mm/memfd: add MFD_NOEXEC_SEAL and MFD_EXEC

The new MFD_NOEXEC_SEAL and MFD_EXEC flags allows application to set
executable bit at creation time (memfd_create).

When MFD_NOEXEC_SEAL is set, memfd is created without executable bit
(mode:0666), and sealed with F_SEAL_EXEC, so it can't be chmod to be
executable (mode: 0777) after creation.

when MFD_EXEC flag is set, memfd is created with executable bit
(mode:0777), this is the same as the old behavior of memfd_create.

The new pid namespaced sysctl vm.memfd_noexec has 3 values:
0: memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL acts like
        MFD_EXEC was set.
1: memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL acts like
        MFD_NOEXEC_SEAL was set.
2: memfd_create() without MFD_NOEXEC_SEAL will be rejected.

The sysctl allows finer control of memfd_create for old-software that
doesn't set the executable bit, for example, a container with
vm.memfd_noexec=1 means the old-software will create non-executable memfd
by default.  Also, the value of memfd_noexec is passed to child namespace
at creation time.  For example, if the init namespace has
vm.memfd_noexec=2, all its children namespaces will be created with 2.

[akpm@linux-foundation.org: add stub functions to fix build]
[akpm@linux-foundation.org: remove unneeded register_pid_ns_ctl_table_vm() stub, per Jeff]
[akpm@linux-foundation.org: s/pr_warn_ratelimited/pr_warn_once/, per review]
[akpm@linux-foundation.org: fix CONFIG_SYSCTL=n warning]
Link: https://lkml.kernel.org/r/20221215001205.51969-4-jeffxu@google.com
Signed-off-by: Jeff Xu <jeffxu@google.com>
Co-developed-by: Daniel Verkamp <dverkamp@chromium.org>
Signed-off-by: Daniel Verkamp <dverkamp@chromium.org>
Reported-by: kernel test robot <lkp@intel.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Cc: David Herrmann <dh.herrmann@gmail.com>
Cc: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jorge Lucangeli Obes <jorgelo@chromium.org>
Cc: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 46 insertions, 2 deletions

diff --git a/mm/memfd.c b/mm/memfd.c
index 4ebeab94aa74..bc214390e28d 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/pid_namespace.h>
 #include <uapi/linux/memfd.h>
 
 /*
@@ -263,12 +264,13 @@ 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_NOEXEC_SEAL | MFD_EXEC)
 
 SYSCALL_DEFINE2(memfd_create,
 		const char __user *, uname,
 		unsigned int, flags)
 {
+	char comm[TASK_COMM_LEN];
 	unsigned int *file_seals;
 	struct file *file;
 	int fd, error;
@@ -285,6 +287,40 @@ SYSCALL_DEFINE2(memfd_create,
 			return -EINVAL;
 	}
 
+	/* Invalid if both EXEC and NOEXEC_SEAL are set.*/
+	if ((flags & MFD_EXEC) && (flags & MFD_NOEXEC_SEAL))
+		return -EINVAL;
+
+	if (!(flags & (MFD_EXEC | MFD_NOEXEC_SEAL))) {
+#ifdef CONFIG_SYSCTL
+		int sysctl = MEMFD_NOEXEC_SCOPE_EXEC;
+		struct pid_namespace *ns;
+
+		ns = task_active_pid_ns(current);
+		if (ns)
+			sysctl = ns->memfd_noexec_scope;
+
+		switch (sysctl) {
+		case MEMFD_NOEXEC_SCOPE_EXEC:
+			flags |= MFD_EXEC;
+			break;
+		case MEMFD_NOEXEC_SCOPE_NOEXEC_SEAL:
+			flags |= MFD_NOEXEC_SEAL;
+			break;
+		default:
+			pr_warn_once(
+				"memfd_create(): MFD_NOEXEC_SEAL is enforced, pid=%d '%s'\n",
+				task_pid_nr(current), get_task_comm(comm, current));
+			return -EINVAL;
+		}
+#else
+		flags |= MFD_EXEC;
+#endif
+		pr_warn_once(
+			"memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL, pid=%d '%s'\n",
+			task_pid_nr(current), get_task_comm(comm, current));
+	}
+
 	/* length includes terminating zero */
 	len = strnlen_user(uname, MFD_NAME_MAX_LEN + 1);
 	if (len <= 0)
@@ -328,7 +364,15 @@ SYSCALL_DEFINE2(memfd_create,
 	file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE;
 	file->f_flags |= O_LARGEFILE;
 
-	if (flags & MFD_ALLOW_SEALING) {
+	if (flags & MFD_NOEXEC_SEAL) {
+		struct inode *inode = file_inode(file);
+
+		inode->i_mode &= ~0111;
+		file_seals = memfd_file_seals_ptr(file);
+		*file_seals &= ~F_SEAL_SEAL;
+		*file_seals |= F_SEAL_EXEC;
+	} else if (flags & MFD_ALLOW_SEALING) {
+		/* MFD_EXEC and MFD_ALLOW_SEALING are set */
 		file_seals = memfd_file_seals_ptr(file);
 		*file_seals &= ~F_SEAL_SEAL;
 	}