Merge tag 'seccomp-next' of...

Merge tag 'seccomp-next' of https://git.kernel.org/pub/scm/linux/kernel/git/kees/linux into next-seccomp

Add SECCOMP_RET_USER_NOTIF

From Kees.

Documentation/ioctl/ioctl-number.txt

@@ -79,6 +79,7 @@ Code  Seq#(hex)	Include File		Comments
 0x1b	all	InfiniBand Subsystem	<http://infiniband.sourceforge.net/>
 0x20	all	drivers/cdrom/cm206.h
 0x22	all	scsi/sg.h
+'!'	00-1F	uapi/linux/seccomp.h
 '#'	00-3F	IEEE 1394 Subsystem	Block for the entire subsystem
 '$'	00-0F	linux/perf_counter.h, linux/perf_event.h
 '%'	00-0F	include/uapi/linux/stm.h

Documentation/userspace-api/seccomp_filter.rst

@@ -122,6 +122,11 @@ In precedence order, they are:
 	Results in the lower 16-bits of the return value being passed
 	to userland as the errno without executing the system call.
 
+``SECCOMP_RET_USER_NOTIF``:
+    Results in a ``struct seccomp_notif`` message sent on the userspace
+    notification fd, if it is attached, or ``-ENOSYS`` if it is not. See below
+    on discussion of how to handle user notifications.
+
 ``SECCOMP_RET_TRACE``:
 	When returned, this value will cause the kernel to attempt to
 	notify a ``ptrace()``-based tracer prior to executing the system
@@ -183,6 +188,85 @@ The ``samples/seccomp/`` directory contains both an x86-specific example
 and a more generic example of a higher level macro interface for BPF
 program generation.
 
+Userspace Notification
+======================
+
+The ``SECCOMP_RET_USER_NOTIF`` return code lets seccomp filters pass a
+particular syscall to userspace to be handled. This may be useful for
+applications like container managers, which wish to intercept particular
+syscalls (``mount()``, ``finit_module()``, etc.) and change their behavior.
+
+To acquire a notification FD, use the ``SECCOMP_FILTER_FLAG_NEW_LISTENER``
+argument to the ``seccomp()`` syscall:
+
+.. code-block:: c
+
+    fd = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_NEW_LISTENER, &prog);
+
+which (on success) will return a listener fd for the filter, which can then be
+passed around via ``SCM_RIGHTS`` or similar. Note that filter fds correspond to
+a particular filter, and not a particular task. So if this task then forks,
+notifications from both tasks will appear on the same filter fd. Reads and
+writes to/from a filter fd are also synchronized, so a filter fd can safely
+have many readers.
+
+The interface for a seccomp notification fd consists of two structures:
+
+.. code-block:: c
+
+    struct seccomp_notif_sizes {
+        __u16 seccomp_notif;
+        __u16 seccomp_notif_resp;
+        __u16 seccomp_data;
+    };
+
+    struct seccomp_notif {
+        __u64 id;
+        __u32 pid;
+        __u32 flags;
+        struct seccomp_data data;
+    };
+
+    struct seccomp_notif_resp {
+        __u64 id;
+        __s64 val;
+        __s32 error;
+        __u32 flags;
+    };
+
+The ``struct seccomp_notif_sizes`` structure can be used to determine the size
+of the various structures used in seccomp notifications. The size of ``struct
+seccomp_data`` may change in the future, so code should use:
+
+.. code-block:: c
+
+    struct seccomp_notif_sizes sizes;
+    seccomp(SECCOMP_GET_NOTIF_SIZES, 0, &sizes);
+
+to determine the size of the various structures to allocate. See
+samples/seccomp/user-trap.c for an example.
+
+Users can read via ``ioctl(SECCOMP_IOCTL_NOTIF_RECV)``  (or ``poll()``) on a
+seccomp notification fd to receive a ``struct seccomp_notif``, which contains
+five members: the input length of the structure, a unique-per-filter ``id``,
+the ``pid`` of the task which triggered this request (which may be 0 if the
+task is in a pid ns not visible from the listener's pid namespace), a ``flags``
+member which for now only has ``SECCOMP_NOTIF_FLAG_SIGNALED``, representing
+whether or not the notification is a result of a non-fatal signal, and the
+``data`` passed to seccomp. Userspace can then make a decision based on this
+information about what to do, and ``ioctl(SECCOMP_IOCTL_NOTIF_SEND)`` a
+response, indicating what should be returned to userspace. The ``id`` member of
+``struct seccomp_notif_resp`` should be the same ``id`` as in ``struct
+seccomp_notif``.
+
+It is worth noting that ``struct seccomp_data`` contains the values of register
+arguments to the syscall, but does not contain pointers to memory. The task's
+memory is accessible to suitably privileged traces via ``ptrace()`` or
+``/proc/pid/mem``. However, care should be taken to avoid the TOCTOU mentioned
+above in this document: all arguments being read from the tracee's memory
+should be read into the tracer's memory before any policy decisions are made.
+This allows for an atomic decision on syscall arguments.
+
 Sysctls
 =======
 

