There's a problem in machine__findnew_vdso(), vdso buildid generated by a
32-bit machine stores it with the name 'vdso', but when processing buildid on a
64-bit machine with the same 'perf.data', perf will search for vdso named as
'vdso32' and get failed.
This patch tries to find the existing dsos in machine->dsos by thread dso_type.
64-bit thread tries to find vdso with name 'vdso', because all 64-bit vdso is
named as that. 32-bit thread first tries to find vdso with name 'vdso32' if
this thread was run on 64-bit machine, if failed, then it tries 'vdso' which
indicates that the thread was run on 32-bit machine when recording.
Committer note:
Additional explanation by Adrian Hunter:
We match maps to builds ids using the file name - consider
machine__findnew_[v]dso() called in map__new(). So in the context of a perf
data file, we consider the file name to be unique.
A vdso map does not have a file name - all we know is that it is vdso. We look
at the thread to tell if it is 32-bit, 64-bit or x32. Then we need to get the
build id which has been recorded using short name "[vdso]" or "[vdso32]" or
"[vdsox32]".
The problem is that on a 32-bit machine, we use the name "[vdso]". If you take
a 32-bit perf data file to a 64-bit machine, it gets hard to figure out if
"[vdso]" is 32-bit or 64-bit.
This patch solves that problem.
----
This also merges a followup patch fixing a problem introduced by the
original submission of this patch, that would crash 'perf record' when
recording samples for a 32-bit app on a 64-bit system.
Signed-off-by: He Kuang <hekuang@huawei.com>
Acked-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ekaterina Tumanova <tumanova@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1463475894-163531-1-git-send-email-hekuang@huawei.com
Link: http://lkml.kernel.org/r/1466578626-92406-6-git-send-email-hekuang@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The __machine__findnew_compat() function is called only from
__machine__findnew_vdso_compat() which is called only from
machine__findnew_vdso() which already holds machine->dsos.lock, so
remove locking from __machine__findnew_compat().
This manifests itself tracing 32-bit programs with a 64-bit perf.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/1436267618-20521-1-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This has a different model than the 'thread' and 'map' struct lifetimes:
there is not a definitive "don't use this DSO anymore" event, i.e. we may
get many 'struct map' holding references to the '/usr/lib64/libc-2.20.so'
DSO but then at some point some DSO may have no references but we still
don't want to straight away release its resources, because "soon" we may
get a new 'struct map' that needs it and we want to reuse its symtab or
other resources.
So we need some way to garbage collect it when crossing some memory
usage threshold, which is left for anoter patch, for now it is
sufficient to release it when calling dsos__exit(), i.e. when deleting
the whole list as part of deleting the 'struct machine' containing it,
which will leave only referenced objects being used.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/n/tip-majzgz07cm90t2tejrjy4clf@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
To allow concurrent access, next step: refcount struct dso instances, so
that we can ditch unused them when the last map pointing to it goes
away.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/n/tip-yk1k08etpd2aoe3tnrf0oizn@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
To make it consistent with the other dso lifetime routines.
For instance:
struct dso *vdso__new(struct machine *machine, const char *short_name,
const char *long_name)
Becomes:
struct dso *machine__addnew_vdso(struct machine *machine, const
char *short_name, const char *long_name)
Because:
1) There is no 'struct vdso' for us to have vdso__ prefixed routines.
2) Because it will not really just create a new instance of 'struct
dso', it'll call dso__new() but it will also insert it into the
DSO's list/rbtree, and we have a method name for that: 'addnew',
just like we have dsos__addnew().
3) So it is really a 'struct machine' operation, it is the first
argument, etc.
This way the place where this is used gets consistent:
if (vdso) {
pgoff = 0;
- dso = vdso__dso_findnew(machine, thread);
+ dso = machine__findnew_vdso(machine, thread);
} else
dso = machine__findnew_dso(machine, filename);
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/n/tip-r3w3tvh8exm9xfz3p4tz9qbz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
We can, given a DSO, figure out if it is a kernel, a kernel module or
a userlevel DSO, so stop having to process two lists in several
functions.
