Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Thu, 23 Jan 2020 10:36:04 +0100
From:   Peter Zijlstra <peterz@infradead.org>
To:     Marco Elver <elver@google.com>
Cc:     Qian Cai <cai@lca.pw>, Will Deacon <will@kernel.org>,
        mingo@redhat.com, linux-kernel@vger.kernel.org
Subject: Re: [PATCH] locking/osq_lock: fix a data race in osq_wait_next
Message-ID: <20200123093604.GT14914@hirez.programming.kicks-ass.net>
References: <20200122165938.GA16974@willie-the-truck>
 <A5114711-B8DE-48DA-AFD0-62128AC08270@lca.pw>
 <20200122223851.GA45602@google.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=iso-8859-1
Content-Disposition: inline
Content-Transfer-Encoding: 8bit
In-Reply-To: <20200122223851.GA45602@google.com>
User-Agent: Mutt/1.10.1 (2018-07-13)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Wed, Jan 22, 2020 at 11:38:51PM +0100, Marco Elver wrote:

> If possible, decode and get the line numbers. I have observed a data
> race in osq_lock before, however, this is the only one I have recently
> seen in osq_lock:
> 
> read to 0xffff88812c12d3d4 of 4 bytes by task 23304 on cpu 0:
> ?osq_lock+0x170/0x2f0 kernel/locking/osq_lock.c:143
> 
> 	while (!READ_ONCE(node->locked)) {
> 		/*
> 		 * If we need to reschedule bail... so we can block.
> 		 * Use vcpu_is_preempted() to avoid waiting for a preempted
> 		 * lock holder:
> 		 */
> -->		if (need_resched() || vcpu_is_preempted(node_cpu(node->prev)))
> 			goto unqueue;
> 
> 		cpu_relax();
> 	}
> 
> where
> 
> 	static inline int node_cpu(struct optimistic_spin_node *node)
> 	{
> -->		return node->cpu - 1;
> 	}
> 
> 
> write to 0xffff88812c12d3d4 of 4 bytes by task 23334 on cpu 1:
>  osq_lock+0x89/0x2f0 kernel/locking/osq_lock.c:99
> 
> 	bool osq_lock(struct optimistic_spin_queue *lock)
> 	{
> 		struct optimistic_spin_node *node = this_cpu_ptr(&osq_node);
> 		struct optimistic_spin_node *prev, *next;
> 		int curr = encode_cpu(smp_processor_id());
> 		int old;
> 
> 		node->locked = 0;
> 		node->next = NULL;
> -->		node->cpu = curr;
> 

Yeah, that's impossible. This store happens before the node is
published, so no matter how the load in node_cpu() is shattered, it must
observe the right value.