include/linux/seccomp.h

@@ -4,9 +4,10 @@
 
 #include <uapi/linux/seccomp.h>
 
-#define SECCOMP_FILTER_FLAG_MASK	(SECCOMP_FILTER_FLAG_TSYNC	| \
-					 SECCOMP_FILTER_FLAG_LOG	| \
-					 SECCOMP_FILTER_FLAG_SPEC_ALLOW)
+#define SECCOMP_FILTER_FLAG_MASK	(SECCOMP_FILTER_FLAG_TSYNC | \
+					 SECCOMP_FILTER_FLAG_LOG | \
+					 SECCOMP_FILTER_FLAG_SPEC_ALLOW | \
+					 SECCOMP_FILTER_FLAG_NEW_LISTENER)
 
 #ifdef CONFIG_SECCOMP
 
@@ -43,7 +44,7 @@ extern void secure_computing_strict(int this_syscall);
 #endif
 
 extern long prctl_get_seccomp(void);
-extern long prctl_set_seccomp(unsigned long, char __user *);
+extern long prctl_set_seccomp(unsigned long, void __user *);
 
 static inline int seccomp_mode(struct seccomp *s)
 {

include/linux/syscalls.h

@@ -879,7 +879,7 @@ asmlinkage long sys_renameat2(int olddfd, const char __user *oldname,
 			      int newdfd, const char __user *newname,
 			      unsigned int flags);
 asmlinkage long sys_seccomp(unsigned int op, unsigned int flags,
-			    const char __user *uargs);
+			    void __user *uargs);
 asmlinkage long sys_getrandom(char __user *buf, size_t count,
 			      unsigned int flags);
 asmlinkage long sys_memfd_create(const char __user *uname_ptr, unsigned int flags);

include/uapi/linux/seccomp.h

@@ -15,11 +15,13 @@
 #define SECCOMP_SET_MODE_STRICT		0
 #define SECCOMP_SET_MODE_FILTER		1
 #define SECCOMP_GET_ACTION_AVAIL	2
+#define SECCOMP_GET_NOTIF_SIZES		3
 
 /* Valid flags for SECCOMP_SET_MODE_FILTER */
-#define SECCOMP_FILTER_FLAG_TSYNC	(1UL << 0)
-#define SECCOMP_FILTER_FLAG_LOG		(1UL << 1)
-#define SECCOMP_FILTER_FLAG_SPEC_ALLOW	(1UL << 2)
+#define SECCOMP_FILTER_FLAG_TSYNC		(1UL << 0)
+#define SECCOMP_FILTER_FLAG_LOG			(1UL << 1)
+#define SECCOMP_FILTER_FLAG_SPEC_ALLOW		(1UL << 2)
+#define SECCOMP_FILTER_FLAG_NEW_LISTENER	(1UL << 3)
 
 /*
  * All BPF programs must return a 32-bit value.
@@ -35,6 +37,7 @@
 #define SECCOMP_RET_KILL	 SECCOMP_RET_KILL_THREAD
 #define SECCOMP_RET_TRAP	 0x00030000U /* disallow and force a SIGSYS */
 #define SECCOMP_RET_ERRNO	 0x00050000U /* returns an errno */
+#define SECCOMP_RET_USER_NOTIF	 0x7fc00000U /* notifies userspace */
 #define SECCOMP_RET_TRACE	 0x7ff00000U /* pass to a tracer or disallow */
 #define SECCOMP_RET_LOG		 0x7ffc0000U /* allow after logging */
 #define SECCOMP_RET_ALLOW	 0x7fff0000U /* allow */
@@ -60,4 +63,35 @@ struct seccomp_data {
 	__u64 args[6];
 };
 
