| 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
| ||
|
Message-ID: <b0890a74-96ab-478b-967c-31769a02e509@lucifer.local>
Date: Thu, 15 Jan 2026 09:15:51 +0000
From: Lorenzo Stoakes <lorenzo.stoakes@...cle.com>
To: Andrew Morton <akpm@...ux-foundation.org>
Cc: Suren Baghdasaryan <surenb@...gle.com>,
"Liam R . Howlett" <Liam.Howlett@...cle.com>,
Vlastimil Babka <vbabka@...e.cz>,
Shakeel Butt <shakeel.butt@...ux.dev>,
David Hildenbrand <david@...nel.org>, Rik van Riel <riel@...riel.com>,
Harry Yoo <harry.yoo@...cle.com>, Jann Horn <jannh@...gle.com>,
Mike Rapoport <rppt@...nel.org>, Michal Hocko <mhocko@...e.com>,
Pedro Falcato <pfalcato@...e.de>, Chris Li <chriscli@...gle.com>,
Barry Song <v-songbaohua@...o.com>, linux-mm@...ck.org,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH v2 1/8] mm/rmap: improve anon_vma_clone(),
unlink_anon_vmas() comments, add asserts
On Wed, Jan 14, 2026 at 01:59:11PM -0800, Andrew Morton wrote:
> On Wed, 14 Jan 2026 19:02:20 +0000 Lorenzo Stoakes <lorenzo.stoakes@...cle.com> wrote:
>
> > Can you apply the below fix-patch to this to fix up a rather silly
> > failure-to-unlock mistake that Suren picked up on?
> >
> > Luckily this partial unmap function is unlikely to ever be triggerable in real
> > life, AND more to the point - a later patch completely eliminates the locking -
> > but to avoid bisection hazard let's fix this.
> >
> > Note that there is a conflict at 'mm/rmap: allocate anon_vma_chain objects
> > unlocked when possible', please resolve it by just taking that patch and
> > dropping _everything_ from this one _including_ the trailing 'if (root) ...'
> > code.
>
> No probs.
> mm-rmap-allocate-anon_vma_chain-objects-unlocked-when-possible.patch is
> now
LGTM, appreciate it thanks! :)
Cheers, Lorenzo
>
> --- a/mm/rmap.c~mm-rmap-allocate-anon_vma_chain-objects-unlocked-when-possible
> +++ a/mm/rmap.c
> @@ -147,14 +147,13 @@ static void anon_vma_chain_free(struct a
> kmem_cache_free(anon_vma_chain_cachep, anon_vma_chain);
> }
>
> -static void anon_vma_chain_link(struct vm_area_struct *vma,
> - struct anon_vma_chain *avc,
> - struct anon_vma *anon_vma)
> +static void anon_vma_chain_assign(struct vm_area_struct *vma,
> + struct anon_vma_chain *avc,
> + struct anon_vma *anon_vma)
> {
> avc->vma = vma;
> avc->anon_vma = anon_vma;
> list_add(&avc->same_vma, &vma->anon_vma_chain);
> - anon_vma_interval_tree_insert(avc, &anon_vma->rb_root);
> }
>
> /**
> @@ -211,7 +210,8 @@ int __anon_vma_prepare(struct vm_area_st
> spin_lock(&mm->page_table_lock);
> if (likely(!vma->anon_vma)) {
> vma->anon_vma = anon_vma;
> - anon_vma_chain_link(vma, avc, anon_vma);
> + anon_vma_chain_assign(vma, avc, anon_vma);
> + anon_vma_interval_tree_insert(avc, &anon_vma->rb_root);
> anon_vma->num_active_vmas++;
> allocated = NULL;
> avc = NULL;
> @@ -292,21 +292,31 @@ int anon_vma_clone(struct vm_area_struct
>
> check_anon_vma_clone(dst, src);
>
> - /* All anon_vma's share the same root. */
> + /*
> + * Allocate AVCs. We don't need an anon_vma lock for this as we
> + * are not updating the anon_vma rbtree nor are we changing
> + * anon_vma statistics.
