From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Nicholas A. Bellinger" Subject: Re: [PATCH 06/11] mpt2sas: Convert to host_lock less w/ interrupts disabled externally Date: Thu, 18 Nov 2010 15:51:59 -0800 Message-ID: <1290124319.31890.169.camel@haakon2.linux-iscsi.org> References: <1290032349-4959-1-git-send-email-nab@linux-iscsi.org> <4CE4FCB8.20608@panasas.com> <1290121071.31890.135.camel@haakon2.linux-iscsi.org> <4CE5B306.1060203@garzik.org> Mime-Version: 1.0 Content-Type: text/plain Content-Transfer-Encoding: 7bit Return-path: Received: from mail.linux-iscsi.org ([67.23.28.174]:47428 "EHLO linux-iscsi.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S933080Ab0KRX5X (ORCPT ); Thu, 18 Nov 2010 18:57:23 -0500 In-Reply-To: <4CE5B306.1060203@garzik.org> Sender: linux-scsi-owner@vger.kernel.org List-Id: linux-scsi@vger.kernel.org To: Jeff Garzik Cc: Boaz Harrosh , linux-scsi , James Bottomley , Christoph Hellwig , Mike Christie , Vasu Dev , Tejun Heo , MPTFusionLinux , "Kashyap, Desai" , Tim Chen On Thu, 2010-11-18 at 18:13 -0500, Jeff Garzik wrote: > On 11/18/2010 05:57 PM, Nicholas A. Bellinger wrote: > > > > > > On Thu, 2010-11-18 at 12:15 +0200, Boaz Harrosh wrote: > >> On 11/18/2010 12:19 AM, Nicholas A. Bellinger wrote: > >>> From: Nicholas Bellinger > >>> > >>> This patch converts the mpt2sas driver to run in host_lock less mode > >>> with the new IRQ_DISABLE_SCSI_QCMD() that disables interrupts while > >>> calling ->queuecommand() dispatch > >>> > >>> Signed-off-by: Nicholas A. Bellinger > >>> --- > >>> drivers/scsi/mpt2sas/mpt2sas_scsih.c | 6 +++--- > >>> 1 files changed, 3 insertions(+), 3 deletions(-) > >>> > >>> diff --git a/drivers/scsi/mpt2sas/mpt2sas_scsih.c b/drivers/scsi/mpt2sas/mpt2sas_scsih.c > >>> index 1a96a00..e564fe7 100644 > >>> --- a/drivers/scsi/mpt2sas/mpt2sas_scsih.c > >>> +++ b/drivers/scsi/mpt2sas/mpt2sas_scsih.c > >>> @@ -3304,7 +3304,7 @@ _scsih_eedp_error_handling(struct scsi_cmnd *scmd, u16 ioc_status) > >>> } > >>> > >>> /** > >>> - * _scsih_qcmd - main scsi request entry point > >>> + * _scsih_qcmd_irq_disable - main scsi request entry point > >>> * @scmd: pointer to scsi command object > >>> * @done: function pointer to be invoked on completion > >>> * > >>> @@ -3315,7 +3315,7 @@ _scsih_eedp_error_handling(struct scsi_cmnd *scmd, u16 ioc_status) > >>> * SCSI_MLQUEUE_HOST_BUSY if the entire host queue is full > >>> */ > >>> static int > >>> -_scsih_qcmd_lck(struct scsi_cmnd *scmd, void (*done)(struct scsi_cmnd *)) > >>> +_scsih_qcmd_irq_disable(struct scsi_cmnd *scmd, void (*done)(struct scsi_cmnd *)) > >>> { > >>> struct MPT2SAS_ADAPTER *ioc = shost_priv(scmd->device->host); > >>> struct MPT2SAS_DEVICE *sas_device_priv_data; > >>> @@ -3441,7 +3441,7 @@ _scsih_qcmd_lck(struct scsi_cmnd *scmd, void (*done)(struct scsi_cmnd *)) > >>> return SCSI_MLQUEUE_HOST_BUSY; > >>> } > >>> > >>> -static DEF_SCSI_QCMD(_scsih_qcmd) > >>> +static IRQ_DISABLE_SCSI_QCMD(_scsih_qcmd) > >>> > >> > >> How can this (and other in the patchset) can be correct? I mean I expect > >> that if you remove the lock,xx_qcmd_lck,unlock then inside the xx_qcmd_lck > >> there was an unlock,do123,lock and that driver was effectively running lockless > >> before. (like in iscsi). But here this is new behaviour. If it is correct > >> I would like to see a statement from you that: > >> "I have audited this driver, and all shared resources are protected by > >> XYZ so ..." > >> > >> Otherwise how can I know this is correct? I have never audited this driver myself > >> > > > > So for this specific mpt2sas case, Vasu Dev had been testing the > > lock_less case w/o disabling interrupts for his original > > SHT->unlocked_qcmd=1 patch, and from his comments this mode was stable > > during his JBOD lock_less small block IOP performance test. > > Test results are not the same as reviewing and understanding the locking > in the driver, and adjusting the code accordingly... Fair enough.. > > _scsih_qcmd_lck() seems to rely on per-device and per-host data not > changing, which might seem to imply that the driver is secretly using > the SCSI host_lock to guarantee access to members such as > ioc->ioc_link_reset_in_progress or sas_target_priv_data->tm_busy. > > These accesses appear racy in both lock-free and local_irq_save() > configurations from my naive reading, though I do see additional locking > inside mpt2sas_base_get_smid_scsiio() > Mmmm, so in that case I will go ahead and revert this mpt2sas patch in lock_less-LLDs-for-38-v2 until this can be addressed by the LSI folks, or by other folks who have an specific interest in mpt2sas being able to run in lock_less mode for .38 code (Tim and Vasu..?) Also, mpt2sas and message/fusion transport handlers are similar enough that there are some likely issues there as well. Thus far this other patch to drivers/message/fusion/mptscsih.c has been stable in VMW guest in my development testing, but this will need to be audited for lock_less as well. --nab