linux/tools/perf/util/annotate.c

2667 lines
65 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
*
* Parts came from builtin-annotate.c, see those files for further
* copyright notes.
*/
#include <errno.h>
#include <inttypes.h>
#include <libgen.h>
#include <stdlib.h>
#include "util.h" // hex_width()
#include "ui/ui.h"
#include "sort.h"
#include "build-id.h"
#include "color.h"
#include "config.h"
#include "disasm.h"
#include "dso.h"
#include "env.h"
#include "map.h"
#include "maps.h"
#include "symbol.h"
#include "srcline.h"
#include "units.h"
#include "debug.h"
#include "annotate.h"
#include "annotate-data.h"
#include "evsel.h"
#include "evlist.h"
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
#include "bpf-event.h"
#include "bpf-utils.h"
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
#include "block-range.h"
#include "string2.h"
#include "dwarf-regs.h"
#include "util/event.h"
#include "util/sharded_mutex.h"
#include "arch/common.h"
#include "namespaces.h"
#include "thread.h"
#include "hashmap.h"
#include <regex.h>
#include <linux/bitops.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/zalloc.h>
#include <subcmd/parse-options.h>
#include <subcmd/run-command.h>
/* FIXME: For the HE_COLORSET */
#include "ui/browser.h"
/*
* FIXME: Using the same values as slang.h,
* but that header may not be available everywhere
*/
#define LARROW_CHAR ((unsigned char)',')
#define RARROW_CHAR ((unsigned char)'+')
#define DARROW_CHAR ((unsigned char)'.')
#define UARROW_CHAR ((unsigned char)'-')
#include <linux/ctype.h>
/* global annotation options */
struct annotation_options annotate_opts;
/* Data type collection debug statistics */
struct annotated_data_stat ann_data_stat;
LIST_HEAD(ann_insn_stat);
/* Pseudo data types */
struct annotated_data_type stackop_type = {
.self = {
.type_name = (char *)"(stack operation)",
.children = LIST_HEAD_INIT(stackop_type.self.children),
},
};
struct annotated_data_type canary_type = {
.self = {
.type_name = (char *)"(stack canary)",
.children = LIST_HEAD_INIT(canary_type.self.children),
},
};
/* symbol histogram: key = offset << 16 | evsel->core.idx */
static size_t sym_hist_hash(long key, void *ctx __maybe_unused)
{
return (key >> 16) + (key & 0xffff);
}
static bool sym_hist_equal(long key1, long key2, void *ctx __maybe_unused)
{
return key1 == key2;
}
static struct annotated_source *annotated_source__new(void)
{
struct annotated_source *src = zalloc(sizeof(*src));
if (src != NULL)
INIT_LIST_HEAD(&src->source);
return src;
}
static __maybe_unused void annotated_source__delete(struct annotated_source *src)
{
if (src == NULL)
return;
hashmap__free(src->samples);
zfree(&src->histograms);
free(src);
}
static int annotated_source__alloc_histograms(struct annotated_source *src,
int nr_hists)
{
src->nr_histograms = nr_hists;
src->histograms = calloc(nr_hists, sizeof(*src->histograms));
if (src->histograms == NULL)
return -1;
src->samples = hashmap__new(sym_hist_hash, sym_hist_equal, NULL);
if (src->samples == NULL)
zfree(&src->histograms);
return src->histograms ? 0 : -1;
}
void symbol__annotate_zero_histograms(struct symbol *sym)
{
struct annotation *notes = symbol__annotation(sym);
annotation__lock(notes);
if (notes->src != NULL) {
memset(notes->src->histograms, 0,
notes->src->nr_histograms * sizeof(*notes->src->histograms));
hashmap__clear(notes->src->samples);
}
if (notes->branch && notes->branch->cycles_hist) {
memset(notes->branch->cycles_hist, 0,
symbol__size(sym) * sizeof(struct cyc_hist));
}
annotation__unlock(notes);
}
static int __symbol__account_cycles(struct cyc_hist *ch,
u64 start,
unsigned offset, unsigned cycles,
unsigned have_start)
{
/*
* For now we can only account one basic block per
* final jump. But multiple could be overlapping.
* Always account the longest one. So when
* a shorter one has been already seen throw it away.
*
* We separately always account the full cycles.
*/
ch[offset].num_aggr++;
ch[offset].cycles_aggr += cycles;
if (cycles > ch[offset].cycles_max)
ch[offset].cycles_max = cycles;
if (ch[offset].cycles_min) {
if (cycles && cycles < ch[offset].cycles_min)
ch[offset].cycles_min = cycles;
} else
ch[offset].cycles_min = cycles;
if (!have_start && ch[offset].have_start)
return 0;
if (ch[offset].num) {
if (have_start && (!ch[offset].have_start ||
ch[offset].start > start)) {
ch[offset].have_start = 0;
ch[offset].cycles = 0;
ch[offset].num = 0;
if (ch[offset].reset < 0xffff)
ch[offset].reset++;
} else if (have_start &&
ch[offset].start < start)
return 0;
}
perf diff: Report noisy for cycles diff This patch prints the stddev and hist for the cycles diff of program block. It can help us to understand if the cycles is noisy or not. This patch is inspired by Andi Kleen's patch: https://lwn.net/Articles/600471/ We create new option '--cycles-hist'. Example: perf record -b ./div perf record -b ./div perf diff -c cycles # Baseline [Program Block Range] Cycles Diff Shared Object Symbol # ........ .......................................................... .... ................. ............................ # 46.72% [div.c:40 -> div.c:40] 0 div [.] main 46.72% [div.c:42 -> div.c:44] 0 div [.] main 46.72% [div.c:42 -> div.c:39] 0 div [.] main 20.54% [random_r.c:357 -> random_r.c:394] 1 libc-2.27.so [.] __random_r 20.54% [random_r.c:357 -> random_r.c:380] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:388] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:391] 0 libc-2.27.so [.] __random_r 17.04% [random.c:288 -> random.c:291] 0 libc-2.27.so [.] __random 17.04% [random.c:291 -> random.c:291] 0 libc-2.27.so [.] __random 17.04% [random.c:293 -> random.c:293] 0 libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:298 -> random.c:298] 0 libc-2.27.so [.] __random 8.40% [div.c:22 -> div.c:25] 0 div [.] compute_flag 8.40% [div.c:27 -> div.c:28] 0 div [.] compute_flag 5.14% [rand.c:26 -> rand.c:27] 0 libc-2.27.so [.] rand 5.14% [rand.c:28 -> rand.c:28] 0 libc-2.27.so [.] rand 2.15% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.00% [kernel.kallsyms] [k] __x86_indirect_thunk_rax 0.00% [do_mmap+714 -> do_mmap+732] -10 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+737 -> do_mmap+765] 1 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+262 -> do_mmap+299] 0 [kernel.kallsyms] [k] do_mmap 0.00% [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0] 7 [kernel.kallsyms] [k] __x86_indirect_thunk_r15 0.00% [native_sched_clock+0 -> native_sched_clock+119] -1 [kernel.kallsyms] [k] native_sched_clock 0.00% [native_write_msr+0 -> native_write_msr+16] -13 [kernel.kallsyms] [k] native_write_msr When we enable the option '--cycles-hist', the output is perf diff -c cycles --cycles-hist # Baseline [Program Block Range] Cycles Diff stddev/Hist Shared Object Symbol # ........ .......................................................... .... ................. ................. ............................ # 46.72% [div.c:40 -> div.c:40] 0 ± 37.8% ▁█▁▁██▁█ div [.] main 46.72% [div.c:42 -> div.c:44] 0 ± 49.4% ▁▁▂█▂▂▂▂ div [.] main 46.72% [div.c:42 -> div.c:39] 0 ± 24.1% ▃█▂▄▁▃▂▁ div [.] main 20.54% [random_r.c:357 -> random_r.c:394] 1 ± 33.5% ▅▂▁█▃▁▂▁ libc-2.27.so [.] __random_r 20.54% [random_r.c:357 -> random_r.c:380] 0 ± 39.4% ▁▁█▁██▅▁ libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:388] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:391] 0 ± 41.2% ▁▃▁▂█▄▃▁ libc-2.27.so [.] __random_r 17.04% [random.c:288 -> random.c:291] 0 ± 48.8% ▁▁▁▁███▁ libc-2.27.so [.] __random 17.04% [random.c:291 -> random.c:291] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:293 -> random.c:293] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:298 -> random.c:298] 0 ± 75.6% ▃█▁▁▁▁▁▁ libc-2.27.so [.] __random 8.40% [div.c:22 -> div.c:25] 0 ± 42.1% ▁▃▁▁███▁ div [.] compute_flag 8.40% [div.c:27 -> div.c:28] 0 ± 41.8% ██▁▁▄▁▁▄ div [.] compute_flag 5.14% [rand.c:26 -> rand.c:27] 0 ± 37.8% ▁▁▁████▁ libc-2.27.so [.] rand 5.14% [rand.c:28 -> rand.c:28] 0 libc-2.27.so [.] rand 2.15% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.00% [kernel.kallsyms] [k] __x86_indirect_thunk_rax 0.00% [do_mmap+714 -> do_mmap+732] -10 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+737 -> do_mmap+765] 1 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+262 -> do_mmap+299] 0 [kernel.kallsyms] [k] do_mmap 0.00% [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0] 7 [kernel.kallsyms] [k] __x86_indirect_thunk_r15 0.00% [native_sched_clock+0 -> native_sched_clock+119] -1 ± 38.5% ▄█▁ [kernel.kallsyms] [k] native_sched_clock 0.00% [native_write_msr+0 -> native_write_msr+16] -13 ± 47.1% ▁█▇▃▁▁ [kernel.kallsyms] [k] native_write_msr v8: --- Rebase to perf/core branch v7: --- 1. v6 got Jiri's ACK. 2. Rebase to latest perf/core branch. v6: --- 1. Jiri provides better code for using data__hpp_register() in ui_init(). Use this code in v6. v5: --- 1. Refine the use of data__hpp_register() in ui_init() according to Jiri's suggestion. v4: --- 1. Rename the new option from '--noisy' to '--cycles-hist' 2. Remove the option '-n'. 3. Only update the spark value and stats when '--cycles-hist' is enabled. 4. Remove the code of printing '..'. v3: --- 1. Move the histogram to a separate column 2. Move the svals[] out of struct stats v2: --- Jiri got a compile error, CC builtin-diff.o builtin-diff.c: In function ‘compute_cycles_diff’: builtin-diff.c:712:10: error: taking the absolute value of unsigned type ‘u64’ {aka ‘long unsigned int’} has no effect [-Werror=absolute-value] 712 | labs(pair->block_info->cycles_spark[i] - | ^~~~ Because the result of u64 - u64 is still u64. Now we change the type of cycles_spark[] to s64. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20190925011446.30678-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-09-25 09:14:46 +08:00
if (ch[offset].num < NUM_SPARKS)
ch[offset].cycles_spark[ch[offset].num] = cycles;
ch[offset].have_start = have_start;
ch[offset].start = start;
ch[offset].cycles += cycles;
ch[offset].num++;
return 0;
}
static int __symbol__inc_addr_samples(struct map_symbol *ms,
struct annotated_source *src, int evidx, u64 addr,
struct perf_sample *sample)
{
struct symbol *sym = ms->sym;
long hash_key;
u64 offset;
struct sym_hist *h;
struct sym_hist_entry *entry;
perf map: Add helper for ->map_ip() and ->unmap_ip() Later changes will add reference count checking for struct map, add a helper function to invoke the map_ip and unmap_ip function pointers. The helper allows the reference count check to be in fewer places. Committer notes: Add missing conversions to: tools/perf/util/map.c tools/perf/util/cs-etm.c tools/perf/util/annotate.c tools/perf/arch/powerpc/util/sym-handling.c tools/perf/arch/s390/annotate/instructions.c Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Darren Hart <dvhart@infradead.org> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Dmitriy Vyukov <dvyukov@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: German Gomez <german.gomez@arm.com> Cc: Hao Luo <haoluo@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Madhavan Srinivasan <maddy@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Miaoqian Lin <linmq006@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Riccardo Mancini <rickyman7@gmail.com> Cc: Shunsuke Nakamura <nakamura.shun@fujitsu.com> Cc: Song Liu <song@kernel.org> Cc: Stephane Eranian <eranian@google.com> Cc: Stephen Brennan <stephen.s.brennan@oracle.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Yury Norov <yury.norov@gmail.com> Link: https://lore.kernel.org/r/20230404205954.2245628-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-04-04 13:59:44 -07:00
pr_debug3("%s: addr=%#" PRIx64 "\n", __func__, map__unmap_ip(ms->map, addr));
if ((addr < sym->start || addr >= sym->end) &&
(addr != sym->end || sym->start != sym->end)) {
pr_debug("%s(%d): ERANGE! sym->name=%s, start=%#" PRIx64 ", addr=%#" PRIx64 ", end=%#" PRIx64 "\n",
__func__, __LINE__, sym->name, sym->start, addr, sym->end);
return -ERANGE;
}
offset = addr - sym->start;
h = annotated_source__histogram(src, evidx);
if (h == NULL) {
pr_debug("%s(%d): ENOMEM! sym->name=%s, start=%#" PRIx64 ", addr=%#" PRIx64 ", end=%#" PRIx64 ", func: %d\n",
__func__, __LINE__, sym->name, sym->start, addr, sym->end, sym->type == STT_FUNC);
return -ENOMEM;
}
hash_key = offset << 16 | evidx;
if (!hashmap__find(src->samples, hash_key, &entry)) {
entry = zalloc(sizeof(*entry));
if (entry == NULL)
return -ENOMEM;
if (hashmap__add(src->samples, hash_key, entry) < 0)
return -ENOMEM;
}
h->nr_samples++;
h->period += sample->period;
entry->nr_samples++;
entry->period += sample->period;
pr_debug3("%#" PRIx64 " %s: period++ [addr: %#" PRIx64 ", %#" PRIx64
", evidx=%d] => nr_samples: %" PRIu64 ", period: %" PRIu64 "\n",
sym->start, sym->name, addr, addr - sym->start, evidx,
entry->nr_samples, entry->period);
return 0;
}
struct annotated_branch *annotation__get_branch(struct annotation *notes)
{
if (notes == NULL)
return NULL;
if (notes->branch == NULL)
notes->branch = zalloc(sizeof(*notes->branch));
return notes->branch;
}
static struct cyc_hist *symbol__cycles_hist(struct symbol *sym)
{
struct annotation *notes = symbol__annotation(sym);
struct annotated_branch *branch;
branch = annotation__get_branch(notes);
if (branch == NULL)
return NULL;
if (branch->cycles_hist == NULL) {
const size_t size = symbol__size(sym);
branch->cycles_hist = calloc(size, sizeof(struct cyc_hist));
}
return branch->cycles_hist;
}
struct annotated_source *symbol__hists(struct symbol *sym, int nr_hists)
{
struct annotation *notes = symbol__annotation(sym);
if (notes->src == NULL) {
notes->src = annotated_source__new();
if (notes->src == NULL)
return NULL;
goto alloc_histograms;
}
if (notes->src->histograms == NULL) {
alloc_histograms:
annotated_source__alloc_histograms(notes->src, nr_hists);
}
return notes->src;
}
static int symbol__inc_addr_samples(struct map_symbol *ms,
struct evsel *evsel, u64 addr,
struct perf_sample *sample)
{
struct symbol *sym = ms->sym;
struct annotated_source *src;
if (sym == NULL)
return 0;
src = symbol__hists(sym, evsel->evlist->core.nr_entries);
return src ? __symbol__inc_addr_samples(ms, src, evsel->core.idx, addr, sample) : 0;
}
static int symbol__account_cycles(u64 addr, u64 start,
struct symbol *sym, unsigned cycles)
{
struct cyc_hist *cycles_hist;
unsigned offset;
if (sym == NULL)
return 0;
cycles_hist = symbol__cycles_hist(sym);
if (cycles_hist == NULL)
return -ENOMEM;
if (addr < sym->start || addr >= sym->end)
return -ERANGE;
if (start) {
if (start < sym->start || start >= sym->end)
return -ERANGE;
if (start >= addr)
start = 0;
}
offset = addr - sym->start;
return __symbol__account_cycles(cycles_hist,
start ? start - sym->start : 0,
offset, cycles,
!!start);
}
int addr_map_symbol__account_cycles(struct addr_map_symbol *ams,
struct addr_map_symbol *start,
unsigned cycles)
{
u64 saddr = 0;
int err;
if (!cycles)
return 0;
/*
* Only set start when IPC can be computed. We can only
* compute it when the basic block is completely in a single
* function.
