[tip:perf/urgent] perf/x86/intel/pt: Generate PMI in the STOP region as well

[tip:perf/urgent] perf/x86/intel/pt: Generate PMI in the STOP region as well

[tip-bot for Alexander Shishkin]

Commit-ID:  ab92b232ae05c382c3df0e3d6a5c6d16b639ac8c
Gitweb:     http://git.kernel.org/tip/ab92b232ae05c382c3df0e3d6a5c6d16b639ac8c
Author:     Alexander Shishkin <alexander.shishkin@linux.intel.com>
AuthorDate: Tue, 10 May 2016 16:18:32 +0300
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Thu, 12 May 2016 14:45:59 +0200

perf/x86/intel/pt: Generate PMI in the STOP region as well

Currently, the PT driver always sets the PMI bit one region (page) before
the STOP region so that we can wake up the consumer before we run out of
room in the buffer and have to disable the event. However, we also need
an interrupt in the last output region, so that we actually get to disable
the event (if no more room from new data is available at that point),
otherwise hardware just quietly refuses to start, but the event is
scheduled in and we end up losing trace data till the event gets removed.

For a cpu-wide event it is even worse since there may not be any
re-scheduling at all and no chance for the ring buffer code to notice
that its buffer is filled up and the event needs to be disabled (so that
the consumer can re-enable it when it finishes reading the data out). In
other words, all the trace data will be lost after the buffer gets filled
up.

This patch makes PT also generate a PMI when the last output region is
full.

Reported-by: Markus Metzger <markus.t.metzger@intel.com>
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: <stable@vger.kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: vince@deater.net
Link: http://lkml.kernel.org/r/1462886313-13660-2-git-send-email-alexander.shishkin@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/events/intel/pt.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 09a77db..7377814 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -709,6 +709,7 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf,
 
 	/* clear STOP and INT from current entry */
 	buf->topa_index[buf->stop_pos]->stop = 0;
+	buf->topa_index[buf->stop_pos]->intr = 0;
 	buf->topa_index[buf->intr_pos]->intr = 0;
 
 	/* how many pages till the STOP marker */
@@ -733,6 +734,7 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf,
 	buf->intr_pos = idx;
 
 	buf->topa_index[buf->stop_pos]->stop = 1;
+	buf->topa_index[buf->stop_pos]->intr = 1;
 	buf->topa_index[buf->intr_pos]->intr = 1;
 
 	return 0;

Re: [tip:perf/urgent] perf/x86/intel/pt: Generate PMI in the STOP region as well

[Alexander Shishkin]

tip-bot for Alexander Shishkin <tipbot@zytor.com> writes:

> Commit-ID:  ab92b232ae05c382c3df0e3d6a5c6d16b639ac8c
> Gitweb:     http://git.kernel.org/tip/ab92b232ae05c382c3df0e3d6a5c6d16b639ac8c
> Author:     Alexander Shishkin <alexander.shishkin@linux.intel.com>
> AuthorDate: Tue, 10 May 2016 16:18:32 +0300
> Committer:  Ingo Molnar <mingo@kernel.org>
> CommitDate: Thu, 12 May 2016 14:45:59 +0200
>
> perf/x86/intel/pt: Generate PMI in the STOP region as well
>
> Currently, the PT driver always sets the PMI bit one region (page) before
> the STOP region so that we can wake up the consumer before we run out of
> room in the buffer and have to disable the event. However, we also need
> an interrupt in the last output region, so that we actually get to disable
> the event (if no more room from new data is available at that point),
> otherwise hardware just quietly refuses to start, but the event is
> scheduled in and we end up losing trace data till the event gets removed.
>
> For a cpu-wide event it is even worse since there may not be any
> re-scheduling at all and no chance for the ring buffer code to notice
> that its buffer is filled up and the event needs to be disabled (so that
> the consumer can re-enable it when it finishes reading the data out). In
> other words, all the trace data will be lost after the buffer gets filled
> up.
>
> This patch makes PT also generate a PMI when the last output region is
> full.
>
> Reported-by: Markus Metzger <markus.t.metzger@intel.com>
> Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
> Cc: <stable@vger.kernel.org>

Can we also have this one queued up for stable 4.4 and 4.5?

Thanks,
--
Alex

Re: [tip:perf/urgent] perf/x86/intel/pt: Generate PMI in the STOP region as well

[Ingo Molnar]

* Alexander Shishkin <alexander.shishkin@linux.intel.com> wrote:

> tip-bot for Alexander Shishkin <tipbot@zytor.com> writes:
> 
> > Commit-ID:  ab92b232ae05c382c3df0e3d6a5c6d16b639ac8c
> > Gitweb:     http://git.kernel.org/tip/ab92b232ae05c382c3df0e3d6a5c6d16b639ac8c
> > Author:     Alexander Shishkin <alexander.shishkin@linux.intel.com>
> > AuthorDate: Tue, 10 May 2016 16:18:32 +0300
> > Committer:  Ingo Molnar <mingo@kernel.org>
> > CommitDate: Thu, 12 May 2016 14:45:59 +0200
> >
> > perf/x86/intel/pt: Generate PMI in the STOP region as well
> >
> > Currently, the PT driver always sets the PMI bit one region (page) before
> > the STOP region so that we can wake up the consumer before we run out of
> > room in the buffer and have to disable the event. However, we also need
> > an interrupt in the last output region, so that we actually get to disable
> > the event (if no more room from new data is available at that point),
> > otherwise hardware just quietly refuses to start, but the event is
> > scheduled in and we end up losing trace data till the event gets removed.
> >
> > For a cpu-wide event it is even worse since there may not be any
> > re-scheduling at all and no chance for the ring buffer code to notice
> > that its buffer is filled up and the event needs to be disabled (so that
> > the consumer can re-enable it when it finishes reading the data out). In
> > other words, all the trace data will be lost after the buffer gets filled
> > up.
> >
> > This patch makes PT also generate a PMI when the last output region is
> > full.
> >
> > Reported-by: Markus Metzger <markus.t.metzger@intel.com>
> > Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
> > Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
> > Cc: <stable@vger.kernel.org>
> 
> Can we also have this one queued up for stable 4.4 and 4.5?

Agreed.

Acked-by: Ingo Molnar <mingo@kernel.org>

Thanks,

	Ingo

Re: [tip:perf/urgent] perf/x86/intel/pt: Generate PMI in the STOP region as well

[Greg KH]

On Tue, May 17, 2016 at 10:40:34AM +0200, Ingo Molnar wrote:
> 
> * Alexander Shishkin <alexander.shishkin@linux.intel.com> wrote:
> 
> > tip-bot for Alexander Shishkin <tipbot@zytor.com> writes:
> > 
> > > Commit-ID:  ab92b232ae05c382c3df0e3d6a5c6d16b639ac8c
> > > Gitweb:     http://git.kernel.org/tip/ab92b232ae05c382c3df0e3d6a5c6d16b639ac8c
> > > Author:     Alexander Shishkin <alexander.shishkin@linux.intel.com>
> > > AuthorDate: Tue, 10 May 2016 16:18:32 +0300
> > > Committer:  Ingo Molnar <mingo@kernel.org>
> > > CommitDate: Thu, 12 May 2016 14:45:59 +0200
> > >
> > > perf/x86/intel/pt: Generate PMI in the STOP region as well
> > >
> > > Currently, the PT driver always sets the PMI bit one region (page) before
> > > the STOP region so that we can wake up the consumer before we run out of
> > > room in the buffer and have to disable the event. However, we also need
> > > an interrupt in the last output region, so that we actually get to disable
> > > the event (if no more room from new data is available at that point),
> > > otherwise hardware just quietly refuses to start, but the event is
> > > scheduled in and we end up losing trace data till the event gets removed.
> > >
> > > For a cpu-wide event it is even worse since there may not be any
> > > re-scheduling at all and no chance for the ring buffer code to notice
> > > that its buffer is filled up and the event needs to be disabled (so that
> > > the consumer can re-enable it when it finishes reading the data out). In
> > > other words, all the trace data will be lost after the buffer gets filled
> > > up.
> > >
> > > This patch makes PT also generate a PMI when the last output region is
> > > full.
> > >
> > > Reported-by: Markus Metzger <markus.t.metzger@intel.com>
> > > Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
> > > Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
> > > Cc: <stable@vger.kernel.org>
> > 
> > Can we also have this one queued up for stable 4.4 and 4.5?
> 
> Agreed.
> 
> Acked-by: Ingo Molnar <mingo@kernel.org>

The filename moved around, now fixed and queued up, thanks.

greg k-h