1 files changed, 379 insertions, 61 deletions

diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c
index 9d59c3990ca8..20cede4db3ce 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.c
+++ b/tools/testing/selftests/bpf/cgroup_helpers.c
@@ -4,6 +4,7 @@
 #include <sys/mount.h>
 #include <sys/stat.h>
 #include <sys/types.h>
+#include <sys/xattr.h>
 #include <linux/limits.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -13,6 +14,7 @@
 #include <ftw.h>
 
 #include "cgroup_helpers.h"
+#include "bpf_util.h"
 
 /*
  * To avoid relying on the system setup, when setup_cgroup_env is called
@@ -33,49 +35,59 @@
 #define CGROUP_MOUNT_DFLT		"/sys/fs/cgroup"
 #define NETCLS_MOUNT_PATH		CGROUP_MOUNT_DFLT "/net_cls"
 #define CGROUP_WORK_DIR			"/cgroup-test-work-dir"
-#define format_cgroup_path(buf, path) \
+
+#define format_cgroup_path_pid(buf, path, pid) \
 	snprintf(buf, sizeof(buf), "%s%s%d%s", CGROUP_MOUNT_PATH, \
-	CGROUP_WORK_DIR, getpid(), path)
+	CGROUP_WORK_DIR, pid, path)
 
-#define format_classid_path(buf)				\
-	snprintf(buf, sizeof(buf), "%s%s", NETCLS_MOUNT_PATH,	\
-		 CGROUP_WORK_DIR)
+#define format_cgroup_path(buf, path) \
+	format_cgroup_path_pid(buf, path, getpid())
 
-/**
- * enable_all_controllers() - Enable all available cgroup v2 controllers
- *
- * Enable all available cgroup v2 controllers in order to increase
- * the code coverage.
- *
- * If successful, 0 is returned.
- */
-static int enable_all_controllers(char *cgroup_path)
+#define format_parent_cgroup_path(buf, path) \
+	format_cgroup_path_pid(buf, path, getppid())
+
+#define format_classid_path_pid(buf, pid)				\
+	snprintf(buf, sizeof(buf), "%s%s%d", NETCLS_MOUNT_PATH,	\
+		 CGROUP_WORK_DIR, pid)
+
+#define format_classid_path(buf)	\
+	format_classid_path_pid(buf, getpid())
+
+static __thread bool cgroup_workdir_mounted;
+
+static void __cleanup_cgroup_environment(void);
+
+static int __enable_controllers(const char *cgroup_path, const char *controllers)
 {
 	char path[PATH_MAX + 1];
-	char buf[PATH_MAX];
+	char enable[PATH_MAX + 1];
 	char *c, *c2;
 	int fd, cfd;
 	ssize_t len;
 
-	snprintf(path, sizeof(path), "%s/cgroup.controllers", cgroup_path);
-	fd = open(path, O_RDONLY);
-	if (fd < 0) {
-		log_err("Opening cgroup.controllers: %s", path);
-		return 1;
-	}
-
-	len = read(fd, buf, sizeof(buf) - 1);
-	if (len < 0) {
+	/* If not controllers are passed, enable all available controllers */
+	if (!controllers) {
+		snprintf(path, sizeof(path), "%s/cgroup.controllers",
+			 cgroup_path);
+		fd = open(path, O_RDONLY);
+		if (fd < 0) {
+			log_err("Opening cgroup.controllers: %s", path);
+			return 1;
+		}
+		len = read(fd, enable, sizeof(enable) - 1);
+		if (len < 0) {
+			close(fd);
+			log_err("Reading cgroup.controllers: %s", path);
+			return 1;
+		} else if (len == 0) { /* No controllers to enable */
+			close(fd);
+			return 0;
+		}
+		enable[len] = 0;
 		close(fd);
-		log_err("Reading cgroup.controllers: %s", path);
-		return 1;
+	} else {
+		bpf_strlcpy(enable, controllers, sizeof(enable));
 	}
-	buf[len] = 0;
-	close(fd);
-
-	/* No controllers available? We're probably on cgroup v1. */
-	if (len == 0)
-		return 0;
 
 	snprintf(path, sizeof(path), "%s/cgroup.subtree_control", cgroup_path);
 	cfd = open(path, O_RDWR);
@@ -84,7 +96,7 @@ static int enable_all_controllers(char *cgroup_path)
 		return 1;
 	}
 
