linux-kernel - [PATCH v2 1/4] task: Add a count of task rcu users

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-ID: <87woebdplt.fsf_-_@x220.int.ebiederm.org>
Date:   Sat, 14 Sep 2019 07:33:34 -0500
From:   ebiederm@...ssion.com (Eric W. Biederman)
To:     Peter Zijlstra <peterz@...radead.org>
Cc:     Oleg Nesterov <oleg@...hat.com>,
        Russell King - ARM Linux admin <linux@...linux.org.uk>,
        Chris Metcalf <cmetcalf@...hip.com>,
        Christoph Lameter <cl@...ux.com>,
        Kirill Tkhai <tkhai@...dex.ru>, Mike Galbraith <efault@....de>,
        Thomas Gleixner <tglx@...utronix.de>,
        Ingo Molnar <mingo@...nel.org>,
        Linux List Kernel Mailing <linux-kernel@...r.kernel.org>,
        Davidlohr Bueso <dave@...olabs.net>,
        "Paul E. McKenney" <paulmck@...nel.org>,
        Linus Torvalds <torvalds@...ux-foundation.org>
Subject: [PATCH v2 1/4] task: 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@...ux-foundation.org>
Inspired-by: Oleg Nesterov <oleg@...hat.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@...ssion.com>
---
 include/linux/sched.h      | 5 ++++-
 include/linux/sched/task.h | 1 +
 kernel/exit.c              | 7 ++++++-
 kernel/fork.c              | 7 +++----
 4 files changed, 14 insertions(+), 6 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9f51932bd543..99a4518b9b17 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1142,7 +1142,10 @@ 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 0497091e40c1..4c44c37236b2 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -116,6 +116,7 @@ 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 5b4a5dcce8f8..2e259286f4e7 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 @@ void release_task(struct task_struct *p)
 
 	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 2852d0e76ea3..9f04741d5c70 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -900,10 +900,9 @@ 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;
-- 
2.21.0.dirty