Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Mohammed Gamal <mgamal@redhat.com>
To:     kvm@vger.kernel.org, pbonzini@redhat.com
Cc:     linux-kernel@vger.kernel.org, sean.j.christopherson@intel.com,
        vkuznets@redhat.com, wanpengli@tencent.com, jmattson@google.com,
        joro@8bytes.org, Mohammed Gamal <mgamal@redhat.com>
Subject: [PATCH] KVM: x86: VMX: Make smaller physical guest address space support user-configurable
Date:   Thu,  3 Sep 2020 16:11:22 +0200
Message-Id: <20200903141122.72908-1-mgamal@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

This patch exposes allow_smaller_maxphyaddr to the user as a module parameter.

Since smaller physical address spaces are only supported on VMX, the parameter
is only exposed in the kvm_intel module.
Modifications to VMX page fault and EPT violation handling will depend on whether
that parameter is enabled.

Also disable support by default, and let the user decide if they want to enable
it.

Signed-off-by: Mohammed Gamal <mgamal@redhat.com>
---
 arch/x86/kvm/vmx/vmx.c | 15 ++++++---------
 arch/x86/kvm/vmx/vmx.h |  3 +++
 arch/x86/kvm/x86.c     |  2 +-
 3 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 819c185adf09..dc778c7b5a06 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -129,6 +129,9 @@ static bool __read_mostly enable_preemption_timer = 1;
 module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO);
 #endif
 
+extern bool __read_mostly allow_smaller_maxphyaddr;
+module_param(allow_smaller_maxphyaddr, bool, S_IRUGO | S_IWUSR);
+
 #define KVM_VM_CR0_ALWAYS_OFF (X86_CR0_NW | X86_CR0_CD)
 #define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR0_NE
 #define KVM_VM_CR0_ALWAYS_ON				\
@@ -4798,7 +4801,8 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
 
 	if (is_page_fault(intr_info)) {
 		cr2 = vmx_get_exit_qual(vcpu);
-		if (enable_ept && !vcpu->arch.apf.host_apf_flags) {
+		if (enable_ept && !vcpu->arch.apf.host_apf_flags
+			&& allow_smaller_maxphyaddr) {
 			/*
 			 * EPT will cause page fault only if we need to
 			 * detect illegal GPAs.
@@ -5331,7 +5335,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
 	 * would also use advanced VM-exit information for EPT violations to
 	 * reconstruct the page fault error code.
 	 */
-	if (unlikely(kvm_mmu_is_illegal_gpa(vcpu, gpa)))
+	if (unlikely(kvm_mmu_is_illegal_gpa(vcpu, gpa)) && allow_smaller_maxphyaddr)
 		return kvm_emulate_instruction(vcpu, 0);
 
 	return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0);
@@ -8303,13 +8307,6 @@ static int __init vmx_init(void)
 #endif
 	vmx_check_vmcs12_offsets();
 
-	/*
-	 * Intel processors don't have problems with
-	 * GUEST_MAXPHYADDR < HOST_MAXPHYADDR so enable
-	 * it for VMX by default
-	 */
-	allow_smaller_maxphyaddr = true;
-
 	return 0;
 }
 module_init(vmx_init);
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 26175a4759fa..b859435efa2e 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -551,6 +551,9 @@ static inline bool vmx_has_waitpkg(struct vcpu_vmx *vmx)
 
 static inline bool vmx_need_pf_intercept(struct kvm_vcpu *vcpu)
 {
+	if (!allow_smaller_maxphyaddr)
+		return false;
+
 	return !enable_ept || cpuid_maxphyaddr(vcpu) < boot_cpu_data.x86_phys_bits;
 }
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index d39d6cf1d473..982f1d73a884 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -188,7 +188,7 @@ static struct kvm_shared_msrs __percpu *shared_msrs;
 u64 __read_mostly host_efer;
 EXPORT_SYMBOL_GPL(host_efer);
 
-bool __read_mostly allow_smaller_maxphyaddr;
+bool __read_mostly allow_smaller_maxphyaddr = 0;
 EXPORT_SYMBOL_GPL(allow_smaller_maxphyaddr);
 
 static u64 __read_mostly host_xss;
-- 
2.26.2