Re: [PATCH] [RFC] tracehook: Hook in syscall tracing markers.

[Mathieu Desnoyers <compudj@krystal.dyndns.org>]

* Frank Ch. Eigler (fche@redhat.com) wrote:
> Hi -
> 
> > At kernel summit, the idea that syscall tracing was generally desirable
> > for tracing was mentioned several times, as was the argument that kernel
> > developers aren't placing markers in meaningful locations. This is a
> > simple patch to try and do that for the syscall case.[...]
> 
> One problem with this is that a separate mechanism would be needed to
> activate these tracehook_report_* calls in the first place: the
> management of the per-task TIF_SYSCALL_TRACE flag.  This is one of the
> things the utrace API makes straightforward, in which case its own
> native syscall reporting callbacks can be used directly.
> 
> - FChE
> 

There is already a series of patches in the -lttng tree which adds
TIF_KERNEL_TRACE to every architecture. It basically enables syscall
tracing for every threads running on the system.

It't the best way I found to do system-wide syscall tracing without
changing anything of the assembly code except adding one flag to the
tested flags.

Mathieu


-- 
Mathieu Desnoyers
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F  BA06 3F25 A8FE 3BAE 9A68