[GIT PULL] cgroup changes for v3.3-rc1
From: Tejun Heo
Date: Mon Jan 09 2012 - 13:40:01 EST
Hello, Linus.
Please pull from the following branch to receive cgroup changes.
git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup.git for-3.3
The big change is threadgroup locking, which was discussed in the
following thread.
http://thread.gmane.org/gmane.linux.kernel.containers/21716/focus=26390
The change enabled cgroup core cleanups and removal of corner cases,
which Frederic and Mandeep have been working on and more should be
coming.
Thank you.
Dan Carpenter (1):
cgroup: move assignement out of condition in cgroup_attach_proc()
Davidlohr Bueso (1):
resource cgroups: remove bogus cast
Frederic Weisbecker (3):
cgroup: Drop task_lock(parent) on cgroup_fork()
cgroup: Remove unnecessary task_lock before fetching css_set on migration
cgroup: Remove task_lock() from cgroup_post_fork()
Kirill A. Shutemov (2):
cgroup: mark cgroup_rmdir_waitq and cgroup_attach_proc() as static
cgroup: add sparse annotation to cgroup_iter_start() and cgroup_iter_end()
Li Zefan (1):
cgroup: fix to allow mounting a hierarchy by name
Mandeep Singh Baines (4):
cgroups: remove redundant get/put of css_set from css_set_check_fetched()
cgroup: remove redundant get/put of old css_set from migrate
cgroup: remove redundant get/put of task struct
cgroup: only need to check oldcgrp==newgrp once
Tejun Heo (9):
cgroup: add cgroup_root_mutex
threadgroup: rename signal->threadgroup_fork_lock to ->group_rwsem
threadgroup: extend threadgroup_lock() to cover exit and exec
cgroup: always lock threadgroup during migration
cgroup: improve old cgroup handling in cgroup_attach_proc()
cgroup: introduce cgroup_taskset and use it in subsys->can_attach(), cancel_attach() and attach()
cgroup: don't use subsys->can_attach_task() or ->attach_task()
cgroup, cpuset: don't use ss->pre_attach()
cgroup: kill subsys->can_attach_task(), pre_attach() and attach_task()
Documentation/cgroups/cgroups.txt | 51 ++---
block/blk-cgroup.c | 45 +++--
include/linux/cgroup.h | 31 +++-
include/linux/init_task.h | 9 +-
include/linux/sched.h | 73 +++++--
kernel/cgroup.c | 406 +++++++++++++++++++++----------------
kernel/cgroup_freezer.c | 16 +-
kernel/cpuset.c | 105 +++++-----
kernel/events/core.c | 13 +-
kernel/fork.c | 8 +-
kernel/res_counter.c | 3 +-
kernel/sched.c | 31 ++-
kernel/signal.c | 10 +
mm/memcontrol.c | 16 +-
security/device_cgroup.c | 7 +-
15 files changed, 470 insertions(+), 354 deletions(-)
diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt
index 9c452ef..a7c96ae 100644
--- a/Documentation/cgroups/cgroups.txt
+++ b/Documentation/cgroups/cgroups.txt
@@ -594,53 +594,44 @@ 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 task_struct *task)
+ struct cgroup_taskset *tset)
(cgroup_mutex held by caller)
-Called prior to moving a task into a cgroup; if the subsystem
-returns an error, this will abort the attach operation. If a NULL
-task is passed, then a successful result indicates that *any*
-unspecified task can be moved into the cgroup. Note that this isn't
-called on a fork. If this method returns 0 (success) then this should
-remain valid while the caller holds cgroup_mutex and it is ensured that either
+Called prior to moving one or more tasks into a cgroup; if the
+subsystem returns an error, this will abort the attach operation.
+@tset contains the tasks to be attached and is guaranteed to have at
+least one task in it.
+
+If there are multiple tasks in the taskset, then:
+ - it's guaranteed that all are from the same thread group
+ - @tset contains all tasks from the thread group whether or not
+ they're switching cgroups
+ - the first task is the leader
+
+Each @tset entry also contains the task's old cgroup and tasks which
+aren't switching cgroup can be skipped easily using the
+cgroup_taskset_for_each() iterator. Note that this isn't called on a
+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.
-int can_attach_task(struct cgroup *cgrp, struct task_struct *tsk);
-(cgroup_mutex held by caller)
-
-As can_attach, but for operations that must be run once per task to be
-attached (possibly many when using cgroup_attach_proc). Called after
-can_attach.
-
void cancel_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
- struct task_struct *task, bool threadgroup)
+ struct cgroup_taskset *tset)
(cgroup_mutex held by caller)
Called when a task attach operation has failed after can_attach() has succeeded.
A subsystem whose can_attach() has some side-effects should provide this
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.
-
-void pre_attach(struct cgroup *cgrp);
-(cgroup_mutex held by caller)
-
-For any non-per-thread attachment work that needs to happen before
-attach_task. Needed by cpuset.
+succeeded. The parameters are identical to can_attach().
void attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
- struct cgroup *old_cgrp, struct task_struct *task)
+ 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.
-
-void attach_task(struct cgroup *cgrp, struct task_struct *tsk);
-(cgroup_mutex held by caller)
-
-As attach, but for operations that must be run once per task to be attached,
-like can_attach_task. Called before attach. Currently does not support any
-subsystem that might need the old_cgrp for every thread in the group.
+The parameters are identical to can_attach().
void fork(struct cgroup_subsy *ss, struct task_struct *task)
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 8f630ce..b8c143d 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -30,8 +30,10 @@ EXPORT_SYMBOL_GPL(blkio_root_cgroup);
static struct cgroup_subsys_state *blkiocg_create(struct cgroup_subsys *,
struct cgroup *);
-static int blkiocg_can_attach_task(struct cgroup *, struct task_struct *);
-static void blkiocg_attach_task(struct cgroup *, struct task_struct *);
+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 int blkiocg_populate(struct cgroup_subsys *, struct cgroup *);
@@ -44,8 +46,8 @@ static int blkiocg_populate(struct cgroup_subsys *, struct cgroup *);
struct cgroup_subsys blkio_subsys = {
.name = "blkio",
.create = blkiocg_create,
- .can_attach_task = blkiocg_can_attach_task,
- .attach_task = blkiocg_attach_task,
+ .can_attach = blkiocg_can_attach,
+ .attach = blkiocg_attach,
.destroy = blkiocg_destroy,
.populate = blkiocg_populate,
#ifdef CONFIG_BLK_CGROUP
@@ -1626,30 +1628,39 @@ 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_task(struct cgroup *cgrp, struct task_struct *tsk)
+static int blkiocg_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
+ struct cgroup_taskset *tset)
{
+ struct task_struct *task;
struct io_context *ioc;
int ret = 0;
/* task_lock() is needed to avoid races with exit_io_context() */
- task_lock(tsk);
- ioc = tsk->io_context;
- if (ioc && atomic_read(&ioc->nr_tasks) > 1)
- ret = -EINVAL;
- task_unlock(tsk);
-
+ cgroup_taskset_for_each(task, cgrp, tset) {
+ task_lock(task);
+ ioc = task->io_context;
+ if (ioc && atomic_read(&ioc->nr_tasks) > 1)
+ ret = -EINVAL;
+ task_unlock(task);
+ if (ret)
+ break;
+ }
return ret;
}
-static void blkiocg_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
+static void blkiocg_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
+ struct cgroup_taskset *tset)
{
+ struct task_struct *task;
struct io_context *ioc;
- task_lock(tsk);
- ioc = tsk->io_context;
- if (ioc)
- ioc->cgroup_changed = 1;
- task_unlock(tsk);
+ cgroup_taskset_for_each(task, cgrp, tset) {
+ task_lock(task);
+ ioc = task->io_context;
+ if (ioc)
+ ioc->cgroup_changed = 1;
+ task_unlock(task);
+ }
}
void blkio_policy_register(struct blkio_policy_type *blkiop)
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 1b7f9d5..7ad5e40 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -457,6 +457,28 @@ void cgroup_exclude_rmdir(struct cgroup_subsys_state *css);
void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css);
/*
+ * Control Group taskset, used to pass around set of tasks to cgroup_subsys
+ * methods.
