Merge tag 'threads-v5.6' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux

Pull thread management updates from Christian Brauner:
 "Sargun Dhillon over the last cycle has worked on the pidfd_getfd()
  syscall.

  This syscall allows for the retrieval of file descriptors of a process
  based on its pidfd. A task needs to have ptrace_may_access()
  permissions with PTRACE_MODE_ATTACH_REALCREDS (suggested by Oleg and
  Andy) on the target.

  One of the main use-cases is in combination with seccomp's user
  notification feature. As a reminder, seccomp's user notification
  feature was made available in v5.0. It allows a task to retrieve a
  file descriptor for its seccomp filter. The file descriptor is usually
  handed of to a more privileged supervising process. The supervisor can
  then listen for syscall events caught by the seccomp filter of the
  supervisee and perform actions in lieu of the supervisee, usually
  emulating syscalls. pidfd_getfd() is needed to expand its uses.

  There are currently two major users that wait on pidfd_getfd() and one
  future user:

   - Netflix, Sargun said, is working on a service mesh where users
     should be able to connect to a dns-based VIP. When a user connects
     to e.g. 1.2.3.4:80 that runs e.g. service "foo" they will be
     redirected to an envoy process. This service mesh uses seccomp user
     notifications and pidfd to intercept all connect calls and instead
     of connecting them to 1.2.3.4:80 connects them to e.g.
     127.0.0.1:8080.

   - LXD uses the seccomp notifier heavily to intercept and emulate
     mknod() and mount() syscalls for unprivileged containers/processes.
     With pidfd_getfd() more uses-cases e.g. bridging socket connections
     will be possible.

   - The patchset has also seen some interest from the browser corner.
     Right now, Firefox is using a SECCOMP_RET_TRAP sandbox managed by a
     broker process. In the future glibc will start blocking all signals
     during dlopen() rendering this type of sandbox impossible. Hence,
     in the future Firefox will switch to a seccomp-user-nofication
     based sandbox which also makes use of file descriptor retrieval.
     The thread for this can be found at
     https://sourceware.org/ml/libc-alpha/2019-12/msg00079.html

  With pidfd_getfd() it is e.g. possible to bridge socket connections
  for the supervisee (binding to a privileged port) and taking actions
  on file descriptors on behalf of the supervisee in general.

  Sargun's first version was using an ioctl on pidfds but various people
  pushed for it to be a proper syscall which he duely implemented as
  well over various review cycles. Selftests are of course included.
  I've also added instructions how to deal with merge conflicts below.

  There's also a small fix coming from the kernel mentee project to
  correctly annotate struct sighand_struct with __rcu to fix various
  sparse warnings. We've received a few more such fixes and even though
  they are mostly trivial I've decided to postpone them until after -rc1
  since they came in rather late and I don't want to risk introducing
  build warnings.

  Finally, there's a new prctl() command PR_{G,S}ET_IO_FLUSHER which is
  needed to avoid allocation recursions triggerable by storage drivers
  that have userspace parts that run in the IO path (e.g. dm-multipath,
  iscsi, etc). These allocation recursions deadlock the device.

  The new prctl() allows such privileged userspace components to avoid
  allocation recursions by setting the PF_MEMALLOC_NOIO and
  PF_LESS_THROTTLE flags. The patch carries the necessary acks from the
  relevant maintainers and is routed here as part of prctl()
  thread-management."

* tag 'threads-v5.6' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux:
  prctl: PR_{G,S}ET_IO_FLUSHER to support controlling memory reclaim
  sched.h: Annotate sighand_struct with __rcu
  test: Add test for pidfd getfd
  arch: wire up pidfd_getfd syscall
  pid: Implement pidfd_getfd syscall
  vfs, fdtable: Add fget_task helper

4 files changed, 260 insertions, 1 deletions

diff --git a/tools/testing/selftests/pidfd/.gitignore b/tools/testing/selftests/pidfd/.gitignore
index 8d069490e17b..3a779c084d96 100644
--- a/tools/testing/selftests/pidfd/.gitignore
+++ b/tools/testing/selftests/pidfd/.gitignore
@@ -2,3 +2,4 @@ pidfd_open_test
 pidfd_poll_test
 pidfd_test
 pidfd_wait
+pidfd_getfd_test
diff --git a/tools/testing/selftests/pidfd/Makefile b/tools/testing/selftests/pidfd/Makefile
index 43db1b98e845..75a545861375 100644
--- a/tools/testing/selftests/pidfd/Makefile
+++ b/tools/testing/selftests/pidfd/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 CFLAGS += -g -I../../../../usr/include/ -pthread
 
