[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20161121204445.GX26852@two.firstfloor.org>
Date: Mon, 21 Nov 2016 12:44:45 -0800
From: Andi Kleen <andi@...stfloor.org>
To: Steven Rostedt <rostedt@...dmis.org>
Cc: Andi Kleen <andi@...stfloor.org>,
Peter Zijlstra <peterz@...radead.org>,
Jiri Olsa <jolsa@...hat.com>,
"Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>,
linux-kernel@...r.kernel.org, Ingo Molnar <mingo@...nel.org>,
Josh Triplett <josh@...htriplett.org>,
Jan Stancek <jstancek@...hat.com>
Subject: Re: [BUG] msr-trace.h:42 suspicious rcu_dereference_check() usage!
> > http://halobates.de/tracepoint-trace
>
> There's a lot of push and pop regs due to function calling. There's
> places that inlines can still improve things, and perhaps even some
> likely unlikelys well placed.
Assuming you avoid all the push/pop and all the call/ret this would only be
~25% of the total instructions. There is just far too much logic and
computation in there.
% awk ' { print $5 } ' tracepoint-trace | sort | uniq -c | sort -rn
222 mov
57 push
57 pop
35 test
34 cmp
32 and
28 jz
25 jnz
21 ret
20 call
16 lea
11 add
-Andi
Powered by blists - more mailing lists