KVM: MMU: handle invalid root_hpa at __direct_map

Commit Message

Marcelo Tosatti Dec. 27, 2013, 7:43 p.m. UTC

On Sun, Dec 22, 2013 at 12:56:49PM -0200, Marcelo Tosatti wrote:
> On Sun, Dec 22, 2013 at 11:17:21AM +0200, Rom Freiman wrote:
> > Hello everyone,
> > 
> > I've been chasing this bug for a while.
> > 
> > According to my research, this bug fix is works fine for
> > 3.11.9-200.fc19.x86_64 kernel version (and I also came to almost similar
> > solution and really solved the crash).
> > 
> > But, the problem is, that it seems that this patch does not work on 3.13.0-rc2+
> > - it looks like the code flow is different and it crashes in ept_page_fault
> > and does not reach __direct_map:
> 
> Yep, similar problem, care to send a patch against
> 
> FNAME(page_fault), kvm_mmu_get_spte_hierarchy
> 
> Maybe there are more vulnerable sites, should secure them all.

These should cover all it?

--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Patch

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 31a5702..e50425d 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2832,6 +2832,9 @@  static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
 	bool ret = false;
 	u64 spte = 0ull;
 
+	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+		return false;
+
 	if (!page_fault_can_be_fast(error_code))
 		return false;
 
@@ -3227,6 +3230,9 @@  static u64 walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr)
 	struct kvm_shadow_walk_iterator iterator;
 	u64 spte = 0ull;
 
+	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+		return spte;
+
 	walk_shadow_page_lockless_begin(vcpu);
 	for_each_shadow_entry_lockless(vcpu, addr, iterator, spte)
 		if (!is_shadow_present_pte(spte))
@@ -4513,6 +4519,9 @@  int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4])
 	u64 spte;
 	int nr_sptes = 0;
 
+	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+		return nr_sptes;
+
 	walk_shadow_page_lockless_begin(vcpu);
 	for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) {
 		sptes[iterator.level-1] = spte;
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index ad75d77..cba218a 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -569,6 +569,9 @@  static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 	if (FNAME(gpte_changed)(vcpu, gw, top_level))
 		goto out_gpte_changed;
 
+	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+		goto out_gpte_changed;
+
 	for (shadow_walk_init(&it, vcpu, addr);
 	     shadow_walk_okay(&it) && it.level > gw->level;
 	     shadow_walk_next(&it)) {
@@ -820,6 +823,11 @@  static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
 	 */
 	mmu_topup_memory_caches(vcpu);
 
+	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) {
+		WARN_ON(1);
+		return;
+	}
+
 	spin_lock(&vcpu->kvm->mmu_lock);
 	for_each_shadow_entry(vcpu, gva, iterator) {
 		level = iterator.level;