2019-02-13 13:32:39 +01:00
|
|
|
perf-y += header.o
|
|
|
|
|
perf-y += tsc.o
|
|
|
|
|
perf-y += pmu.o
|
|
|
|
|
perf-y += kvm-stat.o
|
|
|
|
|
perf-y += perf_regs.o
|
2020-09-11 07:48:05 -07:00
|
|
|
perf-y += topdown.o
|
2019-02-13 13:32:39 +01:00
|
|
|
perf-y += machine.o
|
|
|
|
|
perf-y += event.o
|
perf stat: Add Topdown metrics events as default events
The Topdown Microarchitecture Analysis (TMA) Method is a structured
analysis methodology to identify critical performance bottlenecks in
out-of-order processors. From the Ice Lake and later platforms, the
Topdown information can be retrieved from the dedicated "metrics"
register, which isn't impacted by other events. Also, the Topdown
metrics support both per thread/process and per core measuring. Adding
Topdown metrics events as default events can enrich the default
measuring information, and would not cost any extra multiplexing.
Introduce arch_evlist__add_default_attrs() to allow architecture
specific default events. Add the Topdown metrics events in the X86
specific arch_evlist__add_default_attrs(). Other architectures can add
their own default events later separately.
With the patch:
$ perf stat sleep 1
Performance counter stats for 'sleep 1':
0.82 msec task-clock:u # 0.001 CPUs utilized
0 context-switches:u # 0.000 K/sec
0 cpu-migrations:u # 0.000 K/sec
61 page-faults:u # 0.074 M/sec
319,941 cycles:u # 0.388 GHz
242,802 instructions:u # 0.76 insn per cycle
54,380 branches:u # 66.028 M/sec
4,043 branch-misses:u # 7.43% of all branches
1,585,555 slots:u # 1925.189 M/sec
238,941 topdown-retiring:u # 15.0% retiring
410,378 topdown-bad-spec:u # 25.8% bad speculation
634,222 topdown-fe-bound:u # 39.9% frontend bound
304,675 topdown-be-bound:u # 19.2% backend bound
1.001791625 seconds time elapsed
0.000000000 seconds user
0.001572000 seconds sys
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lore.kernel.org/lkml/20210121133752.118327-1-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2021-01-21 05:37:52 -08:00
|
|
|
perf-y += evlist.o
|
2014-12-30 14:03:40 +01:00
|
|
|
|
2019-02-13 13:32:39 +01:00
|
|
|
perf-$(CONFIG_DWARF) += dwarf-regs.o
|
|
|
|
|
perf-$(CONFIG_BPF_PROLOGUE) += dwarf-regs.o
|
2014-12-30 14:03:40 +01:00
|
|
|
|
2019-02-13 13:32:39 +01:00
|
|
|
perf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o
|
|
|
|
|
perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
|
2015-07-17 19:33:41 +03:00
|
|
|
|
2019-02-13 13:32:39 +01:00
|
|
|
perf-$(CONFIG_AUXTRACE) += auxtrace.o
|
perf script: Support insn output for normal samples
perf script -F +insn was only working for PT traces because the PT
instruction decoder was filling in the insn/insn_len sample attributes.
Support it for non PT samples too on x86 using the existing x86
instruction decoder.
This adds some extra checking to ensure that we don't try to decode
instructions when using perf.data from a different architecture.
% perf record -a sleep 1
% perf script -F ip,sym,insn --xed
ffffffff811704c9 remote_function movl %eax, 0x18(%rbx)
ffffffff8100bb50 intel_bts_enable_local retq
ffffffff81048612 native_apic_mem_write movl %esi, -0xa04000(%rdi)
ffffffff81048612 native_apic_mem_write movl %esi, -0xa04000(%rdi)
ffffffff81048612 native_apic_mem_write movl %esi, -0xa04000(%rdi)
ffffffff810f1f79 generic_exec_single xor %eax, %eax
ffffffff811704c9 remote_function movl %eax, 0x18(%rbx)
ffffffff8100bb34 intel_bts_enable_local movl 0x2000(%rax), %edx
ffffffff81048610 native_apic_mem_write mov %edi, %edi
...
Committer testing:
Before:
# perf script -F ip,sym,insn --xed | head -5
ffffffffa4068804 native_write_msr addb %al, (%rax)
ffffffffa4068804 native_write_msr addb %al, (%rax)
ffffffffa4068804 native_write_msr addb %al, (%rax)
ffffffffa4068806 native_write_msr addb %al, (%rax)
ffffffffa4068806 native_write_msr addb %al, (%rax)
# perf script -F ip,sym,insn --xed | grep -v "addb %al, (%rax)"
#
After:
# perf script -F ip,sym,insn --xed | head -5
ffffffffa4068804 native_write_msr wrmsr
ffffffffa4068804 native_write_msr wrmsr
ffffffffa4068804 native_write_msr wrmsr
ffffffffa4068806 native_write_msr nopl %eax, (%rax,%rax,1)
ffffffffa4068806 native_write_msr nopl %eax, (%rax,%rax,1)
# perf script -F ip,sym,insn --xed | grep -v "addb %al, (%rax)" | head -5
ffffffffa4068804 native_write_msr wrmsr
ffffffffa4068804 native_write_msr wrmsr
ffffffffa4068804 native_write_msr wrmsr
ffffffffa4068806 native_write_msr nopl %eax, (%rax,%rax,1)
ffffffffa4068806 native_write_msr nopl %eax, (%rax,%rax,1)
#
More examples:
# perf script -F ip,sym,insn --xed | grep -v native_write_msr | head
ffffffffa416b90e tick_check_broadcast_expired btq %rax, 0x1a5f42a(%rip)
ffffffffa4956bd0 nmi_cpu_backtrace pushq %r13
ffffffffa415b95e __hrtimer_next_event_base movq 0x18(%rax), %rdx
ffffffffa4956bf3 nmi_cpu_backtrace popq %r12
ffffffffa4171d5c smp_call_function_single pause
ffffffffa4956bdd nmi_cpu_backtrace mov %ebp, %r12d
ffffffffa4797e4d menu_select cmp $0x190, %rax
ffffffffa4171d5c smp_call_function_single pause
ffffffffa405a7d8 nmi_cpu_backtrace_handler callq 0xffffffffa4956bd0
ffffffffa4797f7a menu_select shr $0x3, %rax
#
Which matches the annotate output modulo resolving callqs:
# perf annotate --stdio2 nmi_cpu_backtrace_handler
Samples: 4 of event 'cycles:ppp', 4000 Hz, Event count (approx.): 35908, [percent: local period]
nmi_cpu_backtrace_handler() /lib/modules/5.0.0+/build/vmlinux
Percent
Disassembly of section .text:
ffffffff8105a7d0 <nmi_cpu_backtrace_handler>:
nmi_cpu_backtrace_handler():
nmi_trigger_cpumask_backtrace(mask, exclude_self,
nmi_raise_cpu_backtrace);
}
static int nmi_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs)
{
24.45 → callq __fentry__
if (nmi_cpu_backtrace(regs))
mov %rsi,%rdi
75.55 → callq nmi_cpu_backtrace
return NMI_HANDLED;
movzbl %al,%eax
return NMI_DONE;
}
← retq
#
# perf annotate --stdio2 __hrtimer_next_event_base
Samples: 4 of event 'cycles:ppp', 4000 Hz, Event count (approx.): 767977, [percent: local period]
__hrtimer_next_event_base() /lib/modules/5.0.0+/build/vmlinux
Percent
Disassembly of section .text:
ffffffff8115b910 <__hrtimer_next_event_base>:
__hrtimer_next_event_base():
static ktime_t __hrtimer_next_event_base(struct hrtimer_cpu_base *cpu_base,
const struct hrtimer *exclude,
unsigned int active,
ktime_t expires_next)
{
→ callq __fentry__
<SNIP>
4a: add $0x1,%r14
77.31 mov 0x18(%rax),%rdx
shl $0x6,%r14
sub 0x38(%rbx,%r14,1),%rdx
if (expires < expires_next) {
cmp %r12,%rdx
↓ jge 68
<SNIP>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/20190305144758.12397-3-andi@firstfloor.org
[ Converted fetch_exe() to use the name it ended up having when merged: thread__memcpy() ]
[ archinsn.c needs the instruction decoder that is only build when CONFIG_AUXTRACE=y, fix that ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-03-05 06:47:45 -08:00
|
|
|
perf-$(CONFIG_AUXTRACE) += archinsn.o
|
2019-02-13 13:32:39 +01:00
|
|
|
perf-$(CONFIG_AUXTRACE) += intel-pt.o
|
|
|
|
|
perf-$(CONFIG_AUXTRACE) += intel-bts.o
|