Merge branch 'for-3.9' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup changes from Tejun Heo:
 "Nothing too drastic.

   - Removal of synchronize_rcu() from userland visible paths.

   - Various fixes and cleanups from Li.

   - cgroup_rightmost_descendant() added which will be used by cpuset
     changes (it will be a separate pull request)."

* 'for-3.9' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cgroup: fail if monitored file and event_control are in different cgroup
  cgroup: fix cgroup_rmdir() vs close(eventfd) race
  cpuset: fix cpuset_print_task_mems_allowed() vs rename() race
  cgroup: fix exit() vs rmdir() race
  cgroup: remove bogus comments in cgroup_diput()
  cgroup: remove synchronize_rcu() from cgroup_diput()
  cgroup: remove duplicate RCU free on struct cgroup
  sched: remove redundant NULL cgroup check in task_group_path()
  sched: split out css_online/css_offline from tg creation/destruction
  cgroup: initialize cgrp->dentry before css_alloc()
  cgroup: remove a NULL check in cgroup_exit()
  cgroup: fix bogus kernel warnings when cgroup_create() failed
  cgroup: remove synchronize_rcu() from rebind_subsystems()
  cgroup: remove synchronize_rcu() from cgroup_attach_{task|proc}()
  cgroup: use new hashtable implementation
  cgroups: fix cgroup_event_listener error handling
  cgroups: move cgroup_event_listener.c to tools/cgroup
  cgroup: implement cgroup_rightmost_descendant()
  cgroup: remove unused dummy cgroup_fork_callbacks()

Documentation/cgroups/00-INDEX

@@ -4,8 +4,6 @@ blkio-controller.txt
 	- Description for Block IO Controller, implementation and usage details.
 cgroups.txt
 	- Control Groups definition, implementation details, examples and API.
-cgroup_event_listener.c
-	- A user program for cgroup listener.
 cpuacct.txt
 	- CPU Accounting Controller; account CPU usage for groups of tasks.
 cpusets.txt

Documentation/cgroups/memcg_test.txt

@@ -399,8 +399,7 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
 
  9.10 Memory thresholds
 	Memory controller implements memory thresholds using cgroups notification
-	API. You can use Documentation/cgroups/cgroup_event_listener.c to test
-	it.
+	API. You can use tools/cgroup/cgroup_event_listener.c to test it.
 
 	(Shell-A) Create cgroup and run event listener
 	# mkdir /cgroup/A

include/linux/cgroup.h

@@ -203,6 +203,7 @@ struct cgroup {
 
 	/* For RCU-protected deletion */
 	struct rcu_head rcu_head;
+	struct work_struct free_work;
 
 	/* List of events which userspace want to receive */
 	struct list_head event_list;
@@ -558,6 +559,7 @@ static inline struct cgroup* task_cgroup(struct task_struct *task,
 
 struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos,
 					  struct cgroup *cgroup);
+struct cgroup *cgroup_rightmost_descendant(struct cgroup *pos);
 
 /**
  * cgroup_for_each_descendant_pre - pre-order walk of a cgroup's descendants
@@ -706,7 +708,6 @@ struct cgroup_subsys_state *cgroup_css_from_dir(struct file *f, int id);
 static inline int cgroup_init_early(void) { return 0; }
 static inline int cgroup_init(void) { return 0; }
 static inline void cgroup_fork(struct task_struct *p) {}
-static inline void cgroup_fork_callbacks(struct task_struct *p) {}
 static inline void cgroup_post_fork(struct task_struct *p) {}
 static inline void cgroup_exit(struct task_struct *p, int callbacks) {}
 

include/linux/sched.h

@@ -2659,7 +2659,10 @@ extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
 extern struct task_group root_task_group;
 
 extern struct task_group *sched_create_group(struct task_group *parent);
+extern void sched_online_group(struct task_group *tg,
+			       struct task_group *parent);
 extern void sched_destroy_group(struct task_group *tg);
+extern void sched_offline_group(struct task_group *tg);
 extern void sched_move_task(struct task_struct *tsk);
 #ifdef CONFIG_FAIR_GROUP_SCHED
 extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);

kernel/cpuset.c

@@ -2511,8 +2511,16 @@ void cpuset_print_task_mems_allowed(struct task_struct *tsk)
 