If searching becomes an issue at some point, we can have them in a
rbtree, etc.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-s4yb0onpdywu6dj2xl9lxi4t@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
popen() causes an error message to print if perf-read-vdso32 does not
run. Avoid that by not trying to run it if it was not built. Ditto
perf-read-vdsox32.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1414061124-26830-17-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
'perf record' post-processes the event stream to create a list of
build-ids for object files for which sample events have been recorded.
That results in those object files being recorded in the build-id cache.
In the case of VDSO, perf tools reads it from memory and copies it into
a temporary file, which as decribed above, gets added to the build-id
cache.
Then when the perf.data file is processed by other tools, the build-id
of VDSO is listed in the perf.data file and the VDSO can be read from
the build-id cache. In that case the name of the map, the short name of
the DSO, and the entry in the build-id cache are all "[vdso]".
However, in the 64-bit case, there also can be 32-bit compatibility
VDSOs.
A previous patch added programs "perf-read-vdso32" and "perf
read-vdsox32".
This patch uses those programs to read the correct VDSO for a thread and
create a temporary file just as for the 64-bit VDSO.
The map name and the entry in the build-id cache are still "[vdso]" but
the DSO short name becomes "[vdso32]" and "[vdsox32]" respectively.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1414061124-26830-16-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
perf tools copy VDSO out of memory. However, on 64-bit machines there
may be 32-bit compatibility VDOs also. To copy those requires separate
32-bit executables.
This patch adds to the build additional programs perf-read-vdso32 and
perf-read-vdsox32 for 32-bit and x32 respectively.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>,
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1414061124-26830-15-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The thread will be needed to determine the VDSO type.
Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1406035081-14301-52-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This is in preparation for supporting 32-bit compatibility VDSOs.
Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1406035081-14301-49-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This is preparation for adding support for compat VDSOs.
Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1406035081-14301-48-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The VDSO temporary file is unlinked when a session is deleted. That
precludes the possibilities that there is no session or there is more
than one session.
Correctly the vdso belongs to the machine so put the information on
'struct machine' and get rid of the global variables.
Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/53CF9B14.7040408@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This is preparation for removing the global variables used in vdso.c and
thereby fixing the lifetime of the VDSO temporary file.
Also allowance is made for the later addition of support for compat
VDSOs.
Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1406035081-14301-46-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This is preparation for removing the global variables used in vdso.c and
thereby fixing the lifetime of the VDSO temporary file.
Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1406035081-14301-45-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Moving pr_* debug macros to have it with in same object as debug
variables, becase we will change them to use verbose variable in next
patch.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1405374411-29012-3-git-send-email-jolsa@kernel.org
[ Add missing debug.h include in python scripting glue and in the libdw unwind lib ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Instead of expecting callers to set this member accodingly so that later
at dso destruction it can, if needed, be correctly free()d, make it a
requirement by passing it as a parameter to dso__set_long_name.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-na7t1tqim22vuqkt4zq5n4ri@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
When "perf record" was used on a large machine with a lot of CPUs, the
perf post-processing time (the time after the workload was done until
the perf command itself exited) could take a lot of minutes and even
hours depending on how large the resulting perf.data file was.
While running AIM7 1500-user high_systime workload on a 80-core x86-64
system with a 3.9 kernel (with only the -s -a options used), the
workload itself took about 2 minutes to run and the perf.data file had a
size of 1108.746 MB. However, the post-processing step took more than 10
minutes.
