From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from zrtps0kp.nortelnetworks.com ([47.140.192.56]) by canuck.infradead.org with esmtp (Exim 4.42 #1 (Red Hat Linux)) id 1C5TPj-0006Gf-WA for linux-mtd@lists.infradead.org; Thu, 09 Sep 2004 14:12:57 -0400 To: David Woodhouse References: <1093426720.3777.1480.camel@imladris.demon.co.uk> <1093431210.3777.1535.camel@imladris.demon.co.uk> From: "Linh Dang" Date: Thu, 09 Sep 2004 14:12:19 -0400 In-Reply-To: <1093431210.3777.1535.camel@imladris.demon.co.uk> (David Woodhouse's message of "Wed, 25 Aug 2004 11:53:30 +0100") Message-ID: MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Sender: "Linh Dang" Cc: linux-mtd@lists.infradead.org Subject: Hi Latency in do_read_onechip (was Re: Bottom halves being disabled) List-Id: Linux MTD discussion mailing list List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Hi David, On our system, we have some slow AMD nor flash. The line map_copy_from(map, buf, adr, len); in do_read_onechip (in cfi_cmdset_0002.c) is called while holding a spin_lock (chip->mutex). This triggers 450usec non-preemptible periods on our system. 1. Is there any plan to fix this? 2. Is it safe to replace the spin_lock with a semaphore? 3. while mtd has to lock softirq? Thanx -- Linh Dang