[PATCH v2 2/3] KVM: x86: Handle the case of 5-level shadow page table

[Wei Huang <wei.huang2@amd.com>]

When the 5-level page table CPU flag is exposed, KVM code needs to handle
this case by pointing mmu->root_hpa to a properly-constructed 5-level page
table.

Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Wei Huang <wei.huang2@amd.com>
---
 arch/x86/include/asm/kvm_host.h |  1 +
 arch/x86/kvm/mmu/mmu.c          | 48 +++++++++++++++++++++------------
 2 files changed, 32 insertions(+), 17 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 6d16f75cc8da..5d66a94ca428 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -447,6 +447,7 @@ struct kvm_mmu {
 
 	u64 *pae_root;
 	u64 *pml4_root;
+	u64 *pml5_root;
 
 	/*
 	 * check zero bits on shadow page table entries, these
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index c11ee4531f6d..9985488c9524 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3430,7 +3430,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
 	 * the shadow page table may be a PAE or a long mode page table.
 	 */
 	pm_mask = PT_PRESENT_MASK | shadow_me_mask;
-	if (mmu->shadow_root_level == PT64_ROOT_4LEVEL) {
+	if (mmu->shadow_root_level >= PT64_ROOT_4LEVEL) {
 		pm_mask |= PT_ACCESSED_MASK | PT_WRITABLE_MASK | PT_USER_MASK;
 
 		if (WARN_ON_ONCE(!mmu->pml4_root)) {
@@ -3457,10 +3457,19 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
 		mmu->pae_root[i] = root | pm_mask;
 	}
 
-	if (mmu->shadow_root_level == PT64_ROOT_4LEVEL)
+	/*
+	 * Depending on the shadow_root_level, build the root_hpa table by
+	 * chaining either pml5->pml4->pae or pml4->pae.
+	 */
+	mmu->root_hpa = __pa(mmu->pae_root);
+	if (mmu->shadow_root_level >= PT64_ROOT_4LEVEL) {
+		mmu->pml4_root[0] = mmu->root_hpa | pm_mask;
 		mmu->root_hpa = __pa(mmu->pml4_root);
-	else
-		mmu->root_hpa = __pa(mmu->pae_root);
+	}
+	if (mmu->shadow_root_level == PT64_ROOT_5LEVEL) {
+		mmu->pml5_root[0] = mmu->root_hpa | pm_mask;
+		mmu->root_hpa = __pa(mmu->pml5_root);
+	}
 
 set_root_pgd:
 	mmu->root_pgd = root_pgd;
@@ -3473,7 +3482,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
 static int mmu_alloc_special_roots(struct kvm_vcpu *vcpu)
 {
 	struct kvm_mmu *mmu = vcpu->arch.mmu;
-	u64 *pml4_root, *pae_root;
+	u64 *pml5_root, *pml4_root, *pae_root;
 
 	/*
 	 * When shadowing 32-bit or PAE NPT with 64-bit NPT, the PML4 and PDP
@@ -3485,21 +3494,15 @@ static int mmu_alloc_special_roots(struct kvm_vcpu *vcpu)
 	    mmu->shadow_root_level < PT64_ROOT_4LEVEL)
 		return 0;
 
-	/*
-	 * This mess only works with 4-level paging and needs to be updated to
-	 * work with 5-level paging.
-	 */
-	if (WARN_ON_ONCE(mmu->shadow_root_level != PT64_ROOT_4LEVEL))
-		return -EIO;
-
-	if (mmu->pae_root && mmu->pml4_root)
+	if (mmu->pae_root && mmu->pml4_root && mmu->pml5_root)
 		return 0;
 
 	/*
 	 * The special roots should always be allocated in concert.  Yell and
 	 * bail if KVM ends up in a state where only one of the roots is valid.
 	 */
-	if (WARN_ON_ONCE(!tdp_enabled || mmu->pae_root || mmu->pml4_root))
+	if (WARN_ON_ONCE(!tdp_enabled || mmu->pae_root || mmu->pml4_root ||
+			 mmu->pml5_root))
 		return -EIO;
 
 	/*
@@ -3511,15 +3514,25 @@ static int mmu_alloc_special_roots(struct kvm_vcpu *vcpu)
 		return -ENOMEM;
 
 	pml4_root = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT);
-	if (!pml4_root) {
-		free_page((unsigned long)pae_root);
-		return -ENOMEM;
+	if (!pml4_root)
+		goto err_pml4;
+
+	if (mmu->shadow_root_level > PT64_ROOT_4LEVEL) {
+		pml5_root = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT);
+		if (!pml5_root)
+			goto err_pml5;
 	}
 
 	mmu->pae_root = pae_root;
 	mmu->pml4_root = pml4_root;
+	mmu->pml5_root = pml5_root;
 
 	return 0;
+err_pml5:
+	free_page((unsigned long)pml4_root);
+err_pml4:
+	free_page((unsigned long)pae_root);
+	return -ENOMEM;
 }
 
 void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
@@ -5338,6 +5351,7 @@ static void free_mmu_pages(struct kvm_mmu *mmu)
 		set_memory_encrypted((unsigned long)mmu->pae_root, 1);
 	free_page((unsigned long)mmu->pae_root);
 	free_page((unsigned long)mmu->pml4_root);
+	free_page((unsigned long)mmu->pml5_root);
 }
 
 static int __kvm_mmu_create(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
-- 
2.31.1