Re: [PATCH 1/8] perf: Add PERF_SAMPLE_PHYS_ADDR

[Jiri Olsa]

On Thu, Jan 07, 2016 at 03:55:23PM +0000, Liang, Kan wrote:
> 
> 
> > On Wed, Jan 06, 2016 at 06:04:30AM -0500, kan.liang@xxxxxxxxx wrote:
> > > From: Kan Liang <kan.liang@xxxxxxxxx>
> > >
> > > For understanding how the workload maps to memory channels and
> > > hardware behavior, it's useful to collect address maps with physical
> > addresses.
> > > This is not intended for detecting page sharing (which can be already
> > > done using the mmap inode), but for lower level hardware behavior
> > > studies.
> > > Perf supports load latency/DLA which can only collect virtual addresses.
> > > This patch add a new sample type PERF_SAMPLE_PHYS_ADDR to expose
> > the
> > > physical addresses.
> > > For kernel direct mapping addresses, the patch uses virt_to_phys to
> > > convert the virtual addresses from DLA to physical address.
> > > For user virtual addresses, __get_user_pages_fast is used to walk the
> > > pages tables for user physical address.
> > > This does not work for vmalloc addresses. Right now these are not
> > > resolved, but code to do that could be added.
> > > For security, the physical address can only be exposed to root or
> > > privileged user.
> > >
> > > Signed-off-by: Kan Liang <kan.liang@xxxxxxxxx>
> > > ---
> > >  arch/x86/kernel/cpu/perf_event.h          |  2 +-
> > >  arch/x86/kernel/cpu/perf_event_intel_ds.c | 23
> > +++++++++++++++++++++++
> > >  include/linux/perf_event.h                |  3 +++
> > >  include/uapi/linux/perf_event.h           |  4 +++-
> > >  kernel/events/core.c                      | 11 +++++++++++
> > >  5 files changed, 41 insertions(+), 2 deletions(-)
> > >
> > > diff --git a/arch/x86/kernel/cpu/perf_event.h
> > > b/arch/x86/kernel/cpu/perf_event.h
> > > index 799e6bd..164de68 100644
> > > --- a/arch/x86/kernel/cpu/perf_event.h
> > > +++ b/arch/x86/kernel/cpu/perf_event.h
> > > @@ -90,7 +90,7 @@ struct amd_nb {
> > >  	(PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \
> > >  	PERF_SAMPLE_ID | PERF_SAMPLE_CPU |
> > PERF_SAMPLE_STREAM_ID | \
> > >  	PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \
> > > -	PERF_SAMPLE_TRANSACTION)
> > > +	PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR)
> > 
> > could you please add some probe code to detect kernel support, so we get
> > some sensible error message
> > 
> 
> I'm not quite sure what kind of probe code do you mean.
> Yes, the error message below is not accurate. It could be some errors in
> sample_type, read_format, branch_sample_type or something else.
> Because they share the same error code -EINVAL. Perf tool cannot know
> more. 
> I think we may print some error kernel messages when invalid attr is
> detected. So the user can get more detail messages from dmesg.  
> 
> Or you want me to add some extra code to detect the kernel capability
> before opening event? If so, I think we may do it in separate patches.

yep, could be done later

jirka