From: "Alexei Starovoitov" <alexei.starovoitov@gmail.com>
To: "Eduard Zingerman" <eddyz87@gmail.com>,
"Yonghong Song" <yonghong.song@linux.dev>, <bpf@vger.kernel.org>
Cc: "Alexei Starovoitov" <ast@kernel.org>,
"Andrii Nakryiko" <andrii@kernel.org>,
"Daniel Borkmann" <daniel@iogearbox.net>, <kernel-team@fb.com>
Subject: Re: [PATCH bpf-next v4 00/20] bpf: Run exception cleanup landing pads when bpf_throw() unwinds
Date: Tue, 22 Sep 2026 23:37:02 +0000 [thread overview]
Message-ID: <DLM8NP9S8A4E.1YIS9HRMSR62@gmail.com> (raw)
In-Reply-To: <37e53199dfda608de30a31fc51d22ed2b25d6d2e.camel@gmail.com>
On Tue Sep 22, 2026 at 11:08 PM UTC, Eduard Zingerman wrote:
> On Tue, 2026-09-22 at 21:47 +0000, Alexei Starovoitov wrote:
>> On Tue Sep 22, 2026 at 4:27 AM UTC, Eduard Zingerman wrote:
>> >
>> > Total size of executable sections for all Meta BPF object files used
>> > for CI veristat testing is 10Mb. Of these there are 30K non-helper
>> > call instructions in total.
>> > So we are talking about increase by 8 * 30K = 240K ~ 2.4% worst case.
>> > Note that the instruction encoding optimized for size already hearts
>> > us in src/dst registers department: we have no room for virtual
>> > registers, which would have simplified e.g. register allocation task
>> > for ARM64. Point being that optimizing intermediate IR for size is not
>> > always a right target.
>>
>> I wasn't talking about increase in bpf ELF size,
>> but the amount of the verifier work necessary to double the number
>> of call insns.
>
> I don't understand what you mean by the amount of the verifier work.
> Traced program paths would remain the same, only the encoding of the
> information about exceptions changes.
Any new insn requires plumbing through out.
imo ld_imm64 encoding FD inline was a mistake.
We should have went with relocations through out.
Much cleaner to extend.
Same philosophy here. Landing pad is a metadata.
It's not a good idea to encode metadata into assembly instruction.
bpf ISA is not a high level IR.
> Do we have a working toolchain somewhere? I can work a few examples.
Please send SCEV upstream asap. This is way more important
then arguing over this bits.
next prev parent reply other threads:[~2026-09-22 23:37 UTC|newest]
Thread overview: 80+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-09-21 21:00 [PATCH bpf-next v4 00/20] bpf: Run exception cleanup landing pads when bpf_throw() unwinds Yonghong Song
2026-09-21 21:00 ` [PATCH bpf-next v4 01/20] bpf: Accept the compiler's exception cleanup table at program load Yonghong Song
2026-09-21 21:56 ` bot+bpf-ci
2026-09-22 3:27 ` Yonghong Song
2026-09-21 21:00 ` [PATCH bpf-next v4 02/20] bpf: Add the bpf_unwind_resume() kfunc Yonghong Song
2026-09-21 21:56 ` bot+bpf-ci
2026-09-22 3:31 ` Yonghong Song
2026-09-21 21:00 ` [PATCH bpf-next v4 03/20] bpf: Add lookups for exception cleanup resumes and landing pads Yonghong Song
2026-09-22 4:04 ` Alexei Starovoitov
2026-09-22 5:28 ` Yonghong Song
2026-09-21 21:00 ` [PATCH bpf-next v4 04/20] bpf: Prepare for an exception cleanup table before the CFG walk Yonghong Song
2026-09-22 18:27 ` Eduard Zingerman
2026-09-23 3:07 ` Yonghong Song
2026-09-23 3:54 ` Eduard Zingerman
2026-09-23 4:05 ` Yonghong Song
2026-09-21 21:00 ` [PATCH bpf-next v4 05/20] bpf: Make exception landing pads reachable in the CFG Yonghong Song
2026-09-21 21:01 ` [PATCH bpf-next v4 06/20] bpf: Explore the landing pads no call site reaches Yonghong Song
2026-09-21 23:58 ` Eduard Zingerman
2026-09-22 3:32 ` Yonghong Song
2026-09-22 4:10 ` Eduard Zingerman