 	dentry = task_cs(tsk)->css.cgroup->dentry;
 	spin_lock(&cpuset_buffer_lock);
-	snprintf(cpuset_name, CPUSET_NAME_LEN,
-		 dentry ? (const char *)dentry->d_name.name : "/");
+
+	if (!dentry) {
+		strcpy(cpuset_name, "/");
+	} else {
+		spin_lock(&dentry->d_lock);
+		strlcpy(cpuset_name, (const char *)dentry->d_name.name,
+			CPUSET_NAME_LEN);
+		spin_unlock(&dentry->d_lock);
+	}
+
 	nodelist_scnprintf(cpuset_nodelist, CPUSET_NODELIST_LEN,
 			   tsk->mems_allowed);
 	printk(KERN_INFO "%s cpuset=%s mems_allowed=%s\n",

kernel/sched/auto_group.c

@@ -35,6 +35,7 @@ static inline void autogroup_destroy(struct kref *kref)
 	ag->tg->rt_se = NULL;
 	ag->tg->rt_rq = NULL;
 #endif
+	sched_offline_group(ag->tg);
 	sched_destroy_group(ag->tg);
 }
 
@@ -76,6 +77,8 @@ static inline struct autogroup *autogroup_create(void)
 	if (IS_ERR(tg))
 		goto out_free;
 
+	sched_online_group(tg, &root_task_group);
+
 	kref_init(&ag->kref);
 	init_rwsem(&ag->lock);
 	ag->id = atomic_inc_return(&autogroup_seq_nr);

kernel/sched/core.c

@@ -7161,7 +7161,6 @@ static void free_sched_group(struct task_group *tg)
 struct task_group *sched_create_group(struct task_group *parent)
 {
 	struct task_group *tg;
-	unsigned long flags;
 
 	tg = kzalloc(sizeof(*tg), GFP_KERNEL);
 	if (!tg)
@@ -7173,6 +7172,17 @@ struct task_group *sched_create_group(struct task_group *parent)
 	if (!alloc_rt_sched_group(tg, parent))
 		goto err;
 
+	return tg;
+
+err:
+	free_sched_group(tg);
+	return ERR_PTR(-ENOMEM);
+}
+
+void sched_online_group(struct task_group *tg, struct task_group *parent)
+{
+	unsigned long flags;
+
 	spin_lock_irqsave(&task_group_lock, flags);
 	list_add_rcu(&tg->list, &task_groups);
 
@@ -7182,12 +7192,6 @@ struct task_group *sched_create_group(struct task_group *parent)
 	INIT_LIST_HEAD(&tg->children);
 	list_add_rcu(&tg->siblings, &parent->children);
 	spin_unlock_irqrestore(&task_group_lock, flags);
-
-	return tg;
-
-err:
-	free_sched_group(tg);
-	return ERR_PTR(-ENOMEM);
 }
 
 /* rcu callback to free various structures associated with a task group */
@@ -7199,6 +7203,12 @@ static void free_sched_group_rcu(struct rcu_head *rhp)
 
 /* Destroy runqueue etc associated with a task group */
 void sched_destroy_group(struct task_group *tg)
+{
+	/* wait for possible concurrent references to cfs_rqs complete */
+	call_rcu(&tg->rcu, free_sched_group_rcu);
+}
+
+void sched_offline_group(struct task_group *tg)
 {
 	unsigned long flags;
 	int i;
@@ -7211,9 +7221,6 @@ void sched_destroy_group(struct task_group *tg)
 	list_del_rcu(&tg->list);
 	list_del_rcu(&tg->siblings);
 	spin_unlock_irqrestore(&task_group_lock, flags);
-
-	/* wait for possible concurrent references to cfs_rqs complete */
-	call_rcu(&tg->rcu, free_sched_group_rcu);
 }
 
 /* change task's runqueue when it moves between groups.
@@ -7584,6 +7591,19 @@ static struct cgroup_subsys_state *cpu_cgroup_css_alloc(struct cgroup *cgrp)
 	return &tg->css;
 }
 
+static int cpu_cgroup_css_online(struct cgroup *cgrp)
+{
+	struct task_group *tg = cgroup_tg(cgrp);
+	struct task_group *parent;
+
+	if (!cgrp->parent)
+		return 0;
+
+	parent = cgroup_tg(cgrp->parent);
+	sched_online_group(tg, parent);
+	return 0;
+}
+
 static void cpu_cgroup_css_free(struct cgroup *cgrp)
 {
 	struct task_group *tg = cgroup_tg(cgrp);
@@ -7591,6 +7611,13 @@ static void cpu_cgroup_css_free(struct cgroup *cgrp)
 	sched_destroy_group(tg);
 }
 
