[PATCH v2 07/24] KVM: TDX: Add load_mmu_pgd method for TDX

[Yan Zhao <yan.y.zhao@intel.com>]

From: Sean Christopherson <sean.j.christopherson@intel.com>

TDX uses two EPT pointers, one for the private half of the GPA space and
one for the shared half. The private half uses the normal EPT_POINTER vmcs
field, which is managed in a special way by the TDX module. For TDX, KVM is
not allowed to operate on it directly. The shared half uses a new
SHARED_EPT_POINTER field and will be managed by the conventional MMU
management operations that operate directly on the EPT root. This means for
TDX the .load_mmu_pgd() operation will need to know to use the
SHARED_EPT_POINTER field instead of the normal one. Add a new wrapper in
x86 ops for load_mmu_pgd() that either directs the write to the existing
vmx implementation or a TDX one.

tdx_load_mmu_pgd() is so much simpler than vmx_load_mmu_pgd() since for the
TDX mode of operation, EPT will always be used and KVM does not need to be
involved in virtualization of CR3 behavior. So tdx_load_mmu_pgd() can
simply write to SHARED_EPT_POINTER.

Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Co-developed-by: Isaku Yamahata <isaku.yamahata@intel.com>
Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
Co-developed-by: Rick Edgecombe <rick.p.edgecombe@intel.com>
Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com>
Co-developed-by: Yan Zhao <yan.y.zhao@intel.com>
Signed-off-by: Yan Zhao <yan.y.zhao@intel.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
---
TDX MMU part 2 v2:
-Check shared EPT level matches to direct bits mask in tdx_load_mmu_pgd()
 (Chao Gao)

TDX MMU part 2 v1:
- update the commit msg with the version rephrased by Rick.
  https://lore.kernel.org/all/78b1024ec3f5868e228baf797c6be98c5397bd49.camel@intel.com/

v19:
- Add WARN_ON_ONCE() to tdx_load_mmu_pgd() and drop unconditional mask
---
 arch/x86/include/asm/vmx.h |  1 +
 arch/x86/kvm/vmx/main.c    | 13 ++++++++++++-
 arch/x86/kvm/vmx/tdx.c     | 15 +++++++++++++++
 arch/x86/kvm/vmx/x86_ops.h |  4 ++++
 4 files changed, 32 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index f7fd4369b821..9298fb9d4bb3 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -256,6 +256,7 @@ enum vmcs_field {
 	TSC_MULTIPLIER_HIGH             = 0x00002033,
 	TERTIARY_VM_EXEC_CONTROL	= 0x00002034,
 	TERTIARY_VM_EXEC_CONTROL_HIGH	= 0x00002035,
+	SHARED_EPT_POINTER		= 0x0000203C,
 	PID_POINTER_TABLE		= 0x00002042,
 	PID_POINTER_TABLE_HIGH		= 0x00002043,
 	GUEST_PHYSICAL_ADDRESS          = 0x00002400,
diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index d28ffddd766f..3c292b4a063a 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -98,6 +98,17 @@ static void vt_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	vmx_vcpu_reset(vcpu, init_event);
 }
 
+static void vt_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa,
+			    int pgd_level)
+{
+	if (is_td_vcpu(vcpu)) {
+		tdx_load_mmu_pgd(vcpu, root_hpa, pgd_level);
+		return;
+	}
+
+	vmx_load_mmu_pgd(vcpu, root_hpa, pgd_level);
+}
+
 static int vt_mem_enc_ioctl(struct kvm *kvm, void __user *argp)
 {
 	if (!is_td(kvm))
@@ -229,7 +240,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.write_tsc_offset = vmx_write_tsc_offset,
 	.write_tsc_multiplier = vmx_write_tsc_multiplier,
 
-	.load_mmu_pgd = vmx_load_mmu_pgd,
+	.load_mmu_pgd = vt_load_mmu_pgd,
 
 	.check_intercept = vmx_check_intercept,
 	.handle_exit_irqoff = vmx_handle_exit_irqoff,
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index ed4473d0c2cd..785ee9f95504 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -28,6 +28,9 @@
 bool enable_tdx __ro_after_init;
 module_param_named(tdx, enable_tdx, bool, 0444);
 
+#define TDX_SHARED_BIT_PWL_5 gpa_to_gfn(BIT_ULL(51))
+#define TDX_SHARED_BIT_PWL_4 gpa_to_gfn(BIT_ULL(47))
+
 static enum cpuhp_state tdx_cpuhp_state;
 
 static const struct tdx_sys_info *tdx_sysinfo;
@@ -495,6 +498,18 @@ void tdx_vcpu_free(struct kvm_vcpu *vcpu)
 	tdx->state = VCPU_TD_STATE_UNINITIALIZED;
 }
 
+
+void tdx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int pgd_level)
+{
+	u64 shared_bit = (pgd_level == 5) ? TDX_SHARED_BIT_PWL_5 :
+			  TDX_SHARED_BIT_PWL_4;
+
+	if (KVM_BUG_ON(shared_bit != kvm_gfn_direct_bits(vcpu->kvm), vcpu->kvm))
+		return;
+
+	td_vmcs_write64(to_tdx(vcpu), SHARED_EPT_POINTER, root_hpa);
+}
+
 static int tdx_get_capabilities(struct kvm_tdx_cmd *cmd)
 {
 	const struct tdx_sys_info_td_conf *td_conf = &tdx_sysinfo->td_conf;
diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
index 4739891858ea..f49135094c94 100644
--- a/arch/x86/kvm/vmx/x86_ops.h
+++ b/arch/x86/kvm/vmx/x86_ops.h
@@ -129,6 +129,8 @@ int tdx_vcpu_create(struct kvm_vcpu *vcpu);
 void tdx_vcpu_free(struct kvm_vcpu *vcpu);
 
 int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp);
+
+void tdx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level);
 #else
 static inline int tdx_vm_init(struct kvm *kvm) { return -EOPNOTSUPP; }
 static inline void tdx_mmu_release_hkid(struct kvm *kvm) {}
@@ -140,6 +142,8 @@ static inline int tdx_vcpu_create(struct kvm_vcpu *vcpu) { return -EOPNOTSUPP; }
 static inline void tdx_vcpu_free(struct kvm_vcpu *vcpu) {}
 
 static inline int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp) { return -EOPNOTSUPP; }
+
+static inline void tdx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level) {}
 #endif
 
 #endif /* __KVM_X86_VMX_X86_OPS_H */
-- 
2.43.2