kernel_optimize_test/tools/perf/builtin-annotate.c

482 lines
11 KiB
C
Raw Normal View History

/*
* builtin-annotate.c
*
* Builtin annotate command: Analyze the perf.data input file,
* look up and read DSOs and symbol information and display
* a histogram of results, along various sorting keys.
*/
#include "builtin.h"
#include "util/util.h"
#include "util/color.h"
#include <linux/list.h>
#include "util/cache.h"
#include <linux/rbtree.h>
#include "util/symbol.h"
#include "perf.h"
#include "util/debug.h"
#include "util/event.h"
#include "util/parse-options.h"
#include "util/parse-events.h"
#include "util/thread.h"
#include "util/sort.h"
#include "util/hist.h"
#include "util/session.h"
static char const *input_name = "perf.data";
static bool force, use_tui, use_stdio;
perf: Fix endianness argument compatibility with OPT_BOOLEAN() and introduce OPT_INCR() Parsing an option from the command line with OPT_BOOLEAN on a bool data type would not work on a big-endian machine due to the manner in which the boolean was being cast into an int and incremented. For example, running 'perf probe --list' on a PowerPC machine would fail to properly set the list_events bool and would therefore print out the usage information and terminate. This patch makes OPT_BOOLEAN work as expected with a bool datatype. For cases where the original OPT_BOOLEAN was intentionally being used to increment an int each time it was passed in on the command line, this patch introduces OPT_INCR with the old behaviour of OPT_BOOLEAN (the verbose variable is currently the only such example of this). I have reviewed every use of OPT_BOOLEAN to verify that a true C99 bool was passed. Where integers were used, I verified that they were only being used for boolean logic and changed them to bools to ensure that they would not be mistakenly used as ints. The major exception was the verbose variable which now uses OPT_INCR instead of OPT_BOOLEAN. Signed-off-by: Ian Munsie <imunsie@au.ibm.com> Acked-by: David S. Miller <davem@davemloft.net> Cc: <stable@kernel.org> # NOTE: wont apply to .3[34].x cleanly, please backport Cc: Git development list <git@vger.kernel.org> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Eric B Munson <ebmunson@us.ibm.com> Cc: Valdis.Kletnieks@vt.edu Cc: WANG Cong <amwang@redhat.com> Cc: Thiago Farina <tfransosi@gmail.com> Cc: Masami Hiramatsu <mhiramat@redhat.com> Cc: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> Cc: Jaswinder Singh Rajput <jaswinderrajput@gmail.com> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Mike Galbraith <efault@gmx.de> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Anton Blanchard <anton@samba.org> Cc: John Kacur <jkacur@redhat.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1271147857-11604-1-git-send-email-imunsie@au.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-04-13 16:37:33 +08:00
static bool full_paths;
perf: Fix endianness argument compatibility with OPT_BOOLEAN() and introduce OPT_INCR() Parsing an option from the command line with OPT_BOOLEAN on a bool data type would not work on a big-endian machine due to the manner in which the boolean was being cast into an int and incremented. For example, running 'perf probe --list' on a PowerPC machine would fail to properly set the list_events bool and would therefore print out the usage information and terminate. This patch makes OPT_BOOLEAN work as expected with a bool datatype. For cases where the original OPT_BOOLEAN was intentionally being used to increment an int each time it was passed in on the command line, this patch introduces OPT_INCR with the old behaviour of OPT_BOOLEAN (the verbose variable is currently the only such example of this). I have reviewed every use of OPT_BOOLEAN to verify that a true C99 bool was passed. Where integers were used, I verified that they were only being used for boolean logic and changed them to bools to ensure that they would not be mistakenly used as ints. The major exception was the verbose variable which now uses OPT_INCR instead of OPT_BOOLEAN. Signed-off-by: Ian Munsie <imunsie@au.ibm.com> Acked-by: David S. Miller <davem@davemloft.net> Cc: <stable@kernel.org> # NOTE: wont apply to .3[34].x cleanly, please backport Cc: Git development list <git@vger.kernel.org> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Eric B Munson <ebmunson@us.ibm.com> Cc: Valdis.Kletnieks@vt.edu Cc: WANG Cong <amwang@redhat.com> Cc: Thiago Farina <tfransosi@gmail.com> Cc: Masami Hiramatsu <mhiramat@redhat.com> Cc: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> Cc: Jaswinder Singh Rajput <jaswinderrajput@gmail.com> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Mike Galbraith <efault@gmx.de> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Anton Blanchard <anton@samba.org> Cc: John Kacur <jkacur@redhat.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1271147857-11604-1-git-send-email-imunsie@au.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-04-13 16:37:33 +08:00
static bool print_line;
static const char *sym_hist_filter;
2010-05-11 00:04:11 +08:00
static int hists__add_entry(struct hists *self, struct addr_location *al)
{
struct hist_entry *he;
if (sym_hist_filter != NULL &&
(al->sym == NULL || strcmp(sym_hist_filter, al->sym->name) != 0)) {
/* We're only interested in a symbol named sym_hist_filter */
if (al->sym != NULL) {
rb_erase(&al->sym->rb_node,
&al->map->dso->symbols[al->map->type]);
symbol__delete(al->sym);
}
return 0;
}
2010-05-11 00:04:11 +08:00
he = __hists__add_entry(self, al, NULL, 1);
if (he == NULL)
return -ENOMEM;
return hist_entry__inc_addr_samples(he, al->addr);
}
static int process_sample_event(event_t *event, struct perf_sample *sample,
struct perf_session *session)
{
perf tools: Consolidate symbol resolving across all tools Now we have a very high level routine for simple tools to process IP sample events: int event__preprocess_sample(const event_t *self, struct addr_location *al, symbol_filter_t filter) It receives the event itself and will insert new threads in the global threads list and resolve the map and symbol, filling all this info into the new addr_location struct, so that tools like annotate and report can further process the event by creating hist_entries in their specific way (with or without callgraphs, etc). It in turn uses the new next layer function: void thread__find_addr_location(struct thread *self, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter) This one will, given a thread (userspace or the kernel kthread one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE too in the near future) at the given cpumode, taking vdsos into account (userspace hit, but kernel symbol) and will fill all these details in the addr_location given. Tools that need a more compact API for plain function resolution, like 'kmem', can use this other one: struct symbol *thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) So, to resolve a kernel symbol, that is all the 'kmem' tool needs, its just a matter of calling: sym = thread__find_function(kthread, addr, NULL); The 'filter' parameter is needed because we do lazy parsing/loading of ELF symtabs or /proc/kallsyms. With this we remove more code duplication all around, which is always good, huh? :-) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: John Kacur <jkacur@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
struct addr_location al;
if (event__preprocess_sample(event, session, &al, sample, NULL) < 0) {
pr_warning("problem processing %d event, skipping it.\n",
event->header.type);
return -1;
}
2010-05-11 00:04:11 +08:00
if (!al.filtered && hists__add_entry(&session->hists, &al)) {
pr_warning("problem incrementing symbol count, "
"skipping event\n");
return -1;
}
return 0;
}
perf annotate: Handle samples not at objdump output addr boundaries Without this patch we get this for need_resched: [root@mica ~]# perf annotate need_resched ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ : : : Disassembly of section .text: : : ffffffff810095ed <need_resched>: : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095ed: 55 push %rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 0.00 : ffffffff810095ee: be 03 00 00 00 mov $0x3,%esi : : static inline struct thread_info *current_thread_info(void) : { : struct thread_info *ti; : ti = (void *)(percpu_read_stable(kernel_stack) + 0.00 : ffffffff810095f3: 65 48 8b 3c 25 48 b5 mov %gs:0xb548,%rdi 0.00 : ffffffff810095fa: 00 00 : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095fc: 48 89 e5 mov %rsp,%rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 0.00 : ffffffff810095ff: 48 81 ef d8 1f 00 00 sub $0x1fd8,%rdi 0.00 : ffffffff81009606: e8 9d ff ff ff callq ffffffff810095a8 <test_ti_thread_flag> : } 0.00 : ffffffff8100960b: c9 leaveq 0.00 : ffffffff8100960c: 85 c0 test %eax,%eax 0.00 : ffffffff8100960e: 0f 95 c0 setne %al 0.00 : ffffffff81009611: 0f b6 c0 movzbl %al,%eax : Disassembly of section .vsyscall_0: : Disassembly of section .vsyscall_fn: : Disassembly of section .vsyscall_1: : Disassembly of section .vsyscall_2: : Disassembly of section .init.text: : Disassembly of section .altinstr_replacement: : Disassembly of section .exit.text: [root@mica ~]# But from the 'perf report' result we know that there are hits for need_resched on a 4 way machine mostly doing nothing, so after adding code to show what is in each hist offset and collapsing IP hits for what happens between objdump lines we get, for the same perf.data file: [root@mica ~]# perf annotate -v need_resched ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ : : : Disassembly of section .text: : : ffffffff810095ed <need_resched>: : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095ed: 55 push %rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 52.78 : ffffffff810095ee: be 03 00 00 00 mov $0x3,%esi : : static inline struct thread_info *current_thread_info(void) : { : struct thread_info *ti; : ti = (void *)(percpu_read_stable(kernel_stack) + 0.00 : ffffffff810095f3: 65 48 8b 3c 25 48 b5 mov %gs:0xb548,%rdi 0.00 : ffffffff810095fa: 00 00 : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095fc: 48 89 e5 mov %rsp,%rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 9.72 : ffffffff810095ff: 48 81 ef d8 1f 00 00 sub $0x1fd8,%rdi 0.00 : ffffffff81009606: e8 9d ff ff ff callq ffffffff810095a8 <test_ti_thread_flag> : } 0.00 : ffffffff8100960b: c9 leaveq 0.00 : ffffffff8100960c: 85 c0 test %eax,%eax 37.50 : ffffffff8100960e: 0f 95 c0 setne %al 0.00 : ffffffff81009611: 0f b6 c0 movzbl %al,%eax : Disassembly of section .vsyscall_0: : Disassembly of section .vsyscall_fn: : Disassembly of section .vsyscall_1: : Disassembly of section .vsyscall_2: : Disassembly of section .init.text: : Disassembly of section .altinstr_replacement: : Disassembly of section .exit.text: [root@mica ~]# And now 'perf annotate -v', verbose mode, will show the hits per precise IP, so that one can make sense of the attribution to each objdumop line: [root@mica ~]# perf annotate -v need_resched Looking at the vmlinux_path (5 entries long) Using /lib/modules/2.6.33-rc8-tip-00784-g3471df5-dirty/build/vmlinux for symbols annotate_sym: filename=/lib/modules/2.6.33-rc8-tip-00784-g3471df5-dirty/build/vmlinux, sym=need_resched, start=0xffffffff810095ed, end=0xffffffff81009614 ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ ffffffff810095f1: 152 ffffffff81009603: 28 ffffffff8100960f: 55 ffffffff81009610: 53 h->sum: 288 <SNIP same annotation> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Miller <davem@davemloft.net> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1267194194-15670-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-26 22:23:14 +08:00
static int objdump_line__print(struct objdump_line *self,
struct list_head *head,
struct hist_entry *he, u64 len)
{
struct symbol *sym = he->ms.sym;
perf annotate: Handle samples not at objdump output addr boundaries Without this patch we get this for need_resched: [root@mica ~]# perf annotate need_resched ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ : : : Disassembly of section .text: : : ffffffff810095ed <need_resched>: : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095ed: 55 push %rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 0.00 : ffffffff810095ee: be 03 00 00 00 mov $0x3,%esi : : static inline struct thread_info *current_thread_info(void) : { : struct thread_info *ti; : ti = (void *)(percpu_read_stable(kernel_stack) + 0.00 : ffffffff810095f3: 65 48 8b 3c 25 48 b5 mov %gs:0xb548,%rdi 0.00 : ffffffff810095fa: 00 00 : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095fc: 48 89 e5 mov %rsp,%rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 0.00 : ffffffff810095ff: 48 81 ef d8 1f 00 00 sub $0x1fd8,%rdi 0.00 : ffffffff81009606: e8 9d ff ff ff callq ffffffff810095a8 <test_ti_thread_flag> : } 0.00 : ffffffff8100960b: c9 leaveq 0.00 : ffffffff8100960c: 85 c0 test %eax,%eax 0.00 : ffffffff8100960e: 0f 95 c0 setne %al 0.00 : ffffffff81009611: 0f b6 c0 movzbl %al,%eax : Disassembly of section .vsyscall_0: : Disassembly of section .vsyscall_fn: : Disassembly of section .vsyscall_1: : Disassembly of section .vsyscall_2: : Disassembly of section .init.text: : Disassembly of section .altinstr_replacement: : Disassembly of section .exit.text: [root@mica ~]# But from the 'perf report' result we know that there are hits for need_resched on a 4 way machine mostly doing nothing, so after adding code to show what is in each hist offset and collapsing IP hits for what happens between objdump lines we get, for the same perf.data file: [root@mica ~]# perf annotate -v need_resched ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ : : : Disassembly of section .text: : : ffffffff810095ed <need_resched>: : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095ed: 55 push %rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 52.78 : ffffffff810095ee: be 03 00 00 00 mov $0x3,%esi : : static inline struct thread_info *current_thread_info(void) : { : struct thread_info *ti; : ti = (void *)(percpu_read_stable(kernel_stack) + 0.00 : ffffffff810095f3: 65 48 8b 3c 25 48 b5 mov %gs:0xb548,%rdi 0.00 : ffffffff810095fa: 00 00 : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095fc: 48 89 e5 mov %rsp,%rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 9.72 : ffffffff810095ff: 48 81 ef d8 1f 00 00 sub $0x1fd8,%rdi 0.00 : ffffffff81009606: e8 9d ff ff ff callq ffffffff810095a8 <test_ti_thread_flag> : } 0.00 : ffffffff8100960b: c9 leaveq 0.00 : ffffffff8100960c: 85 c0 test %eax,%eax 37.50 : ffffffff8100960e: 0f 95 c0 setne %al 0.00 : ffffffff81009611: 0f b6 c0 movzbl %al,%eax : Disassembly of section .vsyscall_0: : Disassembly of section .vsyscall_fn: : Disassembly of section .vsyscall_1: : Disassembly of section .vsyscall_2: : Disassembly of section .init.text: : Disassembly of section .altinstr_replacement: : Disassembly of section .exit.text: [root@mica ~]# And now 'perf annotate -v', verbose mode, will show the hits per precise IP, so that one can make sense of the attribution to each objdumop line: [root@mica ~]# perf annotate -v need_resched Looking at the vmlinux_path (5 entries long) Using /lib/modules/2.6.33-rc8-tip-00784-g3471df5-dirty/build/vmlinux for symbols annotate_sym: filename=/lib/modules/2.6.33-rc8-tip-00784-g3471df5-dirty/build/vmlinux, sym=need_resched, start=0xffffffff810095ed, end=0xffffffff81009614 ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ ffffffff810095f1: 152 ffffffff81009603: 28 ffffffff8100960f: 55 ffffffff81009610: 53 h->sum: 288 <SNIP same annotation> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Miller <davem@davemloft.net> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1267194194-15670-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-26 22:23:14 +08:00
static const char *prev_line;
static const char *prev_color;
if (self->offset != -1) {
const char *path = NULL;
perf_counter tools: Add 'perf annotate' feature Add new perf sub-command to display annotated source code: $ perf annotate decode_tree_entry ------------------------------------------------ Percent | Source code & Disassembly of /home/mingo/git/git ------------------------------------------------ : : /home/mingo/git/git: file format elf64-x86-64 : : : Disassembly of section .text: : : 00000000004a0da0 <decode_tree_entry>: : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 3.82 : 4a0da0: 41 54 push %r12 : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.17 : 4a0da2: 48 83 fa 17 cmp $0x17,%rdx : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 0.00 : 4a0da6: 49 89 fc mov %rdi,%r12 0.00 : 4a0da9: 55 push %rbp 3.37 : 4a0daa: 53 push %rbx : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.08 : 4a0dab: 76 73 jbe 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dad: 80 7c 16 eb 00 cmpb $0x0,-0x15(%rsi,%rdx,1) 3.48 : 4a0db2: 75 6c jne 4a0e20 <decode_tree_entry+0x80> : static const char *get_mode(const char *str, unsigned int *modep) : { : unsigned char c; : unsigned int mode = 0; : : if (*str == ' ') 1.94 : 4a0db4: 0f b6 06 movzbl (%rsi),%eax 0.39 : 4a0db7: 3c 20 cmp $0x20,%al 0.00 : 4a0db9: 74 65 je 4a0e20 <decode_tree_entry+0x80> : return NULL; : : while ((c = *str++) != ' ') { 0.06 : 4a0dbb: 89 c2 mov %eax,%edx : if (c < '0' || c > '7') 1.99 : 4a0dbd: 31 ed xor %ebp,%ebp : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 1.74 : 4a0dbf: 48 8d 5e 01 lea 0x1(%rsi),%rbx : if (c < '0' || c > '7') 0.00 : 4a0dc3: 8d 42 d0 lea -0x30(%rdx),%eax 0.17 : 4a0dc6: 3c 07 cmp $0x7,%al 0.00 : 4a0dc8: 76 0d jbe 4a0dd7 <decode_tree_entry+0x37> 0.00 : 4a0dca: eb 54 jmp 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dcc: 0f 1f 40 00 nopl 0x0(%rax) 16.57 : 4a0dd0: 8d 42 d0 lea -0x30(%rdx),%eax 0.14 : 4a0dd3: 3c 07 cmp $0x7,%al 0.00 : 4a0dd5: 77 49 ja 4a0e20 <decode_tree_entry+0x80> : return NULL; : mode = (mode << 3) + (c - '0'); 3.12 : 4a0dd7: 0f b6 c2 movzbl %dl,%eax : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 0.00 : 4a0dda: 0f b6 13 movzbl (%rbx),%edx 16.74 : 4a0ddd: 48 83 c3 01 add $0x1,%rbx : if (c < '0' || c > '7') : return NULL; : mode = (mode << 3) + (c - '0'); The first column is the percentage of samples that arrived on that particular line - relative to the total cost of the function. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-06 21:48:52 +08:00
unsigned int hits = 0;
double percent = 0.0;
