OpenCloudOS-Kernel/tools/perf/builtin-mem.c

324 lines
7.2 KiB
C
Raw Normal View History

#include "builtin.h"
#include "perf.h"
#include "util/parse-options.h"
#include "util/trace-event.h"
#include "util/tool.h"
#include "util/session.h"
#include "util/data.h"
#define MEM_OPERATION_LOAD 0x1
#define MEM_OPERATION_STORE 0x2
struct perf_mem {
struct perf_tool tool;
char const *input_name;
bool hide_unresolved;
bool dump_raw;
perf mem: Support using -f to override perf.data file ownership Enable perf mem to use perf.data when it is not owned by current user or root. Example: # perf mem -t load record ls # chown Yunlong.Song:Yunlong.Song perf.data # ls -al perf.data -rw------- 1 Yunlong.Song Yunlong.Song 16392 Apr 2 14:34 perf.data # id uid=0(root) gid=0(root) groups=0(root),64(pkcs11) Before this patch: # perf mem -D report File perf.data not owned by current user or root (use -f to override) # perf mem -D -f report Error: unknown switch `f' usage: perf mem [<options>] {record|report} -t, --type <type> memory operations(load,store) Default load,store -D, --dump-raw-samples dump raw samples in ASCII -U, --hide-unresolved Only display entries resolved to a symbol -i, --input <file> input file name -C, --cpu <cpu> list of cpus to profile -x, --field-separator <separator> separator for columns, no spaces will be added between columns '.' is reserved. As shown above, the -f option does not work at all. After this patch: # perf mem -D report File perf.data not owned by current user or root (use -f to override) # perf mem -D -f report # PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL 39095 39095 0xffffffff81127e40 0x016ffff887f45148338 8 0x68100142 /proc/kcore:perf_event_aux 39095 39095 0xffffffff8100a3fe 0xffff89007f8cb7d0 6 0x68100142 /proc/kcore:native_sched_clock 39095 39095 0xffffffff81309139 0xffff88bf44c9ded8 6 0x68100142 /proc/kcore:acpi_map_lookup 39095 39095 0xffffffff810f8c4c 0xffff89007f8ccd88 6 0x68100142 /proc/kcore:rcu_nmi_exit 39095 39095 0xffffffff81136346 0xffff88fea995dd50 6 0x68100142 /proc/kcore:unlock_page 39095 39095 0xffffffff812a64a2 0xffff88fea995dcc8 6 0x68100142 /proc/kcore:half_md4_transform 39095 39095 0x7f0cf877c7e9 0x25dfb94 6 0x68100142 /lib64/libc-2.19.so:__readdir64 39095 39095 0x7f0cf87575a3 0x7f0cf9163731 6 0x68100142 /lib64/libc-2.19.so:__strcoll_l 39095 39095 0xffffffff8116910e 0xffffea01c1bfbd50 23 0x68100242 /proc/kcore:page_remove_rmap As shown above, the -f option really works now. Signed-off-by: Yunlong Song <yunlong.song@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1427982439-27388-7-git-send-email-yunlong.song@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-02 21:47:15 +08:00
bool force;
int operation;
const char *cpu_list;
DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
};
static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
{
int rec_argc, i = 0, j;
const char **rec_argv;
int ret;
rec_argc = argc + 7; /* max number of arguments */
rec_argv = calloc(rec_argc + 1, sizeof(char *));
if (!rec_argv)
return -1;
rec_argv[i++] = "record";
if (mem->operation & MEM_OPERATION_LOAD)
rec_argv[i++] = "-W";
rec_argv[i++] = "-d";
if (mem->operation & MEM_OPERATION_LOAD) {
rec_argv[i++] = "-e";
rec_argv[i++] = "cpu/mem-loads/pp";
}
if (mem->operation & MEM_OPERATION_STORE) {
rec_argv[i++] = "-e";
rec_argv[i++] = "cpu/mem-stores/pp";
}
for (j = 1; j < argc; j++, i++)
rec_argv[i] = argv[j];
ret = cmd_record(i, rec_argv, NULL);
free(rec_argv);
return ret;
}
static int
dump_raw_samples(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct machine *machine)
{
struct perf_mem *mem = container_of(tool, struct perf_mem, tool);
struct addr_location al;
const char *fmt;
if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
fprintf(stderr, "problem processing %d event, skipping it.\n",
event->header.type);
return -1;
}
if (al.filtered || (mem->hide_unresolved && al.sym == NULL))
