_INVALID_HOST_STATE_FIELD);
+ return 1;
+ }
+
+ if (((vmcs12->guest_cr0 & VMXON_CR0_ALWAYSON) != VMXON_CR0_ALWAYSON) ||
+ ((vmcs12->guest_cr4 & VMXON_CR4_ALWAYSON) != VMXON_CR4_ALWAYSON)) {
+ nested_vmx_entry_failure(vcpu, vmcs12,
+ EXIT_REASON_INVALID_STATE, ENTRY_FAIL_DEFAULT);
+ return 1;
+ }
+ if (vmcs12->vmcs_link_pointer != -1ull) {
+ nested_vmx_entry_failure(vcpu, vmcs12,
+ EXIT_REASON_INVALID_STATE, ENTRY_FAIL_VMCS_LINK_PTR);
+ return 1;
+ }
+
+ /*
+ * We're finally done with prerequisite checking, and can start with
+ * the nested entry.
+ */
+
+ vmcs02 = nested_get_current_vmcs02(vmx);
+ if (!vmcs02)
+ return -ENOMEM;
+
+ enter_guest_mode(vcpu);
+
+ vmx->nested.vmcs01_tsc_offset = vmcs_read64(TSC_OFFSET);
+
+ cpu = get_cpu();
+ vmx->loaded_vmcs = vmcs02;
+ vmx_vcpu_put(vcpu);
+ vmx_vcpu_load(vcpu, cpu);
+ vcpu->cpu = cpu;
+ put_cpu();
+
+ vmcs12->launch_state = 1;
+
+ prepare_vmcs02(vcpu, vmcs12);
+
+ /*
+ * Note no nested_vmx_succeed or nested_vmx_fail here. At this point
+ * we are no longer running L1, and VMLAUNCH/VMRESUME has not yet
+ * returned as far as L1 is concerned. It will only return (and set
+ * the success flag) when L2 exits (see nested_vmx_vmexit()).
+ */
+ return 1;
+}
+
+/*
+ * On a nested exit from L2 to L1, vmcs12.guest_cr0 might not be up-to-date
+ * because L2 may have changed some cr0 bits directly (CRO_GUEST_HOST_MASK).
+ * This function returns the new value we should put in vmcs12.guest_cr0.
+ * It's not enough to just return the vmcs02 GUEST_CR0. Rather,
+ * 1. Bits that neither L0 nor L1 trapped, were set directly by L2 and are now
+ * available in vmcs02 GUEST_CR0. (Note: It's enough to check that L0
+ * didn't trap the bit, because if L1 did, so would L0).
+ * 2. Bits that L1 asked to trap (and therefore L0 also did) could not have
+ * been modified by L2, and L1 knows it. So just leave the old value of
+ * the bit from vmcs12.guest_cr0. Note that the bit from vmcs02 GUEST_CR0
+ * isn't relevant, because if L0 traps this bit it can set it to anything.
+ * 3. Bits that L1 didn't trap, but L0 did. L1 believes the guest could have
+ * changed these bits, and therefore they need to be updated, but L0
+ * didn't necessarily allow them to be changed in GUEST_CR0 - and rather
+ * put them in vmcs02 CR0_READ_SHADOW. So take these bits from there.
+ */
+static inline unsigned long
+vmcs12_guest_cr0(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
+{
+ return
+ /*1*/ (vmcs_readl(GUEST_CR0) & vcpu->arch.cr0_guest_owned_bits) |
+ /*2*/ (vmcs12->guest_cr0 & vmcs12->cr0_guest_host_mask) |
+ /*3*/ (vmcs_readl(CR0_READ_SHADOW) & ~(vmcs12->cr0_guest_host_mask |
+ vcpu->arch.cr0_guest_owned_bits));
+}
+
+static inline unsigned long
+vmcs12_guest_cr4(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
+{
+ return
+ /*1*/ (vmcs_readl(GUEST_CR4) & vcpu->arch.cr4_guest_owned_bits) |
+ /*2*/ (vmcs12->guest_cr4 & vmcs12->cr4_guest_host_mask) |
+ /*3*/ (vmcs_readl(CR4_READ_SHADOW) & ~(vmcs12->cr4_guest_host_mask |
+ vcpu->arch.cr4_guest_owned_bits));
+}
+
+/*
+ * prepare_vmcs12 is part of what we need to do when the nested L2 guest exits
+ * and we want to prepare to run its L1 parent. L1 keeps a vmcs for L2 (vmcs12),
+ * and this function updates it to reflect the changes to the guest state while
+ * L2 was running (and perhaps made some exits which were handled directly by L0
+ * without going back to L1), and to reflect the exit reason.
