From: maxg@mellanox.com (Max Gurtovoy)
Subject: [PATCH 07/17] nvme-fc: use nr_phys_segments to determine existence of sgl
Date: Thu, 14 Mar 2019 11:57:55 +0200 [thread overview]
Message-ID: <a488077e-d68e-a388-4d45-5b966f01f96e@mellanox.com> (raw)
In-Reply-To: <20190313175510.20725-8-hch@lst.de>
On 3/13/2019 7:55 PM, Christoph Hellwig wrote:
> From: James Smart <jsmart2021 at gmail.com>
>
> For some nvme command, when issued by the nvme core layer, there
> is an internal buffer which can cause blk_rq_payload_bytes() to
> return a non-zero value yet there is no actual/real command payload
> and sg list. An example is the WRITE ZEROES command.
>
> To address this, when making choices on whether to dma map an sgl,
> use blk_rq_nr_phys_segments() instead of blk_rq_payload_bytes().
> When there is a sgl, blk_rq_payload_bytes() will return the amount
> of data to be transferred by the sgl.
>
> Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni at wdc.com>
> Signed-off-by: James Smart <jsmart2021 at gmail.com>
> Signed-off-by: Christoph Hellwig <hch at lst.de>
I guess we'll need it for all transport.
I saw that pci is covered, RDMA isn't.
Also IMO tcp should be fixed (didn't dive into it yet, just high level
check for blk_rq_payload_bytes).
may we should have a core function for it to reduce code duplication.
next prev parent reply other threads:[~2019-03-14 9:57 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-03-13 17:54 [PATCHBOMB] nvme fixes for 5.1 Christoph Hellwig
2019-03-13 17:54 ` [PATCH 01/17] nvme: add get-feature to admin cmds tracer Christoph Hellwig
2019-03-13 17:54 ` [PATCH 02/17] nvme: don't warn on block content change effects Christoph Hellwig
2019-03-13 17:54 ` [PATCH 03/17] nvme-trace: fix cdw10 buffer overrun Christoph Hellwig
2019-03-13 17:54 ` [PATCH 04/17] nvme: put ns_head ref if namespace fails allocation Christoph Hellwig
2019-03-13 17:54 ` [PATCH 05/17] nvme: update comment to make the code easier to read Christoph Hellwig
2019-03-13 17:54 ` [PATCH 06/17] nvme-loop: init nvmet_ctrl fatal_err_work when allocate Christoph Hellwig
2019-03-13 17:55 ` [PATCH 07/17] nvme-fc: use nr_phys_segments to determine existence of sgl Christoph Hellwig
2019-03-14 9:57 ` Max Gurtovoy [this message]
2019-03-14 21:43 ` Sagi Grimberg
2019-03-13 17:55 ` [PATCH 08/17] nvme-fc: fix numa_node when dev is null Christoph Hellwig
2019-03-13 17:55 ` [PATCH 09/17] nvme-fc: reject reconnect if io queue count is reduced to zero Christoph Hellwig
2019-03-13 17:55 ` [PATCH 10/17] nvmet-fc: fix issues with targetport assoc_list list walking Christoph Hellwig
2019-03-13 18:53 ` James Smart
2019-03-13 18:58 ` Jens Axboe
2019-03-13 17:55 ` [PATCH 11/17] nvmet-fc: bring Disconnect into compliance with FC-NVME spec Christoph Hellwig
2019-03-13 17:55 ` [PATCH 12/17] nvme: disable Write Zeroes for qemu controllers Christoph Hellwig
2019-03-13 17:55 ` [PATCH 13/17] nvme: remove nvme_ns_config_oncs Christoph Hellwig
2019-03-13 17:55 ` [PATCH 14/17] nvme: add proper discard setup for the multipath device Christoph Hellwig
2019-03-13 17:55 ` [PATCH 15/17] nvme: add proper write zeroes " Christoph Hellwig
2019-03-13 17:55 ` [PATCH 16/17] nvmet: ignore EOPNOTSUPP for discard Christoph Hellwig
2019-03-13 17:55 ` [PATCH 17/17] nvme-tcp: support C2HData with SUCCESS flag Christoph Hellwig
2019-03-13 19:12 ` Sagi Grimberg
2019-03-13 19:14 ` Sagi Grimberg
2019-03-13 18:06 ` [PATCHBOMB] nvme fixes for 5.1 Jens Axboe
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=a488077e-d68e-a388-4d45-5b966f01f96e@mellanox.com \
--to=maxg@mellanox.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).