-	for (c = strtok_r(buf, " ", &c2); c; c = strtok_r(NULL, " ", &c2)) {
+	for (c = strtok_r(enable, " ", &c2); c; c = strtok_r(NULL, " ", &c2)) {
 		if (dprintf(cfd, "+%s\n", c) <= 0) {
 			log_err("Enabling controller %s: %s", c, path);
 			close(cfd);
@@ -96,6 +108,87 @@ static int enable_all_controllers(char *cgroup_path)
 }
 
 /**
+ * enable_controllers() - Enable cgroup v2 controllers
+ * @relative_path: The cgroup path, relative to the workdir
+ * @controllers: List of controllers to enable in cgroup.controllers format
+ *
+ *
+ * Enable given cgroup v2 controllers, if @controllers is NULL, enable all
+ * available controllers.
+ *
+ * If successful, 0 is returned.
+ */
+int enable_controllers(const char *relative_path, const char *controllers)
+{
+	char cgroup_path[PATH_MAX + 1];
+
+	format_cgroup_path(cgroup_path, relative_path);
+	return __enable_controllers(cgroup_path, controllers);
+}
+
+static int __write_cgroup_file(const char *cgroup_path, const char *file,
+			       const char *buf)
+{
+	char file_path[PATH_MAX + 1];
+	int fd;
+
+	snprintf(file_path, sizeof(file_path), "%s/%s", cgroup_path, file);
+	fd = open(file_path, O_RDWR);
+	if (fd < 0) {
+		log_err("Opening %s", file_path);
+		return 1;
+	}
+
+	if (dprintf(fd, "%s", buf) <= 0) {
+		log_err("Writing to %s", file_path);
+		close(fd);
+		return 1;
+	}
+	close(fd);
+	return 0;
+}
+
+/**
+ * write_cgroup_file() - Write to a cgroup file
+ * @relative_path: The cgroup path, relative to the workdir
+ * @file: The name of the file in cgroupfs to write to
+ * @buf: Buffer to write to the file
+ *
+ * Write to a file in the given cgroup's directory.
+ *
+ * If successful, 0 is returned.
+ */
+int write_cgroup_file(const char *relative_path, const char *file,
+		      const char *buf)
+{
+	char cgroup_path[PATH_MAX - 24];
+
+	format_cgroup_path(cgroup_path, relative_path);
+	return __write_cgroup_file(cgroup_path, file, buf);
+}
+
+/**
+ * write_cgroup_file_parent() - Write to a cgroup file in the parent process
+ *                              workdir
+ * @relative_path: The cgroup path, relative to the parent process workdir
+ * @file: The name of the file in cgroupfs to write to
+ * @buf: Buffer to write to the file
+ *
+ * Write to a file in the given cgroup's directory under the parent process
+ * workdir.
+ *
+ * If successful, 0 is returned.
+ */
+int write_cgroup_file_parent(const char *relative_path, const char *file,
+			     const char *buf)
+{
+	char cgroup_path[PATH_MAX - 24];
+
+	format_parent_cgroup_path(cgroup_path, relative_path);
+	return __write_cgroup_file(cgroup_path, file, buf);
+}
+
+/**
  * setup_cgroup_environment() - Setup the cgroup environment
  *
  * After calling this function, cleanup_cgroup_environment should be called
@@ -110,6 +203,11 @@ int setup_cgroup_environment(void)
 
 	format_cgroup_path(cgroup_workdir, "");
 
+	if (mkdir(CGROUP_MOUNT_PATH, 0777) && errno != EEXIST) {
+		log_err("mkdir mount");
+		return 1;
+	}
+
 	if (unshare(CLONE_NEWNS)) {
 		log_err("unshare");
 		return 1;
@@ -124,16 +222,19 @@ int setup_cgroup_environment(void)
 		log_err("mount cgroup2");
 		return 1;
 	}
+	cgroup_workdir_mounted = true;
 
 	/* Cleanup existing failed runs, now that the environment is setup */
-	cleanup_cgroup_environment();
+	__cleanup_cgroup_environment();
 
 	if (mkdir(cgroup_workdir, 0777) && errno != EEXIST) {
 		log_err("mkdir cgroup work dir");
 		return 1;
 	}
 
-	if (enable_all_controllers(cgroup_workdir))
+	/* Enable all available controllers to increase test coverage */
+	if (__enable_controllers(CGROUP_MOUNT_PATH, NULL) ||
+	    __enable_controllers(cgroup_workdir, NULL))
 		return 1;
 
 	return 0;
@@ -173,7 +274,7 @@ static int join_cgroup_from_top(const char *cgroup_path)
 
