From: Jakub Kicinski <kuba@kernel.org>
To: Paolo Abeni <pabeni@redhat.com>
Cc: davem@davemloft.net, netdev@vger.kernel.org, edumazet@google.com,
michael.chan@broadcom.com
Subject: Re: [PATCH net-next 3/3] eth: bnxt: handle invalid Tx completions more gracefully
Date: Wed, 12 Jul 2023 13:50:32 -0700 [thread overview]
Message-ID: <20230712135032.28011bc4@kernel.org> (raw)
In-Reply-To: <c3ad12394627fffc5a0d8e48e019e6ef61814597.camel@redhat.com>
On Wed, 12 Jul 2023 22:31:45 +0200 Paolo Abeni wrote:
> > Is there really any difference whether one changes a byte or ors
> > in a bit? Either way it's a partial update of a word.
>
> Really not a big deal, but 'or' fetches memory and then store it, while
> move [immediate] is a single store. In case of a cache miss, 'or'
> should stall, while 'mov' should not. In general with 'mov' there
> should be less pressure on the cache and/or bus.
You're right, if the store buffer can buffer 1B stores then we won't
stall the instruction pile line. But we most likely will for the bit
op. The setting is an extremely rare path, tho, so given your
"not a big deal" disclaimer I'm intending to keep the bitfield :)
next prev parent reply other threads:[~2023-07-12 20:50 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-07-10 20:56 [PATCH net-next 0/3] eth: bnxt: handle invalid Tx completions more gracefully Jakub Kicinski
2023-07-10 20:56 ` [PATCH net-next 1/3] eth: bnxt: move and rename reset helpers Jakub Kicinski
2023-07-10 20:56 ` [PATCH net-next 2/3] eth: bnxt: take the bit to set as argument of bnxt_queue_sp_work() Jakub Kicinski
2023-07-10 20:56 ` [PATCH net-next 3/3] eth: bnxt: handle invalid Tx completions more gracefully Jakub Kicinski
2023-07-11 8:00 ` Michael Chan
2023-07-12 0:01 ` Michael Chan
2023-07-12 1:09 ` Jakub Kicinski
2023-07-12 4:11 ` Michael Chan
2023-07-12 4:24 ` Jakub Kicinski
2023-07-12 4:50 ` Michael Chan
2023-07-12 16:35 ` Jakub Kicinski
2023-07-11 10:10 ` Paolo Abeni
2023-07-12 1:19 ` Jakub Kicinski
2023-07-12 6:50 ` Paolo Abeni
2023-07-12 16:34 ` Jakub Kicinski
2023-07-12 20:31 ` Paolo Abeni
2023-07-12 20:50 ` Jakub Kicinski [this message]
2023-07-10 21:44 ` [PATCH net-next 0/3] " Michael Chan
2023-07-11 0:38 ` Jakub Kicinski
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=20230712135032.28011bc4@kernel.org \
--to=kuba@kernel.org \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=michael.chan@broadcom.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.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).