From: Paul Chaignon <paul.chaignon@orange.com>
To: "Paul Burton" <paulburton@kernel.org>,
"Björn Töpel" <bjorn.topel@gmail.com>
Cc: Mahshid Khezri <khezri.mahshid@gmail.com>,
paul.chaignon@gmail.com, bpf@vger.kernel.org,
netdev@vger.kernel.org, Alexei Starovoitov <ast@kernel.org>,
Daniel Borkmann <daniel@iogearbox.net>,
Martin KaFai Lau <kafai@fb.com>, Song Liu <songliubraving@fb.com>,
Yonghong Song <yhs@fb.com>, Andrii Nakryiko <andriin@fb.com>
Subject: [PATCH bpf 0/2] Limit tail calls to 33 in all JIT compilers
Date: Mon, 9 Dec 2019 19:51:52 +0100 [thread overview]
Message-ID: <cover.1575916815.git.paul.chaignon@gmail.com> (raw)
The BPF interpreter and all JIT compilers, except RISC-V's and MIPS',
enforce a 33-tail calls limit at runtime. Because of this discrepancy, a
BPF program can have a different behavior and output depending on whether
it is interpreted or JIT compiled, or depending on the underlying
architecture.
This patchset changes the RISC-V and MIPS JIT compilers to limit tail
calls to 33 instead of 32. I have checked other BPF JIT compilers for the
same discrepancy.
Paul Chaignon (2):
bpf, riscv: limit to 33 tail calls
bpf, mips: limit to 33 tail calls
arch/mips/net/ebpf_jit.c | 9 +++++----
arch/riscv/net/bpf_jit_comp.c | 4 ++--
2 files changed, 7 insertions(+), 6 deletions(-)
--
2.17.1
next reply other threads:[~2019-12-09 18:51 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-12-09 18:51 Paul Chaignon [this message]
2019-12-09 18:52 ` [PATCH bpf 1/2] bpf, riscv: limit to 33 tail calls Paul Chaignon
2019-12-09 19:57 ` Björn Töpel
2019-12-10 6:31 ` Björn Töpel
2019-12-10 9:36 ` Paul Chaignon
2019-12-09 18:52 ` [PATCH bpf 2/2] bpf, mips: " Paul Chaignon
2019-12-10 23:23 ` Paul Burton
2019-12-12 16:19 ` Daniel Borkmann
2019-12-18 9:32 ` Alexander Lobakin
2019-12-18 9:58 ` Paul Chaignon
2019-12-18 10:02 ` Alexander Lobakin
2019-12-10 18:19 ` [PATCH bpf 0/2] Limit tail calls to 33 in all JIT compilers Martin Lau
2019-12-11 13:00 ` Daniel Borkmann
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=cover.1575916815.git.paul.chaignon@gmail.com \
--to=paul.chaignon@orange.com \
--cc=andriin@fb.com \
--cc=ast@kernel.org \
--cc=bjorn.topel@gmail.com \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=kafai@fb.com \
--cc=khezri.mahshid@gmail.com \
--cc=netdev@vger.kernel.org \
--cc=paul.chaignon@gmail.com \
--cc=paulburton@kernel.org \
--cc=songliubraving@fb.com \
--cc=yhs@fb.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).