Merge branch 'for-3.3' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

* 'for-3.3' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (21 commits)
  cgroup: fix to allow mounting a hierarchy by name
  cgroup: move assignement out of condition in cgroup_attach_proc()
  cgroup: Remove task_lock() from cgroup_post_fork()
  cgroup: add sparse annotation to cgroup_iter_start() and cgroup_iter_end()
  cgroup: mark cgroup_rmdir_waitq and cgroup_attach_proc() as static
  cgroup: only need to check oldcgrp==newgrp once
  cgroup: remove redundant get/put of task struct
  cgroup: remove redundant get/put of old css_set from migrate
  cgroup: Remove unnecessary task_lock before fetching css_set on migration
  cgroup: Drop task_lock(parent) on cgroup_fork()
  cgroups: remove redundant get/put of css_set from css_set_check_fetched()
  resource cgroups: remove bogus cast
  cgroup: kill subsys->can_attach_task(), pre_attach() and attach_task()
  cgroup, cpuset: don't use ss->pre_attach()
  cgroup: don't use subsys->can_attach_task() or ->attach_task()
  cgroup: introduce cgroup_taskset and use it in subsys->can_attach(), cancel_attach() and attach()
  cgroup: improve old cgroup handling in cgroup_attach_proc()
  cgroup: always lock threadgroup during migration
  threadgroup: extend threadgroup_lock() to cover exit and exec
  threadgroup: rename signal->threadgroup_fork_lock to ->group_rwsem
  ...

Fix up conflict in kernel/cgroup.c due to commit e0197aae59e5: "cgroups:
fix a css_set not found bug in cgroup_attach_proc" that already
mentioned that the bug is fixed (differently) in Tejun's cgroup
patchset. This one, in other words.

3 files changed, 83 insertions, 30 deletions

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index a17becc36ca1..e9b602151caf 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 32574eef9394..9c66b1ada9d7 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 ad93e1ec8c65..f044f66018f2 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -637,13 +637,15 @@ 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) */
@@ -2394,29 +2396,62 @@ 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