#include "util/symbol.h"
#include "util/thread.h"
#include "util/header.h"
+#include "util/session.h"
#include "util/parse-options.h"
#include "util/trace-event.h"
#include "util/debug.h"
-#include "util/data_map.h"
#include <linux/rbtree.h>
static char const *input_name = "perf.data";
-static struct perf_header *header;
-static u64 sample_type;
-
static int alloc_flag;
static int caller_flag;
static unsigned long total_requested, total_allocated;
static unsigned long nr_allocs, nr_cross_allocs;
-struct raw_event_sample {
- u32 size;
- char data[0];
-};
-
#define PATH_SYS_NODE "/sys/devices/system/node"
static void init_cpunode_map(void)
if (!dir1)
return;
- while (true) {
- dent1 = readdir(dir1);
- if (!dent1)
- break;
-
- if (sscanf(dent1->d_name, "node%u", &mem) < 1)
+ while ((dent1 = readdir(dir1)) != NULL) {
+ if (dent1->d_type != DT_DIR ||
+ sscanf(dent1->d_name, "node%u", &mem) < 1)
continue;
snprintf(buf, PATH_MAX, "%s/%s", PATH_SYS_NODE, dent1->d_name);
dir2 = opendir(buf);
if (!dir2)
continue;
- while (true) {
- dent2 = readdir(dir2);
- if (!dent2)
- break;
- if (sscanf(dent2->d_name, "cpu%u", &cpu) < 1)
+ while ((dent2 = readdir(dir2)) != NULL) {
+ if (dent2->d_type != DT_LNK ||
+ sscanf(dent2->d_name, "cpu%u", &cpu) < 1)
continue;
cpunode_map[cpu] = mem;
}
if (data && data->ptr == ptr) {
data->hit++;
data->bytes_req += bytes_req;
- data->bytes_alloc += bytes_req;
+ data->bytes_alloc += bytes_alloc;
} else {
data = malloc(sizeof(*data));
if (!data)
if (data && data->call_site == call_site) {
data->hit++;
data->bytes_req += bytes_req;
- data->bytes_alloc += bytes_req;
+ data->bytes_alloc += bytes_alloc;
} else {
data = malloc(sizeof(*data));
if (!data)
}
}
-static void process_alloc_event(struct raw_event_sample *raw,
+static void process_alloc_event(void *data,
struct event *event,
int cpu,
u64 timestamp __used,
int bytes_alloc;
int node1, node2;
- ptr = raw_field_value(event, "ptr", raw->data);
- call_site = raw_field_value(event, "call_site", raw->data);
- bytes_req = raw_field_value(event, "bytes_req", raw->data);
- bytes_alloc = raw_field_value(event, "bytes_alloc", raw->data);
+ ptr = raw_field_value(event, "ptr", data);
+ call_site = raw_field_value(event, "call_site", data);
+ bytes_req = raw_field_value(event, "bytes_req", data);
+ bytes_alloc = raw_field_value(event, "bytes_alloc", data);
insert_alloc_stat(call_site, ptr, bytes_req, bytes_alloc, cpu);
insert_caller_stat(call_site, bytes_req, bytes_alloc);
if (node) {
node1 = cpunode_map[cpu];
- node2 = raw_field_value(event, "node", raw->data);
+ node2 = raw_field_value(event, "node", data);
if (node1 != node2)
nr_cross_allocs++;
}
return NULL;
}
-static void process_free_event(struct raw_event_sample *raw,
+static void process_free_event(void *data,
struct event *event,
int cpu,
u64 timestamp __used,
unsigned long ptr;
struct alloc_stat *s_alloc, *s_caller;
- ptr = raw_field_value(event, "ptr", raw->data);
+ ptr = raw_field_value(event, "ptr", data);
s_alloc = search_alloc_stat(ptr, 0, &root_alloc_stat, ptr_cmp);
if (!s_alloc)
}
static void
-process_raw_event(event_t *raw_event __used, void *more_data,
+process_raw_event(event_t *raw_event __used, void *data,
int cpu, u64 timestamp, struct thread *thread)
{
- struct raw_event_sample *raw = more_data;
struct event *event;
int type;
- type = trace_parse_common_type(raw->data);
+ type = trace_parse_common_type(data);
event = trace_find_event(type);
if (!strcmp(event->name, "kmalloc") ||
!strcmp(event->name, "kmem_cache_alloc")) {
- process_alloc_event(raw, event, cpu, timestamp, thread, 0);
+ process_alloc_event(data, event, cpu, timestamp, thread, 0);
return;
}
if (!strcmp(event->name, "kmalloc_node") ||
!strcmp(event->name, "kmem_cache_alloc_node")) {
- process_alloc_event(raw, event, cpu, timestamp, thread, 1);
+ process_alloc_event(data, event, cpu, timestamp, thread, 1);
return;
}
if (!strcmp(event->name, "kfree") ||
!strcmp(event->name, "kmem_cache_free")) {
- process_free_event(raw, event, cpu, timestamp, thread);
+ process_free_event(data, event, cpu, timestamp, thread);
return;
}
}
-static int process_sample_event(event_t *event)
+static int process_sample_event(event_t *event, struct perf_session *session)
{
- u64 ip = event->ip.ip;
- u64 timestamp = -1;
- u32 cpu = -1;
- u64 period = 1;
- void *more_data = event->ip.__more_data;
- struct thread *thread = threads__findnew(event->ip.pid);
-
- if (sample_type & PERF_SAMPLE_TIME) {
- timestamp = *(u64 *)more_data;
- more_data += sizeof(u64);
- }
+ struct sample_data data;
+ struct thread *thread;
- if (sample_type & PERF_SAMPLE_CPU) {
- cpu = *(u32 *)more_data;
- more_data += sizeof(u32);
- more_data += sizeof(u32); /* reserved */
- }
+ memset(&data, 0, sizeof(data));
+ data.time = -1;
+ data.cpu = -1;
+ data.period = 1;
- if (sample_type & PERF_SAMPLE_PERIOD) {
- period = *(u64 *)more_data;
- more_data += sizeof(u64);
- }
+ event__parse_sample(event, session->sample_type, &data);
- dump_printf("(IP, %d): %d/%d: %p period: %Ld\n",
- event->header.misc,
- event->ip.pid, event->ip.tid,
- (void *)(long)ip,
- (long long)period);
+ dump_printf("(IP, %d): %d/%d: %#Lx period: %Ld\n", event->header.misc,
+ data.pid, data.tid, data.ip, data.period);
+ thread = perf_session__findnew(session, event->ip.pid);
if (thread == NULL) {
pr_debug("problem processing %d event, skipping it.\n",
event->header.type);
dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
- process_raw_event(event, more_data, cpu, timestamp, thread);
-
- return 0;
-}
-
-static int sample_type_check(u64 type)
-{
- sample_type = type;
-
- if (!(sample_type & PERF_SAMPLE_RAW)) {
- fprintf(stderr,
- "No trace sample to read. Did you call perf record "
- "without -R?");
- return -1;
- }
+ process_raw_event(event, data.raw_data, data.cpu,
+ data.time, thread);
return 0;
}
-static struct perf_file_handler file_handler = {
- .process_sample_event = process_sample_event,
- .process_comm_event = event__process_comm,
- .sample_type_check = sample_type_check,
+static struct perf_event_ops event_ops = {
+ .sample = process_sample_event,
+ .comm = event__process_comm,
+ .ordered_samples = true,
};
-static int read_events(void)
-{
- register_idle_thread();
- register_perf_file_handler(&file_handler);
-
- return mmap_dispatch_perf_file(&header, input_name, 0, 0,
- &event__cwdlen, &event__cwd);
-}
-
static double fragmentation(unsigned long n_req, unsigned long n_alloc)
{
if (n_alloc == 0)
return 100.0 - (100.0 * n_req / n_alloc);
}
-static void __print_result(struct rb_root *root, int n_lines, int is_caller)
+static void __print_result(struct rb_root *root, struct perf_session *session,
+ int n_lines, int is_caller)
{
struct rb_node *next;
+ struct machine *machine;
printf("%.102s\n", graph_dotted_line);
printf(" %-34s |", is_caller ? "Callsite": "Alloc Ptr");
- printf(" Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag\n");
+ printf(" Total_alloc/Per | Total_req/Per | Hit | Ping-pong | Frag\n");
printf("%.102s\n", graph_dotted_line);
next = rb_first(root);
+ machine = perf_session__find_host_machine(session);
+ if (!machine) {
+ pr_err("__print_result: couldn't find kernel information\n");
+ return;
+ }
while (next && n_lines--) {
struct alloc_stat *data = rb_entry(next, struct alloc_stat,
node);
struct symbol *sym = NULL;
+ struct map *map;
char buf[BUFSIZ];
u64 addr;
if (is_caller) {
addr = data->call_site;
if (!raw_ip)
- sym = thread__find_function(kthread, addr, NULL);
+ sym = machine__find_kernel_function(machine, addr, &map, NULL);
} else
addr = data->ptr;
if (sym != NULL)
snprintf(buf, sizeof(buf), "%s+%Lx", sym->name,
- addr - sym->start);
+ addr - map->unmap_ip(map, sym->start));
else
snprintf(buf, sizeof(buf), "%#Lx", addr);
printf(" %-34s |", buf);
- printf(" %9llu/%-5lu | %9llu/%-5lu | %6lu | %8lu | %6.3f%%\n",
+ printf(" %9llu/%-5lu | %9llu/%-5lu | %8lu | %8lu | %6.3f%%\n",
(unsigned long long)data->bytes_alloc,
(unsigned long)data->bytes_alloc / data->hit,
(unsigned long long)data->bytes_req,
printf("Cross CPU allocations: %lu/%lu\n", nr_cross_allocs, nr_allocs);
}
-static void print_result(void)
+static void print_result(struct perf_session *session)
{
if (caller_flag)
- __print_result(&root_caller_sorted, caller_lines, 1);
+ __print_result(&root_caller_sorted, session, caller_lines, 1);
if (alloc_flag)
- __print_result(&root_alloc_sorted, alloc_lines, 0);
+ __print_result(&root_alloc_sorted, session, alloc_lines, 0);
print_summary();
}
static int __cmd_kmem(void)
{
+ int err = -EINVAL;
+ struct perf_session *session = perf_session__new(input_name, O_RDONLY, 0, false);
+ if (session == NULL)
+ return -ENOMEM;
+
+ if (perf_session__create_kernel_maps(session) < 0)
+ goto out_delete;
+
+ if (!perf_session__has_traces(session, "kmem record"))
+ goto out_delete;
+
setup_pager();
- read_events();
+ err = perf_session__process_events(session, &event_ops);
+ if (err != 0)
+ goto out_delete;
sort_result();
- print_result();
-
- return 0;
+ print_result(session);
+out_delete:
+ perf_session__delete(session);
+ return err;
}
static const char * const kmem_usage[] = {
- "perf kmem [<options>] {record}",
+ "perf kmem [<options>] {record|stat}",
NULL
};
return 0;
}
-static int parse_stat_opt(const struct option *opt __used,
- const char *arg, int unset __used)
+static int parse_caller_opt(const struct option *opt __used,
+ const char *arg __used, int unset __used)
{
- if (!arg)
- return -1;
+ caller_flag = (alloc_flag + 1);
+ return 0;
+}
- if (strcmp(arg, "alloc") == 0)
- alloc_flag = (caller_flag + 1);
- else if (strcmp(arg, "caller") == 0)
- caller_flag = (alloc_flag + 1);
- else
- return -1;
+static int parse_alloc_opt(const struct option *opt __used,
+ const char *arg __used, int unset __used)
+{
+ alloc_flag = (caller_flag + 1);
return 0;
}
static const struct option kmem_options[] = {
OPT_STRING('i', "input", &input_name, "file",
"input file name"),
- OPT_CALLBACK(0, "stat", NULL, "<alloc>|<caller>",
- "stat selector, Pass 'alloc' or 'caller'.",
- parse_stat_opt),
+ OPT_CALLBACK_NOOPT(0, "caller", NULL, NULL,
+ "show per-callsite statistics",
+ parse_caller_opt),
+ OPT_CALLBACK_NOOPT(0, "alloc", NULL, NULL,
+ "show per-allocation statistics",
+ parse_alloc_opt),
OPT_CALLBACK('s', "sort", NULL, "key[,key2...]",
"sort by keys: ptr, call_site, bytes, hit, pingpong, frag",
parse_sort_opt),
OPT_CALLBACK('l', "line", NULL, "num",
- "show n lins",
+ "show n lines",
parse_line_opt),
OPT_BOOLEAN(0, "raw-ip", &raw_ip, "show raw ip instead of symbol"),
OPT_END()
"record",
"-a",
"-R",
- "-M",
"-f",
"-c", "1",
"-e", "kmem:kmalloc",
int cmd_kmem(int argc, const char **argv, const char *prefix __used)
{
- symbol__init(0);
-
argc = parse_options(argc, argv, kmem_options, kmem_usage, 0);
- if (argc && !strncmp(argv[0], "rec", 3))
- return __cmd_record(argc, argv);
- else if (argc)
+ if (!argc)
usage_with_options(kmem_usage, kmem_options);
- if (list_empty(&caller_sort))
- setup_sorting(&caller_sort, default_sort_order);
- if (list_empty(&alloc_sort))
- setup_sorting(&alloc_sort, default_sort_order);
+ symbol__init();
- setup_cpunode_map();
+ if (!strncmp(argv[0], "rec", 3)) {
+ return __cmd_record(argc, argv);
+ } else if (!strcmp(argv[0], "stat")) {
+ setup_cpunode_map();
+
+ if (list_empty(&caller_sort))
+ setup_sorting(&caller_sort, default_sort_order);
+ if (list_empty(&alloc_sort))
+ setup_sorting(&alloc_sort, default_sort_order);
- return __cmd_kmem();
+ return __cmd_kmem();
+ } else
+ usage_with_options(kmem_usage, kmem_options);
+
+ return 0;
}