2019-05-29 07:12:25 -07:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-04-18 10:46:11 -03:00
|
|
|
|
2017-04-17 15:23:08 -03:00
|
|
|
|
2019-01-22 11:14:55 -02:00
|
|
|
|
2019-08-30 14:45:20 -03:00
|
|
|
|
2019-09-03 10:56:06 -03:00
|
|
|
|
2014-02-20 10:32:53 +09:00
|
|
|
|
|
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
|
|
|
|
|
2018-03-16 14:33:38 -03:00
|
|
|
|
2024-03-29 14:58:10 -07:00
|
|
|
|
2019-08-30 09:43:25 -03:00
|
|
|
|
2019-08-30 14:45:20 -03:00
|
|
|
|
2019-01-27 13:42:37 +01:00
|
|
|
|
2019-11-25 22:24:10 -03:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
2019-08-22 17:10:08 -03:00
|
|
|
|
2018-04-03 15:19:47 -03:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
2024-08-05 16:46:48 -07:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
2023-12-12 16:13:13 -08:00
|
|
|
|
2013-03-05 14:53:21 +09:00
|
|
|
|
2018-05-24 17:20:53 -03:00
|
|
|
|
perf annotate: Enable annotation of BPF programs
In symbol__disassemble(), DSO_BINARY_TYPE__BPF_PROG_INFO dso calls into
a new function symbol__disassemble_bpf(), where annotation line
information is filled based on the bpf_prog_info and btf data saved in
given perf_env.
symbol__disassemble_bpf() uses binutils's libopcodes to disassemble bpf
programs.
Committer testing:
After fixing this:
- u64 *addrs = (u64 *)(info_linear->info.jited_ksyms);
+ u64 *addrs = (u64 *)(uintptr_t)(info_linear->info.jited_ksyms);
Detected when crossbuilding to a 32-bit arch.
And making all this dependent on HAVE_LIBBFD_SUPPORT and
HAVE_LIBBPF_SUPPORT:
1) Have a BPF program running, one that has BTF info, etc, I used
the tools/perf/examples/bpf/augmented_raw_syscalls.c put in place
by 'perf trace'.
# grep -B1 augmented_raw ~/.perfconfig
[trace]
add_events = /home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.c
#
# perf trace -e *mmsg
dnf/6245 sendmmsg(20, 0x7f5485a88030, 2, MSG_NOSIGNAL) = 2
NetworkManager/10055 sendmmsg(22<socket:[1056822]>, 0x7f8126ad1bb0, 2, MSG_NOSIGNAL) = 2
2) Then do a 'perf record' system wide for a while:
# perf record -a
^C[ perf record: Woken up 68 times to write data ]
[ perf record: Captured and wrote 19.427 MB perf.data (366891 samples) ]
#
3) Check that we captured BPF and BTF info in the perf.data file:
# perf report --header-only | grep 'b[pt]f'
# event : name = cycles:ppp, , id = { 294789, 294790, 294791, 294792, 294793, 294794, 294795, 294796 }, size = 112, { sample_period, sample_freq } = 4000, sample_type = IP|TID|TIME|CPU|PERIOD, 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
# bpf_prog_info of id 13
# bpf_prog_info of id 14
# bpf_prog_info of id 15
# bpf_prog_info of id 16
# bpf_prog_info of id 17
# bpf_prog_info of id 18
# bpf_prog_info of id 21
# bpf_prog_info of id 22
# bpf_prog_info of id 41
# bpf_prog_info of id 42
# btf info of id 2
#
4) Check which programs got recorded:
# perf report | grep bpf_prog | head
0.16% exe bpf_prog_819967866022f1e1_sys_enter [k] bpf_prog_819967866022f1e1_sys_enter
0.14% exe bpf_prog_c1bd85c092d6e4aa_sys_exit [k] bpf_prog_c1bd85c092d6e4aa_sys_exit
0.08% fuse-overlayfs bpf_prog_819967866022f1e1_sys_enter [k] bpf_prog_819967866022f1e1_sys_enter
0.07% fuse-overlayfs bpf_prog_c1bd85c092d6e4aa_sys_exit [k] bpf_prog_c1bd85c092d6e4aa_sys_exit
0.01% clang-4.0 bpf_prog_c1bd85c092d6e4aa_sys_exit [k] bpf_prog_c1bd85c092d6e4aa_sys_exit
0.01% clang-4.0 bpf_prog_819967866022f1e1_sys_enter [k] bpf_prog_819967866022f1e1_sys_enter
0.00% clang bpf_prog_c1bd85c092d6e4aa_sys_exit [k] bpf_prog_c1bd85c092d6e4aa_sys_exit
0.00% runc bpf_prog_819967866022f1e1_sys_enter [k] bpf_prog_819967866022f1e1_sys_enter
0.00% clang bpf_prog_819967866022f1e1_sys_enter [k] bpf_prog_819967866022f1e1_sys_enter
0.00% sh bpf_prog_c1bd85c092d6e4aa_sys_exit [k] bpf_prog_c1bd85c092d6e4aa_sys_exit
#
This was with the default --sort order for 'perf report', which is:
--sort comm,dso,symbol
If we just look for the symbol, for instance:
# perf report --sort symbol | grep bpf_prog | head
0.26% [k] bpf_prog_819967866022f1e1_sys_enter - -
0.24% [k] bpf_prog_c1bd85c092d6e4aa_sys_exit - -
#
or the DSO:
# perf report --sort dso | grep bpf_prog | head
0.26% bpf_prog_819967866022f1e1_sys_enter
0.24% bpf_prog_c1bd85c092d6e4aa_sys_exit
#
We'll see the two BPF programs that augmented_raw_syscalls.o puts in
place, one attached to the raw_syscalls:sys_enter and another to the
raw_syscalls:sys_exit tracepoints, as expected.
Now we can finally do, from the command line, annotation for one of
those two symbols, with the original BPF program source coude intermixed
with the disassembled JITed code:
# perf annotate --stdio2 bpf_prog_819967866022f1e1_sys_enter
Samples: 950 of event 'cycles:ppp', 4000 Hz, Event count (approx.): 553756947, [percent: local period]
bpf_prog_819967866022f1e1_sys_enter() bpf_prog_819967866022f1e1_sys_enter
Percent int sys_enter(struct syscall_enter_args *args)
53.41 push %rbp
0.63 mov %rsp,%rbp
0.31 sub $0x170,%rsp
1.93 sub $0x28,%rbp
7.02 mov %rbx,0x0(%rbp)
3.20 mov %r13,0x8(%rbp)
1.07 mov %r14,0x10(%rbp)
0.61 mov %r15,0x18(%rbp)
0.11 xor %eax,%eax
1.29 mov %rax,0x20(%rbp)
0.11 mov %rdi,%rbx
return bpf_get_current_pid_tgid();
2.02 → callq *ffffffffda6776d9
2.76 mov %eax,-0x148(%rbp)
mov %rbp,%rsi
int sys_enter(struct syscall_enter_args *args)
add $0xfffffffffffffeb8,%rsi
return bpf_map_lookup_elem(pids, &pid) != NULL;
movabs $0xffff975ac2607800,%rdi
1.26 → callq *ffffffffda6789e9
cmp $0x0,%rax
2.43 → je 0
add $0x38,%rax
0.21 xor %r13d,%r13d
if (pid_filter__has(&pids_filtered, getpid()))
0.81 cmp $0x0,%rax
→ jne 0
mov %rbp,%rdi
probe_read(&augmented_args.args, sizeof(augmented_args.args), args);
2.22 add $0xfffffffffffffeb8,%rdi
0.11 mov $0x40,%esi
0.32 mov %rbx,%rdx
2.74 → callq *ffffffffda658409
syscall = bpf_map_lookup_elem(&syscalls, &augmented_args.args.syscall_nr);
0.22 mov %rbp,%rsi
1.69 add $0xfffffffffffffec0,%rsi
syscall = bpf_map_lookup_elem(&syscalls, &augmented_args.args.syscall_nr);
movabs $0xffff975bfcd36000,%rdi
add $0xd0,%rdi
0.21 mov 0x0(%rsi),%eax
0.93 cmp $0x200,%rax
→ jae 0
0.10 shl $0x3,%rax
0.11 add %rdi,%rax
0.11 → jmp 0
xor %eax,%eax
if (syscall == NULL || !syscall->enabled)
1.07 cmp $0x0,%rax
→ je 0
if (syscall == NULL || !syscall->enabled)
6.57 movzbq 0x0(%rax),%rdi
if (syscall == NULL || !syscall->enabled)
cmp $0x0,%rdi
0.95 → je 0
mov $0x40,%r8d
switch (augmented_args.args.syscall_nr) {
mov -0x140(%rbp),%rdi
switch (augmented_args.args.syscall_nr) {
cmp $0x2,%rdi
→ je 0
cmp $0x101,%rdi
→ je 0
cmp $0x15,%rdi
→ jne 0
case SYS_OPEN: filename_arg = (const void *)args->args[0];
mov 0x10(%rbx),%rdx
→ jmp 0
case SYS_OPENAT: filename_arg = (const void *)args->args[1];
mov 0x18(%rbx),%rdx
if (filename_arg != NULL) {
cmp $0x0,%rdx
→ je 0
xor %edi,%edi
augmented_args.filename.reserved = 0;
mov %edi,-0x104(%rbp)
augmented_args.filename.size = probe_read_str(&augmented_args.filename.value,
mov %rbp,%rdi
add $0xffffffffffffff00,%rdi
augmented_args.filename.size = probe_read_str(&augmented_args.filename.value,
mov $0x100,%esi
→ callq *ffffffffda658499
mov $0x148,%r8d
augmented_args.filename.size = probe_read_str(&augmented_args.filename.value,
mov %eax,-0x108(%rbp)
augmented_args.filename.size = probe_read_str(&augmented_args.filename.value,
mov %rax,%rdi
shl $0x20,%rdi
shr $0x20,%rdi
if (augmented_args.filename.size < sizeof(augmented_args.filename.value)) {
cmp $0xff,%rdi
→ ja 0
len -= sizeof(augmented_args.filename.value) - augmented_args.filename.size;
add $0x48,%rax
len &= sizeof(augmented_args.filename.value) - 1;
and $0xff,%rax
mov %rax,%r8
mov %rbp,%rcx
return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, &augmented_args, len);
add $0xfffffffffffffeb8,%rcx
mov %rbx,%rdi
movabs $0xffff975fbd72d800,%rsi
mov $0xffffffff,%edx
→ callq *ffffffffda658ad9
mov %rax,%r13
}
mov %r13,%rax
0.72 mov 0x0(%rbp),%rbx
mov 0x8(%rbp),%r13
1.16 mov 0x10(%rbp),%r14
0.10 mov 0x18(%rbp),%r15
0.42 add $0x28,%rbp
0.54 leaveq
0.54 ← retq
#
Please see 'man perf-config' to see how to control what should be seen,
via ~/.perfconfig [annotate] section, for instance, one can suppress the
source code and see just the disassembly, etc.
Alternatively, use the TUI bu just using 'perf annotate', press
'/bpf_prog' to see the bpf symbols, press enter and do the interactive
annotation, which allows for dumping to a file after selecting the
the various output tunables, for instance, the above without source code
intermixed, plus showing all the instruction offsets:
# perf annotate bpf_prog_819967866022f1e1_sys_enter
Then press: 's' to hide the source code + 'O' twice to show all
instruction offsets, then 'P' to print to the
bpf_prog_819967866022f1e1_sys_enter.annotation file, which will have:
# cat bpf_prog_819967866022f1e1_sys_enter.annotation
bpf_prog_819967866022f1e1_sys_enter() bpf_prog_819967866022f1e1_sys_enter
Event: cycles:ppp
53.41 0: push %rbp
0.63 1: mov %rsp,%rbp
0.31 4: sub $0x170,%rsp
1.93 b: sub $0x28,%rbp
7.02 f: mov %rbx,0x0(%rbp)
3.20 13: mov %r13,0x8(%rbp)
1.07 17: mov %r14,0x10(%rbp)
0.61 1b: mov %r15,0x18(%rbp)
0.11 1f: xor %eax,%eax
1.29 21: mov %rax,0x20(%rbp)
0.11 25: mov %rdi,%rbx
2.02 28: → callq *ffffffffda6776d9
2.76 2d: mov %eax,-0x148(%rbp)
33: mov %rbp,%rsi
36: add $0xfffffffffffffeb8,%rsi
3d: movabs $0xffff975ac2607800,%rdi
1.26 47: → callq *ffffffffda6789e9
4c: cmp $0x0,%rax
2.43 50: → je 0
52: add $0x38,%rax
0.21 56: xor %r13d,%r13d
0.81 59: cmp $0x0,%rax
5d: → jne 0
63: mov %rbp,%rdi
2.22 66: add $0xfffffffffffffeb8,%rdi
0.11 6d: mov $0x40,%esi
0.32 72: mov %rbx,%rdx
2.74 75: → callq *ffffffffda658409
0.22 7a: mov %rbp,%rsi
1.69 7d: add $0xfffffffffffffec0,%rsi
84: movabs $0xffff975bfcd36000,%rdi
8e: add $0xd0,%rdi
0.21 95: mov 0x0(%rsi),%eax
0.93 98: cmp $0x200,%rax
9f: → jae 0
0.10 a1: shl $0x3,%rax
0.11 a5: add %rdi,%rax
0.11 a8: → jmp 0
aa: xor %eax,%eax
1.07 ac: cmp $0x0,%rax
b0: → je 0
6.57 b6: movzbq 0x0(%rax),%rdi
bb: cmp $0x0,%rdi
0.95 bf: → je 0
c5: mov $0x40,%r8d
cb: mov -0x140(%rbp),%rdi
d2: cmp $0x2,%rdi
d6: → je 0
d8: cmp $0x101,%rdi
df: → je 0
e1: cmp $0x15,%rdi
e5: → jne 0
e7: mov 0x10(%rbx),%rdx
eb: → jmp 0
ed: mov 0x18(%rbx),%rdx
f1: cmp $0x0,%rdx
f5: → je 0
f7: xor %edi,%edi
f9: mov %edi,-0x104(%rbp)
ff: mov %rbp,%rdi
102: add $0xffffffffffffff00,%rdi
109: mov $0x100,%esi
10e: → callq *ffffffffda658499
113: mov $0x148,%r8d
119: mov %eax,-0x108(%rbp)
11f: mov %rax,%rdi
122: shl $0x20,%rdi
126: shr $0x20,%rdi
12a: cmp $0xff,%rdi
131: → ja 0
133: add $0x48,%rax
137: and $0xff,%rax
13d: mov %rax,%r8
140: mov %rbp,%rcx
143: add $0xfffffffffffffeb8,%rcx
14a: mov %rbx,%rdi
14d: movabs $0xffff975fbd72d800,%rsi
157: mov $0xffffffff,%edx
15c: → callq *ffffffffda658ad9
161: mov %rax,%r13
164: mov %r13,%rax
0.72 167: mov 0x0(%rbp),%rbx
16b: mov 0x8(%rbp),%r13
1.16 16f: mov 0x10(%rbp),%r14
0.10 173: mov 0x18(%rbp),%r15
0.42 177: add $0x28,%rbp
0.54 17b: leaveq
0.54 17c: ← retq
Another cool way to test all this is to symple use 'perf top' look for
those symbols, go there and press enter, annotate it live :-)
Signed-off-by: Song Liu <songliubraving@fb.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stanislav Fomichev <sdf@google.com>
Link: http://lkml.kernel.org/r/20190312053051.2690567-13-songliubraving@fb.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-03-11 22:30:48 -07:00
|
|
|
|
2021-10-11 01:20:30 -07:00
|
|
|
|
perf annotate: Add branch stack / basic block
I wanted to know the hottest path through a function and figured the
branch-stack (LBR) information should be able to help out with that.
The below uses the branch-stack to create basic blocks and generate
statistics from them.
from to branch_i
* ----> *
|
| block
v
* ----> *
from to branch_i+1
The blocks are broken down into non-overlapping ranges, while tracking
if the start of each range is an entry point and/or the end of a range
is a branch.
Each block iterates all ranges it covers (while splitting where required
to exactly match the block) and increments the 'coverage' count.
For the range including the branch we increment the taken counter, as
well as the pred counter if flags.predicted.
Using these number we can find if an instruction:
- had coverage; given by:
br->coverage / br->sym->max_coverage
This metric ensures each symbol has a 100% spot, which reflects the
observation that each symbol must have a most covered/hottest
block.
- is a branch target: br->is_target && br->start == add
- for targets, how much of a branch's coverages comes from it:
target->entry / branch->coverage
- is a branch: br->is_branch && br->end == addr
- for branches, how often it was taken:
br->taken / br->coverage
after all, all execution that didn't take the branch would have
incremented the coverage and continued onward to a later branch.
- for branches, how often it was predicted:
br->pred / br->taken
The coverage percentage is used to color the address and asm sections;
for low (<1%) coverage we use NORMAL (uncolored), indicating that these
instructions are not 'important'. For high coverage (>75%) we color the
address RED.
For each branch, we add an asm comment after the instruction with
information on how often it was taken and predicted.
Output looks like (sans color, which does loose a lot of the
information :/)
$ perf record --branch-filter u,any -e cycles:p ./branches 27
$ perf annotate branches
Percent | Source code & Disassembly of branches for cycles:pu (217 samples)
---------------------------------------------------------------------------------
: branches():
0.00 : 40057a: push %rbp
0.00 : 40057b: mov %rsp,%rbp
0.00 : 40057e: sub $0x20,%rsp
0.00 : 400582: mov %rdi,-0x18(%rbp)
0.00 : 400586: mov %rsi,-0x20(%rbp)
0.00 : 40058a: mov -0x18(%rbp),%rax
0.00 : 40058e: mov %rax,-0x10(%rbp)
0.00 : 400592: movq $0x0,-0x8(%rbp)
0.00 : 40059a: jmpq 400656 <branches+0xdc>
1.84 : 40059f: mov -0x10(%rbp),%rax # +100.00%
3.23 : 4005a3: and $0x1,%eax
1.84 : 4005a6: test %rax,%rax
0.00 : 4005a9: je 4005bf <branches+0x45> # -54.50% (p:42.00%)
0.46 : 4005ab: mov 0x200bbe(%rip),%rax # 601170 <acc>
12.90 : 4005b2: add $0x1,%rax
2.30 : 4005b6: mov %rax,0x200bb3(%rip) # 601170 <acc>
0.46 : 4005bd: jmp 4005d1 <branches+0x57> # -100.00% (p:100.00%)
0.92 : 4005bf: mov 0x200baa(%rip),%rax # 601170 <acc> # +49.54%
13.82 : 4005c6: sub $0x1,%rax
0.46 : 4005ca: mov %rax,0x200b9f(%rip) # 601170 <acc>
2.30 : 4005d1: mov -0x10(%rbp),%rax # +50.46%
0.46 : 4005d5: mov %rax,%rdi
0.46 : 4005d8: callq 400526 <lfsr> # -100.00% (p:100.00%)
0.00 : 4005dd: mov %rax,-0x10(%rbp) # +100.00%
0.92 : 4005e1: mov -0x18(%rbp),%rax
0.00 : 4005e5: and $0x1,%eax
0.00 : 4005e8: test %rax,%rax
0.00 : 4005eb: je 4005ff <branches+0x85> # -100.00% (p:100.00%)
0.00 : 4005ed: mov 0x200b7c(%rip),%rax # 601170 <acc>
0.00 : 4005f4: shr $0x2,%rax
0.00 : 4005f8: mov %rax,0x200b71(%rip) # 601170 <acc>
0.00 : 4005ff: mov -0x10(%rbp),%rax # +100.00%
7.37 : 400603: and $0x1,%eax
3.69 : 400606: test %rax,%rax
0.00 : 400609: jne 400612 <branches+0x98> # -59.25% (p:42.99%)
1.84 : 40060b: mov $0x1,%eax
14.29 : 400610: jmp 400617 <branches+0x9d> # -100.00% (p:100.00%)
1.38 : 400612: mov $0x0,%eax # +57.65%
10.14 : 400617: test %al,%al # +42.35%
0.00 : 400619: je 40062f <branches+0xb5> # -57.65% (p:100.00%)
0.46 : 40061b: mov 0x200b4e(%rip),%rax # 601170 <acc>
2.76 : 400622: sub $0x1,%rax
0.00 : 400626: mov %rax,0x200b43(%rip) # 601170 <acc>
0.46 : 40062d: jmp 400641 <branches+0xc7> # -100.00% (p:100.00%)
0.92 : 40062f: mov 0x200b3a(%rip),%rax # 601170 <acc> # +56.13%
2.30 : 400636: add $0x1,%rax
0.92 : 40063a: mov %rax,0x200b2f(%rip) # 601170 <acc>
0.92 : 400641: mov -0x10(%rbp),%rax # +43.87%
2.30 : 400645: mov %rax,%rdi
0.00 : 400648: callq 400526 <lfsr> # -100.00% (p:100.00%)
0.00 : 40064d: mov %rax,-0x10(%rbp) # +100.00%
1.84 : 400651: addq $0x1,-0x8(%rbp)
0.92 : 400656: mov -0x8(%rbp),%rax
5.07 : 40065a: cmp -0x20(%rbp),%rax
0.00 : 40065e: jb 40059f <branches+0x25> # -100.00% (p:100.00%)
0.00 : 400664: nop
0.00 : 400665: leaveq
0.00 : 400666: retq
(Note: the --branch-filter u,any was used to avoid spurious target and
branch points due to interrupts/faults, they show up as very small -/+
annotations on 'weird' locations)
Committer note:
Please take a look at:
http://vger.kernel.org/~acme/perf/annotate_basic_blocks.png
To see the colors.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Anshuman Khandual <khandual@linux.vnet.ibm.com>
Cc: David Carrillo-Cisneros <davidcc@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
[ Moved sym->max_coverage to 'struct annotate', aka symbol__annotate(sym) ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-09-05 16:08:12 -03:00
|
|
|
|
2017-04-17 16:51:59 -03:00
|
|
|
|
2023-12-12 16:13:12 -08:00
|
|
|
|
2019-09-24 16:07:59 -03:00
|
|
|
|
2023-06-14 21:07:15 -07:00
|
|
|
|
2016-11-16 15:39:50 -03:00
|
|
|
|
2022-02-01 23:08:28 -08:00
|
|
|
|
2024-01-16 22:26:54 -08:00
|
|
|
|
2024-03-04 15:08:12 -08:00
|
|
|
|
perf report: Display the branch counter histogram
Reusing the existing --total-cycles option to display the branch
counters. Add a new PERF_HPP_REPORT__BLOCK_BRANCH_COUNTER to display
the logged branch counter events. They are shown right after all the
cycle-related annotations.
Extend the 'struct block_info' to store and pass the branch counter
related information.
The annotation_br_cntr_entry() is to print the histogram of each branch
counter event. If the number of logged events is less than 4, the exact
number of the abbr name is printed. Otherwise, using '+' to stands for
more than 3 events.
Assume the number of logged events is less than 4.
The annotation_br_cntr_abbr_list() prints the branch counter's
abbreviation list. Press 'B' to display the list in the TUI mode.
$ perf record -e "{branch-instructions:ppp,branch-misses}:S" -j any,counter
$ perf report --total-cycles --stdio
# To display the perf.data header info, please use --header/--header-only options.
#
#
# Total Lost Samples: 0
#
# Samples: 1M of events 'anon group { branch-instructions:ppp, branch-misses }'
# Event count (approx.): 1610046
#
# Branch counter abbr list:
# branch-instructions:ppp = A
# branch-misses = B
# '-' No event occurs
# '+' Event occurrences may be lost due to branch counter saturated
#
# Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles Branch Counter [Program Block Range]
# ............... .............. ........... .......... .............. ..................
#
57.55% 2.5M 0.00% 3 |A |- | ...
25.27% 1.1M 0.00% 2 |AA |- | ...
15.61% 667.2K 0.00% 1 |A |- | ...
0.16% 6.9K 0.81% 575 |A |- | ...
0.16% 6.8K 1.38% 977 |AA |- | ...
0.16% 6.8K 0.04% 28 |AA |B | ...
0.15% 6.6K 1.33% 946 |A |- | ...
0.11% 4.5K 0.06% 46 |AAA+|- | ...
0.10% 4.4K 0.88% 624 |A |- | ...
0.09% 3.7K 0.74% 524 |AAA+|B | ...
With -v applied,
# Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles Branch Counter [Program Block Range]
# ............... .............. ........... .......... .............. ..................
#
57.55% 2.5M 0.00% 3 A=1 ,B=- ...
25.27% 1.1M 0.00% 2 A=2 ,B=- ...
15.61% 667.2K 0.00% 1 A=1 ,B=- ...
0.16% 6.9K 0.81% 575 A=1 ,B=- ...
0.16% 6.8K 1.38% 977 A=2 ,B=- ...
0.16% 6.8K 0.04% 28 A=2 ,B=1 ...
0.15% 6.6K 1.33% 946 A=1 ,B=- ...
0.11% 4.5K 0.06% 46 A=3+,B=- ...
0.10% 4.4K 0.88% 624 A=1 ,B=- ...
0.09% 3.7K 0.74% 524 A=3+,B=1 ...
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20240813160208.2493643-7-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-08-13 09:02:05 -07:00
|
|
|
|
2014-11-12 18:05:26 -08:00
|
|
|
|
2012-10-27 23:18:29 +02:00
|
|
|
|
2017-04-17 11:39:06 -03:00
|
|
|
|
2019-06-26 12:13:13 -03:00
|
|
|
|
2023-04-12 09:50:08 -03:00
|
|
|
|
2019-08-22 17:10:08 -03:00
|
|
|
|
2019-10-10 11:36:46 -07:00
|
|
|
|
perf report: Display the branch counter histogram
Reusing the existing --total-cycles option to display the branch
counters. Add a new PERF_HPP_REPORT__BLOCK_BRANCH_COUNTER to display
the logged branch counter events. They are shown right after all the
cycle-related annotations.
Extend the 'struct block_info' to store and pass the branch counter
related information.
The annotation_br_cntr_entry() is to print the histogram of each branch
counter event. If the number of logged events is less than 4, the exact
number of the abbr name is printed. Otherwise, using '+' to stands for
more than 3 events.
Assume the number of logged events is less than 4.
The annotation_br_cntr_abbr_list() prints the branch counter's
abbreviation list. Press 'B' to display the list in the TUI mode.
$ perf record -e "{branch-instructions:ppp,branch-misses}:S" -j any,counter
$ perf report --total-cycles --stdio
# To display the perf.data header info, please use --header/--header-only options.
#
#
# Total Lost Samples: 0
#
# Samples: 1M of events 'anon group { branch-instructions:ppp, branch-misses }'
# Event count (approx.): 1610046
#
# Branch counter abbr list:
# branch-instructions:ppp = A
# branch-misses = B
# '-' No event occurs
# '+' Event occurrences may be lost due to branch counter saturated
#
# Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles Branch Counter [Program Block Range]
# ............... .............. ........... .......... .............. ..................
#
57.55% 2.5M 0.00% 3 |A |- | ...
25.27% 1.1M 0.00% 2 |AA |- | ...
15.61% 667.2K 0.00% 1 |A |- | ...
0.16% 6.9K 0.81% 575 |A |- | ...
0.16% 6.8K 1.38% 977 |AA |- | ...
0.16% 6.8K 0.04% 28 |AA |B | ...
0.15% 6.6K 1.33% 946 |A |- | ...
0.11% 4.5K 0.06% 46 |AAA+|- | ...
0.10% 4.4K 0.88% 624 |A |- | ...
0.09% 3.7K 0.74% 524 |AAA+|B | ...
With -v applied,
# Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles Branch Counter [Program Block Range]
# ............... .............. ........... .......... .............. ..................
#
57.55% 2.5M 0.00% 3 A=1 ,B=- ...
25.27% 1.1M 0.00% 2 A=2 ,B=- ...
15.61% 667.2K 0.00% 1 A=1 ,B=- ...
0.16% 6.9K 0.81% 575 A=1 ,B=- ...
0.16% 6.8K 1.38% 977 A=2 ,B=- ...
0.16% 6.8K 0.04% 28 A=2 ,B=1 ...
0.15% 6.6K 1.33% 946 A=1 ,B=- ...
0.11% 4.5K 0.06% 46 A=3+,B=- ...
0.10% 4.4K 0.88% 624 A=1 ,B=- ...
0.09% 3.7K 0.74% 524 A=3+,B=1 ...
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20240813160208.2493643-7-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-08-13 09:02:05 -07:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
2018-03-15 19:12:39 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-03-15 23:14:51 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-03-15 19:12:39 -03:00
|
|
|
|
tools perf: Move from sane_ctype.h obtained from git to the Linux's original
We got the sane_ctype.h headers from git and kept using it so far, but
since that code originally came from the kernel sources to the git
sources, perhaps its better to just use the one in the kernel, so that
we can leverage tools/perf/check_headers.sh to be notified when our copy
gets out of sync, i.e. when fixes or goodies are added to the code we've
copied.
This will help with things like tools/lib/string.c where we want to have
more things in common with the kernel, such as strim(), skip_spaces(),
etc so as to go on removing the things that we have in tools/perf/util/
and instead using the code in the kernel, indirectly and removing things
like EXPORT_SYMBOL(), etc, getting notified when fixes and improvements
are made to the original code.
Hopefully this also should help with reducing the difference of code
hosted in tools/ to the one in the kernel proper.
