2009-06-06 21:19:13 +08:00
|
|
|
/*
|
|
|
|
|
* 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"
|
|
|
|
|
|
2011-02-04 19:45:46 +08:00
|
|
|
#include "util/util.h"
|
2009-06-06 21:19:13 +08:00
|
|
|
#include "util/color.h"
|
2009-07-02 01:46:08 +08:00
|
|
|
#include <linux/list.h>
|
2009-06-06 21:19:13 +08:00
|
|
|
#include "util/cache.h"
|
2009-07-01 23:28:37 +08:00
|
|
|
#include <linux/rbtree.h>
|
2009-06-06 21:19:13 +08:00
|
|
|
#include "util/symbol.h"
|
|
|
|
|
|
|
|
|
|
#include "perf.h"
|
2009-08-17 04:05:48 +08:00
|
|
|
#include "util/debug.h"
|
2009-06-06 21:19:13 +08:00
|
|
|
|
2011-03-06 08:40:06 +08:00
|
|
|
#include "util/evlist.h"
|
|
|
|
|
#include "util/evsel.h"
|
2011-02-04 19:45:46 +08:00
|
|
|
#include "util/annotate.h"
|
2009-11-28 02:29:22 +08:00
|
|
|
#include "util/event.h"
|
2015-12-15 23:39:39 +08:00
|
|
|
#include <subcmd/parse-options.h>
|
2009-06-06 21:19:13 +08:00
|
|
|
#include "util/parse-events.h"
|
2009-08-14 18:21:53 +08:00
|
|
|
#include "util/thread.h"
|
2009-09-25 00:02:49 +08:00
|
|
|
#include "util/sort.h"
|
2009-09-28 21:32:55 +08:00
|
|
|
#include "util/hist.h"
|
2009-12-12 07:24:02 +08:00
|
|
|
#include "util/session.h"
|
2011-11-28 18:30:20 +08:00
|
|
|
#include "util/tool.h"
|
2013-10-15 22:27:32 +08:00
|
|
|
#include "util/data.h"
|
2012-10-16 07:33:38 +08:00
|
|
|
#include "arch/common.h"
|
perf annotate: Add branch stack / basic block
I wanted to know the hottest path through a function and figured the
branch-stack (LBR) information should be able to help out with that.
The below uses the branch-stack to create basic blocks and generate
statistics from them.
from to branch_i
* ----> *
|
| block
v
* ----> *
from to branch_i+1
The blocks are broken down into non-overlapping ranges, while tracking
if the start of each range is an entry point and/or the end of a range
is a branch.
Each block iterates all ranges it covers (while splitting where required
to exactly match the block) and increments the 'coverage' count.
For the range including the branch we increment the taken counter, as
well as the pred counter if flags.predicted.
Using these number we can find if an instruction:
- had coverage; given by:
br->coverage / br->sym->max_coverage
This metric ensures each symbol has a 100% spot, which reflects the
observation that each symbol must have a most covered/hottest
block.
- is a branch target: br->is_target && br->start == add
- for targets, how much of a branch's coverages comes from it:
target->entry / branch->coverage
- is a branch: br->is_branch && br->end == addr
- for branches, how often it was taken:
br->taken / br->coverage
after all, all execution that didn't take the branch would have
incremented the coverage and continued onward to a later branch.
- for branches, how often it was predicted:
br->pred / br->taken
The coverage percentage is used to color the address and asm sections;
for low (<1%) coverage we use NORMAL (uncolored), indicating that these
instructions are not 'important'. For high coverage (>75%) we color the
address RED.
For each branch, we add an asm comment after the instruction with
information on how often it was taken and predicted.
Output looks like (sans color, which does loose a lot of the
information :/)
$ perf record --branch-filter u,any -e cycles:p ./branches 27
$ perf annotate branches
Percent | Source code & Disassembly of branches for cycles:pu (217 samples)
---------------------------------------------------------------------------------
: branches():
0.00 : 40057a: push %rbp
0.00 : 40057b: mov %rsp,%rbp
0.00 : 40057e: sub $0x20,%rsp
0.00 : 400582: mov %rdi,-0x18(%rbp)
0.00 : 400586: mov %rsi,-0x20(%rbp)
0.00 : 40058a: mov -0x18(%rbp),%rax
0.00 : 40058e: mov %rax,-0x10(%rbp)
0.00 : 400592: movq $0x0,-0x8(%rbp)
0.00 : 40059a: jmpq 400656 <branches+0xdc>
1.84 : 40059f: mov -0x10(%rbp),%rax # +100.00%
3.23 : 4005a3: and $0x1,%eax
1.84 : 4005a6: test %rax,%rax
0.00 : 4005a9: je 4005bf <branches+0x45> # -54.50% (p:42.00%)
0.46 : 4005ab: mov 0x200bbe(%rip),%rax # 601170 <acc>
12.90 : 4005b2: add $0x1,%rax
2.30 : 4005b6: mov %rax,0x200bb3(%rip) # 601170 <acc>
0.46 : 4005bd: jmp 4005d1 <branches+0x57> # -100.00% (p:100.00%)
0.92 : 4005bf: mov 0x200baa(%rip),%rax # 601170 <acc> # +49.54%
13.82 : 4005c6: sub $0x1,%rax
0.46 : 4005ca: mov %rax,0x200b9f(%rip) # 601170 <acc>
2.30 : 4005d1: mov -0x10(%rbp),%rax # +50.46%
0.46 : 4005d5: mov %rax,%rdi
0.46 : 4005d8: callq 400526 <lfsr> # -100.00% (p:100.00%)
0.00 : 4005dd: mov %rax,-0x10(%rbp) # +100.00%
0.92 : 4005e1: mov -0x18(%rbp),%rax
0.00 : 4005e5: and $0x1,%eax
0.00 : 4005e8: test %rax,%rax
0.00 : 4005eb: je 4005ff <branches+0x85> # -100.00% (p:100.00%)
0.00 : 4005ed: mov 0x200b7c(%rip),%rax # 601170 <acc>
0.00 : 4005f4: shr $0x2,%rax
0.00 : 4005f8: mov %rax,0x200b71(%rip) # 601170 <acc>
0.00 : 4005ff: mov -0x10(%rbp),%rax # +100.00%
7.37 : 400603: and $0x1,%eax
3.69 : 400606: test %rax,%rax
0.00 : 400609: jne 400612 <branches+0x98> # -59.25% (p:42.99%)
1.84 : 40060b: mov $0x1,%eax
14.29 : 400610: jmp 400617 <branches+0x9d> # -100.00% (p:100.00%)
1.38 : 400612: mov $0x0,%eax # +57.65%
10.14 : 400617: test %al,%al # +42.35%
0.00 : 400619: je 40062f <branches+0xb5> # -57.65% (p:100.00%)
0.46 : 40061b: mov 0x200b4e(%rip),%rax # 601170 <acc>
2.76 : 400622: sub $0x1,%rax
0.00 : 400626: mov %rax,0x200b43(%rip) # 601170 <acc>
0.46 : 40062d: jmp 400641 <branches+0xc7> # -100.00% (p:100.00%)
0.92 : 40062f: mov 0x200b3a(%rip),%rax # 601170 <acc> # +56.13%
2.30 : 400636: add $0x1,%rax
0.92 : 40063a: mov %rax,0x200b2f(%rip) # 601170 <acc>
0.92 : 400641: mov -0x10(%rbp),%rax # +43.87%
2.30 : 400645: mov %rax,%rdi
0.00 : 400648: callq 400526 <lfsr> # -100.00% (p:100.00%)
0.00 : 40064d: mov %rax,-0x10(%rbp) # +100.00%
1.84 : 400651: addq $0x1,-0x8(%rbp)
0.92 : 400656: mov -0x8(%rbp),%rax
5.07 : 40065a: cmp -0x20(%rbp),%rax
0.00 : 40065e: jb 40059f <branches+0x25> # -100.00% (p:100.00%)
0.00 : 400664: nop
0.00 : 400665: leaveq
0.00 : 400666: retq
(Note: the --branch-filter u,any was used to avoid spurious target and
branch points due to interrupts/faults, they show up as very small -/+
annotations on 'weird' locations)
Committer note:
Please take a look at:
http://vger.kernel.org/~acme/perf/annotate_basic_blocks.png
To see the colors.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Anshuman Khandual <khandual@linux.vnet.ibm.com>
Cc: David Carrillo-Cisneros <davidcc@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
[ Moved sym->max_coverage to 'struct annotate', aka symbol__annotate(sym) ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-09-06 03:08:12 +08:00
|
|
|
#include "util/block-range.h"
|
2009-06-06 21:19:13 +08:00
|
|
|
|
2013-09-13 14:27:43 +08:00
|
|
|
#include <dlfcn.h>
|
2017-04-18 21:46:11 +08:00
|
|
|
#include <errno.h>
|
2011-07-04 19:57:50 +08:00
|
|
|
#include <linux/bitmap.h>
|
|
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
struct perf_annotate {
|
2011-11-28 18:30:20 +08:00
|
|
|
struct perf_tool tool;
|
2014-08-12 14:40:35 +08:00
|
|
|
struct perf_session *session;
|
|
|
|
|
bool use_tui, use_stdio, use_gtk;
|
2011-11-17 22:33:21 +08:00
|
|
|
bool full_paths;
|
|
|
|
|
bool print_line;
|
2013-02-07 17:02:14 +08:00
|
|
|
bool skip_missing;
|
2011-11-17 22:33:21 +08:00
|
|
|
const char *sym_hist_filter;
|
|
|
|
|
const char *cpu_list;
|
|
|
|
|
DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
|
2011-11-25 18:19:45 +08:00
|
|
|
};
|
2011-07-04 19:57:50 +08:00
|
|
|
|
perf annotate: Add branch stack / basic block
I wanted to know the hottest path through a function and figured the
branch-stack (LBR) information should be able to help out with that.
