2019-01-22 20:32:27 +08:00
|
|
|
/* SPDX-License-Identifier: GPL-2.0 */
|
|
|
|
|
#ifndef __PERF_SYMBOL_CONF
|
|
|
|
|
#define __PERF_SYMBOL_CONF 1
|
|
|
|
|
|
|
|
|
|
#include <stdbool.h>
|
|
|
|
|
|
|
|
|
|
struct strlist;
|
|
|
|
|
struct intlist;
|
|
|
|
|
|
|
|
|
|
struct symbol_conf {
|
2019-03-05 22:47:47 +08:00
|
|
|
bool nanosecs;
|
2019-01-22 20:32:27 +08:00
|
|
|
unsigned short priv_size;
|
|
|
|
|
bool try_vmlinux_path,
|
|
|
|
|
init_annotation,
|
|
|
|
|
force,
|
|
|
|
|
ignore_vmlinux,
|
|
|
|
|
ignore_vmlinux_buildid,
|
|
|
|
|
show_kernel_path,
|
|
|
|
|
use_modules,
|
|
|
|
|
allow_aliases,
|
|
|
|
|
sort_by_name,
|
|
|
|
|
show_nr_samples,
|
|
|
|
|
show_total_period,
|
|
|
|
|
use_callchain,
|
|
|
|
|
cumulate_callchain,
|
|
|
|
|
show_branchflag_count,
|
|
|
|
|
exclude_other,
|
|
|
|
|
show_cpu_utilization,
|
|
|
|
|
initialized,
|
|
|
|
|
kptr_restrict,
|
|
|
|
|
event_group,
|
|
|
|
|
demangle,
|
|
|
|
|
demangle_kernel,
|
|
|
|
|
filter_relative,
|
|
|
|
|
show_hist_headers,
|
|
|
|
|
branch_callstack,
|
|
|
|
|
has_filter,
|
|
|
|
|
show_ref_callgraph,
|
|
|
|
|
hide_unresolved,
|
|
|
|
|
raw_trace,
|
|
|
|
|
report_hierarchy,
|
2019-06-28 17:23:03 +08:00
|
|
|
report_block,
|
perf report: Sort by sampled cycles percent per block for stdio
It would be useful to support sorting for all blocks by the sampled
cycles percent per block. This is useful to concentrate on the globally
hottest blocks.
This patch implements a new option "--total-cycles" which sorts all
blocks by 'Sampled Cycles%'. The 'Sampled Cycles%' is the percent:
percent = block sampled cycles aggregation / total sampled cycles
Note that, this patch only supports "--stdio" mode.
For example,
# perf record -b ./div
# perf report --total-cycles --stdio
# To display the perf.data header info, please use --header/--header-only options.
#
# Total Lost Samples: 0
#
# Samples: 2M of event 'cycles'
# Event count (approx.): 2753248
#
# Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles [Program Block Range] Shared Object
# ............... .............. ........... .......... ................................................ .................
