public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
* [RFC patch 00/20] LTTng Kernel Trace Thread Flag v2
@ 2009-03-15 20:01 Mathieu Desnoyers
  2009-03-15 20:01 ` [RFC patch 01/20] LTTng Kernel Trace Thread Flag Alpha Mathieu Desnoyers
                   ` (19 more replies)
  0 siblings, 20 replies; 23+ messages in thread
From: Mathieu Desnoyers @ 2009-03-15 20:01 UTC (permalink / raw)
  To: Ingo Molnar, akpm, Frederic Weisbecker, Steven Rostedt, LKML

Frederic noticed that the assembly file modifications I did were not present in
the TIF_* modifications. So I took them from my lttng architecture specific
instrumentation files and integrated them into each architecture's TIF addition.

Sorry for the quick repost.

Mathieu

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

^ permalink raw reply	[flat|nested] 23+ messages in thread
* [RFC patch 00/20] Kernel tracing thread flag
@ 2009-05-09 16:22 Mathieu Desnoyers
  2009-05-09 16:22 ` [RFC patch 15/20] LTTng Kernel Trace Thread Flag SH Mathieu Desnoyers
  0 siblings, 1 reply; 23+ messages in thread
From: Mathieu Desnoyers @ 2009-05-09 16:22 UTC (permalink / raw)
  To: akpm, Ingo Molnar, linux-kernel, Frank Ch. Eigler, Jason Baron,
	Tom Zanussi, fweisbec, laijs, rostedt, peterz, jiayingz, roland,
	mbligh

This is the generalisation of the TIF_SYSCALL_FTRACE thread flag for :

- multiple tracers (even accessible from modules)
- multiple architectures

It includes :

- Addition of the TIF_KERNEL_TRACE for all Linux architectures.
- Modification of some architecture entry*.S files to ensure that the thread
  flag is re-read upon syscall exit to ensure that syscall exit is traced.
  Basically, what I try to achieve here is to make sure that given the following
  sequence will get its syscall exit event traced :

- Thread preempted in a system call
- Activation of all TIF_KERNEL_TRACE thread flags
- ...enough time passes to expect that all tracing sites are activated...
- syscall exit -> expected to be traced

But if the thread flags used at syscall exit are the same that has been read at
syscall entry, the event will be skipped. This does not permit reaching a known
"quiescent state" where we know that all tracing sites are activated.

Note that having non-perfectly matched syscall trace entry/exit may have
implications wrt getname/putname refcounting for instance, and could cause
problems if getname/putname was used in the syscall entry/exit pairs. We will
have to deal with this somehow when we face this problem. Keeping a per-thread
flag saying that a matching syscall_entry tracing has been executed could fix
this problem. We could even re-use TIF_SYSCALL_FTRACE for this specific purpose.

Mathieu

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

^ permalink raw reply	[flat|nested] 23+ messages in thread

end of thread, other threads:[~2009-05-09 17:21 UTC | newest]

Thread overview: 23+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2009-03-15 20:01 [RFC patch 00/20] LTTng Kernel Trace Thread Flag v2 Mathieu Desnoyers
2009-03-15 20:01 ` [RFC patch 01/20] LTTng Kernel Trace Thread Flag Alpha Mathieu Desnoyers
2009-03-15 20:01 ` [RFC patch 02/20] LTTng Kernel Trace Thread Flag ARM Mathieu Desnoyers
2009-03-15 20:01 ` [RFC patch 03/20] LTTng Kernel Trace Thread Flag AVR32 Mathieu Desnoyers
2009-03-15 20:01 ` [RFC patch 04/20] LTTng Kernel Trace Thread Flag Blackfin Mathieu Desnoyers
2009-03-15 20:01 ` [RFC patch 05/20] LTTng Kernel Trace Thread Flag Cris Mathieu Desnoyers
2009-03-15 20:01 ` [RFC patch 06/20] LTTng Kernel Trace Thread Flag Frv Mathieu Desnoyers
2009-03-15 20:01 ` [RFC patch 07/20] LTTng Kernel Trace Thread Flag H8300 Mathieu Desnoyers
2009-03-15 20:01 ` [RFC patch 08/20] LTTng Kernel Trace Thread Flag ia64 Mathieu Desnoyers
2009-03-15 20:01 ` [RFC patch 09/20] LTTng Kernel Trace Thread Flag m32r Mathieu Desnoyers
2009-03-15 20:01 ` [RFC patch 10/20] LTTng Kernel Trace Thread Flag m68k Mathieu Desnoyers
2009-03-15 20:01 ` [RFC patch 11/20] LTTng Kernel Trace Thread Flag MIPS Mathieu Desnoyers
2009-03-15 20:01 ` [RFC patch 12/20] LTTng Kernel Trace Thread Flag parisc Mathieu Desnoyers
2009-03-15 20:01 ` [RFC patch 13/20] LTTng Kernel Trace Thread Flag powerpc Mathieu Desnoyers
2009-03-15 20:01 ` [RFC patch 14/20] LTTng Kernel Trace Thread Flag s390 Mathieu Desnoyers
2009-03-15 20:01 ` [RFC patch 15/20] LTTng Kernel Trace Thread Flag SH Mathieu Desnoyers
2009-03-15 20:02 ` [RFC patch 16/20] LTTng Kernel Trace Thread Flag sparc Mathieu Desnoyers
2009-03-15 20:02 ` [RFC patch 17/20] LTTng Kernel Trace Thread Flag UML Mathieu Desnoyers
2009-03-15 20:02 ` [RFC patch 18/20] LTTng Linux Kernel Trace Thread Flag x86 Mathieu Desnoyers
2009-03-15 20:02 ` [RFC patch 19/20] LTTng Kernel Trace Thread Flag xtensa Mathieu Desnoyers
2009-03-15 20:02 ` [RFC patch 20/20] LTTng Kernel Trace Thread Flag API Mathieu Desnoyers
  -- strict thread matches above, loose matches on Subject: below --
2009-05-09 16:22 [RFC patch 00/20] Kernel tracing thread flag Mathieu Desnoyers
2009-05-09 16:22 ` [RFC patch 15/20] LTTng Kernel Trace Thread Flag SH Mathieu Desnoyers
2009-05-09 17:15   ` Paul Mundt

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox