cgroups: allow subsystems to cancel a fork

Let the subsystem's fork callback return an error value so that they can
cancel a fork.  This is going to be used by the task counter subsystem to
implement the limit.

Suggested-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Paul Menage <paul@paulmenage.org>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Aditya Kali <adityakali@google.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Kay Sievers <kay.sievers@vrfy.org>
Cc: Tim Hockin <thockin@hockin.org>
Cc: Tejun Heo <htejun@gmail.com>
Acked-by: Kirill A. Shutemov <kirill@shutemov.name>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 3c54299a73c3483f139ac6f066f4b36f2644d48d..ddc13eb76b09eafe813388d35a28dd1bd14157f3 100644 (file)
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -17,10 +17,11 @@
 #include <linux/rwsem.h>
 #include <linux/idr.h>
 
+struct cgroup_subsys;
+
 #ifdef CONFIG_CGROUPS
 
 struct cgroupfs_root;
-struct cgroup_subsys;
 struct inode;
 struct cgroup;
 struct css_id;
@@ -32,9 +33,11 @@ extern int cgroup_lock_is_held(void);
 extern bool cgroup_lock_live_group(struct cgroup *cgrp);
 extern void cgroup_unlock(void);
 extern void cgroup_fork(struct task_struct *p);
-extern void cgroup_fork_callbacks(struct task_struct *p);
+extern int cgroup_fork_callbacks(struct task_struct *p,
+                                struct cgroup_subsys **failed_ss);
 extern void cgroup_post_fork(struct task_struct *p);
-extern void cgroup_exit(struct task_struct *p, int run_callbacks);
+extern void cgroup_exit(struct task_struct *p, int run_callbacks,
+                       struct cgroup_subsys *failed_ss);
 extern int cgroupstats_build(struct cgroupstats *stats,
                                struct dentry *dentry);
 extern int cgroup_load_subsys(struct cgroup_subsys *ss);
@@ -479,7 +482,7 @@ struct cgroup_subsys {
                            struct task_struct *tsk);
        void (*attach)(struct cgroup_subsys *ss, struct cgroup *cgrp,
                       struct cgroup *old_cgrp, struct task_struct *tsk);
-       void (*fork)(struct cgroup_subsys *ss, struct task_struct *task);
+       int (*fork)(struct cgroup_subsys *ss, struct task_struct *task);
        void (*exit)(struct cgroup_subsys *ss, struct cgroup *cgrp,
                        struct cgroup *old_cgrp, struct task_struct *task);
        int (*populate)(struct cgroup_subsys *ss,
@@ -636,9 +639,14 @@ 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 int cgroup_fork_callbacks(struct task_struct *p,
+                                       struct cgroup_subsys **failed_ss)
+{
+       return 0;
+}
 static inline void cgroup_post_fork(struct task_struct *p) {}
-static inline void cgroup_exit(struct task_struct *p, int callbacks) {}
+static inline void cgroup_exit(struct task_struct *p, int callbacks,
+                              struct cgroup_subsys *failed_ss) {}
 
 static inline void cgroup_lock(void) {}
 static inline void cgroup_unlock(void) {}

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 23d2bad671498c265fb7d039dc5b25cae1120857..893fc3d5c87604d738c9a5cbee461671212d4858 100644 (file)
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4540,8 +4540,11 @@ void cgroup_fork(struct task_struct *child)
  * tasklist. No need to take any locks since no-one can
  * be operating on this task.
  */
-void cgroup_fork_callbacks(struct task_struct *child)
+int cgroup_fork_callbacks(struct task_struct *child,
+                         struct cgroup_subsys **failed_ss)
 {
+       int err;
+
        if (need_forkexit_callback) {
                int i;
                /*
@@ -4551,10 +4554,17 @@ void cgroup_fork_callbacks(struct task_struct *child)
                 */
                for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
                        struct cgroup_subsys *ss = subsys[i];
-                       if (ss->fork)
-                               ss->fork(ss, child);
+                       if (ss->fork) {
+                               err = ss->fork(ss, child);
+                               if (err) {
+                                       *failed_ss = ss;
+                                       return err;
+                               }
+                       }
                }
        }
+
+       return 0;
 }
 
