Commit a81fef34 authored by Ingo Molnar's avatar Ingo Molnar

Merge tag 'perf-core-for-mingo' of...

Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/jolsa/perf into perf/core

Pull perf/core improvements and fixes from Jiri Olsa:

Infrastructure changes:

  * Making some code (cpu node map and report parse callchain callback) global
    to be usable by upcomming changes (Don Zickus)

  * Fix pmu object compilation error (Jiri Olsa)
Signed-off-by: default avatarJiri Olsa <jolsa@redhat.com>
Signed-off-by: default avatarIngo Molnar <mingo@kernel.org>
parents 4a3dc121 cff6bb46
...@@ -14,6 +14,7 @@ ...@@ -14,6 +14,7 @@
#include "util/parse-options.h" #include "util/parse-options.h"
#include "util/trace-event.h" #include "util/trace-event.h"
#include "util/data.h" #include "util/data.h"
#include "util/cpumap.h"
#include "util/debug.h" #include "util/debug.h"
...@@ -31,9 +32,6 @@ static int caller_lines = -1; ...@@ -31,9 +32,6 @@ static int caller_lines = -1;
static bool raw_ip; static bool raw_ip;
static int *cpunode_map;
static int max_cpu_num;
struct alloc_stat { struct alloc_stat {
u64 call_site; u64 call_site;
u64 ptr; u64 ptr;
...@@ -55,76 +53,6 @@ static struct rb_root root_caller_sorted; ...@@ -55,76 +53,6 @@ static struct rb_root root_caller_sorted;
static unsigned long total_requested, total_allocated; static unsigned long total_requested, total_allocated;
static unsigned long nr_allocs, nr_cross_allocs; static unsigned long nr_allocs, nr_cross_allocs;
#define PATH_SYS_NODE "/sys/devices/system/node"
static int init_cpunode_map(void)
{
FILE *fp;
int i, err = -1;
fp = fopen("/sys/devices/system/cpu/kernel_max", "r");
if (!fp) {
max_cpu_num = 4096;
return 0;
}
if (fscanf(fp, "%d", &max_cpu_num) < 1) {
pr_err("Failed to read 'kernel_max' from sysfs");
goto out_close;
}
max_cpu_num++;
cpunode_map = calloc(max_cpu_num, sizeof(int));
if (!cpunode_map) {
pr_err("%s: calloc failed\n", __func__);
goto out_close;
}
for (i = 0; i < max_cpu_num; i++)
cpunode_map[i] = -1;
err = 0;
out_close:
fclose(fp);
return err;
}
static int setup_cpunode_map(void)
{
struct dirent *dent1, *dent2;
DIR *dir1, *dir2;
unsigned int cpu, mem;
char buf[PATH_MAX];
if (init_cpunode_map())
return -1;
dir1 = opendir(PATH_SYS_NODE);
if (!dir1)
return 0;
while ((dent1 = readdir(dir1)) != NULL) {
if (dent1->d_type != DT_DIR ||
sscanf(dent1->d_name, "node%u", &mem) < 1)
continue;
snprintf(buf, PATH_MAX, "%s/%s", PATH_SYS_NODE, dent1->d_name);
dir2 = opendir(buf);
if (!dir2)
continue;
while ((dent2 = readdir(dir2)) != NULL) {
if (dent2->d_type != DT_LNK ||
sscanf(dent2->d_name, "cpu%u", &cpu) < 1)
continue;
cpunode_map[cpu] = mem;
}
closedir(dir2);
}
closedir(dir1);
return 0;
}
static int insert_alloc_stat(unsigned long call_site, unsigned long ptr, static int insert_alloc_stat(unsigned long call_site, unsigned long ptr,
int bytes_req, int bytes_alloc, int cpu) int bytes_req, int bytes_alloc, int cpu)
{ {
...@@ -235,7 +163,7 @@ static int perf_evsel__process_alloc_node_event(struct perf_evsel *evsel, ...@@ -235,7 +163,7 @@ static int perf_evsel__process_alloc_node_event(struct perf_evsel *evsel,
int ret = perf_evsel__process_alloc_event(evsel, sample); int ret = perf_evsel__process_alloc_event(evsel, sample);
if (!ret) { if (!ret) {
int node1 = cpunode_map[sample->cpu], int node1 = cpu__get_node(sample->cpu),
node2 = perf_evsel__intval(evsel, sample, "node"); node2 = perf_evsel__intval(evsel, sample, "node");
if (node1 != node2) if (node1 != node2)
...@@ -772,7 +700,7 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused) ...@@ -772,7 +700,7 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
if (!strncmp(argv[0], "rec", 3)) { if (!strncmp(argv[0], "rec", 3)) {
return __cmd_record(argc, argv); return __cmd_record(argc, argv);
} else if (!strcmp(argv[0], "stat")) { } else if (!strcmp(argv[0], "stat")) {
if (setup_cpunode_map()) if (cpu__setup_cpunode_map())
return -1; return -1;
if (list_empty(&caller_sort)) if (list_empty(&caller_sort))
......
...@@ -589,11 +589,9 @@ static int __cmd_report(struct report *rep) ...@@ -589,11 +589,9 @@ static int __cmd_report(struct report *rep)
} }
static int static int
parse_callchain_opt(const struct option *opt, const char *arg, int unset) report_parse_callchain_opt(const struct option *opt, const char *arg, int unset)
{ {
struct report *rep = (struct report *)opt->value; struct report *rep = (struct report *)opt->value;
char *tok, *tok2;
char *endptr;
/* /*
* --no-call-graph * --no-call-graph
...@@ -603,80 +601,7 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset) ...@@ -603,80 +601,7 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset)
return 0; return 0;
} }
symbol_conf.use_callchain = true; return parse_callchain_report_opt(arg);
if (!arg)
return 0;
tok = strtok((char *)arg, ",");
if (!tok)
return -1;
/* get the output mode */
if (!strncmp(tok, "graph", strlen(arg)))
callchain_param.mode = CHAIN_GRAPH_ABS;
else if (!strncmp(tok, "flat", strlen(arg)))
callchain_param.mode = CHAIN_FLAT;
else if (!strncmp(tok, "fractal", strlen(arg)))
callchain_param.mode = CHAIN_GRAPH_REL;
else if (!strncmp(tok, "none", strlen(arg))) {
callchain_param.mode = CHAIN_NONE;
symbol_conf.use_callchain = false;
return 0;
}
else
return -1;
/* get the min percentage */
tok = strtok(NULL, ",");
if (!tok)
goto setup;
callchain_param.min_percent = strtod(tok, &endptr);
if (tok == endptr)
return -1;
/* get the print limit */
tok2 = strtok(NULL, ",");
if (!tok2)
goto setup;
if (tok2[0] != 'c') {
callchain_param.print_limit = strtoul(tok2, &endptr, 0);
tok2 = strtok(NULL, ",");
if (!tok2)
goto setup;
}
/* get the call chain order */
if (!strncmp(tok2, "caller", strlen("caller")))
callchain_param.order = ORDER_CALLER;
else if (!strncmp(tok2, "callee", strlen("callee")))
callchain_param.order = ORDER_CALLEE;
else
return -1;
/* Get the sort key */
tok2 = strtok(NULL, ",");
if (!tok2)
goto setup;
if (!strncmp(tok2, "function", strlen("function")))
callchain_param.key = CCKEY_FUNCTION;
else if (!strncmp(tok2, "address", strlen("address")))
callchain_param.key = CCKEY_ADDRESS;
else
return -1;
setup:
if (callchain_register_param(&callchain_param) < 0) {
pr_err("Can't register callchain params\n");
return -1;
}
return 0;
} }
int int
...@@ -788,7 +713,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) ...@@ -788,7 +713,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
"Only display entries with parent-match"), "Only display entries with parent-match"),
OPT_CALLBACK_DEFAULT('g', "call-graph", &report, "output_type,min_percent[,print_limit],call_order", OPT_CALLBACK_DEFAULT('g', "call-graph", &report, "output_type,min_percent[,print_limit],call_order",
"Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit, callchain order, key (function or address). " "Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit, callchain order, key (function or address). "
"Default: fractal,0.5,callee,function", &parse_callchain_opt, callchain_default_opt), "Default: fractal,0.5,callee,function", &report_parse_callchain_opt, callchain_default_opt),
OPT_INTEGER(0, "max-stack", &report.max_stack, OPT_INTEGER(0, "max-stack", &report.max_stack,
"Set the maximum stack depth when parsing the callchain, " "Set the maximum stack depth when parsing the callchain, "
"anything beyond the specified depth will be ignored. " "anything beyond the specified depth will be ignored. "
......
...@@ -25,6 +25,84 @@ ...@@ -25,6 +25,84 @@
__thread struct callchain_cursor callchain_cursor; __thread struct callchain_cursor callchain_cursor;
int
parse_callchain_report_opt(const char *arg)
{
char *tok, *tok2;
char *endptr;
symbol_conf.use_callchain = true;
if (!arg)
return 0;
tok = strtok((char *)arg, ",");
if (!tok)
return -1;
/* get the output mode */
if (!strncmp(tok, "graph", strlen(arg))) {
callchain_param.mode = CHAIN_GRAPH_ABS;
} else if (!strncmp(tok, "flat", strlen(arg))) {
callchain_param.mode = CHAIN_FLAT;
} else if (!strncmp(tok, "fractal", strlen(arg))) {
callchain_param.mode = CHAIN_GRAPH_REL;
} else if (!strncmp(tok, "none", strlen(arg))) {
callchain_param.mode = CHAIN_NONE;
symbol_conf.use_callchain = false;
return 0;
} else {
return -1;
}
/* get the min percentage */
tok = strtok(NULL, ",");
if (!tok)
goto setup;
callchain_param.min_percent = strtod(tok, &endptr);
if (tok == endptr)
return -1;
/* get the print limit */
tok2 = strtok(NULL, ",");
if (!tok2)
goto setup;
if (tok2[0] != 'c') {
callchain_param.print_limit = strtoul(tok2, &endptr, 0);
tok2 = strtok(NULL, ",");
if (!tok2)
goto setup;
}
/* get the call chain order */
if (!strncmp(tok2, "caller", strlen("caller")))
callchain_param.order = ORDER_CALLER;
else if (!strncmp(tok2, "callee", strlen("callee")))
callchain_param.order = ORDER_CALLEE;
else
return -1;
/* Get the sort key */
tok2 = strtok(NULL, ",");
if (!tok2)
goto setup;
if (!strncmp(tok2, "function", strlen("function")))
callchain_param.key = CCKEY_FUNCTION;
else if (!strncmp(tok2, "address", strlen("address")))
callchain_param.key = CCKEY_ADDRESS;
else
return -1;
setup:
if (callchain_register_param(&callchain_param) < 0) {
pr_err("Can't register callchain params\n");
return -1;
}
return 0;
}
static void static void
rb_insert_callchain(struct rb_root *root, struct callchain_node *chain, rb_insert_callchain(struct rb_root *root, struct callchain_node *chain,
enum chain_mode mode) enum chain_mode mode)
......
...@@ -157,4 +157,5 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent ...@@ -157,4 +157,5 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent
int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample); int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample);
extern const char record_callchain_help[]; extern const char record_callchain_help[];
int parse_callchain_report_opt(const char *arg);
#endif /* __PERF_CALLCHAIN_H */ #endif /* __PERF_CALLCHAIN_H */
...@@ -317,3 +317,163 @@ int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep) ...@@ -317,3 +317,163 @@ int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep)
{ {
return cpu_map__build_map(cpus, corep, cpu_map__get_core); return cpu_map__build_map(cpus, corep, cpu_map__get_core);
} }
/* setup simple routines to easily access node numbers given a cpu number */
static int get_max_num(char *path, int *max)
{
size_t num;
char *buf;
int err = 0;
if (filename__read_str(path, &buf, &num))
return -1;
buf[num] = '\0';
/* start on the right, to find highest node num */
while (--num) {
if ((buf[num] == ',') || (buf[num] == '-')) {
num++;
break;
}
}
if (sscanf(&buf[num], "%d", max) < 1) {
err = -1;
goto out;
}
/* convert from 0-based to 1-based */
(*max)++;
out:
free(buf);
return err;
}
/* Determine highest possible cpu in the system for sparse allocation */
static void set_max_cpu_num(void)
{
const char *mnt;
char path[PATH_MAX];
int ret = -1;
/* set up default */
max_cpu_num = 4096;
mnt = sysfs__mountpoint();
if (!mnt)
goto out;
/* get the highest possible cpu number for a sparse allocation */
ret = snprintf(path, PATH_MAX, "%s/devices/system/cpu/possible", mnt);
if (ret == PATH_MAX) {
pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
goto out;
}
ret = get_max_num(path, &max_cpu_num);
out:
if (ret)
pr_err("Failed to read max cpus, using default of %d\n", max_cpu_num);
}
/* Determine highest possible node in the system for sparse allocation */
static void set_max_node_num(void)
{
const char *mnt;
char path[PATH_MAX];
int ret = -1;
/* set up default */
max_node_num = 8;
mnt = sysfs__mountpoint();
if (!mnt)
goto out;
/* get the highest possible cpu number for a sparse allocation */
ret = snprintf(path, PATH_MAX, "%s/devices/system/node/possible", mnt);
if (ret == PATH_MAX) {
pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
goto out;
}
ret = get_max_num(path, &max_node_num);
out:
if (ret)
pr_err("Failed to read max nodes, using default of %d\n", max_node_num);
}
static int init_cpunode_map(void)
{
int i;
set_max_cpu_num();
set_max_node_num();
cpunode_map = calloc(max_cpu_num, sizeof(int));
if (!cpunode_map) {
pr_err("%s: calloc failed\n", __func__);
return -1;
}
for (i = 0; i < max_cpu_num; i++)
cpunode_map[i] = -1;
return 0;
}
int cpu__setup_cpunode_map(void)
{
struct dirent *dent1, *dent2;
DIR *dir1, *dir2;
unsigned int cpu, mem;
char buf[PATH_MAX];
char path[PATH_MAX];
const char *mnt;
int n;
/* initialize globals */
if (init_cpunode_map())
return -1;
mnt = sysfs__mountpoint();
if (!mnt)
return 0;
n = snprintf(path, PATH_MAX, "%s/devices/system/node", mnt);
if (n == PATH_MAX) {
pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
return -1;
}
dir1 = opendir(path);
if (!dir1)
return 0;
/* walk tree and setup map */
while ((dent1 = readdir(dir1)) != NULL) {
if (dent1->d_type != DT_DIR || sscanf(dent1->d_name, "node%u", &mem) < 1)
continue;
n = snprintf(buf, PATH_MAX, "%s/%s", path, dent1->d_name);
if (n == PATH_MAX) {
pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
continue;
}
dir2 = opendir(buf);
if (!dir2)
continue;
while ((dent2 = readdir(dir2)) != NULL) {
if (dent2->d_type != DT_LNK || sscanf(dent2->d_name, "cpu%u", &cpu) < 1)
continue;
cpunode_map[cpu] = mem;
}
closedir(dir2);
}
closedir(dir1);
return 0;
}
...@@ -4,6 +4,9 @@ ...@@ -4,6 +4,9 @@
#include <stdio.h> #include <stdio.h>
#include <stdbool.h> #include <stdbool.h>
#include "perf.h"
#include "util/debug.h"
struct cpu_map { struct cpu_map {
int nr; int nr;
int map[]; int map[];
...@@ -46,4 +49,36 @@ static inline bool cpu_map__empty(const struct cpu_map *map) ...@@ -46,4 +49,36 @@ static inline bool cpu_map__empty(const struct cpu_map *map)
return map ? map->map[0] == -1 : true; return map ? map->map[0] == -1 : true;
} }
int max_cpu_num;
int max_node_num;
int *cpunode_map;
int cpu__setup_cpunode_map(void);
static inline int cpu__max_node(void)
{
if (unlikely(!max_node_num))
pr_debug("cpu_map not initialized\n");
return max_node_num;
}
static inline int cpu__max_cpu(void)
{
if (unlikely(!max_cpu_num))
pr_debug("cpu_map not initialized\n");
return max_cpu_num;
}
static inline int cpu__get_node(int cpu)
{
if (unlikely(cpunode_map == NULL)) {
pr_debug("cpu_map not initialized\n");
return -1;
}
return cpunode_map[cpu];
}
#endif /* __PERF_CPUMAP_H */ #endif /* __PERF_CPUMAP_H */
...@@ -284,17 +284,17 @@ static int pmu_aliases(const char *name, struct list_head *head) ...@@ -284,17 +284,17 @@ static int pmu_aliases(const char *name, struct list_head *head)
static int pmu_alias_terms(struct perf_pmu_alias *alias, static int pmu_alias_terms(struct perf_pmu_alias *alias,
struct list_head *terms) struct list_head *terms)
{ {
struct parse_events_term *term, *clone; struct parse_events_term *term, *cloned;
LIST_HEAD(list); LIST_HEAD(list);
int ret; int ret;
list_for_each_entry(term, &alias->terms, list) { list_for_each_entry(term, &alias->terms, list) {
ret = parse_events_term__clone(&clone, term); ret = parse_events_term__clone(&cloned, term);
if (ret) { if (ret) {
parse_events__free_terms(&list); parse_events__free_terms(&list);
return ret; return ret;
} }
list_add_tail(&clone->list, &list); list_add_tail(&cloned->list, &list);
} }
list_splice(&list, terms); list_splice(&list, terms);
return 0; return 0;
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment