All of lore.kernel.org
 help / color / mirror / Atom feed
From: Christoph Hellwig <hch@lst.de>
To: Dongli Zhang <dongli.zhang@oracle.com>
Cc: ulf.hansson@linaro.org, airlied@linux.ie,
	benh@kernel.crashing.org, dri-devel@lists.freedesktop.org,
	linux-kernel@vger.kernel.org, bhelgaas@google.com,
	paulus@samba.org, hpa@zytor.com, hch@lst.de,
	m.szyprowski@samsung.com, sstabellini@kernel.org,
	adrian.hunter@intel.com, mpe@ellerman.id.au, x86@kernel.org,
	joe.jin@oracle.com, mingo@kernel.org, peterz@infradead.org,
	mingo@redhat.com, bskeggs@redhat.com, linux-pci@vger.kernel.org,
	xen-devel@lists.xenproject.org, matthew.auld@intel.com,
	thomas.lendacky@amd.com, konrad.wilk@oracle.com,
	intel-gfx@lists.freedesktop.org, bp@alien8.de,
	nouveau@lists.freedesktop.org, boris.ostrovsky@oracle.com,
	chris@chris-wilson.co.uk, jgross@suse.com,
	tsbogend@alpha.franken.de, robin.murphy@arm.com,
	linux-mmc@vger.kernel.org, linux-mips@vger.kernel.org,
	iommu@lists.linux-foundation.org, tglx@linutronix.de,
	bauerman@linux.ibm.com, akpm@linux-foundation.org,
	linuxppc-dev@lists.ozlabs.org, rppt@kernel.org
Subject: Re: [Intel-gfx] [PATCH RFC v1 5/6] xen-swiotlb: convert variables to arrays
Date: Thu, 4 Feb 2021 09:40:23 +0100	[thread overview]
Message-ID: <20210204084023.GA32328@lst.de> (raw)
In-Reply-To: <20210203233709.19819-6-dongli.zhang@oracle.com>

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?
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

WARNING: multiple messages have this Message-ID (diff)
From: Christoph Hellwig <hch@lst.de>
To: Dongli Zhang <dongli.zhang@oracle.com>
Cc: ulf.hansson@linaro.org, airlied@linux.ie,
	benh@kernel.crashing.org, joonas.lahtinen@linux.intel.com,
	dri-devel@lists.freedesktop.org, linux-kernel@vger.kernel.org,
	bhelgaas@google.com, paulus@samba.org, hpa@zytor.com, hch@lst.de,
	sstabellini@kernel.org, adrian.hunter@intel.com,
	mpe@ellerman.id.au, x86@kernel.org, joe.jin@oracle.com,
	mingo@kernel.org, peterz@infradead.org, mingo@redhat.com,
	bskeggs@redhat.com, linux-pci@vger.kernel.org,
	xen-devel@lists.xenproject.org, matthew.auld@intel.com,
	thomas.lendacky@amd.com, konrad.wilk@oracle.com,
	intel-gfx@lists.freedesktop.org, jani.nikula@linux.intel.com,
	bp@alien8.de, rodrigo.vivi@intel.com,
	nouveau@lists.freedesktop.org, boris.ostrovsky@oracle.com,
	chris@chris-wilson.co.uk, jgross@suse.com,
	tsbogend@alpha.franken.de, robin.murphy@arm.com,
	linux-mmc@vger.kernel.org, linux-mips@vger.kernel.org,
	iommu@lists.linux-foundation.org, tglx@linutronix.de,
	daniel@ffwll.ch, akpm@linux-foundation.org,
	linuxppc-dev@lists.ozlabs.org, rppt@kernel.org
Subject: Re: [PATCH RFC v1 5/6] xen-swiotlb: convert variables to arrays
Date: Thu, 4 Feb 2021 09:40:23 +0100	[thread overview]
Message-ID: <20210204084023.GA32328@lst.de> (raw)
In-Reply-To: <20210203233709.19819-6-dongli.zhang@oracle.com>

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?
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

WARNING: multiple messages have this Message-ID (diff)
From: Christoph Hellwig <hch@lst.de>
To: Dongli Zhang <dongli.zhang@oracle.com>
Cc: 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,
	boris.ostrovsky@oracle.com, hch@lst.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, jgross@suse.com,
	konrad.wilk@oracle.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: Thu, 4 Feb 2021 09:40:23 +0100	[thread overview]
Message-ID: <20210204084023.GA32328@lst.de> (raw)
In-Reply-To: <20210203233709.19819-6-dongli.zhang@oracle.com>

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?

WARNING: multiple messages have this Message-ID (diff)
From: Christoph Hellwig <hch@lst.de>
To: Dongli Zhang <dongli.zhang@oracle.com>
Cc: ulf.hansson@linaro.org, airlied@linux.ie,
	benh@kernel.crashing.org, joonas.lahtinen@linux.intel.com,
	dri-devel@lists.freedesktop.org, linux-kernel@vger.kernel.org,
	bhelgaas@google.com, paulus@samba.org, hpa@zytor.com, hch@lst.de,
	m.szyprowski@samsung.com, sstabellini@kernel.org,
	adrian.hunter@intel.com, mpe@ellerman.id.au, x86@kernel.org,
	joe.jin@oracle.com, mingo@kernel.org, peterz@infradead.org,
	mingo@redhat.com, bskeggs@redhat.com, linux-pci@vger.kernel.org,
	xen-devel@lists.xenproject.org, matthew.auld@intel.com,
	thomas.lendacky@amd.com, konrad.wilk@oracle.com,
	intel-gfx@lists.freedesktop.org, jani.nikula@linux.intel.com,
	bp@alien8.de, rodrigo.vivi@intel.com,
	nouveau@lists.freedesktop.org, boris.ostrovsky@oracle.com,
	chris@chris-wilson.co.uk, jgross@suse.com,
	tsbogend@alpha.franken.de, robin.murphy@arm.com,
	linux-mmc@vger.kernel.org, linux-mips@vger.kernel.org,
	iommu@lists.linux-foundation.org, tglx@linutronix.de,
	bauerman@linux.ibm.com, daniel@ffwll.ch,
	akpm@linux-foundation.org, linuxppc-dev@lists.ozlabs.org,
	rppt@kernel.org
Subject: Re: [Nouveau] [PATCH RFC v1 5/6] xen-swiotlb: convert variables to arrays
Date: Thu, 4 Feb 2021 09:40:23 +0100	[thread overview]
Message-ID: <20210204084023.GA32328@lst.de> (raw)
In-Reply-To: <20210203233709.19819-6-dongli.zhang@oracle.com>

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?
_______________________________________________
Nouveau mailing list
Nouveau@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/nouveau

WARNING: multiple messages have this Message-ID (diff)
From: Christoph Hellwig <hch@lst.de>
To: Dongli Zhang <dongli.zhang@oracle.com>
Cc: ulf.hansson@linaro.org, airlied@linux.ie,
	joonas.lahtinen@linux.intel.com, dri-devel@lists.freedesktop.org,
	linux-kernel@vger.kernel.org, bhelgaas@google.com,
	paulus@samba.org, hpa@zytor.com, hch@lst.de,
	m.szyprowski@samsung.com, sstabellini@kernel.org,
	adrian.hunter@intel.com, x86@kernel.org, joe.jin@oracle.com,
	mingo@kernel.org, peterz@infradead.org, mingo@redhat.com,
	bskeggs@redhat.com, linux-pci@vger.kernel.org,
	xen-devel@lists.xenproject.org, matthew.auld@intel.com,
	thomas.lendacky@amd.com, konrad.wilk@oracle.com,
	intel-gfx@lists.freedesktop.org, jani.nikula@linux.intel.com,
	bp@alien8.de, rodrigo.vivi@intel.com,
	nouveau@lists.freedesktop.org, boris.ostrovsky@oracle.com,
	chris@chris-wilson.co.uk, jgross@suse.com,
	tsbogend@alpha.franken.de, robin.murphy@arm.com,
	linux-mmc@vger.kernel.org, linux-mips@vger.kernel.org,
	iommu@lists.linux-foundation.org, tglx@linutronix.de,
	bauerman@linux.ibm.com, daniel@ffwll.ch,
	akpm@linux-foundation.org, linuxppc-dev@lists.ozlabs.org,
	rppt@kernel.org
Subject: Re: [PATCH RFC v1 5/6] xen-swiotlb: convert variables to arrays
Date: Thu, 4 Feb 2021 09:40:23 +0100	[thread overview]
Message-ID: <20210204084023.GA32328@lst.de> (raw)
In-Reply-To: <20210203233709.19819-6-dongli.zhang@oracle.com>

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?

  reply	other threads:[~2021-02-04  8:40 UTC|newest]

Thread overview: 95+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-02-03 23:37 [Intel-gfx] [PATCH RFC v1 0/6] swiotlb: 64-bit DMA buffer Dongli Zhang
2021-02-03 23:37 ` Dongli Zhang
2021-02-03 23:37 ` Dongli Zhang
2021-02-03 23:37 ` [Nouveau] " Dongli Zhang
2021-02-03 23:37 ` Dongli Zhang
2021-02-03 23:37 ` Dongli Zhang
2021-02-03 23:37 ` [Intel-gfx] [PATCH RFC v1 1/6] swiotlb: define new enumerated type Dongli Zhang
2021-02-03 23:37   ` Dongli Zhang
2021-02-03 23:37   ` Dongli Zhang
2021-02-03 23:37   ` [Nouveau] " Dongli Zhang
2021-02-03 23:37   ` Dongli Zhang
2021-02-03 23:37   ` Dongli Zhang
2021-02-03 23:37 ` [Intel-gfx] [PATCH RFC v1 2/6] swiotlb: convert variables to arrays Dongli Zhang
2021-02-03 23:37   ` Dongli Zhang
2021-02-03 23:37   ` Dongli Zhang
2021-02-03 23:37   ` [Nouveau] " Dongli Zhang
2021-02-03 23:37   ` Dongli Zhang
2021-02-03 23:37   ` Dongli Zhang
2021-02-04  4:17   ` kernel test robot
2021-02-04  5:16   ` kernel test robot
2021-02-04  7:29   ` [Intel-gfx] " Christoph Hellwig
2021-02-04  7:29     ` Christoph Hellwig
2021-02-04  7:29     ` [Nouveau] " Christoph Hellwig
2021-02-04  7:29     ` Christoph Hellwig
2021-02-04  7:29     ` Christoph Hellwig
2021-02-04 11:49     ` [Intel-gfx] " Robin Murphy
2021-02-04 11:49       ` Robin Murphy
2021-02-04 11:49       ` Robin Murphy
2021-02-04 11:49       ` [Nouveau] " Robin Murphy
2021-02-04 11:49       ` Robin Murphy
2021-02-04 11:49       ` Robin Murphy
2021-02-04 19:31       ` [Intel-gfx] " Konrad Rzeszutek Wilk
2021-02-04 19:31         ` Konrad Rzeszutek Wilk
2021-02-04 19:31         ` Konrad Rzeszutek Wilk
2021-02-04 19:31         ` [Nouveau] " Konrad Rzeszutek Wilk
2021-02-04 19:31         ` Konrad Rzeszutek Wilk
2021-02-04 19:31         ` Konrad Rzeszutek Wilk
2021-02-03 23:37 ` [Intel-gfx] [PATCH RFC v1 3/6] swiotlb: introduce swiotlb_get_type() to calculate swiotlb buffer type Dongli Zhang
2021-02-03 23:37   ` Dongli Zhang
2021-02-03 23:37   ` Dongli Zhang
2021-02-03 23:37   ` [Nouveau] " Dongli Zhang
2021-02-03 23:37   ` Dongli Zhang
2021-02-03 23:37   ` Dongli Zhang
2021-02-03 23:37 ` [Intel-gfx] [PATCH RFC v1 4/6] swiotlb: enable 64-bit swiotlb Dongli Zhang
2021-02-03 23:37   ` Dongli Zhang
2021-02-03 23:37   ` Dongli Zhang
2021-02-03 23:37   ` [Nouveau] " Dongli Zhang
2021-02-03 23:37   ` Dongli Zhang
2021-02-03 23:37   ` Dongli Zhang
2021-02-04  4:10   ` kernel test robot
2021-02-03 23:37 ` [Intel-gfx] [PATCH RFC v1 5/6] xen-swiotlb: convert variables to arrays Dongli Zhang
2021-02-03 23:37   ` Dongli Zhang
2021-02-03 23:37   ` Dongli Zhang
2021-02-03 23:37   ` [Nouveau] " Dongli Zhang
2021-02-03 23:37   ` Dongli Zhang
2021-02-03 23:37   ` Dongli Zhang
2021-02-04  8:40   ` Christoph Hellwig [this message]
2021-02-04  8:40     ` Christoph Hellwig
2021-02-04  8:40     ` [Nouveau] " Christoph Hellwig
2021-02-04  8:40     ` Christoph Hellwig
2021-02-04  8:40     ` Christoph Hellwig
2021-02-07 15:56     ` [Intel-gfx] " Christoph Hellwig
2021-02-07 15:56       ` Christoph Hellwig
2021-02-07 15:56       ` [Nouveau] " Christoph Hellwig
2021-02-07 15:56       ` Christoph Hellwig
2021-02-07 15:56       ` Christoph Hellwig
2021-02-19 20:32       ` [Intel-gfx] " Konrad Rzeszutek Wilk
2021-02-19 20:32         ` Konrad Rzeszutek Wilk
2021-02-19 20:32         ` Konrad Rzeszutek Wilk
2021-02-19 20:32         ` [Nouveau] " Konrad Rzeszutek Wilk
2021-02-19 20:32         ` Konrad Rzeszutek Wilk
2021-02-19 20:32         ` Konrad Rzeszutek Wilk
2021-02-19 23:59         ` [Intel-gfx] " Boris Ostrovsky
2021-02-19 23:59           ` Boris Ostrovsky
2021-02-19 23:59           ` Boris Ostrovsky
2021-02-19 23:59           ` [Nouveau] " Boris Ostrovsky
2021-02-19 23:59           ` Boris Ostrovsky
2021-02-19 23:59           ` Boris Ostrovsky
2021-02-23  1:22         ` [Intel-gfx] " Stefano Stabellini
2021-02-23  1:22           ` Stefano Stabellini
2021-02-23  1:22           ` Stefano Stabellini
2021-02-23  1:22           ` [Nouveau] " Stefano Stabellini
2021-02-23  1:22           ` Stefano Stabellini
2021-02-23  1:22           ` Stefano Stabellini
2021-02-03 23:37 ` [Intel-gfx] [PATCH RFC v1 6/6] xen-swiotlb: enable 64-bit xen-swiotlb Dongli Zhang
2021-02-03 23:37   ` Dongli Zhang
2021-02-03 23:37   ` Dongli Zhang
2021-02-03 23:37   ` [Nouveau] " Dongli Zhang
2021-02-03 23:37   ` Dongli Zhang
2021-02-03 23:37   ` Dongli Zhang
2021-02-04 11:50   ` kernel test robot
2021-02-04 19:53 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for swiotlb: 64-bit DMA buffer Patchwork
2021-02-04 19:54 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2021-02-04 20:22 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2021-02-05  2:08 ` [Intel-gfx] ✗ Fi.CI.IGT: failure " Patchwork

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210204084023.GA32328@lst.de \
    --to=hch@lst.de \
    --cc=adrian.hunter@intel.com \
    --cc=airlied@linux.ie \
    --cc=akpm@linux-foundation.org \
    --cc=bauerman@linux.ibm.com \
    --cc=benh@kernel.crashing.org \
    --cc=bhelgaas@google.com \
    --cc=boris.ostrovsky@oracle.com \
    --cc=bp@alien8.de \
    --cc=bskeggs@redhat.com \
    --cc=chris@chris-wilson.co.uk \
    --cc=dongli.zhang@oracle.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=hpa@zytor.com \
    --cc=intel-gfx@lists.freedesktop.org \
    --cc=iommu@lists.linux-foundation.org \
    --cc=jgross@suse.com \
    --cc=joe.jin@oracle.com \
    --cc=konrad.wilk@oracle.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mips@vger.kernel.org \
    --cc=linux-mmc@vger.kernel.org \
    --cc=linux-pci@vger.kernel.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=m.szyprowski@samsung.com \
    --cc=matthew.auld@intel.com \
    --cc=mingo@kernel.org \
    --cc=mingo@redhat.com \
    --cc=mpe@ellerman.id.au \
    --cc=nouveau@lists.freedesktop.org \
    --cc=paulus@samba.org \
    --cc=peterz@infradead.org \
    --cc=robin.murphy@arm.com \
    --cc=rppt@kernel.org \
    --cc=sstabellini@kernel.org \
    --cc=tglx@linutronix.de \
    --cc=thomas.lendacky@amd.com \
    --cc=tsbogend@alpha.franken.de \
    --cc=ulf.hansson@linaro.org \
    --cc=x86@kernel.org \
    --cc=xen-devel@lists.xenproject.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.