+ */
+struct cgroup_taskset;
+struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset);
+struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset);
+struct cgroup *cgroup_taskset_cur_cgroup(struct cgroup_taskset *tset);
+int cgroup_taskset_size(struct cgroup_taskset *tset);
+
+/**
+ * cgroup_taskset_for_each - iterate cgroup_taskset
+ * @task: the loop cursor
+ * @skip_cgrp: skip if task's cgroup matches this, %NULL to iterate through all
+ * @tset: taskset to iterate
+ */
+#define cgroup_taskset_for_each(task, skip_cgrp, tset) \
+ for ((task) = cgroup_taskset_first((tset)); (task); \
+ (task) = cgroup_taskset_next((tset))) \
+ if (!(skip_cgrp) || \
+ cgroup_taskset_cur_cgroup((tset)) != (skip_cgrp))
+
+/*
* Control Group subsystem type.
* See Documentation/cgroups/cgroups.txt for details
*/
@@ -467,14 +489,11 @@ struct cgroup_subsys {
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 task_struct *tsk);
- int (*can_attach_task)(struct cgroup *cgrp, struct task_struct *tsk);
+ struct cgroup_taskset *tset);
void (*cancel_attach)(struct cgroup_subsys *ss, struct cgroup *cgrp,
- struct task_struct *tsk);
- void (*pre_attach)(struct cgroup *cgrp);
- void (*attach_task)(struct cgroup *cgrp, struct task_struct *tsk);
+ struct cgroup_taskset *tset);
void (*attach)(struct cgroup_subsys *ss, struct cgroup *cgrp,
- struct cgroup *old_cgrp, struct task_struct *tsk);
+ 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);
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 94b1e35..f4544b9 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -23,11 +23,10 @@ extern struct files_struct init_files;
extern struct fs_struct init_fs;
#ifdef CONFIG_CGROUPS
-#define INIT_THREADGROUP_FORK_LOCK(sig) \
- .threadgroup_fork_lock = \
- __RWSEM_INITIALIZER(sig.threadgroup_fork_lock),
+#define INIT_GROUP_RWSEM(sig) \
+ .group_rwsem = __RWSEM_INITIALIZER(sig.group_rwsem),
#else
-#define INIT_THREADGROUP_FORK_LOCK(sig)
+#define INIT_GROUP_RWSEM(sig)
#endif
#define INIT_SIGNALS(sig) { \
@@ -46,7 +45,7 @@ extern struct fs_struct init_fs;
}, \
.cred_guard_mutex = \
__MUTEX_INITIALIZER(sig.cred_guard_mutex), \
- INIT_THREADGROUP_FORK_LOCK(sig) \
+ INIT_GROUP_RWSEM(sig) \
}
extern struct nsproxy init_nsproxy;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index d81cce9..c0c5876 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -635,13 +635,15 @@ struct signal_struct {
#endif
#ifdef CONFIG_CGROUPS
/*
- * The threadgroup_fork_lock prevents threads from forking with
- * CLONE_THREAD while held for writing. Use this for fork-sensitive
- * threadgroup-wide operations. It's taken for reading in fork.c in
- * copy_process().
- * Currently only needed write-side by cgroups.
+ * group_rwsem prevents new tasks from entering the threadgroup and
+ * member tasks from exiting,a more specifically, setting of
+ * PF_EXITING. fork and exit paths are protected with this rwsem
+ * using threadgroup_change_begin/end(). Users which require
+ * threadgroup to remain stable should use threadgroup_[un]lock()
+ * which also takes care of exec path. Currently, cgroup is the
+ * only user.
*/
- struct rw_semaphore threadgroup_fork_lock;
+ struct rw_semaphore group_rwsem;
#endif
int oom_adj; /* OOM kill score adjustment (bit shift) */
@@ -2371,29 +2373,62 @@ static inline void unlock_task_sighand(struct task_struct *tsk,
spin_unlock_irqrestore(&tsk->sighand->siglock, *flags);
}
-/* See the declaration of threadgroup_fork_lock in signal_struct. */
#ifdef CONFIG_CGROUPS
-static inline void threadgroup_fork_read_lock(struct task_struct *tsk)
+static inline void threadgroup_change_begin(struct task_struct *tsk)
{
- down_read(&tsk->signal->threadgroup_fork_lock);
+ down_read(&tsk->signal->group_rwsem);
}
-static inline void threadgroup_fork_read_unlock(struct task_struct *tsk)
+static inline void threadgroup_change_end(struct task_struct *tsk)
{
- up_read(&tsk->signal->threadgroup_fork_lock);
+ up_read(&tsk->signal->group_rwsem);
}
-static inline void threadgroup_fork_write_lock(struct task_struct *tsk)
+
+/**
+ * threadgroup_lock - lock threadgroup
+ * @tsk: member task of the threadgroup to lock
+ *
+ * Lock the threadgroup @tsk belongs to. No new task is allowed to enter
+ * and member tasks aren't allowed to exit (as indicated by PF_EXITING) or
+ * perform exec. This is useful for cases where the threadgroup needs to
+ * stay stable across blockable operations.
+ *
+ * fork and exit paths explicitly call threadgroup_change_{begin|end}() for
+ * synchronization. While held, no new task will be added to threadgroup
+ * and no existing live task will have its PF_EXITING set.
+ *
+ * During exec, a task goes and puts its thread group through unusual
+ * changes. After de-threading, exclusive access is assumed to resources
+ * which are usually shared by tasks in the same group - e.g. sighand may
+ * be replaced with a new one. Also, the exec'ing task takes over group
+ * leader role including its pid. Exclude these changes while locked by
+ * grabbing cred_guard_mutex which is used to synchronize exec path.
+ */
+static inline void threadgroup_lock(struct task_struct *tsk)
{
- down_write(&tsk->signal->threadgroup_fork_lock);
+ /*
+ * exec uses exit for de-threading nesting group_rwsem inside
+ * cred_guard_mutex. Grab cred_guard_mutex first.
+ */
+ mutex_lock(&tsk->signal->cred_guard_mutex);
+ down_write(&tsk->signal->group_rwsem);
}
-static inline void threadgroup_fork_write_unlock(struct task_struct *tsk)
+
+/**
+ * threadgroup_unlock - unlock threadgroup
+ * @tsk: member task of the threadgroup to unlock
+ *
+ * Reverse threadgroup_lock().
+ */
+static inline void threadgroup_unlock(struct task_struct *tsk)
{
- up_write(&tsk->signal->threadgroup_fork_lock);
+ up_write(&tsk->signal->group_rwsem);
+ mutex_unlock(&tsk->signal->cred_guard_mutex);
}
#else
-static inline void threadgroup_fork_read_lock(struct task_struct *tsk) {}
-static inline void threadgroup_fork_read_unlock(struct task_struct *tsk) {}
-static inline void threadgroup_fork_write_lock(struct task_struct *tsk) {}
-static inline void threadgroup_fork_write_unlock(struct task_struct *tsk) {}
+static inline void threadgroup_change_begin(struct task_struct *tsk) {}
+static inline void threadgroup_change_end(struct task_struct *tsk) {}
+static inline void threadgroup_lock(struct task_struct *tsk) {}
+static inline void threadgroup_unlock(struct task_struct *tsk) {}
#endif
#ifndef __HAVE_THREAD_FUNCTIONS
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index d9d5648..39c7cae 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -63,7 +63,24 @@
#include <linux/atomic.h>
+/*
+ * cgroup_mutex is the master lock. Any modification to cgroup or its
+ * hierarchy must be performed while holding it.
+ *
+ * cgroup_root_mutex nests inside cgroup_mutex and should be held to modify
+ * cgroupfs_root of any cgroup hierarchy - subsys list, flags,
+ * release_agent_path and so on. Modifying requires both cgroup_mutex and
+ * cgroup_root_mutex. Readers can acquire either of the two. This is to
+ * break the following locking order cycle.
+ *
+ * A. cgroup_mutex -> cred_guard_mutex -> s_type->i_mutex_key -> namespace_sem
+ * B. namespace_sem -> cgroup_mutex
+ *
+ * B happens only through cgroup_show_options() and using cgroup_root_mutex
+ * breaks it.
+ */
static DEFINE_MUTEX(cgroup_mutex);
+static DEFINE_MUTEX(cgroup_root_mutex);
/*
* Generate an array of cgroup subsystem pointers. At boot time, this is
@@ -921,7 +938,7 @@ static void cgroup_d_remove_dir(struct dentry *dentry)
*
* CGRP_WAIT_ON_RMDIR flag is set under cgroup's inode->i_mutex;
*/
-DECLARE_WAIT_QUEUE_HEAD(cgroup_rmdir_waitq);
+static DECLARE_WAIT_QUEUE_HEAD(cgroup_rmdir_waitq);
static void cgroup_wakeup_rmdir_waiter(struct cgroup *cgrp)
{
@@ -953,6 +970,7 @@ static int rebind_subsystems(struct cgroupfs_root *root,
int i;
BUG_ON(!mutex_is_locked(&cgroup_mutex));
+ BUG_ON(!mutex_is_locked(&cgroup_root_mutex));
removed_bits = root->actual_subsys_bits & ~final_bits;
added_bits = final_bits & ~root->actual_subsys_bits;
@@ -1043,7 +1061,7 @@ static int cgroup_show_options(struct seq_file *seq, struct vfsmount *vfs)
struct cgroupfs_root *root = vfs->mnt_sb->s_fs_info;
struct cgroup_subsys *ss;
- mutex_lock(&cgroup_mutex);
+ mutex_lock(&cgroup_root_mutex);
for_each_subsys(root, ss)
seq_printf(seq, ",%s", ss->name);
if (test_bit(ROOT_NOPREFIX, &root->flags))
@@ -1054,7 +1072,7 @@ static int cgroup_show_options(struct seq_file *seq, struct vfsmount *vfs)
seq_puts(seq, ",clone_children");
if (strlen(root->name))
seq_printf(seq, ",name=%s", root->name);
- mutex_unlock(&cgroup_mutex);
+ mutex_unlock(&cgroup_root_mutex);
return 0;
}
@@ -1175,10 +1193,10 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
/*
* If the 'all' option was specified select all the subsystems,
- * otherwise 'all, 'none' and a subsystem name options were not
- * specified, let's default to 'all'
+ * otherwise if 'none', 'name=' and a subsystem name options
+ * were not specified, let's default to 'all'
*/
- if (all_ss || (!all_ss && !one_ss && !opts->none)) {
+ if (all_ss || (!one_ss && !opts->none && !opts->name)) {
for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
struct cgroup_subsys *ss = subsys[i];
if (ss == NULL)
@@ -1269,6 +1287,7 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
mutex_lock(&cgrp->dentry->d_inode->i_mutex);
mutex_lock(&cgroup_mutex);
+ mutex_lock(&cgroup_root_mutex);
/* See what subsystems are wanted */
ret = parse_cgroupfs_options(data, &opts);
@@ -1297,6 +1316,7 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
out_unlock:
kfree(opts.release_agent);
kfree(opts.name);
+ mutex_unlock(&cgroup_root_mutex);
mutex_unlock(&cgroup_mutex);
mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
return ret;
@@ -1481,6 +1501,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
int ret = 0;
struct super_block *sb;
struct cgroupfs_root *new_root;
+ struct inode *inode;
/* First find the desired set of subsystems */
mutex_lock(&cgroup_mutex);
@@ -1514,7 +1535,6 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
/* We used the new root structure, so this is a new hierarchy */
struct list_head tmp_cg_links;
struct cgroup *root_cgrp = &root->top_cgroup;
- struct inode *inode;
struct cgroupfs_root *existing_root;
const struct cred *cred;
int i;
@@ -1528,18 +1548,14 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
mutex_lock(&inode->i_mutex);
mutex_lock(&cgroup_mutex);
+ mutex_lock(&cgroup_root_mutex);
- if (strlen(root->name)) {
- /* Check for name clashes with existing mounts */
- for_each_active_root(existing_root) {
- if (!strcmp(existing_root->name, root->name)) {
- ret = -EBUSY;
- mutex_unlock(&cgroup_mutex);
- mutex_unlock(&inode->i_mutex);
- goto drop_new_super;
- }
- }
- }
+ /* Check for name clashes with existing mounts */
+ ret = -EBUSY;
+ if (strlen(root->name))
+ for_each_active_root(existing_root)
+ if (!strcmp(existing_root->name, root->name))
+ goto unlock_drop;
/*
* We're accessing css_set_count without locking
@@ -1549,18 +1565,13 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
* have some link structures left over
*/
ret = allocate_cg_links(css_set_count, &tmp_cg_links);
- if (ret) {
- mutex_unlock(&cgroup_mutex);
- mutex_unlock(&inode->i_mutex);
- goto drop_new_super;
- }
+ if (ret)
+ goto unlock_drop;
ret = rebind_subsystems(root, root->subsys_bits);
if (ret == -EBUSY) {
- mutex_unlock(&cgroup_mutex);
- mutex_unlock(&inode->i_mutex);
free_cg_links(&tmp_cg_links);
- goto drop_new_super;
+ goto unlock_drop;
}
/*
* There must be no failure case after here, since rebinding
@@ -1599,6 +1610,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
cred = override_creds(&init_cred);
cgroup_populate_dir(root_cgrp);
revert_creds(cred);
+ mutex_unlock(&cgroup_root_mutex);
mutex_unlock(&cgroup_mutex);
mutex_unlock(&inode->i_mutex);
} else {
@@ -1615,6 +1627,10 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
kfree(opts.name);
return dget(sb->s_root);
+ unlock_drop:
+ mutex_unlock(&cgroup_root_mutex);
+ mutex_unlock(&cgroup_mutex);
+ mutex_unlock(&inode->i_mutex);
drop_new_super:
deactivate_locked_super(sb);
drop_modules:
@@ -1639,6 +1655,7 @@ static void cgroup_kill_sb(struct super_block *sb) {
BUG_ON(!list_empty(&cgrp->sibling));
mutex_lock(&cgroup_mutex);
+ mutex_lock(&cgroup_root_mutex);
/* Rebind all subsystems back to the default hierarchy */
ret = rebind_subsystems(root, 0);
@@ -1664,6 +1681,7 @@ static void cgroup_kill_sb(struct super_block *sb) {
root_count--;
}
+ mutex_unlock(&cgroup_root_mutex);
mutex_unlock(&cgroup_mutex);
kill_litter_super(sb);
@@ -1740,11 +1758,90 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
EXPORT_SYMBOL_GPL(cgroup_path);
/*
+ * Control Group taskset
+ */
+struct task_and_cgroup {
+ struct task_struct *task;
+ struct cgroup *cgrp;
+};
+
+struct cgroup_taskset {
+ struct task_and_cgroup single;
+ struct flex_array *tc_array;
+ int tc_array_len;
+ int idx;
+ struct cgroup *cur_cgrp;
+};
+
+/**
+ * cgroup_taskset_first - reset taskset and return the first task
+ * @tset: taskset of interest
+ *
+ * @tset iteration is initialized and the first task is returned.
