netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: FUJITA Tomonori <tomof@acm.org>
To: open-iscsi@googlegroups.com
Cc: davem@davemloft.net, mchristi@redhat.com, netdev@vger.kernel.org,
	anilgv@broadcom.com, talm@broadcom.com, lusinsky@broadcom.com,
	uri@broadcom.com
Cc: fujita.tomonori@lab.ntt.co.jp
Subject: Re: [PATCH v3 2/2][BNX2]: Add iSCSI support to BNX2 devices.
Date: Sat, 8 Sep 2007 16:41:09 +0900	[thread overview]
Message-ID: <20070908084127G.tomof@acm.org> (raw)
In-Reply-To: <46E1D27F.2040701@cs.wisc.edu>

On Fri, 07 Sep 2007 17:36:47 -0500
Mike Christie <michaelc@cs.wisc.edu> wrote:

> > +/*
> > + * map SG list
> > + */
> > +static int bnx2i_map_sg(struct bnx2i_hba *hba, struct bnx2i_cmd *cmd)
> > +{
> > +	struct scsi_cmnd *sc = cmd->scsi_cmd;
> > +	struct iscsi_bd *bd = cmd->bd_tbl->bd_tbl;
> > +	struct scatterlist *sg;
> > +	int byte_count = 0;
> > +	int sg_frags;
> > +	int bd_count = 0;
> > +	int sg_count;
> > +	int sg_len;
> > +	u64 addr;
> > +	int i;
> > +
> > +	sg = sc->request_buffer;
> > +	sg_count = pci_map_sg(hba->pci_dev, sg, sc->use_sg,
> > +			      sc->sc_data_direction);

Can you use scsi_dma_map() here?


> > +	for (i = 0; i < sg_count; i++) {
> > +		sg_len = sg_dma_len(sg);
> > +		addr = sg_dma_address(sg);
> > +		if (sg_len > MAX_BD_LENGTH)
> > +			sg_frags = bnx2i_split_bd(cmd, addr, sg_len,
> > +						  bd_count);

Please use scsi_for_each_sg().

You can't directly access to use_sg, request_buffer, request_bufflen,
and resid in scsi_cmnd structure. Please use the scsi data accessors
in scsi_cmnd.h: scsi_sg_count, scsi_sglist, scsi_bufflen,
scsi_set_resid, and scsi_get_resid.


> If you call blk_queue_max_segment_size() in the slave_configure callout 
> you can limit the size of the segments that the block layer builds so 
> they are smaller than MAX_BD_LENGTH. However, I am not sure how useful 
> that is. I think DMA-API.txt states that the mapping code is ok to 
> merged mutliple sglists entries into one so I think that means that we 
> can still end up with an entry that is larger than MAX_BD_LENGTH. Not 
> sure if there is way to tell the pci/dma map_sg code to limit this too.

Yeah, iommu code ignores the lld limitations (the problem is that the
lld limitations are in request_queue and iommu code can't access to
request_queue). There is no way to tell iommu code about the lld
limitations.

  reply	other threads:[~2007-09-08  7:56 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <1188599815.5176.12.camel@dell>
2007-09-05 18:34 ` [PATCH v3 2/2][BNX2]: Add iSCSI support to BNX2 devices Mike Christie
2007-09-05 21:27   ` Anil Veerabhadrappa
2007-09-07 22:23     ` Mike Christie
2007-11-21 18:38       ` Anil Veerabhadrappa
2007-11-21 19:17         ` James Smart
     [not found]         ` <1195670296.8767.9.camel-opBMJL+S1+mb6IhXEaeG+wpgy58w7zIFpWgKQ6/u3Fg@public.gmane.org>
2007-11-27  4:15           ` Mike Christie
2007-11-28  0:44             ` Anil Veerabhadrappa
     [not found]               ` <1196210691.5980.20.camel-opBMJL+S1+mb6IhXEaeG+20Cxg0+/0ngpWgKQ6/u3Fg@public.gmane.org>
2007-11-28 20:06                 ` Mike Christie
2007-11-29  0:36                   ` Anil Veerabhadrappa
2007-09-08 11:59     ` Christoph Hellwig
2007-09-08 14:49       ` Michael Chan
2007-09-08 17:57         ` Anil Veerabhadrappa
2007-09-07 22:36 ` Mike Christie
2007-09-08  7:41   ` FUJITA Tomonori [this message]
2007-09-08 11:32     ` Jeff Garzik
2007-09-08 12:00       ` Christoph Hellwig
2007-09-09 15:05         ` FUJITA Tomonori
2007-09-25  8:39           ` Hannes Reinecke
2007-09-26  8:57             ` FUJITA Tomonori
2007-09-27  7:31               ` Jeff Garzik
2007-09-27  7:38                 ` Benjamin Herrenschmidt
2007-09-27  7:49                   ` Jeff Garzik
2007-09-27  8:12                     ` Benjamin Herrenschmidt
2007-09-27  8:22                       ` Jeff Garzik
2007-09-27  8:46                         ` FUJITA Tomonori
2007-09-27  8:06                 ` FUJITA Tomonori
2007-09-27  8:23                   ` Jeff Garzik

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20070908084127G.tomof@acm.org \
    --to=tomof@acm.org \
    --cc=anilgv@broadcom.com \
    --cc=davem@davemloft.net \
    --cc=lusinsky@broadcom.com \
    --cc=mchristi@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=open-iscsi@googlegroups.com \
    --cc=talm@broadcom.com \
    --cc=uri@broadcom.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).