DPDK patches and discussions
 help / color / Atom feed
From: Thomas Monjalon <thomas@monjalon.net>
To: "Stojaczyk, Dariusz" <dariusz.stojaczyk@intel.com>
Cc: Jerin Jacob Kollanukkaran <jerinj@marvell.com>,
	David Marchand <david.marchand@redhat.com>,
	"Burakov, Anatoly" <anatoly.burakov@intel.com>,
	"dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [dpdk-dev] [PATCH v4 0/4] Fixes on IOVA mode selection
Date: Tue, 23 Jul 2019 09:21:33 +0200
Message-ID: <7803044.SvP54Un6Iq@xps> (raw)
In-Reply-To: <BYAPR18MB24248F465CD67C4654F497F1C8C70@BYAPR18MB2424.namprd18.prod.outlook.com>

23/07/2019 07:27, Jerin Jacob Kollanukkaran:
> From: Stojaczyk, Dariusz <dariusz.stojaczyk@intel.com>
> > From: Jerin Jacob Kollanukkaran [mailto:jerinj@marvell.com]
> > > From: Stojaczyk, Dariusz <dariusz.stojaczyk@intel.com>
> > > >
> > > > This introduces a regression where uio-bound devies are attached to
> > > > a DPDK app at runtime.

Yes it is a regression on purpose.
We can also name it a behaviour change (more below).

> > >
[...]
> There reason to choose VA incase if bus detects DC is following:
> 
> - All drivers are expected to work in RTE_IOVA_VA mode, irrespective of
>       physical address availability.
> - By default, the mempool, first asks for IOVA-contiguous memory using
>       ``RTE_MEMZONE_IOVA_CONTIG``. This is slow in RTE_IOVA_PA mode and it may
>       affect the application boot time.
> - It is easy to enable large amount of IOVA-contiguous memory use-cases
>       with IOVA in VA mode.
> 
[...]
> > The PCI device could have been simply hotplugged to the system after DPDK
> > app start. DPDK didn't know about it at initialization, so it picked
> > RTE_IOVA_VA and then would fail to attach any UIO-bound device ever
> > after:
> > 
> > EAL:   Expecting 'PA' IOVA mode but current mode is 'VA', not initializing
> 
> We have RTE_PCI_DRV_NEED_IOVA_AS_VA devices in DPDK, Which can work
> Only on VA. If we default 'PA' incase of DC, then what do with hotplugging on those devices?
[...]
> > > > When there are no devices attached at initialization, the only safe
> > > > default should be RTE_IOVA_PA. With RTE_IOVA_VA we just won't be
> > > > able to do any DMA to uio-bound PCI devices.

As Jerin explained, there is no safe default.
There are two cases which cannot work together:
	1/ no IOMMU
	2/ driver supporting only IOMMU address (named IOVA_AS_VA)

In the past we were defaulting to physical addressing,
it was in favor of case 1.
Now we decided to switch to IOMMU address by default,
which is in favor of case 2.
As explained above by Jerin, this is considered as an improvement.
We should explain this change in the known issues of the release notes.

The only real fix would be to allow both addresses at the same time,
with separate memory allocators.



  reply index

Thread overview: 57+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-07-10 21:48 [dpdk-dev] [PATCH 0/2] " David Marchand
2019-07-10 21:48 ` [dpdk-dev] [PATCH 1/2] Revert "bus/pci: add Mellanox kernel driver type" David Marchand
2019-07-16 10:37   ` [dpdk-dev] [EXT] " Jerin Jacob Kollanukkaran
2019-07-10 21:48 ` [dpdk-dev] [PATCH 2/2] eal: fix IOVA mode selection as VA for pci drivers David Marchand
2019-07-11 14:40   ` Thomas Monjalon
2019-07-12  8:05     ` Jerin Jacob Kollanukkaran
2019-07-12 11:03   ` Burakov, Anatoly
2019-07-12 12:43     ` Thomas Monjalon
2019-07-12 12:58       ` Burakov, Anatoly
2019-07-12 13:19         ` Bruce Richardson
2019-07-15 14:26       ` Jerin Jacob Kollanukkaran
2019-07-15 15:03         ` Thomas Monjalon
2019-07-15 15:35           ` Jerin Jacob Kollanukkaran
2019-07-15 16:06             ` Thomas Monjalon
2019-07-15 16:27               ` Jerin Jacob Kollanukkaran
2019-07-16 13:46 ` [dpdk-dev] [PATCH v2 0/4] Fixes on IOVA mode selection jerinj
2019-07-16 13:46   ` [dpdk-dev] [PATCH v2 1/4] Revert "bus/pci: add Mellanox kernel driver type" jerinj
2019-07-16 13:46   ` [dpdk-dev] [PATCH v2 2/4] eal: fix IOVA mode selection as VA for pci drivers jerinj
2019-07-16 14:26     ` Burakov, Anatoly
2019-07-16 15:07       ` Jerin Jacob Kollanukkaran
2019-07-16 13:46   ` [dpdk-dev] [PATCH v2 3/4] eal: change RTE_PCI_DRV_IOVA_AS_VA flag name jerinj
2019-07-16 13:46   ` [dpdk-dev] [PATCH v2 4/4] eal: select IOVA mode as VA for default case jerinj
2019-07-16 14:33     ` Burakov, Anatoly
2019-07-17  8:33       ` [dpdk-dev] [EXT] " Jerin Jacob Kollanukkaran
2019-07-17 12:38         ` Burakov, Anatoly
2019-07-17 14:04           ` Jerin Jacob Kollanukkaran
2019-07-18  6:45   ` [dpdk-dev] [PATCH v3 0/4] Fixes on IOVA mode selection jerinj
2019-07-18  6:45     ` [dpdk-dev] [PATCH v3 1/4] Revert "bus/pci: add Mellanox kernel driver type" jerinj
2019-07-18  6:45     ` [dpdk-dev] [PATCH v3 2/4] eal: fix IOVA mode selection as VA for pci drivers jerinj
2019-07-18  6:45     ` [dpdk-dev] [PATCH v3 3/4] eal: change RTE_PCI_DRV_IOVA_AS_VA flag name jerinj
2019-07-18  6:45     ` [dpdk-dev] [PATCH v3 4/4] eal: select IOVA mode as VA for default case jerinj
2019-07-22 11:28     ` [dpdk-dev] [PATCH v3 0/4] Fixes on IOVA mode selection David Marchand
2019-07-22 12:56 ` [dpdk-dev] [PATCH v4 " David Marchand
2019-07-22 12:56   ` [dpdk-dev] [PATCH v4 1/4] Revert "bus/pci: add Mellanox kernel driver type" David Marchand
2019-07-22 12:56   ` [dpdk-dev] [PATCH v4 2/4] eal: fix IOVA mode selection as VA for PCI drivers David Marchand
2019-11-25  9:33     ` Ferruh Yigit
2019-11-25 10:22       ` Thomas Monjalon
2019-11-25 12:03         ` Ferruh Yigit
2019-11-25 12:36           ` David Marchand
2019-11-25 12:58             ` Burakov, Anatoly
2019-11-25 14:29               ` Thomas Monjalon
2019-11-25 11:07       ` Jerin Jacob
2019-07-22 12:56   ` [dpdk-dev] [PATCH v4 3/4] drivers: change IOVA as VA PCI flag name David Marchand
2019-07-22 12:56   ` [dpdk-dev] [PATCH v4 4/4] eal: select IOVA as VA mode for default case David Marchand
2019-07-22 15:53   ` [dpdk-dev] [PATCH v4 0/4] Fixes on IOVA mode selection Thomas Monjalon
2019-07-23  3:35     ` Stojaczyk, Dariusz
2019-07-23  4:18       ` Jerin Jacob Kollanukkaran
2019-07-23  4:54         ` Stojaczyk, Dariusz
2019-07-23  5:27           ` Jerin Jacob Kollanukkaran
2019-07-23  7:21             ` Thomas Monjalon [this message]
2019-07-23  9:57             ` Burakov, Anatoly
2019-07-23 10:25               ` Thomas Monjalon
2019-07-23 13:56                 ` Burakov, Anatoly
2019-07-23 14:24                   ` [dpdk-dev] [EXT] " Jerin Jacob Kollanukkaran
2019-07-23 14:29                   ` [dpdk-dev] " Burakov, Anatoly
2019-07-23 14:36                     ` [dpdk-dev] [EXT] " Jerin Jacob Kollanukkaran
2019-07-23 15:47                       ` Burakov, Anatoly

Reply instructions:

You may reply publically 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=7803044.SvP54Un6Iq@xps \
    --to=thomas@monjalon.net \
    --cc=anatoly.burakov@intel.com \
    --cc=dariusz.stojaczyk@intel.com \
    --cc=david.marchand@redhat.com \
    --cc=dev@dpdk.org \
    --cc=jerinj@marvell.com \
    /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

DPDK patches and discussions

Archives are clonable:
	git clone --mirror http://inbox.dpdk.org/dev/0 dev/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 dev dev/ http://inbox.dpdk.org/dev \
		dev@dpdk.org
	public-inbox-index dev


Newsgroup available over NNTP:
	nntp://inbox.dpdk.org/inbox.dpdk.dev


AGPL code for this site: git clone https://public-inbox.org/ public-inbox