+ */
+struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset)
+{
+ if (tset->tc_array) {
+ tset->idx = 0;
+ return cgroup_taskset_next(tset);
+ } else {
+ tset->cur_cgrp = tset->single.cgrp;
+ return tset->single.task;
+ }
+}
+EXPORT_SYMBOL_GPL(cgroup_taskset_first);
+
+/**
+ * cgroup_taskset_next - iterate to the next task in taskset
+ * @tset: taskset of interest
+ *
+ * Return the next task in @tset. Iteration must have been initialized
+ * with cgroup_taskset_first().
+ */
+struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset)
+{
+ struct task_and_cgroup *tc;
+
+ if (!tset->tc_array || tset->idx >= tset->tc_array_len)
+ return NULL;
+
+ tc = flex_array_get(tset->tc_array, tset->idx++);
+ tset->cur_cgrp = tc->cgrp;
+ return tc->task;
+}
+EXPORT_SYMBOL_GPL(cgroup_taskset_next);
+
+/**
+ * cgroup_taskset_cur_cgroup - return the matching cgroup for the current task
+ * @tset: taskset of interest
+ *
+ * Return the cgroup for the current (last returned) task of @tset. This
+ * function must be preceded by either cgroup_taskset_first() or
+ * cgroup_taskset_next().
+ */
+struct cgroup *cgroup_taskset_cur_cgroup(struct cgroup_taskset *tset)
+{
+ return tset->cur_cgrp;
+}
+EXPORT_SYMBOL_GPL(cgroup_taskset_cur_cgroup);
+
+/**
+ * cgroup_taskset_size - return the number of tasks in taskset
+ * @tset: taskset of interest
+ */
+int cgroup_taskset_size(struct cgroup_taskset *tset)
+{
+ return tset->tc_array ? tset->tc_array_len : 1;
+}
+EXPORT_SYMBOL_GPL(cgroup_taskset_size);
+
+
+/*
* cgroup_task_migrate - move a task from one cgroup to another.
*
* 'guarantee' is set if the caller promises that a new css_set for the task
* will already exist. If not set, this function might sleep, and can fail with
- * -ENOMEM. Otherwise, it can only fail with -ESRCH.
+ * -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)
@@ -1753,14 +1850,12 @@ static int cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp,
struct css_set *newcg;
/*
- * get old css_set. we need to take task_lock and refcount it, because
- * an exiting task can change its css_set to init_css_set and drop its
- * old one without taking cgroup_mutex.
+ * We are synchronized through threadgroup_lock() against PF_EXITING
+ * setting such that we can't race against cgroup_exit() changing the
+ * css_set to init_css_set and dropping the old one.
*/
- task_lock(tsk);
+ WARN_ON_ONCE(tsk->flags & PF_EXITING);
oldcg = tsk->cgroups;
- get_css_set(oldcg);
- task_unlock(tsk);
/* locate or allocate a new css_set for this task. */
if (guarantee) {
@@ -1775,20 +1870,11 @@ static int cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp,
might_sleep();
/* find_css_set will give us newcg already referenced. */
newcg = find_css_set(oldcg, cgrp);
- if (!newcg) {
- put_css_set(oldcg);
+ if (!newcg)
return -ENOMEM;
- }
}
- put_css_set(oldcg);
- /* if PF_EXITING is set, the tsk->cgroups pointer is no longer safe. */
task_lock(tsk);
- if (tsk->flags & PF_EXITING) {
- task_unlock(tsk);
- put_css_set(newcg);
- return -ESRCH;
- }
rcu_assign_pointer(tsk->cgroups, newcg);
task_unlock(tsk);
@@ -1814,8 +1900,8 @@ static int cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp,
* @cgrp: the cgroup the task is attaching to
* @tsk: the task to be attached
*
- * Call holding cgroup_mutex. May take task_lock of
- * the task 'tsk' during call.
+ * Call with cgroup_mutex and threadgroup locked. May take task_lock of
+ * @tsk during call.
