diff mbox

[v2,2/8] KVM: x86: add pcommit support

Message ID 1441778757-5866-3-git-send-email-guangrong.xiao@linux.intel.com (mailing list archive)
State New, archived
Headers show

Commit Message

Xiao Guangrong Sept. 9, 2015, 6:05 a.m. UTC
Pass PCOMMIT CPU feature to guest to enable PCOMMIT instruction

Currently we do not catch pcommit instruction for L1 guest and
allow L1 to catch this instruction for L2 if, as required by the spec,
L1 can enumerate the PCOMMIT instruction via CPUID:
| IA32_VMX_PROCBASED_CTLS2[53] (which enumerates support for the
| 1-setting of PCOMMIT exiting) is always the same as
| CPUID.07H:EBX.PCOMMIT[bit 22]. Thus, software can set PCOMMIT exiting
| to 1 if and only if the PCOMMIT instruction is enumerated via CPUID

The spec can be found at
https://software.intel.com/sites/default/files/managed/0d/53/319433-022.pdf

Signed-off-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
---
 arch/x86/include/asm/vmx.h      |  2 +-
 arch/x86/include/uapi/asm/vmx.h |  4 +++-
 arch/x86/kvm/cpuid.c            |  2 +-
 arch/x86/kvm/cpuid.h            |  8 ++++++++
 arch/x86/kvm/vmx.c              | 29 ++++++++++++++++++++++++-----
 5 files changed, 37 insertions(+), 8 deletions(-)

Comments

Paolo Bonzini Sept. 15, 2015, 3:30 p.m. UTC | #1
On 09/09/2015 08:05, Xiao Guangrong wrote:
> +	if (!guest_cpuid_has_pcommit(vcpu) && nested)
> +		vmx->nested.nested_vmx_secondary_ctls_high &=
> +			~SECONDARY_EXEC_PCOMMIT;

It is legal to set CPUID multiple times, so I think we need

        if (static_cpu_has(X86_FEATURE_PCOMMIT) && nested) {
                if (guest_cpuid_has_pcommit(vcpu))
                        vmx->nested.nested_vmx_secondary_ctls_high |=
                                SECONDARY_EXEC_PCOMMIT;
                else
                        vmx->nested.nested_vmx_secondary_ctls_high &=
                                ~SECONDARY_EXEC_PCOMMIT;
        }

The INVPCID exit probably should be handled the same way as PCOMMIT;
moving both to a new nested_vmx_update_ctls_msrs probably makes sense.

This can be done on top of this series.

Paolo
--
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

diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 448b7ca..d25f32a 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -72,7 +72,7 @@ 
 #define SECONDARY_EXEC_SHADOW_VMCS              0x00004000
 #define SECONDARY_EXEC_ENABLE_PML               0x00020000
 #define SECONDARY_EXEC_XSAVES			0x00100000
-
+#define SECONDARY_EXEC_PCOMMIT			0x00200000
 
 #define PIN_BASED_EXT_INTR_MASK                 0x00000001
 #define PIN_BASED_NMI_EXITING                   0x00000008
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index 37fee27..5b15d94 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -78,6 +78,7 @@ 
 #define EXIT_REASON_PML_FULL            62
 #define EXIT_REASON_XSAVES              63
 #define EXIT_REASON_XRSTORS             64
+#define EXIT_REASON_PCOMMIT             65
 
 #define VMX_EXIT_REASONS \
 	{ EXIT_REASON_EXCEPTION_NMI,         "EXCEPTION_NMI" }, \
@@ -126,7 +127,8 @@ 
 	{ EXIT_REASON_INVVPID,               "INVVPID" }, \
 	{ EXIT_REASON_INVPCID,               "INVPCID" }, \
 	{ EXIT_REASON_XSAVES,                "XSAVES" }, \
-	{ EXIT_REASON_XRSTORS,               "XRSTORS" }
+	{ EXIT_REASON_XRSTORS,               "XRSTORS" }, \
+	{ EXIT_REASON_PCOMMIT,               "PCOMMIT" }
 
 #define VMX_ABORT_SAVE_GUEST_MSR_FAIL        1
 #define VMX_ABORT_LOAD_HOST_MSR_FAIL         4
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 962fc7d..faeb0b3 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -348,7 +348,7 @@  static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		F(FSGSBASE) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) |
 		F(BMI2) | F(ERMS) | f_invpcid | F(RTM) | f_mpx | F(RDSEED) |
 		F(ADX) | F(SMAP) | F(AVX512F) | F(AVX512PF) | F(AVX512ER) |
-		F(AVX512CD) | F(CLFLUSHOPT) | F(CLWB);
+		F(AVX512CD) | F(CLFLUSHOPT) | F(CLWB) | F(PCOMMIT);
 
