summaryrefslogtreecommitdiff
path: root/tools/perf/util/sort.c
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf/util/sort.c')
-rw-r--r--tools/perf/util/sort.c211
1 files changed, 154 insertions, 57 deletions
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index c51049087e4e..f3a565b0e230 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -141,6 +141,43 @@ struct sort_entry sort_thread = {
.se_width_idx = HISTC_THREAD,
};
+/* --sort tgid */
+
+static int64_t
+sort__tgid_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+ return thread__pid(right->thread) - thread__pid(left->thread);
+}
+
+static int hist_entry__tgid_snprintf(struct hist_entry *he, char *bf,
+ size_t size, unsigned int width)
+{
+ int tgid = thread__pid(he->thread);
+ const char *comm = NULL;
+
+ /* display comm of the thread-group leader */
+ if (thread__pid(he->thread) == thread__tid(he->thread)) {
+ comm = thread__comm_str(he->thread);
+ } else {
+ struct maps *maps = thread__maps(he->thread);
+ struct thread *leader = machine__find_thread(maps__machine(maps),
+ tgid, tgid);
+ if (leader) {
+ comm = thread__comm_str(leader);
+ thread__put(leader);
+ }
+ }
+ width = max(7U, width) - 8;
+ return repsep_snprintf(bf, size, "%7d:%-*.*s", tgid, width, width, comm ?: "");
+}
+
+struct sort_entry sort_tgid = {
+ .se_header = " Tgid:Command",
+ .se_cmp = sort__tgid_cmp,
+ .se_snprintf = hist_entry__tgid_snprintf,
+ .se_width_idx = HISTC_TGID,
+};
+
/* --sort simd */
static int64_t
@@ -1709,22 +1746,27 @@ sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right)
if (rc)
return rc;
/*
- * Addresses with no major/minor numbers are assumed to be
+ * Addresses with no major/minor numbers or build ID are assumed to be
* anonymous in userspace. Sort those on pid then address.
*
* The kernel and non-zero major/minor mapped areas are
* assumed to be unity mapped. Sort those on address.
*/
+ if (left->cpumode != PERF_RECORD_MISC_KERNEL && (map__flags(l_map) & MAP_SHARED) == 0) {
+ const struct dso_id *dso_id = dso__id_const(l_dso);
- if ((left->cpumode != PERF_RECORD_MISC_KERNEL) &&
- (!(map__flags(l_map) & MAP_SHARED)) && !dso__id(l_dso)->maj && !dso__id(l_dso)->min &&
- !dso__id(l_dso)->ino && !dso__id(l_dso)->ino_generation) {
- /* userspace anonymous */
+ if (!dso_id->mmap2_valid)
+ dso_id = dso__id_const(r_dso);
- if (thread__pid(left->thread) > thread__pid(right->thread))
- return -1;
- if (thread__pid(left->thread) < thread__pid(right->thread))
- return 1;
+ if (!build_id__is_defined(&dso_id->build_id) &&
+ (!dso_id->mmap2_valid || (dso_id->maj == 0 && dso_id->min == 0))) {
+ /* userspace anonymous */
+
+ if (thread__pid(left->thread) > thread__pid(right->thread))
+ return -1;
+ if (thread__pid(left->thread) < thread__pid(right->thread))
+ return 1;
+ }
}
addr:
@@ -1749,6 +1791,7 @@ static int hist_entry__dcacheline_snprintf(struct hist_entry *he, char *bf,
if (he->mem_info) {
struct map *map = mem_info__daddr(he->mem_info)->ms.map;
struct dso *dso = map ? map__dso(map) : NULL;
+ const struct dso_id *dso_id = dso ? dso__id_const(dso) : &dso_id_empty;
addr = cl_address(mem_info__daddr(he->mem_info)->al_addr, chk_double_cl);