*/
int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
{
@@ -1823,15 +1909,23 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
struct cgroup_subsys *ss, *failed_ss = NULL;
struct cgroup *oldcgrp;
struct cgroupfs_root *root = cgrp->root;
+ struct cgroup_taskset tset = { };
+
+ /* @tsk either already exited or can't exit until the end */
+ if (tsk->flags & PF_EXITING)
+ return -ESRCH;
/* Nothing to do if the task is already in that cgroup */
oldcgrp = task_cgroup_from_root(tsk, root);
if (cgrp == oldcgrp)
return 0;
+ tset.single.task = tsk;
+ tset.single.cgrp = oldcgrp;
+
for_each_subsys(root, ss) {
if (ss->can_attach) {
- retval = ss->can_attach(ss, cgrp, tsk);
+ retval = ss->can_attach(ss, cgrp, &tset);
if (retval) {
/*
* Remember on which subsystem the can_attach()
@@ -1843,13 +1937,6 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
goto out;
}
}
- if (ss->can_attach_task) {
- retval = ss->can_attach_task(cgrp, tsk);
- if (retval) {
- failed_ss = ss;
- goto out;
- }
- }
}
retval = cgroup_task_migrate(cgrp, oldcgrp, tsk, false);
@@ -1857,12 +1944,8 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
goto out;
for_each_subsys(root, ss) {
- if (ss->pre_attach)
- ss->pre_attach(cgrp);
- if (ss->attach_task)
- ss->attach_task(cgrp, tsk);
if (ss->attach)
- ss->attach(ss, cgrp, oldcgrp, tsk);
+ ss->attach(ss, cgrp, &tset);
}
synchronize_rcu();
@@ -1884,7 +1967,7 @@ out:
*/
break;
if (ss->cancel_attach)
- ss->cancel_attach(ss, cgrp, tsk);
+ ss->cancel_attach(ss, cgrp, &tset);
}
}
return retval;
@@ -1935,23 +2018,17 @@ static bool css_set_check_fetched(struct cgroup *cgrp,
read_lock(&css_set_lock);
newcg = find_existing_css_set(cg, cgrp, template);
- if (newcg)
- get_css_set(newcg);
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) {
- put_css_set(newcg);
+ list_for_each_entry(cg_entry, newcg_list, links)
+ if (cg_entry->cg == newcg)
return true;
- }
- }
/* not found */
- put_css_set(newcg);
return false;
}
@@ -1985,21 +2062,21 @@ static int css_set_prefetch(struct cgroup *cgrp, struct css_set *cg,
* @cgrp: the cgroup to attach to
* @leader: the threadgroup leader task_struct of the group to be attached
*
- * Call holding cgroup_mutex and the threadgroup_fork_lock of the leader. Will
- * take task_lock of each thread in leader's threadgroup individually in turn.
+ * Call holding cgroup_mutex and the group_rwsem of the leader. Will take
+ * task_lock of each thread in leader's threadgroup individually in turn.
*/
-int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
+static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
{
int retval, i, group_size;
struct cgroup_subsys *ss, *failed_ss = NULL;
- bool cancel_failed_ss = false;
/* guaranteed to be initialized later, but the compiler needs this */
- struct cgroup *oldcgrp = NULL;
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
@@ -2012,13 +2089,12 @@ int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
* step 0: in order to do expensive, possibly blocking operations for
* every thread, we cannot iterate the thread group list, since it needs
* rcu or tasklist locked. instead, build an array of all threads in the
- * group - threadgroup_fork_lock prevents new threads from appearing,
- * and if threads exit, this will just be an over-estimate.
+ * group - group_rwsem prevents new threads from appearing, and if
+ * threads exit, this will just be an over-estimate.
*/
group_size = get_nr_threads(leader);
/* flex_array supports very large thread-groups better than kmalloc. */
- group = flex_array_alloc(sizeof(struct task_struct *), group_size,
- GFP_KERNEL);
+ group = flex_array_alloc(sizeof(*tc), group_size, GFP_KERNEL);
if (!group)
return -ENOMEM;
/* pre-allocate to guarantee space while iterating in rcu read-side. */
@@ -2040,49 +2116,53 @@ int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
retval = -EAGAIN;
goto out_free_group_list;
}
- /* take a reference on each task in the group to go in the array. */
+
tsk = leader;
i = 0;
do {
+ struct task_and_cgroup ent;
+
+ /* @tsk either already exited or can't exit until the end */
+ if (tsk->flags & PF_EXITING)
+ continue;
+
/* as per above, nr_threads may decrease, but not increase. */
BUG_ON(i >= group_size);
- get_task_struct(tsk);
/*
* 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_ptr(group, i, tsk, GFP_ATOMIC);
+ 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;
+ retval = flex_array_put(group, i, &ent, GFP_ATOMIC);
BUG_ON(retval != 0);
i++;
} while_each_thread(leader, tsk);
/* 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;
+ if (!group_size)
+ goto out_free_group_list;
+
/*
* step 1: check that we can legitimately attach to the cgroup.
*/
for_each_subsys(root, ss) {
if (ss->can_attach) {
- retval = ss->can_attach(ss, cgrp, leader);
+ retval = ss->can_attach(ss, cgrp, &tset);
if (retval) {
failed_ss = ss;
goto out_cancel_attach;
}
}
- /* a callback to be run on every thread in the threadgroup. */
- if (ss->can_attach_task) {
- /* run on each task in the threadgroup. */
- for (i = 0; i < group_size; i++) {
- tsk = flex_array_get_ptr(group, i);
- retval = ss->can_attach_task(cgrp, tsk);
- if (retval) {
- failed_ss = ss;
- cancel_failed_ss = true;
- goto out_cancel_attach;
- }
- }
- }
}
/*
@@ -2091,72 +2171,36 @@ int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
*/
INIT_LIST_HEAD(&newcg_list);
for (i = 0; i < group_size; i++) {
- tsk = flex_array_get_ptr(group, i);
- /* nothing to do if this task is already in the cgroup */
- oldcgrp = task_cgroup_from_root(tsk, root);
- if (cgrp == oldcgrp)
- continue;
- /* get old css_set pointer */
- task_lock(tsk);
- if (tsk->flags & PF_EXITING) {
- /* ignore this task if it's going away */
- task_unlock(tsk);
- continue;
- }
- oldcg = tsk->cgroups;
- get_css_set(oldcg);
- task_unlock(tsk);
- /* see if the new one for us is already in the list? */
- if (css_set_check_fetched(cgrp, tsk, oldcg, &newcg_list)) {
- /* was already there, nothing to do. */
- put_css_set(oldcg);
- } else {
- /* we don't already have it. get new one. */
+ 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);
- put_css_set(oldcg);
if (retval)
goto out_list_teardown;
}
}
/*
- * step 3: now that we're guaranteed success wrt the css_sets, proceed
- * to move all tasks to the new cgroup, calling ss->attach_task for each
- * one along the way. there are no failure cases after here, so this is
- * the commit point.
+ * step 3: now that we're guaranteed success wrt the css_sets,
+ * proceed to move all tasks to the new cgroup. There are no
+ * failure cases after here, so this is the commit point.
*/
- for_each_subsys(root, ss) {
- if (ss->pre_attach)
- ss->pre_attach(cgrp);
- }
for (i = 0; i < group_size; i++) {
- tsk = flex_array_get_ptr(group, i);
- /* leave current thread as it is if it's already there */
- oldcgrp = task_cgroup_from_root(tsk, root);
- if (cgrp == oldcgrp)
- continue;
- /* if the thread is PF_EXITING, it can just get skipped. */
- retval = cgroup_task_migrate(cgrp, oldcgrp, tsk, true);
- if (retval == 0) {
- /* attach each task to each subsystem */
- for_each_subsys(root, ss) {
- if (ss->attach_task)
- ss->attach_task(cgrp, tsk);
- }
- } else {
- BUG_ON(retval != -ESRCH);
- }
+ tc = flex_array_get(group, i);
+ retval = cgroup_task_migrate(cgrp, tc->cgrp, tc->task, true);
+ BUG_ON(retval);
}
/* nothing is sensitive to fork() after this point. */
/*
- * step 4: do expensive, non-thread-specific subsystem callbacks.
- * TODO: if ever a subsystem needs to know the oldcgrp for each task
- * being moved, this call will need to be reworked to communicate that.
+ * step 4: do subsystem attach callbacks.
*/
for_each_subsys(root, ss) {
if (ss->attach)
- ss->attach(ss, cgrp, oldcgrp, leader);
+ ss->attach(ss, cgrp, &tset);
}
/*
@@ -2176,20 +2220,12 @@ out_cancel_attach:
/* same deal as in cgroup_attach_task */
if (retval) {
for_each_subsys(root, ss) {
- if (ss == failed_ss) {
- if (cancel_failed_ss && ss->cancel_attach)
- ss->cancel_attach(ss, cgrp, leader);
+ if (ss == failed_ss)
break;
- }
if (ss->cancel_attach)
- ss->cancel_attach(ss, cgrp, leader);
+ ss->cancel_attach(ss, cgrp, &tset);
}
}
- /* clean up the array of referenced threads in the group. */
- for (i = 0; i < group_size; i++) {
- tsk = flex_array_get_ptr(group, i);
- put_task_struct(tsk);
- }
out_free_group_list:
flex_array_free(group);
return retval;
@@ -2197,8 +2233,8 @@ out_free_group_list:
/*
* Find the task_struct of the task to attach by vpid and pass it along to the
- * function to attach either it or all tasks in its threadgroup. Will take
- * cgroup_mutex; may take task_lock of task.
+ * function to attach either it or all tasks in its threadgroup. Will lock
+ * cgroup_mutex and threadgroup; may take task_lock of task.
*/
static int attach_task_by_pid(struct cgroup *cgrp, u64 pid, bool threadgroup)
{
@@ -2225,13 +2261,7 @@ static int attach_task_by_pid(struct cgroup *cgrp, u64 pid, bool threadgroup)
* detect it later.
*/
tsk = tsk->group_leader;
- } else if (tsk->flags & PF_EXITING) {
- /* optimization for the single-task-only case */
- rcu_read_unlock();
- cgroup_unlock();
- return -ESRCH;
}
-
/*
* even if we're attaching all tasks in the thread group, we
* only need to check permissions on one of them.
@@ -2254,13 +2284,15 @@ static int attach_task_by_pid(struct cgroup *cgrp, u64 pid, bool threadgroup)
get_task_struct(tsk);
}
- if (threadgroup) {
- threadgroup_fork_write_lock(tsk);
+ threadgroup_lock(tsk);
+
+ if (threadgroup)
ret = cgroup_attach_proc(cgrp, tsk);
- threadgroup_fork_write_unlock(tsk);
- } else {
+ else
ret = cgroup_attach_task(cgrp, tsk);
- }
+
+ threadgroup_unlock(tsk);
+
put_task_struct(tsk);
cgroup_unlock();
return ret;
@@ -2311,7 +2343,9 @@ static int cgroup_release_agent_write(struct cgroup *cgrp, struct cftype *cft,
return -EINVAL;
if (!cgroup_lock_live_group(cgrp))
return -ENODEV;
+ mutex_lock(&cgroup_root_mutex);
strcpy(cgrp->root->release_agent_path, buffer);
+ mutex_unlock(&cgroup_root_mutex);
cgroup_unlock();
return 0;
}
@@ -2794,6 +2828,7 @@ static void cgroup_enable_task_cg_lists(void)
}
void cgroup_iter_start(struct cgroup *cgrp, struct cgroup_iter *it)
+ __acquires(css_set_lock)
{
/*
* The first time anyone tries to iterate across a cgroup,
@@ -2833,6 +2868,7 @@ struct task_struct *cgroup_iter_next(struct cgroup *cgrp,
}
void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it)
+ __releases(css_set_lock)
{
read_unlock(&css_set_lock);
}
@@ -4496,20 +4532,31 @@ static const struct file_operations proc_cgroupstats_operations = {
*
* A pointer to the shared css_set was automatically copied in
* fork.c by dup_task_struct(). However, we ignore that copy, since
- * it was not made under the protection of RCU or cgroup_mutex, so
- * might no longer be a valid cgroup pointer. cgroup_attach_task() might
- * have already changed current->cgroups, allowing the previously
- * referenced cgroup group to be removed and freed.
+ * it was not made under the protection of RCU, cgroup_mutex or
+ * threadgroup_change_begin(), so it might no longer be a valid
+ * cgroup pointer. cgroup_attach_task() might have already changed
+ * current->cgroups, allowing the previously referenced cgroup
+ * group to be removed and freed.
+ *
+ * Outside the pointer validity we also need to process the css_set
+ * inheritance between threadgoup_change_begin() and
+ * threadgoup_change_end(), this way there is no leak in any process
+ * wide migration performed by cgroup_attach_proc() that could otherwise
+ * miss a thread because it is too early or too late in the fork stage.
*
* At the point that cgroup_fork() is called, 'current' is the parent
* task, and the passed argument 'child' points to the child task.
*/
void cgroup_fork(struct task_struct *child)
{
- task_lock(current);
+ /*
+ * We don't need to task_lock() current because current->cgroups
+ * can't be changed concurrently here. The parent obviously hasn't
+ * exited and called cgroup_exit(), and we are synchronized against
+ * cgroup migration through threadgroup_change_begin().
+ */
child->cgroups = current->cgroups;
get_css_set(child->cgroups);
- task_unlock(current);
INIT_LIST_HEAD(&child->cg_list);
}
@@ -4551,10 +4598,19 @@ void cgroup_post_fork(struct task_struct *child)
{
if (use_task_css_set_links) {
write_lock(&css_set_lock);
- task_lock(child);
- if (list_empty(&child->cg_list))
+ if (list_empty(&child->cg_list)) {
+ /*
+ * It's safe to use child->cgroups without task_lock()
+ * here because we are protected through
+ * threadgroup_change_begin() against concurrent
+ * css_set change in cgroup_task_migrate(). Also
+ * the task can't exit at that point until
+ * wake_up_new_task() is called, so we are protected
+ * against cgroup_exit() setting child->cgroup to
+ * init_css_set.
+ */
list_add(&child->cg_list, &child->cgroups->tasks);
- task_unlock(child);
+ }
write_unlock(&css_set_lock);
}
}
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index e411a60..0e74805 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -159,13 +159,17 @@ static void freezer_destroy(struct cgroup_subsys *ss,
*/
static int freezer_can_attach(struct cgroup_subsys *ss,
struct cgroup *new_cgroup,
- struct task_struct *task)
+ struct cgroup_taskset *tset)
{
struct freezer *freezer;
+ struct task_struct *task;
/*
* Anything frozen can't move or be moved to/from.
