All of lore.kernel.org
 help / color / mirror / Atom feed
From: Christoph Hellwig <hch@lst.de>
To: Keith Busch <kbusch@meta.com>
Cc: linux-block@vger.kernel.org, linux-nvme@lists.infradead.org,
	hch@lst.de, axboe@kernel.dk, joshi.k@samsung.com,
	Keith Busch <kbusch@kernel.org>
Subject: Re: [PATCHv5 7/8] nvme-pci: create common sgl unmapping helper
Date: Sun, 10 Aug 2025 16:21:21 +0200	[thread overview]
Message-ID: <20250810142121.GH4262@lst.de> (raw)
In-Reply-To: <20250808155826.1864803-8-kbusch@meta.com>

On Fri, Aug 08, 2025 at 08:58:25AM -0700, Keith Busch wrote:
> From: Keith Busch <kbusch@kernel.org>
> 
> This can be reused by metadata sgls once that starts using the blk-mq
> dma api.
> 
> Signed-off-by: Keith Busch <kbusch@kernel.org>
> ---
>  drivers/nvme/host/pci.c | 31 ++++++++++++++++++++-----------
>  1 file changed, 20 insertions(+), 11 deletions(-)

> +static void __nvme_free_sgls(struct device *dma_dev, struct nvme_sgl_desc *sge,
> +		struct nvme_sgl_desc *sg_list, enum dma_data_direction dir)
> +{
> +	unsigned int len = le32_to_cpu(sge->length);
> +	unsigned int i, nr_entries;
> +
> +	if (sge->type == (NVME_SGL_FMT_DATA_DESC << 4)) {
> +		dma_unmap_page(dma_dev, le64_to_cpu(sge->addr), len, dir);
> +		return;
> +	}
> +
> +	nr_entries = len / sizeof(*sg_list);
> +	for (i = 0; i < nr_entries; i++)


We can probably just do away with the nr_entries variable, the compiler
is not going to recompute this for every loop ieration.


>  {
>  	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
>  	struct nvme_queue *nvmeq = req->mq_hctx->driver_data;
>  	struct device *dma_dev = nvmeq->dev->dev;
>  	struct nvme_sgl_desc *sg_list = iod->descriptors[0];
>  	enum dma_data_direction dir = rq_dma_dir(req);
>  
> +	__nvme_free_sgls(dma_dev, sge, sg_list, dir);

Shouldn't we move the calculation of nvmeq, dma_dev and dir into
__nvme_free_sgls as they are going to be the same for data and metadata.
And then maybe rename it to __nvme_free_sgls and just opencode the
iod->descriptors[0] and &iod->cmd.common.dptr.sgl dereferences in
nvme_unmap_data?


  reply	other threads:[~2025-08-10 14:21 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-08-08 15:58 [PATCHv5 0/8] blk dma iter for integrity metadata Keith Busch
2025-08-08 15:58 ` [PATCHv5 1/8] blk-mq-dma: introduce blk_map_iter Keith Busch
2025-08-10 14:04   ` Christoph Hellwig
2025-08-11 13:30     ` Keith Busch
2025-08-11 14:05       ` Christoph Hellwig
2025-08-08 15:58 ` [PATCHv5 2/8] blk-mq-dma: provide the bio_vec list being iterated Keith Busch
2025-08-10 14:07   ` Christoph Hellwig
2025-08-11 17:04     ` Keith Busch
2025-08-10 14:09   ` Christoph Hellwig
2025-08-08 15:58 ` [PATCHv5 3/8] blk-mq-dma: require unmap caller provide p2p map type Keith Busch
2025-08-10 14:08   ` Christoph Hellwig
2025-08-08 15:58 ` [PATCHv5 4/8] blk-mq: remove REQ_P2PDMA flag Keith Busch
2025-08-10 14:08   ` Christoph Hellwig
2025-08-08 15:58 ` [PATCHv5 5/8] blk-mq-dma: move common dma start code to a helper Keith Busch
2025-08-10 14:10   ` Christoph Hellwig
2025-08-08 15:58 ` [PATCHv5 6/8] blk-mq-dma: add support for mapping integrity metadata Keith Busch
2025-08-10 14:16   ` Christoph Hellwig
2025-08-08 15:58 ` [PATCHv5 7/8] nvme-pci: create common sgl unmapping helper Keith Busch
2025-08-10 14:21   ` Christoph Hellwig [this message]
2025-08-08 15:58 ` [PATCHv5 8/8] nvme-pci: convert metadata mapping to dma iter Keith Busch
2025-08-10 14:27   ` Christoph Hellwig

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=20250810142121.GH4262@lst.de \
    --to=hch@lst.de \
    --cc=axboe@kernel.dk \
    --cc=joshi.k@samsung.com \
    --cc=kbusch@kernel.org \
    --cc=kbusch@meta.com \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.