+static void cpu_cgroup_css_offline(struct cgroup *cgrp)
+{
+	struct task_group *tg = cgroup_tg(cgrp);
+
+	sched_offline_group(tg);
+}
+
 static int cpu_cgroup_can_attach(struct cgroup *cgrp,
 				 struct cgroup_taskset *tset)
 {
@@ -7946,6 +7973,8 @@ struct cgroup_subsys cpu_cgroup_subsys = {
 	.name		= "cpu",
 	.css_alloc	= cpu_cgroup_css_alloc,
 	.css_free	= cpu_cgroup_css_free,
+	.css_online	= cpu_cgroup_css_online,
+	.css_offline	= cpu_cgroup_css_offline,
 	.can_attach	= cpu_cgroup_can_attach,
 	.attach		= cpu_cgroup_attach,
 	.exit		= cpu_cgroup_exit,

kernel/sched/debug.c

@@ -110,13 +110,6 @@ static char *task_group_path(struct task_group *tg)
 	if (autogroup_path(tg, group_path, PATH_MAX))
 		return group_path;
 
-	/*
-	 * May be NULL if the underlying cgroup isn't fully-created yet
-	 */
-	if (!tg->css.cgroup) {
-		group_path[0] = '\0';
-		return group_path;
-	}
 	cgroup_path(tg->css.cgroup, group_path, PATH_MAX);
 	return group_path;
 }

tools/Makefile

@@ -3,6 +3,7 @@ include scripts/Makefile.include
 help:
 	@echo 'Possible targets:'
 	@echo ''
+	@echo '  cgroup     - cgroup tools'
 	@echo '  cpupower   - a tool for all things x86 CPU power'
 	@echo '  firewire   - the userspace part of nosy, an IEEE-1394 traffic sniffer'
 	@echo '  lguest     - a minimal 32-bit x86 hypervisor'
@@ -33,7 +34,7 @@ help:
 cpupower: FORCE
 	$(call descend,power/$@)
 
-firewire lguest perf usb virtio vm: FORCE
+cgroup firewire lguest perf usb virtio vm: FORCE
 	$(call descend,$@)
 
 selftests: FORCE
@@ -45,7 +46,7 @@ turbostat x86_energy_perf_policy: FORCE
 cpupower_install:
 	$(call descend,power/$(@:_install=),install)
 
-firewire_install lguest_install perf_install usb_install virtio_install vm_install:
+cgroup_install firewire_install lguest_install perf_install usb_install virtio_install vm_install:
 	$(call descend,$(@:_install=),install)
 
 selftests_install:
@@ -54,14 +55,14 @@ selftests_install:
 turbostat_install x86_energy_perf_policy_install:
 	$(call descend,power/x86/$(@:_install=),install)
 
-install: cpupower_install firewire_install lguest_install perf_install \
-		selftests_install turbostat_install usb_install virtio_install \
-		vm_install x86_energy_perf_policy_install
+install: cgroup_install cpupower_install firewire_install lguest_install \
+		perf_install selftests_install turbostat_install usb_install \
+		virtio_install vm_install x86_energy_perf_policy_install
 
 cpupower_clean:
 	$(call descend,power/cpupower,clean)
 
-firewire_clean lguest_clean perf_clean usb_clean virtio_clean vm_clean:
+cgroup_clean firewire_clean lguest_clean perf_clean usb_clean virtio_clean vm_clean:
 	$(call descend,$(@:_clean=),clean)
 
 selftests_clean:
@@ -70,8 +71,8 @@ selftests_clean:
 turbostat_clean x86_energy_perf_policy_clean:
 	$(call descend,power/x86/$(@:_clean=),clean)
 
-clean: cpupower_clean firewire_clean lguest_clean perf_clean selftests_clean \
-		turbostat_clean usb_clean virtio_clean vm_clean \
-		x86_energy_perf_policy_clean
+clean: cgroup_clean cpupower_clean firewire_clean lguest_clean perf_clean \
+		selftests_clean turbostat_clean usb_clean virtio_clean \
+		vm_clean x86_energy_perf_policy_clean
 
