lwn.git/tools/perf/util/annotate.c, branch docs-5.2a

perf annotate: Calculate the max instruction name, align column to that

2019-03-06T19:40:15+00:00

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 LPU-Reference: CAOBGo4z1KfmWeOm6Et0cnX5Z6DWsG2PQbAvRn1MhVPJmXHrc5g@mail.gmail.com Cc: Adrian Hunter Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lkml.kernel.org/n/tip-89wsdd9h9g6bvq52sgp6d0u4@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo

perf annotate: Fix getting source line failure

2019-02-21T20:00:35+00:00

The output of "perf annotate -l --stdio xxx" changed since commit 425859ff0de33 ("perf annotate: No need to calculate notes->start twice") removed notes->start assignment in symbol__calc_lines(). It will get failed in find_address_in_section() from symbol__tty_annotate() subroutine as the a2l->addr is wrong. So the annotate summary doesn't report the line number of source code correctly. Before fix: liwei@euler:~/main_code/hulk_work/hulk/tools/perf$ cat common_while_1.c void hotspot_1(void) { volatile int i; for (i = 0; i < 0x10000000; i++); for (i = 0; i < 0x10000000; i++); for (i = 0; i < 0x10000000; i++); } int main(void) { hotspot_1(); return 0; } liwei@euler:~/main_code/hulk_work/hulk/tools/perf$ gcc common_while_1.c -g -o common_while_1 liwei@euler:~/main_code/hulk_work/hulk/tools/perf$ sudo ./perf record ./common_while_1 [ perf record: Woken up 2 times to write data ] [ perf record: Captured and wrote 0.488 MB perf.data (12498 samples) ] liwei@euler:~/main_code/hulk_work/hulk/tools/perf$ sudo ./perf annotate -l -s hotspot_1 --stdio Sorted summary for file /home/liwei/main_code/hulk_work/hulk/tools/perf/common_while_1 ---------------------------------------------- 19.30 common_while_1[32] 19.03 common_while_1[4e] 19.01 common_while_1[16] 5.04 common_while_1[13] 4.99 common_while_1[4b] 4.78 common_while_1[2c] 4.77 common_while_1[10] 4.66 common_while_1[2f] 4.59 common_while_1[51] 4.59 common_while_1[35] 4.52 common_while_1[19] 4.20 common_while_1[56] 0.51 common_while_1[48] Percent | Source code & Disassembly of common_while_1 for cycles:ppp (12480 samples, percent: local period) ----------------------------------------------------------------------------------------------------------------- : : : : Disassembly of section .text: : : 00000000000005fa : : hotspot_1(): : void hotspot_1(void) : { 0.00 : 5fa: push %rbp 0.00 : 5fb: mov %rsp,%rbp : volatile int i; : : for (i = 0; i < 0x10000000; i++); 0.00 : 5fe: movl $0x0,-0x4(%rbp) 0.00 : 605: jmp 610 0.00 : 607: mov -0x4(%rbp),%eax common_while_1[10] 4.77 : 60a: add $0x1,%eax common_while_1[13] 5.04 : 60d: mov %eax,-0x4(%rbp) common_while_1[16] 19.01 : 610: mov -0x4(%rbp),%eax common_while_1[19] 4.52 : 613: cmp $0xfffffff,%eax 0.00 : 618: jle 607 : for (i = 0; i < 0x10000000; i++); ... After fix: liwei@euler:~/main_code/hulk_work/hulk/tools/perf$ sudo ./perf record ./common_while_1 [ perf record: Woken up 2 times to write data ] [ perf record: Captured and wrote 0.488 MB perf.data (12500 samples) ] liwei@euler:~/main_code/hulk_work/hulk/tools/perf$ sudo ./perf annotate -l -s hotspot_1 --stdio Sorted summary for file /home/liwei/main_code/hulk_work/hulk/tools/perf/common_while_1 ---------------------------------------------- 33.34 common_while_1.c:5 33.34 common_while_1.c:6 33.32 common_while_1.c:7 Percent | Source code & Disassembly of common_while_1 for cycles:ppp (12482 samples, percent: local period) ----------------------------------------------------------------------------------------------------------------- : : : : Disassembly of section .text: : : 00000000000005fa : : hotspot_1(): : void hotspot_1(void) : { 0.00 : 5fa: push %rbp 0.00 : 5fb: mov %rsp,%rbp : volatile int i; : : for (i = 0; i < 0x10000000; i++); 0.00 : 5fe: movl $0x0,-0x4(%rbp) 0.00 : 605: jmp 610 0.00 : 607: mov -0x4(%rbp),%eax common_while_1.c:5 4.70 : 60a: add $0x1,%eax 4.89 : 60d: mov %eax,-0x4(%rbp) common_while_1.c:5 19.03 : 610: mov -0x4(%rbp),%eax common_while_1.c:5 4.72 : 613: cmp $0xfffffff,%eax 0.00 : 618: jle 607 : for (i = 0; i < 0x10000000; i++); 0.00 : 61a: movl $0x0,-0x4(%rbp) 0.00 : 621: jmp 62c 0.00 : 623: mov -0x4(%rbp),%eax common_while_1.c:6 4.54 : 626: add $0x1,%eax 4.73 : 629: mov %eax,-0x4(%rbp) common_while_1.c:6 19.54 : 62c: mov -0x4(%rbp),%eax common_while_1.c:6 4.54 : 62f: cmp $0xfffffff,%eax ... Signed-off-by: Wei Li Acked-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Jin Yao Cc: Namhyung Kim Cc: Peter Zijlstra Fixes: 425859ff0de33 ("perf annotate: No need to calculate notes->start twice") Link: http://lkml.kernel.org/r/20190221095716.39529-1-liwei391@huawei.com Signed-off-by: Arnaldo Carvalho de Melo