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-7k9868l713wqtgo01xxygn12@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-25 17:27:31 -03:00
|
|
|
|
2017-04-17 16:10:49 -03:00
|
|
|
|
2023-11-28 09:54:34 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-29 14:58:10 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-11-16 15:39:50 -03:00
|
|
|
|
2024-03-29 14:58:10 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-11-16 15:39:50 -03:00
|
|
|
|
2024-03-29 14:58:10 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-12-12 16:13:11 -08:00
|
|
|
|
2025-03-10 15:49:23 -07:00
|
|
|
|
|
|
|
|
|
2024-03-04 15:08:12 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-24 16:01:31 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-24 17:33:18 -03:00
|
|
|
|
2018-05-24 16:01:31 -03:00
|
|
|
|
2024-05-07 11:35:39 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-24 16:01:31 -03:00
|
|
|
|
|
|
|
|
|
2024-03-04 15:08:12 -08:00
|
|
|
|
2024-05-10 14:04:51 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-24 16:01:31 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-24 16:23:08 -03:00
|
|
|
|
2024-03-04 15:08:14 -08:00
|
|
|
|
2011-02-08 13:27:39 -02:00
|
|
|
|
2018-05-24 16:23:08 -03:00
|
|
|
|
2024-03-04 15:08:14 -08:00
|
|
|
|
2024-03-04 15:08:12 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-24 16:23:08 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-02-06 14:54:44 -02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-06-14 21:07:15 -07:00
|
|
|
|
2015-07-18 08:24:48 -07:00
|
|
|
|
2011-02-08 13:27:39 -02:00
|
|
|
|
2024-03-04 15:08:14 -08:00
|
|
|
|
2024-03-04 15:08:12 -08:00
|
|
|
|
2023-11-03 12:19:04 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-07-18 08:24:48 -07:00
|
|
|
|
2023-06-14 21:07:15 -07:00
|
|
|
|
2011-02-06 14:54:44 -02:00
|
|
|
|
|
|
|
|
|
2018-05-24 15:20:18 -03:00
|
|
|
|
2015-07-18 08:24:48 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-17 22:58:37 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-07-18 08:24:48 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-09-25 09:14:46 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-07-18 08:24:48 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-11-04 15:57:38 -03:00
|
|
|
|
2025-01-17 10:18:48 -08:00
|
|
|
|
2017-07-20 17:18:05 -03:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
2019-11-04 15:57:38 -03:00
|
|
|
|
2024-03-04 15:08:12 -08:00
|
|
|
|
|
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
2024-03-04 15:08:12 -08:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
2023-04-04 13:59:44 -07:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
2016-11-22 14:10:50 +05:30
|
|
|
|
|
|
|
|
|
2015-10-21 15:45:13 -03:00
|
|
|
|
|
|
|
|
|
2012-03-27 12:55:57 -03:00
|
|
|
|
2015-10-21 15:45:13 -03:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
2011-02-04 13:43:24 -02:00
|
|
|
|
2025-01-17 10:18:48 -08:00
|
|
|
|
2018-06-05 16:31:21 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-04 15:08:12 -08:00
|
|
|
|
2025-01-17 10:18:48 -08:00
|
|
|
|
2024-03-04 15:08:12 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-07-20 06:36:51 +09:00
|
|
|
|
2017-07-20 17:18:05 -03:00
|
|
|
|
2024-03-04 15:08:12 -08:00
|
|
|
|
|
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
|
|
|
|
|
2017-07-20 17:18:05 -03:00
|
|
|
|
2025-01-17 10:18:48 -08:00
|
|
|
|
2024-03-04 15:08:12 -08:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-03 12:19:05 -07:00
|
|
|
|
2023-11-03 12:19:04 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-08-13 09:02:03 -07:00
|
|
|
|
|
|
|
|
|
2015-05-27 10:51:46 -07:00
|
|
|
|
|
|
|
|
|
2023-11-03 12:19:04 -07:00
|
|
|
|
2024-08-13 09:02:03 -07:00
|
|
|
|
2015-05-27 10:51:46 -07:00
|
|
|
|
2023-11-03 12:19:04 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-08-13 09:02:03 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-07-18 08:24:48 -07:00
|
|
|
|
2018-05-24 17:17:05 -03:00
|
|
|
|
2024-08-13 09:02:03 -07:00
|
|
|
|
2015-05-27 10:51:46 -07:00
|
|
|
|
|
|
|
|
|
2018-05-24 17:33:18 -03:00
|
|
|
|
2018-05-24 16:37:53 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-04 15:08:14 -08:00
|
|
|
|
2018-05-24 16:37:53 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-11-04 15:57:38 -03:00
|
|
|
|
2019-07-21 13:23:51 +02:00
|
|
|
|
2017-07-20 16:28:53 -03:00
|
|
|
|
2013-12-18 15:37:41 -03:00
|
|
|
|
2019-11-04 15:57:38 -03:00
|
|
|
|
2018-05-24 16:37:53 -03:00
|
|
|
|
2013-12-18 15:37:41 -03:00
|
|
|
|
2014-02-20 10:32:53 +09:00
|
|
|
|
2013-12-18 15:37:41 -03:00
|
|
|
|
2019-07-21 13:24:28 +02:00
|
|
|
|
2025-01-17 10:18:48 -08:00
|
|
|
|
2013-12-18 15:37:41 -03:00
|
|
|
|
|
|
|
|
|
2024-08-13 09:02:03 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-07-18 08:24:48 -07:00
|
|
|
|
2024-08-13 09:02:03 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf env: Find correct branch counter info on hybrid
No event is printed in the "Branch Counter" column on hybrid machines.
For example,
$ perf record -e "{cpu_core/branch-instructions/pp,cpu_core/branches/}:S" -j any,counter
$ perf report --total-cycles
# Branch counter abbr list:
# cpu_core/branch-instructions/pp = A
# cpu_core/branches/ = B
# '-' No event occurs
# '+' Event occurrences may be lost due to branch counter saturated
#
# Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles Branch Counter
# ............... .............. ........... .......... ..............
44.54% 727.1K 0.00% 1 |+ |+ |
36.31% 592.7K 0.00% 2 |+ |+ |
17.83% 291.1K 0.00% 1 |+ |+ |
The branch counter information (br_cntr_width and br_cntr_nr) in the
perf_env is retrieved from the CPU_PMU_CAPS. However, the CPU_PMU_CAPS
is not available on hybrid machines. Without the width information, the
number of occurrences of an event cannot be calculated.
For a hybrid machine, the caps information should be retrieved from the
PMU_CAPS, and stored in the perf_env->pmu_caps.
Add a perf_env__find_br_cntr_info() to return the correct branch counter
information from the corresponding fields.
Committer notes:
While testing I couldn't s ee those "Branch counter" columns enabled by
pressing 'B' on the TUI, after reporting it to the list Kan explained
the situation:
<quote Kan Liang>
For a hybrid client, the "Branch Counter" feature is only supported
starting from the just released Lunar Lake. Perf falls back to only
"ANY" on your Raptor Lake.
The "The branch counter is not available" message is expected.
Here is the 'perf evlist' result from my Lunar Lake machine,
# perf evlist -v
cpu_core/branch-instructions/pp: type: 4 (cpu_core), size: 136, config: 0xc4 (branch-instructions), { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|READ|PERIOD|BRANCH_STACK|IDENTIFIER, read_format: ID|GROUP|LOST, disabled: 1, freq: 1, enable_on_exec: 1, precise_ip: 2, sample_id_all: 1, exclude_guest: 1, branch_sample_type: ANY|COUNTERS
#
</quote>
Fixes: 6f9d8d1de2c61288 ("perf script: Add branch counters")
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20240909184201.553519-1-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-09-09 11:42:00 -07:00
|
|
|
|
2024-08-13 09:02:03 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf env: Find correct branch counter info on hybrid
No event is printed in the "Branch Counter" column on hybrid machines.
For example,
$ perf record -e "{cpu_core/branch-instructions/pp,cpu_core/branches/}:S" -j any,counter
$ perf report --total-cycles
# Branch counter abbr list:
# cpu_core/branch-instructions/pp = A
# cpu_core/branches/ = B
# '-' No event occurs
# '+' Event occurrences may be lost due to branch counter saturated
#
# Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles Branch Counter
# ............... .............. ........... .......... ..............
44.54% 727.1K 0.00% 1 |+ |+ |
36.31% 592.7K 0.00% 2 |+ |+ |
17.83% 291.1K 0.00% 1 |+ |+ |
The branch counter information (br_cntr_width and br_cntr_nr) in the
perf_env is retrieved from the CPU_PMU_CAPS. However, the CPU_PMU_CAPS
is not available on hybrid machines. Without the width information, the
number of occurrences of an event cannot be calculated.
For a hybrid machine, the caps information should be retrieved from the
PMU_CAPS, and stored in the perf_env->pmu_caps.
Add a perf_env__find_br_cntr_info() to return the correct branch counter
information from the corresponding fields.
Committer notes:
While testing I couldn't s ee those "Branch counter" columns enabled by
pressing 'B' on the TUI, after reporting it to the list Kan explained
the situation:
<quote Kan Liang>
For a hybrid client, the "Branch Counter" feature is only supported
starting from the just released Lunar Lake. Perf falls back to only
"ANY" on your Raptor Lake.
The "The branch counter is not available" message is expected.
Here is the 'perf evlist' result from my Lunar Lake machine,
# perf evlist -v
cpu_core/branch-instructions/pp: type: 4 (cpu_core), size: 136, config: 0xc4 (branch-instructions), { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|READ|PERIOD|BRANCH_STACK|IDENTIFIER, read_format: ID|GROUP|LOST, disabled: 1, freq: 1, enable_on_exec: 1, precise_ip: 2, sample_id_all: 1, exclude_guest: 1, branch_sample_type: ANY|COUNTERS
#
</quote>
Fixes: 6f9d8d1de2c61288 ("perf script: Add branch counters")
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20240909184201.553519-1-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-09-09 11:42:00 -07:00
|
|
|
|
|
|
|
|
|
2024-08-13 09:02:03 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-07-18 08:24:48 -07:00
|
|
|
|
2024-08-13 09:02:03 -07:00
|
|
|
|
2015-07-18 08:24:48 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-08-13 09:02:03 -07:00
|
|
|
|
|
|
|
|
|
2015-07-18 08:24:48 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-08-13 09:02:03 -07:00
|
|
|
|
2015-07-18 08:24:48 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-08-13 09:02:03 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-07-18 08:24:48 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-08-13 09:02:03 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-07-18 08:24:48 -07:00
|
|
|
|
2015-08-14 10:11:34 +03:00
|
|
|
|
2015-07-18 08:24:48 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-11-04 15:57:38 -03:00
|
|
|
|
|
|
|
|
|
2023-03-20 14:22:36 -07:00
|
|
|
|
2015-07-18 08:24:48 -07:00
|
|
|
|
|
|
|
|
|
2015-08-14 10:11:34 +03:00
|
|
|
|
2015-07-18 08:24:48 -07:00
|
|
|
|
|
|
|
|
|
2023-03-20 14:22:36 -07:00
|
|
|
|
2015-07-18 08:24:48 -07:00
|
|
|
|
2024-08-13 09:02:03 -07:00
|
|
|
|
2015-07-18 08:24:48 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-04-04 10:57:10 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-03-15 11:46:23 -03:00
|
|
|
|
|
|
|
|
|
2024-04-04 10:57:11 -07:00
|
|
|
|
2018-03-15 11:46:23 -03:00
|
|
|
|
|
|
|
|
|
2024-04-04 10:57:11 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-03-15 11:46:23 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-03 12:19:04 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-08-13 09:02:03 -07:00
|
|
|
|
2023-11-03 12:19:04 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-03-15 11:46:23 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf annotate: Compute average IPC and IPC coverage per symbol
Add support to 'perf report' annotate view or 'perf annotate --stdio2'
to aggregate the IPC derived from timed LBRs per symbol. We compute the
average IPC and the IPC coverage percentage.
For example:
$ perf annotate --stdio2
Percent IPC Cycle (Average IPC: 2.30, IPC Coverage: 54.8%)
Disassembly of section .text:
000000000003aac0 <random@@GLIBC_2.2.5>:
8.32 3.28 sub $0x18,%rsp
3.28 mov $0x1,%esi
3.28 xor %eax,%eax
3.28 cmpl $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x1e0
11.57 3.28 1 ↓ je 20
lock cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
↓ jne 29
↓ jmp 43
11.57 1.10 20: cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
0.00 1.10 1 ↓ je 43
29: lea __abort_msg@@GLIBC_PRIVATE+0x8a0,%rdi
sub $0x80,%rsp
→ callq __lll_lock_wait_private
add $0x80,%rsp
0.00 3.00 43: lea __ctype_b@GLIBC_2.2.5+0x38,%rdi
3.00 lea 0xc(%rsp),%rsi
8.49 3.00 1 → callq __random_r
7.91 1.94 cmpl $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x1e0
0.00 1.94 1 ↓ je 68
lock decl __abort_msg@@GLIBC_PRIVATE+0x8a0
↓ jne 70
↓ jmp 8a
0.00 2.00 68: decl __abort_msg@@GLIBC_PRIVATE+0x8a0
21.56 2.00 1 ↓ je 8a
70: lea __abort_msg@@GLIBC_PRIVATE+0x8a0,%rdi
sub $0x80,%rsp
→ callq __lll_unlock_wake_private
add $0x80,%rsp
21.56 2.90 8a: movslq 0xc(%rsp),%rax
2.90 add $0x18,%rsp
9.03 2.90 1 ← retq
It shows for this symbol the average IPC is 2.30 and the IPC coverage is
54.8%.
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Reviewed-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://lkml.kernel.org/r/1543586097-27632-2-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-11-30 21:54:54 +08:00
|
|
|
|
2018-03-15 11:46:23 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-04-04 10:57:11 -07:00
|
|
|
|
2023-11-03 12:19:04 -07:00
|
|
|
|
2018-03-15 11:46:23 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-03-16 05:16:17 +08:00
|
|
|
|
2018-03-15 11:46:23 -03:00
|
|
|
|
|
|
|
|
|
2024-04-04 10:57:11 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-03-15 11:46:23 -03:00
|
|
|
|
2024-04-04 10:57:11 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-03 12:19:03 -07:00
|
|
|
|
perf annotate: Compute average IPC and IPC coverage per symbol
Add support to 'perf report' annotate view or 'perf annotate --stdio2'
to aggregate the IPC derived from timed LBRs per symbol. We compute the
average IPC and the IPC coverage percentage.
For example:
$ perf annotate --stdio2
Percent IPC Cycle (Average IPC: 2.30, IPC Coverage: 54.8%)
Disassembly of section .text:
000000000003aac0 <random@@GLIBC_2.2.5>:
8.32 3.28 sub $0x18,%rsp
3.28 mov $0x1,%esi
3.28 xor %eax,%eax
3.28 cmpl $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x1e0
11.57 3.28 1 ↓ je 20
lock cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
↓ jne 29
↓ jmp 43
11.57 1.10 20: cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
0.00 1.10 1 ↓ je 43
29: lea __abort_msg@@GLIBC_PRIVATE+0x8a0,%rdi
sub $0x80,%rsp
→ callq __lll_lock_wait_private
add $0x80,%rsp
0.00 3.00 43: lea __ctype_b@GLIBC_2.2.5+0x38,%rdi
3.00 lea 0xc(%rsp),%rsi
8.49 3.00 1 → callq __random_r
7.91 1.94 cmpl $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x1e0
0.00 1.94 1 ↓ je 68
lock decl __abort_msg@@GLIBC_PRIVATE+0x8a0
↓ jne 70
↓ jmp 8a
0.00 2.00 68: decl __abort_msg@@GLIBC_PRIVATE+0x8a0
21.56 2.00 1 ↓ je 8a
70: lea __abort_msg@@GLIBC_PRIVATE+0x8a0,%rdi
sub $0x80,%rsp
→ callq __lll_unlock_wake_private
add $0x80,%rsp
21.56 2.90 8a: movslq 0xc(%rsp),%rax
2.90 add $0x18,%rsp
9.03 2.90 1 ← retq
It shows for this symbol the average IPC is 2.30 and the IPC coverage is
54.8%.
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Reviewed-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://lkml.kernel.org/r/1543586097-27632-2-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-11-30 21:54:54 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-03 12:19:04 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-03-15 11:46:23 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf annotate: Display the branch counter histogram
Display the branch counter histogram in the annotation view.
Press 'B' to display the branch counter's abbreviation list as well.
Samples: 1M of events 'anon group { branch-instructions:ppp, branch-misses }',
4000 Hz, Event count (approx.):
f3 /home/sdp/test/tchain_edit [Percent: local period]
Percent │ IPC Cycle Branch Counter (Average IPC: 1.39, IPC Coverage: 29.4%)
│ 0000000000401755 <f3>:
0.00 0.00 │ endbr64
│ push %rbp
│ mov %rsp,%rbp
│ movl $0x0,-0x4(%rbp)
0.00 0.00 │1.33 3 |A |- | ↓ jmp 25
11.03 11.03 │ 11: mov -0x4(%rbp),%eax
│ and $0x1,%eax
│ test %eax,%eax
17.13 17.13 │2.41 1 |A |- | ↓ je 21
│ addl $0x1,-0x4(%rbp)
21.84 21.84 │2.22 2 |AA |- | ↓ jmp 25
17.13 17.13 │ 21: addl $0x1,-0x4(%rbp)
21.84 21.84 │ 25: cmpl $0x270f,-0x4(%rbp)
11.03 11.03 │0.61 3 |A |- | ↑ jle 11
│ nop
│ pop %rbp
0.00 0.00 │0.24 20 |AA |B | ← ret
Originally-by: Tinghao Zhang <tinghao.zhang@intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20240813160208.2493643-8-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-08-13 09:02:06 -07:00
|
|
|
|
|
|
|
|
|
2018-03-15 11:46:23 -03:00
|
|
|
|
perf annotate: Display the branch counter histogram
Display the branch counter histogram in the annotation view.
Press 'B' to display the branch counter's abbreviation list as well.
Samples: 1M of events 'anon group { branch-instructions:ppp, branch-misses }',
4000 Hz, Event count (approx.):
f3 /home/sdp/test/tchain_edit [Percent: local period]
Percent │ IPC Cycle Branch Counter (Average IPC: 1.39, IPC Coverage: 29.4%)
│ 0000000000401755 <f3>:
0.00 0.00 │ endbr64
│ push %rbp
│ mov %rsp,%rbp
│ movl $0x0,-0x4(%rbp)
0.00 0.00 │1.33 3 |A |- | ↓ jmp 25
11.03 11.03 │ 11: mov -0x4(%rbp),%eax
│ and $0x1,%eax
│ test %eax,%eax
17.13 17.13 │2.41 1 |A |- | ↓ je 21
│ addl $0x1,-0x4(%rbp)
21.84 21.84 │2.22 2 |AA |- | ↓ jmp 25
17.13 17.13 │ 21: addl $0x1,-0x4(%rbp)
21.84 21.84 │ 25: cmpl $0x270f,-0x4(%rbp)
11.03 11.03 │0.61 3 |A |- | ↑ jle 11
│ nop
│ pop %rbp
0.00 0.00 │0.24 20 |AA |B | ← ret
Originally-by: Tinghao Zhang <tinghao.zhang@intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20240813160208.2493643-8-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-08-13 09:02:06 -07:00
|
|
|
|
2023-11-03 12:19:03 -07:00
|
|
|
|
perf annotate: Compute average IPC and IPC coverage per symbol
Add support to 'perf report' annotate view or 'perf annotate --stdio2'
to aggregate the IPC derived from timed LBRs per symbol. We compute the
average IPC and the IPC coverage percentage.
For example:
$ perf annotate --stdio2
Percent IPC Cycle (Average IPC: 2.30, IPC Coverage: 54.8%)
Disassembly of section .text:
000000000003aac0 <random@@GLIBC_2.2.5>:
8.32 3.28 sub $0x18,%rsp
3.28 mov $0x1,%esi
3.28 xor %eax,%eax
3.28 cmpl $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x1e0
11.57 3.28 1 ↓ je 20
lock cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
↓ jne 29
↓ jmp 43
11.57 1.10 20: cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
0.00 1.10 1 ↓ je 43
29: lea __abort_msg@@GLIBC_PRIVATE+0x8a0,%rdi
sub $0x80,%rsp
→ callq __lll_lock_wait_private
add $0x80,%rsp
0.00 3.00 43: lea __ctype_b@GLIBC_2.2.5+0x38,%rdi
3.00 lea 0xc(%rsp),%rsi
8.49 3.00 1 → callq __random_r
7.91 1.94 cmpl $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x1e0
0.00 1.94 1 ↓ je 68
lock decl __abort_msg@@GLIBC_PRIVATE+0x8a0
↓ jne 70
↓ jmp 8a
0.00 2.00 68: decl __abort_msg@@GLIBC_PRIVATE+0x8a0
21.56 2.00 1 ↓ je 8a
70: lea __abort_msg@@GLIBC_PRIVATE+0x8a0,%rdi
sub $0x80,%rsp
→ callq __lll_unlock_wake_private
add $0x80,%rsp
21.56 2.90 8a: movslq 0xc(%rsp),%rax
2.90 add $0x18,%rsp
9.03 2.90 1 ← retq
It shows for this symbol the average IPC is 2.30 and the IPC coverage is
54.8%.
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Reviewed-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://lkml.kernel.org/r/1543586097-27632-2-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-11-30 21:54:54 +08:00
|
|
|
|
2018-03-15 11:46:23 -03:00
|
|
|
|
2023-11-03 12:19:04 -07:00
|
|
|
|
2023-11-03 12:19:03 -07:00
|
|
|
|
2018-03-15 11:46:23 -03:00
|
|
|
|
2023-11-03 12:19:04 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf annotate: Compute average IPC and IPC coverage per symbol
Add support to 'perf report' annotate view or 'perf annotate --stdio2'
to aggregate the IPC derived from timed LBRs per symbol. We compute the
average IPC and the IPC coverage percentage.
For example:
$ perf annotate --stdio2
Percent IPC Cycle (Average IPC: 2.30, IPC Coverage: 54.8%)
Disassembly of section .text:
000000000003aac0 <random@@GLIBC_2.2.5>:
8.32 3.28 sub $0x18,%rsp
3.28 mov $0x1,%esi
3.28 xor %eax,%eax
3.28 cmpl $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x1e0
11.57 3.28 1 ↓ je 20
lock cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
↓ jne 29
↓ jmp 43
11.57 1.10 20: cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
0.00 1.10 1 ↓ je 43
29: lea __abort_msg@@GLIBC_PRIVATE+0x8a0,%rdi
sub $0x80,%rsp
→ callq __lll_lock_wait_private
add $0x80,%rsp
0.00 3.00 43: lea __ctype_b@GLIBC_2.2.5+0x38,%rdi
3.00 lea 0xc(%rsp),%rsi
8.49 3.00 1 → callq __random_r
7.91 1.94 cmpl $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x1e0
0.00 1.94 1 ↓ je 68
lock decl __abort_msg@@GLIBC_PRIVATE+0x8a0
↓ jne 70
↓ jmp 8a
0.00 2.00 68: decl __abort_msg@@GLIBC_PRIVATE+0x8a0
21.56 2.00 1 ↓ je 8a
70: lea __abort_msg@@GLIBC_PRIVATE+0x8a0,%rdi
sub $0x80,%rsp
→ callq __lll_unlock_wake_private
add $0x80,%rsp
21.56 2.90 8a: movslq 0xc(%rsp),%rax
2.90 add $0x18,%rsp
9.03 2.90 1 ← retq
It shows for this symbol the average IPC is 2.30 and the IPC coverage is
54.8%.
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Reviewed-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://lkml.kernel.org/r/1543586097-27632-2-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-11-30 21:54:54 +08:00
|
|
|
|
2023-06-14 21:07:15 -07:00
|
|
|
|
perf annotate: Compute average IPC and IPC coverage per symbol
Add support to 'perf report' annotate view or 'perf annotate --stdio2'
to aggregate the IPC derived from timed LBRs per symbol. We compute the
average IPC and the IPC coverage percentage.
For example:
$ perf annotate --stdio2
Percent IPC Cycle (Average IPC: 2.30, IPC Coverage: 54.8%)
Disassembly of section .text:
000000000003aac0 <random@@GLIBC_2.2.5>:
8.32 3.28 sub $0x18,%rsp
3.28 mov $0x1,%esi
3.28 xor %eax,%eax
3.28 cmpl $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x1e0
11.57 3.28 1 ↓ je 20
lock cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
↓ jne 29
↓ jmp 43
11.57 1.10 20: cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
0.00 1.10 1 ↓ je 43
29: lea __abort_msg@@GLIBC_PRIVATE+0x8a0,%rdi
sub $0x80,%rsp
→ callq __lll_lock_wait_private
add $0x80,%rsp
0.00 3.00 43: lea __ctype_b@GLIBC_2.2.5+0x38,%rdi
3.00 lea 0xc(%rsp),%rsi
8.49 3.00 1 → callq __random_r
7.91 1.94 cmpl $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x1e0
0.00 1.94 1 ↓ je 68
lock decl __abort_msg@@GLIBC_PRIVATE+0x8a0
↓ jne 70
↓ jmp 8a
0.00 2.00 68: decl __abort_msg@@GLIBC_PRIVATE+0x8a0
21.56 2.00 1 ↓ je 8a
70: lea __abort_msg@@GLIBC_PRIVATE+0x8a0,%rdi
sub $0x80,%rsp
→ callq __lll_unlock_wake_private
add $0x80,%rsp
21.56 2.90 8a: movslq 0xc(%rsp),%rax
2.90 add $0x18,%rsp
9.03 2.90 1 ← retq
It shows for this symbol the average IPC is 2.30 and the IPC coverage is
54.8%.
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Reviewed-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://lkml.kernel.org/r/1543586097-27632-2-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-11-30 21:54:54 +08:00
|
|
|
|
2018-03-15 11:46:23 -03:00
|
|
|
|
|
|
|
|
|
2023-11-03 12:19:04 -07:00
|
|
|
|
2018-03-15 11:46:23 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-04-04 10:57:10 -07:00
|
|
|
|
2023-11-03 12:19:03 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-03-15 11:46:23 -03:00
|
|
|
|
|
|
|
|
|
2018-05-17 22:58:37 +08:00
|
|
|
|
2023-11-03 12:19:03 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-17 22:58:37 +08:00
|
|
|
|
perf annotate: Display the branch counter histogram
Display the branch counter histogram in the annotation view.
Press 'B' to display the branch counter's abbreviation list as well.
Samples: 1M of events 'anon group { branch-instructions:ppp, branch-misses }',
4000 Hz, Event count (approx.):
f3 /home/sdp/test/tchain_edit [Percent: local period]
Percent │ IPC Cycle Branch Counter (Average IPC: 1.39, IPC Coverage: 29.4%)
│ 0000000000401755 <f3>:
0.00 0.00 │ endbr64
│ push %rbp
│ mov %rsp,%rbp
│ movl $0x0,-0x4(%rbp)
0.00 0.00 │1.33 3 |A |- | ↓ jmp 25
11.03 11.03 │ 11: mov -0x4(%rbp),%eax
│ and $0x1,%eax
│ test %eax,%eax
17.13 17.13 │2.41 1 |A |- | ↓ je 21
│ addl $0x1,-0x4(%rbp)
21.84 21.84 │2.22 2 |AA |- | ↓ jmp 25
17.13 17.13 │ 21: addl $0x1,-0x4(%rbp)
21.84 21.84 │ 25: cmpl $0x270f,-0x4(%rbp)
11.03 11.03 │0.61 3 |A |- | ↑ jle 11
│ nop
│ pop %rbp
0.00 0.00 │0.24 20 |AA |B | ← ret
Originally-by: Tinghao Zhang <tinghao.zhang@intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20240813160208.2493643-8-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-08-13 09:02:06 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-03-15 11:46:23 -03:00
|
|
|
|
|
|
|
|
|
2023-11-03 12:19:03 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-03 12:19:04 -07:00
|
|
|
|
2023-11-03 12:19:03 -07:00
|
|
|
|
|
|
|
|
|
2024-04-04 10:57:10 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf annotate: Display the branch counter histogram
Display the branch counter histogram in the annotation view.
Press 'B' to display the branch counter's abbreviation list as well.
Samples: 1M of events 'anon group { branch-instructions:ppp, branch-misses }',
4000 Hz, Event count (approx.):
f3 /home/sdp/test/tchain_edit [Percent: local period]
Percent │ IPC Cycle Branch Counter (Average IPC: 1.39, IPC Coverage: 29.4%)
│ 0000000000401755 <f3>:
0.00 0.00 │ endbr64
│ push %rbp
│ mov %rsp,%rbp
│ movl $0x0,-0x4(%rbp)
0.00 0.00 │1.33 3 |A |- | ↓ jmp 25
11.03 11.03 │ 11: mov -0x4(%rbp),%eax
│ and $0x1,%eax
│ test %eax,%eax
17.13 17.13 │2.41 1 |A |- | ↓ je 21
│ addl $0x1,-0x4(%rbp)
21.84 21.84 │2.22 2 |AA |- | ↓ jmp 25
17.13 17.13 │ 21: addl $0x1,-0x4(%rbp)
21.84 21.84 │ 25: cmpl $0x270f,-0x4(%rbp)
11.03 11.03 │0.61 3 |A |- | ↑ jle 11
│ nop
│ pop %rbp
0.00 0.00 │0.24 20 |AA |B | ← ret
Originally-by: Tinghao Zhang <tinghao.zhang@intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20240813160208.2493643-8-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-08-13 09:02:06 -07:00
|
|
|
|
2023-11-03 12:19:03 -07:00
|
|
|
|
perf annotate: Display the branch counter histogram
Display the branch counter histogram in the annotation view.
Press 'B' to display the branch counter's abbreviation list as well.
Samples: 1M of events 'anon group { branch-instructions:ppp, branch-misses }',
4000 Hz, Event count (approx.):
f3 /home/sdp/test/tchain_edit [Percent: local period]
Percent │ IPC Cycle Branch Counter (Average IPC: 1.39, IPC Coverage: 29.4%)
│ 0000000000401755 <f3>:
0.00 0.00 │ endbr64
│ push %rbp
│ mov %rsp,%rbp
│ movl $0x0,-0x4(%rbp)
0.00 0.00 │1.33 3 |A |- | ↓ jmp 25
11.03 11.03 │ 11: mov -0x4(%rbp),%eax
│ and $0x1,%eax
│ test %eax,%eax
17.13 17.13 │2.41 1 |A |- | ↓ je 21
│ addl $0x1,-0x4(%rbp)
21.84 21.84 │2.22 2 |AA |- | ↓ jmp 25
17.13 17.13 │ 21: addl $0x1,-0x4(%rbp)
21.84 21.84 │ 25: cmpl $0x270f,-0x4(%rbp)
11.03 11.03 │0.61 3 |A |- | ↑ jle 11
│ nop
│ pop %rbp
0.00 0.00 │0.24 20 |AA |B | ← ret
Originally-by: Tinghao Zhang <tinghao.zhang@intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20240813160208.2493643-8-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-08-13 09:02:06 -07:00
|
|
|
|
|
|
|
|
|
2023-11-03 12:19:03 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-06-14 21:07:15 -07:00
|
|
|
|
2023-11-03 12:19:03 -07:00
|
|
|
|
2018-03-15 11:46:23 -03:00
|
|
|
|
|
|
|
|
|
2017-07-20 16:28:53 -03:00
|
|
|
|
2019-07-21 13:23:51 +02:00
|
|
|
|
2013-12-18 16:48:29 -03:00
|
|
|
|
2019-11-04 15:57:38 -03:00
|
|
|
|
2013-12-18 16:48:29 -03:00
|
|
|
|
|
|
|
|
|
2017-07-20 16:28:53 -03:00
|
|
|
|
2019-07-21 13:23:51 +02:00
|
|
|
|
2013-12-18 17:10:15 -03:00
|
|
|
|
2019-11-04 15:57:38 -03:00
|
|
|
|
2013-12-18 17:10:15 -03:00
|
|
|
|
|
|
|
|
|
2012-05-07 18:54:16 -03:00
|
|
|
|
2023-06-14 21:07:15 -07:00
|
|
|
|
2021-11-11 19:51:24 -08:00
|
|
|
|
2023-06-14 21:07:15 -07:00
|
|
|
|
2023-11-03 12:19:04 -07:00
|
|
|
|
2021-11-11 19:51:24 -08:00
|
|
|
|
|
|
|
|
|
2023-06-14 21:07:15 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-11-11 19:51:24 -08:00
|
|
|
|
2023-06-14 21:07:15 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-11-11 19:51:24 -08:00
|
|
|
|
|
|
|
|
|
2023-06-14 21:07:15 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-29 14:58:10 -07:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
2017-10-11 17:01:35 +02:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
|
|
|
|
|
2017-10-11 17:01:34 +02:00
|
|
|
|
|
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
2017-10-11 17:01:34 +02:00
|
|
|
|
|
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf annotate: Add branch stack / basic block
I wanted to know the hottest path through a function and figured the
branch-stack (LBR) information should be able to help out with that.
The below uses the branch-stack to create basic blocks and generate
statistics from them.
from to branch_i
* ----> *
|
| block
v
* ----> *
from to branch_i+1
The blocks are broken down into non-overlapping ranges, while tracking
if the start of each range is an entry point and/or the end of a range
is a branch.
Each block iterates all ranges it covers (while splitting where required
to exactly match the block) and increments the 'coverage' count.
For the range including the branch we increment the taken counter, as
well as the pred counter if flags.predicted.
Using these number we can find if an instruction:
- had coverage; given by:
br->coverage / br->sym->max_coverage
This metric ensures each symbol has a 100% spot, which reflects the
observation that each symbol must have a most covered/hottest
block.
- is a branch target: br->is_target && br->start == add
- for targets, how much of a branch's coverages comes from it:
target->entry / branch->coverage
- is a branch: br->is_branch && br->end == addr
- for branches, how often it was taken:
br->taken / br->coverage
after all, all execution that didn't take the branch would have
incremented the coverage and continued onward to a later branch.
- for branches, how often it was predicted:
br->pred / br->taken
The coverage percentage is used to color the address and asm sections;
for low (<1%) coverage we use NORMAL (uncolored), indicating that these
instructions are not 'important'. For high coverage (>75%) we color the
address RED.
For each branch, we add an asm comment after the instruction with
information on how often it was taken and predicted.
Output looks like (sans color, which does loose a lot of the
information :/)
$ perf record --branch-filter u,any -e cycles:p ./branches 27
$ perf annotate branches
Percent | Source code & Disassembly of branches for cycles:pu (217 samples)
---------------------------------------------------------------------------------
: branches():
0.00 : 40057a: push %rbp
0.00 : 40057b: mov %rsp,%rbp
0.00 : 40057e: sub $0x20,%rsp
0.00 : 400582: mov %rdi,-0x18(%rbp)
0.00 : 400586: mov %rsi,-0x20(%rbp)
0.00 : 40058a: mov -0x18(%rbp),%rax
0.00 : 40058e: mov %rax,-0x10(%rbp)
0.00 : 400592: movq $0x0,-0x8(%rbp)
0.00 : 40059a: jmpq 400656 <branches+0xdc>
1.84 : 40059f: mov -0x10(%rbp),%rax # +100.00%
3.23 : 4005a3: and $0x1,%eax
1.84 : 4005a6: test %rax,%rax
0.00 : 4005a9: je 4005bf <branches+0x45> # -54.50% (p:42.00%)
0.46 : 4005ab: mov 0x200bbe(%rip),%rax # 601170 <acc>
12.90 : 4005b2: add $0x1,%rax
2.30 : 4005b6: mov %rax,0x200bb3(%rip) # 601170 <acc>
0.46 : 4005bd: jmp 4005d1 <branches+0x57> # -100.00% (p:100.00%)
0.92 : 4005bf: mov 0x200baa(%rip),%rax # 601170 <acc> # +49.54%
13.82 : 4005c6: sub $0x1,%rax
0.46 : 4005ca: mov %rax,0x200b9f(%rip) # 601170 <acc>
2.30 : 4005d1: mov -0x10(%rbp),%rax # +50.46%
0.46 : 4005d5: mov %rax,%rdi
0.46 : 4005d8: callq 400526 <lfsr> # -100.00% (p:100.00%)
0.00 : 4005dd: mov %rax,-0x10(%rbp) # +100.00%
0.92 : 4005e1: mov -0x18(%rbp),%rax
0.00 : 4005e5: and $0x1,%eax
0.00 : 4005e8: test %rax,%rax
0.00 : 4005eb: je 4005ff <branches+0x85> # -100.00% (p:100.00%)
0.00 : 4005ed: mov 0x200b7c(%rip),%rax # 601170 <acc>
0.00 : 4005f4: shr $0x2,%rax
0.00 : 4005f8: mov %rax,0x200b71(%rip) # 601170 <acc>
0.00 : 4005ff: mov -0x10(%rbp),%rax # +100.00%
7.37 : 400603: and $0x1,%eax
3.69 : 400606: test %rax,%rax
0.00 : 400609: jne 400612 <branches+0x98> # -59.25% (p:42.99%)
1.84 : 40060b: mov $0x1,%eax
14.29 : 400610: jmp 400617 <branches+0x9d> # -100.00% (p:100.00%)
1.38 : 400612: mov $0x0,%eax # +57.65%
10.14 : 400617: test %al,%al # +42.35%
0.00 : 400619: je 40062f <branches+0xb5> # -57.65% (p:100.00%)
0.46 : 40061b: mov 0x200b4e(%rip),%rax # 601170 <acc>
2.76 : 400622: sub $0x1,%rax
0.00 : 400626: mov %rax,0x200b43(%rip) # 601170 <acc>
0.46 : 40062d: jmp 400641 <branches+0xc7> # -100.00% (p:100.00%)
0.92 : 40062f: mov 0x200b3a(%rip),%rax # 601170 <acc> # +56.13%
2.30 : 400636: add $0x1,%rax
0.92 : 40063a: mov %rax,0x200b2f(%rip) # 601170 <acc>
0.92 : 400641: mov -0x10(%rbp),%rax # +43.87%
2.30 : 400645: mov %rax,%rdi
0.00 : 400648: callq 400526 <lfsr> # -100.00% (p:100.00%)
0.00 : 40064d: mov %rax,-0x10(%rbp) # +100.00%
1.84 : 400651: addq $0x1,-0x8(%rbp)
0.92 : 400656: mov -0x8(%rbp),%rax
5.07 : 40065a: cmp -0x20(%rbp),%rax
0.00 : 40065e: jb 40059f <branches+0x25> # -100.00% (p:100.00%)
0.00 : 400664: nop
0.00 : 400665: leaveq
0.00 : 400666: retq
(Note: the --branch-filter u,any was used to avoid spurious target and
branch points due to interrupts/faults, they show up as very small -/+
annotations on 'weird' locations)
Committer note:
Please take a look at:
http://vger.kernel.org/~acme/perf/annotate_basic_blocks.png
To see the colors.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Anshuman Khandual <khandual@linux.vnet.ibm.com>
Cc: David Carrillo-Cisneros <davidcc@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
[ Moved sym->max_coverage to 'struct annotate', aka symbol__annotate(sym) ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-09-05 16:08:12 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf annotate: Align source and offset lines
Align source with offset lines, which are more advanced, because of the
address column.
Before:
: static void *worker_thread(void *__tdata)
: {
0.00 : 48a971: push %rbp
0.00 : 48a972: mov %rsp,%rbp
0.00 : 48a975: sub $0x30,%rsp
0.00 : 48a979: mov %rdi,-0x28(%rbp)
0.00 : 48a97d: mov %fs:0x28,%rax
0.00 : 48a986: mov %rax,-0x8(%rbp)
0.00 : 48a98a: xor %eax,%eax
: struct thread_data *td = __tdata;
0.00 : 48a98c: mov -0x28(%rbp),%rax
0.00 : 48a990: mov %rax,-0x10(%rbp)
: int m = 0, i;
0.00 : 48a994: movl $0x0,-0x1c(%rbp)
: int ret;
:
: for (i = 0; i < loops; i++) {
0.00 : 48a99b: movl $0x0,-0x18(%rbp)
After:
: static void *worker_thread(void *__tdata)
: {
0.00 : 48a971: push %rbp
0.00 : 48a972: mov %rsp,%rbp
0.00 : 48a975: sub $0x30,%rsp
0.00 : 48a979: mov %rdi,-0x28(%rbp)
0.00 : 48a97d: mov %fs:0x28,%rax
0.00 : 48a986: mov %rax,-0x8(%rbp)
0.00 : 48a98a: xor %eax,%eax
: struct thread_data *td = __tdata;
0.00 : 48a98c: mov -0x28(%rbp),%rax
0.00 : 48a990: mov %rax,-0x10(%rbp)
: int m = 0, i;
0.00 : 48a994: movl $0x0,-0x1c(%rbp)
: int ret;
:
: for (i = 0; i < loops; i++) {
0.00 : 48a99b: movl $0x0,-0x18(%rbp)
It makes bigger different when displaying script sources, where the
comment lines looks oddly shifted from the lines which actually hold
code. I'll send script support separately.
Committer note:
Do not use a fixed column width for the addresses, as kernel ones se
more than 10 columns, look at the last offset and get the right width.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20171011150158.11895-36-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-10-11 17:01:58 +02:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
2017-10-11 17:01:47 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf annotate: Align source and offset lines
Align source with offset lines, which are more advanced, because of the
address column.
Before:
: static void *worker_thread(void *__tdata)
: {
0.00 : 48a971: push %rbp
0.00 : 48a972: mov %rsp,%rbp
0.00 : 48a975: sub $0x30,%rsp
0.00 : 48a979: mov %rdi,-0x28(%rbp)
0.00 : 48a97d: mov %fs:0x28,%rax
0.00 : 48a986: mov %rax,-0x8(%rbp)
0.00 : 48a98a: xor %eax,%eax
: struct thread_data *td = __tdata;
0.00 : 48a98c: mov -0x28(%rbp),%rax
0.00 : 48a990: mov %rax,-0x10(%rbp)
: int m = 0, i;
0.00 : 48a994: movl $0x0,-0x1c(%rbp)
: int ret;
:
: for (i = 0; i < loops; i++) {
0.00 : 48a99b: movl $0x0,-0x18(%rbp)
After:
: static void *worker_thread(void *__tdata)
: {
0.00 : 48a971: push %rbp
0.00 : 48a972: mov %rsp,%rbp
0.00 : 48a975: sub $0x30,%rsp
0.00 : 48a979: mov %rdi,-0x28(%rbp)
0.00 : 48a97d: mov %fs:0x28,%rax
0.00 : 48a986: mov %rax,-0x8(%rbp)
0.00 : 48a98a: xor %eax,%eax
: struct thread_data *td = __tdata;
0.00 : 48a98c: mov -0x28(%rbp),%rax
0.00 : 48a990: mov %rax,-0x10(%rbp)
: int m = 0, i;
0.00 : 48a994: movl $0x0,-0x1c(%rbp)
: int ret;
:
: for (i = 0; i < loops; i++) {
0.00 : 48a99b: movl $0x0,-0x18(%rbp)
It makes bigger different when displaying script sources, where the
comment lines looks oddly shifted from the lines which actually hold
code. I'll send script support separately.
Committer note:
Do not use a fixed column width for the addresses, as kernel ones se
more than 10 columns, look at the last offset and get the right width.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20171011150158.11895-36-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-10-11 17:01:58 +02:00
|
|
|
|
2017-10-11 17:01:47 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-03-10 15:49:24 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf annotate: Hide data-type for stack operation and canary
It's mostly unnecessary to print when it has no actual type information
like in the stack operations and canary. Let's have them if -v option
is given.
Before:
$ perf annotate --code-with-type
...
: 0 0xd640 <_dl_relocate_object>:
0.00 : 0: endbr64
0.00 : 4: pushq %rbp # data-type: (stack operation)
0.00 : 5: movq %rsp, %rbp
0.00 : 8: pushq %r15 # data-type: (stack operation)
0.00 : a: pushq %r14 # data-type: (stack operation)
0.00 : c: pushq %r13 # data-type: (stack operation)
0.00 : e: pushq %r12 # data-type: (stack operation)
0.00 : 10: pushq %rbx # data-type: (stack operation)
0.00 : 11: subq $0xf8, %rsp
...
0.00 : d4: testl %eax, %eax
0.00 : d6: jne 0xf424
0.00 : dc: movq 0xf0(%r14), %rbx # data-type: struct link_map +0xf0
0.00 : e3: testq %rbx, %rbx
0.00 : e6: jne 0xf2dd
0.00 : ec: cmpq $0, 0xf8(%r14) # data-type: struct link_map +0xf8
...
After:
: 0 0xd640 <_dl_relocate_object>:
0.00 : 0: endbr64
0.00 : 4: pushq %rbp
0.00 : 5: movq %rsp, %rbp
0.00 : 8: pushq %r15
0.00 : a: pushq %r14
0.00 : c: pushq %r13
0.00 : e: pushq %r12
0.00 : 10: pushq %rbx
0.00 : 11: subq $0xf8, %rsp
...
0.00 : d4: testl %eax, %eax
0.00 : d6: jne 0xf424
0.00 : dc: movq 0xf0(%r14), %rbx # data-type: struct link_map +0xf0
0.00 : e3: testq %rbx, %rbx
0.00 : e6: jne 0xf2dd
0.00 : ec: cmpq $0, 0xf8(%r14) # data-type: struct link_map +0xf8
...
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250816031635.25318-11-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2025-08-15 20:16:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-10-11 17:01:47 +02:00
|
|
|
|
2025-03-10 15:49:24 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-10-11 17:01:47 +02:00
|
|
|
|
2025-03-10 15:49:24 -07:00
|
|
|
|
2017-10-11 17:01:47 +02:00
|
|
|
|
2024-08-03 14:13:30 -07:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
2025-03-10 15:49:21 -07:00
|
|
|
|
|
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
2017-10-11 17:01:47 +02:00
|
|
|
|
2017-10-11 17:01:42 +02:00
|
|
|
|
perf annotate: Add basic support to event group view
Add --group option to enable event grouping. When enabled, all the
group members information will be shown with the leader so skip
non-leader events.
It only supports --stdio output currently. Later patches will extend
additional features.
$ perf annotate --group --stdio
...
Percent | Source code & Disassembly of libpthread-2.15.so
--------------------------------------------------------------------------------
:
:
:
: Disassembly of section .text:
:
: 000000387dc0aa50 <__pthread_mutex_unlock_usercnt>:
8.08 2.40 5.29 : 387dc0aa50: mov %rdi,%rdx
0.00 0.00 0.00 : 387dc0aa53: mov 0x10(%rdi),%edi
0.00 0.00 0.00 : 387dc0aa56: mov %edi,%eax
0.00 0.80 0.00 : 387dc0aa58: and $0x7f,%eax
3.03 2.40 3.53 : 387dc0aa5b: test $0x7c,%dil
0.00 0.00 0.00 : 387dc0aa5f: jne 387dc0aaa9 <__pthread_mutex_unlock_use
0.00 0.00 0.00 : 387dc0aa61: test %eax,%eax
0.00 0.00 0.00 : 387dc0aa63: jne 387dc0aa85 <__pthread_mutex_unlock_use
0.00 0.00 0.00 : 387dc0aa65: and $0x80,%edi
0.00 0.00 0.00 : 387dc0aa6b: test %esi,%esi
3.03 5.60 7.06 : 387dc0aa6d: movl $0x0,0x8(%rdx)
0.00 0.00 0.59 : 387dc0aa74: je 387dc0aa7a <__pthread_mutex_unlock_use
0.00 0.00 0.00 : 387dc0aa76: subl $0x1,0xc(%rdx)
2.02 5.60 1.18 : 387dc0aa7a: mov %edi,%esi
0.00 0.00 0.00 : 387dc0aa7c: lock decl (%rdx)
83.84 83.20 82.35 : 387dc0aa7f: jne 387dc0aada <_L_unlock_586>
0.00 0.00 0.00 : 387dc0aa81: nop
0.00 0.00 0.00 : 387dc0aa82: xor %eax,%eax
0.00 0.00 0.00 : 387dc0aa84: retq
...
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1362462812-30885-6-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-03-05 14:53:25 +09:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
2011-02-08 13:27:39 -02:00
|
|
|
|
2018-08-04 15:05:05 +02:00
|
|
|
|
2018-08-04 15:05:09 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-08-04 15:05:13 +02:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
2018-08-04 15:05:09 +02:00
|
|
|
|
|
|
|
|
|
perf annotate: Add basic support to event group view
Add --group option to enable event grouping. When enabled, all the
group members information will be shown with the leader so skip
non-leader events.
It only supports --stdio output currently. Later patches will extend
additional features.
$ perf annotate --group --stdio
...
Percent | Source code & Disassembly of libpthread-2.15.so
--------------------------------------------------------------------------------
:
:
:
: Disassembly of section .text:
:
: 000000387dc0aa50 <__pthread_mutex_unlock_usercnt>:
8.08 2.40 5.29 : 387dc0aa50: mov %rdi,%rdx
0.00 0.00 0.00 : 387dc0aa53: mov 0x10(%rdi),%edi
0.00 0.00 0.00 : 387dc0aa56: mov %edi,%eax
0.00 0.80 0.00 : 387dc0aa58: and $0x7f,%eax
3.03 2.40 3.53 : 387dc0aa5b: test $0x7c,%dil
0.00 0.00 0.00 : 387dc0aa5f: jne 387dc0aaa9 <__pthread_mutex_unlock_use
0.00 0.00 0.00 : 387dc0aa61: test %eax,%eax
0.00 0.00 0.00 : 387dc0aa63: jne 387dc0aa85 <__pthread_mutex_unlock_use
0.00 0.00 0.00 : 387dc0aa65: and $0x80,%edi
0.00 0.00 0.00 : 387dc0aa6b: test %esi,%esi
3.03 5.60 7.06 : 387dc0aa6d: movl $0x0,0x8(%rdx)
0.00 0.00 0.59 : 387dc0aa74: je 387dc0aa7a <__pthread_mutex_unlock_use
0.00 0.00 0.00 : 387dc0aa76: subl $0x1,0xc(%rdx)
2.02 5.60 1.18 : 387dc0aa7a: mov %edi,%esi
0.00 0.00 0.00 : 387dc0aa7c: lock decl (%rdx)
83.84 83.20 82.35 : 387dc0aa7f: jne 387dc0aada <_L_unlock_586>
0.00 0.00 0.00 : 387dc0aa81: nop
0.00 0.00 0.00 : 387dc0aa82: xor %eax,%eax
0.00 0.00 0.00 : 387dc0aa84: retq
...
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1362462812-30885-6-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-03-05 14:53:25 +09:00
|
|
|
|
|
|
|
|
|
2018-08-04 15:05:05 +02:00
|
|
|
|
|
|
|
|
|
2018-05-09 23:57:15 +08:00
|
|
|
|
2025-03-10 15:49:21 -07:00
|
|
|
|
2011-02-06 14:54:44 -02:00
|
|
|
|
|
|
|
|
|
2011-02-08 15:01:39 -02:00
|
|
|
|
2011-02-06 14:54:44 -02:00
|
|
|
|
2011-02-05 15:37:31 -02:00
|
|
|
|
2011-02-08 15:29:25 -02:00
|
|
|
|
2025-03-10 15:49:21 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-10-11 17:01:47 +02:00
|
|
|
|
|
|
|
|
|
2011-02-08 15:29:25 -02:00
|
|
|
|
2025-03-10 15:49:24 -07:00
|
|
|
|
|
|
|
|
|
2011-02-08 15:29:25 -02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf annotate: Add basic support to event group view
Add --group option to enable event grouping. When enabled, all the
group members information will be shown with the leader so skip
non-leader events.
It only supports --stdio output currently. Later patches will extend
additional features.
$ perf annotate --group --stdio
...
Percent | Source code & Disassembly of libpthread-2.15.so
--------------------------------------------------------------------------------
:
:
:
: Disassembly of section .text:
:
: 000000387dc0aa50 <__pthread_mutex_unlock_usercnt>:
8.08 2.40 5.29 : 387dc0aa50: mov %rdi,%rdx
0.00 0.00 0.00 : 387dc0aa53: mov 0x10(%rdi),%edi
0.00 0.00 0.00 : 387dc0aa56: mov %edi,%eax
0.00 0.80 0.00 : 387dc0aa58: and $0x7f,%eax
3.03 2.40 3.53 : 387dc0aa5b: test $0x7c,%dil
0.00 0.00 0.00 : 387dc0aa5f: jne 387dc0aaa9 <__pthread_mutex_unlock_use
0.00 0.00 0.00 : 387dc0aa61: test %eax,%eax
0.00 0.00 0.00 : 387dc0aa63: jne 387dc0aa85 <__pthread_mutex_unlock_use
0.00 0.00 0.00 : 387dc0aa65: and $0x80,%edi
0.00 0.00 0.00 : 387dc0aa6b: test %esi,%esi
3.03 5.60 7.06 : 387dc0aa6d: movl $0x0,0x8(%rdx)
0.00 0.00 0.59 : 387dc0aa74: je 387dc0aa7a <__pthread_mutex_unlock_use
0.00 0.00 0.00 : 387dc0aa76: subl $0x1,0xc(%rdx)
2.02 5.60 1.18 : 387dc0aa7a: mov %edi,%esi
0.00 0.00 0.00 : 387dc0aa7c: lock decl (%rdx)
83.84 83.20 82.35 : 387dc0aa7f: jne 387dc0aada <_L_unlock_586>
0.00 0.00 0.00 : 387dc0aa81: nop
0.00 0.00 0.00 : 387dc0aa82: xor %eax,%eax
0.00 0.00 0.00 : 387dc0aa84: retq
...
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1362462812-30885-6-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-03-05 14:53:25 +09:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
perf annotate: Add basic support to event group view
Add --group option to enable event grouping. When enabled, all the
group members information will be shown with the leader so skip
non-leader events.
It only supports --stdio output currently. Later patches will extend
additional features.
$ perf annotate --group --stdio
...
Percent | Source code & Disassembly of libpthread-2.15.so
--------------------------------------------------------------------------------
:
:
:
: Disassembly of section .text:
:
: 000000387dc0aa50 <__pthread_mutex_unlock_usercnt>:
8.08 2.40 5.29 : 387dc0aa50: mov %rdi,%rdx
0.00 0.00 0.00 : 387dc0aa53: mov 0x10(%rdi),%edi
0.00 0.00 0.00 : 387dc0aa56: mov %edi,%eax
0.00 0.80 0.00 : 387dc0aa58: and $0x7f,%eax
3.03 2.40 3.53 : 387dc0aa5b: test $0x7c,%dil
0.00 0.00 0.00 : 387dc0aa5f: jne 387dc0aaa9 <__pthread_mutex_unlock_use
0.00 0.00 0.00 : 387dc0aa61: test %eax,%eax
0.00 0.00 0.00 : 387dc0aa63: jne 387dc0aa85 <__pthread_mutex_unlock_use
0.00 0.00 0.00 : 387dc0aa65: and $0x80,%edi
0.00 0.00 0.00 : 387dc0aa6b: test %esi,%esi
3.03 5.60 7.06 : 387dc0aa6d: movl $0x0,0x8(%rdx)
0.00 0.00 0.59 : 387dc0aa74: je 387dc0aa7a <__pthread_mutex_unlock_use
0.00 0.00 0.00 : 387dc0aa76: subl $0x1,0xc(%rdx)
2.02 5.60 1.18 : 387dc0aa7a: mov %edi,%esi
0.00 0.00 0.00 : 387dc0aa7c: lock decl (%rdx)
83.84 83.20 82.35 : 387dc0aa7f: jne 387dc0aada <_L_unlock_586>
0.00 0.00 0.00 : 387dc0aa81: nop
0.00 0.00 0.00 : 387dc0aa82: xor %eax,%eax
0.00 0.00 0.00 : 387dc0aa84: retq
...
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1362462812-30885-6-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-03-05 14:53:25 +09:00
|
|
|
|
2018-08-04 15:05:06 +02:00
|
|
|
|
2018-08-04 15:05:09 +02:00
|
|
|
|
2017-10-11 17:01:42 +02:00
|
|
|
|
2018-08-04 15:05:13 +02:00
|
|
|
|
2018-08-04 15:05:09 +02:00
|
|
|
|
2015-06-19 16:10:43 -03:00
|
|
|
|
|
|
|
|
|
2017-07-26 17:16:46 -03:00
|
|
|
|
2018-08-04 15:05:06 +02:00
|
|
|
|
2017-08-18 17:46:48 +09:00
|
|
|
|
|
|
|
|
|
2018-08-04 15:05:06 +02:00
|
|
|
|
2015-06-19 16:10:43 -03:00
|
|
|
|
2018-08-04 15:05:09 +02:00
|
|
|
|
perf annotate: Add basic support to event group view
Add --group option to enable event grouping. When enabled, all the
group members information will be shown with the leader so skip
non-leader events.
It only supports --stdio output currently. Later patches will extend
additional features.
$ perf annotate --group --stdio
...
Percent | Source code & Disassembly of libpthread-2.15.so
--------------------------------------------------------------------------------
:
:
:
: Disassembly of section .text:
:
: 000000387dc0aa50 <__pthread_mutex_unlock_usercnt>:
8.08 2.40 5.29 : 387dc0aa50: mov %rdi,%rdx
0.00 0.00 0.00 : 387dc0aa53: mov 0x10(%rdi),%edi
0.00 0.00 0.00 : 387dc0aa56: mov %edi,%eax
0.00 0.80 0.00 : 387dc0aa58: and $0x7f,%eax
3.03 2.40 3.53 : 387dc0aa5b: test $0x7c,%dil
0.00 0.00 0.00 : 387dc0aa5f: jne 387dc0aaa9 <__pthread_mutex_unlock_use
0.00 0.00 0.00 : 387dc0aa61: test %eax,%eax
0.00 0.00 0.00 : 387dc0aa63: jne 387dc0aa85 <__pthread_mutex_unlock_use
0.00 0.00 0.00 : 387dc0aa65: and $0x80,%edi
0.00 0.00 0.00 : 387dc0aa6b: test %esi,%esi
3.03 5.60 7.06 : 387dc0aa6d: movl $0x0,0x8(%rdx)
0.00 0.00 0.59 : 387dc0aa74: je 387dc0aa7a <__pthread_mutex_unlock_use
0.00 0.00 0.00 : 387dc0aa76: subl $0x1,0xc(%rdx)
2.02 5.60 1.18 : 387dc0aa7a: mov %edi,%esi
0.00 0.00 0.00 : 387dc0aa7c: lock decl (%rdx)
83.84 83.20 82.35 : 387dc0aa7f: jne 387dc0aada <_L_unlock_586>
0.00 0.00 0.00 : 387dc0aa81: nop
0.00 0.00 0.00 : 387dc0aa82: xor %eax,%eax
0.00 0.00 0.00 : 387dc0aa84: retq
...
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1362462812-30885-6-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-03-05 14:53:25 +09:00
|
|
|
|
|
|
|
|
|
perf annotate: Align source and offset lines
Align source with offset lines, which are more advanced, because of the
address column.
Before:
: static void *worker_thread(void *__tdata)
: {
0.00 : 48a971: push %rbp
0.00 : 48a972: mov %rsp,%rbp
0.00 : 48a975: sub $0x30,%rsp
0.00 : 48a979: mov %rdi,-0x28(%rbp)
0.00 : 48a97d: mov %fs:0x28,%rax
0.00 : 48a986: mov %rax,-0x8(%rbp)
0.00 : 48a98a: xor %eax,%eax
: struct thread_data *td = __tdata;
0.00 : 48a98c: mov -0x28(%rbp),%rax
0.00 : 48a990: mov %rax,-0x10(%rbp)
: int m = 0, i;
0.00 : 48a994: movl $0x0,-0x1c(%rbp)
: int ret;
:
: for (i = 0; i < loops; i++) {
0.00 : 48a99b: movl $0x0,-0x18(%rbp)
After:
: static void *worker_thread(void *__tdata)
: {
0.00 : 48a971: push %rbp
0.00 : 48a972: mov %rsp,%rbp
0.00 : 48a975: sub $0x30,%rsp
0.00 : 48a979: mov %rdi,-0x28(%rbp)
0.00 : 48a97d: mov %fs:0x28,%rax
0.00 : 48a986: mov %rax,-0x8(%rbp)
0.00 : 48a98a: xor %eax,%eax
: struct thread_data *td = __tdata;
0.00 : 48a98c: mov -0x28(%rbp),%rax
0.00 : 48a990: mov %rax,-0x10(%rbp)
: int m = 0, i;
0.00 : 48a994: movl $0x0,-0x1c(%rbp)
: int ret;
:
: for (i = 0; i < loops; i++) {
0.00 : 48a99b: movl $0x0,-0x18(%rbp)
It makes bigger different when displaying script sources, where the
comment lines looks oddly shifted from the lines which actually hold
code. I'll send script support separately.
Committer note:
Do not use a fixed column width for the addresses, as kernel ones se
more than 10 columns, look at the last offset and get the right width.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20171011150158.11895-36-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-10-11 17:01:58 +02:00
|
|
|
|
perf annotate: Add branch stack / basic block
I wanted to know the hottest path through a function and figured the
branch-stack (LBR) information should be able to help out with that.
The below uses the branch-stack to create basic blocks and generate
statistics from them.
from to branch_i
* ----> *
|
| block
v
* ----> *
from to branch_i+1
The blocks are broken down into non-overlapping ranges, while tracking
if the start of each range is an entry point and/or the end of a range
is a branch.
Each block iterates all ranges it covers (while splitting where required
to exactly match the block) and increments the 'coverage' count.
For the range including the branch we increment the taken counter, as
well as the pred counter if flags.predicted.
Using these number we can find if an instruction:
- had coverage; given by:
br->coverage / br->sym->max_coverage
This metric ensures each symbol has a 100% spot, which reflects the
observation that each symbol must have a most covered/hottest
block.
- is a branch target: br->is_target && br->start == add
- for targets, how much of a branch's coverages comes from it:
target->entry / branch->coverage
- is a branch: br->is_branch && br->end == addr
- for branches, how often it was taken:
br->taken / br->coverage
after all, all execution that didn't take the branch would have
incremented the coverage and continued onward to a later branch.
- for branches, how often it was predicted:
br->pred / br->taken
The coverage percentage is used to color the address and asm sections;
for low (<1%) coverage we use NORMAL (uncolored), indicating that these
instructions are not 'important'. For high coverage (>75%) we color the
address RED.
For each branch, we add an asm comment after the instruction with
information on how often it was taken and predicted.
Output looks like (sans color, which does loose a lot of the
information :/)
$ perf record --branch-filter u,any -e cycles:p ./branches 27
$ perf annotate branches
Percent | Source code & Disassembly of branches for cycles:pu (217 samples)
---------------------------------------------------------------------------------
: branches():
0.00 : 40057a: push %rbp
0.00 : 40057b: mov %rsp,%rbp
0.00 : 40057e: sub $0x20,%rsp
0.00 : 400582: mov %rdi,-0x18(%rbp)
0.00 : 400586: mov %rsi,-0x20(%rbp)
0.00 : 40058a: mov -0x18(%rbp),%rax
0.00 : 40058e: mov %rax,-0x10(%rbp)
0.00 : 400592: movq $0x0,-0x8(%rbp)
0.00 : 40059a: jmpq 400656 <branches+0xdc>
1.84 : 40059f: mov -0x10(%rbp),%rax # +100.00%
3.23 : 4005a3: and $0x1,%eax
1.84 : 4005a6: test %rax,%rax
0.00 : 4005a9: je 4005bf <branches+0x45> # -54.50% (p:42.00%)
0.46 : 4005ab: mov 0x200bbe(%rip),%rax # 601170 <acc>
12.90 : 4005b2: add $0x1,%rax
2.30 : 4005b6: mov %rax,0x200bb3(%rip) # 601170 <acc>
0.46 : 4005bd: jmp 4005d1 <branches+0x57> # -100.00% (p:100.00%)
0.92 : 4005bf: mov 0x200baa(%rip),%rax # 601170 <acc> # +49.54%
13.82 : 4005c6: sub $0x1,%rax
0.46 : 4005ca: mov %rax,0x200b9f(%rip) # 601170 <acc>
2.30 : 4005d1: mov -0x10(%rbp),%rax # +50.46%
0.46 : 4005d5: mov %rax,%rdi
0.46 : 4005d8: callq 400526 <lfsr> # -100.00% (p:100.00%)
0.00 : 4005dd: mov %rax,-0x10(%rbp) # +100.00%
0.92 : 4005e1: mov -0x18(%rbp),%rax
0.00 : 4005e5: and $0x1,%eax
0.00 : 4005e8: test %rax,%rax
0.00 : 4005eb: je 4005ff <branches+0x85> # -100.00% (p:100.00%)
0.00 : 4005ed: mov 0x200b7c(%rip),%rax # 601170 <acc>
0.00 : 4005f4: shr $0x2,%rax
0.00 : 4005f8: mov %rax,0x200b71(%rip) # 601170 <acc>
0.00 : 4005ff: mov -0x10(%rbp),%rax # +100.00%
7.37 : 400603: and $0x1,%eax
3.69 : 400606: test %rax,%rax
0.00 : 400609: jne 400612 <branches+0x98> # -59.25% (p:42.99%)
1.84 : 40060b: mov $0x1,%eax
14.29 : 400610: jmp 400617 <branches+0x9d> # -100.00% (p:100.00%)
1.38 : 400612: mov $0x0,%eax # +57.65%
10.14 : 400617: test %al,%al # +42.35%
0.00 : 400619: je 40062f <branches+0xb5> # -57.65% (p:100.00%)
0.46 : 40061b: mov 0x200b4e(%rip),%rax # 601170 <acc>
2.76 : 400622: sub $0x1,%rax
0.00 : 400626: mov %rax,0x200b43(%rip) # 601170 <acc>
0.46 : 40062d: jmp 400641 <branches+0xc7> # -100.00% (p:100.00%)
0.92 : 40062f: mov 0x200b3a(%rip),%rax # 601170 <acc> # +56.13%
2.30 : 400636: add $0x1,%rax
0.92 : 40063a: mov %rax,0x200b2f(%rip) # 601170 <acc>
0.92 : 400641: mov -0x10(%rbp),%rax # +43.87%
2.30 : 400645: mov %rax,%rdi
0.00 : 400648: callq 400526 <lfsr> # -100.00% (p:100.00%)
0.00 : 40064d: mov %rax,-0x10(%rbp) # +100.00%
1.84 : 400651: addq $0x1,-0x8(%rbp)
0.92 : 400656: mov -0x8(%rbp),%rax
5.07 : 40065a: cmp -0x20(%rbp),%rax
0.00 : 40065e: jb 40059f <branches+0x25> # -100.00% (p:100.00%)
0.00 : 400664: nop
0.00 : 400665: leaveq
0.00 : 400666: retq
(Note: the --branch-filter u,any was used to avoid spurious target and
branch points due to interrupts/faults, they show up as very small -/+
annotations on 'weird' locations)
Committer note:
Please take a look at:
http://vger.kernel.org/~acme/perf/annotate_basic_blocks.png
To see the colors.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Anshuman Khandual <khandual@linux.vnet.ibm.com>
Cc: David Carrillo-Cisneros <davidcc@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
[ Moved sym->max_coverage to 'struct annotate', aka symbol__annotate(sym) ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-09-05 16:08:12 -03:00
|
|
|
|
2025-08-15 20:16:25 -07:00
|
|
|
|
2025-03-10 15:49:24 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf annotate: Hide data-type for stack operation and canary
It's mostly unnecessary to print when it has no actual type information
like in the stack operations and canary. Let's have them if -v option
is given.
Before:
$ perf annotate --code-with-type
...
: 0 0xd640 <_dl_relocate_object>:
0.00 : 0: endbr64
0.00 : 4: pushq %rbp # data-type: (stack operation)
0.00 : 5: movq %rsp, %rbp
0.00 : 8: pushq %r15 # data-type: (stack operation)
0.00 : a: pushq %r14 # data-type: (stack operation)
0.00 : c: pushq %r13 # data-type: (stack operation)
0.00 : e: pushq %r12 # data-type: (stack operation)
0.00 : 10: pushq %rbx # data-type: (stack operation)
0.00 : 11: subq $0xf8, %rsp
...
0.00 : d4: testl %eax, %eax
0.00 : d6: jne 0xf424
0.00 : dc: movq 0xf0(%r14), %rbx # data-type: struct link_map +0xf0
0.00 : e3: testq %rbx, %rbx
0.00 : e6: jne 0xf2dd
0.00 : ec: cmpq $0, 0xf8(%r14) # data-type: struct link_map +0xf8
...
After:
: 0 0xd640 <_dl_relocate_object>:
0.00 : 0: endbr64
0.00 : 4: pushq %rbp
0.00 : 5: movq %rsp, %rbp
0.00 : 8: pushq %r15
0.00 : a: pushq %r14
0.00 : c: pushq %r13
0.00 : e: pushq %r12
0.00 : 10: pushq %rbx
0.00 : 11: subq $0xf8, %rsp
...
0.00 : d4: testl %eax, %eax
0.00 : d6: jne 0xf424
0.00 : dc: movq 0xf0(%r14), %rbx # data-type: struct link_map +0xf0
0.00 : e3: testq %rbx, %rbx
0.00 : e6: jne 0xf2dd
0.00 : ec: cmpq $0, 0xf8(%r14) # data-type: struct link_map +0xf8
...
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250816031635.25318-11-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2025-08-15 20:16:33 -07:00
|
|
|
|
2025-03-10 15:49:24 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf annotate: Add line number like in TUI and source location at EOL
The patch changes the output format in 2 ways:
- line number is displayed for all source lines (matching TUI mode)
- source locations for the hottest lines are printed
at the line end in order to preserve layout
Before:
0.00 : 405ef1: inc %r15
: tmpsd * (TD + tmpsd * TDD)));
0.01 : 405ef4: vfmadd213sd 0x2b9b3(%rip),%xmm0,%xmm3 # 4318b0 <_IO_stdin_used+0x8b0>
: tmpsd * (TC +
eff.c:1811 0.67 : 405efd: vfmadd213sd 0x2b9b2(%rip),%xmm0,%xmm3 # 4318b8 <_IO_stdin_used+0x8b8>
: TA + tmpsd * (TB +
0.35 : 405f06: vfmadd213sd 0x2b9b1(%rip),%xmm0,%xmm3 # 4318c0 <_IO_stdin_used+0x8c0>
: dumbo =
eff.c:1809 1.41 : 405f0f: vfmadd213sd 0x2b9b0(%rip),%xmm0,%xmm3 # 4318c8 <_IO_stdin_used+0x8c8>
: sumi -= sj * tmpsd * dij2i * dumbo;
eff.c:1813 2.58 : 405f18: vmulsd %xmm3,%xmm0,%xmm0
2.81 : 405f1c: vfnmadd213sd 0x30(%rsp),%xmm1,%xmm0
3.78 : 405f23: vmovsd %xmm0,0x30(%rsp)
: for (k = 0; k < lpears[i] + upears[i]; k++) {
eff.c:1761 0.90 : 405f29: cmp %r15d,%r12d
After:
0.00 : 405ef1: inc %r15
: 1812 tmpsd * (TD + tmpsd * TDD)));
0.01 : 405ef4: vfmadd213sd 0x2b9b3(%rip),%xmm0,%xmm3 # 4318b0 <_IO_stdin_used+0x8b0>
: 1811 tmpsd * (TC +
0.67 : 405efd: vfmadd213sd 0x2b9b2(%rip),%xmm0,%xmm3 # 4318b8 <_IO_stdin_used+0x8b8> // eff.c:1811
: 1810 TA + tmpsd * (TB +
0.35 : 405f06: vfmadd213sd 0x2b9b1(%rip),%xmm0,%xmm3 # 4318c0 <_IO_stdin_used+0x8c0>
: 1809 dumbo =
1.41 : 405f0f: vfmadd213sd 0x2b9b0(%rip),%xmm0,%xmm3 # 4318c8 <_IO_stdin_used+0x8c8> // eff.c:1809
: 1813 sumi -= sj * tmpsd * dij2i * dumbo;
2.58 : 405f18: vmulsd %xmm3,%xmm0,%xmm0 // eff.c:1813
2.81 : 405f1c: vfnmadd213sd 0x30(%rsp),%xmm1,%xmm0
3.78 : 405f23: vmovsd %xmm0,0x30(%rsp)
: 1761 for (k = 0; k < lpears[i] + upears[i]; k++) {
Where e.g. '// eff.c:1811' shares the same color as the percentantage
at the line beginning.
Signed-off-by: Martin Liška <mliska@suse.cz>
Link: http://lore.kernel.org/lkml/a0d53f31-f633-5013-c386-a4452391b081@suse.cz
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2021-02-21 13:46:36 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf annotate: Add branch stack / basic block
I wanted to know the hottest path through a function and figured the
branch-stack (LBR) information should be able to help out with that.
The below uses the branch-stack to create basic blocks and generate
statistics from them.
from to branch_i
* ----> *
|
| block
v
* ----> *
from to branch_i+1
The blocks are broken down into non-overlapping ranges, while tracking
if the start of each range is an entry point and/or the end of a range
is a branch.
Each block iterates all ranges it covers (while splitting where required
to exactly match the block) and increments the 'coverage' count.
For the range including the branch we increment the taken counter, as
well as the pred counter if flags.predicted.
Using these number we can find if an instruction:
- had coverage; given by:
br->coverage / br->sym->max_coverage
This metric ensures each symbol has a 100% spot, which reflects the
observation that each symbol must have a most covered/hottest
block.
- is a branch target: br->is_target && br->start == add
- for targets, how much of a branch's coverages comes from it:
target->entry / branch->coverage
- is a branch: br->is_branch && br->end == addr
- for branches, how often it was taken:
br->taken / br->coverage
after all, all execution that didn't take the branch would have
incremented the coverage and continued onward to a later branch.
- for branches, how often it was predicted:
br->pred / br->taken
The coverage percentage is used to color the address and asm sections;
for low (<1%) coverage we use NORMAL (uncolored), indicating that these
instructions are not 'important'. For high coverage (>75%) we color the
address RED.
For each branch, we add an asm comment after the instruction with
information on how often it was taken and predicted.
Output looks like (sans color, which does loose a lot of the
information :/)
$ perf record --branch-filter u,any -e cycles:p ./branches 27
$ perf annotate branches
Percent | Source code & Disassembly of branches for cycles:pu (217 samples)
---------------------------------------------------------------------------------
: branches():
0.00 : 40057a: push %rbp
0.00 : 40057b: mov %rsp,%rbp
0.00 : 40057e: sub $0x20,%rsp
0.00 : 400582: mov %rdi,-0x18(%rbp)
0.00 : 400586: mov %rsi,-0x20(%rbp)
0.00 : 40058a: mov -0x18(%rbp),%rax
0.00 : 40058e: mov %rax,-0x10(%rbp)
0.00 : 400592: movq $0x0,-0x8(%rbp)
0.00 : 40059a: jmpq 400656 <branches+0xdc>
1.84 : 40059f: mov -0x10(%rbp),%rax # +100.00%
3.23 : 4005a3: and $0x1,%eax
1.84 : 4005a6: test %rax,%rax
0.00 : 4005a9: je 4005bf <branches+0x45> # -54.50% (p:42.00%)
0.46 : 4005ab: mov 0x200bbe(%rip),%rax # 601170 <acc>
12.90 : 4005b2: add $0x1,%rax
2.30 : 4005b6: mov %rax,0x200bb3(%rip) # 601170 <acc>
0.46 : 4005bd: jmp 4005d1 <branches+0x57> # -100.00% (p:100.00%)
0.92 : 4005bf: mov 0x200baa(%rip),%rax # 601170 <acc> # +49.54%
13.82 : 4005c6: sub $0x1,%rax
0.46 : 4005ca: mov %rax,0x200b9f(%rip) # 601170 <acc>
2.30 : 4005d1: mov -0x10(%rbp),%rax # +50.46%
0.46 : 4005d5: mov %rax,%rdi
0.46 : 4005d8: callq 400526 <lfsr> # -100.00% (p:100.00%)
0.00 : 4005dd: mov %rax,-0x10(%rbp) # +100.00%
0.92 : 4005e1: mov -0x18(%rbp),%rax
0.00 : 4005e5: and $0x1,%eax
0.00 : 4005e8: test %rax,%rax
0.00 : 4005eb: je 4005ff <branches+0x85> # -100.00% (p:100.00%)
0.00 : 4005ed: mov 0x200b7c(%rip),%rax # 601170 <acc>
0.00 : 4005f4: shr $0x2,%rax
0.00 : 4005f8: mov %rax,0x200b71(%rip) # 601170 <acc>
0.00 : 4005ff: mov -0x10(%rbp),%rax # +100.00%
7.37 : 400603: and $0x1,%eax
3.69 : 400606: test %rax,%rax
0.00 : 400609: jne 400612 <branches+0x98> # -59.25% (p:42.99%)
1.84 : 40060b: mov $0x1,%eax
14.29 : 400610: jmp 400617 <branches+0x9d> # -100.00% (p:100.00%)
1.38 : 400612: mov $0x0,%eax # +57.65%
10.14 : 400617: test %al,%al # +42.35%
0.00 : 400619: je 40062f <branches+0xb5> # -57.65% (p:100.00%)
0.46 : 40061b: mov 0x200b4e(%rip),%rax # 601170 <acc>
2.76 : 400622: sub $0x1,%rax
0.00 : 400626: mov %rax,0x200b43(%rip) # 601170 <acc>
0.46 : 40062d: jmp 400641 <branches+0xc7> # -100.00% (p:100.00%)
0.92 : 40062f: mov 0x200b3a(%rip),%rax # 601170 <acc> # +56.13%
2.30 : 400636: add $0x1,%rax
0.92 : 40063a: mov %rax,0x200b2f(%rip) # 601170 <acc>
0.92 : 400641: mov -0x10(%rbp),%rax # +43.87%
2.30 : 400645: mov %rax,%rdi
0.00 : 400648: callq 400526 <lfsr> # -100.00% (p:100.00%)
0.00 : 40064d: mov %rax,-0x10(%rbp) # +100.00%
1.84 : 400651: addq $0x1,-0x8(%rbp)
0.92 : 400656: mov -0x8(%rbp),%rax
5.07 : 40065a: cmp -0x20(%rbp),%rax
0.00 : 40065e: jb 40059f <branches+0x25> # -100.00% (p:100.00%)
0.00 : 400664: nop
0.00 : 400665: leaveq
0.00 : 400666: retq
(Note: the --branch-filter u,any was used to avoid spurious target and
branch points due to interrupts/faults, they show up as very small -/+
annotations on 'weird' locations)
Committer note:
Please take a look at:
http://vger.kernel.org/~acme/perf/annotate_basic_blocks.png
To see the colors.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Anshuman Khandual <khandual@linux.vnet.ibm.com>
Cc: David Carrillo-Cisneros <davidcc@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
[ Moved sym->max_coverage to 'struct annotate', aka symbol__annotate(sym) ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-09-05 16:08:12 -03:00
|
|
|
|
2011-02-08 15:01:39 -02:00
|
|
|
|
2011-02-06 14:54:44 -02:00
|
|
|
|
|
|
|
|
|
2024-08-03 14:13:30 -07:00
|
|
|
|
perf annotate: Add basic support to event group view
Add --group option to enable event grouping. When enabled, all the
group members information will be shown with the leader so skip
non-leader events.
It only supports --stdio output currently. Later patches will extend
additional features.
$ perf annotate --group --stdio
...
Percent | Source code & Disassembly of libpthread-2.15.so
--------------------------------------------------------------------------------
:
:
:
: Disassembly of section .text:
:
: 000000387dc0aa50 <__pthread_mutex_unlock_usercnt>:
8.08 2.40 5.29 : 387dc0aa50: mov %rdi,%rdx
0.00 0.00 0.00 : 387dc0aa53: mov 0x10(%rdi),%edi
0.00 0.00 0.00 : 387dc0aa56: mov %edi,%eax
0.00 0.80 0.00 : 387dc0aa58: and $0x7f,%eax
3.03 2.40 3.53 : 387dc0aa5b: test $0x7c,%dil
0.00 0.00 0.00 : 387dc0aa5f: jne 387dc0aaa9 <__pthread_mutex_unlock_use
0.00 0.00 0.00 : 387dc0aa61: test %eax,%eax
0.00 0.00 0.00 : 387dc0aa63: jne 387dc0aa85 <__pthread_mutex_unlock_use
0.00 0.00 0.00 : 387dc0aa65: and $0x80,%edi
0.00 0.00 0.00 : 387dc0aa6b: test %esi,%esi
3.03 5.60 7.06 : 387dc0aa6d: movl $0x0,0x8(%rdx)
0.00 0.00 0.59 : 387dc0aa74: je 387dc0aa7a <__pthread_mutex_unlock_use
0.00 0.00 0.00 : 387dc0aa76: subl $0x1,0xc(%rdx)
2.02 5.60 1.18 : 387dc0aa7a: mov %edi,%esi
0.00 0.00 0.00 : 387dc0aa7c: lock decl (%rdx)
83.84 83.20 82.35 : 387dc0aa7f: jne 387dc0aada <_L_unlock_586>
0.00 0.00 0.00 : 387dc0aa81: nop
0.00 0.00 0.00 : 387dc0aa82: xor %eax,%eax
0.00 0.00 0.00 : 387dc0aa84: retq
...
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1362462812-30885-6-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-03-05 14:53:25 +09:00
|
|
|
|
2011-02-08 15:29:25 -02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-10-11 17:01:47 +02:00
|
|
|
|
perf annotate: Add basic support to event group view
Add --group option to enable event grouping. When enabled, all the
group members information will be shown with the leader so skip
non-leader events.
It only supports --stdio output currently. Later patches will extend
additional features.
$ perf annotate --group --stdio
...
Percent | Source code & Disassembly of libpthread-2.15.so
--------------------------------------------------------------------------------
:
:
:
: Disassembly of section .text:
:
: 000000387dc0aa50 <__pthread_mutex_unlock_usercnt>:
8.08 2.40 5.29 : 387dc0aa50: mov %rdi,%rdx
0.00 0.00 0.00 : 387dc0aa53: mov 0x10(%rdi),%edi
0.00 0.00 0.00 : 387dc0aa56: mov %edi,%eax
0.00 0.80 0.00 : 387dc0aa58: and $0x7f,%eax
3.03 2.40 3.53 : 387dc0aa5b: test $0x7c,%dil
0.00 0.00 0.00 : 387dc0aa5f: jne 387dc0aaa9 <__pthread_mutex_unlock_use
0.00 0.00 0.00 : 387dc0aa61: test %eax,%eax
0.00 0.00 0.00 : 387dc0aa63: jne 387dc0aa85 <__pthread_mutex_unlock_use
0.00 0.00 0.00 : 387dc0aa65: and $0x80,%edi
0.00 0.00 0.00 : 387dc0aa6b: test %esi,%esi
3.03 5.60 7.06 : 387dc0aa6d: movl $0x0,0x8(%rdx)
0.00 0.00 0.59 : 387dc0aa74: je 387dc0aa7a <__pthread_mutex_unlock_use
0.00 0.00 0.00 : 387dc0aa76: subl $0x1,0xc(%rdx)
2.02 5.60 1.18 : 387dc0aa7a: mov %edi,%esi
0.00 0.00 0.00 : 387dc0aa7c: lock decl (%rdx)
83.84 83.20 82.35 : 387dc0aa7f: jne 387dc0aada <_L_unlock_586>
0.00 0.00 0.00 : 387dc0aa81: nop
0.00 0.00 0.00 : 387dc0aa82: xor %eax,%eax
0.00 0.00 0.00 : 387dc0aa84: retq
...
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1362462812-30885-6-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-03-05 14:53:25 +09:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
2025-03-10 15:49:24 -07:00
|
|
|
|
|
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
2011-02-06 14:54:44 -02:00
|
|
|
|
|
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
|
|
|
|
|
2024-03-04 15:08:13 -08:00
|
|
|
|
|
|
|
|
|
2018-08-04 15:05:06 +02:00
|
|
|
|
2017-10-11 17:01:40 +02:00
|
|
|
|
|
|
|
|
|
2024-03-04 15:08:13 -08:00
|
|
|
|
2025-01-17 10:18:48 -08:00
|
|
|
|
2017-10-11 17:01:40 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-04 15:08:13 -08:00
|
|
|
|
|
|
|
|
|
2025-01-17 10:18:48 -08:00
|
|
|
|
2024-03-04 15:08:13 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-10-11 17:01:40 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-08-04 15:05:07 +02:00
|
|
|
|
2018-08-04 15:05:06 +02:00
|
|
|
|
|
|
|
|
|
2018-08-04 15:05:09 +02:00
|
|
|
|
2017-10-11 17:01:40 +02:00
|
|
|
|
2018-08-04 15:05:10 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-08-04 15:05:11 +02:00
|
|
|
|
|
|
|
|
|
2018-08-04 15:05:12 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-10-11 17:01:40 +02:00
|
|
|
|
|
|
|
|
|
2017-11-15 12:05:59 +01:00
|
|
|
|
2019-07-21 13:23:51 +02:00
|
|
|
|
2017-10-11 17:01:40 +02:00
|
|
|
|
|
|
|
|
|
2019-07-21 13:23:51 +02:00
|
|
|
|
2017-10-11 17:01:40 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-08-04 15:05:08 +02:00
|
|
|
|
2017-10-11 17:01:40 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-08-04 15:05:08 +02:00
|
|
|
|
2018-08-04 15:05:06 +02:00
|
|
|
|
2017-10-11 17:01:40 +02:00
|
|
|
|
2018-08-04 15:05:08 +02:00
|
|
|
|
|
|
|
|
|
perf annotate: Add --skip-empty option
Like in 'perf report', we want to hide empty events in the 'perf annotate'
output. This is consistent when the option is set in perf report.
For example, the following command would use 3 events including dummy.
$ perf mem record -a -- perf test -w noploop
$ perf evlist
cpu/mem-loads,ldlat=30/P
cpu/mem-stores/P
dummy:u
Just using perf annotate with --group will show the all 3 events.
$ perf annotate --group --stdio | head
Percent | Source code & Disassembly of ...
--------------------------------------------------------------
: 0 0xe060 <_dl_relocate_object>:
0.00 0.00 0.00 : e060: pushq %rbp
0.00 0.00 0.00 : e061: movq %rsp, %rbp
0.00 0.00 0.00 : e064: pushq %r15
0.00 0.00 0.00 : e066: movq %rdi, %r15
0.00 0.00 0.00 : e069: pushq %r14
0.00 0.00 0.00 : e06b: pushq %r13
0.00 0.00 0.00 : e06d: movl %edx, %r13d
Now with --skip-empty, it'll hide the last dummy event.
$ perf annotate --group --stdio --skip-empty | head
Percent | Source code & Disassembly of ...
------------------------------------------------------
: 0 0xe060 <_dl_relocate_object>:
0.00 0.00 : e060: pushq %rbp
0.00 0.00 : e061: movq %rsp, %rbp
0.00 0.00 : e064: pushq %r15
0.00 0.00 : e066: movq %rdi, %r15
0.00 0.00 : e069: pushq %r14
0.00 0.00 : e06b: pushq %r13
0.00 0.00 : e06d: movl %edx, %r13d
Committer testing:
root@x1:~# perf evlist
cpu_atom/mem-loads,ldlat=30/P
cpu_atom/mem-stores/P
dummy:u
root@x1:~#
Before:
root@x1:~# perf annotate --group --stdio2 do_lookup_x | head -25
Samples: 20 of events 'cpu_atom/mem-loads,ldlat=30/P, cpu_atom/mem-stores/P, dummy:u', 4000 Hz, Event count (approx.): 769079, [percent: local period]
do_lookup_x() /usr/lib64/ld-linux-x86-64.so.2
Percent 0x9900 <do_lookup_x>:
pushq %rbp
movq %rsp,%rbp
pushq %r15
pushq %r14
pushq %r13
pushq %r12
pushq %rbx
subq $0x88,%rsp
movq %rdi,-0x50(%rbp)
movl 8(%r9),%edi
movq 0x10(%rbp),%r12
movq 0x28(%rbp),%r10
movq %rdx,-0x70(%rbp)
movq %rcx,-0x58(%rbp)
movq %rdi,%r11
0.00 5.73 0.00 movq %r8,-0x68(%rbp)
movq (%r9),%r8
movl %esi,%eax
8.30 0.00 0.00 movl 0x30(%rbp),%r9d
movl %esi,%r15d
shrl $6, %eax
movq %r8,%r13
root@x1:~#
After:
root@x1:~# perf annotate --group --skip-empty --stdio2 do_lookup_x | head -25
Samples: 20 of events 'cpu_atom/mem-loads,ldlat=30/P, cpu_atom/mem-stores/P', 4000 Hz, Event count (approx.): 769079, [percent: local period]
do_lookup_x() /usr/lib64/ld-linux-x86-64.so.2
Percent 0x9900 <do_lookup_x>:
pushq %rbp
movq %rsp,%rbp
pushq %r15
pushq %r14
pushq %r13
pushq %r12
pushq %rbx
subq $0x88,%rsp
movq %rdi,-0x50(%rbp)
movl 8(%r9),%edi
movq 0x10(%rbp),%r12
movq 0x28(%rbp),%r10
movq %rdx,-0x70(%rbp)
movq %rcx,-0x58(%rbp)
movq %rdi,%r11
0.00 5.73 movq %r8,-0x68(%rbp)
movq (%r9),%r8
movl %esi,%eax
8.30 0.00 movl 0x30(%rbp),%r9d
movl %esi,%r15d
shrl $6, %eax
movq %r8,%r13
root@x1:~#
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20240803211332.1107222-6-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-08-03 14:13:32 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-08-04 15:05:08 +02:00
|
|
|
|
2017-10-11 17:01:40 +02:00
|
|
|
|
2024-03-04 15:08:13 -08:00
|
|
|
|
2017-10-11 17:01:40 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-07-21 13:23:51 +02:00
|
|
|
|
2017-10-11 17:01:40 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-11-15 12:05:59 +01:00
|
|
|
|
2017-10-11 17:01:40 +02:00
|
|
|
|
|
|
|
|
|
2023-12-12 16:13:11 -08:00
|
|
|
|
2017-10-11 17:01:28 +02:00
|
|
|
|
2020-05-04 13:44:03 -03:00
|
|
|
|
2017-12-11 12:52:17 -03:00
|
|
|
|
2017-10-11 17:01:28 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-04-03 11:44:19 -03:00
|
|
|
|
|
|
|
|
|
2019-09-30 15:06:01 -03:00
|
|
|
|
2024-04-03 11:44:19 -03:00
|
|
|
|
2017-10-11 17:01:28 +02:00
|
|
|
|
2023-12-12 16:13:11 -08:00
|
|
|
|
2021-07-26 20:38:54 +08:00
|
|
|
|
|
|
|
|
|
2019-09-30 15:11:47 -03:00
|
|
|
|
2021-07-26 20:38:54 +08:00
|
|
|
|
2017-10-11 17:01:28 +02:00
|
|
|
|
|
|
|
|
|
2017-12-11 12:46:11 -03:00
|
|
|
|
2017-10-11 17:01:28 +02:00
|
|
|
|
2023-12-12 16:13:11 -08:00
|
|
|
|
|
|
|
|
|
2017-10-11 17:01:28 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-12-12 16:13:11 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf annotate: Add --skip-empty option
Like in 'perf report', we want to hide empty events in the 'perf annotate'
output. This is consistent when the option is set in perf report.
For example, the following command would use 3 events including dummy.
$ perf mem record -a -- perf test -w noploop
$ perf evlist
cpu/mem-loads,ldlat=30/P
cpu/mem-stores/P
dummy:u
Just using perf annotate with --group will show the all 3 events.
$ perf annotate --group --stdio | head
Percent | Source code & Disassembly of ...
--------------------------------------------------------------
: 0 0xe060 <_dl_relocate_object>:
0.00 0.00 0.00 : e060: pushq %rbp
0.00 0.00 0.00 : e061: movq %rsp, %rbp
0.00 0.00 0.00 : e064: pushq %r15
0.00 0.00 0.00 : e066: movq %rdi, %r15
0.00 0.00 0.00 : e069: pushq %r14
0.00 0.00 0.00 : e06b: pushq %r13
0.00 0.00 0.00 : e06d: movl %edx, %r13d
Now with --skip-empty, it'll hide the last dummy event.
$ perf annotate --group --stdio --skip-empty | head
Percent | Source code & Disassembly of ...
------------------------------------------------------
: 0 0xe060 <_dl_relocate_object>:
0.00 0.00 : e060: pushq %rbp
0.00 0.00 : e061: movq %rsp, %rbp
0.00 0.00 : e064: pushq %r15
0.00 0.00 : e066: movq %rdi, %r15
0.00 0.00 : e069: pushq %r14
0.00 0.00 : e06b: pushq %r13
0.00 0.00 : e06d: movl %edx, %r13d
Committer testing:
root@x1:~# perf evlist
cpu_atom/mem-loads,ldlat=30/P
cpu_atom/mem-stores/P
dummy:u
root@x1:~#
Before:
root@x1:~# perf annotate --group --stdio2 do_lookup_x | head -25
Samples: 20 of events 'cpu_atom/mem-loads,ldlat=30/P, cpu_atom/mem-stores/P, dummy:u', 4000 Hz, Event count (approx.): 769079, [percent: local period]
do_lookup_x() /usr/lib64/ld-linux-x86-64.so.2
Percent 0x9900 <do_lookup_x>:
pushq %rbp
movq %rsp,%rbp
pushq %r15
pushq %r14
pushq %r13
pushq %r12
pushq %rbx
subq $0x88,%rsp
movq %rdi,-0x50(%rbp)
movl 8(%r9),%edi
movq 0x10(%rbp),%r12
movq 0x28(%rbp),%r10
movq %rdx,-0x70(%rbp)
movq %rcx,-0x58(%rbp)
movq %rdi,%r11
0.00 5.73 0.00 movq %r8,-0x68(%rbp)
movq (%r9),%r8
movl %esi,%eax
8.30 0.00 0.00 movl 0x30(%rbp),%r9d
movl %esi,%r15d
shrl $6, %eax
movq %r8,%r13
root@x1:~#
After:
root@x1:~# perf annotate --group --skip-empty --stdio2 do_lookup_x | head -25
Samples: 20 of events 'cpu_atom/mem-loads,ldlat=30/P, cpu_atom/mem-stores/P', 4000 Hz, Event count (approx.): 769079, [percent: local period]
do_lookup_x() /usr/lib64/ld-linux-x86-64.so.2
Percent 0x9900 <do_lookup_x>:
pushq %rbp
movq %rsp,%rbp
pushq %r15
pushq %r14
pushq %r13
pushq %r12
pushq %rbx
subq $0x88,%rsp
movq %rdi,-0x50(%rbp)
movl 8(%r9),%edi
movq 0x10(%rbp),%r12
movq 0x28(%rbp),%r10
movq %rdx,-0x70(%rbp)
movq %rcx,-0x58(%rbp)
movq %rdi,%r11
0.00 5.73 movq %r8,-0x68(%rbp)
movq (%r9),%r8
movl %esi,%eax
8.30 0.00 movl 0x30(%rbp),%r9d
movl %esi,%r15d
shrl $6, %eax
movq %r8,%r13
root@x1:~#
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20240803211332.1107222-6-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-08-03 14:13:32 -07:00
|
|
|
|
2023-12-12 16:13:11 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-10-11 17:01:28 +02:00
|
|
|
|
2024-04-24 16:00:15 -07:00
|
|
|
|
2024-04-05 14:17:57 -07:00
|
|
|
|
|
|
|
|
|
2023-12-12 16:13:11 -08:00
|
|
|
|
2019-11-04 11:10:00 -03:00
|
|
|
|
2024-04-10 20:32:56 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf annotate: Add --skip-empty option
Like in 'perf report', we want to hide empty events in the 'perf annotate'
output. This is consistent when the option is set in perf report.
For example, the following command would use 3 events including dummy.
$ perf mem record -a -- perf test -w noploop
$ perf evlist
cpu/mem-loads,ldlat=30/P
cpu/mem-stores/P
dummy:u
Just using perf annotate with --group will show the all 3 events.
$ perf annotate --group --stdio | head
Percent | Source code & Disassembly of ...
--------------------------------------------------------------
: 0 0xe060 <_dl_relocate_object>:
0.00 0.00 0.00 : e060: pushq %rbp
0.00 0.00 0.00 : e061: movq %rsp, %rbp
0.00 0.00 0.00 : e064: pushq %r15
0.00 0.00 0.00 : e066: movq %rdi, %r15
0.00 0.00 0.00 : e069: pushq %r14
0.00 0.00 0.00 : e06b: pushq %r13
0.00 0.00 0.00 : e06d: movl %edx, %r13d
Now with --skip-empty, it'll hide the last dummy event.
$ perf annotate --group --stdio --skip-empty | head
Percent | Source code & Disassembly of ...
------------------------------------------------------
: 0 0xe060 <_dl_relocate_object>:
0.00 0.00 : e060: pushq %rbp
0.00 0.00 : e061: movq %rsp, %rbp
0.00 0.00 : e064: pushq %r15
0.00 0.00 : e066: movq %rdi, %r15
0.00 0.00 : e069: pushq %r14
0.00 0.00 : e06b: pushq %r13
0.00 0.00 : e06d: movl %edx, %r13d
Committer testing:
root@x1:~# perf evlist
cpu_atom/mem-loads,ldlat=30/P
cpu_atom/mem-stores/P
dummy:u
root@x1:~#
Before:
root@x1:~# perf annotate --group --stdio2 do_lookup_x | head -25
Samples: 20 of events 'cpu_atom/mem-loads,ldlat=30/P, cpu_atom/mem-stores/P, dummy:u', 4000 Hz, Event count (approx.): 769079, [percent: local period]
do_lookup_x() /usr/lib64/ld-linux-x86-64.so.2
Percent 0x9900 <do_lookup_x>:
pushq %rbp
movq %rsp,%rbp
pushq %r15
pushq %r14
pushq %r13
pushq %r12
pushq %rbx
subq $0x88,%rsp
movq %rdi,-0x50(%rbp)
movl 8(%r9),%edi
movq 0x10(%rbp),%r12
movq 0x28(%rbp),%r10
movq %rdx,-0x70(%rbp)
movq %rcx,-0x58(%rbp)
movq %rdi,%r11
0.00 5.73 0.00 movq %r8,-0x68(%rbp)
movq (%r9),%r8
movl %esi,%eax
8.30 0.00 0.00 movl 0x30(%rbp),%r9d
movl %esi,%r15d
shrl $6, %eax
movq %r8,%r13
root@x1:~#
After:
root@x1:~# perf annotate --group --skip-empty --stdio2 do_lookup_x | head -25
Samples: 20 of events 'cpu_atom/mem-loads,ldlat=30/P, cpu_atom/mem-stores/P', 4000 Hz, Event count (approx.): 769079, [percent: local period]
do_lookup_x() /usr/lib64/ld-linux-x86-64.so.2
Percent 0x9900 <do_lookup_x>:
pushq %rbp
movq %rsp,%rbp
pushq %r15
pushq %r14
pushq %r13
pushq %r12
pushq %rbx
subq $0x88,%rsp
movq %rdi,-0x50(%rbp)
movl 8(%r9),%edi
movq 0x10(%rbp),%r12
movq 0x28(%rbp),%r10
movq %rdx,-0x70(%rbp)
movq %rcx,-0x58(%rbp)
movq %rdi,%r11
0.00 5.73 movq %r8,-0x68(%rbp)
movq (%r9),%r8
movl %esi,%eax
8.30 0.00 movl 0x30(%rbp),%r9d
movl %esi,%r15d
shrl $6, %eax
movq %r8,%r13
root@x1:~#
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20240803211332.1107222-6-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-08-03 14:13:32 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-08-03 14:13:29 -07:00
|
|
|
|
2023-11-28 09:54:37 -08:00
|
|
|
|
2024-04-04 10:57:16 -07:00
|
|
|
|
2022-09-23 10:31:42 -07:00
|
|
|
|
2024-04-04 10:57:16 -07:00
|
|
|
|
2018-03-20 16:19:08 -03:00
|
|
|
|
2017-11-15 12:20:08 +01:00
|
|
|
|
2017-10-11 17:01:28 +02:00
|
|
|
|
|
|
|
|
|
2023-11-28 09:54:37 -08:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
2017-10-11 17:01:41 +02:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
|
|
|
|
|
2023-11-28 09:54:37 -08:00
|
|
|
|
2013-03-05 14:53:28 +09:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-10-11 17:01:41 +02:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
2017-10-11 17:01:41 +02:00
|
|
|
|
2012-11-09 14:58:49 +09:00
|
|
|
|
2018-08-04 15:05:09 +02:00
|
|
|
|
|
|
|
|
|
2023-11-28 09:54:37 -08:00
|
|
|
|
2018-08-04 15:05:09 +02:00
|
|
|
|
2012-11-09 14:58:49 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-08-04 15:05:09 +02:00
|
|
|
|
|
|
|
|
|
2023-11-28 09:54:37 -08:00
|
|
|
|
2018-08-04 15:05:09 +02:00
|
|
|
|
2012-11-09 14:58:49 +09:00
|
|
|
|
2017-10-11 17:01:41 +02:00
|
|
|
|
|
|
|
|
|
2012-11-09 14:58:49 +09:00
|
|
|
|
|
|
|
|
|
2017-10-11 17:01:41 +02:00
|
|
|
|
2013-03-05 14:53:28 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-08-04 15:05:05 +02:00
|
|
|
|
|
|
|
|
|
2013-03-05 14:53:28 +09:00
|
|
|
|
2018-08-04 15:05:05 +02:00
|
|
|
|
2013-03-05 14:53:28 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-10-11 17:01:41 +02:00
|
|
|
|
2012-11-09 14:58:49 +09:00
|
|
|
|
2017-10-11 17:01:41 +02:00
|
|
|
|
2012-11-09 14:58:49 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-10-11 17:01:41 +02:00
|
|
|
|
2012-11-09 14:58:49 +09:00
|
|
|
|
2017-10-11 17:01:41 +02:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-10-11 17:01:41 +02:00
|
|
|
|
|
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
|
|
|
|
|
2012-11-09 14:58:49 +09:00
|
|
|
|
|
|
|
|
|
2017-10-11 17:01:41 +02:00
|
|
|
|
2012-11-09 14:58:49 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-10-11 17:01:41 +02:00
|
|
|
|
2012-11-09 14:58:49 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-10-11 17:01:41 +02:00
|
|
|
|
2012-11-09 14:58:49 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
|
|
|
|
|
2017-10-11 17:01:41 +02:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-03-05 14:53:28 +09:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
|
|
|
|
|
2013-03-05 14:53:28 +09:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
2017-10-11 17:01:41 +02:00
|
|
|
|
2018-08-04 15:05:05 +02:00
|
|
|
|
|
|
|
|
|
2013-03-05 14:53:28 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-10-11 17:01:41 +02:00
|
|
|
|
2013-03-05 14:53:28 +09:00
|
|
|
|
2013-09-11 14:09:28 +09:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-07-21 13:23:51 +02:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
|
|
|
|
|
2025-01-17 10:18:48 -08:00
|
|
|
|
2012-04-19 10:57:06 -03:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
2024-03-04 15:08:13 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-01-17 10:18:48 -08:00
|
|
|
|
2024-03-04 15:08:13 -08:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
2024-03-04 15:08:13 -08:00
|
|
|
|
|
|
|
|
|
2017-07-20 06:36:51 +09:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
|
|
|
|
|
perf annotate: Align source and offset lines
Align source with offset lines, which are more advanced, because of the
address column.
Before:
: static void *worker_thread(void *__tdata)
: {
0.00 : 48a971: push %rbp
0.00 : 48a972: mov %rsp,%rbp
0.00 : 48a975: sub $0x30,%rsp
0.00 : 48a979: mov %rdi,-0x28(%rbp)
0.00 : 48a97d: mov %fs:0x28,%rax
0.00 : 48a986: mov %rax,-0x8(%rbp)
0.00 : 48a98a: xor %eax,%eax
: struct thread_data *td = __tdata;
0.00 : 48a98c: mov -0x28(%rbp),%rax
0.00 : 48a990: mov %rax,-0x10(%rbp)
: int m = 0, i;
0.00 : 48a994: movl $0x0,-0x1c(%rbp)
: int ret;
:
: for (i = 0; i < loops; i++) {
0.00 : 48a99b: movl $0x0,-0x18(%rbp)
After:
: static void *worker_thread(void *__tdata)
: {
0.00 : 48a971: push %rbp
0.00 : 48a972: mov %rsp,%rbp
0.00 : 48a975: sub $0x30,%rsp
0.00 : 48a979: mov %rdi,-0x28(%rbp)
0.00 : 48a97d: mov %fs:0x28,%rax
0.00 : 48a986: mov %rax,-0x8(%rbp)
0.00 : 48a98a: xor %eax,%eax
: struct thread_data *td = __tdata;
0.00 : 48a98c: mov -0x28(%rbp),%rax
0.00 : 48a990: mov %rax,-0x10(%rbp)
: int m = 0, i;
0.00 : 48a994: movl $0x0,-0x1c(%rbp)
: int ret;
:
: for (i = 0; i < loops; i++) {
0.00 : 48a99b: movl $0x0,-0x18(%rbp)
It makes bigger different when displaying script sources, where the
comment lines looks oddly shifted from the lines which actually hold
code. I'll send script support separately.
Committer note:
Do not use a fixed column width for the addresses, as kernel ones se
more than 10 columns, look at the last offset and get the right width.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20171011150158.11895-36-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-10-11 17:01:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-03-10 15:49:22 -07:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
2025-03-10 15:49:22 -07:00
|
|
|
|
2019-11-04 11:10:00 -03:00
|
|
|
|
|
|
|
|
|
2023-03-20 14:22:35 -07:00
|
|
|
|
2012-09-08 09:06:50 -06:00
|
|
|
|
|
|
|
|
|
2020-04-29 16:07:09 -03:00
|
|
|
|
2011-02-08 13:27:39 -02:00
|
|
|
|
2025-01-17 10:18:48 -08:00
|
|
|
|
2017-10-11 17:01:46 +02:00
|
|
|
|
2023-11-28 09:54:37 -08:00
|
|
|
|
2025-03-10 15:49:24 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-02-06 14:54:44 -02:00
|
|
|
|
2018-05-25 17:28:37 -03:00
|
|
|
|
2024-08-03 14:13:30 -07:00
|
|
|
|
2016-06-30 09:17:26 -03:00
|
|
|
|
2018-05-22 19:38:35 +08:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
2024-05-04 14:38:01 -07:00
|
|
|
|
2012-09-08 09:06:50 -06:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-05-25 17:28:37 -03:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-04-30 10:51:16 -03:00
|
|
|
|
2020-04-29 16:09:12 -03:00
|
|
|
|
2018-05-22 19:38:35 +08:00
|
|
|
|
|
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
2018-08-04 15:05:19 +02:00
|
|
|
|
|
|
|
|
|
2017-08-18 17:46:48 +09:00
|
|
|
|
|
|
|
|
|
2018-08-04 15:05:19 +02:00
|
|
|
|
|
|
|
|
|
2014-03-18 11:50:21 -03:00
|
|
|
|
2016-06-30 09:17:26 -03:00
|
|
|
|
2014-03-18 11:50:21 -03:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
2017-02-17 17:17:38 +09:00
|
|
|
|
2013-03-05 14:53:21 +09:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
2025-03-10 15:49:24 -07:00
|
|
|
|
2025-08-15 20:16:25 -07:00
|
|
|
|
2025-03-10 15:49:24 -07:00
|
|
|
|
2025-08-15 20:16:34 -07:00
|
|
|
|
perf annotate: Align source and offset lines
Align source with offset lines, which are more advanced, because of the
address column.
Before:
: static void *worker_thread(void *__tdata)
: {
0.00 : 48a971: push %rbp
0.00 : 48a972: mov %rsp,%rbp
0.00 : 48a975: sub $0x30,%rsp
0.00 : 48a979: mov %rdi,-0x28(%rbp)
0.00 : 48a97d: mov %fs:0x28,%rax
0.00 : 48a986: mov %rax,-0x8(%rbp)
0.00 : 48a98a: xor %eax,%eax
: struct thread_data *td = __tdata;
0.00 : 48a98c: mov -0x28(%rbp),%rax
0.00 : 48a990: mov %rax,-0x10(%rbp)
: int m = 0, i;
0.00 : 48a994: movl $0x0,-0x1c(%rbp)
: int ret;
:
: for (i = 0; i < loops; i++) {
0.00 : 48a99b: movl $0x0,-0x18(%rbp)
After:
: static void *worker_thread(void *__tdata)
: {
0.00 : 48a971: push %rbp
0.00 : 48a972: mov %rsp,%rbp
0.00 : 48a975: sub $0x30,%rsp
0.00 : 48a979: mov %rdi,-0x28(%rbp)
0.00 : 48a97d: mov %fs:0x28,%rax
0.00 : 48a986: mov %rax,-0x8(%rbp)
0.00 : 48a98a: xor %eax,%eax
: struct thread_data *td = __tdata;
0.00 : 48a98c: mov -0x28(%rbp),%rax
0.00 : 48a990: mov %rax,-0x10(%rbp)
: int m = 0, i;
0.00 : 48a994: movl $0x0,-0x1c(%rbp)
: int ret;
:
: for (i = 0; i < loops; i++) {
0.00 : 48a99b: movl $0x0,-0x18(%rbp)
It makes bigger different when displaying script sources, where the
comment lines looks oddly shifted from the lines which actually hold
code. I'll send script support separately.
Committer note:
Do not use a fixed column width for the addresses, as kernel ones se
more than 10 columns, look at the last offset and get the right width.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20171011150158.11895-36-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-10-11 17:01:58 +02:00
|
|
|
|
2017-10-11 17:01:46 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-02-08 15:29:25 -02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-03-10 15:49:24 -07:00
|
|
|
|
2017-10-11 17:01:46 +02:00
|
|
|
|
|
|
|
|
|
2011-02-06 14:54:44 -02:00
|
|
|
|
|
|
|
|
|
2011-02-08 15:29:25 -02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-02-06 14:54:44 -02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-02-05 15:37:31 -02:00
|
|
|
|
2011-02-06 14:54:44 -02:00
|
|
|
|
|
|
|
|
|
2011-02-08 15:29:25 -02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-10-11 17:01:46 +02:00
|
|
|
|
2011-02-08 15:29:25 -02:00
|
|
|
|
|
|
|
|
|
2011-02-06 14:54:44 -02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-03-10 15:49:24 -07:00
|
|
|
|
2012-09-08 09:06:50 -06:00
|
|
|
|
|
|
|
|
|
2011-02-06 14:54:44 -02:00
|
|
|
|
|
|
|
|
|
2011-02-05 18:51:38 -02:00
|
|
|
|
2018-03-15 23:44:34 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:27 -07:00
|
|
|
|
|
|
|
|
|
2018-03-15 23:44:34 -03:00
|
|
|
|
|
|
|
|
|
2018-08-04 15:05:15 +02:00
|
|
|
|
2018-03-15 23:44:34 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:30 -07:00
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:34 -07:00
|
|
|
|
2025-08-15 20:16:30 -07:00
|
|
|
|
|
|
|
|
|
2018-03-15 23:44:34 -03:00
|
|
|
|
2023-11-28 09:54:40 -08:00
|
|
|
|
2018-03-15 23:44:34 -03:00
|
|
|
|
2025-08-15 20:16:27 -07:00
|
|
|
|
2018-03-15 23:44:34 -03:00
|
|
|
|
2018-08-04 15:05:15 +02:00
|
|
|
|
2018-03-15 23:44:34 -03:00
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:30 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-03-15 23:44:34 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:27 -07:00
|
|
|
|
|
|
|
|
|
perf annotate browser: Add 'P' hotkey to dump annotation to file
Just like we have in the histograms browser used as the main screen for
'perf top --tui' and 'perf report --tui', to print the current
annotation to a file with a named composed by the symbol name and the
".annotation" suffix.
Here is one example of pressing 'A' on 'perf top' to live annotate a
kernel function and then press 'P' to dump that annotation, the
resulting file:
# cat _raw_spin_lock_irqsave.annotation
_raw_spin_lock_irqsave() /proc/kcore
Event: cycles:ppp
7.14 nop
21.43 push %rbx
7.14 pushfq
pop %rax
nop
mov %rax,%rbx
cli
nop
xor %eax,%eax
mov $0x1,%edx
64.29 lock cmpxchg %edx,(%rdi)
test %eax,%eax
↓ jne 2b
mov %rbx,%rax
pop %rbx
← retq
2b: mov %eax,%esi
→ callq queued_spin_lock_slowpath
mov %rbx,%rax
pop %rbx
← retq
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-zzmnrwugb5vtk7bvg0rbx150@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-16 16:57:47 -03:00
|
|
|
|
2020-04-29 16:07:09 -03:00
|
|
|
|
perf annotate browser: Add 'P' hotkey to dump annotation to file
Just like we have in the histograms browser used as the main screen for
'perf top --tui' and 'perf report --tui', to print the current
annotation to a file with a named composed by the symbol name and the
".annotation" suffix.
Here is one example of pressing 'A' on 'perf top' to live annotate a
kernel function and then press 'P' to dump that annotation, the
resulting file:
# cat _raw_spin_lock_irqsave.annotation
_raw_spin_lock_irqsave() /proc/kcore
Event: cycles:ppp
7.14 nop
21.43 push %rbx
7.14 pushfq
pop %rax
nop
mov %rax,%rbx
cli
nop
xor %eax,%eax
mov $0x1,%edx
64.29 lock cmpxchg %edx,(%rdi)
test %eax,%eax
↓ jne 2b
mov %rbx,%rax
pop %rbx
← retq
2b: mov %eax,%esi
→ callq queued_spin_lock_slowpath
mov %rbx,%rax
pop %rbx
← retq
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-zzmnrwugb5vtk7bvg0rbx150@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-16 16:57:47 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:27 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf annotate browser: Add 'P' hotkey to dump annotation to file
Just like we have in the histograms browser used as the main screen for
'perf top --tui' and 'perf report --tui', to print the current
annotation to a file with a named composed by the symbol name and the
".annotation" suffix.
Here is one example of pressing 'A' on 'perf top' to live annotate a
kernel function and then press 'P' to dump that annotation, the
resulting file:
# cat _raw_spin_lock_irqsave.annotation
_raw_spin_lock_irqsave() /proc/kcore
Event: cycles:ppp
7.14 nop
21.43 push %rbx
7.14 pushfq
pop %rax
nop
mov %rax,%rbx
cli
nop
xor %eax,%eax
mov $0x1,%edx
64.29 lock cmpxchg %edx,(%rdi)
test %eax,%eax
↓ jne 2b
mov %rbx,%rax
pop %rbx
← retq
2b: mov %eax,%esi
→ callq queued_spin_lock_slowpath
mov %rbx,%rax
pop %rbx
← retq
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-zzmnrwugb5vtk7bvg0rbx150@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-16 16:57:47 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-04-30 10:51:16 -03:00
|
|
|
|
2020-04-29 16:09:12 -03:00
|
|
|
|
perf annotate browser: Add 'P' hotkey to dump annotation to file
Just like we have in the histograms browser used as the main screen for
'perf top --tui' and 'perf report --tui', to print the current
annotation to a file with a named composed by the symbol name and the
".annotation" suffix.
Here is one example of pressing 'A' on 'perf top' to live annotate a
kernel function and then press 'P' to dump that annotation, the
resulting file:
# cat _raw_spin_lock_irqsave.annotation
_raw_spin_lock_irqsave() /proc/kcore
Event: cycles:ppp
7.14 nop
21.43 push %rbx
7.14 pushfq
pop %rax
nop
mov %rax,%rbx
cli
nop
xor %eax,%eax
mov $0x1,%edx
64.29 lock cmpxchg %edx,(%rdi)
test %eax,%eax
↓ jne 2b
mov %rbx,%rax
pop %rbx
← retq
2b: mov %eax,%esi
→ callq queued_spin_lock_slowpath
mov %rbx,%rax
pop %rbx
← retq
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-zzmnrwugb5vtk7bvg0rbx150@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-16 16:57:47 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-05-04 14:38:01 -07:00
|
|
|
|
2025-08-15 20:16:27 -07:00
|
|
|
|
perf annotate browser: Add 'P' hotkey to dump annotation to file
Just like we have in the histograms browser used as the main screen for
'perf top --tui' and 'perf report --tui', to print the current
annotation to a file with a named composed by the symbol name and the
".annotation" suffix.
Here is one example of pressing 'A' on 'perf top' to live annotate a
kernel function and then press 'P' to dump that annotation, the
resulting file:
# cat _raw_spin_lock_irqsave.annotation
_raw_spin_lock_irqsave() /proc/kcore
Event: cycles:ppp
7.14 nop
21.43 push %rbx
7.14 pushfq
pop %rax
nop
mov %rax,%rbx
cli
nop
xor %eax,%eax
mov $0x1,%edx
64.29 lock cmpxchg %edx,(%rdi)
test %eax,%eax
↓ jne 2b
mov %rbx,%rax
pop %rbx
← retq
2b: mov %eax,%esi
→ callq queued_spin_lock_slowpath
mov %rbx,%rax
pop %rbx
← retq
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-zzmnrwugb5vtk7bvg0rbx150@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-16 16:57:47 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-01-17 10:18:48 -08:00
|
|
|
|
2011-02-06 14:54:44 -02:00
|
|
|
|
|
|
|
|
|
2025-01-17 10:18:48 -08:00
|
|
|
|
2011-02-06 14:54:44 -02:00
|
|
|
|
2024-03-04 15:08:14 -08:00
|
|
|
|
2011-02-06 14:54:44 -02:00
|
|
|
|
|
|
|
|
|
2025-01-17 10:18:48 -08:00
|
|
|
|
2011-02-06 14:54:44 -02:00
|
|
|
|
|
|
|
|
|
2025-01-17 10:18:48 -08:00
|
|
|
|
2024-04-04 10:57:11 -07:00
|
|
|
|
2011-02-06 14:54:44 -02:00
|
|
|
|
2017-07-20 06:36:51 +09:00
|
|
|
|
2024-04-04 10:57:11 -07:00
|
|
|
|
2024-03-04 15:08:13 -08:00
|
|
|
|
|
|
|
|
|
2024-04-04 10:57:11 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-01-17 10:18:48 -08:00
|
|
|
|
2024-03-04 15:08:13 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-02-05 18:51:38 -02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-10-11 17:01:38 +02:00
|
|
|
|
2011-02-05 18:51:38 -02:00
|
|
|
|
2017-10-11 17:01:38 +02:00
|
|
|
|
2011-02-05 18:51:38 -02:00
|
|
|
|
2017-10-11 17:01:38 +02:00
|
|
|
|
2019-07-04 12:13:46 -03:00
|
|
|
|
2017-10-11 17:01:38 +02:00
|
|
|
|
2011-02-05 18:51:38 -02:00
|
|
|
|
2025-06-25 16:03:39 -07:00
|
|
|
|
2011-02-05 18:51:38 -02:00
|
|
|
|
|
|
|
|
|
2012-04-15 15:52:18 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-10-11 17:01:26 +02:00
|
|
|
|
|
|
|
|
|
2012-04-15 15:52:18 -03:00
|
|
|
|
2017-10-11 17:01:26 +02:00
|
|
|
|
2012-04-15 15:52:18 -03:00
|
|
|
|
2012-04-20 14:38:46 -03:00
|
|
|
|
2012-04-15 15:52:18 -03:00
|
|
|
|
2012-04-20 14:38:46 -03:00
|
|
|
|
2012-04-15 15:52:18 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-10-11 17:01:25 +02:00
|
|
|
|
2012-04-15 15:52:18 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf annotate: Add "_local" to jump/offset validation routines
Because they all really check if we can access data structures/visual
constructs where a "jump" instruction targets code in the same function,
i.e. things like:
__pthread_mutex_lock /usr/lib64/libpthread-2.26.so
1.95 │ mov __pthread_force_elision,%ecx
│ ┌──test %ecx,%ecx
0.07 │ ├──je 60
│ │ test $0x300,%esi
│ │↓ jne 60
│ │ or $0x100,%esi
│ │ mov %esi,0x10(%rdi)
│ 42:│ mov %esi,%edx
│ │ lea 0x16(%r8),%rsi
│ │ mov %r8,%rdi
│ │ and $0x80,%edx
│ │ add $0x8,%rsp
│ │→ jmpq __lll_lock_elision
│ │ nop
0.29 │ 60:└─→and $0x80,%esi
0.07 │ mov $0x1,%edi
0.29 │ xor %eax,%eax
2.53 │ lock cmpxchg %edi,(%r8)
And not things like that "jmpq __lll_lock_elision", that instead should behave
like a "call" instruction and "jump" to the disassembly of "___lll_lock_elision".
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-3cwx39u3h66dfw9xjrlt7ca2@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-23 10:12:33 -03:00
|
|
|
|
2018-03-15 15:31:56 -03:00
|
|
|
|
|
|
|
|
|
perf annotate: Add "_local" to jump/offset validation routines
Because they all really check if we can access data structures/visual
constructs where a "jump" instruction targets code in the same function,
i.e. things like:
__pthread_mutex_lock /usr/lib64/libpthread-2.26.so
1.95 │ mov __pthread_force_elision,%ecx
│ ┌──test %ecx,%ecx
0.07 │ ├──je 60
│ │ test $0x300,%esi
│ │↓ jne 60
│ │ or $0x100,%esi
│ │ mov %esi,0x10(%rdi)
│ 42:│ mov %esi,%edx
│ │ lea 0x16(%r8),%rsi
│ │ mov %r8,%rdi
│ │ and $0x80,%edx
│ │ add $0x8,%rsp
│ │→ jmpq __lll_lock_elision
│ │ nop
0.29 │ 60:└─→and $0x80,%esi
0.07 │ mov $0x1,%edi
0.29 │ xor %eax,%eax
2.53 │ lock cmpxchg %edi,(%r8)
And not things like that "jmpq __lll_lock_elision", that instead should behave
like a "call" instruction and "jump" to the disassembly of "___lll_lock_elision".
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-3cwx39u3h66dfw9xjrlt7ca2@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-23 10:12:33 -03:00
|
|
|
|
2018-03-15 15:31:56 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-04-04 10:57:09 -07:00
|
|
|
|
|
|
|
|
|
2018-03-15 15:31:56 -03:00
|
|
|
|
2024-04-04 10:57:11 -07:00
|
|
|
|
2018-03-15 15:31:56 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-04-04 10:57:11 -07:00
|
|
|
|
2018-03-15 15:31:56 -03:00
|
|
|
|
2024-04-04 10:57:11 -07:00
|
|
|
|
2018-03-15 15:31:56 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf annotate: Add "_local" to jump/offset validation routines
Because they all really check if we can access data structures/visual
constructs where a "jump" instruction targets code in the same function,
i.e. things like:
__pthread_mutex_lock /usr/lib64/libpthread-2.26.so
1.95 │ mov __pthread_force_elision,%ecx
│ ┌──test %ecx,%ecx
0.07 │ ├──je 60
│ │ test $0x300,%esi
│ │↓ jne 60
│ │ or $0x100,%esi
│ │ mov %esi,0x10(%rdi)
│ 42:│ mov %esi,%edx
│ │ lea 0x16(%r8),%rsi
│ │ mov %r8,%rdi
│ │ and $0x80,%edx
│ │ add $0x8,%rsp
│ │→ jmpq __lll_lock_elision
│ │ nop
0.29 │ 60:└─→and $0x80,%esi
0.07 │ mov $0x1,%edi
0.29 │ xor %eax,%eax
2.53 │ lock cmpxchg %edi,(%r8)
And not things like that "jmpq __lll_lock_elision", that instead should behave
like a "call" instruction and "jump" to the disassembly of "___lll_lock_elision".
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-3cwx39u3h66dfw9xjrlt7ca2@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-23 10:12:33 -03:00
|
|
|
|
2018-03-15 15:31:56 -03:00
|
|
|
|
|
|
|
|
|
2024-04-04 10:57:11 -07:00
|
|
|
|
|
|
|
|
|
2018-03-15 15:31:56 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-04-04 10:57:11 -07:00
|
|
|
|
2018-03-15 15:31:56 -03:00
|
|
|
|
|
|
|
|
|
2024-04-04 10:57:14 -07:00
|
|
|
|
|
|
|
|
|
2018-03-15 15:31:56 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-04-04 10:57:12 -07:00
|
|
|
|
2018-03-15 15:59:01 -03:00
|
|
|
|
|
|
|
|
|
2023-11-03 12:19:06 -07:00
|
|
|
|
2018-03-15 15:59:01 -03:00
|
|
|
|
2024-04-04 10:57:13 -07:00
|
|
|
|
2023-11-03 12:19:06 -07:00
|
|
|
|
|
|
|
|
|
2018-03-15 15:59:01 -03:00
|
|
|
|
2023-11-03 12:19:06 -07:00
|
|
|
|
2018-03-15 15:59:01 -03:00
|
|
|
|
|
|
|
|
|
2024-04-04 10:57:13 -07:00
|
|
|
|
|
|
|
|
|
2023-11-03 12:19:06 -07:00
|
|
|
|
2024-04-04 10:57:12 -07:00
|
|
|
|
2023-11-03 12:19:06 -07:00
|
|
|
|
2024-04-04 10:57:12 -07:00
|
|
|
|
2018-03-15 15:59:01 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-03-15 16:26:29 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf annotate: Calculate the max instruction name, align column to that
We were hardcoding '6' as the max instruction name, and we have lots
that are longer than that, see the diff from two 'P' printed TUI
annotations for a libc function that uses instructions with long names,
such as 'vpmovmskb' with its 9 chars:
--- __strcmp_avx2.annotation.before 2019-03-06 16:31:39.368020425 -0300
+++ __strcmp_avx2.annotation 2019-03-06 16:32:12.079450508 -0300
@@ -2,284 +2,284 @@
Event: cycles:ppp
Percent endbr64
- 0.10 mov %edi,%eax
+ 0.10 mov %edi,%eax
- xor %edx,%edx
+ xor %edx,%edx
- 3.54 vpxor %ymm7,%ymm7,%ymm7
+ 3.54 vpxor %ymm7,%ymm7,%ymm7
- or %esi,%eax
+ or %esi,%eax
- and $0xfff,%eax
+ and $0xfff,%eax
- cmp $0xf80,%eax
+ cmp $0xf80,%eax
- ↓ jg 370
+ ↓ jg 370
- 27.07 vmovdqu (%rdi),%ymm1
+ 27.07 vmovdqu (%rdi),%ymm1
- 7.97 vpcmpeqb (%rsi),%ymm1,%ymm0
+ 7.97 vpcmpeqb (%rsi),%ymm1,%ymm0
- 2.15 vpminub %ymm1,%ymm0,%ymm0
+ 2.15 vpminub %ymm1,%ymm0,%ymm0
- 4.09 vpcmpeqb %ymm7,%ymm0,%ymm0
+ 4.09 vpcmpeqb %ymm7,%ymm0,%ymm0
- 0.43 vpmovmskb %ymm0,%ecx
+ 0.43 vpmovmskb %ymm0,%ecx
- 1.53 test %ecx,%ecx
+ 1.53 test %ecx,%ecx
- ↓ je b0
+ ↓ je b0
- 5.26 tzcnt %ecx,%edx
+ 5.26 tzcnt %ecx,%edx
- 18.40 movzbl (%rdi,%rdx,1),%eax
+ 18.40 movzbl (%rdi,%rdx,1),%eax
- 7.09 movzbl (%rsi,%rdx,1),%edx
+ 7.09 movzbl (%rsi,%rdx,1),%edx
- 3.34 sub %edx,%eax
+ 3.34 sub %edx,%eax
2.37 vzeroupper
← retq
nop
- 50: tzcnt %ecx,%edx
+ 50: tzcnt %ecx,%edx
- movzbl 0x20(%rdi,%rdx,1),%eax
+ movzbl 0x20(%rdi,%rdx,1),%eax
- movzbl 0x20(%rsi,%rdx,1),%edx
+ movzbl 0x20(%rsi,%rdx,1),%edx
- sub %edx,%eax
+ sub %edx,%eax
vzeroupper
← retq
- data16 nopw %cs:0x0(%rax,%rax,1)
+ data16 nopw %cs:0x0(%rax,%rax,1)
Reported-by: Travis Downs <travis.downs@gmail.com>
LPU-Reference: CAOBGo4z1KfmWeOm6Et0cnX5Z6DWsG2PQbAvRn1MhVPJmXHrc5g@mail.gmail.com
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-89wsdd9h9g6bvq52sgp6d0u4@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-03-06 16:40:15 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-04-04 10:57:09 -07:00
|
|
|
|
|
|
|
|
|
2018-03-15 16:26:29 -03:00
|
|
|
|
2024-04-04 10:57:13 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-04-04 10:57:14 -07:00
|
|
|
|
2024-04-04 10:57:13 -07:00
|
|
|
|
2018-03-15 16:26:29 -03:00
|
|
|
|
|
|
|
|
|
2018-03-15 16:19:59 -03:00
|
|
|
|
|
|
|
|
|
2023-11-28 09:54:37 -08:00
|
|
|
|
2024-04-04 10:57:13 -07:00
|
|
|
|
2023-11-28 09:54:37 -08:00
|
|
|
|
2024-04-04 10:57:13 -07:00
|
|
|
|
2018-03-15 16:19:59 -03:00
|
|
|
|
2024-04-04 10:57:13 -07:00
|
|
|
|
2018-03-15 16:19:59 -03:00
|
|
|
|
2024-04-04 10:57:13 -07:00
|
|
|
|
2018-03-15 16:19:59 -03:00
|
|
|
|
2023-11-28 09:54:37 -08:00
|
|
|
|
2024-04-04 10:57:13 -07:00
|
|
|
|
2018-03-15 16:19:59 -03:00
|
|
|
|
|
|
|
|
|
2022-09-23 10:31:42 -07:00
|
|
|
|
|
|
|
|
|
2023-11-28 09:54:37 -08:00
|
|
|
|
2022-09-23 10:31:42 -07:00
|
|
|
|
2023-11-28 09:54:37 -08:00
|
|
|
|
2024-04-04 10:57:16 -07:00
|
|
|
|
2022-09-23 10:31:42 -07:00
|
|
|
|
2024-04-04 10:57:16 -07:00
|
|
|
|
2022-09-23 10:31:42 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-04-04 10:57:08 -07:00
|
|
|
|
2023-11-28 09:54:37 -08:00
|
|
|
|
2017-10-11 17:01:41 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-04-04 10:57:08 -07:00
|
|
|
|
2017-10-11 17:01:41 +02:00
|
|
|
|
|
|
|
|
|
2018-08-04 15:05:05 +02:00
|
|
|
|
2018-08-04 15:05:09 +02:00
|
|
|
|
2017-10-11 17:01:41 +02:00
|
|
|
|
2018-08-04 15:05:09 +02:00
|
|
|
|
2023-11-28 09:54:37 -08:00
|
|
|
|
2017-10-11 17:01:41 +02:00
|
|
|
|
2018-08-04 15:05:09 +02:00
|
|
|
|
|
|
|
|
|
2017-10-11 17:01:41 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-04-04 10:57:08 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-28 09:54:37 -08:00
|
|
|
|
2017-10-11 17:01:41 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-28 09:54:37 -08:00
|
|
|
|
2017-10-11 17:01:41 +02:00
|
|
|
|
2019-11-04 11:10:00 -03:00
|
|
|
|
2017-10-11 17:01:41 +02:00
|
|
|
|
2024-04-04 10:57:08 -07:00
|
|
|
|
2017-10-11 17:01:41 +02:00
|
|
|
|
|
|
|
|
|
2025-03-10 15:49:22 -07:00
|
|
|
|
2018-03-15 23:44:34 -03:00
|
|
|
|
2025-03-10 15:49:22 -07:00
|
|
|
|
2023-03-20 14:22:35 -07:00
|
|
|
|
2019-11-04 11:10:00 -03:00
|
|
|
|
2018-03-15 23:44:34 -03:00
|
|
|
|
2018-08-04 15:05:04 +02:00
|
|
|
|
2025-08-15 20:16:27 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-03-16 15:17:23 -03:00
|
|
|
|
2021-07-29 16:58:02 +01:00
|
|
|
|
|
|
|
|
|
2023-11-28 09:54:37 -08:00
|
|
|
|
2021-07-29 16:58:02 +01:00
|
|
|
|
|
|
|
|
|
2018-03-15 23:44:34 -03:00
|
|
|
|
2024-05-04 14:38:01 -07:00
|
|
|
|
2021-07-29 16:58:02 +01:00
|
|
|
|
|
|
|
|
|
2018-03-15 23:44:34 -03:00
|
|
|
|
2021-07-29 16:58:02 +01:00
|
|
|
|
2018-03-15 23:44:34 -03:00
|
|
|
|
2023-11-28 09:54:37 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-05-04 14:38:01 -07:00
|
|
|
|
2018-03-15 23:44:34 -03:00
|
|
|
|
|
|
|
|
|
2018-08-04 15:05:04 +02:00
|
|
|
|
2018-08-04 15:05:19 +02:00
|
|
|
|
2024-05-04 14:38:01 -07:00
|
|
|
|
2025-08-15 20:16:27 -07:00
|
|
|
|
2018-03-15 23:44:34 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-03-10 15:49:22 -07:00
|
|
|
|
2011-02-05 18:51:38 -02:00
|
|
|
|
2025-03-10 15:49:22 -07:00
|
|
|
|
2023-03-20 14:22:35 -07:00
|
|
|
|
2019-11-04 11:10:00 -03:00
|
|
|
|
2011-02-05 18:51:38 -02:00
|
|
|
|
2021-07-29 16:58:02 +01:00
|
|
|
|
|
|
|
|
|
2023-11-28 09:54:37 -08:00
|
|
|
|
2021-07-29 16:58:02 +01:00
|
|
|
|
|
|
|
|
|
2011-02-05 18:51:38 -02:00
|
|
|
|
2024-05-04 14:38:01 -07:00
|
|
|
|
2021-07-29 16:58:02 +01:00
|
|
|
|
|
|
|
|
|
2011-02-05 18:51:38 -02:00
|
|
|
|
2021-07-29 16:58:02 +01:00
|
|
|
|
2011-02-05 18:51:38 -02:00
|
|
|
|
2017-11-15 12:20:08 +01:00
|
|
|
|
|
|
|
|
|
2023-11-28 09:54:37 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-05-04 14:38:01 -07:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
|
|
|
|
|
2025-03-10 15:49:22 -07:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
2017-10-11 17:01:38 +02:00
|
|
|
|
2011-02-05 18:51:38 -02:00
|
|
|
|
2011-02-04 09:45:46 -02:00
|
|
|
|
|
|
|
|
|
2013-12-18 17:10:15 -03:00
|
|
|
|
2014-02-20 10:32:53 +09:00
|
|
|
|
|
|
|
|
|
2016-05-03 13:54:44 +02:00
|
|
|
|
2014-02-20 10:32:53 +09:00
|
|
|
|
2018-03-15 16:54:11 -03:00
|
|
|
|
2018-03-15 17:04:53 -03:00
|
|
|
|
2018-08-04 15:05:03 +02:00
|
|
|
|
2018-08-04 15:05:15 +02:00
|
|
|
|
2018-03-15 17:04:53 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-08-03 14:13:28 -07:00
|
|
|
|
2018-08-04 15:05:09 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-08-04 15:05:15 +02:00
|
|
|
|
2018-08-04 15:05:09 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-03-15 17:04:53 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:29 -07:00
|
|
|
|
2018-03-15 19:12:39 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-03-20 17:20:43 -03:00
|
|
|
|
2018-03-15 19:12:39 -03:00
|
|
|
|
2018-03-20 17:20:43 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-03-15 19:12:39 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-03-20 17:20:43 -03:00
|
|
|
|
2018-03-15 19:12:39 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:29 -07:00
|
|
|
|
|
|
|
|
|
2018-03-15 19:12:39 -03:00
|
|
|
|
|
|
|
|
|
perf annotate: Compute average IPC and IPC coverage per symbol
Add support to 'perf report' annotate view or 'perf annotate --stdio2'
to aggregate the IPC derived from timed LBRs per symbol. We compute the
average IPC and the IPC coverage percentage.
For example:
$ perf annotate --stdio2
Percent IPC Cycle (Average IPC: 2.30, IPC Coverage: 54.8%)
Disassembly of section .text:
000000000003aac0 <random@@GLIBC_2.2.5>:
8.32 3.28 sub $0x18,%rsp
3.28 mov $0x1,%esi
3.28 xor %eax,%eax
3.28 cmpl $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x1e0
11.57 3.28 1 ↓ je 20
lock cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
↓ jne 29
↓ jmp 43
11.57 1.10 20: cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
0.00 1.10 1 ↓ je 43
29: lea __abort_msg@@GLIBC_PRIVATE+0x8a0,%rdi
sub $0x80,%rsp
→ callq __lll_lock_wait_private
add $0x80,%rsp
0.00 3.00 43: lea __ctype_b@GLIBC_2.2.5+0x38,%rdi
3.00 lea 0xc(%rsp),%rsi
8.49 3.00 1 → callq __random_r
7.91 1.94 cmpl $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x1e0
0.00 1.94 1 ↓ je 68
lock decl __abort_msg@@GLIBC_PRIVATE+0x8a0
↓ jne 70
↓ jmp 8a
0.00 2.00 68: decl __abort_msg@@GLIBC_PRIVATE+0x8a0
21.56 2.00 1 ↓ je 8a
70: lea __abort_msg@@GLIBC_PRIVATE+0x8a0,%rdi
sub $0x80,%rsp
→ callq __lll_unlock_wake_private
add $0x80,%rsp
21.56 2.90 8a: movslq 0xc(%rsp),%rax
2.90 add $0x18,%rsp
9.03 2.90 1 ← retq
It shows for this symbol the average IPC is 2.30 and the IPC coverage is
54.8%.
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Reviewed-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://lkml.kernel.org/r/1543586097-27632-2-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-11-30 21:54:54 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-03 12:19:04 -07:00
|
|
|
|
perf annotate: Compute average IPC and IPC coverage per symbol
Add support to 'perf report' annotate view or 'perf annotate --stdio2'
to aggregate the IPC derived from timed LBRs per symbol. We compute the
average IPC and the IPC coverage percentage.
For example:
$ perf annotate --stdio2
Percent IPC Cycle (Average IPC: 2.30, IPC Coverage: 54.8%)
Disassembly of section .text:
000000000003aac0 <random@@GLIBC_2.2.5>:
8.32 3.28 sub $0x18,%rsp
3.28 mov $0x1,%esi
3.28 xor %eax,%eax
3.28 cmpl $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x1e0
11.57 3.28 1 ↓ je 20
lock cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
↓ jne 29
↓ jmp 43
11.57 1.10 20: cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
0.00 1.10 1 ↓ je 43
29: lea __abort_msg@@GLIBC_PRIVATE+0x8a0,%rdi
sub $0x80,%rsp
→ callq __lll_lock_wait_private
add $0x80,%rsp
0.00 3.00 43: lea __ctype_b@GLIBC_2.2.5+0x38,%rdi
3.00 lea 0xc(%rsp),%rsi
8.49 3.00 1 → callq __random_r
7.91 1.94 cmpl $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x1e0
0.00 1.94 1 ↓ je 68
lock decl __abort_msg@@GLIBC_PRIVATE+0x8a0
↓ jne 70
↓ jmp 8a
0.00 2.00 68: decl __abort_msg@@GLIBC_PRIVATE+0x8a0
21.56 2.00 1 ↓ je 8a
70: lea __abort_msg@@GLIBC_PRIVATE+0x8a0,%rdi
sub $0x80,%rsp
→ callq __lll_unlock_wake_private
add $0x80,%rsp
21.56 2.90 8a: movslq 0xc(%rsp),%rax
2.90 add $0x18,%rsp
9.03 2.90 1 ← retq
It shows for this symbol the average IPC is 2.30 and the IPC coverage is
54.8%.
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Reviewed-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://lkml.kernel.org/r/1543586097-27632-2-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-11-30 21:54:54 +08:00
|
|
|
|
2023-11-03 12:19:04 -07:00
|
|
|
|
|
|
|
|
|
perf annotate: Compute average IPC and IPC coverage per symbol
Add support to 'perf report' annotate view or 'perf annotate --stdio2'
to aggregate the IPC derived from timed LBRs per symbol. We compute the
average IPC and the IPC coverage percentage.
For example:
$ perf annotate --stdio2
Percent IPC Cycle (Average IPC: 2.30, IPC Coverage: 54.8%)
Disassembly of section .text:
000000000003aac0 <random@@GLIBC_2.2.5>:
8.32 3.28 sub $0x18,%rsp
3.28 mov $0x1,%esi
3.28 xor %eax,%eax
3.28 cmpl $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x1e0
11.57 3.28 1 ↓ je 20
lock cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
↓ jne 29
↓ jmp 43
11.57 1.10 20: cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
0.00 1.10 1 ↓ je 43
29: lea __abort_msg@@GLIBC_PRIVATE+0x8a0,%rdi
sub $0x80,%rsp
→ callq __lll_lock_wait_private
add $0x80,%rsp
0.00 3.00 43: lea __ctype_b@GLIBC_2.2.5+0x38,%rdi
3.00 lea 0xc(%rsp),%rsi
8.49 3.00 1 → callq __random_r
7.91 1.94 cmpl $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x1e0
0.00 1.94 1 ↓ je 68
lock decl __abort_msg@@GLIBC_PRIVATE+0x8a0
↓ jne 70
↓ jmp 8a
0.00 2.00 68: decl __abort_msg@@GLIBC_PRIVATE+0x8a0
21.56 2.00 1 ↓ je 8a
70: lea __abort_msg@@GLIBC_PRIVATE+0x8a0,%rdi
sub $0x80,%rsp
→ callq __lll_unlock_wake_private
add $0x80,%rsp
21.56 2.90 8a: movslq 0xc(%rsp),%rax
2.90 add $0x18,%rsp
9.03 2.90 1 ← retq
It shows for this symbol the average IPC is 2.30 and the IPC coverage is
54.8%.
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Reviewed-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://lkml.kernel.org/r/1543586097-27632-2-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-11-30 21:54:54 +08:00
|
|
|
|
2023-11-03 12:19:04 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf annotate: Compute average IPC and IPC coverage per symbol
Add support to 'perf report' annotate view or 'perf annotate --stdio2'
to aggregate the IPC derived from timed LBRs per symbol. We compute the
average IPC and the IPC coverage percentage.
For example:
$ perf annotate --stdio2
Percent IPC Cycle (Average IPC: 2.30, IPC Coverage: 54.8%)
Disassembly of section .text:
000000000003aac0 <random@@GLIBC_2.2.5>:
8.32 3.28 sub $0x18,%rsp
3.28 mov $0x1,%esi
3.28 xor %eax,%eax
3.28 cmpl $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x1e0
11.57 3.28 1 ↓ je 20
lock cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
↓ jne 29
↓ jmp 43
11.57 1.10 20: cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
0.00 1.10 1 ↓ je 43
29: lea __abort_msg@@GLIBC_PRIVATE+0x8a0,%rdi
sub $0x80,%rsp
→ callq __lll_lock_wait_private
add $0x80,%rsp
0.00 3.00 43: lea __ctype_b@GLIBC_2.2.5+0x38,%rdi
3.00 lea 0xc(%rsp),%rsi
8.49 3.00 1 → callq __random_r
7.91 1.94 cmpl $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x1e0
0.00 1.94 1 ↓ je 68
lock decl __abort_msg@@GLIBC_PRIVATE+0x8a0
↓ jne 70
↓ jmp 8a
0.00 2.00 68: decl __abort_msg@@GLIBC_PRIVATE+0x8a0
21.56 2.00 1 ↓ je 8a
70: lea __abort_msg@@GLIBC_PRIVATE+0x8a0,%rdi
sub $0x80,%rsp
→ callq __lll_unlock_wake_private
add $0x80,%rsp
21.56 2.90 8a: movslq 0xc(%rsp),%rax
2.90 add $0x18,%rsp
9.03 2.90 1 ← retq
It shows for this symbol the average IPC is 2.30 and the IPC coverage is
54.8%.
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Reviewed-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://lkml.kernel.org/r/1543586097-27632-2-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-11-30 21:54:54 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf report: Display the branch counter histogram
Reusing the existing --total-cycles option to display the branch
counters. Add a new PERF_HPP_REPORT__BLOCK_BRANCH_COUNTER to display
the logged branch counter events. They are shown right after all the
cycle-related annotations.
Extend the 'struct block_info' to store and pass the branch counter
related information.
The annotation_br_cntr_entry() is to print the histogram of each branch
counter event. If the number of logged events is less than 4, the exact
number of the abbr name is printed. Otherwise, using '+' to stands for
more than 3 events.
Assume the number of logged events is less than 4.
The annotation_br_cntr_abbr_list() prints the branch counter's
abbreviation list. Press 'B' to display the list in the TUI mode.
$ perf record -e "{branch-instructions:ppp,branch-misses}:S" -j any,counter
$ perf report --total-cycles --stdio
# To display the perf.data header info, please use --header/--header-only options.
#
#
# Total Lost Samples: 0
#
# Samples: 1M of events 'anon group { branch-instructions:ppp, branch-misses }'
# Event count (approx.): 1610046
#
# Branch counter abbr list:
# branch-instructions:ppp = A
# branch-misses = B
# '-' No event occurs
# '+' Event occurrences may be lost due to branch counter saturated
#
# Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles Branch Counter [Program Block Range]
# ............... .............. ........... .......... .............. ..................
#
57.55% 2.5M 0.00% 3 |A |- | ...
25.27% 1.1M 0.00% 2 |AA |- | ...
15.61% 667.2K 0.00% 1 |A |- | ...
0.16% 6.9K 0.81% 575 |A |- | ...
0.16% 6.8K 1.38% 977 |AA |- | ...
0.16% 6.8K 0.04% 28 |AA |B | ...
0.15% 6.6K 1.33% 946 |A |- | ...
0.11% 4.5K 0.06% 46 |AAA+|- | ...
0.10% 4.4K 0.88% 624 |A |- | ...
0.09% 3.7K 0.74% 524 |AAA+|B | ...
With -v applied,
# Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles Branch Counter [Program Block Range]
# ............... .............. ........... .......... .............. ..................
#
57.55% 2.5M 0.00% 3 A=1 ,B=- ...
25.27% 1.1M 0.00% 2 A=2 ,B=- ...
15.61% 667.2K 0.00% 1 A=1 ,B=- ...
0.16% 6.9K 0.81% 575 A=1 ,B=- ...
0.16% 6.8K 1.38% 977 A=2 ,B=- ...
0.16% 6.8K 0.04% 28 A=2 ,B=1 ...
0.15% 6.6K 1.33% 946 A=1 ,B=- ...
0.11% 4.5K 0.06% 46 A=3+,B=- ...
0.10% 4.4K 0.88% 624 A=1 ,B=- ...
0.09% 3.7K 0.74% 524 A=3+,B=1 ...
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20240813160208.2493643-7-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-08-13 09:02:05 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:35 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:30 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:35 -07:00
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:30 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:35 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf annotate: Hide data-type for stack operation and canary
It's mostly unnecessary to print when it has no actual type information
like in the stack operations and canary. Let's have them if -v option
is given.
Before:
$ perf annotate --code-with-type
...
: 0 0xd640 <_dl_relocate_object>:
0.00 : 0: endbr64
0.00 : 4: pushq %rbp # data-type: (stack operation)
0.00 : 5: movq %rsp, %rbp
0.00 : 8: pushq %r15 # data-type: (stack operation)
0.00 : a: pushq %r14 # data-type: (stack operation)
0.00 : c: pushq %r13 # data-type: (stack operation)
0.00 : e: pushq %r12 # data-type: (stack operation)
0.00 : 10: pushq %rbx # data-type: (stack operation)
0.00 : 11: subq $0xf8, %rsp
...
0.00 : d4: testl %eax, %eax
0.00 : d6: jne 0xf424
0.00 : dc: movq 0xf0(%r14), %rbx # data-type: struct link_map +0xf0
0.00 : e3: testq %rbx, %rbx
0.00 : e6: jne 0xf2dd
0.00 : ec: cmpq $0, 0xf8(%r14) # data-type: struct link_map +0xf8
...
After:
: 0 0xd640 <_dl_relocate_object>:
0.00 : 0: endbr64
0.00 : 4: pushq %rbp
0.00 : 5: movq %rsp, %rbp
0.00 : 8: pushq %r15
0.00 : a: pushq %r14
0.00 : c: pushq %r13
0.00 : e: pushq %r12
0.00 : 10: pushq %rbx
0.00 : 11: subq $0xf8, %rsp
...
0.00 : d4: testl %eax, %eax
0.00 : d6: jne 0xf424
0.00 : dc: movq 0xf0(%r14), %rbx # data-type: struct link_map +0xf0
0.00 : e3: testq %rbx, %rbx
0.00 : e6: jne 0xf2dd
0.00 : ec: cmpq $0, 0xf8(%r14) # data-type: struct link_map +0xf8
...
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250816031635.25318-11-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2025-08-15 20:16:33 -07:00
|
|
|
|
2025-08-15 20:16:30 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:26 -07:00
|
|
|
|
2025-08-15 20:16:27 -07:00
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:26 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-03-15 17:54:36 -03:00
|
|
|
|
2018-03-15 19:12:39 -03:00
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:26 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-03 12:19:04 -07:00
|
|
|
|
2023-11-03 12:19:03 -07:00
|
|
|
|
2018-03-15 17:54:36 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-08-03 14:13:28 -07:00
|
|
|
|
2018-08-04 15:05:09 +02:00
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:26 -07:00
|
|
|
|
|
|
|
|
|
2018-08-04 15:05:09 +02:00
|
|
|
|
|
|
|
|
|
2020-02-13 12:13:00 +05:30
|
|
|
|
2018-08-04 15:05:05 +02:00
|
|
|
|
2020-02-13 12:13:01 +05:30
|
|
|
|
2024-08-03 14:13:30 -07:00
|
|
|
|
2018-08-04 15:05:05 +02:00
|
|
|
|
2018-03-15 17:54:36 -03:00
|
|
|
|
2024-08-03 14:13:30 -07:00
|
|
|
|
2018-03-15 17:54:36 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-03-15 19:12:39 -03:00
|
|
|
|
2018-03-15 17:54:36 -03:00
|
|
|
|
2018-03-15 19:12:39 -03:00
|
|
|
|
2020-02-13 12:13:00 +05:30
|
|
|
|
2020-02-13 12:13:01 +05:30
|
|
|
|
2018-03-15 17:54:36 -03:00
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:28 -07:00
|
|
|
|
2018-03-15 17:54:36 -03:00
|
|
|
|
2023-11-03 12:19:04 -07:00
|
|
|
|
2023-11-03 12:19:03 -07:00
|
|
|
|
|
|
|
|
|
2018-03-15 17:54:36 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-28 09:54:37 -08:00
|
|
|
|
2023-11-03 12:19:03 -07:00
|
|
|
|
perf annotate: Create hotkey 'c' to show min/max cycles
In the 'perf annotate' view, a new hotkey 'c' is created for showing the
min/max cycles.
For example, when press 'c', the annotate view is:
Percent│ IPC Cycle(min/max)
│
│
│ Disassembly of section .text:
│
│ 000000000003aab0 <random@@GLIBC_2.2.5>:
8.22 │3.92 sub $0x18,%rsp
│3.92 mov $0x1,%esi
│3.92 xor %eax,%eax
│3.92 cmpl $0x0,argp_program_version_hook@@G
│3.92 1(2/1) ↓ je 20
│ lock cmpxchg %esi,__abort_msg@@GLIBC_P
│ ↓ jne 29
│ ↓ jmp 43
│1.10 20: cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+
8.93 │1.10 1(5/1) ↓ je 43
When press 'c' again, the annotate view is switched back:
Percent│ IPC Cycle
│
│
│ Disassembly of section .text:
│
│ 000000000003aab0 <random@@GLIBC_2.2.5>:
8.22 │3.92 sub $0x18,%rsp
│3.92 mov $0x1,%esi
│3.92 xor %eax,%eax
│3.92 cmpl $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x
│3.92 1 ↓ je 20
│ lock cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
│ ↓ jne 29
│ ↓ jmp 43
│1.10 20: cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
8.93 │1.10 1 ↓ je 43
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://lkml.kernel.org/r/1526569118-14217-3-git-send-email-yao.jin@linux.intel.com
[ Rename all maxmin to minmax ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-05-17 22:58:38 +08:00
|
|
|
|
2023-11-03 12:19:03 -07:00
|
|
|
|
perf annotate: Create hotkey 'c' to show min/max cycles
In the 'perf annotate' view, a new hotkey 'c' is created for showing the
min/max cycles.
For example, when press 'c', the annotate view is:
Percent│ IPC Cycle(min/max)
│
│
│ Disassembly of section .text:
│
│ 000000000003aab0 <random@@GLIBC_2.2.5>:
8.22 │3.92 sub $0x18,%rsp
│3.92 mov $0x1,%esi
│3.92 xor %eax,%eax
│3.92 cmpl $0x0,argp_program_version_hook@@G
│3.92 1(2/1) ↓ je 20
│ lock cmpxchg %esi,__abort_msg@@GLIBC_P
│ ↓ jne 29
│ ↓ jmp 43
│1.10 20: cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+
8.93 │1.10 1(5/1) ↓ je 43
When press 'c' again, the annotate view is switched back:
Percent│ IPC Cycle
│
│
│ Disassembly of section .text:
│
│ 000000000003aab0 <random@@GLIBC_2.2.5>:
8.22 │3.92 sub $0x18,%rsp
│3.92 mov $0x1,%esi
│3.92 xor %eax,%eax
│3.92 cmpl $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x
│3.92 1 ↓ je 20
│ lock cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
│ ↓ jne 29
│ ↓ jmp 43
│1.10 20: cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
8.93 │1.10 1 ↓ je 43
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://lkml.kernel.org/r/1526569118-14217-3-git-send-email-yao.jin@linux.intel.com
[ Rename all maxmin to minmax ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-05-17 22:58:38 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-03 12:19:03 -07:00
|
|
|
|
|
|
|
|
|
perf annotate: Create hotkey 'c' to show min/max cycles
In the 'perf annotate' view, a new hotkey 'c' is created for showing the
min/max cycles.
For example, when press 'c', the annotate view is:
Percent│ IPC Cycle(min/max)
│
│
│ Disassembly of section .text:
│
│ 000000000003aab0 <random@@GLIBC_2.2.5>:
8.22 │3.92 sub $0x18,%rsp
│3.92 mov $0x1,%esi
│3.92 xor %eax,%eax
│3.92 cmpl $0x0,argp_program_version_hook@@G
│3.92 1(2/1) ↓ je 20
│ lock cmpxchg %esi,__abort_msg@@GLIBC_P
│ ↓ jne 29
│ ↓ jmp 43
│1.10 20: cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+
8.93 │1.10 1(5/1) ↓ je 43
When press 'c' again, the annotate view is switched back:
Percent│ IPC Cycle
│
│
│ Disassembly of section .text:
│
│ 000000000003aab0 <random@@GLIBC_2.2.5>:
8.22 │3.92 sub $0x18,%rsp
│3.92 mov $0x1,%esi
│3.92 xor %eax,%eax
│3.92 cmpl $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x
│3.92 1 ↓ je 20
│ lock cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
│ ↓ jne 29
│ ↓ jmp 43
│1.10 20: cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
8.93 │1.10 1 ↓ je 43
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://lkml.kernel.org/r/1526569118-14217-3-git-send-email-yao.jin@linux.intel.com
[ Rename all maxmin to minmax ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-05-17 22:58:38 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf annotate: Compute average IPC and IPC coverage per symbol
Add support to 'perf report' annotate view or 'perf annotate --stdio2'
to aggregate the IPC derived from timed LBRs per symbol. We compute the
average IPC and the IPC coverage percentage.
For example:
$ perf annotate --stdio2
Percent IPC Cycle (Average IPC: 2.30, IPC Coverage: 54.8%)
Disassembly of section .text:
000000000003aac0 <random@@GLIBC_2.2.5>:
8.32 3.28 sub $0x18,%rsp
3.28 mov $0x1,%esi
3.28 xor %eax,%eax
3.28 cmpl $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x1e0
11.57 3.28 1 ↓ je 20
lock cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
↓ jne 29
↓ jmp 43
11.57 1.10 20: cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
0.00 1.10 1 ↓ je 43
29: lea __abort_msg@@GLIBC_PRIVATE+0x8a0,%rdi
sub $0x80,%rsp
→ callq __lll_lock_wait_private
add $0x80,%rsp
0.00 3.00 43: lea __ctype_b@GLIBC_2.2.5+0x38,%rdi
3.00 lea 0xc(%rsp),%rsi
8.49 3.00 1 → callq __random_r
7.91 1.94 cmpl $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x1e0
0.00 1.94 1 ↓ je 68
lock decl __abort_msg@@GLIBC_PRIVATE+0x8a0
↓ jne 70
↓ jmp 8a
0.00 2.00 68: decl __abort_msg@@GLIBC_PRIVATE+0x8a0
21.56 2.00 1 ↓ je 8a
70: lea __abort_msg@@GLIBC_PRIVATE+0x8a0,%rdi
sub $0x80,%rsp
→ callq __lll_unlock_wake_private
add $0x80,%rsp
21.56 2.90 8a: movslq 0xc(%rsp),%rax
2.90 add $0x18,%rsp
9.03 2.90 1 ← retq
It shows for this symbol the average IPC is 2.30 and the IPC coverage is
54.8%.
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Reviewed-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://lkml.kernel.org/r/1543586097-27632-2-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-11-30 21:54:54 +08:00
|
|
|
|
perf annotate: Display the branch counter histogram
Display the branch counter histogram in the annotation view.
Press 'B' to display the branch counter's abbreviation list as well.
Samples: 1M of events 'anon group { branch-instructions:ppp, branch-misses }',
4000 Hz, Event count (approx.):
f3 /home/sdp/test/tchain_edit [Percent: local period]
Percent │ IPC Cycle Branch Counter (Average IPC: 1.39, IPC Coverage: 29.4%)
│ 0000000000401755 <f3>:
0.00 0.00 │ endbr64
│ push %rbp
│ mov %rsp,%rbp
│ movl $0x0,-0x4(%rbp)
0.00 0.00 │1.33 3 |A |- | ↓ jmp 25
11.03 11.03 │ 11: mov -0x4(%rbp),%eax
│ and $0x1,%eax
│ test %eax,%eax
17.13 17.13 │2.41 1 |A |- | ↓ je 21
│ addl $0x1,-0x4(%rbp)
21.84 21.84 │2.22 2 |AA |- | ↓ jmp 25
17.13 17.13 │ 21: addl $0x1,-0x4(%rbp)
21.84 21.84 │ 25: cmpl $0x270f,-0x4(%rbp)
11.03 11.03 │0.61 3 |A |- | ↑ jle 11
│ nop
│ pop %rbp
0.00 0.00 │0.24 20 |AA |B | ← ret
Originally-by: Tinghao Zhang <tinghao.zhang@intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20240813160208.2493643-8-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-08-13 09:02:06 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf annotate: Compute average IPC and IPC coverage per symbol
Add support to 'perf report' annotate view or 'perf annotate --stdio2'
to aggregate the IPC derived from timed LBRs per symbol. We compute the
average IPC and the IPC coverage percentage.
For example:
$ perf annotate --stdio2
Percent IPC Cycle (Average IPC: 2.30, IPC Coverage: 54.8%)
Disassembly of section .text:
000000000003aac0 <random@@GLIBC_2.2.5>:
8.32 3.28 sub $0x18,%rsp
3.28 mov $0x1,%esi
3.28 xor %eax,%eax
3.28 cmpl $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x1e0
11.57 3.28 1 ↓ je 20
lock cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
↓ jne 29
↓ jmp 43
11.57 1.10 20: cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
0.00 1.10 1 ↓ je 43
29: lea __abort_msg@@GLIBC_PRIVATE+0x8a0,%rdi
sub $0x80,%rsp
→ callq __lll_lock_wait_private
add $0x80,%rsp
0.00 3.00 43: lea __ctype_b@GLIBC_2.2.5+0x38,%rdi
3.00 lea 0xc(%rsp),%rsi
8.49 3.00 1 → callq __random_r
7.91 1.94 cmpl $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x1e0
0.00 1.94 1 ↓ je 68
lock decl __abort_msg@@GLIBC_PRIVATE+0x8a0
↓ jne 70
↓ jmp 8a
0.00 2.00 68: decl __abort_msg@@GLIBC_PRIVATE+0x8a0
21.56 2.00 1 ↓ je 8a
70: lea __abort_msg@@GLIBC_PRIVATE+0x8a0,%rdi
sub $0x80,%rsp
→ callq __lll_unlock_wake_private
add $0x80,%rsp
21.56 2.90 8a: movslq 0xc(%rsp),%rax
2.90 add $0x18,%rsp
9.03 2.90 1 ← retq
It shows for this symbol the average IPC is 2.30 and the IPC coverage is
54.8%.
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Reviewed-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://lkml.kernel.org/r/1543586097-27632-2-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-11-30 21:54:54 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-03-15 17:54:36 -03:00
|
|
|
|
2025-08-15 20:16:28 -07:00
|
|
|
|
2018-03-15 17:54:36 -03:00
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:28 -07:00
|
|
|
|
2018-03-15 19:12:39 -03:00
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:28 -07:00
|
|
|
|
2018-03-15 19:12:39 -03:00
|
|
|
|
2023-11-28 09:54:37 -08:00
|
|
|
|
2024-04-04 10:57:13 -07:00
|
|
|
|
|
|
|
|
|
2018-03-15 19:12:39 -03:00
|
|
|
|
2024-04-04 10:57:13 -07:00
|
|
|
|
|
|
|
|
|
2018-03-15 19:12:39 -03:00
|
|
|
|
2025-08-15 20:16:28 -07:00
|
|
|
|
|
|
|
|
|
2018-03-15 19:12:39 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-28 09:54:37 -08:00
|
|
|
|
2024-04-04 10:57:16 -07:00
|
|
|
|
2018-03-15 19:12:39 -03:00
|
|
|
|
2023-11-28 09:54:37 -08:00
|
|
|
|
2018-03-15 19:12:39 -03:00
|
|
|
|
|
|
|
|
|
2018-04-11 10:30:03 -03:00
|
|
|
|
2023-11-28 09:54:37 -08:00
|
|
|
|
|
|
|
|
|
2018-03-15 19:12:39 -03:00
|
|
|
|
|
|
|
|
|
2024-04-04 10:57:13 -07:00
|
|
|
|
2018-03-15 19:12:39 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-04-11 10:30:03 -03:00
|
|
|
|
2018-03-15 19:12:39 -03:00
|
|
|
|
2024-04-04 10:57:13 -07:00
|
|
|
|
2018-04-11 10:30:03 -03:00
|
|
|
|
2023-11-28 09:54:37 -08:00
|
|
|
|
2018-04-11 10:30:03 -03:00
|
|
|
|
2023-11-28 09:54:37 -08:00
|
|
|
|
2018-04-11 10:30:03 -03:00
|
|
|
|
2018-03-15 19:12:39 -03:00
|
|
|
|
|
|
|
|
|
2024-04-04 10:57:13 -07:00
|
|
|
|
2018-03-15 19:12:39 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:28 -07:00
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:30 -07:00
|
|
|
|
|
|
|
|
|
2018-03-15 19:12:39 -03:00
|
|
|
|
2025-08-15 20:16:30 -07:00
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:27 -07:00
|
|
|
|
2025-08-15 20:16:30 -07:00
|
|
|
|
|
|
|
|
|
2018-03-15 19:12:39 -03:00
|
|
|
|
|
|
|
|
|
2018-03-15 17:54:36 -03:00
|
|
|
|
|
|
|
|
|
2019-11-04 11:10:00 -03:00
|
|
|
|
2023-11-28 09:54:37 -08:00
|
|
|
|
2018-03-15 16:54:11 -03:00
|
|
|
|
2019-11-04 11:10:00 -03:00
|
|
|
|
2018-03-15 16:54:11 -03:00
|
|
|
|
|
|
|
|
|
2024-08-03 14:13:29 -07:00
|
|
|
|
2018-03-15 16:54:11 -03:00
|
|
|
|
2023-11-28 09:54:37 -08:00
|
|
|
|
2018-03-15 16:54:11 -03:00
|
|
|
|
2024-04-04 10:57:12 -07:00
|
|
|
|
2018-03-15 16:54:11 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-04-04 10:57:12 -07:00
|
|
|
|
2018-03-15 16:54:11 -03:00
|
|
|
|
2023-11-03 12:19:03 -07:00
|
|
|
|
perf annotate: Display the branch counter histogram
Display the branch counter histogram in the annotation view.
Press 'B' to display the branch counter's abbreviation list as well.
Samples: 1M of events 'anon group { branch-instructions:ppp, branch-misses }',
4000 Hz, Event count (approx.):
f3 /home/sdp/test/tchain_edit [Percent: local period]
Percent │ IPC Cycle Branch Counter (Average IPC: 1.39, IPC Coverage: 29.4%)
│ 0000000000401755 <f3>:
0.00 0.00 │ endbr64
│ push %rbp
│ mov %rsp,%rbp
│ movl $0x0,-0x4(%rbp)
0.00 0.00 │1.33 3 |A |- | ↓ jmp 25
11.03 11.03 │ 11: mov -0x4(%rbp),%eax
│ and $0x1,%eax
│ test %eax,%eax
17.13 17.13 │2.41 1 |A |- | ↓ je 21
│ addl $0x1,-0x4(%rbp)
21.84 21.84 │2.22 2 |AA |- | ↓ jmp 25
17.13 17.13 │ 21: addl $0x1,-0x4(%rbp)
21.84 21.84 │ 25: cmpl $0x270f,-0x4(%rbp)
11.03 11.03 │0.61 3 |A |- | ↑ jle 11
│ nop
│ pop %rbp
0.00 0.00 │0.24 20 |AA |B | ← ret
Originally-by: Tinghao Zhang <tinghao.zhang@intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20240813160208.2493643-8-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-08-13 09:02:06 -07:00
|
|
|
|
2023-11-03 12:19:03 -07:00
|
|
|
|
2024-04-04 10:57:12 -07:00
|
|
|
|
2023-11-03 12:19:03 -07:00
|
|
|
|
2018-03-15 16:54:11 -03:00
|
|
|
|
|
|
|
|
|
2021-11-11 19:51:23 -08:00
|
|
|
|
2018-03-15 16:54:11 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-03-16 14:33:38 -03:00
|
|
|
|
2025-01-23 20:38:56 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf annotate: Make perf config effective
perf default config set by user in [annotate] section is totally ignored
by annotate code. Fix it.
Before:
$ ./perf config
annotate.hide_src_code=true
annotate.show_nr_jumps=true
annotate.show_nr_samples=true
$ ./perf annotate shash
│ unsigned h = 0;
│ movl $0x0,-0xc(%rbp)
│ while (*s)
│ ↓ jmp 44
│ h = 65599 * h + *s++;
11.33 │24: mov -0xc(%rbp),%eax
43.50 │ imul $0x1003f,%eax,%ecx
│ mov -0x18(%rbp),%rax
After:
│ movl $0x0,-0xc(%rbp)
│ ↓ jmp 44
1 │1 24: mov -0xc(%rbp),%eax
4 │ imul $0x1003f,%eax,%ecx
│ mov -0x18(%rbp),%rax
Note that we have removed show_nr_samples and show_total_period from
annotation_options because they are not used. Instead of them we use
symbol_conf.show_nr_samples and symbol_conf.show_total_period.
Committer testing:
Using 'perf annotate --stdio2' to use the TUI rendering but emitting the output to stdio:
# perf config
#
# perf config annotate.hide_src_code=true
# perf config
annotate.hide_src_code=true
#
# perf config annotate.show_nr_jumps=true
# perf config annotate.show_nr_samples=true
# perf config
annotate.hide_src_code=true
annotate.show_nr_jumps=true
annotate.show_nr_samples=true
#
#
Before:
# perf annotate --stdio2 ObjectInstance::weak_pointer_was_finalized
Samples: 1 of event 'cycles', 4000 Hz, Event count (approx.): 830873, [percent: local period]
ObjectInstance::weak_pointer_was_finalized() /usr/lib64/libgjs.so.0.0.0
Percent
00000000000609f0 <ObjectInstance::weak_pointer_was_finalized()@@Base>:
endbr64
cmpq $0x0,0x20(%rdi)
↓ je 10
xor %eax,%eax
← retq
xchg %ax,%ax
100.00 10: push %rbp
cmpq $0x0,0x18(%rdi)
mov %rdi,%rbp
↓ jne 20
1b: xor %eax,%eax
pop %rbp
← retq
nop
20: lea 0x18(%rdi),%rdi
→ callq JS_UpdateWeakPointerAfterGC(JS::Heap<JSObject*
cmpq $0x0,0x18(%rbp)
↑ jne 1b
mov %rbp,%rdi
→ callq ObjectBase::jsobj_addr() const@plt
mov $0x1,%eax
pop %rbp
← retq
#
After:
# perf annotate --stdio2 ObjectInstance::weak_pointer_was_finalized 2> /dev/null
Samples: 1 of event 'cycles', 4000 Hz, Event count (approx.): 830873, [percent: local period]
ObjectInstance::weak_pointer_was_finalized() /usr/lib64/libgjs.so.0.0.0
Samples endbr64
cmpq $0x0,0x20(%rdi)
↓ je 10
xor %eax,%eax
← retq
xchg %ax,%ax
1 1 10: push %rbp
cmpq $0x0,0x18(%rdi)
mov %rdi,%rbp
↓ jne 20
1 1b: xor %eax,%eax
pop %rbp
← retq
nop
1 20: lea 0x18(%rdi),%rdi
→ callq JS_UpdateWeakPointerAfterGC(JS::Heap<JSObject*
cmpq $0x0,0x18(%rbp)
↑ jne 1b
mov %rbp,%rdi
→ callq ObjectBase::jsobj_addr() const@plt
mov $0x1,%eax
pop %rbp
← retq
#
# perf config annotate.show_nr_jumps
annotate.show_nr_jumps=true
# perf config annotate.show_nr_jumps=false
# perf config annotate.show_nr_jumps
annotate.show_nr_jumps=false
#
# perf annotate --stdio2 ObjectInstance::weak_pointer_was_finalized 2> /dev/null
Samples: 1 of event 'cycles', 4000 Hz, Event count (approx.): 830873, [percent: local period]
ObjectInstance::weak_pointer_was_finalized() /usr/lib64/libgjs.so.0.0.0
Samples endbr64
cmpq $0x0,0x20(%rdi)
↓ je 10
xor %eax,%eax
← retq
xchg %ax,%ax
1 10: push %rbp
cmpq $0x0,0x18(%rdi)
mov %rdi,%rbp
↓ jne 20
1b: xor %eax,%eax
pop %rbp
← retq
nop
20: lea 0x18(%rdi),%rdi
→ callq JS_UpdateWeakPointerAfterGC(JS::Heap<JSObject*
cmpq $0x0,0x18(%rbp)
↑ jne 1b
mov %rbp,%rdi
→ callq ObjectBase::jsobj_addr() const@plt
mov $0x1,%eax
pop %rbp
← retq
#
Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Changbin Du <changbin.du@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: Taeung Song <treeze.taeung@gmail.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Yisheng Xie <xieyisheng1@huawei.com>
Link: http://lore.kernel.org/lkml/20200213064306.160480-6-ravi.bangoria@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-02-13 12:13:03 +05:30
|
|
|
|
2018-03-16 14:33:38 -03:00
|
|
|
|
perf annotate: Make perf config effective
perf default config set by user in [annotate] section is totally ignored
by annotate code. Fix it.
Before:
$ ./perf config
annotate.hide_src_code=true
annotate.show_nr_jumps=true
annotate.show_nr_samples=true
$ ./perf annotate shash
│ unsigned h = 0;
│ movl $0x0,-0xc(%rbp)
│ while (*s)
│ ↓ jmp 44
│ h = 65599 * h + *s++;
11.33 │24: mov -0xc(%rbp),%eax
43.50 │ imul $0x1003f,%eax,%ecx
│ mov -0x18(%rbp),%rax
After:
│ movl $0x0,-0xc(%rbp)
│ ↓ jmp 44
1 │1 24: mov -0xc(%rbp),%eax
4 │ imul $0x1003f,%eax,%ecx
│ mov -0x18(%rbp),%rax
Note that we have removed show_nr_samples and show_total_period from
annotation_options because they are not used. Instead of them we use
symbol_conf.show_nr_samples and symbol_conf.show_total_period.
Committer testing:
Using 'perf annotate --stdio2' to use the TUI rendering but emitting the output to stdio:
# perf config
#
# perf config annotate.hide_src_code=true
# perf config
annotate.hide_src_code=true
#
# perf config annotate.show_nr_jumps=true
# perf config annotate.show_nr_samples=true
# perf config
annotate.hide_src_code=true
annotate.show_nr_jumps=true
annotate.show_nr_samples=true
#
#
Before:
# perf annotate --stdio2 ObjectInstance::weak_pointer_was_finalized
Samples: 1 of event 'cycles', 4000 Hz, Event count (approx.): 830873, [percent: local period]
ObjectInstance::weak_pointer_was_finalized() /usr/lib64/libgjs.so.0.0.0
Percent
00000000000609f0 <ObjectInstance::weak_pointer_was_finalized()@@Base>:
endbr64
cmpq $0x0,0x20(%rdi)
↓ je 10
xor %eax,%eax
← retq
xchg %ax,%ax
100.00 10: push %rbp
cmpq $0x0,0x18(%rdi)
mov %rdi,%rbp
↓ jne 20
1b: xor %eax,%eax
pop %rbp
← retq
nop
20: lea 0x18(%rdi),%rdi
→ callq JS_UpdateWeakPointerAfterGC(JS::Heap<JSObject*
cmpq $0x0,0x18(%rbp)
↑ jne 1b
mov %rbp,%rdi
→ callq ObjectBase::jsobj_addr() const@plt
mov $0x1,%eax
pop %rbp
← retq
#
After:
# perf annotate --stdio2 ObjectInstance::weak_pointer_was_finalized 2> /dev/null
Samples: 1 of event 'cycles', 4000 Hz, Event count (approx.): 830873, [percent: local period]
ObjectInstance::weak_pointer_was_finalized() /usr/lib64/libgjs.so.0.0.0
Samples endbr64
cmpq $0x0,0x20(%rdi)
↓ je 10
xor %eax,%eax
← retq
xchg %ax,%ax
1 1 10: push %rbp
cmpq $0x0,0x18(%rdi)
mov %rdi,%rbp
↓ jne 20
1 1b: xor %eax,%eax
pop %rbp
← retq
nop
1 20: lea 0x18(%rdi),%rdi
→ callq JS_UpdateWeakPointerAfterGC(JS::Heap<JSObject*
cmpq $0x0,0x18(%rbp)
↑ jne 1b
mov %rbp,%rdi
→ callq ObjectBase::jsobj_addr() const@plt
mov $0x1,%eax
pop %rbp
← retq
#
# perf config annotate.show_nr_jumps
annotate.show_nr_jumps=true
# perf config annotate.show_nr_jumps=false
# perf config annotate.show_nr_jumps
annotate.show_nr_jumps=false
#
# perf annotate --stdio2 ObjectInstance::weak_pointer_was_finalized 2> /dev/null
Samples: 1 of event 'cycles', 4000 Hz, Event count (approx.): 830873, [percent: local period]
ObjectInstance::weak_pointer_was_finalized() /usr/lib64/libgjs.so.0.0.0
Samples endbr64
cmpq $0x0,0x20(%rdi)
↓ je 10
xor %eax,%eax
← retq
xchg %ax,%ax
1 10: push %rbp
cmpq $0x0,0x18(%rdi)
mov %rdi,%rbp
↓ jne 20
1b: xor %eax,%eax
pop %rbp
← retq
nop
20: lea 0x18(%rdi),%rdi
→ callq JS_UpdateWeakPointerAfterGC(JS::Heap<JSObject*
cmpq $0x0,0x18(%rbp)
↑ jne 1b
mov %rbp,%rdi
→ callq ObjectBase::jsobj_addr() const@plt
mov $0x1,%eax
pop %rbp
← retq
#
Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Changbin Du <changbin.du@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: Taeung Song <treeze.taeung@gmail.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Yisheng Xie <xieyisheng1@huawei.com>
Link: http://lore.kernel.org/lkml/20200213064306.160480-6-ravi.bangoria@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-02-13 12:13:03 +05:30
|
|
|
|
2018-03-16 14:33:38 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf annotate: Make perf config effective
perf default config set by user in [annotate] section is totally ignored
by annotate code. Fix it.
Before:
$ ./perf config
annotate.hide_src_code=true
annotate.show_nr_jumps=true
annotate.show_nr_samples=true
$ ./perf annotate shash
│ unsigned h = 0;
│ movl $0x0,-0xc(%rbp)
│ while (*s)
│ ↓ jmp 44
│ h = 65599 * h + *s++;
11.33 │24: mov -0xc(%rbp),%eax
43.50 │ imul $0x1003f,%eax,%ecx
│ mov -0x18(%rbp),%rax
After:
│ movl $0x0,-0xc(%rbp)
│ ↓ jmp 44
1 │1 24: mov -0xc(%rbp),%eax
4 │ imul $0x1003f,%eax,%ecx
│ mov -0x18(%rbp),%rax
Note that we have removed show_nr_samples and show_total_period from
annotation_options because they are not used. Instead of them we use
symbol_conf.show_nr_samples and symbol_conf.show_total_period.
Committer testing:
Using 'perf annotate --stdio2' to use the TUI rendering but emitting the output to stdio:
# perf config
#
# perf config annotate.hide_src_code=true
# perf config
annotate.hide_src_code=true
#
# perf config annotate.show_nr_jumps=true
# perf config annotate.show_nr_samples=true
# perf config
annotate.hide_src_code=true
annotate.show_nr_jumps=true
annotate.show_nr_samples=true
#
#
Before:
# perf annotate --stdio2 ObjectInstance::weak_pointer_was_finalized
Samples: 1 of event 'cycles', 4000 Hz, Event count (approx.): 830873, [percent: local period]
ObjectInstance::weak_pointer_was_finalized() /usr/lib64/libgjs.so.0.0.0
Percent
00000000000609f0 <ObjectInstance::weak_pointer_was_finalized()@@Base>:
endbr64
cmpq $0x0,0x20(%rdi)
↓ je 10
xor %eax,%eax
← retq
xchg %ax,%ax
100.00 10: push %rbp
cmpq $0x0,0x18(%rdi)
mov %rdi,%rbp
↓ jne 20
1b: xor %eax,%eax
pop %rbp
← retq
nop
20: lea 0x18(%rdi),%rdi
→ callq JS_UpdateWeakPointerAfterGC(JS::Heap<JSObject*
cmpq $0x0,0x18(%rbp)
↑ jne 1b
mov %rbp,%rdi
→ callq ObjectBase::jsobj_addr() const@plt
mov $0x1,%eax
pop %rbp
← retq
#
After:
# perf annotate --stdio2 ObjectInstance::weak_pointer_was_finalized 2> /dev/null
Samples: 1 of event 'cycles', 4000 Hz, Event count (approx.): 830873, [percent: local period]
ObjectInstance::weak_pointer_was_finalized() /usr/lib64/libgjs.so.0.0.0
Samples endbr64
cmpq $0x0,0x20(%rdi)
↓ je 10
xor %eax,%eax
← retq
xchg %ax,%ax
1 1 10: push %rbp
cmpq $0x0,0x18(%rdi)
mov %rdi,%rbp
↓ jne 20
1 1b: xor %eax,%eax
pop %rbp
← retq
nop
1 20: lea 0x18(%rdi),%rdi
→ callq JS_UpdateWeakPointerAfterGC(JS::Heap<JSObject*
cmpq $0x0,0x18(%rbp)
↑ jne 1b
mov %rbp,%rdi
→ callq ObjectBase::jsobj_addr() const@plt
mov $0x1,%eax
pop %rbp
← retq
#
# perf config annotate.show_nr_jumps
annotate.show_nr_jumps=true
# perf config annotate.show_nr_jumps=false
# perf config annotate.show_nr_jumps
annotate.show_nr_jumps=false
#
# perf annotate --stdio2 ObjectInstance::weak_pointer_was_finalized 2> /dev/null
Samples: 1 of event 'cycles', 4000 Hz, Event count (approx.): 830873, [percent: local period]
ObjectInstance::weak_pointer_was_finalized() /usr/lib64/libgjs.so.0.0.0
Samples endbr64
cmpq $0x0,0x20(%rdi)
↓ je 10
xor %eax,%eax
← retq
xchg %ax,%ax
1 10: push %rbp
cmpq $0x0,0x18(%rdi)
mov %rdi,%rbp
↓ jne 20
1b: xor %eax,%eax
pop %rbp
← retq
nop
20: lea 0x18(%rdi),%rdi
→ callq JS_UpdateWeakPointerAfterGC(JS::Heap<JSObject*
cmpq $0x0,0x18(%rbp)
↑ jne 1b
mov %rbp,%rdi
→ callq ObjectBase::jsobj_addr() const@plt
mov $0x1,%eax
pop %rbp
← retq
#
Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Changbin Du <changbin.du@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: Taeung Song <treeze.taeung@gmail.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Yisheng Xie <xieyisheng1@huawei.com>
Link: http://lore.kernel.org/lkml/20200213064306.160480-6-ravi.bangoria@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-02-13 12:13:03 +05:30
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf disasm: Allow configuring what disassemblers to use
The perf tools annotation code used for a long time parsing the output
of binutils's objdump (or its reimplementations, like llvm's) to then
parse and augment it with samples, allow navigation, etc.
More recently disassemblers from the capstone and llvm (libraries, not
parsing the output of tools using those libraries to mimic binutils's
objdump output) were introduced.
So when all those methods are available, there is a static preference
for a series of attempts of disassembling a binary, with the 'llvm,
capstone, objdump' sequence being hard coded.
This patch allows users to change that sequence, specifying via a 'perf
config' 'annotate.disassemblers' entry which and in what order
disassemblers should be attempted.
As alluded to in the comments in the source code of this series, this
flexibility is useful for users and developers alike, elliminating the
requirement to rebuild the tool with some specific set of libraries to
see how the output of disassembling would be for one of these methods.
root@x1:~# rm -f ~/.perfconfig
root@x1:~# perf annotate -v --stdio2 update_load_avg
<SNIP>
symbol__disassemble:
filename=/usr/lib/debug/lib/modules/6.11.4-201.fc40.x86_64/vmlinux,
sym=update_load_avg, start=0xffffffffb6148fe0, en>
annotating [0x6ff7170]
/usr/lib/debug/lib/modules/6.11.4-201.fc40.x86_64/vmlinux :
[0x7407ca0] update_load_avg
Disassembled with llvm
annotate.disassemblers=llvm,capstone,objdump
Samples: 66 of event 'cpu_atom/cycles/P', 10000 Hz,
Event count (approx.): 5185444, [percent: local period]
update_load_avg()
/usr/lib/debug/lib/modules/6.11.4-201.fc40.x86_64/vmlinux
Percent 0xffffffff81148fe0 <update_load_avg>:
1.61 pushq %r15
pushq %r14
1.00 pushq %r13
movl %edx,%r13d
1.90 pushq %r12
pushq %rbp
movq %rsi,%rbp
pushq %rbx
movq %rdi,%rbx
subq $0x18,%rsp
15.14 movl 0x1a4(%rdi),%eax
root@x1:~# perf config annotate.disassemblers=capstone
root@x1:~# cat ~/.perfconfig
# this file is auto-generated.
[annotate]
disassemblers = capstone
root@x1:~#
root@x1:~# perf annotate -v --stdio2 update_load_avg
<SNIP>
Disassembled with capstone
annotate.disassemblers=capstone
Samples: 66 of event 'cpu_atom/cycles/P', 10000 Hz,
Event count (approx.): 5185444, [percent: local period]
update_load_avg()
/usr/lib/debug/lib/modules/6.11.4-201.fc40.x86_64/vmlinux
Percent 0xffffffff81148fe0 <update_load_avg>:
1.61 pushq %r15
pushq %r14
1.00 pushq %r13
movl %edx,%r13d
1.90 pushq %r12
pushq %rbp
movq %rsi,%rbp
pushq %rbx
movq %rdi,%rbx
subq $0x18,%rsp
15.14 movl 0x1a4(%rdi),%eax
root@x1:~# perf config annotate.disassemblers=objdump,capstone
root@x1:~# perf config annotate.disassemblers
annotate.disassemblers=objdump,capstone
root@x1:~# cat ~/.perfconfig
# this file is auto-generated.
[annotate]
disassemblers = objdump,capstone
root@x1:~# perf annotate -v --stdio2 update_load_avg
Executing: objdump --start-address=0xffffffff81148fe0 \
--stop-address=0xffffffff811497aa \
-d --no-show-raw-insn -S -C "$1"
Disassembled with objdump
annotate.disassemblers=objdump,capstone
Samples: 66 of event 'cpu_atom/cycles/P', 10000 Hz,
Event count (approx.): 5185444, [percent: local period]
update_load_avg()
/usr/lib/debug/lib/modules/6.11.4-201.fc40.x86_64/vmlinux
Percent
Disassembly of section .text:
ffffffff81148fe0 <update_load_avg>:
#define DO_ATTACH 0x4
ffffffff81148fe0 <update_load_avg>:
#define DO_ATTACH 0x4
#define DO_DETACH 0x8
/* Update task and its cfs_rq load average */
static inline void update_load_avg(struct cfs_rq *cfs_rq,
struct sched_entity *se,
int flags)
{
1.61 push %r15
push %r14
1.00 push %r13
mov %edx,%r13d
1.90 push %r12
push %rbp
mov %rsi,%rbp
push %rbx
mov %rdi,%rbx
sub $0x18,%rsp
}
/* rq->task_clock normalized against any time
this cfs_rq has spent throttled */
static inline u64 cfs_rq_clock_pelt(struct cfs_rq *cfs_rq)
{
if (unlikely(cfs_rq->throttle_count))
15.14 mov 0x1a4(%rdi),%eax
root@x1:~#
After adding a way to select the disassembler from the command line a
'perf test' comparing the output of the various diassemblers should be
introduced, to test these codebases.
Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Steinar H. Gunderson <sesse@google.com>
Link: https://lore.kernel.org/r/20241111151734.1018476-4-acme@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-11 12:17:34 -03:00
|
|
|
|
2025-01-23 20:38:56 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf annotate: Make perf config effective
perf default config set by user in [annotate] section is totally ignored
by annotate code. Fix it.
Before:
$ ./perf config
annotate.hide_src_code=true
annotate.show_nr_jumps=true
annotate.show_nr_samples=true
$ ./perf annotate shash
│ unsigned h = 0;
│ movl $0x0,-0xc(%rbp)
│ while (*s)
│ ↓ jmp 44
│ h = 65599 * h + *s++;
11.33 │24: mov -0xc(%rbp),%eax
43.50 │ imul $0x1003f,%eax,%ecx
│ mov -0x18(%rbp),%rax
After:
│ movl $0x0,-0xc(%rbp)
│ ↓ jmp 44
1 │1 24: mov -0xc(%rbp),%eax
4 │ imul $0x1003f,%eax,%ecx
│ mov -0x18(%rbp),%rax
Note that we have removed show_nr_samples and show_total_period from
annotation_options because they are not used. Instead of them we use
symbol_conf.show_nr_samples and symbol_conf.show_total_period.
Committer testing:
Using 'perf annotate --stdio2' to use the TUI rendering but emitting the output to stdio:
# perf config
#
# perf config annotate.hide_src_code=true
# perf config
annotate.hide_src_code=true
#
# perf config annotate.show_nr_jumps=true
# perf config annotate.show_nr_samples=true
# perf config
annotate.hide_src_code=true
annotate.show_nr_jumps=true
annotate.show_nr_samples=true
#
#
Before:
# perf annotate --stdio2 ObjectInstance::weak_pointer_was_finalized
Samples: 1 of event 'cycles', 4000 Hz, Event count (approx.): 830873, [percent: local period]
ObjectInstance::weak_pointer_was_finalized() /usr/lib64/libgjs.so.0.0.0
Percent
00000000000609f0 <ObjectInstance::weak_pointer_was_finalized()@@Base>:
endbr64
cmpq $0x0,0x20(%rdi)
↓ je 10
xor %eax,%eax
← retq
xchg %ax,%ax
100.00 10: push %rbp
cmpq $0x0,0x18(%rdi)
mov %rdi,%rbp
↓ jne 20
1b: xor %eax,%eax
pop %rbp
← retq
nop
20: lea 0x18(%rdi),%rdi
→ callq JS_UpdateWeakPointerAfterGC(JS::Heap<JSObject*
cmpq $0x0,0x18(%rbp)
↑ jne 1b
mov %rbp,%rdi
→ callq ObjectBase::jsobj_addr() const@plt
mov $0x1,%eax
pop %rbp
← retq
#
After:
# perf annotate --stdio2 ObjectInstance::weak_pointer_was_finalized 2> /dev/null
Samples: 1 of event 'cycles', 4000 Hz, Event count (approx.): 830873, [percent: local period]
ObjectInstance::weak_pointer_was_finalized() /usr/lib64/libgjs.so.0.0.0
Samples endbr64
cmpq $0x0,0x20(%rdi)
↓ je 10
xor %eax,%eax
← retq
xchg %ax,%ax
1 1 10: push %rbp
cmpq $0x0,0x18(%rdi)
mov %rdi,%rbp
↓ jne 20
1 1b: xor %eax,%eax
pop %rbp
← retq
nop
1 20: lea 0x18(%rdi),%rdi
→ callq JS_UpdateWeakPointerAfterGC(JS::Heap<JSObject*
cmpq $0x0,0x18(%rbp)
↑ jne 1b
mov %rbp,%rdi
→ callq ObjectBase::jsobj_addr() const@plt
mov $0x1,%eax
pop %rbp
← retq
#
# perf config annotate.show_nr_jumps
annotate.show_nr_jumps=true
# perf config annotate.show_nr_jumps=false
# perf config annotate.show_nr_jumps
annotate.show_nr_jumps=false
#
# perf annotate --stdio2 ObjectInstance::weak_pointer_was_finalized 2> /dev/null
Samples: 1 of event 'cycles', 4000 Hz, Event count (approx.): 830873, [percent: local period]
ObjectInstance::weak_pointer_was_finalized() /usr/lib64/libgjs.so.0.0.0
Samples endbr64
cmpq $0x0,0x20(%rdi)
↓ je 10
xor %eax,%eax
← retq
xchg %ax,%ax
1 10: push %rbp
cmpq $0x0,0x18(%rdi)
mov %rdi,%rbp
↓ jne 20
1b: xor %eax,%eax
pop %rbp
← retq
nop
20: lea 0x18(%rdi),%rdi
→ callq JS_UpdateWeakPointerAfterGC(JS::Heap<JSObject*
cmpq $0x0,0x18(%rbp)
↑ jne 1b
mov %rbp,%rdi
→ callq ObjectBase::jsobj_addr() const@plt
mov $0x1,%eax
pop %rbp
← retq
#
Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Changbin Du <changbin.du@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: Taeung Song <treeze.taeung@gmail.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Yisheng Xie <xieyisheng1@huawei.com>
Link: http://lore.kernel.org/lkml/20200213064306.160480-6-ravi.bangoria@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-02-13 12:13:03 +05:30
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf annotate: Allow configuring the 'disassembler_style' knob via 'perf config'
# perf annotate --stdio2 acpi_processor_ffh_cstate_enter > default
# perf config annotate.disassembler_style=intel
# perf config annotate.disassembler_style
annotate.disassembler_style=intel
# perf annotate --stdio2 acpi_processor_ffh_cstate_enter > intel
# diff -u default intel
--- default 2020-09-04 13:09:26.019205732 -0300
+++ intel 2020-09-04 13:09:52.823795081 -0300
@@ -1,42 +1,42 @@
Samples: 1K of event 'cycles', 4000 Hz, Event count (approx.): 990065316, [percent: local period]
acpi_processor_ffh_cstate_enter() /lib/modules/5.9.0-rc3/build/vmlinux
-Percent → callq __fentry__
- mov cpu_number,%edx
- mov %edx,%edx
- mov cpu_cstate_entry,%rax
- add -0x7dbe9700(,%rdx,8),%rax
- movzbl 0x9(%rdi),%edx
- mov 0x4(%rax,%rdx,8),%edi
- mov (%rax,%rdx,8),%esi
- → jmpq 137ccc6
- 2d: → jmpq 137ccd8
+Percent → call __fentry__
+ mov edx,DWORD PTR gs:[rip+0x7e541d74]
+ mov edx,edx
+ mov rax,QWORD PTR [rip+0x152b8fb]
+ add rax,QWORD PTR [rdx*8-0x7dbe9700]
+ movzx edx,BYTE PTR [rdi+0x9]
+ mov edi,DWORD PTR [rax+rdx*8+0x4]
+ mov esi,DWORD PTR [rax+rdx*8]
+ → jmp 137ccc6
+ 2d: → jmp 137ccd8
mfence
- mov %gs:0x17bc0,%rax
- clflush (%rax)
+ mov rax,QWORD PTR gs:0x17bc0
+ clflush BYTE PTR [rax]
mfence
- xor %edx,%edx
- mov %rdx,%rcx
- mov %gs:0x17bc0,%rax
- 0.00 monitor %rax,%ecx,%edx
- mov (%rax),%rax
- test $0x8,%al
+ xor edx,edx
+ mov rcx,rdx
+ mov rax,QWORD PTR gs:0x17bc0
+ 0.00 monitor
+ mov rax,QWORD PTR [rax]
+ test al,0x8
↓ jne 71
- ↓ jmpq 68
- verw 0x538b08(%rip) # ffffffff82008150 <ds.0>
- 68: mov %rsi,%rax
- mov %rdi,%rcx
-100.00 mwait %eax,%ecx
- 71: mov %gs:0x17bc0,%rax
- lock andb $0xdf,0x2(%rax)
- lock addl $0x0,-0x4(%rsp)
- mov (%rax),%rax
- test $0x8,%al
+ ↓ jmp 68
+ verw WORD PTR [rip+0x538b08] # ffffffff82008150 <ds.0>
+ 68: mov rax,rsi
+ mov rcx,rdi
+100.00 mwait
+ 71: mov rax,QWORD PTR gs:0x17bc0
+ lock and BYTE PTR [rax+0x2],0xdf
+ lock add DWORD PTR [rsp-0x4],0x0
+ mov rax,QWORD PTR [rax]
+ test al,0x8
↓ je 97
- andl $0x7fffffff,__preempt_count
- 97: ← retq
- mov %gs:0x17bc0,%rax
- lock orb $0x20,0x2(%rax)
- mov (%rax),%rax
- test $0x8,%al
+ and DWORD PTR gs:[rip+0x7e548509],0x7fffffff
+ 97: ret
+ mov rax,QWORD PTR gs:0x17bc0
+ lock or BYTE PTR [rax+0x2],0x20
+ mov rax,QWORD PTR [rax]
+ test al,0x8
↑ jne 71
- ↑ jmpq 2d
+ ↑ jmp 2d
#
Requested-by: Matt P. Dziubinski <matdzb@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-09-04 13:10:43 -03:00
|
|
|
|
2023-03-28 16:55:41 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-03-28 16:55:42 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-03-28 16:55:43 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-03-28 16:55:41 -07:00
|
|
|
|
2021-02-26 11:01:24 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf annotate: Allow setting the offset level in .perfconfig
The default is 1 (jump_target):
# perf annotate --ignore-vmlinux --stdio2 _raw_spin_lock_irqsave
Samples: 3K of event 'cycles:ppp', 3000 Hz, Event count (approx.): 2766398574
_raw_spin_lock_irqsave() /proc/kcore
0.26 nop
4.61 push %rbx
19.33 pushfq
7.97 pop %rax
0.32 nop
0.06 mov %rax,%rbx
14.63 cli
0.06 nop
xor %eax,%eax
mov $0x1,%edx
49.94 lock cmpxchg %edx,(%rdi)
0.16 test %eax,%eax
↓ jne 2b
2.66 mov %rbx,%rax
pop %rbx
← retq
2b: mov %eax,%esi
→ callq *ffffffffb30eaed0
mov %rbx,%rax
pop %rbx
← retq
#
But one can ask for showing offsets for call instructions by setting
this:
# perf annotate --ignore-vmlinux --stdio2 _raw_spin_lock_irqsave
Samples: 3K of event 'cycles:ppp', 3000 Hz, Event count (approx.): 2766398574
_raw_spin_lock_irqsave() /proc/kcore
0.26 nop
4.61 push %rbx
19.33 pushfq
7.97 pop %rax
0.32 nop
0.06 mov %rax,%rbx
14.63 cli
0.06 nop
xor %eax,%eax
mov $0x1,%edx
49.94 lock cmpxchg %edx,(%rdi)
0.16 test %eax,%eax
↓ jne 2b
2.66 mov %rbx,%rax
pop %rbx
← retq
2b: mov %eax,%esi
2d: → callq *ffffffffb30eaed0
mov %rbx,%rax
pop %rbx
← retq
#
Or using a big value to ask for all offsets to be shown:
# cat ~/.perfconfig
[annotate]
offset_level = 100
hide_src_code = true
# perf annotate --ignore-vmlinux --stdio2 _raw_spin_lock_irqsave
Samples: 3K of event 'cycles:ppp', 3000 Hz, Event count (approx.): 2766398574
_raw_spin_lock_irqsave() /proc/kcore
0.26 0: nop
4.61 5: push %rbx
19.33 6: pushfq
7.97 7: pop %rax
0.32 8: nop
0.06 d: mov %rax,%rbx
14.63 10: cli
0.06 11: nop
17: xor %eax,%eax
19: mov $0x1,%edx
49.94 1e: lock cmpxchg %edx,(%rdi)
0.16 22: test %eax,%eax
24: ↓ jne 2b
2.66 26: mov %rbx,%rax
29: pop %rbx
2a: ← retq
2b: mov %eax,%esi
2d: → callq *ffffffffb30eaed0
32: mov %rbx,%rax
35: pop %rbx
36: ← retq
#
This also affects the TUI, i.e. the default 'perf annotate' and 'perf
top/report' -> A hotkey -> annotate interfaces, when slang-devel is present
in the build, i.e.:
# perf version --build-options | grep slang
libslang: [ on ] # HAVE_SLANG_SUPPORT
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Martin Liška <mliska@suse.cz>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Cc: Thomas Richter <tmricht@linux.vnet.ibm.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-venm6x5zrt40eu8hxdsmqxz6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-04-12 15:23:02 -03:00
|
|
|
|
perf annotate: Make perf config effective
perf default config set by user in [annotate] section is totally ignored
by annotate code. Fix it.
Before:
$ ./perf config
annotate.hide_src_code=true
annotate.show_nr_jumps=true
annotate.show_nr_samples=true
$ ./perf annotate shash
│ unsigned h = 0;
│ movl $0x0,-0xc(%rbp)
│ while (*s)
│ ↓ jmp 44
│ h = 65599 * h + *s++;
11.33 │24: mov -0xc(%rbp),%eax
43.50 │ imul $0x1003f,%eax,%ecx
│ mov -0x18(%rbp),%rax
After:
│ movl $0x0,-0xc(%rbp)
│ ↓ jmp 44
1 │1 24: mov -0xc(%rbp),%eax
4 │ imul $0x1003f,%eax,%ecx
│ mov -0x18(%rbp),%rax
Note that we have removed show_nr_samples and show_total_period from
annotation_options because they are not used. Instead of them we use
symbol_conf.show_nr_samples and symbol_conf.show_total_period.
Committer testing:
Using 'perf annotate --stdio2' to use the TUI rendering but emitting the output to stdio:
# perf config
#
# perf config annotate.hide_src_code=true
# perf config
annotate.hide_src_code=true
#
# perf config annotate.show_nr_jumps=true
# perf config annotate.show_nr_samples=true
# perf config
annotate.hide_src_code=true
annotate.show_nr_jumps=true
annotate.show_nr_samples=true
#
#
Before:
# perf annotate --stdio2 ObjectInstance::weak_pointer_was_finalized
Samples: 1 of event 'cycles', 4000 Hz, Event count (approx.): 830873, [percent: local period]
ObjectInstance::weak_pointer_was_finalized() /usr/lib64/libgjs.so.0.0.0
Percent
00000000000609f0 <ObjectInstance::weak_pointer_was_finalized()@@Base>:
endbr64
cmpq $0x0,0x20(%rdi)
↓ je 10
xor %eax,%eax
← retq
xchg %ax,%ax
100.00 10: push %rbp
cmpq $0x0,0x18(%rdi)
mov %rdi,%rbp
↓ jne 20
1b: xor %eax,%eax
pop %rbp
← retq
nop
20: lea 0x18(%rdi),%rdi
→ callq JS_UpdateWeakPointerAfterGC(JS::Heap<JSObject*
cmpq $0x0,0x18(%rbp)
↑ jne 1b
mov %rbp,%rdi
→ callq ObjectBase::jsobj_addr() const@plt
mov $0x1,%eax
pop %rbp
← retq
#
After:
# perf annotate --stdio2 ObjectInstance::weak_pointer_was_finalized 2> /dev/null
Samples: 1 of event 'cycles', 4000 Hz, Event count (approx.): 830873, [percent: local period]
ObjectInstance::weak_pointer_was_finalized() /usr/lib64/libgjs.so.0.0.0
Samples endbr64
cmpq $0x0,0x20(%rdi)
↓ je 10
xor %eax,%eax
← retq
xchg %ax,%ax
1 1 10: push %rbp
cmpq $0x0,0x18(%rdi)
mov %rdi,%rbp
↓ jne 20
1 1b: xor %eax,%eax
pop %rbp
← retq
nop
1 20: lea 0x18(%rdi),%rdi
→ callq JS_UpdateWeakPointerAfterGC(JS::Heap<JSObject*
cmpq $0x0,0x18(%rbp)
↑ jne 1b
mov %rbp,%rdi
→ callq ObjectBase::jsobj_addr() const@plt
mov $0x1,%eax
pop %rbp
← retq
#
# perf config annotate.show_nr_jumps
annotate.show_nr_jumps=true
# perf config annotate.show_nr_jumps=false
# perf config annotate.show_nr_jumps
annotate.show_nr_jumps=false
#
# perf annotate --stdio2 ObjectInstance::weak_pointer_was_finalized 2> /dev/null
Samples: 1 of event 'cycles', 4000 Hz, Event count (approx.): 830873, [percent: local period]
ObjectInstance::weak_pointer_was_finalized() /usr/lib64/libgjs.so.0.0.0
Samples endbr64
cmpq $0x0,0x20(%rdi)
↓ je 10
xor %eax,%eax
← retq
xchg %ax,%ax
1 10: push %rbp
cmpq $0x0,0x18(%rdi)
mov %rdi,%rbp
↓ jne 20
1b: xor %eax,%eax
pop %rbp
← retq
nop
20: lea 0x18(%rdi),%rdi
→ callq JS_UpdateWeakPointerAfterGC(JS::Heap<JSObject*
cmpq $0x0,0x18(%rbp)
↑ jne 1b
mov %rbp,%rdi
→ callq ObjectBase::jsobj_addr() const@plt
mov $0x1,%eax
pop %rbp
← retq
#
Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Changbin Du <changbin.du@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: Taeung Song <treeze.taeung@gmail.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Yisheng Xie <xieyisheng1@huawei.com>
Link: http://lore.kernel.org/lkml/20200213064306.160480-6-ravi.bangoria@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-02-13 12:13:03 +05:30
|
|
|
|
perf annotate: Allow setting the offset level in .perfconfig
The default is 1 (jump_target):
# perf annotate --ignore-vmlinux --stdio2 _raw_spin_lock_irqsave
Samples: 3K of event 'cycles:ppp', 3000 Hz, Event count (approx.): 2766398574
_raw_spin_lock_irqsave() /proc/kcore
0.26 nop
4.61 push %rbx
19.33 pushfq
7.97 pop %rax
0.32 nop
0.06 mov %rax,%rbx
14.63 cli
0.06 nop
xor %eax,%eax
mov $0x1,%edx
49.94 lock cmpxchg %edx,(%rdi)
0.16 test %eax,%eax
↓ jne 2b
2.66 mov %rbx,%rax
pop %rbx
← retq
2b: mov %eax,%esi
→ callq *ffffffffb30eaed0
mov %rbx,%rax
pop %rbx
← retq
#
But one can ask for showing offsets for call instructions by setting
this:
# perf annotate --ignore-vmlinux --stdio2 _raw_spin_lock_irqsave
Samples: 3K of event 'cycles:ppp', 3000 Hz, Event count (approx.): 2766398574
_raw_spin_lock_irqsave() /proc/kcore
0.26 nop
4.61 push %rbx
19.33 pushfq
7.97 pop %rax
0.32 nop
0.06 mov %rax,%rbx
14.63 cli
0.06 nop
xor %eax,%eax
mov $0x1,%edx
49.94 lock cmpxchg %edx,(%rdi)
0.16 test %eax,%eax
↓ jne 2b
2.66 mov %rbx,%rax
pop %rbx
← retq
2b: mov %eax,%esi
2d: → callq *ffffffffb30eaed0
mov %rbx,%rax
pop %rbx
← retq
#
Or using a big value to ask for all offsets to be shown:
# cat ~/.perfconfig
[annotate]
offset_level = 100
hide_src_code = true
# perf annotate --ignore-vmlinux --stdio2 _raw_spin_lock_irqsave
Samples: 3K of event 'cycles:ppp', 3000 Hz, Event count (approx.): 2766398574
_raw_spin_lock_irqsave() /proc/kcore
0.26 0: nop
4.61 5: push %rbx
19.33 6: pushfq
7.97 7: pop %rax
0.32 8: nop
0.06 d: mov %rax,%rbx
14.63 10: cli
0.06 11: nop
17: xor %eax,%eax
19: mov $0x1,%edx
49.94 1e: lock cmpxchg %edx,(%rdi)
0.16 22: test %eax,%eax
24: ↓ jne 2b
2.66 26: mov %rbx,%rax
29: pop %rbx
2a: ← retq
2b: mov %eax,%esi
2d: → callq *ffffffffb30eaed0
32: mov %rbx,%rax
35: pop %rbx
36: ← retq
#
This also affects the TUI, i.e. the default 'perf annotate' and 'perf
top/report' -> A hotkey -> annotate interfaces, when slang-devel is present
in the build, i.e.:
# perf version --build-options | grep slang
libslang: [ on ] # HAVE_SLANG_SUPPORT
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Martin Liška <mliska@suse.cz>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Cc: Thomas Richter <tmricht@linux.vnet.ibm.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-venm6x5zrt40eu8hxdsmqxz6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-04-12 15:23:02 -03:00
|
|
|
|
perf annotate: Make perf config effective
perf default config set by user in [annotate] section is totally ignored
by annotate code. Fix it.
Before:
$ ./perf config
annotate.hide_src_code=true
annotate.show_nr_jumps=true
annotate.show_nr_samples=true
$ ./perf annotate shash
│ unsigned h = 0;
│ movl $0x0,-0xc(%rbp)
│ while (*s)
│ ↓ jmp 44
│ h = 65599 * h + *s++;
11.33 │24: mov -0xc(%rbp),%eax
43.50 │ imul $0x1003f,%eax,%ecx
│ mov -0x18(%rbp),%rax
After:
│ movl $0x0,-0xc(%rbp)
│ ↓ jmp 44
1 │1 24: mov -0xc(%rbp),%eax
4 │ imul $0x1003f,%eax,%ecx
│ mov -0x18(%rbp),%rax
Note that we have removed show_nr_samples and show_total_period from
annotation_options because they are not used. Instead of them we use
symbol_conf.show_nr_samples and symbol_conf.show_total_period.
Committer testing:
Using 'perf annotate --stdio2' to use the TUI rendering but emitting the output to stdio:
# perf config
#
# perf config annotate.hide_src_code=true
# perf config
annotate.hide_src_code=true
#
# perf config annotate.show_nr_jumps=true
# perf config annotate.show_nr_samples=true
# perf config
annotate.hide_src_code=true
annotate.show_nr_jumps=true
annotate.show_nr_samples=true
#
#
Before:
# perf annotate --stdio2 ObjectInstance::weak_pointer_was_finalized
Samples: 1 of event 'cycles', 4000 Hz, Event count (approx.): 830873, [percent: local period]
ObjectInstance::weak_pointer_was_finalized() /usr/lib64/libgjs.so.0.0.0
Percent
00000000000609f0 <ObjectInstance::weak_pointer_was_finalized()@@Base>:
endbr64
cmpq $0x0,0x20(%rdi)
↓ je 10
xor %eax,%eax
← retq
xchg %ax,%ax
100.00 10: push %rbp
cmpq $0x0,0x18(%rdi)
mov %rdi,%rbp
↓ jne 20
1b: xor %eax,%eax
pop %rbp
← retq
nop
20: lea 0x18(%rdi),%rdi
→ callq JS_UpdateWeakPointerAfterGC(JS::Heap<JSObject*
cmpq $0x0,0x18(%rbp)
↑ jne 1b
mov %rbp,%rdi
→ callq ObjectBase::jsobj_addr() const@plt
mov $0x1,%eax
pop %rbp
← retq
#
After:
# perf annotate --stdio2 ObjectInstance::weak_pointer_was_finalized 2> /dev/null
Samples: 1 of event 'cycles', 4000 Hz, Event count (approx.): 830873, [percent: local period]
ObjectInstance::weak_pointer_was_finalized() /usr/lib64/libgjs.so.0.0.0
Samples endbr64
cmpq $0x0,0x20(%rdi)
↓ je 10
xor %eax,%eax
← retq
xchg %ax,%ax
1 1 10: push %rbp
cmpq $0x0,0x18(%rdi)
mov %rdi,%rbp
↓ jne 20
1 1b: xor %eax,%eax
pop %rbp
← retq
nop
1 20: lea 0x18(%rdi),%rdi
→ callq JS_UpdateWeakPointerAfterGC(JS::Heap<JSObject*
cmpq $0x0,0x18(%rbp)
↑ jne 1b
mov %rbp,%rdi
→ callq ObjectBase::jsobj_addr() const@plt
mov $0x1,%eax
pop %rbp
← retq
#
# perf config annotate.show_nr_jumps
annotate.show_nr_jumps=true
# perf config annotate.show_nr_jumps=false
# perf config annotate.show_nr_jumps
annotate.show_nr_jumps=false
#
# perf annotate --stdio2 ObjectInstance::weak_pointer_was_finalized 2> /dev/null
Samples: 1 of event 'cycles', 4000 Hz, Event count (approx.): 830873, [percent: local period]
ObjectInstance::weak_pointer_was_finalized() /usr/lib64/libgjs.so.0.0.0
Samples endbr64
cmpq $0x0,0x20(%rdi)
↓ je 10
xor %eax,%eax
← retq
xchg %ax,%ax
1 10: push %rbp
cmpq $0x0,0x18(%rdi)
mov %rdi,%rbp
↓ jne 20
1b: xor %eax,%eax
pop %rbp
← retq
nop
20: lea 0x18(%rdi),%rdi
→ callq JS_UpdateWeakPointerAfterGC(JS::Heap<JSObject*
cmpq $0x0,0x18(%rbp)
↑ jne 1b
mov %rbp,%rdi
→ callq ObjectBase::jsobj_addr() const@plt
mov $0x1,%eax
pop %rbp
← retq
#
Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Changbin Du <changbin.du@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: Taeung Song <treeze.taeung@gmail.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Yisheng Xie <xieyisheng1@huawei.com>
Link: http://lore.kernel.org/lkml/20200213064306.160480-6-ravi.bangoria@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-02-13 12:13:03 +05:30
|
|
|
|
2018-03-16 14:33:38 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-28 09:54:39 -08:00
|
|
|
|
2023-03-28 16:55:40 -07:00
|
|
|
|
2023-11-28 09:54:39 -08:00
|
|
|
|
|
|
|
|
|
2023-03-28 16:55:40 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-06-25 16:03:39 -07:00
|
|
|
|
2025-04-08 19:22:09 -03:00
|
|
|
|
2023-03-28 16:55:40 -07:00
|
|
|
|
|
|
|
|
|
2023-11-28 09:54:39 -08:00
|
|
|
|
2023-03-28 16:55:40 -07:00
|
|
|
|
2023-11-28 09:54:39 -08:00
|
|
|
|
|
|
|
|
|
2023-03-28 16:55:40 -07:00
|
|
|
|
|
|
|
|
|
2025-01-23 20:38:56 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-28 09:54:39 -08:00
|
|
|
|
2018-03-16 14:33:38 -03:00
|
|
|
|
2023-11-28 09:54:39 -08:00
|
|
|
|
2025-01-23 20:38:56 -08:00
|
|
|
|
2018-03-16 14:33:38 -03:00
|
|
|
|
2018-08-04 15:05:20 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-28 09:54:37 -08:00
|
|
|
|
2018-08-04 15:05:20 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-28 09:54:37 -08:00
|
|
|
|
2018-08-04 15:05:20 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-01-07 13:04:44 -08:00
|
|
|
|
2023-11-28 09:54:39 -08:00
|
|
|
|
2020-01-07 13:04:44 -08:00
|
|
|
|
2023-11-28 09:54:39 -08:00
|
|
|
|
|
|
|
|
|
2020-01-07 13:04:44 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-12-12 16:13:12 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-18 22:51:08 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-12-12 16:13:12 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-11-08 15:45:50 -08:00
|
|
|
|
2023-12-12 16:13:12 -08:00
|
|
|
|
2024-01-16 22:26:51 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-11-08 15:45:50 -08:00
|
|
|
|
2024-01-16 22:26:51 -08:00
|
|
|
|
|
|
|
|
|
2023-12-12 16:13:12 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-01-16 22:26:51 -08:00
|
|
|
|
|
|
|
|
|
2023-12-12 16:13:12 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-01-16 22:26:51 -08:00
|
|
|
|
|
|
|
|
|
2023-12-12 16:13:12 -08:00
|
|
|
|
2024-01-16 22:26:51 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-05-06 17:49:00 +05:30
|
|
|
|
2024-01-16 22:26:51 -08:00
|
|
|
|
|
|
|
|
|
2023-12-12 16:13:12 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-29 14:58:08 -07:00
|
|
|
|
2023-12-12 16:13:12 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-01-16 22:26:51 -08:00
|
|
|
|
2024-07-18 14:13:49 +05:30
|
|
|
|
2023-12-12 16:13:12 -08:00
|
|
|
|
2024-01-16 22:26:51 -08:00
|
|
|
|
2023-12-12 16:13:12 -08:00
|
|
|
|
2024-01-16 22:26:51 -08:00
|
|
|
|
2024-07-18 14:13:49 +05:30
|
|
|
|
2024-01-16 22:26:51 -08:00
|
|
|
|
2023-12-12 16:13:12 -08:00
|
|
|
|
|
|
|
|
|
2024-01-16 22:26:51 -08:00
|
|
|
|
|
|
|
|
|
2023-12-12 16:13:12 -08:00
|
|
|
|
2024-07-18 14:13:49 +05:30
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-12-12 16:13:12 -08:00
|
|
|
|
2024-07-18 14:13:49 +05:30
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-12-12 16:13:12 -08:00
|
|
|
|
2024-01-16 22:26:51 -08:00
|
|
|
|
2023-12-12 16:13:12 -08:00
|
|
|
|
|
|
|
|
|
2024-03-18 22:51:08 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-12-12 16:13:12 -08:00
|
|
|
|
2024-03-18 22:51:08 -07:00
|
|
|
|
2024-11-08 15:45:50 -08:00
|
|
|
|
2024-03-18 22:51:08 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-12-12 16:13:12 -08:00
|
|
|
|
2024-03-18 22:51:08 -07:00
|
|
|
|
2023-12-12 16:13:12 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-12-12 16:13:13 -08:00
|
|
|
|
2024-03-18 22:50:59 -07:00
|
|
|
|
|
|
|
|
|
2023-12-12 16:13:13 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-04-05 14:17:59 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-01-16 22:26:49 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-29 14:58:08 -07:00
|
|
|
|
2024-03-18 22:50:59 -07:00
|
|
|
|
2024-01-16 22:26:49 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-12-12 16:13:13 -08:00
|
|
|
|
2024-01-16 22:26:49 -08:00
|
|
|
|
2023-12-12 16:13:13 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
perf annotate: Add --insn-stat option for debugging
This is for a debugging purpose. It'd be useful to see per-instrucion
level success/failure stats.
$ perf annotate --data-type --insn-stat
Annotate Instruction stats
total 264, ok 143 (54.2%), bad 121 (45.8%)
Name : Good Bad
-----------------------------------------------------------
movq : 45 31
movl : 22 11
popq : 0 19
cmpl : 16 3
addq : 8 7
cmpq : 11 3
cmpxchgl : 3 7
cmpxchgq : 8 0
incl : 3 3
movzbl : 4 2
incq : 4 2
decl : 6 0
...
Committer notes:
So these are about being able to find the type for accesses from these
instructions, we should improve the naming, but it is for debugging, we
can improve this later:
@@ -3726,6 +3759,10 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
continue;
mem_type = find_data_type(ms, ip, op_loc->reg, op_loc->offset);
+ if (mem_type)
+ istat->good++;
+ else
+ istat->bad++;
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231213001323.718046-18-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-12-12 16:13:23 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-07-18 14:13:58 +05:30
|
|
|
|
perf annotate: Add --insn-stat option for debugging
This is for a debugging purpose. It'd be useful to see per-instrucion
level success/failure stats.
$ perf annotate --data-type --insn-stat
Annotate Instruction stats
total 264, ok 143 (54.2%), bad 121 (45.8%)
Name : Good Bad
-----------------------------------------------------------
movq : 45 31
movl : 22 11
popq : 0 19
cmpl : 16 3
addq : 8 7
cmpq : 11 3
cmpxchgl : 3 7
cmpxchgq : 8 0
incl : 3 3
movzbl : 4 2
incq : 4 2
decl : 6 0
...
Committer notes:
So these are about being able to find the type for accesses from these
instructions, we should improve the naming, but it is for debugging, we
can improve this later:
@@ -3726,6 +3759,10 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
continue;
mem_type = find_data_type(ms, ip, op_loc->reg, op_loc->offset);
+ if (mem_type)
+ istat->good++;
+ else
+ istat->bad++;
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231213001323.718046-18-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-12-12 16:13:23 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-01-16 22:26:52 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-09-09 14:42:50 -07:00
|
|
|
|
2024-01-16 22:26:52 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-18 22:51:13 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-04-05 14:17:59 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-01-16 22:26:54 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-04-05 14:17:59 -07:00
|
|
|
|
|
|
|
|
|
2024-01-16 22:26:54 -08:00
|
|
|
|
2024-04-05 14:17:59 -07:00
|
|
|
|
2024-01-16 22:26:54 -08:00
|
|
|
|
2024-04-05 14:17:59 -07:00
|
|
|
|
2024-01-16 22:26:54 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-08-05 16:46:48 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-03-10 15:49:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-12-12 16:13:13 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-12-12 16:13:17 -08:00
|
|
|
|
perf annotate: Add --insn-stat option for debugging
This is for a debugging purpose. It'd be useful to see per-instrucion
level success/failure stats.
$ perf annotate --data-type --insn-stat
Annotate Instruction stats
total 264, ok 143 (54.2%), bad 121 (45.8%)
Name : Good Bad
-----------------------------------------------------------
movq : 45 31
movl : 22 11
popq : 0 19
cmpl : 16 3
addq : 8 7
cmpq : 11 3
cmpxchgl : 3 7
cmpxchgq : 8 0
incl : 3 3
movzbl : 4 2
incq : 4 2
decl : 6 0
...
Committer notes:
So these are about being able to find the type for accesses from these
instructions, we should improve the naming, but it is for debugging, we
can improve this later:
@@ -3726,6 +3759,10 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
continue;
mem_type = find_data_type(ms, ip, op_loc->reg, op_loc->offset);
+ if (mem_type)
+ istat->good++;
+ else
+ istat->bad++;
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20231213001323.718046-18-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-12-12 16:13:23 -08:00
|
|
|
|
2024-03-18 22:50:58 -07:00
|
|
|
|
2023-12-12 16:13:13 -08:00
|
|
|
|
2023-12-12 16:13:22 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-12-12 16:13:13 -08:00
|
|
|
|
2023-12-12 16:13:22 -08:00
|
|
|
|
2023-12-12 16:13:13 -08:00
|
|
|
|
2023-12-12 16:13:22 -08:00
|
|
|
|
|
|
|
|
|
2023-12-12 16:13:13 -08:00
|
|
|
|
2023-12-12 16:13:22 -08:00
|
|
|
|
2023-12-12 16:13:13 -08:00
|
|
|
|
2024-08-05 16:46:48 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-08-15 20:16:34 -07:00
|
|
|
|
2024-08-05 16:46:48 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-04-05 14:18:00 -07:00
|
|
|
|
|
|
|
|
|
2023-12-12 16:13:22 -08:00
|
|
|
|
2023-12-12 16:13:13 -08:00
|
|
|
|
2023-12-12 16:13:22 -08:00
|
|
|
|
2023-12-12 16:13:13 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-18 22:50:59 -07:00
|
|
|
|
2023-12-12 16:13:22 -08:00
|
|
|
|
|
|
|
|
|
2023-12-12 16:13:13 -08:00
|
|
|
|
2023-12-12 16:13:22 -08:00
|
|
|
|
2023-12-12 16:13:13 -08:00
|
|
|
|
2024-01-16 22:26:50 -08:00
|
|
|
|
2025-03-10 15:49:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-12-12 16:13:22 -08:00
|
|
|
|
2024-01-16 22:26:50 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-04-05 14:17:59 -07:00
|
|
|
|
2024-01-16 22:26:50 -08:00
|
|
|
|
|
|
|
|
|
2024-04-05 14:17:59 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-01-16 22:26:50 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-12-12 16:13:22 -08:00
|
|
|
|
2025-03-10 15:49:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-12-12 16:13:13 -08:00
|
|
|
|
|
|
|
|
|
2024-03-18 22:50:59 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-04-05 14:17:59 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-18 22:50:59 -07:00
|
|
|
|
|
|
|
|
|
2024-04-05 14:17:59 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-18 22:50:59 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-29 14:58:08 -07:00
|
|
|
|
2024-03-18 22:50:59 -07:00
|
|
|
|
|
|
|
|
|
2024-03-29 14:58:08 -07:00
|
|
|
|
2024-03-18 22:50:59 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-04-05 14:17:59 -07:00
|
|
|
|
|
|
|
|
|
2024-03-18 22:50:59 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-04-05 14:17:59 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-18 22:50:59 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-05-07 00:04:06 -03:00
|
|
|
|
2024-03-18 22:50:59 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-05-07 00:04:06 -03:00
|
|
|
|
2024-03-18 22:50:59 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