 /**
  * join_cgroup() - Join a cgroup
- * @path: The cgroup path, relative to the workdir, to join
+ * @relative_path: The cgroup path, relative to the workdir, to join
  *
  * This function expects a cgroup to already be created, relative to the cgroup
  * work dir, and it joins it. For example, passing "/my-cgroup" as the path
@@ -182,19 +283,82 @@ static int join_cgroup_from_top(const char *cgroup_path)
  *
  * On success, it returns 0, otherwise on failure it returns 1.
  */
-int join_cgroup(const char *path)
+int join_cgroup(const char *relative_path)
 {
 	char cgroup_path[PATH_MAX + 1];
 
-	format_cgroup_path(cgroup_path, path);
+	format_cgroup_path(cgroup_path, relative_path);
 	return join_cgroup_from_top(cgroup_path);
 }
 
 /**
+ * join_root_cgroup() - Join the root cgroup
+ *
+ * This function joins the root cgroup.
+ *
+ * On success, it returns 0, otherwise on failure it returns 1.
+ */
+int join_root_cgroup(void)
+{
+	return join_cgroup_from_top(CGROUP_MOUNT_PATH);
+}
+
+/**
+ * join_parent_cgroup() - Join a cgroup in the parent process workdir
+ * @relative_path: The cgroup path, relative to parent process workdir, to join
+ *
+ * See join_cgroup().
+ *
+ * On success, it returns 0, otherwise on failure it returns 1.
+ */
+int join_parent_cgroup(const char *relative_path)
+{
+	char cgroup_path[PATH_MAX + 1];
+
+	format_parent_cgroup_path(cgroup_path, relative_path);
+	return join_cgroup_from_top(cgroup_path);
+}
+
+/**
+ * set_cgroup_xattr() - Set xattr on a cgroup dir
+ * @relative_path: The cgroup path, relative to the workdir, to set xattr
+ * @name: xattr name
+ * @value: xattr value
+ *
+ * This function set xattr on cgroup dir.
+ *
+ * On success, it returns 0, otherwise on failure it returns -1.
+ */
+int set_cgroup_xattr(const char *relative_path,
+		     const char *name,
+		     const char *value)
+{
+	char cgroup_path[PATH_MAX + 1];
+
+	format_cgroup_path(cgroup_path, relative_path);
+	return setxattr(cgroup_path, name, value, strlen(value) + 1, 0);
+}
+
+/**
+ * __cleanup_cgroup_environment() - Delete temporary cgroups
+ *
+ * This is a helper for cleanup_cgroup_environment() that is responsible for
+ * deletion of all temporary cgroups that have been created during the test.
+ */
+static void __cleanup_cgroup_environment(void)
+{
+	char cgroup_workdir[PATH_MAX + 1];
+
+	format_cgroup_path(cgroup_workdir, "");
+	join_cgroup_from_top(CGROUP_MOUNT_PATH);
+	nftw(cgroup_workdir, nftwfunc, WALK_FD_LIMIT, FTW_DEPTH | FTW_MOUNT);
+}
+
+/**
  * cleanup_cgroup_environment() - Cleanup Cgroup Testing Environment
  *
  * This is an idempotent function to delete all temporary cgroups that
- * have been created during the test, including the cgroup testing work
+ * have been created during the test and unmount the cgroup testing work
  * directory.
  *
  * At call time, it moves the calling process to the root cgroup, and then
@@ -205,16 +369,72 @@ int join_cgroup(const char *path)
  */
 void cleanup_cgroup_environment(void)
 {
-	char cgroup_workdir[PATH_MAX + 1];
+	__cleanup_cgroup_environment();
+	if (cgroup_workdir_mounted && umount(CGROUP_MOUNT_PATH))
+		log_err("umount cgroup2");
+	cgroup_workdir_mounted = false;
+}
 
-	format_cgroup_path(cgroup_workdir, "");
-	join_cgroup_from_top(CGROUP_MOUNT_PATH);
-	nftw(cgroup_workdir, nftwfunc, WALK_FD_LIMIT, FTW_DEPTH | FTW_MOUNT);
+/**
+ * get_root_cgroup() - Get the FD of the root cgroup
+ *
+ * On success, it returns the file descriptor. On failure, it returns -1.
+ * If there is a failure, it prints the error to stderr.
+ */
+int get_root_cgroup(void)
+{
+	int fd;
+
+	fd = open(CGROUP_MOUNT_PATH, O_RDONLY);
+	if (fd < 0) {
+		log_err("Opening root cgroup");
+		return -1;
+	}
+	return fd;
+}
+
+/*
+ * remove_cgroup() - Remove a cgroup
+ * @relative_path: The cgroup path, relative to the workdir, to remove
+ *
+ * This function expects a cgroup to already be created, relative to the cgroup
+ * work dir. It also expects the cgroup doesn't have any children or live
+ * processes and it removes the cgroup.
+ *
+ * On failure, it will print an error to stderr.
+ */
+void remove_cgroup(const char *relative_path)
+{
+	char cgroup_path[PATH_MAX + 1];
+
+	format_cgroup_path(cgroup_path, relative_path);
+	if (rmdir(cgroup_path))
+		log_err("rmdiring cgroup %s .. %s", relative_path, cgroup_path);
+}
+
+/*
+ * remove_cgroup_pid() - Remove a cgroup setup by process identified by PID
+ * @relative_path: The cgroup path, relative to the workdir, to remove
+ * @pid: PID to be used to find cgroup_path
+ *
+ * This function expects a cgroup to already be created, relative to the cgroup
+ * work dir. It also expects the cgroup doesn't have any children or live
+ * processes and it removes the cgroup.
+ *
+ * On failure, it will print an error to stderr.
+ */
+void remove_cgroup_pid(const char *relative_path, int pid)
+{
+	char cgroup_path[PATH_MAX + 1];
+
+	format_cgroup_path_pid(cgroup_path, relative_path, pid);
+	if (rmdir(cgroup_path))
+		log_err("rmdiring cgroup %s .. %s", relative_path, cgroup_path);
 }
 
 /**
  * create_and_get_cgroup() - Create a cgroup, relative to workdir, and get the FD
- * @path: The cgroup path, relative to the workdir, to join
+ * @relative_path: The cgroup path, relative to the workdir, to join
  *
  * This function creates a cgroup under the top level workdir and returns the
  * file descriptor. It is idempotent.
@@ -222,14 +442,14 @@ void cleanup_cgroup_environment(void)
  * On success, it returns the file descriptor. On failure it returns -1.
  * If there is a failure, it prints the error to stderr.
  */
-int create_and_get_cgroup(const char *path)
+int create_and_get_cgroup(const char *relative_path)
 {
 	char cgroup_path[PATH_MAX + 1];
 	int fd;
 
-	format_cgroup_path(cgroup_path, path);
+	format_cgroup_path(cgroup_path, relative_path);
 	if (mkdir(cgroup_path, 0777) && errno != EEXIST) {
-		log_err("mkdiring cgroup %s .. %s", path, cgroup_path);
+		log_err("mkdiring cgroup %s .. %s", relative_path, cgroup_path);
 		return -1;
 	}
 
@@ -243,26 +463,23 @@ int create_and_get_cgroup(const char *path)
 }
 
 /**
- * get_cgroup_id() - Get cgroup id for a particular cgroup path
- * @path: The cgroup path, relative to the workdir, to join
+ * get_cgroup_id_from_path - Get cgroup id for a particular cgroup path
+ * @cgroup_workdir: The absolute cgroup path
  *
  * On success, it returns the cgroup id. On failure it returns 0,
  * which is an invalid cgroup id.
  * If there is a failure, it prints the error to stderr.
  */
-unsigned long long get_cgroup_id(const char *path)
+static unsigned long long get_cgroup_id_from_path(const char *cgroup_workdir)
 {
 	int dirfd, err, flags, mount_id, fhsize;
 	union {
 		unsigned long long cgid;
 		unsigned char raw_bytes[8];
 	} id;
-	char cgroup_workdir[PATH_MAX + 1];
 	struct file_handle *fhp, *fhp2;
 	unsigned long long ret = 0;
 
-	format_cgroup_path(cgroup_workdir, path);
-
 	dirfd = AT_FDCWD;
 	flags = 0;
 	fhsize = sizeof(*fhp);
@@ -298,6 +515,14 @@ free_mem:
 	return ret;
 }
 
+unsigned long long get_cgroup_id(const char *relative_path)
+{
+	char cgroup_workdir[PATH_MAX + 1];
+
+	format_cgroup_path(cgroup_workdir, relative_path);
+	return get_cgroup_id_from_path(cgroup_workdir);
+}
+
 int cgroup_setup_and_join(const char *path) {
 	int cg_fd;
 
@@ -324,6 +549,9 @@ int cgroup_setup_and_join(const char *path) {
 /**
  * setup_classid_environment() - Setup the cgroupv1 net_cls environment
  *
+ * This function should only be called in a custom mount namespace, e.g.
+ * created by running setup_cgroup_environment.
+ *
  * After calling this function, cleanup_classid_environment should be called
  * once testing is complete.
  *
@@ -347,10 +575,20 @@ int setup_classid_environment(void)
 		return 1;
 	}
 
