From: Peter Zijlstra <peterz@infradead.org>
To: Menglong Dong <menglong8.dong@gmail.com>
Cc: rostedt@goodmis.org, mark.rutland@arm.com,
alexei.starovoitov@gmail.com, catalin.marinas@arm.com,
will@kernel.org, mhiramat@kernel.org, tglx@linutronix.de,
mingo@redhat.com, bp@alien8.de, dave.hansen@linux.intel.com,
x86@kernel.org, hpa@zytor.com, ast@kernel.org,
daniel@iogearbox.net, andrii@kernel.org, martin.lau@linux.dev,
eddyz87@gmail.com, yonghong.song@linux.dev,
john.fastabend@gmail.com, kpsingh@kernel.org, sdf@fomichev.me,
jolsa@kernel.org, davem@davemloft.net, dsahern@kernel.org,
mathieu.desnoyers@efficios.com, nathan@kernel.org,
nick.desaulniers+lkml@gmail.com, morbo@google.com,
samitolvanen@google.com, kees@kernel.org,
dongml2@chinatelecom.cn, akpm@linux-foundation.org,
riel@surriel.com, rppt@kernel.org,
linux-arm-kernel@lists.infradead.org,
linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org,
bpf@vger.kernel.org, netdev@vger.kernel.org,
llvm@lists.linux.dev
Subject: Re: [PATCH v4 1/4] x86/ibt: factor out cfi and fineibt offset
Date: Mon, 3 Mar 2025 17:54:54 +0100 [thread overview]
Message-ID: <20250303165454.GB11590@noisy.programming.kicks-ass.net> (raw)
In-Reply-To: <20250303132837.498938-2-dongml2@chinatelecom.cn>
On Mon, Mar 03, 2025 at 09:28:34PM +0800, Menglong Dong wrote:
> For now, the layout of cfi and fineibt is hard coded, and the padding is
> fixed on 16 bytes.
>
> Factor out FINEIBT_INSN_OFFSET and CFI_INSN_OFFSET. CFI_INSN_OFFSET is
> the offset of cfi, which is the same as FUNCTION_ALIGNMENT when
> CALL_PADDING is enabled. And FINEIBT_INSN_OFFSET is the offset where we
> put the fineibt preamble on, which is 16 for now.
>
> When the FUNCTION_ALIGNMENT is bigger than 16, we place the fineibt
> preamble on the last 16 bytes of the padding for better performance, which
> means the fineibt preamble don't use the space that cfi uses.
>
> The FINEIBT_INSN_OFFSET is not used in fineibt_caller_start and
> fineibt_paranoid_start, as it is always "0x10". Note that we need to
> update the offset in fineibt_caller_start and fineibt_paranoid_start if
> FINEIBT_INSN_OFFSET changes.
>
> Signed-off-by: Menglong Dong <dongml2@chinatelecom.cn>
I'm confused as to what exactly you mean.
Preamble will have __cfi symbol and some number of NOPs right before
actual symbol like:
__cfi_foo:
mov $0x12345678, %reg
nop
nop
nop
...
foo:
FineIBT must be at foo-16, has nothing to do with performance. This 16
can also be spelled: fineibt_preamble_size.
The total size of the preamble is FUNCTION_PADDING_BYTES + CFI_CLANG*5.
If you increase FUNCTION_PADDING_BYTES by another 5, which is what you
want I think, then we'll have total preamble of 21 bytes; 5 bytes kCFI,
16 bytes nop.
Then kCFI expects hash to be at -20, while FineIBT must be at -16.
This then means there is no unambiguous hole for you to stick your
meta-data thing (whatever that is).
There are two options: make meta data location depend on cfi_mode, or
have __apply_fineibt() rewrite kCFI to also be at -16, so that you can
have -21 for your 5 bytes.
I think I prefer latter.
In any case, I don't think we need *_INSN_OFFSET. At most we need
PREAMBLE_SIZE.
Hmm?
next prev parent reply other threads:[~2025-03-03 16:55 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-03-03 13:28 [PATCH v4 0/4] per-function storage support Menglong Dong
2025-03-03 13:28 ` [PATCH v4 1/4] x86/ibt: factor out cfi and fineibt offset Menglong Dong
2025-03-03 16:54 ` Peter Zijlstra [this message]
2025-03-04 1:10 ` Menglong Dong
2025-03-04 5:38 ` Peter Zijlstra
2025-03-04 6:16 ` Peter Zijlstra
2025-03-04 7:47 ` Menglong Dong
2025-03-04 8:41 ` Menglong Dong
2025-03-04 9:42 ` Peter Zijlstra
2025-03-04 14:52 ` H. Peter Anvin
2025-03-05 1:19 ` Menglong Dong
2025-03-05 8:29 ` H. Peter Anvin
2025-03-05 8:49 ` Menglong Dong
2025-03-05 15:03 ` Steven Rostedt
2025-03-06 2:58 ` Menglong Dong
2025-03-06 3:39 ` Alexei Starovoitov
2025-03-06 8:50 ` Menglong Dong
2025-03-23 3:51 ` Menglong Dong
2025-03-03 13:28 ` [PATCH v4 2/4] add per-function metadata storage support Menglong Dong
2025-03-03 13:28 ` [PATCH v4 3/4] x86: implement per-function metadata storage for x86 Menglong Dong
2025-03-03 13:28 ` [PATCH v4 4/4] arm64: implement per-function metadata storage for arm64 Menglong Dong
2025-03-03 21:40 ` Sami Tolvanen
2025-03-04 1:21 ` Menglong Dong
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=20250303165454.GB11590@noisy.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=akpm@linux-foundation.org \
--cc=alexei.starovoitov@gmail.com \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bp@alien8.de \
--cc=bpf@vger.kernel.org \
--cc=catalin.marinas@arm.com \
--cc=daniel@iogearbox.net \
--cc=dave.hansen@linux.intel.com \
--cc=davem@davemloft.net \
--cc=dongml2@chinatelecom.cn \
--cc=dsahern@kernel.org \
--cc=eddyz87@gmail.com \
--cc=hpa@zytor.com \
--cc=john.fastabend@gmail.com \
--cc=jolsa@kernel.org \
--cc=kees@kernel.org \
--cc=kpsingh@kernel.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-trace-kernel@vger.kernel.org \
--cc=llvm@lists.linux.dev \
--cc=mark.rutland@arm.com \
--cc=martin.lau@linux.dev \
--cc=mathieu.desnoyers@efficios.com \
--cc=menglong8.dong@gmail.com \
--cc=mhiramat@kernel.org \
--cc=mingo@redhat.com \
--cc=morbo@google.com \
--cc=nathan@kernel.org \
--cc=netdev@vger.kernel.org \
--cc=nick.desaulniers+lkml@gmail.com \
--cc=riel@surriel.com \
--cc=rostedt@goodmis.org \
--cc=rppt@kernel.org \
--cc=samitolvanen@google.com \
--cc=sdf@fomichev.me \
--cc=tglx@linutronix.de \
--cc=will@kernel.org \
--cc=x86@kernel.org \
--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
all inboxes | Powered by JetHome®