linux.git/tools/perf/util, branch v2.6.35

perf annotate: Fix handling of goto labels that are valid hex numbers

2010-07-22T17:04:13+00:00

When parsing the objdump disassembly output we can have goto labels that
are valid hex numbers and thus get confused with lines with machine
code.

Handle the common case of a label that has nothing after it and other
cases where there is just source code by validating the resulting "ip".

It is still possible that we find goto labels that are in the function
address range, but only if they are located before the real address we
should be OK.

A change in the objdump output to have a clear marker separating
addresses from the disassembly would come handy, but we would still have
to deal with older versions.

Reported-by: Gleb Natapov 
Cc: Frederic Weisbecker 
Cc: Gleb Natapov 
Cc: Mike Galbraith 
Cc: Peter Zijlstra 
Cc: Stephane Eranian 
LKML-Reference: <20100722170541.GF17631@ghostprotocols.net>
Signed-off-by: Arnaldo Carvalho de Melo

perf symbols: Fix directory descriptor leaking

2010-07-16T17:16:47+00:00

When I ran "perf kvm ... top", I encountered the following error output.

  Error: perfcounter syscall returned with -1 (Too many open files)

  Fatal: No CONFIG_PERF_EVENTS=y kernel support configured?

Looking into perf, I found perf opens too many directories at
initialization time, but forgets to close them. Here is the fix.

LKML-Reference: <4C230362.5080704@cn.fujitsu.com>
Cc: Ingo Molnar 
Cc: Paul Mackerras 
Cc: Peter Zijlstra 
Signed-off-by: Gui Jianfeng 
Signed-off-by: Arnaldo Carvalho de Melo

perf: Fix various display bugs with parent filtering

2010-07-16T02:56:09+00:00

Hists that have been filtered, because they don't have callchains
matching the parent filter, won't be printed. As such,
hist_entry__snprintf() returns 0 for them, but we don't control
this value and we always print the buffer, which might be
untouched and then only made of random stack garbage.

Not only does it paint the screen with barf, it also prints
the callchains for these hists, even though they have been filtered,
since the hist has been filtered as well.

We need to check the return value of hist_entry__snprintf() and
ignore the hist if it is 0, which means it didn't get any callchain
matching the parent filter. This fixes the barf and the undesired
callchains.

Reported-by: Ingo Molnar 
Signed-off-by: Frederic Weisbecker 
Cc: Ingo Molnar 
Cc: Peter Zijlstra 
Cc: Arnaldo Carvalho de Melo 
Cc: Paul Mackerras

perf: Sync callchains with period based hits

2010-07-08T04:26:56+00:00

Hists have their hits increased by the event period. And this
period based counting is the foundation of all the stats in
perf report.

But callchains still use the raw number of hits, without taking
the period into account. So when we compute the percentage,
absolute based percentages are totally broken, and relative ones
too in the first parent level. Because we pass the number of events
muliplied by their period as the total number of hits to the
callchain filtering, while callchains expect this number to be
the number of raw hits.

perf report -g graph was simply not working, showing no graph unless
the min percent was zero. And even there the percentage of the
branches was always 0. And may be fractal filtering was broken on
the first branch level too.

flat also was broken, but it was hidden because of other breakages.

Anyway fix this by counting using periods on callchains.

Signed-off-by: Frederic Weisbecker 
Cc: Ingo Molnar 
Cc: Peter Zijlstra 
Cc: Arnaldo Carvalho de Melo 
Cc: Paul Mackerras

perf: Resurrect flat callchains

2010-07-08T04:20:15+00:00

Initialize the callchain radix tree root correctly.

When we walk through the parents, we must stop after the root, but
since it wasn't well initialized, its parent pointer was random.

Also the number of hits was random because uninitialized, hence it
was part of the callchain while the root doesn't contain anything.

This fixes segfaults and percentages followed by empty callchains
while running:

	perf report -g flat

Reported-by: Ingo Molnar 
Signed-off-by: Frederic Weisbecker 
Cc: Peter Zijlstra 
Cc: Arnaldo Carvalho de Melo 
Cc: Paul Mackerras 
Cc: 2.6.31.x-2.6.34.x

perf: Version String fix, for fallback if not from git

2010-07-05T08:42:58+00:00

This gets rid of the default version fallback for Perf and
changes it so that it returns the version of the kernel from
it's Makefile (if sources were not from git, ie. if it was
downloaded from a tarball)

Signed-off-by: Thavidu Ranatunga 
Acked-by: Ian Munsie 
Acked-by: Peter Zijlstra 
Cc: Paul Mackerras 
Cc: Arnaldo Carvalho de Melo 
LKML-Reference: <1278316815-6099-2-git-send-email-tharan@au1.ibm.com>
Signed-off-by: Ingo Molnar

perf: Version String fix, using kernel version

2010-07-05T08:42:58+00:00

Changes the Perf --version string such that it shows the kernel
version as suggested by Ingo as follows:

That way the perf that comes with v2.6.34 will be:

  perf version v2.6.34

while interim versions will have the version of the interim
kernel - for example:

 perf version v2.6.35-rc4-70-g39ef13a

This functionality was already in the perf version generator
file except that it was looking for a .git in the perf directory
instead of the kernel directory.

Signed-off-by: Thavidu Ranatunga 
Acked-by: Ian Munsie 
Acked-by: Peter Zijlstra 
Cc: Paul Mackerras 
Cc: Arnaldo Carvalho de Melo 
LKML-Reference: <1278316815-6099-1-git-send-email-tharan@au1.ibm.com>
Signed-off-by: Ingo Molnar

perf tools: Fix find tids routine by excluding "." and ".."

2010-07-01T17:02:38+00:00

Introduce a filter function to skip "." and ".." directories when calculating
tid number, otherwise tid 0 will be included in the all_tid result array.

Cc: Ingo Molnar 
LKML-Reference: <4C185F68.1020505@cn.fujitsu.com>
Signed-off-by: Gui Jianfeng 
Signed-off-by: Arnaldo Carvalho de Melo

perf session: Remove threads from tree on PERF_RECORD_EXIT

2010-06-17T11:37:44+00:00

Move them to a session->dead_threads list just like we do with maps that
are replaced, because we may have hist_entries pointing to them.

This fixes a bug when inserting maps for a new thread that reused the
TID, mixing maps for two different threads, causing an endless loop.

The code for insering maps should be made more robust but for .35 this
is the minimalistic patch.

Reported-by: Ingo Molnar 
Cc: David S. Miller 
Cc: Frédéric Weisbecker 
Cc: Mike Galbraith 
Cc: Paul Mackerras 
Cc: Peter Zijlstra 
Cc: Stephane Eranian 
Cc: Tom Zanussi 
LKML-Reference: 
Signed-off-by: Arnaldo Carvalho de Melo

perf record: Don't call newt functions when not initialized

2010-06-10T11:29:19+00:00

When processing events we want to give visual feedback to the user when
using the newt browser, so there are ui_progress calls in
__perf_session__process_events, but those should check if newt is being
used.

Reported-by: Srikar Dronamraju 
Tested-by: Srikar Dronamraju 
Cc: Ananth N Mavinakayanahalli 
Cc: Frédéric Weisbecker 
Cc: Ingo Molnar 
Cc: Masami Hiramatsu ,
Cc: Peter Zijlstra 
Cc: Srikar Dronamraju 
Cc: Stephane Eranian 
Cc: Tom Zanussi 
LKML-Reference: <20100609123530.GB9471@ghostprotocols.net>
Signed-off-by: Arnaldo Carvalho de Melo