litmus-rt.git/tools, branch linux-tip

perf symbols: Remove incorrect open-coded container_of()

2010-11-23T18:30:32+00:00

At least on ARM, padding is inserted between rb_node and sym in struct
symbol_name_rb_node, causing "((void *)sym) - sizeof(struct rb_node)" to
point inside rb_node rather than to the symbol_name_rb_node.  Fix this
by converting the code to use container_of().

Cc: Ian Munsie 
Cc: Ingo Molnar 
Cc: Ming Lei 
Cc: Paul Mackerras 
Cc: Peter Zijlstra 
Cc: Thomas Gleixner 
Cc: Tom Zanussi 
LKML-Reference: <20101123163106.GA25677@debian>
Signed-off-by: Rabin Vincent 
Signed-off-by: Arnaldo Carvalho de Melo

perf record: Handle restrictive permissions in /proc/{kallsyms,modules}

2010-11-22T16:01:55+00:00

The 59365d1 commit, even being reverted by 33e0d57, showed a non robust
behavior in 'perf record': it really should just warn the user that some
functionality will not be available.

The new behavior then becomes:

	[acme@felicio linux]$ ls -la /proc/{kallsyms,modules}
	-r-------- 1 root root 0 Nov 22 12:19 /proc/kallsyms
	-r-------- 1 root root 0 Nov 22 12:19 /proc/modules
	[acme@felicio linux]$ perf record ls -R > /dev/null
	Couldn't record kernel reference relocation symbol
	Symbol resolution may be skewed if relocation was used (e.g. kexec).
	Check /proc/kallsyms permission or run as root.
	[ perf record: Woken up 1 times to write data ]
	[ perf record: Captured and wrote 0.004 MB perf.data (~161 samples) ]
	[acme@felicio linux]$ perf report --stdio
	[kernel.kallsyms] with build id 77b05e00e64e4de1c9347d83879779b540d69f00 not found, continuing without symbols
	# Events: 98  cycles
	#
	# Overhead  Command    Shared Object                Symbol
	# ........  .......  ...............  ....................
	#
	    48.26%       ls  [kernel]         [k] ffffffff8102b92b
	    22.49%       ls  libc-2.12.90.so  [.] __strlen_sse2
	     8.35%       ls  libc-2.12.90.so  [.] __GI___strcoll_l
	     8.17%       ls  ls               [.]            11580
	     3.35%       ls  libc-2.12.90.so  [.] _IO_new_file_xsputn
	     3.33%       ls  libc-2.12.90.so  [.] _int_malloc
	     1.88%       ls  libc-2.12.90.so  [.] _int_free
	     0.84%       ls  libc-2.12.90.so  [.] malloc_consolidate
	     0.84%       ls  libc-2.12.90.so  [.] __readdir64
	     0.83%       ls  ls               [.] strlen@plt
	     0.83%       ls  libc-2.12.90.so  [.] __GI_fwrite_unlocked
	     0.83%       ls  libc-2.12.90.so  [.] __memcpy_sse2

	#
	# (For a higher level overview, try: perf report --sort comm,dso)
	#
[acme@felicio linux]$

It still has the build-ids for DSOs in the maps with hits:

[acme@felicio linux]$ perf buildid-list
77b05e00e64e4de1c9347d83879779b540d69f00 [kernel.kallsyms]
09c4a431a4a8b648fcfc2c2bdda70f56050ddff1 /bin/ls
af75ea9ad951d25e0f038901a11b3846dccb29a4 /lib64/libc-2.12.90.so
[acme@felicio linux]$

That can be used in another machine to resolve kernel symbols.

Cc: Eugene Teo 
Cc: Frederic Weisbecker 
Cc: Ingo Molnar 
Cc: Jesper Juhl 
Cc: Marcus Meissner 
Cc: Mike Galbraith 
Cc: Paul Mackerras 
Cc: Peter Zijlstra 
Cc: Sarah Sharp 
Cc: Stephane Eranian 
Cc: Tejun Heo 
Cc: Tom Zanussi 
LKML-Reference: 
Signed-off-by: Arnaldo Carvalho de Melo 

Signed-off-by: Arnaldo Carvalho de Melo

perf trace: update usage

2010-11-10T14:20:45+00:00

Update usage to reflect the different perf trace variants.

Signed-off-by: Tom Zanussi 
Acked-by: Arnaldo Carvalho de Melo

perf trace: update Documentation with new perf trace variants

2010-11-10T14:19:35+00:00

Add documentation describing new 'perf trace' command changes
e.g.  handling and live-mode/top variants.

