From 7368bec565bac3e536cd43579dbde1e715e6ba61 Mon Sep 17 00:00:00 2001 From: Pedro Falcato Date: Tue, 21 Jul 2026 13:13:04 -0400 Subject: [PATCH] mm: do file ownership checks with the proper mount idmap [ Upstream commit e187bc02f8fa4226d62814592cf064ee4557c470 ] Ever since idmapped mounts were introduced, inode ownership checks (for side-channel protection) in mincore() and madvise(MADV_PAGEOUT) were done against the nop_mnt_idmap, which completely ignores the file's mount's idmap. This results in odd edgecases like: 1) mount/bind-mount with an idmap userA:userB:1 2) userB runs an owner_or_capable() check on file that is owned by userA on-disk/in-memory, but owned by userB after idmap translation 3) owner_or_capable() mysteriously fails as the correct idmap wasn't supplied In the case of mincore/madvise MADV_PAGEOUT, this is usually benign, because file_permission(file, MAY_WRITE) will probably succeed, as it uses the proper idmap internally, but it does not need to be the case on e.g a 0444 file where even the owner itself doesn't have permissions to write to it. Since this is clearly not trivial to get right, introduce a file_owner_or_capable() that can carry the correct semantics, and switch the various users in mm to it. The issue was found by manual code inspection & an off-list discussion with Jan Kara. Link: https://lore.kernel.org/20260625153853.913949-1-pfalcato@suse.de Fixes: 9caccd41541a ("fs: introduce MOUNT_ATTR_IDMAP") Signed-off-by: Pedro Falcato Reviewed-by: Jan Kara Reviewed-by: Christian Brauner (Amutable) Acked-by: David Hildenbrand (Arm) Cc: Al Viro Cc: Jann Horn Cc: Liam R. Howlett Cc: Matthew Wilcox (Oracle) Cc: Vlastimil Babka Cc: Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- include/linux/fs.h | 5 +++++ mm/madvise.c | 3 +-- mm/mincore.c | 3 +-- 3 files changed, 7 insertions(+), 4 deletions(-) diff --git a/include/linux/fs.h b/include/linux/fs.h index 72a956d243c2..5b85d4e73219 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2743,6 +2743,11 @@ static inline struct user_namespace *file_mnt_user_ns(struct file *file) return mnt_user_ns(file->f_path.mnt); } +static inline bool file_owner_or_capable(struct file *file) +{ + return inode_owner_or_capable(file_mnt_user_ns(file), file_inode(file)); +} + /** * is_idmapped_mnt - check whether a mount is mapped * @mnt: the mount to check diff --git a/mm/madvise.c b/mm/madvise.c index ef9382f77624..367220e1fe52 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -544,8 +544,7 @@ static inline bool can_do_pageout(struct vm_area_struct *vma) * otherwise we'd be including shared non-exclusive mappings, which * opens a side channel. */ - return inode_owner_or_capable(&init_user_ns, - file_inode(vma->vm_file)) || + return file_owner_or_capable(vma->vm_file) || file_permission(vma->vm_file, MAY_WRITE) == 0; } diff --git a/mm/mincore.c b/mm/mincore.c index 9122676b54d6..889d84477a77 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -166,8 +166,7 @@ static inline bool can_do_mincore(struct vm_area_struct *vma) * for writing; otherwise we'd be including shared non-exclusive * mappings, which opens a side channel. */ - return inode_owner_or_capable(&init_user_ns, - file_inode(vma->vm_file)) || + return file_owner_or_capable(vma->vm_file) || file_permission(vma->vm_file, MAY_WRITE) == 0; }