Subject: Re: [PATCH V2] net: ethernet: mellanox: correct page conversion
To: Sinan Kaya <okaya@codeaurora.org>, Christoph Hellwig <hch@infradead.org>
Cc: linux-rdma@vger.kernel.org, cov@codeaurora.org,
        Yishai Hadas <yishaih@mellanox.com>, netdev@vger.kernel.org,
        linux-kernel@vger.kernel.org
References: <1460845412-13120-1-git-send-email-okaya@codeaurora.org>
 <20160418121247.GA25387@infradead.org>
 <0c6a430c5f0ec64f51d7c594ef9751dd@codeaurora.org>
 <20160418131058.GA25421@infradead.org> <5714E5D6.7050600@codeaurora.org>
From: Timur Tabi <timur@codeaurora.org>
Message-ID: <5714FA2C.4030209@codeaurora.org>
Date: Mon, 18 Apr 2016 10:15:56 -0500
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:43.0) Gecko/20100101
 Firefox/43.0 SeaMonkey/2.40
MIME-Version: 1.0
In-Reply-To: <5714E5D6.7050600@codeaurora.org>
Content-Type: text/plain; charset=windows-1252; format=flowed
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1503
Lines: 30

Sinan Kaya wrote:
>
> VMAP allows you to make several pages look contiguous to the CPU.
> It can only be used against logical addresses returned from kmalloc
> or alloc_page.
>
> You cannot take several virtually mapped addresses returned by dma_alloc_coherent
> and try to make them virtually contiguous again.
>
> The code happens to work on other architectures by pure luck. AFAIK, dma_alloc_coherent
> returns logical addresses on Intel systems until it runs out of DMA memory. After
> that intel arch will also start returning virtually mapped addresses and this code
> will also fail. ARM64 on the other hand always returns a virtually mapped address.
>
> The goal of this code is to allocate a bunch of page sized memory and make it look
> contiguous. It is just using the wrong API. The correct API is either kmalloc or
> alloc_page map it with dma_map_page not dma_alloc_coherent.
>
> The proper usage of dma_map_page requires code to call dma_sync API in correct
> places to be compatible with noncoherent systems. This code is already assuming
> coherency. It would be a nice to have dma_sync APIs in right places. There is no
> harm in calling dma_sync API for coherent systems as they are no-ops in DMA mapping
> layer whereas it is a cache flush for non-coherent systems.

The text would be a great addition to the patch description.

-- 
Qualcomm Innovation Center, Inc.
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora
Forum, a Linux Foundation collaborative project.