Merge branch 'for-5.7' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:

 - Christian extended clone3 so that processes can be spawned into
   cgroups directly.

   This is not only neat in terms of semantics but also avoids grabbing
   the global cgroup_threadgroup_rwsem for migration.

 - Daniel added !root xattr support to cgroupfs.

   Userland already uses xattrs on cgroupfs for bookkeeping. This will
   allow delegated cgroups to support such usages.

 - Prateek tried to make cpuset hotplug handling synchronous but that
   led to possible deadlock scenarios. Reverted.

 - Other minor changes including release_agent_path handling cleanup.

* 'for-5.7' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  docs: cgroup-v1: Document the cpuset_v2_mode mount option
  Revert "cpuset: Make cpuset hotplug synchronous"
  cgroupfs: Support user xattrs
  kernfs: Add option to enable user xattrs
  kernfs: Add removed_size out param for simple_xattr_set
  kernfs: kvmalloc xattr value instead of kmalloc
  cgroup: Restructure release_agent_path handling
  selftests/cgroup: add tests for cloning into cgroups
  clone3: allow spawning processes into cgroups
  cgroup: add cgroup_may_write() helper
  cgroup: refactor fork helpers
  cgroup: add cgroup_get_from_file() helper
  cgroup: unify attach permission checking
  cpuset: Make cpuset hotplug synchronous
  cgroup.c: Use built-in RCU list checking
  kselftest/cgroup: add cgroup destruction test
  cgroup: Clean up css_set task traversal

5 files changed, 327 insertions, 5 deletions

diff --git a/tools/testing/selftests/cgroup/Makefile b/tools/testing/selftests/cgroup/Makefile
index 66aafe1f5746..967f268fde74 100644
--- a/tools/testing/selftests/cgroup/Makefile
+++ b/tools/testing/selftests/cgroup/Makefile
@@ -11,6 +11,6 @@ TEST_GEN_PROGS += test_freezer
 
 include ../lib.mk
 
-$(OUTPUT)/test_memcontrol: cgroup_util.c
-$(OUTPUT)/test_core: cgroup_util.c
-$(OUTPUT)/test_freezer: cgroup_util.c
+$(OUTPUT)/test_memcontrol: cgroup_util.c ../clone3/clone3_selftests.h
+$(OUTPUT)/test_core: cgroup_util.c ../clone3/clone3_selftests.h
+$(OUTPUT)/test_freezer: cgroup_util.c ../clone3/clone3_selftests.h
diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c
index 8f7131dcf1ff..8a637ca7d73a 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.c
+++ b/tools/testing/selftests/cgroup/cgroup_util.c
@@ -15,6 +15,7 @@
 #include <unistd.h>
 
 #include "cgroup_util.h"
+#include "../clone3/clone3_selftests.h"
 
 static ssize_t read_text(const char *path, char *buf, size_t max_len)
 {
@@ -331,12 +332,112 @@ int cg_run(const char *cgroup,
 	}
 }
 
