[PATCH 20/30] nVMX: Exiting from L2 to L1

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



This patch implements nested_vmx_vmexit(), called when the nested L2 guest
exits and we want to run its L1 parent and let it handle this exit.

Note that this will not necessarily be called on every L2 exit. L0 may decide
to handle a particular exit on its own, without L1's involvement; In that
case, L0 will handle the exit, and resume running L2, without running L1 and
without calling nested_vmx_vmexit(). The logic for deciding whether to handle
a particular exit in L1 or in L0, i.e., whether to call nested_vmx_vmexit(),
will appear in the next patch.

Signed-off-by: Nadav Har'El <nyh@xxxxxxxxxx>
---
 arch/x86/kvm/vmx.c |  288 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 288 insertions(+)

--- .before/arch/x86/kvm/vmx.c	2011-05-08 10:43:20.000000000 +0300
+++ .after/arch/x86/kvm/vmx.c	2011-05-08 10:43:20.000000000 +0300
@@ -6150,6 +6150,294 @@ static int nested_vmx_run(struct kvm_vcp
 	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 (see CRO_GUEST_HOST_MASK)
+ * without L0 trapping the change and updating vmcs12.
+ * This function returns the value we should put in vmcs12.guest_cr0. It's not
+ * enough to just return the current (vmcs02) GUEST_CR0 - that may not be the
+ * guest cr0 that L1 thought it was giving its L2 guest; It is possible that
+ * L1 wished to allow its guest to set some cr0 bit directly, but we (L0) asked
+ * to trap this change and instead set just the read shadow bit. If this is the
+ * case, we need to copy these read-shadow bits back to vmcs12.guest_cr0, where
+ * L1 believes they already are.
+ */
+static inline unsigned long
+vmcs12_guest_cr0(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
+{
+	/*
+	 * As explained above, we take a bit from GUEST_CR0 if we allowed the
+	 * guest to modify it untrapped (vcpu->arch.cr0_guest_owned_bits), or
+	 * if we did trap it - if we did so because L1 asked to trap this bit
+	 * (vmcs12->cr0_guest_host_mask). Otherwise (bits we trapped but L1
+	 * didn't expect us to trap) we read from CR0_READ_SHADOW.
+	 */
+	unsigned long guest_cr0_bits =
+		vcpu->arch.cr0_guest_owned_bits | vmcs12->cr0_guest_host_mask;
+	return (vmcs_readl(GUEST_CR0) & guest_cr0_bits) |
+	       (vmcs_readl(CR0_READ_SHADOW) & ~guest_cr0_bits);
+}
+
+static inline unsigned long
+vmcs12_guest_cr4(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
+{
+	unsigned long guest_cr4_bits =
+		vcpu->arch.cr4_guest_owned_bits | vmcs12->cr4_guest_host_mask;
+	return (vmcs_readl(GUEST_CR4) & guest_cr4_bits) |
+	       (vmcs_readl(CR4_READ_SHADOW) & ~guest_cr4_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);
+	vmcs12->vmcs_link_pointer = vmcs_read64(VMCS_LINK_POINTER);
+
+	/* 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);
+
+	if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT)
+		vmcs_write64(GUEST_IA32_PAT, vmcs12->host_ia32_pat);
+
+	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);
+	}
+}
+
+/*
+ * 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, bool is_interrupt)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	int cpu;
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+
+	leave_guest_mode(vcpu);
+
+	prepare_vmcs12(vcpu, vmcs12);
+
+	/*
+	 * Usually, nested_vmx_vmexit() is called after an exit from L2 that
+	 * we wish to pass to L1, so we can pass this exit reason. However,
+	 * when the ad-hoc is_interrupt flag is on, it means there was no
+	 * real exit reason: The caller wanted to exit to L1 just to inject
+	 * an interrupt to it, and we set here a fictitious exit reason.
+	 * In the future, this call option will be eliminated: Instead of
+	 * exiting to L1 and later injecting to it, the better solution would
+	 * be to exit to L1 with the injected interrupt as the exit reason.
+	 */
+	if (is_interrupt)
+		vmcs12->vm_exit_reason = EXIT_REASON_EXTERNAL_INTERRUPT;
+
+	/*
+	 * Switch from L2's VMCS, to L1's VMCS. Remember on which CPU the L2
+	 * VMCS was last loaded, and whether it was launched (we need to know
+	 * this next time we use L2), and recall these values as they were for
+	 * L1's VMCS.
+	 */
+	cpu = get_cpu();
+	if (VMCS02_POOL_SIZE > 0) {
+		struct saved_vmcs *saved_vmcs02 =
+			nested_get_current_vmcs02(vmx);
+		saved_vmcs02->cpu = vcpu->cpu;
+		saved_vmcs02->launched = vmx->launched;
+	} else {
+		/* no vmcs02 cache requested, so free the one we used */
+		nested_free_vmcs02(vmx, vmx->nested.current_vmptr);
+	}
+	vmx->vmcs = vmx->nested.saved_vmcs01.vmcs;
+	vcpu->cpu = vmx->nested.saved_vmcs01.cpu;
+	vmx->launched = vmx->nested.saved_vmcs01.launched;
+
+	vmx_vcpu_put(vcpu);
+	vmx_vcpu_load(vcpu, cpu);
+	vcpu->cpu = cpu;
+	put_cpu();
+
+	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". 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)
+{
+	load_vmcs12_host_state(vcpu, vmcs12);
+	/* TODO: there are more possible types of failures - see 23.7 */
+	vmcs12->vm_exit_reason = EXIT_REASON_INVALID_STATE |
+		VMX_EXIT_REASONS_FAILED_VMENTRY;
+	vmcs12->exit_qualification = 0;
+	nested_vmx_succeed(vcpu);
+}
+
 static int vmx_check_intercept(struct kvm_vcpu *vcpu,
 			       struct x86_instruction_info *info,
 			       enum x86_intercept_stage stage)
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html


[Index of Archives]     [KVM ARM]     [KVM ia64]     [KVM ppc]     [Virtualization Tools]     [Spice Development]     [Libvirt]     [Libvirt Users]     [Linux USB Devel]     [Linux Audio Users]     [Yosemite Questions]     [Linux Kernel]     [Linux SCSI]     [XFree86]
  Powered by Linux