+struct seccomp_notif_sizes {
+	__u16 seccomp_notif;
+	__u16 seccomp_notif_resp;
+	__u16 seccomp_data;
+};
+
+struct seccomp_notif {
+	__u64 id;
+	__u32 pid;
+	__u32 flags;
+	struct seccomp_data data;
+};
+
+struct seccomp_notif_resp {
+	__u64 id;
+	__s64 val;
+	__s32 error;
+	__u32 flags;
+};
+
+#define SECCOMP_IOC_MAGIC		'!'
+#define SECCOMP_IO(nr)			_IO(SECCOMP_IOC_MAGIC, nr)
+#define SECCOMP_IOR(nr, type)		_IOR(SECCOMP_IOC_MAGIC, nr, type)
+#define SECCOMP_IOW(nr, type)		_IOW(SECCOMP_IOC_MAGIC, nr, type)
+#define SECCOMP_IOWR(nr, type)		_IOWR(SECCOMP_IOC_MAGIC, nr, type)
+
+/* Flags for seccomp notification fd ioctl. */
+#define SECCOMP_IOCTL_NOTIF_RECV	SECCOMP_IOWR(0, struct seccomp_notif)
+#define SECCOMP_IOCTL_NOTIF_SEND	SECCOMP_IOWR(1,	\
+						struct seccomp_notif_resp)
+#define SECCOMP_IOCTL_NOTIF_ID_VALID	SECCOMP_IOR(2, __u64)
 #endif /* _UAPI_LINUX_SECCOMP_H */

samples/seccomp/.gitignore

 bpf-direct
 bpf-fancy
 dropper
+user-trap

samples/seccomp/Makefile

 # SPDX-License-Identifier: GPL-2.0
 ifndef CROSS_COMPILE
-hostprogs-$(CONFIG_SAMPLE_SECCOMP) := bpf-fancy dropper bpf-direct
+hostprogs-$(CONFIG_SAMPLE_SECCOMP) := bpf-fancy dropper bpf-direct user-trap
 
 HOSTCFLAGS_bpf-fancy.o += -I$(objtree)/usr/include
 HOSTCFLAGS_bpf-fancy.o += -idirafter $(objtree)/include
@@ -16,6 +16,10 @@ HOSTCFLAGS_bpf-direct.o += -I$(objtree)/usr/include
 HOSTCFLAGS_bpf-direct.o += -idirafter $(objtree)/include
 bpf-direct-objs := bpf-direct.o
 
+HOSTCFLAGS_user-trap.o += -I$(objtree)/usr/include
+HOSTCFLAGS_user-trap.o += -idirafter $(objtree)/include
+user-trap-objs := user-trap.o
+
 # Try to match the kernel target.
 ifndef CONFIG_64BIT
 
@@ -33,6 +37,7 @@ HOSTCFLAGS_bpf-fancy.o += $(MFLAG)
 HOSTLDLIBS_bpf-direct += $(MFLAG)
 HOSTLDLIBS_bpf-fancy += $(MFLAG)
 HOSTLDLIBS_dropper += $(MFLAG)
+HOSTLDLIBS_user-trap += $(MFLAG)
 endif
 always := $(hostprogs-m)
 endif

samples/seccomp/user-trap.c

+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <string.h>
+#include <stddef.h>
+#include <sys/sysmacros.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/mman.h>
+#include <sys/syscall.h>
+#include <sys/user.h>
+#include <sys/ioctl.h>
+#include <sys/ptrace.h>
+#include <sys/mount.h>
+#include <linux/limits.h>
+#include <linux/filter.h>
+#include <linux/seccomp.h>
+
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x)))
+
+static int seccomp(unsigned int op, unsigned int flags, void *args)
+{
+	errno = 0;
+	return syscall(__NR_seccomp, op, flags, args);
+}
+
+static int send_fd(int sock, int fd)
+{
+	struct msghdr msg = {};
+	struct cmsghdr *cmsg;
+	char buf[CMSG_SPACE(sizeof(int))] = {0}, c = 'c';
+	struct iovec io = {
+		.iov_base = &c,
+		.iov_len = 1,
+	};
+
+	msg.msg_iov = &io;
+	msg.msg_iovlen = 1;
+	msg.msg_control = buf;
+	msg.msg_controllen = sizeof(buf);
+	cmsg = CMSG_FIRSTHDR(&msg);
+	cmsg->cmsg_level = SOL_SOCKET;
+	cmsg->cmsg_type = SCM_RIGHTS;
+	cmsg->cmsg_len = CMSG_LEN(sizeof(int));
+	*((int *)CMSG_DATA(cmsg)) = fd;
+	msg.msg_controllen = cmsg->cmsg_len;
+
+	if (sendmsg(sock, &msg, 0) < 0) {
+		perror("sendmsg");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int recv_fd(int sock)
+{
+	struct msghdr msg = {};
+	struct cmsghdr *cmsg;
+	char buf[CMSG_SPACE(sizeof(int))] = {0}, c = 'c';
+	struct iovec io = {
+		.iov_base = &c,
+		.iov_len = 1,
+	};
+
+	msg.msg_iov = &io;
+	msg.msg_iovlen = 1;
+	msg.msg_control = buf;
+	msg.msg_controllen = sizeof(buf);
+
+	if (recvmsg(sock, &msg, 0) < 0) {
+		perror("recvmsg");
+		return -1;
+	}
+
+	cmsg = CMSG_FIRSTHDR(&msg);
+
+	return *((int *)CMSG_DATA(cmsg));
+}
+
+static int user_trap_syscall(int nr, unsigned int flags)
+{
+	struct sock_filter filter[] = {
+		BPF_STMT(BPF_LD+BPF_W+BPF_ABS,
+			offsetof(struct seccomp_data, nr)),
+		BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, nr, 0, 1),
+		BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_USER_NOTIF),
+		BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW),
+	};
+
+	struct sock_fprog prog = {
+		.len = (unsigned short)ARRAY_SIZE(filter),
+		.filter = filter,
+	};
+
+	return seccomp(SECCOMP_SET_MODE_FILTER, flags, &prog);
+}
+
+static int handle_req(struct seccomp_notif *req,
+		      struct seccomp_notif_resp *resp, int listener)
+{
+	char path[PATH_MAX], source[PATH_MAX], target[PATH_MAX];
+	int ret = -1, mem;
+
+	resp->id = req->id;
+	resp->error = -EPERM;
+	resp->val = 0;
+
+	if (req->data.nr != __NR_mount) {
+		fprintf(stderr, "huh? trapped something besides mount? %d\n", req->data.nr);
+		return -1;
+	}
+
+	/* Only allow bind mounts. */
+	if (!(req->data.args[3] & MS_BIND))
+		return 0;
+
+	/*
+	 * Ok, let's read the task's memory to see where they wanted their
+	 * mount to go.
+	 */
+	snprintf(path, sizeof(path), "/proc/%d/mem", req->pid);
+	mem = open(path, O_RDONLY);
+	if (mem < 0) {
+		perror("open mem");
+		return -1;
+	}
+
+	/*
+	 * Now we avoid a TOCTOU: we referred to a pid by its pid, but since
+	 * the pid that made the syscall may have died, we need to confirm that
+	 * the pid is still valid after we open its /proc/pid/mem file. We can
+	 * ask the listener fd this as follows.
+	 *
+	 * Note that this check should occur *after* any task-specific
+	 * resources are opened, to make sure that the task has not died and
+	 * we're not wrongly reading someone else's state in order to make
+	 * decisions.
+	 */
+	if (ioctl(listener, SECCOMP_IOCTL_NOTIF_ID_VALID, &req->id) < 0) {
+		fprintf(stderr, "task died before we could map its memory\n");
+		goto out;
+	}
+
+	/*
+	 * Phew, we've got the right /proc/pid/mem. Now we can read it. Note
+	 * that to avoid another TOCTOU, we should read all of the pointer args
+	 * before we decide to allow the syscall.
+	 */
+	if (lseek(mem, req->data.args[0], SEEK_SET) < 0) {
+		perror("seek");
+		goto out;
+	}
+
+	ret = read(mem, source, sizeof(source));
+	if (ret < 0) {
+		perror("read");
+		goto out;
+	}
+
+	if (lseek(mem, req->data.args[1], SEEK_SET) < 0) {
+		perror("seek");
+		goto out;
+	}
+
+	ret = read(mem, target, sizeof(target));
+	if (ret < 0) {
+		perror("read");
+		goto out;
+	}
+
+	/*
+	 * Our policy is to only allow bind mounts inside /tmp. This isn't very