perf machine: Protect the machine->threads with a rwlock In addition to using refcounts for the struct thread lifetime management, we need to protect access to machine->threads from concurrent access. That happens in 'perf top', where a thread processes events, inserting and deleting entries from that rb_tree while another thread decays hist_entries, that end up dropping references and ultimately deleting threads from the rb_tree and releasing its resources when no further hist_entry (or other data structures, like in 'perf sched') references it. So the rule is the same for refcounts + protected trees in the kernel, get the tree lock, find object, bump the refcount, drop the tree lock, return, use object, drop the refcount if no more use of it is needed, keep it if storing it in some other data structure, drop when releasing that data structure. I.e. pair "t = machine__find(new)_thread()" with a "thread__put(t)", and "perf_event__preprocess_sample(&al)" with "addr_location__put(&al)". The addr_location__put() one is because as we return references to several data structures, we may end up adding more reference counting for the other data structures and then we'll drop it at addr_location__put() time. Acked-by: David Ahern <dsahern@gmail.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Borislav Petkov <bp@suse.de> Cc: Don Zickus <dzickus@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-bs9rt4n0jw3hi9f3zxyy3xln@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-07 07:43:22 +08:00
goto out_put;
if (al.map != NULL)
al.map->dso->hit = 1;
if (symbol_conf.field_sep) {
fmt = "%d%s%d%s0x%"PRIx64"%s0x%"PRIx64"%s%"PRIu64
"%s0x%"PRIx64"%s%s:%s\n";
} else {
fmt = "%5d%s%5d%s0x%016"PRIx64"%s0x016%"PRIx64
"%s%5"PRIu64"%s0x%06"PRIx64"%s%s:%s\n";
symbol_conf.field_sep = " ";
}
printf(fmt,
sample->pid,
symbol_conf.field_sep,
sample->tid,
symbol_conf.field_sep,
sample->ip,
symbol_conf.field_sep,
sample->addr,
symbol_conf.field_sep,
sample->weight,
symbol_conf.field_sep,
sample->data_src,
symbol_conf.field_sep,
al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???",
al.sym ? al.sym->name : "???");
perf machine: Protect the machine->threads with a rwlock In addition to using refcounts for the struct thread lifetime management, we need to protect access to machine->threads from concurrent access. That happens in 'perf top', where a thread processes events, inserting and deleting entries from that rb_tree while another thread decays hist_entries, that end up dropping references and ultimately deleting threads from the rb_tree and releasing its resources when no further hist_entry (or other data structures, like in 'perf sched') references it. So the rule is the same for refcounts + protected trees in the kernel, get the tree lock, find object, bump the refcount, drop the tree lock, return, use object, drop the refcount if no more use of it is needed, keep it if storing it in some other data structure, drop when releasing that data structure. I.e. pair "t = machine__find(new)_thread()" with a "thread__put(t)", and "perf_event__preprocess_sample(&al)" with "addr_location__put(&al)". The addr_location__put() one is because as we return references to several data structures, we may end up adding more reference counting for the other data structures and then we'll drop it at addr_location__put() time. Acked-by: David Ahern <dsahern@gmail.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Borislav Petkov <bp@suse.de> Cc: Don Zickus <dzickus@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-bs9rt4n0jw3hi9f3zxyy3xln@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-07 07:43:22 +08:00
out_put:
addr_location__put(&al);
return 0;
}
static int process_sample_event(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct perf_evsel *evsel __maybe_unused,
struct machine *machine)
{
return dump_raw_samples(tool, event, sample, machine);
}
static int report_raw_events(struct perf_mem *mem)
{
struct perf_data_file file = {
.path = input_name,
.mode = PERF_DATA_MODE_READ,
perf mem: Support using -f to override perf.data file ownership Enable perf mem to use perf.data when it is not owned by current user or root. Example: # perf mem -t load record ls # chown Yunlong.Song:Yunlong.Song perf.data # ls -al perf.data -rw------- 1 Yunlong.Song Yunlong.Song 16392 Apr 2 14:34 perf.data # id uid=0(root) gid=0(root) groups=0(root),64(pkcs11) Before this patch: # perf mem -D report File perf.data not owned by current user or root (use -f to override) # perf mem -D -f report Error: unknown switch `f' usage: perf mem [<options>] {record|report} -t, --type <type> memory operations(load,store) Default load,store -D, --dump-raw-samples dump raw samples in ASCII -U, --hide-unresolved Only display entries resolved to a symbol -i, --input <file> input file name -C, --cpu <cpu> list of cpus to profile -x, --field-separator <separator> separator for columns, no spaces will be added between columns '.' is reserved. As shown above, the -f option does not work at all. After this patch: # perf mem -D report File perf.data not owned by current user or root (use -f to override) # perf mem -D -f report # PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL 39095 39095 0xffffffff81127e40 0x016ffff887f45148338 8 0x68100142 /proc/kcore:perf_event_aux 39095 39095 0xffffffff8100a3fe 0xffff89007f8cb7d0 6 0x68100142 /proc/kcore:native_sched_clock 39095 39095 0xffffffff81309139 0xffff88bf44c9ded8 6 0x68100142 /proc/kcore:acpi_map_lookup 39095 39095 0xffffffff810f8c4c 0xffff89007f8ccd88 6 0x68100142 /proc/kcore:rcu_nmi_exit 39095 39095 0xffffffff81136346 0xffff88fea995dd50 6 0x68100142 /proc/kcore:unlock_page 39095 39095 0xffffffff812a64a2 0xffff88fea995dcc8 6 0x68100142 /proc/kcore:half_md4_transform 39095 39095 0x7f0cf877c7e9 0x25dfb94 6 0x68100142 /lib64/libc-2.19.so:__readdir64 39095 39095 0x7f0cf87575a3 0x7f0cf9163731 6 0x68100142 /lib64/libc-2.19.so:__strcoll_l 39095 39095 0xffffffff8116910e 0xffffea01c1bfbd50 23 0x68100242 /proc/kcore:page_remove_rmap As shown above, the -f option really works now. Signed-off-by: Yunlong Song <yunlong.song@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1427982439-27388-7-git-send-email-yunlong.song@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-02 21:47:15 +08:00
.force = mem->force,
};
int ret;
struct perf_session *session = perf_session__new(&file, false,
&mem->tool);
if (session == NULL)
return -1;
if (mem->cpu_list) {
ret = perf_session__cpu_bitmap(session, mem->cpu_list,
mem->cpu_bitmap);
if (ret < 0)
goto out_delete;
}
ret = symbol__init(&session->header.env);
if (ret < 0)
goto out_delete;
printf("# PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n");
ret = perf_session__process_events(session);
out_delete:
perf_session__delete(session);
return ret;
}
static int report_events(int argc, const char **argv, struct perf_mem *mem)
{
const char **rep_argv;
int ret, i = 0, j, rep_argc;
if (mem->dump_raw)
return report_raw_events(mem);
rep_argc = argc + 3;
rep_argv = calloc(rep_argc + 1, sizeof(char *));
if (!rep_argv)
return -1;
rep_argv[i++] = "report";
rep_argv[i++] = "--mem-mode";
rep_argv[i++] = "-n"; /* display number of samples */
/*
* there is no weight (cost) associated with stores, so don't print
* the column
*/
if (!(mem->operation & MEM_OPERATION_LOAD))
rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr,"
"dso_daddr,tlb,locked";
for (j = 1; j < argc; j++, i++)
rep_argv[i] = argv[j];
ret = cmd_report(i, rep_argv, NULL);
free(rep_argv);
return ret;
}
struct mem_mode {
const char *name;
int mode;
};
#define MEM_OPT(n, m) \
{ .name = n, .mode = (m) }
#define MEM_END { .name = NULL }
static const struct mem_mode mem_modes[]={
MEM_OPT("load", MEM_OPERATION_LOAD),
MEM_OPT("store", MEM_OPERATION_STORE),
MEM_END
};
static int
parse_mem_ops(const struct option *opt, const char *str, int unset)
{
int *mode = (int *)opt->value;
const struct mem_mode *m;
char *s, *os = NULL, *p;
int ret = -1;
if (unset)
return 0;
/* str may be NULL in case no arg is passed to -t */
if (str) {
/* because str is read-only */
s = os = strdup(str);
if (!s)
return -1;
/* reset mode */
*mode = 0;
for (;;) {
p = strchr(s, ',');
if (p)
*p = '\0';
for (m = mem_modes; m->name; m++) {
if (!strcasecmp(s, m->name))
break;
}
if (!m->name) {
fprintf(stderr, "unknown sampling op %s,"
" check man page\n", s);
goto error;
}
*mode |= m->mode;
if (!p)
break;
s = p + 1;
}
}
ret = 0;
if (*mode == 0)
*mode = MEM_OPERATION_LOAD;
error:
free(os);
return ret;
}
int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
{
struct stat st;
struct perf_mem mem = {
.tool = {
.sample = process_sample_event,
.mmap = perf_event__process_mmap,
.mmap2 = perf_event__process_mmap2,
.comm = perf_event__process_comm,
.lost = perf_event__process_lost,
.fork = perf_event__process_fork,
.build_id = perf_event__process_build_id,
.ordered_events = true,
},
.input_name = "perf.data",
/*
* default to both load an store sampling
*/
.operation = MEM_OPERATION_LOAD | MEM_OPERATION_STORE,
};
const struct option mem_options[] = {
OPT_CALLBACK('t', "type", &mem.operation,
"type", "memory operations(load,store) Default load,store",
parse_mem_ops),
OPT_BOOLEAN('D', "dump-raw-samples", &mem.dump_raw,
"dump raw samples in ASCII"),
OPT_BOOLEAN('U', "hide-unresolved", &mem.hide_unresolved,
"Only display entries resolved to a symbol"),
OPT_STRING('i', "input", &input_name, "file",
"input file name"),
OPT_STRING('C', "cpu", &mem.cpu_list, "cpu",
"list of cpus to profile"),
OPT_STRING_NOEMPTY('x', "field-separator", &symbol_conf.field_sep,
"separator",
"separator for columns, no spaces will be added"
" between columns '.' is reserved."),
perf mem: Support using -f to override perf.data file ownership Enable perf mem to use perf.data when it is not owned by current user or root. Example: # perf mem -t load record ls # chown Yunlong.Song:Yunlong.Song perf.data # ls -al perf.data -rw------- 1 Yunlong.Song Yunlong.Song 16392 Apr 2 14:34 perf.data # id uid=0(root) gid=0(root) groups=0(root),64(pkcs11) Before this patch: # perf mem -D report File perf.data not owned by current user or root (use -f to override) # perf mem -D -f report Error: unknown switch `f' usage: perf mem [<options>] {record|report} -t, --type <type> memory operations(load,store) Default load,store -D, --dump-raw-samples dump raw samples in ASCII -U, --hide-unresolved Only display entries resolved to a symbol -i, --input <file> input file name -C, --cpu <cpu> list of cpus to profile -x, --field-separator <separator> separator for columns, no spaces will be added between columns '.' is reserved. As shown above, the -f option does not work at all. After this patch: # perf mem -D report File perf.data not owned by current user or root (use -f to override) # perf mem -D -f report # PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL 39095 39095 0xffffffff81127e40 0x016ffff887f45148338 8 0x68100142 /proc/kcore:perf_event_aux 39095 39095 0xffffffff8100a3fe 0xffff89007f8cb7d0 6 0x68100142 /proc/kcore:native_sched_clock 39095 39095 0xffffffff81309139 0xffff88bf44c9ded8 6 0x68100142 /proc/kcore:acpi_map_lookup 39095 39095 0xffffffff810f8c4c 0xffff89007f8ccd88 6 0x68100142 /proc/kcore:rcu_nmi_exit 39095 39095 0xffffffff81136346 0xffff88fea995dd50 6 0x68100142 /proc/kcore:unlock_page 39095 39095 0xffffffff812a64a2 0xffff88fea995dcc8 6 0x68100142 /proc/kcore:half_md4_transform 39095 39095 0x7f0cf877c7e9 0x25dfb94 6 0x68100142 /lib64/libc-2.19.so:__readdir64 39095 39095 0x7f0cf87575a3 0x7f0cf9163731 6 0x68100142 /lib64/libc-2.19.so:__strcoll_l 39095 39095 0xffffffff8116910e 0xffffea01c1bfbd50 23 0x68100242 /proc/kcore:page_remove_rmap As shown above, the -f option really works now. Signed-off-by: Yunlong Song <yunlong.song@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1427982439-27388-7-git-send-email-yunlong.song@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-02 21:47:15 +08:00
OPT_BOOLEAN('f', "force", &mem.force, "don't complain, do it"),
OPT_END()
};
const char *const mem_subcommands[] = { "record", "report", NULL };
const char *mem_usage[] = {
NULL,
NULL
};
argc = parse_options_subcommand(argc, argv, mem_options, mem_subcommands,
mem_usage, PARSE_OPT_STOP_AT_NON_OPTION);
if (!argc || !(strncmp(argv[0], "rec", 3) || mem.operation))
usage_with_options(mem_usage, mem_options);
if (!mem.input_name || !strlen(mem.input_name)) {
if (!fstat(STDIN_FILENO, &st) && S_ISFIFO(st.st_mode))
mem.input_name = "-";
else
mem.input_name = "perf.data";
}
if (!strncmp(argv[0], "rec", 3))
return __cmd_record(argc, argv, &mem);
else if (!strncmp(argv[0], "rep", 3))
return report_events(argc, argv, &mem);
else
usage_with_options(mem_usage, mem_options);
return 0;
}