 .PHONY: FORCE

tools/cgroup/.gitignore

+cgroup_event_listener

tools/cgroup/Makefile

+# Makefile for cgroup tools
+
+CC = $(CROSS_COMPILE)gcc
+CFLAGS = -Wall -Wextra
+
+all: cgroup_event_listener
+%: %.c
+	$(CC) $(CFLAGS) -o $@ $^
+
+clean:
+	$(RM) cgroup_event_listener

Documentation/cgroups/cgroup_event_listener.c → tools/cgroup/cgroup_event_listener.c

@@ -5,6 +5,7 @@
  */
 
 #include <assert.h>
+#include <err.h>
 #include <errno.h>
 #include <fcntl.h>
 #include <libgen.h>
@@ -15,7 +16,7 @@
 
 #include <sys/eventfd.h>
 
-#define USAGE_STR "Usage: cgroup_event_listener <path-to-control-file> <args>\n"
+#define USAGE_STR "Usage: cgroup_event_listener <path-to-control-file> <args>"
 
 int main(int argc, char **argv)
 {
@@ -26,49 +27,33 @@ int main(int argc, char **argv)
 	char line[LINE_MAX];
 	int ret;
 
-	if (argc != 3) {
-		fputs(USAGE_STR, stderr);
-		return 1;
-	}
+	if (argc != 3)
+		errx(1, "%s", USAGE_STR);
 
 	cfd = open(argv[1], O_RDONLY);
-	if (cfd == -1) {
-		fprintf(stderr, "Cannot open %s: %s\n", argv[1],
-				strerror(errno));
-		goto out;
-	}
+	if (cfd == -1)
+		err(1, "Cannot open %s", argv[1]);
 
 	ret = snprintf(event_control_path, PATH_MAX, "%s/cgroup.event_control",
 			dirname(argv[1]));
-	if (ret >= PATH_MAX) {
-		fputs("Path to cgroup.event_control is too long\n", stderr);
-		goto out;
-	}
+	if (ret >= PATH_MAX)
+		errx(1, "Path to cgroup.event_control is too long");
 
 	event_control = open(event_control_path, O_WRONLY);
-	if (event_control == -1) {
-		fprintf(stderr, "Cannot open %s: %s\n", event_control_path,
-				strerror(errno));
-		goto out;
-	}
+	if (event_control == -1)
+		err(1, "Cannot open %s", event_control_path);
 
 	efd = eventfd(0, 0);
-	if (efd == -1) {
-		perror("eventfd() failed");
-		goto out;
-	}
+	if (efd == -1)
+		err(1, "eventfd() failed");
 
 	ret = snprintf(line, LINE_MAX, "%d %d %s", efd, cfd, argv[2]);
-	if (ret >= LINE_MAX) {
-		fputs("Arguments string is too long\n", stderr);
-		goto out;
-	}
+	if (ret >= LINE_MAX)
+		errx(1, "Arguments string is too long");
 
 	ret = write(event_control, line, strlen(line) + 1);
-	if (ret == -1) {
-		perror("Cannot write to cgroup.event_control");
-		goto out;
-	}
+	if (ret == -1)
+		err(1, "Cannot write to cgroup.event_control");
 
 	while (1) {
 		uint64_t result;
@@ -77,34 +62,21 @@ int main(int argc, char **argv)
 		if (ret == -1) {
 			if (errno == EINTR)
 				continue;
-			perror("Cannot read from eventfd");
-			break;
+			err(1, "Cannot read from eventfd");
 		}
 		assert(ret == sizeof(result));
 
 		ret = access(event_control_path, W_OK);
 		if ((ret == -1) && (errno == ENOENT)) {
 			puts("The cgroup seems to have removed.");
-				ret = 0;
 			break;
 		}
 
-		if (ret == -1) {
-			perror("cgroup.event_control "
-					"is not accessible any more");
-			break;
-		}
+		if (ret == -1)
+			err(1, "cgroup.event_control is not accessible any more");
 
 		printf("%s %s: crossed\n", argv[1], argv[2]);
 	}
 
-out:
-	if (efd >= 0)
-		close(efd);
-	if (event_control >= 0)
-		close(event_control);
-	if (cfd >= 0)
-		close(cfd);
-
-	return (ret != 0);
+	return 0;
 }