All of lore.kernel.org
 help / color / mirror / Atom feed
From: Daniel Vetter <daniel@ffwll.ch>
To: "Christian König" <ckoenig.leichtzumerken@gmail.com>
Cc: dri-devel@lists.freedesktop.org
Subject: Re: [PATCH 03/12] dma-buf: start caching of sg_table objects
Date: Tue, 30 Apr 2019 16:18:27 +0200	[thread overview]
Message-ID: <20190430141827.GU3271@phenom.ffwll.local> (raw)
In-Reply-To: <20190426123638.40221-3-christian.koenig@amd.com>

On Fri, Apr 26, 2019 at 02:36:29PM +0200, Christian König wrote:
> To allow a smooth transition from pinning buffer objects to dynamic
> invalidation we first start to cache the sg_table for an attachment
> unless the driver has implemented the explicite pin/unpin callbacks.
> 
> Signed-off-by: Christian König <christian.koenig@amd.com>

btw given how huge a change this is the doc update is rather thin :-)

Probably better to revise this all together, so we have a coherent
documentation story between static and dynamic dma-buf attachments and
what exactly that means in each case.

> ---
>  drivers/dma-buf/dma-buf.c | 24 ++++++++++++++++++++++++
>  include/linux/dma-buf.h   |  1 +
>  2 files changed, 25 insertions(+)
> 
> diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
> index 0656dcf289be..a18d10c4425a 100644
> --- a/drivers/dma-buf/dma-buf.c
> +++ b/drivers/dma-buf/dma-buf.c
> @@ -610,6 +610,20 @@ dma_buf_attach(const struct dma_buf_attach_info *info)
>  	list_add(&attach->node, &dmabuf->attachments);
>  
>  	mutex_unlock(&dmabuf->lock);
> +
> +	if (!dmabuf->ops->pin) {
> +		struct sg_table *sgt;
> +
> +		sgt = dmabuf->ops->map_dma_buf(attach, DMA_BIDIRECTIONAL);
> +		if (!sgt)
> +			sgt = ERR_PTR(-ENOMEM);
> +		if (IS_ERR(sgt)) {
> +			dma_buf_detach(dmabuf, attach);
> +			return ERR_CAST(sgt);
> +		}
> +		attach->sgt = sgt;
> +	}
> +
>  	return attach;
>  
>  err_attach:
> @@ -632,6 +646,10 @@ void dma_buf_detach(struct dma_buf *dmabuf, struct dma_buf_attachment *attach)
>  	if (WARN_ON(!dmabuf || !attach))
>  		return;
>  
> +	if (attach->sgt)
> +		dmabuf->ops->unmap_dma_buf(attach, attach->sgt,
> +					   DMA_BIDIRECTIONAL);
> +
>  	mutex_lock(&dmabuf->lock);
>  	list_del(&attach->node);
>  	if (dmabuf->ops->detach)
> @@ -668,6 +686,9 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach,
>  	if (WARN_ON(!attach || !attach->dmabuf))
>  		return ERR_PTR(-EINVAL);
>  
> +	if (attach->sgt)
> +		return attach->sgt;
> +
>  	reservation_object_lock(attach->dmabuf->resv, NULL);
>  	r = dma_buf_pin(attach->dmabuf);
>  	reservation_object_unlock(attach->dmabuf->resv);
> @@ -701,6 +722,9 @@ void dma_buf_unmap_attachment(struct dma_buf_attachment *attach,
>  	if (WARN_ON(!attach || !attach->dmabuf || !sg_table))
>  		return;
>  
> +	if (attach->sgt == sg_table)
> +		return;
> +
>  	attach->dmabuf->ops->unmap_dma_buf(attach, sg_table,
>  						direction);
>  
> diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
> index 0321939b1c3d..b9d0719581cd 100644
> --- a/include/linux/dma-buf.h
> +++ b/include/linux/dma-buf.h
> @@ -345,6 +345,7 @@ struct dma_buf_attachment {
>  	struct dma_buf *dmabuf;
>  	struct device *dev;
>  	struct list_head node;
> +	struct sg_table *sgt;
>  	void *priv;
>  };
>  
> -- 
> 2.17.1
> 
> _______________________________________________
> dri-devel mailing list
> dri-devel@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/dri-devel

-- 
Daniel Vetter
Software Engineer, Intel Corporation
http://blog.ffwll.ch
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

  parent reply	other threads:[~2019-04-30 14:18 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-04-26 12:36 [PATCH 01/12] dma-buf: add struct dma_buf_attach_info Christian König
2019-04-26 12:36 ` [PATCH 02/12] dma-buf: add explicit buffer pinning v2 Christian König
2019-04-29  8:40   ` Daniel Vetter
2019-04-30 13:42     ` Christian König
2019-04-30 13:59       ` Daniel Vetter
2019-04-30 14:26         ` Christian König
2019-04-30 14:34           ` Daniel Vetter
2019-04-30 14:41             ` Koenig, Christian
2019-04-30 15:22               ` Daniel Vetter
2019-04-26 12:36 ` [PATCH 03/12] dma-buf: start caching of sg_table objects Christian König
2019-04-29  8:54   ` Daniel Vetter
2019-04-30 14:18   ` Daniel Vetter [this message]
2019-04-26 12:36 ` [PATCH 04/12] dma-buf: lock the reservation object during (un)map_dma_buf v4 Christian König
2019-04-26 12:36 ` [PATCH 05/12] dma-buf: add dma_buf_(un)map_attachment_locked variants v4 Christian König
2019-04-26 12:36 ` [PATCH 06/12] dma-buf: add optional invalidate_mappings callback v5 Christian König
2019-04-29  8:42   ` Daniel Vetter
2019-04-26 12:36 ` [PATCH 07/12] drm: remove prime sg_table caching Christian König
2019-04-26 12:36 ` [PATCH 08/12] drm/ttm: remove the backing store if no placement is given Christian König
2019-04-26 12:36 ` [PATCH 09/12] drm/ttm: use the parent resv for ghost objects Christian König
2019-04-26 12:36 ` [PATCH 10/12] drm/amdgpu: add independent DMA-buf export v3 Christian König
2019-04-30 14:16   ` Daniel Vetter
2019-05-03 12:35     ` Christian König
2019-05-06  8:04       ` Daniel Vetter
2019-05-06 10:05         ` Koenig, Christian
2019-05-06 15:10           ` Daniel Vetter
2019-04-26 12:36 ` [PATCH 11/12] drm/amdgpu: add independent DMA-buf import v4 Christian König
2019-04-26 12:36 ` [PATCH 12/12] drm/amdgpu: add DMA-buf invalidation callback v2 Christian König
2019-04-29  8:24 ` [PATCH 01/12] dma-buf: add struct dma_buf_attach_info Daniel Vetter
2019-04-30 12:40   ` Christian König

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=20190430141827.GU3271@phenom.ffwll.local \
    --to=daniel@ffwll.ch \
    --cc=ckoenig.leichtzumerken@gmail.com \
    --cc=dri-devel@lists.freedesktop.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.