Skip to contentSkip to conversation

mm/memfd: add MFD_NOEXEC_SEAL and MFD_EXEC

PATCH Superseded [email protected] 1 participant 7 messages Dec 6, 2022

Subsystems (6)

v4 of 8 Superseded Latest is v8 →

lore
Share & tools
lore
#0 lore raw

v4 cover mm/memfd: add MFD_NOEXEC_SEAL and MFD_EXEC

From: Jeff Xu <[email protected]>

Since Linux introduced the memfd feature, memfd have always had their execute bit set, and the memfd_create() syscall doesn't allow setting it differently.

However, in a secure by default system, such as ChromeOS, (where all executables should come from the rootfs, which is protected by Verified boot), this executable nature of memfd opens a door for NoExec bypass and enables “confused deputy attack”. E.g, in VRP bug [1]: cros_vm process created a memfd to share the content with an external process, however the memfd is overwritten and used for executing arbitrary code and root escalation. [2] lists more VRP in this kind.

On the other hand, executable memfd has its legit use, runc uses memfd’s seal and executable feature to copy the contents of the binary then execute them, for such system, we need a solution to differentiate runc's use of executable memfds and an attacker's [3].

To address those above, this set of patches add following:
1> Let memfd_create() set X bit at creation time.
2> Let memfd to be sealed for modifying X bit.
3> A new pid namespace sysctl: vm.memfd_noexec to control behavior of X bit. For example, if a container has vm.memfd_noexec=2, then memfd_create() without MFD_NOEXEC_SEAL will be rejected. 4> A new security hook in memfd_create(). This make it possible to a new LSM, which rejects or allows executable memfd based on its security policy.

This is V4 version of patch: see [4] [5] [6] for previous versions.

[1] https://crbug.com/1305411
[2] https://bugs.chromium.org/p/chromium/issues/list?q=type%3Dbug-security%20memfd%20escalation&can=1
[3] https://lwn.net/Articles/781013/
[4] https://lwn.net/Articles/890096/
[5] https://lore.kernel.org/lkml/[email protected]/
[6] https://lore.kernel.org/lkml/[email protected]/

Daniel Verkamp (2):
mm/memfd: add F_SEAL_EXEC
selftests/memfd: add tests for F_SEAL_EXEC

Jeff Xu (4):
mm/memfd: add MFD_NOEXEC_SEAL and MFD_EXEC
mm/memfd: Add write seals when apply SEAL_EXEC to executable memfd selftests/memfd: add tests for MFD_NOEXEC_SEAL MFD_EXEC mm/memfd: security hook for memfd_create

 include/linux/lsm_hook_defs.h              |   1 +
 include/linux/lsm_hooks.h                  |   4 +
 include/linux/pid_namespace.h              |  19 ++
 include/linux/security.h                   |   6 +
 include/uapi/linux/fcntl.h                 |   1 +
 include/uapi/linux/memfd.h                 |   4 +
 kernel/pid_namespace.c                     |  48 ++++
 mm/memfd.c                                 |  61 ++++-
 mm/shmem.c                                 |   6 +
 security/security.c                        |  13 +
 tools/testing/selftests/memfd/fuse_test.c  |   1 +
 tools/testing/selftests/memfd/memfd_test.c | 304 ++++++++++++++++++++-
 12 files changed, 465 insertions(+), 3 deletions(-)

base-commit: eb7081409f94a9a8608593d0fb63a1aa3d6f95d8

Signature · 1 line
2.39.0.rc0.267.gcb52ba06e7-goog
#1 lore raw

PATCH v4 1/6 mm/memfd: add F_SEAL_EXEC

From: Daniel Verkamp <[email protected]>

The new F_SEAL_EXEC flag will prevent modification of the exec bits:
written as traditional octal mask, 0111, or as named flags, S_IXUSR | S_IXGRP | S_IXOTH. Any chmod(2) or similar call that attempts to modify any of these bits after the seal is applied will fail with errno EPERM.

This will preserve the execute bits as they are at the time of sealing, so the memfd will become either permanently executable or permanently un-executable.

---
 include/uapi/linux/fcntl.h | 1 +
 mm/memfd.c                 | 2 ++
 mm/shmem.c                 | 6 ++++++
 3 files changed, 9 insertions(+)
include/uapi/linux/fcntl.h +1 -0
index 2f86b2ad6d7e..e8c07da58c9f 100644
@@ -43,6 +43,7 @@
 #define F_SEAL_GROW	0x0004	/* prevent file from growing */
 #define F_SEAL_WRITE	0x0008	/* prevent writes */
 #define F_SEAL_FUTURE_WRITE	0x0010  /* prevent future writes while mapped */
+#define F_SEAL_EXEC	0x0020  /* prevent chmod modifying exec bits */
 /* (1U << 31) is reserved for signed error codes */
 
 /*
mm/memfd.c +2 -0
index 08f5f8304746..4ebeab94aa74 100644
@@ -147,6 +147,7 @@ static unsigned int *memfd_file_seals_ptr(struct file *file)
 }
 
 #define F_ALL_SEALS (F_SEAL_SEAL | \
+		     F_SEAL_EXEC | \
 		     F_SEAL_SHRINK | \
 		     F_SEAL_GROW | \
 		     F_SEAL_WRITE | \
@@ -175,6 +176,7 @@ static int memfd_add_seals(struct file *file, unsigned int seals)
 	 *   SEAL_SHRINK: Prevent the file from shrinking
 	 *   SEAL_GROW: Prevent the file from growing
 	 *   SEAL_WRITE: Prevent write access to the file
+	 *   SEAL_EXEC: Prevent modification of the exec bits in the file mode
 	 *
 	 * As we don't require any trust relationship between two parties, we
 	 * must prevent seals from being removed. Therefore, sealing a file
mm/shmem.c +6 -0
index c1d8b8a1aa3b..e18a9cf9d937 100644
@@ -1085,6 +1085,12 @@ static int shmem_setattr(struct user_namespace *mnt_userns,
 	if (error)
 		return error;
 
+	if ((info->seals & F_SEAL_EXEC) && (attr->ia_valid & ATTR_MODE)) {
+		if ((inode->i_mode ^ attr->ia_mode) & 0111) {
+			return -EPERM;
+		}
+	}
+
 	if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) {
 		loff_t oldsize = inode->i_size;
 		loff_t newsize = attr->ia_size;
Signature · 1 line
2.39.0.rc0.267.gcb52ba06e7-goog
#2 lore raw

PATCH v4 2/6 selftests/memfd: add tests for F_SEAL_EXEC

In reply to [email protected]

From: Daniel Verkamp <[email protected]>

Basic tests to ensure that user/group/other execute bits cannot be changed after applying F_SEAL_EXEC to a memfd.

---
 tools/testing/selftests/memfd/memfd_test.c | 129 ++++++++++++++++++++-
 1 file changed, 128 insertions(+), 1 deletion(-)
tools/testing/selftests/memfd/memfd_test.c +128 -1
index 94df2692e6e4..1d7e7b36bbdd 100644
@@ -28,12 +28,44 @@
 #define MFD_DEF_SIZE 8192
 #define STACK_SIZE 65536
 
+#ifndef F_SEAL_EXEC
+#define F_SEAL_EXEC	0x0020
+#endif
+
+#ifndef MAX_PATH
+#define MAX_PATH 256
+#endif
+
 /*
  * Default is not to test hugetlbfs
  */
 static size_t mfd_def_size = MFD_DEF_SIZE;
 static const char *memfd_str = MEMFD_STR;
 
+static ssize_t fd2name(int fd, char *buf, size_t bufsize)
+{
+	char buf1[MAX_PATH];
+	int size;
+	ssize_t nbytes;
+
+	size = snprintf(buf1, MAX_PATH, "/proc/self/fd/%d", fd);
+	if (size < 0) {
+		printf("snprintf(%d) failed on %m\n", fd);
+		abort();
+	}
+
+	/*
+	 * reserver one byte for string termination.
+	 */
+	nbytes = readlink(buf1, buf, bufsize-1);
+	if (nbytes == -1) {
+		printf("readlink(%s) failed %m\n", buf1);
+		abort();
+	}
+	buf[nbytes] = '\0';
+	return nbytes;
+}
+
 static int mfd_assert_new(const char *name, loff_t sz, unsigned int flags)
 {
 	int r, fd;
@@ -98,11 +130,14 @@ static unsigned int mfd_assert_get_seals(int fd)
 
 static void mfd_assert_has_seals(int fd, unsigned int seals)
 {
+	char buf[MAX_PATH];
+	int nbytes;
 	unsigned int s;
+	fd2name(fd, buf, MAX_PATH);
 
 	s = mfd_assert_get_seals(fd);
 	if (s != seals) {
-		printf("%u != %u = GET_SEALS(%d)\n", seals, s, fd);
+		printf("%u != %u = GET_SEALS(%s)\n", seals, s, buf);
 		abort();
 	}
 }
@@ -594,6 +629,64 @@ static void mfd_fail_grow_write(int fd)
 	}
 }
 
+static void mfd_assert_mode(int fd, int mode)
+{
+	struct stat st;
+	char buf[MAX_PATH];
+	int nbytes;
+
+	fd2name(fd, buf, MAX_PATH);
+
+	if (fstat(fd, &st) < 0) {
+		printf("fstat(%s) failed: %m\n", buf);
+		abort();
+	}
+
+	if ((st.st_mode & 07777) != mode) {
+		printf("fstat(%s) wrong file mode 0%04o, but expected 0%04o\n",
+		       buf, (int)st.st_mode & 07777, mode);
+		abort();
+	}
+}
+
+static void mfd_assert_chmod(int fd, int mode)
+{
+	char buf[MAX_PATH];
+	int nbytes;
+
+	fd2name(fd, buf, MAX_PATH);
+
+	if (fchmod(fd, mode) < 0) {
+		printf("fchmod(%s, 0%04o) failed: %m\n", buf, mode);
+		abort();
+	}
+
+	mfd_assert_mode(fd, mode);
+}
+
+static void mfd_fail_chmod(int fd, int mode)
+{
+	struct stat st;
+	char buf[MAX_PATH];
+	int nbytes;
+
+	fd2name(fd, buf, MAX_PATH);
+
+	if (fstat(fd, &st) < 0) {
+		printf("fstat(%s) failed: %m\n", buf);
+		abort();
+	}
+
+	if (fchmod(fd, mode) == 0) {
+		printf("fchmod(%s, 0%04o) didn't fail as expected\n",
+		       buf, mode);
+		abort();
+	}
+
+	/* verify that file mode bits did not change */
+	mfd_assert_mode(fd, st.st_mode & 07777);
+}
+
 static int idle_thread_fn(void *arg)
 {
 	sigset_t set;
@@ -880,6 +973,39 @@ static void test_seal_resize(void)
 	close(fd);
 }
 
+/*
+ * Test SEAL_EXEC
+ * Test that chmod() cannot change x bits after sealing
+ */
+static void test_seal_exec(void)
+{
+	int fd;
+
+	printf("%s SEAL-EXEC\n", memfd_str);
+
+	fd = mfd_assert_new("kern_memfd_seal_exec",
+			    mfd_def_size,
+			    MFD_CLOEXEC | MFD_ALLOW_SEALING);
+
+	mfd_assert_mode(fd, 0777);
+
+	mfd_assert_chmod(fd, 0644);
+
+	mfd_assert_has_seals(fd, 0);
+	mfd_assert_add_seals(fd, F_SEAL_EXEC);
+	mfd_assert_has_seals(fd, F_SEAL_EXEC);
+
+	mfd_assert_chmod(fd, 0600);
+	mfd_fail_chmod(fd, 0777);
+	mfd_fail_chmod(fd, 0670);
+	mfd_fail_chmod(fd, 0605);
+	mfd_fail_chmod(fd, 0700);
+	mfd_fail_chmod(fd, 0100);
+	mfd_assert_chmod(fd, 0666);
+
+	close(fd);
+}
+
 /*
  * Test sharing via dup()
  * Test that seals are shared between dupped FDs and they're all equal.
@@ -1059,6 +1185,7 @@ int main(int argc, char **argv)
 	test_seal_shrink();
 	test_seal_grow();
 	test_seal_resize();
+	test_seal_exec();
 
 	test_share_dup("SHARE-DUP", "");
 	test_share_mmap("SHARE-MMAP", "");
Signature · 1 line
2.39.0.rc0.267.gcb52ba06e7-goog
#3 lore raw

PATCH v4 3/6 mm/memfd: add MFD_NOEXEC_SEAL and MFD_EXEC

In reply to [email protected]

From: Jeff Xu <[email protected]>

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.

