linux-kernel - [PATCH AUTOSEL 5.2 185/185] kvm: Nested KVM MMUs need PAE root too

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: <20190922184924.32534-185-sashal@kernel.org>
Date:   Sun, 22 Sep 2019 14:49:23 -0400
From:   Sasha Levin <sashal@...nel.org>
To:     linux-kernel@...r.kernel.org, stable@...r.kernel.org
Cc:     Jiří Paleček <jpalecek@....de>,
        Paolo Bonzini <pbonzini@...hat.com>,
        Sasha Levin <sashal@...nel.org>, kvm@...r.kernel.org
Subject: [PATCH AUTOSEL 5.2 185/185] kvm: Nested KVM MMUs need PAE root too

From: Jiří Paleček <jpalecek@....de>

[ Upstream commit 1cfff4d9a5d01fa61e5768a6afffc81ae1c8ecb9 ]

On AMD processors, in PAE 32bit mode, nested KVM instances don't
work. The L0 host get a kernel OOPS, which is related to
arch.mmu->pae_root being NULL.

The reason for this is that when setting up nested KVM instance,
arch.mmu is set to &arch.guest_mmu (while normally, it would be
&arch.root_mmu). However, the initialization and allocation of
pae_root only creates it in root_mmu. KVM code (ie. in
mmu_alloc_shadow_roots) then accesses arch.mmu->pae_root, which is the
unallocated arch.guest_mmu->pae_root.

This fix just allocates (and frees) pae_root in both guest_mmu and
root_mmu (and also lm_root if it was allocated). The allocation is
subject to previous restrictions ie. it won't allocate anything on
64-bit and AFAIK not on Intel.

Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=203923
Fixes: 14c07ad89f4d ("x86/kvm/mmu: introduce guest_mmu")
Signed-off-by: Jiri Palecek <jpalecek@....de>
Tested-by: Jiri Palecek <jpalecek@....de>
Signed-off-by: Paolo Bonzini <pbonzini@...hat.com>
Signed-off-by: Sasha Levin <sashal@...nel.org>
---
 arch/x86/kvm/mmu.c | 30 ++++++++++++++++++++++--------
 1 file changed, 22 insertions(+), 8 deletions(-)

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 66055ca29b6b4..9130152d5ed83 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -5607,13 +5607,13 @@ slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot,
 				 PT_PAGE_TABLE_LEVEL, lock_flush_tlb);
 }
 
-static void free_mmu_pages(struct kvm_vcpu *vcpu)
+static void free_mmu_pages(struct kvm_mmu *mmu)
 {
-	free_page((unsigned long)vcpu->arch.mmu->pae_root);
-	free_page((unsigned long)vcpu->arch.mmu->lm_root);
+	free_page((unsigned long)mmu->pae_root);
+	free_page((unsigned long)mmu->lm_root);
 }
 
-static int alloc_mmu_pages(struct kvm_vcpu *vcpu)
+static int alloc_mmu_pages(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
 {
 	struct page *page;
 	int i;
@@ -5634,9 +5634,9 @@ static int alloc_mmu_pages(struct kvm_vcpu *vcpu)
 	if (!page)
 		return -ENOMEM;
 
-	vcpu->arch.mmu->pae_root = page_address(page);
+	mmu->pae_root = page_address(page);
 	for (i = 0; i < 4; ++i)
-		vcpu->arch.mmu->pae_root[i] = INVALID_PAGE;
+		mmu->pae_root[i] = INVALID_PAGE;
 
 	return 0;
 }
@@ -5644,6 +5644,7 @@ static int alloc_mmu_pages(struct kvm_vcpu *vcpu)
 int kvm_mmu_create(struct kvm_vcpu *vcpu)
 {
 	uint i;
+	int ret;
 
 	vcpu->arch.mmu = &vcpu->arch.root_mmu;
 	vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
@@ -5661,7 +5662,19 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu)
 		vcpu->arch.guest_mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;
 
 	vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa;
-	return alloc_mmu_pages(vcpu);
+
+	ret = alloc_mmu_pages(vcpu, &vcpu->arch.guest_mmu);
+	if (ret)
+		return ret;
+
+	ret = alloc_mmu_pages(vcpu, &vcpu->arch.root_mmu);
+	if (ret)
+		goto fail_allocate_root;
+
+	return ret;
+ fail_allocate_root:
+	free_mmu_pages(&vcpu->arch.guest_mmu);
+	return ret;
 }
 
 
@@ -6134,7 +6147,8 @@ unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm)
 void kvm_mmu_destroy(struct kvm_vcpu *vcpu)
 {
 	kvm_mmu_unload(vcpu);
-	free_mmu_pages(vcpu);
+	free_mmu_pages(&vcpu->arch.root_mmu);
+	free_mmu_pages(&vcpu->arch.guest_mmu);
 	mmu_free_memory_caches(vcpu);
 }
 
-- 
2.20.1