mm: perform all memfd seal checks in a single place

We no longer actually need to perform these checks in the f_op->mmap()
hook any longer.

We already moved the operation which clears VM_MAYWRITE on a read-only
mapping of a write-sealed memfd in order to work around the restrictions
imposed by commit 5de195060b2e ("mm: resolve faulty mmap_region() error
path behaviour").

There is no reason for us not to simply go ahead and additionally check to
see if any pre-existing seals are in place here rather than defer this to
the f_op->mmap() hook.

By doing this we remove more logic from shmem_mmap() which doesn't belong
there, as well as doing the same for hugetlbfs_file_mmap().  We also
remove dubious shared logic in mm.h which simply does not belong there
either.

It makes sense to do these checks at the earliest opportunity, we know
these are shmem (or hugetlbfs) mappings whose relevant VMA flags will not
change from the invoking do_mmap() so there is simply no need to wait.

This also means the implementation of further memfd seal flags can be done
within mm/memfd.c and also have the opportunity to modify VMA flags as
necessary early in the mapping logic.

[lorenzo.stoakes@oracle.com: fix typos in !memfd inline stub]
  Link: https://lkml.kernel.org/r/7dee6c5d-480b-4c24-b98e-6fa47dbd8a23@lucifer.local
Link: https://lkml.kernel.org/r/20241206212846.210835-1-lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Tested-by: Isaac J. Manjarres <isaacmanjarres@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: Liam R. Howlett <Liam.Howlett@Oracle.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jeff Xu <jeffxu@chromium.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 43 insertions, 1 deletions

diff --git a/mm/memfd.c b/mm/memfd.c
index 35a370d75c9a..5f5a23c9051d 100644
--- a/mm/memfd.c
+++ b/mm/memfd.c
@@ -170,7 +170,7 @@ static int memfd_wait_for_pins(struct address_space *mapping)
 	return error;
 }
 
-unsigned int *memfd_file_seals_ptr(struct file *file)
+static unsigned int *memfd_file_seals_ptr(struct file *file)
 {
 	if (shmem_file(file))
 		return &SHMEM_I(file_inode(file))->seals;
@@ -327,6 +327,48 @@ static int check_sysctl_memfd_noexec(unsigned int *flags)
 	return 0;
 }
 
+static inline bool is_write_sealed(unsigned int seals)
+{
+	return seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE);
+}
+
+static int check_write_seal(unsigned long *vm_flags_ptr)
+{
+	unsigned long vm_flags = *vm_flags_ptr;
+	unsigned long mask = vm_flags & (VM_SHARED | VM_WRITE);
+
+	/* If a private matting then writability is irrelevant. */
+	if (!(mask & VM_SHARED))
+		return 0;
+
+	/*
+	 * New PROT_WRITE and MAP_SHARED mmaps are not allowed when
+	 * write seals are active.
+	 */
+	if (mask & VM_WRITE)
+		return -EPERM;
+
+	/*
+	 * This is a read-only mapping, disallow mprotect() from making a
+	 * write-sealed mapping writable in future.
+	 */
+	*vm_flags_ptr &= ~VM_MAYWRITE;
+
+	return 0;
+}
+
+int memfd_check_seals_mmap(struct file *file, unsigned long *vm_flags_ptr)
+{
+	int err = 0;
+	unsigned int *seals_ptr = memfd_file_seals_ptr(file);
+	unsigned int seals = seals_ptr ? *seals_ptr : 0;
+
+	if (is_write_sealed(seals))
+		err = check_write_seal(vm_flags_ptr);
+
+	return err;
+}
+
 SYSCALL_DEFINE2(memfd_create,
 		const char __user *, uname,
 		unsigned int, flags)