linux/tools/perf/util/sort.c
Linus Torvalds 9c2b957db1 Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf events changes for v3.4 from Ingo Molnar:

 - New "hardware based branch profiling" feature both on the kernel and
   the tooling side, on CPUs that support it.  (modern x86 Intel CPUs
   with the 'LBR' hardware feature currently.)

   This new feature is basically a sophisticated 'magnifying glass' for
   branch execution - something that is pretty difficult to extract from
   regular, function histogram centric profiles.

   The simplest mode is activated via 'perf record -b', and the result
   looks like this in perf report:

	$ perf record -b any_call,u -e cycles:u branchy

	$ perf report -b --sort=symbol
	    52.34%  [.] main                   [.] f1
	    24.04%  [.] f1                     [.] f3
	    23.60%  [.] f1                     [.] f2
	     0.01%  [k] _IO_new_file_xsputn    [k] _IO_file_overflow
	     0.01%  [k] _IO_vfprintf_internal  [k] _IO_new_file_xsputn
	     0.01%  [k] _IO_vfprintf_internal  [k] strchrnul
	     0.01%  [k] __printf               [k] _IO_vfprintf_internal
	     0.01%  [k] main                   [k] __printf

   This output shows from/to branch columns and shows the highest
   percentage (from,to) jump combinations - i.e.  the most likely taken
   branches in the system.  "branches" can also include function calls
   and any other synchronous and asynchronous transitions of the
   instruction pointer that are not 'next instruction' - such as system
   calls, traps, interrupts, etc.

   This feature comes with (hopefully intuitive) flat ascii and TUI
   support in perf report.

 - Various 'perf annotate' visual improvements for us assembly junkies.
   It will now recognize function calls in the TUI and by hitting enter
   you can follow the call (recursively) and back, amongst other
   improvements.

 - Multiple threads/processes recording support in perf record, perf
   stat, perf top - which is activated via a comma-list of PIDs:

	perf top -p 21483,21485
	perf stat -p 21483,21485 -ddd
	perf record -p 21483,21485

 - Support for per UID views, via the --uid paramter to perf top, perf
   report, etc.  For example 'perf top --uid mingo' will only show the
   tasks that I am running, excluding other users, root, etc.

 - Jump label restructurings and improvements - this includes the
   factoring out of the (hopefully much clearer) include/linux/static_key.h
   generic facility:

	struct static_key key = STATIC_KEY_INIT_FALSE;

	...

	if (static_key_false(&key))
	        do unlikely code
	else
	        do likely code

	...
	static_key_slow_inc();
	...
	static_key_slow_inc();
	...

   The static_key_false() branch will be generated into the code with as
   little impact to the likely code path as possible.  the
   static_key_slow_*() APIs flip the branch via live kernel code patching.

   This facility can now be used more widely within the kernel to
   micro-optimize hot branches whose likelihood matches the static-key
   usage and fast/slow cost patterns.

 - SW function tracer improvements: perf support and filtering support.

 - Various hardenings of the perf.data ABI, to make older perf.data's
   smoother on newer tool versions, to make new features integrate more
   smoothly, to support cross-endian recording/analyzing workflows
   better, etc.

 - Restructuring of the kprobes code, the splitting out of 'optprobes',
   and a corner case bugfix.

 - Allow the tracing of kernel console output (printk).

 - Improvements/fixes to user-space RDPMC support, allowing user-space
   self-profiling code to extract PMU counts without performing any
   system calls, while playing nice with the kernel side.

 - 'perf bench' improvements

 - ... and lots of internal restructurings, cleanups and fixes that made
   these features possible.  And, as usual this list is incomplete as
   there were also lots of other improvements