+ * Note that we do not have to copy here all VMCS fields, just those that
+ * could have changed by the L2 guest or the exit - i.e., the guest-state and
+ * exit-information fields only. Other fields are modified by L1 with VMWRITE,
+ * which already writes to vmcs12 directly.
+ */
+void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
+{
+ /* update guest state fields: */
+ vmcs12->guest_cr0 = vmcs12_guest_cr0(vcpu, vmcs12);
+ vmcs12->guest_cr4 = vmcs12_guest_cr4(vcpu, vmcs12);
+
+ kvm_get_dr(vcpu, 7, (unsigned long *)&vmcs12->guest_dr7);
+ vmcs12->guest_rsp = kvm_register_read(vcpu, VCPU_REGS_RSP);
+ vmcs12->guest_rip = kvm_register_read(vcpu, VCPU_REGS_RIP);
+ vmcs12->guest_rflags = vmcs_readl(GUEST_RFLAGS);
+
+ vmcs12->guest_es_selector = vmcs_read16(GUEST_ES_SELECTOR);
+ vmcs12->guest_cs_selector = vmcs_read16(GUEST_CS_SELECTOR);
+ vmcs12->guest_ss_selector = vmcs_read16(GUEST_SS_SELECTOR);
+ vmcs12->guest_ds_selector = vmcs_read16(GUEST_DS_SELECTOR);
+ vmcs12->guest_fs_selector = vmcs_read16(GUEST_FS_SELECTOR);
+ vmcs12->guest_gs_selector = vmcs_read16(GUEST_GS_SELECTOR);
+ vmcs12->guest_ldtr_selector = vmcs_read16(GUEST_LDTR_SELECTOR);
+ vmcs12->guest_tr_selector = vmcs_read16(GUEST_TR_SELECTOR);
+ vmcs12->guest_es_limit = vmcs_read32(GUEST_ES_LIMIT);
+ vmcs12->guest_cs_limit = vmcs_read32(GUEST_CS_LIMIT);
+ vmcs12->guest_ss_limit = vmcs_read32(GUEST_SS_LIMIT);
+ vmcs12->guest_ds_limit = vmcs_read32(GUEST_DS_LIMIT);
+ vmcs12->guest_fs_limit = vmcs_read32(GUEST_FS_LIMIT);
+ vmcs12->guest_gs_limit = vmcs_read32(GUEST_GS_LIMIT);
+ vmcs12->guest_ldtr_limit = vmcs_read32(GUEST_LDTR_LIMIT);
+ vmcs12->guest_tr_limit = vmcs_read32(GUEST_TR_LIMIT);
+ vmcs12->guest_gdtr_limit = vmcs_read32(GUEST_GDTR_LIMIT);
+ vmcs12->guest_idtr_limit = vmcs_read32(GUEST_IDTR_LIMIT);
+ vmcs12->guest_es_ar_bytes = vmcs_read32(GUEST_ES_AR_BYTES);
+ vmcs12->guest_cs_ar_bytes = vmcs_read32(GUEST_CS_AR_BYTES);
+ vmcs12->guest_ss_ar_bytes = vmcs_read32(GUEST_SS_AR_BYTES);
+ vmcs12->guest_ds_ar_bytes = vmcs_read32(GUEST_DS_AR_BYTES);
+ vmcs12->guest_fs_ar_bytes = vmcs_read32(GUEST_FS_AR_BYTES);
+ vmcs12->guest_gs_ar_bytes = vmcs_read32(GUEST_GS_AR_BYTES);
+ vmcs12->guest_ldtr_ar_bytes = vmcs_read32(GUEST_LDTR_AR_BYTES);
+ vmcs12->guest_tr_ar_bytes = vmcs_read32(GUEST_TR_AR_BYTES);
+ vmcs12->guest_es_base = vmcs_readl(GUEST_ES_BASE);
+ vmcs12->guest_cs_base = vmcs_readl(GUEST_CS_BASE);
+ vmcs12->guest_ss_base = vmcs_readl(GUEST_SS_BASE);
+ vmcs12->guest_ds_base = vmcs_readl(GUEST_DS_BASE);
+ vmcs12->guest_fs_base = vmcs_readl(GUEST_FS_BASE);
+ vmcs12->guest_gs_base = vmcs_readl(GUEST_GS_BASE);
+ vmcs12->guest_ldtr_base = vmcs_readl(GUEST_LDTR_BASE);
+ vmcs12->guest_tr_base = vmcs_readl(GUEST_TR_BASE);
+ vmcs12->guest_gdtr_base = vmcs_readl(GUEST_GDTR_BASE);
+ vmcs12->guest_idtr_base = vmcs_readl(GUEST_IDTR_BASE);
+
+ vmcs12->guest_activity_state = vmcs_read32(GUEST_ACTIVITY_STATE);
+ vmcs12->guest_interruptibility_info =
+ vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
+ vmcs12->guest_pending_dbg_exceptions =
+ vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS);
+
+ /* TODO: These cannot have changed unless we have MSR bitmaps and
+ * the relevant bit asks not to trap the change */
+ vmcs12->guest_ia32_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
+ if (vmcs12->vm_entry_controls & VM_EXIT_SAVE_IA32_PAT)
