2009-06-26 22:28:00 +08:00
|
|
|
#ifndef __PERF_CALLCHAIN_H
|
|
|
|
#define __PERF_CALLCHAIN_H
|
|
|
|
|
|
|
|
#include "../perf.h"
|
2009-07-02 01:46:08 +08:00
|
|
|
#include <linux/list.h>
|
2009-07-01 23:28:37 +08:00
|
|
|
#include <linux/rbtree.h>
|
2010-05-09 22:47:13 +08:00
|
|
|
#include "event.h"
|
2017-01-06 14:23:31 +08:00
|
|
|
#include "map.h"
|
2009-07-01 11:35:14 +08:00
|
|
|
#include "symbol.h"
|
2017-07-18 20:13:15 +08:00
|
|
|
#include "branch.h"
|
2009-06-26 22:28:00 +08:00
|
|
|
|
perf tools: Improve call graph documents and help messages
The --call-graph option is complex so we should provide better guide for
users. Also change help message to be consistent with config option
names. Now perf top will show help like below:
$ perf top --call-graph
Error: option `call-graph' requires a value
Usage: perf top [<options>]
--call-graph <record_mode[,record_size],print_type,threshold[,print_limit],order,sort_key[,branch]>
setup and enables call-graph (stack chain/backtrace):
record_mode: call graph recording mode (fp|dwarf|lbr)
record_size: if record_mode is 'dwarf', max size of stack recording (<bytes>)
default: 8192 (bytes)
print_type: call graph printing style (graph|flat|fractal|none)
threshold: minimum call graph inclusion threshold (<percent>)
print_limit: maximum number of call graph entry (<number>)
order: call graph order (caller|callee)
sort_key: call graph sort key (function|address)
branch: include last branch info to call graph (branch)
Default: fp,graph,0.5,caller,function
Requested-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Chandler Carruth <chandlerc@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1445524112-5201-2-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-10-22 22:28:32 +08:00
|
|
|
#define HELP_PAD "\t\t\t\t"
|
|
|
|
|
|
|
|
#define CALLCHAIN_HELP "setup and enables call-graph (stack chain/backtrace):\n\n"
|
2015-10-22 14:28:48 +08:00
|
|
|
|
perf tools: Improve call graph documents and help messages
The --call-graph option is complex so we should provide better guide for
users. Also change help message to be consistent with config option
names. Now perf top will show help like below:
$ perf top --call-graph
Error: option `call-graph' requires a value
Usage: perf top [<options>]
--call-graph <record_mode[,record_size],print_type,threshold[,print_limit],order,sort_key[,branch]>
setup and enables call-graph (stack chain/backtrace):
record_mode: call graph recording mode (fp|dwarf|lbr)
record_size: if record_mode is 'dwarf', max size of stack recording (<bytes>)
default: 8192 (bytes)
print_type: call graph printing style (graph|flat|fractal|none)
threshold: minimum call graph inclusion threshold (<percent>)
print_limit: maximum number of call graph entry (<number>)
order: call graph order (caller|callee)
sort_key: call graph sort key (function|address)
branch: include last branch info to call graph (branch)
Default: fp,graph,0.5,caller,function
Requested-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Chandler Carruth <chandlerc@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1445524112-5201-2-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-10-22 22:28:32 +08:00
|
|
|
# define RECORD_MODE_HELP HELP_PAD "record_mode:\tcall graph recording mode (fp|dwarf|lbr)\n"
|
2015-10-22 14:28:48 +08:00
|
|
|
|
perf tools: Improve call graph documents and help messages
The --call-graph option is complex so we should provide better guide for
users. Also change help message to be consistent with config option
names. Now perf top will show help like below:
$ perf top --call-graph
Error: option `call-graph' requires a value
Usage: perf top [<options>]
--call-graph <record_mode[,record_size],print_type,threshold[,print_limit],order,sort_key[,branch]>
setup and enables call-graph (stack chain/backtrace):
record_mode: call graph recording mode (fp|dwarf|lbr)
record_size: if record_mode is 'dwarf', max size of stack recording (<bytes>)
default: 8192 (bytes)
print_type: call graph printing style (graph|flat|fractal|none)
threshold: minimum call graph inclusion threshold (<percent>)
print_limit: maximum number of call graph entry (<number>)
order: call graph order (caller|callee)
sort_key: call graph sort key (function|address)
branch: include last branch info to call graph (branch)
Default: fp,graph,0.5,caller,function
Requested-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Chandler Carruth <chandlerc@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1445524112-5201-2-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-10-22 22:28:32 +08:00
|
|
|
#define RECORD_SIZE_HELP \
|
|
|
|
HELP_PAD "record_size:\tif record_mode is 'dwarf', max size of stack recording (<bytes>)\n" \
|
|
|
|
HELP_PAD "\t\tdefault: 8192 (bytes)\n"
|
|
|
|
|
|
|
|
#define CALLCHAIN_RECORD_HELP CALLCHAIN_HELP RECORD_MODE_HELP RECORD_SIZE_HELP
|
|
|
|
|
|
|
|
#define CALLCHAIN_REPORT_HELP \
|
2015-11-09 13:45:37 +08:00
|
|
|
HELP_PAD "print_type:\tcall graph printing style (graph|flat|fractal|folded|none)\n" \
|
perf tools: Improve call graph documents and help messages
The --call-graph option is complex so we should provide better guide for
users. Also change help message to be consistent with config option
names. Now perf top will show help like below:
$ perf top --call-graph
Error: option `call-graph' requires a value
Usage: perf top [<options>]
--call-graph <record_mode[,record_size],print_type,threshold[,print_limit],order,sort_key[,branch]>
setup and enables call-graph (stack chain/backtrace):
record_mode: call graph recording mode (fp|dwarf|lbr)
record_size: if record_mode is 'dwarf', max size of stack recording (<bytes>)
default: 8192 (bytes)
print_type: call graph printing style (graph|flat|fractal|none)
threshold: minimum call graph inclusion threshold (<percent>)
print_limit: maximum number of call graph entry (<number>)
order: call graph order (caller|callee)
sort_key: call graph sort key (function|address)
branch: include last branch info to call graph (branch)
Default: fp,graph,0.5,caller,function
Requested-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Chandler Carruth <chandlerc@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1445524112-5201-2-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-10-22 22:28:32 +08:00
|
|
|
HELP_PAD "threshold:\tminimum call graph inclusion threshold (<percent>)\n" \
|
|
|
|
HELP_PAD "print_limit:\tmaximum number of call graph entry (<number>)\n" \
|
|
|
|
HELP_PAD "order:\t\tcall graph order (caller|callee)\n" \
|
|
|
|
HELP_PAD "sort_key:\tcall graph sort key (function|address)\n" \
|
2015-11-09 13:45:41 +08:00
|
|
|
HELP_PAD "branch:\t\tinclude last branch info to call graph (branch)\n" \
|
|
|
|
HELP_PAD "value:\t\tcall graph value (percent|period|count)\n"
|
2015-10-22 14:28:48 +08:00
|
|
|
|
2014-05-05 18:46:17 +08:00
|
|
|
enum perf_call_graph_mode {
|
|
|
|
CALLCHAIN_NONE,
|
|
|
|
CALLCHAIN_FP,
|
|
|
|
CALLCHAIN_DWARF,
|
2015-01-06 02:23:04 +08:00
|
|
|
CALLCHAIN_LBR,
|
2014-05-05 18:46:17 +08:00
|
|
|
CALLCHAIN_MAX
|
|
|
|
};
|
|
|
|
|
2009-07-02 23:58:21 +08:00
|
|
|
enum chain_mode {
|
2009-08-08 08:16:24 +08:00
|
|
|
CHAIN_NONE,
|
2009-07-05 13:39:21 +08:00
|
|
|
CHAIN_FLAT,
|
|
|
|
CHAIN_GRAPH_ABS,
|
2015-11-09 13:45:37 +08:00
|
|
|
CHAIN_GRAPH_REL,
|
|
|
|
CHAIN_FOLDED,
|
2009-07-02 23:58:21 +08:00
|
|
|
};
|
2009-06-26 22:28:00 +08:00
|
|
|
|
2011-06-07 23:49:46 +08:00
|
|
|
enum chain_order {
|
|
|
|
ORDER_CALLER,
|
|
|
|
ORDER_CALLEE
|
|
|
|
};
|
|
|
|
|
2009-06-26 22:28:00 +08:00
|
|
|
struct callchain_node {
|
|
|
|
struct callchain_node *parent;
|
2009-07-01 18:37:06 +08:00
|
|
|
struct list_head val;
|
2015-11-09 13:45:43 +08:00
|
|
|
struct list_head parent_val;
|
2013-10-11 13:15:36 +08:00
|
|
|
struct rb_node rb_node_in; /* to insert nodes in an rbtree */
|
|
|
|
struct rb_node rb_node; /* to sort nodes in an output tree */
|
|
|
|
struct rb_root rb_root_in; /* input tree of children */
|
|
|
|
struct rb_root rb_root; /* sorted output tree of children */
|
2009-07-01 18:37:06 +08:00
|
|
|
unsigned int val_nr;
|
2015-11-09 13:45:40 +08:00
|
|
|
unsigned int count;
|
|
|
|
unsigned int children_count;
|
2009-07-01 18:37:06 +08:00
|
|
|
u64 hit;
|
2009-08-07 13:11:05 +08:00
|
|
|
u64 children_hit;
|
2009-06-26 22:28:00 +08:00
|
|
|
};
|
|
|
|
|
2010-08-23 02:05:22 +08:00
|
|
|
struct callchain_root {
|
|
|
|
u64 max_depth;
|
|
|
|
struct callchain_node node;
|
|
|
|
};
|
|
|
|
|
2009-07-05 13:39:21 +08:00
|
|
|
struct callchain_param;
|
|
|
|
|
2010-08-23 02:05:22 +08:00
|
|
|
typedef void (*sort_chain_func_t)(struct rb_root *, struct callchain_root *,
|
2009-07-05 13:39:21 +08:00
|
|
|
u64, struct callchain_param *);
|
|
|
|
|
2013-07-19 06:33:57 +08:00
|
|
|
enum chain_key {
|
|
|
|
CCKEY_FUNCTION,
|
2017-03-19 05:49:28 +08:00
|
|
|
CCKEY_ADDRESS,
|
|
|
|
CCKEY_SRCLINE
|
2013-07-19 06:33:57 +08:00
|
|
|
};
|
|
|
|
|
2015-11-09 13:45:41 +08:00
|
|
|
enum chain_value {
|
|
|
|
CCVAL_PERCENT,
|
|
|
|
CCVAL_PERIOD,
|
|
|
|
CCVAL_COUNT,
|
|
|
|
};
|
|
|
|
|
2009-07-05 13:39:21 +08:00
|
|
|
struct callchain_param {
|
2014-09-23 09:01:41 +08:00
|
|
|
bool enabled;
|
|
|
|
enum perf_call_graph_mode record_mode;
|
|
|
|
u32 dump_size;
|
2009-07-05 13:39:21 +08:00
|
|
|
enum chain_mode mode;
|
perf tools: Per event max-stack settings
The tooling counterpart, now it is possible to do:
# perf record -e sched:sched_switch/max-stack=10/ -e cycles/call-graph=dwarf,max-stack=4/ -e cpu-cycles/call-graph=dwarf,max-stack=1024/ usleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.052 MB perf.data (5 samples) ]
# perf evlist -v
sched:sched_switch: type: 2, size: 112, config: 0x110, { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|CALLCHAIN|CPU|PERIOD|RAW|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, sample_max_stack: 10
cycles/call-graph=dwarf,max-stack=4/: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CALLCHAIN|PERIOD|REGS_USER|STACK_USER|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, freq: 1, enable_on_exec: 1, sample_id_all: 1, exclude_guest: 1, exclude_callchain_user: 1, sample_regs_user: 0xff0fff, sample_stack_user: 8192, sample_max_stack: 4
cpu-cycles/call-graph=dwarf,max-stack=1024/: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CALLCHAIN|PERIOD|REGS_USER|STACK_USER|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, freq: 1, enable_on_exec: 1, sample_id_all: 1, exclude_guest: 1, exclude_callchain_user: 1, sample_regs_user: 0xff0fff, sample_stack_user: 8192, sample_max_stack: 1024
# Tip: use 'perf evlist --trace-fields' to show fields for tracepoint events
Using just /max-stack=N/ means /call-graph=fp,max-stack=N/, that should
be further configurable by means of some .perfconfig knob.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Zefan Li <lizefan@huawei.com>
Link: http://lkml.kernel.org/n/tip-kolmn1yo40p7jhswxwrc7rrd@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-29 06:03:42 +08:00
|
|
|
u16 max_stack;
|
2010-05-10 07:28:10 +08:00
|
|
|
u32 print_limit;
|
2009-07-05 13:39:21 +08:00
|
|
|
double min_percent;
|
|
|
|
sort_chain_func_t sort;
|
2011-06-07 23:49:46 +08:00
|
|
|
enum chain_order order;
|
2015-10-22 15:45:46 +08:00
|
|
|
bool order_set;
|
2013-07-19 06:33:57 +08:00
|
|
|
enum chain_key key;
|
perf callchain: Support handling complete branch stacks as histograms
Currently branch stacks can be only shown as edge histograms for
individual branches. I never found this display particularly useful.
This implements an alternative mode that creates histograms over
complete branch traces, instead of individual branches, similar to how
normal callgraphs are handled. This is done by putting it in front of
the normal callgraph and then using the normal callgraph histogram
infrastructure to unify them.
This way in complex functions we can understand the control flow that
lead to a particular sample, and may even see some control flow in the
caller for short functions.
Example (simplified, of course for such simple code this is usually not
needed), please run this after the whole patchkit is in, as at this
point in the patch order there is no --branch-history, that will be
added in a patch after this one:
tcall.c:
volatile a = 10000, b = 100000, c;
__attribute__((noinline)) f2()
{
c = a / b;
}
__attribute__((noinline)) f1()
{
f2();
f2();
}
main()
{
int i;
for (i = 0; i < 1000000; i++)
f1();
}
% perf record -b -g ./tsrc/tcall
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.044 MB perf.data (~1923 samples) ]
% perf report --no-children --branch-history
...
54.91% tcall.c:6 [.] f2 tcall
|
|--65.53%-- f2 tcall.c:5
| |
| |--70.83%-- f1 tcall.c:11
| | f1 tcall.c:10
| | main tcall.c:18
| | main tcall.c:18
| | main tcall.c:17
| | main tcall.c:17
| | f1 tcall.c:13
| | f1 tcall.c:13
| | f2 tcall.c:7
| | f2 tcall.c:5
| | f1 tcall.c:12
| | f1 tcall.c:12
| | f2 tcall.c:7
| | f2 tcall.c:5
| | f1 tcall.c:11
| |
| --29.17%-- f1 tcall.c:12
| f1 tcall.c:12
| f2 tcall.c:7
| f2 tcall.c:5
| f1 tcall.c:11
| f1 tcall.c:10
| main tcall.c:18
| main tcall.c:18
| main tcall.c:17
| main tcall.c:17
| f1 tcall.c:13
| f1 tcall.c:13
| f2 tcall.c:7
| f2 tcall.c:5
| f1 tcall.c:12
The default output is unchanged.
This is only implemented in perf report, no change to record or anywhere
else.
This adds the basic code to report:
- add a new "branch" option to the -g option parser to enable this mode
- when the flag is set include the LBR into the callstack in machine.c.
The rest of the history code is unchanged and doesn't know the
difference between LBR entry and normal call entry.
- detect overlaps with the callchain
- remove small loop duplicates in the LBR
Current limitations:
- The LBR flags (mispredict etc.) are not shown in the history
and LBR entries have no special marker.
- It would be nice if annotate marked the LBR entries somehow
(e.g. with arrows)
v2: Various fixes.
v3: Merge further patches into this one. Fix white space.
v4: Improve manpage. Address review feedback.
v5: Rename functions. Better error message without -g. Fix crash without
-b.
v6: Rebase
v7: Rebase. Use NO_ENTRY in memset.
v8: Port to latest tip. Move add_callchain_ip to separate
patch. Skip initial entries in callchain. Minor cleanups.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/1415844328-4884-3-git-send-email-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-11-13 10:05:20 +08:00
|
|
|
bool branch_callstack;
|
2015-11-09 13:45:41 +08:00
|
|
|
enum chain_value value;
|
2009-07-05 13:39:21 +08:00
|
|
|
};
|
|
|
|
|
2014-10-10 03:12:24 +08:00
|
|
|
extern struct callchain_param callchain_param;
|
2016-07-04 20:16:21 +08:00
|
|
|
extern struct callchain_param callchain_param_default;
|
2014-10-10 03:12:24 +08:00
|
|
|
|
2009-06-26 22:28:00 +08:00
|
|
|
struct callchain_list {
|
2009-07-01 18:37:06 +08:00
|
|
|
u64 ip;
|
2010-03-25 03:40:18 +08:00
|
|
|
struct map_symbol ms;
|
2015-05-05 22:55:46 +08:00
|
|
|
struct /* for TUI */ {
|
|
|
|
bool unfolded;
|
|
|
|
bool has_children;
|
|
|
|
};
|
2016-10-31 09:19:51 +08:00
|
|
|
u64 branch_count;
|
|
|
|
u64 predicted_count;
|
|
|
|
u64 abort_count;
|
|
|
|
u64 cycles_count;
|
|
|
|
u64 iter_count;
|
|
|
|
u64 samples_count;
|
2017-07-18 20:13:15 +08:00
|
|
|
struct branch_type_stat brtype_stat;
|
2014-11-13 10:05:24 +08:00
|
|
|
char *srcline;
|
2009-06-26 22:28:00 +08:00
|
|
|
struct list_head list;
|
|
|
|
};
|
|
|
|
|
2011-01-14 11:51:58 +08:00
|
|
|
/*
|
|
|
|
* A callchain cursor is a single linked list that
|
|
|
|
* let one feed a callchain progressively.
|
2012-07-18 00:20:59 +08:00
|
|
|
* It keeps persistent allocated entries to minimize
|
2011-01-14 11:51:58 +08:00
|
|
|
* allocations.
|
|
|
|
*/
|
|
|
|
struct callchain_cursor_node {
|
|
|
|
u64 ip;
|
|
|
|
struct map *map;
|
|
|
|
struct symbol *sym;
|
perf report: Add branch flag to callchain cursor node
Since the branch ip has been added to call stack for easier browsing,
this patch adds more branch information. For example, add a flag to
indicate if this ip is a branch, and also add with the branch flag.
Then we can know if the cursor node represents a branch and know what
the branch flag it has.
The branch history code has a loop detection pass that removes loops. It
would be nice for knowing how many loops were removed then in next
steps, we can compute out the average number of iterations.
For example:
Before remove_loops(),
entry0: from = 0x100, to = 0x200
entry1: from = 0x300, to = 0x250
entry2: from = 0x300, to = 0x250
entry3: from = 0x300, to = 0x250
entry4: from = 0x700, to = 0x800
After remove_loops()
entry0: from = 0x100, to = 0x200
entry1: from = 0x300, to = 0x250
entry2: from = 0x700, to = 0x800
The original entry2 and entry3 are removed. So the number of iterations
(from = 0x300, to = 0x250) is equal to removed number + 1 (2 + 1).
iterations = removed number + 1;
average iteractions = Sum(iteractions) / number of samples
This formula ignores other cases, for example, iterations cross multiple
buffers and one buffer contains 2+ loops. Because in practice, it's good
enough.
Signed-off-by: Yao Jin <yao.jin@linux.intel.com>
Acked-by: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linux-kernel@vger.kernel.org
Cc: Yao Jin <yao.jin@linux.intel.com>
Link: http://lkml.kernel.org/n/1477876794-30749-2-git-send-email-yao.jin@linux.intel.com
[ Renamed 'iter' to 'nr_loop_iter' for clarity ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-10-31 09:19:49 +08:00
|
|
|
bool branch;
|
|
|
|
struct branch_flags branch_flags;
|
2017-07-18 20:13:15 +08:00
|
|
|
u64 branch_from;
|
perf report: Add branch flag to callchain cursor node
Since the branch ip has been added to call stack for easier browsing,
this patch adds more branch information. For example, add a flag to
indicate if this ip is a branch, and also add with the branch flag.
Then we can know if the cursor node represents a branch and know what
the branch flag it has.
The branch history code has a loop detection pass that removes loops. It
would be nice for knowing how many loops were removed then in next
steps, we can compute out the average number of iterations.
For example:
Before remove_loops(),
entry0: from = 0x100, to = 0x200
entry1: from = 0x300, to = 0x250
entry2: from = 0x300, to = 0x250
entry3: from = 0x300, to = 0x250
entry4: from = 0x700, to = 0x800
After remove_loops()
entry0: from = 0x100, to = 0x200
entry1: from = 0x300, to = 0x250
entry2: from = 0x700, to = 0x800
The original entry2 and entry3 are removed. So the number of iterations
(from = 0x300, to = 0x250) is equal to removed number + 1 (2 + 1).
iterations = removed number + 1;
average iteractions = Sum(iteractions) / number of samples
This formula ignores other cases, for example, iterations cross multiple
buffers and one buffer contains 2+ loops. Because in practice, it's good
enough.
Signed-off-by: Yao Jin <yao.jin@linux.intel.com>
Acked-by: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linux-kernel@vger.kernel.org
Cc: Yao Jin <yao.jin@linux.intel.com>
Link: http://lkml.kernel.org/n/1477876794-30749-2-git-send-email-yao.jin@linux.intel.com
[ Renamed 'iter' to 'nr_loop_iter' for clarity ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-10-31 09:19:49 +08:00
|
|
|
int nr_loop_iter;
|
|
|
|
int samples;
|
2011-01-14 11:51:58 +08:00
|
|
|
struct callchain_cursor_node *next;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct callchain_cursor {
|
|
|
|
u64 nr;
|
|
|
|
struct callchain_cursor_node *first;
|
|
|
|
struct callchain_cursor_node **last;
|
|
|
|
u64 pos;
|
|
|
|
struct callchain_cursor_node *curr;
|
|
|
|
};
|
|
|
|
|
2012-05-31 13:43:26 +08:00
|
|
|
extern __thread struct callchain_cursor callchain_cursor;
|
|
|
|
|
2010-08-23 02:05:22 +08:00
|
|
|
static inline void callchain_init(struct callchain_root *root)
|
2009-06-26 22:28:00 +08:00
|
|
|
{
|
2010-08-23 02:05:22 +08:00
|
|
|
INIT_LIST_HEAD(&root->node.val);
|
2015-11-21 18:23:55 +08:00
|
|
|
INIT_LIST_HEAD(&root->node.parent_val);
|
2010-07-08 12:06:17 +08:00
|
|
|
|
2010-08-23 02:05:22 +08:00
|
|
|
root->node.parent = NULL;
|
|
|
|
root->node.hit = 0;
|
2010-08-27 08:28:40 +08:00
|
|
|
root->node.children_hit = 0;
|
2013-10-11 13:15:36 +08:00
|
|
|
root->node.rb_root_in = RB_ROOT;
|
2010-08-23 02:05:22 +08:00
|
|
|
root->max_depth = 0;
|
2009-06-26 22:28:00 +08:00
|
|
|
}
|
|
|
|
|
2011-01-14 11:51:59 +08:00
|
|
|
static inline u64 callchain_cumul_hits(struct callchain_node *node)
|
2009-08-07 13:11:05 +08:00
|
|
|
{
|
|
|
|
return node->hit + node->children_hit;
|
|
|
|
}
|
|
|
|
|
2015-11-09 13:45:40 +08:00
|
|
|
static inline unsigned callchain_cumul_counts(struct callchain_node *node)
|
|
|
|
{
|
|
|
|
return node->count + node->children_count;
|
|
|
|
}
|
|
|
|
|
2011-01-14 11:52:00 +08:00
|
|
|
int callchain_register_param(struct callchain_param *param);
|
2011-01-14 11:51:58 +08:00
|
|
|
int callchain_append(struct callchain_root *root,
|
|
|
|
struct callchain_cursor *cursor,
|
|
|
|
u64 period);
|
|
|
|
|
|
|
|
int callchain_merge(struct callchain_cursor *cursor,
|
|
|
|
struct callchain_root *dst, struct callchain_root *src);
|
2010-05-09 22:47:13 +08:00
|
|
|
|
2011-01-14 11:51:58 +08:00
|
|
|
/*
|
|
|
|
* Initialize a cursor before adding entries inside, but keep
|
|
|
|
* the previously allocated entries as a cache.
|
|
|
|
*/
|
|
|
|
static inline void callchain_cursor_reset(struct callchain_cursor *cursor)
|
|
|
|
{
|
2017-01-06 14:23:31 +08:00
|
|
|
struct callchain_cursor_node *node;
|
|
|
|
|
2011-01-14 11:51:58 +08:00
|
|
|
cursor->nr = 0;
|
|
|
|
cursor->last = &cursor->first;
|
2017-01-06 14:23:31 +08:00
|
|
|
|
|
|
|
for (node = cursor->first; node != NULL; node = node->next)
|
|
|
|
map__zput(node->map);
|
2011-01-14 11:51:58 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip,
|
perf report: Add branch flag to callchain cursor node
Since the branch ip has been added to call stack for easier browsing,
this patch adds more branch information. For example, add a flag to
indicate if this ip is a branch, and also add with the branch flag.
Then we can know if the cursor node represents a branch and know what
the branch flag it has.
The branch history code has a loop detection pass that removes loops. It
would be nice for knowing how many loops were removed then in next
steps, we can compute out the average number of iterations.
For example:
Before remove_loops(),
entry0: from = 0x100, to = 0x200
entry1: from = 0x300, to = 0x250
entry2: from = 0x300, to = 0x250
entry3: from = 0x300, to = 0x250
entry4: from = 0x700, to = 0x800
After remove_loops()
entry0: from = 0x100, to = 0x200
entry1: from = 0x300, to = 0x250
entry2: from = 0x700, to = 0x800
The original entry2 and entry3 are removed. So the number of iterations
(from = 0x300, to = 0x250) is equal to removed number + 1 (2 + 1).
iterations = removed number + 1;
average iteractions = Sum(iteractions) / number of samples
This formula ignores other cases, for example, iterations cross multiple
buffers and one buffer contains 2+ loops. Because in practice, it's good
enough.
Signed-off-by: Yao Jin <yao.jin@linux.intel.com>
Acked-by: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linux-kernel@vger.kernel.org
Cc: Yao Jin <yao.jin@linux.intel.com>
Link: http://lkml.kernel.org/n/1477876794-30749-2-git-send-email-yao.jin@linux.intel.com
[ Renamed 'iter' to 'nr_loop_iter' for clarity ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-10-31 09:19:49 +08:00
|
|
|
struct map *map, struct symbol *sym,
|
|
|
|
bool branch, struct branch_flags *flags,
|
2017-07-18 20:13:15 +08:00
|
|
|
int nr_loop_iter, int samples, u64 branch_from);
|
2011-01-14 11:51:58 +08:00
|
|
|
|
|
|
|
/* Close a cursor writing session. Initialize for the reader */
|
|
|
|
static inline void callchain_cursor_commit(struct callchain_cursor *cursor)
|
|
|
|
{
|
|
|
|
cursor->curr = cursor->first;
|
|
|
|
cursor->pos = 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Cursor reading iteration helpers */
|
|
|
|
static inline struct callchain_cursor_node *
|
|
|
|
callchain_cursor_current(struct callchain_cursor *cursor)
|
|
|
|
{
|
|
|
|
if (cursor->pos == cursor->nr)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
return cursor->curr;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void callchain_cursor_advance(struct callchain_cursor *cursor)
|
|
|
|
{
|
|
|
|
cursor->curr = cursor->curr->next;
|
|
|
|
cursor->pos++;
|
|
|
|
}
|
2012-12-12 03:46:05 +08:00
|
|
|
|
2016-12-06 11:40:02 +08:00
|
|
|
int callchain_cursor__copy(struct callchain_cursor *dst,
|
|
|
|
struct callchain_cursor *src);
|
|
|
|
|
2012-12-12 03:46:05 +08:00
|
|
|
struct option;
|
2014-01-14 13:25:35 +08:00
|
|
|
struct hist_entry;
|
2012-12-12 03:46:05 +08:00
|
|
|
|
|
|
|
int record_parse_callchain_opt(const struct option *opt, const char *arg, int unset);
|
2013-10-26 22:25:33 +08:00
|
|
|
int record_callchain_opt(const struct option *opt, const char *arg, int unset);
|
|
|
|
|
2016-04-16 03:37:17 +08:00
|
|
|
struct record_opts;
|
|
|
|
|
|
|
|
int record_opts__parse_callchain(struct record_opts *record,
|
|
|
|
struct callchain_param *callchain,
|
|
|
|
const char *arg, bool unset);
|
|
|
|
|
2016-04-15 01:48:07 +08:00
|
|
|
int sample__resolve_callchain(struct perf_sample *sample,
|
|
|
|
struct callchain_cursor *cursor, struct symbol **parent,
|
2014-01-14 13:25:35 +08:00
|
|
|
struct perf_evsel *evsel, struct addr_location *al,
|
|
|
|
int max_stack);
|
|
|
|
int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample);
|
2013-10-31 12:58:30 +08:00
|
|
|
int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node,
|
|
|
|
bool hide_unresolved);
|
2014-01-14 13:25:35 +08:00
|
|
|
|
2012-12-12 03:46:05 +08:00
|
|
|
extern const char record_callchain_help[];
|
2016-03-24 02:06:35 +08:00
|
|
|
int parse_callchain_record(const char *arg, struct callchain_param *param);
|
2015-08-04 16:30:20 +08:00
|
|
|
int parse_callchain_record_opt(const char *arg, struct callchain_param *param);
|
2014-04-08 02:55:24 +08:00
|
|
|
int parse_callchain_report_opt(const char *arg);
|
perf top: Support call-graph display options also
Currently 'perf top --call-graph' option is same as 'perf record'. But
'perf top' also need to receive display options in 'perf report'. To do
that, change parse_callchain_report_opt() to allow record options too.
Now perf top can receive display options like below:
$ perf top --call-graph
Error: option `call-graph' requires a value
Usage: perf top [<options>]
--call-graph
<mode[,dump_size],output_type,min_percent[,print_limit],call_order[,branch]>
setup and enables call-graph (stack chain/backtrace)
recording: fp dwarf lbr, output_type (graph, flat,
fractal, or none), min percent threshold, optional
print limit, callchain order, key (function or
address), add branches
$ perf top --call-graph callee,graph,fp
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Chandler Carruth <chandlerc@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1445495330-25416-2-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-10-22 14:28:49 +08:00
|
|
|
int parse_callchain_top_opt(const char *arg);
|
2014-09-23 09:01:43 +08:00
|
|
|
int perf_callchain_config(const char *var, const char *value);
|
2012-09-10 12:38:00 +08:00
|
|
|
|
|
|
|
static inline void callchain_cursor_snapshot(struct callchain_cursor *dest,
|
|
|
|
struct callchain_cursor *src)
|
|
|
|
{
|
|
|
|
*dest = *src;
|
|
|
|
|
|
|
|
dest->first = src->curr;
|
|
|
|
dest->nr -= src->pos;
|
|
|
|
}
|
2014-06-25 23:49:03 +08:00
|
|
|
|
|
|
|
#ifdef HAVE_SKIP_CALLCHAIN_IDX
|
2016-03-24 02:06:35 +08:00
|
|
|
int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain);
|
2014-06-25 23:49:03 +08:00
|
|
|
#else
|
2014-10-23 23:50:25 +08:00
|
|
|
static inline int arch_skip_callchain_idx(struct thread *thread __maybe_unused,
|
2014-06-25 23:49:03 +08:00
|
|
|
struct ip_callchain *chain __maybe_unused)
|
|
|
|
{
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2014-11-13 10:05:23 +08:00
|
|
|
char *callchain_list__sym_name(struct callchain_list *cl,
|
|
|
|
char *bf, size_t bfsize, bool show_dso);
|
2015-11-09 13:45:39 +08:00
|
|
|
char *callchain_node__scnprintf_value(struct callchain_node *node,
|
|
|
|
char *bf, size_t bfsize, u64 total);
|
|
|
|
int callchain_node__fprintf_value(struct callchain_node *node,
|
|
|
|
FILE *fp, u64 total);
|
2014-11-13 10:05:23 +08:00
|
|
|
|
2016-10-31 09:19:51 +08:00
|
|
|
int callchain_list_counts__printf_value(struct callchain_node *node,
|
|
|
|
struct callchain_list *clist,
|
|
|
|
FILE *fp, char *bf, int bfsize);
|
|
|
|
|
2014-12-30 13:38:13 +08:00
|
|
|
void free_callchain(struct callchain_root *root);
|
2016-01-05 11:06:00 +08:00
|
|
|
void decay_callchain(struct callchain_root *root);
|
2015-11-09 13:45:43 +08:00
|
|
|
int callchain_node__make_parent_list(struct callchain_node *node);
|
2014-12-30 13:38:13 +08:00
|
|
|
|
2016-10-31 09:19:51 +08:00
|
|
|
int callchain_branch_counts(struct callchain_root *root,
|
|
|
|
u64 *branch_count, u64 *predicted_count,
|
|
|
|
u64 *abort_count, u64 *cycles_count);
|
|
|
|
|
2009-09-25 00:02:18 +08:00
|
|
|
#endif /* __PERF_CALLCHAIN_H */
|