ms = &mem_info__daddr(he->mem_info)->ms;
@@ -1757,8 +1800,7 @@ static int hist_entry__dcacheline_snprintf(struct hist_entry *he, char *bf,
if ((he->cpumode != PERF_RECORD_MISC_KERNEL) &&
map && !(map__prot(map) & PROT_EXEC) &&
(map__flags(map) & MAP_SHARED) &&
- (dso__id(dso)->maj || dso__id(dso)->min || dso__id(dso)->ino ||
- dso__id(dso)->ino_generation))
+ (!dso_id->mmap2_valid || (dso_id->maj == 0 && dso_id->min == 0)))
level = 's';
else if (!map)
level = 'X';
@@ -1842,21 +1884,20 @@ struct sort_entry sort_global_ins_lat = {
static int64_t
sort__p_stage_cyc_cmp(struct hist_entry *left, struct hist_entry *right)
{
- return left->p_stage_cyc - right->p_stage_cyc;
+ return left->weight3 - right->weight3;
}
static int hist_entry__global_p_stage_cyc_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
- return repsep_snprintf(bf, size, "%-*u", width,
- he->p_stage_cyc * he->stat.nr_events);
+ return repsep_snprintf(bf, size, "%-*u", width, he->weight3 * he->stat.nr_events);
}
static int hist_entry__p_stage_cyc_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
- return repsep_snprintf(bf, size, "%-*u", width, he->p_stage_cyc);
+ return repsep_snprintf(bf, size, "%-*u", width, he->weight3);
}
struct sort_entry sort_local_p_stage_cyc = {
@@ -2489,25 +2530,51 @@ struct sort_dimension {
int taken;
};
-int __weak arch_support_sort_key(const char *sort_key __maybe_unused)
+static int arch_support_sort_key(const char *sort_key, struct perf_env *env)
{
+ const char *arch = perf_env__arch(env);
+
+ if (!strcmp("x86", arch) || !strcmp("powerpc", arch)) {
+ if (!strcmp(sort_key, "p_stage_cyc"))
+ return 1;
+ if (!strcmp(sort_key, "local_p_stage_cyc"))
+ return 1;
+ }
return 0;
}
-const char * __weak arch_perf_header_entry(const char *se_header)
-{
+static const char *arch_perf_header_entry(const char *se_header, struct perf_env *env)
+{
+ const char *arch = perf_env__arch(env);
+
+ if (!strcmp("x86", arch)) {
+ if (!strcmp(se_header, "Local Pipeline Stage Cycle"))
+ return "Local Retire Latency";
+ else if (!strcmp(se_header, "Pipeline Stage Cycle"))
+ return "Retire Latency";
+ } else if (!strcmp("powerpc", arch)) {
+ if (!strcmp(se_header, "Local INSTR Latency"))
+ return "Finish Cyc";
+ else if (!strcmp(se_header, "INSTR Latency"))
+ return "Global Finish_cyc";
+ else if (!strcmp(se_header, "Local Pipeline Stage Cycle"))
+ return "Dispatch Cyc";
+ else if (!strcmp(se_header, "Pipeline Stage Cycle"))
+ return "Global Dispatch_cyc";
+ }
return se_header;
}
-static void sort_dimension_add_dynamic_header(struct sort_dimension *sd)
+static void sort_dimension_add_dynamic_header(struct sort_dimension *sd, struct perf_env *env)
{
- sd->entry->se_header = arch_perf_header_entry(sd->entry->se_header);
+ sd->entry->se_header = arch_perf_header_entry(sd->entry->se_header, env);
}
#define DIM(d, n, func) [d] = { .name = n, .entry = &(func) }
static struct sort_dimension common_sort_dimensions[] = {
DIM(SORT_PID, "pid", sort_thread),
+ DIM(SORT_TGID, "tgid", sort_tgid),
DIM(SORT_COMM, "comm", sort_comm),
DIM(SORT_DSO, "dso", sort_dso),
DIM(SORT_SYM, "symbol", sort_sym),