perf: Enable more compiler warnings Related to a shadowed variable bug fix Valdis Kletnieks noticed that perf does not get built with -Wshadow, which could have helped us avoid the bug. So enable -Wshadow and also enable the following warnings on perf builds, in addition to the already enabled -Wall -Wextra -std=gnu99 warnings: -Wcast-align -Wformat=2 -Wshadow -Winit-self -Wpacked -Wredundant-decls -Wstack-protector -Wstrict-aliasing=3 -Wswitch-default -Wswitch-enum -Wno-system-headers -Wundef -Wvolatile-register-var -Wwrite-strings -Wbad-function-cast -Wmissing-declarations -Wmissing-prototypes -Wnested-externs -Wold-style-definition -Wstrict-prototypes -Wdeclaration-after-statement And change/fix the perf code to build cleanly under GCC 4.3.2. The list of warnings enablement is rather arbitrary: it's based on my (quick) reading of the GCC manpages and trying them on perf. I categorized the warnings based on individually enabling them and looking whether they trigger something in the perf build. If i liked those warnings (i.e. if they trigger for something that arguably could be improved) i enabled the warning. If the warnings seemed to come from language laywers spamming the build with tons of nuisance warnings i generally kept them off. Most of the sign conversion related warnings were in this category. (A second patch enabling some of the sign warnings might be welcome - sign bugs can be nasty.) I also kept warnings that seem to make sense from their manpage description and which produced no actual warnings on our code base. These warnings might still be turned off if they end up being a nuisance. I also left out a few warnings that are not supported in older compilers. [ Note that these changes might break the build on older compilers i did not test, or on non-x86 architectures that produce different warnings, so more testing would be welcome. ] Reported-by: Valdis.Kletnieks@vt.edu Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-15 18:26:57 +08:00
const char *color;
struct sym_priv *priv = symbol__priv(sym);
struct sym_ext *sym_ext = priv->ext;
struct sym_hist *h = priv->hist;
perf annotate: Handle samples not at objdump output addr boundaries Without this patch we get this for need_resched: [root@mica ~]# perf annotate need_resched ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ : : : Disassembly of section .text: : : ffffffff810095ed <need_resched>: : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095ed: 55 push %rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 0.00 : ffffffff810095ee: be 03 00 00 00 mov $0x3,%esi : : static inline struct thread_info *current_thread_info(void) : { : struct thread_info *ti; : ti = (void *)(percpu_read_stable(kernel_stack) + 0.00 : ffffffff810095f3: 65 48 8b 3c 25 48 b5 mov %gs:0xb548,%rdi 0.00 : ffffffff810095fa: 00 00 : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095fc: 48 89 e5 mov %rsp,%rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 0.00 : ffffffff810095ff: 48 81 ef d8 1f 00 00 sub $0x1fd8,%rdi 0.00 : ffffffff81009606: e8 9d ff ff ff callq ffffffff810095a8 <test_ti_thread_flag> : } 0.00 : ffffffff8100960b: c9 leaveq 0.00 : ffffffff8100960c: 85 c0 test %eax,%eax 0.00 : ffffffff8100960e: 0f 95 c0 setne %al 0.00 : ffffffff81009611: 0f b6 c0 movzbl %al,%eax : Disassembly of section .vsyscall_0: : Disassembly of section .vsyscall_fn: : Disassembly of section .vsyscall_1: : Disassembly of section .vsyscall_2: : Disassembly of section .init.text: : Disassembly of section .altinstr_replacement: : Disassembly of section .exit.text: [root@mica ~]# But from the 'perf report' result we know that there are hits for need_resched on a 4 way machine mostly doing nothing, so after adding code to show what is in each hist offset and collapsing IP hits for what happens between objdump lines we get, for the same perf.data file: [root@mica ~]# perf annotate -v need_resched ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ : : : Disassembly of section .text: : : ffffffff810095ed <need_resched>: : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095ed: 55 push %rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 52.78 : ffffffff810095ee: be 03 00 00 00 mov $0x3,%esi : : static inline struct thread_info *current_thread_info(void) : { : struct thread_info *ti; : ti = (void *)(percpu_read_stable(kernel_stack) + 0.00 : ffffffff810095f3: 65 48 8b 3c 25 48 b5 mov %gs:0xb548,%rdi 0.00 : ffffffff810095fa: 00 00 : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095fc: 48 89 e5 mov %rsp,%rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 9.72 : ffffffff810095ff: 48 81 ef d8 1f 00 00 sub $0x1fd8,%rdi 0.00 : ffffffff81009606: e8 9d ff ff ff callq ffffffff810095a8 <test_ti_thread_flag> : } 0.00 : ffffffff8100960b: c9 leaveq 0.00 : ffffffff8100960c: 85 c0 test %eax,%eax 37.50 : ffffffff8100960e: 0f 95 c0 setne %al 0.00 : ffffffff81009611: 0f b6 c0 movzbl %al,%eax : Disassembly of section .vsyscall_0: : Disassembly of section .vsyscall_fn: : Disassembly of section .vsyscall_1: : Disassembly of section .vsyscall_2: : Disassembly of section .init.text: : Disassembly of section .altinstr_replacement: : Disassembly of section .exit.text: [root@mica ~]# And now 'perf annotate -v', verbose mode, will show the hits per precise IP, so that one can make sense of the attribution to each objdumop line: [root@mica ~]# perf annotate -v need_resched Looking at the vmlinux_path (5 entries long) Using /lib/modules/2.6.33-rc8-tip-00784-g3471df5-dirty/build/vmlinux for symbols annotate_sym: filename=/lib/modules/2.6.33-rc8-tip-00784-g3471df5-dirty/build/vmlinux, sym=need_resched, start=0xffffffff810095ed, end=0xffffffff81009614 ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ ffffffff810095f1: 152 ffffffff81009603: 28 ffffffff8100960f: 55 ffffffff81009610: 53 h->sum: 288 <SNIP same annotation> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Miller <davem@davemloft.net> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1267194194-15670-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-26 22:23:14 +08:00
s64 offset = self->offset;
struct objdump_line *next = objdump__get_next_ip_line(head, self);
while (offset < (s64)len &&
(next == NULL || offset < next->offset)) {
if (sym_ext) {
if (path == NULL)
path = sym_ext[offset].path;
percent += sym_ext[offset].percent;
} else
hits += h->ip[offset];
++offset;
}
perf_counter tools: Add 'perf annotate' feature Add new perf sub-command to display annotated source code: $ perf annotate decode_tree_entry ------------------------------------------------ Percent | Source code & Disassembly of /home/mingo/git/git ------------------------------------------------ : : /home/mingo/git/git: file format elf64-x86-64 : : : Disassembly of section .text: : : 00000000004a0da0 <decode_tree_entry>: : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 3.82 : 4a0da0: 41 54 push %r12 : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.17 : 4a0da2: 48 83 fa 17 cmp $0x17,%rdx : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 0.00 : 4a0da6: 49 89 fc mov %rdi,%r12 0.00 : 4a0da9: 55 push %rbp 3.37 : 4a0daa: 53 push %rbx : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.08 : 4a0dab: 76 73 jbe 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dad: 80 7c 16 eb 00 cmpb $0x0,-0x15(%rsi,%rdx,1) 3.48 : 4a0db2: 75 6c jne 4a0e20 <decode_tree_entry+0x80> : static const char *get_mode(const char *str, unsigned int *modep) : { : unsigned char c; : unsigned int mode = 0; : : if (*str == ' ') 1.94 : 4a0db4: 0f b6 06 movzbl (%rsi),%eax 0.39 : 4a0db7: 3c 20 cmp $0x20,%al 0.00 : 4a0db9: 74 65 je 4a0e20 <decode_tree_entry+0x80> : return NULL; : : while ((c = *str++) != ' ') { 0.06 : 4a0dbb: 89 c2 mov %eax,%edx : if (c < '0' || c > '7') 1.99 : 4a0dbd: 31 ed xor %ebp,%ebp : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 1.74 : 4a0dbf: 48 8d 5e 01 lea 0x1(%rsi),%rbx : if (c < '0' || c > '7') 0.00 : 4a0dc3: 8d 42 d0 lea -0x30(%rdx),%eax 0.17 : 4a0dc6: 3c 07 cmp $0x7,%al 0.00 : 4a0dc8: 76 0d jbe 4a0dd7 <decode_tree_entry+0x37> 0.00 : 4a0dca: eb 54 jmp 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dcc: 0f 1f 40 00 nopl 0x0(%rax) 16.57 : 4a0dd0: 8d 42 d0 lea -0x30(%rdx),%eax 0.14 : 4a0dd3: 3c 07 cmp $0x7,%al 0.00 : 4a0dd5: 77 49 ja 4a0e20 <decode_tree_entry+0x80> : return NULL; : mode = (mode << 3) + (c - '0'); 3.12 : 4a0dd7: 0f b6 c2 movzbl %dl,%eax : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 0.00 : 4a0dda: 0f b6 13 movzbl (%rbx),%edx 16.74 : 4a0ddd: 48 83 c3 01 add $0x1,%rbx : if (c < '0' || c > '7') : return NULL; : mode = (mode << 3) + (c - '0'); The first column is the percentage of samples that arrived on that particular line - relative to the total cost of the function. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-06 21:48:52 +08:00
perf annotate: Handle samples not at objdump output addr boundaries Without this patch we get this for need_resched: [root@mica ~]# perf annotate need_resched ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ : : : Disassembly of section .text: : : ffffffff810095ed <need_resched>: : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095ed: 55 push %rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 0.00 : ffffffff810095ee: be 03 00 00 00 mov $0x3,%esi : : static inline struct thread_info *current_thread_info(void) : { : struct thread_info *ti; : ti = (void *)(percpu_read_stable(kernel_stack) + 0.00 : ffffffff810095f3: 65 48 8b 3c 25 48 b5 mov %gs:0xb548,%rdi 0.00 : ffffffff810095fa: 00 00 : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095fc: 48 89 e5 mov %rsp,%rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 0.00 : ffffffff810095ff: 48 81 ef d8 1f 00 00 sub $0x1fd8,%rdi 0.00 : ffffffff81009606: e8 9d ff ff ff callq ffffffff810095a8 <test_ti_thread_flag> : } 0.00 : ffffffff8100960b: c9 leaveq 0.00 : ffffffff8100960c: 85 c0 test %eax,%eax 0.00 : ffffffff8100960e: 0f 95 c0 setne %al 0.00 : ffffffff81009611: 0f b6 c0 movzbl %al,%eax : Disassembly of section .vsyscall_0: : Disassembly of section .vsyscall_fn: : Disassembly of section .vsyscall_1: : Disassembly of section .vsyscall_2: : Disassembly of section .init.text: : Disassembly of section .altinstr_replacement: : Disassembly of section .exit.text: [root@mica ~]# But from the 'perf report' result we know that there are hits for need_resched on a 4 way machine mostly doing nothing, so after adding code to show what is in each hist offset and collapsing IP hits for what happens between objdump lines we get, for the same perf.data file: [root@mica ~]# perf annotate -v need_resched ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ : : : Disassembly of section .text: : : ffffffff810095ed <need_resched>: : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095ed: 55 push %rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 52.78 : ffffffff810095ee: be 03 00 00 00 mov $0x3,%esi : : static inline struct thread_info *current_thread_info(void) : { : struct thread_info *ti; : ti = (void *)(percpu_read_stable(kernel_stack) + 0.00 : ffffffff810095f3: 65 48 8b 3c 25 48 b5 mov %gs:0xb548,%rdi 0.00 : ffffffff810095fa: 00 00 : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095fc: 48 89 e5 mov %rsp,%rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 9.72 : ffffffff810095ff: 48 81 ef d8 1f 00 00 sub $0x1fd8,%rdi 0.00 : ffffffff81009606: e8 9d ff ff ff callq ffffffff810095a8 <test_ti_thread_flag> : } 0.00 : ffffffff8100960b: c9 leaveq 0.00 : ffffffff8100960c: 85 c0 test %eax,%eax 37.50 : ffffffff8100960e: 0f 95 c0 setne %al 0.00 : ffffffff81009611: 0f b6 c0 movzbl %al,%eax : Disassembly of section .vsyscall_0: : Disassembly of section .vsyscall_fn: : Disassembly of section .vsyscall_1: : Disassembly of section .vsyscall_2: : Disassembly of section .init.text: : Disassembly of section .altinstr_replacement: : Disassembly of section .exit.text: [root@mica ~]# And now 'perf annotate -v', verbose mode, will show the hits per precise IP, so that one can make sense of the attribution to each objdumop line: [root@mica ~]# perf annotate -v need_resched Looking at the vmlinux_path (5 entries long) Using /lib/modules/2.6.33-rc8-tip-00784-g3471df5-dirty/build/vmlinux for symbols annotate_sym: filename=/lib/modules/2.6.33-rc8-tip-00784-g3471df5-dirty/build/vmlinux, sym=need_resched, start=0xffffffff810095ed, end=0xffffffff81009614 ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ ffffffff810095f1: 152 ffffffff81009603: 28 ffffffff8100960f: 55 ffffffff81009610: 53 h->sum: 288 <SNIP same annotation> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Miller <davem@davemloft.net> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1267194194-15670-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-26 22:23:14 +08:00
if (sym_ext == NULL && h->sum)
percent = 100.0 * hits / h->sum;
perf_counter tools: Add 'perf annotate' feature Add new perf sub-command to display annotated source code: $ perf annotate decode_tree_entry ------------------------------------------------ Percent | Source code & Disassembly of /home/mingo/git/git ------------------------------------------------ : : /home/mingo/git/git: file format elf64-x86-64 : : : Disassembly of section .text: : : 00000000004a0da0 <decode_tree_entry>: : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 3.82 : 4a0da0: 41 54 push %r12 : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.17 : 4a0da2: 48 83 fa 17 cmp $0x17,%rdx : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 0.00 : 4a0da6: 49 89 fc mov %rdi,%r12 0.00 : 4a0da9: 55 push %rbp 3.37 : 4a0daa: 53 push %rbx : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.08 : 4a0dab: 76 73 jbe 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dad: 80 7c 16 eb 00 cmpb $0x0,-0x15(%rsi,%rdx,1) 3.48 : 4a0db2: 75 6c jne 4a0e20 <decode_tree_entry+0x80> : static const char *get_mode(const char *str, unsigned int *modep) : { : unsigned char c; : unsigned int mode = 0; : : if (*str == ' ') 1.94 : 4a0db4: 0f b6 06 movzbl (%rsi),%eax 0.39 : 4a0db7: 3c 20 cmp $0x20,%al 0.00 : 4a0db9: 74 65 je 4a0e20 <decode_tree_entry+0x80> : return NULL; : : while ((c = *str++) != ' ') { 0.06 : 4a0dbb: 89 c2 mov %eax,%edx : if (c < '0' || c > '7') 1.99 : 4a0dbd: 31 ed xor %ebp,%ebp : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 1.74 : 4a0dbf: 48 8d 5e 01 lea 0x1(%rsi),%rbx : if (c < '0' || c > '7') 0.00 : 4a0dc3: 8d 42 d0 lea -0x30(%rdx),%eax 0.17 : 4a0dc6: 3c 07 cmp $0x7,%al 0.00 : 4a0dc8: 76 0d jbe 4a0dd7 <decode_tree_entry+0x37> 0.00 : 4a0dca: eb 54 jmp 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dcc: 0f 1f 40 00 nopl 0x0(%rax) 16.57 : 4a0dd0: 8d 42 d0 lea -0x30(%rdx),%eax 0.14 : 4a0dd3: 3c 07 cmp $0x7,%al 0.00 : 4a0dd5: 77 49 ja 4a0e20 <decode_tree_entry+0x80> : return NULL; : mode = (mode << 3) + (c - '0'); 3.12 : 4a0dd7: 0f b6 c2 movzbl %dl,%eax : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 0.00 : 4a0dda: 0f b6 13 movzbl (%rbx),%edx 16.74 : 4a0ddd: 48 83 c3 01 add $0x1,%rbx : if (c < '0' || c > '7') : return NULL; : mode = (mode << 3) + (c - '0'); The first column is the percentage of samples that arrived on that particular line - relative to the total cost of the function. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-06 21:48:52 +08:00
color = get_percent_color(percent);
perf_counter tools: Add 'perf annotate' feature Add new perf sub-command to display annotated source code: $ perf annotate decode_tree_entry ------------------------------------------------ Percent | Source code & Disassembly of /home/mingo/git/git ------------------------------------------------ : : /home/mingo/git/git: file format elf64-x86-64 : : : Disassembly of section .text: : : 00000000004a0da0 <decode_tree_entry>: : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 3.82 : 4a0da0: 41 54 push %r12 : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.17 : 4a0da2: 48 83 fa 17 cmp $0x17,%rdx : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 0.00 : 4a0da6: 49 89 fc mov %rdi,%r12 0.00 : 4a0da9: 55 push %rbp 3.37 : 4a0daa: 53 push %rbx : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.08 : 4a0dab: 76 73 jbe 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dad: 80 7c 16 eb 00 cmpb $0x0,-0x15(%rsi,%rdx,1) 3.48 : 4a0db2: 75 6c jne 4a0e20 <decode_tree_entry+0x80> : static const char *get_mode(const char *str, unsigned int *modep) : { : unsigned char c; : unsigned int mode = 0; : : if (*str == ' ') 1.94 : 4a0db4: 0f b6 06 movzbl (%rsi),%eax 0.39 : 4a0db7: 3c 20 cmp $0x20,%al 0.00 : 4a0db9: 74 65 je 4a0e20 <decode_tree_entry+0x80> : return NULL; : : while ((c = *str++) != ' ') { 0.06 : 4a0dbb: 89 c2 mov %eax,%edx : if (c < '0' || c > '7') 1.99 : 4a0dbd: 31 ed xor %ebp,%ebp : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 1.74 : 4a0dbf: 48 8d 5e 01 lea 0x1(%rsi),%rbx : if (c < '0' || c > '7') 0.00 : 4a0dc3: 8d 42 d0 lea -0x30(%rdx),%eax 0.17 : 4a0dc6: 3c 07 cmp $0x7,%al 0.00 : 4a0dc8: 76 0d jbe 4a0dd7 <decode_tree_entry+0x37> 0.00 : 4a0dca: eb 54 jmp 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dcc: 0f 1f 40 00 nopl 0x0(%rax) 16.57 : 4a0dd0: 8d 42 d0 lea -0x30(%rdx),%eax 0.14 : 4a0dd3: 3c 07 cmp $0x7,%al 0.00 : 4a0dd5: 77 49 ja 4a0e20 <decode_tree_entry+0x80> : return NULL; : mode = (mode << 3) + (c - '0'); 3.12 : 4a0dd7: 0f b6 c2 movzbl %dl,%eax : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 0.00 : 4a0dda: 0f b6 13 movzbl (%rbx),%edx 16.74 : 4a0ddd: 48 83 c3 01 add $0x1,%rbx : if (c < '0' || c > '7') : return NULL; : mode = (mode << 3) + (c - '0'); The first column is the percentage of samples that arrived on that particular line - relative to the total cost of the function. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-06 21:48:52 +08:00
/*
* Also color the filename and line if needed, with
* the same color than the percentage. Don't print it
* twice for close colored ip with the same filename:line
*/
if (path) {
if (!prev_line || strcmp(prev_line, path)
|| color != prev_color) {
color_fprintf(stdout, color, " %s", path);
prev_line = path;
prev_color = color;
}
}
perf_counter tools: Add 'perf annotate' feature Add new perf sub-command to display annotated source code: $ perf annotate decode_tree_entry ------------------------------------------------ Percent | Source code & Disassembly of /home/mingo/git/git ------------------------------------------------ : : /home/mingo/git/git: file format elf64-x86-64 : : : Disassembly of section .text: : : 00000000004a0da0 <decode_tree_entry>: : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 3.82 : 4a0da0: 41 54 push %r12 : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.17 : 4a0da2: 48 83 fa 17 cmp $0x17,%rdx : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 0.00 : 4a0da6: 49 89 fc mov %rdi,%r12 0.00 : 4a0da9: 55 push %rbp 3.37 : 4a0daa: 53 push %rbx : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.08 : 4a0dab: 76 73 jbe 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dad: 80 7c 16 eb 00 cmpb $0x0,-0x15(%rsi,%rdx,1) 3.48 : 4a0db2: 75 6c jne 4a0e20 <decode_tree_entry+0x80> : static const char *get_mode(const char *str, unsigned int *modep) : { : unsigned char c; : unsigned int mode = 0; : : if (*str == ' ') 1.94 : 4a0db4: 0f b6 06 movzbl (%rsi),%eax 0.39 : 4a0db7: 3c 20 cmp $0x20,%al 0.00 : 4a0db9: 74 65 je 4a0e20 <decode_tree_entry+0x80> : return NULL; : : while ((c = *str++) != ' ') { 0.06 : 4a0dbb: 89 c2 mov %eax,%edx : if (c < '0' || c > '7') 1.99 : 4a0dbd: 31 ed xor %ebp,%ebp : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 1.74 : 4a0dbf: 48 8d 5e 01 lea 0x1(%rsi),%rbx : if (c < '0' || c > '7') 0.00 : 4a0dc3: 8d 42 d0 lea -0x30(%rdx),%eax 0.17 : 4a0dc6: 3c 07 cmp $0x7,%al 0.00 : 4a0dc8: 76 0d jbe 4a0dd7 <decode_tree_entry+0x37> 0.00 : 4a0dca: eb 54 jmp 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dcc: 0f 1f 40 00 nopl 0x0(%rax) 16.57 : 4a0dd0: 8d 42 d0 lea -0x30(%rdx),%eax 0.14 : 4a0dd3: 3c 07 cmp $0x7,%al 0.00 : 4a0dd5: 77 49 ja 4a0e20 <decode_tree_entry+0x80> : return NULL; : mode = (mode << 3) + (c - '0'); 3.12 : 4a0dd7: 0f b6 c2 movzbl %dl,%eax : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 0.00 : 4a0dda: 0f b6 13 movzbl (%rbx),%edx 16.74 : 4a0ddd: 48 83 c3 01 add $0x1,%rbx : if (c < '0' || c > '7') : return NULL; : mode = (mode << 3) + (c - '0'); The first column is the percentage of samples that arrived on that particular line - relative to the total cost of the function. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-06 21:48:52 +08:00
color_fprintf(stdout, color, " %7.2f", percent);
printf(" : ");
perf annotate: Handle samples not at objdump output addr boundaries Without this patch we get this for need_resched: [root@mica ~]# perf annotate need_resched ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ : : : Disassembly of section .text: : : ffffffff810095ed <need_resched>: : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095ed: 55 push %rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 0.00 : ffffffff810095ee: be 03 00 00 00 mov $0x3,%esi : : static inline struct thread_info *current_thread_info(void) : { : struct thread_info *ti; : ti = (void *)(percpu_read_stable(kernel_stack) + 0.00 : ffffffff810095f3: 65 48 8b 3c 25 48 b5 mov %gs:0xb548,%rdi 0.00 : ffffffff810095fa: 00 00 : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095fc: 48 89 e5 mov %rsp,%rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 0.00 : ffffffff810095ff: 48 81 ef d8 1f 00 00 sub $0x1fd8,%rdi 0.00 : ffffffff81009606: e8 9d ff ff ff callq ffffffff810095a8 <test_ti_thread_flag> : } 0.00 : ffffffff8100960b: c9 leaveq 0.00 : ffffffff8100960c: 85 c0 test %eax,%eax 0.00 : ffffffff8100960e: 0f 95 c0 setne %al 0.00 : ffffffff81009611: 0f b6 c0 movzbl %al,%eax : Disassembly of section .vsyscall_0: : Disassembly of section .vsyscall_fn: : Disassembly of section .vsyscall_1: : Disassembly of section .vsyscall_2: : Disassembly of section .init.text: : Disassembly of section .altinstr_replacement: : Disassembly of section .exit.text: [root@mica ~]# But from the 'perf report' result we know that there are hits for need_resched on a 4 way machine mostly doing nothing, so after adding code to show what is in each hist offset and collapsing IP hits for what happens between objdump lines we get, for the same perf.data file: [root@mica ~]# perf annotate -v need_resched ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ : : : Disassembly of section .text: : : ffffffff810095ed <need_resched>: : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095ed: 55 push %rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 52.78 : ffffffff810095ee: be 03 00 00 00 mov $0x3,%esi : : static inline struct thread_info *current_thread_info(void) : { : struct thread_info *ti; : ti = (void *)(percpu_read_stable(kernel_stack) + 0.00 : ffffffff810095f3: 65 48 8b 3c 25 48 b5 mov %gs:0xb548,%rdi 0.00 : ffffffff810095fa: 00 00 : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095fc: 48 89 e5 mov %rsp,%rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 9.72 : ffffffff810095ff: 48 81 ef d8 1f 00 00 sub $0x1fd8,%rdi 0.00 : ffffffff81009606: e8 9d ff ff ff callq ffffffff810095a8 <test_ti_thread_flag> : } 0.00 : ffffffff8100960b: c9 leaveq 0.00 : ffffffff8100960c: 85 c0 test %eax,%eax 37.50 : ffffffff8100960e: 0f 95 c0 setne %al 0.00 : ffffffff81009611: 0f b6 c0 movzbl %al,%eax : Disassembly of section .vsyscall_0: : Disassembly of section .vsyscall_fn: : Disassembly of section .vsyscall_1: : Disassembly of section .vsyscall_2: : Disassembly of section .init.text: : Disassembly of section .altinstr_replacement: : Disassembly of section .exit.text: [root@mica ~]# And now 'perf annotate -v', verbose mode, will show the hits per precise IP, so that one can make sense of the attribution to each objdumop line: [root@mica ~]# perf annotate -v need_resched Looking at the vmlinux_path (5 entries long) Using /lib/modules/2.6.33-rc8-tip-00784-g3471df5-dirty/build/vmlinux for symbols annotate_sym: filename=/lib/modules/2.6.33-rc8-tip-00784-g3471df5-dirty/build/vmlinux, sym=need_resched, start=0xffffffff810095ed, end=0xffffffff81009614 ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ ffffffff810095f1: 152 ffffffff81009603: 28 ffffffff8100960f: 55 ffffffff81009610: 53 h->sum: 288 <SNIP same annotation> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Miller <davem@davemloft.net> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1267194194-15670-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-26 22:23:14 +08:00
color_fprintf(stdout, PERF_COLOR_BLUE, "%s\n", self->line);
perf_counter tools: Add 'perf annotate' feature Add new perf sub-command to display annotated source code: $ perf annotate decode_tree_entry ------------------------------------------------ Percent | Source code & Disassembly of /home/mingo/git/git ------------------------------------------------ : : /home/mingo/git/git: file format elf64-x86-64 : : : Disassembly of section .text: : : 00000000004a0da0 <decode_tree_entry>: : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 3.82 : 4a0da0: 41 54 push %r12 : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.17 : 4a0da2: 48 83 fa 17 cmp $0x17,%rdx : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 0.00 : 4a0da6: 49 89 fc mov %rdi,%r12 0.00 : 4a0da9: 55 push %rbp 3.37 : 4a0daa: 53 push %rbx : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.08 : 4a0dab: 76 73 jbe 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dad: 80 7c 16 eb 00 cmpb $0x0,-0x15(%rsi,%rdx,1) 3.48 : 4a0db2: 75 6c jne 4a0e20 <decode_tree_entry+0x80> : static const char *get_mode(const char *str, unsigned int *modep) : { : unsigned char c; : unsigned int mode = 0; : : if (*str == ' ') 1.94 : 4a0db4: 0f b6 06 movzbl (%rsi),%eax 0.39 : 4a0db7: 3c 20 cmp $0x20,%al 0.00 : 4a0db9: 74 65 je 4a0e20 <decode_tree_entry+0x80> : return NULL; : : while ((c = *str++) != ' ') { 0.06 : 4a0dbb: 89 c2 mov %eax,%edx : if (c < '0' || c > '7') 1.99 : 4a0dbd: 31 ed xor %ebp,%ebp : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 1.74 : 4a0dbf: 48 8d 5e 01 lea 0x1(%rsi),%rbx : if (c < '0' || c > '7') 0.00 : 4a0dc3: 8d 42 d0 lea -0x30(%rdx),%eax 0.17 : 4a0dc6: 3c 07 cmp $0x7,%al 0.00 : 4a0dc8: 76 0d jbe 4a0dd7 <decode_tree_entry+0x37> 0.00 : 4a0dca: eb 54 jmp 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dcc: 0f 1f 40 00 nopl 0x0(%rax) 16.57 : 4a0dd0: 8d 42 d0 lea -0x30(%rdx),%eax 0.14 : 4a0dd3: 3c 07 cmp $0x7,%al 0.00 : 4a0dd5: 77 49 ja 4a0e20 <decode_tree_entry+0x80> : return NULL; : mode = (mode << 3) + (c - '0'); 3.12 : 4a0dd7: 0f b6 c2 movzbl %dl,%eax : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 0.00 : 4a0dda: 0f b6 13 movzbl (%rbx),%edx 16.74 : 4a0ddd: 48 83 c3 01 add $0x1,%rbx : if (c < '0' || c > '7') : return NULL; : mode = (mode << 3) + (c - '0'); The first column is the percentage of samples that arrived on that particular line - relative to the total cost of the function. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-06 21:48:52 +08:00
} else {
perf annotate: Handle samples not at objdump output addr boundaries Without this patch we get this for need_resched: [root@mica ~]# perf annotate need_resched ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ : : : Disassembly of section .text: : : ffffffff810095ed <need_resched>: : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095ed: 55 push %rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 0.00 : ffffffff810095ee: be 03 00 00 00 mov $0x3,%esi : : static inline struct thread_info *current_thread_info(void) : { : struct thread_info *ti; : ti = (void *)(percpu_read_stable(kernel_stack) + 0.00 : ffffffff810095f3: 65 48 8b 3c 25 48 b5 mov %gs:0xb548,%rdi 0.00 : ffffffff810095fa: 00 00 : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095fc: 48 89 e5 mov %rsp,%rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 0.00 : ffffffff810095ff: 48 81 ef d8 1f 00 00 sub $0x1fd8,%rdi 0.00 : ffffffff81009606: e8 9d ff ff ff callq ffffffff810095a8 <test_ti_thread_flag> : } 0.00 : ffffffff8100960b: c9 leaveq 0.00 : ffffffff8100960c: 85 c0 test %eax,%eax 0.00 : ffffffff8100960e: 0f 95 c0 setne %al 0.00 : ffffffff81009611: 0f b6 c0 movzbl %al,%eax : Disassembly of section .vsyscall_0: : Disassembly of section .vsyscall_fn: : Disassembly of section .vsyscall_1: : Disassembly of section .vsyscall_2: : Disassembly of section .init.text: : Disassembly of section .altinstr_replacement: : Disassembly of section .exit.text: [root@mica ~]# But from the 'perf report' result we know that there are hits for need_resched on a 4 way machine mostly doing nothing, so after adding code to show what is in each hist offset and collapsing IP hits for what happens between objdump lines we get, for the same perf.data file: [root@mica ~]# perf annotate -v need_resched ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ : : : Disassembly of section .text: : : ffffffff810095ed <need_resched>: : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095ed: 55 push %rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 52.78 : ffffffff810095ee: be 03 00 00 00 mov $0x3,%esi : : static inline struct thread_info *current_thread_info(void) : { : struct thread_info *ti; : ti = (void *)(percpu_read_stable(kernel_stack) + 0.00 : ffffffff810095f3: 65 48 8b 3c 25 48 b5 mov %gs:0xb548,%rdi 0.00 : ffffffff810095fa: 00 00 : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095fc: 48 89 e5 mov %rsp,%rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 9.72 : ffffffff810095ff: 48 81 ef d8 1f 00 00 sub $0x1fd8,%rdi 0.00 : ffffffff81009606: e8 9d ff ff ff callq ffffffff810095a8 <test_ti_thread_flag> : } 0.00 : ffffffff8100960b: c9 leaveq 0.00 : ffffffff8100960c: 85 c0 test %eax,%eax 37.50 : ffffffff8100960e: 0f 95 c0 setne %al 0.00 : ffffffff81009611: 0f b6 c0 movzbl %al,%eax : Disassembly of section .vsyscall_0: : Disassembly of section .vsyscall_fn: : Disassembly of section .vsyscall_1: : Disassembly of section .vsyscall_2: : Disassembly of section .init.text: : Disassembly of section .altinstr_replacement: : Disassembly of section .exit.text: [root@mica ~]# And now 'perf annotate -v', verbose mode, will show the hits per precise IP, so that one can make sense of the attribution to each objdumop line: [root@mica ~]# perf annotate -v need_resched Looking at the vmlinux_path (5 entries long) Using /lib/modules/2.6.33-rc8-tip-00784-g3471df5-dirty/build/vmlinux for symbols annotate_sym: filename=/lib/modules/2.6.33-rc8-tip-00784-g3471df5-dirty/build/vmlinux, sym=need_resched, start=0xffffffff810095ed, end=0xffffffff81009614 ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ ffffffff810095f1: 152 ffffffff81009603: 28 ffffffff8100960f: 55 ffffffff81009610: 53 h->sum: 288 <SNIP same annotation> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Miller <davem@davemloft.net> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1267194194-15670-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-26 22:23:14 +08:00
if (!*self->line)
perf_counter tools: Add 'perf annotate' feature Add new perf sub-command to display annotated source code: $ perf annotate decode_tree_entry ------------------------------------------------ Percent | Source code & Disassembly of /home/mingo/git/git ------------------------------------------------ : : /home/mingo/git/git: file format elf64-x86-64 : : : Disassembly of section .text: : : 00000000004a0da0 <decode_tree_entry>: : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 3.82 : 4a0da0: 41 54 push %r12 : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.17 : 4a0da2: 48 83 fa 17 cmp $0x17,%rdx : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 0.00 : 4a0da6: 49 89 fc mov %rdi,%r12 0.00 : 4a0da9: 55 push %rbp 3.37 : 4a0daa: 53 push %rbx : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.08 : 4a0dab: 76 73 jbe 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dad: 80 7c 16 eb 00 cmpb $0x0,-0x15(%rsi,%rdx,1) 3.48 : 4a0db2: 75 6c jne 4a0e20 <decode_tree_entry+0x80> : static const char *get_mode(const char *str, unsigned int *modep) : { : unsigned char c; : unsigned int mode = 0; : : if (*str == ' ') 1.94 : 4a0db4: 0f b6 06 movzbl (%rsi),%eax 0.39 : 4a0db7: 3c 20 cmp $0x20,%al 0.00 : 4a0db9: 74 65 je 4a0e20 <decode_tree_entry+0x80> : return NULL; : : while ((c = *str++) != ' ') { 0.06 : 4a0dbb: 89 c2 mov %eax,%edx : if (c < '0' || c > '7') 1.99 : 4a0dbd: 31 ed xor %ebp,%ebp : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 1.74 : 4a0dbf: 48 8d 5e 01 lea 0x1(%rsi),%rbx : if (c < '0' || c > '7') 0.00 : 4a0dc3: 8d 42 d0 lea -0x30(%rdx),%eax 0.17 : 4a0dc6: 3c 07 cmp $0x7,%al 0.00 : 4a0dc8: 76 0d jbe 4a0dd7 <decode_tree_entry+0x37> 0.00 : 4a0dca: eb 54 jmp 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dcc: 0f 1f 40 00 nopl 0x0(%rax) 16.57 : 4a0dd0: 8d 42 d0 lea -0x30(%rdx),%eax 0.14 : 4a0dd3: 3c 07 cmp $0x7,%al 0.00 : 4a0dd5: 77 49 ja 4a0e20 <decode_tree_entry+0x80> : return NULL; : mode = (mode << 3) + (c - '0'); 3.12 : 4a0dd7: 0f b6 c2 movzbl %dl,%eax : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 0.00 : 4a0dda: 0f b6 13 movzbl (%rbx),%edx 16.74 : 4a0ddd: 48 83 c3 01 add $0x1,%rbx : if (c < '0' || c > '7') : return NULL; : mode = (mode << 3) + (c - '0'); The first column is the percentage of samples that arrived on that particular line - relative to the total cost of the function. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-06 21:48:52 +08:00
printf(" :\n");
else
perf annotate: Handle samples not at objdump output addr boundaries Without this patch we get this for need_resched: [root@mica ~]# perf annotate need_resched ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ : : : Disassembly of section .text: : : ffffffff810095ed <need_resched>: : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095ed: 55 push %rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 0.00 : ffffffff810095ee: be 03 00 00 00 mov $0x3,%esi : : static inline struct thread_info *current_thread_info(void) : { : struct thread_info *ti; : ti = (void *)(percpu_read_stable(kernel_stack) + 0.00 : ffffffff810095f3: 65 48 8b 3c 25 48 b5 mov %gs:0xb548,%rdi 0.00 : ffffffff810095fa: 00 00 : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095fc: 48 89 e5 mov %rsp,%rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 0.00 : ffffffff810095ff: 48 81 ef d8 1f 00 00 sub $0x1fd8,%rdi 0.00 : ffffffff81009606: e8 9d ff ff ff callq ffffffff810095a8 <test_ti_thread_flag> : } 0.00 : ffffffff8100960b: c9 leaveq 0.00 : ffffffff8100960c: 85 c0 test %eax,%eax 0.00 : ffffffff8100960e: 0f 95 c0 setne %al 0.00 : ffffffff81009611: 0f b6 c0 movzbl %al,%eax : Disassembly of section .vsyscall_0: : Disassembly of section .vsyscall_fn: : Disassembly of section .vsyscall_1: : Disassembly of section .vsyscall_2: : Disassembly of section .init.text: : Disassembly of section .altinstr_replacement: : Disassembly of section .exit.text: [root@mica ~]# But from the 'perf report' result we know that there are hits for need_resched on a 4 way machine mostly doing nothing, so after adding code to show what is in each hist offset and collapsing IP hits for what happens between objdump lines we get, for the same perf.data file: [root@mica ~]# perf annotate -v need_resched ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ : : : Disassembly of section .text: : : ffffffff810095ed <need_resched>: : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095ed: 55 push %rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 52.78 : ffffffff810095ee: be 03 00 00 00 mov $0x3,%esi : : static inline struct thread_info *current_thread_info(void) : { : struct thread_info *ti; : ti = (void *)(percpu_read_stable(kernel_stack) + 0.00 : ffffffff810095f3: 65 48 8b 3c 25 48 b5 mov %gs:0xb548,%rdi 0.00 : ffffffff810095fa: 00 00 : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095fc: 48 89 e5 mov %rsp,%rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 9.72 : ffffffff810095ff: 48 81 ef d8 1f 00 00 sub $0x1fd8,%rdi 0.00 : ffffffff81009606: e8 9d ff ff ff callq ffffffff810095a8 <test_ti_thread_flag> : } 0.00 : ffffffff8100960b: c9 leaveq 0.00 : ffffffff8100960c: 85 c0 test %eax,%eax 37.50 : ffffffff8100960e: 0f 95 c0 setne %al 0.00 : ffffffff81009611: 0f b6 c0 movzbl %al,%eax : Disassembly of section .vsyscall_0: : Disassembly of section .vsyscall_fn: : Disassembly of section .vsyscall_1: : Disassembly of section .vsyscall_2: : Disassembly of section .init.text: : Disassembly of section .altinstr_replacement: : Disassembly of section .exit.text: [root@mica ~]# And now 'perf annotate -v', verbose mode, will show the hits per precise IP, so that one can make sense of the attribution to each objdumop line: [root@mica ~]# perf annotate -v need_resched Looking at the vmlinux_path (5 entries long) Using /lib/modules/2.6.33-rc8-tip-00784-g3471df5-dirty/build/vmlinux for symbols annotate_sym: filename=/lib/modules/2.6.33-rc8-tip-00784-g3471df5-dirty/build/vmlinux, sym=need_resched, start=0xffffffff810095ed, end=0xffffffff81009614 ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ ffffffff810095f1: 152 ffffffff81009603: 28 ffffffff8100960f: 55 ffffffff81009610: 53 h->sum: 288 <SNIP same annotation> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Miller <davem@davemloft.net> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1267194194-15670-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-26 22:23:14 +08:00
printf(" : %s\n", self->line);
perf_counter tools: Add 'perf annotate' feature Add new perf sub-command to display annotated source code: $ perf annotate decode_tree_entry ------------------------------------------------ Percent | Source code & Disassembly of /home/mingo/git/git ------------------------------------------------ : : /home/mingo/git/git: file format elf64-x86-64 : : : Disassembly of section .text: : : 00000000004a0da0 <decode_tree_entry>: : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 3.82 : 4a0da0: 41 54 push %r12 : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.17 : 4a0da2: 48 83 fa 17 cmp $0x17,%rdx : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 0.00 : 4a0da6: 49 89 fc mov %rdi,%r12 0.00 : 4a0da9: 55 push %rbp 3.37 : 4a0daa: 53 push %rbx : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.08 : 4a0dab: 76 73 jbe 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dad: 80 7c 16 eb 00 cmpb $0x0,-0x15(%rsi,%rdx,1) 3.48 : 4a0db2: 75 6c jne 4a0e20 <decode_tree_entry+0x80> : static const char *get_mode(const char *str, unsigned int *modep) : { : unsigned char c; : unsigned int mode = 0; : : if (*str == ' ') 1.94 : 4a0db4: 0f b6 06 movzbl (%rsi),%eax 0.39 : 4a0db7: 3c 20 cmp $0x20,%al 0.00 : 4a0db9: 74 65 je 4a0e20 <decode_tree_entry+0x80> : return NULL; : : while ((c = *str++) != ' ') { 0.06 : 4a0dbb: 89 c2 mov %eax,%edx : if (c < '0' || c > '7') 1.99 : 4a0dbd: 31 ed xor %ebp,%ebp : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 1.74 : 4a0dbf: 48 8d 5e 01 lea 0x1(%rsi),%rbx : if (c < '0' || c > '7') 0.00 : 4a0dc3: 8d 42 d0 lea -0x30(%rdx),%eax 0.17 : 4a0dc6: 3c 07 cmp $0x7,%al 0.00 : 4a0dc8: 76 0d jbe 4a0dd7 <decode_tree_entry+0x37> 0.00 : 4a0dca: eb 54 jmp 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dcc: 0f 1f 40 00 nopl 0x0(%rax) 16.57 : 4a0dd0: 8d 42 d0 lea -0x30(%rdx),%eax 0.14 : 4a0dd3: 3c 07 cmp $0x7,%al 0.00 : 4a0dd5: 77 49 ja 4a0e20 <decode_tree_entry+0x80> : return NULL; : mode = (mode << 3) + (c - '0'); 3.12 : 4a0dd7: 0f b6 c2 movzbl %dl,%eax : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 0.00 : 4a0dda: 0f b6 13 movzbl (%rbx),%edx 16.74 : 4a0ddd: 48 83 c3 01 add $0x1,%rbx : if (c < '0' || c > '7') : return NULL; : mode = (mode << 3) + (c - '0'); The first column is the percentage of samples that arrived on that particular line - relative to the total cost of the function. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-06 21:48:52 +08:00
}
return 0;
}
perf annotate: Print a sorted summary of annotated overhead lines It's can be very annoying to scroll down perf annotated output until we find relevant overhead. Using the -l option, you can now have a small summary sorted per overhead in the beginning of the output. Example: ./perf annotate -l -k ../../vmlinux -s __lock_acquire Sorted summary for file ../../vmlinux ---------------------------------------------- 12.04 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1653 4.61 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1740 3.77 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1775 3.56 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1653 2.93 /home/fweisbec/linux/linux-2.6-tip/arch/x86/include/asm/irqflags.h:15 2.83 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2545 2.30 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2594 2.20 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2388 2.20 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:730 2.09 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:730 2.09 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:138 1.88 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2548 1.47 /home/fweisbec/linux/linux-2.6-tip/arch/x86/include/asm/irqflags.h:15 1.36 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2594 1.36 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:730 1.26 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1654 1.26 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1653 1.15 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2592 1.15 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1740 1.15 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1740 [...] Only overhead over 0.5% are summarized. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1244844682-12928-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 06:11:22 +08:00
static struct rb_root root_sym_ext;
static void insert_source_line(struct sym_ext *sym_ext)
{
struct sym_ext *iter;
struct rb_node **p = &root_sym_ext.rb_node;
struct rb_node *parent = NULL;
while (*p != NULL) {
parent = *p;
iter = rb_entry(parent, struct sym_ext, node);
if (sym_ext->percent > iter->percent)
p = &(*p)->rb_left;
else
p = &(*p)->rb_right;
}
rb_link_node(&sym_ext->node, parent, p);
rb_insert_color(&sym_ext->node, &root_sym_ext);
}
static void free_source_line(struct hist_entry *he, int len)
{
struct sym_priv *priv = symbol__priv(he->ms.sym);
struct sym_ext *sym_ext = priv->ext;
int i;
if (!sym_ext)
return;
for (i = 0; i < len; i++)
free(sym_ext[i].path);
free(sym_ext);
priv->ext = NULL;
perf annotate: Print a sorted summary of annotated overhead lines It's can be very annoying to scroll down perf annotated output until we find relevant overhead. Using the -l option, you can now have a small summary sorted per overhead in the beginning of the output. Example: ./perf annotate -l -k ../../vmlinux -s __lock_acquire Sorted summary for file ../../vmlinux ---------------------------------------------- 12.04 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1653 4.61 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1740 3.77 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1775 3.56 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1653 2.93 /home/fweisbec/linux/linux-2.6-tip/arch/x86/include/asm/irqflags.h:15 2.83 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2545 2.30 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2594 2.20 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2388 2.20 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:730 2.09 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:730 2.09 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:138 1.88 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2548 1.47 /home/fweisbec/linux/linux-2.6-tip/arch/x86/include/asm/irqflags.h:15 1.36 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2594 1.36 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:730 1.26 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1654 1.26 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1653 1.15 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2592 1.15 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1740 1.15 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1740 [...] Only overhead over 0.5% are summarized. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1244844682-12928-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 06:11:22 +08:00
root_sym_ext = RB_ROOT;
}
/* Get the filename:line for the colored entries */
static void
get_source_line(struct hist_entry *he, int len, const char *filename)
{
struct symbol *sym = he->ms.sym;
u64 start;
int i;
char cmd[PATH_MAX * 2];
struct sym_ext *sym_ext;
struct sym_priv *priv = symbol__priv(sym);
struct sym_hist *h = priv->hist;
if (!h->sum)
return;
sym_ext = priv->ext = calloc(len, sizeof(struct sym_ext));
if (!priv->ext)
return;
start = he->ms.map->unmap_ip(he->ms.map, sym->start);
for (i = 0; i < len; i++) {
char *path = NULL;
size_t line_len;
u64 offset;
FILE *fp;
sym_ext[i].percent = 100.0 * h->ip[i] / h->sum;
if (sym_ext[i].percent <= 0.5)
continue;
offset = start + i;
sprintf(cmd, "addr2line -e %s %016" PRIx64, filename, offset);
fp = popen(cmd, "r");
if (!fp)
continue;
if (getline(&path, &line_len, fp) < 0 || !line_len)
goto next;
sym_ext[i].path = malloc(sizeof(char) * line_len + 1);
if (!sym_ext[i].path)
goto next;
strcpy(sym_ext[i].path, path);
perf annotate: Print a sorted summary of annotated overhead lines It's can be very annoying to scroll down perf annotated output until we find relevant overhead. Using the -l option, you can now have a small summary sorted per overhead in the beginning of the output. Example: ./perf annotate -l -k ../../vmlinux -s __lock_acquire Sorted summary for file ../../vmlinux ---------------------------------------------- 12.04 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1653 4.61 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1740 3.77 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1775 3.56 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1653 2.93 /home/fweisbec/linux/linux-2.6-tip/arch/x86/include/asm/irqflags.h:15 2.83 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2545 2.30 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2594 2.20 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2388 2.20 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:730 2.09 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:730 2.09 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:138 1.88 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2548 1.47 /home/fweisbec/linux/linux-2.6-tip/arch/x86/include/asm/irqflags.h:15 1.36 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2594 1.36 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:730 1.26 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1654 1.26 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1653 1.15 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2592 1.15 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1740 1.15 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1740 [...] Only overhead over 0.5% are summarized. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1244844682-12928-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 06:11:22 +08:00
insert_source_line(&sym_ext[i]);
next:
pclose(fp);
}
}
perf: Enable more compiler warnings Related to a shadowed variable bug fix Valdis Kletnieks noticed that perf does not get built with -Wshadow, which could have helped us avoid the bug. So enable -Wshadow and also enable the following warnings on perf builds, in addition to the already enabled -Wall -Wextra -std=gnu99 warnings: -Wcast-align -Wformat=2 -Wshadow -Winit-self -Wpacked -Wredundant-decls -Wstack-protector -Wstrict-aliasing=3 -Wswitch-default -Wswitch-enum -Wno-system-headers -Wundef -Wvolatile-register-var -Wwrite-strings -Wbad-function-cast -Wmissing-declarations -Wmissing-prototypes -Wnested-externs -Wold-style-definition -Wstrict-prototypes -Wdeclaration-after-statement And change/fix the perf code to build cleanly under GCC 4.3.2. The list of warnings enablement is rather arbitrary: it's based on my (quick) reading of the GCC manpages and trying them on perf. I categorized the warnings based on individually enabling them and looking whether they trigger something in the perf build. If i liked those warnings (i.e. if they trigger for something that arguably could be improved) i enabled the warning. If the warnings seemed to come from language laywers spamming the build with tons of nuisance warnings i generally kept them off. Most of the sign conversion related warnings were in this category. (A second patch enabling some of the sign warnings might be welcome - sign bugs can be nasty.) I also kept warnings that seem to make sense from their manpage description and which produced no actual warnings on our code base. These warnings might still be turned off if they end up being a nuisance. I also left out a few warnings that are not supported in older compilers. [ Note that these changes might break the build on older compilers i did not test, or on non-x86 architectures that produce different warnings, so more testing would be welcome. ] Reported-by: Valdis.Kletnieks@vt.edu Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-15 18:26:57 +08:00
static void print_summary(const char *filename)
perf annotate: Print a sorted summary of annotated overhead lines It's can be very annoying to scroll down perf annotated output until we find relevant overhead. Using the -l option, you can now have a small summary sorted per overhead in the beginning of the output. Example: ./perf annotate -l -k ../../vmlinux -s __lock_acquire Sorted summary for file ../../vmlinux ---------------------------------------------- 12.04 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1653 4.61 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1740 3.77 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1775 3.56 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1653 2.93 /home/fweisbec/linux/linux-2.6-tip/arch/x86/include/asm/irqflags.h:15 2.83 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2545 2.30 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2594 2.20 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2388 2.20 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:730 2.09 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:730 2.09 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:138 1.88 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2548 1.47 /home/fweisbec/linux/linux-2.6-tip/arch/x86/include/asm/irqflags.h:15 1.36 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2594 1.36 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:730 1.26 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1654 1.26 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1653 1.15 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2592 1.15 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1740 1.15 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1740 [...] Only overhead over 0.5% are summarized. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1244844682-12928-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 06:11:22 +08:00
{
struct sym_ext *sym_ext;
struct rb_node *node;
printf("\nSorted summary for file %s\n", filename);
printf("----------------------------------------------\n\n");
if (RB_EMPTY_ROOT(&root_sym_ext)) {
printf(" Nothing higher than %1.1f%%\n", MIN_GREEN);
return;
}
node = rb_first(&root_sym_ext);
while (node) {
double percent;
perf: Enable more compiler warnings Related to a shadowed variable bug fix Valdis Kletnieks noticed that perf does not get built with -Wshadow, which could have helped us avoid the bug. So enable -Wshadow and also enable the following warnings on perf builds, in addition to the already enabled -Wall -Wextra -std=gnu99 warnings: -Wcast-align -Wformat=2 -Wshadow -Winit-self -Wpacked -Wredundant-decls -Wstack-protector -Wstrict-aliasing=3 -Wswitch-default -Wswitch-enum -Wno-system-headers -Wundef -Wvolatile-register-var -Wwrite-strings -Wbad-function-cast -Wmissing-declarations -Wmissing-prototypes -Wnested-externs -Wold-style-definition -Wstrict-prototypes -Wdeclaration-after-statement And change/fix the perf code to build cleanly under GCC 4.3.2. The list of warnings enablement is rather arbitrary: it's based on my (quick) reading of the GCC manpages and trying them on perf. I categorized the warnings based on individually enabling them and looking whether they trigger something in the perf build. If i liked those warnings (i.e. if they trigger for something that arguably could be improved) i enabled the warning. If the warnings seemed to come from language laywers spamming the build with tons of nuisance warnings i generally kept them off. Most of the sign conversion related warnings were in this category. (A second patch enabling some of the sign warnings might be welcome - sign bugs can be nasty.) I also kept warnings that seem to make sense from their manpage description and which produced no actual warnings on our code base. These warnings might still be turned off if they end up being a nuisance. I also left out a few warnings that are not supported in older compilers. [ Note that these changes might break the build on older compilers i did not test, or on non-x86 architectures that produce different warnings, so more testing would be welcome. ] Reported-by: Valdis.Kletnieks@vt.edu Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-15 18:26:57 +08:00
const char *color;
perf annotate: Print a sorted summary of annotated overhead lines It's can be very annoying to scroll down perf annotated output until we find relevant overhead. Using the -l option, you can now have a small summary sorted per overhead in the beginning of the output. Example: ./perf annotate -l -k ../../vmlinux -s __lock_acquire Sorted summary for file ../../vmlinux ---------------------------------------------- 12.04 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1653 4.61 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1740 3.77 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1775 3.56 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1653 2.93 /home/fweisbec/linux/linux-2.6-tip/arch/x86/include/asm/irqflags.h:15 2.83 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2545 2.30 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2594 2.20 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2388 2.20 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:730 2.09 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:730 2.09 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:138 1.88 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2548 1.47 /home/fweisbec/linux/linux-2.6-tip/arch/x86/include/asm/irqflags.h:15 1.36 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2594 1.36 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:730 1.26 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1654 1.26 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1653 1.15 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2592 1.15 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1740 1.15 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1740 [...] Only overhead over 0.5% are summarized. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1244844682-12928-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 06:11:22 +08:00
char *path;
sym_ext = rb_entry(node, struct sym_ext, node);
percent = sym_ext->percent;
color = get_percent_color(percent);
perf annotate: Print a sorted summary of annotated overhead lines It's can be very annoying to scroll down perf annotated output until we find relevant overhead. Using the -l option, you can now have a small summary sorted per overhead in the beginning of the output. Example: ./perf annotate -l -k ../../vmlinux -s __lock_acquire Sorted summary for file ../../vmlinux ---------------------------------------------- 12.04 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1653 4.61 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1740 3.77 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1775 3.56 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1653 2.93 /home/fweisbec/linux/linux-2.6-tip/arch/x86/include/asm/irqflags.h:15 2.83 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2545 2.30 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2594 2.20 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2388 2.20 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:730 2.09 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:730 2.09 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:138 1.88 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2548 1.47 /home/fweisbec/linux/linux-2.6-tip/arch/x86/include/asm/irqflags.h:15 1.36 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2594 1.36 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:730 1.26 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1654 1.26 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1653 1.15 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2592 1.15 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1740 1.15 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1740 [...] Only overhead over 0.5% are summarized. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1244844682-12928-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 06:11:22 +08:00
path = sym_ext->path;
color_fprintf(stdout, color, " %7.2f %s", percent, path);
node = rb_next(node);
}
}
perf annotate: Handle samples not at objdump output addr boundaries Without this patch we get this for need_resched: [root@mica ~]# perf annotate need_resched ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ : : : Disassembly of section .text: : : ffffffff810095ed <need_resched>: : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095ed: 55 push %rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 0.00 : ffffffff810095ee: be 03 00 00 00 mov $0x3,%esi : : static inline struct thread_info *current_thread_info(void) : { : struct thread_info *ti; : ti = (void *)(percpu_read_stable(kernel_stack) + 0.00 : ffffffff810095f3: 65 48 8b 3c 25 48 b5 mov %gs:0xb548,%rdi 0.00 : ffffffff810095fa: 00 00 : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095fc: 48 89 e5 mov %rsp,%rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 0.00 : ffffffff810095ff: 48 81 ef d8 1f 00 00 sub $0x1fd8,%rdi 0.00 : ffffffff81009606: e8 9d ff ff ff callq ffffffff810095a8 <test_ti_thread_flag> : } 0.00 : ffffffff8100960b: c9 leaveq 0.00 : ffffffff8100960c: 85 c0 test %eax,%eax 0.00 : ffffffff8100960e: 0f 95 c0 setne %al 0.00 : ffffffff81009611: 0f b6 c0 movzbl %al,%eax : Disassembly of section .vsyscall_0: : Disassembly of section .vsyscall_fn: : Disassembly of section .vsyscall_1: : Disassembly of section .vsyscall_2: : Disassembly of section .init.text: : Disassembly of section .altinstr_replacement: : Disassembly of section .exit.text: [root@mica ~]# But from the 'perf report' result we know that there are hits for need_resched on a 4 way machine mostly doing nothing, so after adding code to show what is in each hist offset and collapsing IP hits for what happens between objdump lines we get, for the same perf.data file: [root@mica ~]# perf annotate -v need_resched ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ : : : Disassembly of section .text: : : ffffffff810095ed <need_resched>: : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095ed: 55 push %rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 52.78 : ffffffff810095ee: be 03 00 00 00 mov $0x3,%esi : : static inline struct thread_info *current_thread_info(void) : { : struct thread_info *ti; : ti = (void *)(percpu_read_stable(kernel_stack) + 0.00 : ffffffff810095f3: 65 48 8b 3c 25 48 b5 mov %gs:0xb548,%rdi 0.00 : ffffffff810095fa: 00 00 : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095fc: 48 89 e5 mov %rsp,%rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 9.72 : ffffffff810095ff: 48 81 ef d8 1f 00 00 sub $0x1fd8,%rdi 0.00 : ffffffff81009606: e8 9d ff ff ff callq ffffffff810095a8 <test_ti_thread_flag> : } 0.00 : ffffffff8100960b: c9 leaveq 0.00 : ffffffff8100960c: 85 c0 test %eax,%eax 37.50 : ffffffff8100960e: 0f 95 c0 setne %al 0.00 : ffffffff81009611: 0f b6 c0 movzbl %al,%eax : Disassembly of section .vsyscall_0: : Disassembly of section .vsyscall_fn: : Disassembly of section .vsyscall_1: : Disassembly of section .vsyscall_2: : Disassembly of section .init.text: : Disassembly of section .altinstr_replacement: : Disassembly of section .exit.text: [root@mica ~]# And now 'perf annotate -v', verbose mode, will show the hits per precise IP, so that one can make sense of the attribution to each objdumop line: [root@mica ~]# perf annotate -v need_resched Looking at the vmlinux_path (5 entries long) Using /lib/modules/2.6.33-rc8-tip-00784-g3471df5-dirty/build/vmlinux for symbols annotate_sym: filename=/lib/modules/2.6.33-rc8-tip-00784-g3471df5-dirty/build/vmlinux, sym=need_resched, start=0xffffffff810095ed, end=0xffffffff81009614 ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ ffffffff810095f1: 152 ffffffff81009603: 28 ffffffff8100960f: 55 ffffffff81009610: 53 h->sum: 288 <SNIP same annotation> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Miller <davem@davemloft.net> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1267194194-15670-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-26 22:23:14 +08:00
static void hist_entry__print_hits(struct hist_entry *self)
{
struct symbol *sym = self->ms.sym;
perf annotate: Handle samples not at objdump output addr boundaries Without this patch we get this for need_resched: [root@mica ~]# perf annotate need_resched ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ : : : Disassembly of section .text: : : ffffffff810095ed <need_resched>: : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095ed: 55 push %rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 0.00 : ffffffff810095ee: be 03 00 00 00 mov $0x3,%esi : : static inline struct thread_info *current_thread_info(void) : { : struct thread_info *ti; : ti = (void *)(percpu_read_stable(kernel_stack) + 0.00 : ffffffff810095f3: 65 48 8b 3c 25 48 b5 mov %gs:0xb548,%rdi 0.00 : ffffffff810095fa: 00 00 : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095fc: 48 89 e5 mov %rsp,%rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 0.00 : ffffffff810095ff: 48 81 ef d8 1f 00 00 sub $0x1fd8,%rdi 0.00 : ffffffff81009606: e8 9d ff ff ff callq ffffffff810095a8 <test_ti_thread_flag> : } 0.00 : ffffffff8100960b: c9 leaveq 0.00 : ffffffff8100960c: 85 c0 test %eax,%eax 0.00 : ffffffff8100960e: 0f 95 c0 setne %al 0.00 : ffffffff81009611: 0f b6 c0 movzbl %al,%eax : Disassembly of section .vsyscall_0: : Disassembly of section .vsyscall_fn: : Disassembly of section .vsyscall_1: : Disassembly of section .vsyscall_2: : Disassembly of section .init.text: : Disassembly of section .altinstr_replacement: : Disassembly of section .exit.text: [root@mica ~]# But from the 'perf report' result we know that there are hits for need_resched on a 4 way machine mostly doing nothing, so after adding code to show what is in each hist offset and collapsing IP hits for what happens between objdump lines we get, for the same perf.data file: [root@mica ~]# perf annotate -v need_resched ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ : : : Disassembly of section .text: : : ffffffff810095ed <need_resched>: : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095ed: 55 push %rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 52.78 : ffffffff810095ee: be 03 00 00 00 mov $0x3,%esi : : static inline struct thread_info *current_thread_info(void) : { : struct thread_info *ti; : ti = (void *)(percpu_read_stable(kernel_stack) + 0.00 : ffffffff810095f3: 65 48 8b 3c 25 48 b5 mov %gs:0xb548,%rdi 0.00 : ffffffff810095fa: 00 00 : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095fc: 48 89 e5 mov %rsp,%rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 9.72 : ffffffff810095ff: 48 81 ef d8 1f 00 00 sub $0x1fd8,%rdi 0.00 : ffffffff81009606: e8 9d ff ff ff callq ffffffff810095a8 <test_ti_thread_flag> : } 0.00 : ffffffff8100960b: c9 leaveq 0.00 : ffffffff8100960c: 85 c0 test %eax,%eax 37.50 : ffffffff8100960e: 0f 95 c0 setne %al 0.00 : ffffffff81009611: 0f b6 c0 movzbl %al,%eax : Disassembly of section .vsyscall_0: : Disassembly of section .vsyscall_fn: : Disassembly of section .vsyscall_1: : Disassembly of section .vsyscall_2: : Disassembly of section .init.text: : Disassembly of section .altinstr_replacement: : Disassembly of section .exit.text: [root@mica ~]# And now 'perf annotate -v', verbose mode, will show the hits per precise IP, so that one can make sense of the attribution to each objdumop line: [root@mica ~]# perf annotate -v need_resched Looking at the vmlinux_path (5 entries long) Using /lib/modules/2.6.33-rc8-tip-00784-g3471df5-dirty/build/vmlinux for symbols annotate_sym: filename=/lib/modules/2.6.33-rc8-tip-00784-g3471df5-dirty/build/vmlinux, sym=need_resched, start=0xffffffff810095ed, end=0xffffffff81009614 ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ ffffffff810095f1: 152 ffffffff81009603: 28 ffffffff8100960f: 55 ffffffff81009610: 53 h->sum: 288 <SNIP same annotation> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Miller <davem@davemloft.net> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1267194194-15670-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-26 22:23:14 +08:00
struct sym_priv *priv = symbol__priv(sym);
struct sym_hist *h = priv->hist;
u64 len = sym->end - sym->start, offset;
for (offset = 0; offset < len; ++offset)
if (h->ip[offset] != 0)
printf("%*" PRIx64 ": %" PRIu64 "\n", BITS_PER_LONG / 2,
perf annotate: Handle samples not at objdump output addr boundaries Without this patch we get this for need_resched: [root@mica ~]# perf annotate need_resched ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ : : : Disassembly of section .text: : : ffffffff810095ed <need_resched>: : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095ed: 55 push %rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 0.00 : ffffffff810095ee: be 03 00 00 00 mov $0x3,%esi : : static inline struct thread_info *current_thread_info(void) : { : struct thread_info *ti; : ti = (void *)(percpu_read_stable(kernel_stack) + 0.00 : ffffffff810095f3: 65 48 8b 3c 25 48 b5 mov %gs:0xb548,%rdi 0.00 : ffffffff810095fa: 00 00 : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095fc: 48 89 e5 mov %rsp,%rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 0.00 : ffffffff810095ff: 48 81 ef d8 1f 00 00 sub $0x1fd8,%rdi 0.00 : ffffffff81009606: e8 9d ff ff ff callq ffffffff810095a8 <test_ti_thread_flag> : } 0.00 : ffffffff8100960b: c9 leaveq 0.00 : ffffffff8100960c: 85 c0 test %eax,%eax 0.00 : ffffffff8100960e: 0f 95 c0 setne %al 0.00 : ffffffff81009611: 0f b6 c0 movzbl %al,%eax : Disassembly of section .vsyscall_0: : Disassembly of section .vsyscall_fn: : Disassembly of section .vsyscall_1: : Disassembly of section .vsyscall_2: : Disassembly of section .init.text: : Disassembly of section .altinstr_replacement: : Disassembly of section .exit.text: [root@mica ~]# But from the 'perf report' result we know that there are hits for need_resched on a 4 way machine mostly doing nothing, so after adding code to show what is in each hist offset and collapsing IP hits for what happens between objdump lines we get, for the same perf.data file: [root@mica ~]# perf annotate -v need_resched ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ : : : Disassembly of section .text: : : ffffffff810095ed <need_resched>: : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095ed: 55 push %rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 52.78 : ffffffff810095ee: be 03 00 00 00 mov $0x3,%esi : : static inline struct thread_info *current_thread_info(void) : { : struct thread_info *ti; : ti = (void *)(percpu_read_stable(kernel_stack) + 0.00 : ffffffff810095f3: 65 48 8b 3c 25 48 b5 mov %gs:0xb548,%rdi 0.00 : ffffffff810095fa: 00 00 : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095fc: 48 89 e5 mov %rsp,%rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 9.72 : ffffffff810095ff: 48 81 ef d8 1f 00 00 sub $0x1fd8,%rdi 0.00 : ffffffff81009606: e8 9d ff ff ff callq ffffffff810095a8 <test_ti_thread_flag> : } 0.00 : ffffffff8100960b: c9 leaveq 0.00 : ffffffff8100960c: 85 c0 test %eax,%eax 37.50 : ffffffff8100960e: 0f 95 c0 setne %al 0.00 : ffffffff81009611: 0f b6 c0 movzbl %al,%eax : Disassembly of section .vsyscall_0: : Disassembly of section .vsyscall_fn: : Disassembly of section .vsyscall_1: : Disassembly of section .vsyscall_2: : Disassembly of section .init.text: : Disassembly of section .altinstr_replacement: : Disassembly of section .exit.text: [root@mica ~]# And now 'perf annotate -v', verbose mode, will show the hits per precise IP, so that one can make sense of the attribution to each objdumop line: [root@mica ~]# perf annotate -v need_resched Looking at the vmlinux_path (5 entries long) Using /lib/modules/2.6.33-rc8-tip-00784-g3471df5-dirty/build/vmlinux for symbols annotate_sym: filename=/lib/modules/2.6.33-rc8-tip-00784-g3471df5-dirty/build/vmlinux, sym=need_resched, start=0xffffffff810095ed, end=0xffffffff81009614 ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ ffffffff810095f1: 152 ffffffff81009603: 28 ffffffff8100960f: 55 ffffffff81009610: 53 h->sum: 288 <SNIP same annotation> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Miller <davem@davemloft.net> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1267194194-15670-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-26 22:23:14 +08:00
sym->start + offset, h->ip[offset]);
printf("%*s: %" PRIu64 "\n", BITS_PER_LONG / 2, "h->sum", h->sum);
perf annotate: Handle samples not at objdump output addr boundaries Without this patch we get this for need_resched: [root@mica ~]# perf annotate need_resched ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ : : : Disassembly of section .text: : : ffffffff810095ed <need_resched>: : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095ed: 55 push %rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 0.00 : ffffffff810095ee: be 03 00 00 00 mov $0x3,%esi : : static inline struct thread_info *current_thread_info(void) : { : struct thread_info *ti; : ti = (void *)(percpu_read_stable(kernel_stack) + 0.00 : ffffffff810095f3: 65 48 8b 3c 25 48 b5 mov %gs:0xb548,%rdi 0.00 : ffffffff810095fa: 00 00 : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095fc: 48 89 e5 mov %rsp,%rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 0.00 : ffffffff810095ff: 48 81 ef d8 1f 00 00 sub $0x1fd8,%rdi 0.00 : ffffffff81009606: e8 9d ff ff ff callq ffffffff810095a8 <test_ti_thread_flag> : } 0.00 : ffffffff8100960b: c9 leaveq 0.00 : ffffffff8100960c: 85 c0 test %eax,%eax 0.00 : ffffffff8100960e: 0f 95 c0 setne %al 0.00 : ffffffff81009611: 0f b6 c0 movzbl %al,%eax : Disassembly of section .vsyscall_0: : Disassembly of section .vsyscall_fn: : Disassembly of section .vsyscall_1: : Disassembly of section .vsyscall_2: : Disassembly of section .init.text: : Disassembly of section .altinstr_replacement: : Disassembly of section .exit.text: [root@mica ~]# But from the 'perf report' result we know that there are hits for need_resched on a 4 way machine mostly doing nothing, so after adding code to show what is in each hist offset and collapsing IP hits for what happens between objdump lines we get, for the same perf.data file: [root@mica ~]# perf annotate -v need_resched ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ : : : Disassembly of section .text: : : ffffffff810095ed <need_resched>: : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095ed: 55 push %rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 52.78 : ffffffff810095ee: be 03 00 00 00 mov $0x3,%esi : : static inline struct thread_info *current_thread_info(void) : { : struct thread_info *ti; : ti = (void *)(percpu_read_stable(kernel_stack) + 0.00 : ffffffff810095f3: 65 48 8b 3c 25 48 b5 mov %gs:0xb548,%rdi 0.00 : ffffffff810095fa: 00 00 : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095fc: 48 89 e5 mov %rsp,%rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 9.72 : ffffffff810095ff: 48 81 ef d8 1f 00 00 sub $0x1fd8,%rdi 0.00 : ffffffff81009606: e8 9d ff ff ff callq ffffffff810095a8 <test_ti_thread_flag> : } 0.00 : ffffffff8100960b: c9 leaveq 0.00 : ffffffff8100960c: 85 c0 test %eax,%eax 37.50 : ffffffff8100960e: 0f 95 c0 setne %al 0.00 : ffffffff81009611: 0f b6 c0 movzbl %al,%eax : Disassembly of section .vsyscall_0: : Disassembly of section .vsyscall_fn: : Disassembly of section .vsyscall_1: : Disassembly of section .vsyscall_2: : Disassembly of section .init.text: : Disassembly of section .altinstr_replacement: : Disassembly of section .exit.text: [root@mica ~]# And now 'perf annotate -v', verbose mode, will show the hits per precise IP, so that one can make sense of the attribution to each objdumop line: [root@mica ~]# perf annotate -v need_resched Looking at the vmlinux_path (5 entries long) Using /lib/modules/2.6.33-rc8-tip-00784-g3471df5-dirty/build/vmlinux for symbols annotate_sym: filename=/lib/modules/2.6.33-rc8-tip-00784-g3471df5-dirty/build/vmlinux, sym=need_resched, start=0xffffffff810095ed, end=0xffffffff81009614 ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ ffffffff810095f1: 152 ffffffff81009603: 28 ffffffff8100960f: 55 ffffffff81009610: 53 h->sum: 288 <SNIP same annotation> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Miller <davem@davemloft.net> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1267194194-15670-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-26 22:23:14 +08:00
}
static int hist_entry__tty_annotate(struct hist_entry *he)
perf_counter tools: Add 'perf annotate' feature Add new perf sub-command to display annotated source code: $ perf annotate decode_tree_entry ------------------------------------------------ Percent | Source code & Disassembly of /home/mingo/git/git ------------------------------------------------ : : /home/mingo/git/git: file format elf64-x86-64 : : : Disassembly of section .text: : : 00000000004a0da0 <decode_tree_entry>: : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 3.82 : 4a0da0: 41 54 push %r12 : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.17 : 4a0da2: 48 83 fa 17 cmp $0x17,%rdx : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 0.00 : 4a0da6: 49 89 fc mov %rdi,%r12 0.00 : 4a0da9: 55 push %rbp 3.37 : 4a0daa: 53 push %rbx : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.08 : 4a0dab: 76 73 jbe 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dad: 80 7c 16 eb 00 cmpb $0x0,-0x15(%rsi,%rdx,1) 3.48 : 4a0db2: 75 6c jne 4a0e20 <decode_tree_entry+0x80> : static const char *get_mode(const char *str, unsigned int *modep) : { : unsigned char c; : unsigned int mode = 0; : : if (*str == ' ') 1.94 : 4a0db4: 0f b6 06 movzbl (%rsi),%eax 0.39 : 4a0db7: 3c 20 cmp $0x20,%al 0.00 : 4a0db9: 74 65 je 4a0e20 <decode_tree_entry+0x80> : return NULL; : : while ((c = *str++) != ' ') { 0.06 : 4a0dbb: 89 c2 mov %eax,%edx : if (c < '0' || c > '7') 1.99 : 4a0dbd: 31 ed xor %ebp,%ebp : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 1.74 : 4a0dbf: 48 8d 5e 01 lea 0x1(%rsi),%rbx : if (c < '0' || c > '7') 0.00 : 4a0dc3: 8d 42 d0 lea -0x30(%rdx),%eax 0.17 : 4a0dc6: 3c 07 cmp $0x7,%al 0.00 : 4a0dc8: 76 0d jbe 4a0dd7 <decode_tree_entry+0x37> 0.00 : 4a0dca: eb 54 jmp 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dcc: 0f 1f 40 00 nopl 0x0(%rax) 16.57 : 4a0dd0: 8d 42 d0 lea -0x30(%rdx),%eax 0.14 : 4a0dd3: 3c 07 cmp $0x7,%al 0.00 : 4a0dd5: 77 49 ja 4a0e20 <decode_tree_entry+0x80> : return NULL; : mode = (mode << 3) + (c - '0'); 3.12 : 4a0dd7: 0f b6 c2 movzbl %dl,%eax : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 0.00 : 4a0dda: 0f b6 13 movzbl (%rbx),%edx 16.74 : 4a0ddd: 48 83 c3 01 add $0x1,%rbx : if (c < '0' || c > '7') : return NULL; : mode = (mode << 3) + (c - '0'); The first column is the percentage of samples that arrived on that particular line - relative to the total cost of the function. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-06 21:48:52 +08:00
{
struct map *map = he->ms.map;
struct dso *dso = map->dso;
struct symbol *sym = he->ms.sym;
perf tools: Rewrite and improve support for kernel modules Representing modules as struct map entries, backed by a DSO, etc, using /proc/modules to find where the module is loaded. DSOs now can have a short and long name, so that in verbose mode we can show exactly which .ko or vmlinux image was used. As kernel modules now are a DSO separate from the kernel, we can ask for just the hits for a particular set of kernel modules, just like we can do with shared libraries: [root@doppio linux-2.6-tip]# perf report -n --vmlinux /home/acme/git/build/tip-recvmmsg/vmlinux --modules --dsos \[drm\] | head -15 84.58% 13266 Xorg [k] drm_clflush_pages 4.02% 630 Xorg [k] trace_kmalloc.clone.0 3.95% 619 Xorg [k] drm_ioctl 2.07% 324 Xorg [k] drm_addbufs 1.68% 263 Xorg [k] drm_gem_close_ioctl 0.77% 120 Xorg [k] drm_setmaster_ioctl 0.70% 110 Xorg [k] drm_lastclose 0.68% 106 Xorg [k] drm_open 0.54% 85 Xorg [k] drm_mm_search_free [root@doppio linux-2.6-tip]# Specifying --dsos /lib/modules/2.6.31-tip/kernel/drivers/gpu/drm/drm.ko would have the same effect. Allowing specifying just 'drm.ko' is left for another patch. Processing kallsyms so that per kernel module struct map are instantiated was also left for another patch. That will allow removing the module name from each of its symbols. struct symbol was reduced by removing the ->module backpointer and moving it (well now the map) to struct symbol_entry in perf top, that is its only user right now. The total linecount went down by ~500 lines. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Avi Kivity <avi@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-02 14:29:58 +08:00
const char *filename = dso->long_name, *d_filename;
u64 len;
perf annotate: Handle samples not at objdump output addr boundaries Without this patch we get this for need_resched: [root@mica ~]# perf annotate need_resched ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ : : : Disassembly of section .text: : : ffffffff810095ed <need_resched>: : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095ed: 55 push %rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 0.00 : ffffffff810095ee: be 03 00 00 00 mov $0x3,%esi : : static inline struct thread_info *current_thread_info(void) : { : struct thread_info *ti; : ti = (void *)(percpu_read_stable(kernel_stack) + 0.00 : ffffffff810095f3: 65 48 8b 3c 25 48 b5 mov %gs:0xb548,%rdi 0.00 : ffffffff810095fa: 00 00 : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095fc: 48 89 e5 mov %rsp,%rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 0.00 : ffffffff810095ff: 48 81 ef d8 1f 00 00 sub $0x1fd8,%rdi 0.00 : ffffffff81009606: e8 9d ff ff ff callq ffffffff810095a8 <test_ti_thread_flag> : } 0.00 : ffffffff8100960b: c9 leaveq 0.00 : ffffffff8100960c: 85 c0 test %eax,%eax 0.00 : ffffffff8100960e: 0f 95 c0 setne %al 0.00 : ffffffff81009611: 0f b6 c0 movzbl %al,%eax : Disassembly of section .vsyscall_0: : Disassembly of section .vsyscall_fn: : Disassembly of section .vsyscall_1: : Disassembly of section .vsyscall_2: : Disassembly of section .init.text: : Disassembly of section .altinstr_replacement: : Disassembly of section .exit.text: [root@mica ~]# But from the 'perf report' result we know that there are hits for need_resched on a 4 way machine mostly doing nothing, so after adding code to show what is in each hist offset and collapsing IP hits for what happens between objdump lines we get, for the same perf.data file: [root@mica ~]# perf annotate -v need_resched ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ : : : Disassembly of section .text: : : ffffffff810095ed <need_resched>: : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095ed: 55 push %rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 52.78 : ffffffff810095ee: be 03 00 00 00 mov $0x3,%esi : : static inline struct thread_info *current_thread_info(void) : { : struct thread_info *ti; : ti = (void *)(percpu_read_stable(kernel_stack) + 0.00 : ffffffff810095f3: 65 48 8b 3c 25 48 b5 mov %gs:0xb548,%rdi 0.00 : ffffffff810095fa: 00 00 : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095fc: 48 89 e5 mov %rsp,%rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 9.72 : ffffffff810095ff: 48 81 ef d8 1f 00 00 sub $0x1fd8,%rdi 0.00 : ffffffff81009606: e8 9d ff ff ff callq ffffffff810095a8 <test_ti_thread_flag> : } 0.00 : ffffffff8100960b: c9 leaveq 0.00 : ffffffff8100960c: 85 c0 test %eax,%eax 37.50 : ffffffff8100960e: 0f 95 c0 setne %al 0.00 : ffffffff81009611: 0f b6 c0 movzbl %al,%eax : Disassembly of section .vsyscall_0: : Disassembly of section .vsyscall_fn: : Disassembly of section .vsyscall_1: : Disassembly of section .vsyscall_2: : Disassembly of section .init.text: : Disassembly of section .altinstr_replacement: : Disassembly of section .exit.text: [root@mica ~]# And now 'perf annotate -v', verbose mode, will show the hits per precise IP, so that one can make sense of the attribution to each objdumop line: [root@mica ~]# perf annotate -v need_resched Looking at the vmlinux_path (5 entries long) Using /lib/modules/2.6.33-rc8-tip-00784-g3471df5-dirty/build/vmlinux for symbols annotate_sym: filename=/lib/modules/2.6.33-rc8-tip-00784-g3471df5-dirty/build/vmlinux, sym=need_resched, start=0xffffffff810095ed, end=0xffffffff81009614 ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ ffffffff810095f1: 152 ffffffff81009603: 28 ffffffff8100960f: 55 ffffffff81009610: 53 h->sum: 288 <SNIP same annotation> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Miller <davem@davemloft.net> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1267194194-15670-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-26 22:23:14 +08:00
LIST_HEAD(head);
struct objdump_line *pos, *n;
perf_counter tools: Add 'perf annotate' feature Add new perf sub-command to display annotated source code: $ perf annotate decode_tree_entry ------------------------------------------------ Percent | Source code & Disassembly of /home/mingo/git/git ------------------------------------------------ : : /home/mingo/git/git: file format elf64-x86-64 : : : Disassembly of section .text: : : 00000000004a0da0 <decode_tree_entry>: : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 3.82 : 4a0da0: 41 54 push %r12 : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.17 : 4a0da2: 48 83 fa 17 cmp $0x17,%rdx : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 0.00 : 4a0da6: 49 89 fc mov %rdi,%r12 0.00 : 4a0da9: 55 push %rbp 3.37 : 4a0daa: 53 push %rbx : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.08 : 4a0dab: 76 73 jbe 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dad: 80 7c 16 eb 00 cmpb $0x0,-0x15(%rsi,%rdx,1) 3.48 : 4a0db2: 75 6c jne 4a0e20 <decode_tree_entry+0x80> : static const char *get_mode(const char *str, unsigned int *modep) : { : unsigned char c; : unsigned int mode = 0; : : if (*str == ' ') 1.94 : 4a0db4: 0f b6 06 movzbl (%rsi),%eax 0.39 : 4a0db7: 3c 20 cmp $0x20,%al 0.00 : 4a0db9: 74 65 je 4a0e20 <decode_tree_entry+0x80> : return NULL; : : while ((c = *str++) != ' ') { 0.06 : 4a0dbb: 89 c2 mov %eax,%edx : if (c < '0' || c > '7') 1.99 : 4a0dbd: 31 ed xor %ebp,%ebp : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 1.74 : 4a0dbf: 48 8d 5e 01 lea 0x1(%rsi),%rbx : if (c < '0' || c > '7') 0.00 : 4a0dc3: 8d 42 d0 lea -0x30(%rdx),%eax 0.17 : 4a0dc6: 3c 07 cmp $0x7,%al 0.00 : 4a0dc8: 76 0d jbe 4a0dd7 <decode_tree_entry+0x37> 0.00 : 4a0dca: eb 54 jmp 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dcc: 0f 1f 40 00 nopl 0x0(%rax) 16.57 : 4a0dd0: 8d 42 d0 lea -0x30(%rdx),%eax 0.14 : 4a0dd3: 3c 07 cmp $0x7,%al 0.00 : 4a0dd5: 77 49 ja 4a0e20 <decode_tree_entry+0x80> : return NULL; : mode = (mode << 3) + (c - '0'); 3.12 : 4a0dd7: 0f b6 c2 movzbl %dl,%eax : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 0.00 : 4a0dda: 0f b6 13 movzbl (%rbx),%edx 16.74 : 4a0ddd: 48 83 c3 01 add $0x1,%rbx : if (c < '0' || c > '7') : return NULL; : mode = (mode << 3) + (c - '0'); The first column is the percentage of samples that arrived on that particular line - relative to the total cost of the function. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-06 21:48:52 +08:00
if (hist_entry__annotate(he, &head, 0) < 0)
return -1;
if (full_paths)
d_filename = filename;
else
d_filename = basename(filename);
perf_counter tools: Add 'perf annotate' feature Add new perf sub-command to display annotated source code: $ perf annotate decode_tree_entry ------------------------------------------------ Percent | Source code & Disassembly of /home/mingo/git/git ------------------------------------------------ : : /home/mingo/git/git: file format elf64-x86-64 : : : Disassembly of section .text: : : 00000000004a0da0 <decode_tree_entry>: : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 3.82 : 4a0da0: 41 54 push %r12 : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.17 : 4a0da2: 48 83 fa 17 cmp $0x17,%rdx : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 0.00 : 4a0da6: 49 89 fc mov %rdi,%r12 0.00 : 4a0da9: 55 push %rbp 3.37 : 4a0daa: 53 push %rbx : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.08 : 4a0dab: 76 73 jbe 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dad: 80 7c 16 eb 00 cmpb $0x0,-0x15(%rsi,%rdx,1) 3.48 : 4a0db2: 75 6c jne 4a0e20 <decode_tree_entry+0x80> : static const char *get_mode(const char *str, unsigned int *modep) : { : unsigned char c; : unsigned int mode = 0; : : if (*str == ' ') 1.94 : 4a0db4: 0f b6 06 movzbl (%rsi),%eax 0.39 : 4a0db7: 3c 20 cmp $0x20,%al 0.00 : 4a0db9: 74 65 je 4a0e20 <decode_tree_entry+0x80> : return NULL; : : while ((c = *str++) != ' ') { 0.06 : 4a0dbb: 89 c2 mov %eax,%edx : if (c < '0' || c > '7') 1.99 : 4a0dbd: 31 ed xor %ebp,%ebp : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 1.74 : 4a0dbf: 48 8d 5e 01 lea 0x1(%rsi),%rbx : if (c < '0' || c > '7') 0.00 : 4a0dc3: 8d 42 d0 lea -0x30(%rdx),%eax 0.17 : 4a0dc6: 3c 07 cmp $0x7,%al 0.00 : 4a0dc8: 76 0d jbe 4a0dd7 <decode_tree_entry+0x37> 0.00 : 4a0dca: eb 54 jmp 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dcc: 0f 1f 40 00 nopl 0x0(%rax) 16.57 : 4a0dd0: 8d 42 d0 lea -0x30(%rdx),%eax 0.14 : 4a0dd3: 3c 07 cmp $0x7,%al 0.00 : 4a0dd5: 77 49 ja 4a0e20 <decode_tree_entry+0x80> : return NULL; : mode = (mode << 3) + (c - '0'); 3.12 : 4a0dd7: 0f b6 c2 movzbl %dl,%eax : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 0.00 : 4a0dda: 0f b6 13 movzbl (%rbx),%edx 16.74 : 4a0ddd: 48 83 c3 01 add $0x1,%rbx : if (c < '0' || c > '7') : return NULL; : mode = (mode << 3) + (c - '0'); The first column is the percentage of samples that arrived on that particular line - relative to the total cost of the function. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-06 21:48:52 +08:00
len = sym->end - sym->start;
perf annotate: Print a sorted summary of annotated overhead lines It's can be very annoying to scroll down perf annotated output until we find relevant overhead. Using the -l option, you can now have a small summary sorted per overhead in the beginning of the output. Example: ./perf annotate -l -k ../../vmlinux -s __lock_acquire Sorted summary for file ../../vmlinux ---------------------------------------------- 12.04 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1653 4.61 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1740 3.77 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1775 3.56 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1653 2.93 /home/fweisbec/linux/linux-2.6-tip/arch/x86/include/asm/irqflags.h:15 2.83 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2545 2.30 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2594 2.20 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2388 2.20 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:730 2.09 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:730 2.09 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:138 1.88 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2548 1.47 /home/fweisbec/linux/linux-2.6-tip/arch/x86/include/asm/irqflags.h:15 1.36 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2594 1.36 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:730 1.26 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1654 1.26 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1653 1.15 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2592 1.15 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1740 1.15 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1740 [...] Only overhead over 0.5% are summarized. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1244844682-12928-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 06:11:22 +08:00
if (print_line) {
get_source_line(he, len, filename);
perf annotate: Print a sorted summary of annotated overhead lines It's can be very annoying to scroll down perf annotated output until we find relevant overhead. Using the -l option, you can now have a small summary sorted per overhead in the beginning of the output. Example: ./perf annotate -l -k ../../vmlinux -s __lock_acquire Sorted summary for file ../../vmlinux ---------------------------------------------- 12.04 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1653 4.61 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1740 3.77 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1775 3.56 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1653 2.93 /home/fweisbec/linux/linux-2.6-tip/arch/x86/include/asm/irqflags.h:15 2.83 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2545 2.30 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2594 2.20 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2388 2.20 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:730 2.09 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:730 2.09 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:138 1.88 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2548 1.47 /home/fweisbec/linux/linux-2.6-tip/arch/x86/include/asm/irqflags.h:15 1.36 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2594 1.36 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:730 1.26 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1654 1.26 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1653 1.15 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2592 1.15 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1740 1.15 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1740 [...] Only overhead over 0.5% are summarized. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1244844682-12928-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 06:11:22 +08:00
print_summary(filename);
}
printf("\n\n------------------------------------------------\n");
printf(" Percent | Source code & Disassembly of %s\n", d_filename);
perf annotate: Print a sorted summary of annotated overhead lines It's can be very annoying to scroll down perf annotated output until we find relevant overhead. Using the -l option, you can now have a small summary sorted per overhead in the beginning of the output. Example: ./perf annotate -l -k ../../vmlinux -s __lock_acquire Sorted summary for file ../../vmlinux ---------------------------------------------- 12.04 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1653 4.61 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1740 3.77 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1775 3.56 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1653 2.93 /home/fweisbec/linux/linux-2.6-tip/arch/x86/include/asm/irqflags.h:15 2.83 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2545 2.30 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2594 2.20 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2388 2.20 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:730 2.09 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:730 2.09 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:138 1.88 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2548 1.47 /home/fweisbec/linux/linux-2.6-tip/arch/x86/include/asm/irqflags.h:15 1.36 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2594 1.36 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:730 1.26 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1654 1.26 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1653 1.15 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2592 1.15 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1740 1.15 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1740 [...] Only overhead over 0.5% are summarized. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1244844682-12928-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 06:11:22 +08:00
printf("------------------------------------------------\n");
perf annotate: Handle samples not at objdump output addr boundaries Without this patch we get this for need_resched: [root@mica ~]# perf annotate need_resched ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ : : : Disassembly of section .text: : : ffffffff810095ed <need_resched>: : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095ed: 55 push %rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 0.00 : ffffffff810095ee: be 03 00 00 00 mov $0x3,%esi : : static inline struct thread_info *current_thread_info(void) : { : struct thread_info *ti; : ti = (void *)(percpu_read_stable(kernel_stack) + 0.00 : ffffffff810095f3: 65 48 8b 3c 25 48 b5 mov %gs:0xb548,%rdi 0.00 : ffffffff810095fa: 00 00 : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095fc: 48 89 e5 mov %rsp,%rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 0.00 : ffffffff810095ff: 48 81 ef d8 1f 00 00 sub $0x1fd8,%rdi 0.00 : ffffffff81009606: e8 9d ff ff ff callq ffffffff810095a8 <test_ti_thread_flag> : } 0.00 : ffffffff8100960b: c9 leaveq 0.00 : ffffffff8100960c: 85 c0 test %eax,%eax 0.00 : ffffffff8100960e: 0f 95 c0 setne %al 0.00 : ffffffff81009611: 0f b6 c0 movzbl %al,%eax : Disassembly of section .vsyscall_0: : Disassembly of section .vsyscall_fn: : Disassembly of section .vsyscall_1: : Disassembly of section .vsyscall_2: : Disassembly of section .init.text: : Disassembly of section .altinstr_replacement: : Disassembly of section .exit.text: [root@mica ~]# But from the 'perf report' result we know that there are hits for need_resched on a 4 way machine mostly doing nothing, so after adding code to show what is in each hist offset and collapsing IP hits for what happens between objdump lines we get, for the same perf.data file: [root@mica ~]# perf annotate -v need_resched ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ : : : Disassembly of section .text: : : ffffffff810095ed <need_resched>: : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095ed: 55 push %rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 52.78 : ffffffff810095ee: be 03 00 00 00 mov $0x3,%esi : : static inline struct thread_info *current_thread_info(void) : { : struct thread_info *ti; : ti = (void *)(percpu_read_stable(kernel_stack) + 0.00 : ffffffff810095f3: 65 48 8b 3c 25 48 b5 mov %gs:0xb548,%rdi 0.00 : ffffffff810095fa: 00 00 : return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); : } : : static inline int need_resched(void) : { 0.00 : ffffffff810095fc: 48 89 e5 mov %rsp,%rbp : return unlikely(test_thread_flag(TIF_NEED_RESCHED)); 9.72 : ffffffff810095ff: 48 81 ef d8 1f 00 00 sub $0x1fd8,%rdi 0.00 : ffffffff81009606: e8 9d ff ff ff callq ffffffff810095a8 <test_ti_thread_flag> : } 0.00 : ffffffff8100960b: c9 leaveq 0.00 : ffffffff8100960c: 85 c0 test %eax,%eax 37.50 : ffffffff8100960e: 0f 95 c0 setne %al 0.00 : ffffffff81009611: 0f b6 c0 movzbl %al,%eax : Disassembly of section .vsyscall_0: : Disassembly of section .vsyscall_fn: : Disassembly of section .vsyscall_1: : Disassembly of section .vsyscall_2: : Disassembly of section .init.text: : Disassembly of section .altinstr_replacement: : Disassembly of section .exit.text: [root@mica ~]# And now 'perf annotate -v', verbose mode, will show the hits per precise IP, so that one can make sense of the attribution to each objdumop line: [root@mica ~]# perf annotate -v need_resched Looking at the vmlinux_path (5 entries long) Using /lib/modules/2.6.33-rc8-tip-00784-g3471df5-dirty/build/vmlinux for symbols annotate_sym: filename=/lib/modules/2.6.33-rc8-tip-00784-g3471df5-dirty/build/vmlinux, sym=need_resched, start=0xffffffff810095ed, end=0xffffffff81009614 ------------------------------------------------ Percent | Source code & Disassembly of vmlinux ------------------------------------------------ ffffffff810095f1: 152 ffffffff81009603: 28 ffffffff8100960f: 55 ffffffff81009610: 53 h->sum: 288 <SNIP same annotation> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Miller <davem@davemloft.net> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1267194194-15670-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-26 22:23:14 +08:00
if (verbose)
hist_entry__print_hits(he);
list_for_each_entry_safe(pos, n, &head, node) {
objdump_line__print(pos, &head, he, len);
list_del(&pos->node);
objdump_line__free(pos);
}
perf annotate: Print a sorted summary of annotated overhead lines It's can be very annoying to scroll down perf annotated output until we find relevant overhead. Using the -l option, you can now have a small summary sorted per overhead in the beginning of the output. Example: ./perf annotate -l -k ../../vmlinux -s __lock_acquire Sorted summary for file ../../vmlinux ---------------------------------------------- 12.04 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1653 4.61 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1740 3.77 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1775 3.56 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1653 2.93 /home/fweisbec/linux/linux-2.6-tip/arch/x86/include/asm/irqflags.h:15 2.83 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2545 2.30 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2594 2.20 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2388 2.20 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:730 2.09 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:730 2.09 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:138 1.88 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2548 1.47 /home/fweisbec/linux/linux-2.6-tip/arch/x86/include/asm/irqflags.h:15 1.36 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2594 1.36 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:730 1.26 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1654 1.26 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1653 1.15 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:2592 1.15 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1740 1.15 /home/fweisbec/linux/linux-2.6-tip/kernel/lockdep.c:1740 [...] Only overhead over 0.5% are summarized. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1244844682-12928-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 06:11:22 +08:00
if (print_line)
free_source_line(he, len);
return 0;
perf_counter tools: Add 'perf annotate' feature Add new perf sub-command to display annotated source code: $ perf annotate decode_tree_entry ------------------------------------------------ Percent | Source code & Disassembly of /home/mingo/git/git ------------------------------------------------ : : /home/mingo/git/git: file format elf64-x86-64 : : : Disassembly of section .text: : : 00000000004a0da0 <decode_tree_entry>: : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 3.82 : 4a0da0: 41 54 push %r12 : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.17 : 4a0da2: 48 83 fa 17 cmp $0x17,%rdx : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 0.00 : 4a0da6: 49 89 fc mov %rdi,%r12 0.00 : 4a0da9: 55 push %rbp 3.37 : 4a0daa: 53 push %rbx : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.08 : 4a0dab: 76 73 jbe 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dad: 80 7c 16 eb 00 cmpb $0x0,-0x15(%rsi,%rdx,1) 3.48 : 4a0db2: 75 6c jne 4a0e20 <decode_tree_entry+0x80> : static const char *get_mode(const char *str, unsigned int *modep) : { : unsigned char c; : unsigned int mode = 0; : : if (*str == ' ') 1.94 : 4a0db4: 0f b6 06 movzbl (%rsi),%eax 0.39 : 4a0db7: 3c 20 cmp $0x20,%al 0.00 : 4a0db9: 74 65 je 4a0e20 <decode_tree_entry+0x80> : return NULL; : : while ((c = *str++) != ' ') { 0.06 : 4a0dbb: 89 c2 mov %eax,%edx : if (c < '0' || c > '7') 1.99 : 4a0dbd: 31 ed xor %ebp,%ebp : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 1.74 : 4a0dbf: 48 8d 5e 01 lea 0x1(%rsi),%rbx : if (c < '0' || c > '7') 0.00 : 4a0dc3: 8d 42 d0 lea -0x30(%rdx),%eax 0.17 : 4a0dc6: 3c 07 cmp $0x7,%al 0.00 : 4a0dc8: 76 0d jbe 4a0dd7 <decode_tree_entry+0x37> 0.00 : 4a0dca: eb 54 jmp 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dcc: 0f 1f 40 00 nopl 0x0(%rax) 16.57 : 4a0dd0: 8d 42 d0 lea -0x30(%rdx),%eax 0.14 : 4a0dd3: 3c 07 cmp $0x7,%al 0.00 : 4a0dd5: 77 49 ja 4a0e20 <decode_tree_entry+0x80> : return NULL; : mode = (mode << 3) + (c - '0'); 3.12 : 4a0dd7: 0f b6 c2 movzbl %dl,%eax : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 0.00 : 4a0dda: 0f b6 13 movzbl (%rbx),%edx 16.74 : 4a0ddd: 48 83 c3 01 add $0x1,%rbx : if (c < '0' || c > '7') : return NULL; : mode = (mode << 3) + (c - '0'); The first column is the percentage of samples that arrived on that particular line - relative to the total cost of the function. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-06 21:48:52 +08:00
}
2010-05-11 00:04:11 +08:00
static void hists__find_annotations(struct hists *self)
perf_counter tools: Add 'perf annotate' feature Add new perf sub-command to display annotated source code: $ perf annotate decode_tree_entry ------------------------------------------------ Percent | Source code & Disassembly of /home/mingo/git/git ------------------------------------------------ : : /home/mingo/git/git: file format elf64-x86-64 : : : Disassembly of section .text: : : 00000000004a0da0 <decode_tree_entry>: : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 3.82 : 4a0da0: 41 54 push %r12 : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.17 : 4a0da2: 48 83 fa 17 cmp $0x17,%rdx : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 0.00 : 4a0da6: 49 89 fc mov %rdi,%r12 0.00 : 4a0da9: 55 push %rbp 3.37 : 4a0daa: 53 push %rbx : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.08 : 4a0dab: 76 73 jbe 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dad: 80 7c 16 eb 00 cmpb $0x0,-0x15(%rsi,%rdx,1) 3.48 : 4a0db2: 75 6c jne 4a0e20 <decode_tree_entry+0x80> : static const char *get_mode(const char *str, unsigned int *modep) : { : unsigned char c; : unsigned int mode = 0; : : if (*str == ' ') 1.94 : 4a0db4: 0f b6 06 movzbl (%rsi),%eax 0.39 : 4a0db7: 3c 20 cmp $0x20,%al 0.00 : 4a0db9: 74 65 je 4a0e20 <decode_tree_entry+0x80> : return NULL; : : while ((c = *str++) != ' ') { 0.06 : 4a0dbb: 89 c2 mov %eax,%edx : if (c < '0' || c > '7') 1.99 : 4a0dbd: 31 ed xor %ebp,%ebp : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 1.74 : 4a0dbf: 48 8d 5e 01 lea 0x1(%rsi),%rbx : if (c < '0' || c > '7') 0.00 : 4a0dc3: 8d 42 d0 lea -0x30(%rdx),%eax 0.17 : 4a0dc6: 3c 07 cmp $0x7,%al 0.00 : 4a0dc8: 76 0d jbe 4a0dd7 <decode_tree_entry+0x37> 0.00 : 4a0dca: eb 54 jmp 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dcc: 0f 1f 40 00 nopl 0x0(%rax) 16.57 : 4a0dd0: 8d 42 d0 lea -0x30(%rdx),%eax 0.14 : 4a0dd3: 3c 07 cmp $0x7,%al 0.00 : 4a0dd5: 77 49 ja 4a0e20 <decode_tree_entry+0x80> : return NULL; : mode = (mode << 3) + (c - '0'); 3.12 : 4a0dd7: 0f b6 c2 movzbl %dl,%eax : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 0.00 : 4a0dda: 0f b6 13 movzbl (%rbx),%edx 16.74 : 4a0ddd: 48 83 c3 01 add $0x1,%rbx : if (c < '0' || c > '7') : return NULL; : mode = (mode << 3) + (c - '0'); The first column is the percentage of samples that arrived on that particular line - relative to the total cost of the function. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-06 21:48:52 +08:00
{
struct rb_node *nd = rb_first(&self->entries), *next;
int key = KEY_RIGHT;
perf_counter tools: Add 'perf annotate' feature Add new perf sub-command to display annotated source code: $ perf annotate decode_tree_entry ------------------------------------------------ Percent | Source code & Disassembly of /home/mingo/git/git ------------------------------------------------ : : /home/mingo/git/git: file format elf64-x86-64 : : : Disassembly of section .text: : : 00000000004a0da0 <decode_tree_entry>: : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 3.82 : 4a0da0: 41 54 push %r12 : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.17 : 4a0da2: 48 83 fa 17 cmp $0x17,%rdx : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 0.00 : 4a0da6: 49 89 fc mov %rdi,%r12 0.00 : 4a0da9: 55 push %rbp 3.37 : 4a0daa: 53 push %rbx : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.08 : 4a0dab: 76 73 jbe 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dad: 80 7c 16 eb 00 cmpb $0x0,-0x15(%rsi,%rdx,1) 3.48 : 4a0db2: 75 6c jne 4a0e20 <decode_tree_entry+0x80> : static const char *get_mode(const char *str, unsigned int *modep) : { : unsigned char c; : unsigned int mode = 0; : : if (*str == ' ') 1.94 : 4a0db4: 0f b6 06 movzbl (%rsi),%eax 0.39 : 4a0db7: 3c 20 cmp $0x20,%al 0.00 : 4a0db9: 74 65 je 4a0e20 <decode_tree_entry+0x80> : return NULL; : : while ((c = *str++) != ' ') { 0.06 : 4a0dbb: 89 c2 mov %eax,%edx : if (c < '0' || c > '7') 1.99 : 4a0dbd: 31 ed xor %ebp,%ebp : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 1.74 : 4a0dbf: 48 8d 5e 01 lea 0x1(%rsi),%rbx : if (c < '0' || c > '7') 0.00 : 4a0dc3: 8d 42 d0 lea -0x30(%rdx),%eax 0.17 : 4a0dc6: 3c 07 cmp $0x7,%al 0.00 : 4a0dc8: 76 0d jbe 4a0dd7 <decode_tree_entry+0x37> 0.00 : 4a0dca: eb 54 jmp 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dcc: 0f 1f 40 00 nopl 0x0(%rax) 16.57 : 4a0dd0: 8d 42 d0 lea -0x30(%rdx),%eax 0.14 : 4a0dd3: 3c 07 cmp $0x7,%al 0.00 : 4a0dd5: 77 49 ja 4a0e20 <decode_tree_entry+0x80> : return NULL; : mode = (mode << 3) + (c - '0'); 3.12 : 4a0dd7: 0f b6 c2 movzbl %dl,%eax : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 0.00 : 4a0dda: 0f b6 13 movzbl (%rbx),%edx 16.74 : 4a0ddd: 48 83 c3 01 add $0x1,%rbx : if (c < '0' || c > '7') : return NULL; : mode = (mode << 3) + (c - '0'); The first column is the percentage of samples that arrived on that particular line - relative to the total cost of the function. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-06 21:48:52 +08:00
while (nd) {
struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
struct sym_priv *priv;
perf_counter tools: Add 'perf annotate' feature Add new perf sub-command to display annotated source code: $ perf annotate decode_tree_entry ------------------------------------------------ Percent | Source code & Disassembly of /home/mingo/git/git ------------------------------------------------ : : /home/mingo/git/git: file format elf64-x86-64 : : : Disassembly of section .text: : : 00000000004a0da0 <decode_tree_entry>: : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 3.82 : 4a0da0: 41 54 push %r12 : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.17 : 4a0da2: 48 83 fa 17 cmp $0x17,%rdx : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 0.00 : 4a0da6: 49 89 fc mov %rdi,%r12 0.00 : 4a0da9: 55 push %rbp 3.37 : 4a0daa: 53 push %rbx : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.08 : 4a0dab: 76 73 jbe 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dad: 80 7c 16 eb 00 cmpb $0x0,-0x15(%rsi,%rdx,1) 3.48 : 4a0db2: 75 6c jne 4a0e20 <decode_tree_entry+0x80> : static const char *get_mode(const char *str, unsigned int *modep) : { : unsigned char c; : unsigned int mode = 0; : : if (*str == ' ') 1.94 : 4a0db4: 0f b6 06 movzbl (%rsi),%eax 0.39 : 4a0db7: 3c 20 cmp $0x20,%al 0.00 : 4a0db9: 74 65 je 4a0e20 <decode_tree_entry+0x80> : return NULL; : : while ((c = *str++) != ' ') { 0.06 : 4a0dbb: 89 c2 mov %eax,%edx : if (c < '0' || c > '7') 1.99 : 4a0dbd: 31 ed xor %ebp,%ebp : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 1.74 : 4a0dbf: 48 8d 5e 01 lea 0x1(%rsi),%rbx : if (c < '0' || c > '7') 0.00 : 4a0dc3: 8d 42 d0 lea -0x30(%rdx),%eax 0.17 : 4a0dc6: 3c 07 cmp $0x7,%al 0.00 : 4a0dc8: 76 0d jbe 4a0dd7 <decode_tree_entry+0x37> 0.00 : 4a0dca: eb 54 jmp 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dcc: 0f 1f 40 00 nopl 0x0(%rax) 16.57 : 4a0dd0: 8d 42 d0 lea -0x30(%rdx),%eax 0.14 : 4a0dd3: 3c 07 cmp $0x7,%al 0.00 : 4a0dd5: 77 49 ja 4a0e20 <decode_tree_entry+0x80> : return NULL; : mode = (mode << 3) + (c - '0'); 3.12 : 4a0dd7: 0f b6 c2 movzbl %dl,%eax : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 0.00 : 4a0dda: 0f b6 13 movzbl (%rbx),%edx 16.74 : 4a0ddd: 48 83 c3 01 add $0x1,%rbx : if (c < '0' || c > '7') : return NULL; : mode = (mode << 3) + (c - '0'); The first column is the percentage of samples that arrived on that particular line - relative to the total cost of the function. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-06 21:48:52 +08:00
if (he->ms.sym == NULL || he->ms.map->dso->annotate_warned)
goto find_next;
perf_counter tools: Add 'perf annotate' feature Add new perf sub-command to display annotated source code: $ perf annotate decode_tree_entry ------------------------------------------------ Percent | Source code & Disassembly of /home/mingo/git/git ------------------------------------------------ : : /home/mingo/git/git: file format elf64-x86-64 : : : Disassembly of section .text: : : 00000000004a0da0 <decode_tree_entry>: : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 3.82 : 4a0da0: 41 54 push %r12 : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.17 : 4a0da2: 48 83 fa 17 cmp $0x17,%rdx : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 0.00 : 4a0da6: 49 89 fc mov %rdi,%r12 0.00 : 4a0da9: 55 push %rbp 3.37 : 4a0daa: 53 push %rbx : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.08 : 4a0dab: 76 73 jbe 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dad: 80 7c 16 eb 00 cmpb $0x0,-0x15(%rsi,%rdx,1) 3.48 : 4a0db2: 75 6c jne 4a0e20 <decode_tree_entry+0x80> : static const char *get_mode(const char *str, unsigned int *modep) : { : unsigned char c; : unsigned int mode = 0; : : if (*str == ' ') 1.94 : 4a0db4: 0f b6 06 movzbl (%rsi),%eax 0.39 : 4a0db7: 3c 20 cmp $0x20,%al 0.00 : 4a0db9: 74 65 je 4a0e20 <decode_tree_entry+0x80> : return NULL; : : while ((c = *str++) != ' ') { 0.06 : 4a0dbb: 89 c2 mov %eax,%edx : if (c < '0' || c > '7') 1.99 : 4a0dbd: 31 ed xor %ebp,%ebp : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 1.74 : 4a0dbf: 48 8d 5e 01 lea 0x1(%rsi),%rbx : if (c < '0' || c > '7') 0.00 : 4a0dc3: 8d 42 d0 lea -0x30(%rdx),%eax 0.17 : 4a0dc6: 3c 07 cmp $0x7,%al 0.00 : 4a0dc8: 76 0d jbe 4a0dd7 <decode_tree_entry+0x37> 0.00 : 4a0dca: eb 54 jmp 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dcc: 0f 1f 40 00 nopl 0x0(%rax) 16.57 : 4a0dd0: 8d 42 d0 lea -0x30(%rdx),%eax 0.14 : 4a0dd3: 3c 07 cmp $0x7,%al 0.00 : 4a0dd5: 77 49 ja 4a0e20 <decode_tree_entry+0x80> : return NULL; : mode = (mode << 3) + (c - '0'); 3.12 : 4a0dd7: 0f b6 c2 movzbl %dl,%eax : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 0.00 : 4a0dda: 0f b6 13 movzbl (%rbx),%edx 16.74 : 4a0ddd: 48 83 c3 01 add $0x1,%rbx : if (c < '0' || c > '7') : return NULL; : mode = (mode << 3) + (c - '0'); The first column is the percentage of samples that arrived on that particular line - relative to the total cost of the function. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-06 21:48:52 +08:00
priv = symbol__priv(he->ms.sym);
if (priv->hist == NULL) {
find_next:
if (key == KEY_LEFT)
nd = rb_prev(nd);
else
nd = rb_next(nd);
continue;
}
if (use_browser > 0) {
key = hist_entry__tui_annotate(he);
switch (key) {
case KEY_RIGHT:
next = rb_next(nd);
break;
case KEY_LEFT:
next = rb_prev(nd);
break;
default:
return;
}
if (next != NULL)
nd = next;
} else {
hist_entry__tty_annotate(he);
nd = rb_next(nd);
/*
* Since we have a hist_entry per IP for the same
* symbol, free he->ms.sym->hist to signal we already
* processed this symbol.
