Re: [PATCH 5/5] Nested VMX patch 5 implements vmlaunch and vmresume

[Gleb Natapov <gleb@redhat.com>]

On Thu, Oct 15, 2009 at 04:41:46PM +0200, oritw@il.ibm.com wrote:
> From: Orit Wasserman <oritw@il.ibm.com>
> 
> ---
>  arch/x86/kvm/vmx.c | 1173 ++++++++++++++++++++++++++++++++++++++++++++++++++--
>  1 files changed, 1148 insertions(+), 25 deletions(-)
> 
> diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
> index 6a4c252..e814029 100644
> --- a/arch/x86/kvm/vmx.c
> +++ b/arch/x86/kvm/vmx.c
> @@ -209,6 +209,7 @@ struct __attribute__ ((__packed__)) level_state {
>  	struct vmcs *vmcs;
>  	int cpu;
>  	int launched;
> +	bool first_launch;
>  };
>  
>  struct nested_vmx {
> @@ -216,6 +217,12 @@ struct nested_vmx {
>  	bool vmxon;
>  	/* What is the location of the  vmcs l1 keeps for l2? (in level1 gpa) */
>  	u64 vmptr;
> +	/* Are we running nested guest */
> +	bool nested_mode;
> +	/* L1 requested VMLAUNCH or VMRESUME but we didn't run L2 yet */
> +	bool nested_run_pending;
> +	/* flag indicating if there was a valid IDT after exiting from l2 */
> +	bool nested_valid_idt;
>  	/*
>  	 * Level 2 state : includes vmcs,registers and
>  	 * a copy of vmcs12 for vmread/vmwrite
> @@ -240,6 +247,10 @@ static inline int vmcs_field_length(unsigned long field)
>  	return (VMCS_FIELD_LENGTH_MASK & field) >> 13;
>  }
>  
> +#define NESTED_VM_EXIT_CONTROLS_MASK (~(VM_EXIT_LOAD_IA32_PAT | \
> +					VM_EXIT_SAVE_IA32_PAT))
> +#define NESTED_VM_ENTRY_CONTROLS_MASK (~(VM_ENTRY_LOAD_IA32_PAT | \
> +					 VM_ENTRY_IA32E_MODE))
>  struct vmcs {
>  	u32 revision_id;
>  	u32 abort;
> @@ -303,6 +314,12 @@ static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
>  	return container_of(vcpu, struct vcpu_vmx, vcpu);
>  }
>  
> +static inline struct shadow_vmcs *get_shadow_vmcs(struct kvm_vcpu *vcpu)
> +{
> +	WARN_ON(!to_vmx(vcpu)->nested.l2_state->shadow_vmcs);
> +	return to_vmx(vcpu)->nested.l2_state->shadow_vmcs;
> +}
> +
>  #define SHADOW_VMCS_OFFSET(x) offsetof(struct shadow_vmcs, x)
>  
>  static unsigned short vmcs_field_to_offset_table[HOST_RIP+1] = {
> @@ -822,8 +839,16 @@ static struct kvm_vmx_segment_field {
>  static void ept_save_pdptrs(struct kvm_vcpu *vcpu);
>  
>  static int nested_vmx_check_permission(struct kvm_vcpu *vcpu);
> +static int nested_vmx_check_exception(struct vcpu_vmx *vmx, unsigned nr,
> +				      bool has_error_code, u32 error_code);
> +static int nested_vmx_intr(struct kvm_vcpu *vcpu);
>  static int create_l1_state(struct kvm_vcpu *vcpu);
>  static int create_l2_state(struct kvm_vcpu *vcpu);
> +static int launch_guest(struct kvm_vcpu *vcpu);
> +static int nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu);
> +static int nested_vmx_exit_handled(struct kvm_vcpu *vcpu, bool kvm_override);
> +static int nested_vmx_vmexit(struct kvm_vcpu *vcpu,
> +			     bool is_interrupt);
>  
>  /*
>   * Keep MSR_K6_STAR at the end, as setup_msrs() will try to optimize it
> @@ -940,6 +965,18 @@ static inline bool cpu_has_vmx_ept_2m_page(void)
>  	return !!(vmx_capability.ept & VMX_EPT_2MB_PAGE_BIT);
>  }
>  
> +static inline int 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 inline int is_nmi(u32 intr_info)
> +{
> +	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
> +		== (INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK);
> +}
> +
>  static inline int cpu_has_vmx_invept_individual_addr(void)
>  {
>  	return !!(vmx_capability.ept & VMX_EPT_EXTENT_INDIVIDUAL_BIT);
> @@ -990,6 +1027,51 @@ static inline bool report_flexpriority(void)
>  	return flexpriority_enabled;
>  }
>  
> +static inline int nested_cpu_has_vmx_tpr_shadow(struct  kvm_vcpu *vcpu)
> +{
> +	return cpu_has_vmx_tpr_shadow() &&
> +		get_shadow_vmcs(vcpu)->cpu_based_vm_exec_control &
> +		CPU_BASED_TPR_SHADOW;
> +}
> +
> +static inline int nested_cpu_has_secondary_exec_ctrls(struct kvm_vcpu *vcpu)
> +{
> +	return cpu_has_secondary_exec_ctrls() &&
> +		get_shadow_vmcs(vcpu)->cpu_based_vm_exec_control &
> +		CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
> +}
> +
> +static inline bool nested_vm_need_virtualize_apic_accesses(struct kvm_vcpu
> +							   *vcpu)
> +{
> +	return get_shadow_vmcs(vcpu)->secondary_vm_exec_control &
> +		SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
> +}
> +
> +static inline int nested_cpu_has_vmx_ept(struct kvm_vcpu *vcpu)
> +{
> +	return get_shadow_vmcs(vcpu)->
> +		secondary_vm_exec_control & SECONDARY_EXEC_ENABLE_EPT;
> +}
> +
> +static inline int nested_cpu_has_vmx_vpid(struct kvm_vcpu *vcpu)
> +{
> +	return get_shadow_vmcs(vcpu)->secondary_vm_exec_control &
> +		SECONDARY_EXEC_ENABLE_VPID;
> +}
> +
> +static inline int nested_cpu_has_vmx_pat(struct kvm_vcpu *vcpu)
> +{
> +	return get_shadow_vmcs(vcpu)->vm_entry_controls &
> +		VM_ENTRY_LOAD_IA32_PAT;
> +}
> +
> +static inline int nested_cpu_has_vmx_msr_bitmap(struct kvm_vcpu *vcpu)
> +{
> +	return get_shadow_vmcs(vcpu)->cpu_based_vm_exec_control &
> +		CPU_BASED_USE_MSR_BITMAPS;
> +}
> +
>  static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr)
>  {
>  	int i;
> @@ -1501,6 +1583,9 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
>  	struct vcpu_vmx *vmx = to_vmx(vcpu);
>  	u32 intr_info = nr | INTR_INFO_VALID_MASK;
>  
> +	if (nested_vmx_check_exception(vmx, nr, has_error_code, error_code))
> +		return;
> +
>  	if (has_error_code) {
>  		vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code);
>  		intr_info |= INTR_INFO_DELIVER_CODE_MASK;
> @@ -1943,6 +2028,200 @@ static void vmclear_local_vcpus(void)
>  		__vcpu_clear(vmx);
>  }
>  
> +void prepare_vmcs_12(struct kvm_vcpu *vcpu)
> +{
> +	struct shadow_vmcs *l2_shadow_vmcs =
> +		get_shadow_vmcs(vcpu);
> +
> +	l2_shadow_vmcs->guest_es_selector = vmcs_read16(GUEST_ES_SELECTOR);
> +	l2_shadow_vmcs->guest_cs_selector = vmcs_read16(GUEST_CS_SELECTOR);
> +	l2_shadow_vmcs->guest_ss_selector = vmcs_read16(GUEST_SS_SELECTOR);
> +	l2_shadow_vmcs->guest_ds_selector = vmcs_read16(GUEST_DS_SELECTOR);
> +	l2_shadow_vmcs->guest_fs_selector = vmcs_read16(GUEST_FS_SELECTOR);
> +	l2_shadow_vmcs->guest_gs_selector = vmcs_read16(GUEST_GS_SELECTOR);
> +	l2_shadow_vmcs->guest_ldtr_selector = vmcs_read16(GUEST_LDTR_SELECTOR);
> +	l2_shadow_vmcs->guest_tr_selector = vmcs_read16(GUEST_TR_SELECTOR);
> +
> +	l2_shadow_vmcs->tsc_offset = vmcs_read64(TSC_OFFSET);
> +	l2_shadow_vmcs->guest_physical_address =
> +		vmcs_read64(GUEST_PHYSICAL_ADDRESS);
> +	l2_shadow_vmcs->vmcs_link_pointer = vmcs_read64(VMCS_LINK_POINTER);
> +	l2_shadow_vmcs->guest_ia32_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
> +	if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT)
> +		l2_shadow_vmcs->guest_ia32_pat = vmcs_read64(GUEST_IA32_PAT);
> +	l2_shadow_vmcs->cr3_target_count = vmcs_read32(CR3_TARGET_COUNT);
> +	l2_shadow_vmcs->vm_entry_intr_info_field =
> +		vmcs_read32(VM_ENTRY_INTR_INFO_FIELD);
> +	l2_shadow_vmcs->vm_entry_exception_error_code =
> +		vmcs_read32(VM_ENTRY_EXCEPTION_ERROR_CODE);
> +	l2_shadow_vmcs->vm_entry_instruction_len =
> +		vmcs_read32(VM_ENTRY_INSTRUCTION_LEN);
> +	l2_shadow_vmcs->vm_instruction_error =
> +		vmcs_read32(VM_INSTRUCTION_ERROR);
> +	l2_shadow_vmcs->vm_exit_reason  = vmcs_read32(VM_EXIT_REASON);
> +	l2_shadow_vmcs->vm_exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
> +	l2_shadow_vmcs->vm_exit_intr_error_code =
> +		vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
> +	l2_shadow_vmcs->idt_vectoring_info_field =
> +		vmcs_read32(IDT_VECTORING_INFO_FIELD);
> +	l2_shadow_vmcs->idt_vectoring_error_code =
> +		vmcs_read32(IDT_VECTORING_ERROR_CODE);
> +	l2_shadow_vmcs->vm_exit_instruction_len =
> +		vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
> +	l2_shadow_vmcs->vmx_instruction_info =
> +		vmcs_read32(VMX_INSTRUCTION_INFO);
> +	l2_shadow_vmcs->guest_es_limit = vmcs_read32(GUEST_ES_LIMIT);
> +	l2_shadow_vmcs->guest_cs_limit = vmcs_read32(GUEST_CS_LIMIT);
> +	l2_shadow_vmcs->guest_ss_limit = vmcs_read32(GUEST_SS_LIMIT);
> +	l2_shadow_vmcs->guest_ds_limit = vmcs_read32(GUEST_DS_LIMIT);
> +	l2_shadow_vmcs->guest_fs_limit = vmcs_read32(GUEST_FS_LIMIT);
> +	l2_shadow_vmcs->guest_gs_limit = vmcs_read32(GUEST_GS_LIMIT);
