From c103a75c61648203d731e3b97a6fbeea4003cb15 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Fri, 21 Mar 2025 10:09:37 +0000 Subject: mm/vma: add give_up_on_oom option on modify/merge, use in uffd release commit 41e6ddcaa0f18dda4c3fadf22533775a30d6f72f upstream. Currently, if a VMA merge fails due to an OOM condition arising on commit merge or a failure to duplicate anon_vma's, we report this so the caller can handle it. However there are cases where the caller is only ostensibly trying a merge, and doesn't mind if it fails due to this condition. Since we do not want to introduce an implicit assumption that we only actually modify VMAs after OOM conditions might arise, add a 'give up on oom' option and make an explicit contract that, should this flag be set, we absolutely will not modify any VMAs should OOM arise and just bail out. Since it'd be very unusual for a user to try to vma_modify() with this flag set but be specifying a range within a VMA which ends up being split (which can fail due to rlimit issues, not only OOM), we add a debug warning for this condition. The motivating reason for this is uffd release - syzkaller (and Pedro Falcato's VERY astute analysis) found a way in which an injected fault on allocation, triggering an OOM condition on commit merge, would result in uffd code becoming confused and treating an error value as if it were a VMA pointer. To avoid this, we make use of this new VMG flag to ensure that this never occurs, utilising the fact that, should we be clearing entire VMAs, we do not wish an OOM event to be reported to us. Many thanks to Pedro Falcato for his excellent analysis and Jann Horn for his insightful and intelligent analysis of the situation, both of whom were instrumental in this fix. Link: https://lkml.kernel.org/r/20250321100937.46634-1-lorenzo.stoakes@oracle.com Reported-by: syzbot+20ed41006cf9d842c2b5@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/67dc67f0.050a0220.25ae54.001e.GAE@google.com/ Fixes: 47b16d0462a4 ("mm: abort vma_modify() on merge out of memory failure") Signed-off-by: Lorenzo Stoakes Suggested-by: Pedro Falcato Suggested-by: Jann Horn Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/userfaultfd.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'mm/userfaultfd.c') diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index d06453fa8aba..4295a599d714 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -1898,6 +1898,14 @@ struct vm_area_struct *userfaultfd_clear_vma(struct vma_iterator *vmi, unsigned long end) { struct vm_area_struct *ret; + bool give_up_on_oom = false; + + /* + * If we are modifying only and not splitting, just give up on the merge + * if OOM prevents us from merging successfully. + */ + if (start == vma->vm_start && end == vma->vm_end) + give_up_on_oom = true; /* Reset ptes for the whole vma range if wr-protected */ if (userfaultfd_wp(vma)) @@ -1905,7 +1913,7 @@ struct vm_area_struct *userfaultfd_clear_vma(struct vma_iterator *vmi, ret = vma_modify_flags_uffd(vmi, prev, vma, start, end, vma->vm_flags & ~__VM_UFFD_FLAGS, - NULL_VM_UFFD_CTX); + NULL_VM_UFFD_CTX, give_up_on_oom); /* * In the vma_merge() successful mprotect-like case 8: @@ -1956,7 +1964,8 @@ int userfaultfd_register_range(struct userfaultfd_ctx *ctx, new_flags = (vma->vm_flags & ~__VM_UFFD_FLAGS) | vm_flags; vma = vma_modify_flags_uffd(&vmi, prev, vma, start, vma_end, new_flags, - (struct vm_userfaultfd_ctx){ctx}); + (struct vm_userfaultfd_ctx){ctx}, + /* give_up_on_oom = */false); if (IS_ERR(vma)) return PTR_ERR(vma); -- cgit v1.2.3