* Special case the case when the jump is elsewhere, but
* it starts on the function start.
*/
if (start &&
(start->ms.sym == ams->ms.sym ||
(ams->ms.sym &&
perf map: Add accessor for start and end Later changes will add reference count checking for struct map, start and end are frequently accessed variables. Add an accessor so that the reference count check is only necessary in one place. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Darren Hart <dvhart@infradead.org> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Dmitriy Vyukov <dvyukov@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: German Gomez <german.gomez@arm.com> Cc: Hao Luo <haoluo@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Madhavan Srinivasan <maddy@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Miaoqian Lin <linmq006@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Riccardo Mancini <rickyman7@gmail.com> Cc: Shunsuke Nakamura <nakamura.shun@fujitsu.com> Cc: Song Liu <song@kernel.org> Cc: Stephane Eranian <eranian@google.com> Cc: Stephen Brennan <stephen.s.brennan@oracle.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Yury Norov <yury.norov@gmail.com> Link: https://lore.kernel.org/r/20230320212248.1175731-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-03-20 14:22:36 -07:00
start->addr == ams->ms.sym->start + map__start(ams->ms.map))))
saddr = start->al_addr;
if (saddr == 0)
pr_debug2("BB with bad start: addr %"PRIx64" start %"PRIx64" sym %"PRIx64" saddr %"PRIx64"\n",
ams->addr,
start ? start->addr : 0,
perf map: Add accessor for start and end Later changes will add reference count checking for struct map, start and end are frequently accessed variables. Add an accessor so that the reference count check is only necessary in one place. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Darren Hart <dvhart@infradead.org> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Dmitriy Vyukov <dvyukov@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: German Gomez <german.gomez@arm.com> Cc: Hao Luo <haoluo@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Madhavan Srinivasan <maddy@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Miaoqian Lin <linmq006@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Riccardo Mancini <rickyman7@gmail.com> Cc: Shunsuke Nakamura <nakamura.shun@fujitsu.com> Cc: Song Liu <song@kernel.org> Cc: Stephane Eranian <eranian@google.com> Cc: Stephen Brennan <stephen.s.brennan@oracle.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Yury Norov <yury.norov@gmail.com> Link: https://lore.kernel.org/r/20230320212248.1175731-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-03-20 14:22:36 -07:00
ams->ms.sym ? ams->ms.sym->start + map__start(ams->ms.map) : 0,
saddr);
err = symbol__account_cycles(ams->al_addr, saddr, ams->ms.sym, cycles);
if (err)
pr_debug2("account_cycles failed %d\n", err);
return err;
}
struct annotation_line *annotated_source__get_line(struct annotated_source *src,
s64 offset)
{
struct annotation_line *al;
list_for_each_entry(al, &src->source, node) {
if (al->offset == offset)
return al;
}
return NULL;
}
static unsigned annotation__count_insn(struct annotation *notes, u64 start, u64 end)
{
struct annotation_line *al;
unsigned n_insn = 0;
al = annotated_source__get_line(notes->src, start);
if (al == NULL)
return 0;
list_for_each_entry_from(al, &notes->src->source, node) {
if (al->offset == -1)
continue;
if ((u64)al->offset > end)
break;
n_insn++;
}
return n_insn;
}
static void annotated_branch__delete(struct annotated_branch *branch)
{
if (branch) {
zfree(&branch->cycles_hist);
free(branch);
}
}
static void annotation__count_and_fill(struct annotation *notes, u64 start, u64 end, struct cyc_hist *ch)
{
unsigned n_insn;
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
unsigned int cover_insn = 0;
n_insn = annotation__count_insn(notes, start, end);
if (n_insn && ch->num && ch->cycles) {
struct annotation_line *al;
struct annotated_branch *branch;
float ipc = n_insn / ((double)ch->cycles / (double)ch->num);
/* Hide data when there are too many overlaps. */
perf annotate: Remove hist__account_cycles() from callback The hist__account_cycles() function is executed when the hist_iter__branch_callback() is called. But it looks it's not necessary. In hist__account_cycles, it already walks on all branch entries. This patch moves the hist__account_cycles out of callback, now the data processing is much faster than before. Previous code has an issue that the ch[offset].num++ (in __symbol__account_cycles) is executed repeatedly since hist__account_cycles is called in each hist_iter__branch_callback, so the counting of ch[offset].num is not correct (too big). With this patch, the issue is fixed. And we don't need the code of "ch->reset >= ch->num / 2" to check if there are too many overlaps (in annotation__count_and_fill), otherwise some data would be hidden. Now, we can try, for example: perf record -b ... perf annotate or perf report -s symbol The before/after output should be no change. v3: --- Fix the crash in stdio mode. Like previous code, it needs the checking of ui__has_annotation() before hist__account_cycles() v2: --- 1. Cover the similar perf report 2. Remove the checking code "ch->reset >= ch->num / 2" 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: Jin Yao <yao.jin@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/1552684577-29041-1-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-03-16 05:16:17 +08:00
if (ch->reset >= 0x7fff)
return;
al = annotated_source__get_line(notes->src, start);
if (al == NULL)
return;
list_for_each_entry_from(al, &notes->src->source, node) {
if (al->offset == -1)
continue;
if ((u64)al->offset > end)
break;
if (al->cycles && al->cycles->ipc == 0.0) {
al->cycles->ipc = ipc;
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
cover_insn++;
}
}
branch = annotation__get_branch(notes);
if (cover_insn && branch) {
branch->hit_cycles += ch->cycles;
branch->hit_insn += n_insn * ch->num;
branch->cover_insn += cover_insn;
}
}
}
static int annotation__compute_ipc(struct annotation *notes, size_t size)
{
int err = 0;
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
s64 offset;
if (!notes->branch || !notes->branch->cycles_hist)
return 0;
notes->branch->total_insn = annotation__count_insn(notes, 0, size - 1);
notes->branch->hit_cycles = 0;
notes->branch->hit_insn = 0;
notes->branch->cover_insn = 0;
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
annotation__lock(notes);
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
for (offset = size - 1; offset >= 0; --offset) {
struct cyc_hist *ch;
ch = &notes->branch->cycles_hist[offset];
if (ch && ch->cycles) {
struct annotation_line *al;
al = annotated_source__get_line(notes->src, offset);
if (al && al->cycles == NULL) {
al->cycles = zalloc(sizeof(*al->cycles));
if (al->cycles == NULL) {
err = ENOMEM;
break;
}
}
if (ch->have_start)
annotation__count_and_fill(notes, ch->start, offset, ch);
if (al && ch->num_aggr) {
al->cycles->avg = ch->cycles_aggr / ch->num_aggr;
al->cycles->max = ch->cycles_max;
al->cycles->min = ch->cycles_min;
}
}
}
if (err) {
while (++offset < (s64)size) {
struct cyc_hist *ch = &notes->branch->cycles_hist[offset];
if (ch && ch->cycles) {
struct annotation_line *al;
al = annotated_source__get_line(notes->src, offset);
if (al)
zfree(&al->cycles);
}
}
}
annotation__unlock(notes);
return 0;
}
int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample,
struct evsel *evsel)
{
return symbol__inc_addr_samples(&ams->ms, evsel, ams->al_addr, sample);
}
int hist_entry__inc_addr_samples(struct hist_entry *he, struct perf_sample *sample,
struct evsel *evsel, u64 ip)
{
return symbol__inc_addr_samples(&he->ms, evsel, ip, sample);
}
void annotation__exit(struct annotation *notes)
perf symbols: Factor out annotation init/exit The exit function fixes a memory leak with the src field as detected by leak sanitizer. An example of which is: Indirect leak of 25133184 byte(s) in 207 object(s) allocated from: #0 0x7f199ecfe987 in __interceptor_calloc libsanitizer/asan/asan_malloc_linux.cpp:154 #1 0x55defe638224 in annotated_source__alloc_histograms util/annotate.c:803 #2 0x55defe6397e4 in symbol__hists util/annotate.c:952 #3 0x55defe639908 in symbol__inc_addr_samples util/annotate.c:968 #4 0x55defe63aa29 in hist_entry__inc_addr_samples util/annotate.c:1119 #5 0x55defe499a79 in hist_iter__report_callback tools/perf/builtin-report.c:182 #6 0x55defe7a859d in hist_entry_iter__add util/hist.c:1236 #7 0x55defe49aa63 in process_sample_event tools/perf/builtin-report.c:315 #8 0x55defe731bc8 in evlist__deliver_sample util/session.c:1473 #9 0x55defe731e38 in machines__deliver_event util/session.c:1510 #10 0x55defe732a23 in perf_session__deliver_event util/session.c:1590 #11 0x55defe72951e in ordered_events__deliver_event util/session.c:183 #12 0x55defe740082 in do_flush util/ordered-events.c:244 #13 0x55defe7407cb in __ordered_events__flush util/ordered-events.c:323 #14 0x55defe740a61 in ordered_events__flush util/ordered-events.c:341 #15 0x55defe73837f in __perf_session__process_events util/session.c:2390 #16 0x55defe7385ff in perf_session__process_events util/session.c:2420 ... Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Martin Liška <mliska@suse.cz> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20211112035124.94327-3-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2021-11-11 19:51:24 -08:00
{
annotated_source__delete(notes->src);
annotated_branch__delete(notes->branch);
perf symbols: Factor out annotation init/exit The exit function fixes a memory leak with the src field as detected by leak sanitizer. An example of which is: Indirect leak of 25133184 byte(s) in 207 object(s) allocated from: #0 0x7f199ecfe987 in __interceptor_calloc libsanitizer/asan/asan_malloc_linux.cpp:154 #1 0x55defe638224 in annotated_source__alloc_histograms util/annotate.c:803 #2 0x55defe6397e4 in symbol__hists util/annotate.c:952 #3 0x55defe639908 in symbol__inc_addr_samples util/annotate.c:968 #4 0x55defe63aa29 in hist_entry__inc_addr_samples util/annotate.c:1119 #5 0x55defe499a79 in hist_iter__report_callback tools/perf/builtin-report.c:182 #6 0x55defe7a859d in hist_entry_iter__add util/hist.c:1236 #7 0x55defe49aa63 in process_sample_event tools/perf/builtin-report.c:315 #8 0x55defe731bc8 in evlist__deliver_sample util/session.c:1473 #9 0x55defe731e38 in machines__deliver_event util/session.c:1510 #10 0x55defe732a23 in perf_session__deliver_event util/session.c:1590 #11 0x55defe72951e in ordered_events__deliver_event util/session.c:183 #12 0x55defe740082 in do_flush util/ordered-events.c:244 #13 0x55defe7407cb in __ordered_events__flush util/ordered-events.c:323 #14 0x55defe740a61 in ordered_events__flush util/ordered-events.c:341 #15 0x55defe73837f in __perf_session__process_events util/session.c:2390 #16 0x55defe7385ff in perf_session__process_events util/session.c:2420 ... Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Martin Liška <mliska@suse.cz> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20211112035124.94327-3-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2021-11-11 19:51:24 -08:00
}
static struct sharded_mutex *sharded_mutex;
static void annotation__init_sharded_mutex(void)
perf symbols: Factor out annotation init/exit The exit function fixes a memory leak with the src field as detected by leak sanitizer. An example of which is: Indirect leak of 25133184 byte(s) in 207 object(s) allocated from: #0 0x7f199ecfe987 in __interceptor_calloc libsanitizer/asan/asan_malloc_linux.cpp:154 #1 0x55defe638224 in annotated_source__alloc_histograms util/annotate.c:803 #2 0x55defe6397e4 in symbol__hists util/annotate.c:952 #3 0x55defe639908 in symbol__inc_addr_samples util/annotate.c:968 #4 0x55defe63aa29 in hist_entry__inc_addr_samples util/annotate.c:1119 #5 0x55defe499a79 in hist_iter__report_callback tools/perf/builtin-report.c:182 #6 0x55defe7a859d in hist_entry_iter__add util/hist.c:1236 #7 0x55defe49aa63 in process_sample_event tools/perf/builtin-report.c:315 #8 0x55defe731bc8 in evlist__deliver_sample util/session.c:1473 #9 0x55defe731e38 in machines__deliver_event util/session.c:1510 #10 0x55defe732a23 in perf_session__deliver_event util/session.c:1590 #11 0x55defe72951e in ordered_events__deliver_event util/session.c:183 #12 0x55defe740082 in do_flush util/ordered-events.c:244 #13 0x55defe7407cb in __ordered_events__flush util/ordered-events.c:323 #14 0x55defe740a61 in ordered_events__flush util/ordered-events.c:341 #15 0x55defe73837f in __perf_session__process_events util/session.c:2390 #16 0x55defe7385ff in perf_session__process_events util/session.c:2420 ... Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Martin Liška <mliska@suse.cz> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20211112035124.94327-3-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2021-11-11 19:51:24 -08:00
{
/* As many mutexes as there are CPUs. */
sharded_mutex = sharded_mutex__new(cpu__max_present_cpu().cpu);
}
static size_t annotation__hash(const struct annotation *notes)
{
return (size_t)notes;
perf symbols: Factor out annotation init/exit The exit function fixes a memory leak with the src field as detected by leak sanitizer. An example of which is: Indirect leak of 25133184 byte(s) in 207 object(s) allocated from: #0 0x7f199ecfe987 in __interceptor_calloc libsanitizer/asan/asan_malloc_linux.cpp:154 #1 0x55defe638224 in annotated_source__alloc_histograms util/annotate.c:803 #2 0x55defe6397e4 in symbol__hists util/annotate.c:952 #3 0x55defe639908 in symbol__inc_addr_samples util/annotate.c:968 #4 0x55defe63aa29 in hist_entry__inc_addr_samples util/annotate.c:1119 #5 0x55defe499a79 in hist_iter__report_callback tools/perf/builtin-report.c:182 #6 0x55defe7a859d in hist_entry_iter__add util/hist.c:1236 #7 0x55defe49aa63 in process_sample_event tools/perf/builtin-report.c:315 #8 0x55defe731bc8 in evlist__deliver_sample util/session.c:1473 #9 0x55defe731e38 in machines__deliver_event util/session.c:1510 #10 0x55defe732a23 in perf_session__deliver_event util/session.c:1590 #11 0x55defe72951e in ordered_events__deliver_event util/session.c:183 #12 0x55defe740082 in do_flush util/ordered-events.c:244 #13 0x55defe7407cb in __ordered_events__flush util/ordered-events.c:323 #14 0x55defe740a61 in ordered_events__flush util/ordered-events.c:341 #15 0x55defe73837f in __perf_session__process_events util/session.c:2390 #16 0x55defe7385ff in perf_session__process_events util/session.c:2420 ... Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Martin Liška <mliska@suse.cz> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20211112035124.94327-3-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2021-11-11 19:51:24 -08:00
}
static struct mutex *annotation__get_mutex(const struct annotation *notes)
{
static pthread_once_t once = PTHREAD_ONCE_INIT;
pthread_once(&once, annotation__init_sharded_mutex);
if (!sharded_mutex)
return NULL;
return sharded_mutex__get_mutex(sharded_mutex, annotation__hash(notes));
}
void annotation__lock(struct annotation *notes)
NO_THREAD_SAFETY_ANALYSIS
{
struct mutex *mutex = annotation__get_mutex(notes);
if (mutex)
mutex_lock(mutex);
}
void annotation__unlock(struct annotation *notes)
NO_THREAD_SAFETY_ANALYSIS
{
struct mutex *mutex = annotation__get_mutex(notes);
if (mutex)
mutex_unlock(mutex);
}
bool annotation__trylock(struct annotation *notes)
{
struct mutex *mutex = annotation__get_mutex(notes);
if (!mutex)
return false;
return mutex_trylock(mutex);
}
void annotation_line__add(struct annotation_line *al, struct list_head *head)
{
list_add_tail(&al->node, head);
}
struct annotation_line *
annotation_line__next(struct annotation_line *pos, struct list_head *head)
{
list_for_each_entry_continue(pos, head, node)
if (pos->offset >= 0)
return pos;
return NULL;
}
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
static const char *annotate__address_color(struct block_range *br)
{
double cov = block_range__coverage(br);
if (cov >= 0) {
/* mark red for >75% coverage */
if (cov > 0.75)
return PERF_COLOR_RED;
/* mark dull for <1% coverage */
if (cov < 0.01)
return PERF_COLOR_NORMAL;
}
return PERF_COLOR_MAGENTA;
}
static const char *annotate__asm_color(struct block_range *br)
{
double cov = block_range__coverage(br);
if (cov >= 0) {
/* mark dull for <1% coverage */
if (cov < 0.01)
return PERF_COLOR_NORMAL;
}
return PERF_COLOR_BLUE;
}
static void annotate__branch_printf(struct block_range *br, u64 addr)
{
bool emit_comment = true;
if (!br)
return;
#if 1
if (br->is_target && br->start == addr) {
struct block_range *branch = br;
double p;
/*
* Find matching branch to our target.
*/
while (!branch->is_branch)
branch = block_range__next(branch);
p = 100 *(double)br->entry / branch->coverage;
if (p > 0.1) {
if (emit_comment) {
emit_comment = false;
printf("\t#");
}
/*
* The percentage of coverage joined at this target in relation
* to the next branch.
*/
printf(" +%.2f%%", p);
}
}
#endif
if (br->is_branch && br->end == addr) {
double p = 100*(double)br->taken / br->coverage;
if (p > 0.1) {
if (emit_comment) {
emit_comment = false;
printf("\t#");
}
/*
* The percentage of coverage leaving at this branch, and
* its prediction ratio.
*/
printf(" -%.2f%% (p:%.2f%%)", p, 100*(double)br->pred / br->taken);
}
}
}
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
static int disasm_line__print(struct disasm_line *dl, u64 start, int addr_fmt_width)
{
s64 offset = dl->al.offset;
const u64 addr = start + offset;
struct block_range *br;
br = block_range__find(addr);
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
color_fprintf(stdout, annotate__address_color(br), " %*" PRIx64 ":", addr_fmt_width, addr);
color_fprintf(stdout, annotate__asm_color(br), "%s", dl->al.line);
annotate__branch_printf(br, addr);
return 0;
}
static int
annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start,
struct evsel *evsel, u64 len, int min_pcnt, int printed,
int max_lines, struct annotation_line *queue, int addr_fmt_width,
int percent_type)
{
struct disasm_line *dl = container_of(al, struct disasm_line, al);
static const char *prev_line;
if (al->offset != -1) {
double max_percent = 0.0;
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
int i, nr_percent = 1;
const char *color;
struct annotation *notes = symbol__annotation(sym);
for (i = 0; i < al->data_nr; i++) {
double percent;
percent = annotation_data__percent(&al->data[i],
percent_type);
if (percent > max_percent)
max_percent = percent;
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
}
if (al->data_nr > nr_percent)
nr_percent = al->data_nr;
perf annotate: Display all available events on --stdio When we perform the following command lines: $ perf record -e "{cycles,branches}" ./div $ perf annotate main --stdio The output shows only the first event, "cycles" and the displaying format is not correct. Percent | Source code & Disassembly of div for cycles (44550 samples) ----------------------------------------------------------------------------------- : : : : Disassembly of section .text: : : 00000000004004b0 <main>: : main(): : : return i; : } : : int main(void) : { 0.00 : 4004b0: push %rbx : int i; : int flag; : volatile double x = 1212121212, y = 121212; : : s_randseed = time(0); 0.00 : 4004b1: xor %edi,%edi : srand(s_randseed); 0.00 : 4004b3: mov $0x77359400,%ebx : : return i; : } The issue is that the value of the 'nr_percent' variable is hardcoded to 1. This patch fixes it. With this patch, the output is: Percent | Source code & Disassembly of div for cycles (44550 samples) ----------------------------------------------------------------------------------- : : : : Disassembly of section .text: : : 00000000004004b0 <main>: : main(): : : return i; : } : : int main(void) : { 0.00 0.00 : 4004b0: push %rbx : int i; : int flag; : volatile double x = 1212121212, y = 121212; : : s_randseed = time(0); 0.00 0.00 : 4004b1: xor %edi,%edi : srand(s_randseed); 0.00 0.00 : 4004b3: mov $0x77359400,%ebx : : return i; : } 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> Fixes: f681d593d1ce ("perf annotate: Remove disasm__calc_percent() from disasm_line__print()") Link: http://lkml.kernel.org/r/1525881435-4092-1-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-05-09 23:57:15 +08:00
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
if (max_percent < min_pcnt)
return -1;
if (max_lines && printed >= max_lines)
return 1;
if (queue != NULL) {
list_for_each_entry_from(queue, &notes->src->source, node) {
if (queue == al)
break;
annotation_line__print(queue, sym, start, evsel, len,
0, 0, 1, NULL, addr_fmt_width,
percent_type);
}
}
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
color = get_percent_color(max_percent);
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
for (i = 0; i < nr_percent; i++) {
struct annotation_data *data = &al->data[i];
double percent;
percent = annotation_data__percent(data, percent_type);
color = get_percent_color(percent);
if (symbol_conf.show_total_period)
color_fprintf(stdout, color, " %11" PRIu64,
data->he.period);
else if (symbol_conf.show_nr_samples)
color_fprintf(stdout, color, " %7" PRIu64,
data->he.nr_samples);
else
color_fprintf(stdout, color, " %7.2f", percent);
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
printf(" : ");
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
disasm_line__print(dl, start, addr_fmt_width);
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
/*
* Also color the filename and line if needed, with
* the same color than the percentage. Don't print it
* twice for close colored addr with the same filename:line
*/
if (al->path) {
if (!prev_line || strcmp(prev_line, al->path)) {
color_fprintf(stdout, color, " // %s", al->path);
prev_line = al->path;
}
}
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
printf("\n");
} else if (max_lines && printed >= max_lines)
return 1;
else {
int width = symbol_conf.show_total_period ? 12 : 8;
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
if (queue)
return -1;
if (evsel__is_group_event(evsel))
width *= evsel->core.nr_members;
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
if (!*al->line)
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
printf(" %*s:\n", width, " ");
