[PATCH 14/14] perf tools: Take Intel PT into use

From: Arnaldo Carvalho de Melo
Date: Mon Aug 17 2015 - 15:15:45 EST


From: Adrian Hunter <adrian.hunter@xxxxxxxxx>

To record an AUX area, the weak function auxtrace_record__init() must be
implemented.

Equally to decode an AUX area, the AUX area tracing type must be added
to the perf_event__process_auxtrace_info() function.

This patch makes those two changes plus hooks up default config for the
intel_pt PMU. Also some brief documentation is provided for using the
tools with intel_pt.

Commiter note:

E.g:

[root@perf4 ~]# dmesg
451 [0.405807] Performance Events: PEBS fmt2+, 16-deep LBR, Broadwell events, full-width counters, Intel PMU driver.
[root@perf4 ~]# perf --version
perf version 4.1.g53874a
[root@perf4 ~]# perf record -e intel_pt//u -a sleep 10
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.383 MB perf.data ]
[root@perf4 ~]# perf evlist
intel_pt//u
sched:sched_switch
dummy:u
[root@perf4 ~]# perf report --stdio
# To display the perf.data header info, please use --header/--header-only options.
#
#
# Total Lost Samples: 0
#
# Samples: 0 of event 'intel_pt//u'
# Event count (approx.): 0
#
# Overhead Command Shared Object Symbol
# ........ ....... ............. ......
#

# Samples: 393 of event 'sched:sched_switch'
# Event count (approx.): 393
#
# Overhead Command Shared Object Symbol
# ........ .............. ................ ..............
49.62% swapper [kernel.vmlinux] [k] __schedule
10.69% rcu_sched [kernel.vmlinux] [k] __schedule
6.62% rcuos/0 [kernel.vmlinux] [k] __schedule
5.60% kworker/0:1 [kernel.vmlinux] [k] __schedule
3.56% rcuos/3 [kernel.vmlinux] [k] __schedule
3.05% kworker/u384:2 [kernel.vmlinux] [k] __schedule
2.54% kworker/2:0 [kernel.vmlinux] [k] __schedule
2.54% tuned [kernel.vmlinux] [k] __schedule
<SNIP>
# Samples: 0 of event 'dummy:u'
# Event count (approx.): 0
#
# Overhead Command Shared Object Symbol
# ........ ....... ............. ......

# Samples: 28 of event 'instructions:u'
# Event count (approx.): 5030172
#
# Overhead Command Shared Object Symbol
# ........ .......... ................... ................................
#
21.43% tuned libpython2.7.so.1.0 [.] PyEval_EvalFrameEx
|
---PyEval_EvalFrameEx
|
|--83.33%-- PyEval_EvalCodeEx
| PyEval_EvalFrameEx
| |
| |--60.00%-- PyEval_EvalCodeEx
| | PyEval_EvalFrameEx
| | PyEval_EvalFrameEx
| |
| --40.00%-- PyEval_EvalFrameEx
|
--16.67%-- PyEval_EvalFrameEx
PyEval_EvalCodeEx
PyEval_EvalFrameEx
PyEval_EvalCodeEx
PyEval_EvalFrameEx
PyEval_EvalFrameEx

14.29% tuned libpython2.7.so.1.0 [.] _PyType_Lookup
|
---_PyType_Lookup
_PyObject_GenericGetAttrWithDict
PyEval_EvalFrameEx
PyEval_EvalCodeEx
PyEval_EvalFrameEx
PyEval_EvalCodeEx
PyEval_EvalFrameEx
|
|--75.00%-- PyEval_EvalFrameEx
|
--25.00%-- PyEval_EvalCodeEx
PyEval_EvalFrameEx
PyEval_EvalFrameEx

3.57% irqbalance irqbalance [.] 0x0000000000004038
|
---0x4038
0x4761
0x4761
0x4761
0x49f1
0x2295

3.57% irqbalance libc-2.17.so [.] __GI_____strtoull_l_internal
|
---__GI_____strtoull_l_internal
0x6f49
0x229a

3.57% irqbalance libc-2.17.so [.] __strchrnul
|
---__strchrnul
vfprintf
__vsprintf_chk
__sprintf_chk
0x2724
0x4038
0x2331

3.57% irqbalance libc-2.17.so [.] __strstr_sse42
|
---__strstr_sse42
0x71e0
0x229f

# And now to some userspace ftrace on uninstrumented binaries 8-) :
# Hand edited to make it a bit more compact, replacing /home/acme/bin/perf
# with /bin/perf:

[root@perf4 ~]# perf script
perf 8921 [3] 7.310889: 1 branches:u: 0 [unknown] ([unknown]) => 7fcecadbf257 __GI___ioctl (/usr/lib64/libc-2.17.so)
perf 8921 [3] 7.310889: 1 branches:u: 7fcecadbf25f __GI___ioctl (/usr/lib64/libc-2.17.so) => 481689 perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.310889: 1 branches:u: 481694 perf_evlist__enable (/bin/perf) => 481614 perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.310889: 1 branches:u: 481630 perf_evlist__enable (/bin/perf) => 4816d8 perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.310889: 1 branches:u: 4816de perf_evlist__enable (/bin/perf) => 48164f perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.310889: 1 branches:u: 481652 perf_evlist__enable (/bin/perf) => 48165f perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.310889: 1 branches:u: 481684 perf_evlist__enable (/bin/perf) => 41d250 ioctl@plt (/bin/perf)
perf 8921 [3] 7.310889: 1 branches:u: 41d250 ioctl@plt (/bin/perf) => 7fcecadbf250 __GI___ioctl (/usr/lib64/libc-2.17.so)
perf 8921 [3] 7.310889: 1 branches:u: 7fcecadbf255 __GI___ioctl (/usr/lib64/libc-2.17.so) => 0 [unknown] ([unknown])
perf 8921 [3] 7.310890: 1 branches:u: 0 [unknown] ([unknown]) => 7fcecadbf257 __GI___ioctl (/usr/lib64/libc-2.17.so)
perf 8921 [3] 7.310890: 1 branches:u: 7fcecadbf25f __GI___ioctl (/usr/lib64/libc-2.17.so) => 481689 perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.310890: 1 branches:u: 481694 perf_evlist__enable (/bin/perf) => 481614 perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.310890: 1 branches:u: 481652 perf_evlist__enable (/bin/perf) => 48165f perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.310890: 1 branches:u: 481684 perf_evlist__enable (/bin/perf) => 41d250 ioctl@plt (/bin/perf)
perf 8921 [3] 7.310890: 1 branches:u: 41d250 ioctl@plt (/bin/perf) => 7fcecadbf250 __GI___ioctl (/usr/lib64/libc-2.17.so)
perf 8921 [3] 7.310890: 1 branches:u: 7fcecadbf255 __GI___ioctl (/usr/lib64/libc-2.17.so) => 0 [unknown] ([unknown])
perf 8921 [3] 7.310893: 1 branches:u: 0 [unknown] ([unknown]) => 7fcecadbf257 __GI___ioctl (/usr/lib64/libc-2.17.so)
perf 8921 [3] 7.310893: 1 branches:u: 7fcecadbf25f __GI___ioctl (/usr/lib64/libc-2.17.so) => 481689 perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.310893: 1 branches:u: 4816a8 perf_evlist__enable (/bin/perf) => 4815f8 perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.310893: 1 branches:u: 4815fe perf_evlist__enable (/bin/perf) => 481614 perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.310893: 1 branches:u: 481652 perf_evlist__enable (/bin/perf) => 48165f perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.310893: 1 branches:u: 481684 perf_evlist__enable (/bin/perf) => 41d250 ioctl@plt (/bin/perf)
perf 8921 [3] 7.310893: 1 branches:u: 41d250 ioctl@plt (/bin/perf) => 7fcecadbf250 __GI___ioctl (/usr/lib64/libc-2.17.so)
perf 8921 [3] 7.310893: 1 branches:u: 7fcecadbf255 __GI___ioctl (/usr/lib64/libc-2.17.so) => 0 [unknown] ([unknown])
perf 8921 [3] 7.310956: 1 branches:u: 0 [unknown] ([unknown]) => 7fcecadbf257 __GI___ioctl (/usr/lib64/libc-2.17.so)
perf 8921 [3] 7.310956: 1 branches:u: 7fcecadbf25f __GI___ioctl (/usr/lib64/libc-2.17.so) => 481689 perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.310956: 1 branches:u: 481694 perf_evlist__enable (/bin/perf) => 481614 perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.310956: 1 branches:u: 481630 perf_evlist__enable (/bin/perf) => 4816d8 perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.310956: 1 branches:u: 4816de perf_evlist__enable (/bin/perf) => 48164f perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.310956: 1 branches:u: 481652 perf_evlist__enable (/bin/perf) => 48165f perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.310956: 1 branches:u: 481684 perf_evlist__enable (/bin/perf) => 41d250 ioctl@plt (/bin/perf)
perf 8921 [3] 7.310956: 1 branches:u: 41d250 ioctl@plt (/bin/perf) => 7fcecadbf250 __GI___ioctl (/usr/lib64/libc-2.17.so)
perf 8921 [3] 7.310956: 1 branches:u: 7fcecadbf255 __GI___ioctl (/usr/lib64/libc-2.17.so) => 0 [unknown] ([unknown])
