Re: [PATCH RFC v1 5/6] xen-swiotlb: convert variables to arrays

From: Boris Ostrovsky <boris.ostrovsky@oracle.com>
To: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
	Christoph Hellwig <hch@lst.de>,
	jgross@suse.com
Cc: Dongli Zhang <dongli.zhang@oracle.com>,
	dri-devel@lists.freedesktop.org, intel-gfx@lists.freedesktop.org,
	iommu@lists.linux-foundation.org, linux-mips@vger.kernel.org,
	linux-mmc@vger.kernel.org, linux-pci@vger.kernel.org,
	linuxppc-dev@lists.ozlabs.org, nouveau@lists.freedesktop.org,
	x86@kernel.org, xen-devel@lists.xenproject.org,
	linux-kernel@vger.kernel.org, adrian.hunter@intel.com,
	akpm@linux-foundation.org, benh@kernel.crashing.org,
	bskeggs@redhat.com, bhelgaas@google.com, bp@alien8.de,
	chris@chris-wilson.co.uk, daniel@ffwll.ch, airlied@linux.ie,
	hpa@zytor.com, mingo@kernel.org, mingo@redhat.com,
	jani.nikula@linux.intel.com, joonas.lahtinen@linux.intel.com,
	m.szyprowski@samsung.com, matthew.auld@intel.com,
	mpe@ellerman.id.au, rppt@kernel.org, paulus@samba.org,
	peterz@infradead.org, robin.murphy@arm.com,
	rodrigo.vivi@intel.com, sstabellini@kernel.org,
	bauerman@linux.ibm.com, tsbogend@alpha.franken.de,
	tglx@linutronix.de, ulf.hansson@linaro.org, joe.jin@oracle.com,
	thomas.lendacky@amd.com
Subject: Re: [PATCH RFC v1 5/6] xen-swiotlb: convert variables to arrays
Date: Fri, 19 Feb 2021 18:59:50 -0500	[thread overview]
Message-ID: <e0baa2fa-0ca4-ef21-aeb0-319d9648e830@oracle.com> (raw)
In-Reply-To: <YDAgT2ZIdncNwNlf@Konrads-MacBook-Pro.local>

On 2/19/21 3:32 PM, Konrad Rzeszutek Wilk wrote:
> On Sun, Feb 07, 2021 at 04:56:01PM +0100, Christoph Hellwig wrote:
>> On Thu, Feb 04, 2021 at 09:40:23AM +0100, Christoph Hellwig wrote:
>>> So one thing that has been on my mind for a while:  I'd really like
>>> to kill the separate dma ops in Xen swiotlb.  If we compare xen-swiotlb
>>> to swiotlb the main difference seems to be:
>>>
>>>  - additional reasons to bounce I/O vs the plain DMA capable
>>>  - the possibility to do a hypercall on arm/arm64
>>>  - an extra translation layer before doing the phys_to_dma and vice
>>>    versa
>>>  - an special memory allocator
>>>
>>> I wonder if inbetween a few jump labels or other no overhead enablement
>>> options and possibly better use of the dma_range_map we could kill
>>> off most of swiotlb-xen instead of maintaining all this code duplication?
>> So I looked at this a bit more.
>>
>> For x86 with XENFEAT_auto_translated_physmap (how common is that?)
> Juergen, Boris please correct me if I am wrong, but that XENFEAT_auto_translated_physmap
> only works for PVH guests?

That's both HVM and PVH (for dom0 it's only PVH).

-boris

>
>> pfn_to_gfn is a nop, so plain phys_to_dma/dma_to_phys do work as-is.
>>
>> xen_arch_need_swiotlb always returns true for x86, and
>> range_straddles_page_boundary should never be true for the
>> XENFEAT_auto_translated_physmap case.
> Correct. The kernel should have no clue of what the real MFNs are
> for PFNs.
>> So as far as I can tell the mapping fast path for the
>> XENFEAT_auto_translated_physmap can be trivially reused from swiotlb.
>>
>> That leaves us with the next more complicated case, x86 or fully cache
>> coherent arm{,64} without XENFEAT_auto_translated_physmap.  In that case
>> we need to patch in a phys_to_dma/dma_to_phys that performs the MFN
>> lookup, which could be done using alternatives or jump labels.
>> I think if that is done right we should also be able to let that cover
>> the foreign pages in is_xen_swiotlb_buffer/is_swiotlb_buffer, but
>> in that worst case that would need another alternative / jump label.
>>
>> For non-coherent arm{,64} we'd also need to use alternatives or jump
>> labels to for the cache maintainance ops, but that isn't a hard problem
>> either.
>>
>>