-	if (mount("net_cls", NETCLS_MOUNT_PATH, "cgroup", 0, "net_cls") &&
-	    errno != EBUSY) {
-		log_err("mount cgroup net_cls");
-		return 1;
+	if (mount("net_cls", NETCLS_MOUNT_PATH, "cgroup", 0, "net_cls")) {
+		if (errno != EBUSY) {
+			log_err("mount cgroup net_cls");
+			return 1;
+		}
+
+		if (rmdir(NETCLS_MOUNT_PATH)) {
+			log_err("rmdir cgroup net_cls");
+			return 1;
+		}
+		if (umount(CGROUP_MOUNT_DFLT)) {
+			log_err("umount cgroup base");
+			return 1;
+		}
 	}
 
 	cleanup_classid_environment();
@@ -365,15 +603,16 @@ int setup_classid_environment(void)
 
 /**
  * set_classid() - Set a cgroupv1 net_cls classid
- * @id: the numeric classid
  *
- * Writes the passed classid into the cgroup work dir's net_cls.classid
+ * Writes the classid into the cgroup work dir's net_cls.classid
  * file in order to later on trigger socket tagging.
  *
+ * We leverage the current pid as the classid, ensuring unique identification.
+ *
  * On success, it returns 0, otherwise on failure it returns 1. If there
  * is a failure, it prints the error to stderr.
  */
-int set_classid(unsigned int id)
+int set_classid(void)
 {
 	char cgroup_workdir[PATH_MAX - 42];
 	char cgroup_classid_path[PATH_MAX + 1];
@@ -389,7 +628,7 @@ int set_classid(unsigned int id)
 		return 1;
 	}
 
-	if (dprintf(fd, "%u\n", id) < 0) {
+	if (dprintf(fd, "%u\n", getpid()) < 0) {
 		log_err("Setting cgroup classid");
 		rc = 1;
 	}
@@ -431,3 +670,82 @@ void cleanup_classid_environment(void)
 	join_cgroup_from_top(NETCLS_MOUNT_PATH);
 	nftw(cgroup_workdir, nftwfunc, WALK_FD_LIMIT, FTW_DEPTH | FTW_MOUNT);
 }
+
+/**
+ * get_classid_cgroup_id - Get the cgroup id of a net_cls cgroup
+ */
+unsigned long long get_classid_cgroup_id(void)
+{
+	char cgroup_workdir[PATH_MAX + 1];
+
+	format_classid_path(cgroup_workdir);
+	return get_cgroup_id_from_path(cgroup_workdir);
+}
+
+/**
+ * get_cgroup1_hierarchy_id - Retrieves the ID of a cgroup1 hierarchy from the cgroup1 subsys name.
+ * @subsys_name: The cgroup1 subsys name, which can be retrieved from /proc/self/cgroup. It can be
+ * a named cgroup like "name=systemd", a controller name like "net_cls", or multi-controllers like
+ * "net_cls,net_prio".
+ */
+int get_cgroup1_hierarchy_id(const char *subsys_name)
+{
+	char *c, *c2, *c3, *c4;
+	bool found = false;
+	char line[1024];
+	FILE *file;
+	int i, id;
+
+	if (!subsys_name)
+		return -1;
+
+	file = fopen("/proc/self/cgroup", "r");
+	if (!file) {
+		log_err("fopen /proc/self/cgroup");
+		return -1;
+	}
+
+	while (fgets(line, 1024, file)) {
+		i = 0;
+		for (c = strtok_r(line, ":", &c2); c && i < 2; c = strtok_r(NULL, ":", &c2)) {
+			if (i == 0) {
+				id = strtol(c, NULL, 10);
+			} else if (i == 1) {
+				if (!strcmp(c, subsys_name)) {
+					found = true;
+					break;
+				}
+
+				/* Multiple subsystems may share one single mount point */
+				for (c3 = strtok_r(c, ",", &c4); c3;
+				     c3 = strtok_r(NULL, ",", &c4)) {
+					if (!strcmp(c, subsys_name)) {
+						found = true;
+						break;
+					}
+				}
+			}
+			i++;
+		}
+		if (found)
+			break;
+	}
+	fclose(file);
+	return found ? id : -1;
+}
+
+/**
+ * open_classid() - Open a cgroupv1 net_cls classid
+ *
+ * This function expects the cgroup work dir to be already created, as we
+ * open it here.
+ *
+ * On success, it returns the file descriptor. On failure it returns -1.
+ */
+int open_classid(void)
+{
+	char cgroup_workdir[PATH_MAX + 1];
+
+	format_classid_path(cgroup_workdir);
+	return open(cgroup_workdir, O_RDONLY);
+}