From patchwork Sun Jul 11 08:27:03 2010 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Nadav Har'El X-Patchwork-Id: 111276 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by demeter.kernel.org (8.14.4/8.14.3) with ESMTP id o6B8RQw0021051 for ; Sun, 11 Jul 2010 08:27:26 GMT Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752188Ab0GKI1R (ORCPT ); Sun, 11 Jul 2010 04:27:17 -0400 Received: from mailgw11.technion.ac.il ([132.68.225.11]:32125 "EHLO mailgw11.technion.ac.il" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751978Ab0GKI1J (ORCPT ); Sun, 11 Jul 2010 04:27:09 -0400 X-IronPort-Anti-Spam-Filtered: true X-IronPort-Anti-Spam-Result: AvsEAG8dOUyERHMG/2dsb2JhbACgP3G8ZwKFJQSDdoRW X-IronPort-AV: E=Sophos;i="4.55,182,1278277200"; d="scan'208";a="12118313" Received: from fermat.math.technion.ac.il ([132.68.115.6]) by mailgw11.technion.ac.il with ESMTP; 11 Jul 2010 11:27:06 +0300 Received: from fermat.math.technion.ac.il (localhost [127.0.0.1]) by fermat.math.technion.ac.il (8.12.10/8.12.10) with ESMTP id o6B8R4cQ002990; Sun, 11 Jul 2010 11:27:04 +0300 (IDT) Received: (from nyh@localhost) by fermat.math.technion.ac.il (8.12.10/8.12.10/Submit) id o6B8R3sE002989; Sun, 11 Jul 2010 11:27:03 +0300 (IDT) X-Authentication-Warning: fermat.math.technion.ac.il: nyh set sender to nyh@math.technion.ac.il using -f Date: Sun, 11 Jul 2010 11:27:03 +0300 From: "Nadav Har'El" To: "Dong, Eddie" Cc: "avi@redhat.com" , "kvm@vger.kernel.org" Subject: Re: [PATCH 0/24] Nested VMX, v5 Message-ID: <20100711082703.GA37@fermat.math.technion.ac.il> References: <1276431753-nyh@il.ibm.com> <1A42CE6F5F474C41B63392A5F80372B21F70B7B1@shsmsx501.ccr.corp.intel.com> Mime-Version: 1.0 Content-Disposition: inline In-Reply-To: <1A42CE6F5F474C41B63392A5F80372B21F70B7B1@shsmsx501.ccr.corp.intel.com> User-Agent: Mutt/1.4.2.2i Hebrew-Date: 29 Tammuz 5770 Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org X-Greylist: IP, sender and recipient auto-whitelisted, not delayed by milter-greylist-4.2.3 (demeter.kernel.org [140.211.167.41]); Sun, 11 Jul 2010 08:27:26 +0000 (UTC) ========= Subject: [PATCH 16/26] nVMX: Implement VMLAUNCH and VMRESUME Implement the VMLAUNCH and VMRESUME instructions, allowing a guest hypervisor to run its own guests. Signed-off-by: Nadav Har'El --- arch/x86/kvm/vmx.c | 200 ++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 197 insertions(+), 3 deletions(-) --- .before/arch/x86/kvm/vmx.c 2010-07-11 11:11:11.000000000 +0300 +++ .after/arch/x86/kvm/vmx.c 2010-07-11 11:11:11.000000000 +0300 @@ -279,6 +279,9 @@ struct __packed vmcs12 { struct vmcs_fields fields; bool launch_state; /* set to 0 by VMCLEAR, to 1 by VMLAUNCH */ + + int cpu; + int launched; }; /* @@ -313,6 +316,23 @@ struct nested_vmx { /* list of real (hardware) VMCS, one for each L2 guest of L1 */ struct list_head vmcs02_list; /* a vmcs_list */ int vmcs02_num; + + /* Are we running a nested guest now */ + bool nested_mode; + /* Level 1 state for switching to level 2 and back */ + struct { + u64 efer; + unsigned long cr3; + unsigned long cr4; + u64 io_bitmap_a; + u64 io_bitmap_b; + u64 msr_bitmap; + int cpu; + int launched; + } l1_state; + /* Saving the VMCS that we used for running L1 */ + struct vmcs *vmcs01; + struct vmcs_fields *vmcs01_fields; }; enum vmcs_field_type { @@ -1383,6 +1403,19 @@ static void vmx_vcpu_load(struct kvm_vcp new_offset = vmcs_read64(TSC_OFFSET) + delta; vmcs_write64(TSC_OFFSET, new_offset); } + + if (vmx->nested.vmcs01_fields != NULL) { + struct vmcs_fields *vmcs01 = + vmx->nested.vmcs01_fields; + vmcs01->host_tr_base = vmcs_readl(HOST_TR_BASE); + vmcs01->host_gdtr_base = vmcs_readl(HOST_GDTR_BASE); + vmcs01->host_ia32_sysenter_esp = + vmcs_readl(HOST_IA32_SYSENTER_ESP); + if (tsc_this < vcpu->arch.host_tsc) + vmcs01->tsc_offset = vmcs_read64(TSC_OFFSET); + if (vmx->nested.nested_mode) + load_vmcs_host_state(vmcs01); + } } } @@ -2278,6 +2311,9 @@ static void free_l1_state(struct kvm_vcp kfree(list_item); } vmx->nested.vmcs02_num = 0; + + kfree(vmx->nested.vmcs01_fields); + vmx->nested.vmcs01_fields = NULL; } static void free_kvm_area(void) @@ -4141,6 +4177,10 @@ static int handle_vmon(struct kvm_vcpu * INIT_LIST_HEAD(&(vmx->nested.vmcs02_list)); vmx->nested.vmcs02_num = 0; + vmx->nested.vmcs01_fields = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!vmx->nested.vmcs01_fields) + return -ENOMEM; + vmx->nested.vmxon = true; skip_emulated_instruction(vcpu); @@ -4339,6 +4379,38 @@ static int handle_vmclear(struct kvm_vcp return 1; } +static int nested_vmx_run(struct kvm_vcpu *vcpu); + +static int handle_launch_or_resume(struct kvm_vcpu *vcpu, bool launch) +{ + if (!nested_vmx_check_permission(vcpu)) + return 1; + + if (to_vmx(vcpu)->nested.current_vmcs12->launch_state == launch) { + /* Must use VMLAUNCH for the first time, VMRESUME later */ + set_rflags_to_vmx_fail_valid(vcpu); + return 1; + } + + skip_emulated_instruction(vcpu); + + nested_vmx_run(vcpu); + return 1; +} + +/* Emulate the VMLAUNCH instruction */ +static int handle_vmlaunch(struct kvm_vcpu *vcpu) +{ + return handle_launch_or_resume(vcpu, true); +} + +/* Emulate the VMRESUME instruction */ +static int handle_vmresume(struct kvm_vcpu *vcpu) +{ + + return handle_launch_or_resume(vcpu, false); +} + static inline bool vmcs12_read_any(struct kvm_vcpu *vcpu, unsigned long field, u64 *ret) { @@ -4869,11 +4941,11 @@ static int (*kvm_vmx_exit_handlers[])(st [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, @@ -4935,7 +5007,8 @@ static int vmx_handle_exit(struct kvm_vc "(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 && @@ -5756,6 +5829,127 @@ int prepare_vmcs_02(struct kvm_vcpu *vcp return 0; } +static int nested_vmx_run(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + vmx->nested.nested_mode = 1; + sync_cached_regs_to_vmcs(vcpu); + save_vmcs(vmx->nested.vmcs01_fields); + + vmx->nested.l1_state.efer = vcpu->arch.efer; + if (!enable_ept) + vmx->nested.l1_state.cr3 = vcpu->arch.cr3; + vmx->nested.l1_state.cr4 = vcpu->arch.cr4; + + 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.vmcs01 = vmx->vmcs; + vmx->nested.l1_state.cpu = vcpu->cpu; + vmx->nested.l1_state.launched = vmx->launched; + + vmx->vmcs = nested_get_current_vmcs(vcpu); + if (!vmx->vmcs) { + printk(KERN_ERR "Missing VMCS\n"); + set_rflags_to_vmx_fail_valid(vcpu); + return 1; + } + + vcpu->cpu = vmx->nested.current_vmcs12->cpu; + vmx->launched = vmx->nested.current_vmcs12->launched; + + if (!vmx->nested.current_vmcs12->launch_state || !vmx->launched) { + vmcs_clear(vmx->vmcs); + vmx->launched = 0; + vmx->nested.current_vmcs12->launch_state = 1; + } + + vmx_vcpu_load(vcpu, get_cpu()); + put_cpu(); + + prepare_vmcs_02(vcpu, + get_vmcs12_fields(vcpu), vmx->nested.vmcs01_fields); + + if (get_vmcs12_fields(vcpu)->vm_entry_controls & + VM_ENTRY_IA32E_MODE) { + if (!((vcpu->arch.efer & EFER_LMA) && + (vcpu->arch.efer & EFER_LME))) + vcpu->arch.efer |= (EFER_LMA | EFER_LME); + } else { + if ((vcpu->arch.efer & EFER_LMA) || + (vcpu->arch.efer & EFER_LME)) + vcpu->arch.efer = 0; + } + + /* vmx_set_cr0() sets the cr0 that L2 will read, to be the one that L1 + * dictated, and takes appropriate actions for special cr0 bits (like + * real mode, etc.). + */ + vmx_set_cr0(vcpu, + (get_vmcs12_fields(vcpu)->guest_cr0 & + ~get_vmcs12_fields(vcpu)->cr0_guest_host_mask) | + (get_vmcs12_fields(vcpu)->cr0_read_shadow & + get_vmcs12_fields(vcpu)->cr0_guest_host_mask)); + + /* However, vmx_set_cr0 incorrectly enforces KVM's relationship between + * GUEST_CR0 and CR0_READ_SHADOW, e.g., that the former is the same as + * the latter with with TS added if !fpu_active. We need to take the + * actual GUEST_CR0 that L1 wanted, just with added TS if !fpu_active + * like KVM wants (for the "lazy fpu" feature, to avoid the costly + * restoration of fpu registers until the FPU is really used). + */ + vmcs_writel(GUEST_CR0, get_vmcs12_fields(vcpu)->guest_cr0 | + (vcpu->fpu_active ? 0 : X86_CR0_TS)); + + vmx_set_cr4(vcpu, get_vmcs12_fields(vcpu)->guest_cr4); + vmcs_writel(CR4_READ_SHADOW, + get_vmcs12_fields(vcpu)->cr4_read_shadow); + + /* we have to set the X86_CR0_PG bit of the cached cr0, because + * kvm_mmu_reset_context enables paging only if X86_CR0_PG is set in + * CR0 (we need the paging so that KVM treat this guest as a paging + * guest so we can easly forward page faults to L1.) + */ + vcpu->arch.cr0 |= X86_CR0_PG; + + if (enable_ept && !nested_cpu_has_vmx_ept(vcpu)) { + vmcs_write32(GUEST_CR3, get_vmcs12_fields(vcpu)->guest_cr3); + vmx->vcpu.arch.cr3 = get_vmcs12_fields(vcpu)->guest_cr3; + } else { + int r; + kvm_set_cr3(vcpu, get_vmcs12_fields(vcpu)->guest_cr3); + kvm_mmu_reset_context(vcpu); + + r = kvm_mmu_load(vcpu); + if (unlikely(r)) { + printk(KERN_ERR "Error in kvm_mmu_load r %d\n", r); + set_rflags_to_vmx_fail_valid(vcpu); + /* switch back to L1 */ + vmx->nested.nested_mode = 0; + vmx->vmcs = vmx->nested.vmcs01; + vcpu->cpu = vmx->nested.l1_state.cpu; + vmx->launched = vmx->nested.l1_state.launched; + + vmx_vcpu_load(vcpu, get_cpu()); + put_cpu(); + + return 1; + } + } + + kvm_register_write(vcpu, VCPU_REGS_RSP, + get_vmcs12_fields(vcpu)->guest_rsp); + kvm_register_write(vcpu, VCPU_REGS_RIP, + get_vmcs12_fields(vcpu)->guest_rip); + + return 1; +} + static struct kvm_x86_ops vmx_x86_ops = { .cpu_has_kvm_support = cpu_has_kvm_support, .disabled_by_bios = vmx_disabled_by_bios,