From: David Howells <dhowells@redhat.com>
To: lkp@lists.01.org
Subject: Re: [lkp-robot] [iversion] c0cef30e4f: aim7.jobs-per-min -18.0% regression
Date: Tue, 27 Feb 2018 13:43:13 +0000 [thread overview]
Message-ID: <666.1519738993@warthog.procyon.org.uk> (raw)
In-Reply-To: <1519738149.4300.45.camel@redhat.com>
[-- Attachment #1: Type: text/plain, Size: 822 bytes --]
Jeff Layton <jlayton@redhat.com> wrote:
> 0xffffffff813ae828 <+136>: je 0xffffffff813ae83a <ima_file_free+154>
> 0xffffffff813ae82a <+138>: mov 0x150(%rbp),%rcx
> 0xffffffff813ae831 <+145>: shr %rcx
> 0xffffffff813ae834 <+148>: cmp %rcx,0x20(%rax)
> 0xffffffff813ae838 <+152>: je 0xffffffff813ae862 <ima_file_free+194>
Is it possible there's a stall between the load of RCX and the subsequent
instructions because they all have to wait for RCX to become available?
The interleaving between operating on RSI and RCX in the older code might
alleviate that.
In addition, the load if the 20(%rax) value is now done in the CMP instruction
rather than earlier, so it might not get speculatively loaded in time, whereas
the earlier code explicitly loads it up front.
David
WARNING: multiple messages have this Message-ID (diff)
From: David Howells <dhowells@redhat.com>
To: Jeff Layton <jlayton@redhat.com>
Cc: dhowells@redhat.com, kemi <kemi.wang@intel.com>,
Ye Xiaolong <xiaolong.ye@intel.com>,
lkp@01.org, Linus Torvalds <torvalds@linux-foundation.org>,
LKML <linux-kernel@vger.kernel.org>
Subject: Re: [LKP] [lkp-robot] [iversion] c0cef30e4f: aim7.jobs-per-min -18.0% regression
Date: Tue, 27 Feb 2018 13:43:13 +0000 [thread overview]
Message-ID: <666.1519738993@warthog.procyon.org.uk> (raw)
In-Reply-To: <1519738149.4300.45.camel@redhat.com>
Jeff Layton <jlayton@redhat.com> wrote:
> 0xffffffff813ae828 <+136>: je 0xffffffff813ae83a <ima_file_free+154>
> 0xffffffff813ae82a <+138>: mov 0x150(%rbp),%rcx
> 0xffffffff813ae831 <+145>: shr %rcx
> 0xffffffff813ae834 <+148>: cmp %rcx,0x20(%rax)
> 0xffffffff813ae838 <+152>: je 0xffffffff813ae862 <ima_file_free+194>
Is it possible there's a stall between the load of RCX and the subsequent
instructions because they all have to wait for RCX to become available?
The interleaving between operating on RSI and RCX in the older code might
alleviate that.
In addition, the load if the 20(%rax) value is now done in the CMP instruction
rather than earlier, so it might not get speculatively loaded in time, whereas
the earlier code explicitly loads it up front.
David
next prev parent reply other threads:[~2018-02-27 13:43 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-02-25 15:05 [lkp-robot] [iversion] c0cef30e4f: aim7.jobs-per-min -18.0% regression kernel test robot
2018-02-25 15:05 ` kernel test robot
2018-02-25 15:41 ` Jeff Layton
2018-02-25 15:41 ` Jeff Layton
2018-02-26 8:38 ` Ye Xiaolong
2018-02-26 8:38 ` Ye Xiaolong
2018-02-26 11:43 ` Jeff Layton
2018-02-26 11:43 ` Jeff Layton
2018-02-26 12:33 ` Jeff Layton
2018-02-26 12:33 ` Jeff Layton
2018-02-27 7:42 ` kemi
2018-02-27 7:42 ` [LKP] " kemi
2018-02-27 13:29 ` Jeff Layton
2018-02-27 13:29 ` [LKP] " Jeff Layton
2018-02-27 13:43 ` David Howells [this message]
2018-02-27 13:43 ` David Howells
2018-02-27 15:27 ` Jeff Layton
2018-02-27 15:27 ` [LKP] " Jeff Layton
2018-02-27 17:04 ` Linus Torvalds
2018-02-27 17:04 ` [LKP] " Linus Torvalds
2018-03-02 5:54 ` kemi
2018-03-02 5:54 ` [LKP] " kemi
2018-03-15 7:33 ` kemi
2018-03-15 7:33 ` [LKP] " kemi
2018-03-15 17:46 ` Linus Torvalds
2018-03-15 17:46 ` [LKP] " Linus Torvalds
2018-02-25 21:18 ` Linus Torvalds
2018-02-25 21:18 ` Linus Torvalds
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=666.1519738993@warthog.procyon.org.uk \
--to=dhowells@redhat.com \
--cc=lkp@lists.01.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 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.