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (120 commits)
  perf report: Fix annotate double quit issue in branch view mode
  perf report: Remove duplicate annotate choice in branch view mode
  perf/x86: Prettify pmu config literals
  perf report: Enable TUI in branch view mode
  perf report: Auto-detect branch stack sampling mode
  perf record: Add HEADER_BRANCH_STACK tag
  perf record: Provide default branch stack sampling mode option
  perf tools: Make perf able to read files from older ABIs
  perf tools: Fix ABI compatibility bug in print_event_desc()
  perf tools: Enable reading of perf.data files from different ABI rev
  perf: Add ABI reference sizes
  perf report: Add support for taken branch sampling
  perf record: Add support for sampling taken branch
  perf tools: Add code to support PERF_SAMPLE_BRANCH_STACK
  x86/kprobes: Split out optprobe related code to kprobes-opt.c
  x86/kprobes: Fix a bug which can modify kernel code permanently
  x86/kprobes: Fix instruction recovery on optimized path
  perf: Add callback to flush branch_stack on context switch
  perf: Disable PERF_SAMPLE_BRANCH_* when not supported
  perf/x86: Add LBR software filter support for Intel CPUs
  ...
2012-03-20 10:29:15 -07:00

528 lines
13 KiB
C

#include "sort.h"
#include "hist.h"
regex_t parent_regex;
const char default_parent_pattern[] = "^sys_|^do_page_fault";
const char *parent_pattern = default_parent_pattern;
const char default_sort_order[] = "comm,dso,symbol";
const char *sort_order = default_sort_order;
int sort__need_collapse = 0;
int sort__has_parent = 0;
int sort__branch_mode = -1; /* -1 = means not set */
enum sort_type sort__first_dimension;
char * field_sep;
LIST_HEAD(hist_entry__sort_list);
static int repsep_snprintf(char *bf, size_t size, const char *fmt, ...)
{
int n;
va_list ap;
va_start(ap, fmt);
n = vsnprintf(bf, size, fmt, ap);
if (field_sep && n > 0) {
char *sep = bf;
while (1) {
sep = strchr(sep, *field_sep);
if (sep == NULL)
break;
*sep = '.';
}
}
va_end(ap);
if (n >= (int)size)
return size - 1;
return n;
}
static int64_t cmp_null(void *l, void *r)
{
if (!l && !r)
return 0;
else if (!l)
return -1;
else
return 1;
}
/* --sort pid */
static int64_t
sort__thread_cmp(struct hist_entry *left, struct hist_entry *right)
{
return right->thread->pid - left->thread->pid;
}
static int hist_entry__thread_snprintf(struct hist_entry *self, char *bf,
size_t size, unsigned int width)
{
return repsep_snprintf(bf, size, "%*s:%5d", width,
self->thread->comm ?: "", self->thread->pid);
}
struct sort_entry sort_thread = {
.se_header = "Command: Pid",
.se_cmp = sort__thread_cmp,
.se_snprintf = hist_entry__thread_snprintf,
.se_width_idx = HISTC_THREAD,
};
/* --sort comm */
static int64_t
sort__comm_cmp(struct hist_entry *left, struct hist_entry *right)
{
return right->thread->pid - left->thread->pid;
}
static int64_t
sort__comm_collapse(struct hist_entry *left, struct hist_entry *right)
{
char *comm_l = left->thread->comm;
char *comm_r = right->thread->comm;
if (!comm_l || !comm_r)
return cmp_null(comm_l, comm_r);
return strcmp(comm_l, comm_r);
}
static int hist_entry__comm_snprintf(struct hist_entry *self, char *bf,
size_t size, unsigned int width)
{
return repsep_snprintf(bf, size, "%*s", width, self->thread->comm);
}
static int64_t _sort__dso_cmp(struct map *map_l, struct map *map_r)
{
struct dso *dso_l = map_l ? map_l->dso : NULL;
struct dso *dso_r = map_r ? map_r->dso : NULL;
const char *dso_name_l, *dso_name_r;
if (!dso_l || !dso_r)
return cmp_null(dso_l, dso_r);
if (verbose) {
dso_name_l = dso_l->long_name;
dso_name_r = dso_r->long_name;
} else {
dso_name_l = dso_l->short_name;
dso_name_r = dso_r->short_name;
}
return strcmp(dso_name_l, dso_name_r);
}
struct sort_entry sort_comm = {
.se_header = "Command",
.se_cmp = sort__comm_cmp,
.se_collapse = sort__comm_collapse,
.se_snprintf = hist_entry__comm_snprintf,
.se_width_idx = HISTC_COMM,
};
/* --sort dso */
static int64_t
sort__dso_cmp(struct hist_entry *left, struct hist_entry *right)
{
return _sort__dso_cmp(left->ms.map, right->ms.map);
}
static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r,
u64 ip_l, u64 ip_r)
{
if (!sym_l || !sym_r)
return cmp_null(sym_l, sym_r);
if (sym_l == sym_r)
return 0;
if (sym_l)
ip_l = sym_l->start;
if (sym_r)
ip_r = sym_r->start;
return (int64_t)(ip_r - ip_l);
}
static int _hist_entry__dso_snprintf(struct map *map, char *bf,
size_t size, unsigned int width)
{
if (map && map->dso) {
const char *dso_name = !verbose ? map->dso->short_name :
map->dso->long_name;
return repsep_snprintf(bf, size, "%-*s", width, dso_name);
}
return repsep_snprintf(bf, size, "%-*s", width, "[unknown]");
}
static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf,
size_t size, unsigned int width)
{
return _hist_entry__dso_snprintf(self->ms.map, bf, size, width);
}
static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
u64 ip, char level, char *bf, size_t size,
unsigned int width __used)
{
size_t ret = 0;
if (verbose) {
char o = map ? dso__symtab_origin(map->dso) : '!';
ret += repsep_snprintf(bf, size, "%-#*llx %c ",
BITS_PER_LONG / 4, ip, o);
}
ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", level);
if (sym)
ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
width - ret,
sym->name);
else {
size_t len = BITS_PER_LONG / 4;
ret += repsep_snprintf(bf + ret, size - ret, "%-#.*llx",
len, ip);
ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
width - ret, "");
}
return ret;
}
struct sort_entry sort_dso = {
.se_header = "Shared Object",
.se_cmp = sort__dso_cmp,
.se_snprintf = hist_entry__dso_snprintf,
.se_width_idx = HISTC_DSO,
};
static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf,
size_t size, unsigned int width __used)
{
return _hist_entry__sym_snprintf(self->ms.map, self->ms.sym, self->ip,
self->level, bf, size, width);
}
/* --sort symbol */
static int64_t
sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
{
u64 ip_l, ip_r;
if (!left->ms.sym && !right->ms.sym)
return right->level - left->level;
if (!left->ms.sym || !right->ms.sym)
return cmp_null(left->ms.sym, right->ms.sym);
if (left->ms.sym == right->ms.sym)
return 0;
ip_l = left->ms.sym->start;
ip_r = right->ms.sym->start;
return _sort__sym_cmp(left->ms.sym, right->ms.sym, ip_l, ip_r);
}
struct sort_entry sort_sym = {
.se_header = "Symbol",
.se_cmp = sort__sym_cmp,
.se_snprintf = hist_entry__sym_snprintf,
.se_width_idx = HISTC_SYMBOL,
};
/* --sort parent */
static int64_t
sort__parent_cmp(struct hist_entry *left, struct hist_entry *right)
{
struct symbol *sym_l = left->parent;
struct symbol *sym_r = right->parent;
if (!sym_l || !sym_r)
return cmp_null(sym_l, sym_r);
return strcmp(sym_l->name, sym_r->name);
}
static int hist_entry__parent_snprintf(struct hist_entry *self, char *bf,
size_t size, unsigned int width)
{
return repsep_snprintf(bf, size, "%-*s", width,
