This patch contains the logic of whether an L2 exit should be handled by L0 and then L2 should be resumed, or whether L1 should be run to handle this exit (using the nested_vmx_vmexit() function of the previous patch).
The basic idea is to let L1 handle the exit only if it actually asked to trap this sort of event. For example, when L2 exits on a change to CR0, we check L1's CR0_GUEST_HOST_MASK to see if L1 expressed interest in any bit which changed; If it did, we exit to L1. But if it didn't it means that it is we (L0) that wished to trap this event, so we handle it ourselves. The next two patches add additional logic of what to do when an interrupt or exception is injected: Does L0 need to do it, should we exit to L1 to do it, or should we resume L2 and keep the exception to be injected later. We keep a new flag, "nested_run_pending", which can override the decision of which should run next, L1 or L2. nested_run_pending=1 means that we *must* run L2 next, not L1. This is necessary in particular when L1 did a VMLAUNCH of L2 and therefore expects L2 to be run (and perhaps be injected with an event it specified, etc.). Nested_run_pending is especially intended to avoid switching to L1 in the injection decision-point described above. Signed-off-by: Nadav Har'El <n...@il.ibm.com> --- arch/x86/kvm/vmx.c | 217 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 217 insertions(+) --- .before/arch/x86/kvm/vmx.c 2010-12-08 18:56:51.000000000 +0200 +++ .after/arch/x86/kvm/vmx.c 2010-12-08 18:56:51.000000000 +0200 @@ -333,6 +333,8 @@ struct nested_vmx { struct vmcs_fields *vmcs01_fields; /* Saving some vcpu->arch.* data we had for L1, while running L2 */ unsigned long l1_arch_cr3; + /* L2 must run next, and mustn't decide to exit to L1. */ + bool nested_run_pending; }; struct vcpu_vmx { @@ -845,6 +847,20 @@ static inline bool nested_vm_need_virtua SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES); } +static inline bool nested_cpu_has_vmx_msr_bitmap(struct kvm_vcpu *vcpu) +{ + return get_vmcs12_fields(vcpu)->cpu_based_vm_exec_control & + CPU_BASED_USE_MSR_BITMAPS; +} + +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 int nested_vmx_vmexit(struct kvm_vcpu *vcpu, bool is_interrupt); + static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr) { int i; @@ -4894,6 +4910,195 @@ static int (*kvm_vmx_exit_handlers[])(st 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 L1's MSR bitmap whether + * it expressed interest in the current event (read or write a specific MSR). + */ +static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu, + struct vmcs_fields *vmcs12, u32 exit_reason) +{ + u32 msr_index = vcpu->arch.regs[VCPU_REGS_RCX]; + struct page *msr_bitmap_page; + void *va; + bool ret; + + if (!cpu_has_vmx_msr_bitmap() || !nested_cpu_has_vmx_msr_bitmap(vcpu)) + return 1; + + msr_bitmap_page = nested_get_page(vcpu, vmcs12->msr_bitmap); + if (!msr_bitmap_page) { + printk(KERN_INFO "%s error in nested_get_page\n", __func__); + return 0; + } + + va = kmap_atomic(msr_bitmap_page, KM_USER1); + if (exit_reason == EXIT_REASON_MSR_WRITE) + va += 0x800; + if (msr_index >= 0xc0000000) { + msr_index -= 0xc0000000; + va += 0x400; + } + if (msr_index > 0x1fff) + return 0; + ret = test_bit(msr_index, va); + kunmap_atomic(va, KM_USER1); + return ret; +} + +/* + * 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 vmcs_fields *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_secondary_exec_ctrls(vcpu) && + (vmcs12->cpu_based_vm_exec_control & + 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_secondary_exec_ctrls(vcpu) && + (vmcs12->cpu_based_vm_exec_control & + CPU_BASED_CR8_LOAD_EXITING)) + return 1; + /* + * TODO: missing else if control & CPU_BASED_TPR_SHADOW + * then set tpr shadow and if below tpr_threshold, exit. + */ + break; + } + break; + case 2: /* clts */ + if (vmcs12->cr0_guest_host_mask & X86_CR0_TS) + return 1; + break; + case 1: /* mov from cr */ + switch (cr) { + case 0: + return 1; + case 3: + if (vmcs12->cpu_based_vm_exec_control & + CPU_BASED_CR3_STORE_EXITING) + return 1; + break; + case 4: + 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 vmcs_fields *vmcs12 = get_vmcs12_fields(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_EXTERNAL_INTERRUPT: + return 0; + 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_EPT_VIOLATION: + return 0; + case EXIT_REASON_INVLPG: + return vmcs12->cpu_based_vm_exec_control & + CPU_BASED_INVLPG_EXITING; + case EXIT_REASON_MSR_READ: + case EXIT_REASON_MSR_WRITE: + return nested_vmx_exit_handled_msr(vcpu, vmcs12, exit_reason); + case EXIT_REASON_CR_ACCESS: + return nested_vmx_exit_handled_cr(vcpu, vmcs12); + case EXIT_REASON_DR_ACCESS: + return vmcs12->cpu_based_vm_exec_control & + CPU_BASED_MOV_DR_EXITING; + default: + /* + * One particularly interesting case that is covered here is an + * exit caused by L2 running a VMX instruction. L2 is guest + * mode in L1's world, and according to the VMX spec running a + * VMX instruction in guest mode should cause an exit to root + * mode, i.e., to L1. This is why we need to return r=1 for + * those exit reasons too. This enables further nesting: Like + * L0 emulates VMX for L1, we now allow L1 to emulate VMX for + * L2, who will then be able to run L3. + */ + return 1; + } +} + static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2) { *info1 = vmcs_readl(EXIT_QUALIFICATION); @@ -4921,6 +5126,17 @@ static int vmx_handle_exit(struct kvm_vc if (enable_ept && is_paging(vcpu)) vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); + 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 (is_guest_mode(vcpu) && nested_vmx_exit_handled(vcpu)) { + nested_vmx_vmexit(vcpu, false); + 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 @@ -5981,6 +6197,7 @@ static int nested_vmx_run(struct kvm_vcp kvm_mmu_reset_context(vcpu); if (unlikely(kvm_mmu_load(vcpu))) { + nested_vmx_vmexit(vcpu, false); nested_vmx_failValid(vcpu, VMXERR_VMRESUME_CORRUPTED_VMCS /* ? */); /* switch back to L1 */ -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html