On 2014/11/27 22:36, Jon Medhurst (Tixy) wrote:

On Fri, 2014-11-21 at 14:35 +0800, Wang Nan wrote:

quoted

This patch introduce kprobeopt for ARM 32.

If I've understood things correctly, this is a feature which inserts
probes by using a branch instruction to some trampoline code rather than
using an undefined instruction as a breakpoint. That way we avoid the
overhead of processing the exception and it is this performance
improvement which is the main/only reason for implementing it?

If so, I though it good to see what kind of improvement we get by
running the micro benchmarks in the kprobes test code. On an A7/A15
big.LITTLE vexpress board the approximate figures I get are 0.3us for
optimised probe, 1us for un-optimised, so a three times performance
improvement. This is with an empty probe pre-handler and no post
handler, so with a more realistic usecase, the relative improvement we
get from optimisation would be less.

I thought it good to see what sort of benefits this code achieves,
especially as it could grow quite complex over time, and the cost of
that versus the benefit should be considered.

Thanks for your comments and your comprehensive testing.

In fact I have got even worst performance result on my hardware platform.
However, by utilizing previous introduced checker code to check instructions
in detail, I believe we can eliminate most of the emulation/simulation works
so the cost can be reduced.

Futhermore, kprobeopt can avoid exceptions, which have at least 2 advantanges:

1. Make things simpler. Although exception processing is fast in real hardware,
   it still need more state changing and processing than a branch instruction,
   which may cause unexcepted problems.

2. Branch instructions can be used in more cases than exception. For example,
   at very early stage of kernel booting when exception vector is
   not installed, and at kernel panic processing.