From: Jonathan Lemon <jonathan.lemon@gmail.com>
To: Jason Gunthorpe <jgg@nvidia.com>
Cc: Bjorn Helgaas <helgaas@kernel.org>, Aya Levin <ayal@mellanox.com>,
David Miller <davem@davemloft.net>,
kuba@kernel.org, saeedm@mellanox.com, mkubecek@suse.cz,
linux-pci@vger.kernel.org, netdev@vger.kernel.org,
tariqt@mellanox.com, alexander.h.duyck@linux.intel.com
Subject: Re: [net-next 10/10] net/mlx5e: Add support for PCI relaxed ordering
Date: Thu, 9 Jul 2020 13:33:51 -0700 [thread overview]
Message-ID: <20200709203351.2bj4vf5gehphy2ru@bsd-mbp.dhcp.thefacebook.com> (raw)
In-Reply-To: <20200709182011.GQ23676@nvidia.com>
On Thu, Jul 09, 2020 at 03:20:11PM -0300, Jason Gunthorpe wrote:
> On Thu, Jul 09, 2020 at 10:35:50AM -0700, Jonathan Lemon wrote:
> > On Wed, Jul 08, 2020 at 08:26:02PM -0300, Jason Gunthorpe wrote:
> > > On Wed, Jul 08, 2020 at 06:16:30PM -0500, Bjorn Helgaas wrote:
> > > > I suspect there may be device-specific controls, too, because [1]
> > > > claims to enable/disable Relaxed Ordering but doesn't touch the
> > > > PCIe Device Control register. Device-specific controls are
> > > > certainly allowed, but of course it would be up to the driver, and
> > > > the device cannot generate TLPs with Relaxed Ordering unless the
> > > > architected PCIe Enable Relaxed Ordering bit is *also* set.
> > >
> > > Yes, at least on RDMA relaxed ordering can be set on a per transaction
> > > basis and is something userspace can choose to use or not at a fine
> > > granularity. This is because we have to support historical
> > > applications that make assumptions that data arrives in certain
> > > orders.
> > >
> > > I've been thinking of doing the same as this patch but for RDMA kernel
> > > ULPs and just globally turn it on if the PCI CAP is enabled as none of
> > > our in-kernel uses have the legacy data ordering problem.
> >
> > If I'm following this correctly - there are two different controls being
> > discussed here:
> >
> > 1) having the driver request PCI relaxed ordering, which may or may
> > not be granted, based on other system settings, and
>
> This is what Bjorn was thinking about, yes, it is some PCI layer
> function to control the global config space bit.
>
> > 2) having the driver set RO on the transactions it initiates, which
> > are honored iff the PCI bit is set.
> >
> > It seems that in addition to the PCI core changes, there still is a need
> > for driver controls? Unless the driver always enables RO if it's capable?
>
> I think the PCI spec imagined that when the config space RO bit was
> enabled the PCI device would just start using RO packets, in an
> appropriate and device specific way.
>
> So the fine grained control in #2 is something done extra by some
> devices.
>
> IMHO if the driver knows it is functionally correct with RO then it
> should enable it fully on the device when the config space bit is set.
Sounds reasonable to me.
--
Jonathan
next prev parent reply other threads:[~2020-07-09 20:34 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20200623195229.26411-1-saeedm@mellanox.com>
[not found] ` <20200623195229.26411-11-saeedm@mellanox.com>
[not found] ` <20200623143118.51373eb7@kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com>
[not found] ` <dda5c2b729bbaf025592aa84e2bdb84d0cda7570.camel@mellanox.com>
[not found] ` <082c6bfe-5146-c213-9220-65177717c342@mellanox.com>
2020-06-24 17:22 ` [net-next 10/10] net/mlx5e: Add support for PCI relaxed ordering Jakub Kicinski
2020-06-24 20:15 ` Saeed Mahameed
[not found] ` <20200624133018.5a4d238b@kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com>
2020-07-06 13:00 ` Aya Levin
2020-07-06 16:52 ` Jakub Kicinski
2020-07-06 19:49 ` David Miller
2040-07-08 8:22 ` Aya Levin
2020-07-08 23:16 ` Bjorn Helgaas
2020-07-08 23:26 ` Jason Gunthorpe
2020-07-09 17:35 ` Jonathan Lemon
2020-07-09 18:20 ` Jason Gunthorpe
2020-07-09 19:47 ` Jakub Kicinski
2020-07-10 2:18 ` Saeed Mahameed
2020-07-10 12:21 ` Jason Gunthorpe
2020-07-09 20:33 ` Jonathan Lemon [this message]
2020-07-14 10:47 ` Aya Levin
2020-07-23 21:03 ` Alexander Duyck
2020-06-26 20:12 ` Bjorn Helgaas
2020-06-26 20:24 ` David Miller
2020-06-29 9:32 ` Aya Levin
2020-06-29 19:33 ` Bjorn Helgaas
2020-06-29 19:57 ` Raj, Ashok
2020-06-30 7:32 ` Ding Tianhong
2020-07-05 11:15 ` Aya Levin
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=20200709203351.2bj4vf5gehphy2ru@bsd-mbp.dhcp.thefacebook.com \
--to=jonathan.lemon@gmail.com \
--cc=alexander.h.duyck@linux.intel.com \
--cc=ayal@mellanox.com \
--cc=davem@davemloft.net \
--cc=helgaas@kernel.org \
--cc=jgg@nvidia.com \
--cc=kuba@kernel.org \
--cc=linux-pci@vger.kernel.org \
--cc=mkubecek@suse.cz \
--cc=netdev@vger.kernel.org \
--cc=saeedm@mellanox.com \
--cc=tariqt@mellanox.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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).