diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2012-03-20 18:11:21 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2012-03-20 18:11:21 -0700 |
commit | 0d9cabdccedb79ee5f27b77ff51f29a9e7d23275 (patch) | |
tree | 8bfb64c3672d058eb90aec3c3a9c4f61cef9097c | |
parent | 701085b219016d38f105b031381b9cee6200253a (diff) | |
parent | 3ce3230a0cff484e5130153f244d4fb8a56b3a8b (diff) |
Merge branch 'for-3.4' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup
Pull cgroup changes from Tejun Heo:
"Out of the 8 commits, one fixes a long-standing locking issue around
tasklist walking and others are cleanups."
* 'for-3.4' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
cgroup: Walk task list under tasklist_lock in cgroup_enable_task_cg_list
cgroup: Remove wrong comment on cgroup_enable_task_cg_list()
cgroup: remove cgroup_subsys argument from callbacks
cgroup: remove extra calls to find_existing_css_set
cgroup: replace tasklist_lock with rcu_read_lock
cgroup: simplify double-check locking in cgroup_attach_proc
cgroup: move struct cgroup_pidlist out from the header file
cgroup: remove cgroup_attach_task_current_cg()
-rw-r--r-- | Documentation/cgroups/cgroups.txt | 26 | ||||
-rw-r--r-- | block/blk-cgroup.c | 22 | ||||
-rw-r--r-- | include/linux/cgroup.h | 70 | ||||
-rw-r--r-- | include/net/sock.h | 7 | ||||
-rw-r--r-- | include/net/tcp_memcontrol.h | 2 | ||||
-rw-r--r-- | kernel/cgroup.c | 327 | ||||
-rw-r--r-- | kernel/cgroup_freezer.c | 11 | ||||
-rw-r--r-- | kernel/cpuset.c | 16 | ||||
-rw-r--r-- | kernel/events/core.c | 13 | ||||
-rw-r--r-- | kernel/sched/core.c | 20 | ||||
-rw-r--r-- | mm/memcontrol.c | 48 | ||||
-rw-r--r-- | net/core/netprio_cgroup.c | 10 | ||||
-rw-r--r-- | net/core/sock.c | 6 | ||||
-rw-r--r-- | net/ipv4/tcp_memcontrol.c | 2 | ||||
-rw-r--r-- | net/sched/cls_cgroup.c | 10 | ||||
-rw-r--r-- | security/device_cgroup.c | 10 |
16 files changed, 228 insertions, 372 deletions
diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt index a7c96ae5557..8e74980ab38 100644 --- a/Documentation/cgroups/cgroups.txt +++ b/Documentation/cgroups/cgroups.txt @@ -558,8 +558,7 @@ Each subsystem may export the following methods. The only mandatory methods are create/destroy. Any others that are null are presumed to be successful no-ops. -struct cgroup_subsys_state *create(struct cgroup_subsys *ss, - struct cgroup *cgrp) +struct cgroup_subsys_state *create(struct cgroup *cgrp) (cgroup_mutex held by caller) Called to create a subsystem state object for a cgroup. The @@ -574,7 +573,7 @@ identified by the passed cgroup object having a NULL parent (since it's the root of the hierarchy) and may be an appropriate place for initialization code. -void destroy(struct cgroup_subsys *ss, struct cgroup *cgrp) +void destroy(struct cgroup *cgrp) (cgroup_mutex held by caller) The cgroup system is about to destroy the passed cgroup; the subsystem @@ -585,7 +584,7 @@ cgroup->parent is still valid. (Note - can also be called for a newly-created cgroup if an error occurs after this subsystem's create() method has been called for the new cgroup). -int pre_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp); +int pre_destroy(struct cgroup *cgrp); Called before checking the reference count on each subsystem. This may be useful for subsystems which have some extra references even if @@ -593,8 +592,7 @@ there are not tasks in the cgroup. If pre_destroy() returns error code, rmdir() will fail with it. From this behavior, pre_destroy() can be called multiple times against a cgroup. -int can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, - struct cgroup_taskset *tset) +int can_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) (cgroup_mutex held by caller) Called prior to moving one or more tasks into a cgroup; if the @@ -615,8 +613,7 @@ fork. If this method returns 0 (success) then this should remain valid while the caller holds