sched, cgroup: replace signal_struct->group_rwsem with a global percpu_rwsem

The cgroup side of threadgroup locking uses signal_struct->group_rwsem
to synchronize against threadgroup changes.  This per-process rwsem
adds small overhead to thread creation, exit and exec paths, forces
cgroup code paths to do lock-verify-unlock-retry dance in a couple
places and makes it impossible to atomically perform operations across
multiple processes.

This patch replaces signal_struct->group_rwsem with a global
percpu_rwsem cgroup_threadgroup_rwsem which is cheaper on the reader
side and contained in cgroups proper.  This patch converts one-to-one.

This does make writer side heavier and lower the granularity; however,
cgroup process migration is a fairly cold path, we do want to optimize
thread operations over it and cgroup migration operations don't take
enough time for the lower granularity to matter.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>

2 files changed, 20 insertions, 61 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 980b1f52f39f..77578a169b8c 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -46,6 +46,7 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/rwsem.h>
+#include <linux/percpu-rwsem.h>
 #include <linux/string.h>
 #include <linux/sort.h>
 #include <linux/kmod.h>
@@ -103,6 +104,8 @@ static DEFINE_SPINLOCK(cgroup_idr_lock);
  */
 static DEFINE_SPINLOCK(release_agent_path_lock);
 
+struct percpu_rw_semaphore cgroup_threadgroup_rwsem;
+
 #define cgroup_assert_mutex_or_rcu_locked()                             \
         rcu_lockdep_assert(rcu_read_lock_held() ||                      \
                            lockdep_is_held(&cgroup_mutex),              \
@@ -848,48 +851,6 @@ static struct css_set *find_css_set(struct css_set *old_cset,
         return cset;
 }
 
-void cgroup_threadgroup_change_begin(struct task_struct *tsk)
-{
-        down_read(&tsk->signal->group_rwsem);
-}
-
-void cgroup_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
- * change ->group_leader/pid.  This is useful for cases where the threadgroup
- * needs to stay stable across blockable operations.
- *
- * fork and exit 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.
- *
- * de_thread() does threadgroup_change_{begin|end}() when a non-leader
- * sub-thread becomes a new leader.
- */
-static void threadgroup_lock(struct task_struct *tsk)
-{
-        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);
-}
-
 static struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root)
 {
         struct cgroup *root_cgrp = kf_root->kn->priv;
@@ -2095,9 +2056,9 @@ static void cgroup_task_migrate(struct cgroup *old_cgrp,
         lockdep_assert_held(&css_set_rwsem);
 
         /*
-         * 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.
+         * We are synchronized through cgroup_threadgroup_rwsem 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.
          */
         WARN_ON_ONCE(tsk->flags & PF_EXITING);
         old_cset = task_css_set(tsk);
@@ -2154,10 +2115,11 @@ static void cgroup_migrate_finish(struct list_head *preloaded_csets)
  * @src_cset and add it to @preloaded_csets, which should later be cleaned
  * up by cgroup_migrate_finish().
  *
- * This function may be called without holding threadgroup_lock even if the
- * target is a process.  Threads may be created and destroyed but as long
- * as cgroup_mutex is not dropped, no new css_set can be put into play and
- * the preloaded css_sets are guaranteed to cover all migrations.
+ * This function may be called without holding cgroup_threadgroup_rwsem
+ * even if the target is a process.  Threads may be created and destroyed
+ * but as long as cgroup_mutex is not dropped, no new css_set can be put
+ * into play and the preloaded css_sets are guaranteed to cover all
+ * migrations.
  */
 static void cgroup_migrate_add_src(struct css_set *src_cset,
                                    struct cgroup *dst_cgrp,
@@ -2260,7 +2222,7 @@ err:
  * @threadgroup: whether @leader points to the whole process or a single task
  *
  * Migrate a process or task denoted by @leader to @cgrp.  If migrating a
- * process, the caller must be holding threadgroup_lock of @leader.  The
+ * process, the caller must be holding cgroup_threadgroup_rwsem.  The
  * caller is also responsible for invoking cgroup_migrate_add_src() and
  * cgroup_migrate_prepare_dst() on the targets before invoking this
  * function and following up with cgroup_migrate_finish().
@@ -2388,7 +2350,7 @@ out_release_tset:
  * @leader: the task or the leader of the threadgroup to be attached
  * @threadgroup: attach the whole threadgroup?
  *
- * Call holding cgroup_mutex and threadgroup_lock of @leader.
+ * Call holding cgroup_mutex and cgroup_threadgroup_rwsem.
  */
 static int cgroup_attach_task(struct cgroup *dst_cgrp,
                               struct task_struct *leader, bool threadgroup)
@@ -2481,7 +2443,7 @@ retry_find_task:
         get_task_struct(tsk);
         rcu_read_unlock();
 
-        threadgroup_lock(tsk);
+        percpu_down_write(&cgroup_threadgroup_rwsem);
         if (threadgroup) {
                 if (!thread_group_leader(tsk)) {
                         /*
@@ -2491,7 +2453,7 @@ retry_find_task:
                          * try again; this is
                          * "double-double-toil-and-trouble-check locking".
                          */
-                        threadgroup_unlock(tsk);
+                        percpu_up_write(&cgroup_threadgroup_rwsem);
                         put_task_struct(tsk);
                         goto retry_find_task;
                 }
@@ -2499,7 +2461,7 @@ retry_find_task:
 
         ret = cgroup_attach_task(cgrp, tsk, threadgroup);
 
-        threadgroup_unlock(tsk);
+        percpu_up_write(&cgroup_threadgroup_rwsem);
 
         put_task_struct(tsk);
 out_unlock_cgroup:
@@ -2704,17 +2666,17 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
                                 goto out_finish;
                         last_task = task;
 
-                        threadgroup_lock(task);
+                        percpu_down_write(&cgroup_threadgroup_rwsem);
                         /* raced against de_thread() from another thread? */
                         if (!thread_group_leader(task)) {
-                                threadgroup_unlock(task);
+                                percpu_up_write(&cgroup_threadgroup_rwsem);
                                 put_task_struct(task);
                                 continue;
                         }
 
                         ret = cgroup_migrate(src_cset->dfl_cgrp, task, true);
 
-                        threadgroup_unlock(task);
+                        percpu_up_write(&cgroup_threadgroup_rwsem);
                         put_task_struct(task);
 
                         if (WARN(ret, "cgroup: failed to update controllers for the default hierarchy (%d), further operations may crash or hang\n", ret))
@@ -5032,6 +4994,7 @@ int __init cgroup_init(void)
         unsigned long key;
         int ssid, err;
 
+        BUG_ON(percpu_init_rwsem(&cgroup_threadgroup_rwsem));
         BUG_ON(cgroup_init_cftypes(NULL, cgroup_dfl_base_files));
         BUG_ON(cgroup_init_cftypes(NULL, cgroup_legacy_base_files));
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 03c1eaaa6ef5..9531275e12a9 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1144,10 +1144,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
         tty_audit_fork(sig);
         sched_autogroup_fork(sig);
 
-#ifdef CONFIG_CGROUPS
-        init_rwsem(&sig->group_rwsem);
-#endif
-
         sig->oom_score_adj = current->signal->oom_score_adj;
         sig->oom_score_adj_min = current->signal->oom_score_adj_min;