2026-09-21 21:01 ` [PATCH bpf-next v4 07/20] bpf: Refuse exception cleanup shapes bpf_throw() cannot dispatch Yonghong Song
2026-09-21 21:20 ` sashiko-bot
2026-09-22 3:39 ` Yonghong Song
2026-09-21 21:56 ` bot+bpf-ci
2026-09-22 3:44 ` Yonghong Song
2026-09-22 0:30 ` Eduard Zingerman
2026-09-22 3:45 ` Yonghong Song
2026-09-22 21:43 ` Eduard Zingerman
2026-09-23 3:11 ` Yonghong Song
2026-09-21 21:01 ` [PATCH bpf-next v4 08/20] bpf: Walk the exception unwind in the verifier Yonghong Song
2026-09-21 21:40 ` sashiko-bot
2026-09-22 4:17 ` Yonghong Song
2026-09-21 21:56 ` bot+bpf-ci
2026-09-22 5:21 ` Yonghong Song
2026-09-22 4:08 ` Alexei Starovoitov
2026-09-22 5:25 ` Yonghong Song
2026-09-22 21:53 ` Eduard Zingerman
2026-09-23 3:18 ` Yonghong Song
2026-09-22 23:43 ` Eduard Zingerman
2026-09-23 3:21 ` Yonghong Song
2026-09-21 21:01 ` [PATCH bpf-next v4 09/20] bpf: Refuse a private stack for a program with an exception cleanup table Yonghong Song
2026-09-21 21:01 ` [PATCH bpf-next v4 10/20] bpf: Dispatch exception cleanup pads from bpf_throw() Yonghong Song
2026-09-22 21:38 ` Eduard Zingerman
2026-09-23 3:22 ` Yonghong Song
2026-09-21 21:01 ` [PATCH bpf-next v4 11/20] bpf, x86: Dispatch exception cleanup pads at run time Yonghong Song
2026-09-21 21:01 ` [PATCH bpf-next v4 12/20] bpf, arm64: " Yonghong Song
2026-09-21 21:01 ` [PATCH bpf-next v4 13/20] libbpf: Resolve the compiler's _Unwind_Resume to the kernel's kfunc Yonghong Song
2026-09-21 21:13 ` sashiko-bot
2026-09-21 21:01 ` [PATCH bpf-next v4 14/20] libbpf: Add cleanup_info to bpf_prog_load_opts Yonghong Song
2026-09-21 21:01 ` [PATCH bpf-next v4 15/20] libbpf: Collect .bpf_cleanup records and pass them to the kernel Yonghong Song
2026-09-21 21:20 ` sashiko-bot
2026-09-21 21:01 ` [PATCH bpf-next v4 16/20] libbpf: Carry the exception cleanup table through the light skeleton Yonghong Song
2026-09-21 21:02 ` [PATCH bpf-next v4 17/20] libbpf: Let the static linker carry .bpf_cleanup relocations Yonghong Song
2026-09-21 21:02 ` [PATCH bpf-next v4 18/20] selftests/bpf: Add an end-to-end .bpf_cleanup exception test Yonghong Song
2026-09-21 21:22 ` sashiko-bot
2026-09-22 5:26 ` Yonghong Song
2026-09-21 21:56 ` bot+bpf-ci
2026-09-21 21:02 ` [PATCH bpf-next v4 19/20] selftests/bpf: Cover the exception cleanup shapes the chain does not reach Yonghong Song
2026-09-21 21:19 ` sashiko-bot
2026-09-21 21:02 ` [PATCH bpf-next v4 20/20] selftests/bpf: Load an exception cleanup program from a light skeleton Yonghong Song
2026-09-22 1:08 ` [PATCH bpf-next v4 00/20] bpf: Run exception cleanup landing pads when bpf_throw() unwinds Eduard Zingerman
2026-09-22 2:16 ` Alexei Starovoitov
2026-09-22 2:31 ` Kumar Kartikeya Dwivedi
2026-09-22 21:44 ` Alexei Starovoitov
2026-09-23 4:36 ` Kumar Kartikeya Dwivedi
2026-09-23 4:54 ` Alexei Starovoitov
2026-09-23 5:20 ` Kumar Kartikeya Dwivedi
2026-09-23 6:16 ` Eduard Zingerman
2026-09-23 6:44 ` Kumar Kartikeya Dwivedi
2026-09-22 4:27 ` Eduard Zingerman
2026-09-22 21:47 ` Alexei Starovoitov
2026-09-22 23:08 ` Eduard Zingerman
2026-09-22 23:37 ` Alexei Starovoitov [this message]
2026-09-23 0:04 ` Eduard Zingerman
2026-09-23 19:04 ` Eduard Zingerman
2026-09-23 19:24 ` Andrii Nakryiko
2026-09-23 19:34 ` Kumar Kartikeya Dwivedi
2026-09-23 21:34 ` Alexei Starovoitov
2026-09-23 22:00 ` Eduard Zingerman
2026-09-23 23:22 ` Alexei Starovoitov
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=DLM8NP9S8A4E.1YIS9HRMSR62@gmail.com \
--to=alexei.starovoitov@gmail.com \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=eddyz87@gmail.com \
--cc=kernel-team@fb.com \
--cc=yonghong.song@linux.dev \
/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