Netdev List
 help / color / mirror / Atom feed
From: Sagi Grimberg <sagi@grimberg.me>
To: Saeed Mahameed <saeedm@mellanox.com>,
	"David S. Miller" <davem@davemloft.net>
Cc: netdev@vger.kernel.org, Thomas Gleixner <tglx@linutronix.de>,
	Jes Sorensen <jsorensen@fb.com>
Subject: Re: [net 02/14] Revert "mlx5: move affinity hints assignments to generic code"
Date: Mon, 25 Dec 2017 15:53:17 +0200	[thread overview]
Message-ID: <459db705-4586-9eab-2f5b-15014a6730da@grimberg.me> (raw)
In-Reply-To: <20171219222456.29627-3-saeedm@mellanox.com>


> Before the offending commit, mlx5 core did the IRQ affinity itself,
> and it seems that the new generic code have some drawbacks and one
> of them is the lack for user ability to modify irq affinity after
> the initial affinity values got assigned.
> 
> The issue is still being discussed and a solution in the new generic code
> is required, until then we need to revert this patch.
> 
> This fixes the following issue:
> echo <new affinity> > /proc/irq/<x>/smp_affinity
> fails with  -EIO
> 
> This reverts commit a435393acafbf0ecff4deb3e3cb554b34f0d0664.
> Note: kept mlx5_get_vector_affinity in include/linux/mlx5/driver.h since
 > it is used in mlx5_ib driver.

This won't work for sure because the msi_desc affinity cpumask won't
ever be populated. You need to re-implement it in mlx5 if you don't want
to break rdma ULPs that rely on it.

  parent reply	other threads:[~2017-12-25 13:53 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-12-19 22:24 [pull request][net 00/14] Mellanox, mlx5 fixes 2017-12-19 Saeed Mahameed
2017-12-19 22:24 ` [net 01/14] net/mlx5: FPGA, return -EINVAL if size is zero Saeed Mahameed
2017-12-19 22:24 ` [net 02/14] Revert "mlx5: move affinity hints assignments to generic code" Saeed Mahameed
2017-12-19 22:42   ` Jes Sorensen
2017-12-25 13:53   ` Sagi Grimberg [this message]
2017-12-26 15:58     ` Saeed Mahameed
2017-12-26 17:14       ` Sagi Grimberg
2018-01-04 20:19         ` Saeed Mahameed
2017-12-19 22:24 ` [net 03/14] net/mlx5: Fix rate limit packet pacing naming and struct Saeed Mahameed
2017-12-19 22:24 ` [net 04/14] net/mlx5e: Fix ETS BW check Saeed Mahameed
2017-12-20  7:42   ` Or Gerlitz
2017-12-19 22:24 ` [net 05/14] net/mlx5e: Fix features check of IPv6 traffic Saeed Mahameed
2017-12-20  7:45   ` Or Gerlitz
2017-12-19 22:24 ` [net 06/14] net/mlx5e: Fix defaulting RX ring size when not needed Saeed Mahameed
2017-12-19 22:24 ` [net 07/14] net/mlx5: Fix misspelling in the error message and comment Saeed Mahameed
2017-12-19 22:24 ` [net 08/14] net/mlx5: Fix error flow in CREATE_QP command Saeed Mahameed
2017-12-19 22:24 ` [net 09/14] net/mlx5e: Fix possible deadlock of VXLAN lock Saeed Mahameed
2017-12-19 22:24 ` [net 10/14] net/mlx5e: Add refcount to VXLAN structure Saeed Mahameed
2017-12-19 22:24 ` [net 11/14] net/mlx5e: Prevent possible races in VXLAN control flow Saeed Mahameed
2017-12-19 22:24 ` [net 12/14] net/mlx5: Fix steering memory leak Saeed Mahameed
2017-12-19 22:24 ` [net 13/14] net/mlx5: Cleanup IRQs in case of unload failure Saeed Mahameed
2017-12-19 22:24 ` [net 14/14] net/mlx5: Stay in polling mode when command EQ destroy fails Saeed Mahameed
2017-12-20 18:42 ` [pull request][net 00/14] Mellanox, mlx5 fixes 2017-12-19 David Miller

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=459db705-4586-9eab-2f5b-15014a6730da@grimberg.me \
    --to=sagi@grimberg.me \
    --cc=davem@davemloft.net \
    --cc=jsorensen@fb.com \
    --cc=netdev@vger.kernel.org \
    --cc=saeedm@mellanox.com \
    --cc=tglx@linutronix.de \
    /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