self->parent ? self->parent->name : "[other]");
}
struct sort_entry sort_parent = {
.se_header = "Parent symbol",
.se_cmp = sort__parent_cmp,
.se_snprintf = hist_entry__parent_snprintf,
.se_width_idx = HISTC_PARENT,
};
/* --sort cpu */
static int64_t
sort__cpu_cmp(struct hist_entry *left, struct hist_entry *right)
{
return right->cpu - left->cpu;
}
static int hist_entry__cpu_snprintf(struct hist_entry *self, char *bf,
size_t size, unsigned int width)
{
return repsep_snprintf(bf, size, "%-*d", width, self->cpu);
}
struct sort_entry sort_cpu = {
.se_header = "CPU",
.se_cmp = sort__cpu_cmp,
.se_snprintf = hist_entry__cpu_snprintf,
.se_width_idx = HISTC_CPU,
};
static int64_t
sort__dso_from_cmp(struct hist_entry *left, struct hist_entry *right)
{
return _sort__dso_cmp(left->branch_info->from.map,
right->branch_info->from.map);
}
static int hist_entry__dso_from_snprintf(struct hist_entry *self, char *bf,
size_t size, unsigned int width)
{
return _hist_entry__dso_snprintf(self->branch_info->from.map,
bf, size, width);
}
struct sort_entry sort_dso_from = {
.se_header = "Source Shared Object",
.se_cmp = sort__dso_from_cmp,
.se_snprintf = hist_entry__dso_from_snprintf,
.se_width_idx = HISTC_DSO_FROM,
};
static int64_t
sort__dso_to_cmp(struct hist_entry *left, struct hist_entry *right)
{
return _sort__dso_cmp(left->branch_info->to.map,
right->branch_info->to.map);
}
static int hist_entry__dso_to_snprintf(struct hist_entry *self, char *bf,
size_t size, unsigned int width)
{
return _hist_entry__dso_snprintf(self->branch_info->to.map,
bf, size, width);
}
static int64_t
sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right)
{
struct addr_map_symbol *from_l = &left->branch_info->from;
struct addr_map_symbol *from_r = &right->branch_info->from;
if (!from_l->sym && !from_r->sym)
return right->level - left->level;
return _sort__sym_cmp(from_l->sym, from_r->sym, from_l->addr,
from_r->addr);
}
static int64_t
sort__sym_to_cmp(struct hist_entry *left, struct hist_entry *right)
{
struct addr_map_symbol *to_l = &left->branch_info->to;
struct addr_map_symbol *to_r = &right->branch_info->to;
if (!to_l->sym && !to_r->sym)
return right->level - left->level;
return _sort__sym_cmp(to_l->sym, to_r->sym, to_l->addr, to_r->addr);
}
static int hist_entry__sym_from_snprintf(struct hist_entry *self, char *bf,
size_t size, unsigned int width __used)
{
struct addr_map_symbol *from = &self->branch_info->from;
return _hist_entry__sym_snprintf(from->map, from->sym, from->addr,
self->level, bf, size, width);
}
static int hist_entry__sym_to_snprintf(struct hist_entry *self, char *bf,
size_t size, unsigned int width __used)
{
struct addr_map_symbol *to = &self->branch_info->to;
return _hist_entry__sym_snprintf(to->map, to->sym, to->addr,
self->level, bf, size, width);
}
struct sort_entry sort_dso_to = {
.se_header = "Target Shared Object",
.se_cmp = sort__dso_to_cmp,
.se_snprintf = hist_entry__dso_to_snprintf,
.se_width_idx = HISTC_DSO_TO,
};
struct sort_entry sort_sym_from = {
.se_header = "Source Symbol",
.se_cmp = sort__sym_from_cmp,
.se_snprintf = hist_entry__sym_from_snprintf,
.se_width_idx = HISTC_SYMBOL_FROM,
};
struct sort_entry sort_sym_to = {
.se_header = "Target Symbol",
.se_cmp = sort__sym_to_cmp,
.se_snprintf = hist_entry__sym_to_snprintf,
.se_width_idx = HISTC_SYMBOL_TO,
};
static int64_t
sort__mispredict_cmp(struct hist_entry *left, struct hist_entry *right)
{
const unsigned char mp = left->branch_info->flags.mispred !=
right->branch_info->flags.mispred;
const unsigned char p = left->branch_info->flags.predicted !=
right->branch_info->flags.predicted;
return mp || p;
}
static int hist_entry__mispredict_snprintf(struct hist_entry *self, char *bf,
size_t size, unsigned int width){
static const char *out = "N/A";
if (self->branch_info->flags.predicted)
out = "N";
else if (self->branch_info->flags.mispred)
out = "Y";
return repsep_snprintf(bf, size, "%-*s", width, out);
}
struct sort_entry sort_mispredict = {
.se_header = "Branch Mispredicted",
.se_cmp = sort__mispredict_cmp,
.se_snprintf = hist_entry__mispredict_snprintf,
.se_width_idx = HISTC_MISPREDICT,
};
struct sort_dimension {
const char *name;
struct sort_entry *entry;
int taken;
};
#define DIM(d, n, func) [d] = { .name = n, .entry = &(func) }
static struct sort_dimension sort_dimensions[] = {
DIM(SORT_PID, "pid", sort_thread),
DIM(SORT_COMM, "comm", sort_comm),
DIM(SORT_DSO, "dso", sort_dso),
DIM(SORT_DSO_FROM, "dso_from", sort_dso_from),
DIM(SORT_DSO_TO, "dso_to", sort_dso_to),
DIM(SORT_SYM, "symbol", sort_sym),
DIM(SORT_SYM_TO, "symbol_from", sort_sym_from),
DIM(SORT_SYM_FROM, "symbol_to", sort_sym_to),
DIM(SORT_PARENT, "parent", sort_parent),
DIM(SORT_CPU, "cpu", sort_cpu),
DIM(SORT_MISPREDICT, "mispredict", sort_mispredict),
};
int sort_dimension__add(const char *tok)
{
unsigned int i;
for (i = 0; i < ARRAY_SIZE(sort_dimensions); i++) {
struct sort_dimension *sd = &sort_dimensions[i];
if (strncasecmp(tok, sd->name, strlen(tok)))
continue;
if (sd->entry == &sort_parent) {
int ret = regcomp(&parent_regex, parent_pattern, REG_EXTENDED);
if (ret) {
char err[BUFSIZ];
regerror(ret, &parent_regex, err, sizeof(err));
pr_err("Invalid regex: %s\n%s", parent_pattern, err);
return -EINVAL;
}
sort__has_parent = 1;
}
if (sd->taken)
return 0;
if (sd->entry->se_collapse)
sort__need_collapse = 1;
if (list_empty(&hist_entry__sort_list)) {
if (!strcmp(sd->name, "pid"))
sort__first_dimension = SORT_PID;
else if (!strcmp(sd->name, "comm"))
sort__first_dimension = SORT_COMM;
else if (!strcmp(sd->name, "dso"))
sort__first_dimension = SORT_DSO;
else if (!strcmp(sd->name, "symbol"))
sort__first_dimension = SORT_SYM;
else if (!strcmp(sd->name, "parent"))
sort__first_dimension = SORT_PARENT;
else if (!strcmp(sd->name, "cpu"))
sort__first_dimension = SORT_CPU;
else if (!strcmp(sd->name, "symbol_from"))
sort__first_dimension = SORT_SYM_FROM;
else if (!strcmp(sd->name, "symbol_to"))
sort__first_dimension = SORT_SYM_TO;
else if (!strcmp(sd->name, "dso_from"))
sort__first_dimension = SORT_DSO_FROM;
else if (!strcmp(sd->name, "dso_to"))
sort__first_dimension = SORT_DSO_TO;
else if (!strcmp(sd->name, "mispredict"))
sort__first_dimension = SORT_MISPREDICT;
}
list_add_tail(&sd->entry->list, &hist_entry__sort_list);
sd->taken = 1;
return 0;
}
return -ESRCH;
}
void setup_sorting(const char * const usagestr[], const struct option *opts)
{
char *tmp, *tok, *str = strdup(sort_order);
for (tok = strtok_r(str, ", ", &tmp);
tok; tok = strtok_r(NULL, ", ", &tmp)) {
if (sort_dimension__add(tok) < 0) {
error("Unknown --sort key: `%s'", tok);
usage_with_options(usagestr, opts);
}
}
free(str);
}
void sort_entry__setup_elide(struct sort_entry *self, struct strlist *list,
const char *list_name, FILE *fp)
{
if (list && strlist__nr_entries(list) == 1) {
if (fp != NULL)
fprintf(fp, "# %s: %s\n", list_name,
strlist__entry(list, 0)->s);
self->elide = true;
}
}