The below uses the branch-stack to create basic blocks and generate
statistics from them.
from to branch_i
* ----> *
|
| block
v
* ----> *
from to branch_i+1
The blocks are broken down into non-overlapping ranges, while tracking
if the start of each range is an entry point and/or the end of a range
is a branch.
Each block iterates all ranges it covers (while splitting where required
to exactly match the block) and increments the 'coverage' count.
For the range including the branch we increment the taken counter, as
well as the pred counter if flags.predicted.
Using these number we can find if an instruction:
- had coverage; given by:
br->coverage / br->sym->max_coverage
This metric ensures each symbol has a 100% spot, which reflects the
observation that each symbol must have a most covered/hottest
block.
- is a branch target: br->is_target && br->start == add
- for targets, how much of a branch's coverages comes from it:
target->entry / branch->coverage
- is a branch: br->is_branch && br->end == addr
- for branches, how often it was taken:
br->taken / br->coverage
after all, all execution that didn't take the branch would have
incremented the coverage and continued onward to a later branch.
- for branches, how often it was predicted:
br->pred / br->taken
The coverage percentage is used to color the address and asm sections;
for low (<1%) coverage we use NORMAL (uncolored), indicating that these
instructions are not 'important'. For high coverage (>75%) we color the
address RED.
For each branch, we add an asm comment after the instruction with
information on how often it was taken and predicted.
Output looks like (sans color, which does loose a lot of the
information :/)
$ perf record --branch-filter u,any -e cycles:p ./branches 27
$ perf annotate branches
Percent | Source code & Disassembly of branches for cycles:pu (217 samples)
---------------------------------------------------------------------------------
: branches():
0.00 : 40057a: push %rbp
0.00 : 40057b: mov %rsp,%rbp
0.00 : 40057e: sub $0x20,%rsp
0.00 : 400582: mov %rdi,-0x18(%rbp)
0.00 : 400586: mov %rsi,-0x20(%rbp)
0.00 : 40058a: mov -0x18(%rbp),%rax
0.00 : 40058e: mov %rax,-0x10(%rbp)
0.00 : 400592: movq $0x0,-0x8(%rbp)
0.00 : 40059a: jmpq 400656 <branches+0xdc>
1.84 : 40059f: mov -0x10(%rbp),%rax # +100.00%
3.23 : 4005a3: and $0x1,%eax
1.84 : 4005a6: test %rax,%rax
0.00 : 4005a9: je 4005bf <branches+0x45> # -54.50% (p:42.00%)
0.46 : 4005ab: mov 0x200bbe(%rip),%rax # 601170 <acc>
12.90 : 4005b2: add $0x1,%rax
2.30 : 4005b6: mov %rax,0x200bb3(%rip) # 601170 <acc>
0.46 : 4005bd: jmp 4005d1 <branches+0x57> # -100.00% (p:100.00%)
0.92 : 4005bf: mov 0x200baa(%rip),%rax # 601170 <acc> # +49.54%
13.82 : 4005c6: sub $0x1,%rax
0.46 : 4005ca: mov %rax,0x200b9f(%rip) # 601170 <acc>
2.30 : 4005d1: mov -0x10(%rbp),%rax # +50.46%
0.46 : 4005d5: mov %rax,%rdi
0.46 : 4005d8: callq 400526 <lfsr> # -100.00% (p:100.00%)
0.00 : 4005dd: mov %rax,-0x10(%rbp) # +100.00%
0.92 : 4005e1: mov -0x18(%rbp),%rax
0.00 : 4005e5: and $0x1,%eax
0.00 : 4005e8: test %rax,%rax
0.00 : 4005eb: je 4005ff <branches+0x85> # -100.00% (p:100.00%)
0.00 : 4005ed: mov 0x200b7c(%rip),%rax # 601170 <acc>
0.00 : 4005f4: shr $0x2,%rax
0.00 : 4005f8: mov %rax,0x200b71(%rip) # 601170 <acc>
0.00 : 4005ff: mov -0x10(%rbp),%rax # +100.00%
7.37 : 400603: and $0x1,%eax
3.69 : 400606: test %rax,%rax
0.00 : 400609: jne 400612 <branches+0x98> # -59.25% (p:42.99%)
1.84 : 40060b: mov $0x1,%eax
14.29 : 400610: jmp 400617 <branches+0x9d> # -100.00% (p:100.00%)
1.38 : 400612: mov $0x0,%eax # +57.65%
10.14 : 400617: test %al,%al # +42.35%
0.00 : 400619: je 40062f <branches+0xb5> # -57.65% (p:100.00%)
0.46 : 40061b: mov 0x200b4e(%rip),%rax # 601170 <acc>
2.76 : 400622: sub $0x1,%rax
0.00 : 400626: mov %rax,0x200b43(%rip) # 601170 <acc>
0.46 : 40062d: jmp 400641 <branches+0xc7> # -100.00% (p:100.00%)
0.92 : 40062f: mov 0x200b3a(%rip),%rax # 601170 <acc> # +56.13%
2.30 : 400636: add $0x1,%rax
0.92 : 40063a: mov %rax,0x200b2f(%rip) # 601170 <acc>
0.92 : 400641: mov -0x10(%rbp),%rax # +43.87%
2.30 : 400645: mov %rax,%rdi
0.00 : 400648: callq 400526 <lfsr> # -100.00% (p:100.00%)
0.00 : 40064d: mov %rax,-0x10(%rbp) # +100.00%
1.84 : 400651: addq $0x1,-0x8(%rbp)
0.92 : 400656: mov -0x8(%rbp),%rax
5.07 : 40065a: cmp -0x20(%rbp),%rax
0.00 : 40065e: jb 40059f <branches+0x25> # -100.00% (p:100.00%)
0.00 : 400664: nop
0.00 : 400665: leaveq
0.00 : 400666: retq
(Note: the --branch-filter u,any was used to avoid spurious target and
branch points due to interrupts/faults, they show up as very small -/+
annotations on 'weird' locations)
Committer note:
Please take a look at:
http://vger.kernel.org/~acme/perf/annotate_basic_blocks.png
To see the colors.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Anshuman Khandual <khandual@linux.vnet.ibm.com>
Cc: David Carrillo-Cisneros <davidcc@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
[ Moved sym->max_coverage to 'struct annotate', aka symbol__annotate(sym) ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-09-06 03:08:12 +08:00
|
|
|
/*
|
|
|
|
|
* Given one basic block:
|
|
|
|
|
*
|
|
|
|
|
* from to branch_i
|
|
|
|
|
* * ----> *
|
|
|
|
|
* |
|
|
|
|
|
* | block
|
|
|
|
|
* v
|
|
|
|
|
* * ----> *
|
|
|
|
|
* from to branch_i+1
|
|
|
|
|
*
|
|
|
|
|
* where the horizontal are the branches and the vertical is the executed
|
|
|
|
|
* block of instructions.
|
|
|
|
|
*
|
|
|
|
|
* We count, for each 'instruction', the number of blocks that covered it as
|
|
|
|
|
* well as count the ratio each branch is taken.
|
|
|
|
|
*
|
|
|
|
|
* We can do this without knowing the actual instruction stream by keeping
|
|
|
|
|
* track of the address ranges. We break down ranges such that there is no
|
|
|
|
|
* overlap and iterate from the start until the end.
