diff options
author | Peter Xu <peterx@redhat.com> | 2021-05-14 17:27:04 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-05-14 19:41:32 -0700 |
commit | 22247efd822e6d263f3c8bd327f3f769aea9b1d9 (patch) | |
tree | 2bc99fea483cdffe7a0e114b629ab194c5aec04f | |
parent | bd3c9cdb21a2674dd0db70199df884828e37abd4 (diff) |
mm/hugetlb: fix F_SEAL_FUTURE_WRITE
Patch series "mm/hugetlb: Fix issues on file sealing and fork", v2.
Hugh reported issue with F_SEAL_FUTURE_WRITE not applied correctly to
hugetlbfs, which I can easily verify using the memfd_test program, which
seems that the program is hardly run with hugetlbfs pages (as by default
shmem).
Meanwhile I found another probably even more severe issue on that hugetlb
fork won't wr-protect child cow pages, so child can potentially write to
parent private pages. Patch 2 addresses that.
After this series applied, "memfd_test hugetlbfs" should start to pass.
This patch (of 2):
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.
Link: https://lkml.kernel.org/r/20210503234356.9097-1-peterx@redhat.com
Link: https://lkml.kernel.org/r/20210503234356.9097-2-peterx@redhat.com
Fixes: ab3948f58ff84 ("mm/memfd: add an F_SEAL_FUTURE_WRITE seal to memfd")
Signed-off-by: Peter Xu <peterx@redhat.com>
Reported-by: Hugh Dickins <hughd@google.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Joel Fernandes (Google) <joel@joelfernandes.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r-- | fs/hugetlbfs/inode.c | 5 | ||||
-rw-r--r-- | include/linux/mm.h | 32 | ||||
-rw-r--r-- | mm/shmem.c | 22 |
3 files changed, 41 insertions, 18 deletions
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index a2a42335e8fd..9d9e0097c1d3 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 322ec61d0da7..c274f75efcf9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3216,5 +3216,37 @@ void mem_dump_obj(void *object); static inline void mem_dump_obj(void *object) {} #endif +/** + * 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 a08cedefbfaa..eb131b9fb190 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2258,25 +2258,11 @@ out_nomem: 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; |