<p dir="ltr">There are two ways to do this 1. Allocate a physical memory at boot time itself by reserve_mem fn pointer and you could use this large buffer when you need dma using dma map single fn.</p>
<p dir="ltr">2. Patch the kernel with bigphysarea patch and allocate large buffer with that patch. And you can use that buffer for dma. </p>
<p dir="ltr">I have used both methods it works for large physical buffer you need for dma. </p>
<p dir="ltr">Thanks, <br>
Haresh</p>
<p dir="ltr">Thanks, <br>
Haresh. </p>
<div class="gmail_quote">On 7 Jan 2014 03:27, "Steven Bell" <<a href="mailto:botsnlinux@gmail.com">botsnlinux@gmail.com</a>> wrote:<br type="attribution"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
>> I want to allocate a contiguous 8MB buffer and use it for streaming DMA. I don't need or want<br>
>> a coherent buffer, since I'm using streaming DMA, and so dma_alloc_coherent() seems like<br>
>> the wrong method to use. Is that true, or should I use it anyway? If not, what method do I use?<br>
>><br>
>> The DMA-API and DMA-API-HOWTO documents don't seem to say anything about allocating<br>
>> memory for streaming DMA operations. Have I missed something?<br>
<br>
On Mon, Jan 6, 2014 at 1:29 AM, saumendra dash <<a href="mailto:saumendradash@gmail.com">saumendradash@gmail.com</a>> wrote:<br>
><br>
> For streaming DMA, you can use the function dma_map_single().<br>
> Alternatively, you can create your own DMA pool using dma_pool_create(), and allocate memory from that using dma_pool_alloc(().<br>
><br>
> The later case will be more suitable for you, since you want a 8MB DMA buffer for your DMA.<br>
> Hope that helps/<br>
<br>
I am using dma_map_single, but it doesn't allocate any memory. From<br>
what I understand, it takes a pointer to a buffer and performs the<br>
necessary cache flushes or invalidations to make sure that the memory<br>
is safe to DMA. Is there a correct way to allocate large buffers for<br>
streaming DMA? Right now, I'm allocating memory with get_free_pages,<br>
but that is prone to fail on large allocations, and only works up to<br>
4MB on my system (i.e get_free_pages order 10).<br>
<br>
>From reading LDD3 and DMA-API.txt, DMA pools are for allocating "small<br>
dma-coherent memory regions". LDD3 specifically states that pools are<br>
useful where the driver needs regions smaller than 1 page. Since I<br>
want large, non-coherent buffers, I don't see how this helps.<br>
<br>
Steven<br>
<br>
_______________________________________________<br>
Kernelnewbies mailing list<br>
<a href="mailto:Kernelnewbies@kernelnewbies.org">Kernelnewbies@kernelnewbies.org</a><br>
<a href="http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies" target="_blank">http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies</a><br>
</blockquote></div>