[GIT]: libpfm4 branch, master, updated. 104238d7811e2350925c94b4121a400da76b2606

[seranian <ser...@us...>]

This is an automated email from the git hooks/post-receive script. It was
generated because a ref change was pushed to the repository containing
the project "libpfm4".

The branch, master has been updated
       via  104238d7811e2350925c94b4121a400da76b2606 (commit)
       via  20bb44d922f0cfa2f1c2b861bbcb8e08b6261863 (commit)
      from  d887442e1d67034a90076511429e287b82a7bfb9 (commit)

Those revisions listed above that are new to this repository have
not appeared on any other notification email; so we list those
revisions in full, below.

- Log -----------------------------------------------------------------
commit 104238d7811e2350925c94b4121a400da76b2606
Author: Corey Ashford <cja...@li...>
Date:   Tue May 10 14:49:15 2011 +0200

    Enable translating of libpfm4 user/kernel/hypervisor modifiers to raw event code syntax
    
    If a user specifies an event code with ":u=<n>", ":k=<n>", or
    ":h=<n>" modifiers, evt2raw will now output a raw event code
    which is compatible with "perf stat" and "perf record".  For
    example, it will translate:
    
    PM_RUN_CYC:k=1:u=1
    
    to
    
    r200f4:uk
    
    Without this change, the u,k, and h modifiers are simply dropped
    silently by evt2raw.
    
    Note that in order for this to work correctly, I had to change
    the default privilege mask to add hypervisor mode.
    
    Signed-off-by: Corey Ashford <cja...@li...>

commit 20bb44d922f0cfa2f1c2b861bbcb8e08b6261863
Author: Corey Ashford <cja...@li...>
Date:   Tue May 10 14:38:21 2011 +0200

    Set size field before calling pfm_get_perf_event_encoding()
    
    Anton Blanchard discovered that when he ran a simple example of
    evt2raw on a POWER7 machine, he got a seg fault in libpfm because
    libpfm checked the size field of the perf_event_attr struct, and
    if it's non-zero, it uses that size to memset the struct to all
    zeros.  If the size is garbage (a large number), memset will write
    past the end of the structure, corrupting memory, and possibly
    causing a seg fault.
    
    This patch corrects that by initializing the size field to the
    size of the perf_event_addr_struct which is being passed in.  This
    should be the safest route.
    
    Reported-by: Anton Blanchard <an...@au...>
    Signed-off-by: Corey Ashford <cja...@li...>

-----------------------------------------------------------------------

Summary of changes:
 perf_examples/evt2raw.c |   21 ++++++++++++++++++---
 1 files changed, 18 insertions(+), 3 deletions(-)


hooks/post-receive
-- 
libpfm4