linux-kernel - Re: [RFC 3/3] dmaengine: Support for requesting channels preferring DMA domain controller

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20190908121507.GN2672@vkoul-mobl>
Date:   Sun, 8 Sep 2019 17:45:07 +0530
From:   Vinod Koul <vkoul@...nel.org>
To:     Peter Ujfalusi <peter.ujfalusi@...com>
Cc:     robh+dt@...nel.org, dmaengine@...r.kernel.org,
        linux-kernel@...r.kernel.org, dan.j.williams@...el.com,
        devicetree@...r.kernel.org
Subject: Re: [RFC 3/3] dmaengine: Support for requesting channels preferring
 DMA domain controller

On 06-09-19, 17:18, Peter Ujfalusi wrote:
> In case the channel is not requested via the slave API, use the
> of_find_dma_domain() to see if a system default DMA controller is
> specified.
> 
> Add new function which can be used by clients to request channels by mask
> from their DMA domain controller if specified.
> 
> Client drivers can take advantage of the domain support by moving from
> dma_request_chan_by_mask() to dma_domain_request_chan_by_mask()
> 
> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@...com>
> ---
>  drivers/dma/dmaengine.c   | 17 ++++++++++++-----
>  include/linux/dmaengine.h |  9 ++++++---
>  2 files changed, 18 insertions(+), 8 deletions(-)
> 
> diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
> index 6baddf7dcbfd..087450eed68c 100644
> --- a/drivers/dma/dmaengine.c
> +++ b/drivers/dma/dmaengine.c
> @@ -640,6 +640,10 @@ struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask,
>  	struct dma_device *device, *_d;
>  	struct dma_chan *chan = NULL;
>  
> +	/* If np is not specified, get the default DMA domain controller */
> +	if (!np)
> +		np = of_find_dma_domain(NULL);
> +
>  	/* Find a channel */
>  	mutex_lock(&dma_list_mutex);
>  	list_for_each_entry_safe(device, _d, &dma_device_list, global_node) {
> @@ -751,19 +755,22 @@ struct dma_chan *dma_request_slave_channel(struct device *dev,
>  EXPORT_SYMBOL_GPL(dma_request_slave_channel);
>  
>  /**
> - * dma_request_chan_by_mask - allocate a channel satisfying certain capabilities
> - * @mask: capabilities that the channel must satisfy
> + * dma_domain_request_chan_by_mask - allocate a channel by mask from DMA domain
> + * @dev:	pointer to client device structure
> + * @mask:	capabilities that the channel must satisfy
>   *
>   * Returns pointer to appropriate DMA channel on success or an error pointer.
>   */
> -struct dma_chan *dma_request_chan_by_mask(const dma_cap_mask_t *mask)
> +struct dma_chan *dma_domain_request_chan_by_mask(struct device *dev,
> +						 const dma_cap_mask_t *mask)

should we really use dma_request_chan_by_mask() why not create a new api
dma_request_chan_by_domain() and use that, it falls back to
dma_request_chan_by_mask() if it doesnt find a valid domain!

-- 
~Vinod