From mboxrd@z Thu Jan  1 00:00:00 1970
From: David Miller <davem@davemloft.net>
Subject: Re: [PATCH 3/4] sparc64: convert spinlock_t to raw_spinlock_t in
 mmu_context_t
Date: Tue, 04 Mar 2014 15:01:00 -0500 (EST)
Message-ID: <20140304.150100.26024134985698152.davem@davemloft.net>
References: <52FB65AC.4000808@oracle.com>
	<268891392209126@web5h.yandex.ru>
	<53042ACA.6060907@oracle.com>
Mime-Version: 1.0
Content-Type: Text/Plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Cc: tkhai@yandex.ru, linux-rt-users@vger.kernel.org,
	sparclinux@vger.kernel.org, bigeasy@linutronix.de
To: allen.pais@oracle.com
Return-path: <sparclinux-owner@vger.kernel.org>
In-Reply-To: <53042ACA.6060907@oracle.com>
Sender: sparclinux-owner@vger.kernel.org
List-Id: linux-rt-users.vger.kernel.org

From: Allen Pais <allen.pais@oracle.com>
Date: Wed, 19 Feb 2014 09:23:46 +0530

>  I realized locking in tsb is very tricky. My attempts to try and get hackbench run
> without causing a stall failed. So here's what I tried to fix it, am not sure if it's
> an appropriate fix, I would love to get comments. I have tested this fix for over 24 hours
> with hackbench and dd, the system did not stall :)

If using a local lock fixes your problem, it just means we're being
preempted during flush_tsb_user() which is absolutely not allowed.

The batch is a per-cpu object, and must be forcibly flushed if we
preempt.