|
|
|
|
|
*
|
|
|
|
|
* @acme: once we parse the objdump output _before_ processing the samples,
|
|
|
|
|
* we can easily fold the branch.cycles IPC bits in.
|
|
|
|
|
*/
|
|
|
|
|
static void process_basic_block(struct addr_map_symbol *start,
|
|
|
|
|
struct addr_map_symbol *end,
|
|
|
|
|
struct branch_flags *flags)
|
|
|
|
|
{
|
|
|
|
|
struct symbol *sym = start->sym;
|
|
|
|
|
struct annotation *notes = sym ? symbol__annotation(sym) : NULL;
|
|
|
|
|
struct block_range_iter iter;
|
|
|
|
|
struct block_range *entry;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Sanity; NULL isn't executable and the CPU cannot execute backwards
|
|
|
|
|
*/
|
|
|
|
|
if (!start->addr || start->addr > end->addr)
|
|
|
|
|
return;
|
|
|
|
|
|
|
|
|
|
iter = block_range__create(start->addr, end->addr);
|
|
|
|
|
if (!block_range_iter__valid(&iter))
|
|
|
|
|
return;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* First block in range is a branch target.
|
|
|
|
|
*/
|
|
|
|
|
entry = block_range_iter(&iter);
|
|
|
|
|
assert(entry->is_target);
|
|
|
|
|
entry->entry++;
|
|
|
|
|
|
|
|
|
|
do {
|
|
|
|
|
entry = block_range_iter(&iter);
|
|
|
|
|
|
|
|
|
|
entry->coverage++;
|
|
|
|
|
entry->sym = sym;
|
|
|
|
|
|
|
|
|
|
if (notes)
|
|
|
|
|
notes->max_coverage = max(notes->max_coverage, entry->coverage);
|
|
|
|
|
|
|
|
|
|
} while (block_range_iter__next(&iter));
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Last block in rage is a branch.
|
|
|
|
|
*/
|
|
|
|
|
entry = block_range_iter(&iter);
|
|
|
|
|
assert(entry->is_branch);
|
|
|
|
|
entry->taken++;
|
|
|
|
|
if (flags->predicted)
|
|
|
|
|
entry->pred++;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static void process_branch_stack(struct branch_stack *bs, struct addr_location *al,
|
|
|
|
|
struct perf_sample *sample)
|
|
|
|
|
{
|
|
|
|
|
struct addr_map_symbol *prev = NULL;
|
|
|
|
|
struct branch_info *bi;
|
|
|
|
|
int i;
|
|
|
|
|
|
|
|
|
|
if (!bs || !bs->nr)
|
|
|
|
|
return;
|
|
|
|
|
|
|
|
|
|
bi = sample__resolve_bstack(sample, al);
|
|
|
|
|
if (!bi)
|
|
|
|
|
return;
|
|
|
|
|
|
|
|
|
|
for (i = bs->nr - 1; i >= 0; i--) {
|
|
|
|
|
/*
|
|
|
|
|
* XXX filter against symbol
|
|
|
|
|
*/
|
|
|
|
|
if (prev)
|
|
|
|
|
process_basic_block(prev, &bi[i].from, &bi[i].flags);
|
|
|
|
|
prev = &bi[i].to;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
free(bi);
|
|
|
|
|
}
|
|
|
|
|
|
2011-11-12 08:17:32 +08:00
|
|
|
static int perf_evsel__add_sample(struct perf_evsel *evsel,
|
2015-12-23 01:06:58 +08:00
|
|
|
struct perf_sample *sample,
|
2011-11-25 18:19:45 +08:00
|
|
|
struct addr_location *al,
|
|
|
|
|
struct perf_annotate *ann)
|
2009-06-06 21:19:13 +08:00
|
|
|
{
|
2014-10-10 00:13:41 +08:00
|
|
|
struct hists *hists = evsel__hists(evsel);
|
2010-02-25 23:57:40 +08:00
|
|
|
struct hist_entry *he;
|
2011-03-06 08:40:06 +08:00
|
|
|
int ret;
|
2010-02-25 23:57:40 +08:00
|
|
|
|
2011-11-17 22:33:21 +08:00
|
|
|
if (ann->sym_hist_filter != NULL &&
|
|
|
|
|
(al->sym == NULL ||
|
|
|
|
|
strcmp(ann->sym_hist_filter, al->sym->name) != 0)) {
|
2010-02-25 23:57:40 +08:00
|
|
|
/* We're only interested in a symbol named sym_hist_filter */
|
2015-05-26 02:30:09 +08:00
|
|
|
/*
|
|
|
|
|
* FIXME: why isn't this done in the symbol_filter when loading
|
|
|
|
|
* the DSO?
|
|
|
|
|
*/
|
2010-02-25 23:57:40 +08:00
|
|
|
if (al->sym != NULL) {
|
|
|
|
|
rb_erase(&al->sym->rb_node,
|
|
|
|
|
&al->map->dso->symbols[al->map->type]);
|
|
|
|
|
symbol__delete(al->sym);
|
2015-08-25 00:33:14 +08:00
|
|
|
dso__reset_find_symbol_cache(al->map->dso);
|
2010-02-25 23:57:40 +08:00
|
|
|
}
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
perf annotate: Add branch stack / basic block
I wanted to know the hottest path through a function and figured the
branch-stack (LBR) information should be able to help out with that.
The below uses the branch-stack to create basic blocks and generate
statistics from them.
from to branch_i
* ----> *
|
| block
v
* ----> *
from to branch_i+1
The blocks are broken down into non-overlapping ranges, while tracking
if the start of each range is an entry point and/or the end of a range
is a branch.
Each block iterates all ranges it covers (while splitting where required
to exactly match the block) and increments the 'coverage' count.
For the range including the branch we increment the taken counter, as
well as the pred counter if flags.predicted.
Using these number we can find if an instruction:
- had coverage; given by:
br->coverage / br->sym->max_coverage
This metric ensures each symbol has a 100% spot, which reflects the
observation that each symbol must have a most covered/hottest
block.
- is a branch target: br->is_target && br->start == add
- for targets, how much of a branch's coverages comes from it:
target->entry / branch->coverage
- is a branch: br->is_branch && br->end == addr
- for branches, how often it was taken:
br->taken / br->coverage
after all, all execution that didn't take the branch would have
incremented the coverage and continued onward to a later branch.
- for branches, how often it was predicted:
br->pred / br->taken
The coverage percentage is used to color the address and asm sections;
for low (<1%) coverage we use NORMAL (uncolored), indicating that these
instructions are not 'important'. For high coverage (>75%) we color the
address RED.
For each branch, we add an asm comment after the instruction with
information on how often it was taken and predicted.
Output looks like (sans color, which does loose a lot of the
information :/)
$ perf record --branch-filter u,any -e cycles:p ./branches 27
$ perf annotate branches
Percent | Source code & Disassembly of branches for cycles:pu (217 samples)
---------------------------------------------------------------------------------
: branches():
0.00 : 40057a: push %rbp
0.00 : 40057b: mov %rsp,%rbp
0.00 : 40057e: sub $0x20,%rsp
0.00 : 400582: mov %rdi,-0x18(%rbp)
0.00 : 400586: mov %rsi,-0x20(%rbp)
0.00 : 40058a: mov -0x18(%rbp),%rax
0.00 : 40058e: mov %rax,-0x10(%rbp)
0.00 : 400592: movq $0x0,-0x8(%rbp)
0.00 : 40059a: jmpq 400656 <branches+0xdc>
1.84 : 40059f: mov -0x10(%rbp),%rax # +100.00%
3.23 : 4005a3: and $0x1,%eax
1.84 : 4005a6: test %rax,%rax
0.00 : 4005a9: je 4005bf <branches+0x45> # -54.50% (p:42.00%)
0.46 : 4005ab: mov 0x200bbe(%rip),%rax # 601170 <acc>
12.90 : 4005b2: add $0x1,%rax
2.30 : 4005b6: mov %rax,0x200bb3(%rip) # 601170 <acc>
0.46 : 4005bd: jmp 4005d1 <branches+0x57> # -100.00% (p:100.00%)
0.92 : 4005bf: mov 0x200baa(%rip),%rax # 601170 <acc> # +49.54%
13.82 : 4005c6: sub $0x1,%rax
0.46 : 4005ca: mov %rax,0x200b9f(%rip) # 601170 <acc>
2.30 : 4005d1: mov -0x10(%rbp),%rax # +50.46%
0.46 : 4005d5: mov %rax,%rdi
0.46 : 4005d8: callq 400526 <lfsr> # -100.00% (p:100.00%)
0.00 : 4005dd: mov %rax,-0x10(%rbp) # +100.00%
0.92 : 4005e1: mov -0x18(%rbp),%rax
0.00 : 4005e5: and $0x1,%eax
0.00 : 4005e8: test %rax,%rax
0.00 : 4005eb: je 4005ff <branches+0x85> # -100.00% (p:100.00%)
0.00 : 4005ed: mov 0x200b7c(%rip),%rax # 601170 <acc>
0.00 : 4005f4: shr $0x2,%rax
0.00 : 4005f8: mov %rax,0x200b71(%rip) # 601170 <acc>
0.00 : 4005ff: mov -0x10(%rbp),%rax # +100.00%
7.37 : 400603: and $0x1,%eax
3.69 : 400606: test %rax,%rax
0.00 : 400609: jne 400612 <branches+0x98> # -59.25% (p:42.99%)
1.84 : 40060b: mov $0x1,%eax
14.29 : 400610: jmp 400617 <branches+0x9d> # -100.00% (p:100.00%)
1.38 : 400612: mov $0x0,%eax # +57.65%
10.14 : 400617: test %al,%al # +42.35%
0.00 : 400619: je 40062f <branches+0xb5> # -57.65% (p:100.00%)
0.46 : 40061b: mov 0x200b4e(%rip),%rax # 601170 <acc>
2.76 : 400622: sub $0x1,%rax
0.00 : 400626: mov %rax,0x200b43(%rip) # 601170 <acc>
0.46 : 40062d: jmp 400641 <branches+0xc7> # -100.00% (p:100.00%)
0.92 : 40062f: mov 0x200b3a(%rip),%rax # 601170 <acc> # +56.13%
2.30 : 400636: add $0x1,%rax
0.92 : 40063a: mov %rax,0x200b2f(%rip) # 601170 <acc>
0.92 : 400641: mov -0x10(%rbp),%rax # +43.87%
2.30 : 400645: mov %rax,%rdi
0.00 : 400648: callq 400526 <lfsr> # -100.00% (p:100.00%)
0.00 : 40064d: mov %rax,-0x10(%rbp) # +100.00%
1.84 : 400651: addq $0x1,-0x8(%rbp)
0.92 : 400656: mov -0x8(%rbp),%rax
5.07 : 40065a: cmp -0x20(%rbp),%rax
0.00 : 40065e: jb 40059f <branches+0x25> # -100.00% (p:100.00%)
0.00 : 400664: nop
0.00 : 400665: leaveq
0.00 : 400666: retq
(Note: the --branch-filter u,any was used to avoid spurious target and
branch points due to interrupts/faults, they show up as very small -/+
annotations on 'weird' locations)
Committer note:
Please take a look at:
http://vger.kernel.org/~acme/perf/annotate_basic_blocks.png
To see the colors.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Anshuman Khandual <khandual@linux.vnet.ibm.com>
Cc: David Carrillo-Cisneros <davidcc@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
[ Moved sym->max_coverage to 'struct annotate', aka symbol__annotate(sym) ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-09-06 03:08:12 +08:00
|
|
|
/*
|
|
|
|
|
* XXX filtered samples can still have branch entires pointing into our
|
|
|
|
|
* symbol and are missed.
|
|
|
|
|
*/
|
|
|
|
|
process_branch_stack(sample->branch_stack, al, sample);
|
|
|
|
|
|
2015-12-23 01:06:58 +08:00
|
|
|
sample->period = 1;
|
|
|
|
|
sample->weight = 1;
|
|
|
|
|
|
2016-06-15 02:19:21 +08:00
|
|
|
he = hists__add_entry(hists, al, NULL, NULL, NULL, sample, true);
|
2009-10-03 21:42:45 +08:00
|
|
|
if (he == NULL)
|
2009-06-06 21:19:13 +08:00
|
|
|
return -ENOMEM;
|
2010-02-25 23:57:40 +08:00
|
|
|
|
2013-12-19 02:46:32 +08:00
|
|
|
ret = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
|
2014-10-10 00:13:41 +08:00
|
|
|
hists__inc_nr_samples(hists, true);
|
2011-03-06 08:40:06 +08:00
|
|
|
return ret;
|
2009-06-06 21:19:13 +08:00
|
|
|
}
|
|
|
|
|
|
2011-11-28 18:30:20 +08:00
|
|
|
static int process_sample_event(struct perf_tool *tool,
|
2011-11-25 18:19:45 +08:00
|
|
|
union perf_event *event,
|
2011-01-30 00:01:45 +08:00
|
|
|
struct perf_sample *sample,
|
2011-03-16 02:44:01 +08:00
|
|
|
struct perf_evsel *evsel,
|
2011-11-28 17:56:39 +08:00
|
|
|
struct machine *machine)
|
2009-06-06 21:19:13 +08:00
|
|
|
{
|
2011-11-28 18:30:20 +08:00
|
|
|
struct perf_annotate *ann = container_of(tool, struct perf_annotate, tool);
|
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;
|
perf machine: Protect the machine->threads with a rwlock
In addition to using refcounts for the struct thread lifetime
management, we need to protect access to machine->threads from
concurrent access.
That happens in 'perf top', where a thread processes events, inserting
and deleting entries from that rb_tree while another thread decays
hist_entries, that end up dropping references and ultimately deleting
threads from the rb_tree and releasing its resources when no further
hist_entry (or other data structures, like in 'perf sched') references
it.
So the rule is the same for refcounts + protected trees in the kernel,
get the tree lock, find object, bump the refcount, drop the tree lock,
return, use object, drop the refcount if no more use of it is needed,
keep it if storing it in some other data structure, drop when releasing
that data structure.
I.e. pair "t = machine__find(new)_thread()" with a "thread__put(t)", and
"perf_event__preprocess_sample(&al)" with "addr_location__put(&al)".
The addr_location__put() one is because as we return references to
several data structures, we may end up adding more reference counting
for the other data structures and then we'll drop it at
addr_location__put() time.
Acked-by: David Ahern <dsahern@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-bs9rt4n0jw3hi9f3zxyy3xln@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-07 07:43:22 +08:00
|
|
|
int ret = 0;
|
2009-08-14 18:21:53 +08:00
|
|
|
|
2016-03-23 05:39:09 +08:00
|
|
|
if (machine__resolve(machine, &al, sample) < 0) {
|
2010-02-04 02:52:06 +08:00
|
|
|
pr_warning("problem processing %d event, skipping it.\n",
|
|
|
|
|
event->header.type);
|
2009-06-06 21:19:13 +08:00
|
|
|
return -1;
|
|
|
|
|
}
|
|
|
|
|
|
2011-11-17 22:33:21 +08:00
|
|
|
if (ann->cpu_list && !test_bit(sample->cpu, ann->cpu_bitmap))
|
perf machine: Protect the machine->threads with a rwlock
In addition to using refcounts for the struct thread lifetime
management, we need to protect access to machine->threads from
concurrent access.
That happens in 'perf top', where a thread processes events, inserting
and deleting entries from that rb_tree while another thread decays
hist_entries, that end up dropping references and ultimately deleting
threads from the rb_tree and releasing its resources when no further
hist_entry (or other data structures, like in 'perf sched') references
it.
So the rule is the same for refcounts + protected trees in the kernel,
get the tree lock, find object, bump the refcount, drop the tree lock,
return, use object, drop the refcount if no more use of it is needed,
keep it if storing it in some other data structure, drop when releasing
that data structure.
I.e. pair "t = machine__find(new)_thread()" with a "thread__put(t)", and
"perf_event__preprocess_sample(&al)" with "addr_location__put(&al)".
The addr_location__put() one is because as we return references to
several data structures, we may end up adding more reference counting
for the other data structures and then we'll drop it at
addr_location__put() time.
Acked-by: David Ahern <dsahern@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-bs9rt4n0jw3hi9f3zxyy3xln@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-07 07:43:22 +08:00
|
|
|
goto out_put;
|
2011-07-04 19:57:50 +08:00
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
if (!al.filtered && perf_evsel__add_sample(evsel, sample, &al, ann)) {
|
2010-02-04 02:52:06 +08:00
|
|
|
pr_warning("problem incrementing symbol count, "
|
|
|
|
|
"skipping event\n");
|
perf machine: Protect the machine->threads with a rwlock
In addition to using refcounts for the struct thread lifetime
management, we need to protect access to machine->threads from
concurrent access.
That happens in 'perf top', where a thread processes events, inserting
and deleting entries from that rb_tree while another thread decays
hist_entries, that end up dropping references and ultimately deleting
threads from the rb_tree and releasing its resources when no further
hist_entry (or other data structures, like in 'perf sched') references
it.
So the rule is the same for refcounts + protected trees in the kernel,
get the tree lock, find object, bump the refcount, drop the tree lock,
return, use object, drop the refcount if no more use of it is needed,
keep it if storing it in some other data structure, drop when releasing
that data structure.
I.e. pair "t = machine__find(new)_thread()" with a "thread__put(t)", and
"perf_event__preprocess_sample(&al)" with "addr_location__put(&al)".
The addr_location__put() one is because as we return references to
several data structures, we may end up adding more reference counting
for the other data structures and then we'll drop it at
addr_location__put() time.
Acked-by: David Ahern <dsahern@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-bs9rt4n0jw3hi9f3zxyy3xln@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-07 07:43:22 +08:00
|
|
|
ret = -1;
|
2009-06-06 21:19:13 +08:00
|
|
|
}
|
perf machine: Protect the machine->threads with a rwlock
In addition to using refcounts for the struct thread lifetime
management, we need to protect access to machine->threads from
concurrent access.
That happens in 'perf top', where a thread processes events, inserting
and deleting entries from that rb_tree while another thread decays
hist_entries, that end up dropping references and ultimately deleting
threads from the rb_tree and releasing its resources when no further
hist_entry (or other data structures, like in 'perf sched') references
it.
So the rule is the same for refcounts + protected trees in the kernel,
get the tree lock, find object, bump the refcount, drop the tree lock,
return, use object, drop the refcount if no more use of it is needed,
keep it if storing it in some other data structure, drop when releasing
that data structure.
I.e. pair "t = machine__find(new)_thread()" with a "thread__put(t)", and
"perf_event__preprocess_sample(&al)" with "addr_location__put(&al)".
The addr_location__put() one is because as we return references to
several data structures, we may end up adding more reference counting
for the other data structures and then we'll drop it at
addr_location__put() time.
Acked-by: David Ahern <dsahern@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-bs9rt4n0jw3hi9f3zxyy3xln@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-07 07:43:22 +08:00
|
|
|
out_put:
|
|
|
|
|
addr_location__put(&al);
|
|
|
|
|
return ret;
|
2009-06-06 21:19:13 +08:00
|
|
|
}
|
|
|
|
|
|
2013-03-05 13:53:21 +08:00
|
|
|
static int hist_entry__tty_annotate(struct hist_entry *he,
|
|
|
|
|
struct perf_evsel *evsel,
|
2011-11-25 18:19:45 +08:00
|
|
|
struct perf_annotate *ann)
|
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
|
|
|
{
|
2013-03-05 13:53:21 +08:00
|
|
|
return symbol__tty_annotate(he->ms.sym, he->ms.map, evsel,
|
2011-11-17 22:33:21 +08:00
|
|
|
ann->print_line, ann->full_paths, 0, 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
|
|
|
}
|
|
|
|
|
|
2013-10-23 06:01:31 +08:00
|
|
|
static void hists__find_annotations(struct hists *hists,
|
2013-03-05 13:53:21 +08:00
|
|
|
struct perf_evsel *evsel,
|
2011-11-25 18:19:45 +08:00
|
|
|
struct perf_annotate *ann)
|
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
|
|
|
{
|
2013-10-23 06:01:31 +08:00
|
|
|
struct rb_node *nd = rb_first(&hists->entries), *next;
|
2011-10-21 02:59:15 +08:00
|
|
|
int key = K_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
|
|
|
|
2010-05-22 22:25:40 +08:00
|
|
|
while (nd) {
|
2009-10-20 03:17:57 +08:00
|
|
|
struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
|
2011-02-04 19:45:46 +08:00
|
|
|
struct annotation *notes;
|
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
|
|
|
|
2010-05-22 22:25:40 +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
|
|
|
|
2011-02-04 19:45:46 +08:00
|
|
|
notes = symbol__annotation(he->ms.sym);
|
2011-02-08 23:27:39 +08:00
|
|
|
if (notes->src == NULL) {
|
2010-05-22 22:25:40 +08:00
|
|
|
find_next:
|
2011-10-21 02:59:15 +08:00
|
|
|
if (key == K_LEFT)
|
2010-05-22 22:25:40 +08:00
|
|
|
nd = rb_prev(nd);
|
|
|
|
|
else
|
|
|
|
|
nd = rb_next(nd);
|
2009-10-21 00:25:40 +08:00
|
|
|
continue;
|
2010-05-22 22:25:40 +08:00
|
|
|
}
|
2009-10-21 00:25:40 +08:00
|
|
|
|
2013-02-07 17:02:08 +08:00
|
|
|
if (use_browser == 2) {
|
2013-02-07 17:02:14 +08:00
|
|
|
int ret;
|
2013-09-13 14:27:43 +08:00
|
|
|
int (*annotate)(struct hist_entry *he,
|
|
|
|
|
struct perf_evsel *evsel,
|
|
|
|
|
struct hist_browser_timer *hbt);
|
|
|
|
|
|
|
|
|
|
annotate = dlsym(perf_gtk_handle,
|
|
|
|
|
"hist_entry__gtk_annotate");
|
|
|
|
|
if (annotate == NULL) {
|
|
|
|
|
ui__error("GTK browser not found!\n");
|
|
|
|
|
return;
|
|
|
|
|
}
|
2013-02-07 17:02:14 +08:00
|
|
|
|
2013-09-13 14:27:43 +08:00
|
|
|
ret = annotate(he, evsel, NULL);
|
2013-02-07 17:02:14 +08:00
|
|
|
if (!ret || !ann->skip_missing)
|
|
|
|
|
return;
|
|
|
|
|
|
|
|
|
|
/* skip missing symbols */
|
|
|
|
|
nd = rb_next(nd);
|
2013-02-07 17:02:08 +08:00
|
|
|
} else if (use_browser == 1) {
|
2013-03-05 13:53:21 +08:00
|
|
|
key = hist_entry__tui_annotate(he, evsel, NULL);
|
2010-05-22 22:25:40 +08:00
|
|
|
switch (key) {
|
2013-02-07 17:02:14 +08:00
|
|
|
case -1:
|
|
|
|
|
if (!ann->skip_missing)
|
|
|
|
|
return;
|
|
|
|
|
/* fall through */
|
2011-10-21 02:59:15 +08:00
|
|
|
case K_RIGHT:
|
2010-08-11 21:07:43 +08:00
|
|
|
next = rb_next(nd);
|
2010-05-22 22:25:40 +08:00
|
|
|
break;
|
2011-10-21 02:59:15 +08:00
|
|
|
case K_LEFT:
|
2010-08-11 21:07:43 +08:00
|
|
|
next = rb_prev(nd);
|
2010-05-22 22:25:40 +08:00
|
|
|
break;
|
2010-08-11 21:07:43 +08:00
|
|
|
default:
|
|
|
|
|
return;
|
2010-05-22 22:25:40 +08:00
|
|
|
}
|
2010-08-11 21:07:43 +08:00
|
|
|
|
|
|
|
|
if (next != NULL)
|
|
|
|
|
nd = next;
|
2010-05-22 22:25:40 +08:00
|
|
|
} else {
|
2013-03-05 13:53:21 +08:00
|
|
|
hist_entry__tty_annotate(he, evsel, ann);
|
2010-05-22 22:25:40 +08:00
|
|
|
nd = rb_next(nd);
|
|
|
|
|
/*
|
|
|
|
|
* Since we have a hist_entry per IP for the same
|
2011-02-08 23:27:39 +08:00
|
|
|
* symbol, free he->ms.sym->src to signal we already
|
2010-05-22 22:25:40 +08:00
|
|
|
* processed this symbol.
|
|
|
|
|
*/
|
2015-07-18 23:24:48 +08:00
|
|
|
zfree(¬es->src->cycles_hist);
|
2013-12-27 04:41:15 +08:00
|
|
|
zfree(¬es->src);
|
2010-05-22 22:25:40 +08:00
|
|
|
}
|
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
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2011-11-25 18:19:45 +08:00
|
|
|
static int __cmd_annotate(struct perf_annotate *ann)
|
2009-06-06 21:19:13 +08:00
|
|
|
{
|
2009-12-01 14:04:49 +08:00
|
|
|
int ret;
|
2014-08-12 14:40:35 +08:00
|
|
|
struct perf_session *session = ann->session;
|
2011-03-06 08:40:06 +08:00
|
|
|
struct perf_evsel *pos;
|
|
|
|
|
u64 total_nr_samples;
|
2009-12-12 07:24:02 +08:00
|
|
|
|
2011-11-17 22:33:21 +08:00
|
|
|
if (ann->cpu_list) {
|
|
|
|
|
ret = perf_session__cpu_bitmap(session, ann->cpu_list,
|
|
|
|
|
ann->cpu_bitmap);
|
2011-07-04 19:57:50 +08:00
|
|
|
if (ret)
|
2014-08-12 14:40:35 +08:00
|
|
|
goto out;
|
2011-07-04 19:57:50 +08:00
|
|
|
}
|
|
|
|
|
|
2012-10-16 07:33:38 +08:00
|
|
|
if (!objdump_path) {
|
2015-09-09 02:52:20 +08:00
|
|
|
ret = perf_env__lookup_objdump(&session->header.env);
|
2012-10-16 07:33:38 +08:00
|
|
|
if (ret)
|
2014-08-12 14:40:35 +08:00
|
|
|
goto out;
|
2012-10-16 07:33:38 +08:00
|
|
|
}
|
|
|
|
|
|
2015-03-03 22:58:45 +08:00
|
|
|
ret = perf_session__process_events(session);
|
2009-12-01 14:04:49 +08:00
|
|
|
if (ret)
|
2014-08-12 14:40:35 +08:00
|
|
|
goto out;
|
2009-06-06 21:19:13 +08:00
|
|
|
|
2009-11-28 02:29:22 +08:00
|
|
|
if (dump_trace) {
|
2010-05-14 21:36:42 +08:00
|
|
|
perf_session__fprintf_nr_events(session, stdout);
|
2014-10-11 02:49:21 +08:00
|
|
|
perf_evlist__fprintf_nr_events(session->evlist, stdout);
|
2014-08-12 14:40:35 +08:00
|
|
|
goto out;
|
2009-11-28 02:29:22 +08:00
|
|
|
}
|
2009-06-06 21:19:13 +08:00
|
|
|
|
2009-10-07 21:49:00 +08:00
|
|
|
if (verbose > 3)
|
2009-12-14 05:50:28 +08:00
|
|
|
perf_session__fprintf(session, stdout);
|
2009-06-06 21:19:13 +08:00
|
|
|
|
2009-10-07 21:49:00 +08:00
|
|
|
if (verbose > 2)
|
2010-04-28 08:22:44 +08:00
|
|
|
perf_session__fprintf_dsos(session, stdout);
|
2009-06-06 21:19:13 +08:00
|
|
|
|
2011-03-06 08:40:06 +08:00
|
|
|
total_nr_samples = 0;
|
2016-06-23 22:26:15 +08:00
|
|
|
evlist__for_each_entry(session->evlist, pos) {
|
2014-10-10 00:13:41 +08:00
|
|
|
struct hists *hists = evsel__hists(pos);
|
2011-03-06 08:40:06 +08:00
|
|
|
u32 nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
|
|
|
|
|
|
|
|
|
|
if (nr_samples > 0) {
|
|
|
|
|
total_nr_samples += nr_samples;
|
2013-10-11 13:15:38 +08:00
|
|
|
hists__collapse_resort(hists, NULL);
|
2015-08-11 18:30:48 +08:00
|
|
|
/* Don't sort callchain */
|
|
|
|
|
perf_evsel__reset_sample_bit(pos, CALLCHAIN);
|
2016-01-18 17:24:00 +08:00
|
|
|
perf_evsel__output_resort(pos, NULL);
|
perf annotate: Add basic support to event group view
Add --group option to enable event grouping. When enabled, all the
group members information will be shown with the leader so skip
non-leader events.
It only supports --stdio output currently. Later patches will extend
additional features.
$ perf annotate --group --stdio
...
Percent | Source code & Disassembly of libpthread-2.15.so
--------------------------------------------------------------------------------
:
:
:
: Disassembly of section .text:
:
: 000000387dc0aa50 <__pthread_mutex_unlock_usercnt>:
8.08 2.40 5.29 : 387dc0aa50: mov %rdi,%rdx
0.00 0.00 0.00 : 387dc0aa53: mov 0x10(%rdi),%edi
0.00 0.00 0.00 : 387dc0aa56: mov %edi,%eax
0.00 0.80 0.00 : 387dc0aa58: and $0x7f,%eax
3.03 2.40 3.53 : 387dc0aa5b: test $0x7c,%dil
0.00 0.00 0.00 : 387dc0aa5f: jne 387dc0aaa9 <__pthread_mutex_unlock_use
0.00 0.00 0.00 : 387dc0aa61: test %eax,%eax
0.00 0.00 0.00 : 387dc0aa63: jne 387dc0aa85 <__pthread_mutex_unlock_use
0.00 0.00 0.00 : 387dc0aa65: and $0x80,%edi
0.00 0.00 0.00 : 387dc0aa6b: test %esi,%esi
3.03 5.60 7.06 : 387dc0aa6d: movl $0x0,0x8(%rdx)
0.00 0.00 0.59 : 387dc0aa74: je 387dc0aa7a <__pthread_mutex_unlock_use
0.00 0.00 0.00 : 387dc0aa76: subl $0x1,0xc(%rdx)
2.02 5.60 1.18 : 387dc0aa7a: mov %edi,%esi
0.00 0.00 0.00 : 387dc0aa7c: lock decl (%rdx)
83.84 83.20 82.35 : 387dc0aa7f: jne 387dc0aada <_L_unlock_586>
0.00 0.00 0.00 : 387dc0aa81: nop
0.00 0.00 0.00 : 387dc0aa82: xor %eax,%eax
0.00 0.00 0.00 : 387dc0aa84: retq
...
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1362462812-30885-6-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-03-05 13:53:25 +08:00
|
|
|
|
|
|
|
|
if (symbol_conf.event_group &&
|
|
|
|
|
!perf_evsel__is_group_leader(pos))
|
|
|
|
|
continue;
|
|
|
|
|
|
2013-03-05 13:53:21 +08:00
|
|
|
hists__find_annotations(hists, pos, ann);
|
2011-03-06 08:40:06 +08:00
|
|
|
}
|
|
|
|
|
}
|
2009-06-06 21:19:13 +08:00
|
|
|
|
2011-03-06 08:40:06 +08:00
|
|
|
if (total_nr_samples == 0) {
|
2014-08-12 14:40:35 +08:00
|
|
|
ui__error("The %s file has no samples!\n", session->file->path);
|
|
|
|
|
goto out;
|
2011-03-06 08:40:06 +08:00
|
|
|
}
|
2013-02-07 17:02:09 +08:00
|
|
|
|
2013-09-13 14:27:43 +08:00
|
|
|
if (use_browser == 2) {
|
|
|
|
|
void (*show_annotations)(void);
|
|
|
|
|
|
|
|
|
|
show_annotations = dlsym(perf_gtk_handle,
|
|
|
|
|
"perf_gtk__show_annotations");
|
|
|
|
|
if (show_annotations == NULL) {
|
|
|
|
|
ui__error("GTK browser not found!\n");
|
2014-08-12 14:40:35 +08:00
|
|
|
goto out;
|
2013-09-13 14:27:43 +08:00
|
|
|
}
|
|
|
|
|
show_annotations();
|
|
|
|
|
}
|
2013-02-07 17:02:09 +08:00
|
|
|
|
2014-08-12 14:40:35 +08:00
|
|
|
out:
|
2009-12-01 14:04:49 +08:00
|
|
|
return ret;
|
2009-06-06 21:19:13 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static const char * const annotate_usage[] = {
|
2012-01-08 01:25:30 +08:00
|
|
|
"perf annotate [<options>]",
|
2009-06-06 21:19:13 +08:00
|
|
|
NULL
|
|
|
|
|
};
|
|
|
|
|
|
2017-03-27 22:47:20 +08:00
|
|
|
int cmd_annotate(int argc, const char **argv)
|
2011-11-25 18:19:45 +08:00
|
|
|
{
|
|
|
|
|
struct perf_annotate annotate = {
|
2011-11-28 18:30:20 +08:00
|
|
|
.tool = {
|
2011-11-25 18:19:45 +08:00
|
|
|
.sample = process_sample_event,
|
|
|
|
|
.mmap = perf_event__process_mmap,
|
2013-08-21 18:10:25 +08:00
|
|
|
.mmap2 = perf_event__process_mmap2,
|
2011-11-25 18:19:45 +08:00
|
|
|
.comm = perf_event__process_comm,
|
2012-10-07 02:53:41 +08:00
|
|
|
.exit = perf_event__process_exit,
|
2012-10-07 02:44:59 +08:00
|
|
|
.fork = perf_event__process_fork,
|
perf tools: Add PERF_RECORD_NAMESPACES to include namespaces related info
Introduce a new option to record PERF_RECORD_NAMESPACES events emitted
by the kernel when fork, clone, setns or unshare are invoked. And update
perf-record documentation with the new option to record namespace
events.
Committer notes:
Combined it with a later patch to allow printing it via 'perf report -D'
and be able to test the feature introduced in this patch. Had to move
here also perf_ns__name(), that was introduced in another later patch.
Also used PRIu64 and PRIx64 to fix the build in some enfironments wrt:
util/event.c:1129:39: error: format '%lx' expects argument of type 'long unsigned int', but argument 6 has type 'long long unsigned int' [-Werror=format=]
ret += fprintf(fp, "%u/%s: %lu/0x%lx%s", idx
^
Testing it:
# perf record --namespaces -a
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 1.083 MB perf.data (423 samples) ]
#
# perf report -D
<SNIP>
3 2028902078892 0x115140 [0xa0]: PERF_RECORD_NAMESPACES 14783/14783 - nr_namespaces: 7
[0/net: 3/0xf0000081, 1/uts: 3/0xeffffffe, 2/ipc: 3/0xefffffff, 3/pid: 3/0xeffffffc,
4/user: 3/0xeffffffd, 5/mnt: 3/0xf0000000, 6/cgroup: 3/0xeffffffb]
0x1151e0 [0x30]: event: 9
.
. ... raw event: size 48 bytes
. 0000: 09 00 00 00 02 00 30 00 c4 71 82 68 0c 7f 00 00 ......0..q.h....
. 0010: a9 39 00 00 a9 39 00 00 94 28 fe 63 d8 01 00 00 .9...9...(.c....
. 0020: 03 00 00 00 00 00 00 00 ce c4 02 00 00 00 00 00 ................
<SNIP>
NAMESPACES events: 1
<SNIP>
#
Signed-off-by: Hari Bathini <hbathini@linux.vnet.ibm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@fb.com>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Aravinda Prasad <aravinda@linux.vnet.ibm.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sargun Dhillon <sargun@sargun.me>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/148891930386.25309.18412039920746995488.stgit@hbathini.in.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-08 04:41:43 +08:00
|
|
|
.namespaces = perf_event__process_namespaces,
|
perf annotate: Process attr and build_id records
perf annotate did not get some love for pipe-mode, and did not have
.attr and .buil_id setup (while record and inject did. Fix that.
It can easily be reproduced by:
perf record -o - noploop | perf annotate
that in my system shows:
0xd8 [0x28]: failed to process type: 9
Committer Testing:
Before:
$ perf record -o - stress -t 2 -c 2 | perf annotate --stdio
stress: info: [11060] dispatching hogs: 2 cpu, 0 io, 0 vm, 0 hdd
0x4470 [0x28]: failed to process type: 9
$ stress: info: [11060] successful run completed in 2s
$
After:
$ perf record -o - stress -t 2 -c 2 | perf annotate --stdio
stress: info: [11871] dispatching hogs: 2 cpu, 0 io, 0 vm, 0 hdd
stress: info: [11871] successful run completed in 2s
[ perf record: Woken up 2 times to write data ]
[ perf record: Captured and wrote 0.000 MB - ]
no symbols found in /usr/bin/stress, maybe install a debug package?
Percent | Source code & Disassembly of libc-2.24.so for cycles:uhH (6117 samples)
---------------------------------------------------------------------------------------
:
: Disassembly of section .text:
:
: 000000000003b050 <random_r>:
: __random_r():
10.56 : 3b050: test %rdi,%rdi
0.00 : 3b053: je 3b0d0 <random_r+0x80>
0.34 : 3b055: test %rsi,%rsi
0.00 : 3b058: je 3b0d0 <random_r+0x80>
0.46 : 3b05a: mov 0x18(%rdi),%eax
12.44 : 3b05d: mov 0x10(%rdi),%r8
0.18 : 3b061: test %eax,%eax
0.00 : 3b063: je 3b0b0 <random_r+0x60>
<SNIP>
Signed-off-by: David Carrillo-Cisneros <davidcc@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Paul Turner <pjt@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Simon Que <sque@chromium.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/20170410201432.24807-5-davidcc@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-04-11 04:14:29 +08:00
|
|
|
.attr = perf_event__process_attr,
|
|
|
|
|
.build_id = perf_event__process_build_id,
|
perf tools: Add feature header record to pipe-mode
Add header record types to pipe-mode, reusing the functions
used in file-mode and leveraging the new struct feat_fd.
For alignment, check that synthesized events don't exceed
pagesize.
Add the perf_event__synthesize_feature event call back to
process the new header records.
Before this patch:
$ perf record -o - -e cycles sleep 1 | perf report --stdio --header
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.000 MB - ]
...
After this patch:
$ perf record -o - -e cycles sleep 1 | perf report --stdio --header
# ========
# captured on: Mon May 22 16:33:43 2017
# ========
#
# hostname : my_hostname
# os release : 4.11.0-dbx-up_perf
# perf version : 4.11.rc6.g6277c80
# arch : x86_64
# nrcpus online : 72
# nrcpus avail : 72
# cpudesc : Intel(R) Xeon(R) CPU E5-2696 v3 @ 2.30GHz
# cpuid : GenuineIntel,6,63,2
# total memory : 263457192 kB
# cmdline : /root/perf record -o - -e cycles -c 100000 sleep 1
# HEADER_CPU_TOPOLOGY info available, use -I to display
# HEADER_NUMA_TOPOLOGY info available, use -I to display
# pmu mappings: intel_bts = 6, uncore_imc_4 = 22, uncore_sbox_1 = 47, uncore_cbox_5 = 33, uncore_ha_0 = 16, uncore_cbox
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.000 MB - ]
...
Support added for the subcommands: report, inject, annotate and script.
Signed-off-by: David Carrillo-Cisneros <davidcc@google.com>
Acked-by: David Ahern <dsahern@gmail.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Turner <pjt@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Simon Que <sque@chromium.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/20170718042549.145161-16-davidcc@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-07-18 12:25:48 +08:00
|
|
|
.feature = perf_event__process_feature,
|
2014-07-06 20:18:21 +08:00
|
|
|
.ordered_events = true,
|
2011-11-25 18:19:45 +08:00
|
|
|
.ordering_requires_timestamps = true,
|
|
|
|
|
},
|
|
|
|
|
};
|
2014-08-12 14:40:35 +08:00
|
|
|
struct perf_data_file file = {
|
|
|
|
|
.mode = PERF_DATA_MODE_READ,
|
|
|
|
|
};
|
2011-11-25 18:19:45 +08:00
|
|
|
const struct option options[] = {
|
2012-10-30 11:56:02 +08:00
|
|
|
OPT_STRING('i', "input", &input_name, "file",
|
2009-06-06 21:19:13 +08:00
|
|
|
"input file name"),
|
2010-03-25 03:40:16 +08:00
|
|
|
OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]",
|
|
|
|
|
"only consider symbols in these dsos"),
|
2011-11-17 22:33:21 +08:00
|
|
|
OPT_STRING('s', "symbol", &annotate.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"),
|
2014-08-12 14:40:35 +08:00
|
|
|
OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
|
2010-04-13 16:37:33 +08:00
|
|
|
OPT_INCR('v', "verbose", &verbose,
|
2009-06-06 21:19:13 +08:00
|
|
|
"be more verbose (show symbol address, etc)"),
|
2017-02-17 16:17:41 +08:00
|
|
|
OPT_BOOLEAN('q', "quiet", &quiet, "do now show any message"),
|
2009-06-06 21:19:13 +08:00
|
|
|
OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
|
|
|
|
|
"dump raw trace in ASCII"),
|
2013-02-07 17:02:08 +08:00
|
|
|
OPT_BOOLEAN(0, "gtk", &annotate.use_gtk, "Use the GTK interface"),
|
2011-11-17 22:33:21 +08:00
|
|
|
OPT_BOOLEAN(0, "tui", &annotate.use_tui, "Use the TUI interface"),
|
|
|
|
|
OPT_BOOLEAN(0, "stdio", &annotate.use_stdio, "Use the stdio interface"),
|
2009-11-24 22:05:15 +08:00
|
|
|
OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
|
|
|
|
|
"file", "vmlinux pathname"),
|
|
|
|
|
OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules,
|
2009-07-02 14:09:46 +08:00
|
|
|
"load module symbols - WARNING: use only with -k and LIVE kernel"),
|
2011-11-17 22:33:21 +08:00
|
|
|
OPT_BOOLEAN('l', "print-line", &annotate.print_line,
|
2009-06-13 06:11:21 +08:00
|
|
|
"print matching source lines (may be slow)"),
|
2011-11-17 22:33:21 +08:00
|
|
|
OPT_BOOLEAN('P', "full-paths", &annotate.full_paths,
|
2009-07-02 14:09:46 +08:00
|
|
|
"Don't shorten the displayed pathnames"),
|
2013-02-07 17:02:14 +08:00
|
|
|
OPT_BOOLEAN(0, "skip-missing", &annotate.skip_missing,
|
|
|
|
|
"Skip symbols that cannot be annotated"),
|
2011-11-14 02:30:08 +08:00
|
|
|
OPT_STRING('C', "cpu", &annotate.cpu_list, "cpu", "list of cpus to profile"),
|
2016-05-19 19:47:37 +08:00
|
|
|
OPT_CALLBACK(0, "symfs", NULL, "directory",
|
|
|
|
|
"Look for files with symbols relative to this directory",
|
|
|
|
|
symbol__config_symfs),
|
2011-10-06 23:48:31 +08:00
|
|
|
OPT_BOOLEAN(0, "source", &symbol_conf.annotate_src,
|
2011-05-17 23:32:07 +08:00
|
|
|
"Interleave source code with assembly code (default)"),
|
2011-10-06 23:48:31 +08:00
|
|
|
OPT_BOOLEAN(0, "asm-raw", &symbol_conf.annotate_asm_raw,
|
2011-05-17 23:32:07 +08:00
|
|
|
"Display raw encoding of assembly instructions (default)"),
|
2011-09-16 05:31:41 +08:00
|
|
|
OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
|
|
|
|
|
"Specify disassembler style (e.g. -M intel for intel syntax)"),
|
2012-09-04 18:32:30 +08:00
|
|
|
OPT_STRING(0, "objdump", &objdump_path, "path",
|
|
|
|
|
"objdump binary to use for disassembly and annotations"),
|
perf annotate: Add basic support to event group view
Add --group option to enable event grouping. When enabled, all the
group members information will be shown with the leader so skip
non-leader events.
It only supports --stdio output currently. Later patches will extend
additional features.
$ perf annotate --group --stdio
...
Percent | Source code & Disassembly of libpthread-2.15.so
--------------------------------------------------------------------------------
:
:
:
: Disassembly of section .text:
:
: 000000387dc0aa50 <__pthread_mutex_unlock_usercnt>:
8.08 2.40 5.29 : 387dc0aa50: mov %rdi,%rdx
0.00 0.00 0.00 : 387dc0aa53: mov 0x10(%rdi),%edi
0.00 0.00 0.00 : 387dc0aa56: mov %edi,%eax
0.00 0.80 0.00 : 387dc0aa58: and $0x7f,%eax
3.03 2.40 3.53 : 387dc0aa5b: test $0x7c,%dil
0.00 0.00 0.00 : 387dc0aa5f: jne 387dc0aaa9 <__pthread_mutex_unlock_use
0.00 0.00 0.00 : 387dc0aa61: test %eax,%eax
0.00 0.00 0.00 : 387dc0aa63: jne 387dc0aa85 <__pthread_mutex_unlock_use
0.00 0.00 0.00 : 387dc0aa65: and $0x80,%edi
0.00 0.00 0.00 : 387dc0aa6b: test %esi,%esi
3.03 5.60 7.06 : 387dc0aa6d: movl $0x0,0x8(%rdx)
0.00 0.00 0.59 : 387dc0aa74: je 387dc0aa7a <__pthread_mutex_unlock_use
0.00 0.00 0.00 : 387dc0aa76: subl $0x1,0xc(%rdx)
2.02 5.60 1.18 : 387dc0aa7a: mov %edi,%esi
0.00 0.00 0.00 : 387dc0aa7c: lock decl (%rdx)
83.84 83.20 82.35 : 387dc0aa7f: jne 387dc0aada <_L_unlock_586>
0.00 0.00 0.00 : 387dc0aa81: nop
0.00 0.00 0.00 : 387dc0aa82: xor %eax,%eax
0.00 0.00 0.00 : 387dc0aa84: retq
...
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1362462812-30885-6-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-03-05 13:53:25 +08:00
|
|
|
OPT_BOOLEAN(0, "group", &symbol_conf.event_group,
|
|
|
|
|
"Show event group information together"),
|
2015-06-20 03:10:43 +08:00
|
|
|
OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
|
|
|
|
|
"Show a column with the sum of periods"),
|
2016-07-05 22:08:17 +08:00
|
|
|
OPT_CALLBACK_DEFAULT(0, "stdio-color", NULL, "mode",
|
|
|
|
|
"'always' (default), 'never' or 'auto' only applicable to --stdio mode",
|
|
|
|
|
stdio__config_color, "always"),
|
2009-06-06 21:19:13 +08:00
|
|
|
OPT_END()
|
2011-11-25 18:19:45 +08:00
|
|
|
};
|
2014-10-10 03:16:00 +08:00
|
|
|
int ret = hists__init();
|
|
|
|
|
|
|
|
|
|
if (ret < 0)
|
|
|
|
|
return ret;
|
2009-06-06 21:19:13 +08:00
|
|
|
|
2009-12-16 06:04:40 +08:00
|
|
|
argc = parse_options(argc, argv, options, annotate_usage, 0);
|
2015-12-10 11:00:53 +08:00
|
|
|
if (argc) {
|
|
|
|
|
/*
|
|
|
|
|
* Special case: if there's an argument left then assume that
|
|
|
|
|
* it's a symbol filter:
|
|
|
|
|
*/
|
|
|
|
|
if (argc > 1)
|
|
|
|
|
usage_with_options(annotate_usage, options);
|
|
|
|
|
|
|
|
|
|
annotate.sym_hist_filter = argv[0];
|
|
|
|
|
}
|
2009-12-16 06:04:40 +08:00
|
|
|
|
2017-02-17 16:17:41 +08:00
|
|
|
if (quiet)
|
|
|
|
|
perf_quiet_option();
|
|
|
|
|
|
2015-05-29 20:06:44 +08:00
|
|
|
file.path = input_name;
|
|
|
|
|
|
2014-08-12 14:40:35 +08:00
|
|
|
annotate.session = perf_session__new(&file, false, &annotate.tool);
|
|
|
|
|
if (annotate.session == NULL)
|
2014-09-24 09:33:37 +08:00
|
|
|
return -1;
|
2014-08-12 14:40:35 +08:00
|
|
|
|
2016-08-26 03:09:21 +08:00
|
|
|
ret = symbol__annotation_init();
|
|
|
|
|
if (ret < 0)
|
|
|
|
|
goto out_delete;
|
|
|
|
|
|
2009-12-16 06:04:39 +08:00
|
|
|
symbol_conf.try_vmlinux_path = true;
|
|
|
|
|
|
2014-08-12 14:40:45 +08:00
|
|
|
ret = symbol__init(&annotate.session->header.env);
|
2014-08-12 14:40:35 +08:00
|
|
|
if (ret < 0)
|
|
|
|
|
goto out_delete;
|
2009-06-06 21:19:13 +08:00
|
|
|
|
2015-12-23 01:07:01 +08:00
|
|
|
if (setup_sorting(NULL) < 0)
|
2013-02-06 13:57:16 +08:00
|
|
|
usage_with_options(annotate_usage, options);
|
2009-06-06 21:19:13 +08:00
|
|
|
|
2015-12-10 11:00:54 +08:00
|
|
|
if (annotate.use_stdio)
|
|
|
|
|
use_browser = 0;
|
|
|
|
|
else if (annotate.use_tui)
|
|
|
|
|
use_browser = 1;
|
|
|
|
|
else if (annotate.use_gtk)
|
|
|
|
|
use_browser = 2;
|
|
|
|
|
|
|
|
|
|
setup_browser(true);
|
|
|
|
|
|
2014-08-12 14:40:35 +08:00
|
|
|
ret = __cmd_annotate(&annotate);
|
|
|
|
|
|
|
|
|
|
out_delete:
|
|
|
|
|
/*
|
|
|
|
|
* Speed up the exit process, for large files this can
|
|
|
|
|
* take quite a while.
|
|
|
|
|
*
|
|
|
|
|
* XXX Enable this when using valgrind or if we ever
|
|
|
|
|
* librarize this command.
|
|
|
|
|
*
|
|
|
|
|
* Also experiment with obstacks to see how much speed
|
|
|
|
|
* up we'll get here.
|
|
|
|
|
*
|
|
|
|
|
* perf_session__delete(session);
|
|
|
|
|
*/
|
|
|
|
|
return ret;
|
2009-06-06 21:19:13 +08:00
|
|
|
}
|