else
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
printf(" %*s: %-*d %s\n", width, " ", addr_fmt_width, al->line_nr, al->line);
}
return 0;
}
static void calc_percent(struct annotation *notes,
struct evsel *evsel,
struct annotation_data *data,
s64 offset, s64 end)
{
struct hists *hists = evsel__hists(evsel);
int evidx = evsel->core.idx;
struct sym_hist *sym_hist = annotation__histogram(notes, evidx);
unsigned int hits = 0;
u64 period = 0;
while (offset < end) {
struct sym_hist_entry *entry;
entry = annotated_source__hist_entry(notes->src, evidx, offset);
if (entry) {
hits += entry->nr_samples;
period += entry->period;
}
++offset;
}
if (sym_hist->nr_samples) {
data->he.period = period;
data->he.nr_samples = hits;
data->percent[PERCENT_HITS_LOCAL] = 100.0 * hits / sym_hist->nr_samples;
}
if (hists->stats.nr_non_filtered_samples)
data->percent[PERCENT_HITS_GLOBAL] = 100.0 * hits / hists->stats.nr_non_filtered_samples;
if (sym_hist->period)
data->percent[PERCENT_PERIOD_LOCAL] = 100.0 * period / sym_hist->period;
if (hists->stats.total_period)
data->percent[PERCENT_PERIOD_GLOBAL] = 100.0 * period / hists->stats.total_period;
}
static void annotation__calc_percent(struct annotation *notes,
struct evsel *leader, s64 len)
{
struct annotation_line *al, *next;
struct evsel *evsel;
list_for_each_entry(al, &notes->src->source, node) {
s64 end;
int i = 0;
if (al->offset == -1)
continue;
next = annotation_line__next(al, &notes->src->source);
end = next ? next->offset : len;
for_each_group_evsel(evsel, leader) {
struct annotation_data *data;
BUG_ON(i >= al->data_nr);
data = &al->data[i++];
calc_percent(notes, evsel, data, al->offset, end);
}
}
}
void symbol__calc_percent(struct symbol *sym, struct evsel *evsel)
{
struct annotation *notes = symbol__annotation(sym);
annotation__calc_percent(notes, evsel, symbol__size(sym));
}
static int evsel__get_arch(struct evsel *evsel, struct arch **parch)
{
struct perf_env *env = evsel__env(evsel);
const char *arch_name = perf_env__arch(env);
struct arch *arch;
int err;
if (!arch_name) {
*parch = NULL;
return errno;
}
*parch = arch = arch__find(arch_name);
if (arch == NULL) {
pr_err("%s: unsupported arch %s\n", __func__, arch_name);
return ENOTSUP;
}
if (arch->init) {
err = arch->init(arch, env ? env->cpuid : NULL);
if (err) {
pr_err("%s: failed to initialize %s arch priv area\n",
__func__, arch->name);
return err;
}
}
return 0;
}
int symbol__annotate(struct map_symbol *ms, struct evsel *evsel,
struct arch **parch)
{
struct symbol *sym = ms->sym;
struct annotation *notes = symbol__annotation(sym);
struct annotate_args args = {
.evsel = evsel,
.options = &annotate_opts,
};
struct arch *arch = NULL;
int err;
err = evsel__get_arch(evsel, &arch);
if (err < 0)
return err;
if (parch)
*parch = arch;
args.arch = arch;
args.ms = *ms;
if (annotate_opts.full_addr)
notes->src->start = map__objdump_2mem(ms->map, ms->sym->start);
else
notes->src->start = map__rip_2objdump(ms->map, ms->sym->start);
return symbol__disassemble(sym, &args);
}
static void insert_source_line(struct rb_root *root, struct annotation_line *al)
{
struct annotation_line *iter;
struct rb_node **p = &root->rb_node;
struct rb_node *parent = NULL;
unsigned int percent_type = annotate_opts.percent_type;
int i, ret;
while (*p != NULL) {
parent = *p;
iter = rb_entry(parent, struct annotation_line, rb_node);
ret = strcmp(iter->path, al->path);
if (ret == 0) {
for (i = 0; i < al->data_nr; i++) {
iter->data[i].percent_sum += annotation_data__percent(&al->data[i],
percent_type);
}
return;
}
if (ret < 0)
p = &(*p)->rb_left;
else
p = &(*p)->rb_right;
}
for (i = 0; i < al->data_nr; i++) {
al->data[i].percent_sum = annotation_data__percent(&al->data[i],
percent_type);
}
rb_link_node(&al->rb_node, parent, p);
rb_insert_color(&al->rb_node, root);
}
static int cmp_source_line(struct annotation_line *a, struct annotation_line *b)
{
int i;
for (i = 0; i < a->data_nr; i++) {
if (a->data[i].percent_sum == b->data[i].percent_sum)
continue;
return a->data[i].percent_sum > b->data[i].percent_sum;
}
return 0;
}
static void __resort_source_line(struct rb_root *root, struct annotation_line *al)
{
struct annotation_line *iter;
struct rb_node **p = &root->rb_node;
struct rb_node *parent = NULL;
while (*p != NULL) {
parent = *p;
iter = rb_entry(parent, struct annotation_line, rb_node);
if (cmp_source_line(al, iter))
p = &(*p)->rb_left;
else
p = &(*p)->rb_right;
}
rb_link_node(&al->rb_node, parent, p);
rb_insert_color(&al->rb_node, root);
}
static void resort_source_line(struct rb_root *dest_root, struct rb_root *src_root)
{
struct annotation_line *al;
struct rb_node *node;
node = rb_first(src_root);
while (node) {
struct rb_node *next;
al = rb_entry(node, struct annotation_line, rb_node);
next = rb_next(node);
rb_erase(node, src_root);
__resort_source_line(dest_root, al);
node = next;
}
}
static void print_summary(struct rb_root *root, const char *filename)
{
struct annotation_line *al;
struct rb_node *node;
printf("\nSorted summary for file %s\n", filename);
printf("----------------------------------------------\n\n");
if (RB_EMPTY_ROOT(root)) {
printf(" Nothing higher than %1.1f%%\n", MIN_GREEN);
return;
}
node = rb_first(root);
while (node) {
double percent, percent_max = 0.0;
const char *color;
char *path;
int i;
al = rb_entry(node, struct annotation_line, rb_node);
for (i = 0; i < al->data_nr; i++) {
percent = al->data[i].percent_sum;
color = get_percent_color(percent);
color_fprintf(stdout, color, " %7.2f", percent);
if (percent > percent_max)
percent_max = percent;
}
path = al->path;
color = get_percent_color(percent_max);
color_fprintf(stdout, color, " %s\n", path);
node = rb_next(node);
}
}
static void symbol__annotate_hits(struct symbol *sym, struct evsel *evsel)
{
int evidx = evsel->core.idx;
struct annotation *notes = symbol__annotation(sym);
struct sym_hist *h = annotation__histogram(notes, evidx);
u64 len = symbol__size(sym), offset;
for (offset = 0; offset < len; ++offset) {
struct sym_hist_entry *entry;
entry = annotated_source__hist_entry(notes->src, evidx, offset);
if (entry && entry->nr_samples != 0)
printf("%*" PRIx64 ": %" PRIu64 "\n", BITS_PER_LONG / 2,
sym->start + offset, entry->nr_samples);
}
printf("%*s: %" PRIu64 "\n", BITS_PER_LONG / 2, "h->nr_samples", h->nr_samples);
}
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
static int annotated_source__addr_fmt_width(struct list_head *lines, u64 start)
{
char bf[32];
struct annotation_line *line;
list_for_each_entry_reverse(line, lines, node) {
if (line->offset != -1)
return scnprintf(bf, sizeof(bf), "%" PRIx64, start + line->offset);
}
return 0;
}
int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel)
{
struct map *map = ms->map;
struct symbol *sym = ms->sym;
perf map: Add accessor for dso Later changes will add reference count checking for struct map, with dso being the most frequently accessed variable. Add an accessor so that the reference count check is only necessary in one place. Additional changes: - add a dso variable to avoid repeated map__dso calls. - in builtin-mem.c dump_raw_samples, code only partially tested for dso == NULL. Make the possibility of NULL consistent. - in thread.c thread__memcpy fix use of spaces and use tabs. Committer notes: Did missing conversions on these files: tools/perf/arch/powerpc/util/skip-callchain-idx.c tools/perf/arch/powerpc/util/sym-handling.c tools/perf/ui/browsers/hists.c tools/perf/ui/gtk/annotate.c tools/perf/util/cs-etm.c tools/perf/util/thread.c tools/perf/util/unwind-libunwind-local.c tools/perf/util/unwind-libunwind.c Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Darren Hart <dvhart@infradead.org> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Dmitriy Vyukov <dvyukov@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: German Gomez <german.gomez@arm.com> Cc: Hao Luo <haoluo@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Madhavan Srinivasan <maddy@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Miaoqian Lin <linmq006@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Riccardo Mancini <rickyman7@gmail.com> Cc: Shunsuke Nakamura <nakamura.shun@fujitsu.com> Cc: Song Liu <song@kernel.org> Cc: Stephane Eranian <eranian@google.com> Cc: Stephen Brennan <stephen.s.brennan@oracle.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Yury Norov <yury.norov@gmail.com> Link: https://lore.kernel.org/r/20230320212248.1175731-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-03-20 14:22:35 -07:00
struct dso *dso = map__dso(map);
char *filename;
const char *d_filename;
const char *evsel_name = evsel__name(evsel);
struct annotation *notes = symbol__annotation(sym);
struct sym_hist *h = annotation__histogram(notes, evsel->core.idx);
struct annotation_line *pos, *queue = NULL;
struct annotation_options *opts = &annotate_opts;
u64 start = map__rip_2objdump(map, sym->start);
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
int printed = 2, queue_len = 0, addr_fmt_width;
int more = 0;
bool context = opts->context;
u64 len;
int width = symbol_conf.show_total_period ? 12 : 8;
int graph_dotted_len;
char buf[512];
filename = strdup(dso->long_name);
if (!filename)
return -ENOMEM;
if (opts->full_path)
d_filename = filename;
else
d_filename = basename(filename);
len = symbol__size(sym);
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
if (evsel__is_group_event(evsel)) {
width *= evsel->core.nr_members;
evsel__group_desc(evsel, buf, sizeof(buf));
evsel_name = buf;
}
graph_dotted_len = printf(" %-*.*s| Source code & Disassembly of %s for %s (%" PRIu64 " samples, "
"percent: %s)\n",
width, width, symbol_conf.show_total_period ? "Period" :
symbol_conf.show_nr_samples ? "Samples" : "Percent",
d_filename, evsel_name, h->nr_samples,
percent_type_str(opts->percent_type));
printf("%-*.*s----\n",
graph_dotted_len, graph_dotted_len, graph_dotted_line);
if (verbose > 0)
symbol__annotate_hits(sym, evsel);
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
addr_fmt_width = annotated_source__addr_fmt_width(&notes->src->source, start);
list_for_each_entry(pos, &notes->src->source, node) {
int err;
if (context && queue == NULL) {
queue = pos;
queue_len = 0;
}
err = annotation_line__print(pos, sym, start, evsel, len,
opts->min_pcnt, printed, opts->max_lines,
queue, addr_fmt_width, opts->percent_type);
switch (err) {
case 0:
++printed;
if (context) {
printed += queue_len;
queue = NULL;
queue_len = 0;
}
break;
case 1:
/* filtered by max_lines */
++more;
break;
case -1:
default:
/*
* Filtered by min_pcnt or non IP lines when
* context != 0
*/
if (!context)
break;
if (queue_len == context)
queue = list_entry(queue->node.next, typeof(*queue), node);
else
++queue_len;
break;
}
}
free(filename);
return more;
}
static void FILE__set_percent_color(void *fp __maybe_unused,
double percent __maybe_unused,
bool current __maybe_unused)
{
}
static int FILE__set_jumps_percent_color(void *fp __maybe_unused,
int nr __maybe_unused, bool current __maybe_unused)
{
return 0;
}
static int FILE__set_color(void *fp __maybe_unused, int color __maybe_unused)
{
return 0;
}
static void FILE__printf(void *fp, const char *fmt, ...)