+	 * interesting, because we could do unprivlieged bind mounts with user
+	 * namespaces already, but you get the idea.
+	 */
+	if (!strncmp(source, "/tmp/", 5) && !strncmp(target, "/tmp/", 5)) {
+		if (mount(source, target, NULL, req->data.args[3], NULL) < 0) {
+			ret = -1;
+			perror("actual mount");
+			goto out;
+		}
+		resp->error = 0;
+	}
+
+	/* Even if we didn't allow it because of policy, generating the
+	 * response was be a success, because we want to tell the worker EPERM.
+	 */
+	ret = 0;
+
+out:
+	close(mem);
+	return ret;
+}
+
+int main(void)
+{
+	int sk_pair[2], ret = 1, status, listener;
+	pid_t worker = 0 , tracer = 0;
+
+	if (socketpair(PF_LOCAL, SOCK_SEQPACKET, 0, sk_pair) < 0) {
+		perror("socketpair");
+		return 1;
+	}
+
+	worker = fork();
+	if (worker < 0) {
+		perror("fork");
+		goto close_pair;
+	}
+
+	if (worker == 0) {
+		listener = user_trap_syscall(__NR_mount,
+					     SECCOMP_FILTER_FLAG_NEW_LISTENER);
+		if (listener < 0) {
+			perror("seccomp");
+			exit(1);
+		}
+
+		/*
+		 * Drop privileges. We definitely can't mount as uid 1000.
+		 */
+		if (setuid(1000) < 0) {
+			perror("setuid");
+			exit(1);
+		}
+
+		/*
+		 * Send the listener to the parent; also serves as
+		 * synchronization.
+		 */
+		if (send_fd(sk_pair[1], listener) < 0)
+			exit(1);
+		close(listener);
+
+		if (mkdir("/tmp/foo", 0755) < 0) {
+			perror("mkdir");
+			exit(1);
+		}
+
+		/*
+		 * Try a bad mount just for grins.
+		 */
+		if (mount("/dev/sda", "/tmp/foo", NULL, 0, NULL) != -1) {
+			fprintf(stderr, "huh? mounted /dev/sda?\n");
+			exit(1);
+		}
+
+		if (errno != EPERM) {
+			perror("bad error from mount");
+			exit(1);
+		}
+
+		/*
+		 * Ok, we expect this one to succeed.
+		 */
+		if (mount("/tmp/foo", "/tmp/foo", NULL, MS_BIND, NULL) < 0) {
+			perror("mount");
+			exit(1);
+		}
+
+		exit(0);
+	}
+
+	/*
+	 * Get the listener from the child.
+	 */
+	listener = recv_fd(sk_pair[0]);
+	if (listener < 0)
+		goto out_kill;
+
+	/*
+	 * Fork a task to handle the requests. This isn't strictly necessary,
+	 * but it makes the particular writing of this sample easier, since we
+	 * can just wait ofr the tracee to exit and kill the tracer.
+	 */
+	tracer = fork();
+	if (tracer < 0) {
+		perror("fork");
+		goto out_kill;
+	}
+
+	if (tracer == 0) {
+		struct seccomp_notif *req;
+		struct seccomp_notif_resp *resp;
+		struct seccomp_notif_sizes sizes;
+
+		if (seccomp(SECCOMP_GET_NOTIF_SIZES, 0, &sizes) < 0) {
+			perror("seccomp(GET_NOTIF_SIZES)");
+			goto out_close;
+		}
+
+		req = malloc(sizes.seccomp_notif);
+		if (!req)
+			goto out_close;
+		memset(req, 0, sizeof(*req));
+
+		resp = malloc(sizes.seccomp_notif_resp);
+		if (!resp)
+			goto out_req;
+		memset(resp, 0, sizeof(*resp));
+
+		while (1) {
+			if (ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, req)) {
+				perror("ioctl recv");
+				goto out_resp;
+			}
+
+			if (handle_req(req, resp, listener) < 0)
+				goto out_resp;
+
+			/*
+			 * ENOENT here means that the task may have gotten a
+			 * signal and restarted the syscall. It's up to the
+			 * handler to decide what to do in this case, but for
+			 * the sample code, we just ignore it. Probably
+			 * something better should happen, like undoing the
+			 * mount, or keeping track of the args to make sure we
+			 * don't do it again.
+			 */
+			if (ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, resp) < 0 &&
+			    errno != ENOENT) {
+				perror("ioctl send");
+				goto out_resp;
+			}
+		}
+out_resp:
+		free(resp);
+out_req:
+		free(req);
+out_close:
+		close(listener);
+		exit(1);
+	}
+
+	close(listener);
+
+	if (waitpid(worker, &status, 0) != worker) {
+		perror("waitpid");
+		goto out_kill;
+	}
+
+	if (umount2("/tmp/foo", MNT_DETACH) < 0 && errno != EINVAL) {
+		perror("umount2");
+		goto out_kill;
+	}
+
+	if (remove("/tmp/foo") < 0 && errno != ENOENT) {
+		perror("remove");
+		exit(1);
+	}
+
+	if (!WIFEXITED(status) || WEXITSTATUS(status)) {
+		fprintf(stderr, "worker exited nonzero\n");
+		goto out_kill;
+	}
+
+	ret = 0;
+
+out_kill:
+	if (tracer > 0)
+		kill(tracer, SIGKILL);
+	if (worker > 0)
+		kill(worker, SIGKILL);
+
+close_pair:
+	close(sk_pair[0]);
+	close(sk_pair[1]);
+	return ret;
+}