[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <41ad0c01-93f3-67eb-1695-43446d2eb438@intel.com>
Date: Fri, 29 Sep 2023 10:19:45 -0700
From: Jacob Keller <jacob.e.keller@...el.com>
To: Chris Leech <cleech@...hat.com>, Greg Kroah-Hartman
<gregkh@...uxfoundation.org>, Christoph Hellwig <hch@....de>, Rasesh Mody
<rmody@...vell.com>, Ariel Elior <aelior@...vell.com>, Sudarsana Kalluru
<skalluru@...vell.com>, Manish Chopra <manishc@...vell.com>
CC: Nilesh Javali <njavali@...vell.com>, Manish Rangankar
<mrangankar@...vell.com>, Jerry Snitselaar <jsnitsel@...hat.com>, "John
Meneghini" <jmeneghi@...hat.com>, Lee Duncan <lduncan@...e.com>, Mike
Christie <michael.christie@...cle.com>, Hannes Reinecke <hare@...nel.org>,
<netdev@...r.kernel.org>, <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH 3/3] cnic,bnx2,bnx2x: use UIO_MEM_DMA_COHERENT
On 9/29/2023 10:00 AM, Chris Leech wrote:
> Make use of the new UIO_MEM_DMA_COHERENT type to properly handle mmap
> for dma_alloc_coherent buffers.
>
> The cnic l2_ring and l2_buf mmaps have caused page refcount issues since
> the misuse of the __GFP_COMP flag was removed from their
> dma_alloc_coherent calls. Fix that by having the uio device use
> dma_mmap_coherent.
>
> The bnx2 and bnx2x status block allocations are also dma_alloc_coherent,
> and should use dma_mmap_coherent. They didn't allocate multiple pages,
> but also didn't seem to work correctly with an iommu enabled.
>
> Fixes: bb73955c0b1d ("cnic: don't pass bogus GFP_ flags to dma_alloc_coherent")
> Signed-off-by: Chris Leech <cleech@...hat.com>
> ---
Reviewed-by: Jacob Keller <jacob.e.keller@...el.com>
Powered by blists - more mailing lists