{
va_list args;
va_start(args, fmt);
vfprintf(fp, fmt, args);
va_end(args);
}
static void FILE__write_graph(void *fp, int graph)
{
const char *s;
switch (graph) {
case DARROW_CHAR: s = ""; break;
case UARROW_CHAR: s = ""; break;
case LARROW_CHAR: s = ""; break;
case RARROW_CHAR: s = ""; break;
default: s = "?"; break;
}
fputs(s, fp);
}
static int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp)
{
struct annotation *notes = symbol__annotation(sym);
struct annotation_write_ops wops = {
.first_line = true,
.obj = fp,
.set_color = FILE__set_color,
.set_percent_color = FILE__set_percent_color,
.set_jumps_percent_color = FILE__set_jumps_percent_color,
.printf = FILE__printf,
.write_graph = FILE__write_graph,
};
struct annotation_line *al;
list_for_each_entry(al, &notes->src->source, node) {
if (annotation_line__filter(al))
continue;
annotation_line__write(al, notes, &wops);
fputc('\n', fp);
wops.first_line = false;
}
return 0;
}
int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel)
{
const char *ev_name = evsel__name(evsel);
char buf[1024];
char *filename;
int err = -1;
FILE *fp;
if (asprintf(&filename, "%s.annotation", ms->sym->name) < 0)
return -1;
fp = fopen(filename, "w");
if (fp == NULL)
goto out_free_filename;
if (evsel__is_group_event(evsel)) {
evsel__group_desc(evsel, buf, sizeof(buf));
ev_name = buf;
}
fprintf(fp, "%s() %s\nEvent: %s\n\n",
perf map: Add accessor for dso Later changes will add reference count checking for struct map, with dso being the most frequently accessed variable. Add an accessor so that the reference count check is only necessary in one place. Additional changes: - add a dso variable to avoid repeated map__dso calls. - in builtin-mem.c dump_raw_samples, code only partially tested for dso == NULL. Make the possibility of NULL consistent. - in thread.c thread__memcpy fix use of spaces and use tabs. Committer notes: Did missing conversions on these files: tools/perf/arch/powerpc/util/skip-callchain-idx.c tools/perf/arch/powerpc/util/sym-handling.c tools/perf/ui/browsers/hists.c tools/perf/ui/gtk/annotate.c tools/perf/util/cs-etm.c tools/perf/util/thread.c tools/perf/util/unwind-libunwind-local.c tools/perf/util/unwind-libunwind.c Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Darren Hart <dvhart@infradead.org> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Dmitriy Vyukov <dvyukov@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: German Gomez <german.gomez@arm.com> Cc: Hao Luo <haoluo@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Madhavan Srinivasan <maddy@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Miaoqian Lin <linmq006@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Riccardo Mancini <rickyman7@gmail.com> Cc: Shunsuke Nakamura <nakamura.shun@fujitsu.com> Cc: Song Liu <song@kernel.org> Cc: Stephane Eranian <eranian@google.com> Cc: Stephen Brennan <stephen.s.brennan@oracle.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Yury Norov <yury.norov@gmail.com> Link: https://lore.kernel.org/r/20230320212248.1175731-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-03-20 14:22:35 -07:00
ms->sym->name, map__dso(ms->map)->long_name, ev_name);
symbol__annotate_fprintf2(ms->sym, fp);
fclose(fp);
err = 0;
out_free_filename:
free(filename);
return err;
}
void symbol__annotate_zero_histogram(struct symbol *sym, int evidx)
{
struct annotation *notes = symbol__annotation(sym);
struct sym_hist *h = annotation__histogram(notes, evidx);
memset(h, 0, sizeof(*notes->src->histograms) * notes->src->nr_histograms);
}
void symbol__annotate_decay_histogram(struct symbol *sym, int evidx)
{
struct annotation *notes = symbol__annotation(sym);
struct sym_hist *h = annotation__histogram(notes, evidx);
struct annotation_line *al;
h->nr_samples = 0;
list_for_each_entry(al, &notes->src->source, node) {
struct sym_hist_entry *entry;
if (al->offset == -1)
continue;
entry = annotated_source__hist_entry(notes->src, evidx, al->offset);
if (entry == NULL)
continue;
entry->nr_samples = entry->nr_samples * 7 / 8;
h->nr_samples += entry->nr_samples;
}
}
void annotated_source__purge(struct annotated_source *as)
{
struct annotation_line *al, *n;
list_for_each_entry_safe(al, n, &as->source, node) {
list_del_init(&al->node);
disasm_line__free(disasm_line(al));
}
}
static size_t disasm_line__fprintf(struct disasm_line *dl, FILE *fp)
{
size_t printed;
if (dl->al.offset == -1)
return fprintf(fp, "%s\n", dl->al.line);
printed = fprintf(fp, "%#" PRIx64 " %s", dl->al.offset, dl->ins.name);
if (dl->ops.raw[0] != '\0') {
printed += fprintf(fp, "%.*s %s\n", 6 - (int)printed, " ",
dl->ops.raw);
}
return printed + fprintf(fp, "\n");
}
size_t disasm__fprintf(struct list_head *head, FILE *fp)
{
struct disasm_line *pos;
size_t printed = 0;
list_for_each_entry(pos, head, al.node)
printed += disasm_line__fprintf(pos, fp);
return printed;
}
bool disasm_line__is_valid_local_jump(struct disasm_line *dl, struct symbol *sym)
{
if (!dl || !dl->ins.ops || !ins__is_jump(&dl->ins) ||
!disasm_line__has_local_offset(dl) || dl->ops.target.offset < 0 ||
dl->ops.target.offset >= (s64)symbol__size(sym))
return false;
return true;
}
static void
annotation__mark_jump_targets(struct annotation *notes, struct symbol *sym)
{
struct annotation_line *al;
/* PLT symbols contain external offsets */
if (strstr(sym->name, "@plt"))
return;
list_for_each_entry(al, &notes->src->source, node) {
struct disasm_line *dl;
struct annotation_line *target;
dl = disasm_line(al);
if (!disasm_line__is_valid_local_jump(dl, sym))
continue;
target = annotated_source__get_line(notes->src,
dl->ops.target.offset);
/*
* FIXME: Oops, no jump target? Buggy disassembler? Or do we
* have to adjust to the previous offset?
*/
if (target == NULL)
continue;
if (++target->jump_sources > notes->src->max_jump_sources)
notes->src->max_jump_sources = target->jump_sources;
}
}
static void annotation__set_index(struct annotation *notes)
{
struct annotation_line *al;
struct annotated_source *src = notes->src;
src->widths.max_line_len = 0;
src->nr_entries = 0;
src->nr_asm_entries = 0;
list_for_each_entry(al, &src->source, node) {
size_t line_len = strlen(al->line);
if (src->widths.max_line_len < line_len)
src->widths.max_line_len = line_len;
al->idx = src->nr_entries++;
if (al->offset != -1)
al->idx_asm = src->nr_asm_entries++;
else
al->idx_asm = -1;
}
}
static inline int width_jumps(int n)
{
if (n >= 100)
return 5;
if (n / 10)
return 2;
return 1;
}
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
static int annotation__max_ins_name(struct annotation *notes)
{
int max_name = 0, len;
struct annotation_line *al;
list_for_each_entry(al, &notes->src->source, node) {
if (al->offset == -1)
continue;
len = strlen(disasm_line(al)->ins.name);
if (max_name < len)
max_name = len;
}
return max_name;
}
static void
annotation__init_column_widths(struct annotation *notes, struct symbol *sym)
{
notes->src->widths.addr = notes->src->widths.target =
notes->src->widths.min_addr = hex_width(symbol__size(sym));
notes->src->widths.max_addr = hex_width(sym->end);
notes->src->widths.jumps = width_jumps(notes->src->max_jump_sources);
notes->src->widths.max_ins_name = annotation__max_ins_name(notes);
}
void annotation__update_column_widths(struct annotation *notes)
{
if (annotate_opts.use_offset)
notes->src->widths.target = notes->src->widths.min_addr;
else if (annotate_opts.full_addr)
notes->src->widths.target = BITS_PER_LONG / 4;
else
notes->src->widths.target = notes->src->widths.max_addr;
notes->src->widths.addr = notes->src->widths.target;
if (annotate_opts.show_nr_jumps)
notes->src->widths.addr += notes->src->widths.jumps + 1;
}
void annotation__toggle_full_addr(struct annotation *notes, struct map_symbol *ms)
{
annotate_opts.full_addr = !annotate_opts.full_addr;
if (annotate_opts.full_addr)
notes->src->start = map__objdump_2mem(ms->map, ms->sym->start);
else
notes->src->start = map__rip_2objdump(ms->map, ms->sym->start);
annotation__update_column_widths(notes);
}
static void annotation__calc_lines(struct annotation *notes, struct map_symbol *ms,
struct rb_root *root)
{
struct annotation_line *al;
struct rb_root tmp_root = RB_ROOT;
list_for_each_entry(al, &notes->src->source, node) {
double percent_max = 0.0;
u64 addr;
int i;
for (i = 0; i < al->data_nr; i++) {
double percent;
percent = annotation_data__percent(&al->data[i],
annotate_opts.percent_type);
if (percent > percent_max)
percent_max = percent;
}
if (percent_max <= 0.5)
continue;
addr = map__rip_2objdump(ms->map, ms->sym->start);
al->path = get_srcline(map__dso(ms->map), addr + al->offset, NULL,
false, true, ms->sym->start + al->offset);
insert_source_line(&tmp_root, al);
}
resort_source_line(root, &tmp_root);
}
static void symbol__calc_lines(struct map_symbol *ms, struct rb_root *root)
{
struct annotation *notes = symbol__annotation(ms->sym);
annotation__calc_lines(notes, ms, root);
}
int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel)
{
perf map: Add accessor for dso Later changes will add reference count checking for struct map, with dso being the most frequently accessed variable. Add an accessor so that the reference count check is only necessary in one place. Additional changes: - add a dso variable to avoid repeated map__dso calls. - in builtin-mem.c dump_raw_samples, code only partially tested for dso == NULL. Make the possibility of NULL consistent. - in thread.c thread__memcpy fix use of spaces and use tabs. Committer notes: Did missing conversions on these files: tools/perf/arch/powerpc/util/skip-callchain-idx.c tools/perf/arch/powerpc/util/sym-handling.c tools/perf/ui/browsers/hists.c tools/perf/ui/gtk/annotate.c tools/perf/util/cs-etm.c tools/perf/util/thread.c tools/perf/util/unwind-libunwind-local.c tools/perf/util/unwind-libunwind.c Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Darren Hart <dvhart@infradead.org> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Dmitriy Vyukov <dvyukov@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: German Gomez <german.gomez@arm.com> Cc: Hao Luo <haoluo@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Madhavan Srinivasan <maddy@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Miaoqian Lin <linmq006@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Riccardo Mancini <rickyman7@gmail.com> Cc: Shunsuke Nakamura <nakamura.shun@fujitsu.com> Cc: Song Liu <song@kernel.org> Cc: Stephane Eranian <eranian@google.com> Cc: Stephen Brennan <stephen.s.brennan@oracle.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Yury Norov <yury.norov@gmail.com> Link: https://lore.kernel.org/r/20230320212248.1175731-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-03-20 14:22:35 -07:00
struct dso *dso = map__dso(ms->map);
struct symbol *sym = ms->sym;
struct rb_root source_line = RB_ROOT;
struct hists *hists = evsel__hists(evsel);
char buf[1024];
int err;
err = symbol__annotate2(ms, evsel, NULL);
if (err) {
char msg[BUFSIZ];
dso->annotate_warned = true;
symbol__strerror_disassemble(ms, err, msg, sizeof(msg));
ui__error("Couldn't annotate %s:\n%s", sym->name, msg);
return -1;
}
if (annotate_opts.print_lines) {
srcline_full_filename = annotate_opts.full_path;
symbol__calc_lines(ms, &source_line);
print_summary(&source_line, dso->long_name);
}
hists__scnprintf_title(hists, buf, sizeof(buf));
fprintf(stdout, "%s, [percent: %s]\n%s() %s\n",
buf, percent_type_str(annotate_opts.percent_type), sym->name,
dso->long_name);
symbol__annotate_fprintf2(sym, stdout);
annotated_source__purge(symbol__annotation(sym)->src);
return 0;
}
int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel)
{
perf map: Add accessor for dso Later changes will add reference count checking for struct map, with dso being the most frequently accessed variable. Add an accessor so that the reference count check is only necessary in one place. Additional changes: - add a dso variable to avoid repeated map__dso calls. - in builtin-mem.c dump_raw_samples, code only partially tested for dso == NULL. Make the possibility of NULL consistent. - in thread.c thread__memcpy fix use of spaces and use tabs. Committer notes: Did missing conversions on these files: tools/perf/arch/powerpc/util/skip-callchain-idx.c tools/perf/arch/powerpc/util/sym-handling.c tools/perf/ui/browsers/hists.c tools/perf/ui/gtk/annotate.c tools/perf/util/cs-etm.c tools/perf/util/thread.c tools/perf/util/unwind-libunwind-local.c tools/perf/util/unwind-libunwind.c Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Darren Hart <dvhart@infradead.org> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Dmitriy Vyukov <dvyukov@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: German Gomez <german.gomez@arm.com> Cc: Hao Luo <haoluo@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Madhavan Srinivasan <maddy@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Miaoqian Lin <linmq006@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Riccardo Mancini <rickyman7@gmail.com> Cc: Shunsuke Nakamura <nakamura.shun@fujitsu.com> Cc: Song Liu <song@kernel.org> Cc: Stephane Eranian <eranian@google.com> Cc: Stephen Brennan <stephen.s.brennan@oracle.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Yury Norov <yury.norov@gmail.com> Link: https://lore.kernel.org/r/20230320212248.1175731-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-03-20 14:22:35 -07:00
struct dso *dso = map__dso(ms->map);
struct symbol *sym = ms->sym;
struct rb_root source_line = RB_ROOT;
int err;
err = symbol__annotate(ms, evsel, NULL);
if (err) {
char msg[BUFSIZ];
dso->annotate_warned = true;
symbol__strerror_disassemble(ms, err, msg, sizeof(msg));
ui__error("Couldn't annotate %s:\n%s", sym->name, msg);
return -1;
}
symbol__calc_percent(sym, evsel);
if (annotate_opts.print_lines) {
srcline_full_filename = annotate_opts.full_path;
symbol__calc_lines(ms, &source_line);
print_summary(&source_line, dso->long_name);
}
symbol__annotate_printf(ms, evsel);
annotated_source__purge(symbol__annotation(sym)->src);
return 0;
}
bool ui__has_annotation(void)
{
return use_browser == 1 && perf_hpp_list.sym;
}
static double annotation_line__max_percent(struct annotation_line *al,
struct annotation *notes,
unsigned int percent_type)
{
double percent_max = 0.0;
int i;
for (i = 0; i < notes->src->nr_events; i++) {
double percent;
percent = annotation_data__percent(&al->data[i],
percent_type);
if (percent > percent_max)
percent_max = percent;
}
return percent_max;
}
static void disasm_line__write(struct disasm_line *dl, struct annotation *notes,
void *obj, char *bf, size_t size,
void (*obj__printf)(void *obj, const char *fmt, ...),
void (*obj__write_graph)(void *obj, int graph))
{
if (dl->ins.ops && dl->ins.ops->scnprintf) {
if (ins__is_jump(&dl->ins)) {
bool fwd;
if (dl->ops.target.outside)
goto call_like;
fwd = dl->ops.target.offset > dl->al.offset;
obj__write_graph(obj, fwd ? DARROW_CHAR : UARROW_CHAR);
obj__printf(obj, " ");
} else if (ins__is_call(&dl->ins)) {
call_like:
obj__write_graph(obj, RARROW_CHAR);
obj__printf(obj, " ");
} else if (ins__is_ret(&dl->ins)) {
obj__write_graph(obj, LARROW_CHAR);
obj__printf(obj, " ");
} else {
obj__printf(obj, " ");
}
} else {
obj__printf(obj, " ");
}
disasm_line__scnprintf(dl, bf, size, !annotate_opts.use_offset,
notes->src->widths.max_ins_name);
}
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
static void ipc_coverage_string(char *bf, int size, struct annotation *notes)
{
double ipc = 0.0, coverage = 0.0;
struct annotated_branch *branch = annotation__get_branch(notes);
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
if (branch && branch->hit_cycles)
ipc = branch->hit_insn / ((double)branch->hit_cycles);
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
if (branch && branch->total_insn) {
coverage = branch->cover_insn * 100.0 /
((double)branch->total_insn);
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
}
scnprintf(bf, size, "(Average IPC: %.2f, IPC Coverage: %.1f%%)",
ipc, coverage);
}
static void __annotation_line__write(struct annotation_line *al, struct annotation *notes,
bool first_line, bool current_entry, bool change_color, int width,
void *obj, unsigned int percent_type,
int (*obj__set_color)(void *obj, int color),
void (*obj__set_percent_color)(void *obj, double percent, bool current),
int (*obj__set_jumps_percent_color)(void *obj, int nr, bool current),
void (*obj__printf)(void *obj, const char *fmt, ...),
void (*obj__write_graph)(void *obj, int graph))
{
double percent_max = annotation_line__max_percent(al, notes, percent_type);
int pcnt_width = annotation__pcnt_width(notes),
cycles_width = annotation__cycles_width(notes);
bool show_title = false;
char bf[256];
int printed;
if (first_line && (al->offset == -1 || percent_max == 0.0)) {
if (notes->branch && al->cycles) {
if (al->cycles->ipc == 0.0 && al->cycles->avg == 0)
show_title = true;
} else
show_title = true;
}
if (al->offset != -1 && percent_max != 0.0) {
int i;
for (i = 0; i < notes->src->nr_events; i++) {
double percent;
percent = annotation_data__percent(&al->data[i], percent_type);
obj__set_percent_color(obj, percent, current_entry);
perf annotate: Fix --show-total-period for tui/stdio2 perf annotate --show-total-period does not really show total period. The reason is we have two separate variables for the same purpose. One is in symbol_conf.show_total_period and another is annotation_options.show_total_period. We save command line option in symbol_conf.show_total_period but uses annotation_option.show_total_period while rendering tui/stdio2 browser. Though, we copy symbol_conf.show_total_period to annotation__default_options.show_total_period but that is not really effective as we don't use annotation__default_options once we copy default options to dynamic variable annotate.opts in cmd_annotate(). Instead of all these complication, keep only one variable and use it all over. symbol_conf.show_total_period is used by perf report/top as well. So let's kill annotation_options.show_total_period. On a side note, I've kept annotation_options.show_total_period definition because it's still used by perf-config code. Follow up patch to fix perf-config for annotate will remove annotation_options.show_total_period. 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/20200213064306.160480-3-ravi.bangoria@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-02-13 12:13:00 +05:30
if (symbol_conf.show_total_period) {
obj__printf(obj, "%11" PRIu64 " ", al->data[i].he.period);
perf annotate: Fix --show-nr-samples for tui/stdio2 perf annotate --show-nr-samples does not really show number of samples. The reason is we have two separate variables for the same purpose. One is in symbol_conf.show_nr_samples and another is annotation_options.show_nr_samples. We save command line option in symbol_conf.show_nr_samples but uses annotation_option.show_nr_samples while rendering tui/stdio2 browser. Though, we copy symbol_conf.show_nr_samples to annotation__default_options.show_nr_samples but that is not really effective as we don't use annotation__default_options once we copy default options to dynamic variable annotate.opts in cmd_annotate(). Instead of all these complication, keep only one variable and use it all over. symbol_conf.show_nr_samples is used by perf report/top as well. So let's kill annotation_options.show_nr_samples. On a side note, I've kept annotation_options.show_nr_samples definition because it's still used by perf-config code. Follow up patch to fix perf-config for annotate will remove annotation_options.show_nr_samples. 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/20200213064306.160480-4-ravi.bangoria@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-02-13 12:13:01 +05:30
} else if (symbol_conf.show_nr_samples) {
obj__printf(obj, "%6" PRIu64 " ",
al->data[i].he.nr_samples);
} else {
obj__printf(obj, "%6.2f ", percent);
}
}
} else {
obj__set_percent_color(obj, 0, current_entry);
if (!show_title)
obj__printf(obj, "%-*s", pcnt_width, " ");
else {
obj__printf(obj, "%-*s", pcnt_width,
perf annotate: Fix --show-total-period for tui/stdio2 perf annotate --show-total-period does not really show total period. The reason is we have two separate variables for the same purpose. One is in symbol_conf.show_total_period and another is annotation_options.show_total_period. We save command line option in symbol_conf.show_total_period but uses annotation_option.show_total_period while rendering tui/stdio2 browser. Though, we copy symbol_conf.show_total_period to annotation__default_options.show_total_period but that is not really effective as we don't use annotation__default_options once we copy default options to dynamic variable annotate.opts in cmd_annotate(). Instead of all these complication, keep only one variable and use it all over. symbol_conf.show_total_period is used by perf report/top as well. So let's kill annotation_options.show_total_period. On a side note, I've kept annotation_options.show_total_period definition because it's still used by perf-config code. Follow up patch to fix perf-config for annotate will remove annotation_options.show_total_period. 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/20200213064306.160480-3-ravi.bangoria@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-02-13 12:13:00 +05:30
symbol_conf.show_total_period ? "Period" :
perf annotate: Fix --show-nr-samples for tui/stdio2 perf annotate --show-nr-samples does not really show number of samples. The reason is we have two separate variables for the same purpose. One is in symbol_conf.show_nr_samples and another is annotation_options.show_nr_samples. We save command line option in symbol_conf.show_nr_samples but uses annotation_option.show_nr_samples while rendering tui/stdio2 browser. Though, we copy symbol_conf.show_nr_samples to annotation__default_options.show_nr_samples but that is not really effective as we don't use annotation__default_options once we copy default options to dynamic variable annotate.opts in cmd_annotate(). Instead of all these complication, keep only one variable and use it all over. symbol_conf.show_nr_samples is used by perf report/top as well. So let's kill annotation_options.show_nr_samples. On a side note, I've kept annotation_options.show_nr_samples definition because it's still used by perf-config code. Follow up patch to fix perf-config for annotate will remove annotation_options.show_nr_samples. 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/20200213064306.160480-4-ravi.bangoria@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-02-13 12:13:01 +05:30
symbol_conf.show_nr_samples ? "Samples" : "Percent");
}
}
if (notes->branch) {
if (al->cycles && al->cycles->ipc)
obj__printf(obj, "%*.2f ", ANNOTATION__IPC_WIDTH - 1, al->cycles->ipc);
else if (!show_title)
obj__printf(obj, "%*s", ANNOTATION__IPC_WIDTH, " ");
else
obj__printf(obj, "%*s ", ANNOTATION__IPC_WIDTH - 1, "IPC");
if (!annotate_opts.show_minmax_cycle) {
if (al->cycles && al->cycles->avg)
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
obj__printf(obj, "%*" PRIu64 " ",
ANNOTATION__CYCLES_WIDTH - 1, al->cycles->avg);
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
else if (!show_title)
obj__printf(obj, "%*s",
ANNOTATION__CYCLES_WIDTH, " ");
else
obj__printf(obj, "%*s ",
ANNOTATION__CYCLES_WIDTH - 1,
"Cycle");
} else {
if (al->cycles) {
char str[32];
scnprintf(str, sizeof(str),
"%" PRIu64 "(%" PRIu64 "/%" PRIu64 ")",
al->cycles->avg, al->cycles->min,
al->cycles->max);
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
obj__printf(obj, "%*s ",
ANNOTATION__MINMAX_CYCLES_WIDTH - 1,
str);
} else if (!show_title)
obj__printf(obj, "%*s",
ANNOTATION__MINMAX_CYCLES_WIDTH,
" ");
else
obj__printf(obj, "%*s ",
ANNOTATION__MINMAX_CYCLES_WIDTH - 1,
"Cycle(min/max)");
}
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
if (show_title && !*al->line) {
ipc_coverage_string(bf, sizeof(bf), notes);
obj__printf(obj, "%*s", ANNOTATION__AVG_IPC_WIDTH, bf);
}
}
obj__printf(obj, " ");
if (!*al->line)
obj__printf(obj, "%-*s", width - pcnt_width - cycles_width, " ");
else if (al->offset == -1) {
if (al->line_nr && annotate_opts.show_linenr)
printed = scnprintf(bf, sizeof(bf), "%-*d ",
notes->src->widths.addr + 1, al->line_nr);
else
printed = scnprintf(bf, sizeof(bf), "%-*s ",
notes->src->widths.addr, " ");
obj__printf(obj, bf);
obj__printf(obj, "%-*s", width - printed - pcnt_width - cycles_width + 1, al->line);
} else {
u64 addr = al->offset;
int color = -1;
if (!annotate_opts.use_offset)
addr += notes->src->start;
if (!annotate_opts.use_offset) {
printed = scnprintf(bf, sizeof(bf), "%" PRIx64 ": ", addr);
} else {
if (al->jump_sources &&
annotate_opts.offset_level >= ANNOTATION__OFFSET_JUMP_TARGETS) {
if (annotate_opts.show_nr_jumps) {
int prev;
printed = scnprintf(bf, sizeof(bf), "%*d ",
notes->src->widths.jumps,
al->jump_sources);
prev = obj__set_jumps_percent_color(obj, al->jump_sources,
current_entry);
obj__printf(obj, bf);
obj__set_color(obj, prev);
}
print_addr:
printed = scnprintf(bf, sizeof(bf), "%*" PRIx64 ": ",
notes->src->widths.target, addr);
} else if (ins__is_call(&disasm_line(al)->ins) &&
annotate_opts.offset_level >= ANNOTATION__OFFSET_CALL) {
goto print_addr;
} else if (annotate_opts.offset_level == ANNOTATION__MAX_OFFSET_LEVEL) {
goto print_addr;
} else {
printed = scnprintf(bf, sizeof(bf), "%-*s ",
notes->src->widths.addr, " ");
}
}
if (change_color)
color = obj__set_color(obj, HE_COLORSET_ADDR);
obj__printf(obj, bf);
if (change_color)
obj__set_color(obj, color);
disasm_line__write(disasm_line(al), notes, obj, bf, sizeof(bf), obj__printf, obj__write_graph);
obj__printf(obj, "%-*s", width - pcnt_width - cycles_width - 3 - printed, bf);
}
}
void annotation_line__write(struct annotation_line *al, struct annotation *notes,
struct annotation_write_ops *wops)
{
__annotation_line__write(al, notes, wops->first_line, wops->current_entry,
wops->change_color, wops->width, wops->obj,
annotate_opts.percent_type,
wops->set_color, wops->set_percent_color,
wops->set_jumps_percent_color, wops->printf,
wops->write_graph);
}
int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel,
struct arch **parch)
{
struct symbol *sym = ms->sym;
struct annotation *notes = symbol__annotation(sym);
size_t size = symbol__size(sym);
int nr_pcnt = 1, err;
if (evsel__is_group_event(evsel))
nr_pcnt = evsel->core.nr_members;
err = symbol__annotate(ms, evsel, parch);
if (err)
return err;
symbol__calc_percent(sym, evsel);
annotation__set_index(notes);
annotation__mark_jump_targets(notes, sym);
err = annotation__compute_ipc(notes, size);
if (err)
return err;
annotation__init_column_widths(notes, sym);
notes->src->nr_events = nr_pcnt;
annotation__update_column_widths(notes);
sym->annotate2 = 1;
return 0;
}
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
static int annotation__config(const char *var, const char *value, void *data)
{
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
struct annotation_options *opt = data;
if (!strstarts(var, "annotate."))
return 0;
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
if (!strcmp(var, "annotate.offset_level")) {
perf_config_u8(&opt->offset_level, "offset_level", value);
if (opt->offset_level > ANNOTATION__MAX_OFFSET_LEVEL)
opt->offset_level = ANNOTATION__MAX_OFFSET_LEVEL;
else if (opt->offset_level < ANNOTATION__MIN_OFFSET_LEVEL)
opt->offset_level = ANNOTATION__MIN_OFFSET_LEVEL;
} else if (!strcmp(var, "annotate.hide_src_code")) {
opt->hide_src_code = perf_config_bool("hide_src_code", value);
} else if (!strcmp(var, "annotate.jump_arrows")) {
opt->jump_arrows = perf_config_bool("jump_arrows", value);
} else if (!strcmp(var, "annotate.show_linenr")) {
opt->show_linenr = perf_config_bool("show_linenr", value);
} else if (!strcmp(var, "annotate.show_nr_jumps")) {
opt->show_nr_jumps = perf_config_bool("show_nr_jumps", value);
} else if (!strcmp(var, "annotate.show_nr_samples")) {
symbol_conf.show_nr_samples = perf_config_bool("show_nr_samples",
value);
} else if (!strcmp(var, "annotate.show_total_period")) {
symbol_conf.show_total_period = perf_config_bool("show_total_period",
value);
} else if (!strcmp(var, "annotate.use_offset")) {
opt->use_offset = perf_config_bool("use_offset", value);
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
} else if (!strcmp(var, "annotate.disassembler_style")) {
opt->disassembler_style = strdup(value);
if (!opt->disassembler_style) {
pr_err("Not enough memory for annotate.disassembler_style\n");
return -1;
}
} else if (!strcmp(var, "annotate.objdump")) {
opt->objdump_path = strdup(value);
if (!opt->objdump_path) {
pr_err("Not enough memory for annotate.objdump\n");
return -1;
}
} else if (!strcmp(var, "annotate.addr2line")) {
symbol_conf.addr2line_path = strdup(value);
if (!symbol_conf.addr2line_path) {
pr_err("Not enough memory for annotate.addr2line\n");
return -1;
}
} else if (!strcmp(var, "annotate.demangle")) {
symbol_conf.demangle = perf_config_bool("demangle", value);
} else if (!strcmp(var, "annotate.demangle_kernel")) {
symbol_conf.demangle_kernel = perf_config_bool("demangle_kernel", value);
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
} else {
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
pr_debug("%s variable unknown, ignoring...", var);
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
return 0;
}
void annotation_options__init(void)
{
struct annotation_options *opt = &annotate_opts;
memset(opt, 0, sizeof(*opt));
/* Default values. */
opt->use_offset = true;
opt->jump_arrows = true;
opt->annotate_src = true;
opt->offset_level = ANNOTATION__OFFSET_JUMP_TARGETS;
opt->percent_type = PERCENT_PERIOD_LOCAL;
}
void annotation_options__exit(void)
{
zfree(&annotate_opts.disassembler_style);
zfree(&annotate_opts.objdump_path);
}
void annotation_config__init(void)
{
perf_config(annotation__config, &annotate_opts);
}
static unsigned int parse_percent_type(char *str1, char *str2)
{
unsigned int type = (unsigned int) -1;
if (!strcmp("period", str1)) {
if (!strcmp("local", str2))
type = PERCENT_PERIOD_LOCAL;
else if (!strcmp("global", str2))
type = PERCENT_PERIOD_GLOBAL;
}
if (!strcmp("hits", str1)) {
if (!strcmp("local", str2))
type = PERCENT_HITS_LOCAL;
else if (!strcmp("global", str2))
type = PERCENT_HITS_GLOBAL;
}
return type;
}
int annotate_parse_percent_type(const struct option *opt __maybe_unused, const char *_str,
int unset __maybe_unused)
{
unsigned int type;
char *str1, *str2;
int err = -1;
str1 = strdup(_str);
if (!str1)
return -ENOMEM;
str2 = strchr(str1, '-');
if (!str2)
goto out;
*str2++ = 0;
type = parse_percent_type(str1, str2);
if (type == (unsigned int) -1)
type = parse_percent_type(str2, str1);
if (type != (unsigned int) -1) {
annotate_opts.percent_type = type;
err = 0;
}
out:
free(str1);
return err;
}
int annotate_check_args(void)
{
struct annotation_options *args = &annotate_opts;
if (args->prefix_strip && !args->prefix) {
pr_err("--prefix-strip requires --prefix\n");
return -1;
}
return 0;
}
/*
* Get register number and access offset from the given instruction.
* It assumes AT&T x86 asm format like OFFSET(REG). Maybe it needs
* to revisit the format when it handles different architecture.
* Fills @reg and @offset when return 0.
*/
static int extract_reg_offset(struct arch *arch, const char *str,
struct annotated_op_loc *op_loc)
{
char *p;
char *regname;
if (arch->objdump.register_char == 0)
return -1;
/*
* It should start from offset, but it's possible to skip 0
* in the asm. So 0(%rax) should be same as (%rax).
*
* However, it also start with a segment select register like
* %gs:0x18(%rbx). In that case it should skip the part.
*/
if (*str == arch->objdump.register_char) {
if (arch__is(arch, "x86")) {
/* FIXME: Handle other segment registers */
if (!strncmp(str, "%gs:", 4))
op_loc->segment = INSN_SEG_X86_GS;
}
while (*str && !isdigit(*str) &&
*str != arch->objdump.memory_ref_char)
str++;
}
op_loc->offset = strtol(str, &p, 0);
p = strchr(p, arch->objdump.register_char);
if (p == NULL)
return -1;
regname = strdup(p);
if (regname == NULL)
return -1;
op_loc->reg1 = get_dwarf_regnum(regname, 0);
free(regname);
/* Get the second register */
if (op_loc->multi_regs) {
p = strchr(p + 1, arch->objdump.register_char);
if (p == NULL)
return -1;
regname = strdup(p);
if (regname == NULL)
return -1;
op_loc->reg2 = get_dwarf_regnum(regname, 0);
free(regname);
}
return 0;
}
/**
* annotate_get_insn_location - Get location of instruction
* @arch: the architecture info
* @dl: the target instruction
* @loc: a buffer to save the data
*
* Get detailed location info (register and offset) in the instruction.
* It needs both source and target operand and whether it accesses a
* memory location. The offset field is meaningful only when the
* corresponding mem flag is set. The reg2 field is meaningful only
* when multi_regs flag is set.
*
* Some examples on x86:
*
* mov (%rax), %rcx # src_reg1 = rax, src_mem = 1, src_offset = 0
* # dst_reg1 = rcx, dst_mem = 0
*
* mov 0x18, %r8 # src_reg1 = -1, src_mem = 0
* # dst_reg1 = r8, dst_mem = 0
*
* mov %rsi, 8(%rbx,%rcx,4) # src_reg1 = rsi, src_mem = 0, dst_multi_regs = 0
* # dst_reg1 = rbx, dst_reg2 = rcx, dst_mem = 1
* # dst_multi_regs = 1, dst_offset = 8
*/
int annotate_get_insn_location(struct arch *arch, struct disasm_line *dl,
struct annotated_insn_loc *loc)
{
struct ins_operands *ops;
struct annotated_op_loc *op_loc;
int i;
if (ins__is_lock(&dl->ins))
ops = dl->ops.locked.ops;
else
ops = &dl->ops;
if (ops == NULL)
return -1;
memset(loc, 0, sizeof(*loc));
for_each_insn_op_loc(loc, i, op_loc) {
const char *insn_str = ops->source.raw;
bool multi_regs = ops->source.multi_regs;
if (i == INSN_OP_TARGET) {
insn_str = ops->target.raw;
multi_regs = ops->target.multi_regs;
}
/* Invalidate the register by default */
op_loc->reg1 = -1;
op_loc->reg2 = -1;
if (insn_str == NULL)
continue;
if (strchr(insn_str, arch->objdump.memory_ref_char)) {
op_loc->mem_ref = true;
op_loc->multi_regs = multi_regs;
extract_reg_offset(arch, insn_str, op_loc);
} else {
char *s, *p = NULL;
if (arch__is(arch, "x86")) {
/* FIXME: Handle other segment registers */
if (!strncmp(insn_str, "%gs:", 4)) {
op_loc->segment = INSN_SEG_X86_GS;
op_loc->offset = strtol(insn_str + 4,
&p, 0);
if (p && p != insn_str + 4)
op_loc->imm = true;
continue;
}
}
s = strdup(insn_str);
if (s == NULL)
return -1;
if (*s == arch->objdump.register_char)
op_loc->reg1 = get_dwarf_regnum(s, 0);
else if (*s == arch->objdump.imm_char) {
op_loc->offset = strtol(s + 1, &p, 0);
if (p && p != s + 1)
op_loc->imm = true;
}
free(s);
}
}
return 0;
}
static struct disasm_line *find_disasm_line(struct symbol *sym, u64 ip,
bool allow_update)
{
struct disasm_line *dl;
struct annotation *notes;
notes = symbol__annotation(sym);
list_for_each_entry(dl, &notes->src->source, al.node) {
if (dl->al.offset == -1)
continue;
if (sym->start + dl->al.offset == ip) {
/*
* llvm-objdump places "lock" in a separate line and
* in that case, we want to get the next line.
*/
if (ins__is_lock(&dl->ins) &&
*dl->ops.raw == '\0' && allow_update) {
ip++;
continue;
}
return dl;
}
}
return NULL;
}
2023-12-12 16:13:23 -08:00
static struct annotated_item_stat *annotate_data_stat(struct list_head *head,
const char *name)
{
struct annotated_item_stat *istat;
list_for_each_entry(istat, head, list) {
if (!strcmp(istat->name, name))
return istat;
}
istat = zalloc(sizeof(*istat));
if (istat == NULL)
return NULL;
istat->name = strdup(name);
if (istat->name == NULL) {
free(istat);
return NULL;
}
list_add_tail(&istat->list, head);
return istat;
}
static bool is_stack_operation(struct arch *arch, struct disasm_line *dl)
{
if (arch__is(arch, "x86")) {
if (!strncmp(dl->ins.name, "push", 4) ||
!strncmp(dl->ins.name, "pop", 3) ||
!strncmp(dl->ins.name, "ret", 3))
return true;
}
return false;
}
static bool is_stack_canary(struct arch *arch, struct annotated_op_loc *loc)
{
/* On x86_64, %gs:40 is used for stack canary */
if (arch__is(arch, "x86")) {
if (loc->segment == INSN_SEG_X86_GS && loc->imm &&
loc->offset == 40)
return true;
}
return false;
}
static struct disasm_line *
annotation__prev_asm_line(struct annotation *notes, struct disasm_line *curr)
{
struct list_head *sources = &notes->src->source;
struct disasm_line *prev;
if (curr == list_first_entry(sources, struct disasm_line, al.node))
return NULL;
prev = list_prev_entry(curr, al.node);
while (prev->al.offset == -1 &&
prev != list_first_entry(sources, struct disasm_line, al.node))
prev = list_prev_entry(prev, al.node);
if (prev->al.offset == -1)
return NULL;
return prev;
}
static struct disasm_line *
annotation__next_asm_line(struct annotation *notes, struct disasm_line *curr)
{
struct list_head *sources = &notes->src->source;
struct disasm_line *next;
if (curr == list_last_entry(sources, struct disasm_line, al.node))
return NULL;
next = list_next_entry(curr, al.node);
while (next->al.offset == -1 &&
next != list_last_entry(sources, struct disasm_line, al.node))
next = list_next_entry(next, al.node);
if (next->al.offset == -1)
return NULL;
return next;
}
u64 annotate_calc_pcrel(struct map_symbol *ms, u64 ip, int offset,
struct disasm_line *dl)
{
struct annotation *notes;
struct disasm_line *next;
u64 addr;
notes = symbol__annotation(ms->sym);
/*
* PC-relative addressing starts from the next instruction address
* But the IP is for the current instruction. Since disasm_line
* doesn't have the instruction size, calculate it using the next
* disasm_line. If it's the last one, we can use symbol's end
* address directly.
*/
next = annotation__next_asm_line(notes, dl);
if (next == NULL)
addr = ms->sym->end + offset;
else
addr = ip + (next->al.offset - dl->al.offset) + offset;
return map__rip_2objdump(ms->map, addr);
}
/**
* hist_entry__get_data_type - find data type for given hist entry
* @he: hist entry
*
* This function first annotates the instruction at @he->ip and extracts
* register and offset info from it. Then it searches the DWARF debug
* info to get a variable and type information using the address, register,
* and offset.
*/
struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
{
struct map_symbol *ms = &he->ms;
struct evsel *evsel = hists_to_evsel(he->hists);
struct arch *arch;
struct disasm_line *dl;
struct annotated_insn_loc loc;
struct annotated_op_loc *op_loc;
struct annotated_data_type *mem_type;
2023-12-12 16:13:23 -08:00
struct annotated_item_stat *istat;
u64 ip = he->ip;
int i;
ann_data_stat.total++;
if (ms->map == NULL || ms->sym == NULL) {
ann_data_stat.no_sym++;
return NULL;
}
if (!symbol_conf.init_annotation) {
ann_data_stat.no_sym++;
return NULL;
}
/* Make sure it has the disasm of the function */
if (symbol__annotate(ms, evsel, &arch) < 0) {
ann_data_stat.no_insn++;
return NULL;
}
/*
* Get a disasm to extract the location from the insn.
* This is too slow...
*/
dl = find_disasm_line(ms->sym, ip, /*allow_update=*/true);
if (dl == NULL) {
ann_data_stat.no_insn++;
return NULL;
}
retry:
2023-12-12 16:13:23 -08:00
istat = annotate_data_stat(&ann_insn_stat, dl->ins.name);
if (istat == NULL) {
ann_data_stat.no_insn++;
return NULL;
}
if (annotate_get_insn_location(arch, dl, &loc) < 0) {
ann_data_stat.no_insn_ops++;
2023-12-12 16:13:23 -08:00
istat->bad++;
return NULL;
}
if (is_stack_operation(arch, dl)) {
istat->good++;
he->mem_type_off = 0;
return &stackop_type;
}
for_each_insn_op_loc(&loc, i, op_loc) {
struct data_loc_info dloc = {
.arch = arch,
.thread = he->thread,
.ms = ms,
/* Recalculate IP for LOCK prefix or insn fusion */
.ip = ms->sym->start + dl->al.offset,
.cpumode = he->cpumode,
.op = op_loc,
};
if (!op_loc->mem_ref && op_loc->segment == INSN_SEG_NONE)
continue;
/* Recalculate IP because of LOCK prefix or insn fusion */
ip = ms->sym->start + dl->al.offset;
/* PC-relative addressing */
if (op_loc->reg1 == DWARF_REG_PC) {
dloc.var_addr = annotate_calc_pcrel(ms, dloc.ip,
op_loc->offset, dl);
}
/* This CPU access in kernel - pretend PC-relative addressing */
if (map__dso(ms->map)->kernel && arch__is(arch, "x86") &&
op_loc->segment == INSN_SEG_X86_GS && op_loc->imm) {
dloc.var_addr = op_loc->offset;
op_loc->reg1 = DWARF_REG_PC;
}
mem_type = find_data_type(&dloc);
if (mem_type == NULL && is_stack_canary(arch, op_loc)) {
istat->good++;
he->mem_type_off = 0;
return &canary_type;
}
2023-12-12 16:13:23 -08:00
if (mem_type)
istat->good++;
else
istat->bad++;
perf annotate: Add --data-type option Support data type annotation with new --data-type option. It internally uses type sort key to collect sample histogram for the type and display every members like below. $ perf annotate --data-type ... Annotate type: 'struct cfs_rq' in [kernel.kallsyms] (13 samples): ============================================================================ samples offset size field 13 0 640 struct cfs_rq { 2 0 16 struct load_weight load { 2 0 8 unsigned long weight; 0 8 4 u32 inv_weight; }; 0 16 8 unsigned long runnable_weight; 0 24 4 unsigned int nr_running; 1 28 4 unsigned int h_nr_running; ... For simplicity it prints the number of samples per field for now. But it should be easy to show the overhead percentage instead. The number at the outer struct is a sum of the numbers of the inner members. For example, struct cfs_rq got total 13 samples, and 2 came from the load (struct load_weight) and 1 from h_nr_running. Similarly, the struct load_weight got total 2 samples and they all came from the weight field. I've added two new flags in the symbol_conf for this. The annotate_data_member is to get the members of the type. This is also needed for perf report with typeoff sort key. The annotate_data_sample is to update sample stats for each offset and used only in annotate. Currently it only support stdio output mode, TUI support can be added later. Committer testing: With the perf.data from the previous csets, a very simple, short duration one: # perf annotate --data-type Annotate type: 'struct list_head' in [kernel.kallsyms] (1 samples): ============================================================================ samples offset size field 1 0 16 struct list_head { 0 0 8 struct list_head* next; 1 8 8 struct list_head* prev; }; Annotate type: 'char' in [kernel.kallsyms] (1 samples): ============================================================================ samples offset size field 1 0 1 char ; # 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: 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/20231213001323.718046-15-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-12-12 16:13:20 -08:00
if (symbol_conf.annotate_data_sample) {
annotated_data_type__update_samples(mem_type, evsel,
dloc.type_offset,
perf annotate: Add --data-type option Support data type annotation with new --data-type option. It internally uses type sort key to collect sample histogram for the type and display every members like below. $ perf annotate --data-type ... Annotate type: 'struct cfs_rq' in [kernel.kallsyms] (13 samples): ============================================================================ samples offset size field 13 0 640 struct cfs_rq { 2 0 16 struct load_weight load { 2 0 8 unsigned long weight; 0 8 4 u32 inv_weight; }; 0 16 8 unsigned long runnable_weight; 0 24 4 unsigned int nr_running; 1 28 4 unsigned int h_nr_running; ... For simplicity it prints the number of samples per field for now. But it should be easy to show the overhead percentage instead. The number at the outer struct is a sum of the numbers of the inner members. For example, struct cfs_rq got total 13 samples, and 2 came from the load (struct load_weight) and 1 from h_nr_running. Similarly, the struct load_weight got total 2 samples and they all came from the weight field. I've added two new flags in the symbol_conf for this. The annotate_data_member is to get the members of the type. This is also needed for perf report with typeoff sort key. The annotate_data_sample is to update sample stats for each offset and used only in annotate. Currently it only support stdio output mode, TUI support can be added later. Committer testing: With the perf.data from the previous csets, a very simple, short duration one: # perf annotate --data-type Annotate type: 'struct list_head' in [kernel.kallsyms] (1 samples): ============================================================================ samples offset size field 1 0 16 struct list_head { 0 0 8 struct list_head* next; 1 8 8 struct list_head* prev; }; Annotate type: 'char' in [kernel.kallsyms] (1 samples): ============================================================================ samples offset size field 1 0 1 char ; # 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: 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/20231213001323.718046-15-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-12-12 16:13:20 -08:00
he->stat.nr_events,
he->stat.period);
}
he->mem_type_off = dloc.type_offset;
return mem_type;
}
/*
* Some instructions can be fused and the actual memory access came
* from the previous instruction.
*/
if (dl->al.offset > 0) {
struct annotation *notes;
struct disasm_line *prev_dl;
notes = symbol__annotation(ms->sym);
prev_dl = annotation__prev_asm_line(notes, dl);
if (prev_dl && ins__is_fused(arch, prev_dl->ins.name, dl->ins.name)) {
dl = prev_dl;
goto retry;
}
}
ann_data_stat.no_mem_ops++;
2023-12-12 16:13:23 -08:00
istat->bad++;
return NULL;
}
/* Basic block traversal (BFS) data structure */
struct basic_block_data {
struct list_head queue;
struct list_head visited;
};
/*
* During the traversal, it needs to know the parent block where the current
* block block started from. Note that single basic block can be parent of
* two child basic blocks (in case of condition jump).
*/
struct basic_block_link {
struct list_head node;
struct basic_block_link *parent;
struct annotated_basic_block *bb;
};
/* Check any of basic block in the list already has the offset */
static bool basic_block_has_offset(struct list_head *head, s64 offset)
{
struct basic_block_link *link;
list_for_each_entry(link, head, node) {
s64 begin_offset = link->bb->begin->al.offset;
s64 end_offset = link->bb->end->al.offset;
if (begin_offset <= offset && offset <= end_offset)
return true;
}
return false;
}
static bool is_new_basic_block(struct basic_block_data *bb_data,
struct disasm_line *dl)
{
s64 offset = dl->al.offset;
if (basic_block_has_offset(&bb_data->visited, offset))
return false;
if (basic_block_has_offset(&bb_data->queue, offset))
return false;
return true;
}
/* Add a basic block starting from dl and link it to the parent */
static int add_basic_block(struct basic_block_data *bb_data,
struct basic_block_link *parent,
struct disasm_line *dl)
{
struct annotated_basic_block *bb;
struct basic_block_link *link;
if (dl == NULL)
return -1;
if (!is_new_basic_block(bb_data, dl))
return 0;
bb = zalloc(sizeof(*bb));
if (bb == NULL)
return -1;
bb->begin = dl;
bb->end = dl;
INIT_LIST_HEAD(&bb->list);
link = malloc(sizeof(*link));
if (link == NULL) {
free(bb);
return -1;
}
link->bb = bb;
link->parent = parent;
list_add_tail(&link->node, &bb_data->queue);
return 0;
}
/* Returns true when it finds the target in the current basic block */
static bool process_basic_block(struct basic_block_data *bb_data,
struct basic_block_link *link,
struct symbol *sym, u64 target)
{
struct disasm_line *dl, *next_dl, *last_dl;
struct annotation *notes = symbol__annotation(sym);
bool found = false;
dl = link->bb->begin;
/* Check if it's already visited */
if (basic_block_has_offset(&bb_data->visited, dl->al.offset))
return false;
last_dl = list_last_entry(&notes->src->source,
struct disasm_line, al.node);
if (last_dl->al.offset == -1)
last_dl = annotation__prev_asm_line(notes, last_dl);
if (last_dl == NULL)
return false;
list_for_each_entry_from(dl, &notes->src->source, al.node) {
/* Skip comment or debug info line */
if (dl->al.offset == -1)
continue;
/* Found the target instruction */
if (sym->start + dl->al.offset == target) {
found = true;
break;
}
/* End of the function, finish the block */
if (dl == last_dl)
break;
/* 'return' instruction finishes the block */
if (ins__is_ret(&dl->ins))
break;
/* normal instructions are part of the basic block */
if (!ins__is_jump(&dl->ins))
continue;
/* jump to a different function, tail call or return */
if (dl->ops.target.outside)
break;
/* jump instruction creates new basic block(s) */
next_dl = find_disasm_line(sym, sym->start + dl->ops.target.offset,
/*allow_update=*/false);
if (next_dl)
add_basic_block(bb_data, link, next_dl);
/*
* FIXME: determine conditional jumps properly.
* Conditional jumps create another basic block with the
* next disasm line.
*/
if (!strstr(dl->ins.name, "jmp")) {
next_dl = annotation__next_asm_line(notes, dl);
if (next_dl)
add_basic_block(bb_data, link, next_dl);
}
break;
}
link->bb->end = dl;
return found;
}
/*
* It founds a target basic block, build a proper linked list of basic blocks
* by following the link recursively.
*/
static void link_found_basic_blocks(struct basic_block_link *link,
struct list_head *head)
{
while (link) {
struct basic_block_link *parent = link->parent;
list_move(&link->bb->list, head);
list_del(&link->node);
free(link);
link = parent;
}
}
static void delete_basic_blocks(struct basic_block_data *bb_data)
{
struct basic_block_link *link, *tmp;
list_for_each_entry_safe(link, tmp, &bb_data->queue, node) {
list_del(&link->node);
free(link->bb);
free(link);
}
list_for_each_entry_safe(link, tmp, &bb_data->visited, node) {
list_del(&link->node);
free(link->bb);
free(link);
}
}
/**
* annotate_get_basic_blocks - Get basic blocks for given address range
* @sym: symbol to annotate
* @src: source address
* @dst: destination address
* @head: list head to save basic blocks
*
* This function traverses disasm_lines from @src to @dst and save them in a
* list of annotated_basic_block to @head. It uses BFS to find the shortest
* path between two. The basic_block_link is to maintain parent links so
* that it can build a list of blocks from the start.
*/
int annotate_get_basic_blocks(struct symbol *sym, s64 src, s64 dst,
struct list_head *head)
{
struct basic_block_data bb_data = {
.queue = LIST_HEAD_INIT(bb_data.queue),
.visited = LIST_HEAD_INIT(bb_data.visited),
};
struct basic_block_link *link;
struct disasm_line *dl;
int ret = -1;
dl = find_disasm_line(sym, src, /*allow_update=*/false);
if (dl == NULL)
return -1;
if (add_basic_block(&bb_data, /*parent=*/NULL, dl) < 0)
return -1;
/* Find shortest path from src to dst using BFS */
while (!list_empty(&bb_data.queue)) {
link = list_first_entry(&bb_data.queue, struct basic_block_link, node);
if (process_basic_block(&bb_data, link, sym, dst)) {
link_found_basic_blocks(link, head);
ret = 0;
break;
}
list_move(&link->node, &bb_data.visited);
}
delete_basic_blocks(&bb_data);
return ret;
}