 /**
@@ -4612,7 +4622,8 @@ void cgroup_post_fork(struct task_struct *child)
  *    which wards off any cgroup_attach_task() attempts, or task is a failed
  *    fork, never visible to cgroup_attach_task.
  */
-void cgroup_exit(struct task_struct *tsk, int run_callbacks)
+void cgroup_exit(struct task_struct *tsk, int run_callbacks,
+                struct cgroup_subsys *failed_ss)
 {
        struct css_set *cg;
        int i;
@@ -4641,6 +4652,10 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks)
                 */
                for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
                        struct cgroup_subsys *ss = subsys[i];
+
+                       if (ss == failed_ss)
+                               break;
+
                        if (ss->exit) {
                                struct cgroup *old_cgrp =
                                        rcu_dereference_raw(cg->subsys[i])->cgroup;

diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index 719d0db44f2f51fe10902e6cd2f82a65dee1198b..701b5868942fea324edf6690a7bd7d54c877fed3 100644 (file)
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -180,7 +180,7 @@ static int freezer_can_attach_task(struct cgroup *cgrp, struct cgroup *old_cgrp,
        return cgroup_freezing(tsk) ? -EBUSY : 0;
 }
 
-static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task)
+static int freezer_fork(struct cgroup_subsys *ss, struct task_struct *task)
 {
        struct freezer *freezer;
 
@@ -200,7 +200,7 @@ static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task)
         * following check.
         */
        if (!freezer->css.cgroup->parent)
-               return;
+               return 0;
 
        spin_lock_irq(&freezer->lock);
        BUG_ON(freezer->state == CGROUP_FROZEN);
@@ -209,6 +209,8 @@ static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task)
        if (freezer->state == CGROUP_FREEZING)
                freeze_task(task);
        spin_unlock_irq(&freezer->lock);
+
+       return 0;
 }
 
 /*

diff --git a/kernel/exit.c b/kernel/exit.c
index da299148af3c85a48524a6cea01a032dc7033c59..5b1e44035bb9fa6bc265a81ba39560489f5b3396 100644 (file)
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -990,7 +990,7 @@ NORET_TYPE void do_exit(long code)
         */
        perf_event_exit_task(tsk);
 
-       cgroup_exit(tsk, 1);
+       cgroup_exit(tsk, 1, NULL);
 
        if (group_dead)
                disassociate_ctty(1);

diff --git a/kernel/fork.c b/kernel/fork.c
index e2cdbb060eeda3e03287606420d4e391b8a828da..2a23af9f8070f78b8818079e6002dba050b4b3b7 100644 (file)
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1055,6 +1055,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
        int retval;
        struct task_struct *p;
        int cgroup_callbacks_done = 0;
+       struct cgroup_subsys *cgroup_failed_ss = NULL;
 
        if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
                return ERR_PTR(-EINVAL);
@@ -1308,8 +1309,10 @@ static struct task_struct *copy_process(unsigned long clone_flags,
        /* Now that the task is set up, run cgroup callbacks if
         * necessary. We need to run them before the task is visible
         * on the tasklist. */
-       cgroup_fork_callbacks(p);
+       retval = cgroup_fork_callbacks(p, &cgroup_failed_ss);
        cgroup_callbacks_done = 1;
+       if (retval)
+               goto bad_fork_free_pid;
 
        /* Need tasklist lock for parent etc handling! */
        write_lock_irq(&tasklist_lock);
@@ -1410,7 +1413,7 @@ bad_fork_cleanup_cgroup:
 #endif
        if (clone_flags & CLONE_THREAD)
                threadgroup_fork_read_unlock(current);
-       cgroup_exit(p, cgroup_callbacks_done);
+       cgroup_exit(p, cgroup_callbacks_done, cgroup_failed_ss);
        delayacct_tsk_free(p);
        module_put(task_thread_info(p)->exec_domain->module);
 bad_fork_cleanup_count: