KVM: x86: Allow deflecting unknown MSR accesses to user space

MSRs are weird. Some of them are normal control registers, such as EFER.
Some however are registers that really are model specific, not very
interesting to virtualization workloads, and not performance critical.
Others again are really just windows into package configuration.

Out of these MSRs, only the first category is necessary to implement in
kernel space. Rarely accessed MSRs, MSRs that should be fine tunes against
certain CPU models and MSRs that contain information on the package level
are much better suited for user space to process. However, over time we have
accumulated a lot of MSRs that are not the first category, but still handled
by in-kernel KVM code.

This patch adds a generic interface to handle WRMSR and RDMSR from user
space. With this, any future MSR that is part of the latter categories can
be handled in user space.

Furthermore, it allows us to replace the existing "ignore_msrs" logic with
something that applies per-VM rather than on the full system. That way you
can run productive VMs in parallel to experimental ones where you don't care
about proper MSR handling.

Signed-off-by: Alexander Graf <graf@amazon.com>
Reviewed-by: Jim Mattson <jmattson@google.com>

Message-Id: <20200925143422.21718-3-graf@amazon.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

3 files changed, 135 insertions, 6 deletions

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 5d4c39c37390..dd2665504dc0 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -961,6 +961,9 @@ struct kvm_arch {
 	bool guest_can_read_msr_platform_info;
 	bool exception_payload_enabled;
 
+	/* Deflect RDMSR and WRMSR to user space when they trigger a #GP */
+	u32 user_space_msr_mask;
+
 	struct kvm_pmu_event_filter *pmu_event_filter;
 	struct task_struct *nx_lpage_recovery_thread;
 };
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 85111cd0adcd..0cc0db500f71 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -3701,11 +3701,18 @@ static int em_dr_write(struct x86_emulate_ctxt *ctxt)
 
 static int em_wrmsr(struct x86_emulate_ctxt *ctxt)
 {
+	u64 msr_index = reg_read(ctxt, VCPU_REGS_RCX);
 	u64 msr_data;
+	int r;
 
 	msr_data = (u32)reg_read(ctxt, VCPU_REGS_RAX)
 		| ((u64)reg_read(ctxt, VCPU_REGS_RDX) << 32);
-	if (ctxt->ops->set_msr(ctxt, reg_read(ctxt, VCPU_REGS_RCX), msr_data))
+	r = ctxt->ops->set_msr(ctxt, msr_index, msr_data);
+
+	if (r == X86EMUL_IO_NEEDED)
+		return r;
+
+	if (r)
 		return emulate_gp(ctxt, 0);
 
 	return X86EMUL_CONTINUE;
@@ -3713,9 +3720,16 @@ static int em_wrmsr(struct x86_emulate_ctxt *ctxt)
 
 static int em_rdmsr(struct x86_emulate_ctxt *ctxt)
 {
+	u64 msr_index = reg_read(ctxt, VCPU_REGS_RCX);
 	u64 msr_data;
+	int r;
+
+	r = ctxt->ops->get_msr(ctxt, msr_index, &msr_data);
+
+	if (r == X86EMUL_IO_NEEDED)
+		return r;
 
-	if (ctxt->ops->get_msr(ctxt, reg_read(ctxt, VCPU_REGS_RCX), &msr_data))
+	if (r)
 		return emulate_gp(ctxt, 0);
 
 	*reg_write(ctxt, VCPU_REGS_RAX) = (u32)msr_data;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 43173382f02f..af6d008145cd 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1590,12 +1590,89 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data)
 }
 EXPORT_SYMBOL_GPL(kvm_set_msr);
 
+static int complete_emulated_msr(struct kvm_vcpu *vcpu, bool is_read)
+{
+	if (vcpu->run->msr.error) {
+		kvm_inject_gp(vcpu, 0);
+		return 1;
+	} else if (is_read) {
+		kvm_rax_write(vcpu, (u32)vcpu->run->msr.data);
+		kvm_rdx_write(vcpu, vcpu->run->msr.data >> 32);
+	}
+
+	return kvm_skip_emulated_instruction(vcpu);
+}
+
+static int complete_emulated_rdmsr(struct kvm_vcpu *vcpu)
+{
+	return complete_emulated_msr(vcpu, true);
+}
+
+static int complete_emulated_wrmsr(struct kvm_vcpu *vcpu)
+{
+	return complete_emulated_msr(vcpu, false);
+}
+
+static u64 kvm_msr_reason(int r)
+{
+	switch (r) {
+	case -ENOENT:
+		return KVM_MSR_EXIT_REASON_UNKNOWN;
+	default:
+		return KVM_MSR_EXIT_REASON_INVAL;
+	}
+}
+
+static int kvm_msr_user_space(struct kvm_vcpu *vcpu, u32 index,
+			      u32 exit_reason, u64 data,
+			      int (*completion)(struct kvm_vcpu *vcpu),
+			      int r)
+{
+	u64 msr_reason = kvm_msr_reason(r);
+
+	/* Check if the user wanted to know about this MSR fault */
+	if (!(vcpu->kvm->arch.user_space_msr_mask & msr_reason))
+		return 0;
+
+	vcpu->run->exit_reason = exit_reason;
+	vcpu->run->msr.error = 0;
+	memset(vcpu->run->msr.pad, 0, sizeof(vcpu->run->msr.pad));
+	vcpu->run->msr.reason = msr_reason;
+	vcpu->run->msr.index = index;
+	vcpu->run->msr.data = data;
+	vcpu->arch.complete_userspace_io = completion;
+
+	return 1;
+}
+
+static int kvm_get_msr_user_space(struct kvm_vcpu *vcpu, u32 index, int r)
+{
+	return kvm_msr_user_space(vcpu, index, KVM_EXIT_X86_RDMSR, 0,
+				   complete_emulated_rdmsr, r);
+}
+
+static int kvm_set_msr_user_space(struct kvm_vcpu *vcpu, u32 index, u64 data, int r)
+{
+	return kvm_msr_user_space(vcpu, index, KVM_EXIT_X86_WRMSR, data,
+				   complete_emulated_wrmsr, r);
+}
+
 int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu)
 {
 	u32 ecx = kvm_rcx_read(vcpu);
 	u64 data;
+	int r;
+
+	r = kvm_get_msr(vcpu, ecx, &data);
 
-	if (kvm_get_msr(vcpu, ecx, &data)) {
+	/* MSR read failed? See if we should ask user space */
+	if (r && kvm_get_msr_user_space(vcpu, ecx, r)) {
+		/* Bounce to user space */
+		return 0;
+	}
+
+	/* MSR read failed? Inject a #GP */
+	if (r) {
 		trace_kvm_msr_read_ex(ecx);
 		kvm_inject_gp(vcpu, 0);
 		return 1;
@@ -1613,8 +1690,18 @@ int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu)
 {
 	u32 ecx = kvm_rcx_read(vcpu);
 	u64 data = kvm_read_edx_eax(vcpu);
+	int r;
 
-	if (kvm_set_msr(vcpu, ecx, data)) {
+	r = kvm_set_msr(vcpu, ecx, data);
+
+	/* MSR write failed? See if we should ask user space */
+	if (r && kvm_set_msr_user_space(vcpu, ecx, data, r)) {
+		/* Bounce to user space */
+		return 0;
+	}
+
+	/* MSR write failed? Inject a #GP */
+	if (r) {
 		trace_kvm_msr_write_ex(ecx, data);
 		kvm_inject_gp(vcpu, 0);
 		return 1;
@@ -3526,6 +3613,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_EXCEPTION_PAYLOAD:
 	case KVM_CAP_SET_GUEST_DEBUG:
 	case KVM_CAP_LAST_CPU:
+	case KVM_CAP_X86_USER_SPACE_MSR:
 		r = 1;
 		break;
 	case KVM_CAP_SYNC_REGS:
@@ -5046,6 +5134,10 @@ split_irqchip_unlock:
 		kvm->arch.exception_payload_enabled = cap->args[0];
 		r = 0;
 		break;
+	case KVM_CAP_X86_USER_SPACE_MSR:
+		kvm->arch.user_space_msr_mask = cap->args[0];
+		r = 0;
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -6378,13 +6470,33 @@ static void emulator_set_segment(struct x86_emulate_ctxt *ctxt, u16 selector,
 static int emulator_get_msr(struct x86_emulate_ctxt *ctxt,
 			    u32 msr_index, u64 *pdata)
 {
-	return kvm_get_msr(emul_to_vcpu(ctxt), msr_index, pdata);
+	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
+	int r;
+
+	r = kvm_get_msr(vcpu, msr_index, pdata);
+
+	if (r && kvm_get_msr_user_space(vcpu, msr_index, r)) {
+		/* Bounce to user space */
+		return X86EMUL_IO_NEEDED;
+	}
+
+	return r;
 }
 
 static int emulator_set_msr(struct x86_emulate_ctxt *ctxt,
 			    u32 msr_index, u64 data)
 {
-	return kvm_set_msr(emul_to_vcpu(ctxt), msr_index, data);
+	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
+	int r;
+
+	r = kvm_set_msr(vcpu, msr_index, data);
+
+	if (r && kvm_set_msr_user_space(vcpu, msr_index, data, r)) {
+		/* Bounce to user space */
+		return X86EMUL_IO_NEEDED;
+	}
+
+	return r;
 }
 
 static u64 emulator_get_smbase(struct x86_emulate_ctxt *ctxt)