From: Florian Westphal <fw@strlen.de>
To: Stefano Brivio <sbrivio@redhat.com>
Cc: Florian Westphal <fw@strlen.de>,
netfilter-devel@vger.kernel.org, sontu21@gmail.com
Subject: Re: [PATCH nf 1/3] nft_set_pipapo: add avx register usage tracking for NET_DEBUG builds
Date: Fri, 4 Apr 2025 13:42:33 +0200 [thread overview]
Message-ID: <20250404114233.GA28604@breakpoint.cc> (raw)
In-Reply-To: <20250404124005.75ed1949@elisabeth>
Stefano Brivio <sbrivio@redhat.com> wrote:
> This made me wonder if there's any specific reason why we would need
> #if defined(x) here instead of a common #ifdef x. It looks like there
> isn't a reason, so maybe #ifdef CONFIG_DEBUG_NET is more... expected.
Ok, I'll change it and will also update the rest as per your comments.
Not sure I will be able to spin v2 before next week though.
> Perhaps those could all be uint16_t to reflect that it's YMM registers,
> and nft_pipapo_avx2_debug_usable() could simply promote them to
> unsigned long as needed by test_bit().
I'll swich to u16 and will ditch test_bit in favor of BIT(a) & r->.
> They could even be uint32_t to represent ZMM registers (or extended
> YMM) if we want to make this AVX512-ready, I'm not sure.
Can be done later.
next prev parent reply other threads:[~2025-04-04 11:42 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-04-04 6:20 [PATCH nf 0/3] nft_set_pipapo: fix incorrect avx2 match of 5th field octet Florian Westphal
2025-04-04 6:20 ` [PATCH nf 1/3] nft_set_pipapo: add avx register usage tracking for NET_DEBUG builds Florian Westphal
2025-04-04 10:40 ` Stefano Brivio
2025-04-04 11:42 ` Florian Westphal [this message]
2025-04-04 6:20 ` [PATCH nf 2/3] nft_set_pipapo: fix incorrect avx2 match of 5th field octet Florian Westphal
2025-04-04 8:34 ` Stefano Brivio
2025-04-04 6:20 ` [PATCH nf 3/3] selftests: netfilter: add test case for recent mismatch bug Florian Westphal
2025-04-04 11:51 ` Stefano Brivio
2025-04-09 9:51 ` sontu mazumdar
2025-04-09 10:13 ` Stefano Brivio
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=20250404114233.GA28604@breakpoint.cc \
--to=fw@strlen.de \
--cc=netfilter-devel@vger.kernel.org \
--cc=sbrivio@redhat.com \
--cc=sontu21@gmail.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.