+ vmcs12->guest_ia32_pat = vmcs_read64(GUEST_IA32_PAT);
+ vmcs12->guest_sysenter_cs = vmcs_read32(GUEST_SYSENTER_CS);
+ vmcs12->guest_sysenter_esp = vmcs_readl(GUEST_SYSENTER_ESP);
+ vmcs12->guest_sysenter_eip = vmcs_readl(GUEST_SYSENTER_EIP);
+
+ /* update exit information fields: */
+
+ vmcs12->vm_exit_reason = vmcs_read32(VM_EXIT_REASON);
+ vmcs12->exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+
+ vmcs12->vm_exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
+ vmcs12->vm_exit_intr_error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
+ vmcs12->idt_vectoring_info_field =
+ vmcs_read32(IDT_VECTORING_INFO_FIELD);
+ vmcs12->idt_vectoring_error_code =
+ vmcs_read32(IDT_VECTORING_ERROR_CODE);
+ vmcs12->vm_exit_instruction_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
+ vmcs12->vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
+
+ /* clear vm-entry fields which are to be cleared on exit */
+ if (!(vmcs12->vm_exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY))
+ vmcs12->vm_entry_intr_info_field &= ~INTR_INFO_VALID_MASK;
+}
+
+/*
+ * A part of what we need to when the nested L2 guest exits and we want to
+ * run its L1 parent, is to reset L1's guest state to the host state specified
+ * in vmcs12.
+ * This function is to be called not only on normal nested exit, but also on
+ * a nested entry failure, as explained in Intel's spec, 3B.23.7 ("VM-Entry
+ * Failures During or After Loading Guest State").
+ * This function should be called when the active VMCS is L1's (vmcs01).
+ */
+void load_vmcs12_host_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
+{
+ if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER)
+ vcpu->arch.efer = vmcs12->host_ia32_efer;
+ if (vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE)
+ vcpu->arch.efer |= (EFER_LMA | EFER_LME);
+ else
+ vcpu->arch.efer &= ~(EFER_LMA | EFER_LME);
+ vmx_set_efer(vcpu, vcpu->arch.efer);
+
+ kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->host_rsp);
+ kvm_register_write(vcpu, VCPU_REGS_RIP, vmcs12->host_rip);
+ /*
+ * Note that calling vmx_set_cr0 is important, even if cr0 hasn't
+ * actually changed, because it depends on the current state of
+ * fpu_active (which may have changed).
+ * Note that vmx_set_cr0 refers to efer set above.
+ */
+ kvm_set_cr0(vcpu, vmcs12->host_cr0);
+ /*
+ * If we did fpu_activate()/fpu_deactivate() during L2's run, we need
+ * to apply the same changes to L1's vmcs. We just set cr0 correctly,
+ * but we also need to update cr0_guest_host_mask and exception_bitmap.
+ */
+ update_exception_bitmap(vcpu);
+ vcpu->arch.cr0_guest_owned_bits = (vcpu->fpu_active ? X86_CR0_TS : 0);
+ vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits);
+
+ /*
+ * Note that CR4_GUEST_HOST_MASK is already set in the original vmcs01
+ * (KVM doesn't change it)- no reason to call set_cr4_guest_host_mask();
+ */
+ vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
+ kvm_set_cr4(vcpu, vmcs12->host_cr4);
+
+ /* shadow page tables on either EPT or shadow page tables */
+ kvm_set_cr3(vcpu, vmcs12->host_cr3);
+ kvm_mmu_reset_context(vcpu);
+
+ if (enable_vpid) {
+ /*
+ * Trivially support vpid by letting L2s share their parent
+ * L1's vpid. TODO: move to a more elaborate solution, giving
+ * each L2 its own vpid and exposing the vpid feature to L1.
