linux-kernel - Re: [RFC PATCH 1/3] KVM: arm64: Fix possible memory leak in kvm stage2

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 for Android: free password hash cracker in your pocket
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20201201141632.GC26973@willie-the-truck>
Date:   Tue, 1 Dec 2020 14:16:33 +0000
From:   Will Deacon <will@...nel.org>
To:     "wangyanan (Y)" <wangyanan55@...wei.com>
Cc:     linux-kernel@...r.kernel.org, linux-arm-kernel@...ts.infradead.org,
        Marc Zyngier <maz@...nel.org>,
        Catalin Marinas <catalin.marinas@....com>,
        James Morse <james.morse@....com>,
        Julien Thierry <julien.thierry.kdev@...il.com>,
        Suzuki K Poulose <suzuki.poulose@....com>,
        Gavin Shan <gshan@...hat.com>,
        Quentin Perret <qperret@...gle.com>,
        wanghaibin.wang@...wei.com, yezengruan@...wei.com,
        zhukeqian1@...wei.com, yuzenghui@...wei.com,
        jiangkunkun@...wei.com, wangjingyi11@...wei.com,
        lushenming@...wei.com
Subject: Re: [RFC PATCH 1/3] KVM: arm64: Fix possible memory leak in kvm
 stage2

On Tue, Dec 01, 2020 at 03:21:23PM +0800, wangyanan (Y) wrote:
> On 2020/11/30 21:21, Will Deacon wrote:
> > On Mon, Nov 30, 2020 at 08:18:45PM +0800, Yanan Wang wrote:
> > > diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
> > > index 0271b4a3b9fe..696b6aa83faf 100644
> > > --- a/arch/arm64/kvm/hyp/pgtable.c
> > > +++ b/arch/arm64/kvm/hyp/pgtable.c
> > > @@ -186,6 +186,7 @@ static bool kvm_set_valid_leaf_pte(kvm_pte_t *ptep, u64 pa, kvm_pte_t attr,
> > >   		return old == pte;
> > >   	smp_store_release(ptep, pte);
> > > +	get_page(virt_to_page(ptep));
> > This is also used for the hypervisor stage-1 page-table, so I'd prefer to
> > leave this function as-is.
> I agree at this point.
> > >   	return true;
> > >   }
> > > @@ -476,6 +477,7 @@ static bool stage2_map_walker_try_leaf(u64 addr, u64 end, u32 level,
> > >   	/* There's an existing valid leaf entry, so perform break-before-make */
> > >   	kvm_set_invalid_pte(ptep);
> > >   	kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, data->mmu, addr, level);
> > > +	put_page(virt_to_page(ptep));
> > >   	kvm_set_valid_leaf_pte(ptep, phys, data->attr, level);
> > >   out:
> > >   	data->phys += granule;
> > Isn't this hunk alone sufficient to solve the problem?
> > 
> > Will
> > .
> 
> Not sufficient enough. When the old ptep is valid and old pte equlas new
> pte, in this case, "True" is also returned by kvm_set_valid_leaf_pte()
> 
> and get_page() will still be called.

I had a go at fixing this without introducing refcounting to the hyp stage-1
case, and ended up with the diff below. What do you think?

Will

--->8

diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 0271b4a3b9fe..78e2c0dc47ae 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -170,23 +170,16 @@ static void kvm_set_table_pte(kvm_pte_t *ptep, kvm_pte_t *childp)
 	smp_store_release(ptep, pte);
 }
 
-static bool kvm_set_valid_leaf_pte(kvm_pte_t *ptep, u64 pa, kvm_pte_t attr,
-				   u32 level)
+static kvm_pte_t kvm_init_valid_leaf_pte(u64 pa, kvm_pte_t attr, u32 level)
 {
-	kvm_pte_t old = *ptep, pte = kvm_phys_to_pte(pa);
+	kvm_pte_t pte = kvm_phys_to_pte(pa);
 	u64 type = (level == KVM_PGTABLE_MAX_LEVELS - 1) ? KVM_PTE_TYPE_PAGE :
 							   KVM_PTE_TYPE_BLOCK;
 
 	pte |= attr & (KVM_PTE_LEAF_ATTR_LO | KVM_PTE_LEAF_ATTR_HI);
 	pte |= FIELD_PREP(KVM_PTE_TYPE, type);
 	pte |= KVM_PTE_VALID;
-
-	/* Tolerate KVM recreating the exact same mapping. */
-	if (kvm_pte_valid(old))
-		return old == pte;
-
-	smp_store_release(ptep, pte);
-	return true;
+	return pte;
 }
 
 static int kvm_pgtable_visitor_cb(struct kvm_pgtable_walk_data *data, u64 addr,
@@ -341,12 +334,17 @@ static int hyp_map_set_prot_attr(enum kvm_pgtable_prot prot,
 static bool hyp_map_walker_try_leaf(u64 addr, u64 end, u32 level,
 				    kvm_pte_t *ptep, struct hyp_map_data *data)
 {
+	kvm_pte_t new, old = *ptep;
 	u64 granule = kvm_granule_size(level), phys = data->phys;
 
 	if (!kvm_block_mapping_supported(addr, end, phys, level))
 		return false;
 
-	WARN_ON(!kvm_set_valid_leaf_pte(ptep, phys, data->attr, level));
+	/* Tolerate KVM recreating the exact same mapping. */
+	new = kvm_init_valid_leaf_pte(phys, data->attr, level);
+	if (old != new && !WARN_ON(kvm_pte_valid(old)))
+		smp_store_release(ptep, new);
+
 	data->phys += granule;
 	return true;
 }
@@ -465,19 +463,24 @@ static bool stage2_map_walker_try_leaf(u64 addr, u64 end, u32 level,
 				       kvm_pte_t *ptep,
 				       struct stage2_map_data *data)
 {
+	kvm_pte_t new, old = *ptep;
 	u64 granule = kvm_granule_size(level), phys = data->phys;
 
 	if (!kvm_block_mapping_supported(addr, end, phys, level))
 		return false;
 
-	if (kvm_set_valid_leaf_pte(ptep, phys, data->attr, level))
-		goto out;
+	new = kvm_init_valid_leaf_pte(phys, data->attr, level);
+	if (kvm_pte_valid(old)) {
+		/*
+		 * There's an existing valid leaf entry, so perform
+		 * break-before-make.
+		 */
+		kvm_set_invalid_pte(ptep);
+		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, data->mmu, addr, level);
+		put_page(virt_to_page(ptep));
+	}
 
-	/* There's an existing valid leaf entry, so perform break-before-make */
-	kvm_set_invalid_pte(ptep);
-	kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, data->mmu, addr, level);
-	kvm_set_valid_leaf_pte(ptep, phys, data->attr, level);
-out:
+	smp_store_release(ptep, new);
 	data->phys += granule;
 	return true;
 }