From: Jann Horn jannh@google.com
stable inclusion from stable-v4.19.257 commit 6dbfc25d68d922736381988d64156a649ccf7bf1 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I5USOP CVE: CVE-2022-42703
--------------------------------
commit 2555283eb40df89945557273121e9393ef9b542b upstream.
anon_vma->degree tracks the combined number of child anon_vmas and VMAs that use the anon_vma as their ->anon_vma.
anon_vma_clone() then assumes that for any anon_vma attached to src->anon_vma_chain other than src->anon_vma, it is impossible for it to be a leaf node of the VMA tree, meaning that for such VMAs ->degree is elevated by 1 because of a child anon_vma, meaning that if ->degree equals 1 there are no VMAs that use the anon_vma as their ->anon_vma.
This assumption is wrong because the ->degree optimization leads to leaf nodes being abandoned on anon_vma_clone() - an existing anon_vma is reused and no new parent-child relationship is created. So it is possible to reuse an anon_vma for one VMA while it is still tied to another VMA.
This is an issue because is_mergeable_anon_vma() and its callers assume that if two VMAs have the same ->anon_vma, the list of anon_vmas attached to the VMAs is guaranteed to be the same. When this assumption is violated, vma_merge() can merge pages into a VMA that is not attached to the corresponding anon_vma, leading to dangling page->mapping pointers that will be dereferenced during rmap walks.
Fix it by separately tracking the number of child anon_vmas and the number of VMAs using the anon_vma as their ->anon_vma.
Fixes: 7a3ef208e662 ("mm: prevent endless growth of anon_vma hierarchy") Cc: stable@kernel.org Acked-by: Michal Hocko mhocko@suse.com Acked-by: Vlastimil Babka vbabka@suse.cz Signed-off-by: Jann Horn jannh@google.com Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Ma Wupeng mawupeng1@huawei.com Reviewed-by: Kefeng Wang wangkefeng.wang@huawei.com Reviewed-by: Xiu Jianfeng xiujianfeng@huawei.com Signed-off-by: Yongqiang Liu liuyongqiang13@huawei.com --- include/linux/rmap.h | 7 +++++-- mm/rmap.c | 29 ++++++++++++++++------------- 2 files changed, 21 insertions(+), 15 deletions(-)
diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 91ccae946716..c80bd129e939 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -39,12 +39,15 @@ struct anon_vma { atomic_t refcount;
/* - * Count of child anon_vmas and VMAs which points to this anon_vma. + * Count of child anon_vmas. Equals to the count of all anon_vmas that + * have ->parent pointing to this one, including itself. * * This counter is used for making decision about reusing anon_vma * instead of forking new one. See comments in function anon_vma_clone. */ - unsigned degree; + unsigned long num_children; + /* Count of VMAs whose ->anon_vma pointer points to this object. */ + unsigned long num_active_vmas;
struct anon_vma *parent; /* Parent of this anon_vma */
diff --git a/mm/rmap.c b/mm/rmap.c index 2db733c42799..c336dacfac52 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -82,7 +82,8 @@ static inline struct anon_vma *anon_vma_alloc(void) anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL); if (anon_vma) { atomic_set(&anon_vma->refcount, 1); - anon_vma->degree = 1; /* Reference for first vma */ + anon_vma->num_children = 0; + anon_vma->num_active_vmas = 0; anon_vma->parent = anon_vma; /* * Initialise the anon_vma root to point to itself. If called @@ -190,6 +191,7 @@ int __anon_vma_prepare(struct vm_area_struct *vma) anon_vma = anon_vma_alloc(); if (unlikely(!anon_vma)) goto out_enomem_free_avc; + anon_vma->num_children++; /* self-parent link for new root */ allocated = anon_vma; }
@@ -199,8 +201,7 @@ int __anon_vma_prepare(struct vm_area_struct *vma) if (likely(!vma->anon_vma)) { vma->anon_vma = anon_vma; anon_vma_chain_link(vma, avc, anon_vma); - /* vma reference or self-parent link for new root */ - anon_vma->degree++; + anon_vma->num_active_vmas++; allocated = NULL; avc = NULL; } @@ -285,19 +286,19 @@ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) anon_vma_chain_link(dst, avc, anon_vma);
/* - * Reuse existing anon_vma if its degree lower than two, - * that means it has no vma and only one anon_vma child. + * Reuse existing anon_vma if it has no vma and only one + * anon_vma child. * - * Do not chose parent anon_vma, otherwise first child - * will always reuse it. Root anon_vma is never reused: + * Root anon_vma is never reused: * it has self-parent reference and at least one child. */ if (!dst->anon_vma && src->anon_vma && - anon_vma != src->anon_vma && anon_vma->degree < 2) + anon_vma->num_children < 2 && + anon_vma->num_active_vmas == 0) dst->anon_vma = anon_vma; } if (dst->anon_vma) - dst->anon_vma->degree++; + dst->anon_vma->num_active_vmas++; unlock_anon_vma_root(root); return 0;
@@ -347,6 +348,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) anon_vma = anon_vma_alloc(); if (!anon_vma) goto out_error; + anon_vma->num_active_vmas++; avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto out_error_free_anon_vma; @@ -367,7 +369,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) vma->anon_vma = anon_vma; anon_vma_lock_write(anon_vma); anon_vma_chain_link(vma, avc, anon_vma); - anon_vma->parent->degree++; + anon_vma->parent->num_children++; anon_vma_unlock_write(anon_vma);
return 0; @@ -399,7 +401,7 @@ void unlink_anon_vmas(struct vm_area_struct *vma) * to free them outside the lock. */ if (RB_EMPTY_ROOT(&anon_vma->rb_root.rb_root)) { - anon_vma->parent->degree--; + anon_vma->parent->num_children--; continue; }
@@ -407,7 +409,7 @@ void unlink_anon_vmas(struct vm_area_struct *vma) anon_vma_chain_free(avc); } if (vma->anon_vma) { - vma->anon_vma->degree--; + vma->anon_vma->num_active_vmas--;
/* * vma would still be needed after unlink, and anon_vma will be prepared @@ -425,7 +427,8 @@ void unlink_anon_vmas(struct vm_area_struct *vma) list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma;
- VM_WARN_ON(anon_vma->degree); + VM_WARN_ON(anon_vma->num_children); + VM_WARN_ON(anon_vma->num_active_vmas); put_anon_vma(anon_vma);
list_del(&avc->same_vma);