[PATCH 3/3] KVM: x86: Sync SPTEs when injecting page/EPT fault into L1

From: Paolo Bonzini <pbonzini@redhat.com>
To: linux-kernel@vger.kernel.org, kvm@vger.kernel.org
Cc: Junaid Shahid <junaids@google.com>,
	Sean Christopherson <sean.j.christopherson@intel.com>,
	Vitaly Kuznetsov <vkuznets@redhat.com>
Subject: [PATCH 3/3] KVM: x86: Sync SPTEs when injecting page/EPT fault into L1
Date: Thu, 26 Mar 2020 05:35:16 -0400	[thread overview]
Message-ID: <20200326093516.24215-4-pbonzini@redhat.com> (raw)
In-Reply-To: <20200326093516.24215-1-pbonzini@redhat.com>

From: Junaid Shahid <junaids@google.com>

When injecting a page fault or EPT violation/misconfiguration, KVM is
not syncing any shadow PTEs associated with the faulting address,
including those in previous MMUs that are associated with L1's current
EPTP (in a nested EPT scenario), nor is it flushing any hardware TLB
entries.  All this is done by kvm_mmu_invalidate_gva.

Page faults that are either !PRESENT or RSVD are exempt from the flushing,
as the CPU is not allowed to cache such translations.

Signed-off-by: Junaid Shahid <junaids@google.com>
Co-developed-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20200320212833.3507-8-sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/vmx/nested.c | 12 ++++++------
 arch/x86/kvm/vmx/vmx.c    |  2 +-
 arch/x86/kvm/x86.c        | 11 ++++++++++-
 3 files changed, 17 insertions(+), 8 deletions(-)

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 2c450b0ba592..1586b1b5ba93 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -4559,7 +4559,7 @@ static int nested_vmx_get_vmptr(struct kvm_vcpu *vcpu, gpa_t *vmpointer)
 		return 1;
 
 	if (kvm_read_guest_virt(vcpu, gva, vmpointer, sizeof(*vmpointer), &e)) {
-		kvm_inject_page_fault(vcpu, &e);
+		kvm_inject_emulated_page_fault(vcpu, &e);
 		return 1;
 	}
 
@@ -4868,7 +4868,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
 			return 1;
 		/* _system ok, nested_vmx_check_permission has verified cpl=0 */
 		if (kvm_write_guest_virt_system(vcpu, gva, &value, len, &e)) {
-			kvm_inject_page_fault(vcpu, &e);
+			kvm_inject_emulated_page_fault(vcpu, &e);
 			return 1;
 		}
 	}
@@ -4942,7 +4942,7 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu)
 					instr_info, false, len, &gva))
 			return 1;
 		if (kvm_read_guest_virt(vcpu, gva, &value, len, &e)) {
-			kvm_inject_page_fault(vcpu, &e);
+			kvm_inject_emulated_page_fault(vcpu, &e);
 			return 1;
 		}
 	}
@@ -5107,7 +5107,7 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu)
 	/* *_system ok, nested_vmx_check_permission has verified cpl=0 */
 	if (kvm_write_guest_virt_system(vcpu, gva, (void *)&current_vmptr,
 					sizeof(gpa_t), &e)) {
-		kvm_inject_page_fault(vcpu, &e);
+		kvm_inject_emulated_page_fault(vcpu, &e);
 		return 1;
 	}
 	return nested_vmx_succeed(vcpu);
@@ -5151,7 +5151,7 @@ static int handle_invept(struct kvm_vcpu *vcpu)
 			vmx_instruction_info, false, sizeof(operand), &gva))
 		return 1;
 	if (kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e)) {
-		kvm_inject_page_fault(vcpu, &e);
+		kvm_inject_emulated_page_fault(vcpu, &e);
 		return 1;
 	}
 
@@ -5219,7 +5219,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 			vmx_instruction_info, false, sizeof(operand), &gva))
 		return 1;
 	if (kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e)) {
-		kvm_inject_page_fault(vcpu, &e);
+		kvm_inject_emulated_page_fault(vcpu, &e);
 		return 1;
 	}
 	if (operand.vpid >> 16)
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 07299a957d4a..c944726b3c0c 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -5404,7 +5404,7 @@ static int handle_invpcid(struct kvm_vcpu *vcpu)
 		return 1;
 
 	if (kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e)) {
-		kvm_inject_page_fault(vcpu, &e);
+		kvm_inject_emulated_page_fault(vcpu, &e);
 		return 1;
 	}
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 522905523bf0..dbca6c3bd0db 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -618,8 +618,17 @@ bool kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu,
 	WARN_ON_ONCE(fault->vector != PF_VECTOR);
 
 	fault_mmu = fault->nested_page_fault ? vcpu->arch.mmu : vcpu->arch.walk_mmu;
-	fault_mmu->inject_page_fault(vcpu, fault);
 
+	/*
+	 * Invalidate the TLB entry for the faulting address, if it exists,
+	 * else the access will fault indefinitely (and to emulate hardware).
+	 */
+	if ((fault->error_code & PFERR_PRESENT_MASK)
+	    && !(fault->error_code & PFERR_RSVD_MASK))
+		kvm_mmu_invalidate_gva(vcpu, fault_mmu,
+				       fault->address, fault_mmu->root_hpa);
+
+	fault_mmu->inject_page_fault(vcpu, fault);
 	return fault->nested_page_fault;
 }
 EXPORT_SYMBOL_GPL(kvm_inject_emulated_page_fault);
-- 
2.18.2

