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, vkuznets@redhat.com,
        sean.j.christopherson@intel.com, wanpengli@tencent.com,
        jmattson@google.com, joro@8bytes.org
Subject: [PATCH v3 6/9] KVM: VMX: introduce vmx_need_pf_intercept
Date:   Fri, 10 Jul 2020 17:48:08 +0200
Message-Id: <20200710154811.418214-7-mgamal@redhat.com>
In-Reply-To: <20200710154811.418214-1-mgamal@redhat.com>
References: <20200710154811.418214-1-mgamal@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

From: Paolo Bonzini <pbonzini@redhat.com>

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/vmx/nested.c | 28 +++++++++++++++++-----------
 arch/x86/kvm/vmx/vmx.c    |  2 +-
 arch/x86/kvm/vmx/vmx.h    |  5 +++++
 3 files changed, 23 insertions(+), 12 deletions(-)

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index b26655104d4a..1aea9e3b8c43 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2433,22 +2433,28 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
 
 	/*
 	 * Whether page-faults are trapped is determined by a combination of
-	 * 3 settings: PFEC_MASK, PFEC_MATCH and EXCEPTION_BITMAP.PF.
-	 * If enable_ept, L0 doesn't care about page faults and we should
-	 * set all of these to L1's desires. However, if !enable_ept, L0 does
-	 * care about (at least some) page faults, and because it is not easy
-	 * (if at all possible?) to merge L0 and L1's desires, we simply ask
-	 * to exit on each and every L2 page fault. This is done by setting
-	 * MASK=MATCH=0 and (see below) EB.PF=1.
+	 * 3 settings: PFEC_MASK, PFEC_MATCH and EXCEPTION_BITMAP.PF.  If L0
+	 * doesn't care about page faults then we should set all of these to
+	 * L1's desires. However, if L0 does care about (some) page faults, it
+	 * is not easy (if at all possible?) to merge L0 and L1's desires, we
+	 * simply ask to exit on each and every L2 page fault. This is done by
+	 * setting MASK=MATCH=0 and (see below) EB.PF=1.
 	 * Note that below we don't need special code to set EB.PF beyond the
 	 * "or"ing of the EB of vmcs01 and vmcs12, because when enable_ept,
 	 * vmcs01's EB.PF is 0 so the "or" will take vmcs12's value, and when
 	 * !enable_ept, EB.PF is 1, so the "or" will always be 1.
 	 */
-	vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK,
-		enable_ept ? vmcs12->page_fault_error_code_mask : 0);
-	vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH,
-		enable_ept ? vmcs12->page_fault_error_code_match : 0);
+	if (vmx_need_pf_intercept(&vmx->vcpu)) {
+		/*
+		 * TODO: if both L0 and L1 need the same MASK and MATCH,
+		 * go ahead and use it?
+		 */
+		vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, 0);
+		vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, 0);
+	} else {
+		vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, vmcs12->page_fault_error_code_mask);
+		vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, vmcs12->page_fault_error_code_match);
+	}
 
 	if (cpu_has_vmx_apicv()) {
 		vmcs_write64(EOI_EXIT_BITMAP0, vmcs12->eoi_exit_bitmap0);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 178ee92551a9..770b090969fb 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -780,7 +780,7 @@ void update_exception_bitmap(struct kvm_vcpu *vcpu)
 		eb |= 1u << BP_VECTOR;
 	if (to_vmx(vcpu)->rmode.vm86_active)
 		eb = ~0;
-	if (enable_ept)
+	if (!vmx_need_pf_intercept(vcpu))
 		eb &= ~(1u << PF_VECTOR);
 
 	/* When we are running a nested L2 guest and L1 specified for it a
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 639798e4a6ca..b0e5e210f1c1 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -550,6 +550,11 @@ static inline bool vmx_has_waitpkg(struct vcpu_vmx *vmx)
 		SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE;
 }
 
+static inline bool vmx_need_pf_intercept(struct kvm_vcpu *vcpu)
+{
+	return !enable_ept;
+}
+
 void dump_vmcs(void);
 
 #endif /* __KVM_X86_VMX_H */
-- 
2.26.2