From: Peter Zijlstra <peterz@infradead.org>
To: Vineet Gupta <Vineet.Gupta1@synopsys.com>
Cc: "linux-arch@vger.kernel.org" <linux-arch@vger.kernel.org>,
Ard Biesheuvel <ard.biesheuvel@linaro.org>,
Alexey Brodkin <Alexey.Brodkin@synopsys.com>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
Jason Baron <jbaron@akamai.com>,
Paolo Bonzini <pbonzini@redhat.com>,
"linux-snps-arc@lists.infradead.org"
<linux-snps-arc@lists.infradead.org>,
Eugeniy Paltsev <Eugeniy.Paltsev@synopsys.com>
Subject: Re: [PATCH] ARC: ARCv2: jump label: implement jump label patching
Date: Thu, 20 Jun 2019 09:15:14 +0200 [thread overview]
Message-ID: <20190620071514.GR3419@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <C2D7FE5348E1B147BCA15975FBA2307501A252E40B@us01wembx1.internal.synopsys.com>
On Wed, Jun 19, 2019 at 11:55:41PM +0000, Vineet Gupta wrote:
> FWIW I tried to avoid all of this by using the 2 byte NOP_S and B_S variants which
> ensures we can never straddle cache line so the alignment issue goes away. There's
> a nice code size reduction too - see [1] . But I get build link errors in
> networking code around DO_ONCE where the unlikely code is too much and offset
> can't be encoded in signed 10 bits which B_S is allowed.
Yeah, so on x86 we have a 2 byte and a 5 byte relative jump and have the
exact same issue. We're currently using 5 byte jumps unconditionally for
the same reason.
Getting it to use the 2 byte one where possible is a 'fun' project for
someone with spare time at some point. It might need a GCC plugin to
pull off, I've not put too much tought into it.
WARNING: multiple messages have this Message-ID (diff)
From: Peter Zijlstra <peterz@infradead.org>
To: Vineet Gupta <Vineet.Gupta1@synopsys.com>
Cc: Eugeniy Paltsev <Eugeniy.Paltsev@synopsys.com>,
"linux-snps-arc@lists.infradead.org"
<linux-snps-arc@lists.infradead.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
Alexey Brodkin <Alexey.Brodkin@synopsys.com>,
Jason Baron <jbaron@akamai.com>,
Paolo Bonzini <pbonzini@redhat.com>,
Ard Biesheuvel <ard.biesheuvel@linaro.org>,
"linux-arch@vger.kernel.org" <linux-arch@vger.kernel.org>
Subject: Re: [PATCH] ARC: ARCv2: jump label: implement jump label patching
Date: Thu, 20 Jun 2019 09:15:14 +0200 [thread overview]
Message-ID: <20190620071514.GR3419@hirez.programming.kicks-ass.net> (raw)
Message-ID: <20190620071514.88Yqf7kE06Uo4t3r2R4oCH9HXhyP8X6jNK6fbwI_r2E@z> (raw)
In-Reply-To: <C2D7FE5348E1B147BCA15975FBA2307501A252E40B@us01wembx1.internal.synopsys.com>
On Wed, Jun 19, 2019 at 11:55:41PM +0000, Vineet Gupta wrote:
> FWIW I tried to avoid all of this by using the 2 byte NOP_S and B_S variants which
> ensures we can never straddle cache line so the alignment issue goes away. There's
> a nice code size reduction too - see [1] . But I get build link errors in
> networking code around DO_ONCE where the unlikely code is too much and offset
> can't be encoded in signed 10 bits which B_S is allowed.
Yeah, so on x86 we have a 2 byte and a 5 byte relative jump and have the
exact same issue. We're currently using 5 byte jumps unconditionally for
the same reason.
Getting it to use the 2 byte one where possible is a 'fun' project for
someone with spare time at some point. It might need a GCC plugin to
pull off, I've not put too much tought into it.
WARNING: multiple messages have this Message-ID (diff)
From: peterz@infradead.org (Peter Zijlstra)
To: linux-snps-arc@lists.infradead.org
Subject: [PATCH] ARC: ARCv2: jump label: implement jump label patching
Date: Thu, 20 Jun 2019 09:15:14 +0200 [thread overview]
Message-ID: <20190620071514.GR3419@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <C2D7FE5348E1B147BCA15975FBA2307501A252E40B@us01wembx1.internal.synopsys.com>
On Wed, Jun 19, 2019@11:55:41PM +0000, Vineet Gupta wrote:
> FWIW I tried to avoid all of this by using the 2 byte NOP_S and B_S variants which
> ensures we can never straddle cache line so the alignment issue goes away. There's
> a nice code size reduction too - see [1] . But I get build link errors in
> networking code around DO_ONCE where the unlikely code is too much and offset
> can't be encoded in signed 10 bits which B_S is allowed.
Yeah, so on x86 we have a 2 byte and a 5 byte relative jump and have the
exact same issue. We're currently using 5 byte jumps unconditionally for
the same reason.
Getting it to use the 2 byte one where possible is a 'fun' project for
someone with spare time at some point. It might need a GCC plugin to
pull off, I've not put too much tought into it.
next prev parent reply other threads:[~2019-06-20 7:15 UTC|newest]
Thread overview: 53+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-06-14 16:40 [PATCH] ARC: ARCv2: jump label: implement jump label patching Eugeniy Paltsev
2019-06-14 16:40 ` Eugeniy Paltsev
2019-06-18 16:16 ` Vineet Gupta
2019-06-18 16:16 ` Vineet Gupta
2019-06-19 8:12 ` Peter Zijlstra
2019-06-19 8:12 ` Peter Zijlstra
2019-06-19 23:55 ` Vineet Gupta
2019-06-19 23:55 ` Vineet Gupta
2019-06-20 7:01 ` Peter Zijlstra
2019-06-20 7:01 ` Peter Zijlstra
2019-06-20 18:34 ` Eugeniy Paltsev
2019-06-20 18:34 ` Eugeniy Paltsev
2019-06-20 21:30 ` Peter Zijlstra
2019-06-20 21:30 ` Peter Zijlstra
2019-06-20 21:30 ` Peter Zijlstra
2019-06-20 18:48 ` Vineet Gupta
2019-06-20 18:48 ` Vineet Gupta
2019-06-20 21:22 ` Peter Zijlstra
2019-06-20 21:22 ` Peter Zijlstra
2019-06-21 12:09 ` Peter Zijlstra
2019-06-21 12:09 ` Peter Zijlstra
2019-06-21 12:09 ` Peter Zijlstra
2019-06-21 12:12 ` Peter Zijlstra
2019-06-21 12:12 ` Peter Zijlstra
2019-06-21 12:12 ` Peter Zijlstra
2019-06-21 18:37 ` Nadav Amit
2019-06-21 18:37 ` Nadav Amit
2019-06-20 7:15 ` Peter Zijlstra [this message]
2019-06-20 7:15 ` Peter Zijlstra
2019-06-20 7:15 ` Peter Zijlstra
2019-06-20 7:21 ` Peter Zijlstra
2019-06-20 7:21 ` Peter Zijlstra
2019-06-20 7:52 ` Peter Zijlstra
2019-06-20 7:52 ` Peter Zijlstra
2019-06-20 7:52 ` Peter Zijlstra
2019-06-20 20:49 ` Vineet Gupta
2019-06-20 20:49 ` Vineet Gupta
2019-06-21 15:39 ` Alexey Brodkin
2019-06-21 15:39 ` Alexey Brodkin
2019-06-20 18:34 ` Eugeniy Paltsev
2019-06-20 18:34 ` Eugeniy Paltsev
2019-06-20 21:12 ` Peter Zijlstra
2019-06-20 21:12 ` Peter Zijlstra
2019-06-28 22:59 ` Vineet Gupta
2019-06-28 22:59 ` Vineet Gupta
2019-07-03 16:15 ` Vineet Gupta
2019-07-03 16:15 ` Vineet Gupta
2019-07-17 15:09 ` Eugeniy Paltsev
2019-07-17 15:09 ` Eugeniy Paltsev
2019-07-17 17:45 ` Vineet Gupta
2019-07-17 17:45 ` Vineet Gupta
2019-07-17 18:54 ` Eugeniy Paltsev
2019-07-17 18:54 ` Eugeniy Paltsev
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=20190620071514.GR3419@hirez.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=Alexey.Brodkin@synopsys.com \
--cc=Eugeniy.Paltsev@synopsys.com \
--cc=Vineet.Gupta1@synopsys.com \
--cc=ard.biesheuvel@linaro.org \
--cc=jbaron@akamai.com \
--cc=linux-arch@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-snps-arc@lists.infradead.org \
--cc=pbonzini@redhat.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.