[RFC PATCH v5 072/104] KVM: TDX: handle vcpu migration over logical processor

[isaku . yamahata]

From: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>

For vcpu migration, in the case of VMX, VCMS is flushed on the source pcpu,
and load it on the target pcpu.  There are corresponding TDX SEAMCALL APIs,
call them on vcpu migration.  The logic is mostly same as VMX except the
TDX SEAMCALLs are used.

Signed-off-by: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>
---
 arch/x86/kvm/vmx/main.c    | 20 +++++++++++++--
 arch/x86/kvm/vmx/tdx.c     | 51 ++++++++++++++++++++++++++++++++++++++
 arch/x86/kvm/vmx/x86_ops.h |  2 ++
 3 files changed, 71 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index f9d43f2de145..2cd5ba0e8788 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -121,6 +121,14 @@ static fastpath_t vt_vcpu_run(struct kvm_vcpu *vcpu)
 	return vmx_vcpu_run(vcpu);
 }
 
+static void vt_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	if (is_td_vcpu(vcpu))
+		return tdx_vcpu_load(vcpu, cpu);
+
+	return vmx_vcpu_load(vcpu, cpu);
+}
+
 static void vt_flush_tlb_all(struct kvm_vcpu *vcpu)
 {
 	if (is_td_vcpu(vcpu))
@@ -162,6 +170,14 @@ static void vt_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa,
 	vmx_load_mmu_pgd(vcpu, root_hpa, pgd_level);
 }
 
+static void vt_sched_in(struct kvm_vcpu *vcpu, int cpu)
+{
+	if (is_td_vcpu(vcpu))
+		return;
+
+	vmx_sched_in(vcpu, cpu);
+}
+
 static int vt_mem_enc_op(struct kvm *kvm, void __user *argp)
 {
 	if (!is_td(kvm))
@@ -199,7 +215,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.vcpu_reset = vt_vcpu_reset,
 
 	.prepare_guest_switch = vt_prepare_switch_to_guest,
-	.vcpu_load = vmx_vcpu_load,
+	.vcpu_load = vt_vcpu_load,
 	.vcpu_put = vt_vcpu_put,
 
 	.update_exception_bitmap = vmx_update_exception_bitmap,
@@ -285,7 +301,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 
 	.request_immediate_exit = vmx_request_immediate_exit,
 
-	.sched_in = vmx_sched_in,
+	.sched_in = vt_sched_in,
 
 	.cpu_dirty_log_size = PML_ENTITY_NUM,
 	.update_cpu_dirty_logging = vmx_update_cpu_dirty_logging,
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index 37cf7d43435d..a6b1a8ce888d 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -85,6 +85,18 @@ static inline bool is_td_finalized(struct kvm_tdx *kvm_tdx)
 	return kvm_tdx->finalized;
 }
 
+static inline void tdx_disassociate_vp(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * Ensure tdx->cpu_list is updated is before setting vcpu->cpu to -1,
+	 * otherwise, a different CPU can see vcpu->cpu = -1 and add the vCPU
+	 * to its list before its deleted from this CPUs list.
+	 */
+	smp_wmb();
+
+	vcpu->cpu = -1;
+}
+
 static void tdx_clear_page(unsigned long page)
 {
 	const void *zero_page = (const void *) __va(page_to_phys(ZERO_PAGE(0)));
@@ -155,6 +167,39 @@ static void tdx_reclaim_td_page(struct tdx_td_page *page)
 	free_page(page->va);
 }
 
+static void tdx_flush_vp(void *arg)
+{
+	struct kvm_vcpu *vcpu = arg;
+	u64 err;
+
+	/* Task migration can race with CPU offlining. */
+	if (vcpu->cpu != raw_smp_processor_id())
+		return;
+
+	/*
+	 * No need to do TDH_VP_FLUSH if the vCPU hasn't been initialized.  The
+	 * list tracking still needs to be updated so that it's correct if/when
+	 * the vCPU does get initialized.
+	 */
+	if (is_td_vcpu_created(to_tdx(vcpu))) {
+		err = tdh_vp_flush(to_tdx(vcpu)->tdvpr.pa);
+		if (unlikely(err && err != TDX_VCPU_NOT_ASSOCIATED)) {
+			if (WARN_ON_ONCE(err))
+				pr_tdx_error(TDH_VP_FLUSH, err, NULL);
+		}
+	}
+
+	tdx_disassociate_vp(vcpu);
+}
+
+static void tdx_flush_vp_on_cpu(struct kvm_vcpu *vcpu)
+{
+	if (unlikely(vcpu->cpu == -1))
+		return;
+
+	smp_call_function_single(vcpu->cpu, tdx_flush_vp, vcpu, 1);
+}
+
 static int tdx_do_tdh_phymem_cache_wb(void *param)
 {
 	u64 err = 0;
@@ -425,6 +470,12 @@ int tdx_vcpu_create(struct kvm_vcpu *vcpu)
 	return ret;
 }
 
+void tdx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	if (vcpu->cpu != cpu)
+		tdx_flush_vp_on_cpu(vcpu);
+}
+
 void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_tdx *tdx = to_tdx(vcpu);
diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
index 8b871c5f52cf..ceafd6e18f4e 100644
--- a/arch/x86/kvm/vmx/x86_ops.h
+++ b/arch/x86/kvm/vmx/x86_ops.h
@@ -143,6 +143,7 @@ void tdx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
 fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu);
 void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu);
 void tdx_vcpu_put(struct kvm_vcpu *vcpu);
+void tdx_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
 
 int tdx_vm_ioctl(struct kvm *kvm, void __user *argp);
 int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp);
@@ -166,6 +167,7 @@ static inline void tdx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) {}
 static inline fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu) { return EXIT_FASTPATH_NONE; }
 static inline void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) {}
 static inline void tdx_vcpu_put(struct kvm_vcpu *vcpu) {}
+static inline void tdx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) {}
 
 static inline int tdx_vm_ioctl(struct kvm *kvm, void __user *argp) { return -EOPNOTSUPP; }
 static inline int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp) { return -EOPNOTSUPP; }
-- 
2.25.1