Signed-off-by: Tom Zanussi 
Acked-by: Arnaldo Carvalho de Melo

perf trace: live-mode command-line cleanup

2010-11-10T14:16:51+00:00

This patch attempts to make the perf trace command-line for live-mode
commands more user-friendly and consistent with other perf commands.

The main change it makes is to allow  to be run as part of
perf trace live-mode commands, as other perf commands do, instead of
the system-wide traces they're currently hard-coded to by the shell
scripts.

With this patch, the following live-mode trace now works as expected:

 $ perf trace rw-by-pid ls -al

The previous system-wide behavior for this command would still be
available by explicitly specifying -a:

 $ perf trace rw-by-pid -a ls -al

and if no  is specified, the output is also system-wide:

 $ perf trace rw-by-pid

Because live-mode requires both record and report steps to be invoked,
it isn't always possible to know which args to send to the report and
which to send to the record steps - mainly this is the case for report
scripts with optional args - in those cases it would be necessary to
use separate 'perf trace record' and 'perf trace report' steps.

For example:

 $ perf trace syscall-counts ls

Here we can't decide whether ls should be passed as a param to the
syscall-counts script or whether we should invoke ls as a .
In these cases, we just say that we'll ignore optional script params
and always interpret the extra arguments as a .

If the user instead wants the other interpretation, that can be
accomplished by using separate record and report commands explicitly:

 $ perf trace record syscall-counts
 $ perf trace report syscall-counts ls

So the rules that this patch implements, which seem to make the most
intuitive sense for live-mode commands:

- for commands with optional args and commands with no args, no args
  are sent to the report script, all are sent to the record step

- for 'top' commands i.e. that end with 'top',  can't be
  used - all extra args are send to the report script as params

- for commands with required args, the n required args are taken to be
  the first n args after the script name and sent to the report
  script, and the rest are sent to the record step

Signed-off-by: Tom Zanussi 
Acked-by: Arnaldo Carvalho de Melo

perf trace record: handle commands correctly

2010-11-10T14:15:43+00:00

Because the perf-trace shell scripts hard-coded the use of the
perf-record system-wide param, a perf trace record session was always
system wide, even if it was given a command.

If given a command, perf trace record now only records the events for
the command, as users expect.

If no command is given, or if the '-a' option is used, the recorded
events are system-wide, as before.

root@tropicana:~# perf trace record syscall-counts ls -al
root@tropicana:~# perf trace
              ls-23152 [000] 39984.890387: sys_enter: NR 12 (0, 0, 0, 0, 0, 0)
              ls-23152 [000] 39984.890404: sys_enter: NR 9 (0, 0, 0, 0, 0, 0)

root@tropicana:~# perf trace record syscall-counts -a ls -al
root@tropicana:~# perf trace
    npviewer.bin-22297 [000] 39831.102709: sys_enter: NR 168 (0, 0, 0, 0, 0, 0)
              ls-23111 [000] 39831.107679: sys_enter: NR 59 (0, 0, 0, 0, 0, 0)

Signed-off-by: Tom Zanussi 
Acked-by: Arnaldo Carvalho de Melo

perf record: make the record options available outside perf record

2010-11-10T14:11:30+00:00

Other perf commands that invoke perf record, such as perf trace, may
want to reuse the options used by perf record.

This makes them non-static and renames them to avoid clashes with
other 'options' variables.

Signed-off-by: Tom Zanussi 
Acked-by: Arnaldo Carvalho de Melo

perf trace scripting: remove system-wide param from shell scripts

2010-11-10T14:08:20+00:00

Including -a unconditionally when recording doesn't allow for the
option of running scripts without it.  Future patches will add add it
back if needed at run-time.

Signed-off-by: Tom Zanussi 
Acked-by: Arnaldo Carvalho de Melo

perf trace scripting: fix some small memory leaks and missing error checks

2010-11-10T13:52:32+00:00

Free the other two fields of script_desc which somehow got overlooked,
free malloc'ed args in case exec fails, and add missing checks for
failed mallocs.

Signed-off-by: Tom Zanussi 
Acked-by: Arnaldo Carvalho de Melo

perf: Fix usages of profile_cpu in builtin-top.c to use cpu_list

2010-11-10T08:16:12+00:00

profile_cpu was left over from an earlier implementation that
supported running perf top on a single CPU.  profile_cpu was no
longer set by any switch and usages of it resulted in dead code.

Instead, convert the code to use cpu_list, which is set by the
-C  option.

Also improved the printing of nr_cpus and cpu_list by correcting
the plurals.

Signed-off-by: Corey Ashford 
Cc: a.p.zijlstra@chello.nl
Cc: acme@redhat.com
LKML-Reference: <1289269245-9388-1-git-send-email-cjashfor@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar