linux-kernel - Re: [GIT PULL] killable rwsems for v4.7

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: Windows password security audit tool. GUI, reports in PDF.

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

Message-ID: <20160517110242.GV3193@twins.programming.kicks-ass.net>
Date:	Tue, 17 May 2016 13:02:42 +0200
From:	Peter Zijlstra <peterz@...radead.org>
To:	Linus Torvalds <torvalds@...ux-foundation.org>
Cc:	Ingo Molnar <mingo@...nel.org>, Michal Hocko <mhocko@...nel.org>,
	Al Viro <viro@...iv.linux.org.uk>,
	Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
	Thomas Gleixner <tglx@...utronix.de>,
	Andrew Morton <akpm@...ux-foundation.org>
Subject: Re: [GIT PULL] killable rwsems for v4.7

On Mon, May 16, 2016 at 01:32:28PM -0700, Linus Torvalds wrote:
> On Mon, May 16, 2016 at 7:55 AM, Ingo Molnar <mingo@...nel.org> wrote:
> >
> > This tree, by Michal Hocko, implements down_write_killable(). The main usecase
> > will be to update mm_sem usage sites to use this new API,
> 
> Hmm. Is somebody (Michal?) looking at down_read_killable() too?
> 
> The VFS layer will want it with the pending parallel lookup code - the
> inode semaphore is being converted to a rwsem, and there's a couple of
> "killable" users.. The first step actually just wants to the exclusive
> case (ie the write case that this adds), but I think the readdir code
> could really use a reading version too..

Something roughly like so.

Completely untested etc..

---
 kernel/locking/rwsem-spinlock.c | 28 +++++++++++++++++++++++-----
 kernel/locking/rwsem-xadd.c     | 28 +++++++++++++++++++++++++---
 2 files changed, 48 insertions(+), 8 deletions(-)

diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c
index 1591f6b3539f..d66325970248 100644
--- a/kernel/locking/rwsem-spinlock.c
+++ b/kernel/locking/rwsem-spinlock.c
@@ -125,7 +125,7 @@ __rwsem_wake_one_writer(struct rw_semaphore *sem)
 /*
  * get a read lock on the semaphore
  */
-void __sched __down_read(struct rw_semaphore *sem)
+int __sched __down_read_common(struct rw_semaphore *sem, int state)
 {
 	struct rwsem_waiter waiter;
 	struct task_struct *tsk;
@@ -137,11 +137,11 @@ void __sched __down_read(struct rw_semaphore *sem)
 		/* granted */
 		sem->count++;
 		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-		goto out;
+		return 0;
 	}
 
 	tsk = current;
-	set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+	set_task_state(tsk, state);
 
 	/* set up my own style of waitqueue */
 	waiter.task = tsk;
@@ -155,6 +155,8 @@ void __sched __down_read(struct rw_semaphore *sem)
 
 	/* wait to be given the lock */
 	for (;;) {
+		if (signal_pending_state(state, current))
+			goto out_nolock;
 		if (!waiter.task)
 			break;
 		schedule();
@@ -162,8 +164,24 @@ void __sched __down_read(struct rw_semaphore *sem)
 	}
 
 	__set_task_state(tsk, TASK_RUNNING);
- out:
-	;
+	return 0;
+
+out_nolock:
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
+	if (waiter.task)
+		list_del(&waiter.list);
+	else
+		sem->count--;
+	if (!list_empty(&sem->wait_list))
+		__rwsem_do_wake(sem, 1);
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+	return -EINTR;
+}
+
+void __sched __down_read(struct rw_semaphore *sem)
+{
+	__down_read_common(sem, TASK_UNINTERRUPTIBLE);
 }
 
 /*
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index 09e30c6225e5..4f7b1fb1f127 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -210,8 +210,8 @@ __rwsem_do_wake(struct rw_semaphore *sem, enum rwsem_wake_type wake_type)
 /*
  * Wait for the read lock to be granted
  */
-__visible
-struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
+static inline struct rw_semaphore *
+rwsem_down_read_failed_common(struct rw_semaphore *sem, int state)
 {
 	long count, adjustment = -RWSEM_ACTIVE_READ_BIAS;
 	struct rwsem_waiter waiter;
@@ -244,7 +244,9 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
 
 	/* wait to be given the lock */
 	while (true) {
-		set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+		set_task_state(tsk, state);
+		if (signal_pending_state(state, current))
+			goto out_nolock;
 		if (!waiter.task)
 			break;
 		schedule();
@@ -252,6 +254,26 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
 
 	__set_task_state(tsk, TASK_RUNNING);
 	return sem;
+
+out_nolock:
+	raw_spin_lock_irq(&sem->wait_lock);
+	if (waiter.task != NULL)
+		list_del(&waiter.list);
+	else
+		rwsem_atomic_update(-RWSEM_ACTIVE_READ_BIAS, sem);
+	if (list_empty(&sem->wait_list))
+		rwsem_atomic_update(-RWSEM_WAITING_BIAS, sem);
+	else
+		__rwsem_do_wake(sem, RWSEM_WAKE_ANY);
+	raw_spin_unlock_irq(&sem->wait_lock);
+
+	return ERR_PTR(-EINTR);
+}
+
+__visible struct rw_semaphore * __sched
+rwsem_down_read_failed(struct rw_semaphore *sem)
+{
+	return rwsem_down_read_failed_common(sem, TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL(rwsem_down_read_failed);