diff mbox

[08/10] nEPT: Nested INVEPT

Message ID 201208011440.q71EemBU023913@rice.haifa.ibm.com (mailing list archive)
State New, archived
Headers show

Commit Message

Nadav Har'El Aug. 1, 2012, 2:40 p.m. UTC
If we let L1 use EPT, we should probably also support the INVEPT instruction.

In our current nested EPT implementation, when L1 changes its EPT table for
L2 (i.e., EPT12), L0 modifies the shadow EPT table (EPT02), and in the course
of this modification already calls INVEPT. Therefore, when L1 calls INVEPT,
we don't really need to do anything. In particular we *don't* need to call
the real INVEPT again. All we do in our INVEPT is verify the validity of the
call, and its parameters, and then do nothing.

In KVM Forum 2010, Dong et al. presented "Nested Virtualization Friendly KVM"
and classified our current nested EPT implementation as "shadow-like virtual
EPT". He recommended instead a different approach, which he called "VTLB-like
virtual EPT". If we had taken that alternative approach, INVEPT would have had
a bigger role: L0 would only rebuild the shadow EPT table when L1 calls INVEPT.

Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
---
 arch/x86/include/asm/vmx.h |    2 
 arch/x86/kvm/vmx.c         |   87 +++++++++++++++++++++++++++++++++++
 2 files changed, 89 insertions(+)


--
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
diff mbox

Patch

--- .before/arch/x86/include/asm/vmx.h	2012-08-01 17:22:47.000000000 +0300
+++ .after/arch/x86/include/asm/vmx.h	2012-08-01 17:22:47.000000000 +0300
@@ -280,6 +280,7 @@  enum vmcs_field {
 #define EXIT_REASON_APIC_ACCESS         44
 #define EXIT_REASON_EPT_VIOLATION       48
 #define EXIT_REASON_EPT_MISCONFIG       49
+#define EXIT_REASON_INVEPT		50
 #define EXIT_REASON_WBINVD		54
 #define EXIT_REASON_XSETBV		55
 #define EXIT_REASON_INVPCID		58
@@ -406,6 +407,7 @@  enum vmcs_field {
 #define VMX_EPTP_WB_BIT				(1ull << 14)
 #define VMX_EPT_2MB_PAGE_BIT			(1ull << 16)
 #define VMX_EPT_1GB_PAGE_BIT			(1ull << 17)
+#define VMX_EPT_INVEPT_BIT			(1ull << 20)
 #define VMX_EPT_AD_BIT					(1ull << 21)
 #define VMX_EPT_EXTENT_INDIVIDUAL_BIT		(1ull << 24)
 #define VMX_EPT_EXTENT_CONTEXT_BIT		(1ull << 25)
--- .before/arch/x86/kvm/vmx.c	2012-08-01 17:22:47.000000000 +0300
+++ .after/arch/x86/kvm/vmx.c	2012-08-01 17:22:47.000000000 +0300
@@ -2026,6 +2026,10 @@  static __init void nested_vmx_setup_ctls
 		/* nested EPT: emulate EPT also to L1 */
 		nested_vmx_secondary_ctls_high |= SECONDARY_EXEC_ENABLE_EPT;
 		nested_vmx_ept_caps = VMX_EPT_PAGE_WALK_4_BIT;
+		nested_vmx_ept_caps |=
+			VMX_EPT_INVEPT_BIT | VMX_EPT_EXTENT_GLOBAL_BIT |
+			VMX_EPT_EXTENT_CONTEXT_BIT |
+			VMX_EPT_EXTENT_INDIVIDUAL_BIT;
 		nested_vmx_ept_caps &= vmx_capability.ept;
 	} else
 		nested_vmx_ept_caps = 0;
@@ -5702,6 +5706,87 @@  static int handle_vmptrst(struct kvm_vcp
 	return 1;
 }
 
