summaryrefslogtreecommitdiff
path: root/tools/perf/util/annotate.h
AgeCommit message (Collapse)Author
2019-03-20perf annotate: Enable annotation of BPF programsSong Liu
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>
2019-03-06perf annotate: Calculate the max instruction name, align column to thatArnaldo Carvalho de Melo
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>
2019-01-25perf annotate: Remove lots of headers from annotate.hArnaldo Carvalho de Melo
To reduce the chances changes trigger tons of rebuilds, more to come. 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-ytbykaku63862guk7muflcy4@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-17perf annotate: Compute average IPC and IPC coverage per symbolJin Yao
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>
2018-08-30perf annotate: Fix parsing aarch64 branch instructions after objdump updateKim Phillips
Starting with binutils 2.28, aarch64 objdump adds comments to the disassembly output to show the alternative names of a condition code [1]. It is assumed that commas in objdump comments could occur in other arches now or in the future, so this fix is arch-independent. The fix could have been done with arm64 specific jump__parse and jump__scnprintf functions, but the jump__scnprintf instruction would have to have its comment character be a literal, since the scnprintf functions cannot receive a struct arch easily. This inconvenience also applies to the generic jump__scnprintf, which is why we add a raw_comment pointer to struct ins_operands, so the __parse function assigns it to be re-used by its corresponding __scnprintf function. Example differences in 'perf annotate --stdio2' output on an aarch64 perf.data file: BEFORE: → b.cs ffff200008133d1c <unwind_frame+0x18c> // b.hs, dffff7ecc47b AFTER : ↓ b.cs 18c BEFORE: → b.cc ffff200008d8d9cc <get_alloc_profile+0x31c> // b.lo, b.ul, dffff727295b AFTER : ↓ b.cc 31c The branch target labels 18c and 31c also now appear in the output: BEFORE: add x26, x29, #0x80 AFTER : 18c: add x26, x29, #0x80 BEFORE: add x21, x21, #0x8 AFTER : 31c: add x21, x21, #0x8 The Fixes: tag below is added so stable branches will get the update; it doesn't necessarily mean that commit was broken at the time, rather it didn't withstand the aarch64 objdump update. Tested no difference in output for sample x86_64, power arch perf.data files. [1] https://sourceware.org/git/gitweb.cgi?p=binutils-gdb.git;a=commit;h=bb7eff5206e4795ac79c177a80fe9f4630aaf730 Signed-off-by: Kim Phillips <kim.phillips@arm.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Anton Blanchard <anton@samba.org> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com> Cc: Robin Murphy <robin.murphy@arm.com> Cc: Taeung Song <treeze.taeung@gmail.com> Cc: linux-arm-kernel@lists.infradead.org Fixes: b13bbeee5ee6 ("perf annotate: Fix branch instruction with multiple operands") Link: http://lkml.kernel.org/r/20180827125340.a2f7e291901d17cea05daba4@arm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-08perf annotate: Add --percent-type optionJiri Olsa
Add --percent-type option to set annotation percent type from following choices: global-period, local-period, global-hits, local-hits Examples: $ perf annotate --percent-type period-local --stdio | head -1 Percent | Source code ... es, percent: local period) $ perf annotate --percent-type hits-local --stdio | head -1 Percent | Source code ... es, percent: local hits) $ perf annotate --percent-type hits-global --stdio | head -1 Percent | Source code ... es, percent: global hits) $ perf annotate --percent-type period-global --stdio | head -1 Percent | Source code ... es, percent: global period) The local/global keywords set if the percentage is computed in the scope of the function (local) or the whole data (global). The period/hits keywords set the base the percentage is computed on - the samples period or the number of samples (hits). Signed-off-by: Jiri Olsa <jolsa@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/20180804130521.11408-20-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-08perf annotate: Add support to toggle percent typeJiri Olsa
Add new key bindings to toggle percent type/base in annotation UI browser: 'p' to switch between local and global percent type 'b' to switch between hits and perdio percent base Add the following help messages to the UI browser '?' window: ... p Toggle percent type [local/global] b Toggle percent base [period/hits] ... Signed-off-by: Jiri Olsa <jolsa@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/20180804130521.11408-17-jolsa@kernel.org [ Moved percent_type to be the last arg to sym_title(), its an arg to what is being formmated (buf, size) ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-08perf annotate: Pass 'struct annotation_options' to map_symbol__annotation_dump()Jiri Olsa
Pass 'struct annotation_options' to map_symbol__annotation_dump(), to carry on and pass the percent_type value. Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/20180804130521.11408-15-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-08perf annotate: Add percent_type to struct annotation_optionsJiri Olsa
It will be used to carry user selection of percent type for annotation output. Passing the percent_type to the annotation_line__print function as the first step and making it default to current percentage type (PERCENT_HITS_LOCAL) value. Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/20180804130521.11408-13-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-08perf annotate: Add PERCENT_PERIOD_GLOBAL percent valueJiri Olsa