*/
free(priv->hist);
priv->hist = NULL;
}
perf_counter tools: Add 'perf annotate' feature Add new perf sub-command to display annotated source code: $ perf annotate decode_tree_entry ------------------------------------------------ Percent | Source code & Disassembly of /home/mingo/git/git ------------------------------------------------ : : /home/mingo/git/git: file format elf64-x86-64 : : : Disassembly of section .text: : : 00000000004a0da0 <decode_tree_entry>: : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 3.82 : 4a0da0: 41 54 push %r12 : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.17 : 4a0da2: 48 83 fa 17 cmp $0x17,%rdx : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 0.00 : 4a0da6: 49 89 fc mov %rdi,%r12 0.00 : 4a0da9: 55 push %rbp 3.37 : 4a0daa: 53 push %rbx : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.08 : 4a0dab: 76 73 jbe 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dad: 80 7c 16 eb 00 cmpb $0x0,-0x15(%rsi,%rdx,1) 3.48 : 4a0db2: 75 6c jne 4a0e20 <decode_tree_entry+0x80> : static const char *get_mode(const char *str, unsigned int *modep) : { : unsigned char c; : unsigned int mode = 0; : : if (*str == ' ') 1.94 : 4a0db4: 0f b6 06 movzbl (%rsi),%eax 0.39 : 4a0db7: 3c 20 cmp $0x20,%al 0.00 : 4a0db9: 74 65 je 4a0e20 <decode_tree_entry+0x80> : return NULL; : : while ((c = *str++) != ' ') { 0.06 : 4a0dbb: 89 c2 mov %eax,%edx : if (c < '0' || c > '7') 1.99 : 4a0dbd: 31 ed xor %ebp,%ebp : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 1.74 : 4a0dbf: 48 8d 5e 01 lea 0x1(%rsi),%rbx : if (c < '0' || c > '7') 0.00 : 4a0dc3: 8d 42 d0 lea -0x30(%rdx),%eax 0.17 : 4a0dc6: 3c 07 cmp $0x7,%al 0.00 : 4a0dc8: 76 0d jbe 4a0dd7 <decode_tree_entry+0x37> 0.00 : 4a0dca: eb 54 jmp 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dcc: 0f 1f 40 00 nopl 0x0(%rax) 16.57 : 4a0dd0: 8d 42 d0 lea -0x30(%rdx),%eax 0.14 : 4a0dd3: 3c 07 cmp $0x7,%al 0.00 : 4a0dd5: 77 49 ja 4a0e20 <decode_tree_entry+0x80> : return NULL; : mode = (mode << 3) + (c - '0'); 3.12 : 4a0dd7: 0f b6 c2 movzbl %dl,%eax : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 0.00 : 4a0dda: 0f b6 13 movzbl (%rbx),%edx 16.74 : 4a0ddd: 48 83 c3 01 add $0x1,%rbx : if (c < '0' || c > '7') : return NULL; : mode = (mode << 3) + (c - '0'); The first column is the percentage of samples that arrived on that particular line - relative to the total cost of the function. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-06 21:48:52 +08:00
}
}
static struct perf_event_ops event_ops = {
.sample = process_sample_event,
.mmap = event__process_mmap,
.comm = event__process_comm,
.fork = event__process_task,
perf record,report,annotate,diff: Process events in order This patch changes perf report to ask for the ID info on all events be default if recording from multiple CPUs. Perf report, annotate and diff will now process the events in order if the kernel is able to provide timestamps on all events. This ensures that events such as COMM and MMAP which are necessary to correctly interpret samples are processed prior to those samples so that they are attributed correctly. Before: # perf record ./cachetest # perf report # Events: 6K cycles # # Overhead Command Shared Object Symbol # ........ ....... ................. ............................... # 74.11% :3259 [unknown] [k] 0x4a6c 1.50% cachetest ld-2.11.2.so [.] 0x1777c 1.46% :3259 [kernel.kallsyms] [k] .perf_event_mmap_ctx 1.25% :3259 [kernel.kallsyms] [k] restore 0.74% :3259 [kernel.kallsyms] [k] ._raw_spin_lock 0.71% :3259 [kernel.kallsyms] [k] .filemap_fault 0.66% :3259 [kernel.kallsyms] [k] .memset 0.54% cachetest [kernel.kallsyms] [k] .sha_transform 0.54% :3259 [kernel.kallsyms] [k] .copy_4K_page 0.54% :3259 [kernel.kallsyms] [k] .find_get_page 0.52% :3259 [kernel.kallsyms] [k] .trace_hardirqs_off 0.50% :3259 [kernel.kallsyms] [k] .__do_fault <SNIP> After: # perf report # Events: 6K cycles # # Overhead Command Shared Object Symbol # ........ ....... ................. ............................... # 44.28% cachetest cachetest [.] sumArrayNaive 22.53% cachetest cachetest [.] sumArrayOptimal 6.59% cachetest ld-2.11.2.so [.] 0x1777c 2.13% cachetest [unknown] [k] 0x340 1.46% cachetest [kernel.kallsyms] [k] .perf_event_mmap_ctx 1.25% cachetest [kernel.kallsyms] [k] restore 0.74% cachetest [kernel.kallsyms] [k] ._raw_spin_lock 0.71% cachetest [kernel.kallsyms] [k] .filemap_fault 0.66% cachetest [kernel.kallsyms] [k] .memset 0.54% cachetest [kernel.kallsyms] [k] .copy_4K_page 0.54% cachetest [kernel.kallsyms] [k] .find_get_page 0.54% cachetest [kernel.kallsyms] [k] .sha_transform 0.52% cachetest [kernel.kallsyms] [k] .trace_hardirqs_off 0.50% cachetest [kernel.kallsyms] [k] .__do_fault <SNIP> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1291872833-839-1-git-send-email-imunsie@au1.ibm.com> Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-09 13:33:53 +08:00
.ordered_samples = true,
.ordering_requires_timestamps = true,
};
static int __cmd_annotate(void)
{
int ret;
struct perf_session *session;
perf session: Fallback to unordered processing if no sample_id_all If we are running the new perf on an old kernel without support for sample_id_all, we should fall back to the old unordered processing of events. If we didn't than we would *always* process events without timestamps out of order, whether or not we hit a reordering race. In other words, instead of there being a chance of not attributing samples correctly, we would guarantee that samples would not be attributed. While processing all events without timestamps before events with timestamps may seem like an intuitive solution, it falls down as PERF_RECORD_EXIT events would also be processed before any samples. Even with a workaround for that case, samples before/after an exec would not be attributed correctly. This patch allows commands to indicate whether they need to fall back to unordered processing, so that commands that do not care about timestamps on every event will not be affected. If we do fallback, this will print out a warning if report -D was invoked. This patch adds the test in perf_session__new so that we only need to test once per session. Commands that do not use an event_ops (such as record and top) can simply pass NULL in it's place. Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1291951882-sup-6069@au1.ibm.com> Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-10 11:09:16 +08:00
session = perf_session__new(input_name, O_RDONLY, force, false, &event_ops);
if (session == NULL)
return -ENOMEM;
ret = perf_session__process_events(session, &event_ops);
if (ret)
goto out_delete;
if (dump_trace) {
perf_session__fprintf_nr_events(session, stdout);
goto out_delete;
}
if (verbose > 3)
perf_session__fprintf(session, stdout);
if (verbose > 2)
perf_session__fprintf_dsos(session, stdout);
2010-05-11 00:04:11 +08:00
hists__collapse_resort(&session->hists);
hists__output_resort(&session->hists);
hists__find_annotations(&session->hists);
out_delete:
perf_session__delete(session);
return ret;
}
static const char * const annotate_usage[] = {
"perf annotate [<options>] <command>",
NULL
};
static const struct option options[] = {
OPT_STRING('i', "input", &input_name, "file",
"input file name"),
OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]",
"only consider symbols in these dsos"),
OPT_STRING('s', "symbol", &sym_hist_filter, "symbol",
perf_counter tools: Add 'perf annotate' feature Add new perf sub-command to display annotated source code: $ perf annotate decode_tree_entry ------------------------------------------------ Percent | Source code & Disassembly of /home/mingo/git/git ------------------------------------------------ : : /home/mingo/git/git: file format elf64-x86-64 : : : Disassembly of section .text: : : 00000000004a0da0 <decode_tree_entry>: : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 3.82 : 4a0da0: 41 54 push %r12 : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.17 : 4a0da2: 48 83 fa 17 cmp $0x17,%rdx : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 0.00 : 4a0da6: 49 89 fc mov %rdi,%r12 0.00 : 4a0da9: 55 push %rbp 3.37 : 4a0daa: 53 push %rbx : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.08 : 4a0dab: 76 73 jbe 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dad: 80 7c 16 eb 00 cmpb $0x0,-0x15(%rsi,%rdx,1) 3.48 : 4a0db2: 75 6c jne 4a0e20 <decode_tree_entry+0x80> : static const char *get_mode(const char *str, unsigned int *modep) : { : unsigned char c; : unsigned int mode = 0; : : if (*str == ' ') 1.94 : 4a0db4: 0f b6 06 movzbl (%rsi),%eax 0.39 : 4a0db7: 3c 20 cmp $0x20,%al 0.00 : 4a0db9: 74 65 je 4a0e20 <decode_tree_entry+0x80> : return NULL; : : while ((c = *str++) != ' ') { 0.06 : 4a0dbb: 89 c2 mov %eax,%edx : if (c < '0' || c > '7') 1.99 : 4a0dbd: 31 ed xor %ebp,%ebp : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 1.74 : 4a0dbf: 48 8d 5e 01 lea 0x1(%rsi),%rbx : if (c < '0' || c > '7') 0.00 : 4a0dc3: 8d 42 d0 lea -0x30(%rdx),%eax 0.17 : 4a0dc6: 3c 07 cmp $0x7,%al 0.00 : 4a0dc8: 76 0d jbe 4a0dd7 <decode_tree_entry+0x37> 0.00 : 4a0dca: eb 54 jmp 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dcc: 0f 1f 40 00 nopl 0x0(%rax) 16.57 : 4a0dd0: 8d 42 d0 lea -0x30(%rdx),%eax 0.14 : 4a0dd3: 3c 07 cmp $0x7,%al 0.00 : 4a0dd5: 77 49 ja 4a0e20 <decode_tree_entry+0x80> : return NULL; : mode = (mode << 3) + (c - '0'); 3.12 : 4a0dd7: 0f b6 c2 movzbl %dl,%eax : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 0.00 : 4a0dda: 0f b6 13 movzbl (%rbx),%edx 16.74 : 4a0ddd: 48 83 c3 01 add $0x1,%rbx : if (c < '0' || c > '7') : return NULL; : mode = (mode << 3) + (c - '0'); The first column is the percentage of samples that arrived on that particular line - relative to the total cost of the function. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-06 21:48:52 +08:00
"symbol to annotate"),
OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
perf: Fix endianness argument compatibility with OPT_BOOLEAN() and introduce OPT_INCR() Parsing an option from the command line with OPT_BOOLEAN on a bool data type would not work on a big-endian machine due to the manner in which the boolean was being cast into an int and incremented. For example, running 'perf probe --list' on a PowerPC machine would fail to properly set the list_events bool and would therefore print out the usage information and terminate. This patch makes OPT_BOOLEAN work as expected with a bool datatype. For cases where the original OPT_BOOLEAN was intentionally being used to increment an int each time it was passed in on the command line, this patch introduces OPT_INCR with the old behaviour of OPT_BOOLEAN (the verbose variable is currently the only such example of this). I have reviewed every use of OPT_BOOLEAN to verify that a true C99 bool was passed. Where integers were used, I verified that they were only being used for boolean logic and changed them to bools to ensure that they would not be mistakenly used as ints. The major exception was the verbose variable which now uses OPT_INCR instead of OPT_BOOLEAN. Signed-off-by: Ian Munsie <imunsie@au.ibm.com> Acked-by: David S. Miller <davem@davemloft.net> Cc: <stable@kernel.org> # NOTE: wont apply to .3[34].x cleanly, please backport Cc: Git development list <git@vger.kernel.org> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Eric B Munson <ebmunson@us.ibm.com> Cc: Valdis.Kletnieks@vt.edu Cc: WANG Cong <amwang@redhat.com> Cc: Thiago Farina <tfransosi@gmail.com> Cc: Masami Hiramatsu <mhiramat@redhat.com> Cc: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> Cc: Jaswinder Singh Rajput <jaswinderrajput@gmail.com> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Mike Galbraith <efault@gmx.de> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Anton Blanchard <anton@samba.org> Cc: John Kacur <jkacur@redhat.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1271147857-11604-1-git-send-email-imunsie@au.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-04-13 16:37:33 +08:00
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show symbol address, etc)"),
OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
"dump raw trace in ASCII"),
OPT_BOOLEAN(0, "tui", &use_tui, "Use the TUI interface"),
OPT_BOOLEAN(0, "stdio", &use_stdio, "Use the stdio interface"),
OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
"file", "vmlinux pathname"),
OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules,
"load module symbols - WARNING: use only with -k and LIVE kernel"),
OPT_BOOLEAN('l', "print-line", &print_line,
"print matching source lines (may be slow)"),
OPT_BOOLEAN('P', "full-paths", &full_paths,
"Don't shorten the displayed pathnames"),
OPT_END()
};
int cmd_annotate(int argc, const char **argv, const char *prefix __used)
{
argc = parse_options(argc, argv, options, annotate_usage, 0);
if (use_stdio)
use_browser = 0;
else if (use_tui)
use_browser = 1;
setup_browser();
symbol_conf.priv_size = sizeof(struct sym_priv);
symbol_conf.try_vmlinux_path = true;
if (symbol__init() < 0)
return -1;
setup_sorting(annotate_usage, options);
perf_counter tools: Add 'perf annotate' feature Add new perf sub-command to display annotated source code: $ perf annotate decode_tree_entry ------------------------------------------------ Percent | Source code & Disassembly of /home/mingo/git/git ------------------------------------------------ : : /home/mingo/git/git: file format elf64-x86-64 : : : Disassembly of section .text: : : 00000000004a0da0 <decode_tree_entry>: : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 3.82 : 4a0da0: 41 54 push %r12 : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.17 : 4a0da2: 48 83 fa 17 cmp $0x17,%rdx : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 0.00 : 4a0da6: 49 89 fc mov %rdi,%r12 0.00 : 4a0da9: 55 push %rbp 3.37 : 4a0daa: 53 push %rbx : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.08 : 4a0dab: 76 73 jbe 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dad: 80 7c 16 eb 00 cmpb $0x0,-0x15(%rsi,%rdx,1) 3.48 : 4a0db2: 75 6c jne 4a0e20 <decode_tree_entry+0x80> : static const char *get_mode(const char *str, unsigned int *modep) : { : unsigned char c; : unsigned int mode = 0; : : if (*str == ' ') 1.94 : 4a0db4: 0f b6 06 movzbl (%rsi),%eax 0.39 : 4a0db7: 3c 20 cmp $0x20,%al 0.00 : 4a0db9: 74 65 je 4a0e20 <decode_tree_entry+0x80> : return NULL; : : while ((c = *str++) != ' ') { 0.06 : 4a0dbb: 89 c2 mov %eax,%edx : if (c < '0' || c > '7') 1.99 : 4a0dbd: 31 ed xor %ebp,%ebp : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 1.74 : 4a0dbf: 48 8d 5e 01 lea 0x1(%rsi),%rbx : if (c < '0' || c > '7') 0.00 : 4a0dc3: 8d 42 d0 lea -0x30(%rdx),%eax 0.17 : 4a0dc6: 3c 07 cmp $0x7,%al 0.00 : 4a0dc8: 76 0d jbe 4a0dd7 <decode_tree_entry+0x37> 0.00 : 4a0dca: eb 54 jmp 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dcc: 0f 1f 40 00 nopl 0x0(%rax) 16.57 : 4a0dd0: 8d 42 d0 lea -0x30(%rdx),%eax 0.14 : 4a0dd3: 3c 07 cmp $0x7,%al 0.00 : 4a0dd5: 77 49 ja 4a0e20 <decode_tree_entry+0x80> : return NULL; : mode = (mode << 3) + (c - '0'); 3.12 : 4a0dd7: 0f b6 c2 movzbl %dl,%eax : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 0.00 : 4a0dda: 0f b6 13 movzbl (%rbx),%edx 16.74 : 4a0ddd: 48 83 c3 01 add $0x1,%rbx : if (c < '0' || c > '7') : return NULL; : mode = (mode << 3) + (c - '0'); The first column is the percentage of samples that arrived on that particular line - relative to the total cost of the function. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-06 21:48:52 +08:00
if (argc) {
/*
* Special case: if there's an argument left then assume tha
* it's a symbol filter:
*/
if (argc > 1)
usage_with_options(annotate_usage, options);
sym_hist_filter = argv[0];
}
if (field_sep && *field_sep == '.') {
pr_err("'.' is the only non valid --field-separator argument\n");
return -1;
}
return __cmd_annotate();
}