> +	l2_shadow_vmcs->guest_ldtr_limit = vmcs_read32(GUEST_LDTR_LIMIT);
> +	l2_shadow_vmcs->guest_tr_limit = vmcs_read32(GUEST_TR_LIMIT);
> +	l2_shadow_vmcs->guest_gdtr_limit = vmcs_read32(GUEST_GDTR_LIMIT);
> +	l2_shadow_vmcs->guest_idtr_limit = vmcs_read32(GUEST_IDTR_LIMIT);
> +	l2_shadow_vmcs->guest_es_ar_bytes = vmcs_read32(GUEST_ES_AR_BYTES);
> +	l2_shadow_vmcs->guest_cs_ar_bytes = vmcs_read32(GUEST_CS_AR_BYTES);
> +	l2_shadow_vmcs->guest_ss_ar_bytes = vmcs_read32(GUEST_SS_AR_BYTES);
> +	l2_shadow_vmcs->guest_ds_ar_bytes = vmcs_read32(GUEST_DS_AR_BYTES);
> +	l2_shadow_vmcs->guest_fs_ar_bytes = vmcs_read32(GUEST_FS_AR_BYTES);
> +	l2_shadow_vmcs->guest_gs_ar_bytes = vmcs_read32(GUEST_GS_AR_BYTES);
> +	l2_shadow_vmcs->guest_ldtr_ar_bytes = vmcs_read32(GUEST_LDTR_AR_BYTES);
> +	l2_shadow_vmcs->guest_tr_ar_bytes = vmcs_read32(GUEST_TR_AR_BYTES);
> +	l2_shadow_vmcs->guest_interruptibility_info =
> +		vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
> +	l2_shadow_vmcs->guest_activity_state =
> +		vmcs_read32(GUEST_ACTIVITY_STATE);
> +	l2_shadow_vmcs->guest_sysenter_cs = vmcs_read32(GUEST_SYSENTER_CS);
> +
> +	l2_shadow_vmcs->cr0_read_shadow = vmcs_readl(CR0_READ_SHADOW);
> +	l2_shadow_vmcs->cr4_read_shadow = vmcs_readl(CR4_READ_SHADOW);
> +	l2_shadow_vmcs->exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
> +	l2_shadow_vmcs->guest_linear_address = vmcs_readl(GUEST_LINEAR_ADDRESS);
> +	l2_shadow_vmcs->guest_cr0 = vmcs_readl(GUEST_CR0);
> +
> +	l2_shadow_vmcs->guest_cr4 = vmcs_readl(GUEST_CR4);
> +	l2_shadow_vmcs->guest_es_base = vmcs_readl(GUEST_ES_BASE);
> +	l2_shadow_vmcs->guest_cs_base = vmcs_readl(GUEST_CS_BASE);
> +	l2_shadow_vmcs->guest_ss_base = vmcs_readl(GUEST_SS_BASE);
> +	l2_shadow_vmcs->guest_ds_base = vmcs_readl(GUEST_DS_BASE);
> +	l2_shadow_vmcs->guest_fs_base = vmcs_readl(GUEST_FS_BASE);
> +	l2_shadow_vmcs->guest_gs_base = vmcs_readl(GUEST_GS_BASE);
> +	l2_shadow_vmcs->guest_ldtr_base = vmcs_readl(GUEST_LDTR_BASE);
> +	l2_shadow_vmcs->guest_tr_base = vmcs_readl(GUEST_TR_BASE);
> +	l2_shadow_vmcs->guest_gdtr_base = vmcs_readl(GUEST_GDTR_BASE);
> +	l2_shadow_vmcs->guest_idtr_base = vmcs_readl(GUEST_IDTR_BASE);
> +	l2_shadow_vmcs->guest_dr7 = vmcs_readl(GUEST_DR7);
> +	l2_shadow_vmcs->guest_rsp = vmcs_readl(GUEST_RSP);
> +	l2_shadow_vmcs->guest_rip = vmcs_readl(GUEST_RIP);
> +	l2_shadow_vmcs->guest_rflags = vmcs_readl(GUEST_RFLAGS);
> +	l2_shadow_vmcs->guest_pending_dbg_exceptions =
> +		vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS);
> +	l2_shadow_vmcs->guest_sysenter_esp = vmcs_readl(GUEST_SYSENTER_ESP);
> +	l2_shadow_vmcs->guest_sysenter_eip = vmcs_readl(GUEST_SYSENTER_EIP);
> +}
> +
> +int load_vmcs_common(struct shadow_vmcs *src)
> +{
> +	vmcs_write16(GUEST_ES_SELECTOR, src->guest_es_selector);
> +	vmcs_write16(GUEST_CS_SELECTOR, src->guest_cs_selector);
> +	vmcs_write16(GUEST_SS_SELECTOR, src->guest_ss_selector);
> +	vmcs_write16(GUEST_DS_SELECTOR, src->guest_ds_selector);
> +	vmcs_write16(GUEST_FS_SELECTOR, src->guest_fs_selector);
> +	vmcs_write16(GUEST_GS_SELECTOR, src->guest_gs_selector);
> +	vmcs_write16(GUEST_LDTR_SELECTOR, src->guest_ldtr_selector);
> +	vmcs_write16(GUEST_TR_SELECTOR, src->guest_tr_selector);
> +
> +	vmcs_write64(VMCS_LINK_POINTER, src->vmcs_link_pointer);
> +	vmcs_write64(GUEST_IA32_DEBUGCTL, src->guest_ia32_debugctl);
> +
> +	if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT)
> +		vmcs_write64(GUEST_IA32_PAT, src->guest_ia32_pat);
> +
> +	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, src->vm_entry_msr_load_count);
> +	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, src->vm_entry_intr_info_field);
> +	vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE,
> +		     src->vm_entry_exception_error_code);
> +	vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, src->vm_entry_instruction_len);
> +
> +	vmcs_write32(GUEST_ES_LIMIT, src->guest_es_limit);
> +	vmcs_write32(GUEST_CS_LIMIT, src->guest_cs_limit);
> +	vmcs_write32(GUEST_SS_LIMIT, src->guest_ss_limit);
> +	vmcs_write32(GUEST_DS_LIMIT, src->guest_ds_limit);
> +	vmcs_write32(GUEST_FS_LIMIT, src->guest_fs_limit);
> +	vmcs_write32(GUEST_GS_LIMIT, src->guest_gs_limit);
> +	vmcs_write32(GUEST_LDTR_LIMIT, src->guest_ldtr_limit);
> +	vmcs_write32(GUEST_TR_LIMIT, src->guest_tr_limit);
> +	vmcs_write32(GUEST_GDTR_LIMIT, src->guest_gdtr_limit);
> +	vmcs_write32(GUEST_IDTR_LIMIT, src->guest_idtr_limit);
> +	vmcs_write32(GUEST_ES_AR_BYTES, src->guest_es_ar_bytes);
> +	vmcs_write32(GUEST_CS_AR_BYTES, src->guest_cs_ar_bytes);
> +	vmcs_write32(GUEST_SS_AR_BYTES, src->guest_ss_ar_bytes);
> +	vmcs_write32(GUEST_DS_AR_BYTES, src->guest_ds_ar_bytes);
> +	vmcs_write32(GUEST_FS_AR_BYTES, src->guest_fs_ar_bytes);
> +	vmcs_write32(GUEST_GS_AR_BYTES, src->guest_gs_ar_bytes);
> +	vmcs_write32(GUEST_LDTR_AR_BYTES, src->guest_ldtr_ar_bytes);
> +	vmcs_write32(GUEST_TR_AR_BYTES, src->guest_tr_ar_bytes);
> +	vmcs_write32(GUEST_INTERRUPTIBILITY_INFO,
> +		     src->guest_interruptibility_info);
> +	vmcs_write32(GUEST_ACTIVITY_STATE, src->guest_activity_state);
> +	vmcs_write32(GUEST_SYSENTER_CS, src->guest_sysenter_cs);
> +
> +	vmcs_writel(GUEST_ES_BASE, src->guest_es_base);
> +	vmcs_writel(GUEST_CS_BASE, src->guest_cs_base);
> +	vmcs_writel(GUEST_SS_BASE, src->guest_ss_base);
> +	vmcs_writel(GUEST_DS_BASE, src->guest_ds_base);
> +	vmcs_writel(GUEST_FS_BASE, src->guest_fs_base);
> +	vmcs_writel(GUEST_GS_BASE, src->guest_gs_base);
> +	vmcs_writel(GUEST_LDTR_BASE, src->guest_ldtr_base);
> +	vmcs_writel(GUEST_TR_BASE, src->guest_tr_base);
> +	vmcs_writel(GUEST_GDTR_BASE, src->guest_gdtr_base);
> +	vmcs_writel(GUEST_IDTR_BASE, src->guest_idtr_base);
> +	vmcs_writel(GUEST_DR7, src->guest_dr7);
> +	vmcs_writel(GUEST_RSP, src->guest_rsp);
> +	vmcs_writel(GUEST_RIP, src->guest_rip);
> +	vmcs_writel(GUEST_RFLAGS, src->guest_rflags);
> +	vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS,
> +		    src->guest_pending_dbg_exceptions);
> +	vmcs_writel(GUEST_SYSENTER_ESP, src->guest_sysenter_esp);
> +	vmcs_writel(GUEST_SYSENTER_EIP, src->guest_sysenter_eip);
> +
> +	return 0;
> +}
> +
> +int load_vmcs_host_state(struct shadow_vmcs *src)
> +{
> +	vmcs_write16(HOST_ES_SELECTOR, src->host_es_selector);
> +	vmcs_write16(HOST_CS_SELECTOR, src->host_cs_selector);
> +	vmcs_write16(HOST_SS_SELECTOR, src->host_ss_selector);
> +	vmcs_write16(HOST_DS_SELECTOR, src->host_ds_selector);
> +	vmcs_write16(HOST_FS_SELECTOR, src->host_fs_selector);
> +	vmcs_write16(HOST_GS_SELECTOR, src->host_gs_selector);
> +	vmcs_write16(HOST_TR_SELECTOR, src->host_tr_selector);
> +
> +	vmcs_write64(TSC_OFFSET, src->tsc_offset);
> +
> +	if (vmcs_config.vmexit_ctrl & VM_EXIT_LOAD_IA32_PAT)
> +		vmcs_write64(HOST_IA32_PAT, src->host_ia32_pat);
> +
> +	vmcs_write32(HOST_IA32_SYSENTER_CS, src->host_ia32_sysenter_cs);
> +
> +	vmcs_writel(HOST_CR0, src->host_cr0);
> +	vmcs_writel(HOST_CR3, src->host_cr3);
> +	vmcs_writel(HOST_CR4, src->host_cr4);
> +	vmcs_writel(HOST_FS_BASE, src->host_fs_base);
> +	vmcs_writel(HOST_GS_BASE, src->host_gs_base);
> +	vmcs_writel(HOST_TR_BASE, src->host_tr_base);
> +	vmcs_writel(HOST_GDTR_BASE, src->host_gdtr_base);
> +	vmcs_writel(HOST_IDTR_BASE, src->host_idtr_base);
> +	vmcs_writel(HOST_RSP, src->host_rsp);
> +	vmcs_writel(HOST_RIP, src->host_rip);
> +	vmcs_writel(HOST_IA32_SYSENTER_ESP, src->host_ia32_sysenter_esp);
> +	vmcs_writel(HOST_IA32_SYSENTER_EIP, src->host_ia32_sysenter_eip);
> +
> +	return 0;
> +}
> +
>  struct level_state *create_state(void)
>  {
>  	struct level_state *state = NULL;
> @@ -2003,6 +2282,8 @@ int create_l2_state(struct kvm_vcpu *vcpu)
>  	vmx->nested.l2_state->io_bitmap_a = vmcs_read64(IO_BITMAP_A);
>  	vmx->nested.l2_state->io_bitmap_b = vmcs_read64(IO_BITMAP_B);
>  
> +	vmx->nested.l2_state->first_launch = true;
> +
>  	return 0;
>  }
>  
> @@ -3393,6 +3674,14 @@ static void enable_irq_window(struct kvm_vcpu *vcpu)
>  {
>  	u32 cpu_based_vm_exec_control;
>  
> +	if (to_vmx(vcpu)->nested.nested_mode) {
> +		if (kvm_cpu_has_interrupt(vcpu)) {
Why interrupt will not be present during the call to
enable_irq_window()?