-TEST_GEN_PROGS := pidfd_test pidfd_fdinfo_test pidfd_open_test pidfd_poll_test pidfd_wait
+TEST_GEN_PROGS := pidfd_test pidfd_fdinfo_test pidfd_open_test pidfd_poll_test pidfd_wait pidfd_getfd_test
 
 include ../lib.mk
 
diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h
index c6bc68329f4b..d482515604db 100644
--- a/tools/testing/selftests/pidfd/pidfd.h
+++ b/tools/testing/selftests/pidfd/pidfd.h
@@ -36,6 +36,10 @@
 #define __NR_clone3 -1
 #endif
 
+#ifndef __NR_pidfd_getfd
+#define __NR_pidfd_getfd -1
+#endif
+
 /*
  * The kernel reserves 300 pids via RESERVED_PIDS in kernel/pid.c
  * That means, when it wraps around any pid < 300 will be skipped.
@@ -84,4 +88,9 @@ static inline int sys_pidfd_send_signal(int pidfd, int sig, siginfo_t *info,
 	return syscall(__NR_pidfd_send_signal, pidfd, sig, info, flags);
 }
 
+static inline int sys_pidfd_getfd(int pidfd, int fd, int flags)
+{
+	return syscall(__NR_pidfd_getfd, pidfd, fd, flags);
+}
+
 #endif /* __PIDFD_H */
diff --git a/tools/testing/selftests/pidfd/pidfd_getfd_test.c b/tools/testing/selftests/pidfd/pidfd_getfd_test.c
new file mode 100644
index 000000000000..401a7c1d0312
--- /dev/null
+++ b/tools/testing/selftests/pidfd/pidfd_getfd_test.c
@@ -0,0 +1,249 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <linux/types.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <syscall.h>
+#include <sys/prctl.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include <sys/socket.h>
+#include <linux/kcmp.h>
+
+#include "pidfd.h"
+#include "../kselftest.h"
+#include "../kselftest_harness.h"
+
+/*
+ * UNKNOWN_FD is an fd number that should never exist in the child, as it is
+ * used to check the negative case.
+ */
+#define UNKNOWN_FD 111
+#define UID_NOBODY 65535
+
+static int sys_kcmp(pid_t pid1, pid_t pid2, int type, unsigned long idx1,
+		    unsigned long idx2)
+{
+	return syscall(__NR_kcmp, pid1, pid2, type, idx1, idx2);
+}
+
+static int sys_memfd_create(const char *name, unsigned int flags)
+{
+	return syscall(__NR_memfd_create, name, flags);
+}
+
+static int __child(int sk, int memfd)
+{
+	int ret;
+	char buf;
+
+	/*
+	 * Ensure we don't leave around a bunch of orphaned children if our
+	 * tests fail.
+	 */
+	ret = prctl(PR_SET_PDEATHSIG, SIGKILL);
+	if (ret) {
+		fprintf(stderr, "%s: Child could not set DEATHSIG\n",
+			strerror(errno));
+		return -1;
+	}
+
+	ret = send(sk, &memfd, sizeof(memfd), 0);
+	if (ret != sizeof(memfd)) {
+		fprintf(stderr, "%s: Child failed to send fd number\n",
+			strerror(errno));
+		return -1;
+	}
+
+	/*
+	 * The fixture setup is completed at this point. The tests will run.
+	 *
+	 * This blocking recv enables the parent to message the child.
+	 * Either we will read 'P' off of the sk, indicating that we need
+	 * to disable ptrace, or we will read a 0, indicating that the other
+	 * side has closed the sk. This occurs during fixture teardown time,
+	 * indicating that the child should exit.
+	 */
+	while ((ret = recv(sk, &buf, sizeof(buf), 0)) > 0) {
+		if (buf == 'P') {
+			ret = prctl(PR_SET_DUMPABLE, 0);
+			if (ret < 0) {
+				fprintf(stderr,
+					"%s: Child failed to disable ptrace\n",
+					strerror(errno));
+				return -1;
+			}
+		} else {
+			fprintf(stderr, "Child received unknown command %c\n",
+				buf);
+			return -1;
+		}
+		ret = send(sk, &buf, sizeof(buf), 0);
