mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Ronak Doshi <doshir@vmware.com>
To: Yunsheng Lin <linyunsheng@huawei.com>,
	"netdev@vger.kernel.org" <netdev@vger.kernel.org>
Cc: "stable@vger.kernel.org" <stable@vger.kernel.org>,
	Pv-drivers <Pv-drivers@vmware.com>,
	"David S. Miller" <davem@davemloft.net>,
	Eric Dumazet <edumazet@google.com>,
	Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
	Guolin Yang <gyang@vmware.com>,
	open list <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH net] vmxnet3: use gro callback when UPT is enabled
Date: Thu, 16 Mar 2023 04:03:52 +0000	[thread overview]
Message-ID: <1743CDA0-8F35-4F60-9D22-A17788B90F9B@vmware.com> (raw)
In-Reply-To: <77c30632-849f-8b7b-42ef-be8b32981c15@huawei.com>


> On 3/15/23, 6:47 PM, "Yunsheng Lin" <linyunsheng@huawei.com <mailto:linyunsheng@huawei.com>> wrote:
>
> That's the piont I am trying to make.
> If I understand it correctly, you can not change callback from napi_gro_receive() to
> netif_receive_skb() when netdev->features has the NETIF_F_GRO bit set.
Where are we doing this? Our preference is to use netif_receive_skb() only when LRO is enabled.
If both LRO and GRO are enabled on the vnic, which API should be used?

> NETIF_F_GRO bit in netdev->features is to tell user that netstack will perform the
> software GRO processing if the packet can be GRO'ed.
Even if the packet is already LRO'ed?

> Calling netif_receive_skb() with NETIF_F_GRO bit set in netdev->features will cause
> confusion for user, IMHO.
As long as LRO is enabled and performed by ESXi (which it will do), I don’t think user cares for GRO.
Even if we use napi_gro_receive() for such case, it degrades the performance as unnecessary cycles
are spend on an already LRO'ed packet.


> As above, there is different feature bit for that, NETIF_F_LRO, NETIF_F_GRO and
> NETIF_F_GRO_HW.
> IMHO, deciding which callback to be used depending on some driver configuation
> without corporation with the above feature bits does not seems right to me.

We are not neglecting feature bits. We just know that in UPT LRO won’t be done, so we by
default use napi_gro_receive() callback.

Thanks, 
Ronak


  reply	other threads:[~2023-03-16  4:04 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-03-08 22:25 Ronak Doshi
2023-03-09  0:34 ` Yunsheng Lin
2023-03-09 22:50   ` Ronak Doshi
2023-03-10  1:02     ` Yunsheng Lin
2023-03-14 21:09       ` Ronak Doshi
2023-03-15  1:51         ` Yunsheng Lin
2023-03-15  2:27           ` Ronak Doshi
2023-03-15  3:04             ` Yunsheng Lin
2023-03-15 23:44               ` Ronak Doshi
2023-03-16  1:47                 ` Yunsheng Lin
2023-03-16  4:03                   ` Ronak Doshi [this message]
2023-03-16  4:13                     ` Jakub Kicinski
2023-03-16  5:21                       ` Ronak Doshi
2023-03-16 20:34                         ` Jakub Kicinski
2023-03-17  2:37                           ` Yunsheng Lin
2023-03-17 20:27                             ` Ronak Doshi
2023-03-18  2:43                               ` Jakub Kicinski
2023-03-23  5:43 Ronak Doshi
2023-03-23 15:48 ` Simon Horman

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=1743CDA0-8F35-4F60-9D22-A17788B90F9B@vmware.com \
    --to=doshir@vmware.com \
    --cc=Pv-drivers@vmware.com \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=gyang@vmware.com \
    --cc=kuba@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linyunsheng@huawei.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=stable@vger.kernel.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®