> +			if (nested_vmx_intr(vcpu))
> +				return;
> +		}
> +		return;
> +	}
> +
>  	cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
>  	cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_INTR_PENDING;
>  	vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
> @@ -3448,6 +3737,10 @@ static void vmx_inject_nmi(struct kvm_vcpu *vcpu)
>  {
>  	struct vcpu_vmx *vmx = to_vmx(vcpu);
>  
> +	if (vmx->nested.nested_mode) {
> +		return;
> +	}
> +
>  	if (!cpu_has_virtual_nmis()) {
>  		/*
>  		 * Tracking the NMI-blocked state in software is built upon
> @@ -3489,6 +3782,13 @@ static int vmx_nmi_allowed(struct kvm_vcpu *vcpu)
>  
>  static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu)
>  {
> +	if (to_vmx(vcpu)->nested.nested_mode) {
> +		if (kvm_cpu_has_interrupt(vcpu)) {
> +			if (!nested_vmx_intr(vcpu))
> +				return 0;
> +		}
> +	}
> +
Same as above. kvm_cpu_has_interrupt() should alway return true here.
More interesting question: why not return 0 here if in nested mode and
PIN_BASED_EXT_INTR_MASK is not set and let enable_irq_window() to do
nested exit. This is what svm does as far as I see.
 
