linux_dsm_epyc7002/tools/perf/tests/code-reading.c

744 lines
16 KiB
C
Raw Normal View History

License cleanup: add SPDX GPL-2.0 license identifier to files with no license Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 21:07:57 +07:00
// SPDX-License-Identifier: GPL-2.0
#include <errno.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <inttypes.h>
#include <stdlib.h>
#include <unistd.h>
#include <stdio.h>
#include <string.h>
#include <sys/param.h>
#include "parse-events.h"
#include "evlist.h"
#include "evsel.h"
#include "thread_map.h"
#include "cpumap.h"
#include "machine.h"
#include "map.h"
#include "symbol.h"
#include "event.h"
#include "thread.h"
#include "tests.h"
#include "sane_ctype.h"
#define BUFSZ 1024
#define READLEN 128
struct state {
u64 done[1024];
size_t done_cnt;
};
static unsigned int hex(char c)
{
if (c >= '0' && c <= '9')
return c - '0';
if (c >= 'a' && c <= 'f')
return c - 'a' + 10;
return c - 'A' + 10;
}
static size_t read_objdump_chunk(const char **line, unsigned char **buf,
size_t *buf_len)
{
size_t bytes_read = 0;
unsigned char *chunk_start = *buf;
/* Read bytes */
while (*buf_len > 0) {
char c1, c2;
/* Get 2 hex digits */
c1 = *(*line)++;
if (!isxdigit(c1))
break;
c2 = *(*line)++;
if (!isxdigit(c2))
break;
/* Store byte and advance buf */
**buf = (hex(c1) << 4) | hex(c2);
(*buf)++;
(*buf_len)--;
bytes_read++;
/* End of chunk? */
if (isspace(**line))
break;
}
/*
* objdump will display raw insn as LE if code endian
* is LE and bytes_per_chunk > 1. In that case reverse
* the chunk we just read.
*
* see disassemble_bytes() at binutils/objdump.c for details
* how objdump chooses display endian)
*/
if (bytes_read > 1 && !bigendian()) {
unsigned char *chunk_end = chunk_start + bytes_read - 1;
unsigned char tmp;
while (chunk_start < chunk_end) {
tmp = *chunk_start;
*chunk_start = *chunk_end;
*chunk_end = tmp;
chunk_start++;
chunk_end--;
}
}
return bytes_read;
}
static size_t read_objdump_line(const char *line, unsigned char *buf,
size_t buf_len)
{
const char *p;
size_t ret, bytes_read = 0;
/* Skip to a colon */
p = strchr(line, ':');
if (!p)
return 0;
p++;
/* Skip initial spaces */
while (*p) {
if (!isspace(*p))
break;
p++;
}
do {
ret = read_objdump_chunk(&p, &buf, &buf_len);
bytes_read += ret;
p++;
} while (ret > 0);
/* return number of successfully read bytes */
return bytes_read;
}
static int read_objdump_output(FILE *f, void *buf, size_t *len, u64 start_addr)
{
char *line = NULL;
size_t line_len, off_last = 0;
ssize_t ret;
int err = 0;
u64 addr, last_addr = start_addr;
while (off_last < *len) {
size_t off, read_bytes, written_bytes;
unsigned char tmp[BUFSZ];
ret = getline(&line, &line_len, f);
if (feof(f))
break;
if (ret < 0) {
pr_debug("getline failed\n");
err = -1;
break;
}
/* read objdump data into temporary buffer */
read_bytes = read_objdump_line(line, tmp, sizeof(tmp));
if (!read_bytes)
continue;
if (sscanf(line, "%"PRIx64, &addr) != 1)
continue;
if (addr < last_addr) {
pr_debug("addr going backwards, read beyond section?\n");
break;
}
last_addr = addr;
/* copy it from temporary buffer to 'buf' according
* to address on current objdump line */
off = addr - start_addr;
if (off >= *len)
break;
written_bytes = MIN(read_bytes, *len - off);
memcpy(buf + off, tmp, written_bytes);
off_last = off + written_bytes;
}
/* len returns number of bytes that could not be read */
*len -= off_last;
free(line);
return err;
}
static int read_via_objdump(const char *filename, u64 addr, void *buf,
size_t len)
{
char cmd[PATH_MAX * 2];
const char *fmt;
FILE *f;
int ret;
fmt = "%s -z -d --start-address=0x%"PRIx64" --stop-address=0x%"PRIx64" %s";
ret = snprintf(cmd, sizeof(cmd), fmt, "objdump", addr, addr + len,
filename);
if (ret <= 0 || (size_t)ret >= sizeof(cmd))
return -1;
pr_debug("Objdump command is: %s\n", cmd);
/* Ignore objdump errors */
strcat(cmd, " 2>/dev/null");
f = popen(cmd, "r");
if (!f) {
pr_debug("popen failed\n");
return -1;
}
ret = read_objdump_output(f, buf, &len, addr);
if (len) {
pr_debug("objdump read too few bytes: %zd\n", len);
if (!ret)
ret = len;
}
pclose(f);
return ret;
}
static void dump_buf(unsigned char *buf, size_t len)
{
size_t i;
for (i = 0; i < len; i++) {
pr_debug("0x%02x ", buf[i]);
if (i % 16 == 15)
pr_debug("\n");
}
pr_debug("\n");
}
static int read_object_code(u64 addr, size_t len, u8 cpumode,
struct thread *thread, struct state *state)
{
struct addr_location al;
unsigned char buf1[BUFSZ];
unsigned char buf2[BUFSZ];
size_t ret_len;
u64 objdump_addr;
const char *objdump_name;
char decomp_name[KMOD_DECOMP_LEN];
bool decomp = false;
int ret;
pr_debug("Reading object code for memory address: %#"PRIx64"\n", addr);
if (!thread__find_map(thread, cpumode, addr, &al) || !al.map->dso) {
if (cpumode == PERF_RECORD_MISC_HYPERVISOR) {
pr_debug("Hypervisor address can not be resolved - skipping\n");
return 0;
}
pr_debug("thread__find_map failed\n");
return -1;
}
pr_debug("File is: %s\n", al.map->dso->long_name);
if (al.map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS &&
!dso__is_kcore(al.map->dso)) {
pr_debug("Unexpected kernel address - skipping\n");
return 0;
}
pr_debug("On file address is: %#"PRIx64"\n", al.addr);
if (len > BUFSZ)
len = BUFSZ;
/* Do not go off the map */
if (addr + len > al.map->end)
len = al.map->end - addr;
/* Read the object code using perf */
ret_len = dso__data_read_offset(al.map->dso, thread->mg->machine,
al.addr, buf1, len);
if (ret_len != len) {
pr_debug("dso__data_read_offset failed\n");
return -1;
}
/*
* Converting addresses for use by objdump requires more information.
* map__load() does that. See map__rip_2objdump() for details.
*/
if (map__load(al.map))
return -1;
/* objdump struggles with kcore - try each map only once */
if (dso__is_kcore(al.map->dso)) {
size_t d;
for (d = 0; d < state->done_cnt; d++) {
if (state->done[d] == al.map->start) {
pr_debug("kcore map tested already");
pr_debug(" - skipping\n");
return 0;
}
}
if (state->done_cnt >= ARRAY_SIZE(state->done)) {
pr_debug("Too many kcore maps - skipping\n");
return 0;
}
state->done[state->done_cnt++] = al.map->start;
}
objdump_name = al.map->dso->long_name;
if (dso__needs_decompress(al.map->dso)) {
if (dso__decompress_kmodule_path(al.map->dso, objdump_name,
decomp_name,
sizeof(decomp_name)) < 0) {
pr_debug("decompression failed\n");
return -1;
}
decomp = true;
objdump_name = decomp_name;
}
/* Read the object code using objdump */
objdump_addr = map__rip_2objdump(al.map, al.addr);
ret = read_via_objdump(objdump_name, objdump_addr, buf2, len);
if (decomp)
unlink(objdump_name);
if (ret > 0) {
/*
* The kernel maps are inaccurate - assume objdump is right in
* that case.
*/
if (cpumode == PERF_RECORD_MISC_KERNEL ||
cpumode == PERF_RECORD_MISC_GUEST_KERNEL) {
len -= ret;
if (len) {
pr_debug("Reducing len to %zu\n", len);
} else if (dso__is_kcore(al.map->dso)) {
/*
* objdump cannot handle very large segments
* that may be found in kcore.
*/
pr_debug("objdump failed for kcore");
pr_debug(" - skipping\n");
return 0;
} else {
return -1;
}
}
}
if (ret < 0) {
pr_debug("read_via_objdump failed\n");
return -1;
}
/* The results should be identical */
if (memcmp(buf1, buf2, len)) {
pr_debug("Bytes read differ from those read by objdump\n");
pr_debug("buf1 (dso):\n");
dump_buf(buf1, len);
pr_debug("buf2 (objdump):\n");
dump_buf(buf2, len);
return -1;
}
pr_debug("Bytes read match those read by objdump\n");
return 0;
}
static int process_sample_event(struct machine *machine,
struct perf_evlist *evlist,
union perf_event *event, struct state *state)
{
struct perf_sample sample;
struct thread *thread;
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 06:43:22 +07:00
int ret;
if (perf_evlist__parse_sample(evlist, event, &sample)) {
pr_debug("perf_evlist__parse_sample failed\n");
return -1;
}
thread = machine__findnew_thread(machine, sample.pid, sample.tid);
if (!thread) {
pr_debug("machine__findnew_thread failed\n");
return -1;
}
ret = read_object_code(sample.ip, READLEN, sample.cpumode, thread, state);
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 06:43:22 +07:00
thread__put(thread);
return ret;
}
static int process_event(struct machine *machine, struct perf_evlist *evlist,
union perf_event *event, struct state *state)
{
if (event->header.type == PERF_RECORD_SAMPLE)
return process_sample_event(machine, evlist, event, state);
if (event->header.type == PERF_RECORD_THROTTLE ||
event->header.type == PERF_RECORD_UNTHROTTLE)
return 0;
if (event->header.type < PERF_RECORD_MAX) {
int ret;
ret = machine__process_event(machine, event, NULL);
if (ret < 0)
pr_debug("machine__process_event failed, event type %u\n",
event->header.type);
return ret;
}
return 0;
}
static int process_events(struct machine *machine, struct perf_evlist *evlist,
struct state *state)
{
union perf_event *event;
struct perf_mmap *md;
int i, ret;
for (i = 0; i < evlist->nr_mmaps; i++) {
md = &evlist->mmap[i];
if (perf_mmap__read_init(md) < 0)
continue;
while ((event = perf_mmap__read_event(md)) != NULL) {
ret = process_event(machine, evlist, event, state);
perf_mmap__consume(md);
if (ret < 0)
return ret;
}
perf_mmap__read_done(md);
}
return 0;
}
static int comp(const void *a, const void *b)
{
return *(int *)a - *(int *)b;
}
static void do_sort_something(void)
{
int buf[40960], i;
for (i = 0; i < (int)ARRAY_SIZE(buf); i++)
buf[i] = ARRAY_SIZE(buf) - i - 1;
qsort(buf, ARRAY_SIZE(buf), sizeof(int), comp);
for (i = 0; i < (int)ARRAY_SIZE(buf); i++) {
if (buf[i] != i) {
pr_debug("qsort failed\n");
break;
}
}
}
static void sort_something(void)
{
int i;
for (i = 0; i < 10; i++)
do_sort_something();
}
static void syscall_something(void)
{
int pipefd[2];
int i;
for (i = 0; i < 1000; i++) {
if (pipe(pipefd) < 0) {
pr_debug("pipe failed\n");
break;
}
close(pipefd[1]);
close(pipefd[0]);
}
}
static void fs_something(void)
{
const char *test_file_name = "temp-perf-code-reading-test-file--";
FILE *f;
int i;
for (i = 0; i < 1000; i++) {
f = fopen(test_file_name, "w+");
if (f) {
fclose(f);
unlink(test_file_name);
}
}
}
static const char *do_determine_event(bool excl_kernel)
{
const char *event = excl_kernel ? "cycles:u" : "cycles";
#ifdef __s390x__
char cpuid[128], model[16], model_c[16], cpum_cf_v[16];
unsigned int family;
int ret, cpum_cf_a;
if (get_cpuid(cpuid, sizeof(cpuid)))
goto out_clocks;
ret = sscanf(cpuid, "%*[^,],%u,%[^,],%[^,],%[^,],%x", &family, model_c,
model, cpum_cf_v, &cpum_cf_a);
if (ret != 5) /* Not available */
goto out_clocks;
if (excl_kernel && (cpum_cf_a & 4))
return event;
if (!excl_kernel && (cpum_cf_a & 2))
return event;
/* Fall through: missing authorization */
out_clocks:
event = excl_kernel ? "cpu-clock:u" : "cpu-clock";
#endif
return event;
}
static void do_something(void)
{
fs_something();
sort_something();
syscall_something();
}
enum {
TEST_CODE_READING_OK,
TEST_CODE_READING_NO_VMLINUX,
TEST_CODE_READING_NO_KCORE,
TEST_CODE_READING_NO_ACCESS,
TEST_CODE_READING_NO_KERNEL_OBJ,
};
static int do_test_code_reading(bool try_kcore)
{
struct machine *machine;
struct thread *thread;
struct record_opts opts = {
.mmap_pages = UINT_MAX,
.user_freq = UINT_MAX,
.user_interval = ULLONG_MAX,
perf test: Reduce the sample_freq for the 'object code reading' test Using 4 kHz is not necessary and sometimes is more than what was auto-tuned: # dmesg | grep max_sample_rate | tail -2 [ 2499.144373] perf interrupt took too long (2501 > 2500), lowering kernel.perf_event_max_sample_rate to 50000 [ 3592.413606] perf interrupt took too long (5069 > 5000), lowering kernel.perf_event_max_sample_rate to 25000 Simulating a auto-tune of 2000 we make the test fail, as reported by Steven Noonan for one of his machines, so reduce it to 500 HZ, it is enough to get a good number of samples for this test: # perf test -v 21 2>&1 | grep '^Reading object code for memory address' | tee /tmp/out | tail -5 Reading object code for memory address: 0x479f40 Reading object code for memory address: 0x7f29b7eea80d Reading object code for memory address: 0x7f29b7eea80d Reading object code for memory address: 0x7f29b7eea800 Reading object code for memory address: 0xffffffff813b2f23 [root@jouet ~]# wc -l /tmp/out 40 /tmp/out [root@jouet ~]# For systems that auto-tune below that, the previous patches will tell the user what is happening so that he may either ignore the result of this test or bump /proc/sys/kernel/perf_event_max_sample_rate. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Steven Noonan <steven@uplinklabs.net> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-6kufyy1iprdfzrbtuqgxir70@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-02-18 23:45:25 +07:00
.freq = 500,
.target = {
.uses_mmap = true,
},
};
struct state state = {
.done_cnt = 0,
};
struct thread_map *threads = NULL;
struct cpu_map *cpus = NULL;
struct perf_evlist *evlist = NULL;
struct perf_evsel *evsel = NULL;
int err = -1, ret;
pid_t pid;
struct map *map;
bool have_vmlinux, have_kcore, excl_kernel = false;
pid = getpid();
machine = machine__new_host();
machine->env = &perf_env;
ret = machine__create_kernel_maps(machine);
if (ret < 0) {
pr_debug("machine__create_kernel_maps failed\n");
goto out_err;
}
/* Force the use of kallsyms instead of vmlinux to try kcore */
if (try_kcore)
symbol_conf.kallsyms_name = "/proc/kallsyms";
/* Load kernel map */
map = machine__kernel_map(machine);
ret = map__load(map);
if (ret < 0) {
pr_debug("map__load failed\n");
goto out_err;
}
have_vmlinux = dso__is_vmlinux(map->dso);
have_kcore = dso__is_kcore(map->dso);
/* 2nd time through we just try kcore */
if (try_kcore && !have_kcore)
return TEST_CODE_READING_NO_KCORE;
/* No point getting kernel events if there is no kernel object */
if (!have_vmlinux && !have_kcore)
excl_kernel = true;
threads = thread_map__new_by_tid(pid);
if (!threads) {
pr_debug("thread_map__new_by_tid failed\n");
goto out_err;
}
ret = perf_event__synthesize_thread_map(NULL, threads,
perf_event__process, machine, false);
if (ret < 0) {
pr_debug("perf_event__synthesize_thread_map failed\n");
goto out_err;
}
thread = machine__findnew_thread(machine, pid, pid);
if (!thread) {
pr_debug("machine__findnew_thread failed\n");
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 06:43:22 +07:00
goto out_put;
}
cpus = cpu_map__new(NULL);
if (!cpus) {
pr_debug("cpu_map__new failed\n");
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 06:43:22 +07:00
goto out_put;
}
while (1) {
const char *str;
evlist = perf_evlist__new();
if (!evlist) {
pr_debug("perf_evlist__new failed\n");
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 06:43:22 +07:00
goto out_put;
}
perf_evlist__set_maps(evlist, cpus, threads);
str = do_determine_event(excl_kernel);
pr_debug("Parsing event '%s'\n", str);