+ */
+ vmx_flush_tlb(vcpu);
+ }
+
+
+ vmcs_write32(GUEST_SYSENTER_CS, vmcs12->host_ia32_sysenter_cs);
+ vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->host_ia32_sysenter_esp);
+ vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->host_ia32_sysenter_eip);
+ vmcs_writel(GUEST_IDTR_BASE, vmcs12->host_idtr_base);
+ vmcs_writel(GUEST_GDTR_BASE, vmcs12->host_gdtr_base);
+ vmcs_writel(GUEST_TR_BASE, vmcs12->host_tr_base);
+ vmcs_writel(GUEST_GS_BASE, vmcs12->host_gs_base);
+ vmcs_writel(GUEST_FS_BASE, vmcs12->host_fs_base);
+ vmcs_write16(GUEST_ES_SELECTOR, vmcs12->host_es_selector);
+ vmcs_write16(GUEST_CS_SELECTOR, vmcs12->host_cs_selector);
+ vmcs_write16(GUEST_SS_SELECTOR, vmcs12->host_ss_selector);
+ vmcs_write16(GUEST_DS_SELECTOR, vmcs12->host_ds_selector);
+ vmcs_write16(GUEST_FS_SELECTOR, vmcs12->host_fs_selector);
+ vmcs_write16(GUEST_GS_SELECTOR, vmcs12->host_gs_selector);
+ vmcs_write16(GUEST_TR_SELECTOR, vmcs12->host_tr_selector);
+
+ if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT)
+ vmcs_write64(GUEST_IA32_PAT, vmcs12->host_ia32_pat);
+ if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
+ vmcs_write64(GUEST_IA32_PERF_GLOBAL_CTRL,
+ vmcs12->host_ia32_perf_global_ctrl);
+}
+
+/*
+ * Emulate an exit from nested guest (L2) to L1, i.e., prepare to run L1
+ * and modify vmcs12 to make it see what it would expect to see there if
+ * L2 was its real guest. Must only be called when in L2 (is_guest_mode())
+ */
+static void nested_vmx_vmexit(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ int cpu;
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+
+ leave_guest_mode(vcpu);
+ prepare_vmcs12(vcpu, vmcs12);
+
+ cpu = get_cpu();
+ vmx->loaded_vmcs = &vmx->vmcs01;
+ vmx_vcpu_put(vcpu);
+ vmx_vcpu_load(vcpu, cpu);
+ vcpu->cpu = cpu;
+ put_cpu();
+
+ /* if no vmcs02 cache requested, remove the one we used */
+ if (VMCS02_POOL_SIZE == 0)
+ nested_free_vmcs02(vmx, vmx->nested.current_vmptr);
+
+ load_vmcs12_host_state(vcpu, vmcs12);
+
+ /* Update TSC_OFFSET if vmx_adjust_tsc_offset() was used while L2 ran */
+ vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset);
+
+ /* This is needed for same reason as it was needed in prepare_vmcs02 */
+ vmx->host_rsp = 0;
+
+ /* Unpin physical memory we referred to in vmcs02 */
+ if (vmx->nested.apic_access_page) {
+ nested_release_page(vmx->nested.apic_access_page);
+ vmx->nested.apic_access_page = 0;
+ }
+
+ /*
+ * Exiting from L2 to L1, we're now back to L1 which thinks it just
+ * finished a VMLAUNCH or VMRESUME instruction, so we need to set the
+ * success or failure flag accordingly.
+ */
+ if (unlikely(vmx->fail)) {
+ vmx->fail = 0;
+ nested_vmx_failValid(vcpu, vmcs_read32(VM_INSTRUCTION_ERROR));
+ } else
+ nested_vmx_succeed(vcpu);
+}
+
+/*
+ * L1's failure to enter L2 is a subset of a normal exit, as explained in
+ * 23.7 "VM-entry failures during or after loading guest state" (this also
+ * lists the acceptable exit-reason and exit-qualification parameters).
+ * It should only be called before L2 actually succeeded to run, and when
+ * vmcs01 is current (it doesn't leave_guest_mode() or switch vmcss).
+ */
+static void nested_vmx_entry_failure(struct kvm_vcpu *vcpu,
+ struct vmcs12 *vmcs12,
+ u32 reason, unsigned long qualification)
+{
+ load_vmcs12_host_state(vcpu, vmcs12);
+ vmcs12->vm_exit_reason = reason | VMX_EXIT_REASONS_FAILED_VMENTRY;
+ vmcs12->exit_qualification = qualification;
+ nested_vmx_succeed(vcpu);
}
static int vmx_check_intercept(struct kvm_vcpu *vcpu,
vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false);
if (enable_ept) {
- bypass_guest_pf = 0;
kvm_mmu_set_mask_ptes(0ull, 0ull, 0ull, 0ull,
VMX_EPT_EXECUTABLE_MASK);
+ ept_set_mmio_spte_mask();
kvm_enable_tdp();
} else
kvm_disable_tdp();
- if (bypass_guest_pf)
- kvm_mmu_set_nonpresent_ptes(~0xffeull, 0ull);
-
return 0;
out3: