From: Andrew Cooper <andrew.cooper3@citrix.com>
To: Jan Beulich <JBeulich@suse.com>,
xen-devel <xen-devel@lists.xenproject.org>
Cc: WeiLiu <wl@xen.org>, Roger Pau Monne <roger.pau@citrix.com>
Subject: Re: [Xen-devel] [PATCH v2 2/2] x86/traps: widen condition for logging top-of-stack
Date: Wed, 3 Jul 2019 11:21:57 +0100 [thread overview]
Message-ID: <eb44801a-1081-858d-4853-6dc574e0c6d6@citrix.com> (raw)
In-Reply-To: <5D074BA30200007800238B6C@prv1-mh.provo.novell.com>
On 17/06/2019 09:13, Jan Beulich wrote:
> Despite -fno-omit-frame-pointer the compiler may omit the frame pointer,
> often for relatively simple leaf functions.
Actually, the problem is more widespread than this. For every function,
there is a non-zero quantity of time between the function starting and
the frame pointer being set up.
However, half of this time is spent with the old %rbp on the top of the
stack, so won't benefit from these changes.
> (To give a specific example,
> the case I've run into this with is _pci_hide_device() and gcc 8.
> Interestingly the even more simple neighboring iommu_has_feature() does
> get a frame pointer set up, around just a single instruction. But this
> may be a result of the size-of-asm() effects discussed elsewhere.)
>
> Log the top-of-stack value if it looks valid _or_ if RIP looks invalid.
This far, I'm happy with.
> Also annotate non-frame-pointer-based stack trace entries with a
> question mark, to signal clearly that any one of them may not actually
> be part of the call stack.
I'm still opposed to this. The introduction of ? does more harm than
good IMO, because it simply can't be trusted.
Stack traces are not guaranteed-accurate, even with frame pointers
enabled. The only thing we can say for certain in any trace is where
%rip points.
~Andrew
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
next prev parent reply other threads:[~2019-07-03 10:22 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-05-31 8:59 [PATCH 0/2]: x86/traps: improve show_trace()'s top-of-stack handling Jan Beulich
2019-05-31 8:59 ` [Xen-devel] " Jan Beulich
2019-05-31 9:17 ` [PATCH 1/2] x86/traps: guard top-of-stack reads Jan Beulich
2019-05-31 9:17 ` [Xen-devel] " Jan Beulich
2019-06-07 17:51 ` Andrew Cooper
2019-06-11 9:57 ` Jan Beulich
2019-05-31 9:22 ` [PATCH 2/2] x86/traps: widen condition for logging top-of-stack Jan Beulich
2019-05-31 9:22 ` [Xen-devel] " Jan Beulich
2019-06-07 18:01 ` Andrew Cooper
2019-06-11 9:46 ` Jan Beulich
2019-06-17 8:10 ` [Xen-devel] [PATCH v2 0/2]: x86/traps: improve show_trace()'s top-of-stack handling Jan Beulich
2019-06-17 8:12 ` [Xen-devel] [PATCH v2 1/2] x86/traps: guard top-of-stack reads Jan Beulich
2019-07-02 17:47 ` Andrew Cooper
2019-07-03 7:10 ` Jan Beulich
2019-06-17 8:13 ` [Xen-devel] [PATCH v2 2/2] x86/traps: widen condition for logging top-of-stack Jan Beulich
2019-07-03 10:21 ` Andrew Cooper [this message]
2019-07-03 10:34 ` Jan Beulich
2019-07-03 19:47 ` Andrew Cooper
2019-07-04 9:09 ` Jan Beulich
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=eb44801a-1081-858d-4853-6dc574e0c6d6@citrix.com \
--to=andrew.cooper3@citrix.com \
--cc=JBeulich@suse.com \
--cc=roger.pau@citrix.com \
--cc=wl@xen.org \
--cc=xen-devel@lists.xenproject.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).