From mboxrd@z Thu Jan 1 00:00:00 1970 From: Frederic Weisbecker Subject: [PATCH 7/8] cgroups: allow subsystems to cancel a fork Date: Fri, 13 Jan 2012 19:13:58 +0100 Message-ID: <1326478441-3048-15-git-send-email-fweisbec@gmail.com> References: <1326478441-3048-1-git-send-email-fweisbec@gmail.com> Return-path: DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=from:to:cc:subject:date:message-id:x-mailer:in-reply-to:references; bh=PFE+eijWbl1LWvNNr2in/UI2YjxNJPoa0rBXsG8+Z1E=; b=Y3dLai9FWoIRanrhUobycF55sT+6VxSC1m81H2LYCqCOt+8TH/Uq07Y+rdzzT4JDvS 41OTT0D6eGuLCN7tsYDpFgOhVyqolCK2tJqQcfr2BXcRaR1USsyyAAhr4uHq/T2HN/9B V3i3hSTt+EN6LhOMXJku3piwIqpvoaoBEkX7g= In-Reply-To: <1326478441-3048-1-git-send-email-fweisbec-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org> Sender: cgroups-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org List-ID: MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: LKML Cc: Frederic Weisbecker , Glauber Costa , Cgroups , "Kirill A. Shutemov" , Daniel J Walsh , "Daniel P. Berrange" , KAMEZAWA Hiroyuki , Max Kellermann , Mandeep Singh Baines , Paul Menage , Li Zefan , Johannes Weiner , Aditya Kali , Oleg Nesterov , Kay Sievers , Tim Hockin , Tejun Heo , Andrew Morton 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 Signed-off-by: Frederic Weisbecker Cc: Paul Menage Cc: Li Zefan Cc: Johannes Weiner Cc: Aditya Kali Cc: Oleg Nesterov Cc: Kay Sievers Cc: Tim Hockin Cc: Tejun Heo Acked-by: Kirill A. Shutemov Signed-off-by: Andrew Morton --- include/linux/cgroup.h | 20 ++++++++++++++------ kernel/cgroup.c | 23 +++++++++++++++++++---- kernel/cgroup_freezer.c | 6 ++++-- kernel/exit.c | 2 +- kernel/fork.c | 7 +++++-- 5 files changed, 43 insertions(+), 15 deletions(-) diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 7ad5e40..095e66d 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -17,10 +17,11 @@ #include #include +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); @@ -494,7 +497,7 @@ struct cgroup_subsys { struct cgroup_taskset *tset); void (*attach)(struct cgroup_subsys *ss, struct cgroup *cgrp, struct cgroup_taskset *tset); - 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, @@ -651,9 +654,14 @@ 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 39c7cae..109530a 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -4568,8 +4568,11 @@ 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; /* @@ -4579,10 +4582,17 @@ 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; } /** @@ -4649,7 +4659,8 @@ 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; @@ -4678,6 +4689,10 @@ 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 0e74805..6cdce8f 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -178,7 +178,7 @@ static int freezer_can_attach(struct cgroup_subsys *ss, return 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; @@ -198,7 +198,7 @@ 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); @@ -207,6 +207,8 @@ 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 95a4141..b9728d9 100644 --- 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 d4ac9e3..097c597 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1049,6 +1049,7 @@ 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); @@ -1306,8 +1307,10 @@ 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); @@ -1408,7 +1411,7 @@ bad_fork_cleanup_cgroup: #endif if (clone_flags & CLONE_THREAD) threadgroup_change_end(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: -- 1.7.5.4