F_SEAL_FUTURE_WRITE is missing for hugetlb starting from the first day. There is a test program for that and it fails constantly.
$ ./memfd_test hugetlbfs memfd-hugetlb: CREATE memfd-hugetlb: BASIC memfd-hugetlb: SEAL-WRITE memfd-hugetlb: SEAL-FUTURE-WRITE mmap() didn't fail as expected Aborted (core dumped)
I think it's probably because no one is really running the hugetlbfs test.
Fix it by checking FUTURE_WRITE also in hugetlbfs_file_mmap() as what we do in shmem_mmap(). Generalize a helper for that.
Cc: Joel Fernandes (Google) joel@joelfernandes.org Cc: stable@vger.kernel.org Fixes: ab3948f58ff84 ("mm/memfd: add an F_SEAL_FUTURE_WRITE seal to memfd") Reported-by: Hugh Dickins hughd@google.com Reviewed-by: Mike Kravetz mike.kravetz@oracle.com Signed-off-by: Peter Xu peterx@redhat.com --- fs/hugetlbfs/inode.c | 5 +++++ include/linux/mm.h | 32 ++++++++++++++++++++++++++++++++ mm/shmem.c | 22 ++++------------------ 3 files changed, 41 insertions(+), 18 deletions(-)
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 9b383c39756a5..6557cf2cb1879 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -131,6 +131,7 @@ static void huge_pagevec_release(struct pagevec *pvec) static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) { struct inode *inode = file_inode(file); + struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode); loff_t len, vma_len; int ret; struct hstate *h = hstate_file(file); @@ -146,6 +147,10 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) vma->vm_flags |= VM_HUGETLB | VM_DONTEXPAND; vma->vm_ops = &hugetlb_vm_ops;
+ ret = seal_check_future_write(info->seals, vma); + if (ret) + return ret; + /* * page based offset in vm_pgoff could be sufficiently large to * overflow a loff_t when converted to byte offset. This can diff --git a/include/linux/mm.h b/include/linux/mm.h index d6790ab0cf575..b9b2caf9302bc 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3238,5 +3238,37 @@ extern int sysctl_nr_trim_pages;
void mem_dump_obj(void *object);
+/** + * seal_check_future_write - Check for F_SEAL_FUTURE_WRITE flag and handle it + * @seals: the seals to check + * @vma: the vma to operate on + * + * Check whether F_SEAL_FUTURE_WRITE is set; if so, do proper check/handling on + * the vma flags. Return 0 if check pass, or <0 for errors. + */ +static inline int seal_check_future_write(int seals, struct vm_area_struct *vma) +{ + if (seals & F_SEAL_FUTURE_WRITE) { + /* + * New PROT_WRITE and MAP_SHARED mmaps are not allowed when + * "future write" seal active. + */ + if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) + return -EPERM; + + /* + * Since an F_SEAL_FUTURE_WRITE sealed memfd can be mapped as + * MAP_SHARED and read-only, take care to not allow mprotect to + * revert protections on such mappings. Do this only for shared + * mappings. For private mappings, don't need to mask + * VM_MAYWRITE as we still want them to be COW-writable. + */ + if (vma->vm_flags & VM_SHARED) + vma->vm_flags &= ~(VM_MAYWRITE); + } + + return 0; +} + #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ diff --git a/mm/shmem.c b/mm/shmem.c index a1f21736ad68e..250b52e682590 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2258,25 +2258,11 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user) static int shmem_mmap(struct file *file, struct vm_area_struct *vma) { struct shmem_inode_info *info = SHMEM_I(file_inode(file)); + int ret;
- if (info->seals & F_SEAL_FUTURE_WRITE) { - /* - * New PROT_WRITE and MAP_SHARED mmaps are not allowed when - * "future write" seal active. - */ - if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) - return -EPERM; - - /* - * Since an F_SEAL_FUTURE_WRITE sealed memfd can be mapped as - * MAP_SHARED and read-only, take care to not allow mprotect to - * revert protections on such mappings. Do this only for shared - * mappings. For private mappings, don't need to mask - * VM_MAYWRITE as we still want them to be COW-writable. - */ - if (vma->vm_flags & VM_SHARED) - vma->vm_flags &= ~(VM_MAYWRITE); - } + ret = seal_check_future_write(info->seals, vma); + if (ret) + return ret;
/* arm64 - allow memory tagging on RAM-based files */ vma->vm_flags |= VM_MTE_ALLOWED;