*/
+ cgroup_taskset_for_each(task, new_cgroup, tset)
+ if (cgroup_freezing(task))
+ return -EBUSY;
freezer = cgroup_freezer(new_cgroup);
if (freezer->state != CGROUP_THAWED)
@@ -174,11 +178,6 @@ static int freezer_can_attach(struct cgroup_subsys *ss,
return 0;
}
-static int freezer_can_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
-{
- return cgroup_freezing(tsk) ? -EBUSY : 0;
-}
-
static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task)
{
struct freezer *freezer;
@@ -374,10 +373,5 @@ struct cgroup_subsys freezer_subsys = {
.populate = freezer_populate,
.subsys_id = freezer_subsys_id,
.can_attach = freezer_can_attach,
- .can_attach_task = freezer_can_attach_task,
- .pre_attach = NULL,
- .attach_task = NULL,
- .attach = NULL,
.fork = freezer_fork,
- .exit = NULL,
};
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 9fe58c4..42e5683 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1370,79 +1370,73 @@ static int fmeter_getrate(struct fmeter *fmp)
return val;
}
-/* Called by cgroups to determine if a cpuset is usable; cgroup_mutex held */
-static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cont,
- struct task_struct *tsk)
-{
- struct cpuset *cs = cgroup_cs(cont);
-
- if (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))
- return -ENOSPC;
-
- /*
- * Kthreads bound to specific cpus cannot be moved to a new cpuset; we
- * cannot change their cpu affinity and isolating such threads by their
- * set of allowed nodes is unnecessary. Thus, cpusets are not
- * applicable for such threads. This prevents checking for success of
- * set_cpus_allowed_ptr() on all attached tasks before cpus_allowed may
- * be changed.
- */
- if (tsk->flags & PF_THREAD_BOUND)
- return -EINVAL;
-
- return 0;
-}
-
-static int cpuset_can_attach_task(struct cgroup *cgrp, struct task_struct *task)
-{
- return security_task_setscheduler(task);
-}
-
/*
* Protected by cgroup_lock. The nodemasks must be stored globally because
- * dynamically allocating them is not allowed in pre_attach, and they must
- * persist among pre_attach, attach_task, and attach.
+ * dynamically allocating them is not allowed in can_attach, and they must
+ * persist until attach.
*/
static cpumask_var_t cpus_attach;
static nodemask_t cpuset_attach_nodemask_from;
static nodemask_t cpuset_attach_nodemask_to;
-/* Set-up work for before attaching each task. */
-static void cpuset_pre_attach(struct cgroup *cont)
+/* Called by cgroups to determine if a cpuset is usable; cgroup_mutex held */
+static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
+ struct cgroup_taskset *tset)
{
- struct cpuset *cs = cgroup_cs(cont);
+ struct cpuset *cs = cgroup_cs(cgrp);
+ struct task_struct *task;
+ int ret;
+
+ if (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))
+ return -ENOSPC;
+
+ cgroup_taskset_for_each(task, cgrp, tset) {
+ /*
+ * Kthreads bound to specific cpus cannot be moved to a new
+ * cpuset; we cannot change their cpu affinity and
+ * isolating such threads by their set of allowed nodes is
+ * unnecessary. Thus, cpusets are not applicable for such
+ * threads. This prevents checking for success of
+ * set_cpus_allowed_ptr() on all attached tasks before
+ * cpus_allowed may be changed.
+ */
+ if (task->flags & PF_THREAD_BOUND)
+ return -EINVAL;
+ if ((ret = security_task_setscheduler(task)))
+ return ret;
+ }
+ /* prepare for attach */
if (cs == &top_cpuset)
cpumask_copy(cpus_attach, cpu_possible_mask);
else
guarantee_online_cpus(cs, cpus_attach);
guarantee_online_mems(cs, &cpuset_attach_nodemask_to);
-}
-
-/* Per-thread attachment work. */
-static void cpuset_attach_task(struct cgroup *cont, struct task_struct *tsk)
-{
- int err;
- struct cpuset *cs = cgroup_cs(cont);
- /*
- * can_attach beforehand should guarantee that this doesn't fail.
- * TODO: have a better way to handle failure here
- */
- err = set_cpus_allowed_ptr(tsk, cpus_attach);
- WARN_ON_ONCE(err);
-
- cpuset_change_task_nodemask(tsk, &cpuset_attach_nodemask_to);
- cpuset_update_task_spread_flag(cs, tsk);
+ return 0;
}
-static void cpuset_attach(struct cgroup_subsys *ss, struct cgroup *cont,
- struct cgroup *oldcont, struct task_struct *tsk)
+static void cpuset_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
+ struct cgroup_taskset *tset)
{
struct mm_struct *mm;
- struct cpuset *cs = cgroup_cs(cont);
- struct cpuset *oldcs = cgroup_cs(oldcont);
+ struct task_struct *task;
+ struct task_struct *leader = cgroup_taskset_first(tset);
+ struct cgroup *oldcgrp = cgroup_taskset_cur_cgroup(tset);
+ struct cpuset *cs = cgroup_cs(cgrp);
+ struct cpuset *oldcs = cgroup_cs(oldcgrp);
+
+ cgroup_taskset_for_each(task, cgrp, tset) {
+ /*
+ * can_attach beforehand should guarantee that this doesn't
+ * fail. TODO: have a better way to handle failure here
+ */
+ WARN_ON_ONCE(set_cpus_allowed_ptr(task, cpus_attach));
+
+ cpuset_change_task_nodemask(task, &cpuset_attach_nodemask_to);
+ cpuset_update_task_spread_flag(cs, task);
+ }
/*
* Change mm, possibly for multiple threads in a threadgroup. This is
@@ -1450,7 +1444,7 @@ static void cpuset_attach(struct cgroup_subsys *ss, struct cgroup *cont,
*/
cpuset_attach_nodemask_from = oldcs->mems_allowed;
cpuset_attach_nodemask_to = cs->mems_allowed;
- mm = get_task_mm(tsk);
+ mm = get_task_mm(leader);
if (mm) {
mpol_rebind_mm(mm, &cpuset_attach_nodemask_to);
if (is_memory_migrate(cs))
@@ -1906,9 +1900,6 @@ struct cgroup_subsys cpuset_subsys = {
.create = cpuset_create,
.destroy = cpuset_destroy,
.can_attach = cpuset_can_attach,
- .can_attach_task = cpuset_can_attach_task,
- .pre_attach = cpuset_pre_attach,
- .attach_task = cpuset_attach_task,
.attach = cpuset_attach,
.populate = cpuset_populate,
.post_clone = cpuset_post_clone,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0e8457d..3b8e0ed 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7044,10 +7044,13 @@ static int __perf_cgroup_move(void *info)
return 0;
}
-static void
-perf_cgroup_attach_task(struct cgroup *cgrp, struct task_struct *task)
+static void perf_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
+ struct cgroup_taskset *tset)
{
- task_function_call(task, __perf_cgroup_move, task);
+ struct task_struct *task;
+
+ cgroup_taskset_for_each(task, cgrp, tset)
+ task_function_call(task, __perf_cgroup_move, task);
}
static void perf_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp,
@@ -7061,7 +7064,7 @@ static void perf_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp,
if (!(task->flags & PF_EXITING))
return;
- perf_cgroup_attach_task(cgrp, task);
+ task_function_call(task, __perf_cgroup_move, task);
}
struct cgroup_subsys perf_subsys = {
@@ -7070,6 +7073,6 @@ struct cgroup_subsys perf_subsys = {
.create = perf_cgroup_create,
.destroy = perf_cgroup_destroy,
.exit = perf_cgroup_exit,
- .attach_task = perf_cgroup_attach_task,
+ .attach = perf_cgroup_attach,
};
#endif /* CONFIG_CGROUP_PERF */
diff --git a/kernel/fork.c b/kernel/fork.c
index 8278086..d4ac9e3 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -972,7 +972,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
sched_autogroup_fork(sig);
#ifdef CONFIG_CGROUPS
- init_rwsem(&sig->threadgroup_fork_lock);
+ init_rwsem(&sig->group_rwsem);
#endif
sig->oom_adj = current->signal->oom_adj;
@@ -1157,7 +1157,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
p->io_context = NULL;
p->audit_context = NULL;
if (clone_flags & CLONE_THREAD)
- threadgroup_fork_read_lock(current);
+ threadgroup_change_begin(current);
cgroup_fork(p);
#ifdef CONFIG_NUMA
p->mempolicy = mpol_dup(p->mempolicy);
@@ -1372,7 +1372,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
proc_fork_connector(p);
cgroup_post_fork(p);
if (clone_flags & CLONE_THREAD)
- threadgroup_fork_read_unlock(current);
+ threadgroup_change_end(current);
perf_event_fork(p);
return p;
@@ -1407,7 +1407,7 @@ bad_fork_cleanup_policy:
bad_fork_cleanup_cgroup:
#endif
if (clone_flags & CLONE_THREAD)
- threadgroup_fork_read_unlock(current);
+ threadgroup_change_end(current);
cgroup_exit(p, cgroup_callbacks_done);
delayacct_tsk_free(p);
module_put(task_thread_info(p)->exec_domain->module);
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
index 34683ef..6d269cc 100644
--- a/kernel/res_counter.c
+++ b/kernel/res_counter.c
@@ -159,8 +159,7 @@ int res_counter_memparse_write_strategy(const char *buf,
return 0;
}
- /* FIXME - make memparse() take const char* args */
- *res = memparse((char *)buf, &end);
+ *res = memparse(buf, &end);
if (*end != '\0')
return -EINVAL;
diff --git a/kernel/sched.c b/kernel/sched.c
index 0e9344a..161184d 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -9127,24 +9127,31 @@ cpu_cgroup_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
sched_destroy_group(tg);
}
-static int
-cpu_cgroup_can_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
+static int cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
+ struct cgroup_taskset *tset)
{
+ struct task_struct *task;
+
+ cgroup_taskset_for_each(task, cgrp, tset) {
#ifdef CONFIG_RT_GROUP_SCHED
- if (!sched_rt_can_attach(cgroup_tg(cgrp), tsk))
- return -EINVAL;
+ if (!sched_rt_can_attach(cgroup_tg(cgrp), task))
+ return -EINVAL;
#else
- /* We don't support RT-tasks being in separate groups */
- if (tsk->sched_class != &fair_sched_class)
- return -EINVAL;
+ /* We don't support RT-tasks being in separate groups */
+ if (task->sched_class != &fair_sched_class)
+ return -EINVAL;
#endif
+ }
return 0;
}
-static void
-cpu_cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
+static void cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
+ struct cgroup_taskset *tset)
{
- sched_move_task(tsk);
+ struct task_struct *task;
+
+ cgroup_taskset_for_each(task, cgrp, tset)
+ sched_move_task(task);
}
static void
@@ -9480,8 +9487,8 @@ struct cgroup_subsys cpu_cgroup_subsys = {
.name = "cpu",
.create = cpu_cgroup_create,
.destroy = cpu_cgroup_destroy,
- .can_attach_task = cpu_cgroup_can_attach_task,
- .attach_task = cpu_cgroup_attach_task,
+ .can_attach = cpu_cgroup_can_attach,
+ .attach = cpu_cgroup_attach,
.exit = cpu_cgroup_exit,
.populate = cpu_cgroup_populate,
.subsys_id = cpu_cgroup_subsys_id,
diff --git a/kernel/signal.c b/kernel/signal.c
index b3f78d0..399c184 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2359,8 +2359,15 @@ void exit_signals(struct task_struct *tsk)
int group_stop = 0;
sigset_t unblocked;
+ /*
+ * @tsk is about to have PF_EXITING set - lock out users which
+ * expect stable threadgroup.
+ */
+ threadgroup_change_begin(tsk);
+
if (thread_group_empty(tsk) || signal_group_exit(tsk->signal)) {
tsk->flags |= PF_EXITING;
+ threadgroup_change_end(tsk);
return;
}
@@ -2370,6 +2377,9 @@ void exit_signals(struct task_struct *tsk)
* see wants_signal(), do_signal_stop().
*/
tsk->flags |= PF_EXITING;
+
+ threadgroup_change_end(tsk);
+
if (!signal_pending(tsk))
goto out;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6aff93c..81640e7 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5298,8 +5298,9 @@ static void mem_cgroup_clear_mc(void)
static int mem_cgroup_can_attach(struct cgroup_subsys *ss,
struct cgroup *cgroup,
- struct task_struct *p)
+ struct cgroup_taskset *tset)
{
+ struct task_struct *p = cgroup_taskset_first(tset);
int ret = 0;
struct mem_cgroup *memcg = mem_cgroup_from_cont(cgroup);
@@ -5337,7 +5338,7 @@ static int mem_cgroup_can_attach(struct cgroup_subsys *ss,
static void mem_cgroup_cancel_attach(struct cgroup_subsys *ss,
struct cgroup *cgroup,
- struct task_struct *p)
+ struct cgroup_taskset *tset)
{
mem_cgroup_clear_mc();
}
@@ -5454,9 +5455,9 @@ retry:
static void mem_cgroup_move_task(struct cgroup_subsys *ss,
struct cgroup *cont,
- struct cgroup *old_cont,
- struct task_struct *p)
+ struct cgroup_taskset *tset)
{
+ struct task_struct *p = cgroup_taskset_first(tset);
struct mm_struct *mm = get_task_mm(p);
if (mm) {
@@ -5471,19 +5472,18 @@ static void mem_cgroup_move_task(struct cgroup_subsys *ss,
#else /* !CONFIG_MMU */
static int mem_cgroup_can_attach(struct cgroup_subsys *ss,
struct cgroup *cgroup,
- struct task_struct *p)
+ struct cgroup_taskset *tset)
{
return 0;
}
static void mem_cgroup_cancel_attach(struct cgroup_subsys *ss,
struct cgroup *cgroup,
- struct task_struct *p)
+ struct cgroup_taskset *tset)
{
}
static void mem_cgroup_move_task(struct cgroup_subsys *ss,
struct cgroup *cont,
- struct cgroup *old_cont,
- struct task_struct *p)
+ struct cgroup_taskset *tset)
{
}
#endif
diff --git a/security/device_cgroup.c b/security/device_cgroup.c
index 4450fbe..8b5b5d8 100644
--- a/security/device_cgroup.c
+++ b/security/device_cgroup.c
@@ -62,11 +62,12 @@ static inline struct dev_cgroup *task_devcgroup(struct task_struct *task)
struct cgroup_subsys devices_subsys;
static int devcgroup_can_attach(struct cgroup_subsys *ss,
- struct cgroup *new_cgroup, struct task_struct *task)
+ struct cgroup *new_cgrp, struct cgroup_taskset *set)
{
- if (current != task && !capable(CAP_SYS_ADMIN))
- return -EPERM;
+ struct task_struct *task = cgroup_taskset_first(set);
+ if (current != task && !capable(CAP_SYS_ADMIN))
+ return -EPERM;
return 0;
}
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/