Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Lei Wang <lei4.wang@intel.com>
To:     pbonzini@redhat.com, seanjc@google.com, vkuznets@redhat.com,
        wanpengli@tencent.com, jmattson@google.com, joro@8bytes.org
Cc:     lei4.wang@intel.com, chenyi.qiang@intel.com, kvm@vger.kernel.org,
        linux-kernel@vger.kernel.org
Subject: [PATCH v7 2/8] KVM: VMX: Add proper cache tracking for PKRS
Date:   Sun, 24 Apr 2022 03:15:51 -0700
Message-Id: <20220424101557.134102-3-lei4.wang@intel.com>
In-Reply-To: <20220424101557.134102-1-lei4.wang@intel.com>
References: <20220424101557.134102-1-lei4.wang@intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Chenyi Qiang <chenyi.qiang@intel.com>

Add PKRS caching into the standard register caching mechanism in order
to take advantage of the availability checks provided by regs_avail.

This is because vcpu->arch.pkrs will be rarely acceesed by KVM, only in
the case of host userspace MSR reads and GVA->GPA translation in
following patches. It is unnecessary to keep it up-to-date at all times.

It also should be noted that the potential benefits of this caching are
tenuous because the MSR read is not a hot path. it's nice-to-have so that
we don't hesitate to rip it out in the future if there's a strong reason
to drop the caching.

Signed-off-by: Chenyi Qiang <chenyi.qiang@intel.com>
Co-developed-by: Lei Wang <lei4.wang@intel.com>
Signed-off-by: Lei Wang <lei4.wang@intel.com>
---
 arch/x86/include/asm/kvm_host.h |  2 ++
 arch/x86/kvm/kvm_cache_regs.h   |  7 +++++++
 arch/x86/kvm/vmx/vmx.c          | 11 +++++++++++
 arch/x86/kvm/vmx/vmx.h          |  3 ++-
 4 files changed, 22 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index e0c0f0e1f754..f5455bada8cd 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -180,6 +180,7 @@ enum kvm_reg {
 	VCPU_EXREG_SEGMENTS,
 	VCPU_EXREG_EXIT_INFO_1,
 	VCPU_EXREG_EXIT_INFO_2,
+	VCPU_EXREG_PKRS,
 };
 
 enum {
@@ -638,6 +639,7 @@ struct kvm_vcpu_arch {
 	unsigned long cr8;
 	u32 host_pkru;
 	u32 pkru;
+	u32 pkrs;
 	u32 hflags;
 	u64 efer;
 	u64 apic_base;
diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h
index 3febc342360c..2b2540ca584f 100644
--- a/arch/x86/kvm/kvm_cache_regs.h
+++ b/arch/x86/kvm/kvm_cache_regs.h
@@ -177,6 +177,13 @@ static inline u64 kvm_read_edx_eax(struct kvm_vcpu *vcpu)
 		| ((u64)(kvm_rdx_read(vcpu) & -1u) << 32);
 }
 
+static inline u32 kvm_read_pkrs(struct kvm_vcpu *vcpu)
+{
+	if (!kvm_register_is_available(vcpu, VCPU_EXREG_PKRS))
+		static_call(kvm_x86_cache_reg)(vcpu, VCPU_EXREG_PKRS);
+	return vcpu->arch.pkrs;
+}
+
 static inline void enter_guest_mode(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.hflags |= HF_GUEST_MASK;
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 04d170c4b61e..395b2deb76aa 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2258,6 +2258,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
 {
 	unsigned long guest_owned_bits;
+	u64 ia32_pkrs;
 
 	kvm_register_mark_available(vcpu, reg);
 
@@ -2292,6 +2293,16 @@ static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
 		vcpu->arch.cr4 &= ~guest_owned_bits;
 		vcpu->arch.cr4 |= vmcs_readl(GUEST_CR4) & guest_owned_bits;
 		break;
+	case VCPU_EXREG_PKRS:
+		/*
+		 * The high 32 bits of PKRS are reserved and attempting to write
+		 * non-zero value will cause #GP. KVM intentionally drops those
+		 * bits.
+		 */
+		ia32_pkrs = vmcs_read64(GUEST_IA32_PKRS);
+		WARN_ON_ONCE(ia32_pkrs >> 32);
+		vcpu->arch.pkrs = ia32_pkrs;
+		break;
 	default:
 		KVM_BUG_ON(1, vcpu->kvm);
 		break;
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 9c6bfcd84008..661df9584b12 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -499,7 +499,8 @@ BUILD_CONTROLS_SHADOW(secondary_exec, SECONDARY_VM_EXEC_CONTROL)
 				(1 << VCPU_EXREG_CR3) |         \
 				(1 << VCPU_EXREG_CR4) |         \
 				(1 << VCPU_EXREG_EXIT_INFO_1) | \
-				(1 << VCPU_EXREG_EXIT_INFO_2))
+				(1 << VCPU_EXREG_EXIT_INFO_2) | \
+				(1 << VCPU_EXREG_PKRS))
 
 static inline struct kvm_vmx *to_kvm_vmx(struct kvm *kvm)
 {
-- 
2.25.1