 	/* cpuid 0xD.1.eax */
 	const u32 kvm_supported_word10_x86_features =
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index dd05b9c..aed7bfe 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -133,4 +133,12 @@  static inline bool guest_cpuid_has_mpx(struct kvm_vcpu *vcpu)
 	best = kvm_find_cpuid_entry(vcpu, 7, 0);
 	return best && (best->ebx & bit(X86_FEATURE_MPX));
 }
+
+static inline bool guest_cpuid_has_pcommit(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 7, 0);
+	return best && (best->ebx & bit(X86_FEATURE_PCOMMIT));
+}
 #endif
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index da1590e..073cbc8 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2474,7 +2474,8 @@  static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 		SECONDARY_EXEC_APIC_REGISTER_VIRT |
 		SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
 		SECONDARY_EXEC_WBINVD_EXITING |
-		SECONDARY_EXEC_XSAVES;
+		SECONDARY_EXEC_XSAVES |
+		SECONDARY_EXEC_PCOMMIT;
 
 	if (enable_ept) {
 		/* nested EPT: emulate EPT also to L1 */
@@ -3015,7 +3016,8 @@  static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
 			SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
 			SECONDARY_EXEC_SHADOW_VMCS |
 			SECONDARY_EXEC_XSAVES |
-			SECONDARY_EXEC_ENABLE_PML;
+			SECONDARY_EXEC_ENABLE_PML |
+			SECONDARY_EXEC_PCOMMIT;
 		if (adjust_vmx_controls(min2, opt2,
 					MSR_IA32_VMX_PROCBASED_CTLS2,
 					&_cpu_based_2nd_exec_control) < 0)
@@ -4570,6 +4572,9 @@  static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx)
 	/* PML is enabled/disabled in creating/destorying vcpu */
 	exec_control &= ~SECONDARY_EXEC_ENABLE_PML;
 
+	/* Currently, we allow L1 guest to directly run pcommit instruction. */
+	exec_control &= ~SECONDARY_EXEC_PCOMMIT;
+
 	return exec_control;
 }
 
@@ -4613,10 +4618,9 @@  static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 
 	vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, vmx_exec_control(vmx));
 
-	if (cpu_has_secondary_exec_ctrls()) {
+	if (cpu_has_secondary_exec_ctrls())
 		vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
 				vmx_secondary_exec_control(vmx));
-	}
 
 	if (vmx_vm_has_apicv(vmx->vcpu.kvm)) {
 		vmcs_write64(EOI_EXIT_BITMAP0, 0);
@@ -7219,6 +7223,13 @@  static int handle_pml_full(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static int handle_pcommit(struct kvm_vcpu *vcpu)
+{
+	/* we never catch pcommit instruct for L1 guest. */
+	WARN_ON(1);
+	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
@@ -7269,6 +7280,7 @@  static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_XSAVES]                  = handle_xsaves,
 	[EXIT_REASON_XRSTORS]                 = handle_xrstors,
 	[EXIT_REASON_PML_FULL]		      = handle_pml_full,
+	[EXIT_REASON_PCOMMIT]                 = handle_pcommit,
 };
 
 static const int kvm_vmx_max_exit_handlers =
@@ -7570,6 +7582,8 @@  static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 		 * the XSS exit bitmap in vmcs12.
 		 */
 		return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES);
+	case EXIT_REASON_PCOMMIT:
+		return nested_cpu_has2(vmcs12, SECONDARY_EXEC_PCOMMIT);
 	default:
 		return true;
 	}
@@ -8698,6 +8712,10 @@  static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 		if (best)
 			best->ebx &= ~bit(X86_FEATURE_INVPCID);
 	}
+
+	if (!guest_cpuid_has_pcommit(vcpu) && nested)
+		vmx->nested.nested_vmx_secondary_ctls_high &=
+			~SECONDARY_EXEC_PCOMMIT;
 }
 
 static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
@@ -9311,7 +9329,8 @@  static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 		exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
 				  SECONDARY_EXEC_RDTSCP |
 				  SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
-				  SECONDARY_EXEC_APIC_REGISTER_VIRT);
+				  SECONDARY_EXEC_APIC_REGISTER_VIRT |
+				  SECONDARY_EXEC_PCOMMIT);
 		if (nested_cpu_has(vmcs12,
 				CPU_BASED_ACTIVATE_SECONDARY_CONTROLS))
 			exec_control |= vmcs12->secondary_vm_exec_control;