Observe a segmentation fault when 'perf stat' is asked to repeat forever
with the interval option.
Without fix:
# perf stat -r 0 -I 5000 -e cycles -a sleep 10
# time counts unit events
5.000211692 3,13,89,82,34,157 cycles
10.000380119 1,53,98,52,22,294 cycles
10.040467280 17,16,79,265 cycles
Segmentation fault
This problem was only observed when we use forever option aka -r 0 and
works with limited repeats. Calling print_counter with ts being set to
NULL, is not a correct option when interval is set. Hence avoid
print_counter(NULL,..) if interval is set.
With fix:
# perf stat -r 0 -I 5000 -e cycles -a sleep 10
# time counts unit events
5.019866622 3,15,14,43,08,697 cycles
10.039865756 3,15,16,31,95,261 cycles
10.059950628 1,26,05,47,158 cycles
5.009902655 3,14,52,62,33,932 cycles
10.019880228 3,14,52,22,89,154 cycles
10.030543876 66,90,18,333 cycles
5.009848281 3,14,51,98,25,437 cycles
10.029854402 3,15,14,93,04,918 cycles
5.009834177 3,14,51,95,92,316 cycles
Committer notes:
Did the 'git bisect' to find the cset introducing the problem to add the
Fixes tag below, and at that time the problem reproduced as:
(gdb) run stat -r0 -I500 sleep 1
<SNIP>
Program received signal SIGSEGV, Segmentation fault.
print_interval (prefix=prefix@entry=0x7fffffffc8d0 "", ts=ts@entry=0x0) at builtin-stat.c:866
866 sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, csv_sep);
(gdb) bt
#0 print_interval (prefix=prefix@entry=0x7fffffffc8d0 "", ts=ts@entry=0x0) at builtin-stat.c:866
#1 0x000000000041860a in print_counters (ts=ts@entry=0x0, argc=argc@entry=2, argv=argv@entry=0x7fffffffd640) at builtin-stat.c:938
#2 0x0000000000419a7f in cmd_stat (argc=2, argv=0x7fffffffd640, prefix=<optimized out>) at builtin-stat.c:1411
#3 0x000000000045c65a in run_builtin (p=p@entry=0x6291b8 <commands+216>, argc=argc@entry=5, argv=argv@entry=0x7fffffffd640) at perf.c:370
#4 0x000000000045c893 in handle_internal_command (argc=5, argv=0x7fffffffd640) at perf.c:429
#5 0x000000000045c8f1 in run_argv (argcp=argcp@entry=0x7fffffffd4ac, argv=argv@entry=0x7fffffffd4a0) at perf.c:473
#6 0x000000000045cac9 in main (argc=<optimized out>, argv=<optimized out>) at perf.c:588
(gdb)
Mostly the same as just before this patch:
Program received signal SIGSEGV, Segmentation fault.
0x00000000005874a7 in print_interval (config=0xa1f2a0 <stat_config>, evlist=0xbc9b90, prefix=0x7fffffffd1c0 "`", ts=0x0) at util/stat-display.c:964
964 sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, config->csv_sep);
(gdb) bt
#0 0x00000000005874a7 in print_interval (config=0xa1f2a0 <stat_config>, evlist=0xbc9b90, prefix=0x7fffffffd1c0 "`", ts=0x0) at util/stat-display.c:964
#1 0x0000000000588047 in perf_evlist__print_counters (evlist=0xbc9b90, config=0xa1f2a0 <stat_config>, _target=0xa1f0c0 <target>, ts=0x0, argc=2, argv=0x7fffffffd670)
at util/stat-display.c:1172
#2 0x000000000045390f in print_counters (ts=0x0, argc=2, argv=0x7fffffffd670) at builtin-stat.c:656
#3 0x0000000000456bb5 in cmd_stat (argc=2, argv=0x7fffffffd670) at builtin-stat.c:1960
#4 0x00000000004dd2e0 in run_builtin (p=0xa30e00 <commands+288>, argc=5, argv=0x7fffffffd670) at perf.c:310
#5 0x00000000004dd54d in handle_internal_command (argc=5, argv=0x7fffffffd670) at perf.c:362
#6 0x00000000004dd694 in run_argv (argcp=0x7fffffffd4cc, argv=0x7fffffffd4c0) at perf.c:406
#7 0x00000000004dda11 in main (argc=5, argv=0x7fffffffd670) at perf.c:531
(gdb)
Fixes: d4f63a4741 ("perf stat: Introduce print_counters function")
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: stable@vger.kernel.org # v4.2+
Link: http://lore.kernel.org/lkml/20190904094738.9558-3-srikar@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
When using 'perf stat' with repeat and interval option, it shows wrong
values for events.
The wrong values will be shown for the first interval on the second and
subsequent repetitions.
Without the fix:
# perf stat -r 3 -I 2000 -e faults -e sched:sched_switch -a sleep 5
2.000282489 53 faults
2.000282489 513 sched:sched_switch
4.005478208 3,721 faults
4.005478208 2,666 sched:sched_switch
5.025470933 395 faults
5.025470933 1,307 sched:sched_switch
2.009602825 1,84,46,74,40,73,70,95,47,520 faults <------
2.009602825 1,84,46,74,40,73,70,95,49,568 sched:sched_switch <------
4.019612206 4,730 faults
4.019612206 2,746 sched:sched_switch
5.039615484 3,953 faults
5.039615484 1,496 sched:sched_switch
2.000274620 1,84,46,74,40,73,70,95,47,520 faults <------
2.000274620 1,84,46,74,40,73,70,95,47,520 sched:sched_switch <------
4.000480342 4,282 faults
4.000480342 2,303 sched:sched_switch
5.000916811 1,322 faults
5.000916811 1,064 sched:sched_switch
#
prev_raw_counts is allocated when using intervals. This is used when
calculating the difference in the counts of events when using interval.
The current counts are stored in prev_raw_counts to calculate the
differences in the next iteration.
On the first interval of the second and subsequent repetitions,
prev_raw_counts would be the values stored in the last interval of the
previous repetitions, while the current counts will only be for the
first interval of the current repetition.
Hence there is a possibility of events showing up as big number.
Fix this by resetting prev_raw_counts whenever perf stat repeats the
command.
With the fix:
# perf stat -r 3 -I 2000 -e faults -e sched:sched_switch -a sleep 5
2.019349347 2,597 faults
2.019349347 2,753 sched:sched_switch
4.019577372 3,098 faults
4.019577372 2,532 sched:sched_switch
5.019415481 1,879 faults
5.019415481 1,356 sched:sched_switch
2.000178813 8,468 faults
2.000178813 2,254 sched:sched_switch
4.000404621 7,440 faults
4.000404621 1,266 sched:sched_switch
5.040196079 2,458 faults
5.040196079 556 sched:sched_switch
2.000191939 6,870 faults
2.000191939 1,170 sched:sched_switch
4.000414103 541 faults
4.000414103 902 sched:sched_switch
5.000809863 450 faults
5.000809863 364 sched:sched_switch
#
Committer notes:
This was broken since the cset introducing the --interval feature, i.e.
--repeat + --interval wasn't tested at that point, add the Fixes tag so
that automatic scripts can pick this up.
Fixes: 13370a9b5b ("perf stat: Add interval printing")
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: stable@vger.kernel.org # v3.9+
Link: http://lore.kernel.org/lkml/20190904094738.9558-2-srikar@linux.vnet.ibm.com
[ Fixed up conflicts with libperf, i.e. some perf_{evsel,evlist} lost the 'perf' prefix ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Pruning a bit more the includes dependency tree. Building this thing on
lots of containers takes time, we better reduce the time per build, each
container is doing 6 builds when clang and clang-devel are available,
and the plan is to do a 'make -C tools/perf build-test' that have many
more.
Also helps when doing normal development, as touching some random file
will have a much reduced chance of triggering lots of rebuilds.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-r889ur2cxe16m91m2a4pl15p@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
When building with C=2, sparse makes note of a number of things:
arch/x86/events/intel/rapl.c:637:30: warning: symbol 'rapl_attr_update' was not declared. Should it be static?
arch/x86/events/intel/cstate.c:449:30: warning: symbol 'core_attr_update' was not declared. Should it be static?
arch/x86/events/intel/cstate.c:457:30: warning: symbol 'pkg_attr_update' was not declared. Should it be static?
arch/x86/events/msr.c:170:30: warning: symbol 'attr_update' was not declared. Should it be static?
arch/x86/events/intel/lbr.c:276:1: warning: symbol 'lbr_from_quirk_key' was not declared. Should it be static?
And they can all indeed be static.
Signed-off-by: Valdis Kletnieks <valdis.kletnieks@vt.edu>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/128059.1565286242@turing-police
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Since x86 instruction decoder is not only for kprobes,
it should be tested when the insn.c is compiled.
(e.g. perf is enabled but kprobes is disabled)
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: cbe5c34c8c ("x86: Compile insn.c and inat.c only for KPROBES")
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:
objtool:
Josh Poimboeuf:
- Move x86 insn decoder to a common location.
Arnaldo Carvalho de Melo:
- Ignore intentional differences for the x86 insn decoder.
build:
Arnaldo Carvalho de Melo:
- Ignore intentional differences for the x86 insn decoder.
Intel PT:
Josh Poimboeuf:
- Use shared x86 insn decoder.
metric groups:
Jin Yao:
- Scale the metric result.
- Support multiple events.
perf c2c:
Jiri Olsa:
- Display proper cpu count in nodes column.
Miscellaneous:
Kyle Meyer:
- Replace MAX_NR_CPUS with perf_env::nr_cpus_online, i.e. with
the number of online CPUs as detected at tool start and/or
recorded in the perf.data file.
libtraceevent:
Tzvetomir Stoyanov:
- Simplify the tep_print_event_* APIs.
- Remove tep_register_trace_clock().
- Change users plugin directory.
Cleanups:
Arnaldo Carvalho de Melo:
- Continue taming the includes hell: remove needless include directives, fix
the fallout, rinse, repeat.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Pull x86 fixes from Thomas Gleixner:
"A set of fixes for x86:
- Fix the bogus detection of 32bit user mode for uretprobes which
caused corruption of the user return address resulting in
application crashes. In the uprobes handler in_ia32_syscall() is
obviously always returning false on a 64bit kernel. Use
user_64bit_mode() instead which works correctly.
- Prevent large page splitting when ftrace flips RW/RO on the kernel
text which caused iTLB performance issues. Ftrace wants to be
converted to text_poke() which avoids the problem, but for now
allow large page preservation in the static protections check when
the change request spawns a full large page.
- Prevent arch_dynirq_lower_bound() from returning 0 when the IOAPIC
is configured via device tree. In the device tree case the GSI 1:1
mapping is meaningless therefore the lower bound which protects the
GSI range on ACPI machines is irrelevant. Return the lower bound
which the core hands to the function instead of blindly returning 0
which causes the core to allocate the invalid virtual interupt
number 0 which in turn prevents all drivers from allocating and
requesting an interrupt.
- Remove the bogus initialization of LDR and DFR in the 32bit bigsmp
APIC driver. That uses physical destination mode where LDR/DFR are
ignored, but the initialization and the missing clear of LDR caused
the APIC to be left in a inconsistent state on kexec/reboot.
- Clear LDR when clearing the APIC registers so the APIC is in a well
defined state.
- Initialize variables proper in the find_trampoline_placement()
code.
- Silence GCC( build warning for the real mode part of the build"
* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/mm/cpa: Prevent large page split when ftrace flips RW on kernel text
x86/build: Add -Wnoaddress-of-packed-member to REALMODE_CFLAGS, to silence GCC9 build warning
x86/boot/compressed/64: Fix missing initialization in find_trampoline_placement()
x86/apic: Include the LDR when clearing out APIC registers
x86/apic: Do not initialize LDR and DFR for bigsmp
uprobes/x86: Fix detection of 32-bit user mode
x86/apic: Fix arch_dynirq_lower_bound() bug for DT enabled machines
Pull perf fixes from Thomas Gleixner:
"Two fixes for perf x86 hardware implementations:
- Restrict the period on Nehalem machines to prevent perf from
hogging the CPU
- Prevent the AMD IBS driver from overwriting the hardwre controlled
and pre-seeded reserved bits (0-6) in the count register which
caused a sample bias for dispatched micro-ops"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf/x86/amd/ibs: Fix sample bias for dispatched micro-ops
perf/x86/intel: Restrict period on Nehalem
Pull turbostat updates from Len Brown:
"User-space turbostat (and x86_energy_perf_policy) patches.
They are primarily bug fixes from users"
* 'turbostat' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux:
tools/power turbostat: update version number
tools/power turbostat: Add support for Hygon Fam 18h (Dhyana) RAPL
tools/power turbostat: Fix caller parameter of get_tdp_amd()
tools/power turbostat: Fix CPU%C1 display value
tools/power turbostat: do not enforce 1ms
tools/power turbostat: read from pipes too
tools/power turbostat: Add Ice Lake NNPI support
tools/power turbostat: rename has_hsw_msrs()
tools/power turbostat: Fix Haswell Core systems
tools/power turbostat: add Jacobsville support
tools/power turbostat: fix buffer overrun
tools/power turbostat: fix file descriptor leaks
tools/power turbostat: fix leak of file descriptor on error return path
tools/power turbostat: Make interval calculation per thread to reduce jitter
tools/power turbostat: remove duplicate pc10 column
tools/power x86_energy_perf_policy: Fix argument parsing
tools/power: Fix typo in man page
tools/power/x86: Enable compiler optimisations and Fortify by default
tools/power x86_energy_perf_policy: Fix "uninitialized variable" warnings at -O2
To allow using the -I trick that will be needed for checking the x86
insn decoder files.
Without the specific -I lines we still get the same warnings as before:
$ make -C tools/objtool/ clean ; make -C tools/objtool/
make: Entering directory '/home/acme/git/perf/tools/objtool'
CLEAN objtool
find -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
rm -f arch/x86/inat-tables.c fixdep
<SNIP>
LD objtool-in.o
make[1]: Leaving directory '/home/acme/git/perf/tools/objtool'
Warning: Kernel ABI header at 'tools/arch/x86/include/asm/inat.h' differs from latest version at 'arch/x86/include/asm/inat.h'
diff -u tools/arch/x86/include/asm/inat.h arch/x86/include/asm/inat.h
Warning: Kernel ABI header at 'tools/arch/x86/include/asm/insn.h' differs from latest version at 'arch/x86/include/asm/insn.h'
diff -u tools/arch/x86/include/asm/insn.h arch/x86/include/asm/insn.h
Warning: Kernel ABI header at 'tools/arch/x86/lib/inat.c' differs from latest version at 'arch/x86/lib/inat.c'
diff -u tools/arch/x86/lib/inat.c arch/x86/lib/inat.c
Warning: Kernel ABI header at 'tools/arch/x86/lib/insn.c' differs from latest version at 'arch/x86/lib/insn.c'
diff -u tools/arch/x86/lib/insn.c arch/x86/lib/insn.c
/home/acme/git/perf/tools/objtool
LINK objtool
make: Leaving directory '/home/acme/git/perf/tools/objtool'
$
The next patch will add the -I lines for those files.
Acked-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: http://lore.kernel.org/lkml/20190830193109.p7jagidsrahoa4pn@treble
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/n/tip-vu3p38mnxlwd80rlsnjkqcf2@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Now that there's a common version of the decoder for all tools, use it
instead of the local copy.
Also use perf's check-headers.sh script to diff the decoder files to
make sure they remain in sync with the kernel version. Objtool has a
similar check.
Committer notes:
Had to keep this all pointing explicitely to x86 headers/files, i.e.
instead of asm/isnn.h we had to use ../include/asm/insn.h when the files
were in differemt dirs, or just replace "<asm/foo.h>" with "foo.h".
This way we continue to be able to process perf.data files with Intel PT
traces in distros other than x86.
Also fixed up the awk script paths to use $(srcdir)/tools/arch instead
or relative directories so that we keep detached tarballs (make help |
grep perf) working.
For now the include lines in these headers are being ignored so as not
to flag false reports of kernel/tools out of sync.
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: x86@kernel.org
Link: http://lore.kernel.org/lkml/8a37e615d2880f039505d693d1e068a009358a2b.1567118001.git.jpoimboe@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Some uncore metrics don't work as expected. For example, on
cascadelakex:
root@lkp-csl-2sp2:~# perf stat -M UNC_M_PMM_BANDWIDTH.TOTAL -a -- sleep 1
Performance counter stats for 'system wide':
1841092 unc_m_pmm_rpq_inserts
3680816 unc_m_pmm_wpq_inserts
1.001775055 seconds time elapsed
root@lkp-csl-2sp2:~# perf stat -M UNC_M_PMM_READ_LATENCY -a -- sleep 1
Performance counter stats for 'system wide':
860649746 unc_m_pmm_rpq_occupancy.all
1840557 unc_m_pmm_rpq_inserts
12790627455 unc_m_clockticks
1.001773348 seconds time elapsed
No metrics 'UNC_M_PMM_BANDWIDTH.TOTAL' or 'UNC_M_PMM_READ_LATENCY' are
reported.
The issue is, the case of an alias expanding to mulitple events is not
supported, typically the uncore events. (see comments in
find_evsel_group()).
For UNC_M_PMM_BANDWIDTH.TOTAL in above example, the expanded event group
is '{unc_m_pmm_rpq_inserts,unc_m_pmm_wpq_inserts}:W', but the actual
events passed to find_evsel_group are:
unc_m_pmm_rpq_inserts
unc_m_pmm_rpq_inserts
unc_m_pmm_rpq_inserts
unc_m_pmm_rpq_inserts
unc_m_pmm_rpq_inserts
unc_m_pmm_rpq_inserts
unc_m_pmm_wpq_inserts
unc_m_pmm_wpq_inserts
unc_m_pmm_wpq_inserts
unc_m_pmm_wpq_inserts
unc_m_pmm_wpq_inserts
unc_m_pmm_wpq_inserts
For this multiple events case, it's not supported well.
This patch introduces a new field 'metric_leader' in struct evsel. The
first event is considered as a metric leader. For the rest of same
events, they point to the first event via it's metric_leader field in
struct evsel.
This design is for adding the counting results of all same events to the
first event in group (the metric_leader).
With this patch,
root@lkp-csl-2sp2:~# perf stat -M UNC_M_PMM_BANDWIDTH.TOTAL -a -- sleep 1
Performance counter stats for 'system wide':
1842108 unc_m_pmm_rpq_inserts # 337.2 MB/sec UNC_M_PMM_BANDWIDTH.TOTAL
3682209 unc_m_pmm_wpq_inserts
1.001819706 seconds time elapsed
root@lkp-csl-2sp2:~# perf stat -M UNC_M_PMM_READ_LATENCY -a -- sleep 1
Performance counter stats for 'system wide':
861970685 unc_m_pmm_rpq_occupancy.all # 219.4 ns UNC_M_PMM_READ_LATENCY
1842772 unc_m_pmm_rpq_inserts
12790196356 unc_m_clockticks
1.001749103 seconds time elapsed
Now we can see the correct metrics 'UNC_M_PMM_BANDWIDTH.TOTAL' and
'UNC_M_PMM_READ_LATENCY'.
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20190828055932.8269-5-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Some metrics define the scale unit, such as
{
"BriefDescription": "Intel Optane DC persistent memory read latency (ns). Derived from unc_m_pmm_rpq_occupancy.all",
"Counter": "0,1,2,3",
"EventCode": "0xE0",
"EventName": "UNC_M_PMM_READ_LATENCY",
"MetricExpr": "UNC_M_PMM_RPQ_OCCUPANCY.ALL / UNC_M_PMM_RPQ_INSERTS / UNC_M_CLOCKTICKS",
"MetricName": "UNC_M_PMM_READ_LATENCY",
"PerPkg": "1",
"ScaleUnit": "6000000000ns",
"UMask": "0x1",
"Unit": "iMC"
},
For above example, the ratio should be,
ratio = (UNC_M_PMM_RPQ_OCCUPANCY.ALL / UNC_M_PMM_RPQ_INSERTS / UNC_M_CLOCKTICKS) * 6000000000
But in current code, the ratio is not scaled ( * 6000000000)
With this patch, the ratio is scaled and the unit (ns) is printed.
For example,
# 219.4 ns UNC_M_PMM_READ_LATENCY
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20190828055932.8269-4-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
