From 2e5cbab8ccbfc7d4a3d8a21d3c2a1f2c1aa29b5b Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Thu, 2 Apr 2026 18:13:11 +0200 Subject: [PATCH] fork: defer linking file vma until vma is fully initialized MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 35e351780fa9d8240dd6f7e4f245f9ea37e96c19 ] Thorvald reported a WARNING [1]. And the root cause is below race: CPU 1 CPU 2 fork hugetlbfs_fallocate dup_mmap hugetlbfs_punch_hole i_mmap_lock_write(mapping); vma_interval_tree_insert_after -- Child vma is visible through i_mmap tree. i_mmap_unlock_write(mapping); hugetlb_dup_vma_private -- Clear vma_lock outside i_mmap_rwsem! i_mmap_lock_write(mapping); hugetlb_vmdelete_list vma_interval_tree_foreach hugetlb_vma_trylock_write -- Vma_lock is cleared. tmp->vm_ops->open -- Alloc new vma_lock outside i_mmap_rwsem! hugetlb_vma_unlock_write -- Vma_lock is assigned!!! i_mmap_unlock_write(mapping); hugetlb_dup_vma_private() and hugetlb_vm_op_open() are called outside i_mmap_rwsem lock while vma lock can be used in the same time. Fix this by deferring linking file vma until vma is fully initialized. Those vmas should be initialized first before they can be used. [tk: Adapted to 6.6 stable where vma_iter_bulk_store() can fail (unlike mainline which uses __mt_dup() for pre-allocation). Preserved error handling via goto fail_nomem_vmi_store. Previous backport (cec11fa2eb512) was reverted (dd782da470761) due to xfstests failures.] Link: https://lkml.kernel.org/r/20240410091441.3539905-1-linmiaohe@huawei.com Fixes: 8d9bfb260814 ("hugetlb: add vma based lock for pmd sharing") Signed-off-by: Miaohe Lin Reported-by: Thorvald Natvig Closes: https://lore.kernel.org/linux-mm/20240129161735.6gmjsswx62o4pbja@revolver/T/ [1] Reviewed-by: Jane Chu Cc: Christian Brauner Cc: Heiko Carstens Cc: Kent Overstreet Cc: Liam R. Howlett Cc: Mateusz Guzik Cc: Matthew Wilcox (Oracle) Cc: Miaohe Lin Cc: Muchun Song Cc: Oleg Nesterov Cc: Peng Zhang Cc: Tycho Andersen Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton Assisted-by: Claude:claude-opus-4.6 Suggested-by: David Nyström Signed-off-by: Tugrul Kukul Acked-by: Alex Williamson Signed-off-by: Sasha Levin --- kernel/fork.c | 29 +++++++++++++++-------------- 1 file changed, 15 insertions(+), 14 deletions(-) diff --git a/kernel/fork.c b/kernel/fork.c index ce6f6e1e3905..5b60692b1a4e 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -733,6 +733,21 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, } else if (anon_vma_fork(tmp, mpnt)) goto fail_nomem_anon_vma_fork; vm_flags_clear(tmp, VM_LOCKED_MASK); + /* + * Copy/update hugetlb private vma information. + */ + if (is_vm_hugetlb_page(tmp)) + hugetlb_dup_vma_private(tmp); + + /* Link the vma into the MT */ + if (vma_iter_bulk_store(&vmi, tmp)) + goto fail_nomem_vmi_store; + + mm->map_count++; + + if (tmp->vm_ops && tmp->vm_ops->open) + tmp->vm_ops->open(tmp); + file = tmp->vm_file; if (file) { struct address_space *mapping = file->f_mapping; @@ -749,23 +764,9 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, i_mmap_unlock_write(mapping); } - /* - * Copy/update hugetlb private vma information. - */ - if (is_vm_hugetlb_page(tmp)) - hugetlb_dup_vma_private(tmp); - - /* Link the vma into the MT */ - if (vma_iter_bulk_store(&vmi, tmp)) - goto fail_nomem_vmi_store; - - mm->map_count++; if (!(tmp->vm_flags & VM_WIPEONFORK)) retval = copy_page_range(tmp, mpnt); - if (tmp->vm_ops && tmp->vm_ops->open) - tmp->vm_ops->open(tmp); - if (retval) goto loop_out; }