linux-kernel - [PATCH v2 05/17] KVM: x86/mmu: Allocate pae_root and 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: <20210305011101.3597423-6-seanjc@google.com>
Date:   Thu,  4 Mar 2021 17:10:49 -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 v2 05/17] KVM: x86/mmu: Allocate pae_root and lm_root pages in
 dedicated helper

Move the on-demand allocation of the pae_root and lm_root pages, used by
nested NPT for 32-bit L1s, into a separate helper.  This will allow a
future patch to hold mmu_lock while allocating the non-special roots so
that make_mmu_pages_available() can be checked once at the start of root
allocation, and thus avoid having to deal with failure in the middle of
root allocation.

Signed-off-by: Sean Christopherson <seanjc@...gle.com>
---
 arch/x86/kvm/mmu/mmu.c | 84 +++++++++++++++++++++++++++---------------
 1 file changed, 54 insertions(+), 30 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 7cb5fb5d2d4d..dd9d5cc13a46 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3308,38 +3308,10 @@ 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 (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;
 
-	/*
-	 * 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 (mmu->shadow_root_level == PT64_ROOT_4LEVEL &&
-	    (!mmu->pae_root || !mmu->lm_root)) {
-		u64 *lm_root, *pae_root;
-
-		if (WARN_ON_ONCE(!tdp_enabled || mmu->pae_root || 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;
-		}
-
-		mmu->pae_root = pae_root;
-		mmu->lm_root = lm_root;
-
-		lm_root[0] = __pa(mmu->pae_root) | pm_mask;
+		mmu->lm_root[0] = __pa(mmu->pae_root) | pm_mask;
 	}
 
 	for (i = 0; i < 4; ++i) {
@@ -3373,6 +3345,55 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static int mmu_alloc_special_roots(struct kvm_vcpu *vcpu)
+{
+	struct kvm_mmu *mmu = vcpu->arch.mmu;
+	u64 *lm_root, *pae_root;
+
+	/*
+	 * 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 on 64-bit KVM is very rare.
+	 */
+	if (mmu->direct_map || mmu->root_level >= PT64_ROOT_4LEVEL ||
+	    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->lm_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->lm_root))
+		return -EIO;
+
+	/* Unlike 32-bit NPT, the PDP table doesn't need to be in low mem. */
+	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;
+	}
+
+	mmu->pae_root = pae_root;
+	mmu->lm_root = lm_root;
+
+	return 0;
+}
+
 static int mmu_alloc_roots(struct kvm_vcpu *vcpu)
 {
 	if (vcpu->arch.mmu->direct_map)
@@ -4820,6 +4841,9 @@ int kvm_mmu_load(struct kvm_vcpu *vcpu)
 	int r;
 
 	r = mmu_topup_memory_caches(vcpu, !vcpu->arch.mmu->direct_map);
+	if (r)
+		goto out;
+	r = mmu_alloc_special_roots(vcpu);
 	if (r)
 		goto out;
 	r = mmu_alloc_roots(vcpu);
-- 
2.30.1.766.gb4fecdf3b7-goog