With a gprof-profiled perf binary, the time spent by perf was as
follows:
% cumulative self self total
time seconds seconds calls s/call s/call name
96.90 822.10 822.10 192156 0.00 0.00 dsos__find
0.81 828.96 6.86 172089958 0.00 0.00 rb_next
0.41 832.44 3.48 48539289 0.00 0.00 rb_erase
So 97% (822 seconds) of the time was spent in a single dsos_find()
function. After analyzing the call-graph data below:
-----------------------------------------------
0.00 822.12 192156/192156 map__new [6]
[7] 96.9 0.00 822.12 192156 vdso__dso_findnew [7]
822.10 0.00 192156/192156 dsos__find [8]
0.01 0.00 192156/192156 dsos__add [62]
0.01 0.00 192156/192366 dso__new [61]
0.00 0.00 1/45282525 memdup [31]
0.00 0.00 192156/192230 dso__set_long_name [91]
-----------------------------------------------
822.10 0.00 192156/192156 vdso__dso_findnew [7]
[8] 96.9 822.10 0.00 192156 dsos__find [8]
-----------------------------------------------
It was found that the vdso__dso_findnew() function failed to locate
VDSO__MAP_NAME ("[vdso]") in the dso list and have to insert a new
entry at the end for 192156 times. This problem is due to the fact that
there are 2 types of name in the dso entry - short name and long name.
The initial dso__new() adds "[vdso]" to both the short and long names.
After that, vdso__dso_findnew() modifies the long name to something
like /tmp/perf-vdso.so-NoXkDj. The dsos__find() function only compares
the long name. As a result, the same vdso entry is duplicated many
time in the dso list. This bug increases memory consumption as well
as slows the symbol processing time to a crawl.
To resolve this problem, the dsos__find() function interface was
modified to enable searching either the long name or the short
name. The vdso__dso_findnew() will now search only the short name
while the other call sites search for the long name as before.
With this change, the cpu time of perf was reduced from 848.38s to
15.77s and dsos__find() only accounted for 0.06% of the total time.
0.06 15.73 0.01 192151 0.00 0.00 dsos__find
Signed-off-by: Waiman Long <Waiman.Long@hp.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: "Chandramouleeswaran, Aswin" <aswin@hp.com>
Cc: "Norton, Scott J" <scott.norton@hp.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1368110568-64714-1-git-send-email-Waiman.Long@hp.com
[ replaced TRUE/FALSE with stdbool.h equivalents, fixing builds where
those macros are not present (NO_LIBPYTHON=1 NO_LIBPERL=1), fix from Jiri Olsa ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Storing data for VDSO shared object, because we need it for the post
unwind processing.
The VDSO shared object is same for all process on a running system, so
it makes no difference when we store it inside the tracer - perf.
When [vdso] map memory is hit, we retrieve [vdso] DSO image and store it
into temporary file.
During the build-id processing phase, the [vdso] DSO image is stored in
build-id db, and build-id reference is made inside perf.data. The
build-id vdso file object is called '[vdso]'. We don't use temporary
file name which gets removed when record is finished.
During report phase the vdso build-id object is treated as any other
build-id DSO object.
Adding following API for vdso object:
bool is_vdso_map(const char *filename)
- returns true if the filename matches vdso map name
struct dso *vdso__dso_findnew(struct list_head *head)
- find/create proper vdso DSO object
vdso__exit(void)
- removes temporary VDSO image if there's any
This change makes backtrace dwarf post unwind possible from [vdso] maps.
Following output is current report of [vdso] sample dwarf backtrace:
# Overhead Command Shared Object Symbol
# ........ ....... ................. .............................
#
99.52% ex [vdso] [.] 0x00007fff3ace89af
|
--- 0x7fff3ace89af
Following output is new report of [vdso] sample dwarf backtrace:
# Overhead Command Shared Object Symbol
# ........ ....... ................. .............................
#
99.52% ex [vdso] [.] 0x00000000000009af
|
--- 0x7fff3ace89af
main
__libc_start_main
_start
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1347295819-23177-5-git-send-email-jolsa@redhat.com
[ committer note: s/ALIGN/PERF_ALIGN/g to cope with the android build changes ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
He Kuang
Adrian Hunter
Arnaldo Carvalho de Melo
Jiri Olsa
Waiman Long
Jiri Olsa