+/* Emulate the INVEPT instruction */
+static int handle_invept(struct kvm_vcpu *vcpu)
+{
+	u32 vmx_instruction_info;
+	unsigned long type;
+	gva_t gva;
+	struct x86_exception e;
+	struct {
+		u64 eptp, gpa;
+	} operand;
+
+	if (!(nested_vmx_secondary_ctls_high & SECONDARY_EXEC_ENABLE_EPT) ||
+	    !(nested_vmx_ept_caps & VMX_EPT_INVEPT_BIT)) {
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return 1;
+	}
+
+	if (!nested_vmx_check_permission(vcpu))
+		return 1;
+
+	if (!kvm_read_cr0_bits(vcpu, X86_CR0_PE)) {
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return 1;
+	}
+
+	/* According to the Intel VMX instruction reference, the memory
+	 * operand is read even if it isn't needed (e.g., for type==global)
+	 */
+	vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
+	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
+			vmx_instruction_info, &gva))
+		return 1;
+	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &operand,
+				sizeof(operand), &e)) {
+		kvm_inject_page_fault(vcpu, &e);
+		return 1;
+	}
+
+	type = kvm_register_read(vcpu, (vmx_instruction_info >> 28) & 0xf);
+
+	switch (type) {
+	case VMX_EPT_EXTENT_GLOBAL:
+		if (!(nested_vmx_ept_caps & VMX_EPT_EXTENT_GLOBAL_BIT))
+			nested_vmx_failValid(vcpu,
+				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
+		else {
+			/*
+			 * Do nothing: when L1 changes EPT12, we already
+			 * update EPT02 (the shadow EPT table) and call INVEPT.
+			 * So when L1 calls INVEPT, there's nothing left to do.
+			 */
+			nested_vmx_succeed(vcpu);
+		}
+		break;
+	case VMX_EPT_EXTENT_CONTEXT:
+		if (!(nested_vmx_ept_caps & VMX_EPT_EXTENT_CONTEXT_BIT))
+			nested_vmx_failValid(vcpu,
+				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
+		else {
+			/* Do nothing */
+			nested_vmx_succeed(vcpu);
+		}
+		break;
+	case VMX_EPT_EXTENT_INDIVIDUAL_ADDR:
+		if (!(nested_vmx_ept_caps & VMX_EPT_EXTENT_INDIVIDUAL_BIT))
+			nested_vmx_failValid(vcpu,
+				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
+		else {
+			/* Do nothing */
+			nested_vmx_succeed(vcpu);
+		}
+		break;
+	default:
+		nested_vmx_failValid(vcpu,
+			VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
+	}
+
+	skip_emulated_instruction(vcpu);
+	return 1;
+}
+
 /*
  * The exit handlers return 1 if the exit was handled fully and guest execution
  * may resume.  Otherwise they set the kvm_run parameter to indicate what needs
@@ -5744,6 +5829,7 @@  static int (*kvm_vmx_exit_handlers[])(st
 	[EXIT_REASON_PAUSE_INSTRUCTION]       = handle_pause,
 	[EXIT_REASON_MWAIT_INSTRUCTION]	      = handle_invalid_op,
 	[EXIT_REASON_MONITOR_INSTRUCTION]     = handle_invalid_op,
+	[EXIT_REASON_INVEPT]                  = handle_invept,
 };
 
 static const int kvm_vmx_max_exit_handlers =
@@ -5928,6 +6014,7 @@  static bool nested_vmx_exit_handled(stru
 	case EXIT_REASON_VMPTRST: case EXIT_REASON_VMREAD:
 	case EXIT_REASON_VMRESUME: case EXIT_REASON_VMWRITE:
 	case EXIT_REASON_VMOFF: case EXIT_REASON_VMON:
+	case EXIT_REASON_INVEPT:
 		/*
 		 * VMX instructions trap unconditionally. This allows L1 to
 		 * emulate them for its L2 guest, i.e., allows 3-level nesting!