From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757422AbaISQeh (ORCPT ); Fri, 19 Sep 2014 12:34:37 -0400 Received: from mail-qa0-f52.google.com ([209.85.216.52]:32886 "EHLO mail-qa0-f52.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756107AbaISQef (ORCPT ); Fri, 19 Sep 2014 12:34:35 -0400 MIME-Version: 1.0 In-Reply-To: <20140919082552.GH8793@agordeev.usersys.redhat.com> References: <20140919082552.GH8793@agordeev.usersys.redhat.com> Date: Fri, 19 Sep 2014 09:34:34 -0700 Message-ID: Subject: Re: [PATCH v3 6/5] AHCI: Do not read HOST_IRQ_STAT register in multi-MSI mode From: Dan Williams To: Alexander Gordeev Cc: Linux Kernel Mailing List , "IDE/ATA development list" , "Jiang, Dave" Content-Type: text/plain; charset=UTF-8 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, Sep 19, 2014 at 1:25 AM, Alexander Gordeev wrote: > As described in AHCI v1.0 specification chapter 10.6.2.2 > "Multiple MSI Based Messages" generation of interrupts > is not controlled through the HOST_IRQ_STAT register. > > Considering MMIO access is expensive remove unnecessary > reading and writing of HOST_IRQ_STAT register. > > Further, serializing access to the host data is no longer > needed and the interrupt service routine can avoid competing > on the host lock. > > Signed-off-by: Alexander Gordeev > Suggested-by: "Jiang, Dave" > Cc: linux-ide@vger.kernel.org > --- > drivers/ata/ahci.h | 1 + > drivers/ata/libahci.c | 54 ++++++++------------------------------------------- > 2 files changed, 9 insertions(+), 46 deletions(-) > > diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h > index c12f590..b8e117a 100644 > --- a/drivers/ata/ahci.h > +++ b/drivers/ata/ahci.h > @@ -305,6 +305,7 @@ struct ahci_port_priv { > unsigned int ncq_saw_dmas:1; > unsigned int ncq_saw_sdb:1; > u32 intr_status; /* interrupts to handle */ > + spinlock_t intr_lock; /* protects intr_status */ Why introduce a new lock? Can't we switch to per-ata port locking rather than ata_host locking?