perf 8921 [3] 7.310961: 1 branches:u: 0 [unknown] ([unknown]) => 7fcecadbf257 __GI___ioctl (/usr/lib64/libc-2.17.so)
perf 8921 [3] 7.310961: 1 branches:u: 7fcecadbf25f __GI___ioctl (/usr/lib64/libc-2.17.so) => 481689 perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.310961: 1 branches:u: 481694 perf_evlist__enable (/bin/perf) => 481614 perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.310961: 1 branches:u: 481652 perf_evlist__enable (/bin/perf) => 48165f perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.310961: 1 branches:u: 481684 perf_evlist__enable (/bin/perf) => 41d250 ioctl@plt (/bin/perf)
perf 8921 [3] 7.310961: 1 branches:u: 41d250 ioctl@plt (/bin/perf) => 7fcecadbf250 __GI___ioctl (/usr/lib64/libc-2.17.so)
perf 8921 [3] 7.310961: 1 branches:u: 7fcecadbf255 __GI___ioctl (/usr/lib64/libc-2.17.so) => 0 [unknown] ([unknown])
perf 8921 [3] 7.310968: 1 branches:u: 0 [unknown] ([unknown]) => 7fcecadbf257 __GI___ioctl (/usr/lib64/libc-2.17.so)
perf 8921 [3] 7.310968: 1 branches:u: 7fcecadbf25f __GI___ioctl (/usr/lib64/libc-2.17.so) => 481689 perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.310968: 1 branches:u: 4816a8 perf_evlist__enable (/bin/perf) => 4815f8 perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.310968: 1 branches:u: 4815fe perf_evlist__enable (/bin/perf) => 481614 perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.310968: 1 branches:u: 481652 perf_evlist__enable (/bin/perf) => 48165f perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.310968: 1 branches:u: 481684 perf_evlist__enable (/bin/perf) => 41d250 ioctl@plt (/bin/perf)
perf 8921 [3] 7.310968: 1 branches:u: 41d250 ioctl@plt (/bin/perf) => 7fcecadbf250 __GI___ioctl (/usr/lib64/libc-2.17.so)
perf 8921 [3] 7.310968: 1 branches:u: 7fcecadbf255 __GI___ioctl (/usr/lib64/libc-2.17.so) => 0 [unknown] ([unknown])
perf 8921 [3] 7.311040: 1 branches:u: 0 [unknown] ([unknown]) => 7fcecadbf257 __GI___ioctl (/usr/lib64/libc-2.17.so)
perf 8921 [3] 7.311040: 1 branches:u: 7fcecadbf25f __GI___ioctl (/usr/lib64/libc-2.17.so) => 481689 perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.311040: 1 branches:u: 481694 perf_evlist__enable (/bin/perf) => 481614 perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.311040: 1 branches:u: 481630 perf_evlist__enable (/bin/perf) => 4816d8 perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.311040: 1 branches:u: 4816de perf_evlist__enable (/bin/perf) => 48164f perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.311040: 1 branches:u: 481652 perf_evlist__enable (/bin/perf) => 48165f perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.311040: 1 branches:u: 481684 perf_evlist__enable (/bin/perf) => 41d250 ioctl@plt (/bin/perf)
perf 8921 [3] 7.311040: 1 branches:u: 41d250 ioctl@plt (/bin/perf) => 7fcecadbf250 __GI___ioctl (/usr/lib64/libc-2.17.so)
perf 8921 [3] 7.311040: 1 branches:u: 7fcecadbf255 __GI___ioctl (/usr/lib64/libc-2.17.so) => 0 [unknown] ([unknown])
perf 8921 [3] 7.311046: 1 branches:u: 0 [unknown] ([unknown]) => 7fcecadbf257 __GI___ioctl (/usr/lib64/libc-2.17.so)
perf 8921 [3] 7.311046: 1 branches:u: 7fcecadbf25f __GI___ioctl (/usr/lib64/libc-2.17.so) => 481689 perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.311046: 1 branches:u: 481694 perf_evlist__enable (/bin/perf) => 481614 perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.311046: 1 branches:u: 481652 perf_evlist__enable (/bin/perf) => 48165f perf_evlist__enable (/bin/perf)
perf 8921 [3] 7.311046: 1 branches:u: 481684 perf_evlist__enable (/bin/perf) => 41d250 ioctl@plt (/bin/perf)
perf 8921 [3] 7.311046: 1 branches:u: 41d250 ioctl@plt (/bin/perf) => 7fcecadbf250 __GI___ioctl (/usr/lib64/libc-2.17.so)
perf 8921 [3] 7.311046: 1 branches:u: 7fcecadbf255 __GI___ioctl (/usr/lib64/libc-2.17.so) => 0 [unknown] ([unknown])
perf 8921 [3] 7.311050: 1 branches:u: 0 [unknown] ([unknown]) => 7fcecadbf257 __GI___ioctl (/usr/lib64/libc-2.17.so)
perf 8921 [3] 7.311050: 1 branches:u: 7fcecadbf25f __GI___ioctl (/usr/lib64/libc-2.17.so) => 481689 perf_evlist__enable (/bin/perf)
:

Signed-off-by: Adrian Hunter <adrian.hunter@xxxxxxxxx>
Tested-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Link: http://lkml.kernel.org/r/1437150840-31811-8-git-send-email-adrian.hunter@xxxxxxxxx
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
---
tools/perf/Documentation/intel-pt.txt | 588 ++++++++++++++++++++++++++++++++++
tools/perf/arch/x86/util/Build | 2 +
tools/perf/arch/x86/util/auxtrace.c | 38 +++
tools/perf/arch/x86/util/pmu.c | 15 +
tools/perf/util/auxtrace.c | 5 +-
tools/perf/util/pmu.c | 4 +-
6 files changed, 649 insertions(+), 3 deletions(-)
create mode 100644 tools/perf/Documentation/intel-pt.txt
create mode 100644 tools/perf/arch/x86/util/auxtrace.c
create mode 100644 tools/perf/arch/x86/util/pmu.c

diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt
new file mode 100644
index 000000000000..2866b62eb293
--- /dev/null
+++ b/tools/perf/Documentation/intel-pt.txt
@@ -0,0 +1,588 @@
+Intel Processor Trace
+=====================
+
+Overview
+========
+
+Intel Processor Trace (Intel PT) is an extension of Intel Architecture that
+collects information about software execution such as control flow, execution
+modes and timings and formats it into highly compressed binary packets.
+Technical details are documented in the Intel 64 and IA-32 Architectures
+Software Developer Manuals, Chapter 36 Intel Processor Trace.
+
+Intel PT is first supported in Intel Core M and 5th generation Intel Core
+processors that are based on the Intel micro-architecture code name Broadwell.
+
+Trace data is collected by 'perf record' and stored within the perf.data file.
+See below for options to 'perf record'.
+
+Trace data must be 'decoded' which involves walking the object code and matching
+the trace data packets. For example a TNT packet only tells whether a
+conditional branch was taken or not taken, so to make use of that packet the
+decoder must know precisely which instruction was being executed.
+
+Decoding is done on-the-fly. The decoder outputs samples in the same format as
+samples output by perf hardware events, for example as though the "instructions"
+or "branches" events had been recorded. Presently 3 tools support this:
+'perf script', 'perf report' and 'perf inject'. See below for more information
+on using those tools.
+
+The main distinguishing feature of Intel PT is that the decoder can determine
+the exact flow of software execution. Intel PT can be used to understand why
+and how did software get to a certain point, or behave a certain way. The
+software does not have to be recompiled, so Intel PT works with debug or release
+builds, however the executed images are needed - which makes use in JIT-compiled
+environments, or with self-modified code, a challenge. Also symbols need to be
+provided to make sense of addresses.
+
+A limitation of Intel PT is that it produces huge amounts of trace data
+(hundreds of megabytes per second per core) which takes a long time to decode,
+for example two or three orders of magnitude longer than it took to collect.
+Another limitation is the performance impact of tracing, something that will
+vary depending on the use-case and architecture.
+
+
+Quickstart
+==========
+
+It is important to start small. That is because it is easy to capture vastly
+more data than can possibly be processed.
+
+The simplest thing to do with Intel PT is userspace profiling of small programs.
+Data is captured with 'perf record' e.g. to trace 'ls' userspace-only:
+
+ perf record -e intel_pt//u ls
+
+And profiled with 'perf report' e.g.
+
+ perf report
+
+To also trace kernel space presents a problem, namely kernel self-modifying
+code. A fairly good kernel image is available in /proc/kcore but to get an
+accurate image a copy of /proc/kcore needs to be made under the same conditions
+as the data capture. A script perf-with-kcore can do that, but beware that the
+script makes use of 'sudo' to copy /proc/kcore. If you have perf installed
+locally from the source tree you can do:
+
+ ~/libexec/perf-core/perf-with-kcore record pt_ls -e intel_pt// -- ls
+
+which will create a directory named 'pt_ls' and put the perf.data file and
+copies of /proc/kcore, /proc/kallsyms and /proc/modules into it. Then to use
+'perf report' becomes:
+
+ ~/libexec/perf-core/perf-with-kcore report pt_ls
+
+Because samples are synthesized after-the-fact, the sampling period can be
+selected for reporting. e.g. sample every microsecond
+
+ ~/libexec/perf-core/perf-with-kcore report pt_ls --itrace=i1usge
+
+See the sections below for more information about the --itrace option.
+
+Beware the smaller the period, the more samples that are produced, and the
+longer it takes to process them.
+
+Also note that the coarseness of Intel PT timing information will start to
+distort the statistical value of the sampling as the sampling period becomes
+smaller.
+
+To represent software control flow, "branches" samples are produced. By default
+a branch sample is synthesized for every single branch. To get an idea what
+data is available you can use the 'perf script' tool with no parameters, which
+will list all the samples.
+
+ perf record -e intel_pt//u ls
+ perf script
+
+An interesting field that is not printed by default is 'flags' which can be
+displayed as follows:
+
+ perf script -Fcomm,tid,pid,time,cpu,event,trace,ip,sym,dso,addr,symoff,flags
+
+The flags are "bcrosyiABEx" which stand for branch, call, return, conditional,
+system, asynchronous, interrupt, transaction abort, trace begin, trace end, and
+in transaction, respectively.
+
+While it is possible to create scripts to analyze the data, an alternative
+approach is available to export the data to a postgresql database. Refer to
+script export-to-postgresql.py for more details, and to script
+call-graph-from-postgresql.py for an example of using the database.
+
+As mentioned above, it is easy to capture too much data. One way to limit the
+data captured is to use 'snapshot' mode which is explained further below.
+Refer to 'new snapshot option' and 'Intel PT modes of operation' further below.
+
+Another problem that will be experienced is decoder errors. They can be caused
+by inability to access the executed image, self-modified or JIT-ed code, or the
+inability to match side-band information (such as context switches and mmaps)
+which results in the decoder not knowing what code was executed.
+
+There is also the problem of perf not being able to copy the data fast enough,
+resulting in data lost because the buffer was full. See 'Buffer handling' below
+for more details.
+
+
+perf record
+===========
+
+new event
+---------
+
+The Intel PT kernel driver creates a new PMU for Intel PT. PMU events are
+selected by providing the PMU name followed by the "config" separated by slashes.
+An enhancement has been made to allow default "config" e.g. the option
+
+ -e intel_pt//
+
+will use a default config value. Currently that is the same as
+
+ -e intel_pt/tsc,noretcomp=0/
+
+which is the same as
+
+ -e intel_pt/tsc=1,noretcomp=0/
+
+The config terms are listed in /sys/devices/intel_pt/format. They are bit
+fields within the config member of the struct perf_event_attr which is
+passed to the kernel by the perf_event_open system call. They correspond to bit
+fields in the IA32_RTIT_CTL MSR. Here is a list of them and their definitions:
+
+ $ for f in `ls /sys/devices/intel_pt/format`;do
+ > echo $f
+ > cat /sys/devices/intel_pt/format/$f
+ > done
+ noretcomp
+ config:11
+ tsc
+ config:10
+
+Note that the default config must be overridden for each term i.e.
+
+ -e intel_pt/noretcomp=0/
+
+is the same as:
+
+ -e intel_pt/tsc=1,noretcomp=0/
+
+So, to disable TSC packets use:
+
+ -e intel_pt/tsc=0/
+
+It is also possible to specify the config value explicitly:
+
+ -e intel_pt/config=0x400/
+
+Note that, as with all events, the event is suffixed with event modifiers:
+
+ u userspace
+ k kernel
+ h hypervisor
+ G guest
+ H host
+ p precise ip
+
+'h', 'G' and 'H' are for virtualization which is not supported by Intel PT.
+'p' is also not relevant to Intel PT. So only options 'u' and 'k' are
+meaningful for Intel PT.
+
+perf_event_attr is displayed if the -vv option is used e.g.
+
+ ------------------------------------------------------------
+ perf_event_attr:
+ type 6
+ size 112
+ config 0x400
+ { sample_period, sample_freq } 1
+ sample_type IP|TID|TIME|CPU|IDENTIFIER
+ read_format ID
+ disabled 1
+ inherit 1
+ exclude_kernel 1
+ exclude_hv 1
+ enable_on_exec 1
+ sample_id_all 1
+ ------------------------------------------------------------
+ sys_perf_event_open: pid 31104 cpu 0 group_fd -1 flags 0x8
+ sys_perf_event_open: pid 31104 cpu 1 group_fd -1 flags 0x8
+ sys_perf_event_open: pid 31104 cpu 2 group_fd -1 flags 0x8
+ sys_perf_event_open: pid 31104 cpu 3 group_fd -1 flags 0x8
+ ------------------------------------------------------------
+
+
+new snapshot option
+-------------------
+
+To select snapshot mode a new option has been added:
+
+ -S
+
+Optionally it can be followed by the snapshot size e.g.
+
+ -S0x100000
+
+The default snapshot size is the auxtrace mmap size. If neither auxtrace mmap size
+nor snapshot size is specified, then the default is 4MiB for privileged users
+(or if /proc/sys/kernel/perf_event_paranoid < 0), 128KiB for unprivileged users.
+If an unprivileged user does not specify mmap pages, the mmap pages will be
+reduced as described in the 'new auxtrace mmap size option' section below.
+
+The snapshot size is displayed if the option -vv is used e.g.
+
+ Intel PT snapshot size: %zu
+
+
+new auxtrace mmap size option
+---------------------------
+
+Intel PT buffer size is specified by an addition to the -m option e.g.
+
+ -m,16
+
+selects a buffer size of 16 pages i.e. 64KiB.
+
+Note that the existing functionality of -m is unchanged. The auxtrace mmap size
+is specified by the optional addition of a comma and the value.
+
+The default auxtrace mmap size for Intel PT is 4MiB/page_size for privileged users
+(or if /proc/sys/kernel/perf_event_paranoid < 0), 128KiB for unprivileged users.
+If an unprivileged user does not specify mmap pages, the mmap pages will be
+reduced from the default 512KiB/page_size to 256KiB/page_size, otherwise the
+user is likely to get an error as they exceed their mlock limit (Max locked
+memory as shown in /proc/self/limits). Note that perf does not count the first
+512KiB (actually /proc/sys/kernel/perf_event_mlock_kb minus 1 page) per cpu
+against the mlock limit so an unprivileged user is allowed 512KiB per cpu plus
+their mlock limit (which defaults to 64KiB but is not multiplied by the number
+of cpus).
+
+In full-trace mode, powers of two are allowed for buffer size, with a minimum
+size of 2 pages. In snapshot mode, it is the same but the minimum size is
+1 page.
+
+The mmap size and auxtrace mmap size are displayed if the -vv option is used e.g.
+
+ mmap length 528384
+ auxtrace mmap length 4198400
+
+
+Intel PT modes of operation
+---------------------------
+
+Intel PT can be used in 2 modes:
+ full-trace mode
+ snapshot mode
+
+Full-trace mode traces continuously e.g.
+
+ perf record -e intel_pt//u uname
+
+Snapshot mode captures the available data when a signal is sent e.g.
+
+ perf record -v -e intel_pt//u -S ./loopy 1000000000 &
+ [1] 11435
+ kill -USR2 11435
+ Recording AUX area tracing snapshot
+
+Note that the signal sent is SIGUSR2.
+Note that "Recording AUX area tracing snapshot" is displayed because the -v
+option is used.
+
+The 2 modes cannot be used together.
+
+
+Buffer handling
+---------------
+
+There may be buffer limitations (i.e. single ToPa entry) which means that actual
+buffer sizes are limited to powers of 2 up to 4MiB (MAX_ORDER). In order to
+provide other sizes, and in particular an arbitrarily large size, multiple
+buffers are logically concatenated. However an interrupt must be used to switch
+between buffers. That has two potential problems:
+ a) the interrupt may not be handled in time so that the current buffer
+ becomes full and some trace data is lost.
+ b) the interrupts may slow the system and affect the performance
+ results.
+
+If trace data is lost, the driver sets 'truncated' in the PERF_RECORD_AUX event
+which the tools report as an error.
+
+In full-trace mode, the driver waits for data to be copied out before allowing
+the (logical) buffer to wrap-around. If data is not copied out quickly enough,
+again 'truncated' is set in the PERF_RECORD_AUX event. If the driver has to
+wait, the intel_pt event gets disabled. Because it is difficult to know when
+that happens, perf tools always re-enable the intel_pt event after copying out
+data.
+
+
+Intel PT and build ids
+----------------------
+
+By default "perf record" post-processes the event stream to find all build ids
+for executables for all addresses sampled. Deliberately, Intel PT is not
+decoded for that purpose (it would take too long). Instead the build ids for
+all executables encountered (due to mmap, comm or task events) are included
+in the perf.data file.
+
+To see buildids included in the perf.data file use the command:
+
+ perf buildid-list
+
+If the perf.data file contains Intel PT data, that is the same as:
+
+ perf buildid-list --with-hits
+
+
+Snapshot mode and event disabling
+---------------------------------
+
+In order to make a snapshot, the intel_pt event is disabled using an IOCTL,
+namely PERF_EVENT_IOC_DISABLE. However doing that can also disable the
+collection of side-band information. In order to prevent that, a dummy
+software event has been introduced that permits tracking events (like mmaps) to
+continue to be recorded while intel_pt is disabled. That is important to ensure
+there is complete side-band information to allow the decoding of subsequent
+snapshots.
+
+A test has been created for that. To find the test:
+
+ perf test list
+ ...
+ 23: Test using a dummy software event to keep tracking
+
+To run the test:
+
+ perf test 23
+ 23: Test using a dummy software event to keep tracking : Ok
+
+
+perf record modes (nothing new here)
+------------------------------------
+
+perf record essentially operates in one of three modes:
+ per thread
+ per cpu
+ workload only
+
+"per thread" mode is selected by -t or by --per-thread (with -p or -u or just a
+workload).
+"per cpu" is selected by -C or -a.
+"workload only" mode is selected by not using the other options but providing a
+command to run (i.e. the workload).
+
+In per-thread mode an exact list of threads is traced. There is no inheritance.
+Each thread has its own event buffer.
+
+In per-cpu mode all processes (or processes from the selected cgroup i.e. -G
+option, or processes selected with -p or -u) are traced. Each cpu has its own
+buffer. Inheritance is allowed.
+
+In workload-only mode, the workload is traced but with per-cpu buffers.
+Inheritance is allowed. Note that you can now trace a workload in per-thread
+mode by using the --per-thread option.
+
+
+Privileged vs non-privileged users
+----------------------------------
+
+Unless /proc/sys/kernel/perf_event_paranoid is set to -1, unprivileged users
+have memory limits imposed upon them. That affects what buffer sizes they can
+have as outlined above.
+
+Unless /proc/sys/kernel/perf_event_paranoid is set to -1, unprivileged users are
+not permitted to use tracepoints which means there is insufficient side-band
+information to decode Intel PT in per-cpu mode, and potentially workload-only
+mode too if the workload creates new processes.
+
+Note also, that to use tracepoints, read-access to debugfs is required. So if
+debugfs is not mounted or the user does not have read-access, it will again not
+be possible to decode Intel PT in per-cpu mode.
+
+
+sched_switch tracepoint
+-----------------------
+
+The sched_switch tracepoint is used to provide side-band data for Intel PT
+decoding. sched_switch events are automatically added. e.g. the second event
+shown below
+
+ $ perf record -vv -e intel_pt//u uname
+ ------------------------------------------------------------
+ perf_event_attr:
+ type 6
+ size 112
+ config 0x400
+ { sample_period, sample_freq } 1
+ sample_type IP|TID|TIME|CPU|IDENTIFIER
+ read_format ID
+ disabled 1
+ inherit 1
+ exclude_kernel 1
+ exclude_hv 1
+ enable_on_exec 1
+ sample_id_all 1
+ ------------------------------------------------------------
+ sys_perf_event_open: pid 31104 cpu 0 group_fd -1 flags 0x8
+ sys_perf_event_open: pid 31104 cpu 1 group_fd -1 flags 0x8
+ sys_perf_event_open: pid 31104 cpu 2 group_fd -1 flags 0x8
+ sys_perf_event_open: pid 31104 cpu 3 group_fd -1 flags 0x8
+ ------------------------------------------------------------
+ perf_event_attr:
+ type 2
+ size 112
+ config 0x108
+ { sample_period, sample_freq } 1
+ sample_type IP|TID|TIME|CPU|PERIOD|RAW|IDENTIFIER
+ read_format ID
+ inherit 1
+ sample_id_all 1
+ exclude_guest 1
+ ------------------------------------------------------------
+ sys_perf_event_open: pid -1 cpu 0 group_fd -1 flags 0x8
+ sys_perf_event_open: pid -1 cpu 1 group_fd -1 flags 0x8
+ sys_perf_event_open: pid -1 cpu 2 group_fd -1 flags 0x8
+ sys_perf_event_open: pid -1 cpu 3 group_fd -1 flags 0x8
+ ------------------------------------------------------------
+ perf_event_attr:
+ type 1
+ size 112
+ config 0x9
+ { sample_period, sample_freq } 1
+ sample_type IP|TID|TIME|IDENTIFIER
+ read_format ID
+ disabled 1
+ inherit 1
+ exclude_kernel 1
+ exclude_hv 1
+ mmap 1
+ comm 1
+ enable_on_exec 1
+ task 1
+ sample_id_all 1
+ mmap2 1
+ comm_exec 1
+ ------------------------------------------------------------
+ sys_perf_event_open: pid 31104 cpu 0 group_fd -1 flags 0x8
+ sys_perf_event_open: pid 31104 cpu 1 group_fd -1 flags 0x8
+ sys_perf_event_open: pid 31104 cpu 2 group_fd -1 flags 0x8
+ sys_perf_event_open: pid 31104 cpu 3 group_fd -1 flags 0x8
+ mmap size 528384B
+ AUX area mmap length 4194304
+ perf event ring buffer mmapped per cpu
+ Synthesizing auxtrace information
+ Linux
+ [ perf record: Woken up 1 times to write data ]
+ [ perf record: Captured and wrote 0.042 MB perf.data ]
+
+Note, the sched_switch event is only added if the user is permitted to use it
+and only in per-cpu mode.
+
+Note also, the sched_switch event is only added if TSC packets are requested.
+That is because, in the absence of timing information, the sched_switch events
+cannot be matched against the Intel PT trace.
+
+
+perf script
+===========
+
+By default, perf script will decode trace data found in the perf.data file.
+This can be further controlled by new option --itrace.
+
+
+New --itrace option
+-------------------
+
+Having no option is the same as
+
+ --itrace
+
+which, in turn, is the same as
+
+ --itrace=ibxe
+
+The letters are:
+
+ i synthesize "instructions" events
+ b synthesize "branches" events
+ x synthesize "transactions" events
+ c synthesize branches events (calls only)
+ r synthesize branches events (returns only)
+ e synthesize tracing error events
+ d create a debug log
+ g synthesize a call chain (use with i or x)
+
+"Instructions" events look like they were recorded by "perf record -e
+instructions".
+
+"Branches" events look like they were recorded by "perf record -e branches". "c"
+and "r" can be combined to get calls and returns.
+
+"Transactions" events correspond to the start or end of transactions. The
+'flags' field can be used in perf script to determine whether the event is a
+tranasaction start, commit or abort.
+
+Error events are new. They show where the decoder lost the trace. Error events
+are quite important. Users must know if what they are seeing is a complete
+picture or not.
+
+The "d" option will cause the creation of a file "intel_pt.log" containing all
+decoded packets and instructions. Note that this option slows down the decoder
+and that the resulting file may be very large.
+
+In addition, the period of the "instructions" event can be specified. e.g.
+
+ --itrace=i10us
+
+sets the period to 10us i.e. one instruction sample is synthesized for each 10
+microseconds of trace. Alternatives to "us" are "ms" (milliseconds),
+"ns" (nanoseconds), "t" (TSC ticks) or "i" (instructions).
+
+"ms", "us" and "ns" are converted to TSC ticks.
+
+The timing information included with Intel PT does not give the time of every
+instruction. Consequently, for the purpose of sampling, the decoder estimates
+the time since the last timing packet based on 1 tick per instruction. The time
+on the sample is *not* adjusted and reflects the last known value of TSC.
+
+For Intel PT, the default period is 100us.
+
+Also the call chain size (default 16, max. 1024) for instructions or
+transactions events can be specified. e.g.
+
+ --itrace=ig32
+ --itrace=xg32
+
+To disable trace decoding entirely, use the option --no-itrace.
+
+
+dump option
+-----------
+
+perf script has an option (-D) to "dump" the events i.e. display the binary
+data.
+
+When -D is used, Intel PT packets are displayed. The packet decoder does not
+pay attention to PSB packets, but just decodes the bytes - so the packets seen
+by the actual decoder may not be identical in places where the data is corrupt.
+One example of that would be when the buffer-switching interrupt has been too
+slow, and the buffer has been filled completely. In that case, the last packet
+in the buffer might be truncated and immediately followed by a PSB as the trace
+continues in the next buffer.
+
+To disable the display of Intel PT packets, combine the -D option with
+--no-itrace.
+
+
+perf report
+===========
+
+By default, perf report will decode trace data found in the perf.data file.
+This can be further controlled by new option --itrace exactly the same as
+perf script, with the exception that the default is --itrace=igxe.
+
+
+perf inject
+===========
+
+perf inject also accepts the --itrace option in which case tracing data is
+removed and replaced with the synthesized events. e.g.
+
+ perf inject --itrace -i perf.data -o perf.data.new
diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build
index 139608878888..a8be9f9d0462 100644
--- a/tools/perf/arch/x86/util/Build
+++ b/tools/perf/arch/x86/util/Build
@@ -1,5 +1,6 @@
libperf-y += header.o
libperf-y += tsc.o
+libperf-y += pmu.o
libperf-y += kvm-stat.o

libperf-$(CONFIG_DWARF) += dwarf-regs.o
@@ -7,4 +8,5 @@ libperf-$(CONFIG_DWARF) += dwarf-regs.o
libperf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o
libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o

+libperf-$(CONFIG_AUXTRACE) += auxtrace.o
libperf-$(CONFIG_AUXTRACE) += intel-pt.o
diff --git a/tools/perf/arch/x86/util/auxtrace.c b/tools/perf/arch/x86/util/auxtrace.c
new file mode 100644
index 000000000000..e7654b506312
--- /dev/null
+++ b/tools/perf/arch/x86/util/auxtrace.c
@@ -0,0 +1,38 @@
+/*
+ * auxtrace.c: AUX area tracing support
+ * Copyright (c) 2013-2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include "../../util/header.h"
+#include "../../util/auxtrace.h"
+#include "../../util/intel-pt.h"
+
+struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist __maybe_unused,
+ int *err)
+{
+ char buffer[64];
+ int ret;
+
+ *err = 0;
+
+ ret = get_cpuid(buffer, sizeof(buffer));
+ if (ret) {
+ *err = ret;
+ return NULL;
+ }
+
+ if (!strncmp(buffer, "GenuineIntel,", 13))
+ return intel_pt_recording_init(err);
+
+ return NULL;
+}
diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c
new file mode 100644
index 000000000000..fd11cc3ce780
--- /dev/null
+++ b/tools/perf/arch/x86/util/pmu.c
@@ -0,0 +1,15 @@
+#include <string.h>
+
+#include <linux/perf_event.h>
+
+#include "../../util/intel-pt.h"
+#include "../../util/pmu.h"
+
+struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
+{
+#ifdef HAVE_AUXTRACE_SUPPORT
+ if (!strcmp(pmu->name, INTEL_PT_PMU_NAME))
+ return intel_pt_pmu_default_config(pmu);
+#endif
+ return NULL;
+}
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 49dbfbeedb68..0f0b7e11e2d9 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -47,6 +47,8 @@
#include "debug.h"
#include "parse-options.h"

+#include "intel-pt.h"
+
int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
struct auxtrace_mmap_params *mp,
void *userpg, int fd)
@@ -876,7 +878,7 @@ static bool auxtrace__dont_decode(struct perf_session *session)

int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
union perf_event *event,
- struct perf_session *session __maybe_unused)
+ struct perf_session *session)
{
enum auxtrace_type type = event->auxtrace_info.type;

@@ -885,6 +887,7 @@ int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,

switch (type) {
case PERF_AUXTRACE_INTEL_PT:
+ return intel_pt_process_auxtrace_info(event, session);
case PERF_AUXTRACE_UNKNOWN:
default:
return -EINVAL;
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 84cad054d6f7..3c71138e7672 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -462,8 +462,8 @@ static struct perf_pmu *pmu_lookup(const char *name)
LIST_HEAD(aliases);
__u32 type;

- /* No support for intel_bts or intel_pt so disallow them */
- if (!strcmp(name, "intel_bts") || !strcmp(name, "intel_pt"))
+ /* No support for intel_bts so disallow it */
+ if (!strcmp(name, "intel_bts"))
return NULL;

/*
--
2.1.0

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/