@@ -2598,9 +2665,11 @@ struct hpp_dimension {
struct perf_hpp_fmt *fmt;
int taken;
int was_taken;
+ int mem_mode;
};
#define DIM(d, n) { .name = n, .fmt = &perf_hpp__format[d], }
+#define DIM_MEM(d, n) { .name = n, .fmt = &perf_hpp__format[d], .mem_mode = 1, }
static struct hpp_dimension hpp_sort_dimensions[] = {
DIM(PERF_HPP__OVERHEAD, "overhead"),
@@ -2620,8 +2689,15 @@ static struct hpp_dimension hpp_sort_dimensions[] = {
DIM(PERF_HPP__WEIGHT2, "ins_lat"),
DIM(PERF_HPP__WEIGHT3, "retire_lat"),
DIM(PERF_HPP__WEIGHT3, "p_stage_cyc"),
+ /* used for output only when SORT_MODE__MEM */
+ DIM_MEM(PERF_HPP__MEM_STAT_OP, "op"),
+ DIM_MEM(PERF_HPP__MEM_STAT_CACHE, "cache"),
+ DIM_MEM(PERF_HPP__MEM_STAT_MEMORY, "memory"),
+ DIM_MEM(PERF_HPP__MEM_STAT_SNOOP, "snoop"),
+ DIM_MEM(PERF_HPP__MEM_STAT_DTLB, "dtlb"),
};
+#undef DIM_MEM
#undef DIM
struct hpp_sort_entry {
@@ -2641,18 +2717,22 @@ void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists)
}
static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
- struct hists *hists, int line __maybe_unused,
+ struct hists *hists, int line,
int *span __maybe_unused)
{
struct hpp_sort_entry *hse;
size_t len = fmt->user_len;
+ const char *hdr = "";
+
+ if (line == hists->hpp_list->nr_header_lines - 1)
+ hdr = fmt->name;
hse = container_of(fmt, struct hpp_sort_entry, hpp);
if (!len)
len = hists__col_len(hists, hse->se->se_width_idx);
- return scnprintf(hpp->buf, hpp->size, "%-*.*s", len, len, fmt->name);
+ return scnprintf(hpp->buf, hpp->size, "%-*.*s", len, len, hdr);
}
static int __sort__hpp_width(struct perf_hpp_fmt *fmt,
@@ -2884,9 +2964,10 @@ static int __sort_dimension__add_hpp_sort(struct sort_dimension *sd,
}
static int __sort_dimension__add_hpp_output(struct sort_dimension *sd,
- struct perf_hpp_list *list)
+ struct perf_hpp_list *list,
+ int level)
{
- struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd, 0);
+ struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd, level);
if (hse == NULL)
return -1;
@@ -3495,12 +3576,13 @@ static int __hpp_dimension__add(struct hpp_dimension *hd,
}
static int __sort_dimension__add_output(struct perf_hpp_list *list,
- struct sort_dimension *sd)
+ struct sort_dimension *sd,
+ int level)
{
if (sd->taken)
return 0;
- if (__sort_dimension__add_hpp_output(sd, list) < 0)
+ if (__sort_dimension__add_hpp_output(sd, list, level) < 0)
return -1;
sd->taken = 1;
@@ -3508,14 +3590,15 @@ static int __sort_dimension__add_output(struct perf_hpp_list *list,
}
static int __hpp_dimension__add_output(struct perf_hpp_list *list,
- struct hpp_dimension *hd)
+ struct hpp_dimension *hd,
+ int level)
{
struct perf_hpp_fmt *fmt;
if (hd->taken)
return 0;
- fmt = __hpp_dimension__alloc_hpp(hd, 0);
+ fmt = __hpp_dimension__alloc_hpp(hd, level);
if (!fmt)
return -1;
@@ -3532,11 +3615,11 @@ int hpp_dimension__add_output(unsigned col, bool implicit)
hd = &hpp_sort_dimensions[col];
if (implicit && !hd->was_taken)
return 0;
- return __hpp_dimension__add_output(&perf_hpp_list, hd);
+ return __hpp_dimension__add_output(&perf_hpp_list, hd, /*level=*/0);
}
int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
- struct evlist *evlist,
+ struct evlist *evlist, struct perf_env *env,
int level)
{
unsigned int i, j;
@@ -3549,7 +3632,7 @@ int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
*/
for (j = 0; j < ARRAY_SIZE(arch_specific_sort_keys); j++) {
if (!strcmp(arch_specific_sort_keys[j], tok) &&
- !arch_support_sort_key(tok)) {
+ !arch_support_sort_key(tok, env)) {
return 0;
}
}
@@ -3562,7 +3645,7 @@ int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
for (j = 0; j < ARRAY_SIZE(dynamic_headers); j++) {
if (sd->name && !strcmp(dynamic_headers[j], sd->name))
- sort_dimension_add_dynamic_header(sd);
+ sort_dimension_add_dynamic_header(sd, env);
}
if (sd->entry == &sort_parent && parent_pattern) {
@@ -3601,15 +3684,6 @@ int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
return __sort_dimension__add(sd, list, level);
}
- for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) {
- struct hpp_dimension *hd = &hpp_sort_dimensions[i];
-
- if (strncasecmp(tok, hd->name, strlen(tok)))
- continue;
-
- return __hpp_dimension__add(hd, list, level);
- }
-
for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) {
struct sort_dimension *sd = &bstack_sort_dimensions[i];
@@ -3651,6 +3725,15 @@ int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
return 0;
}
+ for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) {
+ struct hpp_dimension *hd = &hpp_sort_dimensions[i];
+
+ if (strncasecmp(tok, hd->name, strlen(tok)))
+ continue;
+
+ return __hpp_dimension__add(hd, list, level);
+ }
+
if (!add_dynamic_entry(evlist, tok, level))
return 0;
@@ -3658,13 +3741,13 @@ int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
}
/* This should match with sort_dimension__add() above */
-static bool is_hpp_sort_key(const char *key)
+static bool is_hpp_sort_key(const char *key, struct perf_env *env)
{
unsigned i;
for (i = 0; i < ARRAY_SIZE(arch_specific_sort_keys); i++) {
if (!strcmp(arch_specific_sort_keys[i], key) &&
- !arch_support_sort_key(key)) {
+ !arch_support_sort_key(key, env)) {
return false;
}
}
@@ -3686,7 +3769,7 @@ static bool is_hpp_sort_key(const char *key)
}
static int setup_sort_list(struct perf_hpp_list *list, char *str,
- struct evlist *evlist)
+ struct evlist *evlist, struct perf_env *env)
{
char *tmp, *tok;
int ret = 0;
@@ -3715,7 +3798,7 @@ static int setup_sort_list(struct perf_hpp_list *list, char *str,
}
if (*tok) {
- if (is_hpp_sort_key(tok)) {
+ if (is_hpp_sort_key(tok, env)) {
/* keep output (hpp) sort keys in the same level */
if (prev_was_hpp) {
bool next_same = (level == next_level);
@@ -3728,7 +3811,7 @@ static int setup_sort_list(struct perf_hpp_list *list, char *str,
prev_was_hpp = false;
}
- ret = sort_dimension__add(list, tok, evlist, level);
+ ret = sort_dimension__add(list, tok, evlist, env, level);
if (ret == -EINVAL) {
if (!cacheline_size() && !strncasecmp(tok, "dcacheline", strlen(tok)))
ui__error("The \"dcacheline\" --sort key needs to know the cacheline size and it couldn't be determined on this system");
@@ -3857,7 +3940,7 @@ static char *setup_overhead(char *keys)
return keys;
}
-static int __setup_sorting(struct evlist *evlist)
+static int __setup_sorting(struct evlist *evlist, struct perf_env *env)
{
char *str;
const char *sort_keys;
@@ -3897,7 +3980,7 @@ static int __setup_sorting(struct evlist *evlist)
}
}
- ret = setup_sort_list(&perf_hpp_list, str, evlist);
+ ret = setup_sort_list(&perf_hpp_list, str, evlist, env);
free(str);
return ret;
@@ -4000,7 +4083,7 @@ void sort__setup_elide(FILE *output)
}
}
-int output_field_add(struct perf_hpp_list *list, const char *tok)
+int output_field_add(struct perf_hpp_list *list, const char *tok, int *level)
{
unsigned int i;
@@ -4013,16 +4096,25 @@ int output_field_add(struct perf_hpp_list *list, const char *tok)
if (!strcasecmp(tok, "weight"))
ui__warning("--fields weight shows the average value unlike in the --sort key.\n");
- return __hpp_dimension__add_output(list, hd);
+ if (hd->mem_mode && sort__mode != SORT_MODE__MEMORY)
+ continue;
+
+ return __hpp_dimension__add_output(list, hd, *level);
}
+ /*
+ * A non-output field will increase level so that it can be in a
+ * different hierarchy.
+ */
+ (*level)++;
+
for (i = 0; i < ARRAY_SIZE(common_sort_dimensions); i++) {
struct sort_dimension *sd = &common_sort_dimensions[i];
if (!sd->name || strncasecmp(tok, sd->name, strlen(tok)))
continue;
- return __sort_dimension__add_output(list, sd);
+ return __sort_dimension__add_output(list, sd, *level);
}
for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) {
@@ -4034,7 +4126,7 @@ int output_field_add(struct perf_hpp_list *list, const char *tok)
if (sort__mode != SORT_MODE__BRANCH)
return -EINVAL;
- return __sort_dimension__add_output(list, sd);
+ return __sort_dimension__add_output(list, sd, *level);
}
for (i = 0; i < ARRAY_SIZE(memory_sort_dimensions); i++) {
@@ -4046,7 +4138,7 @@ int output_field_add(struct perf_hpp_list *list, const char *tok)
if (sort__mode != SORT_MODE__MEMORY)
return -EINVAL;
- return __sort_dimension__add_output(list, sd);
+ return __sort_dimension__add_output(list, sd, *level);
}
return -ESRCH;
@@ -4056,10 +4148,11 @@ static int setup_output_list(struct perf_hpp_list *list, char *str)
{
char *tmp, *tok;
int ret = 0;
+ int level = 0;
for (tok = strtok_r(str, ", ", &tmp);
tok; tok = strtok_r(NULL, ", ", &tmp)) {
- ret = output_field_add(list, tok);
+ ret = output_field_add(list, tok, &level);
if (ret == -EINVAL) {
ui__error("Invalid --fields key: `%s'", tok);
break;
@@ -4123,16 +4216,16 @@ out:
return ret;
}
-int setup_sorting(struct evlist *evlist)
+int setup_sorting(struct evlist *evlist, struct perf_env *env)
{
int err;
- err = __setup_sorting(evlist);
+ err = __setup_sorting(evlist, env);
if (err < 0)
return err;
if (parent_pattern != default_parent_pattern) {
- err = sort_dimension__add(&perf_hpp_list, "parent", evlist, -1);
+ err = sort_dimension__add(&perf_hpp_list, "parent", evlist, env, -1);
if (err < 0)
return err;
}
@@ -4149,6 +4242,10 @@ int setup_sorting(struct evlist *evlist)
if (err < 0)
return err;
+ err = perf_hpp__alloc_mem_stats(&perf_hpp_list, evlist);
+ if (err < 0)
+ return err;
+
/* copy sort keys to output fields */
perf_hpp__setup_output_field(&perf_hpp_list);
/* and then copy output fields to sort keys */