linux-pci.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Christoph Hellwig <hch@lst.de>
To: Logan Gunthorpe <logang@deltatee.com>
Cc: linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org,
	linux-nvme@lists.infradead.org, linux-rdma@vger.kernel.org,
	Bjorn Helgaas <bhelgaas@google.com>,
	Christoph Hellwig <hch@lst.de>,
	Christian Koenig <Christian.Koenig@amd.com>,
	Jason Gunthorpe <jgg@mellanox.com>,
	Sagi Grimberg <sagi@grimberg.me>, Keith Busch <kbusch@kernel.org>,
	Jens Axboe <axboe@fb.com>,
	Dan Williams <dan.j.williams@intel.com>,
	Eric Pilmore <epilmore@gigaio.com>,
	Stephen Bates <sbates@raithlin.com>
Subject: Re: [PATCH 11/14] PCI/P2PDMA: dma_map P2PDMA map requests that traverse the host bridge
Date: Wed, 24 Jul 2019 08:32:32 +0200	[thread overview]
Message-ID: <20190724063232.GB1804@lst.de> (raw)
In-Reply-To: <20190722230859.5436-12-logang@deltatee.com>

>  	struct dev_pagemap *pgmap = sg_page(sg)->pgmap;
> +	struct pci_dev *client;
> +	int dist;
> +
> +	client = find_parent_pci_dev(dev);
> +	if (WARN_ON_ONCE(!client))
> +		return 0;
>  
> +	dist = upstream_bridge_distance(pgmap->pci_p2pdma_provider,
> +					client, NULL);

Doing this on every mapping call sounds expensive..

> +	if (WARN_ON_ONCE(dist & P2PDMA_NOT_SUPPORTED))
> +		return 0;
> +
> +	if (dist & P2PDMA_THRU_HOST_BRIDGE)
> +		return dma_map_sg_attrs(dev, sg, nents, dir, attrs);
> +	else
> +		return __pci_p2pdma_map_sg(pgmap, dev, sg, nents);

Can't we organize the values so that we can switch on the return
value instead of doing flag checks?

>  }
>  EXPORT_SYMBOL_GPL(pci_p2pdma_map_sg_attrs);
>  
> @@ -847,6 +861,21 @@ EXPORT_SYMBOL_GPL(pci_p2pdma_map_sg_attrs);
>  void pci_p2pdma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg,
>  		int nents, enum dma_data_direction dir, unsigned long attrs)
>  {
> +	struct dev_pagemap *pgmap = sg_page(sg)->pgmap;
> +	struct pci_dev *client;
> +	int dist;
> +
> +	client = find_parent_pci_dev(dev);
> +	if (!client)
> +		return;
> +
> +	dist = upstream_bridge_distance(pgmap->pci_p2pdma_provider,
> +					client, NULL);

And then we do it for every unmap again..

  reply	other threads:[~2019-07-24  6:32 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-07-22 23:08 [PATCH 00/14] PCI/P2PDMA: Support transactions that hit the host bridge Logan Gunthorpe
2019-07-22 23:08 ` [PATCH 01/14] PCI/P2PDMA: Add constants for not-supported result upstream_bridge_distance() Logan Gunthorpe
2019-07-23 16:20   ` Koenig, Christian
2019-07-22 23:08 ` [PATCH 02/14] PCI/P2PDMA: Factor out __upstream_bridge_distance() Logan Gunthorpe
2019-07-22 23:08 ` [PATCH 03/14] PCI/P2PDMA: Apply host bridge white list for ACS Logan Gunthorpe
2019-07-23 16:23   ` Koenig, Christian
2019-07-22 23:08 ` [PATCH 04/14] PCI/P2PDMA: Cache the result of upstream_bridge_distance() Logan Gunthorpe
2019-07-22 23:08 ` [PATCH 05/14] PCI/P2PDMA: Factor out host_bridge_whitelist() Logan Gunthorpe
2019-07-22 23:08 ` [PATCH 06/14] PCI/P2PDMA: Add whitelist support for Intel Host Bridges Logan Gunthorpe
2019-07-25 18:52   ` Jason Gunthorpe
2019-07-25 19:14     ` Logan Gunthorpe
2019-07-22 23:08 ` [PATCH 07/14] PCI/P2PDMA: Add the provider's pci_dev to the dev_pgmap struct Logan Gunthorpe
2019-07-24  6:32   ` Christoph Hellwig
2019-07-24 15:50     ` Logan Gunthorpe
2019-07-25  6:02       ` Christoph Hellwig
2019-07-22 23:08 ` [PATCH 08/14] PCI/P2PDMA: Add attrs argument to pci_p2pdma_map_sg() Logan Gunthorpe
2019-07-22 23:08 ` [PATCH 09/14] PCI/P2PDMA: Introduce pci_p2pdma_unmap_sg() Logan Gunthorpe
2019-07-22 23:08 ` [PATCH 10/14] PCI/P2PDMA: Factor out __pci_p2pdma_map_sg() Logan Gunthorpe
2019-07-22 23:08 ` [PATCH 11/14] PCI/P2PDMA: dma_map P2PDMA map requests that traverse the host bridge Logan Gunthorpe
2019-07-24  6:32   ` Christoph Hellwig [this message]
2019-07-24 15:58     ` Logan Gunthorpe
2019-07-25  6:10       ` Christoph Hellwig
2019-07-25 16:00         ` Logan Gunthorpe
2019-07-25 16:34           ` Jason Gunthorpe
2019-07-25 17:22             ` Logan Gunthorpe
2019-07-25 18:58   ` Jason Gunthorpe
2019-07-25 19:17     ` Logan Gunthorpe
2019-07-25 19:29       ` Jason Gunthorpe
2019-07-25 19:36         ` Logan Gunthorpe
2019-07-22 23:08 ` [PATCH 12/14] PCI/P2PDMA: No longer require no-mmu for host bridge whitelist Logan Gunthorpe
2019-07-22 23:08 ` [PATCH 13/14] PCI/P2PDMA: Update documentation for pci_p2pdma_distance_many() Logan Gunthorpe
2019-07-22 23:08 ` [PATCH 14/14] PCI/P2PDMA: Introduce pci_p2pdma_[un]map_resource() Logan Gunthorpe
2019-07-23 16:28   ` Koenig, Christian
2019-07-23 16:58     ` Logan Gunthorpe
2019-07-24  6:32   ` Christoph Hellwig
2019-07-24 16:06     ` Logan Gunthorpe
2019-07-25 11:50       ` Christoph Hellwig
2019-07-25 16:00         ` Logan Gunthorpe
2019-07-23 16:30 ` [PATCH 00/14] PCI/P2PDMA: Support transactions that hit the host bridge Koenig, Christian
2019-07-23 16:58   ` Logan Gunthorpe

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=20190724063232.GB1804@lst.de \
    --to=hch@lst.de \
    --cc=Christian.Koenig@amd.com \
    --cc=axboe@fb.com \
    --cc=bhelgaas@google.com \
    --cc=dan.j.williams@intel.com \
    --cc=epilmore@gigaio.com \
    --cc=jgg@mellanox.com \
    --cc=kbusch@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=linux-pci@vger.kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=logang@deltatee.com \
    --cc=sagi@grimberg.me \
    --cc=sbates@raithlin.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).