perf tools: Add parse_events_error interface Adding support to return error information from parse_events function. Following struct will be populated by parse_events function on return: struct parse_events_error { int idx; char *str; char *help; }; where 'idx' is the position in the string where the parsing failed, 'str' contains dynamically allocated error string describing the error and 'help' is optional help string. The change contains reporting function, which currently does not display anything. The code changes to supply error data for specific event types are coming in next patches. However this is what the expected output is: $ sudo perf record -e 'sched:krava' ls event syntax error: 'sched:krava' \___ unknown tracepoint ... $ perf record -e 'cpu/even=0x1/' ls event syntax error: 'cpu/even=0x1/' \___ unknown term valid terms: pc,any,inv,edge,cmask,event,in_tx,ldlat,umask,in_tx_cp,offcore_rsp,config,config1,config2,name,period,branch_type ... $ perf record -e cycles,cache-mises ls event syntax error: '..es,cache-mises' \___ parser error ... The output functions cut the beginning of the event string so the error starts up to 10th character and cut the end of the string of it crosses the terminal width. Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1429729824-13932-2-git-send-email-jolsa@kernel.org [ Renamed 'error' variables to 'err', not to clash with util.h error() ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-23 02:10:16 +07:00
ret = parse_events(evlist, str, NULL);
if (ret < 0) {
pr_debug("parse_events failed\n");
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 06:43:22 +07:00
goto out_put;
}
perf_evlist__config(evlist, &opts, NULL);
evsel = perf_evlist__first(evlist);
evsel->attr.comm = 1;
evsel->attr.disabled = 1;
evsel->attr.enable_on_exec = 0;
ret = perf_evlist__open(evlist);
if (ret < 0) {
if (!excl_kernel) {
excl_kernel = true;
/*
* Both cpus and threads are now owned by evlist
* and will be freed by following perf_evlist__set_maps
* call. Getting refference to keep them alive.
*/
cpu_map__get(cpus);
thread_map__get(threads);
perf_evlist__set_maps(evlist, NULL, NULL);
perf_evlist__delete(evlist);
evlist = NULL;
continue;
}
if (verbose > 0) {
char errbuf[512];
perf_evlist__strerror_open(evlist, errno, errbuf, sizeof(errbuf));
pr_debug("perf_evlist__open() failed!\n%s\n", errbuf);
}
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 06:43:22 +07:00
goto out_put;
}
break;
}
ret = perf_evlist__mmap(evlist, UINT_MAX);
if (ret < 0) {
pr_debug("perf_evlist__mmap failed\n");
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 06:43:22 +07:00
goto out_put;
}
perf_evlist__enable(evlist);
do_something();
perf_evlist__disable(evlist);
ret = process_events(machine, evlist, &state);
if (ret < 0)
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 06:43:22 +07:00
goto out_put;
if (!have_vmlinux && !have_kcore && !try_kcore)
err = TEST_CODE_READING_NO_KERNEL_OBJ;
else if (!have_vmlinux && !try_kcore)
err = TEST_CODE_READING_NO_VMLINUX;
else if (excl_kernel)
err = TEST_CODE_READING_NO_ACCESS;
else
err = TEST_CODE_READING_OK;
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 06:43:22 +07:00
out_put:
thread__put(thread);
out_err:
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 06:43:22 +07:00
if (evlist) {
perf_evlist__delete(evlist);
} else {
cpu_map__put(cpus);
thread_map__put(threads);
}
machine__delete_threads(machine);
machine__delete(machine);
return err;
}
int test__code_reading(struct test *test __maybe_unused, int subtest __maybe_unused)
{
int ret;
ret = do_test_code_reading(false);
if (!ret)
ret = do_test_code_reading(true);
switch (ret) {
case TEST_CODE_READING_OK:
return 0;
case TEST_CODE_READING_NO_VMLINUX:
pr_debug("no vmlinux\n");
return 0;
case TEST_CODE_READING_NO_KCORE:
pr_debug("no kcore\n");
return 0;
case TEST_CODE_READING_NO_ACCESS:
pr_debug("no access\n");
return 0;
case TEST_CODE_READING_NO_KERNEL_OBJ:
pr_debug("no kernel obj\n");
return 0;
default:
return -1;
};
}