[RFC PATCH 25/35] KVM: x86: Update __get_sregs() / __set_sregs() to support SEV-ES

From: Tom Lendacky <thomas.lendacky@amd.com>
To: kvm@vger.kernel.org, linux-kernel@vger.kernel.org, x86@kernel.org
Cc: Paolo Bonzini <pbonzini@redhat.com>,
	Jim Mattson <jmattson@google.com>, Joerg Roedel <joro@8bytes.org>,
	Sean Christopherson <sean.j.christopherson@intel.com>,
	Vitaly Kuznetsov <vkuznets@redhat.com>,
	Wanpeng Li <wanpengli@tencent.com>,
	Borislav Petkov <bp@alien8.de>, Ingo Molnar <mingo@redhat.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Brijesh Singh <brijesh.singh@amd.com>
Subject: [RFC PATCH 25/35] KVM: x86: Update __get_sregs() / __set_sregs() to support SEV-ES
Date: Mon, 14 Sep 2020 15:15:39 -0500	[thread overview]
Message-ID: <e08f56496a52a3a974310fbe05bb19100fd6c1d8.1600114548.git.thomas.lendacky@amd.com> (raw)
In-Reply-To: <cover.1600114548.git.thomas.lendacky@amd.com>

From: Tom Lendacky <thomas.lendacky@amd.com>

Since many of the registers used by the SEV-ES are encrypted and cannot
be read or written, adjust the __get_sregs() / __set_sregs() to only get
or set the registers being tracked (efer, cr0, cr4 and cr8) once the VMSA
is encrypted.

For __get_sregs(), return the actual value that is in use by the guest
as determined by the write trap support of the registers.

For __set_sregs(), set the arch specific value that KVM believes the guest
to be using. Note, this will not set the guest's actual value so it might
only be useful for such things as live migration.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
---
 arch/x86/kvm/x86.c | 56 +++++++++++++++++++++++++++-------------------
 1 file changed, 33 insertions(+), 23 deletions(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6e445a76b691..76efe70cd635 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -9090,6 +9090,9 @@ static void __get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 {
 	struct desc_ptr dt;
 
+	if (vcpu->arch.vmsa_encrypted)
+		goto tracking_regs;
+
 	kvm_get_segment(vcpu, &sregs->cs, VCPU_SREG_CS);
 	kvm_get_segment(vcpu, &sregs->ds, VCPU_SREG_DS);
 	kvm_get_segment(vcpu, &sregs->es, VCPU_SREG_ES);
@@ -9107,12 +9110,15 @@ static void __get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	sregs->gdt.limit = dt.size;
 	sregs->gdt.base = dt.address;
 
-	sregs->cr0 = kvm_read_cr0(vcpu);
 	sregs->cr2 = vcpu->arch.cr2;
 	sregs->cr3 = kvm_read_cr3(vcpu);
+
+tracking_regs:
+	sregs->cr0 = kvm_read_cr0(vcpu);
 	sregs->cr4 = kvm_read_cr4(vcpu);
 	sregs->cr8 = kvm_get_cr8(vcpu);
 	sregs->efer = vcpu->arch.efer;
+
 	sregs->apic_base = kvm_get_apic_base(vcpu);
 
 	memset(sregs->interrupt_bitmap, 0, sizeof(sregs->interrupt_bitmap));
@@ -9248,18 +9254,6 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	if (kvm_set_apic_base(vcpu, &apic_base_msr))
 		goto out;
 
-	dt.size = sregs->idt.limit;
-	dt.address = sregs->idt.base;
-	kvm_x86_ops.set_idt(vcpu, &dt);
-	dt.size = sregs->gdt.limit;
-	dt.address = sregs->gdt.base;
-	kvm_x86_ops.set_gdt(vcpu, &dt);
-
-	vcpu->arch.cr2 = sregs->cr2;
-	mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3;
-	vcpu->arch.cr3 = sregs->cr3;
-	kvm_register_mark_available(vcpu, VCPU_EXREG_CR3);
-
 	kvm_set_cr8(vcpu, sregs->cr8);
 
 	mmu_reset_needed |= vcpu->arch.efer != sregs->efer;
@@ -9276,6 +9270,14 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	if (cpuid_update_needed)
 		kvm_update_cpuid_runtime(vcpu);
 
+	if (vcpu->arch.vmsa_encrypted)
+		goto tracking_regs;
+
+	vcpu->arch.cr2 = sregs->cr2;
+	mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3;
+	vcpu->arch.cr3 = sregs->cr3;
+	kvm_register_mark_available(vcpu, VCPU_EXREG_CR3);
+
 	idx = srcu_read_lock(&vcpu->kvm->srcu);
 	if (is_pae_paging(vcpu)) {
 		load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu));
@@ -9283,16 +9285,12 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	}
 	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 
-	if (mmu_reset_needed)
-		kvm_mmu_reset_context(vcpu);
-
-	max_bits = KVM_NR_INTERRUPTS;
-	pending_vec = find_first_bit(
-		(const unsigned long *)sregs->interrupt_bitmap, max_bits);
-	if (pending_vec < max_bits) {
-		kvm_queue_interrupt(vcpu, pending_vec, false);
-		pr_debug("Set back pending irq %d\n", pending_vec);
-	}
+	dt.size = sregs->idt.limit;
+	dt.address = sregs->idt.base;
+	kvm_x86_ops.set_idt(vcpu, &dt);
+	dt.size = sregs->gdt.limit;
+	dt.address = sregs->gdt.base;
+	kvm_x86_ops.set_gdt(vcpu, &dt);
 
 	kvm_set_segment(vcpu, &sregs->cs, VCPU_SREG_CS);
 	kvm_set_segment(vcpu, &sregs->ds, VCPU_SREG_DS);
@@ -9312,6 +9310,18 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	    !is_protmode(vcpu))
 		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 
+tracking_regs:
+	if (mmu_reset_needed)
+		kvm_mmu_reset_context(vcpu);
+
+	max_bits = KVM_NR_INTERRUPTS;
+	pending_vec = find_first_bit(
+		(const unsigned long *)sregs->interrupt_bitmap, max_bits);
+	if (pending_vec < max_bits) {
+		kvm_queue_interrupt(vcpu, pending_vec, false);
+		pr_debug("Set back pending irq %d\n", pending_vec);
+	}
+
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 
 	ret = 0;
-- 
2.28.0