>  	return (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) &&
>  		!(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
>  			(GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS));
> @@ -3993,12 +4293,6 @@ static int nested_vmx_check_permission(struct kvm_vcpu *vcpu)
>  	return 1;
>  }
>  
> -static int handle_vmx_insn(struct kvm_vcpu *vcpu)
> -{
> -	kvm_queue_exception(vcpu, UD_VECTOR);
> -	return 1;
> -}
> -
>  static void clear_rflags_cf_zf(struct kvm_vcpu *vcpu)
>  {
>  	unsigned long rflags;
> @@ -4040,6 +4334,27 @@ static int handle_vmclear(struct kvm_vcpu *vcpu)
>  	return 1;
>  }
>  
> +static int handle_vmlaunch(struct kvm_vcpu *vcpu)
> +{
> +	if (!nested_vmx_check_permission(vcpu))
> +		return 1;
> +	if (!to_vmx(vcpu)->nested.l2_state->vmclear)
> +		return 1;
> +
> +	return launch_guest(vcpu);
> +}
> +
> +static int handle_vmresume(struct kvm_vcpu *vcpu)
> +{
> +	if (!nested_vmx_check_permission(vcpu))
> +		return 1;
> +
> +	if (to_vmx(vcpu)->nested.l2_state->vmclear)
> +		return 1;
> +
> +	return launch_guest(vcpu);
> +}
> +
handle_vmlaunch() and handle_vmresume() are looking suspiciously
similar may be move vmclear checking logic into launch_guest()?
It will get additional parameter: expected value of vmclear.

>  static int handle_vmread(struct kvm_vcpu *vcpu)
>  {
>  #ifndef CONFIG_X86_64
> @@ -4050,7 +4365,6 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
>  		return 1;
>  
>  	if (!nested_map_shadow_vmcs(vcpu)) {
> -		printk(KERN_INFO "%s invalid shadow vmcs\n", __func__);
>  		set_rflags_to_vmx_fail_invalid(vcpu);
>  		return 1;
>  	}
Remove from a patch that add it if you don't need this. Also all
prinks that can be triggered by a guest should be removed/changed to
debug output.

> @@ -4107,7 +4421,6 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu)
>  		return 1;
>  
>  	if (!nested_map_shadow_vmcs(vcpu)) {
> -		printk(KERN_INFO "%s invalid shadow vmcs\n", __func__);
>  		set_rflags_to_vmx_fail_invalid(vcpu);
>  		return 1;
>  	}
> @@ -4137,16 +4450,16 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu)
>  				   vcpu->arch.regs[VCPU_REGS_RAX]);
>  		break;
>  	default:
> +		nested_unmap_shadow_vmcs(vcpu);
>  		printk(KERN_INFO "%s invalid field\n", __func__);
>  		set_rflags_to_vmx_fail_valid(vcpu);
>  		vmcs_write32(VM_INSTRUCTION_ERROR, 12);
> -		nested_unmap_shadow_vmcs(vcpu);
>  		return 1;
>  	}
Why this is here and not in the patch that introduce the function?

>  
> +	nested_unmap_shadow_vmcs(vcpu);
>  	clear_rflags_cf_zf(vcpu);
>  	skip_emulated_instruction(vcpu);
> -	nested_unmap_shadow_vmcs(vcpu);
>  	return 1;
>  }
Same.

>  
> @@ -4208,7 +4521,6 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
>  static int handle_vmptrld(struct kvm_vcpu *vcpu)
>  {
>  	struct vcpu_vmx *vmx = to_vmx(vcpu);
> -	struct page *vmcs_page;
>  	u64 guest_vmcs_addr;
>  
>  	if (!nested_vmx_check_permission(vcpu))
> @@ -4228,14 +4540,7 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
>  	}
>  
>  	if (vmx->nested.vmptr != guest_vmcs_addr) {
> -		/* checking vmptr address */
> -		vmcs_page = nested_get_page(vcpu, guest_vmcs_addr);
> -		if (vmcs_page == NULL)
> -			return 1;
> -
>  		vmx->nested.vmptr = guest_vmcs_addr;
> -
> -		kvm_release_page_clean(vmcs_page);
>  	}
Same.

>  
>  	clear_rflags_cf_zf(vcpu);
> @@ -4534,11 +4839,11 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
>  	[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,
> @@ -4566,6 +4871,17 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
>  
>  	trace_kvm_exit(exit_reason, kvm_rip_read(vcpu));
>  
> +	if (exit_reason == EXIT_REASON_VMLAUNCH ||
> +	    exit_reason == EXIT_REASON_VMRESUME)
> +		vmx->nested.nested_run_pending = 1;
> +	else
> +		vmx->nested.nested_run_pending = 0;
> +
> +	if (vmx->nested.nested_mode && nested_vmx_exit_handled(vcpu, true)) {
> +		nested_vmx_vmexit(vcpu, false);
> +		return 1;
> +	}
> +
>  	/* If we need to emulate an MMIO from handle_invalid_guest_state
>  	 * we just return 0 */
>  	if (vmx->emulation_required && emulate_invalid_guest_state) {
> @@ -4585,7 +4901,6 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
>  			= vmcs_read32(VM_INSTRUCTION_ERROR);
>  		return 0;
>  	}
> -
No spurious line deletions please.

>  	if ((vectoring_info & VECTORING_INFO_VALID_MASK) &&
>  			(exit_reason != EXIT_REASON_EXCEPTION_NMI &&
>  			exit_reason != EXIT_REASON_EPT_VIOLATION &&
> @@ -4593,8 +4908,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
>  		printk(KERN_WARNING "%s: unexpected, valid vectoring info "
>  		       "(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 (!vmx->nested.nested_mode && unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked)) {
>  		if (vmx_interrupt_allowed(vcpu)) {
>  			vmx->soft_vnmi_blocked = 0;
>  		} else if (vmx->vnmi_blocked_time > 1000000000LL &&
> @@ -4641,10 +4955,13 @@ static void vmx_complete_interrupts(struct vcpu_vmx *vmx)
>  	int type;
>  	bool idtv_info_valid;
>  
> -	exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
> -
>  	vmx->exit_reason = vmcs_read32(VM_EXIT_REASON);
>  
> +	if (vmx->nested.nested_mode)
> +		return;
> +
Why return here? What the function does that should not be done in
nested mode?

> +	exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
> +
>  	/* Handle machine checks before interrupts are enabled */
>  	if ((vmx->exit_reason == EXIT_REASON_MCE_DURING_VMENTRY)
>  	    || (vmx->exit_reason == EXIT_REASON_EXCEPTION_NMI
> @@ -4747,6 +5064,60 @@ static void fixup_rmode_irq(struct vcpu_vmx *vmx)
>  		| vmx->rmode.irq.vector;
>  }
>  
> +static int nested_handle_valid_idt(struct kvm_vcpu *vcpu)
> +{
It seems by this function you are trying to bypass general event
reinjection logic. Why?

> +	struct vcpu_vmx *vmx = to_vmx(vcpu);
> +	int irq;
> +	int type;
> +	int errCodeValid;
> +	u32 idt_vectoring_info;
> +	u32 guest_intr;
> +	bool nmi_window_open;
> +	bool interrupt_window_open;
> +
> +	if (vmx->nested.nested_mode && vmx->nested.nested_valid_idt) {
Caller already checked nested_mode why recheck?

> +		idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
> +		irq  = idt_vectoring_info & VECTORING_INFO_VECTOR_MASK;
> +		type = idt_vectoring_info & VECTORING_INFO_TYPE_MASK;
> +		errCodeValid = idt_vectoring_info &
> +			VECTORING_INFO_DELIVER_CODE_MASK;
> +
> +		guest_intr = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
> +		nmi_window_open =
> +			!(guest_intr & (GUEST_INTR_STATE_STI |
> +					GUEST_INTR_STATE_MOV_SS |
> +					GUEST_INTR_STATE_NMI));
> +
> +		interrupt_window_open =
> +			((vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) &&
> +			 !(guest_intr & (GUEST_INTR_STATE_STI |
> +					 GUEST_INTR_STATE_MOV_SS)));
> +
> +		if (type == INTR_TYPE_EXT_INTR && !interrupt_window_open) {
> +			printk(KERN_INFO "IDT ignored, l2 interrupt window closed!\n");
> +			return 0;
> +		}
> +
> +		if (type == INTR_TYPE_NMI_INTR && !nmi_window_open) {
> +			printk(KERN_INFO "IDT ignored, l2 nmi window closed!\n");
> +			return 0;
> +		}
> +
> +		vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
> +			irq | type | INTR_INFO_VALID_MASK | errCodeValid);
> +
> +
> +		vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
> +			     vmcs_read32(VM_EXIT_INSTRUCTION_LEN));
> +
> +		if (errCodeValid)
> +			vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE,
> +				     vmcs_read32(IDT_VECTORING_ERROR_CODE));
> +	}
> +
> +	return 1;
> +}
> +
>  #ifdef CONFIG_X86_64
>  #define R "r"
>  #define Q "q"
> @@ -4758,6 +5129,26 @@ static void fixup_rmode_irq(struct vcpu_vmx *vmx)
>  static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
>  {
>  	struct vcpu_vmx *vmx = to_vmx(vcpu);
> +	int r;
> +
> +	if (vmx->nested.nested_mode) {
> +		r = nested_handle_valid_idt(vcpu);
> +		if (!r) {
> +			vmx->fail = 1;
> +			return;
> +		}
> +
> +		if (!nested_map_shadow_vmcs(vcpu)) {
> +			vmx->fail = 1;
> +			return;
> +		}
> +
> +		vmcs_write32(EXCEPTION_BITMAP, get_shadow_vmcs(vcpu)->
> +			     exception_bitmap |
> +			     vmx->nested.l1_state->shadow_vmcs->exception_bitmap);
> +
> +		nested_unmap_shadow_vmcs(vcpu);
> +	}
>  
>  	if (enable_ept && is_paging(vcpu)) {
>  		vmcs_writel(GUEST_CR3, vcpu->arch.cr3);
> @@ -4896,6 +5287,10 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
>  	get_debugreg(vcpu->arch.dr6, 6);
>  
>  	vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
> +
> +	vmx->nested.nested_valid_idt = vmx->nested.nested_mode &&
> +		(vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK);
> +
>  	if (vmx->rmode.irq.pending)
>  		fixup_rmode_irq(vmx);
>  
> @@ -4984,6 +5379,11 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
>  			goto free_vmcs;
>  	}
>  
> +	vmx->nested.vmptr = 0;
> +
> +	vmx->nested.l1_state = NULL;
> +	vmx->nested.l2_state = NULL;
> +
>  	return &vmx->vcpu;
>  
>  free_vmcs:
> @@ -5215,6 +5615,729 @@ void save_vmcs(struct shadow_vmcs *dst)
>  	if (vmcs_config.vmexit_ctrl & VM_EXIT_LOAD_IA32_PAT)
>  		dst->host_ia32_pat = vmcs_read64(HOST_IA32_PAT);
>  }
> +int prepare_vmcs_02(struct kvm_vcpu *vcpu)
> +{
> +	struct vcpu_vmx *vmx = to_vmx(vcpu);
> +	struct shadow_vmcs *src = get_shadow_vmcs(vcpu);
> +	u32 exec_control;
> +
> +	if (!src) {
> +		printk(KERN_INFO "%s: Error no shadow vmcs\n", __func__);
> +		return 1;
> +	}
> +
> +	load_vmcs_common(src);
> +
> +	if (vmx->nested.l2_state->first_launch) {
> +		if (cpu_has_vmx_vpid() && vmx->nested.l2_state->vpid != 0)
> +			vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->nested.l2_state->vpid);
> +
> +		if (vmx->nested.l2_state->io_bitmap_a)
> +			vmcs_write64(IO_BITMAP_A, vmx->nested.l2_state->io_bitmap_a);
> +
> +		if (vmx->nested.l2_state->io_bitmap_b)
> +			vmcs_write64(IO_BITMAP_B, vmx->nested.l2_state->io_bitmap_b);
> +
> +		if (vmx->nested.l2_state->msr_bitmap)
> +			vmcs_write64(MSR_BITMAP, vmx->nested.l2_state->msr_bitmap);
> +
> +		if (src->vm_entry_msr_load_count > 0) {
> +			struct page *page;
> +
> +			page = nested_get_page(vcpu,
> +					       src->vm_entry_msr_load_addr);
> +			if (!page)
> +				return 1;
> +
> +			vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, page_to_phys(page));
> +
> +			kvm_release_page_clean(page);
> +		}
> +
> +		if (nested_cpu_has_vmx_tpr_shadow(vcpu)) {
> +			struct page *page;
> +
> +			page = nested_get_page(vcpu,
> +					       src->virtual_apic_page_addr);
> +			if (!page)
> +				return 1;
> +
> +			vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, page_to_phys(page));
> +
> +			kvm_release_page_clean(page);
> +		}
> +
> +		if (nested_vm_need_virtualize_apic_accesses(vcpu)) {
> +			struct page *page =
> +				nested_get_page(vcpu, src->apic_access_addr);
> +			if (!page)
> +				return 1;
> +
> +			vmcs_write64(APIC_ACCESS_ADDR, page_to_phys(page));
> +			kvm_release_page_clean(page);
> +		}
> +
> +		vmcs_write32(PIN_BASED_VM_EXEC_CONTROL,
> +			     (vmx->nested.l1_state->shadow_vmcs->pin_based_vm_exec_control |
> +			      src->pin_based_vm_exec_control));
> +
> +		vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK,
> +			     (vmx->nested.l1_state->shadow_vmcs->page_fault_error_code_mask &
> +			      src->page_fault_error_code_mask));
> +
> +		vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH,
> +			     (vmx->nested.l1_state->shadow_vmcs->page_fault_error_code_match &
> +			      src->page_fault_error_code_match));
> +
> +		if (cpu_has_secondary_exec_ctrls()) {
> +
> +			exec_control =
> +				vmx->nested.l1_state->shadow_vmcs->secondary_vm_exec_control;
> +
> +			if (nested_cpu_has_secondary_exec_ctrls(vcpu)) {
> +
> +				exec_control |= src->secondary_vm_exec_control;
> +
> +				if (!vm_need_virtualize_apic_accesses(vcpu->kvm) ||
> +				    !nested_vm_need_virtualize_apic_accesses(vcpu))
> +					exec_control &=
> +						~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
> +			}
> +
> +			vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
> +		}
> +
> +		load_vmcs_host_state(vmx->nested.l1_state->shadow_vmcs);
> +
> +		vmx->nested.l2_state->first_launch = false;
> +	}
> +
> +	if (vm_need_tpr_shadow(vcpu->kvm) &&
> +	    nested_cpu_has_vmx_tpr_shadow(vcpu))
> +		vmcs_write32(TPR_THRESHOLD, src->tpr_threshold);
> +
> +	if (enable_ept) {
> +		if (!nested_cpu_has_vmx_ept(vcpu)) {
> +			vmcs_write64(EPT_POINTER,
> +				     vmx->nested.l1_state->shadow_vmcs->ept_pointer);
> +			vmcs_write64(GUEST_PDPTR0,
> +				     vmx->nested.l1_state->shadow_vmcs->guest_pdptr0);
> +			vmcs_write64(GUEST_PDPTR1,
> +				     vmx->nested.l1_state->shadow_vmcs->guest_pdptr1);
> +			vmcs_write64(GUEST_PDPTR2,
> +				     vmx->nested.l1_state->shadow_vmcs->guest_pdptr2);
> +			vmcs_write64(GUEST_PDPTR3,
> +				     vmx->nested.l1_state->shadow_vmcs->guest_pdptr3);
> +		}
> +	}
> +
> +	exec_control = vmx->nested.l1_state->shadow_vmcs->cpu_based_vm_exec_control;
> +
> +	exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING;
> +
> +	exec_control &= ~CPU_BASED_VIRTUAL_NMI_PENDING;
> +
> +	exec_control &= ~CPU_BASED_TPR_SHADOW;
> +
> +	exec_control |= src->cpu_based_vm_exec_control;
> +
> +	if (!vm_need_tpr_shadow(vcpu->kvm) ||
> +	    src->virtual_apic_page_addr == 0) {
> +		exec_control &= ~CPU_BASED_TPR_SHADOW;
> +#ifdef CONFIG_X86_64
> +		exec_control |= CPU_BASED_CR8_STORE_EXITING |
> +			CPU_BASED_CR8_LOAD_EXITING;
> +#endif
> +	} else if (exec_control & CPU_BASED_TPR_SHADOW) {
> +
> +#ifdef CONFIG_X86_64
> +		exec_control &= ~CPU_BASED_CR8_STORE_EXITING;
> +		exec_control &= ~CPU_BASED_CR8_LOAD_EXITING;
> +#endif
> +	}
> +
> +	vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, exec_control);
> +
> +	vmcs_write32(EXCEPTION_BITMAP,
> +		     (vmx->nested.l1_state->shadow_vmcs->exception_bitmap |
> +		      src->exception_bitmap));
> +
> +	vmcs_write32(VM_EXIT_CONTROLS,
> +		     ((vmx->nested.l1_state->shadow_vmcs->vm_exit_controls &
> +		       NESTED_VM_EXIT_CONTROLS_MASK) | src->vm_exit_controls));
> +
> +	vmcs_write32(VM_ENTRY_CONTROLS,
> +		     (vmx->nested.l1_state->shadow_vmcs->vm_entry_controls &
> +		      NESTED_VM_ENTRY_CONTROLS_MASK) | src->vm_entry_controls);
> +
> +	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, src->vm_entry_msr_load_count);
> +
> +	vmcs_writel(CR0_GUEST_HOST_MASK,
> +		    (vmx->nested.l1_state->shadow_vmcs->cr0_guest_host_mask  &
> +		     src->cr0_guest_host_mask));
> +	vmcs_writel(CR4_GUEST_HOST_MASK,
> +		    (vmx->nested.l1_state->shadow_vmcs->cr4_guest_host_mask  &
> +		     src->cr4_guest_host_mask));
> +
> +	return 0;
> +}
> +
> +int switch_back_vmcs(struct kvm_vcpu *vcpu)
> +{
> +	struct shadow_vmcs *src = to_vmx(vcpu)->nested.l1_state->shadow_vmcs;
> +
> +	if (enable_vpid && src->virtual_processor_id != 0)
> +		vmcs_write16(VIRTUAL_PROCESSOR_ID, src->virtual_processor_id);
> +
> +	vmcs_write64(IO_BITMAP_A, src->io_bitmap_a);
> +	vmcs_write64(IO_BITMAP_B, src->io_bitmap_b);
> +
> +	if (cpu_has_vmx_msr_bitmap())
> +		vmcs_write64(MSR_BITMAP, src->msr_bitmap);
> +
> +	vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, src->virtual_apic_page_addr);
> +
> +	if (vm_need_virtualize_apic_accesses(vcpu->kvm))
> +		vmcs_write64(APIC_ACCESS_ADDR,
> +			     src->apic_access_addr);
> +
> +	if (enable_ept) {
> +		vmcs_write64(EPT_POINTER, src->ept_pointer);
> +		vmcs_write64(GUEST_PDPTR0, src->guest_pdptr0);
> +		vmcs_write64(GUEST_PDPTR1, src->guest_pdptr1);
> +		vmcs_write64(GUEST_PDPTR2, src->guest_pdptr2);
> +		vmcs_write64(GUEST_PDPTR3, src->guest_pdptr3);
> +	}
> +
> +	vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, src->pin_based_vm_exec_control);
> +	vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, src->cpu_based_vm_exec_control);
> +	vmcs_write32(EXCEPTION_BITMAP, src->exception_bitmap);
> +	vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK,
> +		     src->page_fault_error_code_mask);
> +	vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH,
> +		     src->page_fault_error_code_match);
> +	vmcs_write32(VM_EXIT_CONTROLS, src->vm_exit_controls);
> +	vmcs_write32(VM_ENTRY_CONTROLS, src->vm_entry_controls);
> +	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, src->vm_entry_msr_load_count);
> +
> +	if (cpu_has_secondary_exec_ctrls())
> +		vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
> +			     src->secondary_vm_exec_control);
> +
> +	load_vmcs_common(src);
> +
> +	load_vmcs_host_state(to_vmx(vcpu)->nested.l1_state->shadow_vmcs);
> +
> +	return 0;
> +}
> +
> +void sync_cached_regs_to_vmcs(struct kvm_vcpu *vcpu)
> +{
> +	unsigned long mask;
> +
> +	if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty))
> +		vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]);
> +	if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty))
> +		vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
> +
> +	mask = ~((1 << VCPU_REGS_RSP) | (1 << VCPU_REGS_RIP));
> +
> +	if (vcpu->arch.regs_dirty & mask) {
> +		printk(KERN_INFO "WARNING: dirty cached registers regs_dirty 0x%x mask 0x%lx\n",
> +		       vcpu->arch.regs_dirty, mask);
> +		WARN_ON(1);
> +	}
> +
> +	vcpu->arch.regs_dirty = 0;
> +}
> +
> +static int nested_vmx_run(struct kvm_vcpu *vcpu)
> +{
> +	/* verify that l1 has done vmptrld for l2 earlier */
> +	struct vcpu_vmx *vmx = to_vmx(vcpu);
> +	int initial_pfu_active = vcpu->fpu_active;
> +	int r = 0;
> +
> +	if (vmx->nested.nested_mode) {
> +		printk(KERN_INFO "Nested guest already running\n");
> +		set_rflags_to_vmx_fail_valid(vcpu);
> +		return 1;
> +	}
> +
> +
> +	vmx->nested.nested_mode = 1;
> +
> +	vcpu->arch.exception.pending = false;
Why need this?

> +
> +	sync_cached_regs_to_vmcs(vcpu);
> +
> +	save_vmcs(vmx->nested.l1_state->shadow_vmcs);
> +
> +	vmx->nested.l1_state->shadow_efer = vcpu->arch.shadow_efer;
> +	if (!enable_ept)
> +		vmx->nested.l1_state->cr3 = vcpu->arch.cr3;
> +	vmx->nested.l1_state->cr4 = vcpu->arch.cr4;
> +
> +	if (enable_vpid) {
> +		if (vmx->nested.l2_state->vpid == 0) {
> +			allocate_vpid(vmx);
> +			vmx->nested.l2_state->vpid = vmx->vpid;
> +		}
> +	}
> +
> +	if (cpu_has_vmx_msr_bitmap())
> +		vmx->nested.l1_state->msr_bitmap = vmcs_read64(MSR_BITMAP);
> +	else
> +		vmx->nested.l1_state->msr_bitmap = 0;
> +
> +	vmx->nested.l1_state->io_bitmap_a = vmcs_read64(IO_BITMAP_A);
> +	vmx->nested.l1_state->io_bitmap_b = vmcs_read64(IO_BITMAP_B);
> +	vmx->nested.l1_state->vmcs = vmx->vmcs;
> +	vmx->nested.l1_state->cpu = vcpu->cpu;
> +	vmx->nested.l1_state->launched = vmx->launched;
> +
> +	vmx->vmcs = vmx->nested.l2_state->vmcs;
> +	vcpu->cpu = vmx->nested.l2_state->cpu;
Who initialize vmx->nested.l2_state->cpu before first launch?
Why have different cpu for l1 and l2 guest? It seems like this is global
vcpu thread property.

> +	vmx->launched = vmx->nested.l2_state->launched;
> +
Can you explain why ->launched logic is needed?

> +	if (vmx->nested.l2_state->vmclear || !vmx->launched) {
> +		vmcs_clear(vmx->vmcs);
> +		vmx->launched = 0;
> +		vmx->nested.l2_state->vmclear = 0;
> +	}
> +
> +	vmx_vcpu_load(vcpu, get_cpu());
> +	put_cpu();
> +
> +
> +	if (!nested_map_shadow_vmcs(vcpu)) {
> +		set_rflags_to_vmx_fail_valid(vcpu);
> +		return 1;
> +	}
No cleanup on error. Is looks like we are on an l2 vmcs at this point.

> +
> +	prepare_vmcs_02(vcpu);
> +
> +	if (get_shadow_vmcs(vcpu)->vm_entry_controls &
> +	    VM_ENTRY_IA32E_MODE) {
> +		if (!((vcpu->arch.shadow_efer & EFER_LMA) &&
> +		      (vcpu->arch.shadow_efer & EFER_LME)))
> +			vcpu->arch.shadow_efer |= (EFER_LMA | EFER_LME);
> +	} else {
> +		if ((vcpu->arch.shadow_efer & EFER_LMA) ||
> +		    (vcpu->arch.shadow_efer & EFER_LME))
> +			vcpu->arch.shadow_efer = 0;
> +	}
> +
> +	vmx_set_cr0(vcpu, get_shadow_vmcs(vcpu)->guest_cr0);
> +	vmcs_writel(CR0_READ_SHADOW,
> +		    get_shadow_vmcs(vcpu)->cr0_read_shadow);
> +	vmx_set_cr4(vcpu, get_shadow_vmcs(vcpu)->guest_cr4);
> +	vmcs_writel(CR4_READ_SHADOW,
> +		    get_shadow_vmcs(vcpu)->cr4_read_shadow);
> +
> +	vcpu->arch.cr0 |= X86_CR0_PG;
> +
> +	if (enable_ept && !nested_cpu_has_vmx_ept(vcpu)) {
> +		vmcs_write32(GUEST_CR3, get_shadow_vmcs(vcpu)->guest_cr3);
> +		vmx->vcpu.arch.cr3 = get_shadow_vmcs(vcpu)->guest_cr3;
> +	} else {
> +		kvm_set_cr3(vcpu, get_shadow_vmcs(vcpu)->guest_cr3);
> +		kvm_mmu_reset_context(vcpu);
> +
> +		nested_unmap_shadow_vmcs(vcpu);
> +
> +		r = kvm_mmu_load(vcpu);
> +		if (unlikely(r)) {
> +			printk(KERN_ERR "Error in kvm_mmu_load r %d\n", r);
> +			nested_vmx_vmexit(vcpu, false);
> +			set_rflags_to_vmx_fail_valid(vcpu);
> +			return 1;
> +		}
> +
> +		nested_map_shadow_vmcs(vcpu);
> +	}
> +
> +	kvm_register_write(vcpu, VCPU_REGS_RSP,
> +			   get_shadow_vmcs(vcpu)->guest_rsp);
> +	kvm_register_write(vcpu, VCPU_REGS_RIP,
> +			   get_shadow_vmcs(vcpu)->guest_rip);
> +
> +	vmcs_write32(EXCEPTION_BITMAP,
> +		     (vmx->nested.l1_state->shadow_vmcs->exception_bitmap |
> +		      get_shadow_vmcs(vcpu)->exception_bitmap));
> +
> +	nested_unmap_shadow_vmcs(vcpu);
> +
> +	if (initial_pfu_active)
> +		vmx_fpu_activate(vcpu);
> +
> +	return 1;
> +}
> +
> +static int launch_guest(struct kvm_vcpu *vcpu)
> +{
> +	if (!nested_vmx_check_permission(vcpu))
> +		return 1;
> +
> +	skip_emulated_instruction(vcpu);
> +
> +	nested_vmx_run(vcpu);
> +
> +	return 1;
> +}
> +
> +static int nested_vmx_vmexit(struct kvm_vcpu *vcpu,
> +			     bool is_interrupt)
> +{
> +	struct vcpu_vmx *vmx = to_vmx(vcpu);
> +	int initial_pfu_active = vcpu->fpu_active;
> +
> +	if (!vmx->nested.nested_mode) {
> +		printk(KERN_INFO "WARNING: %s called but not in nested mode\n",
> +		       __func__);
> +		return 0;
> +	}
> +
> +	save_msrs(vmx->guest_msrs, vmx->save_nmsrs);
> +
> +	sync_cached_regs_to_vmcs(vcpu);
> +
> +	if (!nested_map_shadow_vmcs(vcpu)) {
> +		printk(KERN_INFO "Error mapping shadow vmcs\n");
> +		set_rflags_to_vmx_fail_valid(vcpu);
Error during vmexit should set abort flag, not change flags.

> +		return 1;
> +	}
> +
> +	prepare_vmcs_12(vcpu);
> +	if (is_interrupt)
> +		get_shadow_vmcs(vcpu)->vm_exit_reason =
> +			EXIT_REASON_EXTERNAL_INTERRUPT;
> +
> +	vmx->nested.l2_state->launched = vmx->launched;
> +	vmx->nested.l2_state->cpu = vcpu->cpu;
> +
> +	nested_unmap_shadow_vmcs(vcpu);
> +
> +	vmx->vmcs = vmx->nested.l1_state->vmcs;
> +	vcpu->cpu = vmx->nested.l1_state->cpu;
> +	vmx->launched = vmx->nested.l1_state->launched;
> +
> +	vmx_vcpu_load(vcpu, get_cpu());
> +	put_cpu();
> +
> +	vcpu->arch.exception.pending = false;
Why need this?

> +
> +	vcpu->arch.shadow_efer = vmx->nested.l1_state->shadow_efer;
> +	vmx_set_cr0(vcpu, vmx->nested.l1_state->shadow_vmcs->cr0_read_shadow);
> +	vmx_set_cr4(vcpu, vmx->nested.l1_state->cr4);
> +
> +	if (enable_ept) {
> +		vcpu->arch.cr3 = vmx->nested.l1_state->shadow_vmcs->guest_cr3;
> +		vmcs_write32(GUEST_CR3, vmx->nested.l1_state->shadow_vmcs->guest_cr3);
> +	} else {
> +		kvm_set_cr3(vcpu, vmx->nested.l1_state->cr3);
> +	}
> +
> +	if (!nested_map_shadow_vmcs(vcpu)) {
> +		printk(KERN_INFO "Error mapping shadow vmcs\n");
> +		set_rflags_to_vmx_fail_valid(vcpu);
Abort not flags.