#
26.04% 2.8M 0.40% 18 [div.c:42 -> div.c:39] div
15.17% 1.2M 0.16% 7 [random_r.c:357 -> random_r.c:380] libc-2.27.so
5.11% 402.0K 0.04% 2 [div.c:27 -> div.c:28] div
4.87% 381.6K 0.04% 2 [random.c:288 -> random.c:291] libc-2.27.so
4.53% 381.0K 0.04% 2 [div.c:40 -> div.c:40] div
3.85% 300.9K 0.02% 1 [div.c:22 -> div.c:25] div
3.08% 241.1K 0.02% 1 [rand.c:26 -> rand.c:27] libc-2.27.so
3.06% 240.0K 0.02% 1 [random.c:291 -> random.c:291] libc-2.27.so
2.78% 215.7K 0.02% 1 [random.c:298 -> random.c:298] libc-2.27.so
2.52% 198.3K 0.02% 1 [random.c:293 -> random.c:293] libc-2.27.so
2.36% 184.8K 0.02% 1 [rand.c:28 -> rand.c:28] libc-2.27.so
2.33% 180.5K 0.02% 1 [random.c:295 -> random.c:295] libc-2.27.so
2.28% 176.7K 0.02% 1 [random.c:295 -> random.c:295] libc-2.27.so
2.20% 168.8K 0.02% 1 [rand@plt+0 -> rand@plt+0] div
1.98% 158.2K 0.02% 1 [random_r.c:388 -> random_r.c:388] libc-2.27.so
1.57% 123.3K 0.02% 1 [div.c:42 -> div.c:44] div
1.44% 116.0K 0.42% 19 [random_r.c:357 -> random_r.c:394] libc-2.27.so
0.25% 182.5K 0.02% 1 [random_r.c:388 -> random_r.c:391] libc-2.27.so
0.00% 48 1.07% 48 [x86_pmu_enable+284 -> x86_pmu_enable+298] [kernel.kallsyms]
0.00% 74 1.64% 74 [vm_mmap_pgoff+0 -> vm_mmap_pgoff+92] [kernel.kallsyms]
0.00% 73 1.62% 73 [vm_mmap+0 -> vm_mmap+48] [kernel.kallsyms]
0.00% 63 0.69% 31 [up_write+0 -> up_write+34] [kernel.kallsyms]
0.00% 13 0.29% 13 [setup_arg_pages+396 -> setup_arg_pages+413] [kernel.kallsyms]
0.00% 3 0.07% 3 [setup_arg_pages+418 -> setup_arg_pages+450] [kernel.kallsyms]
0.00% 616 6.84% 308 [security_mmap_file+0 -> security_mmap_file+72] [kernel.kallsyms]
0.00% 23 0.51% 23 [security_mmap_file+77 -> security_mmap_file+87] [kernel.kallsyms]
0.00% 4 0.02% 1 [sched_clock+0 -> sched_clock+4] [kernel.kallsyms]
0.00% 4 0.02% 1 [sched_clock+9 -> sched_clock+12] [kernel.kallsyms]
0.00% 1 0.02% 1 [rcu_nmi_exit+0 -> rcu_nmi_exit+9] [kernel.kallsyms]
Committer testing:
This should provide material for hours of endless joy, both from looking
for suspicious things in the implementation of this patch, such as the
top one:
# Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles [Program Block Range] Shared Object
2.17% 1.7M 0.08% 607 [compiler.h:199 -> common.c:221] [kernel.vmlinux]
As well from things that look legit:
# Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles [Program Block Range] Shared Object
0.16% 123.0K 0.60% 4.7K [nospec-branch.h:265 -> nospec-branch.h:278] [kernel.vmlinux]
:-)
Very short system wide taken branches session:
# perf record -h -b
Usage: perf record [<options>] [<command>]
or: perf record [<options>] -- <command> [<options>]
-b, --branch-any sample any taken branches
#
# perf record -b
^C[ perf record: Woken up 595 times to write data ]
[ perf record: Captured and wrote 156.672 MB perf.data (196873 samples) ]
#
# perf evlist -v
cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CPU|PERIOD|BRANCH_STACK, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, task: 1, precise_ip: 3, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, ksymbol: 1, bpf_event: 1, branch_sample_type: ANY
#
# perf report --total-cycles --stdio
# To display the perf.data header info, please use --header/--header-only options.
#
# Total Lost Samples: 0
#
# Samples: 6M of event 'cycles'
# Event count (approx.): 6299936
#
# Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles [Program Block Range] Shared Object
# ............... .............. ........... .......... ...................................................................... ....................
#
2.17% 1.7M 0.08% 607 [compiler.h:199 -> common.c:221] [kernel.vmlinux]
1.75% 1.3M 8.34% 65.5K [memset-vec-unaligned-erms.S:147 -> memset-vec-unaligned-erms.S:151] libc-2.29.so
0.72% 544.5K 0.03% 230 [entry_64.S:657 -> entry_64.S:662] [kernel.vmlinux]
0.56% 541.8K 0.09% 672 [compiler.h:199 -> common.c:300] [kernel.vmlinux]
0.39% 293.2K 0.01% 104 [list_debug.c:43 -> list_debug.c:61] [kernel.vmlinux]
0.36% 278.6K 0.03% 272 [entry_64.S:1289 -> entry_64.S:1308] [kernel.vmlinux]
0.30% 260.8K 0.07% 564 [clear_page_64.S:47 -> clear_page_64.S:50] [kernel.vmlinux]
0.28% 215.3K 0.05% 369 [traps.c:623 -> traps.c:628] [kernel.vmlinux]
0.23% 178.1K 0.04% 278 [entry_64.S:271 -> entry_64.S:275] [kernel.vmlinux]
0.20% 152.6K 0.09% 706 [paravirt.c:177 -> paravirt.c:179] [kernel.vmlinux]
0.20% 155.8K 0.05% 373 [entry_64.S:153 -> entry_64.S:175] [kernel.vmlinux]
0.18% 136.6K 0.03% 222 [msr.h:105 -> msr.h:166] [kernel.vmlinux]
0.16% 123.0K 0.60% 4.7K [nospec-branch.h:265 -> nospec-branch.h:278] [kernel.vmlinux]
0.16% 118.3K 0.01% 44 [entry_64.S:632 -> entry_64.S:657] [kernel.vmlinux]
0.14% 104.5K 0.00% 28 [rwsem.c:1541 -> rwsem.c:1544] [kernel.vmlinux]
0.13% 99.2K 0.01% 53 [spinlock.c:150 -> spinlock.c:152] [kernel.vmlinux]
0.13% 95.5K 0.00% 35 [swap.c:456 -> swap.c:471] [kernel.vmlinux]
0.12% 96.2K 0.05% 407 [copy_user_64.S:175 -> copy_user_64.S:209] [kernel.vmlinux]
0.11% 85.9K 0.00% 31 [swap.c:400 -> page-flags.h:188] [kernel.vmlinux]
0.10% 73.0K 0.01% 52 [paravirt.h:763 -> list.h:131] [kernel.vmlinux]
0.07% 56.2K 0.03% 214 [filemap.c:1524 -> filemap.c:1557] [kernel.vmlinux]
0.07% 54.2K 0.02% 145 [memory.c:1032 -> memory.c:1049] [kernel.vmlinux]
0.07% 50.3K 0.00% 39 [mmzone.c:49 -> mmzone.c:69] [kernel.vmlinux]
0.06% 48.3K 0.01% 40 [paravirt.h:768 -> page_alloc.c:3304] [kernel.vmlinux]
0.06% 46.7K 0.02% 155 [memory.c:1032 -> memory.c:1056] [kernel.vmlinux]
0.06% 46.9K 0.01% 103 [swap.c:867 -> swap.c:902] [kernel.vmlinux]
0.06% 47.8K 0.00% 34 [entry_64.S:1201 -> entry_64.S:1202] [kernel.vmlinux]
-----------------------------------------------------------
v7:
---
Use use_browser in report__browse_block_hists for supporting
stdio and potential tui mode.
v6:
---
Create report__browse_block_hists in block-info.c (codes are
moved from builtin-report.c). It's called from
perf_evlist__tty_browse_hists.
v5:
---
1. Move all block functions to block-info.c
2. Move the code of setting ms in block hist_entry to
other patch.
v4:
---
1. Use new option '--total-cycles' to replace
'-s total_cycles' in v3.
2. Move block info collection out of block info
printing.
v3:
---
1. Use common function block_info__process_sym to
process the blocks per symbol.
2. Remove the nasty hack for skipping calculation
of column length
3. Some minor cleanup
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20191107074719.26139-6-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-07 15:47:17 +08:00
|
|
|
report_individual_block,
|
2019-06-28 17:23:03 +08:00
|
|
|
inline_name,
|
2020-12-14 18:54:50 +08:00
|
|
|
disable_add2line_warn,
|
perf tools: Add guest_code support
A common case for KVM test programs is that the test program acts as the
hypervisor, creating, running and destroying the virtual machine, and
providing the guest object code from its own object code. In this case,
the VM is not running an OS, but only the functions loaded into it by the
hypervisor test program, and conveniently, loaded at the same virtual
addresses.
Normally to resolve addresses, MMAP events are needed to map addresses
back to the object code and debug symbols for that object code.
Currently, there is no way to get such mapping information from guests
but, in the scenario described above, the guest has the same mappings
as the hypervisor, so support for that scenario can be achieved.
To support that, copy the host thread's maps to the guest thread's maps.
Note, we do not discover the guest until we encounter a guest event,
which works well because it is not until then that we know that the host
thread's maps have been set up.
Typically the main function for the guest object code is called
"guest_code", hence the name chosen for this feature. Note, that is just a
convention, the function could be named anything, and the tools do not
care.
This is primarily aimed at supporting Intel PT, or similar, where trace
data can be recorded for a guest. Refer to the final patch in this series
"perf intel-pt: Add guest_code support" for an example.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: kvm@vger.kernel.org
Link: https://lore.kernel.org/r/20220517131011.6117-4-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-05-17 21:10:08 +08:00
|
|
|
buildid_mmap2,
|
|
|
|
|
guest_code;
|
2019-01-22 20:32:27 +08:00
|
|
|
const char *vmlinux_name,
|
|
|
|
|
*kallsyms_name,
|
|
|
|
|
*source_prefix,
|
|
|
|
|
*field_sep,
|
|
|
|
|
*graph_function;
|
|
|
|
|
const char *default_guest_vmlinux_name,
|
|
|
|
|
*default_guest_kallsyms,
|
|
|
|
|
*default_guest_modules;
|
|
|
|
|
const char *guestmount;
|
|
|
|
|
const char *dso_list_str,
|
|
|
|
|
*comm_list_str,
|
|
|
|
|
*pid_list_str,
|
|
|
|
|
*tid_list_str,
|
|
|
|
|
*sym_list_str,
|
|
|
|
|
*col_width_list_str,
|
|
|
|
|
*bt_stop_list_str;
|
2019-03-05 22:47:48 +08:00
|
|
|
unsigned long time_quantum;
|
2019-01-22 20:32:27 +08:00
|
|
|
struct strlist *dso_list,
|
|
|
|
|
*comm_list,
|
|
|
|
|
*sym_list,
|
|
|
|
|
*dso_from_list,
|
|
|
|
|
*dso_to_list,
|
|
|
|
|
*sym_from_list,
|
|
|
|
|
*sym_to_list,
|
|
|
|
|
*bt_stop_list;
|
|
|
|
|
struct intlist *pid_list,
|
2021-02-07 16:09:35 +08:00
|
|
|
*tid_list,
|
|
|
|
|
*addr_list;
|
2019-01-22 20:32:27 +08:00
|
|
|
const char *symfs;
|
2019-03-11 22:44:58 +08:00
|
|
|
int res_sample;
|
2019-05-08 21:20:05 +08:00
|
|
|
int pad_output_len_dso;
|
perf report: Allow specifying event to be used as sort key in --group output
When performing "perf report --group", it shows the event group
information together. By default, the output is sorted by the first
event in group.
It would be nice for user to select any event for sorting. This patch
introduces a new option "--group-sort-idx" to sort the output by the
event at the index n in event group.
For example,
Before:
# perf report --group --stdio
# To display the perf.data header info, please use --header/--header-only options.
#
#
# Total Lost Samples: 0
#
# Samples: 12K of events 'cpu/instructions,period=2000003/, cpu/cpu-cycles,period=200003/, BR_MISP_RETIRED.ALL_BRANCHES:pp, cpu/event=0xc0,umask=1,cmask=1,
# Event count (approx.): 6451235635
#
# Overhead Command Shared Object Symbol
# ................................ ......... ....................... ...................................
#
92.19% 98.68% 0.00% 93.30% mgen mgen [.] LOOP1
3.12% 0.29% 0.00% 0.16% gsd-color libglib-2.0.so.0.5600.4 [.] 0x0000000000049515
1.56% 0.03% 0.00% 0.04% gsd-color libglib-2.0.so.0.5600.4 [.] 0x00000000000494b7
1.56% 0.01% 0.00% 0.00% gsd-color libglib-2.0.so.0.5600.4 [.] 0x00000000000494ce
1.56% 0.00% 0.00% 0.00% mgen [kernel.kallsyms] [k] task_tick_fair
0.00% 0.15% 0.00% 0.04% perf [kernel.kallsyms] [k] smp_call_function_single
0.00% 0.13% 0.00% 6.08% swapper [kernel.kallsyms] [k] intel_idle
0.00% 0.03% 0.00% 0.00% gsd-color libglib-2.0.so.0.5600.4 [.] g_main_context_check
0.00% 0.03% 0.00% 0.00% swapper [kernel.kallsyms] [k] apic_timer_interrupt
...
After:
# perf report --group --stdio --group-sort-idx 3
# To display the perf.data header info, please use --header/--header-only options.
#
#
# Total Lost Samples: 0
#
# Samples: 12K of events 'cpu/instructions,period=2000003/, cpu/cpu-cycles,period=200003/, BR_MISP_RETIRED.ALL_BRANCHES:pp, cpu/event=0xc0,umask=1,cmask=1,
# Event count (approx.): 6451235635
#
# Overhead Command Shared Object Symbol
# ................................ ......... ....................... ...................................
#
92.19% 98.68% 0.00% 93.30% mgen mgen [.] LOOP1
0.00% 0.13% 0.00% 6.08% swapper [kernel.kallsyms] [k] intel_idle
3.12% 0.29% 0.00% 0.16% gsd-color libglib-2.0.so.0.5600.4 [.] 0x0000000000049515
0.00% 0.00% 0.00% 0.06% swapper [kernel.kallsyms] [k] hrtimer_start_range_ns
1.56% 0.03% 0.00% 0.04% gsd-color libglib-2.0.so.0.5600.4 [.] 0x00000000000494b7
0.00% 0.15% 0.00% 0.04% perf [kernel.kallsyms] [k] smp_call_function_single
0.00% 0.00% 0.00% 0.02% mgen [kernel.kallsyms] [k] update_curr
0.00% 0.00% 0.00% 0.02% mgen [kernel.kallsyms] [k] apic_timer_interrupt
0.00% 0.00% 0.00% 0.02% mgen [kernel.kallsyms] [k] native_apic_msr_eoi_write
0.00% 0.00% 0.00% 0.02% mgen [kernel.kallsyms] [k] __update_load_avg_se
0.00% 0.00% 0.00% 0.02% mgen [kernel.kallsyms] [k] scheduler_tick
Now the output is sorted by the fourth event in group.
v7:
---
Rebase to latest perf/core, no other change.
v4:
---
1. Update Documentation/perf-report.txt to mention
'--group-sort-idx' support multiple groups with different
amount of events and it should be used on grouped events.
2. Update __hpp__group_sort_idx(), just return when the
idx is out of limit.
3. Return failure on symbol_conf.group_sort_idx && !session->evlist->nr_groups.
So now we don't need to use together with --group.
v3:
---
Refine the code in __hpp__group_sort_idx().
Before:
for (i = 1; i < nr_members; i++) {
if (i == idx) {
ret = field_cmp(fields_a[i], fields_b[i]);
if (ret)
goto out;
}
}
After:
if (idx >= 1 && idx < nr_members) {
ret = field_cmp(fields_a[idx], fields_b[idx]);
if (ret)
goto out;
}
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20200220013616.19916-2-yao.jin@linux.intel.com
[ Renamed pair_fields_alloc() to hist_entry__new_pair() and combined decl + assignment of vars ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-02-20 09:36:14 +08:00
|
|
|
int group_sort_idx;
|
2021-02-07 16:09:35 +08:00
|
|
|
int addr_range;
|
2019-01-22 20:32:27 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
extern struct symbol_conf symbol_conf;
|
|
|
|
|
|
|
|
|
|
#endif // __PERF_SYMBOL_CONF
|
