summaryrefslogtreecommitdiff
path: root/tools/perf/util
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf/util')
-rw-r--r--tools/perf/util/annotate.h2
-rw-r--r--tools/perf/util/build-id.c2
-rw-r--r--tools/perf/util/build-id.h2
-rw-r--r--tools/perf/util/callchain.c123
-rw-r--r--tools/perf/util/callchain.h19
-rw-r--r--tools/perf/util/config.c4
-rw-r--r--tools/perf/util/cpumap.c160
-rw-r--r--tools/perf/util/cpumap.h35
-rw-r--r--tools/perf/util/dso.c279
-rw-r--r--tools/perf/util/dso.h52
-rw-r--r--tools/perf/util/dwarf-aux.c7
-rw-r--r--tools/perf/util/event.c61
-rw-r--r--tools/perf/util/event.h31
-rw-r--r--tools/perf/util/evsel.c5
-rw-r--r--tools/perf/util/evsel.h9
-rw-r--r--tools/perf/util/header.h4
-rw-r--r--tools/perf/util/hist.c677
-rw-r--r--tools/perf/util/hist.h102
-rw-r--r--tools/perf/util/include/linux/bitmap.h3
-rw-r--r--tools/perf/util/include/linux/export.h6
-rw-r--r--tools/perf/util/include/linux/list.h1
-rw-r--r--tools/perf/util/include/linux/types.h29
-rw-r--r--tools/perf/util/machine.c69
-rw-r--r--tools/perf/util/map.c122
-rw-r--r--tools/perf/util/map.h18
-rw-r--r--tools/perf/util/pager.c12
-rw-r--r--tools/perf/util/parse-events.h3
-rw-r--r--tools/perf/util/parse-events.y14
-rw-r--r--tools/perf/util/perf_regs.c10
-rw-r--r--tools/perf/util/perf_regs.h6
-rw-r--r--tools/perf/util/pmu.c6
-rw-r--r--tools/perf/util/pmu.h2
-rw-r--r--tools/perf/util/probe-event.c13
-rw-r--r--tools/perf/util/probe-finder.c15
-rw-r--r--tools/perf/util/scripting-engines/trace-event-perl.c1
-rw-r--r--tools/perf/util/scripting-engines/trace-event-python.c2
-rw-r--r--tools/perf/util/session.c5
-rw-r--r--tools/perf/util/sort.c630
-rw-r--r--tools/perf/util/sort.h28
-rw-r--r--tools/perf/util/stat.h2
-rw-r--r--tools/perf/util/svghelper.c2
-rw-r--r--tools/perf/util/svghelper.h2
-rw-r--r--tools/perf/util/symbol.c11
-rw-r--r--tools/perf/util/symbol.h5
-rw-r--r--tools/perf/util/thread.c52
-rw-r--r--tools/perf/util/thread.h3
-rw-r--r--tools/perf/util/top.h2
-rw-r--r--tools/perf/util/types.h24
-rw-r--r--tools/perf/util/unwind-libdw.c2
-rw-r--r--tools/perf/util/unwind-libunwind.c2
-rw-r--r--tools/perf/util/unwind.h2
-rw-r--r--tools/perf/util/util.c3
-rw-r--r--tools/perf/util/util.h3
-rw-r--r--tools/perf/util/values.h2
54 files changed, 2311 insertions, 375 deletions
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 56ad4f5287de..112d6e268150 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -3,7 +3,7 @@
#include <stdbool.h>
#include <stdint.h>
-#include "types.h"
+#include <linux/types.h>
#include "symbol.h"
#include "hist.h"
#include "sort.h"
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 6baabe63182b..a904a4cfe7d3 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -25,7 +25,7 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
struct addr_location al;
u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
struct thread *thread = machine__findnew_thread(machine, sample->pid,
- sample->pid);
+ sample->tid);
if (thread == NULL) {
pr_err("problem processing %d event, skipping it.\n",
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index 845ef865eced..ae392561470b 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -4,7 +4,7 @@
#define BUILD_ID_SIZE 20
#include "tool.h"
-#include "types.h"
+#include <linux/types.h>
extern struct perf_tool build_id__mark_dso_hit_ops;
struct dso;
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 8d9db454f1a9..48b6d3f50012 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -25,6 +25,84 @@
__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
rb_insert_callchain(struct rb_root *root, struct callchain_node *chain,
enum chain_mode mode)
@@ -538,7 +616,8 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent
if (sample->callchain == NULL)
return 0;
- if (symbol_conf.use_callchain || sort__has_parent) {
+ if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain ||
+ sort__has_parent) {
return machine__resolve_callchain(al->machine, evsel, al->thread,
sample, parent, al, max_stack);
}
@@ -551,3 +630,45 @@ int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *samp
return 0;
return callchain_append(he->callchain, &callchain_cursor, sample->period);
}
+
+int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node,
+ bool hide_unresolved)
+{
+ al->map = node->map;
+ al->sym = node->sym;
+ if (node->map)
+ al->addr = node->map->map_ip(node->map, node->ip);
+ else
+ al->addr = node->ip;
+
+ if (al->sym == NULL) {
+ if (hide_unresolved)
+ return 0;
+ if (al->map == NULL)
+ goto out;
+ }
+
+ if (al->map->groups == &al->machine->kmaps) {
+ if (machine__is_host(al->machine)) {
+ al->cpumode = PERF_RECORD_MISC_KERNEL;
+ al->level = 'k';
+ } else {
+ al->cpumode = PERF_RECORD_MISC_GUEST_KERNEL;
+ al->level = 'g';
+ }
+ } else {
+ if (machine__is_host(al->machine)) {
+ al->cpumode = PERF_RECORD_MISC_USER;
+ al->level = '.';
+ } else if (perf_guest) {
+ al->cpumode = PERF_RECORD_MISC_GUEST_USER;
+ al->level = 'u';
+ } else {
+ al->cpumode = PERF_RECORD_MISC_HYPERVISOR;
+ al->level = 'H';
+ }
+ }
+
+out:
+ return 1;
+}
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 8ad97e9b119f..8f84423a75da 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -7,6 +7,13 @@
#include "event.h"
#include "symbol.h"
+enum perf_call_graph_mode {
+ CALLCHAIN_NONE,
+ CALLCHAIN_FP,
+ CALLCHAIN_DWARF,
+ CALLCHAIN_MAX
+};
+
enum chain_mode {
CHAIN_NONE,
CHAIN_FLAT,
@@ -155,6 +162,18 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent
struct perf_evsel *evsel, struct addr_location *al,
int max_stack);
int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample);
+int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node,
+ bool hide_unresolved);
extern const char record_callchain_help[];
+int parse_callchain_report_opt(const char *arg);
+
+static inline void callchain_cursor_snapshot(struct callchain_cursor *dest,
+ struct callchain_cursor *src)
+{
+ *dest = *src;
+
+ dest->first = src->curr;
+ dest->nr -= src->pos;
+}
#endif /* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 3e0fdd369ccb..24519e14ac56 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -11,6 +11,7 @@
#include "util.h"
#include "cache.h"
#include "exec_cmd.h"
+#include "util/hist.h" /* perf_hist_config */
#define MAXNAME (256)
@@ -355,6 +356,9 @@ int perf_default_config(const char *var, const char *value,
if (!prefixcmp(var, "core."))
return perf_default_core_config(var, value);
+ if (!prefixcmp(var, "hist."))
+ return perf_hist_config(var, value);
+
/* Add other config variables here. */
return 0;
}
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 7fe4994eeb63..c4e55b71010c 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -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);
}
+
+/* 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;
+}
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index b123bb9d6f55..61a654849002 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -4,6 +4,9 @@
#include <stdio.h>
#include <stdbool.h>
+#include "perf.h"
+#include "util/debug.h"
+
struct cpu_map {
int nr;
int map[];
@@ -46,4 +49,36 @@ static inline bool cpu_map__empty(const struct cpu_map *map)
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 */
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 64453d63b971..819f10414f08 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -1,3 +1,6 @@
+#include <asm/bug.h>
+#include <sys/time.h>
+#include <sys/resource.h>
#include "symbol.h"
#include "dso.h"
#include "machine.h"
@@ -136,7 +139,48 @@ int dso__read_binary_type_filename(const struct dso *dso,
return ret;
}
-static int open_dso(struct dso *dso, struct machine *machine)
+/*
+ * Global list of open DSOs and the counter.
+ */
+static LIST_HEAD(dso__data_open);
+static long dso__data_open_cnt;
+
+static void dso__list_add(struct dso *dso)
+{
+ list_add_tail(&dso->data.open_entry, &dso__data_open);
+ dso__data_open_cnt++;
+}
+
+static void dso__list_del(struct dso *dso)
+{
+ list_del(&dso->data.open_entry);
+ WARN_ONCE(dso__data_open_cnt <= 0,
+ "DSO data fd counter out of bounds.");
+ dso__data_open_cnt--;
+}
+
+static void close_first_dso(void);
+
+static int do_open(char *name)
+{
+ int fd;
+
+ do {
+ fd = open(name, O_RDONLY);
+ if (fd >= 0)
+ return fd;
+
+ pr_debug("dso open failed, mmap: %s\n", strerror(errno));
+ if (!dso__data_open_cnt || errno != EMFILE)
+ break;
+
+ close_first_dso();
+ } while (1);
+
+ return -1;
+}
+
+static int __open_dso(struct dso *dso, struct machine *machine)
{
int fd;
char *root_dir = (char *)"";
@@ -154,11 +198,130 @@ static int open_dso(struct dso *dso, struct machine *machine)
return -EINVAL;
}
- fd = open(name, O_RDONLY);
+ fd = do_open(name);
free(name);
return fd;
}
+static void check_data_close(void);
+
+/**
+ * dso_close - Open DSO data file
+ * @dso: dso object
+ *
+ * Open @dso's data file descriptor and updates
+ * list/count of open DSO objects.
+ */
+static int open_dso(struct dso *dso, struct machine *machine)
+{
+ int fd = __open_dso(dso, machine);
+
+ if (fd > 0) {
+ dso__list_add(dso);
+ /*
+ * Check if we crossed the allowed number
+ * of opened DSOs and close one if needed.
+ */
+ check_data_close();
+ }
+
+ return fd;
+}
+
+static void close_data_fd(struct dso *dso)
+{
+ if (dso->data.fd >= 0) {
+ close(dso->data.fd);
+ dso->data.fd = -1;
+ dso->data.file_size = 0;
+ dso__list_del(dso);
+ }
+}
+
+/**
+ * dso_close - Close DSO data file
+ * @dso: dso object
+ *
+ * Close @dso's data file descriptor and updates
+ * list/count of open DSO objects.
+ */
+static void close_dso(struct dso *dso)
+{
+ close_data_fd(dso);
+}
+
+static void close_first_dso(void)
+{
+ struct dso *dso;
+
+ dso = list_first_entry(&dso__data_open, struct dso, data.open_entry);
+ close_dso(dso);
+}
+
+static rlim_t get_fd_limit(void)
+{
+ struct rlimit l;
+ rlim_t limit = 0;
+
+ /* Allow half of the current open fd limit. */
+ if (getrlimit(RLIMIT_NOFILE, &l) == 0) {
+ if (l.rlim_cur == RLIM_INFINITY)
+ limit = l.rlim_cur;
+ else
+ limit = l.rlim_cur / 2;
+ } else {
+ pr_err("failed to get fd limit\n");
+ limit = 1;
+ }
+
+ return limit;
+}
+
+static bool may_cache_fd(void)
+{
+ static rlim_t limit;
+
+ if (!limit)
+ limit = get_fd_limit();
+
+ if (limit == RLIM_INFINITY)
+ return true;
+
+ return limit > (rlim_t) dso__data_open_cnt;
+}
+
+/*
+ * Check and close LRU dso if we crossed allowed limit
+ * for opened dso file descriptors. The limit is half
+ * of the RLIMIT_NOFILE files opened.
+*/
+static void check_data_close(void)
+{
+ bool cache_fd = may_cache_fd();
+
+ if (!cache_fd)
+ close_first_dso();
+}
+
+/**
+ * dso__data_close - Close DSO data file
+ * @dso: dso object
+ *
+ * External interface to close @dso's data file descriptor.
+ */
+void dso__data_close(struct dso *dso)
+{
+ close_dso(dso);
+}
+
+/**
+ * dso__data_fd - Get dso's data file descriptor
+ * @dso: dso object
+ * @machine: machine object
+ *
+ * External interface to find dso's file, open it and
+ * returns file descriptor.
+ */
int dso__data_fd(struct dso *dso, struct machine *machine)
{
enum dso_binary_type binary_type_data[] = {
@@ -168,8 +331,13 @@ int dso__data_fd(struct dso *dso, struct machine *machine)
};
int i = 0;
- if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND)
- return open_dso(dso, machine);
+ if (dso->data.fd >= 0)
+ return dso->data.fd;
+
+ if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND) {
+ dso->data.fd = open_dso(dso, machine);
+ return dso->data.fd;
+ }
do {
int fd;
@@ -178,7 +346,7 @@ int dso__data_fd(struct dso *dso, struct machine *machine)
fd = open_dso(dso, machine);
if (fd >= 0)
- return fd;
+ return dso->data.fd = fd;
} while (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND);
@@ -260,16 +428,10 @@ dso_cache__memcpy(struct dso_cache *cache, u64 offset,
}
static ssize_t
-dso_cache__read(struct dso *dso, struct machine *machine,
- u64 offset, u8 *data, ssize_t size)
+dso_cache__read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
{
struct dso_cache *cache;
ssize_t ret;
- int fd;
-
- fd = dso__data_fd(dso, machine);
- if (fd < 0)
- return -1;
do {
u64 cache_offset;
@@ -283,16 +445,16 @@ dso_cache__read(struct dso *dso, struct machine *machine,
cache_offset = offset & DSO__DATA_CACHE_MASK;
ret = -EINVAL;
- if (-1 == lseek(fd, cache_offset, SEEK_SET))
+ if (-1 == lseek(dso->data.fd, cache_offset, SEEK_SET))
break;
- ret = read(fd, cache->data, DSO__DATA_CACHE_SIZE);
+ ret = read(dso->data.fd, cache->data, DSO__DATA_CACHE_SIZE);
if (ret <= 0)
break;
cache->offset = cache_offset;
cache->size = ret;
- dso_cache__insert(&dso->cache, cache);
+ dso_cache__insert(&dso->data.cache, cache);
ret = dso_cache__memcpy(cache, offset, data, size);
@@ -301,24 +463,27 @@ dso_cache__read(struct dso *dso, struct machine *machine,
if (ret <= 0)
free(cache);
- close(fd);
return ret;
}
-static ssize_t dso_cache_read(struct dso *dso, struct machine *machine,
- u64 offset, u8 *data, ssize_t size)
+static ssize_t dso_cache_read(struct dso *dso, u64 offset,
+ u8 *data, ssize_t size)
{
struct dso_cache *cache;
- cache = dso_cache__find(&dso->cache, offset);
+ cache = dso_cache__find(&dso->data.cache, offset);
if (cache)
return dso_cache__memcpy(cache, offset, data, size);
else
- return dso_cache__read(dso, machine, offset, data, size);
+ return dso_cache__read(dso, offset, data, size);
}
-ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
- u64 offset, u8 *data, ssize_t size)
+/*
+ * Reads and caches dso data DSO__DATA_CACHE_SIZE size chunks
+ * in the rb_tree. Any read to already cached data is served
+ * by cached data.
+ */
+static ssize_t cached_read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
{
ssize_t r = 0;
u8 *p = data;
@@ -326,7 +491,7 @@ ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
do {
ssize_t ret;
- ret = dso_cache_read(dso, machine, offset, p, size);
+ ret = dso_cache_read(dso, offset, p, size);
if (ret < 0)
return ret;
@@ -346,6 +511,67 @@ ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
return r;
}
+static int data_file_size(struct dso *dso)
+{
+ struct stat st;
+
+ if (!dso->data.file_size) {
+ if (fstat(dso->data.fd, &st)) {
+ pr_err("dso mmap failed, fstat: %s\n", strerror(errno));
+ return -1;
+ }
+ dso->data.file_size = st.st_size;
+ }
+
+ return 0;
+}
+
+static ssize_t data_read_offset(struct dso *dso, u64 offset,
+ u8 *data, ssize_t size)
+{
+ if (data_file_size(dso))
+ return -1;
+
+ /* Check the offset sanity. */
+ if (offset > dso->data.file_size)
+ return -1;
+
+ if (offset + size < offset)
+ return -1;
+
+ return cached_read(dso, offset, data, size);
+}
+
+/**
+ * dso__data_read_offset - Read data from dso file offset
+ * @dso: dso object
+ * @machine: machine object
+ * @offset: file offset
+ * @data: buffer to store data
+ * @size: size of the @data buffer
+ *
+ * External interface to read data from dso file offset. Open
+ * dso data file and use cached_read to get the data.
+ */
+ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
+ u64 offset, u8 *data, ssize_t size)
+{
+ if (dso__data_fd(dso, machine) < 0)
+ return -1;
+
+ return data_read_offset(dso, offset, data, size);
+}
+
+/**
+ * dso__data_read_addr - Read data from dso address
+ * @dso: dso object
+ * @machine: machine object
+ * @add: virtual memory address
+ * @data: buffer to store data
+ * @size: size of the @data buffer
+ *
+ * External interface to read data from dso address.
+ */
ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
struct machine *machine, u64 addr,
u8 *data, ssize_t size)
@@ -473,7 +699,8 @@ struct dso *dso__new(const char *name)
dso__set_short_name(dso, dso->name, false);
for (i = 0; i < MAP__NR_TYPES; ++i)
dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
- dso->cache = RB_ROOT;
+ dso->data.cache = RB_ROOT;
+ dso->data.fd = -1;
dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
dso->binary_type = DSO_BINARY_TYPE__NOT_FOUND;
dso->loaded = 0;
@@ -485,6 +712,7 @@ struct dso *dso__new(const char *name)
dso->kernel = DSO_TYPE_USER;
dso->needs_swap = DSO_SWAP__UNSET;
INIT_LIST_HEAD(&dso->node);
+ INIT_LIST_HEAD(&dso->data.open_entry);
}
return dso;
@@ -506,7 +734,8 @@ void dso__delete(struct dso *dso)
dso->long_name_allocated = false;
}
- dso_cache__free(&dso->cache);
+ dso__data_close(dso);
+ dso_cache__free(&dso->data.cache);
dso__free_a2l(dso);
zfree(&dso->symsrc_filename);
free(dso);
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index ab06f1c03655..ad553ba257bf 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -4,7 +4,7 @@
#include <linux/types.h>
#include <linux/rbtree.h>
#include <stdbool.h>
-#include "types.h"
+#include <linux/types.h>
#include "map.h"
#include "build-id.h"
@@ -76,7 +76,6 @@ struct dso {
struct list_head node;
struct rb_root symbols[MAP__NR_TYPES];
struct rb_root symbol_names[MAP__NR_TYPES];
- struct rb_root cache;
void *a2l;
char *symsrc_filename;
unsigned int a2l_fails;
@@ -99,6 +98,15 @@ struct dso {
const char *long_name;
u16 long_name_len;
u16 short_name_len;
+
+ /* dso data file */
+ struct {
+ struct rb_root cache;
+ int fd;
+ size_t file_size;
+ struct list_head open_entry;
+ } data;
+
char name[0];
};
@@ -141,7 +149,47 @@ char dso__symtab_origin(const struct dso *dso);
int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type,
char *root_dir, char *filename, size_t size);
+/*
+ * The dso__data_* external interface provides following functions:
+ * dso__data_fd
+ * dso__data_close
+ * dso__data_read_offset
+ * dso__data_read_addr
+ *
+ * Please refer to the dso.c object code for each function and
+ * arguments documentation. Following text tries to explain the
+ * dso file descriptor caching.
+ *
+ * The dso__data* interface allows caching of opened file descriptors
+ * to speed up the dso data accesses. The idea is to leave the file
+ * descriptor opened ideally for the whole life of the dso object.
+ *
+ * The current usage of the dso__data_* interface is as follows:
+ *
+ * Get DSO's fd:
+ * int fd = dso__data_fd(dso, machine);
+ * USE 'fd' SOMEHOW
+ *
+ * Read DSO's data:
+ * n = dso__data_read_offset(dso_0, &machine, 0, buf, BUFSIZE);
+ * n = dso__data_read_addr(dso_0, &machine, 0, buf, BUFSIZE);
+ *
+ * Eventually close DSO's fd:
+ * dso__data_close(dso);
+ *
+ * It is not necessary to close the DSO object data file. Each time new
+ * DSO data file is opened, the limit (RLIMIT_NOFILE/2) is checked. Once
+ * it is crossed, the oldest opened DSO object is closed.
+ *
+ * The dso__delete function calls close_dso function to ensure the
+ * data file descriptor gets closed/unmapped before the dso object
+ * is freed.
+ *
+ * TODO
+*/
int dso__data_fd(struct dso *dso, struct machine *machine);
+void dso__data_close(struct dso *dso);
+
ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
u64 offset, u8 *data, ssize_t size);
ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index 7defd77105d0..cc66c4049e09 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -747,14 +747,17 @@ struct __find_variable_param {
static int __die_find_variable_cb(Dwarf_Die *die_mem, void *data)
{
struct __find_variable_param *fvp = data;
+ Dwarf_Attribute attr;
int tag;
tag = dwarf_tag(die_mem);
if ((tag == DW_TAG_formal_parameter ||
tag == DW_TAG_variable) &&
- die_compare_name(die_mem, fvp->name))
+ die_compare_name(die_mem, fvp->name) &&
+ /* Does the DIE have location information or external instance? */
+ (dwarf_attr(die_mem, DW_AT_external, &attr) ||
+ dwarf_attr(die_mem, DW_AT_location, &attr)))
return DIE_FIND_CB_END;
-
if (dwarf_haspc(die_mem, fvp->addr))
return DIE_FIND_CB_CONTINUE;
else
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 9d12aa6dd485..d0281bdfa582 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -1,4 +1,5 @@
#include <linux/types.h>
+#include <sys/mman.h>
#include "event.h"
#include "debug.h"
#include "hist.h"
@@ -178,13 +179,14 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
return -1;
}
- event->header.type = PERF_RECORD_MMAP;
+ event->header.type = PERF_RECORD_MMAP2;
while (1) {
char bf[BUFSIZ];
char prot[5];
char execname[PATH_MAX];
char anonstr[] = "//anon";
+ unsigned int ino;
size_t size;
ssize_t n;
@@ -195,15 +197,20 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
strcpy(execname, "");
/* 00400000-0040c000 r-xp 00000000 fd:01 41038 /bin/cat */
- n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %*x:%*x %*u %s\n",
- &event->mmap.start, &event->mmap.len, prot,
- &event->mmap.pgoff,
- execname);
+ n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %s\n",
+ &event->mmap2.start, &event->mmap2.len, prot,
+ &event->mmap2.pgoff, &event->mmap2.maj,
+ &event->mmap2.min,
+ &ino, execname);
+
/*
* Anon maps don't have the execname.
*/
- if (n < 4)
+ if (n < 7)
continue;
+
+ event->mmap2.ino = (u64)ino;
+
/*
* Just like the kernel, see __perf_event_mmap in kernel/perf_event.c
*/
@@ -212,6 +219,21 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
else
event->header.misc = PERF_RECORD_MISC_GUEST_USER;
+ /* map protection and flags bits */
+ event->mmap2.prot = 0;
+ event->mmap2.flags = 0;
+ if (prot[0] == 'r')
+ event->mmap2.prot |= PROT_READ;
+ if (prot[1] == 'w')
+ event->mmap2.prot |= PROT_WRITE;
+ if (prot[2] == 'x')
+ event->mmap2.prot |= PROT_EXEC;
+
+ if (prot[3] == 's')
+ event->mmap2.flags |= MAP_SHARED;
+ else
+ event->mmap2.flags |= MAP_PRIVATE;
+
if (prot[2] != 'x') {
if (!mmap_data || prot[0] != 'r')
continue;
@@ -223,15 +245,15 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
strcpy(execname, anonstr);
size = strlen(execname) + 1;
- memcpy(event->mmap.filename, execname, size);
+ memcpy(event->mmap2.filename, execname, size);
size = PERF_ALIGN(size, sizeof(u64));
- event->mmap.len -= event->mmap.start;
- event->mmap.header.size = (sizeof(event->mmap) -
- (sizeof(event->mmap.filename) - size));
- memset(event->mmap.filename + size, 0, machine->id_hdr_size);
- event->mmap.header.size += machine->id_hdr_size;
- event->mmap.pid = tgid;
- event->mmap.tid = pid;
+ event->mmap2.len -= event->mmap.start;
+ event->mmap2.header.size = (sizeof(event->mmap2) -
+ (sizeof(event->mmap2.filename) - size));
+ memset(event->mmap2.filename + size, 0, machine->id_hdr_size);
+ event->mmap2.header.size += machine->id_hdr_size;
+ event->mmap2.pid = tgid;
+ event->mmap2.tid = pid;
if (process(tool, event, &synth_sample, machine) != 0) {
rc = -1;
@@ -612,12 +634,15 @@ size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp)
{
return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64
- " %02x:%02x %"PRIu64" %"PRIu64"]: %c %s\n",
+ " %02x:%02x %"PRIu64" %"PRIu64"]: %c%c%c%c %s\n",
event->mmap2.pid, event->mmap2.tid, event->mmap2.start,
event->mmap2.len, event->mmap2.pgoff, event->mmap2.maj,
event->mmap2.min, event->mmap2.ino,
event->mmap2.ino_generation,
- (event->header.misc & PERF_RECORD_MISC_MMAP_DATA) ? 'r' : 'x',
+ (event->mmap2.prot & PROT_READ) ? 'r' : '-',
+ (event->mmap2.prot & PROT_WRITE) ? 'w' : '-',
+ (event->mmap2.prot & PROT_EXEC) ? 'x' : '-',
+ (event->mmap2.flags & MAP_SHARED) ? 's' : 'p',
event->mmap2.filename);
}
@@ -699,7 +724,7 @@ void thread__find_addr_map(struct thread *thread,
enum map_type type, u64 addr,
struct addr_location *al)
{
- struct map_groups *mg = &thread->mg;
+ struct map_groups *mg = thread->mg;
bool load_map = false;
al->machine = machine;
@@ -788,7 +813,7 @@ int perf_event__preprocess_sample(const union perf_event *event,
{
u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
struct thread *thread = machine__findnew_thread(machine, sample->pid,
- sample->pid);
+ sample->tid);
if (thread == NULL)
return -1;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 38457d447a13..e5dd40addb30 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -7,6 +7,7 @@
#include "../perf.h"
#include "map.h"
#include "build-id.h"
+#include "perf_regs.h"
struct mmap_event {
struct perf_event_header header;
@@ -27,6 +28,8 @@ struct mmap2_event {
u32 min;
u64 ino;
u64 ino_generation;
+ u32 prot;
+ u32 flags;
char filename[PATH_MAX];
};
@@ -87,6 +90,10 @@ struct regs_dump {
u64 abi;
u64 mask;
u64 *regs;
+
+ /* Cached values/mask filled by first register access. */
+ u64 cache_regs[PERF_REGS_MAX];
+ u64 cache_mask;
};
struct stack_dump {
@@ -112,6 +119,30 @@ struct sample_read {
};
};
+struct ip_callchain {
+ u64 nr;
+ u64 ips[0];
+};
+
+struct branch_flags {
+ u64 mispred:1;
+ u64 predicted:1;
+ u64 in_tx:1;
+ u64 abort:1;
+ u64 reserved:60;
+};
+
+struct branch_entry {
+ u64 from;
+ u64 to;
+ struct branch_flags flags;
+};
+
+struct branch_stack {
+ u64 nr;
+ struct branch_entry entries[0];
+};
+
struct perf_sample {
u64 ip;
u32 pid, tid;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 5c28d82b76c4..8606175fe1e8 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -589,10 +589,10 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
}
/*
- * We default some events to a 1 default interval. But keep
+ * We default some events to have a default interval. But keep
* it a weak assumption overridable by the user.
*/
- if (!attr->sample_period || (opts->user_freq != UINT_MAX &&
+ if (!attr->sample_period || (opts->user_freq != UINT_MAX ||
opts->user_interval != ULLONG_MAX)) {
if (opts->freq) {
perf_evsel__set_sample_bit(evsel, PERIOD);
@@ -659,6 +659,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
perf_evsel__set_sample_bit(evsel, WEIGHT);
attr->mmap = track;
+ attr->mmap2 = track && !perf_missing_features.mmap2;
attr->comm = track;
if (opts->sample_transaction)
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 0c9926cfb292..a52e9a5bb2d0 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -5,12 +5,12 @@
#include <stdbool.h>
#include <stddef.h>
#include <linux/perf_event.h>
-#include "types.h"
+#include <linux/types.h>
#include "xyarray.h"
#include "cgroup.h"
#include "hist.h"
#include "symbol.h"
-
+
struct perf_counts_values {
union {
struct {
@@ -91,6 +91,11 @@ struct perf_evsel {
char *group_name;
};
+union u64_swap {
+ u64 val64;
+ u32 val32[2];
+};
+
#define hists_to_evsel(h) container_of(h, struct perf_evsel, hists)
struct cpu_map;
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index a2d047bdf4ef..d08cfe499404 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -4,10 +4,10 @@
#include <linux/perf_event.h>
#include <sys/types.h>
#include <stdbool.h>
-#include "types.h"
+#include <linux/bitmap.h>
+#include <linux/types.h>
#include "event.h"
-#include <linux/bitmap.h>
enum {
HEADER_RESERVED = 0, /* always cleared */
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index f38590d7561b..30df6187ee02 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -4,6 +4,7 @@
#include "session.h"
#include "sort.h"
#include "evsel.h"
+#include "annotate.h"
#include <math.h>
static bool hists__filter_entry_by_dso(struct hists *hists,
@@ -127,6 +128,8 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
+ unresolved_col_width + 2;
hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL,
symlen);
+ hists__new_col_len(hists, HISTC_MEM_DCACHELINE,
+ symlen + 1);
} else {
symlen = unresolved_col_width + 4 + 2;
hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL,
@@ -225,14 +228,20 @@ static void he_stat__decay(struct he_stat *he_stat)
static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
{
u64 prev_period = he->stat.period;
+ u64 diff;
if (prev_period == 0)
return true;
he_stat__decay(&he->stat);
+ if (symbol_conf.cumulate_callchain)
+ he_stat__decay(he->stat_acc);
+ diff = prev_period - he->stat.period;
+
+ hists->stats.total_period -= diff;
if (!he->filtered)
- hists->stats.total_period -= prev_period - he->stat.period;
+ hists->stats.total_non_filtered_period -= diff;
return he->stat.period == 0;
}
@@ -259,8 +268,11 @@ void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel)
if (sort__need_collapse)
rb_erase(&n->rb_node_in, &hists->entries_collapsed);
- hist_entry__free(n);
--hists->nr_entries;
+ if (!n->filtered)
+ --hists->nr_non_filtered_entries;
+
+ hist_entry__free(n);
}
}
}
@@ -269,14 +281,31 @@ void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel)
* histogram, sorted on item, collects periods
*/
-static struct hist_entry *hist_entry__new(struct hist_entry *template)
+static struct hist_entry *hist_entry__new(struct hist_entry *template,
+ bool sample_self)
{
- size_t callchain_size = symbol_conf.use_callchain ? sizeof(struct callchain_root) : 0;
- struct hist_entry *he = zalloc(sizeof(*he) + callchain_size);
+ size_t callchain_size = 0;
+ struct hist_entry *he;
+
+ if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain)
+ callchain_size = sizeof(struct callchain_root);
+
+ he = zalloc(sizeof(*he) + callchain_size);
if (he != NULL) {
*he = *template;
+ if (symbol_conf.cumulate_callchain) {
+ he->stat_acc = malloc(sizeof(he->stat));
+ if (he->stat_acc == NULL) {
+ free(he);
+ return NULL;
+ }
+ memcpy(he->stat_acc, &he->stat, sizeof(he->stat));
+ if (!sample_self)
+ memset(&he->stat, 0, sizeof(he->stat));
+ }
+
if (he->ms.map)
he->ms.map->referenced = true;
@@ -288,6 +317,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template)
*/
he->branch_info = malloc(sizeof(*he->branch_info));
if (he->branch_info == NULL) {
+ free(he->stat_acc);
free(he);
return NULL;
}
@@ -317,15 +347,6 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template)
return he;
}
-void hists__inc_nr_entries(struct hists *hists, struct hist_entry *h)
-{
- if (!h->filtered) {
- hists__calc_col_len(hists, h);
- ++hists->nr_entries;
- hists->stats.total_period += h->stat.period;
- }
-}
-
static u8 symbol__parent_filter(const struct symbol *parent)
{
if (symbol_conf.exclude_other && parent == NULL)
@@ -335,7 +356,8 @@ static u8 symbol__parent_filter(const struct symbol *parent)
static struct hist_entry *add_hist_entry(struct hists *hists,
struct hist_entry *entry,
- struct addr_location *al)
+ struct addr_location *al,
+ bool sample_self)
{
struct rb_node **p;
struct rb_node *parent = NULL;
@@ -359,7 +381,10 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
cmp = hist_entry__cmp(he, entry);
if (!cmp) {
- he_stat__add_period(&he->stat, period, weight);
+ if (sample_self)
+ he_stat__add_period(&he->stat, period, weight);
+ if (symbol_conf.cumulate_callchain)
+ he_stat__add_period(he->stat_acc, period, weight);
/*
* This mem info was allocated from sample__resolve_mem
@@ -387,15 +412,17 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
p = &(*p)->rb_right;
}
- he = hist_entry__new(entry);
+ he = hist_entry__new(entry, sample_self);
if (!he)
return NULL;
- hists->nr_entries++;
rb_link_node(&he->rb_node_in, parent, p);
rb_insert_color(&he->rb_node_in, hists->entries_in);
out:
- he_stat__add_cpumode_period(&he->stat, al->cpumode, period);
+ if (sample_self)
+ he_stat__add_cpumode_period(&he->stat, al->cpumode, period);
+ if (symbol_conf.cumulate_callchain)
+ he_stat__add_cpumode_period(he->stat_acc, al->cpumode, period);
return he;
}
@@ -404,7 +431,8 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
struct symbol *sym_parent,
struct branch_info *bi,
struct mem_info *mi,
- u64 period, u64 weight, u64 transaction)
+ u64 period, u64 weight, u64 transaction,
+ bool sample_self)
{
struct hist_entry entry = {
.thread = al->thread,
@@ -413,9 +441,10 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
.map = al->map,
.sym = al->sym,
},
- .cpu = al->cpu,
- .ip = al->addr,
- .level = al->level,
+ .cpu = al->cpu,
+ .cpumode = al->cpumode,
+ .ip = al->addr,
+ .level = al->level,
.stat = {
.nr_events = 1,
.period = period,
@@ -429,17 +458,442 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
.transaction = transaction,
};
- return add_hist_entry(hists, &entry, al);
+ return add_hist_entry(hists, &entry, al, sample_self);
+}
+
+static int
+iter_next_nop_entry(struct hist_entry_iter *iter __maybe_unused,
+ struct addr_location *al __maybe_unused)
+{
+ return 0;
+}
+
+static int
+iter_add_next_nop_entry(struct hist_entry_iter *iter __maybe_unused,
+ struct addr_location *al __maybe_unused)
+{
+ return 0;
+}
+
+static int
+iter_prepare_mem_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+ struct perf_sample *sample = iter->sample;
+ struct mem_info *mi;
+
+ mi = sample__resolve_mem(sample, al);
+ if (mi == NULL)
+ return -ENOMEM;
+
+ iter->priv = mi;
+ return 0;
+}
+
+static int
+iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+ u64 cost;
+ struct mem_info *mi = iter->priv;
+ struct hist_entry *he;
+
+ if (mi == NULL)
+ return -EINVAL;
+
+ cost = iter->sample->weight;
+ if (!cost)
+ cost = 1;
+
+ /*
+ * must pass period=weight in order to get the correct
+ * sorting from hists__collapse_resort() which is solely
+ * based on periods. We want sorting be done on nr_events * weight
+ * and this is indirectly achieved by passing period=weight here
+ * and the he_stat__add_period() function.
+ */
+ he = __hists__add_entry(&iter->evsel->hists, al, iter->parent, NULL, mi,
+ cost, cost, 0, true);
+ if (!he)
+ return -ENOMEM;
+
+ iter->he = he;
+ return 0;
+}
+
+static int
+iter_finish_mem_entry(struct hist_entry_iter *iter,
+ struct addr_location *al __maybe_unused)
+{
+ struct perf_evsel *evsel = iter->evsel;
+ struct hist_entry *he = iter->he;
+ int err = -EINVAL;
+
+ if (he == NULL)
+ goto out;
+
+ hists__inc_nr_samples(&evsel->hists, he->filtered);
+
+ err = hist_entry__append_callchain(he, iter->sample);
+
+out:
+ /*
+ * We don't need to free iter->priv (mem_info) here since
+ * the mem info was either already freed in add_hist_entry() or
+ * passed to a new hist entry by hist_entry__new().
+ */
+ iter->priv = NULL;
+
+ iter->he = NULL;
+ return err;
+}
+
+static int
+iter_prepare_branch_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+ struct branch_info *bi;
+ struct perf_sample *sample = iter->sample;
+
+ bi = sample__resolve_bstack(sample, al);
+ if (!bi)
+ return -ENOMEM;
+
+ iter->curr = 0;
+ iter->total = sample->branch_stack->nr;
+
+ iter->priv = bi;
+ return 0;
+}
+
+static int
+iter_add_single_branch_entry(struct hist_entry_iter *iter __maybe_unused,
+ struct addr_location *al __maybe_unused)
+{
+ /* to avoid calling callback function */
+ iter->he = NULL;
+
+ return 0;
+}
+
+static int
+iter_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+ struct branch_info *bi = iter->priv;
+ int i = iter->curr;
+
+ if (bi == NULL)
+ return 0;
+
+ if (iter->curr >= iter->total)
+ return 0;
+
+ al->map = bi[i].to.map;
+ al->sym = bi[i].to.sym;
+ al->addr = bi[i].to.addr;
+ return 1;
+}
+
+static int
+iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+ struct branch_info *bi;
+ struct perf_evsel *evsel = iter->evsel;
+ struct hist_entry *he = NULL;
+ int i = iter->curr;
+ int err = 0;
+
+ bi = iter->priv;
+
+ if (iter->hide_unresolved && !(bi[i].from.sym && bi[i].to.sym))
+ goto out;
+
+ /*
+ * The report shows the percentage of total branches captured
+ * and not events sampled. Thus we use a pseudo period of 1.
+ */
+ he = __hists__add_entry(&evsel->hists, al, iter->parent, &bi[i], NULL,
+ 1, 1, 0, true);
+ if (he == NULL)
+ return -ENOMEM;
+
+ hists__inc_nr_samples(&evsel->hists, he->filtered);
+
+out:
+ iter->he = he;
+ iter->curr++;
+ return err;
+}
+
+static int
+iter_finish_branch_entry(struct hist_entry_iter *iter,
+ struct addr_location *al __maybe_unused)
+{
+ zfree(&iter->priv);
+ iter->he = NULL;
+
+ return iter->curr >= iter->total ? 0 : -1;
+}
+
+static int
+iter_prepare_normal_entry(struct hist_entry_iter *iter __maybe_unused,
+ struct addr_location *al __maybe_unused)
+{
+ return 0;
+}
+
+static int
+iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+ struct perf_evsel *evsel = iter->evsel;
+ struct perf_sample *sample = iter->sample;
+ struct hist_entry *he;
+
+ he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
+ sample->period, sample->weight,
+ sample->transaction, true);
+ if (he == NULL)
+ return -ENOMEM;
+
+ iter->he = he;
+ return 0;
+}
+
+static int
+iter_finish_normal_entry(struct hist_entry_iter *iter,
+ struct addr_location *al __maybe_unused)
+{
+ struct hist_entry *he = iter->he;
+ struct perf_evsel *evsel = iter->evsel;
+ struct perf_sample *sample = iter->sample;
+
+ if (he == NULL)
+ return 0;
+
+ iter->he = NULL;
+
+ hists__inc_nr_samples(&evsel->hists, he->filtered);
+
+ return hist_entry__append_callchain(he, sample);
+}
+
+static int
+iter_prepare_cumulative_entry(struct hist_entry_iter *iter __maybe_unused,
+ struct addr_location *al __maybe_unused)
+{
+ struct hist_entry **he_cache;
+
+ callchain_cursor_commit(&callchain_cursor);
+
+ /*
+ * This is for detecting cycles or recursions so that they're
+ * cumulated only one time to prevent entries more than 100%
+ * overhead.
+ */
+ he_cache = malloc(sizeof(*he_cache) * (PERF_MAX_STACK_DEPTH + 1));
+ if (he_cache == NULL)
+ return -ENOMEM;
+
+ iter->priv = he_cache;
+ iter->curr = 0;
+
+ return 0;
+}
+
+static int
+iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
+ struct addr_location *al)
+{
+ struct perf_evsel *evsel = iter->evsel;
+ struct perf_sample *sample = iter->sample;
+ struct hist_entry **he_cache = iter->priv;
+ struct hist_entry *he;
+ int err = 0;
+
+ he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
+ sample->period, sample->weight,
+ sample->transaction, true);
+ if (he == NULL)
+ return -ENOMEM;
+
+ iter->he = he;
+ he_cache[iter->curr++] = he;
+
+ callchain_append(he->callchain, &callchain_cursor, sample->period);
+
+ /*
+ * We need to re-initialize the cursor since callchain_append()
+ * advanced the cursor to the end.
+ */
+ callchain_cursor_commit(&callchain_cursor);
+
+ hists__inc_nr_samples(&evsel->hists, he->filtered);
+
+ return err;
+}
+
+static int
+iter_next_cumulative_entry(struct hist_entry_iter *iter,
+ struct addr_location *al)
+{
+ struct callchain_cursor_node *node;
+
+ node = callchain_cursor_current(&callchain_cursor);
+ if (node == NULL)
+ return 0;
+
+ return fill_callchain_info(al, node, iter->hide_unresolved);
+}
+
+static int
+iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
+ struct addr_location *al)
+{
+ struct perf_evsel *evsel = iter->evsel;
+ struct perf_sample *sample = iter->sample;
+ struct hist_entry **he_cache = iter->priv;
+ struct hist_entry *he;
+ struct hist_entry he_tmp = {
+ .cpu = al->cpu,
+ .thread = al->thread,
+ .comm = thread__comm(al->thread),
+ .ip = al->addr,
+ .ms = {
+ .map = al->map,
+ .sym = al->sym,
+ },
+ .parent = iter->parent,
+ };
+ int i;
+ struct callchain_cursor cursor;
+
+ callchain_cursor_snapshot(&cursor, &callchain_cursor);
+
+ callchain_cursor_advance(&callchain_cursor);
+
+ /*
+ * Check if there's duplicate entries in the callchain.
+ * It's possible that it has cycles or recursive calls.
+ */
+ for (i = 0; i < iter->curr; i++) {
+ if (hist_entry__cmp(he_cache[i], &he_tmp) == 0) {
+ /* to avoid calling callback function */
+ iter->he = NULL;
+ return 0;
+ }
+ }
+
+ he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
+ sample->period, sample->weight,
+ sample->transaction, false);
+ if (he == NULL)
+ return -ENOMEM;
+
+ iter->he = he;
+ he_cache[iter->curr++] = he;
+
+ callchain_append(he->callchain, &cursor, sample->period);
+ return 0;
+}
+
+static int
+iter_finish_cumulative_entry(struct hist_entry_iter *iter,
+ struct addr_location *al __maybe_unused)
+{
+ zfree(&iter->priv);
+ iter->he = NULL;
+
+ return 0;
+}
+
+const struct hist_iter_ops hist_iter_mem = {
+ .prepare_entry = iter_prepare_mem_entry,
+ .add_single_entry = iter_add_single_mem_entry,
+ .next_entry = iter_next_nop_entry,
+ .add_next_entry = iter_add_next_nop_entry,
+ .finish_entry = iter_finish_mem_entry,
+};
+
+const struct hist_iter_ops hist_iter_branch = {
+ .prepare_entry = iter_prepare_branch_entry,
+ .add_single_entry = iter_add_single_branch_entry,
+ .next_entry = iter_next_branch_entry,
+ .add_next_entry = iter_add_next_branch_entry,
+ .finish_entry = iter_finish_branch_entry,
+};
+
+const struct hist_iter_ops hist_iter_normal = {
+ .prepare_entry = iter_prepare_normal_entry,
+ .add_single_entry = iter_add_single_normal_entry,
+ .next_entry = iter_next_nop_entry,
+ .add_next_entry = iter_add_next_nop_entry,
+ .finish_entry = iter_finish_normal_entry,
+};
+
+const struct hist_iter_ops hist_iter_cumulative = {
+ .prepare_entry = iter_prepare_cumulative_entry,
+ .add_single_entry = iter_add_single_cumulative_entry,
+ .next_entry = iter_next_cumulative_entry,
+ .add_next_entry = iter_add_next_cumulative_entry,
+ .finish_entry = iter_finish_cumulative_entry,
+};
+
+int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
+ struct perf_evsel *evsel, struct perf_sample *sample,
+ int max_stack_depth, void *arg)
+{
+ int err, err2;
+
+ err = sample__resolve_callchain(sample, &iter->parent, evsel, al,
+ max_stack_depth);
+ if (err)
+ return err;
+
+ iter->evsel = evsel;
+ iter->sample = sample;
+
+ err = iter->ops->prepare_entry(iter, al);
+ if (err)
+ goto out;
+
+ err = iter->ops->add_single_entry(iter, al);
+ if (err)
+ goto out;
+
+ if (iter->he && iter->add_entry_cb) {
+ err = iter->add_entry_cb(iter, al, true, arg);
+ if (err)
+ goto out;
+ }
+
+ while (iter->ops->next_entry(iter, al)) {
+ err = iter->ops->add_next_entry(iter, al);
+ if (err)
+ break;
+
+ if (iter->he && iter->add_entry_cb) {
+ err = iter->add_entry_cb(iter, al, false, arg);
+ if (err)
+ goto out;
+ }
+ }
+
+out:
+ err2 = iter->ops->finish_entry(iter, al);
+ if (!err)
+ err = err2;
+
+ return err;
}
int64_t
hist_entry__cmp(struct hist_entry *left, struct hist_entry *right)
{
- struct sort_entry *se;
+ struct perf_hpp_fmt *fmt;
int64_t cmp = 0;
- list_for_each_entry(se, &hist_entry__sort_list, list) {
- cmp = se->se_cmp(left, right);
+ perf_hpp__for_each_sort_list(fmt) {
+ if (perf_hpp__should_skip(fmt))
+ continue;
+
+ cmp = fmt->cmp(left, right);
if (cmp)
break;
}
@@ -450,15 +904,14 @@ hist_entry__cmp(struct hist_entry *left, struct hist_entry *right)
int64_t
hist_entry__collapse(struct hist_entry *left, struct hist_entry *right)
{
- struct sort_entry *se;
+ struct perf_hpp_fmt *fmt;
int64_t cmp = 0;
- list_for_each_entry(se, &hist_entry__sort_list, list) {
- int64_t (*f)(struct hist_entry *, struct hist_entry *);
-
- f = se->se_collapse ?: se->se_cmp;
+ perf_hpp__for_each_sort_list(fmt) {
+ if (perf_hpp__should_skip(fmt))
+ continue;
- cmp = f(left, right);
+ cmp = fmt->collapse(left, right);
if (cmp)
break;
}
@@ -470,6 +923,7 @@ void hist_entry__free(struct hist_entry *he)
{
zfree(&he->branch_info);
zfree(&he->mem_info);
+ zfree(&he->stat_acc);
free_srcline(he->srcline);
free(he);
}
@@ -495,6 +949,8 @@ static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
if (!cmp) {
he_stat__add_stat(&iter->stat, &he->stat);
+ if (symbol_conf.cumulate_callchain)
+ he_stat__add_stat(iter->stat_acc, he->stat_acc);
if (symbol_conf.use_callchain) {
callchain_cursor_reset(&callchain_cursor);
@@ -571,64 +1027,50 @@ void hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
}
}
-/*
- * reverse the map, sort on period.
- */
-
-static int period_cmp(u64 period_a, u64 period_b)
-{
- if (period_a > period_b)
- return 1;
- if (period_a < period_b)
- return -1;
- return 0;
-}
-
-static int hist_entry__sort_on_period(struct hist_entry *a,
- struct hist_entry *b)
+static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b)
{
- int ret;
- int i, nr_members;
- struct perf_evsel *evsel;
- struct hist_entry *pair;
- u64 *periods_a, *periods_b;
+ struct perf_hpp_fmt *fmt;
+ int64_t cmp = 0;
- ret = period_cmp(a->stat.period, b->stat.period);
- if (ret || !symbol_conf.event_group)
- return ret;
+ perf_hpp__for_each_sort_list(fmt) {
+ if (perf_hpp__should_skip(fmt))
+ continue;
- evsel = hists_to_evsel(a->hists);
- nr_members = evsel->nr_members;
- if (nr_members <= 1)
- return ret;
+ cmp = fmt->sort(a, b);
+ if (cmp)
+ break;
+ }
- periods_a = zalloc(sizeof(periods_a) * nr_members);
- periods_b = zalloc(sizeof(periods_b) * nr_members);
+ return cmp;
+}
- if (!periods_a || !periods_b)
- goto out;
+static void hists__reset_filter_stats(struct hists *hists)
+{
+ hists->nr_non_filtered_entries = 0;
+ hists->stats.total_non_filtered_period = 0;
+}
- list_for_each_entry(pair, &a->pairs.head, pairs.node) {
- evsel = hists_to_evsel(pair->hists);
- periods_a[perf_evsel__group_idx(evsel)] = pair->stat.period;
- }
+void hists__reset_stats(struct hists *hists)
+{
+ hists->nr_entries = 0;
+ hists->stats.total_period = 0;
- list_for_each_entry(pair, &b->pairs.head, pairs.node) {
- evsel = hists_to_evsel(pair->hists);
- periods_b[perf_evsel__group_idx(evsel)] = pair->stat.period;
- }
+ hists__reset_filter_stats(hists);
+}
- for (i = 1; i < nr_members; i++) {
- ret = period_cmp(periods_a[i], periods_b[i]);
- if (ret)
- break;
- }
+static void hists__inc_filter_stats(struct hists *hists, struct hist_entry *h)
+{
+ hists->nr_non_filtered_entries++;
+ hists->stats.total_non_filtered_period += h->stat.period;
+}
-out:
- free(periods_a);
- free(periods_b);
+void hists__inc_stats(struct hists *hists, struct hist_entry *h)
+{
+ if (!h->filtered)
+ hists__inc_filter_stats(hists, h);
- return ret;
+ hists->nr_entries++;
+ hists->stats.total_period += h->stat.period;
}
static void __hists__insert_output_entry(struct rb_root *entries,
@@ -647,7 +1089,7 @@ static void __hists__insert_output_entry(struct rb_root *entries,
parent = *p;
iter = rb_entry(parent, struct hist_entry, rb_node);
- if (hist_entry__sort_on_period(he, iter) > 0)
+ if (hist_entry__sort(he, iter) > 0)
p = &(*p)->rb_left;
else
p = &(*p)->rb_right;
@@ -674,8 +1116,7 @@ void hists__output_resort(struct hists *hists)
next = rb_first(root);
hists->entries = RB_ROOT;
- hists->nr_entries = 0;
- hists->stats.total_period = 0;
+ hists__reset_stats(hists);
hists__reset_col_len(hists);
while (next) {
@@ -683,7 +1124,10 @@ void hists__output_resort(struct hists *hists)
next = rb_next(&n->rb_node_in);
__hists__insert_output_entry(&hists->entries, n, min_callchain_hits);
- hists__inc_nr_entries(hists, n);
+ hists__inc_stats(hists, n);
+
+ if (!n->filtered)
+ hists__calc_col_len(hists, n);
}
}
@@ -694,13 +1138,13 @@ static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h
if (h->filtered)
return;
- ++hists->nr_entries;
- if (h->ms.unfolded)
- hists->nr_entries += h->nr_rows;
+ /* force fold unfiltered entry for simplicity */
+ h->ms.unfolded = false;
h->row_offset = 0;
- hists->stats.total_period += h->stat.period;
- hists->stats.nr_events[PERF_RECORD_SAMPLE] += h->stat.nr_events;
+ hists->stats.nr_non_filtered_samples += h->stat.nr_events;
+
+ hists__inc_filter_stats(hists, h);
hists__calc_col_len(hists, h);
}
@@ -721,8 +1165,9 @@ void hists__filter_by_dso(struct hists *hists)
{
struct rb_node *nd;
- hists->nr_entries = hists->stats.total_period = 0;
- hists->stats.nr_events[PERF_RECORD_SAMPLE] = 0;
+ hists->stats.nr_non_filtered_samples = 0;
+
+ hists__reset_filter_stats(hists);
hists__reset_col_len(hists);
for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
@@ -754,8 +1199,9 @@ void hists__filter_by_thread(struct hists *hists)
{
struct rb_node *nd;
- hists->nr_entries = hists->stats.total_period = 0;
- hists->stats.nr_events[PERF_RECORD_SAMPLE] = 0;
+ hists->stats.nr_non_filtered_samples = 0;
+
+ hists__reset_filter_stats(hists);
hists__reset_col_len(hists);
for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
@@ -785,8 +1231,9 @@ void hists__filter_by_symbol(struct hists *hists)
{
struct rb_node *nd;
- hists->nr_entries = hists->stats.total_period = 0;
- hists->stats.nr_events[PERF_RECORD_SAMPLE] = 0;
+ hists->stats.nr_non_filtered_samples = 0;
+
+ hists__reset_filter_stats(hists);
hists__reset_col_len(hists);
for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
@@ -810,6 +1257,13 @@ void hists__inc_nr_events(struct hists *hists, u32 type)
events_stats__inc(&hists->stats, type);
}
+void hists__inc_nr_samples(struct hists *hists, bool filtered)
+{
+ events_stats__inc(&hists->stats, PERF_RECORD_SAMPLE);
+ if (!filtered)
+ hists->stats.nr_non_filtered_samples++;
+}
+
static struct hist_entry *hists__add_dummy_entry(struct hists *hists,
struct hist_entry *pair)
{
@@ -841,13 +1295,13 @@ static struct hist_entry *hists__add_dummy_entry(struct hists *hists,
p = &(*p)->rb_right;
}
- he = hist_entry__new(pair);
+ he = hist_entry__new(pair, true);
if (he) {
memset(&he->stat, 0, sizeof(he->stat));
he->hists = hists;
rb_link_node(&he->rb_node_in, parent, p);
rb_insert_color(&he->rb_node_in, root);
- hists__inc_nr_entries(hists, he);
+ hists__inc_stats(hists, he);
he->dummy = true;
}
out:
@@ -931,3 +1385,30 @@ int hists__link(struct hists *leader, struct hists *other)
return 0;
}
+
+u64 hists__total_period(struct hists *hists)
+{
+ return symbol_conf.filter_relative ? hists->stats.total_non_filtered_period :
+ hists->stats.total_period;
+}
+
+int parse_filter_percentage(const struct option *opt __maybe_unused,
+ const char *arg, int unset __maybe_unused)
+{
+ if (!strcmp(arg, "relative"))
+ symbol_conf.filter_relative = true;
+ else if (!strcmp(arg, "absolute"))
+ symbol_conf.filter_relative = false;
+ else
+ return -1;
+
+ return 0;
+}
+
+int perf_hist_config(const char *var, const char *value)
+{
+ if (!strcmp(var, "hist.percentage"))
+ return parse_filter_percentage(NULL, value, 0);
+
+ return 0;
+}
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 1f1f513dfe7f..742f49a85725 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -37,9 +37,11 @@ enum hist_filter {
*/
struct events_stats {
u64 total_period;
+ u64 total_non_filtered_period;
u64 total_lost;
u64 total_invalid_chains;
u32 nr_events[PERF_RECORD_HEADER_MAX];
+ u32 nr_non_filtered_samples;
u32 nr_lost_warned;
u32 nr_unknown_events;
u32 nr_invalid_chains;
@@ -70,6 +72,7 @@ enum hist_column {
HISTC_MEM_TLB,
HISTC_MEM_LVL,
HISTC_MEM_SNOOP,
+ HISTC_MEM_DCACHELINE,
HISTC_TRANSACTION,
HISTC_NR_COLS, /* Last entry */
};
@@ -83,6 +86,7 @@ struct hists {
struct rb_root entries;
struct rb_root entries_collapsed;
u64 nr_entries;
+ u64 nr_non_filtered_entries;
const struct thread *thread_filter;
const struct dso *dso_filter;
const char *uid_filter_str;
@@ -93,12 +97,50 @@ struct hists {
u16 col_len[HISTC_NR_COLS];
};
+struct hist_entry_iter;
+
+struct hist_iter_ops {
+ int (*prepare_entry)(struct hist_entry_iter *, struct addr_location *);
+ int (*add_single_entry)(struct hist_entry_iter *, struct addr_location *);
+ int (*next_entry)(struct hist_entry_iter *, struct addr_location *);
+ int (*add_next_entry)(struct hist_entry_iter *, struct addr_location *);
+ int (*finish_entry)(struct hist_entry_iter *, struct addr_location *);
+};
+
+struct hist_entry_iter {
+ int total;
+ int curr;
+
+ bool hide_unresolved;
+
+ struct perf_evsel *evsel;
+ struct perf_sample *sample;
+ struct hist_entry *he;
+ struct symbol *parent;
+ void *priv;
+
+ const struct hist_iter_ops *ops;
+ /* user-defined callback function (optional) */
+ int (*add_entry_cb)(struct hist_entry_iter *iter,
+ struct addr_location *al, bool single, void *arg);
+};
+
+extern const struct hist_iter_ops hist_iter_normal;
+extern const struct hist_iter_ops hist_iter_branch;
+extern const struct hist_iter_ops hist_iter_mem;
+extern const struct hist_iter_ops hist_iter_cumulative;
+
struct hist_entry *__hists__add_entry(struct hists *hists,
struct addr_location *al,
struct symbol *parent,
struct branch_info *bi,
struct mem_info *mi, u64 period,
- u64 weight, u64 transaction);
+ u64 weight, u64 transaction,
+ bool sample_self);
+int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
+ struct perf_evsel *evsel, struct perf_sample *sample,
+ int max_stack_depth, void *arg);
+
int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right);
int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right);
int hist_entry__transaction_len(void);
@@ -112,8 +154,11 @@ void hists__collapse_resort(struct hists *hists, struct ui_progress *prog);
void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel);
void hists__output_recalc_col_len(struct hists *hists, int max_rows);
-void hists__inc_nr_entries(struct hists *hists, struct hist_entry *h);
+u64 hists__total_period(struct hists *hists);
+void hists__reset_stats(struct hists *hists);
+void hists__inc_stats(struct hists *hists, struct hist_entry *h);
void hists__inc_nr_events(struct hists *hists, u32 type);
+void hists__inc_nr_samples(struct hists *hists, bool filtered);
void events_stats__inc(struct events_stats *stats, u32 type);
size_t events_stats__fprintf(struct events_stats *stats, FILE *fp);
@@ -124,6 +169,12 @@ void hists__filter_by_dso(struct hists *hists);
void hists__filter_by_thread(struct hists *hists);
void hists__filter_by_symbol(struct hists *hists);
+static inline bool hists__has_filter(struct hists *hists)
+{
+ return hists->thread_filter || hists->dso_filter ||
+ hists->symbol_filter_str;
+}
+
u16 hists__col_len(struct hists *hists, enum hist_column col);
void hists__set_col_len(struct hists *hists, enum hist_column col, u16 len);
bool hists__new_col_len(struct hists *hists, enum hist_column col, u16 len);
@@ -149,15 +200,30 @@ struct perf_hpp_fmt {
struct hist_entry *he);
int (*entry)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
struct hist_entry *he);
+ int64_t (*cmp)(struct hist_entry *a, struct hist_entry *b);
+ int64_t (*collapse)(struct hist_entry *a, struct hist_entry *b);
+ int64_t (*sort)(struct hist_entry *a, struct hist_entry *b);
struct list_head list;
+ struct list_head sort_list;
+ bool elide;
};
extern struct list_head perf_hpp__list;
+extern struct list_head perf_hpp__sort_list;
#define perf_hpp__for_each_format(format) \
list_for_each_entry(format, &perf_hpp__list, list)
+#define perf_hpp__for_each_format_safe(format, tmp) \
+ list_for_each_entry_safe(format, tmp, &perf_hpp__list, list)
+
+#define perf_hpp__for_each_sort_list(format) \
+ list_for_each_entry(format, &perf_hpp__sort_list, sort_list)
+
+#define perf_hpp__for_each_sort_list_safe(format, tmp) \
+ list_for_each_entry_safe(format, tmp, &perf_hpp__sort_list, sort_list)
+
extern struct perf_hpp_fmt perf_hpp__format[];
enum {
@@ -167,6 +233,7 @@ enum {
PERF_HPP__OVERHEAD_US,
PERF_HPP__OVERHEAD_GUEST_SYS,
PERF_HPP__OVERHEAD_GUEST_US,
+ PERF_HPP__OVERHEAD_ACC,
PERF_HPP__SAMPLES,
PERF_HPP__PERIOD,
@@ -175,15 +242,36 @@ enum {
void perf_hpp__init(void);
void perf_hpp__column_register(struct perf_hpp_fmt *format);
+void perf_hpp__column_unregister(struct perf_hpp_fmt *format);
void perf_hpp__column_enable(unsigned col);
+void perf_hpp__column_disable(unsigned col);
+void perf_hpp__cancel_cumulate(void);
+
+void perf_hpp__register_sort_field(struct perf_hpp_fmt *format);
+void perf_hpp__setup_output_field(void);
+void perf_hpp__reset_output_field(void);
+void perf_hpp__append_sort_keys(void);
+
+bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format);
+bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b);
+
+static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format)
+{
+ return format->elide;
+}
+
+void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists);
typedef u64 (*hpp_field_fn)(struct hist_entry *he);
typedef int (*hpp_callback_fn)(struct perf_hpp *hpp, bool front);
typedef int (*hpp_snprint_fn)(struct perf_hpp *hpp, const char *fmt, ...);
int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
- hpp_field_fn get_field, hpp_callback_fn callback,
- const char *fmt, hpp_snprint_fn print_fn, bool fmt_percent);
+ hpp_field_fn get_field, const char *fmt,
+ hpp_snprint_fn print_fn, bool fmt_percent);
+int __hpp__fmt_acc(struct perf_hpp *hpp, struct hist_entry *he,
+ hpp_field_fn get_field, const char *fmt,
+ hpp_snprint_fn print_fn, bool fmt_percent);
static inline void advance_hpp(struct perf_hpp *hpp, int inc)
{
@@ -250,4 +338,10 @@ static inline int script_browse(const char *script_opt __maybe_unused)
#endif
unsigned int hists__sort_list_width(struct hists *hists);
+
+struct option;
+int parse_filter_percentage(const struct option *opt __maybe_unused,
+ const char *arg, int unset __maybe_unused);
+int perf_hist_config(const char *var, const char *value);
+
#endif /* __PERF_HIST_H */
diff --git a/tools/perf/util/include/linux/bitmap.h b/tools/perf/util/include/linux/bitmap.h
index bb162e40c76c..01ffd12dc791 100644
--- a/tools/perf/util/include/linux/bitmap.h
+++ b/tools/perf/util/include/linux/bitmap.h
@@ -4,6 +4,9 @@
#include <string.h>
#include <linux/bitops.h>
+#define DECLARE_BITMAP(name,bits) \
+ unsigned long name[BITS_TO_LONGS(bits)]
+
int __bitmap_weight(const unsigned long *bitmap, int bits);
void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
const unsigned long *bitmap2, int bits);
diff --git a/tools/perf/util/include/linux/export.h b/tools/perf/util/include/linux/export.h
deleted file mode 100644
index b43e2dc21e04..000000000000
--- a/tools/perf/util/include/linux/export.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef PERF_LINUX_MODULE_H
-#define PERF_LINUX_MODULE_H
-
-#define EXPORT_SYMBOL(name)
-
-#endif
diff --git a/tools/perf/util/include/linux/list.h b/tools/perf/util/include/linux/list.h
index bfe0a2afd0d2..76ddbc726343 100644
--- a/tools/perf/util/include/linux/list.h
+++ b/tools/perf/util/include/linux/list.h
@@ -1,4 +1,5 @@
#include <linux/kernel.h>
+#include <linux/types.h>
#include "../../../../include/linux/list.h"
diff --git a/tools/perf/util/include/linux/types.h b/tools/perf/util/include/linux/types.h
deleted file mode 100644
index eb464786c084..000000000000
--- a/tools/perf/util/include/linux/types.h
+++ /dev/null
@@ -1,29 +0,0 @@
-#ifndef _PERF_LINUX_TYPES_H_
-#define _PERF_LINUX_TYPES_H_
-
-#include <asm/types.h>
-
-#ifndef __bitwise
-#define __bitwise
-#endif
-
-#ifndef __le32
-typedef __u32 __bitwise __le32;
-#endif
-
-#define DECLARE_BITMAP(name,bits) \
- unsigned long name[BITS_TO_LONGS(bits)]
-
-struct list_head {
- struct list_head *next, *prev;
-};
-
-struct hlist_head {
- struct hlist_node *first;
-};
-
-struct hlist_node {
- struct hlist_node *next, **pprev;
-};
-
-#endif
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 27c2a5efe450..c73e1fc12e53 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -316,6 +316,17 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
rb_link_node(&th->rb_node, parent, p);
rb_insert_color(&th->rb_node, &machine->threads);
machine->last_match = th;
+
+ /*
+ * We have to initialize map_groups separately
+ * after rb tree is updated.
+ *
+ * The reason is that we call machine__findnew_thread
+ * within thread__init_map_groups to find the thread
+ * leader and that would screwed the rb tree.
+ */
+ if (thread__init_map_groups(th, machine))
+ return NULL;
}
return th;
@@ -485,18 +496,6 @@ struct process_args {
u64 start;
};
-static int symbol__in_kernel(void *arg, const char *name,
- char type __maybe_unused, u64 start)
-{
- struct process_args *args = arg;
-
- if (strchr(name, '['))
- return 0;
-
- args->start = start;
- return 1;
-}
-
static void machine__get_kallsyms_filename(struct machine *machine, char *buf,
size_t bufsz)
{
@@ -506,27 +505,41 @@ static void machine__get_kallsyms_filename(struct machine *machine, char *buf,
scnprintf(buf, bufsz, "%s/proc/kallsyms", machine->root_dir);
}
-/* Figure out the start address of kernel map from /proc/kallsyms */
-static u64 machine__get_kernel_start_addr(struct machine *machine)
+const char *ref_reloc_sym_names[] = {"_text", "_stext", NULL};
+
+/* Figure out the start address of kernel map from /proc/kallsyms.
+ * Returns the name of the start symbol in *symbol_name. Pass in NULL as
+ * symbol_name if it's not that important.
+ */
+static u64 machine__get_kernel_start_addr(struct machine *machine,
+ const char **symbol_name)
{
char filename[PATH_MAX];
- struct process_args args;
+ int i;
+ const char *name;
+ u64 addr = 0;
machine__get_kallsyms_filename(machine, filename, PATH_MAX);
if (symbol__restricted_filename(filename, "/proc/kallsyms"))
return 0;
- if (kallsyms__parse(filename, &args, symbol__in_kernel) <= 0)
- return 0;
+ for (i = 0; (name = ref_reloc_sym_names[i]) != NULL; i++) {
+ addr = kallsyms__get_function_start(filename, name);
+ if (addr)
+ break;
+ }
- return args.start;
+ if (symbol_name)
+ *symbol_name = name;
+
+ return addr;
}
int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
{
enum map_type type;
- u64 start = machine__get_kernel_start_addr(machine);
+ u64 start = machine__get_kernel_start_addr(machine, NULL);
for (type = 0; type < MAP__NR_TYPES; ++type) {
struct kmap *kmap;
@@ -841,23 +854,11 @@ static int machine__create_modules(struct machine *machine)
return 0;
}
-const char *ref_reloc_sym_names[] = {"_text", "_stext", NULL};
-
int machine__create_kernel_maps(struct machine *machine)
{
struct dso *kernel = machine__get_kernel(machine);
- char filename[PATH_MAX];
const char *name;
- u64 addr = 0;
- int i;
-
- machine__get_kallsyms_filename(machine, filename, PATH_MAX);
-
- for (i = 0; (name = ref_reloc_sym_names[i]) != NULL; i++) {
- addr = kallsyms__get_function_start(filename, name);
- if (addr)
- break;
- }
+ u64 addr = machine__get_kernel_start_addr(machine, &name);
if (!addr)
return -1;
@@ -1049,6 +1050,8 @@ int machine__process_mmap2_event(struct machine *machine,
event->mmap2.pid, event->mmap2.maj,
event->mmap2.min, event->mmap2.ino,
event->mmap2.ino_generation,
+ event->mmap2.prot,
+ event->mmap2.flags,
event->mmap2.filename, type);
if (map == NULL)
@@ -1094,7 +1097,7 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
map = map__new(&machine->user_dsos, event->mmap.start,
event->mmap.len, event->mmap.pgoff,
- event->mmap.pid, 0, 0, 0, 0,
+ event->mmap.pid, 0, 0, 0, 0, 0, 0,
event->mmap.filename,
type);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 39cd2d0faff6..25c571f4cba6 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -32,6 +32,93 @@ static inline int is_no_dso_memory(const char *filename)
!strcmp(filename, "[heap]");
}
+static inline int is_android_lib(const char *filename)
+{
+ return !strncmp(filename, "/data/app-lib", 13) ||
+ !strncmp(filename, "/system/lib", 11);
+}
+
+static inline bool replace_android_lib(const char *filename, char *newfilename)
+{
+ const char *libname;
+ char *app_abi;
+ size_t app_abi_length, new_length;
+ size_t lib_length = 0;
+
+ libname = strrchr(filename, '/');
+ if (libname)
+ lib_length = strlen(libname);
+
+ app_abi = getenv("APP_ABI");
+ if (!app_abi)
+ return false;
+
+ app_abi_length = strlen(app_abi);
+
+ if (!strncmp(filename, "/data/app-lib", 13)) {
+ char *apk_path;
+
+ if (!app_abi_length)
+ return false;
+
+ new_length = 7 + app_abi_length + lib_length;
+
+ apk_path = getenv("APK_PATH");
+ if (apk_path) {
+ new_length += strlen(apk_path) + 1;
+ if (new_length > PATH_MAX)
+ return false;
+ snprintf(newfilename, new_length,
+ "%s/libs/%s/%s", apk_path, app_abi, libname);
+ } else {
+ if (new_length > PATH_MAX)
+ return false;
+ snprintf(newfilename, new_length,
+ "libs/%s/%s", app_abi, libname);
+ }
+ return true;
+ }
+
+ if (!strncmp(filename, "/system/lib/", 11)) {
+ char *ndk, *app;
+ const char *arch;
+ size_t ndk_length;
+ size_t app_length;
+
+ ndk = getenv("NDK_ROOT");
+ app = getenv("APP_PLATFORM");
+
+ if (!(ndk && app))
+ return false;
+
+ ndk_length = strlen(ndk);
+ app_length = strlen(app);
+
+ if (!(ndk_length && app_length && app_abi_length))
+ return false;
+
+ arch = !strncmp(app_abi, "arm", 3) ? "arm" :
+ !strncmp(app_abi, "mips", 4) ? "mips" :
+ !strncmp(app_abi, "x86", 3) ? "x86" : NULL;
+
+ if (!arch)
+ return false;
+
+ new_length = 27 + ndk_length +
+ app_length + lib_length
+ + strlen(arch);
+
+ if (new_length > PATH_MAX)
+ return false;
+ snprintf(newfilename, new_length,
+ "%s/platforms/%s/arch-%s/usr/lib/%s",
+ ndk, app, arch, libname);
+
+ return true;
+ }
+ return false;
+}
+
void map__init(struct map *map, enum map_type type,
u64 start, u64 end, u64 pgoff, struct dso *dso)
{
@@ -51,7 +138,7 @@ void map__init(struct map *map, enum map_type type,
struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino,
- u64 ino_gen, char *filename,
+ u64 ino_gen, u32 prot, u32 flags, char *filename,
enum map_type type)
{
struct map *map = malloc(sizeof(*map));
@@ -59,8 +146,9 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
if (map != NULL) {
char newfilename[PATH_MAX];
struct dso *dso;
- int anon, no_dso, vdso;
+ int anon, no_dso, vdso, android;
+ android = is_android_lib(filename);
anon = is_anon_memory(filename);
vdso = is_vdso_map(filename);
no_dso = is_no_dso_memory(filename);
@@ -69,12 +157,19 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
map->min = d_min;
map->ino = ino;
map->ino_generation = ino_gen;
+ map->prot = prot;
+ map->flags = flags;
if ((anon || no_dso) && type == MAP__FUNCTION) {
snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", pid);
filename = newfilename;
}
+ if (android) {
+ if (replace_android_lib(filename, newfilename))
+ filename = newfilename;
+ }
+
if (vdso) {
pgoff = 0;
dso = vdso__dso_findnew(dsos__list);
@@ -323,6 +418,7 @@ void map_groups__init(struct map_groups *mg)
INIT_LIST_HEAD(&mg->removed_maps[i]);
}
mg->machine = NULL;
+ mg->refcnt = 1;
}
static void maps__delete(struct rb_root *maps)
@@ -358,6 +454,28 @@ void map_groups__exit(struct map_groups *mg)
}
}
+struct map_groups *map_groups__new(void)
+{
+ struct map_groups *mg = malloc(sizeof(*mg));
+
+ if (mg != NULL)
+ map_groups__init(mg);
+
+ return mg;
+}
+
+void map_groups__delete(struct map_groups *mg)
+{
+ map_groups__exit(mg);
+ free(mg);
+}
+
+void map_groups__put(struct map_groups *mg)
+{
+ if (--mg->refcnt == 0)
+ map_groups__delete(mg);
+}
+
void map_groups__flush(struct map_groups *mg)
{
int type;
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index f00f058afb3b..7758c72522ef 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -6,7 +6,7 @@
#include <linux/rbtree.h>
#include <stdio.h>
#include <stdbool.h>
-#include "types.h"
+#include <linux/types.h>
enum map_type {
MAP__FUNCTION = 0,
@@ -35,6 +35,8 @@ struct map {
bool referenced;
bool erange_warned;
u32 priv;
+ u32 prot;
+ u32 flags;
u64 pgoff;
u64 reloc;
u32 maj, min; /* only valid for MMAP2 record */
@@ -59,8 +61,20 @@ struct map_groups {
struct rb_root maps[MAP__NR_TYPES];
struct list_head removed_maps[MAP__NR_TYPES];
struct machine *machine;
+ int refcnt;
};
+struct map_groups *map_groups__new(void);
+void map_groups__delete(struct map_groups *mg);
+
+static inline struct map_groups *map_groups__get(struct map_groups *mg)
+{
+ ++mg->refcnt;
+ return mg;
+}
+
+void map_groups__put(struct map_groups *mg);
+
static inline struct kmap *map__kmap(struct map *map)
{
return (struct kmap *)(map + 1);
@@ -106,7 +120,7 @@ void map__init(struct map *map, enum map_type type,
u64 start, u64 end, u64 pgoff, struct dso *dso);
struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino,
- u64 ino_gen,
+ u64 ino_gen, u32 prot, u32 flags,
char *filename, enum map_type type);
struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
void map__delete(struct map *map);
diff --git a/tools/perf/util/pager.c b/tools/perf/util/pager.c
index 3322b8446e89..31ee02d4e988 100644
--- a/tools/perf/util/pager.c
+++ b/tools/perf/util/pager.c
@@ -57,13 +57,13 @@ void setup_pager(void)
}
if (!pager)
pager = getenv("PAGER");
- if (!pager) {
- if (!access("/usr/bin/pager", X_OK))
- pager = "/usr/bin/pager";
- }
+ if (!(pager || access("/usr/bin/pager", X_OK)))
+ pager = "/usr/bin/pager";
+ if (!(pager || access("/usr/bin/less", X_OK)))
+ pager = "/usr/bin/less";
if (!pager)
- pager = "less";
- else if (!*pager || !strcmp(pager, "cat"))
+ pager = "cat";
+ if (!*pager || !strcmp(pager, "cat"))
return;
spawned_pager = 1; /* means we are emitting to terminal */
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index f1cb4c4b3c70..df094b4ed5ed 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -6,9 +6,8 @@
#include <linux/list.h>
#include <stdbool.h>
-#include "types.h"
+#include <linux/types.h>
#include <linux/perf_event.h>
-#include "types.h"
struct list_head;
struct perf_evsel;
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 4eb67ec333f1..0bc87ba46bf3 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -9,7 +9,7 @@
#include <linux/compiler.h>
#include <linux/list.h>
-#include "types.h"
+#include <linux/types.h>
#include "util.h"
#include "parse-events.h"
#include "parse-events-bison.h"
@@ -299,6 +299,18 @@ PE_PREFIX_MEM PE_VALUE sep_dc
}
event_legacy_tracepoint:
+PE_NAME '-' PE_NAME ':' PE_NAME
+{
+ struct parse_events_evlist *data = _data;
+ struct list_head *list;
+ char sys_name[128];
+ snprintf(&sys_name, 128, "%s-%s", $1, $3);
+
+ ALLOC_LIST(list);
+ ABORT_ON(parse_events_add_tracepoint(list, &data->idx, &sys_name, $5));
+ $$ = list;
+}
+|
PE_NAME ':' PE_NAME
{
struct parse_events_evlist *data = _data;
diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c
index a3539ef30b15..43168fb0d9a2 100644
--- a/tools/perf/util/perf_regs.c
+++ b/tools/perf/util/perf_regs.c
@@ -1,11 +1,15 @@
#include <errno.h>
#include "perf_regs.h"
+#include "event.h"
int perf_reg_value(u64 *valp, struct regs_dump *regs, int id)
{
int i, idx = 0;
u64 mask = regs->mask;
+ if (regs->cache_mask & (1 << id))
+ goto out;
+
if (!(mask & (1 << id)))
return -EINVAL;
@@ -14,6 +18,10 @@ int perf_reg_value(u64 *valp, struct regs_dump *regs, int id)
idx++;
}
- *valp = regs->regs[idx];
+ regs->cache_mask |= (1 << id);
+ regs->cache_regs[id] = regs->regs[idx];
+
+out:
+ *valp = regs->cache_regs[id];
return 0;
}
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
index d6e8b6a8d7f3..980dbf76bc98 100644
--- a/tools/perf/util/perf_regs.h
+++ b/tools/perf/util/perf_regs.h
@@ -1,8 +1,9 @@
#ifndef __PERF_REGS_H
#define __PERF_REGS_H
-#include "types.h"
-#include "event.h"
+#include <linux/types.h>
+
+struct regs_dump;
#ifdef HAVE_PERF_REGS_SUPPORT
#include <perf_regs.h>
@@ -11,6 +12,7 @@ int perf_reg_value(u64 *valp, struct regs_dump *regs, int id);
#else
#define PERF_REGS_MASK 0
+#define PERF_REGS_MAX 0
static inline const char *perf_reg_name(int id __maybe_unused)
{
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 00a7dcb2f55c..7a811eb61f75 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -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,
struct list_head *terms)
{
- struct parse_events_term *term, *clone;
+ struct parse_events_term *term, *cloned;
LIST_HEAD(list);
int ret;
list_for_each_entry(term, &alias->terms, list) {
- ret = parse_events_term__clone(&clone, term);
+ ret = parse_events_term__clone(&cloned, term);
if (ret) {
parse_events__free_terms(&list);
return ret;
}
- list_add_tail(&clone->list, &list);
+ list_add_tail(&cloned->list, &list);
}
list_splice(&list, terms);
return 0;
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 8b64125a9281..c14a543ce1f3 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -1,7 +1,7 @@
#ifndef __PMU_H
#define __PMU_H
-#include <linux/bitops.h>
+#include <linux/bitmap.h>
#include <linux/perf_event.h>
#include <stdbool.h>
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 0d1542f33d87..9a0a1839a377 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -628,11 +628,11 @@ static int __show_line_range(struct line_range *lr, const char *module)
ret = debuginfo__find_line_range(dinfo, lr);
debuginfo__delete(dinfo);
- if (ret == 0) {
+ if (ret == 0 || ret == -ENOENT) {
pr_warning("Specified source line is not found.\n");
return -ENOENT;
} else if (ret < 0) {
- pr_warning("Debuginfo analysis failed. (%d)\n", ret);
+ pr_warning("Debuginfo analysis failed.\n");
return ret;
}
@@ -641,7 +641,7 @@ static int __show_line_range(struct line_range *lr, const char *module)
ret = get_real_path(tmp, lr->comp_dir, &lr->path);
free(tmp); /* Free old path */
if (ret < 0) {
- pr_warning("Failed to find source file. (%d)\n", ret);
+ pr_warning("Failed to find source file path.\n");
return ret;
}
@@ -721,9 +721,14 @@ static int show_available_vars_at(struct debuginfo *dinfo,
ret = debuginfo__find_available_vars_at(dinfo, pev, &vls,
max_vls, externs);
if (ret <= 0) {
- pr_err("Failed to find variables at %s (%d)\n", buf, ret);
+ if (ret == 0 || ret == -ENOENT) {
+ pr_err("Failed to find the address of %s\n", buf);
+ ret = -ENOENT;
+ } else
+ pr_warning("Debuginfo analysis failed.\n");
goto end;
}
+
/* Some variables are found */
fprintf(stdout, "Available variables at %s\n", buf);
for (i = 0; i < ret; i++) {
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 562762117639..98e304766416 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -511,12 +511,12 @@ static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf)
ret = convert_variable_location(vr_die, pf->addr, pf->fb_ops,
&pf->sp_die, pf->tvar);
- if (ret == -ENOENT)
+ if (ret == -ENOENT || ret == -EINVAL)
pr_err("Failed to find the location of %s at this address.\n"
" Perhaps, it has been optimized out.\n", pf->pvar->var);
else if (ret == -ENOTSUP)
pr_err("Sorry, we don't support this variable location yet.\n");
- else if (pf->pvar->field) {
+ else if (ret == 0 && pf->pvar->field) {
ret = convert_variable_fields(vr_die, pf->pvar->var,
pf->pvar->field, &pf->tvar->ref,
&die_mem);
@@ -573,14 +573,13 @@ static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf)
if (!die_find_variable_at(sc_die, pf->pvar->var, pf->addr, &vr_die)) {
/* Search again in global variables */
if (!die_find_variable_at(&pf->cu_die, pf->pvar->var, 0, &vr_die))
+ pr_warning("Failed to find '%s' in this function.\n",
+ pf->pvar->var);
ret = -ENOENT;
}
if (ret >= 0)
ret = convert_variable(&vr_die, pf);
- if (ret < 0)
- pr_warning("Failed to find '%s' in this function.\n",
- pf->pvar->var);
return ret;
}
@@ -1281,7 +1280,11 @@ out:
return ret;
}
-/* Find available variables at given probe point */
+/*
+ * Find available variables at given probe point
+ * Return the number of found probe points. Return 0 if there is no
+ * matched probe point. Return <0 if an error occurs.
+ */
int debuginfo__find_available_vars_at(struct debuginfo *dbg,
struct perf_probe_event *pev,
struct variable_list **vls,
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index e108207c5de0..af7da565a750 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -215,6 +215,7 @@ static void define_event_symbols(struct event_format *event,
case PRINT_BSTRING:
case PRINT_DYNAMIC_ARRAY:
case PRINT_STRING:
+ case PRINT_BITMASK:
break;
case PRINT_TYPE:
define_event_symbols(event, ev_name, args->typecast.item);
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index cd9774df3750..1c419321f707 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -197,6 +197,7 @@ static void define_event_symbols(struct event_format *event,
case PRINT_BSTRING:
case PRINT_DYNAMIC_ARRAY:
case PRINT_FUNC:
+ case PRINT_BITMASK:
/* we should warn... */
return;
}
@@ -622,6 +623,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
fprintf(ofp, "%s=", f->name);
if (f->flags & FIELD_IS_STRING ||
f->flags & FIELD_IS_FLAG ||
+ f->flags & FIELD_IS_ARRAY ||
f->flags & FIELD_IS_SYMBOLIC)
fprintf(ofp, "%%s");
else if (f->flags & FIELD_IS_SIGNED)
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 55960f22233c..64a186edc7be 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1625,13 +1625,14 @@ out_delete_map:
void perf_session__fprintf_info(struct perf_session *session, FILE *fp,
bool full)
{
- int fd = perf_data_file__fd(session->file);
struct stat st;
- int ret;
+ int fd, ret;
if (session == NULL || fp == NULL)
return;
+ fd = perf_data_file__fd(session->file);
+
ret = fstat(fd, &st);
if (ret == -1)
return;
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 635cd8f8b22e..1ec57dd82284 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1,13 +1,20 @@
+#include <sys/mman.h>
#include "sort.h"
#include "hist.h"
#include "comm.h"
#include "symbol.h"
+#include "evsel.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;
+const char default_branch_sort_order[] = "comm,dso_from,symbol_from,dso_to,symbol_to";
+const char default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked";
+const char default_top_sort_order[] = "dso,symbol";
+const char default_diff_sort_order[] = "dso,symbol";
+const char *sort_order;
+const char *field_order;
regex_t ignore_callees_regex;
int have_ignore_callees = 0;
int sort__need_collapse = 0;
@@ -16,9 +23,6 @@ int sort__has_sym = 0;
int sort__has_dso = 0;
enum sort_mode sort__mode = SORT_MODE__NORMAL;
-enum sort_type sort__first_dimension;
-
-LIST_HEAD(hist_entry__sort_list);
static int repsep_snprintf(char *bf, size_t size, const char *fmt, ...)
{
@@ -93,6 +97,12 @@ sort__comm_collapse(struct hist_entry *left, struct hist_entry *right)
return comm__str(right->comm) - comm__str(left->comm);
}
+static int64_t
+sort__comm_sort(struct hist_entry *left, struct hist_entry *right)
+{
+ return strcmp(comm__str(right->comm), comm__str(left->comm));
+}
+
static int hist_entry__comm_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
@@ -103,6 +113,7 @@ struct sort_entry sort_comm = {
.se_header = "Command",
.se_cmp = sort__comm_cmp,
.se_collapse = sort__comm_collapse,
+ .se_sort = sort__comm_sort,
.se_snprintf = hist_entry__comm_snprintf,
.se_width_idx = HISTC_COMM,
};
@@ -116,7 +127,7 @@ static int64_t _sort__dso_cmp(struct map *map_l, struct map *map_r)
const char *dso_name_l, *dso_name_r;
if (!dso_l || !dso_r)
- return cmp_null(dso_l, dso_r);
+ return cmp_null(dso_r, dso_l);
if (verbose) {
dso_name_l = dso_l->long_name;
@@ -132,7 +143,7 @@ static int64_t _sort__dso_cmp(struct map *map_l, struct map *map_r)
static int64_t
sort__dso_cmp(struct hist_entry *left, struct hist_entry *right)
{
- return _sort__dso_cmp(left->ms.map, right->ms.map);
+ return _sort__dso_cmp(right->ms.map, left->ms.map);
}
static int _hist_entry__dso_snprintf(struct map *map, char *bf,
@@ -204,6 +215,15 @@ sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
return _sort__sym_cmp(left->ms.sym, right->ms.sym);
}
+static int64_t
+sort__sym_sort(struct hist_entry *left, struct hist_entry *right)
+{
+ if (!left->ms.sym || !right->ms.sym)
+ return cmp_null(left->ms.sym, right->ms.sym);
+
+ return strcmp(right->ms.sym->name, left->ms.sym->name);
+}
+
static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
u64 ip, char level, char *bf, size_t size,
unsigned int width)
@@ -250,6 +270,7 @@ static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf,
struct sort_entry sort_sym = {
.se_header = "Symbol",
.se_cmp = sort__sym_cmp,
+ .se_sort = sort__sym_sort,
.se_snprintf = hist_entry__sym_snprintf,
.se_width_idx = HISTC_SYMBOL,
};
@@ -277,7 +298,7 @@ sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right)
map__rip_2objdump(map, right->ip));
}
}
- return strcmp(left->srcline, right->srcline);
+ return strcmp(right->srcline, left->srcline);
}
static int hist_entry__srcline_snprintf(struct hist_entry *he, char *bf,
@@ -305,7 +326,7 @@ sort__parent_cmp(struct hist_entry *left, struct hist_entry *right)
if (!sym_l || !sym_r)
return cmp_null(sym_l, sym_r);
- return strcmp(sym_l->name, sym_r->name);
+ return strcmp(sym_r->name, sym_l->name);
}
static int hist_entry__parent_snprintf(struct hist_entry *he, char *bf,
@@ -764,6 +785,104 @@ static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf,
return repsep_snprintf(bf, size, "%-*s", width, out);
}
+static inline u64 cl_address(u64 address)
+{
+ /* return the cacheline of the address */
+ return (address & ~(cacheline_size - 1));
+}
+
+static int64_t
+sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+ u64 l, r;
+ struct map *l_map, *r_map;
+
+ if (!left->mem_info) return -1;
+ if (!right->mem_info) return 1;
+
+ /* group event types together */
+ if (left->cpumode > right->cpumode) return -1;
+ if (left->cpumode < right->cpumode) return 1;
+
+ l_map = left->mem_info->daddr.map;
+ r_map = right->mem_info->daddr.map;
+
+ /* if both are NULL, jump to sort on al_addr instead */
+ if (!l_map && !r_map)
+ goto addr;
+
+ if (!l_map) return -1;
+ if (!r_map) return 1;
+
+ if (l_map->maj > r_map->maj) return -1;
+ if (l_map->maj < r_map->maj) return 1;
+
+ if (l_map->min > r_map->min) return -1;
+ if (l_map->min < r_map->min) return 1;
+
+ if (l_map->ino > r_map->ino) return -1;
+ if (l_map->ino < r_map->ino) return 1;
+
+ if (l_map->ino_generation > r_map->ino_generation) return -1;
+ if (l_map->ino_generation < r_map->ino_generation) return 1;
+
+ /*
+ * Addresses with no major/minor numbers 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) &&
+ (!(l_map->flags & MAP_SHARED)) &&
+ !l_map->maj && !l_map->min && !l_map->ino &&
+ !l_map->ino_generation) {
+ /* userspace anonymous */
+
+ if (left->thread->pid_ > right->thread->pid_) return -1;
+ if (left->thread->pid_ < right->thread->pid_) return 1;
+ }
+
+addr:
+ /* al_addr does all the right addr - start + offset calculations */
+ l = cl_address(left->mem_info->daddr.al_addr);
+ r = cl_address(right->mem_info->daddr.al_addr);
+
+ if (l > r) return -1;
+ if (l < r) return 1;
+
+ return 0;
+}
+
+static int hist_entry__dcacheline_snprintf(struct hist_entry *he, char *bf,
+ size_t size, unsigned int width)
+{
+
+ uint64_t addr = 0;
+ struct map *map = NULL;
+ struct symbol *sym = NULL;
+ char level = he->level;
+
+ if (he->mem_info) {
+ addr = cl_address(he->mem_info->daddr.al_addr);
+ map = he->mem_info->daddr.map;
+ sym = he->mem_info->daddr.sym;
+
+ /* print [s] for shared data mmaps */
+ if ((he->cpumode != PERF_RECORD_MISC_KERNEL) &&
+ map && (map->type == MAP__VARIABLE) &&
+ (map->flags & MAP_SHARED) &&
+ (map->maj || map->min || map->ino ||
+ map->ino_generation))
+ level = 's';
+ else if (!map)
+ level = 'X';
+ }
+ return _hist_entry__sym_snprintf(map, sym, addr, level, bf, size,
+ width);
+}
+
struct sort_entry sort_mispredict = {
.se_header = "Branch Mispredicted",
.se_cmp = sort__mispredict_cmp,
@@ -856,6 +975,13 @@ struct sort_entry sort_mem_snoop = {
.se_width_idx = HISTC_MEM_SNOOP,
};
+struct sort_entry sort_mem_dcacheline = {
+ .se_header = "Data Cacheline",
+ .se_cmp = sort__dcacheline_cmp,
+ .se_snprintf = hist_entry__dcacheline_snprintf,
+ .se_width_idx = HISTC_MEM_DCACHELINE,
+};
+
static int64_t
sort__abort_cmp(struct hist_entry *left, struct hist_entry *right)
{
@@ -1023,23 +1149,199 @@ static struct sort_dimension memory_sort_dimensions[] = {
DIM(SORT_MEM_TLB, "tlb", sort_mem_tlb),
DIM(SORT_MEM_LVL, "mem", sort_mem_lvl),
DIM(SORT_MEM_SNOOP, "snoop", sort_mem_snoop),
+ DIM(SORT_MEM_DCACHELINE, "dcacheline", sort_mem_dcacheline),
+};
+
+#undef DIM
+
+struct hpp_dimension {
+ const char *name;
+ struct perf_hpp_fmt *fmt;
+ int taken;
+};
+
+#define DIM(d, n) { .name = n, .fmt = &perf_hpp__format[d], }
+
+static struct hpp_dimension hpp_sort_dimensions[] = {
+ DIM(PERF_HPP__OVERHEAD, "overhead"),
+ DIM(PERF_HPP__OVERHEAD_SYS, "overhead_sys"),
+ DIM(PERF_HPP__OVERHEAD_US, "overhead_us"),
+ DIM(PERF_HPP__OVERHEAD_GUEST_SYS, "overhead_guest_sys"),
+ DIM(PERF_HPP__OVERHEAD_GUEST_US, "overhead_guest_us"),
+ DIM(PERF_HPP__OVERHEAD_ACC, "overhead_children"),
+ DIM(PERF_HPP__SAMPLES, "sample"),
+ DIM(PERF_HPP__PERIOD, "period"),
};
#undef DIM
-static void __sort_dimension__add(struct sort_dimension *sd, enum sort_type idx)
+struct hpp_sort_entry {
+ struct perf_hpp_fmt hpp;
+ struct sort_entry *se;
+};
+
+bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
{
- if (sd->taken)
+ struct hpp_sort_entry *hse_a;
+ struct hpp_sort_entry *hse_b;
+
+ if (!perf_hpp__is_sort_entry(a) || !perf_hpp__is_sort_entry(b))
+ return false;
+
+ hse_a = container_of(a, struct hpp_sort_entry, hpp);
+ hse_b = container_of(b, struct hpp_sort_entry, hpp);
+
+ return hse_a->se == hse_b->se;
+}
+
+void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
+{
+ struct hpp_sort_entry *hse;
+
+ if (!perf_hpp__is_sort_entry(fmt))
return;
+ hse = container_of(fmt, struct hpp_sort_entry, hpp);
+ hists__new_col_len(hists, hse->se->se_width_idx,
+ strlen(hse->se->se_header));
+}
+
+static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct perf_evsel *evsel)
+{
+ struct hpp_sort_entry *hse;
+ size_t len;
+
+ hse = container_of(fmt, struct hpp_sort_entry, hpp);
+ len = hists__col_len(&evsel->hists, hse->se->se_width_idx);
+
+ return scnprintf(hpp->buf, hpp->size, "%*s", len, hse->se->se_header);
+}
+
+static int __sort__hpp_width(struct perf_hpp_fmt *fmt,
+ struct perf_hpp *hpp __maybe_unused,
+ struct perf_evsel *evsel)
+{
+ struct hpp_sort_entry *hse;
+
+ hse = container_of(fmt, struct hpp_sort_entry, hpp);
+
+ return hists__col_len(&evsel->hists, hse->se->se_width_idx);
+}
+
+static int __sort__hpp_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hist_entry *he)
+{
+ struct hpp_sort_entry *hse;
+ size_t len;
+
+ hse = container_of(fmt, struct hpp_sort_entry, hpp);
+ len = hists__col_len(he->hists, hse->se->se_width_idx);
+
+ return hse->se->se_snprintf(he, hpp->buf, hpp->size, len);
+}
+
+static struct hpp_sort_entry *
+__sort_dimension__alloc_hpp(struct sort_dimension *sd)
+{
+ struct hpp_sort_entry *hse;
+
+ hse = malloc(sizeof(*hse));
+ if (hse == NULL) {
+ pr_err("Memory allocation failed\n");
+ return NULL;
+ }
+
+ hse->se = sd->entry;
+ hse->hpp.header = __sort__hpp_header;
+ hse->hpp.width = __sort__hpp_width;
+ hse->hpp.entry = __sort__hpp_entry;
+ hse->hpp.color = NULL;
+
+ hse->hpp.cmp = sd->entry->se_cmp;
+ hse->hpp.collapse = sd->entry->se_collapse ? : sd->entry->se_cmp;
+ hse->hpp.sort = sd->entry->se_sort ? : hse->hpp.collapse;
+
+ INIT_LIST_HEAD(&hse->hpp.list);
+ INIT_LIST_HEAD(&hse->hpp.sort_list);
+ hse->hpp.elide = false;
+
+ return hse;
+}
+
+bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format)
+{
+ return format->header == __sort__hpp_header;
+}
+
+static int __sort_dimension__add_hpp_sort(struct sort_dimension *sd)
+{
+ struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd);
+
+ if (hse == NULL)
+ return -1;
+
+ perf_hpp__register_sort_field(&hse->hpp);
+ return 0;
+}
+
+static int __sort_dimension__add_hpp_output(struct sort_dimension *sd)
+{
+ struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd);
+
+ if (hse == NULL)
+ return -1;
+
+ perf_hpp__column_register(&hse->hpp);
+ return 0;
+}
+
+static int __sort_dimension__add(struct sort_dimension *sd)
+{
+ if (sd->taken)
+ return 0;
+
+ if (__sort_dimension__add_hpp_sort(sd) < 0)
+ return -1;
+
if (sd->entry->se_collapse)
sort__need_collapse = 1;
- if (list_empty(&hist_entry__sort_list))
- sort__first_dimension = idx;
+ sd->taken = 1;
+
+ return 0;
+}
+
+static int __hpp_dimension__add(struct hpp_dimension *hd)
+{
+ if (!hd->taken) {
+ hd->taken = 1;
+
+ perf_hpp__register_sort_field(hd->fmt);
+ }
+ return 0;
+}
+
+static int __sort_dimension__add_output(struct sort_dimension *sd)
+{
+ if (sd->taken)
+ return 0;
+
+ if (__sort_dimension__add_hpp_output(sd) < 0)
+ return -1;
- list_add_tail(&sd->entry->list, &hist_entry__sort_list);
sd->taken = 1;
+ return 0;
+}
+
+static int __hpp_dimension__add_output(struct hpp_dimension *hd)
+{
+ if (!hd->taken) {
+ hd->taken = 1;
+
+ perf_hpp__column_register(hd->fmt);
+ }
+ return 0;
}
int sort_dimension__add(const char *tok)
@@ -1068,8 +1370,16 @@ int sort_dimension__add(const char *tok)
sort__has_dso = 1;
}
- __sort_dimension__add(sd, i);
- return 0;
+ return __sort_dimension__add(sd);
+ }
+
+ 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);
}
for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) {
@@ -1084,7 +1394,7 @@ int sort_dimension__add(const char *tok)
if (sd->entry == &sort_sym_from || sd->entry == &sort_sym_to)
sort__has_sym = 1;
- __sort_dimension__add(sd, i + __SORT_BRANCH_STACK);
+ __sort_dimension__add(sd);
return 0;
}
@@ -1100,18 +1410,47 @@ int sort_dimension__add(const char *tok)
if (sd->entry == &sort_mem_daddr_sym)
sort__has_sym = 1;
- __sort_dimension__add(sd, i + __SORT_MEMORY_MODE);
+ __sort_dimension__add(sd);
return 0;
}
return -ESRCH;
}
-int setup_sorting(void)
+static const char *get_default_sort_order(void)
+{
+ const char *default_sort_orders[] = {
+ default_sort_order,
+ default_branch_sort_order,
+ default_mem_sort_order,
+ default_top_sort_order,
+ default_diff_sort_order,
+ };
+
+ BUG_ON(sort__mode >= ARRAY_SIZE(default_sort_orders));
+
+ return default_sort_orders[sort__mode];
+}
+
+static int __setup_sorting(void)
{
- char *tmp, *tok, *str = strdup(sort_order);
+ char *tmp, *tok, *str;
+ const char *sort_keys = sort_order;
int ret = 0;
+ if (sort_keys == NULL) {
+ if (field_order) {
+ /*
+ * If user specified field order but no sort order,
+ * we'll honor it and not add default sort orders.
+ */
+ return 0;
+ }
+
+ sort_keys = get_default_sort_order();
+ }
+
+ str = strdup(sort_keys);
if (str == NULL) {
error("Not enough memory to setup sort keys");
return -ENOMEM;
@@ -1133,66 +1472,235 @@ int setup_sorting(void)
return ret;
}
-static void sort_entry__setup_elide(struct sort_entry *se,
- struct strlist *list,
- const char *list_name, FILE *fp)
+void perf_hpp__set_elide(int idx, bool elide)
+{
+ struct perf_hpp_fmt *fmt;
+ struct hpp_sort_entry *hse;
+
+ perf_hpp__for_each_format(fmt) {
+ if (!perf_hpp__is_sort_entry(fmt))
+ continue;
+
+ hse = container_of(fmt, struct hpp_sort_entry, hpp);
+ if (hse->se->se_width_idx == idx) {
+ fmt->elide = elide;
+ break;
+ }
+ }
+}
+
+static bool __get_elide(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);
- se->elide = true;
+ return true;
}
+ return false;
+}
+
+static bool get_elide(int idx, FILE *output)
+{
+ switch (idx) {
+ case HISTC_SYMBOL:
+ return __get_elide(symbol_conf.sym_list, "symbol", output);
+ case HISTC_DSO:
+ return __get_elide(symbol_conf.dso_list, "dso", output);
+ case HISTC_COMM:
+ return __get_elide(symbol_conf.comm_list, "comm", output);
+ default:
+ break;
+ }
+
+ if (sort__mode != SORT_MODE__BRANCH)
+ return false;
+
+ switch (idx) {
+ case HISTC_SYMBOL_FROM:
+ return __get_elide(symbol_conf.sym_from_list, "sym_from", output);
+ case HISTC_SYMBOL_TO:
+ return __get_elide(symbol_conf.sym_to_list, "sym_to", output);
+ case HISTC_DSO_FROM:
+ return __get_elide(symbol_conf.dso_from_list, "dso_from", output);
+ case HISTC_DSO_TO:
+ return __get_elide(symbol_conf.dso_to_list, "dso_to", output);
+ default:
+ break;
+ }
+
+ return false;
}
void sort__setup_elide(FILE *output)
{
- struct sort_entry *se;
+ struct perf_hpp_fmt *fmt;
+ struct hpp_sort_entry *hse;
+
+ perf_hpp__for_each_format(fmt) {
+ if (!perf_hpp__is_sort_entry(fmt))
+ continue;
- sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
- "dso", output);
- sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list,
- "comm", output);
- sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list,
- "symbol", output);
-
- if (sort__mode == SORT_MODE__BRANCH) {
- sort_entry__setup_elide(&sort_dso_from,
- symbol_conf.dso_from_list,
- "dso_from", output);
- sort_entry__setup_elide(&sort_dso_to,
- symbol_conf.dso_to_list,
- "dso_to", output);
- sort_entry__setup_elide(&sort_sym_from,
- symbol_conf.sym_from_list,
- "sym_from", output);
- sort_entry__setup_elide(&sort_sym_to,
- symbol_conf.sym_to_list,
- "sym_to", output);
- } else if (sort__mode == SORT_MODE__MEMORY) {
- sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
- "symbol_daddr", output);
- sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
- "dso_daddr", output);
- sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
- "mem", output);
- sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
- "local_weight", output);
- sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
- "tlb", output);
- sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
- "snoop", output);
+ hse = container_of(fmt, struct hpp_sort_entry, hpp);
+ fmt->elide = get_elide(hse->se->se_width_idx, output);
}
/*
* It makes no sense to elide all of sort entries.
* Just revert them to show up again.
*/
- list_for_each_entry(se, &hist_entry__sort_list, list) {
- if (!se->elide)
+ perf_hpp__for_each_format(fmt) {
+ if (!perf_hpp__is_sort_entry(fmt))
+ continue;
+
+ if (!fmt->elide)
return;
}
- list_for_each_entry(se, &hist_entry__sort_list, list)
- se->elide = false;
+ perf_hpp__for_each_format(fmt) {
+ if (!perf_hpp__is_sort_entry(fmt))
+ continue;
+
+ fmt->elide = false;
+ }
+}
+
+static int output_field_add(char *tok)
+{
+ unsigned int i;
+
+ for (i = 0; i < ARRAY_SIZE(common_sort_dimensions); i++) {
+ struct sort_dimension *sd = &common_sort_dimensions[i];
+
+ if (strncasecmp(tok, sd->name, strlen(tok)))
+ continue;
+
+ return __sort_dimension__add_output(sd);
+ }
+
+ 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_output(hd);
+ }
+
+ for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) {
+ struct sort_dimension *sd = &bstack_sort_dimensions[i];
+
+ if (strncasecmp(tok, sd->name, strlen(tok)))
+ continue;
+
+ return __sort_dimension__add_output(sd);
+ }
+
+ for (i = 0; i < ARRAY_SIZE(memory_sort_dimensions); i++) {
+ struct sort_dimension *sd = &memory_sort_dimensions[i];
+
+ if (strncasecmp(tok, sd->name, strlen(tok)))
+ continue;
+
+ return __sort_dimension__add_output(sd);
+ }
+
+ return -ESRCH;
+}
+
+static void reset_dimensions(void)
+{
+ unsigned int i;
+
+ for (i = 0; i < ARRAY_SIZE(common_sort_dimensions); i++)
+ common_sort_dimensions[i].taken = 0;
+
+ for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++)
+ hpp_sort_dimensions[i].taken = 0;
+
+ for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++)
+ bstack_sort_dimensions[i].taken = 0;
+
+ for (i = 0; i < ARRAY_SIZE(memory_sort_dimensions); i++)
+ memory_sort_dimensions[i].taken = 0;
+}
+
+static int __setup_output_field(void)
+{
+ char *tmp, *tok, *str;
+ int ret = 0;
+
+ if (field_order == NULL)
+ return 0;
+
+ reset_dimensions();
+
+ str = strdup(field_order);
+ if (str == NULL) {
+ error("Not enough memory to setup output fields");
+ return -ENOMEM;
+ }
+
+ for (tok = strtok_r(str, ", ", &tmp);
+ tok; tok = strtok_r(NULL, ", ", &tmp)) {
+ ret = output_field_add(tok);
+ if (ret == -EINVAL) {
+ error("Invalid --fields key: `%s'", tok);
+ break;
+ } else if (ret == -ESRCH) {
+ error("Unknown --fields key: `%s'", tok);
+ break;
+ }
+ }
+
+ free(str);
+ return ret;
+}
+
+int setup_sorting(void)
+{
+ int err;
+
+ err = __setup_sorting();
+ if (err < 0)
+ return err;
+
+ if (parent_pattern != default_parent_pattern) {
+ err = sort_dimension__add("parent");
+ if (err < 0)
+ return err;
+ }
+
+ reset_dimensions();
+
+ /*
+ * perf diff doesn't use default hpp output fields.
+ */
+ if (sort__mode != SORT_MODE__DIFF)
+ perf_hpp__init();
+
+ err = __setup_output_field();
+ if (err < 0)
+ return err;
+
+ /* copy sort keys to output fields */
+ perf_hpp__setup_output_field();
+ /* and then copy output fields to sort keys */
+ perf_hpp__append_sort_keys();
+
+ return 0;
+}
+
+void reset_output_field(void)
+{
+ sort__need_collapse = 0;
+ sort__has_parent = 0;
+ sort__has_sym = 0;
+ sort__has_dso = 0;
+
+ field_order = NULL;
+ sort_order = NULL;
+
+ reset_dimensions();
+ perf_hpp__reset_output_field();
}
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 43e5ff42a609..041f0c9cea2b 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -20,11 +20,12 @@
#include "parse-options.h"
#include "parse-events.h"
-
+#include "hist.h"
#include "thread.h"
extern regex_t parent_regex;
extern const char *sort_order;
+extern const char *field_order;
extern const char default_parent_pattern[];
extern const char *parent_pattern;
extern const char default_sort_order[];
@@ -81,12 +82,14 @@ struct hist_entry {
struct list_head head;
} pairs;
struct he_stat stat;
+ struct he_stat *stat_acc;
struct map_symbol ms;
struct thread *thread;
struct comm *comm;
u64 ip;
u64 transaction;
s32 cpu;
+ u8 cpumode;
struct hist_entry_diff diff;
@@ -129,10 +132,27 @@ static inline void hist_entry__add_pair(struct hist_entry *pair,
list_add_tail(&pair->pairs.node, &he->pairs.head);
}
+static inline float hist_entry__get_percent_limit(struct hist_entry *he)
+{
+ u64 period = he->stat.period;
+ u64 total_period = hists__total_period(he->hists);
+
+ if (unlikely(total_period == 0))
+ return 0;
+
+ if (symbol_conf.cumulate_callchain)
+ period = he->stat_acc->period;
+
+ return period * 100.0 / total_period;
+}
+
+
enum sort_mode {
SORT_MODE__NORMAL,
SORT_MODE__BRANCH,
SORT_MODE__MEMORY,
+ SORT_MODE__TOP,
+ SORT_MODE__DIFF,
};
enum sort_type {
@@ -166,6 +186,7 @@ enum sort_type {
SORT_MEM_TLB,
SORT_MEM_LVL,
SORT_MEM_SNOOP,
+ SORT_MEM_DCACHELINE,
};
/*
@@ -179,18 +200,21 @@ struct sort_entry {
int64_t (*se_cmp)(struct hist_entry *, struct hist_entry *);
int64_t (*se_collapse)(struct hist_entry *, struct hist_entry *);
+ int64_t (*se_sort)(struct hist_entry *, struct hist_entry *);
int (*se_snprintf)(struct hist_entry *he, char *bf, size_t size,
unsigned int width);
u8 se_width_idx;
- bool elide;
};
extern struct sort_entry sort_thread;
extern struct list_head hist_entry__sort_list;
int setup_sorting(void);
+int setup_output_field(void);
+void reset_output_field(void);
extern int sort_dimension__add(const char *);
void sort__setup_elide(FILE *fp);
+void perf_hpp__set_elide(int idx, bool elide);
int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset);
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index ae8ccd7227cf..5667fc3e39cf 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -1,7 +1,7 @@
#ifndef __PERF_STATS_H
#define __PERF_STATS_H
-#include "types.h"
+#include <linux/types.h>
struct stats
{
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index 43262b83c541..6a0a13d07a28 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -17,7 +17,7 @@
#include <stdlib.h>
#include <unistd.h>
#include <string.h>
-#include <linux/bitops.h>
+#include <linux/bitmap.h>
#include "perf.h"
#include "svghelper.h"
diff --git a/tools/perf/util/svghelper.h b/tools/perf/util/svghelper.h
index f7b4d6e699ea..e3aff5332e30 100644
--- a/tools/perf/util/svghelper.h
+++ b/tools/perf/util/svghelper.h
@@ -1,7 +1,7 @@
#ifndef __PERF_SVGHELPER_H
#define __PERF_SVGHELPER_H
-#include "types.h"
+#include <linux/types.h>
extern void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end);
extern void svg_box(int Yslot, u64 start, u64 end, const char *type);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 95e249779931..7b9096f29cdb 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -29,11 +29,12 @@ int vmlinux_path__nr_entries;
char **vmlinux_path;
struct symbol_conf symbol_conf = {
- .use_modules = true,
- .try_vmlinux_path = true,
- .annotate_src = true,
- .demangle = true,
- .symfs = "",
+ .use_modules = true,
+ .try_vmlinux_path = true,
+ .annotate_src = true,
+ .demangle = true,
+ .cumulate_callchain = true,
+ .symfs = "",
};
static enum dso_binary_type binary_type_symtab[] = {
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 501e4e722e8e..615c752dd767 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -12,6 +12,7 @@
#include <byteswap.h>
#include <libgen.h>
#include "build-id.h"
+#include "event.h"
#ifdef HAVE_LIBELF_SUPPORT
#include <libelf.h>
@@ -108,6 +109,7 @@ struct symbol_conf {
show_nr_samples,
show_total_period,
use_callchain,
+ cumulate_callchain,
exclude_other,
show_cpu_utilization,
initialized,
@@ -115,7 +117,8 @@ struct symbol_conf {
annotate_asm_raw,
annotate_src,
event_group,
- demangle;
+ demangle,
+ filter_relative;
const char *vmlinux_name,
*kallsyms_name,
*source_prefix,
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 3ce0498bdae6..2fde0d5e40b5 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -8,6 +8,22 @@
#include "debug.h"
#include "comm.h"
+int thread__init_map_groups(struct thread *thread, struct machine *machine)
+{
+ struct thread *leader;
+ pid_t pid = thread->pid_;
+
+ if (pid == thread->tid) {
+ thread->mg = map_groups__new();
+ } else {
+ leader = machine__findnew_thread(machine, pid, pid);
+ if (leader)
+ thread->mg = map_groups__get(leader->mg);
+ }
+
+ return thread->mg ? 0 : -1;
+}
+
struct thread *thread__new(pid_t pid, pid_t tid)
{
char *comm_str;
@@ -15,7 +31,6 @@ struct thread *thread__new(pid_t pid, pid_t tid)
struct thread *thread = zalloc(sizeof(*thread));
if (thread != NULL) {
- map_groups__init(&thread->mg);
thread->pid_ = pid;
thread->tid = tid;
thread->ppid = -1;
@@ -45,7 +60,8 @@ void thread__delete(struct thread *thread)
{
struct comm *comm, *tmp;
- map_groups__exit(&thread->mg);
+ map_groups__put(thread->mg);
+ thread->mg = NULL;
list_for_each_entry_safe(comm, tmp, &thread->comm_list, list) {
list_del(&comm->list);
comm__free(comm);
@@ -111,18 +127,35 @@ int thread__comm_len(struct thread *thread)
size_t thread__fprintf(struct thread *thread, FILE *fp)
{
return fprintf(fp, "Thread %d %s\n", thread->tid, thread__comm_str(thread)) +
- map_groups__fprintf(&thread->mg, verbose, fp);
+ map_groups__fprintf(thread->mg, verbose, fp);
}
void thread__insert_map(struct thread *thread, struct map *map)
{
- map_groups__fixup_overlappings(&thread->mg, map, verbose, stderr);
- map_groups__insert(&thread->mg, map);
+ map_groups__fixup_overlappings(thread->mg, map, verbose, stderr);
+ map_groups__insert(thread->mg, map);
+}
+
+static int thread__clone_map_groups(struct thread *thread,
+ struct thread *parent)
+{
+ int i;
+
+ /* This is new thread, we share map groups for process. */
+ if (thread->pid_ == parent->pid_)
+ return 0;
+
+ /* But this one is new process, copy maps. */
+ for (i = 0; i < MAP__NR_TYPES; ++i)
+ if (map_groups__clone(thread->mg, parent->mg, i) < 0)
+ return -ENOMEM;
+
+ return 0;
}
int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
{
- int i, err;
+ int err;
if (parent->comm_set) {
const char *comm = thread__comm_str(parent);
@@ -134,13 +167,8 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
thread->comm_set = true;
}
- for (i = 0; i < MAP__NR_TYPES; ++i)
- if (map_groups__clone(&thread->mg, &parent->mg, i) < 0)
- return -ENOMEM;
-
thread->ppid = parent->tid;
-
- return 0;
+ return thread__clone_map_groups(thread, parent);
}
void thread__find_cpumode_addr_location(struct thread *thread,
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 9b29f085aede..3c0c2724f82c 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -13,7 +13,7 @@ struct thread {
struct rb_node rb_node;
struct list_head node;
};
- struct map_groups mg;
+ struct map_groups *mg;
pid_t pid_; /* Not all tools update this */
pid_t tid;
pid_t ppid;
@@ -30,6 +30,7 @@ struct machine;
struct comm;
struct thread *thread__new(pid_t pid, pid_t tid);
+int thread__init_map_groups(struct thread *thread, struct machine *machine);
void thread__delete(struct thread *thread);
static inline void thread__exited(struct thread *thread)
{
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index dab14d0ad3d0..f92c37abb0a8 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -2,7 +2,7 @@
#define __PERF_TOP_H 1
#include "tool.h"
-#include "types.h"
+#include <linux/types.h>
#include <stddef.h>
#include <stdbool.h>
#include <termios.h>
diff --git a/tools/perf/util/types.h b/tools/perf/util/types.h
deleted file mode 100644
index c51fa6b70a28..000000000000
--- a/tools/perf/util/types.h
+++ /dev/null
@@ -1,24 +0,0 @@
-#ifndef __PERF_TYPES_H
-#define __PERF_TYPES_H
-
-#include <stdint.h>
-
-/*
- * We define u64 as uint64_t for every architecture
- * so that we can print it with "%"PRIx64 without getting warnings.
- */
-typedef uint64_t u64;
-typedef int64_t s64;
-typedef unsigned int u32;
-typedef signed int s32;
-typedef unsigned short u16;
-typedef signed short s16;
-typedef unsigned char u8;
-typedef signed char s8;
-
-union u64_swap {
- u64 val64;
- u32 val32[2];
-};
-
-#endif /* __PERF_TYPES_H */
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 67db73ec3dab..5ec80a575b50 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -7,7 +7,7 @@
#include "unwind-libdw.h"
#include "machine.h"
#include "thread.h"
-#include "types.h"
+#include <linux/types.h>
#include "event.h"
#include "perf_regs.h"
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index bd5768d74f01..25578b98f5c5 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -250,7 +250,6 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine,
/* Check the .eh_frame section for unwinding info */
offset = elf_section_offset(fd, ".eh_frame_hdr");
- close(fd);
if (offset)
ret = unwind_spec_ehframe(dso, machine, offset,
@@ -271,7 +270,6 @@ static int read_unwind_spec_debug_frame(struct dso *dso,
/* Check the .debug_frame section for unwinding info */
*offset = elf_section_offset(fd, ".debug_frame");
- close(fd);
if (*offset)
return 0;
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
index b031316f221a..f03061260b4e 100644
--- a/tools/perf/util/unwind.h
+++ b/tools/perf/util/unwind.h
@@ -1,7 +1,7 @@
#ifndef __UNWIND_H
#define __UNWIND_H
-#include "types.h"
+#include <linux/types.h>
#include "event.h"
#include "symbol.h"
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 9f66549562bd..95aefa78bb07 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -17,6 +17,7 @@
* XXX We need to find a better place for these things...
*/
unsigned int page_size;
+int cacheline_size;
bool test_attr__enabled;
@@ -166,6 +167,8 @@ static ssize_t ion(bool is_read, int fd, void *buf, size_t n)
ssize_t ret = is_read ? read(fd, buf, left) :
write(fd, buf, left);
+ if (ret < 0 && errno == EINTR)
+ continue;
if (ret <= 0)
return ret;
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 6995d66f225c..66864364ccb4 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -69,7 +69,7 @@
#include <sys/ioctl.h>
#include <inttypes.h>
#include <linux/magic.h>
-#include "types.h"
+#include <linux/types.h>
#include <sys/ttydefaults.h>
#include <api/fs/debugfs.h>
#include <termios.h>
@@ -304,6 +304,7 @@ char *rtrim(char *s);
void dump_stack(void);
extern unsigned int page_size;
+extern int cacheline_size;
void get_term_dimensions(struct winsize *ws);
diff --git a/tools/perf/util/values.h b/tools/perf/util/values.h
index 2fa967e1a88a..b21a80c6cf8d 100644
--- a/tools/perf/util/values.h
+++ b/tools/perf/util/values.h
@@ -1,7 +1,7 @@
#ifndef __PERF_VALUES_H
#define __PERF_VALUES_H
-#include "types.h"
+#include <linux/types.h>
struct perf_read_values {
int threads;