> +		return 1;
> +	}
> +
> +	switch_back_vmcs(vcpu);
> +
> +	nested_unmap_shadow_vmcs(vcpu);
> +
> +	kvm_register_write(vcpu, VCPU_REGS_RSP,
> +			   vmx->nested.l1_state->shadow_vmcs->guest_rsp);
> +	kvm_register_write(vcpu, VCPU_REGS_RIP,
> +			   vmx->nested.l1_state->shadow_vmcs->guest_rip);
> +
> +	vmx->nested.nested_mode = 0;
> +
> +	kvm_mmu_reset_context(vcpu);
> +	kvm_mmu_load(vcpu);
> +
> +	if (unlikely(vmx->fail)) {
> +		vmx->fail = 0;
> +		set_rflags_to_vmx_fail_valid(vcpu);
> +	} else
> +		clear_rflags_cf_zf(vcpu);
> +
> +	if (initial_pfu_active)
> +		vmx_fpu_activate(vcpu);
> +
> +	return 0;
> +}
> +
> +static int nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu)
> +{
> +	if (to_vmx(vcpu)->nested.nested_mode) {
> +		struct page *msr_page = NULL;
> +		u32 msr_index = vcpu->arch.regs[VCPU_REGS_RCX];
> +		u32 exit_code = vmcs_read32(VM_EXIT_REASON);
> +		struct shadow_vmcs *l2svmcs = get_shadow_vmcs(vcpu);
> +
> +		if (!cpu_has_vmx_msr_bitmap()
> +		    || !nested_cpu_has_vmx_msr_bitmap(vcpu))
> +			return 1;
> +
> +		msr_page = nested_get_page(vcpu,
> +					   l2svmcs->msr_bitmap);
> +
> +		if (!msr_page) {
> +			printk(KERN_INFO "%s error in nested_get_page\n",
> +			       __func__);
> +			return 0;
> +		}
> +
> +		switch (exit_code) {
> +		case EXIT_REASON_MSR_READ:
> +			if (msr_index <= 0x1fff) {
> +				if (test_bit(msr_index,
> +					     (unsigned long *)(msr_page +
> +							       0x000)))
> +					return 1;
> +			} else if ((msr_index >= 0xc0000000) &&
> +				   (msr_index <= 0xc0001fff)) {
> +				msr_index &= 0x1fff;
> +				if (test_bit(msr_index,
> +					     (unsigned long *)(msr_page +
> +							       0x400)))
> +					return 1;
> +			}
> +			break;
> +		case EXIT_REASON_MSR_WRITE:
> +			if (msr_index <= 0x1fff) {
> +				if (test_bit(msr_index,
> +					     (unsigned long *)(msr_page +
> +							       0x800)))
> +						return 1;
> +			} else if ((msr_index >= 0xc0000000) &&
> +				   (msr_index <= 0xc0001fff)) {
> +				msr_index &= 0x1fff;
> +				if (test_bit(msr_index,
> +					     (unsigned long *)(msr_page +
> +							       0xc00)))
> +					return 1;
> +			}
> +			break;
> +		}
> +	}
> +
> +	return 0;
> +}
> +
> +static int nested_vmx_exit_handled(struct kvm_vcpu *vcpu, bool kvm_override)
> +{
> +	u32 exit_code = vmcs_read32(VM_EXIT_REASON);
> +	struct vcpu_vmx *vmx = to_vmx(vcpu);
> +	u32 intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
> +	struct shadow_vmcs *l2svmcs;
> +
> +	int r = 0;
> +
> +	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;
> +	}
> +
> +	if (kvm_override) {
> +		switch (exit_code) {
> +		case EXIT_REASON_EXTERNAL_INTERRUPT:
> +			return 0;
> +		case EXIT_REASON_EXCEPTION_NMI:
> +			if (!is_exception(intr_info))
> +				return 0;
> +
> +			if (is_page_fault(intr_info) && (!enable_ept))
> +				return 0;
> +
> +			break;
> +		case EXIT_REASON_EPT_VIOLATION:
> +			if (enable_ept)
> +				return 0;
> +
> +			break;
> +		}
> +	}
> +
> +
> +	if (!nested_map_shadow_vmcs(vcpu))
> +		return 0;
> +	l2svmcs = get_shadow_vmcs(vcpu);
> +
> +	switch (exit_code) {
> +	case EXIT_REASON_INVLPG:
> +		if (l2svmcs->cpu_based_vm_exec_control &
> +		    CPU_BASED_INVLPG_EXITING)
> +			r = 1;
> +		break;
> +	case EXIT_REASON_MSR_READ:
> +	case EXIT_REASON_MSR_WRITE:
> +		r = nested_vmx_exit_handled_msr(vcpu);
> +		break;
> +	case EXIT_REASON_CR_ACCESS: {
> +		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 (l2svmcs->cr0_guest_host_mask &
> +				    (val ^ l2svmcs->cr0_read_shadow))
> +					r = 1;
> +				break;
> +			case 3:
> +				if (l2svmcs->cpu_based_vm_exec_control &
> +				    CPU_BASED_CR3_LOAD_EXITING)
> +					r = 1;
> +				break;
> +			case 4:
> +				if (l2svmcs->cr4_guest_host_mask &
> +				    (l2svmcs->cr4_read_shadow ^ val))
> +					r = 1;
> +				break;
> +			case 8:
> +				if (l2svmcs->cpu_based_vm_exec_control &
> +				    CPU_BASED_CR8_LOAD_EXITING)
> +					r = 1;
> +				break;
> +			}
> +			break;
> +		case 2: /* clts */
> +			if (l2svmcs->cr0_guest_host_mask &
> +			    (val ^ l2svmcs->cr0_read_shadow))
> +				r = 1;
> +			break;
> +		case 1: /*mov from cr*/
> +			switch (cr) {
> +			case 0:
> +				r = 1;
> +			case 3:
> +				if (l2svmcs->cpu_based_vm_exec_control &
> +				    CPU_BASED_CR3_STORE_EXITING)
> +					r = 1;
> +				break;
> +			case 4:
> +				r = 1;
> +				break;
> +			case 8:
> +				if (l2svmcs->cpu_based_vm_exec_control &
> +				    CPU_BASED_CR8_STORE_EXITING)
> +					r = 1;
> +				break;
> +			}
> +			break;
> +		case 3: /* lmsw */
> +			if (l2svmcs->cr0_guest_host_mask &
> +			    (val ^ l2svmcs->cr0_read_shadow))
> +				r = 1;
> +			break;
> +		}
> +		break;
> +	}
> +	case EXIT_REASON_DR_ACCESS: {
> +		if (l2svmcs->cpu_based_vm_exec_control &
> +		    CPU_BASED_MOV_DR_EXITING)
> +			r = 1;
> +		break;
> +	}
> +
> +	case EXIT_REASON_EXCEPTION_NMI: {
> +
> +		if (is_external_interrupt(intr_info) &&
> +		    (l2svmcs->pin_based_vm_exec_control &
> +		     PIN_BASED_EXT_INTR_MASK))
> +			r = 1;
> +		else if (is_nmi(intr_info) &&
> +		    (l2svmcs->pin_based_vm_exec_control &
> +		     PIN_BASED_NMI_EXITING))
> +			r = 1;
> +		else if (is_exception(intr_info) &&
> +		    (l2svmcs->exception_bitmap &
> +		     (1u << (intr_info & INTR_INFO_VECTOR_MASK))))
> +			r = 1;
> +		else if (is_page_fault(intr_info))
> +			r = 1;
> +		break;
> +	}
> +
> +	case EXIT_REASON_EXTERNAL_INTERRUPT:
> +		if (l2svmcs->pin_based_vm_exec_control &
> +		    PIN_BASED_EXT_INTR_MASK)
> +			r = 1;
> +		break;
> +	default:
> +		r = 1;
> +	}
> +	nested_unmap_shadow_vmcs(vcpu);
> +
> +	return r;
> +}
> +
> +static int nested_vmx_check_exception(struct vcpu_vmx *vmx, unsigned nr,
> +				      bool has_error_code, u32 error_code)
> +{
> +	if (vmx->nested.nested_mode) {
> +		if (nested_vmx_exit_handled(&vmx->vcpu, false)) {
> +			nested_vmx_vmexit(&vmx->vcpu, false);
> +			if (!nested_map_shadow_vmcs(&vmx->vcpu))
> +				return 1;
> +			get_shadow_vmcs(&vmx->vcpu)->vm_exit_reason =
> +				EXIT_REASON_EXCEPTION_NMI;
> +			get_shadow_vmcs(&vmx->vcpu)->vm_exit_intr_info =
> +				(nr | INTR_TYPE_HARD_EXCEPTION
> +				 | (has_error_code ?
> +				    INTR_INFO_DELIVER_CODE_MASK : 0)
> +				 | INTR_INFO_VALID_MASK);
> +
> +			if (has_error_code)
> +				get_shadow_vmcs(&vmx->vcpu)->
> +					vm_exit_intr_error_code = error_code;
> +			nested_unmap_shadow_vmcs(&vmx->vcpu);
> +			return 1;
> +		}
> +	}
> +	return 0;
> +}
> +
> +static int nested_vmx_intr(struct kvm_vcpu *vcpu)
> +{
> +	struct vcpu_vmx *vmx = to_vmx(vcpu);
> +
> +	if (vmx->nested.nested_mode) {
This function is called only after checking nested_mode. Why recheck?

> +
> +		if (!nested_map_shadow_vmcs(vcpu))
> +			return 0;
> +
> +		if (get_shadow_vmcs(vcpu)->pin_based_vm_exec_control &
> +		    PIN_BASED_EXT_INTR_MASK) {
> +
> +			if (vmx->nested.nested_run_pending) {
> +				nested_unmap_shadow_vmcs(vcpu);
> +				return 0;
> +			}
> +
> +			nested_unmap_shadow_vmcs(vcpu);
> +			nested_vmx_vmexit(vcpu, true);
> +			return 1;		
> +		}
> +
> +		nested_unmap_shadow_vmcs(vcpu);
> +
> +	}
> +
> +	return 0;
> +}
>  
>  static struct kvm_x86_ops vmx_x86_ops = {
>  	.cpu_has_kvm_support = cpu_has_kvm_support,
> -- 
> 1.6.0.4
> 
> --
> To unsubscribe from this list: send the line "unsubscribe kvm" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html

--
			Gleb.