summaryrefslogtreecommitdiffstats
path: root/include/linux/sched.h
diff options
context:
space:
mode:
authorTejun Heo <tj@kernel.org>2011-12-12 18:12:21 -0800
committerTejun Heo <tj@kernel.org>2011-12-12 18:12:21 -0800
commit77e4ef99d1c596a31747668e5fd837f77b6349b6 (patch)
treeb9dcc8d73f9febf6a18edc0b2efa3ecddc2a7a35 /include/linux/sched.h
parent257058ae2b971646b96ab3a15605ac69186e562a (diff)
downloadop-kernel-dev-77e4ef99d1c596a31747668e5fd837f77b6349b6.zip
op-kernel-dev-77e4ef99d1c596a31747668e5fd837f77b6349b6.tar.gz
threadgroup: extend threadgroup_lock() to cover exit and exec
threadgroup_lock() protected only protected against new addition to the threadgroup, which was inherently somewhat incomplete and problematic for its only user cgroup. On-going migration could race against exec and exit leading to interesting problems - the symmetry between various attach methods, task exiting during method execution, ->exit() racing against attach methods, migrating task switching basic properties during exec and so on. This patch extends threadgroup_lock() such that it protects against all three threadgroup altering operations - fork, exit and exec. For exit, threadgroup_change_begin/end() calls are added to exit_signals around assertion of PF_EXITING. For exec, threadgroup_[un]lock() are updated to also grab and release cred_guard_mutex. With this change, threadgroup_lock() guarantees that the target threadgroup will remain stable - no new task will be added, no new PF_EXITING will be set and exec won't happen. The next patch will update cgroup so that it can take full advantage of this change. -v2: beefed up comment as suggested by Frederic. -v3: narrowed scope of protection in exit path as suggested by Frederic. Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Paul Menage <paul@paulmenage.org> Cc: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'include/linux/sched.h')
-rw-r--r--include/linux/sched.h47
1 files changed, 41 insertions, 6 deletions
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8cd5232..c0c5876 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -635,11 +635,13 @@ struct signal_struct {
#endif
#ifdef CONFIG_CGROUPS
/*
- * The group_rwsem 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 group_rwsem;
#endif
@@ -2371,7 +2373,6 @@ static inline void unlock_task_sighand(struct task_struct *tsk,
spin_unlock_irqrestore(&tsk->sighand->siglock, *flags);
}
-/* See the declaration of group_rwsem in signal_struct. */
#ifdef CONFIG_CGROUPS
static inline void threadgroup_change_begin(struct task_struct *tsk)
{
@@ -2381,13 +2382,47 @@ static inline void threadgroup_change_end(struct task_struct *tsk)
{
up_read(&tsk->signal->group_rwsem);
}
+
+/**
+ * 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)
{
+ /*
+ * 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);
}
+
+/**
+ * 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->group_rwsem);
+ mutex_unlock(&tsk->signal->cred_guard_mutex);
}
#else
static inline void threadgroup_change_begin(struct task_struct *tsk) {}
OpenPOWER on IntegriCloud