From: Peter Zijlstra <peterz@infradead.org>
To: Alexandre Chartre <alexandre.chartre@oracle.com>
Cc: x86@kernel.org, linux-kernel@vger.kernel.org,
jpoimboe@redhat.com, jthierry@redhat.com, tglx@linutronix.de
Subject: Re: [PATCH V2 9/9] x86/speculation: Remove all ANNOTATE_NOSPEC_ALTERNATIVE directives
Date: Tue, 7 Apr 2020 15:59:53 +0200 [thread overview]
Message-ID: <20200407135953.GC20730@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <20200407135211.GB20730@hirez.programming.kicks-ass.net>
On Tue, Apr 07, 2020 at 03:52:11PM +0200, Peter Zijlstra wrote:
> On Tue, Apr 07, 2020 at 09:31:42AM +0200, Alexandre Chartre wrote:
>
> > - ANNOTATE_NOSPEC_ALTERNATIVE
> > ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *\reg), \
> > __stringify(RETPOLINE_JMP \reg), X86_FEATURE_RETPOLINE, \
> > __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *\reg), X86_FEATURE_RETPOLINE_AMD
>
> Possibly we can write this like:
.macro OOL_RETPOLINE_JMP reg:req
SYM_FUNC_START(__x86_retpoline_jmp_\reg)
CFI_STARTPROC
RETPOLINE_JMP \reg
CFI_ENDPROC
SYM_FUNC_END(__x86_retpoline_jmp_\reg)
.endm
> ALTERNATIVE("", "lfence", X86_FEATURE_RETPOLINE_AMD);
> ALTERNATIVE("jmp *\reg", "jmp __x86_retpoline_jmp_\reg", X86_FEATURE_RETPOLINE);
>
> With an out-of-line copy of the retpoline, just like the THUNKs the
> compiler uses, except of course, it can't be those, because we actually
> want to use the alternative to implement those.
>
> By moving the retpoline magic out-of-line we ensure it has a unique
> address and the ORC stuff should work.
>
> I'm just not sure what to do about the RETPOLINE_CALL variant.
Duh, something like so:
ALTERNATIVE("", "lfence", X86_FEATURE_RETPOLINE_AMD);
ALTERNATIVE("call *\reg", "call __x86_retpoline_jmp_\reg", X86_FEATURE_RETPOLINE);
next prev parent reply other threads:[~2020-04-07 14:00 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-04-07 7:31 [PATCH V2 0/9] objtool changes to remove all ANNOTATE_NOSPEC_ALTERNATIVE Alexandre Chartre
2020-04-07 7:31 ` [PATCH V2 1/9] objtool: Introduce HINT_RET_OFFSET Alexandre Chartre
2020-04-07 12:53 ` Peter Zijlstra
2020-04-07 13:17 ` Alexandre Chartre
2020-04-07 7:31 ` [PATCH V2 2/9] objtool: UNWIND_HINT_RET_OFFSET should not check registers Alexandre Chartre
2020-05-01 18:22 ` [tip: objtool/core] " tip-bot2 for Alexandre Chartre
2020-04-07 7:31 ` [PATCH V2 3/9] objtool: is_fentry_call() crashes if call has no destination Alexandre Chartre
2020-04-07 7:31 ` [PATCH V2 4/9] objtool: Allow branches within the same alternative Alexandre Chartre
2020-04-07 7:31 ` [PATCH V2 5/9] objtool: Add support for intra-function calls Alexandre Chartre
2020-04-07 13:07 ` Peter Zijlstra
2020-04-07 13:28 ` Alexandre Chartre
2020-04-08 14:06 ` Alexandre Chartre
2020-04-08 14:19 ` Julien Thierry
2020-04-08 16:03 ` Alexandre Chartre
2020-04-08 16:04 ` Julien Thierry
2020-04-08 17:06 ` Alexandre Chartre
2020-04-08 17:07 ` Julien Thierry
2020-04-07 7:31 ` [PATCH V2 6/9] x86/speculation: Change __FILL_RETURN_BUFFER to work with objtool Alexandre Chartre
2020-04-07 13:27 ` Josh Poimboeuf
2020-04-07 7:31 ` [PATCH V2 7/9] x86/speculation: Annotate intra-function calls Alexandre Chartre
2020-04-07 7:31 ` [PATCH V2 8/9] x86/speculation: Add unwind hint to trampoline return Alexandre Chartre
2020-04-07 7:31 ` [PATCH V2 9/9] x86/speculation: Remove all ANNOTATE_NOSPEC_ALTERNATIVE directives Alexandre Chartre
2020-04-07 13:28 ` Peter Zijlstra
2020-04-07 13:34 ` Josh Poimboeuf
2020-04-07 14:32 ` Alexandre Chartre
2020-04-07 16:18 ` Alexandre Chartre
2020-04-07 16:28 ` Josh Poimboeuf
2020-04-07 17:01 ` Alexandre Chartre
2020-04-07 17:26 ` Peter Zijlstra
2020-04-07 17:27 ` Peter Zijlstra
2020-04-08 21:35 ` Peter Zijlstra
2020-04-09 8:18 ` Alexandre Chartre
2020-04-09 10:34 ` Peter Zijlstra
2020-04-09 10:40 ` Peter Zijlstra
2020-04-07 16:41 ` Peter Zijlstra
2020-04-07 17:04 ` Alexandre Chartre
2020-04-07 13:52 ` Peter Zijlstra
2020-04-07 13:59 ` Peter Zijlstra [this message]
2020-04-07 13:35 ` [PATCH V2 0/9] objtool changes to remove all ANNOTATE_NOSPEC_ALTERNATIVE Josh Poimboeuf
2020-04-07 14:02 ` Alexandre Chartre
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=20200407135953.GC20730@hirez.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=alexandre.chartre@oracle.com \
--cc=jpoimboe@redhat.com \
--cc=jthierry@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=tglx@linutronix.de \
--cc=x86@kernel.org \
/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).