cgroup_mutex and it is ensured that either attach() or cancel_attach() will be called in future. -void cancel_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, - struct cgroup_taskset *tset) +void cancel_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) (cgroup_mutex held by caller) Called when a task attach operation has failed after can_attach() has succeeded. @@ -625,23 +622,22 @@ function, so that the subsystem can implement a rollback. If not, not necessary. This will be called only about subsystems whose can_attach() operation have succeeded. The parameters are identical to can_attach(). -void attach(struct cgroup_subsys *ss, struct cgroup *cgrp, - struct cgroup_taskset *tset) +void attach(struct cgroup *cgrp, struct cgroup_taskset *tset) (cgroup_mutex held by caller) Called after the task has been attached to the cgroup, to allow any post-attachment activity that requires memory allocations or blocking. The parameters are identical to can_attach(). -void fork(struct cgroup_subsy *ss, struct task_struct *task) +void fork(struct task_struct *task) Called when a task is forked into a cgroup. -void exit(struct cgroup_subsys *ss, struct task_struct *task) +void exit(struct task_struct *task) Called during task exit. -int populate(struct cgroup_subsys *ss, struct cgroup *cgrp) +int populate(struct cgroup *cgrp) (cgroup_mutex held by caller) Called after creation of a cgroup to allow a subsystem to populate @@ -651,7 +647,7 @@ include/linux/cgroup.h for details). Note that although this method can return an error code, the error code is currently not always handled well. -void post_clone(struct cgroup_subsys *ss, struct cgroup *cgrp) +void post_clone(struct cgroup *cgrp) (cgroup_mutex held by caller) Called during cgroup_create() to do any parameter @@ -659,7 +655,7 @@ initialization which might be required before a task could attach. For example in cpusets, no task may attach before 'cpus' and 'mems' are set up. -void bind(struct cgroup_subsys *ss, struct cgroup *root) +void bind(struct cgroup *root) (cgroup_mutex and ss->hierarchy_mutex held by caller) Called when a cgroup subsystem is rebound to a different hierarchy diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 75642a352a8..ea84a23d5e6 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -28,13 +28,10 @@ static LIST_HEAD(blkio_list); struct blkio_cgroup blkio_root_cgroup = { .weight = 2*BLKIO_WEIGHT_DEFAULT }; EXPORT_SYMBOL_GPL(blkio_root_cgroup); -static struct cgroup_subsys_state *blkiocg_create(struct cgroup_subsys *, - struct cgroup *); -static int blkiocg_can_attach(struct cgroup_subsys *, struct cgroup *, - struct cgroup_taskset *); -static void blkiocg_attach(struct cgroup_subsys *, struct cgroup *, - struct cgroup_taskset *); -static void blkiocg_destroy(struct cgroup_subsys *, struct cgroup *); +static struct cgroup_subsys_state *blkiocg_create(struct cgroup *); +static int blkiocg_can_attach(struct cgroup *, struct cgroup_taskset *); +static void blkiocg_attach(struct cgroup *, struct cgroup_taskset *); +static void blkiocg_destroy(struct cgroup *); static int blkiocg_populate(struct cgroup_subsys *, struct cgroup *); /* for encoding cft->private value on file */ @@ -1548,7 +1545,7 @@ static int blkiocg_populate(struct cgroup_subsys *subsys, struct cgroup *cgroup) ARRAY_SIZE(blkio_files)); } -static void blkiocg_destroy(struct cgroup_subsys *subsys, struct cgroup *cgroup) +static void blkiocg_destroy(struct cgroup *cgroup) { struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup); unsigned long flags; @@ -1598,8 +1595,7 @@ static void blkiocg_destroy(struct cgroup_subsys *subsys, struct cgroup *cgroup) kfree(blkcg); } -static struct cgroup_subsys_state * -blkiocg_create(struct cgroup_subsys *subsys, struct cgroup *cgroup) +static struct cgroup_subsys_state *blkiocg_create(struct cgroup *cgroup) { struct blkio_cgroup *blkcg; struct cgroup *parent = cgroup->parent; @@ -1628,8 +1624,7 @@ done: * of the main cic data structures. For now we allow a task to change * its cgroup only if it's the only owner of its ioc. */ -static int blkiocg_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, - struct cgroup_taskset *tset) +static int blkiocg_can_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) { struct task_struct *task; struct io_context *ioc; @@ -1648,8 +1643,7 @@ static int blkiocg_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, return ret; } -static void blkiocg_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, - struct cgroup_taskset *tset) +static void blkiocg_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) { struct task_struct *task; struct io_context *ioc; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index e9b602151ca..501adb1b2f4 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -160,38 +160,6 @@ enum { CGRP_CLONE_CHILDREN, }; -/* which pidlist file are we talking about? */ -enum cgroup_filetype { - CGROUP_FILE_PROCS, - CGROUP_FILE_TASKS, -}; - -/* - * A pidlist is a list of pids that virtually represents the contents of one - * of the cgroup files ("procs" or "tasks"). We keep a list of such pidlists, - * a pair (one each for procs, tasks) for each pid namespace that's relevant - * to the cgroup. - */ -struct cgroup_pidlist { - /* - * used to find which pidlist is wanted. doesn't change as long as - * this particular list stays in the list. - */ - struct { enum cgroup_filetype type; struct pid_namespace *ns; } key; - /* array of xids */ - pid_t *list; - /* how many elements the above list has */ - int length; - /* how many files are using the current array */ - int use_count; - /* each of these stored in a list by its cgroup */ - struct list_head links; - /* pointer to the cgroup we belong to, for list removal purposes */ - struct cgroup *owner; - /* protects the other fields */ - struct rw_semaphore mutex; -}; - struct cgroup { unsigned long flags; /* "unsigned long" so bitops work */ @@ -484,23 +452,18 @@ int cgroup_taskset_size(struct cgroup_taskset *tset); */ struct cgroup_subsys { - struct cgroup_subsys_state *(*create)(struct cgroup_subsys *ss, - struct cgroup *cgrp); - int (*pre_destroy)(struct cgroup_subsys *ss, struct cgroup *cgrp); - void (*destroy)(struct cgroup_subsys *ss, struct cgroup *cgrp); - int (*can_attach)(struct cgroup_subsys *ss, struct cgroup *cgrp, - struct cgroup_taskset *tset); - void (*cancel_attach)(struct cgroup_subsys *ss, struct cgroup *cgrp, - 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); - void (*exit)(struct cgroup_subsys *ss, struct cgroup *cgrp, - struct cgroup *old_cgrp, struct task_struct *task); - int (*populate)(struct cgroup_subsys *ss, - struct cgroup *cgrp); - void (*post_clone)(struct cgroup_subsys *ss, struct cgroup *cgrp); - void (*bind)(struct cgroup_subsys *ss, struct cgroup *root); + struct cgroup_subsys_state *(*create)(struct cgroup *cgrp); + int (*pre_destroy)(struct cgroup *cgrp); + void (*destroy)(struct cgroup *cgrp); + int (*can_attach)(struct cgroup *cgrp, struct cgroup_taskset *tset); + void (*cancel_attach)(struct cgroup *cgrp, struct cgroup_taskset *tset); + void (*attach)(struct cgroup *cgrp, struct cgroup_taskset *tset); + void (*fork)(struct task_struct *task); + void (*exit)(struct cgroup *cgrp, struct cgroup *old_cgrp, + struct task_struct *task); + int (*populate)(struct cgroup_subsys *ss, struct cgroup *cgrp); + void (*post_clone)(struct cgroup *cgrp); + void (*bind)(struct cgroup *root); int subsys_id; int active; @@ -602,11 +565,6 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan); int cgroup_attach_task(struct cgroup *, struct task_struct *); int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); -static inline int cgroup_attach_task_current_cg(struct task_struct *tsk) -{ - return cgroup_attach_task_all(current, tsk); -} - /* * CSS ID is ID for cgroup_subsys_state structs under subsys. This only works * if cgroup_subsys.use_id == true. It can be used for looking up and scanning. @@ -669,10 +627,6 @@ static inline int cgroup_attach_task_all(struct task_struct *from, { return 0; } -static inline int cgroup_attach_task_current_cg(struct task_struct *t) -{ - return 0; -} #endif /* !CONFIG_CGROUPS */ diff --git a/include/net/sock.h b/include/net/sock.h index dcde2d9268c..7ef5c58f3f4 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -69,7 +69,7 @@ struct cgroup; struct cgroup_subsys; #ifdef CONFIG_NET int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss); -void mem_cgroup_sockets_destroy(struct cgroup *cgrp, struct cgroup_subsys *ss); +void mem_cgroup_sockets_destroy(struct cgroup *cgrp); #else static inline int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss) @@ -77,7 +77,7 @@ int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss) return 0; } static inline -void mem_cgroup_sockets_destroy(struct cgroup *cgrp, struct cgroup_subsys *ss) +void mem_cgroup_sockets_destroy(struct cgroup *cgrp) { } #endif @@ -871,8 +871,7 @@ struct proto { */ int (*init_cgroup)(struct cgroup *cgrp, struct cgroup_subsys *ss); - void (*destroy_cgroup)(struct cgroup *cgrp, - struct cgroup_subsys *ss); + void (*destroy_cgroup)(struct cgroup *cgrp); struct cg_proto *(*proto_cgroup)(struct mem_cgroup *memcg); #endif }; diff --git a/include/net/tcp_memcontrol.h b/include/net/tcp_memcontrol.h index 3512082fa90..48410ff25c9 100644 --- a/include/net/tcp_memcontrol.h +++ b/include/net/tcp_memcontrol.h @@ -13,7 +13,7 @@ struct tcp_memcontrol { struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg); int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss); -void tcp_destroy_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss); +void tcp_destroy_cgroup(struct cgroup *cgrp); unsigned long long tcp_max_memory(const struct mem_cgroup *memcg); void tcp_prot_mem(struct mem_cgroup *memcg, long val, int idx); #endif /* _TCP_MEMCG_H */ diff --git a/kernel/cgroup.c b/kernel/cgroup.c index a5d3b5325f7..c6877fe9a83 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -818,7 +818,7 @@ static int cgroup_call_pre_destroy(struct cgroup *cgrp) for_each_subsys(cgrp->root, ss) if (ss->pre_destroy) { - ret = ss->pre_destroy(ss, cgrp); + ret = ss->pre_destroy(cgrp); if (ret) break; } @@ -846,7 +846,7 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode) * Release the subsystem state objects. */ for_each_subsys(cgrp->root, ss) - ss->destroy(ss, cgrp); + ss->destroy(cgrp); cgrp->root->number_of_cgroups--; mutex_unlock(&cgroup_mutex); @@ -1015,7 +1015,7 @@ static int rebind_subsystems(struct cgroupfs_root *root, list_move(&ss->sibling, &root->subsys_list); ss->root = root; if (ss->bind) - ss->bind(ss, cgrp); + ss->bind(cgrp); mutex_unlock(&ss->hierarchy_mutex); /* refcount was already taken, and we're keeping it */ } else if (bit & removed_bits) { @@ -1025,7 +1025,7 @@ static int rebind_subsystems(struct cgroupfs_root *root, BUG_ON(cgrp->subsys[i]->cgroup != cgrp); mutex_lock(&ss->hierarchy_mutex); if (ss->bind) - ss->bind(ss, dummytop); + ss->bind(dummytop); dummytop->subsys[i]->cgroup = dummytop; cgrp->subsys[i] = NULL; subsys[i]->root = &rootnode; @@ -1763,6 +1763,7 @@ EXPORT_SYMBOL_GPL(cgroup_path); struct task_and_cgroup { struct task_struct *task; struct cgroup *cgrp; + struct css_set *cg; }; struct cgroup_taskset { @@ -1843,11 +1844,10 @@ EXPORT_SYMBOL_GPL(cgroup_taskset_size); * will already exist. If not set, this function might sleep, and can fail with * -ENOMEM. Must be called with cgroup_mutex and threadgroup locked. */ -static int cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp, - struct task_struct *tsk, bool guarantee) +static void cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp, + struct task_struct *tsk, struct css_set *newcg) { struct css_set *oldcg; - struct css_set *newcg; /* * We are synchronized through threadgroup_lock() against PF_EXITING @@ -1857,23 +1857,6 @@ static int cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp, WARN_ON_ONCE(tsk->flags & PF_EXITING); oldcg = tsk->cgroups; - /* locate or allocate a new css_set for this task. */ - if (guarantee) { - /* we know the css_set we want already exists. */ - struct cgroup_subsys_state *template[CGROUP_SUBSYS_COUNT]; - read_lock(&css_set_lock); - newcg = find_existing_css_set(oldcg, cgrp, template); - BUG_ON(!newcg); - get_css_set(newcg); - read_unlock(&css_set_lock); - } else { - might_sleep(); - /* find_css_set will give us newcg already referenced. */ - newcg = find_css_set(oldcg, cgrp); - if (!newcg) - return -ENOMEM; - } - task_lock(tsk); rcu_assign_pointer(tsk->cgroups, newcg); task_unlock(tsk); @@ -1892,7 +1875,6 @@ static int cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp, put_css_set(oldcg); set_bit(CGRP_RELEASABLE, &oldcgrp->flags); - return 0; } /** @@ -1910,6 +1892,7 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) struct cgroup *oldcgrp; struct cgroupfs_root *root = cgrp->root; struct cgroup_taskset tset = { }; + struct css_set *newcg; /* @tsk either already exited or can't exit until the end */ if (tsk->flags & PF_EXITING) @@ -1925,7 +1908,7 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) for_each_subsys(root, ss) { if (ss->can_attach) { - retval = ss->can_attach(ss, cgrp, &tset); + retval = ss->can_attach(cgrp, &tset); if (retval) { /* * Remember on which subsystem the can_attach() @@ -1939,13 +1922,17 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) } } - retval = cgroup_task_migrate(cgrp, oldcgrp, tsk, false); - if (retval) + newcg = find_css_set(tsk->cgroups, cgrp); + if (!newcg) { + retval = -ENOMEM; goto out; + } + + cgroup_task_migrate(cgrp, oldcgrp, tsk, newcg); for_each_subsys(root, ss) { if (ss->attach) - ss->attach(ss, cgrp, &tset); + ss->attach(cgrp, &tset); } synchronize_rcu(); @@ -1967,7 +1954,7 @@ out: */ break; if (ss->cancel_attach) - ss->cancel_attach(ss, cgrp, &tset); + ss->cancel_attach(cgrp, &tset); } } return retval; @@ -1997,66 +1984,6 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) } EXPORT_SYMBOL_GPL(cgroup_attach_task_all); -/* - * cgroup_attach_proc works in two stages, the first of which prefetches all - * new css_sets needed (to make sure we have enough memory before committing - * to the move) and stores them in a list of entries of the following type. - * TODO: possible optimization: use css_set->rcu_head for chaining instead - */ -struct cg_list_entry { - struct css_set *cg; - struct list_head links; -}; - -static bool css_set_check_fetched(struct cgroup *cgrp, - struct task_struct *tsk, struct css_set *cg, - struct list_head *newcg_list) -{ - struct css_set *newcg; - struct cg_list_entry *cg_entry; - struct cgroup_subsys_state *template[CGROUP_SUBSYS_COUNT]; - - read_lock(&css_set_lock); - newcg = find_existing_css_set(cg, cgrp, template); - read_unlock(&css_set_lock); - - /* doesn't exist at all? */ - if (!newcg) - return false; - /* see if it's already in the list */ - list_for_each_entry(cg_entry, newcg_list, links) - if (cg_entry->cg == newcg) - return true; - - /* not found */ - return false; -} - -/* - * Find the new css_set and store it in the list in preparation for moving the - * given task to the given cgroup. Returns 0 or -ENOMEM. - */ -static int css_set_prefetch(struct cgroup *cgrp, struct css_set *cg, - struct list_head *newcg_list) -{ - struct css_set *newcg; - struct cg_list_entry *cg_entry; - - /* ensure a new css_set will exist for this thread */ - newcg = find_css_set(cg, cgrp); - if (!newcg) - return -ENOMEM; - /* add it to the list */ - cg_entry = kmalloc(sizeof(struct cg_list_entry), GFP_KERNEL); - if (!cg_entry) { - put_css_set(newcg); - return -ENOMEM; - } - cg_entry->cg = newcg; - list_add(&cg_entry->links, newcg_list); - return 0; -} - /** * cgroup_attach_proc - attach all threads in a threadgroup to a cgroup * @cgrp: the cgroup to attach to @@ -2070,20 +1997,12 @@ static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader) int retval, i, group_size; struct cgroup_subsys *ss, *failed_ss = NULL; /* guaranteed to be initialized later, but the compiler needs this */ - struct css_set *oldcg; struct cgroupfs_root *root = cgrp->root; /* threadgroup list cursor and array */ struct task_struct *tsk; struct task_and_cgroup *tc; struct flex_array *group; struct cgroup_taskset tset = { }; - /* - * we need to make sure we have css_sets for all the tasks we're - * going to move -before- we actually start moving them, so that in - * case we get an ENOMEM we can bail out before making any changes. - */ - struct list_head newcg_list; - struct cg_list_entry *cg_entry, *temp_nobe; /* * step 0: in order to do expensive, possibly blocking operations for @@ -2102,23 +2021,14 @@ static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader) if (retval) goto out_free_group_list; - /* prevent changes to the threadgroup list while we take a snapshot. */ - read_lock(&tasklist_lock); - if (!thread_group_leader(leader)) { - /* - * a race with de_thread from another thread's exec() may strip - * us of our leadership, making while_each_thread unsafe to use - * on this task. if this happens, there is no choice but to - * throw this task away and try again (from cgroup_procs_write); - * this is "double-double-toil-and-trouble-check locking". - */ - read_unlock(&tasklist_lock); - retval = -EAGAIN; - goto out_free_group_list; - } - tsk = leader; i = 0; + /* + * Prevent freeing of tasks while we take a snapshot. Tasks that are + * already PF_EXITING could be freed from underneath us unless we + * take an rcu_read_lock. + */ + rcu_read_lock(); do { struct task_and_cgroup ent; @@ -2128,24 +2038,24 @@ static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader) /* as per above, nr_threads may decrease, but not increase. */ BUG_ON(i >= group_size); - /* - * saying GFP_ATOMIC has no effect here because we did prealloc - * earlier, but it's good form to communicate our expectations. - */ ent.task = tsk; ent.cgrp = task_cgroup_from_root(tsk, root); /* nothing to do if this task is already in the cgroup */ if (ent.cgrp == cgrp) continue; + /* + * saying GFP_ATOMIC has no effect here because we did prealloc + * earlier, but it's good form to communicate our expectations. + */ retval = flex_array_put(group, i, &ent, GFP_ATOMIC); BUG_ON(retval != 0); i++; } while_each_thread(leader, tsk); + rcu_read_unlock(); /* remember the number of threads in the array for later. */ group_size = i; tset.tc_array = group; tset.tc_array_len = group_size; - read_unlock(&tasklist_lock); /* methods shouldn't be called if no task is actually migrating */ retval = 0; @@ -2157,7 +2067,7 @@ static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader) */ for_each_subsys(root, ss) { if (ss->can_attach) { - retval = ss->can_attach(ss, cgrp, &tset); + retval = ss->can_attach(cgrp, &tset); if (retval) { failed_ss = ss; goto out_cancel_attach; @@ -2169,17 +2079,12 @@ static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader) * step 2: make sure css_sets exist for all threads to be migrated. * we use find_css_set, which allocates a new one if necessary. */ - INIT_LIST_HEAD(&newcg_list); for (i = 0; i < group_size; i++) { tc = flex_array_get(group, i); - oldcg = tc->task->cgroups; - - /* if we don't already have it in the list get a new one */ - if (!css_set_check_fetched(cgrp, tc->task, oldcg, - &newcg_list)) { - retval = css_set_prefetch(cgrp, oldcg, &newcg_list); - if (retval) - goto out_list_teardown; + tc->cg = find_css_set(tc->task->cgroups, cgrp); + if (!tc->cg) { + retval = -ENOMEM; + goto out_put_css_set_refs; } } @@ -2190,8 +2095,7 @@ static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader) */ for (i = 0; i < group_size; i++) { tc = flex_array_get(group, i); - retval = cgroup_task_migrate(cgrp, tc->cgrp, tc->task, true); - BUG_ON(retval); + cgroup_task_migrate(cgrp, tc->cgrp, tc->task, tc->cg); } /* nothing is sensitive to fork() after this point. */ @@ -2200,7 +2104,7 @@ static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader) */ for_each_subsys(root, ss) { if (ss->attach) - ss->attach(ss, cgrp, &tset); + ss->attach(cgrp, &tset); } /* @@ -2209,21 +2113,22 @@ static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader) synchronize_rcu(); cgroup_wakeup_rmdir_waiter(cgrp); retval = 0; -out_list_teardown: - /* clean up the list of prefetched css_sets. */ - list_for_each_entry_safe(cg_entry, temp_nobe, &newcg_list, links) { - list_del(&cg_entry->links); - put_css_set(cg_entry->cg); - kfree(cg_entry); +out_put_css_set_refs: + if (retval) { + for (i = 0; i < group_size; i++) { + tc = flex_array_get(group, i); + if (!tc->cg) + break; + put_css_set(tc->cg); + } } out_cancel_attach: - /* same deal as in cgroup_attach_task */ if (retval) { for_each_subsys(root, ss) { if (ss == failed_ss) break; if (ss->cancel_attach) - ss->cancel_attach(ss, cgrp, &tset); + ss->cancel_attach(cgrp, &tset); } } out_free_group_list: @@ -2245,22 +2150,14 @@ static int attach_task_by_pid(struct cgroup *cgrp, u64 pid, bool threadgroup) if (!cgroup_lock_live_group(cgrp)) return -ENODEV; +retry_find_task: + rcu_read_lock(); if (pid) { - rcu_read_lock(); tsk = find_task_by_vpid(pid); if (!tsk) { rcu_read_unlock(); - cgroup_unlock(); - return -ESRCH; - } - if (threadgroup) { - /* - * RCU protects this access, since tsk was found in the - * tid map. a race with de_thread may cause group_leader - * to stop being the leader, but cgroup_attach_proc will - * detect it later. - */ - tsk = tsk->group_leader; + ret= -ESRCH; + goto out_unlock_cgroup; } /* * even if we're attaching all tasks in the thread group, we @@ -2271,29 +2168,38 @@ static int attach_task_by_pid(struct cgroup *cgrp, u64 pid, bool threadgroup) cred->euid != tcred->uid && cred->euid != tcred->suid) { rcu_read_unlock(); - cgroup_unlock(); - return -EACCES; + ret = -EACCES; + goto out_unlock_cgroup; } - get_task_struct(tsk); - rcu_read_unlock(); - } else { - if (threadgroup) - tsk = current->group_leader; - else - tsk = current; - get_task_struct(tsk); - } - - threadgroup_lock(tsk); + } else + tsk = current; if (threadgroup) + tsk = tsk->group_leader; + get_task_struct(tsk); + rcu_read_unlock(); + + threadgroup_lock(tsk); + if (threadgroup) { + if (!thread_group_leader(tsk)) { + /* + * a race with de_thread from another thread's exec() + * may strip us of our leadership, if this happens, + * there is no choice but to throw this task away and + * try again; this is + * "double-double-toil-and-trouble-check locking". + */ + threadgroup_unlock(tsk); + put_task_struct(tsk); + goto retry_find_task; + } ret = cgroup_attach_proc(cgrp, tsk); - else + } else ret = cgroup_attach_task(cgrp, tsk); - threadgroup_unlock(tsk); put_task_struct(tsk); +out_unlock_cgroup: cgroup_unlock(); return ret; } @@ -2305,16 +2211,7 @@ static int cgroup_tasks_write(struct cgroup *cgrp, struct cftype *cft, u64 pid) static int cgroup_procs_write(struct cgroup *cgrp, struct cftype *cft, u64 tgid) { - int ret; - do { - /* - * attach_proc fails with -EAGAIN if threadgroup leadership - * changes in the middle of the operation, in which case we need - * to find the task_struct for the new leader and start over. - */ - ret = attach_task_by_pid(cgrp, tgid, true); - } while (ret == -EAGAIN); - return ret; + return attach_task_by_pid(cgrp, tgid, true); } /** @@ -2804,15 +2701,20 @@ static void cgroup_advance_iter(struct cgroup *cgrp, * using their cgroups capability, we don't maintain the lists running * through each css_set to its tasks until we see the list actually * used - in other words after the first call to cgroup_iter_start(). - * - * The tasklist_lock is not held here, as do_each_thread() and - * while_each_thread() are protected by RCU. */ static void cgroup_enable_task_cg_lists(void) { struct task_struct *p, *g; write_lock(&css_set_lock); use_task_css_set_links = 1; + /* + * We need tasklist_lock because RCU is not safe against + * while_each_thread(). Besides, a forking task that has passed + * cgroup_post_fork() without seeing use_task_css_set_links = 1 + * is not guaranteed to have its child immediately visible in the + * tasklist if we walk through it with RCU. + */ + read_lock(&tasklist_lock); do_each_thread(g, p) { task_lock(p); /* @@ -2824,6 +2726,7 @@ static void cgroup_enable_task_cg_lists(void) list_add(&p->cg_list, &p->cgroups->tasks); task_unlock(p); } while_each_thread(g, p); + read_unlock(&tasklist_lock); write_unlock(&css_set_lock); } @@ -3043,6 +2946,38 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan) * */ +/* which pidlist file are we talking about? */ +enum cgroup_filetype { + CGROUP_FILE_PROCS, + CGROUP_FILE_TASKS, +}; + +/* + * A pidlist is a list of pids that virtually represents the contents of one + * of the cgroup files ("procs" or "tasks"). We keep a list of such pidlists, + * a pair (one each for procs, tasks) for each pid namespace that's relevant + * to the cgroup. + */ +struct cgroup_pidlist { + /* + * used to find which pidlist is wanted. doesn't change as long as + * this particular list stays in the list. + */ + struct { enum cgroup_filetype type; struct pid_namespace *ns; } key; + /* array of xids */ + pid_t *list; + /* how many elements the above list has */ + int length; + /* how many files are using the current array */ + int use_count; + /* each of these stored in a list by its cgroup */ + struct list_head links; + /* pointer to the cgroup we belong to, for list removal purposes */ + struct cgroup *owner; + /* protects the other fields */ + struct rw_semaphore mutex; +}; + /* * The following two functions "fix" the issue where there are more pids * than kmalloc will give memory for; in such cases, we use vmalloc/vfree. @@ -3827,7 +3762,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, set_bit(CGRP_CLONE_CHILDREN, &cgrp->flags); for_each_subsys(root, ss) { - struct cgroup_subsys_state *css = ss->create(ss, cgrp); + struct cgroup_subsys_state *css = ss->create(cgrp); if (IS_ERR(css)) { err = PTR_ERR(css); @@ -3841,7 +3776,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, } /* At error, ->destroy() callback has to free assigned ID. */ if (clone_children(parent) && ss->post_clone) - ss->post_clone(ss, cgrp); + ss->post_clone(cgrp); } cgroup_lock_hierarchy(root); @@ -3875,7 +3810,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, for_each_subsys(root, ss) { if (cgrp->subsys[ss->subsys_id]) - ss->destroy(ss, cgrp); + ss->destroy(cgrp); } mutex_unlock(&cgroup_mutex); @@ -4099,7 +4034,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss) /* Create the top cgroup state for this subsystem */ list_add(&ss->sibling, &rootnode.subsys_list); ss->root = &rootnode; - css = ss->create(ss, dummytop); + css = ss->create(dummytop); /* We don't handle early failures gracefully */ BUG_ON(IS_ERR(css)); init_cgroup_css(css, ss, dummytop); @@ -4188,7 +4123,7 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss) * no ss->create seems to need anything important in the ss struct, so * this can happen first (i.e. before the rootnode attachment). */ - css = ss->create(ss, dummytop); + css = ss->create(dummytop); if (IS_ERR(css)) { /* failure case - need to deassign the subsys[] slot. */ subsys[i] = NULL; @@ -4206,7 +4141,7 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss) int ret = cgroup_init_idr(ss, css); if (ret) { dummytop->subsys[ss->subsys_id] = NULL; - ss->destroy(ss, dummytop); + ss->destroy(dummytop); subsys[i] = NULL; mutex_unlock(&cgroup_mutex); |