From patchwork Thu Dec 10 18:38:26 2009 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: oritw@il.ibm.com X-Patchwork-Id: 66324 Received: from vger.kernel.org (vger.kernel.org [209.132.176.167]) by demeter.kernel.org (8.14.2/8.14.2) with ESMTP id nBAIcjCF003688 for ; Thu, 10 Dec 2009 18:38:46 GMT Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1761424AbZLJSif (ORCPT ); Thu, 10 Dec 2009 13:38:35 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1761404AbZLJSif (ORCPT ); Thu, 10 Dec 2009 13:38:35 -0500 Received: from mtagate2.de.ibm.com ([195.212.17.162]:38344 "EHLO mtagate2.de.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1761412AbZLJSi3 (ORCPT ); Thu, 10 Dec 2009 13:38:29 -0500 Received: from d12nrmr1607.megacenter.de.ibm.com (d12nrmr1607.megacenter.de.ibm.com [9.149.167.49]) by mtagate2.de.ibm.com (8.13.1/8.13.1) with ESMTP id nBAIcYkO010013 for ; Thu, 10 Dec 2009 18:38:34 GMT Received: from d12av02.megacenter.de.ibm.com (d12av02.megacenter.de.ibm.com [9.149.165.228]) by d12nrmr1607.megacenter.de.ibm.com (8.13.8/8.13.8/NCO v10.0) with ESMTP id nBAIcYsP1151030 for ; Thu, 10 Dec 2009 19:38:34 +0100 Received: from d12av02.megacenter.de.ibm.com (loopback [127.0.0.1]) by d12av02.megacenter.de.ibm.com (8.12.11.20060308/8.13.3) with ESMTP id nBAIcYUo005112 for ; Thu, 10 Dec 2009 19:38:34 +0100 Received: from localhost.localdomain (cluwyn.haifa.ibm.com [9.148.27.75]) by d12av02.megacenter.de.ibm.com (8.12.11.20060308/8.12.11) with ESMTP id nBAIcUFm004785; Thu, 10 Dec 2009 19:38:33 +0100 From: oritw@il.ibm.com To: avi@redhat.com Cc: kvm@vger.kernel.org, oritw@il.ibm.com, benami@il.ibm.com, abelg@il.ibm.com, muli@il.ibm.com, aliguori@us.ibm.com, mdday@us.ibm.com Subject: [PATCH 4/7] Nested VMX patch 4 implements vmread and vmwrite Date: Thu, 10 Dec 2009 20:38:26 +0200 Message-Id: <1260470309-7166-5-git-send-email-oritw@il.ibm.com> X-Mailer: git-send-email 1.6.0.4 In-Reply-To: <1260470309-7166-4-git-send-email-oritw@il.ibm.com> References: <1260470309-7166-1-git-send-email-oritw@il.ibm.com> <1260470309-7166-2-git-send-email-oritw@il.ibm.com> <1260470309-7166-3-git-send-email-oritw@il.ibm.com> <1260470309-7166-4-git-send-email-oritw@il.ibm.com> Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 46a4f3a..8745d44 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -239,6 +239,7 @@ struct __attribute__ ((__packed__)) level_state { struct __attribute__ ((__packed__)) nested_vmcs_page { u32 revision_id; u32 abort; + struct shadow_vmcs shadow_vmcs; struct level_state l2_state; }; @@ -263,6 +264,55 @@ struct nested_vmx { struct nested_vmcs_page *current_l2_page; }; +enum vmcs_field_type { + VMCS_FIELD_TYPE_U16 = 0, + VMCS_FIELD_TYPE_U64 = 1, + VMCS_FIELD_TYPE_U32 = 2, + VMCS_FIELD_TYPE_ULONG = 3 +}; + +#define VMCS_FIELD_LENGTH_OFFSET 13 +#define VMCS_FIELD_LENGTH_MASK 0x6000 + +/* + Returns VMCS Field type +*/ +static inline int vmcs_field_type(unsigned long field) +{ + /* For 32 bit L1 when it using the HIGH field */ + if (0x1 & field) + return VMCS_FIELD_TYPE_U32; + + return (VMCS_FIELD_LENGTH_MASK & field) >> 13; +} + +/* + Returncs VMCS field size in bits +*/ +static inline int vmcs_field_size(int field_type, struct kvm_vcpu *vcpu) +{ + switch (field_type) { + case VMCS_FIELD_TYPE_U16: + return 2; + case VMCS_FIELD_TYPE_U32: + return 4; + case VMCS_FIELD_TYPE_U64: + return 8; + case VMCS_FIELD_TYPE_ULONG: +#ifdef CONFIG_X86_64 + if (is_long_mode(vcpu)) + return 8; + else + return 4; +#else + return 4; +#endif + } + + printk(KERN_INFO "WARNING: invalid field type %d \n", field_type); + return 0; +} + struct vcpu_vmx { struct kvm_vcpu vcpu; struct list_head local_vcpus_link; @@ -317,6 +367,411 @@ 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.current_l2_page); + return &(to_vmx(vcpu)->nested.current_l2_page->shadow_vmcs); +} + +#define SHADOW_VMCS_OFFSET(x) offsetof(struct shadow_vmcs, x) + +static unsigned short vmcs_field_to_offset_table[HOST_RIP+1] = { + + [VIRTUAL_PROCESSOR_ID] = + SHADOW_VMCS_OFFSET(virtual_processor_id), + [GUEST_ES_SELECTOR] = + SHADOW_VMCS_OFFSET(guest_es_selector), + [GUEST_CS_SELECTOR] = + SHADOW_VMCS_OFFSET(guest_cs_selector), + [GUEST_SS_SELECTOR] = + SHADOW_VMCS_OFFSET(guest_ss_selector), + [GUEST_DS_SELECTOR] = + SHADOW_VMCS_OFFSET(guest_ds_selector), + [GUEST_FS_SELECTOR] = + SHADOW_VMCS_OFFSET(guest_fs_selector), + [GUEST_GS_SELECTOR] = + SHADOW_VMCS_OFFSET(guest_gs_selector), + [GUEST_LDTR_SELECTOR] = + SHADOW_VMCS_OFFSET(guest_ldtr_selector), + [GUEST_TR_SELECTOR] = + SHADOW_VMCS_OFFSET(guest_tr_selector), + [HOST_ES_SELECTOR] = + SHADOW_VMCS_OFFSET(host_es_selector), + [HOST_CS_SELECTOR] = + SHADOW_VMCS_OFFSET(host_cs_selector), + [HOST_SS_SELECTOR] = + SHADOW_VMCS_OFFSET(host_ss_selector), + [HOST_DS_SELECTOR] = + SHADOW_VMCS_OFFSET(host_ds_selector), + [HOST_FS_SELECTOR] = + SHADOW_VMCS_OFFSET(host_fs_selector), + [HOST_GS_SELECTOR] = + SHADOW_VMCS_OFFSET(host_gs_selector), + [HOST_TR_SELECTOR] = + SHADOW_VMCS_OFFSET(host_tr_selector), + [IO_BITMAP_A] = + SHADOW_VMCS_OFFSET(io_bitmap_a), + [IO_BITMAP_A_HIGH] = + SHADOW_VMCS_OFFSET(io_bitmap_a)+4, + [IO_BITMAP_B] = + SHADOW_VMCS_OFFSET(io_bitmap_b), + [IO_BITMAP_B_HIGH] = + SHADOW_VMCS_OFFSET(io_bitmap_b)+4, + [MSR_BITMAP] = + SHADOW_VMCS_OFFSET(msr_bitmap), + [MSR_BITMAP_HIGH] = + SHADOW_VMCS_OFFSET(msr_bitmap)+4, + [VM_EXIT_MSR_STORE_ADDR] = + SHADOW_VMCS_OFFSET(vm_exit_msr_store_addr), + [VM_EXIT_MSR_STORE_ADDR_HIGH] = + SHADOW_VMCS_OFFSET(vm_exit_msr_store_addr)+4, + [VM_EXIT_MSR_LOAD_ADDR] = + SHADOW_VMCS_OFFSET(vm_exit_msr_load_addr), + [VM_EXIT_MSR_LOAD_ADDR_HIGH] = + SHADOW_VMCS_OFFSET(vm_exit_msr_load_addr)+4, + [VM_ENTRY_MSR_LOAD_ADDR] = + SHADOW_VMCS_OFFSET(vm_entry_msr_load_addr), + [VM_ENTRY_MSR_LOAD_ADDR_HIGH] = + SHADOW_VMCS_OFFSET(vm_entry_msr_load_addr)+4, + [TSC_OFFSET] = + SHADOW_VMCS_OFFSET(tsc_offset), + [TSC_OFFSET_HIGH] = + SHADOW_VMCS_OFFSET(tsc_offset)+4, + [VIRTUAL_APIC_PAGE_ADDR] = + SHADOW_VMCS_OFFSET(virtual_apic_page_addr), + [VIRTUAL_APIC_PAGE_ADDR_HIGH] = + SHADOW_VMCS_OFFSET(virtual_apic_page_addr)+4, + [APIC_ACCESS_ADDR] = + SHADOW_VMCS_OFFSET(apic_access_addr), + [APIC_ACCESS_ADDR_HIGH] = + SHADOW_VMCS_OFFSET(apic_access_addr)+4, + [EPT_POINTER] = + SHADOW_VMCS_OFFSET(ept_pointer), + [EPT_POINTER_HIGH] = + SHADOW_VMCS_OFFSET(ept_pointer)+4, + [GUEST_PHYSICAL_ADDRESS] = + SHADOW_VMCS_OFFSET(guest_physical_address), + [GUEST_PHYSICAL_ADDRESS_HIGH] = + SHADOW_VMCS_OFFSET(guest_physical_address)+4, + [VMCS_LINK_POINTER] = + SHADOW_VMCS_OFFSET(vmcs_link_pointer), + [VMCS_LINK_POINTER_HIGH] = + SHADOW_VMCS_OFFSET(vmcs_link_pointer)+4, + [GUEST_IA32_DEBUGCTL] = + SHADOW_VMCS_OFFSET(guest_ia32_debugctl), + [GUEST_IA32_DEBUGCTL_HIGH] = + SHADOW_VMCS_OFFSET(guest_ia32_debugctl)+4, + [GUEST_IA32_PAT] = + SHADOW_VMCS_OFFSET(guest_ia32_pat), + [GUEST_IA32_PAT_HIGH] = + SHADOW_VMCS_OFFSET(guest_ia32_pat)+4, + [GUEST_PDPTR0] = + SHADOW_VMCS_OFFSET(guest_pdptr0), + [GUEST_PDPTR0_HIGH] = + SHADOW_VMCS_OFFSET(guest_pdptr0)+4, + [GUEST_PDPTR1] = + SHADOW_VMCS_OFFSET(guest_pdptr1), + [GUEST_PDPTR1_HIGH] = + SHADOW_VMCS_OFFSET(guest_pdptr1)+4, + [GUEST_PDPTR2] = + SHADOW_VMCS_OFFSET(guest_pdptr2), + [GUEST_PDPTR2_HIGH] = + SHADOW_VMCS_OFFSET(guest_pdptr2)+4, + [GUEST_PDPTR3] = + SHADOW_VMCS_OFFSET(guest_pdptr3), + [GUEST_PDPTR3_HIGH] = + SHADOW_VMCS_OFFSET(guest_pdptr3)+4, + [HOST_IA32_PAT] = + SHADOW_VMCS_OFFSET(host_ia32_pat), + [HOST_IA32_PAT_HIGH] = + SHADOW_VMCS_OFFSET(host_ia32_pat)+4, + [PIN_BASED_VM_EXEC_CONTROL] = + SHADOW_VMCS_OFFSET(pin_based_vm_exec_control), + [CPU_BASED_VM_EXEC_CONTROL] = + SHADOW_VMCS_OFFSET(cpu_based_vm_exec_control), + [EXCEPTION_BITMAP] = + SHADOW_VMCS_OFFSET(exception_bitmap), + [PAGE_FAULT_ERROR_CODE_MASK] = + SHADOW_VMCS_OFFSET(page_fault_error_code_mask), + [PAGE_FAULT_ERROR_CODE_MATCH] = + SHADOW_VMCS_OFFSET(page_fault_error_code_match), + [CR3_TARGET_COUNT] = + SHADOW_VMCS_OFFSET(cr3_target_count), + [VM_EXIT_CONTROLS] = + SHADOW_VMCS_OFFSET(vm_exit_controls), + [VM_EXIT_MSR_STORE_COUNT] = + SHADOW_VMCS_OFFSET(vm_exit_msr_store_count), + [VM_EXIT_MSR_LOAD_COUNT] = + SHADOW_VMCS_OFFSET(vm_exit_msr_load_count), + [VM_ENTRY_CONTROLS] = + SHADOW_VMCS_OFFSET(vm_entry_controls), + [VM_ENTRY_MSR_LOAD_COUNT] = + SHADOW_VMCS_OFFSET(vm_entry_msr_load_count), + [VM_ENTRY_INTR_INFO_FIELD] = + SHADOW_VMCS_OFFSET(vm_entry_intr_info_field), + [VM_ENTRY_EXCEPTION_ERROR_CODE] = + SHADOW_VMCS_OFFSET(vm_entry_exception_error_code), + [VM_ENTRY_INSTRUCTION_LEN] = + SHADOW_VMCS_OFFSET(vm_entry_instruction_len), + [TPR_THRESHOLD] = + SHADOW_VMCS_OFFSET(tpr_threshold), + [SECONDARY_VM_EXEC_CONTROL] = + SHADOW_VMCS_OFFSET(secondary_vm_exec_control), + [VM_INSTRUCTION_ERROR] = + SHADOW_VMCS_OFFSET(vm_instruction_error), + [VM_EXIT_REASON] = + SHADOW_VMCS_OFFSET(vm_exit_reason), + [VM_EXIT_INTR_INFO] = + SHADOW_VMCS_OFFSET(vm_exit_intr_info), + [VM_EXIT_INTR_ERROR_CODE] = + SHADOW_VMCS_OFFSET(vm_exit_intr_error_code), + [IDT_VECTORING_INFO_FIELD] = + SHADOW_VMCS_OFFSET(idt_vectoring_info_field), + [IDT_VECTORING_ERROR_CODE] = + SHADOW_VMCS_OFFSET(idt_vectoring_error_code), + [VM_EXIT_INSTRUCTION_LEN] = + SHADOW_VMCS_OFFSET(vm_exit_instruction_len), + [VMX_INSTRUCTION_INFO] = + SHADOW_VMCS_OFFSET(vmx_instruction_info), + [GUEST_ES_LIMIT] = + SHADOW_VMCS_OFFSET(guest_es_limit), + [GUEST_CS_LIMIT] = + SHADOW_VMCS_OFFSET(guest_cs_limit), + [GUEST_SS_LIMIT] = + SHADOW_VMCS_OFFSET(guest_ss_limit), + [GUEST_DS_LIMIT] = + SHADOW_VMCS_OFFSET(guest_ds_limit), + [GUEST_FS_LIMIT] = + SHADOW_VMCS_OFFSET(guest_fs_limit), + [GUEST_GS_LIMIT] = + SHADOW_VMCS_OFFSET(guest_gs_limit), + [GUEST_LDTR_LIMIT] = + SHADOW_VMCS_OFFSET(guest_ldtr_limit), + [GUEST_TR_LIMIT] = + SHADOW_VMCS_OFFSET(guest_tr_limit), + [GUEST_GDTR_LIMIT] = + SHADOW_VMCS_OFFSET(guest_gdtr_limit), + [GUEST_IDTR_LIMIT] = + SHADOW_VMCS_OFFSET(guest_idtr_limit), + [GUEST_ES_AR_BYTES] = + SHADOW_VMCS_OFFSET(guest_es_ar_bytes), + [GUEST_CS_AR_BYTES] = + SHADOW_VMCS_OFFSET(guest_cs_ar_bytes), + [GUEST_SS_AR_BYTES] = + SHADOW_VMCS_OFFSET(guest_ss_ar_bytes), + [GUEST_DS_AR_BYTES] = + SHADOW_VMCS_OFFSET(guest_ds_ar_bytes), + [GUEST_FS_AR_BYTES] = + SHADOW_VMCS_OFFSET(guest_fs_ar_bytes), + [GUEST_GS_AR_BYTES] = + SHADOW_VMCS_OFFSET(guest_gs_ar_bytes), + [GUEST_LDTR_AR_BYTES] = + SHADOW_VMCS_OFFSET(guest_ldtr_ar_bytes), + [GUEST_TR_AR_BYTES] = + SHADOW_VMCS_OFFSET(guest_tr_ar_bytes), + [GUEST_INTERRUPTIBILITY_INFO] = + SHADOW_VMCS_OFFSET(guest_interruptibility_info), + [GUEST_ACTIVITY_STATE] = + SHADOW_VMCS_OFFSET(guest_activity_state), + [GUEST_SYSENTER_CS] = + SHADOW_VMCS_OFFSET(guest_sysenter_cs), + [HOST_IA32_SYSENTER_CS] = + SHADOW_VMCS_OFFSET(host_ia32_sysenter_cs), + [CR0_GUEST_HOST_MASK] = + SHADOW_VMCS_OFFSET(cr0_guest_host_mask), + [CR4_GUEST_HOST_MASK] = + SHADOW_VMCS_OFFSET(cr4_guest_host_mask), + [CR0_READ_SHADOW] = + SHADOW_VMCS_OFFSET(cr0_read_shadow), + [CR4_READ_SHADOW] = + SHADOW_VMCS_OFFSET(cr4_read_shadow), + [CR3_TARGET_VALUE0] = + SHADOW_VMCS_OFFSET(cr3_target_value0), + [CR3_TARGET_VALUE1] = + SHADOW_VMCS_OFFSET(cr3_target_value1), + [CR3_TARGET_VALUE2] = + SHADOW_VMCS_OFFSET(cr3_target_value2), + [CR3_TARGET_VALUE3] = + SHADOW_VMCS_OFFSET(cr3_target_value3), + [EXIT_QUALIFICATION] = + SHADOW_VMCS_OFFSET(exit_qualification), + [GUEST_LINEAR_ADDRESS] = + SHADOW_VMCS_OFFSET(guest_linear_address), + [GUEST_CR0] = + SHADOW_VMCS_OFFSET(guest_cr0), + [GUEST_CR3] = + SHADOW_VMCS_OFFSET(guest_cr3), + [GUEST_CR4] = + SHADOW_VMCS_OFFSET(guest_cr4), + [GUEST_ES_BASE] = + SHADOW_VMCS_OFFSET(guest_es_base), + [GUEST_CS_BASE] = + SHADOW_VMCS_OFFSET(guest_cs_base), + [GUEST_SS_BASE] = + SHADOW_VMCS_OFFSET(guest_ss_base), + [GUEST_DS_BASE] = + SHADOW_VMCS_OFFSET(guest_ds_base), + [GUEST_FS_BASE] = + SHADOW_VMCS_OFFSET(guest_fs_base), + [GUEST_GS_BASE] = + SHADOW_VMCS_OFFSET(guest_gs_base), + [GUEST_LDTR_BASE] = + SHADOW_VMCS_OFFSET(guest_ldtr_base), + [GUEST_TR_BASE] = + SHADOW_VMCS_OFFSET(guest_tr_base), + [GUEST_GDTR_BASE] = + SHADOW_VMCS_OFFSET(guest_gdtr_base), + [GUEST_IDTR_BASE] = + SHADOW_VMCS_OFFSET(guest_idtr_base), + [GUEST_DR7] = + SHADOW_VMCS_OFFSET(guest_dr7), + [GUEST_RSP] = + SHADOW_VMCS_OFFSET(guest_rsp), + [GUEST_RIP] = + SHADOW_VMCS_OFFSET(guest_rip), + [GUEST_RFLAGS] = + SHADOW_VMCS_OFFSET(guest_rflags), + [GUEST_PENDING_DBG_EXCEPTIONS] = + SHADOW_VMCS_OFFSET(guest_pending_dbg_exceptions), + [GUEST_SYSENTER_ESP] = + SHADOW_VMCS_OFFSET(guest_sysenter_esp), + [GUEST_SYSENTER_EIP] = + SHADOW_VMCS_OFFSET(guest_sysenter_eip), + [HOST_CR0] = + SHADOW_VMCS_OFFSET(host_cr0), + [HOST_CR3] = + SHADOW_VMCS_OFFSET(host_cr3), + [HOST_CR4] = + SHADOW_VMCS_OFFSET(host_cr4), + [HOST_FS_BASE] = + SHADOW_VMCS_OFFSET(host_fs_base), + [HOST_GS_BASE] = + SHADOW_VMCS_OFFSET(host_gs_base), + [HOST_TR_BASE] = + SHADOW_VMCS_OFFSET(host_tr_base), + [HOST_GDTR_BASE] = + SHADOW_VMCS_OFFSET(host_gdtr_base), + [HOST_IDTR_BASE] = + SHADOW_VMCS_OFFSET(host_idtr_base), + [HOST_IA32_SYSENTER_ESP] = + SHADOW_VMCS_OFFSET(host_ia32_sysenter_esp), + [HOST_IA32_SYSENTER_EIP] = + SHADOW_VMCS_OFFSET(host_ia32_sysenter_eip), + [HOST_RSP] = + SHADOW_VMCS_OFFSET(host_rsp), + [HOST_RIP] = + SHADOW_VMCS_OFFSET(host_rip), +}; + +static inline unsigned short vmcs_field_to_offset(unsigned long field) +{ + + if (field > HOST_RIP || vmcs_field_to_offset_table[field] == 0) { + printk(KERN_ERR "invalid vmcs encoding 0x%lx\n", field); + return -1; + } + + return vmcs_field_to_offset_table[field]; +} + +static inline unsigned long nested_vmcs_readl(struct kvm_vcpu *vcpu, + unsigned long field) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + unsigned long *entry; + + if (!vmx->nested.current_l2_page) { + printk(KERN_ERR "%s invalid nested vmcs\n", __func__); + return -1; + } + + entry = (unsigned long *)((char *)(get_shadow_vmcs(vcpu)) + + vmcs_field_to_offset(field)); + return *entry; +} + +static inline u16 nested_vmcs_read16(struct kvm_vcpu *vcpu, + unsigned long field) +{ + return nested_vmcs_readl(vcpu, field); +} + +static inline u32 nested_vmcs_read32(struct kvm_vcpu *vcpu, unsigned long field) +{ + return nested_vmcs_readl(vcpu, field); +} + +static inline u64 nested_vmcs_read64(struct kvm_vcpu *vcpu, unsigned long field) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + u64 *entry; + if (!vmx->nested.current_l2_page) { + printk(KERN_ERR "%s invalid nested vmcs\n", __func__); + return -1; + } + + entry = (u64 *)((char *)(get_shadow_vmcs(vcpu)) + + vmcs_field_to_offset(field)); + return *entry; +} + +static inline void nested_vmcs_writel(struct kvm_vcpu *vcpu, + unsigned long field, unsigned long value) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + unsigned long entry = + (unsigned long)(get_shadow_vmcs(vcpu)); + + if (!vmx->nested.current_l2_page) { + printk(KERN_ERR "%s invalid nested vmcs\n", __func__); + return; + } + + entry += vmcs_field_to_offset(field); + *(unsigned long *)entry = value; +} + +static inline void nested_vmcs_write16(struct kvm_vcpu *vcpu, + unsigned long field, u16 value) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + unsigned long entry = + (unsigned long)(get_shadow_vmcs(vcpu)); + + if (!vmx->nested.current_l2_page) { + printk(KERN_ERR "%s invalid nested vmcs\n", __func__); + return; + } + entry += vmcs_field_to_offset(field); + *(u16 *)entry = value; +} + +static inline void nested_vmcs_write32(struct kvm_vcpu *vcpu, + unsigned long field, u32 value) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + unsigned long entry = + (unsigned long)(get_shadow_vmcs(vcpu)); + + if (!vmx->nested.current_l2_page) { + printk(KERN_ERR "%s invalid nested vmcs\n", __func__); + return; + } + entry += vmcs_field_to_offset(field); + *(u32 *)entry = value; +} + +static inline void nested_vmcs_write64(struct kvm_vcpu *vcpu, + unsigned long field, u64 value) +{ +#ifdef CONFIG_X86_64 + nested_vmcs_writel(vcpu, field, value); +#else /* nested: 32 bit not actually tested */ + nested_vmcs_writel(vcpu, field, value); + nested_vmcs_writel(vcpu, field+1, value >> 32); +#endif +} + static struct page *nested_get_page(struct kvm_vcpu *vcpu, u64 vmcs_addr) { @@ -354,11 +809,6 @@ static int nested_map_current(struct kvm_vcpu *vcpu) mapped_page = kmap_atomic(vmcs_page, KM_USER0); - if (!mapped_page) { - printk(KERN_INFO "%s: error in kmap_atomic\n", __func__); - return 0; - } - vmx->nested.current_l2_page = mapped_page; return 1; @@ -1390,7 +1840,7 @@ static int read_guest_vmcs_gpa(struct kvm_vcpu *vcpu, gva_t gva, u64 *gentry) size, vcpu); if (r) { printk(KERN_ERR "%s cannot read guest vmcs addr %lx : %d\n", - __func__, vcpu->arch.regs[VCPU_REGS_RAX], r); + __func__, gva, r); return r; } @@ -3764,6 +4214,26 @@ static gva_t get_vmx_mem_address(struct kvm_vcpu *vcpu, return addr; } +static void set_rflags_to_vmx_fail_invalid(struct kvm_vcpu *vcpu) +{ + unsigned long rflags; + rflags = vmx_get_rflags(vcpu); + rflags |= X86_EFLAGS_CF; + rflags &= ~X86_EFLAGS_PF & ~X86_EFLAGS_AF & ~X86_EFLAGS_ZF & + ~X86_EFLAGS_SF & ~X86_EFLAGS_OF; + vmx_set_rflags(vcpu, rflags); +} + +static void set_rflags_to_vmx_fail_valid(struct kvm_vcpu *vcpu) +{ + unsigned long rflags; + rflags = vmx_get_rflags(vcpu); + rflags |= X86_EFLAGS_ZF; + rflags &= ~X86_EFLAGS_PF & ~X86_EFLAGS_AF & ~X86_EFLAGS_CF & + ~X86_EFLAGS_SF & ~X86_EFLAGS_OF; + vmx_set_rflags(vcpu, rflags); + } + static int handle_vmclear(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -3800,6 +4270,181 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) return 1; } +static int handle_vmread_reg(struct kvm_vcpu *vcpu, int reg, + unsigned long field) +{ + u64 field_value; + + switch (vmcs_field_type(field)) { + case VMCS_FIELD_TYPE_U16: + field_value = nested_vmcs_read16(vcpu, field); + break; + case VMCS_FIELD_TYPE_U32: + field_value = nested_vmcs_read32(vcpu, field); + break; + case VMCS_FIELD_TYPE_U64: + field_value = nested_vmcs_read64(vcpu, field); +#ifdef CONFIG_X86_64 + if (!is_long_mode(vcpu)) { + kvm_register_write(vcpu, reg+1, field_value >> 32); + field_value = (u32)field_value; + } +#endif + break; + case VMCS_FIELD_TYPE_ULONG: + field_value = nested_vmcs_readl(vcpu, field); +#ifdef CONFIG_X86_64 + if (!is_long_mode(vcpu)) { + kvm_register_write(vcpu, reg+1, field_value >> 32); + field_value = (u32)field_value; + } +#endif + break; + default: + printk(KERN_INFO "%s invalid field\n", __func__); + return 0; + } + + kvm_register_write(vcpu, reg, field_value); + return 1; +} + +static int handle_vmread_mem(struct kvm_vcpu *vcpu, gva_t gva, + unsigned long field) +{ + u64 field_value; + + switch (vmcs_field_type(field)) { + case VMCS_FIELD_TYPE_U16: + field_value = nested_vmcs_read16(vcpu, field); + break; + case VMCS_FIELD_TYPE_U32: + field_value = nested_vmcs_read32(vcpu, field); + break; + case VMCS_FIELD_TYPE_U64: + field_value = nested_vmcs_read64(vcpu, field); + break; + case VMCS_FIELD_TYPE_ULONG: + field_value = nested_vmcs_readl(vcpu, field); + break; + default: + printk(KERN_INFO "%s invalid field\n", __func__); + return 0; + } + + kvm_write_guest_virt(gva, &field_value, + vmcs_field_size(vmcs_field_type(field), vcpu), + vcpu); + return 1; +} + +static int handle_vmread(struct kvm_vcpu *vcpu) +{ + unsigned long field; + int reg; + int is_reg; + unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); + gva_t gva = 0; + int read_succeed; + + if (!nested_vmx_check_permission(vcpu)) + return 1; + + if (!nested_map_current(vcpu)) { + printk(KERN_INFO "%s invalid shadow vmcs\n", __func__); + set_rflags_to_vmx_fail_invalid(vcpu); + return 1; + } + + /* decode instruction info to get the field to read and where to store its value */ + /* Bit 10, Mem/Reg (0 = memory, 1 = register) */ + is_reg = vmx_instruction_info & (1u << 10); /* bit 10 */ + field = kvm_register_read(vcpu, (vmx_instruction_info >> 28) & 0xf); /* bits 31:28 */ + + if (is_reg) { + reg = (vmx_instruction_info >> 3) & 0xf; /* bits 3:6 */ + read_succeed = handle_vmread_reg(vcpu, reg, field); + } else { + gva = get_vmx_mem_address(vcpu, exit_qualification, + vmx_instruction_info); + read_succeed = handle_vmread_mem(vcpu, gva, field); + } + + if (read_succeed) { + clear_rflags_cf_zf(vcpu); + skip_emulated_instruction(vcpu); + } else { + set_rflags_to_vmx_fail_valid(vcpu); + vmcs_write32(VM_INSTRUCTION_ERROR, 12); + } + + nested_unmap_current(vcpu); + return 1; +} + + +static int handle_vmwrite(struct kvm_vcpu *vcpu) +{ + unsigned long field; + u64 field_value = 0; + int reg; + int is_reg; + gva_t gva; + int field_type; + unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); + + if (!nested_vmx_check_permission(vcpu)) + return 1; + + if (!nested_map_current(vcpu)) { + printk(KERN_INFO "%s invalid shadow vmcs\n", __func__); + set_rflags_to_vmx_fail_invalid(vcpu); + return 1; + } + + /* decode instruction info to get the field to read and where to store its value */ + /* Bit 10, Mem/Reg (0 = memory, 1 = register */ + is_reg = vmx_instruction_info & (1u << 10); /* bit 10 */ + reg = (vmx_instruction_info >> 3) & 0xf; /* bits 3:6 */ + field = kvm_register_read(vcpu, (vmx_instruction_info >> 28) & 0xf); /* bits 31:28 */ + field_type = vmcs_field_type(field); + + if (is_reg) + field_value = kvm_register_read(vcpu, reg); + else { + gva = get_vmx_mem_address(vcpu, exit_qualification, vmx_instruction_info); + kvm_read_guest_virt(gva, &field_value, vmcs_field_size(field_type, vcpu), vcpu); + } + + switch (field_type) { + case VMCS_FIELD_TYPE_U16: + nested_vmcs_write16(vcpu, field, field_value); + break; + case VMCS_FIELD_TYPE_U32: + nested_vmcs_write32(vcpu, field, field_value); + break; + case VMCS_FIELD_TYPE_U64: + nested_vmcs_write64(vcpu, field, field_value); + break; + case VMCS_FIELD_TYPE_ULONG: + nested_vmcs_writel(vcpu, field, field_value); + break; + default: + printk(KERN_INFO "%s invalid field\n", __func__); + set_rflags_to_vmx_fail_valid(vcpu); + vmcs_write32(VM_INSTRUCTION_ERROR, 12); + nested_unmap_current(vcpu); + return 1; + } + + clear_rflags_cf_zf(vcpu); + skip_emulated_instruction(vcpu); + nested_unmap_current(vcpu); + return 1; +} + static int handle_vmoff(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -3901,15 +4546,20 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu) unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); gva_t vmcs_gva; - + uint size; if (!nested_vmx_check_permission(vcpu)) return 1; vmcs_gva = get_vmx_mem_address(vcpu, exit_qualification, vmx_instruction_info); + if (is_long_mode(vcpu)) + size = sizeof(u64); + else + size = sizeof(u32); + r = kvm_write_guest_virt(vmcs_gva, (void *)&to_vmx(vcpu)->nested.current_vmptr, - sizeof(u64), vcpu); + size, vcpu); if (r) { printk(KERN_INFO "%s failed to write vmptr\n", __func__); return 1; @@ -4206,9 +4856,9 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_VMLAUNCH] = handle_vmx_insn, [EXIT_REASON_VMPTRLD] = handle_vmptrld, [EXIT_REASON_VMPTRST] = handle_vmptrst, - [EXIT_REASON_VMREAD] = handle_vmx_insn, + [EXIT_REASON_VMREAD] = handle_vmread, [EXIT_REASON_VMRESUME] = handle_vmx_insn, - [EXIT_REASON_VMWRITE] = handle_vmx_insn, + [EXIT_REASON_VMWRITE] = handle_vmwrite, [EXIT_REASON_VMOFF] = handle_vmoff, [EXIT_REASON_VMON] = handle_vmon, [EXIT_REASON_TPR_BELOW_THRESHOLD] = handle_tpr_below_threshold,