---
 include/linux/pid_namespace.h | 19 ++++++++++++++
 include/uapi/linux/memfd.h    |  4 +++
 kernel/pid_namespace.c        | 48 +++++++++++++++++++++++++++++++++++
 mm/memfd.c                    | 48 +++++++++++++++++++++++++++++++++--
 4 files changed, 117 insertions(+), 2 deletions(-)
include/linux/pid_namespace.h +19 -0
index 07481bb87d4e..a4789a7b34a9 100644
@@ -16,6 +16,21 @@
 
 struct fs_pin;
 
+#if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE)
+/*
+ * sysctl for vm.memfd_noexec
+ * 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.
+ */
+#define MEMFD_NOEXEC_SCOPE_EXEC		0
+#define MEMFD_NOEXEC_SCOPE_NOEXEC_SEAL		1
+#define MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED	2
+#endif
+
 struct pid_namespace {
 	struct idr idr;
 	struct rcu_head rcu;
@@ -31,6 +46,10 @@ struct pid_namespace {
 	struct ucounts *ucounts;
 	int reboot;	/* group exit code if this pidns was rebooted */
 	struct ns_common ns;
+#if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE)
+	/* sysctl for vm.memfd_noexec */
+	int memfd_noexec_scope;
+#endif
 } __randomize_layout;
 
 extern struct pid_namespace init_pid_ns;
include/uapi/linux/memfd.h +4 -0
index 7a8a26751c23..273a4e15dfcf 100644
@@ -8,6 +8,10 @@
 #define MFD_CLOEXEC		0x0001U
 #define MFD_ALLOW_SEALING	0x0002U
 #define MFD_HUGETLB		0x0004U
+/* not executable and sealed to prevent changing to executable. */
+#define MFD_NOEXEC_SEAL		0x0008U
+/* executable */
+#define MFD_EXEC		0x0010U
 
 /*
  * Huge page size encoding when MFD_HUGETLB is specified, and a huge page
kernel/pid_namespace.c +48 -0

66 lines not on this page · raw message

mm/memfd.c +46 -2

77 lines not on this page · raw message

Signature · 1 line
2.39.0.rc0.267.gcb52ba06e7-goog
#4 lore raw

PATCH v4 4/6 mm/memfd: Add write seals when apply SEAL_EXEC to executable memfd

In reply to [email protected]

From: Jeff Xu <[email protected]>

In order to avoid WX mappings, add F_SEAL_WRITE when apply F_SEAL_EXEC to an executable memfd, so W^X from start.

This implys application need to fill the content of the memfd first, after F_SEAL_EXEC is applied, application won't be able to modify the content of the memfd.

Typically, application seals the memfd right after writing to it. For example: 3> shall be right after 2> in steps below.
1. memfd_create(MFD_EXEC).
2. write() code to the memfd.
3. fcntl(F_ADD_SEALS, F_SEAL_EXEC) to convert the memfd to W^X.
4. call exec() on the memfd.

---
 mm/memfd.c | 6 ++++++
 1 file changed, 6 insertions(+)
mm/memfd.c +6 -0
index ec70675a7069..92f0a5765f7c 100644
@@ -222,6 +222,12 @@ static int memfd_add_seals(struct file *file, unsigned int seals)
 		}
 	}
 
+	/*
+	 * SEAL_EXEC implys SEAL_WRITE, making W^X from the start.
+	 */
+	if (seals & F_SEAL_EXEC && inode->i_mode & 0111)
+		seals |= F_SEAL_SHRINK|F_SEAL_GROW|F_SEAL_WRITE|F_SEAL_FUTURE_WRITE;
+
 	*file_seals |= seals;
 	error = 0;
 
Signature · 1 line
2.39.0.rc0.267.gcb52ba06e7-goog
#5 lore raw

PATCH v4 5/6 selftests/memfd: add tests for MFD_NOEXEC_SEAL MFD_EXEC

In reply to [email protected]

From: Jeff Xu <[email protected]>

Tests to verify MFD_NOEXEC, MFD_EXEC and vm.memfd_noexec sysctl.

Change-Id: Idccec1141255ca948c849f4efc8ba5e97f78b6eb

---
 tools/testing/selftests/memfd/fuse_test.c  |   1 +
 tools/testing/selftests/memfd/memfd_test.c | 185 ++++++++++++++++++++-
 2 files changed, 181 insertions(+), 5 deletions(-)
tools/testing/selftests/memfd/fuse_test.c +1 -0
index be675002f918..93798c8c5d54 100644
@@ -22,6 +22,7 @@
 #include <linux/falloc.h>
 #include <fcntl.h>
 #include <linux/memfd.h>
+#include <linux/types.h>
 #include <sched.h>
 #include <stdio.h>
 #include <stdlib.h>
tools/testing/selftests/memfd/memfd_test.c +180 -5

251 lines not on this page · raw message

Signature · 1 line
2.39.0.rc0.267.gcb52ba06e7-goog
#6 lore raw

PATCH v4 6/6 mm/memfd: security hook for memfd_create

In reply to [email protected]

From: Jeff Xu <[email protected]>

The new security_memfd_create allows lsm to check flags of memfd_create.

