BACKPORT: mm: Add an F_SEAL_FUTURE_WRITE seal to memfd

Android uses ashmem for sharing memory regions. We are looking forward
to migrating all usecases of ashmem to memfd so that we can possibly
remove the ashmem driver in the future from staging while also
benefiting from using memfd and contributing to it. Note staging drivers
are also not ABI and generally can be removed at anytime.

One of the main usecases Android has is the ability to create a region
and mmap it as writeable, then add protection against making any
"future" writes while keeping the existing already mmap'ed
writeable-region active.  This allows us to implement a usecase where
receivers of the shared memory buffer can get a read-only view, while
the sender continues to write to the buffer.
See CursorWindow documentation in Android for more details:
https://developer.android.com/reference/android/database/CursorWindow

This usecase cannot be implemented with the existing F_SEAL_WRITE seal.
To support the usecase, this patch adds a new F_SEAL_FUTURE_WRITE seal
which prevents any future mmap and write syscalls from succeeding while
keeping the existing mmap active.

Verified with test program at: https://lore.kernel.org/patchwork/patch/1008117/
link: https://lore.kernel.org/patchwork/patch/1014892/
Bug: 113362644
Change-Id: If7424db3b64372932d455f0219cd9df613fec1d4
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Joel Fernandes <joelaf@google.com>

diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h
index beed138bd359382273cd9f9c114f44b7bd559841..328288611fa99947dca0c9ae32bfaac41cc39302 100644 (file)
--- a/include/uapi/linux/fcntl.h
+++ b/include/uapi/linux/fcntl.h
@@ -40,6 +40,7 @@
 #define F_SEAL_SHRINK  0x0002  /* prevent file from shrinking */
 #define F_SEAL_GROW    0x0004  /* prevent file from growing */
 #define F_SEAL_WRITE   0x0008  /* prevent writes */
+#define F_SEAL_FUTURE_WRITE    0x0010  /* prevent writes */
 /* (1U << 31) is reserved for signed error codes */
 
 /*

diff --git a/mm/shmem.c b/mm/shmem.c
index a7cf8c0371a2ba7ad560535a397084d7ec1f445d..55313d02d0b4b41f98a5ab7436c2cde15903746e 100644 (file)
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1444,6 +1444,25 @@ out_nomem:
 
 static int shmem_mmap(struct file *file, struct vm_area_struct *vma)
 {
+        struct inode *inode = file->f_path.dentry->d_inode;
+       struct shmem_inode_info *info = SHMEM_I(inode);
+
+       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 the F_SEAL_FUTURE_WRITE seals allow for a MAP_SHARED
+                * read-only mapping, take care to not allow mprotect to revert
+                * protections.
+                */
+               vma->vm_flags &= ~(VM_MAYWRITE);
+       }
+
        file_accessed(file);
        vma->vm_ops = &shmem_vm_ops;
        return 0;
@@ -1528,8 +1547,9 @@ shmem_write_begin(struct file *file, struct address_space *mapping,
        pgoff_t index = pos >> PAGE_CACHE_SHIFT;
 
        /* i_mutex is held by caller */
-       if (unlikely(info->seals & (F_SEAL_WRITE | F_SEAL_GROW))) {
-               if (info->seals & F_SEAL_WRITE)
+       if (unlikely(info->seals & (F_SEAL_GROW |
+                                  F_SEAL_WRITE | F_SEAL_FUTURE_WRITE))) {
+               if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE))
                        return -EPERM;
                if ((info->seals & F_SEAL_GROW) && pos + len > inode->i_size)
                        return -EPERM;
@@ -2023,7 +2043,8 @@ continue_resched:
 #define F_ALL_SEALS (F_SEAL_SEAL | \
                     F_SEAL_SHRINK | \
                     F_SEAL_GROW | \
-                    F_SEAL_WRITE)
+                    F_SEAL_WRITE | \
+                    F_SEAL_FUTURE_WRITE)
 
 int shmem_add_seals(struct file *file, unsigned int seals)
 {
@@ -2147,7 +2168,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
                DECLARE_WAIT_QUEUE_HEAD_ONSTACK(shmem_falloc_waitq);
 
                /* protected by i_mutex */
-               if (info->seals & F_SEAL_WRITE) {
+               if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) {
                        error = -EPERM;
                        goto out;
                }