linux-kernel - [PATCH 04/15] KVM: x86/mmu: Allocate the lm

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20210302184540.2829328-5-seanjc@google.com>
Date:   Tue,  2 Mar 2021 10:45:29 -0800
From:   Sean Christopherson <seanjc@...gle.com>
To:     Paolo Bonzini <pbonzini@...hat.com>
Cc:     Sean Christopherson <seanjc@...gle.com>,
        Vitaly Kuznetsov <vkuznets@...hat.com>,
        Wanpeng Li <wanpengli@...cent.com>,
        Jim Mattson <jmattson@...gle.com>,
        Joerg Roedel <joro@...tes.org>, kvm@...r.kernel.org,
        linux-kernel@...r.kernel.org, Ben Gardon <bgardon@...gle.com>,
        Brijesh Singh <brijesh.singh@....com>,
        Tom Lendacky <thomas.lendacky@....com>
Subject: [PATCH 04/15] KVM: x86/mmu: Allocate the lm_root before allocating
 PAE roots

Allocate lm_root before the PAE roots so that the PAE roots aren't
leaked if the memory allocation for the lm_root happens to fail.

Note, KVM can _still_ leak PAE roots if mmu_check_root() fails on a
guest's PDPTR.  That too will be fixed in a future commit.

Signed-off-by: Sean Christopherson <seanjc@...gle.com>
---
 arch/x86/kvm/mmu/mmu.c | 65 +++++++++++++++++++++---------------------
 1 file changed, 32 insertions(+), 33 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 1f129001a30c..e5c3701112f8 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3292,21 +3292,39 @@ 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;
-	if (vcpu->arch.mmu->shadow_root_level == PT64_ROOT_4LEVEL) {
+	if (vcpu->arch.mmu->shadow_root_level == PT64_ROOT_4LEVEL)
 		pm_mask |= PT_ACCESSED_MASK | PT_WRITABLE_MASK | PT_USER_MASK;
 
-		/*
-		 * Allocate the page for the PDPTEs when shadowing 32-bit NPT
-		 * with 64-bit only when needed.  Unlike 32-bit NPT, it doesn't
-		 * need to be in low mem.  See also lm_root below.
-		 */
-		if (!vcpu->arch.mmu->pae_root) {
-			WARN_ON_ONCE(!tdp_enabled);
+	/*
+	 * When shadowing 32-bit or PAE NPT with 64-bit NPT, the PML4 and PDP
+	 * tables are allocated and initialized at root creation as there is no
+	 * equivalent level in the guest's NPT to shadow.  Allocate the tables
+	 * on demand, as running a 32-bit L1 VMM is very rare.  Unlike 32-bit
+	 * NPT, the PDP table doesn't need to be in low mem.  Preallocate the
+	 * pages so that the PAE roots aren't leaked on failure.
+	 */
+	if (vcpu->arch.mmu->shadow_root_level == PT64_ROOT_4LEVEL &&
+	    (!vcpu->arch.mmu->pae_root || !vcpu->arch.mmu->lm_root)) {
+		u64 *lm_root, *pae_root;
 
-			vcpu->arch.mmu->pae_root = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT);
-			if (!vcpu->arch.mmu->pae_root)
-				return -ENOMEM;
+		if (WARN_ON_ONCE(!tdp_enabled || vcpu->arch.mmu->pae_root ||
+				 vcpu->arch.mmu->lm_root))
+			return -EIO;
+
+		pae_root = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT);
+		if (!pae_root)
+			return -ENOMEM;
+
+		lm_root = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT);
+		if (!lm_root) {
+			free_page((unsigned long)pae_root);
+			return -ENOMEM;
 		}
+
+		vcpu->arch.mmu->pae_root = pae_root;
+		vcpu->arch.mmu->lm_root = lm_root;
+
+		lm_root[0] = __pa(vcpu->arch.mmu->pae_root) | pm_mask;
 	}
 
 	for (i = 0; i < 4; ++i) {
@@ -3327,30 +3345,11 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
 				      PT32_ROOT_LEVEL, false);
 		vcpu->arch.mmu->pae_root[i] = root | pm_mask;
 	}
-	vcpu->arch.mmu->root_hpa = __pa(vcpu->arch.mmu->pae_root);
-
-	/*
-	 * When shadowing 32-bit or PAE NPT with 64-bit NPT, the PML4 and PDP
-	 * tables are allocated and initialized at MMU creation as there is no
-	 * equivalent level in the guest's NPT to shadow.  Allocate the tables
-	 * on demand, as running a 32-bit L1 VMM is very rare.  The PDP is
-	 * handled above (to share logic with PAE), deal with the PML4 here.
-	 */
-	if (vcpu->arch.mmu->shadow_root_level == PT64_ROOT_4LEVEL) {
-		if (vcpu->arch.mmu->lm_root == NULL) {
-			u64 *lm_root;
-
-			lm_root = (void*)get_zeroed_page(GFP_KERNEL_ACCOUNT);
-			if (!lm_root)
-				return -ENOMEM;
-
-			lm_root[0] = __pa(vcpu->arch.mmu->pae_root) | pm_mask;
-
-			vcpu->arch.mmu->lm_root = lm_root;
-		}
 
+	if (vcpu->arch.mmu->shadow_root_level == PT64_ROOT_4LEVEL)
 		vcpu->arch.mmu->root_hpa = __pa(vcpu->arch.mmu->lm_root);
-	}
+	else
+		vcpu->arch.mmu->root_hpa = __pa(vcpu->arch.mmu->pae_root);
 
 set_root_pgd:
 	vcpu->arch.mmu->root_pgd = root_pgd;
-- 
2.30.1.766.gb4fecdf3b7-goog