Adding and computing global period percent value for annotation line. Storing it in struct annotation_data percent array under new PERCENT_PERIOD_GLOBAL index. At the moment it's not displayed, it's coming in following patches. Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/20180804130521.11408-12-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-08perf annotate: Add PERCENT_PERIOD_LOCAL percent valueJiri Olsa
Adding and computing local period percent value for annotation line. Storing it in struct annotation_data percent array under new PERCENT_PERIOD_LOCAL index. At the moment it's not displayed, it's coming in following patches. Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/20180804130521.11408-11-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-08perf annotate: Add PERCENT_HITS_GLOBAL percent valueJiri Olsa
Adding and computing global hits percent value for annotation line. Storing it in struct annotation_data percent array under new PERCENT_HITS_GLOBAL index. At the moment it's not displayed, it's coming in following patches. Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/20180804130521.11408-10-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-08perf annotate: Switch struct annotation_data::percent to arrayJiri Olsa
So we can hold multiple percent values for annotation line. The first member of this array is current local hits percent value (PERCENT_HITS_LOCAL index), so no functional change is expected. Adding annotation_data__percent function to return requested percent value from struct annotation_data. Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/20180804130521.11408-9-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-08perf annotate: Rename struct annotation_line::samples* to data*Jiri Olsa
The name 'samples*' is little confusing because we have nested 'struct sym_hist_entry' under annotation_line struct, which holds 'nr_samples' as well. Also the holding struct name is 'annotation_data' so the 'data' name fits better. Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/20180804130521.11408-5-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-08perf annotate: Get rid of annotation__scnprintf_samples_period()Jiri Olsa
We have more current function tto get the title for annotation, which is hists__scnprintf_title. They both have same output as far as the annotation's header line goes. They differ in counting of the nr_samples, hists__scnprintf_title provides more accurate number based on the setup of the symbol_conf.filter_relative variable. Plus it also displays any uid/thread/dso/socket filters/zooms if there are set any, which annotation__scnprintf_samples_period does not. Signed-off-by: Jiri Olsa <jolsa@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/20180804130521.11408-4-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-08perf annotate: Make annotation_line__max_percent staticJiri Olsa
There's no outside user of it. Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/20180804130521.11408-3-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-08perf annotate: Make symbol__annotate_fprintf2() localJiri Olsa
There's no outside user of it. Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lkml.kernel.org/r/20180804130521.11408-2-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-06-04perf annotate: Move objdump_path to struct annotation_optionsArnaldo Carvalho de Melo
One more step in grouping annotation options. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.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-sogzdhugoavm6fyw60jnb0vs@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-06-04perf hists browser: Pass annotation_options from tool to browserArnaldo Carvalho de Melo
So that things changed in the command line may percolate to the browser code without using globals. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.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-5daawc40zhl6gcs600com1ua@git.kernel.org [ Merged fix for NO_SLANG=1 build provided by Jiri Olsa ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-06-04perf annotate: Move disassembler_style global to annotation_optionsArnaldo Carvalho de Melo
Continuing to group annotation specific stuff into a struct. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.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-p3cdhltj58jt0byjzg3g7obx@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-06-04perf annotate: Adopt anotation options from symbol_confArnaldo Carvalho de Melo
Continuing to group annotation options in an annotation specific struct. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.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-astei92tzxp4yccag5pxb2h7@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-06-04perf annotate: Pass annotation_options to symbol__annotate()Arnaldo Carvalho de Melo
Now all callers to symbol__disassemble() can hand it the per-tool annotation_options, which will allow us to remove lots of stuff from symbol_options, the kitchen sink of perf configs, reducing its size and getting annotation specific stuff grouped together. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.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-vpr7ys7ggvs2fzpg8wbjcw7e@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-06-04perf annotate stdio: Use annotation_options consistentlyArnaldo Carvalho de Melo
Accross all the routines, this way we can have eventually have a consistent set of defaults for all UIs. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.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-6qgtixurjgdk5u0n3rw78ges@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-06-04perf annotate: Add comment about annotated_src->nr_histogramsArnaldo Carvalho de Melo
When we have multiple groups in an evlist, say: $ perf stat -e '{cycles,instructions},{cache-references,cache-misses}' sleep 1 Performance counter stats for 'sleep 1': 343,134 cycles:u 249,292 instructions:u # 0.73 insn per cycle 15,556 cache-references:u 8,925 cache-misses:u # 57.373 % of all cache refs 1.000957550 seconds time elapsed $ Then the perf_evsel instances for the two group leaders ("cycles" and "cache-references") will have evsel->nr_members set to 2, while all the evsel->evlist->nr_entries will be set to 4, so we can't use evsel->evlist->nr_entries everywhere, as event groups need to be taken into account. But this probably requires us to audit at least the forced-group code, where we want all of the events to be in a "group", to see them all in the screen, one column for each, even knowing that they were not necessarily scheduled to count at the same time by the kernel perf subsystem. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.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-2g0vwqnc49wl4ttjk8dvpgcc@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-06-04perf annotate: Replace symbol__alloc_hists() with symbol__hists()Arnaldo Carvalho de Melo
Its a bit shorter, so ditch the old symbol__alloc_hists() function. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.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-m7tienxk7dijh5ln62yln1m9@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-06-04perf annotate: __symbol__inc_addr_samples() needs just annotated_sourceArnaldo Carvalho de Melo
It only operates on the histograms, so no need for the encompassing 'struct annotation'. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.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-2se2v7rrjil0kwqywks04ey2@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-06-04perf annotate: Split allocation of annotated_source structArnaldo Carvalho de Melo
So that we can allocate just the notes->src->cyc_hist, that, unlike notes->src->histograms, is not per event, and in paths where we need to lazily allocate notes->src->cyc_hist we don't have the number of events handy to also allocate ->histograms. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.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-tsx7dhxzpi0criyx0sio3pz3@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-06-04perf annotate: Pass perf_evsel instead of just evsel->idxArnaldo Carvalho de Melo
The code gets shorter and we'll be able to use evsel->evlist in a followup patch. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.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-t0s7vy19wq5kak74kavm8swf@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-05-19perf annotate: Create hotkey 'c' to show min/max cyclesJin Yao
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>
2018-05-18perf annotate: Record the min/max cyclesJin Yao
Currently perf has a feature to account cycles for LBRs For example, on skylake: perf record -b ... perf report or perf annotate And then browsing the annotate browser gives average cycle counts for program blocks. For some analysis it would be useful if we could know not only the average cycles but also the min and max cycles. This patch records the min and max cycles. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: 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/1526569118-14217-2-git-send-email-yao.jin@linux.intel.com [ Switch from max/min to min/max ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-04-12perf annotate: Allow showing offsets in more than just jump targetsArnaldo Carvalho de Melo
Jesper wanted to see offsets at callq sites when doing some performance investigation related to retpolines, so save him some time by providing an 'struct annotation_options' to control where offsets should appear: just on jump targets? That + call instructions? All? This puts in place the logic to show the offsets, now we need to wire this up in the TUI browser (next patch) and on the 'perf annotate --stdio2" interface, where we need a more general mechanism to setup the 'annotation_options' struct from the command line. Suggested-by: Jesper Dangaard Brouer <brouer@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: David Ahern <dsahern@gmail.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Linus Torvalds <torvalds@linux-foundation.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-m3jc9c3swobye9tj08gnh5i7@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-04-03perf annotate: Introduce annotation__scnprintf_samples_period() methodArnaldo Carvalho de Melo
To print a string using the total period (nr_events) and the number of samples for a given annotation, i.e. for a given symbol, the counterpart to hists__scnprintf_samples_period(), that is for all the samples in a session (be it a live session, think 'perf top' or a perf.data file, think 'perf report'). Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Martin Liška <mliska@suse.cz> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=196935 Link: https://lkml.kernel.org/n/tip-goj2wu4fxutc8vd46mw3yg14@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-23perf annotate: Add "_local" to jump/offset validation routinesArnaldo Carvalho de Melo
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>
2018-03-21perf annotate: Mark jumps to outher functions with the call arrowArnaldo Carvalho de Melo
Things like this in _cpp_lex_token (gcc's cc1 program): cpp_named_operator2name@@Base+0xa72 Point to a place that is after the cpp_named_operator2name boundaries, i.e. in the ELF symbol table for cc1 cpp_named_operator2name is marked as being 32-bytes long, but it in fact is much larger than that, so we seem to need a symbols__find() routine that looks for >= current->start and < next_symbol->start, possibly just for C++ objects? For now lets just make some progress by marking jumps to outside the current function as call like. Actual navigation will come next, with further understanding of how the symbol searching and disassembly should be done. 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-aiys0a0bsgm3e00hbi6fg7yy@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-21perf annotate: Pass function descriptor to its instruction parsing routinesArnaldo Carvalho de Melo