> + *
> + * We hold the exclusive mmap write lock so there's no possibliity of
> + * the unlinked AVC's being observed yet.
> + */
> + list_for_each_entry(pavc, &src->anon_vma_chain, same_vma) {
> + avc = anon_vma_chain_alloc(GFP_KERNEL);
> + if (!avc)
> + goto enomem_failure;
> +
> + anon_vma_chain_assign(dst, avc, pavc->anon_vma);
> + }
> +
> + /*
> + * Now link the anon_vma's back to the newly inserted AVCs.
> + * Note that all anon_vma's share the same root.
> + */
> anon_vma_lock_write(src->anon_vma);
> - list_for_each_entry_reverse(pavc, &src->anon_vma_chain, same_vma) {
> - struct anon_vma *anon_vma;
> + list_for_each_entry_reverse(avc, &dst->anon_vma_chain, same_vma) {
> + struct anon_vma *anon_vma = avc->anon_vma;
>
> - avc = anon_vma_chain_alloc(GFP_NOWAIT);
> - if (unlikely(!avc)) {
> - anon_vma_unlock_write(src->anon_vma);
> - avc = anon_vma_chain_alloc(GFP_KERNEL);
> - if (!avc)
> - goto enomem_failure;
> - anon_vma_lock_write(src->anon_vma);
> - }
> - anon_vma = pavc->anon_vma;
> - anon_vma_chain_link(dst, avc, anon_vma);
> + anon_vma_interval_tree_insert(avc, &anon_vma->rb_root);
>
> /*
> * Reuse existing anon_vma if it has no vma and only one
> @@ -322,7 +332,6 @@ int anon_vma_clone(struct vm_area_struct
> }
> if (dst->anon_vma)
> dst->anon_vma->num_active_vmas++;
> -
> anon_vma_unlock_write(src->anon_vma);
> return 0;
>
> @@ -384,8 +393,10 @@ int anon_vma_fork(struct vm_area_struct
> get_anon_vma(anon_vma->root);
> /* Mark this anon_vma as the one where our new (COWed) pages go. */
> vma->anon_vma = anon_vma;
> + anon_vma_chain_assign(vma, avc, anon_vma);
> + /* Now let rmap see it. */
> anon_vma_lock_write(anon_vma);
> - anon_vma_chain_link(vma, avc, anon_vma);
> + anon_vma_interval_tree_insert(avc, &anon_vma->rb_root);
> anon_vma->parent->num_children++;
> anon_vma_unlock_write(anon_vma);
>
> @@ -402,40 +413,18 @@ int anon_vma_fork(struct vm_area_struct
> * In the unfortunate case of anon_vma_clone() failing to allocate memory we
> * have to clean things up.
> *
> - * On clone we hold the exclusive mmap write lock, so we can't race
> - * unlink_anon_vmas(). Since we're cloning, we know we can't have empty
> - * anon_vma's, since existing anon_vma's are what we're cloning from.
> - *
> - * So this function needs only traverse the anon_vma_chain and free each
> - * allocated anon_vma_chain.
> + * Since we allocate anon_vma_chain's before we insert them into the interval
> + * trees, we simply have to free up the AVC's and remove the entries from the
> + * VMA's anon_vma_chain.
> */
> static void cleanup_partial_anon_vmas(struct vm_area_struct *vma)
> {
> struct anon_vma_chain *avc, *next;
> - struct anon_vma *root = NULL;
> -
> - /*
> - * We exclude everybody else from being able to modify anon_vma's
> - * underneath us.
> - */
> - mmap_assert_locked(vma->vm_mm);
>
> list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) {
> - struct anon_vma *anon_vma = avc->anon_vma;
> -
> - /* All anon_vma's share the same root. */
> - if (!root) {
> - root = anon_vma->root;
> - anon_vma_lock_write(root);
> - }
> -
> - anon_vma_interval_tree_remove(avc, &anon_vma->rb_root);
> list_del(&avc->same_vma);
> anon_vma_chain_free(avc);
> }
> -
> - if (root)
> - anon_vma_unlock_write(root);
> }
>
> /**
> _
>
Powered by blists - more mailing lists