+pid_t clone_into_cgroup(int cgroup_fd)
+{
+#ifdef CLONE_ARGS_SIZE_VER2
+	pid_t pid;
+
+	struct clone_args args = {
+		.flags = CLONE_INTO_CGROUP,
+		.exit_signal = SIGCHLD,
+		.cgroup = cgroup_fd,
+	};
+
+	pid = sys_clone3(&args, sizeof(struct clone_args));
+	/*
+	 * Verify that this is a genuine test failure:
+	 * ENOSYS -> clone3() not available
+	 * E2BIG  -> CLONE_INTO_CGROUP not available
+	 */
+	if (pid < 0 && (errno == ENOSYS || errno == E2BIG))
+		goto pretend_enosys;
+
+	return pid;
+
+pretend_enosys:
+#endif
+	errno = ENOSYS;
+	return -ENOSYS;
+}
+
+int clone_reap(pid_t pid, int options)
+{
+	int ret;
+	siginfo_t info = {
+		.si_signo = 0,
+	};
+
+again:
+	ret = waitid(P_PID, pid, &info, options | __WALL | __WNOTHREAD);
+	if (ret < 0) {
+		if (errno == EINTR)
+			goto again;
+		return -1;
+	}
+
+	if (options & WEXITED) {
+		if (WIFEXITED(info.si_status))
+			return WEXITSTATUS(info.si_status);
+	}
+
+	if (options & WSTOPPED) {
+		if (WIFSTOPPED(info.si_status))
+			return WSTOPSIG(info.si_status);
+	}
+
+	if (options & WCONTINUED) {
+		if (WIFCONTINUED(info.si_status))
+			return 0;
+	}
+
+	return -1;
+}
+
+int dirfd_open_opath(const char *dir)
+{
+	return open(dir, O_DIRECTORY | O_CLOEXEC | O_NOFOLLOW | O_PATH);
+}
+
+#define close_prot_errno(fd)                                                   \
+	if (fd >= 0) {                                                         \
+		int _e_ = errno;                                               \
+		close(fd);                                                     \
+		errno = _e_;                                                   \
+	}
+
+static int clone_into_cgroup_run_nowait(const char *cgroup,
+					int (*fn)(const char *cgroup, void *arg),
+					void *arg)
+{
+	int cgroup_fd;
+	pid_t pid;
+
+	cgroup_fd =  dirfd_open_opath(cgroup);
+	if (cgroup_fd < 0)
+		return -1;
+
+	pid = clone_into_cgroup(cgroup_fd);
+	close_prot_errno(cgroup_fd);
+	if (pid == 0)
+		exit(fn(cgroup, arg));
+
+	return pid;
+}
+
 int cg_run_nowait(const char *cgroup,
 		  int (*fn)(const char *cgroup, void *arg),
 		  void *arg)
 {
 	int pid;
 
+	pid = clone_into_cgroup_run_nowait(cgroup, fn, arg);
+	if (pid > 0)
+		return pid;
+
+	/* Genuine test failure. */
+	if (pid < 0 && errno != ENOSYS)
+		return -1;
+
 	pid = fork();
 	if (pid == 0) {
 		char buf[64];
@@ -450,3 +551,28 @@ int proc_read_strstr(int pid, bool thread, const char *item, const char *needle)
 
 	return strstr(buf, needle) ? 0 : -1;
 }
+
+int clone_into_cgroup_run_wait(const char *cgroup)
+{
+	int cgroup_fd;
+	pid_t pid;
+
+	cgroup_fd =  dirfd_open_opath(cgroup);
+	if (cgroup_fd < 0)
+		return -1;
+
+	pid = clone_into_cgroup(cgroup_fd);
+	close_prot_errno(cgroup_fd);
+	if (pid < 0)
+		return -1;
+
+	if (pid == 0)
+		exit(EXIT_SUCCESS);
+
+	/*
+	 * We don't care whether this fails. We only care whether the initial
+	 * clone succeeded.
+	 */
+	(void)clone_reap(pid, WEXITED);
+	return 0;
+}
diff --git a/tools/testing/selftests/cgroup/cgroup_util.h b/tools/testing/selftests/cgroup/cgroup_util.h
index 49c54fbdb229..5a1305dd1f0b 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.h
+++ b/tools/testing/selftests/cgroup/cgroup_util.h
@@ -50,3 +50,7 @@ extern int cg_wait_for_proc_count(const char *cgroup, int count);
 extern int cg_killall(const char *cgroup);
 extern ssize_t proc_read_text(int pid, bool thread, const char *item, char *buf, size_t size);
 extern int proc_read_strstr(int pid, bool thread, const char *item, const char *needle);
+extern pid_t clone_into_cgroup(int cgroup_fd);
+extern int clone_reap(pid_t pid, int options);
+extern int clone_into_cgroup_run_wait(const char *cgroup);
+extern int dirfd_open_opath(const char *dir);
diff --git a/tools/testing/selftests/cgroup/test_core.c b/tools/testing/selftests/cgroup/test_core.c
index e19ce940cd6a..3df648c37876 100644
--- a/tools/testing/selftests/cgroup/test_core.c
+++ b/tools/testing/selftests/cgroup/test_core.c
@@ -2,7 +2,10 @@
 
 #include <linux/limits.h>
 #include <sys/types.h>
+#include <sys/mman.h>
+#include <sys/wait.h>
 #include <unistd.h>
+#include <fcntl.h>
 #include <stdio.h>
 #include <errno.h>
 #include <signal.h>
@@ -12,6 +15,115 @@
 #include "../kselftest.h"
 #include "cgroup_util.h"
 