We need that to figure out if jumps have targets in a different function. E.g. _cpp_lex_token(), in /usr/libexec/gcc/x86_64-redhat-linux/5.3.1/cc1 has a line like this: jne c469be <cpp_named_operator2name@@Base+0xa72> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.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-ris0ioziyp469pofpzix2atb@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-21perf annotate browser: Add 'P' hotkey to dump annotation to fileArnaldo Carvalho de Melo
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>
2018-03-21perf annotate: Move the default annotate options to the libraryArnaldo Carvalho de Melo
One more thing that goes from the TUI code to be used more widely, for instance it'll affect the default options used by: perf annotate --stdio2 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-0nsz0dm0akdbo30vgja2a10e@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-21perf annotate: Introduce the --stdio2 output modeArnaldo Carvalho de Melo
This uses the TUI augmented formatting routines, modulo interactivity. # perf annotate --ignore-vmlinux --stdio2 _raw_spin_lock_irqsave _raw_spin_lock_irqsave() /proc/kcore Event: cycles:ppp Percent Disassembly of section load0: ffffffff9a8734b0 <load0>: nop push %rbx 50.00 pushfq pop %rax nop mov %rax,%rbx cli nop xor %eax,%eax mov $0x1,%edx 50.00 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 Tested-by: Jin Yao <yao.jin@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: David Ahern <dsahern@gmail.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-6cte5o8z84mbivbvqlg14uh1@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-20perf annotate: Introduce annotation_line__filter()Arnaldo Carvalho de Melo
Out of the TUI logic that allows toggling the presentation of source code lines. Will be used in the upcoming --stdio2 mode. 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-g0ckz9ajy6unswrv2iy39mxk@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-20perf annotate: Use a ops table for annotation_line__write()Arnaldo Carvalho de Melo
To simplify the passing of arguments, the --stdio2 code will have to set all the fields with operations printing to stdout. 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-pcs3c7vdy9ucygxflo4nl1o7@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-20perf annotate: Finish the generalization of annotate_browser__write()Arnaldo Carvalho de Melo
We pass some more callbacks and all of annotate_browser__write() seems to be free of TUI code (except for some arrow constants, will fix). 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-5uo6yvwnxtsbe8y6v0ysaakf@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-20perf annotate: Introduce annotation_line__print_start() out of TUI codeArnaldo Carvalho de Melo
For the --tui and --stdio2 cases using callbacks for print() and set_percent_color() end up being the easiest path, real GUI remains as an exercise. 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-1o7az1ng55g2g6ppr2jpeuct@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-20perf annotate: Introduce annotation_line__max_percent()Arnaldo Carvalho de Melo
Out of the annotate_browser__write() routine, to be used in the --stdio2 mode. 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-0he0wyy4haswqi1qb35x37do@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-20perf annotate: Introduce symbol__annotate2 methodArnaldo Carvalho de Melo
That does all the extended boilerplate the TUI browser did, leaving the symbol__annotate() function to be used by the old --stdio output mode. Now the upcoming --stdio2 output mode should just use this one to set things up. 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-e2x8wuf6gvdhzdryo229vj4i@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-20perf annotate: Introduce init_column_widths() method out of TUI codeArnaldo Carvalho de Melo
More non-TUI stuff goes to the UI-agnostic library 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-hngv7rpqvtta69ouj7ne770q@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-20perf annotate: Move update_column_widths() to the generic libArnaldo Carvalho de Melo
Previous patch left it where it was to ease review, move it to its right place. 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-ikdjr014p7k5kachgyjrgiey@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-20perf annotate: Move the column widths from the TUI to generic libArnaldo Carvalho de Melo
This also will be used in other output formats, such as --stdio2. 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-86h6ftebc62ij1rx8q9zkpwk@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-20perf annotate: Introduce set_offsets() method out of TUI codeArnaldo Carvalho de Melo
More non-strictly TUI code being moved to the UI neutral annotation library, to be used in the upcoming --stdio2 output mode. 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-ek20dnd8z2y5v54pcepihybz@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-20perf annotate: Move nr_{asm_}entries to struct annotationArnaldo Carvalho de Melo
More non-TUI stuff. 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-yd4g6q0rngq4i49hz6iymtta@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-20perf annotate: Move 'start' to struct annotationArnaldo Carvalho de Melo
Another field that is not TUI specific. 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-jj3dwswndft5mln8hu9k0idv@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
generated by cgit (git 2.34.1) at 2024-05-28 10:10:47 +0000