+		if (ret != 1) {
+			fprintf(stderr, "%s: Child failed to ack\n",
+				strerror(errno));
+			return -1;
+		}
+	}
+	if (ret < 0) {
+		fprintf(stderr, "%s: Child failed to read from socket\n",
+			strerror(errno));
+		return -1;
+	}
+
+	return 0;
+}
+
+static int child(int sk)
+{
+	int memfd, ret;
+
+	memfd = sys_memfd_create("test", 0);
+	if (memfd < 0) {
+		fprintf(stderr, "%s: Child could not create memfd\n",
+			strerror(errno));
+		ret = -1;
+	} else {
+		ret = __child(sk, memfd);
+		close(memfd);
+	}
+
+	close(sk);
+	return ret;
+}
+
+FIXTURE(child)
+{
+	/*
+	 * remote_fd is the number of the FD which we are trying to retrieve
+	 * from the child.
+	 */
+	int remote_fd;
+	/* pid points to the child which we are fetching FDs from */
+	pid_t pid;
+	/* pidfd is the pidfd of the child */
+	int pidfd;
+	/*
+	 * sk is our side of the socketpair used to communicate with the child.
+	 * When it is closed, the child will exit.
+	 */
+	int sk;
+};
+
+FIXTURE_SETUP(child)
+{
+	int ret, sk_pair[2];
+
+	ASSERT_EQ(0, socketpair(PF_LOCAL, SOCK_SEQPACKET, 0, sk_pair)) {
+		TH_LOG("%s: failed to create socketpair", strerror(errno));
+	}
+	self->sk = sk_pair[0];
+
+	self->pid = fork();
+	ASSERT_GE(self->pid, 0);
+
+	if (self->pid == 0) {
+		close(sk_pair[0]);
+		if (child(sk_pair[1]))
+			_exit(EXIT_FAILURE);
+		_exit(EXIT_SUCCESS);
+	}
+
+	close(sk_pair[1]);
+
+	self->pidfd = sys_pidfd_open(self->pid, 0);
+	ASSERT_GE(self->pidfd, 0);
+
+	/*
+	 * Wait for the child to complete setup. It'll send the remote memfd's
+	 * number when ready.
+	 */
+	ret = recv(sk_pair[0], &self->remote_fd, sizeof(self->remote_fd), 0);
+	ASSERT_EQ(sizeof(self->remote_fd), ret);
+}
+
+FIXTURE_TEARDOWN(child)
+{
+	EXPECT_EQ(0, close(self->pidfd));
+	EXPECT_EQ(0, close(self->sk));
+
+	EXPECT_EQ(0, wait_for_pid(self->pid));
+}
+
+TEST_F(child, disable_ptrace)
+{
+	int uid, fd;
+	char c;
+
+	/*
+	 * Turn into nobody if we're root, to avoid CAP_SYS_PTRACE
+	 *
+	 * The tests should run in their own process, so even this test fails,
+	 * it shouldn't result in subsequent tests failing.
+	 */
+	uid = getuid();
+	if (uid == 0)
+		ASSERT_EQ(0, seteuid(UID_NOBODY));
+
+	ASSERT_EQ(1, send(self->sk, "P", 1, 0));
+	ASSERT_EQ(1, recv(self->sk, &c, 1, 0));
+
+	fd = sys_pidfd_getfd(self->pidfd, self->remote_fd, 0);
+	EXPECT_EQ(-1, fd);
+	EXPECT_EQ(EPERM, errno);
+
+	if (uid == 0)
+		ASSERT_EQ(0, seteuid(0));
+}
+
+TEST_F(child, fetch_fd)
+{
+	int fd, ret;
+
+	fd = sys_pidfd_getfd(self->pidfd, self->remote_fd, 0);
+	ASSERT_GE(fd, 0);
+
+	EXPECT_EQ(0, sys_kcmp(getpid(), self->pid, KCMP_FILE, fd, self->remote_fd));
+
+	ret = fcntl(fd, F_GETFD);
+	ASSERT_GE(ret, 0);
+	EXPECT_GE(ret & FD_CLOEXEC, 0);
+
+	close(fd);
+}
+
+TEST_F(child, test_unknown_fd)
+{
+	int fd;
+
+	fd = sys_pidfd_getfd(self->pidfd, UNKNOWN_FD, 0);
+	EXPECT_EQ(-1, fd) {
+		TH_LOG("getfd succeeded while fetching unknown fd");
+	};
+	EXPECT_EQ(EBADF, errno) {
+		TH_LOG("%s: getfd did not get EBADF", strerror(errno));
+	}
+}
+
+TEST(flags_set)
+{
+	ASSERT_EQ(-1, sys_pidfd_getfd(0, 0, 1));
+	EXPECT_EQ(errno, EINVAL);
+}
+
+#if __NR_pidfd_getfd == -1
+int main(void)
+{
+	fprintf(stderr, "__NR_pidfd_getfd undefined. The pidfd_getfd syscall is unavailable. Test aborting\n");
+	return KSFT_SKIP;
+}
+#else
+TEST_HARNESS_MAIN
+#endif