The security by default system (such as chromeos) can use this to implement system wide lsm to allow only non-executable memfd being created.

---
 include/linux/lsm_hook_defs.h |  1 +
 include/linux/lsm_hooks.h     |  4 ++++
 include/linux/security.h      |  6 ++++++
 mm/memfd.c                    |  5 +++++
 security/security.c           | 13 +++++++++++++
 5 files changed, 29 insertions(+)
include/linux/lsm_hook_defs.h +1 -0
index ec119da1d89b..fd40840927c8 100644
@@ -164,6 +164,7 @@ LSM_HOOK(int, 0, file_alloc_security, struct file *file)
 LSM_HOOK(void, LSM_RET_VOID, file_free_security, struct file *file)
 LSM_HOOK(int, 0, file_ioctl, struct file *file, unsigned int cmd,
 	 unsigned long arg)
+LSM_HOOK(int, 0, memfd_create, char *name, unsigned int flags)
 LSM_HOOK(int, 0, mmap_addr, unsigned long addr)
 LSM_HOOK(int, 0, mmap_file, struct file *file, unsigned long reqprot,
 	 unsigned long prot, unsigned long flags)
include/linux/lsm_hooks.h +4 -0
index 4ec80b96c22e..5a18a6552278 100644
@@ -543,6 +543,10 @@
  *	simple integer value.  When @arg represents a user space pointer, it
  *	should never be used by the security module.
  *	Return 0 if permission is granted.
+ * @memfd_create:
+ *	@name is the name of memfd file.
+ *	@flags is the flags used in memfd_create.
+ *	Return 0 if permission is granted.
  * @mmap_addr :
  *	Check permissions for a mmap operation at @addr.
  *	@addr contains virtual address that will be used for the operation.
include/linux/security.h +6 -0
index ca1b7109c0db..5b87a780822a 100644
@@ -384,6 +384,7 @@ int security_file_permission(struct file *file, int mask);
 int security_file_alloc(struct file *file);
 void security_file_free(struct file *file);
 int security_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
+int security_memfd_create(char *name, unsigned int flags);
 int security_mmap_file(struct file *file, unsigned long prot,
 			unsigned long flags);
 int security_mmap_addr(unsigned long addr);
@@ -963,6 +964,11 @@ static inline int security_file_ioctl(struct file *file, unsigned int cmd,
 	return 0;
 }
 
+static inline int security_memfd_create(char *name, unsigned int flags)
+{
+	return 0;
+}
+
 static inline int security_mmap_file(struct file *file, unsigned long prot,
 				     unsigned long flags)
 {
mm/memfd.c +5 -0
index 92f0a5765f7c..f04ed5f0474f 100644
@@ -356,6 +356,11 @@ SYSCALL_DEFINE2(memfd_create,
 		goto err_name;
 	}
 
+	/* security hook for memfd_create */
+	error = security_memfd_create(name, flags);
+	if (error)
+		return error;
+
 	if (flags & MFD_HUGETLB) {
 		file = hugetlb_file_setup(name, 0, VM_NORESERVE,
 					HUGETLB_ANONHUGE_INODE,
security/security.c +13 -0
index 79d82cb6e469..5c018e080923 100644
@@ -1010,6 +1010,19 @@ int security_sb_clone_mnt_opts(const struct super_block *oldsb,
 }
 EXPORT_SYMBOL(security_sb_clone_mnt_opts);
 
+int security_add_mnt_opt(const char *option, const char *val, int len,
+			 void **mnt_opts)
+{
+	return call_int_hook(sb_add_mnt_opt, -EINVAL,
+					option, val, len, mnt_opts);
+}
+EXPORT_SYMBOL(security_add_mnt_opt);
+
+int security_memfd_create(char *name, unsigned int flags)
+{
+	return call_int_hook(memfd_create, 0, name, flags);
+}
+
 int security_move_mount(const struct path *from_path, const struct path *to_path)
 {
 	return call_int_hook(move_mount, 0, from_path, to_path);
Signature · 1 line
2.39.0.rc0.267.gcb52ba06e7-goog