[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <YqF/eZE9eozDURWz@infradead.org>
Date: Wed, 8 Jun 2022 22:04:57 -0700
From: Christoph Hellwig <hch@...radead.org>
To: Dongli Zhang <dongli.zhang@...cle.com>
Cc: iommu@...ts.linux-foundation.org, xen-devel@...ts.xenproject.org,
x86@...nel.org, linuxppc-dev@...ts.ozlabs.org,
virtualization@...ts.linux-foundation.org,
linux-kernel@...r.kernel.org, hch@...radead.org,
m.szyprowski@...sung.com, jgross@...e.com, tglx@...utronix.de,
mingo@...hat.com, bp@...en8.de, dave.hansen@...ux.intel.com,
sstabellini@...nel.org, mpe@...erman.id.au, konrad.wilk@...cle.com,
mst@...hat.com, jasowang@...hat.com, joe.jin@...cle.com
Subject: Re: [PATCH RFC v1 1/7] swiotlb: introduce the highmem swiotlb buffer
On Wed, Jun 08, 2022 at 05:55:47PM -0700, Dongli Zhang wrote:
> @@ -109,6 +109,7 @@ struct io_tlb_mem {
> } *slots;
> };
> extern struct io_tlb_mem io_tlb_default_mem;
> +extern struct io_tlb_mem io_tlb_high_mem;
Tis should not be exposed.
> +extern bool swiotlb_high_active(void);
And this should not even exist.
> +static unsigned long high_nslabs;
And I don't think "high" is a good name here to start with. That
suggests highmem, which we are not using here.
Powered by blists - more mailing lists