+static int touch_anon(char *buf, size_t size)
+{
+	int fd;
+	char *pos = buf;
+
+	fd = open("/dev/urandom", O_RDONLY);
+	if (fd < 0)
+		return -1;
+
+	while (size > 0) {
+		ssize_t ret = read(fd, pos, size);
+
+		if (ret < 0) {
+			if (errno != EINTR) {
+				close(fd);
+				return -1;
+			}
+		} else {
+			pos += ret;
+			size -= ret;
+		}
+	}
+	close(fd);
+
+	return 0;
+}
+
+static int alloc_and_touch_anon_noexit(const char *cgroup, void *arg)
+{
+	int ppid = getppid();
+	size_t size = (size_t)arg;
+	void *buf;
+
+	buf = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON,
+		   0, 0);
+	if (buf == MAP_FAILED)
+		return -1;
+
+	if (touch_anon((char *)buf, size)) {
+		munmap(buf, size);
+		return -1;
+	}
+
+	while (getppid() == ppid)
+		sleep(1);
+
+	munmap(buf, size);
+	return 0;
+}
+
+/*
+ * Create a child process that allocates and touches 100MB, then waits to be
+ * killed. Wait until the child is attached to the cgroup, kill all processes
+ * in that cgroup and wait until "cgroup.procs" is empty. At this point try to
+ * destroy the empty cgroup. The test helps detect race conditions between
+ * dying processes leaving the cgroup and cgroup destruction path.
+ */
+static int test_cgcore_destroy(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *cg_test = NULL;
+	int child_pid;
+	char buf[PAGE_SIZE];
+
+	cg_test = cg_name(root, "cg_test");
+
+	if (!cg_test)
+		goto cleanup;
+
+	for (int i = 0; i < 10; i++) {
+		if (cg_create(cg_test))
+			goto cleanup;
+
+		child_pid = cg_run_nowait(cg_test, alloc_and_touch_anon_noexit,
+					  (void *) MB(100));
+
+		if (child_pid < 0)
+			goto cleanup;
+
+		/* wait for the child to enter cgroup */
+		if (cg_wait_for_proc_count(cg_test, 1))
+			goto cleanup;
+
+		if (cg_killall(cg_test))
+			goto cleanup;
+
+		/* wait for cgroup to be empty */
+		while (1) {
+			if (cg_read(cg_test, "cgroup.procs", buf, sizeof(buf)))
+				goto cleanup;
+			if (buf[0] == '\0')
+				break;
+			usleep(1000);
+		}
+
+		if (rmdir(cg_test))
+			goto cleanup;
+
+		if (waitpid(child_pid, NULL, 0) < 0)
+			goto cleanup;
+	}
+	ret = KSFT_PASS;
+cleanup:
+	if (cg_test)
+		cg_destroy(cg_test);
+	free(cg_test);
+	return ret;
+}
+
 /*
  * A(0) - B(0) - C(1)
  *        \ D(0)
@@ -25,8 +137,11 @@
 static int test_cgcore_populated(const char *root)
 {
 	int ret = KSFT_FAIL;
+	int err;
 	char *cg_test_a = NULL, *cg_test_b = NULL;
 	char *cg_test_c = NULL, *cg_test_d = NULL;
+	int cgroup_fd = -EBADF;
+	pid_t pid;
 
 	cg_test_a = cg_name(root, "cg_test_a");
 	cg_test_b = cg_name(root, "cg_test_a/cg_test_b");
@@ -78,6 +193,52 @@ static int test_cgcore_populated(const char *root)
 	if (cg_read_strcmp(cg_test_d, "cgroup.events", "populated 0\n"))
 		goto cleanup;
 
+	/* Test that we can directly clone into a new cgroup. */
+	cgroup_fd = dirfd_open_opath(cg_test_d);
+	if (cgroup_fd < 0)
+		goto cleanup;
+
+	pid = clone_into_cgroup(cgroup_fd);
+	if (pid < 0) {
+		if (errno == ENOSYS)
+			goto cleanup_pass;
+		goto cleanup;
+	}
+
+	if (pid == 0) {
+		if (raise(SIGSTOP))
+			exit(EXIT_FAILURE);
+		exit(EXIT_SUCCESS);
+	}
+
+	err = cg_read_strcmp(cg_test_d, "cgroup.events", "populated 1\n");
+
+	(void)clone_reap(pid, WSTOPPED);
+	(void)kill(pid, SIGCONT);
+	(void)clone_reap(pid, WEXITED);
+
+	if (err)
+		goto cleanup;
+
+	if (cg_read_strcmp(cg_test_d, "cgroup.events", "populated 0\n"))
+		goto cleanup;
+
+	/* Remove cgroup. */
+	if (cg_test_d) {
+		cg_destroy(cg_test_d);
+		free(cg_test_d);
+		cg_test_d = NULL;
+	}
+
+	pid = clone_into_cgroup(cgroup_fd);
+	if (pid < 0)
+		goto cleanup_pass;
+	if (pid == 0)
+		exit(EXIT_SUCCESS);
+	(void)clone_reap(pid, WEXITED);
+	goto cleanup;
+
+cleanup_pass:
 	ret = KSFT_PASS;
 
 cleanup:
@@ -93,6 +254,8 @@ cleanup:
 	free(cg_test_c);
 	free(cg_test_b);
 	free(cg_test_a);
+	if (cgroup_fd >= 0)
+		close(cgroup_fd);
 	return ret;
 }
 
@@ -136,6 +299,16 @@ static int test_cgcore_invalid_domain(const char *root)
 	if (errno != EOPNOTSUPP)
 		goto cleanup;
 
+	if (!clone_into_cgroup_run_wait(child))
+		goto cleanup;
+
+	if (errno == ENOSYS)
+		goto cleanup_pass;
+
+	if (errno != EOPNOTSUPP)
+		goto cleanup;
+
+cleanup_pass:
 	ret = KSFT_PASS;
 
 cleanup:
@@ -345,6 +518,9 @@ static int test_cgcore_internal_process_constraint(const char *root)
 	if (!cg_enter_current(parent))
 		goto cleanup;
 
+	if (!clone_into_cgroup_run_wait(parent))
+		goto cleanup;
+
 	ret = KSFT_PASS;
 
 cleanup:
@@ -512,6 +688,7 @@ struct corecg_test {
 	T(test_cgcore_populated),
 	T(test_cgcore_proc_migration),
 	T(test_cgcore_thread_migration),
+	T(test_cgcore_destroy),
 };
 #undef T
 
diff --git a/tools/testing/selftests/clone3/clone3_selftests.h b/tools/testing/selftests/clone3/clone3_selftests.h
index a3f2c8ad8bcc..91c1a78ddb39 100644
--- a/tools/testing/selftests/clone3/clone3_selftests.h
+++ b/tools/testing/selftests/clone3/clone3_selftests.h
@@ -5,12 +5,24 @@
 
 #define _GNU_SOURCE
 #include <sched.h>
+#include <linux/sched.h>
+#include <linux/types.h>
 #include <stdint.h>
 #include <syscall.h>
-#include <linux/types.h>
+#include <sys/wait.h>
+
+#include "../kselftest.h"
 
 #define ptr_to_u64(ptr) ((__u64)((uintptr_t)(ptr)))
 
+#ifndef CLONE_INTO_CGROUP
+#define CLONE_INTO_CGROUP 0x200000000ULL /* Clone into a specific cgroup given the right permissions. */
+#endif
+
+#ifndef CLONE_ARGS_SIZE_VER0
+#define CLONE_ARGS_SIZE_VER0 64
+#endif
+
 #ifndef __NR_clone3
 #define __NR_clone3 -1
 struct clone_args {
@@ -22,10 +34,13 @@ struct clone_args {
 	__aligned_u64 stack;
 	__aligned_u64 stack_size;
 	__aligned_u64 tls;
+#define CLONE_ARGS_SIZE_VER1 80
 	__aligned_u64 set_tid;
 	__aligned_u64 set_tid_size;
+#define CLONE_ARGS_SIZE_VER2 88
+	__aligned_u64 cgroup;
 };
-#endif
+#endif /* __NR_clone3 */
 
 static pid_t sys_clone3(struct clone_args *args, size_t size)
 {