tasks: Add a count of task RCU users

Add a count of the number of RCU users (currently 1) of the task
struct so that we can later add the scheduler case and get rid of the
very subtle task_rcu_dereference(), and just use rcu_dereference().

As suggested by Oleg have the count overlap rcu_head so that no
additional space in task_struct is required.

Inspired-by: Linus Torvalds <torvalds@linux-foundation.org>
Inspired-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Chris Metcalf <cmetcalf@ezchip.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Kirill Tkhai <tkhai@yandex.ru>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Russell King - ARM Linux admin <linux@armlinux.org.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/87woebdplt.fsf_-_@x220.int.ebiederm.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

4 files changed, 14 insertions, 6 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index e2e91960d79f..8e43e54a02c7 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1147,7 +1147,10 @@ struct task_struct {
 
         struct tlbflush_unmap_batch     tlb_ubc;
 
-        struct rcu_head                 rcu;
+        union {
+                refcount_t              rcu_users;
+                struct rcu_head         rcu;
+        };
 
         /* Cache last used pipe for splice(): */
         struct pipe_inode_info          *splice_pipe;
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 3d90ed8f75f0..153a683646ac 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -120,6 +120,7 @@ static inline void put_task_struct(struct task_struct *t)
 }
 
 struct task_struct *task_rcu_dereference(struct task_struct **ptask);
+void put_task_struct_rcu_user(struct task_struct *task);
 
 #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT
 extern int arch_task_struct_size __read_mostly;
diff --git a/kernel/exit.c b/kernel/exit.c
index 22ab6a4bdc51..3bcaec2ea3ba 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -182,6 +182,11 @@ static void delayed_put_task_struct(struct rcu_head *rhp)
         put_task_struct(tsk);
 }
 
+void put_task_struct_rcu_user(struct task_struct *task)
+{
+        if (refcount_dec_and_test(&task->rcu_users))
+                call_rcu(&task->rcu, delayed_put_task_struct);
+}
 
 void release_task(struct task_struct *p)
 {
@@ -222,7 +227,7 @@ repeat:
 
         write_unlock_irq(&tasklist_lock);
         release_thread(p);
-        call_rcu(&p->rcu, delayed_put_task_struct);
+        put_task_struct_rcu_user(p);
 
         p = leader;
         if (unlikely(zap_leader))
diff --git a/kernel/fork.c b/kernel/fork.c
index 1d1cd06edbc1..7eefe338d7a2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -902,10 +902,9 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
         if (orig->cpus_ptr == &orig->cpus_mask)
                 tsk->cpus_ptr = &tsk->cpus_mask;
 
-        /*
-         * One for us, one for whoever does the "release_task()" (usually
-         * parent)
-         */
+        /* One for the user space visible state that goes away when reaped. */
+        refcount_set(&tsk->rcu_users, 1);
+        /* One for the rcu users, and one for the scheduler */
         refcount_set(&tsk->usage, 2);
 #ifdef CONFIG_BLK_DEV_IO_TRACE
         tsk->btrace_seq = 0;