IF YOU WOULD LIKE TO GET AN ACCOUNT, please write an
email to Administrator. User accounts are meant only to access repo
and report issues and/or generate pull requests.
This is a purpose-specific Git hosting for
BaseALT
projects. Thank you for your understanding!
Только зарегистрированные пользователи имеют доступ к сервису!
Для получения аккаунта, обратитесь к администратору.
Pull perf events changes for v3.4 from Ingo Molnar:
- New "hardware based branch profiling" feature both on the kernel and
the tooling side, on CPUs that support it. (modern x86 Intel CPUs
with the 'LBR' hardware feature currently.)
This new feature is basically a sophisticated 'magnifying glass' for
branch execution - something that is pretty difficult to extract from
regular, function histogram centric profiles.
The simplest mode is activated via 'perf record -b', and the result
looks like this in perf report:
$ perf record -b any_call,u -e cycles:u branchy
$ perf report -b --sort=symbol
52.34% [.] main [.] f1
24.04% [.] f1 [.] f3
23.60% [.] f1 [.] f2
0.01% [k] _IO_new_file_xsputn [k] _IO_file_overflow
0.01% [k] _IO_vfprintf_internal [k] _IO_new_file_xsputn
0.01% [k] _IO_vfprintf_internal [k] strchrnul
0.01% [k] __printf [k] _IO_vfprintf_internal
0.01% [k] main [k] __printf
This output shows from/to branch columns and shows the highest
percentage (from,to) jump combinations - i.e. the most likely taken
branches in the system. "branches" can also include function calls
and any other synchronous and asynchronous transitions of the
instruction pointer that are not 'next instruction' - such as system
calls, traps, interrupts, etc.
This feature comes with (hopefully intuitive) flat ascii and TUI
support in perf report.
- Various 'perf annotate' visual improvements for us assembly junkies.
It will now recognize function calls in the TUI and by hitting enter
you can follow the call (recursively) and back, amongst other
improvements.
- Multiple threads/processes recording support in perf record, perf
stat, perf top - which is activated via a comma-list of PIDs:
perf top -p 21483,21485
perf stat -p 21483,21485 -ddd
perf record -p 21483,21485
- Support for per UID views, via the --uid paramter to perf top, perf
report, etc. For example 'perf top --uid mingo' will only show the
tasks that I am running, excluding other users, root, etc.
- Jump label restructurings and improvements - this includes the
factoring out of the (hopefully much clearer) include/linux/static_key.h
generic facility:
struct static_key key = STATIC_KEY_INIT_FALSE;
...
if (static_key_false(&key))
do unlikely code
else
do likely code
...
static_key_slow_inc();
...
static_key_slow_inc();
...
The static_key_false() branch will be generated into the code with as
little impact to the likely code path as possible. the
static_key_slow_*() APIs flip the branch via live kernel code patching.
This facility can now be used more widely within the kernel to
micro-optimize hot branches whose likelihood matches the static-key
usage and fast/slow cost patterns.
- SW function tracer improvements: perf support and filtering support.
- Various hardenings of the perf.data ABI, to make older perf.data's
smoother on newer tool versions, to make new features integrate more
smoothly, to support cross-endian recording/analyzing workflows
better, etc.
- Restructuring of the kprobes code, the splitting out of 'optprobes',
and a corner case bugfix.
- Allow the tracing of kernel console output (printk).
- Improvements/fixes to user-space RDPMC support, allowing user-space
self-profiling code to extract PMU counts without performing any
system calls, while playing nice with the kernel side.
- 'perf bench' improvements
- ... and lots of internal restructurings, cleanups and fixes that made
these features possible. And, as usual this list is incomplete as
there were also lots of other improvements
* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (120 commits)
perf report: Fix annotate double quit issue in branch view mode
perf report: Remove duplicate annotate choice in branch view mode
perf/x86: Prettify pmu config literals
perf report: Enable TUI in branch view mode
perf report: Auto-detect branch stack sampling mode
perf record: Add HEADER_BRANCH_STACK tag
perf record: Provide default branch stack sampling mode option
perf tools: Make perf able to read files from older ABIs
perf tools: Fix ABI compatibility bug in print_event_desc()
perf tools: Enable reading of perf.data files from different ABI rev
perf: Add ABI reference sizes
perf report: Add support for taken branch sampling
perf record: Add support for sampling taken branch
perf tools: Add code to support PERF_SAMPLE_BRANCH_STACK
x86/kprobes: Split out optprobe related code to kprobes-opt.c
x86/kprobes: Fix a bug which can modify kernel code permanently
x86/kprobes: Fix instruction recovery on optimized path
perf: Add callback to flush branch_stack on context switch
perf: Disable PERF_SAMPLE_BRANCH_* when not supported
perf/x86: Add LBR software filter support for Intel CPUs
...
On ancient systems I get this build failure:
util/../../../arch/x86/include/asm/unistd.h:67:29: error: asm/unistd_64.h: No such file or directory
In file included from util/cache.h:7,
from builtin-test.c:8:
util/../perf.h: In function ‘sys_perf_event_open’:In file included from util/../perf.h:16
perf.h:170: error: ‘__NR_perf_event_open’ undeclared (first use in this function)
The reason is that this old system does not have the split
unistd.h headers yet, from which to pick up the syscall
definitions.
Add the syscall numbers to the already existing i386 and x86_64
blocks in perf.h, and also provide empty include file stubs.
With this patch perf builds and works fine on 5 years old
user-space as well.
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Link: http://lkml.kernel.org/n/tip-jctwg64le1w47tuaoeyftsg9@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
I have a workload where perf top scribbles over the stack and we SEGV.
What makes it interesting is that an snprintf is causing this.
The workload is a c++ gem that has method names over 3000 characters
long, but snprintf is designed to avoid overrunning buffers. So what
went wrong?
The problem is we assume snprintf returns the number of characters
written:
ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", self->level);
...
ret += repsep_snprintf(bf + ret, size - ret, "%s", self->ms.sym->name);
Unfortunately this is not how snprintf works. snprintf returns the
number of characters that would have been written if there was enough
space. In the above case, if the first snprintf returns a value larger
than size, we pass a negative size into the second snprintf and happily
scribble over the stack. If you have 3000 character c++ methods thats a
lot of stack to trample.
This patch fixes repsep_snprintf by clamping the value at size - 1 which
is the maximum snprintf can write before adding the NULL terminator.
I get the sinking feeling that there are a lot of other uses of snprintf
that have this same bug, we should audit them all.
Cc: David Ahern <dsahern@gmail.com>
Cc: Eric B Munson <emunson@mgebm.net>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Yanmin Zhang <yanmin_zhang@linux.intel.com>
Cc: stable@kernel.org
Link: http://lkml.kernel.org/r/20120307114249.44275ca3@kryten
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This patch fixes a buffer overrun bug in
tracepoint_id_to_path(). The bug manisfested itself as a memory
error reported by perf record. I ran into it with perf sched:
$ perf sched rec noploop 2 noploop for 2 seconds
[ perf record: Woken up 14 times to write data ]
[ perf record: Captured and wrote 42.701 MB perf.data (~1865622 samples) ]
Fatal: No memory to alloc tracepoints list
It turned out that tracepoint_id_to_path() was reading the
tracepoint id using read() but the buffer was not large enough
to include the \n terminator for id with 4 digits or more.
The patch fixes the problem by extending the buffer to a more
reasonable size covering all possible id length include \n
terminator. Note that atoll() stops at the first non digit
character, thus it is not necessary to clear the buffer between
each read.
Signed-off-by: Stephane Eranian <eranian@google.com>
Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: fweisbec@gmail.com
Cc: dsahern@gmail.com
Link: http://lkml.kernel.org/r/20120313155102.GA6465@quad
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This patch adds support for taken branch sampling, i.e, the
PERF_SAMPLE_BRANCH_STACK feature to perf report. In other
words, to display histograms based on taken branches rather
than executed instructions addresses.
The new option is called -b and it takes no argument. To
generate meaningful output, the perf.data must have been
obtained using perf record -b xxx ... where xxx is a branch
filter option.
The output shows symbols, modules, sorted by 'who branches
where' the most often. The percentages reported in the first
column refer to the total number of branches captured and
not the usual number of samples.
Here is a quick example.
Here branchy is simple test program which looks as follows:
void f2(void)
{}
void f3(void)
{}
void f1(unsigned long n)
{
if (n & 1UL)
f2();
else
f3();
}
int main(void)
{
unsigned long i;
for (i=0; i < N; i++)
f1(i);
return 0;
}
Here is the output captured on Nehalem, if we are
only interested in user level function calls.
$ perf record -b any_call,u -e cycles:u branchy
$ perf report -b --sort=symbol
52.34% [.] main [.] f1
24.04% [.] f1 [.] f3
23.60% [.] f1 [.] f2
0.01% [k] _IO_new_file_xsputn [k] _IO_file_overflow
0.01% [k] _IO_vfprintf_internal [k] _IO_new_file_xsputn
0.01% [k] _IO_vfprintf_internal [k] strchrnul
0.01% [k] __printf [k] _IO_vfprintf_internal
0.01% [k] main [k] __printf
About half (52%) of the call branches captured are from main()
-> f1(). The second half (24%+23%) is split in two equal shares
between f1() -> f2(), f1() ->f3(). The output is as expected
given the code.
It should be noted, that using -b in perf record does not
eliminate information in the perf.data file. Consequently, a
typical profile can also be obtained by perf report by simply
not using its -b option.
It is possible to sort on branch related columns:
- dso_from, symbol_from
- dso_to, symbol_to
- mispredict
Signed-off-by: Roberto Agostino Vitillo <ravitillo@lbl.gov>
Signed-off-by: Stephane Eranian <eranian@google.com>
Cc: peterz@infradead.org
Cc: acme@redhat.com
Cc: robert.richter@amd.com
Cc: ming.m.lin@intel.com
Cc: andi@firstfloor.org
Cc: asharma@fb.com
Cc: vweaver1@eecs.utk.edu
Cc: khandual@linux.vnet.ibm.com
Cc: dsahern@gmail.com
Link: http://lkml.kernel.org/r/1328826068-11713-14-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
If perf_evsel__open() failed, the errno was set and returned properly.
However since the perf_evlist__open() called close() on fd's for all of
evsel x cpu x thread after the failure, the errno was overridden by
other code (EBADF). So the caller of the function ended up seeing
different error message and getting confused.
Fit it by restoring original return value. Because one of caller of the
function is in the python extension, and it uses system errno
internally, it'd be better restoring the original value rather than
using the return value of the function directly, IMHO (i.e. I'm not a
python expert :)
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/1329966816-23175-1-git-send-email-namhyung.kim@lge.com
Signed-off-by: Namhyung Kim <namhyung.kim@lge.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
If threads in a multi-threaded process have names shorter than the main
thread the comm for the named threads is not properly terminated.
E.g., for the process 'namedthreads' where each thread is named noploop%d
where %d is the thread number:
Before:
perf script -f comm,tid,ip,sym,dso
noploop:4ads 21616 400a49 noploop (/tmp/namedthreads)
The 'ads' in the thread comm bleeds over from the process name.
After:
perf script -f comm,tid,ip,sym,dso
noploop:4 21616 400a49 noploop (/tmp/namedthreads)
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1330111898-68071-1-git-send-email-dsahern@gmail.com
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The following commit:
b52956c perf tools: Allow multiple threads or processes in record, stat, top
introduced a bug in the thread_map code which caused perf record -a to
not setup system-wide monitoring properly.
$ taskset -c 1 noploop 1000 &
$ perf record -a -C 1 sleep 10
$ perf report -D | tail -20
cycles stats:
TOTAL events: 4413
MMAP events: 4025
COMM events: 340
SAMPLE events: 48
Here I was expecting about 10,000 samples and not 48.
In system-wide mode, the PID passed to perf_event_open() must be -1 and
it was 0. That caused the kernel to setup a per-process event on PID:0.
Consequently, the number of samples captured does not correspond to the
requested measurement.
The following one-liner fixes the problem for me with or without -C.
I would also suggest to change the malloc() to something that matches
the struct definition. thread_map->map[] is declared as int map[] and
not pid_t map[]. If map[] can only contain pids, then change the struct
definition.
Acked-by: David Ahern <dsahern@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20120221145424.GA6757@quad
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The __print_symbolic() function takes a sequence of key-value pairs for
pretty-printing a constant. The new kvm:kvm_exit print fmt uses the
expression:
__print_symbolic(..., { 0x040 + 1, "DB excp" }, ...)
Currently only atoms are supported and this print fmt fails to parse.
This patch adds support for expressions instead of just atoms so that
0x040 + 1 is parsed successfully. Also add arg_num_eval() support for
the '+' operator.
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1315148939-14313-1-git-send-email-stefanha@linux.vnet.ibm.com
Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The perf_event_attr size needs to be initialized in all cases because it
captures the ABI version.
This patch moves the initialization of the field from the
perf_event_open() syscall stub to its proper location in the
event_attr_init().
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20120209151238.GA10272@quad
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