pref tools: Add missing map.h includes

2019-02-06T13:00:38+00:00

Lots of places get the map.h file indirectly, and since we're going to remove it from machine.h, then those need to include it directly, do it now, before we remove that dep. Cc: Adrian Hunter Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lkml.kernel.org/n/tip-ob8jehdjda8h5jsrv9dqj9tf@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo

perf symbols: Remove some unnecessary includes from symbol.h

2019-01-25T14:12:09+00:00

And fixup the fallout in places like annotation and jitdump that were using things like dirname() but weren't including libgen.h, etc. Cc: Adrian Hunter Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lkml.kernel.org/n/tip-wrii9hy1a1wathc0398f9fgt@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo

perf annotate: Pass filename to objdump via execl

2019-01-04T15:54:49+00:00

The symbol__disassemble() function uses shell to launch objdump and filter its output via grep. Passing filenames by interpolating them into the command line via "%s" may lead to problems if said filenames contain special characters. Instead, pass the filename as a command line argument where it is not subject to any kind of interpretation, then use quoted shell interpolation to build the strings we need safely. Signed-off-by: Ivan Krylov Acked-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20181014111803.5d83b806@Tarkus Signed-off-by: Arnaldo Carvalho de Melo

perf annotate: Introduce basic support for ARC

2018-12-17T17:59:42+00:00

Introduce basic 'perf annotate' support for ARC to be able to use anotation via stdio interface. Signed-off-by: Eugeniy Paltsev Cc: Alexander Shishkin Cc: Alexey Brodkin Cc: Jiri Olsa Cc: linux-snps-arc@lists.infradead.org Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Vineet Gupta Link: http://lkml.kernel.org/r/20181204175118.25232-1-Eugeniy.Paltsev@synopsys.com Signed-off-by: Arnaldo Carvalho de Melo

perf tools: Fix diverse comment typos

2018-12-17T17:56:47+00:00

Go over the tools/ files that are maintained in Arnaldo's tree and fix common typos: half of them were in comments, the other half in JSON files. No change in functionality intended. Committer notes: This was split from a larger patch as there are code that is, additionally, maintained outside the kernel tree, so to ease cherry-picking and/or backporting, split this into multiple patches. Just typos in comments, no need to backport, reducing the possibility of possible backporting artifacts. Signed-off-by: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20181203102200.GA104797@gmail.com Signed-off-by: Arnaldo Carvalho de Melo

perf annotate: Create a annotate2 flag in struct symbol

2018-12-17T17:55:40+00:00

We often use the symbol__annotate2() to annotate a specified symbol. While annotating may take some time, so in order to avoid annotating the same symbol repeatedly, the patch creates a new flag to indicate the symbol has been annotated. Signed-off-by: Jin Yao Reviewed-by: Ingo Molnar Reviewed-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Kan Liang Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1543586097-27632-3-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo

perf annotate: Compute average IPC and IPC coverage per symbol

2018-12-17T17:55:32+00:00

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 : 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 Reviewed-by: Ingo Molnar Reviewed-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Kan Liang Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1543586097-27632-2-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo

perf annotate: Add Sparc support

2018-10-18T14:16:38+00:00

E.g.: $ perf annotate --stdio2 Samples: 7K of event 'cycles:ppp', 4000 Hz, Event count (approx.): 3086733887 __gettimeofday /lib32/libc-2.27.so [Percent: local period] Percent│ │ │ │ Disassembly of section .text: │ │ 000a6fa0 <__gettimeofday@@GLIBC_2.0>: 0.47 │ save %sp, -96, %sp 0.73 │ sethi %hi(0xe9000), %l7 │ → call __frame_state_for@@GLIBC_2.0+0x480 0.30 │ add %l7, 0x58, %l7 ! e9058 1.33 │ mov %i0, %o0 │ mov %i1, %o1 0.43 │ mov 0x74, %g1 │ ta 0x10 88.92 │ ↓ bcc 30 2.95 │ clr %g1 │ neg %o0 │ mov 1, %g1 0.31 │30: cmp %g1, 0 │ bne,pn %icc, a6fe4 <__gettimeofday@@GLIBC_2.0+0x44> │ mov %o0, %i0 1.96 │ ← return %i7 + 8 2.62 │ nop │ sethi %hi(0), %g1 │ neg %o0, %g2 │ add %g1, 0x160, %g1 │ ld [ %l7 + %g1 ], %g1 │ st %g2, [ %g7 + %g1 ] │ ← return %i7 + 8 │ mov -1, %o0 Signed-off-by: David S. Miller Link: http://lkml.kernel.org/r/20181016.205555.1070918198627611771.davem@davemloft.net Signed-off-by: Arnaldo Carvalho de Melo