[PATCH v6 3/8] mm/memfd: Introduce MFD_INACCESSIBLE flag

[Chao Peng]

Introduce a new memfd_create() flag indicating the content of the
created memfd is inaccessible from userspace through ordinary MMU
access (e.g., read/write/mmap). However, the file content can be
accessed via a different mechanism (e.g. KVM MMU) indirectly.

It provides semantics required for KVM guest private memory support
that a file descriptor with this flag set is going to be used as the
source of guest memory in confidential computing environments such
as Intel TDX/AMD SEV but may not be accessible from host userspace.

The flag can not coexist with MFD_ALLOW_SEALING, future sealing is
also impossible for a memfd created with this flag.

Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
---
 include/uapi/linux/memfd.h |  1 +
 mm/memfd.c                 | 15 ++++++++++++++-
 2 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/memfd.h b/include/uapi/linux/memfd.h
index 7a8a26751c23..48750474b904 100644
--- a/include/uapi/linux/memfd.h
+++ b/include/uapi/linux/memfd.h
@@ -8,6 +8,7 @@
 #define MFD_CLOEXEC            0x0001U
 #define MFD_ALLOW_SEALING      0x0002U
 #define MFD_HUGETLB            0x0004U
+#define MFD_INACCESSIBLE       0x0008U
 
 /*
  * Huge page size encoding when MFD_HUGETLB is specified, and a huge page
diff --git a/mm/memfd.c b/mm/memfd.c
index 08f5f8304746..775541d53f1b 100644
--- a/mm/memfd.c
+++ b/mm/memfd.c
@@ -18,6 +18,7 @@
 #include <linux/hugetlb.h>
 #include <linux/shmem_fs.h>
 #include <linux/memfd.h>
+#include <linux/memfile_notifier.h>
 #include <uapi/linux/memfd.h>
 
 /*
@@ -261,7 +262,8 @@ long memfd_fcntl(struct file *file, unsigned int cmd, 
unsigned long arg)
 #define MFD_NAME_PREFIX_LEN (sizeof(MFD_NAME_PREFIX) - 1)
 #define MFD_NAME_MAX_LEN (NAME_MAX - MFD_NAME_PREFIX_LEN)
 
-#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_HUGETLB)
+#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_HUGETLB | \
+                      MFD_INACCESSIBLE)
 
 SYSCALL_DEFINE2(memfd_create,
                const char __user *, uname,
@@ -283,6 +285,10 @@ SYSCALL_DEFINE2(memfd_create,
                        return -EINVAL;
        }
 
+       /* Disallow sealing when MFD_INACCESSIBLE is set. */
+       if (flags & MFD_INACCESSIBLE && flags & MFD_ALLOW_SEALING)
+               return -EINVAL;
+
        /* length includes terminating zero */
        len = strnlen_user(uname, MFD_NAME_MAX_LEN + 1);
        if (len <= 0)
@@ -329,12 +335,19 @@ SYSCALL_DEFINE2(memfd_create,
        if (flags & MFD_ALLOW_SEALING) {
                file_seals = memfd_file_seals_ptr(file);
                *file_seals &= ~F_SEAL_SEAL;
+       } else if (flags & MFD_INACCESSIBLE) {
+               error = memfile_node_set_flags(file,
+                                              MEMFILE_F_USER_INACCESSIBLE);
+               if (error)
+                       goto err_file;
        }
 
        fd_install(fd, file);
        kfree(name);
        return fd;
 
+err_file:
+       fput(file);
 err_fd:
        put_unused_fd(fd);
 err_name:
-- 
2.25.1