public inbox for linux-nfs@vger.kernel.org
 help / color / mirror / Atom feed
From: Christoph Hellwig <hch@lst.de>
To: Chuck Lever <cel@kernel.org>
Cc: Jason Gunthorpe <jgg@nvidia.com>,
	Leon Romanovsky <leon@kernel.org>, Christoph Hellwig <hch@lst.de>,
	NeilBrown <neilb@ownmail.net>, Jeff Layton <jlayton@kernel.org>,
	Olga Kornievskaia <okorniev@redhat.com>,
	Dai Ngo <dai.ngo@oracle.com>, Tom Talpey <tom@talpey.com>,
	linux-rdma@vger.kernel.org, linux-nfs@vger.kernel.org,
	Chuck Lever <chuck.lever@oracle.com>
Subject: Re: [PATCH v2 3/4] RDMA/core: add MR support for bvec-based RDMA operations
Date: Wed, 21 Jan 2026 10:05:08 +0100	[thread overview]
Message-ID: <20260121090508.GE16458@lst.de> (raw)
In-Reply-To: <20260120143124.1822121-4-cel@kernel.org>

> +static int rdma_rw_init_mr_wrs_bvec(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
> +		u32 port_num, const struct bio_vec *bvec, u32 nr_bvec,
> +		u32 offset, u64 remote_addr, u32 rkey,
> +		enum dma_data_direction dir)

Any reason this is not using the bvec_iter like the other paths?

Yhe mapping to the scatterlist would then basically be a much
simplified version of __blk_rq_map_sg.

> +		dma_addr = ib_dma_map_bvec(dev, bv, dir);
> +		if (ib_dma_mapping_error(dev, dma_addr)) {
> +			ret = -ENOMEM;
> +			goto out_unmap;
> +		}
> +
> +		/* sg_set_page() initializes the entry; ib_map_mr_sg() uses
> +		 * only sg_dma_address/len, ignoring the page pointer.
> +		 */
> +		sg_set_page(&sgl[i], bv->bv_page, len, bv->bv_offset);
> +		sg_dma_address(&sgl[i]) = dma_addr;
> +		sg_dma_len(&sgl[i]) = len;

And once we have a scatterlist, this should probably just use
ib_dma_map_sg* ?  And maybe rdma_rw_init_one_mr?

> +	/*
> +	 * For bvec MR path: store synthetic scatterlist with DMA addresses
> +	 * for cleanup. Only valid when type == RDMA_RW_MR and initialized
> +	 * via rdma_rw_ctx_init_bvec().
> +	 */
> +	struct scatterlist	*mr_sgl;
> +	u32			mr_sg_cnt;
>  };

This probably should be in the reg union arm and thus the separate
allocatiom?

  reply	other threads:[~2026-01-21  9:05 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-01-20 14:31 [PATCH v2 0/4] Add a bio_vec based API to core/rw.c Chuck Lever
2026-01-20 14:31 ` [PATCH v2 1/4] RDMA/core: add bio_vec based RDMA read/write API Chuck Lever
2026-01-21  8:42   ` Christoph Hellwig
2026-01-21  8:48     ` Leon Romanovsky
2026-01-21  8:57       ` Christoph Hellwig
2026-01-21 10:16         ` Leon Romanovsky
2026-01-21  8:56   ` Christoph Hellwig
2026-01-21 14:14     ` Chuck Lever
2026-01-21 14:57       ` Christoph Hellwig
2026-01-21 15:10         ` Chuck Lever
2026-01-20 14:31 ` [PATCH v2 2/4] RDMA/core: use IOVA-based DMA mapping for bvec RDMA operations Chuck Lever
2026-01-21  8:51   ` Christoph Hellwig
2026-01-20 14:31 ` [PATCH v2 3/4] RDMA/core: add MR support for bvec-based " Chuck Lever
2026-01-21  9:05   ` Christoph Hellwig [this message]
2026-01-20 14:31 ` [PATCH v2 4/4] svcrdma: use bvec-based RDMA read/write API Chuck Lever

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=20260121090508.GE16458@lst.de \
    --to=hch@lst.de \
    --cc=cel@kernel.org \
    --cc=chuck.lever@oracle.com \
    --cc=dai.ngo@oracle.com \
    --cc=jgg@nvidia.com \
    --cc=jlayton@kernel.org \
    --cc=leon@kernel.org \
    --cc=linux-nfs@vger.kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=neilb@ownmail.net \
    --cc=okorniev@redhat.com \
    --cc=tom@talpey.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